Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - i915 has seen a lot of refactoring and uAPI cleanups due to a
     change in the upstream direction going forward

     This has all been audited with known userspace, but there may be
     some pitfalls that were missed.

   - i915 now uses common TTM to enable discrete memory on DG1/2 GPUs

   - i915 enables Jasper and Elkhart Lake by default and has preliminary
     XeHP/DG2 support

   - amdgpu adds support for Cyan Skillfish

   - lots of implicit fencing rules documented and fixed up in drivers

   - msm now uses the core scheduler

   - the irq midlayer has been removed for non-legacy drivers

   - the sysfb code now works on more than x86.

  Otherwise the usual smattering of stuff everywhere, panels, bridges,
  refactorings.

  Detailed summary:

  core:
   - extract i915 eDP backlight into core
   - DP aux bus support
   - drm_device.irq_enabled removed
   - port drivers to native irq interfaces
   - export gem shadow plane handling for vgem
   - print proper driver name in framebuffer registration
   - driver fixes for implicit fencing rules
   - ARM fixed rate compression modifier added
   - updated fb damage handling
   - rmfb ioctl logging/docs
   - drop drm_gem_object_put_locked
   - define DRM_FORMAT_MAX_PLANES
   - add gem fb vmap/vunmap helpers
   - add lockdep_assert(once) helpers
   - mark drm irq midlayer as legacy
   - use offset adjusted bo mapping conversion

  vgaarb:
   - cleanups

  fbdev:
   - extend efifb handling to all arches
   - div by 0 fixes for multiple drivers

  udmabuf:
   - add hugepage mapping support

  dma-buf:
   - non-dynamic exporter fixups
   - document implicit fencing rules

  amdgpu:
   - Initial Cyan Skillfish support
   - switch virtual DCE over to vkms based atomic
   - VCN/JPEG power down fixes
   - NAVI PCIE link handling fixes
   - AMD HDMI freesync fixes
   - Yellow Carp + Beige Goby fixes
   - Clockgating/S0ix/SMU/EEPROM fixes
   - embed hw fence in job
   - rework dma-resv handling
   - ensure eviction to system ram

  amdkfd:
   - uapi: SVM address range query added
   - sysfs leak fix
   - GPUVM TLB optimizations
   - vmfault/migration counters

  i915:
   - Enable JSL and EHL by default
   - preliminary XeHP/DG2 support
   - remove all CNL support (never shipped)
   - move to TTM for discrete memory support
   - allow mixed object mmap handling
   - GEM uAPI spring cleaning
       - add I915_MMAP_OBJECT_FIXED
       - reinstate ADL-P mmap ioctls
       - drop a bunch of unused by userspace features
       - disable and remove GPU relocations
   - revert some i915 misfeatures
   - major refactoring of GuC for Gen11+
   - execbuffer object locking separate step
   - reject caching/set-domain on discrete
   - Enable pipe DMC loading on XE-LPD and ADL-P
   - add PSF GV point support
   - Refactor and fix DDI buffer translations
   - Clean up FBC CFB allocation code
   - Finish INTEL_GEN() and friends macro conversions

  nouveau:
   - add eDP backlight support
   - implicit fence fix

  msm:
   - a680/7c3 support
   - drm/scheduler conversion

  panfrost:
   - rework GPU reset

  virtio:
   - fix fencing for planes

  ast:
   - add detect support

  bochs:
   - move to tiny GPU driver

  vc4:
   - use hotplug irqs
   - HDMI codec support

  vmwgfx:
   - use internal vmware device headers

  ingenic:
   - demidlayering irq

  rcar-du:
   - shutdown fixes
   - convert to bridge connector helpers

  zynqmp-dsub:
   - misc fixes

  mgag200:
   - convert PLL handling to atomic

  mediatek:
   - MT8133 AAL support
   - gem mmap object support
   - MT8167 support

  etnaviv:
   - NXP Layerscape LS1028A SoC support
   - GEM mmap cleanups

  tegra:
   - new user API

  exynos:
   - missing unlock fix
   - build warning fix
   - use refcount_t"

* tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits)
  drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box
  drm/amd/display: Remove duplicate dml init
  drm/amd/display: Update bounding box states (v2)
  drm/amd/display: Update number of DCN3 clock states
  drm/amdgpu: disable GFX CGCG in aldebaran
  drm/amdgpu: Clear RAS interrupt status on aldebaran
  drm/amdgpu: Add support for RAS XGMI err query
  drm/amdkfd: Account for SH/SE count when setting up cu masks.
  drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain
  drm/amdgpu: drop redundant cancel_delayed_work_sync call
  drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend
  drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend
  drm/amdkfd: map SVM range with correct access permission
  drm/amdkfd: check access permisson to restore retry fault
  drm/amdgpu: Update RAS XGMI Error Query
  drm/amdgpu: Add driver infrastructure for MCA RAS
  drm/amd/display: Add Logging for HDMI color depth information
  drm/amd/amdgpu: consolidate PSP TA init shared buf functions
  drm/amd/amdgpu: add name field back to ras_common_if
  drm/amdgpu: Fix build with missing pm_suspend_target_state module export
  ...

1042 files changed, 59765 insertions, 34587 deletions

diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index 4e16c71c24b7..9561e3d2d428 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -72,6 +72,17 @@ menuconfig DMABUF_HEAPS
 	  allows userspace to allocate dma-bufs that can be shared
 	  between drivers.
 
+menuconfig DMABUF_SYSFS_STATS
+	bool "DMA-BUF sysfs statistics"
+	select DMA_SHARED_BUFFER
+	help
+	   Choose this option to enable DMA-BUF sysfs statistics
+	   in location /sys/kernel/dmabuf/buffers.
+
+	   /sys/kernel/dmabuf/buffers/<inode_number> will contain
+	   statistics for the DMA-BUF with the unique inode number
+	   <inode_number>.
+
 source "drivers/dma-buf/heaps/Kconfig"
 
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 995e05f609ff..40d81f23cacf 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
+obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o
 
 dmabuf_selftests-y := \
 	selftest.o \
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c
new file mode 100644
index 000000000000..053baadcada9
--- /dev/null
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DMA-BUF sysfs statistics.
+ *
+ * Copyright (C) 2021 Google LLC.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
+#include <linux/kobject.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#include "dma-buf-sysfs-stats.h"
+
+#define to_dma_buf_entry_from_kobj(x) container_of(x, struct dma_buf_sysfs_entry, kobj)
+
+/**
+ * DOC: overview
+ *
+ * ``/sys/kernel/debug/dma_buf/bufinfo`` provides an overview of every DMA-BUF
+ * in the system. However, since debugfs is not safe to be mounted in
+ * production, procfs and sysfs can be used to gather DMA-BUF statistics on
+ * production systems.
+ *
+ * The ``/proc/<pid>/fdinfo/<fd>`` files in procfs can be used to gather
+ * information about DMA-BUF fds. Detailed documentation about the interface
+ * is present in Documentation/filesystems/proc.rst.
+ *
+ * Unfortunately, the existing procfs interfaces can only provide information
+ * about the DMA-BUFs for which processes hold fds or have the buffers mmapped
+ * into their address space. This necessitated the creation of the DMA-BUF sysfs
+ * statistics interface to provide per-buffer information on production systems.
+ *
+ * The interface at ``/sys/kernel/dma-buf/buffers`` exposes information about
+ * every DMA-BUF when ``CONFIG_DMABUF_SYSFS_STATS`` is enabled.
+ *
+ * The following stats are exposed by the interface:
+ *
+ * * ``/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name``
+ * * ``/sys/kernel/dmabuf/buffers/<inode_number>/size``
+ *
+ * The information in the interface can also be used to derive per-exporter
+ * statistics. The data from the interface can be gathered on error conditions
+ * or other important events to provide a snapshot of DMA-BUF usage.
+ * It can also be collected periodically by telemetry to monitor various metrics.
+ *
+ * Detailed documentation about the interface is present in
+ * Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers.
+ */
+
+struct dma_buf_stats_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct dma_buf *dmabuf,
+			struct dma_buf_stats_attribute *attr, char *buf);
+};
+#define to_dma_buf_stats_attr(x) container_of(x, struct dma_buf_stats_attribute, attr)
+
+static ssize_t dma_buf_stats_attribute_show(struct kobject *kobj,
+					    struct attribute *attr,
+					    char *buf)
+{
+	struct dma_buf_stats_attribute *attribute;
+	struct dma_buf_sysfs_entry *sysfs_entry;
+	struct dma_buf *dmabuf;
+
+	attribute = to_dma_buf_stats_attr(attr);
+	sysfs_entry = to_dma_buf_entry_from_kobj(kobj);
+	dmabuf = sysfs_entry->dmabuf;
+
+	if (!dmabuf || !attribute->show)
+		return -EIO;
+
+	return attribute->show(dmabuf, attribute, buf);
+}
+
+static const struct sysfs_ops dma_buf_stats_sysfs_ops = {
+	.show = dma_buf_stats_attribute_show,
+};
+
+static ssize_t exporter_name_show(struct dma_buf *dmabuf,
+				  struct dma_buf_stats_attribute *attr,
+				  char *buf)
+{
+	return sysfs_emit(buf, "%s\n", dmabuf->exp_name);
+}
+
+static ssize_t size_show(struct dma_buf *dmabuf,
+			 struct dma_buf_stats_attribute *attr,
+			 char *buf)
+{
+	return sysfs_emit(buf, "%zu\n", dmabuf->size);
+}
+
+static struct dma_buf_stats_attribute exporter_name_attribute =
+	__ATTR_RO(exporter_name);
+static struct dma_buf_stats_attribute size_attribute = __ATTR_RO(size);
+
+static struct attribute *dma_buf_stats_default_attrs[] = {
+	&exporter_name_attribute.attr,
+	&size_attribute.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(dma_buf_stats_default);
+
+static void dma_buf_sysfs_release(struct kobject *kobj)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+
+	sysfs_entry = to_dma_buf_entry_from_kobj(kobj);
+	kfree(sysfs_entry);
+}
+
+static struct kobj_type dma_buf_ktype = {
+	.sysfs_ops = &dma_buf_stats_sysfs_ops,
+	.release = dma_buf_sysfs_release,
+	.default_groups = dma_buf_stats_default_groups,
+};
+
+void dma_buf_stats_teardown(struct dma_buf *dmabuf)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+
+	sysfs_entry = dmabuf->sysfs_entry;
+	if (!sysfs_entry)
+		return;
+
+	kobject_del(&sysfs_entry->kobj);
+	kobject_put(&sysfs_entry->kobj);
+}
+
+
+/* Statistics files do not need to send uevents. */
+static int dmabuf_sysfs_uevent_filter(struct kset *kset, struct kobject *kobj)
+{
+	return 0;
+}
+
+static const struct kset_uevent_ops dmabuf_sysfs_no_uevent_ops = {
+	.filter = dmabuf_sysfs_uevent_filter,
+};
+
+static struct kset *dma_buf_stats_kset;
+static struct kset *dma_buf_per_buffer_stats_kset;
+int dma_buf_init_sysfs_statistics(void)
+{
+	dma_buf_stats_kset = kset_create_and_add("dmabuf",
+						 &dmabuf_sysfs_no_uevent_ops,
+						 kernel_kobj);
+	if (!dma_buf_stats_kset)
+		return -ENOMEM;
+
+	dma_buf_per_buffer_stats_kset = kset_create_and_add("buffers",
+							    &dmabuf_sysfs_no_uevent_ops,
+							    &dma_buf_stats_kset->kobj);
+	if (!dma_buf_per_buffer_stats_kset) {
+		kset_unregister(dma_buf_stats_kset);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void dma_buf_uninit_sysfs_statistics(void)
+{
+	kset_unregister(dma_buf_per_buffer_stats_kset);
+	kset_unregister(dma_buf_stats_kset);
+}
+
+int dma_buf_stats_setup(struct dma_buf *dmabuf)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+	int ret;
+
+	if (!dmabuf || !dmabuf->file)
+		return -EINVAL;
+
+	if (!dmabuf->exp_name) {
+		pr_err("exporter name must not be empty if stats needed\n");
+		return -EINVAL;
+	}
+
+	sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
+	if (!sysfs_entry)
+		return -ENOMEM;
+
+	sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
+	sysfs_entry->dmabuf = dmabuf;
+
+	dmabuf->sysfs_entry = sysfs_entry;
+
+	/* create the directory for buffer stats */
+	ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
+				   "%lu", file_inode(dmabuf->file)->i_ino);
+	if (ret)
+		goto err_sysfs_dmabuf;
+
+	return 0;
+
+err_sysfs_dmabuf:
+	kobject_put(&sysfs_entry->kobj);
+	dmabuf->sysfs_entry = NULL;
+	return ret;
+}
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h
new file mode 100644
index 000000000000..a49c6e2650cc
--- /dev/null
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * DMA-BUF sysfs statistics.
+ *
+ * Copyright (C) 2021 Google LLC.
+ */
+
+#ifndef _DMA_BUF_SYSFS_STATS_H
+#define _DMA_BUF_SYSFS_STATS_H
+
+#ifdef CONFIG_DMABUF_SYSFS_STATS
+
+int dma_buf_init_sysfs_statistics(void);
+void dma_buf_uninit_sysfs_statistics(void);
+
+int dma_buf_stats_setup(struct dma_buf *dmabuf);
+
+void dma_buf_stats_teardown(struct dma_buf *dmabuf);
+#else
+
+static inline int dma_buf_init_sysfs_statistics(void)
+{
+	return 0;
+}
+
+static inline void dma_buf_uninit_sysfs_statistics(void) {}
+
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+{
+	return 0;
+}
+
+static inline void dma_buf_stats_teardown(struct dma_buf *dmabuf) {}
+#endif
+#endif // _DMA_BUF_SYSFS_STATS_H
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 511fe0d217a0..63d32261b63f 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -29,6 +29,8 @@
 #include <uapi/linux/dma-buf.h>
 #include <uapi/linux/magic.h>
 
+#include "dma-buf-sysfs-stats.h"
+
 static inline int is_dma_buf_file(struct file *);
 
 struct dma_buf_list {
@@ -74,6 +76,7 @@ static void dma_buf_release(struct dentry *dentry)
 	 */
 	BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active);
 
+	dma_buf_stats_teardown(dmabuf);
 	dmabuf->ops->release(dmabuf);
 
 	if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
@@ -580,6 +583,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	file->f_mode |= FMODE_LSEEK;
 	dmabuf->file = file;
 
+	ret = dma_buf_stats_setup(dmabuf);
+	if (ret)
+		goto err_sysfs;
+
 	mutex_init(&dmabuf->lock);
 	INIT_LIST_HEAD(&dmabuf->attachments);
 
@@ -589,6 +596,14 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 
 	return dmabuf;
 
+err_sysfs:
+	/*
+	 * Set file->f_path.dentry->d_fsdata to NULL so that when
+	 * dma_buf_release() gets invoked by dentry_ops, it exits
+	 * early before calling the release() dma_buf op.
+	 */
+	file->f_path.dentry->d_fsdata = NULL;
+	fput(file);
 err_dmabuf:
 	kfree(dmabuf);
 err_module:
@@ -926,6 +941,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unpin);
  * the underlying backing storage is pinned for as long as a mapping exists,
  * therefore users/importers should not hold onto a mapping for undue amounts of
  * time.
+ *
+ * Important: Dynamic importers must wait for the exclusive fence of the struct
+ * dma_resv attached to the DMA-BUF first.
  */
 struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 					enum dma_data_direction direction)
@@ -992,7 +1010,6 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		}
 	}
 #endif /* CONFIG_DMA_API_DEBUG */
-
 	return sg_table;
 }
 EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
@@ -1469,6 +1486,12 @@ static inline void dma_buf_uninit_debugfs(void)
 
 static int __init dma_buf_init(void)
 {
+	int ret;
+
+	ret = dma_buf_init_sysfs_statistics();
+	if (ret)
+		return ret;
+
 	dma_buf_mnt = kern_mount(&dma_buf_fs_type);
 	if (IS_ERR(dma_buf_mnt))
 		return PTR_ERR(dma_buf_mnt);
@@ -1484,5 +1507,6 @@ static void __exit dma_buf_deinit(void)
 {
 	dma_buf_uninit_debugfs();
 	kern_unmount(dma_buf_mnt);
+	dma_buf_uninit_sysfs_statistics();
 }
 __exitcall(dma_buf_deinit);
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
index 7d129e68ac70..1b4cb3e5cec9 100644
--- a/drivers/dma-buf/dma-fence-chain.c
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -137,6 +137,7 @@ static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
 	struct dma_fence_chain *chain;
 
 	chain = container_of(cb, typeof(*chain), cb);
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
 	irq_work_queue(&chain->work);
 	dma_fence_put(f);
 }
@@ -239,7 +240,6 @@ void dma_fence_chain_init(struct dma_fence_chain *chain,
 	rcu_assign_pointer(chain->prev, prev);
 	chain->fence = fence;
 	chain->prev_seqno = 0;
-	init_irq_work(&chain->work, dma_fence_chain_irq_work);
 
 	/* Try to reuse the context of the previous chain node. */
 	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno, prev->ops)) {
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index f26c71747d43..e744fd87c63c 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -615,25 +615,21 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence)
  */
 bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all)
 {
-	unsigned int seq, shared_count;
+	struct dma_fence *fence;
+	unsigned int seq;
 	int ret;
 
 	rcu_read_lock();
 retry:
 	ret = true;
-	shared_count = 0;
 	seq = read_seqcount_begin(&obj->seq);
 
 	if (test_all) {
 		struct dma_resv_list *fobj = dma_resv_shared_list(obj);
-		unsigned int i;
-
-		if (fobj)
-			shared_count = fobj->shared_count;
+		unsigned int i, shared_count;
 
+		shared_count = fobj ? fobj->shared_count : 0;
 		for (i = 0; i < shared_count; ++i) {
-			struct dma_fence *fence;
-
 			fence = rcu_dereference(fobj->shared[i]);
 			ret = dma_resv_test_signaled_single(fence);
 			if (ret < 0)
@@ -641,24 +637,19 @@ retry:
 			else if (!ret)
 				break;
 		}
-
-		if (read_seqcount_retry(&obj->seq, seq))
-			goto retry;
 	}
 
-	if (!shared_count) {
-		struct dma_fence *fence_excl = dma_resv_excl_fence(obj);
-
-		if (fence_excl) {
-			ret = dma_resv_test_signaled_single(fence_excl);
-			if (ret < 0)
-				goto retry;
+	fence = dma_resv_excl_fence(obj);
+	if (ret && fence) {
+		ret = dma_resv_test_signaled_single(fence);
+		if (ret < 0)
+			goto retry;
 
-			if (read_seqcount_retry(&obj->seq, seq))
-				goto retry;
-		}
 	}
 
+	if (read_seqcount_retry(&obj->seq, seq))
+		goto retry;
+
 	rcu_read_unlock();
 	return ret;
 }
diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c
index 9525f7f56119..8ce1ea59d31b 100644
--- a/drivers/dma-buf/st-dma-fence-chain.c
+++ b/drivers/dma-buf/st-dma-fence-chain.c
@@ -58,28 +58,20 @@ static struct dma_fence *mock_fence(void)
 	return &f->base;
 }
 
-static inline struct mock_chain {
-	struct dma_fence_chain base;
-} *to_mock_chain(struct dma_fence *f) {
-	return container_of(f, struct mock_chain, base.base);
-}
-
 static struct dma_fence *mock_chain(struct dma_fence *prev,
 				    struct dma_fence *fence,
 				    u64 seqno)
 {
-	struct mock_chain *f;
+	struct dma_fence_chain *f;
 
-	f = kmalloc(sizeof(*f), GFP_KERNEL);
+	f = dma_fence_chain_alloc();
 	if (!f)
 		return NULL;
 
-	dma_fence_chain_init(&f->base,
-			     dma_fence_get(prev),
-			     dma_fence_get(fence),
+	dma_fence_chain_init(f, dma_fence_get(prev), dma_fence_get(fence),
 			     seqno);
 
-	return &f->base.base;
+	return &f->base;
 }
 
 static int sanitycheck(void *arg)
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index db732f71e59a..c57a609db75b 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -11,9 +11,15 @@
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/udmabuf.h>
+#include <linux/hugetlb.h>
 
-static const u32    list_limit = 1024;  /* udmabuf_create_list->count limit */
-static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes  */
+static int list_limit = 1024;
+module_param(list_limit, int, 0644);
+MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024.");
+
+static int size_limit_mb = 64;
+module_param(size_limit_mb, int, 0644);
+MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64.");
 
 struct udmabuf {
 	pgoff_t pagecount;
@@ -160,10 +166,13 @@ static long udmabuf_create(struct miscdevice *device,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
+	struct address_space *mapping = NULL;
 	struct udmabuf *ubuf;
 	struct dma_buf *buf;
 	pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
-	struct page *page;
+	struct page *page, *hpage = NULL;
+	pgoff_t subpgoff, maxsubpgs;
+	struct hstate *hpstate;
 	int seals, ret = -EINVAL;
 	u32 i, flags;
 
@@ -194,7 +203,8 @@ static long udmabuf_create(struct miscdevice *device,
 		memfd = fget(list[i].memfd);
 		if (!memfd)
 			goto err;
-		if (!shmem_mapping(file_inode(memfd)->i_mapping))
+		mapping = file_inode(memfd)->i_mapping;
+		if (!shmem_mapping(mapping) && !is_file_hugepages(memfd))
 			goto err;
 		seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
 		if (seals == -EINVAL)
@@ -205,17 +215,48 @@ static long udmabuf_create(struct miscdevice *device,
 			goto err;
 		pgoff = list[i].offset >> PAGE_SHIFT;
 		pgcnt = list[i].size   >> PAGE_SHIFT;
+		if (is_file_hugepages(memfd)) {
+			hpstate = hstate_file(memfd);
+			pgoff = list[i].offset >> huge_page_shift(hpstate);
+			subpgoff = (list[i].offset &
+				    ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
+			maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
+		}
 		for (pgidx = 0; pgidx < pgcnt; pgidx++) {
-			page = shmem_read_mapping_page(
-				file_inode(memfd)->i_mapping, pgoff + pgidx);
-			if (IS_ERR(page)) {
-				ret = PTR_ERR(page);
-				goto err;
+			if (is_file_hugepages(memfd)) {
+				if (!hpage) {
+					hpage = find_get_page_flags(mapping, pgoff,
+								    FGP_ACCESSED);
+					if (!hpage) {
+						ret = -EINVAL;
+						goto err;
+					}
+				}
+				page = hpage + subpgoff;
+				get_page(page);
+				subpgoff++;
+				if (subpgoff == maxsubpgs) {
+					put_page(hpage);
+					hpage = NULL;
+					subpgoff = 0;
+					pgoff++;
+				}
+			} else {
+				page = shmem_read_mapping_page(mapping,
+							       pgoff + pgidx);
+				if (IS_ERR(page)) {
+					ret = PTR_ERR(page);
+					goto err;
+				}
 			}
 			ubuf->pages[pgbuf++] = page;
 		}
 		fput(memfd);
 		memfd = NULL;
+		if (hpage) {
+			put_page(hpage);
+			hpage = NULL;
+		}
 	}
 
 	exp_info.ops  = &udmabuf_ops;
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 1db738d5b301..5d3fd803d2bb 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -251,6 +251,38 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT
 
 	  Say Y here to enable "download mode" by default.
 
+config SYSFB
+	bool
+	default y
+	depends on X86 || EFI
+
+config SYSFB_SIMPLEFB
+	bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
+	depends on SYSFB
+	help
+	  Firmwares often provide initial graphics framebuffers so the BIOS,
+	  bootloader or kernel can show basic video-output during boot for
+	  user-guidance and debugging. Historically, x86 used the VESA BIOS
+	  Extensions and EFI-framebuffers for this, which are mostly limited
+	  to x86 BIOS or EFI systems.
+	  This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
+	  framebuffers so the new generic system-framebuffer drivers can be
+	  used instead. If the framebuffer is not compatible with the generic
+	  modes, it is advertised as fallback platform framebuffer so legacy
+	  drivers like efifb, vesafb and uvesafb can pick it up.
+	  If this option is not selected, all system framebuffers are always
+	  marked as fallback platform framebuffers as usual.
+
+	  Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
+	  not be able to pick up generic system framebuffers if this option
+	  is selected. You are highly encouraged to enable simplefb as
+	  replacement if you select this option. simplefb can correctly deal
+	  with generic system framebuffers. But you should still keep vesafb
+	  and others enabled as fallback if a system framebuffer is
+	  incompatible with simplefb.
+
+	  If unsure, say Y.
+
 config TI_SCI_PROTOCOL
 	tristate "TI System Control Interface (TISCI) Message Protocol"
 	depends on TI_MESSAGE_MANAGER
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 546ac8e7f6d0..705fabe88156 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -18,6 +18,8 @@ obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_RASPBERRYPI_FIRMWARE) += raspberrypi.o
 obj-$(CONFIG_FW_CFG_SYSFS)	+= qemu_fw_cfg.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom_scm.o qcom_scm-smc.o qcom_scm-legacy.o
+obj-$(CONFIG_SYSFB)		+= sysfb.o
+obj-$(CONFIG_SYSFB_SIMPLEFB)	+= sysfb_simplefb.o
 obj-$(CONFIG_TI_SCI_PROTOCOL)	+= ti_sci.o
 obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
 obj-$(CONFIG_TURRIS_MOX_RWTM)	+= turris-mox-rwtm.o
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 467e94259679..c02ff25dd477 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -36,6 +36,8 @@ obj-$(CONFIG_LOAD_UEFI_KEYS)		+= mokvar-table.o
 fake_map-y				+= fake_mem.o
 fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
 
+obj-$(CONFIG_SYSFB)			+= sysfb_efi.o
+
 arm-obj-$(CONFIG_EFI)			:= efi-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index a552a08a1741..b19ce1a83f91 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -275,93 +275,3 @@ void __init efi_init(void)
 	}
 #endif
 }
-
-static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
-{
-	u64 fb_base = screen_info.lfb_base;
-
-	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
-		fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32;
-
-	return fb_base >= range->cpu_addr &&
-	       fb_base < (range->cpu_addr + range->size);
-}
-
-static struct device_node *find_pci_overlap_node(void)
-{
-	struct device_node *np;
-
-	for_each_node_by_type(np, "pci") {
-		struct of_pci_range_parser parser;
-		struct of_pci_range range;
-		int err;
-
-		err = of_pci_range_parser_init(&parser, np);
-		if (err) {
-			pr_warn("of_pci_range_parser_init() failed: %d\n", err);
-			continue;
-		}
-
-		for_each_of_pci_range(&parser, &range)
-			if (efifb_overlaps_pci_range(&range))
-				return np;
-	}
-	return NULL;
-}
-
-/*
- * If the efifb framebuffer is backed by a PCI graphics controller, we have
- * to ensure that this relation is expressed using a device link when
- * running in DT mode, or the probe order may be reversed, resulting in a
- * resource reservation conflict on the memory window that the efifb
- * framebuffer steals from the PCIe host bridge.
- */
-static int efifb_add_links(struct fwnode_handle *fwnode)
-{
-	struct device_node *sup_np;
-
-	sup_np = find_pci_overlap_node();
-
-	/*
-	 * If there's no PCI graphics controller backing the efifb, we are
-	 * done here.
-	 */
-	if (!sup_np)
-		return 0;
-
-	fwnode_link_add(fwnode, of_fwnode_handle(sup_np));
-	of_node_put(sup_np);
-
-	return 0;
-}
-
-static const struct fwnode_operations efifb_fwnode_ops = {
-	.add_links = efifb_add_links,
-};
-
-static struct fwnode_handle efifb_fwnode;
-
-static int __init register_gop_device(void)
-{
-	struct platform_device *pd;
-	int err;
-
-	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
-		return 0;
-
-	pd = platform_device_alloc("efi-framebuffer", 0);
-	if (!pd)
-		return -ENOMEM;
-
-	if (IS_ENABLED(CONFIG_PCI)) {
-		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
-		pd->dev.fwnode = &efifb_fwnode;
-	}
-
-	err = platform_device_add_data(pd, &screen_info, sizeof(screen_info));
-	if (err)
-		return err;
-
-	return platform_device_add(pd);
-}
-subsys_initcall(register_gop_device);
diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c
new file mode 100644
index 000000000000..4c7c9dd7733f
--- /dev/null
+++ b/drivers/firmware/efi/sysfb_efi.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic System Framebuffers
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com>
+ */
+
+/*
+ * EFI Quirks
+ * Several EFI systems do not correctly advertise their boot framebuffers.
+ * Hence, we use this static table of known broken machines and fix up the
+ * information so framebuffer drivers can load correctly.
+ */
+
+#include <linux/dmi.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of_address.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <linux/sysfb.h>
+#include <video/vga.h>
+
+#include <asm/efi.h>
+
+enum {
+	OVERRIDE_NONE = 0x0,
+	OVERRIDE_BASE = 0x1,
+	OVERRIDE_STRIDE = 0x2,
+	OVERRIDE_HEIGHT = 0x4,
+	OVERRIDE_WIDTH = 0x8,
+};
+
+struct efifb_dmi_info efifb_dmi_list[] = {
+	[M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */
+	[M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE },
+	[M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */
+	[M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE },
+	[M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE },
+	[M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE },
+	[M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE },
+	[M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	/* 11" Macbook Air 3,1 passes the wrong stride */
+	[M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE },
+	[M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */
+	[M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE },
+	[M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE }
+};
+
+void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
+{
+	int i;
+
+	for (i = 0; i < M_UNKNOWN; i++) {
+		if (efifb_dmi_list[i].base != 0 &&
+		    !strcmp(opt, efifb_dmi_list[i].optname)) {
+			si->lfb_base = efifb_dmi_list[i].base;
+			si->lfb_linelength = efifb_dmi_list[i].stride;
+			si->lfb_width = efifb_dmi_list[i].width;
+			si->lfb_height = efifb_dmi_list[i].height;
+		}
+	}
+}
+
+#define choose_value(dmivalue, fwvalue, field, flags) ({	\
+		typeof(fwvalue) _ret_ = fwvalue;		\
+		if ((flags) & (field))				\
+			_ret_ = dmivalue;			\
+		else if ((fwvalue) == 0)			\
+			_ret_ = dmivalue;			\
+		_ret_;						\
+	})
+
+static int __init efifb_set_system(const struct dmi_system_id *id)
+{
+	struct efifb_dmi_info *info = id->driver_data;
+
+	if (info->base == 0 && info->height == 0 && info->width == 0 &&
+	    info->stride == 0)
+		return 0;
+
+	/* Trust the bootloader over the DMI tables */
+	if (screen_info.lfb_base == 0) {
+#if defined(CONFIG_PCI)
+		struct pci_dev *dev = NULL;
+		int found_bar = 0;
+#endif
+		if (info->base) {
+			screen_info.lfb_base = choose_value(info->base,
+				screen_info.lfb_base, OVERRIDE_BASE,
+				info->flags);
+
+#if defined(CONFIG_PCI)
+			/* make sure that the address in the table is actually
+			 * on a VGA device's PCI BAR */
+
+			for_each_pci_dev(dev) {
+				int i;
+				if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
+					continue;
+				for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+					resource_size_t start, end;
+					unsigned long flags;
+
+					flags = pci_resource_flags(dev, i);
+					if (!(flags & IORESOURCE_MEM))
+						continue;
+
+					if (flags & IORESOURCE_UNSET)
+						continue;
+
+					if (pci_resource_len(dev, i) == 0)
+						continue;
+
+					start = pci_resource_start(dev, i);
+					end = pci_resource_end(dev, i);
+					if (screen_info.lfb_base >= start &&
+					    screen_info.lfb_base < end) {
+						found_bar = 1;
+						break;
+					}
+				}
+			}
+			if (!found_bar)
+				screen_info.lfb_base = 0;
+#endif
+		}
+	}
+	if (screen_info.lfb_base) {
+		screen_info.lfb_linelength = choose_value(info->stride,
+			screen_info.lfb_linelength, OVERRIDE_STRIDE,
+			info->flags);
+		screen_info.lfb_width = choose_value(info->width,
+			screen_info.lfb_width, OVERRIDE_WIDTH,
+			info->flags);
+		screen_info.lfb_height = choose_value(info->height,
+			screen_info.lfb_height, OVERRIDE_HEIGHT,
+			info->flags);
+		if (screen_info.orig_video_isVGA == 0)
+			screen_info.orig_video_isVGA = VIDEO_TYPE_EFI;
+	} else {
+		screen_info.lfb_linelength = 0;
+		screen_info.lfb_width = 0;
+		screen_info.lfb_height = 0;
+		screen_info.orig_video_isVGA = 0;
+		return 0;
+	}
+
+	printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x "
+			 "(%dx%d, stride %d)\n", id->ident,
+			 screen_info.lfb_base, screen_info.lfb_width,
+			 screen_info.lfb_height, screen_info.lfb_linelength);
+
+	return 1;
+}
+
+#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid)		\
+	{							\
+		efifb_set_system,				\
+		name,						\
+		{						\
+			DMI_MATCH(DMI_BIOS_VENDOR, vendor),	\
+			DMI_MATCH(DMI_PRODUCT_NAME, name)	\
+		},						\
+		&efifb_dmi_list[enumid]				\
+	}
+
+static const struct dmi_system_id efifb_dmi_system_table[] __initconst = {
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2),
+	{},
+};
+
+/*
+ * Some devices have a portrait LCD but advertise a landscape resolution (and
+ * pitch). We simply swap width and height for these devices so that we can
+ * correctly deal with some of them coming with multiple resolutions.
+ */
+static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
+	{
+		/*
+		 * Lenovo MIIX310-10ICR, only some batches have the troublesome
+		 * 800x1280 portrait screen. Luckily the portrait version has
+		 * its own BIOS version, so we match on that.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"),
+		},
+	},
+	{
+		/* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"Lenovo MIIX 320-10ICR"),
+		},
+	},
+	{
+		/* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"Lenovo ideapad D330-10IGM"),
+		},
+	},
+	{},
+};
+
+static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
+{
+	u64 fb_base = screen_info.lfb_base;
+
+	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32;
+
+	return fb_base >= range->cpu_addr &&
+	       fb_base < (range->cpu_addr + range->size);
+}
+
+static struct device_node *find_pci_overlap_node(void)
+{
+	struct device_node *np;
+
+	for_each_node_by_type(np, "pci") {
+		struct of_pci_range_parser parser;
+		struct of_pci_range range;
+		int err;
+
+		err = of_pci_range_parser_init(&parser, np);
+		if (err) {
+			pr_warn("of_pci_range_parser_init() failed: %d\n", err);
+			continue;
+		}
+
+		for_each_of_pci_range(&parser, &range)
+			if (efifb_overlaps_pci_range(&range))
+				return np;
+	}
+	return NULL;
+}
+
+/*
+ * If the efifb framebuffer is backed by a PCI graphics controller, we have
+ * to ensure that this relation is expressed using a device link when
+ * running in DT mode, or the probe order may be reversed, resulting in a
+ * resource reservation conflict on the memory window that the efifb
+ * framebuffer steals from the PCIe host bridge.
+ */
+static int efifb_add_links(struct fwnode_handle *fwnode)
+{
+	struct device_node *sup_np;
+
+	sup_np = find_pci_overlap_node();
+
+	/*
+	 * If there's no PCI graphics controller backing the efifb, we are
+	 * done here.
+	 */
+	if (!sup_np)
+		return 0;
+
+	fwnode_link_add(fwnode, of_fwnode_handle(sup_np));
+	of_node_put(sup_np);
+
+	return 0;
+}
+
+static const struct fwnode_operations efifb_fwnode_ops = {
+	.add_links = efifb_add_links,
+};
+
+#ifdef CONFIG_EFI
+static struct fwnode_handle efifb_fwnode;
+
+__init void sysfb_apply_efi_quirks(struct platform_device *pd)
+{
+	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
+	    !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
+		dmi_check_system(efifb_dmi_system_table);
+
+	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI &&
+	    dmi_check_system(efifb_dmi_swap_width_height)) {
+		u16 temp = screen_info.lfb_width;
+
+		screen_info.lfb_width = screen_info.lfb_height;
+		screen_info.lfb_height = temp;
+		screen_info.lfb_linelength = 4 * screen_info.lfb_width;
+	}
+
+	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && IS_ENABLED(CONFIG_PCI)) {
+		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
+		pd->dev.fwnode = &efifb_fwnode;
+	}
+}
+#endif
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
new file mode 100644
index 000000000000..2bfbb05f7d89
--- /dev/null
+++ b/drivers/firmware/sysfb.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic System Framebuffers
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ */
+
+/*
+ * Simple-Framebuffer support
+ * Create a platform-device for any available boot framebuffer. The
+ * simple-framebuffer platform device is already available on DT systems, so
+ * this module parses the global "screen_info" object and creates a suitable
+ * platform device compatible with the "simple-framebuffer" DT object. If
+ * the framebuffer is incompatible, we instead create a legacy
+ * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and
+ * pass the screen_info as platform_data. This allows legacy drivers
+ * to pick these devices up without messing with simple-framebuffer drivers.
+ * The global "screen_info" is still valid at all times.
+ *
+ * If CONFIG_SYSFB_SIMPLEFB is not selected, never register "simple-framebuffer"
+ * platform devices, but only use legacy framebuffer devices for
+ * backwards compatibility.
+ *
+ * TODO: We set the dev_id field of all platform-devices to 0. This allows
+ * other OF/DT parsers to create such devices, too. However, they must
+ * start at offset 1 for this to work.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <linux/sysfb.h>
+
+static __init int sysfb_init(void)
+{
+	struct screen_info *si = &screen_info;
+	struct simplefb_platform_data mode;
+	struct platform_device *pd;
+	const char *name;
+	bool compatible;
+	int ret;
+
+	/* try to create a simple-framebuffer device */
+	compatible = sysfb_parse_mode(si, &mode);
+	if (compatible) {
+		ret = sysfb_create_simplefb(si, &mode);
+		if (!ret)
+			return 0;
+	}
+
+	/* if the FB is incompatible, create a legacy framebuffer device */
+	if (si->orig_video_isVGA == VIDEO_TYPE_EFI)
+		name = "efi-framebuffer";
+	else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+		name = "vesa-framebuffer";
+	else
+		name = "platform-framebuffer";
+
+	pd = platform_device_alloc(name, 0);
+	if (!pd)
+		return -ENOMEM;
+
+	sysfb_apply_efi_quirks(pd);
+
+	ret = platform_device_add_data(pd, si, sizeof(*si));
+	if (ret)
+		goto err;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	platform_device_put(pd);
+	return ret;
+}
+
+/* must execute after PCI subsystem for EFI quirks */
+device_initcall(sysfb_init);
diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c
new file mode 100644
index 000000000000..b86761904949
--- /dev/null
+++ b/drivers/firmware/sysfb_simplefb.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic System Framebuffers
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ */
+
+/*
+ * simple-framebuffer probing
+ * Try to convert "screen_info" into a "simple-framebuffer" compatible mode.
+ * If the mode is incompatible, we return "false" and let the caller create
+ * legacy nodes instead.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <linux/sysfb.h>
+
+static const char simplefb_resname[] = "BOOTFB";
+static const struct simplefb_format formats[] = SIMPLEFB_FORMATS;
+
+/* try parsing screen_info into a simple-framebuffer mode struct */
+__init bool sysfb_parse_mode(const struct screen_info *si,
+			     struct simplefb_platform_data *mode)
+{
+	const struct simplefb_format *f;
+	__u8 type;
+	unsigned int i;
+
+	type = si->orig_video_isVGA;
+	if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI)
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
+		f = &formats[i];
+		if (si->lfb_depth == f->bits_per_pixel &&
+		    si->red_size == f->red.length &&
+		    si->red_pos == f->red.offset &&
+		    si->green_size == f->green.length &&
+		    si->green_pos == f->green.offset &&
+		    si->blue_size == f->blue.length &&
+		    si->blue_pos == f->blue.offset &&
+		    si->rsvd_size == f->transp.length &&
+		    si->rsvd_pos == f->transp.offset) {
+			mode->format = f->name;
+			mode->width = si->lfb_width;
+			mode->height = si->lfb_height;
+			mode->stride = si->lfb_linelength;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+__init int sysfb_create_simplefb(const struct screen_info *si,
+				 const struct simplefb_platform_data *mode)
+{
+	struct platform_device *pd;
+	struct resource res;
+	u64 base, size;
+	u32 length;
+	int ret;
+
+	/*
+	 * If the 64BIT_BASE capability is set, ext_lfb_base will contain the
+	 * upper half of the base address. Assemble the address, then make sure
+	 * it is valid and we can actually access it.
+	 */
+	base = si->lfb_base;
+	if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)si->ext_lfb_base << 32;
+	if (!base || (u64)(resource_size_t)base != base) {
+		printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Don't use lfb_size as IORESOURCE size, since it may contain the
+	 * entire VMEM, and thus require huge mappings. Use just the part we
+	 * need, that is, the part where the framebuffer is located. But verify
+	 * that it does not exceed the advertised VMEM.
+	 * Note that in case of VBE, the lfb_size is shifted by 16 bits for
+	 * historical reasons.
+	 */
+	size = si->lfb_size;
+	if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+		size <<= 16;
+	length = mode->height * mode->stride;
+	if (length > size) {
+		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
+		return -EINVAL;
+	}
+	length = PAGE_ALIGN(length);
+
+	/* setup IORESOURCE_MEM as framebuffer memory */
+	memset(&res, 0, sizeof(res));
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res.name = simplefb_resname;
+	res.start = base;
+	res.end = res.start + length - 1;
+	if (res.end <= res.start)
+		return -EINVAL;
+
+	pd = platform_device_alloc("simple-framebuffer", 0);
+	if (!pd)
+		return -ENOMEM;
+
+	sysfb_apply_efi_quirks(pd);
+
+	ret = platform_device_add_resources(pd, &res, 1);
+	if (ret)
+		return ret;
+
+	ret = platform_device_add_data(pd, mode, sizeof(*mode));
+	if (ret)
+		return ret;
+
+	return platform_device_add(pd);
+}
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 7ff89690a976..cea777ae7fb9 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -35,6 +35,11 @@ config DRM_MIPI_DSI
 	bool
 	depends on DRM
 
+config DRM_DP_AUX_BUS
+	tristate
+	depends on DRM
+	depends on OF
+
 config DRM_DP_AUX_CHARDEV
 	bool "DRM DP AUX Interface"
 	depends on DRM
@@ -251,7 +256,6 @@ config DRM_AMDGPU
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
 	select INTERVAL_TREE
-	select CHASH
 	help
 	  Choose this option if you have a recent AMD Radeon graphics card.
 
@@ -317,8 +321,6 @@ source "drivers/gpu/drm/tilcdc/Kconfig"
 
 source "drivers/gpu/drm/qxl/Kconfig"
 
-source "drivers/gpu/drm/bochs/Kconfig"
-
 source "drivers/gpu/drm/virtio/Kconfig"
 
 source "drivers/gpu/drm/msm/Kconfig"
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index a118692a6df7..ad1112154898 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -33,6 +33,8 @@ drm-$(CONFIG_PCI) += drm_pci.o
 drm-$(CONFIG_DEBUG_FS) += drm_debugfs.o drm_debugfs_crc.o
 drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
 
+obj-$(CONFIG_DRM_DP_AUX_BUS) += drm_dp_aux_bus.o
+
 drm_vram_helper-y := drm_gem_vram_helper.o
 obj-$(CONFIG_DRM_VRAM_HELPER) += drm_vram_helper.o
 
@@ -96,7 +98,6 @@ obj-y			+= omapdrm/
 obj-$(CONFIG_DRM_SUN4I) += sun4i/
 obj-y			+= tilcdc/
 obj-$(CONFIG_DRM_QXL) += qxl/
-obj-$(CONFIG_DRM_BOCHS) += bochs/
 obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio/
 obj-$(CONFIG_DRM_MSM) += msm/
 obj-$(CONFIG_DRM_TEGRA) += tegra/
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index c56320e78c0e..8d0748184a14 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -57,7 +57,8 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
 	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
-	amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o
+	amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o \
+	amdgpu_eeprom.o amdgpu_mca.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 
@@ -75,7 +76,7 @@ amdgpu-y += \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \
 	arct_reg_init.o navi12_reg_init.o mxgpu_nv.o sienna_cichlid_reg_init.o vangogh_reg_init.o \
 	nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o \
-	beige_goby_reg_init.o yellow_carp_reg_init.o
+	beige_goby_reg_init.o yellow_carp_reg_init.o cyan_skillfish_reg_init.o
 
 # add DF block
 amdgpu-y += \
@@ -111,6 +112,7 @@ amdgpu-y += \
 	psp_v3_1.o \
 	psp_v10_0.o \
 	psp_v11_0.o \
+	psp_v11_0_8.o \
 	psp_v12_0.o \
 	psp_v13_0.o
 
@@ -118,7 +120,7 @@ amdgpu-y += \
 amdgpu-y += \
 	dce_v10_0.o \
 	dce_v11_0.o \
-	dce_virtual.o
+	amdgpu_vkms.o
 
 # add GFX block
 amdgpu-y += \
@@ -187,6 +189,10 @@ amdgpu-y += \
 amdgpu-y += \
 	amdgpu_reset.o
 
+# add MCA block
+amdgpu-y += \
+	mca_v3_0.o
+
 # add amdkfd interfaces
 amdgpu-y += amdgpu_amdkfd.o
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8ac6eb9f1fdb..dc3c6b3a00e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -108,6 +108,7 @@
 #include "amdgpu_df.h"
 #include "amdgpu_smuio.h"
 #include "amdgpu_fdinfo.h"
+#include "amdgpu_mca.h"
 
 #define MAX_GPU_INSTANCE		16
 
@@ -916,6 +917,7 @@ struct amdgpu_device {
 
 	/* display */
 	bool				enable_virtual_display;
+	struct amdgpu_vkms_output       *amdgpu_vkms_output;
 	struct amdgpu_mode_info		mode_info;
 	/* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */
 	struct work_struct		hotplug_work;
@@ -1008,6 +1010,9 @@ struct amdgpu_device {
 	/* df */
 	struct amdgpu_df                df;
 
+	/* MCA */
+	struct amdgpu_mca               mca;
+
 	struct amdgpu_ip_block          ip_blocks[AMDGPU_MAX_IP_NUM];
 	uint32_t		        harvest_ip_mask;
 	int				num_ip_blocks;
@@ -1108,8 +1113,13 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev);
 
 int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
+void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
+			     void *buf, size_t size, bool write);
+size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
+				 void *buf, size_t size, bool write);
+
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
-			       uint32_t *buf, size_t size, bool write);
+			       void *buf, size_t size, bool write);
 uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
 			    uint32_t reg, uint32_t acc_flags);
 void amdgpu_device_wreg(struct amdgpu_device *adev,
@@ -1265,6 +1275,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+
 /* Common functions */
 bool amdgpu_device_has_job_running(struct amdgpu_device *adev);
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
@@ -1385,12 +1397,12 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta
 int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
 
 void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps);
-bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev);
+bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
 void amdgpu_acpi_detect(void);
 #else
 static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
 static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
-static inline bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { return false; }
+static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline void amdgpu_acpi_detect(void) { }
 static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; }
 static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index b8655ff73a65..cc9c9f8b23b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -160,17 +160,28 @@ static int acp_poweron(struct generic_pm_domain *genpd)
 	return 0;
 }
 
-static struct device *get_mfd_cell_dev(const char *device_name, int r)
+static int acp_genpd_add_device(struct device *dev, void *data)
 {
-	char auto_dev_name[25];
-	struct device *dev;
+	struct generic_pm_domain *gpd = data;
+	int ret;
 
-	snprintf(auto_dev_name, sizeof(auto_dev_name),
-		 "%s.%d.auto", device_name, r);
-	dev = bus_find_device_by_name(&platform_bus_type, NULL, auto_dev_name);
-	dev_info(dev, "device %s added to pm domain\n", auto_dev_name);
+	ret = pm_genpd_add_device(gpd, dev);
+	if (ret)
+		dev_err(dev, "Failed to add dev to genpd %d\n", ret);
 
-	return dev;
+	return ret;
+}
+
+static int acp_genpd_remove_device(struct device *dev, void *data)
+{
+	int ret;
+
+	ret = pm_genpd_remove_device(dev);
+	if (ret)
+		dev_err(dev, "Failed to remove dev from genpd %d\n", ret);
+
+	/* Continue to remove */
+	return 0;
 }
 
 /**
@@ -181,11 +192,10 @@ static struct device *get_mfd_cell_dev(const char *device_name, int r)
  */
 static int acp_hw_init(void *handle)
 {
-	int r, i;
+	int r;
 	uint64_t acp_base;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -341,15 +351,10 @@ static int acp_hw_init(void *handle)
 	if (r)
 		goto failure;
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
-		if (r) {
-			dev_err(dev, "Failed to add dev to genpd\n");
-			goto failure;
-		}
-	}
-
+	r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd,
+				  acp_genpd_add_device);
+	if (r)
+		goto failure;
 
 	/* Assert Soft reset of ACP */
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
@@ -410,10 +415,8 @@ failure:
  */
 static int acp_hw_fini(void *handle)
 {
-	int i, ret;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* return early if no ACP */
@@ -458,13 +461,8 @@ static int acp_hw_fini(void *handle)
 		udelay(100);
 	}
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		ret = pm_genpd_remove_device(dev);
-		/* If removal fails, dont giveup and try rest */
-		if (ret)
-			dev_err(dev, "remove dev from genpd failed\n");
-	}
+	device_for_each_child(adev->acp.parent, NULL,
+			      acp_genpd_remove_device);
 
 	mfd_remove_devices(adev->acp.parent);
 	kfree(adev->acp.acp_res);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index a9ce3b20d371..4811b0faafd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -854,8 +854,8 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 		if (amdgpu_device_has_dc_support(adev)) {
 #if defined(CONFIG_DRM_AMD_DC)
 			struct amdgpu_display_manager *dm = &adev->dm;
-			if (dm->backlight_dev)
-				atif->bd = dm->backlight_dev;
+			if (dm->backlight_dev[0])
+				atif->bd = dm->backlight_dev[0];
 #endif
 		} else {
 			struct drm_encoder *tmp;
@@ -1032,13 +1032,13 @@ void amdgpu_acpi_detect(void)
 }
 
 /**
- * amdgpu_acpi_is_s0ix_supported
+ * amdgpu_acpi_is_s0ix_active
  *
  * @adev: amdgpu_device_pointer
  *
  * returns true if supported, false if not.
  */
-bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
+bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 {
 #if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_SUSPEND)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index f9c01bdc3d4c..3003ee1c9487 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -21,6 +21,7 @@
  */
 
 #include "amdgpu_amdkfd.h"
+#include "amd_pcie.h"
 #include "amd_shared.h"
 
 #include "amdgpu.h"
@@ -553,6 +554,88 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	return  (uint8_t)ret;
 }
 
+int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dst, *peer_adev;
+	int num_links;
+
+	if (adev->asic_type != CHIP_ALDEBARAN)
+		return 0;
+
+	if (src)
+		peer_adev = (struct amdgpu_device *)src;
+
+	/* num links returns 0 for indirect peers since indirect route is unknown. */
+	num_links = is_min ? 1 : amdgpu_xgmi_get_num_links(adev, peer_adev);
+	if (num_links < 0) {
+		DRM_ERROR("amdgpu: failed to get xgmi num links between node %d and %d. ret = %d\n",
+			adev->gmc.xgmi.physical_node_id,
+			peer_adev->gmc.xgmi.physical_node_id, num_links);
+		num_links = 0;
+	}
+
+	/* Aldebaran xGMI DPM is defeatured so assume x16 x 25Gbps for bandwidth. */
+	return (num_links * 16 * 25000)/BITS_PER_BYTE;
+}
+
+int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct kgd_dev *dev, bool is_min)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dev;
+	int num_lanes_shift = (is_min ? ffs(adev->pm.pcie_mlw_mask) :
+							fls(adev->pm.pcie_mlw_mask)) - 1;
+	int gen_speed_shift = (is_min ? ffs(adev->pm.pcie_gen_mask &
+						CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) :
+					fls(adev->pm.pcie_gen_mask &
+						CAIL_PCIE_LINK_SPEED_SUPPORT_MASK)) - 1;
+	uint32_t num_lanes_mask = 1 << num_lanes_shift;
+	uint32_t gen_speed_mask = 1 << gen_speed_shift;
+	int num_lanes_factor = 0, gen_speed_mbits_factor = 0;
+
+	switch (num_lanes_mask) {
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X1:
+		num_lanes_factor = 1;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X2:
+		num_lanes_factor = 2;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X4:
+		num_lanes_factor = 4;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X8:
+		num_lanes_factor = 8;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X12:
+		num_lanes_factor = 12;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X16:
+		num_lanes_factor = 16;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X32:
+		num_lanes_factor = 32;
+		break;
+	}
+
+	switch (gen_speed_mask) {
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1:
+		gen_speed_mbits_factor = 2500;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2:
+		gen_speed_mbits_factor = 5000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3:
+		gen_speed_mbits_factor = 8000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4:
+		gen_speed_mbits_factor = 16000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN5:
+		gen_speed_mbits_factor = 32000;
+		break;
+	}
+
+	return (num_lanes_factor * gen_speed_mbits_factor)/BITS_PER_BYTE;
+}
+
 uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
@@ -631,7 +714,6 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 	ret = dma_fence_wait(f, false);
 
 err_ib_sched:
-	dma_fence_put(f);
 	amdgpu_job_free(job);
 err:
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index cf62f43a03da..ec028cf963f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -226,6 +226,8 @@ uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
 int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
+int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min);
+int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct kgd_dev *dev, bool is_min);
 
 /* Read user wptr from a specified user address space with page fault
  * disabled. The memory must be pinned and mapped to the hardware when
@@ -269,7 +271,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
 		uint64_t *size);
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
@@ -330,7 +332,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
-void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask);
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask);
 #else
 static inline int kgd2kfd_init(void)
 {
@@ -389,7 +391,7 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 }
 
 static inline
-void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask)
 {
 }
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
index a5434b713856..46cd4ee6bafb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
@@ -44,4 +44,5 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 6409d6b1b2df..5a7f680bcb3f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -305,5 +305,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base =
 				kgd_gfx_v9_set_vm_context_page_table_base,
-	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 491acdf92f73..960acf68150a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -560,6 +560,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -754,6 +757,33 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
+static void program_trap_handler_settings(struct kgd_dev *kgd,
+		uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+			lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+			upper_32_bits(tba_addr >> 8) |
+			(1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -774,4 +804,5 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.program_trap_handler_settings = program_trap_handler_settings,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
index 1f5620cc3570..dac0d751d5af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
@@ -537,6 +537,9 @@ static int hqd_destroy_v10_3(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -658,6 +661,33 @@ static void set_vm_context_page_table_base_v10_3(struct kgd_dev *kgd, uint32_t v
 	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
+static void program_trap_handler_settings_v10_3(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+			lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+			upper_32_bits(tba_addr >> 8) |
+			(1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			 upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 #if 0
 uint32_t enable_debug_trap_v10_3(struct kgd_dev *kgd,
 				uint32_t trap_debug_wave_launch_mode,
@@ -820,6 +850,7 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = {
 	.address_watch_get_offset = address_watch_get_offset_v10_3,
 	.get_atc_vmid_pasid_mapping_info = NULL,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base_v10_3,
+	.program_trap_handler_settings = program_trap_handler_settings_v10_3,
 #if 0
 	.enable_debug_trap = enable_debug_trap_v10_3,
 	.disable_debug_trap = disable_debug_trap_v10_3,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index ed3014fbb563..bcc1cbeb8799 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -42,7 +42,8 @@
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
 	DRAIN_PIPE,
-	RESET_WAVES
+	RESET_WAVES,
+	SAVE_WAVES
 };
 
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
@@ -566,6 +567,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -878,6 +882,32 @@ void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
 				adev->gfx.cu_info.max_waves_per_simd;
 }
 
+void kgd_gfx_v9_program_trap_handler_settings(struct kgd_dev *kgd,
+                        uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+                        lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+                        upper_32_bits(tba_addr >> 8));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
@@ -899,4 +929,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
 	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index e64deba8900f..c63591106879 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -65,3 +65,5 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
 void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
 		int *pasid_wave_cnt, int *max_waves_per_cu);
+void kgd_gfx_v9_program_trap_handler_settings(struct kgd_dev *kgd,
+		uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 4fb15750b9bb..2d6b2d77b738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1057,7 +1057,8 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 static int update_gpuvm_pte(struct kgd_mem *mem,
 			    struct kfd_mem_attachment *entry,
-			    struct amdgpu_sync *sync)
+			    struct amdgpu_sync *sync,
+			    bool *table_freed)
 {
 	struct amdgpu_bo_va *bo_va = entry->bo_va;
 	struct amdgpu_device *adev = entry->adev;
@@ -1068,7 +1069,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 
 	/* Update the page tables  */
-	ret = amdgpu_vm_bo_update(adev, bo_va, false);
+	ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed);
 	if (ret) {
 		pr_err("amdgpu_vm_bo_update failed\n");
 		return ret;
@@ -1080,7 +1081,8 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
 			   struct kfd_mem_attachment *entry,
 			   struct amdgpu_sync *sync,
-			   bool no_update_pte)
+			   bool no_update_pte,
+			   bool *table_freed)
 {
 	int ret;
 
@@ -1097,7 +1099,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,
 	if (no_update_pte)
 		return 0;
 
-	ret = update_gpuvm_pte(mem, entry, sync);
+	ret = update_gpuvm_pte(mem, entry, sync, table_freed);
 	if (ret) {
 		pr_err("update_gpuvm_pte() failed\n");
 		goto update_gpuvm_pte_failed;
@@ -1285,11 +1287,22 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
 	if (avm->process_info)
 		return -EINVAL;
 
+	/* Free the original amdgpu allocated pasid,
+	 * will be replaced with kfd allocated pasid.
+	 */
+	if (avm->pasid) {
+		amdgpu_pasid_free(avm->pasid);
+		amdgpu_vm_set_pasid(adev, avm, 0);
+	}
+
 	/* Convert VM into a compute VM */
-	ret = amdgpu_vm_make_compute(adev, avm, pasid);
+	ret = amdgpu_vm_make_compute(adev, avm);
 	if (ret)
 		return ret;
 
+	ret = amdgpu_vm_set_pasid(adev, avm, pasid);
+	if (ret)
+		return ret;
 	/* Initialize KFD part of the VM and process info */
 	ret = init_kfd_vm(avm, process_info, ef);
 	if (ret)
@@ -1594,7 +1607,8 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 }
 
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv)
+		struct kgd_dev *kgd, struct kgd_mem *mem,
+		void *drm_priv, bool *table_freed)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
@@ -1682,7 +1696,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			 entry->va, entry->va + bo_size, entry);
 
 		ret = map_bo_to_gpuvm(mem, entry, ctx.sync,
-				      is_invalid_userptr);
+				      is_invalid_userptr, table_freed);
 		if (ret) {
 			pr_err("Failed to map bo to gpuvm\n");
 			goto out_unreserve;
@@ -1706,6 +1720,12 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 				true);
 	ret = unreserve_bo_and_vms(&ctx, false, false);
 
+	/* Only apply no TLB flush on Aldebaran to
+	 * workaround regressions on other Asics.
+	 */
+	if (table_freed && (adev->asic_type != CHIP_ALDEBARAN))
+		*table_freed = true;
+
 	goto out;
 
 out_unreserve:
@@ -2132,7 +2152,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync);
+			ret = update_gpuvm_pte(mem, attachment, &sync, NULL);
 			if (ret) {
 				pr_err("%s: update PTE failed\n", __func__);
 				/* make sure this gets validated again */
@@ -2338,7 +2358,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync_obj);
+			ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL);
 			if (ret) {
 				pr_debug("Memory eviction: update PTE failed. Try again\n");
 				goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index a130e766cbdb..c905a4cfc173 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -34,6 +34,7 @@ struct amdgpu_fpriv;
 struct amdgpu_bo_list_entry {
 	struct ttm_validate_buffer	tv;
 	struct amdgpu_bo_va		*bo_va;
+	struct dma_fence_chain		*chain;
 	uint32_t			priority;
 	struct page			**user_pages;
 	bool				user_invalidated;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 30fa1f61e0e5..913f9eaa9cd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -572,6 +572,20 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		goto out;
 	}
 
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
+
+		e->bo_va = amdgpu_vm_bo_find(vm, bo);
+
+		if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) {
+			e->chain = dma_fence_chain_alloc();
+			if (!e->chain) {
+				r = -ENOMEM;
+				goto error_validate;
+			}
+		}
+	}
+
 	amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
 					  &p->bytes_moved_vis_threshold);
 	p->bytes_moved = 0;
@@ -599,15 +613,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	gws = p->bo_list->gws_obj;
 	oa = p->bo_list->oa_obj;
 
-	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
-
-		/* Make sure we use the exclusive slot for shared BOs */
-		if (bo->prime_shared_count)
-			e->tv.num_shared = 0;
-		e->bo_va = amdgpu_vm_bo_find(vm, bo);
-	}
-
 	if (gds) {
 		p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT;
 		p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT;
@@ -629,8 +634,13 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	}
 
 error_validate:
-	if (r)
+	if (r) {
+		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+			dma_fence_chain_free(e->chain);
+			e->chain = NULL;
+		}
 		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
+	}
 out:
 	return r;
 }
@@ -670,9 +680,17 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 {
 	unsigned i;
 
-	if (error && backoff)
+	if (error && backoff) {
+		struct amdgpu_bo_list_entry *e;
+
+		amdgpu_bo_list_for_each_entry(e, parser->bo_list) {
+			dma_fence_chain_free(e->chain);
+			e->chain = NULL;
+		}
+
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
+	}
 
 	for (i = 0; i < parser->num_post_deps; i++) {
 		drm_syncobj_put(parser->post_deps[i].syncobj);
@@ -781,7 +799,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
+	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL);
 	if (r)
 		return r;
 
@@ -792,7 +810,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
@@ -811,7 +829,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (bo_va == NULL)
 			continue;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
@@ -1109,7 +1127,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p
 
 		dep->chain = NULL;
 		if (syncobj_deps[i].point) {
-			dep->chain = kmalloc(sizeof(*dep->chain), GFP_KERNEL);
+			dep->chain = dma_fence_chain_alloc();
 			if (!dep->chain)
 				return -ENOMEM;
 		}
@@ -1117,7 +1135,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p
 		dep->syncobj = drm_syncobj_find(p->filp,
 						syncobj_deps[i].handle);
 		if (!dep->syncobj) {
-			kfree(dep->chain);
+			dma_fence_chain_free(dep->chain);
 			return -EINVAL;
 		}
 		dep->point = syncobj_deps[i].point;
@@ -1245,6 +1263,28 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);
 
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct dma_resv *resv = e->tv.bo->base.resv;
+		struct dma_fence_chain *chain = e->chain;
+
+		if (!chain)
+			continue;
+
+		/*
+		 * Work around dma_resv shortcommings by wrapping up the
+		 * submission in a dma_fence_chain and add it as exclusive
+		 * fence, but first add the submission as shared fence to make
+		 * sure that shared fences never signal before the exclusive
+		 * one.
+		 */
+		dma_fence_chain_init(chain, dma_resv_excl_fence(resv),
+				     dma_fence_get(p->fence), 1);
+
+		dma_resv_add_shared_fence(resv, p->fence);
+		rcu_assign_pointer(resv->fence_excl, &chain->base);
+		e->chain = NULL;
+	}
+
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	mutex_unlock(&p->adev->notifier_lock);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 536005bff24a..277128846dd1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1414,7 +1414,7 @@ no_preempt:
 			continue;
 		}
 		job = to_amdgpu_job(s_job);
-		if (preempted && job->fence == fence)
+		if (preempted && (&job->hw_fence) == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f944ed858f3e..41c6b3aacd37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -116,6 +116,7 @@ const char *amdgpu_asic_name[] = {
 	"RENOIR",
 	"ALDEBARAN",
 	"NAVI10",
+	"CYAN_SKILLFISH",
 	"NAVI14",
 	"NAVI12",
 	"SIENNA_CICHLID",
@@ -287,7 +288,7 @@ bool amdgpu_device_supports_smart_shift(struct drm_device *dev)
  */
 
 /**
- * amdgpu_device_vram_access - read/write a buffer in vram
+ * amdgpu_device_mm_access - access vram by MM_INDEX/MM_DATA
  *
  * @adev: amdgpu_device pointer
  * @pos: offset of the buffer in vram
@@ -295,22 +296,65 @@ bool amdgpu_device_supports_smart_shift(struct drm_device *dev)
  * @size: read/write size, sizeof(@buf) must > @size
  * @write: true - write to vram, otherwise - read from vram
  */
-void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
-			       uint32_t *buf, size_t size, bool write)
+void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
+			     void *buf, size_t size, bool write)
 {
 	unsigned long flags;
-	uint32_t hi = ~0;
+	uint32_t hi = ~0, tmp = 0;
+	uint32_t *data = buf;
 	uint64_t last;
 	int idx;
 
 	if (!drm_dev_enter(&adev->ddev, &idx))
 		return;
 
+	BUG_ON(!IS_ALIGNED(pos, 4) || !IS_ALIGNED(size, 4));
+
+	spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+	for (last = pos + size; pos < last; pos += 4) {
+		tmp = pos >> 31;
+
+		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
+		if (tmp != hi) {
+			WREG32_NO_KIQ(mmMM_INDEX_HI, tmp);
+			hi = tmp;
+		}
+		if (write)
+			WREG32_NO_KIQ(mmMM_DATA, *data++);
+		else
+			*data++ = RREG32_NO_KIQ(mmMM_DATA);
+	}
+
+	spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	drm_dev_exit(idx);
+}
+
+/**
+ * amdgpu_device_vram_access - access vram by vram aperature
+ *
+ * @adev: amdgpu_device pointer
+ * @pos: offset of the buffer in vram
+ * @buf: virtual address of the buffer in system memory
+ * @size: read/write size, sizeof(@buf) must > @size
+ * @write: true - write to vram, otherwise - read from vram
+ *
+ * The return value means how many bytes have been transferred.
+ */
+size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
+				 void *buf, size_t size, bool write)
+{
 #ifdef CONFIG_64BIT
+	void __iomem *addr;
+	size_t count = 0;
+	uint64_t last;
+
+	if (!adev->mman.aper_base_kaddr)
+		return 0;
+
 	last = min(pos + size, adev->gmc.visible_vram_size);
 	if (last > pos) {
-		void __iomem *addr = adev->mman.aper_base_kaddr + pos;
-		size_t count = last - pos;
+		addr = adev->mman.aper_base_kaddr + pos;
+		count = last - pos;
 
 		if (write) {
 			memcpy_toio(addr, buf, count);
@@ -322,35 +366,37 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 			memcpy_fromio(buf, addr, count);
 		}
 
-		if (count == size)
-			goto exit;
-
-		pos += count;
-		buf += count / 4;
-		size -= count;
 	}
+
+	return count;
+#else
+	return 0;
 #endif
+}
 
-	spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-	for (last = pos + size; pos < last; pos += 4) {
-		uint32_t tmp = pos >> 31;
+/**
+ * amdgpu_device_vram_access - read/write a buffer in vram
+ *
+ * @adev: amdgpu_device pointer
+ * @pos: offset of the buffer in vram
+ * @buf: virtual address of the buffer in system memory
+ * @size: read/write size, sizeof(@buf) must > @size
+ * @write: true - write to vram, otherwise - read from vram
+ */
+void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
+			       void *buf, size_t size, bool write)
+{
+	size_t count;
 
-		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
-		if (tmp != hi) {
-			WREG32_NO_KIQ(mmMM_INDEX_HI, tmp);
-			hi = tmp;
-		}
-		if (write)
-			WREG32_NO_KIQ(mmMM_DATA, *buf++);
-		else
-			*buf++ = RREG32_NO_KIQ(mmMM_DATA);
+	/* try to using vram apreature to access vram first */
+	count = amdgpu_device_aper_access(adev, pos, buf, size, write);
+	size -= count;
+	if (size) {
+		/* using MM to access rest vram */
+		pos += count;
+		buf += count;
+		amdgpu_device_mm_access(adev, pos, buf, size, write);
 	}
-	spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-
-#ifdef CONFIG_64BIT
-exit:
-#endif
-	drm_dev_exit(idx);
 }
 
 /*
@@ -518,7 +564,7 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 	    adev->gfx.rlc.funcs &&
 	    adev->gfx.rlc.funcs->is_rlcg_access_range) {
 		if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg))
-			return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v, 0, 0);
+			return adev->gfx.rlc.funcs->sriov_wreg(adev, reg, v, 0, 0);
 	} else {
 		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
 	}
@@ -1266,15 +1312,16 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 /**
  * amdgpu_device_vga_set_decode - enable/disable vga decode
  *
- * @cookie: amdgpu_device pointer
+ * @pdev: PCI device pointer
  * @state: enable/disable vga decode
  *
  * Enable/disable vga decode (all asics).
  * Returns VGA resource flags.
  */
-static unsigned int amdgpu_device_vga_set_decode(void *cookie, bool state)
+static unsigned int amdgpu_device_vga_set_decode(struct pci_dev *pdev,
+		bool state)
 {
-	struct amdgpu_device *adev = cookie;
+	struct amdgpu_device *adev = drm_to_adev(pci_get_drvdata(pdev));
 	amdgpu_asic_set_vga_state(adev, state);
 	if (state)
 		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
@@ -1394,6 +1441,10 @@ static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev)
 		break;
 	case CHIP_YELLOW_CARP:
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->pdev->device == 0x13FE)
+			adev->apu_flags |= AMD_APU_IS_CYAN_SKILLFISH2;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -2100,6 +2151,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	case  CHIP_BEIGE_GOBY:
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		if (adev->asic_type == CHIP_VANGOGH)
 			adev->family = AMDGPU_FAMILY_VGH;
 		else if (adev->asic_type == CHIP_YELLOW_CARP)
@@ -3594,9 +3646,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 fence_driver_init:
 	/* Fence driver */
-	r = amdgpu_fence_driver_init(adev);
+	r = amdgpu_fence_driver_sw_init(adev);
 	if (r) {
-		dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
+		dev_err(adev->dev, "amdgpu_fence_driver_sw_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
 		goto failed;
 	}
@@ -3623,6 +3675,8 @@ fence_driver_init:
 		goto release_ras_con;
 	}
 
+	amdgpu_fence_driver_hw_init(adev);
+
 	dev_info(adev->dev,
 		"SE %d, SH per SE %d, CU per SH %d, active_cu_number %d\n",
 			adev->gfx.config.max_shader_engines,
@@ -3714,7 +3768,7 @@ fence_driver_init:
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
 	if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
-		vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
+		vga_client_register(adev->pdev, amdgpu_device_vga_set_decode);
 
 	if (amdgpu_device_supports_px(ddev)) {
 		px = true;
@@ -3771,7 +3825,10 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
-	ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	if (adev->mman.initialized) {
+		flush_delayed_work(&adev->mman.bdev.wq);
+		ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	}
 	adev->shutdown = true;
 
 	/* make sure IB test finished before entering exclusive mode
@@ -3790,7 +3847,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		else
 			drm_atomic_helper_shutdown(adev_to_drm(adev));
 	}
-	amdgpu_fence_driver_fini_hw(adev);
+	amdgpu_fence_driver_hw_fini(adev);
 
 	if (adev->pm_sysfs_en)
 		amdgpu_pm_sysfs_fini(adev);
@@ -3812,7 +3869,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 {
 	amdgpu_device_ip_fini(adev);
-	amdgpu_fence_driver_fini_sw(adev);
+	amdgpu_fence_driver_sw_fini(adev);
 	release_firmware(adev->firmware.gpu_info_fw);
 	adev->firmware.gpu_info_fw = NULL;
 	adev->accel_working = false;
@@ -3833,7 +3890,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	}
 	if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
-		vga_client_register(adev->pdev, NULL, NULL, NULL);
+		vga_client_unregister(adev->pdev);
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
@@ -3887,7 +3944,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
-	amdgpu_fence_driver_suspend(adev);
+	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
 	/* evict remaining vram memory
@@ -3932,8 +3989,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
 		return r;
 	}
-	amdgpu_fence_driver_resume(adev);
-
+	amdgpu_fence_driver_hw_init(adev);
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
@@ -4394,7 +4450,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 				 struct amdgpu_reset_context *reset_context)
 {
-	int i, r = 0;
+	int i, j, r = 0;
 	struct amdgpu_job *job = NULL;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4418,11 +4474,22 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!ring || !ring->sched.thread)
 			continue;
 
+		/*clear job fence from fence drv to avoid force_completion
+		 *leave NULL and vm flush fence in fence drv */
+		for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
+			struct dma_fence *old, **ptr;
+
+			ptr = &ring->fence_drv.fences[j];
+			old = rcu_dereference_protected(*ptr, 1);
+			if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
+				RCU_INIT_POINTER(*ptr, NULL);
+			}
+		}
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
 
-	if(job)
+	if (job && job->vm)
 		drm_sched_increase_karma(&job->base);
 
 	r = amdgpu_reset_prepare_hwcontext(adev, reset_context);
@@ -4886,7 +4953,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
 				job ? job->base.id : -1, hive->hive_id);
 			amdgpu_put_xgmi_hive(hive);
-			if (job)
+			if (job && job->vm)
 				drm_sched_increase_karma(&job->base);
 			return 0;
 		}
@@ -4910,7 +4977,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 					job ? job->base.id : -1);
 
 		/* even we skipped this reset, still need to set the job to guilty */
-		if (job)
+		if (job && job->vm)
 			drm_sched_increase_karma(&job->base);
 		goto skip_recovery;
 	}
@@ -5277,6 +5344,10 @@ int amdgpu_device_baco_exit(struct drm_device *dev)
 	    adev->nbio.funcs->enable_doorbell_interrupt)
 		adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
 
+	if (amdgpu_passthrough(adev) &&
+	    adev->nbio.funcs->clear_doorbell_interrupt)
+		adev->nbio.funcs->clear_doorbell_interrupt(adev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index a9475b207510..ae6ab93c868b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -42,48 +42,6 @@
 #include <linux/pci-p2pdma.h>
 #include <linux/pm_runtime.h>
 
-static int
-__dma_resv_make_exclusive(struct dma_resv *obj)
-{
-	struct dma_fence **fences;
-	unsigned int count;
-	int r;
-
-	if (!dma_resv_shared_list(obj)) /* no shared fences to convert */
-		return 0;
-
-	r = dma_resv_get_fences(obj, NULL, &count, &fences);
-	if (r)
-		return r;
-
-	if (count == 0) {
-		/* Now that was unexpected. */
-	} else if (count == 1) {
-		dma_resv_add_excl_fence(obj, fences[0]);
-		dma_fence_put(fences[0]);
-		kfree(fences);
-	} else {
-		struct dma_fence_array *array;
-
-		array = dma_fence_array_create(count, fences,
-					       dma_fence_context_alloc(1), 0,
-					       false);
-		if (!array)
-			goto err_fences_put;
-
-		dma_resv_add_excl_fence(obj, &array->base);
-		dma_fence_put(&array->base);
-	}
-
-	return 0;
-
-err_fences_put:
-	while (count--)
-		dma_fence_put(fences[count]);
-	kfree(fences);
-	return -ENOMEM;
-}
-
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
  *
@@ -110,24 +68,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	if (r < 0)
 		goto out;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (unlikely(r != 0))
-		goto out;
-
-	/*
-	 * We only create shared fences for internal use, but importers
-	 * of the dmabuf rely on exclusive fences for implicitly
-	 * tracking write hazards. As any of the current fences may
-	 * correspond to a write, we need to convert all existing
-	 * fences on the reservation object into a single exclusive
-	 * fence.
-	 */
-	r = __dma_resv_make_exclusive(bo->tbo.base.resv);
-	if (r)
-		goto out;
-
-	bo->prime_shared_count++;
-	amdgpu_bo_unreserve(bo);
 	return 0;
 
 out:
@@ -150,9 +90,6 @@ static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
-		bo->prime_shared_count--;
-
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 }
@@ -418,8 +355,6 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 	bo = gem_to_amdgpu_bo(gobj);
 	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
-	if (dma_buf->ops != &amdgpu_dmabuf_ops)
-		bo->prime_shared_count = 1;
 
 	dma_resv_unlock(resv);
 	return gobj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 971c5b8e75dc..b6640291f980 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -870,11 +870,10 @@ MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legac
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
 /**
- * DOC: bad_page_threshold (int)
- * Bad page threshold is to specify the threshold value of faulty pages
- * detected by RAS ECC, that may result in GPU entering bad status if total
- * faulty pages by ECC exceed threshold value and leave it for user's further
- * check.
+ * DOC: bad_page_threshold (int) Bad page threshold is specifies the
+ * threshold value of faulty pages detected by RAS ECC, which may
+ * result in the GPU entering bad status when the number of total
+ * faulty pages by ECC exceeds the threshold value.
  */
 MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
 module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
@@ -1213,6 +1212,9 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x740F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 	{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 
+	/* CYAN_SKILLFISH */
+	{0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+
 	/* BEIGE_GOBY */
 	{0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
@@ -1236,7 +1238,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	int ret, retry = 0;
 	bool supports_atomic = false;
 
-	if (!amdgpu_virtual_display &&
+	if (amdgpu_virtual_display ||
 	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
 		supports_atomic = true;
 
@@ -1292,7 +1294,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 #endif
 
 	/* Get rid of things like offb */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "amdgpudrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
 	if (ret)
 		return ret;
 
@@ -1474,7 +1476,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
-	if (amdgpu_acpi_is_s0ix_supported(adev))
+	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	adev->in_s3 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
@@ -1490,7 +1492,7 @@ static int amdgpu_pmops_resume(struct device *dev)
 	int r;
 
 	r = amdgpu_device_resume(drm_dev, true);
-	if (amdgpu_acpi_is_s0ix_supported(adev))
+	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = false;
 	return r;
 }
@@ -1784,7 +1786,6 @@ static const struct drm_driver amdgpu_kms_driver = {
 	.open = amdgpu_driver_open_kms,
 	.postclose = amdgpu_driver_postclose_kms,
 	.lastclose = amdgpu_driver_lastclose_kms,
-	.irq_handler = amdgpu_irq_handler,
 	.ioctls = amdgpu_ioctls_kms,
 	.num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms),
 	.dumb_create = amdgpu_mode_dumb_create,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c
new file mode 100644
index 000000000000..4d9eb0137f8c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c
@@ -0,0 +1,239 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu_eeprom.h"
+#include "amdgpu.h"
+
+/* AT24CM02 and M24M02-R have a 256-byte write page size.
+ */
+#define EEPROM_PAGE_BITS   8
+#define EEPROM_PAGE_SIZE   (1U << EEPROM_PAGE_BITS)
+#define EEPROM_PAGE_MASK   (EEPROM_PAGE_SIZE - 1)
+
+#define EEPROM_OFFSET_SIZE 2
+
+/* EEPROM memory addresses are 19-bits long, which can
+ * be partitioned into 3, 8, 8 bits, for a total of 19.
+ * The upper 3 bits are sent as part of the 7-bit
+ * "Device Type Identifier"--an I2C concept, which for EEPROM devices
+ * is hard-coded as 1010b, indicating that it is an EEPROM
+ * device--this is the wire format, followed by the upper
+ * 3 bits of the 19-bit address, followed by the direction,
+ * followed by two bytes holding the rest of the 16-bits of
+ * the EEPROM memory address. The format on the wire for EEPROM
+ * devices is: 1010XYZD, A15:A8, A7:A0,
+ * Where D is the direction and sequenced out by the hardware.
+ * Bits XYZ are memory address bits 18, 17 and 16.
+ * These bits are compared to how pins 1-3 of the part are connected,
+ * depending on the size of the part, more on that later.
+ *
+ * Note that of this wire format, a client is in control
+ * of, and needs to specify only XYZ, A15:A8, A7:0, bits,
+ * which is exactly the EEPROM memory address, or offset,
+ * in order to address up to 8 EEPROM devices on the I2C bus.
+ *
+ * For instance, a 2-Mbit I2C EEPROM part, addresses all its bytes,
+ * using an 18-bit address, bit 17 to 0 and thus would use all but one bit of
+ * the 19 bits previously mentioned. The designer would then not connect
+ * pins 1 and 2, and pin 3 usually named "A_2" or "E2", would be connected to
+ * either Vcc or GND. This would allow for up to two 2-Mbit parts on
+ * the same bus, where one would be addressable with bit 18 as 1, and
+ * the other with bit 18 of the address as 0.
+ *
+ * For a 2-Mbit part, bit 18 is usually known as the "Chip Enable" or
+ * "Hardware Address Bit". This bit is compared to the load on pin 3
+ * of the device, described above, and if there is a match, then this
+ * device responds to the command. This way, you can connect two
+ * 2-Mbit EEPROM devices on the same bus, but see one contiguous
+ * memory from 0 to 7FFFFh, where address 0 to 3FFFF is in the device
+ * whose pin 3 is connected to GND, and address 40000 to 7FFFFh is in
+ * the 2nd device, whose pin 3 is connected to Vcc.
+ *
+ * This addressing you encode in the 32-bit "eeprom_addr" below,
+ * namely the 19-bits "XYZ,A15:A0", as a single 19-bit address. For
+ * instance, eeprom_addr = 0x6DA01, is 110_1101_1010_0000_0001, where
+ * XYZ=110b, and A15:A0=DA01h. The XYZ bits become part of the device
+ * address, and the rest of the address bits are sent as the memory
+ * address bytes.
+ *
+ * That is, for an I2C EEPROM driver everything is controlled by
+ * the "eeprom_addr".
+ *
+ * P.S. If you need to write, lock and read the Identification Page,
+ * (M24M02-DR device only, which we do not use), change the "7" to
+ * "0xF" in the macro below, and let the client set bit 20 to 1 in
+ * "eeprom_addr", and set A10 to 0 to write into it, and A10 and A1 to
+ * 1 to lock it permanently.
+ */
+#define MAKE_I2C_ADDR(_aa) ((0xA << 3) | (((_aa) >> 16) & 7))
+
+static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+				u8 *eeprom_buf, u16 buf_size, bool read)
+{
+	u8 eeprom_offset_buf[EEPROM_OFFSET_SIZE];
+	struct i2c_msg msgs[] = {
+		{
+			.flags = 0,
+			.len = EEPROM_OFFSET_SIZE,
+			.buf = eeprom_offset_buf,
+		},
+		{
+			.flags = read ? I2C_M_RD : 0,
+		},
+	};
+	const u8 *p = eeprom_buf;
+	int r;
+	u16 len;
+
+	for (r = 0; buf_size > 0;
+	      buf_size -= len, eeprom_addr += len, eeprom_buf += len) {
+		/* Set the EEPROM address we want to write to/read from.
+		 */
+		msgs[0].addr = MAKE_I2C_ADDR(eeprom_addr);
+		msgs[1].addr = msgs[0].addr;
+		msgs[0].buf[0] = (eeprom_addr >> 8) & 0xff;
+		msgs[0].buf[1] = eeprom_addr & 0xff;
+
+		if (!read) {
+			/* Write the maximum amount of data, without
+			 * crossing the device's page boundary, as per
+			 * its spec. Partial page writes are allowed,
+			 * starting at any location within the page,
+			 * so long as the page boundary isn't crossed
+			 * over (actually the page pointer rolls
+			 * over).
+			 *
+			 * As per the AT24CM02 EEPROM spec, after
+			 * writing into a page, the I2C driver should
+			 * terminate the transfer, i.e. in
+			 * "i2c_transfer()" below, with a STOP
+			 * condition, so that the self-timed write
+			 * cycle begins. This is implied for the
+			 * "i2c_transfer()" abstraction.
+			 */
+			len = min(EEPROM_PAGE_SIZE - (eeprom_addr &
+						      EEPROM_PAGE_MASK),
+				  (u32)buf_size);
+		} else {
+			/* Reading from the EEPROM has no limitation
+			 * on the number of bytes read from the EEPROM
+			 * device--they are simply sequenced out.
+			 */
+			len = buf_size;
+		}
+		msgs[1].len = len;
+		msgs[1].buf = eeprom_buf;
+
+		/* This constitutes a START-STOP transaction.
+		 */
+		r = i2c_transfer(i2c_adap, msgs, ARRAY_SIZE(msgs));
+		if (r != ARRAY_SIZE(msgs))
+			break;
+
+		if (!read) {
+			/* According to EEPROM specs the length of the
+			 * self-writing cycle, tWR (tW), is 10 ms.
+			 *
+			 * TODO: Use polling on ACK, aka Acknowledge
+			 * Polling, to minimize waiting for the
+			 * internal write cycle to complete, as it is
+			 * usually smaller than tWR (tW).
+			 */
+			msleep(10);
+		}
+	}
+
+	return r < 0 ? r : eeprom_buf - p;
+}
+
+/**
+ * amdgpu_eeprom_xfer -- Read/write from/to an I2C EEPROM device
+ * @i2c_adap: pointer to the I2C adapter to use
+ * @eeprom_addr: EEPROM address from which to read/write
+ * @eeprom_buf: pointer to data buffer to read into/write from
+ * @buf_size: the size of @eeprom_buf
+ * @read: True if reading from the EEPROM, false if writing
+ *
+ * Returns the number of bytes read/written; -errno on error.
+ */
+static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+			      u8 *eeprom_buf, u16 buf_size, bool read)
+{
+	const struct i2c_adapter_quirks *quirks = i2c_adap->quirks;
+	u16 limit;
+
+	if (!quirks)
+		limit = 0;
+	else if (read)
+		limit = quirks->max_read_len;
+	else
+		limit = quirks->max_write_len;
+
+	if (limit == 0) {
+		return __amdgpu_eeprom_xfer(i2c_adap, eeprom_addr,
+					    eeprom_buf, buf_size, read);
+	} else if (limit <= EEPROM_OFFSET_SIZE) {
+		dev_err_ratelimited(&i2c_adap->dev,
+				    "maddr:0x%04X size:0x%02X:quirk max_%s_len must be > %d",
+				    eeprom_addr, buf_size,
+				    read ? "read" : "write", EEPROM_OFFSET_SIZE);
+		return -EINVAL;
+	} else {
+		u16 ps; /* Partial size */
+		int res = 0, r;
+
+		/* The "limit" includes all data bytes sent/received,
+		 * which would include the EEPROM_OFFSET_SIZE bytes.
+		 * Account for them here.
+		 */
+		limit -= EEPROM_OFFSET_SIZE;
+		for ( ; buf_size > 0;
+		      buf_size -= ps, eeprom_addr += ps, eeprom_buf += ps) {
+			ps = min(limit, buf_size);
+
+			r = __amdgpu_eeprom_xfer(i2c_adap, eeprom_addr,
+						 eeprom_buf, ps, read);
+			if (r < 0)
+				return r;
+			res += r;
+		}
+
+		return res;
+	}
+}
+
+int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+		       u32 eeprom_addr, u8 *eeprom_buf,
+		       u16 bytes)
+{
+	return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+				  true);
+}
+
+int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+			u32 eeprom_addr, u8 *eeprom_buf,
+			u16 bytes)
+{
+	return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+				  false);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h
new file mode 100644
index 000000000000..6935adb2be1f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _AMDGPU_EEPROM_H
+#define _AMDGPU_EEPROM_H
+
+#include <linux/i2c.h>
+
+int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+		       u32 eeprom_addr, u8 *eeprom_buf,
+		       u16 bytes);
+
+int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+			u32 eeprom_addr, u8 *eeprom_buf,
+			u16 bytes);
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 09b048647523..cd0acbea75da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -273,9 +273,6 @@ static int amdgpufb_create(struct drm_fb_helper *helper,
 	return 0;
 
 out:
-	if (abo) {
-
-	}
 	if (fb && ret) {
 		drm_gem_object_put(gobj);
 		drm_framebuffer_unregister_private(fb);
@@ -344,7 +341,7 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 	}
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
-	if (!amdgpu_device_has_dc_support(adev))
+	if (!amdgpu_device_has_dc_support(adev) && !amdgpu_virtual_display)
 		drm_helper_disable_unused_functions(adev_to_drm(adev));
 
 	drm_fb_helper_initial_config(&rfbdev->helper, bpp_sel);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 72d9b92b1754..14499f0de32d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -129,30 +129,50 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
  *
  * @ring: ring the fence is associated with
  * @f: resulting fence object
+ * @job: job the fence is embedded in
  * @flags: flags to pass into the subordinate .emit_fence() call
  *
  * Emits a fence command on the requested ring (all asics).
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amdgpu_job *job,
 		      unsigned flags)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_fence *fence;
+	struct dma_fence *fence;
+	struct amdgpu_fence *am_fence;
 	struct dma_fence __rcu **ptr;
 	uint32_t seq;
 	int r;
 
-	fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
-	if (fence == NULL)
-		return -ENOMEM;
+	if (job == NULL) {
+		/* create a sperate hw fence */
+		am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
+		if (am_fence == NULL)
+			return -ENOMEM;
+		fence = &am_fence->base;
+		am_fence->ring = ring;
+	} else {
+		/* take use of job-embedded fence */
+		fence = &job->hw_fence;
+	}
 
 	seq = ++ring->fence_drv.sync_seq;
-	fence->ring = ring;
-	dma_fence_init(&fence->base, &amdgpu_fence_ops,
-		       &ring->fence_drv.lock,
-		       adev->fence_context + ring->idx,
-		       seq);
+	if (job != NULL && job->job_run_counter) {
+		/* reinit seq for resubmitted jobs */
+		fence->seqno = seq;
+	} else {
+		dma_fence_init(fence, &amdgpu_fence_ops,
+				&ring->fence_drv.lock,
+				adev->fence_context + ring->idx,
+				seq);
+	}
+
+	if (job != NULL) {
+		/* mark this fence has a parent job */
+		set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+	}
+
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
 	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
@@ -175,9 +195,9 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 	/* This function can't be called concurrently anyway, otherwise
 	 * emitting the fence would mess up the hardware ring buffer.
 	 */
-	rcu_assign_pointer(*ptr, dma_fence_get(&fence->base));
+	rcu_assign_pointer(*ptr, dma_fence_get(fence));
 
-	*f = &fence->base;
+	*f = fence;
 
 	return 0;
 }
@@ -417,9 +437,6 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	}
 	amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq));
 
-	if (irq_src)
-		amdgpu_irq_get(adev, irq_src, irq_type);
-
 	ring->fence_drv.irq_src = irq_src;
 	ring->fence_drv.irq_type = irq_type;
 	ring->fence_drv.initialized = true;
@@ -490,7 +507,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 
 	r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
 			   num_hw_submission, amdgpu_job_hang_limit,
-			   timeout, sched_score, ring->name);
+			   timeout, NULL, sched_score, ring->name);
 	if (r) {
 		DRM_ERROR("Failed to create scheduler on ring %s.\n",
 			  ring->name);
@@ -501,7 +518,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 }
 
 /**
- * amdgpu_fence_driver_init - init the fence driver
+ * amdgpu_fence_driver_sw_init - init the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -512,20 +529,20 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-int amdgpu_fence_driver_init(struct amdgpu_device *adev)
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 {
 	return 0;
 }
 
 /**
- * amdgpu_fence_driver_fini - tear down the fence driver
+ * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
  *
  * Tear down the fence driver for all possible rings (all asics).
  */
-void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
+void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -534,8 +551,7 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
-		if (!ring->no_scheduler)
-			drm_sched_fini(&ring->sched);
+
 		/* You can't wait for HW to signal if it's gone */
 		if (!drm_dev_is_unplugged(&adev->ddev))
 			r = amdgpu_fence_wait_empty(ring);
@@ -553,7 +569,7 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 	}
 }
 
-void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
+void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 {
 	unsigned int i, j;
 
@@ -563,6 +579,9 @@ void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler)
+			drm_sched_fini(&ring->sched);
+
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
 		kfree(ring->fence_drv.fences);
@@ -572,49 +591,18 @@ void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_fence_driver_suspend - suspend the fence driver
- * for all possible rings.
- *
- * @adev: amdgpu device pointer
- *
- * Suspend the fence driver for all possible rings (all asics).
- */
-void amdgpu_fence_driver_suspend(struct amdgpu_device *adev)
-{
-	int i, r;
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		if (!ring || !ring->fence_drv.initialized)
-			continue;
-
-		/* wait for gpu to finish processing current batch */
-		r = amdgpu_fence_wait_empty(ring);
-		if (r) {
-			/* delay GPU reset to resume */
-			amdgpu_fence_driver_force_completion(ring);
-		}
-
-		/* disable the interrupt */
-		if (ring->fence_drv.irq_src)
-			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-				       ring->fence_drv.irq_type);
-	}
-}
-
-/**
- * amdgpu_fence_driver_resume - resume the fence driver
+ * amdgpu_fence_driver_hw_init - enable the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
  *
- * Resume the fence driver for all possible rings (all asics).
+ * Enable the fence driver for all possible rings (all asics).
  * Not all asics have all rings, so each asic will only
  * start the fence driver on the rings it has using
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-void amdgpu_fence_driver_resume(struct amdgpu_device *adev)
+void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 {
 	int i;
 
@@ -653,8 +641,16 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
 
 static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
-	return (const char *)fence->ring->name;
+	struct amdgpu_ring *ring;
+
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+		ring = to_amdgpu_ring(job->base.sched);
+	} else {
+		ring = to_amdgpu_fence(f)->ring;
+	}
+	return (const char *)ring->name;
 }
 
 /**
@@ -667,13 +663,20 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
  */
 static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
-	struct amdgpu_ring *ring = fence->ring;
+	struct amdgpu_ring *ring;
+
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+		ring = to_amdgpu_ring(job->base.sched);
+	} else {
+		ring = to_amdgpu_fence(f)->ring;
+	}
 
 	if (!timer_pending(&ring->fence_drv.fallback_timer))
 		amdgpu_fence_schedule_fallback(ring);
 
-	DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx);
+	DMA_FENCE_TRACE(f, "armed on ring %i!\n", ring->idx);
 
 	return true;
 }
@@ -688,8 +691,20 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 static void amdgpu_fence_free(struct rcu_head *rcu)
 {
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
-	kmem_cache_free(amdgpu_fence_slab, fence);
+
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+	/* free job if fence has a parent job */
+		struct amdgpu_job *job;
+
+		job = container_of(f, struct amdgpu_job, hw_fence);
+		kfree(job);
+	} else {
+	/* free fence_slab if it's separated fence*/
+		struct amdgpu_fence *fence;
+
+		fence = to_amdgpu_fence(f);
+		kmem_cache_free(amdgpu_fence_slab, fence);
+	}
 }
 
 /**
@@ -712,6 +727,7 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.release = amdgpu_fence_release,
 };
 
+
 /*
  * Fence debugfs
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index 39b6c6bfab45..7709caeb233d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -27,10 +27,10 @@
 #include "smu_v11_0_i2c.h"
 #include "atom.h"
 #include "amdgpu_fru_eeprom.h"
+#include "amdgpu_eeprom.h"
 
-#define I2C_PRODUCT_INFO_ADDR		0xAC
-#define I2C_PRODUCT_INFO_ADDR_SIZE	0x2
-#define I2C_PRODUCT_INFO_OFFSET		0xC0
+#define FRU_EEPROM_MADDR        0x60000
+#define I2C_PRODUCT_INFO_OFFSET 0xC0
 
 static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 {
@@ -62,19 +62,11 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 }
 
 static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
-			   unsigned char *buff)
+				  unsigned char *buff)
 {
 	int ret, size;
-	struct i2c_msg msg = {
-			.addr   = I2C_PRODUCT_INFO_ADDR,
-			.flags  = I2C_M_RD,
-			.buf    = buff,
-	};
-	buff[0] = 0;
-	buff[1] = addrptr;
-	msg.len = I2C_PRODUCT_INFO_ADDR_SIZE + 1;
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
 
+	ret = amdgpu_eeprom_read(&adev->pm.smu_i2c, addrptr, buff, 1);
 	if (ret < 1) {
 		DRM_WARN("FRU: Failed to get size field");
 		return ret;
@@ -83,13 +75,9 @@ static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
 	/* The size returned by the i2c requires subtraction of 0xC0 since the
 	 * size apparently always reports as 0xC0+actual size.
 	 */
-	size = buff[2] - I2C_PRODUCT_INFO_OFFSET;
-	/* Add 1 since address field was 1 byte */
-	buff[1] = addrptr + 1;
-
-	msg.len = I2C_PRODUCT_INFO_ADDR_SIZE + size;
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	size = buff[0] - I2C_PRODUCT_INFO_OFFSET;
 
+	ret = amdgpu_eeprom_read(&adev->pm.smu_i2c, addrptr + 1, buff, size);
 	if (ret < 1) {
 		DRM_WARN("FRU: Failed to get data field");
 		return ret;
@@ -101,8 +89,8 @@ static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
 int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 {
 	unsigned char buff[34];
-	int addrptr, size;
-	int len;
+	u32 addrptr;
+	int size, len;
 
 	if (!is_fru_eeprom_supported(adev))
 		return 0;
@@ -125,7 +113,7 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 	 * Bytes 8-a are all 1-byte and refer to the size of the entire struct,
 	 * and the language field, so just start from 0xb, manufacturer size
 	 */
-	addrptr = 0xb;
+	addrptr = FRU_EEPROM_MADDR + 0xb;
 	size = amdgpu_fru_read_eeprom(adev, addrptr, buff);
 	if (size < 1) {
 		DRM_ERROR("Failed to read FRU Manufacturer, ret:%d", size);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index b36405170ff3..76efd5f8950f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -76,7 +76,7 @@ static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
 	if (adev->dummy_page_addr)
 		return 0;
 	adev->dummy_page_addr = dma_map_page(&adev->pdev->dev, dummy_page, 0,
-					     PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+					     PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(&adev->pdev->dev, adev->dummy_page_addr)) {
 		dev_err(&adev->pdev->dev, "Failed to DMA MAP the dummy page\n");
 		adev->dummy_page_addr = 0;
@@ -96,8 +96,8 @@ void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
 {
 	if (!adev->dummy_page_addr)
 		return;
-	pci_unmap_page(adev->pdev, adev->dummy_page_addr,
-		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_page(&adev->pdev->dev, adev->dummy_page_addr, PAGE_SIZE,
+		       DMA_BIDIRECTIONAL);
 	adev->dummy_page_addr = 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 854fc497844b..cb07cc3b06ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -621,7 +621,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 
 	if (operation == AMDGPU_VA_OP_MAP ||
 	    operation == AMDGPU_VA_OP_REPLACE) {
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			goto error;
 	}
@@ -838,7 +838,8 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	case AMDGPU_GEM_OP_SET_PLACEMENT:
-		if (robj->prime_shared_count && (args->value & AMDGPU_GEM_DOMAIN_VRAM)) {
+		if (robj->tbo.base.import_attach &&
+		    args->value & AMDGPU_GEM_DOMAIN_VRAM) {
 			r = -EINVAL;
 			amdgpu_bo_unreserve(robj);
 			break;
@@ -903,7 +904,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 					 DIV_ROUND_UP(args->bpp, 8), 0);
 	args->size = (u64)args->pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
-	domain = amdgpu_bo_get_preferred_pin_domain(adev,
+	domain = amdgpu_bo_get_preferred_domain(adev,
 				amdgpu_display_supported_domains(adev, flags));
 	r = amdgpu_gem_object_create(adev, args->size, 0, domain, flags,
 				     ttm_bo_type_device, NULL, &gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b4ced45301be..e7f06bd0f0cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -629,7 +629,6 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
 		adev->gfx.ras_if->block = AMDGPU_RAS_BLOCK__GFX;
 		adev->gfx.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->gfx.ras_if->sub_block_index = 0;
-		strcpy(adev->gfx.ras_if->name, "gfx");
 	}
 	fs_info.head = ih_info.head = *adev->gfx.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->gfx.ras_if,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index d0b8d415b63b..c7797eac83c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -471,6 +471,27 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev)
 			return r;
 	}
 
+	if (adev->mca.mp0.ras_funcs &&
+	    adev->mca.mp0.ras_funcs->ras_late_init) {
+		r = adev->mca.mp0.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->mca.mp1.ras_funcs &&
+	    adev->mca.mp1.ras_funcs->ras_late_init) {
+		r = adev->mca.mp1.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->mca.mpio.ras_funcs &&
+	    adev->mca.mpio.ras_funcs->ras_late_init) {
+		r = adev->mca.mpio.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index ec96e0b26b11..543000304a1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -132,14 +132,11 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_gtt_node *node;
 	int r;
 
-	spin_lock(&mgr->lock);
-	if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT &&
-	    atomic64_read(&mgr->available) < num_pages) {
-		spin_unlock(&mgr->lock);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY) &&
+	    atomic64_add_return(num_pages, &mgr->used) >  man->size) {
+		atomic64_sub(num_pages, &mgr->used);
 		return -ENOSPC;
 	}
-	atomic64_sub(num_pages, &mgr->available);
-	spin_unlock(&mgr->lock);
 
 	node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL);
 	if (!node) {
@@ -175,7 +172,8 @@ err_free:
 	kfree(node);
 
 err_out:
-	atomic64_add(num_pages, &mgr->available);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
+		atomic64_sub(num_pages, &mgr->used);
 
 	return r;
 }
@@ -198,7 +196,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 	if (drm_mm_node_allocated(&node->base.mm_nodes[0]))
 		drm_mm_remove_node(&node->base.mm_nodes[0]);
 	spin_unlock(&mgr->lock);
-	atomic64_add(res->num_pages, &mgr->available);
+
+	if (!(res->placement & TTM_PL_FLAG_TEMPORARY))
+		atomic64_sub(res->num_pages, &mgr->used);
 
 	kfree(node);
 }
@@ -213,9 +213,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
-	s64 result = man->size - atomic64_read(&mgr->available);
 
-	return (result > 0 ? result : 0) * PAGE_SIZE;
+	return atomic64_read(&mgr->used) * PAGE_SIZE;
 }
 
 /**
@@ -265,9 +264,8 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
 	drm_mm_print(&mgr->mm, printer);
 	spin_unlock(&mgr->lock);
 
-	drm_printf(printer, "man size:%llu pages, gtt available:%lld pages, usage:%lluMB\n",
-		   man->size, (u64)atomic64_read(&mgr->available),
-		   amdgpu_gtt_mgr_usage(man) >> 20);
+	drm_printf(printer, "man size:%llu pages,  gtt used:%llu pages\n",
+		   man->size, atomic64_read(&mgr->used));
 }
 
 static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
@@ -299,7 +297,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
 	drm_mm_init(&mgr->mm, start, size);
 	spin_lock_init(&mgr->lock);
-	atomic64_set(&mgr->available, gtt_size >> PAGE_SHIFT);
+	atomic64_set(&mgr->used, 0);
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c
index 1d50d534d77c..a766e1aad2b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c
@@ -41,7 +41,6 @@ int amdgpu_hdp_ras_late_init(struct amdgpu_device *adev)
 		adev->hdp.ras_if->block = AMDGPU_RAS_BLOCK__HDP;
 		adev->hdp.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->hdp.ras_if->sub_block_index = 0;
-		strcpy(adev->hdp.ras_if->name, "hdp");
 	}
 	ih_info.head = fs_info.head = *adev->hdp.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->hdp.ras_if,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index bca4dddd5a15..82608df43396 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -339,7 +339,7 @@ static void amdgpu_i2c_put_byte(struct amdgpu_i2c_chan *i2c_bus,
 void
 amdgpu_i2c_router_select_ddc_port(const struct amdgpu_connector *amdgpu_connector)
 {
-	u8 val;
+	u8 val = 0;
 
 	if (!amdgpu_connector->router.ddc_valid)
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index ec65ab0ddf89..c076a6b9a5a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -262,7 +262,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
 	}
 
-	r = amdgpu_fence_emit(ring, f, fence_flags);
+	r = amdgpu_fence_emit(ring, f, job, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
 		if (job && job->vmid)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index cd2e18f072fc..cc2e0c9cfe0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -46,7 +46,6 @@
 #include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_vblank.h>
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_drv.h>
@@ -184,7 +183,7 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev)
  * Returns:
  * result of handling the IRQ, as defined by &irqreturn_t
  */
-irqreturn_t amdgpu_irq_handler(int irq, void *arg)
+static irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct amdgpu_device *adev = drm_to_adev(dev);
@@ -307,6 +306,7 @@ static void amdgpu_restore_msix(struct amdgpu_device *adev)
 int amdgpu_irq_init(struct amdgpu_device *adev)
 {
 	int r = 0;
+	unsigned int irq;
 
 	spin_lock_init(&adev->irq.lock);
 
@@ -349,15 +349,22 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	INIT_WORK(&adev->irq.ih2_work, amdgpu_irq_handle_ih2);
 	INIT_WORK(&adev->irq.ih_soft_work, amdgpu_irq_handle_ih_soft);
 
-	adev->irq.installed = true;
-	/* Use vector 0 for MSI-X */
-	r = drm_irq_install(adev_to_drm(adev), pci_irq_vector(adev->pdev, 0));
+	/* Use vector 0 for MSI-X. */
+	r = pci_irq_vector(adev->pdev, 0);
+	if (r < 0)
+		return r;
+	irq = r;
+
+	/* PCI devices require shared interrupts. */
+	r = request_irq(irq, amdgpu_irq_handler, IRQF_SHARED, adev_to_drm(adev)->driver->name,
+			adev_to_drm(adev));
 	if (r) {
-		adev->irq.installed = false;
 		if (!amdgpu_device_has_dc_support(adev))
 			flush_work(&adev->hotplug_work);
 		return r;
 	}
+	adev->irq.installed = true;
+	adev->irq.irq = irq;
 	adev_to_drm(adev)->max_vblank_count = 0x00ffffff;
 
 	DRM_DEBUG("amdgpu: irq initialized.\n");
@@ -368,7 +375,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
 {
 	if (adev->irq.installed) {
-		drm_irq_uninstall(&adev->ddev);
+		free_irq(adev->irq.irq, adev_to_drm(adev));
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
 			pci_free_irq_vectors(adev->pdev);
@@ -584,7 +591,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 {
 	int i, j, k;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
 		amdgpu_restore_msix(adev);
 
 	for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
@@ -617,7 +624,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -647,7 +654,7 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -678,7 +685,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return false;
 
 	if (type >= src->num_types)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
index 78ad4784cc74..e9f2c11ea416 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
@@ -80,6 +80,7 @@ struct amdgpu_irq_src_funcs {
 
 struct amdgpu_irq {
 	bool				installed;
+	unsigned int			irq;
 	spinlock_t			lock;
 	/* interrupt sources */
 	struct amdgpu_irq_client	client[AMDGPU_IRQ_CLIENTID_MAX];
@@ -100,7 +101,6 @@ struct amdgpu_irq {
 };
 
 void amdgpu_irq_disable_all(struct amdgpu_device *adev);
-irqreturn_t amdgpu_irq_handler(int irq, void *arg);
 
 int amdgpu_irq_init(struct amdgpu_device *adev);
 void amdgpu_irq_fini_sw(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index d33e6d97cc89..de29518673dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -127,11 +127,16 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
+	struct dma_fence *hw_fence;
 	unsigned i;
 
-	/* use sched fence if available */
-	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
+	if (job->hw_fence.ops == NULL)
+		hw_fence = job->external_hw_fence;
+	else
+		hw_fence = &job->hw_fence;
 
+	/* use sched fence if available */
+	f = job->base.s_fence ? &job->base.s_fence->finished : hw_fence;
 	for (i = 0; i < job->num_ibs; ++i)
 		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
@@ -142,20 +147,27 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 
 	drm_sched_job_cleanup(s_job);
 
-	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
-	kfree(job);
+
+    /* only put the hw fence if has embedded fence */
+	if (job->hw_fence.ops != NULL)
+		dma_fence_put(&job->hw_fence);
+	else
+		kfree(job);
 }
 
 void amdgpu_job_free(struct amdgpu_job *job)
 {
 	amdgpu_job_free_resources(job);
-
-	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
-	kfree(job);
+
+	/* only put the hw fence if has embedded fence */
+	if (job->hw_fence.ops != NULL)
+		dma_fence_put(&job->hw_fence);
+	else
+		kfree(job);
 }
 
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
@@ -184,11 +196,14 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
 
 	job->base.sched = &ring->sched;
 	r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, NULL, fence);
-	job->fence = dma_fence_get(*fence);
+	/* record external_hw_fence for direct submit */
+	job->external_hw_fence = dma_fence_get(*fence);
 	if (r)
 		return r;
 
 	amdgpu_job_free(job);
+	dma_fence_put(*fence);
+
 	return 0;
 }
 
@@ -246,10 +261,12 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 		if (r)
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
 	}
-	/* if gpu reset, hw fence will be replaced here */
-	dma_fence_put(job->fence);
-	job->fence = dma_fence_get(fence);
 
+	if (!job->job_run_counter)
+		dma_fence_get(fence);
+	else if (finished->error < 0)
+		dma_fence_put(&job->hw_fence);
+	job->job_run_counter++;
 	amdgpu_job_free_resources(job);
 
 	fence = r ? ERR_PTR(r) : fence;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 81caac9b958a..9e65730193b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -46,7 +46,8 @@ struct amdgpu_job {
 	struct amdgpu_sync	sync;
 	struct amdgpu_sync	sched_sync;
 	struct amdgpu_ib	*ibs;
-	struct dma_fence	*fence; /* the hw fence */
+	struct dma_fence	hw_fence;
+	struct dma_fence	*external_hw_fence;
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
 	uint32_t		num_ibs;
@@ -62,6 +63,9 @@ struct amdgpu_job {
 	/* user fence handling */
 	uint64_t		uf_addr;
 	uint64_t		uf_sequence;
+
+	/* job_run_counter >= 1 means a resubmit job */
+	uint32_t		job_run_counter;
 };
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 8996cb4ed57a..9342aa23ebd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -47,8 +47,6 @@ int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
 {
 	int i;
 
-	cancel_delayed_work_sync(&adev->jpeg.idle_work);
-
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 96ef3f1051d8..7e45640fbee0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -341,27 +341,27 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		switch (query_fw->index) {
 		case TA_FW_TYPE_PSP_XGMI:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_xgmi_ucode_version;
+			fw_info->feature = adev->psp.xgmi.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAS:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_ras_ucode_version;
+			fw_info->feature = adev->psp.ras.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_HDCP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_hdcp_ucode_version;
+			fw_info->feature = adev->psp.hdcp.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_DTM:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_dtm_ucode_version;
+			fw_info->feature = adev->psp.dtm.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_rap_ucode_version;
+			fw_info->feature = adev->psp.rap.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_SECUREDISPLAY:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_securedisplay_ucode_version;
+			fw_info->feature = adev->psp.securedisplay.feature_version;
 			break;
 		default:
 			return -EINVAL;
@@ -374,12 +374,12 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = adev->sdma.instance[query_fw->index].feature_version;
 		break;
 	case AMDGPU_INFO_FW_SOS:
-		fw_info->ver = adev->psp.sos_fw_version;
-		fw_info->feature = adev->psp.sos_feature_version;
+		fw_info->ver = adev->psp.sos.fw_version;
+		fw_info->feature = adev->psp.sos.feature_version;
 		break;
 	case AMDGPU_INFO_FW_ASD:
-		fw_info->ver = adev->psp.asd_fw_version;
-		fw_info->feature = adev->psp.asd_feature_version;
+		fw_info->ver = adev->psp.asd.fw_version;
+		fw_info->feature = adev->psp.asd.feature_version;
 		break;
 	case AMDGPU_INFO_FW_DMCU:
 		fw_info->ver = adev->dm.dmcu_fw_version;
@@ -390,8 +390,8 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = 0;
 		break;
 	case AMDGPU_INFO_FW_TOC:
-		fw_info->ver = adev->psp.toc_fw_version;
-		fw_info->feature = adev->psp.toc_feature_version;
+		fw_info->ver = adev->psp.toc.fw_version;
+		fw_info->feature = adev->psp.toc.feature_version;
 		break;
 	default:
 		return -EINVAL;
@@ -1179,10 +1179,14 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		pasid = 0;
 	}
 
-	r = amdgpu_vm_init(adev, &fpriv->vm, pasid);
+	r = amdgpu_vm_init(adev, &fpriv->vm);
 	if (r)
 		goto error_pasid;
 
+	r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid);
+	if (r)
+		goto error_vm;
+
 	fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL);
 	if (!fpriv->prt_va) {
 		r = -ENOMEM;
@@ -1210,8 +1214,10 @@ error_vm:
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 error_pasid:
-	if (pasid)
+	if (pasid) {
 		amdgpu_pasid_free(pasid);
+		amdgpu_vm_set_pasid(adev, &fpriv->vm, 0);
+	}
 
 	kfree(fpriv);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
new file mode 100644
index 000000000000..a2d3dbbf7d25
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu_ras.h"
+#include "amdgpu.h"
+#include "amdgpu_mca.h"
+
+#include "umc/umc_6_7_0_offset.h"
+#include "umc/umc_6_7_0_sh_mask.h"
+
+void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
+					      uint64_t mc_status_addr,
+					      unsigned long *error_count)
+{
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+
+	if (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
+		*error_count += 1;
+}
+
+void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
+						uint64_t mc_status_addr,
+						unsigned long *error_count)
+{
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+
+	if ((REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
+		*error_count += 1;
+}
+
+void amdgpu_mca_reset_error_count(struct amdgpu_device *adev,
+				  uint64_t mc_status_addr)
+{
+	WREG64_PCIE(mc_status_addr * 4, 0x0ULL);
+}
+
+void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
+				      uint64_t mc_status_addr,
+				      void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+	amdgpu_mca_query_correctable_error_count(adev, mc_status_addr, &(err_data->ce_count));
+	amdgpu_mca_query_uncorrectable_error_count(adev, mc_status_addr, &(err_data->ue_count));
+
+	amdgpu_mca_reset_error_count(adev, mc_status_addr);
+}
+
+int amdgpu_mca_ras_late_init(struct amdgpu_device *adev,
+			     struct amdgpu_mca_ras *mca_dev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = mca_dev->ras_funcs->sysfs_name,
+	};
+
+	if (!mca_dev->ras_if) {
+		mca_dev->ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!mca_dev->ras_if)
+			return -ENOMEM;
+		mca_dev->ras_if->block = mca_dev->ras_funcs->ras_block;
+		mca_dev->ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		mca_dev->ras_if->sub_block_index = 0;
+	}
+	ih_info.head = fs_info.head = *mca_dev->ras_if;
+	r = amdgpu_ras_late_init(adev, mca_dev->ras_if,
+				 &fs_info, &ih_info);
+	if (r || !amdgpu_ras_is_supported(adev, mca_dev->ras_if->block)) {
+		kfree(mca_dev->ras_if);
+		mca_dev->ras_if = NULL;
+	}
+
+	return r;
+}
+
+void amdgpu_mca_ras_fini(struct amdgpu_device *adev,
+			 struct amdgpu_mca_ras *mca_dev)
+{
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+
+	if (!mca_dev->ras_if)
+		return;
+
+	amdgpu_ras_late_fini(adev, mca_dev->ras_if, &ih_info);
+	kfree(mca_dev->ras_if);
+	mca_dev->ras_if = NULL;
+}
\ No newline at end of file
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
new file mode 100644
index 000000000000..f860f2f0e296
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2021  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef __AMDGPU_MCA_H__
+#define __AMDGPU_MCA_H__
+
+struct amdgpu_mca_ras_funcs {
+	int (*ras_late_init)(struct amdgpu_device *adev);
+	void (*ras_fini)(struct amdgpu_device *adev);
+	void (*query_ras_error_count)(struct amdgpu_device *adev,
+				      void *ras_error_status);
+	void (*query_ras_error_address)(struct amdgpu_device *adev,
+					void *ras_error_status);
+	uint32_t ras_block;
+	const char* sysfs_name;
+};
+
+struct amdgpu_mca_ras {
+	struct ras_common_if *ras_if;
+	const struct amdgpu_mca_ras_funcs *ras_funcs;
+};
+
+struct amdgpu_mca_funcs {
+	void (*init)(struct amdgpu_device *adev);
+};
+
+struct amdgpu_mca {
+	const struct amdgpu_mca_funcs *funcs;
+	struct amdgpu_mca_ras mp0;
+	struct amdgpu_mca_ras mp1;
+	struct amdgpu_mca_ras mpio;
+};
+
+void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
+					      uint64_t mc_status_addr,
+					      unsigned long *error_count);
+
+void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
+						uint64_t mc_status_addr,
+						unsigned long *error_count);
+
+void amdgpu_mca_reset_error_count(struct amdgpu_device *adev,
+				  uint64_t mc_status_addr);
+
+void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
+				      uint64_t mc_status_addr,
+				      void *ras_error_status);
+
+int amdgpu_mca_ras_late_init(struct amdgpu_device *adev,
+			     struct amdgpu_mca_ras *mca_dev);
+
+void amdgpu_mca_ras_fini(struct amdgpu_device *adev,
+			 struct amdgpu_mca_ras *mca_dev);
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c
index ead3dc572ec5..24297dc51434 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c
@@ -41,7 +41,6 @@ int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev)
 		adev->mmhub.ras_if->block = AMDGPU_RAS_BLOCK__MMHUB;
 		adev->mmhub.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->mmhub.ras_if->sub_block_index = 0;
-		strcpy(adev->mmhub.ras_if->name, "mmhub");
 	}
 	ih_info.head = fs_info.head = *adev->mmhub.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->mmhub.ras_if,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
index 6201a5f4b4fa..6afb02fef8cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
@@ -39,7 +39,6 @@ int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev)
 		adev->nbio.ras_if->block = AMDGPU_RAS_BLOCK__PCIE_BIF;
 		adev->nbio.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->nbio.ras_if->sub_block_index = 0;
-		strcpy(adev->nbio.ras_if->name, "pcie_bif");
 	}
 	ih_info.head = fs_info.head = *adev->nbio.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->nbio.ras_if,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 45295dce5c3e..843052205bd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -95,6 +95,7 @@ struct amdgpu_nbio_funcs {
 	void (*program_aspm)(struct amdgpu_device *adev);
 	void (*apply_lc_spc_mode_wa)(struct amdgpu_device *adev);
 	void (*apply_l1_link_width_reconfig_wa)(struct amdgpu_device *adev);
+	void (*clear_doorbell_interrupt)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_nbio {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 92c8e6e7f346..01a78c786536 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -196,7 +196,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
-	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+	BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
 
 	placement->num_placement = c;
 	placement->placement = places;
@@ -731,7 +731,7 @@ retry:
 /**
  * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list
  *
- * @bo: BO that will be inserted into the shadow list
+ * @vmbo: BO that will be inserted into the shadow list
  *
  * Insert a BO to the shadow list.
  */
@@ -913,7 +913,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return -EINVAL;
 
 	/* A shared bo cannot be migrated to VRAM */
-	if (bo->prime_shared_count || bo->tbo.base.import_attach) {
+	if (bo->tbo.base.import_attach) {
 		if (domain & AMDGPU_GEM_DOMAIN_GTT)
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 		else
@@ -947,7 +947,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
 	 * See function amdgpu_display_supported_domains()
 	 */
-	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
+	domain = amdgpu_bo_get_preferred_domain(adev, domain);
 
 	if (bo->tbo.base.import_attach)
 		dma_buf_pin(bo->tbo.base.import_attach);
@@ -1518,14 +1518,14 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 }
 
 /**
- * amdgpu_bo_get_preferred_pin_domain - get preferred domain for scanout
+ * amdgpu_bo_get_preferred_domain - get preferred domain
  * @adev: amdgpu device object
  * @domain: allowed :ref:`memory domains <amdgpu_memory_domains>`
  *
  * Returns:
- * Which of the allowed domains is preferred for pinning the BO for scanout.
+ * Which of the allowed domains is preferred for allocating the BO.
  */
-uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
 					    uint32_t domain)
 {
 	if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 38c834d0f930..9d6c001c15f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -100,7 +100,6 @@ struct amdgpu_bo {
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
 	u64				flags;
-	unsigned			prime_shared_count;
 	/* per VM structure for page tables and with virtual addresses */
 	struct amdgpu_vm_bo_base	*vm_bo;
 	/* Constant after initialization */
@@ -334,7 +333,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem,
 void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo);
 int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow,
 			     struct dma_fence **fence);
-uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
 					    uint32_t domain);
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c
index f2e20666c9c1..4eaec446b49d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c
@@ -80,12 +80,17 @@ static void amdgpu_pll_reduce_ratio(unsigned *nom, unsigned *den,
  * Calculate feedback and reference divider for a given post divider. Makes
  * sure we stay within the limits.
  */
-static void amdgpu_pll_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
-				      unsigned fb_div_max, unsigned ref_div_max,
-				      unsigned *fb_div, unsigned *ref_div)
+static void amdgpu_pll_get_fb_ref_div(struct amdgpu_device *adev, unsigned int nom,
+				      unsigned int den, unsigned int post_div,
+				      unsigned int fb_div_max, unsigned int ref_div_max,
+				      unsigned int *fb_div, unsigned int *ref_div)
 {
+
 	/* limit reference * post divider to a maximum */
-	ref_div_max = min(128 / post_div, ref_div_max);
+	if (adev->family == AMDGPU_FAMILY_SI)
+		ref_div_max = min(100 / post_div, ref_div_max);
+	else
+		ref_div_max = min(128 / post_div, ref_div_max);
 
 	/* get matching reference and feedback divider */
 	*ref_div = min(max(DIV_ROUND_CLOSEST(den, post_div), 1u), ref_div_max);
@@ -112,7 +117,8 @@ static void amdgpu_pll_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_
  * Try to calculate the PLL parameters to generate the given frequency:
  * dot_clock = (ref_freq * feedback_div) / (ref_div * post_div)
  */
-void amdgpu_pll_compute(struct amdgpu_pll *pll,
+void amdgpu_pll_compute(struct amdgpu_device *adev,
+			struct amdgpu_pll *pll,
 			u32 freq,
 			u32 *dot_clock_p,
 			u32 *fb_div_p,
@@ -199,7 +205,7 @@ void amdgpu_pll_compute(struct amdgpu_pll *pll,
 
 	for (post_div = post_div_min; post_div <= post_div_max; ++post_div) {
 		unsigned diff;
-		amdgpu_pll_get_fb_ref_div(nom, den, post_div, fb_div_max,
+		amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max,
 					  ref_div_max, &fb_div, &ref_div);
 		diff = abs(target_clock - (pll->reference_freq * fb_div) /
 			(ref_div * post_div));
@@ -214,7 +220,7 @@ void amdgpu_pll_compute(struct amdgpu_pll *pll,
 	post_div = post_div_best;
 
 	/* get the feedback and reference divider for the optimal value */
-	amdgpu_pll_get_fb_ref_div(nom, den, post_div, fb_div_max, ref_div_max,
+	amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max, ref_div_max,
 				  &fb_div, &ref_div);
 
 	/* reduce the numbers to a simpler ratio once more */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.h
index db6136f68b82..44a583d6c9b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.h
@@ -24,7 +24,8 @@
 #ifndef __AMDGPU_PLL_H__
 #define __AMDGPU_PLL_H__
 
-void amdgpu_pll_compute(struct amdgpu_pll *pll,
+void amdgpu_pll_compute(struct amdgpu_device *adev,
+			 struct amdgpu_pll *pll,
 			 u32 freq,
 			 u32 *dot_clock_p,
 			 u32 *fb_div_p,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 3ec5099ffeb6..23efdc672502 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -24,16 +24,17 @@
  */
 
 #include <linux/firmware.h>
-#include <linux/dma-mapping.h>
 #include <drm/drm_drv.h>
 
 #include "amdgpu.h"
 #include "amdgpu_psp.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_xgmi.h"
 #include "soc15_common.h"
 #include "psp_v3_1.h"
 #include "psp_v10_0.h"
 #include "psp_v11_0.h"
+#include "psp_v11_0_8.h"
 #include "psp_v12_0.h"
 #include "psp_v13_0.h"
 
@@ -41,8 +42,6 @@
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_atomfirmware.h"
 
-#include <drm/drm_drv.h>
-
 static int psp_sysfs_init(struct amdgpu_device *adev);
 static void psp_sysfs_fini(struct amdgpu_device *adev);
 
@@ -122,6 +121,12 @@ static int psp_early_init(void *handle)
 		psp_v13_0_set_psp_funcs(psp);
 		psp->autoload_supported = true;
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) {
+			psp_v11_0_8_set_psp_funcs(psp);
+			psp->autoload_supported = false;
+		}
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -247,6 +252,12 @@ static int psp_sw_init(void *handle)
 	struct psp_runtime_boot_cfg_entry boot_cfg_entry;
 	struct psp_memory_training_context *mem_training_ctx = &psp->mem_train_ctx;
 
+	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!psp->cmd) {
+		DRM_ERROR("Failed to allocate memory to command buffer!\n");
+		ret = -ENOMEM;
+	}
+
 	if (!amdgpu_sriov_vf(adev)) {
 		ret = psp_init_microcode(psp);
 		if (ret) {
@@ -309,25 +320,30 @@ static int psp_sw_init(void *handle)
 static int psp_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct psp_context *psp = &adev->psp;
+	struct psp_gfx_cmd_resp *cmd = psp->cmd;
 
-	psp_memory_training_fini(&adev->psp);
-	if (adev->psp.sos_fw) {
-		release_firmware(adev->psp.sos_fw);
-		adev->psp.sos_fw = NULL;
+	psp_memory_training_fini(psp);
+	if (psp->sos_fw) {
+		release_firmware(psp->sos_fw);
+		psp->sos_fw = NULL;
 	}
-	if (adev->psp.asd_fw) {
-		release_firmware(adev->psp.asd_fw);
-		adev->psp.asd_fw = NULL;
+	if (psp->asd_fw) {
+		release_firmware(psp->asd_fw);
+		psp->asd_fw = NULL;
 	}
-	if (adev->psp.ta_fw) {
-		release_firmware(adev->psp.ta_fw);
-		adev->psp.ta_fw = NULL;
+	if (psp->ta_fw) {
+		release_firmware(psp->ta_fw);
+		psp->ta_fw = NULL;
 	}
 
 	if (adev->asic_type == CHIP_NAVI10 ||
 	    adev->asic_type == CHIP_SIENNA_CICHLID)
 		psp_sysfs_fini(adev);
 
+	kfree(cmd);
+	cmd = NULL;
+
 	return 0;
 }
 
@@ -356,6 +372,44 @@ int psp_wait_for(struct psp_context *psp, uint32_t reg_index,
 	return -ETIME;
 }
 
+static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id)
+{
+	switch (cmd_id) {
+	case GFX_CMD_ID_LOAD_TA:
+		return "LOAD_TA";
+	case GFX_CMD_ID_UNLOAD_TA:
+		return "UNLOAD_TA";
+	case GFX_CMD_ID_INVOKE_CMD:
+		return "INVOKE_CMD";
+	case GFX_CMD_ID_LOAD_ASD:
+		return "LOAD_ASD";
+	case GFX_CMD_ID_SETUP_TMR:
+		return "SETUP_TMR";
+	case GFX_CMD_ID_LOAD_IP_FW:
+		return "LOAD_IP_FW";
+	case GFX_CMD_ID_DESTROY_TMR:
+		return "DESTROY_TMR";
+	case GFX_CMD_ID_SAVE_RESTORE:
+		return "SAVE_RESTORE_IP_FW";
+	case GFX_CMD_ID_SETUP_VMR:
+		return "SETUP_VMR";
+	case GFX_CMD_ID_DESTROY_VMR:
+		return "DESTROY_VMR";
+	case GFX_CMD_ID_PROG_REG:
+		return "PROG_REG";
+	case GFX_CMD_ID_GET_FW_ATTESTATION:
+		return "GET_FW_ATTESTATION";
+	case GFX_CMD_ID_LOAD_TOC:
+		return "ID_LOAD_TOC";
+	case GFX_CMD_ID_AUTOLOAD_RLC:
+		return "AUTOLOAD_RLC";
+	case GFX_CMD_ID_BOOT_CFG:
+		return "BOOT_CFG";
+	default:
+		return "UNKNOWN CMD";
+	}
+}
+
 static int
 psp_cmd_submit_buf(struct psp_context *psp,
 		   struct amdgpu_firmware_info *ucode,
@@ -373,8 +427,6 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	if (!drm_dev_enter(&psp->adev->ddev, &idx))
 		return 0;
 
-	mutex_lock(&psp->mutex);
-
 	memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE);
 
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
@@ -417,10 +469,10 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	 */
 	if (!skip_unsupport && (psp->cmd_buf_mem->resp.status || !timeout) && !ras_intr) {
 		if (ucode)
-			DRM_WARN("failed to load ucode id (%d) ",
-				  ucode->ucode_id);
-		DRM_WARN("psp command (0x%X) failed and response status is (0x%X)\n",
-			 psp->cmd_buf_mem->cmd_id,
+			DRM_WARN("failed to load ucode (%s) ",
+				  amdgpu_ucode_name(ucode->ucode_id));
+		DRM_WARN("psp gfx command (%s) failed and response status is (0x%X)\n",
+			 psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id),
 			 psp->cmd_buf_mem->resp.status);
 		if (!timeout) {
 			ret = -EINVAL;
@@ -434,11 +486,26 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	}
 
 exit:
-	mutex_unlock(&psp->mutex);
 	drm_dev_exit(idx);
 	return ret;
 }
 
+static struct psp_gfx_cmd_resp *acquire_psp_cmd_buf(struct psp_context *psp)
+{
+	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+
+	mutex_lock(&psp->mutex);
+
+	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+
+	return cmd;
+}
+
+void release_psp_cmd_buf(struct psp_context *psp)
+{
+	mutex_unlock(&psp->mutex);
+}
+
 static void psp_prep_tmr_cmd_buf(struct psp_context *psp,
 				 struct psp_gfx_cmd_resp *cmd,
 				 uint64_t tmr_mc, struct amdgpu_bo *tmr_bo)
@@ -473,21 +540,20 @@ static int psp_load_toc(struct psp_context *psp,
 			uint32_t *tmr_size)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
 	/* Copy toc to psp firmware private buffer */
-	psp_copy_fw(psp, psp->toc_start_addr, psp->toc_bin_size);
+	psp_copy_fw(psp, psp->toc.start_addr, psp->toc.size_bytes);
 
-	psp_prep_load_toc_cmd_buf(cmd, psp->fw_pri_mc_addr, psp->toc_bin_size);
+	psp_prep_load_toc_cmd_buf(cmd, psp->fw_pri_mc_addr, psp->toc.size_bytes);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 	if (!ret)
 		*tmr_size = psp->cmd_buf_mem->resp.tmr_size;
-	kfree(cmd);
+
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
@@ -511,8 +577,8 @@ static int psp_tmr_init(struct psp_context *psp)
 	/* For ASICs support RLC autoload, psp will parse the toc
 	 * and calculate the total size of TMR needed */
 	if (!amdgpu_sriov_vf(psp->adev) &&
-	    psp->toc_start_addr &&
-	    psp->toc_bin_size &&
+	    psp->toc.start_addr &&
+	    psp->toc.size_bytes &&
 	    psp->fw_pri_buf) {
 		ret = psp_load_toc(psp, &tmr_size);
 		if (ret) {
@@ -552,9 +618,7 @@ static int psp_tmr_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev) && psp_skip_tmr(psp))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_tmr_cmd_buf(psp, cmd, psp->tmr_mc_addr, psp->tmr_bo);
 	DRM_INFO("reserve 0x%lx from 0x%llx for PSP TMR\n",
@@ -563,13 +627,13 @@ static int psp_tmr_load(struct psp_context *psp)
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
 
 static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
-					struct psp_gfx_cmd_resp *cmd)
+				        struct psp_gfx_cmd_resp *cmd)
 {
 	if (amdgpu_sriov_vf(psp->adev))
 		cmd->cmd_id = GFX_CMD_ID_DESTROY_VMR;
@@ -580,11 +644,7 @@ static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
 static int psp_tmr_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_tmr_unload_cmd_buf(psp, cmd);
 	DRM_INFO("free PSP TMR buffer\n");
@@ -592,7 +652,7 @@ static int psp_tmr_unload(struct psp_context *psp)
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -626,9 +686,7 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_GET_FW_ATTESTATION;
 
@@ -640,7 +698,7 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 			      ((uint64_t)cmd->resp.uresp.fwar_db_info.fwar_db_addr_hi << 32);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -648,13 +706,13 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg)
 {
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 	int ret;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
 	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_GET;
@@ -665,47 +723,59 @@ static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg)
 			(cmd->resp.uresp.boot_cfg.boot_cfg & BOOT_CONFIG_GECC) ? 1 : 0;
 	}
 
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
 static int psp_boot_config_set(struct amdgpu_device *adev, uint32_t boot_cfg)
 {
+	int ret;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
 	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_SET;
 	cmd->cmd.boot_cfg.boot_config = boot_cfg;
 	cmd->cmd.boot_cfg.boot_config_valid = boot_cfg;
 
-	return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	release_psp_cmd_buf(psp);
+
+	return ret;
 }
 
 static int psp_rl_load(struct amdgpu_device *adev)
 {
+	int ret;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 
-	if (psp->rl_bin_size == 0)
+	if (!is_psp_fw_valid(psp->rl))
 		return 0;
 
-	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
-	memcpy(psp->fw_pri_buf, psp->rl_start_addr, psp->rl_bin_size);
+	cmd = acquire_psp_cmd_buf(psp);
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
+	memcpy(psp->fw_pri_buf, psp->rl.start_addr, psp->rl.size_bytes);
 
 	cmd->cmd_id = GFX_CMD_ID_LOAD_IP_FW;
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_lo = lower_32_bits(psp->fw_pri_mc_addr);
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_hi = upper_32_bits(psp->fw_pri_mc_addr);
-	cmd->cmd.cmd_load_ip_fw.fw_size = psp->rl_bin_size;
+	cmd->cmd.cmd_load_ip_fw.fw_size = psp->rl.size_bytes;
 	cmd->cmd.cmd_load_ip_fw.fw_type = GFX_FW_TYPE_REG_LIST;
 
-	return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	release_psp_cmd_buf(psp);
+
+	return ret;
 }
 
 static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
@@ -730,17 +800,15 @@ static int psp_asd_load(struct psp_context *psp)
 	 * add workaround to bypass it for sriov now.
 	 * TODO: add version check to make it common
 	 */
-	if (amdgpu_sriov_vf(psp->adev) || !psp->asd_ucode_size)
+	if (amdgpu_sriov_vf(psp->adev) || !psp->asd.size_bytes)
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_copy_fw(psp, psp->asd_start_addr, psp->asd_ucode_size);
+	psp_copy_fw(psp, psp->asd.start_addr, psp->asd.size_bytes);
 
 	psp_prep_asd_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				  psp->asd_ucode_size);
+				  psp->asd.size_bytes);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
@@ -749,7 +817,7 @@ static int psp_asd_load(struct psp_context *psp)
 		psp->asd_context.session_id = cmd->resp.session_id;
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -772,9 +840,7 @@ static int psp_asd_unload(struct psp_context *psp)
 	if (!psp->asd_context.asd_initialized)
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->asd_context.session_id);
 
@@ -783,7 +849,7 @@ static int psp_asd_unload(struct psp_context *psp)
 	if (!ret)
 		psp->asd_context.asd_initialized = false;
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -799,22 +865,21 @@ static void psp_prep_reg_prog_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 		uint32_t value)
 {
-	struct psp_gfx_cmd_resp *cmd = NULL;
+	struct psp_gfx_cmd_resp *cmd;
 	int ret = 0;
 
 	if (reg >= PSP_REG_LAST)
 		return -EINVAL;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_reg_prog_cmd_buf(cmd, reg, value);
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 	if (ret)
 		DRM_ERROR("PSP failed to program reg id %d", reg);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
@@ -834,23 +899,37 @@ static void psp_prep_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 	cmd->cmd.cmd_load_ta.cmd_buf_len	 = ta_shared_size;
 }
 
-static int psp_xgmi_init_shared_buf(struct psp_context *psp)
+static int psp_ta_init_shared_buf(struct psp_context *psp,
+				  struct ta_mem_context *mem_ctx,
+				  uint32_t shared_mem_size)
 {
 	int ret;
 
 	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for xgmi ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_XGMI_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->xgmi_context.xgmi_shared_bo,
-				      &psp->xgmi_context.xgmi_shared_mc_addr,
-				      &psp->xgmi_context.xgmi_shared_buf);
+	* Allocate 16k memory aligned to 4k from Frame Buffer (local
+	* physical) for ta to host memory
+	*/
+	ret = amdgpu_bo_create_kernel(psp->adev, shared_mem_size, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &mem_ctx->shared_bo,
+				      &mem_ctx->shared_mc_addr,
+				      &mem_ctx->shared_buf);
 
 	return ret;
 }
 
+static void psp_ta_free_shared_buf(struct ta_mem_context *mem_ctx)
+{
+	amdgpu_bo_free_kernel(&mem_ctx->shared_bo, &mem_ctx->shared_mc_addr,
+			      &mem_ctx->shared_buf);
+}
+
+static int psp_xgmi_init_shared_buf(struct psp_context *psp)
+{
+	return psp_ta_init_shared_buf(psp, &psp->xgmi_context.context.mem_context,
+				      PSP_XGMI_SHARED_MEM_SIZE);
+}
+
 static void psp_prep_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 				       uint32_t ta_cmd_id,
 				       uint32_t session_id)
@@ -865,18 +944,14 @@ static int psp_ta_invoke(struct psp_context *psp,
 		  uint32_t session_id)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_invoke_cmd_buf(cmd, ta_cmd_id, session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -890,27 +965,25 @@ static int psp_xgmi_load(struct psp_context *psp)
 	 * TODO: bypass the loading in sriov for now
 	 */
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_copy_fw(psp, psp->ta_xgmi_start_addr, psp->ta_xgmi_ucode_size);
+	psp_copy_fw(psp, psp->xgmi.start_addr, psp->xgmi.size_bytes);
 
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_xgmi_ucode_size,
-				 psp->xgmi_context.xgmi_shared_mc_addr,
+				 psp->xgmi.size_bytes,
+				 psp->xgmi_context.context.mem_context.shared_mc_addr,
 				 PSP_XGMI_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->xgmi_context.initialized = 1;
-		psp->xgmi_context.session_id = cmd->resp.session_id;
+		psp->xgmi_context.context.initialized = true;
+		psp->xgmi_context.context.session_id = cmd->resp.session_id;
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -930,57 +1003,56 @@ static int psp_xgmi_unload(struct psp_context *psp)
 	 * TODO: bypass the unloading in sriov for now
 	 */
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_prep_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->xgmi_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
 
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	return psp_ta_invoke(psp, ta_cmd_id, psp->xgmi_context.session_id);
+	return psp_ta_invoke(psp, ta_cmd_id, psp->xgmi_context.context.session_id);
 }
 
 int psp_xgmi_terminate(struct psp_context *psp)
 {
 	int ret;
 
-	if (!psp->xgmi_context.initialized)
+	if (!psp->xgmi_context.context.initialized)
 		return 0;
 
 	ret = psp_xgmi_unload(psp);
 	if (ret)
 		return ret;
 
-	psp->xgmi_context.initialized = 0;
+	psp->xgmi_context.context.initialized = false;
 
 	/* free xgmi shared memory */
-	amdgpu_bo_free_kernel(&psp->xgmi_context.xgmi_shared_bo,
-			&psp->xgmi_context.xgmi_shared_mc_addr,
-			&psp->xgmi_context.xgmi_shared_buf);
+	psp_ta_free_shared_buf(&psp->xgmi_context.context.mem_context);
 
 	return 0;
 }
 
-int psp_xgmi_initialize(struct psp_context *psp)
+int psp_xgmi_initialize(struct psp_context *psp, bool set_extended_data, bool load_ta)
 {
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
-	if (!psp->adev->psp.ta_fw ||
-	    !psp->adev->psp.ta_xgmi_ucode_size ||
-	    !psp->adev->psp.ta_xgmi_start_addr)
+	if (!psp->ta_fw ||
+	    !psp->xgmi.size_bytes ||
+	    !psp->xgmi.start_addr)
 		return -ENOENT;
 
-	if (!psp->xgmi_context.initialized) {
+	if (!load_ta)
+		goto invoke;
+
+	if (!psp->xgmi_context.context.initialized) {
 		ret = psp_xgmi_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -991,9 +1063,11 @@ int psp_xgmi_initialize(struct psp_context *psp)
 	if (ret)
 		return ret;
 
+invoke:
 	/* Initialize XGMI session */
-	xgmi_cmd = (struct ta_xgmi_shared_memory *)(psp->xgmi_context.xgmi_shared_buf);
+	xgmi_cmd = (struct ta_xgmi_shared_memory *)(psp->xgmi_context.context.mem_context.shared_buf);
 	memset(xgmi_cmd, 0, sizeof(struct ta_xgmi_shared_memory));
+	xgmi_cmd->flag_extend_link_record = set_extended_data;
 	xgmi_cmd->cmd_id = TA_COMMAND_XGMI__INITIALIZE;
 
 	ret = psp_xgmi_invoke(psp, xgmi_cmd->cmd_id);
@@ -1006,7 +1080,7 @@ int psp_xgmi_get_hive_id(struct psp_context *psp, uint64_t *hive_id)
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
-	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.xgmi_shared_buf;
+	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.context.mem_context.shared_buf;
 	memset(xgmi_cmd, 0, sizeof(struct ta_xgmi_shared_memory));
 
 	xgmi_cmd->cmd_id = TA_COMMAND_XGMI__GET_HIVE_ID;
@@ -1026,7 +1100,7 @@ int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id)
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
-	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.xgmi_shared_buf;
+	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.context.mem_context.shared_buf;
 	memset(xgmi_cmd, 0, sizeof(struct ta_xgmi_shared_memory));
 
 	xgmi_cmd->cmd_id = TA_COMMAND_XGMI__GET_NODE_ID;
@@ -1041,9 +1115,62 @@ int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id)
 	return 0;
 }
 
+static bool psp_xgmi_peer_link_info_supported(struct psp_context *psp)
+{
+	return psp->adev->asic_type == CHIP_ALDEBARAN &&
+				psp->xgmi.feature_version >= 0x2000000b;
+}
+
+/*
+ * Chips that support extended topology information require the driver to
+ * reflect topology information in the opposite direction.  This is
+ * because the TA has already exceeded its link record limit and if the
+ * TA holds bi-directional information, the driver would have to do
+ * multiple fetches instead of just two.
+ */
+static void psp_xgmi_reflect_topology_info(struct psp_context *psp,
+					struct psp_xgmi_node_info node_info)
+{
+	struct amdgpu_device *mirror_adev;
+	struct amdgpu_hive_info *hive;
+	uint64_t src_node_id = psp->adev->gmc.xgmi.node_id;
+	uint64_t dst_node_id = node_info.node_id;
+	uint8_t dst_num_hops = node_info.num_hops;
+	uint8_t dst_num_links = node_info.num_links;
+
+	hive = amdgpu_get_xgmi_hive(psp->adev);
+	list_for_each_entry(mirror_adev, &hive->device_list, gmc.xgmi.head) {
+		struct psp_xgmi_topology_info *mirror_top_info;
+		int j;
+
+		if (mirror_adev->gmc.xgmi.node_id != dst_node_id)
+			continue;
+
+		mirror_top_info = &mirror_adev->psp.xgmi_context.top_info;
+		for (j = 0; j < mirror_top_info->num_nodes; j++) {
+			if (mirror_top_info->nodes[j].node_id != src_node_id)
+				continue;
+
+			mirror_top_info->nodes[j].num_hops = dst_num_hops;
+			/*
+			 * prevent 0 num_links value re-reflection since reflection
+			 * criteria is based on num_hops (direct or indirect).
+			 *
+			 */
+			if (dst_num_links)
+				mirror_top_info->nodes[j].num_links = dst_num_links;
+
+			break;
+		}
+
+		break;
+	}
+}
+
 int psp_xgmi_get_topology_info(struct psp_context *psp,
 			       int number_devices,
-			       struct psp_xgmi_topology_info *topology)
+			       struct psp_xgmi_topology_info *topology,
+			       bool get_extended_data)
 {
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	struct ta_xgmi_cmd_get_topology_info_input *topology_info_input;
@@ -1054,8 +1181,9 @@ int psp_xgmi_get_topology_info(struct psp_context *psp,
 	if (!topology || topology->num_nodes > TA_XGMI__MAX_CONNECTED_NODES)
 		return -EINVAL;
 
-	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.xgmi_shared_buf;
+	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.context.mem_context.shared_buf;
 	memset(xgmi_cmd, 0, sizeof(struct ta_xgmi_shared_memory));
+	xgmi_cmd->flag_extend_link_record = get_extended_data;
 
 	/* Fill in the shared memory with topology information as input */
 	topology_info_input = &xgmi_cmd->xgmi_in_message.get_topology_info;
@@ -1078,10 +1206,45 @@ int psp_xgmi_get_topology_info(struct psp_context *psp,
 	topology_info_output = &xgmi_cmd->xgmi_out_message.get_topology_info;
 	topology->num_nodes = xgmi_cmd->xgmi_out_message.get_topology_info.num_nodes;
 	for (i = 0; i < topology->num_nodes; i++) {
-		topology->nodes[i].node_id = topology_info_output->nodes[i].node_id;
-		topology->nodes[i].num_hops = topology_info_output->nodes[i].num_hops;
-		topology->nodes[i].is_sharing_enabled = topology_info_output->nodes[i].is_sharing_enabled;
-		topology->nodes[i].sdma_engine = topology_info_output->nodes[i].sdma_engine;
+		/* extended data will either be 0 or equal to non-extended data */
+		if (topology_info_output->nodes[i].num_hops)
+			topology->nodes[i].num_hops = topology_info_output->nodes[i].num_hops;
+
+		/* non-extended data gets everything here so no need to update */
+		if (!get_extended_data) {
+			topology->nodes[i].node_id = topology_info_output->nodes[i].node_id;
+			topology->nodes[i].is_sharing_enabled =
+					topology_info_output->nodes[i].is_sharing_enabled;
+			topology->nodes[i].sdma_engine =
+					topology_info_output->nodes[i].sdma_engine;
+		}
+
+	}
+
+	/* Invoke xgmi ta again to get the link information */
+	if (psp_xgmi_peer_link_info_supported(psp)) {
+		struct ta_xgmi_cmd_get_peer_link_info_output *link_info_output;
+
+		xgmi_cmd->cmd_id = TA_COMMAND_XGMI__GET_PEER_LINKS;
+
+		ret = psp_xgmi_invoke(psp, TA_COMMAND_XGMI__GET_PEER_LINKS);
+
+		if (ret)
+			return ret;
+
+		link_info_output = &xgmi_cmd->xgmi_out_message.get_link_info;
+		for (i = 0; i < topology->num_nodes; i++) {
+			/* accumulate num_links on extended data */
+			topology->nodes[i].num_links = get_extended_data ?
+					topology->nodes[i].num_links +
+							link_info_output->nodes[i].num_links :
+					link_info_output->nodes[i].num_links;
+
+			/* reflect the topology information for bi-directionality */
+			if (psp->xgmi_context.supports_extended_data &&
+					get_extended_data && topology->nodes[i].num_hops)
+				psp_xgmi_reflect_topology_info(psp, topology->nodes[i]);
+		}
 	}
 
 	return 0;
@@ -1098,7 +1261,7 @@ int psp_xgmi_set_topology_info(struct psp_context *psp,
 	if (!topology || topology->num_nodes > TA_XGMI__MAX_CONNECTED_NODES)
 		return -EINVAL;
 
-	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.xgmi_shared_buf;
+	xgmi_cmd = (struct ta_xgmi_shared_memory *)psp->xgmi_context.context.mem_context.shared_buf;
 	memset(xgmi_cmd, 0, sizeof(struct ta_xgmi_shared_memory));
 
 	topology_info_input = &xgmi_cmd->xgmi_in_message.get_topology_info;
@@ -1119,19 +1282,8 @@ int psp_xgmi_set_topology_info(struct psp_context *psp,
 // ras begin
 static int psp_ras_init_shared_buf(struct psp_context *psp)
 {
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for ras ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_RAS_SHARED_MEM_SIZE,
-			PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-			&psp->ras.ras_shared_bo,
-			&psp->ras.ras_shared_mc_addr,
-			&psp->ras.ras_shared_buf);
-
-	return ret;
+	return psp_ta_init_shared_buf(psp, &psp->ras_context.context.mem_context,
+				      PSP_RAS_SHARED_MEM_SIZE);
 }
 
 static int psp_ras_load(struct psp_context *psp)
@@ -1146,42 +1298,40 @@ static int psp_ras_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_copy_fw(psp, psp->ta_ras_start_addr, psp->ta_ras_ucode_size);
+	psp_copy_fw(psp, psp->ras.start_addr, psp->ras.size_bytes);
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras.ras_shared_buf;
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
 
 	if (psp->adev->gmc.xgmi.connected_to_cpu)
 		ras_cmd->ras_in_message.init_flags.poison_mode_en = 1;
 	else
 		ras_cmd->ras_in_message.init_flags.dgpu_mode = 1;
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_ras_ucode_size,
-				 psp->ras.ras_shared_mc_addr,
+				 psp->ras.size_bytes,
+				 psp->ras_context.context.mem_context.shared_mc_addr,
 				 PSP_RAS_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->ras.session_id = cmd->resp.session_id;
+		psp->ras_context.context.session_id = cmd->resp.session_id;
 
 		if (!ras_cmd->ras_status)
-			psp->ras.ras_initialized = true;
+			psp->ras_context.context.initialized = true;
 		else
 			dev_warn(psp->adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
 	}
 
+	release_psp_cmd_buf(psp);
+
 	if (ret || ras_cmd->ras_status)
 		amdgpu_ras_fini(psp->adev);
 
-	kfree(cmd);
-
 	return ret;
 }
 
@@ -1196,16 +1346,14 @@ static int psp_ras_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_prep_ta_unload_cmd_buf(cmd, psp->ras.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->ras_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1215,7 +1363,7 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	struct ta_ras_shared_memory *ras_cmd;
 	int ret;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras.ras_shared_buf;
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
 
 	/*
 	 * TODO: bypass the loading in sriov for now
@@ -1223,7 +1371,7 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	ret = psp_ta_invoke(psp, ta_cmd_id, psp->ras.session_id);
+	ret = psp_ta_invoke(psp, ta_cmd_id, psp->ras_context.context.session_id);
 
 	if (amdgpu_ras_intr_triggered())
 		return ret;
@@ -1279,10 +1427,10 @@ int psp_ras_enable_features(struct psp_context *psp,
 	struct ta_ras_shared_memory *ras_cmd;
 	int ret;
 
-	if (!psp->ras.ras_initialized)
+	if (!psp->ras_context.context.initialized)
 		return -EINVAL;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras.ras_shared_buf;
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
 	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
 
 	if (enable)
@@ -1309,19 +1457,17 @@ static int psp_ras_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->ras.ras_initialized)
+	if (!psp->ras_context.context.initialized)
 		return 0;
 
 	ret = psp_ras_unload(psp);
 	if (ret)
 		return ret;
 
-	psp->ras.ras_initialized = false;
+	psp->ras_context.context.initialized = false;
 
 	/* free ras shared memory */
-	amdgpu_bo_free_kernel(&psp->ras.ras_shared_bo,
-			&psp->ras.ras_shared_mc_addr,
-			&psp->ras.ras_shared_buf);
+	psp_ta_free_shared_buf(&psp->ras_context.context.mem_context);
 
 	return 0;
 }
@@ -1338,8 +1484,8 @@ static int psp_ras_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	if (!adev->psp.ta_ras_ucode_size ||
-	    !adev->psp.ta_ras_start_addr) {
+	if (!adev->psp.ras.size_bytes ||
+	    !adev->psp.ras.start_addr) {
 		dev_info(adev->dev, "RAS: optional ras ta ucode is not available\n");
 		return 0;
 	}
@@ -1385,7 +1531,7 @@ static int psp_ras_initialize(struct psp_context *psp)
 		}
 	}
 
-	if (!psp->ras.ras_initialized) {
+	if (!psp->ras_context.context.initialized) {
 		ret = psp_ras_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -1404,10 +1550,10 @@ int psp_ras_trigger_error(struct psp_context *psp,
 	struct ta_ras_shared_memory *ras_cmd;
 	int ret;
 
-	if (!psp->ras.ras_initialized)
+	if (!psp->ras_context.context.initialized)
 		return -EINVAL;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras.ras_shared_buf;
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
 	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
 
 	ras_cmd->cmd_id = TA_RAS_COMMAND__TRIGGER_ERROR;
@@ -1429,19 +1575,8 @@ int psp_ras_trigger_error(struct psp_context *psp,
 // HDCP start
 static int psp_hdcp_init_shared_buf(struct psp_context *psp)
 {
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for hdcp ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_HDCP_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->hdcp_context.hdcp_shared_bo,
-				      &psp->hdcp_context.hdcp_shared_mc_addr,
-				      &psp->hdcp_context.hdcp_shared_buf);
-
-	return ret;
+	return psp_ta_init_shared_buf(psp, &psp->hdcp_context.context.mem_context,
+				      PSP_HDCP_SHARED_MEM_SIZE);
 }
 
 static int psp_hdcp_load(struct psp_context *psp)
@@ -1455,28 +1590,26 @@ static int psp_hdcp_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	psp_copy_fw(psp, psp->hdcp.start_addr,
+		    psp->hdcp.size_bytes);
 
-	psp_copy_fw(psp, psp->ta_hdcp_start_addr,
-		    psp->ta_hdcp_ucode_size);
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_hdcp_ucode_size,
-				 psp->hdcp_context.hdcp_shared_mc_addr,
+				 psp->hdcp.size_bytes,
+				 psp->hdcp_context.context.mem_context.shared_mc_addr,
 				 PSP_HDCP_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->hdcp_context.hdcp_initialized = true;
-		psp->hdcp_context.session_id = cmd->resp.session_id;
+		psp->hdcp_context.context.initialized = true;
+		psp->hdcp_context.context.session_id = cmd->resp.session_id;
 		mutex_init(&psp->hdcp_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1490,13 +1623,13 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->adev->psp.ta_hdcp_ucode_size ||
-	    !psp->adev->psp.ta_hdcp_start_addr) {
+	if (!psp->hdcp.size_bytes ||
+	    !psp->hdcp.start_addr) {
 		dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n");
 		return 0;
 	}
 
-	if (!psp->hdcp_context.hdcp_initialized) {
+	if (!psp->hdcp_context.context.initialized) {
 		ret = psp_hdcp_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -1520,15 +1653,13 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_prep_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->hdcp_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1541,7 +1672,7 @@ int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	return psp_ta_invoke(psp, ta_cmd_id, psp->hdcp_context.session_id);
+	return psp_ta_invoke(psp, ta_cmd_id, psp->hdcp_context.context.session_id);
 }
 
 static int psp_hdcp_terminate(struct psp_context *psp)
@@ -1554,8 +1685,8 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->hdcp_context.hdcp_initialized) {
-		if (psp->hdcp_context.hdcp_shared_buf)
+	if (!psp->hdcp_context.context.initialized) {
+		if (psp->hdcp_context.context.mem_context.shared_buf)
 			goto out;
 		else
 			return 0;
@@ -1565,13 +1696,11 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->hdcp_context.hdcp_initialized = false;
+	psp->hdcp_context.context.initialized = false;
 
 out:
 	/* free hdcp shared memory */
-	amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
-			      &psp->hdcp_context.hdcp_shared_mc_addr,
-			      &psp->hdcp_context.hdcp_shared_buf);
+	psp_ta_free_shared_buf(&psp->hdcp_context.context.mem_context);
 
 	return 0;
 }
@@ -1580,19 +1709,8 @@ out:
 // DTM start
 static int psp_dtm_init_shared_buf(struct psp_context *psp)
 {
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for dtm ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_DTM_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->dtm_context.dtm_shared_bo,
-				      &psp->dtm_context.dtm_shared_mc_addr,
-				      &psp->dtm_context.dtm_shared_buf);
-
-	return ret;
+	return psp_ta_init_shared_buf(psp, &psp->dtm_context.context.mem_context,
+				      PSP_DTM_SHARED_MEM_SIZE);
 }
 
 static int psp_dtm_load(struct psp_context *psp)
@@ -1606,27 +1724,25 @@ static int psp_dtm_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	psp_copy_fw(psp, psp->dtm.start_addr, psp->dtm.size_bytes);
 
-	psp_copy_fw(psp, psp->ta_dtm_start_addr, psp->ta_dtm_ucode_size);
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_dtm_ucode_size,
-				 psp->dtm_context.dtm_shared_mc_addr,
+				 psp->dtm.size_bytes,
+				 psp->dtm_context.context.mem_context.shared_mc_addr,
 				 PSP_DTM_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->dtm_context.dtm_initialized = true;
-		psp->dtm_context.session_id = cmd->resp.session_id;
+		psp->dtm_context.context.initialized = true;
+		psp->dtm_context.context.session_id = cmd->resp.session_id;
 		mutex_init(&psp->dtm_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1641,13 +1757,13 @@ static int psp_dtm_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->adev->psp.ta_dtm_ucode_size ||
-	    !psp->adev->psp.ta_dtm_start_addr) {
+	if (!psp->dtm.size_bytes ||
+	    !psp->dtm.start_addr) {
 		dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n");
 		return 0;
 	}
 
-	if (!psp->dtm_context.dtm_initialized) {
+	if (!psp->dtm_context.context.initialized) {
 		ret = psp_dtm_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -1671,15 +1787,13 @@ static int psp_dtm_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
-	psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1692,7 +1806,7 @@ int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	return psp_ta_invoke(psp, ta_cmd_id, psp->dtm_context.session_id);
+	return psp_ta_invoke(psp, ta_cmd_id, psp->dtm_context.context.session_id);
 }
 
 static int psp_dtm_terminate(struct psp_context *psp)
@@ -1705,8 +1819,8 @@ static int psp_dtm_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->dtm_context.dtm_initialized) {
-		if (psp->dtm_context.dtm_shared_buf)
+	if (!psp->dtm_context.context.initialized) {
+		if (psp->dtm_context.context.mem_context.shared_buf)
 			goto out;
 		else
 			return 0;
@@ -1716,13 +1830,11 @@ static int psp_dtm_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->dtm_context.dtm_initialized = false;
+	psp->dtm_context.context.initialized = false;
 
 out:
-	/* free hdcp shared memory */
-	amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
-			      &psp->dtm_context.dtm_shared_mc_addr,
-			      &psp->dtm_context.dtm_shared_buf);
+	/* free dtm shared memory */
+	psp_ta_free_shared_buf(&psp->dtm_context.context.mem_context);
 
 	return 0;
 }
@@ -1731,19 +1843,8 @@ out:
 // RAP start
 static int psp_rap_init_shared_buf(struct psp_context *psp)
 {
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for rap ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_RAP_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->rap_context.rap_shared_bo,
-				      &psp->rap_context.rap_shared_mc_addr,
-				      &psp->rap_context.rap_shared_buf);
-
-	return ret;
+	return psp_ta_init_shared_buf(psp, &psp->rap_context.context.mem_context,
+				      PSP_RAP_SHARED_MEM_SIZE);
 }
 
 static int psp_rap_load(struct psp_context *psp)
@@ -1751,27 +1852,25 @@ static int psp_rap_load(struct psp_context *psp)
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	psp_copy_fw(psp, psp->rap.start_addr, psp->rap.size_bytes);
 
-	psp_copy_fw(psp, psp->ta_rap_start_addr, psp->ta_rap_ucode_size);
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_rap_ucode_size,
-				 psp->rap_context.rap_shared_mc_addr,
+				 psp->rap.size_bytes,
+				 psp->rap_context.context.mem_context.shared_mc_addr,
 				 PSP_RAP_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->rap_context.rap_initialized = true;
-		psp->rap_context.session_id = cmd->resp.session_id;
+		psp->rap_context.context.initialized = true;
+		psp->rap_context.context.session_id = cmd->resp.session_id;
 		mutex_init(&psp->rap_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1779,17 +1878,13 @@ static int psp_rap_load(struct psp_context *psp)
 static int psp_rap_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_ta_unload_cmd_buf(cmd, psp->rap_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->rap_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1805,13 +1900,13 @@ static int psp_rap_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->adev->psp.ta_rap_ucode_size ||
-	    !psp->adev->psp.ta_rap_start_addr) {
+	if (!psp->rap.size_bytes ||
+	    !psp->rap.start_addr) {
 		dev_info(psp->adev->dev, "RAP: optional rap ta ucode is not available\n");
 		return 0;
 	}
 
-	if (!psp->rap_context.rap_initialized) {
+	if (!psp->rap_context.context.initialized) {
 		ret = psp_rap_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -1825,11 +1920,9 @@ static int psp_rap_initialize(struct psp_context *psp)
 	if (ret || status != TA_RAP_STATUS__SUCCESS) {
 		psp_rap_unload(psp);
 
-		amdgpu_bo_free_kernel(&psp->rap_context.rap_shared_bo,
-			      &psp->rap_context.rap_shared_mc_addr,
-			      &psp->rap_context.rap_shared_buf);
+		psp_ta_free_shared_buf(&psp->rap_context.context.mem_context);
 
-		psp->rap_context.rap_initialized = false;
+		psp->rap_context.context.initialized = false;
 
 		dev_warn(psp->adev->dev, "RAP TA initialize fail (%d) status %d.\n",
 			 ret, status);
@@ -1844,17 +1937,15 @@ static int psp_rap_terminate(struct psp_context *psp)
 {
 	int ret;
 
-	if (!psp->rap_context.rap_initialized)
+	if (!psp->rap_context.context.initialized)
 		return 0;
 
 	ret = psp_rap_unload(psp);
 
-	psp->rap_context.rap_initialized = false;
+	psp->rap_context.context.initialized = false;
 
 	/* free rap shared memory */
-	amdgpu_bo_free_kernel(&psp->rap_context.rap_shared_bo,
-			      &psp->rap_context.rap_shared_mc_addr,
-			      &psp->rap_context.rap_shared_buf);
+	psp_ta_free_shared_buf(&psp->rap_context.context.mem_context);
 
 	return ret;
 }
@@ -1864,7 +1955,7 @@ int psp_rap_invoke(struct psp_context *psp, uint32_t ta_cmd_id, enum ta_rap_stat
 	struct ta_rap_shared_memory *rap_cmd;
 	int ret = 0;
 
-	if (!psp->rap_context.rap_initialized)
+	if (!psp->rap_context.context.initialized)
 		return 0;
 
 	if (ta_cmd_id != TA_CMD_RAP__INITIALIZE &&
@@ -1874,13 +1965,13 @@ int psp_rap_invoke(struct psp_context *psp, uint32_t ta_cmd_id, enum ta_rap_stat
 	mutex_lock(&psp->rap_context.mutex);
 
 	rap_cmd = (struct ta_rap_shared_memory *)
-		  psp->rap_context.rap_shared_buf;
+		  psp->rap_context.context.mem_context.shared_buf;
 	memset(rap_cmd, 0, sizeof(struct ta_rap_shared_memory));
 
 	rap_cmd->cmd_id = ta_cmd_id;
 	rap_cmd->validation_method_id = METHOD_A;
 
-	ret = psp_ta_invoke(psp, rap_cmd->cmd_id, psp->rap_context.session_id);
+	ret = psp_ta_invoke(psp, rap_cmd->cmd_id, psp->rap_context.context.session_id);
 	if (ret)
 		goto out_unlock;
 
@@ -1897,67 +1988,48 @@ out_unlock:
 /* securedisplay start */
 static int psp_securedisplay_init_shared_buf(struct psp_context *psp)
 {
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for sa ta <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_SECUREDISPLAY_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->securedisplay_context.securedisplay_shared_bo,
-				      &psp->securedisplay_context.securedisplay_shared_mc_addr,
-				      &psp->securedisplay_context.securedisplay_shared_buf);
-
-	return ret;
+	return psp_ta_init_shared_buf(
+		psp, &psp->securedisplay_context.context.mem_context,
+		PSP_SECUREDISPLAY_SHARED_MEM_SIZE);
 }
 
 static int psp_securedisplay_load(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
-	memcpy(psp->fw_pri_buf, psp->ta_securedisplay_start_addr, psp->ta_securedisplay_ucode_size);
+	memcpy(psp->fw_pri_buf, psp->securedisplay.start_addr, psp->securedisplay.size_bytes);
 
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
-				 psp->ta_securedisplay_ucode_size,
-				 psp->securedisplay_context.securedisplay_shared_mc_addr,
+				 psp->securedisplay.size_bytes,
+				 psp->securedisplay_context.context.mem_context.shared_mc_addr,
 				 PSP_SECUREDISPLAY_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	if (ret)
-		goto failed;
+	if (!ret) {
+		psp->securedisplay_context.context.initialized = true;
+		psp->securedisplay_context.context.session_id = cmd->resp.session_id;
+		mutex_init(&psp->securedisplay_context.mutex);
+	}
 
-	psp->securedisplay_context.securedisplay_initialized = true;
-	psp->securedisplay_context.session_id = cmd->resp.session_id;
-	mutex_init(&psp->securedisplay_context.mutex);
+	release_psp_cmd_buf(psp);
 
-failed:
-	kfree(cmd);
 	return ret;
 }
 
 static int psp_securedisplay_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	psp_prep_ta_unload_cmd_buf(cmd, psp->securedisplay_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->securedisplay_context.context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1973,13 +2045,13 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->adev->psp.ta_securedisplay_ucode_size ||
-	    !psp->adev->psp.ta_securedisplay_start_addr) {
+	if (!psp->securedisplay.size_bytes ||
+	    !psp->securedisplay.start_addr) {
 		dev_info(psp->adev->dev, "SECUREDISPLAY: securedisplay ta ucode is not available\n");
 		return 0;
 	}
 
-	if (!psp->securedisplay_context.securedisplay_initialized) {
+	if (!psp->securedisplay_context.context.initialized) {
 		ret = psp_securedisplay_init_shared_buf(psp);
 		if (ret)
 			return ret;
@@ -1996,11 +2068,9 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (ret) {
 		psp_securedisplay_unload(psp);
 
-		amdgpu_bo_free_kernel(&psp->securedisplay_context.securedisplay_shared_bo,
-			      &psp->securedisplay_context.securedisplay_shared_mc_addr,
-			      &psp->securedisplay_context.securedisplay_shared_buf);
+		psp_ta_free_shared_buf(&psp->securedisplay_context.context.mem_context);
 
-		psp->securedisplay_context.securedisplay_initialized = false;
+		psp->securedisplay_context.context.initialized = false;
 
 		dev_err(psp->adev->dev, "SECUREDISPLAY TA initialize fail.\n");
 		return -EINVAL;
@@ -2025,19 +2095,17 @@ static int psp_securedisplay_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->securedisplay_context.securedisplay_initialized)
+	if (!psp->securedisplay_context.context.initialized)
 		return 0;
 
 	ret = psp_securedisplay_unload(psp);
 	if (ret)
 		return ret;
 
-	psp->securedisplay_context.securedisplay_initialized = false;
+	psp->securedisplay_context.context.initialized = false;
 
 	/* free securedisplay shared memory */
-	amdgpu_bo_free_kernel(&psp->securedisplay_context.securedisplay_shared_bo,
-			      &psp->securedisplay_context.securedisplay_shared_mc_addr,
-			      &psp->securedisplay_context.securedisplay_shared_buf);
+	psp_ta_free_shared_buf(&psp->securedisplay_context.context.mem_context);
 
 	return ret;
 }
@@ -2046,7 +2114,7 @@ int psp_securedisplay_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
 	int ret;
 
-	if (!psp->securedisplay_context.securedisplay_initialized)
+	if (!psp->securedisplay_context.context.initialized)
 		return -EINVAL;
 
 	if (ta_cmd_id != TA_SECUREDISPLAY_COMMAND__QUERY_TA &&
@@ -2055,7 +2123,7 @@ int psp_securedisplay_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 
 	mutex_lock(&psp->securedisplay_context.mutex);
 
-	ret = psp_ta_invoke(psp, ta_cmd_id, psp->securedisplay_context.session_id);
+	ret = psp_ta_invoke(psp, ta_cmd_id, psp->securedisplay_context.context.session_id);
 
 	mutex_unlock(&psp->securedisplay_context.mutex);
 
@@ -2069,7 +2137,7 @@ static int psp_hw_start(struct psp_context *psp)
 	int ret;
 
 	if (!amdgpu_sriov_vf(adev)) {
-		if (psp->kdb_bin_size &&
+		if ((is_psp_fw_valid(psp->kdb)) &&
 		    (psp->funcs->bootloader_load_kdb != NULL)) {
 			ret = psp_bootloader_load_kdb(psp);
 			if (ret) {
@@ -2078,7 +2146,8 @@ static int psp_hw_start(struct psp_context *psp)
 			}
 		}
 
-		if (psp->spl_bin_size) {
+		if ((is_psp_fw_valid(psp->spl)) &&
+		    (psp->funcs->bootloader_load_spl != NULL)) {
 			ret = psp_bootloader_load_spl(psp);
 			if (ret) {
 				DRM_ERROR("PSP load spl failed!\n");
@@ -2086,16 +2155,49 @@ static int psp_hw_start(struct psp_context *psp)
 			}
 		}
 
-		ret = psp_bootloader_load_sysdrv(psp);
-		if (ret) {
-			DRM_ERROR("PSP load sysdrv failed!\n");
-			return ret;
+		if ((is_psp_fw_valid(psp->sys)) &&
+		    (psp->funcs->bootloader_load_sysdrv != NULL)) {
+			ret = psp_bootloader_load_sysdrv(psp);
+			if (ret) {
+				DRM_ERROR("PSP load sys drv failed!\n");
+				return ret;
+			}
 		}
 
-		ret = psp_bootloader_load_sos(psp);
-		if (ret) {
-			DRM_ERROR("PSP load sos failed!\n");
-			return ret;
+		if ((is_psp_fw_valid(psp->soc_drv)) &&
+		    (psp->funcs->bootloader_load_soc_drv != NULL)) {
+			ret = psp_bootloader_load_soc_drv(psp);
+			if (ret) {
+				DRM_ERROR("PSP load soc drv failed!\n");
+				return ret;
+			}
+		}
+
+		if ((is_psp_fw_valid(psp->intf_drv)) &&
+		    (psp->funcs->bootloader_load_intf_drv != NULL)) {
+			ret = psp_bootloader_load_intf_drv(psp);
+			if (ret) {
+				DRM_ERROR("PSP load intf drv failed!\n");
+				return ret;
+			}
+		}
+
+		if ((is_psp_fw_valid(psp->dbg_drv)) &&
+		    (psp->funcs->bootloader_load_dbg_drv != NULL)) {
+			ret = psp_bootloader_load_dbg_drv(psp);
+			if (ret) {
+				DRM_ERROR("PSP load dbg drv failed!\n");
+				return ret;
+			}
+		}
+
+		if ((is_psp_fw_valid(psp->sos)) &&
+		    (psp->funcs->bootloader_load_sos != NULL)) {
+			ret = psp_bootloader_load_sos(psp);
+			if (ret) {
+				DRM_ERROR("PSP load sos failed!\n");
+				return ret;
+			}
 		}
 	}
 
@@ -2299,8 +2401,6 @@ static int psp_prep_load_ip_fw_cmd_buf(struct amdgpu_firmware_info *ucode,
 	int ret;
 	uint64_t fw_mem_mc_addr = ucode->mc_addr;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
-
 	cmd->cmd_id = GFX_CMD_ID_LOAD_IP_FW;
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_lo = lower_32_bits(fw_mem_mc_addr);
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_hi = upper_32_bits(fw_mem_mc_addr);
@@ -2313,17 +2413,19 @@ static int psp_prep_load_ip_fw_cmd_buf(struct amdgpu_firmware_info *ucode,
 	return ret;
 }
 
-static int psp_execute_np_fw_load(struct psp_context *psp,
+static int psp_execute_non_psp_fw_load(struct psp_context *psp,
 			          struct amdgpu_firmware_info *ucode)
 {
 	int ret = 0;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	ret = psp_prep_load_ip_fw_cmd_buf(ucode, psp->cmd);
-	if (ret)
-		return ret;
+	ret = psp_prep_load_ip_fw_cmd_buf(ucode, cmd);
+	if (!ret) {
+		ret = psp_cmd_submit_buf(psp, ucode, cmd,
+					 psp->fence_buf_mc_addr);
+	}
 
-	ret = psp_cmd_submit_buf(psp, ucode, psp->cmd,
-				 psp->fence_buf_mc_addr);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -2334,7 +2436,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 	struct amdgpu_device *adev = psp->adev;
 	struct amdgpu_firmware_info *ucode =
 			&adev->firmware.ucode[AMDGPU_UCODE_ID_SMC];
-	struct amdgpu_ras *ras = psp->ras.ras;
+	struct amdgpu_ras *ras = psp->ras_context.ras;
 
 	if (!ucode->fw || amdgpu_sriov_vf(psp->adev))
 		return 0;
@@ -2349,7 +2451,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 		}
 	}
 
-	ret = psp_execute_np_fw_load(psp, ucode);
+	ret = psp_execute_non_psp_fw_load(psp, ucode);
 
 	if (ret)
 		DRM_ERROR("PSP load smu failed!\n");
@@ -2404,14 +2506,14 @@ int psp_load_fw_list(struct psp_context *psp,
 	for (i = 0; i < ucode_count; ++i) {
 		ucode = ucode_list[i];
 		psp_print_fw_hdr(psp, ucode);
-		ret = psp_execute_np_fw_load(psp, ucode);
+		ret = psp_execute_non_psp_fw_load(psp, ucode);
 		if (ret)
 			return ret;
 	}
 	return ret;
 }
 
-static int psp_np_fw_load(struct psp_context *psp)
+static int psp_load_non_psp_fw(struct psp_context *psp)
 {
 	int i, ret;
 	struct amdgpu_firmware_info *ucode;
@@ -2450,7 +2552,7 @@ static int psp_np_fw_load(struct psp_context *psp)
 
 		psp_print_fw_hdr(psp, ucode);
 
-		ret = psp_execute_np_fw_load(psp, ucode);
+		ret = psp_execute_non_psp_fw_load(psp, ucode);
 		if (ret)
 			return ret;
 
@@ -2478,10 +2580,6 @@ static int psp_load_fw(struct amdgpu_device *adev)
 		goto skip_memalloc;
 	}
 
-	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!psp->cmd)
-		return -ENOMEM;
-
 	if (amdgpu_sriov_vf(adev)) {
 		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
 						AMDGPU_GEM_DOMAIN_VRAM,
@@ -2527,7 +2625,7 @@ skip_memalloc:
 	if (ret)
 		goto failed;
 
-	ret = psp_np_fw_load(psp);
+	ret = psp_load_non_psp_fw(psp);
 	if (ret)
 		goto failed;
 
@@ -2543,7 +2641,7 @@ skip_memalloc:
 		return ret;
 	}
 
-	if (psp->adev->psp.ta_fw) {
+	if (psp->ta_fw) {
 		ret = psp_ras_initialize(psp);
 		if (ret)
 			dev_err(psp->adev->dev,
@@ -2615,7 +2713,7 @@ static int psp_hw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
 
-	if (psp->adev->psp.ta_fw) {
+	if (psp->ta_fw) {
 		psp_ras_terminate(psp);
 		psp_securedisplay_terminate(psp);
 		psp_rap_terminate(psp);
@@ -2635,9 +2733,6 @@ static int psp_hw_fini(void *handle)
 	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
 			      (void **)&psp->cmd_buf_mem);
 
-	kfree(psp->cmd);
-	psp->cmd = NULL;
-
 	return 0;
 }
 
@@ -2648,7 +2743,7 @@ static int psp_suspend(void *handle)
 	struct psp_context *psp = &adev->psp;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1 &&
-	    psp->xgmi_context.initialized == 1) {
+	    psp->xgmi_context.context.initialized) {
 		ret = psp_xgmi_terminate(psp);
 		if (ret) {
 			DRM_ERROR("Failed to terminate xgmi ta\n");
@@ -2656,7 +2751,7 @@ static int psp_suspend(void *handle)
 		}
 	}
 
-	if (psp->adev->psp.ta_fw) {
+	if (psp->ta_fw) {
 		ret = psp_ras_terminate(psp);
 		if (ret) {
 			DRM_ERROR("Failed to terminate ras ta\n");
@@ -2727,7 +2822,7 @@ static int psp_resume(void *handle)
 	if (ret)
 		goto failed;
 
-	ret = psp_np_fw_load(psp);
+	ret = psp_load_non_psp_fw(psp);
 	if (ret)
 		goto failed;
 
@@ -2738,7 +2833,7 @@ static int psp_resume(void *handle)
 	}
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1) {
-		ret = psp_xgmi_initialize(psp);
+		ret = psp_xgmi_initialize(psp, false, true);
 		/* Warning the XGMI seesion initialize failure
 		 * Instead of stop driver initialization
 		 */
@@ -2747,7 +2842,7 @@ static int psp_resume(void *handle)
 				"XGMI: Failed to initialize XGMI session\n");
 	}
 
-	if (psp->adev->psp.ta_fw) {
+	if (psp->ta_fw) {
 		ret = psp_ras_initialize(psp);
 		if (ret)
 			dev_err(psp->adev->dev,
@@ -2801,17 +2896,15 @@ int psp_gpu_reset(struct amdgpu_device *adev)
 int psp_rlc_autoload_start(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_AUTOLOAD_RLC;
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
-	kfree(cmd);
+
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
@@ -2825,7 +2918,7 @@ int psp_update_vcn_sram(struct amdgpu_device *adev, int inst_idx,
 	ucode.mc_addr = cmd_gpu_addr;
 	ucode.ucode_size = cmd_size;
 
-	return psp_execute_np_fw_load(&adev->psp, &ucode);
+	return psp_execute_non_psp_fw_load(&adev->psp, &ucode);
 }
 
 int psp_ring_cmd_submit(struct psp_context *psp,
@@ -2901,10 +2994,10 @@ int psp_init_asd_microcode(struct psp_context *psp,
 		goto out;
 
 	asd_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.asd_fw->data;
-	adev->psp.asd_fw_version = le32_to_cpu(asd_hdr->header.ucode_version);
-	adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->sos.fw_version);
-	adev->psp.asd_ucode_size = le32_to_cpu(asd_hdr->header.ucode_size_bytes);
-	adev->psp.asd_start_addr = (uint8_t *)asd_hdr +
+	adev->psp.asd.fw_version = le32_to_cpu(asd_hdr->header.ucode_version);
+	adev->psp.asd.feature_version = le32_to_cpu(asd_hdr->sos.fw_version);
+	adev->psp.asd.size_bytes = le32_to_cpu(asd_hdr->header.ucode_size_bytes);
+	adev->psp.asd.start_addr = (uint8_t *)asd_hdr +
 				le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes);
 	return 0;
 out:
@@ -2918,7 +3011,7 @@ int psp_init_toc_microcode(struct psp_context *psp,
 			   const char *chip_name)
 {
 	struct amdgpu_device *adev = psp->adev;
-	char fw_name[30];
+	char fw_name[PSP_FW_NAME_LEN];
 	const struct psp_firmware_header_v1_0 *toc_hdr;
 	int err = 0;
 
@@ -2937,10 +3030,10 @@ int psp_init_toc_microcode(struct psp_context *psp,
 		goto out;
 
 	toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data;
-	adev->psp.toc_fw_version = le32_to_cpu(toc_hdr->header.ucode_version);
-	adev->psp.toc_feature_version = le32_to_cpu(toc_hdr->sos.fw_version);
-	adev->psp.toc_bin_size = le32_to_cpu(toc_hdr->header.ucode_size_bytes);
-	adev->psp.toc_start_addr = (uint8_t *)toc_hdr +
+	adev->psp.toc.fw_version = le32_to_cpu(toc_hdr->header.ucode_version);
+	adev->psp.toc.feature_version = le32_to_cpu(toc_hdr->sos.fw_version);
+	adev->psp.toc.size_bytes = le32_to_cpu(toc_hdr->header.ucode_size_bytes);
+	adev->psp.toc.start_addr = (uint8_t *)toc_hdr +
 				le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes);
 	return 0;
 out:
@@ -2950,6 +3043,82 @@ out:
 	return err;
 }
 
+static int parse_sos_bin_descriptor(struct psp_context *psp,
+				   const struct psp_fw_bin_desc *desc,
+				   const struct psp_firmware_header_v2_0 *sos_hdr)
+{
+	uint8_t *ucode_start_addr  = NULL;
+
+	if (!psp || !desc || !sos_hdr)
+		return -EINVAL;
+
+	ucode_start_addr  = (uint8_t *)sos_hdr +
+			    le32_to_cpu(desc->offset_bytes) +
+			    le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes);
+
+	switch (desc->fw_type) {
+	case PSP_FW_TYPE_PSP_SOS:
+		psp->sos.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->sos.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->sos.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->sos.start_addr 	   = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_SYS_DRV:
+		psp->sys.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->sys.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->sys.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->sys.start_addr        = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_KDB:
+		psp->kdb.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->kdb.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->kdb.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->kdb.start_addr        = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_TOC:
+		psp->toc.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->toc.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->toc.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->toc.start_addr        = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_SPL:
+		psp->spl.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->spl.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->spl.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->spl.start_addr        = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_RL:
+		psp->rl.fw_version         = le32_to_cpu(desc->fw_version);
+		psp->rl.feature_version    = le32_to_cpu(desc->fw_version);
+		psp->rl.size_bytes         = le32_to_cpu(desc->size_bytes);
+		psp->rl.start_addr         = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_SOC_DRV:
+		psp->soc_drv.fw_version         = le32_to_cpu(desc->fw_version);
+		psp->soc_drv.feature_version    = le32_to_cpu(desc->fw_version);
+		psp->soc_drv.size_bytes         = le32_to_cpu(desc->size_bytes);
+		psp->soc_drv.start_addr         = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_INTF_DRV:
+		psp->intf_drv.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->intf_drv.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->intf_drv.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->intf_drv.start_addr        = ucode_start_addr;
+		break;
+	case PSP_FW_TYPE_PSP_DBG_DRV:
+		psp->dbg_drv.fw_version         = le32_to_cpu(desc->fw_version);
+		psp->dbg_drv.feature_version    = le32_to_cpu(desc->fw_version);
+		psp->dbg_drv.size_bytes         = le32_to_cpu(desc->size_bytes);
+		psp->dbg_drv.start_addr         = ucode_start_addr;
+		break;
+	default:
+		dev_warn(psp->adev->dev, "Unsupported PSP FW type: %d\n", desc->fw_type);
+		break;
+	}
+
+	return 0;
+}
+
 static int psp_init_sos_base_fw(struct amdgpu_device *adev)
 {
 	const struct psp_firmware_header_v1_0 *sos_hdr;
@@ -2961,32 +3130,34 @@ static int psp_init_sos_base_fw(struct amdgpu_device *adev)
 		le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes);
 
 	if (adev->gmc.xgmi.connected_to_cpu || (adev->asic_type != CHIP_ALDEBARAN)) {
-		adev->psp.sos_fw_version = le32_to_cpu(sos_hdr->header.ucode_version);
-		adev->psp.sos_feature_version = le32_to_cpu(sos_hdr->sos.fw_version);
+		adev->psp.sos.fw_version = le32_to_cpu(sos_hdr->header.ucode_version);
+		adev->psp.sos.feature_version = le32_to_cpu(sos_hdr->sos.fw_version);
 
-		adev->psp.sys_bin_size = le32_to_cpu(sos_hdr->sos.offset_bytes);
-		adev->psp.sys_start_addr = ucode_array_start_addr;
+		adev->psp.sys.size_bytes = le32_to_cpu(sos_hdr->sos.offset_bytes);
+		adev->psp.sys.start_addr = ucode_array_start_addr;
 
-		adev->psp.sos_bin_size = le32_to_cpu(sos_hdr->sos.size_bytes);
-		adev->psp.sos_start_addr = ucode_array_start_addr +
+		adev->psp.sos.size_bytes = le32_to_cpu(sos_hdr->sos.size_bytes);
+		adev->psp.sos.start_addr = ucode_array_start_addr +
 				le32_to_cpu(sos_hdr->sos.offset_bytes);
+		adev->psp.xgmi_context.supports_extended_data = false;
 	} else {
 		/* Load alternate PSP SOS FW */
 		sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data;
 
-		adev->psp.sos_fw_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
-		adev->psp.sos_feature_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
+		adev->psp.sos.fw_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
+		adev->psp.sos.feature_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
 
-		adev->psp.sys_bin_size = le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.size_bytes);
-		adev->psp.sys_start_addr = ucode_array_start_addr +
+		adev->psp.sys.size_bytes = le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.size_bytes);
+		adev->psp.sys.start_addr = ucode_array_start_addr +
 			le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.offset_bytes);
 
-		adev->psp.sos_bin_size = le32_to_cpu(sos_hdr_v1_3->sos_aux.size_bytes);
-		adev->psp.sos_start_addr = ucode_array_start_addr +
+		adev->psp.sos.size_bytes = le32_to_cpu(sos_hdr_v1_3->sos_aux.size_bytes);
+		adev->psp.sos.start_addr = ucode_array_start_addr +
 			le32_to_cpu(sos_hdr_v1_3->sos_aux.offset_bytes);
+		adev->psp.xgmi_context.supports_extended_data = true;
 	}
 
-	if ((adev->psp.sys_bin_size == 0) || (adev->psp.sos_bin_size == 0)) {
+	if ((adev->psp.sys.size_bytes == 0) || (adev->psp.sos.size_bytes == 0)) {
 		dev_warn(adev->dev, "PSP SOS FW not available");
 		return -EINVAL;
 	}
@@ -3003,8 +3174,10 @@ int psp_init_sos_microcode(struct psp_context *psp,
 	const struct psp_firmware_header_v1_1 *sos_hdr_v1_1;
 	const struct psp_firmware_header_v1_2 *sos_hdr_v1_2;
 	const struct psp_firmware_header_v1_3 *sos_hdr_v1_3;
+	const struct psp_firmware_header_v2_0 *sos_hdr_v2_0;
 	int err = 0;
 	uint8_t *ucode_array_start_addr;
+	int fw_index = 0;
 
 	if (!chip_name) {
 		dev_err(adev->dev, "invalid chip name for sos microcode\n");
@@ -3033,35 +3206,52 @@ int psp_init_sos_microcode(struct psp_context *psp,
 
 		if (sos_hdr->header.header_version_minor == 1) {
 			sos_hdr_v1_1 = (const struct psp_firmware_header_v1_1 *)adev->psp.sos_fw->data;
-			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_1->toc.size_bytes);
-			adev->psp.toc_start_addr = (uint8_t *)adev->psp.sys_start_addr +
+			adev->psp.toc.size_bytes = le32_to_cpu(sos_hdr_v1_1->toc.size_bytes);
+			adev->psp.toc.start_addr = (uint8_t *)adev->psp.sys.start_addr +
 					le32_to_cpu(sos_hdr_v1_1->toc.offset_bytes);
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_1->kdb.size_bytes);
-			adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr +
+			adev->psp.kdb.size_bytes = le32_to_cpu(sos_hdr_v1_1->kdb.size_bytes);
+			adev->psp.kdb.start_addr = (uint8_t *)adev->psp.sys.start_addr +
 					le32_to_cpu(sos_hdr_v1_1->kdb.offset_bytes);
 		}
 		if (sos_hdr->header.header_version_minor == 2) {
 			sos_hdr_v1_2 = (const struct psp_firmware_header_v1_2 *)adev->psp.sos_fw->data;
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_2->kdb.size_bytes);
-			adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr +
+			adev->psp.kdb.size_bytes = le32_to_cpu(sos_hdr_v1_2->kdb.size_bytes);
+			adev->psp.kdb.start_addr = (uint8_t *)adev->psp.sys.start_addr +
 						    le32_to_cpu(sos_hdr_v1_2->kdb.offset_bytes);
 		}
 		if (sos_hdr->header.header_version_minor == 3) {
 			sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data;
-			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.toc.size_bytes);
-			adev->psp.toc_start_addr = ucode_array_start_addr +
+			adev->psp.toc.size_bytes = le32_to_cpu(sos_hdr_v1_3->v1_1.toc.size_bytes);
+			adev->psp.toc.start_addr = ucode_array_start_addr +
 				le32_to_cpu(sos_hdr_v1_3->v1_1.toc.offset_bytes);
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.size_bytes);
-			adev->psp.kdb_start_addr = ucode_array_start_addr +
+			adev->psp.kdb.size_bytes = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.size_bytes);
+			adev->psp.kdb.start_addr = ucode_array_start_addr +
 				le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.offset_bytes);
-			adev->psp.spl_bin_size = le32_to_cpu(sos_hdr_v1_3->spl.size_bytes);
-			adev->psp.spl_start_addr = ucode_array_start_addr +
+			adev->psp.spl.size_bytes = le32_to_cpu(sos_hdr_v1_3->spl.size_bytes);
+			adev->psp.spl.start_addr = ucode_array_start_addr +
 				le32_to_cpu(sos_hdr_v1_3->spl.offset_bytes);
-			adev->psp.rl_bin_size = le32_to_cpu(sos_hdr_v1_3->rl.size_bytes);
-			adev->psp.rl_start_addr = ucode_array_start_addr +
+			adev->psp.rl.size_bytes = le32_to_cpu(sos_hdr_v1_3->rl.size_bytes);
+			adev->psp.rl.start_addr = ucode_array_start_addr +
 				le32_to_cpu(sos_hdr_v1_3->rl.offset_bytes);
 		}
 		break;
+	case 2:
+		sos_hdr_v2_0 = (const struct psp_firmware_header_v2_0 *)adev->psp.sos_fw->data;
+
+		if (le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count) >= UCODE_MAX_PSP_PACKAGING) {
+			dev_err(adev->dev, "packed SOS count exceeds maximum limit\n");
+			err = -EINVAL;
+			goto out;
+		}
+
+		for (fw_index = 0; fw_index < le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count); fw_index++) {
+			err = parse_sos_bin_descriptor(psp,
+						       &sos_hdr_v2_0->psp_fw_bin[fw_index],
+						       sos_hdr_v2_0);
+			if (err)
+				goto out;
+		}
+		break;
 	default:
 		dev_err(adev->dev,
 			"unsupported psp sos firmware\n");
@@ -3080,7 +3270,7 @@ out:
 }
 
 static int parse_ta_bin_descriptor(struct psp_context *psp,
-				   const struct ta_fw_bin_desc *desc,
+				   const struct psp_fw_bin_desc *desc,
 				   const struct ta_firmware_header_v2_0 *ta_hdr)
 {
 	uint8_t *ucode_start_addr  = NULL;
@@ -3094,40 +3284,40 @@ static int parse_ta_bin_descriptor(struct psp_context *psp,
 
 	switch (desc->fw_type) {
 	case TA_FW_TYPE_PSP_ASD:
-		psp->asd_fw_version        = le32_to_cpu(desc->fw_version);
-		psp->asd_feature_version   = le32_to_cpu(desc->fw_version);
-		psp->asd_ucode_size        = le32_to_cpu(desc->size_bytes);
-		psp->asd_start_addr 	   = ucode_start_addr;
+		psp->asd.fw_version        = le32_to_cpu(desc->fw_version);
+		psp->asd.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->asd.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->asd.start_addr 	   = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_XGMI:
-		psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
-		psp->ta_xgmi_ucode_size    = le32_to_cpu(desc->size_bytes);
-		psp->ta_xgmi_start_addr    = ucode_start_addr;
+		psp->xgmi.feature_version  = le32_to_cpu(desc->fw_version);
+		psp->xgmi.size_bytes       = le32_to_cpu(desc->size_bytes);
+		psp->xgmi.start_addr       = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_RAS:
-		psp->ta_ras_ucode_version  = le32_to_cpu(desc->fw_version);
-		psp->ta_ras_ucode_size     = le32_to_cpu(desc->size_bytes);
-		psp->ta_ras_start_addr     = ucode_start_addr;
+		psp->ras.feature_version   = le32_to_cpu(desc->fw_version);
+		psp->ras.size_bytes        = le32_to_cpu(desc->size_bytes);
+		psp->ras.start_addr        = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_HDCP:
-		psp->ta_hdcp_ucode_version = le32_to_cpu(desc->fw_version);
-		psp->ta_hdcp_ucode_size    = le32_to_cpu(desc->size_bytes);
-		psp->ta_hdcp_start_addr    = ucode_start_addr;
+		psp->hdcp.feature_version  = le32_to_cpu(desc->fw_version);
+		psp->hdcp.size_bytes       = le32_to_cpu(desc->size_bytes);
+		psp->hdcp.start_addr       = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_DTM:
-		psp->ta_dtm_ucode_version  = le32_to_cpu(desc->fw_version);
-		psp->ta_dtm_ucode_size     = le32_to_cpu(desc->size_bytes);
-		psp->ta_dtm_start_addr     = ucode_start_addr;
+		psp->dtm.feature_version  = le32_to_cpu(desc->fw_version);
+		psp->dtm.size_bytes       = le32_to_cpu(desc->size_bytes);
+		psp->dtm.start_addr       = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_RAP:
-		psp->ta_rap_ucode_version  = le32_to_cpu(desc->fw_version);
-		psp->ta_rap_ucode_size     = le32_to_cpu(desc->size_bytes);
-		psp->ta_rap_start_addr     = ucode_start_addr;
+		psp->rap.feature_version  = le32_to_cpu(desc->fw_version);
+		psp->rap.size_bytes       = le32_to_cpu(desc->size_bytes);
+		psp->rap.start_addr       = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_SECUREDISPLAY:
-		psp->ta_securedisplay_ucode_version  = le32_to_cpu(desc->fw_version);
-		psp->ta_securedisplay_ucode_size     = le32_to_cpu(desc->size_bytes);
-		psp->ta_securedisplay_start_addr     = ucode_start_addr;
+		psp->securedisplay.feature_version  = le32_to_cpu(desc->fw_version);
+		psp->securedisplay.size_bytes       = le32_to_cpu(desc->size_bytes);
+		psp->securedisplay.start_addr       = ucode_start_addr;
 		break;
 	default:
 		dev_warn(psp->adev->dev, "Unsupported TA type: %d\n", desc->fw_type);
@@ -3168,7 +3358,7 @@ int psp_init_ta_microcode(struct psp_context *psp,
 		goto out;
 	}
 
-	if (le32_to_cpu(ta_hdr->ta_fw_bin_count) >= UCODE_MAX_TA_PACKAGING) {
+	if (le32_to_cpu(ta_hdr->ta_fw_bin_count) >= UCODE_MAX_PSP_PACKAGING) {
 		dev_err(adev->dev, "packed TA count exceeds maximum limit\n");
 		err = -EINVAL;
 		goto out;
@@ -3235,11 +3425,12 @@ static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(ddev);
-	void *cpu_addr;
-	dma_addr_t dma_addr;
 	int ret, idx;
 	char fw_name[100];
 	const struct firmware *usbc_pd_fw;
+	struct amdgpu_bo *fw_buf_bo = NULL;
+	uint64_t fw_pri_mc_addr;
+	void *fw_pri_cpu_addr;
 
 	if (!adev->ip_blocks[AMD_IP_BLOCK_TYPE_PSP].status.late_initialized) {
 		DRM_INFO("PSP block is not ready yet.");
@@ -3254,31 +3445,24 @@ static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev,
 	if (ret)
 		goto fail;
 
-	/* We need contiguous physical mem to place the FW  for psp to access */
-	cpu_addr = dma_alloc_coherent(adev->dev, usbc_pd_fw->size, &dma_addr, GFP_KERNEL);
-
-	ret = dma_mapping_error(adev->dev, dma_addr);
+	/* LFB address which is aligned to 1MB boundary per PSP request */
+	ret = amdgpu_bo_create_kernel(adev, usbc_pd_fw->size, 0x100000,
+						AMDGPU_GEM_DOMAIN_VRAM,
+						&fw_buf_bo,
+						&fw_pri_mc_addr,
+						&fw_pri_cpu_addr);
 	if (ret)
 		goto rel_buf;
 
-	memcpy_toio(cpu_addr, usbc_pd_fw->data, usbc_pd_fw->size);
-
-	/*
-	 * x86 specific workaround.
-	 * Without it the buffer is invisible in PSP.
-	 *
-	 * TODO Remove once PSP starts snooping CPU cache
-	 */
-#ifdef CONFIG_X86
-	clflush_cache_range(cpu_addr, (usbc_pd_fw->size & ~(L1_CACHE_BYTES - 1)));
-#endif
+	memcpy_toio(fw_pri_cpu_addr, usbc_pd_fw->data, usbc_pd_fw->size);
 
 	mutex_lock(&adev->psp.mutex);
-	ret = psp_load_usbc_pd_fw(&adev->psp, dma_addr);
+	ret = psp_load_usbc_pd_fw(&adev->psp, fw_pri_mc_addr);
 	mutex_unlock(&adev->psp.mutex);
 
+	amdgpu_bo_free_kernel(&fw_buf_bo, &fw_pri_mc_addr, &fw_pri_cpu_addr);
+
 rel_buf:
-	dma_free_coherent(adev->dev, usbc_pd_fw->size, cpu_addr, dma_addr);
 	release_firmware(usbc_pd_fw);
 fail:
 	if (ret) {
@@ -3307,7 +3491,10 @@ static DEVICE_ATTR(usbc_pd_fw, S_IRUGO | S_IWUSR,
 		   psp_usbc_pd_fw_sysfs_read,
 		   psp_usbc_pd_fw_sysfs_write);
 
-
+int is_psp_fw_valid(struct psp_bin_desc bin)
+{
+	return bin.size_bytes;
+}
 
 const struct amd_ip_funcs psp_ip_funcs = {
 	.name = "psp",
@@ -3369,6 +3556,14 @@ const struct amdgpu_ip_block_version psp_v11_0_ip_block =
 	.funcs = &psp_ip_funcs,
 };
 
+const struct amdgpu_ip_block_version psp_v11_0_8_ip_block = {
+	.type = AMD_IP_BLOCK_TYPE_PSP,
+	.major = 11,
+	.minor = 0,
+	.rev = 8,
+	.funcs = &psp_ip_funcs,
+};
+
 const struct amdgpu_ip_block_version psp_v12_0_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_PSP,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 3030ec24eb3b..8ef2d28af92a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -48,11 +48,15 @@
 struct psp_context;
 struct psp_xgmi_node_info;
 struct psp_xgmi_topology_info;
+struct psp_bin_desc;
 
 enum psp_bootloader_cmd {
 	PSP_BL__LOAD_SYSDRV		= 0x10000,
 	PSP_BL__LOAD_SOSDRV		= 0x20000,
 	PSP_BL__LOAD_KEY_DATABASE	= 0x80000,
+	PSP_BL__LOAD_SOCDRV             = 0xB0000,
+	PSP_BL__LOAD_INTFDRV            = 0xC0000,
+	PSP_BL__LOAD_DBGDRV             = 0xD0000,
 	PSP_BL__DRAM_LONG_TRAIN		= 0x100000,
 	PSP_BL__DRAM_SHORT_TRAIN	= 0x200000,
 	PSP_BL__LOAD_TOS_SPL_TABLE	= 0x10000000,
@@ -93,6 +97,9 @@ struct psp_funcs
 	int (*bootloader_load_kdb)(struct psp_context *psp);
 	int (*bootloader_load_spl)(struct psp_context *psp);
 	int (*bootloader_load_sysdrv)(struct psp_context *psp);
+	int (*bootloader_load_soc_drv)(struct psp_context *psp);
+	int (*bootloader_load_intf_drv)(struct psp_context *psp);
+	int (*bootloader_load_dbg_drv)(struct psp_context *psp);
 	int (*bootloader_load_sos)(struct psp_context *psp);
 	int (*ring_init)(struct psp_context *psp, enum psp_ring_type ring_type);
 	int (*ring_create)(struct psp_context *psp,
@@ -106,7 +113,7 @@ struct psp_funcs
 	int (*mem_training)(struct psp_context *psp, uint32_t ops);
 	uint32_t (*ring_get_wptr)(struct psp_context *psp);
 	void (*ring_set_wptr)(struct psp_context *psp, uint32_t value);
-	int (*load_usbc_pd_fw)(struct psp_context *psp, dma_addr_t dma_addr);
+	int (*load_usbc_pd_fw)(struct psp_context *psp, uint64_t fw_pri_mc_addr);
 	int (*read_usbc_pd_fw)(struct psp_context *psp, uint32_t *fw_ver);
 };
 
@@ -116,6 +123,7 @@ struct psp_xgmi_node_info {
 	uint8_t					num_hops;
 	uint8_t					is_sharing_enabled;
 	enum ta_xgmi_assigned_sdma_engine	sdma_engine;
+	uint8_t					num_links;
 };
 
 struct psp_xgmi_topology_info {
@@ -128,59 +136,32 @@ struct psp_asd_context {
 	uint32_t		session_id;
 };
 
-struct psp_xgmi_context {
-	uint8_t				initialized;
-	uint32_t			session_id;
-	struct amdgpu_bo                *xgmi_shared_bo;
-	uint64_t                        xgmi_shared_mc_addr;
-	void                            *xgmi_shared_buf;
-	struct psp_xgmi_topology_info	top_info;
-};
-
-struct psp_ras_context {
-	/*ras fw*/
-	bool			ras_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*ras_shared_bo;
-	uint64_t		ras_shared_mc_addr;
-	void			*ras_shared_buf;
-	struct amdgpu_ras	*ras;
+struct ta_mem_context {
+	struct amdgpu_bo		*shared_bo;
+	uint64_t		shared_mc_addr;
+	void			*shared_buf;
 };
 
-struct psp_hdcp_context {
-	bool			hdcp_initialized;
+struct ta_context {
+	bool			initialized;
 	uint32_t		session_id;
-	struct amdgpu_bo	*hdcp_shared_bo;
-	uint64_t		hdcp_shared_mc_addr;
-	void			*hdcp_shared_buf;
-	struct mutex		mutex;
+	struct ta_mem_context	mem_context;
 };
 
-struct psp_dtm_context {
-	bool			dtm_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*dtm_shared_bo;
-	uint64_t		dtm_shared_mc_addr;
-	void			*dtm_shared_buf;
-	struct mutex		mutex;
+struct ta_cp_context {
+	struct ta_context		context;
+	struct mutex			mutex;
 };
 
-struct psp_rap_context {
-	bool			rap_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*rap_shared_bo;
-	uint64_t		rap_shared_mc_addr;
-	void			*rap_shared_buf;
-	struct mutex		mutex;
+struct psp_xgmi_context {
+	struct ta_context		context;
+	struct psp_xgmi_topology_info	top_info;
+	bool				supports_extended_data;
 };
 
-struct psp_securedisplay_context {
-	bool			securedisplay_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*securedisplay_shared_bo;
-	uint64_t		securedisplay_shared_mc_addr;
-	void			*securedisplay_shared_buf;
-	struct mutex		mutex;
+struct psp_ras_context {
+	struct ta_context		context;
+	struct amdgpu_ras		*ras;
 };
 
 #define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
@@ -282,6 +263,13 @@ struct psp_runtime_boot_cfg_entry {
 	uint32_t reserved;
 };
 
+struct psp_bin_desc {
+	uint32_t fw_version;
+	uint32_t feature_version;
+	uint32_t size_bytes;
+	uint8_t *start_addr;
+};
+
 struct psp_context
 {
 	struct amdgpu_device            *adev;
@@ -297,36 +285,26 @@ struct psp_context
 
 	/* sos firmware */
 	const struct firmware		*sos_fw;
-	uint32_t			sos_fw_version;
-	uint32_t			sos_feature_version;
-	uint32_t			sys_bin_size;
-	uint32_t			sos_bin_size;
-	uint32_t			toc_bin_size;
-	uint32_t			kdb_bin_size;
-	uint32_t			spl_bin_size;
-	uint32_t			rl_bin_size;
-	uint8_t				*sys_start_addr;
-	uint8_t				*sos_start_addr;
-	uint8_t				*toc_start_addr;
-	uint8_t				*kdb_start_addr;
-	uint8_t				*spl_start_addr;
-	uint8_t				*rl_start_addr;
+	struct psp_bin_desc		sys;
+	struct psp_bin_desc		sos;
+	struct psp_bin_desc		toc;
+	struct psp_bin_desc		kdb;
+	struct psp_bin_desc		spl;
+	struct psp_bin_desc		rl;
+	struct psp_bin_desc		soc_drv;
+	struct psp_bin_desc		intf_drv;
+	struct psp_bin_desc		dbg_drv;
 
 	/* tmr buffer */
 	struct amdgpu_bo		*tmr_bo;
 	uint64_t			tmr_mc_addr;
 
 	/* asd firmware */
-	const struct firmware		*asd_fw;
-	uint32_t			asd_fw_version;
-	uint32_t			asd_feature_version;
-	uint32_t			asd_ucode_size;
-	uint8_t				*asd_start_addr;
+	const struct firmware	*asd_fw;
+	struct psp_bin_desc		asd;
 
 	/* toc firmware */
 	const struct firmware		*toc_fw;
-	uint32_t			toc_fw_version;
-	uint32_t			toc_feature_version;
 
 	/* fence buffer */
 	struct amdgpu_bo		*fence_buf_bo;
@@ -348,36 +326,20 @@ struct psp_context
 	/* xgmi ta firmware and buffer */
 	const struct firmware		*ta_fw;
 	uint32_t			ta_fw_version;
-	uint32_t			ta_xgmi_ucode_version;
-	uint32_t			ta_xgmi_ucode_size;
-	uint8_t				*ta_xgmi_start_addr;
-	uint32_t			ta_ras_ucode_version;
-	uint32_t			ta_ras_ucode_size;
-	uint8_t				*ta_ras_start_addr;
-
-	uint32_t			ta_hdcp_ucode_version;
-	uint32_t			ta_hdcp_ucode_size;
-	uint8_t				*ta_hdcp_start_addr;
-
-	uint32_t			ta_dtm_ucode_version;
-	uint32_t			ta_dtm_ucode_size;
-	uint8_t				*ta_dtm_start_addr;
-
-	uint32_t			ta_rap_ucode_version;
-	uint32_t			ta_rap_ucode_size;
-	uint8_t				*ta_rap_start_addr;
-
-	uint32_t			ta_securedisplay_ucode_version;
-	uint32_t			ta_securedisplay_ucode_size;
-	uint8_t				*ta_securedisplay_start_addr;
+	struct psp_bin_desc		xgmi;
+	struct psp_bin_desc		ras;
+	struct psp_bin_desc		hdcp;
+	struct psp_bin_desc		dtm;
+	struct psp_bin_desc		rap;
+	struct psp_bin_desc		securedisplay;
 
 	struct psp_asd_context		asd_context;
 	struct psp_xgmi_context		xgmi_context;
-	struct psp_ras_context		ras;
-	struct psp_hdcp_context 	hdcp_context;
-	struct psp_dtm_context		dtm_context;
-	struct psp_rap_context		rap_context;
-	struct psp_securedisplay_context	securedisplay_context;
+	struct psp_ras_context		ras_context;
+	struct ta_cp_context		hdcp_context;
+	struct ta_cp_context		dtm_context;
+	struct ta_cp_context		rap_context;
+	struct ta_cp_context		securedisplay_context;
 	struct mutex			mutex;
 	struct psp_memory_training_context mem_train_ctx;
 
@@ -402,6 +364,12 @@ struct amdgpu_psp_funcs {
 		((psp)->funcs->bootloader_load_spl ? (psp)->funcs->bootloader_load_spl((psp)) : 0)
 #define psp_bootloader_load_sysdrv(psp) \
 		((psp)->funcs->bootloader_load_sysdrv ? (psp)->funcs->bootloader_load_sysdrv((psp)) : 0)
+#define psp_bootloader_load_soc_drv(psp) \
+		((psp)->funcs->bootloader_load_soc_drv ? (psp)->funcs->bootloader_load_soc_drv((psp)) : 0)
+#define psp_bootloader_load_intf_drv(psp) \
+		((psp)->funcs->bootloader_load_intf_drv ? (psp)->funcs->bootloader_load_intf_drv((psp)) : 0)
+#define psp_bootloader_load_dbg_drv(psp) \
+		((psp)->funcs->bootloader_load_dbg_drv ? (psp)->funcs->bootloader_load_dbg_drv((psp)) : 0)
 #define psp_bootloader_load_sos(psp) \
 		((psp)->funcs->bootloader_load_sos ? (psp)->funcs->bootloader_load_sos((psp)) : 0)
 #define psp_smu_reload_quirk(psp) \
@@ -414,9 +382,9 @@ struct amdgpu_psp_funcs {
 #define psp_ring_get_wptr(psp) (psp)->funcs->ring_get_wptr((psp))
 #define psp_ring_set_wptr(psp, value) (psp)->funcs->ring_set_wptr((psp), (value))
 
-#define psp_load_usbc_pd_fw(psp, dma_addr) \
+#define psp_load_usbc_pd_fw(psp, fw_pri_mc_addr) \
 	((psp)->funcs->load_usbc_pd_fw ? \
-	(psp)->funcs->load_usbc_pd_fw((psp), (dma_addr)) : -EINVAL)
+	(psp)->funcs->load_usbc_pd_fw((psp), (fw_pri_mc_addr)) : -EINVAL)
 
 #define psp_read_usbc_pd_fw(psp, fw_ver) \
 	((psp)->funcs->read_usbc_pd_fw ? \
@@ -427,6 +395,7 @@ extern const struct amd_ip_funcs psp_ip_funcs;
 extern const struct amdgpu_ip_block_version psp_v3_1_ip_block;
 extern const struct amdgpu_ip_block_version psp_v10_0_ip_block;
 extern const struct amdgpu_ip_block_version psp_v11_0_ip_block;
+extern const struct amdgpu_ip_block_version psp_v11_0_8_ip_block;
 extern const struct amdgpu_ip_block_version psp_v12_0_ip_block;
 extern const struct amdgpu_ip_block_version psp_v13_0_ip_block;
 
@@ -437,14 +406,15 @@ int psp_gpu_reset(struct amdgpu_device *adev);
 int psp_update_vcn_sram(struct amdgpu_device *adev, int inst_idx,
 			uint64_t cmd_gpu_addr, int cmd_size);
 
-int psp_xgmi_initialize(struct psp_context *psp);
+int psp_xgmi_initialize(struct psp_context *psp, bool set_extended_data, bool load_ta);
 int psp_xgmi_terminate(struct psp_context *psp);
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 int psp_xgmi_get_hive_id(struct psp_context *psp, uint64_t *hive_id);
 int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id);
 int psp_xgmi_get_topology_info(struct psp_context *psp,
 			       int number_devices,
-			       struct psp_xgmi_topology_info *topology);
+			       struct psp_xgmi_topology_info *topology,
+			       bool get_extended_data);
 int psp_xgmi_set_topology_info(struct psp_context *psp,
 			       int number_devices,
 			       struct psp_xgmi_topology_info *topology);
@@ -483,4 +453,5 @@ int psp_load_fw_list(struct psp_context *psp,
 		     struct amdgpu_firmware_info **ucode_list, int ucode_count);
 void psp_copy_fw(struct psp_context *psp, uint8_t *start_addr, uint32_t bin_size);
 
+int is_psp_fw_valid(struct psp_bin_desc bin);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
index 51909bf8798c..12010c988c8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
@@ -76,7 +76,7 @@ static ssize_t amdgpu_rap_debugfs_write(struct file *f, const char __user *buf,
 			dev_info(adev->dev, "RAP L0 validate test success.\n");
 		} else {
 			rap_shared_mem = (struct ta_rap_shared_memory *)
-					 adev->psp.rap_context.rap_shared_buf;
+					 adev->psp.rap_context.context.mem_context.shared_buf;
 			rap_cmd_output = &(rap_shared_mem->rap_out_message.output);
 
 			dev_info(adev->dev, "RAP test failed, the output is:\n");
@@ -119,7 +119,7 @@ void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 
-	if (!adev->psp.rap_context.rap_initialized)
+	if (!adev->psp.rap_context.context.initialized)
 		return;
 
 	debugfs_create_file("rap_test", S_IWUSR, minor->debugfs_root,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index fc66aca28594..96a8fd0ca1df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -64,15 +64,14 @@ const char *ras_block_string[] = {
 };
 
 #define ras_err_str(i) (ras_error_string[ffs(i)])
-#define ras_block_str(i) (ras_block_string[i])
 
 #define RAS_DEFAULT_FLAGS (AMDGPU_RAS_FLAG_INIT_BY_VBIOS)
 
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
-/* typical ECC bad page rate(1 bad page per 100MB VRAM) */
-#define RAS_BAD_PAGE_RATE		(100 * 1024 * 1024ULL)
+/* typical ECC bad page rate is 1 bad page per 100MB VRAM */
+#define RAS_BAD_PAGE_COVER              (100 * 1024 * 1024ULL)
 
 enum amdgpu_ras_retire_page_reservation {
 	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
@@ -355,8 +354,9 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
  *	to see which blocks support RAS on a particular asic.
  *
  */
-static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *buf,
-		size_t size, loff_t *pos)
+static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f,
+					     const char __user *buf,
+					     size_t size, loff_t *pos)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
 	struct ras_debug_if data;
@@ -370,7 +370,7 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 
 	ret = amdgpu_ras_debugfs_ctrl_parse_data(f, buf, size, pos, &data);
 	if (ret)
-		return -EINVAL;
+		return ret;
 
 	if (data.op == 3) {
 		ret = amdgpu_reserve_page_direct(adev, data.inject.address);
@@ -403,9 +403,9 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 		/* umc ce/ue error injection for a bad page is not allowed */
 		if ((data.head.block == AMDGPU_RAS_BLOCK__UMC) &&
 		    amdgpu_ras_check_bad_page(adev, data.inject.address)) {
-			dev_warn(adev->dev, "RAS WARN: 0x%llx has been marked "
-					"as bad before error injection!\n",
-					data.inject.address);
+			dev_warn(adev->dev, "RAS WARN: inject: 0x%llx has "
+				 "already been marked as bad!\n",
+				 data.inject.address);
 			break;
 		}
 
@@ -439,21 +439,24 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
  * will reset EEPROM table to 0 entries.
  *
  */
-static ssize_t amdgpu_ras_debugfs_eeprom_write(struct file *f, const char __user *buf,
-		size_t size, loff_t *pos)
+static ssize_t amdgpu_ras_debugfs_eeprom_write(struct file *f,
+					       const char __user *buf,
+					       size_t size, loff_t *pos)
 {
 	struct amdgpu_device *adev =
 		(struct amdgpu_device *)file_inode(f)->i_private;
 	int ret;
 
 	ret = amdgpu_ras_eeprom_reset_table(
-			&(amdgpu_ras_get_context(adev)->eeprom_control));
+		&(amdgpu_ras_get_context(adev)->eeprom_control));
 
-	if (ret == 1) {
+	if (!ret) {
+		/* Something was written to EEPROM.
+		 */
 		amdgpu_ras_get_context(adev)->flags = RAS_DEFAULT_FLAGS;
 		return size;
 	} else {
-		return -EIO;
+		return ret;
 	}
 }
 
@@ -526,7 +529,7 @@ static inline void put_obj(struct ras_manager *obj)
 	if (obj && (--obj->use == 0))
 		list_del(&obj->node);
 	if (obj && (obj->use < 0))
-		DRM_ERROR("RAS ERROR: Unbalance obj(%s) use\n", obj->head.name);
+		DRM_ERROR("RAS ERROR: Unbalance obj(%s) use\n", ras_block_str(obj->head.block));
 }
 
 /* make one obj and return it. */
@@ -789,7 +792,6 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev,
 			.type = default_ras_type,
 			.sub_block_index = 0,
 		};
-		strcpy(head.name, ras_block_str(i));
 		if (bypass) {
 			/*
 			 * bypass psp. vbios enable ras for us.
@@ -1316,6 +1318,12 @@ static struct dentry *amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *
 			   &con->bad_page_cnt_threshold);
 	debugfs_create_x32("ras_hw_enabled", 0444, dir, &adev->ras_hw_enabled);
 	debugfs_create_x32("ras_enabled", 0444, dir, &adev->ras_enabled);
+	debugfs_create_file("ras_eeprom_size", S_IRUGO, dir, adev,
+			    &amdgpu_ras_debugfs_eeprom_size_ops);
+	con->de_ras_eeprom_table = debugfs_create_file("ras_eeprom_table",
+						       S_IRUGO, dir, adev,
+						       &amdgpu_ras_debugfs_eeprom_table_ops);
+	amdgpu_ras_debugfs_set_ret_size(&con->eeprom_control);
 
 	/*
 	 * After one uncorrectable error happens, usually GPU recovery will
@@ -1833,13 +1841,12 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 
 	control = &con->eeprom_control;
 	data = con->eh_data;
-	save_count = data->count - control->num_recs;
+	save_count = data->count - control->ras_num_recs;
 	/* only new entries are saved */
 	if (save_count > 0) {
-		if (amdgpu_ras_eeprom_process_recods(control,
-							&data->bps[control->num_recs],
-							true,
-							save_count)) {
+		if (amdgpu_ras_eeprom_append(control,
+					     &data->bps[control->ras_num_recs],
+					     save_count)) {
 			dev_err(adev->dev, "Failed to save EEPROM table data!");
 			return -EIO;
 		}
@@ -1857,28 +1864,24 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras_eeprom_control *control =
-					&adev->psp.ras.ras->eeprom_control;
-	struct eeprom_table_record *bps = NULL;
-	int ret = 0;
+		&adev->psp.ras_context.ras->eeprom_control;
+	struct eeprom_table_record *bps;
+	int ret;
 
 	/* no bad page record, skip eeprom access */
-	if (!control->num_recs || (amdgpu_bad_page_threshold == 0))
-		return ret;
+	if (control->ras_num_recs == 0 || amdgpu_bad_page_threshold == 0)
+		return 0;
 
-	bps = kcalloc(control->num_recs, sizeof(*bps), GFP_KERNEL);
+	bps = kcalloc(control->ras_num_recs, sizeof(*bps), GFP_KERNEL);
 	if (!bps)
 		return -ENOMEM;
 
-	if (amdgpu_ras_eeprom_process_recods(control, bps, false,
-		control->num_recs)) {
+	ret = amdgpu_ras_eeprom_read(control, bps, control->ras_num_recs);
+	if (ret)
 		dev_err(adev->dev, "Failed to load EEPROM table records!");
-		ret = -EIO;
-		goto out;
-	}
-
-	ret = amdgpu_ras_add_bad_pages(adev, bps, control->num_recs);
+	else
+		ret = amdgpu_ras_add_bad_pages(adev, bps, control->ras_num_recs);
 
-out:
 	kfree(bps);
 	return ret;
 }
@@ -1918,11 +1921,9 @@ static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 }
 
 static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
-					uint32_t max_length)
+					  uint32_t max_count)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	int tmp_threshold = amdgpu_bad_page_threshold;
-	u64 val;
 
 	/*
 	 * Justification of value bad_page_cnt_threshold in ras structure
@@ -1943,18 +1944,15 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
 	 *      take no effect.
 	 */
 
-	if (tmp_threshold < -1)
-		tmp_threshold = -1;
-	else if (tmp_threshold > max_length)
-		tmp_threshold = max_length;
+	if (amdgpu_bad_page_threshold < 0) {
+		u64 val = adev->gmc.mc_vram_size;
 
-	if (tmp_threshold == -1) {
-		val = adev->gmc.mc_vram_size;
-		do_div(val, RAS_BAD_PAGE_RATE);
+		do_div(val, RAS_BAD_PAGE_COVER);
 		con->bad_page_cnt_threshold = min(lower_32_bits(val),
-						max_length);
+						  max_count);
 	} else {
-		con->bad_page_cnt_threshold = tmp_threshold;
+		con->bad_page_cnt_threshold = min_t(int, max_count,
+						    amdgpu_bad_page_threshold);
 	}
 }
 
@@ -1962,15 +1960,24 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data **data;
-	uint32_t max_eeprom_records_len = 0;
+	u32  max_eeprom_records_count = 0;
 	bool exc_err_limit = false;
 	int ret;
 
-	if (adev->ras_enabled && con)
-		data = &con->eh_data;
-	else
+	if (!con)
 		return 0;
 
+	/* Allow access to RAS EEPROM via debugfs, when the ASIC
+	 * supports RAS and debugfs is enabled, but when
+	 * adev->ras_enabled is unset, i.e. when "ras_enable"
+	 * module parameter is set to 0.
+	 */
+	con->adev = adev;
+
+	if (!adev->ras_enabled)
+		return 0;
+
+	data = &con->eh_data;
 	*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
 	if (!*data) {
 		ret = -ENOMEM;
@@ -1980,10 +1987,9 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	mutex_init(&con->recovery_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
-	con->adev = adev;
 
-	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
-	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
+	max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count();
+	amdgpu_ras_validate_threshold(adev, max_eeprom_records_count);
 
 	/* Todo: During test the SMU might fail to read the eeprom through I2C
 	 * when the GPU is pending on XGMI reset during probe time
@@ -1999,13 +2005,13 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	if (exc_err_limit || ret)
 		goto free;
 
-	if (con->eeprom_control.num_recs) {
+	if (con->eeprom_control.ras_num_recs) {
 		ret = amdgpu_ras_load_bad_pages(adev);
 		if (ret)
 			goto free;
 
 		if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num)
-			adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs);
+			adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.ras_num_recs);
 	}
 
 	return 0;
@@ -2015,7 +2021,7 @@ free:
 	kfree(*data);
 	con->eh_data = NULL;
 out:
-	dev_warn(adev->dev, "Failed to initialize ras recovery!\n");
+	dev_warn(adev->dev, "Failed to initialize ras recovery! (%d)\n", ret);
 
 	/*
 	 * Except error threshold exceeding case, other failure cases in this
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index b504ed8c9b50..eae604fd90b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -49,10 +49,14 @@ enum amdgpu_ras_block {
 	AMDGPU_RAS_BLOCK__MP0,
 	AMDGPU_RAS_BLOCK__MP1,
 	AMDGPU_RAS_BLOCK__FUSE,
+	AMDGPU_RAS_BLOCK__MPIO,
 
 	AMDGPU_RAS_BLOCK__LAST
 };
 
+extern const char *ras_block_string[];
+
+#define ras_block_str(i) (ras_block_string[i])
 #define AMDGPU_RAS_BLOCK_COUNT	AMDGPU_RAS_BLOCK__LAST
 #define AMDGPU_RAS_BLOCK_MASK	((1ULL << AMDGPU_RAS_BLOCK_COUNT) - 1)
 
@@ -306,7 +310,6 @@ struct ras_common_if {
 	enum amdgpu_ras_block block;
 	enum amdgpu_ras_error_type type;
 	uint32_t sub_block_index;
-	/* block name */
 	char name[32];
 };
 
@@ -318,6 +321,7 @@ struct amdgpu_ras {
 	/* sysfs */
 	struct device_attribute features_attr;
 	struct bin_attribute badpages_attr;
+	struct dentry *de_ras_eeprom_table;
 	/* block array */
 	struct ras_manager *objs;
 
@@ -417,7 +421,7 @@ struct ras_badpage {
 /* interfaces for IP */
 struct ras_fs_if {
 	struct ras_common_if head;
-	char sysfs_name[32];
+	const char* sysfs_name;
 	char debugfs_name[32];
 };
 
@@ -469,8 +473,8 @@ struct ras_debug_if {
  * 8: feature disable
  */
 
-#define amdgpu_ras_get_context(adev)		((adev)->psp.ras.ras)
-#define amdgpu_ras_set_context(adev, ras_con)	((adev)->psp.ras.ras = (ras_con))
+#define amdgpu_ras_get_context(adev)		((adev)->psp.ras_context.ras)
+#define amdgpu_ras_set_context(adev, ras_con)	((adev)->psp.ras_context.ras = (ras_con))
 
 /* check if ras is supported on block, say, sdma, gfx */
 static inline int amdgpu_ras_is_supported(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 38222de921d1..9dc3b2d88176 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -26,94 +26,131 @@
 #include "amdgpu_ras.h"
 #include <linux/bits.h>
 #include "atom.h"
+#include "amdgpu_eeprom.h"
 #include "amdgpu_atomfirmware.h"
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
 
-#define EEPROM_I2C_TARGET_ADDR_VEGA20		0xA0
-#define EEPROM_I2C_TARGET_ADDR_ARCTURUS		0xA8
-#define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342	0xA0
-#define EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID   0xA0
-#define EEPROM_I2C_TARGET_ADDR_ALDEBARAN        0xA0
+#define EEPROM_I2C_MADDR_VEGA20         0x0
+#define EEPROM_I2C_MADDR_ARCTURUS       0x40000
+#define EEPROM_I2C_MADDR_ARCTURUS_D342  0x0
+#define EEPROM_I2C_MADDR_SIENNA_CICHLID 0x0
+#define EEPROM_I2C_MADDR_ALDEBARAN      0x0
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
  * those entities occupy in the EEPROM memory.
- * EEPROM_TABLE_RECORD_SIZE is different than sizeof(eeprom_table_record) which
+ * RAS_TABLE_RECORD_SIZE is different than sizeof(eeprom_table_record) which
  * uses uint64 to store 6b fields such as retired_page.
  */
-#define EEPROM_TABLE_HEADER_SIZE 20
-#define EEPROM_TABLE_RECORD_SIZE 24
-
-#define EEPROM_ADDRESS_SIZE 0x2
+#define RAS_TABLE_HEADER_SIZE   20
+#define RAS_TABLE_RECORD_SIZE   24
 
 /* Table hdr is 'AMDR' */
-#define EEPROM_TABLE_HDR_VAL 0x414d4452
-#define EEPROM_TABLE_VER 0x00010000
+#define RAS_TABLE_HDR_VAL       0x414d4452
+#define RAS_TABLE_VER           0x00010000
 
 /* Bad GPU tag ‘BADG’ */
-#define EEPROM_TABLE_HDR_BAD 0x42414447
+#define RAS_TABLE_HDR_BAD       0x42414447
+
+/* Assume 2-Mbit size EEPROM and take up the whole space. */
+#define RAS_TBL_SIZE_BYTES      (256 * 1024)
+#define RAS_TABLE_START         0
+#define RAS_HDR_START           RAS_TABLE_START
+#define RAS_RECORD_START        (RAS_HDR_START + RAS_TABLE_HEADER_SIZE)
+#define RAS_MAX_RECORD_COUNT    ((RAS_TBL_SIZE_BYTES - RAS_TABLE_HEADER_SIZE) \
+				 / RAS_TABLE_RECORD_SIZE)
+
+/* Given a zero-based index of an EEPROM RAS record, yields the EEPROM
+ * offset off of RAS_TABLE_START.  That is, this is something you can
+ * add to control->i2c_address, and then tell I2C layer to read
+ * from/write to there. _N is the so called absolute index,
+ * because it starts right after the table header.
+ */
+#define RAS_INDEX_TO_OFFSET(_C, _N) ((_C)->ras_record_offset + \
+				     (_N) * RAS_TABLE_RECORD_SIZE)
+
+#define RAS_OFFSET_TO_INDEX(_C, _O) (((_O) - \
+				      (_C)->ras_record_offset) / RAS_TABLE_RECORD_SIZE)
+
+/* Given a 0-based relative record index, 0, 1, 2, ..., etc., off
+ * of "fri", return the absolute record index off of the end of
+ * the table header.
+ */
+#define RAS_RI_TO_AI(_C, _I) (((_I) + (_C)->ras_fri) % \
+			      (_C)->ras_max_record_count)
 
-/* Assume 2 Mbit size */
-#define EEPROM_SIZE_BYTES 256000
-#define EEPROM_PAGE__SIZE_BYTES 256
-#define EEPROM_HDR_START 0
-#define EEPROM_RECORD_START (EEPROM_HDR_START + EEPROM_TABLE_HEADER_SIZE)
-#define EEPROM_MAX_RECORD_NUM ((EEPROM_SIZE_BYTES - EEPROM_TABLE_HEADER_SIZE) / EEPROM_TABLE_RECORD_SIZE)
-#define EEPROM_ADDR_MSB_MASK GENMASK(17, 8)
+#define RAS_NUM_RECS(_tbl_hdr)  (((_tbl_hdr)->tbl_size - \
+				  RAS_TABLE_HEADER_SIZE) / RAS_TABLE_RECORD_SIZE)
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_ras, eeprom_control))->adev
 
 static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
 {
-	if ((adev->asic_type == CHIP_VEGA20) ||
-	    (adev->asic_type == CHIP_ARCTURUS) ||
-	    (adev->asic_type == CHIP_SIENNA_CICHLID) ||
-	    (adev->asic_type == CHIP_ALDEBARAN))
-		return true;
-
-	return false;
+	return  adev->asic_type == CHIP_VEGA20 ||
+		adev->asic_type == CHIP_ARCTURUS ||
+		adev->asic_type == CHIP_SIENNA_CICHLID ||
+		adev->asic_type == CHIP_ALDEBARAN;
 }
 
 static bool __get_eeprom_i2c_addr_arct(struct amdgpu_device *adev,
-				       uint16_t *i2c_addr)
+				       struct amdgpu_ras_eeprom_control *control)
 {
 	struct atom_context *atom_ctx = adev->mode_info.atom_context;
 
-	if (!i2c_addr || !atom_ctx)
+	if (!control || !atom_ctx)
 		return false;
 
 	if (strnstr(atom_ctx->vbios_version,
 	            "D342",
 		    sizeof(atom_ctx->vbios_version)))
-		*i2c_addr = EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342;
+		control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS_D342;
 	else
-		*i2c_addr = EEPROM_I2C_TARGET_ADDR_ARCTURUS;
+		control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS;
 
 	return true;
 }
 
 static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
-				  uint16_t *i2c_addr)
+				  struct amdgpu_ras_eeprom_control *control)
 {
-	if (!i2c_addr)
+	uint8_t ras_rom_i2c_slave_addr;
+
+	if (!control)
 		return false;
 
-	if (amdgpu_atomfirmware_ras_rom_addr(adev, (uint8_t*)i2c_addr))
-		return true;
+	control->i2c_address = 0;
+
+	if (amdgpu_atomfirmware_ras_rom_addr(adev, &ras_rom_i2c_slave_addr))
+	{
+		switch (ras_rom_i2c_slave_addr) {
+		case 0xA0:
+			control->i2c_address = 0;
+			return true;
+		case 0xA8:
+			control->i2c_address = 0x40000;
+			return true;
+		default:
+			dev_warn(adev->dev, "RAS EEPROM I2C slave address %02x not supported",
+				 ras_rom_i2c_slave_addr);
+			return false;
+		}
+	}
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-		*i2c_addr = EEPROM_I2C_TARGET_ADDR_VEGA20;
+		control->i2c_address = EEPROM_I2C_MADDR_VEGA20;
 		break;
 
 	case CHIP_ARCTURUS:
-		return __get_eeprom_i2c_addr_arct(adev, i2c_addr);
+		return __get_eeprom_i2c_addr_arct(adev, control);
 
 	case CHIP_SIENNA_CICHLID:
-		*i2c_addr = EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID;
+		control->i2c_address = EEPROM_I2C_MADDR_SIENNA_CICHLID;
 		break;
 
 	case CHIP_ALDEBARAN:
-		*i2c_addr = EEPROM_I2C_TARGET_ADDR_ALDEBARAN;
+		control->i2c_address = EEPROM_I2C_MADDR_ALDEBARAN;
 		break;
 
 	default:
@@ -123,10 +160,11 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 	return true;
 }
 
-static void __encode_table_header_to_buff(struct amdgpu_ras_eeprom_table_header *hdr,
-					  unsigned char *buff)
+static void
+__encode_table_header_to_buf(struct amdgpu_ras_eeprom_table_header *hdr,
+			     unsigned char *buf)
 {
-	uint32_t *pp = (uint32_t *) buff;
+	u32 *pp = (uint32_t *)buf;
 
 	pp[0] = cpu_to_le32(hdr->header);
 	pp[1] = cpu_to_le32(hdr->version);
@@ -135,10 +173,11 @@ static void __encode_table_header_to_buff(struct amdgpu_ras_eeprom_table_header
 	pp[4] = cpu_to_le32(hdr->checksum);
 }
 
-static void __decode_table_header_from_buff(struct amdgpu_ras_eeprom_table_header *hdr,
-					  unsigned char *buff)
+static void
+__decode_table_header_from_buf(struct amdgpu_ras_eeprom_table_header *hdr,
+			       unsigned char *buf)
 {
-	uint32_t *pp = (uint32_t *)buff;
+	u32 *pp = (uint32_t *)buf;
 
 	hdr->header	      = le32_to_cpu(pp[0]);
 	hdr->version	      = le32_to_cpu(pp[1]);
@@ -147,303 +186,168 @@ static void __decode_table_header_from_buff(struct amdgpu_ras_eeprom_table_heade
 	hdr->checksum	      = le32_to_cpu(pp[4]);
 }
 
-static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
-				 unsigned char *buff)
+static int __write_table_header(struct amdgpu_ras_eeprom_control *control)
 {
-	int ret = 0;
+	u8 buf[RAS_TABLE_HEADER_SIZE];
 	struct amdgpu_device *adev = to_amdgpu_device(control);
-	struct i2c_msg msg = {
-			.addr	= 0,
-			.flags	= 0,
-			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
-			.buf	= buff,
-	};
-
+	int res;
 
-	*(uint16_t *)buff = EEPROM_HDR_START;
-	__encode_table_header_to_buff(&control->tbl_hdr, buff + EEPROM_ADDRESS_SIZE);
-
-	msg.addr = control->i2c_address;
+	memset(buf, 0, sizeof(buf));
+	__encode_table_header_to_buf(&control->tbl_hdr, buf);
 
 	/* i2c may be unstable in gpu reset */
 	down_read(&adev->reset_sem);
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	res = amdgpu_eeprom_write(&adev->pm.smu_i2c,
+				  control->i2c_address +
+				  control->ras_header_offset,
+				  buf, RAS_TABLE_HEADER_SIZE);
 	up_read(&adev->reset_sem);
 
-	if (ret < 1)
-		DRM_ERROR("Failed to write EEPROM table header, ret:%d", ret);
-
-	return ret;
-}
-
-static uint32_t  __calc_hdr_byte_sum(struct amdgpu_ras_eeprom_control *control)
-{
-	int i;
-	uint32_t tbl_sum = 0;
-
-	/* Header checksum, skip checksum field in the calculation */
-	for (i = 0; i < sizeof(control->tbl_hdr) - sizeof(control->tbl_hdr.checksum); i++)
-		tbl_sum += *(((unsigned char *)&control->tbl_hdr) + i);
-
-	return tbl_sum;
-}
-
-static uint32_t  __calc_recs_byte_sum(struct eeprom_table_record *records,
-				      int num)
-{
-	int i, j;
-	uint32_t tbl_sum = 0;
-
-	/* Records checksum */
-	for (i = 0; i < num; i++) {
-		struct eeprom_table_record *record = &records[i];
-
-		for (j = 0; j < sizeof(*record); j++) {
-			tbl_sum += *(((unsigned char *)record) + j);
-		}
+	if (res < 0) {
+		DRM_ERROR("Failed to write EEPROM table header:%d", res);
+	} else if (res < RAS_TABLE_HEADER_SIZE) {
+		DRM_ERROR("Short write:%d out of %d\n",
+			  res, RAS_TABLE_HEADER_SIZE);
+		res = -EIO;
+	} else {
+		res = 0;
 	}
 
-	return tbl_sum;
-}
-
-static inline uint32_t  __calc_tbl_byte_sum(struct amdgpu_ras_eeprom_control *control,
-				  struct eeprom_table_record *records, int num)
-{
-	return __calc_hdr_byte_sum(control) + __calc_recs_byte_sum(records, num);
-}
-
-/* Checksum = 256 -((sum of all table entries) mod 256) */
-static void __update_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
-				  struct eeprom_table_record *records, int num,
-				  uint32_t old_hdr_byte_sum)
-{
-	/*
-	 * This will update the table sum with new records.
-	 *
-	 * TODO: What happens when the EEPROM table is to be wrapped around
-	 * and old records from start will get overridden.
-	 */
-
-	/* need to recalculate updated header byte sum */
-	control->tbl_byte_sum -= old_hdr_byte_sum;
-	control->tbl_byte_sum += __calc_tbl_byte_sum(control, records, num);
-
-	control->tbl_hdr.checksum = 256 - (control->tbl_byte_sum % 256);
+	return res;
 }
 
-/* table sum mod 256 + checksum must equals 256 */
-static bool __validate_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
-			    struct eeprom_table_record *records, int num)
+static u8 __calc_hdr_byte_sum(const struct amdgpu_ras_eeprom_control *control)
 {
-	control->tbl_byte_sum = __calc_tbl_byte_sum(control, records, num);
+	int ii;
+	u8  *pp, csum;
+	size_t sz;
 
-	if (control->tbl_hdr.checksum + (control->tbl_byte_sum % 256) != 256) {
-		DRM_WARN("Checksum mismatch, checksum: %u ", control->tbl_hdr.checksum);
-		return false;
-	}
+	/* Header checksum, skip checksum field in the calculation */
+	sz = sizeof(control->tbl_hdr) - sizeof(control->tbl_hdr.checksum);
+	pp = (u8 *) &control->tbl_hdr;
+	csum = 0;
+	for (ii = 0; ii < sz; ii++, pp++)
+		csum += *pp;
 
-	return true;
+	return csum;
 }
 
 static int amdgpu_ras_eeprom_correct_header_tag(
-				struct amdgpu_ras_eeprom_control *control,
-				uint32_t header)
+	struct amdgpu_ras_eeprom_control *control,
+	uint32_t header)
 {
-	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE];
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
-	int ret = 0;
-
-	memset(buff, 0, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE);
-
-	mutex_lock(&control->tbl_mutex);
+	u8 *hh;
+	int res;
+	u8 csum;
+
+	csum = -hdr->checksum;
+
+	hh = (void *) &hdr->header;
+	csum -= (hh[0] + hh[1] + hh[2] + hh[3]);
+	hh = (void *) &header;
+	csum += hh[0] + hh[1] + hh[2] + hh[3];
+	csum = -csum;
+	mutex_lock(&control->ras_tbl_mutex);
 	hdr->header = header;
-	ret = __update_table_header(control, buff);
-	mutex_unlock(&control->tbl_mutex);
+	hdr->checksum = csum;
+	res = __write_table_header(control);
+	mutex_unlock(&control->ras_tbl_mutex);
 
-	return ret;
+	return res;
 }
 
+/**
+ * amdgpu_ras_eeprom_reset_table -- Reset the RAS EEPROM table
+ * @control: pointer to control structure
+ *
+ * Reset the contents of the header of the RAS EEPROM table.
+ * Return 0 on success, -errno on error.
+ */
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 {
-	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
-	int ret = 0;
-
-	mutex_lock(&control->tbl_mutex);
-
-	hdr->header = EEPROM_TABLE_HDR_VAL;
-	hdr->version = EEPROM_TABLE_VER;
-	hdr->first_rec_offset = EEPROM_RECORD_START;
-	hdr->tbl_size = EEPROM_TABLE_HEADER_SIZE;
-
-	control->tbl_byte_sum = 0;
-	__update_tbl_checksum(control, NULL, 0, 0);
-	control->next_addr = EEPROM_RECORD_START;
-
-	ret = __update_table_header(control, buff);
-
-	mutex_unlock(&control->tbl_mutex);
-
-	return ret;
-
-}
-
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
-			bool *exceed_err_limit)
-{
-	int ret = 0;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
-	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
-	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
-	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
-	struct i2c_msg msg = {
-			.addr	= 0,
-			.flags	= I2C_M_RD,
-			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
-			.buf	= buff,
-	};
-
-	*exceed_err_limit = false;
-
-	if (!__is_ras_eeprom_supported(adev))
-		return 0;
-
-	/* Verify i2c adapter is initialized */
-	if (!adev->pm.smu_i2c.algo)
-		return -ENOENT;
+	u8 csum;
+	int res;
 
-	if (!__get_eeprom_i2c_addr(adev, &control->i2c_address))
-		return -EINVAL;
+	mutex_lock(&control->ras_tbl_mutex);
 
-	mutex_init(&control->tbl_mutex);
+	hdr->header = RAS_TABLE_HDR_VAL;
+	hdr->version = RAS_TABLE_VER;
+	hdr->first_rec_offset = RAS_RECORD_START;
+	hdr->tbl_size = RAS_TABLE_HEADER_SIZE;
 
-	msg.addr = control->i2c_address;
-	/* Read/Create table header from EEPROM address 0 */
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
-	if (ret < 1) {
-		DRM_ERROR("Failed to read EEPROM table header, ret:%d", ret);
-		return ret;
-	}
+	csum = __calc_hdr_byte_sum(control);
+	csum = -csum;
+	hdr->checksum = csum;
+	res = __write_table_header(control);
 
-	__decode_table_header_from_buff(hdr, &buff[2]);
+	control->ras_num_recs = 0;
+	control->ras_fri = 0;
 
-	if (hdr->header == EEPROM_TABLE_HDR_VAL) {
-		control->num_recs = (hdr->tbl_size - EEPROM_TABLE_HEADER_SIZE) /
-				    EEPROM_TABLE_RECORD_SIZE;
-		control->tbl_byte_sum = __calc_hdr_byte_sum(control);
-		control->next_addr = EEPROM_RECORD_START;
+	amdgpu_ras_debugfs_set_ret_size(control);
 
-		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
-				 control->num_recs);
-
-	} else if ((hdr->header == EEPROM_TABLE_HDR_BAD) &&
-			(amdgpu_bad_page_threshold != 0)) {
-		if (ras->bad_page_cnt_threshold > control->num_recs) {
-			dev_info(adev->dev, "Using one valid bigger bad page "
-				"threshold and correcting eeprom header tag.\n");
-			ret = amdgpu_ras_eeprom_correct_header_tag(control,
-							EEPROM_TABLE_HDR_VAL);
-		} else {
-			*exceed_err_limit = true;
-			dev_err(adev->dev, "Exceeding the bad_page_threshold parameter, "
-				"disabling the GPU.\n");
-		}
-	} else {
-		DRM_INFO("Creating new EEPROM table");
+	mutex_unlock(&control->ras_tbl_mutex);
 
-		ret = amdgpu_ras_eeprom_reset_table(control);
-	}
-
-	return ret == 1 ? 0 : -EIO;
+	return res;
 }
 
-static void __encode_table_record_to_buff(struct amdgpu_ras_eeprom_control *control,
-					  struct eeprom_table_record *record,
-					  unsigned char *buff)
+static void
+__encode_table_record_to_buf(struct amdgpu_ras_eeprom_control *control,
+			     struct eeprom_table_record *record,
+			     unsigned char *buf)
 {
 	__le64 tmp = 0;
 	int i = 0;
 
 	/* Next are all record fields according to EEPROM page spec in LE foramt */
-	buff[i++] = record->err_type;
+	buf[i++] = record->err_type;
 
-	buff[i++] = record->bank;
+	buf[i++] = record->bank;
 
 	tmp = cpu_to_le64(record->ts);
-	memcpy(buff + i, &tmp, 8);
+	memcpy(buf + i, &tmp, 8);
 	i += 8;
 
 	tmp = cpu_to_le64((record->offset & 0xffffffffffff));
-	memcpy(buff + i, &tmp, 6);
+	memcpy(buf + i, &tmp, 6);
 	i += 6;
 
-	buff[i++] = record->mem_channel;
-	buff[i++] = record->mcumc_id;
+	buf[i++] = record->mem_channel;
+	buf[i++] = record->mcumc_id;
 
 	tmp = cpu_to_le64((record->retired_page & 0xffffffffffff));
-	memcpy(buff + i, &tmp, 6);
+	memcpy(buf + i, &tmp, 6);
 }
 
-static void __decode_table_record_from_buff(struct amdgpu_ras_eeprom_control *control,
-					    struct eeprom_table_record *record,
-					    unsigned char *buff)
+static void
+__decode_table_record_from_buf(struct amdgpu_ras_eeprom_control *control,
+			       struct eeprom_table_record *record,
+			       unsigned char *buf)
 {
 	__le64 tmp = 0;
 	int i =  0;
 
 	/* Next are all record fields according to EEPROM page spec in LE foramt */
-	record->err_type = buff[i++];
+	record->err_type = buf[i++];
 
-	record->bank = buff[i++];
+	record->bank = buf[i++];
 
-	memcpy(&tmp, buff + i, 8);
+	memcpy(&tmp, buf + i, 8);
 	record->ts = le64_to_cpu(tmp);
 	i += 8;
 
-	memcpy(&tmp, buff + i, 6);
+	memcpy(&tmp, buf + i, 6);
 	record->offset = (le64_to_cpu(tmp) & 0xffffffffffff);
 	i += 6;
 
-	record->mem_channel = buff[i++];
-	record->mcumc_id = buff[i++];
+	record->mem_channel = buf[i++];
+	record->mcumc_id = buf[i++];
 
-	memcpy(&tmp, buff + i,  6);
+	memcpy(&tmp, buf + i,  6);
 	record->retired_page = (le64_to_cpu(tmp) & 0xffffffffffff);
 }
 
-/*
- * When reaching end of EEPROM memory jump back to 0 record address
- * When next record access will go beyond EEPROM page boundary modify bits A17/A8
- * in I2C selector to go to next page
- */
-static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
-{
-	uint32_t next_address = curr_address + EEPROM_TABLE_RECORD_SIZE;
-
-	/* When all EEPROM memory used jump back to 0 address */
-	if (next_address > EEPROM_SIZE_BYTES) {
-		DRM_INFO("Reached end of EEPROM memory, jumping to 0 "
-			 "and overriding old record");
-		return EEPROM_RECORD_START;
-	}
-
-	/*
-	 * To check if we overflow page boundary  compare next address with
-	 * current and see if bits 17/8 of the EEPROM address will change
-	 * If they do start from the next 256b page
-	 *
-	 * https://www.st.com/resource/en/datasheet/m24m02-dr.pdf sec. 5.1.2
-	 */
-	if ((curr_address & EEPROM_ADDR_MSB_MASK) != (next_address & EEPROM_ADDR_MSB_MASK)) {
-		DRM_DEBUG_DRIVER("Reached end of EEPROM memory page, jumping to next: %lx",
-				(next_address & EEPROM_ADDR_MSB_MASK));
-
-		return  (next_address & EEPROM_ADDR_MSB_MASK);
-	}
-
-	return curr_address;
-}
-
 bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -458,197 +362,756 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev)
 		if (!(con->features & BIT(AMDGPU_RAS_BLOCK__UMC)))
 			return false;
 
-	if (con->eeprom_control.tbl_hdr.header == EEPROM_TABLE_HDR_BAD) {
+	if (con->eeprom_control.tbl_hdr.header == RAS_TABLE_HDR_BAD) {
 		dev_warn(adev->dev, "This GPU is in BAD status.");
-		dev_warn(adev->dev, "Please retire it or setting one bigger "
-				"threshold value when reloading driver.\n");
+		dev_warn(adev->dev, "Please retire it or set a larger "
+			 "threshold value when reloading driver.\n");
 		return true;
 	}
 
 	return false;
 }
 
-int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
-					    struct eeprom_table_record *records,
-					    bool write,
-					    int num)
+/**
+ * __amdgpu_ras_eeprom_write -- write indexed from buffer to EEPROM
+ * @control: pointer to control structure
+ * @buf: pointer to buffer containing data to write
+ * @fri: start writing at this index
+ * @num: number of records to write
+ *
+ * The caller must hold the table mutex in @control.
+ * Return 0 on success, -errno otherwise.
+ */
+static int __amdgpu_ras_eeprom_write(struct amdgpu_ras_eeprom_control *control,
+				     u8 *buf, const u32 fri, const u32 num)
 {
-	int i, ret = 0;
-	struct i2c_msg *msgs, *msg;
-	unsigned char *buffs, *buff;
-	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
-	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	u32 buf_size;
+	int res;
 
-	if (!__is_ras_eeprom_supported(adev))
-		return 0;
+	/* i2c may be unstable in gpu reset */
+	down_read(&adev->reset_sem);
+	buf_size = num * RAS_TABLE_RECORD_SIZE;
+	res = amdgpu_eeprom_write(&adev->pm.smu_i2c,
+				  control->i2c_address +
+				  RAS_INDEX_TO_OFFSET(control, fri),
+				  buf, buf_size);
+	up_read(&adev->reset_sem);
+	if (res < 0) {
+		DRM_ERROR("Writing %d EEPROM table records error:%d",
+			  num, res);
+	} else if (res < buf_size) {
+		/* Short write, return error.
+		 */
+		DRM_ERROR("Wrote %d records out of %d",
+			  res / RAS_TABLE_RECORD_SIZE, num);
+		res = -EIO;
+	} else {
+		res = 0;
+	}
 
-	buffs = kcalloc(num, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE,
-			 GFP_KERNEL);
-	if (!buffs)
-		return -ENOMEM;
+	return res;
+}
 
-	mutex_lock(&control->tbl_mutex);
+static int
+amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
+			       struct eeprom_table_record *record,
+			       const u32 num)
+{
+	u32 a, b, i;
+	u8 *buf, *pp;
+	int res;
+
+	buf = kcalloc(num, RAS_TABLE_RECORD_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
-	msgs = kcalloc(num, sizeof(*msgs), GFP_KERNEL);
-	if (!msgs) {
-		ret = -ENOMEM;
-		goto free_buff;
+	/* Encode all of them in one go.
+	 */
+	pp = buf;
+	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE)
+		__encode_table_record_to_buf(control, &record[i], pp);
+
+	/* a, first record index to write into.
+	 * b, last record index to write into.
+	 * a = first index to read (fri) + number of records in the table,
+	 * b = a + @num - 1.
+	 * Let N = control->ras_max_num_record_count, then we have,
+	 * case 0: 0 <= a <= b < N,
+	 *   just append @num records starting at a;
+	 * case 1: 0 <= a < N <= b,
+	 *   append (N - a) records starting at a, and
+	 *   append the remainder,  b % N + 1, starting at 0.
+	 * case 2: 0 <= fri < N <= a <= b, then modulo N we get two subcases,
+	 * case 2a: 0 <= a <= b < N
+	 *   append num records starting at a; and fix fri if b overwrote it,
+	 *   and since a <= b, if b overwrote it then a must've also,
+	 *   and if b didn't overwrite it, then a didn't also.
+	 * case 2b: 0 <= b < a < N
+	 *   write num records starting at a, which wraps around 0=N
+	 *   and overwrite fri unconditionally. Now from case 2a,
+	 *   this means that b eclipsed fri to overwrite it and wrap
+	 *   around 0 again, i.e. b = 2N+r pre modulo N, so we unconditionally
+	 *   set fri = b + 1 (mod N).
+	 * Now, since fri is updated in every case, except the trivial case 0,
+	 * the number of records present in the table after writing, is,
+	 * num_recs - 1 = b - fri (mod N), and we take the positive value,
+	 * by adding an arbitrary multiple of N before taking the modulo N
+	 * as shown below.
+	 */
+	a = control->ras_fri + control->ras_num_recs;
+	b = a + num  - 1;
+	if (b < control->ras_max_record_count) {
+		res = __amdgpu_ras_eeprom_write(control, buf, a, num);
+	} else if (a < control->ras_max_record_count) {
+		u32 g0, g1;
+
+		g0 = control->ras_max_record_count - a;
+		g1 = b % control->ras_max_record_count + 1;
+		res = __amdgpu_ras_eeprom_write(control, buf, a, g0);
+		if (res)
+			goto Out;
+		res = __amdgpu_ras_eeprom_write(control,
+						buf + g0 * RAS_TABLE_RECORD_SIZE,
+						0, g1);
+		if (res)
+			goto Out;
+		if (g1 > control->ras_fri)
+			control->ras_fri = g1 % control->ras_max_record_count;
+	} else {
+		a %= control->ras_max_record_count;
+		b %= control->ras_max_record_count;
+
+		if (a <= b) {
+			/* Note that, b - a + 1 = num. */
+			res = __amdgpu_ras_eeprom_write(control, buf, a, num);
+			if (res)
+				goto Out;
+			if (b >= control->ras_fri)
+				control->ras_fri = (b + 1) % control->ras_max_record_count;
+		} else {
+			u32 g0, g1;
+
+			/* b < a, which means, we write from
+			 * a to the end of the table, and from
+			 * the start of the table to b.
+			 */
+			g0 = control->ras_max_record_count - a;
+			g1 = b + 1;
+			res = __amdgpu_ras_eeprom_write(control, buf, a, g0);
+			if (res)
+				goto Out;
+			res = __amdgpu_ras_eeprom_write(control,
+							buf + g0 * RAS_TABLE_RECORD_SIZE,
+							0, g1);
+			if (res)
+				goto Out;
+			control->ras_fri = g1 % control->ras_max_record_count;
+		}
 	}
+	control->ras_num_recs = 1 + (control->ras_max_record_count + b
+				     - control->ras_fri)
+		% control->ras_max_record_count;
+Out:
+	kfree(buf);
+	return res;
+}
 
-	/*
-	 * If saved bad pages number exceeds the bad page threshold for
-	 * the whole VRAM, update table header to mark the BAD GPU tag
-	 * and schedule one ras recovery after eeprom write is done,
-	 * this can avoid the missing for latest records.
-	 *
-	 * This new header will be picked up and checked in the bootup
-	 * by ras recovery, which may break bootup process to notify
-	 * user this GPU is in bad state and to retire such GPU for
-	 * further check.
+static int
+amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	u8 *buf, *pp, csum;
+	u32 buf_size;
+	int res;
+
+	/* Modify the header if it exceeds.
 	 */
-	if (write && (amdgpu_bad_page_threshold != 0) &&
-		((control->num_recs + num) >= ras->bad_page_cnt_threshold)) {
+	if (amdgpu_bad_page_threshold != 0 &&
+	    control->ras_num_recs >= ras->bad_page_cnt_threshold) {
 		dev_warn(adev->dev,
-			"Saved bad pages(%d) reaches threshold value(%d).\n",
-			control->num_recs + num, ras->bad_page_cnt_threshold);
-		control->tbl_hdr.header = EEPROM_TABLE_HDR_BAD;
+			"Saved bad pages %d reaches threshold value %d\n",
+			control->ras_num_recs, ras->bad_page_cnt_threshold);
+		control->tbl_hdr.header = RAS_TABLE_HDR_BAD;
+	}
+
+	control->tbl_hdr.version = RAS_TABLE_VER;
+	control->tbl_hdr.first_rec_offset = RAS_INDEX_TO_OFFSET(control, control->ras_fri);
+	control->tbl_hdr.tbl_size = RAS_TABLE_HEADER_SIZE + control->ras_num_recs * RAS_TABLE_RECORD_SIZE;
+	control->tbl_hdr.checksum = 0;
+
+	buf_size = control->ras_num_recs * RAS_TABLE_RECORD_SIZE;
+	buf = kcalloc(control->ras_num_recs, RAS_TABLE_RECORD_SIZE, GFP_KERNEL);
+	if (!buf) {
+		DRM_ERROR("allocating memory for table of size %d bytes failed\n",
+			  control->tbl_hdr.tbl_size);
+		res = -ENOMEM;
+		goto Out;
 	}
 
-	/* In case of overflow just start from beginning to not lose newest records */
-	if (write && (control->next_addr + EEPROM_TABLE_RECORD_SIZE * num > EEPROM_SIZE_BYTES))
-		control->next_addr = EEPROM_RECORD_START;
+	down_read(&adev->reset_sem);
+	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+				 control->i2c_address +
+				 control->ras_record_offset,
+				 buf, buf_size);
+	up_read(&adev->reset_sem);
+	if (res < 0) {
+		DRM_ERROR("EEPROM failed reading records:%d\n",
+			  res);
+		goto Out;
+	} else if (res < buf_size) {
+		DRM_ERROR("EEPROM read %d out of %d bytes\n",
+			  res, buf_size);
+		res = -EIO;
+		goto Out;
+	}
 
-	/*
-	 * TODO Currently makes EEPROM writes for each record, this creates
-	 * internal fragmentation. Optimized the code to do full page write of
-	 * 256b
+	/* Recalc the checksum.
 	 */
-	for (i = 0; i < num; i++) {
-		buff = &buffs[i * (EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
-		record = &records[i];
-		msg = &msgs[i];
+	csum = 0;
+	for (pp = buf; pp < buf + buf_size; pp++)
+		csum += *pp;
+
+	csum += __calc_hdr_byte_sum(control);
+	/* avoid sign extension when assigning to "checksum" */
+	csum = -csum;
+	control->tbl_hdr.checksum = csum;
+	res = __write_table_header(control);
+Out:
+	kfree(buf);
+	return res;
+}
 
-		control->next_addr = __correct_eeprom_dest_address(control->next_addr);
+/**
+ * amdgpu_ras_eeprom_append -- append records to the EEPROM RAS table
+ * @control: pointer to control structure
+ * @record: array of records to append
+ * @num: number of records in @record array
+ *
+ * Append @num records to the table, calculate the checksum and write
+ * the table back to EEPROM. The maximum number of records that
+ * can be appended is between 1 and control->ras_max_record_count,
+ * regardless of how many records are already stored in the table.
+ *
+ * Return 0 on success or if EEPROM is not supported, -errno on error.
+ */
+int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
+			     struct eeprom_table_record *record,
+			     const u32 num)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	int res;
 
-		/*
-		 * Update bits 16,17 of EEPROM address in I2C address by setting them
-		 * to bits 1,2 of Device address byte
-		 */
-		msg->addr = control->i2c_address |
-			        ((control->next_addr & EEPROM_ADDR_MSB_MASK) >> 15);
-		msg->flags	= write ? 0 : I2C_M_RD;
-		msg->len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE;
-		msg->buf	= buff;
-
-		/* Insert the EEPROM dest addess, bits 0-15 */
-		buff[0] = ((control->next_addr >> 8) & 0xff);
-		buff[1] = (control->next_addr & 0xff);
-
-		/* EEPROM table content is stored in LE format */
-		if (write)
-			__encode_table_record_to_buff(control, record, buff + EEPROM_ADDRESS_SIZE);
-
-		/*
-		 * The destination EEPROM address might need to be corrected to account
-		 * for page or entire memory wrapping
-		 */
-		control->next_addr += EEPROM_TABLE_RECORD_SIZE;
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
+	if (num == 0) {
+		DRM_ERROR("will not append 0 records\n");
+		return -EINVAL;
+	} else if (num > control->ras_max_record_count) {
+		DRM_ERROR("cannot append %d records than the size of table %d\n",
+			  num, control->ras_max_record_count);
+		return -EINVAL;
 	}
 
+	mutex_lock(&control->ras_tbl_mutex);
+
+	res = amdgpu_ras_eeprom_append_table(control, record, num);
+	if (!res)
+		res = amdgpu_ras_eeprom_update_header(control);
+	if (!res)
+		amdgpu_ras_debugfs_set_ret_size(control);
+
+	mutex_unlock(&control->ras_tbl_mutex);
+	return res;
+}
+
+/**
+ * __amdgpu_ras_eeprom_read -- read indexed from EEPROM into buffer
+ * @control: pointer to control structure
+ * @buf: pointer to buffer to read into
+ * @fri: first record index, start reading at this index, absolute index
+ * @num: number of records to read
+ *
+ * The caller must hold the table mutex in @control.
+ * Return 0 on success, -errno otherwise.
+ */
+static int __amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
+				    u8 *buf, const u32 fri, const u32 num)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	u32 buf_size;
+	int res;
+
 	/* i2c may be unstable in gpu reset */
 	down_read(&adev->reset_sem);
-	ret = i2c_transfer(&adev->pm.smu_i2c, msgs, num);
+	buf_size = num * RAS_TABLE_RECORD_SIZE;
+	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+				 control->i2c_address +
+				 RAS_INDEX_TO_OFFSET(control, fri),
+				 buf, buf_size);
 	up_read(&adev->reset_sem);
+	if (res < 0) {
+		DRM_ERROR("Reading %d EEPROM table records error:%d",
+			  num, res);
+	} else if (res < buf_size) {
+		/* Short read, return error.
+		 */
+		DRM_ERROR("Read %d records out of %d",
+			  res / RAS_TABLE_RECORD_SIZE, num);
+		res = -EIO;
+	} else {
+		res = 0;
+	}
+
+	return res;
+}
+
+/**
+ * amdgpu_ras_eeprom_read -- read EEPROM
+ * @control: pointer to control structure
+ * @record: array of records to read into
+ * @num: number of records in @record
+ *
+ * Reads num records from the RAS table in EEPROM and
+ * writes the data into @record array.
+ *
+ * Returns 0 on success, -errno on error.
+ */
+int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
+			   struct eeprom_table_record *record,
+			   const u32 num)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	int i, res;
+	u8 *buf, *pp;
+	u32 g0, g1;
 
-	if (ret < 1) {
-		DRM_ERROR("Failed to process EEPROM table records, ret:%d", ret);
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
 
-		/* TODO Restore prev next EEPROM address ? */
-		goto free_msgs;
+	if (num == 0) {
+		DRM_ERROR("will not read 0 records\n");
+		return -EINVAL;
+	} else if (num > control->ras_num_recs) {
+		DRM_ERROR("too many records to read:%d available:%d\n",
+			  num, control->ras_num_recs);
+		return -EINVAL;
 	}
 
+	buf = kcalloc(num, RAS_TABLE_RECORD_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
-	if (!write) {
-		for (i = 0; i < num; i++) {
-			buff = &buffs[i*(EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
-			record = &records[i];
+	/* Determine how many records to read, from the first record
+	 * index, fri, to the end of the table, and from the beginning
+	 * of the table, such that the total number of records is
+	 * @num, and we handle wrap around when fri > 0 and
+	 * fri + num > RAS_MAX_RECORD_COUNT.
+	 *
+	 * First we compute the index of the last element
+	 * which would be fetched from each region,
+	 * g0 is in [fri, fri + num - 1], and
+	 * g1 is in [0, RAS_MAX_RECORD_COUNT - 1].
+	 * Then, if g0 < RAS_MAX_RECORD_COUNT, the index of
+	 * the last element to fetch, we set g0 to _the number_
+	 * of elements to fetch, @num, since we know that the last
+	 * indexed to be fetched does not exceed the table.
+	 *
+	 * If, however, g0 >= RAS_MAX_RECORD_COUNT, then
+	 * we set g0 to the number of elements to read
+	 * until the end of the table, and g1 to the number of
+	 * elements to read from the beginning of the table.
+	 */
+	g0 = control->ras_fri + num - 1;
+	g1 = g0 % control->ras_max_record_count;
+	if (g0 < control->ras_max_record_count) {
+		g0 = num;
+		g1 = 0;
+	} else {
+		g0 = control->ras_max_record_count - control->ras_fri;
+		g1 += 1;
+	}
 
-			__decode_table_record_from_buff(control, record, buff + EEPROM_ADDRESS_SIZE);
-		}
+	mutex_lock(&control->ras_tbl_mutex);
+	res = __amdgpu_ras_eeprom_read(control, buf, control->ras_fri, g0);
+	if (res)
+		goto Out;
+	if (g1) {
+		res = __amdgpu_ras_eeprom_read(control,
+					       buf + g0 * RAS_TABLE_RECORD_SIZE,
+					       0, g1);
+		if (res)
+			goto Out;
 	}
 
-	if (write) {
-		uint32_t old_hdr_byte_sum = __calc_hdr_byte_sum(control);
+	res = 0;
+
+	/* Read up everything? Then transform.
+	 */
+	pp = buf;
+	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE)
+		__decode_table_record_from_buf(control, &record[i], pp);
+Out:
+	kfree(buf);
+	mutex_unlock(&control->ras_tbl_mutex);
+
+	return res;
+}
+
+inline uint32_t amdgpu_ras_eeprom_max_record_count(void)
+{
+	return RAS_MAX_RECORD_COUNT;
+}
+
+static ssize_t
+amdgpu_ras_debugfs_eeprom_size_read(struct file *f, char __user *buf,
+				    size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	struct amdgpu_ras_eeprom_control *control = ras ? &ras->eeprom_control : NULL;
+	u8 data[50];
+	int res;
+
+	if (!size)
+		return size;
+
+	if (!ras || !control) {
+		res = snprintf(data, sizeof(data), "Not supported\n");
+	} else {
+		res = snprintf(data, sizeof(data), "%d bytes or %d records\n",
+			       RAS_TBL_SIZE_BYTES, control->ras_max_record_count);
+	}
+
+	if (*pos >= res)
+		return 0;
+
+	res -= *pos;
+	res = min_t(size_t, res, size);
+
+	if (copy_to_user(buf, &data[*pos], res))
+		return -EFAULT;
+
+	*pos += res;
 
-		/*
-		 * Update table header with size and CRC and account for table
-		 * wrap around where the assumption is that we treat it as empty
-		 * table
-		 *
-		 * TODO - Check the assumption is correct
+	return res;
+}
+
+const struct file_operations amdgpu_ras_debugfs_eeprom_size_ops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_ras_debugfs_eeprom_size_read,
+	.write = NULL,
+	.llseek = default_llseek,
+};
+
+static const char *tbl_hdr_str = " Signature    Version  FirstOffs       Size   Checksum\n";
+static const char *tbl_hdr_fmt = "0x%08X 0x%08X 0x%08X 0x%08X 0x%08X\n";
+#define tbl_hdr_fmt_size (5 * (2+8) + 4 + 1)
+static const char *rec_hdr_str = "Index  Offset ErrType Bank/CU          TimeStamp      Offs/Addr MemChl MCUMCID    RetiredPage\n";
+static const char *rec_hdr_fmt = "%5d 0x%05X %7s    0x%02X 0x%016llX 0x%012llX   0x%02X    0x%02X 0x%012llX\n";
+#define rec_hdr_fmt_size (5 + 1 + 7 + 1 + 7 + 1 + 7 + 1 + 18 + 1 + 14 + 1 + 6 + 1 + 7 + 1 + 14 + 1)
+
+static const char *record_err_type_str[AMDGPU_RAS_EEPROM_ERR_COUNT] = {
+	"ignore",
+	"re",
+	"ue",
+};
+
+static loff_t amdgpu_ras_debugfs_table_size(struct amdgpu_ras_eeprom_control *control)
+{
+	return strlen(tbl_hdr_str) + tbl_hdr_fmt_size +
+		strlen(rec_hdr_str) + rec_hdr_fmt_size * control->ras_num_recs;
+}
+
+void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control)
+{
+	struct amdgpu_ras *ras = container_of(control, struct amdgpu_ras,
+					      eeprom_control);
+	struct dentry *de = ras->de_ras_eeprom_table;
+
+	if (de)
+		d_inode(de)->i_size = amdgpu_ras_debugfs_table_size(control);
+}
+
+static ssize_t amdgpu_ras_debugfs_table_read(struct file *f, char __user *buf,
+					     size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	struct amdgpu_ras_eeprom_control *control = &ras->eeprom_control;
+	const size_t orig_size = size;
+	int res = -EFAULT;
+	size_t data_len;
+
+	mutex_lock(&control->ras_tbl_mutex);
+
+	/* We want *pos - data_len > 0, which means there's
+	 * bytes to be printed from data.
+	 */
+	data_len = strlen(tbl_hdr_str);
+	if (*pos < data_len) {
+		data_len -= *pos;
+		data_len = min_t(size_t, data_len, size);
+		if (copy_to_user(buf, &tbl_hdr_str[*pos], data_len))
+			goto Out;
+		buf += data_len;
+		size -= data_len;
+		*pos += data_len;
+	}
+
+	data_len = strlen(tbl_hdr_str) + tbl_hdr_fmt_size;
+	if (*pos < data_len && size > 0) {
+		u8 data[tbl_hdr_fmt_size + 1];
+		loff_t lpos;
+
+		snprintf(data, sizeof(data), tbl_hdr_fmt,
+			 control->tbl_hdr.header,
+			 control->tbl_hdr.version,
+			 control->tbl_hdr.first_rec_offset,
+			 control->tbl_hdr.tbl_size,
+			 control->tbl_hdr.checksum);
+
+		data_len -= *pos;
+		data_len = min_t(size_t, data_len, size);
+		lpos = *pos - strlen(tbl_hdr_str);
+		if (copy_to_user(buf, &data[lpos], data_len))
+			goto Out;
+		buf += data_len;
+		size -= data_len;
+		*pos += data_len;
+	}
+
+	data_len = strlen(tbl_hdr_str) + tbl_hdr_fmt_size + strlen(rec_hdr_str);
+	if (*pos < data_len && size > 0) {
+		loff_t lpos;
+
+		data_len -= *pos;
+		data_len = min_t(size_t, data_len, size);
+		lpos = *pos - strlen(tbl_hdr_str) - tbl_hdr_fmt_size;
+		if (copy_to_user(buf, &rec_hdr_str[lpos], data_len))
+			goto Out;
+		buf += data_len;
+		size -= data_len;
+		*pos += data_len;
+	}
+
+	data_len = amdgpu_ras_debugfs_table_size(control);
+	if (*pos < data_len && size > 0) {
+		u8 dare[RAS_TABLE_RECORD_SIZE];
+		u8 data[rec_hdr_fmt_size + 1];
+		struct eeprom_table_record record;
+		int s, r;
+
+		/* Find the starting record index
 		 */
-		control->num_recs += num;
-		control->num_recs %= EEPROM_MAX_RECORD_NUM;
-		control->tbl_hdr.tbl_size += EEPROM_TABLE_RECORD_SIZE * num;
-		if (control->tbl_hdr.tbl_size > EEPROM_SIZE_BYTES)
-			control->tbl_hdr.tbl_size = EEPROM_TABLE_HEADER_SIZE +
-			control->num_recs * EEPROM_TABLE_RECORD_SIZE;
-
-		__update_tbl_checksum(control, records, num, old_hdr_byte_sum);
-
-		__update_table_header(control, buffs);
-	} else if (!__validate_tbl_checksum(control, records, num)) {
-		DRM_WARN("EEPROM Table checksum mismatch!");
-		/* TODO Uncomment when EEPROM read/write is relliable */
-		/* ret = -EIO; */
+		s = *pos - strlen(tbl_hdr_str) - tbl_hdr_fmt_size -
+			strlen(rec_hdr_str);
+		s = s / rec_hdr_fmt_size;
+		r = *pos - strlen(tbl_hdr_str) - tbl_hdr_fmt_size -
+			strlen(rec_hdr_str);
+		r = r % rec_hdr_fmt_size;
+
+		for ( ; size > 0 && s < control->ras_num_recs; s++) {
+			u32 ai = RAS_RI_TO_AI(control, s);
+			/* Read a single record
+			 */
+			res = __amdgpu_ras_eeprom_read(control, dare, ai, 1);
+			if (res)
+				goto Out;
+			__decode_table_record_from_buf(control, &record, dare);
+			snprintf(data, sizeof(data), rec_hdr_fmt,
+				 s,
+				 RAS_INDEX_TO_OFFSET(control, ai),
+				 record_err_type_str[record.err_type],
+				 record.bank,
+				 record.ts,
+				 record.offset,
+				 record.mem_channel,
+				 record.mcumc_id,
+				 record.retired_page);
+
+			data_len = min_t(size_t, rec_hdr_fmt_size - r, size);
+			if (copy_to_user(buf, &data[r], data_len)) {
+				res = -EFAULT;
+				goto Out;
+			}
+			buf += data_len;
+			size -= data_len;
+			*pos += data_len;
+			r = 0;
+		}
 	}
+	res = 0;
+Out:
+	mutex_unlock(&control->ras_tbl_mutex);
+	return res < 0 ? res : orig_size - size;
+}
 
-free_msgs:
-	kfree(msgs);
+static ssize_t
+amdgpu_ras_debugfs_eeprom_table_read(struct file *f, char __user *buf,
+				     size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	struct amdgpu_ras_eeprom_control *control = ras ? &ras->eeprom_control : NULL;
+	u8 data[81];
+	int res;
+
+	if (!size)
+		return size;
+
+	if (!ras || !control) {
+		res = snprintf(data, sizeof(data), "Not supported\n");
+		if (*pos >= res)
+			return 0;
+
+		res -= *pos;
+		res = min_t(size_t, res, size);
 
-free_buff:
-	kfree(buffs);
+		if (copy_to_user(buf, &data[*pos], res))
+			return -EFAULT;
 
-	mutex_unlock(&control->tbl_mutex);
+		*pos += res;
 
-	return ret == num ? 0 : -EIO;
+		return res;
+	} else {
+		return amdgpu_ras_debugfs_table_read(f, buf, size, pos);
+	}
 }
 
-inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void)
+const struct file_operations amdgpu_ras_debugfs_eeprom_table_ops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_ras_debugfs_eeprom_table_read,
+	.write = NULL,
+	.llseek = default_llseek,
+};
+
+/**
+ * __verify_ras_table_checksum -- verify the RAS EEPROM table checksum
+ * @control: pointer to control structure
+ *
+ * Check the checksum of the stored in EEPROM RAS table.
+ *
+ * Return 0 if the checksum is correct,
+ * positive if it is not correct, and
+ * -errno on I/O error.
+ */
+static int __verify_ras_table_checksum(struct amdgpu_ras_eeprom_control *control)
 {
-	return EEPROM_MAX_RECORD_NUM;
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	int buf_size, res;
+	u8  csum, *buf, *pp;
+
+	buf_size = RAS_TABLE_HEADER_SIZE +
+		control->ras_num_recs * RAS_TABLE_RECORD_SIZE;
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		DRM_ERROR("Out of memory checking RAS table checksum.\n");
+		return -ENOMEM;
+	}
+
+	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+				 control->i2c_address +
+				 control->ras_header_offset,
+				 buf, buf_size);
+	if (res < buf_size) {
+		DRM_ERROR("Partial read for checksum, res:%d\n", res);
+		/* On partial reads, return -EIO.
+		 */
+		if (res >= 0)
+			res = -EIO;
+		goto Out;
+	}
+
+	csum = 0;
+	for (pp = buf; pp < buf + buf_size; pp++)
+		csum += *pp;
+Out:
+	kfree(buf);
+	return res < 0 ? res : csum;
 }
 
-/* Used for testing if bugs encountered */
-#if 0
-void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control)
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			   bool *exceed_err_limit)
 {
-	int i;
-	struct eeprom_table_record *recs = kcalloc(1, sizeof(*recs), GFP_KERNEL);
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	unsigned char buf[RAS_TABLE_HEADER_SIZE] = { 0 };
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int res;
+
+	*exceed_err_limit = false;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
 
-	if (!recs)
-		return;
+	/* Verify i2c adapter is initialized */
+	if (!adev->pm.smu_i2c.algo)
+		return -ENOENT;
 
-	for (i = 0; i < 1 ; i++) {
-		recs[i].address = 0xdeadbeef;
-		recs[i].retired_page = i;
+	if (!__get_eeprom_i2c_addr(adev, control))
+		return -EINVAL;
+
+	control->ras_header_offset = RAS_HDR_START;
+	control->ras_record_offset = RAS_RECORD_START;
+	control->ras_max_record_count  = RAS_MAX_RECORD_COUNT;
+	mutex_init(&control->ras_tbl_mutex);
+
+	/* Read the table header from EEPROM address */
+	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+				 control->i2c_address + control->ras_header_offset,
+				 buf, RAS_TABLE_HEADER_SIZE);
+	if (res < RAS_TABLE_HEADER_SIZE) {
+		DRM_ERROR("Failed to read EEPROM table header, res:%d", res);
+		return res >= 0 ? -EIO : res;
 	}
 
-	if (!amdgpu_ras_eeprom_process_recods(control, recs, true, 1)) {
+	__decode_table_header_from_buf(hdr, buf);
 
-		memset(recs, 0, sizeof(*recs) * 1);
+	control->ras_num_recs = RAS_NUM_RECS(hdr);
+	control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset);
 
-		control->next_addr = EEPROM_RECORD_START;
+	if (hdr->header == RAS_TABLE_HDR_VAL) {
+		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
+				 control->ras_num_recs);
+		res = __verify_ras_table_checksum(control);
+		if (res)
+			DRM_ERROR("RAS table incorrect checksum or error:%d\n",
+				  res);
+	} else if (hdr->header == RAS_TABLE_HDR_BAD &&
+		   amdgpu_bad_page_threshold != 0) {
+		res = __verify_ras_table_checksum(control);
+		if (res)
+			DRM_ERROR("RAS Table incorrect checksum or error:%d\n",
+				  res);
+		if (ras->bad_page_cnt_threshold > control->ras_num_recs) {
+			/* This means that, the threshold was increased since
+			 * the last time the system was booted, and now,
+			 * ras->bad_page_cnt_threshold - control->num_recs > 0,
+			 * so that at least one more record can be saved,
+			 * before the page count threshold is reached.
+			 */
+			dev_info(adev->dev,
+				 "records:%d threshold:%d, resetting "
+				 "RAS table header signature",
+				 control->ras_num_recs,
+				 ras->bad_page_cnt_threshold);
+			res = amdgpu_ras_eeprom_correct_header_tag(control,
+								   RAS_TABLE_HDR_VAL);
+		} else {
+			*exceed_err_limit = true;
+			dev_err(adev->dev,
+				"RAS records:%d exceed threshold:%d, "
+				"maybe retire this GPU?",
+				control->ras_num_recs, ras->bad_page_cnt_threshold);
+		}
+	} else {
+		DRM_INFO("Creating a new EEPROM table");
 
-		if (!amdgpu_ras_eeprom_process_recods(control, recs, false, 1)) {
-			for (i = 0; i < 1; i++)
-				DRM_INFO("rec.address :0x%llx, rec.retired_page :%llu",
-					 recs[i].address, recs[i].retired_page);
-		} else
-			DRM_ERROR("Failed in reading from table");
+		res = amdgpu_ras_eeprom_reset_table(control);
+	}
 
-	} else
-		DRM_ERROR("Failed in writing to table");
+	return res < 0 ? res : 0;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index 178721170974..f95fc61b3021 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -28,10 +28,11 @@
 
 struct amdgpu_device;
 
-enum amdgpu_ras_eeprom_err_type{
-	AMDGPU_RAS_EEPROM_ERR_PLACE_HOLDER,
+enum amdgpu_ras_eeprom_err_type {
+	AMDGPU_RAS_EEPROM_ERR_NA,
 	AMDGPU_RAS_EEPROM_ERR_RECOVERABLE,
-	AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE
+	AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE,
+	AMDGPU_RAS_EEPROM_ERR_COUNT,
 };
 
 struct amdgpu_ras_eeprom_table_header {
@@ -40,15 +41,45 @@ struct amdgpu_ras_eeprom_table_header {
 	uint32_t first_rec_offset;
 	uint32_t tbl_size;
 	uint32_t checksum;
-}__attribute__((__packed__));
+} __packed;
 
 struct amdgpu_ras_eeprom_control {
 	struct amdgpu_ras_eeprom_table_header tbl_hdr;
-	uint32_t next_addr;
-	unsigned int num_recs;
-	struct mutex tbl_mutex;
-	uint32_t tbl_byte_sum;
-	uint16_t i2c_address; // 8-bit represented address
+
+	/* Base I2C EEPPROM 19-bit memory address,
+	 * where the table is located. For more information,
+	 * see top of amdgpu_eeprom.c.
+	 */
+	u32 i2c_address;
+
+	/* The byte offset off of @i2c_address
+	 * where the table header is found,
+	 * and where the records start--always
+	 * right after the header.
+	 */
+	u32 ras_header_offset;
+	u32 ras_record_offset;
+
+	/* Number of records in the table.
+	 */
+	u32 ras_num_recs;
+
+	/* First record index to read, 0-based.
+	 * Range is [0, num_recs-1]. This is
+	 * an absolute index, starting right after
+	 * the table header.
+	 */
+	u32 ras_fri;
+
+	/* Maximum possible number of records
+	 * we could store, i.e. the maximum capacity
+	 * of the table.
+	 */
+	u32 ras_max_record_count;
+
+	/* Protect table access via this mutex.
+	 */
+	struct mutex ras_tbl_mutex;
 };
 
 /*
@@ -74,21 +105,26 @@ struct eeprom_table_record {
 
 	unsigned char mem_channel;
 	unsigned char mcumc_id;
-}__attribute__((__packed__));
+} __packed;
 
 int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
-			bool *exceed_err_limit);
+			   bool *exceed_err_limit);
+
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control);
 
 bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev);
 
-int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
-					    struct eeprom_table_record *records,
-					    bool write,
-					    int num);
+int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
+			   struct eeprom_table_record *records, const u32 num);
+
+int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
+			     struct eeprom_table_record *records, const u32 num);
+
+inline uint32_t amdgpu_ras_eeprom_max_record_count(void);
 
-inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void);
+void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 
-void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control);
+extern const struct file_operations amdgpu_ras_debugfs_eeprom_size_ops;
+extern const struct file_operations amdgpu_ras_debugfs_eeprom_table_ops;
 
 #endif // _AMDGPU_RAS_EEPROM_H
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index e7d3d0dbdd96..e713d31619fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -48,6 +48,9 @@
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 #define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
+/* fence flag bit to indicate the face is embedded in job*/
+#define AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT		(DMA_FENCE_FLAG_USER_BITS + 1)
+
 #define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
 
 #define AMDGPU_IB_POOL_SIZE	(1024 * 1024)
@@ -106,9 +109,6 @@ struct amdgpu_fence_driver {
 	struct dma_fence		**fences;
 };
 
-int amdgpu_fence_driver_init(struct amdgpu_device *adev);
-void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev);
-void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
@@ -117,9 +117,11 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq_src,
 				   unsigned irq_type);
-void amdgpu_fence_driver_suspend(struct amdgpu_device *adev);
-void amdgpu_fence_driver_resume(struct amdgpu_device *adev);
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
+void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
+void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev);
+void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev);
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence, struct amdgpu_job *job,
 		      unsigned flags);
 int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
 			      uint32_t timeout);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 7a4775ab6804..00afd0dcae86 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -127,8 +127,8 @@ struct amdgpu_rlc_funcs {
 	void (*reset)(struct amdgpu_device *adev);
 	void (*start)(struct amdgpu_device *adev);
 	void (*update_spm_vmid)(struct amdgpu_device *adev, unsigned vmid);
-	void (*rlcg_wreg)(struct amdgpu_device *adev, u32 offset, u32 v, u32 acc_flags, u32 hwip);
-	u32 (*rlcg_rreg)(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip);
+	void (*sriov_wreg)(struct amdgpu_device *adev, u32 offset, u32 v, u32 acc_flags, u32 hwip);
+	u32 (*sriov_rreg)(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip);
 	bool (*is_rlcg_access_range)(struct amdgpu_device *adev, uint32_t reg);
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index de91d29c9d96..65debb65a5df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -105,7 +105,6 @@ int amdgpu_sdma_ras_late_init(struct amdgpu_device *adev,
 		adev->sdma.ras_if->block = AMDGPU_RAS_BLOCK__SDMA;
 		adev->sdma.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->sdma.ras_if->sub_block_index = 0;
-		strcpy(adev->sdma.ras_if->name, "sdma");
 	}
 	fs_info.head = ih_info->head = *adev->sdma.ras_if;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
index 123453999093..cc7597a15fe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
@@ -80,7 +80,7 @@ void psp_securedisplay_parse_resp_status(struct psp_context *psp,
 void psp_prep_securedisplay_cmd_buf(struct psp_context *psp, struct securedisplay_cmd **cmd,
 	enum ta_securedisplay_command command_id)
 {
-	*cmd = (struct securedisplay_cmd *)psp->securedisplay_context.securedisplay_shared_buf;
+	*cmd = (struct securedisplay_cmd *)psp->securedisplay_context.context.mem_context.shared_buf;
 	memset(*cmd, 0, sizeof(struct securedisplay_cmd));
 	(*cmd)->status = TA_SECUREDISPLAY_STATUS__GENERIC_FAILURE;
 	(*cmd)->cmd_id = command_id;
@@ -170,7 +170,7 @@ void amdgpu_securedisplay_debugfs_init(struct amdgpu_device *adev)
 {
 #if defined(CONFIG_DEBUG_FS)
 
-	if (!adev->psp.securedisplay_context.securedisplay_initialized)
+	if (!adev->psp.securedisplay_context.context.initialized)
 		return;
 
 	debugfs_create_file("securedisplay_test", S_IWUSR, adev_to_drm(adev)->primary->debugfs_root,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 1b2ceccaf5b0..862eb3c1c4c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -28,6 +28,8 @@
  *    Christian König <christian.koenig@amd.com>
  */
 
+#include <linux/dma-fence-chain.h>
+
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
@@ -186,6 +188,55 @@ int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence)
 	return amdgpu_sync_fence(sync, fence);
 }
 
+/* Determine based on the owner and mode if we should sync to a fence or not */
+static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
+				   enum amdgpu_sync_mode mode,
+				   void *owner, struct dma_fence *f)
+{
+	void *fence_owner = amdgpu_sync_get_owner(f);
+
+	/* Always sync to moves, no matter what */
+	if (fence_owner == AMDGPU_FENCE_OWNER_UNDEFINED)
+		return true;
+
+	/* We only want to trigger KFD eviction fences on
+	 * evict or move jobs. Skip KFD fences otherwise.
+	 */
+	if (fence_owner == AMDGPU_FENCE_OWNER_KFD &&
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+		return false;
+
+	/* Never sync to VM updates either. */
+	if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+		return false;
+
+	/* Ignore fences depending on the sync mode */
+	switch (mode) {
+	case AMDGPU_SYNC_ALWAYS:
+		return true;
+
+	case AMDGPU_SYNC_NE_OWNER:
+		if (amdgpu_sync_same_dev(adev, f) &&
+		    fence_owner == owner)
+			return false;
+		break;
+
+	case AMDGPU_SYNC_EQ_OWNER:
+		if (amdgpu_sync_same_dev(adev, f) &&
+		    fence_owner != owner)
+			return false;
+		break;
+
+	case AMDGPU_SYNC_EXPLICIT:
+		return false;
+	}
+
+	WARN(debug_evictions && fence_owner == AMDGPU_FENCE_OWNER_KFD,
+	     "Adding eviction fence to sync obj");
+	return true;
+}
+
 /**
  * amdgpu_sync_resv - sync to a reservation object
  *
@@ -211,67 +262,34 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
 
 	/* always sync to the exclusive fence */
 	f = dma_resv_excl_fence(resv);
-	r = amdgpu_sync_fence(sync, f);
+	dma_fence_chain_for_each(f, f) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(f);
+
+		if (amdgpu_sync_test_fence(adev, mode, owner, chain ?
+					   chain->fence : f)) {
+			r = amdgpu_sync_fence(sync, f);
+			dma_fence_put(f);
+			if (r)
+				return r;
+			break;
+		}
+	}
 
 	flist = dma_resv_shared_list(resv);
-	if (!flist || r)
-		return r;
+	if (!flist)
+		return 0;
 
 	for (i = 0; i < flist->shared_count; ++i) {
-		void *fence_owner;
-
 		f = rcu_dereference_protected(flist->shared[i],
 					      dma_resv_held(resv));
 
-		fence_owner = amdgpu_sync_get_owner(f);
-
-		/* Always sync to moves, no matter what */
-		if (fence_owner == AMDGPU_FENCE_OWNER_UNDEFINED) {
+		if (amdgpu_sync_test_fence(adev, mode, owner, f)) {
 			r = amdgpu_sync_fence(sync, f);
 			if (r)
-				break;
-		}
-
-		/* We only want to trigger KFD eviction fences on
-		 * evict or move jobs. Skip KFD fences otherwise.
-		 */
-		if (fence_owner == AMDGPU_FENCE_OWNER_KFD &&
-		    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
-			continue;
-
-		/* Never sync to VM updates either. */
-		if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
-		    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
-			continue;
-
-		/* Ignore fences depending on the sync mode */
-		switch (mode) {
-		case AMDGPU_SYNC_ALWAYS:
-			break;
-
-		case AMDGPU_SYNC_NE_OWNER:
-			if (amdgpu_sync_same_dev(adev, f) &&
-			    fence_owner == owner)
-				continue;
-			break;
-
-		case AMDGPU_SYNC_EQ_OWNER:
-			if (amdgpu_sync_same_dev(adev, f) &&
-			    fence_owner != owner)
-				continue;
-			break;
-
-		case AMDGPU_SYNC_EXPLICIT:
-			continue;
+				return r;
 		}
-
-		WARN(debug_evictions && fence_owner == AMDGPU_FENCE_OWNER_KFD,
-		     "Adding eviction fence to sync obj");
-		r = amdgpu_sync_fence(sync, f);
-		if (r)
-			break;
 	}
-	return r;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3a55f08e00e1..38dade421d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -149,14 +149,16 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BOs to be evicted from VRAM
 			 */
 			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-							 AMDGPU_GEM_DOMAIN_GTT);
+							AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
 			abo->placement.busy_placement = &abo->placements[1];
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 		}
 		break;
 	case TTM_PL_TT:
@@ -521,7 +523,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			hop->fpfn = 0;
 			hop->lpfn = 0;
 			hop->mem_type = TTM_PL_TT;
-			hop->flags = 0;
+			hop->flags = TTM_PL_FLAG_TEMPORARY;
 			return -EMULTIHOP;
 		}
 
@@ -1121,7 +1123,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
@@ -1146,7 +1148,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	struct amdgpu_device *adev;
 
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
 		kfree(ttm->sg);
 		ttm->sg = NULL;
@@ -1394,6 +1396,41 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	return ttm_bo_eviction_valuable(bo, place);
 }
 
+static void amdgpu_ttm_vram_mm_access(struct amdgpu_device *adev, loff_t pos,
+				      void *buf, size_t size, bool write)
+{
+	while (size) {
+		uint64_t aligned_pos = ALIGN_DOWN(pos, 4);
+		uint64_t bytes = 4 - (pos & 0x3);
+		uint32_t shift = (pos & 0x3) * 8;
+		uint32_t mask = 0xffffffff << shift;
+		uint32_t value = 0;
+
+		if (size < bytes) {
+			mask &= 0xffffffff >> (bytes - size) * 8;
+			bytes = size;
+		}
+
+		if (mask != 0xffffffff) {
+			amdgpu_device_mm_access(adev, aligned_pos, &value, 4, false);
+			if (write) {
+				value &= ~mask;
+				value |= (*(uint32_t *)buf << shift) & mask;
+				amdgpu_device_mm_access(adev, aligned_pos, &value, 4, true);
+			} else {
+				value = (value & mask) >> shift;
+				memcpy(buf, &value, bytes);
+			}
+		} else {
+			amdgpu_device_mm_access(adev, aligned_pos, buf, 4, write);
+		}
+
+		pos += bytes;
+		buf += bytes;
+		size -= bytes;
+	}
+}
+
 /**
  * amdgpu_ttm_access_memory - Read or Write memory that backs a buffer object.
  *
@@ -1413,8 +1450,6 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
 	struct amdgpu_res_cursor cursor;
-	unsigned long flags;
-	uint32_t value = 0;
 	int ret = 0;
 
 	if (bo->resource->mem_type != TTM_PL_VRAM)
@@ -1422,41 +1457,21 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 
 	amdgpu_res_first(bo->resource, offset, len, &cursor);
 	while (cursor.remaining) {
-		uint64_t aligned_pos = cursor.start & ~(uint64_t)3;
-		uint64_t bytes = 4 - (cursor.start & 3);
-		uint32_t shift = (cursor.start & 3) * 8;
-		uint32_t mask = 0xffffffff << shift;
-
-		if (cursor.size < bytes) {
-			mask &= 0xffffffff >> (bytes - cursor.size) * 8;
-			bytes = cursor.size;
-		}
-
-		if (mask != 0xffffffff) {
-			spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-			WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)aligned_pos) | 0x80000000);
-			WREG32_NO_KIQ(mmMM_INDEX_HI, aligned_pos >> 31);
-			value = RREG32_NO_KIQ(mmMM_DATA);
-			if (write) {
-				value &= ~mask;
-				value |= (*(uint32_t *)buf << shift) & mask;
-				WREG32_NO_KIQ(mmMM_DATA, value);
-			}
-			spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-			if (!write) {
-				value = (value & mask) >> shift;
-				memcpy(buf, &value, bytes);
-			}
-		} else {
-			bytes = cursor.size & ~0x3ULL;
-			amdgpu_device_vram_access(adev, cursor.start,
-						  (uint32_t *)buf, bytes,
-						  write);
+		size_t count, size = cursor.size;
+		loff_t pos = cursor.start;
+
+		count = amdgpu_device_aper_access(adev, pos, buf, size, write);
+		size -= count;
+		if (size) {
+			/* using MM to access rest vram and handle un-aligned address */
+			pos += count;
+			buf += count;
+			amdgpu_ttm_vram_mm_access(adev, pos, buf, size, write);
 		}
 
-		ret += bytes;
-		buf = (uint8_t *)buf + bytes;
-		amdgpu_res_next(&cursor, bytes);
+		ret += cursor.size;
+		buf += cursor.size;
+		amdgpu_res_next(&cursor, cursor.size);
 	}
 
 	return ret;
@@ -2146,7 +2161,6 @@ static ssize_t amdgpu_ttm_vram_write(struct file *f, const char __user *buf,
 		return -ENXIO;
 
 	while (size) {
-		unsigned long flags;
 		uint32_t value;
 
 		if (*pos >= adev->gmc.mc_vram_size)
@@ -2156,11 +2170,7 @@ static ssize_t amdgpu_ttm_vram_write(struct file *f, const char __user *buf,
 		if (r)
 			return r;
 
-		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)*pos) | 0x80000000);
-		WREG32_NO_KIQ(mmMM_INDEX_HI, *pos >> 31);
-		WREG32_NO_KIQ(mmMM_DATA, value);
-		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+		amdgpu_device_mm_access(adev, *pos, &value, 4, true);
 
 		result += 4;
 		buf += 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index e69f3e8e06e5..3205fd520060 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -52,7 +52,7 @@ struct amdgpu_gtt_mgr {
 	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
-	atomic64_t available;
+	atomic64_t used;
 };
 
 struct amdgpu_preempt_mgr {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 2834981f8c08..abd8469380e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -409,6 +409,12 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 			return AMDGPU_FW_LOAD_DIRECT;
 		else
 			return AMDGPU_FW_LOAD_PSP;
+	case CHIP_CYAN_SKILLFISH:
+		if (!(load_type &&
+		      adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2))
+			return AMDGPU_FW_LOAD_DIRECT;
+		else
+			return AMDGPU_FW_LOAD_PSP;
 	default:
 		DRM_ERROR("Unknown firmware load type\n");
 	}
@@ -416,6 +422,84 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 	return AMDGPU_FW_LOAD_DIRECT;
 }
 
+const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id)
+{
+	switch (ucode_id) {
+	case AMDGPU_UCODE_ID_SDMA0:
+		return "SDMA0";
+	case AMDGPU_UCODE_ID_SDMA1:
+		return "SDMA1";
+	case AMDGPU_UCODE_ID_SDMA2:
+		return "SDMA2";
+	case AMDGPU_UCODE_ID_SDMA3:
+		return "SDMA3";
+	case AMDGPU_UCODE_ID_SDMA4:
+		return "SDMA4";
+	case AMDGPU_UCODE_ID_SDMA5:
+		return "SDMA5";
+	case AMDGPU_UCODE_ID_SDMA6:
+		return "SDMA6";
+	case AMDGPU_UCODE_ID_SDMA7:
+		return "SDMA7";
+	case AMDGPU_UCODE_ID_CP_CE:
+		return "CP_CE";
+	case AMDGPU_UCODE_ID_CP_PFP:
+		return "CP_PFP";
+	case AMDGPU_UCODE_ID_CP_ME:
+		return "CP_ME";
+	case AMDGPU_UCODE_ID_CP_MEC1:
+		return "CP_MEC1";
+	case AMDGPU_UCODE_ID_CP_MEC1_JT:
+		return "CP_MEC1_JT";
+	case AMDGPU_UCODE_ID_CP_MEC2:
+		return "CP_MEC2";
+	case AMDGPU_UCODE_ID_CP_MEC2_JT:
+		return "CP_MEC2_JT";
+	case AMDGPU_UCODE_ID_CP_MES:
+		return "CP_MES";
+	case AMDGPU_UCODE_ID_CP_MES_DATA:
+		return "CP_MES_DATA";
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL:
+		return "RLC_RESTORE_LIST_CNTL";
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM:
+		return "RLC_RESTORE_LIST_GPM_MEM";
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM:
+		return "RLC_RESTORE_LIST_SRM_MEM";
+	case AMDGPU_UCODE_ID_RLC_IRAM:
+		return "RLC_IRAM";
+	case AMDGPU_UCODE_ID_RLC_DRAM:
+		return "RLC_DRAM";
+	case AMDGPU_UCODE_ID_RLC_G:
+		return "RLC_G";
+	case AMDGPU_UCODE_ID_STORAGE:
+		return "STORAGE";
+	case AMDGPU_UCODE_ID_SMC:
+		return "SMC";
+	case AMDGPU_UCODE_ID_UVD:
+		return "UVD";
+	case AMDGPU_UCODE_ID_UVD1:
+		return "UVD1";
+	case AMDGPU_UCODE_ID_VCE:
+		return "VCE";
+	case AMDGPU_UCODE_ID_VCN:
+		return "VCN";
+	case AMDGPU_UCODE_ID_VCN1:
+		return "VCN1";
+	case AMDGPU_UCODE_ID_DMCU_ERAM:
+		return "DMCU_ERAM";
+	case AMDGPU_UCODE_ID_DMCU_INTV:
+		return "DMCU_INTV";
+	case AMDGPU_UCODE_ID_VCN0_RAM:
+		return "VCN0_RAM";
+	case AMDGPU_UCODE_ID_VCN1_RAM:
+		return "VCN1_RAM";
+	case AMDGPU_UCODE_ID_DMCUB:
+		return "DMCUB";
+	default:
+		return "UNKNOWN UCODE";
+	}
+}
+
 #define FW_VERSION_ATTR(name, mode, field)				\
 static ssize_t show_##name(struct device *dev,				\
 			  struct device_attribute *attr,		\
@@ -440,10 +524,10 @@ FW_VERSION_ATTR(rlc_srlg_fw_version, 0444, gfx.rlc_srlg_fw_version);
 FW_VERSION_ATTR(rlc_srls_fw_version, 0444, gfx.rlc_srls_fw_version);
 FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version);
 FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version);
-FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos_fw_version);
-FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_fw_version);
-FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ta_ras_ucode_version);
-FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.ta_xgmi_ucode_version);
+FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version);
+FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd.fw_version);
+FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras.feature_version);
+FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.xgmi.feature_version);
 FW_VERSION_ATTR(smc_fw_version, 0444, pm.fw_version);
 FW_VERSION_ATTR(sdma_fw_version, 0444, sdma.instance[0].fw_version);
 FW_VERSION_ATTR(sdma2_fw_version, 0444, sdma.instance[1].fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 270309e7f5f5..7c2538db3cd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -71,7 +71,7 @@ struct smc_firmware_header_v2_1 {
         uint32_t pptable_entry_offset;
 };
 
-struct psp_fw_bin_desc {
+struct psp_fw_legacy_bin_desc {
 	uint32_t fw_version;
 	uint32_t offset_bytes;
 	uint32_t size_bytes;
@@ -80,50 +80,67 @@ struct psp_fw_bin_desc {
 /* version_major=1, version_minor=0 */
 struct psp_firmware_header_v1_0 {
 	struct common_firmware_header header;
-	struct psp_fw_bin_desc sos;
+	struct psp_fw_legacy_bin_desc sos;
 };
 
 /* version_major=1, version_minor=1 */
 struct psp_firmware_header_v1_1 {
 	struct psp_firmware_header_v1_0 v1_0;
-	struct psp_fw_bin_desc toc;
-	struct psp_fw_bin_desc kdb;
+	struct psp_fw_legacy_bin_desc toc;
+	struct psp_fw_legacy_bin_desc kdb;
 };
 
 /* version_major=1, version_minor=2 */
 struct psp_firmware_header_v1_2 {
 	struct psp_firmware_header_v1_0 v1_0;
-	struct psp_fw_bin_desc res;
-	struct psp_fw_bin_desc kdb;
+	struct psp_fw_legacy_bin_desc res;
+	struct psp_fw_legacy_bin_desc kdb;
 };
 
 /* version_major=1, version_minor=3 */
 struct psp_firmware_header_v1_3 {
 	struct psp_firmware_header_v1_1 v1_1;
-	struct psp_fw_bin_desc spl;
-	struct psp_fw_bin_desc rl;
-	struct psp_fw_bin_desc sys_drv_aux;
-	struct psp_fw_bin_desc sos_aux;
+	struct psp_fw_legacy_bin_desc spl;
+	struct psp_fw_legacy_bin_desc rl;
+	struct psp_fw_legacy_bin_desc sys_drv_aux;
+	struct psp_fw_legacy_bin_desc sos_aux;
+};
+
+struct psp_fw_bin_desc {
+	uint32_t fw_type;
+	uint32_t fw_version;
+	uint32_t offset_bytes;
+	uint32_t size_bytes;
+};
+
+enum psp_fw_type {
+	PSP_FW_TYPE_UNKOWN,
+	PSP_FW_TYPE_PSP_SOS,
+	PSP_FW_TYPE_PSP_SYS_DRV,
+	PSP_FW_TYPE_PSP_KDB,
+	PSP_FW_TYPE_PSP_TOC,
+	PSP_FW_TYPE_PSP_SPL,
+	PSP_FW_TYPE_PSP_RL,
+	PSP_FW_TYPE_PSP_SOC_DRV,
+	PSP_FW_TYPE_PSP_INTF_DRV,
+	PSP_FW_TYPE_PSP_DBG_DRV,
+};
+
+/* version_major=2, version_minor=0 */
+struct psp_firmware_header_v2_0 {
+	struct common_firmware_header header;
+	uint32_t psp_fw_bin_count;
+	struct psp_fw_bin_desc psp_fw_bin[];
 };
 
 /* version_major=1, version_minor=0 */
 struct ta_firmware_header_v1_0 {
 	struct common_firmware_header header;
-	uint32_t ta_xgmi_ucode_version;
-	uint32_t ta_xgmi_offset_bytes;
-	uint32_t ta_xgmi_size_bytes;
-	uint32_t ta_ras_ucode_version;
-	uint32_t ta_ras_offset_bytes;
-	uint32_t ta_ras_size_bytes;
-	uint32_t ta_hdcp_ucode_version;
-	uint32_t ta_hdcp_offset_bytes;
-	uint32_t ta_hdcp_size_bytes;
-	uint32_t ta_dtm_ucode_version;
-	uint32_t ta_dtm_offset_bytes;
-	uint32_t ta_dtm_size_bytes;
-	uint32_t ta_securedisplay_ucode_version;
-	uint32_t ta_securedisplay_offset_bytes;
-	uint32_t ta_securedisplay_size_bytes;
+	struct psp_fw_legacy_bin_desc xgmi;
+	struct psp_fw_legacy_bin_desc ras;
+	struct psp_fw_legacy_bin_desc hdcp;
+	struct psp_fw_legacy_bin_desc dtm;
+	struct psp_fw_legacy_bin_desc securedisplay;
 };
 
 enum ta_fw_type {
@@ -138,18 +155,11 @@ enum ta_fw_type {
 	TA_FW_TYPE_MAX_INDEX,
 };
 
-struct ta_fw_bin_desc {
-	uint32_t fw_type;
-	uint32_t fw_version;
-	uint32_t offset_bytes;
-	uint32_t size_bytes;
-};
-
 /* version_major=2, version_minor=0 */
 struct ta_firmware_header_v2_0 {
 	struct common_firmware_header header;
 	uint32_t ta_fw_bin_count;
-	struct ta_fw_bin_desc ta_fw_bin[];
+	struct psp_fw_bin_desc ta_fw_bin[];
 };
 
 /* version_major=1, version_minor=0 */
@@ -312,6 +322,7 @@ union amdgpu_firmware_header {
 	struct psp_firmware_header_v1_0 psp;
 	struct psp_firmware_header_v1_1 psp_v1_1;
 	struct psp_firmware_header_v1_3 psp_v1_3;
+	struct psp_firmware_header_v2_0 psp_v2_0;
 	struct ta_firmware_header_v1_0 ta;
 	struct ta_firmware_header_v2_0 ta_v2_0;
 	struct gfx_firmware_header_v1_0 gfx;
@@ -326,7 +337,7 @@ union amdgpu_firmware_header {
 	uint8_t raw[0x100];
 };
 
-#define UCODE_MAX_TA_PACKAGING ((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct ta_fw_bin_desc))
+#define UCODE_MAX_PSP_PACKAGING ((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct psp_fw_bin_desc))
 
 /*
  * fw loading support
@@ -449,4 +460,6 @@ void amdgpu_ucode_sysfs_fini(struct amdgpu_device *adev);
 enum amdgpu_firmware_load_type
 amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type);
 
+const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index f4489773715e..a90029ee9733 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -41,7 +41,6 @@ int amdgpu_umc_ras_late_init(struct amdgpu_device *adev)
 		adev->umc.ras_if->block = AMDGPU_RAS_BLOCK__UMC;
 		adev->umc.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->umc.ras_if->sub_block_index = 0;
-		strcpy(adev->umc.ras_if->name, "umc");
 	}
 	ih_info.head = fs_info.head = *adev->umc.ras_if;
 
@@ -134,7 +133,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 			amdgpu_ras_save_bad_pages(adev);
 
 			if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num)
-				adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs);
+				adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.ras_num_recs);
 		}
 
 		amdgpu_ras_reset_gpu(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 0f576f294d8a..d451c359606a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -326,7 +326,6 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
-	cancel_delayed_work_sync(&adev->uvd.idle_work);
 	drm_sched_entity_destroy(&adev->uvd.entity);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 1ae7f824adc7..8e8dee9fac9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -218,7 +218,6 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vce.idle_work);
 	drm_sched_entity_destroy(&adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 6780df0fb265..008a308a4eca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -258,8 +258,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index b71dd1deeb2d..ca058fbcccd4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -531,10 +531,10 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC,      adev->gfx.mec_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2,     adev->gfx.mec2_fw_version);
-	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS,      adev->psp.sos_fw_version);
-	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,      adev->psp.asd_fw_version);
-	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS,   adev->psp.ta_ras_ucode_version);
-	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI,  adev->psp.ta_xgmi_ucode_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS,      adev->psp.sos.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,      adev->psp.asd.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS,   adev->psp.ras.feature_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI,  adev->psp.xgmi.feature_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SMC,      adev->pm.fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA,     adev->sdma.instance[0].fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA2,    adev->sdma.instance[1].fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
new file mode 100644
index 000000000000..ce982afeff91
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+#include <drm/drm_vblank.h>
+
+#include "amdgpu.h"
+#ifdef CONFIG_DRM_AMDGPU_SI
+#include "dce_v6_0.h"
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+#include "dce_v8_0.h"
+#endif
+#include "dce_v10_0.h"
+#include "dce_v11_0.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
+#include "amdgpu_vkms.h"
+#include "amdgpu_display.h"
+
+/**
+ * DOC: amdgpu_vkms
+ *
+ * The amdgpu vkms interface provides a virtual KMS interface for several use
+ * cases: devices without display hardware, platforms where the actual display
+ * hardware is not useful (e.g., servers), SR-IOV virtual functions, device
+ * emulation/simulation, and device bring up prior to display hardware being
+ * usable. We previously emulated a legacy KMS interface, but there was a desire
+ * to move to the atomic KMS interface. The vkms driver did everything we
+ * needed, but we wanted KMS support natively in the driver without buffer
+ * sharing and the ability to support an instance of VKMS per device. We first
+ * looked at splitting vkms into a stub driver and a helper module that other
+ * drivers could use to implement a virtual display, but this strategy ended up
+ * being messy due to driver specific callbacks needed for buffer management.
+ * Ultimately, it proved easier to import the vkms code as it mostly used core
+ * drm helpers anyway.
+ */
+
+static const u32 amdgpu_vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+static enum hrtimer_restart amdgpu_vkms_vblank_simulate(struct hrtimer *timer)
+{
+	struct amdgpu_vkms_output *output = container_of(timer,
+							 struct amdgpu_vkms_output,
+							 vblank_hrtimer);
+	struct drm_crtc *crtc = &output->crtc;
+	u64 ret_overrun;
+	bool ret;
+
+	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
+					  output->period_ns);
+	WARN_ON(ret_overrun != 1);
+
+	ret = drm_crtc_handle_vblank(crtc);
+	if (!ret)
+		DRM_ERROR("amdgpu_vkms failure on handling vblank");
+
+	return HRTIMER_RESTART;
+}
+
+static int amdgpu_vkms_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+	struct amdgpu_vkms_output *out = drm_crtc_to_amdgpu_vkms_output(crtc);
+
+	drm_calc_timestamping_constants(crtc, &crtc->mode);
+
+	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	out->vblank_hrtimer.function = &amdgpu_vkms_vblank_simulate;
+	out->period_ns = ktime_set(0, vblank->framedur_ns);
+	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void amdgpu_vkms_disable_vblank(struct drm_crtc *crtc)
+{
+	struct amdgpu_vkms_output *out = drm_crtc_to_amdgpu_vkms_output(crtc);
+
+	hrtimer_cancel(&out->vblank_hrtimer);
+}
+
+static bool amdgpu_vkms_get_vblank_timestamp(struct drm_crtc *crtc,
+					     int *max_error,
+					     ktime_t *vblank_time,
+					     bool in_vblank_irq)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = crtc->index;
+	struct amdgpu_vkms_output *output = drm_crtc_to_amdgpu_vkms_output(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+
+	if (!READ_ONCE(vblank->enabled)) {
+		*vblank_time = ktime_get();
+		return true;
+	}
+
+	*vblank_time = READ_ONCE(output->vblank_hrtimer.node.expires);
+
+	if (WARN_ON(*vblank_time == vblank->time))
+		return true;
+
+	/*
+	 * To prevent races we roll the hrtimer forward before we do any
+	 * interrupt processing - this is how real hw works (the interrupt is
+	 * only generated after all the vblank registers are updated) and what
+	 * the vblank core expects. Therefore we need to always correct the
+	 * timestampe by one frame.
+	 */
+	*vblank_time -= output->period_ns;
+
+	return true;
+}
+
+static const struct drm_crtc_funcs amdgpu_vkms_crtc_funcs = {
+	.set_config             = drm_atomic_helper_set_config,
+	.destroy                = drm_crtc_cleanup,
+	.page_flip              = drm_atomic_helper_page_flip,
+	.reset                  = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank		= amdgpu_vkms_enable_vblank,
+	.disable_vblank		= amdgpu_vkms_disable_vblank,
+	.get_vblank_timestamp	= amdgpu_vkms_get_vblank_timestamp,
+};
+
+static void amdgpu_vkms_crtc_atomic_enable(struct drm_crtc *crtc,
+					   struct drm_atomic_state *state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void amdgpu_vkms_crtc_atomic_disable(struct drm_crtc *crtc,
+					    struct drm_atomic_state *state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void amdgpu_vkms_crtc_atomic_flush(struct drm_crtc *crtc,
+					  struct drm_atomic_state *state)
+{
+	if (crtc->state->event) {
+		spin_lock(&crtc->dev->event_lock);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		else
+			drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+
+		spin_unlock(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
+}
+
+static const struct drm_crtc_helper_funcs amdgpu_vkms_crtc_helper_funcs = {
+	.atomic_flush	= amdgpu_vkms_crtc_atomic_flush,
+	.atomic_enable	= amdgpu_vkms_crtc_atomic_enable,
+	.atomic_disable	= amdgpu_vkms_crtc_atomic_disable,
+};
+
+static int amdgpu_vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+			  struct drm_plane *primary, struct drm_plane *cursor)
+{
+	int ret;
+
+	ret = drm_crtc_init_with_planes(dev, crtc, primary, cursor,
+					&amdgpu_vkms_crtc_funcs, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init CRTC\n");
+		return ret;
+	}
+
+	drm_crtc_helper_add(crtc, &amdgpu_vkms_crtc_helper_funcs);
+
+	return ret;
+}
+
+static const struct drm_connector_funcs amdgpu_vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int amdgpu_vkms_conn_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_display_mode *mode = NULL;
+	unsigned i;
+	static const struct mode_size {
+		int w;
+		int h;
+	} common_modes[] = {
+		{ 640,  480},
+		{ 720,  480},
+		{ 800,  600},
+		{ 848,  480},
+		{1024,  768},
+		{1152,  768},
+		{1280,  720},
+		{1280,  800},
+		{1280,  854},
+		{1280,  960},
+		{1280, 1024},
+		{1440,  900},
+		{1400, 1050},
+		{1680, 1050},
+		{1600, 1200},
+		{1920, 1080},
+		{1920, 1200},
+		{2560, 1440},
+		{4096, 3112},
+		{3656, 2664},
+		{3840, 2160},
+		{4096, 2160},
+	};
+
+	for (i = 0; i < ARRAY_SIZE(common_modes); i++) {
+		mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false);
+		drm_mode_probed_add(connector, mode);
+	}
+
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+
+	return ARRAY_SIZE(common_modes);
+}
+
+static const struct drm_connector_helper_funcs amdgpu_vkms_conn_helper_funcs = {
+	.get_modes    = amdgpu_vkms_conn_get_modes,
+};
+
+static const struct drm_plane_funcs amdgpu_vkms_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static void amdgpu_vkms_plane_atomic_update(struct drm_plane *plane,
+					    struct drm_atomic_state *old_state)
+{
+	return;
+}
+
+static int amdgpu_vkms_plane_atomic_check(struct drm_plane *plane,
+					  struct drm_atomic_state *state)
+{
+	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
+										 plane);
+	struct drm_crtc_state *crtc_state;
+	int ret;
+
+	if (!new_plane_state->fb || WARN_ON(!new_plane_state->crtc))
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state,
+					       new_plane_state->crtc);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
+
+	ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, true);
+	if (ret != 0)
+		return ret;
+
+	/* for now primary plane must be visible and full screen */
+	if (!new_plane_state->visible)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
+				  struct drm_plane_state *new_state)
+{
+	struct amdgpu_framebuffer *afb;
+	struct drm_gem_object *obj;
+	struct amdgpu_device *adev;
+	struct amdgpu_bo *rbo;
+	struct list_head list;
+	struct ttm_validate_buffer tv;
+	struct ww_acquire_ctx ticket;
+	uint32_t domain;
+	int r;
+
+	if (!new_state->fb) {
+		DRM_DEBUG_KMS("No FB bound\n");
+		return 0;
+	}
+	afb = to_amdgpu_framebuffer(new_state->fb);
+	obj = new_state->fb->obj[0];
+	rbo = gem_to_amdgpu_bo(obj);
+	adev = amdgpu_ttm_adev(rbo->tbo.bdev);
+	INIT_LIST_HEAD(&list);
+
+	tv.bo = &rbo->tbo;
+	tv.num_shared = 1;
+	list_add(&tv.head, &list);
+
+	r = ttm_eu_reserve_buffers(&ticket, &list, false, NULL);
+	if (r) {
+		dev_err(adev->dev, "fail to reserve bo (%d)\n", r);
+		return r;
+	}
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR)
+		domain = amdgpu_display_supported_domains(adev, rbo->flags);
+	else
+		domain = AMDGPU_GEM_DOMAIN_VRAM;
+
+	r = amdgpu_bo_pin(rbo, domain);
+	if (unlikely(r != 0)) {
+		if (r != -ERESTARTSYS)
+			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		return r;
+	}
+
+	r = amdgpu_ttm_alloc_gart(&rbo->tbo);
+	if (unlikely(r != 0)) {
+		amdgpu_bo_unpin(rbo);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		DRM_ERROR("%p bind failed\n", rbo);
+		return r;
+	}
+
+	ttm_eu_backoff_reservation(&ticket, &list);
+
+	afb->address = amdgpu_bo_gpu_offset(rbo);
+
+	amdgpu_bo_ref(rbo);
+
+	return 0;
+}
+
+static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane,
+				   struct drm_plane_state *old_state)
+{
+	struct amdgpu_bo *rbo;
+	int r;
+
+	if (!old_state->fb)
+		return;
+
+	rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]);
+	r = amdgpu_bo_reserve(rbo, false);
+	if (unlikely(r)) {
+		DRM_ERROR("failed to reserve rbo before unpin\n");
+		return;
+	}
+
+	amdgpu_bo_unpin(rbo);
+	amdgpu_bo_unreserve(rbo);
+	amdgpu_bo_unref(&rbo);
+}
+
+static const struct drm_plane_helper_funcs amdgpu_vkms_primary_helper_funcs = {
+	.atomic_update		= amdgpu_vkms_plane_atomic_update,
+	.atomic_check		= amdgpu_vkms_plane_atomic_check,
+	.prepare_fb		= amdgpu_vkms_prepare_fb,
+	.cleanup_fb		= amdgpu_vkms_cleanup_fb,
+};
+
+static struct drm_plane *amdgpu_vkms_plane_init(struct drm_device *dev,
+						enum drm_plane_type type,
+						int index)
+{
+	struct drm_plane *plane;
+	int ret;
+
+	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+	if (!plane)
+		return ERR_PTR(-ENOMEM);
+
+	ret = drm_universal_plane_init(dev, plane, 1 << index,
+				       &amdgpu_vkms_plane_funcs,
+				       amdgpu_vkms_formats,
+				       ARRAY_SIZE(amdgpu_vkms_formats),
+				       NULL, type, NULL);
+	if (ret) {
+		kfree(plane);
+		return ERR_PTR(ret);
+	}
+
+	drm_plane_helper_add(plane, &amdgpu_vkms_primary_helper_funcs);
+
+	return plane;
+}
+
+int amdgpu_vkms_output_init(struct drm_device *dev,
+			    struct amdgpu_vkms_output *output, int index)
+{
+	struct drm_connector *connector = &output->connector;
+	struct drm_encoder *encoder = &output->encoder;
+	struct drm_crtc *crtc = &output->crtc;
+	struct drm_plane *primary, *cursor = NULL;
+	int ret;
+
+	primary = amdgpu_vkms_plane_init(dev, DRM_PLANE_TYPE_PRIMARY, index);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+
+	ret = amdgpu_vkms_crtc_init(dev, crtc, primary, cursor);
+	if (ret)
+		goto err_crtc;
+
+	ret = drm_connector_init(dev, connector, &amdgpu_vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init connector\n");
+		goto err_connector;
+	}
+
+	drm_connector_helper_add(connector, &amdgpu_vkms_conn_helper_funcs);
+
+	ret = drm_simple_encoder_init(dev, encoder, DRM_MODE_ENCODER_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init encoder\n");
+		goto err_encoder;
+	}
+	encoder->possible_crtcs = 1 << index;
+
+	ret = drm_connector_attach_encoder(connector, encoder);
+	if (ret) {
+		DRM_ERROR("Failed to attach connector to encoder\n");
+		goto err_attach;
+	}
+
+	drm_mode_config_reset(dev);
+
+	return 0;
+
+err_attach:
+	drm_encoder_cleanup(encoder);
+
+err_encoder:
+	drm_connector_cleanup(connector);
+
+err_connector:
+	drm_crtc_cleanup(crtc);
+
+err_crtc:
+	drm_plane_cleanup(primary);
+
+	return ret;
+}
+
+const struct drm_mode_config_funcs amdgpu_vkms_mode_funcs = {
+	.fb_create = amdgpu_display_user_framebuffer_create,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int amdgpu_vkms_sw_init(void *handle)
+{
+	int r, i;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev_to_drm(adev)->max_vblank_count = 0;
+
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_vkms_mode_funcs;
+
+	adev_to_drm(adev)->mode_config.max_width = XRES_MAX;
+	adev_to_drm(adev)->mode_config.max_height = YRES_MAX;
+
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
+
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
+
+	r = amdgpu_display_modeset_create_props(adev);
+	if (r)
+		return r;
+
+	adev->amdgpu_vkms_output = kcalloc(adev->mode_info.num_crtc, sizeof(struct amdgpu_vkms_output), GFP_KERNEL);
+	if (!adev->amdgpu_vkms_output)
+		return -ENOMEM;
+
+	/* allocate crtcs, encoders, connectors */
+	for (i = 0; i < adev->mode_info.num_crtc; i++) {
+		r = amdgpu_vkms_output_init(adev_to_drm(adev), &adev->amdgpu_vkms_output[i], i);
+		if (r)
+			return r;
+	}
+
+	drm_kms_helper_poll_init(adev_to_drm(adev));
+
+	adev->mode_info.mode_config_initialized = true;
+	return 0;
+}
+
+static int amdgpu_vkms_sw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i = 0;
+
+	for (i = 0; i < adev->mode_info.num_crtc; i++)
+		if (adev->mode_info.crtcs[i])
+			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
+
+	kfree(adev->mode_info.bios_hardcoded_edid);
+	kfree(adev->amdgpu_vkms_output);
+
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
+
+	adev->mode_info.mode_config_initialized = false;
+	return 0;
+}
+
+static int amdgpu_vkms_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	switch (adev->asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+		dce_v6_0_disable_dce(adev);
+		break;
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+	case CHIP_KAVERI:
+	case CHIP_KABINI:
+	case CHIP_MULLINS:
+		dce_v8_0_disable_dce(adev);
+		break;
+#endif
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+		dce_v10_0_disable_dce(adev);
+		break;
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_VEGAM:
+		dce_v11_0_disable_dce(adev);
+		break;
+	case CHIP_TOPAZ:
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_HAINAN:
+#endif
+		/* no DCE */
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int amdgpu_vkms_hw_fini(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = drm_mode_config_helper_suspend(adev_to_drm(adev));
+	if (r)
+		return r;
+	return amdgpu_vkms_hw_fini(handle);
+}
+
+static int amdgpu_vkms_resume(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_vkms_hw_init(handle);
+	if (r)
+		return r;
+	return drm_mode_config_helper_resume(adev_to_drm(adev));
+}
+
+static bool amdgpu_vkms_is_idle(void *handle)
+{
+	return true;
+}
+
+static int amdgpu_vkms_wait_for_idle(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_soft_reset(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	return 0;
+}
+
+static const struct amd_ip_funcs amdgpu_vkms_ip_funcs = {
+	.name = "amdgpu_vkms",
+	.early_init = NULL,
+	.late_init = NULL,
+	.sw_init = amdgpu_vkms_sw_init,
+	.sw_fini = amdgpu_vkms_sw_fini,
+	.hw_init = amdgpu_vkms_hw_init,
+	.hw_fini = amdgpu_vkms_hw_fini,
+	.suspend = amdgpu_vkms_suspend,
+	.resume = amdgpu_vkms_resume,
+	.is_idle = amdgpu_vkms_is_idle,
+	.wait_for_idle = amdgpu_vkms_wait_for_idle,
+	.soft_reset = amdgpu_vkms_soft_reset,
+	.set_clockgating_state = amdgpu_vkms_set_clockgating_state,
+	.set_powergating_state = amdgpu_vkms_set_powergating_state,
+};
+
+const struct amdgpu_ip_block_version amdgpu_vkms_ip_block =
+{
+	.type = AMD_IP_BLOCK_TYPE_DCE,
+	.major = 1,
+	.minor = 0,
+	.rev = 0,
+	.funcs = &amdgpu_vkms_ip_funcs,
+};
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h
new file mode 100644
index 000000000000..97f1b79c0724
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _AMDGPU_VKMS_H_
+#define _AMDGPU_VKMS_H_
+
+#define XRES_DEF  1024
+#define YRES_DEF   768
+
+#define XRES_MAX  16384
+#define YRES_MAX  16384
+
+#define drm_crtc_to_amdgpu_vkms_output(target) \
+	container_of(target, struct amdgpu_vkms_output, crtc)
+
+extern const struct amdgpu_ip_block_version amdgpu_vkms_ip_block;
+
+struct amdgpu_vkms_output {
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+	struct hrtimer vblank_hrtimer;
+	ktime_t period_ns;
+	struct drm_pending_vblank_event *event;
+};
+
+#endif /* _AMDGPU_VKMS_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 078c068937fe..6b15cad78de9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -88,6 +88,46 @@ struct amdgpu_prt_cb {
 	struct dma_fence_cb cb;
 };
 
+/**
+ * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping
+ *
+ * @adev: amdgpu_device pointer
+ * @vm: amdgpu_vm pointer
+ * @pasid: the pasid the VM is using on this GPU
+ *
+ * Set the pasid this VM is using on this GPU, can also be used to remove the
+ * pasid by passing in zero.
+ *
+ */
+int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			u32 pasid)
+{
+	int r;
+
+	if (vm->pasid == pasid)
+		return 0;
+
+	if (vm->pasid) {
+		r = xa_err(xa_erase_irq(&adev->vm_manager.pasids, vm->pasid));
+		if (r < 0)
+			return r;
+
+		vm->pasid = 0;
+	}
+
+	if (pasid) {
+		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm,
+					GFP_KERNEL));
+		if (r < 0)
+			return r;
+
+		vm->pasid = pasid;
+	}
+
+
+	return 0;
+}
+
 /*
  * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS
  * happens while holding this lock anywhere to prevent deadlocks when
@@ -886,7 +926,7 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
 	bp.size = amdgpu_vm_bo_size(adev, level);
 	bp.byte_align = AMDGPU_GPU_PAGE_SIZE;
 	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.domain = amdgpu_bo_get_preferred_pin_domain(adev, bp.domain);
+	bp.domain = amdgpu_bo_get_preferred_domain(adev, bp.domain);
 	bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 		AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 
@@ -1178,7 +1218,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);
 
 	if (vm_flush_needed || pasid_mapping_needed) {
-		r = amdgpu_fence_emit(ring, &fence, 0);
+		r = amdgpu_fence_emit(ring, &fence, NULL, 0);
 		if (r)
 			return r;
 	}
@@ -1758,7 +1798,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	r = vm->update_funcs->commit(&params, fence);
 
 	if (table_freed)
-		*table_freed = params.table_freed;
+		*table_freed = *table_freed || params.table_freed;
 
 error_unlock:
 	amdgpu_vm_eviction_unlock(vm);
@@ -1816,6 +1856,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * @adev: amdgpu_device pointer
  * @bo_va: requested BO and VM object
  * @clear: if true clear the entries
+ * @table_freed: return true if page table is freed
  *
  * Fill in the page table entries for @bo_va.
  *
@@ -1823,7 +1864,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * 0 for success, -EINVAL for failure.
  */
 int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
-			bool clear)
+			bool clear, bool *table_freed)
 {
 	struct amdgpu_bo *bo = bo_va->base.bo;
 	struct amdgpu_vm *vm = bo_va->base.vm;
@@ -1902,7 +1943,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 						resv, mapping->start,
 						mapping->last, update_flags,
 						mapping->offset, mem,
-						pages_addr, last_update, NULL);
+						pages_addr, last_update, table_freed);
 		if (r)
 			return r;
 	}
@@ -2154,7 +2195,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 
 	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
 		/* Per VM BOs never need to bo cleared in the page tables */
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 	}
@@ -2173,7 +2214,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		else
 			clear = true;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, clear);
+		r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL);
 		if (r)
 			return r;
 
@@ -2863,14 +2904,13 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
- * @pasid: Process address space identifier
  *
  * Init @vm fields.
  *
  * Returns:
  * 0 for success, error for failure.
  */
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid)
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
 	struct amdgpu_bo *root_bo;
 	struct amdgpu_bo_vm *root;
@@ -2944,19 +2984,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid)
 
 	amdgpu_bo_unreserve(vm->root.bo);
 
-	if (pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		r = idr_alloc(&adev->vm_manager.pasid_idr, vm, pasid, pasid + 1,
-			      GFP_ATOMIC);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-		if (r < 0)
-			goto error_free_root;
-
-		vm->pasid = pasid;
-	}
-
 	INIT_KFIFO(vm->faults);
 
 	return 0;
@@ -3012,7 +3039,6 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
- * @pasid: pasid to use
  *
  * This only works on GFX VMs that don't have any BOs added and no
  * page tables allocated yet.
@@ -3020,7 +3046,6 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * Changes the following VM parameters:
  * - use_cpu_for_update
  * - pte_supports_ats
- * - pasid (old PASID is released, because compute manages its own PASIDs)
  *
  * Reinitializes the page directory to reflect the changed ATS
  * setting.
@@ -3028,8 +3053,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * Returns:
  * 0 for success, -errno for errors.
  */
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			   u32 pasid)
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
@@ -3043,19 +3067,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		goto unreserve_bo;
 
-	if (pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		r = idr_alloc(&adev->vm_manager.pasid_idr, vm, pasid, pasid + 1,
-			      GFP_ATOMIC);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-
-		if (r == -ENOSPC)
-			goto unreserve_bo;
-		r = 0;
-	}
-
 	/* Check if PD needs to be reinitialized and do it before
 	 * changing any other state, in case it fails.
 	 */
@@ -3065,7 +3076,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 				       to_amdgpu_bo_vm(vm->root.bo),
 				       false);
 		if (r)
-			goto free_idr;
+			goto unreserve_bo;
 	}
 
 	/* Update VM state */
@@ -3082,7 +3093,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		r = amdgpu_bo_sync_wait(vm->root.bo,
 					AMDGPU_FENCE_OWNER_UNDEFINED, true);
 		if (r)
-			goto free_idr;
+			goto unreserve_bo;
 
 		vm->update_funcs = &amdgpu_vm_cpu_funcs;
 	} else {
@@ -3092,36 +3103,11 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	vm->last_update = NULL;
 	vm->is_compute_context = true;
 
-	if (vm->pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-
-		/* Free the original amdgpu allocated pasid
-		 * Will be replaced with kfd allocated pasid
-		 */
-		amdgpu_pasid_free(vm->pasid);
-		vm->pasid = 0;
-	}
-
 	/* Free the shadow bo for compute VM */
 	amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow);
 
-	if (pasid)
-		vm->pasid = pasid;
-
 	goto unreserve_bo;
 
-free_idr:
-	if (pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		idr_remove(&adev->vm_manager.pasid_idr, pasid);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-	}
 unreserve_bo:
 	amdgpu_bo_unreserve(vm->root.bo);
 	return r;
@@ -3137,14 +3123,7 @@ unreserve_bo:
  */
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
-	if (vm->pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-	}
-	vm->pasid = 0;
+	amdgpu_vm_set_pasid(adev, vm, 0);
 	vm->is_compute_context = false;
 }
 
@@ -3168,15 +3147,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
-	if (vm->pasid) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
-		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
-		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
-		vm->pasid = 0;
-	}
-
+	amdgpu_vm_set_pasid(adev, vm, 0);
 	dma_fence_wait(vm->last_unlocked, false);
 	dma_fence_put(vm->last_unlocked);
 
@@ -3258,8 +3229,7 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	adev->vm_manager.vm_update_mode = 0;
 #endif
 
-	idr_init(&adev->vm_manager.pasid_idr);
-	spin_lock_init(&adev->vm_manager.pasid_lock);
+	xa_init_flags(&adev->vm_manager.pasids, XA_FLAGS_LOCK_IRQ);
 }
 
 /**
@@ -3271,8 +3241,8 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
  */
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 {
-	WARN_ON(!idr_is_empty(&adev->vm_manager.pasid_idr));
-	idr_destroy(&adev->vm_manager.pasid_idr);
+	WARN_ON(!xa_empty(&adev->vm_manager.pasids));
+	xa_destroy(&adev->vm_manager.pasids);
 
 	amdgpu_vmid_mgr_fini(adev);
 }
@@ -3341,13 +3311,13 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 	struct amdgpu_vm *vm;
 	unsigned long flags;
 
-	spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
+	xa_lock_irqsave(&adev->vm_manager.pasids, flags);
 
-	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	vm = xa_load(&adev->vm_manager.pasids, pasid);
 	if (vm)
 		*task_info = vm->task_info;
 
-	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
+	xa_unlock_irqrestore(&adev->vm_manager.pasids, flags);
 }
 
 /**
@@ -3375,12 +3345,13 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * @adev: amdgpu device pointer
  * @pasid: PASID of the VM
  * @addr: Address of the fault
+ * @write_fault: true is write fault, false is read fault
  *
  * Try to gracefully handle a VM fault. Return true if the fault was handled and
  * shouldn't be reported any more.
  */
 bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
-			    uint64_t addr)
+			    uint64_t addr, bool write_fault)
 {
 	bool is_compute_context = false;
 	struct amdgpu_bo *root;
@@ -3389,15 +3360,15 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 	struct amdgpu_vm *vm;
 	int r;
 
-	spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags);
-	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	xa_lock_irqsave(&adev->vm_manager.pasids, irqflags);
+	vm = xa_load(&adev->vm_manager.pasids, pasid);
 	if (vm) {
 		root = amdgpu_bo_ref(vm->root.bo);
 		is_compute_context = vm->is_compute_context;
 	} else {
 		root = NULL;
 	}
-	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags);
+	xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags);
 
 	if (!root)
 		return false;
@@ -3405,7 +3376,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 	addr /= AMDGPU_GPU_PAGE_SIZE;
 
 	if (is_compute_context &&
-	    !svm_range_restore_pages(adev, pasid, addr)) {
+	    !svm_range_restore_pages(adev, pasid, addr, write_fault)) {
 		amdgpu_bo_unref(&root);
 		return true;
 	}
@@ -3415,11 +3386,11 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 		goto error_unref;
 
 	/* Double check that the VM still exists */
-	spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags);
-	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	xa_lock_irqsave(&adev->vm_manager.pasids, irqflags);
+	vm = xa_load(&adev->vm_manager.pasids, pasid);
 	if (vm && vm->root.bo != root)
 		vm = NULL;
-	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags);
+	xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags);
 	if (!vm)
 		goto error_unlock;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index f8fa653d4da7..85fcfb8c5efd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -359,8 +359,7 @@ struct amdgpu_vm_manager {
 	/* PASID to VM mapping, will be used in interrupt context to
 	 * look up VM of a page fault
 	 */
-	struct idr				pasid_idr;
-	spinlock_t				pasid_lock;
+	struct xarray				pasids;
 };
 
 struct amdgpu_bo_va_mapping;
@@ -375,9 +374,12 @@ extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs;
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
+int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			u32 pasid);
+
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
@@ -406,7 +408,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 				struct dma_fence **fence, bool *free_table);
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
-			bool clear);
+			bool clear, bool *table_freed);
 bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
 void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 			     struct amdgpu_bo *bo, bool evicted);
@@ -446,7 +448,7 @@ void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			     struct amdgpu_task_info *task_info);
 bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
-			    uint64_t addr);
+			    uint64_t addr, bool write_fault);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 8567d5d77346..978ac927ac11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -32,6 +32,10 @@
 #include "wafl/wafl2_4_0_0_smn.h"
 #include "wafl/wafl2_4_0_0_sh_mask.h"
 
+#define smnPCS_XGMI23_PCS_ERROR_STATUS   0x11a01210
+#define smnPCS_XGMI3X16_PCS_ERROR_STATUS 0x11a0020c
+#define smnPCS_GOPX1_PCS_ERROR_STATUS    0x12200210
+
 static DEFINE_MUTEX(xgmi_mutex);
 
 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4
@@ -63,6 +67,33 @@ static const int wafl_pcs_err_status_reg_arct[] = {
 	smnPCS_GOPX1_0_PCS_GOPX1_PCS_ERROR_STATUS + 0x100000,
 };
 
+static const int xgmi23_pcs_err_status_reg_aldebaran[] = {
+	smnPCS_XGMI23_PCS_ERROR_STATUS,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x100000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x200000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x300000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x400000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x500000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x600000,
+	smnPCS_XGMI23_PCS_ERROR_STATUS + 0x700000
+};
+
+static const int xgmi3x16_pcs_err_status_reg_aldebaran[] = {
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x100000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x200000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x300000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x400000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x500000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x600000,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x700000
+};
+
+static const int walf_pcs_err_status_reg_aldebaran[] = {
+	smnPCS_GOPX1_PCS_ERROR_STATUS,
+	smnPCS_GOPX1_PCS_ERROR_STATUS + 0x100000
+};
+
 static const struct amdgpu_pcs_ras_field xgmi_pcs_ras_fields[] = {
 	{"XGMI PCS DataLossErr",
 	 SOC15_REG_FIELD(XGMI0_PCS_GOPX16_PCS_ERROR_STATUS, DataLossErr)},
@@ -486,6 +517,44 @@ int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 	return	-EINVAL;
 }
 
+int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,
+		struct amdgpu_device *peer_adev)
+{
+	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	int i;
+
+	for (i = 0 ; i < top->num_nodes; ++i)
+		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
+			return top->nodes[i].num_links;
+	return	-EINVAL;
+}
+
+/*
+ * Devices that support extended data require the entire hive to initialize with
+ * the shared memory buffer flag set.
+ *
+ * Hive locks and conditions apply - see amdgpu_xgmi_add_device
+ */
+static int amdgpu_xgmi_initialize_hive_get_data_partition(struct amdgpu_hive_info *hive,
+							bool set_extended_data)
+{
+	struct amdgpu_device *tmp_adev;
+	int ret;
+
+	list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		ret = psp_xgmi_initialize(&tmp_adev->psp, set_extended_data, false);
+		if (ret) {
+			dev_err(tmp_adev->dev,
+				"XGMI: Failed to initialize xgmi session for data partition %i\n",
+				set_extended_data);
+			return ret;
+		}
+
+	}
+
+	return 0;
+}
+
 int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 {
 	struct psp_xgmi_topology_info *top_info;
@@ -500,7 +569,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 
 	if (!adev->gmc.xgmi.pending_reset &&
 	    amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
-		ret = psp_xgmi_initialize(&adev->psp);
+		ret = psp_xgmi_initialize(&adev->psp, false, true);
 		if (ret) {
 			dev_err(adev->dev,
 				"XGMI: Failed to initialize xgmi session\n");
@@ -563,7 +632,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		/* get latest topology info for each device from psp */
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count,
-					&tmp_adev->psp.xgmi_context.top_info);
+					&tmp_adev->psp.xgmi_context.top_info, false);
 			if (ret) {
 				dev_err(tmp_adev->dev,
 					"XGMI: Get topology failure on device %llx, hive %llx, ret %d",
@@ -573,6 +642,34 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 				goto exit_unlock;
 			}
 		}
+
+		/* get topology again for hives that support extended data */
+		if (adev->psp.xgmi_context.supports_extended_data) {
+
+			/* initialize the hive to get extended data.  */
+			ret = amdgpu_xgmi_initialize_hive_get_data_partition(hive, true);
+			if (ret)
+				goto exit_unlock;
+
+			/* get the extended data. */
+			list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+				ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count,
+						&tmp_adev->psp.xgmi_context.top_info, true);
+				if (ret) {
+					dev_err(tmp_adev->dev,
+						"XGMI: Get topology for extended data failure on device %llx, hive %llx, ret %d",
+						tmp_adev->gmc.xgmi.node_id,
+						tmp_adev->gmc.xgmi.hive_id, ret);
+					goto exit_unlock;
+				}
+			}
+
+			/* initialize the hive to get non-extended data for the next round. */
+			ret = amdgpu_xgmi_initialize_hive_get_data_partition(hive, false);
+			if (ret)
+				goto exit_unlock;
+
+		}
 	}
 
 	if (!ret && !adev->gmc.xgmi.pending_reset)
@@ -651,7 +748,6 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
 		adev->gmc.xgmi.ras_if->block = AMDGPU_RAS_BLOCK__XGMI_WAFL;
 		adev->gmc.xgmi.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->gmc.xgmi.ras_if->sub_block_index = 0;
-		strcpy(adev->gmc.xgmi.ras_if->name, "xgmi_wafl");
 	}
 	ih_info.head = fs_info.head = *adev->gmc.xgmi.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->gmc.xgmi.ras_if,
@@ -706,6 +802,17 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 			pcs_clear_status(adev,
 					 xgmi_pcs_err_status_reg_vg20[i]);
 		break;
+	case CHIP_ALDEBARAN:
+		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
+			pcs_clear_status(adev,
+					 xgmi23_pcs_err_status_reg_aldebaran[i]);
+		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
+			pcs_clear_status(adev,
+					 xgmi23_pcs_err_status_reg_aldebaran[i]);
+		for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++)
+			pcs_clear_status(adev,
+					 walf_pcs_err_status_reg_aldebaran[i]);
+		break;
 	default:
 		break;
 	}
@@ -783,7 +890,6 @@ static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 		}
 		break;
 	case CHIP_VEGA20:
-	default:
 		/* check xgmi pcs error */
 		for (i = 0; i < ARRAY_SIZE(xgmi_pcs_err_status_reg_vg20); i++) {
 			data = RREG32_PCIE(xgmi_pcs_err_status_reg_vg20[i]);
@@ -799,6 +905,32 @@ static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 						data, &ue_cnt, &ce_cnt, false);
 		}
 		break;
+	case CHIP_ALDEBARAN:
+		/* check xgmi23 pcs error */
+		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++) {
+			data = RREG32_PCIE(xgmi23_pcs_err_status_reg_aldebaran[i]);
+			if (data)
+				amdgpu_xgmi_query_pcs_error_status(adev,
+						data, &ue_cnt, &ce_cnt, true);
+		}
+		/* check xgmi3x16 pcs error */
+		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) {
+			data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_aldebaran[i]);
+			if (data)
+				amdgpu_xgmi_query_pcs_error_status(adev,
+						data, &ue_cnt, &ce_cnt, true);
+		}
+		/* check wafl pcs error */
+		for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++) {
+			data = RREG32_PCIE(walf_pcs_err_status_reg_aldebaran[i]);
+			if (data)
+				amdgpu_xgmi_query_pcs_error_status(adev,
+						data, &ue_cnt, &ce_cnt, false);
+		}
+		break;
+	default:
+		dev_warn(adev->dev, "XGMI RAS error query not supported");
+		break;
 	}
 
 	adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 12969c0830d5..d2189bf7d428 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -59,6 +59,8 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 		struct amdgpu_device *peer_adev);
+int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,
+		struct amdgpu_device *peer_adev);
 uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev,
 					   uint64_t addr);
 static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
index 159a2a4385a1..afad094f84c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
@@ -851,7 +851,7 @@ void amdgpu_atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 	pll->reference_div = amdgpu_crtc->pll_reference_div;
 	pll->post_div = amdgpu_crtc->pll_post_div;
 
-	amdgpu_pll_compute(pll, amdgpu_crtc->adjusted_clock, &pll_clock,
+	amdgpu_pll_compute(adev, pll, amdgpu_crtc->adjusted_clock, &pll_clock,
 			    &fb_div, &frac_fb_div, &ref_div, &post_div);
 
 	amdgpu_atombios_crtc_program_ss(adev, ATOM_DISABLE, amdgpu_crtc->pll_id,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index c0fcc41ee574..54f28c075f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -70,7 +70,7 @@
 
 #include "amdgpu_dm.h"
 #include "amdgpu_amdkfd.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 
 static const struct amdgpu_video_codec_info cik_video_codecs_encode_array[] =
 {
@@ -2259,7 +2259,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2277,7 +2277,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2295,7 +2295,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2315,7 +2315,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c
new file mode 100644
index 000000000000..58808814d8fb
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "nv.h"
+
+#include "soc15_common.h"
+#include "soc15_hw_ip.h"
+#include "cyan_skillfish_ip_offset.h"
+
+int cyan_skillfish_reg_base_init(struct amdgpu_device *adev)
+{
+	/* HW has more IP blocks,  only initialized the blocke needed by driver */
+	uint32_t i;
+	for (i = 0 ; i < MAX_INSTANCE ; ++i) {
+		adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i]));
+		adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i]));
+		adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i]));
+		adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
+		adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i]));
+		adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i]));
+		adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i]));
+		adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i]));
+		adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i]));
+		adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i]));
+		adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
deleted file mode 100644
index 7e0d8c092c7e..000000000000
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ /dev/null
@@ -1,780 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include <drm/drm_vblank.h>
-
-#include "amdgpu.h"
-#include "amdgpu_pm.h"
-#include "amdgpu_i2c.h"
-#include "atom.h"
-#include "amdgpu_pll.h"
-#include "amdgpu_connectors.h"
-#ifdef CONFIG_DRM_AMDGPU_SI
-#include "dce_v6_0.h"
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-#include "dce_v8_0.h"
-#endif
-#include "dce_v10_0.h"
-#include "dce_v11_0.h"
-#include "dce_virtual.h"
-#include "ivsrcid/ivsrcid_vislands30.h"
-#include "amdgpu_display.h"
-
-#define DCE_VIRTUAL_VBLANK_PERIOD 16666666
-
-
-static void dce_virtual_set_display_funcs(struct amdgpu_device *adev);
-static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev);
-static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
-					      int index);
-static int dce_virtual_pageflip(struct amdgpu_device *adev,
-				unsigned crtc_id);
-static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer);
-static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
-							int crtc,
-							enum amdgpu_interrupt_state state);
-
-static u32 dce_virtual_vblank_get_counter(struct amdgpu_device *adev, int crtc)
-{
-	return 0;
-}
-
-static void dce_virtual_page_flip(struct amdgpu_device *adev,
-			      int crtc_id, u64 crtc_base, bool async)
-{
-	return;
-}
-
-static int dce_virtual_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
-					u32 *vbl, u32 *position)
-{
-	*vbl = 0;
-	*position = 0;
-
-	return -EINVAL;
-}
-
-static bool dce_virtual_hpd_sense(struct amdgpu_device *adev,
-			       enum amdgpu_hpd_id hpd)
-{
-	return true;
-}
-
-static void dce_virtual_hpd_set_polarity(struct amdgpu_device *adev,
-				      enum amdgpu_hpd_id hpd)
-{
-	return;
-}
-
-static u32 dce_virtual_hpd_get_gpio_reg(struct amdgpu_device *adev)
-{
-	return 0;
-}
-
-/**
- * dce_virtual_bandwidth_update - program display watermarks
- *
- * @adev: amdgpu_device pointer
- *
- * Calculate and program the display watermarks and line
- * buffer allocation (CIK).
- */
-static void dce_virtual_bandwidth_update(struct amdgpu_device *adev)
-{
-	return;
-}
-
-static int dce_virtual_crtc_gamma_set(struct drm_crtc *crtc, u16 *red,
-				      u16 *green, u16 *blue, uint32_t size,
-				      struct drm_modeset_acquire_ctx *ctx)
-{
-	return 0;
-}
-
-static void dce_virtual_crtc_destroy(struct drm_crtc *crtc)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-	drm_crtc_cleanup(crtc);
-	kfree(amdgpu_crtc);
-}
-
-static const struct drm_crtc_funcs dce_virtual_crtc_funcs = {
-	.cursor_set2 = NULL,
-	.cursor_move = NULL,
-	.gamma_set = dce_virtual_crtc_gamma_set,
-	.set_config = amdgpu_display_crtc_set_config,
-	.destroy = dce_virtual_crtc_destroy,
-	.page_flip_target = amdgpu_display_crtc_page_flip_target,
-	.get_vblank_counter = amdgpu_get_vblank_counter_kms,
-	.enable_vblank = amdgpu_enable_vblank_kms,
-	.disable_vblank = amdgpu_disable_vblank_kms,
-	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-};
-
-static void dce_virtual_crtc_dpms(struct drm_crtc *crtc, int mode)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	unsigned type;
-
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-		amdgpu_crtc->enabled = true;
-		/* Make sure VBLANK interrupts are still enabled */
-		type = amdgpu_display_crtc_idx_to_irq_type(adev,
-						amdgpu_crtc->crtc_id);
-		amdgpu_irq_update(adev, &adev->crtc_irq, type);
-		drm_crtc_vblank_on(crtc);
-		break;
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-	case DRM_MODE_DPMS_OFF:
-		drm_crtc_vblank_off(crtc);
-		amdgpu_crtc->enabled = false;
-		break;
-	}
-}
-
-
-static void dce_virtual_crtc_prepare(struct drm_crtc *crtc)
-{
-	dce_virtual_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void dce_virtual_crtc_commit(struct drm_crtc *crtc)
-{
-	dce_virtual_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-static void dce_virtual_crtc_disable(struct drm_crtc *crtc)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct drm_device *dev = crtc->dev;
-
-	if (dev->num_crtcs)
-		drm_crtc_vblank_off(crtc);
-
-	amdgpu_crtc->enabled = false;
-	amdgpu_crtc->pll_id = ATOM_PPLL_INVALID;
-	amdgpu_crtc->encoder = NULL;
-	amdgpu_crtc->connector = NULL;
-}
-
-static int dce_virtual_crtc_mode_set(struct drm_crtc *crtc,
-				  struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode,
-				  int x, int y, struct drm_framebuffer *old_fb)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-	/* update the hw version fpr dpm */
-	amdgpu_crtc->hw_mode = *adjusted_mode;
-
-	return 0;
-}
-
-static bool dce_virtual_crtc_mode_fixup(struct drm_crtc *crtc,
-				     const struct drm_display_mode *mode,
-				     struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-
-static int dce_virtual_crtc_set_base(struct drm_crtc *crtc, int x, int y,
-				  struct drm_framebuffer *old_fb)
-{
-	return 0;
-}
-
-static int dce_virtual_crtc_set_base_atomic(struct drm_crtc *crtc,
-					 struct drm_framebuffer *fb,
-					 int x, int y, enum mode_set_atomic state)
-{
-	return 0;
-}
-
-static const struct drm_crtc_helper_funcs dce_virtual_crtc_helper_funcs = {
-	.dpms = dce_virtual_crtc_dpms,
-	.mode_fixup = dce_virtual_crtc_mode_fixup,
-	.mode_set = dce_virtual_crtc_mode_set,
-	.mode_set_base = dce_virtual_crtc_set_base,
-	.mode_set_base_atomic = dce_virtual_crtc_set_base_atomic,
-	.prepare = dce_virtual_crtc_prepare,
-	.commit = dce_virtual_crtc_commit,
-	.disable = dce_virtual_crtc_disable,
-	.get_scanout_position = amdgpu_crtc_get_scanout_position,
-};
-
-static int dce_virtual_crtc_init(struct amdgpu_device *adev, int index)
-{
-	struct amdgpu_crtc *amdgpu_crtc;
-
-	amdgpu_crtc = kzalloc(sizeof(struct amdgpu_crtc) +
-			      (AMDGPUFB_CONN_LIMIT * sizeof(struct drm_connector *)), GFP_KERNEL);
-	if (amdgpu_crtc == NULL)
-		return -ENOMEM;
-
-	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_virtual_crtc_funcs);
-
-	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
-	amdgpu_crtc->crtc_id = index;
-	adev->mode_info.crtcs[index] = amdgpu_crtc;
-
-	amdgpu_crtc->pll_id = ATOM_PPLL_INVALID;
-	amdgpu_crtc->encoder = NULL;
-	amdgpu_crtc->connector = NULL;
-	amdgpu_crtc->vsync_timer_enabled = AMDGPU_IRQ_STATE_DISABLE;
-	drm_crtc_helper_add(&amdgpu_crtc->base, &dce_virtual_crtc_helper_funcs);
-
-	hrtimer_init(&amdgpu_crtc->vblank_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer_set_expires(&amdgpu_crtc->vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD);
-	amdgpu_crtc->vblank_timer.function = dce_virtual_vblank_timer_handle;
-	hrtimer_start(&amdgpu_crtc->vblank_timer,
-		      DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL);
-	return 0;
-}
-
-static int dce_virtual_early_init(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	dce_virtual_set_display_funcs(adev);
-	dce_virtual_set_irq_funcs(adev);
-
-	adev->mode_info.num_hpd = 1;
-	adev->mode_info.num_dig = 1;
-	return 0;
-}
-
-static struct drm_encoder *
-dce_virtual_encoder(struct drm_connector *connector)
-{
-	struct drm_encoder *encoder;
-
-	drm_connector_for_each_possible_encoder(connector, encoder) {
-		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
-			return encoder;
-	}
-
-	/* pick the first one */
-	drm_connector_for_each_possible_encoder(connector, encoder)
-		return encoder;
-
-	return NULL;
-}
-
-static int dce_virtual_get_modes(struct drm_connector *connector)
-{
-	struct drm_device *dev = connector->dev;
-	struct drm_display_mode *mode = NULL;
-	unsigned i;
-	static const struct mode_size {
-		int w;
-		int h;
-	} common_modes[] = {
-		{ 640,  480},
-		{ 720,  480},
-		{ 800,  600},
-		{ 848,  480},
-		{1024,  768},
-		{1152,  768},
-		{1280,  720},
-		{1280,  800},
-		{1280,  854},
-		{1280,  960},
-		{1280, 1024},
-		{1440,  900},
-		{1400, 1050},
-		{1680, 1050},
-		{1600, 1200},
-		{1920, 1080},
-		{1920, 1200},
-		{2560, 1440},
-		{4096, 3112},
-		{3656, 2664},
-		{3840, 2160},
-		{4096, 2160},
-	};
-
-	for (i = 0; i < ARRAY_SIZE(common_modes); i++) {
-		mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false);
-		drm_mode_probed_add(connector, mode);
-	}
-
-	return 0;
-}
-
-static enum drm_mode_status dce_virtual_mode_valid(struct drm_connector *connector,
-				  struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
-static int
-dce_virtual_dpms(struct drm_connector *connector, int mode)
-{
-	return 0;
-}
-
-static int
-dce_virtual_set_property(struct drm_connector *connector,
-			 struct drm_property *property,
-			 uint64_t val)
-{
-	return 0;
-}
-
-static void dce_virtual_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(connector);
-}
-
-static void dce_virtual_force(struct drm_connector *connector)
-{
-	return;
-}
-
-static const struct drm_connector_helper_funcs dce_virtual_connector_helper_funcs = {
-	.get_modes = dce_virtual_get_modes,
-	.mode_valid = dce_virtual_mode_valid,
-	.best_encoder = dce_virtual_encoder,
-};
-
-static const struct drm_connector_funcs dce_virtual_connector_funcs = {
-	.dpms = dce_virtual_dpms,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.set_property = dce_virtual_set_property,
-	.destroy = dce_virtual_destroy,
-	.force = dce_virtual_force,
-};
-
-static int dce_virtual_sw_init(void *handle)
-{
-	int r, i;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER, &adev->crtc_irq);
-	if (r)
-		return r;
-
-	adev_to_drm(adev)->max_vblank_count = 0;
-
-	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
-
-	adev_to_drm(adev)->mode_config.max_width = 16384;
-	adev_to_drm(adev)->mode_config.max_height = 16384;
-
-	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-
-	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
-
-	r = amdgpu_display_modeset_create_props(adev);
-	if (r)
-		return r;
-
-	adev_to_drm(adev)->mode_config.max_width = 16384;
-	adev_to_drm(adev)->mode_config.max_height = 16384;
-
-	/* allocate crtcs, encoders, connectors */
-	for (i = 0; i < adev->mode_info.num_crtc; i++) {
-		r = dce_virtual_crtc_init(adev, i);
-		if (r)
-			return r;
-		r = dce_virtual_connector_encoder_init(adev, i);
-		if (r)
-			return r;
-	}
-
-	drm_kms_helper_poll_init(adev_to_drm(adev));
-
-	adev->mode_info.mode_config_initialized = true;
-	return 0;
-}
-
-static int dce_virtual_sw_fini(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int i = 0;
-
-	for (i = 0; i < adev->mode_info.num_crtc; i++)
-		if (adev->mode_info.crtcs[i])
-			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
-
-	kfree(adev->mode_info.bios_hardcoded_edid);
-
-	drm_kms_helper_poll_fini(adev_to_drm(adev));
-
-	drm_mode_config_cleanup(adev_to_drm(adev));
-	/* clear crtcs pointer to avoid dce irq finish routine access freed data */
-	memset(adev->mode_info.crtcs, 0, sizeof(adev->mode_info.crtcs[0]) * AMDGPU_MAX_CRTCS);
-	adev->mode_info.mode_config_initialized = false;
-	return 0;
-}
-
-static int dce_virtual_hw_init(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	switch (adev->asic_type) {
-#ifdef CONFIG_DRM_AMDGPU_SI
-	case CHIP_TAHITI:
-	case CHIP_PITCAIRN:
-	case CHIP_VERDE:
-	case CHIP_OLAND:
-		dce_v6_0_disable_dce(adev);
-		break;
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	case CHIP_BONAIRE:
-	case CHIP_HAWAII:
-	case CHIP_KAVERI:
-	case CHIP_KABINI:
-	case CHIP_MULLINS:
-		dce_v8_0_disable_dce(adev);
-		break;
-#endif
-	case CHIP_FIJI:
-	case CHIP_TONGA:
-		dce_v10_0_disable_dce(adev);
-		break;
-	case CHIP_CARRIZO:
-	case CHIP_STONEY:
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_VEGAM:
-		dce_v11_0_disable_dce(adev);
-		break;
-	case CHIP_TOPAZ:
-#ifdef CONFIG_DRM_AMDGPU_SI
-	case CHIP_HAINAN:
-#endif
-		/* no DCE */
-		break;
-	default:
-		break;
-	}
-	return 0;
-}
-
-static int dce_virtual_hw_fini(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_suspend(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = amdgpu_display_suspend_helper(adev);
-	if (r)
-		return r;
-	return dce_virtual_hw_fini(handle);
-}
-
-static int dce_virtual_resume(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = dce_virtual_hw_init(handle);
-	if (r)
-		return r;
-	return amdgpu_display_resume_helper(adev);
-}
-
-static bool dce_virtual_is_idle(void *handle)
-{
-	return true;
-}
-
-static int dce_virtual_wait_for_idle(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_soft_reset(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_set_clockgating_state(void *handle,
-					  enum amd_clockgating_state state)
-{
-	return 0;
-}
-
-static int dce_virtual_set_powergating_state(void *handle,
-					  enum amd_powergating_state state)
-{
-	return 0;
-}
-
-static const struct amd_ip_funcs dce_virtual_ip_funcs = {
-	.name = "dce_virtual",
-	.early_init = dce_virtual_early_init,
-	.late_init = NULL,
-	.sw_init = dce_virtual_sw_init,
-	.sw_fini = dce_virtual_sw_fini,
-	.hw_init = dce_virtual_hw_init,
-	.hw_fini = dce_virtual_hw_fini,
-	.suspend = dce_virtual_suspend,
-	.resume = dce_virtual_resume,
-	.is_idle = dce_virtual_is_idle,
-	.wait_for_idle = dce_virtual_wait_for_idle,
-	.soft_reset = dce_virtual_soft_reset,
-	.set_clockgating_state = dce_virtual_set_clockgating_state,
-	.set_powergating_state = dce_virtual_set_powergating_state,
-};
-
-/* these are handled by the primary encoders */
-static void dce_virtual_encoder_prepare(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void dce_virtual_encoder_commit(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void
-dce_virtual_encoder_mode_set(struct drm_encoder *encoder,
-			     struct drm_display_mode *mode,
-			     struct drm_display_mode *adjusted_mode)
-{
-	return;
-}
-
-static void dce_virtual_encoder_disable(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void
-dce_virtual_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	return;
-}
-
-static bool dce_virtual_encoder_mode_fixup(struct drm_encoder *encoder,
-				    const struct drm_display_mode *mode,
-				    struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-static const struct drm_encoder_helper_funcs dce_virtual_encoder_helper_funcs = {
-	.dpms = dce_virtual_encoder_dpms,
-	.mode_fixup = dce_virtual_encoder_mode_fixup,
-	.prepare = dce_virtual_encoder_prepare,
-	.mode_set = dce_virtual_encoder_mode_set,
-	.commit = dce_virtual_encoder_commit,
-	.disable = dce_virtual_encoder_disable,
-};
-
-static void dce_virtual_encoder_destroy(struct drm_encoder *encoder)
-{
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static const struct drm_encoder_funcs dce_virtual_encoder_funcs = {
-	.destroy = dce_virtual_encoder_destroy,
-};
-
-static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
-					      int index)
-{
-	struct drm_encoder *encoder;
-	struct drm_connector *connector;
-
-	/* add a new encoder */
-	encoder = kzalloc(sizeof(struct drm_encoder), GFP_KERNEL);
-	if (!encoder)
-		return -ENOMEM;
-	encoder->possible_crtcs = 1 << index;
-	drm_encoder_init(adev_to_drm(adev), encoder, &dce_virtual_encoder_funcs,
-			 DRM_MODE_ENCODER_VIRTUAL, NULL);
-	drm_encoder_helper_add(encoder, &dce_virtual_encoder_helper_funcs);
-
-	connector = kzalloc(sizeof(struct drm_connector), GFP_KERNEL);
-	if (!connector) {
-		kfree(encoder);
-		return -ENOMEM;
-	}
-
-	/* add a new connector */
-	drm_connector_init(adev_to_drm(adev), connector, &dce_virtual_connector_funcs,
-			   DRM_MODE_CONNECTOR_VIRTUAL);
-	drm_connector_helper_add(connector, &dce_virtual_connector_helper_funcs);
-	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
-
-	/* link them */
-	drm_connector_attach_encoder(connector, encoder);
-
-	return 0;
-}
-
-static const struct amdgpu_display_funcs dce_virtual_display_funcs = {
-	.bandwidth_update = &dce_virtual_bandwidth_update,
-	.vblank_get_counter = &dce_virtual_vblank_get_counter,
-	.backlight_set_level = NULL,
-	.backlight_get_level = NULL,
-	.hpd_sense = &dce_virtual_hpd_sense,
-	.hpd_set_polarity = &dce_virtual_hpd_set_polarity,
-	.hpd_get_gpio_reg = &dce_virtual_hpd_get_gpio_reg,
-	.page_flip = &dce_virtual_page_flip,
-	.page_flip_get_scanoutpos = &dce_virtual_crtc_get_scanoutpos,
-	.add_encoder = NULL,
-	.add_connector = NULL,
-};
-
-static void dce_virtual_set_display_funcs(struct amdgpu_device *adev)
-{
-	adev->mode_info.funcs = &dce_virtual_display_funcs;
-}
-
-static int dce_virtual_pageflip(struct amdgpu_device *adev,
-				unsigned crtc_id)
-{
-	unsigned long flags;
-	struct amdgpu_crtc *amdgpu_crtc;
-	struct amdgpu_flip_work *works;
-
-	amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
-
-	if (crtc_id >= adev->mode_info.num_crtc) {
-		DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
-		return -EINVAL;
-	}
-
-	/* IRQ could occur when in initial stage */
-	if (amdgpu_crtc == NULL)
-		return 0;
-
-	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
-	works = amdgpu_crtc->pflip_works;
-	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED) {
-		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
-			"AMDGPU_FLIP_SUBMITTED(%d)\n",
-			amdgpu_crtc->pflip_status,
-			AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
-		return 0;
-	}
-
-	/* page flip completed. clean up */
-	amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE;
-	amdgpu_crtc->pflip_works = NULL;
-
-	/* wakeup usersapce */
-	if (works->event)
-		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
-
-	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
-
-	drm_crtc_vblank_put(&amdgpu_crtc->base);
-	amdgpu_bo_unref(&works->old_abo);
-	kfree(works->shared);
-	kfree(works);
-
-	return 0;
-}
-
-static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer)
-{
-	struct amdgpu_crtc *amdgpu_crtc = container_of(vblank_timer,
-						       struct amdgpu_crtc, vblank_timer);
-	struct drm_device *ddev = amdgpu_crtc->base.dev;
-	struct amdgpu_device *adev = drm_to_adev(ddev);
-	struct amdgpu_irq_src *source = adev->irq.client[AMDGPU_IRQ_CLIENTID_LEGACY].sources
-		[VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER];
-	int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev,
-						amdgpu_crtc->crtc_id);
-
-	if (amdgpu_irq_enabled(adev, source, irq_type)) {
-		drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
-		dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
-	}
-	hrtimer_start(vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD,
-		      HRTIMER_MODE_REL);
-
-	return HRTIMER_NORESTART;
-}
-
-static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
-							int crtc,
-							enum amdgpu_interrupt_state state)
-{
-	if (crtc >= adev->mode_info.num_crtc || !adev->mode_info.crtcs[crtc]) {
-		DRM_DEBUG("invalid crtc %d\n", crtc);
-		return;
-	}
-
-	adev->mode_info.crtcs[crtc]->vsync_timer_enabled = state;
-	DRM_DEBUG("[FM]set crtc %d vblank interrupt state %d\n", crtc, state);
-}
-
-
-static int dce_virtual_set_crtc_irq_state(struct amdgpu_device *adev,
-					  struct amdgpu_irq_src *source,
-					  unsigned type,
-					  enum amdgpu_interrupt_state state)
-{
-	if (type > AMDGPU_CRTC_IRQ_VBLANK6)
-		return -EINVAL;
-
-	dce_virtual_set_crtc_vblank_interrupt_state(adev, type, state);
-
-	return 0;
-}
-
-static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = {
-	.set = dce_virtual_set_crtc_irq_state,
-	.process = NULL,
-};
-
-static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev)
-{
-	adev->crtc_irq.num_types = adev->mode_info.num_crtc;
-	adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs;
-}
-
-const struct amdgpu_ip_block_version dce_virtual_ip_block =
-{
-	.type = AMD_IP_BLOCK_TYPE_DCE,
-	.major = 1,
-	.minor = 0,
-	.rev = 0,
-	.funcs = &dce_virtual_ip_funcs,
-};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index a64b2c706090..16dbe593cba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -56,6 +56,10 @@
 #define GFX10_NUM_GFX_RINGS_Sienna_Cichlid	1
 #define GFX10_MEC_HPD_SIZE	2048
 
+#define RLCG_VFGATE_DISABLED	0x4000000
+#define RLCG_WRONG_OPERATION_TYPE	0x2000000
+#define RLCG_NOT_IN_RANGE	0x1000000
+
 #define F32_CE_PROGRAM_RAM_SIZE		65536
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
 
@@ -181,6 +185,9 @@
 #define GFX_RLCG_GC_READ	(0x1 << 28)
 #define GFX_RLCG_MMHUB_WRITE	(0x2 << 28)
 
+#define RLCG_ERROR_REPORT_ENABLED(adev) \
+	(amdgpu_sriov_reg_indirect_mmhub(adev) || amdgpu_sriov_reg_indirect_gc(adev))
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -249,6 +256,39 @@ MODULE_FIRMWARE("amdgpu/yellow_carp_mec.bin");
 MODULE_FIRMWARE("amdgpu/yellow_carp_mec2.bin");
 MODULE_FIRMWARE("amdgpu/yellow_carp_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_ce.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_pfp.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_me.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_mec.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_mec2.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_ce.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_pfp.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_me.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_mec.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_mec2.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_rlc.bin");
+
+static const struct soc15_reg_golden golden_settings_gc_10_0[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_INDEX, 0xffffffff, 0x00000000),
+	/* TA_GRAD_ADJ_UCONFIG -> TA_GRAD_ADJ */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2544c382),
+	/* VGT_TF_RING_SIZE_UMD -> VGT_TF_RING_SIZE */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2262c24e),
+	/* VGT_HS_OFFCHIP_PARAM_UMD -> VGT_HS_OFFCHIP_PARAM */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x226cc24f),
+	/* VGT_TF_MEMORY_BASE_UMD -> VGT_TF_MEMORY_BASE */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x226ec250),
+	/* VGT_TF_MEMORY_BASE_HI_UMD -> VGT_TF_MEMORY_BASE_HI */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2278c261),
+	/* VGT_ESGS_RING_SIZE_UMD -> VGT_ESGS_RING_SIZE */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2232c240),
+	/* VGT_GSVS_RING_SIZE_UMD -> VGT_GSVS_RING_SIZE */
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2233c241),
+};
+
 static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
@@ -1486,6 +1526,7 @@ static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32
 	uint32_t i = 0;
 	uint32_t retries = 50000;
 	u32 ret = 0;
+	u32 tmp;
 
 	scratch_reg0 = adev->rmmio +
 		       (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0) * 4;
@@ -1519,9 +1560,8 @@ static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32
 		writel(v, scratch_reg0);
 		writel(offset | flag, scratch_reg1);
 		writel(1, spare_int);
-		for (i = 0; i < retries; i++) {
-			u32 tmp;
 
+		for (i = 0; i < retries; i++) {
 			tmp = readl(scratch_reg1);
 			if (!(tmp & flag))
 				break;
@@ -1529,8 +1569,19 @@ static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32
 			udelay(10);
 		}
 
-		if (i >= retries)
-			pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset);
+		if (i >= retries) {
+			if (RLCG_ERROR_REPORT_ENABLED(adev)) {
+				if (tmp & RLCG_VFGATE_DISABLED)
+					pr_err("The vfgate is disabled, program reg:0x%05x failed!\n", offset);
+				else if (tmp & RLCG_WRONG_OPERATION_TYPE)
+					pr_err("Wrong operation type, program reg:0x%05x failed!\n", offset);
+				else if (tmp & RLCG_NOT_IN_RANGE)
+					pr_err("The register is not in range, program reg:0x%05x failed!\n", offset);
+				else
+					pr_err("Unknown error type, program reg:0x%05x failed!\n", offset);
+			} else
+				pr_err("timeout: rlcg program reg:0x%05x failed!\n", offset);
+		}
 	}
 
 	ret = readl(scratch_reg0);
@@ -1538,7 +1589,7 @@ static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32
 	return ret;
 }
 
-static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 value, u32 acc_flags, u32 hwip)
+static void gfx_v10_sriov_wreg(struct amdgpu_device *adev, u32 offset, u32 value, u32 acc_flags, u32 hwip)
 {
 	u32 rlcg_flag;
 
@@ -1554,7 +1605,7 @@ static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 value,
 		WREG32(offset, value);
 }
 
-static u32 gfx_v10_rlcg_rreg(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip)
+static u32 gfx_v10_sriov_rreg(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip)
 {
 	u32 rlcg_flag;
 
@@ -3488,12 +3539,51 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_5[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000)
 };
 
+static const struct soc15_reg_golden golden_settings_gc_10_0_cyan_skillfish[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_GFX_INDEX, 0xffffffff, 0xe0000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_FAST_CLKS, 0x3fffffff, 0x0000493e),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x3c000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0xa0000000, 0xa0000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x00008000, 0x003c8014),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_DRAM_BURST_CTRL, 0x00000010, 0x00000017),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_PIPE_STEER, 0xffffffff, 0xd8d8d8d8),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_VC5_ENABLE, 0x00000003, 0x00000003),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_SD_CNTL, 0x800007ff, 0x000005ff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG, 0xffffffff, 0x20000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04800000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_LAST_OF_BURST_CONFIG, 0xffffffff, 0x03860210),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1800ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x00009d00, 0x00008500),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCMC_VM_CACHEABLE_DRAM_ADDRESS_END, 0xffffffff, 0x000fffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_DRAM_BURST_CTRL, 0x00000010, 0x00000017),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0xfcfcfcfc, 0xd8d8d8d8),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77707770, 0x21302130),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77707770, 0x21302130),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CGTT_SCLK_CTRL, 0x10000000, 0x10000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL2, 0xfc02002f, 0x9402002f),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0x00002188, 0x00000188),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x08000009, 0x08000009),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_0, 0xcc3fcc03, 0x842a4c02),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000000f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffff3109, 0xffff3101),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000100, 0x00000130),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x00030008, 0x01030000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00800000, 0x00800000)
+};
+
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
 	 (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \
 	 (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT))
 
+/* TODO: pending on golden setting value of gb address config */
+#define CYAN_SKILLFISH_GB_ADDR_CONFIG_GOLDEN 0x00100044
 
 static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v10_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -3718,6 +3808,14 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_10_3_5,
 						(const u32)ARRAY_SIZE(golden_settings_gc_10_3_5));
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_0,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_0));
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_0_cyan_skillfish,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_0_cyan_skillfish));
+		break;
 	default:
 		break;
 	}
@@ -3891,6 +3989,7 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
 	case CHIP_NAVI14:
+	case CHIP_CYAN_SKILLFISH:
 		if ((adev->gfx.me_fw_version >= 0x00000046) &&
 		    (adev->gfx.me_feature_version >= 27) &&
 		    (adev->gfx.pfp_fw_version >= 0x00000068) &&
@@ -4025,6 +4124,12 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_YELLOW_CARP:
 		chip_name = "yellow_carp";
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2)
+			chip_name = "cyan_skillfish2";
+		else
+			chip_name = "cyan_skillfish";
+		break;
 	default:
 		BUG();
 	}
@@ -4516,6 +4621,7 @@ static void gfx_v10_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd,
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_STS2);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_DBG1);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v10_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
@@ -4604,6 +4710,14 @@ static void gfx_v10_0_gpu_early_init(struct amdgpu_device *adev)
 		adev->gfx.config.gb_addr_config_fields.num_pkrs =
 			1 << REG_GET_FIELD(gb_addr_config, GB_ADDR_CONFIG, NUM_PKRS);
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		adev->gfx.config.max_hw_contexts = 8;
+		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+		adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+		adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0;
+		gb_addr_config = CYAN_SKILLFISH_GB_ADDR_CONFIG_GOLDEN;
+		break;
 	default:
 		BUG();
 		break;
@@ -4708,6 +4822,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+	case CHIP_CYAN_SKILLFISH:
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
@@ -5319,7 +5434,8 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
+		adev->psp.autoload_supported) {
 
 		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
@@ -5379,7 +5495,7 @@ static int gfx_v10_0_parse_rlc_toc(struct amdgpu_device *adev)
 	int ret;
 	RLC_TABLE_OF_CONTENT *rlc_toc;
 
-	ret = amdgpu_bo_create_reserved(adev, adev->psp.toc_bin_size, PAGE_SIZE,
+	ret = amdgpu_bo_create_reserved(adev, adev->psp.toc.size_bytes, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_GTT,
 					&adev->gfx.rlc.rlc_toc_bo,
 					&adev->gfx.rlc.rlc_toc_gpu_addr,
@@ -5390,7 +5506,7 @@ static int gfx_v10_0_parse_rlc_toc(struct amdgpu_device *adev)
 	}
 
 	/* Copy toc from psp sos fw to rlc toc buffer */
-	memcpy(adev->gfx.rlc.rlc_toc_buf, adev->psp.toc_start_addr, adev->psp.toc_bin_size);
+	memcpy(adev->gfx.rlc.rlc_toc_buf, adev->psp.toc.start_addr, adev->psp.toc.size_bytes);
 
 	rlc_toc = (RLC_TABLE_OF_CONTENT *)adev->gfx.rlc.rlc_toc_buf;
 	while (rlc_toc && (rlc_toc->id > FIRMWARE_ID_INVALID) &&
@@ -7608,10 +7724,8 @@ static int gfx_v10_0_soft_reset(void *handle)
 
 static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
-	uint64_t clock;
+	uint64_t clock, clock_lo, clock_hi, hi_check;
 
-	amdgpu_gfx_off_ctrl(adev, false);
-	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	switch (adev->asic_type) {
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
@@ -7619,12 +7733,21 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
 		break;
 	default:
-		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
-			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+		preempt_disable();
+		clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
+		clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
+		hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
+		/* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+		 * roughly every 42 seconds.
+		 */
+		if (hi_check != clock_hi) {
+			clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
+			clock_hi = hi_check;
+		}
+		preempt_enable();
+		clock = clock_lo | (clock_hi << 32ULL);
 		break;
 	}
-	mutex_unlock(&adev->gfx.gpu_clock_mutex);
-	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
@@ -7665,6 +7788,7 @@ static int gfx_v10_0_early_init(void *handle)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+	case CHIP_CYAN_SKILLFISH:
 		adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS_NV1X;
 		break;
 	case CHIP_SIENNA_CICHLID:
@@ -8261,8 +8385,8 @@ static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs_sriov = {
 	.reset = gfx_v10_0_rlc_reset,
 	.start = gfx_v10_0_rlc_start,
 	.update_spm_vmid = gfx_v10_0_update_spm_vmid,
-	.rlcg_wreg = gfx_v10_rlcg_wreg,
-	.rlcg_rreg = gfx_v10_rlcg_rreg,
+	.sriov_wreg = gfx_v10_sriov_wreg,
+	.sriov_rreg = gfx_v10_sriov_rreg,
 	.is_rlcg_access_range = gfx_v10_0_is_rlcg_access_range,
 };
 
@@ -9425,6 +9549,7 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		adev->gfx.rlc.funcs = &gfx_v10_0_rlc_funcs;
 		break;
 	case CHIP_NAVI12:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 3a8d52a54873..6a8dadea40f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3027,6 +3027,7 @@ static void gfx_v6_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 685212c3ddae..37b4a3db6360 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4198,6 +4198,7 @@ static void gfx_v7_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v7_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index c26e06059466..e0302c23e9a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5279,6 +5279,7 @@ static void gfx_v8_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v8_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6a23c6826e12..603c259b073b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -787,7 +787,7 @@ static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 
 }
 
-static void gfx_v9_0_rlcg_wreg(struct amdgpu_device *adev, u32 offset,
+static void gfx_v9_0_sriov_wreg(struct amdgpu_device *adev, u32 offset,
 			       u32 v, u32 acc_flags, u32 hwip)
 {
 	if ((acc_flags & AMDGPU_REGS_RLC) &&
@@ -2090,6 +2090,7 @@ static void gfx_v9_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_STS);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v9_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
@@ -5150,7 +5151,7 @@ static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
 	.reset = gfx_v9_0_rlc_reset,
 	.start = gfx_v9_0_rlc_start,
 	.update_spm_vmid = gfx_v9_0_update_spm_vmid,
-	.rlcg_wreg = gfx_v9_0_rlcg_wreg,
+	.sriov_wreg = gfx_v9_0_sriov_wreg,
 	.is_rlcg_access_range = gfx_v9_0_is_rlcg_access_range,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
index 1769c4cba2ad..00a2b36a24b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
@@ -85,7 +85,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_2_alde[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCI_CNTL_3, 0xff, 0x20),
 };
 
-/**
+/*
  * This shader is used to clear VGPRS and LDS, and also write the input
  * pattern into the write back buffer, which will be used by driver to
  * check whether all SIMDs have been covered.
@@ -206,7 +206,7 @@ const struct soc15_reg_entry vgpr_init_regs_aldebaran[] = {
 	{ SOC15_REG_ENTRY(GC, 0, regCOMPUTE_STATIC_THREAD_MGMT_SE7), 0xffffffff },
 };
 
-/**
+/*
  * The below shaders are used to clear SGPRS, and also write the input
  * pattern into the write back buffer. The first two dispatch should be
  * scheduled simultaneously which make sure that all SGPRS could be
@@ -302,7 +302,7 @@ const struct soc15_reg_entry sgpr96_init_regs_aldebaran[] = {
 	{ SOC15_REG_ENTRY(GC, 0, regCOMPUTE_STATIC_THREAD_MGMT_SE7), 0xffffffff },
 };
 
-/**
+/*
  * This shader is used to clear the uninitiated sgprs after the above
  * two dispatches, because of hardware feature, dispath 0 couldn't clear
  * top hole sgprs. Therefore need 4 waves per SIMD to cover these sgprs
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 8fca72ebd11c..497b86c376c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -75,9 +75,8 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		max_physical_node_id     = 7;
 		break;
 	case CHIP_ALDEBARAN:
-		/* just using duplicates for Aldebaran support, revisit later */
-		max_num_physical_nodes   = 8;
-		max_physical_node_id     = 7;
+		max_num_physical_nodes   = 16;
+		max_physical_node_id     = 15;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 4523df2785d6..41c3a0d70b7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -93,6 +93,7 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 				       struct amdgpu_iv_entry *entry)
 {
 	bool retry_fault = !!(entry->src_data[1] & 0x80);
+	bool write_fault = !!(entry->src_data[1] & 0x20);
 	struct amdgpu_vmhub *hub = &adev->vmhub[entry->vmid_src];
 	struct amdgpu_task_info task_info;
 	uint32_t status = 0;
@@ -121,7 +122,7 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 		/* Try to handle the recoverable page faults by filling page
 		 * tables
 		 */
-		if (amdgpu_vm_handle_fault(adev, entry->pasid, addr))
+		if (amdgpu_vm_handle_fault(adev, entry->pasid, addr, write_fault))
 			return 1;
 	}
 
@@ -810,6 +811,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev)
 		case CHIP_DIMGREY_CAVEFISH:
 		case CHIP_BEIGE_GOBY:
 		case CHIP_YELLOW_CARP:
+		case CHIP_CYAN_SKILLFISH:
 		default:
 			adev->gmc.gart_size = 512ULL << 20;
 			break;
@@ -879,6 +881,7 @@ static int gmc_v10_0_sw_init(void *handle)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		adev->num_vmhubs = 2;
 		/*
 		 * To fulfill 4-level page support,
@@ -996,6 +999,7 @@ static void gmc_v10_0_init_golden_registers(struct amdgpu_device *adev)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 7eb70d69f760..d90c16a6b2b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -53,7 +53,9 @@
 #include "mmhub_v1_7.h"
 #include "umc_v6_1.h"
 #include "umc_v6_0.h"
+#include "umc_v6_7.h"
 #include "hdp_v4_0.h"
+#include "mca_v3_0.h"
 
 #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
 
@@ -505,6 +507,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_iv_entry *entry)
 {
 	bool retry_fault = !!(entry->src_data[1] & 0x80);
+	bool write_fault = !!(entry->src_data[1] & 0x20);
 	uint32_t status = 0, cid = 0, rw = 0;
 	struct amdgpu_task_info task_info;
 	struct amdgpu_vmhub *hub;
@@ -535,7 +538,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 		/* Try to handle the recoverable page faults by filling page
 		 * tables
 		 */
-		if (amdgpu_vm_handle_fault(adev, entry->pasid, addr))
+		if (amdgpu_vm_handle_fault(adev, entry->pasid, addr, write_fault))
 			return 1;
 	}
 
@@ -1168,6 +1171,18 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 		adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0];
 		adev->umc.ras_funcs = &umc_v6_1_ras_funcs;
 		break;
+	case CHIP_ALDEBARAN:
+		adev->umc.max_ras_err_cnt_per_query = UMC_V6_7_TOTAL_CHANNEL_NUM;
+		adev->umc.channel_inst_num = UMC_V6_7_CHANNEL_INSTANCE_NUM;
+		adev->umc.umc_inst_num = UMC_V6_7_UMC_INSTANCE_NUM;
+		adev->umc.channel_offs = UMC_V6_7_PER_CHANNEL_OFFSET;
+		if (!adev->gmc.xgmi.connected_to_cpu)
+			adev->umc.ras_funcs = &umc_v6_7_ras_funcs;
+		if (1 & adev->smuio.funcs->get_die_id(adev))
+			adev->umc.channel_idx_tbl = &umc_v6_7_channel_idx_tbl_first[0][0];
+		else
+			adev->umc.channel_idx_tbl = &umc_v6_7_channel_idx_tbl_second[0][0];
+		break;
 	default:
 		break;
 	}
@@ -1216,6 +1231,18 @@ static void gmc_v9_0_set_hdp_ras_funcs(struct amdgpu_device *adev)
 	adev->hdp.ras_funcs = &hdp_v4_0_ras_funcs;
 }
 
+static void gmc_v9_0_set_mca_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_ALDEBARAN:
+		if (!adev->gmc.xgmi.connected_to_cpu)
+			adev->mca.funcs = &mca_v3_0_funcs;
+		break;
+	default:
+		break;
+	}
+}
+
 static int gmc_v9_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1237,6 +1264,7 @@ static int gmc_v9_0_early_init(void *handle)
 	gmc_v9_0_set_mmhub_ras_funcs(adev);
 	gmc_v9_0_set_gfxhub_funcs(adev);
 	gmc_v9_0_set_hdp_ras_funcs(adev);
+	gmc_v9_0_set_mca_funcs(adev);
 
 	adev->gmc.shared_aperture_start = 0x2000000000000000ULL;
 	adev->gmc.shared_aperture_end =
@@ -1448,6 +1476,8 @@ static int gmc_v9_0_sw_init(void *handle)
 	adev->gfxhub.funcs->init(adev);
 
 	adev->mmhub.funcs->init(adev);
+	if (adev->mca.funcs)
+		adev->mca.funcs->init(adev);
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c
new file mode 100644
index 000000000000..058b65730a84
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c
@@ -0,0 +1,125 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu_ras.h"
+#include "amdgpu.h"
+#include "amdgpu_mca.h"
+
+#define smnMCMP0_STATUST0 	0x03830408
+#define smnMCMP1_STATUST0 	0x03b30408
+#define smnMCMPIO_STATUST0 	0x0c930408
+
+
+static void mca_v3_0_mp0_query_ras_error_count(struct amdgpu_device *adev,
+					       void *ras_error_status)
+{
+	amdgpu_mca_query_ras_error_count(adev,
+				         smnMCMP0_STATUST0,
+				         ras_error_status);
+}
+
+static int mca_v3_0_mp0_ras_late_init(struct amdgpu_device *adev)
+{
+	return amdgpu_mca_ras_late_init(adev, &adev->mca.mp0);
+}
+
+static void mca_v3_0_mp0_ras_fini(struct amdgpu_device *adev)
+{
+	amdgpu_mca_ras_fini(adev, &adev->mca.mp0);
+}
+
+const struct amdgpu_mca_ras_funcs mca_v3_0_mp0_ras_funcs = {
+	.ras_late_init = mca_v3_0_mp0_ras_late_init,
+	.ras_fini = mca_v3_0_mp0_ras_fini,
+	.query_ras_error_count = mca_v3_0_mp0_query_ras_error_count,
+	.query_ras_error_address = NULL,
+	.ras_block = AMDGPU_RAS_BLOCK__MP0,
+	.sysfs_name = "mp0_err_count",
+};
+
+static void mca_v3_0_mp1_query_ras_error_count(struct amdgpu_device *adev,
+					       void *ras_error_status)
+{
+	amdgpu_mca_query_ras_error_count(adev,
+				         smnMCMP1_STATUST0,
+				         ras_error_status);
+}
+
+static int mca_v3_0_mp1_ras_late_init(struct amdgpu_device *adev)
+{
+	return amdgpu_mca_ras_late_init(adev, &adev->mca.mp1);
+}
+
+static void mca_v3_0_mp1_ras_fini(struct amdgpu_device *adev)
+{
+	amdgpu_mca_ras_fini(adev, &adev->mca.mp1);
+}
+
+const struct amdgpu_mca_ras_funcs mca_v3_0_mp1_ras_funcs = {
+	.ras_late_init = mca_v3_0_mp1_ras_late_init,
+	.ras_fini = mca_v3_0_mp1_ras_fini,
+	.query_ras_error_count = mca_v3_0_mp1_query_ras_error_count,
+	.query_ras_error_address = NULL,
+	.ras_block = AMDGPU_RAS_BLOCK__MP1,
+	.sysfs_name = "mp1_err_count",
+};
+
+static void mca_v3_0_mpio_query_ras_error_count(struct amdgpu_device *adev,
+					       void *ras_error_status)
+{
+	amdgpu_mca_query_ras_error_count(adev,
+				         smnMCMPIO_STATUST0,
+				         ras_error_status);
+}
+
+static int mca_v3_0_mpio_ras_late_init(struct amdgpu_device *adev)
+{
+	return amdgpu_mca_ras_late_init(adev, &adev->mca.mpio);
+}
+
+static void mca_v3_0_mpio_ras_fini(struct amdgpu_device *adev)
+{
+	amdgpu_mca_ras_fini(adev, &adev->mca.mpio);
+}
+
+const struct amdgpu_mca_ras_funcs mca_v3_0_mpio_ras_funcs = {
+	.ras_late_init = mca_v3_0_mpio_ras_late_init,
+	.ras_fini = mca_v3_0_mpio_ras_fini,
+	.query_ras_error_count = mca_v3_0_mpio_query_ras_error_count,
+	.query_ras_error_address = NULL,
+	.ras_block = AMDGPU_RAS_BLOCK__MPIO,
+	.sysfs_name = "mpio_err_count",
+};
+
+
+static void mca_v3_0_init(struct amdgpu_device *adev)
+{
+	struct amdgpu_mca *mca = &adev->mca;
+
+	mca->mp0.ras_funcs = &mca_v3_0_mp0_ras_funcs;
+	mca->mp1.ras_funcs = &mca_v3_0_mp1_ras_funcs;
+	mca->mpio.ras_funcs = &mca_v3_0_mpio_ras_funcs;
+}
+
+const struct amdgpu_mca_funcs mca_v3_0_funcs = {
+	.init = mca_v3_0_init,
+};
\ No newline at end of file
diff --git a/drivers/gpu/drm/amd/amdgpu/mca_v3_0.h b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.h
new file mode 100644
index 000000000000..b899b86194c2
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2021  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef __MCA_V3_0_H__
+#define __MCA_V3_0_H__
+
+extern const struct amdgpu_mca_funcs mca_v3_0_funcs;
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
index 20958639b601..2cdab8062c86 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
@@ -24,9 +24,7 @@
 #ifndef __MMSCH_V1_0_H__
 #define __MMSCH_V1_0_H__
 
-#define MMSCH_VERSION_MAJOR	1
-#define MMSCH_VERSION_MINOR	0
-#define MMSCH_VERSION	(MMSCH_VERSION_MAJOR << 16 | MMSCH_VERSION_MINOR)
+#define MMSCH_VERSION	0x1
 
 enum mmsch_v1_0_command_type {
 	MMSCH_COMMAND__DIRECT_REG_WRITE = 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 9f7aac435d69..a35e6d87e537 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -96,7 +96,11 @@ static int xgpu_nv_poll_ack(struct amdgpu_device *adev)
 
 static int xgpu_nv_poll_msg(struct amdgpu_device *adev, enum idh_event event)
 {
-	int r, timeout = NV_MAILBOX_POLL_MSG_TIMEDOUT;
+	int r;
+	uint64_t timeout, now;
+
+	now = (uint64_t)ktime_to_ms(ktime_get());
+	timeout = now + NV_MAILBOX_POLL_MSG_TIMEDOUT;
 
 	do {
 		r = xgpu_nv_mailbox_rcv_msg(adev, event);
@@ -104,8 +108,8 @@ static int xgpu_nv_poll_msg(struct amdgpu_device *adev, enum idh_event event)
 			return 0;
 
 		msleep(10);
-		timeout -= 10;
-	} while (timeout > 1);
+		now = (uint64_t)ktime_to_ms(ktime_get());
+	} while (timeout > now);
 
 
 	return -ETIME;
@@ -149,9 +153,10 @@ static void xgpu_nv_mailbox_trans_msg (struct amdgpu_device *adev,
 static int xgpu_nv_send_access_requests(struct amdgpu_device *adev,
 					enum idh_request req)
 {
-	int r;
+	int r, retry = 1;
 	enum idh_event event = -1;
 
+send_request:
 	xgpu_nv_mailbox_trans_msg(adev, req, 0, 0, 0);
 
 	switch (req) {
@@ -170,6 +175,9 @@ static int xgpu_nv_send_access_requests(struct amdgpu_device *adev,
 	if (event != -1) {
 		r = xgpu_nv_poll_msg(adev, event);
 		if (r) {
+			if (retry++ < 2)
+				goto send_request;
+
 			if (req != IDH_REQ_GPU_INIT_DATA) {
 				pr_err("Doesn't get msg:%d from pf, error=%d\n", event, r);
 				return r;
@@ -279,6 +287,8 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	amdgpu_virt_fini_data_exchange(adev);
 	atomic_set(&adev->in_gpu_reset, 1);
 
+	xgpu_nv_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
+
 	do {
 		if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
 			goto flr_done;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
index 9f5808616174..73887b0aa1d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
@@ -37,7 +37,8 @@ enum idh_request {
 	IDH_REQ_GPU_RESET_ACCESS,
 	IDH_REQ_GPU_INIT_DATA,
 
-	IDH_LOG_VF_ERROR       = 200,
+	IDH_LOG_VF_ERROR	= 200,
+	IDH_READY_TO_RESET 	= 201,
 };
 
 enum idh_event {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 7b79eeaa88aa..b184b656b9b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -508,6 +508,26 @@ static void nbio_v2_3_apply_l1_link_width_reconfig_wa(struct amdgpu_device *adev
 	WREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL, reg_data);
 }
 
+static void nbio_v2_3_clear_doorbell_interrupt(struct amdgpu_device *adev)
+{
+	uint32_t reg, reg_data;
+
+	if (adev->asic_type != CHIP_SIENNA_CICHLID)
+		return;
+
+	reg = RREG32_SOC15(NBIO, 0, mmBIF_RB_CNTL);
+
+	/* Clear Interrupt Status
+	 */
+	if ((reg & BIF_RB_CNTL__RB_ENABLE_MASK) == 0) {
+		reg = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+		if (reg & BIF_DOORBELL_INT_CNTL__DOORBELL_INTERRUPT_STATUS_MASK) {
+			reg_data = 1 << BIF_DOORBELL_INT_CNTL__DOORBELL_INTERRUPT_CLEAR__SHIFT;
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, reg_data);
+		}
+	}
+}
+
 const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset,
@@ -531,4 +551,5 @@ const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.program_aspm =  nbio_v2_3_program_aspm,
 	.apply_lc_spc_mode_wa = nbio_v2_3_apply_lc_spc_mode_wa,
 	.apply_l1_link_width_reconfig_wa = nbio_v2_3_apply_l1_link_width_reconfig_wa,
+	.clear_doorbell_interrupt = nbio_v2_3_clear_doorbell_interrupt,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index cef929746739..ba1d3ab869c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -85,6 +85,11 @@
 #define mmRCC_DEV0_EPF0_STRAP0_ALDE			0x0015
 #define mmRCC_DEV0_EPF0_STRAP0_ALDE_BASE_IDX		2
 
+#define mmBIF_DOORBELL_INT_CNTL_ALDE 			0x3878
+#define mmBIF_DOORBELL_INT_CNTL_ALDE_BASE_IDX 		2
+#define BIF_DOORBELL_INT_CNTL_ALDE__DOORBELL_INTERRUPT_DISABLE__SHIFT	0x18
+#define BIF_DOORBELL_INT_CNTL_ALDE__DOORBELL_INTERRUPT_DISABLE_MASK	0x01000000L
+
 static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 					void *ras_error_status);
 
@@ -346,14 +351,21 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 	struct ras_err_data err_data = {0, 0, 0, NULL};
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
-	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL_ALDE);
+	else
+		bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+
 	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
 		BIF_DOORBELL_INT_CNTL, RAS_CNTLR_INTERRUPT_STATUS)) {
 		/* driver has to clear the interrupt status when bif ring is disabled */
 		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
 						BIF_DOORBELL_INT_CNTL,
 						RAS_CNTLR_INTERRUPT_CLEAR, 1);
-		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+		if (adev->asic_type == CHIP_ALDEBARAN)
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL_ALDE, bif_doorbell_intr_cntl);
+		else
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
 
 		if (!ras->disable_ras_err_cnt_harvest) {
 			/*
@@ -372,13 +384,13 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 						"errors detected in %s block, "
 						"no user action is needed.\n",
 						obj->err_data.ce_count,
-						adev->nbio.ras_if->name);
+						ras_block_str(adev->nbio.ras_if->block));
 
 			if (err_data.ue_count)
 				dev_info(adev->dev, "%ld uncorrectable hardware "
 						"errors detected in %s block\n",
 						obj->err_data.ue_count,
-						adev->nbio.ras_if->name);
+						ras_block_str(adev->nbio.ras_if->block));
 		}
 
 		dev_info(adev->dev, "RAS controller interrupt triggered "
@@ -395,14 +407,22 @@ static void nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring(struct amdgpu_d
 {
 	uint32_t bif_doorbell_intr_cntl;
 
-	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL_ALDE);
+	else
+		bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+
 	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
 		BIF_DOORBELL_INT_CNTL, RAS_ATHUB_ERR_EVENT_INTERRUPT_STATUS)) {
 		/* driver has to clear the interrupt status when bif ring is disabled */
 		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
 						BIF_DOORBELL_INT_CNTL,
 						RAS_ATHUB_ERR_EVENT_INTERRUPT_CLEAR, 1);
-		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		if (adev->asic_type == CHIP_ALDEBARAN)
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL_ALDE, bif_doorbell_intr_cntl);
+		else
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
 
 		amdgpu_ras_global_ras_isr(adev);
 	}
@@ -572,7 +592,11 @@ static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 static void nbio_v7_4_enable_doorbell_interrupt(struct amdgpu_device *adev,
 						bool enable)
 {
-	WREG32_FIELD15(NBIO, 0, BIF_DOORBELL_INT_CNTL,
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		WREG32_FIELD15(NBIO, 0, BIF_DOORBELL_INT_CNTL_ALDE,
+		       DOORBELL_INTERRUPT_DISABLE, enable ? 0 : 1);
+	else
+		WREG32_FIELD15(NBIO, 0, BIF_DOORBELL_INT_CNTL,
 		       DOORBELL_INTERRUPT_DISABLE, enable ? 0 : 1);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 94d029dbf30d..ff80786e3918 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -58,7 +58,7 @@
 #include "jpeg_v2_0.h"
 #include "vcn_v3_0.h"
 #include "jpeg_v3_0.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mes_v10_1.h"
 #include "mxgpu_nv.h"
 #include "smuio_v11_0.h"
@@ -666,6 +666,9 @@ legacy_init:
 	case CHIP_YELLOW_CARP:
 		yellow_carp_reg_base_init(adev);
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		cyan_skillfish_reg_base_init(adev);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -682,7 +685,10 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (adev->flags & AMD_IS_APU) {
+	if (adev->asic_type == CHIP_CYAN_SKILLFISH) {
+		adev->nbio.funcs = &nbio_v2_3_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg;
+	} else if (adev->flags & AMD_IS_APU) {
 		adev->nbio.funcs = &nbio_v7_2_funcs;
 		adev->nbio.hdp_flush_reg = &nbio_v7_2_hdp_flush_reg;
 	} else {
@@ -715,7 +721,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -743,7 +749,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -773,7 +779,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -796,7 +802,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -817,7 +823,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -837,7 +843,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -859,7 +865,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -877,11 +883,11 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -889,6 +895,20 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) {
+			if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
+				amdgpu_device_ip_block_add(adev, &psp_v11_0_8_ip_block);
+			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		}
+		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1241,6 +1261,11 @@ static int nv_common_early_init(void *handle)
 		else
 			adev->external_rev_id = adev->rev_id + 0x01;
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		adev->cg_flags = 0;
+		adev->pg_flags = 0;
+		adev->external_rev_id = adev->rev_id + 0x82;
+		break;
 	default:
 		/* FIXME: not supported yet */
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.h b/drivers/gpu/drm/amd/amdgpu/nv.h
index eb9aff1e7253..1f40ba3b0460 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/nv.h
@@ -38,5 +38,6 @@ void vangogh_reg_base_init(struct amdgpu_device *adev);
 int dimgrey_cavefish_reg_base_init(struct amdgpu_device *adev);
 int beige_goby_reg_base_init(struct amdgpu_device *adev);
 int yellow_carp_reg_base_init(struct amdgpu_device *adev);
+int cyan_skillfish_reg_base_init(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 4b1cc5e9ee92..5872d68ed13d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -84,29 +84,29 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
 
 		ta_hdr = (const struct ta_firmware_header_v1_0 *)
 				 adev->psp.ta_fw->data;
-		adev->psp.ta_hdcp_ucode_version =
-			le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
-		adev->psp.ta_hdcp_ucode_size =
-			le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
-		adev->psp.ta_hdcp_start_addr =
+		adev->psp.hdcp.feature_version =
+			le32_to_cpu(ta_hdr->hdcp.fw_version);
+		adev->psp.hdcp.size_bytes =
+			le32_to_cpu(ta_hdr->hdcp.size_bytes);
+		adev->psp.hdcp.start_addr =
 			(uint8_t *)ta_hdr +
 			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
 
-		adev->psp.ta_dtm_ucode_version =
-			le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
-		adev->psp.ta_dtm_ucode_size =
-			le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
-		adev->psp.ta_dtm_start_addr =
-			(uint8_t *)adev->psp.ta_hdcp_start_addr +
-			le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
-
-		adev->psp.ta_securedisplay_ucode_version =
-			le32_to_cpu(ta_hdr->ta_securedisplay_ucode_version);
-		adev->psp.ta_securedisplay_ucode_size =
-			le32_to_cpu(ta_hdr->ta_securedisplay_size_bytes);
-		adev->psp.ta_securedisplay_start_addr =
-			(uint8_t *)adev->psp.ta_hdcp_start_addr +
-			le32_to_cpu(ta_hdr->ta_securedisplay_offset_bytes);
+		adev->psp.dtm.feature_version =
+			le32_to_cpu(ta_hdr->dtm.fw_version);
+		adev->psp.dtm.size_bytes =
+			le32_to_cpu(ta_hdr->dtm.size_bytes);
+		adev->psp.dtm.start_addr =
+			(uint8_t *)adev->psp.hdcp.start_addr +
+			le32_to_cpu(ta_hdr->dtm.offset_bytes);
+
+		adev->psp.securedisplay.feature_version =
+			le32_to_cpu(ta_hdr->securedisplay.fw_version);
+		adev->psp.securedisplay.size_bytes =
+			le32_to_cpu(ta_hdr->securedisplay.size_bytes);
+		adev->psp.securedisplay.start_addr =
+			(uint8_t *)adev->psp.hdcp.start_addr +
+			le32_to_cpu(ta_hdr->securedisplay.offset_bytes);
 
 		adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index bc133db2d538..29bf9f09944b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -80,6 +80,9 @@ MODULE_FIRMWARE("amdgpu/beige_goby_ta.bin");
 /* For large FW files the time to complete can be very long */
 #define USBC_PD_POLLING_LIMIT_S 240
 
+/* Read USB-PD from LFB */
+#define GFX_CMD_USB_PD_USE_LFB 0x480
+
 static int psp_v11_0_init_microcode(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -148,15 +151,15 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 				goto out2;
 
 			ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
-			adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
-			adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes);
-			adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr +
+			adev->psp.xgmi.feature_version = le32_to_cpu(ta_hdr->xgmi.fw_version);
+			adev->psp.xgmi.size_bytes = le32_to_cpu(ta_hdr->xgmi.size_bytes);
+			adev->psp.xgmi.start_addr = (uint8_t *)ta_hdr +
 				le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
 			adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
-			adev->psp.ta_ras_ucode_version = le32_to_cpu(ta_hdr->ta_ras_ucode_version);
-			adev->psp.ta_ras_ucode_size = le32_to_cpu(ta_hdr->ta_ras_size_bytes);
-			adev->psp.ta_ras_start_addr = (uint8_t *)adev->psp.ta_xgmi_start_addr +
-				le32_to_cpu(ta_hdr->ta_ras_offset_bytes);
+			adev->psp.ras.feature_version = le32_to_cpu(ta_hdr->ras.fw_version);
+			adev->psp.ras.size_bytes = le32_to_cpu(ta_hdr->ras.size_bytes);
+			adev->psp.ras.start_addr = (uint8_t *)adev->psp.xgmi.start_addr +
+				le32_to_cpu(ta_hdr->ras.offset_bytes);
 		}
 		break;
 	case CHIP_NAVI10:
@@ -183,17 +186,17 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 				goto out2;
 
 			ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
-			adev->psp.ta_hdcp_ucode_version = le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
-			adev->psp.ta_hdcp_ucode_size = le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
-			adev->psp.ta_hdcp_start_addr = (uint8_t *)ta_hdr +
+			adev->psp.hdcp.feature_version = le32_to_cpu(ta_hdr->hdcp.fw_version);
+			adev->psp.hdcp.size_bytes = le32_to_cpu(ta_hdr->hdcp.size_bytes);
+			adev->psp.hdcp.start_addr = (uint8_t *)ta_hdr +
 				le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
 
 			adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
 
-			adev->psp.ta_dtm_ucode_version = le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
-			adev->psp.ta_dtm_ucode_size = le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
-			adev->psp.ta_dtm_start_addr = (uint8_t *)adev->psp.ta_hdcp_start_addr +
-				le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+			adev->psp.dtm.feature_version = le32_to_cpu(ta_hdr->dtm.fw_version);
+			adev->psp.dtm.size_bytes = le32_to_cpu(ta_hdr->dtm.size_bytes);
+			adev->psp.dtm.start_addr = (uint8_t *)adev->psp.hdcp.start_addr +
+				le32_to_cpu(ta_hdr->dtm.offset_bytes);
 		}
 		break;
 	case CHIP_SIENNA_CICHLID:
@@ -284,7 +287,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 		return ret;
 
 	/* Copy PSP KDB binary to memory */
-	psp_copy_fw(psp, psp->kdb_start_addr, psp->kdb_bin_size);
+	psp_copy_fw(psp, psp->kdb.start_addr, psp->kdb.size_bytes);
 
 	/* Provide the PSP KDB to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -315,7 +318,7 @@ static int psp_v11_0_bootloader_load_spl(struct psp_context *psp)
 		return ret;
 
 	/* Copy PSP SPL binary to memory */
-	psp_copy_fw(psp, psp->spl_start_addr, psp->spl_bin_size);
+	psp_copy_fw(psp, psp->spl.start_addr, psp->spl.size_bytes);
 
 	/* Provide the PSP SPL to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -346,7 +349,7 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 		return ret;
 
 	/* Copy PSP System Driver binary to memory */
-	psp_copy_fw(psp, psp->sys_start_addr, psp->sys_bin_size);
+	psp_copy_fw(psp, psp->sys.start_addr, psp->sys.size_bytes);
 
 	/* Provide the sys driver to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -380,7 +383,7 @@ static int psp_v11_0_bootloader_load_sos(struct psp_context *psp)
 		return ret;
 
 	/* Copy Secure OS binary to PSP memory */
-	psp_copy_fw(psp, psp->sos_start_addr, psp->sos_bin_size);
+	psp_copy_fw(psp, psp->sos.start_addr, psp->sos.size_bytes);
 
 	/* Provide the PSP secure OS to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -753,44 +756,26 @@ static void psp_v11_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
 }
 
-static int psp_v11_0_load_usbc_pd_fw(struct psp_context *psp, dma_addr_t dma_addr)
+static int psp_v11_0_load_usbc_pd_fw(struct psp_context *psp, uint64_t fw_pri_mc_addr)
 {
 	struct amdgpu_device *adev = psp->adev;
 	uint32_t reg_status;
 	int ret, i = 0;
 
-	/* Write lower 32-bit address of the PD Controller FW */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36, lower_32_bits(dma_addr));
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			     0x80000000, 0x80000000, false);
-	if (ret)
-		return ret;
-
-	/* Fireup interrupt so PSP can pick up the lower address */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35, 0x800000);
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			     0x80000000, 0x80000000, false);
-	if (ret)
-		return ret;
-
-	reg_status = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35);
-
-	if ((reg_status & 0xFFFF) != 0) {
-		DRM_ERROR("Lower address load failed - MP0_SMN_C2PMSG_35.Bits [15:0] = %02x...\n",
-				reg_status & 0xFFFF);
-		return -EIO;
-	}
-
-	/* Write upper 32-bit address of the PD Controller FW */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36, upper_32_bits(dma_addr));
+	/*
+	 * LFB address which is aligned to 1MB address and has to be
+	 * right-shifted by 20 so that LFB address can be passed on a 32-bit C2P
+	 * register
+	 */
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36, (fw_pri_mc_addr >> 20));
 
 	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
 			     0x80000000, 0x80000000, false);
 	if (ret)
 		return ret;
 
-	/* Fireup interrupt so PSP can pick up the upper address */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35, 0x4000000);
+	/* Fireup interrupt so PSP can pick up the address */
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35, (GFX_CMD_USB_PD_USE_LFB << 16));
 
 	/* FW load takes very long time */
 	do {
@@ -806,7 +791,7 @@ static int psp_v11_0_load_usbc_pd_fw(struct psp_context *psp, dma_addr_t dma_add
 done:
 
 	if ((reg_status & 0xFFFF) != 0) {
-		DRM_ERROR("Upper address load failed - MP0_SMN_C2PMSG_35.Bits [15:0] = x%04x\n",
+		DRM_ERROR("Address load failed - MP0_SMN_C2PMSG_35.Bits [15:0] = 0x%04x\n",
 				reg_status & 0xFFFF);
 		return -EIO;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c
new file mode 100644
index 000000000000..ff13e1beb49b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c
@@ -0,0 +1,208 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "amdgpu_psp.h"
+#include "amdgpu_ucode.h"
+#include "soc15_common.h"
+#include "psp_v11_0_8.h"
+
+#include "mp/mp_11_0_8_offset.h"
+
+static int psp_v11_0_8_ring_init(struct psp_context *psp,
+			      enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	struct psp_ring *ring;
+	struct amdgpu_device *adev = psp->adev;
+
+	ring = &psp->km_ring;
+
+	ring->ring_type = ring_type;
+
+	/* allocate 4k Page of Local Frame Buffer memory for ring */
+	ring->ring_size = 0x1000;
+	ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &adev->firmware.rbuf,
+				      &ring->ring_mem_mc_addr,
+				      (void **)&ring->ring_mem);
+	if (ret) {
+		ring->ring_size = 0;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int psp_v11_0_8_ring_stop(struct psp_context *psp,
+			       enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (amdgpu_sriov_vf(adev)) {
+		/* Write the ring destroy command*/
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+			     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
+		/* there might be handshake issue with hardware which needs delay */
+		mdelay(20);
+		/* Wait for response flag (bit 31) */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
+				   0x80000000, 0x80000000, false);
+	} else {
+		/* Write the ring destroy command*/
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64,
+			     GFX_CTRL_CMD_ID_DESTROY_RINGS);
+		/* there might be handshake issue with hardware which needs delay */
+		mdelay(20);
+		/* Wait for response flag (bit 31) */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+	}
+
+	return ret;
+}
+
+static int psp_v11_0_8_ring_create(struct psp_context *psp,
+				 enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	unsigned int psp_ring_reg = 0;
+	struct psp_ring *ring = &psp->km_ring;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (amdgpu_sriov_vf(adev)) {
+		ret = psp_v11_0_8_ring_stop(psp, ring_type);
+		if (ret) {
+			DRM_ERROR("psp_v11_0_8_ring_stop_sriov failed!\n");
+			return ret;
+		}
+
+		/* Write low address of the ring to C2PMSG_102 */
+		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg);
+		/* Write high address of the ring to C2PMSG_103 */
+		psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_103, psp_ring_reg);
+
+		/* Write the ring initialization command to C2PMSG_101 */
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+			     GFX_CTRL_CMD_ID_INIT_GPCOM_RING);
+
+		/* there might be handshake issue with hardware which needs delay */
+		mdelay(20);
+
+		/* Wait for response flag (bit 31) in C2PMSG_101 */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
+				   0x80000000, 0x8000FFFF, false);
+
+	} else {
+		/* Wait for sOS ready for ring creation */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+		if (ret) {
+			DRM_ERROR("Failed to wait for trust OS ready for ring creation\n");
+			return ret;
+		}
+
+		/* Write low address of the ring to C2PMSG_69 */
+		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_69, psp_ring_reg);
+		/* Write high address of the ring to C2PMSG_70 */
+		psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_70, psp_ring_reg);
+		/* Write size of ring to C2PMSG_71 */
+		psp_ring_reg = ring->ring_size;
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_71, psp_ring_reg);
+		/* Write the ring initialization command to C2PMSG_64 */
+		psp_ring_reg = ring_type;
+		psp_ring_reg = psp_ring_reg << 16;
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64, psp_ring_reg);
+
+		/* there might be handshake issue with hardware which needs delay */
+		mdelay(20);
+
+		/* Wait for response flag (bit 31) in C2PMSG_64 */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x8000FFFF, false);
+	}
+
+	return ret;
+}
+
+static int psp_v11_0_8_ring_destroy(struct psp_context *psp,
+				  enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	struct psp_ring *ring = &psp->km_ring;
+	struct amdgpu_device *adev = psp->adev;
+
+	ret = psp_v11_0_8_ring_stop(psp, ring_type);
+	if (ret)
+		DRM_ERROR("Fail to stop psp ring\n");
+
+	amdgpu_bo_free_kernel(&adev->firmware.rbuf,
+			      &ring->ring_mem_mc_addr,
+			      (void **)&ring->ring_mem);
+
+	return ret;
+}
+
+static uint32_t psp_v11_0_8_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (amdgpu_sriov_vf(adev))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+
+	return data;
+}
+
+static void psp_v11_0_8_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (amdgpu_sriov_vf(adev)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+			     GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
+static const struct psp_funcs psp_v11_0_8_funcs = {
+	.ring_init = psp_v11_0_8_ring_init,
+	.ring_create = psp_v11_0_8_ring_create,
+	.ring_stop = psp_v11_0_8_ring_stop,
+	.ring_destroy = psp_v11_0_8_ring_destroy,
+	.ring_get_wptr = psp_v11_0_8_ring_get_wptr,
+	.ring_set_wptr = psp_v11_0_8_ring_set_wptr,
+};
+
+void psp_v11_0_8_set_psp_funcs(struct psp_context *psp)
+{
+	psp->funcs = &psp_v11_0_8_funcs;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.h b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.h
index ed422012c8c6..890377a5afe0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2014 Advanced Micro Devices, Inc.
+ * Copyright 2021 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -20,11 +20,11 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
+#ifndef __PSP_V11_0_8_H__
+#define __PSP_V11_0_8_H__
 
-#ifndef __DCE_VIRTUAL_H__
-#define __DCE_VIRTUAL_H__
+#include "amdgpu_psp.h"
 
-extern const struct amdgpu_ip_block_version dce_virtual_ip_block;
+void psp_v11_0_8_set_psp_funcs(struct psp_context *psp);
 
 #endif
-
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 536d41f327c1..cc649406234b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -84,23 +84,23 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 
 		ta_hdr = (const struct ta_firmware_header_v1_0 *)
 				 adev->psp.ta_fw->data;
-		adev->psp.ta_hdcp_ucode_version =
-			le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
-		adev->psp.ta_hdcp_ucode_size =
-			le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
-		adev->psp.ta_hdcp_start_addr =
+		adev->psp.hdcp.feature_version =
+			le32_to_cpu(ta_hdr->hdcp.fw_version);
+		adev->psp.hdcp.size_bytes =
+			le32_to_cpu(ta_hdr->hdcp.size_bytes);
+		adev->psp.hdcp.start_addr =
 			(uint8_t *)ta_hdr +
 			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
 
 		adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
 
-		adev->psp.ta_dtm_ucode_version =
-			le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
-		adev->psp.ta_dtm_ucode_size =
-			le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
-		adev->psp.ta_dtm_start_addr =
-			(uint8_t *)adev->psp.ta_hdcp_start_addr +
-			le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+		adev->psp.dtm.feature_version =
+			le32_to_cpu(ta_hdr->dtm.fw_version);
+		adev->psp.dtm.size_bytes =
+			le32_to_cpu(ta_hdr->dtm.size_bytes);
+		adev->psp.dtm.start_addr =
+			(uint8_t *)adev->psp.hdcp.start_addr +
+			le32_to_cpu(ta_hdr->dtm.offset_bytes);
 	}
 
 	return 0;
@@ -138,7 +138,7 @@ static int psp_v12_0_bootloader_load_sysdrv(struct psp_context *psp)
 		return ret;
 
 	/* Copy PSP System Driver binary to memory */
-	psp_copy_fw(psp, psp->sys_start_addr, psp->sys_bin_size);
+	psp_copy_fw(psp, psp->sys.start_addr, psp->sys.size_bytes);
 
 	/* Provide the sys driver to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -177,7 +177,7 @@ static int psp_v12_0_bootloader_load_sos(struct psp_context *psp)
 		return ret;
 
 	/* Copy Secure OS binary to PSP memory */
-	psp_copy_fw(psp, psp->sos_start_addr, psp->sos_bin_size);
+	psp_copy_fw(psp, psp->sos.start_addr, psp->sos.size_bytes);
 
 	/* Provide the PSP secure OS to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index c8949add88f3..47a500f64db2 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -35,6 +35,12 @@ MODULE_FIRMWARE("amdgpu/yellow_carp_asd.bin");
 MODULE_FIRMWARE("amdgpu/yellow_carp_toc.bin");
 MODULE_FIRMWARE("amdgpu/yellow_carp_ta.bin");
 
+/* For large FW files the time to complete can be very long */
+#define USBC_PD_POLLING_LIMIT_S 240
+
+/* Read USB-PD from LFB */
+#define GFX_CMD_USB_PD_USE_LFB 0x480
+
 static int psp_v13_0_init_microcode(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -111,7 +117,9 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 	return ret;
 }
 
-static int psp_v13_0_bootloader_load_kdb(struct psp_context *psp)
+static int psp_v13_0_bootloader_load_component(struct psp_context  	*psp,
+					       struct psp_bin_desc 	*bin_desc,
+					       enum psp_bootloader_cmd  bl_cmd)
 {
 	int ret;
 	uint32_t psp_gfxdrv_command_reg = 0;
@@ -130,12 +138,12 @@ static int psp_v13_0_bootloader_load_kdb(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 
 	/* Copy PSP KDB binary to memory */
-	memcpy(psp->fw_pri_buf, psp->kdb_start_addr, psp->kdb_bin_size);
+	memcpy(psp->fw_pri_buf, bin_desc->start_addr, bin_desc->size_bytes);
 
 	/* Provide the PSP KDB to bootloader */
 	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36,
 	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
-	psp_gfxdrv_command_reg = PSP_BL__LOAD_KEY_DATABASE;
+	psp_gfxdrv_command_reg = bl_cmd;
 	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35,
 	       psp_gfxdrv_command_reg);
 
@@ -144,40 +152,29 @@ static int psp_v13_0_bootloader_load_kdb(struct psp_context *psp)
 	return ret;
 }
 
-static int psp_v13_0_bootloader_load_sysdrv(struct psp_context *psp)
+static int psp_v13_0_bootloader_load_kdb(struct psp_context *psp)
 {
-	int ret;
-	uint32_t psp_gfxdrv_command_reg = 0;
-	struct amdgpu_device *adev = psp->adev;
-
-	/* Check sOS sign of life register to confirm sys driver and sOS
-	 * are already been loaded.
-	 */
-	if (psp_v13_0_is_sos_alive(psp))
-		return 0;
-
-	ret = psp_v13_0_wait_for_bootloader(psp);
-	if (ret)
-		return ret;
-
-	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
-
-	/* Copy PSP System Driver binary to memory */
-	memcpy(psp->fw_pri_buf, psp->sys_start_addr, psp->sys_bin_size);
+	return psp_v13_0_bootloader_load_component(psp, &psp->kdb, PSP_BL__LOAD_KEY_DATABASE);
+}
 
-	/* Provide the sys driver to bootloader */
-	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36,
-	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
-	psp_gfxdrv_command_reg = PSP_BL__LOAD_SYSDRV;
-	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35,
-	       psp_gfxdrv_command_reg);
+static int psp_v13_0_bootloader_load_sysdrv(struct psp_context *psp)
+{
+	return psp_v13_0_bootloader_load_component(psp, &psp->sys, PSP_BL__LOAD_SYSDRV);
+}
 
-	/* there might be handshake issue with hardware which needs delay */
-	mdelay(20);
+static int psp_v13_0_bootloader_load_soc_drv(struct psp_context *psp)
+{
+	return psp_v13_0_bootloader_load_component(psp, &psp->soc_drv, PSP_BL__LOAD_SOCDRV);
+}
 
-	ret = psp_v13_0_wait_for_bootloader(psp);
+static int psp_v13_0_bootloader_load_intf_drv(struct psp_context *psp)
+{
+	return psp_v13_0_bootloader_load_component(psp, &psp->intf_drv, PSP_BL__LOAD_INTFDRV);
+}
 
-	return ret;
+static int psp_v13_0_bootloader_load_dbg_drv(struct psp_context *psp)
+{
+	return psp_v13_0_bootloader_load_component(psp, &psp->dbg_drv, PSP_BL__LOAD_DBGDRV);
 }
 
 static int psp_v13_0_bootloader_load_sos(struct psp_context *psp)
@@ -199,7 +196,7 @@ static int psp_v13_0_bootloader_load_sos(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 
 	/* Copy Secure OS binary to PSP memory */
-	memcpy(psp->fw_pri_buf, psp->sos_start_addr, psp->sos_bin_size);
+	memcpy(psp->fw_pri_buf, psp->sos.start_addr, psp->sos.size_bytes);
 
 	/* Provide the PSP secure OS to bootloader */
 	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36,
@@ -382,10 +379,71 @@ static void psp_v13_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
 		WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_67, value);
 }
 
+static int psp_v13_0_load_usbc_pd_fw(struct psp_context *psp, uint64_t fw_pri_mc_addr)
+{
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t reg_status;
+	int ret, i = 0;
+
+	/*
+	 * LFB address which is aligned to 1MB address and has to be
+	 * right-shifted by 20 so that LFB address can be passed on a 32-bit C2P
+	 * register
+	 */
+	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36, (fw_pri_mc_addr >> 20));
+
+	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
+			     0x80000000, 0x80000000, false);
+	if (ret)
+		return ret;
+
+	/* Fireup interrupt so PSP can pick up the address */
+	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35, (GFX_CMD_USB_PD_USE_LFB << 16));
+
+	/* FW load takes very long time */
+	do {
+		msleep(1000);
+		reg_status = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35);
+
+		if (reg_status & 0x80000000)
+			goto done;
+
+	} while (++i < USBC_PD_POLLING_LIMIT_S);
+
+	return -ETIME;
+done:
+
+	if ((reg_status & 0xFFFF) != 0) {
+		DRM_ERROR("Address load failed - MP0_SMN_C2PMSG_35.Bits [15:0] = %04x\n",
+				reg_status & 0xFFFF);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int psp_v13_0_read_usbc_pd_fw(struct psp_context *psp, uint32_t *fw_ver)
+{
+	struct amdgpu_device *adev = psp->adev;
+	int ret;
+
+	WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35, C2PMSG_CMD_GFX_USB_PD_FW_VER);
+
+	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
+				     0x80000000, 0x80000000, false);
+	if (!ret)
+		*fw_ver = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36);
+
+	return ret;
+}
+
 static const struct psp_funcs psp_v13_0_funcs = {
 	.init_microcode = psp_v13_0_init_microcode,
 	.bootloader_load_kdb = psp_v13_0_bootloader_load_kdb,
 	.bootloader_load_sysdrv = psp_v13_0_bootloader_load_sysdrv,
+	.bootloader_load_soc_drv = psp_v13_0_bootloader_load_soc_drv,
+	.bootloader_load_intf_drv = psp_v13_0_bootloader_load_intf_drv,
+	.bootloader_load_dbg_drv = psp_v13_0_bootloader_load_dbg_drv,
 	.bootloader_load_sos = psp_v13_0_bootloader_load_sos,
 	.ring_init = psp_v13_0_ring_init,
 	.ring_create = psp_v13_0_ring_create,
@@ -393,6 +451,8 @@ static const struct psp_funcs psp_v13_0_funcs = {
 	.ring_destroy = psp_v13_0_ring_destroy,
 	.ring_get_wptr = psp_v13_0_ring_get_wptr,
 	.ring_set_wptr = psp_v13_0_ring_set_wptr,
+	.load_usbc_pd_fw = psp_v13_0_load_usbc_pd_fw,
+	.read_usbc_pd_fw = psp_v13_0_read_usbc_pd_fw
 };
 
 void psp_v13_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index b86dcbabb635..1ed357cb0f49 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -103,7 +103,7 @@ static int psp_v3_1_bootloader_load_sysdrv(struct psp_context *psp)
 		return ret;
 
 	/* Copy PSP System Driver binary to memory */
-	psp_copy_fw(psp, psp->sys_start_addr, psp->sys_bin_size);
+	psp_copy_fw(psp, psp->sys.start_addr, psp->sys.size_bytes);
 
 	/* Provide the sys driver to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
@@ -142,7 +142,7 @@ static int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
 		return ret;
 
 	/* Copy Secure OS binary to PSP memory */
-	psp_copy_fw(psp, psp->sos_start_addr, psp->sos_bin_size);
+	psp_copy_fw(psp, psp->sos.start_addr, psp->sos.size_bytes);
 
 	/* Provide the PSP secure OS to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 6117ba8a4c3f..50bf3b71bc93 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/navi14_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/navi12_sdma.bin");
 MODULE_FIRMWARE("amdgpu/navi12_sdma1.bin");
 
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_sdma.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_sdma1.bin");
+
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_sdma.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish2_sdma1.bin");
+
 #define SDMA1_REG_OFFSET 0x600
 #define SDMA0_HYP_DEC_REG_START 0x5880
 #define SDMA0_HYP_DEC_REG_END 0x5893
@@ -130,6 +136,37 @@ static const struct soc15_reg_golden golden_settings_sdma_nv12[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 };
 
+static const struct soc15_reg_golden golden_settings_sdma_cyan_skillfish[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_CHICKEN_BITS, 0xffbf1f0f, 0x03ab0107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_PAGE_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC2_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC4_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC5_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC6_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC7_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_UTCL1_PAGE, 0x007fffff, 0x004c5c00),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_CHICKEN_BITS, 0xffbf1f0f, 0x03ab0107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_PAGE_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC2_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC4_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC5_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC6_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC7_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_UTCL1_PAGE, 0x007fffff, 0x004c5c00)
+};
+
 static u32 sdma_v5_0_get_reg_offset(struct amdgpu_device *adev, u32 instance, u32 internal_offset)
 {
 	u32 base;
@@ -180,6 +217,11 @@ static void sdma_v5_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_sdma_nv12,
 						(const u32)ARRAY_SIZE(golden_settings_sdma_nv12));
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		soc15_program_register_sequence(adev,
+						golden_settings_sdma_cyan_skillfish,
+						(const u32)ARRAY_SIZE(golden_settings_sdma_cyan_skillfish));
+		break;
 	default:
 		break;
 	}
@@ -200,7 +242,7 @@ static void sdma_v5_0_init_golden_registers(struct amdgpu_device *adev)
 static int sdma_v5_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
-	char fw_name[30];
+	char fw_name[40];
 	int err = 0, i;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
@@ -221,6 +263,12 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_NAVI12:
 		chip_name = "navi12";
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2)
+			chip_name = "cyan_skillfish2";
+		else
+			chip_name = "cyan_skillfish";
+		break;
 	default:
 		BUG();
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 7486e5306786..779f5c911e11 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -87,21 +87,6 @@ static u32 sdma_v5_2_get_reg_offset(struct amdgpu_device *adev, u32 instance, u3
 	return base + internal_offset;
 }
 
-static void sdma_v5_2_init_golden_registers(struct amdgpu_device *adev)
-{
-	switch (adev->asic_type) {
-	case CHIP_SIENNA_CICHLID:
-	case CHIP_NAVY_FLOUNDER:
-	case CHIP_VANGOGH:
-	case CHIP_DIMGREY_CAVEFISH:
-	case CHIP_BEIGE_GOBY:
-	case CHIP_YELLOW_CARP:
-		break;
-	default:
-		break;
-	}
-}
-
 static int sdma_v5_2_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst)
 {
 	int err = 0;
@@ -1345,8 +1330,6 @@ static int sdma_v5_2_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	sdma_v5_2_init_golden_registers(adev);
-
 	r = sdma_v5_2_start(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 7cbc2bb03bc6..e6d2f74a7976 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -44,7 +44,7 @@
 #include "dce_v6_0.h"
 #include "si.h"
 #include "uvd_v3_1.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "gca/gfx_6_0_d.h"
 #include "oss/oss_1_0_d.h"
 #include "oss/oss_1_0_sh_mask.h"
@@ -2759,7 +2759,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2777,7 +2777,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2795,7 +2795,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index 5c7d769aee3f..73ffa8fde3df 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -41,9 +41,7 @@
 #define I2C_SW_TIMEOUT        8
 #define I2C_ABORT             0x10
 
-/* I2C transaction flags */
-#define I2C_NO_STOP	1
-#define I2C_RESTART	2
+#define I2C_X_RESTART         BIT(31)
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
@@ -56,12 +54,48 @@ static void smu_v11_0_i2c_set_clock_gating(struct i2c_adapter *control, bool en)
 	WREG32_SOC15(SMUIO, 0, mmSMUIO_PWRMGT, reg);
 }
 
+/* The T_I2C_POLL_US is defined as follows:
+ *
+ * "Define a timer interval (t_i2c_poll) equal to 10 times the
+ *  signalling period for the highest I2C transfer speed used in the
+ *  system and supported by DW_apb_i2c. For instance, if the highest
+ *  I2C data transfer mode is 400 kb/s, then t_i2c_poll is 25 us."  --
+ * DesignWare DW_apb_i2c Databook, Version 1.21a, section 3.8.3.1,
+ * page 56, with grammar and syntax corrections.
+ *
+ * Vcc for our device is at 1.8V which puts it at 400 kHz,
+ * see Atmel AT24CM02 datasheet, section 8.3 DC Characteristics table, page 14.
+ *
+ * The procedure to disable the IP block is described in section
+ * 3.8.3 Disabling DW_apb_i2c on page 56.
+ */
+#define I2C_SPEED_MODE_FAST     2
+#define T_I2C_POLL_US           25
+#define I2C_MAX_T_POLL_COUNT    1000
 
-static void smu_v11_0_i2c_enable(struct i2c_adapter *control, bool enable)
+static int smu_v11_0_i2c_enable(struct i2c_adapter *control, bool enable)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
 	WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE, enable ? 1 : 0);
+
+	if (!enable) {
+		int ii;
+
+		for (ii = I2C_MAX_T_POLL_COUNT; ii > 0; ii--) {
+			u32 en_stat = RREG32_SOC15(SMUIO,
+						   0,
+						   mmCKSVII2C_IC_ENABLE_STATUS);
+			if (REG_GET_FIELD(en_stat, CKSVII2C_IC_ENABLE_STATUS, IC_EN))
+				udelay(T_I2C_POLL_US);
+			else
+				return I2C_OK;
+		}
+
+		return I2C_ABORT;
+	}
+
+	return I2C_OK;
 }
 
 static void smu_v11_0_i2c_clear_status(struct i2c_adapter *control)
@@ -83,8 +117,13 @@ static void smu_v11_0_i2c_configure(struct i2c_adapter *control)
 	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_RESTART_EN, 1);
 	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_10BITADDR_MASTER, 0);
 	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_10BITADDR_SLAVE, 0);
-	/* Standard mode */
-	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_MAX_SPEED_MODE, 2);
+	/* The values of IC_MAX_SPEED_MODE are,
+	 * 1: standard mode, 0 - 100 Kb/s,
+	 * 2: fast mode, <= 400 Kb/s, or fast mode plus, <= 1000 Kb/s,
+	 * 3: high speed mode, <= 3.4 Mb/s.
+	 */
+	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_MAX_SPEED_MODE,
+			    I2C_SPEED_MODE_FAST);
 	reg = REG_SET_FIELD(reg, CKSVII2C_IC_CON, IC_MASTER_MODE, 1);
 
 	WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_CON, reg);
@@ -113,13 +152,15 @@ static void smu_v11_0_i2c_set_clock(struct i2c_adapter *control)
 	WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_SDA_HOLD, 20);
 }
 
-static void smu_v11_0_i2c_set_address(struct i2c_adapter *control, uint8_t address)
+static void smu_v11_0_i2c_set_address(struct i2c_adapter *control, u16 address)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
-	/* Convert fromr 8-bit to 7-bit address */
-	address >>= 1;
-	WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_TAR, (address & 0xFF));
+	/* The IC_TAR::IC_TAR field is 10-bits wide.
+	 * It takes a 7-bit or 10-bit addresses as an address,
+	 * i.e. no read/write bit--no wire format, just the address.
+	 */
+	WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_TAR, address & 0x3FF);
 }
 
 static uint32_t smu_v11_0_i2c_poll_tx_status(struct i2c_adapter *control)
@@ -206,9 +247,6 @@ static uint32_t smu_v11_0_i2c_poll_rx_status(struct i2c_adapter *control)
 	return ret;
 }
 
-
-
-
 /**
  * smu_v11_0_i2c_transmit - Send a block of data over the I2C bus to a slave device.
  *
@@ -221,17 +259,17 @@ static uint32_t smu_v11_0_i2c_poll_rx_status(struct i2c_adapter *control)
  * Returns 0 on success or error.
  */
 static uint32_t smu_v11_0_i2c_transmit(struct i2c_adapter *control,
-				  uint8_t address, uint8_t *data,
-				  uint32_t numbytes, uint32_t i2c_flag)
+				       u16 address, u8 *data,
+				       u32 numbytes, u32 i2c_flag)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
-	uint32_t bytes_sent, reg, ret = 0;
+	u32 bytes_sent, reg, ret = I2C_OK;
 	unsigned long  timeout_counter;
 
 	bytes_sent = 0;
 
 	DRM_DEBUG_DRIVER("I2C_Transmit(), address = %x, bytes = %d , data: ",
-		 (uint16_t)address, numbytes);
+			 address, numbytes);
 
 	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		print_hex_dump(KERN_INFO, "data: ", DUMP_PREFIX_NONE,
@@ -246,53 +284,49 @@ static uint32_t smu_v11_0_i2c_transmit(struct i2c_adapter *control,
 	/* Clear status bits */
 	smu_v11_0_i2c_clear_status(control);
 
-
 	timeout_counter = jiffies + msecs_to_jiffies(20);
 
 	while (numbytes > 0) {
 		reg = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_STATUS);
-		if (REG_GET_FIELD(reg, CKSVII2C_IC_STATUS, TFNF)) {
-			do {
-				reg = 0;
-				/*
-				 * Prepare transaction, no need to set RESTART. I2C engine will send
-				 * START as soon as it sees data in TXFIFO
-				 */
-				if (bytes_sent == 0)
-					reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, RESTART,
-							    (i2c_flag & I2C_RESTART) ? 1 : 0);
-				reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, DAT, data[bytes_sent]);
-
-				/* determine if we need to send STOP bit or not */
-				if (numbytes == 1)
-					/* Final transaction, so send stop unless I2C_NO_STOP */
-					reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, STOP,
-							    (i2c_flag & I2C_NO_STOP) ? 0 : 1);
-				/* Write */
-				reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, CMD, 0);
-				WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_DATA_CMD, reg);
-
-				/* Record that the bytes were transmitted */
-				bytes_sent++;
-				numbytes--;
-
-				reg = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_STATUS);
-
-			} while (numbytes &&  REG_GET_FIELD(reg, CKSVII2C_IC_STATUS, TFNF));
-		}
-
-		/*
-		 * We waited too long for the transmission FIFO to become not-full.
-		 * Exit the loop with error.
-		 */
-		if (time_after(jiffies, timeout_counter)) {
-			ret |= I2C_SW_TIMEOUT;
-			goto Err;
+		if (!REG_GET_FIELD(reg, CKSVII2C_IC_STATUS, TFNF)) {
+			/*
+			 * We waited for too long for the transmission
+			 * FIFO to become not-full.  Exit the loop
+			 * with error.
+			 */
+			if (time_after(jiffies, timeout_counter)) {
+				ret |= I2C_SW_TIMEOUT;
+				goto Err;
+			}
+		} else {
+			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, DAT,
+					    data[bytes_sent]);
+
+			/* Final message, final byte, must generate a
+			 * STOP to release the bus, i.e. don't hold
+			 * SCL low.
+			 */
+			if (numbytes == 1 && i2c_flag & I2C_M_STOP)
+				reg = REG_SET_FIELD(reg,
+						    CKSVII2C_IC_DATA_CMD,
+						    STOP, 1);
+
+			if (bytes_sent == 0 && i2c_flag & I2C_X_RESTART)
+				reg = REG_SET_FIELD(reg,
+						    CKSVII2C_IC_DATA_CMD,
+						    RESTART, 1);
+
+			/* Write */
+			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, CMD, 0);
+			WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_DATA_CMD, reg);
+
+			/* Record that the bytes were transmitted */
+			bytes_sent++;
+			numbytes--;
 		}
 	}
 
 	ret = smu_v11_0_i2c_poll_tx_status(control);
-
 Err:
 	/* Any error, no point in proceeding */
 	if (ret != I2C_OK) {
@@ -323,8 +357,8 @@ Err:
  * Returns 0 on success or error.
  */
 static uint32_t smu_v11_0_i2c_receive(struct i2c_adapter *control,
-				 uint8_t address, uint8_t *data,
-				 uint32_t numbytes, uint8_t i2c_flag)
+				      u16 address, u8 *data,
+				      u32 numbytes, u32 i2c_flag)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	uint32_t bytes_received, ret = I2C_OK;
@@ -342,23 +376,21 @@ static uint32_t smu_v11_0_i2c_receive(struct i2c_adapter *control,
 
 		smu_v11_0_i2c_clear_status(control);
 
-
 		/* Prepare transaction */
-
-		/* Each time we disable I2C, so this is not a restart */
-		if (bytes_received == 0)
-			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, RESTART,
-					    (i2c_flag & I2C_RESTART) ? 1 : 0);
-
 		reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, DAT, 0);
 		/* Read */
 		reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, CMD, 1);
 
-		/* Transmitting last byte */
-		if (numbytes == 1)
-			/* Final transaction, so send stop if requested */
-			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD, STOP,
-					    (i2c_flag & I2C_NO_STOP) ? 0 : 1);
+		/* Final message, final byte, must generate a STOP
+		 * to release the bus, i.e. don't hold SCL low.
+		 */
+		if (numbytes == 1 && i2c_flag & I2C_M_STOP)
+			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD,
+					    STOP, 1);
+
+		if (bytes_received == 0 && i2c_flag & I2C_X_RESTART)
+			reg = REG_SET_FIELD(reg, CKSVII2C_IC_DATA_CMD,
+					    RESTART, 1);
 
 		WREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_DATA_CMD, reg);
 
@@ -413,7 +445,6 @@ static void smu_v11_0_i2c_abort(struct i2c_adapter *control)
 	DRM_DEBUG_DRIVER("I2C_Abort() Done.");
 }
 
-
 static bool smu_v11_0_i2c_activity_done(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
@@ -425,7 +456,6 @@ static bool smu_v11_0_i2c_activity_done(struct i2c_adapter *control)
 	reg_ic_enable_status = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE_STATUS);
 	reg_ic_enable = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE);
 
-
 	if ((REG_GET_FIELD(reg_ic_enable, CKSVII2C_IC_ENABLE, ENABLE) == 0) &&
 	    (REG_GET_FIELD(reg_ic_enable_status, CKSVII2C_IC_ENABLE_STATUS, IC_EN) == 1)) {
 		/*
@@ -455,6 +485,8 @@ static bool smu_v11_0_i2c_activity_done(struct i2c_adapter *control)
 
 static void smu_v11_0_i2c_init(struct i2c_adapter *control)
 {
+	int res;
+
 	/* Disable clock gating */
 	smu_v11_0_i2c_set_clock_gating(control, false);
 
@@ -462,7 +494,9 @@ static void smu_v11_0_i2c_init(struct i2c_adapter *control)
 		DRM_WARN("I2C busy !");
 
 	/* Disable I2C */
-	smu_v11_0_i2c_enable(control, false);
+	res = smu_v11_0_i2c_enable(control, false);
+	if (res != I2C_OK)
+		smu_v11_0_i2c_abort(control);
 
 	/* Configure I2C to operate as master and in standard mode */
 	smu_v11_0_i2c_configure(control);
@@ -475,21 +509,22 @@ static void smu_v11_0_i2c_init(struct i2c_adapter *control)
 static void smu_v11_0_i2c_fini(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
-	uint32_t reg_ic_enable_status, reg_ic_enable;
+	u32 status, enable, en_stat;
+	int res;
 
-	smu_v11_0_i2c_enable(control, false);
+	res = smu_v11_0_i2c_enable(control, false);
+	if (res != I2C_OK) {
+		status  = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_STATUS);
+		enable  = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE);
+		en_stat = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE_STATUS);
 
-	/* Double check if disabled, else force abort */
-	reg_ic_enable_status = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE_STATUS);
-	reg_ic_enable = RREG32_SOC15(SMUIO, 0, mmCKSVII2C_IC_ENABLE);
-
-	if ((REG_GET_FIELD(reg_ic_enable, CKSVII2C_IC_ENABLE, ENABLE) == 0) &&
-	    (REG_GET_FIELD(reg_ic_enable_status,
-			   CKSVII2C_IC_ENABLE_STATUS, IC_EN) == 1)) {
-		/*
-		 * Nobody is using I2C engine, but engine remains active because
-		 * someone missed to send STOP
+		/* Nobody is using the I2C engine, yet it remains
+		 * active, possibly because someone missed to send
+		 * STOP.
 		 */
+		DRM_DEBUG_DRIVER("Aborting from fini: status:0x%08x "
+				 "enable:0x%08x enable_stat:0x%08x",
+				 status, enable, en_stat);
 		smu_v11_0_i2c_abort(control);
 	}
 
@@ -531,22 +566,12 @@ static bool smu_v11_0_i2c_bus_unlock(struct i2c_adapter *control)
 /***************************** I2C GLUE ****************************/
 
 static uint32_t smu_v11_0_i2c_read_data(struct i2c_adapter *control,
-					uint8_t address,
-					uint8_t *data,
-					uint32_t numbytes)
+					struct i2c_msg *msg, uint32_t i2c_flag)
 {
-	uint32_t  ret = 0;
-
-	/* First 2 bytes are dummy write to set EEPROM address */
-	ret = smu_v11_0_i2c_transmit(control, address, data, 2, I2C_NO_STOP);
-	if (ret != I2C_OK)
-		goto Fail;
+	uint32_t  ret;
 
-	/* Now read data starting with that address */
-	ret = smu_v11_0_i2c_receive(control, address, data + 2, numbytes - 2,
-				    I2C_RESTART);
+	ret = smu_v11_0_i2c_receive(control, msg->addr, msg->buf, msg->len, i2c_flag);
 
-Fail:
 	if (ret != I2C_OK)
 		DRM_ERROR("ReadData() - I2C error occurred :%x", ret);
 
@@ -554,28 +579,15 @@ Fail:
 }
 
 static uint32_t smu_v11_0_i2c_write_data(struct i2c_adapter *control,
-					 uint8_t address,
-					 uint8_t *data,
-					 uint32_t numbytes)
+					struct i2c_msg *msg, uint32_t i2c_flag)
 {
 	uint32_t  ret;
 
-	ret = smu_v11_0_i2c_transmit(control, address, data, numbytes, 0);
+	ret = smu_v11_0_i2c_transmit(control, msg->addr, msg->buf, msg->len, i2c_flag);
 
 	if (ret != I2C_OK)
 		DRM_ERROR("WriteI2CData() - I2C error occurred :%x", ret);
-	else
-		/*
-		 * According to EEPROM spec there is a MAX of 10 ms required for
-		 * EEPROM to flush internal RX buffer after STOP was issued at the
-		 * end of write transaction. During this time the EEPROM will not be
-		 * responsive to any more commands - so wait a bit more.
-		 *
-		 * TODO Improve to wait for first ACK for slave address after
-		 * internal write cycle done.
-		 */
-		msleep(10);
-
+	
 	return ret;
 
 }
@@ -584,12 +596,11 @@ static void lock_bus(struct i2c_adapter *i2c, unsigned int flags)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(i2c);
 
-	if (!smu_v11_0_i2c_bus_lock(i2c)) {
+	mutex_lock(&adev->pm.smu_i2c_mutex);
+	if (!smu_v11_0_i2c_bus_lock(i2c))
 		DRM_ERROR("Failed to lock the bus from SMU");
-		return;
-	}
-
-	adev->pm.bus_locked = true;
+	else
+		adev->pm.bus_locked = true;
 }
 
 static int trylock_bus(struct i2c_adapter *i2c, unsigned int flags)
@@ -602,12 +613,11 @@ static void unlock_bus(struct i2c_adapter *i2c, unsigned int flags)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(i2c);
 
-	if (!smu_v11_0_i2c_bus_unlock(i2c)) {
+	if (!smu_v11_0_i2c_bus_unlock(i2c))
 		DRM_ERROR("Failed to unlock the bus from SMU");
-		return;
-	}
-
-	adev->pm.bus_locked = false;
+	else
+		adev->pm.bus_locked = false;
+	mutex_unlock(&adev->pm.smu_i2c_mutex);
 }
 
 static const struct i2c_lock_operations smu_v11_0_i2c_i2c_lock_ops = {
@@ -617,27 +627,60 @@ static const struct i2c_lock_operations smu_v11_0_i2c_i2c_lock_ops = {
 };
 
 static int smu_v11_0_i2c_xfer(struct i2c_adapter *i2c_adap,
-			      struct i2c_msg *msgs, int num)
+			      struct i2c_msg *msg, int num)
 {
 	int i, ret;
-	struct amdgpu_device *adev = to_amdgpu_device(i2c_adap);
-
-	if (!adev->pm.bus_locked) {
-		DRM_ERROR("I2C bus unlocked, stopping transaction!");
-		return -EIO;
-	}
+	u16 addr, dir;
 
 	smu_v11_0_i2c_init(i2c_adap);
 
+	/* From the client's point of view, this sequence of
+	 * messages-- the array i2c_msg *msg, is a single transaction
+	 * on the bus, starting with START and ending with STOP.
+	 *
+	 * The client is welcome to send any sequence of messages in
+	 * this array, as processing under this function here is
+	 * striving to be agnostic.
+	 *
+	 * Record the first address and direction we see. If either
+	 * changes for a subsequent message, generate ReSTART. The
+	 * DW_apb_i2c databook, v1.21a, specifies that ReSTART is
+	 * generated when the direction changes, with the default IP
+	 * block parameter settings, but it doesn't specify if ReSTART
+	 * is generated when the address changes (possibly...). We
+	 * don't rely on the default IP block parameter settings as
+	 * the block is shared and they may change.
+	 */
+	if (num > 0) {
+		addr = msg[0].addr;
+		dir  = msg[0].flags & I2C_M_RD;
+	}
+
 	for (i = 0; i < num; i++) {
-		if (msgs[i].flags & I2C_M_RD)
+		u32 i2c_flag = 0;
+
+		if (msg[i].addr != addr || (msg[i].flags ^ dir) & I2C_M_RD) {
+			addr = msg[i].addr;
+			dir  = msg[i].flags & I2C_M_RD;
+			i2c_flag |= I2C_X_RESTART;
+		}
+
+		if (i == num - 1) {
+			/* Set the STOP bit on the last message, so
+			 * that the IP block generates a STOP after
+			 * the last byte of the message.
+			 */
+			i2c_flag |= I2C_M_STOP;
+		}
+
+		if (msg[i].flags & I2C_M_RD)
 			ret = smu_v11_0_i2c_read_data(i2c_adap,
-						      (uint8_t)msgs[i].addr,
-						      msgs[i].buf, msgs[i].len);
+						      msg + i,
+						      i2c_flag);
 		else
 			ret = smu_v11_0_i2c_write_data(i2c_adap,
-						       (uint8_t)msgs[i].addr,
-						       msgs[i].buf, msgs[i].len);
+						       msg + i,
+						       i2c_flag);
 
 		if (ret != I2C_OK) {
 			num = -EIO;
@@ -654,23 +697,28 @@ static u32 smu_v11_0_i2c_func(struct i2c_adapter *adap)
 	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
 }
 
-
 static const struct i2c_algorithm smu_v11_0_i2c_algo = {
 	.master_xfer = smu_v11_0_i2c_xfer,
 	.functionality = smu_v11_0_i2c_func,
 };
 
+static const struct i2c_adapter_quirks smu_v11_0_i2c_control_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN,
+};
+
 int smu_v11_0_i2c_control_init(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
+	mutex_init(&adev->pm.smu_i2c_mutex);
 	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
+	control->class = I2C_CLASS_HWMON;
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &smu_v11_0_i2c_algo;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
 	control->lock_ops = &smu_v11_0_i2c_i2c_lock_ops;
+	control->quirks = &smu_v11_0_i2c_control_quirks;
 
 	res = i2c_add_adapter(control);
 	if (res)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index b7d350be8050..0fc97c364fd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -74,7 +74,7 @@
 #include "smuio_v9_0.h"
 #include "smuio_v11_0.h"
 #include "smuio_v13_0.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mxgpu_ai.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_xgmi.h"
@@ -575,7 +575,7 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		baco_reset = amdgpu_dpm_is_baco_supported(adev);
 		break;
 	case CHIP_VEGA20:
-		if (adev->psp.sos_fw_version >= 0x80067)
+		if (adev->psp.sos.fw_version >= 0x80067)
 			baco_reset = amdgpu_dpm_is_baco_supported(adev);
 
 		/*
@@ -635,7 +635,7 @@ static bool soc15_supports_baco(struct amdgpu_device *adev)
 	case CHIP_ARCTURUS:
 		return amdgpu_dpm_is_baco_supported(adev);
 	case CHIP_VEGA20:
-		if (adev->psp.sos_fw_version >= 0x80067)
+		if (adev->psp.sos.fw_version >= 0x80067)
 			return amdgpu_dpm_is_baco_supported(adev);
 		return false;
 	default:
@@ -843,7 +843,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -863,7 +863,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -885,7 +885,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		}
 
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
@@ -909,7 +909,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -1353,8 +1353,6 @@ static int soc15_common_early_init(void *handle)
 		adev->asic_funcs = &vega20_asic_funcs;
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
-			AMD_CG_SUPPORT_GFX_CGCG |
-			AMD_CG_SUPPORT_GFX_CGLS |
 			AMD_CG_SUPPORT_GFX_CP_LS |
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_SDMA_MGCG |
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 0eeb5e073be8..8a9ca87d8663 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -28,13 +28,13 @@
 #define SOC15_REG_OFFSET(ip, inst, reg)	(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
 
 #define __WREG32_SOC15_RLC__(reg, value, flag, hwip) \
-	((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.funcs->rlcg_wreg) ? \
-	 adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, flag, hwip) : \
+	((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.funcs->sriov_wreg) ? \
+	 adev->gfx.rlc.funcs->sriov_wreg(adev, reg, value, flag, hwip) : \
 	 WREG32(reg, value))
 
 #define __RREG32_SOC15_RLC__(reg, flag, hwip) \
-	((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.funcs->rlcg_rreg) ? \
-	 adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, flag, hwip) : \
+	((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.funcs->sriov_rreg) ? \
+	 adev->gfx.rlc.funcs->sriov_rreg(adev, reg, flag, hwip) : \
 	 RREG32(reg))
 
 #define WREG32_FIELD15(ip, idx, reg, field, val)	\
diff --git a/drivers/gpu/drm/amd/amdgpu/ta_xgmi_if.h b/drivers/gpu/drm/amd/amdgpu/ta_xgmi_if.h
index ac2c27b7630c..da815a93d46e 100644
--- a/drivers/gpu/drm/amd/amdgpu/ta_xgmi_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/ta_xgmi_if.h
@@ -33,7 +33,8 @@ enum ta_command_xgmi {
 	TA_COMMAND_XGMI__GET_NODE_ID			= 0x01,
 	TA_COMMAND_XGMI__GET_HIVE_ID			= 0x02,
 	TA_COMMAND_XGMI__GET_GET_TOPOLOGY_INFO		= 0x03,
-	TA_COMMAND_XGMI__SET_TOPOLOGY_INFO		= 0x04
+	TA_COMMAND_XGMI__SET_TOPOLOGY_INFO		= 0x04,
+	TA_COMMAND_XGMI__GET_PEER_LINKS			= 0x0B
 };
 
 /* XGMI related enumerations */
@@ -75,6 +76,11 @@ struct ta_xgmi_node_info {
 	enum ta_xgmi_assigned_sdma_engine	sdma_engine;
 };
 
+struct ta_xgmi_peer_link_info {
+	uint64_t				node_id;
+	uint8_t					num_links;
+};
+
 struct ta_xgmi_cmd_initialize_output {
 	uint32_t	status;
 };
@@ -97,6 +103,11 @@ struct ta_xgmi_cmd_get_topology_info_output {
 	struct ta_xgmi_node_info	nodes[TA_XGMI__MAX_CONNECTED_NODES];
 };
 
+struct ta_xgmi_cmd_get_peer_link_info_output {
+	uint32_t			num_nodes;
+	struct ta_xgmi_peer_link_info	nodes[TA_XGMI__MAX_CONNECTED_NODES];
+};
+
 struct ta_xgmi_cmd_set_topology_info_input {
 	uint32_t			num_nodes;
 	struct ta_xgmi_node_info	nodes[TA_XGMI__MAX_CONNECTED_NODES];
@@ -115,6 +126,7 @@ union ta_xgmi_cmd_output {
 	struct ta_xgmi_cmd_get_node_id_output		get_node_id;
 	struct ta_xgmi_cmd_get_hive_id_output		get_hive_id;
 	struct ta_xgmi_cmd_get_topology_info_output	get_topology_info;
+	struct ta_xgmi_cmd_get_peer_link_info_output	get_link_info;
 };
 /**********************************************************/
 
@@ -122,7 +134,8 @@ struct ta_xgmi_shared_memory {
 	uint32_t			cmd_id;
 	uint32_t			resp_id;
 	enum ta_xgmi_status		xgmi_status;
-	uint32_t			reserved;
+	uint8_t				flag_extend_link_record;
+	uint8_t				reserved0[3];
 	union ta_xgmi_cmd_input		xgmi_in_message;
 	union ta_xgmi_cmd_output	xgmi_out_message;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 3a8f787374c0..bb30336b1e8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -28,6 +28,21 @@
 #include "umc/umc_6_7_0_offset.h"
 #include "umc/umc_6_7_0_sh_mask.h"
 
+const uint32_t
+	umc_v6_7_channel_idx_tbl_second[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM] = {
+		{28, 20, 24, 16, 12, 4, 8, 0},
+		{6, 30, 2, 26, 22, 14, 18, 10},
+		{19, 11, 15, 7, 3, 27, 31, 23},
+		{9, 1, 5, 29, 25, 17, 21, 13}
+};
+const uint32_t
+	umc_v6_7_channel_idx_tbl_first[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM] = {
+		{19, 11, 15, 7,	3, 27, 31, 23},
+		{9, 1, 5, 29, 25, 17, 21, 13},
+		{28, 20, 24, 16, 12, 4, 8, 0},
+		{6, 30, 2, 26, 22, 14, 18, 10},
+};
+
 static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev,
 					      uint32_t umc_inst,
 					      uint32_t ch_inst)
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
index 4eb85f247e96..57f2557e7aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
@@ -23,6 +23,9 @@
 #ifndef __UMC_V6_7_H__
 #define __UMC_V6_7_H__
 
+#include "soc15_common.h"
+#include "amdgpu.h"
+
 /* EccErrCnt max value */
 #define UMC_V6_7_CE_CNT_MAX		0xffff
 /* umc ce interrupt threshold */
@@ -32,6 +35,18 @@
 
 #define UMC_V6_7_INST_DIST	0x40000
 
+/* number of umc channel instance with memory map register access */
+#define UMC_V6_7_UMC_INSTANCE_NUM		4
+/* number of umc instance with memory map register access */
+#define UMC_V6_7_CHANNEL_INSTANCE_NUM		8
+/* total channel instances in one umc block */
+#define UMC_V6_7_TOTAL_CHANNEL_NUM	(UMC_V6_7_CHANNEL_INSTANCE_NUM * UMC_V6_7_UMC_INSTANCE_NUM)
+/* UMC regiser per channel offset */
+#define UMC_V6_7_PER_CHANNEL_OFFSET		0x400
 extern const struct amdgpu_umc_ras_funcs umc_v6_7_ras_funcs;
+extern const uint32_t
+	umc_v6_7_channel_idx_tbl_second[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM];
+extern const uint32_t
+	umc_v6_7_channel_idx_tbl_first[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM];
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
index 6c0e91495365..7232241e3bfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
@@ -698,6 +698,30 @@ static int uvd_v3_1_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v3_1_stop(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index a301518e4957..52d6de969f46 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -212,6 +212,30 @@ static int uvd_v4_2_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v4_2_stop(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index a4d5bd21c83c..db6d06758e4d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -210,6 +210,30 @@ static int uvd_v5_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v5_0_stop(adev);
 
@@ -224,7 +248,6 @@ static int uvd_v5_0_suspend(void *handle)
 	r = uvd_v5_0_hw_fini(adev);
 	if (r)
 		return r;
-	uvd_v5_0_set_clockgating_state(adev, AMD_CG_STATE_GATE);
 
 	return amdgpu_uvd_suspend(adev);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index cf3803f8f075..bc571833632e 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -543,6 +543,30 @@ static int uvd_v6_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v6_0_stop(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 939bcfa2a4ec..b6e82d75561f 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -606,6 +606,30 @@ static int uvd_v7_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (!amdgpu_sriov_vf(adev))
 		uvd_v7_0_stop(adev);
 	else {
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index c7d28c169be5..b70c17f0c52e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -477,6 +477,31 @@ static int vce_v2_0_hw_init(void *handle)
 
 static int vce_v2_0_hw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_vce(adev, false);
+	} else {
+		amdgpu_asic_set_vce_clocks(adev, 0, 0);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_CG_STATE_GATE);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 3b82fb289ef6..9de66893ccd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -490,6 +490,29 @@ static int vce_v3_0_hw_fini(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_vce(adev, false);
+	} else {
+		amdgpu_asic_set_vce_clocks(adev, 0, 0);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_CG_STATE_GATE);
+	}
+
 	r = vce_v3_0_wait_for_idle(handle);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 90910d19db12..fec902b800c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -542,6 +542,29 @@ static int vce_v4_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_vce(adev, false);
+	} else {
+		amdgpu_asic_set_vce_clocks(adev, 0, 0);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_CG_STATE_GATE);
+	}
+
 	if (!amdgpu_sriov_vf(adev)) {
 		/* vce_v4_0_wait_for_idle(handle); */
 		vce_v4_0_stop(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 284bb42d6c86..121ee9f2b8d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -119,7 +119,7 @@ static int vcn_v1_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 8af567c546db..f4686e918e0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -122,7 +122,7 @@ static int vcn_v2_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 888b17d84691..e0c0c3734432 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -152,7 +152,7 @@ static int vcn_v2_5_sw_init(void *handle)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 47d4f04cbd69..3d18aab88b4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -90,9 +90,7 @@ static int vcn_v3_0_early_init(void *handle)
 	int i;
 
 	if (amdgpu_sriov_vf(adev)) {
-		for (i = 0; i < VCN_INSTANCES_SIENNA_CICHLID; i++)
-			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i))
-				adev->vcn.num_vcn_inst++;
+		adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
 		adev->vcn.harvest_config = 0;
 		adev->vcn.num_enc_rings = 1;
 
@@ -153,14 +151,13 @@ static int vcn_v3_0_sw_init(void *handle)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 
-		if ((adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) ||
-		    (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)) {
+		if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) {
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1;
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw;
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
@@ -328,18 +325,28 @@ static int vcn_v3_0_hw_init(void *handle)
 				continue;
 
 			ring = &adev->vcn.inst[i].ring_dec;
-			ring->wptr = 0;
-			ring->wptr_old = 0;
-			vcn_v3_0_dec_ring_set_wptr(ring);
-			ring->sched.ready = true;
-
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
-				ring = &adev->vcn.inst[i].ring_enc[j];
+			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) {
+				ring->sched.ready = false;
+				dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
+			} else {
 				ring->wptr = 0;
 				ring->wptr_old = 0;
-				vcn_v3_0_enc_ring_set_wptr(ring);
+				vcn_v3_0_dec_ring_set_wptr(ring);
 				ring->sched.ready = true;
 			}
+
+			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+				ring = &adev->vcn.inst[i].ring_enc[j];
+				if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) {
+					ring->sched.ready = false;
+					dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
+				} else {
+					ring->wptr = 0;
+					ring->wptr_old = 0;
+					vcn_v3_0_enc_ring_set_wptr(ring);
+					ring->sched.ready = true;
+				}
+			}
 		}
 	} else {
 		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 3d21c0799037..42a35d9520f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -77,7 +77,7 @@
 #if defined(CONFIG_DRM_AMD_ACP)
 #include "amdgpu_acp.h"
 #endif
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mxgpu_vi.h"
 #include "amdgpu_dm.h"
 
@@ -904,7 +904,14 @@ static bool vi_asic_supports_baco(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 	case CHIP_TOPAZ:
-		return amdgpu_dpm_is_baco_supported(adev);
+		/* Disable BACO support for the specific polaris12 SKU temporarily */
+		if ((adev->pdev->device == 0x699F) &&
+		     (adev->pdev->revision == 0xC7) &&
+		     (adev->pdev->subsystem_vendor == 0x1028) &&
+		     (adev->pdev->subsystem_device == 0x0039))
+			return false;
+		else
+			return amdgpu_dpm_is_baco_supported(adev);
 	default:
 		return false;
 	}
@@ -2102,7 +2109,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v2_4_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		break;
 	case CHIP_FIJI:
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
@@ -2112,7 +2119,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2132,7 +2139,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2155,7 +2162,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2173,7 +2180,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2194,7 +2201,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e48acdd03c1a..86afd37b098d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1393,6 +1393,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	long err = 0;
 	int i;
 	uint32_t *devices_arr = NULL;
+	bool table_freed = false;
 
 	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
 	if (!dev)
@@ -1450,7 +1451,8 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 			goto get_mem_obj_from_handle_failed;
 		}
 		err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-			peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+			peer->kgd, (struct kgd_mem *)mem,
+			peer_pdd->drm_priv, &table_freed);
 		if (err) {
 			pr_err("Failed to map to gpu %d/%d\n",
 			       i, args->n_devices);
@@ -1468,16 +1470,17 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	}
 
 	/* Flush TLBs after waiting for the page table updates to complete */
-	for (i = 0; i < args->n_devices; i++) {
-		peer = kfd_device_by_id(devices_arr[i]);
-		if (WARN_ON_ONCE(!peer))
-			continue;
-		peer_pdd = kfd_get_process_device_data(peer, p);
-		if (WARN_ON_ONCE(!peer_pdd))
-			continue;
-		kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+	if (table_freed) {
+		for (i = 0; i < args->n_devices; i++) {
+			peer = kfd_device_by_id(devices_arr[i]);
+			if (WARN_ON_ONCE(!peer))
+				continue;
+			peer_pdd = kfd_get_process_device_data(peer, p);
+			if (WARN_ON_ONCE(!peer_pdd))
+				continue;
+			kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+		}
 	}
-
 	kfree(devices_arr);
 
 	return err;
@@ -1565,10 +1568,29 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 		}
 		args->n_success = i+1;
 	}
-	kfree(devices_arr);
-
 	mutex_unlock(&p->mutex);
 
+	if (dev->device_info->asic_family == CHIP_ALDEBARAN) {
+		err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd,
+				(struct kgd_mem *) mem, true);
+		if (err) {
+			pr_debug("Sync memory failed, wait interrupted by user signal\n");
+			goto sync_memory_failed;
+		}
+
+		/* Flush TLBs after waiting for the page table updates to complete */
+		for (i = 0; i < args->n_devices; i++) {
+			peer = kfd_device_by_id(devices_arr[i]);
+			if (WARN_ON_ONCE(!peer))
+				continue;
+			peer_pdd = kfd_get_process_device_data(peer, p);
+			if (WARN_ON_ONCE(!peer_pdd))
+				continue;
+			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
+		}
+	}
+	kfree(devices_arr);
+
 	return 0;
 
 bind_process_to_device_failed:
@@ -1576,6 +1598,7 @@ get_mem_obj_from_handle_failed:
 unmap_memory_from_gpu_failed:
 	mutex_unlock(&p->mutex);
 copy_from_user_failed:
+sync_memory_failed:
 	kfree(devices_arr);
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index c6b02aee4993..cfedfb1e8596 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1404,6 +1404,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 		break;
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
+	case CHIP_CYAN_SKILLFISH:
 		pcache_info = navi10_cache_info;
 		num_of_cache_types = ARRAY_SIZE(navi10_cache_info);
 		break;
@@ -1989,8 +1990,19 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size,
 		sub_type_hdr->flags |= CRAT_IOLINK_FLAGS_BI_DIRECTIONAL;
 		sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_XGMI;
 		sub_type_hdr->num_hops_xgmi = 1;
+		if (adev->asic_type == CHIP_ALDEBARAN) {
+			sub_type_hdr->minimum_bandwidth_mbs =
+					amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(
+							kdev->kgd, NULL, true);
+			sub_type_hdr->maximum_bandwidth_mbs =
+					sub_type_hdr->minimum_bandwidth_mbs;
+		}
 	} else {
 		sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_PCIEXPRESS;
+		sub_type_hdr->minimum_bandwidth_mbs =
+				amdgpu_amdkfd_get_pcie_bandwidth_mbytes(kdev->kgd, true);
+		sub_type_hdr->maximum_bandwidth_mbs =
+				amdgpu_amdkfd_get_pcie_bandwidth_mbytes(kdev->kgd, false);
 	}
 
 	sub_type_hdr->proximity_domain_from = proximity_domain;
@@ -2033,6 +2045,11 @@ static int kfd_fill_gpu_xgmi_link_to_gpu(int *avail_size,
 	sub_type_hdr->proximity_domain_to = proximity_domain_to;
 	sub_type_hdr->num_hops_xgmi =
 		amdgpu_amdkfd_get_xgmi_hops_count(kdev->kgd, peer_kdev->kgd);
+	sub_type_hdr->maximum_bandwidth_mbs =
+		amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->kgd, peer_kdev->kgd, false);
+	sub_type_hdr->minimum_bandwidth_mbs = sub_type_hdr->maximum_bandwidth_mbs ?
+		amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->kgd, NULL, true) : 0;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 6b57dfd2cd2a..16a57b70cc1a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -84,12 +84,14 @@ static const struct kfd2kgd_calls *kfd2kgd_funcs[] = {
 	[CHIP_DIMGREY_CAVEFISH] = &gfx_v10_3_kfd2kgd,
 	[CHIP_BEIGE_GOBY] = &gfx_v10_3_kfd2kgd,
 	[CHIP_YELLOW_CARP] = &gfx_v10_3_kfd2kgd,
+	[CHIP_CYAN_SKILLFISH] = &gfx_v10_kfd2kgd,
 };
 
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
 	.asic_family = CHIP_KAVERI,
 	.asic_name = "kaveri",
+	.gfx_target_version = 70000,
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -109,6 +111,7 @@ static const struct kfd_device_info kaveri_device_info = {
 static const struct kfd_device_info carrizo_device_info = {
 	.asic_family = CHIP_CARRIZO,
 	.asic_name = "carrizo",
+	.gfx_target_version = 80001,
 	.max_pasid_bits = 16,
 	/* max num of queues for CZ.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -129,6 +132,7 @@ static const struct kfd_device_info carrizo_device_info = {
 static const struct kfd_device_info raven_device_info = {
 	.asic_family = CHIP_RAVEN,
 	.asic_name = "raven",
+	.gfx_target_version = 90002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -147,6 +151,7 @@ static const struct kfd_device_info raven_device_info = {
 static const struct kfd_device_info hawaii_device_info = {
 	.asic_family = CHIP_HAWAII,
 	.asic_name = "hawaii",
+	.gfx_target_version = 70001,
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -166,6 +171,7 @@ static const struct kfd_device_info hawaii_device_info = {
 static const struct kfd_device_info tonga_device_info = {
 	.asic_family = CHIP_TONGA,
 	.asic_name = "tonga",
+	.gfx_target_version = 80002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -184,6 +190,7 @@ static const struct kfd_device_info tonga_device_info = {
 static const struct kfd_device_info fiji_device_info = {
 	.asic_family = CHIP_FIJI,
 	.asic_name = "fiji",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -202,6 +209,7 @@ static const struct kfd_device_info fiji_device_info = {
 static const struct kfd_device_info fiji_vf_device_info = {
 	.asic_family = CHIP_FIJI,
 	.asic_name = "fiji",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -221,6 +229,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 static const struct kfd_device_info polaris10_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.asic_name = "polaris10",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -239,6 +248,7 @@ static const struct kfd_device_info polaris10_device_info = {
 static const struct kfd_device_info polaris10_vf_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.asic_name = "polaris10",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -257,6 +267,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 static const struct kfd_device_info polaris11_device_info = {
 	.asic_family = CHIP_POLARIS11,
 	.asic_name = "polaris11",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -275,6 +286,7 @@ static const struct kfd_device_info polaris11_device_info = {
 static const struct kfd_device_info polaris12_device_info = {
 	.asic_family = CHIP_POLARIS12,
 	.asic_name = "polaris12",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -293,6 +305,7 @@ static const struct kfd_device_info polaris12_device_info = {
 static const struct kfd_device_info vegam_device_info = {
 	.asic_family = CHIP_VEGAM,
 	.asic_name = "vegam",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -311,6 +324,7 @@ static const struct kfd_device_info vegam_device_info = {
 static const struct kfd_device_info vega10_device_info = {
 	.asic_family = CHIP_VEGA10,
 	.asic_name = "vega10",
+	.gfx_target_version = 90000,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -329,6 +343,7 @@ static const struct kfd_device_info vega10_device_info = {
 static const struct kfd_device_info vega10_vf_device_info = {
 	.asic_family = CHIP_VEGA10,
 	.asic_name = "vega10",
+	.gfx_target_version = 90000,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -347,6 +362,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 static const struct kfd_device_info vega12_device_info = {
 	.asic_family = CHIP_VEGA12,
 	.asic_name = "vega12",
+	.gfx_target_version = 90004,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -365,6 +381,7 @@ static const struct kfd_device_info vega12_device_info = {
 static const struct kfd_device_info vega20_device_info = {
 	.asic_family = CHIP_VEGA20,
 	.asic_name = "vega20",
+	.gfx_target_version = 90006,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -383,6 +400,7 @@ static const struct kfd_device_info vega20_device_info = {
 static const struct kfd_device_info arcturus_device_info = {
 	.asic_family = CHIP_ARCTURUS,
 	.asic_name = "arcturus",
+	.gfx_target_version = 90008,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -401,6 +419,7 @@ static const struct kfd_device_info arcturus_device_info = {
 static const struct kfd_device_info aldebaran_device_info = {
 	.asic_family = CHIP_ALDEBARAN,
 	.asic_name = "aldebaran",
+	.gfx_target_version = 90010,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -419,6 +438,7 @@ static const struct kfd_device_info aldebaran_device_info = {
 static const struct kfd_device_info renoir_device_info = {
 	.asic_family = CHIP_RENOIR,
 	.asic_name = "renoir",
+	.gfx_target_version = 90002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -437,6 +457,7 @@ static const struct kfd_device_info renoir_device_info = {
 static const struct kfd_device_info navi10_device_info = {
 	.asic_family = CHIP_NAVI10,
 	.asic_name = "navi10",
+	.gfx_target_version = 100100,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -455,6 +476,7 @@ static const struct kfd_device_info navi10_device_info = {
 static const struct kfd_device_info navi12_device_info = {
 	.asic_family = CHIP_NAVI12,
 	.asic_name = "navi12",
+	.gfx_target_version = 100101,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -473,6 +495,7 @@ static const struct kfd_device_info navi12_device_info = {
 static const struct kfd_device_info navi14_device_info = {
 	.asic_family = CHIP_NAVI14,
 	.asic_name = "navi14",
+	.gfx_target_version = 100102,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -491,6 +514,7 @@ static const struct kfd_device_info navi14_device_info = {
 static const struct kfd_device_info sienna_cichlid_device_info = {
 	.asic_family = CHIP_SIENNA_CICHLID,
 	.asic_name = "sienna_cichlid",
+	.gfx_target_version = 100300,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -509,6 +533,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = {
 static const struct kfd_device_info navy_flounder_device_info = {
 	.asic_family = CHIP_NAVY_FLOUNDER,
 	.asic_name = "navy_flounder",
+	.gfx_target_version = 100301,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -527,6 +552,7 @@ static const struct kfd_device_info navy_flounder_device_info = {
 static const struct kfd_device_info vangogh_device_info = {
 	.asic_family = CHIP_VANGOGH,
 	.asic_name = "vangogh",
+	.gfx_target_version = 100303,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -545,6 +571,7 @@ static const struct kfd_device_info vangogh_device_info = {
 static const struct kfd_device_info dimgrey_cavefish_device_info = {
 	.asic_family = CHIP_DIMGREY_CAVEFISH,
 	.asic_name = "dimgrey_cavefish",
+	.gfx_target_version = 100302,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -563,6 +590,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = {
 static const struct kfd_device_info beige_goby_device_info = {
 	.asic_family = CHIP_BEIGE_GOBY,
 	.asic_name = "beige_goby",
+	.gfx_target_version = 100304,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -581,6 +609,7 @@ static const struct kfd_device_info beige_goby_device_info = {
 static const struct kfd_device_info yellow_carp_device_info = {
 	.asic_family = CHIP_YELLOW_CARP,
 	.asic_name = "yellow_carp",
+	.gfx_target_version = 100305,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -596,6 +625,25 @@ static const struct kfd_device_info yellow_carp_device_info = {
 	.num_sdma_queues_per_engine = 2,
 };
 
+static const struct kfd_device_info cyan_skillfish_device_info = {
+	.asic_family = CHIP_CYAN_SKILLFISH,
+	.asic_name = "cyan_skillfish",
+	.gfx_target_version = 100103,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.needs_iommu_device = false,
+	.supports_cwsr = true,
+	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
+	.num_sdma_queues_per_engine = 8,
+};
+
 /* For each entry, [0] is regular and [1] is virtualisation device. */
 static const struct kfd_device_info *kfd_supported_devices[][2] = {
 #ifdef KFD_SUPPORT_IOMMU_V2
@@ -625,6 +673,7 @@ static const struct kfd_device_info *kfd_supported_devices[][2] = {
 	[CHIP_DIMGREY_CAVEFISH] = {&dimgrey_cavefish_device_info, &dimgrey_cavefish_device_info},
 	[CHIP_BEIGE_GOBY] = {&beige_goby_device_info, &beige_goby_device_info},
 	[CHIP_YELLOW_CARP] = {&yellow_carp_device_info, NULL},
+	[CHIP_CYAN_SKILLFISH] = {&cyan_skillfish_device_info, NULL},
 };
 
 static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
@@ -1369,7 +1418,7 @@ void kfd_dec_compute_active(struct kfd_dev *kfd)
 	WARN_ONCE(count < 0, "Compute profile ref. count error");
 }
 
-void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask)
 {
 	if (kfd && kfd->init_complete)
 		kfd_smi_event_update_thermal_throttling(kfd, throttle_bitmask);
@@ -1382,18 +1431,12 @@ void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
  */
 int kfd_debugfs_hang_hws(struct kfd_dev *dev)
 {
-	int r = 0;
-
 	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
 		pr_err("HWS is not enabled");
 		return -EINVAL;
 	}
 
-	r = pm_debugfs_hang_hws(&dev->dqm->packets);
-	if (!r)
-		r = dqm_debugfs_execute_queues(dev->dqm);
-
-	return r;
+	return dqm_debugfs_hang_hws(dev->dqm);
 }
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 16a1713808c2..f8fce9d05f50 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -211,6 +211,15 @@ static void deallocate_doorbell(struct qcm_process_device *qpd,
 	WARN_ON(!old);
 }
 
+static void program_trap_handler_settings(struct device_queue_manager *dqm,
+				struct qcm_process_device *qpd)
+{
+	if (dqm->dev->kfd2kgd->program_trap_handler_settings)
+		dqm->dev->kfd2kgd->program_trap_handler_settings(
+						dqm->dev->kgd, qpd->vmid,
+						qpd->tba_addr, qpd->tma_addr);
+}
+
 static int allocate_vmid(struct device_queue_manager *dqm,
 			struct qcm_process_device *qpd,
 			struct queue *q)
@@ -241,6 +250,10 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 
 	program_sh_mem_settings(dqm, qpd);
 
+	if (dqm->dev->device_info->asic_family >= CHIP_VEGA10 &&
+	    dqm->dev->cwsr_enabled)
+		program_trap_handler_settings(dqm, qpd);
+
 	/* qpd->page_table_base is set earlier when register_process()
 	 * is called, i.e. when the first queue is created.
 	 */
@@ -260,7 +273,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 static int flush_texture_cache_nocpsch(struct kfd_dev *kdev,
 				struct qcm_process_device *qpd)
 {
-	const struct packet_manager_funcs *pmf = qpd->dqm->packets.pmf;
+	const struct packet_manager_funcs *pmf = qpd->dqm->packet_mgr.pmf;
 	int ret;
 
 	if (!qpd->ib_kaddr)
@@ -582,7 +595,9 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		}
 
 		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
-				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
+				(dqm->dev->cwsr_enabled?
+				 KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN),
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval) {
 			pr_err("destroy mqd failed\n");
@@ -675,7 +690,9 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 			continue;
 
 		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
-				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
+				(dqm->dev->cwsr_enabled?
+				 KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN),
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval && !ret)
 			/* Return the first error, but keep going to
@@ -1000,7 +1017,7 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 	init_interrupts(dqm);
 	
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		return pm_init(&dqm->packets, dqm);
+		return pm_init(&dqm->packet_mgr, dqm);
 	dqm->sched_running = true;
 
 	return 0;
@@ -1009,7 +1026,7 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		pm_uninit(&dqm->packets, false);
+		pm_uninit(&dqm->packet_mgr, false);
 	dqm->sched_running = false;
 
 	return 0;
@@ -1124,7 +1141,7 @@ static int set_sched_resources(struct device_queue_manager *dqm)
 			"queue mask: 0x%8llX\n",
 			res.vmid_mask, res.queue_mask);
 
-	return pm_send_set_resources(&dqm->packets, &res);
+	return pm_send_set_resources(&dqm->packet_mgr, &res);
 }
 
 static int initialize_cpsch(struct device_queue_manager *dqm)
@@ -1164,7 +1181,8 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	retval = 0;
 
-	retval = pm_init(&dqm->packets, dqm);
+	dqm_lock(dqm);
+	retval = pm_init(&dqm->packet_mgr, dqm);
 	if (retval)
 		goto fail_packet_manager_init;
 
@@ -1186,7 +1204,6 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	dqm_lock(dqm);
 	/* clear hang status when driver try to start the hw scheduler */
 	dqm->is_hws_hang = false;
 	dqm->is_resetting = false;
@@ -1197,8 +1214,9 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	return 0;
 fail_allocate_vidmem:
 fail_set_sched_resources:
-	pm_uninit(&dqm->packets, false);
+	pm_uninit(&dqm->packet_mgr, false);
 fail_packet_manager_init:
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1211,12 +1229,12 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	hanging = dqm->is_hws_hang || dqm->is_resetting;
 	dqm->sched_running = false;
-	dqm_unlock(dqm);
 
-	pm_release_ib(&dqm->packets);
+	pm_release_ib(&dqm->packet_mgr);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
-	pm_uninit(&dqm->packets, hanging);
+	pm_uninit(&dqm->packet_mgr, hanging);
+	dqm_unlock(dqm);
 
 	return 0;
 }
@@ -1390,7 +1408,7 @@ static int map_queues_cpsch(struct device_queue_manager *dqm)
 	if (dqm->active_runlist)
 		return 0;
 
-	retval = pm_send_runlist(&dqm->packets, &dqm->queues);
+	retval = pm_send_runlist(&dqm->packet_mgr, &dqm->queues);
 	pr_debug("%s sent runlist\n", __func__);
 	if (retval) {
 		pr_err("failed to execute runlist\n");
@@ -1416,13 +1434,13 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	if (!dqm->active_runlist)
 		return retval;
 
-	retval = pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_COMPUTE,
+	retval = pm_send_unmap_queue(&dqm->packet_mgr, KFD_QUEUE_TYPE_COMPUTE,
 			filter, filter_param, false, 0);
 	if (retval)
 		return retval;
 
 	*dqm->fence_addr = KFD_FENCE_INIT;
-	pm_send_query_status(&dqm->packets, dqm->fence_gpu_addr,
+	pm_send_query_status(&dqm->packet_mgr, dqm->fence_gpu_addr,
 				KFD_FENCE_COMPLETED);
 	/* should be timed out */
 	retval = amdkfd_fence_wait_timeout(dqm->fence_addr, KFD_FENCE_COMPLETED,
@@ -1448,14 +1466,14 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	 * check those fields
 	 */
 	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
-	if (mqd_mgr->read_doorbell_id(dqm->packets.priv_queue->queue->mqd)) {
+	if (mqd_mgr->read_doorbell_id(dqm->packet_mgr.priv_queue->queue->mqd)) {
 		pr_err("HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
 		while (halt_if_hws_hang)
 			schedule();
 		return -ETIME;
 	}
 
-	pm_release_ib(&dqm->packets);
+	pm_release_ib(&dqm->packet_mgr);
 	dqm->active_runlist = false;
 
 	return retval;
@@ -1946,6 +1964,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		device_queue_manager_init_v10_navi10(&dqm->asic_ops);
 		break;
 	default:
@@ -2099,11 +2118,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
-int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+int dqm_debugfs_hang_hws(struct device_queue_manager *dqm)
 {
 	int r = 0;
 
 	dqm_lock(dqm);
+	r = pm_debugfs_hang_hws(&dqm->packet_mgr);
+	if (r) {
+		dqm_unlock(dqm);
+		return r;
+	}
 	dqm->active_runlist = true;
 	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	dqm_unlock(dqm);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 71e2fde56b2b..c8719682c4da 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -169,7 +169,7 @@ struct device_queue_manager {
 	struct device_queue_manager_asic_ops asic_ops;
 
 	struct mqd_manager	*mqd_mgrs[KFD_MQD_TYPE_MAX];
-	struct packet_manager	packets;
+	struct packet_manager	packet_mgr;
 	struct kfd_dev		*dev;
 	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
 	struct list_head	queues;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index a9b329f0f862..2e86692def19 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -422,6 +422,7 @@ int kfd_init_apertures(struct kfd_process *process)
 			case CHIP_DIMGREY_CAVEFISH:
 			case CHIP_BEIGE_GOBY:
 			case CHIP_YELLOW_CARP:
+			case CHIP_CYAN_SKILLFISH:
 				kfd_init_apertures_v9(pdd, id);
 				break;
 			default:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 88813dad731f..c021519af810 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -98,36 +98,78 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		uint32_t *se_mask)
 {
 	struct kfd_cu_info cu_info;
-	uint32_t cu_per_se[KFD_MAX_NUM_SE] = {0};
-	int i, se, sh, cu = 0;
-
+	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
+	int i, se, sh, cu;
 	amdgpu_amdkfd_get_cu_info(mm->dev->kgd, &cu_info);
 
 	if (cu_mask_count > cu_info.cu_active_number)
 		cu_mask_count = cu_info.cu_active_number;
 
+	/* Exceeding these bounds corrupts the stack and indicates a coding error.
+	 * Returning with no CU's enabled will hang the queue, which should be
+	 * attention grabbing.
+	 */
+	if (cu_info.num_shader_engines > KFD_MAX_NUM_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SE, chip reports %d\n", cu_info.num_shader_engines);
+		return;
+	}
+	if (cu_info.num_shader_arrays_per_engine > KFD_MAX_NUM_SH_PER_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SH, chip reports %d\n",
+			cu_info.num_shader_arrays_per_engine * cu_info.num_shader_engines);
+		return;
+	}
+	/* Count active CUs per SH.
+	 *
+	 * Some CUs in an SH may be disabled.	HW expects disabled CUs to be
+	 * represented in the high bits of each SH's enable mask (the upper and lower
+	 * 16 bits of se_mask) and will take care of the actual distribution of
+	 * disabled CUs within each SH automatically.
+	 * Each half of se_mask must be filled only on bits 0-cu_per_sh[se][sh]-1.
+	 *
+	 * See note on Arcturus cu_bitmap layout in gfx_v9_0_get_cu_info.
+	 */
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
-			cu_per_se[se] += hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
-
-	/* Symmetrically map cu_mask to all SEs:
-	 * cu_mask[0] bit0 -> se_mask[0] bit0;
-	 * cu_mask[0] bit1 -> se_mask[1] bit0;
-	 * ... (if # SE is 4)
-	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+			cu_per_sh[se][sh] = hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
+
+	/* Symmetrically map cu_mask to all SEs & SHs:
+	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
+	 *
+	 * Examples
+	 * Assuming 1 SH/SE, 4 SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0
+	 * cu_mask[0] bit1 -> se_mask[1] bit0
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit1
+	 * ...
+	 *
+	 * Assuming 2 SH/SE, 4 SEs
+	 * cu_mask[0] bit0 -> se_mask[0] bit0 (SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> se_mask[1] bit0 (SE1,SH0,CU0)
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit16 (SE0,SH1,CU0)
+	 * cu_mask[0] bit5 -> se_mask[1] bit16 (SE1,SH1,CU0)
+	 * ...
+	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
 	 * ...
+	 *
+	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
-	se = 0;
-	for (i = 0; i < cu_mask_count; i++) {
-		if (cu_mask[i / 32] & (1 << (i % 32)))
-			se_mask[se] |= 1 << cu;
-
-		do {
-			se++;
-			if (se == cu_info.num_shader_engines) {
-				se = 0;
-				cu++;
+	for (i = 0; i < cu_info.num_shader_engines; i++)
+		se_mask[i] = 0;
+
+	i = 0;
+	for (cu = 0; cu < 16; cu++) {
+		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++) {
+			for (se = 0; se < cu_info.num_shader_engines; se++) {
+				if (cu_per_sh[se][sh] > cu) {
+					if (cu_mask[i / 32] & (1 << (i % 32)))
+						se_mask[se] |= 1 << (cu + sh * 16);
+					i++;
+					if (i == cu_mask_count)
+						return;
+				}
 			}
-		} while (cu >= cu_per_se[se] && cu < 32);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index b5e2ea7550d4..6e6918ccedfd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -27,6 +27,7 @@
 #include "kfd_priv.h"
 
 #define KFD_MAX_NUM_SE 8
+#define KFD_MAX_NUM_SH_PER_SE 2
 
 /**
  * struct mqd_manager
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index d8e940f03102..e547f1f8c49f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -251,6 +251,7 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		pm->pmf = &kfd_v9_pm_funcs;
 		break;
 	case CHIP_ALDEBARAN:
@@ -278,6 +279,7 @@ void pm_uninit(struct packet_manager *pm, bool hanging)
 {
 	mutex_destroy(&pm->lock);
 	kernel_queue_uninit(pm->priv_queue, hanging);
+	pm->priv_queue = NULL;
 }
 
 int pm_send_set_resources(struct packet_manager *pm,
@@ -447,6 +449,9 @@ int pm_debugfs_hang_hws(struct packet_manager *pm)
 	uint32_t *buffer, size;
 	int r = 0;
 
+	if (!pm->priv_queue)
+		return -EAGAIN;
+
 	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
 	kq_acquire_packet_buffer(pm->priv_queue,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 3426743ed228..ab83b0de6b22 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -196,6 +196,7 @@ struct kfd_event_interrupt_class {
 struct kfd_device_info {
 	enum amd_asic_type asic_family;
 	const char *asic_name;
+	uint32_t gfx_target_version;
 	const struct kfd_event_interrupt_class *event_interrupt_class;
 	unsigned int max_pasid_bits;
 	unsigned int max_no_of_hqd;
@@ -1194,7 +1195,7 @@ int pm_debugfs_runlist(struct seq_file *m, void *data);
 
 int kfd_debugfs_hang_hws(struct kfd_dev *dev);
 int pm_debugfs_hang_hws(struct packet_manager *pm);
-int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+int dqm_debugfs_hang_hws(struct device_queue_manager *dqm);
 
 #else
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 8a2c6fc438c0..21ec8a18cad2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -714,7 +714,8 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd,
 	if (err)
 		goto err_alloc_mem;
 
-	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv);
+	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem,
+			pdd->drm_priv, NULL);
 	if (err)
 		goto err_map_mem;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 246522423559..ed4bc5f844ce 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -205,23 +205,23 @@ void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset)
 }
 
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
-					     uint32_t throttle_bitmask)
+					     uint64_t throttle_bitmask)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
 	/*
 	 * ThermalThrottle msg = throttle_bitmask(8):
 	 * 			 thermal_interrupt_count(16):
-	 * 1 byte event + 1 byte space + 8 byte throttle_bitmask +
+	 * 1 byte event + 1 byte space + 16 byte throttle_bitmask +
 	 * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n +
-	 * 1 byte \0 = 29
+	 * 1 byte \0 = 37
 	 */
-	char fifo_in[29];
+	char fifo_in[37];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
 		return;
 
-	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%llx\n",
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %llx:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
 		       atomic64_read(&adev->smu.throttle_int_counter));
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index b9b0438202e2..bffd0c32b060 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -26,7 +26,7 @@
 int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
-					     uint32_t throttle_bitmask);
+					     uint64_t throttle_bitmask);
 void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index e883731c3f8f..491373fcdb38 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -120,6 +120,7 @@ static void svm_range_remove_notifier(struct svm_range *prange)
 
 static int
 svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
+		      unsigned long offset, unsigned long npages,
 		      unsigned long *hmm_pfns, uint32_t gpuidx)
 {
 	enum dma_data_direction dir = DMA_BIDIRECTIONAL;
@@ -136,7 +137,8 @@ svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
 		prange->dma_addr[gpuidx] = addr;
 	}
 
-	for (i = 0; i < prange->npages; i++) {
+	addr += offset;
+	for (i = 0; i < npages; i++) {
 		if (WARN_ONCE(addr[i] && !dma_mapping_error(dev, addr[i]),
 			      "leaking dma mapping\n"))
 			dma_unmap_page(dev, addr[i], PAGE_SIZE, dir);
@@ -167,6 +169,7 @@ svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
 
 static int
 svm_range_dma_map(struct svm_range *prange, unsigned long *bitmap,
+		  unsigned long offset, unsigned long npages,
 		  unsigned long *hmm_pfns)
 {
 	struct kfd_process *p;
@@ -187,7 +190,8 @@ svm_range_dma_map(struct svm_range *prange, unsigned long *bitmap,
 		}
 		adev = (struct amdgpu_device *)pdd->dev->kgd;
 
-		r = svm_range_dma_map_dev(adev, prange, hmm_pfns, gpuidx);
+		r = svm_range_dma_map_dev(adev, prange, offset, npages,
+					  hmm_pfns, gpuidx);
 		if (r)
 			break;
 	}
@@ -1088,11 +1092,6 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange,
 	pte_flags |= snoop ? AMDGPU_PTE_SNOOPED : 0;
 
 	pte_flags |= amdgpu_gem_va_map_flags(adev, mapping_flags);
-
-	pr_debug("svms 0x%p [0x%lx 0x%lx] vram %d PTE 0x%llx mapping 0x%x\n",
-		 prange->svms, prange->start, prange->last,
-		 (domain == SVM_RANGE_VRAM_DOMAIN) ? 1:0, pte_flags, mapping_flags);
-
 	return pte_flags;
 }
 
@@ -1156,7 +1155,8 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
 
 static int
 svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		     struct svm_range *prange, dma_addr_t *dma_addr,
+		     struct svm_range *prange, unsigned long offset,
+		     unsigned long npages, bool readonly, dma_addr_t *dma_addr,
 		     struct amdgpu_device *bo_adev, struct dma_fence **fence)
 {
 	struct amdgpu_bo_va bo_va;
@@ -1167,14 +1167,15 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	int r = 0;
 	int64_t i;
 
-	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
-		 prange->last);
+	last_start = prange->start + offset;
+
+	pr_debug("svms 0x%p [0x%lx 0x%lx] readonly %d\n", prange->svms,
+		 last_start, last_start + npages - 1, readonly);
 
 	if (prange->svm_bo && prange->ttm_res)
 		bo_va.is_xgmi = amdgpu_xgmi_same_hive(adev, bo_adev);
 
-	last_start = prange->start;
-	for (i = 0; i < prange->npages; i++) {
+	for (i = offset; i < offset + npages; i++) {
 		last_domain = dma_addr[i] & SVM_RANGE_VRAM_DOMAIN;
 		dma_addr[i] &= ~SVM_RANGE_VRAM_DOMAIN;
 		if ((prange->start + i) < prange->last &&
@@ -1183,13 +1184,21 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 		pr_debug("Mapping range [0x%lx 0x%llx] on domain: %s\n",
 			 last_start, prange->start + i, last_domain ? "GPU" : "CPU");
+
 		pte_flags = svm_range_get_pte_flags(adev, prange, last_domain);
-		r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
-						last_start,
+		if (readonly)
+			pte_flags &= ~AMDGPU_PTE_WRITEABLE;
+
+		pr_debug("svms 0x%p map [0x%lx 0x%llx] vram %d PTE 0x%llx\n",
+			 prange->svms, last_start, prange->start + i,
+			 (last_domain == SVM_RANGE_VRAM_DOMAIN) ? 1 : 0,
+			 pte_flags);
+
+		r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false,
+						NULL, last_start,
 						prange->start + i, pte_flags,
 						last_start - prange->start,
-						NULL,
-						dma_addr,
+						NULL, dma_addr,
 						&vm->last_update,
 						&table_freed);
 		if (r) {
@@ -1220,8 +1229,10 @@ out:
 	return r;
 }
 
-static int svm_range_map_to_gpus(struct svm_range *prange,
-				 unsigned long *bitmap, bool wait)
+static int
+svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
+		      unsigned long npages, bool readonly,
+		      unsigned long *bitmap, bool wait)
 {
 	struct kfd_process_device *pdd;
 	struct amdgpu_device *bo_adev;
@@ -1257,7 +1268,8 @@ static int svm_range_map_to_gpus(struct svm_range *prange,
 		}
 
 		r = svm_range_map_to_gpu(adev, drm_priv_to_vm(pdd->drm_priv),
-					 prange, prange->dma_addr[gpuidx],
+					 prange, offset, npages, readonly,
+					 prange->dma_addr[gpuidx],
 					 bo_adev, wait ? &fence : NULL);
 		if (r)
 			break;
@@ -1390,7 +1402,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 				      int32_t gpuidx, bool intr, bool wait)
 {
 	struct svm_validate_context ctx;
-	struct hmm_range *hmm_range;
+	unsigned long start, end, addr;
 	struct kfd_process *p;
 	void *owner;
 	int32_t idx;
@@ -1448,40 +1460,66 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 			break;
 		}
 	}
-	r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
-				       prange->start << PAGE_SHIFT,
-				       prange->npages, &hmm_range,
-				       false, true, owner);
-	if (r) {
-		pr_debug("failed %d to get svm range pages\n", r);
-		goto unreserve_out;
-	}
 
-	r = svm_range_dma_map(prange, ctx.bitmap,
-			      hmm_range->hmm_pfns);
-	if (r) {
-		pr_debug("failed %d to dma map range\n", r);
-		goto unreserve_out;
-	}
+	start = prange->start << PAGE_SHIFT;
+	end = (prange->last + 1) << PAGE_SHIFT;
+	for (addr = start; addr < end && !r; ) {
+		struct hmm_range *hmm_range;
+		struct vm_area_struct *vma;
+		unsigned long next;
+		unsigned long offset;
+		unsigned long npages;
+		bool readonly;
 
-	prange->validated_once = true;
+		vma = find_vma(mm, addr);
+		if (!vma || addr < vma->vm_start) {
+			r = -EFAULT;
+			goto unreserve_out;
+		}
+		readonly = !(vma->vm_flags & VM_WRITE);
 
-	svm_range_lock(prange);
-	if (amdgpu_hmm_range_get_pages_done(hmm_range)) {
-		pr_debug("hmm update the range, need validate again\n");
-		r = -EAGAIN;
-		goto unlock_out;
-	}
-	if (!list_empty(&prange->child_list)) {
-		pr_debug("range split by unmap in parallel, validate again\n");
-		r = -EAGAIN;
-		goto unlock_out;
-	}
+		next = min(vma->vm_end, end);
+		npages = (next - addr) >> PAGE_SHIFT;
+		r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
+					       addr, npages, &hmm_range,
+					       readonly, true, owner);
+		if (r) {
+			pr_debug("failed %d to get svm range pages\n", r);
+			goto unreserve_out;
+		}
 
-	r = svm_range_map_to_gpus(prange, ctx.bitmap, wait);
+		offset = (addr - start) >> PAGE_SHIFT;
+		r = svm_range_dma_map(prange, ctx.bitmap, offset, npages,
+				      hmm_range->hmm_pfns);
+		if (r) {
+			pr_debug("failed %d to dma map range\n", r);
+			goto unreserve_out;
+		}
+
+		svm_range_lock(prange);
+		if (amdgpu_hmm_range_get_pages_done(hmm_range)) {
+			pr_debug("hmm update the range, need validate again\n");
+			r = -EAGAIN;
+			goto unlock_out;
+		}
+		if (!list_empty(&prange->child_list)) {
+			pr_debug("range split by unmap in parallel, validate again\n");
+			r = -EAGAIN;
+			goto unlock_out;
+		}
+
+		r = svm_range_map_to_gpus(prange, offset, npages, readonly,
+					  ctx.bitmap, wait);
 
 unlock_out:
-	svm_range_unlock(prange);
+		svm_range_unlock(prange);
+
+		addr = next;
+	}
+
+	if (addr == end)
+		prange->validated_once = true;
+
 unreserve_out:
 	svm_range_unreserve_bos(&ctx);
 
@@ -2400,9 +2438,29 @@ svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p,
 		WRITE_ONCE(pdd->faults, pdd->faults + 1);
 }
 
+static bool
+svm_fault_allowed(struct mm_struct *mm, uint64_t addr, bool write_fault)
+{
+	unsigned long requested = VM_READ;
+	struct vm_area_struct *vma;
+
+	if (write_fault)
+		requested |= VM_WRITE;
+
+	vma = find_vma(mm, addr << PAGE_SHIFT);
+	if (!vma || (addr << PAGE_SHIFT) < vma->vm_start) {
+		pr_debug("address 0x%llx VMA is removed\n", addr);
+		return true;
+	}
+
+	pr_debug("requested 0x%lx, vma permission flags 0x%lx\n", requested,
+		vma->vm_flags);
+	return (vma->vm_flags & requested) == requested;
+}
+
 int
 svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
-			uint64_t addr)
+			uint64_t addr, bool write_fault)
 {
 	struct mm_struct *mm = NULL;
 	struct svm_range_list *svms;
@@ -2484,6 +2542,13 @@ retry_write_locked:
 		goto out_unlock_range;
 	}
 
+	if (!svm_fault_allowed(mm, addr, write_fault)) {
+		pr_debug("fault addr 0x%llx no %s permission\n", addr,
+			write_fault ? "write" : "read");
+		r = -EPERM;
+		goto out_unlock_range;
+	}
+
 	best_loc = svm_range_best_restore_location(prange, adev, &gpuidx);
 	if (best_loc == -1) {
 		pr_debug("svms %p failed get best restore loc [0x%lx 0x%lx]\n",
@@ -2675,22 +2740,26 @@ svm_range_add(struct kfd_process *p, uint64_t start, uint64_t size,
 	return 0;
 }
 
-/* svm_range_best_prefetch_location - decide the best prefetch location
+/**
+ * svm_range_best_prefetch_location - decide the best prefetch location
  * @prange: svm range structure
  *
  * For xnack off:
- * If range map to single GPU, the best acutal location is prefetch loc, which
+ * If range map to single GPU, the best prefetch location is prefetch_loc, which
  * can be CPU or GPU.
  *
- * If range map to multiple GPUs, only if mGPU connection on xgmi same hive,
- * the best actual location could be prefetch_loc GPU. If mGPU connection on
- * PCIe, the best actual location is always CPU, because GPU cannot access vram
- * of other GPUs, assuming PCIe small bar (large bar support is not upstream).
+ * If range is ACCESS or ACCESS_IN_PLACE by mGPUs, only if mGPU connection on
+ * XGMI same hive, the best prefetch location is prefetch_loc GPU, othervise
+ * the best prefetch location is always CPU, because GPU can not have coherent
+ * mapping VRAM of other GPUs even with large-BAR PCIe connection.
  *
  * For xnack on:
- * The best actual location is prefetch location. If mGPU connection on xgmi
- * same hive, range map to multiple GPUs. Otherwise, the range only map to
- * actual location GPU. Other GPU access vm fault will trigger migration.
+ * If range is not ACCESS_IN_PLACE by mGPUs, the best prefetch location is
+ * prefetch_loc, other GPU access will generate vm fault and trigger migration.
+ *
+ * If range is ACCESS_IN_PLACE by mGPUs, only if mGPU connection on XGMI same
+ * hive, the best prefetch location is prefetch_loc GPU, otherwise the best
+ * prefetch location is always CPU.
  *
  * Context: Process context
  *
@@ -2710,11 +2779,6 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 
 	p = container_of(prange->svms, struct kfd_process, svms);
 
-	/* xnack on */
-	if (p->xnack_enabled)
-		goto out;
-
-	/* xnack off */
 	if (!best_loc || best_loc == KFD_IOCTL_SVM_LOCATION_UNDEFINED)
 		goto out;
 
@@ -2724,8 +2788,12 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 		best_loc = 0;
 		goto out;
 	}
-	bitmap_or(bitmap, prange->bitmap_access, prange->bitmap_aip,
-		  MAX_GPU_INSTANCE);
+
+	if (p->xnack_enabled)
+		bitmap_copy(bitmap, prange->bitmap_aip, MAX_GPU_INSTANCE);
+	else
+		bitmap_or(bitmap, prange->bitmap_access, prange->bitmap_aip,
+			  MAX_GPU_INSTANCE);
 
 	for_each_set_bit(gpuidx, bitmap, MAX_GPU_INSTANCE) {
 		pdd = kfd_process_device_from_gpuidx(p, gpuidx);
@@ -3019,7 +3087,8 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	struct svm_range *prange;
 	uint32_t prefetch_loc = KFD_IOCTL_SVM_LOCATION_UNDEFINED;
 	uint32_t location = KFD_IOCTL_SVM_LOCATION_UNDEFINED;
-	uint32_t flags = 0xffffffff;
+	uint32_t flags_and = 0xffffffff;
+	uint32_t flags_or = 0;
 	int gpuidx;
 	uint32_t i;
 
@@ -3054,12 +3123,12 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 			get_accessible = true;
 			break;
 		case KFD_IOCTL_SVM_ATTR_SET_FLAGS:
+		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
 			get_flags = true;
 			break;
 		case KFD_IOCTL_SVM_ATTR_GRANULARITY:
 			get_granularity = true;
 			break;
-		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
 		case KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE:
 		case KFD_IOCTL_SVM_ATTR_NO_ACCESS:
 			fallthrough;
@@ -3077,7 +3146,8 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	if (!node) {
 		pr_debug("range attrs not found return default values\n");
 		svm_range_set_default_attributes(&location, &prefetch_loc,
-						 &granularity, &flags);
+						 &granularity, &flags_and);
+		flags_or = flags_and;
 		if (p->xnack_enabled)
 			bitmap_copy(bitmap_access, svms->bitmap_supported,
 				    MAX_GPU_INSTANCE);
@@ -3123,8 +3193,10 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 			bitmap_and(bitmap_aip, bitmap_aip,
 				   prange->bitmap_aip, MAX_GPU_INSTANCE);
 		}
-		if (get_flags)
-			flags &= prange->flags;
+		if (get_flags) {
+			flags_and &= prange->flags;
+			flags_or |= prange->flags;
+		}
 
 		if (get_granularity && prange->granularity < granularity)
 			granularity = prange->granularity;
@@ -3158,7 +3230,10 @@ fill_values:
 				attrs[i].type = KFD_IOCTL_SVM_ATTR_NO_ACCESS;
 			break;
 		case KFD_IOCTL_SVM_ATTR_SET_FLAGS:
-			attrs[i].value = flags;
+			attrs[i].value = flags_and;
+			break;
+		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
+			attrs[i].value = ~flags_or;
 			break;
 		case KFD_IOCTL_SVM_ATTR_GRANULARITY:
 			attrs[i].value = (uint32_t)granularity;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 3fc1fd8b4fbc..c6ec55354c7b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -175,7 +175,7 @@ int svm_range_split_by_granularity(struct kfd_process *p, struct mm_struct *mm,
 			       unsigned long addr, struct svm_range *parent,
 			       struct svm_range *prange);
 int svm_range_restore_pages(struct amdgpu_device *adev,
-			    unsigned int pasid, uint64_t addr);
+			    unsigned int pasid, uint64_t addr, bool write_fault);
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence);
 void svm_range_add_list_work(struct svm_range_list *svms,
 			     struct svm_range *prange, struct mm_struct *mm,
@@ -209,7 +209,8 @@ static inline void svm_range_list_fini(struct kfd_process *p)
 }
 
 static inline int svm_range_restore_pages(struct amdgpu_device *adev,
-					  unsigned int pasid, uint64_t addr)
+					  unsigned int pasid, uint64_t addr,
+					  bool write_fault)
 {
 	return -EFAULT;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index b1ce072aa20b..98cca5f2b27f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -478,6 +478,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			      dev->node_props.simd_per_cu);
 	sysfs_show_32bit_prop(buffer, offs, "max_slots_scratch_cu",
 			      dev->node_props.max_slots_scratch_cu);
+	sysfs_show_32bit_prop(buffer, offs, "gfx_target_version",
+			      dev->node_props.gfx_target_version);
 	sysfs_show_32bit_prop(buffer, offs, "vendor_id",
 			      dev->node_props.vendor_id);
 	sysfs_show_32bit_prop(buffer, offs, "device_id",
@@ -1360,6 +1362,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	dev->node_props.simd_arrays_per_engine =
 		cu_info.num_shader_arrays_per_engine;
 
+	dev->node_props.gfx_target_version = gpu->device_info->gfx_target_version;
 	dev->node_props.vendor_id = gpu->pdev->vendor;
 	dev->node_props.device_id = gpu->pdev->device;
 	dev->node_props.capability |=
@@ -1424,6 +1427,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 <<
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
@@ -1630,7 +1634,7 @@ int kfd_debugfs_rls_by_device(struct seq_file *m, void *data)
 		}
 
 		seq_printf(m, "Node %u, gpu_id %x:\n", i++, dev->gpu->id);
-		r = pm_debugfs_runlist(m, &dev->gpu->dqm->packets);
+		r = pm_debugfs_runlist(m, &dev->gpu->dqm->packet_mgr);
 		if (r)
 			break;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index 8b48c6692007..a8db017c9b8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -78,6 +78,7 @@ struct kfd_node_properties {
 	uint32_t simd_per_cu;
 	uint32_t max_slots_scratch_cu;
 	uint32_t engine_id;
+	uint32_t gfx_target_version;
 	uint32_t vendor_id;
 	uint32_t device_id;
 	uint32_t location_id;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 91fb72c96545..718e123a3230 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -27,6 +27,10 @@
 
 AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o
 
+ifdef CONFIG_DRM_AMD_DC_DCN
+AMDGPUDM += dc_fpu.o
+endif
+
 ifneq ($(CONFIG_DRM_AMD_DC),)
 AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o amdgpu_dm_psr.o
 endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index afa96c8f721b..816723691d51 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -618,6 +618,7 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params)
 }
 #endif
 
+#define DMUB_TRACE_MAX_READ 64
 /**
  * dm_dmub_outbox1_low_irq() - Handles Outbox interrupt
  * @interrupt_params: used for determining the Outbox instance
@@ -625,7 +626,6 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params)
  * Handles the Outbox Interrupt
  * event handler.
  */
-#define DMUB_TRACE_MAX_READ 64
 static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 {
 	struct dmub_notification notify;
@@ -1044,10 +1044,10 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 }
 #endif
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-static void event_mall_stutter(struct work_struct *work)
+static void vblank_control_worker(struct work_struct *work)
 {
-
-	struct vblank_workqueue *vblank_work = container_of(work, struct vblank_workqueue, mall_work);
+	struct vblank_control_work *vblank_work =
+		container_of(work, struct vblank_control_work, work);
 	struct amdgpu_display_manager *dm = vblank_work->dm;
 
 	mutex_lock(&dm->dc_lock);
@@ -1061,27 +1061,25 @@ static void event_mall_stutter(struct work_struct *work)
 
 	DRM_DEBUG_KMS("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0);
 
-	mutex_unlock(&dm->dc_lock);
-}
-
-static struct vblank_workqueue *vblank_create_workqueue(struct amdgpu_device *adev, struct dc *dc)
-{
-
-	int max_caps = dc->caps.max_links;
-	struct vblank_workqueue *vblank_work;
-	int i = 0;
-
-	vblank_work = kcalloc(max_caps, sizeof(*vblank_work), GFP_KERNEL);
-	if (ZERO_OR_NULL_PTR(vblank_work)) {
-		kfree(vblank_work);
-		return NULL;
+	/* Control PSR based on vblank requirements from OS */
+	if (vblank_work->stream && vblank_work->stream->link) {
+		if (vblank_work->enable) {
+			if (vblank_work->stream->link->psr_settings.psr_allow_active)
+				amdgpu_dm_psr_disable(vblank_work->stream);
+		} else if (vblank_work->stream->link->psr_settings.psr_feature_enabled &&
+			   !vblank_work->stream->link->psr_settings.psr_allow_active &&
+			   vblank_work->acrtc->dm_irq_params.allow_psr_entry) {
+			amdgpu_dm_psr_enable(vblank_work->stream);
+		}
 	}
 
-	for (i = 0; i < max_caps; i++)
-		INIT_WORK(&vblank_work[i].mall_work, event_mall_stutter);
+	mutex_unlock(&dm->dc_lock);
+
+	dc_stream_release(vblank_work->stream);
 
-	return vblank_work;
+	kfree(vblank_work);
 }
+
 #endif
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
@@ -1224,12 +1222,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (adev->dm.dc->caps.max_links > 0) {
-		adev->dm.vblank_workqueue = vblank_create_workqueue(adev, adev->dm.dc);
-
-		if (!adev->dm.vblank_workqueue)
+		adev->dm.vblank_control_workqueue =
+			create_singlethread_workqueue("dm_vblank_control_workqueue");
+		if (!adev->dm.vblank_control_workqueue)
 			DRM_ERROR("amdgpu: failed to initialize vblank_workqueue.\n");
-		else
-			DRM_DEBUG_DRIVER("amdgpu: vblank_workqueue init done %p.\n", adev->dm.vblank_workqueue);
 	}
 #endif
 
@@ -1302,6 +1298,13 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 {
 	int i;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (adev->dm.vblank_control_workqueue) {
+		destroy_workqueue(adev->dm.vblank_control_workqueue);
+		adev->dm.vblank_control_workqueue = NULL;
+	}
+#endif
+
 	for (i = 0; i < adev->dm.display_indexes_num; i++) {
 		drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
 	}
@@ -1325,14 +1328,6 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 		dc_deinit_callbacks(adev->dm.dc);
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (adev->dm.vblank_workqueue) {
-		adev->dm.vblank_workqueue->dm = NULL;
-		kfree(adev->dm.vblank_workqueue);
-		adev->dm.vblank_workqueue = NULL;
-	}
-#endif
-
 	dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv);
 
 	if (dc_enable_dmub_notifications(adev->dm.dc)) {
@@ -2412,6 +2407,7 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	static const u8 pre_computed_values[] = {
 		50, 51, 52, 53, 55, 56, 57, 58, 59, 61, 62, 63, 65, 66, 68, 69,
 		71, 72, 74, 75, 77, 79, 81, 82, 84, 86, 88, 90, 92, 94, 96, 98};
+	int i;
 
 	if (!aconnector || !aconnector->dc_link)
 		return;
@@ -2423,7 +2419,13 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	conn_base = &aconnector->base;
 	adev = drm_to_adev(conn_base->dev);
 	dm = &adev->dm;
-	caps = &dm->backlight_caps;
+	for (i = 0; i < dm->num_of_edps; i++) {
+		if (link == dm->backlight_link[i])
+			break;
+	}
+	if (i >= dm->num_of_edps)
+		return;
+	caps = &dm->backlight_caps[i];
 	caps->ext_caps = &aconnector->dc_link->dpcd_sink_ext_caps;
 	caps->aux_support = false;
 	max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll;
@@ -3423,35 +3425,36 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
-static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm)
+static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm,
+					    int bl_idx)
 {
 #if defined(CONFIG_ACPI)
 	struct amdgpu_dm_backlight_caps caps;
 
 	memset(&caps, 0, sizeof(caps));
 
-	if (dm->backlight_caps.caps_valid)
+	if (dm->backlight_caps[bl_idx].caps_valid)
 		return;
 
 	amdgpu_acpi_get_backlight_caps(&caps);
 	if (caps.caps_valid) {
-		dm->backlight_caps.caps_valid = true;
+		dm->backlight_caps[bl_idx].caps_valid = true;
 		if (caps.aux_support)
 			return;
-		dm->backlight_caps.min_input_signal = caps.min_input_signal;
-		dm->backlight_caps.max_input_signal = caps.max_input_signal;
+		dm->backlight_caps[bl_idx].min_input_signal = caps.min_input_signal;
+		dm->backlight_caps[bl_idx].max_input_signal = caps.max_input_signal;
 	} else {
-		dm->backlight_caps.min_input_signal =
+		dm->backlight_caps[bl_idx].min_input_signal =
 				AMDGPU_DM_DEFAULT_MIN_BACKLIGHT;
-		dm->backlight_caps.max_input_signal =
+		dm->backlight_caps[bl_idx].max_input_signal =
 				AMDGPU_DM_DEFAULT_MAX_BACKLIGHT;
 	}
 #else
-	if (dm->backlight_caps.aux_support)
+	if (dm->backlight_caps[bl_idx].aux_support)
 		return;
 
-	dm->backlight_caps.min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT;
-	dm->backlight_caps.max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT;
+	dm->backlight_caps[bl_idx].min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT;
+	dm->backlight_caps[bl_idx].max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT;
 #endif
 }
 
@@ -3502,41 +3505,31 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap
 }
 
 static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+					 int bl_idx,
 					 u32 user_brightness)
 {
 	struct amdgpu_dm_backlight_caps caps;
-	struct dc_link *link[AMDGPU_DM_MAX_NUM_EDP];
-	u32 brightness[AMDGPU_DM_MAX_NUM_EDP];
+	struct dc_link *link;
+	u32 brightness;
 	bool rc;
-	int i;
 
-	amdgpu_dm_update_backlight_caps(dm);
-	caps = dm->backlight_caps;
+	amdgpu_dm_update_backlight_caps(dm, bl_idx);
+	caps = dm->backlight_caps[bl_idx];
 
-	for (i = 0; i < dm->num_of_edps; i++) {
-		dm->brightness[i] = user_brightness;
-		brightness[i] = convert_brightness_from_user(&caps, dm->brightness[i]);
-		link[i] = (struct dc_link *)dm->backlight_link[i];
-	}
+	dm->brightness[bl_idx] = user_brightness;
+	brightness = convert_brightness_from_user(&caps, dm->brightness[bl_idx]);
+	link = (struct dc_link *)dm->backlight_link[bl_idx];
 
 	/* Change brightness based on AUX property */
 	if (caps.aux_support) {
-		for (i = 0; i < dm->num_of_edps; i++) {
-			rc = dc_link_set_backlight_level_nits(link[i], true, brightness[i],
-				AUX_BL_DEFAULT_TRANSITION_TIME_MS);
-			if (!rc) {
-				DRM_DEBUG("DM: Failed to update backlight via AUX on eDP[%d]\n", i);
-				break;
-			}
-		}
+		rc = dc_link_set_backlight_level_nits(link, true, brightness,
+						      AUX_BL_DEFAULT_TRANSITION_TIME_MS);
+		if (!rc)
+			DRM_DEBUG("DM: Failed to update backlight via AUX on eDP[%d]\n", bl_idx);
 	} else {
-		for (i = 0; i < dm->num_of_edps; i++) {
-			rc = dc_link_set_backlight_level(dm->backlight_link[i], brightness[i], 0);
-			if (!rc) {
-				DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", i);
-				break;
-			}
-		}
+		rc = dc_link_set_backlight_level(link, brightness, 0);
+		if (!rc)
+			DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx);
 	}
 
 	return rc ? 0 : 1;
@@ -3545,33 +3538,41 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
 static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 {
 	struct amdgpu_display_manager *dm = bl_get_data(bd);
+	int i;
 
-	amdgpu_dm_backlight_set_level(dm, bd->props.brightness);
+	for (i = 0; i < dm->num_of_edps; i++) {
+		if (bd == dm->backlight_dev[i])
+			break;
+	}
+	if (i >= AMDGPU_DM_MAX_NUM_EDP)
+		i = 0;
+	amdgpu_dm_backlight_set_level(dm, i, bd->props.brightness);
 
 	return 0;
 }
 
-static u32 amdgpu_dm_backlight_get_level(struct amdgpu_display_manager *dm)
+static u32 amdgpu_dm_backlight_get_level(struct amdgpu_display_manager *dm,
+					 int bl_idx)
 {
 	struct amdgpu_dm_backlight_caps caps;
+	struct dc_link *link = (struct dc_link *)dm->backlight_link[bl_idx];
 
-	amdgpu_dm_update_backlight_caps(dm);
-	caps = dm->backlight_caps;
+	amdgpu_dm_update_backlight_caps(dm, bl_idx);
+	caps = dm->backlight_caps[bl_idx];
 
 	if (caps.aux_support) {
-		struct dc_link *link = (struct dc_link *)dm->backlight_link[0];
 		u32 avg, peak;
 		bool rc;
 
 		rc = dc_link_get_backlight_level_nits(link, &avg, &peak);
 		if (!rc)
-			return dm->brightness[0];
+			return dm->brightness[bl_idx];
 		return convert_brightness_to_user(&caps, avg);
 	} else {
-		int ret = dc_link_get_backlight_level(dm->backlight_link[0]);
+		int ret = dc_link_get_backlight_level(link);
 
 		if (ret == DC_ERROR_UNEXPECTED)
-			return dm->brightness[0];
+			return dm->brightness[bl_idx];
 		return convert_brightness_to_user(&caps, ret);
 	}
 }
@@ -3579,8 +3580,15 @@ static u32 amdgpu_dm_backlight_get_level(struct amdgpu_display_manager *dm)
 static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 {
 	struct amdgpu_display_manager *dm = bl_get_data(bd);
+	int i;
 
-	return amdgpu_dm_backlight_get_level(dm);
+	for (i = 0; i < dm->num_of_edps; i++) {
+		if (bd == dm->backlight_dev[i])
+			break;
+	}
+	if (i >= AMDGPU_DM_MAX_NUM_EDP)
+		i = 0;
+	return amdgpu_dm_backlight_get_level(dm, i);
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
@@ -3594,31 +3602,28 @@ amdgpu_dm_register_backlight_device(struct amdgpu_display_manager *dm)
 {
 	char bl_name[16];
 	struct backlight_properties props = { 0 };
-	int i;
 
-	amdgpu_dm_update_backlight_caps(dm);
-	for (i = 0; i < dm->num_of_edps; i++)
-		dm->brightness[i] = AMDGPU_MAX_BL_LEVEL;
+	amdgpu_dm_update_backlight_caps(dm, dm->num_of_edps);
+	dm->brightness[dm->num_of_edps] = AMDGPU_MAX_BL_LEVEL;
 
 	props.max_brightness = AMDGPU_MAX_BL_LEVEL;
 	props.brightness = AMDGPU_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",
-		 adev_to_drm(dm->adev)->primary->index);
+		 adev_to_drm(dm->adev)->primary->index + dm->num_of_edps);
 
-	dm->backlight_dev = backlight_device_register(bl_name,
-						      adev_to_drm(dm->adev)->dev,
-						      dm,
-						      &amdgpu_dm_backlight_ops,
-						      &props);
+	dm->backlight_dev[dm->num_of_edps] = backlight_device_register(bl_name,
+								       adev_to_drm(dm->adev)->dev,
+								       dm,
+								       &amdgpu_dm_backlight_ops,
+								       &props);
 
-	if (IS_ERR(dm->backlight_dev))
+	if (IS_ERR(dm->backlight_dev[dm->num_of_edps]))
 		DRM_ERROR("DM: Backlight registration failed!\n");
 	else
 		DRM_DEBUG_DRIVER("DM: Registered Backlight device: %s\n", bl_name);
 }
-
 #endif
 
 static int initialize_plane(struct amdgpu_display_manager *dm,
@@ -3675,10 +3680,10 @@ static void register_backlight_device(struct amdgpu_display_manager *dm,
 		 * DM initialization because not having a backlight control
 		 * is better then a black screen.
 		 */
-		if (!dm->backlight_dev)
+		if (!dm->backlight_dev[dm->num_of_edps])
 			amdgpu_dm_register_backlight_device(dm);
 
-		if (dm->backlight_dev) {
+		if (dm->backlight_dev[dm->num_of_edps]) {
 			dm->backlight_link[dm->num_of_edps] = link;
 			dm->num_of_edps++;
 		}
@@ -4747,7 +4752,7 @@ fill_gfx9_plane_attributes_from_modifiers(struct amdgpu_device *adev,
 					  const bool force_disable_dcc)
 {
 	const uint64_t modifier = afb->base.modifier;
-	int ret;
+	int ret = 0;
 
 	fill_gfx9_tiling_info_from_modifier(adev, tiling_info, modifier);
 	tiling_info->gfx9.swizzle = modifier_gfx9_swizzle_mode(modifier);
@@ -4765,9 +4770,9 @@ fill_gfx9_plane_attributes_from_modifiers(struct amdgpu_device *adev,
 
 	ret = validate_dcc(adev, format, rotation, tiling_info, dcc, address, plane_size);
 	if (ret)
-		return ret;
+		drm_dbg_kms(adev_to_drm(adev), "validate_dcc: returned error: %d\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -5994,7 +5999,7 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state);
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	struct amdgpu_display_manager *dm = &adev->dm;
-	unsigned long flags;
+	struct vblank_control_work *work;
 #endif
 	int rc = 0;
 
@@ -6019,12 +6024,21 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 		return 0;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	spin_lock_irqsave(&dm->vblank_lock, flags);
-	dm->vblank_workqueue->dm = dm;
-	dm->vblank_workqueue->otg_inst = acrtc->otg_inst;
-	dm->vblank_workqueue->enable = enable;
-	spin_unlock_irqrestore(&dm->vblank_lock, flags);
-	schedule_work(&dm->vblank_workqueue->mall_work);
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return -ENOMEM;
+
+	INIT_WORK(&work->work, vblank_control_worker);
+	work->dm = dm;
+	work->acrtc = acrtc;
+	work->enable = enable;
+
+	if (acrtc_state->stream) {
+		dc_stream_retain(acrtc_state->stream);
+		work->stream = acrtc_state->stream;
+	}
+
+	queue_work(dm->vblank_control_workqueue, &work->work);
 #endif
 
 	return 0;
@@ -6198,6 +6212,7 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 	const struct dc_link *link = aconnector->dc_link;
 	struct amdgpu_device *adev = drm_to_adev(connector->dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
+	int i;
 
 	/*
 	 * Call only if mst_mgr was iniitalized before since it's not done
@@ -6208,12 +6223,11 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
-
-	if ((link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) &&
-	    link->type != dc_connection_none &&
-	    dm->backlight_dev) {
-		backlight_device_unregister(dm->backlight_dev);
-		dm->backlight_dev = NULL;
+	for (i = 0; i < dm->num_of_edps; i++) {
+		if ((link == dm->backlight_link[i]) && dm->backlight_dev[i]) {
+			backlight_device_unregister(dm->backlight_dev[i]);
+			dm->backlight_dev[i] = NULL;
+		}
 	}
 #endif
 
@@ -7570,8 +7584,10 @@ static uint add_fs_modes(struct amdgpu_dm_connector *aconnector)
 	 * 60 	    - Commonly used
 	 * 48,72,96 - Multiples of 24
 	 */
-	const uint32_t common_rates[] = { 23976, 24000, 25000, 29970, 30000,
-					 48000, 50000, 60000, 72000, 96000 };
+	static const uint32_t common_rates[] = {
+		23976, 24000, 25000, 29970, 30000,
+		48000, 50000, 60000, 72000, 96000
+	};
 
 	/*
 	 * Find mode with highest refresh rate with the same resolution
@@ -8627,6 +8643,14 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	/* Update the planes if changed or disable if we don't have any. */
 	if ((planes_count || acrtc_state->active_planes == 0) &&
 		acrtc_state->stream) {
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		/*
+		 * If PSR or idle optimizations are enabled then flush out
+		 * any pending work before hardware programming.
+		 */
+		flush_workqueue(dm->vblank_control_workqueue);
+#endif
+
 		bundle->stream_update.stream = acrtc_state->stream;
 		if (new_pcrtc_state->mode_changed) {
 			bundle->stream_update.src = acrtc_state->stream->src;
@@ -8695,16 +8719,20 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
 				!acrtc_state->stream->link->psr_settings.psr_feature_enabled)
 			amdgpu_dm_link_setup_psr(acrtc_state->stream);
-		else if ((acrtc_state->update_type == UPDATE_TYPE_FAST) &&
-				acrtc_state->stream->link->psr_settings.psr_feature_enabled &&
-				!acrtc_state->stream->link->psr_settings.psr_allow_active) {
-			struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *)
-					acrtc_state->stream->dm_stream_context;
+
+		/* Decrement skip count when PSR is enabled and we're doing fast updates. */
+		if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
+		    acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
+			struct amdgpu_dm_connector *aconn =
+				(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
 
 			if (aconn->psr_skip_count > 0)
 				aconn->psr_skip_count--;
-			else
-				amdgpu_dm_psr_enable(acrtc_state->stream);
+
+			/* Allow PSR when skip count is 0. */
+			acrtc_attach->dm_irq_params.allow_psr_entry = !aconn->psr_skip_count;
+		} else {
+			acrtc_attach->dm_irq_params.allow_psr_entry = false;
 		}
 
 		mutex_unlock(&dm->dc_lock);
@@ -8953,8 +8981,12 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	if (dc_state) {
 		/* if there mode set or reset, disable eDP PSR */
-		if (mode_set_reset_required)
+		if (mode_set_reset_required) {
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			flush_workqueue(dm->vblank_control_workqueue);
+#endif
 			amdgpu_dm_psr_disable_all(dm);
+		}
 
 		dm_enable_per_frame_crtc_master_sync(dc_state);
 		mutex_lock(&dm->dc_lock);
@@ -9191,8 +9223,11 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||		\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 	/* restore the backlight level */
-	if (dm->backlight_dev && (amdgpu_dm_backlight_get_level(dm) != dm->brightness[0]))
-		amdgpu_dm_backlight_set_level(dm, dm->brightness[0]);
+	for (i = 0; i < dm->num_of_edps; i++) {
+		if (dm->backlight_dev[i] &&
+		    (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i]))
+			amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
+	}
 #endif
 	/*
 	 * send vblank event on all events not handled in flip and
@@ -10554,13 +10589,68 @@ static bool is_dp_capable_without_timing_msa(struct dc *dc,
 	return capable;
 }
 
-static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
+static bool dm_edid_parser_send_cea(struct amdgpu_display_manager *dm,
+		unsigned int offset,
+		unsigned int total_length,
+		uint8_t *data,
+		unsigned int length,
+		struct amdgpu_hdmi_vsdb_info *vsdb)
+{
+	bool res;
+	union dmub_rb_cmd cmd;
+	struct dmub_cmd_send_edid_cea *input;
+	struct dmub_cmd_edid_cea_output *output;
+
+	if (length > DMUB_EDID_CEA_DATA_CHUNK_BYTES)
+		return false;
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	input = &cmd.edid_cea.data.input;
+
+	cmd.edid_cea.header.type = DMUB_CMD__EDID_CEA;
+	cmd.edid_cea.header.sub_type = 0;
+	cmd.edid_cea.header.payload_bytes =
+		sizeof(cmd.edid_cea) - sizeof(cmd.edid_cea.header);
+	input->offset = offset;
+	input->length = length;
+	input->total_length = total_length;
+	memcpy(input->payload, data, length);
+
+	res = dc_dmub_srv_cmd_with_reply_data(dm->dc->ctx->dmub_srv, &cmd);
+	if (!res) {
+		DRM_ERROR("EDID CEA parser failed\n");
+		return false;
+	}
+
+	output = &cmd.edid_cea.data.output;
+
+	if (output->type == DMUB_CMD__EDID_CEA_ACK) {
+		if (!output->ack.success) {
+			DRM_ERROR("EDID CEA ack failed at offset %d\n",
+					output->ack.offset);
+		}
+	} else if (output->type == DMUB_CMD__EDID_CEA_AMD_VSDB) {
+		if (!output->amd_vsdb.vsdb_found)
+			return false;
+
+		vsdb->freesync_supported = output->amd_vsdb.freesync_supported;
+		vsdb->amd_vsdb_version = output->amd_vsdb.amd_vsdb_version;
+		vsdb->min_refresh_rate_hz = output->amd_vsdb.min_frame_rate;
+		vsdb->max_refresh_rate_hz = output->amd_vsdb.max_frame_rate;
+	} else {
+		DRM_WARN("Unknown EDID CEA parser results\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool parse_edid_cea_dmcu(struct amdgpu_display_manager *dm,
 		uint8_t *edid_ext, int len,
 		struct amdgpu_hdmi_vsdb_info *vsdb_info)
 {
 	int i;
-	struct amdgpu_device *adev = drm_to_adev(aconnector->base.dev);
-	struct dc *dc = adev->dm.dc;
 
 	/* send extension block to DMCU for parsing */
 	for (i = 0; i < len; i += 8) {
@@ -10568,14 +10658,14 @@ static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
 		int offset;
 
 		/* send 8 bytes a time */
-		if (!dc_edid_parser_send_cea(dc, i, len, &edid_ext[i], 8))
+		if (!dc_edid_parser_send_cea(dm->dc, i, len, &edid_ext[i], 8))
 			return false;
 
 		if (i+8 == len) {
 			/* EDID block sent completed, expect result */
 			int version, min_rate, max_rate;
 
-			res = dc_edid_parser_recv_amd_vsdb(dc, &version, &min_rate, &max_rate);
+			res = dc_edid_parser_recv_amd_vsdb(dm->dc, &version, &min_rate, &max_rate);
 			if (res) {
 				/* amd vsdb found */
 				vsdb_info->freesync_supported = 1;
@@ -10589,7 +10679,7 @@ static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
 		}
 
 		/* check for ack*/
-		res = dc_edid_parser_recv_cea_ack(dc, &offset);
+		res = dc_edid_parser_recv_cea_ack(dm->dc, &offset);
 		if (!res)
 			return false;
 	}
@@ -10597,6 +10687,34 @@ static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
 	return false;
 }
 
+static bool parse_edid_cea_dmub(struct amdgpu_display_manager *dm,
+		uint8_t *edid_ext, int len,
+		struct amdgpu_hdmi_vsdb_info *vsdb_info)
+{
+	int i;
+
+	/* send extension block to DMCU for parsing */
+	for (i = 0; i < len; i += 8) {
+		/* send 8 bytes a time */
+		if (!dm_edid_parser_send_cea(dm, i, len, &edid_ext[i], 8, vsdb_info))
+			return false;
+	}
+
+	return vsdb_info->freesync_supported;
+}
+
+static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
+		uint8_t *edid_ext, int len,
+		struct amdgpu_hdmi_vsdb_info *vsdb_info)
+{
+	struct amdgpu_device *adev = drm_to_adev(aconnector->base.dev);
+
+	if (adev->dm.dmub_srv)
+		return parse_edid_cea_dmub(&adev->dm, edid_ext, len, vsdb_info);
+	else
+		return parse_edid_cea_dmcu(&adev->dm, edid_ext, len, vsdb_info);
+}
+
 static int parse_hdmi_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 		struct edid *edid, struct amdgpu_hdmi_vsdb_info *vsdb_info)
 {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 9522d4ca299e..d1d353a7c77d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -60,6 +60,7 @@ enum aux_return_code_type;
 
 /* Forward declarations */
 struct amdgpu_device;
+struct amdgpu_crtc;
 struct drm_device;
 struct dc;
 struct amdgpu_bo;
@@ -86,16 +87,18 @@ struct dm_compressor_info {
 };
 
 /**
- * struct vblank_workqueue - Works to be executed in a separate thread during vblank
- * @mall_work: work for mall stutter
+ * struct vblank_control_work - Work data for vblank control
+ * @work: Kernel work data for the work event
  * @dm: amdgpu display manager device
- * @otg_inst: otg instance of which vblank is being set
- * @enable: true if enable vblank
+ * @acrtc: amdgpu CRTC instance for which the event has occurred
+ * @stream: DC stream for which the event has occurred
+ * @enable: true if enabling vblank
  */
-struct vblank_workqueue {
-	struct work_struct mall_work;
+struct vblank_control_work {
+	struct work_struct work;
 	struct amdgpu_display_manager *dm;
-	int otg_inst;
+	struct amdgpu_crtc *acrtc;
+	struct dc_stream_state *stream;
 	bool enable;
 };
 
@@ -365,13 +368,13 @@ struct amdgpu_display_manager {
 
 	spinlock_t irq_handler_list_table_lock;
 
-	struct backlight_device *backlight_dev;
+	struct backlight_device *backlight_dev[AMDGPU_DM_MAX_NUM_EDP];
 
 	const struct dc_link *backlight_link[AMDGPU_DM_MAX_NUM_EDP];
 
 	uint8_t num_of_edps;
 
-	struct amdgpu_dm_backlight_caps backlight_caps;
+	struct amdgpu_dm_backlight_caps backlight_caps[AMDGPU_DM_MAX_NUM_EDP];
 
 	struct mod_freesync *freesync_module;
 #ifdef CONFIG_DRM_AMD_DC_HDCP
@@ -380,11 +383,11 @@ struct amdgpu_display_manager {
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	/**
-	 * @vblank_workqueue:
+	 * @vblank_control_workqueue:
 	 *
-	 * amdgpu workqueue during vblank
+	 * Deferred work for vblank control events.
 	 */
-	struct vblank_workqueue *vblank_workqueue;
+	struct workqueue_struct *vblank_control_workqueue;
 #endif
 
 	struct drm_atomic_state *cached_state;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f1145086a468..87daa78a32b8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -197,29 +197,29 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 
 	rd_buf_ptr = rd_buf;
 
-	str_len = strlen("Current:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+	str_len = strlen("Current:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  0x%x  %d  ",
 			link->cur_link_settings.lane_count,
 			link->cur_link_settings.link_rate,
 			link->cur_link_settings.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Verified:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+	str_len = strlen("Verified:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  0x%x  %d  ",
 			link->verified_link_cap.lane_count,
 			link->verified_link_cap.link_rate,
 			link->verified_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Reported:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+	str_len = strlen("Reported:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  0x%x  %d  ",
 			link->reported_link_cap.lane_count,
 			link->reported_link_cap.link_rate,
 			link->reported_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Preferred:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+	str_len = strlen("Preferred:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  0x%x  %d\n",
 			link->preferred_link_setting.lane_count,
 			link->preferred_link_setting.link_rate,
 			link->preferred_link_setting.link_spread);
@@ -377,7 +377,7 @@ static ssize_t dp_phy_settings_read(struct file *f, char __user *buf,
 	if (!rd_buf)
 		return -EINVAL;
 
-	snprintf(rd_buf, rd_buf_size, "  %d  %d  %d  ",
+	snprintf(rd_buf, rd_buf_size, "  %d  %d  %d\n",
 			link->cur_lane_setting.VOLTAGE_SWING,
 			link->cur_lane_setting.PRE_EMPHASIS,
 			link->cur_lane_setting.POST_CURSOR2);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index e63c6885c757..c5f1dc3b5961 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -79,12 +79,12 @@ static uint8_t *psp_get_srm(struct psp_context *psp, uint32_t *srm_version, uint
 
 	struct ta_hdcp_shared_memory *hdcp_cmd;
 
-	if (!psp->hdcp_context.hdcp_initialized) {
+	if (!psp->hdcp_context.context.initialized) {
 		DRM_WARN("Failed to get hdcp srm. HDCP TA is not initialized.");
 		return NULL;
 	}
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP_GET_SRM;
@@ -105,12 +105,12 @@ static int psp_set_srm(struct psp_context *psp, uint8_t *srm, uint32_t srm_size,
 
 	struct ta_hdcp_shared_memory *hdcp_cmd;
 
-	if (!psp->hdcp_context.hdcp_initialized) {
+	if (!psp->hdcp_context.context.initialized) {
 		DRM_WARN("Failed to get hdcp srm. HDCP TA is not initialized.");
 		return -EINVAL;
 	}
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	memcpy(hdcp_cmd->in_msg.hdcp_set_srm.srm_buf, srm, srm_size);
@@ -414,12 +414,12 @@ static bool enable_assr(void *handle, struct dc_link *link)
 	struct ta_dtm_shared_memory *dtm_cmd;
 	bool res = true;
 
-	if (!psp->dtm_context.dtm_initialized) {
+	if (!psp->dtm_context.context.initialized) {
 		DRM_INFO("Failed to enable ASSR, DTM TA is not initialized.");
 		return false;
 	}
 
-	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->dtm_context.mutex);
 	memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
@@ -655,10 +655,8 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct
 		INIT_DELAYED_WORK(&hdcp_work[i].property_validate_dwork, event_property_validate);
 
 		hdcp_work[i].hdcp.config.psp.handle = &adev->psp;
-		if (dc->ctx->dce_version == DCN_VERSION_3_1) {
+		if (dc->ctx->dce_version == DCN_VERSION_3_1)
 			hdcp_work[i].hdcp.config.psp.caps.dtm_v3_supported = 1;
-			hdcp_work[i].hdcp.config.psp.caps.opm_state_query_supported = false;
-		}
 		hdcp_work[i].hdcp.config.ddc.handle = dc_get_link_at_index(dc, i);
 		hdcp_work[i].hdcp.config.ddc.funcs.write_i2c = lp_write_i2c;
 		hdcp_work[i].hdcp.config.ddc.funcs.read_i2c = lp_read_i2c;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
index f3b93ba69a27..79b5f9999fec 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -33,6 +33,7 @@ struct dm_irq_params {
 	struct mod_vrr_params vrr_params;
 	struct dc_stream_state *stream;
 	int active_planes;
+	bool allow_psr_entry;
 	struct mod_freesync_config freesync_config;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 5568d4e518e6..1bcba6943fd7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -213,6 +213,29 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 			drm_connector_update_edid_property(
 				&aconnector->base,
 				NULL);
+
+			DRM_DEBUG_KMS("Can't get EDID of %s. Add default remote sink.", connector->name);
+			if (!aconnector->dc_sink) {
+				struct dc_sink *dc_sink;
+				struct dc_sink_init_data init_params = {
+					.link = aconnector->dc_link,
+					.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
+
+				dc_sink = dc_link_add_remote_sink(
+					aconnector->dc_link,
+					NULL,
+					0,
+					&init_params);
+
+				if (!dc_sink) {
+					DRM_ERROR("Unable to add a remote sink\n");
+					return 0;
+				}
+
+				dc_sink->priv = aconnector;
+				aconnector->dc_sink = dc_sink;
+			}
+
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
index 46a33f64cf8e..fdcaea22b456 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
@@ -637,6 +637,30 @@ TRACE_EVENT(amdgpu_refresh_rate_track,
 		  __entry->refresh_rate_ns)
 );
 
+TRACE_EVENT(dcn_fpu,
+	    TP_PROTO(bool begin, const char *function, const int line, const int recursion_depth),
+	    TP_ARGS(begin, function, line, recursion_depth),
+
+	    TP_STRUCT__entry(
+			     __field(bool, begin)
+			     __field(const char *, function)
+			     __field(int, line)
+			     __field(int, recursion_depth)
+	    ),
+	    TP_fast_assign(
+			   __entry->begin = begin;
+			   __entry->function = function;
+			   __entry->line = line;
+			   __entry->recursion_depth = recursion_depth;
+	    ),
+	    TP_printk("%s: recursion_depth: %d: %s()+%d:",
+		      __entry->begin ? "begin" : "end",
+		      __entry->recursion_depth,
+		      __entry->function,
+		      __entry->line
+	    )
+);
+
 #endif /* _AMDGPU_DM_TRACE_H_ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
new file mode 100644
index 000000000000..c9f47d167472
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dc_trace.h"
+
+#if defined(CONFIG_X86)
+#include <asm/fpu/api.h>
+#elif defined(CONFIG_PPC64)
+#include <asm/switch_to.h>
+#include <asm/cputable.h>
+#endif
+
+/**
+ * DOC: DC FPU manipulation overview
+ *
+ * DC core uses FPU operations in multiple parts of the code, which requires a
+ * more specialized way to manage these areas' entrance. To fulfill this
+ * requirement, we created some wrapper functions that encapsulate
+ * kernel_fpu_begin/end to better fit our need in the display component. In
+ * summary, in this file, you can find functions related to FPU operation
+ * management.
+ */
+
+static DEFINE_PER_CPU(int, fpu_recursion_depth);
+
+/**
+ * dc_assert_fp_enabled - Check if FPU protection is enabled
+ *
+ * This function tells if the code is already under FPU protection or not. A
+ * function that works as an API for a set of FPU operations can use this
+ * function for checking if the caller invoked it after DC_FP_START(). For
+ * example, take a look at dcn2x.c file.
+ */
+inline void dc_assert_fp_enabled(void)
+{
+	int *pcpu, depth = 0;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	depth = *pcpu;
+	put_cpu_ptr(&fpu_recursion_depth);
+
+	ASSERT(depth > 1);
+}
+
+/**
+ * dc_fpu_begin - Enables FPU protection
+ * @function_name: A string containing the function name for debug purposes
+ *   (usually __func__)
+ *
+ * @line: A line number where DC_FP_START was invoked for debug purpose
+ *   (usually __LINE__)
+ *
+ * This function is responsible for managing the use of kernel_fpu_begin() with
+ * the advantage of providing an event trace for debugging.
+ *
+ * Note: Do not call this function directly; always use DC_FP_START().
+ */
+void dc_fpu_begin(const char *function_name, const int line)
+{
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu += 1;
+
+	if (*pcpu == 1) {
+#if defined(CONFIG_X86)
+		kernel_fpu_begin();
+#elif defined(CONFIG_PPC64)
+		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
+			preempt_disable();
+			enable_kernel_vsx();
+		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
+			preempt_disable();
+			enable_kernel_altivec();
+		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
+			preempt_disable();
+			enable_kernel_fp();
+		}
+#endif
+	}
+
+	TRACE_DCN_FPU(true, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
+}
+
+/**
+ * dc_fpu_end - Disable FPU protection
+ * @function_name: A string containing the function name for debug purposes
+ * @line: A-line number where DC_FP_END was invoked for debug purpose
+ *
+ * This function is responsible for managing the use of kernel_fpu_end() with
+ * the advantage of providing an event trace for debugging.
+ *
+ * Note: Do not call this function directly; always use DC_FP_END().
+ */
+void dc_fpu_end(const char *function_name, const int line)
+{
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu -= 1;
+	if (*pcpu <= 0) {
+#if defined(CONFIG_X86)
+		kernel_fpu_end();
+#elif defined(CONFIG_PPC64)
+		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
+			disable_kernel_vsx();
+			preempt_enable();
+		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
+			disable_kernel_altivec();
+			preempt_enable();
+		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
+			disable_kernel_fp();
+			preempt_enable();
+		}
+#endif
+	}
+
+	TRACE_DCN_FPU(false, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h
new file mode 100644
index 000000000000..b8275b397920
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_FPU_H__
+#define __DC_FPU_H__
+
+void dc_assert_fp_enabled(void);
+void dc_fpu_begin(const char *function_name, const int line);
+void dc_fpu_end(const char *function_name, const int line);
+
+#endif /* __DC_FPU_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
index e133edc587d3..76ec8ec92efd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
@@ -264,9 +264,9 @@ static void rv1_update_clocks(struct clk_mgr *clk_mgr_base,
 		if (pp_smu->set_hard_min_fclk_by_freq &&
 				pp_smu->set_hard_min_dcfclk_by_freq &&
 				pp_smu->set_min_deep_sleep_dcfclk) {
-			pp_smu->set_hard_min_fclk_by_freq(&pp_smu->pp_smu, new_clocks->fclk_khz / 1000);
-			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, new_clocks->dcfclk_khz / 1000);
-			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, (new_clocks->dcfclk_deep_sleep_khz + 999) / 1000);
+			pp_smu->set_hard_min_fclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->fclk_khz));
+			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->dcfclk_khz));
+			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->dcfclk_deep_sleep_khz));
 		}
 	}
 
@@ -284,9 +284,9 @@ static void rv1_update_clocks(struct clk_mgr *clk_mgr_base,
 		if (pp_smu->set_hard_min_fclk_by_freq &&
 				pp_smu->set_hard_min_dcfclk_by_freq &&
 				pp_smu->set_min_deep_sleep_dcfclk) {
-			pp_smu->set_hard_min_fclk_by_freq(&pp_smu->pp_smu, new_clocks->fclk_khz / 1000);
-			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, new_clocks->dcfclk_khz / 1000);
-			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, (new_clocks->dcfclk_deep_sleep_khz + 999) / 1000);
+			pp_smu->set_hard_min_fclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->fclk_khz));
+			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->dcfclk_khz));
+			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, khz_to_mhz_ceil(new_clocks->dcfclk_deep_sleep_khz));
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
index dbc7cde00433..fe18bb9e19aa 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
@@ -130,7 +130,7 @@ int rv1_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_di
 	actual_dispclk_set_mhz = rv1_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDispclkFreq,
-			requested_dispclk_khz / 1000);
+			khz_to_mhz_ceil(requested_dispclk_khz));
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
@@ -150,7 +150,7 @@ int rv1_vbios_smu_set_dprefclk(struct clk_mgr_internal *clk_mgr)
 	actual_dprefclk_set_mhz = rv1_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDprefclkFreq,
-			clk_mgr->base.dprefclk_khz / 1000);
+			khz_to_mhz_ceil(clk_mgr->base.dprefclk_khz));
 
 	/* TODO: add code for programing DP DTO, currently this is down by command table */
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index a5331b96f551..0d01aa9f15a6 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -253,20 +253,20 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) {
 		clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz;
 		if (pp_smu && pp_smu->set_hard_min_dcfclk_by_freq)
-			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, clk_mgr_base->clks.dcfclk_khz / 1000);
+			pp_smu->set_hard_min_dcfclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_khz));
 	}
 
 	if (should_set_clock(safe_to_lower,
 			new_clocks->dcfclk_deep_sleep_khz, clk_mgr_base->clks.dcfclk_deep_sleep_khz)) {
 		clk_mgr_base->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
 		if (pp_smu && pp_smu->set_min_deep_sleep_dcfclk)
-			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, clk_mgr_base->clks.dcfclk_deep_sleep_khz / 1000);
+			pp_smu->set_min_deep_sleep_dcfclk(&pp_smu->pp_smu, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_deep_sleep_khz));
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->socclk_khz, clk_mgr_base->clks.socclk_khz)) {
 		clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz;
 		if (pp_smu && pp_smu->set_hard_min_socclk_by_freq)
-			pp_smu->set_hard_min_socclk_by_freq(&pp_smu->pp_smu, clk_mgr_base->clks.socclk_khz / 1000);
+			pp_smu->set_hard_min_socclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(clk_mgr_base->clks.socclk_khz));
 	}
 
 	total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context);
@@ -281,7 +281,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (should_set_clock(safe_to_lower, new_clocks->dramclk_khz, clk_mgr_base->clks.dramclk_khz)) {
 		clk_mgr_base->clks.dramclk_khz = new_clocks->dramclk_khz;
 		if (pp_smu && pp_smu->set_hard_min_uclk_by_freq)
-			pp_smu->set_hard_min_uclk_by_freq(&pp_smu->pp_smu, clk_mgr_base->clks.dramclk_khz / 1000);
+			pp_smu->set_hard_min_uclk_by_freq(&pp_smu->pp_smu, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
@@ -306,7 +306,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 
 		clk_mgr_base->clks.disp_dpp_voltage_level_khz = new_clocks->disp_dpp_voltage_level_khz;
 		if (pp_smu && pp_smu->set_voltage_by_freq)
-			pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_DISPCLK, clk_mgr_base->clks.disp_dpp_voltage_level_khz / 1000);
+			pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_DISPCLK, khz_to_mhz_ceil(clk_mgr_base->clks.disp_dpp_voltage_level_khz));
 	}
 
 	if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) {
@@ -502,7 +502,7 @@ static void dcn2_notify_link_rate_change(struct clk_mgr *clk_mgr_base, struct dc
 
 	if (max_phyclk_req != clk_mgr_base->clks.phyclk_khz) {
 		clk_mgr_base->clks.phyclk_khz = max_phyclk_req;
-		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_PHYCLK, clk_mgr_base->clks.phyclk_khz / 1000);
+		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_PHYCLK, khz_to_mhz_ceil(clk_mgr_base->clks.phyclk_khz));
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index 7deeec9d1c7c..9f7eed6688c4 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -126,7 +126,7 @@ int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dis
 	actual_dispclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDispclkFreq,
-			requested_dispclk_khz / 1000);
+			khz_to_mhz_ceil(requested_dispclk_khz));
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
@@ -138,7 +138,7 @@ int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dis
 
 	// pmfw always set clock more than or equal requested clock
 	if (!IS_DIAG_DC(dc->ctx->dce_environment))
-		ASSERT(actual_dispclk_set_mhz >= requested_dispclk_khz / 1000);
+		ASSERT(actual_dispclk_set_mhz >= khz_to_mhz_ceil(requested_dispclk_khz));
 
 	return actual_dispclk_set_mhz * 1000;
 }
@@ -150,7 +150,7 @@ int rn_vbios_smu_set_dprefclk(struct clk_mgr_internal *clk_mgr)
 	actual_dprefclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDprefclkFreq,
-			clk_mgr->base.dprefclk_khz / 1000);
+			khz_to_mhz_ceil(clk_mgr->base.dprefclk_khz));
 
 	/* TODO: add code for programing DP DTO, currently this is down by command table */
 
@@ -167,7 +167,7 @@ int rn_vbios_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int reque
 	actual_dcfclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetHardMinDcfclkByFreq,
-			requested_dcfclk_khz / 1000);
+			khz_to_mhz_ceil(requested_dcfclk_khz));
 
 	return actual_dcfclk_set_mhz * 1000;
 }
@@ -182,7 +182,7 @@ int rn_vbios_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int
 	actual_min_ds_dcfclk_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetMinDeepSleepDcfclk,
-			requested_min_ds_dcfclk_khz / 1000);
+			khz_to_mhz_ceil(requested_min_ds_dcfclk_khz));
 
 	return actual_min_ds_dcfclk_mhz * 1000;
 }
@@ -192,7 +192,7 @@ void rn_vbios_smu_set_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phy
 	rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetPhyclkVoltageByFreq,
-			requested_phyclk_khz / 1000);
+			khz_to_mhz_ceil(requested_phyclk_khz));
 }
 
 int rn_vbios_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_khz)
@@ -203,10 +203,10 @@ int rn_vbios_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_
 	actual_dppclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDppclkFreq,
-			requested_dpp_khz / 1000);
+			khz_to_mhz_ceil(requested_dpp_khz));
 
 	if (!IS_DIAG_DC(dc->ctx->dce_environment))
-		ASSERT(actual_dppclk_set_mhz >= requested_dpp_khz / 1000);
+		ASSERT(actual_dppclk_set_mhz >= khz_to_mhz_ceil(requested_dpp_khz));
 
 	return actual_dppclk_set_mhz * 1000;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index af7004b770ae..1861a147a7fa 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -284,12 +284,12 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) {
 		clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz;
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DCEFCLK, clk_mgr_base->clks.dcfclk_khz / 1000);
+		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DCEFCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_khz));
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_deep_sleep_khz, clk_mgr_base->clks.dcfclk_deep_sleep_khz)) {
 		clk_mgr_base->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
-		dcn30_smu_set_min_deep_sleep_dcef_clk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz / 1000);
+		dcn30_smu_set_min_deep_sleep_dcef_clk(clk_mgr, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_deep_sleep_khz));
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->socclk_khz, clk_mgr_base->clks.socclk_khz))
@@ -317,20 +317,20 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 	/* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */
 	if (clk_mgr_base->clks.p_state_change_support &&
 			(update_uclk || !clk_mgr_base->clks.prev_p_state_change_support))
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, clk_mgr_base->clks.dramclk_khz / 1000);
+		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
 
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) {
 		if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz)
 			dpp_clock_lowered = true;
 
 		clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz;
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_PIXCLK, clk_mgr_base->clks.dppclk_khz / 1000);
+		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_PIXCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dppclk_khz));
 		update_dppclk = true;
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DISPCLK, clk_mgr_base->clks.dispclk_khz / 1000);
+		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DISPCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dispclk_khz));
 		update_dispclk = true;
 	}
 
@@ -396,12 +396,17 @@ static void dcn3_set_hard_min_memclk(struct clk_mgr *clk_mgr_base, bool current_
 	if (!clk_mgr->smu_present)
 		return;
 
-	if (current_mode)
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
-				clk_mgr_base->clks.dramclk_khz / 1000);
-	else
+	if (current_mode) {
+		if (clk_mgr_base->clks.p_state_change_support)
+			dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
+					khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
+		else
+			dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
+					clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz);
+	} else {
 		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
 				clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz);
+	}
 }
 
 /* Set max memclk to highest DPM value */
@@ -489,7 +494,7 @@ static void dcn30_notify_link_rate_change(struct clk_mgr *clk_mgr_base, struct d
 
 	if (max_phyclk_req != clk_mgr_base->clks.phyclk_khz) {
 		clk_mgr_base->clks.phyclk_khz = max_phyclk_req;
-		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_PHYCLK, clk_mgr_base->clks.phyclk_khz / 1000);
+		dcn30_smu_set_hard_min_by_freq(clk_mgr, PPCLK_PHYCLK, khz_to_mhz_ceil(clk_mgr_base->clks.phyclk_khz));
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c
index 07774fa2c2cf..6ea642615854 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c
@@ -133,7 +133,7 @@ int dcn301_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispc
 	actual_dispclk_set_mhz = dcn301_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDispclkFreq,
-			requested_dispclk_khz / 1000);
+			khz_to_mhz_ceil(requested_dispclk_khz));
 
 	return actual_dispclk_set_mhz * 1000;
 }
@@ -147,7 +147,7 @@ int dcn301_smu_set_dprefclk(struct clk_mgr_internal *clk_mgr)
 	actual_dprefclk_set_mhz = dcn301_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDprefclkFreq,
-			clk_mgr->base.dprefclk_khz / 1000);
+			khz_to_mhz_ceil(clk_mgr->base.dprefclk_khz));
 
 	/* TODO: add code for programing DP DTO, currently this is down by command table */
 
@@ -163,7 +163,7 @@ int dcn301_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int request
 	actual_dcfclk_set_mhz = dcn301_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetHardMinDcfclkByFreq,
-			requested_dcfclk_khz / 1000);
+			khz_to_mhz_ceil(requested_dcfclk_khz));
 
 	return actual_dcfclk_set_mhz * 1000;
 }
@@ -177,7 +177,7 @@ int dcn301_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int r
 	actual_min_ds_dcfclk_mhz = dcn301_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetMinDeepSleepDcfclk,
-			requested_min_ds_dcfclk_khz / 1000);
+			khz_to_mhz_ceil(requested_min_ds_dcfclk_khz));
 
 	return actual_min_ds_dcfclk_mhz * 1000;
 }
@@ -191,7 +191,7 @@ int dcn301_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_kh
 	actual_dppclk_set_mhz = dcn301_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDppclkFreq,
-			requested_dpp_khz / 1000);
+			khz_to_mhz_ceil(requested_dpp_khz));
 
 	return actual_dppclk_set_mhz * 1000;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index c636b589d69d..7046da14bb2a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -114,7 +114,7 @@ void vg_update_clocks(struct clk_mgr *clk_mgr_base,
 
 			display_count = vg_get_active_display_cnt_wa(dc, context);
 			/* if we can go lower, go lower */
-			if (display_count == 0) {
+			if (display_count == 0 && !IS_DIAG_DC(dc->ctx->dce_environment)) {
 				union display_idle_optimization_u idle_info = { 0 };
 
 				idle_info.idle_info.df_request_disabled = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c
index dad4a4c18bcf..8c2b77eb9459 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c
@@ -147,7 +147,7 @@ int dcn31_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispcl
 	actual_dispclk_set_mhz = dcn31_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDispclkFreq,
-			(requested_dispclk_khz + 999) / 1000);
+			khz_to_mhz_ceil(requested_dispclk_khz));
 
 	return actual_dispclk_set_mhz * 1000;
 }
@@ -162,7 +162,7 @@ int dcn31_smu_set_dprefclk(struct clk_mgr_internal *clk_mgr)
 	actual_dprefclk_set_mhz = dcn31_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDprefclkFreq,
-			(clk_mgr->base.dprefclk_khz + 999) / 1000);
+			khz_to_mhz_ceil(clk_mgr->base.dprefclk_khz));
 
 	/* TODO: add code for programing DP DTO, currently this is down by command table */
 
@@ -182,7 +182,7 @@ int dcn31_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int requeste
 	actual_dcfclk_set_mhz = dcn31_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetHardMinDcfclkByFreq,
-			(requested_dcfclk_khz + 999) / 1000);
+			khz_to_mhz_ceil(requested_dcfclk_khz));
 
 	return actual_dcfclk_set_mhz * 1000;
 }
@@ -200,7 +200,7 @@ int dcn31_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int re
 	actual_min_ds_dcfclk_mhz = dcn31_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetMinDeepSleepDcfclk,
-			(requested_min_ds_dcfclk_khz + 999) / 1000);
+			khz_to_mhz_ceil(requested_min_ds_dcfclk_khz));
 
 	return actual_min_ds_dcfclk_mhz * 1000;
 }
@@ -215,7 +215,7 @@ int dcn31_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_khz
 	actual_dppclk_set_mhz = dcn31_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDppclkFreq,
-			(requested_dpp_khz + 999) / 1000);
+			khz_to_mhz_ceil(requested_dpp_khz));
 
 	return actual_dppclk_set_mhz * 1000;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index a30283fa5173..c798c65d4276 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1481,6 +1481,22 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc,
 	return true;
 }
 
+static inline bool should_update_pipe_for_stream(
+		struct dc_state *context,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_stream_state *stream)
+{
+	return (pipe_ctx->stream && pipe_ctx->stream == stream);
+}
+
+static inline bool should_update_pipe_for_plane(
+		struct dc_state *context,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_plane_state *plane_state)
+{
+	return (pipe_ctx->plane_state == plane_state);
+}
+
 void dc_enable_stereo(
 	struct dc *dc,
 	struct dc_state *context,
@@ -1491,12 +1507,15 @@ void dc_enable_stereo(
 	struct pipe_ctx *pipe;
 
 	for (i = 0; i < MAX_PIPES; i++) {
-		if (context != NULL)
+		if (context != NULL) {
 			pipe = &context->res_ctx.pipe_ctx[i];
-		else
+		} else {
+			context = dc->current_state;
 			pipe = &dc->current_state->res_ctx.pipe_ctx[i];
-		for (j = 0 ; pipe && j < stream_count; j++)  {
-			if (streams[j] && streams[j] == pipe->stream &&
+		}
+
+		for (j = 0; pipe && j < stream_count; j++)  {
+			if (should_update_pipe_for_stream(context, pipe, streams[j]) &&
 				dc->hwss.setup_stereo)
 				dc->hwss.setup_stereo(pipe, dc);
 		}
@@ -2629,6 +2648,7 @@ static void commit_planes_for_stream(struct dc *dc,
 {
 	int i, j;
 	struct pipe_ctx *top_pipe_to_program = NULL;
+	bool should_lock_all_pipes = (update_type != UPDATE_TYPE_FAST);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	dc_z10_restore(dc);
@@ -2700,7 +2720,7 @@ static void commit_planes_for_stream(struct dc *dc,
 						top_pipe_to_program->stream_res.tg);
 		}
 
-	if ((update_type != UPDATE_TYPE_FAST) && dc->hwss.interdependent_update_lock)
+	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock)
 		dc->hwss.interdependent_update_lock(dc, context, true);
 	else
 		/* Lock the top pipe while updating plane addrs, since freesync requires
@@ -2723,7 +2743,7 @@ static void commit_planes_for_stream(struct dc *dc,
 		if (dc->hwss.program_front_end_for_ctx)
 			dc->hwss.program_front_end_for_ctx(dc, context);
 
-		if ((update_type != UPDATE_TYPE_FAST) && dc->hwss.interdependent_update_lock)
+		if (should_lock_all_pipes && dc->hwss.interdependent_update_lock)
 			dc->hwss.interdependent_update_lock(dc, context, false);
 		else
 			dc->hwss.pipe_control_lock(dc, top_pipe_to_program, false);
@@ -2739,14 +2759,14 @@ static void commit_planes_for_stream(struct dc *dc,
 				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 				if (!pipe_ctx->plane_state)
 					continue;
-				if (pipe_ctx->plane_state != plane_state)
+				if (should_update_pipe_for_plane(context, pipe_ctx, plane_state))
 					continue;
-				plane_state->triplebuffer_flips = false;
+				pipe_ctx->plane_state->triplebuffer_flips = false;
 				if (update_type == UPDATE_TYPE_FAST &&
 					dc->hwss.program_triplebuffer != NULL &&
-					!plane_state->flip_immediate && dc->debug.enable_tri_buf) {
+					!pipe_ctx->plane_state->flip_immediate && dc->debug.enable_tri_buf) {
 						/*triple buffer for VUpdate  only*/
-						plane_state->triplebuffer_flips = true;
+						pipe_ctx->plane_state->triplebuffer_flips = true;
 				}
 			}
 			if (update_type == UPDATE_TYPE_FULL) {
@@ -2762,8 +2782,7 @@ static void commit_planes_for_stream(struct dc *dc,
 
 		if (!pipe_ctx->top_pipe &&
 			!pipe_ctx->prev_odm_pipe &&
-			pipe_ctx->stream &&
-			pipe_ctx->stream == stream) {
+			should_update_pipe_for_stream(context, pipe_ctx, stream)) {
 			struct dc_stream_status *stream_status = NULL;
 
 			if (!pipe_ctx->plane_state)
@@ -2816,15 +2835,15 @@ static void commit_planes_for_stream(struct dc *dc,
 				for (j = 0; j < dc->res_pool->pipe_count; j++) {
 					struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 
-					if (pipe_ctx->stream != stream)
+					if (!should_update_pipe_for_stream(context, pipe_ctx, stream))
 						continue;
 
-					if (pipe_ctx->plane_state != plane_state)
+					if (!should_update_pipe_for_plane(context, pipe_ctx, plane_state))
 						continue;
 
 					// GSL has to be used for flip immediate
 					dc->hwss.set_flip_control_gsl(pipe_ctx,
-							plane_state->flip_immediate);
+							pipe_ctx->plane_state->flip_immediate);
 				}
 			}
 
@@ -2835,25 +2854,26 @@ static void commit_planes_for_stream(struct dc *dc,
 			for (j = 0; j < dc->res_pool->pipe_count; j++) {
 				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 
-				if (pipe_ctx->stream != stream)
+				if (!should_update_pipe_for_stream(context, pipe_ctx, stream))
 					continue;
 
-				if (pipe_ctx->plane_state != plane_state)
+				if (!should_update_pipe_for_plane(context, pipe_ctx, plane_state))
 					continue;
+
 				/*program triple buffer after lock based on flip type*/
 				if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
 					/*only enable triplebuffer for  fast_update*/
 					dc->hwss.program_triplebuffer(
-						dc, pipe_ctx, plane_state->triplebuffer_flips);
+						dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
 				}
-				if (srf_updates[i].flip_addr)
+				if (pipe_ctx->plane_state->update_flags.bits.addr_update)
 					dc->hwss.update_plane_addr(dc, pipe_ctx);
 			}
 		}
 
 	}
 
-	if ((update_type != UPDATE_TYPE_FAST) && dc->hwss.interdependent_update_lock)
+	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock)
 		dc->hwss.interdependent_update_lock(dc, context, false);
 	else
 		dc->hwss.pipe_control_lock(dc, top_pipe_to_program, false);
@@ -2897,7 +2917,7 @@ static void commit_planes_for_stream(struct dc *dc,
 			continue;
 
 		if (pipe_ctx->bottom_pipe || pipe_ctx->next_odm_pipe ||
-				!pipe_ctx->stream || pipe_ctx->stream != stream ||
+				!pipe_ctx->stream || !should_update_pipe_for_stream(context, pipe_ctx, stream) ||
 				!pipe_ctx->plane_state->update_flags.bits.addr_update ||
 				pipe_ctx->plane_state->skip_manual_trigger)
 			continue;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 6132b645bfd1..8bd7f42a8053 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -541,6 +541,7 @@ static void link_disconnect_sink(struct dc_link *link)
 	}
 
 	link->dpcd_sink_count = 0;
+	//link->dpcd_caps.dpcd_rev.raw = 0;
 }
 
 static void link_disconnect_remap(struct dc_sink *prev_sink, struct dc_link *link)
@@ -742,6 +743,7 @@ static bool detect_dp(struct dc_link *link,
 								sink_caps,
 								audio_support);
 		link->dpcd_caps.dongle_type = sink_caps->dongle_type;
+		link->dpcd_caps.dpcd_rev.raw = 0;
 	}
 
 	return true;
@@ -1663,6 +1665,12 @@ struct dc_link *link_create(const struct link_init_data *init_params)
 	if (false == dc_link_construct(link, init_params))
 		goto construct_fail;
 
+	/*
+	 * Must use preferred_link_setting, not reported_link_cap or verified_link_cap,
+	 * since struct preferred_link_setting won't be reset after S3.
+	 */
+	link->preferred_link_setting.dpcd_source_device_specific_field_support = true;
+
 	return link;
 
 construct_fail:
@@ -3509,61 +3517,6 @@ void dc_link_enable_hpd_filter(struct dc_link *link, bool enable)
 	}
 }
 
-uint32_t dc_bandwidth_in_kbps_from_timing(
-	const struct dc_crtc_timing *timing)
-{
-	uint32_t bits_per_channel = 0;
-	uint32_t kbps;
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (timing->flags.DSC)
-		return dc_dsc_stream_bandwidth_in_kbps(timing,
-				timing->dsc_cfg.bits_per_pixel,
-				timing->dsc_cfg.num_slices_h,
-				timing->dsc_cfg.is_dp);
-#endif
-
-	switch (timing->display_color_depth) {
-	case COLOR_DEPTH_666:
-		bits_per_channel = 6;
-		break;
-	case COLOR_DEPTH_888:
-		bits_per_channel = 8;
-		break;
-	case COLOR_DEPTH_101010:
-		bits_per_channel = 10;
-		break;
-	case COLOR_DEPTH_121212:
-		bits_per_channel = 12;
-		break;
-	case COLOR_DEPTH_141414:
-		bits_per_channel = 14;
-		break;
-	case COLOR_DEPTH_161616:
-		bits_per_channel = 16;
-		break;
-	default:
-		ASSERT(bits_per_channel != 0);
-		bits_per_channel = 8;
-		break;
-	}
-
-	kbps = timing->pix_clk_100hz / 10;
-	kbps *= bits_per_channel;
-
-	if (timing->flags.Y_ONLY != 1) {
-		/*Only YOnly make reduce bandwidth by 1/3 compares to RGB*/
-		kbps *= 3;
-		if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
-			kbps /= 2;
-		else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
-			kbps = kbps * 2 / 3;
-	}
-
-	return kbps;
-
-}
-
 void dc_link_set_drive_settings(struct dc *dc,
 				struct link_training_settings *lt_settings,
 				const struct dc_link *link)
@@ -3769,3 +3722,58 @@ bool dc_link_should_enable_fec(const struct dc_link *link)
 
 	return ret;
 }
+
+uint32_t dc_bandwidth_in_kbps_from_timing(
+		const struct dc_crtc_timing *timing)
+{
+	uint32_t bits_per_channel = 0;
+	uint32_t kbps;
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (timing->flags.DSC)
+		return dc_dsc_stream_bandwidth_in_kbps(timing,
+				timing->dsc_cfg.bits_per_pixel,
+				timing->dsc_cfg.num_slices_h,
+				timing->dsc_cfg.is_dp);
+#endif
+
+	switch (timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+		bits_per_channel = 6;
+		break;
+	case COLOR_DEPTH_888:
+		bits_per_channel = 8;
+		break;
+	case COLOR_DEPTH_101010:
+		bits_per_channel = 10;
+		break;
+	case COLOR_DEPTH_121212:
+		bits_per_channel = 12;
+		break;
+	case COLOR_DEPTH_141414:
+		bits_per_channel = 14;
+		break;
+	case COLOR_DEPTH_161616:
+		bits_per_channel = 16;
+		break;
+	default:
+		ASSERT(bits_per_channel != 0);
+		bits_per_channel = 8;
+		break;
+	}
+
+	kbps = timing->pix_clk_100hz / 10;
+	kbps *= bits_per_channel;
+
+	if (timing->flags.Y_ONLY != 1) {
+		/*Only YOnly make reduce bandwidth by 1/3 compares to RGB*/
+		kbps *= 3;
+		if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			kbps /= 2;
+		else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			kbps = kbps * 2 / 3;
+	}
+
+	return kbps;
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index a6d0fd24fd02..cd025c12f17b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1241,29 +1241,15 @@ enum link_training_result dp_check_link_loss_status(
 static inline void decide_8b_10b_training_settings(
 	 struct dc_link *link,
 	const struct dc_link_settings *link_setting,
-	const struct dc_link_training_overrides *overrides,
 	struct link_training_settings *lt_settings)
 {
-	uint32_t lane;
-
 	memset(lt_settings, '\0', sizeof(struct link_training_settings));
 
 	/* Initialize link settings */
 	lt_settings->link_settings.use_link_rate_set = link_setting->use_link_rate_set;
 	lt_settings->link_settings.link_rate_set = link_setting->link_rate_set;
-
-	if (link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN)
-		lt_settings->link_settings.link_rate = link->preferred_link_setting.link_rate;
-	else
-		lt_settings->link_settings.link_rate = link_setting->link_rate;
-
-	if (link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN)
-		lt_settings->link_settings.lane_count = link->preferred_link_setting.lane_count;
-	else
-		lt_settings->link_settings.lane_count = link_setting->lane_count;
-
-	/*@todo[vdevulap] move SS to LS, should not be handled by displaypath*/
-
+	lt_settings->link_settings.link_rate = link_setting->link_rate;
+	lt_settings->link_settings.lane_count = link_setting->lane_count;
 	/* TODO hard coded to SS for now
 	 * lt_settings.link_settings.link_spread =
 	 * dal_display_path_is_ss_supported(
@@ -1271,30 +1257,52 @@ static inline void decide_8b_10b_training_settings(
 	 * LINK_SPREAD_05_DOWNSPREAD_30KHZ :
 	 * LINK_SPREAD_DISABLED;
 	 */
-	/* Initialize link spread */
-	if (link->dp_ss_off)
-		lt_settings->link_settings.link_spread = LINK_SPREAD_DISABLED;
-	else if (overrides->downspread != NULL)
-		lt_settings->link_settings.link_spread
-			= *overrides->downspread
-			? LINK_SPREAD_05_DOWNSPREAD_30KHZ
-			: LINK_SPREAD_DISABLED;
-	else
-		lt_settings->link_settings.link_spread = LINK_SPREAD_05_DOWNSPREAD_30KHZ;
-
+	lt_settings->link_settings.link_spread = link->dp_ss_off ?
+			LINK_SPREAD_DISABLED : LINK_SPREAD_05_DOWNSPREAD_30KHZ;
 	lt_settings->lttpr_mode = link->lttpr_mode;
+	lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting);
+	lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting);
+	lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting);
+	lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting);
+	lt_settings->enhanced_framing = 1;
+	lt_settings->should_set_fec_ready = true;
+}
+
+void dp_decide_training_settings(
+		struct dc_link *link,
+		const struct dc_link_settings *link_settings,
+		struct link_training_settings *lt_settings)
+{
+	if (dp_get_link_encoding_format(link_settings) == DP_8b_10b_ENCODING)
+		decide_8b_10b_training_settings(link, link_settings, lt_settings);
+}
+
+static void override_training_settings(
+		struct dc_link *link,
+		const struct dc_link_training_overrides *overrides,
+		struct link_training_settings *lt_settings)
+{
+	uint32_t lane;
+
+	/* Override link settings */
+	if (link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN)
+		lt_settings->link_settings.link_rate = link->preferred_link_setting.link_rate;
+	if (link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN)
+		lt_settings->link_settings.lane_count = link->preferred_link_setting.lane_count;
+
+	/* Override link spread */
+	if (!link->dp_ss_off && overrides->downspread != NULL)
+		lt_settings->link_settings.link_spread = *overrides->downspread ?
+				LINK_SPREAD_05_DOWNSPREAD_30KHZ
+				: LINK_SPREAD_DISABLED;
 
-	/* Initialize lane settings overrides */
+	/* Override lane settings */
 	if (overrides->voltage_swing != NULL)
 		lt_settings->voltage_swing = overrides->voltage_swing;
-
 	if (overrides->pre_emphasis != NULL)
 		lt_settings->pre_emphasis = overrides->pre_emphasis;
-
 	if (overrides->post_cursor2 != NULL)
 		lt_settings->post_cursor2 = overrides->post_cursor2;
-
-	/* Initialize lane settings (VS/PE/PC2) */
 	for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) {
 		lt_settings->lane_settings[lane].VOLTAGE_SWING =
 			lt_settings->voltage_swing != NULL ?
@@ -1313,45 +1321,22 @@ static inline void decide_8b_10b_training_settings(
 	/* Initialize training timings */
 	if (overrides->cr_pattern_time != NULL)
 		lt_settings->cr_pattern_time = *overrides->cr_pattern_time;
-	else
-		lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting);
 
 	if (overrides->eq_pattern_time != NULL)
 		lt_settings->eq_pattern_time = *overrides->eq_pattern_time;
-	else
-		lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting);
 
 	if (overrides->pattern_for_cr != NULL)
 		lt_settings->pattern_for_cr = *overrides->pattern_for_cr;
-	else
-		lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting);
 	if (overrides->pattern_for_eq != NULL)
 		lt_settings->pattern_for_eq = *overrides->pattern_for_eq;
-	else
-		lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting);
 
 	if (overrides->enhanced_framing != NULL)
 		lt_settings->enhanced_framing = *overrides->enhanced_framing;
-	else
-		lt_settings->enhanced_framing = 1;
 
 	if (link->preferred_training_settings.fec_enable != NULL)
 		lt_settings->should_set_fec_ready = *link->preferred_training_settings.fec_enable;
-	else
-		lt_settings->should_set_fec_ready = true;
-}
-
-void dp_decide_training_settings(
-		struct dc_link *link,
-		const struct dc_link_settings *link_settings,
-		const struct dc_link_training_overrides *overrides,
-		struct link_training_settings *lt_settings)
-{
-	if (dp_get_link_encoding_format(link_settings) == DP_8b_10b_ENCODING)
-		decide_8b_10b_training_settings(link, link_settings, overrides, lt_settings);
 }
 
-
 uint8_t dp_convert_to_count(uint8_t lttpr_repeater_count)
 {
 	switch (lttpr_repeater_count) {
@@ -1581,6 +1566,9 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	dp_decide_training_settings(
 			link,
 			link_setting,
+			&lt_settings);
+	override_training_settings(
+			link,
 			&link->preferred_training_settings,
 			&lt_settings);
 
@@ -1727,6 +1715,9 @@ enum link_training_result dc_link_dp_perform_link_training(
 	dp_decide_training_settings(
 			link,
 			link_settings,
+			&lt_settings);
+	override_training_settings(
+			link,
 			&link->preferred_training_settings,
 			&lt_settings);
 
@@ -1939,11 +1930,13 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	bool fec_enable = false;
 
 	dp_decide_training_settings(
-		link,
-		link_settings,
-		lt_overrides,
-		&lt_settings);
-
+			link,
+			link_settings,
+			&lt_settings);
+	override_training_settings(
+			link,
+			lt_overrides,
+			&lt_settings);
 	/* Setup MST Mode */
 	if (lt_overrides->mst_enable)
 		set_dp_mst_mode(link, *lt_overrides->mst_enable);
@@ -4776,10 +4769,18 @@ void dpcd_set_source_specific_data(struct dc_link *link)
 
 			uint8_t hblank_size = (uint8_t)link->dc->caps.min_horizontal_blanking_period;
 
-			result_write_min_hblank = core_link_write_dpcd(link,
-				DP_SOURCE_MINIMUM_HBLANK_SUPPORTED, (uint8_t *)(&hblank_size),
-				sizeof(hblank_size));
+			if (link->preferred_link_setting.dpcd_source_device_specific_field_support) {
+				result_write_min_hblank = core_link_write_dpcd(link,
+					DP_SOURCE_MINIMUM_HBLANK_SUPPORTED, (uint8_t *)(&hblank_size),
+					sizeof(hblank_size));
+
+				if (result_write_min_hblank == DC_ERROR_UNEXPECTED)
+					link->preferred_link_setting.dpcd_source_device_specific_field_support = false;
+			} else {
+				DC_LOG_DC("Sink device does not support 00340h DPCD write. Skipping on purpose.\n");
+			}
 		}
+
 		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
 							WPP_BIT_FLAG_DC_DETECTION_DP_CAPS,
 							"result=%u link_index=%u enum dce_version=%d DPCD=0x%04X min_hblank=%u branch_dev_id=0x%x branch_dev_name='%c%c%c%c%c%c'",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c
index fe234760a0f5..72970e49800a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c
@@ -1,3 +1,28 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
 #include <inc/core_status.h>
 #include <dc_link.h>
 #include <inc/link_hwss.h>
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
index 1a89d565c92e..de80a9ea4cfa 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
@@ -305,7 +305,7 @@ struct link_encoder *link_enc_cfg_get_next_avail_link_enc(
 	const struct dc_state *state)
 {
 	struct link_encoder *link_enc = NULL;
-	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
+	enum engine_id eng_id;
 
 	eng_id = find_first_avail_link_enc(dc->ctx, state);
 	if (eng_id != ENGINE_ID_UNKNOWN)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 1596f6b7fed7..a60396d5be44 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1030,7 +1030,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 
 	/* Timing borders are part of vactive that we are also supposed to skip in addition
 	 * to any stream dst offset. Since dm logic assumes dst is in addressable
-	 * space we need to add the the left and top borders to dst offsets temporarily.
+	 * space we need to add the left and top borders to dst offsets temporarily.
 	 * TODO: fix in DM, stream dst is supposed to be in vactive
 	 */
 	pipe_ctx->stream->dst.x += timing->h_border_left;
@@ -1051,6 +1051,11 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	/* depends on scaling ratios and recout, does not calculate offset yet */
 	calculate_viewport_size(pipe_ctx);
 
+	/* Stopgap for validation of ODM + MPO on one side of screen case */
+	if (pipe_ctx->plane_res.scl_data.viewport.height < 1 ||
+			pipe_ctx->plane_res.scl_data.viewport.width < 1)
+		return false;
+
 	/*
 	 * LB calculations depend on vp size, h/v_active and scaling ratios
 	 * Setting line buffer pixel depth to 24bpp yields banding
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stat.c b/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
index 31761f3595a6..28ef9760fa34 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
@@ -62,3 +62,27 @@ void dc_stat_get_dmub_notification(const struct dc *dc, struct dmub_notification
 	status = dmub_srv_stat_get_notification(dmub, notify);
 	ASSERT(status == DMUB_STATUS_OK);
 }
+
+/**
+ *****************************************************************************
+ *  Function: dc_stat_get_dmub_dataout
+ *
+ *  @brief
+ *		Calls dmub layer to retrieve dmub gpint dataout
+ *
+ *  @param
+ *		[in] dc: dc structure
+ *		[in] dataout: dmub gpint dataout
+ *
+ *  @return
+ *     None
+ *****************************************************************************
+ */
+void dc_stat_get_dmub_dataout(const struct dc *dc, uint32_t *dataout)
+{
+	struct dmub_srv *dmub = dc->ctx->dmub_srv->dmub;
+	enum dmub_status status;
+
+	status = dmub_srv_get_gpint_dataout(dmub, dataout);
+	ASSERT(status == DMUB_STATUS_OK);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 45931ee14a6e..f0f54f4d3d9b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -221,6 +221,9 @@ struct dc_stream_status *dc_stream_get_status_from_state(
 {
 	uint8_t i;
 
+	if (state == NULL)
+		return NULL;
+
 	for (i = 0; i < state->stream_count; i++) {
 		if (stream == state->streams[i])
 			return &state->stream_status[i];
@@ -243,6 +246,40 @@ struct dc_stream_status *dc_stream_get_status(
 	return dc_stream_get_status_from_state(dc->current_state, stream);
 }
 
+static void program_cursor_attributes(
+	struct dc *dc,
+	struct dc_stream_state *stream,
+	const struct dc_cursor_attributes *attributes)
+{
+	int i;
+	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
+
+	if (!stream)
+		return;
+
+	res_ctx = &dc->current_state->res_ctx;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
+
+		if (pipe_ctx->stream != stream)
+			continue;
+
+		if (!pipe_to_program) {
+			pipe_to_program = pipe_ctx;
+			dc->hwss.cursor_lock(dc, pipe_to_program, true);
+		}
+
+		dc->hwss.set_cursor_attribute(pipe_ctx);
+		if (dc->hwss.set_cursor_sdr_white_level)
+			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+	}
+
+	if (pipe_to_program)
+		dc->hwss.cursor_lock(dc, pipe_to_program, false);
+}
+
 #ifndef TRIM_FSFT
 /*
  * dc_optimize_timing_for_fsft() - dc to optimize timing
@@ -267,10 +304,7 @@ bool dc_stream_set_cursor_attributes(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_attributes *attributes)
 {
-	int i;
 	struct dc  *dc;
-	struct resource_context *res_ctx;
-	struct pipe_ctx *pipe_to_program = NULL;
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	bool reset_idle_optimizations = false;
 #endif
@@ -290,7 +324,6 @@ bool dc_stream_set_cursor_attributes(
 	}
 
 	dc = stream->ctx->dc;
-	res_ctx = &dc->current_state->res_ctx;
 	stream->cursor_attributes = *attributes;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
@@ -302,11 +335,39 @@ bool dc_stream_set_cursor_attributes(
 	}
 
 #endif
+	program_cursor_attributes(dc, stream, attributes);
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	/* re-enable idle optimizations if necessary */
+	if (reset_idle_optimizations)
+		dc_allow_idle_optimizations(dc, true);
+
+#endif
+	return true;
+}
+
+static void program_cursor_position(
+	struct dc *dc,
+	struct dc_stream_state *stream,
+	const struct dc_cursor_position *position)
+{
+	int i;
+	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
+
+	if (!stream)
+		return;
+
+	res_ctx = &dc->current_state->res_ctx;
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 
-		if (pipe_ctx->stream != stream)
+		if (pipe_ctx->stream != stream ||
+				(!pipe_ctx->plane_res.mi  && !pipe_ctx->plane_res.hubp) ||
+				!pipe_ctx->plane_state ||
+				(!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp) ||
+				(!pipe_ctx->plane_res.ipp && !pipe_ctx->plane_res.dpp))
 			continue;
 
 		if (!pipe_to_program) {
@@ -314,31 +375,18 @@ bool dc_stream_set_cursor_attributes(
 			dc->hwss.cursor_lock(dc, pipe_to_program, true);
 		}
 
-		dc->hwss.set_cursor_attribute(pipe_ctx);
-		if (dc->hwss.set_cursor_sdr_white_level)
-			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+		dc->hwss.set_cursor_position(pipe_ctx);
 	}
 
 	if (pipe_to_program)
 		dc->hwss.cursor_lock(dc, pipe_to_program, false);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	/* re-enable idle optimizations if necessary */
-	if (reset_idle_optimizations)
-		dc_allow_idle_optimizations(dc, true);
-
-#endif
-	return true;
 }
 
 bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position)
 {
-	int i;
 	struct dc  *dc;
-	struct resource_context *res_ctx;
-	struct pipe_ctx *pipe_to_program = NULL;
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	bool reset_idle_optimizations = false;
 #endif
@@ -354,7 +402,6 @@ bool dc_stream_set_cursor_position(
 	}
 
 	dc = stream->ctx->dc;
-	res_ctx = &dc->current_state->res_ctx;
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	dc_z10_restore(dc);
 
@@ -367,27 +414,7 @@ bool dc_stream_set_cursor_position(
 #endif
 	stream->cursor_position = *position;
 
-	for (i = 0; i < MAX_PIPES; i++) {
-		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
-
-		if (pipe_ctx->stream != stream ||
-				(!pipe_ctx->plane_res.mi  && !pipe_ctx->plane_res.hubp) ||
-				!pipe_ctx->plane_state ||
-				(!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp) ||
-				(!pipe_ctx->plane_res.ipp && !pipe_ctx->plane_res.dpp))
-			continue;
-
-		if (!pipe_to_program) {
-			pipe_to_program = pipe_ctx;
-			dc->hwss.cursor_lock(dc, pipe_to_program, true);
-		}
-
-		dc->hwss.set_cursor_position(pipe_ctx);
-	}
-
-	if (pipe_to_program)
-		dc->hwss.cursor_lock(dc, pipe_to_program, false);
-
+	program_cursor_position(dc, stream, position);
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* re-enable idle optimizations if necessary */
 	if (reset_idle_optimizations)
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 21d78289b048..3ab52d9a82cf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -45,7 +45,7 @@
 /* forward declaration */
 struct aux_payload;
 
-#define DC_VER "3.2.141"
+#define DC_VER "3.2.149"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -460,7 +460,65 @@ union mem_low_power_enable_options {
 	uint32_t u32All;
 };
 
+struct dc_debug_data {
+	uint32_t ltFailCount;
+	uint32_t i2cErrorCount;
+	uint32_t auxErrorCount;
+};
+
+struct dc_phy_addr_space_config {
+	struct {
+		uint64_t start_addr;
+		uint64_t end_addr;
+		uint64_t fb_top;
+		uint64_t fb_offset;
+		uint64_t fb_base;
+		uint64_t agp_top;
+		uint64_t agp_bot;
+		uint64_t agp_base;
+	} system_aperture;
+
+	struct {
+		uint64_t page_table_start_addr;
+		uint64_t page_table_end_addr;
+		uint64_t page_table_base_addr;
+		bool base_addr_is_mc_addr;
+	} gart_config;
+
+	bool valid;
+	bool is_hvm_enabled;
+	uint64_t page_table_default_page_addr;
+};
+
+struct dc_virtual_addr_space_config {
+	uint64_t	page_table_base_addr;
+	uint64_t	page_table_start_addr;
+	uint64_t	page_table_end_addr;
+	uint32_t	page_table_block_size_in_bytes;
+	uint8_t		page_table_depth; // 1 = 1 level, 2 = 2 level, etc.  0 = invalid
+};
+
+struct dc_bounding_box_overrides {
+	int sr_exit_time_ns;
+	int sr_enter_plus_exit_time_ns;
+	int urgent_latency_ns;
+	int percent_of_ideal_drambw;
+	int dram_clock_change_latency_ns;
+	int dummy_clock_change_latency_ns;
+	/* This forces a hard min on the DCFCLK we use
+	 * for DML.  Unlike the debug option for forcing
+	 * DCFCLK, this override affects watermark calculations
+	 */
+	int min_dcfclk_mhz;
+};
+
+struct dc_state;
+struct resource_pool;
+struct dce_hwseq;
+
 struct dc_debug_options {
+	bool native422_support;
+	bool disable_dsc;
 	enum visual_confirm visual_confirm;
 	bool sanity_checks;
 	bool max_disp_clk;
@@ -486,7 +544,6 @@ struct dc_debug_options {
 	bool disable_dsc_power_gate;
 	int dsc_min_slice_height_override;
 	int dsc_bpp_increment_div;
-	bool native422_support;
 	bool disable_pplib_wm_range;
 	enum wm_report_mode pplib_wm_report_mode;
 	unsigned int min_disp_clk_khz;
@@ -556,7 +613,6 @@ struct dc_debug_options {
 	bool validate_dml_output;
 	bool enable_dmcub_surface_flip;
 	bool usbc_combo_phy_reset_wa;
-	bool disable_dsc;
 	bool enable_dram_clock_change_one_display_vactive;
 	union mem_low_power_enable_options enable_mem_low_power;
 	bool force_vblank_alignment;
@@ -574,69 +630,13 @@ struct dc_debug_options {
 #endif
 };
 
-struct dc_debug_data {
-	uint32_t ltFailCount;
-	uint32_t i2cErrorCount;
-	uint32_t auxErrorCount;
-};
-
-struct dc_phy_addr_space_config {
-	struct {
-		uint64_t start_addr;
-		uint64_t end_addr;
-		uint64_t fb_top;
-		uint64_t fb_offset;
-		uint64_t fb_base;
-		uint64_t agp_top;
-		uint64_t agp_bot;
-		uint64_t agp_base;
-	} system_aperture;
-
-	struct {
-		uint64_t page_table_start_addr;
-		uint64_t page_table_end_addr;
-		uint64_t page_table_base_addr;
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-		bool base_addr_is_mc_addr;
-#endif
-	} gart_config;
-
-	bool valid;
-	bool is_hvm_enabled;
-	uint64_t page_table_default_page_addr;
-};
-
-struct dc_virtual_addr_space_config {
-	uint64_t	page_table_base_addr;
-	uint64_t	page_table_start_addr;
-	uint64_t	page_table_end_addr;
-	uint32_t	page_table_block_size_in_bytes;
-	uint8_t		page_table_depth; // 1 = 1 level, 2 = 2 level, etc.  0 = invalid
-};
-
-struct dc_bounding_box_overrides {
-	int sr_exit_time_ns;
-	int sr_enter_plus_exit_time_ns;
-	int urgent_latency_ns;
-	int percent_of_ideal_drambw;
-	int dram_clock_change_latency_ns;
-	int dummy_clock_change_latency_ns;
-	/* This forces a hard min on the DCFCLK we use
-	 * for DML.  Unlike the debug option for forcing
-	 * DCFCLK, this override affects watermark calculations
-	 */
-	int min_dcfclk_mhz;
-};
-
-struct resource_pool;
-struct dce_hwseq;
 struct gpu_info_soc_bounding_box_v1_0;
 struct dc {
+	struct dc_debug_options debug;
 	struct dc_versions versions;
 	struct dc_caps caps;
 	struct dc_cap_funcs cap_funcs;
 	struct dc_config config;
-	struct dc_debug_options debug;
 	struct dc_bounding_box_overrides bb_overrides;
 	struct dc_bug_wa work_arounds;
 	struct dc_context *ctx;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 1948cd9427d7..4f54bde1bb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -109,6 +109,7 @@ struct dc_link_settings {
 	enum dc_link_spread link_spread;
 	bool use_link_rate_set;
 	uint8_t link_rate_set;
+	bool dpcd_source_device_specific_field_support;
 };
 
 struct dc_lane_settings {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stat.h b/drivers/gpu/drm/amd/display/dc/dc_stat.h
index 2a000ba54ddb..aacbfd786c6c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stat.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stat.h
@@ -38,5 +38,6 @@
 #include "dmub/dmub_srv.h"
 
 void dc_stat_get_dmub_notification(const struct dc *dc, struct dmub_notification *notify);
+void dc_stat_get_dmub_dataout(const struct dc *dc, uint32_t *dataout);
 
 #endif /* _DC_STAT_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_trace.h b/drivers/gpu/drm/amd/display/dc/dc_trace.h
index d2615357269b..c711797e5c9e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_trace.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_trace.h
@@ -37,3 +37,6 @@
 
 #define TRACE_DCN_CLOCK_STATE(dcn_clocks) \
 	trace_amdgpu_dm_dc_clocks_state(dcn_clocks)
+
+#define TRACE_DCN_FPU(begin, function, line, ref_count) \
+	trace_dcn_fpu(begin, function, line, ref_count)
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 8016e22114ce..c1532930169b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -75,18 +75,6 @@ enum dce_environment {
 #define IS_DIAG_DC(dce_environment) \
 	(IS_FPGA_MAXIMUS_DC(dce_environment) || (dce_environment == DCE_ENV_DIAG))
 
-struct hw_asic_id {
-	uint32_t chip_id;
-	uint32_t chip_family;
-	uint32_t pci_revision_id;
-	uint32_t hw_internal_rev;
-	uint32_t vram_type;
-	uint32_t vram_width;
-	uint32_t feature_flags;
-	uint32_t fake_paths_num;
-	void *atombios_base_address;
-};
-
 struct dc_perf_trace {
 	unsigned long read_count;
 	unsigned long write_count;
@@ -94,36 +82,7 @@ struct dc_perf_trace {
 	unsigned long last_entry_write;
 };
 
-struct dc_context {
-	struct dc *dc;
-
-	void *driver_context; /* e.g. amdgpu_device */
-	struct dc_perf_trace *perf_trace;
-	void *cgs_device;
-
-	enum dce_environment dce_environment;
-	struct hw_asic_id asic_id;
-
-	/* todo: below should probably move to dc.  to facilitate removal
-	 * of AS we will store these here
-	 */
-	enum dce_version dce_version;
-	struct dc_bios *dc_bios;
-	bool created_bios;
-	struct gpio_service *gpio_service;
-	uint32_t dc_sink_id_count;
-	uint32_t dc_stream_id_count;
-	uint32_t dc_edp_id_count;
-	uint64_t fbc_gpu_addr;
-	struct dc_dmub_srv *dmub_srv;
-
-#ifdef CONFIG_DRM_AMD_DC_HDCP
-	struct cp_psp cp_psp;
-#endif
-};
-
-
-#define DC_MAX_EDID_BUFFER_SIZE 1280
+#define DC_MAX_EDID_BUFFER_SIZE 2048
 #define DC_EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
@@ -836,6 +795,46 @@ struct dc_clock_config {
 	uint32_t current_clock_khz;/*current clock in use*/
 };
 
+struct hw_asic_id {
+	uint32_t chip_id;
+	uint32_t chip_family;
+	uint32_t pci_revision_id;
+	uint32_t hw_internal_rev;
+	uint32_t vram_type;
+	uint32_t vram_width;
+	uint32_t feature_flags;
+	uint32_t fake_paths_num;
+	void *atombios_base_address;
+};
+
+struct dc_context {
+	struct dc *dc;
+
+	void *driver_context; /* e.g. amdgpu_device */
+	struct dc_perf_trace *perf_trace;
+	void *cgs_device;
+
+	enum dce_environment dce_environment;
+	struct hw_asic_id asic_id;
+
+	/* todo: below should probably move to dc.  to facilitate removal
+	 * of AS we will store these here
+	 */
+	enum dce_version dce_version;
+	struct dc_bios *dc_bios;
+	bool created_bios;
+	struct gpio_service *gpio_service;
+	uint32_t dc_sink_id_count;
+	uint32_t dc_stream_id_count;
+	uint32_t dc_edp_id_count;
+	uint64_t fbc_gpu_addr;
+	struct dc_dmub_srv *dmub_srv;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct cp_psp cp_psp;
+#endif
+
+};
+
 /* DSC DPCD capabilities */
 union dsc_slice_caps1 {
 	struct {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 2fb88e54a4bf..e14f99b4b0c3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -42,6 +42,11 @@
 #define DC_LOGGER \
 	engine->ctx->logger
 
+#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
+#define IS_DC_I2CAUX_LOGGING_ENABLED() (false)
+#define LOG_FLAG_Error_I2cAux LOG_ERROR
+#define LOG_FLAG_I2cAux_DceAux LOG_I2C_AUX
+
 #include "reg_helper.h"
 
 #undef FN
@@ -71,6 +76,8 @@ enum {
 #define DEFAULT_AUX_ENGINE_MULT   0
 #define DEFAULT_AUX_ENGINE_LENGTH 69
 
+#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
+
 static void release_engine(
 	struct dce_aux *engine)
 {
@@ -621,6 +628,58 @@ int dce_aux_transfer_dmub_raw(struct ddc_service *ddc,
 #define AUX_MAX_INVALID_REPLY_RETRIES 2
 #define AUX_MAX_TIMEOUT_RETRIES 3
 
+static void dce_aux_log_payload(const char *payload_name,
+	unsigned char *payload, uint32_t length, uint32_t max_length_to_log)
+{
+	if (!IS_DC_I2CAUX_LOGGING_ENABLED())
+		return;
+
+	if (payload && length) {
+		char hex_str[128] = {0};
+		char *hex_str_ptr = &hex_str[0];
+		uint32_t hex_str_remaining = sizeof(hex_str);
+		unsigned char *payload_ptr = payload;
+		unsigned char *payload_max_to_log_ptr = payload_ptr + min(max_length_to_log, length);
+		unsigned int count;
+		char *padding = "";
+
+		while (payload_ptr < payload_max_to_log_ptr) {
+			count = snprintf_count(hex_str_ptr, hex_str_remaining, "%s%02X", padding, *payload_ptr);
+			padding = " ";
+			hex_str_remaining -= count;
+			hex_str_ptr += count;
+			payload_ptr++;
+		}
+
+		count = snprintf_count(hex_str_ptr, hex_str_remaining, "   ");
+		hex_str_remaining -= count;
+		hex_str_ptr += count;
+
+		payload_ptr = payload;
+		while (payload_ptr < payload_max_to_log_ptr) {
+			count = snprintf_count(hex_str_ptr, hex_str_remaining, "%c",
+				*payload_ptr >= ' ' ? *payload_ptr : '.');
+			hex_str_remaining -= count;
+			hex_str_ptr += count;
+			payload_ptr++;
+		}
+
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_VERBOSE,
+					LOG_FLAG_I2cAux_DceAux,
+					"dce_aux_log_payload: %s: length=%u: data: %s%s",
+					payload_name,
+					length,
+					hex_str,
+					(length > max_length_to_log ? " (...)" : " "));
+	} else {
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_VERBOSE,
+					LOG_FLAG_I2cAux_DceAux,
+					"dce_aux_log_payload: %s: length=%u: data: <empty payload>",
+					payload_name,
+					length);
+	}
+}
+
 bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *payload)
 {
@@ -646,7 +705,34 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 	}
 
 	for (i = 0; i < AUX_MAX_RETRIES; i++) {
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+					LOG_FLAG_I2cAux_DceAux,
+					"dce_aux_transfer_with_retries: link_index=%u: START: retry %d of %d: address=0x%04x length=%u write=%d mot=%d",
+					ddc && ddc->link ? ddc->link->link_index : UINT_MAX,
+					i + 1,
+					(int)AUX_MAX_RETRIES,
+					payload->address,
+					payload->length,
+					(unsigned int) payload->write,
+					(unsigned int) payload->mot);
+		if (payload->write)
+			dce_aux_log_payload("  write", payload->data, payload->length, 16);
 		ret = dce_aux_transfer_raw(ddc, payload, &operation_result);
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+					LOG_FLAG_I2cAux_DceAux,
+					"dce_aux_transfer_with_retries: link_index=%u: END: retry %d of %d: address=0x%04x length=%u write=%d mot=%d: ret=%d operation_result=%d payload->reply=%u",
+					ddc && ddc->link ? ddc->link->link_index : UINT_MAX,
+					i + 1,
+					(int)AUX_MAX_RETRIES,
+					payload->address,
+					payload->length,
+					(unsigned int) payload->write,
+					(unsigned int) payload->mot,
+					ret,
+					(int)operation_result,
+					(unsigned int) *payload->reply);
+		if (!payload->write)
+			dce_aux_log_payload("  read", payload->data, ret > 0 ? ret : 0, 16);
 
 		switch (operation_result) {
 		case AUX_RET_SUCCESS:
@@ -655,30 +741,64 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 
 			switch (*payload->reply) {
 			case AUX_TRANSACTION_REPLY_AUX_ACK:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+							LOG_FLAG_I2cAux_DceAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_AUX_ACK");
 				if (!payload->write && payload->length != ret) {
-					if (++aux_ack_retries >= AUX_MAX_RETRIES)
+					if (++aux_ack_retries >= AUX_MAX_RETRIES) {
+						DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+									LOG_FLAG_Error_I2cAux,
+									"dce_aux_transfer_with_retries: FAILURE: aux_ack_retries=%d >= AUX_MAX_RETRIES=%d",
+									aux_defer_retries,
+									AUX_MAX_RETRIES);
 						goto fail;
-					else
+					} else {
 						udelay(300);
+					}
 				} else
 					return true;
 			break;
 
 			case AUX_TRANSACTION_REPLY_AUX_DEFER:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+							LOG_FLAG_I2cAux_DceAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_AUX_DEFER");
+
 				/* polling_timeout_period is in us */
 				defer_time_in_ms += aux110->polling_timeout_period / 1000;
 				++aux_defer_retries;
 				fallthrough;
 			case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER:
+				if (*payload->reply == AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER)
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+								LOG_FLAG_I2cAux_DceAux,
+								"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER");
+
 				retry_on_defer = true;
 				fallthrough;
 			case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK:
+				if (*payload->reply == AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK)
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+								LOG_FLAG_I2cAux_DceAux,
+								"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK");
+
 				if (aux_defer_retries >= AUX_MIN_DEFER_RETRIES
 						&& defer_time_in_ms >= AUX_MAX_DEFER_TIMEOUT_MS) {
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+								LOG_FLAG_Error_I2cAux,
+								"dce_aux_transfer_with_retries: FAILURE: aux_defer_retries=%d >= AUX_MIN_DEFER_RETRIES=%d && defer_time_in_ms=%d >= AUX_MAX_DEFER_TIMEOUT_MS=%d",
+								aux_defer_retries,
+								AUX_MIN_DEFER_RETRIES,
+								defer_time_in_ms,
+								AUX_MAX_DEFER_TIMEOUT_MS);
 					goto fail;
 				} else {
 					if ((*payload->reply == AUX_TRANSACTION_REPLY_AUX_DEFER) ||
 						(*payload->reply == AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER)) {
+						DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+									LOG_FLAG_I2cAux_DceAux,
+									"dce_aux_transfer_with_retries: payload->defer_delay=%u",
+									payload->defer_delay);
 						if (payload->defer_delay > 1) {
 							msleep(payload->defer_delay);
 							defer_time_in_ms += payload->defer_delay;
@@ -691,37 +811,86 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 				break;
 
 			case AUX_TRANSACTION_REPLY_I2C_DEFER:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+							LOG_FLAG_I2cAux_DceAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_I2C_DEFER");
+
 				aux_defer_retries = 0;
-				if (++aux_i2c_defer_retries >= AUX_MAX_I2C_DEFER_RETRIES)
+				if (++aux_i2c_defer_retries >= AUX_MAX_I2C_DEFER_RETRIES) {
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+								LOG_FLAG_Error_I2cAux,
+								"dce_aux_transfer_with_retries: FAILURE: aux_i2c_defer_retries=%d >= AUX_MAX_I2C_DEFER_RETRIES=%d",
+								aux_i2c_defer_retries,
+								AUX_MAX_I2C_DEFER_RETRIES);
 					goto fail;
+				}
 				break;
 
 			case AUX_TRANSACTION_REPLY_AUX_NACK:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+							LOG_FLAG_I2cAux_DceAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_AUX_NACK");
+				goto fail;
+
 			case AUX_TRANSACTION_REPLY_HPD_DISCON:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+							LOG_FLAG_I2cAux_DceAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_HPD_DISCON");
+				goto fail;
+
 			default:
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+							LOG_FLAG_Error_I2cAux,
+							"dce_aux_transfer_with_retries: AUX_RET_SUCCESS: FAILURE: AUX_TRANSACTION_REPLY_* unknown, default case.");
 				goto fail;
 			}
 			break;
 
 		case AUX_RET_ERROR_INVALID_REPLY:
-			if (++aux_invalid_reply_retries >= AUX_MAX_INVALID_REPLY_RETRIES)
+			DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+						LOG_FLAG_I2cAux_DceAux,
+						"dce_aux_transfer_with_retries: AUX_RET_ERROR_INVALID_REPLY");
+			if (++aux_invalid_reply_retries >= AUX_MAX_INVALID_REPLY_RETRIES) {
+				DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+							LOG_FLAG_Error_I2cAux,
+							"dce_aux_transfer_with_retries: FAILURE: aux_invalid_reply_retries=%d >= AUX_MAX_INVALID_REPLY_RETRIES=%d",
+							aux_invalid_reply_retries,
+							AUX_MAX_INVALID_REPLY_RETRIES);
 				goto fail;
-			else
+			} else
 				udelay(400);
 			break;
 
 		case AUX_RET_ERROR_TIMEOUT:
+			DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+						LOG_FLAG_I2cAux_DceAux,
+						"dce_aux_transfer_with_retries: AUX_RET_ERROR_TIMEOUT");
 			// Check whether a DEFER had occurred before the timeout.
 			// If so, treat timeout as a DEFER.
 			if (retry_on_defer) {
-				if (++aux_defer_retries >= AUX_MIN_DEFER_RETRIES)
+				if (++aux_defer_retries >= AUX_MIN_DEFER_RETRIES) {
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+								LOG_FLAG_Error_I2cAux,
+								"dce_aux_transfer_with_retries: FAILURE: aux_defer_retries=%d >= AUX_MIN_DEFER_RETRIES=%d",
+								aux_defer_retries,
+								AUX_MIN_DEFER_RETRIES);
 					goto fail;
-				else if (payload->defer_delay > 0)
+				} else if (payload->defer_delay > 0) {
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+								LOG_FLAG_I2cAux_DceAux,
+								"dce_aux_transfer_with_retries: payload->defer_delay=%u",
+								payload->defer_delay);
 					msleep(payload->defer_delay);
+				}
 			} else {
-				if (++aux_timeout_retries >= AUX_MAX_TIMEOUT_RETRIES)
+				if (++aux_timeout_retries >= AUX_MAX_TIMEOUT_RETRIES) {
+					DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+								LOG_FLAG_Error_I2cAux,
+								"dce_aux_transfer_with_retries: FAILURE: aux_timeout_retries=%d >= AUX_MAX_TIMEOUT_RETRIES=%d",
+								aux_timeout_retries,
+								AUX_MAX_TIMEOUT_RETRIES);
 					goto fail;
-				else {
+				} else {
 					/*
 					 * DP 1.4, 2.8.2:  AUX Transaction Response/Reply Timeouts
 					 * According to the DP spec there should be 3 retries total
@@ -736,12 +905,25 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 		case AUX_RET_ERROR_ENGINE_ACQUIRE:
 		case AUX_RET_ERROR_UNKNOWN:
 		default:
+			DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
+						LOG_FLAG_I2cAux_DceAux,
+						"dce_aux_transfer_with_retries: Failure: operation_result=%d",
+						(int)operation_result);
 			goto fail;
 		}
 	}
 
 fail:
+	DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+				LOG_FLAG_Error_I2cAux,
+				"dce_aux_transfer_with_retries: FAILURE");
 	if (!payload_reply)
 		payload->reply = NULL;
+
+	DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+				WPP_BIT_FLAG_DC_ERROR,
+				"AUX transaction failed. Result: %d",
+				operation_result);
+
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index 10d42ae0cffe..aa8403bc4c83 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -29,6 +29,8 @@
 #include "dmub/dmub_srv.h"
 #include "core_types.h"
 
+#define DC_TRACE_LEVEL_MESSAGE(...)	do {} while (0) /* do nothing */
+
 #define MAX_PIPES 6
 
 /*
@@ -96,10 +98,19 @@ static void dmub_psr_get_state(struct dmub_psr *dmub, enum dc_psr_state *state,
 			// Return invalid state when GPINT times out
 			*state = PSR_STATE_INVALID;
 
-		// Assert if max retry hit
-		if (retry_count >= 1000)
-			ASSERT(0);
 	} while (++retry_count <= 1000 && *state == PSR_STATE_INVALID);
+
+	// Assert if max retry hit
+	if (retry_count >= 1000 && *state == PSR_STATE_INVALID) {
+		ASSERT(0);
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR,
+				WPP_BIT_FLAG_Firmware_PsrState,
+				"Unable to get PSR state from FW.");
+	} else
+		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_VERBOSE,
+				WPP_BIT_FLAG_Firmware_PsrState,
+				"Got PSR state from FW. PSR state: %d, Retry count: %d",
+				*state, retry_count);
 }
 
 /*
@@ -207,7 +218,7 @@ static void dmub_psr_set_level(struct dmub_psr *dmub, uint16_t psr_level, uint8_
 	cmd.psr_set_level.header.sub_type = DMUB_CMD__PSR_SET_LEVEL;
 	cmd.psr_set_level.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_level_data);
 	cmd.psr_set_level.psr_set_level_data.psr_level = psr_level;
-	cmd.psr_set_level.psr_set_level_data.cmd_version = PSR_VERSION_1;
+	cmd.psr_set_level.psr_set_level_data.cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1;
 	cmd.psr_set_level.psr_set_level_data.panel_inst = panel_inst;
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
 	dc_dmub_srv_cmd_execute(dc->dmub_srv);
@@ -293,7 +304,7 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 	copy_settings_data->debug.bitfields.use_hw_lock_mgr		= 1;
 	copy_settings_data->fec_enable_status = (link->fec_state == dc_link_fec_enabled);
 	copy_settings_data->fec_enable_delay_in100us = link->dc->debug.fec_enable_delay_in100us;
-	copy_settings_data->cmd_version =  PSR_VERSION_1;
+	copy_settings_data->cmd_version =  DMUB_CMD_PSR_CONTROL_VERSION_1;
 	copy_settings_data->panel_inst = panel_inst;
 
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 8d7e92d5d3e4..39485bdeb90e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -121,6 +121,10 @@ struct dcn_hubbub_registers {
 	uint32_t DCN_VM_AGP_BASE;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB;
+	uint32_t DCN_VM_FAULT_ADDR_MSB;
+	uint32_t DCN_VM_FAULT_ADDR_LSB;
+	uint32_t DCN_VM_FAULT_CNTL;
+	uint32_t DCN_VM_FAULT_STATUS;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_A;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_B;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_C;
@@ -233,7 +237,19 @@ struct dcn_hubbub_registers {
 		type DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C;\
 		type DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D;\
 		type DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB;\
-		type DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB
+		type DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB;\
+		type DCN_VM_FAULT_ADDR_MSB;\
+		type DCN_VM_FAULT_ADDR_LSB;\
+		type DCN_VM_ERROR_STATUS_CLEAR;\
+		type DCN_VM_ERROR_STATUS_MODE;\
+		type DCN_VM_ERROR_INTERRUPT_ENABLE;\
+		type DCN_VM_RANGE_FAULT_DISABLE;\
+		type DCN_VM_PRQ_FAULT_DISABLE;\
+		type DCN_VM_ERROR_STATUS;\
+		type DCN_VM_ERROR_VMID;\
+		type DCN_VM_ERROR_TABLE_LEVEL;\
+		type DCN_VM_ERROR_PIPE;\
+		type DCN_VM_ERROR_INTERRUPT_STATUS
 
 #define HUBBUB_STUTTER_REG_FIELD_LIST(type) \
 		type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A;\
@@ -303,6 +319,7 @@ struct dcn_hubbub_registers {
 		type DET3_SIZE_CURRENT;\
 		type COMPBUF_SIZE;\
 		type COMPBUF_SIZE_CURRENT;\
+		type CONFIG_ERROR;\
 		type COMPBUF_RESERVED_SPACE_64B;\
 		type COMPBUF_RESERVED_SPACE_ZS;\
 		type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_A;\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 04303fe9c659..ea185c877323 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -871,6 +871,8 @@ void hubp1_read_state_common(struct hubp *hubp)
 	struct _vcs_dpi_display_dlg_regs_st *dlg_attr = &s->dlg_attr;
 	struct _vcs_dpi_display_ttu_regs_st *ttu_attr = &s->ttu_attr;
 	struct _vcs_dpi_display_rq_regs_st *rq_regs = &s->rq_regs;
+	uint32_t aperture_low_msb, aperture_low_lsb;
+	uint32_t aperture_high_msb, aperture_high_lsb;
 
 	/* Requester */
 	REG_GET(HUBPRET_CONTROL,
@@ -881,6 +883,22 @@ void hubp1_read_state_common(struct hubp *hubp)
 			MRQ_EXPANSION_MODE, &rq_regs->mrq_expansion_mode,
 			CRQ_EXPANSION_MODE, &rq_regs->crq_expansion_mode);
 
+	REG_GET(DCN_VM_SYSTEM_APERTURE_LOW_ADDR_MSB,
+			MC_VM_SYSTEM_APERTURE_LOW_ADDR_MSB, &aperture_low_msb);
+
+	REG_GET(DCN_VM_SYSTEM_APERTURE_LOW_ADDR_LSB,
+			MC_VM_SYSTEM_APERTURE_LOW_ADDR_LSB, &aperture_low_lsb);
+
+	REG_GET(DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB,
+			MC_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB, &aperture_high_msb);
+
+	REG_GET(DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB,
+			MC_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB, &aperture_high_lsb);
+
+	// On DCN1, aperture is broken down into MSB and LSB; only keep bits [47:18] to match later DCN format
+	rq_regs->aperture_low_addr = (aperture_low_msb << 26) | (aperture_low_lsb >> 6);
+	rq_regs->aperture_high_addr = (aperture_high_msb << 26) | (aperture_high_lsb >> 6);
+
 	/* DLG - Per hubp */
 	REG_GET_2(BLANK_OFFSET_0,
 		REFCYC_H_BLANK_END, &dlg_attr->refcyc_h_blank_end,
@@ -1037,6 +1055,17 @@ void hubp1_read_state_common(struct hubp *hubp)
 			QoS_LEVEL_LOW_WM, &s->qos_level_low_wm,
 			QoS_LEVEL_HIGH_WM, &s->qos_level_high_wm);
 
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS,
+			PRIMARY_SURFACE_ADDRESS, &s->primary_surface_addr_lo);
+
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH,
+			PRIMARY_SURFACE_ADDRESS, &s->primary_surface_addr_hi);
+
+	REG_GET(DCSURF_PRIMARY_META_SURFACE_ADDRESS,
+			PRIMARY_META_SURFACE_ADDRESS, &s->primary_meta_addr_lo);
+
+	REG_GET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH,
+			PRIMARY_META_SURFACE_ADDRESS, &s->primary_meta_addr_hi);
 }
 
 void hubp1_read_state(struct hubp *hubp)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index e2f2f6995935..9cb8c383d673 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -682,6 +682,10 @@ struct dcn_hubp_state {
 	uint32_t min_ttu_vblank;
 	uint32_t qos_level_low_wm;
 	uint32_t qos_level_high_wm;
+	uint32_t primary_surface_addr_lo;
+	uint32_t primary_surface_addr_hi;
+	uint32_t primary_meta_addr_lo;
+	uint32_t primary_meta_addr_hi;
 };
 
 struct dcn10_hubp {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index c545eddabdcc..df8a7718a85f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1502,25 +1502,22 @@ void dcn10_init_hw(struct dc *dc)
 void dcn10_power_down_on_boot(struct dc *dc)
 {
 	struct dc_link *edp_links[MAX_NUM_EDP];
-	struct dc_link *edp_link;
+	struct dc_link *edp_link = NULL;
 	int edp_num;
 	int i = 0;
 
 	get_edp_links(dc, edp_links, &edp_num);
-
-	if (edp_num) {
-		for (i = 0; i < edp_num; i++) {
-			edp_link = edp_links[i];
-			if (edp_link->link_enc->funcs->is_dig_enabled &&
-					edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
-					dc->hwseq->funcs.edp_backlight_control &&
-					dc->hwss.power_down &&
-					dc->hwss.edp_power_control) {
-				dc->hwseq->funcs.edp_backlight_control(edp_link, false);
-				dc->hwss.power_down(dc);
-				dc->hwss.edp_power_control(edp_link, false);
-			}
-		}
+	if (edp_num)
+		edp_link = edp_links[0];
+
+	if (edp_link && edp_link->link_enc->funcs->is_dig_enabled &&
+			edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
+			dc->hwseq->funcs.edp_backlight_control &&
+			dc->hwss.power_down &&
+			dc->hwss.edp_power_control) {
+		dc->hwseq->funcs.edp_backlight_control(edp_link, false);
+		dc->hwss.power_down(dc);
+		dc->hwss.edp_power_control(edp_link, false);
 	} else {
 		for (i = 0; i < dc->link_count; i++) {
 			struct dc_link *link = dc->links[i];
@@ -3180,8 +3177,12 @@ void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
 static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx)
 {
 	struct pipe_ctx *test_pipe;
-	const struct rect *r1 = &pipe_ctx->plane_res.scl_data.recout, *r2;
+	const struct scaler_data *scl_data = &pipe_ctx->plane_res.scl_data;
+	const struct rect *r1 = &scl_data->recout, *r2;
 	int r1_r = r1->x + r1->width, r1_b = r1->y + r1->height, r2_r, r2_b;
+	int cur_layer = pipe_ctx->plane_state->layer_index;
+	bool upper_pipe_exists = false;
+	struct fixed31_32 one = dc_fixpt_from_int(1);
 
 	/**
 	 * Disable the cursor if there's another pipe above this with a
@@ -3199,8 +3200,17 @@ static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx)
 
 		if (r1->x >= r2->x && r1->y >= r2->y && r1_r <= r2_r && r1_b <= r2_b)
 			return true;
+
+		if (test_pipe->plane_state->layer_index < cur_layer)
+			upper_pipe_exists = true;
 	}
 
+	// if plane scaled, assume an upper plane can handle cursor if it exists.
+	if (upper_pipe_exists &&
+			(scl_data->ratios.horz.value != one.value ||
+			scl_data->ratios.vert.value != one.value))
+		return true;
+
 	return false;
 }
 
@@ -3631,13 +3641,12 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	struct dc_clock_config clock_cfg = {0};
 	struct dc_clocks *current_clocks = &context->bw_ctx.bw.dcn.clk;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->get_clock)
-				dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
-						context, clock_type, &clock_cfg);
-
-	if (!dc->clk_mgr->funcs->get_clock)
+	if (!dc->clk_mgr || !dc->clk_mgr->funcs->get_clock)
 		return DC_FAIL_UNSUPPORTED_1;
 
+	dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
+		context, clock_type, &clock_cfg);
+
 	if (clk_khz > clock_cfg.max_clock_khz)
 		return DC_FAIL_CLK_EXCEED_MAX;
 
@@ -3655,7 +3664,7 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	else
 		return DC_ERROR_UNEXPECTED;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->update_clocks)
+	if (dc->clk_mgr->funcs->update_clocks)
 				dc->clk_mgr->funcs->update_clocks(dc->clk_mgr,
 				context, true);
 	return DC_OK;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index 3696faf12d86..37848f4577b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1388,6 +1388,12 @@ void optc1_read_otg_state(struct optc *optc1,
 
 	REG_GET(OPTC_INPUT_GLOBAL_CONTROL,
 			OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status);
+
+	REG_GET(OTG_VERTICAL_INTERRUPT2_CONTROL,
+			OTG_VERTICAL_INTERRUPT2_INT_ENABLE, &s->vertical_interrupt2_en);
+
+	REG_GET(OTG_VERTICAL_INTERRUPT2_POSITION,
+			OTG_VERTICAL_INTERRUPT2_LINE_START, &s->vertical_interrupt2_line);
 }
 
 bool optc1_get_otg_active_size(struct timing_generator *optc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index 29d6fbe0093a..c50c29984d51 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -578,6 +578,8 @@ struct dcn_otg_state {
 	uint32_t underflow_occurred_status;
 	uint32_t otg_enabled;
 	uint32_t blank_enabled;
+	uint32_t vertical_interrupt2_en;
+	uint32_t vertical_interrupt2_line;
 };
 
 void optc1_read_otg_state(struct optc *optc1,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index f1a08a7736ac..cf364ae93138 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -522,16 +522,21 @@ void enc1_stream_encoder_hdmi_set_stream_attribute(
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_888:
 		REG_UPDATE(HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, 0);
+		DC_LOG_DEBUG("HDMI source set to 24BPP deep color depth\n");
 		break;
 	case COLOR_DEPTH_101010:
 		if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) {
 			REG_UPDATE_2(HDMI_CONTROL,
 					HDMI_DEEP_COLOR_DEPTH, 1,
 					HDMI_DEEP_COLOR_ENABLE, 0);
+			DC_LOG_DEBUG("HDMI source 30BPP deep color depth"  \
+				"disabled for YCBCR422 pixel encoding\n");
 		} else {
 			REG_UPDATE_2(HDMI_CONTROL,
 					HDMI_DEEP_COLOR_DEPTH, 1,
 					HDMI_DEEP_COLOR_ENABLE, 1);
+			DC_LOG_DEBUG("HDMI source 30BPP deep color depth"  \
+				"enabled for YCBCR422 non-pixel encoding\n");
 			}
 		break;
 	case COLOR_DEPTH_121212:
@@ -539,16 +544,22 @@ void enc1_stream_encoder_hdmi_set_stream_attribute(
 			REG_UPDATE_2(HDMI_CONTROL,
 					HDMI_DEEP_COLOR_DEPTH, 2,
 					HDMI_DEEP_COLOR_ENABLE, 0);
+			DC_LOG_DEBUG("HDMI source 36BPP deep color depth"  \
+				"disabled for YCBCR422 pixel encoding\n");
 		} else {
 			REG_UPDATE_2(HDMI_CONTROL,
 					HDMI_DEEP_COLOR_DEPTH, 2,
 					HDMI_DEEP_COLOR_ENABLE, 1);
+			DC_LOG_DEBUG("HDMI source 36BPP deep color depth"  \
+				"enabled for non-pixel YCBCR422 encoding\n");
 			}
 		break;
 	case COLOR_DEPTH_161616:
 		REG_UPDATE_2(HDMI_CONTROL,
 				HDMI_DEEP_COLOR_DEPTH, 3,
 				HDMI_DEEP_COLOR_ENABLE, 1);
+		DC_LOG_DEBUG("HDMI source deep color depth enabled in"  \
+				"reserved mode\n");
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
index 91a9305d42e8..aacb1fb5c73e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
@@ -605,6 +605,26 @@ static bool hubbub2_program_watermarks(
 	return wm_pending;
 }
 
+void hubbub2_read_state(struct hubbub *hubbub, struct dcn_hubbub_state *hubbub_state)
+{
+	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+
+	if (REG(DCN_VM_FAULT_ADDR_MSB))
+		hubbub_state->vm_fault_addr_msb = REG_READ(DCN_VM_FAULT_ADDR_MSB);
+
+	if (REG(DCN_VM_FAULT_ADDR_LSB))
+		hubbub_state->vm_fault_addr_msb = REG_READ(DCN_VM_FAULT_ADDR_LSB);
+
+	if (REG(DCN_VM_FAULT_CNTL))
+		REG_GET(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_MODE, &hubbub_state->vm_error_mode);
+
+	if (REG(DCN_VM_FAULT_STATUS)) {
+		 REG_GET(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_STATUS, &hubbub_state->vm_error_status);
+		 REG_GET(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, &hubbub_state->vm_error_vmid);
+		 REG_GET(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, &hubbub_state->vm_error_pipe);
+	}
+}
+
 static const struct hubbub_funcs hubbub2_funcs = {
 	.update_dchub = hubbub2_update_dchub,
 	.init_dchub_sys_ctx = hubbub2_init_dchub_sys_ctx,
@@ -617,6 +637,7 @@ static const struct hubbub_funcs hubbub2_funcs = {
 	.program_watermarks = hubbub2_program_watermarks,
 	.is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled,
 	.allow_self_refresh_control = hubbub1_allow_self_refresh_control,
+	.hubbub_read_state = hubbub2_read_state,
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
index 10af257d90ef..2f6146bf1d32 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
@@ -29,16 +29,6 @@
 #include "dcn10/dcn10_hubbub.h"
 #include "dcn20_vmid.h"
 
-#define HUBBUB_REG_LIST_DCN20_COMMON()\
-	HUBBUB_REG_LIST_DCN_COMMON(), \
-	SR(DCHUBBUB_CRC_CTRL), \
-	SR(DCN_VM_FB_LOCATION_BASE),\
-	SR(DCN_VM_FB_LOCATION_TOP),\
-	SR(DCN_VM_FB_OFFSET),\
-	SR(DCN_VM_AGP_BOT),\
-	SR(DCN_VM_AGP_TOP),\
-	SR(DCN_VM_AGP_BASE)
-
 #define TO_DCN20_HUBBUB(hubbub)\
 	container_of(hubbub, struct dcn20_hubbub, base)
 
@@ -50,7 +40,11 @@
 	SR(DCN_VM_FB_OFFSET),\
 	SR(DCN_VM_AGP_BOT),\
 	SR(DCN_VM_AGP_TOP),\
-	SR(DCN_VM_AGP_BASE)
+	SR(DCN_VM_AGP_BASE),\
+	SR(DCN_VM_FAULT_ADDR_MSB), \
+	SR(DCN_VM_FAULT_ADDR_LSB), \
+	SR(DCN_VM_FAULT_CNTL), \
+	SR(DCN_VM_FAULT_STATUS)
 
 #define HUBBUB_REG_LIST_DCN20(id)\
 	HUBBUB_REG_LIST_DCN20_COMMON(), \
@@ -71,7 +65,19 @@
 	HUBBUB_SF(DCN_VM_AGP_TOP, AGP_TOP, mask_sh), \
 	HUBBUB_SF(DCN_VM_AGP_BASE, AGP_BASE, mask_sh), \
 	HUBBUB_SF(DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB, DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB, mask_sh), \
-	HUBBUB_SF(DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB, DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB, mask_sh)
+	HUBBUB_SF(DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB, DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_MSB, DCN_VM_FAULT_ADDR_MSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_LSB, DCN_VM_FAULT_ADDR_LSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_CLEAR, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_MODE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_INTERRUPT_ENABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_RANGE_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_PRQ_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_STATUS, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_TABLE_LEVEL, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh)
 
 struct dcn20_hubbub {
 	struct hubbub base;
@@ -131,4 +137,7 @@ void hubbub2_get_dchub_ref_freq(struct hubbub *hubbub,
 void hubbub2_wm_read_state(struct hubbub *hubbub,
 		struct dcn_hubbub_wm *wm);
 
+void hubbub2_read_state(struct hubbub *hubbub,
+		struct dcn_hubbub_state *hubbub_state);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 7e54058715aa..5adf42a7cc27 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1080,6 +1080,12 @@ void hubp2_read_state_common(struct hubp *hubp)
 			MRQ_EXPANSION_MODE, &rq_regs->mrq_expansion_mode,
 			CRQ_EXPANSION_MODE, &rq_regs->crq_expansion_mode);
 
+	REG_GET(DCN_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			MC_VM_SYSTEM_APERTURE_HIGH_ADDR, &rq_regs->aperture_high_addr);
+
+	REG_GET(DCN_VM_SYSTEM_APERTURE_LOW_ADDR,
+			MC_VM_SYSTEM_APERTURE_LOW_ADDR, &rq_regs->aperture_low_addr);
+
 	/* DLG - Per hubp */
 	REG_GET_2(BLANK_OFFSET_0,
 		REFCYC_H_BLANK_END, &dlg_attr->refcyc_h_blank_end,
@@ -1236,6 +1242,17 @@ void hubp2_read_state_common(struct hubp *hubp)
 			QoS_LEVEL_LOW_WM, &s->qos_level_low_wm,
 			QoS_LEVEL_HIGH_WM, &s->qos_level_high_wm);
 
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS,
+			PRIMARY_SURFACE_ADDRESS, &s->primary_surface_addr_lo);
+
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH,
+			PRIMARY_SURFACE_ADDRESS, &s->primary_surface_addr_hi);
+
+	REG_GET(DCSURF_PRIMARY_META_SURFACE_ADDRESS,
+			PRIMARY_META_SURFACE_ADDRESS, &s->primary_meta_addr_lo);
+
+	REG_GET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH,
+			PRIMARY_META_SURFACE_ADDRESS, &s->primary_meta_addr_hi);
 }
 
 void hubp2_read_state(struct hubp *hubp)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5c2853654cca..a47ba1d45be9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1723,13 +1723,15 @@ void dcn20_program_front_end_for_ctx(
 
 				pipe = pipe->bottom_pipe;
 			}
-			/* Program secondary blending tree and writeback pipes */
-			pipe = &context->res_ctx.pipe_ctx[i];
-			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
-					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
-					&& hws->funcs.program_all_writeback_pipes_in_tree)
-				hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 		}
+		/* Program secondary blending tree and writeback pipes */
+		pipe = &context->res_ctx.pipe_ctx[i];
+		if (!pipe->top_pipe && !pipe->prev_odm_pipe
+				&& pipe->stream && pipe->stream->num_wb_info > 0
+				&& (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw)
+					|| pipe->stream->update_flags.raw)
+				&& hws->funcs.program_all_writeback_pipes_in_tree)
+			hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index b173fa3653b5..e3e01b17c164 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -35,6 +35,8 @@
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
 
+#include "dml/dcn2x/dcn2x.h"
+
 #include "dcn10/dcn10_hubp.h"
 #include "dcn10/dcn10_ipp.h"
 #include "dcn20_hubbub.h"
@@ -1974,43 +1976,6 @@ void dcn20_split_stream_for_mpc(
 	ASSERT(primary_pipe->plane_state);
 }
 
-void dcn20_populate_dml_writeback_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
-{
-	int pipe_cnt, i;
-
-	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
-		struct dc_writeback_info *wb_info = &res_ctx->pipe_ctx[i].stream->writeback_info[0];
-
-		if (!res_ctx->pipe_ctx[i].stream)
-			continue;
-
-		/* Set writeback information */
-		pipes[pipe_cnt].dout.wb_enable = (wb_info->wb_enabled == true) ? 1 : 0;
-		pipes[pipe_cnt].dout.num_active_wb++;
-		pipes[pipe_cnt].dout.wb.wb_src_height = wb_info->dwb_params.cnv_params.crop_height;
-		pipes[pipe_cnt].dout.wb.wb_src_width = wb_info->dwb_params.cnv_params.crop_width;
-		pipes[pipe_cnt].dout.wb.wb_dst_width = wb_info->dwb_params.dest_width;
-		pipes[pipe_cnt].dout.wb.wb_dst_height = wb_info->dwb_params.dest_height;
-		pipes[pipe_cnt].dout.wb.wb_htaps_luma = 1;
-		pipes[pipe_cnt].dout.wb.wb_vtaps_luma = 1;
-		pipes[pipe_cnt].dout.wb.wb_htaps_chroma = wb_info->dwb_params.scaler_taps.h_taps_c;
-		pipes[pipe_cnt].dout.wb.wb_vtaps_chroma = wb_info->dwb_params.scaler_taps.v_taps_c;
-		pipes[pipe_cnt].dout.wb.wb_hratio = 1.0;
-		pipes[pipe_cnt].dout.wb.wb_vratio = 1.0;
-		if (wb_info->dwb_params.out_format == dwb_scaler_mode_yuv420) {
-			if (wb_info->dwb_params.output_depth == DWB_OUTPUT_PIXEL_DEPTH_8BPC)
-				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_8;
-			else
-				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_10;
-		} else
-			pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_444_32;
-
-		pipe_cnt++;
-	}
-
-}
-
 int dcn20_populate_dml_pipes_from_context(
 		struct dc *dc,
 		struct dc_state *context,
@@ -2392,7 +2357,9 @@ int dcn20_populate_dml_pipes_from_context(
 	}
 
 	/* populate writeback information */
+	DC_FP_START();
 	dc->res_pool->funcs->populate_dml_writeback_from_context(dc, res_ctx, pipes);
+	DC_FP_END();
 
 	return pipe_cnt;
 }
@@ -2462,7 +2429,7 @@ void dcn20_set_mcif_arb_params(
 				wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 				wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 			}
-			wb_arb_params->time_per_pixel = 16.0 / context->res_ctx.pipe_ctx[i].stream->phy_pix_clk; /* 4 bit fraction, ms */
+			wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 			wb_arb_params->slice_lines = 32;
 			wb_arb_params->arbitration_slice = 2;
 			wb_arb_params->max_scaled_time = dcn20_calc_max_scaled_time(wb_arb_params->time_per_pixel,
@@ -2531,16 +2498,16 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		 * pick that pipe as secondary
 		 * Same logic applies for ODM pipes
 		 */
-		if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe) {
-			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe->pipe_idx;
+		if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) {
+			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe->pipe_idx;
 			if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) {
 				secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
 				secondary_pipe->pipe_idx = preferred_pipe_idx;
 			}
 		}
 		if (secondary_pipe == NULL &&
-				dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) {
-			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe->pipe_idx;
+				dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe) {
+			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe->pipe_idx;
 			if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) {
 				secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
 				secondary_pipe->pipe_idx = preferred_pipe_idx;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index c8f3127bbcdf..6ec8ff45f0f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -58,8 +58,6 @@ struct pipe_ctx *dcn20_acquire_idle_pipe_for_layer(
 		struct dc_state *state,
 		const struct resource_pool *pool,
 		struct dc_stream_state *stream);
-void dcn20_populate_dml_writeback_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
 
 struct stream_encoder *dcn20_stream_encoder_create(
 	enum engine_id eng_id,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index 42fbb5e6d505..36044cb8ec83 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -701,6 +701,7 @@ static const struct hubbub_funcs hubbub21_funcs = {
 	.program_watermarks = hubbub21_program_watermarks,
 	.allow_self_refresh_control = hubbub1_allow_self_refresh_control,
 	.apply_DEDCN21_147_wa = hubbub21_apply_DEDCN21_147_wa,
+	.hubbub_read_state = hubbub2_read_state,
 };
 
 void hubbub21_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
index ef3ef28509ed..d8eb2bb7282c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
@@ -108,7 +108,19 @@
 	HUBBUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET, mask_sh), \
 	HUBBUB_SF(DCN_VM_AGP_BOT, AGP_BOT, mask_sh), \
 	HUBBUB_SF(DCN_VM_AGP_TOP, AGP_TOP, mask_sh), \
-	HUBBUB_SF(DCN_VM_AGP_BASE, AGP_BASE, mask_sh)
+	HUBBUB_SF(DCN_VM_AGP_BASE, AGP_BASE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_MSB, DCN_VM_FAULT_ADDR_MSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_LSB, DCN_VM_FAULT_ADDR_LSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_CLEAR, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_MODE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_INTERRUPT_ENABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_RANGE_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_PRQ_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_STATUS, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_TABLE_LEVEL, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh)
 
 void dcn21_dchvm_init(struct hubbub *hubbub);
 int hubbub21_init_dchub(struct hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index b0c9180b808f..3de1bcf9b3d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -833,7 +833,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.dmdata_set_attributes = hubp2_dmdata_set_attributes,
 	.dmdata_load = hubp2_dmdata_load,
 	.dmdata_status_done = hubp2_dmdata_status_done,
-	.hubp_read_state = hubp1_read_state,
+	.hubp_read_state = hubp2_read_state,
 	.hubp_clear_underflow = hubp1_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp21_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index bf0a198eae15..fbbdf9976183 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -35,6 +35,8 @@
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
 
+#include "dml/dcn2x/dcn2x.h"
+
 #include "clk_mgr.h"
 #include "dcn10/dcn10_hubp.h"
 #include "dcn10/dcn10_ipp.h"
@@ -884,7 +886,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.disable_48mhz_pwrdwn = false,
 		.usbc_combo_phy_reset_wa = true,
 		.dmub_command_table = true,
-		.use_max_lb = true
+		.use_max_lb = true,
+		.optimize_edp_link_rate = true
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
index 3fe9e41e4dbd..6a3d3a0ec0a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
@@ -49,6 +49,11 @@
 static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	struct dcn3_xfer_func_reg *reg)
 {
+	reg->shifts.field_region_start_base = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->masks.field_region_start_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
+	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
+
 	reg->shifts.exp_region0_lut_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->masks.exp_region0_lut_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->shifts.exp_region0_num_segments = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
@@ -66,8 +71,6 @@ static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	reg->masks.field_region_end_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_END_BASE_B;
 	reg->shifts.field_region_linear_slope = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
 	reg->masks.field_region_linear_slope = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
-	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
-	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
 	reg->shifts.exp_region_start = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->masks.exp_region_start = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->shifts.exp_resion_start_segment = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SEGMENT_B;
@@ -147,18 +150,19 @@ static enum dc_lut_mode dwb3_get_ogam_current(
 	uint32_t state_mode;
 	uint32_t ram_select;
 
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_MODE, &state_mode);
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, &ram_select);
+	REG_GET_2(DWB_OGAM_CONTROL,
+		DWB_OGAM_MODE_CURRENT, &state_mode,
+		DWB_OGAM_SELECT_CURRENT, &ram_select);
 
 	if (state_mode == 0) {
 		mode = LUT_BYPASS;
 	} else if (state_mode == 2) {
 		if (ram_select == 0)
 			mode = LUT_RAM_A;
-		else
+		else if (ram_select == 1)
 			mode = LUT_RAM_B;
+		else
+			mode = LUT_BYPASS;
 	} else {
 		// Reserved value
 		mode = LUT_BYPASS;
@@ -172,10 +176,10 @@ static void dwb3_configure_ogam_lut(
 	struct dcn30_dwbc *dwbc30,
 	bool is_ram_a)
 {
-	REG_UPDATE(DWB_OGAM_LUT_CONTROL,
-		DWB_OGAM_LUT_READ_COLOR_SEL, 7);
-	REG_UPDATE(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, is_ram_a == true ? 0 : 1);
+	REG_UPDATE_2(DWB_OGAM_LUT_CONTROL,
+		DWB_OGAM_LUT_WRITE_COLOR_MASK, 7,
+		DWB_OGAM_LUT_HOST_SEL, (is_ram_a == true) ? 0 : 1);
+
 	REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
 }
 
@@ -185,17 +189,45 @@ static void dwb3_program_ogam_pwl(struct dcn30_dwbc *dwbc30,
 {
 	uint32_t i;
 
-    // triple base implementation
-	for (i = 0; i < num/2; i++) {
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].blue_reg);
+	uint32_t last_base_value_red = rgb[num-1].red_reg + rgb[num-1].delta_red_reg;
+	uint32_t last_base_value_green = rgb[num-1].green_reg + rgb[num-1].delta_green_reg;
+	uint32_t last_base_value_blue = rgb[num-1].blue_reg + rgb[num-1].delta_blue_reg;
+
+	if (is_rgb_equal(rgb,  num)) {
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+	} else {
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 4);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 2);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].green_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_green);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 1);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].blue_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_blue);
 	}
 }
 
@@ -211,6 +243,8 @@ static bool dwb3_program_ogam_lut(
 		return false;
 	}
 
+	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
+
 	current_mode = dwb3_get_ogam_current(dwbc30);
 	if (current_mode == LUT_BYPASS || current_mode == LUT_RAM_A)
 		next_mode = LUT_RAM_B;
@@ -227,8 +261,7 @@ static bool dwb3_program_ogam_lut(
 	dwb3_program_ogam_pwl(
 		dwbc30, params->rgb_resulted, params->hw_points_num);
 
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
+	REG_UPDATE(DWB_OGAM_CONTROL, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
 
 	return true;
 }
@@ -271,14 +304,19 @@ static void dwb3_program_gamut_remap(
 
 	struct color_matrices_reg gam_regs;
 
-	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
-
 	if (regval == NULL || select == CM_GAMUT_REMAP_MODE_BYPASS) {
 		REG_SET(DWB_GAMUT_REMAP_MODE, 0,
 				DWB_GAMUT_REMAP_MODE, 0);
 		return;
 	}
 
+	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
+
+	gam_regs.shifts.csc_c11 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C11;
+	gam_regs.masks.csc_c11  = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C11;
+	gam_regs.shifts.csc_c12 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C12;
+	gam_regs.masks.csc_c12 = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C12;
+
 	switch (select) {
 	case CM_GAMUT_REMAP_MODE_RAMA_COEFF:
 		gam_regs.csc_c11_c12 = REG(DWB_GAMUT_REMAPA_C11_C12);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c
index c0980da6dc49..f4414de96acc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c
@@ -451,6 +451,7 @@ static const struct hubbub_funcs hubbub30_funcs = {
 	.force_wm_propagate_to_pipes = hubbub3_force_wm_propagate_to_pipes,
 	.force_pstate_change_control = hubbub3_force_pstate_change_control,
 	.init_watermarks = hubbub3_init_watermarks,
+	.hubbub_read_state = hubbub2_read_state,
 };
 
 void hubbub3_construct(struct dcn20_hubbub *hubbub3,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.h
index c0bd0fb09455..7b597908b937 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.h
@@ -87,7 +87,19 @@
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, DCHUBBUB_ARB_VM_ROW_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, mask_sh), \
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, DCHUBBUB_ARB_VM_ROW_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, mask_sh), \
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, DCHUBBUB_ARB_VM_ROW_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, mask_sh), \
-	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, DCHUBBUB_ARB_VM_ROW_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, mask_sh)
+	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, DCHUBBUB_ARB_VM_ROW_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_MSB, DCN_VM_FAULT_ADDR_MSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_LSB, DCN_VM_FAULT_ADDR_LSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_CLEAR, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_MODE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_INTERRUPT_ENABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_RANGE_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_PRQ_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_STATUS, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_TABLE_LEVEL, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh)
 
 void hubbub3_construct(struct dcn20_hubbub *hubbub3,
 	struct dc_context *ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index c68e3a708a33..fafed1e4a998 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -398,12 +398,22 @@ void dcn30_program_all_writeback_pipes_in_tree(
 			for (i_pipe = 0; i_pipe < dc->res_pool->pipe_count; i_pipe++) {
 				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i_pipe];
 
+				if (!pipe_ctx->plane_state)
+					continue;
+
 				if (pipe_ctx->plane_state == wb_info.writeback_source_plane) {
 					wb_info.mpcc_inst = pipe_ctx->plane_res.mpcc_inst;
 					break;
 				}
 			}
-			ASSERT(wb_info.mpcc_inst != -1);
+
+			if (wb_info.mpcc_inst == -1) {
+				/* Disable writeback pipe and disconnect from MPCC
+				 * if source plane has been removed
+				 */
+				dc->hwss.disable_writeback(dc, wb_info.dwb_pipe_inst);
+				continue;
+			}
 
 			ASSERT(wb_info.dwb_pipe_inst < dc->res_pool->res_cap->num_dwb);
 			dwb = dc->res_pool->dwbc[wb_info.dwb_pipe_inst];
@@ -580,22 +590,19 @@ void dcn30_init_hw(struct dc *dc)
 	 */
 	if (dc->config.power_down_display_on_boot) {
 		struct dc_link *edp_links[MAX_NUM_EDP];
-		struct dc_link *edp_link;
+		struct dc_link *edp_link = NULL;
 
 		get_edp_links(dc, edp_links, &edp_num);
-		if (edp_num) {
-			for (i = 0; i < edp_num; i++) {
-				edp_link = edp_links[i];
-				if (edp_link->link_enc->funcs->is_dig_enabled &&
-						edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
-						dc->hwss.edp_backlight_control &&
-						dc->hwss.power_down &&
-						dc->hwss.edp_power_control) {
-					dc->hwss.edp_backlight_control(edp_link, false);
-					dc->hwss.power_down(dc);
-					dc->hwss.edp_power_control(edp_link, false);
-				}
-			}
+		if (edp_num)
+			edp_link = edp_links[0];
+		if (edp_link && edp_link->link_enc->funcs->is_dig_enabled &&
+				edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
+				dc->hwss.edp_backlight_control &&
+				dc->hwss.power_down &&
+				dc->hwss.edp_power_control) {
+			dc->hwss.edp_backlight_control(edp_link, false);
+			dc->hwss.power_down(dc);
+			dc->hwss.edp_power_control(edp_link, false);
 		} else {
 			for (i = 0; i < dc->link_count; i++) {
 				struct dc_link *link = dc->links[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
index f37e8254df21..089be7347591 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
@@ -109,11 +109,9 @@ void optc3_lock(struct timing_generator *optc)
 	REG_SET(OTG_MASTER_UPDATE_LOCK, 0,
 		OTG_MASTER_UPDATE_LOCK, 1);
 
-	/* Should be fast, status does not update on maximus */
-	if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
-		REG_WAIT(OTG_MASTER_UPDATE_LOCK,
-				UPDATE_LOCK_STATUS, 1,
-				1, 10);
+	REG_WAIT(OTG_MASTER_UPDATE_LOCK,
+			UPDATE_LOCK_STATUS, 1,
+			1, 10);
 }
 
 void optc3_set_out_mux(struct timing_generator *optc, enum otg_out_mux_dest dest)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 28e15ebf2f43..a0de309475a9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -92,7 +92,7 @@
 #define DC_LOGGER_INIT(logger)
 
 struct _vcs_dpi_ip_params_st dcn3_0_ip = {
-	.use_min_dcfclk = 1,
+	.use_min_dcfclk = 0,
 	.clamp_min_dcfclk = 0,
 	.odm_capable = 1,
 	.gpuvm_enable = 0,
@@ -2398,16 +2398,37 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 
 	if (bw_params->clk_table.entries[0].memclk_mhz) {
+		int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0;
+
+		for (i = 0; i < MAX_NUM_DPM_LVL; i++) {
+			if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz)
+				max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz;
+			if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz)
+				max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz;
+			if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz)
+				max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz;
+			if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz)
+				max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz;
+		}
+
+		if (!max_dcfclk_mhz)
+			max_dcfclk_mhz = dcn3_0_soc.clock_limits[0].dcfclk_mhz;
+		if (!max_dispclk_mhz)
+			max_dispclk_mhz = dcn3_0_soc.clock_limits[0].dispclk_mhz;
+		if (!max_dppclk_mhz)
+			max_dppclk_mhz = dcn3_0_soc.clock_limits[0].dppclk_mhz;
+		if (!max_phyclk_mhz)
+			max_phyclk_mhz = dcn3_0_soc.clock_limits[0].phyclk_mhz;
 
-		if (bw_params->clk_table.entries[1].dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+		if (max_dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
 			// If max DCFCLK is greater than the max DCFCLK STA target, insert into the DCFCLK STA target array
-			dcfclk_sta_targets[num_dcfclk_sta_targets] = bw_params->clk_table.entries[1].dcfclk_mhz;
+			dcfclk_sta_targets[num_dcfclk_sta_targets] = max_dcfclk_mhz;
 			num_dcfclk_sta_targets++;
-		} else if (bw_params->clk_table.entries[1].dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+		} else if (max_dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
 			// If max DCFCLK is less than the max DCFCLK STA target, cap values and remove duplicates
 			for (i = 0; i < num_dcfclk_sta_targets; i++) {
-				if (dcfclk_sta_targets[i] > bw_params->clk_table.entries[1].dcfclk_mhz) {
-					dcfclk_sta_targets[i] = bw_params->clk_table.entries[1].dcfclk_mhz;
+				if (dcfclk_sta_targets[i] > max_dcfclk_mhz) {
+					dcfclk_sta_targets[i] = max_dcfclk_mhz;
 					break;
 				}
 			}
@@ -2447,7 +2468,7 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {
-				if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= bw_params->clk_table.entries[1].dcfclk_mhz) {
+				if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
 					dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
 					dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
 				} else {
@@ -2462,11 +2483,12 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		}
 
 		while (j < num_uclk_states && num_states < DC__VOLTAGE_STATES &&
-				optimal_dcfclk_for_uclk[j] <= bw_params->clk_table.entries[1].dcfclk_mhz) {
+				optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
 			dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
 			dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
 		}
 
+		dcn3_0_soc.num_states = num_states;
 		for (i = 0; i < dcn3_0_soc.num_states; i++) {
 			dcn3_0_soc.clock_limits[i].state = i;
 			dcn3_0_soc.clock_limits[i].dcfclk_mhz = dcfclk_mhz[i];
@@ -2474,9 +2496,9 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 			dcn3_0_soc.clock_limits[i].dram_speed_mts = dram_speed_mts[i];
 
 			/* Fill all states with max values of all other clocks */
-			dcn3_0_soc.clock_limits[i].dispclk_mhz = bw_params->clk_table.entries[1].dispclk_mhz;
-			dcn3_0_soc.clock_limits[i].dppclk_mhz  = bw_params->clk_table.entries[1].dppclk_mhz;
-			dcn3_0_soc.clock_limits[i].phyclk_mhz  = bw_params->clk_table.entries[1].phyclk_mhz;
+			dcn3_0_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
+			dcn3_0_soc.clock_limits[i].dppclk_mhz  = max_dppclk_mhz;
+			dcn3_0_soc.clock_limits[i].phyclk_mhz  = max_phyclk_mhz;
 			dcn3_0_soc.clock_limits[i].dtbclk_mhz = dcn3_0_soc.clock_limits[0].dtbclk_mhz;
 			/* These clocks cannot come from bw_params, always fill from dcn3_0_soc[1] */
 			/* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
@@ -2489,11 +2511,6 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		if (dc->current_state)
 			dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
 	}
-
-	/* re-init DML with updated bb */
-	dml_init_instance(&dc->dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
-	if (dc->current_state)
-		dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
 }
 
 static const struct resource_funcs dcn30_res_pool_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c
index a0b96b3c083f..1e3bd2e9cdcc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c
@@ -62,6 +62,7 @@ static const struct hubbub_funcs hubbub301_funcs = {
 	.is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled,
 	.force_wm_propagate_to_pipes = hubbub3_force_wm_propagate_to_pipes,
 	.force_pstate_change_control = hubbub3_force_pstate_change_control,
+	.hubbub_read_state = hubbub2_read_state,
 };
 
 void hubbub301_construct(struct dcn20_hubbub *hubbub3,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
index bb9648488900..90c73a1cb986 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
@@ -124,8 +124,8 @@ static void dcn31_program_compbuf_size(struct hubbub *hubbub, unsigned int compb
 		ASSERT(hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size
 				+ hubbub2->det3_size + compbuf_size_segments <= hubbub2->crb_size_segs);
 		REG_UPDATE(DCHUBBUB_COMPBUF_CTRL, COMPBUF_SIZE, compbuf_size_segments);
-		REG_WAIT(DCHUBBUB_COMPBUF_CTRL, COMPBUF_SIZE_CURRENT, compbuf_size_segments, 1, 100);
 		hubbub2->compbuf_size_segments = compbuf_size_segments;
+		ASSERT(REG_GET(DCHUBBUB_COMPBUF_CTRL, CONFIG_ERROR, &compbuf_size_segments) && !compbuf_size_segments);
 	}
 }
 
@@ -876,7 +876,33 @@ static bool hubbub31_get_dcc_compression_cap(struct hubbub *hubbub,
 static int hubbub31_init_dchub_sys_ctx(struct hubbub *hubbub,
 		struct dcn_hubbub_phys_addr_config *pa_config)
 {
-	hubbub3_init_dchub_sys_ctx(hubbub, pa_config);
+	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
+	struct dcn_vmid_page_table_config phys_config;
+
+	REG_SET(DCN_VM_FB_LOCATION_BASE, 0,
+			FB_BASE, pa_config->system_aperture.fb_base >> 24);
+	REG_SET(DCN_VM_FB_LOCATION_TOP, 0,
+			FB_TOP, pa_config->system_aperture.fb_top >> 24);
+	REG_SET(DCN_VM_FB_OFFSET, 0,
+			FB_OFFSET, pa_config->system_aperture.fb_offset >> 24);
+	REG_SET(DCN_VM_AGP_BOT, 0,
+			AGP_BOT, pa_config->system_aperture.agp_bot >> 24);
+	REG_SET(DCN_VM_AGP_TOP, 0,
+			AGP_TOP, pa_config->system_aperture.agp_top >> 24);
+	REG_SET(DCN_VM_AGP_BASE, 0,
+			AGP_BASE, pa_config->system_aperture.agp_base >> 24);
+
+	if (pa_config->gart_config.page_table_start_addr != pa_config->gart_config.page_table_end_addr) {
+		phys_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr >> 12;
+		phys_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr >> 12;
+		phys_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr;
+		phys_config.depth = 0;
+		phys_config.block_size = 0;
+		// Init VMID 0 based on PA config
+		dcn20_vmid_setup(&hubbub2->vmid[0], &phys_config);
+
+		dcn20_vmid_setup(&hubbub2->vmid[15], &phys_config);
+	}
 
 	dcn21_dchvm_init(hubbub);
 
@@ -934,7 +960,8 @@ static const struct hubbub_funcs hubbub31_funcs = {
 	.is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled,
 	.program_det_size = dcn31_program_det_size,
 	.program_compbuf_size = dcn31_program_compbuf_size,
-	.init_crb = dcn31_init_crb
+	.init_crb = dcn31_init_crb,
+	.hubbub_read_state = hubbub2_read_state,
 };
 
 void hubbub31_construct(struct dcn20_hubbub *hubbub31,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h
index 8ec98cbcbd47..e3a654bf04e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h
@@ -98,6 +98,7 @@
 	HUBBUB_SF(DCHUBBUB_DET3_CTRL, DET3_SIZE_CURRENT, mask_sh),\
 	HUBBUB_SF(DCHUBBUB_COMPBUF_CTRL, COMPBUF_SIZE, mask_sh),\
 	HUBBUB_SF(DCHUBBUB_COMPBUF_CTRL, COMPBUF_SIZE_CURRENT, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_COMPBUF_CTRL, CONFIG_ERROR, mask_sh),\
 	HUBBUB_SF(COMPBUF_RESERVED_SPACE, COMPBUF_RESERVED_SPACE_64B, mask_sh),\
 	HUBBUB_SF(COMPBUF_RESERVED_SPACE, COMPBUF_RESERVED_SPACE_ZS, mask_sh),\
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_A, DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_A, mask_sh), \
@@ -107,7 +108,19 @@
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_A, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_A, mask_sh), \
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_B, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_B, mask_sh), \
 	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_C, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_C, mask_sh), \
-	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D, mask_sh)
+	HUBBUB_SF(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_MSB, DCN_VM_FAULT_ADDR_MSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_ADDR_LSB, DCN_VM_FAULT_ADDR_LSB, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_CLEAR, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_STATUS_MODE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_ERROR_INTERRUPT_ENABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_RANGE_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_CNTL, DCN_VM_PRQ_FAULT_DISABLE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_STATUS, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_TABLE_LEVEL, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \
+	HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh)
 
 
 void hubbub31_construct(struct dcn20_hubbub *hubbub3,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 8a2119d8ca0d..3f2333ec67e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -226,6 +226,7 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->config.power_down_display_on_boot) {
 		struct dc_link *edp_links[MAX_NUM_EDP];
 		struct dc_link *edp_link;
+		bool power_down = false;
 
 		get_edp_links(dc, edp_links, &edp_num);
 		if (edp_num) {
@@ -239,9 +240,11 @@ void dcn31_init_hw(struct dc *dc)
 					dc->hwss.edp_backlight_control(edp_link, false);
 					dc->hwss.power_down(dc);
 					dc->hwss.edp_power_control(edp_link, false);
+					power_down = true;
 				}
 			}
-		} else {
+		}
+		if (!power_down) {
 			for (i = 0; i < dc->link_count; i++) {
 				struct dc_link *link = dc->links[i];
 
@@ -607,20 +610,3 @@ bool dcn31_is_abm_supported(struct dc *dc,
 	}
 	return false;
 }
-
-static void apply_riommu_invalidation_wa(struct dc *dc)
-{
-	struct dce_hwseq *hws = dc->hwseq;
-
-	if (!hws->wa.early_riommu_invalidation)
-		return;
-
-	REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, 0);
-}
-
-void dcn31_init_pipes(struct dc *dc, struct dc_state *context)
-{
-	dcn10_init_pipes(dc, context);
-	apply_riommu_invalidation_wa(dc);
-
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index b30d923471cb..40011cd3c8ef 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -104,7 +104,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 };
 
 static const struct hwseq_private_funcs dcn31_private_funcs = {
-	.init_pipes = dcn31_init_pipes,
+	.init_pipes = dcn10_init_pipes,
 	.update_plane_addr = dcn20_update_plane_addr,
 	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
 	.update_mpcc = dcn20_update_mpcc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index cd3248dc31d8..a7702d3c75cd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -1302,7 +1302,6 @@ static struct dce_hwseq *dcn31_hwseq_create(
 		hws->regs = &hwseq_reg;
 		hws->shifts = &hwseq_shift;
 		hws->masks = &hwseq_mask;
-		hws->wa.early_riommu_invalidation = true;
 	}
 	return hws;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 45862167e6ce..56055df2e8d2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -58,6 +58,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
@@ -70,6 +72,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(fram
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_rcflags)
@@ -91,6 +94,7 @@ DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
+DML += dcn2x/dcn2x.o
 DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 DML += dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 799bae229e67..2091dd8c252d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -488,7 +488,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index 6a6d5970d1d5..1a0c14e465fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -488,7 +488,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 6655bb99fdfd..4136eb8256cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -2270,7 +2270,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 					&locals->UrgentBurstFactorLumaPre[k],
 					&locals->UrgentBurstFactorChroma[k],
 					&locals->UrgentBurstFactorChromaPre[k],
-					&locals->NotEnoughUrgentLatencyHiding,
+					&locals->NotEnoughUrgentLatencyHiding[0][0],
 					&locals->NotEnoughUrgentLatencyHidingPre);
 
 			if (mode_lib->vba.UseUrgentBurstBandwidth == false) {
@@ -2303,7 +2303,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		}
 		mode_lib->vba.FractionOfUrgentBandwidth = MaxTotalRDBandwidthNoUrgentBurst / mode_lib->vba.ReturnBW;
 
-		if (MaxTotalRDBandwidth <= mode_lib->vba.ReturnBW && locals->NotEnoughUrgentLatencyHiding == 0 && locals->NotEnoughUrgentLatencyHidingPre == 0 && !VRatioPrefetchMoreThan4
+		if (MaxTotalRDBandwidth <= mode_lib->vba.ReturnBW && locals->NotEnoughUrgentLatencyHiding[0][0] == 0 &&
+				locals->NotEnoughUrgentLatencyHidingPre == 0 && !VRatioPrefetchMoreThan4
 				&& !DestinationLineTimesForPrefetchLessThan2)
 			mode_lib->vba.PrefetchModeSupported = true;
 		else {
@@ -4824,7 +4825,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							&locals->UrgentBurstFactorLumaPre[k],
 							&locals->UrgentBurstFactorChroma[k],
 							&locals->UrgentBurstFactorChromaPre[k],
-							&locals->NotEnoughUrgentLatencyHiding,
+							&locals->NotEnoughUrgentLatencyHiding[0][0],
 							&locals->NotEnoughUrgentLatencyHidingPre);
 
 					if (mode_lib->vba.UseUrgentBurstBandwidth == false) {
@@ -4851,13 +4852,13 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
 				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]
-						|| locals->NotEnoughUrgentLatencyHiding == 1) {
+						|| locals->NotEnoughUrgentLatencyHiding[0][0] == 1) {
 					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
 				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]
-						|| locals->NotEnoughUrgentLatencyHiding == 1
+						|| locals->NotEnoughUrgentLatencyHiding[0][0] == 1
 						|| locals->NotEnoughUrgentLatencyHidingPre == 1) {
 					locals->PrefetchSupported[i][j] = false;
 				}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index dc1c81a6e377..287e31052b30 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -482,7 +482,7 @@ static void get_meta_and_pte_attr(
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c
new file mode 100644
index 000000000000..c58522436291
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "resource.h"
+
+#include "dcn2x.h"
+
+/**
+ * DOC: DCN2x FPU manipulation Overview
+ *
+ * The DCN architecture relies on FPU operations, which require special
+ * compilation flags and the use of kernel_fpu_begin/end functions; ideally, we
+ * want to avoid spreading FPU access across multiple files. With this idea in
+ * mind, this file aims to centralize all DCN20 and DCN2.1 (DCN2x) functions
+ * that require FPU access in a single place. Code in this file follows the
+ * following code pattern:
+ *
+ * 1. Functions that use FPU operations should be isolated in static functions.
+ * 2. The FPU functions should have the noinline attribute to ensure anything
+ *    that deals with FP register is contained within this call.
+ * 3. All function that needs to be accessed outside this file requires a
+ *    public interface that not uses any FPU reference.
+ * 4. Developers **must not** use DC_FP_START/END in this file, but they need
+ *    to ensure that the caller invokes it before access any function available
+ *    in this file. For this reason, public functions in this file must invoke
+ *    dc_assert_fp_enabled();
+ *
+ * Let's expand a little bit more the idea in the code pattern. To fully
+ * isolate FPU operations in a single place, we must avoid situations where
+ * compilers spill FP values to registers due to FP enable in a specific C
+ * file. Note that even if we isolate all FPU functions in a single file and
+ * call its interface from other files, the compiler might enable the use of
+ * FPU before we call DC_FP_START. Nevertheless, it is the programmer's
+ * responsibility to invoke DC_FP_START/END in the correct place. To highlight
+ * situations where developers forgot to use the FP protection before calling
+ * the DC FPU interface functions, we introduce a helper that checks if the
+ * function is invoked under FP protection. If not, it will trigger a kernel
+ * warning.
+ */
+
+void dcn20_populate_dml_writeback_from_context(struct dc *dc,
+					       struct resource_context *res_ctx,
+					       display_e2e_pipe_params_st *pipes)
+{
+	int pipe_cnt, i;
+
+	dc_assert_fp_enabled();
+
+	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_writeback_info *wb_info = &res_ctx->pipe_ctx[i].stream->writeback_info[0];
+
+		if (!res_ctx->pipe_ctx[i].stream)
+			continue;
+
+		/* Set writeback information */
+		pipes[pipe_cnt].dout.wb_enable = (wb_info->wb_enabled == true) ? 1 : 0;
+		pipes[pipe_cnt].dout.num_active_wb++;
+		pipes[pipe_cnt].dout.wb.wb_src_height = wb_info->dwb_params.cnv_params.crop_height;
+		pipes[pipe_cnt].dout.wb.wb_src_width = wb_info->dwb_params.cnv_params.crop_width;
+		pipes[pipe_cnt].dout.wb.wb_dst_width = wb_info->dwb_params.dest_width;
+		pipes[pipe_cnt].dout.wb.wb_dst_height = wb_info->dwb_params.dest_height;
+		pipes[pipe_cnt].dout.wb.wb_htaps_luma = 1;
+		pipes[pipe_cnt].dout.wb.wb_vtaps_luma = 1;
+		pipes[pipe_cnt].dout.wb.wb_htaps_chroma = wb_info->dwb_params.scaler_taps.h_taps_c;
+		pipes[pipe_cnt].dout.wb.wb_vtaps_chroma = wb_info->dwb_params.scaler_taps.v_taps_c;
+		pipes[pipe_cnt].dout.wb.wb_hratio = 1.0;
+		pipes[pipe_cnt].dout.wb.wb_vratio = 1.0;
+		if (wb_info->dwb_params.out_format == dwb_scaler_mode_yuv420) {
+			if (wb_info->dwb_params.output_depth == DWB_OUTPUT_PIXEL_DEPTH_8BPC)
+				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_8;
+			else
+				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_10;
+		} else {
+			pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_444_32;
+		}
+
+		pipe_cnt++;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.h b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.h
new file mode 100644
index 000000000000..331547ba0713
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DCN2X_H__
+#define __DCN2X_H__
+
+void dcn20_populate_dml_writeback_from_context(struct dc *dc,
+					       struct resource_context *res_ctx,
+					       display_e2e_pipe_params_st *pipes);
+
+#endif /* __DCN2X_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index 9d2016d8fafe..e3d9f1decdfc 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -2596,7 +2596,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			}
 		}
 
-		v->NotEnoughUrgentLatencyHiding = false;
+		v->NotEnoughUrgentLatencyHiding[0][0] = false;
 		v->NotEnoughUrgentLatencyHidingPre = false;
 
 		for (k = 0; k < v->NumberOfActivePlanes; ++k) {
@@ -2681,7 +2681,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			if (v->VRatioPrefetchY[k] > 4 || v->VRatioPrefetchC[k] > 4)
 				VRatioPrefetchMoreThan4 = true;
 			if (v->NoUrgentLatencyHiding[k] == true)
-				v->NotEnoughUrgentLatencyHiding = true;
+				v->NotEnoughUrgentLatencyHiding[0][0] = true;
 
 			if (v->NoUrgentLatencyHidingPre[k] == true)
 				v->NotEnoughUrgentLatencyHidingPre = true;
@@ -2689,7 +2689,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		v->FractionOfUrgentBandwidth = MaxTotalRDBandwidthNoUrgentBurst / v->ReturnBW;
 
 
-		if (MaxTotalRDBandwidth <= v->ReturnBW && v->NotEnoughUrgentLatencyHiding == 0 && v->NotEnoughUrgentLatencyHidingPre == 0 && !VRatioPrefetchMoreThan4
+		if (MaxTotalRDBandwidth <= v->ReturnBW && v->NotEnoughUrgentLatencyHiding[0][0] == 0
+				&& v->NotEnoughUrgentLatencyHidingPre == 0 && !VRatioPrefetchMoreThan4
 				&& !DestinationLineTimesForPrefetchLessThan2)
 			v->PrefetchModeSupported = true;
 		else {
@@ -2794,8 +2795,9 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		}
 
 		v->VStartupLines = v->VStartupLines + 1;
-		v->PrefetchAndImmediateFlipSupported = (v->PrefetchModeSupported == true && ((!v->ImmediateFlipSupport && !v->HostVMEnable && v->ImmediateFlipRequirement != dm_immediate_flip_required) || v->ImmediateFlipSupported)) ? true : false;
-
+		v->PrefetchModeSupported = (v->PrefetchModeSupported == true && ((!v->ImmediateFlipSupport &&
+				!v->HostVMEnable && v->ImmediateFlipRequirement[0] != dm_immediate_flip_required) ||
+				v->ImmediateFlipSupported)) ? true : false;
 	} while (!v->PrefetchModeSupported && v->VStartupLines <= v->MaximumMaxVStartupLines);
 	ASSERT(v->PrefetchModeSupported);
 
@@ -3642,8 +3644,7 @@ static double TruncToValidBPP(
 void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
 {
 	struct vba_vars_st *v = &mode_lib->vba;
-	int MinPrefetchMode = 0;
-	int MaxPrefetchMode = 2;
+	int MinPrefetchMode, MaxPrefetchMode;
 	int i;
 	unsigned int j, k, m;
 	bool   EnoughWritebackUnits = true;
@@ -3655,6 +3656,10 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 	/*MODE SUPPORT, VOLTAGE STATE AND SOC CONFIGURATION*/
 
+	CalculateMinAndMaxPrefetchMode(
+		mode_lib->vba.AllowDRAMSelfRefreshOrDRAMClockChangeInVblank,
+		&MinPrefetchMode, &MaxPrefetchMode);
+
 	/*Scale Ratio, taps Support Check*/
 
 	v->ScaleRatioAndTapsSupport = true;
@@ -4753,7 +4758,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				v->HostVMMinPageSize,
 				v->HostVMMaxNonCachedPageTableLevels,
 				v->DynamicMetadataVMEnabled,
-				v->ImmediateFlipRequirement,
+				v->ImmediateFlipRequirement[0],
 				v->ProgressiveToInterlaceUnitInOPP,
 				v->MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation,
 				v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
@@ -5164,7 +5169,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					v->NextMaxVStartup = v->NextMaxVStartup - 1;
 				}
 			} while (!((v->PrefetchSupported[i][j] == true && v->DynamicMetadataSupported[i][j] == true && v->VRatioInPrefetchSupported[i][j] == true
-					&& ((v->HostVMEnable == false && v->ImmediateFlipRequirement != dm_immediate_flip_required)
+					&& ((v->HostVMEnable == false && v->ImmediateFlipRequirement[0] != dm_immediate_flip_required)
 							|| v->ImmediateFlipSupportedForState[i][j] == true))
 					|| (v->NextMaxVStartup == v->MaxMaxVStartup[i][j] && NextPrefetchModeState > MaxPrefetchMode)));
 
@@ -5305,7 +5310,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					&& ViewportExceedsSurface == 0 && v->PrefetchSupported[i][j] == 1 && v->DynamicMetadataSupported[i][j] == 1
 					&& v->TotalVerticalActiveBandwidthSupport[i][j] == 1 && v->VRatioInPrefetchSupported[i][j] == 1
 					&& v->PTEBufferSizeNotExceeded[i][j] == 1 && v->NonsupportedDSCInputBPC == 0
-					&& ((v->HostVMEnable == 0 && v->ImmediateFlipRequirement != dm_immediate_flip_required)
+					&& ((v->HostVMEnable == 0 && v->ImmediateFlipRequirement[0] != dm_immediate_flip_required)
 							|| v->ImmediateFlipSupportedForState[i][j] == true)) {
 				v->ModeSupport[i][j] = true;
 			} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
index 04601a767a8f..0d934fae1c3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
@@ -549,7 +549,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 				 // each 64b meta request for dcn is 8x8 meta elements and
-				 // a meta element covers one 256b block of the the data surface.
+				 // a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 		- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index a9667068c690..ce55c9caf9a2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -3036,10 +3036,9 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		}
 
 		v->PrefetchAndImmediateFlipSupported =
-				(v->PrefetchModeSupported == true
-						&& ((!v->ImmediateFlipSupport && !v->HostVMEnable
-								&& v->ImmediateFlipRequirement != dm_immediate_flip_required) || v->ImmediateFlipSupported)) ?
-						true : false;
+				(v->PrefetchModeSupported == true && ((!v->ImmediateFlipSupport && !v->HostVMEnable
+				&& v->ImmediateFlipRequirement[0] != dm_immediate_flip_required) ||
+				v->ImmediateFlipSupported)) ? true : false;
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: PrefetchModeSupported %d\n", __func__, v->PrefetchModeSupported);
 		dml_print("DML::%s: ImmediateFlipRequirement %d\n", __func__, v->ImmediateFlipRequirement == dm_immediate_flip_required);
@@ -5103,7 +5102,7 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				v->HostVMMinPageSize,
 				v->HostVMMaxNonCachedPageTableLevels,
 				v->DynamicMetadataVMEnabled,
-				v->ImmediateFlipRequirement,
+				v->ImmediateFlipRequirement[0],
 				v->ProgressiveToInterlaceUnitInOPP,
 				v->MaxAveragePercentOfIdealFabricAndSDPPortBWDisplayCanUseInNormalSystemOperation,
 				v->PercentOfIdealFabricAndSDPPortBWReceivedAfterUrgLatency,
@@ -5542,7 +5541,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				v->NextPrefetchMode = v->NextPrefetchMode + 1;
 			} while (!((v->PrefetchSupported[i][j] == true && v->DynamicMetadataSupported[i][j] == true && v->VRatioInPrefetchSupported[i][j] == true
-					&& ((v->HostVMEnable == false && v->ImmediateFlipRequirement != dm_immediate_flip_required)
+					&& ((v->HostVMEnable == false &&
+							v->ImmediateFlipRequirement[0] != dm_immediate_flip_required)
 							|| v->ImmediateFlipSupportedForState[i][j] == true))
 					|| (v->NextMaxVStartup == v->MaxMaxVStartup[i][j] && NextPrefetchModeState > MaxPrefetchMode)));
 
@@ -5702,7 +5702,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					&& v->PrefetchSupported[i][j] == true && v->DynamicMetadataSupported[i][j] == true
 					&& v->TotalVerticalActiveBandwidthSupport[i][j] == true && v->VRatioInPrefetchSupported[i][j] == true
 					&& v->PTEBufferSizeNotExceeded[i][j] == true && v->NonsupportedDSCInputBPC == false
-					&& ((v->HostVMEnable == false && v->ImmediateFlipRequirement != dm_immediate_flip_required)
+					&& ((v->HostVMEnable == false
+					&& v->ImmediateFlipRequirement[0] != dm_immediate_flip_required)
 							|| v->ImmediateFlipSupportedForState[i][j] == true)
 					&& FMTBufferExceeded == false) {
 				v->ModeSupport[i][j] = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index 3def093ef88e..c23905bc733a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -563,7 +563,7 @@ static void get_meta_and_pte_attr(
 	log2_meta_req_bytes = 6;	// meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3;	// meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element - log2_meta_req_height;
 	meta_req_width = 1 << log2_meta_req_width;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
index 64f9c735f74d..1051ca1a23b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
@@ -109,7 +109,9 @@ enum clock_change_support {
 };
 
 enum output_standard {
-	dm_std_uninitialized = 0, dm_std_cvtr2, dm_std_cvt
+	dm_std_uninitialized = 0,
+	dm_std_cvtr2,
+	dm_std_cvt
 };
 
 enum mpc_combine_affinity {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 64daa0507393..d46a2733024c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -536,6 +536,8 @@ struct _vcs_dpi_display_rq_regs_st {
 	unsigned int mrq_expansion_mode;
 	unsigned int crq_expansion_mode;
 	unsigned int plane1_base_address;
+	unsigned int aperture_low_addr;   // bits [47:18]
+	unsigned int aperture_high_addr;  // bits [47:18]
 };
 
 struct _vcs_dpi_display_dlg_sys_params_st {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index d3b1b6d4ce2f..0fad15020c74 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -244,6 +244,8 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib)
 	mode_lib->vba.DRAMClockChangeSupportsVActive = !soc->disable_dram_clock_change_vactive_support ||
 			mode_lib->vba.DummyPStateCheck;
 	mode_lib->vba.AllowDramClockChangeOneDisplayVactive = soc->allow_dram_clock_one_display_vactive;
+	mode_lib->vba.AllowDRAMSelfRefreshOrDRAMClockChangeInVblank =
+		soc->allow_dram_self_refresh_or_dram_clock_change_in_vblank;
 
 	mode_lib->vba.Downspreading = soc->downspread_percent;
 	mode_lib->vba.DRAMChannelWidth = soc->dram_channel_width_bytes;   // new!
@@ -396,7 +398,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 
 	mode_lib->vba.NumberOfActivePlanes = 0;
 	mode_lib->vba.ImmediateFlipSupport = false;
-	mode_lib->vba.ImmediateFlipRequirement = dm_immediate_flip_not_required;
 	for (j = 0; j < mode_lib->vba.cache_num_pipes; ++j) {
 		display_pipe_source_params_st *src = &pipes[j].pipe.src;
 		display_pipe_dest_params_st *dst = &pipes[j].pipe.dest;
@@ -409,6 +410,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 			continue;
 		visited[j] = true;
 
+		mode_lib->vba.ImmediateFlipRequirement[j] = dm_immediate_flip_not_required;
 		mode_lib->vba.pipe_plane[j] = mode_lib->vba.NumberOfActivePlanes;
 		mode_lib->vba.DPPPerPlane[mode_lib->vba.NumberOfActivePlanes] = 1;
 		mode_lib->vba.SourceScan[mode_lib->vba.NumberOfActivePlanes] =
@@ -667,9 +669,9 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				mode_lib->vba.ViewportHeightChroma[mode_lib->vba.NumberOfActivePlanes] = src->viewport_height_max / vdiv_c;
 		}
 
-		if (pipes[k].pipe.src.immediate_flip) {
+		if (pipes[j].pipe.src.immediate_flip) {
 			mode_lib->vba.ImmediateFlipSupport = true;
-			mode_lib->vba.ImmediateFlipRequirement = dm_immediate_flip_required;
+			mode_lib->vba.ImmediateFlipRequirement[j] = dm_immediate_flip_required;
 		}
 
 		mode_lib->vba.NumberOfActivePlanes++;
@@ -733,8 +735,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 						mode_lib->vba.OverrideHostVMPageTableLevels;
 	}
 
-	mode_lib->vba.AllowDRAMSelfRefreshOrDRAMClockChangeInVblank = dm_try_to_allow_self_refresh_and_mclk_switch;
-
 	if (mode_lib->vba.OverrideGPUVMPageTableLevels)
 		mode_lib->vba.GPUVMMaxPageTableLevels = mode_lib->vba.OverrideGPUVMPageTableLevels;
 
@@ -845,9 +845,10 @@ void PixelClockAdjustmentForProgressiveToInterlaceUnit(struct display_mode_lib *
 
 	//Progressive To Interlace Unit Effect
 	for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
+		mode_lib->vba.PixelClockBackEnd[k] = mode_lib->vba.PixelClock[k];
 		if (mode_lib->vba.Interlace[k] == 1
 				&& mode_lib->vba.ProgressiveToInterlaceUnitInOPP == true) {
-			mode_lib->vba.PixelClock[k] = 2 * mode_lib->vba.PixelClockBackEnd[k];
+			mode_lib->vba.PixelClock[k] = 2 * mode_lib->vba.PixelClock[k];
 		}
 	}
 }
@@ -890,8 +891,9 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib)
 		mode_lib->vba.DISPCLK = soc->clock_limits[mode_lib->vba.VoltageLevel].dispclk_mhz;
 
 	// Total Available Pipes Support Check
-	for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k)
+	for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
 		total_pipes += mode_lib->vba.DPPPerPlane[k];
+	}
 	ASSERT(total_pipes <= DC__NUM_DPP__MAX);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index d18a021d4d32..90e87961fe3e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -676,7 +676,7 @@ struct vba_vars_st {
 	double         AlignedDCCMetaPitchY[DC__NUM_DPP__MAX];
 	double         AlignedDCCMetaPitchC[DC__NUM_DPP__MAX];
 
-	unsigned int NotEnoughUrgentLatencyHiding;
+	unsigned int NotEnoughUrgentLatencyHiding[DC__VOLTAGE_STATES][2];
 	unsigned int NotEnoughUrgentLatencyHidingPre;
 	int PTEBufferSizeInRequestsForLuma;
 	int PTEBufferSizeInRequestsForChroma;
@@ -877,7 +877,7 @@ struct vba_vars_st {
 
 	int PercentMarginOverMinimumRequiredDCFCLK;
 	bool DynamicMetadataSupported[DC__VOLTAGE_STATES][2];
-	enum immediate_flip_requirement ImmediateFlipRequirement;
+	enum immediate_flip_requirement ImmediateFlipRequirement[DC__NUM_DPP__MAX];
 	unsigned int DETBufferSizeYThisState[DC__NUM_DPP__MAX];
 	unsigned int DETBufferSizeCThisState[DC__NUM_DPP__MAX];
 	bool NoUrgentLatencyHiding[DC__NUM_DPP__MAX];
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index 414da64f5734..8f2b1684c231 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -456,7 +456,7 @@ static void dml1_rq_dlg_get_row_heights(
 	log2_meta_req_bytes = 6; /* meta request is 64b and is 8x8byte meta element */
 
 	/* each 64b meta request for dcn is 8x8 meta elements and
-	 * a meta element covers one 256b block of the the data surface.
+	 * a meta element covers one 256b block of the data surface.
 	 */
 	log2_meta_req_height = log2_blk256_height + 3; /* meta req is 8x8 */
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
@@ -718,7 +718,7 @@ static void get_surf_rq_param(
 	log2_meta_req_bytes = 6; /* meta request is 64b and is 8x8byte meta element */
 
 	/* each 64b meta request for dcn is 8x8 meta elements and
-	 * a meta element covers one 256b block of the the data surface.
+	 * a meta element covers one 256b block of the data surface.
 	 */
 	log2_meta_req_height = log2_blk256_height + 3; /* meta req is 8x8 byte, each byte represent 1 blk256 */
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index f403d8e84a8c..f5b7da0e64c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -28,6 +28,7 @@
 #include <drm/drm_dp_helper.h>
 #include "dc.h"
 #include "rc_calc.h"
+#include "fixed31_32.h"
 
 /* This module's internal functions */
 
@@ -39,6 +40,47 @@ static bool dsc_policy_enable_dsc_when_not_needed;
 
 static bool dsc_policy_disable_dsc_stream_overhead;
 
+/* Forward Declerations */
+static void get_dsc_bandwidth_range(
+		const uint32_t min_bpp_x16,
+		const uint32_t max_bpp_x16,
+		const uint32_t num_slices_h,
+		const struct dsc_enc_caps *dsc_caps,
+		const struct dc_crtc_timing *timing,
+		struct dc_dsc_bw_range *range);
+
+static uint32_t compute_bpp_x16_from_target_bandwidth(
+		const uint32_t bandwidth_in_kbps,
+		const struct dc_crtc_timing *timing,
+		const uint32_t num_slices_h,
+		const uint32_t bpp_increment_div,
+		const bool is_dp);
+
+static void get_dsc_enc_caps(
+		const struct display_stream_compressor *dsc,
+		struct dsc_enc_caps *dsc_enc_caps,
+		int pixel_clock_100Hz);
+
+static bool intersect_dsc_caps(
+		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const struct dsc_enc_caps *dsc_enc_caps,
+		enum dc_pixel_encoding pixel_encoding,
+		struct dsc_enc_caps *dsc_common_caps);
+
+static bool setup_dsc_config(
+		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const struct dsc_enc_caps *dsc_enc_caps,
+		int target_bandwidth_kbps,
+		const struct dc_crtc_timing *timing,
+		int min_slice_height_override,
+		int max_dsc_target_bpp_limit_override_x16,
+		struct dc_dsc_config *dsc_cfg);
+
+static struct fixed31_32 compute_dsc_max_bandwidth_overhead(
+		const struct dc_crtc_timing *timing,
+		const int num_slices_h,
+		const bool is_dp);
+
 static bool dsc_buff_block_size_from_dpcd(int dpcd_buff_block_size, int *buff_block_size)
 {
 
@@ -171,10 +213,164 @@ static bool dsc_bpp_increment_div_from_dpcd(uint8_t bpp_increment_dpcd, uint32_t
 	return true;
 }
 
+
+
+bool dc_dsc_parse_dsc_dpcd(const struct dc *dc,
+		const uint8_t *dpcd_dsc_basic_data,
+		const uint8_t *dpcd_dsc_branch_decoder_caps,
+		struct dsc_dec_dpcd_caps *dsc_sink_caps)
+{
+	if (!dpcd_dsc_basic_data)
+		return false;
+
+	dsc_sink_caps->is_dsc_supported =
+		(dpcd_dsc_basic_data[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & DP_DSC_DECOMPRESSION_IS_SUPPORTED) != 0;
+	if (!dsc_sink_caps->is_dsc_supported)
+		return false;
+
+	dsc_sink_caps->dsc_version = dpcd_dsc_basic_data[DP_DSC_REV - DP_DSC_SUPPORT];
+
+	{
+		int buff_block_size;
+		int buff_size;
+
+		if (!dsc_buff_block_size_from_dpcd(dpcd_dsc_basic_data[DP_DSC_RC_BUF_BLK_SIZE - DP_DSC_SUPPORT],
+										   &buff_block_size))
+			return false;
+
+		buff_size = dpcd_dsc_basic_data[DP_DSC_RC_BUF_SIZE - DP_DSC_SUPPORT] + 1;
+		dsc_sink_caps->rc_buffer_size = buff_size * buff_block_size;
+	}
+
+	dsc_sink_caps->slice_caps1.raw = dpcd_dsc_basic_data[DP_DSC_SLICE_CAP_1 - DP_DSC_SUPPORT];
+	if (!dsc_line_buff_depth_from_dpcd(dpcd_dsc_basic_data[DP_DSC_LINE_BUF_BIT_DEPTH - DP_DSC_SUPPORT],
+									   &dsc_sink_caps->lb_bit_depth))
+		return false;
+
+	dsc_sink_caps->is_block_pred_supported =
+		(dpcd_dsc_basic_data[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] &
+		 DP_DSC_BLK_PREDICTION_IS_SUPPORTED) != 0;
+
+	dsc_sink_caps->edp_max_bits_per_pixel =
+		dpcd_dsc_basic_data[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] |
+		dpcd_dsc_basic_data[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] << 8;
+
+	dsc_sink_caps->color_formats.raw = dpcd_dsc_basic_data[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT];
+	dsc_sink_caps->color_depth.raw = dpcd_dsc_basic_data[DP_DSC_DEC_COLOR_DEPTH_CAP - DP_DSC_SUPPORT];
+
+	{
+		int dpcd_throughput = dpcd_dsc_basic_data[DP_DSC_PEAK_THROUGHPUT - DP_DSC_SUPPORT];
+
+		if (!dsc_throughput_from_dpcd(dpcd_throughput & DP_DSC_THROUGHPUT_MODE_0_MASK,
+									  &dsc_sink_caps->throughput_mode_0_mps))
+			return false;
+
+		dpcd_throughput = (dpcd_throughput & DP_DSC_THROUGHPUT_MODE_1_MASK) >> DP_DSC_THROUGHPUT_MODE_1_SHIFT;
+		if (!dsc_throughput_from_dpcd(dpcd_throughput, &dsc_sink_caps->throughput_mode_1_mps))
+			return false;
+	}
+
+	dsc_sink_caps->max_slice_width = dpcd_dsc_basic_data[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * 320;
+	dsc_sink_caps->slice_caps2.raw = dpcd_dsc_basic_data[DP_DSC_SLICE_CAP_2 - DP_DSC_SUPPORT];
+
+	if (!dsc_bpp_increment_div_from_dpcd(dpcd_dsc_basic_data[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT],
+										 &dsc_sink_caps->bpp_increment_div))
+		return false;
+
+	if (dc->debug.dsc_bpp_increment_div) {
+		/* dsc_bpp_increment_div should onl be 1, 2, 4, 8 or 16, but rather than rejecting invalid values,
+		 * we'll accept all and get it into range. This also makes the above check against 0 redundant,
+		 * but that one stresses out the override will be only used if it's not 0.
+		 */
+		if (dc->debug.dsc_bpp_increment_div >= 1)
+			dsc_sink_caps->bpp_increment_div = 1;
+		if (dc->debug.dsc_bpp_increment_div >= 2)
+			dsc_sink_caps->bpp_increment_div = 2;
+		if (dc->debug.dsc_bpp_increment_div >= 4)
+			dsc_sink_caps->bpp_increment_div = 4;
+		if (dc->debug.dsc_bpp_increment_div >= 8)
+			dsc_sink_caps->bpp_increment_div = 8;
+		if (dc->debug.dsc_bpp_increment_div >= 16)
+			dsc_sink_caps->bpp_increment_div = 16;
+	}
+
+	/* Extended caps */
+	if (dpcd_dsc_branch_decoder_caps == NULL) { // branch decoder DPCD DSC data can be null for non branch device
+		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
+		dsc_sink_caps->branch_overall_throughput_1_mps = 0;
+		dsc_sink_caps->branch_max_line_width = 0;
+		return true;
+	}
+
+	dsc_sink_caps->branch_overall_throughput_0_mps =
+		dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0];
+	if (dsc_sink_caps->branch_overall_throughput_0_mps == 0)
+		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
+	else if (dsc_sink_caps->branch_overall_throughput_0_mps == 1)
+		dsc_sink_caps->branch_overall_throughput_0_mps = 680;
+	else {
+		dsc_sink_caps->branch_overall_throughput_0_mps *= 50;
+		dsc_sink_caps->branch_overall_throughput_0_mps += 600;
+	}
+
+	dsc_sink_caps->branch_overall_throughput_1_mps =
+		dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0];
+	if (dsc_sink_caps->branch_overall_throughput_1_mps == 0)
+		dsc_sink_caps->branch_overall_throughput_1_mps = 0;
+	else if (dsc_sink_caps->branch_overall_throughput_1_mps == 1)
+		dsc_sink_caps->branch_overall_throughput_1_mps = 680;
+	else {
+		dsc_sink_caps->branch_overall_throughput_1_mps *= 50;
+		dsc_sink_caps->branch_overall_throughput_1_mps += 600;
+	}
+
+	dsc_sink_caps->branch_max_line_width =
+		dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_MAX_LINE_WIDTH - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0] * 320;
+	ASSERT(dsc_sink_caps->branch_max_line_width == 0 || dsc_sink_caps->branch_max_line_width >= 5120);
+
+	dsc_sink_caps->is_dp = true;
+	return true;
+}
+
+
+/* If DSC is possbile, get DSC bandwidth range based on [min_bpp, max_bpp] target bitrate range and
+ * timing's pixel clock and uncompressed bandwidth.
+ * If DSC is not possible, leave '*range' untouched.
+ */
+bool dc_dsc_compute_bandwidth_range(
+		const struct display_stream_compressor *dsc,
+		uint32_t dsc_min_slice_height_override,
+		uint32_t min_bpp_x16,
+		uint32_t max_bpp_x16,
+		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const struct dc_crtc_timing *timing,
+		struct dc_dsc_bw_range *range)
+{
+	bool is_dsc_possible = false;
+	struct dsc_enc_caps dsc_enc_caps;
+	struct dsc_enc_caps dsc_common_caps;
+	struct dc_dsc_config config;
+
+	get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz);
+
+	is_dsc_possible = intersect_dsc_caps(dsc_sink_caps, &dsc_enc_caps,
+			timing->pixel_encoding, &dsc_common_caps);
+
+	if (is_dsc_possible)
+		is_dsc_possible = setup_dsc_config(dsc_sink_caps, &dsc_enc_caps, 0, timing,
+				dsc_min_slice_height_override, max_bpp_x16, &config);
+
+	if (is_dsc_possible)
+		get_dsc_bandwidth_range(min_bpp_x16, max_bpp_x16,
+				config.num_slices_h, &dsc_common_caps, timing, range);
+
+	return is_dsc_possible;
+}
+
 static void get_dsc_enc_caps(
-	const struct display_stream_compressor *dsc,
-	struct dsc_enc_caps *dsc_enc_caps,
-	int pixel_clock_100Hz)
+		const struct display_stream_compressor *dsc,
+		struct dsc_enc_caps *dsc_enc_caps,
+		int pixel_clock_100Hz)
 {
 	// This is a static HW query, so we can use any DSC
 
@@ -187,14 +383,14 @@ static void get_dsc_enc_caps(
 	}
 }
 
-/* Returns 'false' if no intersection was found for at least one capablity.
+/* Returns 'false' if no intersection was found for at least one capability.
  * It also implicitly validates some sink caps against invalid value of zero.
  */
 static bool intersect_dsc_caps(
-	const struct dsc_dec_dpcd_caps *dsc_sink_caps,
-	const struct dsc_enc_caps *dsc_enc_caps,
-	enum dc_pixel_encoding pixel_encoding,
-	struct dsc_enc_caps *dsc_common_caps)
+		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const struct dsc_enc_caps *dsc_enc_caps,
+		enum dc_pixel_encoding pixel_encoding,
+		struct dsc_enc_caps *dsc_common_caps)
 {
 	int32_t max_slices;
 	int32_t total_sink_throughput;
@@ -205,10 +401,14 @@ static bool intersect_dsc_caps(
 	if (!dsc_common_caps->dsc_version)
 		return false;
 
-	dsc_common_caps->slice_caps.bits.NUM_SLICES_1 = dsc_sink_caps->slice_caps1.bits.NUM_SLICES_1 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_1;
-	dsc_common_caps->slice_caps.bits.NUM_SLICES_2 = dsc_sink_caps->slice_caps1.bits.NUM_SLICES_2 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_2;
-	dsc_common_caps->slice_caps.bits.NUM_SLICES_4 = dsc_sink_caps->slice_caps1.bits.NUM_SLICES_4 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_4;
-	dsc_common_caps->slice_caps.bits.NUM_SLICES_8 = dsc_sink_caps->slice_caps1.bits.NUM_SLICES_8 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_8;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_1 =
+		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_1 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_1;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_2 =
+		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_2 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_2;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_4 =
+		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_4 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_4;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_8 =
+		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_8 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_8;
 	if (!dsc_common_caps->slice_caps.raw)
 		return false;
 
@@ -216,7 +416,8 @@ static bool intersect_dsc_caps(
 	if (!dsc_common_caps->lb_bit_depth)
 		return false;
 
-	dsc_common_caps->is_block_pred_supported = dsc_sink_caps->is_block_pred_supported && dsc_enc_caps->is_block_pred_supported;
+	dsc_common_caps->is_block_pred_supported =
+		dsc_sink_caps->is_block_pred_supported && dsc_enc_caps->is_block_pred_supported;
 
 	dsc_common_caps->color_formats.raw = dsc_sink_caps->color_formats.raw & dsc_enc_caps->color_formats.raw;
 	if (!dsc_common_caps->color_formats.raw)
@@ -288,11 +489,11 @@ static struct fixed31_32 compute_dsc_max_bandwidth_overhead(
 }
 
 static uint32_t compute_bpp_x16_from_target_bandwidth(
-		const uint32_t bandwidth_in_kbps,
-		const struct dc_crtc_timing *timing,
-		const uint32_t num_slices_h,
-		const uint32_t bpp_increment_div,
-		const bool is_dp)
+	const uint32_t bandwidth_in_kbps,
+	const struct dc_crtc_timing *timing,
+	const uint32_t num_slices_h,
+	const uint32_t bpp_increment_div,
+	const bool is_dp)
 {
 	struct fixed31_32 overhead_in_kbps;
 	struct fixed31_32 effective_bandwidth_in_kbps;
@@ -769,146 +970,6 @@ done:
 	return is_dsc_possible;
 }
 
-bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_branch_decoder_caps, struct dsc_dec_dpcd_caps *dsc_sink_caps)
-{
-	if (!dpcd_dsc_basic_data)
-		return false;
-
-	dsc_sink_caps->is_dsc_supported = (dpcd_dsc_basic_data[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & DP_DSC_DECOMPRESSION_IS_SUPPORTED) != 0;
-	if (!dsc_sink_caps->is_dsc_supported)
-		return false;
-
-	dsc_sink_caps->dsc_version = dpcd_dsc_basic_data[DP_DSC_REV - DP_DSC_SUPPORT];
-
-	{
-		int buff_block_size;
-		int buff_size;
-
-		if (!dsc_buff_block_size_from_dpcd(dpcd_dsc_basic_data[DP_DSC_RC_BUF_BLK_SIZE - DP_DSC_SUPPORT], &buff_block_size))
-			return false;
-
-		buff_size = dpcd_dsc_basic_data[DP_DSC_RC_BUF_SIZE - DP_DSC_SUPPORT] + 1;
-		dsc_sink_caps->rc_buffer_size = buff_size * buff_block_size;
-	}
-
-	dsc_sink_caps->slice_caps1.raw = dpcd_dsc_basic_data[DP_DSC_SLICE_CAP_1 - DP_DSC_SUPPORT];
-	if (!dsc_line_buff_depth_from_dpcd(dpcd_dsc_basic_data[DP_DSC_LINE_BUF_BIT_DEPTH - DP_DSC_SUPPORT], &dsc_sink_caps->lb_bit_depth))
-		return false;
-
-	dsc_sink_caps->is_block_pred_supported =
-		(dpcd_dsc_basic_data[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] & DP_DSC_BLK_PREDICTION_IS_SUPPORTED) != 0;
-
-	dsc_sink_caps->edp_max_bits_per_pixel =
-		dpcd_dsc_basic_data[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] |
-		dpcd_dsc_basic_data[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] << 8;
-
-	dsc_sink_caps->color_formats.raw = dpcd_dsc_basic_data[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT];
-	dsc_sink_caps->color_depth.raw = dpcd_dsc_basic_data[DP_DSC_DEC_COLOR_DEPTH_CAP - DP_DSC_SUPPORT];
-
-	{
-		int dpcd_throughput = dpcd_dsc_basic_data[DP_DSC_PEAK_THROUGHPUT - DP_DSC_SUPPORT];
-
-		if (!dsc_throughput_from_dpcd(dpcd_throughput & DP_DSC_THROUGHPUT_MODE_0_MASK, &dsc_sink_caps->throughput_mode_0_mps))
-			return false;
-
-		dpcd_throughput = (dpcd_throughput & DP_DSC_THROUGHPUT_MODE_1_MASK) >> DP_DSC_THROUGHPUT_MODE_1_SHIFT;
-		if (!dsc_throughput_from_dpcd(dpcd_throughput, &dsc_sink_caps->throughput_mode_1_mps))
-			return false;
-	}
-
-	dsc_sink_caps->max_slice_width = dpcd_dsc_basic_data[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * 320;
-	dsc_sink_caps->slice_caps2.raw = dpcd_dsc_basic_data[DP_DSC_SLICE_CAP_2 - DP_DSC_SUPPORT];
-
-	if (!dsc_bpp_increment_div_from_dpcd(dpcd_dsc_basic_data[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT], &dsc_sink_caps->bpp_increment_div))
-		return false;
-
-	if (dc->debug.dsc_bpp_increment_div) {
-		/* dsc_bpp_increment_div should onl be 1, 2, 4, 8 or 16, but rather than rejecting invalid values,
-		 * we'll accept all and get it into range. This also makes the above check against 0 redundant,
-		 * but that one stresses out the override will be only used if it's not 0.
-		 */
-		if (dc->debug.dsc_bpp_increment_div >= 1)
-			dsc_sink_caps->bpp_increment_div = 1;
-		if (dc->debug.dsc_bpp_increment_div >= 2)
-			dsc_sink_caps->bpp_increment_div = 2;
-		if (dc->debug.dsc_bpp_increment_div >= 4)
-			dsc_sink_caps->bpp_increment_div = 4;
-		if (dc->debug.dsc_bpp_increment_div >= 8)
-			dsc_sink_caps->bpp_increment_div = 8;
-		if (dc->debug.dsc_bpp_increment_div >= 16)
-			dsc_sink_caps->bpp_increment_div = 16;
-	}
-
-	/* Extended caps */
-	if (dpcd_dsc_branch_decoder_caps == NULL) { // branch decoder DPCD DSC data can be null for non branch device
-		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
-		dsc_sink_caps->branch_overall_throughput_1_mps = 0;
-		dsc_sink_caps->branch_max_line_width = 0;
-		return true;
-	}
-
-	dsc_sink_caps->branch_overall_throughput_0_mps = dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0];
-	if (dsc_sink_caps->branch_overall_throughput_0_mps == 0)
-		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
-	else if (dsc_sink_caps->branch_overall_throughput_0_mps == 1)
-		dsc_sink_caps->branch_overall_throughput_0_mps = 680;
-	else {
-		dsc_sink_caps->branch_overall_throughput_0_mps *= 50;
-		dsc_sink_caps->branch_overall_throughput_0_mps += 600;
-	}
-
-	dsc_sink_caps->branch_overall_throughput_1_mps = dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0];
-	if (dsc_sink_caps->branch_overall_throughput_1_mps == 0)
-		dsc_sink_caps->branch_overall_throughput_1_mps = 0;
-	else if (dsc_sink_caps->branch_overall_throughput_1_mps == 1)
-		dsc_sink_caps->branch_overall_throughput_1_mps = 680;
-	else {
-		dsc_sink_caps->branch_overall_throughput_1_mps *= 50;
-		dsc_sink_caps->branch_overall_throughput_1_mps += 600;
-	}
-
-	dsc_sink_caps->branch_max_line_width = dpcd_dsc_branch_decoder_caps[DP_DSC_BRANCH_MAX_LINE_WIDTH - DP_DSC_BRANCH_OVERALL_THROUGHPUT_0] * 320;
-	ASSERT(dsc_sink_caps->branch_max_line_width == 0 || dsc_sink_caps->branch_max_line_width >= 5120);
-
-	dsc_sink_caps->is_dp = true;
-	return true;
-}
-
-
-/* If DSC is possbile, get DSC bandwidth range based on [min_bpp, max_bpp] target bitrate range and
- * timing's pixel clock and uncompressed bandwidth.
- * If DSC is not possible, leave '*range' untouched.
- */
-bool dc_dsc_compute_bandwidth_range(
-		const struct display_stream_compressor *dsc,
-		uint32_t dsc_min_slice_height_override,
-		uint32_t min_bpp_x16,
-		uint32_t max_bpp_x16,
-		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
-		const struct dc_crtc_timing *timing,
-		struct dc_dsc_bw_range *range)
-{
-	bool is_dsc_possible = false;
-	struct dsc_enc_caps dsc_enc_caps;
-	struct dsc_enc_caps dsc_common_caps;
-	struct dc_dsc_config config;
-
-	get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz);
-
-	is_dsc_possible = intersect_dsc_caps(dsc_sink_caps, &dsc_enc_caps,
-			timing->pixel_encoding, &dsc_common_caps);
-
-	if (is_dsc_possible)
-		is_dsc_possible = setup_dsc_config(dsc_sink_caps, &dsc_enc_caps, 0, timing,
-				dsc_min_slice_height_override, max_bpp_x16, &config);
-
-	if (is_dsc_possible)
-		get_dsc_bandwidth_range(min_bpp_x16, max_bpp_x16,
-				config.num_slices_h, &dsc_common_caps, timing, range);
-
-	return is_dsc_possible;
-}
-
 bool dc_dsc_compute_config(
 		const struct display_stream_compressor *dsc,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
@@ -923,22 +984,22 @@ bool dc_dsc_compute_config(
 
 	get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz);
 	is_dsc_possible = setup_dsc_config(dsc_sink_caps,
-			&dsc_enc_caps,
-			target_bandwidth_kbps,
-			timing, dsc_min_slice_height_override,
-			max_target_bpp_limit_override * 16, dsc_cfg);
+		&dsc_enc_caps,
+		target_bandwidth_kbps,
+		timing, dsc_min_slice_height_override,
+		max_target_bpp_limit_override * 16, dsc_cfg);
 	return is_dsc_possible;
 }
 
 uint32_t dc_dsc_stream_bandwidth_in_kbps(const struct dc_crtc_timing *timing,
-		uint32_t bpp_x16, uint32_t num_slices_h, bool is_dp)
+	uint32_t bpp_x16, uint32_t num_slices_h, bool is_dp)
 {
 	struct fixed31_32 overhead_in_kbps;
 	struct fixed31_32 bpp;
 	struct fixed31_32 actual_bandwidth_in_kbps;
 
 	overhead_in_kbps = compute_dsc_max_bandwidth_overhead(
-			timing, num_slices_h, is_dp);
+		timing, num_slices_h, is_dp);
 	bpp = dc_fixpt_from_fraction(bpp_x16, 16);
 	actual_bandwidth_in_kbps = dc_fixpt_from_fraction(timing->pix_clk_100hz, 10);
 	actual_bandwidth_in_kbps = dc_fixpt_mul(actual_bandwidth_in_kbps, bpp);
@@ -946,7 +1007,9 @@ uint32_t dc_dsc_stream_bandwidth_in_kbps(const struct dc_crtc_timing *timing,
 	return dc_fixpt_ceil(actual_bandwidth_in_kbps);
 }
 
-void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, struct dc_dsc_policy *policy)
+void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
+		uint32_t max_target_bpp_limit_override_x16,
+		struct dc_dsc_policy *policy)
 {
 	uint32_t bpc = 0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index e2b58ec9912d..01c3a31be191 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -174,7 +174,6 @@ bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable);
 void dp_decide_training_settings(
 	struct dc_link *link,
 	const struct dc_link_settings *link_setting,
-	const struct dc_link_training_overrides *overrides,
 	struct link_training_settings *lt_settings);
 
 /* Convert PHY repeater count read from DPCD uint8_t. */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index 316301fc1e30..a262f3278c21 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -318,6 +318,11 @@ static inline bool should_update_pstate_support(bool safe_to_lower, bool calc_su
 	return false;
 }
 
+static inline int khz_to_mhz_ceil(int khz)
+{
+	return (khz + 999) / 1000;
+}
+
 int clk_mgr_helper_get_active_display_cnt(
 		struct dc *dc,
 		struct dc_state *context);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index 0638b337f143..713f5558f5e1 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -102,6 +102,15 @@ struct hubbub_addr_config {
 	} default_addrs;
 };
 
+struct dcn_hubbub_state {
+	uint32_t vm_fault_addr_msb;
+	uint32_t vm_fault_addr_lsb;
+	uint32_t vm_error_status;
+	uint32_t vm_error_vmid;
+	uint32_t vm_error_pipe;
+	uint32_t vm_error_mode;
+};
+
 struct hubbub_funcs {
 	void (*update_dchub)(
 			struct hubbub *hubbub,
@@ -149,6 +158,8 @@ struct hubbub_funcs {
 
 	void (*force_wm_propagate_to_pipes)(struct hubbub *hubbub);
 
+	void (*hubbub_read_state)(struct hubbub *hubbub, struct dcn_hubbub_state *hubbub_state);
+
 	void (*force_pstate_change_control)(struct hubbub *hubbub, bool force, bool allow);
 
 	void (*init_watermarks)(struct hubbub *hubbub);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
index 082549f75978..f7f7e4fff0c2 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -41,7 +41,6 @@ struct dce_hwseq_wa {
 	bool DEGVIDCN10_254;
 	bool DEGVIDCN21;
 	bool disallow_self_refresh_during_multi_plane_transition;
-	bool early_riommu_invalidation;
 };
 
 struct hwseq_wa_state {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h b/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h
index d4d52ef1b165..3f12b1600d2a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h
@@ -1,3 +1,28 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
 #ifndef __LINK_DPCD_H__
 #define __LINK_DPCD_H__
 #include <inc/core_status.h>
diff --git a/drivers/gpu/drm/amd/display/dc/irq_types.h b/drivers/gpu/drm/amd/display/dc/irq_types.h
index 1139b9eb9f6f..530c2578db40 100644
--- a/drivers/gpu/drm/amd/display/dc/irq_types.h
+++ b/drivers/gpu/drm/amd/display/dc/irq_types.h
@@ -152,7 +152,7 @@ enum dc_irq_source {
 	DC_IRQ_SOURCE_DC6_VLINE1,
 	DC_IRQ_SOURCE_DMCUB_OUTBOX,
 	DC_IRQ_SOURCE_DMCUB_OUTBOX0,
-
+	DC_IRQ_SOURCE_DMCUB_GENERAL_DATAOUT,
 	DAL_IRQ_SOURCES_NUMBER
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 126c2f3a4dd3..f50cae252de4 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -51,38 +51,9 @@
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-#if defined(CONFIG_X86)
-#include <asm/fpu/api.h>
-#define DC_FP_START() kernel_fpu_begin()
-#define DC_FP_END() kernel_fpu_end()
-#elif defined(CONFIG_PPC64)
-#include <asm/switch_to.h>
-#include <asm/cputable.h>
-#define DC_FP_START() { \
-	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
-		preempt_disable(); \
-		enable_kernel_vsx(); \
-	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
-		preempt_disable(); \
-		enable_kernel_altivec(); \
-	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
-		preempt_disable(); \
-		enable_kernel_fp(); \
-	} \
-}
-#define DC_FP_END() { \
-	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
-		disable_kernel_vsx(); \
-		preempt_enable(); \
-	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
-		disable_kernel_altivec(); \
-		preempt_enable(); \
-	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
-		disable_kernel_fp(); \
-		preempt_enable(); \
-	} \
-}
-#endif
+#include "amdgpu_dm/dc_fpu.h"
+#define DC_FP_START() dc_fpu_begin(__func__, __LINE__)
+#define DC_FP_END() dc_fpu_end(__func__, __LINE__)
 #endif
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index abbf7ae584c9..caf961bb633f 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -352,6 +352,8 @@ struct dmub_srv_hw_funcs {
 
 	uint32_t (*get_gpint_response)(struct dmub_srv *dmub);
 
+	uint32_t (*get_gpint_dataout)(struct dmub_srv *dmub);
+
 	void (*send_inbox0_cmd)(struct dmub_srv *dmub, union dmub_inbox0_data_register data);
 	uint32_t (*get_current_time)(struct dmub_srv *dmub);
 
@@ -677,6 +679,22 @@ enum dmub_status dmub_srv_get_gpint_response(struct dmub_srv *dmub,
 					     uint32_t *response);
 
 /**
+ * dmub_srv_get_gpint_dataout() - Queries the GPINT DATAOUT.
+ * @dmub: the dmub service
+ * @dataout: the data for the GPINT DATAOUT
+ *
+ * Returns the response code for the last GPINT DATAOUT interrupt.
+ *
+ * Can be called after software initialization.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_get_gpint_dataout(struct dmub_srv *dmub,
+					     uint32_t *dataout);
+
+/**
  * dmub_flush_buffer_mem() - Read back entire frame buffer region.
  * This ensures that the write from x86 has been flushed and will not
  * hang the DMCUB.
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 7fafb8d6c1da..7b684e7f60df 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -23,8 +23,8 @@
  *
  */
 
-#ifndef _DMUB_CMD_H_
-#define _DMUB_CMD_H_
+#ifndef DMUB_CMD_H
+#define DMUB_CMD_H
 
 #if defined(_TEST_HARNESS) || defined(FPGA_USB4)
 #include "dmub_fw_types.h"
@@ -47,10 +47,10 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0xf3da2b656
+#define DMUB_FW_VERSION_GIT_HASH 0x7383caadc
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 71
+#define DMUB_FW_VERSION_REVISION 79
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
@@ -322,6 +322,10 @@ union dmub_fw_boot_status {
 		uint32_t mailbox_rdy : 1; /**< 1 if mailbox ready */
 		uint32_t optimized_init_done : 1; /**< 1 if optimized init done */
 		uint32_t restore_required : 1; /**< 1 if driver should call restore */
+		uint32_t defer_load : 1; /**< 1 if VBIOS data is deferred programmed */
+		uint32_t reserved : 1;
+		uint32_t detection_required: 1; /**<  if detection need to be triggered by driver */
+
 	} bits; /**< status bits */
 	uint32_t all; /**< 32-bit access to status bits */
 };
@@ -334,6 +338,8 @@ enum dmub_fw_boot_status_bit {
 	DMUB_FW_BOOT_STATUS_BIT_MAILBOX_READY = (1 << 1), /**< 1 if mailbox ready */
 	DMUB_FW_BOOT_STATUS_BIT_OPTIMIZED_INIT_DONE = (1 << 2), /**< 1 if init done */
 	DMUB_FW_BOOT_STATUS_BIT_RESTORE_REQUIRED = (1 << 3), /**< 1 if driver should call restore */
+	DMUB_FW_BOOT_STATUS_BIT_DEFERRED_LOADED = (1 << 4), /**< 1 if VBIOS data is deferred programmed */
+	DMUB_FW_BOOT_STATUS_BIT_DETECTION_REQUIRED = (1 << 6), /**< 1 if detection need to be triggered by driver*/
 };
 
 /* Register bit definition for SCRATCH5 */
@@ -352,7 +358,7 @@ enum dmub_lvtma_status_bit {
 };
 
 /**
- * union dmub_fw_boot_options - Boot option definitions for SCRATCH15
+ * union dmub_fw_boot_options - Boot option definitions for SCRATCH14
  */
 union dmub_fw_boot_options {
 	struct {
@@ -363,7 +369,10 @@ union dmub_fw_boot_options {
 		uint32_t disable_clk_gate: 1; /**< 1 if clock gating should be disabled */
 		uint32_t skip_phy_init_panel_sequence: 1; /**< 1 to skip panel init seq */
 		uint32_t z10_disable: 1; /**< 1 to disable z10 */
-		uint32_t reserved : 25; /**< reserved */
+		uint32_t reserved2: 1; /**< reserved for an unreleased feature */
+		uint32_t reserved_unreleased1: 1; /**< reserved for an unreleased feature */
+		uint32_t invalid_vbios_data: 1; /**< 1 if VBIOS data table is invalid */
+		uint32_t reserved : 23; /**< reserved */
 	} bits; /**< boot bits */
 	uint32_t all; /**< 32-bit access to bits */
 };
@@ -485,6 +494,11 @@ enum dmub_gpint_command {
 	 * RETURN: PSR residency in milli-percent.
 	 */
 	DMUB_GPINT__PSR_RESIDENCY = 9,
+
+	/**
+	 * DESC: Notifies DMCUB detection is done so detection required can be cleared.
+	 */
+	DMUB_GPINT__NOTIFY_DETECTION_DONE = 12,
 };
 
 /**
@@ -1411,6 +1425,10 @@ struct dmub_cmd_psr_copy_settings_data {
 	 * Currently the support is only for 0 or 1
 	 */
 	uint8_t panel_inst;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad3[4];
 };
 
 /**
@@ -1435,7 +1453,7 @@ struct dmub_cmd_psr_set_level_data {
 	 * 16-bit value dicated by driver that will enable/disable different functionality.
 	 */
 	uint16_t psr_level;
-		/**
+	/**
 	 * PSR control version.
 	 */
 	uint8_t cmd_version;
@@ -2467,16 +2485,14 @@ static inline bool dmub_rb_full(struct dmub_rb *rb)
 static inline bool dmub_rb_push_front(struct dmub_rb *rb,
 				      const union dmub_rb_cmd *cmd)
 {
-	uint64_t volatile *dst = (uint64_t volatile *)(rb->base_address) + rb->wrpt / sizeof(uint64_t);
-	const uint64_t *src = (const uint64_t *)cmd;
-	uint8_t i;
+	uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt;
+	const uint8_t *src = (const uint8_t *)cmd;
 
 	if (dmub_rb_full(rb))
 		return false;
 
 	// copying data
-	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
-		*dst++ = *src++;
+	dmub_memcpy(dst, src, DMUB_RB_CMD_SIZE);
 
 	rb->wrpt += DMUB_RB_CMD_SIZE;
 
@@ -2498,7 +2514,7 @@ static inline bool dmub_rb_out_push_front(struct dmub_rb *rb,
 				      const union dmub_rb_out_cmd *cmd)
 {
 	uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt;
-	const uint8_t *src = (uint8_t *)cmd;
+	const uint8_t *src = (const uint8_t *)cmd;
 
 	if (dmub_rb_full(rb))
 		return false;
@@ -2583,18 +2599,16 @@ static inline bool dmub_rb_peek_offset(struct dmub_rb *rb,
  * @return false otherwise
  */
 static inline bool dmub_rb_out_front(struct dmub_rb *rb,
-				 union dmub_rb_out_cmd  *cmd)
+				 union dmub_rb_out_cmd *cmd)
 {
-	const uint64_t volatile *src = (const uint64_t volatile *)(rb->base_address) + rb->rptr / sizeof(uint64_t);
-	uint64_t *dst = (uint64_t *)cmd;
-	uint8_t i;
+	const uint8_t *src = (const uint8_t *)(rb->base_address) + rb->rptr;
+	uint8_t *dst = (uint8_t *)cmd;
 
 	if (dmub_rb_empty(rb))
 		return false;
 
 	// copying data
-	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
-		*dst++ = *src++;
+	dmub_memcpy(dst, src, DMUB_RB_CMD_SIZE);
 
 	return true;
 }
@@ -2629,15 +2643,14 @@ static inline bool dmub_rb_pop_front(struct dmub_rb *rb)
  */
 static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
 {
+	uint8_t buf[DMUB_RB_CMD_SIZE];
 	uint32_t rptr = rb->rptr;
 	uint32_t wptr = rb->wrpt;
 
 	while (rptr != wptr) {
-		uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t);
-		uint8_t i;
+		const uint8_t *data = (const uint8_t *)rb->base_address + rptr;
 
-		for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
-			*data++;
+		dmub_memcpy(buf, data, DMUB_RB_CMD_SIZE);
 
 		rptr += DMUB_RB_CMD_SIZE;
 		if (rptr >= rb->capacity)
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 27c7fa3110c8..fc667cb17eb0 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -38,7 +38,10 @@
 
 const struct dmub_srv_dcn31_regs dmub_srv_dcn31_regs = {
 #define DMUB_SR(reg) REG_OFFSET_EXP(reg),
-	{ DMUB_DCN31_REGS() },
+	{
+		DMUB_DCN31_REGS()
+		DMCUB_INTERNAL_REGS()
+	},
 #undef DMUB_SR
 
 #define DMUB_SF(reg, field) FD_MASK(reg, field),
@@ -80,7 +83,7 @@ static inline void dmub_dcn31_translate_addr(const union dmub_addr *addr_in,
 void dmub_dcn31_reset(struct dmub_srv *dmub)
 {
 	union dmub_gpint_data_register cmd;
-	const uint32_t timeout = 30;
+	const uint32_t timeout = 100;
 	uint32_t in_reset, scratch, i;
 
 	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset);
@@ -95,26 +98,22 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 		/**
 		 * Timeout covers both the ACK and the wait
 		 * for remaining work to finish.
-		 *
-		 * This is mostly bound by the PHY disable sequence.
-		 * Each register check will be greater than 1us, so
-		 * don't bother using udelay.
 		 */
 
 		for (i = 0; i < timeout; ++i) {
 			if (dmub->hw_funcs.is_gpint_acked(dmub, cmd))
 				break;
+
+			udelay(1);
 		}
 
 		for (i = 0; i < timeout; ++i) {
 			scratch = dmub->hw_funcs.get_gpint_response(dmub);
 			if (scratch == DMUB_GPINT__STOP_FW_RESPONSE)
 				break;
-		}
 
-		/* Clear the GPINT command manually so we don't reset again. */
-		cmd.all = 0;
-		dmub->hw_funcs.set_gpint(dmub, cmd);
+			udelay(1);
+		}
 
 		/* Force reset in case we timed out, DMCUB is likely hung. */
 	}
@@ -127,6 +126,10 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_SCRATCH0, 0);
+
+	/* Clear the GPINT command manually so we don't send anything during boot. */
+	cmd.all = 0;
+	dmub->hw_funcs.set_gpint(dmub, cmd);
 }
 
 void dmub_dcn31_reset_release(struct dmub_srv *dmub)
@@ -307,6 +310,21 @@ uint32_t dmub_dcn31_get_gpint_response(struct dmub_srv *dmub)
 	return REG_READ(DMCUB_SCRATCH7);
 }
 
+uint32_t dmub_dcn31_get_gpint_dataout(struct dmub_srv *dmub)
+{
+	uint32_t dataout = REG_READ(DMCUB_GPINT_DATAOUT);
+
+	REG_UPDATE(DMCUB_INTERRUPT_ENABLE, DMCUB_GPINT_IH_INT_EN, 0);
+
+	REG_WRITE(DMCUB_GPINT_DATAOUT, 0);
+	REG_UPDATE(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK, 1);
+	REG_UPDATE(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK, 0);
+
+	REG_UPDATE(DMCUB_INTERRUPT_ENABLE, DMCUB_GPINT_IH_INT_EN, 1);
+
+	return dataout;
+}
+
 union dmub_fw_boot_status dmub_dcn31_get_fw_boot_status(struct dmub_srv *dmub)
 {
 	union dmub_fw_boot_status status;
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
index 9456a6a2d518..bb62605d2ac8 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
@@ -114,7 +114,9 @@ struct dmub_srv;
 	DMUB_SR(DMCUB_TIMER_CURRENT) \
 	DMUB_SR(DMCUB_INST_FETCH_FAULT_ADDR) \
 	DMUB_SR(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR) \
-	DMUB_SR(DMCUB_DATA_WRITE_FAULT_ADDR)
+	DMUB_SR(DMCUB_DATA_WRITE_FAULT_ADDR) \
+	DMUB_SR(DMCUB_INTERRUPT_ENABLE) \
+	DMUB_SR(DMCUB_INTERRUPT_ACK)
 
 #define DMUB_DCN31_FIELDS() \
 	DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \
@@ -147,7 +149,9 @@ struct dmub_srv;
 	DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET) \
 	DMUB_SF(DCN_VM_FB_LOCATION_BASE, FB_BASE) \
 	DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) \
-	DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR)
+	DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR) \
+	DMUB_SF(DMCUB_INTERRUPT_ENABLE, DMCUB_GPINT_IH_INT_EN) \
+	DMUB_SF(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK)
 
 struct dmub_srv_dcn31_reg_offset {
 #define DMUB_SR(reg) uint32_t reg;
@@ -222,6 +226,8 @@ bool dmub_dcn31_is_gpint_acked(struct dmub_srv *dmub,
 
 uint32_t dmub_dcn31_get_gpint_response(struct dmub_srv *dmub);
 
+uint32_t dmub_dcn31_get_gpint_dataout(struct dmub_srv *dmub);
+
 void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmub_srv_hw_params *params);
 
 void dmub_dcn31_skip_dmub_panel_power_sequence(struct dmub_srv *dmub, bool skip);
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
index 2bdbd7406f56..75a91cfaf036 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -224,6 +224,7 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
 		funcs->set_gpint = dmub_dcn31_set_gpint;
 		funcs->is_gpint_acked = dmub_dcn31_is_gpint_acked;
 		funcs->get_gpint_response = dmub_dcn31_get_gpint_response;
+		funcs->get_gpint_dataout = dmub_dcn31_get_gpint_dataout;
 		funcs->get_fw_status = dmub_dcn31_get_fw_boot_status;
 		funcs->enable_dmub_boot_options = dmub_dcn31_enable_dmub_boot_options;
 		funcs->skip_dmub_panel_power_sequence = dmub_dcn31_skip_dmub_panel_power_sequence;
@@ -719,6 +720,22 @@ enum dmub_status dmub_srv_get_gpint_response(struct dmub_srv *dmub,
 	return DMUB_STATUS_OK;
 }
 
+enum dmub_status dmub_srv_get_gpint_dataout(struct dmub_srv *dmub,
+					     uint32_t *dataout)
+{
+	*dataout = 0;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (!dmub->hw_funcs.get_gpint_dataout)
+		return DMUB_STATUS_INVALID;
+
+	*dataout = dmub->hw_funcs.get_gpint_dataout(dmub);
+
+	return DMUB_STATUS_OK;
+}
+
 enum dmub_status dmub_srv_get_fw_boot_status(struct dmub_srv *dmub,
 					     union dmub_fw_boot_status *status)
 {
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
index b963226e8af4..3e81850a7ffe 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -39,8 +39,12 @@ static void push_error_status(struct mod_hdcp *hdcp,
 
 	if (is_hdcp1(hdcp)) {
 		hdcp->connection.hdcp1_retry_count++;
+		if (hdcp->connection.hdcp1_retry_count == MAX_NUM_OF_ATTEMPTS)
+			hdcp->connection.link.adjust.hdcp1.disable = 1;
 	} else if (is_hdcp2(hdcp)) {
 		hdcp->connection.hdcp2_retry_count++;
+		if (hdcp->connection.hdcp2_retry_count == MAX_NUM_OF_ATTEMPTS)
+			hdcp->connection.link.adjust.hdcp2.disable = 1;
 	}
 }
 
@@ -59,8 +63,7 @@ static uint8_t is_cp_desired_hdcp1(struct mod_hdcp *hdcp)
 		}
 	}
 
-	return (hdcp->connection.hdcp1_retry_count < MAX_NUM_OF_ATTEMPTS) &&
-			is_auth_needed &&
+	return is_auth_needed &&
 			!hdcp->connection.link.adjust.hdcp1.disable &&
 			!hdcp->connection.is_hdcp1_revoked;
 }
@@ -80,8 +83,7 @@ static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp)
 		}
 	}
 
-	return (hdcp->connection.hdcp2_retry_count < MAX_NUM_OF_ATTEMPTS) &&
-			is_auth_needed &&
+	return is_auth_needed &&
 			!hdcp->connection.link.adjust.hdcp2.disable &&
 			!hdcp->connection.is_hdcp2_revoked;
 }
@@ -143,6 +145,7 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 			} else {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+				set_auth_complete(hdcp, output);
 			}
 		else if (is_hdmi_dvi_sl_hdcp(hdcp))
 			if (is_cp_desired_hdcp2(hdcp)) {
@@ -154,10 +157,12 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 			} else {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+				set_auth_complete(hdcp, output);
 			}
 		else {
 			callback_in_ms(0, output);
 			set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+			set_auth_complete(hdcp, output);
 		}
 	} else if (is_in_cp_not_desired_state(hdcp)) {
 		increment_stay_counter(hdcp);
@@ -313,9 +318,6 @@ enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp,
 		goto out;
 	}
 
-	/* save current encryption states to restore after next authentication */
-	mod_hdcp_save_current_encryption_states(hdcp);
-
 	/* reset existing authentication status */
 	status = reset_authentication(hdcp, output);
 	if (status != MOD_HDCP_STATUS_SUCCESS)
@@ -362,9 +364,6 @@ enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp,
 		goto out;
 	}
 
-	/* save current encryption states to restore after next authentication */
-	mod_hdcp_save_current_encryption_states(hdcp);
-
 	/* stop current authentication */
 	status = reset_authentication(hdcp, output);
 	if (status != MOD_HDCP_STATUS_SUCCESS)
@@ -392,6 +391,60 @@ out:
 	return status;
 }
 
+enum mod_hdcp_status mod_hdcp_update_authentication(struct mod_hdcp *hdcp,
+		uint8_t index,
+		struct mod_hdcp_link_adjustment *link_adjust,
+		struct mod_hdcp_display_adjustment *display_adjust,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_display *display = NULL;
+
+	HDCP_TOP_INTERFACE_TRACE_WITH_INDEX(hdcp, index);
+	memset(output, 0, sizeof(struct mod_hdcp_output));
+
+	/* find display in connection */
+	display = get_active_display_at_index(hdcp, index);
+	if (!display) {
+		status = MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+		goto out;
+	}
+
+	/* skip if no changes */
+	if (memcmp(link_adjust, &hdcp->connection.link.adjust,
+			sizeof(struct mod_hdcp_link_adjustment)) == 0 &&
+			memcmp(display_adjust, &display->adjust,
+					sizeof(struct mod_hdcp_display_adjustment)) == 0) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+		goto out;
+	}
+
+	/* stop current authentication */
+	status = reset_authentication(hdcp, output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	/* clear retry counters */
+	reset_retry_counts(hdcp);
+
+	/* reset error trace */
+	memset(&hdcp->connection.trace, 0, sizeof(hdcp->connection.trace));
+
+	/* set new adjustment */
+	hdcp->connection.link.adjust = *link_adjust;
+	display->adjust = *display_adjust;
+
+	/* request authentication when connection is not reset */
+	if (current_state(hdcp) != HDCP_UNINITIALIZED)
+		/* wait 100ms to debounce simultaneous updates for different indices */
+		callback_in_ms(100, output);
+
+out:
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		push_error_status(hdcp, status);
+	return status;
+}
+
 enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
 		uint8_t index, struct mod_hdcp_display_query *query)
 {
@@ -470,7 +523,7 @@ enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp,
 
 	/* reset authentication if needed */
 	if (trans_status == MOD_HDCP_STATUS_RESET_NEEDED) {
-		HDCP_FULL_DDC_TRACE(hdcp);
+		mod_hdcp_log_ddc_trace(hdcp);
 		reset_status = reset_authentication(hdcp, output);
 		if (reset_status != MOD_HDCP_STATUS_SUCCESS)
 			push_error_status(hdcp, reset_status);
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
index 3ce91db560d1..399fbca8947b 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
@@ -324,6 +324,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
 /* log functions */
 void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
 		uint8_t *buf, uint32_t buf_size);
+void mod_hdcp_log_ddc_trace(struct mod_hdcp *hdcp);
 /* TODO: add adjustment log */
 
 /* psp functions */
@@ -331,8 +332,6 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(
 		struct mod_hdcp *hdcp, struct mod_hdcp_display *display);
 enum mod_hdcp_status mod_hdcp_remove_display_from_topology(
 		struct mod_hdcp *hdcp, uint8_t index);
-bool mod_hdcp_is_link_encryption_enabled(struct mod_hdcp *hdcp);
-void mod_hdcp_save_current_encryption_states(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_hdcp1_validate_rx(struct mod_hdcp *hdcp);
@@ -496,6 +495,13 @@ static inline void set_watchdog_in_ms(struct mod_hdcp *hdcp, uint16_t time,
 	output->watchdog_timer_delay = time;
 }
 
+static inline void set_auth_complete(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output)
+{
+	output->auth_complete = 1;
+	mod_hdcp_log_ddc_trace(hdcp);
+}
+
 /* connection topology helpers */
 static inline uint8_t is_display_active(struct mod_hdcp_display *display)
 {
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
index de872e7958b0..6ec918af3bff 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
@@ -266,9 +266,6 @@ static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp,
 	mod_hdcp_execute_and_set(mod_hdcp_hdcp1_link_maintenance,
 			&input->link_maintenance, &status,
 			hdcp, "link_maintenance");
-
-	if (status != MOD_HDCP_STATUS_SUCCESS)
-		mod_hdcp_save_current_encryption_states(hdcp);
 out:
 	return status;
 }
@@ -447,9 +444,6 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp,
 		mod_hdcp_execute_and_set(check_no_reauthentication_request_dp,
 				&input->reauth_request_check, &status,
 				hdcp, "reauth_request_check");
-
-	if (status != MOD_HDCP_STATUS_SUCCESS)
-		mod_hdcp_save_current_encryption_states(hdcp);
 out:
 	return status;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
index 3dda8c1d83fc..7f011196ce98 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
@@ -89,7 +89,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
 		} else {
 			callback_in_ms(0, output);
 			set_state_id(hdcp, output, H1_A45_AUTHENTICATED);
-			HDCP_FULL_DDC_TRACE(hdcp);
+			set_auth_complete(hdcp, output);
 		}
 		break;
 	case H1_A45_AUTHENTICATED:
@@ -137,7 +137,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
 		}
 		callback_in_ms(0, output);
 		set_state_id(hdcp, output, H1_A45_AUTHENTICATED);
-		HDCP_FULL_DDC_TRACE(hdcp);
+		set_auth_complete(hdcp, output);
 		break;
 	default:
 		status = MOD_HDCP_STATUS_INVALID_STATE;
@@ -239,7 +239,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 			set_state_id(hdcp, output, D1_A6_WAIT_FOR_READY);
 		} else {
 			set_state_id(hdcp, output, D1_A4_AUTHENTICATED);
-			HDCP_FULL_DDC_TRACE(hdcp);
+			set_auth_complete(hdcp, output);
 		}
 		break;
 	case D1_A4_AUTHENTICATED:
@@ -311,7 +311,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 			break;
 		}
 		set_state_id(hdcp, output, D1_A4_AUTHENTICATED);
-		HDCP_FULL_DDC_TRACE(hdcp);
+		set_auth_complete(hdcp, output);
 		break;
 	default:
 		fail_and_restart_in_ms(0, &status, output);
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
index 117c6b45f718..91c22b96ebde 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
@@ -571,9 +571,6 @@ static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp,
 	}
 
 	process_rxstatus(hdcp, event_ctx, input, &status);
-
-	if (status != MOD_HDCP_STATUS_SUCCESS)
-		mod_hdcp_save_current_encryption_states(hdcp);
 out:
 	return status;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
index 70cb230d8f56..1f4095b26409 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
@@ -242,7 +242,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp,
 		}
 		callback_in_ms(0, output);
 		set_state_id(hdcp, output, H2_A5_AUTHENTICATED);
-		HDCP_FULL_DDC_TRACE(hdcp);
+		set_auth_complete(hdcp, output);
 		break;
 	case H2_A5_AUTHENTICATED:
 		if (input->rxstatus_read == FAIL ||
@@ -559,7 +559,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
 			break;
 		}
 		set_state_id(hdcp, output, D2_A5_AUTHENTICATED);
-		HDCP_FULL_DDC_TRACE(hdcp);
+		set_auth_complete(hdcp, output);
 		break;
 	case D2_A5_AUTHENTICATED:
 		if (input->rxstatus_read == FAIL ||
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
index 1a0f7c3dc964..6b3b5f610907 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
@@ -51,6 +51,80 @@ void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
 	}
 }
 
+void mod_hdcp_log_ddc_trace(struct mod_hdcp *hdcp)
+{
+	if (is_hdcp1(hdcp)) {
+		HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv,
+				sizeof(hdcp->auth.msg.hdcp1.bksv));
+		HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps,
+				sizeof(hdcp->auth.msg.hdcp1.bcaps));
+		HDCP_DDC_READ_TRACE(hdcp, "BSTATUS",
+				(uint8_t *)&hdcp->auth.msg.hdcp1.bstatus,
+				sizeof(hdcp->auth.msg.hdcp1.bstatus));
+		HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an,
+				sizeof(hdcp->auth.msg.hdcp1.an));
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv,
+				sizeof(hdcp->auth.msg.hdcp1.aksv));
+		HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo,
+				sizeof(hdcp->auth.msg.hdcp1.ainfo));
+		HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'",
+				(uint8_t *)&hdcp->auth.msg.hdcp1.r0p,
+				sizeof(hdcp->auth.msg.hdcp1.r0p));
+		HDCP_DDC_READ_TRACE(hdcp, "BINFO",
+				(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp,
+				sizeof(hdcp->auth.msg.hdcp1.binfo_dp));
+		HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist,
+				hdcp->auth.msg.hdcp1.ksvlist_size);
+		HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp,
+				sizeof(hdcp->auth.msg.hdcp1.vp));
+	} else if (is_hdcp2(hdcp)) {
+		HDCP_DDC_READ_TRACE(hdcp, "HDCP2Version",
+				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi,
+				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi));
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Caps", hdcp->auth.msg.hdcp2.rxcaps_dp,
+				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp));
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKE Init", hdcp->auth.msg.hdcp2.ake_init,
+				sizeof(hdcp->auth.msg.hdcp2.ake_init));
+		HDCP_DDC_READ_TRACE(hdcp, "AKE Cert", hdcp->auth.msg.hdcp2.ake_cert,
+				sizeof(hdcp->auth.msg.hdcp2.ake_cert));
+		HDCP_DDC_WRITE_TRACE(hdcp, "Stored KM",
+				hdcp->auth.msg.hdcp2.ake_stored_km,
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km));
+		HDCP_DDC_WRITE_TRACE(hdcp, "No Stored KM",
+				hdcp->auth.msg.hdcp2.ake_no_stored_km,
+				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km));
+		HDCP_DDC_READ_TRACE(hdcp, "H'", hdcp->auth.msg.hdcp2.ake_h_prime,
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime));
+		HDCP_DDC_READ_TRACE(hdcp, "Pairing Info",
+				hdcp->auth.msg.hdcp2.ake_pairing_info,
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info));
+		HDCP_DDC_WRITE_TRACE(hdcp, "LC Init", hdcp->auth.msg.hdcp2.lc_init,
+				sizeof(hdcp->auth.msg.hdcp2.lc_init));
+		HDCP_DDC_READ_TRACE(hdcp, "L'", hdcp->auth.msg.hdcp2.lc_l_prime,
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime));
+		HDCP_DDC_WRITE_TRACE(hdcp, "Exchange KS", hdcp->auth.msg.hdcp2.ske_eks,
+				sizeof(hdcp->auth.msg.hdcp2.ske_eks));
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Status",
+				(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus,
+				sizeof(hdcp->auth.msg.hdcp2.rxstatus));
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Id List",
+				hdcp->auth.msg.hdcp2.rx_id_list,
+				hdcp->auth.msg.hdcp2.rx_id_list_size);
+		HDCP_DDC_WRITE_TRACE(hdcp, "Rx Id List Ack",
+				hdcp->auth.msg.hdcp2.repeater_auth_ack,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack));
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Management",
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage,
+				hdcp->auth.msg.hdcp2.stream_manage_size);
+		HDCP_DDC_READ_TRACE(hdcp, "Stream Ready",
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready));
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Type",
+				hdcp->auth.msg.hdcp2.content_stream_type_dp,
+				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp));
+	}
+}
+
 char *mod_hdcp_status_to_str(int32_t status)
 {
 	switch (status) {
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
index 47f8ee2832ff..eb6f9b9c504a 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -106,78 +106,6 @@
 				hdcp->config.index, msg_name,\
 				hdcp->buf); \
 } while (0)
-#define HDCP_FULL_DDC_TRACE(hdcp) do { \
-	if (is_hdcp1(hdcp)) { \
-		HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
-				sizeof(hdcp->auth.msg.hdcp1.bksv)); \
-		HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
-				sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
-		HDCP_DDC_READ_TRACE(hdcp, "BSTATUS", \
-				(uint8_t *)&hdcp->auth.msg.hdcp1.bstatus, \
-				sizeof(hdcp->auth.msg.hdcp1.bstatus)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
-				sizeof(hdcp->auth.msg.hdcp1.an)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
-				sizeof(hdcp->auth.msg.hdcp1.aksv)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
-				sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
-		HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
-				(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
-				sizeof(hdcp->auth.msg.hdcp1.r0p)); \
-		HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
-				(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
-				sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
-		HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
-				hdcp->auth.msg.hdcp1.ksvlist_size); \
-		HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
-				sizeof(hdcp->auth.msg.hdcp1.vp)); \
-	} else { \
-		HDCP_DDC_READ_TRACE(hdcp, "HDCP2Version", \
-				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi, \
-				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi)); \
-		HDCP_DDC_READ_TRACE(hdcp, "Rx Caps", hdcp->auth.msg.hdcp2.rxcaps_dp, \
-				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "AKE Init", hdcp->auth.msg.hdcp2.ake_init, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_init)); \
-		HDCP_DDC_READ_TRACE(hdcp, "AKE Cert", hdcp->auth.msg.hdcp2.ake_cert, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_cert)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "Stored KM", \
-				hdcp->auth.msg.hdcp2.ake_stored_km, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "No Stored KM", \
-				hdcp->auth.msg.hdcp2.ake_no_stored_km, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)); \
-		HDCP_DDC_READ_TRACE(hdcp, "H'", hdcp->auth.msg.hdcp2.ake_h_prime, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)); \
-		HDCP_DDC_READ_TRACE(hdcp, "Pairing Info", \
-				hdcp->auth.msg.hdcp2.ake_pairing_info, \
-				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "LC Init", hdcp->auth.msg.hdcp2.lc_init, \
-				sizeof(hdcp->auth.msg.hdcp2.lc_init)); \
-		HDCP_DDC_READ_TRACE(hdcp, "L'", hdcp->auth.msg.hdcp2.lc_l_prime, \
-				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "Exchange KS", hdcp->auth.msg.hdcp2.ske_eks, \
-				sizeof(hdcp->auth.msg.hdcp2.ske_eks)); \
-		HDCP_DDC_READ_TRACE(hdcp, "Rx Status", \
-				(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus, \
-				sizeof(hdcp->auth.msg.hdcp2.rxstatus)); \
-		HDCP_DDC_READ_TRACE(hdcp, "Rx Id List", \
-				hdcp->auth.msg.hdcp2.rx_id_list, \
-				hdcp->auth.msg.hdcp2.rx_id_list_size); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "Rx Id List Ack", \
-				hdcp->auth.msg.hdcp2.repeater_auth_ack, \
-				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Management", \
-				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage, \
-				hdcp->auth.msg.hdcp2.stream_manage_size); \
-		HDCP_DDC_READ_TRACE(hdcp, "Stream Ready", \
-				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready, \
-				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)); \
-		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Type", \
-				hdcp->auth.msg.hdcp2.content_stream_type_dp, \
-				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp)); \
-	} \
-} while (0)
 #define HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, i) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\tadd display %d", \
 				hdcp->config.index, i)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index 1b02056bc8bd..e9bd84ec027d 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -45,7 +45,7 @@ static void hdcp2_message_init(struct mod_hdcp *hdcp,
 	in->process.msg3_desc.msg_size = 0;
 }
 
-static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v2(
+static enum mod_hdcp_status remove_display_from_topology_v2(
 		struct mod_hdcp *hdcp, uint8_t index)
 {
 	struct psp_context *psp = hdcp->config.psp.handle;
@@ -54,7 +54,7 @@ static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v2(
 			get_active_display_at_index(hdcp, index);
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
-	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
 	if (!display || !is_display_active(display))
 		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
@@ -81,7 +81,7 @@ static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v2(
 	return status;
 }
 
-static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v3(
+static enum mod_hdcp_status remove_display_from_topology_v3(
 		struct mod_hdcp *hdcp, uint8_t index)
 {
 	struct psp_context *psp = hdcp->config.psp.handle;
@@ -90,7 +90,7 @@ static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v3(
 		get_active_display_at_index(hdcp, index);
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
-	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
 	if (!display || !is_display_active(display))
 		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
@@ -107,7 +107,7 @@ static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v3(
 	psp_dtm_invoke(psp, dtm_cmd->cmd_id);
 
 	if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
-		status = mod_hdcp_remove_display_from_topology_v2(hdcp, index);
+		status = remove_display_from_topology_v2(hdcp, index);
 		if (status != MOD_HDCP_STATUS_SUCCESS)
 			display->state = MOD_HDCP_DISPLAY_INACTIVE;
 	} else {
@@ -120,20 +120,7 @@ static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v3(
 	return status;
 }
 
-enum mod_hdcp_status mod_hdcp_remove_display_from_topology(
-		struct mod_hdcp *hdcp, uint8_t index)
-{
-	enum mod_hdcp_status status = MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE;
-
-	if (hdcp->config.psp.caps.dtm_v3_supported)
-		status = mod_hdcp_remove_display_from_topology_v3(hdcp, index);
-	else
-		status = mod_hdcp_remove_display_from_topology_v2(hdcp, index);
-
-	return status;
-}
-
-static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v2(
+static enum mod_hdcp_status add_display_to_topology_v2(
 		struct mod_hdcp *hdcp, struct mod_hdcp_display *display)
 {
 	struct psp_context *psp = hdcp->config.psp.handle;
@@ -141,13 +128,13 @@ static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v2(
 	struct mod_hdcp_link *link = &hdcp->connection.link;
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
-	if (!psp->dtm_context.dtm_initialized) {
+	if (!psp->dtm_context.context.initialized) {
 		DRM_INFO("Failed to add display topology, DTM TA is not initialized.");
 		display->state = MOD_HDCP_DISPLAY_INACTIVE;
 		return MOD_HDCP_STATUS_FAILURE;
 	}
 
-	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->dtm_context.mutex);
 	memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
@@ -180,7 +167,7 @@ static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v2(
 	return status;
 }
 
-static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v3(
+static enum mod_hdcp_status add_display_to_topology_v3(
 		struct mod_hdcp *hdcp, struct mod_hdcp_display *display)
 {
 	struct psp_context *psp = hdcp->config.psp.handle;
@@ -188,13 +175,13 @@ static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v3(
 	struct mod_hdcp_link *link = &hdcp->connection.link;
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
-	if (!psp->dtm_context.dtm_initialized) {
+	if (!psp->dtm_context.context.initialized) {
 		DRM_INFO("Failed to add display topology, DTM TA is not initialized.");
 		display->state = MOD_HDCP_DISPLAY_INACTIVE;
 		return MOD_HDCP_STATUS_FAILURE;
 	}
 
-	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->dtm_context.mutex);
 	memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
@@ -220,7 +207,7 @@ static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v3(
 	psp_dtm_invoke(psp, dtm_cmd->cmd_id);
 
 	if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
-		status = mod_hdcp_add_display_to_topology_v2(hdcp, display);
+		status = add_display_to_topology_v2(hdcp, display);
 		if (status != MOD_HDCP_STATUS_SUCCESS)
 			display->state = MOD_HDCP_DISPLAY_INACTIVE;
 	} else {
@@ -232,15 +219,28 @@ static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v3(
 	return status;
 }
 
+enum mod_hdcp_status mod_hdcp_remove_display_from_topology(
+		struct mod_hdcp *hdcp, uint8_t index)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE;
+
+	if (hdcp->config.psp.caps.dtm_v3_supported)
+		status = remove_display_from_topology_v3(hdcp, index);
+	else
+		status = remove_display_from_topology_v2(hdcp, index);
+
+	return status;
+}
+
 enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp,
 					       struct mod_hdcp_display *display)
 {
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	if (hdcp->config.psp.caps.dtm_v3_supported)
-		status = mod_hdcp_add_display_to_topology_v3(hdcp, display);
+		status = add_display_to_topology_v3(hdcp, display);
 	else
-		status = mod_hdcp_add_display_to_topology_v2(hdcp, display);
+		status = add_display_to_topology_v2(hdcp, display);
 
 	return status;
 }
@@ -253,12 +253,12 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
 	struct ta_hdcp_shared_memory *hdcp_cmd;
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
-	if (!psp->hdcp_context.hdcp_initialized) {
+	if (!psp->hdcp_context.context.initialized) {
 		DRM_ERROR("Failed to create hdcp session. HDCP TA is not initialized.");
 		return MOD_HDCP_STATUS_FAILURE;
 	}
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->hdcp_context.mutex);
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
@@ -293,7 +293,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp1_destroy_session.session_handle = hdcp->auth.id;
@@ -325,7 +325,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_validate_rx(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp1_first_part_authentication.session_handle = hdcp->auth.id;
@@ -367,7 +367,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp1_enable_encryption.session_handle = hdcp->auth.id;
@@ -393,7 +393,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_validate_ksvlist_vp(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp1_second_part_authentication.session_handle = hdcp->auth.id;
@@ -436,7 +436,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(struct mod_hdcp
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 
 	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
 
@@ -471,7 +471,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
@@ -498,7 +498,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 
-	if (!psp->hdcp_context.hdcp_initialized) {
+	if (!psp->hdcp_context.context.initialized) {
 		DRM_ERROR("Failed to create hdcp session, HDCP TA is not initialized");
 		return MOD_HDCP_STATUS_FAILURE;
 	}
@@ -508,7 +508,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp)
 
 	mutex_lock(&psp->hdcp_context.mutex);
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index;
@@ -545,7 +545,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp2_destroy_session.session_handle = hdcp->auth.id;
@@ -579,7 +579,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -611,7 +611,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_ake_cert(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -671,7 +671,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -717,7 +717,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_prepare_lc_init(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -750,7 +750,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_l_prime(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -785,7 +785,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_prepare_eks(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -833,7 +833,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp)
 
 	mutex_lock(&psp->hdcp_context.mutex);
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	hdcp_cmd->in_msg.hdcp2_set_encryption.session_handle = hdcp->auth.id;
@@ -862,7 +862,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp)
 
 	mutex_lock(&psp->hdcp_context.mutex);
 
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -914,7 +914,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(struct mod_hdcp
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -958,7 +958,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_prepare_stream_management(struct mod_hdcp *h
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -994,7 +994,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	mutex_lock(&psp->hdcp_context.mutex);
-	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
 	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
@@ -1021,14 +1021,3 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp)
 	mutex_unlock(&psp->hdcp_context.mutex);
 	return status;
 }
-
-bool mod_hdcp_is_link_encryption_enabled(struct mod_hdcp *hdcp)
-{
-	/* unsupported */
-	return true;
-}
-
-void mod_hdcp_save_current_encryption_states(struct mod_hdcp *hdcp)
-{
-	/* unsupported */
-}
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
index c590493fd293..f37101f5a777 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
@@ -123,7 +123,6 @@ enum mod_hdcp_display_state {
 
 struct mod_hdcp_psp_caps {
 	uint8_t dtm_v3_supported;
-	uint8_t opm_state_query_supported;
 };
 
 enum mod_hdcp_display_disable_option {
@@ -226,6 +225,7 @@ struct mod_hdcp_output {
 	uint8_t watchdog_timer_stop;
 	uint16_t callback_delay;
 	uint16_t watchdog_timer_delay;
+	uint8_t auth_complete;
 };
 
 /* used to represent per display info */
@@ -282,15 +282,22 @@ enum mod_hdcp_status mod_hdcp_setup(struct mod_hdcp *hdcp,
 /* called per link on link destroy */
 enum mod_hdcp_status mod_hdcp_teardown(struct mod_hdcp *hdcp);
 
-/* called per display on cp_desired set to true */
+/* called per display after stream is enabled */
 enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp,
 		struct mod_hdcp_link *link, struct mod_hdcp_display *display,
 		struct mod_hdcp_output *output);
 
-/* called per display on cp_desired set to false */
+/* called per display before stream is disabled */
 enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp,
 		uint8_t index, struct mod_hdcp_output *output);
 
+/* called per display to apply new authentication adjustment */
+enum mod_hdcp_status mod_hdcp_update_authentication(struct mod_hdcp *hdcp,
+		uint8_t index,
+		struct mod_hdcp_link_adjustment *link_adjust,
+		struct mod_hdcp_display_adjustment *display_adjust,
+		struct mod_hdcp_output *output);
+
 /* called to query hdcp information on a specific index */
 enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
 		uint8_t index, struct mod_hdcp_display_query *query);
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index ff1d3d4a6488..257f280d3d53 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -47,6 +47,7 @@ enum amd_apu_flags {
 	AMD_APU_IS_RENOIR = 0x00000008UL,
 	AMD_APU_IS_GREEN_SARDINE = 0x00000010UL,
 	AMD_APU_IS_VANGOGH = 0x00000020UL,
+	AMD_APU_IS_CYAN_SKILLFISH2 = 0x00000040UL,
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h
index e5fd0121ceff..a9d553ef26c0 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h
@@ -5971,6 +5971,7 @@
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT1_INT_EN__SHIFT                                                    0xb
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT2_INT_EN__SHIFT                                                    0xc
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_UNDEFINED_ADDRESS_FAULT_INT_EN__SHIFT                                   0xd
+#define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT_IH_INT_EN__SHIFT                                                  0x11
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_TIMER0_INT_EN_MASK                                                      0x00000001L
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_TIMER1_INT_EN_MASK                                                      0x00000002L
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_INBOX0_READY_INT_EN_MASK                                                0x00000004L
@@ -5985,6 +5986,7 @@
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT1_INT_EN_MASK                                                      0x00000800L
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT2_INT_EN_MASK                                                      0x00001000L
 #define DMCUB_INTERRUPT_ENABLE__DMCUB_UNDEFINED_ADDRESS_FAULT_INT_EN_MASK                                     0x00002000L
+#define DMCUB_INTERRUPT_ENABLE__DMCUB_GPINT_IH_INT_EN_MASK                                                    0x00020000L
 //DMCUB_INTERRUPT_ACK
 #define DMCUB_INTERRUPT_ACK__DMCUB_TIMER0_INT_ACK__SHIFT                                                      0x0
 #define DMCUB_INTERRUPT_ACK__DMCUB_TIMER1_INT_ACK__SHIFT                                                      0x1
@@ -6000,6 +6002,7 @@
 #define DMCUB_INTERRUPT_ACK__DMCUB_GPINT1_INT_ACK__SHIFT                                                      0xb
 #define DMCUB_INTERRUPT_ACK__DMCUB_GPINT2_INT_ACK__SHIFT                                                      0xc
 #define DMCUB_INTERRUPT_ACK__DMCUB_UNDEFINED_ADDRESS_FAULT_ACK__SHIFT                                         0xd
+#define DMCUB_INTERRUPT_ACK__DMCUB_GPINT_IH_INT_ACK__SHIFT                                                    0x11
 #define DMCUB_INTERRUPT_ACK__DMCUB_TIMER0_INT_ACK_MASK                                                        0x00000001L
 #define DMCUB_INTERRUPT_ACK__DMCUB_TIMER1_INT_ACK_MASK                                                        0x00000002L
 #define DMCUB_INTERRUPT_ACK__DMCUB_INBOX0_READY_INT_ACK_MASK                                                  0x00000004L
@@ -6014,6 +6017,7 @@
 #define DMCUB_INTERRUPT_ACK__DMCUB_GPINT1_INT_ACK_MASK                                                        0x00000800L
 #define DMCUB_INTERRUPT_ACK__DMCUB_GPINT2_INT_ACK_MASK                                                        0x00001000L
 #define DMCUB_INTERRUPT_ACK__DMCUB_UNDEFINED_ADDRESS_FAULT_ACK_MASK                                           0x00002000L
+#define DMCUB_INTERRUPT_ACK__DMCUB_GPINT_IH_INT_ACK_MASK                                                      0x00020000L
 //DMCUB_INTERRUPT_STATUS
 #define DMCUB_INTERRUPT_STATUS__DMCUB_TIMER0_INT_STAT__SHIFT                                                  0x0
 #define DMCUB_INTERRUPT_STATUS__DMCUB_TIMER1_INT_STAT__SHIFT                                                  0x1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
index a9ad00e017a5..1a8a6a350789 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
@@ -508,6 +508,10 @@
 #define regCP_ME2_PIPE2_INT_STATUS_BASE_IDX                                                             0
 #define regCP_ME2_PIPE3_INT_STATUS                                                                      0x1094
 #define regCP_ME2_PIPE3_INT_STATUS_BASE_IDX                                                             0
+#define regCP_ME1_INT_STAT_DEBUG                                                                        0x1095
+#define regCP_ME1_INT_STAT_DEBUG_BASE_IDX                                                               0
+#define regCP_ME2_INT_STAT_DEBUG                                                                        0x1096
+#define regCP_ME2_INT_STAT_DEBUG_BASE_IDX                                                               0
 #define regCC_GC_EDC_CONFIG                                                                             0x1098
 #define regCC_GC_EDC_CONFIG_BASE_IDX                                                                    0
 #define regCP_ME1_PIPE_PRIORITY_CNTS                                                                    0x1099
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
index bc4d2997cb51..049221262e5c 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
@@ -2989,6 +2989,60 @@
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC2_INT_STATUS_MASK                                                     0x20000000L
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC1_INT_STATUS_MASK                                                     0x40000000L
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC0_INT_STATUS_MASK                                                     0x80000000L
+//CP_ME1_INT_STAT_DEBUG
+#define CP_ME1_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED__SHIFT                                           0xc
+#define CP_ME1_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED__SHIFT                                            0xd
+#define CP_ME1_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED__SHIFT                                               0xe
+#define CP_ME1_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS__SHIFT                                                0xf
+#define CP_ME1_INT_STAT_DEBUG__GPF_INT_ASSERTED__SHIFT                                                        0x10
+#define CP_ME1_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED__SHIFT                                           0x11
+#define CP_ME1_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED__SHIFT                                                   0x17
+#define CP_ME1_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED__SHIFT                                               0x18
+#define CP_ME1_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED__SHIFT                                                 0x1a
+#define CP_ME1_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED__SHIFT                                         0x1b
+#define CP_ME1_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED__SHIFT                                                   0x1d
+#define CP_ME1_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED__SHIFT                                                   0x1e
+#define CP_ME1_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED__SHIFT                                                   0x1f
+#define CP_ME1_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED_MASK                                             0x00001000L
+#define CP_ME1_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED_MASK                                              0x00002000L
+#define CP_ME1_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED_MASK                                                 0x00004000L
+#define CP_ME1_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS_MASK                                                  0x00008000L
+#define CP_ME1_INT_STAT_DEBUG__GPF_INT_ASSERTED_MASK                                                          0x00010000L
+#define CP_ME1_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED_MASK                                             0x00020000L
+#define CP_ME1_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED_MASK                                                     0x00800000L
+#define CP_ME1_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED_MASK                                                 0x01000000L
+#define CP_ME1_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED_MASK                                                   0x04000000L
+#define CP_ME1_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED_MASK                                           0x08000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED_MASK                                                     0x20000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED_MASK                                                     0x40000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED_MASK                                                     0x80000000L
+//CP_ME2_INT_STAT_DEBUG
+#define CP_ME2_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED__SHIFT                                           0xc
+#define CP_ME2_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED__SHIFT                                            0xd
+#define CP_ME2_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED__SHIFT                                               0xe
+#define CP_ME2_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS__SHIFT                                                0xf
+#define CP_ME2_INT_STAT_DEBUG__GPF_INT_ASSERTED__SHIFT                                                        0x10
+#define CP_ME2_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED__SHIFT                                           0x11
+#define CP_ME2_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED__SHIFT                                                   0x17
+#define CP_ME2_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED__SHIFT                                               0x18
+#define CP_ME2_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED__SHIFT                                                 0x1a
+#define CP_ME2_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED__SHIFT                                         0x1b
+#define CP_ME2_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED__SHIFT                                                   0x1d
+#define CP_ME2_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED__SHIFT                                                   0x1e
+#define CP_ME2_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED__SHIFT                                                   0x1f
+#define CP_ME2_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED_MASK                                             0x00001000L
+#define CP_ME2_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED_MASK                                              0x00002000L
+#define CP_ME2_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED_MASK                                                 0x00004000L
+#define CP_ME2_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS_MASK                                                  0x00008000L
+#define CP_ME2_INT_STAT_DEBUG__GPF_INT_ASSERTED_MASK                                                          0x00010000L
+#define CP_ME2_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED_MASK                                             0x00020000L
+#define CP_ME2_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED_MASK                                                     0x00800000L
+#define CP_ME2_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED_MASK                                                 0x01000000L
+#define CP_ME2_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED_MASK                                                   0x04000000L
+#define CP_ME2_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED_MASK                                           0x08000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED_MASK                                                     0x20000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED_MASK                                                     0x40000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED_MASK                                                     0x80000000L
 //CP_ME2_PIPE0_INT_STATUS
 #define CP_ME2_PIPE0_INT_STATUS__CMP_QUERY_STATUS_INT_STATUS__SHIFT                                           0xc
 #define CP_ME2_PIPE0_INT_STATUS__DEQUEUE_REQUEST_INT_STATUS__SHIFT                                            0xd
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_11_0_8_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_11_0_8_offset.h
new file mode 100644
index 000000000000..19293ccaec23
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_11_0_8_offset.h
@@ -0,0 +1,352 @@
+/*
+ * Copyright (C) 2021  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _mp_11_0_8_OFFSET_HEADER
+#define _mp_11_0_8_OFFSET_HEADER
+
+
+
+// addressBlock: mp_SmuMp0_SmnDec
+// base address: 0x0
+#define mmMP0_SMN_C2PMSG_32                                                                            0x0060
+#define mmMP0_SMN_C2PMSG_32_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_33                                                                            0x0061
+#define mmMP0_SMN_C2PMSG_33_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_34                                                                            0x0062
+#define mmMP0_SMN_C2PMSG_34_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_35                                                                            0x0063
+#define mmMP0_SMN_C2PMSG_35_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_36                                                                            0x0064
+#define mmMP0_SMN_C2PMSG_36_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_37                                                                            0x0065
+#define mmMP0_SMN_C2PMSG_37_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_38                                                                            0x0066
+#define mmMP0_SMN_C2PMSG_38_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_39                                                                            0x0067
+#define mmMP0_SMN_C2PMSG_39_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_40                                                                            0x0068
+#define mmMP0_SMN_C2PMSG_40_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_41                                                                            0x0069
+#define mmMP0_SMN_C2PMSG_41_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_42                                                                            0x006a
+#define mmMP0_SMN_C2PMSG_42_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_43                                                                            0x006b
+#define mmMP0_SMN_C2PMSG_43_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_44                                                                            0x006c
+#define mmMP0_SMN_C2PMSG_44_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_45                                                                            0x006d
+#define mmMP0_SMN_C2PMSG_45_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_46                                                                            0x006e
+#define mmMP0_SMN_C2PMSG_46_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_47                                                                            0x006f
+#define mmMP0_SMN_C2PMSG_47_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_48                                                                            0x0070
+#define mmMP0_SMN_C2PMSG_48_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_49                                                                            0x0071
+#define mmMP0_SMN_C2PMSG_49_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_50                                                                            0x0072
+#define mmMP0_SMN_C2PMSG_50_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_51                                                                            0x0073
+#define mmMP0_SMN_C2PMSG_51_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_52                                                                            0x0074
+#define mmMP0_SMN_C2PMSG_52_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_53                                                                            0x0075
+#define mmMP0_SMN_C2PMSG_53_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_54                                                                            0x0076
+#define mmMP0_SMN_C2PMSG_54_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_55                                                                            0x0077
+#define mmMP0_SMN_C2PMSG_55_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_56                                                                            0x0078
+#define mmMP0_SMN_C2PMSG_56_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_57                                                                            0x0079
+#define mmMP0_SMN_C2PMSG_57_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_58                                                                            0x007a
+#define mmMP0_SMN_C2PMSG_58_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_59                                                                            0x007b
+#define mmMP0_SMN_C2PMSG_59_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_60                                                                            0x007c
+#define mmMP0_SMN_C2PMSG_60_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_61                                                                            0x007d
+#define mmMP0_SMN_C2PMSG_61_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_62                                                                            0x007e
+#define mmMP0_SMN_C2PMSG_62_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_63                                                                            0x007f
+#define mmMP0_SMN_C2PMSG_63_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_64                                                                            0x0080
+#define mmMP0_SMN_C2PMSG_64_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_65                                                                            0x0081
+#define mmMP0_SMN_C2PMSG_65_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_66                                                                            0x0082
+#define mmMP0_SMN_C2PMSG_66_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_67                                                                            0x0083
+#define mmMP0_SMN_C2PMSG_67_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_68                                                                            0x0084
+#define mmMP0_SMN_C2PMSG_68_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_69                                                                            0x0085
+#define mmMP0_SMN_C2PMSG_69_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_70                                                                            0x0086
+#define mmMP0_SMN_C2PMSG_70_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_71                                                                            0x0087
+#define mmMP0_SMN_C2PMSG_71_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_72                                                                            0x0088
+#define mmMP0_SMN_C2PMSG_72_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_73                                                                            0x0089
+#define mmMP0_SMN_C2PMSG_73_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_74                                                                            0x008a
+#define mmMP0_SMN_C2PMSG_74_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_75                                                                            0x008b
+#define mmMP0_SMN_C2PMSG_75_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_76                                                                            0x008c
+#define mmMP0_SMN_C2PMSG_76_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_77                                                                            0x008d
+#define mmMP0_SMN_C2PMSG_77_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_78                                                                            0x008e
+#define mmMP0_SMN_C2PMSG_78_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_79                                                                            0x008f
+#define mmMP0_SMN_C2PMSG_79_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_80                                                                            0x0090
+#define mmMP0_SMN_C2PMSG_80_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_81                                                                            0x0091
+#define mmMP0_SMN_C2PMSG_81_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_82                                                                            0x0092
+#define mmMP0_SMN_C2PMSG_82_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_83                                                                            0x0093
+#define mmMP0_SMN_C2PMSG_83_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_84                                                                            0x0094
+#define mmMP0_SMN_C2PMSG_84_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_85                                                                            0x0095
+#define mmMP0_SMN_C2PMSG_85_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_86                                                                            0x0096
+#define mmMP0_SMN_C2PMSG_86_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_87                                                                            0x0097
+#define mmMP0_SMN_C2PMSG_87_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_88                                                                            0x0098
+#define mmMP0_SMN_C2PMSG_88_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_89                                                                            0x0099
+#define mmMP0_SMN_C2PMSG_89_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_90                                                                            0x009a
+#define mmMP0_SMN_C2PMSG_90_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_91                                                                            0x009b
+#define mmMP0_SMN_C2PMSG_91_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_92                                                                            0x009c
+#define mmMP0_SMN_C2PMSG_92_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_93                                                                            0x009d
+#define mmMP0_SMN_C2PMSG_93_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_94                                                                            0x009e
+#define mmMP0_SMN_C2PMSG_94_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_95                                                                            0x009f
+#define mmMP0_SMN_C2PMSG_95_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_96                                                                            0x00a0
+#define mmMP0_SMN_C2PMSG_96_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_97                                                                            0x00a1
+#define mmMP0_SMN_C2PMSG_97_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_98                                                                            0x00a2
+#define mmMP0_SMN_C2PMSG_98_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_99                                                                            0x00a3
+#define mmMP0_SMN_C2PMSG_99_BASE_IDX                                                                   0
+#define mmMP0_SMN_C2PMSG_100                                                                           0x00a4
+#define mmMP0_SMN_C2PMSG_100_BASE_IDX                                                                  0
+#define mmMP0_SMN_C2PMSG_101                                                                           0x00a5
+#define mmMP0_SMN_C2PMSG_101_BASE_IDX                                                                  0
+#define mmMP0_SMN_C2PMSG_102                                                                           0x00a6
+#define mmMP0_SMN_C2PMSG_102_BASE_IDX                                                                  0
+#define mmMP0_SMN_C2PMSG_103                                                                           0x00a7
+#define mmMP0_SMN_C2PMSG_103_BASE_IDX                                                                  0
+#define mmMP0_SMN_IH_CREDIT                                                                            0x00c1
+#define mmMP0_SMN_IH_CREDIT_BASE_IDX                                                                   0
+#define mmMP0_SMN_IH_SW_INT                                                                            0x00c2
+#define mmMP0_SMN_IH_SW_INT_BASE_IDX                                                                   0
+#define mmMP0_SMN_IH_SW_INT_CTRL                                                                       0x00c3
+#define mmMP0_SMN_IH_SW_INT_CTRL_BASE_IDX                                                              0
+
+
+// addressBlock: mp_SmuMp1_SmnDec
+// base address: 0x0
+#define mmMP1_SMN_C2PMSG_32                                                                            0x0260
+#define mmMP1_SMN_C2PMSG_32_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_33                                                                            0x0261
+#define mmMP1_SMN_C2PMSG_33_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_34                                                                            0x0262
+#define mmMP1_SMN_C2PMSG_34_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_35                                                                            0x0263
+#define mmMP1_SMN_C2PMSG_35_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_36                                                                            0x0264
+#define mmMP1_SMN_C2PMSG_36_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_37                                                                            0x0265
+#define mmMP1_SMN_C2PMSG_37_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_38                                                                            0x0266
+#define mmMP1_SMN_C2PMSG_38_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_39                                                                            0x0267
+#define mmMP1_SMN_C2PMSG_39_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_40                                                                            0x0268
+#define mmMP1_SMN_C2PMSG_40_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_41                                                                            0x0269
+#define mmMP1_SMN_C2PMSG_41_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_42                                                                            0x026a
+#define mmMP1_SMN_C2PMSG_42_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_43                                                                            0x026b
+#define mmMP1_SMN_C2PMSG_43_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_44                                                                            0x026c
+#define mmMP1_SMN_C2PMSG_44_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_45                                                                            0x026d
+#define mmMP1_SMN_C2PMSG_45_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_46                                                                            0x026e
+#define mmMP1_SMN_C2PMSG_46_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_47                                                                            0x026f
+#define mmMP1_SMN_C2PMSG_47_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_48                                                                            0x0270
+#define mmMP1_SMN_C2PMSG_48_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_49                                                                            0x0271
+#define mmMP1_SMN_C2PMSG_49_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_50                                                                            0x0272
+#define mmMP1_SMN_C2PMSG_50_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_51                                                                            0x0273
+#define mmMP1_SMN_C2PMSG_51_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_52                                                                            0x0274
+#define mmMP1_SMN_C2PMSG_52_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_53                                                                            0x0275
+#define mmMP1_SMN_C2PMSG_53_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_54                                                                            0x0276
+#define mmMP1_SMN_C2PMSG_54_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_55                                                                            0x0277
+#define mmMP1_SMN_C2PMSG_55_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_56                                                                            0x0278
+#define mmMP1_SMN_C2PMSG_56_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_57                                                                            0x0279
+#define mmMP1_SMN_C2PMSG_57_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_58                                                                            0x027a
+#define mmMP1_SMN_C2PMSG_58_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_59                                                                            0x027b
+#define mmMP1_SMN_C2PMSG_59_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_60                                                                            0x027c
+#define mmMP1_SMN_C2PMSG_60_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_61                                                                            0x027d
+#define mmMP1_SMN_C2PMSG_61_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_62                                                                            0x027e
+#define mmMP1_SMN_C2PMSG_62_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_63                                                                            0x027f
+#define mmMP1_SMN_C2PMSG_63_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_64                                                                            0x0280
+#define mmMP1_SMN_C2PMSG_64_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_65                                                                            0x0281
+#define mmMP1_SMN_C2PMSG_65_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_66                                                                            0x0282
+#define mmMP1_SMN_C2PMSG_66_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_67                                                                            0x0283
+#define mmMP1_SMN_C2PMSG_67_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_68                                                                            0x0284
+#define mmMP1_SMN_C2PMSG_68_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_69                                                                            0x0285
+#define mmMP1_SMN_C2PMSG_69_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_70                                                                            0x0286
+#define mmMP1_SMN_C2PMSG_70_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_71                                                                            0x0287
+#define mmMP1_SMN_C2PMSG_71_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_72                                                                            0x0288
+#define mmMP1_SMN_C2PMSG_72_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_73                                                                            0x0289
+#define mmMP1_SMN_C2PMSG_73_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_74                                                                            0x028a
+#define mmMP1_SMN_C2PMSG_74_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_75                                                                            0x028b
+#define mmMP1_SMN_C2PMSG_75_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_76                                                                            0x028c
+#define mmMP1_SMN_C2PMSG_76_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_77                                                                            0x028d
+#define mmMP1_SMN_C2PMSG_77_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_78                                                                            0x028e
+#define mmMP1_SMN_C2PMSG_78_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_79                                                                            0x028f
+#define mmMP1_SMN_C2PMSG_79_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_80                                                                            0x0290
+#define mmMP1_SMN_C2PMSG_80_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_81                                                                            0x0291
+#define mmMP1_SMN_C2PMSG_81_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_82                                                                            0x0292
+#define mmMP1_SMN_C2PMSG_82_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_83                                                                            0x0293
+#define mmMP1_SMN_C2PMSG_83_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_84                                                                            0x0294
+#define mmMP1_SMN_C2PMSG_84_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_85                                                                            0x0295
+#define mmMP1_SMN_C2PMSG_85_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_86                                                                            0x0296
+#define mmMP1_SMN_C2PMSG_86_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_87                                                                            0x0297
+#define mmMP1_SMN_C2PMSG_87_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_88                                                                            0x0298
+#define mmMP1_SMN_C2PMSG_88_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_89                                                                            0x0299
+#define mmMP1_SMN_C2PMSG_89_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_90                                                                            0x029a
+#define mmMP1_SMN_C2PMSG_90_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_91                                                                            0x029b
+#define mmMP1_SMN_C2PMSG_91_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_92                                                                            0x029c
+#define mmMP1_SMN_C2PMSG_92_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_93                                                                            0x029d
+#define mmMP1_SMN_C2PMSG_93_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_94                                                                            0x029e
+#define mmMP1_SMN_C2PMSG_94_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_95                                                                            0x029f
+#define mmMP1_SMN_C2PMSG_95_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_96                                                                            0x02a0
+#define mmMP1_SMN_C2PMSG_96_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_97                                                                            0x02a1
+#define mmMP1_SMN_C2PMSG_97_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_98                                                                            0x02a2
+#define mmMP1_SMN_C2PMSG_98_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_99                                                                            0x02a3
+#define mmMP1_SMN_C2PMSG_99_BASE_IDX                                                                   0
+#define mmMP1_SMN_C2PMSG_100                                                                           0x02a4
+#define mmMP1_SMN_C2PMSG_100_BASE_IDX                                                                  0
+#define mmMP1_SMN_C2PMSG_101                                                                           0x02a5
+#define mmMP1_SMN_C2PMSG_101_BASE_IDX                                                                  0
+#define mmMP1_SMN_C2PMSG_102                                                                           0x02a6
+#define mmMP1_SMN_C2PMSG_102_BASE_IDX                                                                  0
+#define mmMP1_SMN_C2PMSG_103                                                                           0x02a7
+#define mmMP1_SMN_C2PMSG_103_BASE_IDX                                                                  0
+#define mmMP1_SMN_IH_CREDIT                                                                            0x02c1
+#define mmMP1_SMN_IH_CREDIT_BASE_IDX                                                                   0
+#define mmMP1_SMN_IH_SW_INT                                                                            0x02c2
+#define mmMP1_SMN_IH_SW_INT_BASE_IDX                                                                   0
+#define mmMP1_SMN_IH_SW_INT_CTRL                                                                       0x02c3
+#define mmMP1_SMN_IH_SW_INT_CTRL_BASE_IDX                                                              0
+#define mmMP1_SMN_FPS_CNT                                                                              0x02c4
+#define mmMP1_SMN_FPS_CNT_BASE_IDX                                                                     0
+#define mmMP1_SMN_EXT_SCRATCH0                                                                         0x03c0
+#define mmMP1_SMN_EXT_SCRATCH0_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH1                                                                         0x03c1
+#define mmMP1_SMN_EXT_SCRATCH1_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH2                                                                         0x03c2
+#define mmMP1_SMN_EXT_SCRATCH2_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH3                                                                         0x03c3
+#define mmMP1_SMN_EXT_SCRATCH3_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH4                                                                         0x03c4
+#define mmMP1_SMN_EXT_SCRATCH4_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH5                                                                         0x03c5
+#define mmMP1_SMN_EXT_SCRATCH5_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH6                                                                         0x03c6
+#define mmMP1_SMN_EXT_SCRATCH6_BASE_IDX                                                                0
+#define mmMP1_SMN_EXT_SCRATCH7                                                                         0x03c7
+#define mmMP1_SMN_EXT_SCRATCH7_BASE_IDX                                                                0
+
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
index a485526f3a51..8474f419caa5 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
@@ -38,6 +38,9 @@
 #define mmCG_TACH_CTRL                                                                                 0x006a
 #define mmCG_TACH_CTRL_BASE_IDX                                                                        0
 
+#define mmCG_TACH_STATUS                                                                               0x006b
+#define mmCG_TACH_STATUS_BASE_IDX                                                                      0
+
 #define mmTHM_THERMAL_INT_ENA                                                                          0x000a
 #define mmTHM_THERMAL_INT_ENA_BASE_IDX                                                                 0
 #define mmTHM_THERMAL_INT_CTRL                                                                         0x000b
@@ -49,4 +52,7 @@
 #define mmTHM_BACO_CNTL                                                                                0x0081
 #define mmTHM_BACO_CNTL_BASE_IDX                                                                       0
 
+#define mmCG_THERMAL_STATUS                                                                            0x006C
+#define mmCG_THERMAL_STATUS_BASE_IDX                                                                   0
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
index d130d92aee19..f2f9eae9a68f 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
@@ -92,5 +92,8 @@
 #define THM_TCON_THERM_TRIP__RSVD3_MASK                                                                       0x7FFFC000L
 #define THM_TCON_THERM_TRIP__SW_THERM_TP_MASK                                                                 0x80000000L
 
+#define CG_THERMAL_STATUS__FDO_PWM_DUTY__SHIFT                                                                0x9
+#define CG_THERMAL_STATUS__FDO_PWM_DUTY_MASK                                                                  0x0001FE00L
+
 #endif
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h
index 4c5097fa0c09..20329da53b0a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h
@@ -1,79 +1,100 @@
-#ifndef _umc_8_7_0_SH_MASK_HEADER

-#define _umc_8_7_0_SH_MASK_HEADER

-

-//UMCCH0_0_GeccErrCntSel

-#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel__SHIFT                                                        0x0

-#define UMCCH0_0_GeccErrCntSel__GeccErrInt__SHIFT                                                             0xc

-#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn__SHIFT                                                           0xf

-#define UMCCH0_0_GeccErrCntSel__PoisonCntEn__SHIFT                                                            0x10

-#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel_MASK                                                          0x0000000FL

-#define UMCCH0_0_GeccErrCntSel__GeccErrInt_MASK                                                               0x00003000L

-#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn_MASK                                                             0x00008000L

-#define UMCCH0_0_GeccErrCntSel__PoisonCntEn_MASK                                                              0x00030000L

-//UMCCH0_0_GeccErrCnt

-#define UMCCH0_0_GeccErrCnt__GeccErrCnt__SHIFT                                                                0x0

-#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt__SHIFT                                                          0x10

-#define UMCCH0_0_GeccErrCnt__GeccErrCnt_MASK                                                                  0x0000FFFFL

-#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt_MASK                                                            0xFFFF0000L

-//MCA_UMC_UMC0_MCUMC_STATUST0

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode__SHIFT                                                         0x0

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt__SHIFT                                                      0x10

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22__SHIFT                                                          0x16

-#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb__SHIFT                                                           0x18

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30__SHIFT                                                          0x1e

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId__SHIFT                                                         0x20

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38__SHIFT                                                          0x26

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub__SHIFT                                                             0x28

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41__SHIFT                                                          0x29

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison__SHIFT                                                            0x2b

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred__SHIFT                                                          0x2c

-#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC__SHIFT                                                              0x2d

-#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC__SHIFT                                                              0x2e

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47__SHIFT                                                          0x2f

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent__SHIFT                                                       0x34

-#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV__SHIFT                                                             0x35

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54__SHIFT                                                          0x36

-#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC__SHIFT                                                               0x37

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal__SHIFT                                                      0x38

-#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC__SHIFT                                                               0x39

-#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV__SHIFT                                                             0x3a

-#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV__SHIFT                                                             0x3b

-#define MCA_UMC_UMC0_MCUMC_STATUST0__En__SHIFT                                                                0x3c

-#define MCA_UMC_UMC0_MCUMC_STATUST0__UC__SHIFT                                                                0x3d

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow__SHIFT                                                          0x3e

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Val__SHIFT                                                               0x3f

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode_MASK                                                           0x000000000000FFFFL

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt_MASK                                                        0x00000000003F0000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22_MASK                                                            0x0000000000C00000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb_MASK                                                             0x000000003F000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30_MASK                                                            0x00000000C0000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId_MASK                                                           0x0000003F00000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38_MASK                                                            0x000000C000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub_MASK                                                               0x0000010000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41_MASK                                                            0x0000060000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison_MASK                                                              0x0000080000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred_MASK                                                            0x0000100000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC_MASK                                                                0x0000200000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC_MASK                                                                0x0000400000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47_MASK                                                            0x000F800000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent_MASK                                                         0x0010000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV_MASK                                                               0x0020000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54_MASK                                                            0x0040000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC_MASK                                                                 0x0080000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal_MASK                                                        0x0100000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC_MASK                                                                 0x0200000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV_MASK                                                               0x0400000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV_MASK                                                               0x0800000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__En_MASK                                                                  0x1000000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__UC_MASK                                                                  0x2000000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow_MASK                                                            0x4000000000000000L

-#define MCA_UMC_UMC0_MCUMC_STATUST0__Val_MASK                                                                 0x8000000000000000L

-//MCA_UMC_UMC0_MCUMC_ADDRT0

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr__SHIFT                                                           0x0

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB__SHIFT                                                                 0x38

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved__SHIFT                                                            0x3e

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr_MASK                                                             0x00FFFFFFFFFFFFFFL

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB_MASK                                                                   0x3F00000000000000L

-#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved_MASK                                                              0xC000000000000000L

-

-#endif

+/*
+ * Copyright (C) 2020  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _umc_8_7_0_SH_MASK_HEADER
+#define _umc_8_7_0_SH_MASK_HEADER
+
+//UMCCH0_0_GeccErrCntSel
+#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel__SHIFT                                                        0x0
+#define UMCCH0_0_GeccErrCntSel__GeccErrInt__SHIFT                                                             0xc
+#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn__SHIFT                                                           0xf
+#define UMCCH0_0_GeccErrCntSel__PoisonCntEn__SHIFT                                                            0x10
+#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel_MASK                                                          0x0000000FL
+#define UMCCH0_0_GeccErrCntSel__GeccErrInt_MASK                                                               0x00003000L
+#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn_MASK                                                             0x00008000L
+#define UMCCH0_0_GeccErrCntSel__PoisonCntEn_MASK                                                              0x00030000L
+//UMCCH0_0_GeccErrCnt
+#define UMCCH0_0_GeccErrCnt__GeccErrCnt__SHIFT                                                                0x0
+#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt__SHIFT                                                          0x10
+#define UMCCH0_0_GeccErrCnt__GeccErrCnt_MASK                                                                  0x0000FFFFL
+#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt_MASK                                                            0xFFFF0000L
+//MCA_UMC_UMC0_MCUMC_STATUST0
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode__SHIFT                                                         0x0
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt__SHIFT                                                      0x10
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22__SHIFT                                                          0x16
+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb__SHIFT                                                           0x18
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30__SHIFT                                                          0x1e
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId__SHIFT                                                         0x20
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38__SHIFT                                                          0x26
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub__SHIFT                                                             0x28
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41__SHIFT                                                          0x29
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison__SHIFT                                                            0x2b
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred__SHIFT                                                          0x2c
+#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC__SHIFT                                                              0x2d
+#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC__SHIFT                                                              0x2e
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47__SHIFT                                                          0x2f
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent__SHIFT                                                       0x34
+#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV__SHIFT                                                             0x35
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54__SHIFT                                                          0x36
+#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC__SHIFT                                                               0x37
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal__SHIFT                                                      0x38
+#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC__SHIFT                                                               0x39
+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV__SHIFT                                                             0x3a
+#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV__SHIFT                                                             0x3b
+#define MCA_UMC_UMC0_MCUMC_STATUST0__En__SHIFT                                                                0x3c
+#define MCA_UMC_UMC0_MCUMC_STATUST0__UC__SHIFT                                                                0x3d
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow__SHIFT                                                          0x3e
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Val__SHIFT                                                               0x3f
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode_MASK                                                           0x000000000000FFFFL
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt_MASK                                                        0x00000000003F0000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22_MASK                                                            0x0000000000C00000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb_MASK                                                             0x000000003F000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30_MASK                                                            0x00000000C0000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId_MASK                                                           0x0000003F00000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38_MASK                                                            0x000000C000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub_MASK                                                               0x0000010000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41_MASK                                                            0x0000060000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison_MASK                                                              0x0000080000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred_MASK                                                            0x0000100000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC_MASK                                                                0x0000200000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC_MASK                                                                0x0000400000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47_MASK                                                            0x000F800000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent_MASK                                                         0x0010000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV_MASK                                                               0x0020000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54_MASK                                                            0x0040000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC_MASK                                                                 0x0080000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal_MASK                                                        0x0100000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC_MASK                                                                 0x0200000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV_MASK                                                               0x0400000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV_MASK                                                               0x0800000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__En_MASK                                                                  0x1000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__UC_MASK                                                                  0x2000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow_MASK                                                            0x4000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0__Val_MASK                                                                 0x8000000000000000L
+//MCA_UMC_UMC0_MCUMC_ADDRT0
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr__SHIFT                                                           0x0
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB__SHIFT                                                                 0x38
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved__SHIFT                                                            0x3e
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr_MASK                                                             0x00FFFFFFFFFFFFFFL
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB_MASK                                                                   0x3F00000000000000L
+#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved_MASK                                                              0xC000000000000000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/cyan_skillfish_ip_offset.h b/drivers/gpu/drm/amd/include/cyan_skillfish_ip_offset.h
new file mode 100644
index 000000000000..9cb5f3631c60
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/cyan_skillfish_ip_offset.h
@@ -0,0 +1,714 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _cyan_skillfish_ip_offset_HEADER
+#define _cyan_skillfish_ip_offset_HEADER
+
+#define MAX_INSTANCE                                       6
+#define MAX_SEGMENT                                        5
+
+
+struct IP_BASE_INSTANCE 
+{
+    unsigned int segment[MAX_SEGMENT];
+};
+ 
+struct IP_BASE 
+{
+    struct IP_BASE_INSTANCE instance[MAX_INSTANCE];
+};
+
+
+static const struct IP_BASE ATHUB_BASE            ={ { { { 0x00000C00, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE CLK_BASE            ={ { { { 0x00016C00, 0, 0, 0, 0 } },
+                                        { { 0x00016E00, 0, 0, 0, 0 } },
+                                        { { 0x00017000, 0, 0, 0, 0 } },
+                                        { { 0x00017200, 0, 0, 0, 0 } },
+                                        { { 0x00017E00, 0, 0, 0, 0 } },
+                                        { { 0x0001B000, 0, 0, 0, 0 } } } };
+static const struct IP_BASE DF_BASE            ={ { { { 0x00007000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE DMU_BASE            ={ { { { 0x00000012, 0x000000C0, 0x000034C0, 0x00009000, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE FUSE_BASE            ={ { { { 0x00017400, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE GC_BASE            ={ { { { 0x00001260, 0x0000A000, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE HDP_BASE            ={ { { { 0x00000F20, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MMHUB_BASE            ={ { { { 0x0001A000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MP0_BASE            ={ { { { 0x00016000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MP1_BASE            ={ { { { 0x00016000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE NBIO_BASE            ={ { { { 0x00000000, 0x00000014, 0x00000D20, 0x00010400, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE OSSSYS_BASE            ={ { { { 0x000010A0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE SMUIO_BASE            ={ { { { 0x00016800, 0x00016A00, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE THM_BASE            ={ { { { 0x00016600, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE UMC0_BASE            ={ { { { 0x00014000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE UVD0_BASE            ={ { { { 0x00007800, 0x00007E00, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } },
+					{ { 0, 0, 0, 0, 0 } } } };
+
+
+#define ATHUB_BASE__INST0_SEG0                     0x00000C00
+#define ATHUB_BASE__INST0_SEG1                     0
+#define ATHUB_BASE__INST0_SEG2                     0
+#define ATHUB_BASE__INST0_SEG3                     0
+#define ATHUB_BASE__INST0_SEG4                     0
+
+#define ATHUB_BASE__INST1_SEG0                     0
+#define ATHUB_BASE__INST1_SEG1                     0
+#define ATHUB_BASE__INST1_SEG2                     0
+#define ATHUB_BASE__INST1_SEG3                     0
+#define ATHUB_BASE__INST1_SEG4                     0
+
+#define ATHUB_BASE__INST2_SEG0                     0
+#define ATHUB_BASE__INST2_SEG1                     0
+#define ATHUB_BASE__INST2_SEG2                     0
+#define ATHUB_BASE__INST2_SEG3                     0
+#define ATHUB_BASE__INST2_SEG4                     0
+
+#define ATHUB_BASE__INST3_SEG0                     0
+#define ATHUB_BASE__INST3_SEG1                     0
+#define ATHUB_BASE__INST3_SEG2                     0
+#define ATHUB_BASE__INST3_SEG3                     0
+#define ATHUB_BASE__INST3_SEG4                     0
+
+#define ATHUB_BASE__INST4_SEG0                     0
+#define ATHUB_BASE__INST4_SEG1                     0
+#define ATHUB_BASE__INST4_SEG2                     0
+#define ATHUB_BASE__INST4_SEG3                     0
+#define ATHUB_BASE__INST4_SEG4                     0
+
+#define ATHUB_BASE__INST5_SEG0                     0
+#define ATHUB_BASE__INST5_SEG1                     0
+#define ATHUB_BASE__INST5_SEG2                     0
+#define ATHUB_BASE__INST5_SEG3                     0
+#define ATHUB_BASE__INST5_SEG4                     0
+
+#define CLK_BASE__INST0_SEG0                       0x00016C00
+#define CLK_BASE__INST0_SEG1                       0
+#define CLK_BASE__INST0_SEG2                       0
+#define CLK_BASE__INST0_SEG3                       0
+#define CLK_BASE__INST0_SEG4                       0
+
+#define CLK_BASE__INST1_SEG0                       0x00016E00
+#define CLK_BASE__INST1_SEG1                       0
+#define CLK_BASE__INST1_SEG2                       0
+#define CLK_BASE__INST1_SEG3                       0
+#define CLK_BASE__INST1_SEG4                       0
+
+#define CLK_BASE__INST2_SEG0                       0x00017000
+#define CLK_BASE__INST2_SEG1                       0
+#define CLK_BASE__INST2_SEG2                       0
+#define CLK_BASE__INST2_SEG3                       0
+#define CLK_BASE__INST2_SEG4                       0
+
+#define CLK_BASE__INST3_SEG0                       0x00017200
+#define CLK_BASE__INST3_SEG1                       0
+#define CLK_BASE__INST3_SEG2                       0
+#define CLK_BASE__INST3_SEG3                       0
+#define CLK_BASE__INST3_SEG4                       0
+
+#define CLK_BASE__INST4_SEG0                       0x00017E00
+#define CLK_BASE__INST4_SEG1                       0
+#define CLK_BASE__INST4_SEG2                       0
+#define CLK_BASE__INST4_SEG3                       0
+#define CLK_BASE__INST4_SEG4                       0
+
+#define CLK_BASE__INST5_SEG0                       0x0001B000
+#define CLK_BASE__INST5_SEG1                       0
+#define CLK_BASE__INST5_SEG2                       0
+#define CLK_BASE__INST5_SEG3                       0
+#define CLK_BASE__INST5_SEG4                       0
+
+#define DF_BASE__INST0_SEG0                        0x00007000
+#define DF_BASE__INST0_SEG1                        0
+#define DF_BASE__INST0_SEG2                        0
+#define DF_BASE__INST0_SEG3                        0
+#define DF_BASE__INST0_SEG4                        0
+
+#define DF_BASE__INST1_SEG0                        0
+#define DF_BASE__INST1_SEG1                        0
+#define DF_BASE__INST1_SEG2                        0
+#define DF_BASE__INST1_SEG3                        0
+#define DF_BASE__INST1_SEG4                        0
+
+#define DF_BASE__INST2_SEG0                        0
+#define DF_BASE__INST2_SEG1                        0
+#define DF_BASE__INST2_SEG2                        0
+#define DF_BASE__INST2_SEG3                        0
+#define DF_BASE__INST2_SEG4                        0
+
+#define DF_BASE__INST3_SEG0                        0
+#define DF_BASE__INST3_SEG1                        0
+#define DF_BASE__INST3_SEG2                        0
+#define DF_BASE__INST3_SEG3                        0
+#define DF_BASE__INST3_SEG4                        0
+
+#define DF_BASE__INST4_SEG0                        0
+#define DF_BASE__INST4_SEG1                        0
+#define DF_BASE__INST4_SEG2                        0
+#define DF_BASE__INST4_SEG3                        0
+#define DF_BASE__INST4_SEG4                        0
+
+#define DF_BASE__INST5_SEG0                        0
+#define DF_BASE__INST5_SEG1                        0
+#define DF_BASE__INST5_SEG2                        0
+#define DF_BASE__INST5_SEG3                        0
+#define DF_BASE__INST5_SEG4                        0
+
+#define DMU_BASE__INST0_SEG0                       0x00000012
+#define DMU_BASE__INST0_SEG1                       0x000000C0
+#define DMU_BASE__INST0_SEG2                       0x000034C0
+#define DMU_BASE__INST0_SEG3                       0x00009000
+#define DMU_BASE__INST0_SEG4                       0
+
+#define DMU_BASE__INST1_SEG0                       0
+#define DMU_BASE__INST1_SEG1                       0
+#define DMU_BASE__INST1_SEG2                       0
+#define DMU_BASE__INST1_SEG3                       0
+#define DMU_BASE__INST1_SEG4                       0
+
+#define DMU_BASE__INST2_SEG0                       0
+#define DMU_BASE__INST2_SEG1                       0
+#define DMU_BASE__INST2_SEG2                       0
+#define DMU_BASE__INST2_SEG3                       0
+#define DMU_BASE__INST2_SEG4                       0
+
+#define DMU_BASE__INST3_SEG0                       0
+#define DMU_BASE__INST3_SEG1                       0
+#define DMU_BASE__INST3_SEG2                       0
+#define DMU_BASE__INST3_SEG3                       0
+#define DMU_BASE__INST3_SEG4                       0
+
+#define DMU_BASE__INST4_SEG0                       0
+#define DMU_BASE__INST4_SEG1                       0
+#define DMU_BASE__INST4_SEG2                       0
+#define DMU_BASE__INST4_SEG3                       0
+#define DMU_BASE__INST4_SEG4                       0
+
+#define DMU_BASE__INST5_SEG0                       0
+#define DMU_BASE__INST5_SEG1                       0
+#define DMU_BASE__INST5_SEG2                       0
+#define DMU_BASE__INST5_SEG3                       0
+#define DMU_BASE__INST5_SEG4                       0
+
+#define FUSE_BASE__INST0_SEG0                      0x00017400
+#define FUSE_BASE__INST0_SEG1                      0
+#define FUSE_BASE__INST0_SEG2                      0
+#define FUSE_BASE__INST0_SEG3                      0
+#define FUSE_BASE__INST0_SEG4                      0
+
+#define FUSE_BASE__INST1_SEG0                      0
+#define FUSE_BASE__INST1_SEG1                      0
+#define FUSE_BASE__INST1_SEG2                      0
+#define FUSE_BASE__INST1_SEG3                      0
+#define FUSE_BASE__INST1_SEG4                      0
+
+#define FUSE_BASE__INST2_SEG0                      0
+#define FUSE_BASE__INST2_SEG1                      0
+#define FUSE_BASE__INST2_SEG2                      0
+#define FUSE_BASE__INST2_SEG3                      0
+#define FUSE_BASE__INST2_SEG4                      0
+
+#define FUSE_BASE__INST3_SEG0                      0
+#define FUSE_BASE__INST3_SEG1                      0
+#define FUSE_BASE__INST3_SEG2                      0
+#define FUSE_BASE__INST3_SEG3                      0
+#define FUSE_BASE__INST3_SEG4                      0
+
+#define FUSE_BASE__INST4_SEG0                      0
+#define FUSE_BASE__INST4_SEG1                      0
+#define FUSE_BASE__INST4_SEG2                      0
+#define FUSE_BASE__INST4_SEG3                      0
+#define FUSE_BASE__INST4_SEG4                      0
+
+#define FUSE_BASE__INST5_SEG0                      0
+#define FUSE_BASE__INST5_SEG1                      0
+#define FUSE_BASE__INST5_SEG2                      0
+#define FUSE_BASE__INST5_SEG3                      0
+#define FUSE_BASE__INST5_SEG4                      0
+
+#define GC_BASE__INST0_SEG0                        0x00001260
+#define GC_BASE__INST0_SEG1                        0x0000A000
+#define GC_BASE__INST0_SEG2                        0
+#define GC_BASE__INST0_SEG3                        0
+#define GC_BASE__INST0_SEG4                        0
+
+#define GC_BASE__INST1_SEG0                        0
+#define GC_BASE__INST1_SEG1                        0
+#define GC_BASE__INST1_SEG2                        0
+#define GC_BASE__INST1_SEG3                        0
+#define GC_BASE__INST1_SEG4                        0
+
+#define GC_BASE__INST2_SEG0                        0
+#define GC_BASE__INST2_SEG1                        0
+#define GC_BASE__INST2_SEG2                        0
+#define GC_BASE__INST2_SEG3                        0
+#define GC_BASE__INST2_SEG4                        0
+
+#define GC_BASE__INST3_SEG0                        0
+#define GC_BASE__INST3_SEG1                        0
+#define GC_BASE__INST3_SEG2                        0
+#define GC_BASE__INST3_SEG3                        0
+#define GC_BASE__INST3_SEG4                        0
+
+#define GC_BASE__INST4_SEG0                        0
+#define GC_BASE__INST4_SEG1                        0
+#define GC_BASE__INST4_SEG2                        0
+#define GC_BASE__INST4_SEG3                        0
+#define GC_BASE__INST4_SEG4                        0
+
+#define GC_BASE__INST5_SEG0                        0
+#define GC_BASE__INST5_SEG1                        0
+#define GC_BASE__INST5_SEG2                        0
+#define GC_BASE__INST5_SEG3                        0
+#define GC_BASE__INST5_SEG4                        0
+
+#define HDP_BASE__INST0_SEG0                       0x00000F20
+#define HDP_BASE__INST0_SEG1                       0
+#define HDP_BASE__INST0_SEG2                       0
+#define HDP_BASE__INST0_SEG3                       0
+#define HDP_BASE__INST0_SEG4                       0
+
+#define HDP_BASE__INST1_SEG0                       0
+#define HDP_BASE__INST1_SEG1                       0
+#define HDP_BASE__INST1_SEG2                       0
+#define HDP_BASE__INST1_SEG3                       0
+#define HDP_BASE__INST1_SEG4                       0
+
+#define HDP_BASE__INST2_SEG0                       0
+#define HDP_BASE__INST2_SEG1                       0
+#define HDP_BASE__INST2_SEG2                       0
+#define HDP_BASE__INST2_SEG3                       0
+#define HDP_BASE__INST2_SEG4                       0
+
+#define HDP_BASE__INST3_SEG0                       0
+#define HDP_BASE__INST3_SEG1                       0
+#define HDP_BASE__INST3_SEG2                       0
+#define HDP_BASE__INST3_SEG3                       0
+#define HDP_BASE__INST3_SEG4                       0
+
+#define HDP_BASE__INST4_SEG0                       0
+#define HDP_BASE__INST4_SEG1                       0
+#define HDP_BASE__INST4_SEG2                       0
+#define HDP_BASE__INST4_SEG3                       0
+#define HDP_BASE__INST4_SEG4                       0
+
+#define HDP_BASE__INST5_SEG0                       0
+#define HDP_BASE__INST5_SEG1                       0
+#define HDP_BASE__INST5_SEG2                       0
+#define HDP_BASE__INST5_SEG3                       0
+#define HDP_BASE__INST5_SEG4                       0
+
+#define MMHUB_BASE__INST0_SEG0                     0x0001A000
+#define MMHUB_BASE__INST0_SEG1                     0
+#define MMHUB_BASE__INST0_SEG2                     0
+#define MMHUB_BASE__INST0_SEG3                     0
+#define MMHUB_BASE__INST0_SEG4                     0
+
+#define MMHUB_BASE__INST1_SEG0                     0
+#define MMHUB_BASE__INST1_SEG1                     0
+#define MMHUB_BASE__INST1_SEG2                     0
+#define MMHUB_BASE__INST1_SEG3                     0
+#define MMHUB_BASE__INST1_SEG4                     0
+
+#define MMHUB_BASE__INST2_SEG0                     0
+#define MMHUB_BASE__INST2_SEG1                     0
+#define MMHUB_BASE__INST2_SEG2                     0
+#define MMHUB_BASE__INST2_SEG3                     0
+#define MMHUB_BASE__INST2_SEG4                     0
+
+#define MMHUB_BASE__INST3_SEG0                     0
+#define MMHUB_BASE__INST3_SEG1                     0
+#define MMHUB_BASE__INST3_SEG2                     0
+#define MMHUB_BASE__INST3_SEG3                     0
+#define MMHUB_BASE__INST3_SEG4                     0
+
+#define MMHUB_BASE__INST4_SEG0                     0
+#define MMHUB_BASE__INST4_SEG1                     0
+#define MMHUB_BASE__INST4_SEG2                     0
+#define MMHUB_BASE__INST4_SEG3                     0
+#define MMHUB_BASE__INST4_SEG4                     0
+
+#define MMHUB_BASE__INST5_SEG0                     0
+#define MMHUB_BASE__INST5_SEG1                     0
+#define MMHUB_BASE__INST5_SEG2                     0
+#define MMHUB_BASE__INST5_SEG3                     0
+#define MMHUB_BASE__INST5_SEG4                     0
+
+#define MP0_BASE__INST0_SEG0                       0x00016000
+#define MP0_BASE__INST0_SEG1                       0
+#define MP0_BASE__INST0_SEG2                       0
+#define MP0_BASE__INST0_SEG3                       0
+#define MP0_BASE__INST0_SEG4                       0
+
+#define MP0_BASE__INST1_SEG0                       0
+#define MP0_BASE__INST1_SEG1                       0
+#define MP0_BASE__INST1_SEG2                       0
+#define MP0_BASE__INST1_SEG3                       0
+#define MP0_BASE__INST1_SEG4                       0
+
+#define MP0_BASE__INST2_SEG0                       0
+#define MP0_BASE__INST2_SEG1                       0
+#define MP0_BASE__INST2_SEG2                       0
+#define MP0_BASE__INST2_SEG3                       0
+#define MP0_BASE__INST2_SEG4                       0
+
+#define MP0_BASE__INST3_SEG0                       0
+#define MP0_BASE__INST3_SEG1                       0
+#define MP0_BASE__INST3_SEG2                       0
+#define MP0_BASE__INST3_SEG3                       0
+#define MP0_BASE__INST3_SEG4                       0
+
+#define MP0_BASE__INST4_SEG0                       0
+#define MP0_BASE__INST4_SEG1                       0
+#define MP0_BASE__INST4_SEG2                       0
+#define MP0_BASE__INST4_SEG3                       0
+#define MP0_BASE__INST4_SEG4                       0
+
+#define MP0_BASE__INST5_SEG0                       0
+#define MP0_BASE__INST5_SEG1                       0
+#define MP0_BASE__INST5_SEG2                       0
+#define MP0_BASE__INST5_SEG3                       0
+#define MP0_BASE__INST5_SEG4                       0
+
+#define MP1_BASE__INST0_SEG0                       0x00016000
+#define MP1_BASE__INST0_SEG1                       0
+#define MP1_BASE__INST0_SEG2                       0
+#define MP1_BASE__INST0_SEG3                       0
+#define MP1_BASE__INST0_SEG4                       0
+
+#define MP1_BASE__INST1_SEG0                       0
+#define MP1_BASE__INST1_SEG1                       0
+#define MP1_BASE__INST1_SEG2                       0
+#define MP1_BASE__INST1_SEG3                       0
+#define MP1_BASE__INST1_SEG4                       0
+
+#define MP1_BASE__INST2_SEG0                       0
+#define MP1_BASE__INST2_SEG1                       0
+#define MP1_BASE__INST2_SEG2                       0
+#define MP1_BASE__INST2_SEG3                       0
+#define MP1_BASE__INST2_SEG4                       0
+
+#define MP1_BASE__INST3_SEG0                       0
+#define MP1_BASE__INST3_SEG1                       0
+#define MP1_BASE__INST3_SEG2                       0
+#define MP1_BASE__INST3_SEG3                       0
+#define MP1_BASE__INST3_SEG4                       0
+
+#define MP1_BASE__INST4_SEG0                       0
+#define MP1_BASE__INST4_SEG1                       0
+#define MP1_BASE__INST4_SEG2                       0
+#define MP1_BASE__INST4_SEG3                       0
+#define MP1_BASE__INST4_SEG4                       0
+
+#define MP1_BASE__INST5_SEG0                       0
+#define MP1_BASE__INST5_SEG1                       0
+#define MP1_BASE__INST5_SEG2                       0
+#define MP1_BASE__INST5_SEG3                       0
+#define MP1_BASE__INST5_SEG4                       0
+
+#define NBIO_BASE__INST0_SEG0                     0x00000000
+#define NBIO_BASE__INST0_SEG1                     0x00000014
+#define NBIO_BASE__INST0_SEG2                     0x00000D20
+#define NBIO_BASE__INST0_SEG3                     0x00010400
+#define NBIO_BASE__INST0_SEG4                     0
+
+#define NBIO_BASE__INST1_SEG0                     0
+#define NBIO_BASE__INST1_SEG1                     0
+#define NBIO_BASE__INST1_SEG2                     0
+#define NBIO_BASE__INST1_SEG3                     0
+#define NBIO_BASE__INST1_SEG4                     0
+
+#define NBIO_BASE__INST2_SEG0                     0
+#define NBIO_BASE__INST2_SEG1                     0
+#define NBIO_BASE__INST2_SEG2                     0
+#define NBIO_BASE__INST2_SEG3                     0
+#define NBIO_BASE__INST2_SEG4                     0
+
+#define NBIO_BASE__INST3_SEG0                     0
+#define NBIO_BASE__INST3_SEG1                     0
+#define NBIO_BASE__INST3_SEG2                     0
+#define NBIO_BASE__INST3_SEG3                     0
+#define NBIO_BASE__INST3_SEG4                     0
+
+#define NBIO_BASE__INST4_SEG0                     0
+#define NBIO_BASE__INST4_SEG1                     0
+#define NBIO_BASE__INST4_SEG2                     0
+#define NBIO_BASE__INST4_SEG3                     0
+#define NBIO_BASE__INST4_SEG4                     0
+
+#define NBIO_BASE__INST5_SEG0                     0
+#define NBIO_BASE__INST5_SEG1                     0
+#define NBIO_BASE__INST5_SEG2                     0
+#define NBIO_BASE__INST5_SEG3                     0
+#define NBIO_BASE__INST5_SEG4                     0
+
+#define OSSSYS_BASE__INST0_SEG0                    0x000010A0
+#define OSSSYS_BASE__INST0_SEG1                    0
+#define OSSSYS_BASE__INST0_SEG2                    0
+#define OSSSYS_BASE__INST0_SEG3                    0
+#define OSSSYS_BASE__INST0_SEG4                    0
+
+#define OSSSYS_BASE__INST1_SEG0                    0
+#define OSSSYS_BASE__INST1_SEG1                    0
+#define OSSSYS_BASE__INST1_SEG2                    0
+#define OSSSYS_BASE__INST1_SEG3                    0
+#define OSSSYS_BASE__INST1_SEG4                    0
+
+#define OSSSYS_BASE__INST2_SEG0                    0
+#define OSSSYS_BASE__INST2_SEG1                    0
+#define OSSSYS_BASE__INST2_SEG2                    0
+#define OSSSYS_BASE__INST2_SEG3                    0
+#define OSSSYS_BASE__INST2_SEG4                    0
+
+#define OSSSYS_BASE__INST3_SEG0                    0
+#define OSSSYS_BASE__INST3_SEG1                    0
+#define OSSSYS_BASE__INST3_SEG2                    0
+#define OSSSYS_BASE__INST3_SEG3                    0
+#define OSSSYS_BASE__INST3_SEG4                    0
+
+#define OSSSYS_BASE__INST4_SEG0                    0
+#define OSSSYS_BASE__INST4_SEG1                    0
+#define OSSSYS_BASE__INST4_SEG2                    0
+#define OSSSYS_BASE__INST4_SEG3                    0
+#define OSSSYS_BASE__INST4_SEG4                    0
+
+#define OSSSYS_BASE__INST5_SEG0                    0
+#define OSSSYS_BASE__INST5_SEG1                    0
+#define OSSSYS_BASE__INST5_SEG2                    0
+#define OSSSYS_BASE__INST5_SEG3                    0
+#define OSSSYS_BASE__INST5_SEG4                    0
+
+#define SMUIO_BASE__INST0_SEG0                     0x00016800
+#define SMUIO_BASE__INST0_SEG1                     0x00016A00
+#define SMUIO_BASE__INST0_SEG2                     0
+#define SMUIO_BASE__INST0_SEG3                     0
+#define SMUIO_BASE__INST0_SEG4                     0
+
+#define SMUIO_BASE__INST1_SEG0                     0
+#define SMUIO_BASE__INST1_SEG1                     0
+#define SMUIO_BASE__INST1_SEG2                     0
+#define SMUIO_BASE__INST1_SEG3                     0
+#define SMUIO_BASE__INST1_SEG4                     0
+
+#define SMUIO_BASE__INST2_SEG0                     0
+#define SMUIO_BASE__INST2_SEG1                     0
+#define SMUIO_BASE__INST2_SEG2                     0
+#define SMUIO_BASE__INST2_SEG3                     0
+#define SMUIO_BASE__INST2_SEG4                     0
+
+#define SMUIO_BASE__INST3_SEG0                     0
+#define SMUIO_BASE__INST3_SEG1                     0
+#define SMUIO_BASE__INST3_SEG2                     0
+#define SMUIO_BASE__INST3_SEG3                     0
+#define SMUIO_BASE__INST3_SEG4                     0
+
+#define SMUIO_BASE__INST4_SEG0                     0
+#define SMUIO_BASE__INST4_SEG1                     0
+#define SMUIO_BASE__INST4_SEG2                     0
+#define SMUIO_BASE__INST4_SEG3                     0
+#define SMUIO_BASE__INST4_SEG4                     0
+
+#define SMUIO_BASE__INST5_SEG0                     0
+#define SMUIO_BASE__INST5_SEG1                     0
+#define SMUIO_BASE__INST5_SEG2                     0
+#define SMUIO_BASE__INST5_SEG3                     0
+#define SMUIO_BASE__INST5_SEG4                     0
+
+#define THM_BASE__INST0_SEG0                       0x00016600
+#define THM_BASE__INST0_SEG1                       0
+#define THM_BASE__INST0_SEG2                       0
+#define THM_BASE__INST0_SEG3                       0
+#define THM_BASE__INST0_SEG4                       0
+
+#define THM_BASE__INST1_SEG0                       0
+#define THM_BASE__INST1_SEG1                       0
+#define THM_BASE__INST1_SEG2                       0
+#define THM_BASE__INST1_SEG3                       0
+#define THM_BASE__INST1_SEG4                       0
+
+#define THM_BASE__INST2_SEG0                       0
+#define THM_BASE__INST2_SEG1                       0
+#define THM_BASE__INST2_SEG2                       0
+#define THM_BASE__INST2_SEG3                       0
+#define THM_BASE__INST2_SEG4                       0
+
+#define THM_BASE__INST3_SEG0                       0
+#define THM_BASE__INST3_SEG1                       0
+#define THM_BASE__INST3_SEG2                       0
+#define THM_BASE__INST3_SEG3                       0
+#define THM_BASE__INST3_SEG4                       0
+
+#define THM_BASE__INST4_SEG0                       0
+#define THM_BASE__INST4_SEG1                       0
+#define THM_BASE__INST4_SEG2                       0
+#define THM_BASE__INST4_SEG3                       0
+#define THM_BASE__INST4_SEG4                       0
+
+#define THM_BASE__INST5_SEG0                       0
+#define THM_BASE__INST5_SEG1                       0
+#define THM_BASE__INST5_SEG2                       0
+#define THM_BASE__INST5_SEG3                       0
+#define THM_BASE__INST5_SEG4                       0
+
+#define UMC0_BASE__INST0_SEG0                      0x00014000
+#define UMC0_BASE__INST0_SEG1                      0
+#define UMC0_BASE__INST0_SEG2                      0
+#define UMC0_BASE__INST0_SEG3                      0
+#define UMC0_BASE__INST0_SEG4                      0
+
+#define UMC0_BASE__INST1_SEG0                      0
+#define UMC0_BASE__INST1_SEG1                      0
+#define UMC0_BASE__INST1_SEG2                      0
+#define UMC0_BASE__INST1_SEG3                      0
+#define UMC0_BASE__INST1_SEG4                      0
+
+#define UMC0_BASE__INST2_SEG0                      0
+#define UMC0_BASE__INST2_SEG1                      0
+#define UMC0_BASE__INST2_SEG2                      0
+#define UMC0_BASE__INST2_SEG3                      0
+#define UMC0_BASE__INST2_SEG4                      0
+
+#define UMC0_BASE__INST3_SEG0                      0
+#define UMC0_BASE__INST3_SEG1                      0
+#define UMC0_BASE__INST3_SEG2                      0
+#define UMC0_BASE__INST3_SEG3                      0
+#define UMC0_BASE__INST3_SEG4                      0
+
+#define UMC0_BASE__INST4_SEG0                      0
+#define UMC0_BASE__INST4_SEG1                      0
+#define UMC0_BASE__INST4_SEG2                      0
+#define UMC0_BASE__INST4_SEG3                      0
+#define UMC0_BASE__INST4_SEG4                      0
+
+#define UMC0_BASE__INST5_SEG0                      0
+#define UMC0_BASE__INST5_SEG1                      0
+#define UMC0_BASE__INST5_SEG2                      0
+#define UMC0_BASE__INST5_SEG3                      0
+#define UMC0_BASE__INST5_SEG4                      0
+
+#define UVD0_BASE__INST0_SEG0                      0x00007800
+#define UVD0_BASE__INST0_SEG1                      0x00007E00
+#define UVD0_BASE__INST0_SEG2                      0
+#define UVD0_BASE__INST0_SEG3                      0
+#define UVD0_BASE__INST0_SEG4                      0
+
+#define UVD0_BASE__INST1_SEG0                      0
+#define UVD0_BASE__INST1_SEG1                      0
+#define UVD0_BASE__INST1_SEG2                      0
+#define UVD0_BASE__INST1_SEG3                      0
+#define UVD0_BASE__INST1_SEG4                      0
+
+#define UVD0_BASE__INST2_SEG0                      0
+#define UVD0_BASE__INST2_SEG1                      0
+#define UVD0_BASE__INST2_SEG2                      0
+#define UVD0_BASE__INST2_SEG3                      0
+#define UVD0_BASE__INST2_SEG4                      0
+
+#define UVD0_BASE__INST3_SEG0                      0
+#define UVD0_BASE__INST3_SEG1                      0
+#define UVD0_BASE__INST3_SEG2                      0
+#define UVD0_BASE__INST3_SEG3                      0
+#define UVD0_BASE__INST3_SEG4                      0
+
+#define UVD0_BASE__INST4_SEG0                      0
+#define UVD0_BASE__INST4_SEG1                      0
+#define UVD0_BASE__INST4_SEG2                      0
+#define UVD0_BASE__INST4_SEG3                      0
+#define UVD0_BASE__INST4_SEG4                      0
+
+#define UVD0_BASE__INST5_SEG0                      0
+#define UVD0_BASE__INST5_SEG1                      0
+#define UVD0_BASE__INST5_SEG2                      0
+#define UVD0_BASE__INST5_SEG3                      0
+#define UVD0_BASE__INST5_SEG4                      0
+
+#endif
+
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 95c656d205ed..c84bd7b2cf59 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -44,6 +44,7 @@ struct kgd_mem;
 enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN = 0,
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
+	KFD_PREEMPT_TYPE_WAVEFRONT_SAVE
 };
 
 struct kfd_vm_fault_info {
@@ -298,6 +299,8 @@ struct kfd2kgd_calls {
 
 	void (*get_cu_occupancy)(struct kgd_dev *kgd, int pasid, int *wave_cnt,
 			int *max_waves_per_cu);
+	void (*program_trap_handler_settings)(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr);
 };
 
 #endif	/* KGD_KFD_INTERFACE_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index e38b191c7b7c..bac15c466733 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -306,8 +306,8 @@ struct amd_pm_funcs {
 /* export for sysfs */
 	void (*set_fan_control_mode)(void *handle, u32 mode);
 	u32 (*get_fan_control_mode)(void *handle);
-	int (*set_fan_speed_percent)(void *handle, u32 speed);
-	int (*get_fan_speed_percent)(void *handle, u32 *speed);
+	int (*set_fan_speed_pwm)(void *handle, u32 speed);
+	int (*get_fan_speed_pwm)(void *handle, u32 *speed);
 	int (*force_clock_level)(void *handle, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(void *handle, enum pp_clock_type type, char *buf);
 	int (*force_performance_level)(void *handle, enum amd_dpm_forced_level level);
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 769f58d5ae1a..2d55627b05b1 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2094,14 +2094,19 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 			*states = ATTR_STATE_UNSUPPORTED;
 	}
 
-	if (asic_type == CHIP_ARCTURUS) {
-		/* Arcturus does not support standalone mclk/socclk/fclk level setting */
+	switch (asic_type) {
+	case CHIP_ARCTURUS:
+	case CHIP_ALDEBARAN:
+		/* the Mi series card does not support standalone mclk/socclk/fclk level setting */
 		if (DEVICE_ATTR_IS(pp_dpm_mclk) ||
 		    DEVICE_ATTR_IS(pp_dpm_socclk) ||
 		    DEVICE_ATTR_IS(pp_dpm_fclk)) {
 			dev_attr->attr.mode &= ~S_IWUGO;
 			dev_attr->store = NULL;
 		}
+		break;
+	default:
+		break;
 	}
 
 	if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) {
@@ -2379,7 +2384,7 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev,
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
-	return sprintf(buf, "%u\n", pwm_mode);
+	return sysfs_emit(buf, "%u\n", pwm_mode);
 }
 
 static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
@@ -2424,14 +2429,14 @@ static ssize_t amdgpu_hwmon_get_pwm1_min(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	return sprintf(buf, "%i\n", 0);
+	return sysfs_emit(buf, "%i\n", 0);
 }
 
 static ssize_t amdgpu_hwmon_get_pwm1_max(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	return sprintf(buf, "%i\n", 255);
+	return sysfs_emit(buf, "%i\n", 255);
 }
 
 static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
@@ -2469,10 +2474,8 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 		return err;
 	}
 
-	value = (value * 100) / 255;
-
-	if (adev->powerplay.pp_funcs->set_fan_speed_percent)
-		err = amdgpu_dpm_set_fan_speed_percent(adev, value);
+	if (adev->powerplay.pp_funcs->set_fan_speed_pwm)
+		err = amdgpu_dpm_set_fan_speed_pwm(adev, value);
 	else
 		err = -EINVAL;
 
@@ -2504,8 +2507,8 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 		return err;
 	}
 
-	if (adev->powerplay.pp_funcs->get_fan_speed_percent)
-		err = amdgpu_dpm_get_fan_speed_percent(adev, &speed);
+	if (adev->powerplay.pp_funcs->get_fan_speed_pwm)
+		err = amdgpu_dpm_get_fan_speed_pwm(adev, &speed);
 	else
 		err = -EINVAL;
 
@@ -2515,9 +2518,7 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 	if (err)
 		return err;
 
-	speed = (speed * 255) / 100;
-
-	return sprintf(buf, "%i\n", speed);
+	return sysfs_emit(buf, "%i\n", speed);
 }
 
 static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
@@ -2550,7 +2551,7 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	if (err)
 		return err;
 
-	return sprintf(buf, "%i\n", speed);
+	return sysfs_emit(buf, "%i\n", speed);
 }
 
 static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev,
@@ -2647,7 +2648,7 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
 	if (err)
 		return err;
 
-	return sprintf(buf, "%i\n", rpm);
+	return sysfs_emit(buf, "%i\n", rpm);
 }
 
 static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
@@ -2729,7 +2730,7 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
-	return sprintf(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
+	return sysfs_emit(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
 }
 
 static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
@@ -2899,7 +2900,7 @@ static ssize_t amdgpu_hwmon_show_power_cap_min(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	return sprintf(buf, "%i\n", 0);
+	return sysfs_emit(buf, "%i\n", 0);
 }
 
 
@@ -3174,6 +3175,9 @@ static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
  *
  * - fan[1-\*]_enable: Enable or disable the sensors.1: Enable 0: Disable
  *
+ * NOTE: DO NOT set the fan speed via "pwm1" and "fan[1-\*]_target" interfaces at the same time.
+ *       That will get the former one overridden.
+ *
  * hwmon interfaces for GPU clocks:
  *
  * - freq1_input: the gfx/compute clock in hertz
@@ -3349,13 +3353,13 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 
 	if (!is_support_sw_smu(adev)) {
 		/* mask fan attributes if we have no bindings for this asic to expose */
-		if ((!adev->powerplay.pp_funcs->get_fan_speed_percent &&
+		if ((!adev->powerplay.pp_funcs->get_fan_speed_pwm &&
 		     attr == &sensor_dev_attr_pwm1.dev_attr.attr) || /* can't query fan */
 		    (!adev->powerplay.pp_funcs->get_fan_control_mode &&
 		     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr)) /* can't query state */
 			effective_mode &= ~S_IRUGO;
 
-		if ((!adev->powerplay.pp_funcs->set_fan_speed_percent &&
+		if ((!adev->powerplay.pp_funcs->set_fan_speed_pwm &&
 		     attr == &sensor_dev_attr_pwm1.dev_attr.attr) || /* can't manage fan */
 		    (!adev->powerplay.pp_funcs->set_fan_control_mode &&
 		     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr)) /* can't manage state */
@@ -3379,8 +3383,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 
 	if (!is_support_sw_smu(adev)) {
 		/* hide max/min values if we can't both query and manage the fan */
-		if ((!adev->powerplay.pp_funcs->set_fan_speed_percent &&
-		     !adev->powerplay.pp_funcs->get_fan_speed_percent) &&
+		if ((!adev->powerplay.pp_funcs->set_fan_speed_pwm &&
+		     !adev->powerplay.pp_funcs->get_fan_speed_pwm) &&
 		     (!adev->powerplay.pp_funcs->set_fan_speed_rpm &&
 		     !adev->powerplay.pp_funcs->get_fan_speed_rpm) &&
 		    (attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index f6e0e7d8a007..98f1b3d8c1d5 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -280,11 +280,11 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_get_fan_control_mode(adev) \
 		((adev)->powerplay.pp_funcs->get_fan_control_mode((adev)->powerplay.pp_handle))
 
-#define amdgpu_dpm_set_fan_speed_percent(adev, s) \
-		((adev)->powerplay.pp_funcs->set_fan_speed_percent((adev)->powerplay.pp_handle, (s)))
+#define amdgpu_dpm_set_fan_speed_pwm(adev, s) \
+		((adev)->powerplay.pp_funcs->set_fan_speed_pwm((adev)->powerplay.pp_handle, (s)))
 
-#define amdgpu_dpm_get_fan_speed_percent(adev, s) \
-		((adev)->powerplay.pp_funcs->get_fan_speed_percent((adev)->powerplay.pp_handle, (s)))
+#define amdgpu_dpm_get_fan_speed_pwm(adev, s) \
+		((adev)->powerplay.pp_funcs->get_fan_speed_pwm((adev)->powerplay.pp_handle, (s)))
 
 #define amdgpu_dpm_get_fan_speed_rpm(adev, s) \
 		((adev)->powerplay.pp_funcs->get_fan_speed_rpm)((adev)->powerplay.pp_handle, (s))
@@ -450,6 +450,7 @@ struct amdgpu_pm {
 
 	/* Used for I2C access to various EEPROMs on relevant ASICs */
 	struct i2c_adapter smu_i2c;
+	struct mutex		smu_i2c_mutex;
 	struct list_head	pm_attr_list;
 };
 
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 3e89852e4820..715b4225f5ee 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -34,6 +34,8 @@
 #define SMU_FW_NAME_LEN			0x24
 
 #define SMU_DPM_USER_PROFILE_RESTORE (1 << 0)
+#define SMU_CUSTOM_FAN_SPEED_RPM     (1 << 1)
+#define SMU_CUSTOM_FAN_SPEED_PWM     (1 << 2)
 
 // Power Throttlers
 #define SMU_THROTTLER_PPT0_BIT			0
@@ -229,8 +231,10 @@ enum smu_memory_pool_size
 struct smu_user_dpm_profile {
 	uint32_t fan_mode;
 	uint32_t power_limit;
-	uint32_t fan_speed_percent;
+	uint32_t fan_speed_pwm;
+	uint32_t fan_speed_rpm;
 	uint32_t flags;
+	uint32_t user_od;
 
 	/* user clock state information */
 	uint32_t clk_mask[SMU_CLK_COUNT];
@@ -352,6 +356,7 @@ struct smu_table_context
 
 	void				*overdrive_table;
 	void                            *boot_overdrive_table;
+	void				*user_overdrive_table;
 
 	uint32_t			gpu_metrics_table_size;
 	void				*gpu_metrics_table;
@@ -538,7 +543,7 @@ struct smu_context
 	struct work_struct interrupt_work;
 
 	unsigned fan_max_rpm;
-	unsigned manual_fan_speed_percent;
+	unsigned manual_fan_speed_pwm;
 
 	uint32_t gfx_default_hard_min_freq;
 	uint32_t gfx_default_soft_max_freq;
@@ -624,6 +629,12 @@ struct pptable_funcs {
 				 long *input, uint32_t size);
 
 	/**
+	 * @restore_user_od_settings: Restore the user customized
+	 *                            OD settings on S3/S4/Runpm resume.
+	 */
+	int (*restore_user_od_settings)(struct smu_context *smu);
+
+	/**
 	 * @get_clock_by_type_with_latency: Get the speed and latency of a clock
 	 *                                  domain.
 	 */
@@ -714,9 +725,14 @@ struct pptable_funcs {
 	bool (*is_dpm_running)(struct smu_context *smu);
 
 	/**
-	 * @get_fan_speed_percent: Get the current fan speed in percent.
+	 * @get_fan_speed_pwm: Get the current fan speed in PWM.
 	 */
-	int (*get_fan_speed_percent)(struct smu_context *smu, uint32_t *speed);
+	int (*get_fan_speed_pwm)(struct smu_context *smu, uint32_t *speed);
+
+	/**
+	 * @get_fan_speed_rpm: Get the current fan speed in rpm.
+	 */
+	int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed);
 
 	/**
 	 * @set_watermarks_table: Configure and upload the watermarks tables to
@@ -1035,9 +1051,14 @@ struct pptable_funcs {
 	int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
 
 	/**
-	 * @set_fan_speed_percent: Set a static fan speed in percent.
+	 * @set_fan_speed_pwm: Set a static fan speed in PWM.
+	 */
+	int (*set_fan_speed_pwm)(struct smu_context *smu, uint32_t speed);
+
+	/**
+	 * @set_fan_speed_rpm: Set a static fan speed in rpm.
 	 */
-	int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed);
+	int (*set_fan_speed_rpm)(struct smu_context *smu, uint32_t speed);
 
 	/**
 	 * @set_xgmi_pstate: Set inter-chip global memory interconnect pstate.
diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
index 490371bd2520..8ed01071fe5a 100644
--- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -278,9 +278,9 @@ struct pp_hwmgr_func {
 	int (*get_fan_speed_info)(struct pp_hwmgr *hwmgr, struct phm_fan_speed_info *fan_speed_info);
 	void (*set_fan_control_mode)(struct pp_hwmgr *hwmgr, uint32_t mode);
 	uint32_t (*get_fan_control_mode)(struct pp_hwmgr *hwmgr);
-	int (*set_fan_speed_percent)(struct pp_hwmgr *hwmgr, uint32_t percent);
-	int (*get_fan_speed_percent)(struct pp_hwmgr *hwmgr, uint32_t *speed);
-	int (*set_fan_speed_rpm)(struct pp_hwmgr *hwmgr, uint32_t percent);
+	int (*set_fan_speed_pwm)(struct pp_hwmgr *hwmgr, uint32_t speed);
+	int (*get_fan_speed_pwm)(struct pp_hwmgr *hwmgr, uint32_t *speed);
+	int (*set_fan_speed_rpm)(struct pp_hwmgr *hwmgr, uint32_t speed);
 	int (*get_fan_speed_rpm)(struct pp_hwmgr *hwmgr, uint32_t *speed);
 	int (*reset_fan_speed_to_default)(struct pp_hwmgr *hwmgr);
 	int (*uninitialize_thermal_controller)(struct pp_hwmgr *hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
new file mode 100644
index 000000000000..8a08ecc34c69
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __SMU11_DRIVER_IF_CYAN_SKILLFISH_H__
+#define __SMU11_DRIVER_IF_CYAN_SKILLFISH_H__
+
+// *** IMPORTANT ***
+// Always increment the interface version if
+// any structure is changed in this file
+#define MP1_DRIVER_IF_VERSION 0x8
+
+#define TABLE_BIOS_IF            0 // Called by BIOS
+#define TABLE_WATERMARKS         1 // Called by Driver; defined here, but not used, for backward compatible
+#define TABLE_PMSTATUSLOG        3 // Called by Tools for Agm logging
+#define TABLE_DPMCLOCKS          4 // Called by Driver; defined here, but not used, for backward compatible
+#define TABLE_MOMENTARY_PM       5 // Called by Tools; defined here, but not used, for backward compatible
+#define TABLE_COUNT              6
+
+#define NUM_DSPCLK_LEVELS		8
+#define NUM_SOCCLK_DPM_LEVELS	8
+#define NUM_DCEFCLK_DPM_LEVELS	4
+#define NUM_FCLK_DPM_LEVELS		4
+#define NUM_MEMCLK_DPM_LEVELS	4
+
+#define NUMBER_OF_PSTATES		8
+#define NUMBER_OF_CORES			8
+
+typedef enum {
+	S3_TYPE_ENTRY,
+	S5_TYPE_ENTRY,
+} Sleep_Type_e;
+
+typedef enum {
+	GFX_OFF = 0,
+	GFX_ON  = 1,
+} GFX_Mode_e;
+
+typedef enum {
+	CPU_P0 = 0,
+	CPU_P1,
+	CPU_P2,
+	CPU_P3,
+	CPU_P4,
+	CPU_P5,
+	CPU_P6,
+	CPU_P7
+} CPU_PState_e;
+
+typedef enum {
+	CPU_CORE0 = 0,
+	CPU_CORE1,
+	CPU_CORE2,
+	CPU_CORE3,
+	CPU_CORE4,
+	CPU_CORE5,
+	CPU_CORE6,
+	CPU_CORE7
+} CORE_ID_e;
+
+typedef enum {
+	DF_DPM0 = 0,
+	DF_DPM1,
+	DF_DPM2,
+	DF_DPM3,
+	DF_PState_Count
+} DF_PState_e;
+
+typedef enum {
+	GFX_DPM0 = 0,
+	GFX_DPM1,
+	GFX_DPM2,
+	GFX_DPM3,
+	GFX_PState_Count
+} GFX_PState_e;
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
index 61c87c39be80..63b8701fd466 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
@@ -131,7 +131,7 @@
 #define FEATURE_GFX_EDC_BIT             49
 #define FEATURE_GFX_PER_PART_VMIN_BIT   50
 #define FEATURE_SMART_SHIFT_BIT         51
-#define FEATURE_SPARE_52_BIT            52
+#define FEATURE_APT_BIT                 52
 #define FEATURE_SPARE_53_BIT            53
 #define FEATURE_SPARE_54_BIT            54
 #define FEATURE_SPARE_55_BIT            55
@@ -211,6 +211,7 @@ typedef enum {
 #define THROTTLER_FIT_BIT          17
 #define THROTTLER_PPM_BIT          18
 #define THROTTLER_APCC_BIT         19
+#define THROTTLER_COUNT            20
 
 // FW DState Features Control Bits
 // FW DState Features Control Bits
@@ -1406,7 +1407,67 @@ typedef struct {
 } SmuMetrics_t;
 
 typedef struct {
-  SmuMetrics_t SmuMetrics;
+  uint32_t CurrClock[PPCLK_COUNT];
+
+  uint16_t AverageGfxclkFrequencyPreDs;
+  uint16_t AverageGfxclkFrequencyPostDs;
+  uint16_t AverageFclkFrequencyPreDs;
+  uint16_t AverageFclkFrequencyPostDs;
+  uint16_t AverageUclkFrequencyPreDs  ;
+  uint16_t AverageUclkFrequencyPostDs  ;
+
+
+  uint16_t AverageGfxActivity    ;
+  uint16_t AverageUclkActivity   ;
+  uint8_t  CurrSocVoltageOffset  ;
+  uint8_t  CurrGfxVoltageOffset  ;
+  uint8_t  CurrMemVidOffset      ;
+  uint8_t  Padding8        ;
+  uint16_t AverageSocketPower    ;
+  uint16_t TemperatureEdge       ;
+  uint16_t TemperatureHotspot    ;
+  uint16_t TemperatureMem        ;
+  uint16_t TemperatureVrGfx      ;
+  uint16_t TemperatureVrMem0     ;
+  uint16_t TemperatureVrMem1     ;
+  uint16_t TemperatureVrSoc      ;
+  uint16_t TemperatureLiquid0    ;
+  uint16_t TemperatureLiquid1    ;
+  uint16_t TemperaturePlx        ;
+  uint16_t Padding16             ;
+  uint32_t AccCnt                ;
+  uint8_t  ThrottlingPercentage[THROTTLER_COUNT];
+
+
+  uint8_t  LinkDpmLevel;
+  uint8_t  CurrFanPwm;
+  uint16_t CurrFanSpeed;
+
+  //BACO metrics, PMFW-1721
+  //metrics for D3hot entry/exit and driver ARM msgs
+  uint8_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT];
+  uint8_t D3HotExitCountPerMode[D3HOT_SEQUENCE_COUNT];
+  uint8_t ArmMsgReceivedCountPerMode[D3HOT_SEQUENCE_COUNT];
+
+  //PMFW-4362
+  uint32_t EnergyAccumulator;
+  uint16_t AverageVclk0Frequency  ;
+  uint16_t AverageDclk0Frequency  ;
+  uint16_t AverageVclk1Frequency  ;
+  uint16_t AverageDclk1Frequency  ;
+  uint16_t VcnActivityPercentage  ; //place holder, David N. to provide full sequence
+  uint8_t  PcieRate               ;
+  uint8_t  PcieWidth              ;
+  uint16_t AverageGfxclkFrequencyTarget;
+  uint16_t Padding16_2;
+
+} SmuMetrics_V2_t;
+
+typedef struct {
+  union {
+    SmuMetrics_t SmuMetrics;
+    SmuMetrics_V2_t SmuMetrics_V2;
+  };
   uint32_t Spare[1];
 
   // Padding - ignore
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 1d3765b873df..6f1b1b50d527 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -282,6 +282,7 @@ enum smu_clk_type {
        __SMU_DUMMY_MAP(TDC),                           	\
        __SMU_DUMMY_MAP(THERMAL),                       	\
        __SMU_DUMMY_MAP(GFX_PER_CU_CG),                 	\
+       __SMU_DUMMY_MAP(DATA_CALCULATIONS),                 	\
        __SMU_DUMMY_MAP(RM),                            	\
        __SMU_DUMMY_MAP(DS_DCEFCLK),                    	\
        __SMU_DUMMY_MAP(ACDC),                          	\
@@ -297,7 +298,6 @@ enum smu_clk_type {
        __SMU_DUMMY_MAP(DS_FCLK),                       	\
        __SMU_DUMMY_MAP(DS_MP1CLK),                     	\
        __SMU_DUMMY_MAP(DS_MP0CLK),                     	\
-       __SMU_DUMMY_MAP(XGMI),                          	\
        __SMU_DUMMY_MAP(XGMI_PER_LINK_PWR_DWN),          \
        __SMU_DUMMY_MAP(DPM_GFX_PACE),                  	\
        __SMU_DUMMY_MAP(MEM_VDDCI_SCALING),             	\
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index f61b5c914a3d..cbdae8a2c698 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -30,11 +30,12 @@
 #define SMU11_DRIVER_IF_VERSION_NV10 0x37
 #define SMU11_DRIVER_IF_VERSION_NV12 0x38
 #define SMU11_DRIVER_IF_VERSION_NV14 0x38
-#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x3D
+#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x40
 #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE
 #define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03
 #define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF
 #define SMU11_DRIVER_IF_VERSION_Beige_Goby 0xD
+#define SMU11_DRIVER_IF_VERSION_Cyan_Skillfish 0x8
 
 /* MP Apertures */
 #define MP0_Public			0x03800000
@@ -220,9 +221,18 @@ int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode);
 
-int smu_v11_0_set_fan_speed_percent(struct smu_context *smu,
+int smu_v11_0_set_fan_speed_pwm(struct smu_context *smu,
 				    uint32_t speed);
 
+int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
+				uint32_t speed);
+
+int smu_v11_0_get_fan_speed_pwm(struct smu_context *smu,
+				    uint32_t *speed);
+
+int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu,
+				uint32_t *speed);
+
 int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
 				     uint32_t pstate);
 
@@ -302,5 +312,7 @@ void smu_v11_0_interrupt_work(struct smu_context *smu);
 
 int smu_v11_0_set_light_sbr(struct smu_context *smu, bool enable);
 
+int smu_v11_0_restore_user_od_settings(struct smu_context *smu);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_pmfw.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_pmfw.h
new file mode 100644
index 000000000000..bd4fcb6b9610
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_pmfw.h
@@ -0,0 +1,152 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __SMU_V11_8_0_PMFW_H__
+#define __SMU_V11_8_0_PMFW_H__
+
+#pragma pack(push, 1)
+
+#define ENABLE_DEBUG_FEATURES
+
+// Feature Control Defines
+#define FEATURE_CCLK_CONTROLLER_BIT       0
+#define FEATURE_GFXCLK_EFFT_FREQ_BIT      1
+#define FEATURE_DATA_CALCULATION_BIT      2
+#define FEATURE_THERMAL_BIT               3
+#define FEATURE_PLL_POWER_DOWN_BIT        4
+#define FEATURE_FCLK_DPM_BIT              5
+#define FEATURE_GFX_DPM_BIT               6
+#define FEATURE_DS_GFXCLK_BIT             7
+#define FEATURE_DS_SOCCLK_BIT             8
+#define FEATURE_DS_LCLK_BIT               9
+#define FEATURE_CORE_CSTATES_BIT          10
+#define FEATURE_G6_SSC_BIT                11 //G6 memory UCLK and UCLK_DIV SS
+#define FEATURE_RM_BIT                    12
+#define FEATURE_SOC_DPM_BIT               13
+#define FEATURE_DS_SMNCLK_BIT             14
+#define FEATURE_DS_MP1CLK_BIT             15
+#define FEATURE_DS_MP0CLK_BIT             16
+#define FEATURE_MGCG_BIT                  17
+#define FEATURE_DS_FUSE_SRAM_BIT          18
+#define FEATURE_GFX_CKS_BIT               19
+#define FEATURE_FP_THROTTLING_BIT         20
+#define FEATURE_PROCHOT_BIT               21
+#define FEATURE_CPUOFF_BIT                22
+#define FEATURE_UMC_THROTTLE_BIT          23
+#define FEATURE_DF_THROTTLE_BIT           24
+#define FEATURE_DS_MP3CLK_BIT             25
+#define FEATURE_DS_SHUBCLK_BIT            26
+#define FEATURE_TDC_BIT                   27 //Legacy APM_BIT
+#define FEATURE_UMC_CAL_SHARING_BIT       28
+#define FEATURE_DFLL_BTC_CALIBRATION_BIT  29
+#define FEATURE_EDC_BIT                   30
+#define FEATURE_DLDO_BIT                  31
+#define FEATURE_MEAS_DRAM_BLACKOUT_BIT    32
+#define FEATURE_CC1_BIT                   33
+#define FEATURE_PPT_BIT                   34
+#define FEATURE_STAPM_BIT                 35
+#define FEATURE_CSTATE_BOOST_BIT          36
+#define FEATURE_SPARE_37_BIT              37
+#define FEATURE_SPARE_38_BIT              38
+#define FEATURE_SPARE_39_BIT              39
+#define FEATURE_SPARE_40_BIT              40
+#define FEATURE_SPARE_41_BIT              41
+#define FEATURE_SPARE_42_BIT              42
+#define FEATURE_SPARE_43_BIT              43
+#define FEATURE_SPARE_44_BIT              44
+#define FEATURE_SPARE_45_BIT              45
+#define FEATURE_SPARE_46_BIT              46
+#define FEATURE_SPARE_47_BIT              47
+#define FEATURE_SPARE_48_BIT              48
+#define FEATURE_SPARE_49_BIT              49
+#define FEATURE_SPARE_50_BIT              50
+#define FEATURE_SPARE_51_BIT              51
+#define FEATURE_SPARE_52_BIT              52
+#define FEATURE_SPARE_53_BIT              53
+#define FEATURE_SPARE_54_BIT              54
+#define FEATURE_SPARE_55_BIT              55
+#define FEATURE_SPARE_56_BIT              56
+#define FEATURE_SPARE_57_BIT              57
+#define FEATURE_SPARE_58_BIT              58
+#define FEATURE_SPARE_59_BIT              59
+#define FEATURE_SPARE_60_BIT              60
+#define FEATURE_SPARE_61_BIT              61
+#define FEATURE_SPARE_62_BIT              62
+#define FEATURE_SPARE_63_BIT              63
+
+#define NUM_FEATURES                      64
+
+#define FEATURE_CCLK_CONTROLLER_MASK  (1 << FEATURE_CCLK_CONTROLLER_BIT)
+#define FEATURE_DATA_CALCULATION_MASK (1 << FEATURE_DATA_CALCULATION_BIT)
+#define FEATURE_THERMAL_MASK          (1 << FEATURE_THERMAL_BIT)
+#define FEATURE_PLL_POWER_DOWN_MASK   (1 << FEATURE_PLL_POWER_DOWN_BIT)
+#define FEATURE_FCLK_DPM_MASK         (1 << FEATURE_FCLK_DPM_BIT)
+#define FEATURE_GFX_DPM_MASK          (1 << FEATURE_GFX_DPM_BIT)
+#define FEATURE_DS_GFXCLK_MASK        (1 << FEATURE_DS_GFXCLK_BIT)
+#define FEATURE_DS_SOCCLK_MASK        (1 << FEATURE_DS_SOCCLK_BIT)
+#define FEATURE_DS_LCLK_MASK          (1 << FEATURE_DS_LCLK_BIT)
+#define FEATURE_RM_MASK               (1 << FEATURE_RM_BIT)
+#define FEATURE_DS_SMNCLK_MASK        (1 << FEATURE_DS_SMNCLK_BIT)
+#define FEATURE_DS_MP1CLK_MASK        (1 << FEATURE_DS_MP1CLK_BIT)
+#define FEATURE_DS_MP0CLK_MASK        (1 << FEATURE_DS_MP0CLK_BIT)
+#define FEATURE_MGCG_MASK             (1 << FEATURE_MGCG_BIT)
+#define FEATURE_DS_FUSE_SRAM_MASK     (1 << FEATURE_DS_FUSE_SRAM_BIT)
+#define FEATURE_PROCHOT_MASK          (1 << FEATURE_PROCHOT_BIT)
+#define FEATURE_CPUOFF_MASK           (1 << FEATURE_CPUOFF_BIT)
+#define FEATURE_GFX_CKS_MASK          (1 << FEATURE_GFX_CKS_BIT)
+#define FEATURE_UMC_THROTTLE_MASK     (1 << FEATURE_UMC_THROTTLE_BIT)
+#define FEATURE_DF_THROTTLE_MASK      (1 << FEATURE_DF_THROTTLE_BIT)
+#define FEATURE_SOC_DPM_MASK          (1 << FEATURE_SOC_DPM_BIT)
+
+typedef struct {
+	// MP1_EXT_SCRATCH0
+	uint32_t SPARE1            : 4;
+	uint32_t SPARE2            : 4;
+	uint32_t SPARE3            : 4;
+	uint32_t CurrLevel_LCLK    : 4;
+	uint32_t CurrLevel_MP0CLK  : 4;
+	uint32_t CurrLevel_FCLK    : 4;
+	uint32_t CurrLevel_SOCCLK  : 4;
+	uint32_t CurrLevel_DCEFCLK : 4;
+	// MP1_EXT_SCRATCH1
+	uint32_t SPARE4            : 4;
+	uint32_t SPARE5            : 4;
+	uint32_t SPARE6            : 4;
+	uint32_t TargLevel_LCLK    : 4;
+	uint32_t TargLevel_MP0CLK  : 4;
+	uint32_t TargLevel_FCLK    : 4;
+	uint32_t TargLevel_SOCCLK  : 4;
+	uint32_t TargLevel_DCEFCLK : 4;
+	// MP1_EXT_SCRATCH2
+	uint32_t CurrLevel_SHUBCLK  : 4;
+	uint32_t TargLevel_SHUBCLK  : 4;
+	uint32_t Reserved          : 24;
+	// MP1_EXT_SCRATCH3-4
+	uint32_t Reserved2[2];
+	// MP1_EXT_SCRATCH5
+	uint32_t FeatureStatus[NUM_FEATURES / 32];
+} FwStatus_t;
+
+#pragma pack(pop)
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
new file mode 100644
index 000000000000..6e6088760b18
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef SMU_11_8_0_PPSMC_H
+#define SMU_11_8_0_PPSMC_H
+
+// SMU Response Codes:
+#define PPSMC_Result_OK                    0x1
+#define PPSMC_Result_Failed                0xFF
+#define PPSMC_Result_UnknownCmd            0xFE
+#define PPSMC_Result_CmdRejectedPrereq     0xFD
+#define PPSMC_Result_CmdRejectedBusy       0xFC
+
+// Message Definitions:
+#define PPSMC_MSG_TestMessage                           0x1
+#define PPSMC_MSG_GetSmuVersion                         0x2
+#define PPSMC_MSG_GetDriverIfVersion                    0x3
+#define PPSMC_MSG_SetDriverTableDramAddrHigh            0x4
+#define PPSMC_MSG_SetDriverTableDramAddrLow             0x5
+#define PPSMC_MSG_TransferTableSmu2Dram                 0x6
+#define PPSMC_MSG_TransferTableDram2Smu                 0x7
+#define PPSMC_MSG_Rsvd1                                 0xA
+#define PPSMC_MSG_RequestCorePstate                     0xB
+#define PPSMC_MSG_QueryCorePstate                       0xC
+#define PPSMC_MSG_Rsvd2                                 0xD
+#define PPSMC_MSG_RequestGfxclk                         0xE
+#define PPSMC_MSG_QueryGfxclk                           0xF
+#define PPSMC_MSG_QueryVddcrSocClock                    0x11
+#define PPSMC_MSG_QueryDfPstate                         0x13
+#define PPSMC_MSG_Rsvd3                                 0x14
+#define PPSMC_MSG_ConfigureS3PwrOffRegisterAddressHigh  0x16
+#define PPSMC_MSG_ConfigureS3PwrOffRegisterAddressLow   0x17
+#define PPSMC_MSG_RequestActiveWgp                      0x18
+#define PPSMC_MSG_SetMinDeepSleepGfxclkFreq             0x19
+#define PPSMC_MSG_SetMaxDeepSleepDfllGfxDiv             0x1A
+#define PPSMC_MSG_StartTelemetryReporting               0x1B
+#define PPSMC_MSG_StopTelemetryReporting                0x1C
+#define PPSMC_MSG_ClearTelemetryMax                     0x1D
+#define PPSMC_MSG_QueryActiveWgp                        0x1E
+#define PPSMC_MSG_SetCoreEnableMask                     0x2C
+#define PPSMC_MSG_InitiateGcRsmuSoftReset               0x2E
+#define PPSMC_MSG_GfxCacWeightOperation                 0x2F
+#define PPSMC_MSG_L3CacWeightOperation                  0x30
+#define PPSMC_MSG_PackCoreCacWeight                     0x31
+#define PPSMC_MSG_SetDriverTableVMID                    0x34
+#define PPSMC_MSG_SetSoftMinCclk                        0x35
+#define PPSMC_MSG_SetSoftMaxCclk                        0x36
+#define PPSMC_Message_Count                             0x37
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index d2a38246a78a..321215003643 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -533,7 +533,7 @@ static uint32_t pp_dpm_get_fan_control_mode(void *handle)
 	return mode;
 }
 
-static int pp_dpm_set_fan_speed_percent(void *handle, uint32_t percent)
+static int pp_dpm_set_fan_speed_pwm(void *handle, uint32_t speed)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
@@ -541,17 +541,17 @@ static int pp_dpm_set_fan_speed_percent(void *handle, uint32_t percent)
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->set_fan_speed_percent == NULL) {
+	if (hwmgr->hwmgr_func->set_fan_speed_pwm == NULL) {
 		pr_info_ratelimited("%s was not implemented.\n", __func__);
 		return 0;
 	}
 	mutex_lock(&hwmgr->smu_lock);
-	ret = hwmgr->hwmgr_func->set_fan_speed_percent(hwmgr, percent);
+	ret = hwmgr->hwmgr_func->set_fan_speed_pwm(hwmgr, speed);
 	mutex_unlock(&hwmgr->smu_lock);
 	return ret;
 }
 
-static int pp_dpm_get_fan_speed_percent(void *handle, uint32_t *speed)
+static int pp_dpm_get_fan_speed_pwm(void *handle, uint32_t *speed)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
@@ -559,13 +559,13 @@ static int pp_dpm_get_fan_speed_percent(void *handle, uint32_t *speed)
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->get_fan_speed_percent == NULL) {
+	if (hwmgr->hwmgr_func->get_fan_speed_pwm == NULL) {
 		pr_info_ratelimited("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
 	mutex_lock(&hwmgr->smu_lock);
-	ret = hwmgr->hwmgr_func->get_fan_speed_percent(hwmgr, speed);
+	ret = hwmgr->hwmgr_func->get_fan_speed_pwm(hwmgr, speed);
 	mutex_unlock(&hwmgr->smu_lock);
 	return ret;
 }
@@ -1691,8 +1691,8 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.dispatch_tasks = pp_dpm_dispatch_tasks,
 	.set_fan_control_mode = pp_dpm_set_fan_control_mode,
 	.get_fan_control_mode = pp_dpm_get_fan_control_mode,
-	.set_fan_speed_percent = pp_dpm_set_fan_speed_percent,
-	.get_fan_speed_percent = pp_dpm_get_fan_speed_percent,
+	.set_fan_speed_pwm = pp_dpm_set_fan_speed_pwm,
+	.get_fan_speed_pwm = pp_dpm_get_fan_speed_pwm,
 	.get_fan_speed_rpm = pp_dpm_get_fan_speed_rpm,
 	.set_fan_speed_rpm = pp_dpm_set_fan_speed_rpm,
 	.get_pp_num_states = pp_dpm_get_pp_num_states,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 43c3f6e755e7..1de3ae77e03e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1036,13 +1036,13 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		else
 			i = 1;
 
-		size += sprintf(buf + size, "0: %uMhz %s\n",
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n",
 					data->gfx_min_freq_limit/100,
 					i == 0 ? "*" : "");
-		size += sprintf(buf + size, "1: %uMhz %s\n",
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
 					i == 1 ? now : SMU10_UMD_PSTATE_GFXCLK,
 					i == 1 ? "*" : "");
-		size += sprintf(buf + size, "2: %uMhz %s\n",
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n",
 					data->gfx_max_freq_limit/100,
 					i == 2 ? "*" : "");
 		break;
@@ -1050,7 +1050,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now);
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i,
 					mclk_table->entries[i].clk / 100,
 					((mclk_table->entries[i].clk / 100)
@@ -1065,10 +1065,10 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 			(data->gfx_actual_soft_max_freq > 0) ? data->gfx_actual_soft_max_freq : max_freq);
 		}
 		break;
@@ -1081,8 +1081,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size = sprintf(buf, "%s:\n", "OD_RANGE");
-			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				min_freq, max_freq);
 		}
 		break;
@@ -1456,11 +1456,11 @@ static int smu10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%s %16s %s %s %s %s\n",title[0],
+	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);
 
 	for (i = 0; i <= PP_SMC_POWER_PROFILE_COMPUTE; i++)
-		size += sprintf(buf + size, "%3d %14s%s: %14d %3d %10d %14d\n",
+		size += sysfs_emit_at(buf, size, "%3d %14s%s: %14d %3d %10d %14d\n",
 			i, profile_name[i], (i == hwmgr->power_profile_mode) ? "*" : " ",
 			profile_mode_setting[i][0], profile_mode_setting[i][1],
 			profile_mode_setting[i][2], profile_mode_setting[i][3]);
@@ -1580,7 +1580,7 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
 		}
 
 		if (smu10_data->gfx_actual_soft_min_freq > smu10_data->gfx_actual_soft_max_freq) {
-			pr_err("The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+			pr_err("The setting minimum sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
 					smu10_data->gfx_actual_soft_min_freq, smu10_data->gfx_actual_soft_max_freq);
 			return -EINVAL;
 		}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 0541bfc81c1b..465ff8d2a01a 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3212,7 +3212,7 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr,
 
 	if (!ret) {
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			smu7_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
+			smu7_fan_ctrl_set_fan_speed_pwm(hwmgr, 255);
 		else if (level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu7_fan_ctrl_reset_fan_speed_to_default(hwmgr);
 	}
@@ -4896,8 +4896,8 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct smu7_odn_dpm_table *odn_table = &(data->odn_dpm_table);
 	struct phm_odn_clock_levels *odn_sclk_table = &(odn_table->odn_core_clock_dpm_levels);
 	struct phm_odn_clock_levels *odn_mclk_table = &(odn_table->odn_memory_clock_dpm_levels);
-	int i, now, size = 0;
-	uint32_t clock, pcie_speed;
+	int size = 0;
+	uint32_t i, now, clock, pcie_speed;
 
 	switch (type) {
 	case PP_SCLK:
@@ -4911,7 +4911,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < sclk_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4926,7 +4926,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, mclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4940,7 +4940,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < pcie_table->count; i++)
-			size += sprintf(buf + size, "%d: %s %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %s %s\n", i,
 					(pcie_table->dpm_levels[i].value == 0) ? "2.5GT/s, x8" :
 					(pcie_table->dpm_levels[i].value == 1) ? "5.0GT/s, x16" :
 					(pcie_table->dpm_levels[i].value == 2) ? "8.0GT/s, x16" : "",
@@ -4948,32 +4948,32 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
 			for (i = 0; i < odn_sclk_table->num_of_pl; i++)
-				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
+				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_sclk_table->entries[i].clock/100,
 					odn_sclk_table->entries[i].vddc);
 		}
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_MCLK");
+			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
 			for (i = 0; i < odn_mclk_table->num_of_pl; i++)
-				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
+				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_mclk_table->entries[i].clock/100,
 					odn_mclk_table->entries[i].vddc);
 		}
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_RANGE");
-			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
-			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
+			size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.mclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
-			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
+			size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n",
 				data->odn_dpm_table.min_vddc,
 				data->odn_dpm_table.max_vddc);
 		}
@@ -4988,7 +4988,7 @@ static void smu7_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		smu7_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
+		smu7_fan_ctrl_set_fan_speed_pwm(hwmgr, 255);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
@@ -5503,7 +5503,7 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%s %16s %16s %16s %16s %16s %16s %16s\n",
+	size += sysfs_emit_at(buf, size, "%s %16s %16s %16s %16s %16s %16s %16s\n",
 			title[0], title[1], title[2], title[3],
 			title[4], title[5], title[6], title[7]);
 
@@ -5511,7 +5511,7 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 
 	for (i = 0; i < len; i++) {
 		if (i == hwmgr->power_profile_mode) {
-			size += sprintf(buf + size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n",
+			size += sysfs_emit_at(buf, size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n",
 			i, profile_name[i], "*",
 			data->current_profile_setting.sclk_up_hyst,
 			data->current_profile_setting.sclk_down_hyst,
@@ -5522,21 +5522,21 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			continue;
 		}
 		if (smu7_profiling[i].bupdate_sclk)
-			size += sprintf(buf + size, "%3d %16s: %8d %16d %16d ",
+			size += sysfs_emit_at(buf, size, "%3d %16s: %8d %16d %16d ",
 			i, profile_name[i], smu7_profiling[i].sclk_up_hyst,
 			smu7_profiling[i].sclk_down_hyst,
 			smu7_profiling[i].sclk_activity);
 		else
-			size += sprintf(buf + size, "%3d %16s: %8s %16s %16s ",
+			size += sysfs_emit_at(buf, size, "%3d %16s: %8s %16s %16s ",
 			i, profile_name[i], "-", "-", "-");
 
 		if (smu7_profiling[i].bupdate_mclk)
-			size += sprintf(buf + size, "%16d %16d %16d\n",
+			size += sysfs_emit_at(buf, size, "%16d %16d %16d\n",
 			smu7_profiling[i].mclk_up_hyst,
 			smu7_profiling[i].mclk_down_hyst,
 			smu7_profiling[i].mclk_activity);
 		else
-			size += sprintf(buf + size, "%16s %16s %16s\n",
+			size += sysfs_emit_at(buf, size, "%16s %16s %16s\n",
 			"-", "-", "-");
 	}
 
@@ -5692,8 +5692,8 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
 	.set_max_fan_rpm_output = smu7_set_max_fan_rpm_output,
 	.stop_thermal_controller = smu7_thermal_stop_thermal_controller,
 	.get_fan_speed_info = smu7_fan_ctrl_get_fan_speed_info,
-	.get_fan_speed_percent = smu7_fan_ctrl_get_fan_speed_percent,
-	.set_fan_speed_percent = smu7_fan_ctrl_set_fan_speed_percent,
+	.get_fan_speed_pwm = smu7_fan_ctrl_get_fan_speed_pwm,
+	.set_fan_speed_pwm = smu7_fan_ctrl_set_fan_speed_pwm,
 	.reset_fan_speed_to_default = smu7_fan_ctrl_reset_fan_speed_to_default,
 	.get_fan_speed_rpm = smu7_fan_ctrl_get_fan_speed_rpm,
 	.set_fan_speed_rpm = smu7_fan_ctrl_set_fan_speed_rpm,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
index 6cfe148ed45b..a6c3610db23e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
@@ -51,7 +51,7 @@ int smu7_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-int smu7_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int smu7_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed)
 {
 	uint32_t duty100;
@@ -70,12 +70,9 @@ int smu7_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 
-	tmp64 = (uint64_t)duty * 100;
+	tmp64 = (uint64_t)duty * 255;
 	do_div(tmp64, duty100);
-	*speed = (uint32_t)tmp64;
-
-	if (*speed > 100)
-		*speed = 100;
+	*speed = MIN((uint32_t)tmp64, 255);
 
 	return 0;
 }
@@ -199,12 +196,11 @@ int smu7_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr)
 }
 
 /**
- * smu7_fan_ctrl_set_fan_speed_percent - Set Fan Speed in percent.
+ * smu7_fan_ctrl_set_fan_speed_pwm - Set Fan Speed in PWM.
  * @hwmgr: the address of the powerplay hardware manager.
- * @speed: is the percentage value (0% - 100%) to be set.
- * Exception: Fails is the 100% setting appears to be 0.
+ * @speed: is the pwm value (0 - 255) to be set.
  */
-int smu7_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int smu7_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t speed)
 {
 	uint32_t duty100;
@@ -214,8 +210,7 @@ int smu7_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 	if (hwmgr->thermal_controller.fanInfo.bNoFan)
 		return 0;
 
-	if (speed > 100)
-		speed = 100;
+	speed = MIN(speed, 255);
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		smu7_fan_ctrl_stop_smc_fan_control(hwmgr);
@@ -227,7 +222,7 @@ int smu7_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	tmp64 = (uint64_t)speed * duty100;
-	do_div(tmp64, 100);
+	do_div(tmp64, 255);
 	duty = (uint32_t)tmp64;
 
 	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h
index 42c1ba0fad78..a386a437e1f0 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h
@@ -41,10 +41,10 @@
 extern int smu7_thermal_get_temperature(struct pp_hwmgr *hwmgr);
 extern int smu7_thermal_stop_thermal_controller(struct pp_hwmgr *hwmgr);
 extern int smu7_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr, struct phm_fan_speed_info *fan_speed_info);
-extern int smu7_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr, uint32_t *speed);
+extern int smu7_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t *speed);
 extern int smu7_fan_ctrl_set_default_mode(struct pp_hwmgr *hwmgr);
 extern int smu7_fan_ctrl_set_static_mode(struct pp_hwmgr *hwmgr, uint32_t mode);
-extern int smu7_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr, uint32_t speed);
+extern int smu7_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t speed);
 extern int smu7_fan_ctrl_reset_fan_speed_to_default(struct pp_hwmgr *hwmgr);
 extern int smu7_thermal_ctrl_uninitialize_thermal_controller(struct pp_hwmgr *hwmgr);
 extern int smu7_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
index d425b02b1418..b94a77e4e714 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
@@ -1547,7 +1547,8 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct smu8_hwmgr *data = hwmgr->backend;
 	struct phm_clock_voltage_dependency_table *sclk_table =
 			hwmgr->dyn_state.vddc_dependency_on_sclk;
-	int i, now, size = 0;
+	uint32_t i, now;
+	int size = 0;
 
 	switch (type) {
 	case PP_SCLK:
@@ -1558,7 +1559,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 				CURR_SCLK_INDEX);
 
 		for (i = 0; i < sclk_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, sclk_table->entries[i].clk / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -1570,7 +1571,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 				CURR_MCLK_INDEX);
 
 		for (i = SMU8_NUM_NBPMEMORYCLOCK; i > 0; i--)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					SMU8_NUM_NBPMEMORYCLOCK-i, data->sys_info.nbp_memory_clock[i-1] / 100,
 					(SMU8_NUM_NBPMEMORYCLOCK-i == now) ? "*" : "");
 		break;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 02e8c6e5448d..c152a61ddd2c 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -4199,7 +4199,7 @@ static void vega10_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		vega10_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
+		vega10_fan_ctrl_set_fan_speed_pwm(hwmgr, 255);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
@@ -4553,13 +4553,13 @@ static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
 			return ret);
 
-	size += sprintf(buf + size, "Current ppfeatures: 0x%016llx\n", features_enabled);
-	size += sprintf(buf + size, "%-19s %-22s %s\n",
+	size += sysfs_emit_at(buf, size, "Current ppfeatures: 0x%016llx\n", features_enabled);
+	size += sysfs_emit_at(buf, size, "%-19s %-22s %s\n",
 				output_title[0],
 				output_title[1],
 				output_title[2]);
 	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
-		size += sprintf(buf + size, "%-19s 0x%016llx %6s\n",
+		size += sysfs_emit_at(buf, size, "%-19s 0x%016llx %6s\n",
 					ppfeature_name[i],
 					1ULL << i,
 					(features_enabled & (1ULL << i)) ? "Y" : "N");
@@ -4650,7 +4650,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		else
 			count = sclk_table->count;
 		for (i = 0; i < count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4661,7 +4661,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now);
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, mclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4672,7 +4672,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now);
 
 		for (i = 0; i < soc_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, soc_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4684,7 +4684,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 				PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now);
 
 		for (i = 0; i < dcef_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, dcef_table->dpm_levels[i].value / 100,
 					(dcef_table->dpm_levels[i].value / 100 == now) ?
 					"*" : "");
@@ -4698,7 +4698,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			gen_speed = pptable->PcieGenSpeed[i];
 			lane_width = pptable->PcieLaneCount[i];
 
-			size += sprintf(buf + size, "%d: %s %s %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %s %s %s\n", i,
 					(gen_speed == 0) ? "2.5GT/s," :
 					(gen_speed == 1) ? "5.0GT/s," :
 					(gen_speed == 2) ? "8.0GT/s," :
@@ -4717,34 +4717,34 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
-				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
+				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
 					i, podn_vdd_dep->entries[i].clk / 100,
 						podn_vdd_dep->entries[i].vddc);
 		}
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_MCLK");
+			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
-				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
+				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
 					i, podn_vdd_dep->entries[i].clk/100,
 						podn_vdd_dep->entries[i].vddc);
 		}
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_RANGE");
-			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.gfx_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
-			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
+			size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.mem_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
-			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
+			size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n",
 				data->odn_dpm_table.min_vddc,
 				data->odn_dpm_table.max_vddc);
 		}
@@ -5112,15 +5112,15 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%s %16s %s %s %s %s\n",title[0],
+	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);
 
 	for (i = 0; i < PP_SMC_POWER_PROFILE_CUSTOM; i++)
-		size += sprintf(buf + size, "%3d %14s%s: %14d %3d %10d %14d\n",
+		size += sysfs_emit_at(buf, size, "%3d %14s%s: %14d %3d %10d %14d\n",
 			i, profile_name[i], (i == hwmgr->power_profile_mode) ? "*" : " ",
 			profile_mode_setting[i][0], profile_mode_setting[i][1],
 			profile_mode_setting[i][2], profile_mode_setting[i][3]);
-	size += sprintf(buf + size, "%3d %14s%s: %14d %3d %10d %14d\n", i,
+	size += sysfs_emit_at(buf, size, "%3d %14s%s: %14d %3d %10d %14d\n", i,
 			profile_name[i], (i == hwmgr->power_profile_mode) ? "*" : " ",
 			data->custom_profile_mode[0], data->custom_profile_mode[1],
 			data->custom_profile_mode[2], data->custom_profile_mode[3]);
@@ -5536,8 +5536,8 @@ static const struct pp_hwmgr_func vega10_hwmgr_funcs = {
 	.force_dpm_level = vega10_dpm_force_dpm_level,
 	.stop_thermal_controller = vega10_thermal_stop_thermal_controller,
 	.get_fan_speed_info = vega10_fan_ctrl_get_fan_speed_info,
-	.get_fan_speed_percent = vega10_fan_ctrl_get_fan_speed_percent,
-	.set_fan_speed_percent = vega10_fan_ctrl_set_fan_speed_percent,
+	.get_fan_speed_pwm = vega10_fan_ctrl_get_fan_speed_pwm,
+	.set_fan_speed_pwm = vega10_fan_ctrl_set_fan_speed_pwm,
 	.reset_fan_speed_to_default =
 			vega10_fan_ctrl_reset_fan_speed_to_default,
 	.get_fan_speed_rpm = vega10_fan_ctrl_get_fan_speed_rpm,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
index 9b46b27bd30c..dad3e3741a4e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
@@ -64,7 +64,7 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-int vega10_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed)
 {
 	uint32_t current_rpm;
@@ -78,11 +78,11 @@ int vega10_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
 
 	if (hwmgr->thermal_controller.
 			advanceFanControlParameters.usMaxFanRPM != 0)
-		percent = current_rpm * 100 /
+		percent = current_rpm * 255 /
 			hwmgr->thermal_controller.
 			advanceFanControlParameters.usMaxFanRPM;
 
-	*speed = percent > 100 ? 100 : percent;
+	*speed = MIN(percent, 255);
 
 	return 0;
 }
@@ -241,12 +241,11 @@ int vega10_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr)
 }
 
 /**
- * vega10_fan_ctrl_set_fan_speed_percent - Set Fan Speed in percent.
+ * vega10_fan_ctrl_set_fan_speed_pwm - Set Fan Speed in PWM.
  * @hwmgr:  the address of the powerplay hardware manager.
- * @speed: is the percentage value (0% - 100%) to be set.
- * Exception: Fails is the 100% setting appears to be 0.
+ * @speed: is the percentage value (0 - 255) to be set.
  */
-int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int vega10_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t speed)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
@@ -257,8 +256,7 @@ int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 	if (hwmgr->thermal_controller.fanInfo.bNoFan)
 		return 0;
 
-	if (speed > 100)
-		speed = 100;
+	speed = MIN(speed, 255);
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		vega10_fan_ctrl_stop_smc_fan_control(hwmgr);
@@ -270,7 +268,7 @@ int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	tmp64 = (uint64_t)speed * duty100;
-	do_div(tmp64, 100);
+	do_div(tmp64, 255);
 	duty = (uint32_t)tmp64;
 
 	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h
index 4a0ede7c1f07..6850a21a2991 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h
@@ -54,12 +54,12 @@ extern int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr);
 extern int vega10_thermal_stop_thermal_controller(struct pp_hwmgr *hwmgr);
 extern int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 		struct phm_fan_speed_info *fan_speed_info);
-extern int vega10_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+extern int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed);
 extern int vega10_fan_ctrl_set_default_mode(struct pp_hwmgr *hwmgr);
 extern int vega10_fan_ctrl_set_static_mode(struct pp_hwmgr *hwmgr,
 		uint32_t mode);
-extern int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+extern int vega10_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t speed);
 extern int vega10_fan_ctrl_reset_fan_speed_to_default(struct pp_hwmgr *hwmgr);
 extern int vega10_thermal_ctrl_uninitialize_thermal_controller(
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index 29e0d1d4035a..8558718e15a8 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2146,13 +2146,13 @@ static int vega12_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 		"[EnableAllSmuFeatures] Failed to get enabled smc features!",
 		return ret);
 
-	size += sprintf(buf + size, "Current ppfeatures: 0x%016llx\n", features_enabled);
-	size += sprintf(buf + size, "%-19s %-22s %s\n",
+	size += sysfs_emit_at(buf, size, "Current ppfeatures: 0x%016llx\n", features_enabled);
+	size += sysfs_emit_at(buf, size, "%-19s %-22s %s\n",
 				output_title[0],
 				output_title[1],
 				output_title[2]);
 	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
-		size += sprintf(buf + size, "%-19s 0x%016llx %6s\n",
+		size += sysfs_emit_at(buf, size, "%-19s 0x%016llx %6s\n",
 				ppfeature_name[i],
 				1ULL << i,
 				(features_enabled & (1ULL << i)) ? "Y" : "N");
@@ -2256,7 +2256,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get gfx clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
@@ -2272,7 +2272,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get memory clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
@@ -2290,7 +2290,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get soc clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
@@ -2308,7 +2308,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get dcef clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 0791309586c5..0cf39c1244b1 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -2769,7 +2769,7 @@ static void vega20_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		vega20_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
+		vega20_fan_ctrl_set_fan_speed_pwm(hwmgr, 255);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
@@ -3243,13 +3243,13 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
 			return ret);
 
-	size += sprintf(buf + size, "Current ppfeatures: 0x%016llx\n", features_enabled);
-	size += sprintf(buf + size, "%-19s %-22s %s\n",
+	size += sysfs_emit_at(buf, size, "Current ppfeatures: 0x%016llx\n", features_enabled);
+	size += sysfs_emit_at(buf, size, "%-19s %-22s %s\n",
 				output_title[0],
 				output_title[1],
 				output_title[2]);
 	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
-		size += sprintf(buf + size, "%-19s 0x%016llx %6s\n",
+		size += sysfs_emit_at(buf, size, "%-19s 0x%016llx %6s\n",
 					ppfeature_name[i],
 					1ULL << i,
 					(features_enabled & (1ULL << i)) ? "Y" : "N");
@@ -3372,13 +3372,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_sclks(hwmgr, &clocks)) {
-			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
+			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3390,13 +3390,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_memclocks(hwmgr, &clocks)) {
-			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
+			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3408,13 +3408,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_socclocks(hwmgr, &clocks)) {
-			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
+			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3426,7 +3426,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		for (i = 0; i < fclk_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, fclk_dpm_table->dpm_levels[i].value,
 				fclk_dpm_table->dpm_levels[i].value == (now / 100) ? "*" : "");
 		break;
@@ -3438,13 +3438,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_dcefclocks(hwmgr, &clocks)) {
-			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
+			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3458,7 +3458,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 			gen_speed = pptable->PcieGenSpeed[i];
 			lane_width = pptable->PcieLaneCount[i];
 
-			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %s %s %dMhz %s\n", i,
 					(gen_speed == 0) ? "2.5GT/s," :
 					(gen_speed == 1) ? "5.0GT/s," :
 					(gen_speed == 2) ? "8.0GT/s," :
@@ -3479,18 +3479,18 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	case OD_SCLK:
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 				od_table->GfxclkFmin);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 				od_table->GfxclkFmax);
 		}
 		break;
 
 	case OD_MCLK:
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size = sprintf(buf, "%s:\n", "OD_MCLK");
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 				od_table->UclkFmax);
 		}
 
@@ -3503,14 +3503,14 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size = sprintf(buf, "%s:\n", "OD_VDDC_CURVE");
-			size += sprintf(buf + size, "0: %10uMhz %10dmV\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_VDDC_CURVE");
+			size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq1,
 				od_table->GfxclkVolt1 / VOLTAGE_SCALE);
-			size += sprintf(buf + size, "1: %10uMhz %10dmV\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq2,
 				od_table->GfxclkVolt2 / VOLTAGE_SCALE);
-			size += sprintf(buf + size, "2: %10uMhz %10dmV\n",
+			size += sysfs_emit_at(buf, size, "2: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq3,
 				od_table->GfxclkVolt3 / VOLTAGE_SCALE);
 		}
@@ -3518,17 +3518,17 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 
 	case OD_RANGE:
-		size = sprintf(buf, "%s:\n", "OD_RANGE");
+		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
 
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FMIN].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FMAX].max_value);
 		}
 
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "MCLK: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_UCLK_FMAX].min_value,
 				od8_settings[OD8_SETTING_UCLK_FMAX].max_value);
 		}
@@ -3539,22 +3539,22 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ1].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ1].max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ2].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ2].max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ3].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ3].max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].max_value);
 		}
@@ -4003,7 +4003,7 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+	size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
 
@@ -4016,10 +4016,10 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 				"[GetPowerProfile] Failed to get activity monitor!",
 				return result);
 
-		size += sprintf(buf + size, "%2d %14s%s:\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s:\n",
 			i, profile_name[i], (i == hwmgr->power_profile_mode) ? "*" : " ");
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			0,
 			"GFXCLK",
@@ -4033,7 +4033,7 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			activity_monitor.Gfx_PD_Data_error_coeff,
 			activity_monitor.Gfx_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			1,
 			"SOCCLK",
@@ -4047,7 +4047,7 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			activity_monitor.Soc_PD_Data_error_coeff,
 			activity_monitor.Soc_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			2,
 			"UCLK",
@@ -4061,7 +4061,7 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			activity_monitor.Mem_PD_Data_error_coeff,
 			activity_monitor.Mem_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			3,
 			"FCLK",
@@ -4409,8 +4409,8 @@ static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	.register_irq_handlers = smu9_register_irq_handlers,
 	.disable_smc_firmware_ctf = vega20_thermal_disable_alert,
 	/* fan control related */
-	.get_fan_speed_percent = vega20_fan_ctrl_get_fan_speed_percent,
-	.set_fan_speed_percent = vega20_fan_ctrl_set_fan_speed_percent,
+	.get_fan_speed_pwm = vega20_fan_ctrl_get_fan_speed_pwm,
+	.set_fan_speed_pwm = vega20_fan_ctrl_set_fan_speed_pwm,
 	.get_fan_speed_info = vega20_fan_ctrl_get_fan_speed_info,
 	.get_fan_speed_rpm = vega20_fan_ctrl_get_fan_speed_rpm,
 	.set_fan_speed_rpm = vega20_fan_ctrl_set_fan_speed_rpm,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
index 269dd7e95a44..f4f4efdbda79 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
@@ -114,26 +114,29 @@ static int vega20_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 	return 0;
 }
 
-int vega20_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int vega20_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed)
 {
-	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
-	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
-	uint32_t current_rpm, percent = 0;
-	int ret = 0;
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
 
-	ret = vega20_get_current_rpm(hwmgr, &current_rpm);
-	if (ret)
-		return ret;
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS),
+				CG_THERMAL_STATUS, FDO_PWM_DUTY);
 
-	percent = current_rpm * 100 / pp_table->FanMaximumRpm;
+	if (!duty100)
+		return -EINVAL;
 
-	*speed = percent > 100 ? 100 : percent;
+	tmp64 = (uint64_t)duty * 255;
+	do_div(tmp64, duty100);
+	*speed = MIN((uint32_t)tmp64, 255);
 
 	return 0;
 }
 
-int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+int vega20_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t speed)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
@@ -141,8 +144,7 @@ int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 	uint32_t duty;
 	uint64_t tmp64;
 
-	if (speed > 100)
-		speed = 100;
+	speed = MIN(speed, 255);
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		vega20_fan_ctrl_stop_smc_fan_control(hwmgr);
@@ -154,7 +156,7 @@ int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	tmp64 = (uint64_t)speed * duty100;
-	do_div(tmp64, 100);
+	do_div(tmp64, 255);
 	duty = (uint32_t)tmp64;
 
 	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h
index 2d1769bbd24e..b18d09cf761e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h
@@ -56,9 +56,9 @@ extern int vega20_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed);
 extern int vega20_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr,
 		uint32_t speed);
-extern int vega20_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+extern int vega20_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed);
-extern int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+extern int vega20_fan_ctrl_set_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t speed);
 extern int vega20_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr);
 extern int vega20_fan_ctrl_start_smc_fan_control(struct pp_hwmgr *hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
index 15c0b8af376f..bdbbeb959c68 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
@@ -6539,7 +6539,7 @@ static int si_fan_ctrl_stop_smc_fan_control(struct amdgpu_device *adev)
 	}
 }
 
-static int si_dpm_get_fan_speed_percent(void *handle,
+static int si_dpm_get_fan_speed_pwm(void *handle,
 				      u32 *speed)
 {
 	u32 duty, duty100;
@@ -6555,17 +6555,14 @@ static int si_dpm_get_fan_speed_percent(void *handle,
 	if (duty100 == 0)
 		return -EINVAL;
 
-	tmp64 = (u64)duty * 100;
+	tmp64 = (u64)duty * 255;
 	do_div(tmp64, duty100);
-	*speed = (u32)tmp64;
-
-	if (*speed > 100)
-		*speed = 100;
+	*speed = MIN((u32)tmp64, 255);
 
 	return 0;
 }
 
-static int si_dpm_set_fan_speed_percent(void *handle,
+static int si_dpm_set_fan_speed_pwm(void *handle,
 				      u32 speed)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -6580,7 +6577,7 @@ static int si_dpm_set_fan_speed_percent(void *handle,
 	if (si_pi->fan_is_controlled_by_smc)
 		return -EINVAL;
 
-	if (speed > 100)
+	if (speed > 255)
 		return -EINVAL;
 
 	duty100 = (RREG32(CG_FDO_CTRL1) & FMAX_DUTY100_MASK) >> FMAX_DUTY100_SHIFT;
@@ -6589,7 +6586,7 @@ static int si_dpm_set_fan_speed_percent(void *handle,
 		return -EINVAL;
 
 	tmp64 = (u64)speed * duty100;
-	do_div(tmp64, 100);
+	do_div(tmp64, 255);
 	duty = (u32)tmp64;
 
 	tmp = RREG32(CG_FDO_CTRL0) & ~FDO_STATIC_DUTY_MASK;
@@ -8059,8 +8056,8 @@ static const struct amd_pm_funcs si_dpm_funcs = {
 	.vblank_too_short = &si_dpm_vblank_too_short,
 	.set_fan_control_mode = &si_dpm_set_fan_control_mode,
 	.get_fan_control_mode = &si_dpm_get_fan_control_mode,
-	.set_fan_speed_percent = &si_dpm_set_fan_speed_percent,
-	.get_fan_speed_percent = &si_dpm_get_fan_speed_percent,
+	.set_fan_speed_pwm = &si_dpm_set_fan_speed_pwm,
+	.get_fan_speed_pwm = &si_dpm_get_fan_speed_pwm,
 	.check_state_equal = &si_check_state_equal,
 	.get_vce_clock_state = amdgpu_get_vce_clock_state,
 	.read_sensor = &si_dpm_read_sensor,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index ebe672142808..3ab1ce4d3419 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -36,6 +36,7 @@
 #include "vangogh_ppt.h"
 #include "aldebaran_ppt.h"
 #include "yellow_carp_ppt.h"
+#include "cyan_skillfish_ppt.h"
 #include "amd_pcie.h"
 
 /*
@@ -57,7 +58,7 @@ static int smu_handle_task(struct smu_context *smu,
 			   enum amd_pp_task task_id,
 			   bool lock_needed);
 static int smu_reset(struct smu_context *smu);
-static int smu_set_fan_speed_percent(void *handle, u32 speed);
+static int smu_set_fan_speed_pwm(void *handle, u32 speed);
 static int smu_set_fan_control_mode(struct smu_context *smu, int value);
 static int smu_set_power_limit(void *handle, uint32_t limit);
 static int smu_set_fan_speed_rpm(void *handle, uint32_t speed);
@@ -402,17 +403,35 @@ static void smu_restore_dpm_user_profile(struct smu_context *smu)
 	}
 
 	/* set the user dpm fan configurations */
-	if (smu->user_dpm_profile.fan_mode == AMD_FAN_CTRL_MANUAL) {
+	if (smu->user_dpm_profile.fan_mode == AMD_FAN_CTRL_MANUAL ||
+	    smu->user_dpm_profile.fan_mode == AMD_FAN_CTRL_NONE) {
 		ret = smu_set_fan_control_mode(smu, smu->user_dpm_profile.fan_mode);
 		if (ret) {
+			smu->user_dpm_profile.fan_speed_pwm = 0;
+			smu->user_dpm_profile.fan_speed_rpm = 0;
+			smu->user_dpm_profile.fan_mode = AMD_FAN_CTRL_AUTO;
 			dev_err(smu->adev->dev, "Failed to set manual fan control mode\n");
-			return;
 		}
 
-		if (!ret && smu->user_dpm_profile.fan_speed_percent) {
-			ret = smu_set_fan_speed_percent(smu, smu->user_dpm_profile.fan_speed_percent);
+		if (smu->user_dpm_profile.fan_speed_pwm) {
+			ret = smu_set_fan_speed_pwm(smu, smu->user_dpm_profile.fan_speed_pwm);
+			if (ret)
+				dev_err(smu->adev->dev, "Failed to set manual fan speed in pwm\n");
+		}
+
+		if (smu->user_dpm_profile.fan_speed_rpm) {
+			ret = smu_set_fan_speed_rpm(smu, smu->user_dpm_profile.fan_speed_rpm);
 			if (ret)
-				dev_err(smu->adev->dev, "Failed to set manual fan speed\n");
+				dev_err(smu->adev->dev, "Failed to set manual fan speed in rpm\n");
+		}
+	}
+
+	/* Restore user customized OD settings */
+	if (smu->user_dpm_profile.user_od) {
+		if (smu->ppt_funcs->restore_user_od_settings) {
+			ret = smu->ppt_funcs->restore_user_od_settings(smu);
+			if (ret)
+				dev_err(smu->adev->dev, "Failed to upload customized OD settings\n");
 		}
 	}
 
@@ -588,6 +607,9 @@ static int smu_set_funcs(struct amdgpu_device *adev)
 	case CHIP_YELLOW_CARP:
 		yellow_carp_set_ppt_funcs(smu);
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		cyan_skillfish_set_ppt_funcs(smu);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -607,6 +629,7 @@ static int smu_early_init(void *handle)
 	mutex_init(&smu->smu_baco.mutex);
 	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
+	smu->user_dpm_profile.fan_mode = -1;
 
 	adev->powerplay.pp_handle = smu;
 	adev->powerplay.pp_funcs = &swsmu_pm_funcs;
@@ -2166,7 +2189,6 @@ static int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled)
 static int smu_set_fan_speed_rpm(void *handle, uint32_t speed)
 {
 	struct smu_context *smu = handle;
-	u32 percent;
 	int ret = 0;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
@@ -2174,11 +2196,16 @@ static int smu_set_fan_speed_rpm(void *handle, uint32_t speed)
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->set_fan_speed_percent) {
-		percent = speed * 100 / smu->fan_max_rpm;
-		ret = smu->ppt_funcs->set_fan_speed_percent(smu, percent);
-		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
-			smu->user_dpm_profile.fan_speed_percent = percent;
+	if (smu->ppt_funcs->set_fan_speed_rpm) {
+		ret = smu->ppt_funcs->set_fan_speed_rpm(smu, speed);
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE)) {
+			smu->user_dpm_profile.flags |= SMU_CUSTOM_FAN_SPEED_RPM;
+			smu->user_dpm_profile.fan_speed_rpm = speed;
+
+			/* Override custom PWM setting as they cannot co-exist */
+			smu->user_dpm_profile.flags &= ~SMU_CUSTOM_FAN_SPEED_PWM;
+			smu->user_dpm_profile.fan_speed_pwm = 0;
+		}
 	}
 
 	mutex_unlock(&smu->mutex);
@@ -2538,8 +2565,11 @@ static int smu_set_fan_control_mode(struct smu_context *smu, int value)
 
 	/* reset user dpm fan speed */
 	if (!ret && value != AMD_FAN_CTRL_MANUAL &&
-			!(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
-		smu->user_dpm_profile.fan_speed_percent = 0;
+			!(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE)) {
+		smu->user_dpm_profile.fan_speed_pwm = 0;
+		smu->user_dpm_profile.fan_speed_rpm = 0;
+		smu->user_dpm_profile.flags &= ~(SMU_CUSTOM_FAN_SPEED_RPM | SMU_CUSTOM_FAN_SPEED_PWM);
+	}
 
 	return ret;
 }
@@ -2552,31 +2582,25 @@ static void smu_pp_set_fan_control_mode(void *handle, u32 value)
 }
 
 
-static int smu_get_fan_speed_percent(void *handle, u32 *speed)
+static int smu_get_fan_speed_pwm(void *handle, u32 *speed)
 {
 	struct smu_context *smu = handle;
 	int ret = 0;
-	uint32_t percent;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->get_fan_speed_percent) {
-		ret = smu->ppt_funcs->get_fan_speed_percent(smu, &percent);
-		if (!ret) {
-			*speed = percent > 100 ? 100 : percent;
-		}
-	}
+	if (smu->ppt_funcs->get_fan_speed_pwm)
+		ret = smu->ppt_funcs->get_fan_speed_pwm(smu, speed);
 
 	mutex_unlock(&smu->mutex);
 
-
 	return ret;
 }
 
-static int smu_set_fan_speed_percent(void *handle, u32 speed)
+static int smu_set_fan_speed_pwm(void *handle, u32 speed)
 {
 	struct smu_context *smu = handle;
 	int ret = 0;
@@ -2586,12 +2610,16 @@ static int smu_set_fan_speed_percent(void *handle, u32 speed)
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->set_fan_speed_percent) {
-		if (speed > 100)
-			speed = 100;
-		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
-		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
-			smu->user_dpm_profile.fan_speed_percent = speed;
+	if (smu->ppt_funcs->set_fan_speed_pwm) {
+		ret = smu->ppt_funcs->set_fan_speed_pwm(smu, speed);
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE)) {
+			smu->user_dpm_profile.flags |= SMU_CUSTOM_FAN_SPEED_PWM;
+			smu->user_dpm_profile.fan_speed_pwm = speed;
+
+			/* Override custom RPM setting as they cannot co-exist */
+			smu->user_dpm_profile.flags &= ~SMU_CUSTOM_FAN_SPEED_RPM;
+			smu->user_dpm_profile.fan_speed_rpm = 0;
+		}
 	}
 
 	mutex_unlock(&smu->mutex);
@@ -2603,17 +2631,14 @@ static int smu_get_fan_speed_rpm(void *handle, uint32_t *speed)
 {
 	struct smu_context *smu = handle;
 	int ret = 0;
-	u32 percent;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->get_fan_speed_percent) {
-		ret = smu->ppt_funcs->get_fan_speed_percent(smu, &percent);
-		*speed = percent * smu->fan_max_rpm / 100;
-	}
+	if (smu->ppt_funcs->get_fan_speed_rpm)
+		ret = smu->ppt_funcs->get_fan_speed_rpm(smu, speed);
 
 	mutex_unlock(&smu->mutex);
 
@@ -3030,8 +3055,8 @@ static const struct amd_pm_funcs swsmu_pm_funcs = {
 	/* export for sysfs */
 	.set_fan_control_mode    = smu_pp_set_fan_control_mode,
 	.get_fan_control_mode    = smu_get_fan_control_mode,
-	.set_fan_speed_percent   = smu_set_fan_speed_percent,
-	.get_fan_speed_percent   = smu_get_fan_speed_percent,
+	.set_fan_speed_pwm   = smu_set_fan_speed_pwm,
+	.get_fan_speed_pwm   = smu_get_fan_speed_pwm,
 	.force_clock_level       = smu_force_ppclk_levels,
 	.print_clock_levels      = smu_print_ppclk_levels,
 	.force_performance_level = smu_force_performance_level,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile
index 0138c982dfd3..f9b2e16f6431 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile
@@ -27,6 +27,7 @@ SMU11_MGR = arcturus_ppt.o \
 	    navi10_ppt.o \
 	    sienna_cichlid_ppt.o \
 	    vangogh_ppt.o \
+	    cyan_skillfish_ppt.o \
 	    smu_v11_0.o
 
 AMD_SWSMU_SMU11MGR = $(addprefix $(AMD_SWSMU_PATH)/smu11/,$(SMU11_MGR))
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 094df6f87cfc..273df66cac14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -81,6 +81,24 @@
 
 #define smnPCIE_ESM_CTRL			0x111003D0
 
+#define mmCG_FDO_CTRL0_ARCT			0x8B
+#define mmCG_FDO_CTRL0_ARCT_BASE_IDX		0
+
+#define mmCG_FDO_CTRL1_ARCT			0x8C
+#define mmCG_FDO_CTRL1_ARCT_BASE_IDX		0
+
+#define mmCG_FDO_CTRL2_ARCT			0x8D
+#define mmCG_FDO_CTRL2_ARCT_BASE_IDX		0
+
+#define mmCG_TACH_CTRL_ARCT			0x8E
+#define mmCG_TACH_CTRL_ARCT_BASE_IDX		0
+
+#define mmCG_TACH_STATUS_ARCT			0x8F
+#define mmCG_TACH_STATUS_ARCT_BASE_IDX		0
+
+#define mmCG_THERMAL_STATUS_ARCT		0x90
+#define mmCG_THERMAL_STATUS_ARCT_BASE_IDX	0
+
 static const struct cmn2asic_msg_mapping arcturus_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,			     PPSMC_MSG_GetSmuVersion,			1),
@@ -163,14 +181,14 @@ static const struct cmn2asic_mapping arcturus_feature_mask_map[SMU_FEATURE_COUNT
 	FEA_MAP(DPM_SOCCLK),
 	FEA_MAP(DPM_FCLK),
 	FEA_MAP(DPM_MP0CLK),
-	ARCTURUS_FEA_MAP(SMU_FEATURE_XGMI_BIT, FEATURE_DPM_XGMI_BIT),
+	FEA_MAP(DPM_XGMI),
 	FEA_MAP(DS_GFXCLK),
 	FEA_MAP(DS_SOCCLK),
 	FEA_MAP(DS_LCLK),
 	FEA_MAP(DS_FCLK),
 	FEA_MAP(DS_UCLK),
 	FEA_MAP(GFX_ULV),
-	ARCTURUS_FEA_MAP(SMU_FEATURE_VCN_PG_BIT, FEATURE_DPM_VCN_BIT),
+	ARCTURUS_FEA_MAP(SMU_FEATURE_VCN_DPM_BIT, FEATURE_DPM_VCN_BIT),
 	FEA_MAP(RSMU_SMN_CG),
 	FEA_MAP(WAFL_CG),
 	FEA_MAP(PPT),
@@ -721,13 +739,13 @@ static int arcturus_get_current_clk_freq_by_table(struct smu_context *smu,
 			member_type = METRICS_AVERAGE_SOCCLK;
 		break;
 	case PPCLK_VCLK:
-		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT))
+		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_DPM_BIT))
 			member_type = METRICS_CURR_VCLK;
 		else
 			member_type = METRICS_AVERAGE_VCLK;
 		break;
 	case PPCLK_DCLK:
-		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT))
+		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_DPM_BIT))
 			member_type = METRICS_CURR_DCLK;
 		else
 			member_type = METRICS_AVERAGE_DCLK;
@@ -756,7 +774,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 	uint32_t gen_speed, lane_width;
 
 	if (amdgpu_ras_intr_triggered())
-		return snprintf(buf, PAGE_SIZE, "unavailable\n");
+		return sysfs_emit(buf, "unavailable\n");
 
 	dpm_context = smu_dpm->dpm_context;
 
@@ -780,7 +798,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		 * And it's safe to assume that is always the current clock.
 		 */
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i,
 					clocks.data[i].clocks_in_khz / 1000,
 					(clocks.num_levels == 1) ? "*" :
 					(arcturus_freqs_in_same_level(
@@ -803,7 +821,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.num_levels == 1) ? "*" :
 				(arcturus_freqs_in_same_level(
@@ -826,7 +844,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.num_levels == 1) ? "*" :
 				(arcturus_freqs_in_same_level(
@@ -849,7 +867,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, single_dpm_table->dpm_levels[i].value,
 				(clocks.num_levels == 1) ? "*" :
 				(arcturus_freqs_in_same_level(
@@ -872,7 +890,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, single_dpm_table->dpm_levels[i].value,
 				(clocks.num_levels == 1) ? "*" :
 				(arcturus_freqs_in_same_level(
@@ -895,7 +913,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 				i, single_dpm_table->dpm_levels[i].value,
 				(clocks.num_levels == 1) ? "*" :
 				(arcturus_freqs_in_same_level(
@@ -906,7 +924,7 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 	case SMU_PCIE:
 		gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu);
 		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
-		size += sprintf(buf + size, "0: %s %s %dMhz *\n",
+		size += sysfs_emit_at(buf, size, "0: %s %s %dMhz *\n",
 				(gen_speed == 0) ? "2.5GT/s," :
 				(gen_speed == 1) ? "5.0GT/s," :
 				(gen_speed == 2) ? "8.0GT/s," :
@@ -1162,11 +1180,29 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	return ret;
 }
 
-static int arcturus_get_fan_speed_percent(struct smu_context *smu,
-					  uint32_t *speed)
+static int arcturus_set_fan_static_mode(struct smu_context *smu,
+					uint32_t mode)
 {
-	int ret;
-	u32 rpm;
+	struct amdgpu_device *adev = smu->adev;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2_ARCT,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2_ARCT),
+				   CG_FDO_CTRL2, TMIN, 0));
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2_ARCT,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2_ARCT),
+				   CG_FDO_CTRL2, FDO_PWM_MODE, mode));
+
+	return 0;
+}
+
+static int arcturus_get_fan_speed_rpm(struct smu_context *smu,
+				      uint32_t *speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t crystal_clock_freq = 2500;
+	uint32_t tach_status;
+	uint64_t tmp64;
+	int ret = 0;
 
 	if (!speed)
 		return -EINVAL;
@@ -1175,14 +1211,112 @@ static int arcturus_get_fan_speed_percent(struct smu_context *smu,
 	case AMD_FAN_CTRL_AUTO:
 		ret = arcturus_get_smu_metrics_data(smu,
 						    METRICS_CURR_FANSPEED,
-						    &rpm);
-		if (!ret && smu->fan_max_rpm)
-			*speed = rpm * 100 / smu->fan_max_rpm;
-		return ret;
+						    speed);
+		break;
 	default:
-		*speed = smu->user_dpm_profile.fan_speed_percent;
+		/*
+		 * For pre Sienna Cichlid ASICs, the 0 RPM may be not correctly
+		 * detected via register retrieving. To workaround this, we will
+		 * report the fan speed as 0 RPM if user just requested such.
+		 */
+		if ((smu->user_dpm_profile.flags & SMU_CUSTOM_FAN_SPEED_RPM)
+		     && !smu->user_dpm_profile.fan_speed_rpm) {
+			*speed = 0;
+			return 0;
+		}
+
+		tmp64 = (uint64_t)crystal_clock_freq * 60 * 10000;
+		tach_status = RREG32_SOC15(THM, 0, mmCG_TACH_STATUS_ARCT);
+		if (tach_status) {
+			do_div(tmp64, tach_status);
+			*speed = (uint32_t)tmp64;
+		} else {
+			*speed = 0;
+		}
+
+		break;
+	}
+
+	return ret;
+}
+
+static int arcturus_set_fan_speed_pwm(struct smu_context *smu,
+				      uint32_t speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
+
+	speed = MIN(speed, 255);
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1_ARCT),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	if (!duty100)
+		return -EINVAL;
+
+	tmp64 = (uint64_t)speed * duty100;
+	do_div(tmp64, 255);
+	duty = (uint32_t)tmp64;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0_ARCT,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0_ARCT),
+				   CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
+
+	return arcturus_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
+}
+
+static int arcturus_set_fan_speed_rpm(struct smu_context *smu,
+				      uint32_t speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	/*
+	 * crystal_clock_freq used for fan speed rpm calculation is
+	 * always 25Mhz. So, hardcode it as 2500(in 10K unit).
+	 */
+	uint32_t crystal_clock_freq = 2500;
+	uint32_t tach_period;
+
+	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
+	WREG32_SOC15(THM, 0, mmCG_TACH_CTRL_ARCT,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL_ARCT),
+				   CG_TACH_CTRL, TARGET_PERIOD,
+				   tach_period));
+
+	return arcturus_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC_RPM);
+}
+
+static int arcturus_get_fan_speed_pwm(struct smu_context *smu,
+				      uint32_t *speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
+
+	/*
+	 * For pre Sienna Cichlid ASICs, the 0 RPM may be not correctly
+	 * detected via register retrieving. To workaround this, we will
+	 * report the fan speed as 0 PWM if user just requested such.
+	 */
+	if ((smu->user_dpm_profile.flags & SMU_CUSTOM_FAN_SPEED_PWM)
+	     && !smu->user_dpm_profile.fan_speed_pwm) {
+		*speed = 0;
 		return 0;
 	}
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1_ARCT),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS_ARCT),
+				CG_THERMAL_STATUS, FDO_PWM_DUTY);
+
+	if (duty100) {
+		tmp64 = (uint64_t)duty * 255;
+		do_div(tmp64, duty100);
+		*speed = MIN((uint32_t)tmp64, 255);
+	} else {
+		*speed = 0;
+	}
+
+	return 0;
 }
 
 static int arcturus_get_fan_parameters(struct smu_context *smu)
@@ -1272,11 +1406,11 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 		return result;
 
 	if (smu_version >= 0x360d00)
-		size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+		size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
 	else
-		size += sprintf(buf + size, "%16s\n",
+		size += sysfs_emit_at(buf, size, "%16s\n",
 			title[0]);
 
 	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
@@ -1302,11 +1436,11 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 			}
 		}
 
-		size += sprintf(buf + size, "%2d %14s%s\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 
 		if (smu_version >= 0x360d00) {
-			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+			size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 				" ",
 				0,
 				"GFXCLK",
@@ -1320,7 +1454,7 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 				activity_monitor.Gfx_PD_Data_error_coeff,
 				activity_monitor.Gfx_PD_Data_error_rate_coeff);
 
-			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+			size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 				" ",
 				1,
 				"UCLK",
@@ -1916,16 +2050,16 @@ static int arcturus_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 	int ret = 0;
 
 	if (enable) {
-		if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
-			ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, 1);
+		if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_DPM_BIT)) {
+			ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_VCN_DPM_BIT, 1);
 			if (ret) {
 				dev_err(smu->adev->dev, "[EnableVCNDPM] failed!\n");
 				return ret;
 			}
 		}
 	} else {
-		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
-			ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, 0);
+		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_DPM_BIT)) {
+			ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_VCN_DPM_BIT, 0);
 			if (ret) {
 				dev_err(smu->adev->dev, "[DisableVCNDPM] failed!\n");
 				return ret;
@@ -1936,197 +2070,77 @@ static int arcturus_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 	return ret;
 }
 
-static void arcturus_fill_i2c_req(SwI2cRequest_t  *req, bool write,
-				  uint8_t address, uint32_t numbytes,
-				  uint8_t *data)
-{
-	int i;
-
-	req->I2CcontrollerPort = 0;
-	req->I2CSpeed = 2;
-	req->SlaveAddress = address;
-	req->NumCmds = numbytes;
-
-	for (i = 0; i < numbytes; i++) {
-		SwI2cCmd_t *cmd =  &req->SwI2cCmds[i];
-
-		/* First 2 bytes are always write for lower 2b EEPROM address */
-		if (i < 2)
-			cmd->Cmd = 1;
-		else
-			cmd->Cmd = write;
-
-
-		/* Add RESTART for read  after address filled */
-		cmd->CmdConfig |= (i == 2 && !write) ? CMDCONFIG_RESTART_MASK : 0;
-
-		/* Add STOP in the end */
-		cmd->CmdConfig |= (i == (numbytes - 1)) ? CMDCONFIG_STOP_MASK : 0;
-
-		/* Fill with data regardless if read or write to simplify code */
-		cmd->RegisterAddr = data[i];
-	}
-}
-
-static int arcturus_i2c_read_data(struct i2c_adapter *control,
-					       uint8_t address,
-					       uint8_t *data,
-					       uint32_t numbytes)
+static int arcturus_i2c_xfer(struct i2c_adapter *i2c_adap,
+			     struct i2c_msg *msg, int num_msgs)
 {
-	uint32_t  i, ret = 0;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_device *adev = to_amdgpu_device(i2c_adap);
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
 	struct smu_table *table = &smu_table->driver_table;
+	SwI2cRequest_t *req, *res = (SwI2cRequest_t *)table->cpu_addr;
+	int i, j, r, c;
+	u16 dir;
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
-	}
-
-	memset(&req, 0, sizeof(req));
-	arcturus_fill_i2c_req(&req, false, address, numbytes, data);
-
-	mutex_lock(&adev->smu.mutex);
-	/* Now read data starting with that address */
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req,
-					true);
-	mutex_unlock(&adev->smu.mutex);
-
-	if (!ret) {
-		SwI2cRequest_t *res = (SwI2cRequest_t *)table->cpu_addr;
-
-		/* Assume SMU  fills res.SwI2cCmds[i].Data with read bytes */
-		for (i = 0; i < numbytes; i++)
-			data[i] = res->SwI2cCmds[i].Data;
-
-		dev_dbg(adev->dev, "arcturus_i2c_read_data, address = %x, bytes = %d, data :",
-				  (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-	} else
-		dev_err(adev->dev, "arcturus_i2c_read_data - error occurred :%x", ret);
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
 
-	return ret;
-}
+	req->I2CcontrollerPort = 0;
+	req->I2CSpeed = I2C_SPEED_FAST_400K;
+	req->SlaveAddress = msg[0].addr << 1; /* wants an 8-bit address */
+	dir = msg[0].flags & I2C_M_RD;
+
+	for (c = i = 0; i < num_msgs; i++) {
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &req->SwI2cCmds[c];
+
+			if (!(msg[i].flags & I2C_M_RD)) {
+				/* write */
+				cmd->Cmd = I2C_CMD_WRITE;
+				cmd->RegisterAddr = msg[i].buf[j];
+			}
 
-static int arcturus_i2c_write_data(struct i2c_adapter *control,
-						uint8_t address,
-						uint8_t *data,
-						uint32_t numbytes)
-{
-	uint32_t ret;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+			if ((dir ^ msg[i].flags) & I2C_M_RD) {
+				/* The direction changes.
+				 */
+				dir = msg[i].flags & I2C_M_RD;
+				cmd->CmdConfig |= CMDCONFIG_RESTART_MASK;
+			}
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
+			req->NumCmds++;
+
+			/*
+			 * Insert STOP if we are at the last byte of either last
+			 * message for the transaction or the client explicitly
+			 * requires a STOP at this particular message.
+			 */
+			if ((j == msg[i].len - 1) &&
+			    ((i == num_msgs - 1) || (msg[i].flags & I2C_M_STOP))) {
+				cmd->CmdConfig &= ~CMDCONFIG_RESTART_MASK;
+				cmd->CmdConfig |= CMDCONFIG_STOP_MASK;
+			}
+		}
 	}
-
-	memset(&req, 0, sizeof(req));
-	arcturus_fill_i2c_req(&req, true, address, numbytes, data);
-
 	mutex_lock(&adev->smu.mutex);
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, true);
+	r = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, req, true);
 	mutex_unlock(&adev->smu.mutex);
+	if (r)
+		goto fail;
 
-	if (!ret) {
-		dev_dbg(adev->dev, "arcturus_i2c_write(), address = %x, bytes = %d , data: ",
-					 (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-		/*
-		 * According to EEPROM spec there is a MAX of 10 ms required for
-		 * EEPROM to flush internal RX buffer after STOP was issued at the
-		 * end of write transaction. During this time the EEPROM will not be
-		 * responsive to any more commands - so wait a bit more.
-		 */
-		msleep(10);
-
-	} else
-		dev_err(adev->dev, "arcturus_i2c_write- error occurred :%x", ret);
-
-	return ret;
-}
-
-static int arcturus_i2c_xfer(struct i2c_adapter *i2c_adap,
-			      struct i2c_msg *msgs, int num)
-{
-	uint32_t  i, j, ret, data_size, data_chunk_size, next_eeprom_addr = 0;
-	uint8_t *data_ptr, data_chunk[MAX_SW_I2C_COMMANDS] = { 0 };
-
-	for (i = 0; i < num; i++) {
-		/*
-		 * SMU interface allows at most MAX_SW_I2C_COMMANDS bytes of data at
-		 * once and hence the data needs to be spliced into chunks and sent each
-		 * chunk separately
-		 */
-		data_size = msgs[i].len - 2;
-		data_chunk_size = MAX_SW_I2C_COMMANDS - 2;
-		next_eeprom_addr = (msgs[i].buf[0] << 8 & 0xff00) | (msgs[i].buf[1] & 0xff);
-		data_ptr = msgs[i].buf + 2;
-
-		for (j = 0; j < data_size / data_chunk_size; j++) {
-			/* Insert the EEPROM dest addess, bits 0-15 */
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = arcturus_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, MAX_SW_I2C_COMMANDS);
-
-				memcpy(data_ptr, data_chunk + 2, data_chunk_size);
-			} else {
-
-				memcpy(data_chunk + 2, data_ptr, data_chunk_size);
-
-				ret = arcturus_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, MAX_SW_I2C_COMMANDS);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
-
-			next_eeprom_addr += data_chunk_size;
-			data_ptr += data_chunk_size;
+	for (c = i = 0; i < num_msgs; i++) {
+		if (!(msg[i].flags & I2C_M_RD)) {
+			c += msg[i].len;
+			continue;
 		}
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &res->SwI2cCmds[c];
 
-		if (data_size % data_chunk_size) {
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = arcturus_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, (data_size % data_chunk_size) + 2);
-
-				memcpy(data_ptr, data_chunk + 2, data_size % data_chunk_size);
-			} else {
-				memcpy(data_chunk + 2, data_ptr, data_size % data_chunk_size);
-
-				ret = arcturus_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, (data_size % data_chunk_size) + 2);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
+			msg[i].buf[j] = cmd->Data;
 		}
 	}
-
+	r = num_msgs;
 fail:
-	return num;
+	kfree(req);
+	return r;
 }
 
 static u32 arcturus_i2c_func(struct i2c_adapter *adap)
@@ -2140,15 +2154,25 @@ static const struct i2c_algorithm arcturus_i2c_algo = {
 	.functionality = arcturus_i2c_func,
 };
 
+
+static const struct i2c_adapter_quirks arcturus_i2c_control_quirks = {
+	.flags = I2C_AQ_COMB | I2C_AQ_COMB_SAME_ADDR | I2C_AQ_NO_ZERO_LEN,
+	.max_read_len  = MAX_SW_I2C_COMMANDS,
+	.max_write_len = MAX_SW_I2C_COMMANDS,
+	.max_comb_1st_msg_len = 2,
+	.max_comb_2nd_msg_len = MAX_SW_I2C_COMMANDS - 2,
+};
+
 static int arcturus_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
 	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
+	control->class = I2C_CLASS_HWMON;
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &arcturus_i2c_algo;
+	control->quirks = &arcturus_i2c_control_quirks;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
 
 	res = i2c_add_adapter(control);
@@ -2288,7 +2312,9 @@ static void arcturus_log_thermal_throttling_event(struct smu_context *smu)
 
 	dev_warn(adev->dev, "WARN: GPU thermal throttling temperature reached, expect performance decrease. %s.\n",
 			log_buf);
-	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev, throttler_status);
+	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev,
+		smu_cmn_get_indep_throttler_status(throttler_status,
+						   arcturus_throttler_map));
 }
 
 static uint16_t arcturus_get_current_pcie_link_speed(struct smu_context *smu)
@@ -2378,7 +2404,8 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.print_clk_levels = arcturus_print_clk_levels,
 	.force_clk_levels = arcturus_force_clk_levels,
 	.read_sensor = arcturus_read_sensor,
-	.get_fan_speed_percent = arcturus_get_fan_speed_percent,
+	.get_fan_speed_pwm = arcturus_get_fan_speed_pwm,
+	.get_fan_speed_rpm = arcturus_get_fan_speed_rpm,
 	.get_power_profile_mode = arcturus_get_power_profile_mode,
 	.set_power_profile_mode = arcturus_set_power_profile_mode,
 	.set_performance_level = arcturus_set_performance_level,
@@ -2423,7 +2450,8 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_pwm = arcturus_set_fan_speed_pwm,
+	.set_fan_speed_rpm = arcturus_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
 	.register_irq_handler = smu_v11_0_register_irq_handler,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
new file mode 100644
index 000000000000..b05f9541accc
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#define SWSMU_CODE_LAYER_L2
+
+#include "amdgpu.h"
+#include "amdgpu_smu.h"
+#include "smu_v11_0.h"
+#include "smu11_driver_if_cyan_skillfish.h"
+#include "cyan_skillfish_ppt.h"
+#include "smu_v11_8_ppsmc.h"
+#include "smu_v11_8_pmfw.h"
+#include "smu_cmn.h"
+#include "soc15_common.h"
+
+/*
+ * DO NOT use these for err/warn/info/debug messages.
+ * Use dev_err, dev_warn, dev_info and dev_dbg instead.
+ * They are more MGPU friendly.
+ */
+
+#undef pr_err
+#undef pr_warn
+#undef pr_info
+#undef pr_debug
+
+static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT] = {
+	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,			0),
+	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetSmuVersion,		0),
+	MSG_MAP(GetDriverIfVersion,             PPSMC_MSG_GetDriverIfVersion,		0),
+	MSG_MAP(SetDriverDramAddrHigh,          PPSMC_MSG_SetDriverTableDramAddrHigh,	0),
+	MSG_MAP(SetDriverDramAddrLow,           PPSMC_MSG_SetDriverTableDramAddrLow,	0),
+	MSG_MAP(TransferTableSmu2Dram,          PPSMC_MSG_TransferTableSmu2Dram,	0),
+	MSG_MAP(TransferTableDram2Smu,          PPSMC_MSG_TransferTableDram2Smu,	0),
+};
+
+static const struct pptable_funcs cyan_skillfish_ppt_funcs = {
+
+	.check_fw_status = smu_v11_0_check_fw_status,
+	.check_fw_version = smu_v11_0_check_fw_version,
+	.init_power = smu_v11_0_init_power,
+	.fini_power = smu_v11_0_fini_power,
+	.register_irq_handler = smu_v11_0_register_irq_handler,
+	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
+	.send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param,
+	.send_smc_msg = smu_cmn_send_smc_msg,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
+	.interrupt_work = smu_v11_0_interrupt_work,
+};
+
+void cyan_skillfish_set_ppt_funcs(struct smu_context *smu)
+{
+	smu->ppt_funcs = &cyan_skillfish_ppt_funcs;
+	smu->message_map = cyan_skillfish_message_map;
+	smu->is_apu = true;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.h
new file mode 100644
index 000000000000..76cd7229e383
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __CYAN_SKILLFISH_PPT_H__
+#define __CYAN_SKILLFISH_PPT_H__
+
+extern void cyan_skillfish_set_ppt_funcs(struct smu_context *smu);
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 1ba42b69ce74..f96681700c41 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1303,7 +1303,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 				if (ret)
 					return size;
 
-				size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 						cur_value == value ? "*" : "");
 			}
 		} else {
@@ -1321,7 +1321,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 				freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
 
 			for (i = 0; i < 3; i++) {
-				size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i],
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
 						i == mark_index ? "*" : "");
 			}
 
@@ -1331,7 +1331,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 		gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu);
 		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
 		for (i = 0; i < NUM_LINK_LEVELS; i++)
-			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %s %s %dMhz %s\n", i,
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 1) ? "5.0GT/s," :
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 2) ? "8.0GT/s," :
@@ -1352,23 +1352,24 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			break;
 		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS))
 			break;
-		size += sprintf(buf + size, "OD_SCLK:\n");
-		size += sprintf(buf + size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
+		size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
+		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
+				      od_table->GfxclkFmin, od_table->GfxclkFmax);
 		break;
 	case SMU_OD_MCLK:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
 		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX))
 			break;
-		size += sprintf(buf + size, "OD_MCLK:\n");
-		size += sprintf(buf + size, "1: %uMHz\n", od_table->UclkFmax);
+		size += sysfs_emit_at(buf, size, "OD_MCLK:\n");
+		size += sysfs_emit_at(buf, size, "1: %uMHz\n", od_table->UclkFmax);
 		break;
 	case SMU_OD_VDDC_CURVE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
 		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE))
 			break;
-		size += sprintf(buf + size, "OD_VDDC_CURVE:\n");
+		size += sysfs_emit_at(buf, size, "OD_VDDC_CURVE:\n");
 		for (i = 0; i < 3; i++) {
 			switch (i) {
 			case 0:
@@ -1383,55 +1384,57 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			default:
 				break;
 			}
-			size += sprintf(buf + size, "%d: %uMHz %umV\n", i, curve_settings[0], curve_settings[1] / NAVI10_VOLTAGE_SCALE);
+			size += sysfs_emit_at(buf, size, "%d: %uMHz %umV\n",
+					      i, curve_settings[0],
+					curve_settings[1] / NAVI10_VOLTAGE_SCALE);
 		}
 		break;
 	case SMU_OD_RANGE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		size = sprintf(buf, "%s:\n", "OD_RANGE");
+		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
 
 		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN,
 						    &min_value, NULL);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMAX,
 						    NULL, &max_value);
-			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 					min_value, max_value);
 		}
 
 		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_UCLKFMAX,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "MCLK: %7uMhz %10uMhz\n",
 					min_value, max_value);
 		}
 
 		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P1,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
+					      min_value, max_value);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P1,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
+					      min_value, max_value);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P2,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
+					      min_value, max_value);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P2,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
+					      min_value, max_value);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P3,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
+					      min_value, max_value);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P3,
 						    &min_value, &max_value);
-			size += sprintf(buf + size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
-					min_value, max_value);
+			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
+					      min_value, max_value);
 		}
 
 		break;
@@ -1668,27 +1671,27 @@ static bool navi10_is_dpm_running(struct smu_context *smu)
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
-static int navi10_get_fan_speed_percent(struct smu_context *smu,
-					uint32_t *speed)
+static int navi10_get_fan_speed_rpm(struct smu_context *smu,
+				    uint32_t *speed)
 {
-	int ret;
-	u32 rpm;
+	int ret = 0;
 
 	if (!speed)
 		return -EINVAL;
 
 	switch (smu_v11_0_get_fan_control_mode(smu)) {
 	case AMD_FAN_CTRL_AUTO:
-		ret = navi1x_get_smu_metrics_data(smu,
+		ret = navi10_get_smu_metrics_data(smu,
 						  METRICS_CURR_FANSPEED,
-						  &rpm);
-		if (!ret && smu->fan_max_rpm)
-			*speed = rpm * 100 / smu->fan_max_rpm;
-		return ret;
+						  speed);
+		break;
 	default:
-		*speed = smu->user_dpm_profile.fan_speed_percent;
-		return 0;
+		ret = smu_v11_0_get_fan_speed_rpm(smu,
+						  speed);
+		break;
 	}
+
+	return ret;
 }
 
 static int navi10_get_fan_parameters(struct smu_context *smu)
@@ -1730,7 +1733,7 @@ static int navi10_get_power_profile_mode(struct smu_context *smu, char *buf)
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+	size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
 
@@ -1750,10 +1753,10 @@ static int navi10_get_power_profile_mode(struct smu_context *smu, char *buf)
 			return result;
 		}
 
-		size += sprintf(buf + size, "%2d %14s%s:\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s:\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			0,
 			"GFXCLK",
@@ -1767,7 +1770,7 @@ static int navi10_get_power_profile_mode(struct smu_context *smu, char *buf)
 			activity_monitor.Gfx_PD_Data_error_coeff,
 			activity_monitor.Gfx_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			1,
 			"SOCCLK",
@@ -1781,7 +1784,7 @@ static int navi10_get_power_profile_mode(struct smu_context *smu, char *buf)
 			activity_monitor.Soc_PD_Data_error_coeff,
 			activity_monitor.Soc_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			2,
 			"MEMLK",
@@ -2294,41 +2297,52 @@ static int navi10_set_default_od_settings(struct smu_context *smu)
 		(OverDriveTable_t *)smu->smu_table.overdrive_table;
 	OverDriveTable_t *boot_od_table =
 		(OverDriveTable_t *)smu->smu_table.boot_overdrive_table;
+	OverDriveTable_t *user_od_table =
+		(OverDriveTable_t *)smu->smu_table.user_overdrive_table;
 	int ret = 0;
 
-	ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)od_table, false);
+	/*
+	 * For S3/S4/Runpm resume, no need to setup those overdrive tables again as
+	 *   - either they already have the default OD settings got during cold bootup
+	 *   - or they have some user customized OD settings which cannot be overwritten
+	 */
+	if (smu->adev->in_suspend)
+		return 0;
+
+	ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)boot_od_table, false);
 	if (ret) {
 		dev_err(smu->adev->dev, "Failed to get overdrive table!\n");
 		return ret;
 	}
 
-	if (!od_table->GfxclkVolt1) {
+	if (!boot_od_table->GfxclkVolt1) {
 		ret = navi10_overdrive_get_gfx_clk_base_voltage(smu,
-								&od_table->GfxclkVolt1,
-								od_table->GfxclkFreq1);
+								&boot_od_table->GfxclkVolt1,
+								boot_od_table->GfxclkFreq1);
 		if (ret)
 			return ret;
 	}
 
-	if (!od_table->GfxclkVolt2) {
+	if (!boot_od_table->GfxclkVolt2) {
 		ret = navi10_overdrive_get_gfx_clk_base_voltage(smu,
-								&od_table->GfxclkVolt2,
-								od_table->GfxclkFreq2);
+								&boot_od_table->GfxclkVolt2,
+								boot_od_table->GfxclkFreq2);
 		if (ret)
 			return ret;
 	}
 
-	if (!od_table->GfxclkVolt3) {
+	if (!boot_od_table->GfxclkVolt3) {
 		ret = navi10_overdrive_get_gfx_clk_base_voltage(smu,
-								&od_table->GfxclkVolt3,
-								od_table->GfxclkFreq3);
+								&boot_od_table->GfxclkVolt3,
+								boot_od_table->GfxclkFreq3);
 		if (ret)
 			return ret;
 	}
 
-	memcpy(boot_od_table, od_table, sizeof(OverDriveTable_t));
+	navi10_dump_od_table(smu, boot_od_table);
 
-	navi10_dump_od_table(smu, od_table);
+	memcpy(od_table, boot_od_table, sizeof(OverDriveTable_t));
+	memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t));
 
 	return 0;
 }
@@ -2429,11 +2443,20 @@ static int navi10_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABL
 		memcpy(table_context->overdrive_table, table_context->boot_overdrive_table, sizeof(OverDriveTable_t));
 		break;
 	case PP_OD_COMMIT_DPM_TABLE:
-		navi10_dump_od_table(smu, od_table);
-		ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)od_table, true);
-		if (ret) {
-			dev_err(smu->adev->dev, "Failed to import overdrive table!\n");
-			return ret;
+		if (memcmp(od_table, table_context->user_overdrive_table, sizeof(OverDriveTable_t))) {
+			navi10_dump_od_table(smu, od_table);
+			ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)od_table, true);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to import overdrive table!\n");
+				return ret;
+			}
+			memcpy(table_context->user_overdrive_table, od_table, sizeof(OverDriveTable_t));
+			smu->user_dpm_profile.user_od = true;
+
+			if (!memcmp(table_context->user_overdrive_table,
+				    table_context->boot_overdrive_table,
+				    sizeof(OverDriveTable_t)))
+				smu->user_dpm_profile.user_od = false;
 		}
 		break;
 	case PP_OD_EDIT_VDDC_CURVE:
@@ -2735,6 +2758,122 @@ static ssize_t navi10_get_legacy_gpu_metrics(struct smu_context *smu,
 	return sizeof(struct gpu_metrics_v1_3);
 }
 
+static int navi10_i2c_xfer(struct i2c_adapter *i2c_adap,
+			   struct i2c_msg *msg, int num_msgs)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(i2c_adap);
+	struct smu_table_context *smu_table = &adev->smu.smu_table;
+	struct smu_table *table = &smu_table->driver_table;
+	SwI2cRequest_t *req, *res = (SwI2cRequest_t *)table->cpu_addr;
+	int i, j, r, c;
+	u16 dir;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->I2CcontrollerPort = 0;
+	req->I2CSpeed = I2C_SPEED_FAST_400K;
+	req->SlaveAddress = msg[0].addr << 1; /* wants an 8-bit address */
+	dir = msg[0].flags & I2C_M_RD;
+
+	for (c = i = 0; i < num_msgs; i++) {
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &req->SwI2cCmds[c];
+
+			if (!(msg[i].flags & I2C_M_RD)) {
+				/* write */
+				cmd->Cmd = I2C_CMD_WRITE;
+				cmd->RegisterAddr = msg[i].buf[j];
+			}
+
+			if ((dir ^ msg[i].flags) & I2C_M_RD) {
+				/* The direction changes.
+				 */
+				dir = msg[i].flags & I2C_M_RD;
+				cmd->CmdConfig |= CMDCONFIG_RESTART_MASK;
+			}
+
+			req->NumCmds++;
+
+			/*
+			 * Insert STOP if we are at the last byte of either last
+			 * message for the transaction or the client explicitly
+			 * requires a STOP at this particular message.
+			 */
+			if ((j == msg[i].len - 1) &&
+			    ((i == num_msgs - 1) || (msg[i].flags & I2C_M_STOP))) {
+				cmd->CmdConfig &= ~CMDCONFIG_RESTART_MASK;
+				cmd->CmdConfig |= CMDCONFIG_STOP_MASK;
+			}
+		}
+	}
+	mutex_lock(&adev->smu.mutex);
+	r = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, req, true);
+	mutex_unlock(&adev->smu.mutex);
+	if (r)
+		goto fail;
+
+	for (c = i = 0; i < num_msgs; i++) {
+		if (!(msg[i].flags & I2C_M_RD)) {
+			c += msg[i].len;
+			continue;
+		}
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &res->SwI2cCmds[c];
+
+			msg[i].buf[j] = cmd->Data;
+		}
+	}
+	r = num_msgs;
+fail:
+	kfree(req);
+	return r;
+}
+
+static u32 navi10_i2c_func(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+
+static const struct i2c_algorithm navi10_i2c_algo = {
+	.master_xfer = navi10_i2c_xfer,
+	.functionality = navi10_i2c_func,
+};
+
+static const struct i2c_adapter_quirks navi10_i2c_control_quirks = {
+	.flags = I2C_AQ_COMB | I2C_AQ_COMB_SAME_ADDR | I2C_AQ_NO_ZERO_LEN,
+	.max_read_len  = MAX_SW_I2C_COMMANDS,
+	.max_write_len = MAX_SW_I2C_COMMANDS,
+	.max_comb_1st_msg_len = 2,
+	.max_comb_2nd_msg_len = MAX_SW_I2C_COMMANDS - 2,
+};
+
+static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	int res;
+
+	control->owner = THIS_MODULE;
+	control->class = I2C_CLASS_HWMON;
+	control->dev.parent = &adev->pdev->dev;
+	control->algo = &navi10_i2c_algo;
+	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
+	control->quirks = &navi10_i2c_control_quirks;
+
+	res = i2c_add_adapter(control);
+	if (res)
+		DRM_ERROR("Failed to register hw i2c, err: %d\n", res);
+
+	return res;
+}
+
+static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
+{
+	i2c_del_adapter(control);
+}
+
 static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
 				      void **table)
 {
@@ -3078,6 +3217,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.set_default_dpm_table = navi10_set_default_dpm_table,
 	.dpm_set_vcn_enable = navi10_dpm_set_vcn_enable,
 	.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
+	.i2c_init = navi10_i2c_control_init,
+	.i2c_fini = navi10_i2c_control_fini,
 	.print_clk_levels = navi10_print_clk_levels,
 	.force_clk_levels = navi10_force_clk_levels,
 	.populate_umd_state_clk = navi10_populate_umd_state_clk,
@@ -3086,7 +3227,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_config_changed = navi10_display_config_changed,
 	.notify_smc_display_config = navi10_notify_smc_display_config,
 	.is_dpm_running = navi10_is_dpm_running,
-	.get_fan_speed_percent = navi10_get_fan_speed_percent,
+	.get_fan_speed_pwm = smu_v11_0_get_fan_speed_pwm,
+	.get_fan_speed_rpm = navi10_get_fan_speed_rpm,
 	.get_power_profile_mode = navi10_get_power_profile_mode,
 	.set_power_profile_mode = navi10_set_power_profile_mode,
 	.set_watermarks_table = navi10_set_watermarks_table,
@@ -3129,7 +3271,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_pwm = smu_v11_0_set_fan_speed_pwm,
+	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
 	.register_irq_handler = smu_v11_0_register_irq_handler,
@@ -3144,6 +3287,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.set_default_od_settings = navi10_set_default_od_settings,
 	.od_edit_dpm_table = navi10_od_edit_dpm_table,
+	.restore_user_od_settings = smu_v11_0_restore_user_od_settings,
 	.run_btc = navi10_run_btc,
 	.set_power_source = smu_v11_0_set_power_source,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index d92dd2c7448e..5e292c3f5050 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -488,6 +488,26 @@ err0_out:
 	return -ENOMEM;
 }
 
+static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table= &smu->smu_table;
+	SmuMetricsExternal_t *metrics_ext =
+		(SmuMetricsExternal_t *)(smu_table->metrics_table);
+	uint32_t throttler_status = 0;
+	int i;
+
+	if ((smu->adev->asic_type == CHIP_SIENNA_CICHLID) &&
+	     (smu->smc_fw_version >= 0x3A4300)) {
+		for (i = 0; i < THROTTLER_COUNT; i++)
+			throttler_status |=
+				(metrics_ext->SmuMetrics_V2.ThrottlingPercentage[i] ? 1U << i : 0);
+	} else {
+		throttler_status = metrics_ext->SmuMetrics.ThrottlerStatus;
+	}
+
+	return throttler_status;
+}
+
 static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 					       MetricsMember_t member,
 					       uint32_t *value)
@@ -495,6 +515,11 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	SmuMetrics_t *metrics =
 		&(((SmuMetricsExternal_t *)(smu_table->metrics_table))->SmuMetrics);
+	SmuMetrics_V2_t *metrics_v2 =
+		&(((SmuMetricsExternal_t *)(smu_table->metrics_table))->SmuMetrics_V2);
+	bool use_metrics_v2 = ((smu->adev->asic_type == CHIP_SIENNA_CICHLID) &&
+		(smu->smc_fw_version >= 0x3A4300)) ? true : false;
+	uint16_t average_gfx_activity;
 	int ret = 0;
 
 	mutex_lock(&smu->metrics_lock);
@@ -509,78 +534,96 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 
 	switch (member) {
 	case METRICS_CURR_GFXCLK:
-		*value = metrics->CurrClock[PPCLK_GFXCLK];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_GFXCLK] :
+			metrics->CurrClock[PPCLK_GFXCLK];
 		break;
 	case METRICS_CURR_SOCCLK:
-		*value = metrics->CurrClock[PPCLK_SOCCLK];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_SOCCLK] :
+			metrics->CurrClock[PPCLK_SOCCLK];
 		break;
 	case METRICS_CURR_UCLK:
-		*value = metrics->CurrClock[PPCLK_UCLK];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_UCLK] :
+			metrics->CurrClock[PPCLK_UCLK];
 		break;
 	case METRICS_CURR_VCLK:
-		*value = metrics->CurrClock[PPCLK_VCLK_0];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_0] :
+			metrics->CurrClock[PPCLK_VCLK_0];
 		break;
 	case METRICS_CURR_VCLK1:
-		*value = metrics->CurrClock[PPCLK_VCLK_1];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_1] :
+			metrics->CurrClock[PPCLK_VCLK_1];
 		break;
 	case METRICS_CURR_DCLK:
-		*value = metrics->CurrClock[PPCLK_DCLK_0];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_0] :
+			metrics->CurrClock[PPCLK_DCLK_0];
 		break;
 	case METRICS_CURR_DCLK1:
-		*value = metrics->CurrClock[PPCLK_DCLK_1];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] :
+			metrics->CurrClock[PPCLK_DCLK_1];
 		break;
 	case METRICS_CURR_DCEFCLK:
-		*value = metrics->CurrClock[PPCLK_DCEFCLK];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCEFCLK] :
+			metrics->CurrClock[PPCLK_DCEFCLK];
 		break;
 	case METRICS_CURR_FCLK:
-		*value = metrics->CurrClock[PPCLK_FCLK];
+		*value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_FCLK] :
+			metrics->CurrClock[PPCLK_FCLK];
 		break;
 	case METRICS_AVERAGE_GFXCLK:
-		if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
-			*value = metrics->AverageGfxclkFrequencyPostDs;
+		average_gfx_activity = use_metrics_v2 ? metrics_v2->AverageGfxActivity :
+			metrics->AverageGfxActivity;
+		if (average_gfx_activity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
+			*value = use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs :
+				metrics->AverageGfxclkFrequencyPostDs;
 		else
-			*value = metrics->AverageGfxclkFrequencyPreDs;
+			*value = use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs :
+				metrics->AverageGfxclkFrequencyPreDs;
 		break;
 	case METRICS_AVERAGE_FCLK:
-		*value = metrics->AverageFclkFrequencyPostDs;
+		*value = use_metrics_v2 ? metrics_v2->AverageFclkFrequencyPostDs :
+			metrics->AverageFclkFrequencyPostDs;
 		break;
 	case METRICS_AVERAGE_UCLK:
-		*value = metrics->AverageUclkFrequencyPostDs;
+		*value = use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs :
+			metrics->AverageUclkFrequencyPostDs;
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
-		*value = metrics->AverageGfxActivity;
+		*value = use_metrics_v2 ? metrics_v2->AverageGfxActivity :
+			metrics->AverageGfxActivity;
 		break;
 	case METRICS_AVERAGE_MEMACTIVITY:
-		*value = metrics->AverageUclkActivity;
+		*value = use_metrics_v2 ? metrics_v2->AverageUclkActivity :
+			metrics->AverageUclkActivity;
 		break;
 	case METRICS_AVERAGE_SOCKETPOWER:
-		*value = metrics->AverageSocketPower << 8;
+		*value = use_metrics_v2 ? metrics_v2->AverageSocketPower << 8 :
+			metrics->AverageSocketPower << 8;
 		break;
 	case METRICS_TEMPERATURE_EDGE:
-		*value = metrics->TemperatureEdge *
+		*value = (use_metrics_v2 ? metrics_v2->TemperatureEdge : metrics->TemperatureEdge) *
 			SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_HOTSPOT:
-		*value = metrics->TemperatureHotspot *
+		*value = (use_metrics_v2 ? metrics_v2->TemperatureHotspot : metrics->TemperatureHotspot) *
 			SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_MEM:
-		*value = metrics->TemperatureMem *
+		*value = (use_metrics_v2 ? metrics_v2->TemperatureMem : metrics->TemperatureMem) *
 			SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_VRGFX:
-		*value = metrics->TemperatureVrGfx *
+		*value = (use_metrics_v2 ? metrics_v2->TemperatureVrGfx : metrics->TemperatureVrGfx) *
 			SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_VRSOC:
-		*value = metrics->TemperatureVrSoc *
+		*value = (use_metrics_v2 ? metrics_v2->TemperatureVrSoc : metrics->TemperatureVrSoc) *
 			SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_THROTTLER_STATUS:
-		*value = metrics->ThrottlerStatus;
+		*value = sienna_cichlid_get_throttler_status_locked(smu);
 		break;
 	case METRICS_CURR_FANSPEED:
-		*value = metrics->CurrFanSpeed;
+		*value = use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed;
 		break;
 	default:
 		*value = UINT_MAX;
@@ -1045,7 +1088,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 				if (ret)
 					goto print_clk_out;
 
-				size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 						cur_value == value ? "*" : "");
 			}
 		} else {
@@ -1067,7 +1110,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 			}
 
 			for (i = 0; i < count; i++) {
-				size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i],
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
 						cur_value  == freq_values[i] ? "*" : "");
 			}
 
@@ -1078,7 +1121,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
 		GET_PPTABLE_MEMBER(LclkFreq, &table_member);
 		for (i = 0; i < NUM_LINK_LEVELS; i++)
-			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
+			size += sysfs_emit_at(buf, size, "%d: %s %s %dMhz %s\n", i,
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 1) ? "5.0GT/s," :
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 2) ? "8.0GT/s," :
@@ -1101,8 +1144,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		if (!sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_GFXCLK_LIMITS))
 			break;
 
-		size += sprintf(buf + size, "OD_SCLK:\n");
-		size += sprintf(buf + size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
+		size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
+		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
 		break;
 
 	case SMU_OD_MCLK:
@@ -1112,8 +1155,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		if (!sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_UCLK_LIMITS))
 			break;
 
-		size += sprintf(buf + size, "OD_MCLK:\n");
-		size += sprintf(buf + size, "0: %uMhz\n1: %uMHz\n", od_table->UclkFmin, od_table->UclkFmax);
+		size += sysfs_emit_at(buf, size, "OD_MCLK:\n");
+		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMHz\n", od_table->UclkFmin, od_table->UclkFmax);
 		break;
 
 	case SMU_OD_VDDGFX_OFFSET:
@@ -1129,22 +1172,22 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		     (smu_version < 0x003a2900))
 			break;
 
-		size += sprintf(buf + size, "OD_VDDGFX_OFFSET:\n");
-		size += sprintf(buf + size, "%dmV\n", od_table->VddGfxOffset);
+		size += sysfs_emit_at(buf, size, "OD_VDDGFX_OFFSET:\n");
+		size += sysfs_emit_at(buf, size, "%dmV\n", od_table->VddGfxOffset);
 		break;
 
 	case SMU_OD_RANGE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
 
-		size = sprintf(buf, "%s:\n", "OD_RANGE");
+		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
 
 		if (sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_GFXCLK_LIMITS)) {
 			sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_GFXCLKFMIN,
 							    &min_value, NULL);
 			sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_GFXCLKFMAX,
 							    NULL, &max_value);
-			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 					min_value, max_value);
 		}
 
@@ -1153,7 +1196,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 							    &min_value, NULL);
 			sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_UCLKFMAX,
 							    NULL, &max_value);
-			size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "MCLK: %7uMhz %10uMhz\n",
 					min_value, max_value);
 		}
 		break;
@@ -1311,27 +1354,20 @@ static bool sienna_cichlid_is_dpm_running(struct smu_context *smu)
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
-static int sienna_cichlid_get_fan_speed_percent(struct smu_context *smu,
-						uint32_t *speed)
+static int sienna_cichlid_get_fan_speed_rpm(struct smu_context *smu,
+					    uint32_t *speed)
 {
-	int ret;
-	u32 rpm;
-
 	if (!speed)
 		return -EINVAL;
 
-	switch (smu_v11_0_get_fan_control_mode(smu)) {
-	case AMD_FAN_CTRL_AUTO:
-		ret = sienna_cichlid_get_smu_metrics_data(smu,
-							  METRICS_CURR_FANSPEED,
-							  &rpm);
-		if (!ret && smu->fan_max_rpm)
-			*speed = rpm * 100 / smu->fan_max_rpm;
-		return ret;
-	default:
-		*speed = smu->user_dpm_profile.fan_speed_percent;
-		return 0;
-	}
+	/*
+	 * For Sienna_Cichlid and later, the fan speed(rpm) reported
+	 * by pmfw is always trustable(even when the fan control feature
+	 * disabled or 0 RPM kicked in).
+	 */
+	return sienna_cichlid_get_smu_metrics_data(smu,
+						   METRICS_CURR_FANSPEED,
+						   speed);
 }
 
 static int sienna_cichlid_get_fan_parameters(struct smu_context *smu)
@@ -1376,7 +1412,7 @@ static int sienna_cichlid_get_power_profile_mode(struct smu_context *smu, char *
 	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+	size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
 
@@ -1396,10 +1432,10 @@ static int sienna_cichlid_get_power_profile_mode(struct smu_context *smu, char *
 			return result;
 		}
 
-		size += sprintf(buf + size, "%2d %14s%s:\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s:\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			0,
 			"GFXCLK",
@@ -1413,7 +1449,7 @@ static int sienna_cichlid_get_power_profile_mode(struct smu_context *smu, char *
 			activity_monitor->Gfx_PD_Data_error_coeff,
 			activity_monitor->Gfx_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			1,
 			"SOCCLK",
@@ -1427,7 +1463,7 @@ static int sienna_cichlid_get_power_profile_mode(struct smu_context *smu, char *
 			activity_monitor->Fclk_PD_Data_error_coeff,
 			activity_monitor->Fclk_PD_Data_error_rate_coeff);
 
-		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+		size += sysfs_emit_at(buf, size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
 			" ",
 			2,
 			"MEMLK",
@@ -1910,18 +1946,29 @@ static int sienna_cichlid_set_default_od_settings(struct smu_context *smu)
 		(OverDriveTable_t *)smu->smu_table.overdrive_table;
 	OverDriveTable_t *boot_od_table =
 		(OverDriveTable_t *)smu->smu_table.boot_overdrive_table;
+	OverDriveTable_t *user_od_table =
+		(OverDriveTable_t *)smu->smu_table.user_overdrive_table;
 	int ret = 0;
 
+	/*
+	 * For S3/S4/Runpm resume, no need to setup those overdrive tables again as
+	 *   - either they already have the default OD settings got during cold bootup
+	 *   - or they have some user customized OD settings which cannot be overwritten
+	 */
+	if (smu->adev->in_suspend)
+		return 0;
+
 	ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE,
-				   0, (void *)od_table, false);
+				   0, (void *)boot_od_table, false);
 	if (ret) {
 		dev_err(smu->adev->dev, "Failed to get overdrive table!\n");
 		return ret;
 	}
 
-	memcpy(boot_od_table, od_table, sizeof(OverDriveTable_t));
+	sienna_cichlid_dump_od_table(smu, boot_od_table);
 
-	sienna_cichlid_dump_od_table(smu, od_table);
+	memcpy(od_table, boot_od_table, sizeof(OverDriveTable_t));
+	memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t));
 
 	return 0;
 }
@@ -2084,13 +2131,20 @@ static int sienna_cichlid_od_edit_dpm_table(struct smu_context *smu,
 		fallthrough;
 
 	case PP_OD_COMMIT_DPM_TABLE:
-		sienna_cichlid_dump_od_table(smu, od_table);
+		if (memcmp(od_table, table_context->user_overdrive_table, sizeof(OverDriveTable_t))) {
+			sienna_cichlid_dump_od_table(smu, od_table);
+			ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)od_table, true);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to import overdrive table!\n");
+				return ret;
+			}
+			memcpy(table_context->user_overdrive_table, od_table, sizeof(OverDriveTable_t));
+			smu->user_dpm_profile.user_od = true;
 
-		ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE,
-					   0, (void *)od_table, true);
-		if (ret) {
-			dev_err(smu->adev->dev, "Failed to import overdrive table!\n");
-			return ret;
+			if (!memcmp(table_context->user_overdrive_table,
+				    table_context->boot_overdrive_table,
+				    sizeof(OverDriveTable_t)))
+				smu->user_dpm_profile.user_od = false;
 		}
 		break;
 
@@ -3441,197 +3495,77 @@ static void sienna_cichlid_dump_pptable(struct smu_context *smu)
 	dev_info(smu->adev->dev, "MmHubPadding[7] = 0x%x\n", pptable->MmHubPadding[7]);
 }
 
-static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t  *req, bool write,
-				  uint8_t address, uint32_t numbytes,
-				  uint8_t *data)
-{
-	int i;
-
-	req->I2CcontrollerPort = 1;
-	req->I2CSpeed = 2;
-	req->SlaveAddress = address;
-	req->NumCmds = numbytes;
-
-	for (i = 0; i < numbytes; i++) {
-		SwI2cCmd_t *cmd =  &req->SwI2cCmds[i];
-
-		/* First 2 bytes are always write for lower 2b EEPROM address */
-		if (i < 2)
-			cmd->CmdConfig = CMDCONFIG_READWRITE_MASK;
-		else
-			cmd->CmdConfig = write ? CMDCONFIG_READWRITE_MASK : 0;
-
-
-		/* Add RESTART for read  after address filled */
-		cmd->CmdConfig |= (i == 2 && !write) ? CMDCONFIG_RESTART_MASK : 0;
-
-		/* Add STOP in the end */
-		cmd->CmdConfig |= (i == (numbytes - 1)) ? CMDCONFIG_STOP_MASK : 0;
-
-		/* Fill with data regardless if read or write to simplify code */
-		cmd->ReadWriteData = data[i];
-	}
-}
-
-static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control,
-					       uint8_t address,
-					       uint8_t *data,
-					       uint32_t numbytes)
+static int sienna_cichlid_i2c_xfer(struct i2c_adapter *i2c_adap,
+				   struct i2c_msg *msg, int num_msgs)
 {
-	uint32_t  i, ret = 0;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_device *adev = to_amdgpu_device(i2c_adap);
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
 	struct smu_table *table = &smu_table->driver_table;
+	SwI2cRequest_t *req, *res = (SwI2cRequest_t *)table->cpu_addr;
+	int i, j, r, c;
+	u16 dir;
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
-	}
-
-	memset(&req, 0, sizeof(req));
-	sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data);
-
-	mutex_lock(&adev->smu.mutex);
-	/* Now read data starting with that address */
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req,
-					true);
-	mutex_unlock(&adev->smu.mutex);
-
-	if (!ret) {
-		SwI2cRequest_t *res = (SwI2cRequest_t *)table->cpu_addr;
-
-		/* Assume SMU  fills res.SwI2cCmds[i].Data with read bytes */
-		for (i = 0; i < numbytes; i++)
-			data[i] = res->SwI2cCmds[i].ReadWriteData;
-
-		dev_dbg(adev->dev, "sienna_cichlid_i2c_read_data, address = %x, bytes = %d, data :",
-				  (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-	} else
-		dev_err(adev->dev, "sienna_cichlid_i2c_read_data - error occurred :%x", ret);
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
 
-	return ret;
-}
+	req->I2CcontrollerPort = 1;
+	req->I2CSpeed = I2C_SPEED_FAST_400K;
+	req->SlaveAddress = msg[0].addr << 1; /* wants an 8-bit address */
+	dir = msg[0].flags & I2C_M_RD;
+
+	for (c = i = 0; i < num_msgs; i++) {
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &req->SwI2cCmds[c];
+
+			if (!(msg[i].flags & I2C_M_RD)) {
+				/* write */
+				cmd->CmdConfig |= CMDCONFIG_READWRITE_MASK;
+				cmd->ReadWriteData = msg[i].buf[j];
+			}
 
-static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control,
-						uint8_t address,
-						uint8_t *data,
-						uint32_t numbytes)
-{
-	uint32_t ret;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+			if ((dir ^ msg[i].flags) & I2C_M_RD) {
+				/* The direction changes.
+				 */
+				dir = msg[i].flags & I2C_M_RD;
+				cmd->CmdConfig |= CMDCONFIG_RESTART_MASK;
+			}
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
+			req->NumCmds++;
+
+			/*
+			 * Insert STOP if we are at the last byte of either last
+			 * message for the transaction or the client explicitly
+			 * requires a STOP at this particular message.
+			 */
+			if ((j == msg[i].len - 1) &&
+			    ((i == num_msgs - 1) || (msg[i].flags & I2C_M_STOP))) {
+				cmd->CmdConfig &= ~CMDCONFIG_RESTART_MASK;
+				cmd->CmdConfig |= CMDCONFIG_STOP_MASK;
+			}
+		}
 	}
-
-	memset(&req, 0, sizeof(req));
-	sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data);
-
 	mutex_lock(&adev->smu.mutex);
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, true);
+	r = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, req, true);
 	mutex_unlock(&adev->smu.mutex);
+	if (r)
+		goto fail;
 
-	if (!ret) {
-		dev_dbg(adev->dev, "sienna_cichlid_i2c_write(), address = %x, bytes = %d , data: ",
-					 (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-		/*
-		 * According to EEPROM spec there is a MAX of 10 ms required for
-		 * EEPROM to flush internal RX buffer after STOP was issued at the
-		 * end of write transaction. During this time the EEPROM will not be
-		 * responsive to any more commands - so wait a bit more.
-		 */
-		msleep(10);
-
-	} else
-		dev_err(adev->dev, "sienna_cichlid_i2c_write- error occurred :%x", ret);
-
-	return ret;
-}
-
-static int sienna_cichlid_i2c_xfer(struct i2c_adapter *i2c_adap,
-			      struct i2c_msg *msgs, int num)
-{
-	uint32_t  i, j, ret, data_size, data_chunk_size, next_eeprom_addr = 0;
-	uint8_t *data_ptr, data_chunk[MAX_SW_I2C_COMMANDS] = { 0 };
-
-	for (i = 0; i < num; i++) {
-		/*
-		 * SMU interface allows at most MAX_SW_I2C_COMMANDS bytes of data at
-		 * once and hence the data needs to be spliced into chunks and sent each
-		 * chunk separately
-		 */
-		data_size = msgs[i].len - 2;
-		data_chunk_size = MAX_SW_I2C_COMMANDS - 2;
-		next_eeprom_addr = (msgs[i].buf[0] << 8 & 0xff00) | (msgs[i].buf[1] & 0xff);
-		data_ptr = msgs[i].buf + 2;
-
-		for (j = 0; j < data_size / data_chunk_size; j++) {
-			/* Insert the EEPROM dest addess, bits 0-15 */
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = sienna_cichlid_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, MAX_SW_I2C_COMMANDS);
-
-				memcpy(data_ptr, data_chunk + 2, data_chunk_size);
-			} else {
-
-				memcpy(data_chunk + 2, data_ptr, data_chunk_size);
-
-				ret = sienna_cichlid_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, MAX_SW_I2C_COMMANDS);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
-
-			next_eeprom_addr += data_chunk_size;
-			data_ptr += data_chunk_size;
+	for (c = i = 0; i < num_msgs; i++) {
+		if (!(msg[i].flags & I2C_M_RD)) {
+			c += msg[i].len;
+			continue;
 		}
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &res->SwI2cCmds[c];
 
-		if (data_size % data_chunk_size) {
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = sienna_cichlid_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, (data_size % data_chunk_size) + 2);
-
-				memcpy(data_ptr, data_chunk + 2, data_size % data_chunk_size);
-			} else {
-				memcpy(data_chunk + 2, data_ptr, data_size % data_chunk_size);
-
-				ret = sienna_cichlid_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, (data_size % data_chunk_size) + 2);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
+			msg[i].buf[j] = cmd->ReadWriteData;
 		}
 	}
-
+	r = num_msgs;
 fail:
-	return num;
+	kfree(req);
+	return r;
 }
 
 static u32 sienna_cichlid_i2c_func(struct i2c_adapter *adap)
@@ -3645,16 +3579,25 @@ static const struct i2c_algorithm sienna_cichlid_i2c_algo = {
 	.functionality = sienna_cichlid_i2c_func,
 };
 
+static const struct i2c_adapter_quirks sienna_cichlid_i2c_control_quirks = {
+	.flags = I2C_AQ_COMB | I2C_AQ_COMB_SAME_ADDR | I2C_AQ_NO_ZERO_LEN,
+	.max_read_len  = MAX_SW_I2C_COMMANDS,
+	.max_write_len = MAX_SW_I2C_COMMANDS,
+	.max_comb_1st_msg_len = 2,
+	.max_comb_2nd_msg_len = MAX_SW_I2C_COMMANDS - 2,
+};
+
 static int sienna_cichlid_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
 	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
+	control->class = I2C_CLASS_HWMON;
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &sienna_cichlid_i2c_algo;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
+	control->quirks = &sienna_cichlid_i2c_control_quirks;
 
 	res = i2c_add_adapter(control);
 	if (res)
@@ -3677,65 +3620,94 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu,
 	SmuMetricsExternal_t metrics_external;
 	SmuMetrics_t *metrics =
 		&(metrics_external.SmuMetrics);
+	SmuMetrics_V2_t *metrics_v2 =
+		&(metrics_external.SmuMetrics_V2);
 	struct amdgpu_device *adev = smu->adev;
-	uint32_t smu_version;
+	bool use_metrics_v2 = ((adev->asic_type == CHIP_SIENNA_CICHLID) &&
+		(smu->smc_fw_version >= 0x3A4300)) ? true : false;
+	uint16_t average_gfx_activity;
 	int ret = 0;
 
-	ret = smu_cmn_get_metrics_table(smu,
-					&metrics_external,
-					true);
-	if (ret)
+	mutex_lock(&smu->metrics_lock);
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       &metrics_external,
+					       true);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
 		return ret;
+	}
 
 	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3);
 
-	gpu_metrics->temperature_edge = metrics->TemperatureEdge;
-	gpu_metrics->temperature_hotspot = metrics->TemperatureHotspot;
-	gpu_metrics->temperature_mem = metrics->TemperatureMem;
-	gpu_metrics->temperature_vrgfx = metrics->TemperatureVrGfx;
-	gpu_metrics->temperature_vrsoc = metrics->TemperatureVrSoc;
-	gpu_metrics->temperature_vrmem = metrics->TemperatureVrMem0;
-
-	gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity;
-	gpu_metrics->average_umc_activity = metrics->AverageUclkActivity;
-	gpu_metrics->average_mm_activity = metrics->VcnActivityPercentage;
-
-	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
-
-	if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
-		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
+	gpu_metrics->temperature_edge =
+		use_metrics_v2 ? metrics_v2->TemperatureEdge : metrics->TemperatureEdge;
+	gpu_metrics->temperature_hotspot =
+		use_metrics_v2 ? metrics_v2->TemperatureHotspot : metrics->TemperatureHotspot;
+	gpu_metrics->temperature_mem =
+		use_metrics_v2 ? metrics_v2->TemperatureMem : metrics->TemperatureMem;
+	gpu_metrics->temperature_vrgfx =
+		use_metrics_v2 ? metrics_v2->TemperatureVrGfx : metrics->TemperatureVrGfx;
+	gpu_metrics->temperature_vrsoc =
+		use_metrics_v2 ? metrics_v2->TemperatureVrSoc : metrics->TemperatureVrSoc;
+	gpu_metrics->temperature_vrmem =
+		use_metrics_v2 ? metrics_v2->TemperatureVrMem0 : metrics->TemperatureVrMem0;
+
+	gpu_metrics->average_gfx_activity =
+		use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity;
+	gpu_metrics->average_umc_activity =
+		use_metrics_v2 ? metrics_v2->AverageUclkActivity : metrics->AverageUclkActivity;
+	gpu_metrics->average_mm_activity =
+		use_metrics_v2 ? metrics_v2->VcnActivityPercentage : metrics->VcnActivityPercentage;
+
+	gpu_metrics->average_socket_power =
+		use_metrics_v2 ? metrics_v2->AverageSocketPower : metrics->AverageSocketPower;
+	gpu_metrics->energy_accumulator =
+		use_metrics_v2 ? metrics_v2->EnergyAccumulator : metrics->EnergyAccumulator;
+
+	average_gfx_activity = use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity;
+	if (average_gfx_activity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
+		gpu_metrics->average_gfxclk_frequency =
+			use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs : metrics->AverageGfxclkFrequencyPostDs;
 	else
-		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPreDs;
-	gpu_metrics->average_uclk_frequency = metrics->AverageUclkFrequencyPostDs;
-	gpu_metrics->average_vclk0_frequency = metrics->AverageVclk0Frequency;
-	gpu_metrics->average_dclk0_frequency = metrics->AverageDclk0Frequency;
-	gpu_metrics->average_vclk1_frequency = metrics->AverageVclk1Frequency;
-	gpu_metrics->average_dclk1_frequency = metrics->AverageDclk1Frequency;
-
-	gpu_metrics->current_gfxclk = metrics->CurrClock[PPCLK_GFXCLK];
-	gpu_metrics->current_socclk = metrics->CurrClock[PPCLK_SOCCLK];
-	gpu_metrics->current_uclk = metrics->CurrClock[PPCLK_UCLK];
-	gpu_metrics->current_vclk0 = metrics->CurrClock[PPCLK_VCLK_0];
-	gpu_metrics->current_dclk0 = metrics->CurrClock[PPCLK_DCLK_0];
-	gpu_metrics->current_vclk1 = metrics->CurrClock[PPCLK_VCLK_1];
-	gpu_metrics->current_dclk1 = metrics->CurrClock[PPCLK_DCLK_1];
-
-	gpu_metrics->throttle_status = metrics->ThrottlerStatus;
+		gpu_metrics->average_gfxclk_frequency =
+			use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs : metrics->AverageGfxclkFrequencyPreDs;
+	gpu_metrics->average_uclk_frequency =
+		use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs : metrics->AverageUclkFrequencyPostDs;
+	gpu_metrics->average_vclk0_frequency =
+		use_metrics_v2 ? metrics_v2->AverageVclk0Frequency : metrics->AverageVclk0Frequency;
+	gpu_metrics->average_dclk0_frequency =
+		use_metrics_v2 ? metrics_v2->AverageDclk0Frequency : metrics->AverageDclk0Frequency;
+	gpu_metrics->average_vclk1_frequency =
+		use_metrics_v2 ? metrics_v2->AverageVclk1Frequency : metrics->AverageVclk1Frequency;
+	gpu_metrics->average_dclk1_frequency =
+		use_metrics_v2 ? metrics_v2->AverageDclk1Frequency : metrics->AverageDclk1Frequency;
+
+	gpu_metrics->current_gfxclk =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_GFXCLK] : metrics->CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_SOCCLK] : metrics->CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_UCLK] : metrics->CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_0] : metrics->CurrClock[PPCLK_VCLK_0];
+	gpu_metrics->current_dclk0 =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_0] : metrics->CurrClock[PPCLK_DCLK_0];
+	gpu_metrics->current_vclk1 =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_1] : metrics->CurrClock[PPCLK_VCLK_1];
+	gpu_metrics->current_dclk1 =
+		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1];
+
+	gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu);
 	gpu_metrics->indep_throttle_status =
-			smu_cmn_get_indep_throttler_status(metrics->ThrottlerStatus,
+			smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status,
 							   sienna_cichlid_throttler_map);
 
-	gpu_metrics->current_fan_speed = metrics->CurrFanSpeed;
+	gpu_metrics->current_fan_speed = use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed;
 
-	ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
-	if (ret)
-		return ret;
-
-	if (((adev->asic_type == CHIP_SIENNA_CICHLID) && smu_version > 0x003A1E00) ||
-	      ((adev->asic_type == CHIP_NAVY_FLOUNDER) && smu_version > 0x00410400)) {
-		gpu_metrics->pcie_link_width = metrics->PcieWidth;
-		gpu_metrics->pcie_link_speed = link_speed[metrics->PcieRate];
+	if (((adev->asic_type == CHIP_SIENNA_CICHLID) && smu->smc_fw_version > 0x003A1E00) ||
+	      ((adev->asic_type == CHIP_NAVY_FLOUNDER) && smu->smc_fw_version > 0x00410400)) {
+		gpu_metrics->pcie_link_width = use_metrics_v2 ? metrics_v2->PcieWidth : metrics->PcieWidth;
+		gpu_metrics->pcie_link_speed = link_speed[use_metrics_v2 ? metrics_v2->PcieRate : metrics->PcieRate];
 	} else {
 		gpu_metrics->pcie_link_width =
 				smu_v11_0_get_current_pcie_link_width(smu);
@@ -3743,6 +3715,8 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu,
 				smu_v11_0_get_current_pcie_link_speed(smu);
 	}
 
+	mutex_unlock(&smu->metrics_lock);
+
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
 	*table = (void *)gpu_metrics;
@@ -3878,7 +3852,8 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_config_changed = sienna_cichlid_display_config_changed,
 	.notify_smc_display_config = sienna_cichlid_notify_smc_display_config,
 	.is_dpm_running = sienna_cichlid_is_dpm_running,
-	.get_fan_speed_percent = sienna_cichlid_get_fan_speed_percent,
+	.get_fan_speed_pwm = smu_v11_0_get_fan_speed_pwm,
+	.get_fan_speed_rpm = sienna_cichlid_get_fan_speed_rpm,
 	.get_power_profile_mode = sienna_cichlid_get_power_profile_mode,
 	.set_power_profile_mode = sienna_cichlid_set_power_profile_mode,
 	.set_watermarks_table = sienna_cichlid_set_watermarks_table,
@@ -3921,7 +3896,8 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_pwm = smu_v11_0_set_fan_speed_pwm,
+	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
 	.register_irq_handler = smu_v11_0_register_irq_handler,
@@ -3938,6 +3914,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.set_default_od_settings = sienna_cichlid_set_default_od_settings,
 	.od_edit_dpm_table = sienna_cichlid_od_edit_dpm_table,
+	.restore_user_od_settings = smu_v11_0_restore_user_od_settings,
 	.run_btc = sienna_cichlid_run_btc,
 	.set_power_source = smu_v11_0_set_power_source,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 0a5d46ac9ccd..87b055466a33 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -266,6 +266,9 @@ int smu_v11_0_check_fw_version(struct smu_context *smu)
 	case CHIP_BEIGE_GOBY:
 		smu->smc_driver_if_version = SMU11_DRIVER_IF_VERSION_Beige_Goby;
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		smu->smc_driver_if_version = SMU11_DRIVER_IF_VERSION_Cyan_Skillfish;
+		break;
 	default:
 		dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type);
 		smu->smc_driver_if_version = SMU11_DRIVER_IF_VERSION_INV;
@@ -422,10 +425,20 @@ int smu_v11_0_init_smc_tables(struct smu_context *smu)
 			ret = -ENOMEM;
 			goto err3_out;
 		}
+
+		smu_table->user_overdrive_table =
+			kzalloc(tables[SMU_TABLE_OVERDRIVE].size, GFP_KERNEL);
+		if (!smu_table->user_overdrive_table) {
+			ret = -ENOMEM;
+			goto err4_out;
+		}
+
 	}
 
 	return 0;
 
+err4_out:
+	kfree(smu_table->boot_overdrive_table);
 err3_out:
 	kfree(smu_table->overdrive_table);
 err2_out:
@@ -442,12 +455,14 @@ int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
 
 	kfree(smu_table->gpu_metrics_table);
+	kfree(smu_table->user_overdrive_table);
 	kfree(smu_table->boot_overdrive_table);
 	kfree(smu_table->overdrive_table);
 	kfree(smu_table->max_sustainable_clocks);
 	kfree(smu_table->driver_pptable);
 	kfree(smu_table->clocks_table);
 	smu_table->gpu_metrics_table = NULL;
+	smu_table->user_overdrive_table = NULL;
 	smu_table->boot_overdrive_table = NULL;
 	smu_table->overdrive_table = NULL;
 	smu_table->max_sustainable_clocks = NULL;
@@ -1185,17 +1200,13 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode)
 }
 
 int
-smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
+smu_v11_0_set_fan_speed_pwm(struct smu_context *smu, uint32_t speed)
 {
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t duty100, duty;
 	uint64_t tmp64;
 
-	if (speed > 100)
-		speed = 100;
-
-	if (smu_v11_0_auto_fan_control(smu, 0))
-		return -EINVAL;
+	speed = MIN(speed, 255);
 
 	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
 				CG_FDO_CTRL1, FMAX_DUTY100);
@@ -1203,7 +1214,7 @@ smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 		return -EINVAL;
 
 	tmp64 = (uint64_t)speed * duty100;
-	do_div(tmp64, 100);
+	do_div(tmp64, 255);
 	duty = (uint32_t)tmp64;
 
 	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
@@ -1213,6 +1224,99 @@ smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
 }
 
+int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
+				uint32_t speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	/*
+	 * crystal_clock_freq used for fan speed rpm calculation is
+	 * always 25Mhz. So, hardcode it as 2500(in 10K unit).
+	 */
+	uint32_t crystal_clock_freq = 2500;
+	uint32_t tach_period;
+
+	/*
+	 * To prevent from possible overheat, some ASICs may have requirement
+	 * for minimum fan speed:
+	 * - For some NV10 SKU, the fan speed cannot be set lower than
+	 *   700 RPM.
+	 * - For some Sienna Cichlid SKU, the fan speed cannot be set
+	 *   lower than 500 RPM.
+	 */
+	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
+	WREG32_SOC15(THM, 0, mmCG_TACH_CTRL,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
+				   CG_TACH_CTRL, TARGET_PERIOD,
+				   tach_period));
+
+	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC_RPM);
+}
+
+int smu_v11_0_get_fan_speed_pwm(struct smu_context *smu,
+				uint32_t *speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
+
+	/*
+	 * For pre Sienna Cichlid ASICs, the 0 RPM may be not correctly
+	 * detected via register retrieving. To workaround this, we will
+	 * report the fan speed as 0 PWM if user just requested such.
+	 */
+	if ((smu->user_dpm_profile.flags & SMU_CUSTOM_FAN_SPEED_PWM)
+	     && !smu->user_dpm_profile.fan_speed_pwm) {
+		*speed = 0;
+		return 0;
+	}
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS),
+				CG_THERMAL_STATUS, FDO_PWM_DUTY);
+	if (!duty100)
+		return -EINVAL;
+
+	tmp64 = (uint64_t)duty * 255;
+	do_div(tmp64, duty100);
+	*speed = MIN((uint32_t)tmp64, 255);
+
+	return 0;
+}
+
+int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu,
+				uint32_t *speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t crystal_clock_freq = 2500;
+	uint32_t tach_status;
+	uint64_t tmp64;
+
+	/*
+	 * For pre Sienna Cichlid ASICs, the 0 RPM may be not correctly
+	 * detected via register retrieving. To workaround this, we will
+	 * report the fan speed as 0 RPM if user just requested such.
+	 */
+	if ((smu->user_dpm_profile.flags & SMU_CUSTOM_FAN_SPEED_RPM)
+	     && !smu->user_dpm_profile.fan_speed_rpm) {
+		*speed = 0;
+		return 0;
+	}
+
+	tmp64 = (uint64_t)crystal_clock_freq * 60 * 10000;
+
+	tach_status = RREG32_SOC15(THM, 0, mmCG_TACH_STATUS);
+	if (tach_status) {
+		do_div(tmp64, tach_status);
+		*speed = (uint32_t)tmp64;
+	} else {
+		dev_warn_once(adev->dev, "Got zero output on CG_TACH_STATUS reading!\n");
+		*speed = 0;
+	}
+
+	return 0;
+}
+
 int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode)
@@ -1221,7 +1325,9 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		ret = smu_v11_0_set_fan_speed_percent(smu, 100);
+		ret = smu_v11_0_auto_fan_control(smu, 0);
+		if (!ret)
+			ret = smu_v11_0_set_fan_speed_pwm(smu, 255);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		ret = smu_v11_0_auto_fan_control(smu, 0);
@@ -2101,3 +2207,16 @@ int smu_v11_0_deep_sleep_control(struct smu_context *smu,
 
 	return ret;
 }
+
+int smu_v11_0_restore_user_od_settings(struct smu_context *smu)
+{
+	struct smu_table_context *table_context = &smu->smu_table;
+	void *user_od_table = table_context->user_overdrive_table;
+	int ret = 0;
+
+	ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)user_od_table, true);
+	if (ret)
+		dev_err(smu->adev->dev, "Failed to import overdrive table!\n");
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index bcaaa086fc2f..6eb50b05a33c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -592,28 +592,28 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 			(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		}
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 			(smu->cpu_actual_soft_max_freq > 0) ? smu->cpu_actual_soft_max_freq : smu->cpu_default_soft_max_freq);
 		}
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "%s:\n", "OD_RANGE");
-			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
-			size += sprintf(buf + size, "CCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
 				smu->cpu_default_soft_min_freq, smu->cpu_default_soft_max_freq);
 		}
 		break;
@@ -656,14 +656,14 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 				return ret;
 			if (!value)
 				continue;
-			size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 					cur_value == value ? "*" : "");
 			if (cur_value == value)
 				cur_value_match_level = true;
 		}
 
 		if (!cur_value_match_level)
-			size += sprintf(buf + size, "   %uMhz *\n", cur_value);
+			size += sysfs_emit_at(buf, size, "   %uMhz *\n", cur_value);
 		break;
 	default:
 		break;
@@ -691,28 +691,28 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 			(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		}
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
-			size += sprintf(buf + size, "0: %10uMhz\n",
+			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
-			size += sprintf(buf + size, "1: %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 			(smu->cpu_actual_soft_max_freq > 0) ? smu->cpu_actual_soft_max_freq : smu->cpu_default_soft_max_freq);
 		}
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sprintf(buf, "%s:\n", "OD_RANGE");
-			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
-			size += sprintf(buf + size, "CCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
 				smu->cpu_default_soft_min_freq, smu->cpu_default_soft_max_freq);
 		}
 		break;
@@ -755,14 +755,14 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 				return ret;
 			if (!value)
 				continue;
-			size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 					cur_value == value ? "*" : "");
 			if (cur_value == value)
 				cur_value_match_level = true;
 		}
 
 		if (!cur_value_match_level)
-			size += sprintf(buf + size, "   %uMhz *\n", cur_value);
+			size += sysfs_emit_at(buf, size, "   %uMhz *\n", cur_value);
 		break;
 	default:
 		break;
@@ -1035,7 +1035,7 @@ static int vangogh_get_power_profile_mode(struct smu_context *smu,
 		if (workload_type < 0)
 			continue;
 
-		size += sprintf(buf + size, "%2d %14s%s\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 9a9c24a6ec35..b39138041141 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -510,16 +510,16 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 						0, &max);
 			if (ret)
 				return ret;
-			size += sprintf(buf + size, "OD_RANGE\nSCLK: %10uMhz %10uMhz\n", min, max);
+			size += sysfs_emit_at(buf, size, "OD_RANGE\nSCLK: %10uMhz %10uMhz\n", min, max);
 		}
 		break;
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
 			min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
 			max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
-			size += sprintf(buf + size, "OD_SCLK\n");
-			size += sprintf(buf + size, "0:%10uMhz\n", min);
-			size += sprintf(buf + size, "1:%10uMhz\n", max);
+			size += sysfs_emit_at(buf, size, "OD_SCLK\n");
+			size += sysfs_emit_at(buf, size, "0:%10uMhz\n", min);
+			size += sysfs_emit_at(buf, size, "1:%10uMhz\n", max);
 		}
 		break;
 	case SMU_GFXCLK:
@@ -536,12 +536,12 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 			else
 				i = 1;
 
-			size += sprintf(buf + size, "0: %uMhz %s\n", min,
+			size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
 					i == 0 ? "*" : "");
-			size += sprintf(buf + size, "1: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
 					i == 1 ? cur_value : RENOIR_UMD_PSTATE_GFXCLK,
 					i == 1 ? "*" : "");
-			size += sprintf(buf + size, "2: %uMhz %s\n", max,
+			size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
 					i == 2 ? "*" : "");
 		}
 		return size;
@@ -588,14 +588,14 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 				return ret;
 			if (!value)
 				continue;
-			size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 					cur_value == value ? "*" : "");
 			if (cur_value == value)
 				cur_value_match_level = true;
 		}
 
 		if (!cur_value_match_level)
-			size += sprintf(buf + size, "   %uMhz *\n", cur_value);
+			size += sysfs_emit_at(buf, size, "   %uMhz *\n", cur_value);
 
 		break;
 	default:
@@ -1118,7 +1118,7 @@ static int renoir_get_power_profile_mode(struct smu_context *smu,
 		if (workload_type < 0)
 			continue;
 
-		size += sprintf(buf + size, "%2d %14s%s\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index cb5485cf243f..ec8c30daf31c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -90,8 +90,8 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT
 	MSG_MAP(GetDriverIfVersion,		     PPSMC_MSG_GetDriverIfVersion,		1),
 	MSG_MAP(EnableAllSmuFeatures,		     PPSMC_MSG_EnableAllSmuFeatures,		0),
 	MSG_MAP(DisableAllSmuFeatures,		     PPSMC_MSG_DisableAllSmuFeatures,		0),
-	MSG_MAP(GetEnabledSmuFeaturesLow,	     PPSMC_MSG_GetEnabledSmuFeaturesLow,	0),
-	MSG_MAP(GetEnabledSmuFeaturesHigh,	     PPSMC_MSG_GetEnabledSmuFeaturesHigh,	0),
+	MSG_MAP(GetEnabledSmuFeaturesLow,	     PPSMC_MSG_GetEnabledSmuFeaturesLow,	1),
+	MSG_MAP(GetEnabledSmuFeaturesHigh,	     PPSMC_MSG_GetEnabledSmuFeaturesHigh,	1),
 	MSG_MAP(SetDriverDramAddrHigh,		     PPSMC_MSG_SetDriverDramAddrHigh,		1),
 	MSG_MAP(SetDriverDramAddrLow,		     PPSMC_MSG_SetDriverDramAddrLow,		1),
 	MSG_MAP(SetToolsDramAddrHigh,		     PPSMC_MSG_SetToolsDramAddrHigh,		0),
@@ -150,20 +150,20 @@ static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = {
 };
 
 static const struct cmn2asic_mapping aldebaran_feature_mask_map[SMU_FEATURE_COUNT] = {
-	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_PREFETCHER_BIT, 		FEATURE_DATA_CALCULATIONS),
+	ALDEBARAN_FEA_MAP(SMU_FEATURE_DATA_CALCULATIONS_BIT, 		FEATURE_DATA_CALCULATIONS),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_GFXCLK_BIT, 			FEATURE_DPM_GFXCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_UCLK_BIT, 			FEATURE_DPM_UCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_SOCCLK_BIT, 			FEATURE_DPM_SOCCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_FCLK_BIT, 			FEATURE_DPM_FCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_LCLK_BIT, 			FEATURE_DPM_LCLK_BIT),
-	ALDEBARAN_FEA_MAP(SMU_FEATURE_XGMI_BIT, 				FEATURE_DPM_XGMI_BIT),
+	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_XGMI_BIT, 				FEATURE_DPM_XGMI_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DS_GFXCLK_BIT, 			FEATURE_DS_GFXCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DS_SOCCLK_BIT, 			FEATURE_DS_SOCCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DS_LCLK_BIT, 				FEATURE_DS_LCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DS_FCLK_BIT, 				FEATURE_DS_FCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DS_UCLK_BIT,				FEATURE_DS_UCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_GFX_SS_BIT, 				FEATURE_GFX_SS_BIT),
-	ALDEBARAN_FEA_MAP(SMU_FEATURE_VCN_PG_BIT, 				FEATURE_DPM_VCN_BIT),
+	ALDEBARAN_FEA_MAP(SMU_FEATURE_VCN_DPM_BIT, 				FEATURE_DPM_VCN_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_RSMU_SMN_CG_BIT, 			FEATURE_RSMU_SMN_CG_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_WAFL_CG_BIT, 				FEATURE_WAFL_CG_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_PPT_BIT, 					FEATURE_PPT_BIT),
@@ -735,14 +735,14 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 	uint32_t min_clk, max_clk;
 
 	if (amdgpu_ras_intr_triggered())
-		return snprintf(buf, PAGE_SIZE, "unavailable\n");
+		return sysfs_emit(buf, "unavailable\n");
 
 	dpm_context = smu_dpm->dpm_context;
 
 	switch (type) {
 
 	case SMU_OD_SCLK:
-		size = sprintf(buf, "%s:\n", "GFXCLK");
+		size = sysfs_emit(buf, "%s:\n", "GFXCLK");
 		fallthrough;
 	case SMU_SCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_GFXCLK, &now);
@@ -779,8 +779,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		 */
 		if (display_levels == clocks.num_levels) {
 			for (i = 0; i < clocks.num_levels; i++)
-				size += sprintf(
-					buf + size, "%d: %uMhz %s\n", i,
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i,
 					freq_values[i],
 					(clocks.num_levels == 1) ?
 						"*" :
@@ -790,14 +789,14 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 							 ""));
 		} else {
 			for (i = 0; i < display_levels; i++)
-				size += sprintf(buf + size, "%d: %uMhz %s\n", i,
+				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i,
 						freq_values[i], i == 1 ? "*" : "");
 		}
 
 		break;
 
 	case SMU_OD_MCLK:
-		size = sprintf(buf, "%s:\n", "MCLK");
+		size = sysfs_emit(buf, "%s:\n", "MCLK");
 		fallthrough;
 	case SMU_MCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_UCLK, &now);
@@ -814,7 +813,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, clocks.data[i].clocks_in_khz / 1000,
 					(clocks.num_levels == 1) ? "*" :
 					(aldebaran_freqs_in_same_level(
@@ -837,7 +836,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, clocks.data[i].clocks_in_khz / 1000,
 					(clocks.num_levels == 1) ? "*" :
 					(aldebaran_freqs_in_same_level(
@@ -860,7 +859,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, single_dpm_table->dpm_levels[i].value,
 					(clocks.num_levels == 1) ? "*" :
 					(aldebaran_freqs_in_same_level(
@@ -883,7 +882,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, single_dpm_table->dpm_levels[i].value,
 					(clocks.num_levels == 1) ? "*" :
 					(aldebaran_freqs_in_same_level(
@@ -906,7 +905,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		}
 
 		for (i = 0; i < single_dpm_table->count; i++)
-			size += sprintf(buf + size, "%d: %uMhz %s\n",
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
 					i, single_dpm_table->dpm_levels[i].value,
 					(clocks.num_levels == 1) ? "*" :
 					(aldebaran_freqs_in_same_level(
@@ -1194,8 +1193,19 @@ static int aldebaran_get_power_limit(struct smu_context *smu,
 	uint32_t power_limit = 0;
 	int ret;
 
-	if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT))
-		return -EINVAL;
+	if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) {
+		if (current_power_limit)
+			*current_power_limit = 0;
+		if (default_power_limit)
+			*default_power_limit = 0;
+		if (max_power_limit)
+			*max_power_limit = 0;
+
+		dev_warn(smu->adev->dev,
+			"PPT feature is not enabled, power values can't be fetched.");
+
+		return 0;
+	}
 
 	/* Valid power data is available only from primary die.
 	 * For secondary die show the value as 0.
@@ -1451,197 +1461,77 @@ static bool aldebaran_is_dpm_running(struct smu_context *smu)
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
-static void aldebaran_fill_i2c_req(SwI2cRequest_t  *req, bool write,
-				  uint8_t address, uint32_t numbytes,
-				  uint8_t *data)
-{
-	int i;
-
-	req->I2CcontrollerPort = 0;
-	req->I2CSpeed = 2;
-	req->SlaveAddress = address;
-	req->NumCmds = numbytes;
-
-	for (i = 0; i < numbytes; i++) {
-		SwI2cCmd_t *cmd =  &req->SwI2cCmds[i];
-
-		/* First 2 bytes are always write for lower 2b EEPROM address */
-		if (i < 2)
-			cmd->CmdConfig = CMDCONFIG_READWRITE_MASK;
-		else
-			cmd->CmdConfig = write ? CMDCONFIG_READWRITE_MASK : 0;
-
-
-		/* Add RESTART for read  after address filled */
-		cmd->CmdConfig |= (i == 2 && !write) ? CMDCONFIG_RESTART_MASK : 0;
-
-		/* Add STOP in the end */
-		cmd->CmdConfig |= (i == (numbytes - 1)) ? CMDCONFIG_STOP_MASK : 0;
-
-		/* Fill with data regardless if read or write to simplify code */
-		cmd->ReadWriteData = data[i];
-	}
-}
-
-static int aldebaran_i2c_read_data(struct i2c_adapter *control,
-					       uint8_t address,
-					       uint8_t *data,
-					       uint32_t numbytes)
+static int aldebaran_i2c_xfer(struct i2c_adapter *i2c_adap,
+			      struct i2c_msg *msg, int num_msgs)
 {
-	uint32_t  i, ret = 0;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_device *adev = to_amdgpu_device(i2c_adap);
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
 	struct smu_table *table = &smu_table->driver_table;
+	SwI2cRequest_t *req, *res = (SwI2cRequest_t *)table->cpu_addr;
+	int i, j, r, c;
+	u16 dir;
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
-	}
-
-	memset(&req, 0, sizeof(req));
-	aldebaran_fill_i2c_req(&req, false, address, numbytes, data);
-
-	mutex_lock(&adev->smu.mutex);
-	/* Now read data starting with that address */
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req,
-					true);
-	mutex_unlock(&adev->smu.mutex);
-
-	if (!ret) {
-		SwI2cRequest_t *res = (SwI2cRequest_t *)table->cpu_addr;
-
-		/* Assume SMU  fills res.SwI2cCmds[i].Data with read bytes */
-		for (i = 0; i < numbytes; i++)
-			data[i] = res->SwI2cCmds[i].ReadWriteData;
-
-		dev_dbg(adev->dev, "aldebaran_i2c_read_data, address = %x, bytes = %d, data :",
-				  (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-	} else
-		dev_err(adev->dev, "aldebaran_i2c_read_data - error occurred :%x", ret);
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
 
-	return ret;
-}
+	req->I2CcontrollerPort = 0;
+	req->I2CSpeed = I2C_SPEED_FAST_400K;
+	req->SlaveAddress = msg[0].addr << 1; /* wants an 8-bit address */
+	dir = msg[0].flags & I2C_M_RD;
+
+	for (c = i = 0; i < num_msgs; i++) {
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &req->SwI2cCmds[c];
+
+			if (!(msg[i].flags & I2C_M_RD)) {
+				/* write */
+				cmd->CmdConfig |= CMDCONFIG_READWRITE_MASK;
+				cmd->ReadWriteData = msg[i].buf[j];
+			}
 
-static int aldebaran_i2c_write_data(struct i2c_adapter *control,
-						uint8_t address,
-						uint8_t *data,
-						uint32_t numbytes)
-{
-	uint32_t ret;
-	SwI2cRequest_t req;
-	struct amdgpu_device *adev = to_amdgpu_device(control);
+			if ((dir ^ msg[i].flags) & I2C_M_RD) {
+				/* The direction changes.
+				 */
+				dir = msg[i].flags & I2C_M_RD;
+				cmd->CmdConfig |= CMDCONFIG_RESTART_MASK;
+			}
 
-	if (numbytes > MAX_SW_I2C_COMMANDS) {
-		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
-			numbytes, MAX_SW_I2C_COMMANDS);
-		return -EINVAL;
+			req->NumCmds++;
+
+			/*
+			 * Insert STOP if we are at the last byte of either last
+			 * message for the transaction or the client explicitly
+			 * requires a STOP at this particular message.
+			 */
+			if ((j == msg[i].len - 1) &&
+			    ((i == num_msgs - 1) || (msg[i].flags & I2C_M_STOP))) {
+				cmd->CmdConfig &= ~CMDCONFIG_RESTART_MASK;
+				cmd->CmdConfig |= CMDCONFIG_STOP_MASK;
+			}
+		}
 	}
-
-	memset(&req, 0, sizeof(req));
-	aldebaran_fill_i2c_req(&req, true, address, numbytes, data);
-
 	mutex_lock(&adev->smu.mutex);
-	ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, true);
+	r = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, req, true);
 	mutex_unlock(&adev->smu.mutex);
+	if (r)
+		goto fail;
 
-	if (!ret) {
-		dev_dbg(adev->dev, "aldebaran_i2c_write(), address = %x, bytes = %d , data: ",
-					 (uint16_t)address, numbytes);
-
-		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
-			       8, 1, data, numbytes, false);
-		/*
-		 * According to EEPROM spec there is a MAX of 10 ms required for
-		 * EEPROM to flush internal RX buffer after STOP was issued at the
-		 * end of write transaction. During this time the EEPROM will not be
-		 * responsive to any more commands - so wait a bit more.
-		 */
-		msleep(10);
-
-	} else
-		dev_err(adev->dev, "aldebaran_i2c_write- error occurred :%x", ret);
-
-	return ret;
-}
-
-static int aldebaran_i2c_xfer(struct i2c_adapter *i2c_adap,
-			      struct i2c_msg *msgs, int num)
-{
-	uint32_t  i, j, ret, data_size, data_chunk_size, next_eeprom_addr = 0;
-	uint8_t *data_ptr, data_chunk[MAX_SW_I2C_COMMANDS] = { 0 };
-
-	for (i = 0; i < num; i++) {
-		/*
-		 * SMU interface allows at most MAX_SW_I2C_COMMANDS bytes of data at
-		 * once and hence the data needs to be spliced into chunks and sent each
-		 * chunk separately
-		 */
-		data_size = msgs[i].len - 2;
-		data_chunk_size = MAX_SW_I2C_COMMANDS - 2;
-		next_eeprom_addr = (msgs[i].buf[0] << 8 & 0xff00) | (msgs[i].buf[1] & 0xff);
-		data_ptr = msgs[i].buf + 2;
-
-		for (j = 0; j < data_size / data_chunk_size; j++) {
-			/* Insert the EEPROM dest addess, bits 0-15 */
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = aldebaran_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, MAX_SW_I2C_COMMANDS);
-
-				memcpy(data_ptr, data_chunk + 2, data_chunk_size);
-			} else {
-
-				memcpy(data_chunk + 2, data_ptr, data_chunk_size);
-
-				ret = aldebaran_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, MAX_SW_I2C_COMMANDS);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
-
-			next_eeprom_addr += data_chunk_size;
-			data_ptr += data_chunk_size;
+	for (c = i = 0; i < num_msgs; i++) {
+		if (!(msg[i].flags & I2C_M_RD)) {
+			c += msg[i].len;
+			continue;
 		}
+		for (j = 0; j < msg[i].len; j++, c++) {
+			SwI2cCmd_t *cmd = &res->SwI2cCmds[c];
 
-		if (data_size % data_chunk_size) {
-			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
-			data_chunk[1] = (next_eeprom_addr & 0xff);
-
-			if (msgs[i].flags & I2C_M_RD) {
-				ret = aldebaran_i2c_read_data(i2c_adap,
-							     (uint8_t)msgs[i].addr,
-							     data_chunk, (data_size % data_chunk_size) + 2);
-
-				memcpy(data_ptr, data_chunk + 2, data_size % data_chunk_size);
-			} else {
-				memcpy(data_chunk + 2, data_ptr, data_size % data_chunk_size);
-
-				ret = aldebaran_i2c_write_data(i2c_adap,
-							      (uint8_t)msgs[i].addr,
-							      data_chunk, (data_size % data_chunk_size) + 2);
-			}
-
-			if (ret) {
-				num = -EIO;
-				goto fail;
-			}
+			msg[i].buf[j] = cmd->ReadWriteData;
 		}
 	}
-
+	r = num_msgs;
 fail:
-	return num;
+	kfree(req);
+	return r;
 }
 
 static u32 aldebaran_i2c_func(struct i2c_adapter *adap)
@@ -1655,6 +1545,14 @@ static const struct i2c_algorithm aldebaran_i2c_algo = {
 	.functionality = aldebaran_i2c_func,
 };
 
+static const struct i2c_adapter_quirks aldebaran_i2c_control_quirks = {
+	.flags = I2C_AQ_COMB | I2C_AQ_COMB_SAME_ADDR | I2C_AQ_NO_ZERO_LEN,
+	.max_read_len  = MAX_SW_I2C_COMMANDS,
+	.max_write_len = MAX_SW_I2C_COMMANDS,
+	.max_comb_1st_msg_len = 2,
+	.max_comb_2nd_msg_len = MAX_SW_I2C_COMMANDS - 2,
+};
+
 static int aldebaran_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
@@ -1665,6 +1563,7 @@ static int aldebaran_i2c_control_init(struct smu_context *smu, struct i2c_adapte
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &aldebaran_i2c_algo;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
+	control->quirks = &aldebaran_i2c_control_quirks;
 
 	res = i2c_add_adapter(control);
 	if (res)
@@ -1764,7 +1663,9 @@ static void aldebaran_log_thermal_throttling_event(struct smu_context *smu)
 
 	dev_warn(adev->dev, "WARN: GPU thermal throttling temperature reached, expect performance decrease. %s.\n",
 		 log_buf);
-	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev, throttler_status);
+	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev,
+		smu_cmn_get_indep_throttler_status(throttler_status,
+						   aldebaran_throttler_map));
 }
 
 static int aldebaran_get_current_pcie_link_speed(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index a421ba85bd6d..a0e50f23b1dd 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -85,6 +85,10 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
 	const struct common_firmware_header *header;
 	struct amdgpu_firmware_info *ucode = NULL;
 
+	/* doesn't need to load smu firmware in IOV mode */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	switch (adev->asic_type) {
 	case CHIP_ALDEBARAN:
 		chip_name = "aldebaran";
@@ -268,52 +272,86 @@ static int smu_v13_0_set_pptable_v2_1(struct smu_context *smu, void **table,
 	return 0;
 }
 
-int smu_v13_0_setup_pptable(struct smu_context *smu)
+static int smu_v13_0_get_pptable_from_vbios(struct smu_context *smu, void **table, uint32_t *size)
 {
 	struct amdgpu_device *adev = smu->adev;
-	const struct smc_firmware_header_v1_0 *hdr;
-	int ret, index;
-	uint32_t size = 0;
 	uint16_t atom_table_size;
 	uint8_t frev, crev;
-	void *table;
-	uint16_t version_major, version_minor;
+	int ret, index;
 
+	dev_info(adev->dev, "use vbios provided pptable\n");
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+					    powerplayinfo);
 
-	if (amdgpu_smu_pptable_id >= 0) {
-		smu->smu_table.boot_values.pp_table_id = amdgpu_smu_pptable_id;
-		dev_info(adev->dev, "override pptable id %d\n", amdgpu_smu_pptable_id);
-	}
+	ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev,
+					     (uint8_t **)table);
+	if (ret)
+		return ret;
+
+	if (size)
+		*size = atom_table_size;
+
+	return 0;
+}
+
+static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size,
+					       uint32_t pptable_id)
+{
+	const struct smc_firmware_header_v1_0 *hdr;
+	struct amdgpu_device *adev = smu->adev;
+	uint16_t version_major, version_minor;
+	int ret;
 
 	hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data;
+	if (!hdr)
+		return -EINVAL;
+
+	dev_info(adev->dev, "use driver provided pptable %d\n", pptable_id);
+
 	version_major = le16_to_cpu(hdr->header.header_version_major);
 	version_minor = le16_to_cpu(hdr->header.header_version_minor);
-	if (version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) {
-		dev_info(adev->dev, "use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id);
-		switch (version_minor) {
-		case 1:
-			ret = smu_v13_0_set_pptable_v2_1(smu, &table, &size,
-							 smu->smu_table.boot_values.pp_table_id);
-			break;
-		default:
-			ret = -EINVAL;
-			break;
-		}
-		if (ret)
-			return ret;
+	if (version_major != 2) {
+		dev_err(adev->dev, "Unsupported smu firmware version %d.%d\n",
+			version_major, version_minor);
+		return -EINVAL;
+	}
 
-	} else {
-		dev_info(adev->dev, "use vbios provided pptable\n");
-		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-						    powerplayinfo);
+	switch (version_minor) {
+	case 1:
+		ret = smu_v13_0_set_pptable_v2_1(smu, table, size, pptable_id);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
 
-		ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev,
-						     (uint8_t **)&table);
-		if (ret)
-			return ret;
-		size = atom_table_size;
+	return ret;
+}
+
+int smu_v13_0_setup_pptable(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t size = 0, pptable_id = 0;
+	void *table;
+	int ret = 0;
+
+	/* override pptable_id from driver parameter */
+	if (amdgpu_smu_pptable_id >= 0) {
+		pptable_id = amdgpu_smu_pptable_id;
+		dev_info(adev->dev, "override pptable id %d\n", pptable_id);
+	} else {
+		pptable_id = smu->smu_table.boot_values.pp_table_id;
 	}
 
+	/* force using vbios pptable in sriov mode */
+	if (amdgpu_sriov_vf(adev) || !pptable_id)
+		ret = smu_v13_0_get_pptable_from_vbios(smu, &table, &size);
+	else
+		ret = smu_v13_0_get_pptable_from_firmware(smu, &table, &size, pptable_id);
+
+	if (ret)
+		return ret;
+
 	if (!smu->smu_table.power_play_table)
 		smu->smu_table.power_play_table = table;
 	if (!smu->smu_table.power_play_table_size)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 0cfeb9fc7c03..0f17c2522c85 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -572,7 +572,7 @@ static int yellow_carp_get_power_profile_mode(struct smu_context *smu,
 		if (workload_type < 0)
 			continue;
 
-		size += sprintf(buf + size, "%2d %14s%s\n",
+		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
 	}
 
@@ -1054,15 +1054,15 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 
 	switch (clk_type) {
 	case SMU_OD_SCLK:
-		size = sprintf(buf, "%s:\n", "OD_SCLK");
-		size += sprintf(buf + size, "0: %10uMhz\n",
+		size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 		(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
-		size += sprintf(buf + size, "1: %10uMhz\n",
+		size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 		(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		break;
 	case SMU_OD_RANGE:
-		size = sprintf(buf, "%s:\n", "OD_RANGE");
-		size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
+		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 						smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 		break;
 	case SMU_SOCCLK:
@@ -1083,7 +1083,7 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 			if (ret)
 				goto print_clk_out;
 
-			size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, value,
 					cur_value == value ? "*" : "");
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index e802f9a95f08..66711ab24c15 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -55,7 +55,7 @@
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	#type
-static const char* __smu_message_names[] = {
+static const char * const __smu_message_names[] = {
 	SMU_MESSAGE_TYPES
 };
 
@@ -76,55 +76,256 @@ static void smu_cmn_read_arg(struct smu_context *smu,
 	*arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 }
 
-int smu_cmn_wait_for_response(struct smu_context *smu)
+/* Redefine the SMU error codes here.
+ *
+ * Note that these definitions are redundant and should be removed
+ * when the SMU has exported a unified header file containing these
+ * macros, which header file we can just include and use the SMU's
+ * macros. At the moment, these error codes are defined by the SMU
+ * per-ASIC unfortunately, yet we're a one driver for all ASICs.
+ */
+#define SMU_RESP_NONE           0
+#define SMU_RESP_OK             1
+#define SMU_RESP_CMD_FAIL       0xFF
+#define SMU_RESP_CMD_UNKNOWN    0xFE
+#define SMU_RESP_CMD_BAD_PREREQ 0xFD
+#define SMU_RESP_BUSY_OTHER     0xFC
+#define SMU_RESP_DEBUG_END      0xFB
+
+/**
+ * __smu_cmn_poll_stat -- poll for a status from the SMU
+ * smu: a pointer to SMU context
+ *
+ * Returns the status of the SMU, which could be,
+ *    0, the SMU is busy with your previous command;
+ *    1, execution status: success, execution result: success;
+ * 0xFF, execution status: success, execution result: failure;
+ * 0xFE, unknown command;
+ * 0xFD, valid command, but bad (command) prerequisites;
+ * 0xFC, the command was rejected as the SMU is busy;
+ * 0xFB, "SMC_Result_DebugDataDumpEnd".
+ *
+ * The values here are not defined by macros, because I'd rather we
+ * include a single header file which defines them, which is
+ * maintained by the SMU FW team, so that we're impervious to firmware
+ * changes. At the moment those values are defined in various header
+ * files, one for each ASIC, yet here we're a single ASIC-agnostic
+ * interface. Such a change can be followed-up by a subsequent patch.
+ */
+static u32 __smu_cmn_poll_stat(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	uint32_t cur_value, i, timeout = adev->usec_timeout * 20;
+	int timeout = adev->usec_timeout * 20;
+	u32 reg;
 
-	for (i = 0; i < timeout; i++) {
-		cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-		if ((cur_value & MP1_C2PMSG_90__CONTENT_MASK) != 0)
-			return cur_value;
+	for ( ; timeout > 0; timeout--) {
+		reg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+		if ((reg & MP1_C2PMSG_90__CONTENT_MASK) != 0)
+			break;
 
 		udelay(1);
 	}
 
-	/* timeout means wrong logic */
-	if (i == timeout)
-		return -ETIME;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+	return reg;
 }
 
-int smu_cmn_send_msg_without_waiting(struct smu_context *smu,
-				     uint16_t msg, uint32_t param)
+static void __smu_cmn_reg_print_error(struct smu_context *smu,
+				      u32 reg_c2pmsg_90,
+				      int msg_index,
+				      u32 param,
+				      enum smu_message_type msg)
 {
 	struct amdgpu_device *adev = smu->adev;
-	int ret;
+	const char *message = smu_get_message_name(smu, msg);
 
-	ret = smu_cmn_wait_for_response(smu);
-	if (ret != 0x1) {
-		dev_err(adev->dev, "Msg issuing pre-check failed(0x%x) and "
-		       "SMU may be not in the right state!\n", ret);
-		if (ret != -ETIME)
-			ret = -EIO;
-		return ret;
+	switch (reg_c2pmsg_90) {
+	case SMU_RESP_NONE:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: I'm not done with your previous command!");
+		break;
+	case SMU_RESP_OK:
+		/* The SMU executed the command. It completed with a
+		 * successful result.
+		 */
+		break;
+	case SMU_RESP_CMD_FAIL:
+		/* The SMU executed the command. It completed with an
+		 * unsuccessful result.
+		 */
+		break;
+	case SMU_RESP_CMD_UNKNOWN:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: unknown command: index:%d param:0x%08X message:%s",
+				    msg_index, param, message);
+		break;
+	case SMU_RESP_CMD_BAD_PREREQ:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: valid command, bad prerequisites: index:%d param:0x%08X message:%s",
+				    msg_index, param, message);
+		break;
+	case SMU_RESP_BUSY_OTHER:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: I'm very busy for your command: index:%d param:0x%08X message:%s",
+				    msg_index, param, message);
+		break;
+	case SMU_RESP_DEBUG_END:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: I'm debugging!");
+		break;
+	default:
+		dev_err_ratelimited(adev->dev,
+				    "SMU: response:0x%08X for index:%d param:0x%08X message:%s?",
+				    reg_c2pmsg_90, msg_index, param, message);
+		break;
 	}
+}
+
+static int __smu_cmn_reg2errno(struct smu_context *smu, u32 reg_c2pmsg_90)
+{
+	int res;
+
+	switch (reg_c2pmsg_90) {
+	case SMU_RESP_NONE:
+		/* The SMU is busy--still executing your command.
+		 */
+		res = -ETIME;
+		break;
+	case SMU_RESP_OK:
+		res = 0;
+		break;
+	case SMU_RESP_CMD_FAIL:
+		/* Command completed successfully, but the command
+		 * status was failure.
+		 */
+		res = -EIO;
+		break;
+	case SMU_RESP_CMD_UNKNOWN:
+		/* Unknown command--ignored by the SMU.
+		 */
+		res = -EOPNOTSUPP;
+		break;
+	case SMU_RESP_CMD_BAD_PREREQ:
+		/* Valid command--bad prerequisites.
+		 */
+		res = -EINVAL;
+		break;
+	case SMU_RESP_BUSY_OTHER:
+		/* The SMU is busy with other commands. The client
+		 * should retry in 10 us.
+		 */
+		res = -EBUSY;
+		break;
+	default:
+		/* Unknown or debug response from the SMU.
+		 */
+		res = -EREMOTEIO;
+		break;
+	}
+
+	return res;
+}
+
+static void __smu_cmn_send_msg(struct smu_context *smu,
+			       u16 msg,
+			       u32 param)
+{
+	struct amdgpu_device *adev = smu->adev;
 
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, param);
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+}
 
-	return 0;
+/**
+ * smu_cmn_send_msg_without_waiting -- send the message; don't wait for status
+ * @smu: pointer to an SMU context
+ * @msg_index: message index
+ * @param: message parameter to send to the SMU
+ *
+ * Send a message to the SMU with the parameter passed. Do not wait
+ * for status/result of the message, thus the "without_waiting".
+ *
+ * Return 0 on success, -errno on error if we weren't able to _send_
+ * the message for some reason. See __smu_cmn_reg2errno() for details
+ * of the -errno.
+ */
+int smu_cmn_send_msg_without_waiting(struct smu_context *smu,
+				     uint16_t msg_index,
+				     uint32_t param)
+{
+	u32 reg;
+	int res;
+
+	if (smu->adev->no_hw_access)
+		return 0;
+
+	reg = __smu_cmn_poll_stat(smu);
+	res = __smu_cmn_reg2errno(smu, reg);
+	if (reg == SMU_RESP_NONE ||
+	    reg == SMU_RESP_BUSY_OTHER ||
+	    res == -EREMOTEIO)
+		goto Out;
+	__smu_cmn_send_msg(smu, msg_index, param);
+	res = 0;
+Out:
+	return res;
+}
+
+/**
+ * smu_cmn_wait_for_response -- wait for response from the SMU
+ * @smu: pointer to an SMU context
+ *
+ * Wait for status from the SMU.
+ *
+ * Return 0 on success, -errno on error, indicating the execution
+ * status and result of the message being waited for. See
+ * __smu_cmn_reg2errno() for details of the -errno.
+ */
+int smu_cmn_wait_for_response(struct smu_context *smu)
+{
+	u32 reg;
+
+	reg = __smu_cmn_poll_stat(smu);
+	return __smu_cmn_reg2errno(smu, reg);
 }
 
+/**
+ * smu_cmn_send_smc_msg_with_param -- send a message with parameter
+ * @smu: pointer to an SMU context
+ * @msg: message to send
+ * @param: parameter to send to the SMU
+ * @read_arg: pointer to u32 to return a value from the SMU back
+ *            to the caller
+ *
+ * Send the message @msg with parameter @param to the SMU, wait for
+ * completion of the command, and return back a value from the SMU in
+ * @read_arg pointer.
+ *
+ * Return 0 on success, -errno on error, if we weren't able to send
+ * the message or if the message completed with some kind of
+ * error. See __smu_cmn_reg2errno() for details of the -errno.
+ *
+ * If we weren't able to send the message to the SMU, we also print
+ * the error to the standard log.
+ *
+ * Command completion status is printed only if the -errno is
+ * -EREMOTEIO, indicating that the SMU returned back an
+ * undefined/unknown/unspecified result. All other cases are
+ * well-defined, not printed, but instead given back to the client to
+ * decide what further to do.
+ *
+ * The return value, @read_arg is read back regardless, to give back
+ * more information to the client, which on error would most likely be
+ * @param, but we can't assume that. This also eliminates more
+ * conditionals.
+ */
 int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 				    enum smu_message_type msg,
 				    uint32_t param,
 				    uint32_t *read_arg)
 {
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, index = 0;
+	int res, index;
+	u32 reg;
 
 	if (smu->adev->no_hw_access)
 		return 0;
@@ -136,31 +337,24 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 		return index == -EACCES ? 0 : index;
 
 	mutex_lock(&smu->message_lock);
-	ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, param);
-	if (ret)
-		goto out;
-
-	ret = smu_cmn_wait_for_response(smu);
-	if (ret != 0x1) {
-		if (ret == -ETIME) {
-			dev_err(adev->dev, "message: %15s (%d) \tparam: 0x%08x is timeout (no response)\n",
-				smu_get_message_name(smu, msg), index, param);
-		} else {
-			dev_err(adev->dev, "failed send message: %15s (%d) \tparam: 0x%08x response %#x\n",
-				smu_get_message_name(smu, msg), index, param,
-				ret);
-			ret = -EIO;
-		}
-		goto out;
+	reg = __smu_cmn_poll_stat(smu);
+	res = __smu_cmn_reg2errno(smu, reg);
+	if (reg == SMU_RESP_NONE ||
+	    reg == SMU_RESP_BUSY_OTHER ||
+	    res == -EREMOTEIO) {
+		__smu_cmn_reg_print_error(smu, reg, index, param, msg);
+		goto Out;
 	}
-
+	__smu_cmn_send_msg(smu, (uint16_t) index, param);
+	reg = __smu_cmn_poll_stat(smu);
+	res = __smu_cmn_reg2errno(smu, reg);
+	if (res == -EREMOTEIO)
+		__smu_cmn_reg_print_error(smu, reg, index, param, msg);
 	if (read_arg)
 		smu_cmn_read_arg(smu, read_arg);
-
-	ret = 0; /* 0 as driver return value */
-out:
+Out:
 	mutex_unlock(&smu->message_lock);
-	return ret;
+	return res;
 }
 
 int smu_cmn_send_smc_msg(struct smu_context *smu,
@@ -516,7 +710,7 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu,
 			return 0;
 	}
 
-	size =  sprintf(buf + size, "features high: 0x%08x low: 0x%08x\n",
+	size =  sysfs_emit_at(buf, size, "features high: 0x%08x low: 0x%08x\n",
 			feature_mask[1], feature_mask[0]);
 
 	memset(sort_feature, -1, sizeof(sort_feature));
@@ -531,14 +725,14 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu,
 		sort_feature[feature_index] = i;
 	}
 
-	size += sprintf(buf + size, "%-2s. %-20s  %-3s : %-s\n",
+	size += sysfs_emit_at(buf, size, "%-2s. %-20s  %-3s : %-s\n",
 			"No", "Feature", "Bit", "State");
 
 	for (i = 0; i < SMU_FEATURE_COUNT; i++) {
 		if (sort_feature[i] < 0)
 			continue;
 
-		size += sprintf(buf + size, "%02d. %-20s (%2d) : %s\n",
+		size += sysfs_emit_at(buf, size, "%02d. %-20s (%2d) : %s\n",
 				count++,
 				smu_get_feature_name(smu, sort_feature[i]),
 				i,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 9add5f16ff56..16993daa2ae0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -27,7 +27,8 @@
 
 #if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) || defined(SWSMU_CODE_LAYER_L4)
 int smu_cmn_send_msg_without_waiting(struct smu_context *smu,
-				     uint16_t msg, uint32_t param);
+				     uint16_t msg_index,
+				     uint32_t param);
 int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 				    enum smu_message_type msg,
 				    uint32_t param,
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index ff45f23f3d56..93b7f09b96ca 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -13,7 +13,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -301,8 +300,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 	if (err)
 		goto free_component_binding;
 
-	drm->irq_enabled = true;
-
 	drm_kms_helper_poll_init(drm);
 
 	err = drm_dev_register(drm, 0);
@@ -313,7 +310,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 
 free_interrupts:
 	drm_kms_helper_poll_fini(drm);
-	drm->irq_enabled = false;
 free_component_binding:
 	component_unbind_all(mdev->dev, drm);
 cleanup_mode_config:
@@ -331,7 +327,6 @@ void komeda_kms_detach(struct komeda_kms_dev *kms)
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
-	drm->irq_enabled = false;
 	component_unbind_all(mdev->dev, drm);
 	drm_mode_config_cleanup(drm);
 	komeda_kms_cleanup_private_objs(kms);
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index 81ae92390736..479c2422a2e0 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -29,7 +29,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_modeset_helper.h>
 #include <drm/drm_of.h>
 #include <drm/drm_probe_helper.h>
@@ -38,6 +37,94 @@
 #include "hdlcd_drv.h"
 #include "hdlcd_regs.h"
 
+static irqreturn_t hdlcd_irq(int irq, void *arg)
+{
+	struct drm_device *drm = arg;
+	struct hdlcd_drm_private *hdlcd = drm->dev_private;
+	unsigned long irq_status;
+
+	irq_status = hdlcd_read(hdlcd, HDLCD_REG_INT_STATUS);
+
+#ifdef CONFIG_DEBUG_FS
+	if (irq_status & HDLCD_INTERRUPT_UNDERRUN)
+		atomic_inc(&hdlcd->buffer_underrun_count);
+
+	if (irq_status & HDLCD_INTERRUPT_DMA_END)
+		atomic_inc(&hdlcd->dma_end_count);
+
+	if (irq_status & HDLCD_INTERRUPT_BUS_ERROR)
+		atomic_inc(&hdlcd->bus_error_count);
+
+	if (irq_status & HDLCD_INTERRUPT_VSYNC)
+		atomic_inc(&hdlcd->vsync_count);
+
+#endif
+	if (irq_status & HDLCD_INTERRUPT_VSYNC)
+		drm_crtc_handle_vblank(&hdlcd->crtc);
+
+	/* acknowledge interrupt(s) */
+	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, irq_status);
+
+	return IRQ_HANDLED;
+}
+
+static void hdlcd_irq_preinstall(struct drm_device *drm)
+{
+	struct hdlcd_drm_private *hdlcd = drm->dev_private;
+	/* Ensure interrupts are disabled */
+	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, 0);
+	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, ~0);
+}
+
+static void hdlcd_irq_postinstall(struct drm_device *drm)
+{
+#ifdef CONFIG_DEBUG_FS
+	struct hdlcd_drm_private *hdlcd = drm->dev_private;
+	unsigned long irq_mask = hdlcd_read(hdlcd, HDLCD_REG_INT_MASK);
+
+	/* enable debug interrupts */
+	irq_mask |= HDLCD_DEBUG_INT_MASK;
+
+	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, irq_mask);
+#endif
+}
+
+static int hdlcd_irq_install(struct drm_device *drm, int irq)
+{
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	hdlcd_irq_preinstall(drm);
+
+	ret = request_irq(irq, hdlcd_irq, 0, drm->driver->name, drm);
+	if (ret)
+		return ret;
+
+	hdlcd_irq_postinstall(drm);
+
+	return 0;
+}
+
+static void hdlcd_irq_uninstall(struct drm_device *drm)
+{
+	struct hdlcd_drm_private *hdlcd = drm->dev_private;
+	/* disable all the interrupts that we might have enabled */
+	unsigned long irq_mask = hdlcd_read(hdlcd, HDLCD_REG_INT_MASK);
+
+#ifdef CONFIG_DEBUG_FS
+	/* disable debug interrupts */
+	irq_mask &= ~HDLCD_DEBUG_INT_MASK;
+#endif
+
+	/* disable vsync interrupts */
+	irq_mask &= ~HDLCD_INTERRUPT_VSYNC;
+	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, irq_mask);
+
+	free_irq(hdlcd->irq, drm);
+}
+
 static int hdlcd_load(struct drm_device *drm, unsigned long flags)
 {
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
@@ -90,7 +177,12 @@ static int hdlcd_load(struct drm_device *drm, unsigned long flags)
 		goto setup_fail;
 	}
 
-	ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto irq_fail;
+	hdlcd->irq = ret;
+
+	ret = hdlcd_irq_install(drm, hdlcd->irq);
 	if (ret < 0) {
 		DRM_ERROR("failed to install IRQ handler\n");
 		goto irq_fail;
@@ -122,76 +214,6 @@ static void hdlcd_setup_mode_config(struct drm_device *drm)
 	drm->mode_config.funcs = &hdlcd_mode_config_funcs;
 }
 
-static irqreturn_t hdlcd_irq(int irq, void *arg)
-{
-	struct drm_device *drm = arg;
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-	unsigned long irq_status;
-
-	irq_status = hdlcd_read(hdlcd, HDLCD_REG_INT_STATUS);
-
-#ifdef CONFIG_DEBUG_FS
-	if (irq_status & HDLCD_INTERRUPT_UNDERRUN)
-		atomic_inc(&hdlcd->buffer_underrun_count);
-
-	if (irq_status & HDLCD_INTERRUPT_DMA_END)
-		atomic_inc(&hdlcd->dma_end_count);
-
-	if (irq_status & HDLCD_INTERRUPT_BUS_ERROR)
-		atomic_inc(&hdlcd->bus_error_count);
-
-	if (irq_status & HDLCD_INTERRUPT_VSYNC)
-		atomic_inc(&hdlcd->vsync_count);
-
-#endif
-	if (irq_status & HDLCD_INTERRUPT_VSYNC)
-		drm_crtc_handle_vblank(&hdlcd->crtc);
-
-	/* acknowledge interrupt(s) */
-	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, irq_status);
-
-	return IRQ_HANDLED;
-}
-
-static void hdlcd_irq_preinstall(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-	/* Ensure interrupts are disabled */
-	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, 0);
-	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, ~0);
-}
-
-static int hdlcd_irq_postinstall(struct drm_device *drm)
-{
-#ifdef CONFIG_DEBUG_FS
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-	unsigned long irq_mask = hdlcd_read(hdlcd, HDLCD_REG_INT_MASK);
-
-	/* enable debug interrupts */
-	irq_mask |= HDLCD_DEBUG_INT_MASK;
-
-	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, irq_mask);
-#endif
-	return 0;
-}
-
-static void hdlcd_irq_uninstall(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-	/* disable all the interrupts that we might have enabled */
-	unsigned long irq_mask = hdlcd_read(hdlcd, HDLCD_REG_INT_MASK);
-
-#ifdef CONFIG_DEBUG_FS
-	/* disable debug interrupts */
-	irq_mask &= ~HDLCD_DEBUG_INT_MASK;
-#endif
-
-	/* disable vsync interrupts */
-	irq_mask &= ~HDLCD_INTERRUPT_VSYNC;
-
-	hdlcd_write(hdlcd, HDLCD_REG_INT_MASK, irq_mask);
-}
-
 #ifdef CONFIG_DEBUG_FS
 static int hdlcd_show_underrun_count(struct seq_file *m, void *arg)
 {
@@ -236,10 +258,6 @@ DEFINE_DRM_GEM_CMA_FOPS(fops);
 
 static const struct drm_driver hdlcd_driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
-	.irq_handler = hdlcd_irq,
-	.irq_preinstall = hdlcd_irq_preinstall,
-	.irq_postinstall = hdlcd_irq_postinstall,
-	.irq_uninstall = hdlcd_irq_uninstall,
 	DRM_GEM_CMA_DRIVER_OPS,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init = hdlcd_debugfs_init,
@@ -316,7 +334,7 @@ err_pm_active:
 err_unload:
 	of_node_put(hdlcd->crtc.port);
 	hdlcd->crtc.port = NULL;
-	drm_irq_uninstall(drm);
+	hdlcd_irq_uninstall(drm);
 	of_reserved_mem_device_release(drm->dev);
 err_free:
 	drm_mode_config_cleanup(drm);
@@ -338,7 +356,7 @@ static void hdlcd_drm_unbind(struct device *dev)
 	hdlcd->crtc.port = NULL;
 	pm_runtime_get_sync(dev);
 	drm_atomic_helper_shutdown(drm);
-	drm_irq_uninstall(drm);
+	hdlcd_irq_uninstall(drm);
 	pm_runtime_put(dev);
 	if (pm_runtime_enabled(dev))
 		pm_runtime_disable(dev);
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index fd438d177b64..909c39c28487 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -11,6 +11,7 @@ struct hdlcd_drm_private {
 	struct clk			*clk;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
+	unsigned int			irq;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index de59f3302516..78d15b04b105 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -847,8 +847,6 @@ static int malidp_bind(struct device *dev)
 	if (ret < 0)
 		goto irq_init_fail;
 
-	drm->irq_enabled = true;
-
 	ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
 	if (ret < 0) {
 		DRM_ERROR("failed to initialise vblank\n");
@@ -874,7 +872,6 @@ register_fail:
 vblank_fail:
 	malidp_se_irq_fini(hwdev);
 	malidp_de_irq_fini(hwdev);
-	drm->irq_enabled = false;
 irq_init_fail:
 	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
@@ -909,7 +906,6 @@ static void malidp_unbind(struct device *dev)
 	drm_atomic_helper_shutdown(drm);
 	malidp_se_irq_fini(hwdev);
 	malidp_de_irq_fini(hwdev);
-	drm->irq_enabled = false;
 	component_unbind_all(dev, drm);
 	of_node_put(malidp->crtc.port);
 	malidp->crtc.port = NULL;
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index dab0a1f0983b..8e3e98f13db4 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev)
 	}
 
 	/* Remove early framebuffers */
-	ret = drm_aperture_remove_framebuffers(false, "armada-drm-fb");
+	ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver);
 	if (ret) {
 		dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n",
 			__func__, ret);
@@ -130,8 +130,6 @@ static int armada_drm_bind(struct device *dev)
 	if (ret)
 		goto err_comp;
 
-	priv->drm.irq_enabled = true;
-
 	drm_mode_config_reset(&priv->drm);
 
 	ret = armada_fbdev_init(&priv->drm);
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index d3e3e5fdc390..424250535fed 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -247,8 +247,6 @@ static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
-	.prepare_fb	= armada_drm_plane_prepare_fb,
-	.cleanup_fb	= armada_drm_plane_cleanup_fb,
 	.atomic_check	= armada_drm_plane_atomic_check,
 	.atomic_update	= armada_drm_overlay_plane_atomic_update,
 	.atomic_disable	= armada_drm_overlay_plane_atomic_disable,
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 40209e49f34a..959d7f0a5108 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -78,33 +78,6 @@ void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
 	}
 }
 
-int armada_drm_plane_prepare_fb(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
-		plane->base.id, plane->name,
-		state->fb ? state->fb->base.id : 0);
-
-	/*
-	 * Take a reference on the new framebuffer - we want to
-	 * hold on to it while the hardware is displaying it.
-	 */
-	if (state->fb)
-		drm_framebuffer_get(state->fb);
-	return 0;
-}
-
-void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-	struct drm_plane_state *old_state)
-{
-	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
-		plane->base.id, plane->name,
-		old_state->fb ? old_state->fb->base.id : 0);
-
-	if (old_state->fb)
-		drm_framebuffer_put(old_state->fb);
-}
-
 int armada_drm_plane_atomic_check(struct drm_plane *plane,
 	struct drm_atomic_state *state)
 {
@@ -282,8 +255,6 @@ static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
-	.prepare_fb	= armada_drm_plane_prepare_fb,
-	.cleanup_fb	= armada_drm_plane_cleanup_fb,
 	.atomic_check	= armada_drm_plane_atomic_check,
 	.atomic_update	= armada_drm_primary_plane_atomic_update,
 	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
index 51dab8d8da22..368415c609a6 100644
--- a/drivers/gpu/drm/armada/armada_plane.h
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -21,8 +21,6 @@ struct armada_plane_state {
 
 void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
 	u16 pitches[3], bool interlaced);
-int armada_drm_plane_prepare_fb(struct drm_plane *plane,
-	struct drm_plane_state *state);
 void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_plane_state *old_state);
 int armada_drm_plane_atomic_check(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c
index 098f96d4d50d..827e62c1daba 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c
@@ -220,7 +220,6 @@ static const struct drm_simple_display_pipe_funcs aspeed_gfx_funcs = {
 	.enable		= aspeed_gfx_pipe_enable,
 	.disable	= aspeed_gfx_pipe_disable,
 	.update		= aspeed_gfx_pipe_update,
-	.prepare_fb	= drm_gem_simple_display_pipe_prepare_fb,
 	.enable_vblank	= aspeed_gfx_enable_vblank,
 	.disable_vblank	= aspeed_gfx_disable_vblank,
 };
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index 5aa452b4efe6..86d5cd7b6318 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -100,7 +100,7 @@ static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev)
 	primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
 #endif
 
-	return drm_aperture_remove_conflicting_framebuffers(base, size, primary, "astdrmfb");
+	return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver);
 }
 
 static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 911f9f414774..39ca338eb80b 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -337,6 +337,11 @@ int ast_mode_config_init(struct ast_private *ast);
 #define AST_DP501_LINKRATE	0xf014
 #define AST_DP501_EDID_DATA	0xf020
 
+/* Define for Soc scratched reg */
+#define AST_VRAM_INIT_STATUS_MASK	GENMASK(7, 6)
+//#define AST_VRAM_INIT_BY_BMC		BIT(7)
+//#define AST_VRAM_INIT_READY		BIT(6)
+
 int ast_mm_init(struct ast_private *ast);
 
 /* ast post */
@@ -346,6 +351,7 @@ bool ast_is_vga_enabled(struct drm_device *dev);
 void ast_post_gpu(struct drm_device *dev);
 u32 ast_mindwm(struct ast_private *ast, u32 r);
 void ast_moutdwm(struct ast_private *ast, u32 r, u32 v);
+void ast_patch_ahb_2500(struct ast_private *ast);
 /* ast dp501 */
 void ast_set_dp501_video_output(struct drm_device *dev, u8 mode);
 bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 2aff2e6cf450..79a361867955 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -97,6 +97,11 @@ static void ast_detect_config_mode(struct drm_device *dev, u32 *scu_rev)
 	jregd0 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff);
 	jregd1 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
 	if (!(jregd0 & 0x80) || !(jregd1 & 0x10)) {
+		/* Patch AST2500 */
+		if (((pdev->revision & 0xF0) == 0x40)
+			&& ((jregd0 & AST_VRAM_INIT_STATUS_MASK) == 0))
+			ast_patch_ahb_2500(ast);
+
 		/* Double check it's actually working */
 		data = ast_read32(ast, 0xf004);
 		if ((data != 0xFFFFFFFF) && (data != 0x00)) {
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 36d9575aa27b..6bfaefa01818 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -275,7 +275,7 @@ static void ast_set_std_reg(struct ast_private *ast,
 	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x01, 0xdf, stdtable->seq[0]);
 	for (i = 1; i < 4; i++) {
 		jreg = stdtable->seq[i];
-		ast_set_index_reg(ast, AST_IO_SEQ_PORT, (i + 1) , jreg);
+		ast_set_index_reg(ast, AST_IO_SEQ_PORT, (i + 1), jreg);
 	}
 
 	/* Set CRTC; except base address and offset */
@@ -498,13 +498,15 @@ static void ast_set_sync_reg(struct ast_private *ast,
 
 	jreg  = ast_io_read8(ast, AST_IO_MISC_PORT_READ);
 	jreg &= ~0xC0;
-	if (vbios_mode->enh_table->flags & NVSync) jreg |= 0x80;
-	if (vbios_mode->enh_table->flags & NHSync) jreg |= 0x40;
+	if (vbios_mode->enh_table->flags & NVSync)
+		jreg |= 0x80;
+	if (vbios_mode->enh_table->flags & NHSync)
+		jreg |= 0x40;
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 }
 
 static void ast_set_start_address_crt1(struct ast_private *ast,
-				       unsigned offset)
+				       unsigned int offset)
 {
 	u32 addr;
 
@@ -612,8 +614,7 @@ ast_primary_plane_helper_atomic_disable(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs ast_primary_plane_helper_funcs = {
-	.prepare_fb = drm_gem_vram_plane_helper_prepare_fb,
-	.cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb,
+	DRM_GEM_VRAM_PLANE_HELPER_FUNCS,
 	.atomic_check = ast_primary_plane_helper_atomic_check,
 	.atomic_update = ast_primary_plane_helper_atomic_update,
 	.atomic_disable = ast_primary_plane_helper_atomic_disable,
@@ -807,7 +808,7 @@ ast_cursor_plane_helper_atomic_update(struct drm_plane *plane,
 		ast_cursor_plane->hwc[ast_cursor_plane->next_hwc_index].map;
 	u64 dst_off =
 		ast_cursor_plane->hwc[ast_cursor_plane->next_hwc_index].off;
-	struct dma_buf_map src_map = shadow_plane_state->map[0];
+	struct dma_buf_map src_map = shadow_plane_state->data[0];
 	unsigned int offset_x, offset_y;
 	u16 x, y;
 	u8 x_offset, y_offset;
@@ -1212,6 +1213,7 @@ static int ast_get_modes(struct drm_connector *connector)
 	struct edid *edid;
 	int ret;
 	bool flags = false;
+
 	if (ast->tx_chip_type == AST_TX_DP501) {
 		ast->dp501_maxclk = 0xff;
 		edid = kmalloc(128, GFP_KERNEL);
@@ -1231,8 +1233,8 @@ static int ast_get_modes(struct drm_connector *connector)
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 		return ret;
-	} else
-		drm_connector_update_edid_property(&ast_connector->base, NULL);
+	}
+	drm_connector_update_edid_property(&ast_connector->base, NULL);
 	return 0;
 }
 
@@ -1272,19 +1274,24 @@ static enum drm_mode_status ast_mode_valid(struct drm_connector *connector,
 	}
 	switch (mode->hdisplay) {
 	case 640:
-		if (mode->vdisplay == 480) flags = MODE_OK;
+		if (mode->vdisplay == 480)
+			flags = MODE_OK;
 		break;
 	case 800:
-		if (mode->vdisplay == 600) flags = MODE_OK;
+		if (mode->vdisplay == 600)
+			flags = MODE_OK;
 		break;
 	case 1024:
-		if (mode->vdisplay == 768) flags = MODE_OK;
+		if (mode->vdisplay == 768)
+			flags = MODE_OK;
 		break;
 	case 1280:
-		if (mode->vdisplay == 1024) flags = MODE_OK;
+		if (mode->vdisplay == 1024)
+			flags = MODE_OK;
 		break;
 	case 1600:
-		if (mode->vdisplay == 1200) flags = MODE_OK;
+		if (mode->vdisplay == 1200)
+			flags = MODE_OK;
 		break;
 	default:
 		return flags;
@@ -1293,9 +1300,22 @@ static enum drm_mode_status ast_mode_valid(struct drm_connector *connector,
 	return flags;
 }
 
+static enum drm_connector_status ast_connector_detect(struct drm_connector
+						   *connector, bool force)
+{
+	int r;
+
+	r = ast_get_modes(connector);
+	if (r <= 0)
+		return connector_status_disconnected;
+
+	return connector_status_connected;
+}
+
 static void ast_connector_destroy(struct drm_connector *connector)
 {
 	struct ast_connector *ast_connector = to_ast_connector(connector);
+
 	ast_i2c_destroy(ast_connector->i2c);
 	drm_connector_cleanup(connector);
 }
@@ -1307,6 +1327,7 @@ static const struct drm_connector_helper_funcs ast_connector_helper_funcs = {
 
 static const struct drm_connector_funcs ast_connector_funcs = {
 	.reset = drm_atomic_helper_connector_reset,
+	.detect = ast_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = ast_connector_destroy,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -1334,7 +1355,8 @@ static int ast_connector_init(struct drm_device *dev)
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+						DRM_CONNECTOR_POLL_DISCONNECT;
 
 	drm_connector_attach_encoder(connector, encoder);
 
@@ -1403,6 +1425,8 @@ int ast_mode_config_init(struct ast_private *ast)
 
 	drm_mode_config_reset(dev);
 
+	drm_kms_helper_poll_init(dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 0607658dde51..b5d92f652fd8 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -2028,6 +2028,40 @@ static bool ast_dram_init_2500(struct ast_private *ast)
 	return true;
 }
 
+void ast_patch_ahb_2500(struct ast_private *ast)
+{
+	u32	data;
+
+	/* Clear bus lock condition */
+	ast_moutdwm(ast, 0x1e600000, 0xAEED1A03);
+	ast_moutdwm(ast, 0x1e600084, 0x00010000);
+	ast_moutdwm(ast, 0x1e600088, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e2000, 0x1688A8A8);
+	data = ast_mindwm(ast, 0x1e6e2070);
+	if (data & 0x08000000) {					/* check fast reset */
+		/*
+		 * If "Fast restet" is enabled for ARM-ICE debugger,
+		 * then WDT needs to enable, that
+		 * WDT04 is WDT#1 Reload reg.
+		 * WDT08 is WDT#1 counter restart reg to avoid system deadlock
+		 * WDT0C is WDT#1 control reg
+		 *	[6:5]:= 01:Full chip
+		 *	[4]:= 1:1MHz clock source
+		 *	[1]:= 1:WDT will be cleeared and disabled after timeout occurs
+		 *	[0]:= 1:WDT enable
+		 */
+		ast_moutdwm(ast, 0x1E785004, 0x00000010);
+		ast_moutdwm(ast, 0x1E785008, 0x00004755);
+		ast_moutdwm(ast, 0x1E78500c, 0x00000033);
+		udelay(1000);
+	}
+	do {
+		ast_moutdwm(ast, 0x1e6e2000, 0x1688A8A8);
+		data = ast_mindwm(ast, 0x1e6e2000);
+	}	while (data != 1);
+	ast_moutdwm(ast, 0x1e6e207c, 0x08000000);	/* clear fast reset */
+}
+
 void ast_post_chip_2500(struct drm_device *dev)
 {
 	struct ast_private *ast = to_ast_private(dev);
@@ -2035,39 +2069,44 @@ void ast_post_chip_2500(struct drm_device *dev)
 	u8 reg;
 
 	reg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff);
-	if ((reg & 0x80) == 0) {/* vga only */
+	if ((reg & AST_VRAM_INIT_STATUS_MASK) == 0) {/* vga only */
 		/* Clear bus lock condition */
-		ast_moutdwm(ast, 0x1e600000, 0xAEED1A03);
-		ast_moutdwm(ast, 0x1e600084, 0x00010000);
-		ast_moutdwm(ast, 0x1e600088, 0x00000000);
-		ast_moutdwm(ast, 0x1e6e2000, 0x1688A8A8);
-		ast_write32(ast, 0xf004, 0x1e6e0000);
-		ast_write32(ast, 0xf000, 0x1);
-		ast_write32(ast, 0x12000, 0x1688a8a8);
-		while (ast_read32(ast, 0x12000) != 0x1)
-			;
-
-		ast_write32(ast, 0x10000, 0xfc600309);
-		while (ast_read32(ast, 0x10000) != 0x1)
-			;
+		ast_patch_ahb_2500(ast);
+
+		/* Disable watchdog */
+		ast_moutdwm(ast, 0x1E78502C, 0x00000000);
+		ast_moutdwm(ast, 0x1E78504C, 0x00000000);
+
+		/*
+		 * Reset USB port to patch USB unknown device issue
+		 * SCU90 is Multi-function Pin Control #5
+		 *	[29]:= 1:Enable USB2.0 Host port#1 (that the mutually shared USB2.0 Hub
+		 *				port).
+		 * SCU94 is Multi-function Pin Control #6
+		 *	[14:13]:= 1x:USB2.0 Host2 controller
+		 * SCU70 is Hardware Strap reg
+		 *	[23]:= 1:CLKIN is 25MHz and USBCK1 = 24/48 MHz (determined by
+		 *				[18]: 0(24)/1(48) MHz)
+		 * SCU7C is Write clear reg to SCU70
+		 *	[23]:= write 1 and then SCU70[23] will be clear as 0b.
+		 */
+		ast_moutdwm(ast, 0x1E6E2090, 0x20000000);
+		ast_moutdwm(ast, 0x1E6E2094, 0x00004000);
+		if (ast_mindwm(ast, 0x1E6E2070) & 0x00800000) {
+			ast_moutdwm(ast, 0x1E6E207C, 0x00800000);
+			mdelay(100);
+			ast_moutdwm(ast, 0x1E6E2070, 0x00800000);
+		}
+		/* Modify eSPI reset pin */
+		temp = ast_mindwm(ast, 0x1E6E2070);
+		if (temp & 0x02000000)
+			ast_moutdwm(ast, 0x1E6E207C, 0x00004000);
 
 		/* Slow down CPU/AHB CLK in VGA only mode */
 		temp = ast_read32(ast, 0x12008);
 		temp |= 0x73;
 		ast_write32(ast, 0x12008, temp);
 
-		/* Reset USB port to patch USB unknown device issue */
-		ast_moutdwm(ast, 0x1e6e2090, 0x20000000);
-		temp  = ast_mindwm(ast, 0x1e6e2094);
-		temp |= 0x00004000;
-		ast_moutdwm(ast, 0x1e6e2094, temp);
-		temp  = ast_mindwm(ast, 0x1e6e2070);
-		if (temp & 0x00800000) {
-			ast_moutdwm(ast, 0x1e6e207c, 0x00800000);
-			mdelay(100);
-			ast_moutdwm(ast, 0x1e6e2070, 0x00800000);
-		}
-
 		if (!ast_dram_init_2500(ast))
 			drm_err(dev, "DRAM init failed !\n");
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index f09b6dd8754c..1656d27b78b6 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -22,7 +22,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 
@@ -557,6 +556,51 @@ static irqreturn_t atmel_hlcdc_dc_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void atmel_hlcdc_dc_irq_postinstall(struct drm_device *dev)
+{
+	struct atmel_hlcdc_dc *dc = dev->dev_private;
+	unsigned int cfg = 0;
+	int i;
+
+	/* Enable interrupts on activated layers */
+	for (i = 0; i < ATMEL_HLCDC_MAX_LAYERS; i++) {
+		if (dc->layers[i])
+			cfg |= ATMEL_HLCDC_LAYER_STATUS(i);
+	}
+
+	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IER, cfg);
+}
+
+static void atmel_hlcdc_dc_irq_disable(struct drm_device *dev)
+{
+	struct atmel_hlcdc_dc *dc = dev->dev_private;
+	unsigned int isr;
+
+	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IDR, 0xffffffff);
+	regmap_read(dc->hlcdc->regmap, ATMEL_HLCDC_ISR, &isr);
+}
+
+static int atmel_hlcdc_dc_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	int ret;
+
+	atmel_hlcdc_dc_irq_disable(dev);
+
+	ret = devm_request_irq(dev->dev, irq, atmel_hlcdc_dc_irq_handler, 0,
+			       dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	atmel_hlcdc_dc_irq_postinstall(dev);
+
+	return 0;
+}
+
+static void atmel_hlcdc_dc_irq_uninstall(struct drm_device *dev)
+{
+	atmel_hlcdc_dc_irq_disable(dev);
+}
+
 static const struct drm_mode_config_funcs mode_config_funcs = {
 	.fb_create = drm_gem_fb_create,
 	.atomic_check = drm_atomic_helper_check,
@@ -647,7 +691,7 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 	drm_mode_config_reset(dev);
 
 	pm_runtime_get_sync(dev->dev);
-	ret = drm_irq_install(dev, dc->hlcdc->irq);
+	ret = atmel_hlcdc_dc_irq_install(dev, dc->hlcdc->irq);
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
@@ -676,7 +720,7 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 	drm_mode_config_cleanup(dev);
 
 	pm_runtime_get_sync(dev->dev);
-	drm_irq_uninstall(dev);
+	atmel_hlcdc_dc_irq_uninstall(dev);
 	pm_runtime_put_sync(dev->dev);
 
 	dev->dev_private = NULL;
@@ -685,40 +729,10 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
 }
 
-static int atmel_hlcdc_dc_irq_postinstall(struct drm_device *dev)
-{
-	struct atmel_hlcdc_dc *dc = dev->dev_private;
-	unsigned int cfg = 0;
-	int i;
-
-	/* Enable interrupts on activated layers */
-	for (i = 0; i < ATMEL_HLCDC_MAX_LAYERS; i++) {
-		if (dc->layers[i])
-			cfg |= ATMEL_HLCDC_LAYER_STATUS(i);
-	}
-
-	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IER, cfg);
-
-	return 0;
-}
-
-static void atmel_hlcdc_dc_irq_uninstall(struct drm_device *dev)
-{
-	struct atmel_hlcdc_dc *dc = dev->dev_private;
-	unsigned int isr;
-
-	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IDR, 0xffffffff);
-	regmap_read(dc->hlcdc->regmap, ATMEL_HLCDC_ISR, &isr);
-}
-
 DEFINE_DRM_GEM_CMA_FOPS(fops);
 
 static const struct drm_driver atmel_hlcdc_dc_driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
-	.irq_handler = atmel_hlcdc_dc_irq_handler,
-	.irq_preinstall = atmel_hlcdc_dc_irq_uninstall,
-	.irq_postinstall = atmel_hlcdc_dc_irq_postinstall,
-	.irq_uninstall = atmel_hlcdc_dc_irq_uninstall,
 	DRM_GEM_CMA_DRIVER_OPS,
 	.fops = &fops,
 	.name = "atmel-hlcdc",
diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig
deleted file mode 100644
index 7bcdf294fed8..000000000000
--- a/drivers/gpu/drm/bochs/Kconfig
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config DRM_BOCHS
-	tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
-	depends on DRM && PCI && MMU
-	select DRM_KMS_HELPER
-	select DRM_VRAM_HELPER
-	select DRM_TTM
-	select DRM_TTM_HELPER
-	help
-	  Choose this option for qemu.
-	  If M is selected the module will be called bochs-drm.
diff --git a/drivers/gpu/drm/bochs/Makefile b/drivers/gpu/drm/bochs/Makefile
deleted file mode 100644
index 55473371300f..000000000000
--- a/drivers/gpu/drm/bochs/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-bochs-drm-y := bochs_drv.o bochs_mm.o bochs_kms.o bochs_hw.o
-
-obj-$(CONFIG_DRM_BOCHS)	+= bochs-drm.o
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
deleted file mode 100644
index e9645c612aff..000000000000
--- a/drivers/gpu/drm/bochs/bochs.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#include <linux/io.h>
-#include <linux/console.h>
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_encoder.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_gem.h>
-#include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_simple_kms_helper.h>
-
-/* ---------------------------------------------------------------------- */
-
-#define VBE_DISPI_IOPORT_INDEX           0x01CE
-#define VBE_DISPI_IOPORT_DATA            0x01CF
-
-#define VBE_DISPI_INDEX_ID               0x0
-#define VBE_DISPI_INDEX_XRES             0x1
-#define VBE_DISPI_INDEX_YRES             0x2
-#define VBE_DISPI_INDEX_BPP              0x3
-#define VBE_DISPI_INDEX_ENABLE           0x4
-#define VBE_DISPI_INDEX_BANK             0x5
-#define VBE_DISPI_INDEX_VIRT_WIDTH       0x6
-#define VBE_DISPI_INDEX_VIRT_HEIGHT      0x7
-#define VBE_DISPI_INDEX_X_OFFSET         0x8
-#define VBE_DISPI_INDEX_Y_OFFSET         0x9
-#define VBE_DISPI_INDEX_VIDEO_MEMORY_64K 0xa
-
-#define VBE_DISPI_ID0                    0xB0C0
-#define VBE_DISPI_ID1                    0xB0C1
-#define VBE_DISPI_ID2                    0xB0C2
-#define VBE_DISPI_ID3                    0xB0C3
-#define VBE_DISPI_ID4                    0xB0C4
-#define VBE_DISPI_ID5                    0xB0C5
-
-#define VBE_DISPI_DISABLED               0x00
-#define VBE_DISPI_ENABLED                0x01
-#define VBE_DISPI_GETCAPS                0x02
-#define VBE_DISPI_8BIT_DAC               0x20
-#define VBE_DISPI_LFB_ENABLED            0x40
-#define VBE_DISPI_NOCLEARMEM             0x80
-
-/* ---------------------------------------------------------------------- */
-
-enum bochs_types {
-	BOCHS_QEMU_STDVGA,
-	BOCHS_UNKNOWN,
-};
-
-struct bochs_device {
-	/* hw */
-	void __iomem   *mmio;
-	int            ioports;
-	void __iomem   *fb_map;
-	unsigned long  fb_base;
-	unsigned long  fb_size;
-	unsigned long  qext_size;
-
-	/* mode */
-	u16 xres;
-	u16 yres;
-	u16 yres_virtual;
-	u32 stride;
-	u32 bpp;
-	struct edid *edid;
-
-	/* drm */
-	struct drm_device *dev;
-	struct drm_simple_display_pipe pipe;
-	struct drm_connector connector;
-};
-
-/* ---------------------------------------------------------------------- */
-
-/* bochs_hw.c */
-int bochs_hw_init(struct drm_device *dev);
-void bochs_hw_fini(struct drm_device *dev);
-
-void bochs_hw_blank(struct bochs_device *bochs, bool blank);
-void bochs_hw_setmode(struct bochs_device *bochs,
-		      struct drm_display_mode *mode);
-void bochs_hw_setformat(struct bochs_device *bochs,
-			const struct drm_format_info *format);
-void bochs_hw_setbase(struct bochs_device *bochs,
-		      int x, int y, int stride, u64 addr);
-int bochs_hw_load_edid(struct bochs_device *bochs);
-
-/* bochs_mm.c */
-int bochs_mm_init(struct bochs_device *bochs);
-void bochs_mm_fini(struct bochs_device *bochs);
-
-/* bochs_kms.c */
-int bochs_kms_init(struct bochs_device *bochs);
-
-/* bochs_fbdev.c */
-extern const struct drm_mode_config_funcs bochs_mode_funcs;
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
deleted file mode 100644
index c828cadbabff..000000000000
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ /dev/null
@@ -1,205 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include <linux/module.h>
-#include <linux/pci.h>
-
-#include <drm/drm_drv.h>
-#include <drm/drm_aperture.h>
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_managed.h>
-
-#include "bochs.h"
-
-static int bochs_modeset = -1;
-module_param_named(modeset, bochs_modeset, int, 0444);
-MODULE_PARM_DESC(modeset, "enable/disable kernel modesetting");
-
-/* ---------------------------------------------------------------------- */
-/* drm interface                                                          */
-
-static void bochs_unload(struct drm_device *dev)
-{
-	struct bochs_device *bochs = dev->dev_private;
-
-	bochs_mm_fini(bochs);
-}
-
-static int bochs_load(struct drm_device *dev)
-{
-	struct bochs_device *bochs;
-	int ret;
-
-	bochs = drmm_kzalloc(dev, sizeof(*bochs), GFP_KERNEL);
-	if (bochs == NULL)
-		return -ENOMEM;
-	dev->dev_private = bochs;
-	bochs->dev = dev;
-
-	ret = bochs_hw_init(dev);
-	if (ret)
-		goto err;
-
-	ret = bochs_mm_init(bochs);
-	if (ret)
-		goto err;
-
-	ret = bochs_kms_init(bochs);
-	if (ret)
-		goto err;
-
-	return 0;
-
-err:
-	bochs_unload(dev);
-	return ret;
-}
-
-DEFINE_DRM_GEM_FOPS(bochs_fops);
-
-static const struct drm_driver bochs_driver = {
-	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
-	.fops			= &bochs_fops,
-	.name			= "bochs-drm",
-	.desc			= "bochs dispi vga interface (qemu stdvga)",
-	.date			= "20130925",
-	.major			= 1,
-	.minor			= 0,
-	DRM_GEM_VRAM_DRIVER,
-	.release                = bochs_unload,
-};
-
-/* ---------------------------------------------------------------------- */
-/* pm interface                                                           */
-
-#ifdef CONFIG_PM_SLEEP
-static int bochs_pm_suspend(struct device *dev)
-{
-	struct drm_device *drm_dev = dev_get_drvdata(dev);
-
-	return drm_mode_config_helper_suspend(drm_dev);
-}
-
-static int bochs_pm_resume(struct device *dev)
-{
-	struct drm_device *drm_dev = dev_get_drvdata(dev);
-
-	return drm_mode_config_helper_resume(drm_dev);
-}
-#endif
-
-static const struct dev_pm_ops bochs_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend,
-				bochs_pm_resume)
-};
-
-/* ---------------------------------------------------------------------- */
-/* pci interface                                                          */
-
-static int bochs_pci_probe(struct pci_dev *pdev,
-			   const struct pci_device_id *ent)
-{
-	struct drm_device *dev;
-	unsigned long fbsize;
-	int ret;
-
-	fbsize = pci_resource_len(pdev, 0);
-	if (fbsize < 4 * 1024 * 1024) {
-		DRM_ERROR("less than 4 MB video memory, ignoring device\n");
-		return -ENOMEM;
-	}
-
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "bochsdrmfb");
-	if (ret)
-		return ret;
-
-	dev = drm_dev_alloc(&bochs_driver, &pdev->dev);
-	if (IS_ERR(dev))
-		return PTR_ERR(dev);
-
-	ret = pci_enable_device(pdev);
-	if (ret)
-		goto err_free_dev;
-
-	pci_set_drvdata(pdev, dev);
-
-	ret = bochs_load(dev);
-	if (ret)
-		goto err_free_dev;
-
-	ret = drm_dev_register(dev, 0);
-	if (ret)
-		goto err_unload;
-
-	drm_fbdev_generic_setup(dev, 32);
-	return ret;
-
-err_unload:
-	bochs_unload(dev);
-err_free_dev:
-	drm_dev_put(dev);
-	return ret;
-}
-
-static void bochs_pci_remove(struct pci_dev *pdev)
-{
-	struct drm_device *dev = pci_get_drvdata(pdev);
-
-	drm_dev_unplug(dev);
-	drm_atomic_helper_shutdown(dev);
-	bochs_hw_fini(dev);
-	drm_dev_put(dev);
-}
-
-static const struct pci_device_id bochs_pci_tbl[] = {
-	{
-		.vendor      = 0x1234,
-		.device      = 0x1111,
-		.subvendor   = PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
-		.subdevice   = PCI_SUBDEVICE_ID_QEMU,
-		.driver_data = BOCHS_QEMU_STDVGA,
-	},
-	{
-		.vendor      = 0x1234,
-		.device      = 0x1111,
-		.subvendor   = PCI_ANY_ID,
-		.subdevice   = PCI_ANY_ID,
-		.driver_data = BOCHS_UNKNOWN,
-	},
-	{ /* end of list */ }
-};
-
-static struct pci_driver bochs_pci_driver = {
-	.name =		"bochs-drm",
-	.id_table =	bochs_pci_tbl,
-	.probe =	bochs_pci_probe,
-	.remove =	bochs_pci_remove,
-	.driver.pm =    &bochs_pm_ops,
-};
-
-/* ---------------------------------------------------------------------- */
-/* module init/exit                                                       */
-
-static int __init bochs_init(void)
-{
-	if (vgacon_text_force() && bochs_modeset == -1)
-		return -EINVAL;
-
-	if (bochs_modeset == 0)
-		return -EINVAL;
-
-	return pci_register_driver(&bochs_pci_driver);
-}
-
-static void __exit bochs_exit(void)
-{
-	pci_unregister_driver(&bochs_pci_driver);
-}
-
-module_init(bochs_init);
-module_exit(bochs_exit);
-
-MODULE_DEVICE_TABLE(pci, bochs_pci_tbl);
-MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c
deleted file mode 100644
index 7d3426d8cc69..000000000000
--- a/drivers/gpu/drm/bochs/bochs_hw.c
+++ /dev/null
@@ -1,323 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include <linux/pci.h>
-
-#include <drm/drm_drv.h>
-#include <drm/drm_fourcc.h>
-
-#include <video/vga.h>
-#include "bochs.h"
-
-/* ---------------------------------------------------------------------- */
-
-static void bochs_vga_writeb(struct bochs_device *bochs, u16 ioport, u8 val)
-{
-	if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df))
-		return;
-
-	if (bochs->mmio) {
-		int offset = ioport - 0x3c0 + 0x400;
-		writeb(val, bochs->mmio + offset);
-	} else {
-		outb(val, ioport);
-	}
-}
-
-static u8 bochs_vga_readb(struct bochs_device *bochs, u16 ioport)
-{
-	if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df))
-		return 0xff;
-
-	if (bochs->mmio) {
-		int offset = ioport - 0x3c0 + 0x400;
-		return readb(bochs->mmio + offset);
-	} else {
-		return inb(ioport);
-	}
-}
-
-static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg)
-{
-	u16 ret = 0;
-
-	if (bochs->mmio) {
-		int offset = 0x500 + (reg << 1);
-		ret = readw(bochs->mmio + offset);
-	} else {
-		outw(reg, VBE_DISPI_IOPORT_INDEX);
-		ret = inw(VBE_DISPI_IOPORT_DATA);
-	}
-	return ret;
-}
-
-static void bochs_dispi_write(struct bochs_device *bochs, u16 reg, u16 val)
-{
-	if (bochs->mmio) {
-		int offset = 0x500 + (reg << 1);
-		writew(val, bochs->mmio + offset);
-	} else {
-		outw(reg, VBE_DISPI_IOPORT_INDEX);
-		outw(val, VBE_DISPI_IOPORT_DATA);
-	}
-}
-
-static void bochs_hw_set_big_endian(struct bochs_device *bochs)
-{
-	if (bochs->qext_size < 8)
-		return;
-
-	writel(0xbebebebe, bochs->mmio + 0x604);
-}
-
-static void bochs_hw_set_little_endian(struct bochs_device *bochs)
-{
-	if (bochs->qext_size < 8)
-		return;
-
-	writel(0x1e1e1e1e, bochs->mmio + 0x604);
-}
-
-#ifdef __BIG_ENDIAN
-#define bochs_hw_set_native_endian(_b) bochs_hw_set_big_endian(_b)
-#else
-#define bochs_hw_set_native_endian(_b) bochs_hw_set_little_endian(_b)
-#endif
-
-static int bochs_get_edid_block(void *data, u8 *buf,
-				unsigned int block, size_t len)
-{
-	struct bochs_device *bochs = data;
-	size_t i, start = block * EDID_LENGTH;
-
-	if (start + len > 0x400 /* vga register offset */)
-		return -1;
-
-	for (i = 0; i < len; i++) {
-		buf[i] = readb(bochs->mmio + start + i);
-	}
-	return 0;
-}
-
-int bochs_hw_load_edid(struct bochs_device *bochs)
-{
-	u8 header[8];
-
-	if (!bochs->mmio)
-		return -1;
-
-	/* check header to detect whenever edid support is enabled in qemu */
-	bochs_get_edid_block(bochs, header, 0, ARRAY_SIZE(header));
-	if (drm_edid_header_is_valid(header) != 8)
-		return -1;
-
-	kfree(bochs->edid);
-	bochs->edid = drm_do_get_edid(&bochs->connector,
-				      bochs_get_edid_block, bochs);
-	if (bochs->edid == NULL)
-		return -1;
-
-	return 0;
-}
-
-int bochs_hw_init(struct drm_device *dev)
-{
-	struct bochs_device *bochs = dev->dev_private;
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	unsigned long addr, size, mem, ioaddr, iosize;
-	u16 id;
-
-	if (pdev->resource[2].flags & IORESOURCE_MEM) {
-		/* mmio bar with vga and bochs registers present */
-		if (pci_request_region(pdev, 2, "bochs-drm") != 0) {
-			DRM_ERROR("Cannot request mmio region\n");
-			return -EBUSY;
-		}
-		ioaddr = pci_resource_start(pdev, 2);
-		iosize = pci_resource_len(pdev, 2);
-		bochs->mmio = ioremap(ioaddr, iosize);
-		if (bochs->mmio == NULL) {
-			DRM_ERROR("Cannot map mmio region\n");
-			return -ENOMEM;
-		}
-	} else {
-		ioaddr = VBE_DISPI_IOPORT_INDEX;
-		iosize = 2;
-		if (!request_region(ioaddr, iosize, "bochs-drm")) {
-			DRM_ERROR("Cannot request ioports\n");
-			return -EBUSY;
-		}
-		bochs->ioports = 1;
-	}
-
-	id = bochs_dispi_read(bochs, VBE_DISPI_INDEX_ID);
-	mem = bochs_dispi_read(bochs, VBE_DISPI_INDEX_VIDEO_MEMORY_64K)
-		* 64 * 1024;
-	if ((id & 0xfff0) != VBE_DISPI_ID0) {
-		DRM_ERROR("ID mismatch\n");
-		return -ENODEV;
-	}
-
-	if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0)
-		return -ENODEV;
-	addr = pci_resource_start(pdev, 0);
-	size = pci_resource_len(pdev, 0);
-	if (addr == 0)
-		return -ENODEV;
-	if (size != mem) {
-		DRM_ERROR("Size mismatch: pci=%ld, bochs=%ld\n",
-			size, mem);
-		size = min(size, mem);
-	}
-
-	if (pci_request_region(pdev, 0, "bochs-drm") != 0)
-		DRM_WARN("Cannot request framebuffer, boot fb still active?\n");
-
-	bochs->fb_map = ioremap(addr, size);
-	if (bochs->fb_map == NULL) {
-		DRM_ERROR("Cannot map framebuffer\n");
-		return -ENOMEM;
-	}
-	bochs->fb_base = addr;
-	bochs->fb_size = size;
-
-	DRM_INFO("Found bochs VGA, ID 0x%x.\n", id);
-	DRM_INFO("Framebuffer size %ld kB @ 0x%lx, %s @ 0x%lx.\n",
-		 size / 1024, addr,
-		 bochs->ioports ? "ioports" : "mmio",
-		 ioaddr);
-
-	if (bochs->mmio && pdev->revision >= 2) {
-		bochs->qext_size = readl(bochs->mmio + 0x600);
-		if (bochs->qext_size < 4 || bochs->qext_size > iosize) {
-			bochs->qext_size = 0;
-			goto noext;
-		}
-		DRM_DEBUG("Found qemu ext regs, size %ld\n",
-			  bochs->qext_size);
-		bochs_hw_set_native_endian(bochs);
-	}
-
-noext:
-	return 0;
-}
-
-void bochs_hw_fini(struct drm_device *dev)
-{
-	struct bochs_device *bochs = dev->dev_private;
-
-	/* TODO: shot down existing vram mappings */
-
-	if (bochs->mmio)
-		iounmap(bochs->mmio);
-	if (bochs->ioports)
-		release_region(VBE_DISPI_IOPORT_INDEX, 2);
-	if (bochs->fb_map)
-		iounmap(bochs->fb_map);
-	pci_release_regions(to_pci_dev(dev->dev));
-	kfree(bochs->edid);
-}
-
-void bochs_hw_blank(struct bochs_device *bochs, bool blank)
-{
-	DRM_DEBUG_DRIVER("hw_blank %d\n", blank);
-	/* discard ar_flip_flop */
-	(void)bochs_vga_readb(bochs, VGA_IS1_RC);
-	/* blank or unblank; we need only update index and set 0x20 */
-	bochs_vga_writeb(bochs, VGA_ATT_W, blank ? 0 : 0x20);
-}
-
-void bochs_hw_setmode(struct bochs_device *bochs,
-		      struct drm_display_mode *mode)
-{
-	int idx;
-
-	if (!drm_dev_enter(bochs->dev, &idx))
-		return;
-
-	bochs->xres = mode->hdisplay;
-	bochs->yres = mode->vdisplay;
-	bochs->bpp = 32;
-	bochs->stride = mode->hdisplay * (bochs->bpp / 8);
-	bochs->yres_virtual = bochs->fb_size / bochs->stride;
-
-	DRM_DEBUG_DRIVER("%dx%d @ %d bpp, vy %d\n",
-			 bochs->xres, bochs->yres, bochs->bpp,
-			 bochs->yres_virtual);
-
-	bochs_hw_blank(bochs, false);
-
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,      0);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP,         bochs->bpp);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES,        bochs->xres);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_YRES,        bochs->yres);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BANK,        0);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH,  bochs->xres);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_HEIGHT,
-			  bochs->yres_virtual);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET,    0);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET,    0);
-
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,
-			  VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED);
-
-	drm_dev_exit(idx);
-}
-
-void bochs_hw_setformat(struct bochs_device *bochs,
-			const struct drm_format_info *format)
-{
-	int idx;
-
-	if (!drm_dev_enter(bochs->dev, &idx))
-		return;
-
-	DRM_DEBUG_DRIVER("format %c%c%c%c\n",
-			 (format->format >>  0) & 0xff,
-			 (format->format >>  8) & 0xff,
-			 (format->format >> 16) & 0xff,
-			 (format->format >> 24) & 0xff);
-
-	switch (format->format) {
-	case DRM_FORMAT_XRGB8888:
-		bochs_hw_set_little_endian(bochs);
-		break;
-	case DRM_FORMAT_BGRX8888:
-		bochs_hw_set_big_endian(bochs);
-		break;
-	default:
-		/* should not happen */
-		DRM_ERROR("%s: Huh? Got framebuffer format 0x%x",
-			  __func__, format->format);
-		break;
-	}
-
-	drm_dev_exit(idx);
-}
-
-void bochs_hw_setbase(struct bochs_device *bochs,
-		      int x, int y, int stride, u64 addr)
-{
-	unsigned long offset;
-	unsigned int vx, vy, vwidth, idx;
-
-	if (!drm_dev_enter(bochs->dev, &idx))
-		return;
-
-	bochs->stride = stride;
-	offset = (unsigned long)addr +
-		y * bochs->stride +
-		x * (bochs->bpp / 8);
-	vy = offset / bochs->stride;
-	vx = (offset % bochs->stride) * 8 / bochs->bpp;
-	vwidth = stride * 8 / bochs->bpp;
-
-	DRM_DEBUG_DRIVER("x %d, y %d, addr %llx -> offset %lx, vx %d, vy %d\n",
-			 x, y, addr, offset, vx, vy);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx);
-	bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy);
-
-	drm_dev_exit(idx);
-}
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
deleted file mode 100644
index 99410e77d51a..000000000000
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ /dev/null
@@ -1,178 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include <linux/moduleparam.h>
-
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_probe_helper.h>
-
-#include "bochs.h"
-
-static int defx = 1024;
-static int defy = 768;
-
-module_param(defx, int, 0444);
-module_param(defy, int, 0444);
-MODULE_PARM_DESC(defx, "default x resolution");
-MODULE_PARM_DESC(defy, "default y resolution");
-
-/* ---------------------------------------------------------------------- */
-
-static const uint32_t bochs_formats[] = {
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_BGRX8888,
-};
-
-static void bochs_plane_update(struct bochs_device *bochs,
-			       struct drm_plane_state *state)
-{
-	struct drm_gem_vram_object *gbo;
-	s64 gpu_addr;
-
-	if (!state->fb || !bochs->stride)
-		return;
-
-	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
-	gpu_addr = drm_gem_vram_offset(gbo);
-	if (WARN_ON_ONCE(gpu_addr < 0))
-		return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
-
-	bochs_hw_setbase(bochs,
-			 state->crtc_x,
-			 state->crtc_y,
-			 state->fb->pitches[0],
-			 state->fb->offsets[0] + gpu_addr);
-	bochs_hw_setformat(bochs, state->fb->format);
-}
-
-static void bochs_pipe_enable(struct drm_simple_display_pipe *pipe,
-			      struct drm_crtc_state *crtc_state,
-			      struct drm_plane_state *plane_state)
-{
-	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
-
-	bochs_hw_setmode(bochs, &crtc_state->mode);
-	bochs_plane_update(bochs, plane_state);
-}
-
-static void bochs_pipe_disable(struct drm_simple_display_pipe *pipe)
-{
-	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
-
-	bochs_hw_blank(bochs, true);
-}
-
-static void bochs_pipe_update(struct drm_simple_display_pipe *pipe,
-			      struct drm_plane_state *old_state)
-{
-	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
-
-	bochs_plane_update(bochs, pipe->plane.state);
-}
-
-static const struct drm_simple_display_pipe_funcs bochs_pipe_funcs = {
-	.enable	    = bochs_pipe_enable,
-	.disable    = bochs_pipe_disable,
-	.update	    = bochs_pipe_update,
-	.prepare_fb = drm_gem_vram_simple_display_pipe_prepare_fb,
-	.cleanup_fb = drm_gem_vram_simple_display_pipe_cleanup_fb,
-};
-
-static int bochs_connector_get_modes(struct drm_connector *connector)
-{
-	struct bochs_device *bochs =
-		container_of(connector, struct bochs_device, connector);
-	int count = 0;
-
-	if (bochs->edid)
-		count = drm_add_edid_modes(connector, bochs->edid);
-
-	if (!count) {
-		count = drm_add_modes_noedid(connector, 8192, 8192);
-		drm_set_preferred_mode(connector, defx, defy);
-	}
-	return count;
-}
-
-static const struct drm_connector_helper_funcs bochs_connector_connector_helper_funcs = {
-	.get_modes = bochs_connector_get_modes,
-};
-
-static const struct drm_connector_funcs bochs_connector_connector_funcs = {
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.reset = drm_atomic_helper_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static void bochs_connector_init(struct drm_device *dev)
-{
-	struct bochs_device *bochs = dev->dev_private;
-	struct drm_connector *connector = &bochs->connector;
-
-	drm_connector_init(dev, connector, &bochs_connector_connector_funcs,
-			   DRM_MODE_CONNECTOR_VIRTUAL);
-	drm_connector_helper_add(connector,
-				 &bochs_connector_connector_helper_funcs);
-
-	bochs_hw_load_edid(bochs);
-	if (bochs->edid) {
-		DRM_INFO("Found EDID data blob.\n");
-		drm_connector_attach_edid_property(connector);
-		drm_connector_update_edid_property(connector, bochs->edid);
-	}
-}
-
-static struct drm_framebuffer *
-bochs_gem_fb_create(struct drm_device *dev, struct drm_file *file,
-		    const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	if (mode_cmd->pixel_format != DRM_FORMAT_XRGB8888 &&
-	    mode_cmd->pixel_format != DRM_FORMAT_BGRX8888)
-		return ERR_PTR(-EINVAL);
-
-	return drm_gem_fb_create(dev, file, mode_cmd);
-}
-
-const struct drm_mode_config_funcs bochs_mode_funcs = {
-	.fb_create = bochs_gem_fb_create,
-	.mode_valid = drm_vram_helper_mode_valid,
-	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = drm_atomic_helper_commit,
-};
-
-int bochs_kms_init(struct bochs_device *bochs)
-{
-	int ret;
-
-	ret = drmm_mode_config_init(bochs->dev);
-	if (ret)
-		return ret;
-
-	bochs->dev->mode_config.max_width = 8192;
-	bochs->dev->mode_config.max_height = 8192;
-
-	bochs->dev->mode_config.fb_base = bochs->fb_base;
-	bochs->dev->mode_config.preferred_depth = 24;
-	bochs->dev->mode_config.prefer_shadow = 0;
-	bochs->dev->mode_config.prefer_shadow_fbdev = 1;
-	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
-
-	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
-
-	bochs_connector_init(bochs->dev);
-	drm_simple_display_pipe_init(bochs->dev,
-				     &bochs->pipe,
-				     &bochs_pipe_funcs,
-				     bochs_formats,
-				     ARRAY_SIZE(bochs_formats),
-				     NULL,
-				     &bochs->connector);
-
-	drm_mode_config_reset(bochs->dev);
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
deleted file mode 100644
index 1b74f530b07c..000000000000
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ /dev/null
@@ -1,24 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include "bochs.h"
-
-/* ---------------------------------------------------------------------- */
-
-int bochs_mm_init(struct bochs_device *bochs)
-{
-	struct drm_vram_mm *vmm;
-
-	vmm = drm_vram_helper_alloc_mm(bochs->dev, bochs->fb_base,
-				       bochs->fb_size);
-	return PTR_ERR_OR_ZERO(vmm);
-}
-
-void bochs_mm_fini(struct bochs_device *bochs)
-{
-	if (!bochs->dev->vram_mm)
-		return;
-
-	drm_vram_helper_release_mm(bochs->dev);
-}
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 85b673613687..431b6e12a81f 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -303,6 +303,7 @@ config DRM_TI_SN65DSI86
 	select DRM_PANEL
 	select DRM_MIPI_DSI
 	select AUXILIARY_BUS
+	select DRM_DP_AUX_BUS
 	help
 	  Texas Instruments SN65DSI86 DSI to eDP Bridge driver
 
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c
index aa19d5a40e31..59d718bde8c4 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7533.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c
@@ -165,7 +165,7 @@ int adv7533_attach_dsi(struct adv7511 *adv)
 	dsi->lanes = adv->num_dsi_lanes;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-			  MIPI_DSI_MODE_EOT_PACKET | MIPI_DSI_MODE_VIDEO_HSE;
+			  MIPI_DSI_MODE_NO_EOT_PACKET | MIPI_DSI_MODE_VIDEO_HSE;
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 550814ca2139..b7d2e4449cfa 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1583,7 +1583,6 @@ static int analogix_dp_create_bridge(struct drm_device *drm_dev,
 				     struct analogix_dp_device *dp)
 {
 	struct drm_bridge *bridge;
-	int ret;
 
 	bridge = devm_kzalloc(drm_dev->dev, sizeof(*bridge), GFP_KERNEL);
 	if (!bridge) {
@@ -1596,13 +1595,7 @@ static int analogix_dp_create_bridge(struct drm_device *drm_dev,
 	bridge->driver_private = dp;
 	bridge->funcs = &analogix_dp_bridge_funcs;
 
-	ret = drm_bridge_attach(dp->encoder, bridge, NULL, 0);
-	if (ret) {
-		DRM_ERROR("failed to attach drm bridge\n");
-		return -EINVAL;
-	}
-
-	return 0;
+	return drm_bridge_attach(dp->encoder, bridge, NULL, 0);
 }
 
 static int analogix_dp_dt_parse_pdata(struct analogix_dp_device *dp)
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index 7519b7a0f29d..14d73fb1dd15 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -384,6 +384,25 @@ static int anx7625_odfc_config(struct anx7625_data *ctx,
 	return ret;
 }
 
+/*
+ * The MIPI source video data exist large variation (e.g. 59Hz ~ 61Hz),
+ * anx7625 defined K ratio for matching MIPI input video clock and
+ * DP output video clock. Increase K value can match bigger video data
+ * variation. IVO panel has small variation than DP CTS spec, need
+ * decrease the K value.
+ */
+static int anx7625_set_k_value(struct anx7625_data *ctx)
+{
+	struct edid *edid = (struct edid *)ctx->slimport_edid_p.edid_raw_data;
+
+	if (edid->mfg_id[0] == IVO_MID0 && edid->mfg_id[1] == IVO_MID1)
+		return anx7625_reg_write(ctx, ctx->i2c.rx_p1_client,
+					 MIPI_DIGITAL_ADJ_1, 0x3B);
+
+	return anx7625_reg_write(ctx, ctx->i2c.rx_p1_client,
+				 MIPI_DIGITAL_ADJ_1, 0x3D);
+}
+
 static int anx7625_dsi_video_timing_config(struct anx7625_data *ctx)
 {
 	struct device *dev = &ctx->client->dev;
@@ -470,9 +489,8 @@ static int anx7625_dsi_video_timing_config(struct anx7625_data *ctx)
 			MIPI_PLL_N_NUM_15_8, (n >> 8) & 0xff);
 	ret |= anx7625_reg_write(ctx, ctx->i2c.rx_p1_client, MIPI_PLL_N_NUM_7_0,
 			(n & 0xff));
-	/* Diff */
-	ret |= anx7625_reg_write(ctx, ctx->i2c.rx_p1_client,
-			MIPI_DIGITAL_ADJ_1, 0x3D);
+
+	anx7625_set_k_value(ctx);
 
 	ret |= anx7625_odfc_config(ctx, post_divider - 1);
 
@@ -1307,7 +1325,7 @@ static int anx7625_attach_dsi(struct anx7625_data *ctx)
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO	|
 		MIPI_DSI_MODE_VIDEO_SYNC_PULSE	|
-		MIPI_DSI_MODE_EOT_PACKET	|
+		MIPI_DSI_MODE_NO_EOT_PACKET	|
 		MIPI_DSI_MODE_VIDEO_HSE;
 
 	if (mipi_dsi_attach(dsi) < 0) {
@@ -1359,11 +1377,8 @@ static int anx7625_bridge_attach(struct drm_bridge *bridge,
 		err = drm_bridge_attach(bridge->encoder,
 					ctx->pdata.panel_bridge,
 					&ctx->bridge, flags);
-		if (err) {
-			DRM_DEV_ERROR(dev,
-				      "Fail to attach panel bridge: %d\n", err);
+		if (err)
 			return err;
-		}
 	}
 
 	ctx->bridge_attached = 1;
@@ -1730,7 +1745,6 @@ static int __maybe_unused anx7625_suspend(struct device *dev)
 	if (!pm_runtime_enabled(dev) || !pm_runtime_suspended(dev)) {
 		anx7625_runtime_pm_suspend(dev);
 		disable_irq(ctx->pdata.intp_irq);
-		flush_workqueue(ctx->workqueue);
 	}
 
 	return 0;
@@ -1790,7 +1804,8 @@ static int anx7625_i2c_probe(struct i2c_client *client,
 	platform->pdata.intp_irq = client->irq;
 	if (platform->pdata.intp_irq) {
 		INIT_WORK(&platform->work, anx7625_work_func);
-		platform->workqueue = create_workqueue("anx7625_work");
+		platform->workqueue = alloc_workqueue("anx7625_work",
+						      WQ_FREEZABLE | WQ_MEM_RECLAIM, 1);
 		if (!platform->workqueue) {
 			DRM_DEV_ERROR(dev, "fail to create work queue\n");
 			ret = -ENOMEM;
@@ -1874,6 +1889,7 @@ static const struct of_device_id anx_match_table[] = {
 	{.compatible = "analogix,anx7625",},
 	{},
 };
+MODULE_DEVICE_TABLE(of, anx_match_table);
 
 static struct i2c_driver anx7625_driver = {
 	.driver = {
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h
index 034c3840028f..6dcf64c703f9 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.h
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.h
@@ -210,7 +210,9 @@
 #define  MIPI_VIDEO_STABLE_CNT           0x0A
 
 #define  MIPI_LANE_CTRL_10               0x0F
-#define  MIPI_DIGITAL_ADJ_1   0x1B
+#define  MIPI_DIGITAL_ADJ_1     0x1B
+#define  IVO_MID0               0x26
+#define  IVO_MID1               0xCF
 
 #define  MIPI_PLL_M_NUM_23_16   0x1E
 #define  MIPI_PLL_M_NUM_15_8    0x1F
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index b31281f76117..e6e331071a00 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -829,7 +829,7 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	tmp = DIV_ROUND_UP(dsi_cfg.htotal, nlanes) -
 	      DIV_ROUND_UP(dsi_cfg.hsa, nlanes);
 
-	if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(output->dev->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		tmp -= DIV_ROUND_UP(DSI_EOT_PKT_SIZE, nlanes);
 
 	tx_byte_period = DIV_ROUND_DOWN_ULL((u64)NSEC_PER_SEC * 8,
@@ -902,7 +902,7 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	tmp = readl(dsi->regs + MCTL_MAIN_DATA_CTL);
 	tmp &= ~(IF_VID_SELECT_MASK | HOST_EOT_GEN | IF_VID_MODE);
 
-	if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(output->dev->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		tmp |= HOST_EOT_GEN;
 
 	if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO)
diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c
index 7149ed40af83..2f2a09adb4bc 100644
--- a/drivers/gpu/drm/bridge/ite-it66121.c
+++ b/drivers/gpu/drm/bridge/ite-it66121.c
@@ -536,6 +536,8 @@ static int it66121_bridge_attach(struct drm_bridge *bridge,
 		return -EINVAL;
 
 	ret = drm_bridge_attach(bridge->encoder, ctx->next_bridge, bridge, flags);
+	if (ret)
+		return ret;
 
 	ret = regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG,
 				IT66121_CLK_BANK_PWROFF_RCLK, 0);
diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c
index 76c720b535fb..1b0c7eaf6c84 100644
--- a/drivers/gpu/drm/bridge/lontium-lt8912b.c
+++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c
@@ -487,7 +487,7 @@ static int lt8912_attach_dsi(struct lt8912 *lt)
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO |
 			  MIPI_DSI_MODE_VIDEO_BURST |
 			  MIPI_DSI_MODE_LPM |
-			  MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index 873995f0a741..ed8ac5059cd2 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -48,12 +48,6 @@ enum transfer_direction {
 #define NWL_DSI_ENDPOINT_LCDIF 0
 #define NWL_DSI_ENDPOINT_DCSS 1
 
-struct nwl_dsi_plat_clk_config {
-	const char *id;
-	struct clk *clk;
-	bool present;
-};
-
 struct nwl_dsi_transfer {
 	const struct mipi_dsi_msg *msg;
 	struct mipi_dsi_packet packet;
@@ -196,7 +190,7 @@ static u32 ps2bc(struct nwl_dsi *dsi, unsigned long long ps)
 	u32 bpp = mipi_dsi_pixel_format_to_bpp(dsi->format);
 
 	return DIV64_U64_ROUND_UP(ps * dsi->mode.clock * bpp,
-				  dsi->lanes * 8 * NSEC_PER_SEC);
+				  dsi->lanes * 8ULL * NSEC_PER_SEC);
 }
 
 /*
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index e7c7c9b9c646..f08d0fded61f 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -143,6 +143,7 @@ struct dw_hdmi_phy_data {
 struct dw_hdmi {
 	struct drm_connector connector;
 	struct drm_bridge bridge;
+	struct drm_bridge *next_bridge;
 
 	unsigned int version;
 
@@ -2775,7 +2776,8 @@ static int dw_hdmi_bridge_attach(struct drm_bridge *bridge,
 	struct dw_hdmi *hdmi = bridge->driver_private;
 
 	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)
-		return 0;
+		return drm_bridge_attach(bridge->encoder, hdmi->next_bridge,
+					 bridge, flags);
 
 	return dw_hdmi_connector_create(hdmi);
 }
@@ -3160,6 +3162,52 @@ static void dw_hdmi_init_hw(struct dw_hdmi *hdmi)
 /* -----------------------------------------------------------------------------
  * Probe/remove API, used from platforms based on the DRM bridge API.
  */
+
+static int dw_hdmi_parse_dt(struct dw_hdmi *hdmi)
+{
+	struct device_node *endpoint;
+	struct device_node *remote;
+
+	if (!hdmi->plat_data->output_port)
+		return 0;
+
+	endpoint = of_graph_get_endpoint_by_regs(hdmi->dev->of_node,
+						 hdmi->plat_data->output_port,
+						 -1);
+	if (!endpoint) {
+		/*
+		 * On platforms whose bindings don't make the output port
+		 * mandatory (such as Rockchip) the plat_data->output_port
+		 * field isn't set, so it's safe to make this a fatal error.
+		 */
+		dev_err(hdmi->dev, "Missing endpoint in port@%u\n",
+			hdmi->plat_data->output_port);
+		return -ENODEV;
+	}
+
+	remote = of_graph_get_remote_port_parent(endpoint);
+	of_node_put(endpoint);
+	if (!remote) {
+		dev_err(hdmi->dev, "Endpoint in port@%u unconnected\n",
+			hdmi->plat_data->output_port);
+		return -ENODEV;
+	}
+
+	if (!of_device_is_available(remote)) {
+		dev_err(hdmi->dev, "port@%u remote device is disabled\n",
+			hdmi->plat_data->output_port);
+		of_node_put(remote);
+		return -ENODEV;
+	}
+
+	hdmi->next_bridge = of_drm_find_bridge(remote);
+	of_node_put(remote);
+	if (!hdmi->next_bridge)
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 struct dw_hdmi *dw_hdmi_probe(struct platform_device *pdev,
 			      const struct dw_hdmi_plat_data *plat_data)
 {
@@ -3196,6 +3244,10 @@ struct dw_hdmi *dw_hdmi_probe(struct platform_device *pdev,
 	mutex_init(&hdmi->cec_notifier_mutex);
 	spin_lock_init(&hdmi->audio_lock);
 
+	ret = dw_hdmi_parse_dt(hdmi);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
 	if (ddc_node) {
 		hdmi->ddc = of_get_i2c_adapter_by_node(ddc_node);
@@ -3474,7 +3526,6 @@ struct dw_hdmi *dw_hdmi_bind(struct platform_device *pdev,
 	ret = drm_bridge_attach(encoder, &hdmi->bridge, NULL, 0);
 	if (ret) {
 		dw_hdmi_remove(hdmi);
-		DRM_ERROR("Failed to initialize bridge with drm\n");
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index 6b268f9445b3..e44e18a0112a 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -246,6 +246,7 @@ struct dw_mipi_dsi {
 
 	struct clk *pclk;
 
+	bool device_found;
 	unsigned int lane_mbps; /* per lane */
 	u32 channel;
 	u32 lanes;
@@ -309,13 +310,37 @@ static inline u32 dsi_read(struct dw_mipi_dsi *dsi, u32 reg)
 	return readl(dsi->base + reg);
 }
 
+static int dw_mipi_dsi_panel_or_bridge(struct dw_mipi_dsi *dsi,
+				       struct device_node *node)
+{
+	struct drm_bridge *bridge;
+	struct drm_panel *panel;
+	int ret;
+
+	ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge);
+	if (ret)
+		return ret;
+
+	if (panel) {
+		bridge = drm_panel_bridge_add_typed(panel,
+						    DRM_MODE_CONNECTOR_DSI);
+		if (IS_ERR(bridge))
+			return PTR_ERR(bridge);
+	}
+
+	dsi->panel_bridge = bridge;
+
+	if (!dsi->panel_bridge)
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 				   struct mipi_dsi_device *device)
 {
 	struct dw_mipi_dsi *dsi = host_to_dsi(host);
 	const struct dw_mipi_dsi_plat_data *pdata = dsi->plat_data;
-	struct drm_bridge *bridge;
-	struct drm_panel *panel;
 	int ret;
 
 	if (device->lanes > dsi->plat_data->max_data_lanes) {
@@ -329,22 +354,14 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 
-	ret = drm_of_find_panel_or_bridge(host->dev->of_node, 1, 0,
-					  &panel, &bridge);
-	if (ret)
-		return ret;
+	if (!dsi->device_found) {
+		ret = dw_mipi_dsi_panel_or_bridge(dsi, host->dev->of_node);
+		if (ret)
+			return ret;
 
-	if (panel) {
-		bridge = drm_panel_bridge_add_typed(panel,
-						    DRM_MODE_CONNECTOR_DSI);
-		if (IS_ERR(bridge))
-			return PTR_ERR(bridge);
+		dsi->device_found = true;
 	}
 
-	dsi->panel_bridge = bridge;
-
-	drm_bridge_add(&dsi->bridge);
-
 	if (pdata->host_ops && pdata->host_ops->attach) {
 		ret = pdata->host_ops->attach(pdata->priv_data, device);
 		if (ret < 0)
@@ -999,6 +1016,16 @@ static int dw_mipi_dsi_bridge_attach(struct drm_bridge *bridge,
 	/* Set the encoder type as caller does not know it */
 	bridge->encoder->encoder_type = DRM_MODE_ENCODER_DSI;
 
+	if (!dsi->device_found) {
+		int ret;
+
+		ret = dw_mipi_dsi_panel_or_bridge(dsi, dsi->dev->of_node);
+		if (ret)
+			return ret;
+
+		dsi->device_found = true;
+	}
+
 	/* Attach the panel-bridge to the dsi bridge */
 	return drm_bridge_attach(bridge->encoder, dsi->panel_bridge, bridge,
 				 flags);
@@ -1181,6 +1208,7 @@ __dw_mipi_dsi_probe(struct platform_device *pdev,
 #ifdef CONFIG_OF
 	dsi->bridge.of_node = pdev->dev.of_node;
 #endif
+	drm_bridge_add(&dsi->bridge);
 
 	return dsi;
 }
@@ -1229,15 +1257,7 @@ EXPORT_SYMBOL_GPL(dw_mipi_dsi_remove);
  */
 int dw_mipi_dsi_bind(struct dw_mipi_dsi *dsi, struct drm_encoder *encoder)
 {
-	int ret;
-
-	ret = drm_bridge_attach(encoder, &dsi->bridge, NULL, 0);
-	if (ret) {
-		DRM_ERROR("Failed to initialize bridge with drm\n");
-		return ret;
-	}
-
-	return ret;
+	return drm_bridge_attach(encoder, &dsi->bridge, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(dw_mipi_dsi_bind);
 
diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c
index 8ed8302d6bbb..a3db532bbdd1 100644
--- a/drivers/gpu/drm/bridge/tc358768.c
+++ b/drivers/gpu/drm/bridge/tc358768.c
@@ -291,7 +291,7 @@ static int tc358768_calc_pll(struct tc358768_priv *priv,
 			     const struct drm_display_mode *mode,
 			     bool verify_only)
 {
-	const u32 frs_limits[] = {
+	static const u32 frs_limits[] = {
 		1000000000,
 		500000000,
 		250000000,
@@ -825,7 +825,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge)
 	if (!(dsi_dev->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS))
 		val |= TC358768_DSI_CONTROL_HSCKMD;
 
-	if (dsi_dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET)
+	if (dsi_dev->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET)
 		val |= TC358768_DSI_CONTROL_EOTDIS;
 
 	tc358768_write(priv, TC358768_DSI_CONFW, val);
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
index 750f2172ef08..a32f70bc68ea 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
@@ -137,7 +137,6 @@ enum sn65dsi83_model {
 
 struct sn65dsi83 {
 	struct drm_bridge		bridge;
-	struct drm_display_mode		mode;
 	struct device			*dev;
 	struct regmap			*regmap;
 	struct device_node		*host_node;
@@ -147,8 +146,6 @@ struct sn65dsi83 {
 	int				dsi_lanes;
 	bool				lvds_dual_link;
 	bool				lvds_dual_link_even_odd_swap;
-	bool				lvds_format_24bpp;
-	bool				lvds_format_jeida;
 };
 
 static const struct regmap_range sn65dsi83_readable_ranges[] = {
@@ -291,7 +288,8 @@ err_dsi_attach:
 	return ret;
 }
 
-static void sn65dsi83_pre_enable(struct drm_bridge *bridge)
+static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge,
+					struct drm_bridge_state *old_bridge_state)
 {
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
 
@@ -306,7 +304,8 @@ static void sn65dsi83_pre_enable(struct drm_bridge *bridge)
 	usleep_range(1000, 1100);
 }
 
-static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx)
+static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx,
+				   const struct drm_display_mode *mode)
 {
 	/*
 	 * The encoding of the LVDS_CLK_RANGE is as follows:
@@ -322,7 +321,7 @@ static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx)
 	 * the clock to 25..154 MHz, the range calculation can be simplified
 	 * as follows:
 	 */
-	int mode_clock = ctx->mode.clock;
+	int mode_clock = mode->clock;
 
 	if (ctx->lvds_dual_link)
 		mode_clock /= 2;
@@ -330,7 +329,8 @@ static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx)
 	return (mode_clock - 12500) / 25000;
 }
 
-static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx)
+static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx,
+				  const struct drm_display_mode *mode)
 {
 	/*
 	 * The encoding of the CHA_DSI_CLK_RANGE is as follows:
@@ -346,7 +346,7 @@ static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx)
 	 *  DSI_CLK = mode clock * bpp / dsi_data_lanes / 2
 	 * the 2 is there because the bus is DDR.
 	 */
-	return DIV_ROUND_UP(clamp((unsigned int)ctx->mode.clock *
+	return DIV_ROUND_UP(clamp((unsigned int)mode->clock *
 			    mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) /
 			    ctx->dsi_lanes / 2, 40000U, 500000U), 5000U);
 }
@@ -364,23 +364,73 @@ static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx)
 	return dsi_div - 1;
 }
 
-static void sn65dsi83_enable(struct drm_bridge *bridge)
+static void sn65dsi83_atomic_enable(struct drm_bridge *bridge,
+				    struct drm_bridge_state *old_bridge_state)
 {
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
+	struct drm_atomic_state *state = old_bridge_state->base.state;
+	const struct drm_bridge_state *bridge_state;
+	const struct drm_crtc_state *crtc_state;
+	const struct drm_display_mode *mode;
+	struct drm_connector *connector;
+	struct drm_crtc *crtc;
+	bool lvds_format_24bpp;
+	bool lvds_format_jeida;
 	unsigned int pval;
+	__le16 le16val;
 	u16 val;
 	int ret;
 
+	/* Get the LVDS format from the bridge state. */
+	bridge_state = drm_atomic_get_new_bridge_state(state, bridge);
+
+	switch (bridge_state->output_bus_cfg.format) {
+	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
+		lvds_format_24bpp = false;
+		lvds_format_jeida = true;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
+		lvds_format_24bpp = true;
+		lvds_format_jeida = true;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
+		lvds_format_24bpp = true;
+		lvds_format_jeida = false;
+		break;
+	default:
+		/*
+		 * Some bridges still don't set the correct
+		 * LVDS bus pixel format, use SPWG24 default
+		 * format until those are fixed.
+		 */
+		lvds_format_24bpp = true;
+		lvds_format_jeida = false;
+		dev_warn(ctx->dev,
+			 "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n",
+			 bridge_state->output_bus_cfg.format);
+		break;
+	}
+
+	/*
+	 * Retrieve the CRTC adjusted mode. This requires a little dance to go
+	 * from the bridge to the encoder, to the connector and to the CRTC.
+	 */
+	connector = drm_atomic_get_new_connector_for_encoder(state,
+							     bridge->encoder);
+	crtc = drm_atomic_get_new_connector_state(state, connector)->crtc;
+	crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
+	mode = &crtc_state->adjusted_mode;
+
 	/* Clear reset, disable PLL */
 	regmap_write(ctx->regmap, REG_RC_RESET, 0x00);
 	regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00);
 
 	/* Reference clock derived from DSI link clock. */
 	regmap_write(ctx->regmap, REG_RC_LVDS_PLL,
-		     REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx)) |
+		     REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx, mode)) |
 		     REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY);
 	regmap_write(ctx->regmap, REG_DSI_CLK,
-		     REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx)));
+		     REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx, mode)));
 	regmap_write(ctx->regmap, REG_RC_DSI_CLK,
 		     REG_RC_DSI_CLK_DSI_CLK_DIVIDER(sn65dsi83_get_dsi_div(ctx)));
 
@@ -394,20 +444,20 @@ static void sn65dsi83_enable(struct drm_bridge *bridge)
 	regmap_write(ctx->regmap, REG_DSI_EQ, 0x00);
 
 	/* Set up sync signal polarity. */
-	val = (ctx->mode.flags & DRM_MODE_FLAG_NHSYNC ?
+	val = (mode->flags & DRM_MODE_FLAG_NHSYNC ?
 	       REG_LVDS_FMT_HS_NEG_POLARITY : 0) |
-	      (ctx->mode.flags & DRM_MODE_FLAG_NVSYNC ?
+	      (mode->flags & DRM_MODE_FLAG_NVSYNC ?
 	       REG_LVDS_FMT_VS_NEG_POLARITY : 0);
 
 	/* Set up bits-per-pixel, 18bpp or 24bpp. */
-	if (ctx->lvds_format_24bpp) {
+	if (lvds_format_24bpp) {
 		val |= REG_LVDS_FMT_CHA_24BPP_MODE;
 		if (ctx->lvds_dual_link)
 			val |= REG_LVDS_FMT_CHB_24BPP_MODE;
 	}
 
 	/* Set up LVDS format, JEIDA/Format 1 or SPWG/Format 2 */
-	if (ctx->lvds_format_jeida) {
+	if (lvds_format_jeida) {
 		val |= REG_LVDS_FMT_CHA_24BPP_FORMAT1;
 		if (ctx->lvds_dual_link)
 			val |= REG_LVDS_FMT_CHB_24BPP_FORMAT1;
@@ -426,29 +476,29 @@ static void sn65dsi83_enable(struct drm_bridge *bridge)
 		     REG_LVDS_LANE_CHB_LVDS_TERM);
 	regmap_write(ctx->regmap, REG_LVDS_CM, 0x00);
 
-	val = cpu_to_le16(ctx->mode.hdisplay);
+	le16val = cpu_to_le16(mode->hdisplay);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW,
-			  &val, 2);
-	val = cpu_to_le16(ctx->mode.vdisplay);
+			  &le16val, 2);
+	le16val = cpu_to_le16(mode->vdisplay);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW,
-			  &val, 2);
+			  &le16val, 2);
 	/* 32 + 1 pixel clock to ensure proper operation */
-	val = cpu_to_le16(32 + 1);
-	regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &val, 2);
-	val = cpu_to_le16(ctx->mode.hsync_end - ctx->mode.hsync_start);
+	le16val = cpu_to_le16(32 + 1);
+	regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &le16val, 2);
+	le16val = cpu_to_le16(mode->hsync_end - mode->hsync_start);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW,
-			  &val, 2);
-	val = cpu_to_le16(ctx->mode.vsync_end - ctx->mode.vsync_start);
+			  &le16val, 2);
+	le16val = cpu_to_le16(mode->vsync_end - mode->vsync_start);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW,
-			  &val, 2);
+			  &le16val, 2);
 	regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH,
-		     ctx->mode.htotal - ctx->mode.hsync_end);
+		     mode->htotal - mode->hsync_end);
 	regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH,
-		     ctx->mode.vtotal - ctx->mode.vsync_end);
+		     mode->vtotal - mode->vsync_end);
 	regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH,
-		     ctx->mode.hsync_start - ctx->mode.hdisplay);
+		     mode->hsync_start - mode->hdisplay);
 	regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH,
-		     ctx->mode.vsync_start - ctx->mode.vdisplay);
+		     mode->vsync_start - mode->vdisplay);
 	regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00);
 
 	/* Enable PLL */
@@ -472,7 +522,8 @@ static void sn65dsi83_enable(struct drm_bridge *bridge)
 	regmap_write(ctx->regmap, REG_IRQ_STAT, pval);
 }
 
-static void sn65dsi83_disable(struct drm_bridge *bridge)
+static void sn65dsi83_atomic_disable(struct drm_bridge *bridge,
+				     struct drm_bridge_state *old_bridge_state)
 {
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
 
@@ -481,7 +532,8 @@ static void sn65dsi83_disable(struct drm_bridge *bridge)
 	regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00);
 }
 
-static void sn65dsi83_post_disable(struct drm_bridge *bridge)
+static void sn65dsi83_atomic_post_disable(struct drm_bridge *bridge,
+					  struct drm_bridge_state *old_bridge_state)
 {
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
 
@@ -503,70 +555,44 @@ sn65dsi83_mode_valid(struct drm_bridge *bridge,
 	return MODE_OK;
 }
 
-static void sn65dsi83_mode_set(struct drm_bridge *bridge,
-			       const struct drm_display_mode *mode,
-			       const struct drm_display_mode *adj)
-{
-	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
+#define MAX_INPUT_SEL_FORMATS	1
 
-	ctx->mode = *adj;
-}
-
-static bool sn65dsi83_mode_fixup(struct drm_bridge *bridge,
-				 const struct drm_display_mode *mode,
-				 struct drm_display_mode *adj)
+static u32 *
+sn65dsi83_atomic_get_input_bus_fmts(struct drm_bridge *bridge,
+				    struct drm_bridge_state *bridge_state,
+				    struct drm_crtc_state *crtc_state,
+				    struct drm_connector_state *conn_state,
+				    u32 output_fmt,
+				    unsigned int *num_input_fmts)
 {
-	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
-	u32 input_bus_format = MEDIA_BUS_FMT_RGB888_1X24;
-	struct drm_encoder *encoder = bridge->encoder;
-	struct drm_device *ddev = encoder->dev;
-	struct drm_connector *connector;
+	u32 *input_fmts;
 
-	/* The DSI format is always RGB888_1X24 */
-	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
-		switch (connector->display_info.bus_formats[0]) {
-		case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
-			ctx->lvds_format_24bpp = false;
-			ctx->lvds_format_jeida = true;
-			break;
-		case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
-			ctx->lvds_format_24bpp = true;
-			ctx->lvds_format_jeida = true;
-			break;
-		case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
-			ctx->lvds_format_24bpp = true;
-			ctx->lvds_format_jeida = false;
-			break;
-		default:
-			/*
-			 * Some bridges still don't set the correct
-			 * LVDS bus pixel format, use SPWG24 default
-			 * format until those are fixed.
-			 */
-			ctx->lvds_format_24bpp = true;
-			ctx->lvds_format_jeida = false;
-			dev_warn(ctx->dev,
-				 "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n",
-				 connector->display_info.bus_formats[0]);
-			break;
-		}
+	*num_input_fmts = 0;
 
-		drm_display_info_set_bus_formats(&connector->display_info,
-						 &input_bus_format, 1);
-	}
+	input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts),
+			     GFP_KERNEL);
+	if (!input_fmts)
+		return NULL;
+
+	/* This is the DSI-end bus format */
+	input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24;
+	*num_input_fmts = 1;
 
-	return true;
+	return input_fmts;
 }
 
 static const struct drm_bridge_funcs sn65dsi83_funcs = {
-	.attach		= sn65dsi83_attach,
-	.pre_enable	= sn65dsi83_pre_enable,
-	.enable		= sn65dsi83_enable,
-	.disable	= sn65dsi83_disable,
-	.post_disable	= sn65dsi83_post_disable,
-	.mode_valid	= sn65dsi83_mode_valid,
-	.mode_set	= sn65dsi83_mode_set,
-	.mode_fixup	= sn65dsi83_mode_fixup,
+	.attach			= sn65dsi83_attach,
+	.atomic_pre_enable	= sn65dsi83_atomic_pre_enable,
+	.atomic_enable		= sn65dsi83_atomic_enable,
+	.atomic_disable		= sn65dsi83_atomic_disable,
+	.atomic_post_disable	= sn65dsi83_atomic_post_disable,
+	.mode_valid		= sn65dsi83_mode_valid,
+
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+	.atomic_reset = drm_atomic_helper_bridge_reset,
+	.atomic_get_input_bus_fmts = sn65dsi83_atomic_get_input_bus_fmts,
 };
 
 static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model)
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 45a2969afb2b..41d48a393e7f 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -23,6 +23,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_dp_aux_bus.h>
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_of.h>
@@ -116,6 +117,7 @@
  * struct ti_sn65dsi86 - Platform data for ti-sn65dsi86 driver.
  * @bridge_aux:   AUX-bus sub device for MIPI-to-eDP bridge functionality.
  * @gpio_aux:     AUX-bus sub device for GPIO controller functionality.
+ * @aux_aux:      AUX-bus sub device for eDP AUX channel functionality.
  *
  * @dev:          Pointer to the top level (i2c) device.
  * @regmap:       Regmap for accessing i2c.
@@ -124,9 +126,8 @@
  * @connector:    Our connector.
  * @host_node:    Remote DSI node.
  * @dsi:          Our MIPI DSI source.
- * @edid:         Detected EDID of eDP panel.
  * @refclk:       Our reference clock.
- * @panel:        Our panel.
+ * @next_bridge:  The bridge on the eDP side.
  * @enable_gpio:  The GPIO we toggle to enable the bridge.
  * @supplies:     Data for bulk enabling/disabling our regulators.
  * @dp_lanes:     Count of dp_lanes we're using.
@@ -148,17 +149,17 @@
 struct ti_sn65dsi86 {
 	struct auxiliary_device		bridge_aux;
 	struct auxiliary_device		gpio_aux;
+	struct auxiliary_device		aux_aux;
 
 	struct device			*dev;
 	struct regmap			*regmap;
 	struct drm_dp_aux		aux;
 	struct drm_bridge		bridge;
 	struct drm_connector		connector;
-	struct edid			*edid;
 	struct device_node		*host_node;
 	struct mipi_dsi_device		*dsi;
 	struct clk			*refclk;
-	struct drm_panel		*panel;
+	struct drm_bridge		*next_bridge;
 	struct gpio_desc		*enable_gpio;
 	struct regulator_bulk_data	supplies[SN_REGULATOR_SUPPLY_NUM];
 	int				dp_lanes;
@@ -306,6 +307,9 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev)
 		return ret;
 	}
 
+	/* td2: min 100 us after regulators before enabling the GPIO */
+	usleep_range(100, 110);
+
 	gpiod_set_value(pdata->enable_gpio, 1);
 
 	/*
@@ -393,35 +397,222 @@ static void ti_sn65dsi86_debugfs_init(struct ti_sn65dsi86 *pdata)
 	debugfs_create_file("status", 0600, debugfs, pdata, &status_fops);
 }
 
-/* Connector funcs */
-static struct ti_sn65dsi86 *
-connector_to_ti_sn65dsi86(struct drm_connector *connector)
+/* -----------------------------------------------------------------------------
+ * Auxiliary Devices (*not* AUX)
+ */
+
+static void ti_sn65dsi86_uninit_aux(void *data)
 {
-	return container_of(connector, struct ti_sn65dsi86, connector);
+	auxiliary_device_uninit(data);
 }
 
-static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector)
+static void ti_sn65dsi86_delete_aux(void *data)
 {
-	struct ti_sn65dsi86 *pdata = connector_to_ti_sn65dsi86(connector);
-	struct edid *edid = pdata->edid;
-	int num, ret;
+	auxiliary_device_delete(data);
+}
 
-	if (!edid) {
-		pm_runtime_get_sync(pdata->dev);
-		edid = pdata->edid = drm_get_edid(connector, &pdata->aux.ddc);
-		pm_runtime_put_autosuspend(pdata->dev);
+/*
+ * AUX bus docs say that a non-NULL release is mandatory, but it makes no
+ * sense for the model used here where all of the aux devices are allocated
+ * in the single shared structure. We'll use this noop as a workaround.
+ */
+static void ti_sn65dsi86_noop(struct device *dev) {}
+
+static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata,
+				       struct auxiliary_device *aux,
+				       const char *name)
+{
+	struct device *dev = pdata->dev;
+	int ret;
+
+	aux->name = name;
+	aux->dev.parent = dev;
+	aux->dev.release = ti_sn65dsi86_noop;
+	device_set_of_node_from_dev(&aux->dev, dev);
+	ret = auxiliary_device_init(aux);
+	if (ret)
+		return ret;
+	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_uninit_aux, aux);
+	if (ret)
+		return ret;
+
+	ret = auxiliary_device_add(aux);
+	if (ret)
+		return ret;
+	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_delete_aux, aux);
+
+	return ret;
+}
+
+/* -----------------------------------------------------------------------------
+ * AUX Adapter
+ */
+
+static struct ti_sn65dsi86 *aux_to_ti_sn65dsi86(struct drm_dp_aux *aux)
+{
+	return container_of(aux, struct ti_sn65dsi86, aux);
+}
+
+static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux,
+				  struct drm_dp_aux_msg *msg)
+{
+	struct ti_sn65dsi86 *pdata = aux_to_ti_sn65dsi86(aux);
+	u32 request = msg->request & ~(DP_AUX_I2C_MOT | DP_AUX_I2C_WRITE_STATUS_UPDATE);
+	u32 request_val = AUX_CMD_REQ(msg->request);
+	u8 *buf = msg->buffer;
+	unsigned int len = msg->size;
+	unsigned int val;
+	int ret;
+	u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG];
+
+	if (len > SN_AUX_MAX_PAYLOAD_BYTES)
+		return -EINVAL;
+
+	pm_runtime_get_sync(pdata->dev);
+	mutex_lock(&pdata->comms_mutex);
+
+	/*
+	 * If someone tries to do a DDC over AUX transaction before pre_enable()
+	 * on a device without a dedicated reference clock then we just can't
+	 * do it. Fail right away. This prevents non-refclk users from reading
+	 * the EDID before enabling the panel but such is life.
+	 */
+	if (!pdata->comms_enabled) {
+		ret = -EIO;
+		goto exit;
+	}
+
+	switch (request) {
+	case DP_AUX_NATIVE_WRITE:
+	case DP_AUX_I2C_WRITE:
+	case DP_AUX_NATIVE_READ:
+	case DP_AUX_I2C_READ:
+		regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val);
+		/* Assume it's good */
+		msg->reply = 0;
+		break;
+	default:
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	BUILD_BUG_ON(sizeof(addr_len) != sizeof(__be32));
+	put_unaligned_be32((msg->address & SN_AUX_ADDR_MASK) << 8 | len,
+			   addr_len);
+	regmap_bulk_write(pdata->regmap, SN_AUX_ADDR_19_16_REG, addr_len,
+			  ARRAY_SIZE(addr_len));
+
+	if (request == DP_AUX_NATIVE_WRITE || request == DP_AUX_I2C_WRITE)
+		regmap_bulk_write(pdata->regmap, SN_AUX_WDATA_REG(0), buf, len);
+
+	/* Clear old status bits before start so we don't get confused */
+	regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG,
+		     AUX_IRQ_STATUS_NAT_I2C_FAIL |
+		     AUX_IRQ_STATUS_AUX_RPLY_TOUT |
+		     AUX_IRQ_STATUS_AUX_SHORT);
+
+	regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND);
+
+	/* Zero delay loop because i2c transactions are slow already */
+	ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val,
+				       !(val & AUX_CMD_SEND), 0, 50 * 1000);
+	if (ret)
+		goto exit;
+
+	ret = regmap_read(pdata->regmap, SN_AUX_CMD_STATUS_REG, &val);
+	if (ret)
+		goto exit;
+
+	if (val & AUX_IRQ_STATUS_AUX_RPLY_TOUT) {
+		/*
+		 * The hardware tried the message seven times per the DP spec
+		 * but it hit a timeout. We ignore defers here because they're
+		 * handled in hardware.
+		 */
+		ret = -ETIMEDOUT;
+		goto exit;
 	}
 
-	if (edid && drm_edid_is_valid(edid)) {
-		ret = drm_connector_update_edid_property(connector, edid);
-		if (!ret) {
-			num = drm_add_edid_modes(connector, edid);
-			if (num)
-				return num;
+	if (val & AUX_IRQ_STATUS_AUX_SHORT) {
+		ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len);
+		if (ret)
+			goto exit;
+	} else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) {
+		switch (request) {
+		case DP_AUX_I2C_WRITE:
+		case DP_AUX_I2C_READ:
+			msg->reply |= DP_AUX_I2C_REPLY_NACK;
+			break;
+		case DP_AUX_NATIVE_READ:
+		case DP_AUX_NATIVE_WRITE:
+			msg->reply |= DP_AUX_NATIVE_REPLY_NACK;
+			break;
 		}
+		len = 0;
+		goto exit;
 	}
 
-	return drm_panel_get_modes(pdata->panel, connector);
+	if (request != DP_AUX_NATIVE_WRITE && request != DP_AUX_I2C_WRITE && len != 0)
+		ret = regmap_bulk_read(pdata->regmap, SN_AUX_RDATA_REG(0), buf, len);
+
+exit:
+	mutex_unlock(&pdata->comms_mutex);
+	pm_runtime_mark_last_busy(pdata->dev);
+	pm_runtime_put_autosuspend(pdata->dev);
+
+	if (ret)
+		return ret;
+	return len;
+}
+
+static int ti_sn_aux_probe(struct auxiliary_device *adev,
+			   const struct auxiliary_device_id *id)
+{
+	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
+	int ret;
+
+	pdata->aux.name = "ti-sn65dsi86-aux";
+	pdata->aux.dev = &adev->dev;
+	pdata->aux.transfer = ti_sn_aux_transfer;
+	drm_dp_aux_init(&pdata->aux);
+
+	ret = devm_of_dp_aux_populate_ep_devices(&pdata->aux);
+	if (ret)
+		return ret;
+
+	/*
+	 * The eDP to MIPI bridge parts don't work until the AUX channel is
+	 * setup so we don't add it in the main driver probe, we add it now.
+	 */
+	return ti_sn65dsi86_add_aux_device(pdata, &pdata->bridge_aux, "bridge");
+}
+
+static const struct auxiliary_device_id ti_sn_aux_id_table[] = {
+	{ .name = "ti_sn65dsi86.aux", },
+	{},
+};
+
+static struct auxiliary_driver ti_sn_aux_driver = {
+	.name = "aux",
+	.probe = ti_sn_aux_probe,
+	.id_table = ti_sn_aux_id_table,
+};
+
+/* -----------------------------------------------------------------------------
+ * DRM Connector Operations
+ */
+
+static struct ti_sn65dsi86 *
+connector_to_ti_sn65dsi86(struct drm_connector *connector)
+{
+	return container_of(connector, struct ti_sn65dsi86, connector);
+}
+
+static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector)
+{
+	struct ti_sn65dsi86 *pdata = connector_to_ti_sn65dsi86(connector);
+
+	return drm_bridge_get_modes(pdata->next_bridge, connector);
 }
 
 static enum drm_mode_status
@@ -448,23 +639,32 @@ static const struct drm_connector_funcs ti_sn_bridge_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static struct ti_sn65dsi86 *bridge_to_ti_sn65dsi86(struct drm_bridge *bridge)
+static int ti_sn_bridge_connector_init(struct ti_sn65dsi86 *pdata)
 {
-	return container_of(bridge, struct ti_sn65dsi86, bridge);
-}
+	int ret;
 
-static int ti_sn65dsi86_parse_regulators(struct ti_sn65dsi86 *pdata)
-{
-	unsigned int i;
-	const char * const ti_sn_bridge_supply_names[] = {
-		"vcca", "vcc", "vccio", "vpll",
-	};
+	ret = drm_connector_init(pdata->bridge.dev, &pdata->connector,
+				 &ti_sn_bridge_connector_funcs,
+				 DRM_MODE_CONNECTOR_eDP);
+	if (ret) {
+		DRM_ERROR("Failed to initialize connector with drm\n");
+		return ret;
+	}
 
-	for (i = 0; i < SN_REGULATOR_SUPPLY_NUM; i++)
-		pdata->supplies[i].supply = ti_sn_bridge_supply_names[i];
+	drm_connector_helper_add(&pdata->connector,
+				 &ti_sn_bridge_connector_helper_funcs);
+	drm_connector_attach_encoder(&pdata->connector, pdata->bridge.encoder);
 
-	return devm_regulator_bulk_get(pdata->dev, SN_REGULATOR_SUPPLY_NUM,
-				       pdata->supplies);
+	return 0;
+}
+
+/*------------------------------------------------------------------------------
+ * DRM Bridge
+ */
+
+static struct ti_sn65dsi86 *bridge_to_ti_sn65dsi86(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct ti_sn65dsi86, bridge);
 }
 
 static int ti_sn_bridge_attach(struct drm_bridge *bridge,
@@ -491,17 +691,9 @@ static int ti_sn_bridge_attach(struct drm_bridge *bridge,
 		return ret;
 	}
 
-	ret = drm_connector_init(bridge->dev, &pdata->connector,
-				 &ti_sn_bridge_connector_funcs,
-				 DRM_MODE_CONNECTOR_eDP);
-	if (ret) {
-		DRM_ERROR("Failed to initialize connector with drm\n");
+	ret = ti_sn_bridge_connector_init(pdata);
+	if (ret < 0)
 		goto err_conn_init;
-	}
-
-	drm_connector_helper_add(&pdata->connector,
-				 &ti_sn_bridge_connector_helper_funcs);
-	drm_connector_attach_encoder(&pdata->connector, bridge->encoder);
 
 	/*
 	 * TODO: ideally finding host resource and dsi dev registration needs
@@ -547,8 +739,19 @@ static int ti_sn_bridge_attach(struct drm_bridge *bridge,
 	}
 	pdata->dsi = dsi;
 
+	/* We never want the next bridge to *also* create a connector: */
+	flags |= DRM_BRIDGE_ATTACH_NO_CONNECTOR;
+
+	/* Attach the next bridge */
+	ret = drm_bridge_attach(bridge->encoder, pdata->next_bridge,
+				&pdata->bridge, flags);
+	if (ret < 0)
+		goto err_dsi_detach;
+
 	return 0;
 
+err_dsi_detach:
+	mipi_dsi_detach(dsi);
 err_dsi_attach:
 	mipi_dsi_device_unregister(dsi);
 err_dsi_host:
@@ -567,14 +770,8 @@ static void ti_sn_bridge_disable(struct drm_bridge *bridge)
 {
 	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
 
-	drm_panel_disable(pdata->panel);
-
 	/* disable video stream */
 	regmap_update_bits(pdata->regmap, SN_ENH_FRAME_REG, VSTREAM_ENABLE, 0);
-	/* semi auto link training mode OFF */
-	regmap_write(pdata->regmap, SN_ML_TX_MODE_REG, 0);
-	/* disable DP PLL */
-	regmap_write(pdata->regmap, SN_PLL_ENABLE_REG, 0);
 }
 
 static void ti_sn_bridge_set_dsi_rate(struct ti_sn65dsi86 *pdata)
@@ -633,9 +830,9 @@ static int ti_sn_bridge_calc_min_dp_rate_idx(struct ti_sn65dsi86 *pdata)
 	return i;
 }
 
-static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata,
-					  bool rate_valid[])
+static unsigned int ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata)
 {
+	unsigned int valid_rates = 0;
 	unsigned int rate_per_200khz;
 	unsigned int rate_mhz;
 	u8 dpcd_val;
@@ -675,13 +872,13 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata,
 			     j < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut);
 			     j++) {
 				if (ti_sn_bridge_dp_rate_lut[j] == rate_mhz)
-					rate_valid[j] = true;
+					valid_rates |= BIT(j);
 			}
 		}
 
 		for (i = 0; i < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut); i++) {
-			if (rate_valid[i])
-				return;
+			if (valid_rates & BIT(i))
+				return valid_rates;
 		}
 		DRM_DEV_ERROR(pdata->dev,
 			      "No matching eDP rates in table; falling back\n");
@@ -703,15 +900,17 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata,
 			      (int)dpcd_val);
 		fallthrough;
 	case DP_LINK_BW_5_4:
-		rate_valid[7] = 1;
+		valid_rates |= BIT(7);
 		fallthrough;
 	case DP_LINK_BW_2_7:
-		rate_valid[4] = 1;
+		valid_rates |= BIT(4);
 		fallthrough;
 	case DP_LINK_BW_1_62:
-		rate_valid[1] = 1;
+		valid_rates |= BIT(1);
 		break;
 	}
+
+	return valid_rates;
 }
 
 static void ti_sn_bridge_set_video_timings(struct ti_sn65dsi86 *pdata)
@@ -829,8 +1028,8 @@ exit:
 static void ti_sn_bridge_enable(struct drm_bridge *bridge)
 {
 	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
-	bool rate_valid[ARRAY_SIZE(ti_sn_bridge_dp_rate_lut)] = { };
 	const char *last_err_str = "No supported DP rate";
+	unsigned int valid_rates;
 	int dp_rate_idx;
 	unsigned int val;
 	int ret = -EINVAL;
@@ -869,13 +1068,13 @@ static void ti_sn_bridge_enable(struct drm_bridge *bridge)
 	regmap_update_bits(pdata->regmap, SN_SSC_CONFIG_REG, DP_NUM_LANES_MASK,
 			   val);
 
-	ti_sn_bridge_read_valid_rates(pdata, rate_valid);
+	valid_rates = ti_sn_bridge_read_valid_rates(pdata);
 
 	/* Train until we run out of rates */
 	for (dp_rate_idx = ti_sn_bridge_calc_min_dp_rate_idx(pdata);
 	     dp_rate_idx < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut);
 	     dp_rate_idx++) {
-		if (!rate_valid[dp_rate_idx])
+		if (!(valid_rates & BIT(dp_rate_idx)))
 			continue;
 
 		ret = ti_sn_link_training(pdata, dp_rate_idx, &last_err_str);
@@ -893,8 +1092,6 @@ static void ti_sn_bridge_enable(struct drm_bridge *bridge)
 	/* enable video stream */
 	regmap_update_bits(pdata->regmap, SN_ENH_FRAME_REG, VSTREAM_ENABLE,
 			   VSTREAM_ENABLE);
-
-	drm_panel_enable(pdata->panel);
 }
 
 static void ti_sn_bridge_pre_enable(struct drm_bridge *bridge)
@@ -906,14 +1103,20 @@ static void ti_sn_bridge_pre_enable(struct drm_bridge *bridge)
 	if (!pdata->refclk)
 		ti_sn65dsi86_enable_comms(pdata);
 
-	drm_panel_prepare(pdata->panel);
+	/* td7: min 100 us after enable before DSI data */
+	usleep_range(100, 110);
 }
 
 static void ti_sn_bridge_post_disable(struct drm_bridge *bridge)
 {
 	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
 
-	drm_panel_unprepare(pdata->panel);
+	/* semi auto link training mode OFF */
+	regmap_write(pdata->regmap, SN_ML_TX_MODE_REG, 0);
+	/* Num lanes to 0 as per power sequencing in data sheet */
+	regmap_update_bits(pdata->regmap, SN_SSC_CONFIG_REG, DP_NUM_LANES_MASK, 0);
+	/* disable DP PLL */
+	regmap_write(pdata->regmap, SN_PLL_ENABLE_REG, 0);
 
 	if (!pdata->refclk)
 		ti_sn65dsi86_disable_comms(pdata);
@@ -930,137 +1133,135 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = {
 	.post_disable = ti_sn_bridge_post_disable,
 };
 
-static struct ti_sn65dsi86 *aux_to_ti_sn65dsi86(struct drm_dp_aux *aux)
-{
-	return container_of(aux, struct ti_sn65dsi86, aux);
-}
-
-static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux,
-				  struct drm_dp_aux_msg *msg)
+static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata,
+				     struct device_node *np)
 {
-	struct ti_sn65dsi86 *pdata = aux_to_ti_sn65dsi86(aux);
-	u32 request = msg->request & ~(DP_AUX_I2C_MOT | DP_AUX_I2C_WRITE_STATUS_UPDATE);
-	u32 request_val = AUX_CMD_REQ(msg->request);
-	u8 *buf = msg->buffer;
-	unsigned int len = msg->size;
-	unsigned int val;
-	int ret;
-	u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG];
-
-	if (len > SN_AUX_MAX_PAYLOAD_BYTES)
-		return -EINVAL;
-
-	pm_runtime_get_sync(pdata->dev);
-	mutex_lock(&pdata->comms_mutex);
+	u32 lane_assignments[SN_MAX_DP_LANES] = { 0, 1, 2, 3 };
+	u32 lane_polarities[SN_MAX_DP_LANES] = { };
+	struct device_node *endpoint;
+	u8 ln_assign = 0;
+	u8 ln_polrs = 0;
+	int dp_lanes;
+	int i;
 
 	/*
-	 * If someone tries to do a DDC over AUX transaction before pre_enable()
-	 * on a device without a dedicated reference clock then we just can't
-	 * do it. Fail right away. This prevents non-refclk users from reading
-	 * the EDID before enabling the panel but such is life.
+	 * Read config from the device tree about lane remapping and lane
+	 * polarities.  These are optional and we assume identity map and
+	 * normal polarity if nothing is specified.  It's OK to specify just
+	 * data-lanes but not lane-polarities but not vice versa.
+	 *
+	 * Error checking is light (we just make sure we don't crash or
+	 * buffer overrun) and we assume dts is well formed and specifying
+	 * mappings that the hardware supports.
 	 */
-	if (!pdata->comms_enabled) {
-		ret = -EIO;
-		goto exit;
+	endpoint = of_graph_get_endpoint_by_regs(np, 1, -1);
+	dp_lanes = of_property_count_u32_elems(endpoint, "data-lanes");
+	if (dp_lanes > 0 && dp_lanes <= SN_MAX_DP_LANES) {
+		of_property_read_u32_array(endpoint, "data-lanes",
+					   lane_assignments, dp_lanes);
+		of_property_read_u32_array(endpoint, "lane-polarities",
+					   lane_polarities, dp_lanes);
+	} else {
+		dp_lanes = SN_MAX_DP_LANES;
 	}
+	of_node_put(endpoint);
 
-	switch (request) {
-	case DP_AUX_NATIVE_WRITE:
-	case DP_AUX_I2C_WRITE:
-	case DP_AUX_NATIVE_READ:
-	case DP_AUX_I2C_READ:
-		regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val);
-		/* Assume it's good */
-		msg->reply = 0;
-		break;
-	default:
-		ret = -EINVAL;
-		goto exit;
+	/*
+	 * Convert into register format.  Loop over all lanes even if
+	 * data-lanes had fewer elements so that we nicely initialize
+	 * the LN_ASSIGN register.
+	 */
+	for (i = SN_MAX_DP_LANES - 1; i >= 0; i--) {
+		ln_assign = ln_assign << LN_ASSIGN_WIDTH | lane_assignments[i];
+		ln_polrs = ln_polrs << 1 | lane_polarities[i];
 	}
 
-	BUILD_BUG_ON(sizeof(addr_len) != sizeof(__be32));
-	put_unaligned_be32((msg->address & SN_AUX_ADDR_MASK) << 8 | len,
-			   addr_len);
-	regmap_bulk_write(pdata->regmap, SN_AUX_ADDR_19_16_REG, addr_len,
-			  ARRAY_SIZE(addr_len));
+	/* Stash in our struct for when we power on */
+	pdata->dp_lanes = dp_lanes;
+	pdata->ln_assign = ln_assign;
+	pdata->ln_polrs = ln_polrs;
+}
 
-	if (request == DP_AUX_NATIVE_WRITE || request == DP_AUX_I2C_WRITE)
-		regmap_bulk_write(pdata->regmap, SN_AUX_WDATA_REG(0), buf, len);
+static int ti_sn_bridge_parse_dsi_host(struct ti_sn65dsi86 *pdata)
+{
+	struct device_node *np = pdata->dev->of_node;
 
-	/* Clear old status bits before start so we don't get confused */
-	regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG,
-		     AUX_IRQ_STATUS_NAT_I2C_FAIL |
-		     AUX_IRQ_STATUS_AUX_RPLY_TOUT |
-		     AUX_IRQ_STATUS_AUX_SHORT);
+	pdata->host_node = of_graph_get_remote_node(np, 0, 0);
 
-	regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND);
+	if (!pdata->host_node) {
+		DRM_ERROR("remote dsi host node not found\n");
+		return -ENODEV;
+	}
 
-	/* Zero delay loop because i2c transactions are slow already */
-	ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val,
-				       !(val & AUX_CMD_SEND), 0, 50 * 1000);
-	if (ret)
-		goto exit;
+	return 0;
+}
 
-	ret = regmap_read(pdata->regmap, SN_AUX_CMD_STATUS_REG, &val);
-	if (ret)
-		goto exit;
+static int ti_sn_bridge_probe(struct auxiliary_device *adev,
+			      const struct auxiliary_device_id *id)
+{
+	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
+	struct device_node *np = pdata->dev->of_node;
+	struct drm_panel *panel;
+	int ret;
 
-	if (val & AUX_IRQ_STATUS_AUX_RPLY_TOUT) {
-		/*
-		 * The hardware tried the message seven times per the DP spec
-		 * but it hit a timeout. We ignore defers here because they're
-		 * handled in hardware.
-		 */
-		ret = -ETIMEDOUT;
-		goto exit;
-	}
+	ret = drm_of_find_panel_or_bridge(np, 1, 0, &panel, NULL);
+	if (ret)
+		return dev_err_probe(&adev->dev, ret,
+				     "could not find any panel node\n");
 
-	if (val & AUX_IRQ_STATUS_AUX_SHORT) {
-		ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len);
-		if (ret)
-			goto exit;
-	} else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) {
-		switch (request) {
-		case DP_AUX_I2C_WRITE:
-		case DP_AUX_I2C_READ:
-			msg->reply |= DP_AUX_I2C_REPLY_NACK;
-			break;
-		case DP_AUX_NATIVE_READ:
-		case DP_AUX_NATIVE_WRITE:
-			msg->reply |= DP_AUX_NATIVE_REPLY_NACK;
-			break;
-		}
-		len = 0;
-		goto exit;
+	pdata->next_bridge = devm_drm_panel_bridge_add(pdata->dev, panel);
+	if (IS_ERR(pdata->next_bridge)) {
+		DRM_ERROR("failed to create panel bridge\n");
+		return PTR_ERR(pdata->next_bridge);
 	}
 
-	if (request != DP_AUX_NATIVE_WRITE && request != DP_AUX_I2C_WRITE && len != 0)
-		ret = regmap_bulk_read(pdata->regmap, SN_AUX_RDATA_REG(0), buf, len);
-
-exit:
-	mutex_unlock(&pdata->comms_mutex);
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
+	ti_sn_bridge_parse_lanes(pdata, np);
 
+	ret = ti_sn_bridge_parse_dsi_host(pdata);
 	if (ret)
 		return ret;
-	return len;
+
+	pdata->bridge.funcs = &ti_sn_bridge_funcs;
+	pdata->bridge.of_node = np;
+
+	drm_bridge_add(&pdata->bridge);
+
+	return 0;
 }
 
-static int ti_sn_bridge_parse_dsi_host(struct ti_sn65dsi86 *pdata)
+static void ti_sn_bridge_remove(struct auxiliary_device *adev)
 {
-	struct device_node *np = pdata->dev->of_node;
+	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
 
-	pdata->host_node = of_graph_get_remote_node(np, 0, 0);
+	if (!pdata)
+		return;
 
-	if (!pdata->host_node) {
-		DRM_ERROR("remote dsi host node not found\n");
-		return -ENODEV;
+	if (pdata->dsi) {
+		mipi_dsi_detach(pdata->dsi);
+		mipi_dsi_device_unregister(pdata->dsi);
 	}
 
-	return 0;
+	drm_bridge_remove(&pdata->bridge);
+
+	of_node_put(pdata->host_node);
 }
 
+static const struct auxiliary_device_id ti_sn_bridge_id_table[] = {
+	{ .name = "ti_sn65dsi86.bridge", },
+	{},
+};
+
+static struct auxiliary_driver ti_sn_bridge_driver = {
+	.name = "bridge",
+	.probe = ti_sn_bridge_probe,
+	.remove = ti_sn_bridge_remove,
+	.id_table = ti_sn_bridge_id_table,
+};
+
+/* -----------------------------------------------------------------------------
+ * GPIO Controller
+ */
+
 #if defined(CONFIG_OF_GPIO)
 
 static int tn_sn_bridge_of_xlate(struct gpio_chip *chip,
@@ -1265,171 +1466,27 @@ static inline void ti_sn_gpio_unregister(void) {}
 
 #endif
 
-static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata,
-				     struct device_node *np)
-{
-	u32 lane_assignments[SN_MAX_DP_LANES] = { 0, 1, 2, 3 };
-	u32 lane_polarities[SN_MAX_DP_LANES] = { };
-	struct device_node *endpoint;
-	u8 ln_assign = 0;
-	u8 ln_polrs = 0;
-	int dp_lanes;
-	int i;
-
-	/*
-	 * Read config from the device tree about lane remapping and lane
-	 * polarities.  These are optional and we assume identity map and
-	 * normal polarity if nothing is specified.  It's OK to specify just
-	 * data-lanes but not lane-polarities but not vice versa.
-	 *
-	 * Error checking is light (we just make sure we don't crash or
-	 * buffer overrun) and we assume dts is well formed and specifying
-	 * mappings that the hardware supports.
-	 */
-	endpoint = of_graph_get_endpoint_by_regs(np, 1, -1);
-	dp_lanes = of_property_count_u32_elems(endpoint, "data-lanes");
-	if (dp_lanes > 0 && dp_lanes <= SN_MAX_DP_LANES) {
-		of_property_read_u32_array(endpoint, "data-lanes",
-					   lane_assignments, dp_lanes);
-		of_property_read_u32_array(endpoint, "lane-polarities",
-					   lane_polarities, dp_lanes);
-	} else {
-		dp_lanes = SN_MAX_DP_LANES;
-	}
-	of_node_put(endpoint);
-
-	/*
-	 * Convert into register format.  Loop over all lanes even if
-	 * data-lanes had fewer elements so that we nicely initialize
-	 * the LN_ASSIGN register.
-	 */
-	for (i = SN_MAX_DP_LANES - 1; i >= 0; i--) {
-		ln_assign = ln_assign << LN_ASSIGN_WIDTH | lane_assignments[i];
-		ln_polrs = ln_polrs << 1 | lane_polarities[i];
-	}
-
-	/* Stash in our struct for when we power on */
-	pdata->dp_lanes = dp_lanes;
-	pdata->ln_assign = ln_assign;
-	pdata->ln_polrs = ln_polrs;
-}
-
-static int ti_sn_bridge_probe(struct auxiliary_device *adev,
-			      const struct auxiliary_device_id *id)
-{
-	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
-	struct device_node *np = pdata->dev->of_node;
-	int ret;
-
-	ret = drm_of_find_panel_or_bridge(np, 1, 0, &pdata->panel, NULL);
-	if (ret) {
-		DRM_ERROR("could not find any panel node\n");
-		return ret;
-	}
-
-	ti_sn_bridge_parse_lanes(pdata, np);
-
-	ret = ti_sn_bridge_parse_dsi_host(pdata);
-	if (ret)
-		return ret;
-
-	pdata->aux.name = "ti-sn65dsi86-aux";
-	pdata->aux.dev = pdata->dev;
-	pdata->aux.transfer = ti_sn_aux_transfer;
-	drm_dp_aux_init(&pdata->aux);
-
-	pdata->bridge.funcs = &ti_sn_bridge_funcs;
-	pdata->bridge.of_node = np;
-
-	drm_bridge_add(&pdata->bridge);
-
-	return 0;
-}
-
-static void ti_sn_bridge_remove(struct auxiliary_device *adev)
-{
-	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
-
-	if (!pdata)
-		return;
-
-	if (pdata->dsi) {
-		mipi_dsi_detach(pdata->dsi);
-		mipi_dsi_device_unregister(pdata->dsi);
-	}
-
-	kfree(pdata->edid);
-
-	drm_bridge_remove(&pdata->bridge);
-
-	of_node_put(pdata->host_node);
-}
-
-static const struct auxiliary_device_id ti_sn_bridge_id_table[] = {
-	{ .name = "ti_sn65dsi86.bridge", },
-	{},
-};
-
-static struct auxiliary_driver ti_sn_bridge_driver = {
-	.name = "bridge",
-	.probe = ti_sn_bridge_probe,
-	.remove = ti_sn_bridge_remove,
-	.id_table = ti_sn_bridge_id_table,
-};
+/* -----------------------------------------------------------------------------
+ * Probe & Remove
+ */
 
 static void ti_sn65dsi86_runtime_disable(void *data)
 {
 	pm_runtime_disable(data);
 }
 
-static void ti_sn65dsi86_uninit_aux(void *data)
-{
-	auxiliary_device_uninit(data);
-}
-
-static void ti_sn65dsi86_delete_aux(void *data)
-{
-	auxiliary_device_delete(data);
-}
-
-/*
- * AUX bus docs say that a non-NULL release is mandatory, but it makes no
- * sense for the model used here where all of the aux devices are allocated
- * in the single shared structure. We'll use this noop as a workaround.
- */
-static void ti_sn65dsi86_noop(struct device *dev) {}
-
-static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata,
-				       struct auxiliary_device *aux,
-				       const char *name)
+static int ti_sn65dsi86_parse_regulators(struct ti_sn65dsi86 *pdata)
 {
-	struct device *dev = pdata->dev;
-	int ret;
-
-	/*
-	 * NOTE: It would be nice to set the "of_node" of our children to be
-	 * the same "of_node"" that the top-level component has. That doesn't
-	 * work, though, since pinctrl will try (and fail) to reserve the
-	 * pins again. Until that gets sorted out the children will just need
-	 * to look at the of_node of the main device.
-	 */
-
-	aux->name = name;
-	aux->dev.parent = dev;
-	aux->dev.release = ti_sn65dsi86_noop;
-	ret = auxiliary_device_init(aux);
-	if (ret)
-		return ret;
-	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_uninit_aux, aux);
-	if (ret)
-		return ret;
+	unsigned int i;
+	const char * const ti_sn_bridge_supply_names[] = {
+		"vcca", "vcc", "vccio", "vpll",
+	};
 
-	ret = auxiliary_device_add(aux);
-	if (ret)
-		return ret;
-	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_delete_aux, aux);
+	for (i = 0; i < SN_REGULATOR_SUPPLY_NUM; i++)
+		pdata->supplies[i].supply = ti_sn_bridge_supply_names[i];
 
-	return ret;
+	return devm_regulator_bulk_get(pdata->dev, SN_REGULATOR_SUPPLY_NUM,
+				       pdata->supplies);
 }
 
 static int ti_sn65dsi86_probe(struct i2c_client *client,
@@ -1454,27 +1511,24 @@ static int ti_sn65dsi86_probe(struct i2c_client *client,
 
 	pdata->regmap = devm_regmap_init_i2c(client,
 					     &ti_sn65dsi86_regmap_config);
-	if (IS_ERR(pdata->regmap)) {
-		DRM_ERROR("regmap i2c init failed\n");
-		return PTR_ERR(pdata->regmap);
-	}
+	if (IS_ERR(pdata->regmap))
+		return dev_err_probe(dev, PTR_ERR(pdata->regmap),
+				     "regmap i2c init failed\n");
 
-	pdata->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
-	if (IS_ERR(pdata->enable_gpio)) {
-		DRM_ERROR("failed to get enable gpio from DT\n");
-		ret = PTR_ERR(pdata->enable_gpio);
-		return ret;
-	}
+	pdata->enable_gpio = devm_gpiod_get_optional(dev, "enable",
+						     GPIOD_OUT_LOW);
+	if (IS_ERR(pdata->enable_gpio))
+		return dev_err_probe(dev, PTR_ERR(pdata->enable_gpio),
+				     "failed to get enable gpio from DT\n");
 
 	ret = ti_sn65dsi86_parse_regulators(pdata);
-	if (ret) {
-		DRM_ERROR("failed to parse regulators\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to parse regulators\n");
 
 	pdata->refclk = devm_clk_get_optional(dev, "refclk");
 	if (IS_ERR(pdata->refclk))
-		return PTR_ERR(pdata->refclk);
+		return dev_err_probe(dev, PTR_ERR(pdata->refclk),
+				     "failed to get reference clock\n");
 
 	pm_runtime_enable(dev);
 	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_runtime_disable, dev);
@@ -1490,10 +1544,11 @@ static int ti_sn65dsi86_probe(struct i2c_client *client,
 	 * motiviation here is to solve the chicken-and-egg problem of probe
 	 * ordering. The bridge wants the panel to be there when it probes.
 	 * The panel wants its HPD GPIO (provided by sn65dsi86 on some boards)
-	 * when it probes. There will soon be other devices (DDC I2C bus, PWM)
-	 * that have the same problem. Having sub-devices allows the some sub
-	 * devices to finish probing even if others return -EPROBE_DEFER and
-	 * gets us around the problems.
+	 * when it probes. The panel and maybe backlight might want the DDC
+	 * bus. Soon the PWM provided by the bridge chip will have the same
+	 * problem. Having sub-devices allows the some sub devices to finish
+	 * probing even if others return -EPROBE_DEFER and gets us around the
+	 * problems.
 	 */
 
 	if (IS_ENABLED(CONFIG_OF_GPIO)) {
@@ -1502,7 +1557,13 @@ static int ti_sn65dsi86_probe(struct i2c_client *client,
 			return ret;
 	}
 
-	return ti_sn65dsi86_add_aux_device(pdata, &pdata->bridge_aux, "bridge");
+	/*
+	 * NOTE: At the end of the AUX channel probe we'll add the aux device
+	 * for the bridge. This is because the bridge can't be used until the
+	 * AUX channel is there and this is a very simple solution to the
+	 * dependency problem.
+	 */
+	return ti_sn65dsi86_add_aux_device(pdata, &pdata->aux_aux, "aux");
 }
 
 static struct i2c_device_id ti_sn65dsi86_id[] = {
@@ -1539,12 +1600,18 @@ static int __init ti_sn65dsi86_init(void)
 	if (ret)
 		goto err_main_was_registered;
 
-	ret = auxiliary_driver_register(&ti_sn_bridge_driver);
+	ret = auxiliary_driver_register(&ti_sn_aux_driver);
 	if (ret)
 		goto err_gpio_was_registered;
 
+	ret = auxiliary_driver_register(&ti_sn_bridge_driver);
+	if (ret)
+		goto err_aux_was_registered;
+
 	return 0;
 
+err_aux_was_registered:
+	auxiliary_driver_unregister(&ti_sn_aux_driver);
 err_gpio_was_registered:
 	ti_sn_gpio_unregister();
 err_main_was_registered:
@@ -1557,6 +1624,7 @@ module_init(ti_sn65dsi86_init);
 static void __exit ti_sn65dsi86_exit(void)
 {
 	auxiliary_driver_unregister(&ti_sn_bridge_driver);
+	auxiliary_driver_unregister(&ti_sn_aux_driver);
 	ti_sn_gpio_unregister();
 	i2c_del_driver(&ti_sn65dsi86_driver);
 }
diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c
index 9335d9d6cf9a..74bd4a76b253 100644
--- a/drivers/gpu/drm/drm_aperture.c
+++ b/drivers/gpu/drm/drm_aperture.c
@@ -33,6 +33,10 @@
  *
  * .. code-block:: c
  *
+ *	static const struct drm_driver example_driver = {
+ *		...
+ *	};
+ *
  *	static int remove_conflicting_framebuffers(struct pci_dev *pdev)
  *	{
  *		bool primary = false;
@@ -46,7 +50,7 @@
  *	#endif
  *
  *		return drm_aperture_remove_conflicting_framebuffers(base, size, primary,
- *		                                                    "example driver");
+ *		                                                    &example_driver);
  *	}
  *
  *	static int probe(struct pci_dev *pdev)
@@ -74,7 +78,7 @@
  *
  * Drivers that are susceptible to being removed by other drivers, such as
  * generic EFI or VESA drivers, have to register themselves as owners of their
- * given framebuffer memory. Ownership of the framebuffer memory is achived
+ * given framebuffer memory. Ownership of the framebuffer memory is achieved
  * by calling devm_aperture_acquire_from_firmware(). On success, the driver
  * is the owner of the framebuffer range. The function fails if the
  * framebuffer is already by another driver. See below for an example.
@@ -274,7 +278,7 @@ static void drm_aperture_detach_drivers(resource_size_t base, resource_size_t si
  * @base: the aperture's base address in physical memory
  * @size: aperture size in bytes
  * @primary: also kick vga16fb if present
- * @name: requesting driver name
+ * @req_driver: requesting DRM driver
  *
  * This function removes graphics device drivers which use memory range described by
  * @base and @size.
@@ -283,7 +287,7 @@ static void drm_aperture_detach_drivers(resource_size_t base, resource_size_t si
  * 0 on success, or a negative errno code otherwise
  */
 int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size,
-						 bool primary, const char *name)
+						 bool primary, const struct drm_driver *req_driver)
 {
 #if IS_REACHABLE(CONFIG_FB)
 	struct apertures_struct *a;
@@ -296,7 +300,7 @@ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_
 	a->ranges[0].base = base;
 	a->ranges[0].size = size;
 
-	ret = remove_conflicting_framebuffers(a, name, primary);
+	ret = remove_conflicting_framebuffers(a, req_driver->name, primary);
 	kfree(a);
 
 	if (ret)
@@ -312,7 +316,7 @@ EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers);
 /**
  * drm_aperture_remove_conflicting_pci_framebuffers - remove existing framebuffers for PCI devices
  * @pdev: PCI device
- * @name: requesting driver name
+ * @req_driver: requesting DRM driver
  *
  * This function removes graphics device drivers using memory range configured
  * for any of @pdev's memory bars. The function assumes that PCI device with
@@ -321,7 +325,8 @@ EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers);
  * Returns:
  * 0 on success, or a negative errno code otherwise
  */
-int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name)
+int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
+						     const struct drm_driver *req_driver)
 {
 	resource_size_t base, size;
 	int bar, ret = 0;
@@ -339,7 +344,7 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const
 	 * otherwise the vga fbdev driver falls over.
 	 */
 #if IS_REACHABLE(CONFIG_FB)
-	ret = remove_conflicting_pci_framebuffers(pdev, name);
+	ret = remove_conflicting_pci_framebuffers(pdev, req_driver->name);
 #endif
 	if (ret == 0)
 		ret = vga_remove_vgacon(pdev);
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index d820423fac32..ff1416cd609a 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -660,7 +660,7 @@ static int drm_atomic_plane_check(const struct drm_plane_state *old_plane_state,
 		return -ENOSPC;
 	}
 
-	clips = drm_plane_get_damage_clips(new_plane_state);
+	clips = __drm_plane_get_damage_clips(new_plane_state);
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 
 	/* Make sure damage clips are valid and inside the fb. */
@@ -723,7 +723,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
  * clocks, scaler units, bandwidth and fifo limits shared among a group of
  * planes or CRTCs, and so on) it makes sense to model these as independent
  * objects. Drivers then need to do similar state tracking and commit ordering for
- * such private (since not exposed to userpace) objects as the atomic core and
+ * such private (since not exposed to userspace) objects as the atomic core and
  * helpers already provide for connectors, planes and CRTCs.
  *
  * To make this easier on drivers the atomic core provides some support to track
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index bc3487964fb5..2c0c6ec92820 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -35,6 +35,7 @@
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_print.h>
 #include <drm/drm_self_refresh_helper.h>
@@ -633,7 +634,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 			 * connectors and a NULL mode.
 			 *
 			 * The other way around is true as well. enable != 0
-			 * iff connectors are attached and a mode is set.
+			 * implies that connectors are attached and a mode is set.
 			 */
 			new_crtc_state->mode_changed = true;
 			new_crtc_state->connectors_changed = true;
@@ -1685,7 +1686,7 @@ static void commit_work(struct work_struct *work)
 }
 
 /**
- * drm_atomic_helper_async_check - check if state can be commited asynchronously
+ * drm_atomic_helper_async_check - check if state can be committed asynchronously
  * @dev: DRM device
  * @state: the driver state object
  *
@@ -1694,7 +1695,7 @@ static void commit_work(struct work_struct *work)
  * but just do in-place changes on the current state.
  *
  * It will return 0 if the commit can happen in an asynchronous fashion or error
- * if not. Note that error just mean it can't be commited asynchronously, if it
+ * if not. Note that error just mean it can't be committed asynchronously, if it
  * fails the commit should be treated like a normal synchronous commit.
  */
 int drm_atomic_helper_async_check(struct drm_device *dev,
@@ -2405,6 +2406,15 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 			ret = funcs->prepare_fb(plane, new_plane_state);
 			if (ret)
 				goto fail;
+		} else {
+			WARN_ON_ONCE(funcs->cleanup_fb);
+
+			if (!drm_core_check_feature(dev, DRIVER_GEM))
+				continue;
+
+			ret = drm_gem_plane_helper_prepare_fb(plane, new_plane_state);
+			if (ret)
+				goto fail;
 		}
 	}
 
@@ -2573,7 +2583,7 @@ EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
  *
  * This function can only be savely used when planes are not allowed to move
  * between different CRTCs because this function doesn't handle inter-CRTC
- * depencies. Callers need to ensure that either no such depencies exist,
+ * dependencies. Callers need to ensure that either no such dependencies exist,
  * resolve them through ordering of commit calls or through some other means.
  */
 void
@@ -2710,7 +2720,7 @@ EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
 /**
  * drm_atomic_helper_swap_state - store atomic state into current sw state
  * @state: atomic state
- * @stall: stall for preceeding commits
+ * @stall: stall for preceding commits
  *
  * This function stores the atomic state into the current state pointers in all
  * driver objects. It should be called after all failing steps have been done
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 7e48d40600ff..909f31833181 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -48,7 +48,7 @@
  * in all its forms: The monster ATOMIC IOCTL itself, code for GET_PROPERTY and
  * SET_PROPERTY IOCTLs. Plus interface functions for compatibility helpers and
  * drivers which have special needs to construct their own atomic updates, e.g.
- * for load detect or similiar.
+ * for load detect or similar.
  */
 
 /**
@@ -753,7 +753,7 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		 * restore the state it wants on VT switch. So if the userspace
 		 * tries to change the link_status from GOOD to BAD, driver
 		 * silently rejects it and returns a 0. This prevents userspace
-		 * from accidently breaking  the display when it restores the
+		 * from accidentally breaking  the display when it restores the
 		 * state.
 		 */
 		if (state->link_status != DRM_LINK_STATUS_GOOD)
@@ -1064,7 +1064,7 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
  * DOC: explicit fencing properties
  *
  * Explicit fencing allows userspace to control the buffer synchronization
- * between devices. A Fence or a group of fences are transfered to/from
+ * between devices. A Fence or a group of fences are transferred to/from
  * userspace using Sync File fds and there are two DRM properties for that.
  * IN_FENCE_FD on each DRM Plane to send fences to the kernel and
  * OUT_FENCE_PTR on each DRM CRTC to receive fences from the kernel.
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index b59b26a71ad5..60a6b21474b1 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -52,7 +52,7 @@
  *
  * In addition only one &drm_master can be the current master for a &drm_device.
  * It can be switched through the DROP_MASTER and SET_MASTER IOCTL, or
- * implicitly through closing/openeing the primary device node. See also
+ * implicitly through closing/opening the primary device node. See also
  * drm_is_current_master().
  *
  * Clients can authenticate against the current master (if it matches their own)
@@ -61,6 +61,36 @@
  * trusted clients.
  */
 
+static bool drm_is_current_master_locked(struct drm_file *fpriv)
+{
+	lockdep_assert_once(lockdep_is_held(&fpriv->master_lookup_lock) ||
+			    lockdep_is_held(&fpriv->minor->dev->master_mutex));
+
+	return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master;
+}
+
+/**
+ * drm_is_current_master - checks whether @priv is the current master
+ * @fpriv: DRM file private
+ *
+ * Checks whether @fpriv is current master on its device. This decides whether a
+ * client is allowed to run DRM_MASTER IOCTLs.
+ *
+ * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting
+ * - the current master is assumed to own the non-shareable display hardware.
+ */
+bool drm_is_current_master(struct drm_file *fpriv)
+{
+	bool ret;
+
+	spin_lock(&fpriv->master_lookup_lock);
+	ret = drm_is_current_master_locked(fpriv);
+	spin_unlock(&fpriv->master_lookup_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_is_current_master);
+
 int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_auth *auth = data;
@@ -135,16 +165,18 @@ static void drm_set_master(struct drm_device *dev, struct drm_file *fpriv,
 static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct drm_master *old_master;
+	struct drm_master *new_master;
 
 	lockdep_assert_held_once(&dev->master_mutex);
 
 	WARN_ON(fpriv->is_master);
 	old_master = fpriv->master;
-	fpriv->master = drm_master_create(dev);
-	if (!fpriv->master) {
-		fpriv->master = old_master;
+	new_master = drm_master_create(dev);
+	if (!new_master)
 		return -ENOMEM;
-	}
+	spin_lock(&fpriv->master_lookup_lock);
+	fpriv->master = new_master;
+	spin_unlock(&fpriv->master_lookup_lock);
 
 	fpriv->is_master = 1;
 	fpriv->authenticated = 1;
@@ -223,7 +255,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto out_unlock;
 
-	if (drm_is_current_master(file_priv))
+	if (drm_is_current_master_locked(file_priv))
 		goto out_unlock;
 
 	if (dev->master) {
@@ -272,7 +304,7 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto out_unlock;
 
-	if (!drm_is_current_master(file_priv)) {
+	if (!drm_is_current_master_locked(file_priv)) {
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -303,10 +335,13 @@ int drm_master_open(struct drm_file *file_priv)
 	 * any master object for render clients
 	 */
 	mutex_lock(&dev->master_mutex);
-	if (!dev->master)
+	if (!dev->master) {
 		ret = drm_new_set_master(dev, file_priv);
-	else
+	} else {
+		spin_lock(&file_priv->master_lookup_lock);
 		file_priv->master = drm_master_get(dev->master);
+		spin_unlock(&file_priv->master_lookup_lock);
+	}
 	mutex_unlock(&dev->master_mutex);
 
 	return ret;
@@ -322,7 +357,7 @@ void drm_master_release(struct drm_file *file_priv)
 	if (file_priv->magic)
 		idr_remove(&file_priv->master->magic_map, file_priv->magic);
 
-	if (!drm_is_current_master(file_priv))
+	if (!drm_is_current_master_locked(file_priv))
 		goto out;
 
 	drm_legacy_lock_master_cleanup(dev, master);
@@ -344,22 +379,6 @@ out:
 }
 
 /**
- * drm_is_current_master - checks whether @priv is the current master
- * @fpriv: DRM file private
- *
- * Checks whether @fpriv is current master on its device. This decides whether a
- * client is allowed to run DRM_MASTER IOCTLs.
- *
- * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting
- * - the current master is assumed to own the non-shareable display hardware.
- */
-bool drm_is_current_master(struct drm_file *fpriv)
-{
-	return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master;
-}
-EXPORT_SYMBOL(drm_is_current_master);
-
-/**
  * drm_master_get - reference a master pointer
  * @master: &struct drm_master
  *
@@ -372,6 +391,31 @@ struct drm_master *drm_master_get(struct drm_master *master)
 }
 EXPORT_SYMBOL(drm_master_get);
 
+/**
+ * drm_file_get_master - reference &drm_file.master of @file_priv
+ * @file_priv: DRM file private
+ *
+ * Increments the reference count of @file_priv's &drm_file.master and returns
+ * the &drm_file.master. If @file_priv has no &drm_file.master, returns NULL.
+ *
+ * Master pointers returned from this function should be unreferenced using
+ * drm_master_put().
+ */
+struct drm_master *drm_file_get_master(struct drm_file *file_priv)
+{
+	struct drm_master *master = NULL;
+
+	spin_lock(&file_priv->master_lookup_lock);
+	if (!file_priv->master)
+		goto unlock;
+	master = drm_master_get(file_priv->master);
+
+unlock:
+	spin_unlock(&file_priv->master_lookup_lock);
+	return master;
+}
+EXPORT_SYMBOL(drm_file_get_master);
+
 static void drm_master_destroy(struct kref *kref)
 {
 	struct drm_master *master = container_of(kref, struct drm_master, refcount);
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index 044acd07c153..a8ed66751c2d 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -28,6 +28,7 @@
 #include <drm/drm_atomic_state_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_encoder.h>
+#include <drm/drm_print.h>
 
 #include "drm_crtc_internal.h"
 
@@ -225,6 +226,15 @@ err_reset_bridge:
 	bridge->dev = NULL;
 	bridge->encoder = NULL;
 	list_del(&bridge->chain_node);
+
+#ifdef CONFIG_OF
+	DRM_ERROR("failed to attach bridge %pOF to encoder %s: %d\n",
+		  bridge->of_node, encoder->name, ret);
+#else
+	DRM_ERROR("failed to attach bridge to encoder %s: %d\n",
+		  encoder->name, ret);
+#endif
+
 	return ret;
 }
 EXPORT_SYMBOL(drm_bridge_attach);
@@ -972,7 +982,7 @@ drm_atomic_bridge_propagate_bus_flags(struct drm_bridge *bridge,
 	bridge_state->output_bus_cfg.flags = output_flags;
 
 	/*
-	 * Propage the output flags to the input end of the bridge. Again, it's
+	 * Propagate the output flags to the input end of the bridge. Again, it's
 	 * not necessarily what all bridges want, but that's what most of them
 	 * do, and by doing that by default we avoid forcing drivers to
 	 * duplicate the "dummy propagation" logic.
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index ae8e4d76209c..fcca21e8efac 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1502,7 +1502,7 @@ int drm_legacy_freebufs(struct drm_device *dev, void *data,
  *
  * Maps the AGP, SG or PCI buffer region with vm_mmap(), and copies information
  * about each buffer into user space. For PCI buffers, it calls vm_mmap() with
- * offset equal to 0, which drm_mmap() interpretes as PCI buffers and calls
+ * offset equal to 0, which drm_mmap() interprets as PCI buffers and calls
  * drm_mmap_dma().
  */
 int __drm_legacy_mapbufs(struct drm_device *dev, void *data, int *p,
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 546599f19a93..30cc59fe6ef7 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -170,7 +170,7 @@ drm_clflush_virt_range(void *addr, unsigned long length)
 		for (; addr < end; addr += size)
 			clflushopt(addr);
 		clflushopt(end - 1); /* force serialisation */
-		mb(); /*Ensure that evry data cache line entry is flushed*/
+		mb(); /*Ensure that every data cache line entry is flushed*/
 		return;
 	}
 
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index da39e7ff6965..2ba257b1ae20 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -2414,6 +2414,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	struct drm_mode_modeinfo u_mode;
 	struct drm_mode_modeinfo __user *mode_ptr;
 	uint32_t __user *encoder_ptr;
+	bool is_current_master;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
@@ -2444,9 +2445,11 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	out_resp->connector_type = connector->connector_type;
 	out_resp->connector_type_id = connector->connector_type_id;
 
+	is_current_master = drm_is_current_master(file_priv);
+
 	mutex_lock(&dev->mode_config.mutex);
 	if (out_resp->count_modes == 0) {
-		if (drm_is_current_master(file_priv))
+		if (is_current_master)
 			connector->funcs->fill_modes(connector,
 						     dev->mode_config.max_width,
 						     dev->mode_config.max_height);
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 1ca51addb589..edb772947cb4 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -262,6 +262,8 @@ int drm_plane_register_all(struct drm_device *dev);
 void drm_plane_unregister_all(struct drm_device *dev);
 int drm_plane_check_pixel_format(struct drm_plane *plane,
 				 u32 format, u64 modifier);
+struct drm_mode_rect *
+__drm_plane_get_damage_clips(const struct drm_plane_state *state);
 
 /* drm_bridge.c */
 void drm_bridge_detach(struct drm_bridge *bridge);
diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c
index 3a4126dc2520..8eeff0c7bdd4 100644
--- a/drivers/gpu/drm/drm_damage_helper.c
+++ b/drivers/gpu/drm/drm_damage_helper.c
@@ -34,44 +34,6 @@
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_device.h>
 
-/**
- * DOC: overview
- *
- * FB_DAMAGE_CLIPS is an optional plane property which provides a means to
- * specify a list of damage rectangles on a plane in framebuffer coordinates of
- * the framebuffer attached to the plane. In current context damage is the area
- * of plane framebuffer that has changed since last plane update (also called
- * page-flip), irrespective of whether currently attached framebuffer is same as
- * framebuffer attached during last plane update or not.
- *
- * FB_DAMAGE_CLIPS is a hint to kernel which could be helpful for some drivers
- * to optimize internally especially for virtual devices where each framebuffer
- * change needs to be transmitted over network, usb, etc.
- *
- * Since FB_DAMAGE_CLIPS is a hint so it is an optional property. User-space can
- * ignore damage clips property and in that case driver will do a full plane
- * update. In case damage clips are provided then it is guaranteed that the area
- * inside damage clips will be updated to plane. For efficiency driver can do
- * full update or can update more than specified in damage clips. Since driver
- * is free to read more, user-space must always render the entire visible
- * framebuffer. Otherwise there can be corruptions. Also, if a user-space
- * provides damage clips which doesn't encompass the actual damage to
- * framebuffer (since last plane update) can result in incorrect rendering.
- *
- * FB_DAMAGE_CLIPS is a blob property with the layout of blob data is simply an
- * array of &drm_mode_rect. Unlike plane &drm_plane_state.src coordinates,
- * damage clips are not in 16.16 fixed point. Similar to plane src in
- * framebuffer, damage clips cannot be negative. In damage clip, x1/y1 are
- * inclusive and x2/y2 are exclusive. While kernel does not error for overlapped
- * damage clips, it is strongly discouraged.
- *
- * Drivers that are interested in damage interface for plane should enable
- * FB_DAMAGE_CLIPS property by calling drm_plane_enable_fb_damage_clips().
- * Drivers implementing damage can use drm_atomic_helper_damage_iter_init() and
- * drm_atomic_helper_damage_iter_next() helper iterator function to get damage
- * rectangles clipped to &drm_plane_state.src.
- */
-
 static void convert_clip_rect_to_rect(const struct drm_clip_rect *src,
 				      struct drm_mode_rect *dest,
 				      uint32_t num_clips, uint32_t src_inc)
@@ -88,22 +50,6 @@ static void convert_clip_rect_to_rect(const struct drm_clip_rect *src,
 }
 
 /**
- * drm_plane_enable_fb_damage_clips - Enables plane fb damage clips property.
- * @plane: Plane on which to enable damage clips property.
- *
- * This function lets driver to enable the damage clips property on a plane.
- */
-void drm_plane_enable_fb_damage_clips(struct drm_plane *plane)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_mode_config *config = &dev->mode_config;
-
-	drm_object_attach_property(&plane->base, config->prop_fb_damage_clips,
-				   0);
-}
-EXPORT_SYMBOL(drm_plane_enable_fb_damage_clips);
-
-/**
  * drm_atomic_helper_check_plane_damage - Verify plane damage on atomic_check.
  * @state: The driver state object.
  * @plane_state: Plane state for which to verify damage.
@@ -170,7 +116,7 @@ int drm_atomic_helper_dirtyfb(struct drm_framebuffer *fb,
 	int ret = 0;
 
 	/*
-	 * When called from ioctl, we are interruptable, but not when called
+	 * When called from ioctl, we are interruptible, but not when called
 	 * internally (ie. defio worker)
 	 */
 	drm_modeset_acquire_init(&ctx,
@@ -282,7 +228,7 @@ drm_atomic_helper_damage_iter_init(struct drm_atomic_helper_damage_iter *iter,
 	if (!state || !state->crtc || !state->fb || !state->visible)
 		return;
 
-	iter->clips = drm_helper_get_plane_damage_clips(state);
+	iter->clips = (struct drm_rect *)drm_plane_get_damage_clips(state);
 	iter->num_clips = drm_plane_get_damage_clips_count(state);
 
 	/* Round down for x1/y1 and round up for x2/y2 to catch all pixels */
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 3d7182001004..b0a826489488 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -91,6 +91,7 @@ static int drm_clients_info(struct seq_file *m, void *data)
 	mutex_lock(&dev->filelist_mutex);
 	list_for_each_entry_reverse(priv, &dev->filelist, lhead) {
 		struct task_struct *task;
+		bool is_current_master = drm_is_current_master(priv);
 
 		rcu_read_lock(); /* locks pid_task()->comm */
 		task = pid_task(priv->pid, PIDTYPE_PID);
@@ -99,7 +100,7 @@ static int drm_clients_info(struct seq_file *m, void *data)
 			   task ? task->comm : "<unknown>",
 			   pid_vnr(priv->pid),
 			   priv->minor->index,
-			   drm_is_current_master(priv) ? 'y' : 'n',
+			   is_current_master ? 'y' : 'n',
 			   priv->authenticated ? 'y' : 'n',
 			   from_kuid_munged(seq_user_ns(m), uid),
 			   priv->magic);
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index 3dd70d813f69..bbc3bc4ba844 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -46,10 +46,10 @@
  * it reached a given hardware component (a CRC sampling "source").
  *
  * Userspace can control generation of CRCs in a given CRTC by writing to the
- * file dri/0/crtc-N/crc/control in debugfs, with N being the index of the CRTC.
- * Accepted values are source names (which are driver-specific) and the "auto"
- * keyword, which will let the driver select a default source of frame CRCs
- * for this CRTC.
+ * file dri/0/crtc-N/crc/control in debugfs, with N being the :ref:`index of
+ * the CRTC<crtc_index>`. Accepted values are source names (which are
+ * driver-specific) and the "auto" keyword, which will let the driver select a
+ * default source of frame CRCs for this CRTC.
  *
  * Once frame CRC generation is enabled, userspace can capture them by reading
  * the dri/0/crtc-N/crc/data file. Each line in that file contains the frame
diff --git a/drivers/gpu/drm/drm_dp_aux_bus.c b/drivers/gpu/drm/drm_dp_aux_bus.c
new file mode 100644
index 000000000000..298ea7a49591
--- /dev/null
+++ b/drivers/gpu/drm/drm_dp_aux_bus.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2021 Google Inc.
+ *
+ * The DP AUX bus is used for devices that are connected over a DisplayPort
+ * AUX bus. The devices on the far side of the bus are referred to as
+ * endpoints in this code.
+ *
+ * Commonly there is only one device connected to the DP AUX bus: a panel.
+ * Though historically panels (even DP panels) have been modeled as simple
+ * platform devices, putting them under the DP AUX bus allows the panel driver
+ * to perform transactions on that bus.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+
+#include <drm/drm_dp_aux_bus.h>
+#include <drm/drm_dp_helper.h>
+
+/**
+ * dp_aux_ep_match() - The match function for the dp_aux_bus.
+ * @dev: The device to match.
+ * @drv: The driver to try to match against.
+ *
+ * At the moment, we just match on device tree.
+ *
+ * Return: True if this driver matches this device; false otherwise.
+ */
+static int dp_aux_ep_match(struct device *dev, struct device_driver *drv)
+{
+	return !!of_match_device(drv->of_match_table, dev);
+}
+
+/**
+ * dp_aux_ep_probe() - The probe function for the dp_aux_bus.
+ * @dev: The device to probe.
+ *
+ * Calls through to the endpoint driver probe.
+ *
+ * Return: 0 if no error or negative error code.
+ */
+static int dp_aux_ep_probe(struct device *dev)
+{
+	struct dp_aux_ep_driver *aux_ep_drv = to_dp_aux_ep_drv(dev->driver);
+	struct dp_aux_ep_device *aux_ep = to_dp_aux_ep_dev(dev);
+	int ret;
+
+	ret = dev_pm_domain_attach(dev, true);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to attach to PM Domain\n");
+
+	ret = aux_ep_drv->probe(aux_ep);
+	if (ret)
+		dev_pm_domain_detach(dev, true);
+
+	return ret;
+}
+
+/**
+ * dp_aux_ep_remove() - The remove function for the dp_aux_bus.
+ * @dev: The device to remove.
+ *
+ * Calls through to the endpoint driver remove.
+ *
+ */
+static void dp_aux_ep_remove(struct device *dev)
+{
+	struct dp_aux_ep_driver *aux_ep_drv = to_dp_aux_ep_drv(dev->driver);
+	struct dp_aux_ep_device *aux_ep = to_dp_aux_ep_dev(dev);
+
+	if (aux_ep_drv->remove)
+		aux_ep_drv->remove(aux_ep);
+	dev_pm_domain_detach(dev, true);
+}
+
+/**
+ * dp_aux_ep_shutdown() - The shutdown function for the dp_aux_bus.
+ * @dev: The device to shutdown.
+ *
+ * Calls through to the endpoint driver shutdown.
+ */
+static void dp_aux_ep_shutdown(struct device *dev)
+{
+	struct dp_aux_ep_driver *aux_ep_drv;
+
+	if (!dev->driver)
+		return;
+
+	aux_ep_drv = to_dp_aux_ep_drv(dev->driver);
+	if (aux_ep_drv->shutdown)
+		aux_ep_drv->shutdown(to_dp_aux_ep_dev(dev));
+}
+
+static struct bus_type dp_aux_bus_type = {
+	.name		= "dp-aux",
+	.match		= dp_aux_ep_match,
+	.probe		= dp_aux_ep_probe,
+	.remove		= dp_aux_ep_remove,
+	.shutdown	= dp_aux_ep_shutdown,
+};
+
+static ssize_t modalias_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return of_device_modalias(dev, buf, PAGE_SIZE);
+}
+static DEVICE_ATTR_RO(modalias);
+
+static struct attribute *dp_aux_ep_dev_attrs[] = {
+	&dev_attr_modalias.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(dp_aux_ep_dev);
+
+/**
+ * dp_aux_ep_dev_release() - Free memory for the dp_aux_ep device
+ * @dev: The device to free.
+ *
+ * Return: 0 if no error or negative error code.
+ */
+static void dp_aux_ep_dev_release(struct device *dev)
+{
+	kfree(to_dp_aux_ep_dev(dev));
+}
+
+static struct device_type dp_aux_device_type_type = {
+	.groups		= dp_aux_ep_dev_groups,
+	.uevent		= of_device_uevent_modalias,
+	.release	= dp_aux_ep_dev_release,
+};
+
+/**
+ * of_dp_aux_ep_destroy() - Destroy an DP AUX endpoint device
+ * @dev: The device to destroy.
+ * @data: Not used
+ *
+ * This is just used as a callback by of_dp_aux_depopulate_ep_devices() and
+ * is called for _all_ of the child devices of the device providing the AUX bus.
+ * We'll only act on those that are of type "dp_aux_bus_type".
+ *
+ * This function is effectively an inverse of what's in the loop
+ * in of_dp_aux_populate_ep_devices().
+ *
+ * Return: 0 if no error or negative error code.
+ */
+static int of_dp_aux_ep_destroy(struct device *dev, void *data)
+{
+	struct device_node *np = dev->of_node;
+
+	if (dev->bus != &dp_aux_bus_type)
+		return 0;
+
+	if (!of_node_check_flag(np, OF_POPULATED))
+		return 0;
+
+	of_node_clear_flag(np, OF_POPULATED);
+	of_node_put(np);
+
+	device_unregister(dev);
+
+	return 0;
+}
+
+/**
+ * of_dp_aux_depopulate_ep_devices() - Undo of_dp_aux_populate_ep_devices
+ * @aux: The AUX channel whose devices we want to depopulate
+ *
+ * This will destroy all devices that were created
+ * by of_dp_aux_populate_ep_devices().
+ */
+void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux)
+{
+	device_for_each_child_reverse(aux->dev, NULL, of_dp_aux_ep_destroy);
+}
+EXPORT_SYMBOL_GPL(of_dp_aux_depopulate_ep_devices);
+
+/**
+ * of_dp_aux_populate_ep_devices() - Populate the endpoint devices on the DP AUX
+ * @aux: The AUX channel whose devices we want to populate. It is required that
+ *       drm_dp_aux_init() has already been called for this AUX channel.
+ *
+ * This will populate all the devices under the "aux-bus" node of the device
+ * providing the AUX channel (AKA aux->dev).
+ *
+ * When this function finishes, it is _possible_ (but not guaranteed) that
+ * our sub-devices will have finished probing. It should be noted that if our
+ * sub-devices return -EPROBE_DEFER that we will not return any error codes
+ * ourselves but our sub-devices will _not_ have actually probed successfully
+ * yet. There may be other cases (maybe added in the future?) where sub-devices
+ * won't have been probed yet when this function returns, so it's best not to
+ * rely on that.
+ *
+ * If this function succeeds you should later make sure you call
+ * of_dp_aux_depopulate_ep_devices() to undo it, or just use the devm version
+ * of this function.
+ *
+ * Return: 0 if no error or negative error code.
+ */
+int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux)
+{
+	struct device_node *bus, *np;
+	struct dp_aux_ep_device *aux_ep;
+	int ret;
+
+	/* drm_dp_aux_init() should have been called already; warn if not */
+	WARN_ON_ONCE(!aux->ddc.algo);
+
+	if (!aux->dev->of_node)
+		return 0;
+
+	bus = of_get_child_by_name(aux->dev->of_node, "aux-bus");
+	if (!bus)
+		return 0;
+
+	for_each_available_child_of_node(bus, np) {
+		if (of_node_test_and_set_flag(np, OF_POPULATED))
+			continue;
+
+		aux_ep = kzalloc(sizeof(*aux_ep), GFP_KERNEL);
+		if (!aux_ep)
+			continue;
+		aux_ep->aux = aux;
+
+		aux_ep->dev.parent = aux->dev;
+		aux_ep->dev.bus = &dp_aux_bus_type;
+		aux_ep->dev.type = &dp_aux_device_type_type;
+		aux_ep->dev.of_node = of_node_get(np);
+		dev_set_name(&aux_ep->dev, "aux-%s", dev_name(aux->dev));
+
+		ret = device_register(&aux_ep->dev);
+		if (ret) {
+			dev_err(aux->dev, "Failed to create AUX EP for %pOF: %d\n", np, ret);
+			of_node_clear_flag(np, OF_POPULATED);
+			of_node_put(np);
+
+			/*
+			 * As per docs of device_register(), call this instead
+			 * of kfree() directly for error cases.
+			 */
+			put_device(&aux_ep->dev);
+
+			/*
+			 * Following in the footsteps of of_i2c_register_devices(),
+			 * we won't fail the whole function here--we'll just
+			 * continue registering any other devices we find.
+			 */
+		}
+	}
+
+	of_node_put(bus);
+
+	return 0;
+}
+
+static void of_dp_aux_depopulate_ep_devices_void(void *data)
+{
+	of_dp_aux_depopulate_ep_devices(data);
+}
+
+/**
+ * devm_of_dp_aux_populate_ep_devices() - devm wrapper for of_dp_aux_populate_ep_devices()
+ * @aux: The AUX channel whose devices we want to populate
+ *
+ * Handles freeing w/ devm on the device "aux->dev".
+ *
+ * Return: 0 if no error or negative error code.
+ */
+int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux)
+{
+	int ret;
+
+	ret = of_dp_aux_populate_ep_devices(aux);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(aux->dev,
+					of_dp_aux_depopulate_ep_devices_void,
+					aux);
+}
+EXPORT_SYMBOL_GPL(devm_of_dp_aux_populate_ep_devices);
+
+int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *drv, struct module *owner)
+{
+	drv->driver.owner = owner;
+	drv->driver.bus = &dp_aux_bus_type;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(__dp_aux_dp_driver_register);
+
+void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(dp_aux_dp_driver_unregister);
+
+static int __init dp_aux_bus_init(void)
+{
+	int ret;
+
+	ret = bus_register(&dp_aux_bus_type);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void __exit dp_aux_bus_exit(void)
+{
+	bus_unregister(&dp_aux_bus_type);
+}
+
+subsys_initcall(dp_aux_bus_init);
+module_exit(dp_aux_bus_exit);
+
+MODULE_AUTHOR("Douglas Anderson <dianders@chromium.org>");
+MODULE_DESCRIPTION("DRM DisplayPort AUX bus");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 55b53df6ce34..6d0f2c447f3b 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -33,9 +33,17 @@
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 #include <drm/drm_dp_mst_helper.h>
+#include <drm/drm_panel.h>
 
 #include "drm_crtc_helper_internal.h"
 
+struct dp_aux_backlight {
+	struct backlight_device *base;
+	struct drm_dp_aux *aux;
+	struct drm_edp_backlight_info info;
+	bool enabled;
+};
+
 /**
  * DOC: dp helpers
  *
@@ -764,7 +772,7 @@ int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 		 * It's left up to the driver to check the
 		 * DP dual mode adapter's max TMDS clock.
 		 *
-		 * Unfortunatley it looks like branch devices
+		 * Unfortunately it looks like branch devices
 		 * may not fordward that the DP dual mode i2c
 		 * access so we just usually get i2c nak :(
 		 */
@@ -1357,7 +1365,7 @@ static int drm_dp_i2c_msg_duration(const struct drm_dp_aux_msg *msg,
 }
 
 /*
- * Deterine how many retries should be attempted to successfully transfer
+ * Determine how many retries should be attempted to successfully transfer
  * the specified message, based on the estimated durations of the
  * i2c and AUX transfers.
  */
@@ -1410,7 +1418,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 			/*
 			 * While timeouts can be errors, they're usually normal
 			 * behavior (for instance, when a driver tries to
-			 * communicate with a non-existant DisplayPort device).
+			 * communicate with a non-existent DisplayPort device).
 			 * Avoid spamming the kernel log with timeout errors.
 			 */
 			if (ret == -ETIMEDOUT)
@@ -3115,3 +3123,459 @@ int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc)
 	return 0;
 }
 EXPORT_SYMBOL(drm_dp_pcon_convert_rgb_to_ycbcr);
+
+/**
+ * drm_edp_backlight_set_level() - Set the backlight level of an eDP panel via AUX
+ * @aux: The DP AUX channel to use
+ * @bl: Backlight capability info from drm_edp_backlight_init()
+ * @level: The brightness level to set
+ *
+ * Sets the brightness level of an eDP panel's backlight. Note that the panel's backlight must
+ * already have been enabled by the driver by calling drm_edp_backlight_enable().
+ *
+ * Returns: %0 on success, negative error code on failure
+ */
+int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl,
+				u16 level)
+{
+	int ret;
+	u8 buf[2] = { 0 };
+
+	if (bl->lsb_reg_used) {
+		buf[0] = (level & 0xff00) >> 8;
+		buf[1] = (level & 0x00ff);
+	} else {
+		buf[0] = level;
+	}
+
+	ret = drm_dp_dpcd_write(aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, buf, sizeof(buf));
+	if (ret != sizeof(buf)) {
+		drm_err(aux->drm_dev,
+			"%s: Failed to write aux backlight level: %d\n",
+			aux->name, ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_edp_backlight_set_level);
+
+static int
+drm_edp_backlight_set_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl,
+			     bool enable)
+{
+	int ret;
+	u8 buf;
+
+	/* The panel uses something other then DPCD for enabling its backlight */
+	if (!bl->aux_enable)
+		return 0;
+
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_DISPLAY_CONTROL_REGISTER, &buf);
+	if (ret != 1) {
+		drm_err(aux->drm_dev, "%s: Failed to read eDP display control register: %d\n",
+			aux->name, ret);
+		return ret < 0 ? ret : -EIO;
+	}
+	if (enable)
+		buf |= DP_EDP_BACKLIGHT_ENABLE;
+	else
+		buf &= ~DP_EDP_BACKLIGHT_ENABLE;
+
+	ret = drm_dp_dpcd_writeb(aux, DP_EDP_DISPLAY_CONTROL_REGISTER, buf);
+	if (ret != 1) {
+		drm_err(aux->drm_dev, "%s: Failed to write eDP display control register: %d\n",
+			aux->name, ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * drm_edp_backlight_enable() - Enable an eDP panel's backlight using DPCD
+ * @aux: The DP AUX channel to use
+ * @bl: Backlight capability info from drm_edp_backlight_init()
+ * @level: The initial backlight level to set via AUX, if there is one
+ *
+ * This function handles enabling DPCD backlight controls on a panel over DPCD, while additionally
+ * restoring any important backlight state such as the given backlight level, the brightness byte
+ * count, backlight frequency, etc.
+ *
+ * Note that certain panels, while supporting brightness level controls over DPCD, may not support
+ * having their backlights enabled via the standard %DP_EDP_DISPLAY_CONTROL_REGISTER. On such panels
+ * &drm_edp_backlight_info.aux_enable will be set to %false, this function will skip the step of
+ * programming the %DP_EDP_DISPLAY_CONTROL_REGISTER, and the driver must perform the required
+ * implementation specific step for enabling the backlight after calling this function.
+ *
+ * Returns: %0 on success, negative error code on failure.
+ */
+int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl,
+			     const u16 level)
+{
+	int ret;
+	u8 dpcd_buf, new_dpcd_buf;
+
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev,
+			    "%s: Failed to read backlight mode: %d\n", aux->name, ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	new_dpcd_buf = dpcd_buf;
+
+	if ((dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) != DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) {
+		new_dpcd_buf &= ~DP_EDP_BACKLIGHT_CONTROL_MODE_MASK;
+		new_dpcd_buf |= DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD;
+
+		if (bl->pwmgen_bit_count) {
+			ret = drm_dp_dpcd_writeb(aux, DP_EDP_PWMGEN_BIT_COUNT, bl->pwmgen_bit_count);
+			if (ret != 1)
+				drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux pwmgen bit count: %d\n",
+					    aux->name, ret);
+		}
+	}
+
+	if (bl->pwm_freq_pre_divider) {
+		ret = drm_dp_dpcd_writeb(aux, DP_EDP_BACKLIGHT_FREQ_SET, bl->pwm_freq_pre_divider);
+		if (ret != 1)
+			drm_dbg_kms(aux->drm_dev,
+				    "%s: Failed to write aux backlight frequency: %d\n",
+				    aux->name, ret);
+		else
+			new_dpcd_buf |= DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE;
+	}
+
+	if (new_dpcd_buf != dpcd_buf) {
+		ret = drm_dp_dpcd_writeb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf);
+		if (ret != 1) {
+			drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux backlight mode: %d\n",
+				    aux->name, ret);
+			return ret < 0 ? ret : -EIO;
+		}
+	}
+
+	ret = drm_edp_backlight_set_level(aux, bl, level);
+	if (ret < 0)
+		return ret;
+	ret = drm_edp_backlight_set_enable(aux, bl, true);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_edp_backlight_enable);
+
+/**
+ * drm_edp_backlight_disable() - Disable an eDP backlight using DPCD, if supported
+ * @aux: The DP AUX channel to use
+ * @bl: Backlight capability info from drm_edp_backlight_init()
+ *
+ * This function handles disabling DPCD backlight controls on a panel over AUX. Note that some
+ * panels have backlights that are enabled/disabled by other means, despite having their brightness
+ * values controlled through DPCD. On such panels &drm_edp_backlight_info.aux_enable will be set to
+ * %false, this function will become a no-op (and we will skip updating
+ * %DP_EDP_DISPLAY_CONTROL_REGISTER), and the driver must take care to perform it's own
+ * implementation specific step for disabling the backlight.
+ *
+ * Returns: %0 on success or no-op, negative error code on failure.
+ */
+int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl)
+{
+	int ret;
+
+	ret = drm_edp_backlight_set_enable(aux, bl, false);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_edp_backlight_disable);
+
+static inline int
+drm_edp_backlight_probe_max(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl,
+			    u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE])
+{
+	int fxp, fxp_min, fxp_max, fxp_actual, f = 1;
+	int ret;
+	u8 pn, pn_min, pn_max;
+
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT, &pn);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap: %d\n",
+			    aux->name, ret);
+		return -ENODEV;
+	}
+
+	pn &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
+	bl->max = (1 << pn) - 1;
+	if (!driver_pwm_freq_hz)
+		return 0;
+
+	/*
+	 * Set PWM Frequency divider to match desired frequency provided by the driver.
+	 * The PWM Frequency is calculated as 27Mhz / (F x P).
+	 * - Where F = PWM Frequency Pre-Divider value programmed by field 7:0 of the
+	 *             EDP_BACKLIGHT_FREQ_SET register (DPCD Address 00728h)
+	 * - Where P = 2^Pn, where Pn is the value programmed by field 4:0 of the
+	 *             EDP_PWMGEN_BIT_COUNT register (DPCD Address 00724h)
+	 */
+
+	/* Find desired value of (F x P)
+	 * Note that, if F x P is out of supported range, the maximum value or minimum value will
+	 * applied automatically. So no need to check that.
+	 */
+	fxp = DIV_ROUND_CLOSEST(1000 * DP_EDP_BACKLIGHT_FREQ_BASE_KHZ, driver_pwm_freq_hz);
+
+	/* Use highest possible value of Pn for more granularity of brightness adjustment while
+	 * satisfying the conditions below.
+	 * - Pn is in the range of Pn_min and Pn_max
+	 * - F is in the range of 1 and 255
+	 * - FxP is within 25% of desired value.
+	 *   Note: 25% is arbitrary value and may need some tweak.
+	 */
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap min: %d\n",
+			    aux->name, ret);
+		return 0;
+	}
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap max: %d\n",
+			    aux->name, ret);
+		return 0;
+	}
+	pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
+	pn_max &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
+
+	/* Ensure frequency is within 25% of desired value */
+	fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4);
+	fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4);
+	if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) {
+		drm_dbg_kms(aux->drm_dev,
+			    "%s: Driver defined backlight frequency (%d) out of range\n",
+			    aux->name, driver_pwm_freq_hz);
+		return 0;
+	}
+
+	for (pn = pn_max; pn >= pn_min; pn--) {
+		f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255);
+		fxp_actual = f << pn;
+		if (fxp_min <= fxp_actual && fxp_actual <= fxp_max)
+			break;
+	}
+
+	ret = drm_dp_dpcd_writeb(aux, DP_EDP_PWMGEN_BIT_COUNT, pn);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux pwmgen bit count: %d\n",
+			    aux->name, ret);
+		return 0;
+	}
+	bl->pwmgen_bit_count = pn;
+	bl->max = (1 << pn) - 1;
+
+	if (edp_dpcd[2] & DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP) {
+		bl->pwm_freq_pre_divider = f;
+		drm_dbg_kms(aux->drm_dev, "%s: Using backlight frequency from driver (%dHz)\n",
+			    aux->name, driver_pwm_freq_hz);
+	}
+
+	return 0;
+}
+
+static inline int
+drm_edp_backlight_probe_level(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl,
+			      u8 *current_mode)
+{
+	int ret;
+	u8 buf[2];
+	u8 mode_reg;
+
+	ret = drm_dp_dpcd_readb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &mode_reg);
+	if (ret != 1) {
+		drm_dbg_kms(aux->drm_dev, "%s: Failed to read backlight mode: %d\n",
+			    aux->name, ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	*current_mode = (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK);
+	if (*current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) {
+		int size = 1 + bl->lsb_reg_used;
+
+		ret = drm_dp_dpcd_read(aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, buf, size);
+		if (ret != size) {
+			drm_dbg_kms(aux->drm_dev, "%s: Failed to read backlight level: %d\n",
+				    aux->name, ret);
+			return ret < 0 ? ret : -EIO;
+		}
+
+		if (bl->lsb_reg_used)
+			return (buf[0] << 8) | buf[1];
+		else
+			return buf[0];
+	}
+
+	/*
+	 * If we're not in DPCD control mode yet, the programmed brightness value is meaningless and
+	 * the driver should assume max brightness
+	 */
+	return bl->max;
+}
+
+/**
+ * drm_edp_backlight_init() - Probe a display panel's TCON using the standard VESA eDP backlight
+ * interface.
+ * @aux: The DP aux device to use for probing
+ * @bl: The &drm_edp_backlight_info struct to fill out with information on the backlight
+ * @driver_pwm_freq_hz: Optional PWM frequency from the driver in hz
+ * @edp_dpcd: A cached copy of the eDP DPCD
+ * @current_level: Where to store the probed brightness level
+ * @current_mode: Where to store the currently set backlight control mode
+ *
+ * Initializes a &drm_edp_backlight_info struct by probing @aux for it's backlight capabilities,
+ * along with also probing the current and maximum supported brightness levels.
+ *
+ * If @driver_pwm_freq_hz is non-zero, this will be used as the backlight frequency. Otherwise, the
+ * default frequency from the panel is used.
+ *
+ * Returns: %0 on success, negative error code on failure.
+ */
+int
+drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl,
+		       u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE],
+		       u16 *current_level, u8 *current_mode)
+{
+	int ret;
+
+	if (edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP)
+		bl->aux_enable = true;
+	if (edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
+		bl->lsb_reg_used = true;
+
+	ret = drm_edp_backlight_probe_max(aux, bl, driver_pwm_freq_hz, edp_dpcd);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_edp_backlight_probe_level(aux, bl, current_mode);
+	if (ret < 0)
+		return ret;
+	*current_level = ret;
+
+	drm_dbg_kms(aux->drm_dev,
+		    "%s: Found backlight level=%d/%d pwm_freq_pre_divider=%d mode=%x\n",
+		    aux->name, *current_level, bl->max, bl->pwm_freq_pre_divider, *current_mode);
+	drm_dbg_kms(aux->drm_dev,
+		    "%s: Backlight caps: pwmgen_bit_count=%d lsb_reg_used=%d aux_enable=%d\n",
+		    aux->name, bl->pwmgen_bit_count, bl->lsb_reg_used, bl->aux_enable);
+	return 0;
+}
+EXPORT_SYMBOL(drm_edp_backlight_init);
+
+#if IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \
+	(IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))
+
+static int dp_aux_backlight_update_status(struct backlight_device *bd)
+{
+	struct dp_aux_backlight *bl = bl_get_data(bd);
+	u16 brightness = backlight_get_brightness(bd);
+	int ret = 0;
+
+	if (!backlight_is_blank(bd)) {
+		if (!bl->enabled) {
+			drm_edp_backlight_enable(bl->aux, &bl->info, brightness);
+			bl->enabled = true;
+			return 0;
+		}
+		ret = drm_edp_backlight_set_level(bl->aux, &bl->info, brightness);
+	} else {
+		if (bl->enabled) {
+			drm_edp_backlight_disable(bl->aux, &bl->info);
+			bl->enabled = false;
+		}
+	}
+
+	return ret;
+}
+
+static const struct backlight_ops dp_aux_bl_ops = {
+	.update_status = dp_aux_backlight_update_status,
+};
+
+/**
+ * drm_panel_dp_aux_backlight - create and use DP AUX backlight
+ * @panel: DRM panel
+ * @aux: The DP AUX channel to use
+ *
+ * Use this function to create and handle backlight if your panel
+ * supports backlight control over DP AUX channel using DPCD
+ * registers as per VESA's standard backlight control interface.
+ *
+ * When the panel is enabled backlight will be enabled after a
+ * successful call to &drm_panel_funcs.enable()
+ *
+ * When the panel is disabled backlight will be disabled before the
+ * call to &drm_panel_funcs.disable().
+ *
+ * A typical implementation for a panel driver supporting backlight
+ * control over DP AUX will call this function at probe time.
+ * Backlight will then be handled transparently without requiring
+ * any intervention from the driver.
+ *
+ * drm_panel_dp_aux_backlight() must be called after the call to drm_panel_init().
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux)
+{
+	struct dp_aux_backlight *bl;
+	struct backlight_properties props = { 0 };
+	u16 current_level;
+	u8 current_mode;
+	u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE];
+	int ret;
+
+	if (!panel || !panel->dev || !aux)
+		return -EINVAL;
+
+	ret = drm_dp_dpcd_read(aux, DP_EDP_DPCD_REV, edp_dpcd,
+			       EDP_DISPLAY_CTL_CAP_SIZE);
+	if (ret < 0)
+		return ret;
+
+	if (!drm_edp_backlight_supported(edp_dpcd)) {
+		DRM_DEV_INFO(panel->dev, "DP AUX backlight is not supported\n");
+		return 0;
+	}
+
+	bl = devm_kzalloc(panel->dev, sizeof(*bl), GFP_KERNEL);
+	if (!bl)
+		return -ENOMEM;
+
+	bl->aux = aux;
+
+	ret = drm_edp_backlight_init(aux, &bl->info, 0, edp_dpcd,
+				     &current_level, &current_mode);
+	if (ret < 0)
+		return ret;
+
+	props.type = BACKLIGHT_RAW;
+	props.brightness = current_level;
+	props.max_brightness = bl->info.max;
+
+	bl->base = devm_backlight_device_register(panel->dev, "dp_aux_backlight",
+						  panel->dev, bl,
+						  &dp_aux_bl_ops, &props);
+	if (IS_ERR(bl->base))
+		return PTR_ERR(bl->base);
+
+	backlight_disable(bl->base);
+
+	panel->backlight = bl->base;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_panel_dp_aux_backlight);
+
+#endif
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index ad0795afc21c..86d13d6bc463 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2872,11 +2872,13 @@ static int process_single_tx_qlock(struct drm_dp_mst_topology_mgr *mgr,
 	idx += tosend + 1;
 
 	ret = drm_dp_send_sideband_msg(mgr, up, chunk, idx);
-	if (unlikely(ret) && drm_debug_enabled(DRM_UT_DP)) {
-		struct drm_printer p = drm_debug_printer(DBG_PREFIX);
+	if (ret) {
+		if (drm_debug_enabled(DRM_UT_DP)) {
+			struct drm_printer p = drm_debug_printer(DBG_PREFIX);
 
-		drm_printf(&p, "sideband msg failed to send\n");
-		drm_dp_mst_dump_sideband_msg_tx(&p, txmsg);
+			drm_printf(&p, "sideband msg failed to send\n");
+			drm_dp_mst_dump_sideband_msg_tx(&p, txmsg);
+		}
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 8804ec7d3215..7a5097467ba5 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -249,7 +249,7 @@ void drm_minor_release(struct drm_minor *minor)
  * Finally when everything is up and running and ready for userspace the device
  * instance can be published using drm_dev_register().
  *
- * There is also deprecated support for initalizing device instances using
+ * There is also deprecated support for initializing device instances using
  * bus-specific helpers and the &drm_driver.load callback. But due to
  * backwards-compatibility needs the device instance have to be published too
  * early, which requires unpretty global locking to make safe and is therefore
@@ -379,7 +379,7 @@ void drm_minor_release(struct drm_minor *minor)
  * shortcoming however, drm_dev_unplug() marks the drm_device as unplugged before
  * drm_atomic_helper_shutdown() is called. This means that if the disable code
  * paths are protected, they will not run on regular driver module unload,
- * possibily leaving the hardware enabled.
+ * possibly leaving the hardware enabled.
  */
 
 /**
diff --git a/drivers/gpu/drm/drm_dsc.c b/drivers/gpu/drm/drm_dsc.c
index ff602f7ec65b..46a3c1b62463 100644
--- a/drivers/gpu/drm/drm_dsc.c
+++ b/drivers/gpu/drm/drm_dsc.c
@@ -98,7 +98,7 @@ void drm_dsc_pps_payload_pack(struct drm_dsc_picture_parameter_set *pps_payload,
 {
 	int i;
 
-	/* Protect against someone accidently changing struct size */
+	/* Protect against someone accidentally changing struct size */
 	BUILD_BUG_ON(sizeof(*pps_payload) !=
 		     DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 + 1);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 81d5f2524246..6325877c5fd6 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1919,7 +1919,7 @@ EXPORT_SYMBOL(drm_add_override_edid_modes);
  * level, drivers must make all reasonable efforts to expose it as an I2C
  * adapter and use drm_get_edid() instead of abusing this function.
  *
- * The EDID may be overridden using debugfs override_edid or firmare EDID
+ * The EDID may be overridden using debugfs override_edid or firmware EDID
  * (drm_load_edid_firmware() and drm.edid_firmware parameter), in this priority
  * order. Having either of them bypasses actual EDID reads.
  *
@@ -5906,7 +5906,7 @@ drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame,
 	 * (ie.vic==0 and s3d_struct==0) we will still send it if we
 	 * know that the sink can handle it. This is based on a
 	 * suggestion in HDMI 2.0 Appendix F. Apparently some sinks
-	 * have trouble realizing that they shuld switch from 3D to 2D
+	 * have trouble realizing that they should switch from 3D to 2D
 	 * mode if the source simply stops sending the infoframe when
 	 * it wants to switch from 3D to 2D.
 	 */
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d77a24507d30..3ab078321045 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -565,7 +565,7 @@ struct fb_info *drm_fb_helper_alloc_fbi(struct drm_fb_helper *fb_helper)
 		goto err_release;
 
 	/*
-	 * TODO: We really should be smarter here and alloc an apperture
+	 * TODO: We really should be smarter here and alloc an aperture
 	 * for each IORESOURCE_MEM resource helper->dev->dev has and also
 	 * init the ranges of the appertures based on the resources.
 	 * Note some drivers currently count on there being only 1 empty
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index d4f0bac6f8f8..ed25168619fc 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -176,6 +176,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
 	init_waitqueue_head(&file->event_wait);
 	file->event_space = 4096; /* set aside 4k for event buffer */
 
+	spin_lock_init(&file->master_lookup_lock);
 	mutex_init(&file->event_read_lock);
 
 	if (drm_core_check_feature(dev, DRIVER_GEM))
@@ -404,7 +405,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
  *
  * RETURNS:
  *
- * 0 on success or negative errno value on falure.
+ * 0 on success or negative errno value on failure.
  */
 int drm_open(struct inode *inode, struct file *filp)
 {
@@ -547,7 +548,7 @@ EXPORT_SYMBOL(drm_release_noglobal);
  * @offset: offset to read
  *
  * This function must be used by drivers as their &file_operations.read
- * method iff they use DRM events for asynchronous signalling to userspace.
+ * method if they use DRM events for asynchronous signalling to userspace.
  * Since events are used by the KMS API for vblank and page flip completion this
  * means all modern display drivers must use it.
  *
@@ -640,7 +641,7 @@ EXPORT_SYMBOL(drm_read);
  * @wait: poll waiter table
  *
  * This function must be used by drivers as their &file_operations.read method
- * iff they use DRM events for asynchronous signalling to userspace.  Since
+ * if they use DRM events for asynchronous signalling to userspace.  Since
  * events are used by the KMS API for vblank and page flip completion this means
  * all modern display drivers must use it.
  *
diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c
index 0e885cd34107..5231104b1498 100644
--- a/drivers/gpu/drm/drm_format_helper.c
+++ b/drivers/gpu/drm/drm_format_helper.c
@@ -412,7 +412,7 @@ EXPORT_SYMBOL(drm_fb_blit_rect_dstclip);
  * of the display and the framebuffer mismatch, the copy function will
  * attempt to convert between them.
  *
- * See drm_fb_blit_rect_dstclip() for more inforamtion.
+ * See drm_fb_blit_rect_dstclip() for more information.
  *
  * Returns:
  * 0 on success, or a negative error code otherwise.
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index 4d01464b6f95..07f5abc875e9 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -404,6 +404,9 @@ static void drm_mode_rmfb_work_fn(struct work_struct *w)
 		struct drm_framebuffer *fb =
 			list_first_entry(&arg->fbs, typeof(*fb), filp_head);
 
+		drm_dbg_kms(fb->dev,
+			    "Removing [FB:%d] from all active usage due to RMFB ioctl\n",
+			    fb->base.id);
 		list_del_init(&fb->filp_head);
 		drm_framebuffer_remove(fb);
 	}
@@ -981,6 +984,10 @@ retry:
 		if (plane->state->fb != fb)
 			continue;
 
+		drm_dbg_kms(dev,
+			    "Disabling [PLANE:%d:%s] because [FB:%d] is removed\n",
+			    plane->base.id, plane->name, fb->base.id);
+
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
 			ret = PTR_ERR(plane_state);
@@ -990,6 +997,11 @@ retry:
 		if (disable_crtcs && plane_state->crtc->primary == plane) {
 			struct drm_crtc_state *crtc_state;
 
+			drm_dbg_kms(dev,
+				    "Disabling [CRTC:%d:%s] because [FB:%d] is removed\n",
+				    plane_state->crtc->base.id,
+				    plane_state->crtc->name, fb->base.id);
+
 			crtc_state = drm_atomic_get_existing_crtc_state(state, plane_state->crtc);
 
 			ret = drm_atomic_add_affected_connectors(state, plane_state->crtc);
@@ -1052,6 +1064,10 @@ static void legacy_remove_fb(struct drm_framebuffer *fb)
 	/* remove from any CRTC */
 	drm_for_each_crtc(crtc, dev) {
 		if (crtc->primary->fb == fb) {
+			drm_dbg_kms(dev,
+				    "Disabling [CRTC:%d:%s] because [FB:%d] is removed\n",
+				    crtc->base.id, crtc->name, fb->base.id);
+
 			/* should turn off the crtc */
 			if (drm_crtc_force_disable(crtc))
 				DRM_ERROR("failed to reset crtc %p when fb was deleted\n", crtc);
@@ -1059,8 +1075,12 @@ static void legacy_remove_fb(struct drm_framebuffer *fb)
 	}
 
 	drm_for_each_plane(plane, dev) {
-		if (plane->fb == fb)
+		if (plane->fb == fb) {
+			drm_dbg_kms(dev,
+				    "Disabling [PLANE:%d:%s] because [FB:%d] is removed\n",
+				    plane->base.id, plane->name, fb->base.id);
 			drm_plane_force_disable(plane);
+		}
 	}
 	drm_modeset_unlock_all(dev);
 }
@@ -1090,7 +1110,7 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb)
 
 	/*
 	 * drm ABI mandates that we remove any deleted framebuffers from active
-	 * useage. But since most sane clients only remove framebuffers they no
+	 * usage. But since most sane clients only remove framebuffers they no
 	 * longer need, try to optimize this away.
 	 *
 	 * Since we're holding a reference ourselves, observing a refcount of 1
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index d62fb1a3c916..09c820045859 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -901,7 +901,7 @@ err:
 }
 
 /**
- * drm_gem_open - initalizes GEM file-private structures at devnode open time
+ * drm_gem_open - initializes GEM file-private structures at devnode open time
  * @dev: drm_device which is being opened by userspace
  * @file_private: drm file-private structure to set up
  *
@@ -936,7 +936,7 @@ drm_gem_release(struct drm_device *dev, struct drm_file *file_private)
  * drm_gem_object_release - release GEM buffer object resources
  * @obj: GEM buffer object
  *
- * This releases any structures and resources used by @obj and is the invers of
+ * This releases any structures and resources used by @obj and is the inverse of
  * drm_gem_object_init().
  */
 void
@@ -974,28 +974,6 @@ drm_gem_object_free(struct kref *kref)
 EXPORT_SYMBOL(drm_gem_object_free);
 
 /**
- * drm_gem_object_put_locked - release a GEM buffer object reference
- * @obj: GEM buffer object
- *
- * This releases a reference to @obj. Callers must hold the
- * &drm_device.struct_mutex lock when calling this function, even when the
- * driver doesn't use &drm_device.struct_mutex for anything.
- *
- * For drivers not encumbered with legacy locking use
- * drm_gem_object_put() instead.
- */
-void
-drm_gem_object_put_locked(struct drm_gem_object *obj)
-{
-	if (obj) {
-		WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
-
-		kref_put(&obj->refcount, drm_gem_object_free);
-	}
-}
-EXPORT_SYMBOL(drm_gem_object_put_locked);
-
-/**
  * drm_gem_vm_open - vma->ops->open implementation for GEM
  * @vma: VM area structure
  *
@@ -1148,15 +1126,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EACCES;
 	}
 
-	if (node->readonly) {
-		if (vma->vm_flags & VM_WRITE) {
-			drm_gem_object_put(obj);
-			return -EINVAL;
-		}
-
-		vma->vm_flags &= ~VM_MAYWRITE;
-	}
-
 	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT,
 			       vma);
 
@@ -1311,6 +1280,9 @@ EXPORT_SYMBOL(drm_gem_unlock_reservations);
  * @fence_array: array of dma_fence * for the job to block on.
  * @fence: the dma_fence to add to the list of dependencies.
  *
+ * This functions consumes the reference for @fence both on success and error
+ * cases.
+ *
  * Returns:
  * 0 on success, or an error on failing to expand the array.
  */
diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c
index a27135084ae5..e570398abd78 100644
--- a/drivers/gpu/drm/drm_gem_atomic_helper.c
+++ b/drivers/gpu/drm/drm_gem_atomic_helper.c
@@ -52,7 +52,7 @@
  *
  * The helpers for shadow-buffered planes establish and release mappings,
  * and provide struct drm_shadow_plane_state, which stores the plane's mapping
- * for commit-tail functons.
+ * for commit-tail functions.
  *
  * Shadow-buffered planes can easily be enabled by using the provided macros
  * %DRM_GEM_SHADOW_PLANE_FUNCS and %DRM_GEM_SHADOW_PLANE_HELPER_FUNCS.
@@ -135,6 +135,9 @@
  * GEM based framebuffer drivers which have their buffers always pinned in
  * memory.
  *
+ * This function is the default implementation for GEM drivers of
+ * &drm_plane_helper_funcs.prepare_fb if no callback is provided.
+ *
  * See drm_atomic_set_fence_for_plane() for a discussion of implicit and
  * explicit fencing in atomic modeset updates.
  */
@@ -180,6 +183,27 @@ EXPORT_SYMBOL(drm_gem_simple_display_pipe_prepare_fb);
  */
 
 /**
+ * __drm_gem_duplicate_shadow_plane_state - duplicates shadow-buffered plane state
+ * @plane: the plane
+ * @new_shadow_plane_state: the new shadow-buffered plane state
+ *
+ * This function duplicates shadow-buffered plane state. This is helpful for drivers
+ * that subclass struct drm_shadow_plane_state.
+ *
+ * The function does not duplicate existing mappings of the shadow buffers.
+ * Mappings are maintained during the atomic commit by the plane's prepare_fb
+ * and cleanup_fb helpers. See drm_gem_prepare_shadow_fb() and drm_gem_cleanup_shadow_fb()
+ * for corresponding helpers.
+ */
+void
+__drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane,
+				       struct drm_shadow_plane_state *new_shadow_plane_state)
+{
+	__drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base);
+}
+EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state);
+
+/**
  * drm_gem_duplicate_shadow_plane_state - duplicates shadow-buffered plane state
  * @plane: the plane
  *
@@ -208,13 +232,26 @@ drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane)
 	new_shadow_plane_state = kzalloc(sizeof(*new_shadow_plane_state), GFP_KERNEL);
 	if (!new_shadow_plane_state)
 		return NULL;
-	__drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base);
+	__drm_gem_duplicate_shadow_plane_state(plane, new_shadow_plane_state);
 
 	return &new_shadow_plane_state->base;
 }
 EXPORT_SYMBOL(drm_gem_duplicate_shadow_plane_state);
 
 /**
+ * __drm_gem_destroy_shadow_plane_state - cleans up shadow-buffered plane state
+ * @shadow_plane_state: the shadow-buffered plane state
+ *
+ * This function cleans up shadow-buffered plane state. Helpful for drivers that
+ * subclass struct drm_shadow_plane_state.
+ */
+void __drm_gem_destroy_shadow_plane_state(struct drm_shadow_plane_state *shadow_plane_state)
+{
+	__drm_atomic_helper_plane_destroy_state(&shadow_plane_state->base);
+}
+EXPORT_SYMBOL(__drm_gem_destroy_shadow_plane_state);
+
+/**
  * drm_gem_destroy_shadow_plane_state - deletes shadow-buffered plane state
  * @plane: the plane
  * @plane_state: the plane state of type struct drm_shadow_plane_state
@@ -229,12 +266,27 @@ void drm_gem_destroy_shadow_plane_state(struct drm_plane *plane,
 	struct drm_shadow_plane_state *shadow_plane_state =
 		to_drm_shadow_plane_state(plane_state);
 
-	__drm_atomic_helper_plane_destroy_state(&shadow_plane_state->base);
+	__drm_gem_destroy_shadow_plane_state(shadow_plane_state);
 	kfree(shadow_plane_state);
 }
 EXPORT_SYMBOL(drm_gem_destroy_shadow_plane_state);
 
 /**
+ * __drm_gem_reset_shadow_plane - resets a shadow-buffered plane
+ * @plane: the plane
+ * @shadow_plane_state: the shadow-buffered plane state
+ *
+ * This function resets state for shadow-buffered planes. Helpful
+ * for drivers that subclass struct drm_shadow_plane_state.
+ */
+void __drm_gem_reset_shadow_plane(struct drm_plane *plane,
+				  struct drm_shadow_plane_state *shadow_plane_state)
+{
+	__drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base);
+}
+EXPORT_SYMBOL(__drm_gem_reset_shadow_plane);
+
+/**
  * drm_gem_reset_shadow_plane - resets a shadow-buffered plane
  * @plane: the plane
  *
@@ -255,7 +307,7 @@ void drm_gem_reset_shadow_plane(struct drm_plane *plane)
 	shadow_plane_state = kzalloc(sizeof(*shadow_plane_state), GFP_KERNEL);
 	if (!shadow_plane_state)
 		return;
-	__drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base);
+	__drm_gem_reset_shadow_plane(plane, shadow_plane_state);
 }
 EXPORT_SYMBOL(drm_gem_reset_shadow_plane);
 
@@ -278,10 +330,7 @@ int drm_gem_prepare_shadow_fb(struct drm_plane *plane, struct drm_plane_state *p
 {
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 	struct drm_framebuffer *fb = plane_state->fb;
-	struct drm_gem_object *obj;
-	struct dma_buf_map map;
 	int ret;
-	size_t i;
 
 	if (!fb)
 		return 0;
@@ -290,27 +339,7 @@ int drm_gem_prepare_shadow_fb(struct drm_plane *plane, struct drm_plane_state *p
 	if (ret)
 		return ret;
 
-	for (i = 0; i < ARRAY_SIZE(shadow_plane_state->map); ++i) {
-		obj = drm_gem_fb_get_obj(fb, i);
-		if (!obj)
-			continue;
-		ret = drm_gem_vmap(obj, &map);
-		if (ret)
-			goto err_drm_gem_vunmap;
-		shadow_plane_state->map[i] = map;
-	}
-
-	return 0;
-
-err_drm_gem_vunmap:
-	while (i) {
-		--i;
-		obj = drm_gem_fb_get_obj(fb, i);
-		if (!obj)
-			continue;
-		drm_gem_vunmap(obj, &shadow_plane_state->map[i]);
-	}
-	return ret;
+	return drm_gem_fb_vmap(fb, shadow_plane_state->map, shadow_plane_state->data);
 }
 EXPORT_SYMBOL(drm_gem_prepare_shadow_fb);
 
@@ -322,25 +351,17 @@ EXPORT_SYMBOL(drm_gem_prepare_shadow_fb);
  * This function implements struct &drm_plane_helper_funcs.cleanup_fb.
  * This function unmaps all buffer objects of the plane's framebuffer.
  *
- * See drm_gem_prepare_shadow_fb() for more inforamtion.
+ * See drm_gem_prepare_shadow_fb() for more information.
  */
 void drm_gem_cleanup_shadow_fb(struct drm_plane *plane, struct drm_plane_state *plane_state)
 {
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 	struct drm_framebuffer *fb = plane_state->fb;
-	size_t i = ARRAY_SIZE(shadow_plane_state->map);
-	struct drm_gem_object *obj;
 
 	if (!fb)
 		return;
 
-	while (i) {
-		--i;
-		obj = drm_gem_fb_get_obj(fb, i);
-		if (!obj)
-			continue;
-		drm_gem_vunmap(obj, &shadow_plane_state->map[i]);
-	}
+	drm_gem_fb_vunmap(fb, shadow_plane_state->map);
 }
 EXPORT_SYMBOL(drm_gem_cleanup_shadow_fb);
 
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index e2c68822e05c..3c75d79dbb65 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -15,6 +15,8 @@
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_modeset_helper.h>
 
+#include "drm_internal.h"
+
 #define AFBC_HEADER_SIZE		16
 #define AFBC_TH_LAYOUT_ALIGNMENT	8
 #define AFBC_HDR_ALIGN			64
@@ -48,7 +50,7 @@
 struct drm_gem_object *drm_gem_fb_get_obj(struct drm_framebuffer *fb,
 					  unsigned int plane)
 {
-	if (plane >= 4)
+	if (plane >= ARRAY_SIZE(fb->obj))
 		return NULL;
 
 	return fb->obj[plane];
@@ -62,7 +64,8 @@ drm_gem_fb_init(struct drm_device *dev,
 		 struct drm_gem_object **obj, unsigned int num_planes,
 		 const struct drm_framebuffer_funcs *funcs)
 {
-	int ret, i;
+	unsigned int i;
+	int ret;
 
 	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
 
@@ -86,9 +89,9 @@ drm_gem_fb_init(struct drm_device *dev,
  */
 void drm_gem_fb_destroy(struct drm_framebuffer *fb)
 {
-	int i;
+	size_t i;
 
-	for (i = 0; i < 4; i++)
+	for (i = 0; i < ARRAY_SIZE(fb->obj); i++)
 		drm_gem_object_put(fb->obj[i]);
 
 	drm_framebuffer_cleanup(fb);
@@ -145,8 +148,9 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 			       const struct drm_framebuffer_funcs *funcs)
 {
 	const struct drm_format_info *info;
-	struct drm_gem_object *objs[4];
-	int ret, i;
+	struct drm_gem_object *objs[DRM_FORMAT_MAX_PLANES];
+	unsigned int i;
+	int ret;
 
 	info = drm_get_format_info(dev, mode_cmd);
 	if (!info) {
@@ -187,9 +191,10 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 	return 0;
 
 err_gem_object_put:
-	for (i--; i >= 0; i--)
+	while (i > 0) {
+		--i;
 		drm_gem_object_put(objs[i]);
-
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(drm_gem_fb_init_with_funcs);
@@ -306,6 +311,184 @@ drm_gem_fb_create_with_dirty(struct drm_device *dev, struct drm_file *file,
 }
 EXPORT_SYMBOL_GPL(drm_gem_fb_create_with_dirty);
 
+/**
+ * drm_gem_fb_vmap - maps all framebuffer BOs into kernel address space
+ * @fb: the framebuffer
+ * @map: returns the mapping's address for each BO
+ * @data: returns the data address for each BO, can be NULL
+ *
+ * This function maps all buffer objects of the given framebuffer into
+ * kernel address space and stores them in struct dma_buf_map. If the
+ * mapping operation fails for one of the BOs, the function unmaps the
+ * already established mappings automatically.
+ *
+ * Callers that want to access a BO's stored data should pass @data.
+ * The argument returns the addresses of the data stored in each BO. This
+ * is different from @map if the framebuffer's offsets field is non-zero.
+ *
+ * See drm_gem_fb_vunmap() for unmapping.
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ */
+int drm_gem_fb_vmap(struct drm_framebuffer *fb,
+		    struct dma_buf_map map[static DRM_FORMAT_MAX_PLANES],
+		    struct dma_buf_map data[DRM_FORMAT_MAX_PLANES])
+{
+	struct drm_gem_object *obj;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < DRM_FORMAT_MAX_PLANES; ++i) {
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj) {
+			dma_buf_map_clear(&map[i]);
+			continue;
+		}
+		ret = drm_gem_vmap(obj, &map[i]);
+		if (ret)
+			goto err_drm_gem_vunmap;
+	}
+
+	if (data) {
+		for (i = 0; i < DRM_FORMAT_MAX_PLANES; ++i) {
+			memcpy(&data[i], &map[i], sizeof(data[i]));
+			if (dma_buf_map_is_null(&data[i]))
+				continue;
+			dma_buf_map_incr(&data[i], fb->offsets[i]);
+		}
+	}
+
+	return 0;
+
+err_drm_gem_vunmap:
+	while (i) {
+		--i;
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj)
+			continue;
+		drm_gem_vunmap(obj, &map[i]);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(drm_gem_fb_vmap);
+
+/**
+ * drm_gem_fb_vunmap - unmaps framebuffer BOs from kernel address space
+ * @fb: the framebuffer
+ * @map: mapping addresses as returned by drm_gem_fb_vmap()
+ *
+ * This function unmaps all buffer objects of the given framebuffer.
+ *
+ * See drm_gem_fb_vmap() for more information.
+ */
+void drm_gem_fb_vunmap(struct drm_framebuffer *fb,
+		       struct dma_buf_map map[static DRM_FORMAT_MAX_PLANES])
+{
+	unsigned int i = DRM_FORMAT_MAX_PLANES;
+	struct drm_gem_object *obj;
+
+	while (i) {
+		--i;
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj)
+			continue;
+		if (dma_buf_map_is_null(&map[i]))
+			continue;
+		drm_gem_vunmap(obj, &map[i]);
+	}
+}
+EXPORT_SYMBOL(drm_gem_fb_vunmap);
+
+/**
+ * drm_gem_fb_begin_cpu_access - prepares GEM buffer objects for CPU access
+ * @fb: the framebuffer
+ * @dir: access mode
+ *
+ * Prepares a framebuffer's GEM buffer objects for CPU access. This function
+ * must be called before accessing the BO data within the kernel. For imported
+ * BOs, the function calls dma_buf_begin_cpu_access().
+ *
+ * See drm_gem_fb_end_cpu_access() for signalling the end of CPU access.
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ */
+int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir)
+{
+	struct dma_buf_attachment *import_attach;
+	struct drm_gem_object *obj;
+	size_t i;
+	int ret, ret2;
+
+	for (i = 0; i < ARRAY_SIZE(fb->obj); ++i) {
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj)
+			continue;
+		import_attach = obj->import_attach;
+		if (!import_attach)
+			continue;
+		ret = dma_buf_begin_cpu_access(import_attach->dmabuf, dir);
+		if (ret)
+			goto err_dma_buf_end_cpu_access;
+	}
+
+	return 0;
+
+err_dma_buf_end_cpu_access:
+	while (i) {
+		--i;
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj)
+			continue;
+		import_attach = obj->import_attach;
+		if (!import_attach)
+			continue;
+		ret2 = dma_buf_end_cpu_access(import_attach->dmabuf, dir);
+		if (ret2) {
+			drm_err(fb->dev,
+				"dma_buf_end_cpu_access() failed during error handling: %d\n",
+				ret2);
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_gem_fb_begin_cpu_access);
+
+/**
+ * drm_gem_fb_end_cpu_access - signals end of CPU access to GEM buffer objects
+ * @fb: the framebuffer
+ * @dir: access mode
+ *
+ * Signals the end of CPU access to the given framebuffer's GEM buffer objects. This
+ * function must be paired with a corresponding call to drm_gem_fb_begin_cpu_access().
+ * For imported BOs, the function calls dma_buf_end_cpu_access().
+ *
+ * See also drm_gem_fb_begin_cpu_access().
+ */
+void drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir)
+{
+	size_t i = ARRAY_SIZE(fb->obj);
+	struct dma_buf_attachment *import_attach;
+	struct drm_gem_object *obj;
+	int ret;
+
+	while (i) {
+		--i;
+		obj = drm_gem_fb_get_obj(fb, i);
+		if (!obj)
+			continue;
+		import_attach = obj->import_attach;
+		if (!import_attach)
+			continue;
+		ret = dma_buf_end_cpu_access(import_attach->dmabuf, dir);
+		if (ret)
+			drm_err(fb->dev, "dma_buf_end_cpu_access() failed: %d\n", ret);
+	}
+}
+EXPORT_SYMBOL(drm_gem_fb_end_cpu_access);
+
 static __u32 drm_gem_afbc_get_bpp(struct drm_device *dev,
 				  const struct drm_mode_fb_cmd2 *mode_cmd)
 {
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 6d625cee7a6a..a61946374c82 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -368,7 +368,7 @@ static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem,
 }
 
 /*
- * drm_gem_shmem_vunmap - Unmap a virtual mapping fo a shmem GEM object
+ * drm_gem_shmem_vunmap - Unmap a virtual mapping for a shmem GEM object
  * @shmem: shmem GEM object
  * @map: Kernel virtual address where the SHMEM GEM object was mapped
  *
@@ -505,13 +505,13 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
 
 	if (!args->pitch || !args->size) {
 		args->pitch = min_pitch;
-		args->size = args->pitch * args->height;
+		args->size = PAGE_ALIGN(args->pitch * args->height);
 	} else {
 		/* ensure sane minimum values */
 		if (args->pitch < min_pitch)
 			args->pitch = min_pitch;
 		if (args->size < args->pitch * args->height)
-			args->size = args->pitch * args->height;
+			args->size = PAGE_ALIGN(args->pitch * args->height);
 	}
 
 	shmem = drm_gem_shmem_create_with_handle(file, dev, args->size, &args->handle);
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 2a1229b8364e..43cf7e887d1a 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -96,7 +96,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs;
  * memory region. Call drm_gem_vram_offset() to retrieve this value. Typically
  * it's used to program the hardware's scanout engine for framebuffers, set
  * the cursor overlay's image for a mouse cursor, or use it as input to the
- * hardware's draing engine.
+ * hardware's drawing engine.
  *
  * To access a buffer object's memory from the DRM driver, call
  * drm_gem_vram_vmap(). It maps the buffer into kernel address
@@ -1012,9 +1012,8 @@ static void drm_vram_mm_cleanup(struct drm_vram_mm *vmm)
  * Helpers for integration with struct drm_device
  */
 
-/* deprecated; use drmm_vram_mm_init() */
-struct drm_vram_mm *drm_vram_helper_alloc_mm(
-	struct drm_device *dev, uint64_t vram_base, size_t vram_size)
+static struct drm_vram_mm *drm_vram_helper_alloc_mm(struct drm_device *dev, uint64_t vram_base,
+						    size_t vram_size)
 {
 	int ret;
 
@@ -1036,9 +1035,8 @@ err_kfree:
 	dev->vram_mm = NULL;
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(drm_vram_helper_alloc_mm);
 
-void drm_vram_helper_release_mm(struct drm_device *dev)
+static void drm_vram_helper_release_mm(struct drm_device *dev)
 {
 	if (!dev->vram_mm)
 		return;
@@ -1047,7 +1045,6 @@ void drm_vram_helper_release_mm(struct drm_device *dev)
 	kfree(dev->vram_mm);
 	dev->vram_mm = NULL;
 }
-EXPORT_SYMBOL(drm_vram_helper_release_mm);
 
 static void drm_vram_mm_release(struct drm_device *dev, void *ptr)
 {
diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c
index 910108ccaae1..ca9b8f697202 100644
--- a/drivers/gpu/drm/drm_hdcp.c
+++ b/drivers/gpu/drm/drm_hdcp.c
@@ -280,7 +280,7 @@ exit:
  * https://www.digital-cp.com/sites/default/files/specifications/HDCP%20on%20HDMI%20Specification%20Rev2_2_Final1.pdf
  *
  * Returns:
- * Count of the revoked KSVs or -ve error number incase of the failure.
+ * Count of the revoked KSVs or -ve error number in case of the failure.
  */
 int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs,
 				u32 ksv_count)
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index f454e0424086..be4a52dc4d6f 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -426,7 +426,7 @@ done:
 }
 
 /**
- * drm_noop - DRM no-op ioctl implemntation
+ * drm_noop - DRM no-op ioctl implementation
  * @dev: DRM device for the ioctl
  * @data: data pointer for the ioctl
  * @file_priv: DRM file for the ioctl call
@@ -446,7 +446,7 @@ int drm_noop(struct drm_device *dev, void *data,
 EXPORT_SYMBOL(drm_noop);
 
 /**
- * drm_invalid_op - DRM invalid ioctl implemntation
+ * drm_invalid_op - DRM invalid ioctl implementation
  * @dev: DRM device for the ioctl
  * @data: data pointer for the ioctl
  * @file_priv: DRM file for the ioctl call
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index c3bd664ea733..13e1d5c4ec82 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -60,50 +60,14 @@
 #include <drm/drm.h>
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
-#include <drm/drm_irq.h>
+#include <drm/drm_legacy.h>
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 
 #include "drm_internal.h"
 
-/**
- * DOC: irq helpers
- *
- * The DRM core provides very simple support helpers to enable IRQ handling on a
- * device through the drm_irq_install() and drm_irq_uninstall() functions. This
- * only supports devices with a single interrupt on the main device stored in
- * &drm_device.dev and set as the device paramter in drm_dev_alloc().
- *
- * These IRQ helpers are strictly optional. Drivers which roll their own only
- * need to set &drm_device.irq_enabled to signal the DRM core that vblank
- * interrupts are working. Since these helpers don't automatically clean up the
- * requested interrupt like e.g. devm_request_irq() they're not really
- * recommended.
- */
-
-/**
- * drm_irq_install - install IRQ handler
- * @dev: DRM device
- * @irq: IRQ number to install the handler for
- *
- * Initializes the IRQ related data. Installs the handler, calling the driver
- * &drm_driver.irq_preinstall and &drm_driver.irq_postinstall functions before
- * and after the installation.
- *
- * This is the simplified helper interface provided for drivers with no special
- * needs. Drivers which need to install interrupt handlers for multiple
- * interrupts must instead set &drm_device.irq_enabled to signal the DRM core
- * that vblank interrupts are available.
- *
- * @irq must match the interrupt number that would be passed to request_irq(),
- * if called directly instead of using this helper function.
- *
- * &drm_driver.irq_handler is called to handle the registered interrupt.
- *
- * Returns:
- * Zero on success or a negative error code on failure.
- */
-int drm_irq_install(struct drm_device *dev, int irq)
+#if IS_ENABLED(CONFIG_DRM_LEGACY)
+static int drm_legacy_irq_install(struct drm_device *dev, int irq)
 {
 	int ret;
 	unsigned long sh_flags = 0;
@@ -140,7 +104,7 @@ int drm_irq_install(struct drm_device *dev, int irq)
 	if (ret < 0) {
 		dev->irq_enabled = false;
 		if (drm_core_check_feature(dev, DRIVER_LEGACY))
-			vga_client_register(to_pci_dev(dev->dev), NULL, NULL, NULL);
+			vga_client_unregister(to_pci_dev(dev->dev));
 		free_irq(irq, dev);
 	} else {
 		dev->irq = irq;
@@ -148,25 +112,8 @@ int drm_irq_install(struct drm_device *dev, int irq)
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_irq_install);
 
-/**
- * drm_irq_uninstall - uninstall the IRQ handler
- * @dev: DRM device
- *
- * Calls the driver's &drm_driver.irq_uninstall function and unregisters the IRQ
- * handler.  This should only be called by drivers which used drm_irq_install()
- * to set up their interrupt handler. Other drivers must only reset
- * &drm_device.irq_enabled to false.
- *
- * Note that for kernel modesetting drivers it is a bug if this function fails.
- * The sanity checks are only to catch buggy user modesetting drivers which call
- * the same function through an ioctl.
- *
- * Returns:
- * Zero on success or a negative error code on failure.
- */
-int drm_irq_uninstall(struct drm_device *dev)
+int drm_legacy_irq_uninstall(struct drm_device *dev)
 {
 	unsigned long irqflags;
 	bool irq_enabled;
@@ -203,7 +150,7 @@ int drm_irq_uninstall(struct drm_device *dev)
 	DRM_DEBUG("irq=%d\n", dev->irq);
 
 	if (drm_core_check_feature(dev, DRIVER_LEGACY))
-		vga_client_register(to_pci_dev(dev->dev), NULL, NULL, NULL);
+		vga_client_unregister(to_pci_dev(dev->dev));
 
 	if (dev->driver->irq_uninstall)
 		dev->driver->irq_uninstall(dev);
@@ -212,41 +159,8 @@ int drm_irq_uninstall(struct drm_device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL(drm_irq_uninstall);
+EXPORT_SYMBOL(drm_legacy_irq_uninstall);
 
-static void devm_drm_irq_uninstall(void *data)
-{
-	drm_irq_uninstall(data);
-}
-
-/**
- * devm_drm_irq_install - install IRQ handler
- * @dev: DRM device
- * @irq: IRQ number to install the handler for
- *
- * devm_drm_irq_install is a  help function of drm_irq_install.
- *
- * if the driver uses devm_drm_irq_install, there is no need
- * to call drm_irq_uninstall when the drm module get unloaded,
- * as this will done automagically.
- *
- * Returns:
- * Zero on success or a negative error code on failure.
- */
-int devm_drm_irq_install(struct drm_device *dev, int irq)
-{
-	int ret;
-
-	ret = drm_irq_install(dev, irq);
-	if (ret)
-		return ret;
-
-	return devm_add_action_or_reset(dev->dev,
-					devm_drm_irq_uninstall, dev);
-}
-EXPORT_SYMBOL(devm_drm_irq_install);
-
-#if IS_ENABLED(CONFIG_DRM_LEGACY)
 int drm_legacy_irq_control(struct drm_device *dev, void *data,
 			   struct drm_file *file_priv)
 {
@@ -275,13 +189,13 @@ int drm_legacy_irq_control(struct drm_device *dev, void *data,
 		    ctl->irq != irq)
 			return -EINVAL;
 		mutex_lock(&dev->struct_mutex);
-		ret = drm_irq_install(dev, irq);
+		ret = drm_legacy_irq_install(dev, irq);
 		mutex_unlock(&dev->struct_mutex);
 
 		return ret;
 	case DRM_UNINST_HANDLER:
 		mutex_lock(&dev->struct_mutex);
-		ret = drm_irq_uninstall(dev);
+		ret = drm_legacy_irq_uninstall(dev);
 		mutex_unlock(&dev->struct_mutex);
 
 		return ret;
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index 00fb433bcef1..dee4f24a1808 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -15,19 +15,62 @@
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
 
+/**
+ * DOC: drm leasing
+ *
+ * DRM leases provide information about whether a DRM master may control a DRM
+ * mode setting object. This enables the creation of multiple DRM masters that
+ * manage subsets of display resources.
+ *
+ * The original DRM master of a device 'owns' the available drm resources. It
+ * may create additional DRM masters and 'lease' resources which it controls
+ * to the new DRM master. This gives the new DRM master control over the
+ * leased resources until the owner revokes the lease, or the new DRM master
+ * is closed. Some helpful terminology:
+ *
+ * - An 'owner' is a &struct drm_master that is not leasing objects from
+ *   another &struct drm_master, and hence 'owns' the objects. The owner can be
+ *   identified as the &struct drm_master for which &drm_master.lessor is NULL.
+ *
+ * - A 'lessor' is a &struct drm_master which is leasing objects to one or more
+ *   other &struct drm_master. Currently, lessees are not allowed to
+ *   create sub-leases, hence the lessor is the same as the owner.
+ *
+ * - A 'lessee' is a &struct drm_master which is leasing objects from some
+ *   other &struct drm_master. Each lessee only leases resources from a single
+ *   lessor recorded in &drm_master.lessor, and holds the set of objects that
+ *   it is leasing in &drm_master.leases.
+ *
+ * - A 'lease' is a contract between the lessor and lessee that identifies
+ *   which resources may be controlled by the lessee. All of the resources
+ *   that are leased must be owned by or leased to the lessor, and lessors are
+ *   not permitted to lease the same object to multiple lessees.
+ *
+ * The set of objects any &struct drm_master 'controls' is limited to the set
+ * of objects it leases (for lessees) or all objects (for owners).
+ *
+ * Objects not controlled by a &struct drm_master cannot be modified through
+ * the various state manipulating ioctls, and any state reported back to user
+ * space will be edited to make them appear idle and/or unusable. For
+ * instance, connectors always report 'disconnected', while encoders
+ * report no possible crtcs or clones.
+ *
+ * Since each lessee may lease objects from a single lessor, display resource
+ * leases form a tree of &struct drm_master. As lessees are currently not
+ * allowed to create sub-leases, the tree depth is limited to 1. All of
+ * these get activated simultaneously when the top level device owner changes
+ * through the SETMASTER or DROPMASTER IOCTL, so &drm_device.master points to
+ * the owner at the top of the lease tree (i.e. the &struct drm_master for which
+ * &drm_master.lessor is NULL). The full list of lessees that are leasing
+ * objects from the owner can be searched via the owner's
+ * &drm_master.lessee_idr.
+ */
+
 #define drm_for_each_lessee(lessee, lessor) \
 	list_for_each_entry((lessee), &(lessor)->lessees, lessee_list)
 
 static uint64_t drm_lease_idr_object;
 
-/**
- * drm_lease_owner - return ancestor owner drm_master
- * @master: drm_master somewhere within tree of lessees and lessors
- *
- * RETURN:
- *
- * drm_master at the top of the tree (i.e, with lessor NULL
- */
 struct drm_master *drm_lease_owner(struct drm_master *master)
 {
 	while (master->lessor != NULL)
@@ -35,16 +78,6 @@ struct drm_master *drm_lease_owner(struct drm_master *master)
 	return master;
 }
 
-/**
- * _drm_find_lessee - find lessee by id (idr_mutex held)
- * @master: drm_master of lessor
- * @lessee_id: id
- *
- * RETURN:
- *
- * drm_master of the lessee if valid, NULL otherwise
- */
-
 static struct drm_master*
 _drm_find_lessee(struct drm_master *master, int lessee_id)
 {
@@ -52,17 +85,6 @@ _drm_find_lessee(struct drm_master *master, int lessee_id)
 	return idr_find(&drm_lease_owner(master)->lessee_idr, lessee_id);
 }
 
-/**
- * _drm_lease_held_master - check to see if an object is leased (or owned) by master (idr_mutex held)
- * @master: the master to check the lease status of
- * @id: the id to check
- *
- * Checks if the specified master holds a lease on the object. Return
- * value:
- *
- *	true		'master' holds a lease on (or owns) the object
- *	false		'master' does not hold a lease.
- */
 static int _drm_lease_held_master(struct drm_master *master, int id)
 {
 	lockdep_assert_held(&master->dev->mode_config.idr_mutex);
@@ -71,17 +93,7 @@ static int _drm_lease_held_master(struct drm_master *master, int id)
 	return true;
 }
 
-/**
- * _drm_has_leased - check to see if an object has been leased (idr_mutex held)
- * @master: the master to check the lease status of
- * @id: the id to check
- *
- * Checks if any lessee of 'master' holds a lease on 'id'. Return
- * value:
- *
- *	true		Some lessee holds a lease on the object.
- *	false		No lessee has a lease on the object.
- */
+/* Checks if the given object has been leased to some lessee of drm_master */
 static bool _drm_has_leased(struct drm_master *master, int id)
 {
 	struct drm_master *lessee;
@@ -93,58 +105,51 @@ static bool _drm_has_leased(struct drm_master *master, int id)
 	return false;
 }
 
-/**
- * _drm_lease_held - check drm_mode_object lease status (idr_mutex held)
- * @file_priv: the master drm_file
- * @id: the object id
- *
- * Checks if the specified master holds a lease on the object. Return
- * value:
- *
- *	true		'master' holds a lease on (or owns) the object
- *	false		'master' does not hold a lease.
- */
+/* Called with idr_mutex held */
 bool _drm_lease_held(struct drm_file *file_priv, int id)
 {
-	if (!file_priv || !file_priv->master)
+	bool ret;
+	struct drm_master *master;
+
+	if (!file_priv)
+		return true;
+
+	master = drm_file_get_master(file_priv);
+	if (!master)
 		return true;
+	ret = _drm_lease_held_master(master, id);
+	drm_master_put(&master);
 
-	return _drm_lease_held_master(file_priv->master, id);
+	return ret;
 }
 
-/**
- * drm_lease_held - check drm_mode_object lease status (idr_mutex not held)
- * @file_priv: the master drm_file
- * @id: the object id
- *
- * Checks if the specified master holds a lease on the object. Return
- * value:
- *
- *	true		'master' holds a lease on (or owns) the object
- *	false		'master' does not hold a lease.
- */
 bool drm_lease_held(struct drm_file *file_priv, int id)
 {
 	struct drm_master *master;
 	bool ret;
 
-	if (!file_priv || !file_priv->master || !file_priv->master->lessor)
+	if (!file_priv)
 		return true;
 
-	master = file_priv->master;
+	master = drm_file_get_master(file_priv);
+	if (!master)
+		return true;
+	if (!master->lessor) {
+		ret = true;
+		goto out;
+	}
 	mutex_lock(&master->dev->mode_config.idr_mutex);
 	ret = _drm_lease_held_master(master, id);
 	mutex_unlock(&master->dev->mode_config.idr_mutex);
+
+out:
+	drm_master_put(&master);
 	return ret;
 }
 
-/**
- * drm_lease_filter_crtcs - restricted crtc set to leased values (idr_mutex not held)
- * @file_priv: requestor file
- * @crtcs_in: bitmask of crtcs to check
- *
- * Reconstructs a crtc mask based on the crtcs which are visible
- * through the specified file.
+/*
+ * Given a bitmask of crtcs to check, reconstructs a crtc mask based on the
+ * crtcs which are visible through the specified file.
  */
 uint32_t drm_lease_filter_crtcs(struct drm_file *file_priv, uint32_t crtcs_in)
 {
@@ -154,10 +159,16 @@ uint32_t drm_lease_filter_crtcs(struct drm_file *file_priv, uint32_t crtcs_in)
 	int count_in, count_out;
 	uint32_t crtcs_out = 0;
 
-	if (!file_priv || !file_priv->master || !file_priv->master->lessor)
+	if (!file_priv)
 		return crtcs_in;
 
-	master = file_priv->master;
+	master = drm_file_get_master(file_priv);
+	if (!master)
+		return crtcs_in;
+	if (!master->lessor) {
+		crtcs_out = crtcs_in;
+		goto out;
+	}
 	dev = master->dev;
 
 	count_in = count_out = 0;
@@ -176,14 +187,13 @@ uint32_t drm_lease_filter_crtcs(struct drm_file *file_priv, uint32_t crtcs_in)
 		count_in++;
 	}
 	mutex_unlock(&master->dev->mode_config.idr_mutex);
+
+out:
+	drm_master_put(&master);
 	return crtcs_out;
 }
 
 /*
- * drm_lease_create - create a new drm_master with leased objects (idr_mutex not held)
- * @lessor: lease holder (or owner) of objects
- * @leases: objects to lease to the new drm_master
- *
  * Uses drm_master_create to allocate a new drm_master, then checks to
  * make sure all of the desired objects can be leased, atomically
  * leasing them to the new drmmaster.
@@ -252,15 +262,6 @@ out_lessee:
 	return ERR_PTR(error);
 }
 
-/**
- * drm_lease_destroy - a master is going away (idr_mutex not held)
- * @master: the drm_master being destroyed
- *
- * All lessees will have been destroyed as they
- * hold a reference on their lessor. Notify any
- * lessor for this master so that it can check
- * the list of lessees.
- */
 void drm_lease_destroy(struct drm_master *master)
 {
 	struct drm_device *dev = master->dev;
@@ -294,10 +295,6 @@ void drm_lease_destroy(struct drm_master *master)
 	DRM_DEBUG_LEASE("drm_lease_destroy done %d\n", master->lessee_id);
 }
 
-/**
- * _drm_lease_revoke - revoke access to all leased objects (idr_mutex held)
- * @top: the master losing its lease
- */
 static void _drm_lease_revoke(struct drm_master *top)
 {
 	int object;
@@ -336,10 +333,6 @@ static void _drm_lease_revoke(struct drm_master *top)
 	}
 }
 
-/**
- * drm_lease_revoke - revoke access to all leased objects (idr_mutex not held)
- * @top: the master losing its lease
- */
 void drm_lease_revoke(struct drm_master *top)
 {
 	mutex_lock(&top->dev->mode_config.idr_mutex);
@@ -471,12 +464,7 @@ out_free_objects:
 	return ret;
 }
 
-/**
- * drm_mode_create_lease_ioctl - create a new lease
- * @dev: the drm device
- * @data: pointer to struct drm_mode_create_lease
- * @lessor_priv: the file being manipulated
- *
+/*
  * The master associated with the specified file will have a lease
  * created containing the objects specified in the ioctl structure.
  * A file descriptor will be allocated for that and returned to the
@@ -489,7 +477,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	size_t object_count;
 	int ret = 0;
 	struct idr leases;
-	struct drm_master *lessor = lessor_priv->master;
+	struct drm_master *lessor;
 	struct drm_master *lessee = NULL;
 	struct file *lessee_file = NULL;
 	struct file *lessor_file = lessor_priv->filp;
@@ -501,12 +489,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
-	/* Do not allow sub-leases */
-	if (lessor->lessor) {
-		DRM_DEBUG_LEASE("recursive leasing not allowed\n");
-		return -EINVAL;
-	}
-
 	/* need some objects */
 	if (cl->object_count == 0) {
 		DRM_DEBUG_LEASE("no objects in lease\n");
@@ -518,12 +500,22 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 		return -EINVAL;
 	}
 
+	lessor = drm_file_get_master(lessor_priv);
+	/* Do not allow sub-leases */
+	if (lessor->lessor) {
+		DRM_DEBUG_LEASE("recursive leasing not allowed\n");
+		ret = -EINVAL;
+		goto out_lessor;
+	}
+
 	object_count = cl->object_count;
 
 	object_ids = memdup_user(u64_to_user_ptr(cl->object_ids),
 			array_size(object_count, sizeof(__u32)));
-	if (IS_ERR(object_ids))
-		return PTR_ERR(object_ids);
+	if (IS_ERR(object_ids)) {
+		ret = PTR_ERR(object_ids);
+		goto out_lessor;
+	}
 
 	idr_init(&leases);
 
@@ -534,14 +526,15 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	if (ret) {
 		DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret);
 		idr_destroy(&leases);
-		return ret;
+		goto out_lessor;
 	}
 
 	/* Allocate a file descriptor for the lease */
 	fd = get_unused_fd_flags(cl->flags & (O_CLOEXEC | O_NONBLOCK));
 	if (fd < 0) {
 		idr_destroy(&leases);
-		return fd;
+		ret = fd;
+		goto out_lessor;
 	}
 
 	DRM_DEBUG_LEASE("Creating lease\n");
@@ -577,6 +570,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	/* Hook up the fd */
 	fd_install(fd, lessee_file);
 
+	drm_master_put(&lessor);
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 
@@ -586,29 +580,19 @@ out_lessee:
 out_leases:
 	put_unused_fd(fd);
 
+out_lessor:
+	drm_master_put(&lessor);
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret);
 	return ret;
 }
 
-/**
- * drm_mode_list_lessees_ioctl - list lessee ids
- * @dev: the drm device
- * @data: pointer to struct drm_mode_list_lessees
- * @lessor_priv: the file being manipulated
- *
- * Starting from the master associated with the specified file,
- * the master with the provided lessee_id is found, and then
- * an array of lessee ids associated with leases from that master
- * are returned.
- */
-
 int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *lessor_priv)
 {
 	struct drm_mode_list_lessees *arg = data;
 	__u32 __user *lessee_ids = (__u32 __user *) (uintptr_t) (arg->lessees_ptr);
 	__u32 count_lessees = arg->count_lessees;
-	struct drm_master *lessor = lessor_priv->master, *lessee;
+	struct drm_master *lessor, *lessee;
 	int count;
 	int ret = 0;
 
@@ -619,6 +603,7 @@ int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessor = drm_file_get_master(lessor_priv);
 	DRM_DEBUG_LEASE("List lessees for %d\n", lessor->lessee_id);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
@@ -642,26 +627,19 @@ int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 		arg->count_lessees = count;
 
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessor);
 
 	return ret;
 }
 
-/**
- * drm_mode_get_lease_ioctl - list leased objects
- * @dev: the drm device
- * @data: pointer to struct drm_mode_get_lease
- * @lessee_priv: the file being manipulated
- *
- * Return the list of leased objects for the specified lessee
- */
-
+/* Return the list of leased objects for the specified lessee */
 int drm_mode_get_lease_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *lessee_priv)
 {
 	struct drm_mode_get_lease *arg = data;
 	__u32 __user *object_ids = (__u32 __user *) (uintptr_t) (arg->objects_ptr);
 	__u32 count_objects = arg->count_objects;
-	struct drm_master *lessee = lessee_priv->master;
+	struct drm_master *lessee;
 	struct idr *object_idr;
 	int count;
 	void *entry;
@@ -675,6 +653,7 @@ int drm_mode_get_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessee = drm_file_get_master(lessee_priv);
 	DRM_DEBUG_LEASE("get lease for %d\n", lessee->lessee_id);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
@@ -702,16 +681,12 @@ int drm_mode_get_lease_ioctl(struct drm_device *dev,
 		arg->count_objects = count;
 
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessee);
 
 	return ret;
 }
 
-/**
- * drm_mode_revoke_lease_ioctl - revoke lease
- * @dev: the drm device
- * @data: pointer to struct drm_mode_revoke_lease
- * @lessor_priv: the file being manipulated
- *
+/*
  * This removes all of the objects from the lease without
  * actually getting rid of the lease itself; that way all
  * references to it still work correctly
@@ -720,7 +695,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 				void *data, struct drm_file *lessor_priv)
 {
 	struct drm_mode_revoke_lease *arg = data;
-	struct drm_master *lessor = lessor_priv->master;
+	struct drm_master *lessor;
 	struct drm_master *lessee;
 	int ret = 0;
 
@@ -730,6 +705,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessor = drm_file_get_master(lessor_priv);
 	mutex_lock(&dev->mode_config.idr_mutex);
 
 	lessee = _drm_find_lessee(lessor, arg->lessee_id);
@@ -750,6 +726,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 
 fail:
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessor);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_legacy_misc.c b/drivers/gpu/drm/drm_legacy_misc.c
index 83db43b7a25e..d4c5434062d7 100644
--- a/drivers/gpu/drm/drm_legacy_misc.c
+++ b/drivers/gpu/drm/drm_legacy_misc.c
@@ -35,7 +35,6 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_print.h>
 
 #include "drm_internal.h"
@@ -78,7 +77,7 @@ int drm_legacy_setup(struct drm_device * dev)
 void drm_legacy_dev_reinit(struct drm_device *dev)
 {
 	if (dev->irq_enabled)
-		drm_irq_uninstall(dev);
+		drm_legacy_irq_uninstall(dev);
 
 	mutex_lock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 43a9b739bba7..71b646c4131f 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -7,7 +7,6 @@
 
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/dma-buf.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
@@ -202,21 +201,17 @@ int mipi_dbi_buf_copy(void *dst, struct drm_framebuffer *fb,
 {
 	struct drm_gem_object *gem = drm_gem_fb_get_obj(fb, 0);
 	struct drm_gem_cma_object *cma_obj = to_drm_gem_cma_obj(gem);
-	struct dma_buf_attachment *import_attach = gem->import_attach;
 	void *src = cma_obj->vaddr;
-	int ret = 0;
+	int ret;
 
-	if (import_attach) {
-		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
-					       DMA_FROM_DEVICE);
-		if (ret)
-			return ret;
-	}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret)
+		return ret;
 
 	switch (fb->format->format) {
 	case DRM_FORMAT_RGB565:
 		if (swap)
-			drm_fb_swab(dst, src, fb, clip, !import_attach);
+			drm_fb_swab(dst, src, fb, clip, !gem->import_attach);
 		else
 			drm_fb_memcpy(dst, src, fb, clip);
 		break;
@@ -229,9 +224,8 @@ int mipi_dbi_buf_copy(void *dst, struct drm_framebuffer *fb,
 		return -EINVAL;
 	}
 
-	if (import_attach)
-		ret = dma_buf_end_cpu_access(import_attach->dmabuf,
-					     DMA_FROM_DEVICE);
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
+
 	return ret;
 }
 EXPORT_SYMBOL(mipi_dbi_buf_copy);
@@ -928,6 +922,59 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *dbi, int dc,
 	return 0;
 }
 
+static int mipi_dbi_typec1_command_read(struct mipi_dbi *dbi, u8 *cmd,
+					u8 *data, size_t len)
+{
+	struct spi_device *spi = dbi->spi;
+	u32 speed_hz = min_t(u32, MIPI_DBI_MAX_SPI_READ_SPEED,
+			     spi->max_speed_hz / 2);
+	struct spi_transfer tr[2] = {
+		{
+			.speed_hz = speed_hz,
+			.bits_per_word = 9,
+			.tx_buf = dbi->tx_buf9,
+			.len = 2,
+		}, {
+			.speed_hz = speed_hz,
+			.bits_per_word = 8,
+			.len = len,
+			.rx_buf = data,
+		},
+	};
+	struct spi_message m;
+	u16 *dst16;
+	int ret;
+
+	if (!len)
+		return -EINVAL;
+
+	if (!spi_is_bpw_supported(spi, 9)) {
+		/*
+		 * FIXME: implement something like mipi_dbi_spi1e_transfer() but
+		 * for reads using emulation.
+		 */
+		dev_err(&spi->dev,
+			"reading on host not supporting 9 bpw not yet implemented\n");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * Turn the 8bit command into a 16bit version of the command in the
+	 * buffer. Only 9 bits of this will be used when executing the actual
+	 * transfer.
+	 */
+	dst16 = dbi->tx_buf9;
+	dst16[0] = *cmd;
+
+	spi_message_init_with_transfers(&m, tr, ARRAY_SIZE(tr));
+	ret = spi_sync(spi, &m);
+
+	if (!ret)
+		MIPI_DBI_DEBUG_COMMAND(*cmd, data, len);
+
+	return ret;
+}
+
 static int mipi_dbi_typec1_command(struct mipi_dbi *dbi, u8 *cmd,
 				   u8 *parameters, size_t num)
 {
@@ -935,7 +982,7 @@ static int mipi_dbi_typec1_command(struct mipi_dbi *dbi, u8 *cmd,
 	int ret;
 
 	if (mipi_dbi_command_is_read(dbi, *cmd))
-		return -EOPNOTSUPP;
+		return mipi_dbi_typec1_command_read(dbi, cmd, parameters, num);
 
 	MIPI_DBI_DEBUG_COMMAND(*cmd, parameters, num);
 
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index a4a04d246135..93d48a6f04ab 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -700,7 +700,7 @@ EXPORT_SYMBOL(drm_mm_replace_node);
  * interfaces. First a scan operation needs to be initialized with
  * drm_mm_scan_init() or drm_mm_scan_init_with_range(). The driver adds
  * objects to the roster, probably by walking an LRU list, but this can be
- * freely implemented. Eviction candiates are added using
+ * freely implemented. Eviction candidates are added using
  * drm_mm_scan_add_block() until a suitable hole is found or there are no
  * further evictable objects. Eviction roster metadata is tracked in &struct
  * drm_mm_scan.
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index b26588b52795..86d9e907c0b2 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -91,7 +91,7 @@ void drm_mode_object_register(struct drm_device *dev,
 }
 
 /**
- * drm_mode_object_unregister - free a modeset identifer
+ * drm_mode_object_unregister - free a modeset identifier
  * @dev: DRM device
  * @object: object to free
  *
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ae53ea624c73..1c72208d8133 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1542,7 +1542,7 @@ static int drm_mode_parse_cmdline_int(const char *delim, unsigned int *int_ret)
 
 	/*
 	 * delim must point to the '=', otherwise it is a syntax error and
-	 * if delim points to the terminating zero, then delim + 1 wil point
+	 * if delim points to the terminating zero, then delim + 1 will point
 	 * past the end of the string.
 	 */
 	if (*delim != '=')
@@ -1972,7 +1972,7 @@ int drm_mode_convert_umode(struct drm_device *dev,
 	out->flags = in->flags;
 	/*
 	 * Old xf86-video-vmware (possibly others too) used to
-	 * leave 'type' unititialized. Just ignore any bits we
+	 * leave 'type' uninitialized. Just ignore any bits we
 	 * don't like. It's a just hint after all, and more
 	 * useful for the kernel->userspace direction anyway.
 	 */
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index ca04c34e8251..997b8827fed2 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -315,7 +315,7 @@ static int drm_of_lvds_get_remote_pixels_type(
 
 		remote_port = of_graph_get_remote_port(endpoint);
 		if (!remote_port) {
-			of_node_put(remote_port);
+			of_node_put(endpoint);
 			return -EPIPE;
 		}
 
@@ -331,8 +331,10 @@ static int drm_of_lvds_get_remote_pixels_type(
 		 * configurations by passing the endpoints explicitly to
 		 * drm_of_lvds_get_dual_link_pixel_order().
 		 */
-		if (!current_pt || pixels_type != current_pt)
+		if (!current_pt || pixels_type != current_pt) {
+			of_node_put(endpoint);
 			return -EINVAL;
+		}
 	}
 
 	return pixels_type;
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index b373958ecb30..82afb854141b 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -38,7 +38,7 @@
 /**
  * DOC: overview
  *
- * A plane represents an image source that can be blended with or overlayed on
+ * A plane represents an image source that can be blended with or overlaid on
  * top of a CRTC during the scanout process. Planes take their input data from a
  * &drm_framebuffer object. The plane itself specifies the cropping and scaling
  * of that image, and where it is placed on the visible area of a display
@@ -1397,6 +1397,110 @@ out:
 	return ret;
 }
 
+/**
+ * DOC: damage tracking
+ *
+ * FB_DAMAGE_CLIPS is an optional plane property which provides a means to
+ * specify a list of damage rectangles on a plane in framebuffer coordinates of
+ * the framebuffer attached to the plane. In current context damage is the area
+ * of plane framebuffer that has changed since last plane update (also called
+ * page-flip), irrespective of whether currently attached framebuffer is same as
+ * framebuffer attached during last plane update or not.
+ *
+ * FB_DAMAGE_CLIPS is a hint to kernel which could be helpful for some drivers
+ * to optimize internally especially for virtual devices where each framebuffer
+ * change needs to be transmitted over network, usb, etc.
+ *
+ * Since FB_DAMAGE_CLIPS is a hint so it is an optional property. User-space can
+ * ignore damage clips property and in that case driver will do a full plane
+ * update. In case damage clips are provided then it is guaranteed that the area
+ * inside damage clips will be updated to plane. For efficiency driver can do
+ * full update or can update more than specified in damage clips. Since driver
+ * is free to read more, user-space must always render the entire visible
+ * framebuffer. Otherwise there can be corruptions. Also, if a user-space
+ * provides damage clips which doesn't encompass the actual damage to
+ * framebuffer (since last plane update) can result in incorrect rendering.
+ *
+ * FB_DAMAGE_CLIPS is a blob property with the layout of blob data is simply an
+ * array of &drm_mode_rect. Unlike plane &drm_plane_state.src coordinates,
+ * damage clips are not in 16.16 fixed point. Similar to plane src in
+ * framebuffer, damage clips cannot be negative. In damage clip, x1/y1 are
+ * inclusive and x2/y2 are exclusive. While kernel does not error for overlapped
+ * damage clips, it is strongly discouraged.
+ *
+ * Drivers that are interested in damage interface for plane should enable
+ * FB_DAMAGE_CLIPS property by calling drm_plane_enable_fb_damage_clips().
+ * Drivers implementing damage can use drm_atomic_helper_damage_iter_init() and
+ * drm_atomic_helper_damage_iter_next() helper iterator function to get damage
+ * rectangles clipped to &drm_plane_state.src.
+ */
+
+/**
+ * drm_plane_enable_fb_damage_clips - Enables plane fb damage clips property.
+ * @plane: Plane on which to enable damage clips property.
+ *
+ * This function lets driver to enable the damage clips property on a plane.
+ */
+void drm_plane_enable_fb_damage_clips(struct drm_plane *plane)
+{
+	struct drm_device *dev = plane->dev;
+	struct drm_mode_config *config = &dev->mode_config;
+
+	drm_object_attach_property(&plane->base, config->prop_fb_damage_clips,
+				   0);
+}
+EXPORT_SYMBOL(drm_plane_enable_fb_damage_clips);
+
+/**
+ * drm_plane_get_damage_clips_count - Returns damage clips count.
+ * @state: Plane state.
+ *
+ * Simple helper to get the number of &drm_mode_rect clips set by user-space
+ * during plane update.
+ *
+ * Return: Number of clips in plane fb_damage_clips blob property.
+ */
+unsigned int
+drm_plane_get_damage_clips_count(const struct drm_plane_state *state)
+{
+	return (state && state->fb_damage_clips) ?
+		state->fb_damage_clips->length/sizeof(struct drm_mode_rect) : 0;
+}
+EXPORT_SYMBOL(drm_plane_get_damage_clips_count);
+
+struct drm_mode_rect *
+__drm_plane_get_damage_clips(const struct drm_plane_state *state)
+{
+	return (struct drm_mode_rect *)((state && state->fb_damage_clips) ?
+					state->fb_damage_clips->data : NULL);
+}
+
+/**
+ * drm_plane_get_damage_clips - Returns damage clips.
+ * @state: Plane state.
+ *
+ * Note that this function returns uapi type &drm_mode_rect. Drivers might want
+ * to use the helper functions drm_atomic_helper_damage_iter_init() and
+ * drm_atomic_helper_damage_iter_next() or drm_atomic_helper_damage_merged() if
+ * the driver can only handle a single damage region at most.
+ *
+ * Return: Damage clips in plane fb_damage_clips blob property.
+ */
+struct drm_mode_rect *
+drm_plane_get_damage_clips(const struct drm_plane_state *state)
+{
+	struct drm_device *dev = state->plane->dev;
+	struct drm_mode_config *config = &dev->mode_config;
+
+	/* check that drm_plane_enable_fb_damage_clips() was called */
+	if (!drm_mode_obj_find_prop_id(&state->plane->base,
+				       config->prop_fb_damage_clips->base.id))
+		drm_warn_once(dev, "drm_plane_enable_fb_damage_clips() not called\n");
+
+	return __drm_plane_get_damage_clips(state);
+}
+EXPORT_SYMBOL(drm_plane_get_damage_clips);
+
 struct drm_property *
 drm_create_scaling_filter_prop(struct drm_device *dev,
 			       unsigned int supported_filters)
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 3aae7ea522f2..5b2d0ca03705 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -210,7 +210,7 @@ static int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *c
 	 * We call set_config() directly here rather than using
 	 * drm_mode_set_config_internal.  We're reprogramming the same
 	 * connectors that were already in use, so we shouldn't need the extra
-	 * cross-CRTC fb refcounting to accomodate stealing connectors.
+	 * cross-CRTC fb refcounting to accommodate stealing connectors.
 	 * drm_mode_setplane() already handles the basic refcounting for the
 	 * framebuffers involved in this operation.
 	 */
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 2a54f86856af..1d009494af8b 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -73,7 +73,7 @@
  * Thus the chain of references always flows in one direction, avoiding loops:
  * importing GEM object -> dma-buf -> exported GEM bo. A further complication
  * are the lookup caches for import and export. These are required to guarantee
- * that any given object will always have only one uniqe userspace handle. This
+ * that any given object will always have only one unique userspace handle. This
  * is required to allow userspace to detect duplicated imports, since some GEM
  * drivers do fail command submissions if a given buffer object is listed more
  * than once. These import and export caches in &drm_prime_file_private only
@@ -549,7 +549,7 @@ int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
  *
  * FIXME: The underlying helper functions are named rather inconsistently.
  *
- * Exporting buffers
+ * Importing buffers
  * ~~~~~~~~~~~~~~~~~
  *
  * Importing dma-bufs using drm_gem_prime_import() relies on
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index e7e1ee2aa352..5606bca3caa8 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -757,7 +757,7 @@ EXPORT_SYMBOL(drm_kms_helper_poll_disable);
  * drm_kms_helper_poll_init - initialize and enable output polling
  * @dev: drm_device
  *
- * This function intializes and then also enables output polling support for
+ * This function initializes and then also enables output polling support for
  * @dev. Drivers which do not have reliable hotplug support in hardware can use
  * this helper infrastructure to regularly poll such connectors for changes in
  * their connection state.
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index 27c824a6eb60..6c353c9dc772 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -434,7 +434,7 @@ EXPORT_SYMBOL(drm_property_add_enum);
 /**
  * drm_property_destroy - destroy a drm property
  * @dev: drm device
- * @property: property to destry
+ * @property: property to destroy
  *
  * This function frees a property including any attached resources like
  * enumeration values.
diff --git a/drivers/gpu/drm/drm_scdc_helper.c b/drivers/gpu/drm/drm_scdc_helper.c
index 991b8c86d78d..48a382464d54 100644
--- a/drivers/gpu/drm/drm_scdc_helper.c
+++ b/drivers/gpu/drm/drm_scdc_helper.c
@@ -241,7 +241,7 @@ bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set)
 	/*
 	 * The spec says that a source should wait minimum 1ms and maximum
 	 * 100ms after writing the TMDS config for clock ratio. Lets allow a
-	 * wait of upto 2ms here.
+	 * wait of up to 2ms here.
 	 */
 	usleep_range(1000, 2000);
 	return true;
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 0b095a313c44..72989ed1baba 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -9,6 +9,8 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -143,6 +145,39 @@ static const struct drm_crtc_helper_funcs drm_simple_kms_crtc_helper_funcs = {
 	.atomic_disable = drm_simple_kms_crtc_disable,
 };
 
+static void drm_simple_kms_crtc_reset(struct drm_crtc *crtc)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
+	if (!pipe->funcs || !pipe->funcs->reset_crtc)
+		return drm_atomic_helper_crtc_reset(crtc);
+
+	return pipe->funcs->reset_crtc(pipe);
+}
+
+static struct drm_crtc_state *drm_simple_kms_crtc_duplicate_state(struct drm_crtc *crtc)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
+	if (!pipe->funcs || !pipe->funcs->duplicate_crtc_state)
+		return drm_atomic_helper_crtc_duplicate_state(crtc);
+
+	return pipe->funcs->duplicate_crtc_state(pipe);
+}
+
+static void drm_simple_kms_crtc_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *state)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
+	if (!pipe->funcs || !pipe->funcs->destroy_crtc_state)
+		drm_atomic_helper_crtc_destroy_state(crtc, state);
+	else
+		pipe->funcs->destroy_crtc_state(pipe, state);
+}
+
 static int drm_simple_kms_crtc_enable_vblank(struct drm_crtc *crtc)
 {
 	struct drm_simple_display_pipe *pipe;
@@ -166,12 +201,12 @@ static void drm_simple_kms_crtc_disable_vblank(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_funcs drm_simple_kms_crtc_funcs = {
-	.reset = drm_atomic_helper_crtc_reset,
+	.reset = drm_simple_kms_crtc_reset,
 	.destroy = drm_crtc_cleanup,
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
-	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+	.atomic_duplicate_state = drm_simple_kms_crtc_duplicate_state,
+	.atomic_destroy_state = drm_simple_kms_crtc_destroy_state,
 	.enable_vblank = drm_simple_kms_crtc_enable_vblank,
 	.disable_vblank = drm_simple_kms_crtc_disable_vblank,
 };
@@ -225,8 +260,14 @@ static int drm_simple_kms_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_simple_display_pipe *pipe;
 
 	pipe = container_of(plane, struct drm_simple_display_pipe, plane);
-	if (!pipe->funcs || !pipe->funcs->prepare_fb)
-		return 0;
+	if (!pipe->funcs || !pipe->funcs->prepare_fb) {
+		if (WARN_ON_ONCE(!drm_core_check_feature(plane->dev, DRIVER_GEM)))
+			return 0;
+
+		WARN_ON_ONCE(pipe->funcs && pipe->funcs->cleanup_fb);
+
+		return drm_gem_simple_display_pipe_prepare_fb(pipe, state);
+	}
 
 	return pipe->funcs->prepare_fb(pipe, state);
 }
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index fdd2ec87cdd1..c9a9d74f338c 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -725,7 +725,7 @@ err_put_fd:
 	return ret;
 }
 /**
- * drm_syncobj_open - initalizes syncobj file-private structures at devnode open time
+ * drm_syncobj_open - initializes syncobj file-private structures at devnode open time
  * @file_private: drm file-private structure to set up
  *
  * Called at device open time, sets up the structure for handling refcounting
@@ -861,7 +861,7 @@ static int drm_syncobj_transfer_to_timeline(struct drm_file *file_private,
 				     &fence);
 	if (ret)
 		goto err;
-	chain = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL);
+	chain = dma_fence_chain_alloc();
 	if (!chain) {
 		ret = -ENOMEM;
 		goto err1;
@@ -1402,10 +1402,10 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 		goto err_points;
 	}
 	for (i = 0; i < args->count_handles; i++) {
-		chains[i] = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL);
+		chains[i] = dma_fence_chain_alloc();
 		if (!chains[i]) {
 			for (j = 0; j < i; j++)
-				kfree(chains[j]);
+				dma_fence_chain_free(chains[j]);
 			ret = -ENOMEM;
 			goto err_chains;
 		}
diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index 3417e1ac7918..b701cda86d0c 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -191,7 +191,7 @@ static u32 drm_max_vblank_count(struct drm_device *dev, unsigned int pipe)
 
 /*
  * "No hw counter" fallback implementation of .get_vblank_counter() hook,
- * if there is no useable hardware frame counter available.
+ * if there is no usable hardware frame counter available.
  */
 static u32 drm_vblank_no_hw_counter(struct drm_device *dev, unsigned int pipe)
 {
@@ -905,7 +905,7 @@ drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe,
  * and drm_crtc_vblank_count() or drm_crtc_vblank_count_and_time()
  * provide a barrier: Any writes done before calling
  * drm_crtc_handle_vblank() will be visible to callers of the later
- * functions, iff the vblank count is the same or a later one.
+ * functions, if the vblank count is the same or a later one.
  *
  * See also &drm_vblank_crtc.count.
  *
@@ -968,7 +968,7 @@ static u64 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe,
  * and drm_crtc_vblank_count() or drm_crtc_vblank_count_and_time()
  * provide a barrier: Any writes done before calling
  * drm_crtc_handle_vblank() will be visible to callers of the later
- * functions, iff the vblank count is the same or a later one.
+ * functions, if the vblank count is the same or a later one.
  *
  * See also &drm_vblank_crtc.count.
  */
@@ -1737,6 +1737,15 @@ static void drm_wait_vblank_reply(struct drm_device *dev, unsigned int pipe,
 	reply->tval_usec = ts.tv_nsec / 1000;
 }
 
+static bool drm_wait_vblank_supported(struct drm_device *dev)
+{
+#if IS_ENABLED(CONFIG_DRM_LEGACY)
+	if (unlikely(drm_core_check_feature(dev, DRIVER_LEGACY)))
+		return dev->irq_enabled;
+#endif
+	return drm_dev_has_vblank(dev);
+}
+
 int drm_wait_vblank_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv)
 {
@@ -1748,7 +1757,7 @@ int drm_wait_vblank_ioctl(struct drm_device *dev, void *data,
 	unsigned int pipe_index;
 	unsigned int flags, pipe, high_pipe;
 
-	if (!dev->irq_enabled)
+	if (!drm_wait_vblank_supported(dev))
 		return -EOPNOTSUPP;
 
 	if (vblwait->request.type & _DRM_VBLANK_SIGNAL)
@@ -1988,7 +1997,7 @@ EXPORT_SYMBOL(drm_handle_vblank);
  * and drm_crtc_vblank_count() or drm_crtc_vblank_count_and_time()
  * provide a barrier: Any writes done before calling
  * drm_crtc_handle_vblank() will be visible to callers of the later
- * functions, iff the vblank count is the same or a later one.
+ * functions, if the vblank count is the same or a later one.
  *
  * See also &drm_vblank_crtc.count.
  *
@@ -2005,7 +2014,7 @@ EXPORT_SYMBOL(drm_crtc_handle_vblank);
  * Get crtc VBLANK count.
  *
  * \param dev DRM device
- * \param data user arguement, pointing to a drm_crtc_get_sequence structure.
+ * \param data user argument, pointing to a drm_crtc_get_sequence structure.
  * \param file_priv drm file private for the user's open file descriptor
  */
 
@@ -2023,7 +2032,7 @@ int drm_crtc_get_sequence_ioctl(struct drm_device *dev, void *data,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
-	if (!dev->irq_enabled)
+	if (!drm_dev_has_vblank(dev))
 		return -EOPNOTSUPP;
 
 	crtc = drm_crtc_find(dev, file_priv, get_seq->crtc_id);
@@ -2061,7 +2070,7 @@ int drm_crtc_get_sequence_ioctl(struct drm_device *dev, void *data,
  * Queue a event for VBLANK sequence
  *
  * \param dev DRM device
- * \param data user arguement, pointing to a drm_crtc_queue_sequence structure.
+ * \param data user argument, pointing to a drm_crtc_queue_sequence structure.
  * \param file_priv drm file private for the user's open file descriptor
  */
 
@@ -2082,7 +2091,7 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
-	if (!dev->irq_enabled)
+	if (!drm_dev_has_vblank(dev))
 		return -EOPNOTSUPP;
 
 	crtc = drm_crtc_find(dev, file_priv, queue_seq->crtc_id);
diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 4565319fa6b3..7de37f8c68fd 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -361,7 +361,7 @@ EXPORT_SYMBOL(drm_vma_node_revoke);
  * This is locked against concurrent access internally.
  *
  * RETURNS:
- * true iff @filp is on the list
+ * true if @filp is on the list
  */
 bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node,
 			     struct drm_file *tag)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index f0a07278ad04..7dcc6392792d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -468,17 +468,7 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = {
 	ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW),
 };
 
-static const struct file_operations fops = {
-	.owner              = THIS_MODULE,
-	.open               = drm_open,
-	.release            = drm_release,
-	.unlocked_ioctl     = drm_ioctl,
-	.compat_ioctl       = drm_compat_ioctl,
-	.poll               = drm_poll,
-	.read               = drm_read,
-	.llseek             = no_llseek,
-	.mmap               = etnaviv_gem_mmap,
-};
+DEFINE_DRM_GEM_FOPS(fops);
 
 static const struct drm_driver etnaviv_drm_driver = {
 	.driver_features    = DRIVER_GEM | DRIVER_RENDER,
@@ -487,7 +477,7 @@ static const struct drm_driver etnaviv_drm_driver = {
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import_sg_table = etnaviv_gem_prime_import_sg_table,
-	.gem_prime_mmap     = etnaviv_gem_prime_mmap,
+	.gem_prime_mmap     = drm_gem_prime_mmap,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = etnaviv_debugfs_init,
 #endif
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
index 003288ebd896..049ae87de9be 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
@@ -47,12 +47,9 @@ struct etnaviv_drm_private {
 int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
 
-int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset);
 struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj);
 int etnaviv_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map);
-int etnaviv_gem_prime_mmap(struct drm_gem_object *obj,
-			   struct vm_area_struct *vma);
 struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev,
 	struct dma_buf_attachment *attach, struct sg_table *sg);
 int etnaviv_gem_prime_pin(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index b8fa6ed3dd73..8f1b5af47dd6 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -130,8 +130,7 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 {
 	pgprot_t vm_page_prot;
 
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 
 	vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
@@ -154,19 +153,11 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 	return 0;
 }
 
-int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+static int etnaviv_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 {
-	struct etnaviv_gem_object *obj;
-	int ret;
-
-	ret = drm_gem_mmap(filp, vma);
-	if (ret) {
-		DBG("mmap failed: %d", ret);
-		return ret;
-	}
+	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
 
-	obj = to_etnaviv_bo(vma->vm_private_data);
-	return obj->ops->mmap(obj, vma);
+	return etnaviv_obj->ops->mmap(etnaviv_obj, vma);
 }
 
 static vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf)
@@ -567,6 +558,7 @@ static const struct drm_gem_object_funcs etnaviv_gem_object_funcs = {
 	.unpin = etnaviv_gem_prime_unpin,
 	.get_sg_table = etnaviv_gem_prime_get_sg_table,
 	.vmap = etnaviv_gem_prime_vmap,
+	.mmap = etnaviv_gem_mmap,
 	.vm_ops = &vm_ops,
 };
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index d741b1d735f7..6d8bed9c739d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -34,19 +34,6 @@ int etnaviv_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map)
 	return 0;
 }
 
-int etnaviv_gem_prime_mmap(struct drm_gem_object *obj,
-			   struct vm_area_struct *vma)
-{
-	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
-	int ret;
-
-	ret = drm_gem_mmap_obj(obj, obj->size, vma);
-	if (ret < 0)
-		return ret;
-
-	return etnaviv_obj->ops->mmap(etnaviv_obj, vma);
-}
-
 int etnaviv_gem_prime_pin(struct drm_gem_object *obj)
 {
 	if (!obj->import_attach) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 4102bcea3341..c297fffe06eb 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -613,6 +613,12 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu)
 	    etnaviv_is_model_rev(gpu, GC2000, 0x5108))
 		pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX;
 
+	/* Disable SE, RA and TX clock gating on affected core revisions. */
+	if (etnaviv_is_model_rev(gpu, GC7000, 0x6202))
+		pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SE |
+		       VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA |
+		       VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX;
+
 	pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ;
 	pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
index dfc0f536b3b9..f2fc645c7956 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
@@ -39,6 +39,37 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 	},
 	{
 		.model = 0x7000,
+		.revision = 0x6202,
+		.product_id = 0x70003,
+		.customer_id = 0,
+		.eco_id = 0,
+		.stream_count = 8,
+		.register_max = 64,
+		.thread_count = 512,
+		.shader_core_count = 2,
+		.vertex_cache_size = 16,
+		.vertex_output_buffer_size = 1024,
+		.pixel_pipes = 1,
+		.instruction_count = 512,
+		.num_constants = 320,
+		.buffer_size = 0,
+		.varyings_count = 16,
+		.features = 0xe0287cad,
+		.minor_features0 = 0xc1489eff,
+		.minor_features1 = 0xfefbfad9,
+		.minor_features2 = 0xeb9d4fbf,
+		.minor_features3 = 0xedfffced,
+		.minor_features4 = 0xdb0dafc7,
+		.minor_features5 = 0x3b5ac333,
+		.minor_features6 = 0xfccee201,
+		.minor_features7 = 0x03fffa6f,
+		.minor_features8 = 0x00e10ef0,
+		.minor_features9 = 0x0088003c,
+		.minor_features10 = 0x00004040,
+		.minor_features11 = 0x00000024,
+	},
+	{
+		.model = 0x7000,
 		.revision = 0x6204,
 		.product_id = ~0U,
 		.customer_id = ~0U,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 19826e504efc..feb6da1b6ceb 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -190,7 +190,8 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
 
 	ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops,
 			     etnaviv_hw_jobs_limit, etnaviv_job_hang_limit,
-			     msecs_to_jiffies(500), NULL, dev_name(gpu->dev));
+			     msecs_to_jiffies(500), NULL, NULL,
+			     dev_name(gpu->dev));
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 9ac51b6ab34b..27664f663c5a 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -109,11 +109,8 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
 	if (dp->ptn_bridge) {
 		ret = drm_bridge_attach(&dp->encoder, dp->ptn_bridge, bridge,
 					0);
-		if (ret) {
-			DRM_DEV_ERROR(dp->dev,
-				      "Failed to attach bridge to drm\n");
+		if (ret)
 			return ret;
-		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 0644936afee2..bf33c3084cb4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -115,6 +115,8 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
 				EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE);
 		else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 			mapping = iommu_get_domain_for_dev(priv->dma_dev);
+		else
+			mapping = ERR_PTR(-ENODEV);
 
 		if (IS_ERR(mapping))
 			return PTR_ERR(mapping);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index e60257f1f24b..d8f1cf4d6b69 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -300,16 +300,6 @@ static int exynos_drm_bind(struct device *dev)
 
 	drm_mode_config_reset(drm);
 
-	/*
-	 * enable drm irq mode.
-	 * - with irq_enabled = true, we can use the vblank feature.
-	 *
-	 * P.S. note that we wouldn't use drm irq handler but
-	 *	just specific driver own one instead because
-	 *	drm framework supports only one irq handler.
-	 */
-	drm->irq_enabled = true;
-
 	/* init kms poll for handling hpd */
 	drm_kms_helper_poll_init(drm);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 1d777d8c1a83..e39fac889edc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -809,15 +809,15 @@ static int exynos_dsi_init_link(struct exynos_dsi *dsi)
 			reg |= DSIM_AUTO_MODE;
 		if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_HSE)
 			reg |= DSIM_HSE_MODE;
-		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_HFP))
+		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_NO_HFP))
 			reg |= DSIM_HFP_MODE;
-		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_HBP))
+		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_NO_HBP))
 			reg |= DSIM_HBP_MODE;
-		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_HSA))
+		if (!(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_NO_HSA))
 			reg |= DSIM_HSA_MODE;
 	}
 
-	if (!(dsi->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		reg |= DSIM_EOT_DISABLE;
 
 	switch (dsi->format) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index cab4d2c370a7..b00230626c6a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -4,6 +4,7 @@
  * Authors: Joonyoung Shim <jy0922.shim@samsung.com>
  */
 
+#include <linux/refcount.h>
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <linux/delay.h>
@@ -208,7 +209,7 @@ struct g2d_cmdlist_userptr {
 	struct page		**pages;
 	unsigned int		npages;
 	struct sg_table		*sgt;
-	atomic_t		refcount;
+	refcount_t		refcount;
 	bool			in_pool;
 	bool			out_of_list;
 };
@@ -386,9 +387,9 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
 	if (force)
 		goto out;
 
-	atomic_dec(&g2d_userptr->refcount);
+	refcount_dec(&g2d_userptr->refcount);
 
-	if (atomic_read(&g2d_userptr->refcount) > 0)
+	if (refcount_read(&g2d_userptr->refcount) > 0)
 		return;
 
 	if (g2d_userptr->in_pool)
@@ -436,7 +437,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 			 * and different size.
 			 */
 			if (g2d_userptr->size == size) {
-				atomic_inc(&g2d_userptr->refcount);
+				refcount_inc(&g2d_userptr->refcount);
 				*obj = g2d_userptr;
 
 				return &g2d_userptr->dma_addr;
@@ -461,7 +462,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 	if (!g2d_userptr)
 		return ERR_PTR(-ENOMEM);
 
-	atomic_set(&g2d_userptr->refcount, 1);
+	refcount_set(&g2d_userptr->refcount, 1);
 	g2d_userptr->size = size;
 
 	start = userptr & PAGE_MASK;
@@ -897,13 +898,14 @@ static void g2d_runqueue_worker(struct work_struct *work)
 			ret = pm_runtime_resume_and_get(g2d->dev);
 			if (ret < 0) {
 				dev_err(g2d->dev, "failed to enable G2D device.\n");
-				return;
+				goto out;
 			}
 
 			g2d_dma_start(g2d, g2d->runqueue_node);
 		}
 	}
 
+out:
 	mutex_unlock(&g2d->runqueue_mutex);
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index f893731d6021..c769dec576de 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -970,11 +970,8 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
 	drm_connector_attach_encoder(connector, encoder);
 
-	if (hdata->bridge) {
+	if (hdata->bridge)
 		ret = drm_bridge_attach(encoder, hdata->bridge, NULL, 0);
-		if (ret)
-			DRM_DEV_ERROR(hdata->dev, "Failed to attach bridge\n");
-	}
 
 	cec_fill_conn_info_from_drm(&conn_info, connector);
 
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 7528e8a2d359..660fe573db96 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -23,7 +23,6 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_modeset_helper.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -51,7 +50,7 @@ static const struct regmap_config fsl_dcu_regmap_config = {
 	.volatile_reg = fsl_dcu_drm_is_volatile_reg,
 };
 
-static void fsl_dcu_irq_uninstall(struct drm_device *dev)
+static void fsl_dcu_irq_reset(struct drm_device *dev)
 {
 	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
 
@@ -59,6 +58,45 @@ static void fsl_dcu_irq_uninstall(struct drm_device *dev)
 	regmap_write(fsl_dev->regmap, DCU_INT_MASK, ~0);
 }
 
+static irqreturn_t fsl_dcu_drm_irq(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
+	unsigned int int_status;
+	int ret;
+
+	ret = regmap_read(fsl_dev->regmap, DCU_INT_STATUS, &int_status);
+	if (ret) {
+		dev_err(dev->dev, "read DCU_INT_STATUS failed\n");
+		return IRQ_NONE;
+	}
+
+	if (int_status & DCU_INT_STATUS_VBLANK)
+		drm_handle_vblank(dev, 0);
+
+	regmap_write(fsl_dev->regmap, DCU_INT_STATUS, int_status);
+
+	return IRQ_HANDLED;
+}
+
+static int fsl_dcu_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	fsl_dcu_irq_reset(dev);
+
+	return request_irq(irq, fsl_dcu_drm_irq, 0, dev->driver->name, dev);
+}
+
+static void fsl_dcu_irq_uninstall(struct drm_device *dev)
+{
+	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
+
+	fsl_dcu_irq_reset(dev);
+	free_irq(fsl_dev->irq, dev);
+}
+
 static int fsl_dcu_load(struct drm_device *dev, unsigned long flags)
 {
 	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
@@ -73,13 +111,13 @@ static int fsl_dcu_load(struct drm_device *dev, unsigned long flags)
 	ret = drm_vblank_init(dev, dev->mode_config.num_crtc);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
-		goto done;
+		goto done_vblank;
 	}
 
-	ret = drm_irq_install(dev, fsl_dev->irq);
+	ret = fsl_dcu_irq_install(dev, fsl_dev->irq);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
-		goto done;
+		goto done_irq;
 	}
 
 	if (legacyfb_depth != 16 && legacyfb_depth != 24 &&
@@ -90,11 +128,11 @@ static int fsl_dcu_load(struct drm_device *dev, unsigned long flags)
 	}
 
 	return 0;
-done:
+done_irq:
 	drm_kms_helper_poll_fini(dev);
 
 	drm_mode_config_cleanup(dev);
-	drm_irq_uninstall(dev);
+done_vblank:
 	dev->dev_private = NULL;
 
 	return ret;
@@ -106,41 +144,17 @@ static void fsl_dcu_unload(struct drm_device *dev)
 	drm_kms_helper_poll_fini(dev);
 
 	drm_mode_config_cleanup(dev);
-	drm_irq_uninstall(dev);
+	fsl_dcu_irq_uninstall(dev);
 
 	dev->dev_private = NULL;
 }
 
-static irqreturn_t fsl_dcu_drm_irq(int irq, void *arg)
-{
-	struct drm_device *dev = arg;
-	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
-	unsigned int int_status;
-	int ret;
-
-	ret = regmap_read(fsl_dev->regmap, DCU_INT_STATUS, &int_status);
-	if (ret) {
-		dev_err(dev->dev, "read DCU_INT_STATUS failed\n");
-		return IRQ_NONE;
-	}
-
-	if (int_status & DCU_INT_STATUS_VBLANK)
-		drm_handle_vblank(dev, 0);
-
-	regmap_write(fsl_dev->regmap, DCU_INT_STATUS, int_status);
-
-	return IRQ_HANDLED;
-}
-
 DEFINE_DRM_GEM_CMA_FOPS(fsl_dcu_drm_fops);
 
 static const struct drm_driver fsl_dcu_drm_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
 	.load			= fsl_dcu_load,
 	.unload			= fsl_dcu_unload,
-	.irq_handler		= fsl_dcu_drm_irq,
-	.irq_preinstall		= fsl_dcu_irq_uninstall,
-	.irq_uninstall		= fsl_dcu_irq_uninstall,
 	DRM_GEM_CMA_DRIVER_OPS,
 	.fops			= &fsl_dcu_drm_fops,
 	.name			= "fsl-dcu-drm",
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 432bdcc57ac9..f9b1f88c73bd 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -113,11 +113,11 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder,
 
 	/* Find the connector we're trying to set up */
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
-		if (!connector->encoder || connector->encoder->crtc != crtc)
-			continue;
+		if (connector->encoder && connector->encoder->crtc == crtc)
+			break;
 	}
 
-	if (!connector) {
+	if (list_entry_is_head(connector, &mode_config->connector_list, head)) {
 		DRM_ERROR("Couldn't find connector when setting mode");
 		gma_power_end(dev);
 		return;
diff --git a/drivers/gpu/drm/gma500/power.c b/drivers/gpu/drm/gma500/power.c
index f07641dfa5a4..20ace6010f9f 100644
--- a/drivers/gpu/drm/gma500/power.c
+++ b/drivers/gpu/drm/gma500/power.c
@@ -32,6 +32,7 @@
 #include "psb_drv.h"
 #include "psb_reg.h"
 #include "psb_intel_reg.h"
+#include "psb_irq.h"
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 3850842d58f3..58bce1a60a4d 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -23,7 +23,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_pciids.h>
 #include <drm/drm_vblank.h>
 
@@ -33,6 +32,7 @@
 #include "power.h"
 #include "psb_drv.h"
 #include "psb_intel_reg.h"
+#include "psb_irq.h"
 #include "psb_reg.h"
 
 static const struct drm_driver driver;
@@ -380,7 +380,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags)
 	PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R);
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 
-	drm_irq_install(dev, pdev->irq);
+	psb_irq_install(dev, pdev->irq);
 
 	dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
 
@@ -515,10 +515,6 @@ static const struct drm_driver driver = {
 	.lastclose = drm_fb_helper_lastclose,
 
 	.num_ioctls = ARRAY_SIZE(psb_ioctls),
-	.irq_preinstall = psb_irq_preinstall,
-	.irq_postinstall = psb_irq_postinstall,
-	.irq_uninstall = psb_irq_uninstall,
-	.irq_handler = psb_irq_handler,
 
 	.dumb_create = psb_gem_dumb_create,
 	.ioctls = psb_ioctls,
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index d6e7c2c2c947..f2bae270ca7b 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -624,11 +624,6 @@ static inline struct drm_psb_private *psb_priv(struct drm_device *dev)
 }
 
 /* psb_irq.c */
-extern irqreturn_t psb_irq_handler(int irq, void *arg);
-extern void psb_irq_preinstall(struct drm_device *dev);
-extern int psb_irq_postinstall(struct drm_device *dev);
-extern void psb_irq_uninstall(struct drm_device *dev);
-
 extern void psb_irq_uninstall_islands(struct drm_device *dev, int hw_islands);
 extern int psb_vblank_wait2(struct drm_device *dev, unsigned int *sequence);
 extern int psb_vblank_wait(struct drm_device *dev, unsigned int *sequence);
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index 104009e78487..deb1fbc1f748 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -8,6 +8,7 @@
  *
  **************************************************************************/
 
+#include <drm/drm_drv.h>
 #include <drm/drm_vblank.h>
 
 #include "power.h"
@@ -222,7 +223,7 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2)
 	PSB_RSGX32(PSB_CR_EVENT_HOST_CLEAR2);
 }
 
-irqreturn_t psb_irq_handler(int irq, void *arg)
+static irqreturn_t psb_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
 	struct drm_psb_private *dev_priv = dev->dev_private;
@@ -304,7 +305,7 @@ void psb_irq_preinstall(struct drm_device *dev)
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 }
 
-int psb_irq_postinstall(struct drm_device *dev)
+void psb_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
@@ -332,12 +333,31 @@ int psb_irq_postinstall(struct drm_device *dev)
 		dev_priv->ops->hotplug_enable(dev, true);
 
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
+}
+
+int psb_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	psb_irq_preinstall(dev);
+
+	/* PCI devices require shared interrupts. */
+	ret = request_irq(irq, psb_irq_handler, IRQF_SHARED, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	psb_irq_postinstall(dev);
+
 	return 0;
 }
 
 void psb_irq_uninstall(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	unsigned long irqflags;
 	unsigned int i;
 
@@ -366,6 +386,8 @@ void psb_irq_uninstall(struct drm_device *dev)
 	/* This register is safe even if display island is off */
 	PSB_WVDC32(PSB_RVDC32(PSB_INT_IDENTITY_R), PSB_INT_IDENTITY_R);
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
+
+	free_irq(pdev->irq, dev);
 }
 
 /*
diff --git a/drivers/gpu/drm/gma500/psb_irq.h b/drivers/gpu/drm/gma500/psb_irq.h
index 17c9b0b62471..a97cb49393d8 100644
--- a/drivers/gpu/drm/gma500/psb_irq.h
+++ b/drivers/gpu/drm/gma500/psb_irq.h
@@ -19,9 +19,9 @@ bool sysirq_init(struct drm_device *dev);
 void sysirq_uninit(struct drm_device *dev);
 
 void psb_irq_preinstall(struct drm_device *dev);
-int  psb_irq_postinstall(struct drm_device *dev);
+void psb_irq_postinstall(struct drm_device *dev);
+int  psb_irq_install(struct drm_device *dev, unsigned int irq);
 void psb_irq_uninstall(struct drm_device *dev);
-irqreturn_t psb_irq_handler(int irq, void *arg);
 
 int  psb_enable_vblank(struct drm_crtc *crtc);
 void psb_disable_vblank(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c
index e8b672dc9832..eb4e08846da4 100644
--- a/drivers/gpu/drm/gud/gud_drv.c
+++ b/drivers/gpu/drm/gud/gud_drv.c
@@ -364,7 +364,6 @@ static void gud_debugfs_init(struct drm_minor *minor)
 static const struct drm_simple_display_pipe_funcs gud_pipe_funcs = {
 	.check      = gud_pipe_check,
 	.update	    = gud_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_mode_config_funcs gud_mode_config_funcs = {
@@ -394,14 +393,42 @@ static const struct drm_driver gud_drm_driver = {
 	.minor			= 0,
 };
 
-static void gud_free_buffers_and_mutex(struct drm_device *drm, void *unused)
+static int gud_alloc_bulk_buffer(struct gud_device *gdrm)
 {
-	struct gud_device *gdrm = to_gud_device(drm);
+	unsigned int i, num_pages;
+	struct page **pages;
+	void *ptr;
+	int ret;
+
+	gdrm->bulk_buf = vmalloc_32(gdrm->bulk_len);
+	if (!gdrm->bulk_buf)
+		return -ENOMEM;
+
+	num_pages = DIV_ROUND_UP(gdrm->bulk_len, PAGE_SIZE);
+	pages = kmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	for (i = 0, ptr = gdrm->bulk_buf; i < num_pages; i++, ptr += PAGE_SIZE)
+		pages[i] = vmalloc_to_page(ptr);
+
+	ret = sg_alloc_table_from_pages(&gdrm->bulk_sgt, pages, num_pages,
+					0, gdrm->bulk_len, GFP_KERNEL);
+	kfree(pages);
+
+	return ret;
+}
+
+static void gud_free_buffers_and_mutex(void *data)
+{
+	struct gud_device *gdrm = data;
 
 	vfree(gdrm->compress_buf);
-	kfree(gdrm->bulk_buf);
+	gdrm->compress_buf = NULL;
+	sg_free_table(&gdrm->bulk_sgt);
+	vfree(gdrm->bulk_buf);
+	gdrm->bulk_buf = NULL;
 	mutex_destroy(&gdrm->ctrl_lock);
-	mutex_destroy(&gdrm->damage_lock);
 }
 
 static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id)
@@ -455,7 +482,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	INIT_WORK(&gdrm->work, gud_flush_work);
 	gud_clear_damage(gdrm);
 
-	ret = drmm_add_action_or_reset(drm, gud_free_buffers_and_mutex, NULL);
+	ret = devm_add_action(dev, gud_free_buffers_and_mutex, gdrm);
 	if (ret)
 		return ret;
 
@@ -536,24 +563,17 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id)
 
 	if (desc.max_buffer_size)
 		max_buffer_size = le32_to_cpu(desc.max_buffer_size);
-retry:
-	/*
-	 * Use plain kmalloc here since devm_kmalloc() places struct devres at the beginning
-	 * of the buffer it allocates. This wastes a lot of memory when allocating big buffers.
-	 * Asking for 2M would actually allocate 4M. This would also prevent getting the biggest
-	 * possible buffer potentially leading to split transfers.
-	 */
-	gdrm->bulk_buf = kmalloc(max_buffer_size, GFP_KERNEL | __GFP_NOWARN);
-	if (!gdrm->bulk_buf) {
-		max_buffer_size = roundup_pow_of_two(max_buffer_size) / 2;
-		if (max_buffer_size < SZ_512K)
-			return -ENOMEM;
-		goto retry;
-	}
+	/* Prevent a misbehaving device from allocating loads of RAM. 4096x4096@XRGB8888 = 64 MB */
+	if (max_buffer_size > SZ_64M)
+		max_buffer_size = SZ_64M;
 
 	gdrm->bulk_pipe = usb_sndbulkpipe(interface_to_usbdev(intf), usb_endpoint_num(bulk_out));
 	gdrm->bulk_len = max_buffer_size;
 
+	ret = gud_alloc_bulk_buffer(gdrm);
+	if (ret)
+		return ret;
+
 	if (gdrm->compression & GUD_COMPRESSION_LZ4) {
 		gdrm->lz4_comp_mem = devm_kmalloc(dev, LZ4_MEM_COMPRESS, GFP_KERNEL);
 		if (!gdrm->lz4_comp_mem)
@@ -640,6 +660,7 @@ static int gud_resume(struct usb_interface *intf)
 
 static const struct usb_device_id gud_id_table[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x1d50, 0x614d, USB_CLASS_VENDOR_SPEC) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x16d0, 0x10a9, USB_CLASS_VENDOR_SPEC) },
 	{ }
 };
 
diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h
index b65105585578..2a388e27d5d7 100644
--- a/drivers/gpu/drm/gud/gud_internal.h
+++ b/drivers/gpu/drm/gud/gud_internal.h
@@ -5,6 +5,7 @@
 
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/scatterlist.h>
 #include <linux/usb.h>
 #include <linux/workqueue.h>
 #include <uapi/drm/drm_fourcc.h>
@@ -26,6 +27,7 @@ struct gud_device {
 	unsigned int bulk_pipe;
 	void *bulk_buf;
 	size_t bulk_len;
+	struct sg_table bulk_sgt;
 
 	u8 compression;
 	void *lz4_comp_mem;
diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c
index 2f83ab6b8e61..b9b0e435ea0f 100644
--- a/drivers/gpu/drm/gud/gud_pipe.c
+++ b/drivers/gpu/drm/gud/gud_pipe.c
@@ -3,7 +3,6 @@
  * Copyright 2020 Noralf Trønnes
  */
 
-#include <linux/dma-buf.h>
 #include <linux/lz4.h>
 #include <linux/usb.h>
 #include <linux/workqueue.h>
@@ -15,7 +14,8 @@
 #include <drm/drm_format_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
-#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_print.h>
 #include <drm/drm_rect.h>
 #include <drm/drm_simple_kms_helper.h>
@@ -24,6 +24,19 @@
 #include "gud_internal.h"
 
 /*
+ * Some userspace rendering loops runs all displays in the same loop.
+ * This means that a fast display will have to wait for a slow one.
+ * For this reason gud does flushing asynchronous by default.
+ * The down side is that in e.g. a single display setup userspace thinks
+ * the display is insanely fast since the driver reports back immediately
+ * that the flush/pageflip is done. This wastes CPU and power.
+ * Such users might want to set this module parameter to false.
+ */
+static bool gud_async_flush = true;
+module_param_named(async_flush, gud_async_flush, bool, 0644);
+MODULE_PARM_DESC(async_flush, "Enable asynchronous flushing [default=true]");
+
+/*
  * FIXME: The driver is probably broken on Big Endian machines.
  * See discussion:
  * https://lore.kernel.org/dri-devel/CAKb7UvihLX0hgBOP3VBG7O+atwZcUVCPVuBdfmDMpg0NjXe-cQ@mail.gmail.com/
@@ -139,7 +152,8 @@ static int gud_prep_flush(struct gud_device *gdrm, struct drm_framebuffer *fb,
 {
 	struct dma_buf_attachment *import_attach = fb->obj[0]->import_attach;
 	u8 compression = gdrm->compression;
-	struct dma_buf_map map;
+	struct dma_buf_map map[DRM_FORMAT_MAX_PLANES];
+	struct dma_buf_map map_data[DRM_FORMAT_MAX_PLANES];
 	void *vaddr, *buf;
 	size_t pitch, len;
 	int ret = 0;
@@ -149,17 +163,15 @@ static int gud_prep_flush(struct gud_device *gdrm, struct drm_framebuffer *fb,
 	if (len > gdrm->bulk_len)
 		return -E2BIG;
 
-	ret = drm_gem_shmem_vmap(fb->obj[0], &map);
+	ret = drm_gem_fb_vmap(fb, map, map_data);
 	if (ret)
 		return ret;
 
-	vaddr = map.vaddr + fb->offsets[0];
+	vaddr = map_data[0].vaddr;
 
-	if (import_attach) {
-		ret = dma_buf_begin_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE);
-		if (ret)
-			goto vunmap;
-	}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret)
+		goto vunmap;
 retry:
 	if (compression)
 		buf = gdrm->compress_buf;
@@ -212,10 +224,48 @@ retry:
 	}
 
 end_cpu_access:
-	if (import_attach)
-		dma_buf_end_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE);
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 vunmap:
-	drm_gem_shmem_vunmap(fb->obj[0], &map);
+	drm_gem_fb_vunmap(fb, map);
+
+	return ret;
+}
+
+struct gud_usb_bulk_context {
+	struct timer_list timer;
+	struct usb_sg_request sgr;
+};
+
+static void gud_usb_bulk_timeout(struct timer_list *t)
+{
+	struct gud_usb_bulk_context *ctx = from_timer(ctx, t, timer);
+
+	usb_sg_cancel(&ctx->sgr);
+}
+
+static int gud_usb_bulk(struct gud_device *gdrm, size_t len)
+{
+	struct gud_usb_bulk_context ctx;
+	int ret;
+
+	ret = usb_sg_init(&ctx.sgr, gud_to_usb_device(gdrm), gdrm->bulk_pipe, 0,
+			  gdrm->bulk_sgt.sgl, gdrm->bulk_sgt.nents, len, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	timer_setup_on_stack(&ctx.timer, gud_usb_bulk_timeout, 0);
+	mod_timer(&ctx.timer, jiffies + msecs_to_jiffies(3000));
+
+	usb_sg_wait(&ctx.sgr);
+
+	if (!del_timer_sync(&ctx.timer))
+		ret = -ETIMEDOUT;
+	else if (ctx.sgr.status < 0)
+		ret = ctx.sgr.status;
+	else if (ctx.sgr.bytes != len)
+		ret = -EIO;
+
+	destroy_timer_on_stack(&ctx.timer);
 
 	return ret;
 }
@@ -223,10 +273,9 @@ vunmap:
 static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb,
 			  const struct drm_format_info *format, struct drm_rect *rect)
 {
-	struct usb_device *usb = gud_to_usb_device(gdrm);
 	struct gud_set_buffer_req req;
-	int ret, actual_length;
 	size_t len, trlen;
+	int ret;
 
 	drm_dbg(&gdrm->drm, "Flushing [FB:%d] " DRM_RECT_FMT "\n", fb->base.id, DRM_RECT_ARG(rect));
 
@@ -255,10 +304,7 @@ static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb,
 			return ret;
 	}
 
-	ret = usb_bulk_msg(usb, gdrm->bulk_pipe, gdrm->bulk_buf, trlen,
-			   &actual_length, msecs_to_jiffies(3000));
-	if (!ret && trlen != actual_length)
-		ret = -EIO;
+	ret = gud_usb_bulk(gdrm, trlen);
 	if (ret)
 		gdrm->stats_num_errors++;
 
@@ -543,6 +589,8 @@ void gud_pipe_update(struct drm_simple_display_pipe *pipe,
 		if (gdrm->flags & GUD_DISPLAY_FLAG_FULL_UPDATE)
 			drm_rect_init(&damage, 0, 0, fb->width, fb->height);
 		gud_fb_queue_damage(gdrm, fb, &damage);
+		if (!gud_async_flush)
+			flush_work(&gdrm->work);
 	}
 
 	if (!crtc->state->enable)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index fa8da0ef707e..89bed78f1466 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -152,8 +152,7 @@ static const struct drm_plane_funcs hibmc_plane_funcs = {
 };
 
 static const struct drm_plane_helper_funcs hibmc_plane_helper_funcs = {
-	.prepare_fb	= drm_gem_vram_plane_helper_prepare_fb,
-	.cleanup_fb	= drm_gem_vram_plane_helper_cleanup_fb,
+	DRM_GEM_VRAM_PLANE_HELPER_FUNCS,
 	.atomic_check = hibmc_plane_atomic_check,
 	.atomic_update = hibmc_plane_atomic_update,
 };
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index f4bc5386574a..610fc8e135f9 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -19,7 +19,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_vblank.h>
 
@@ -28,7 +27,7 @@
 
 DEFINE_DRM_GEM_FOPS(hibmc_fops);
 
-static irqreturn_t hibmc_drm_interrupt(int irq, void *arg)
+static irqreturn_t hibmc_interrupt(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *)arg;
 	struct hibmc_drm_private *priv = to_hibmc_drm_private(dev);
@@ -63,7 +62,6 @@ static const struct drm_driver hibmc_driver = {
 	.dumb_create            = hibmc_dumb_create,
 	.dumb_map_offset        = drm_gem_ttm_dumb_map_offset,
 	.gem_prime_mmap		= drm_gem_prime_mmap,
-	.irq_handler		= hibmc_drm_interrupt,
 };
 
 static int __maybe_unused hibmc_pm_suspend(struct device *dev)
@@ -251,10 +249,11 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
 
 static int hibmc_unload(struct drm_device *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
 	drm_atomic_helper_shutdown(dev);
 
-	if (dev->irq_enabled)
-		drm_irq_uninstall(dev);
+	free_irq(pdev->irq, dev);
 
 	pci_disable_msi(to_pci_dev(dev->dev));
 
@@ -291,7 +290,9 @@ static int hibmc_load(struct drm_device *dev)
 	if (ret) {
 		drm_warn(dev, "enabling MSI failed: %d\n", ret);
 	} else {
-		ret = drm_irq_install(dev, pdev->irq);
+		/* PCI devices require shared interrupts. */
+		ret = request_irq(pdev->irq, hibmc_interrupt, IRQF_SHARED,
+				  dev->driver->name, dev);
 		if (ret)
 			drm_warn(dev, "install irq failed: %d\n", ret);
 	}
@@ -314,7 +315,7 @@ static int hibmc_pci_probe(struct pci_dev *pdev,
 	struct drm_device *dev;
 	int ret;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hibmcdrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &hibmc_driver);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
index 9b565a057340..952cfdb1961d 100644
--- a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
+++ b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
@@ -769,16 +769,9 @@ static int dsi_bridge_init(struct drm_device *dev, struct dw_dsi *dsi)
 {
 	struct drm_encoder *encoder = &dsi->encoder;
 	struct drm_bridge *bridge = dsi->bridge;
-	int ret;
 
 	/* associate the bridge to dsi encoder */
-	ret = drm_bridge_attach(encoder, bridge, NULL, 0);
-	if (ret) {
-		DRM_ERROR("failed to attach external bridge\n");
-		return ret;
-	}
-
-	return 0;
+	return drm_bridge_attach(encoder, bridge, NULL, 0);
 }
 
 static int dsi_bind(struct device *dev, struct device *master, void *data)
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
index e590e19db657..98ae9a48f3fe 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
@@ -185,8 +185,6 @@ static int kirin_drm_kms_init(struct drm_device *dev,
 		DRM_ERROR("failed to initialize vblank.\n");
 		goto err_unbind_all;
 	}
-	/* with irq_enabled = true, we can use the vblank feature. */
-	dev->irq_enabled = true;
 
 	/* reset all the states of crtc/plane/encoder/connector */
 	drm_mode_config_reset(dev);
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index eb06c92c4bfd..cd818a629183 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -82,7 +82,7 @@ static int hyperv_setup_gen1(struct hyperv_drm_device *hv)
 		return -ENODEV;
 	}
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hypervdrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &hyperv_driver);
 	if (ret) {
 		drm_err(dev, "Not able to remove boot fb\n");
 		return ret;
@@ -127,7 +127,7 @@ static int hyperv_setup_gen2(struct hyperv_drm_device *hv,
 	drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base,
 						     screen_info.lfb_size,
 						     false,
-						     "hypervdrmfb");
+						     &hyperv_driver);
 
 	hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024;
 
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
index 3aaee4730ec6..6dd4717d3e1e 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
@@ -105,7 +105,7 @@ static void hyperv_pipe_enable(struct drm_simple_display_pipe *pipe,
 				crtc_state->mode.hdisplay,
 				crtc_state->mode.vdisplay,
 				plane_state->fb->pitches[0]);
-	hyperv_blit_to_vram_fullscreen(plane_state->fb, &shadow_plane_state->map[0]);
+	hyperv_blit_to_vram_fullscreen(plane_state->fb, &shadow_plane_state->data[0]);
 }
 
 static int hyperv_pipe_check(struct drm_simple_display_pipe *pipe,
@@ -133,7 +133,7 @@ static void hyperv_pipe_update(struct drm_simple_display_pipe *pipe,
 	struct drm_rect rect;
 
 	if (drm_atomic_helper_damage_merged(old_state, state, &rect)) {
-		hyperv_blit_to_vram_rect(state->fb, &shadow_plane_state->map[0], &rect);
+		hyperv_blit_to_vram_rect(state->fb, &shadow_plane_state->data[0], &rect);
 		hyperv_update_dirt(hv->hdev, &rect);
 	}
 }
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index d78c82af367c..9fb4dd63342f 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -38,7 +38,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_print.h>
 #include <drm/i810_drm.h>
 
@@ -209,7 +208,7 @@ static int i810_dma_cleanup(struct drm_device *dev)
 	 * is freed, it's too late.
 	 */
 	if (drm_core_check_feature(dev, DRIVER_HAVE_IRQ) && dev->irq_enabled)
-		drm_irq_uninstall(dev);
+		drm_legacy_irq_uninstall(dev);
 
 	if (dev->dev_private) {
 		int i;
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 72a38f28393f..47e845353ffa 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -207,6 +207,8 @@ config DRM_I915_LOW_LEVEL_TRACEPOINTS
 	  This provides the ability to precisely monitor engine utilisation
 	  and also analyze the request dependency resolving timeline.
 
+	  Recommended for driver developers only.
+
 	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_VBLANK_EVADE
@@ -220,6 +222,8 @@ config DRM_I915_DEBUG_VBLANK_EVADE
 	  is exceeded, even if there isn't an actual risk of missing
 	  the vblank.
 
+	  Recommended for driver developers only.
+
 	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_RUNTIME_PM
@@ -232,4 +236,6 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	  runtime PM functionality. This may introduce overhead during
 	  driver loading, suspend and resume operations.
 
+	  Recommended for driver developers only.
+
 	  If in doubt, say "N"
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4f22cac1c49b..642a5b5a1b81 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -38,6 +38,7 @@ i915-y += i915_drv.o \
 	  i915_irq.o \
 	  i915_getparam.o \
 	  i915_mitigations.o \
+	  i915_module.o \
 	  i915_params.o \
 	  i915_pci.o \
 	  i915_scatterlist.o \
@@ -89,7 +90,6 @@ gt-y += \
 	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
-	gt/intel_context_param.o \
 	gt/intel_context_sseu.o \
 	gt/intel_engine_cs.o \
 	gt/intel_engine_heartbeat.o \
@@ -108,6 +108,7 @@ gt-y += \
 	gt/intel_gtt.o \
 	gt/intel_llc.o \
 	gt/intel_lrc.o \
+	gt/intel_migrate.o \
 	gt/intel_mocs.o \
 	gt/intel_ppgtt.o \
 	gt/intel_rc6.o \
@@ -135,7 +136,6 @@ i915-y += $(gt-y)
 gem-y += \
 	gem/i915_gem_busy.o \
 	gem/i915_gem_clflush.o \
-	gem/i915_gem_client_blt.o \
 	gem/i915_gem_context.o \
 	gem/i915_gem_create.o \
 	gem/i915_gem_dmabuf.o \
@@ -143,7 +143,6 @@ gem-y += \
 	gem/i915_gem_execbuffer.o \
 	gem/i915_gem_internal.o \
 	gem/i915_gem_object.o \
-	gem/i915_gem_object_blt.o \
 	gem/i915_gem_lmem.o \
 	gem/i915_gem_mman.o \
 	gem/i915_gem_pages.o \
@@ -155,21 +154,24 @@ gem-y += \
 	gem/i915_gem_stolen.o \
 	gem/i915_gem_throttle.o \
 	gem/i915_gem_tiling.o \
+	gem/i915_gem_ttm.o \
 	gem/i915_gem_userptr.o \
 	gem/i915_gem_wait.o \
 	gem/i915_gemfs.o
 i915-y += \
 	  $(gem-y) \
 	  i915_active.o \
+	  i915_buddy.o \
 	  i915_cmd_parser.o \
 	  i915_gem_evict.o \
 	  i915_gem_gtt.o \
+	  i915_gem_ww.o \
 	  i915_gem.o \
-	  i915_globals.o \
 	  i915_query.o \
 	  i915_request.o \
 	  i915_scheduler.o \
 	  i915_trace_points.o \
+	  i915_ttm_buddy_manager.o \
 	  i915_vma.o \
 	  intel_wopcm.o
 
@@ -184,6 +186,8 @@ i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_guc_fw.o \
 	  gt/uc/intel_guc_log.o \
 	  gt/uc/intel_guc_log_debugfs.o \
+	  gt/uc/intel_guc_rc.o \
+	  gt/uc/intel_guc_slpc.o \
 	  gt/uc/intel_guc_submission.o \
 	  gt/uc/intel_huc.o \
 	  gt/uc/intel_huc_debugfs.o \
@@ -265,6 +269,7 @@ i915-y += \
 	display/intel_pps.o \
 	display/intel_qp_tables.o \
 	display/intel_sdvo.o \
+	display/intel_snps_phy.o \
 	display/intel_tv.o \
 	display/intel_vdsc.o \
 	display/intel_vrr.o \
@@ -276,7 +281,9 @@ i915-y += i915_perf.o
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
 i915-$(CONFIG_DRM_I915_SELFTEST) += \
+	gem/selftests/i915_gem_client_blt.o \
 	gem/selftests/igt_gem_utils.o \
+	selftests/intel_scheduler_helpers.o \
 	selftests/i915_random.o \
 	selftests/i915_selftest.o \
 	selftests/igt_atomic.o \
diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c
index 9643c45a2209..b1439ba78f67 100644
--- a/drivers/gpu/drm/i915/display/i9xx_plane.c
+++ b/drivers/gpu/drm/i915/display/i9xx_plane.c
@@ -912,7 +912,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	zpos = 0;
 	drm_plane_create_zpos_immutable_property(&plane->base, zpos);
 
-	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
+	intel_plane_helper_add(plane);
 
 	return plane;
 
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 16812488c5dd..43ec7fcd3f5d 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -729,8 +729,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	enum pipe pipe = crtc->pipe;
 	u32 tmp;
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1253,15 +1253,36 @@ static void gen11_dsi_pre_enable(struct intel_atomic_state *state,
 	gen11_dsi_set_transcoder_timings(encoder, pipe_config);
 }
 
+/*
+ * Wa_1409054076:icl,jsl,ehl
+ * When pipe A is disabled and MIPI DSI is enabled on pipe B,
+ * the AMT KVMR feature will incorrectly see pipe A as enabled.
+ * Set 0x42080 bit 23=1 before enabling DSI on pipe B and leave
+ * it set while DSI is enabled on pipe B
+ */
+static void icl_apply_kvmr_pipe_a_wa(struct intel_encoder *encoder,
+				     enum pipe pipe, bool enable)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B)
+		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+			     IGNORE_KVMR_PIPE_A,
+			     enable ? IGNORE_KVMR_PIPE_A : 0);
+}
 static void gen11_dsi_enable(struct intel_atomic_state *state,
 			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct drm_connector_state *conn_state)
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(conn_state->crtc);
 
 	drm_WARN_ON(state->base.dev, crtc_state->has_pch_encoder);
 
+	/* Wa_1409054076:icl,jsl,ehl */
+	icl_apply_kvmr_pipe_a_wa(encoder, crtc->pipe, true);
+
 	/* step6d: enable dsi transcoder */
 	gen11_dsi_enable_transcoder(encoder);
 
@@ -1415,6 +1436,7 @@ static void gen11_dsi_disable(struct intel_atomic_state *state,
 			      const struct drm_connector_state *old_conn_state)
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(old_conn_state->crtc);
 
 	/* step1: turn off backlight */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
@@ -1423,6 +1445,9 @@ static void gen11_dsi_disable(struct intel_atomic_state *state,
 	/* step2d,e: disable transcoder and wait */
 	gen11_dsi_disable_transcoder(encoder);
 
+	/* Wa_1409054076:icl,jsl,ehl */
+	icl_apply_kvmr_pipe_a_wa(encoder, crtc->pipe, false);
+
 	/* step2f,g: powerdown panel */
 	gen11_dsi_powerdown_panel(encoder);
 
@@ -1548,6 +1573,22 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder,
 		pipe_config->mode_flags |= I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE;
 }
 
+static void gen11_dsi_sync_state(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	enum pipe pipe = intel_crtc->pipe;
+
+	/* wa verify 1409054076:icl,jsl,ehl */
+	if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B &&
+	    !(intel_de_read(dev_priv, CHICKEN_PAR1_1) & IGNORE_KVMR_PIPE_A))
+		drm_dbg_kms(&dev_priv->drm,
+			    "[ENCODER:%d:%s] BIOS left IGNORE_KVMR_PIPE_A cleared with pipe B enabled\n",
+			    encoder->base.base.id,
+			    encoder->base.name);
+}
+
 static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
 					struct intel_crtc_state *crtc_state)
 {
@@ -1966,6 +2007,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	encoder->post_disable = gen11_dsi_post_disable;
 	encoder->port = port;
 	encoder->get_config = gen11_dsi_get_config;
+	encoder->sync_state = gen11_dsi_sync_state;
 	encoder->update_pipe = intel_panel_update_backlight;
 	encoder->compute_config = gen11_dsi_compute_config;
 	encoder->get_hw_state = gen11_dsi_get_hw_state;
diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c
index 833d0c1be4f1..7cfe91fc05f2 100644
--- a/drivers/gpu/drm/i915/display/intel_acpi.c
+++ b/drivers/gpu/drm/i915/display/intel_acpi.c
@@ -19,6 +19,12 @@ static const guid_t intel_dsm_guid =
 	GUID_INIT(0x7ed873d3, 0xc2d0, 0x4e4f,
 		  0xa8, 0x54, 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c);
 
+#define INTEL_DSM_FN_GET_BIOS_DATA_FUNCS_SUPPORTED 0 /* No args */
+
+static const guid_t intel_dsm_guid2 =
+	GUID_INIT(0x3e5b41c6, 0xeb1d, 0x4260,
+		  0x9d, 0x15, 0xc7, 0x1f, 0xba, 0xda, 0xe4, 0x14);
+
 static char *intel_dsm_port_name(u8 id)
 {
 	switch (id) {
@@ -176,6 +182,19 @@ void intel_unregister_dsm_handler(void)
 {
 }
 
+void intel_dsm_get_bios_data_funcs_supported(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+	acpi_handle dhandle;
+
+	dhandle = ACPI_HANDLE(&pdev->dev);
+	if (!dhandle)
+		return;
+
+	acpi_evaluate_dsm(dhandle, &intel_dsm_guid2, INTEL_DSM_REVISION_ID,
+			  INTEL_DSM_FN_GET_BIOS_DATA_FUNCS_SUPPORTED, NULL);
+}
+
 /*
  * ACPI Specification, Revision 5.0, Appendix B.3.2 _DOD (Enumerate All Devices
  * Attached to the Display Adapter).
diff --git a/drivers/gpu/drm/i915/display/intel_acpi.h b/drivers/gpu/drm/i915/display/intel_acpi.h
index e8b068661d22..9f197401c313 100644
--- a/drivers/gpu/drm/i915/display/intel_acpi.h
+++ b/drivers/gpu/drm/i915/display/intel_acpi.h
@@ -11,11 +11,14 @@ struct drm_i915_private;
 #ifdef CONFIG_ACPI
 void intel_register_dsm_handler(void);
 void intel_unregister_dsm_handler(void);
+void intel_dsm_get_bios_data_funcs_supported(struct drm_i915_private *i915);
 void intel_acpi_device_id_update(struct drm_i915_private *i915);
 #else
 static inline void intel_register_dsm_handler(void) { return; }
 static inline void intel_unregister_dsm_handler(void) { return; }
 static inline
+void intel_dsm_get_bios_data_funcs_supported(struct drm_i915_private *i915) { return; }
+static inline
 void intel_acpi_device_id_update(struct drm_i915_private *i915) { return; }
 #endif /* CONFIG_ACPI */
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 36f52a1d7552..47234d898549 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -601,7 +601,12 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state,
 	return 0;
 }
 
-const struct drm_plane_helper_funcs intel_plane_helper_funcs = {
+static const struct drm_plane_helper_funcs intel_plane_helper_funcs = {
 	.prepare_fb = intel_prepare_plane_fb,
 	.cleanup_fb = intel_cleanup_plane_fb,
 };
+
+void intel_plane_helper_add(struct intel_plane *plane)
+{
+	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index dc4d05e75e1c..62e5a2a77fd4 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -17,8 +17,6 @@ struct intel_crtc_state;
 struct intel_plane;
 struct intel_plane_state;
 
-extern const struct drm_plane_helper_funcs intel_plane_helper_funcs;
-
 unsigned int intel_adjusted_rate(const struct drm_rect *src,
 				 const struct drm_rect *dst,
 				 unsigned int rate);
@@ -65,5 +63,6 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state,
 				      bool can_position);
 void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
 			       struct intel_plane_state *plane_state);
+void intel_plane_helper_add(struct intel_plane *plane);
 
 #endif /* __INTEL_ATOMIC_PLANE_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 5f4f316b3ab5..532237588511 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -1001,7 +1001,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 	/* Catch potential impedance mismatches before they occur! */
 	BUILD_BUG_ON(sizeof(intel_wakeref_t) > sizeof(unsigned long));
 
-	ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
+	ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK);
 
 	if (dev_priv->audio_power_refcount++ == 0) {
 		if (DISPLAY_VER(dev_priv) >= 9) {
@@ -1034,7 +1034,7 @@ static void i915_audio_component_put_power(struct device *kdev,
 		if (IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, false);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK, cookie);
 }
 
 static void i915_audio_component_codec_wake_override(struct device *kdev,
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index aa667fa71158..e86e6ed2d3bf 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1871,12 +1871,12 @@ intel_bios_encoder_supports_edp(const struct intel_bios_encoder_data *devdata)
 static bool is_port_valid(struct drm_i915_private *i915, enum port port)
 {
 	/*
-	 * On some ICL/CNL SKUs port F is not present, but broken VBTs mark
+	 * On some ICL SKUs port F is not present, but broken VBTs mark
 	 * the port as present. Only try to initialize port F for the
 	 * SKUs that may actually have it.
 	 */
-	if (port == PORT_F && (IS_ICELAKE(i915) || IS_CANNONLAKE(i915)))
-		return IS_ICL_WITH_PORT_F(i915) || IS_CNL_WITH_PORT_F(i915);
+	if (port == PORT_F && IS_ICELAKE(i915))
+		return IS_ICL_WITH_PORT_F(i915);
 
 	return true;
 }
@@ -1998,7 +1998,7 @@ static void parse_ddi_port(struct drm_i915_private *i915,
 			    "Port %c VBT HDMI boost level: %d\n",
 			    port_name(port), hdmi_boost_level);
 
-	/* DP max link rate for CNL+ */
+	/* DP max link rate for GLK+ */
 	if (i915->vbt.version >= 216) {
 		if (i915->vbt.version >= 230)
 			info->dp_max_link_rate = parse_bdb_230_dp_max_link_rate(child->dp_max_link_rate);
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index bfb398f0432e..e91e0e0191fb 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -17,12 +17,53 @@ struct intel_qgv_point {
 	u16 dclk, t_rp, t_rdpre, t_rc, t_ras, t_rcd;
 };
 
+struct intel_psf_gv_point {
+	u8 clk; /* clock in multiples of 16.6666 MHz */
+};
+
 struct intel_qgv_info {
 	struct intel_qgv_point points[I915_NUM_QGV_POINTS];
+	struct intel_psf_gv_point psf_points[I915_NUM_PSF_GV_POINTS];
 	u8 num_points;
+	u8 num_psf_points;
 	u8 t_bl;
 };
 
+static int dg1_mchbar_read_qgv_point_info(struct drm_i915_private *dev_priv,
+					  struct intel_qgv_point *sp,
+					  int point)
+{
+	u32 dclk_ratio, dclk_reference;
+	u32 val;
+
+	val = intel_uncore_read(&dev_priv->uncore, SA_PERF_STATUS_0_0_0_MCHBAR_PC);
+	dclk_ratio = REG_FIELD_GET(DG1_QCLK_RATIO_MASK, val);
+	if (val & DG1_QCLK_REFERENCE)
+		dclk_reference = 6; /* 6 * 16.666 MHz = 100 MHz */
+	else
+		dclk_reference = 8; /* 8 * 16.666 MHz = 133 MHz */
+	sp->dclk = dclk_ratio * dclk_reference;
+
+	val = intel_uncore_read(&dev_priv->uncore, SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU);
+	if (val & DG1_GEAR_TYPE)
+		sp->dclk *= 2;
+
+	if (sp->dclk == 0)
+		return -EINVAL;
+
+	val = intel_uncore_read(&dev_priv->uncore, MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR);
+	sp->t_rp = REG_FIELD_GET(DG1_DRAM_T_RP_MASK, val);
+	sp->t_rdpre = REG_FIELD_GET(DG1_DRAM_T_RDPRE_MASK, val);
+
+	val = intel_uncore_read(&dev_priv->uncore, MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR_HIGH);
+	sp->t_rcd = REG_FIELD_GET(DG1_DRAM_T_RCD_MASK, val);
+	sp->t_ras = REG_FIELD_GET(DG1_DRAM_T_RAS_MASK, val);
+
+	sp->t_rc = sp->t_rp + sp->t_ras;
+
+	return 0;
+}
+
 static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv,
 					 struct intel_qgv_point *sp,
 					 int point)
@@ -49,6 +90,28 @@ static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+static int adls_pcode_read_psf_gv_point_info(struct drm_i915_private *dev_priv,
+					    struct intel_psf_gv_point *points)
+{
+	u32 val = 0;
+	int ret;
+	int i;
+
+	ret = sandybridge_pcode_read(dev_priv,
+				     ICL_PCODE_MEM_SUBSYSYSTEM_INFO |
+				     ADL_PCODE_MEM_SS_READ_PSF_GV_INFO,
+				     &val, NULL);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < I915_NUM_PSF_GV_POINTS; i++) {
+		points[i].clk = val & 0xff;
+		val >>= 8;
+	}
+
+	return 0;
+}
+
 int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv,
 				  u32 points_mask)
 {
@@ -62,7 +125,7 @@ int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv,
 				1);
 
 	if (ret < 0) {
-		drm_err(&dev_priv->drm, "Failed to disable qgv points (%d)\n", ret);
+		drm_err(&dev_priv->drm, "Failed to disable qgv points (%d) points: 0x%x\n", ret, points_mask);
 		return ret;
 	}
 
@@ -76,6 +139,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
 	int i, ret;
 
 	qi->num_points = dram_info->num_qgv_points;
+	qi->num_psf_points = dram_info->num_psf_gv_points;
 
 	if (DISPLAY_VER(dev_priv) == 12)
 		switch (dram_info->type) {
@@ -99,7 +163,11 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
 	for (i = 0; i < qi->num_points; i++) {
 		struct intel_qgv_point *sp = &qi->points[i];
 
-		ret = icl_pcode_read_qgv_point_info(dev_priv, sp, i);
+		if (IS_DG1(dev_priv))
+			ret = dg1_mchbar_read_qgv_point_info(dev_priv, sp, i);
+		else
+			ret = icl_pcode_read_qgv_point_info(dev_priv, sp, i);
+
 		if (ret)
 			return ret;
 
@@ -109,6 +177,19 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
 			    sp->t_rcd, sp->t_rc);
 	}
 
+	if (qi->num_psf_points > 0) {
+		ret = adls_pcode_read_psf_gv_point_info(dev_priv, qi->psf_points);
+		if (ret) {
+			drm_err(&dev_priv->drm, "Failed to read PSF point data; PSF points will not be considered in bandwidth calculations.\n");
+			qi->num_psf_points = 0;
+		}
+
+		for (i = 0; i < qi->num_psf_points; i++)
+			drm_dbg_kms(&dev_priv->drm,
+				    "PSF GV %d: CLK=%d \n",
+				    i, qi->psf_points[i].clk);
+	}
+
 	return 0;
 }
 
@@ -118,6 +199,16 @@ static int icl_calc_bw(int dclk, int num, int den)
 	return DIV_ROUND_CLOSEST(num * dclk * 100, den * 6);
 }
 
+static int adl_calc_psf_bw(int clk)
+{
+	/*
+	 * clk is multiples of 16.666MHz (100/6)
+	 * According to BSpec PSF GV bandwidth is
+	 * calculated as BW = 64 * clk * 16.666Mhz
+	 */
+	return DIV_ROUND_CLOSEST(64 * clk * 100, 6);
+}
+
 static int icl_sagv_max_dclk(const struct intel_qgv_info *qi)
 {
 	u16 dclk = 0;
@@ -194,6 +285,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 		bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1;
 
 		bi->num_qgv_points = qi.num_points;
+		bi->num_psf_gv_points = qi.num_psf_points;
 
 		for (j = 0; j < qi.num_points; j++) {
 			const struct intel_qgv_point *sp = &qi.points[j];
@@ -217,6 +309,16 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 				    i, j, bi->num_planes, bi->deratedbw[j]);
 		}
 
+		for (j = 0; j < qi.num_psf_points; j++) {
+			const struct intel_psf_gv_point *sp = &qi.psf_points[j];
+
+			bi->psf_bw[j] = adl_calc_psf_bw(sp->clk);
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "BW%d / PSF GV %d: num_planes=%d bw=%u\n",
+				    i, j, bi->num_planes, bi->psf_bw[j]);
+		}
+
 		if (bi->num_planes == 1)
 			break;
 	}
@@ -234,6 +336,26 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 	return 0;
 }
 
+static void dg2_get_bw_info(struct drm_i915_private *i915)
+{
+	struct intel_bw_info *bi = &i915->max_bw[0];
+
+	/*
+	 * DG2 doesn't have SAGV or QGV points, just a constant max bandwidth
+	 * that doesn't depend on the number of planes enabled.  Create a
+	 * single dummy QGV point to reflect that.  DG2-G10 platforms have a
+	 * constant 50 GB/s bandwidth, whereas DG2-G11 platforms have 38 GB/s.
+	 */
+	bi->num_planes = 1;
+	bi->num_qgv_points = 1;
+	if (IS_DG2_G11(i915))
+		bi->deratedbw[0] = 38000;
+	else
+		bi->deratedbw[0] = 50000;
+
+	i915->sagv_status = I915_SAGV_NOT_CONTROLLED;
+}
+
 static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 			       int num_planes, int qgv_point)
 {
@@ -262,12 +384,23 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+static unsigned int adl_psf_bw(struct drm_i915_private *dev_priv,
+			       int psf_gv_point)
+{
+	const struct intel_bw_info *bi =
+			&dev_priv->max_bw[0];
+
+	return bi->psf_bw[psf_gv_point];
+}
+
 void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 {
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
-	if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv))
+	if (IS_DG2(dev_priv))
+		dg2_get_bw_info(dev_priv);
+	else if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv))
 		icl_get_bw_info(dev_priv, &adls_sa_info);
 	else if (IS_ROCKETLAKE(dev_priv))
 		icl_get_bw_info(dev_priv, &rkl_sa_info);
@@ -534,12 +667,24 @@ int intel_bw_atomic_check(struct intel_atomic_state *state)
 	u32 allowed_points = 0;
 	unsigned int max_bw_point = 0, max_bw = 0;
 	unsigned int num_qgv_points = dev_priv->max_bw[0].num_qgv_points;
-	u32 mask = (1 << num_qgv_points) - 1;
+	unsigned int num_psf_gv_points = dev_priv->max_bw[0].num_psf_gv_points;
+	u32 mask = 0;
 
 	/* FIXME earlier gens need some checks too */
 	if (DISPLAY_VER(dev_priv) < 11)
 		return 0;
 
+	/*
+	 * We can _not_ use the whole ADLS_QGV_PT_MASK here, as PCode rejects
+	 * it with failure if we try masking any unadvertised points.
+	 * So need to operate only with those returned from PCode.
+	 */
+	if (num_qgv_points > 0)
+		mask |= REG_GENMASK(num_qgv_points - 1, 0);
+
+	if (num_psf_gv_points > 0)
+		mask |= REG_GENMASK(num_psf_gv_points - 1, 0) << ADLS_PSF_PT_SHIFT;
+
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
 		unsigned int old_data_rate =
@@ -602,23 +747,44 @@ int intel_bw_atomic_check(struct intel_atomic_state *state)
 			max_bw = max_data_rate;
 		}
 		if (max_data_rate >= data_rate)
-			allowed_points |= BIT(i);
+			allowed_points |= REG_FIELD_PREP(ADLS_QGV_PT_MASK, BIT(i));
+
 		drm_dbg_kms(&dev_priv->drm, "QGV point %d: max bw %d required %d\n",
 			    i, max_data_rate, data_rate);
 	}
 
+	for (i = 0; i < num_psf_gv_points; i++) {
+		unsigned int max_data_rate = adl_psf_bw(dev_priv, i);
+
+		if (max_data_rate >= data_rate)
+			allowed_points |= REG_FIELD_PREP(ADLS_PSF_PT_MASK, BIT(i));
+
+		drm_dbg_kms(&dev_priv->drm, "PSF GV point %d: max bw %d"
+			    " required %d\n",
+			    i, max_data_rate, data_rate);
+	}
+
 	/*
 	 * BSpec states that we always should have at least one allowed point
 	 * left, so if we couldn't - simply reject the configuration for obvious
 	 * reasons.
 	 */
-	if (allowed_points == 0) {
+	if ((allowed_points & ADLS_QGV_PT_MASK) == 0) {
 		drm_dbg_kms(&dev_priv->drm, "No QGV points provide sufficient memory"
 			    " bandwidth %d for display configuration(%d active planes).\n",
 			    data_rate, num_active_planes);
 		return -EINVAL;
 	}
 
+	if (num_psf_gv_points > 0) {
+		if ((allowed_points & ADLS_PSF_PT_MASK) == 0) {
+			drm_dbg_kms(&dev_priv->drm, "No PSF GV points provide sufficient memory"
+				    " bandwidth %d for display configuration(%d active planes).\n",
+				    data_rate, num_active_planes);
+			return -EINVAL;
+		}
+	}
+
 	/*
 	 * Leave only single point with highest bandwidth, if
 	 * we can't enable SAGV due to the increased memory latency it may
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 613ffcc68eba..34fa4130d5c4 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1195,17 +1195,6 @@ static const struct intel_cdclk_vals glk_cdclk_table[] = {
 	{}
 };
 
-static const struct intel_cdclk_vals cnl_cdclk_table[] = {
-	{ .refclk = 19200, .cdclk = 168000, .divider = 4, .ratio = 35 },
-	{ .refclk = 19200, .cdclk = 336000, .divider = 2, .ratio = 35 },
-	{ .refclk = 19200, .cdclk = 528000, .divider = 2, .ratio = 55 },
-
-	{ .refclk = 24000, .cdclk = 168000, .divider = 4, .ratio = 28 },
-	{ .refclk = 24000, .cdclk = 336000, .divider = 2, .ratio = 28 },
-	{ .refclk = 24000, .cdclk = 528000, .divider = 2, .ratio = 44 },
-	{}
-};
-
 static const struct intel_cdclk_vals icl_cdclk_table[] = {
 	{ .refclk = 19200, .cdclk = 172800, .divider = 2, .ratio = 18 },
 	{ .refclk = 19200, .cdclk = 192000, .divider = 2, .ratio = 20 },
@@ -1290,6 +1279,16 @@ static const struct intel_cdclk_vals adlp_cdclk_table[] = {
 	{}
 };
 
+static const struct intel_cdclk_vals dg2_cdclk_table[] = {
+	{ .refclk = 38400, .cdclk = 172800, .divider = 2, .ratio =  9 },
+	{ .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 },
+	{ .refclk = 38400, .cdclk = 307200, .divider = 2, .ratio = 16 },
+	{ .refclk = 38400, .cdclk = 326400, .divider = 4, .ratio = 34 },
+	{ .refclk = 38400, .cdclk = 556800, .divider = 2, .ratio = 29 },
+	{ .refclk = 38400, .cdclk = 652800, .divider = 2, .ratio = 34 },
+	{}
+};
+
 static int bxt_calc_cdclk(struct drm_i915_private *dev_priv, int min_cdclk)
 {
 	const struct intel_cdclk_vals *table = dev_priv->cdclk.table;
@@ -1329,16 +1328,6 @@ static u8 bxt_calc_voltage_level(int cdclk)
 	return DIV_ROUND_UP(cdclk, 25000);
 }
 
-static u8 cnl_calc_voltage_level(int cdclk)
-{
-	if (cdclk > 336000)
-		return 2;
-	else if (cdclk > 168000)
-		return 1;
-	else
-		return 0;
-}
-
 static u8 icl_calc_voltage_level(int cdclk)
 {
 	if (cdclk > 556800)
@@ -1373,15 +1362,6 @@ static u8 tgl_calc_voltage_level(int cdclk)
 		return 0;
 }
 
-static void cnl_readout_refclk(struct drm_i915_private *dev_priv,
-			       struct intel_cdclk_config *cdclk_config)
-{
-	if (intel_de_read(dev_priv, SKL_DSSM) & CNL_DSSM_CDCLK_PLL_REFCLK_24MHz)
-		cdclk_config->ref = 24000;
-	else
-		cdclk_config->ref = 19200;
-}
-
 static void icl_readout_refclk(struct drm_i915_private *dev_priv,
 			       struct intel_cdclk_config *cdclk_config)
 {
@@ -1408,10 +1388,10 @@ static void bxt_de_pll_readout(struct drm_i915_private *dev_priv,
 {
 	u32 val, ratio;
 
-	if (DISPLAY_VER(dev_priv) >= 11)
+	if (IS_DG2(dev_priv))
+		cdclk_config->ref = 38400;
+	else if (DISPLAY_VER(dev_priv) >= 11)
 		icl_readout_refclk(dev_priv, cdclk_config);
-	else if (IS_CANNONLAKE(dev_priv))
-		cnl_readout_refclk(dev_priv, cdclk_config);
 	else
 		cdclk_config->ref = 19200;
 
@@ -1427,11 +1407,11 @@ static void bxt_de_pll_readout(struct drm_i915_private *dev_priv,
 	}
 
 	/*
-	 * CNL+ have the ratio directly in the PLL enable register, gen9lp had
-	 * it in a separate PLL control register.
+	 * DISPLAY_VER >= 11 have the ratio directly in the PLL enable register,
+	 * gen9lp had it in a separate PLL control register.
 	 */
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
-		ratio = val & CNL_CDCLK_PLL_RATIO_MASK;
+	if (DISPLAY_VER(dev_priv) >= 11)
+		ratio = val & ICL_CDCLK_PLL_RATIO_MASK;
 	else
 		ratio = intel_de_read(dev_priv, BXT_DE_PLL_CTL) & BXT_DE_PLL_RATIO_MASK;
 
@@ -1518,7 +1498,7 @@ static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco)
 	dev_priv->cdclk.hw.vco = vco;
 }
 
-static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
+static void icl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
 {
 	intel_de_rmw(dev_priv, BXT_DE_PLL_ENABLE,
 		     BXT_DE_PLL_PLL_ENABLE, 0);
@@ -1530,12 +1510,12 @@ static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
 	dev_priv->cdclk.hw.vco = 0;
 }
 
-static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
+static void icl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
 {
 	int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref);
 	u32 val;
 
-	val = CNL_CDCLK_PLL_RATIO(ratio);
+	val = ICL_CDCLK_PLL_RATIO(ratio);
 	intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val);
 
 	val |= BXT_DE_PLL_PLL_ENABLE;
@@ -1548,18 +1528,13 @@ static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
 	dev_priv->cdclk.hw.vco = vco;
 }
 
-static bool has_cdclk_crawl(struct drm_i915_private *i915)
-{
-	return INTEL_INFO(i915)->has_cdclk_crawl;
-}
-
 static void adlp_cdclk_pll_crawl(struct drm_i915_private *dev_priv, int vco)
 {
 	int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref);
 	u32 val;
 
 	/* Write PLL ratio without disabling */
-	val = CNL_CDCLK_PLL_RATIO(ratio) | BXT_DE_PLL_PLL_ENABLE;
+	val = ICL_CDCLK_PLL_RATIO(ratio) | BXT_DE_PLL_PLL_ENABLE;
 	intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val);
 
 	/* Submit freq change request */
@@ -1628,7 +1603,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	int ret;
 
 	/* Inform power controller of upcoming frequency change. */
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 					SKL_CDCLK_PREPARE_FOR_CHANGE,
 					SKL_CDCLK_READY_FOR_CHANGE,
@@ -1649,16 +1624,16 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	if (has_cdclk_crawl(dev_priv) && dev_priv->cdclk.hw.vco > 0 && vco > 0) {
+	if (HAS_CDCLK_CRAWL(dev_priv) && dev_priv->cdclk.hw.vco > 0 && vco > 0) {
 		if (dev_priv->cdclk.hw.vco != vco)
 			adlp_cdclk_pll_crawl(dev_priv, vco);
-	} else if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) {
+	} else if (DISPLAY_VER(dev_priv) >= 11) {
 		if (dev_priv->cdclk.hw.vco != 0 &&
 		    dev_priv->cdclk.hw.vco != vco)
-			cnl_cdclk_pll_disable(dev_priv);
+			icl_cdclk_pll_disable(dev_priv);
 
 		if (dev_priv->cdclk.hw.vco != vco)
-			cnl_cdclk_pll_enable(dev_priv, vco);
+			icl_cdclk_pll_enable(dev_priv, vco);
 	} else {
 		if (dev_priv->cdclk.hw.vco != 0 &&
 		    dev_priv->cdclk.hw.vco != vco)
@@ -1684,7 +1659,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	if (pipe != INVALID_PIPE)
 		intel_wait_for_vblank(dev_priv, pipe);
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) {
+	if (DISPLAY_VER(dev_priv) >= 11) {
 		ret = sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 					      cdclk_config->voltage_level);
 	} else {
@@ -1709,7 +1684,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 
 	intel_update_cdclk(dev_priv);
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		/*
 		 * Can't read out the voltage level :(
 		 * Let's just assume everything is as expected.
@@ -1857,7 +1832,7 @@ static bool intel_cdclk_can_crawl(struct drm_i915_private *dev_priv,
 {
 	int a_div, b_div;
 
-	if (!has_cdclk_crawl(dev_priv))
+	if (!HAS_CDCLK_CRAWL(dev_priv))
 		return false;
 
 	/*
@@ -2118,7 +2093,7 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	    crtc_state->port_clock >= 540000 &&
 	    crtc_state->lane_count == 4) {
 		if (DISPLAY_VER(dev_priv) == 10) {
-			/* Display WA #1145: glk,cnl */
+			/* Display WA #1145: glk */
 			min_cdclk = max(316800, min_cdclk);
 		} else if (DISPLAY_VER(dev_priv) == 9 || IS_BROADWELL(dev_priv)) {
 			/* Display WA #1144: skl,bxt */
@@ -2239,7 +2214,7 @@ static int intel_compute_min_cdclk(struct intel_cdclk_state *cdclk_state)
 
 /*
  * Account for port clock min voltage level requirements.
- * This only really does something on CNL+ but can be
+ * This only really does something on DISPLA_VER >= 11 but can be
  * called on earlier platforms as well.
  *
  * Note that this functions assumes that 0 is
@@ -2653,8 +2628,6 @@ void intel_update_max_cdclk(struct drm_i915_private *dev_priv)
 			dev_priv->max_cdclk_freq = 648000;
 		else
 			dev_priv->max_cdclk_freq = 652800;
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		dev_priv->max_cdclk_freq = 528000;
 	} else if (IS_GEMINILAKE(dev_priv)) {
 		dev_priv->max_cdclk_freq = 316800;
 	} else if (IS_BROXTON(dev_priv)) {
@@ -2878,13 +2851,19 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv)
  */
 void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
-	if (IS_ALDERLAKE_P(dev_priv)) {
+	if (IS_DG2(dev_priv)) {
+		dev_priv->display.set_cdclk = bxt_set_cdclk;
+		dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk;
+		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
+		dev_priv->display.calc_voltage_level = tgl_calc_voltage_level;
+		dev_priv->cdclk.table = dg2_cdclk_table;
+	} else if (IS_ALDERLAKE_P(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk;
 		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = tgl_calc_voltage_level;
-		/* Wa_22011320316:adlp[a0] */
-		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0))
+		/* Wa_22011320316:adl-p[a0] */
+		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 			dev_priv->cdclk.table = adlp_a_step_cdclk_table;
 		else
 			dev_priv->cdclk.table = adlp_cdclk_table;
@@ -2912,12 +2891,6 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = icl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk;
-		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
-		dev_priv->display.calc_voltage_level = cnl_calc_voltage_level;
-		dev_priv->cdclk.table = cnl_cdclk_table;
 	} else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
 		dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk;
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index dab892d2251b..afcb4bf3826c 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -305,13 +305,12 @@ static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 				    ilk_csc_postoff_limited_range);
 	} else if (crtc_state->csc_enable) {
 		/*
-		 * On GLK+ both pipe CSC and degamma LUT are controlled
+		 * On GLK both pipe CSC and degamma LUT are controlled
 		 * by csc_enable. Hence for the cases where the degama
 		 * LUT is needed but CSC is not we need to load an
 		 * identity matrix.
 		 */
-		drm_WARN_ON(&dev_priv->drm, !IS_CANNONLAKE(dev_priv) &&
-			    !IS_GEMINILAKE(dev_priv));
+		drm_WARN_ON(&dev_priv->drm, !IS_GEMINILAKE(dev_priv));
 
 		ilk_update_pipe_csc(crtc, ilk_csc_off_zero,
 				    ilk_csc_coeff_identity,
diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c
index 487c54cd5982..bacdf8a16bcb 100644
--- a/drivers/gpu/drm/i915/display/intel_combo_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c
@@ -23,9 +23,9 @@ enum {
 	PROCMON_1_05V_DOT_1,
 };
 
-static const struct cnl_procmon {
+static const struct icl_procmon {
 	u32 dw1, dw9, dw10;
-} cnl_procmon_values[] = {
+} icl_procmon_values[] = {
 	[PROCMON_0_85V_DOT_0] =
 		{ .dw1 = 0x00000000, .dw9 = 0x62AB67BB, .dw10 = 0x51914F96, },
 	[PROCMON_0_95V_DOT_0] =
@@ -38,15 +38,10 @@ static const struct cnl_procmon {
 		{ .dw1 = 0x00440000, .dw9 = 0x9A00AB25, .dw10 = 0x8AE38FF1, },
 };
 
-/*
- * CNL has just one set of registers, while gen11 has a set for each combo PHY.
- * The CNL registers are equivalent to the gen11 PHY A registers, that's why we
- * call the ICL macros even though the function has CNL on its name.
- */
-static const struct cnl_procmon *
-cnl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
+static const struct icl_procmon *
+icl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
 {
-	const struct cnl_procmon *procmon;
+	const struct icl_procmon *procmon;
 	u32 val;
 
 	val = intel_de_read(dev_priv, ICL_PORT_COMP_DW3(phy));
@@ -55,32 +50,32 @@ cnl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
 		MISSING_CASE(val);
 		fallthrough;
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
-		procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0];
+		procmon = &icl_procmon_values[PROCMON_0_85V_DOT_0];
 		break;
 	case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_0:
-		procmon = &cnl_procmon_values[PROCMON_0_95V_DOT_0];
+		procmon = &icl_procmon_values[PROCMON_0_95V_DOT_0];
 		break;
 	case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_1:
-		procmon = &cnl_procmon_values[PROCMON_0_95V_DOT_1];
+		procmon = &icl_procmon_values[PROCMON_0_95V_DOT_1];
 		break;
 	case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_0:
-		procmon = &cnl_procmon_values[PROCMON_1_05V_DOT_0];
+		procmon = &icl_procmon_values[PROCMON_1_05V_DOT_0];
 		break;
 	case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_1:
-		procmon = &cnl_procmon_values[PROCMON_1_05V_DOT_1];
+		procmon = &icl_procmon_values[PROCMON_1_05V_DOT_1];
 		break;
 	}
 
 	return procmon;
 }
 
-static void cnl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
+static void icl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
 				       enum phy phy)
 {
-	const struct cnl_procmon *procmon;
+	const struct icl_procmon *procmon;
 	u32 val;
 
-	procmon = cnl_get_procmon_ref_values(dev_priv, phy);
+	procmon = icl_get_procmon_ref_values(dev_priv, phy);
 
 	val = intel_de_read(dev_priv, ICL_PORT_COMP_DW1(phy));
 	val &= ~((0xff << 16) | 0xff);
@@ -109,13 +104,13 @@ static bool check_phy_reg(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static bool cnl_verify_procmon_ref_values(struct drm_i915_private *dev_priv,
+static bool icl_verify_procmon_ref_values(struct drm_i915_private *dev_priv,
 					  enum phy phy)
 {
-	const struct cnl_procmon *procmon;
+	const struct icl_procmon *procmon;
 	bool ret;
 
-	procmon = cnl_get_procmon_ref_values(dev_priv, phy);
+	procmon = icl_get_procmon_ref_values(dev_priv, phy);
 
 	ret = check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW1(phy),
 			    (0xff << 16) | 0xff, procmon->dw1);
@@ -127,61 +122,6 @@ static bool cnl_verify_procmon_ref_values(struct drm_i915_private *dev_priv,
 	return ret;
 }
 
-static bool cnl_combo_phy_enabled(struct drm_i915_private *dev_priv)
-{
-	return !(intel_de_read(dev_priv, CHICKEN_MISC_2) & CNL_COMP_PWR_DOWN) &&
-		(intel_de_read(dev_priv, CNL_PORT_COMP_DW0) & COMP_INIT);
-}
-
-static bool cnl_combo_phy_verify_state(struct drm_i915_private *dev_priv)
-{
-	enum phy phy = PHY_A;
-	bool ret;
-
-	if (!cnl_combo_phy_enabled(dev_priv))
-		return false;
-
-	ret = cnl_verify_procmon_ref_values(dev_priv, phy);
-
-	ret &= check_phy_reg(dev_priv, phy, CNL_PORT_CL1CM_DW5,
-			     CL_POWER_DOWN_ENABLE, CL_POWER_DOWN_ENABLE);
-
-	return ret;
-}
-
-static void cnl_combo_phys_init(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	val = intel_de_read(dev_priv, CHICKEN_MISC_2);
-	val &= ~CNL_COMP_PWR_DOWN;
-	intel_de_write(dev_priv, CHICKEN_MISC_2, val);
-
-	/* Dummy PORT_A to get the correct CNL register from the ICL macro */
-	cnl_set_procmon_ref_values(dev_priv, PHY_A);
-
-	val = intel_de_read(dev_priv, CNL_PORT_COMP_DW0);
-	val |= COMP_INIT;
-	intel_de_write(dev_priv, CNL_PORT_COMP_DW0, val);
-
-	val = intel_de_read(dev_priv, CNL_PORT_CL1CM_DW5);
-	val |= CL_POWER_DOWN_ENABLE;
-	intel_de_write(dev_priv, CNL_PORT_CL1CM_DW5, val);
-}
-
-static void cnl_combo_phys_uninit(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	if (!cnl_combo_phy_verify_state(dev_priv))
-		drm_warn(&dev_priv->drm,
-			 "Combo PHY HW state changed unexpectedly.\n");
-
-	val = intel_de_read(dev_priv, CHICKEN_MISC_2);
-	val |= CNL_COMP_PWR_DOWN;
-	intel_de_write(dev_priv, CHICKEN_MISC_2, val);
-}
-
 static bool has_phy_misc(struct drm_i915_private *i915, enum phy phy)
 {
 	/*
@@ -291,7 +231,7 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv,
 				     DCC_MODE_SELECT_CONTINUOSLY);
 	}
 
-	ret &= cnl_verify_procmon_ref_values(dev_priv, phy);
+	ret &= icl_verify_procmon_ref_values(dev_priv, phy);
 
 	if (phy_is_master(dev_priv, phy)) {
 		ret &= check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW8(phy),
@@ -415,7 +355,7 @@ skip_phy_misc:
 			intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy), val);
 		}
 
-		cnl_set_procmon_ref_values(dev_priv, phy);
+		icl_set_procmon_ref_values(dev_priv, phy);
 
 		if (phy_is_master(dev_priv, phy)) {
 			val = intel_de_read(dev_priv, ICL_PORT_COMP_DW8(phy));
@@ -474,16 +414,10 @@ skip_phy_misc:
 
 void intel_combo_phy_init(struct drm_i915_private *i915)
 {
-	if (DISPLAY_VER(i915) >= 11)
-		icl_combo_phys_init(i915);
-	else if (IS_CANNONLAKE(i915))
-		cnl_combo_phys_init(i915);
+	icl_combo_phys_init(i915);
 }
 
 void intel_combo_phy_uninit(struct drm_i915_private *i915)
 {
-	if (DISPLAY_VER(i915) >= 11)
-		icl_combo_phys_uninit(i915);
-	else if (IS_CANNONLAKE(i915))
-		cnl_combo_phys_uninit(i915);
+	icl_combo_phys_uninit(i915);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 648f1c0d3d39..408f82b0dc7d 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -38,6 +38,7 @@
 #include "intel_crt.h"
 #include "intel_crtc.h"
 #include "intel_ddi.h"
+#include "intel_ddi_buf_trans.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
 #include "intel_fdi.h"
@@ -1081,6 +1082,8 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 		crt->base.enable_clock = hsw_ddi_enable_clock;
 		crt->base.disable_clock = hsw_ddi_disable_clock;
 		crt->base.is_clock_enabled = hsw_ddi_is_clock_enabled;
+
+		intel_ddi_buf_trans_init(&crt->base);
 	} else {
 		if (HAS_PCH_SPLIT(dev_priv)) {
 			crt->base.compute_config = pch_crt_compute_config;
diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c
index 95ff1707b4bd..254e67141a77 100644
--- a/drivers/gpu/drm/i915/display/intel_crtc.c
+++ b/drivers/gpu/drm/i915/display/intel_crtc.c
@@ -163,12 +163,12 @@ static void intel_crtc_free(struct intel_crtc *crtc)
 	kfree(crtc);
 }
 
-static void intel_crtc_destroy(struct drm_crtc *crtc)
+static void intel_crtc_destroy(struct drm_crtc *_crtc)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_crtc *crtc = to_intel_crtc(_crtc);
 
-	drm_crtc_cleanup(crtc);
-	kfree(intel_crtc);
+	drm_crtc_cleanup(&crtc->base);
+	kfree(crtc);
 }
 
 static int intel_crtc_late_register(struct drm_crtc *crtc)
@@ -335,7 +335,7 @@ int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 		dev_priv->plane_to_crtc_mapping[i9xx_plane] = crtc;
 	}
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		drm_crtc_create_scaling_filter_property(&crtc->base,
 						BIT(DRM_SCALING_FILTER_DEFAULT) |
 						BIT(DRM_SCALING_FILTER_NEAREST_NEIGHBOR));
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 966e020331fb..c7618fef0143 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -383,7 +383,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	if (plane_state->hw.rotation & DRM_MODE_ROTATE_180)
 		cntl |= MCURSOR_ROTATE_180;
 
-	/* Wa_22012358565:adlp */
+	/* Wa_22012358565:adl-p */
 	if (DISPLAY_VER(dev_priv) == 13)
 		cntl |= MCURSOR_ARB_SLOTS(1);
 
@@ -629,12 +629,16 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 
 	/*
 	 * When crtc is inactive or there is a modeset pending,
-	 * wait for it to complete in the slowpath
+	 * wait for it to complete in the slowpath.
+	 * PSR2 selective fetch also requires the slow path as
+	 * PSR2 plane and transcoder registers can only be updated during
+	 * vblank.
 	 *
 	 * FIXME bigjoiner fastpath would be good
 	 */
 	if (!crtc_state->hw.active || intel_crtc_needs_modeset(crtc_state) ||
-	    crtc_state->update_pipe || crtc_state->bigjoiner)
+	    crtc_state->update_pipe || crtc_state->bigjoiner ||
+	    crtc_state->enable_psr2_sel_fetch)
 		goto slow;
 
 	/*
@@ -801,7 +805,7 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv,
 	if (DISPLAY_VER(dev_priv) >= 12)
 		drm_plane_enable_fb_damage_clips(&cursor->base);
 
-	drm_plane_helper_add(&cursor->base, &intel_plane_helper_funcs);
+	intel_plane_helper_add(cursor);
 
 	return cursor;
 
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 00dade49665b..9903a78df896 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -51,6 +51,7 @@
 #include "intel_panel.h"
 #include "intel_pps.h"
 #include "intel_psr.h"
+#include "intel_snps_phy.h"
 #include "intel_sprite.h"
 #include "intel_tc.h"
 #include "intel_vdsc.h"
@@ -95,24 +96,18 @@ static int intel_ddi_hdmi_level(struct intel_encoder *encoder,
  * values in advance. This function programs the correct values for
  * DP/eDP/FDI use cases.
  */
-void intel_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
-				  const struct intel_crtc_state *crtc_state)
+void hsw_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
+				const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 iboost_bit = 0;
 	int i, n_entries;
 	enum port port = encoder->port;
-	const struct ddi_buf_trans *ddi_translations;
-
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG))
-		ddi_translations = intel_ddi_get_buf_trans_fdi(dev_priv,
-							       &n_entries);
-	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		ddi_translations = intel_ddi_get_buf_trans_edp(encoder,
-							       &n_entries);
-	else
-		ddi_translations = intel_ddi_get_buf_trans_dp(encoder,
-							      &n_entries);
+	const struct intel_ddi_buf_trans *ddi_translations;
+
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
+	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
+		return;
 
 	/* If we're boosting the current, set bit 31 of trans1 */
 	if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv) &&
@@ -121,9 +116,9 @@ void intel_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
 
 	for (i = 0; i < n_entries; i++) {
 		intel_de_write(dev_priv, DDI_BUF_TRANS_LO(port, i),
-			       ddi_translations[i].trans1 | iboost_bit);
+			       ddi_translations->entries[i].hsw.trans1 | iboost_bit);
 		intel_de_write(dev_priv, DDI_BUF_TRANS_HI(port, i),
-			       ddi_translations[i].trans2);
+			       ddi_translations->entries[i].hsw.trans2);
 	}
 }
 
@@ -132,17 +127,17 @@ void intel_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
  * values in advance. This function programs the correct values for
  * HDMI/DVI use cases.
  */
-static void intel_prepare_hdmi_ddi_buffers(struct intel_encoder *encoder,
-					   int level)
+static void hsw_prepare_hdmi_ddi_buffers(struct intel_encoder *encoder,
+					 const struct intel_crtc_state *crtc_state,
+					 int level)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 iboost_bit = 0;
 	int n_entries;
 	enum port port = encoder->port;
-	const struct ddi_buf_trans *ddi_translations;
-
-	ddi_translations = intel_ddi_get_buf_trans_hdmi(encoder, &n_entries);
+	const struct intel_ddi_buf_trans *ddi_translations;
 
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 		return;
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
@@ -155,9 +150,9 @@ static void intel_prepare_hdmi_ddi_buffers(struct intel_encoder *encoder,
 
 	/* Entry 9 is for HDMI: */
 	intel_de_write(dev_priv, DDI_BUF_TRANS_LO(port, 9),
-		       ddi_translations[level].trans1 | iboost_bit);
+		       ddi_translations->entries[level].hsw.trans1 | iboost_bit);
 	intel_de_write(dev_priv, DDI_BUF_TRANS_HI(port, 9),
-		       ddi_translations[level].trans2);
+		       ddi_translations->entries[level].hsw.trans2);
 }
 
 void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
@@ -177,14 +172,18 @@ void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 static void intel_wait_ddi_buf_active(struct drm_i915_private *dev_priv,
 				      enum port port)
 {
+	int ret;
+
 	/* Wait > 518 usecs for DDI_BUF_CTL to be non idle */
 	if (DISPLAY_VER(dev_priv) < 10) {
 		usleep_range(518, 1000);
 		return;
 	}
 
-	if (wait_for_us(!(intel_de_read(dev_priv, DDI_BUF_CTL(port)) &
-			  DDI_BUF_IS_IDLE), 500))
+	ret = _wait_for(!(intel_de_read(dev_priv, DDI_BUF_CTL(port)) &
+			  DDI_BUF_IS_IDLE), IS_DG2(dev_priv) ? 1200 : 500, 10, 10);
+
+	if (ret)
 		drm_err(&dev_priv->drm, "Timeout waiting for DDI BUF %c to get active\n",
 			port_name(port));
 }
@@ -828,7 +827,7 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 static enum intel_display_power_domain
 intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port)
 {
-	/* CNL+ HW requires corresponding AUX IOs to be powered up for PSR with
+	/* ICL+ HW requires corresponding AUX IOs to be powered up for PSR with
 	 * DC states enabled at the same time, while for driver initiated AUX
 	 * transfers we need the same AUX IOs to be powered but with DC states
 	 * disabled. Accordingly use the AUX power domain here which leaves DC
@@ -948,22 +947,16 @@ static void skl_ddi_set_iboost(struct intel_encoder *encoder,
 		iboost = intel_bios_encoder_dp_boost_level(encoder->devdata);
 
 	if (iboost == 0) {
-		const struct ddi_buf_trans *ddi_translations;
+		const struct intel_ddi_buf_trans *ddi_translations;
 		int n_entries;
 
-		if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-			ddi_translations = intel_ddi_get_buf_trans_hdmi(encoder, &n_entries);
-		else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-			ddi_translations = intel_ddi_get_buf_trans_edp(encoder, &n_entries);
-		else
-			ddi_translations = intel_ddi_get_buf_trans_dp(encoder, &n_entries);
-
+		ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 		if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 			return;
 		if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
 			level = n_entries - 1;
 
-		iboost = ddi_translations[level].i_boost;
+		iboost = ddi_translations->entries[level].hsw.i_boost;
 	}
 
 	/* Make sure that the requested I_boost is valid */
@@ -983,21 +976,21 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder,
 				    int level)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	const struct bxt_ddi_buf_trans *ddi_translations;
+	const struct intel_ddi_buf_trans *ddi_translations;
 	enum port port = encoder->port;
 	int n_entries;
 
-	ddi_translations = bxt_get_buf_trans(encoder, crtc_state, &n_entries);
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 		return;
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
 		level = n_entries - 1;
 
 	bxt_ddi_phy_set_signal_level(dev_priv, port,
-				     ddi_translations[level].margin,
-				     ddi_translations[level].scale,
-				     ddi_translations[level].enable,
-				     ddi_translations[level].deemphasis);
+				     ddi_translations->entries[level].bxt.margin,
+				     ddi_translations->entries[level].bxt.scale,
+				     ddi_translations->entries[level].bxt.enable,
+				     ddi_translations->entries[level].bxt.deemphasis);
 }
 
 static u8 intel_ddi_dp_voltage_max(struct intel_dp *intel_dp,
@@ -1005,36 +998,9 @@ static u8 intel_ddi_dp_voltage_max(struct intel_dp *intel_dp,
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
-	enum phy phy = intel_port_to_phy(dev_priv, port);
 	int n_entries;
 
-	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (intel_phy_is_combo(dev_priv, phy))
-			tgl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-		else if (IS_ALDERLAKE_P(dev_priv))
-			adlp_get_dkl_buf_trans(encoder, crtc_state, &n_entries);
-		else
-			tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries);
-	} else if (DISPLAY_VER(dev_priv) == 11) {
-		if (IS_PLATFORM(dev_priv, INTEL_JASPERLAKE))
-			jsl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-		else if (IS_PLATFORM(dev_priv, INTEL_ELKHARTLAKE))
-			ehl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-		else if (intel_phy_is_combo(dev_priv, phy))
-			icl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-		else
-			icl_get_mg_buf_trans(encoder, crtc_state, &n_entries);
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		cnl_get_buf_trans(encoder, crtc_state, &n_entries);
-	} else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
-		bxt_get_buf_trans(encoder, crtc_state, &n_entries);
-	} else {
-		if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-			intel_ddi_get_buf_trans_edp(encoder, &n_entries);
-		else
-			intel_ddi_get_buf_trans_dp(encoder, &n_entries);
-	}
+	encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 
 	if (drm_WARN_ON(&dev_priv->drm, n_entries < 1))
 		n_entries = 1;
@@ -1056,146 +1022,17 @@ static u8 intel_ddi_dp_preemph_max(struct intel_dp *intel_dp)
 	return DP_TRAIN_PRE_EMPH_LEVEL_3;
 }
 
-static void cnl_ddi_vswing_program(struct intel_encoder *encoder,
-				   const struct intel_crtc_state *crtc_state,
-				   int level)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	const struct cnl_ddi_buf_trans *ddi_translations;
-	enum port port = encoder->port;
-	int n_entries, ln;
-	u32 val;
-
-	ddi_translations = cnl_get_buf_trans(encoder, crtc_state, &n_entries);
-
-	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
-		return;
-	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
-		level = n_entries - 1;
-
-	/* Set PORT_TX_DW5 Scaling Mode Sel to 010b. */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW5_LN0(port));
-	val &= ~SCALING_MODE_SEL_MASK;
-	val |= SCALING_MODE_SEL(2);
-	intel_de_write(dev_priv, CNL_PORT_TX_DW5_GRP(port), val);
-
-	/* Program PORT_TX_DW2 */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW2_LN0(port));
-	val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK |
-		 RCOMP_SCALAR_MASK);
-	val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel);
-	val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel);
-	/* Rcomp scalar is fixed as 0x98 for every table entry */
-	val |= RCOMP_SCALAR(0x98);
-	intel_de_write(dev_priv, CNL_PORT_TX_DW2_GRP(port), val);
-
-	/* Program PORT_TX_DW4 */
-	/* We cannot write to GRP. It would overrite individual loadgen */
-	for (ln = 0; ln < 4; ln++) {
-		val = intel_de_read(dev_priv, CNL_PORT_TX_DW4_LN(ln, port));
-		val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK |
-			 CURSOR_COEFF_MASK);
-		val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1);
-		val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2);
-		val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff);
-		intel_de_write(dev_priv, CNL_PORT_TX_DW4_LN(ln, port), val);
-	}
-
-	/* Program PORT_TX_DW5 */
-	/* All DW5 values are fixed for every table entry */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW5_LN0(port));
-	val &= ~RTERM_SELECT_MASK;
-	val |= RTERM_SELECT(6);
-	val |= TAP3_DISABLE;
-	intel_de_write(dev_priv, CNL_PORT_TX_DW5_GRP(port), val);
-
-	/* Program PORT_TX_DW7 */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW7_LN0(port));
-	val &= ~N_SCALAR_MASK;
-	val |= N_SCALAR(ddi_translations[level].dw7_n_scalar);
-	intel_de_write(dev_priv, CNL_PORT_TX_DW7_GRP(port), val);
-}
-
-static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder,
-				    const struct intel_crtc_state *crtc_state,
-				    int level)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
-	int width, rate, ln;
-	u32 val;
-
-	width = crtc_state->lane_count;
-	rate = crtc_state->port_clock;
-
-	/*
-	 * 1. If port type is eDP or DP,
-	 * set PORT_PCS_DW1 cmnkeeper_enable to 1b,
-	 * else clear to 0b.
-	 */
-	val = intel_de_read(dev_priv, CNL_PORT_PCS_DW1_LN0(port));
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		val &= ~COMMON_KEEPER_EN;
-	else
-		val |= COMMON_KEEPER_EN;
-	intel_de_write(dev_priv, CNL_PORT_PCS_DW1_GRP(port), val);
-
-	/* 2. Program loadgen select */
-	/*
-	 * Program PORT_TX_DW4_LN depending on Bit rate and used lanes
-	 * <= 6 GHz and 4 lanes (LN0=0, LN1=1, LN2=1, LN3=1)
-	 * <= 6 GHz and 1,2 lanes (LN0=0, LN1=1, LN2=1, LN3=0)
-	 * > 6 GHz (LN0=0, LN1=0, LN2=0, LN3=0)
-	 */
-	for (ln = 0; ln <= 3; ln++) {
-		val = intel_de_read(dev_priv, CNL_PORT_TX_DW4_LN(ln, port));
-		val &= ~LOADGEN_SELECT;
-
-		if ((rate <= 600000 && width == 4 && ln >= 1)  ||
-		    (rate <= 600000 && width < 4 && (ln == 1 || ln == 2))) {
-			val |= LOADGEN_SELECT;
-		}
-		intel_de_write(dev_priv, CNL_PORT_TX_DW4_LN(ln, port), val);
-	}
-
-	/* 3. Set PORT_CL_DW5 SUS Clock Config to 11b */
-	val = intel_de_read(dev_priv, CNL_PORT_CL1CM_DW5);
-	val |= SUS_CLOCK_CONFIG;
-	intel_de_write(dev_priv, CNL_PORT_CL1CM_DW5, val);
-
-	/* 4. Clear training enable to change swing values */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW5_LN0(port));
-	val &= ~TX_TRAINING_EN;
-	intel_de_write(dev_priv, CNL_PORT_TX_DW5_GRP(port), val);
-
-	/* 5. Program swing and de-emphasis */
-	cnl_ddi_vswing_program(encoder, crtc_state, level);
-
-	/* 6. Set training enable to trigger update */
-	val = intel_de_read(dev_priv, CNL_PORT_TX_DW5_LN0(port));
-	val |= TX_TRAINING_EN;
-	intel_de_write(dev_priv, CNL_PORT_TX_DW5_GRP(port), val);
-}
-
 static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder,
 					 const struct intel_crtc_state *crtc_state,
 					 int level)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	const struct cnl_ddi_buf_trans *ddi_translations;
+	const struct intel_ddi_buf_trans *ddi_translations;
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 	int n_entries, ln;
 	u32 val;
 
-	if (DISPLAY_VER(dev_priv) >= 12)
-		ddi_translations = tgl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-	else if (IS_PLATFORM(dev_priv, INTEL_JASPERLAKE))
-		ddi_translations = jsl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-	else if (IS_PLATFORM(dev_priv, INTEL_ELKHARTLAKE))
-		ddi_translations = ehl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-	else
-		ddi_translations = icl_get_combo_buf_trans(encoder, crtc_state, &n_entries);
-
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 		return;
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
@@ -1223,8 +1060,8 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder,
 	val = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN0(phy));
 	val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK |
 		 RCOMP_SCALAR_MASK);
-	val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel);
-	val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel);
+	val |= SWING_SEL_UPPER(ddi_translations->entries[level].icl.dw2_swing_sel);
+	val |= SWING_SEL_LOWER(ddi_translations->entries[level].icl.dw2_swing_sel);
 	/* Program Rcomp scalar for every table entry */
 	val |= RCOMP_SCALAR(0x98);
 	intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), val);
@@ -1235,16 +1072,16 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder,
 		val = intel_de_read(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy));
 		val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK |
 			 CURSOR_COEFF_MASK);
-		val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1);
-		val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2);
-		val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff);
+		val |= POST_CURSOR_1(ddi_translations->entries[level].icl.dw4_post_cursor_1);
+		val |= POST_CURSOR_2(ddi_translations->entries[level].icl.dw4_post_cursor_2);
+		val |= CURSOR_COEFF(ddi_translations->entries[level].icl.dw4_cursor_coeff);
 		intel_de_write(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), val);
 	}
 
 	/* Program PORT_TX_DW7 */
 	val = intel_de_read(dev_priv, ICL_PORT_TX_DW7_LN0(phy));
 	val &= ~N_SCALAR_MASK;
-	val |= N_SCALAR(ddi_translations[level].dw7_n_scalar);
+	val |= N_SCALAR(ddi_translations->entries[level].icl.dw7_n_scalar);
 	intel_de_write(dev_priv, ICL_PORT_TX_DW7_GRP(phy), val);
 }
 
@@ -1315,15 +1152,14 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
-	const struct icl_mg_phy_ddi_buf_trans *ddi_translations;
+	const struct intel_ddi_buf_trans *ddi_translations;
 	int n_entries, ln;
 	u32 val;
 
 	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
 		return;
 
-	ddi_translations = icl_get_mg_buf_trans(encoder, crtc_state, &n_entries);
-
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 		return;
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
@@ -1345,13 +1181,13 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 		val = intel_de_read(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port));
 		val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK;
 		val |= CRI_TXDEEMPH_OVERRIDE_17_12(
-			ddi_translations[level].cri_txdeemph_override_17_12);
+			ddi_translations->entries[level].mg.cri_txdeemph_override_17_12);
 		intel_de_write(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port), val);
 
 		val = intel_de_read(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port));
 		val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK;
 		val |= CRI_TXDEEMPH_OVERRIDE_17_12(
-			ddi_translations[level].cri_txdeemph_override_17_12);
+			ddi_translations->entries[level].mg.cri_txdeemph_override_17_12);
 		intel_de_write(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port), val);
 	}
 
@@ -1361,9 +1197,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 		val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK |
 			 CRI_TXDEEMPH_OVERRIDE_5_0_MASK);
 		val |= CRI_TXDEEMPH_OVERRIDE_5_0(
-			ddi_translations[level].cri_txdeemph_override_5_0) |
+			ddi_translations->entries[level].mg.cri_txdeemph_override_5_0) |
 			CRI_TXDEEMPH_OVERRIDE_11_6(
-				ddi_translations[level].cri_txdeemph_override_11_6) |
+				ddi_translations->entries[level].mg.cri_txdeemph_override_11_6) |
 			CRI_TXDEEMPH_OVERRIDE_EN;
 		intel_de_write(dev_priv, MG_TX1_DRVCTRL(ln, tc_port), val);
 
@@ -1371,9 +1207,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 		val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK |
 			 CRI_TXDEEMPH_OVERRIDE_5_0_MASK);
 		val |= CRI_TXDEEMPH_OVERRIDE_5_0(
-			ddi_translations[level].cri_txdeemph_override_5_0) |
+			ddi_translations->entries[level].mg.cri_txdeemph_override_5_0) |
 			CRI_TXDEEMPH_OVERRIDE_11_6(
-				ddi_translations[level].cri_txdeemph_override_11_6) |
+				ddi_translations->entries[level].mg.cri_txdeemph_override_11_6) |
 			CRI_TXDEEMPH_OVERRIDE_EN;
 		intel_de_write(dev_priv, MG_TX2_DRVCTRL(ln, tc_port), val);
 
@@ -1453,18 +1289,14 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
-	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
+	const struct intel_ddi_buf_trans *ddi_translations;
 	u32 val, dpcnt_mask, dpcnt_val;
 	int n_entries, ln;
 
 	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
 		return;
 
-	if (IS_ALDERLAKE_P(dev_priv))
-		ddi_translations = adlp_get_dkl_buf_trans(encoder, crtc_state, &n_entries);
-	else
-		ddi_translations = tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries);
-
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations))
 		return;
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries))
@@ -1473,9 +1305,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 	dpcnt_mask = (DKL_TX_PRESHOOT_COEFF_MASK |
 		      DKL_TX_DE_EMPAHSIS_COEFF_MASK |
 		      DKL_TX_VSWING_CONTROL_MASK);
-	dpcnt_val = DKL_TX_VSWING_CONTROL(ddi_translations[level].dkl_vswing_control);
-	dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(ddi_translations[level].dkl_de_emphasis_control);
-	dpcnt_val |= DKL_TX_PRESHOOT_COEFF(ddi_translations[level].dkl_preshoot_control);
+	dpcnt_val = DKL_TX_VSWING_CONTROL(ddi_translations->entries[level].dkl.dkl_vswing_control);
+	dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(ddi_translations->entries[level].dkl.dkl_de_emphasis_control);
+	dpcnt_val |= DKL_TX_PRESHOOT_COEFF(ddi_translations->entries[level].dkl.dkl_preshoot_control);
 
 	for (ln = 0; ln < 2; ln++) {
 		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
@@ -1549,33 +1381,33 @@ static int intel_ddi_dp_level(struct intel_dp *intel_dp)
 }
 
 static void
-tgl_set_signal_levels(struct intel_dp *intel_dp,
+dg2_set_signal_levels(struct intel_dp *intel_dp,
 		      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	tgl_ddi_vswing_sequence(encoder, crtc_state, level);
+	intel_snps_phy_ddi_vswing_sequence(encoder, level);
 }
 
 static void
-icl_set_signal_levels(struct intel_dp *intel_dp,
+tgl_set_signal_levels(struct intel_dp *intel_dp,
 		      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	icl_ddi_vswing_sequence(encoder, crtc_state, level);
+	tgl_ddi_vswing_sequence(encoder, crtc_state, level);
 }
 
 static void
-cnl_set_signal_levels(struct intel_dp *intel_dp,
+icl_set_signal_levels(struct intel_dp *intel_dp,
 		      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	cnl_ddi_vswing_sequence(encoder, crtc_state, level);
+	icl_ddi_vswing_sequence(encoder, crtc_state, level);
 }
 
 static void
@@ -1613,7 +1445,7 @@ hsw_set_signal_levels(struct intel_dp *intel_dp,
 	intel_de_posting_read(dev_priv, DDI_BUF_CTL(port));
 }
 
-static void _cnl_ddi_enable_clock(struct drm_i915_private *i915, i915_reg_t reg,
+static void _icl_ddi_enable_clock(struct drm_i915_private *i915, i915_reg_t reg,
 				  u32 clk_sel_mask, u32 clk_sel, u32 clk_off)
 {
 	mutex_lock(&i915->dpll.lock);
@@ -1629,7 +1461,7 @@ static void _cnl_ddi_enable_clock(struct drm_i915_private *i915, i915_reg_t reg,
 	mutex_unlock(&i915->dpll.lock);
 }
 
-static void _cnl_ddi_disable_clock(struct drm_i915_private *i915, i915_reg_t reg,
+static void _icl_ddi_disable_clock(struct drm_i915_private *i915, i915_reg_t reg,
 				   u32 clk_off)
 {
 	mutex_lock(&i915->dpll.lock);
@@ -1639,14 +1471,14 @@ static void _cnl_ddi_disable_clock(struct drm_i915_private *i915, i915_reg_t reg
 	mutex_unlock(&i915->dpll.lock);
 }
 
-static bool _cnl_ddi_is_clock_enabled(struct drm_i915_private *i915, i915_reg_t reg,
+static bool _icl_ddi_is_clock_enabled(struct drm_i915_private *i915, i915_reg_t reg,
 				      u32 clk_off)
 {
 	return !(intel_de_read(i915, reg) & clk_off);
 }
 
 static struct intel_shared_dpll *
-_cnl_ddi_get_pll(struct drm_i915_private *i915, i915_reg_t reg,
+_icl_ddi_get_pll(struct drm_i915_private *i915, i915_reg_t reg,
 		 u32 clk_sel_mask, u32 clk_sel_shift)
 {
 	enum intel_dpll_id id;
@@ -1666,7 +1498,7 @@ static void adls_ddi_enable_clock(struct intel_encoder *encoder,
 	if (drm_WARN_ON(&i915->drm, !pll))
 		return;
 
-	_cnl_ddi_enable_clock(i915, ADLS_DPCLKA_CFGCR(phy),
+	_icl_ddi_enable_clock(i915, ADLS_DPCLKA_CFGCR(phy),
 			      ADLS_DPCLKA_CFGCR_DDI_CLK_SEL_MASK(phy),
 			      pll->info->id << ADLS_DPCLKA_CFGCR_DDI_SHIFT(phy),
 			      ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
@@ -1677,7 +1509,7 @@ static void adls_ddi_disable_clock(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	_cnl_ddi_disable_clock(i915, ADLS_DPCLKA_CFGCR(phy),
+	_icl_ddi_disable_clock(i915, ADLS_DPCLKA_CFGCR(phy),
 			       ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1686,7 +1518,7 @@ static bool adls_ddi_is_clock_enabled(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_is_clock_enabled(i915, ADLS_DPCLKA_CFGCR(phy),
+	return _icl_ddi_is_clock_enabled(i915, ADLS_DPCLKA_CFGCR(phy),
 					 ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1695,7 +1527,7 @@ static struct intel_shared_dpll *adls_ddi_get_pll(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_get_pll(i915, ADLS_DPCLKA_CFGCR(phy),
+	return _icl_ddi_get_pll(i915, ADLS_DPCLKA_CFGCR(phy),
 				ADLS_DPCLKA_CFGCR_DDI_CLK_SEL_MASK(phy),
 				ADLS_DPCLKA_CFGCR_DDI_SHIFT(phy));
 }
@@ -1710,7 +1542,7 @@ static void rkl_ddi_enable_clock(struct intel_encoder *encoder,
 	if (drm_WARN_ON(&i915->drm, !pll))
 		return;
 
-	_cnl_ddi_enable_clock(i915, ICL_DPCLKA_CFGCR0,
+	_icl_ddi_enable_clock(i915, ICL_DPCLKA_CFGCR0,
 			      RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy),
 			      RKL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy),
 			      RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
@@ -1721,7 +1553,7 @@ static void rkl_ddi_disable_clock(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	_cnl_ddi_disable_clock(i915, ICL_DPCLKA_CFGCR0,
+	_icl_ddi_disable_clock(i915, ICL_DPCLKA_CFGCR0,
 			       RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1730,7 +1562,7 @@ static bool rkl_ddi_is_clock_enabled(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_is_clock_enabled(i915, ICL_DPCLKA_CFGCR0,
+	return _icl_ddi_is_clock_enabled(i915, ICL_DPCLKA_CFGCR0,
 					 RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1739,7 +1571,7 @@ static struct intel_shared_dpll *rkl_ddi_get_pll(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_get_pll(i915, ICL_DPCLKA_CFGCR0,
+	return _icl_ddi_get_pll(i915, ICL_DPCLKA_CFGCR0,
 				RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy),
 				RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy));
 }
@@ -1763,7 +1595,7 @@ static void dg1_ddi_enable_clock(struct intel_encoder *encoder,
 			(pll->info->id >= DPLL_ID_DG1_DPLL2 && phy < PHY_C)))
 		return;
 
-	_cnl_ddi_enable_clock(i915, DG1_DPCLKA_CFGCR0(phy),
+	_icl_ddi_enable_clock(i915, DG1_DPCLKA_CFGCR0(phy),
 			      DG1_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy),
 			      DG1_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy),
 			      DG1_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
@@ -1774,7 +1606,7 @@ static void dg1_ddi_disable_clock(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	_cnl_ddi_disable_clock(i915, DG1_DPCLKA_CFGCR0(phy),
+	_icl_ddi_disable_clock(i915, DG1_DPCLKA_CFGCR0(phy),
 			       DG1_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1783,7 +1615,7 @@ static bool dg1_ddi_is_clock_enabled(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_is_clock_enabled(i915, DG1_DPCLKA_CFGCR0(phy),
+	return _icl_ddi_is_clock_enabled(i915, DG1_DPCLKA_CFGCR0(phy),
 					 DG1_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1820,7 +1652,7 @@ static void icl_ddi_combo_enable_clock(struct intel_encoder *encoder,
 	if (drm_WARN_ON(&i915->drm, !pll))
 		return;
 
-	_cnl_ddi_enable_clock(i915, ICL_DPCLKA_CFGCR0,
+	_icl_ddi_enable_clock(i915, ICL_DPCLKA_CFGCR0,
 			      ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy),
 			      ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy),
 			      ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
@@ -1831,7 +1663,7 @@ static void icl_ddi_combo_disable_clock(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	_cnl_ddi_disable_clock(i915, ICL_DPCLKA_CFGCR0,
+	_icl_ddi_disable_clock(i915, ICL_DPCLKA_CFGCR0,
 			       ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1840,7 +1672,7 @@ static bool icl_ddi_combo_is_clock_enabled(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_is_clock_enabled(i915, ICL_DPCLKA_CFGCR0,
+	return _icl_ddi_is_clock_enabled(i915, ICL_DPCLKA_CFGCR0,
 					 ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy));
 }
 
@@ -1849,7 +1681,7 @@ struct intel_shared_dpll *icl_ddi_combo_get_pll(struct intel_encoder *encoder)
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
-	return _cnl_ddi_get_pll(i915, ICL_DPCLKA_CFGCR0,
+	return _icl_ddi_get_pll(i915, ICL_DPCLKA_CFGCR0,
 				ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy),
 				ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy));
 }
@@ -1982,50 +1814,6 @@ static struct intel_shared_dpll *icl_ddi_tc_get_pll(struct intel_encoder *encode
 	return intel_get_shared_dpll_by_id(i915, id);
 }
 
-static void cnl_ddi_enable_clock(struct intel_encoder *encoder,
-				 const struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
-	const struct intel_shared_dpll *pll = crtc_state->shared_dpll;
-	enum port port = encoder->port;
-
-	if (drm_WARN_ON(&i915->drm, !pll))
-		return;
-
-	_cnl_ddi_enable_clock(i915, DPCLKA_CFGCR0,
-			      DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port),
-			      DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port),
-			      DPCLKA_CFGCR0_DDI_CLK_OFF(port));
-}
-
-static void cnl_ddi_disable_clock(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
-
-	_cnl_ddi_disable_clock(i915, DPCLKA_CFGCR0,
-			       DPCLKA_CFGCR0_DDI_CLK_OFF(port));
-}
-
-static bool cnl_ddi_is_clock_enabled(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
-
-	return _cnl_ddi_is_clock_enabled(i915, DPCLKA_CFGCR0,
-					 DPCLKA_CFGCR0_DDI_CLK_OFF(port));
-}
-
-static struct intel_shared_dpll *cnl_ddi_get_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
-
-	return _cnl_ddi_get_pll(i915, DPCLKA_CFGCR0,
-				DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port),
-				DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port));
-}
-
 static struct intel_shared_dpll *bxt_ddi_get_pll(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
@@ -2249,7 +2037,7 @@ void intel_ddi_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 		ddi_clk_needed = false;
 	}
 
-	if (ddi_clk_needed || !encoder->disable_clock ||
+	if (ddi_clk_needed || !encoder->is_clock_enabled ||
 	    !encoder->is_clock_enabled(encoder))
 		return;
 
@@ -2534,6 +2322,116 @@ static void intel_ddi_mso_configure(const struct intel_crtc_state *crtc_state)
 		     OVERLAP_PIXELS_MASK, dss1);
 }
 
+static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
+	int level = intel_ddi_dp_level(intel_dp);
+
+	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
+				 crtc_state->lane_count);
+
+	/*
+	 * 1. Enable Power Wells
+	 *
+	 * This was handled at the beginning of intel_atomic_commit_tail(),
+	 * before we called down into this function.
+	 */
+
+	/* 2. Enable Panel Power if PPS is required */
+	intel_pps_on(intel_dp);
+
+	/*
+	 * 3. Enable the port PLL.
+	 */
+	intel_ddi_enable_clock(encoder, crtc_state);
+
+	/* 4. Enable IO power */
+	if (!intel_phy_is_tc(dev_priv, phy) ||
+	    dig_port->tc_mode != TC_PORT_TBT_ALT)
+		dig_port->ddi_io_wakeref = intel_display_power_get(dev_priv,
+								   dig_port->ddi_io_power_domain);
+
+	/*
+	 * 5. The rest of the below are substeps under the bspec's "Enable and
+	 * Train Display Port" step.  Note that steps that are specific to
+	 * MST will be handled by intel_mst_pre_enable_dp() before/after it
+	 * calls into this function.  Also intel_mst_pre_enable_dp() only calls
+	 * us when active_mst_links==0, so any steps designated for "single
+	 * stream or multi-stream master transcoder" can just be performed
+	 * unconditionally here.
+	 */
+
+	/*
+	 * 5.a Configure Transcoder Clock Select to direct the Port clock to the
+	 * Transcoder.
+	 */
+	intel_ddi_enable_pipe_clock(encoder, crtc_state);
+
+	/* 5.b Not relevant to i915 for now */
+
+	/*
+	 * 5.c Configure TRANS_DDI_FUNC_CTL DDI Select, DDI Mode Select & MST
+	 * Transport Select
+	 */
+	intel_ddi_config_transcoder_func(encoder, crtc_state);
+
+	/*
+	 * 5.d Configure & enable DP_TP_CTL with link training pattern 1
+	 * selected
+	 *
+	 * This will be handled by the intel_dp_start_link_train() farther
+	 * down this function.
+	 */
+
+	/* 5.e Configure voltage swing and related IO settings */
+	intel_snps_phy_ddi_vswing_sequence(encoder, level);
+
+	/*
+	 * 5.f Configure and enable DDI_BUF_CTL
+	 * 5.g Wait for DDI_BUF_CTL DDI Idle Status = 0b (Not Idle), timeout
+	 *     after 1200 us.
+	 *
+	 * We only configure what the register value will be here.  Actual
+	 * enabling happens during link training farther down.
+	 */
+	intel_ddi_init_dp_buf_reg(encoder, crtc_state);
+
+	if (!is_mst)
+		intel_dp_set_power(intel_dp, DP_SET_POWER_D0);
+
+	intel_dp_sink_set_decompression_state(intel_dp, crtc_state, true);
+	/*
+	 * DDI FEC: "anticipates enabling FEC encoding sets the FEC_READY bit
+	 * in the FEC_CONFIGURATION register to 1 before initiating link
+	 * training
+	 */
+	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
+
+	/*
+	 * 5.h Follow DisplayPort specification training sequence (see notes for
+	 *     failure handling)
+	 * 5.i If DisplayPort multi-stream - Set DP_TP_CTL link training to Idle
+	 *     Pattern, wait for 5 idle patterns (DP_TP_STATUS Min_Idles_Sent)
+	 *     (timeout after 800 us)
+	 */
+	intel_dp_start_link_train(intel_dp, crtc_state);
+
+	/* 5.j Set DP_TP_CTL link training to Normal */
+	if (!is_trans_port_sync_mode(crtc_state))
+		intel_dp_stop_link_train(intel_dp, crtc_state);
+
+	/* 5.k Configure and enable FEC if needed */
+	intel_ddi_enable_fec(encoder, crtc_state);
+	intel_dsc_enable(encoder, crtc_state);
+}
+
 static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state,
 				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
@@ -2714,12 +2612,10 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state,
 
 	if (DISPLAY_VER(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state, level);
-	else if (IS_CANNONLAKE(dev_priv))
-		cnl_ddi_vswing_sequence(encoder, crtc_state, level);
 	else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		bxt_ddi_vswing_sequence(encoder, crtc_state, level);
 	else
-		intel_prepare_dp_ddi_buffers(encoder, crtc_state);
+		hsw_prepare_dp_ddi_buffers(encoder, crtc_state);
 
 	intel_ddi_power_up_lanes(encoder, crtc_state);
 
@@ -2751,7 +2647,9 @@ static void intel_ddi_pre_enable_dp(struct intel_atomic_state *state,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (DISPLAY_VER(dev_priv) >= 12)
+	if (IS_DG2(dev_priv))
+		dg2_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state);
+	else if (DISPLAY_VER(dev_priv) >= 12)
 		tgl_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state);
 	else
 		hsw_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state);
@@ -2827,6 +2725,7 @@ static void intel_ddi_pre_enable(struct intel_atomic_state *state,
 					conn_state);
 
 		/* FIXME precompute everything properly */
+		/* FIXME how do we turn infoframes off again? */
 		if (dig_port->lspcon.active && dig_port->dp.has_hdmi_sink)
 			dig_port->set_infoframes(encoder,
 						 crtc_state->has_infoframe,
@@ -3157,16 +3056,16 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state,
 			    "[CONNECTOR:%d:%s] Failed to configure sink scrambling/TMDS bit clock ratio\n",
 			    connector->base.id, connector->name);
 
-	if (DISPLAY_VER(dev_priv) >= 12)
+	if (IS_DG2(dev_priv))
+		intel_snps_phy_ddi_vswing_sequence(encoder, U32_MAX);
+	else if (DISPLAY_VER(dev_priv) >= 12)
 		tgl_ddi_vswing_sequence(encoder, crtc_state, level);
 	else if (DISPLAY_VER(dev_priv) == 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state, level);
-	else if (IS_CANNONLAKE(dev_priv))
-		cnl_ddi_vswing_sequence(encoder, crtc_state, level);
 	else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		bxt_ddi_vswing_sequence(encoder, crtc_state, level);
 	else
-		intel_prepare_hdmi_ddi_buffers(encoder, level);
+		hsw_prepare_hdmi_ddi_buffers(encoder, crtc_state, level);
 
 	if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv))
 		skl_ddi_set_iboost(encoder, crtc_state, level);
@@ -3260,12 +3159,6 @@ static void intel_disable_ddi_dp(struct intel_atomic_state *state,
 
 	intel_dp->link_trained = false;
 
-	if (old_crtc_state->has_audio)
-		intel_audio_codec_disable(encoder,
-					  old_crtc_state, old_conn_state);
-
-	intel_edp_drrs_disable(intel_dp, old_crtc_state);
-	intel_psr_disable(intel_dp, old_crtc_state);
 	intel_edp_backlight_off(old_conn_state);
 	/* Disable the decompression in DP Sink */
 	intel_dp_sink_set_decompression_state(intel_dp, old_crtc_state,
@@ -3283,10 +3176,6 @@ static void intel_disable_ddi_hdmi(struct intel_atomic_state *state,
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct drm_connector *connector = old_conn_state->connector;
 
-	if (old_crtc_state->has_audio)
-		intel_audio_codec_disable(encoder,
-					  old_crtc_state, old_conn_state);
-
 	if (!intel_hdmi_handle_sink_scrambling(encoder, connector,
 					       false, false))
 		drm_dbg_kms(&i915->drm,
@@ -3294,6 +3183,25 @@ static void intel_disable_ddi_hdmi(struct intel_atomic_state *state,
 			    connector->base.id, connector->name);
 }
 
+static void intel_pre_disable_ddi(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
+				  const struct intel_crtc_state *old_crtc_state,
+				  const struct drm_connector_state *old_conn_state)
+{
+	struct intel_dp *intel_dp;
+
+	if (old_crtc_state->has_audio)
+		intel_audio_codec_disable(encoder, old_crtc_state,
+					  old_conn_state);
+
+	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI))
+		return;
+
+	intel_dp = enc_to_intel_dp(encoder);
+	intel_edp_drrs_disable(intel_dp, old_crtc_state);
+	intel_psr_disable(intel_dp, old_crtc_state);
+}
+
 static void intel_disable_ddi(struct intel_atomic_state *state,
 			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
@@ -3510,7 +3418,7 @@ static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
 	if (cpu_transcoder == TRANSCODER_EDP)
 		return false;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO))
+	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO_MMIO))
 		return false;
 
 	return intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD) &
@@ -3526,8 +3434,6 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 		crtc_state->min_voltage_level = 3;
 	else if (DISPLAY_VER(dev_priv) >= 11 && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 1;
-	else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
-		crtc_state->min_voltage_level = 2;
 }
 
 static enum transcoder bdw_transcoder_master_readout(struct drm_i915_private *dev_priv,
@@ -3594,7 +3500,7 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	u32 temp, flags = 0;
@@ -3657,7 +3563,7 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
 			pipe_config->output_types |= BIT(INTEL_OUTPUT_DP);
 		pipe_config->lane_count =
 			((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
-		intel_dp_get_m_n(intel_crtc, pipe_config);
+		intel_dp_get_m_n(crtc, pipe_config);
 
 		if (DISPLAY_VER(dev_priv) >= 11) {
 			i915_reg_t dp_tp_ctl = dp_tp_ctl_reg(encoder, pipe_config);
@@ -3687,7 +3593,7 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
 			pipe_config->mst_master_transcoder =
 					REG_FIELD_GET(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, temp);
 
-		intel_dp_get_m_n(intel_crtc, pipe_config);
+		intel_dp_get_m_n(crtc, pipe_config);
 
 		pipe_config->infoframes.enable |=
 			intel_hdmi_infoframes_enabled(encoder, pipe_config);
@@ -3801,6 +3707,15 @@ void intel_ddi_get_clock(struct intel_encoder *encoder,
 						     &crtc_state->dpll_hw_state);
 }
 
+static void dg2_ddi_get_config(struct intel_encoder *encoder,
+				struct intel_crtc_state *crtc_state)
+{
+	intel_mpllb_readout_hw_state(encoder, &crtc_state->mpllb_state);
+	crtc_state->port_clock = intel_mpllb_calc_port_clock(encoder, &crtc_state->mpllb_state);
+
+	intel_ddi_get_config(encoder, crtc_state);
+}
+
 static void adls_ddi_get_config(struct intel_encoder *encoder,
 				struct intel_crtc_state *crtc_state)
 {
@@ -3868,13 +3783,6 @@ static void icl_ddi_tc_get_config(struct intel_encoder *encoder,
 	intel_ddi_get_config(encoder, crtc_state);
 }
 
-static void cnl_ddi_get_config(struct intel_encoder *encoder,
-			       struct intel_crtc_state *crtc_state)
-{
-	intel_ddi_get_clock(encoder, crtc_state, cnl_ddi_get_pll(encoder));
-	intel_ddi_get_config(encoder, crtc_state);
-}
-
 static void bxt_ddi_get_config(struct intel_encoder *encoder,
 			       struct intel_crtc_state *crtc_state)
 {
@@ -4121,12 +4029,12 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
 	dig_port->dp.set_link_train = intel_ddi_set_link_train;
 	dig_port->dp.set_idle_link_train = intel_ddi_set_idle_link_train;
 
-	if (DISPLAY_VER(dev_priv) >= 12)
+	if (IS_DG2(dev_priv))
+		dig_port->dp.set_signal_levels = dg2_set_signal_levels;
+	else if (DISPLAY_VER(dev_priv) >= 12)
 		dig_port->dp.set_signal_levels = tgl_set_signal_levels;
 	else if (DISPLAY_VER(dev_priv) >= 11)
 		dig_port->dp.set_signal_levels = icl_set_signal_levels;
-	else if (IS_CANNONLAKE(dev_priv))
-		dig_port->dp.set_signal_levels = cnl_set_signal_levels;
 	else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		dig_port->dp.set_signal_levels = bxt_set_signal_levels;
 	else
@@ -4373,15 +4281,6 @@ static bool intel_ddi_a_force_4_lanes(struct intel_digital_port *dig_port)
 	if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		return true;
 
-	/* Cannonlake: Most of SKUs don't support DDI_E, and the only
-	 *             one who does also have a full A/E split called
-	 *             DDI_F what makes DDI_E useless. However for this
-	 *             case let's trust VBT info.
-	 */
-	if (IS_CANNONLAKE(dev_priv) &&
-	    !intel_bios_is_port_present(dev_priv, PORT_E))
-		return true;
-
 	return false;
 }
 
@@ -4486,15 +4385,6 @@ static enum hpd_pin ehl_hpd_pin(struct drm_i915_private *dev_priv,
 	return HPD_PORT_A + port - PORT_A;
 }
 
-static enum hpd_pin cnl_hpd_pin(struct drm_i915_private *dev_priv,
-				enum port port)
-{
-	if (port == PORT_F)
-		return HPD_PORT_E;
-
-	return HPD_PORT_A + port - PORT_A;
-}
-
 static enum hpd_pin skl_hpd_pin(struct drm_i915_private *dev_priv, enum port port)
 {
 	if (HAS_PCH_TGP(dev_priv))
@@ -4513,6 +4403,36 @@ static bool intel_ddi_is_tc(struct drm_i915_private *i915, enum port port)
 		return false;
 }
 
+static void intel_ddi_encoder_suspend(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+
+	intel_dp_encoder_suspend(encoder);
+
+	if (!intel_phy_is_tc(i915, phy))
+		return;
+
+	intel_tc_port_disconnect_phy(dig_port);
+}
+
+static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+
+	intel_dp_encoder_shutdown(encoder);
+
+	if (!intel_phy_is_tc(i915, phy))
+		return;
+
+	intel_tc_port_disconnect_phy(dig_port);
+}
+
 #define port_tc_name(port) ((port) - PORT_TC1 + '1')
 #define tc_port_name(tc_port) ((tc_port) - TC_PORT_1 + '1')
 
@@ -4616,14 +4536,15 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	encoder->enable = intel_enable_ddi;
 	encoder->pre_pll_enable = intel_ddi_pre_pll_enable;
 	encoder->pre_enable = intel_ddi_pre_enable;
+	encoder->pre_disable = intel_pre_disable_ddi;
 	encoder->disable = intel_disable_ddi;
 	encoder->post_disable = intel_ddi_post_disable;
 	encoder->update_pipe = intel_ddi_update_pipe;
 	encoder->get_hw_state = intel_ddi_get_hw_state;
 	encoder->sync_state = intel_ddi_sync_state;
 	encoder->initial_fastset_check = intel_ddi_initial_fastset_check;
-	encoder->suspend = intel_dp_encoder_suspend;
-	encoder->shutdown = intel_dp_encoder_shutdown;
+	encoder->suspend = intel_ddi_encoder_suspend;
+	encoder->shutdown = intel_ddi_encoder_shutdown;
 	encoder->get_power_domains = intel_ddi_get_power_domains;
 
 	encoder->type = INTEL_OUTPUT_DDI;
@@ -4632,7 +4553,11 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	encoder->cloneable = 0;
 	encoder->pipe_mask = ~0;
 
-	if (IS_ALDERLAKE_S(dev_priv)) {
+	if (IS_DG2(dev_priv)) {
+		encoder->enable_clock = intel_mpllb_enable;
+		encoder->disable_clock = intel_mpllb_disable;
+		encoder->get_config = dg2_ddi_get_config;
+	} else if (IS_ALDERLAKE_S(dev_priv)) {
 		encoder->enable_clock = adls_ddi_enable_clock;
 		encoder->disable_clock = adls_ddi_disable_clock;
 		encoder->is_clock_enabled = adls_ddi_is_clock_enabled;
@@ -4671,11 +4596,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 			encoder->is_clock_enabled = icl_ddi_combo_is_clock_enabled;
 			encoder->get_config = icl_ddi_combo_get_config;
 		}
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		encoder->enable_clock = cnl_ddi_enable_clock;
-		encoder->disable_clock = cnl_ddi_disable_clock;
-		encoder->is_clock_enabled = cnl_ddi_is_clock_enabled;
-		encoder->get_config = cnl_ddi_get_config;
 	} else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
 		/* BXT/GLK have fixed PLL->port mapping */
 		encoder->get_config = bxt_ddi_get_config;
@@ -4691,6 +4611,8 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 		encoder->get_config = hsw_ddi_get_config;
 	}
 
+	intel_ddi_buf_trans_init(encoder);
+
 	if (DISPLAY_VER(dev_priv) >= 13)
 		encoder->hpd_pin = xelpd_hpd_pin(dev_priv, port);
 	else if (IS_DG1(dev_priv))
@@ -4703,8 +4625,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 		encoder->hpd_pin = ehl_hpd_pin(dev_priv, port);
 	else if (DISPLAY_VER(dev_priv) == 11)
 		encoder->hpd_pin = icl_hpd_pin(dev_priv, port);
-	else if (IS_CANNONLAKE(dev_priv))
-		encoder->hpd_pin = cnl_hpd_pin(dev_priv, port);
 	else if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv))
 		encoder->hpd_pin = skl_hpd_pin(dev_priv, port);
 	else
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h
index 59c6b01d4199..7d448485d887 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi.h
@@ -40,8 +40,8 @@ bool hsw_ddi_is_clock_enabled(struct intel_encoder *encoder);
 void hsw_ddi_get_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *crtc_state);
 struct intel_shared_dpll *icl_ddi_combo_get_pll(struct intel_encoder *encoder);
-void intel_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
-				  const struct intel_crtc_state *crtc_state);
+void hsw_prepare_dp_ddi_buffers(struct intel_encoder *encoder,
+				const struct intel_crtc_state *crtc_state);
 void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 			     enum port port);
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
index 8bfd00f49f2a..ba2c08f1a797 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
@@ -13,1095 +13,1160 @@
  * them for both DP and FDI transports, allowing those ports to
  * automatically adapt to HDMI connections as well
  */
-static const struct ddi_buf_trans hsw_ddi_translations_dp[] = {
-	{ 0x00FFFFFF, 0x0006000E, 0x0 },
-	{ 0x00D75FFF, 0x0005000A, 0x0 },
-	{ 0x00C30FFF, 0x00040006, 0x0 },
-	{ 0x80AAAFFF, 0x000B0000, 0x0 },
-	{ 0x00FFFFFF, 0x0005000A, 0x0 },
-	{ 0x00D75FFF, 0x000C0004, 0x0 },
-	{ 0x80C30FFF, 0x000B0000, 0x0 },
-	{ 0x00FFFFFF, 0x00040006, 0x0 },
-	{ 0x80D75FFF, 0x000B0000, 0x0 },
-};
-
-static const struct ddi_buf_trans hsw_ddi_translations_fdi[] = {
-	{ 0x00FFFFFF, 0x0007000E, 0x0 },
-	{ 0x00D75FFF, 0x000F000A, 0x0 },
-	{ 0x00C30FFF, 0x00060006, 0x0 },
-	{ 0x00AAAFFF, 0x001E0000, 0x0 },
-	{ 0x00FFFFFF, 0x000F000A, 0x0 },
-	{ 0x00D75FFF, 0x00160004, 0x0 },
-	{ 0x00C30FFF, 0x001E0000, 0x0 },
-	{ 0x00FFFFFF, 0x00060006, 0x0 },
-	{ 0x00D75FFF, 0x001E0000, 0x0 },
-};
-
-static const struct ddi_buf_trans hsw_ddi_translations_hdmi[] = {
-					/* Idx	NT mV d	T mV d	db	*/
-	{ 0x00FFFFFF, 0x0006000E, 0x0 },/* 0:	400	400	0	*/
-	{ 0x00E79FFF, 0x000E000C, 0x0 },/* 1:	400	500	2	*/
-	{ 0x00D75FFF, 0x0005000A, 0x0 },/* 2:	400	600	3.5	*/
-	{ 0x00FFFFFF, 0x0005000A, 0x0 },/* 3:	600	600	0	*/
-	{ 0x00E79FFF, 0x001D0007, 0x0 },/* 4:	600	750	2	*/
-	{ 0x00D75FFF, 0x000C0004, 0x0 },/* 5:	600	900	3.5	*/
-	{ 0x00FFFFFF, 0x00040006, 0x0 },/* 6:	800	800	0	*/
-	{ 0x80E79FFF, 0x00030002, 0x0 },/* 7:	800	1000	2	*/
-	{ 0x00FFFFFF, 0x00140005, 0x0 },/* 8:	850	850	0	*/
-	{ 0x00FFFFFF, 0x000C0004, 0x0 },/* 9:	900	900	0	*/
-	{ 0x00FFFFFF, 0x001C0003, 0x0 },/* 10:	950	950	0	*/
-	{ 0x80FFFFFF, 0x00030002, 0x0 },/* 11:	1000	1000	0	*/
-};
-
-static const struct ddi_buf_trans bdw_ddi_translations_edp[] = {
-	{ 0x00FFFFFF, 0x00000012, 0x0 },
-	{ 0x00EBAFFF, 0x00020011, 0x0 },
-	{ 0x00C71FFF, 0x0006000F, 0x0 },
-	{ 0x00AAAFFF, 0x000E000A, 0x0 },
-	{ 0x00FFFFFF, 0x00020011, 0x0 },
-	{ 0x00DB6FFF, 0x0005000F, 0x0 },
-	{ 0x00BEEFFF, 0x000A000C, 0x0 },
-	{ 0x00FFFFFF, 0x0005000F, 0x0 },
-	{ 0x00DB6FFF, 0x000A000C, 0x0 },
-};
-
-static const struct ddi_buf_trans bdw_ddi_translations_dp[] = {
-	{ 0x00FFFFFF, 0x0007000E, 0x0 },
-	{ 0x00D75FFF, 0x000E000A, 0x0 },
-	{ 0x00BEFFFF, 0x00140006, 0x0 },
-	{ 0x80B2CFFF, 0x001B0002, 0x0 },
-	{ 0x00FFFFFF, 0x000E000A, 0x0 },
-	{ 0x00DB6FFF, 0x00160005, 0x0 },
-	{ 0x80C71FFF, 0x001A0002, 0x0 },
-	{ 0x00F7DFFF, 0x00180004, 0x0 },
-	{ 0x80D75FFF, 0x001B0002, 0x0 },
-};
-
-static const struct ddi_buf_trans bdw_ddi_translations_fdi[] = {
-	{ 0x00FFFFFF, 0x0001000E, 0x0 },
-	{ 0x00D75FFF, 0x0004000A, 0x0 },
-	{ 0x00C30FFF, 0x00070006, 0x0 },
-	{ 0x00AAAFFF, 0x000C0000, 0x0 },
-	{ 0x00FFFFFF, 0x0004000A, 0x0 },
-	{ 0x00D75FFF, 0x00090004, 0x0 },
-	{ 0x00C30FFF, 0x000C0000, 0x0 },
-	{ 0x00FFFFFF, 0x00070006, 0x0 },
-	{ 0x00D75FFF, 0x000C0000, 0x0 },
-};
-
-static const struct ddi_buf_trans bdw_ddi_translations_hdmi[] = {
-					/* Idx	NT mV d	T mV df	db	*/
-	{ 0x00FFFFFF, 0x0007000E, 0x0 },/* 0:	400	400	0	*/
-	{ 0x00D75FFF, 0x000E000A, 0x0 },/* 1:	400	600	3.5	*/
-	{ 0x00BEFFFF, 0x00140006, 0x0 },/* 2:	400	800	6	*/
-	{ 0x00FFFFFF, 0x0009000D, 0x0 },/* 3:	450	450	0	*/
-	{ 0x00FFFFFF, 0x000E000A, 0x0 },/* 4:	600	600	0	*/
-	{ 0x00D7FFFF, 0x00140006, 0x0 },/* 5:	600	800	2.5	*/
-	{ 0x80CB2FFF, 0x001B0002, 0x0 },/* 6:	600	1000	4.5	*/
-	{ 0x00FFFFFF, 0x00140006, 0x0 },/* 7:	800	800	0	*/
-	{ 0x80E79FFF, 0x001B0002, 0x0 },/* 8:	800	1000	2	*/
-	{ 0x80FFFFFF, 0x001B0002, 0x0 },/* 9:	1000	1000	0	*/
+static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_dp[] = {
+	{ .hsw = { 0x00FFFFFF, 0x0006000E, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x0005000A, 0x0 } },
+	{ .hsw = { 0x00C30FFF, 0x00040006, 0x0 } },
+	{ .hsw = { 0x80AAAFFF, 0x000B0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x0005000A, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x000C0004, 0x0 } },
+	{ .hsw = { 0x80C30FFF, 0x000B0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x00040006, 0x0 } },
+	{ .hsw = { 0x80D75FFF, 0x000B0000, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans hsw_ddi_translations_dp = {
+	.entries = _hsw_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_hsw_ddi_translations_dp),
+};
+
+static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_fdi[] = {
+	{ .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x000F000A, 0x0 } },
+	{ .hsw = { 0x00C30FFF, 0x00060006, 0x0 } },
+	{ .hsw = { 0x00AAAFFF, 0x001E0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x000F000A, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x00160004, 0x0 } },
+	{ .hsw = { 0x00C30FFF, 0x001E0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x00060006, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x001E0000, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans hsw_ddi_translations_fdi = {
+	.entries = _hsw_ddi_translations_fdi,
+	.num_entries = ARRAY_SIZE(_hsw_ddi_translations_fdi),
+};
+
+static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_hdmi[] = {
+							/* Idx	NT mV d	T mV d	db	*/
+	{ .hsw = { 0x00FFFFFF, 0x0006000E, 0x0 } },	/* 0:	400	400	0	*/
+	{ .hsw = { 0x00E79FFF, 0x000E000C, 0x0 } },	/* 1:	400	500	2	*/
+	{ .hsw = { 0x00D75FFF, 0x0005000A, 0x0 } },	/* 2:	400	600	3.5	*/
+	{ .hsw = { 0x00FFFFFF, 0x0005000A, 0x0 } },	/* 3:	600	600	0	*/
+	{ .hsw = { 0x00E79FFF, 0x001D0007, 0x0 } },	/* 4:	600	750	2	*/
+	{ .hsw = { 0x00D75FFF, 0x000C0004, 0x0 } },	/* 5:	600	900	3.5	*/
+	{ .hsw = { 0x00FFFFFF, 0x00040006, 0x0 } },	/* 6:	800	800	0	*/
+	{ .hsw = { 0x80E79FFF, 0x00030002, 0x0 } },	/* 7:	800	1000	2	*/
+	{ .hsw = { 0x00FFFFFF, 0x00140005, 0x0 } },	/* 8:	850	850	0	*/
+	{ .hsw = { 0x00FFFFFF, 0x000C0004, 0x0 } },	/* 9:	900	900	0	*/
+	{ .hsw = { 0x00FFFFFF, 0x001C0003, 0x0 } },	/* 10:	950	950	0	*/
+	{ .hsw = { 0x80FFFFFF, 0x00030002, 0x0 } },	/* 11:	1000	1000	0	*/
+};
+
+static const struct intel_ddi_buf_trans hsw_ddi_translations_hdmi = {
+	.entries = _hsw_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_hsw_ddi_translations_hdmi),
+	.hdmi_default_entry = 6,
+};
+
+static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_edp[] = {
+	{ .hsw = { 0x00FFFFFF, 0x00000012, 0x0 } },
+	{ .hsw = { 0x00EBAFFF, 0x00020011, 0x0 } },
+	{ .hsw = { 0x00C71FFF, 0x0006000F, 0x0 } },
+	{ .hsw = { 0x00AAAFFF, 0x000E000A, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x00020011, 0x0 } },
+	{ .hsw = { 0x00DB6FFF, 0x0005000F, 0x0 } },
+	{ .hsw = { 0x00BEEFFF, 0x000A000C, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x0005000F, 0x0 } },
+	{ .hsw = { 0x00DB6FFF, 0x000A000C, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans bdw_ddi_translations_edp = {
+	.entries = _bdw_ddi_translations_edp,
+	.num_entries = ARRAY_SIZE(_bdw_ddi_translations_edp),
+};
+
+static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_dp[] = {
+	{ .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x000E000A, 0x0 } },
+	{ .hsw = { 0x00BEFFFF, 0x00140006, 0x0 } },
+	{ .hsw = { 0x80B2CFFF, 0x001B0002, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x000E000A, 0x0 } },
+	{ .hsw = { 0x00DB6FFF, 0x00160005, 0x0 } },
+	{ .hsw = { 0x80C71FFF, 0x001A0002, 0x0 } },
+	{ .hsw = { 0x00F7DFFF, 0x00180004, 0x0 } },
+	{ .hsw = { 0x80D75FFF, 0x001B0002, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans bdw_ddi_translations_dp = {
+	.entries = _bdw_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_bdw_ddi_translations_dp),
+};
+
+static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_fdi[] = {
+	{ .hsw = { 0x00FFFFFF, 0x0001000E, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x0004000A, 0x0 } },
+	{ .hsw = { 0x00C30FFF, 0x00070006, 0x0 } },
+	{ .hsw = { 0x00AAAFFF, 0x000C0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x0004000A, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x00090004, 0x0 } },
+	{ .hsw = { 0x00C30FFF, 0x000C0000, 0x0 } },
+	{ .hsw = { 0x00FFFFFF, 0x00070006, 0x0 } },
+	{ .hsw = { 0x00D75FFF, 0x000C0000, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans bdw_ddi_translations_fdi = {
+	.entries = _bdw_ddi_translations_fdi,
+	.num_entries = ARRAY_SIZE(_bdw_ddi_translations_fdi),
+};
+
+static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_hdmi[] = {
+							/* Idx	NT mV d	T mV df	db	*/
+	{ .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } },	/* 0:	400	400	0	*/
+	{ .hsw = { 0x00D75FFF, 0x000E000A, 0x0 } },	/* 1:	400	600	3.5	*/
+	{ .hsw = { 0x00BEFFFF, 0x00140006, 0x0 } },	/* 2:	400	800	6	*/
+	{ .hsw = { 0x00FFFFFF, 0x0009000D, 0x0 } },	/* 3:	450	450	0	*/
+	{ .hsw = { 0x00FFFFFF, 0x000E000A, 0x0 } },	/* 4:	600	600	0	*/
+	{ .hsw = { 0x00D7FFFF, 0x00140006, 0x0 } },	/* 5:	600	800	2.5	*/
+	{ .hsw = { 0x80CB2FFF, 0x001B0002, 0x0 } },	/* 6:	600	1000	4.5	*/
+	{ .hsw = { 0x00FFFFFF, 0x00140006, 0x0 } },	/* 7:	800	800	0	*/
+	{ .hsw = { 0x80E79FFF, 0x001B0002, 0x0 } },	/* 8:	800	1000	2	*/
+	{ .hsw = { 0x80FFFFFF, 0x001B0002, 0x0 } },	/* 9:	1000	1000	0	*/
+};
+
+static const struct intel_ddi_buf_trans bdw_ddi_translations_hdmi = {
+	.entries = _bdw_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_bdw_ddi_translations_hdmi),
+	.hdmi_default_entry = 7,
 };
 
 /* Skylake H and S */
-static const struct ddi_buf_trans skl_ddi_translations_dp[] = {
-	{ 0x00002016, 0x000000A0, 0x0 },
-	{ 0x00005012, 0x0000009B, 0x0 },
-	{ 0x00007011, 0x00000088, 0x0 },
-	{ 0x80009010, 0x000000C0, 0x1 },
-	{ 0x00002016, 0x0000009B, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000C0, 0x1 },
-	{ 0x00002016, 0x000000DF, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },
+static const union intel_ddi_buf_trans_entry _skl_ddi_translations_dp[] = {
+	{ .hsw = { 0x00002016, 0x000000A0, 0x0 } },
+	{ .hsw = { 0x00005012, 0x0000009B, 0x0 } },
+	{ .hsw = { 0x00007011, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80009010, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x00002016, 0x0000009B, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x00002016, 0x000000DF, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x1 } },
+};
+
+static const struct intel_ddi_buf_trans skl_ddi_translations_dp = {
+	.entries = _skl_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_skl_ddi_translations_dp),
 };
 
 /* Skylake U */
-static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = {
-	{ 0x0000201B, 0x000000A2, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000CD, 0x1 },
-	{ 0x80009010, 0x000000C0, 0x1 },
-	{ 0x0000201B, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },
-	{ 0x80007011, 0x000000C0, 0x1 },
-	{ 0x00002016, 0x00000088, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },
+static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_dp[] = {
+	{ .hsw = { 0x0000201B, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000CD, 0x1 } },
+	{ .hsw = { 0x80009010, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x0000201B, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x00002016, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x1 } },
+};
+
+static const struct intel_ddi_buf_trans skl_u_ddi_translations_dp = {
+	.entries = _skl_u_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_skl_u_ddi_translations_dp),
 };
 
 /* Skylake Y */
-static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = {
-	{ 0x00000018, 0x000000A2, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000CD, 0x3 },
-	{ 0x80009010, 0x000000C0, 0x3 },
-	{ 0x00000018, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
-	{ 0x80007011, 0x000000C0, 0x3 },
-	{ 0x00000018, 0x00000088, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
+static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_dp[] = {
+	{ .hsw = { 0x00000018, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000CD, 0x3 } },
+	{ .hsw = { 0x80009010, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00000018, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00000018, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+};
+
+static const struct intel_ddi_buf_trans skl_y_ddi_translations_dp = {
+	.entries = _skl_y_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_skl_y_ddi_translations_dp),
 };
 
 /* Kabylake H and S */
-static const struct ddi_buf_trans kbl_ddi_translations_dp[] = {
-	{ 0x00002016, 0x000000A0, 0x0 },
-	{ 0x00005012, 0x0000009B, 0x0 },
-	{ 0x00007011, 0x00000088, 0x0 },
-	{ 0x80009010, 0x000000C0, 0x1 },
-	{ 0x00002016, 0x0000009B, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000C0, 0x1 },
-	{ 0x00002016, 0x00000097, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },
+static const union intel_ddi_buf_trans_entry _kbl_ddi_translations_dp[] = {
+	{ .hsw = { 0x00002016, 0x000000A0, 0x0 } },
+	{ .hsw = { 0x00005012, 0x0000009B, 0x0 } },
+	{ .hsw = { 0x00007011, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80009010, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x00002016, 0x0000009B, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x00002016, 0x00000097, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x1 } },
+};
+
+static const struct intel_ddi_buf_trans kbl_ddi_translations_dp = {
+	.entries = _kbl_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_kbl_ddi_translations_dp),
 };
 
 /* Kabylake U */
-static const struct ddi_buf_trans kbl_u_ddi_translations_dp[] = {
-	{ 0x0000201B, 0x000000A1, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000CD, 0x3 },
-	{ 0x80009010, 0x000000C0, 0x3 },
-	{ 0x0000201B, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
-	{ 0x80007011, 0x000000C0, 0x3 },
-	{ 0x00002016, 0x0000004F, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
+static const union intel_ddi_buf_trans_entry _kbl_u_ddi_translations_dp[] = {
+	{ .hsw = { 0x0000201B, 0x000000A1, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000CD, 0x3 } },
+	{ .hsw = { 0x80009010, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x0000201B, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00002016, 0x0000004F, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+};
+
+static const struct intel_ddi_buf_trans kbl_u_ddi_translations_dp = {
+	.entries = _kbl_u_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_kbl_u_ddi_translations_dp),
 };
 
 /* Kabylake Y */
-static const struct ddi_buf_trans kbl_y_ddi_translations_dp[] = {
-	{ 0x00001017, 0x000000A1, 0x0 },
-	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000CD, 0x3 },
-	{ 0x8000800F, 0x000000C0, 0x3 },
-	{ 0x00001017, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
-	{ 0x80007011, 0x000000C0, 0x3 },
-	{ 0x00001017, 0x0000004C, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },
+static const union intel_ddi_buf_trans_entry _kbl_y_ddi_translations_dp[] = {
+	{ .hsw = { 0x00001017, 0x000000A1, 0x0 } },
+	{ .hsw = { 0x00005012, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000CD, 0x3 } },
+	{ .hsw = { 0x8000800F, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00001017, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x80007011, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00001017, 0x0000004C, 0x0 } },
+	{ .hsw = { 0x80005012, 0x000000C0, 0x3 } },
+};
+
+static const struct intel_ddi_buf_trans kbl_y_ddi_translations_dp = {
+	.entries = _kbl_y_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_kbl_y_ddi_translations_dp),
 };
 
 /*
  * Skylake/Kabylake H and S
  * eDP 1.4 low vswing translation parameters
  */
-static const struct ddi_buf_trans skl_ddi_translations_edp[] = {
-	{ 0x00000018, 0x000000A8, 0x0 },
-	{ 0x00004013, 0x000000A9, 0x0 },
-	{ 0x00007011, 0x000000A2, 0x0 },
-	{ 0x00009010, 0x0000009C, 0x0 },
-	{ 0x00000018, 0x000000A9, 0x0 },
-	{ 0x00006013, 0x000000A2, 0x0 },
-	{ 0x00007011, 0x000000A6, 0x0 },
-	{ 0x00000018, 0x000000AB, 0x0 },
-	{ 0x00007013, 0x0000009F, 0x0 },
-	{ 0x00000018, 0x000000DF, 0x0 },
+static const union intel_ddi_buf_trans_entry _skl_ddi_translations_edp[] = {
+	{ .hsw = { 0x00000018, 0x000000A8, 0x0 } },
+	{ .hsw = { 0x00004013, 0x000000A9, 0x0 } },
+	{ .hsw = { 0x00007011, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00009010, 0x0000009C, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000A9, 0x0 } },
+	{ .hsw = { 0x00006013, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00007011, 0x000000A6, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000AB, 0x0 } },
+	{ .hsw = { 0x00007013, 0x0000009F, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000DF, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans skl_ddi_translations_edp = {
+	.entries = _skl_ddi_translations_edp,
+	.num_entries = ARRAY_SIZE(_skl_ddi_translations_edp),
 };
 
 /*
  * Skylake/Kabylake U
  * eDP 1.4 low vswing translation parameters
  */
-static const struct ddi_buf_trans skl_u_ddi_translations_edp[] = {
-	{ 0x00000018, 0x000000A8, 0x0 },
-	{ 0x00004013, 0x000000A9, 0x0 },
-	{ 0x00007011, 0x000000A2, 0x0 },
-	{ 0x00009010, 0x0000009C, 0x0 },
-	{ 0x00000018, 0x000000A9, 0x0 },
-	{ 0x00006013, 0x000000A2, 0x0 },
-	{ 0x00007011, 0x000000A6, 0x0 },
-	{ 0x00002016, 0x000000AB, 0x0 },
-	{ 0x00005013, 0x0000009F, 0x0 },
-	{ 0x00000018, 0x000000DF, 0x0 },
+static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_edp[] = {
+	{ .hsw = { 0x00000018, 0x000000A8, 0x0 } },
+	{ .hsw = { 0x00004013, 0x000000A9, 0x0 } },
+	{ .hsw = { 0x00007011, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00009010, 0x0000009C, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000A9, 0x0 } },
+	{ .hsw = { 0x00006013, 0x000000A2, 0x0 } },
+	{ .hsw = { 0x00007011, 0x000000A6, 0x0 } },
+	{ .hsw = { 0x00002016, 0x000000AB, 0x0 } },
+	{ .hsw = { 0x00005013, 0x0000009F, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000DF, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans skl_u_ddi_translations_edp = {
+	.entries = _skl_u_ddi_translations_edp,
+	.num_entries = ARRAY_SIZE(_skl_u_ddi_translations_edp),
 };
 
 /*
  * Skylake/Kabylake Y
  * eDP 1.4 low vswing translation parameters
  */
-static const struct ddi_buf_trans skl_y_ddi_translations_edp[] = {
-	{ 0x00000018, 0x000000A8, 0x0 },
-	{ 0x00004013, 0x000000AB, 0x0 },
-	{ 0x00007011, 0x000000A4, 0x0 },
-	{ 0x00009010, 0x000000DF, 0x0 },
-	{ 0x00000018, 0x000000AA, 0x0 },
-	{ 0x00006013, 0x000000A4, 0x0 },
-	{ 0x00007011, 0x0000009D, 0x0 },
-	{ 0x00000018, 0x000000A0, 0x0 },
-	{ 0x00006012, 0x000000DF, 0x0 },
-	{ 0x00000018, 0x0000008A, 0x0 },
+static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_edp[] = {
+	{ .hsw = { 0x00000018, 0x000000A8, 0x0 } },
+	{ .hsw = { 0x00004013, 0x000000AB, 0x0 } },
+	{ .hsw = { 0x00007011, 0x000000A4, 0x0 } },
+	{ .hsw = { 0x00009010, 0x000000DF, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000AA, 0x0 } },
+	{ .hsw = { 0x00006013, 0x000000A4, 0x0 } },
+	{ .hsw = { 0x00007011, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000A0, 0x0 } },
+	{ .hsw = { 0x00006012, 0x000000DF, 0x0 } },
+	{ .hsw = { 0x00000018, 0x0000008A, 0x0 } },
+};
+
+static const struct intel_ddi_buf_trans skl_y_ddi_translations_edp = {
+	.entries = _skl_y_ddi_translations_edp,
+	.num_entries = ARRAY_SIZE(_skl_y_ddi_translations_edp),
 };
 
 /* Skylake/Kabylake U, H and S */
-static const struct ddi_buf_trans skl_ddi_translations_hdmi[] = {
-	{ 0x00000018, 0x000000AC, 0x0 },
-	{ 0x00005012, 0x0000009D, 0x0 },
-	{ 0x00007011, 0x00000088, 0x0 },
-	{ 0x00000018, 0x000000A1, 0x0 },
-	{ 0x00000018, 0x00000098, 0x0 },
-	{ 0x00004013, 0x00000088, 0x0 },
-	{ 0x80006012, 0x000000CD, 0x1 },
-	{ 0x00000018, 0x000000DF, 0x0 },
-	{ 0x80003015, 0x000000CD, 0x1 },	/* Default */
-	{ 0x80003015, 0x000000C0, 0x1 },
-	{ 0x80000018, 0x000000C0, 0x1 },
+static const union intel_ddi_buf_trans_entry _skl_ddi_translations_hdmi[] = {
+	{ .hsw = { 0x00000018, 0x000000AC, 0x0 } },
+	{ .hsw = { 0x00005012, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x00007011, 0x00000088, 0x0 } },
+	{ .hsw = { 0x00000018, 0x000000A1, 0x0 } },
+	{ .hsw = { 0x00000018, 0x00000098, 0x0 } },
+	{ .hsw = { 0x00004013, 0x00000088, 0x0 } },
+	{ .hsw = { 0x80006012, 0x000000CD, 0x1 } },
+	{ .hsw = { 0x00000018, 0x000000DF, 0x0 } },
+	{ .hsw = { 0x80003015, 0x000000CD, 0x1 } },	/* Default */
+	{ .hsw = { 0x80003015, 0x000000C0, 0x1 } },
+	{ .hsw = { 0x80000018, 0x000000C0, 0x1 } },
+};
+
+static const struct intel_ddi_buf_trans skl_ddi_translations_hdmi = {
+	.entries = _skl_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_skl_ddi_translations_hdmi),
+	.hdmi_default_entry = 8,
 };
 
 /* Skylake/Kabylake Y */
-static const struct ddi_buf_trans skl_y_ddi_translations_hdmi[] = {
-	{ 0x00000018, 0x000000A1, 0x0 },
-	{ 0x00005012, 0x000000DF, 0x0 },
-	{ 0x80007011, 0x000000CB, 0x3 },
-	{ 0x00000018, 0x000000A4, 0x0 },
-	{ 0x00000018, 0x0000009D, 0x0 },
-	{ 0x00004013, 0x00000080, 0x0 },
-	{ 0x80006013, 0x000000C0, 0x3 },
-	{ 0x00000018, 0x0000008A, 0x0 },
-	{ 0x80003015, 0x000000C0, 0x3 },	/* Default */
-	{ 0x80003015, 0x000000C0, 0x3 },
-	{ 0x80000018, 0x000000C0, 0x3 },
-};
-
-
-static const struct bxt_ddi_buf_trans bxt_ddi_translations_dp[] = {
-					/* Idx	NT mV diff	db  */
-	{ 52,  0x9A, 0, 128, },	/* 0:	400		0   */
-	{ 78,  0x9A, 0, 85,  },	/* 1:	400		3.5 */
-	{ 104, 0x9A, 0, 64,  },	/* 2:	400		6   */
-	{ 154, 0x9A, 0, 43,  },	/* 3:	400		9.5 */
-	{ 77,  0x9A, 0, 128, },	/* 4:	600		0   */
-	{ 116, 0x9A, 0, 85,  },	/* 5:	600		3.5 */
-	{ 154, 0x9A, 0, 64,  },	/* 6:	600		6   */
-	{ 102, 0x9A, 0, 128, },	/* 7:	800		0   */
-	{ 154, 0x9A, 0, 85,  },	/* 8:	800		3.5 */
-	{ 154, 0x9A, 1, 128, },	/* 9:	1200		0   */
-};
-
-static const struct bxt_ddi_buf_trans bxt_ddi_translations_edp[] = {
+static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_hdmi[] = {
+	{ .hsw = { 0x00000018, 0x000000A1, 0x0 } },
+	{ .hsw = { 0x00005012, 0x000000DF, 0x0 } },
+	{ .hsw = { 0x80007011, 0x000000CB, 0x3 } },
+	{ .hsw = { 0x00000018, 0x000000A4, 0x0 } },
+	{ .hsw = { 0x00000018, 0x0000009D, 0x0 } },
+	{ .hsw = { 0x00004013, 0x00000080, 0x0 } },
+	{ .hsw = { 0x80006013, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x00000018, 0x0000008A, 0x0 } },
+	{ .hsw = { 0x80003015, 0x000000C0, 0x3 } },	/* Default */
+	{ .hsw = { 0x80003015, 0x000000C0, 0x3 } },
+	{ .hsw = { 0x80000018, 0x000000C0, 0x3 } },
+};
+
+static const struct intel_ddi_buf_trans skl_y_ddi_translations_hdmi = {
+	.entries = _skl_y_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_skl_y_ddi_translations_hdmi),
+	.hdmi_default_entry = 8,
+};
+
+static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_dp[] = {
+						/* Idx	NT mV diff	db  */
+	{ .bxt = { 52,  0x9A, 0, 128, } },	/* 0:	400		0   */
+	{ .bxt = { 78,  0x9A, 0, 85,  } },	/* 1:	400		3.5 */
+	{ .bxt = { 104, 0x9A, 0, 64,  } },	/* 2:	400		6   */
+	{ .bxt = { 154, 0x9A, 0, 43,  } },	/* 3:	400		9.5 */
+	{ .bxt = { 77,  0x9A, 0, 128, } },	/* 4:	600		0   */
+	{ .bxt = { 116, 0x9A, 0, 85,  } },	/* 5:	600		3.5 */
+	{ .bxt = { 154, 0x9A, 0, 64,  } },	/* 6:	600		6   */
+	{ .bxt = { 102, 0x9A, 0, 128, } },	/* 7:	800		0   */
+	{ .bxt = { 154, 0x9A, 0, 85,  } },	/* 8:	800		3.5 */
+	{ .bxt = { 154, 0x9A, 1, 128, } },	/* 9:	1200		0   */
+};
+
+static const struct intel_ddi_buf_trans bxt_ddi_translations_dp = {
+	.entries = _bxt_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_bxt_ddi_translations_dp),
+};
+
+static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_edp[] = {
 					/* Idx	NT mV diff	db  */
-	{ 26, 0, 0, 128, },	/* 0:	200		0   */
-	{ 38, 0, 0, 112, },	/* 1:	200		1.5 */
-	{ 48, 0, 0, 96,  },	/* 2:	200		4   */
-	{ 54, 0, 0, 69,  },	/* 3:	200		6   */
-	{ 32, 0, 0, 128, },	/* 4:	250		0   */
-	{ 48, 0, 0, 104, },	/* 5:	250		1.5 */
-	{ 54, 0, 0, 85,  },	/* 6:	250		4   */
-	{ 43, 0, 0, 128, },	/* 7:	300		0   */
-	{ 54, 0, 0, 101, },	/* 8:	300		1.5 */
-	{ 48, 0, 0, 128, },	/* 9:	300		0   */
+	{ .bxt = { 26, 0, 0, 128, } },	/* 0:	200		0   */
+	{ .bxt = { 38, 0, 0, 112, } },	/* 1:	200		1.5 */
+	{ .bxt = { 48, 0, 0, 96,  } },	/* 2:	200		4   */
+	{ .bxt = { 54, 0, 0, 69,  } },	/* 3:	200		6   */
+	{ .bxt = { 32, 0, 0, 128, } },	/* 4:	250		0   */
+	{ .bxt = { 48, 0, 0, 104, } },	/* 5:	250		1.5 */
+	{ .bxt = { 54, 0, 0, 85,  } },	/* 6:	250		4   */
+	{ .bxt = { 43, 0, 0, 128, } },	/* 7:	300		0   */
+	{ .bxt = { 54, 0, 0, 101, } },	/* 8:	300		1.5 */
+	{ .bxt = { 48, 0, 0, 128, } },	/* 9:	300		0   */
+};
+
+static const struct intel_ddi_buf_trans bxt_ddi_translations_edp = {
+	.entries = _bxt_ddi_translations_edp,
+	.num_entries = ARRAY_SIZE(_bxt_ddi_translations_edp),
 };
 
 /* BSpec has 2 recommended values - entries 0 and 8.
  * Using the entry with higher vswing.
  */
-static const struct bxt_ddi_buf_trans bxt_ddi_translations_hdmi[] = {
-					/* Idx	NT mV diff	db  */
-	{ 52,  0x9A, 0, 128, },	/* 0:	400		0   */
-	{ 52,  0x9A, 0, 85,  },	/* 1:	400		3.5 */
-	{ 52,  0x9A, 0, 64,  },	/* 2:	400		6   */
-	{ 42,  0x9A, 0, 43,  },	/* 3:	400		9.5 */
-	{ 77,  0x9A, 0, 128, },	/* 4:	600		0   */
-	{ 77,  0x9A, 0, 85,  },	/* 5:	600		3.5 */
-	{ 77,  0x9A, 0, 64,  },	/* 6:	600		6   */
-	{ 102, 0x9A, 0, 128, },	/* 7:	800		0   */
-	{ 102, 0x9A, 0, 85,  },	/* 8:	800		3.5 */
-	{ 154, 0x9A, 1, 128, },	/* 9:	1200		0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.85V for DP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_dp_0_85V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x5D, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x6A, 0x38, 0x00, 0x07 },	/* 350   500      3.1   */
-	{ 0xB, 0x7A, 0x32, 0x00, 0x0D },	/* 350   700      6.0   */
-	{ 0x6, 0x7C, 0x2D, 0x00, 0x12 },	/* 350   900      8.2   */
-	{ 0xA, 0x69, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xB, 0x7A, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
-	{ 0x6, 0x7C, 0x30, 0x00, 0x0F },	/* 500   900      5.1   */
-	{ 0xB, 0x7D, 0x3C, 0x00, 0x03 },	/* 650   725      0.9   */
-	{ 0x6, 0x7C, 0x34, 0x00, 0x0B },	/* 600   900      3.5   */
-	{ 0x6, 0x7B, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.85V for HDMI */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_hdmi_0_85V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x60, 0x3F, 0x00, 0x00 },	/* 450   450      0.0   */
-	{ 0xB, 0x73, 0x36, 0x00, 0x09 },	/* 450   650      3.2   */
-	{ 0x6, 0x7F, 0x31, 0x00, 0x0E },	/* 450   850      5.5   */
-	{ 0xB, 0x73, 0x3F, 0x00, 0x00 },	/* 650   650      0.0   */
-	{ 0x6, 0x7F, 0x37, 0x00, 0x08 },	/* 650   850      2.3   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 850   850      0.0   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.85V for eDP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_0_85V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x66, 0x3A, 0x00, 0x05 },	/* 384   500      2.3   */
-	{ 0x0, 0x7F, 0x38, 0x00, 0x07 },	/* 153   200      2.3   */
-	{ 0x8, 0x7F, 0x38, 0x00, 0x07 },	/* 192   250      2.3   */
-	{ 0x1, 0x7F, 0x38, 0x00, 0x07 },	/* 230   300      2.3   */
-	{ 0x9, 0x7F, 0x38, 0x00, 0x07 },	/* 269   350      2.3   */
-	{ 0xA, 0x66, 0x3C, 0x00, 0x03 },	/* 446   500      1.0   */
-	{ 0xB, 0x70, 0x3C, 0x00, 0x03 },	/* 460   600      2.3   */
-	{ 0xC, 0x75, 0x3C, 0x00, 0x03 },	/* 537   700      2.3   */
-	{ 0x2, 0x7F, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.95V for DP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_dp_0_95V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x5D, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x6A, 0x38, 0x00, 0x07 },	/* 350   500      3.1   */
-	{ 0xB, 0x7A, 0x32, 0x00, 0x0D },	/* 350   700      6.0   */
-	{ 0x6, 0x7C, 0x2D, 0x00, 0x12 },	/* 350   900      8.2   */
-	{ 0xA, 0x69, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xB, 0x7A, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
-	{ 0x6, 0x7C, 0x30, 0x00, 0x0F },	/* 500   900      5.1   */
-	{ 0xB, 0x7D, 0x3C, 0x00, 0x03 },	/* 650   725      0.9   */
-	{ 0x6, 0x7C, 0x34, 0x00, 0x0B },	/* 600   900      3.5   */
-	{ 0x6, 0x7B, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.95V for HDMI */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_hdmi_0_95V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x5C, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
-	{ 0xB, 0x69, 0x37, 0x00, 0x08 },	/* 400   600      3.5   */
-	{ 0x5, 0x76, 0x31, 0x00, 0x0E },	/* 400   800      6.0   */
-	{ 0xA, 0x5E, 0x3F, 0x00, 0x00 },	/* 450   450      0.0   */
-	{ 0xB, 0x69, 0x3F, 0x00, 0x00 },	/* 600   600      0.0   */
-	{ 0xB, 0x79, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
-	{ 0x6, 0x7D, 0x32, 0x00, 0x0D },	/* 600   1000     4.4   */
-	{ 0x5, 0x76, 0x3F, 0x00, 0x00 },	/* 800   800      0.0   */
-	{ 0x6, 0x7D, 0x39, 0x00, 0x06 },	/* 800   1000     1.9   */
-	{ 0x6, 0x7F, 0x39, 0x00, 0x06 },	/* 850   1050     1.8   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1050  1050     0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 0.95V for eDP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_0_95V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x61, 0x3A, 0x00, 0x05 },	/* 384   500      2.3   */
-	{ 0x0, 0x7F, 0x38, 0x00, 0x07 },	/* 153   200      2.3   */
-	{ 0x8, 0x7F, 0x38, 0x00, 0x07 },	/* 192   250      2.3   */
-	{ 0x1, 0x7F, 0x38, 0x00, 0x07 },	/* 230   300      2.3   */
-	{ 0x9, 0x7F, 0x38, 0x00, 0x07 },	/* 269   350      2.3   */
-	{ 0xA, 0x61, 0x3C, 0x00, 0x03 },	/* 446   500      1.0   */
-	{ 0xB, 0x68, 0x39, 0x00, 0x06 },	/* 460   600      2.3   */
-	{ 0xC, 0x6E, 0x39, 0x00, 0x06 },	/* 537   700      2.3   */
-	{ 0x4, 0x7F, 0x3A, 0x00, 0x05 },	/* 460   600      2.3   */
-	{ 0x2, 0x7F, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 1.05V for DP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_dp_1_05V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x58, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
-	{ 0xB, 0x64, 0x37, 0x00, 0x08 },	/* 400   600      3.5   */
-	{ 0x5, 0x70, 0x31, 0x00, 0x0E },	/* 400   800      6.0   */
-	{ 0x6, 0x7F, 0x2C, 0x00, 0x13 },	/* 400   1050     8.4   */
-	{ 0xB, 0x64, 0x3F, 0x00, 0x00 },	/* 600   600      0.0   */
-	{ 0x5, 0x73, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
-	{ 0x6, 0x7F, 0x30, 0x00, 0x0F },	/* 550   1050     5.6   */
-	{ 0x5, 0x76, 0x3E, 0x00, 0x01 },	/* 850   900      0.5   */
-	{ 0x6, 0x7F, 0x36, 0x00, 0x09 },	/* 750   1050     2.9   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1050  1050     0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 1.05V for HDMI */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_hdmi_1_05V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x58, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
-	{ 0xB, 0x64, 0x37, 0x00, 0x08 },	/* 400   600      3.5   */
-	{ 0x5, 0x70, 0x31, 0x00, 0x0E },	/* 400   800      6.0   */
-	{ 0xA, 0x5B, 0x3F, 0x00, 0x00 },	/* 450   450      0.0   */
-	{ 0xB, 0x64, 0x3F, 0x00, 0x00 },	/* 600   600      0.0   */
-	{ 0x5, 0x73, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
-	{ 0x6, 0x7C, 0x32, 0x00, 0x0D },	/* 600   1000     4.4   */
-	{ 0x5, 0x70, 0x3F, 0x00, 0x00 },	/* 800   800      0.0   */
-	{ 0x6, 0x7C, 0x39, 0x00, 0x06 },	/* 800   1000     1.9   */
-	{ 0x6, 0x7F, 0x39, 0x00, 0x06 },	/* 850   1050     1.8   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1050  1050     0.0   */
-};
-
-/* Voltage Swing Programming for VccIO 1.05V for eDP */
-static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x5E, 0x3A, 0x00, 0x05 },	/* 384   500      2.3   */
-	{ 0x0, 0x7F, 0x38, 0x00, 0x07 },	/* 153   200      2.3   */
-	{ 0x8, 0x7F, 0x38, 0x00, 0x07 },	/* 192   250      2.3   */
-	{ 0x1, 0x7F, 0x38, 0x00, 0x07 },	/* 230   300      2.3   */
-	{ 0x9, 0x7F, 0x38, 0x00, 0x07 },	/* 269   350      2.3   */
-	{ 0xA, 0x5E, 0x3C, 0x00, 0x03 },	/* 446   500      1.0   */
-	{ 0xB, 0x64, 0x39, 0x00, 0x06 },	/* 460   600      2.3   */
-	{ 0xE, 0x6A, 0x39, 0x00, 0x06 },	/* 537   700      2.3   */
-	{ 0x2, 0x7F, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
+static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_hdmi[] = {
+						/* Idx	NT mV diff	db  */
+	{ .bxt = { 52,  0x9A, 0, 128, } },	/* 0:	400		0   */
+	{ .bxt = { 52,  0x9A, 0, 85,  } },	/* 1:	400		3.5 */
+	{ .bxt = { 52,  0x9A, 0, 64,  } },	/* 2:	400		6   */
+	{ .bxt = { 42,  0x9A, 0, 43,  } },	/* 3:	400		9.5 */
+	{ .bxt = { 77,  0x9A, 0, 128, } },	/* 4:	600		0   */
+	{ .bxt = { 77,  0x9A, 0, 85,  } },	/* 5:	600		3.5 */
+	{ .bxt = { 77,  0x9A, 0, 64,  } },	/* 6:	600		6   */
+	{ .bxt = { 102, 0x9A, 0, 128, } },	/* 7:	800		0   */
+	{ .bxt = { 102, 0x9A, 0, 85,  } },	/* 8:	800		3.5 */
+	{ .bxt = { 154, 0x9A, 1, 128, } },	/* 9:	1200		0   */
+};
+
+static const struct intel_ddi_buf_trans bxt_ddi_translations_hdmi = {
+	.entries = _bxt_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_bxt_ddi_translations_hdmi),
+	.hdmi_default_entry = ARRAY_SIZE(_bxt_ddi_translations_hdmi) - 1,
 };
 
 /* icl_combo_phy_ddi_translations */
-static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x37, 0x00, 0x08 },	/* 350   500      3.1   */
-	{ 0xC, 0x71, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2B, 0x00, 0x14 },	/* 350   900      8.2   */
-	{ 0xA, 0x4C, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x73, 0x34, 0x00, 0x0B },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x6C, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2[] = {
-						/* NT mV Trans mV db    */
-	{ 0x0, 0x7F, 0x3F, 0x00, 0x00 },	/* 200   200      0.0   */
-	{ 0x8, 0x7F, 0x38, 0x00, 0x07 },	/* 200   250      1.9   */
-	{ 0x1, 0x7F, 0x33, 0x00, 0x0C },	/* 200   300      3.5   */
-	{ 0x9, 0x7F, 0x31, 0x00, 0x0E },	/* 200   350      4.9   */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },	/* 250   250      0.0   */
-	{ 0x1, 0x7F, 0x38, 0x00, 0x07 },	/* 250   300      1.6   */
-	{ 0x9, 0x7F, 0x35, 0x00, 0x0A },	/* 250   350      2.9   */
-	{ 0x1, 0x7F, 0x3F, 0x00, 0x00 },	/* 300   300      0.0   */
-	{ 0x9, 0x7F, 0x38, 0x00, 0x07 },	/* 300   350      1.3   */
-	{ 0x9, 0x7F, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr3[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x37, 0x00, 0x08 },	/* 350   500      3.1   */
-	{ 0xC, 0x71, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2B, 0x00, 0x14 },	/* 350   900      8.2   */
-	{ 0xA, 0x4C, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x73, 0x34, 0x00, 0x0B },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x6C, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x60, 0x3F, 0x00, 0x00 },	/* 450   450      0.0   */
-	{ 0xB, 0x73, 0x36, 0x00, 0x09 },	/* 450   650      3.2   */
-	{ 0x6, 0x7F, 0x31, 0x00, 0x0E },	/* 450   850      5.5   */
-	{ 0xB, 0x73, 0x3F, 0x00, 0x00 },	/* 650   650      0.0   ALS */
-	{ 0x6, 0x7F, 0x37, 0x00, 0x08 },	/* 650   850      2.3   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 850   850      0.0   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
-};
-
-static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_dp[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x33, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x47, 0x36, 0x00, 0x09 },	/* 350   500      3.1   */
-	{ 0xC, 0x64, 0x34, 0x00, 0x0B },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x30, 0x00, 0x0F },	/* 350   900      8.2   */
-	{ 0xA, 0x46, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x64, 0x38, 0x00, 0x07 },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x32, 0x00, 0x0D },	/* 500   900      5.1   */
-	{ 0xC, 0x61, 0x3F, 0x00, 0x00 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x38, 0x00, 0x07 },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr[] = {
-						/* NT mV Trans mV db    */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },        /* 200   200      0.0   */
-	{ 0x8, 0x7F, 0x38, 0x00, 0x07 },        /* 200   250      1.9   */
-	{ 0x1, 0x7F, 0x33, 0x00, 0x0C },        /* 200   300      3.5   */
-	{ 0xA, 0x35, 0x36, 0x00, 0x09 },        /* 200   350      4.9   */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },        /* 250   250      0.0   */
-	{ 0x1, 0x7F, 0x38, 0x00, 0x07 },        /* 250   300      1.6   */
-	{ 0xA, 0x35, 0x35, 0x00, 0x0A },        /* 250   350      2.9   */
-	{ 0x1, 0x7F, 0x3F, 0x00, 0x00 },        /* 300   300      0.0   */
-	{ 0xA, 0x35, 0x38, 0x00, 0x07 },        /* 300   350      1.3   */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },        /* 350   350      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr2[] = {
-						/* NT mV Trans mV db    */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },        /* 200   200      0.0   */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },        /* 200   250      1.9   */
-	{ 0x1, 0x7F, 0x3D, 0x00, 0x02 },        /* 200   300      3.5   */
-	{ 0xA, 0x35, 0x38, 0x00, 0x07 },        /* 200   350      4.9   */
-	{ 0x8, 0x7F, 0x3F, 0x00, 0x00 },        /* 250   250      0.0   */
-	{ 0x1, 0x7F, 0x3F, 0x00, 0x00 },        /* 250   300      1.6   */
-	{ 0xA, 0x35, 0x3A, 0x00, 0x05 },        /* 250   350      2.9   */
-	{ 0x1, 0x7F, 0x3F, 0x00, 0x00 },        /* 300   300      0.0   */
-	{ 0xA, 0x35, 0x38, 0x00, 0x07 },        /* 300   350      1.3   */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },        /* 350   350      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_rbr_hbr[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x32, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x48, 0x35, 0x00, 0x0A },	/* 350   500      3.1   */
-	{ 0xC, 0x63, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2C, 0x00, 0x13 },	/* 350   900      8.2   */
-	{ 0xA, 0x43, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x60, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x30, 0x00, 0x0F },	/* 500   900      5.1   */
-	{ 0xC, 0x60, 0x3F, 0x00, 0x00 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x37, 0x00, 0x08 },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x32, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x48, 0x35, 0x00, 0x0A },	/* 350   500      3.1   */
-	{ 0xC, 0x63, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2C, 0x00, 0x13 },	/* 350   900      8.2   */
-	{ 0xA, 0x43, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x60, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x30, 0x00, 0x0F },	/* 500   900      5.1   */
-	{ 0xC, 0x58, 0x3F, 0x00, 0x00 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_rbr_hbr[] = {
-				/* Voltage swing  pre-emphasis */
-	{ 0x18, 0x00, 0x00 },	/* 0              0   */
-	{ 0x1D, 0x00, 0x05 },	/* 0              1   */
-	{ 0x24, 0x00, 0x0C },	/* 0              2   */
-	{ 0x2B, 0x00, 0x14 },	/* 0              3   */
-	{ 0x21, 0x00, 0x00 },	/* 1              0   */
-	{ 0x2B, 0x00, 0x08 },	/* 1              1   */
-	{ 0x30, 0x00, 0x0F },	/* 1              2   */
-	{ 0x31, 0x00, 0x03 },	/* 2              0   */
-	{ 0x34, 0x00, 0x0B },	/* 2              1   */
-	{ 0x3F, 0x00, 0x00 },	/* 3              0   */
-};
-
-static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hbr2_hbr3[] = {
-				/* Voltage swing  pre-emphasis */
-	{ 0x18, 0x00, 0x00 },	/* 0              0   */
-	{ 0x1D, 0x00, 0x05 },	/* 0              1   */
-	{ 0x24, 0x00, 0x0C },	/* 0              2   */
-	{ 0x2B, 0x00, 0x14 },	/* 0              3   */
-	{ 0x26, 0x00, 0x00 },	/* 1              0   */
-	{ 0x2C, 0x00, 0x07 },	/* 1              1   */
-	{ 0x33, 0x00, 0x0C },	/* 1              2   */
-	{ 0x2E, 0x00, 0x00 },	/* 2              0   */
-	{ 0x36, 0x00, 0x09 },	/* 2              1   */
-	{ 0x3F, 0x00, 0x00 },	/* 3              0   */
-};
-
-static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hdmi[] = {
-				/* HDMI Preset	VS	Pre-emph */
-	{ 0x1A, 0x0, 0x0 },	/* 1		400mV	0dB */
-	{ 0x20, 0x0, 0x0 },	/* 2		500mV	0dB */
-	{ 0x29, 0x0, 0x0 },	/* 3		650mV	0dB */
-	{ 0x32, 0x0, 0x0 },	/* 4		800mV	0dB */
-	{ 0x3F, 0x0, 0x0 },	/* 5		1000mV	0dB */
-	{ 0x3A, 0x0, 0x5 },	/* 6		Full	-1.5 dB */
-	{ 0x39, 0x0, 0x6 },	/* 7		Full	-1.8 dB */
-	{ 0x38, 0x0, 0x7 },	/* 8		Full	-2 dB */
-	{ 0x37, 0x0, 0x8 },	/* 9		Full	-2.5 dB */
-	{ 0x36, 0x0, 0x9 },	/* 10		Full	-3 dB */
-};
-
-static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_dp_ddi_trans[] = {
-				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
-	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
-	{ 0x5, 0x0, 0x05 },	/* 0	1	400mV		3.5 dB */
-	{ 0x2, 0x0, 0x0B },	/* 0	2	400mV		6 dB */
-	{ 0x0, 0x0, 0x18 },	/* 0	3	400mV		9.5 dB */
-	{ 0x5, 0x0, 0x00 },	/* 1	0	600mV		0 dB */
-	{ 0x2, 0x0, 0x08 },	/* 1	1	600mV		3.5 dB */
-	{ 0x0, 0x0, 0x14 },	/* 1	2	600mV		6 dB */
-	{ 0x2, 0x0, 0x00 },	/* 2	0	800mV		0 dB */
-	{ 0x0, 0x0, 0x0B },	/* 2	1	800mV		3.5 dB */
-	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB HDMI default */
-};
-
-static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_dp_ddi_trans_hbr2[] = {
-				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
-	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
-	{ 0x5, 0x0, 0x05 },	/* 0	1	400mV		3.5 dB */
-	{ 0x2, 0x0, 0x0B },	/* 0	2	400mV		6 dB */
-	{ 0x0, 0x0, 0x19 },	/* 0	3	400mV		9.5 dB */
-	{ 0x5, 0x0, 0x00 },	/* 1	0	600mV		0 dB */
-	{ 0x2, 0x0, 0x08 },	/* 1	1	600mV		3.5 dB */
-	{ 0x0, 0x0, 0x14 },	/* 1	2	600mV		6 dB */
-	{ 0x2, 0x0, 0x00 },	/* 2	0	800mV		0 dB */
-	{ 0x0, 0x0, 0x0B },	/* 2	1	800mV		3.5 dB */
-	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB HDMI default */
-};
-
-static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_hdmi_ddi_trans[] = {
-				/* HDMI Preset	VS	Pre-emph */
-	{ 0x7, 0x0, 0x0 },	/* 1		400mV	0dB */
-	{ 0x6, 0x0, 0x0 },	/* 2		500mV	0dB */
-	{ 0x4, 0x0, 0x0 },	/* 3		650mV	0dB */
-	{ 0x2, 0x0, 0x0 },	/* 4		800mV	0dB */
-	{ 0x0, 0x0, 0x0 },	/* 5		1000mV	0dB */
-	{ 0x0, 0x0, 0x5 },	/* 6		Full	-1.5 dB */
-	{ 0x0, 0x0, 0x6 },	/* 7		Full	-1.8 dB */
-	{ 0x0, 0x0, 0x7 },	/* 8		Full	-2 dB */
-	{ 0x0, 0x0, 0x8 },	/* 9		Full	-2.5 dB */
-	{ 0x0, 0x0, 0xA },	/* 10		Full	-3 dB */
-};
-
-static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x32, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x37, 0x00, 0x08 },	/* 350   500      3.1   */
-	{ 0xC, 0x71, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7D, 0x2B, 0x00, 0x14 },	/* 350   900      8.2   */
-	{ 0xA, 0x4C, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x73, 0x34, 0x00, 0x0B },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x6C, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr2[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x37, 0x00, 0x08 },	/* 350   500      3.1   */
-	{ 0xC, 0x63, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2B, 0x00, 0x14 },	/* 350   900      8.2   */
-	{ 0xA, 0x47, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x63, 0x34, 0x00, 0x0B },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x61, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
-	{ 0x6, 0x7B, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans tgl_uy_combo_phy_ddi_translations_dp_hbr2[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x36, 0x00, 0x09 },	/* 350   500      3.1   */
-	{ 0xC, 0x60, 0x32, 0x00, 0x0D },	/* 350   700      6.0   */
-	{ 0xC, 0x7F, 0x2D, 0x00, 0x12 },	/* 350   900      8.2   */
-	{ 0xC, 0x47, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x6F, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
-	{ 0x6, 0x7D, 0x32, 0x00, 0x0D },	/* 500   900      5.1   */
-	{ 0x6, 0x60, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x34, 0x00, 0x0B },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
+static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x71, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2B, 0x00, 0x14 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x4C, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x73, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x6C, 0x3C, 0x00, 0x03 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3 = {
+	.entries = _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+	.num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3),
+};
+
+static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_edp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0x0, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   200      0.0   */
+	{ .icl = { 0x8, 0x7F, 0x38, 0x00, 0x07 } },	/* 200   250      1.9   */
+	{ .icl = { 0x1, 0x7F, 0x33, 0x00, 0x0C } },	/* 200   300      3.5   */
+	{ .icl = { 0x9, 0x7F, 0x31, 0x00, 0x0E } },	/* 200   350      4.9   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 250   250      0.0   */
+	{ .icl = { 0x1, 0x7F, 0x38, 0x00, 0x07 } },	/* 250   300      1.6   */
+	{ .icl = { 0x9, 0x7F, 0x35, 0x00, 0x0A } },	/* 250   350      2.9   */
+	{ .icl = { 0x1, 0x7F, 0x3F, 0x00, 0x00 } },	/* 300   300      0.0   */
+	{ .icl = { 0x9, 0x7F, 0x38, 0x00, 0x07 } },	/* 300   350      1.3   */
+	{ .icl = { 0x9, 0x7F, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+};
+
+static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2 = {
+	.entries = _icl_combo_phy_ddi_translations_edp_hbr2,
+	.num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_edp_hbr2),
+};
+
+static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_hdmi[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x60, 0x3F, 0x00, 0x00 } },	/* 450   450      0.0   */
+	{ .icl = { 0xB, 0x73, 0x36, 0x00, 0x09 } },	/* 450   650      3.2   */
+	{ .icl = { 0x6, 0x7F, 0x31, 0x00, 0x0E } },	/* 450   850      5.5   */
+	{ .icl = { 0xB, 0x73, 0x3F, 0x00, 0x00 } },	/* 650   650      0.0   ALS */
+	{ .icl = { 0x6, 0x7F, 0x37, 0x00, 0x08 } },	/* 650   850      2.3   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 850   850      0.0   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   850      3.0   */
+};
+
+static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi = {
+	.entries = _icl_combo_phy_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_hdmi),
+	.hdmi_default_entry = ARRAY_SIZE(_icl_combo_phy_ddi_translations_hdmi) - 1,
+};
+
+static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_dp[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x33, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x47, 0x36, 0x00, 0x09 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x64, 0x34, 0x00, 0x0B } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x30, 0x00, 0x0F } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x46, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x64, 0x38, 0x00, 0x07 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x32, 0x00, 0x0D } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x61, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x38, 0x00, 0x07 } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans ehl_combo_phy_ddi_translations_dp = {
+	.entries = _ehl_combo_phy_ddi_translations_dp,
+	.num_entries = ARRAY_SIZE(_ehl_combo_phy_ddi_translations_dp),
+};
+
+static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_edp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   200      0.0   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   250      1.9   */
+	{ .icl = { 0x1, 0x7F, 0x3D, 0x00, 0x02 } },	/* 200   300      3.5   */
+	{ .icl = { 0xA, 0x35, 0x39, 0x00, 0x06 } },	/* 200   350      4.9   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 250   250      0.0   */
+	{ .icl = { 0x1, 0x7F, 0x3C, 0x00, 0x03 } },	/* 250   300      1.6   */
+	{ .icl = { 0xA, 0x35, 0x39, 0x00, 0x06 } },	/* 250   350      2.9   */
+	{ .icl = { 0x1, 0x7F, 0x3F, 0x00, 0x00 } },	/* 300   300      0.0   */
+	{ .icl = { 0xA, 0x35, 0x38, 0x00, 0x07 } },	/* 300   350      1.3   */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+};
+
+static const struct intel_ddi_buf_trans ehl_combo_phy_ddi_translations_edp_hbr2 = {
+	.entries = _ehl_combo_phy_ddi_translations_edp_hbr2,
+	.num_entries = ARRAY_SIZE(_ehl_combo_phy_ddi_translations_edp_hbr2),
+};
+
+static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp_hbr[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   200      0.0   */
+	{ .icl = { 0x8, 0x7F, 0x38, 0x00, 0x07 } },	/* 200   250      1.9   */
+	{ .icl = { 0x1, 0x7F, 0x33, 0x00, 0x0C } },	/* 200   300      3.5   */
+	{ .icl = { 0xA, 0x35, 0x36, 0x00, 0x09 } },	/* 200   350      4.9   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 250   250      0.0   */
+	{ .icl = { 0x1, 0x7F, 0x38, 0x00, 0x07 } },	/* 250   300      1.6   */
+	{ .icl = { 0xA, 0x35, 0x35, 0x00, 0x0A } },	/* 250   350      2.9   */
+	{ .icl = { 0x1, 0x7F, 0x3F, 0x00, 0x00 } },	/* 300   300      0.0   */
+	{ .icl = { 0xA, 0x35, 0x38, 0x00, 0x07 } },	/* 300   350      1.3   */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+};
+
+static const struct intel_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr = {
+	.entries = _jsl_combo_phy_ddi_translations_edp_hbr,
+	.num_entries = ARRAY_SIZE(_jsl_combo_phy_ddi_translations_edp_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   200      0.0   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 200   250      1.9   */
+	{ .icl = { 0x1, 0x7F, 0x3D, 0x00, 0x02 } },	/* 200   300      3.5   */
+	{ .icl = { 0xA, 0x35, 0x38, 0x00, 0x07 } },	/* 200   350      4.9   */
+	{ .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } },	/* 250   250      0.0   */
+	{ .icl = { 0x1, 0x7F, 0x3F, 0x00, 0x00 } },	/* 250   300      1.6   */
+	{ .icl = { 0xA, 0x35, 0x3A, 0x00, 0x05 } },	/* 250   350      2.9   */
+	{ .icl = { 0x1, 0x7F, 0x3F, 0x00, 0x00 } },	/* 300   300      0.0   */
+	{ .icl = { 0xA, 0x35, 0x38, 0x00, 0x07 } },	/* 300   350      1.3   */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+};
+
+static const struct intel_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr2 = {
+	.entries = _jsl_combo_phy_ddi_translations_edp_hbr2,
+	.num_entries = ARRAY_SIZE(_jsl_combo_phy_ddi_translations_edp_hbr2),
+};
+
+static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_rbr_hbr[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x48, 0x35, 0x00, 0x0A } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2C, 0x00, 0x13 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x43, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x60, 0x36, 0x00, 0x09 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x30, 0x00, 0x0F } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x60, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x37, 0x00, 0x08 } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_rbr_hbr = {
+	.entries = _dg1_combo_phy_ddi_translations_dp_rbr_hbr,
+	.num_entries = ARRAY_SIZE(_dg1_combo_phy_ddi_translations_dp_rbr_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x48, 0x35, 0x00, 0x0A } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2C, 0x00, 0x13 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x43, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x60, 0x36, 0x00, 0x09 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x30, 0x00, 0x0F } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x58, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_hbr2_hbr3 = {
+	.entries = _dg1_combo_phy_ddi_translations_dp_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_dg1_combo_phy_ddi_translations_dp_hbr2_hbr3),
+};
+
+static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_rbr_hbr[] = {
+					/* Voltage swing  pre-emphasis */
+	{ .mg = { 0x18, 0x00, 0x00 } },	/* 0              0   */
+	{ .mg = { 0x1D, 0x00, 0x05 } },	/* 0              1   */
+	{ .mg = { 0x24, 0x00, 0x0C } },	/* 0              2   */
+	{ .mg = { 0x2B, 0x00, 0x14 } },	/* 0              3   */
+	{ .mg = { 0x21, 0x00, 0x00 } },	/* 1              0   */
+	{ .mg = { 0x2B, 0x00, 0x08 } },	/* 1              1   */
+	{ .mg = { 0x30, 0x00, 0x0F } },	/* 1              2   */
+	{ .mg = { 0x31, 0x00, 0x03 } },	/* 2              0   */
+	{ .mg = { 0x34, 0x00, 0x0B } },	/* 2              1   */
+	{ .mg = { 0x3F, 0x00, 0x00 } },	/* 3              0   */
+};
+
+static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_rbr_hbr = {
+	.entries = _icl_mg_phy_ddi_translations_rbr_hbr,
+	.num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_rbr_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hbr2_hbr3[] = {
+					/* Voltage swing  pre-emphasis */
+	{ .mg = { 0x18, 0x00, 0x00 } },	/* 0              0   */
+	{ .mg = { 0x1D, 0x00, 0x05 } },	/* 0              1   */
+	{ .mg = { 0x24, 0x00, 0x0C } },	/* 0              2   */
+	{ .mg = { 0x2B, 0x00, 0x14 } },	/* 0              3   */
+	{ .mg = { 0x26, 0x00, 0x00 } },	/* 1              0   */
+	{ .mg = { 0x2C, 0x00, 0x07 } },	/* 1              1   */
+	{ .mg = { 0x33, 0x00, 0x0C } },	/* 1              2   */
+	{ .mg = { 0x2E, 0x00, 0x00 } },	/* 2              0   */
+	{ .mg = { 0x36, 0x00, 0x09 } },	/* 2              1   */
+	{ .mg = { 0x3F, 0x00, 0x00 } },	/* 3              0   */
+};
+
+static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_hbr2_hbr3 = {
+	.entries = _icl_mg_phy_ddi_translations_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hbr2_hbr3),
+};
+
+static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hdmi[] = {
+					/* HDMI Preset	VS	Pre-emph */
+	{ .mg = { 0x1A, 0x0, 0x0 } },	/* 1		400mV	0dB */
+	{ .mg = { 0x20, 0x0, 0x0 } },	/* 2		500mV	0dB */
+	{ .mg = { 0x29, 0x0, 0x0 } },	/* 3		650mV	0dB */
+	{ .mg = { 0x32, 0x0, 0x0 } },	/* 4		800mV	0dB */
+	{ .mg = { 0x3F, 0x0, 0x0 } },	/* 5		1000mV	0dB */
+	{ .mg = { 0x3A, 0x0, 0x5 } },	/* 6		Full	-1.5 dB */
+	{ .mg = { 0x39, 0x0, 0x6 } },	/* 7		Full	-1.8 dB */
+	{ .mg = { 0x38, 0x0, 0x7 } },	/* 8		Full	-2 dB */
+	{ .mg = { 0x37, 0x0, 0x8 } },	/* 9		Full	-2.5 dB */
+	{ .mg = { 0x36, 0x0, 0x9 } },	/* 10		Full	-3 dB */
+};
+
+static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_hdmi = {
+	.entries = _icl_mg_phy_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hdmi),
+	.hdmi_default_entry = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hdmi) - 1,
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hbr[] = {
+					/* VS	pre-emp	Non-trans mV	Pre-emph dB */
+	{ .dkl = { 0x7, 0x0, 0x00 } },	/* 0	0	400mV		0 dB */
+	{ .dkl = { 0x5, 0x0, 0x05 } },	/* 0	1	400mV		3.5 dB */
+	{ .dkl = { 0x2, 0x0, 0x0B } },	/* 0	2	400mV		6 dB */
+	{ .dkl = { 0x0, 0x0, 0x18 } },	/* 0	3	400mV		9.5 dB */
+	{ .dkl = { 0x5, 0x0, 0x00 } },	/* 1	0	600mV		0 dB */
+	{ .dkl = { 0x2, 0x0, 0x08 } },	/* 1	1	600mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x14 } },	/* 1	2	600mV		6 dB */
+	{ .dkl = { 0x2, 0x0, 0x00 } },	/* 2	0	800mV		0 dB */
+	{ .dkl = { 0x0, 0x0, 0x0B } },	/* 2	1	800mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x00 } },	/* 3	0	1200mV		0 dB HDMI default */
+};
+
+static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_dp_hbr = {
+	.entries = _tgl_dkl_phy_ddi_translations_dp_hbr,
+	.num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_dp_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hbr2[] = {
+					/* VS	pre-emp	Non-trans mV	Pre-emph dB */
+	{ .dkl = { 0x7, 0x0, 0x00 } },	/* 0	0	400mV		0 dB */
+	{ .dkl = { 0x5, 0x0, 0x05 } },	/* 0	1	400mV		3.5 dB */
+	{ .dkl = { 0x2, 0x0, 0x0B } },	/* 0	2	400mV		6 dB */
+	{ .dkl = { 0x0, 0x0, 0x19 } },	/* 0	3	400mV		9.5 dB */
+	{ .dkl = { 0x5, 0x0, 0x00 } },	/* 1	0	600mV		0 dB */
+	{ .dkl = { 0x2, 0x0, 0x08 } },	/* 1	1	600mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x14 } },	/* 1	2	600mV		6 dB */
+	{ .dkl = { 0x2, 0x0, 0x00 } },	/* 2	0	800mV		0 dB */
+	{ .dkl = { 0x0, 0x0, 0x0B } },	/* 2	1	800mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x00 } },	/* 3	0	1200mV		0 dB HDMI default */
+};
+
+static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_dp_hbr2 = {
+	.entries = _tgl_dkl_phy_ddi_translations_dp_hbr2,
+	.num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_dp_hbr2),
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_hdmi[] = {
+					/* HDMI Preset	VS	Pre-emph */
+	{ .dkl = { 0x7, 0x0, 0x0 } },	/* 1		400mV	0dB */
+	{ .dkl = { 0x6, 0x0, 0x0 } },	/* 2		500mV	0dB */
+	{ .dkl = { 0x4, 0x0, 0x0 } },	/* 3		650mV	0dB */
+	{ .dkl = { 0x2, 0x0, 0x0 } },	/* 4		800mV	0dB */
+	{ .dkl = { 0x0, 0x0, 0x0 } },	/* 5		1000mV	0dB */
+	{ .dkl = { 0x0, 0x0, 0x5 } },	/* 6		Full	-1.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x6 } },	/* 7		Full	-1.8 dB */
+	{ .dkl = { 0x0, 0x0, 0x7 } },	/* 8		Full	-2 dB */
+	{ .dkl = { 0x0, 0x0, 0x8 } },	/* 9		Full	-2.5 dB */
+	{ .dkl = { 0x0, 0x0, 0xA } },	/* 10		Full	-3 dB */
+};
+
+static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_hdmi = {
+	.entries = _tgl_dkl_phy_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_hdmi),
+	.hdmi_default_entry = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_hdmi) - 1,
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_hbr[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x71, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7D, 0x2B, 0x00, 0x14 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x4C, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x73, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x6C, 0x3C, 0x00, 0x03 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr = {
+	.entries = _tgl_combo_phy_ddi_translations_dp_hbr,
+	.num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_dp_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2B, 0x00, 0x14 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x47, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x63, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x61, 0x3C, 0x00, 0x03 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7B, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr2 = {
+	.entries = _tgl_combo_phy_ddi_translations_dp_hbr2,
+	.num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_dp_hbr2),
+};
+
+static const union intel_ddi_buf_trans_entry _tgl_uy_combo_phy_ddi_translations_dp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x36, 0x00, 0x09 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x60, 0x32, 0x00, 0x0D } },	/* 350   700      6.0   */
+	{ .icl = { 0xC, 0x7F, 0x2D, 0x00, 0x12 } },	/* 350   900      8.2   */
+	{ .icl = { 0xC, 0x47, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x6F, 0x36, 0x00, 0x09 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7D, 0x32, 0x00, 0x0D } },	/* 500   900      5.1   */
+	{ .icl = { 0x6, 0x60, 0x3C, 0x00, 0x03 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x34, 0x00, 0x0B } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
+
+static const struct intel_ddi_buf_trans tgl_uy_combo_phy_ddi_translations_dp_hbr2 = {
+	.entries = _tgl_uy_combo_phy_ddi_translations_dp_hbr2,
+	.num_entries = ARRAY_SIZE(_tgl_uy_combo_phy_ddi_translations_dp_hbr2),
 };
 
 /*
  * Cloned the HOBL entry to comply with the voltage and pre-emphasis entries
  * that DisplayPort specification requires
  */
-static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_edp_hbr2_hobl[] = {
-						/* VS	pre-emp	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	0	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	1	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	2	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	3	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	0	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	1	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	2	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	0	*/
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	1	*/
-};
-
-static const struct cnl_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x2F, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x4F, 0x37, 0x00, 0x08 },	/* 350   500      3.1   */
-	{ 0xC, 0x63, 0x2F, 0x00, 0x10 },	/* 350   700      6.0   */
-	{ 0x6, 0x7D, 0x2A, 0x00, 0x15 },	/* 350   900      8.2   */
-	{ 0xA, 0x4C, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x73, 0x34, 0x00, 0x0B },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x6E, 0x3E, 0x00, 0x01 },	/* 650   700      0.6   */
-	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct cnl_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
-						/* NT mV Trans mV db    */
-	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
-	{ 0xA, 0x50, 0x38, 0x00, 0x07 },	/* 350   500      3.1   */
-	{ 0xC, 0x61, 0x33, 0x00, 0x0C },	/* 350   700      6.0   */
-	{ 0x6, 0x7F, 0x2E, 0x00, 0x11 },	/* 350   900      8.2   */
-	{ 0xA, 0x47, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
-	{ 0xC, 0x5F, 0x38, 0x00, 0x07 },	/* 500   700      2.9   */
-	{ 0x6, 0x7F, 0x2F, 0x00, 0x10 },	/* 500   900      5.1   */
-	{ 0xC, 0x5F, 0x3F, 0x00, 0x00 },	/* 650   700      0.6   */
-	{ 0x6, 0x7E, 0x36, 0x00, 0x09 },	/* 600   900      3.5   */
-	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
-};
-
-static const struct tgl_dkl_phy_ddi_buf_trans adlp_dkl_phy_dp_ddi_trans_hbr[] = {
-				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
-	{ 0x7, 0x0, 0x01 },	/* 0	0	400mV		0 dB */
-	{ 0x5, 0x0, 0x06 },	/* 0	1	400mV		3.5 dB */
-	{ 0x2, 0x0, 0x0B },	/* 0	2	400mV		6 dB */
-	{ 0x0, 0x0, 0x17 },	/* 0	3	400mV		9.5 dB */
-	{ 0x5, 0x0, 0x00 },	/* 1	0	600mV		0 dB */
-	{ 0x2, 0x0, 0x08 },	/* 1	1	600mV		3.5 dB */
-	{ 0x0, 0x0, 0x14 },	/* 1	2	600mV		6 dB */
-	{ 0x2, 0x0, 0x00 },	/* 2	0	800mV		0 dB */
-	{ 0x0, 0x0, 0x0B },	/* 2	1	800mV		3.5 dB */
-	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB */
-};
-
-static const struct tgl_dkl_phy_ddi_buf_trans adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3[] = {
-				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
-	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
-	{ 0x5, 0x0, 0x04 },	/* 0	1	400mV		3.5 dB */
-	{ 0x2, 0x0, 0x0A },	/* 0	2	400mV		6 dB */
-	{ 0x0, 0x0, 0x18 },	/* 0	3	400mV		9.5 dB */
-	{ 0x5, 0x0, 0x00 },	/* 1	0	600mV		0 dB */
-	{ 0x2, 0x0, 0x06 },	/* 1	1	600mV		3.5 dB */
-	{ 0x0, 0x0, 0x14 },	/* 1	2	600mV		6 dB */
-	{ 0x2, 0x0, 0x00 },	/* 2	0	800mV		0 dB */
-	{ 0x0, 0x0, 0x09 },	/* 2	1	800mV		3.5 dB */
-	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB */
-};
-
-bool is_hobl_buf_trans(const struct cnl_ddi_buf_trans *table)
-{
-	return table == tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
-}
+static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_edp_hbr2_hobl[] = {
+							/* VS	pre-emp	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 0	0	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 0	1	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 0	2	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 0	3	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 1	0	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 1	1	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 1	2	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 2	0	*/
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 2	1	*/
+};
 
-static const struct ddi_buf_trans *
-bdw_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_edp_hbr2_hobl = {
+	.entries = _tgl_combo_phy_ddi_translations_edp_hbr2_hobl,
+	.num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_edp_hbr2_hobl),
+};
 
-	if (dev_priv->vbt.edp.low_vswing) {
-		*n_entries = ARRAY_SIZE(bdw_ddi_translations_edp);
-		return bdw_ddi_translations_edp;
-	} else {
-		*n_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
-		return bdw_ddi_translations_dp;
-	}
-}
+static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_hbr[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x2F, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7D, 0x2A, 0x00, 0x15 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x4C, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x73, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x6E, 0x3E, 0x00, 0x01 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-static const struct ddi_buf_trans *
-skl_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const struct intel_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr = {
+	.entries = _rkl_combo_phy_ddi_translations_dp_hbr,
+	.num_entries = ARRAY_SIZE(_rkl_combo_phy_ddi_translations_dp_hbr),
+};
 
-	if (IS_SKL_ULX(dev_priv)) {
-		*n_entries = ARRAY_SIZE(skl_y_ddi_translations_dp);
-		return skl_y_ddi_translations_dp;
-	} else if (IS_SKL_ULT(dev_priv)) {
-		*n_entries = ARRAY_SIZE(skl_u_ddi_translations_dp);
-		return skl_u_ddi_translations_dp;
-	} else {
-		*n_entries = ARRAY_SIZE(skl_ddi_translations_dp);
-		return skl_ddi_translations_dp;
-	}
-}
+static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x50, 0x38, 0x00, 0x07 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x61, 0x33, 0x00, 0x0C } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2E, 0x00, 0x11 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x47, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x5F, 0x38, 0x00, 0x07 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x5F, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7E, 0x36, 0x00, 0x09 } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-static const struct ddi_buf_trans *
-kbl_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const struct intel_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr2_hbr3 = {
+	.entries = _rkl_combo_phy_ddi_translations_dp_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_rkl_combo_phy_ddi_translations_dp_hbr2_hbr3),
+};
 
-	if (IS_KBL_ULX(dev_priv) ||
-	    IS_CFL_ULX(dev_priv) ||
-	    IS_CML_ULX(dev_priv)) {
-		*n_entries = ARRAY_SIZE(kbl_y_ddi_translations_dp);
-		return kbl_y_ddi_translations_dp;
-	} else if (IS_KBL_ULT(dev_priv) ||
-		   IS_CFL_ULT(dev_priv) ||
-		   IS_CML_ULT(dev_priv)) {
-		*n_entries = ARRAY_SIZE(kbl_u_ddi_translations_dp);
-		return kbl_u_ddi_translations_dp;
-	} else {
-		*n_entries = ARRAY_SIZE(kbl_ddi_translations_dp);
-		return kbl_ddi_translations_dp;
-	}
-}
+static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x31, 0x00, 0x0E } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2C, 0x00, 0x13 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x47, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x63, 0x37, 0x00, 0x08 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x73, 0x32, 0x00, 0x0D } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x58, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-static const struct ddi_buf_trans *
-skl_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_dp_hbr2_hbr3 = {
+	.entries = _adls_combo_phy_ddi_translations_dp_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_dp_hbr2_hbr3),
+};
 
-	if (dev_priv->vbt.edp.low_vswing) {
-		if (IS_SKL_ULX(dev_priv) ||
-		    IS_KBL_ULX(dev_priv) ||
-		    IS_CFL_ULX(dev_priv) ||
-		    IS_CML_ULX(dev_priv)) {
-			*n_entries = ARRAY_SIZE(skl_y_ddi_translations_edp);
-			return skl_y_ddi_translations_edp;
-		} else if (IS_SKL_ULT(dev_priv) ||
-			   IS_KBL_ULT(dev_priv) ||
-			   IS_CFL_ULT(dev_priv) ||
-			   IS_CML_ULT(dev_priv)) {
-			*n_entries = ARRAY_SIZE(skl_u_ddi_translations_edp);
-			return skl_u_ddi_translations_edp;
-		} else {
-			*n_entries = ARRAY_SIZE(skl_ddi_translations_edp);
-			return skl_ddi_translations_edp;
-		}
-	}
+static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_edp_hbr2[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0x9, 0x73, 0x3D, 0x00, 0x02 } },	/* 200   200      0.0   */
+	{ .icl = { 0x9, 0x7A, 0x3C, 0x00, 0x03 } },	/* 200   250      1.9   */
+	{ .icl = { 0x9, 0x7F, 0x3B, 0x00, 0x04 } },	/* 200   300      3.5   */
+	{ .icl = { 0x4, 0x6C, 0x33, 0x00, 0x0C } },	/* 200   350      4.9   */
+	{ .icl = { 0x2, 0x73, 0x3A, 0x00, 0x05 } },	/* 250   250      0.0   */
+	{ .icl = { 0x2, 0x7C, 0x38, 0x00, 0x07 } },	/* 250   300      1.6   */
+	{ .icl = { 0x4, 0x5A, 0x36, 0x00, 0x09 } },	/* 250   350      2.9   */
+	{ .icl = { 0x4, 0x57, 0x3D, 0x00, 0x02 } },	/* 300   300      0.0   */
+	{ .icl = { 0x4, 0x65, 0x38, 0x00, 0x07 } },	/* 300   350      1.3   */
+	{ .icl = { 0x4, 0x6C, 0x3A, 0x00, 0x05 } },	/* 350   350      0.0   */
+};
 
-	if (IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv) ||
-	    IS_COMETLAKE(dev_priv))
-		return kbl_get_buf_trans_dp(encoder, n_entries);
-	else
-		return skl_get_buf_trans_dp(encoder, n_entries);
-}
+static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_edp_hbr2 = {
+	.entries = _adls_combo_phy_ddi_translations_edp_hbr2,
+	.num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_edp_hbr2),
+};
 
-static const struct ddi_buf_trans *
-skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries)
-{
-	if (IS_SKL_ULX(dev_priv) ||
-	    IS_KBL_ULX(dev_priv) ||
-	    IS_CFL_ULX(dev_priv) ||
-	    IS_CML_ULX(dev_priv)) {
-		*n_entries = ARRAY_SIZE(skl_y_ddi_translations_hdmi);
-		return skl_y_ddi_translations_hdmi;
-	} else {
-		*n_entries = ARRAY_SIZE(skl_ddi_translations_hdmi);
-		return skl_ddi_translations_hdmi;
-	}
-}
+static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_edp_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x63, 0x31, 0x00, 0x0E } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2C, 0x00, 0x13 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x47, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x63, 0x37, 0x00, 0x08 } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x73, 0x32, 0x00, 0x0D } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x58, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-static int skl_buf_trans_num_entries(enum port port, int n_entries)
-{
-	/* Only DDIA and DDIE can select the 10th register with DP */
-	if (port == PORT_A || port == PORT_E)
-		return min(n_entries, 10);
-	else
-		return min(n_entries, 9);
-}
+static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_edp_hbr3 = {
+	.entries = _adls_combo_phy_ddi_translations_edp_hbr3,
+	.num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_edp_hbr3),
+};
 
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_hdmi[] = {
+							/* NT mV Trans mV    db   */
+	{ .icl = { 0x6, 0x60, 0x3F, 0x00, 0x00 } },	/*  400    400      0.0 */
+	{ .icl = { 0x6, 0x68, 0x3F, 0x00, 0x00 } },	/*  500    500      0.0 */
+	{ .icl = { 0xA, 0x73, 0x3F, 0x00, 0x00 } },	/*  650    650      0.0 ALS */
+	{ .icl = { 0xA, 0x78, 0x3F, 0x00, 0x00 } },	/*  800    800      0.0 */
+	{ .icl = { 0xB, 0x7F, 0x3F, 0x00, 0x00 } },	/* 1000   1000      0.0 Re-timer */
+	{ .icl = { 0xB, 0x7F, 0x3B, 0x00, 0x04 } },	/* Full    Red     -1.5 */
+	{ .icl = { 0xB, 0x7F, 0x39, 0x00, 0x06 } },	/* Full    Red     -1.8 */
+	{ .icl = { 0xB, 0x7F, 0x37, 0x00, 0x08 } },	/* Full    Red     -2.0 CRLS */
+	{ .icl = { 0xB, 0x7F, 0x35, 0x00, 0x0A } },	/* Full    Red     -2.5 */
+	{ .icl = { 0xB, 0x7F, 0x33, 0x00, 0x0C } },	/* Full    Red     -3.0 */
+};
 
-	if (IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv) ||
-	    IS_COMETLAKE(dev_priv)) {
-		const struct ddi_buf_trans *ddi_translations =
-			kbl_get_buf_trans_dp(encoder, n_entries);
-		*n_entries = skl_buf_trans_num_entries(encoder->port, *n_entries);
-		return ddi_translations;
-	} else if (IS_SKYLAKE(dev_priv)) {
-		const struct ddi_buf_trans *ddi_translations =
-			skl_get_buf_trans_dp(encoder, n_entries);
-		*n_entries = skl_buf_trans_num_entries(encoder->port, *n_entries);
-		return ddi_translations;
-	} else if (IS_BROADWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
-		return  bdw_ddi_translations_dp;
-	} else if (IS_HASWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(hsw_ddi_translations_dp);
-		return hsw_ddi_translations_dp;
-	}
+static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_hdmi = {
+	.entries = _adlp_combo_phy_ddi_translations_hdmi,
+	.num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_hdmi),
+	.hdmi_default_entry = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_hdmi) - 1,
+};
 
-	*n_entries = 0;
-	return NULL;
-}
+static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp_hbr[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x71, 0x31, 0x00, 0x0E } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2C, 0x00, 0x13 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x4C, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x73, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x73, 0x3E, 0x00, 0x01 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_dp_hbr = {
+	.entries = _adlp_combo_phy_ddi_translations_dp_hbr,
+	.num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_dp_hbr),
+};
 
-	if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv)) {
-		const struct ddi_buf_trans *ddi_translations =
-			skl_get_buf_trans_edp(encoder, n_entries);
-		*n_entries = skl_buf_trans_num_entries(encoder->port, *n_entries);
-		return ddi_translations;
-	} else if (IS_BROADWELL(dev_priv)) {
-		return bdw_get_buf_trans_edp(encoder, n_entries);
-	} else if (IS_HASWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(hsw_ddi_translations_dp);
-		return hsw_ddi_translations_dp;
-	}
+static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp_hbr2_hbr3[] = {
+							/* NT mV Trans mV db    */
+	{ .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } },	/* 350   350      0.0   */
+	{ .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } },	/* 350   500      3.1   */
+	{ .icl = { 0xC, 0x71, 0x2F, 0x00, 0x10 } },	/* 350   700      6.0   */
+	{ .icl = { 0x6, 0x7F, 0x2B, 0x00, 0x14 } },	/* 350   900      8.2   */
+	{ .icl = { 0xA, 0x4C, 0x3F, 0x00, 0x00 } },	/* 500   500      0.0   */
+	{ .icl = { 0xC, 0x73, 0x34, 0x00, 0x0B } },	/* 500   700      2.9   */
+	{ .icl = { 0x6, 0x7F, 0x30, 0x00, 0x0F } },	/* 500   900      5.1   */
+	{ .icl = { 0xC, 0x63, 0x3F, 0x00, 0x00 } },	/* 650   700      0.6   */
+	{ .icl = { 0x6, 0x7F, 0x38, 0x00, 0x07 } },	/* 600   900      3.5   */
+	{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } },	/* 900   900      0.0   */
+};
 
-	*n_entries = 0;
-	return NULL;
-}
+static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_dp_hbr2_hbr3 = {
+	.entries = _adlp_combo_phy_ddi_translations_dp_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_dp_hbr2_hbr3),
+};
 
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_fdi(struct drm_i915_private *dev_priv,
-			    int *n_entries)
-{
-	if (IS_BROADWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(bdw_ddi_translations_fdi);
-		return bdw_ddi_translations_fdi;
-	} else if (IS_HASWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(hsw_ddi_translations_fdi);
-		return hsw_ddi_translations_fdi;
-	}
+static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_edp_hbr3 = {
+	.entries = _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+	.num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3),
+};
+
+static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_edp_up_to_hbr2 = {
+	.entries = _icl_combo_phy_ddi_translations_edp_hbr2,
+	.num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_edp_hbr2),
+};
 
-	*n_entries = 0;
-	return NULL;
+static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_hbr[] = {
+					/* VS	pre-emp	Non-trans mV	Pre-emph dB */
+	{ .dkl = { 0x7, 0x0, 0x01 } },	/* 0	0	400mV		0 dB */
+	{ .dkl = { 0x5, 0x0, 0x06 } },	/* 0	1	400mV		3.5 dB */
+	{ .dkl = { 0x2, 0x0, 0x0B } },	/* 0	2	400mV		6 dB */
+	{ .dkl = { 0x0, 0x0, 0x17 } },	/* 0	3	400mV		9.5 dB */
+	{ .dkl = { 0x5, 0x0, 0x00 } },	/* 1	0	600mV		0 dB */
+	{ .dkl = { 0x2, 0x0, 0x08 } },	/* 1	1	600mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x14 } },	/* 1	2	600mV		6 dB */
+	{ .dkl = { 0x2, 0x0, 0x00 } },	/* 2	0	800mV		0 dB */
+	{ .dkl = { 0x0, 0x0, 0x0B } },	/* 2	1	800mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x00 } },	/* 3	0	1200mV		0 dB */
+};
+
+static const struct intel_ddi_buf_trans adlp_dkl_phy_ddi_translations_dp_hbr = {
+	.entries = _adlp_dkl_phy_ddi_translations_dp_hbr,
+	.num_entries = ARRAY_SIZE(_adlp_dkl_phy_ddi_translations_dp_hbr),
+};
+
+static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3[] = {
+					/* VS	pre-emp	Non-trans mV	Pre-emph dB */
+	{ .dkl = { 0x7, 0x0, 0x00 } },	/* 0	0	400mV		0 dB */
+	{ .dkl = { 0x5, 0x0, 0x04 } },	/* 0	1	400mV		3.5 dB */
+	{ .dkl = { 0x2, 0x0, 0x0A } },	/* 0	2	400mV		6 dB */
+	{ .dkl = { 0x0, 0x0, 0x18 } },	/* 0	3	400mV		9.5 dB */
+	{ .dkl = { 0x5, 0x0, 0x00 } },	/* 1	0	600mV		0 dB */
+	{ .dkl = { 0x2, 0x0, 0x06 } },	/* 1	1	600mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x14 } },	/* 1	2	600mV		6 dB */
+	{ .dkl = { 0x2, 0x0, 0x00 } },	/* 2	0	800mV		0 dB */
+	{ .dkl = { 0x0, 0x0, 0x09 } },	/* 2	1	800mV		3.5 dB */
+	{ .dkl = { 0x0, 0x0, 0x00 } },	/* 3	0	1200mV		0 dB */
+};
+
+static const struct intel_ddi_buf_trans adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3 = {
+	.entries = _adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3,
+	.num_entries = ARRAY_SIZE(_adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3),
+};
+
+bool is_hobl_buf_trans(const struct intel_ddi_buf_trans *table)
+{
+	return table == &tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
 }
 
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_hdmi(struct intel_encoder *encoder,
-			     int *n_entries)
+static const struct intel_ddi_buf_trans *
+intel_get_buf_trans(const struct intel_ddi_buf_trans *ddi_translations, int *num_entries)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	*num_entries = ddi_translations->num_entries;
+	return ddi_translations;
+}
 
-	if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv)) {
-		return skl_get_buf_trans_hdmi(dev_priv, n_entries);
-	} else if (IS_BROADWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
-		return bdw_ddi_translations_hdmi;
-	} else if (IS_HASWELL(dev_priv)) {
-		*n_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
-		return hsw_ddi_translations_hdmi;
-	}
+static const struct intel_ddi_buf_trans *
+hsw_get_buf_trans(struct intel_encoder *encoder,
+		  const struct intel_crtc_state *crtc_state,
+		  int *n_entries)
+{
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG))
+		return intel_get_buf_trans(&hsw_ddi_translations_fdi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&hsw_ddi_translations_hdmi, n_entries);
+	else
+		return intel_get_buf_trans(&hsw_ddi_translations_dp, n_entries);
+}
 
-	*n_entries = 0;
-	return NULL;
+static const struct intel_ddi_buf_trans *
+bdw_get_buf_trans(struct intel_encoder *encoder,
+		  const struct intel_crtc_state *crtc_state,
+		  int *n_entries)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG))
+		return intel_get_buf_trans(&bdw_ddi_translations_fdi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&bdw_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return intel_get_buf_trans(&bdw_ddi_translations_edp, n_entries);
+	else
+		return intel_get_buf_trans(&bdw_ddi_translations_dp, n_entries);
 }
 
-static const struct bxt_ddi_buf_trans *
-bxt_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries)
+static int skl_buf_trans_num_entries(enum port port, int n_entries)
 {
-	*n_entries = ARRAY_SIZE(bxt_ddi_translations_dp);
-	return bxt_ddi_translations_dp;
+	/* Only DDIA and DDIE can select the 10th register with DP */
+	if (port == PORT_A || port == PORT_E)
+		return min(n_entries, 10);
+	else
+		return min(n_entries, 9);
 }
 
-static const struct bxt_ddi_buf_trans *
-bxt_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
+static const struct intel_ddi_buf_trans *
+_skl_get_buf_trans_dp(struct intel_encoder *encoder,
+		      const struct intel_ddi_buf_trans *ddi_translations,
+		      int *n_entries)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	ddi_translations = intel_get_buf_trans(ddi_translations, n_entries);
+	*n_entries = skl_buf_trans_num_entries(encoder->port, *n_entries);
+	return ddi_translations;
+}
 
-	if (dev_priv->vbt.edp.low_vswing) {
-		*n_entries = ARRAY_SIZE(bxt_ddi_translations_edp);
-		return bxt_ddi_translations_edp;
-	}
+static const struct intel_ddi_buf_trans *
+skl_y_get_buf_trans(struct intel_encoder *encoder,
+		    const struct intel_crtc_state *crtc_state,
+		    int *n_entries)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 
-	return bxt_get_buf_trans_dp(encoder, n_entries);
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&skl_y_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_dp, n_entries);
 }
 
-static const struct bxt_ddi_buf_trans *
-bxt_get_buf_trans_hdmi(struct intel_encoder *encoder, int *n_entries)
+static const struct intel_ddi_buf_trans *
+skl_u_get_buf_trans(struct intel_encoder *encoder,
+		    const struct intel_crtc_state *crtc_state,
+		    int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(bxt_ddi_translations_hdmi);
-	return bxt_ddi_translations_hdmi;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_dp, n_entries);
 }
 
-const struct bxt_ddi_buf_trans *
-bxt_get_buf_trans(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+skl_get_buf_trans(struct intel_encoder *encoder,
 		  const struct intel_crtc_state *crtc_state,
 		  int *n_entries)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return bxt_get_buf_trans_hdmi(encoder, n_entries);
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		return bxt_get_buf_trans_edp(encoder, n_entries);
-	return bxt_get_buf_trans_dp(encoder, n_entries);
+		return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_dp, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-cnl_get_buf_trans_hdmi(struct intel_encoder *encoder, int *n_entries)
+static const struct intel_ddi_buf_trans *
+kbl_y_get_buf_trans(struct intel_encoder *encoder,
+		    const struct intel_crtc_state *crtc_state,
+		    int *n_entries)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 voltage = intel_de_read(dev_priv, CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
-
-	if (voltage == VOLTAGE_INFO_0_85V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_hdmi_0_85V);
-		return cnl_ddi_translations_hdmi_0_85V;
-	} else if (voltage == VOLTAGE_INFO_0_95V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_hdmi_0_95V);
-		return cnl_ddi_translations_hdmi_0_95V;
-	} else if (voltage == VOLTAGE_INFO_1_05V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_hdmi_1_05V);
-		return cnl_ddi_translations_hdmi_1_05V;
-	} else {
-		*n_entries = 1; /* shut up gcc */
-		MISSING_CASE(voltage);
-	}
-	return NULL;
-}
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 
-static const struct cnl_ddi_buf_trans *
-cnl_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 voltage = intel_de_read(dev_priv, CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
-
-	if (voltage == VOLTAGE_INFO_0_85V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_dp_0_85V);
-		return cnl_ddi_translations_dp_0_85V;
-	} else if (voltage == VOLTAGE_INFO_0_95V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_dp_0_95V);
-		return cnl_ddi_translations_dp_0_95V;
-	} else if (voltage == VOLTAGE_INFO_1_05V) {
-		*n_entries = ARRAY_SIZE(cnl_ddi_translations_dp_1_05V);
-		return cnl_ddi_translations_dp_1_05V;
-	} else {
-		*n_entries = 1; /* shut up gcc */
-		MISSING_CASE(voltage);
-	}
-	return NULL;
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&skl_y_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &kbl_y_ddi_translations_dp, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-cnl_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
+static const struct intel_ddi_buf_trans *
+kbl_u_get_buf_trans(struct intel_encoder *encoder,
+		    const struct intel_crtc_state *crtc_state,
+		    int *n_entries)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 voltage = intel_de_read(dev_priv, CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
-
-	if (dev_priv->vbt.edp.low_vswing) {
-		if (voltage == VOLTAGE_INFO_0_85V) {
-			*n_entries = ARRAY_SIZE(cnl_ddi_translations_edp_0_85V);
-			return cnl_ddi_translations_edp_0_85V;
-		} else if (voltage == VOLTAGE_INFO_0_95V) {
-			*n_entries = ARRAY_SIZE(cnl_ddi_translations_edp_0_95V);
-			return cnl_ddi_translations_edp_0_95V;
-		} else if (voltage == VOLTAGE_INFO_1_05V) {
-			*n_entries = ARRAY_SIZE(cnl_ddi_translations_edp_1_05V);
-			return cnl_ddi_translations_edp_1_05V;
-		} else {
-			*n_entries = 1; /* shut up gcc */
-			MISSING_CASE(voltage);
-		}
-		return NULL;
-	} else {
-		return cnl_get_buf_trans_dp(encoder, n_entries);
-	}
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &kbl_u_ddi_translations_dp, n_entries);
 }
 
-const struct cnl_ddi_buf_trans *
-cnl_get_buf_trans(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+kbl_get_buf_trans(struct intel_encoder *encoder,
 		  const struct intel_crtc_state *crtc_state,
 		  int *n_entries)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return cnl_get_buf_trans_hdmi(encoder, n_entries);
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		return cnl_get_buf_trans_edp(encoder, n_entries);
-	return cnl_get_buf_trans_dp(encoder, n_entries);
+		return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_edp, n_entries);
+	else
+		return _skl_get_buf_trans_dp(encoder, &kbl_ddi_translations_dp, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-icl_get_combo_buf_trans_hdmi(struct intel_encoder *encoder,
-			     const struct intel_crtc_state *crtc_state,
-			     int *n_entries)
+static const struct intel_ddi_buf_trans *
+bxt_get_buf_trans(struct intel_encoder *encoder,
+		  const struct intel_crtc_state *crtc_state,
+		  int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi);
-	return icl_combo_phy_ddi_translations_hdmi;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&bxt_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 i915->vbt.edp.low_vswing)
+		return intel_get_buf_trans(&bxt_ddi_translations_edp, n_entries);
+	else
+		return intel_get_buf_trans(&bxt_ddi_translations_dp, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 icl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state,
 			   int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2);
-	return icl_combo_phy_ddi_translations_dp_hbr2;
+	return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+				   n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 icl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state,
 			    int *n_entries)
@@ -1109,294 +1174,391 @@ icl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	if (crtc_state->port_clock > 540000) {
-		*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3);
-		return icl_combo_phy_ddi_translations_edp_hbr3;
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+					   n_entries);
 	} else if (dev_priv->vbt.edp.low_vswing) {
-		*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2);
-		return icl_combo_phy_ddi_translations_edp_hbr2;
-	} else if (IS_DG1(dev_priv) && crtc_state->port_clock > 270000) {
-		*n_entries = ARRAY_SIZE(dg1_combo_phy_ddi_translations_dp_hbr2_hbr3);
-		return dg1_combo_phy_ddi_translations_dp_hbr2_hbr3;
-	} else if (IS_DG1(dev_priv)) {
-		*n_entries = ARRAY_SIZE(dg1_combo_phy_ddi_translations_dp_rbr_hbr);
-		return dg1_combo_phy_ddi_translations_dp_rbr_hbr;
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2,
+					   n_entries);
 	}
 
 	return icl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-const struct cnl_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 icl_get_combo_buf_trans(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state,
 			int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return icl_get_combo_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
 	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
 		return icl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
 	else
 		return icl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct icl_mg_phy_ddi_buf_trans *
-icl_get_mg_buf_trans_hdmi(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *crtc_state,
-			  int *n_entries)
-{
-	*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hdmi);
-	return icl_mg_phy_ddi_translations_hdmi;
-}
-
-static const struct icl_mg_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 icl_get_mg_buf_trans_dp(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state,
 			int *n_entries)
 {
 	if (crtc_state->port_clock > 270000) {
-		*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hbr2_hbr3);
-		return icl_mg_phy_ddi_translations_hbr2_hbr3;
+		return intel_get_buf_trans(&icl_mg_phy_ddi_translations_hbr2_hbr3,
+					   n_entries);
 	} else {
-		*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_rbr_hbr);
-		return icl_mg_phy_ddi_translations_rbr_hbr;
+		return intel_get_buf_trans(&icl_mg_phy_ddi_translations_rbr_hbr,
+					   n_entries);
 	}
 }
 
-const struct icl_mg_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 icl_get_mg_buf_trans(struct intel_encoder *encoder,
 		     const struct intel_crtc_state *crtc_state,
 		     int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return icl_get_mg_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&icl_mg_phy_ddi_translations_hdmi, n_entries);
 	else
 		return icl_get_mg_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-ehl_get_combo_buf_trans_hdmi(struct intel_encoder *encoder,
-			     const struct intel_crtc_state *crtc_state,
-			     int *n_entries)
+static const struct intel_ddi_buf_trans *
+ehl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    int *n_entries)
+{
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&ehl_combo_phy_ddi_translations_edp_hbr2, n_entries);
+	else
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+ehl_get_combo_buf_trans(struct intel_encoder *encoder,
+			const struct intel_crtc_state *crtc_state,
+			int *n_entries)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 dev_priv->vbt.edp.low_vswing)
+		return ehl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+	else
+		return intel_get_buf_trans(&ehl_combo_phy_ddi_translations_dp, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+jsl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi);
-	return icl_combo_phy_ddi_translations_hdmi;
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&jsl_combo_phy_ddi_translations_edp_hbr2, n_entries);
+	else
+		return intel_get_buf_trans(&jsl_combo_phy_ddi_translations_edp_hbr, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+jsl_get_combo_buf_trans(struct intel_encoder *encoder,
+			const struct intel_crtc_state *crtc_state,
+			int *n_entries)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) &&
+		 dev_priv->vbt.edp.low_vswing)
+		return jsl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+	else
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-ehl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+tgl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state,
 			   int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_dp);
-	return ehl_combo_phy_ddi_translations_dp;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (crtc_state->port_clock > 270000) {
+		if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) {
+			return intel_get_buf_trans(&tgl_uy_combo_phy_ddi_translations_dp_hbr2,
+						   n_entries);
+		} else {
+			return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr2,
+						   n_entries);
+		}
+	} else {
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr,
+					   n_entries);
+	}
 }
 
-static const struct cnl_ddi_buf_trans *
-ehl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+tgl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state,
 			    int *n_entries)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
-	if (dev_priv->vbt.edp.low_vswing) {
-		*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2);
-		return icl_combo_phy_ddi_translations_edp_hbr2;
+	if (crtc_state->port_clock > 540000) {
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+					   n_entries);
+	} else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) {
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl,
+					   n_entries);
+	} else if (dev_priv->vbt.edp.low_vswing) {
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2,
+					   n_entries);
 	}
 
-	return ehl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+	return tgl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-const struct cnl_ddi_buf_trans *
-ehl_get_combo_buf_trans(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+tgl_get_combo_buf_trans(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state,
 			int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return ehl_get_combo_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
 	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		return ehl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+		return tgl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
 	else
-		return ehl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+		return tgl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-jsl_get_combo_buf_trans_hdmi(struct intel_encoder *encoder,
-			     const struct intel_crtc_state *crtc_state,
-			     int *n_entries)
+static const struct intel_ddi_buf_trans *
+dg1_get_combo_buf_trans_dp(struct intel_encoder *encoder,
+			   const struct intel_crtc_state *crtc_state,
+			   int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi);
-	return icl_combo_phy_ddi_translations_hdmi;
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&dg1_combo_phy_ddi_translations_dp_hbr2_hbr3,
+					   n_entries);
+	else
+		return intel_get_buf_trans(&dg1_combo_phy_ddi_translations_dp_rbr_hbr,
+					   n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-jsl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+dg1_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    int *n_entries)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+	if (crtc_state->port_clock > 540000)
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+					   n_entries);
+	else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed)
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl,
+					   n_entries);
+	else if (dev_priv->vbt.edp.low_vswing)
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2,
+					   n_entries);
+	else
+		return dg1_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+dg1_get_combo_buf_trans(struct intel_encoder *encoder,
+			const struct intel_crtc_state *crtc_state,
+			int *n_entries)
+{
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
+		return dg1_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+	else
+		return dg1_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+rkl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state,
 			   int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2);
-	return icl_combo_phy_ddi_translations_dp_hbr2;
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&rkl_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries);
+	else
+		return intel_get_buf_trans(&rkl_combo_phy_ddi_translations_dp_hbr, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-jsl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+rkl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state,
 			    int *n_entries)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
-	if (dev_priv->vbt.edp.low_vswing) {
-		if (crtc_state->port_clock > 270000) {
-			*n_entries = ARRAY_SIZE(jsl_combo_phy_ddi_translations_edp_hbr2);
-			return jsl_combo_phy_ddi_translations_edp_hbr2;
-		} else {
-			*n_entries = ARRAY_SIZE(jsl_combo_phy_ddi_translations_edp_hbr);
-			return jsl_combo_phy_ddi_translations_edp_hbr;
-		}
+	if (crtc_state->port_clock > 540000) {
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3,
+					   n_entries);
+	} else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) {
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl,
+					   n_entries);
+	} else if (dev_priv->vbt.edp.low_vswing) {
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2,
+					   n_entries);
 	}
 
-	return jsl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+	return rkl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-const struct cnl_ddi_buf_trans *
-jsl_get_combo_buf_trans(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+rkl_get_combo_buf_trans(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state,
 			int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return jsl_get_combo_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
 	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		return jsl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+		return rkl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
 	else
-		return jsl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+		return rkl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-tgl_get_combo_buf_trans_hdmi(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+adls_get_combo_buf_trans_dp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    int *n_entries)
+{
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&adls_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries);
+	else
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+adls_get_combo_buf_trans_edp(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state,
 			     int *n_entries)
 {
-	*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi);
-	return icl_combo_phy_ddi_translations_hdmi;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+	if (crtc_state->port_clock > 540000)
+		return intel_get_buf_trans(&adls_combo_phy_ddi_translations_edp_hbr3, n_entries);
+	else if (i915->vbt.edp.hobl && !intel_dp->hobl_failed)
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, n_entries);
+	else if (i915->vbt.edp.low_vswing)
+		return intel_get_buf_trans(&adls_combo_phy_ddi_translations_edp_hbr2, n_entries);
+	else
+		return adls_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-tgl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
-			   const struct intel_crtc_state *crtc_state,
-			   int *n_entries)
+static const struct intel_ddi_buf_trans *
+adls_get_combo_buf_trans(struct intel_encoder *encoder,
+			 const struct intel_crtc_state *crtc_state,
+			 int *n_entries)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (crtc_state->port_clock > 270000) {
-		if (IS_ROCKETLAKE(dev_priv)) {
-			*n_entries = ARRAY_SIZE(rkl_combo_phy_ddi_translations_dp_hbr2_hbr3);
-			return rkl_combo_phy_ddi_translations_dp_hbr2_hbr3;
-		} else if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) {
-			*n_entries = ARRAY_SIZE(tgl_uy_combo_phy_ddi_translations_dp_hbr2);
-			return tgl_uy_combo_phy_ddi_translations_dp_hbr2;
-		} else {
-			*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2);
-			return tgl_combo_phy_ddi_translations_dp_hbr2;
-		}
-	} else {
-		if (IS_ROCKETLAKE(dev_priv)) {
-			*n_entries = ARRAY_SIZE(rkl_combo_phy_ddi_translations_dp_hbr);
-			return rkl_combo_phy_ddi_translations_dp_hbr;
-		} else {
-			*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr);
-			return tgl_combo_phy_ddi_translations_dp_hbr;
-		}
-	}
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries);
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
+		return adls_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+	else
+		return adls_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct cnl_ddi_buf_trans *
-tgl_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+static const struct intel_ddi_buf_trans *
+adlp_get_combo_buf_trans_dp(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state,
 			    int *n_entries)
 {
+	if (crtc_state->port_clock > 270000)
+		return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries);
+	else
+		return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_dp_hbr, n_entries);
+}
+
+static const struct intel_ddi_buf_trans *
+adlp_get_combo_buf_trans_edp(struct intel_encoder *encoder,
+			     const struct intel_crtc_state *crtc_state,
+			     int *n_entries)
+{
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	if (crtc_state->port_clock > 540000) {
-		*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3);
-		return icl_combo_phy_ddi_translations_edp_hbr3;
+		return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_edp_hbr3,
+					   n_entries);
 	} else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) {
-		*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_edp_hbr2_hobl);
-		return tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
+		return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl,
+					   n_entries);
 	} else if (dev_priv->vbt.edp.low_vswing) {
-		*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2);
-		return icl_combo_phy_ddi_translations_edp_hbr2;
+		return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_edp_up_to_hbr2,
+					   n_entries);
 	}
 
-	return tgl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+	return adlp_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-const struct cnl_ddi_buf_trans *
-tgl_get_combo_buf_trans(struct intel_encoder *encoder,
-			const struct intel_crtc_state *crtc_state,
-			int *n_entries)
+static const struct intel_ddi_buf_trans *
+adlp_get_combo_buf_trans(struct intel_encoder *encoder,
+			 const struct intel_crtc_state *crtc_state,
+			 int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return tgl_get_combo_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_hdmi, n_entries);
 	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
-		return tgl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
+		return adlp_get_combo_buf_trans_edp(encoder, crtc_state, n_entries);
 	else
-		return tgl_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
+		return adlp_get_combo_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct tgl_dkl_phy_ddi_buf_trans *
-tgl_get_dkl_buf_trans_hdmi(struct intel_encoder *encoder,
-			   const struct intel_crtc_state *crtc_state,
-			   int *n_entries)
-{
-	*n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
-	return tgl_dkl_phy_hdmi_ddi_trans;
-}
-
-static const struct tgl_dkl_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 tgl_get_dkl_buf_trans_dp(struct intel_encoder *encoder,
 			 const struct intel_crtc_state *crtc_state,
 			 int *n_entries)
 {
 	if (crtc_state->port_clock > 270000) {
-		*n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans_hbr2);
-		return tgl_dkl_phy_dp_ddi_trans_hbr2;
+		return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_dp_hbr2,
+					   n_entries);
 	} else {
-		*n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans);
-		return tgl_dkl_phy_dp_ddi_trans;
+		return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_dp_hbr,
+					   n_entries);
 	}
 }
 
-const struct tgl_dkl_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 tgl_get_dkl_buf_trans(struct intel_encoder *encoder,
 		      const struct intel_crtc_state *crtc_state,
 		      int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return tgl_get_dkl_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_hdmi, n_entries);
 	else
 		return tgl_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries);
 }
 
-static const struct tgl_dkl_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 adlp_get_dkl_buf_trans_dp(struct intel_encoder *encoder,
 			  const struct intel_crtc_state *crtc_state,
 			  int *n_entries)
 {
 	if (crtc_state->port_clock > 270000) {
-		*n_entries = ARRAY_SIZE(adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3);
-		return adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3;
+		return intel_get_buf_trans(&adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3,
+					   n_entries);
+	} else {
+		return intel_get_buf_trans(&adlp_dkl_phy_ddi_translations_dp_hbr,
+					   n_entries);
 	}
-
-	*n_entries = ARRAY_SIZE(adlp_dkl_phy_dp_ddi_trans_hbr);
-	return adlp_dkl_phy_dp_ddi_trans_hbr;
 }
 
-const struct tgl_dkl_phy_ddi_buf_trans *
+static const struct intel_ddi_buf_trans *
 adlp_get_dkl_buf_trans(struct intel_encoder *encoder,
 		       const struct intel_crtc_state *crtc_state,
 		       int *n_entries)
 {
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		return tgl_get_dkl_buf_trans_hdmi(encoder, crtc_state, n_entries);
+		return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_hdmi, n_entries);
 	else
 		return adlp_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries);
 }
@@ -1406,43 +1568,68 @@ int intel_ddi_hdmi_num_entries(struct intel_encoder *encoder,
 			       int *default_entry)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	const struct intel_ddi_buf_trans *ddi_translations;
 	int n_entries;
 
-	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (intel_phy_is_combo(dev_priv, phy))
-			tgl_get_combo_buf_trans_hdmi(encoder, crtc_state, &n_entries);
-		else
-			tgl_get_dkl_buf_trans_hdmi(encoder, crtc_state, &n_entries);
-		*default_entry = n_entries - 1;
-	} else if (DISPLAY_VER(dev_priv) == 11) {
-		if (intel_phy_is_combo(dev_priv, phy))
-			icl_get_combo_buf_trans_hdmi(encoder, crtc_state, &n_entries);
-		else
-			icl_get_mg_buf_trans_hdmi(encoder, crtc_state, &n_entries);
-		*default_entry = n_entries - 1;
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		cnl_get_buf_trans_hdmi(encoder, &n_entries);
-		*default_entry = n_entries - 1;
-	} else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
-		bxt_get_buf_trans_hdmi(encoder, &n_entries);
-		*default_entry = n_entries - 1;
-	} else if (DISPLAY_VER(dev_priv) == 9) {
-		intel_ddi_get_buf_trans_hdmi(encoder, &n_entries);
-		*default_entry = 8;
-	} else if (IS_BROADWELL(dev_priv)) {
-		intel_ddi_get_buf_trans_hdmi(encoder, &n_entries);
-		*default_entry = 7;
-	} else if (IS_HASWELL(dev_priv)) {
-		intel_ddi_get_buf_trans_hdmi(encoder, &n_entries);
-		*default_entry = 6;
-	} else {
-		drm_WARN(&dev_priv->drm, 1, "ddi translation table missing\n");
+	ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries);
+
+	if (drm_WARN_ON(&dev_priv->drm, !ddi_translations)) {
+		*default_entry = 0;
 		return 0;
 	}
 
-	if (drm_WARN_ON_ONCE(&dev_priv->drm, n_entries == 0))
-		return 0;
+	*default_entry = ddi_translations->hdmi_default_entry;
 
 	return n_entries;
 }
+
+void intel_ddi_buf_trans_init(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+
+	if (IS_ALDERLAKE_P(i915)) {
+		if (intel_phy_is_combo(i915, phy))
+			encoder->get_buf_trans = adlp_get_combo_buf_trans;
+		else
+			encoder->get_buf_trans = adlp_get_dkl_buf_trans;
+	} else if (IS_ALDERLAKE_S(i915)) {
+		encoder->get_buf_trans = adls_get_combo_buf_trans;
+	} else if (IS_ROCKETLAKE(i915)) {
+		encoder->get_buf_trans = rkl_get_combo_buf_trans;
+	} else if (IS_DG1(i915)) {
+		encoder->get_buf_trans = dg1_get_combo_buf_trans;
+	} else if (DISPLAY_VER(i915) >= 12) {
+		if (intel_phy_is_combo(i915, phy))
+			encoder->get_buf_trans = tgl_get_combo_buf_trans;
+		else
+			encoder->get_buf_trans = tgl_get_dkl_buf_trans;
+	} else if (DISPLAY_VER(i915) == 11) {
+		if (IS_PLATFORM(i915, INTEL_JASPERLAKE))
+			encoder->get_buf_trans = jsl_get_combo_buf_trans;
+		else if (IS_PLATFORM(i915, INTEL_ELKHARTLAKE))
+			encoder->get_buf_trans = ehl_get_combo_buf_trans;
+		else if (intel_phy_is_combo(i915, phy))
+			encoder->get_buf_trans = icl_get_combo_buf_trans;
+		else
+			encoder->get_buf_trans = icl_get_mg_buf_trans;
+	} else if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) {
+		encoder->get_buf_trans = bxt_get_buf_trans;
+	} else if (IS_CML_ULX(i915) || IS_CFL_ULX(i915) || IS_KBL_ULX(i915)) {
+		encoder->get_buf_trans = kbl_y_get_buf_trans;
+	} else if (IS_CML_ULT(i915) || IS_CFL_ULT(i915) || IS_KBL_ULT(i915)) {
+		encoder->get_buf_trans = kbl_u_get_buf_trans;
+	} else if (IS_COMETLAKE(i915) || IS_COFFEELAKE(i915) || IS_KABYLAKE(i915)) {
+		encoder->get_buf_trans = kbl_get_buf_trans;
+	} else if (IS_SKL_ULX(i915)) {
+		encoder->get_buf_trans = skl_y_get_buf_trans;
+	} else if (IS_SKL_ULT(i915)) {
+		encoder->get_buf_trans = skl_u_get_buf_trans;
+	} else if (IS_SKYLAKE(i915)) {
+		encoder->get_buf_trans = skl_get_buf_trans;
+	} else if (IS_BROADWELL(i915)) {
+		encoder->get_buf_trans = bdw_get_buf_trans;
+	} else {
+		encoder->get_buf_trans = hsw_get_buf_trans;
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h
index 4c2efab38642..2acd720f9d4f 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h
@@ -12,7 +12,7 @@ struct drm_i915_private;
 struct intel_encoder;
 struct intel_crtc_state;
 
-struct ddi_buf_trans {
+struct hsw_ddi_buf_trans {
 	u32 trans1;	/* balance leg enable, de-emph level */
 	u32 trans2;	/* vref sel, vswing */
 	u8 i_boost;	/* SKL: I_boost; valid: 0x0, 0x1, 0x3, 0x7 */
@@ -25,7 +25,7 @@ struct bxt_ddi_buf_trans {
 	u8 deemphasis;
 };
 
-struct cnl_ddi_buf_trans {
+struct icl_ddi_buf_trans {
 	u8 dw2_swing_sel;
 	u8 dw7_n_scalar;
 	u8 dw4_cursor_coeff;
@@ -45,60 +45,26 @@ struct tgl_dkl_phy_ddi_buf_trans {
 	u32 dkl_de_emphasis_control;
 };
 
-bool is_hobl_buf_trans(const struct cnl_ddi_buf_trans *table);
+union intel_ddi_buf_trans_entry {
+	struct hsw_ddi_buf_trans hsw;
+	struct bxt_ddi_buf_trans bxt;
+	struct icl_ddi_buf_trans icl;
+	struct icl_mg_phy_ddi_buf_trans mg;
+	struct tgl_dkl_phy_ddi_buf_trans dkl;
+};
+
+struct intel_ddi_buf_trans {
+	const union intel_ddi_buf_trans_entry *entries;
+	u8 num_entries;
+	u8 hdmi_default_entry;
+};
+
+bool is_hobl_buf_trans(const struct intel_ddi_buf_trans *table);
 
 int intel_ddi_hdmi_num_entries(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *crtc_state,
 			       int *default_entry);
 
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries);
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_fdi(struct drm_i915_private *dev_priv,
-			    int *n_entries);
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_hdmi(struct intel_encoder *encoder,
-			     int *n_entries);
-const struct ddi_buf_trans *
-intel_ddi_get_buf_trans_dp(struct intel_encoder *encoder, int *n_entries);
-
-const struct bxt_ddi_buf_trans *
-bxt_get_buf_trans(struct intel_encoder *encoder,
-		  const struct intel_crtc_state *crtc_state,
-		  int *n_entries);
-
-const struct tgl_dkl_phy_ddi_buf_trans *
-adlp_get_dkl_buf_trans(struct intel_encoder *encoder,
-		       const struct intel_crtc_state *crtc_state,
-		       int *n_entries);
-const struct cnl_ddi_buf_trans *
-tgl_get_combo_buf_trans(struct intel_encoder *encoder,
-			const struct intel_crtc_state *crtc_state,
-			int *n_entries);
-const struct tgl_dkl_phy_ddi_buf_trans *
-tgl_get_dkl_buf_trans(struct intel_encoder *encoder,
-		      const struct intel_crtc_state *crtc_state,
-		      int *n_entries);
-const struct cnl_ddi_buf_trans *
-jsl_get_combo_buf_trans(struct intel_encoder *encoder,
-			const struct intel_crtc_state *crtc_state,
-			int *n_entries);
-const struct cnl_ddi_buf_trans *
-ehl_get_combo_buf_trans(struct intel_encoder *encoder,
-			const struct intel_crtc_state *crtc_state,
-			int *n_entries);
-const struct cnl_ddi_buf_trans *
-icl_get_combo_buf_trans(struct intel_encoder *encoder,
-			const struct intel_crtc_state *crtc_state,
-			int *n_entries);
-const struct icl_mg_phy_ddi_buf_trans *
-icl_get_mg_buf_trans(struct intel_encoder *encoder,
-		     const struct intel_crtc_state *crtc_state,
-		     int *n_entries);
-
-const struct cnl_ddi_buf_trans *
-cnl_get_buf_trans(struct intel_encoder *encoder,
-		  const struct intel_crtc_state *crtc_state,
-		  int *n_entries);
+void intel_ddi_buf_trans_init(struct intel_encoder *encoder);
 
 #endif
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 0a8a2395c8ac..134a6acbd8fb 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -59,6 +59,7 @@
 #include "display/intel_hdmi.h"
 #include "display/intel_lvds.h"
 #include "display/intel_sdvo.h"
+#include "display/intel_snps_phy.h"
 #include "display/intel_tv.h"
 #include "display/intel_vdsc.h"
 #include "display/intel_vrr.h"
@@ -975,7 +976,7 @@ void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 		/* FIXME: assert CPU port conditions for SNB+ */
 	}
 
-	/* Wa_22012358565:adlp */
+	/* Wa_22012358565:adl-p */
 	if (DISPLAY_VER(dev_priv) == 13)
 		intel_de_rmw(dev_priv, PIPE_ARB_CTL(pipe),
 			     0, PIPE_ARB_USE_PROG_SLOTS);
@@ -1035,6 +1036,10 @@ void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state)
 	if (!IS_I830(dev_priv))
 		val &= ~PIPECONF_ENABLE;
 
+	if (DISPLAY_VER(dev_priv) >= 12)
+		intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder),
+			     FECSTALL_DIS_DPTSTREAM_DPTTG, 0);
+
 	intel_de_write(dev_priv, reg, val);
 	if ((val & PIPECONF_ENABLE) == 0)
 		intel_wait_for_pipe_off(old_crtc_state);
@@ -1331,6 +1336,9 @@ retry:
 	ret = i915_gem_object_lock(obj, &ww);
 	if (!ret && phys_cursor)
 		ret = i915_gem_object_attach_phys(obj, alignment);
+	else if (!ret && HAS_LMEM(dev_priv))
+		ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM);
+	/* TODO: Do we need to sync when migration becomes async? */
 	if (!ret)
 		ret = i915_gem_object_pin_pages(obj);
 	if (ret)
@@ -1914,20 +1922,50 @@ static void intel_dpt_unpin(struct i915_address_space *vm)
 	i915_vma_put(dpt->vma);
 }
 
+static bool
+intel_reuse_initial_plane_obj(struct drm_i915_private *i915,
+			      const struct intel_initial_plane_config *plane_config,
+			      struct drm_framebuffer **fb,
+			      struct i915_vma **vma)
+{
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(&i915->drm, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+		struct intel_plane *plane =
+			to_intel_plane(crtc->base.primary);
+		struct intel_plane_state *plane_state =
+			to_intel_plane_state(plane->base.state);
+
+		if (!crtc_state->uapi.active)
+			continue;
+
+		if (!plane_state->ggtt_vma)
+			continue;
+
+		if (intel_plane_ggtt_offset(plane_state) == plane_config->base) {
+			*fb = plane_state->hw.fb;
+			*vma = plane_state->ggtt_vma;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static void
-intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
+intel_find_initial_plane_obj(struct intel_crtc *crtc,
 			     struct intel_initial_plane_config *plane_config)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_crtc *c;
-	struct drm_plane *primary = intel_crtc->base.primary;
-	struct drm_plane_state *plane_state = primary->state;
-	struct intel_plane *intel_plane = to_intel_plane(primary);
-	struct intel_plane_state *intel_state =
-		to_intel_plane_state(plane_state);
 	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(intel_crtc->base.state);
+		to_intel_crtc_state(crtc->base.state);
+	struct intel_plane *plane =
+		to_intel_plane(crtc->base.primary);
+	struct intel_plane_state *plane_state =
+		to_intel_plane_state(plane->base.state);
 	struct drm_framebuffer *fb;
 	struct i915_vma *vma;
 
@@ -1939,7 +1977,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	if (!plane_config->fb)
 		return;
 
-	if (intel_alloc_initial_plane_obj(intel_crtc, plane_config)) {
+	if (intel_alloc_initial_plane_obj(crtc, plane_config)) {
 		fb = &plane_config->fb->base;
 		vma = plane_config->vma;
 		goto valid_fb;
@@ -1949,25 +1987,8 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	 * Failed to alloc the obj, check to see if we should share
 	 * an fb with another CRTC instead
 	 */
-	for_each_crtc(dev, c) {
-		struct intel_plane_state *state;
-
-		if (c == &intel_crtc->base)
-			continue;
-
-		if (!to_intel_crtc_state(c->state)->uapi.active)
-			continue;
-
-		state = to_intel_plane_state(c->primary->state);
-		if (!state->ggtt_vma)
-			continue;
-
-		if (intel_plane_ggtt_offset(state) == plane_config->base) {
-			fb = state->hw.fb;
-			vma = state->ggtt_vma;
-			goto valid_fb;
-		}
-	}
+	if (intel_reuse_initial_plane_obj(dev_priv, plane_config, &fb, &vma))
+		goto valid_fb;
 
 	/*
 	 * We've failed to reconstruct the BIOS FB.  Current display state
@@ -1976,7 +1997,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	 * simplest solution is to just disable the primary plane now and
 	 * pretend the BIOS never had it enabled.
 	 */
-	intel_plane_disable_noatomic(intel_crtc, intel_plane);
+	intel_plane_disable_noatomic(crtc, plane);
 	if (crtc_state->bigjoiner) {
 		struct intel_crtc *slave =
 			crtc_state->bigjoiner_linked_crtc;
@@ -1986,40 +2007,38 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	return;
 
 valid_fb:
-	plane_state->rotation = plane_config->rotation;
-	intel_fb_fill_view(to_intel_framebuffer(fb), plane_state->rotation,
-			   &intel_state->view);
+	plane_state->uapi.rotation = plane_config->rotation;
+	intel_fb_fill_view(to_intel_framebuffer(fb),
+			   plane_state->uapi.rotation, &plane_state->view);
 
 	__i915_vma_pin(vma);
-	intel_state->ggtt_vma = i915_vma_get(vma);
-	if (intel_plane_uses_fence(intel_state) && i915_vma_pin_fence(vma) == 0)
-		if (vma->fence)
-			intel_state->flags |= PLANE_HAS_FENCE;
+	plane_state->ggtt_vma = i915_vma_get(vma);
+	if (intel_plane_uses_fence(plane_state) &&
+	    i915_vma_pin_fence(vma) == 0 && vma->fence)
+		plane_state->flags |= PLANE_HAS_FENCE;
 
-	plane_state->src_x = 0;
-	plane_state->src_y = 0;
-	plane_state->src_w = fb->width << 16;
-	plane_state->src_h = fb->height << 16;
+	plane_state->uapi.src_x = 0;
+	plane_state->uapi.src_y = 0;
+	plane_state->uapi.src_w = fb->width << 16;
+	plane_state->uapi.src_h = fb->height << 16;
 
-	plane_state->crtc_x = 0;
-	plane_state->crtc_y = 0;
-	plane_state->crtc_w = fb->width;
-	plane_state->crtc_h = fb->height;
+	plane_state->uapi.crtc_x = 0;
+	plane_state->uapi.crtc_y = 0;
+	plane_state->uapi.crtc_w = fb->width;
+	plane_state->uapi.crtc_h = fb->height;
 
 	if (plane_config->tiling)
 		dev_priv->preserve_bios_swizzle = true;
 
-	plane_state->fb = fb;
+	plane_state->uapi.fb = fb;
 	drm_framebuffer_get(fb);
 
-	plane_state->crtc = &intel_crtc->base;
-	intel_plane_copy_uapi_to_hw_state(intel_state, intel_state,
-					  intel_crtc);
+	plane_state->uapi.crtc = &crtc->base;
+	intel_plane_copy_uapi_to_hw_state(plane_state, plane_state, crtc);
 
 	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_DIRTYFB);
 
-	atomic_or(to_intel_plane(primary)->frontbuffer_bit,
-		  &to_intel_frontbuffer(fb)->bits);
+	atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits);
 }
 
 unsigned int
@@ -2193,8 +2212,29 @@ unlock:
 	clear_bit_unlock(I915_RESET_MODESET, &dev_priv->gt.reset.flags);
 }
 
-static void icl_set_pipe_chicken(struct intel_crtc *crtc)
+static bool underrun_recovery_supported(const struct intel_crtc_state *crtc_state)
 {
+	if (crtc_state->pch_pfit.enabled &&
+	    (crtc_state->pipe_src_w > drm_rect_width(&crtc_state->pch_pfit.dst) ||
+	     crtc_state->pipe_src_h > drm_rect_height(&crtc_state->pch_pfit.dst) ||
+	     crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420))
+		return false;
+
+	if (crtc_state->dsc.compression_enable)
+		return false;
+
+	if (crtc_state->has_psr2)
+		return false;
+
+	if (crtc_state->splitter.enable)
+		return false;
+
+	return true;
+}
+
+static void icl_set_pipe_chicken(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 tmp;
@@ -2215,19 +2255,19 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 	 */
 	tmp |= PIXEL_ROUNDING_TRUNC_FB_PASSTHRU;
 
-	/*
-	 * "The underrun recovery mechanism should be disabled
-	 *  when the following is enabled for this pipe:
-	 *  WiDi
-	 *  Downscaling (this includes YUV420 fullblend)
-	 *  COG
-	 *  DSC
-	 *  PSR2"
-	 *
-	 * FIXME: enable whenever possible...
-	 */
-	if (IS_ALDERLAKE_P(dev_priv))
-		tmp |= UNDERRUN_RECOVERY_DISABLE;
+	if (IS_DG2(dev_priv)) {
+		/*
+		 * Underrun recovery must always be disabled on DG2.  However
+		 * the chicken bit meaning is inverted compared to other
+		 * platforms.
+		 */
+		tmp &= ~UNDERRUN_RECOVERY_ENABLE_DG2;
+	} else if (DISPLAY_VER(dev_priv) >= 13) {
+		if (underrun_recovery_supported(crtc_state))
+			tmp &= ~UNDERRUN_RECOVERY_DISABLE_ADLP;
+		else
+			tmp |= UNDERRUN_RECOVERY_DISABLE_ADLP;
+	}
 
 	intel_de_write(dev_priv, PIPE_CHICKEN(pipe), tmp);
 }
@@ -2706,10 +2746,10 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
 	intel_wait_for_vblank(dev_priv, crtc->pipe);
 }
 
-static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc)
+static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc)
 {
-	if (intel_crtc->overlay)
-		(void) intel_overlay_switch_off(intel_crtc->overlay);
+	if (crtc->overlay)
+		(void) intel_overlay_switch_off(crtc->overlay);
 
 	/* Let userspace switch the overlay on again. In most cases userspace
 	 * has to recompute where to put it anyway.
@@ -3177,6 +3217,28 @@ static void intel_encoders_enable(struct intel_atomic_state *state,
 	}
 }
 
+static void intel_encoders_pre_disable(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
+{
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
+	struct drm_connector *conn;
+	int i;
+
+	for_each_old_connector_in_state(&state->base, conn, old_conn_state, i) {
+		struct intel_encoder *encoder =
+			to_intel_encoder(old_conn_state->best_encoder);
+
+		if (old_conn_state->crtc != &crtc->base)
+			continue;
+
+		if (encoder->pre_disable)
+			encoder->pre_disable(state, encoder, old_crtc_state,
+					     old_conn_state);
+	}
+}
+
 static void intel_encoders_disable(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc)
 {
@@ -3386,13 +3448,17 @@ static void glk_pipe_scaler_clock_gating_wa(struct drm_i915_private *dev_priv,
 	intel_de_write(dev_priv, CLKGATE_DIS_PSL(pipe), val);
 }
 
-static void icl_pipe_mbus_enable(struct intel_crtc *crtc)
+static void icl_pipe_mbus_enable(struct intel_crtc *crtc, bool joined_mbus)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
 
-	val = MBUS_DBOX_A_CREDIT(2);
+	/* Wa_22010947358:adl-p */
+	if (IS_ALDERLAKE_P(dev_priv))
+		val = joined_mbus ? MBUS_DBOX_A_CREDIT(6) : MBUS_DBOX_A_CREDIT(4);
+	else
+		val = MBUS_DBOX_A_CREDIT(2);
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
 		val |= MBUS_DBOX_BW_CREDIT(2);
@@ -3460,7 +3526,8 @@ static void icl_ddi_bigjoiner_pre_enable(struct intel_atomic_state *state,
 		 * Enable sequence steps 1-7 on bigjoiner master
 		 */
 		intel_encoders_pre_pll_enable(state, master);
-		intel_enable_shared_dpll(master_crtc_state);
+		if (master_crtc_state->shared_dpll)
+			intel_enable_shared_dpll(master_crtc_state);
 		intel_encoders_pre_enable(state, master);
 
 		/* and DSC on slave */
@@ -3518,7 +3585,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 
 	crtc->active = true;
 
-	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
+	/* Display WA #1180: WaDisableScalarClockGating: glk */
 	psl_clkgate_wa = DISPLAY_VER(dev_priv) == 10 &&
 		new_crtc_state->pch_pfit.enabled;
 	if (psl_clkgate_wa)
@@ -3542,13 +3609,17 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 	hsw_set_linetime_wm(new_crtc_state);
 
 	if (DISPLAY_VER(dev_priv) >= 11)
-		icl_set_pipe_chicken(crtc);
+		icl_set_pipe_chicken(new_crtc_state);
 
 	if (dev_priv->display.initial_watermarks)
 		dev_priv->display.initial_watermarks(state, crtc);
 
-	if (DISPLAY_VER(dev_priv) >= 11)
-		icl_pipe_mbus_enable(crtc);
+	if (DISPLAY_VER(dev_priv) >= 11) {
+		const struct intel_dbuf_state *dbuf_state =
+				intel_atomic_get_new_dbuf_state(state);
+
+		icl_pipe_mbus_enable(crtc, dbuf_state->joined_mbus);
+	}
 
 	if (new_crtc_state->bigjoiner_slave)
 		intel_crtc_vblank_on(new_crtc_state);
@@ -3682,6 +3753,13 @@ bool intel_phy_is_combo(struct drm_i915_private *dev_priv, enum phy phy)
 {
 	if (phy == PHY_NONE)
 		return false;
+	else if (IS_DG2(dev_priv))
+		/*
+		 * DG2 outputs labelled as "combo PHY" in the bspec use
+		 * SNPS PHYs with completely different programming,
+		 * hence we always return false here.
+		 */
+		return false;
 	else if (IS_ALDERLAKE_S(dev_priv))
 		return phy <= PHY_E;
 	else if (IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv))
@@ -3696,7 +3774,10 @@ bool intel_phy_is_combo(struct drm_i915_private *dev_priv, enum phy phy)
 
 bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy)
 {
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_DG2(dev_priv))
+		/* DG2's "TC1" output uses a SNPS PHY */
+		return false;
+	else if (IS_ALDERLAKE_P(dev_priv))
 		return phy >= PHY_F && phy <= PHY_I;
 	else if (IS_TIGERLAKE(dev_priv))
 		return phy >= PHY_D && phy <= PHY_I;
@@ -3706,6 +3787,20 @@ bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy)
 		return false;
 }
 
+bool intel_phy_is_snps(struct drm_i915_private *dev_priv, enum phy phy)
+{
+	if (phy == PHY_NONE)
+		return false;
+	else if (IS_DG2(dev_priv))
+		/*
+		 * All four "combo" ports and the TC1 port (PHY E) use
+		 * Synopsis PHYs.
+		 */
+		return phy <= PHY_E;
+
+	return false;
+}
+
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port)
 {
 	if (DISPLAY_VER(i915) >= 13 && port >= PORT_D_XELPD)
@@ -3850,7 +3945,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 	}
 
 	if (HAS_DDI(dev_priv) && crtc_state->has_audio)
-		mask |= BIT_ULL(POWER_DOMAIN_AUDIO);
+		mask |= BIT_ULL(POWER_DOMAIN_AUDIO_MMIO);
 
 	if (crtc_state->shared_dpll)
 		mask |= BIT_ULL(POWER_DOMAIN_DISPLAY_CORE);
@@ -6487,23 +6582,21 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 			       struct intel_load_detect_pipe *old,
 			       struct drm_modeset_acquire_ctx *ctx)
 {
-	struct intel_crtc *intel_crtc;
-	struct intel_encoder *intel_encoder =
+	struct intel_encoder *encoder =
 		intel_attached_encoder(to_intel_connector(connector));
-	struct drm_crtc *possible_crtc;
-	struct drm_encoder *encoder = &intel_encoder->base;
-	struct drm_crtc *crtc = NULL;
-	struct drm_device *dev = encoder->dev;
+	struct intel_crtc *possible_crtc;
+	struct intel_crtc *crtc = NULL;
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_atomic_state *state = NULL, *restore_state = NULL;
 	struct drm_connector_state *connector_state;
 	struct intel_crtc_state *crtc_state;
-	int ret, i = -1;
+	int ret;
 
 	drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 		    connector->base.id, connector->name,
-		    encoder->base.id, encoder->name);
+		    encoder->base.base.id, encoder->base.name);
 
 	old->restore_state = NULL;
 
@@ -6521,9 +6614,9 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 
 	/* See if we already have a CRTC for this connector */
 	if (connector->state->crtc) {
-		crtc = connector->state->crtc;
+		crtc = to_intel_crtc(connector->state->crtc);
 
-		ret = drm_modeset_lock(&crtc->mutex, ctx);
+		ret = drm_modeset_lock(&crtc->base.mutex, ctx);
 		if (ret)
 			goto fail;
 
@@ -6532,17 +6625,17 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 	}
 
 	/* Find an unused one (if possible) */
-	for_each_crtc(dev, possible_crtc) {
-		i++;
-		if (!(encoder->possible_crtcs & (1 << i)))
+	for_each_intel_crtc(dev, possible_crtc) {
+		if (!(encoder->base.possible_crtcs &
+		      drm_crtc_mask(&possible_crtc->base)))
 			continue;
 
-		ret = drm_modeset_lock(&possible_crtc->mutex, ctx);
+		ret = drm_modeset_lock(&possible_crtc->base.mutex, ctx);
 		if (ret)
 			goto fail;
 
-		if (possible_crtc->state->enable) {
-			drm_modeset_unlock(&possible_crtc->mutex);
+		if (possible_crtc->base.state->enable) {
+			drm_modeset_unlock(&possible_crtc->base.mutex);
 			continue;
 		}
 
@@ -6561,8 +6654,6 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 	}
 
 found:
-	intel_crtc = to_intel_crtc(crtc);
-
 	state = drm_atomic_state_alloc(dev);
 	restore_state = drm_atomic_state_alloc(dev);
 	if (!state || !restore_state) {
@@ -6579,11 +6670,11 @@ found:
 		goto fail;
 	}
 
-	ret = drm_atomic_set_crtc_for_connector(connector_state, crtc);
+	ret = drm_atomic_set_crtc_for_connector(connector_state, &crtc->base);
 	if (ret)
 		goto fail;
 
-	crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
+	crtc_state = intel_atomic_get_crtc_state(state, crtc);
 	if (IS_ERR(crtc_state)) {
 		ret = PTR_ERR(crtc_state);
 		goto fail;
@@ -6596,15 +6687,15 @@ found:
 	if (ret)
 		goto fail;
 
-	ret = intel_modeset_disable_planes(state, crtc);
+	ret = intel_modeset_disable_planes(state, &crtc->base);
 	if (ret)
 		goto fail;
 
 	ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(restore_state, connector));
 	if (!ret)
-		ret = PTR_ERR_OR_ZERO(drm_atomic_get_crtc_state(restore_state, crtc));
+		ret = PTR_ERR_OR_ZERO(drm_atomic_get_crtc_state(restore_state, &crtc->base));
 	if (!ret)
-		ret = drm_atomic_add_affected_planes(restore_state, crtc);
+		ret = drm_atomic_add_affected_planes(restore_state, &crtc->base);
 	if (ret) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "Failed to create a copy of old state to restore: %i\n",
@@ -6623,7 +6714,7 @@ found:
 	drm_atomic_state_put(state);
 
 	/* let the connector get through one full cycle before testing */
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
+	intel_wait_for_vblank(dev_priv, crtc->pipe);
 	return true;
 
 fail:
@@ -7295,12 +7386,13 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	}
 
 	if (dev_priv->display.compute_pipe_wm) {
-		ret = dev_priv->display.compute_pipe_wm(crtc_state);
+		ret = dev_priv->display.compute_pipe_wm(state, crtc);
 		if (ret) {
 			drm_dbg_kms(&dev_priv->drm,
 				    "Target pipe watermarks are invalid\n");
 			return ret;
 		}
+
 	}
 
 	if (dev_priv->display.compute_intermediate_wm) {
@@ -7313,7 +7405,7 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 		 * old state and the new state.  We can program these
 		 * immediately.
 		 */
-		ret = dev_priv->display.compute_intermediate_wm(crtc_state);
+		ret = dev_priv->display.compute_intermediate_wm(state, crtc);
 		if (ret) {
 			drm_dbg_kms(&dev_priv->drm,
 				    "No valid intermediate pipe watermarks are possible\n");
@@ -8636,10 +8728,11 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_BOOL(double_wide);
 
-	PIPE_CONF_CHECK_P(shared_dpll);
+	if (dev_priv->dpll.mgr)
+		PIPE_CONF_CHECK_P(shared_dpll);
 
 	/* FIXME do the readout properly and get rid of this quirk */
-	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) {
+	if (dev_priv->dpll.mgr && !PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) {
 		PIPE_CONF_CHECK_X(dpll_hw_state.dpll);
 		PIPE_CONF_CHECK_X(dpll_hw_state.dpll_md);
 		PIPE_CONF_CHECK_X(dpll_hw_state.fp0);
@@ -8671,7 +8764,9 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 		PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_ssc);
 		PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_bias);
 		PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_tdc_coldst_bias);
+	}
 
+	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) {
 		PIPE_CONF_CHECK_X(dsi_pll.ctrl);
 		PIPE_CONF_CHECK_X(dsi_pll.div);
 
@@ -9009,6 +9104,10 @@ verify_crtc_state(struct intel_crtc *crtc,
 	if (!new_crtc_state->hw.active)
 		return;
 
+	if (new_crtc_state->bigjoiner_slave)
+		/* No PLLs set for slave */
+		pipe_config->shared_dpll = NULL;
+
 	intel_pipe_config_sanity_check(dev_priv, pipe_config);
 
 	if (!intel_pipe_config_compare(new_crtc_state,
@@ -9112,6 +9211,55 @@ verify_shared_dpll_state(struct intel_crtc *crtc,
 }
 
 static void
+verify_mpllb_state(struct intel_atomic_state *state,
+		   struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	struct intel_mpllb_state mpllb_hw_state = { 0 };
+	struct intel_mpllb_state *mpllb_sw_state = &new_crtc_state->mpllb_state;
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
+	struct intel_encoder *encoder;
+
+	if (!IS_DG2(i915))
+		return;
+
+	if (!new_crtc_state->hw.active)
+		return;
+
+	if (new_crtc_state->bigjoiner_slave)
+		return;
+
+	encoder = intel_get_crtc_new_encoder(state, new_crtc_state);
+	intel_mpllb_readout_hw_state(encoder, &mpllb_hw_state);
+
+#define MPLLB_CHECK(name) do { \
+	if (mpllb_sw_state->name != mpllb_hw_state.name) { \
+		pipe_config_mismatch(false, crtc, "MPLLB:" __stringify(name), \
+				     "(expected 0x%08x, found 0x%08x)", \
+				     mpllb_sw_state->name, \
+				     mpllb_hw_state.name); \
+	} \
+} while (0)
+
+	MPLLB_CHECK(mpllb_cp);
+	MPLLB_CHECK(mpllb_div);
+	MPLLB_CHECK(mpllb_div2);
+	MPLLB_CHECK(mpllb_fracn1);
+	MPLLB_CHECK(mpllb_fracn2);
+	MPLLB_CHECK(mpllb_sscen);
+	MPLLB_CHECK(mpllb_sscstep);
+
+	/*
+	 * ref_control is handled by the hardware/firemware and never
+	 * programmed by the software, but the proper values are supplied
+	 * in the bspec for verification purposes.
+	 */
+	MPLLB_CHECK(ref_control);
+
+#undef MPLLB_CHECK
+}
+
+static void
 intel_modeset_verify_crtc(struct intel_crtc *crtc,
 			  struct intel_atomic_state *state,
 			  struct intel_crtc_state *old_crtc_state,
@@ -9124,6 +9272,7 @@ intel_modeset_verify_crtc(struct intel_crtc *crtc,
 	verify_connector_state(state, crtc);
 	verify_crtc_state(crtc, old_crtc_state, new_crtc_state);
 	verify_shared_dpll_state(crtc, old_crtc_state, new_crtc_state);
+	verify_mpllb_state(state, new_crtc_state);
 }
 
 static void
@@ -9749,7 +9898,7 @@ static int intel_atomic_check_async(struct intel_atomic_state *state)
 
 		/*
 		 * FIXME: This check is kept generic for all platforms.
-		 * Need to verify this for all gen9 and gen10 platforms to enable
+		 * Need to verify this for all gen9 platforms to enable
 		 * this selectively if required.
 		 */
 		switch (new_plane_state->hw.fb->modifier) {
@@ -10160,7 +10309,7 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 		hsw_set_linetime_wm(new_crtc_state);
 
 	if (DISPLAY_VER(dev_priv) >= 11)
-		icl_set_pipe_chicken(crtc);
+		icl_set_pipe_chicken(new_crtc_state);
 }
 
 static void commit_pipe_pre_planes(struct intel_atomic_state *state,
@@ -10294,6 +10443,8 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 
 	drm_WARN_ON(&dev_priv->drm, old_crtc_state->bigjoiner_slave);
 
+	intel_encoders_pre_disable(state, crtc);
+
 	intel_crtc_disable_planes(state, crtc);
 
 	/*
@@ -11328,7 +11479,12 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
-	if (IS_ALDERLAKE_P(dev_priv)) {
+	if (IS_DG2(dev_priv)) {
+		intel_ddi_init(dev_priv, PORT_A);
+		intel_ddi_init(dev_priv, PORT_B);
+		intel_ddi_init(dev_priv, PORT_C);
+		intel_ddi_init(dev_priv, PORT_D_XELPD);
+	} else if (IS_ALDERLAKE_P(dev_priv)) {
 		intel_ddi_init(dev_priv, PORT_A);
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_TC1);
@@ -11375,13 +11531,6 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 		vlv_dsi_init(dev_priv);
-	} else if (DISPLAY_VER(dev_priv) == 10) {
-		intel_ddi_init(dev_priv, PORT_A);
-		intel_ddi_init(dev_priv, PORT_B);
-		intel_ddi_init(dev_priv, PORT_C);
-		intel_ddi_init(dev_priv, PORT_D);
-		intel_ddi_init(dev_priv, PORT_E);
-		intel_ddi_init(dev_priv, PORT_F);
 	} else if (DISPLAY_VER(dev_priv) >= 9) {
 		intel_ddi_init(dev_priv, PORT_A);
 		intel_ddi_init(dev_priv, PORT_B);
@@ -11790,7 +11939,7 @@ intel_user_framebuffer_create(struct drm_device *dev,
 
 	/* object is backed with LMEM for discrete */
 	i915 = to_i915(obj->base.dev);
-	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) {
+	if (HAS_LMEM(i915) && !i915_gem_object_can_migrate(obj, INTEL_REGION_LMEM)) {
 		/* object is "remote", not in local memory */
 		i915_gem_object_put(obj);
 		return ERR_PTR(-EREMOTE);
@@ -13136,7 +13285,7 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 static void intel_early_display_was(struct drm_i915_private *dev_priv)
 {
 	/*
-	 * Display WA #1185 WaDisableDARBFClkGating:cnl,glk,icl,ehl,tgl
+	 * Display WA #1185 WaDisableDARBFClkGating:glk,icl,ehl,tgl
 	 * Also known as Wa_14010480278.
 	 */
 	if (IS_DISPLAY_VER(dev_priv, 10, 12))
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index c9dbaf074d77..284936f0ddab 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -561,6 +561,7 @@ struct drm_display_mode *
 intel_encoder_current_mode(struct intel_encoder *encoder);
 bool intel_phy_is_combo(struct drm_i915_private *dev_priv, enum phy phy);
 bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy);
+bool intel_phy_is_snps(struct drm_i915_private *dev_priv, enum phy phy);
 enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv,
 			      enum port port);
 int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 88bb05d5c483..8fdacb252bb1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -544,6 +544,11 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 
 	seq_printf(m, "fw loaded: %s\n", yesno(intel_dmc_has_payload(dev_priv)));
 	seq_printf(m, "path: %s\n", dmc->fw_path);
+	seq_printf(m, "Pipe A fw support: %s\n",
+		   yesno(GRAPHICS_VER(dev_priv) >= 12));
+	seq_printf(m, "Pipe A fw loaded: %s\n", yesno(dmc->dmc_info[DMC_FW_PIPEA].payload));
+	seq_printf(m, "Pipe B fw support: %s\n", yesno(IS_ALDERLAKE_P(dev_priv)));
+	seq_printf(m, "Pipe B fw loaded: %s\n", yesno(dmc->dmc_info[DMC_FW_PIPEB].payload));
 
 	if (!intel_dmc_has_payload(dev_priv))
 		goto out;
@@ -582,7 +587,7 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 
 out:
 	seq_printf(m, "program base: 0x%08x\n",
-		   intel_de_read(dev_priv, DMC_PROGRAM(0)));
+		   intel_de_read(dev_priv, DMC_PROGRAM(dmc->dmc_info[DMC_FW_MAIN].start_mmioaddr, 0)));
 	seq_printf(m, "ssp base: 0x%08x\n",
 		   intel_de_read(dev_priv, DMC_SSP_BASE));
 	seq_printf(m, "htp: 0x%08x\n", intel_de_read(dev_priv, DMC_HTP_SKL));
@@ -1225,7 +1230,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 
 static void drrs_status_per_crtc(struct seq_file *m,
 				 struct drm_device *dev,
-				 struct intel_crtc *intel_crtc)
+				 struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_drrs *drrs = &dev_priv->drrs;
@@ -1237,7 +1242,7 @@ static void drrs_status_per_crtc(struct seq_file *m,
 	drm_for_each_connector_iter(connector, &conn_iter) {
 		bool supported = false;
 
-		if (connector->state->crtc != &intel_crtc->base)
+		if (connector->state->crtc != &crtc->base)
 			continue;
 
 		seq_printf(m, "%s:\n", connector->name);
@@ -1252,7 +1257,7 @@ static void drrs_status_per_crtc(struct seq_file *m,
 
 	seq_puts(m, "\n");
 
-	if (to_intel_crtc_state(intel_crtc->base.state)->has_drrs) {
+	if (to_intel_crtc_state(crtc->base.state)->has_drrs) {
 		struct intel_panel *panel;
 
 		mutex_lock(&drrs->mutex);
@@ -1298,16 +1303,16 @@ static int i915_drrs_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_device *dev = &dev_priv->drm;
-	struct intel_crtc *intel_crtc;
+	struct intel_crtc *crtc;
 	int active_crtc_cnt = 0;
 
 	drm_modeset_lock_all(dev);
-	for_each_intel_crtc(dev, intel_crtc) {
-		if (intel_crtc->base.state->active) {
+	for_each_intel_crtc(dev, crtc) {
+		if (crtc->base.state->active) {
 			active_crtc_cnt++;
 			seq_printf(m, "\nCRTC %d:  ", active_crtc_cnt);
 
-			drrs_status_per_crtc(m, dev, intel_crtc);
+			drrs_status_per_crtc(m, dev, crtc);
 		}
 	}
 	drm_modeset_unlock_all(dev);
@@ -2064,7 +2069,7 @@ i915_fifo_underrun_reset_write(struct file *filp,
 			       size_t cnt, loff_t *ppos)
 {
 	struct drm_i915_private *dev_priv = filp->private_data;
-	struct intel_crtc *intel_crtc;
+	struct intel_crtc *crtc;
 	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 	bool reset;
@@ -2076,15 +2081,15 @@ i915_fifo_underrun_reset_write(struct file *filp,
 	if (!reset)
 		return cnt;
 
-	for_each_intel_crtc(dev, intel_crtc) {
+	for_each_intel_crtc(dev, crtc) {
 		struct drm_crtc_commit *commit;
 		struct intel_crtc_state *crtc_state;
 
-		ret = drm_modeset_lock_single_interruptible(&intel_crtc->base.mutex);
+		ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex);
 		if (ret)
 			return ret;
 
-		crtc_state = to_intel_crtc_state(intel_crtc->base.state);
+		crtc_state = to_intel_crtc_state(crtc->base.state);
 		commit = crtc_state->uapi.commit;
 		if (commit) {
 			ret = wait_for_completion_interruptible(&commit->hw_done);
@@ -2095,12 +2100,12 @@ i915_fifo_underrun_reset_write(struct file *filp,
 		if (!ret && crtc_state->hw.active) {
 			drm_dbg_kms(&dev_priv->drm,
 				    "Re-arming FIFO underruns on pipe %c\n",
-				    pipe_name(intel_crtc->pipe));
+				    pipe_name(crtc->pipe));
 
-			intel_crtc_arm_fifo_underrun(intel_crtc, crtc_state);
+			intel_crtc_arm_fifo_underrun(crtc, crtc_state);
 		}
 
-		drm_modeset_unlock(&intel_crtc->base.mutex);
+		drm_modeset_unlock(&crtc->base.mutex);
 
 		if (ret)
 			return ret;
@@ -2251,6 +2256,11 @@ static int i915_lpsp_capability_show(struct seq_file *m, void *data)
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
+	if (DISPLAY_VER(i915) >= 13) {
+		LPSP_CAPABLE(encoder->port <= PORT_B);
+		return 0;
+	}
+
 	switch (DISPLAY_VER(i915)) {
 	case 12:
 		/*
@@ -2385,6 +2395,73 @@ static const struct file_operations i915_dsc_fec_support_fops = {
 	.write = i915_dsc_fec_support_write
 };
 
+static int i915_dsc_bpp_show(struct seq_file *m, void *data)
+{
+	struct drm_connector *connector = m->private;
+	struct drm_device *dev = connector->dev;
+	struct drm_crtc *crtc;
+	struct intel_crtc_state *crtc_state;
+	struct intel_encoder *encoder = intel_attached_encoder(to_intel_connector(connector));
+	int ret;
+
+	if (!encoder)
+		return -ENODEV;
+
+	ret = drm_modeset_lock_single_interruptible(&dev->mode_config.connection_mutex);
+	if (ret)
+		return ret;
+
+	crtc = connector->state->crtc;
+	if (connector->status != connector_status_connected || !crtc) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	crtc_state = to_intel_crtc_state(crtc->state);
+	seq_printf(m, "Compressed_BPP: %d\n", crtc_state->dsc.compressed_bpp);
+
+out:	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+
+	return ret;
+}
+
+static ssize_t i915_dsc_bpp_write(struct file *file,
+				  const char __user *ubuf,
+				  size_t len, loff_t *offp)
+{
+	struct drm_connector *connector =
+		((struct seq_file *)file->private_data)->private;
+	struct intel_encoder *encoder = intel_attached_encoder(to_intel_connector(connector));
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	int dsc_bpp = 0;
+	int ret;
+
+	ret = kstrtoint_from_user(ubuf, len, 0, &dsc_bpp);
+	if (ret < 0)
+		return ret;
+
+	intel_dp->force_dsc_bpp = dsc_bpp;
+	*offp += len;
+
+	return len;
+}
+
+static int i915_dsc_bpp_open(struct inode *inode,
+			     struct file *file)
+{
+	return single_open(file, i915_dsc_bpp_show,
+			   inode->i_private);
+}
+
+static const struct file_operations i915_dsc_bpp_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_dsc_bpp_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.write = i915_dsc_bpp_write
+};
+
 /**
  * intel_connector_debugfs_add - add i915 specific connector debugfs files
  * @connector: pointer to a registered drm_connector
@@ -2423,10 +2500,17 @@ int intel_connector_debugfs_add(struct drm_connector *connector)
 				    connector, &i915_hdcp_sink_capability_fops);
 	}
 
-	if ((DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) && ((connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort && !to_intel_connector(connector)->mst_port) || connector->connector_type == DRM_MODE_CONNECTOR_eDP))
-		debugfs_create_file("i915_dsc_fec_support", S_IRUGO, root,
+	if (DISPLAY_VER(dev_priv) >= 11 &&
+	    ((connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
+	    !to_intel_connector(connector)->mst_port) ||
+	    connector->connector_type == DRM_MODE_CONNECTOR_eDP)) {
+		debugfs_create_file("i915_dsc_fec_support", 0644, root,
 				    connector, &i915_dsc_fec_support_fops);
 
+		debugfs_create_file("i915_dsc_bpp", 0644, root,
+				    connector, &i915_dsc_bpp_fops);
+	}
+
 	/* Legacy panels doesn't lpsp on any platform */
 	if ((DISPLAY_VER(dev_priv) >= 9 || IS_HASWELL(dev_priv) ||
 	     IS_BROADWELL(dev_priv)) &&
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 86b7ac7b65ec..cce1a926fcc1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -18,6 +18,7 @@
 #include "intel_pm.h"
 #include "intel_pps.h"
 #include "intel_sideband.h"
+#include "intel_snps_phy.h"
 #include "intel_tc.h"
 #include "intel_vga.h"
 
@@ -106,8 +107,10 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "PORT_OTHER";
 	case POWER_DOMAIN_VGA:
 		return "VGA";
-	case POWER_DOMAIN_AUDIO:
-		return "AUDIO";
+	case POWER_DOMAIN_AUDIO_MMIO:
+		return "AUDIO_MMIO";
+	case POWER_DOMAIN_AUDIO_PLAYBACK:
+		return "AUDIO_PLAYBACK";
 	case POWER_DOMAIN_AUX_A:
 		return "AUX_A";
 	case POWER_DOMAIN_AUX_B:
@@ -341,6 +344,17 @@ static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
 {
 	const struct i915_power_well_regs *regs = power_well->desc->hsw.regs;
 	int pw_idx = power_well->desc->hsw.idx;
+	int enable_delay = power_well->desc->hsw.fixed_enable_delay;
+
+	/*
+	 * For some power wells we're not supposed to watch the status bit for
+	 * an ack, but rather just wait a fixed amount of time and then
+	 * proceed.  This is only used on DG2.
+	 */
+	if (IS_DG2(dev_priv) && enable_delay) {
+		usleep_range(enable_delay, 2 * enable_delay);
+		return;
+	}
 
 	/* Timeout for PW1:10 us, AUX:not specified, other PWs:20 us. */
 	if (intel_de_wait_for_set(dev_priv, regs->driver,
@@ -436,17 +450,6 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 
 	hsw_wait_for_power_well_enable(dev_priv, power_well, false);
 
-	/* Display WA #1178: cnl */
-	if (IS_CANNONLAKE(dev_priv) &&
-	    pw_idx >= GLK_PW_CTL_IDX_AUX_B &&
-	    pw_idx <= CNL_PW_CTL_IDX_AUX_F) {
-		u32 val;
-
-		val = intel_de_read(dev_priv, CNL_AUX_ANAOVRD1(pw_idx));
-		val |= CNL_AUX_ANAOVRD1_ENABLE | CNL_AUX_ANAOVRD1_LDO_BYPASS;
-		intel_de_write(dev_priv, CNL_AUX_ANAOVRD1(pw_idx), val);
-	}
-
 	if (power_well->desc->hsw.has_fuses) {
 		enum skl_power_gate pg;
 
@@ -961,8 +964,9 @@ static void bxt_disable_dc9(struct drm_i915_private *dev_priv)
 static void assert_dmc_loaded(struct drm_i915_private *dev_priv)
 {
 	drm_WARN_ONCE(&dev_priv->drm,
-		      !intel_de_read(dev_priv, DMC_PROGRAM(0)),
-		      "DMC program storage start is NULL\n");
+		      !intel_de_read(dev_priv,
+				     DMC_PROGRAM(dev_priv->dmc.dmc_info[DMC_FW_MAIN].start_mmioaddr, 0)),
+				     "DMC program storage start is NULL\n");
 	drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, DMC_SSP_BASE),
 		      "DMC SSP Base Not fine\n");
 	drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, DMC_HTP_SKL),
@@ -2507,7 +2511,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DSI) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_CRT) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_C) |		\
 	BIT_ULL(POWER_DOMAIN_GMBUS) |		\
@@ -2557,7 +2562,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |	\
 	BIT_ULL(POWER_DOMAIN_PORT_DSI) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_C) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_D) |		\
@@ -2590,7 +2596,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_CRT) | /* DDI E */	\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
 #define BDW_DISPLAY_POWER_DOMAINS (			\
@@ -2606,7 +2613,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_CRT) | /* DDI E */	\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
 #define SKL_DISPLAY_POWERWELL_2_POWER_DOMAINS (		\
@@ -2624,7 +2632,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_AUX_B) |                       \
 	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define SKL_DISPLAY_DDI_IO_A_E_POWER_DOMAINS (		\
@@ -2659,7 +2668,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define BXT_DISPLAY_DC_OFF_POWER_DOMAINS (		\
@@ -2692,7 +2702,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |                       \
 	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_DDI_IO_A_POWER_DOMAINS (		\
@@ -2731,63 +2742,6 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_GMBUS) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
-#define CNL_DISPLAY_POWERWELL_2_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_TRANSCODER_A) |		\
-	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
-	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
-	BIT_ULL(POWER_DOMAIN_PIPE_C) |			\
-	BIT_ULL(POWER_DOMAIN_TRANSCODER_C) |		\
-	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |		\
-	BIT_ULL(POWER_DOMAIN_PIPE_C_PANEL_FITTER) |		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_LANES) |		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_B) |                       \
-	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
-	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
-	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
-	BIT_ULL(POWER_DOMAIN_VGA) |				\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DDI_A_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DDI_B_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DDI_C_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DDI_D_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_AUX_A_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
-	BIT_ULL(POWER_DOMAIN_AUX_IO_A) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_AUX_B_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_AUX_C_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_AUX_D_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_AUX_F_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DDI_F_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO) |		\
-	BIT_ULL(POWER_DOMAIN_INIT))
-#define CNL_DISPLAY_DC_OFF_POWER_DOMAINS (		\
-	CNL_DISPLAY_POWERWELL_2_POWER_DOMAINS |		\
-	BIT_ULL(POWER_DOMAIN_GT_IRQ) |			\
-	BIT_ULL(POWER_DOMAIN_MODESET) |			\
-	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
-	BIT_ULL(POWER_DOMAIN_INIT))
-
 /*
  * ICL PW_0/PG_0 domains (HW/DMC control):
  * - PCI
@@ -2829,7 +2783,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_AUX_E_TBT) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_F_TBT) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 	/*
 	 * - transcoder WD
@@ -2921,7 +2876,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_AUX_TBT5) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_TBT6) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
 #define TGL_PW_2_POWER_DOMAINS (			\
@@ -2991,7 +2947,8 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	RKL_PW_4_POWER_DOMAINS |			\
 	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
 	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
 	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC1) |	\
@@ -3029,6 +2986,35 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	BIT_ULL(POWER_DOMAIN_INIT))
 
 /*
+ * DG1 onwards Audio MMIO/VERBS lies in PG0 power well.
+ */
+#define DG1_PW_3_POWER_DOMAINS (			\
+	TGL_PW_4_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
+	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC1) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC2) |	\
+	BIT_ULL(POWER_DOMAIN_AUX_USBC1) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_USBC2) |		\
+	BIT_ULL(POWER_DOMAIN_VGA) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+#define DG1_PW_2_POWER_DOMAINS (			\
+	DG1_PW_3_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_VDSC_PW2) |	\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+#define DG1_DISPLAY_DC_OFF_POWER_DOMAINS (		\
+	DG1_PW_3_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
+	BIT_ULL(POWER_DOMAIN_MODESET) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+/*
  * XE_LPD Power Domains
  *
  * Previous platforms required that PG(n-1) be enabled before PG(n).  That
@@ -3073,7 +3059,7 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 	XELPD_PW_B_POWER_DOMAINS |			\
 	XELPD_PW_C_POWER_DOMAINS |			\
 	XELPD_PW_D_POWER_DOMAINS |			\
-	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_PLAYBACK) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |	\
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_D_XELPD) |	\
@@ -3114,6 +3100,7 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915,
 
 #define XELPD_DISPLAY_DC_OFF_POWER_DOMAINS (		\
 	XELPD_PW_2_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO_MMIO) |		\
 	BIT_ULL(POWER_DOMAIN_MODESET) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
@@ -3694,148 +3681,6 @@ static const struct i915_power_well_desc glk_power_wells[] = {
 	},
 };
 
-static const struct i915_power_well_desc cnl_power_wells[] = {
-	{
-		.name = "always-on",
-		.always_on = true,
-		.domains = POWER_DOMAIN_MASK,
-		.ops = &i9xx_always_on_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-	},
-	{
-		.name = "power well 1",
-		/* Handled by the DMC firmware */
-		.always_on = true,
-		.domains = 0,
-		.ops = &hsw_power_well_ops,
-		.id = SKL_DISP_PW_1,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = SKL_PW_CTL_IDX_PW_1,
-			.hsw.has_fuses = true,
-		},
-	},
-	{
-		.name = "AUX A",
-		.domains = CNL_DISPLAY_AUX_A_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = GLK_PW_CTL_IDX_AUX_A,
-		},
-	},
-	{
-		.name = "AUX B",
-		.domains = CNL_DISPLAY_AUX_B_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = GLK_PW_CTL_IDX_AUX_B,
-		},
-	},
-	{
-		.name = "AUX C",
-		.domains = CNL_DISPLAY_AUX_C_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = GLK_PW_CTL_IDX_AUX_C,
-		},
-	},
-	{
-		.name = "AUX D",
-		.domains = CNL_DISPLAY_AUX_D_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = CNL_PW_CTL_IDX_AUX_D,
-		},
-	},
-	{
-		.name = "DC off",
-		.domains = CNL_DISPLAY_DC_OFF_POWER_DOMAINS,
-		.ops = &gen9_dc_off_power_well_ops,
-		.id = SKL_DISP_DC_OFF,
-	},
-	{
-		.name = "power well 2",
-		.domains = CNL_DISPLAY_POWERWELL_2_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = SKL_DISP_PW_2,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = SKL_PW_CTL_IDX_PW_2,
-			.hsw.irq_pipe_mask = BIT(PIPE_B) | BIT(PIPE_C),
-			.hsw.has_vga = true,
-			.hsw.has_fuses = true,
-		},
-	},
-	{
-		.name = "DDI A IO power well",
-		.domains = CNL_DISPLAY_DDI_A_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = GLK_PW_CTL_IDX_DDI_A,
-		},
-	},
-	{
-		.name = "DDI B IO power well",
-		.domains = CNL_DISPLAY_DDI_B_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = SKL_PW_CTL_IDX_DDI_B,
-		},
-	},
-	{
-		.name = "DDI C IO power well",
-		.domains = CNL_DISPLAY_DDI_C_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = SKL_PW_CTL_IDX_DDI_C,
-		},
-	},
-	{
-		.name = "DDI D IO power well",
-		.domains = CNL_DISPLAY_DDI_D_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = SKL_PW_CTL_IDX_DDI_D,
-		},
-	},
-	{
-		.name = "DDI F IO power well",
-		.domains = CNL_DISPLAY_DDI_F_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = CNL_DISP_PW_DDI_F_IO,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = CNL_PW_CTL_IDX_DDI_F,
-		},
-	},
-	{
-		.name = "AUX F",
-		.domains = CNL_DISPLAY_AUX_F_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = CNL_DISP_PW_DDI_F_AUX,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = CNL_PW_CTL_IDX_AUX_F,
-		},
-	},
-};
-
 static const struct i915_power_well_ops icl_aux_power_well_ops = {
 	.sync_hw = hsw_power_well_sync_hw,
 	.enable = icl_aux_power_well_enable,
@@ -4642,6 +4487,165 @@ static const struct i915_power_well_desc rkl_power_wells[] = {
 	},
 };
 
+static const struct i915_power_well_desc dg1_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = true,
+		.domains = POWER_DOMAIN_MASK,
+		.ops = &i9xx_always_on_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+	},
+	{
+		.name = "power well 1",
+		/* Handled by the DMC firmware */
+		.always_on = true,
+		.domains = 0,
+		.ops = &hsw_power_well_ops,
+		.id = SKL_DISP_PW_1,
+		{
+			.hsw.regs = &hsw_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_PW_1,
+			.hsw.has_fuses = true,
+		},
+	},
+	{
+		.name = "DC off",
+		.domains = DG1_DISPLAY_DC_OFF_POWER_DOMAINS,
+		.ops = &gen9_dc_off_power_well_ops,
+		.id = SKL_DISP_DC_OFF,
+	},
+	{
+		.name = "power well 2",
+		.domains = DG1_PW_2_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = SKL_DISP_PW_2,
+		{
+			.hsw.regs = &hsw_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_PW_2,
+			.hsw.has_fuses = true,
+		},
+	},
+	{
+		.name = "power well 3",
+		.domains = DG1_PW_3_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_3,
+		{
+			.hsw.regs = &hsw_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_PW_3,
+			.hsw.irq_pipe_mask = BIT(PIPE_B),
+			.hsw.has_vga = true,
+			.hsw.has_fuses = true,
+		},
+	},
+	{
+		.name = "DDI A IO",
+		.domains = ICL_DDI_IO_A_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_ddi_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_DDI_A,
+		}
+	},
+	{
+		.name = "DDI B IO",
+		.domains = ICL_DDI_IO_B_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_ddi_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_DDI_B,
+		}
+	},
+	{
+		.name = "DDI IO TC1",
+		.domains = TGL_DDI_IO_TC1_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_ddi_power_well_regs,
+			.hsw.idx = TGL_PW_CTL_IDX_DDI_TC1,
+		},
+	},
+	{
+		.name = "DDI IO TC2",
+		.domains = TGL_DDI_IO_TC2_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_ddi_power_well_regs,
+			.hsw.idx = TGL_PW_CTL_IDX_DDI_TC2,
+		},
+	},
+	{
+		.name = "AUX A",
+		.domains = TGL_AUX_A_IO_POWER_DOMAINS,
+		.ops = &icl_aux_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_aux_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_AUX_A,
+		},
+	},
+	{
+		.name = "AUX B",
+		.domains = TGL_AUX_B_IO_POWER_DOMAINS,
+		.ops = &icl_aux_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_aux_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_AUX_B,
+		},
+	},
+	{
+		.name = "AUX USBC1",
+		.domains = TGL_AUX_IO_USBC1_POWER_DOMAINS,
+		.ops = &icl_aux_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_aux_power_well_regs,
+			.hsw.idx = TGL_PW_CTL_IDX_AUX_TC1,
+			.hsw.is_tc_tbt = false,
+		},
+	},
+	{
+		.name = "AUX USBC2",
+		.domains = TGL_AUX_IO_USBC2_POWER_DOMAINS,
+		.ops = &icl_aux_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &icl_aux_power_well_regs,
+			.hsw.idx = TGL_PW_CTL_IDX_AUX_TC2,
+			.hsw.is_tc_tbt = false,
+		},
+	},
+	{
+		.name = "power well 4",
+		.domains = TGL_PW_4_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &hsw_power_well_regs,
+			.hsw.idx = ICL_PW_CTL_IDX_PW_4,
+			.hsw.has_fuses = true,
+			.hsw.irq_pipe_mask = BIT(PIPE_C),
+		}
+	},
+	{
+		.name = "power well 5",
+		.domains = TGL_PW_5_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+		{
+			.hsw.regs = &hsw_power_well_regs,
+			.hsw.idx = TGL_PW_CTL_IDX_PW_5,
+			.hsw.has_fuses = true,
+			.hsw.irq_pipe_mask = BIT(PIPE_D),
+		},
+	},
+};
+
 static const struct i915_power_well_desc xelpd_power_wells[] = {
 	{
 		.name = "always-on",
@@ -4827,6 +4831,7 @@ static const struct i915_power_well_desc xelpd_power_wells[] = {
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
 			.hsw.idx = ICL_PW_CTL_IDX_AUX_A,
+			.hsw.fixed_enable_delay = 600,
 		},
 	},
 	{
@@ -4837,6 +4842,7 @@ static const struct i915_power_well_desc xelpd_power_wells[] = {
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
 			.hsw.idx = ICL_PW_CTL_IDX_AUX_B,
+			.hsw.fixed_enable_delay = 600,
 		},
 	},
 	{
@@ -4847,6 +4853,7 @@ static const struct i915_power_well_desc xelpd_power_wells[] = {
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
 			.hsw.idx = ICL_PW_CTL_IDX_AUX_C,
+			.hsw.fixed_enable_delay = 600,
 		},
 	},
 	{
@@ -4857,6 +4864,7 @@ static const struct i915_power_well_desc xelpd_power_wells[] = {
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
 			.hsw.idx = XELPD_PW_CTL_IDX_AUX_D,
+			.hsw.fixed_enable_delay = 600,
 		},
 	},
 	{
@@ -4877,6 +4885,7 @@ static const struct i915_power_well_desc xelpd_power_wells[] = {
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
 			.hsw.idx = TGL_PW_CTL_IDX_AUX_TC1,
+			.hsw.fixed_enable_delay = 600,
 		},
 	},
 	{
@@ -5121,7 +5130,9 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 		err = 0;
 	} else if (DISPLAY_VER(dev_priv) >= 13) {
 		err = set_power_wells(power_domains, xelpd_power_wells);
-	} else if (IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv)) {
+	} else if (IS_DG1(dev_priv)) {
+		err = set_power_wells(power_domains, dg1_power_wells);
+	} else if (IS_ALDERLAKE_S(dev_priv)) {
 		err = set_power_wells_mask(power_domains, tgl_power_wells,
 					   BIT_ULL(TGL_DISP_PW_TC_COLD_OFF));
 	} else if (IS_ROCKETLAKE(dev_priv)) {
@@ -5130,12 +5141,6 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 		err = set_power_wells(power_domains, tgl_power_wells);
 	} else if (DISPLAY_VER(dev_priv) == 11) {
 		err = set_power_wells(power_domains, icl_power_wells);
-	} else if (IS_CNL_WITH_PORT_F(dev_priv)) {
-		err = set_power_wells(power_domains, cnl_power_wells);
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		err = set_power_wells_mask(power_domains, cnl_power_wells,
-					   BIT_ULL(CNL_DISP_PW_DDI_F_IO) |
-					   BIT_ULL(CNL_DISP_PW_DDI_F_AUX));
 	} else if (IS_GEMINILAKE(dev_priv)) {
 		err = set_power_wells(power_domains, glk_power_wells);
 	} else if (IS_BROXTON(dev_priv)) {
@@ -5690,75 +5695,6 @@ static void bxt_display_core_uninit(struct drm_i915_private *dev_priv)
 	usleep_range(10, 30);		/* 10 us delay per Bspec */
 }
 
-static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume)
-{
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-	struct i915_power_well *well;
-
-	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
-
-	/* 1. Enable PCH Reset Handshake */
-	intel_pch_reset_handshake(dev_priv, !HAS_PCH_NOP(dev_priv));
-
-	if (!HAS_DISPLAY(dev_priv))
-		return;
-
-	/* 2-3. */
-	intel_combo_phy_init(dev_priv);
-
-	/*
-	 * 4. Enable Power Well 1 (PG1).
-	 *    The AUX IO power wells will be enabled on demand.
-	 */
-	mutex_lock(&power_domains->lock);
-	well = lookup_power_well(dev_priv, SKL_DISP_PW_1);
-	intel_power_well_enable(dev_priv, well);
-	mutex_unlock(&power_domains->lock);
-
-	/* 5. Enable CD clock */
-	intel_cdclk_init_hw(dev_priv);
-
-	/* 6. Enable DBUF */
-	gen9_dbuf_enable(dev_priv);
-
-	if (resume && intel_dmc_has_payload(dev_priv))
-		intel_dmc_load_program(dev_priv);
-}
-
-static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
-{
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-	struct i915_power_well *well;
-
-	if (!HAS_DISPLAY(dev_priv))
-		return;
-
-	gen9_disable_dc_states(dev_priv);
-
-	/* 1. Disable all display engine functions -> aready done */
-
-	/* 2. Disable DBUF */
-	gen9_dbuf_disable(dev_priv);
-
-	/* 3. Disable CD clock */
-	intel_cdclk_uninit_hw(dev_priv);
-
-	/*
-	 * 4. Disable Power Well 1 (PG1).
-	 *    The AUX IO power wells are toggled on demand, so they are already
-	 *    disabled at this point.
-	 */
-	mutex_lock(&power_domains->lock);
-	well = lookup_power_well(dev_priv, SKL_DISP_PW_1);
-	intel_power_well_disable(dev_priv, well);
-	mutex_unlock(&power_domains->lock);
-
-	usleep_range(10, 30);		/* 10 us delay per Bspec */
-
-	/* 5. */
-	intel_combo_phy_uninit(dev_priv);
-}
-
 struct buddy_page_mask {
 	u32 page_mask;
 	u8 type;
@@ -5797,9 +5733,14 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
 	unsigned long abox_mask = INTEL_INFO(dev_priv)->abox_mask;
 	int config, i;
 
+	/* BW_BUDDY registers are not used on dgpu's beyond DG1 */
+	if (IS_DGFX(dev_priv) && !IS_DG1(dev_priv))
+		return;
+
 	if (IS_ALDERLAKE_S(dev_priv) ||
-	    IS_DG1_REVID(dev_priv, DG1_REVID_A0, DG1_REVID_A0) ||
-	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
+	    IS_DG1_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) ||
+	    IS_RKL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) ||
+	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0))
 		/* Wa_1409767108:tgl,dg1,adl-s */
 		table = wa_1409767108_buddy_page_masks;
 	else
@@ -5821,10 +5762,11 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
 			intel_de_write(dev_priv, BW_BUDDY_PAGE_MASK(i),
 				       table[config].page_mask);
 
-			/* Wa_22010178259:tgl,rkl */
-			intel_de_rmw(dev_priv, BW_BUDDY_CTL(i),
-				     BW_BUDDY_TLB_REQ_TIMER_MASK,
-				     BW_BUDDY_TLB_REQ_TIMER(0x8));
+			/* Wa_22010178259:tgl,dg1,rkl,adl-s */
+			if (DISPLAY_VER(dev_priv) == 12)
+				intel_de_rmw(dev_priv, BW_BUDDY_CTL(i),
+					     BW_BUDDY_TLB_REQ_TIMER_MASK,
+					     BW_BUDDY_TLB_REQ_TIMER(0x8));
 		}
 	}
 }
@@ -5878,11 +5820,15 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 	if (DISPLAY_VER(dev_priv) >= 12)
 		tgl_bw_buddy_init(dev_priv);
 
+	/* 8. Ensure PHYs have completed calibration and adaptation */
+	if (IS_DG2(dev_priv))
+		intel_snps_phy_wait_for_calibration(dev_priv);
+
 	if (resume && intel_dmc_has_payload(dev_priv))
 		intel_dmc_load_program(dev_priv);
 
-	/* Wa_14011508470 */
-	if (DISPLAY_VER(dev_priv) == 12) {
+	/* Wa_14011508470:tgl,dg1,rkl,adl-s,adl-p */
+	if (DISPLAY_VER(dev_priv) >= 12) {
 		val = DCPR_CLEAR_MEMSTAT_DIS | DCPR_SEND_RESP_IMM |
 		      DCPR_MASK_LPMODE | DCPR_MASK_MAXLATENCY_MEMUP_CLR;
 		intel_uncore_rmw(&dev_priv->uncore, GEN11_CHICKEN_DCPR_2, 0, val);
@@ -6097,8 +6043,6 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume)
 
 	if (DISPLAY_VER(i915) >= 11) {
 		icl_display_core_init(i915, resume);
-	} else if (IS_CANNONLAKE(i915)) {
-		cnl_display_core_init(i915, resume);
 	} else if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) {
 		bxt_display_core_init(i915, resume);
 	} else if (DISPLAY_VER(i915) == 9) {
@@ -6258,8 +6202,6 @@ void intel_power_domains_suspend(struct drm_i915_private *i915,
 
 	if (DISPLAY_VER(i915) >= 11)
 		icl_display_core_uninit(i915);
-	else if (IS_CANNONLAKE(i915))
-		cnl_display_core_uninit(i915);
 	else if (IS_GEMINILAKE(i915) || IS_BROXTON(i915))
 		bxt_display_core_uninit(i915);
 	else if (DISPLAY_VER(i915) == 9)
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index 4f0917df4375..978531841fa3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -76,7 +76,8 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_PORT_CRT,
 	POWER_DOMAIN_PORT_OTHER,
 	POWER_DOMAIN_VGA,
-	POWER_DOMAIN_AUDIO,
+	POWER_DOMAIN_AUDIO_MMIO,
+	POWER_DOMAIN_AUDIO_PLAYBACK,
 	POWER_DOMAIN_AUX_A,
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
@@ -142,8 +143,6 @@ enum i915_power_well_id {
 	SKL_DISP_PW_MISC_IO,
 	SKL_DISP_PW_1,
 	SKL_DISP_PW_2,
-	CNL_DISP_PW_DDI_F_IO,
-	CNL_DISP_PW_DDI_F_AUX,
 	ICL_DISP_PW_3,
 	SKL_DISP_DC_OFF,
 	TGL_DISP_PW_TC_COLD_OFF,
@@ -223,6 +222,12 @@ struct i915_power_well_desc {
 			u8 idx;
 			/* Mask of pipes whose IRQ logic is backed by the pw */
 			u8 irq_pipe_mask;
+			/*
+			 * Instead of waiting for the status bit to ack enables,
+			 * just wait a specific amount of time and then consider
+			 * the well enabled.
+			 */
+			u16 fixed_enable_delay;
 			/* The pw is backing the VGA functionality */
 			bool has_vga:1;
 			bool has_fuses:1;
@@ -386,6 +391,10 @@ intel_display_power_put_all_in_set(struct drm_i915_private *i915,
 	intel_display_power_put_mask_in_set(i915, power_domain_set, power_domain_set->mask);
 }
 
+/*
+ * FIXME: We should probably switch this to a 0-based scheme to be consistent
+ * with how we now name/number DBUF_CTL instances.
+ */
 enum dbuf_slice {
 	DBUF_S1,
 	DBUF_S2,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 04613864cbe8..6beeeeba1bed 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -48,6 +48,7 @@
 
 struct drm_printer;
 struct __intel_global_objs_state;
+struct intel_ddi_buf_trans;
 
 /*
  * Display related stuff
@@ -195,6 +196,10 @@ struct intel_encoder {
 	void (*update_complete)(struct intel_atomic_state *,
 				struct intel_encoder *,
 				struct intel_crtc *);
+	void (*pre_disable)(struct intel_atomic_state *,
+			    struct intel_encoder *,
+			    const struct intel_crtc_state *,
+			    const struct drm_connector_state *);
 	void (*disable)(struct intel_atomic_state *,
 			struct intel_encoder *,
 			const struct intel_crtc_state *,
@@ -263,6 +268,9 @@ struct intel_encoder {
 	 * Returns whether the port clock is enabled or not.
 	 */
 	bool (*is_clock_enabled)(struct intel_encoder *encoder);
+	const struct intel_ddi_buf_trans *(*get_buf_trans)(struct intel_encoder *encoder,
+							   const struct intel_crtc_state *crtc_state,
+							   int *n_entries);
 	enum hpd_pin hpd_pin;
 	enum intel_display_power_domain power_domain;
 	/* for communication with audio component; protected by av_mutex */
@@ -310,7 +318,7 @@ struct intel_panel {
 		/* DPCD backlight */
 		union {
 			struct {
-				u8 pwmgen_bit_count;
+				struct drm_edp_backlight_info info;
 			} vesa;
 			struct {
 				bool sdr_uses_aux;
@@ -880,6 +888,18 @@ enum intel_output_format {
 	INTEL_OUTPUT_FORMAT_YCBCR444,
 };
 
+struct intel_mpllb_state {
+	u32 clock; /* in KHz */
+	u32 ref_control;
+	u32 mpllb_cp;
+	u32 mpllb_div;
+	u32 mpllb_div2;
+	u32 mpllb_fracn1;
+	u32 mpllb_fracn2;
+	u32 mpllb_sscen;
+	u32 mpllb_sscstep;
+};
+
 struct intel_crtc_state {
 	/*
 	 * uapi (drm) state. This is the software state shown to userspace.
@@ -1014,7 +1034,10 @@ struct intel_crtc_state {
 	struct intel_shared_dpll *shared_dpll;
 
 	/* Actual register state of the dpll, for shared dpll cross-checking. */
-	struct intel_dpll_hw_state dpll_hw_state;
+	union {
+		struct intel_dpll_hw_state dpll_hw_state;
+		struct intel_mpllb_state mpllb_state;
+	};
 
 	/*
 	 * ICL reserved DPLLs for the CRTC/port. The active PLL is selected by
@@ -1040,7 +1063,9 @@ struct intel_crtc_state {
 	bool has_psr;
 	bool has_psr2;
 	bool enable_psr2_sel_fetch;
+	bool req_psr2_sdp_prior_scanline;
 	u32 dc3co_exitline;
+	u16 su_y_granularity;
 
 	/*
 	 * Frequence the dpll for the port should run at. Differs from the
@@ -1493,12 +1518,14 @@ struct intel_psr {
 	bool colorimetry_support;
 	bool psr2_enabled;
 	bool psr2_sel_fetch_enabled;
+	bool req_psr2_sdp_prior_scanline;
 	u8 sink_sync_latency;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
 	bool sink_not_reliable;
 	bool irq_aux_error;
-	u16 su_x_granularity;
+	u16 su_w_granularity;
+	u16 su_y_granularity;
 	u32 dc3co_exitline;
 	u32 dc3co_exit_delay;
 	struct delayed_work dc3co_work;
@@ -1604,6 +1631,7 @@ struct intel_dp {
 
 	/* Display stream compression testing */
 	bool force_dsc_en;
+	int force_dsc_bpp;
 
 	bool hobl_failed;
 	bool hobl_active;
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 97308da28059..3c3c6cb5c0df 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -45,6 +45,10 @@
 
 #define GEN12_DMC_MAX_FW_SIZE		ICL_DMC_MAX_FW_SIZE
 
+#define ADLP_DMC_PATH			DMC_PATH(adlp, 2, 10)
+#define ADLP_DMC_VERSION_REQUIRED	DMC_VERSION(2, 10)
+MODULE_FIRMWARE(ADLP_DMC_PATH);
+
 #define ADLS_DMC_PATH			DMC_PATH(adls, 2, 01)
 #define ADLS_DMC_VERSION_REQUIRED	DMC_VERSION(2, 1)
 MODULE_FIRMWARE(ADLS_DMC_PATH);
@@ -53,12 +57,12 @@ MODULE_FIRMWARE(ADLS_DMC_PATH);
 #define DG1_DMC_VERSION_REQUIRED	DMC_VERSION(2, 2)
 MODULE_FIRMWARE(DG1_DMC_PATH);
 
-#define RKL_DMC_PATH			DMC_PATH(rkl, 2, 02)
-#define RKL_DMC_VERSION_REQUIRED	DMC_VERSION(2, 2)
+#define RKL_DMC_PATH			DMC_PATH(rkl, 2, 03)
+#define RKL_DMC_VERSION_REQUIRED	DMC_VERSION(2, 3)
 MODULE_FIRMWARE(RKL_DMC_PATH);
 
-#define TGL_DMC_PATH			DMC_PATH(tgl, 2, 08)
-#define TGL_DMC_VERSION_REQUIRED	DMC_VERSION(2, 8)
+#define TGL_DMC_PATH			DMC_PATH(tgl, 2, 12)
+#define TGL_DMC_VERSION_REQUIRED	DMC_VERSION(2, 12)
 MODULE_FIRMWARE(TGL_DMC_PATH);
 
 #define ICL_DMC_PATH			DMC_PATH(icl, 1, 09)
@@ -66,11 +70,6 @@ MODULE_FIRMWARE(TGL_DMC_PATH);
 #define ICL_DMC_MAX_FW_SIZE		0x6000
 MODULE_FIRMWARE(ICL_DMC_PATH);
 
-#define CNL_DMC_PATH			DMC_PATH(cnl, 1, 07)
-#define CNL_DMC_VERSION_REQUIRED	DMC_VERSION(1, 7)
-#define CNL_DMC_MAX_FW_SIZE		GLK_DMC_MAX_FW_SIZE
-MODULE_FIRMWARE(CNL_DMC_PATH);
-
 #define GLK_DMC_PATH			DMC_PATH(glk, 1, 04)
 #define GLK_DMC_VERSION_REQUIRED	DMC_VERSION(1, 4)
 #define GLK_DMC_MAX_FW_SIZE		0x4000
@@ -96,6 +95,7 @@ MODULE_FIRMWARE(BXT_DMC_PATH);
 #define PACKAGE_V2_MAX_FW_INFO_ENTRIES	32
 #define DMC_V1_MAX_MMIO_COUNT		8
 #define DMC_V3_MAX_MMIO_COUNT		20
+#define DMC_V1_MMIO_START_RANGE		0x80000
 
 struct intel_css_header {
 	/* 0x09 for DMC */
@@ -239,53 +239,18 @@ struct stepping_info {
 
 bool intel_dmc_has_payload(struct drm_i915_private *i915)
 {
-	return i915->dmc.dmc_payload;
+	return i915->dmc.dmc_info[DMC_FW_MAIN].payload;
 }
 
-static const struct stepping_info skl_stepping_info[] = {
-	{'A', '0'}, {'B', '0'}, {'C', '0'},
-	{'D', '0'}, {'E', '0'}, {'F', '0'},
-	{'G', '0'}, {'H', '0'}, {'I', '0'},
-	{'J', '0'}, {'K', '0'}
-};
-
-static const struct stepping_info bxt_stepping_info[] = {
-	{'A', '0'}, {'A', '1'}, {'A', '2'},
-	{'B', '0'}, {'B', '1'}, {'B', '2'}
-};
-
-static const struct stepping_info icl_stepping_info[] = {
-	{'A', '0'}, {'A', '1'}, {'A', '2'},
-	{'B', '0'}, {'B', '2'},
-	{'C', '0'}
-};
-
-static const struct stepping_info no_stepping_info = { '*', '*' };
-
 static const struct stepping_info *
-intel_get_stepping_info(struct drm_i915_private *dev_priv)
+intel_get_stepping_info(struct drm_i915_private *i915,
+			struct stepping_info *si)
 {
-	const struct stepping_info *si;
-	unsigned int size;
-
-	if (IS_ICELAKE(dev_priv)) {
-		size = ARRAY_SIZE(icl_stepping_info);
-		si = icl_stepping_info;
-	} else if (IS_SKYLAKE(dev_priv)) {
-		size = ARRAY_SIZE(skl_stepping_info);
-		si = skl_stepping_info;
-	} else if (IS_BROXTON(dev_priv)) {
-		size = ARRAY_SIZE(bxt_stepping_info);
-		si = bxt_stepping_info;
-	} else {
-		size = 0;
-		si = NULL;
-	}
-
-	if (INTEL_REVID(dev_priv) < size)
-		return si + INTEL_REVID(dev_priv);
+	const char *step_name = intel_step_name(RUNTIME_INFO(i915)->step.display_step);
 
-	return &no_stepping_info;
+	si->stepping = step_name[0];
+	si->substepping = step_name[1];
+	return si;
 }
 
 static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv)
@@ -316,8 +281,8 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv)
  */
 void intel_dmc_load_program(struct drm_i915_private *dev_priv)
 {
-	u32 *payload = dev_priv->dmc.dmc_payload;
-	u32 i, fw_size;
+	struct intel_dmc *dmc = &dev_priv->dmc;
+	u32 id, i;
 
 	if (!HAS_DMC(dev_priv)) {
 		drm_err(&dev_priv->drm,
@@ -325,26 +290,31 @@ void intel_dmc_load_program(struct drm_i915_private *dev_priv)
 		return;
 	}
 
-	if (!intel_dmc_has_payload(dev_priv)) {
+	if (!dev_priv->dmc.dmc_info[DMC_FW_MAIN].payload) {
 		drm_err(&dev_priv->drm,
 			"Tried to program CSR with empty payload\n");
 		return;
 	}
 
-	fw_size = dev_priv->dmc.dmc_fw_size;
 	assert_rpm_wakelock_held(&dev_priv->runtime_pm);
 
 	preempt_disable();
 
-	for (i = 0; i < fw_size; i++)
-		intel_uncore_write_fw(&dev_priv->uncore, DMC_PROGRAM(i),
-				      payload[i]);
+	for (id = 0; id < DMC_FW_MAX; id++) {
+		for (i = 0; i < dmc->dmc_info[id].dmc_fw_size; i++) {
+			intel_uncore_write_fw(&dev_priv->uncore,
+					      DMC_PROGRAM(dmc->dmc_info[id].start_mmioaddr, i),
+					      dmc->dmc_info[id].payload[i]);
+		}
+	}
 
 	preempt_enable();
 
-	for (i = 0; i < dev_priv->dmc.mmio_count; i++) {
-		intel_de_write(dev_priv, dev_priv->dmc.mmioaddr[i],
-			       dev_priv->dmc.mmiodata[i]);
+	for (id = 0; id < DMC_FW_MAX; id++) {
+		for (i = 0; i < dmc->dmc_info[id].mmio_count; i++) {
+			intel_de_write(dev_priv, dmc->dmc_info[id].mmioaddr[i],
+				       dmc->dmc_info[id].mmiodata[i]);
+		}
 	}
 
 	dev_priv->dmc.dc_state = 0;
@@ -352,62 +322,72 @@ void intel_dmc_load_program(struct drm_i915_private *dev_priv)
 	gen9_set_dc_state_debugmask(dev_priv);
 }
 
+static bool fw_info_matches_stepping(const struct intel_fw_info *fw_info,
+				     const struct stepping_info *si)
+{
+	if ((fw_info->substepping == '*' && si->stepping == fw_info->stepping) ||
+	    (si->stepping == fw_info->stepping && si->substepping == fw_info->substepping) ||
+	    /*
+	     * If we don't find a more specific one from above two checks, we
+	     * then check for the generic one to be sure to work even with
+	     * "broken firmware"
+	     */
+	    (si->stepping == '*' && si->substepping == fw_info->substepping) ||
+	    (fw_info->stepping == '*' && fw_info->substepping == '*'))
+		return true;
+
+	return false;
+}
+
 /*
  * Search fw_info table for dmc_offset to find firmware binary: num_entries is
  * already sanitized.
  */
-static u32 find_dmc_fw_offset(const struct intel_fw_info *fw_info,
+static void dmc_set_fw_offset(struct intel_dmc *dmc,
+			      const struct intel_fw_info *fw_info,
 			      unsigned int num_entries,
 			      const struct stepping_info *si,
 			      u8 package_ver)
 {
-	u32 dmc_offset = DMC_DEFAULT_FW_OFFSET;
-	unsigned int i;
+	unsigned int i, id;
+
+	struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc);
 
 	for (i = 0; i < num_entries; i++) {
-		if (package_ver > 1 && fw_info[i].dmc_id != 0)
-			continue;
+		id = package_ver <= 1 ? DMC_FW_MAIN : fw_info[i].dmc_id;
 
-		if (fw_info[i].substepping == '*' &&
-		    si->stepping == fw_info[i].stepping) {
-			dmc_offset = fw_info[i].offset;
-			break;
+		if (id >= DMC_FW_MAX) {
+			drm_dbg(&i915->drm, "Unsupported firmware id: %u\n", id);
+			continue;
 		}
 
-		if (si->stepping == fw_info[i].stepping &&
-		    si->substepping == fw_info[i].substepping) {
-			dmc_offset = fw_info[i].offset;
-			break;
-		}
+		/* More specific versions come first, so we don't even have to
+		 * check for the stepping since we already found a previous FW
+		 * for this id.
+		 */
+		if (dmc->dmc_info[id].present)
+			continue;
 
-		if (fw_info[i].stepping == '*' &&
-		    fw_info[i].substepping == '*') {
-			/*
-			 * In theory we should stop the search as generic
-			 * entries should always come after the more specific
-			 * ones, but let's continue to make sure to work even
-			 * with "broken" firmwares. If we don't find a more
-			 * specific one, then we use this entry
-			 */
-			dmc_offset = fw_info[i].offset;
+		if (fw_info_matches_stepping(&fw_info[i], si)) {
+			dmc->dmc_info[id].present = true;
+			dmc->dmc_info[id].dmc_offset = fw_info[i].offset;
 		}
 	}
-
-	return dmc_offset;
 }
 
 static u32 parse_dmc_fw_header(struct intel_dmc *dmc,
 			       const struct intel_dmc_header_base *dmc_header,
-			       size_t rem_size)
+			       size_t rem_size, u8 dmc_id)
 {
 	struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc);
+	struct dmc_fw_info *dmc_info = &dmc->dmc_info[dmc_id];
 	unsigned int header_len_bytes, dmc_header_size, payload_size, i;
 	const u32 *mmioaddr, *mmiodata;
-	u32 mmio_count, mmio_count_max;
+	u32 mmio_count, mmio_count_max, start_mmioaddr;
 	u8 *payload;
 
-	BUILD_BUG_ON(ARRAY_SIZE(dmc->mmioaddr) < DMC_V3_MAX_MMIO_COUNT ||
-		     ARRAY_SIZE(dmc->mmioaddr) < DMC_V1_MAX_MMIO_COUNT);
+	BUILD_BUG_ON(ARRAY_SIZE(dmc_info->mmioaddr) < DMC_V3_MAX_MMIO_COUNT ||
+		     ARRAY_SIZE(dmc_info->mmioaddr) < DMC_V1_MAX_MMIO_COUNT);
 
 	/*
 	 * Check if we can access common fields, we will checkc again below
@@ -430,6 +410,7 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc,
 		mmio_count_max = DMC_V3_MAX_MMIO_COUNT;
 		/* header_len is in dwords */
 		header_len_bytes = dmc_header->header_len * 4;
+		start_mmioaddr = v3->start_mmioaddr;
 		dmc_header_size = sizeof(*v3);
 	} else if (dmc_header->header_ver == 1) {
 		const struct intel_dmc_header_v1 *v1 =
@@ -443,6 +424,7 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc,
 		mmio_count = v1->mmio_count;
 		mmio_count_max = DMC_V1_MAX_MMIO_COUNT;
 		header_len_bytes = dmc_header->header_len;
+		start_mmioaddr = DMC_V1_MMIO_START_RANGE;
 		dmc_header_size = sizeof(*v1);
 	} else {
 		drm_err(&i915->drm, "Unknown DMC fw header version: %u\n",
@@ -463,16 +445,11 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc,
 	}
 
 	for (i = 0; i < mmio_count; i++) {
-		if (mmioaddr[i] < DMC_MMIO_START_RANGE ||
-		    mmioaddr[i] > DMC_MMIO_END_RANGE) {
-			drm_err(&i915->drm, "DMC firmware has wrong mmio address 0x%x\n",
-				mmioaddr[i]);
-			return 0;
-		}
-		dmc->mmioaddr[i] = _MMIO(mmioaddr[i]);
-		dmc->mmiodata[i] = mmiodata[i];
+		dmc_info->mmioaddr[i] = _MMIO(mmioaddr[i]);
+		dmc_info->mmiodata[i] = mmiodata[i];
 	}
-	dmc->mmio_count = mmio_count;
+	dmc_info->mmio_count = mmio_count;
+	dmc_info->start_mmioaddr = start_mmioaddr;
 
 	rem_size -= header_len_bytes;
 
@@ -485,14 +462,14 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc,
 		drm_err(&i915->drm, "DMC FW too big (%u bytes)\n", payload_size);
 		return 0;
 	}
-	dmc->dmc_fw_size = dmc_header->fw_size;
+	dmc_info->dmc_fw_size = dmc_header->fw_size;
 
-	dmc->dmc_payload = kmalloc(payload_size, GFP_KERNEL);
-	if (!dmc->dmc_payload)
+	dmc_info->payload = kmalloc(payload_size, GFP_KERNEL);
+	if (!dmc_info->payload)
 		return 0;
 
 	payload = (u8 *)(dmc_header) + header_len_bytes;
-	memcpy(dmc->dmc_payload, payload, payload_size);
+	memcpy(dmc_info->payload, payload, payload_size);
 
 	return header_len_bytes + payload_size;
 
@@ -509,7 +486,7 @@ parse_dmc_fw_package(struct intel_dmc *dmc,
 {
 	struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc);
 	u32 package_size = sizeof(struct intel_package_header);
-	u32 num_entries, max_entries, dmc_offset;
+	u32 num_entries, max_entries;
 	const struct intel_fw_info *fw_info;
 
 	if (rem_size < package_size)
@@ -545,16 +522,11 @@ parse_dmc_fw_package(struct intel_dmc *dmc,
 
 	fw_info = (const struct intel_fw_info *)
 		((u8 *)package_header + sizeof(*package_header));
-	dmc_offset = find_dmc_fw_offset(fw_info, num_entries, si,
-					package_header->header_ver);
-	if (dmc_offset == DMC_DEFAULT_FW_OFFSET) {
-		drm_err(&i915->drm, "DMC firmware not supported for %c stepping\n",
-			si->stepping);
-		return 0;
-	}
+	dmc_set_fw_offset(dmc, fw_info, num_entries, si,
+			  package_header->header_ver);
 
 	/* dmc_offset is in dwords */
-	return package_size + dmc_offset * 4;
+	return package_size;
 
 error_truncated:
 	drm_err(&i915->drm, "Truncated DMC firmware, refusing.\n");
@@ -604,9 +576,11 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv,
 	struct intel_package_header *package_header;
 	struct intel_dmc_header_base *dmc_header;
 	struct intel_dmc *dmc = &dev_priv->dmc;
-	const struct stepping_info *si = intel_get_stepping_info(dev_priv);
+	struct stepping_info display_info = { '*', '*'};
+	const struct stepping_info *si = intel_get_stepping_info(dev_priv, &display_info);
 	u32 readcount = 0;
-	u32 r;
+	u32 r, offset;
+	int id;
 
 	if (!fw)
 		return;
@@ -627,9 +601,19 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv,
 
 	readcount += r;
 
-	/* Extract dmc_header information */
-	dmc_header = (struct intel_dmc_header_base *)&fw->data[readcount];
-	parse_dmc_fw_header(dmc, dmc_header, fw->size - readcount);
+	for (id = 0; id < DMC_FW_MAX; id++) {
+		if (!dev_priv->dmc.dmc_info[id].present)
+			continue;
+
+		offset = readcount + dmc->dmc_info[id].dmc_offset * 4;
+		if (fw->size - offset < 0) {
+			drm_err(&dev_priv->drm, "Reading beyond the fw_size\n");
+			continue;
+		}
+
+		dmc_header = (struct intel_dmc_header_base *)&fw->data[offset];
+		parse_dmc_fw_header(dmc, dmc_header, fw->size - offset, id);
+	}
 }
 
 static void intel_dmc_runtime_pm_get(struct drm_i915_private *dev_priv)
@@ -705,7 +689,11 @@ void intel_dmc_ucode_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_dmc_runtime_pm_get(dev_priv);
 
-	if (IS_ALDERLAKE_S(dev_priv)) {
+	if (IS_ALDERLAKE_P(dev_priv)) {
+		dmc->fw_path = ADLP_DMC_PATH;
+		dmc->required_version = ADLP_DMC_VERSION_REQUIRED;
+		dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE;
+	} else if (IS_ALDERLAKE_S(dev_priv)) {
 		dmc->fw_path = ADLS_DMC_PATH;
 		dmc->required_version = ADLS_DMC_VERSION_REQUIRED;
 		dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE;
@@ -725,10 +713,6 @@ void intel_dmc_ucode_init(struct drm_i915_private *dev_priv)
 		dmc->fw_path = ICL_DMC_PATH;
 		dmc->required_version = ICL_DMC_VERSION_REQUIRED;
 		dmc->max_fw_size = ICL_DMC_MAX_FW_SIZE;
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		dmc->fw_path = CNL_DMC_PATH;
-		dmc->required_version = CNL_DMC_VERSION_REQUIRED;
-		dmc->max_fw_size = CNL_DMC_MAX_FW_SIZE;
 	} else if (IS_GEMINILAKE(dev_priv)) {
 		dmc->fw_path = GLK_DMC_PATH;
 		dmc->required_version = GLK_DMC_VERSION_REQUIRED;
@@ -827,5 +811,5 @@ void intel_dmc_ucode_fini(struct drm_i915_private *dev_priv)
 	intel_dmc_ucode_suspend(dev_priv);
 	drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref);
 
-	kfree(dev_priv->dmc.dmc_payload);
+	kfree(dev_priv->dmc.dmc_info[DMC_FW_MAIN].payload);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.h b/drivers/gpu/drm/i915/display/intel_dmc.h
index 4c22f567b61b..c3c00ff03869 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.h
+++ b/drivers/gpu/drm/i915/display/intel_dmc.h
@@ -16,17 +16,30 @@ struct drm_i915_private;
 #define DMC_VERSION_MAJOR(version)	((version) >> 16)
 #define DMC_VERSION_MINOR(version)	((version) & 0xffff)
 
+enum {
+	DMC_FW_MAIN = 0,
+	DMC_FW_PIPEA,
+	DMC_FW_PIPEB,
+	DMC_FW_MAX
+};
+
 struct intel_dmc {
 	struct work_struct work;
 	const char *fw_path;
 	u32 required_version;
 	u32 max_fw_size; /* bytes */
-	u32 *dmc_payload;
-	u32 dmc_fw_size; /* dwords */
 	u32 version;
-	u32 mmio_count;
-	i915_reg_t mmioaddr[20];
-	u32 mmiodata[20];
+	struct dmc_fw_info {
+		u32 mmio_count;
+		i915_reg_t mmioaddr[20];
+		u32 mmiodata[20];
+		u32 dmc_offset;
+		u32 start_mmioaddr;
+		u32 dmc_fw_size; /*dwords */
+		u32 *payload;
+		bool present;
+	} dmc_info[DMC_FW_MAX];
+
 	u32 dc_state;
 	u32 target_dc_state;
 	u32 allowed_dc_mask;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 862c1df69cc2..04175f359fd6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -222,29 +222,6 @@ bool intel_dp_can_bigjoiner(struct intel_dp *intel_dp)
 		 encoder->port != PORT_A);
 }
 
-static int cnl_max_source_rate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum port port = dig_port->base.port;
-
-	u32 voltage = intel_de_read(dev_priv, CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
-
-	/* Low voltage SKUs are limited to max of 5.4G */
-	if (voltage == VOLTAGE_INFO_0_85V)
-		return 540000;
-
-	/* For this SKU 8.1G is supported in all ports */
-	if (IS_CNL_WITH_PORT_F(dev_priv))
-		return 810000;
-
-	/* For other SKUs, max rate on ports A and D is 5.4G */
-	if (port == PORT_A || port == PORT_D)
-		return 540000;
-
-	return 810000;
-}
-
 static int icl_max_source_rate(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -270,7 +247,7 @@ static void
 intel_dp_set_source_rates(struct intel_dp *intel_dp)
 {
 	/* The values must be in increasing order */
-	static const int cnl_rates[] = {
+	static const int icl_rates[] = {
 		162000, 216000, 270000, 324000, 432000, 540000, 648000, 810000
 	};
 	static const int bxt_rates[] = {
@@ -295,12 +272,10 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 	drm_WARN_ON(&dev_priv->drm,
 		    intel_dp->source_rates || intel_dp->num_source_rates);
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) {
-		source_rates = cnl_rates;
-		size = ARRAY_SIZE(cnl_rates);
-		if (DISPLAY_VER(dev_priv) == 10)
-			max_rate = cnl_max_source_rate(intel_dp);
-		else if (IS_JSL_EHL(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11) {
+		source_rates = icl_rates;
+		size = ARRAY_SIZE(icl_rates);
+		if (IS_JSL_EHL(dev_priv))
 			max_rate = ehl_max_source_rate(intel_dp);
 		else
 			max_rate = icl_max_source_rate(intel_dp);
@@ -1274,6 +1249,23 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 							       pipe_config->pipe_bpp);
 		pipe_config->dsc.slice_count = dsc_dp_slice_count;
 	}
+
+	/* As of today we support DSC for only RGB */
+	if (intel_dp->force_dsc_bpp) {
+		if (intel_dp->force_dsc_bpp >= 8 &&
+		    intel_dp->force_dsc_bpp < pipe_bpp) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "DSC BPP forced to %d",
+				    intel_dp->force_dsc_bpp);
+			pipe_config->dsc.compressed_bpp =
+						intel_dp->force_dsc_bpp;
+		} else {
+			drm_dbg_kms(&dev_priv->drm,
+				    "Invalid DSC BPP %d",
+				    intel_dp->force_dsc_bpp);
+		}
+	}
+
 	/*
 	 * VDSC engine operates at 1 Pixel per clock, so if peak pixel rate
 	 * is greater than the maximum Cdclock and if slice count is even
@@ -3031,9 +3023,6 @@ void intel_read_dp_sdp(struct intel_encoder *encoder,
 		       struct intel_crtc_state *crtc_state,
 		       unsigned int type)
 {
-	if (encoder->type != INTEL_OUTPUT_DDI)
-		return;
-
 	switch (type) {
 	case DP_SDP_VSC:
 		intel_read_dp_vsc_sdp(encoder, crtc_state,
@@ -3342,6 +3331,9 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp,
 
 	intel_dp_autotest_phy_ddi_enable(intel_dp, crtc_state);
 
+	drm_dp_dpcd_write(&intel_dp->aux, DP_TRAINING_LANE0_SET,
+			  intel_dp->train_set, crtc_state->lane_count);
+
 	drm_dp_set_phy_test_pattern(&intel_dp->aux, data,
 				    link_status[DP_DPCD_REV]);
 }
@@ -4736,7 +4728,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 				    int refresh_rate)
 {
 	struct intel_dp *intel_dp = dev_priv->drrs.dp;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum drrs_refresh_rate_type index = DRRS_HIGH_RR;
 
 	if (refresh_rate <= 0) {
@@ -4750,7 +4742,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	if (!intel_crtc) {
+	if (!crtc) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "DRRS: intel_crtc not initialized\n");
 		return;
@@ -5233,7 +5225,8 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 
 	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
-	intel_connector->panel.backlight.power = intel_pps_backlight_power;
+	if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK))
+		intel_connector->panel.backlight.power = intel_pps_backlight_power;
 	intel_panel_setup_backlight(connector, pipe);
 
 	if (fixed_mode) {
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c
index 7c048d2ecf43..f483f479dd0b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c
@@ -158,7 +158,6 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	/*
 	 * Max timeout values:
 	 * SKL-GLK: 1.6ms
-	 * CNL: 3.2ms
 	 * ICL+: 4ms
 	 */
 	ret = DP_AUX_CH_CTL_SEND_BUSY |
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 8e9ac9ba1d38..6ac568617ef3 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -107,7 +107,7 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector)
 	u8 tcon_cap[4];
 
 	ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap));
-	if (ret < 0)
+	if (ret != sizeof(tcon_cap))
 		return false;
 
 	if (!(tcon_cap[1] & INTEL_EDP_HDR_TCON_BRIGHTNESS_NITS_CAP))
@@ -137,7 +137,7 @@ intel_dp_aux_hdr_get_backlight(struct intel_connector *connector, enum pipe pipe
 	u8 tmp;
 	u8 buf[2] = { 0 };
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &tmp) < 0) {
+	if (drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &tmp) != 1) {
 		drm_err(&i915->drm, "Failed to read current backlight mode from DPCD\n");
 		return 0;
 	}
@@ -153,7 +153,8 @@ intel_dp_aux_hdr_get_backlight(struct intel_connector *connector, enum pipe pipe
 		return panel->backlight.max;
 	}
 
-	if (drm_dp_dpcd_read(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, sizeof(buf)) < 0) {
+	if (drm_dp_dpcd_read(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf,
+			     sizeof(buf)) != sizeof(buf)) {
 		drm_err(&i915->drm, "Failed to read brightness from DPCD\n");
 		return 0;
 	}
@@ -172,7 +173,8 @@ intel_dp_aux_hdr_set_aux_backlight(const struct drm_connector_state *conn_state,
 	buf[0] = level & 0xFF;
 	buf[1] = (level & 0xFF00) >> 8;
 
-	if (drm_dp_dpcd_write(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, 4) < 0)
+	if (drm_dp_dpcd_write(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf,
+			      sizeof(buf)) != sizeof(buf))
 		drm_err(dev, "Failed to write brightness level to DPCD\n");
 }
 
@@ -203,7 +205,7 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state,
 	u8 old_ctrl, ctrl;
 
 	ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl);
-	if (ret < 0) {
+	if (ret != 1) {
 		drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret);
 		return;
 	}
@@ -221,7 +223,7 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state,
 	}
 
 	if (ctrl != old_ctrl)
-		if (drm_dp_dpcd_writeb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, ctrl) < 0)
+		if (drm_dp_dpcd_writeb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, ctrl) != 1)
 			drm_err(&i915->drm, "Failed to configure DPCD brightness controls\n");
 }
 
@@ -268,153 +270,19 @@ intel_dp_aux_hdr_setup_backlight(struct intel_connector *connector, enum pipe pi
 }
 
 /* VESA backlight callbacks */
-static void set_vesa_backlight_enable(struct intel_dp *intel_dp, bool enable)
-{
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 reg_val = 0;
-
-	/* Early return when display use other mechanism to enable backlight. */
-	if (!(intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP))
-		return;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
-			      &reg_val) < 0) {
-		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
-			    DP_EDP_DISPLAY_CONTROL_REGISTER);
-		return;
-	}
-	if (enable)
-		reg_val |= DP_EDP_BACKLIGHT_ENABLE;
-	else
-		reg_val &= ~(DP_EDP_BACKLIGHT_ENABLE);
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
-			       reg_val) != 1) {
-		drm_dbg_kms(&i915->drm, "Failed to %s aux backlight\n",
-			    enabledisable(enable));
-	}
-}
-
-static bool intel_dp_aux_vesa_backlight_dpcd_mode(struct intel_connector *connector)
-{
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 mode_reg;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux,
-			      DP_EDP_BACKLIGHT_MODE_SET_REGISTER,
-			      &mode_reg) != 1) {
-		drm_dbg_kms(&i915->drm,
-			    "Failed to read the DPCD register 0x%x\n",
-			    DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
-		return false;
-	}
-
-	return (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) ==
-	       DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD;
-}
-
-/*
- * Read the current backlight value from DPCD register(s) based
- * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
- */
 static u32 intel_dp_aux_vesa_get_backlight(struct intel_connector *connector, enum pipe unused)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 read_val[2] = { 0x0 };
-	u16 level = 0;
-
-	/*
-	 * If we're not in DPCD control mode yet, the programmed brightness
-	 * value is meaningless and we should assume max brightness
-	 */
-	if (!intel_dp_aux_vesa_backlight_dpcd_mode(connector))
-		return connector->panel.backlight.max;
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
-			     &read_val, sizeof(read_val)) < 0) {
-		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
-			    DP_EDP_BACKLIGHT_BRIGHTNESS_MSB);
-		return 0;
-	}
-	level = read_val[0];
-	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
-		level = (read_val[0] << 8 | read_val[1]);
-
-	return level;
+	return connector->panel.backlight.level;
 }
 
-/*
- * Sends the current backlight level over the aux channel, checking if its using
- * 8-bit or 16 bit value (MSB and LSB)
- */
 static void
-intel_dp_aux_vesa_set_backlight(const struct drm_connector_state *conn_state,
-				u32 level)
+intel_dp_aux_vesa_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 vals[2] = { 0x0 };
-
-	vals[0] = level;
-
-	/* Write the MSB and/or LSB */
-	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) {
-		vals[0] = (level & 0xFF00) >> 8;
-		vals[1] = (level & 0xFF);
-	}
-	if (drm_dp_dpcd_write(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
-			      vals, sizeof(vals)) < 0) {
-		drm_dbg_kms(&i915->drm,
-			    "Failed to write aux backlight level\n");
-		return;
-	}
-}
-
-/*
- * Set PWM Frequency divider to match desired frequency in vbt.
- * The PWM Frequency is calculated as 27Mhz / (F x P).
- * - Where F = PWM Frequency Pre-Divider value programmed by field 7:0 of the
- *             EDP_BACKLIGHT_FREQ_SET register (DPCD Address 00728h)
- * - Where P = 2^Pn, where Pn is the value programmed by field 4:0 of the
- *             EDP_PWMGEN_BIT_COUNT register (DPCD Address 00724h)
- */
-static bool intel_dp_aux_vesa_set_pwm_freq(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	const u8 pn = connector->panel.backlight.edp.vesa.pwmgen_bit_count;
-	int freq, fxp, f, fxp_actual, fxp_min, fxp_max;
-
-	freq = dev_priv->vbt.backlight.pwm_freq_hz;
-	if (!freq) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "Use panel default backlight frequency\n");
-		return false;
-	}
-
-	fxp = DIV_ROUND_CLOSEST(KHz(DP_EDP_BACKLIGHT_FREQ_BASE_KHZ), freq);
-	f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255);
-	fxp_actual = f << pn;
-
-	/* Ensure frequency is within 25% of desired value */
-	fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4);
-	fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4);
-
-	if (fxp_min > fxp_actual || fxp_actual > fxp_max) {
-		drm_dbg_kms(&dev_priv->drm, "Actual frequency out of range\n");
-		return false;
-	}
+	struct intel_panel *panel = &connector->panel;
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
-	if (drm_dp_dpcd_writeb(&intel_dp->aux,
-			       DP_EDP_BACKLIGHT_FREQ_SET, (u8) f) < 0) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "Failed to write aux backlight freq\n");
-		return false;
-	}
-	return true;
+	drm_edp_backlight_set_level(&intel_dp->aux, &panel->backlight.edp.vesa.info, level);
 }
 
 static void
@@ -422,159 +290,46 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state, u32 level)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_panel *panel = &connector->panel;
-	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
-	u8 pwmgen_bit_count = panel->backlight.edp.vesa.pwmgen_bit_count;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux,
-			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) {
-		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
-			    DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
-		return;
-	}
-
-	new_dpcd_buf = dpcd_buf;
-	edp_backlight_mode = dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK;
-
-	switch (edp_backlight_mode) {
-	case DP_EDP_BACKLIGHT_CONTROL_MODE_PWM:
-	case DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET:
-	case DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT:
-		new_dpcd_buf &= ~DP_EDP_BACKLIGHT_CONTROL_MODE_MASK;
-		new_dpcd_buf |= DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD;
-
-		if (drm_dp_dpcd_writeb(&intel_dp->aux,
-				       DP_EDP_PWMGEN_BIT_COUNT,
-				       pwmgen_bit_count) < 0)
-			drm_dbg_kms(&i915->drm,
-				    "Failed to write aux pwmgen bit count\n");
-
-		break;
-
-	/* Do nothing when it is already DPCD mode */
-	case DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD:
-	default:
-		break;
-	}
-
-	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP)
-		if (intel_dp_aux_vesa_set_pwm_freq(connector))
-			new_dpcd_buf |= DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE;
-
-	if (new_dpcd_buf != dpcd_buf) {
-		if (drm_dp_dpcd_writeb(&intel_dp->aux,
-			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf) < 0) {
-			drm_dbg_kms(&i915->drm,
-				    "Failed to write aux backlight mode\n");
-		}
-	}
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
-	intel_dp_aux_vesa_set_backlight(conn_state, level);
-	set_vesa_backlight_enable(intel_dp, true);
+	drm_edp_backlight_enable(&intel_dp->aux, &panel->backlight.edp.vesa.info, level);
 }
 
 static void intel_dp_aux_vesa_disable_backlight(const struct drm_connector_state *old_conn_state,
 						u32 level)
 {
-	set_vesa_backlight_enable(enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder)),
-				  false);
-}
-
-static u32 intel_dp_aux_vesa_calc_max_backlight(struct intel_connector *connector)
-{
-	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
 	struct intel_panel *panel = &connector->panel;
-	u32 max_backlight = 0;
-	int freq, fxp, fxp_min, fxp_max, fxp_actual, f = 1;
-	u8 pn, pn_min, pn_max;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT, &pn) == 1) {
-		pn &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
-		max_backlight = (1 << pn) - 1;
-	}
-
-	/* Find desired value of (F x P)
-	 * Note that, if F x P is out of supported range, the maximum value or
-	 * minimum value will applied automatically. So no need to check that.
-	 */
-	freq = i915->vbt.backlight.pwm_freq_hz;
-	drm_dbg_kms(&i915->drm, "VBT defined backlight frequency %u Hz\n",
-		    freq);
-	if (!freq) {
-		drm_dbg_kms(&i915->drm,
-			    "Use panel default backlight frequency\n");
-		return max_backlight;
-	}
-
-	fxp = DIV_ROUND_CLOSEST(KHz(DP_EDP_BACKLIGHT_FREQ_BASE_KHZ), freq);
-
-	/* Use highest possible value of Pn for more granularity of brightness
-	 * adjustment while satifying the conditions below.
-	 * - Pn is in the range of Pn_min and Pn_max
-	 * - F is in the range of 1 and 255
-	 * - FxP is within 25% of desired value.
-	 *   Note: 25% is arbitrary value and may need some tweak.
-	 */
-	if (drm_dp_dpcd_readb(&intel_dp->aux,
-			      DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min) != 1) {
-		drm_dbg_kms(&i915->drm,
-			    "Failed to read pwmgen bit count cap min\n");
-		return max_backlight;
-	}
-	if (drm_dp_dpcd_readb(&intel_dp->aux,
-			      DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max) != 1) {
-		drm_dbg_kms(&i915->drm,
-			    "Failed to read pwmgen bit count cap max\n");
-		return max_backlight;
-	}
-	pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
-	pn_max &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
-
-	fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4);
-	fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4);
-	if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) {
-		drm_dbg_kms(&i915->drm,
-			    "VBT defined backlight frequency out of range\n");
-		return max_backlight;
-	}
-
-	for (pn = pn_max; pn >= pn_min; pn--) {
-		f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255);
-		fxp_actual = f << pn;
-		if (fxp_min <= fxp_actual && fxp_actual <= fxp_max)
-			break;
-	}
-
-	drm_dbg_kms(&i915->drm, "Using eDP pwmgen bit count of %d\n", pn);
-	if (drm_dp_dpcd_writeb(&intel_dp->aux,
-			       DP_EDP_PWMGEN_BIT_COUNT, pn) < 0) {
-		drm_dbg_kms(&i915->drm,
-			    "Failed to write aux pwmgen bit count\n");
-		return max_backlight;
-	}
-	panel->backlight.edp.vesa.pwmgen_bit_count = pn;
-
-	max_backlight = (1 << pn) - 1;
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
-	return max_backlight;
+	drm_edp_backlight_disable(&intel_dp->aux, &panel->backlight.edp.vesa.info);
 }
 
-static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector,
-					     enum pipe pipe)
+static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, enum pipe pipe)
 {
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct intel_panel *panel = &connector->panel;
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	u16 current_level;
+	u8 current_mode;
+	int ret;
 
-	panel->backlight.max = intel_dp_aux_vesa_calc_max_backlight(connector);
-	if (!panel->backlight.max)
-		return -ENODEV;
+	ret = drm_edp_backlight_init(&intel_dp->aux, &panel->backlight.edp.vesa.info,
+				     i915->vbt.backlight.pwm_freq_hz, intel_dp->edp_dpcd,
+				     &current_level, &current_mode);
+	if (ret < 0)
+		return ret;
 
+	panel->backlight.max = panel->backlight.edp.vesa.info.max;
 	panel->backlight.min = 0;
-	panel->backlight.level = intel_dp_aux_vesa_get_backlight(connector, pipe);
-	panel->backlight.enabled = intel_dp_aux_vesa_backlight_dpcd_mode(connector) &&
-				   panel->backlight.level != 0;
+	if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) {
+		panel->backlight.level = current_level;
+		panel->backlight.enabled = panel->backlight.level != 0;
+	} else {
+		panel->backlight.level = panel->backlight.max;
+		panel->backlight.enabled = false;
+	}
 
 	return 0;
 }
@@ -585,16 +340,12 @@ intel_dp_aux_supports_vesa_backlight(struct intel_connector *connector)
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
-	/* Check the eDP Display control capabilities registers to determine if
-	 * the panel can support backlight control over the aux channel.
-	 *
-	 * TODO: We currently only support AUX only backlight configurations, not backlights which
+	/* TODO: We currently only support AUX only backlight configurations, not backlights which
 	 * require a mix of PWM and AUX controls to work. In the mean time, these machines typically
 	 * work just fine using normal PWM controls anyway.
 	 */
-	if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP &&
-	    (intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) &&
-	    (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP)) {
+	if ((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) &&
+	    drm_edp_backlight_supported(intel_dp->edp_dpcd)) {
 		drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n");
 		return true;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index b170e272bdee..8d13d7b26a25 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -308,9 +308,9 @@ intel_dp_mst_atomic_check(struct drm_connector *connector,
 	 * connector
 	 */
 	if (new_crtc) {
-		struct intel_crtc *intel_crtc = to_intel_crtc(new_crtc);
+		struct intel_crtc *crtc = to_intel_crtc(new_crtc);
 		struct intel_crtc_state *crtc_state =
-			intel_atomic_get_new_crtc_state(state, intel_crtc);
+			intel_atomic_get_new_crtc_state(state, crtc);
 
 		if (!crtc_state ||
 		    !drm_atomic_crtc_needs_modeset(&crtc_state->uapi) ||
@@ -348,6 +348,16 @@ static void wait_for_act_sent(struct intel_encoder *encoder,
 	drm_dp_check_act_status(&intel_dp->mst_mgr);
 }
 
+static void intel_mst_pre_disable_dp(struct intel_atomic_state *state,
+				     struct intel_encoder *encoder,
+				     const struct intel_crtc_state *old_crtc_state,
+				     const struct drm_connector_state *old_conn_state)
+{
+	if (old_crtc_state->has_audio)
+		intel_audio_codec_disable(encoder, old_crtc_state,
+					  old_conn_state);
+}
+
 static void intel_mst_disable_dp(struct intel_atomic_state *state,
 				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
@@ -372,9 +382,6 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state,
 	if (ret) {
 		drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret);
 	}
-	if (old_crtc_state->has_audio)
-		intel_audio_codec_disable(encoder,
-					  old_crtc_state, old_conn_state);
 }
 
 static void intel_mst_post_disable_dp(struct intel_atomic_state *state,
@@ -542,7 +549,7 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state,
 	struct intel_digital_port *dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 val;
+	enum transcoder trans = pipe_config->cpu_transcoder;
 
 	drm_WARN_ON(&dev_priv->drm, pipe_config->has_pch_encoder);
 
@@ -550,12 +557,8 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state,
 
 	intel_ddi_enable_transcoder_func(encoder, pipe_config);
 
-	val = intel_de_read(dev_priv,
-			    TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder));
-	val |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	intel_de_write(dev_priv,
-		       TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder),
-		       val);
+	intel_de_rmw(dev_priv, TRANS_DDI_FUNC_CTL(trans), 0,
+		     TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
 
 	drm_dbg_kms(&dev_priv->drm, "active links %d\n",
 		    intel_dp->active_mst_links);
@@ -564,6 +567,10 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state,
 
 	drm_dp_update_payload_part2(&intel_dp->mst_mgr);
 
+	if (DISPLAY_VER(dev_priv) >= 12 && pipe_config->fec_enable)
+		intel_de_rmw(dev_priv, CHICKEN_TRANS(trans), 0,
+			     FECSTALL_DIS_DPTSTREAM_DPTTG);
+
 	intel_enable_pipe(pipe_config);
 
 	intel_crtc_vblank_on(pipe_config);
@@ -835,13 +842,10 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 
-	if (DISPLAY_VER(dev_priv) <= 12) {
-		ret = intel_dp_hdcp_init(dig_port, intel_connector);
-		if (ret)
-			drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP MST init failed, skipping.\n",
-				    connector->name, connector->base.id);
-	}
-
+	ret = intel_dp_hdcp_init(dig_port, intel_connector);
+	if (ret)
+		drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP MST init failed, skipping.\n",
+			    connector->name, connector->base.id);
 	/*
 	 * Reuse the prop from the SST connector because we're
 	 * not allowed to create new props after device registration.
@@ -906,6 +910,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *dig_port, enum pipe
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
 	intel_encoder->compute_config_late = intel_dp_mst_compute_config_late;
+	intel_encoder->pre_disable = intel_mst_pre_disable_dp;
 	intel_encoder->disable = intel_mst_disable_dp;
 	intel_encoder->post_disable = intel_mst_post_disable_dp;
 	intel_encoder->update_pipe = intel_ddi_update_pipe;
diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c
index 89635da9f6f6..14515e62c05e 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll.c
@@ -11,6 +11,7 @@
 #include "intel_lvds.h"
 #include "intel_panel.h"
 #include "intel_sideband.h"
+#include "display/intel_snps_phy.h"
 
 struct intel_limit {
 	struct {
@@ -923,12 +924,13 @@ static int hsw_crtc_compute_clock(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
 		to_intel_atomic_state(crtc_state->uapi.state);
+	struct intel_encoder *encoder =
+		intel_get_crtc_new_encoder(state, crtc_state);
 
-	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) ||
-	    DISPLAY_VER(dev_priv) >= 11) {
-		struct intel_encoder *encoder =
-			intel_get_crtc_new_encoder(state, crtc_state);
-
+	if (IS_DG2(dev_priv)) {
+		return intel_mpllb_calc_state(crtc_state, encoder);
+	} else if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) ||
+		   DISPLAY_VER(dev_priv) >= 11) {
 		if (!intel_reserve_shared_dplls(state, crtc, encoder)) {
 			drm_dbg_kms(&dev_priv->drm,
 				    "failed to find PLL for pipe %c\n",
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 71ac57670043..5c91d125a337 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -168,7 +168,7 @@ intel_combo_pll_enable_reg(struct drm_i915_private *i915,
 	else if (IS_JSL_EHL(i915) && (pll->info->id == DPLL_ID_EHL_DPLL4))
 		return MG_PLL_ENABLE(0);
 
-	return CNL_DPLL_ENABLE(pll->info->id);
+	return ICL_DPLL_ENABLE(pll->info->id);
 }
 
 static i915_reg_t
@@ -2346,160 +2346,7 @@ static const struct intel_dpll_mgr bxt_pll_mgr = {
 	.dump_hw_state = bxt_dump_hw_state,
 };
 
-static void cnl_ddi_pll_enable(struct drm_i915_private *dev_priv,
-			       struct intel_shared_dpll *pll)
-{
-	const enum intel_dpll_id id = pll->info->id;
-	u32 val;
-
-	/* 1. Enable DPLL power in DPLL_ENABLE. */
-	val = intel_de_read(dev_priv, CNL_DPLL_ENABLE(id));
-	val |= PLL_POWER_ENABLE;
-	intel_de_write(dev_priv, CNL_DPLL_ENABLE(id), val);
-
-	/* 2. Wait for DPLL power state enabled in DPLL_ENABLE. */
-	if (intel_de_wait_for_set(dev_priv, CNL_DPLL_ENABLE(id),
-				  PLL_POWER_STATE, 5))
-		drm_err(&dev_priv->drm, "PLL %d Power not enabled\n", id);
-
-	/*
-	 * 3. Configure DPLL_CFGCR0 to set SSC enable/disable,
-	 * select DP mode, and set DP link rate.
-	 */
-	val = pll->state.hw_state.cfgcr0;
-	intel_de_write(dev_priv, CNL_DPLL_CFGCR0(id), val);
-
-	/* 4. Reab back to ensure writes completed */
-	intel_de_posting_read(dev_priv, CNL_DPLL_CFGCR0(id));
-
-	/* 3. Configure DPLL_CFGCR0 */
-	/* Avoid touch CFGCR1 if HDMI mode is not enabled */
-	if (pll->state.hw_state.cfgcr0 & DPLL_CFGCR0_HDMI_MODE) {
-		val = pll->state.hw_state.cfgcr1;
-		intel_de_write(dev_priv, CNL_DPLL_CFGCR1(id), val);
-		/* 4. Reab back to ensure writes completed */
-		intel_de_posting_read(dev_priv, CNL_DPLL_CFGCR1(id));
-	}
-
-	/*
-	 * 5. If the frequency will result in a change to the voltage
-	 * requirement, follow the Display Voltage Frequency Switching
-	 * Sequence Before Frequency Change
-	 *
-	 * Note: DVFS is actually handled via the cdclk code paths,
-	 * hence we do nothing here.
-	 */
-
-	/* 6. Enable DPLL in DPLL_ENABLE. */
-	val = intel_de_read(dev_priv, CNL_DPLL_ENABLE(id));
-	val |= PLL_ENABLE;
-	intel_de_write(dev_priv, CNL_DPLL_ENABLE(id), val);
-
-	/* 7. Wait for PLL lock status in DPLL_ENABLE. */
-	if (intel_de_wait_for_set(dev_priv, CNL_DPLL_ENABLE(id), PLL_LOCK, 5))
-		drm_err(&dev_priv->drm, "PLL %d not locked\n", id);
-
-	/*
-	 * 8. If the frequency will result in a change to the voltage
-	 * requirement, follow the Display Voltage Frequency Switching
-	 * Sequence After Frequency Change
-	 *
-	 * Note: DVFS is actually handled via the cdclk code paths,
-	 * hence we do nothing here.
-	 */
-
-	/*
-	 * 9. turn on the clock for the DDI and map the DPLL to the DDI
-	 * Done at intel_ddi_clk_select
-	 */
-}
-
-static void cnl_ddi_pll_disable(struct drm_i915_private *dev_priv,
-				struct intel_shared_dpll *pll)
-{
-	const enum intel_dpll_id id = pll->info->id;
-	u32 val;
-
-	/*
-	 * 1. Configure DPCLKA_CFGCR0 to turn off the clock for the DDI.
-	 * Done at intel_ddi_post_disable
-	 */
-
-	/*
-	 * 2. If the frequency will result in a change to the voltage
-	 * requirement, follow the Display Voltage Frequency Switching
-	 * Sequence Before Frequency Change
-	 *
-	 * Note: DVFS is actually handled via the cdclk code paths,
-	 * hence we do nothing here.
-	 */
-
-	/* 3. Disable DPLL through DPLL_ENABLE. */
-	val = intel_de_read(dev_priv, CNL_DPLL_ENABLE(id));
-	val &= ~PLL_ENABLE;
-	intel_de_write(dev_priv, CNL_DPLL_ENABLE(id), val);
-
-	/* 4. Wait for PLL not locked status in DPLL_ENABLE. */
-	if (intel_de_wait_for_clear(dev_priv, CNL_DPLL_ENABLE(id), PLL_LOCK, 5))
-		drm_err(&dev_priv->drm, "PLL %d locked\n", id);
-
-	/*
-	 * 5. If the frequency will result in a change to the voltage
-	 * requirement, follow the Display Voltage Frequency Switching
-	 * Sequence After Frequency Change
-	 *
-	 * Note: DVFS is actually handled via the cdclk code paths,
-	 * hence we do nothing here.
-	 */
-
-	/* 6. Disable DPLL power in DPLL_ENABLE. */
-	val = intel_de_read(dev_priv, CNL_DPLL_ENABLE(id));
-	val &= ~PLL_POWER_ENABLE;
-	intel_de_write(dev_priv, CNL_DPLL_ENABLE(id), val);
-
-	/* 7. Wait for DPLL power state disabled in DPLL_ENABLE. */
-	if (intel_de_wait_for_clear(dev_priv, CNL_DPLL_ENABLE(id),
-				    PLL_POWER_STATE, 5))
-		drm_err(&dev_priv->drm, "PLL %d Power not disabled\n", id);
-}
-
-static bool cnl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
-				     struct intel_shared_dpll *pll,
-				     struct intel_dpll_hw_state *hw_state)
-{
-	const enum intel_dpll_id id = pll->info->id;
-	intel_wakeref_t wakeref;
-	u32 val;
-	bool ret;
-
-	wakeref = intel_display_power_get_if_enabled(dev_priv,
-						     POWER_DOMAIN_DISPLAY_CORE);
-	if (!wakeref)
-		return false;
-
-	ret = false;
-
-	val = intel_de_read(dev_priv, CNL_DPLL_ENABLE(id));
-	if (!(val & PLL_ENABLE))
-		goto out;
-
-	val = intel_de_read(dev_priv, CNL_DPLL_CFGCR0(id));
-	hw_state->cfgcr0 = val;
-
-	/* avoid reading back stale values if HDMI mode is not enabled */
-	if (val & DPLL_CFGCR0_HDMI_MODE) {
-		hw_state->cfgcr1 = intel_de_read(dev_priv,
-						 CNL_DPLL_CFGCR1(id));
-	}
-	ret = true;
-
-out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_DISPLAY_CORE, wakeref);
-
-	return ret;
-}
-
-static void cnl_wrpll_get_multipliers(int bestdiv, int *pdiv,
+static void icl_wrpll_get_multipliers(int bestdiv, int *pdiv,
 				      int *qdiv, int *kdiv)
 {
 	/* even dividers */
@@ -2538,7 +2385,7 @@ static void cnl_wrpll_get_multipliers(int bestdiv, int *pdiv,
 	}
 }
 
-static void cnl_wrpll_params_populate(struct skl_wrpll_params *params,
+static void icl_wrpll_params_populate(struct skl_wrpll_params *params,
 				      u32 dco_freq, u32 ref_freq,
 				      int pdiv, int qdiv, int kdiv)
 {
@@ -2586,349 +2433,19 @@ static void cnl_wrpll_params_populate(struct skl_wrpll_params *params,
 	params->dco_fraction = dco & 0x7fff;
 }
 
-static bool
-__cnl_ddi_calculate_wrpll(struct intel_crtc_state *crtc_state,
-			  struct skl_wrpll_params *wrpll_params,
-			  int ref_clock)
-{
-	u32 afe_clock = crtc_state->port_clock * 5;
-	u32 dco_min = 7998000;
-	u32 dco_max = 10000000;
-	u32 dco_mid = (dco_min + dco_max) / 2;
-	static const int dividers[] = {  2,  4,  6,  8, 10, 12,  14,  16,
-					 18, 20, 24, 28, 30, 32,  36,  40,
-					 42, 44, 48, 50, 52, 54,  56,  60,
-					 64, 66, 68, 70, 72, 76,  78,  80,
-					 84, 88, 90, 92, 96, 98, 100, 102,
-					  3,  5,  7,  9, 15, 21 };
-	u32 dco, best_dco = 0, dco_centrality = 0;
-	u32 best_dco_centrality = U32_MAX; /* Spec meaning of 999999 MHz */
-	int d, best_div = 0, pdiv = 0, qdiv = 0, kdiv = 0;
-
-	for (d = 0; d < ARRAY_SIZE(dividers); d++) {
-		dco = afe_clock * dividers[d];
-
-		if ((dco <= dco_max) && (dco >= dco_min)) {
-			dco_centrality = abs(dco - dco_mid);
-
-			if (dco_centrality < best_dco_centrality) {
-				best_dco_centrality = dco_centrality;
-				best_div = dividers[d];
-				best_dco = dco;
-			}
-		}
-	}
-
-	if (best_div == 0)
-		return false;
-
-	cnl_wrpll_get_multipliers(best_div, &pdiv, &qdiv, &kdiv);
-	cnl_wrpll_params_populate(wrpll_params, best_dco, ref_clock,
-				  pdiv, qdiv, kdiv);
-
-	return true;
-}
-
-static bool
-cnl_ddi_calculate_wrpll(struct intel_crtc_state *crtc_state,
-			struct skl_wrpll_params *wrpll_params)
-{
-	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
-
-	return __cnl_ddi_calculate_wrpll(crtc_state, wrpll_params,
-					 i915->dpll.ref_clks.nssc);
-}
-
-static bool cnl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state)
-{
-	u32 cfgcr0, cfgcr1;
-	struct skl_wrpll_params wrpll_params = { 0, };
-
-	cfgcr0 = DPLL_CFGCR0_HDMI_MODE;
-
-	if (!cnl_ddi_calculate_wrpll(crtc_state, &wrpll_params))
-		return false;
-
-	cfgcr0 |= DPLL_CFGCR0_DCO_FRACTION(wrpll_params.dco_fraction) |
-		wrpll_params.dco_integer;
-
-	cfgcr1 = DPLL_CFGCR1_QDIV_RATIO(wrpll_params.qdiv_ratio) |
-		DPLL_CFGCR1_QDIV_MODE(wrpll_params.qdiv_mode) |
-		DPLL_CFGCR1_KDIV(wrpll_params.kdiv) |
-		DPLL_CFGCR1_PDIV(wrpll_params.pdiv) |
-		DPLL_CFGCR1_CENTRAL_FREQ;
-
-	memset(&crtc_state->dpll_hw_state, 0,
-	       sizeof(crtc_state->dpll_hw_state));
-
-	crtc_state->dpll_hw_state.cfgcr0 = cfgcr0;
-	crtc_state->dpll_hw_state.cfgcr1 = cfgcr1;
-	return true;
-}
-
 /*
- * Display WA #22010492432: ehl, tgl
+ * Display WA #22010492432: ehl, tgl, adl-p
  * Program half of the nominal DCO divider fraction value.
  */
 static bool
 ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915)
 {
 	return ((IS_PLATFORM(i915, INTEL_ELKHARTLAKE) &&
-		 IS_JSL_EHL_REVID(i915, EHL_REVID_B0, REVID_FOREVER)) ||
-		 IS_TIGERLAKE(i915)) &&
+		 IS_JSL_EHL_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) ||
+		 IS_TIGERLAKE(i915) || IS_ALDERLAKE_P(i915)) &&
 		 i915->dpll.ref_clks.nssc == 38400;
 }
 
-static int __cnl_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv,
-				    const struct intel_shared_dpll *pll,
-				    const struct intel_dpll_hw_state *pll_state,
-				    int ref_clock)
-{
-	u32 dco_fraction;
-	u32 p0, p1, p2, dco_freq;
-
-	p0 = pll_state->cfgcr1 & DPLL_CFGCR1_PDIV_MASK;
-	p2 = pll_state->cfgcr1 & DPLL_CFGCR1_KDIV_MASK;
-
-	if (pll_state->cfgcr1 & DPLL_CFGCR1_QDIV_MODE(1))
-		p1 = (pll_state->cfgcr1 & DPLL_CFGCR1_QDIV_RATIO_MASK) >>
-			DPLL_CFGCR1_QDIV_RATIO_SHIFT;
-	else
-		p1 = 1;
-
-
-	switch (p0) {
-	case DPLL_CFGCR1_PDIV_2:
-		p0 = 2;
-		break;
-	case DPLL_CFGCR1_PDIV_3:
-		p0 = 3;
-		break;
-	case DPLL_CFGCR1_PDIV_5:
-		p0 = 5;
-		break;
-	case DPLL_CFGCR1_PDIV_7:
-		p0 = 7;
-		break;
-	}
-
-	switch (p2) {
-	case DPLL_CFGCR1_KDIV_1:
-		p2 = 1;
-		break;
-	case DPLL_CFGCR1_KDIV_2:
-		p2 = 2;
-		break;
-	case DPLL_CFGCR1_KDIV_3:
-		p2 = 3;
-		break;
-	}
-
-	dco_freq = (pll_state->cfgcr0 & DPLL_CFGCR0_DCO_INTEGER_MASK) *
-		   ref_clock;
-
-	dco_fraction = (pll_state->cfgcr0 & DPLL_CFGCR0_DCO_FRACTION_MASK) >>
-		       DPLL_CFGCR0_DCO_FRACTION_SHIFT;
-
-	if (ehl_combo_pll_div_frac_wa_needed(dev_priv))
-		dco_fraction *= 2;
-
-	dco_freq += (dco_fraction * ref_clock) / 0x8000;
-
-	if (drm_WARN_ON(&dev_priv->drm, p0 == 0 || p1 == 0 || p2 == 0))
-		return 0;
-
-	return dco_freq / (p0 * p1 * p2 * 5);
-}
-
-static int cnl_ddi_wrpll_get_freq(struct drm_i915_private *i915,
-				  const struct intel_shared_dpll *pll,
-				  const struct intel_dpll_hw_state *pll_state)
-{
-	return __cnl_ddi_wrpll_get_freq(i915, pll, pll_state,
-					i915->dpll.ref_clks.nssc);
-}
-
-static bool
-cnl_ddi_dp_set_dpll_hw_state(struct intel_crtc_state *crtc_state)
-{
-	u32 cfgcr0;
-
-	cfgcr0 = DPLL_CFGCR0_SSC_ENABLE;
-
-	switch (crtc_state->port_clock / 2) {
-	case 81000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_810;
-		break;
-	case 135000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_1350;
-		break;
-	case 270000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_2700;
-		break;
-		/* eDP 1.4 rates */
-	case 162000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_1620;
-		break;
-	case 108000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_1080;
-		break;
-	case 216000:
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_2160;
-		break;
-	case 324000:
-		/* Some SKUs may require elevated I/O voltage to support this */
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_3240;
-		break;
-	case 405000:
-		/* Some SKUs may require elevated I/O voltage to support this */
-		cfgcr0 |= DPLL_CFGCR0_LINK_RATE_4050;
-		break;
-	}
-
-	memset(&crtc_state->dpll_hw_state, 0,
-	       sizeof(crtc_state->dpll_hw_state));
-
-	crtc_state->dpll_hw_state.cfgcr0 = cfgcr0;
-
-	return true;
-}
-
-static int cnl_ddi_lcpll_get_freq(struct drm_i915_private *i915,
-				  const struct intel_shared_dpll *pll,
-				  const struct intel_dpll_hw_state *pll_state)
-{
-	int link_clock = 0;
-
-	switch (pll_state->cfgcr0 & DPLL_CFGCR0_LINK_RATE_MASK) {
-	case DPLL_CFGCR0_LINK_RATE_810:
-		link_clock = 81000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_1080:
-		link_clock = 108000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_1350:
-		link_clock = 135000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_1620:
-		link_clock = 162000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_2160:
-		link_clock = 216000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_2700:
-		link_clock = 270000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_3240:
-		link_clock = 324000;
-		break;
-	case DPLL_CFGCR0_LINK_RATE_4050:
-		link_clock = 405000;
-		break;
-	default:
-		drm_WARN(&i915->drm, 1, "Unsupported link rate\n");
-		break;
-	}
-
-	return link_clock * 2;
-}
-
-static bool cnl_get_dpll(struct intel_atomic_state *state,
-			 struct intel_crtc *crtc,
-			 struct intel_encoder *encoder)
-{
-	struct intel_crtc_state *crtc_state =
-		intel_atomic_get_new_crtc_state(state, crtc);
-	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
-	struct intel_shared_dpll *pll;
-	bool bret;
-
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
-		bret = cnl_ddi_hdmi_pll_dividers(crtc_state);
-		if (!bret) {
-			drm_dbg_kms(&i915->drm,
-				    "Could not get HDMI pll dividers.\n");
-			return false;
-		}
-	} else if (intel_crtc_has_dp_encoder(crtc_state)) {
-		bret = cnl_ddi_dp_set_dpll_hw_state(crtc_state);
-		if (!bret) {
-			drm_dbg_kms(&i915->drm,
-				    "Could not set DP dpll HW state.\n");
-			return false;
-		}
-	} else {
-		drm_dbg_kms(&i915->drm,
-			    "Skip DPLL setup for output_types 0x%x\n",
-			    crtc_state->output_types);
-		return false;
-	}
-
-	pll = intel_find_shared_dpll(state, crtc,
-				     &crtc_state->dpll_hw_state,
-				     BIT(DPLL_ID_SKL_DPLL2) |
-				     BIT(DPLL_ID_SKL_DPLL1) |
-				     BIT(DPLL_ID_SKL_DPLL0));
-	if (!pll) {
-		drm_dbg_kms(&i915->drm, "No PLL selected\n");
-		return false;
-	}
-
-	intel_reference_shared_dpll(state, crtc,
-				    pll, &crtc_state->dpll_hw_state);
-
-	crtc_state->shared_dpll = pll;
-
-	return true;
-}
-
-static int cnl_ddi_pll_get_freq(struct drm_i915_private *i915,
-				const struct intel_shared_dpll *pll,
-				const struct intel_dpll_hw_state *pll_state)
-{
-	if (pll_state->cfgcr0 & DPLL_CFGCR0_HDMI_MODE)
-		return cnl_ddi_wrpll_get_freq(i915, pll, pll_state);
-	else
-		return cnl_ddi_lcpll_get_freq(i915, pll, pll_state);
-}
-
-static void cnl_update_dpll_ref_clks(struct drm_i915_private *i915)
-{
-	/* No SSC reference */
-	i915->dpll.ref_clks.nssc = i915->cdclk.hw.ref;
-}
-
-static void cnl_dump_hw_state(struct drm_i915_private *dev_priv,
-			      const struct intel_dpll_hw_state *hw_state)
-{
-	drm_dbg_kms(&dev_priv->drm, "dpll_hw_state: "
-		    "cfgcr0: 0x%x, cfgcr1: 0x%x\n",
-		    hw_state->cfgcr0,
-		    hw_state->cfgcr1);
-}
-
-static const struct intel_shared_dpll_funcs cnl_ddi_pll_funcs = {
-	.enable = cnl_ddi_pll_enable,
-	.disable = cnl_ddi_pll_disable,
-	.get_hw_state = cnl_ddi_pll_get_hw_state,
-	.get_freq = cnl_ddi_pll_get_freq,
-};
-
-static const struct dpll_info cnl_plls[] = {
-	{ "DPLL 0", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL0, 0 },
-	{ "DPLL 1", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL1, 0 },
-	{ "DPLL 2", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL2, 0 },
-	{ },
-};
-
-static const struct intel_dpll_mgr cnl_pll_mgr = {
-	.dpll_info = cnl_plls,
-	.get_dplls = cnl_get_dpll,
-	.put_dplls = intel_put_dpll,
-	.update_ref_clks = cnl_update_dpll_ref_clks,
-	.dump_hw_state = cnl_dump_hw_state,
-};
-
 struct icl_combo_pll_params {
 	int clock;
 	struct skl_wrpll_params wrpll;
@@ -3105,17 +2622,104 @@ icl_calc_wrpll(struct intel_crtc_state *crtc_state,
 	       struct skl_wrpll_params *wrpll_params)
 {
 	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
+	int ref_clock = icl_wrpll_ref_clock(i915);
+	u32 afe_clock = crtc_state->port_clock * 5;
+	u32 dco_min = 7998000;
+	u32 dco_max = 10000000;
+	u32 dco_mid = (dco_min + dco_max) / 2;
+	static const int dividers[] = {  2,  4,  6,  8, 10, 12,  14,  16,
+					 18, 20, 24, 28, 30, 32,  36,  40,
+					 42, 44, 48, 50, 52, 54,  56,  60,
+					 64, 66, 68, 70, 72, 76,  78,  80,
+					 84, 88, 90, 92, 96, 98, 100, 102,
+					  3,  5,  7,  9, 15, 21 };
+	u32 dco, best_dco = 0, dco_centrality = 0;
+	u32 best_dco_centrality = U32_MAX; /* Spec meaning of 999999 MHz */
+	int d, best_div = 0, pdiv = 0, qdiv = 0, kdiv = 0;
 
-	return __cnl_ddi_calculate_wrpll(crtc_state, wrpll_params,
-					 icl_wrpll_ref_clock(i915));
+	for (d = 0; d < ARRAY_SIZE(dividers); d++) {
+		dco = afe_clock * dividers[d];
+
+		if (dco <= dco_max && dco >= dco_min) {
+			dco_centrality = abs(dco - dco_mid);
+
+			if (dco_centrality < best_dco_centrality) {
+				best_dco_centrality = dco_centrality;
+				best_div = dividers[d];
+				best_dco = dco;
+			}
+		}
+	}
+
+	if (best_div == 0)
+		return false;
+
+	icl_wrpll_get_multipliers(best_div, &pdiv, &qdiv, &kdiv);
+	icl_wrpll_params_populate(wrpll_params, best_dco, ref_clock,
+				  pdiv, qdiv, kdiv);
+
+	return true;
 }
 
 static int icl_ddi_combo_pll_get_freq(struct drm_i915_private *i915,
 				      const struct intel_shared_dpll *pll,
 				      const struct intel_dpll_hw_state *pll_state)
 {
-	return __cnl_ddi_wrpll_get_freq(i915, pll, pll_state,
-					icl_wrpll_ref_clock(i915));
+	int ref_clock = icl_wrpll_ref_clock(i915);
+	u32 dco_fraction;
+	u32 p0, p1, p2, dco_freq;
+
+	p0 = pll_state->cfgcr1 & DPLL_CFGCR1_PDIV_MASK;
+	p2 = pll_state->cfgcr1 & DPLL_CFGCR1_KDIV_MASK;
+
+	if (pll_state->cfgcr1 & DPLL_CFGCR1_QDIV_MODE(1))
+		p1 = (pll_state->cfgcr1 & DPLL_CFGCR1_QDIV_RATIO_MASK) >>
+			DPLL_CFGCR1_QDIV_RATIO_SHIFT;
+	else
+		p1 = 1;
+
+	switch (p0) {
+	case DPLL_CFGCR1_PDIV_2:
+		p0 = 2;
+		break;
+	case DPLL_CFGCR1_PDIV_3:
+		p0 = 3;
+		break;
+	case DPLL_CFGCR1_PDIV_5:
+		p0 = 5;
+		break;
+	case DPLL_CFGCR1_PDIV_7:
+		p0 = 7;
+		break;
+	}
+
+	switch (p2) {
+	case DPLL_CFGCR1_KDIV_1:
+		p2 = 1;
+		break;
+	case DPLL_CFGCR1_KDIV_2:
+		p2 = 2;
+		break;
+	case DPLL_CFGCR1_KDIV_3:
+		p2 = 3;
+		break;
+	}
+
+	dco_freq = (pll_state->cfgcr0 & DPLL_CFGCR0_DCO_INTEGER_MASK) *
+		   ref_clock;
+
+	dco_fraction = (pll_state->cfgcr0 & DPLL_CFGCR0_DCO_FRACTION_MASK) >>
+		       DPLL_CFGCR0_DCO_FRACTION_SHIFT;
+
+	if (ehl_combo_pll_div_frac_wa_needed(i915))
+		dco_fraction *= 2;
+
+	dco_freq += (dco_fraction * ref_clock) / 0x8000;
+
+	if (drm_WARN_ON(&i915->drm, p0 == 0 || p1 == 0 || p2 == 0))
+		return 0;
+
+	return dco_freq / (p0 * p1 * p2 * 5);
 }
 
 static void icl_calc_dpll_state(struct drm_i915_private *i915,
@@ -4131,6 +3735,31 @@ static void icl_pll_enable(struct drm_i915_private *dev_priv,
 		drm_err(&dev_priv->drm, "PLL %d not locked\n", pll->info->id);
 }
 
+static void adlp_cmtg_clock_gating_wa(struct drm_i915_private *i915, struct intel_shared_dpll *pll)
+{
+	u32 val;
+
+	if (!IS_ADLP_DISPLAY_STEP(i915, STEP_A0, STEP_B0) ||
+	    pll->info->id != DPLL_ID_ICL_DPLL0)
+		return;
+	/*
+	 * Wa_16011069516:adl-p[a0]
+	 *
+	 * All CMTG regs are unreliable until CMTG clock gating is disabled,
+	 * so we can only assume the default TRANS_CMTG_CHICKEN reg value and
+	 * sanity check this assumption with a double read, which presumably
+	 * returns the correct value even with clock gating on.
+	 *
+	 * Instead of the usual place for workarounds we apply this one here,
+	 * since TRANS_CMTG_CHICKEN is only accessible while DPLL0 is enabled.
+	 */
+	val = intel_de_read(i915, TRANS_CMTG_CHICKEN);
+	val = intel_de_read(i915, TRANS_CMTG_CHICKEN);
+	intel_de_write(i915, TRANS_CMTG_CHICKEN, DISABLE_DPT_CLK_GATING);
+	if (drm_WARN_ON(&i915->drm, val & ~DISABLE_DPT_CLK_GATING))
+		drm_dbg_kms(&i915->drm, "Unexpected flags in TRANS_CMTG_CHICKEN: %08x\n", val);
+}
+
 static void combo_pll_enable(struct drm_i915_private *dev_priv,
 			     struct intel_shared_dpll *pll)
 {
@@ -4160,6 +3789,8 @@ static void combo_pll_enable(struct drm_i915_private *dev_priv,
 
 	icl_pll_enable(dev_priv, pll, enable_reg);
 
+	adlp_cmtg_clock_gating_wa(dev_priv, pll);
+
 	/* DVFS post sequence would be here. See the comment above. */
 }
 
@@ -4462,7 +4093,10 @@ void intel_shared_dpll_init(struct drm_device *dev)
 	const struct dpll_info *dpll_info;
 	int i;
 
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_DG2(dev_priv))
+		/* No shared DPLLs on DG2; port PLLs are part of the PHY */
+		dpll_mgr = NULL;
+	else if (IS_ALDERLAKE_P(dev_priv))
 		dpll_mgr = &adlp_pll_mgr;
 	else if (IS_ALDERLAKE_S(dev_priv))
 		dpll_mgr = &adls_pll_mgr;
@@ -4476,8 +4110,6 @@ void intel_shared_dpll_init(struct drm_device *dev)
 		dpll_mgr = &ehl_pll_mgr;
 	else if (DISPLAY_VER(dev_priv) >= 11)
 		dpll_mgr = &icl_pll_mgr;
-	else if (IS_CANNONLAKE(dev_priv))
-		dpll_mgr = &cnl_pll_mgr;
 	else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		dpll_mgr = &bxt_pll_mgr;
 	else if (DISPLAY_VER(dev_priv) == 9)
@@ -4668,7 +4300,12 @@ void intel_dpll_readout_hw_state(struct drm_i915_private *i915)
 static void sanitize_dpll_state(struct drm_i915_private *i915,
 				struct intel_shared_dpll *pll)
 {
-	if (!pll->on || pll->active_mask)
+	if (!pll->on)
+		return;
+
+	adlp_cmtg_clock_gating_wa(i915, pll);
+
+	if (pll->active_mask)
 		return;
 
 	drm_dbg_kms(&i915->drm,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index 7fd031a70cfd..30e0aa5ca109 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -204,9 +204,8 @@ struct intel_dpll_hw_state {
 	/* HDMI only, 0 when used for DP */
 	u32 cfgcr1, cfgcr2;
 
-	/* cnl */
+	/* icl */
 	u32 cfgcr0;
-	/* CNL also uses cfgcr1 */
 
 	/* bxt */
 	u32 ebb0, ebb4, pll0, pll1, pll2, pll3, pll6, pll8, pll9, pll10, pcsdw12;
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 1847a161cb37..ddfc17e21668 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -104,7 +104,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 	int i;
 	u32 fbc_ctl;
 
-	/* Note: fbc.threshold == 1 for i8xx */
+	/* Note: fbc.limit == 1 for i8xx */
 	cfb_pitch = params->cfb_size / FBC_LL_SIZE;
 	if (params->fb.stride < cfb_pitch)
 		cfb_pitch = params->fb.stride;
@@ -148,16 +148,35 @@ static bool i8xx_fbc_is_active(struct drm_i915_private *dev_priv)
 	return intel_de_read(dev_priv, FBC_CONTROL) & FBC_CTL_EN;
 }
 
+static u32 g4x_dpfc_ctl_limit(struct drm_i915_private *i915)
+{
+	const struct intel_fbc_reg_params *params = &i915->fbc.params;
+	int limit = i915->fbc.limit;
+
+	if (params->fb.format->cpp[0] == 2)
+		limit <<= 1;
+
+	switch (limit) {
+	default:
+		MISSING_CASE(limit);
+		fallthrough;
+	case 1:
+		return DPFC_CTL_LIMIT_1X;
+	case 2:
+		return DPFC_CTL_LIMIT_2X;
+	case 4:
+		return DPFC_CTL_LIMIT_4X;
+	}
+}
+
 static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
 
 	dpfc_ctl = DPFC_CTL_PLANE(params->crtc.i9xx_plane) | DPFC_SR_EN;
-	if (params->fb.format->cpp[0] == 2)
-		dpfc_ctl |= DPFC_CTL_LIMIT_2X;
-	else
-		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
+
+	dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv);
 
 	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id;
@@ -235,24 +254,10 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
-	int threshold = dev_priv->fbc.threshold;
 
 	dpfc_ctl = DPFC_CTL_PLANE(params->crtc.i9xx_plane);
-	if (params->fb.format->cpp[0] == 2)
-		threshold++;
 
-	switch (threshold) {
-	case 4:
-	case 3:
-		dpfc_ctl |= DPFC_CTL_LIMIT_4X;
-		break;
-	case 2:
-		dpfc_ctl |= DPFC_CTL_LIMIT_2X;
-		break;
-	case 1:
-		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
-		break;
-	}
+	dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv);
 
 	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN;
@@ -300,7 +305,6 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
-	int threshold = dev_priv->fbc.threshold;
 
 	/* Display WA #0529: skl, kbl, bxt. */
 	if (DISPLAY_VER(dev_priv) == 9) {
@@ -318,21 +322,7 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 	if (IS_IVYBRIDGE(dev_priv))
 		dpfc_ctl |= IVB_DPFC_CTL_PLANE(params->crtc.i9xx_plane);
 
-	if (params->fb.format->cpp[0] == 2)
-		threshold++;
-
-	switch (threshold) {
-	case 4:
-	case 3:
-		dpfc_ctl |= DPFC_CTL_LIMIT_4X;
-		break;
-	case 2:
-		dpfc_ctl |= DPFC_CTL_LIMIT_2X;
-		break;
-	case 1:
-		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
-		break;
-	}
+	dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv);
 
 	if (params->fence_id >= 0) {
 		dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
@@ -433,13 +423,8 @@ static u64 intel_fbc_cfb_base_max(struct drm_i915_private *i915)
 		return BIT_ULL(32);
 }
 
-static int find_compression_threshold(struct drm_i915_private *dev_priv,
-				      struct drm_mm_node *node,
-				      unsigned int size,
-				      unsigned int fb_cpp)
+static u64 intel_fbc_stolen_end(struct drm_i915_private *dev_priv)
 {
-	int compression_threshold = 1;
-	int ret;
 	u64 end;
 
 	/* The FBC hardware for BDW/SKL doesn't have access to the stolen
@@ -452,51 +437,69 @@ static int find_compression_threshold(struct drm_i915_private *dev_priv,
 	else
 		end = U64_MAX;
 
-	end = min(end, intel_fbc_cfb_base_max(dev_priv));
+	return min(end, intel_fbc_cfb_base_max(dev_priv));
+}
 
-	/* HACK: This code depends on what we will do in *_enable_fbc. If that
-	 * code changes, this code needs to change as well.
-	 *
-	 * The enable_fbc code will attempt to use one of our 2 compression
-	 * thresholds, therefore, in that case, we only have 1 resort.
+static int intel_fbc_max_limit(struct drm_i915_private *dev_priv, int fb_cpp)
+{
+	/*
+	 * FIXME: FBC1 can have arbitrary cfb stride,
+	 * so we could support different compression ratios.
 	 */
+	if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
+		return 1;
+
+	/* WaFbcOnly1to1Ratio:ctg */
+	if (IS_G4X(dev_priv))
+		return 1;
+
+	/* FBC2 can only do 1:1, 1:2, 1:4 */
+	return fb_cpp == 2 ? 2 : 4;
+}
+
+static int find_compression_limit(struct drm_i915_private *dev_priv,
+				  unsigned int size,
+				  unsigned int fb_cpp)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	u64 end = intel_fbc_stolen_end(dev_priv);
+	int ret, limit = 1;
 
 	/* Try to over-allocate to reduce reallocations and fragmentation. */
-	ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size <<= 1,
-						   4096, 0, end);
+	ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb,
+						   size <<= 1, 4096, 0, end);
 	if (ret == 0)
-		return compression_threshold;
+		return limit;
 
-again:
-	/* HW's ability to limit the CFB is 1:4 */
-	if (compression_threshold > 4 ||
-	    (fb_cpp == 2 && compression_threshold == 2))
-		return 0;
-
-	ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size >>= 1,
-						   4096, 0, end);
-	if (ret && DISPLAY_VER(dev_priv) <= 4) {
-		return 0;
-	} else if (ret) {
-		compression_threshold <<= 1;
-		goto again;
-	} else {
-		return compression_threshold;
+	for (; limit <= intel_fbc_max_limit(dev_priv, fb_cpp); limit <<= 1) {
+		ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb,
+							   size >>= 1, 4096, 0, end);
+		if (ret == 0)
+			return limit;
 	}
+
+	return 0;
 }
 
 static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 			       unsigned int size, unsigned int fb_cpp)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct drm_mm_node *compressed_llb;
 	int ret;
 
 	drm_WARN_ON(&dev_priv->drm,
 		    drm_mm_node_allocated(&fbc->compressed_fb));
+	drm_WARN_ON(&dev_priv->drm,
+		    drm_mm_node_allocated(&fbc->compressed_llb));
 
-	ret = find_compression_threshold(dev_priv, &fbc->compressed_fb,
-					 size, fb_cpp);
+	if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) {
+		ret = i915_gem_stolen_insert_node(dev_priv, &fbc->compressed_llb,
+						  4096, 4096);
+		if (ret)
+			goto err;
+	}
+
+	ret = find_compression_limit(dev_priv, size, fb_cpp);
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
@@ -504,51 +507,46 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 			      "Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
-	fbc->threshold = ret;
+	fbc->limit = ret;
 
-	if (DISPLAY_VER(dev_priv) >= 5)
+	drm_dbg_kms(&dev_priv->drm,
+		    "reserved %llu bytes of contiguous stolen space for FBC, limit: %d\n",
+		    fbc->compressed_fb.size, fbc->limit);
+
+	return 0;
+
+err_llb:
+	if (drm_mm_node_allocated(&fbc->compressed_llb))
+		i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_llb);
+err:
+	if (drm_mm_initialized(&dev_priv->mm.stolen))
+		drm_info_once(&dev_priv->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
+	return -ENOSPC;
+}
+
+static void intel_fbc_program_cfb(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	if (DISPLAY_VER(dev_priv) >= 5) {
 		intel_de_write(dev_priv, ILK_DPFC_CB_BASE,
 			       fbc->compressed_fb.start);
-	else if (IS_GM45(dev_priv)) {
+	} else if (IS_GM45(dev_priv)) {
 		intel_de_write(dev_priv, DPFC_CB_BASE,
 			       fbc->compressed_fb.start);
 	} else {
-		compressed_llb = kzalloc(sizeof(*compressed_llb), GFP_KERNEL);
-		if (!compressed_llb)
-			goto err_fb;
-
-		ret = i915_gem_stolen_insert_node(dev_priv, compressed_llb,
-						  4096, 4096);
-		if (ret)
-			goto err_fb;
-
-		fbc->compressed_llb = compressed_llb;
-
 		GEM_BUG_ON(range_overflows_end_t(u64, dev_priv->dsm.start,
 						 fbc->compressed_fb.start,
 						 U32_MAX));
 		GEM_BUG_ON(range_overflows_end_t(u64, dev_priv->dsm.start,
-						 fbc->compressed_llb->start,
+						 fbc->compressed_llb.start,
 						 U32_MAX));
+
 		intel_de_write(dev_priv, FBC_CFB_BASE,
 			       dev_priv->dsm.start + fbc->compressed_fb.start);
 		intel_de_write(dev_priv, FBC_LL_BASE,
-			       dev_priv->dsm.start + compressed_llb->start);
+			       dev_priv->dsm.start + fbc->compressed_llb.start);
 	}
-
-	drm_dbg_kms(&dev_priv->drm,
-		    "reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n",
-		    fbc->compressed_fb.size, fbc->threshold);
-
-	return 0;
-
-err_fb:
-	kfree(compressed_llb);
-	i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
-err_llb:
-	if (drm_mm_initialized(&dev_priv->mm.stolen))
-		drm_info_once(&dev_priv->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
-	return -ENOSPC;
 }
 
 static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
@@ -558,15 +556,10 @@ static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 	if (WARN_ON(intel_fbc_hw_is_active(dev_priv)))
 		return;
 
-	if (!drm_mm_node_allocated(&fbc->compressed_fb))
-		return;
-
-	if (fbc->compressed_llb) {
-		i915_gem_stolen_remove_node(dev_priv, fbc->compressed_llb);
-		kfree(fbc->compressed_llb);
-	}
-
-	i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
+	if (drm_mm_node_allocated(&fbc->compressed_llb))
+		i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_llb);
+	if (drm_mm_node_allocated(&fbc->compressed_fb))
+		i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
 }
 
 void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
@@ -753,7 +746,7 @@ static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	return intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
-		fbc->compressed_fb.size * fbc->threshold;
+		fbc->compressed_fb.size * fbc->limit;
 }
 
 static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
@@ -763,7 +756,7 @@ static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
 
 	if ((DISPLAY_VER(dev_priv) == 9) &&
 	    cache->fb.modifier != I915_FORMAT_MOD_X_TILED)
-		return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+		return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->limit) * 8;
 	else
 		return 0;
 }
@@ -919,11 +912,11 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	}
 
 	/*
-	 * Tigerlake is not supporting FBC with PSR2.
+	 * Display 12+ is not supporting FBC with PSR2.
 	 * Recommendation is to keep this combination disabled
 	 * Bspec: 50422 HSD: 14010260002
 	 */
-	if (fbc->state_cache.psr2_active && IS_TIGERLAKE(dev_priv)) {
+	if (fbc->state_cache.psr2_active && DISPLAY_VER(dev_priv) >= 12) {
 		fbc->no_fbc_reason = "not supported with PSR2";
 		return false;
 	}
@@ -1302,6 +1295,8 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 	fbc->no_fbc_reason = "FBC enabled but not active yet\n";
 
 	fbc->crtc = crtc;
+
+	intel_fbc_program_cfb(dev_priv);
 out:
 	mutex_unlock(&fbc->lock);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 4af40229f5ec..df05d285f0bd 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -335,32 +335,43 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
  * fbcon), so we just find the biggest and use that.
  */
 static bool intel_fbdev_init_bios(struct drm_device *dev,
-				 struct intel_fbdev *ifbdev)
+				  struct intel_fbdev *ifbdev)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct intel_framebuffer *fb = NULL;
-	struct drm_crtc *crtc;
-	struct intel_crtc *intel_crtc;
+	struct intel_crtc *crtc;
 	unsigned int max_size = 0;
 
 	/* Find the largest fb */
-	for_each_crtc(dev, crtc) {
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+		struct intel_plane *plane =
+			to_intel_plane(crtc->base.primary);
+		struct intel_plane_state *plane_state =
+			to_intel_plane_state(plane->base.state);
 		struct drm_i915_gem_object *obj =
-			intel_fb_obj(crtc->primary->state->fb);
-		intel_crtc = to_intel_crtc(crtc);
+			intel_fb_obj(plane_state->uapi.fb);
 
-		if (!crtc->state->active || !obj) {
+		if (!crtc_state->uapi.active) {
 			drm_dbg_kms(&i915->drm,
-				    "pipe %c not active or no fb, skipping\n",
-				    pipe_name(intel_crtc->pipe));
+				    "[CRTC:%d:%s] not active, skipping\n",
+				    crtc->base.base.id, crtc->base.name);
+			continue;
+		}
+
+		if (!obj) {
+			drm_dbg_kms(&i915->drm,
+				    "[PLANE:%d:%s] no fb, skipping\n",
+				    plane->base.base.id, plane->base.name);
 			continue;
 		}
 
 		if (obj->base.size > max_size) {
 			drm_dbg_kms(&i915->drm,
-				    "found possible fb from plane %c\n",
-				    pipe_name(intel_crtc->pipe));
-			fb = to_intel_framebuffer(crtc->primary->state->fb);
+				    "found possible fb from [PLANE:%d:%s]\n",
+				    plane->base.base.id, plane->base.name);
+			fb = to_intel_framebuffer(plane_state->uapi.fb);
 			max_size = obj->base.size;
 		}
 	}
@@ -372,60 +383,62 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 	}
 
 	/* Now make sure all the pipes will fit into it */
-	for_each_crtc(dev, crtc) {
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+		struct intel_plane *plane =
+			to_intel_plane(crtc->base.primary);
 		unsigned int cur_size;
 
-		intel_crtc = to_intel_crtc(crtc);
-
-		if (!crtc->state->active) {
+		if (!crtc_state->uapi.active) {
 			drm_dbg_kms(&i915->drm,
-				    "pipe %c not active, skipping\n",
-				    pipe_name(intel_crtc->pipe));
+				    "[CRTC:%d:%s] not active, skipping\n",
+				    crtc->base.base.id, crtc->base.name);
 			continue;
 		}
 
-		drm_dbg_kms(&i915->drm, "checking plane %c for BIOS fb\n",
-			    pipe_name(intel_crtc->pipe));
+		drm_dbg_kms(&i915->drm, "checking [PLANE:%d:%s] for BIOS fb\n",
+			    plane->base.base.id, plane->base.name);
 
 		/*
 		 * See if the plane fb we found above will fit on this
 		 * pipe.  Note we need to use the selected fb's pitch and bpp
 		 * rather than the current pipe's, since they differ.
 		 */
-		cur_size = crtc->state->adjusted_mode.crtc_hdisplay;
+		cur_size = crtc_state->uapi.adjusted_mode.crtc_hdisplay;
 		cur_size = cur_size * fb->base.format->cpp[0];
 		if (fb->base.pitches[0] < cur_size) {
 			drm_dbg_kms(&i915->drm,
-				    "fb not wide enough for plane %c (%d vs %d)\n",
-				    pipe_name(intel_crtc->pipe),
+				    "fb not wide enough for [PLANE:%d:%s] (%d vs %d)\n",
+				    plane->base.base.id, plane->base.name,
 				    cur_size, fb->base.pitches[0]);
 			fb = NULL;
 			break;
 		}
 
-		cur_size = crtc->state->adjusted_mode.crtc_vdisplay;
+		cur_size = crtc_state->uapi.adjusted_mode.crtc_vdisplay;
 		cur_size = intel_fb_align_height(&fb->base, 0, cur_size);
 		cur_size *= fb->base.pitches[0];
 		drm_dbg_kms(&i915->drm,
-			    "pipe %c area: %dx%d, bpp: %d, size: %d\n",
-			    pipe_name(intel_crtc->pipe),
-			    crtc->state->adjusted_mode.crtc_hdisplay,
-			    crtc->state->adjusted_mode.crtc_vdisplay,
+			    "[CRTC:%d:%s] area: %dx%d, bpp: %d, size: %d\n",
+			    crtc->base.base.id, crtc->base.name,
+			    crtc_state->uapi.adjusted_mode.crtc_hdisplay,
+			    crtc_state->uapi.adjusted_mode.crtc_vdisplay,
 			    fb->base.format->cpp[0] * 8,
 			    cur_size);
 
 		if (cur_size > max_size) {
 			drm_dbg_kms(&i915->drm,
-				    "fb not big enough for plane %c (%d vs %d)\n",
-				    pipe_name(intel_crtc->pipe),
+				    "fb not big enough for [PLANE:%d:%s] (%d vs %d)\n",
+				    plane->base.base.id, plane->base.name,
 				    cur_size, max_size);
 			fb = NULL;
 			break;
 		}
 
 		drm_dbg_kms(&i915->drm,
-			    "fb big enough for plane %c (%d >= %d)\n",
-			    pipe_name(intel_crtc->pipe),
+			    "fb big enough [PLANE:%d:%s] (%d >= %d)\n",
+			    plane->base.base.id, plane->base.name,
 			    max_size, cur_size);
 	}
 
@@ -441,15 +454,20 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 	drm_framebuffer_get(&ifbdev->fb->base);
 
 	/* Final pass to check if any active pipes don't have fbs */
-	for_each_crtc(dev, crtc) {
-		intel_crtc = to_intel_crtc(crtc);
-
-		if (!crtc->state->active)
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+		struct intel_plane *plane =
+			to_intel_plane(crtc->base.primary);
+		struct intel_plane_state *plane_state =
+			to_intel_plane_state(plane->base.state);
+
+		if (!crtc_state->uapi.active)
 			continue;
 
-		drm_WARN(dev, !crtc->primary->state->fb,
-			 "re-used BIOS config but lost an fb on crtc %d\n",
-			 crtc->base.id);
+		drm_WARN(dev, !plane_state->uapi.fb,
+			 "re-used BIOS config but lost an fb on [PLANE:%d:%s]\n",
+			 plane->base.base.id, plane->base.name);
 	}
 
 
diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c
index cef1061fd6cb..e10b9cd8e86e 100644
--- a/drivers/gpu/drm/i915/display/intel_fdi.c
+++ b/drivers/gpu/drm/i915/display/intel_fdi.c
@@ -4,7 +4,6 @@
  */
 #include "intel_atomic.h"
 #include "intel_ddi.h"
-#include "intel_ddi_buf_trans.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
 #include "intel_fdi.h"
@@ -96,10 +95,10 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
 	}
 }
 
-int ilk_fdi_compute_config(struct intel_crtc *intel_crtc,
-				  struct intel_crtc_state *pipe_config)
+int ilk_fdi_compute_config(struct intel_crtc *crtc,
+			   struct intel_crtc_state *pipe_config)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *i915 = to_i915(dev);
 	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int lane, link_bw, fdi_dotclock, ret;
@@ -125,7 +124,7 @@ retry:
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
 			       link_bw, &pipe_config->fdi_m_n, false, false);
 
-	ret = ilk_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
+	ret = ilk_check_fdi_lanes(dev, crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
 		return ret;
 
@@ -569,9 +568,9 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 	u32 temp, i, rx_ctl_val;
 	int n_entries;
 
-	intel_ddi_get_buf_trans_fdi(dev_priv, &n_entries);
+	encoder->get_buf_trans(encoder, crtc_state, &n_entries);
 
-	intel_prepare_dp_ddi_buffers(encoder, crtc_state);
+	hsw_prepare_dp_ddi_buffers(encoder, crtc_state);
 
 	/* Set the FDI_RX_MISC pwrdn lanes and the 2 workarounds listed at the
 	 * mode set "sequence for CRT port" document:
@@ -691,9 +690,9 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 
 void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -726,11 +725,11 @@ void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-void ilk_fdi_pll_disable(struct intel_crtc *intel_crtc)
+void ilk_fdi_pll_disable(struct intel_crtc *crtc)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	enum pipe pipe = intel_crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index fcf47f98ea36..ceb1bf8a8c3c 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -600,7 +600,7 @@ do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num,
 	int i = 0, inc, try = 0;
 	int ret = 0;
 
-	/* Display WA #0868: skl,bxt,kbl,cfl,glk,cnl */
+	/* Display WA #0868: skl,bxt,kbl,cfl,glk */
 	if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		bxt_gmbus_clock_gating(dev_priv, false);
 	else if (HAS_PCH_SPT(dev_priv) || HAS_PCH_CNP(dev_priv))
@@ -713,7 +713,7 @@ timeout:
 	ret = -EAGAIN;
 
 out:
-	/* Display WA #0868: skl,bxt,kbl,cfl,glk,cnl */
+	/* Display WA #0868: skl,bxt,kbl,cfl,glk */
 	if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv))
 		bxt_gmbus_clock_gating(dev_priv, true);
 	else if (HAS_PCH_SPT(dev_priv) || HAS_PCH_CNP(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 7e51c98c475e..b04685bb6439 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -51,6 +51,7 @@
 #include "intel_hdmi.h"
 #include "intel_lspcon.h"
 #include "intel_panel.h"
+#include "intel_snps_phy.h"
 
 static struct drm_device *intel_hdmi_to_dev(struct intel_hdmi *intel_hdmi)
 {
@@ -270,8 +271,8 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	i915_reg_t reg = TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 	int i;
 
@@ -286,13 +287,13 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 	intel_de_write(dev_priv, reg, val);
 
 	for (i = 0; i < len; i += 4) {
-		intel_de_write(dev_priv, TVIDEO_DIP_DATA(intel_crtc->pipe),
+		intel_de_write(dev_priv, TVIDEO_DIP_DATA(crtc->pipe),
 			       *data);
 		data++;
 	}
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
-		intel_de_write(dev_priv, TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
+		intel_de_write(dev_priv, TVIDEO_DIP_DATA(crtc->pipe), 0);
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -349,8 +350,8 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	i915_reg_t reg = TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 	int i;
 
@@ -368,13 +369,13 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 	intel_de_write(dev_priv, reg, val);
 
 	for (i = 0; i < len; i += 4) {
-		intel_de_write(dev_priv, TVIDEO_DIP_DATA(intel_crtc->pipe),
+		intel_de_write(dev_priv, TVIDEO_DIP_DATA(crtc->pipe),
 			       *data);
 		data++;
 	}
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
-		intel_de_write(dev_priv, TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
+		intel_de_write(dev_priv, TVIDEO_DIP_DATA(crtc->pipe), 0);
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -427,8 +428,8 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 	int i;
 
@@ -444,13 +445,13 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 
 	for (i = 0; i < len; i += 4) {
 		intel_de_write(dev_priv,
-			       VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
+			       VLV_TVIDEO_DIP_DATA(crtc->pipe), *data);
 		data++;
 	}
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		intel_de_write(dev_priv,
-			       VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
+			       VLV_TVIDEO_DIP_DATA(crtc->pipe), 0);
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -1040,10 +1041,10 @@ static void ibx_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
-	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
+	i915_reg_t reg = TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 	u32 port = VIDEO_DIP_PORT(encoder->port);
 
@@ -1099,9 +1100,9 @@ static void cpt_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
-	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
+	i915_reg_t reg = TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 
 	assert_hdmi_port_disabled(intel_hdmi);
@@ -1148,9 +1149,9 @@ static void vlv_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
-	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
+	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(crtc->pipe);
 	u32 val = intel_de_read(dev_priv, reg);
 	u32 port = VIDEO_DIP_PORT(encoder->port);
 
@@ -1465,14 +1466,12 @@ static int kbl_repositioning_enc_en_signal(struct intel_connector *connector,
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
-	struct drm_crtc *crtc = connector->base.state->crtc;
-	struct intel_crtc *intel_crtc = container_of(crtc,
-						     struct intel_crtc, base);
+	struct intel_crtc *crtc = to_intel_crtc(connector->base.state->crtc);
 	u32 scanline;
 	int ret;
 
 	for (;;) {
-		scanline = intel_de_read(dev_priv, PIPEDSL(intel_crtc->pipe));
+		scanline = intel_de_read(dev_priv, PIPEDSL(crtc->pipe));
 		if (scanline > 100 && scanline < 200)
 			break;
 		usleep_range(25, 50);
@@ -1852,6 +1851,16 @@ hdmi_port_clock_valid(struct intel_hdmi *hdmi,
 	if (IS_CHERRYVIEW(dev_priv) && clock > 216000 && clock < 240000)
 		return MODE_CLOCK_RANGE;
 
+	/*
+	 * SNPS PHYs' MPLLB table-based programming can only handle a fixed
+	 * set of link rates.
+	 *
+	 * FIXME: We will hopefully get an algorithmic way of programming
+	 * the MPLLB for HDMI in the future.
+	 */
+	if (IS_DG2(dev_priv))
+		return intel_snps_phy_check_hdmi_link_rate(clock);
+
 	return MODE_OK;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 7f40e9f60bc2..e0381b0fce91 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -411,12 +411,12 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	struct intel_connector *intel_connector =
 		lvds_encoder->attached_connector;
 	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	unsigned int lvds_bpp;
 	int ret;
 
 	/* Should never happen!! */
-	if (DISPLAY_VER(dev_priv) < 4 && intel_crtc->pipe == 0) {
+	if (DISPLAY_VER(dev_priv) < 4 && crtc->pipe == 0) {
 		drm_err(&dev_priv->drm, "Can't support LVDS on pipe A\n");
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index dfd724e506b5..3855fba70980 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -1078,6 +1078,9 @@ void intel_opregion_resume(struct drm_i915_private *i915)
 		opregion->asle->ardy = ASLE_ARDY_READY;
 	}
 
+	/* Some platforms abuse the _DSM to enable MUX */
+	intel_dsm_get_bios_data_funcs_supported(i915);
+
 	intel_opregion_notify_adapter(i915, PCI_D0);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 77865cf6641f..1b0daf649e82 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -32,6 +32,7 @@
 #include "intel_dp_aux.h"
 #include "intel_hdmi.h"
 #include "intel_psr.h"
+#include "intel_snps_phy.h"
 #include "intel_sprite.h"
 #include "skl_universal_plane.h"
 
@@ -265,32 +266,44 @@ static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp)
 	return val;
 }
 
-static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp)
+static void intel_dp_get_su_granularity(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u16 val;
 	ssize_t r;
+	u16 w;
+	u8 y;
+
+	/* If sink don't have specific granularity requirements set legacy ones */
+	if (!(intel_dp->psr_dpcd[1] & DP_PSR2_SU_GRANULARITY_REQUIRED)) {
+		/* As PSR2 HW sends full lines, we do not care about x granularity */
+		w = 4;
+		y = 4;
+		goto exit;
+	}
 
-	/*
-	 * Returning the default X granularity if granularity not required or
-	 * if DPCD read fails
-	 */
-	if (!(intel_dp->psr_dpcd[1] & DP_PSR2_SU_GRANULARITY_REQUIRED))
-		return 4;
-
-	r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_X_GRANULARITY, &val, 2);
+	r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_X_GRANULARITY, &w, 2);
 	if (r != 2)
 		drm_dbg_kms(&i915->drm,
 			    "Unable to read DP_PSR2_SU_X_GRANULARITY\n");
-
 	/*
 	 * Spec says that if the value read is 0 the default granularity should
 	 * be used instead.
 	 */
-	if (r != 2 || val == 0)
-		val = 4;
+	if (r != 2 || w == 0)
+		w = 4;
 
-	return val;
+	r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_Y_GRANULARITY, &y, 1);
+	if (r != 1) {
+		drm_dbg_kms(&i915->drm,
+			    "Unable to read DP_PSR2_SU_Y_GRANULARITY\n");
+		y = 4;
+	}
+	if (y == 0)
+		y = 1;
+
+exit:
+	intel_dp->psr.su_w_granularity = w;
+	intel_dp->psr.su_y_granularity = y;
 }
 
 void intel_psr_init_dpcd(struct intel_dp *intel_dp)
@@ -346,8 +359,7 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		if (intel_dp->psr.sink_psr2_support) {
 			intel_dp->psr.colorimetry_support =
 				intel_dp_get_colorimetry_status(intel_dp);
-			intel_dp->psr.su_x_granularity =
-				intel_dp_get_su_x_granulartiy(intel_dp);
+			intel_dp_get_su_granularity(intel_dp);
 		}
 	}
 }
@@ -407,6 +419,9 @@ static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 			dpcd_val |= DP_PSR_CRC_VERIFICATION;
 	}
 
+	if (intel_dp->psr.req_psr2_sdp_prior_scanline)
+		dpcd_val |= DP_PSR_SU_REGION_SCANLINE_CAPTURE;
+
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
@@ -520,18 +535,47 @@ static u32 intel_psr2_get_tp_time(struct intel_dp *intel_dp)
 static void hsw_activate_psr2(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	u32 val;
+	u32 val = EDP_PSR2_ENABLE;
 
-	val = psr_compute_idle_frames(intel_dp) << EDP_PSR2_IDLE_FRAME_SHIFT;
+	val |= psr_compute_idle_frames(intel_dp) << EDP_PSR2_IDLE_FRAME_SHIFT;
+
+	if (!IS_ALDERLAKE_P(dev_priv))
+		val |= EDP_SU_TRACK_ENABLE;
 
-	val |= EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE;
 	if (DISPLAY_VER(dev_priv) >= 10 && DISPLAY_VER(dev_priv) <= 12)
 		val |= EDP_Y_COORDINATE_ENABLE;
 
 	val |= EDP_PSR2_FRAME_BEFORE_SU(intel_dp->psr.sink_sync_latency + 1);
 	val |= intel_psr2_get_tp_time(intel_dp);
 
-	if (DISPLAY_VER(dev_priv) >= 12) {
+	/* Wa_22012278275:adl-p */
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_E0)) {
+		static const u8 map[] = {
+			2, /* 5 lines */
+			1, /* 6 lines */
+			0, /* 7 lines */
+			3, /* 8 lines */
+			6, /* 9 lines */
+			5, /* 10 lines */
+			4, /* 11 lines */
+			7, /* 12 lines */
+		};
+		/*
+		 * Still using the default IO_BUFFER_WAKE and FAST_WAKE, see
+		 * comments bellow for more information
+		 */
+		u32 tmp, lines = 7;
+
+		val |= TGL_EDP_PSR2_BLOCK_COUNT_NUM_2;
+
+		tmp = map[lines - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES];
+		tmp = tmp << TGL_EDP_PSR2_IO_BUFFER_WAKE_SHIFT;
+		val |= tmp;
+
+		tmp = map[lines - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES];
+		tmp = tmp << TGL_EDP_PSR2_FAST_WAKE_MIN_SHIFT;
+		val |= tmp;
+	} else if (DISPLAY_VER(dev_priv) >= 12) {
 		/*
 		 * TODO: 7 lines of IO_BUFFER_WAKE and FAST_WAKE are default
 		 * values from BSpec. In order to setting an optimal power
@@ -547,10 +591,12 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 		val |= EDP_PSR2_FAST_WAKE(7);
 	}
 
+	if (intel_dp->psr.req_psr2_sdp_prior_scanline)
+		val |= EDP_PSR2_SU_SDP_SCANLINE;
+
 	if (intel_dp->psr.psr2_sel_fetch_enabled) {
-		/* WA 1408330847 */
-		if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0) ||
-		    IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0))
+		/* Wa_1408330847 */
+		if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 			intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
 				     DIS_RAM_BYPASS_PSR2_MAN_TRACK,
 				     DIS_RAM_BYPASS_PSR2_MAN_TRACK);
@@ -689,6 +735,10 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp,
 	if (!dc3co_is_pipe_port_compatible(intel_dp, crtc_state))
 		return;
 
+	/* Wa_16011303918:adl-p */
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
+		return;
+
 	/*
 	 * DC3CO Exit time 200us B.Spec 49196
 	 * PSR2 transcoder Early Exit scanlines = ROUNDUP(200 / line time) + 1
@@ -733,7 +783,7 @@ static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp,
 	}
 
 	/* Wa_14010254185 Wa_14010103792 */
-	if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B1)) {
+	if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "PSR2 sel fetch not enabled, missing the implementation of WAs\n");
 		return false;
@@ -742,6 +792,67 @@ static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp,
 	return crtc_state->enable_psr2_sel_fetch = true;
 }
 
+static bool psr2_granularity_check(struct intel_dp *intel_dp,
+				   struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	const int crtc_hdisplay = crtc_state->hw.adjusted_mode.crtc_hdisplay;
+	const int crtc_vdisplay = crtc_state->hw.adjusted_mode.crtc_vdisplay;
+	u16 y_granularity = 0;
+
+	/* PSR2 HW only send full lines so we only need to validate the width */
+	if (crtc_hdisplay % intel_dp->psr.su_w_granularity)
+		return false;
+
+	if (crtc_vdisplay % intel_dp->psr.su_y_granularity)
+		return false;
+
+	/* HW tracking is only aligned to 4 lines */
+	if (!crtc_state->enable_psr2_sel_fetch)
+		return intel_dp->psr.su_y_granularity == 4;
+
+	/*
+	 * adl_p has 1 line granularity. For other platforms with SW tracking we
+	 * can adjust the y coordinates to match sink requirement if multiple of
+	 * 4.
+	 */
+	if (IS_ALDERLAKE_P(dev_priv))
+		y_granularity = intel_dp->psr.su_y_granularity;
+	else if (intel_dp->psr.su_y_granularity <= 2)
+		y_granularity = 4;
+	else if ((intel_dp->psr.su_y_granularity % 4) == 0)
+		y_granularity = intel_dp->psr.su_y_granularity;
+
+	if (y_granularity == 0 || crtc_vdisplay % y_granularity)
+		return false;
+
+	crtc_state->su_y_granularity = y_granularity;
+	return true;
+}
+
+static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_dp,
+							struct intel_crtc_state *crtc_state)
+{
+	const struct drm_display_mode *adjusted_mode = &crtc_state->uapi.adjusted_mode;
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u32 hblank_total, hblank_ns, req_ns;
+
+	hblank_total = adjusted_mode->crtc_hblank_end - adjusted_mode->crtc_hblank_start;
+	hblank_ns = div_u64(1000000ULL * hblank_total, adjusted_mode->crtc_clock);
+
+	/* From spec: (72 / number of lanes) * 1000 / symbol clock frequency MHz */
+	req_ns = (72 / crtc_state->lane_count) * 1000 / (crtc_state->port_clock / 1000);
+
+	if ((hblank_ns - req_ns) > 100)
+		return true;
+
+	if (DISPLAY_VER(dev_priv) < 13 || intel_dp->edp_dpcd[0] < DP_EDP_14b)
+		return false;
+
+	crtc_state->req_psr2_sdp_prior_scanline = true;
+	return true;
+}
+
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -760,7 +871,8 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	}
 
 	/* Wa_16011181250 */
-	if (IS_ROCKETLAKE(dev_priv) || IS_ALDERLAKE_S(dev_priv)) {
+	if (IS_ROCKETLAKE(dev_priv) || IS_ALDERLAKE_S(dev_priv) ||
+	    IS_DG2(dev_priv)) {
 		drm_dbg_kms(&dev_priv->drm, "PSR2 is defeatured for this platform\n");
 		return false;
 	}
@@ -824,19 +936,6 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	/*
-	 * HW sends SU blocks of size four scan lines, which means the starting
-	 * X coordinate and Y granularity requirements will always be met. We
-	 * only need to validate the SU block width is a multiple of
-	 * x granularity.
-	 */
-	if (crtc_hdisplay % intel_dp->psr.su_x_granularity) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "PSR2 not enabled, hdisplay(%d) not multiple of %d\n",
-			    crtc_hdisplay, intel_dp->psr.su_x_granularity);
-		return false;
-	}
-
 	if (HAS_PSR2_SEL_FETCH(dev_priv)) {
 		if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) &&
 		    !HAS_PSR_HW_TRACKING(dev_priv)) {
@@ -848,11 +947,16 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 
 	/* Wa_2209313811 */
 	if (!crtc_state->enable_psr2_sel_fetch &&
-	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B1)) {
+	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) {
 		drm_dbg_kms(&dev_priv->drm, "PSR2 HW tracking is not supported this Display stepping\n");
 		return false;
 	}
 
+	if (!psr2_granularity_check(intel_dp, crtc_state)) {
+		drm_dbg_kms(&dev_priv->drm, "PSR2 not enabled, SU granularity not compatible\n");
+		return false;
+	}
+
 	if (!crtc_state->enable_psr2_sel_fetch &&
 	    (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v)) {
 		drm_dbg_kms(&dev_priv->drm,
@@ -862,6 +966,20 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
+	if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n");
+		return false;
+	}
+
+	/* Wa_16011303918:adl-p */
+	if (crtc_state->vrr.enable &&
+	    IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 not enabled, not compatible with HW stepping + VRR\n");
+		return false;
+	}
+
 	tgl_dc3co_exitline_compute_config(intel_dp, crtc_state);
 	return true;
 }
@@ -1048,6 +1166,14 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp)
 		intel_de_rmw(dev_priv, CHICKEN_PAR1_1, IGNORE_PSR2_HW_TRACKING,
 			     intel_dp->psr.psr2_sel_fetch_enabled ?
 			     IGNORE_PSR2_HW_TRACKING : 0);
+
+	/* Wa_16011168373:adl-p */
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) &&
+	    intel_dp->psr.psr2_enabled)
+		intel_de_rmw(dev_priv,
+			     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
+			     TRANS_SET_CONTEXT_LATENCY_MASK,
+			     TRANS_SET_CONTEXT_LATENCY_VALUE(1));
 }
 
 static bool psr_interrupt_error_check(struct intel_dp *intel_dp)
@@ -1087,6 +1213,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port);
 	struct intel_encoder *encoder = &dig_port->base;
 	u32 val;
 
@@ -1101,6 +1228,8 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 	intel_dp->psr.dc3co_exit_delay = val;
 	intel_dp->psr.dc3co_exitline = crtc_state->dc3co_exitline;
 	intel_dp->psr.psr2_sel_fetch_enabled = crtc_state->enable_psr2_sel_fetch;
+	intel_dp->psr.req_psr2_sdp_prior_scanline =
+		crtc_state->req_psr2_sdp_prior_scanline;
 
 	if (!psr_interrupt_error_check(intel_dp))
 		return;
@@ -1110,6 +1239,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 	intel_dp_compute_psr_vsc_sdp(intel_dp, crtc_state, conn_state,
 				     &intel_dp->psr.vsc);
 	intel_write_dp_vsc_sdp(encoder, crtc_state, &intel_dp->psr.vsc);
+	intel_snps_phy_update_psr_power_state(dev_priv, phy, true);
 	intel_psr_enable_sink(intel_dp);
 	intel_psr_enable_source(intel_dp);
 	intel_dp->psr.enabled = true;
@@ -1206,6 +1336,8 @@ static void intel_psr_wait_exit_locked(struct intel_dp *intel_dp)
 static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	enum phy phy = intel_port_to_phy(dev_priv,
+					 dp_to_dig_port(intel_dp)->base.port);
 
 	lockdep_assert_held(&intel_dp->psr.lock);
 
@@ -1218,13 +1350,21 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 	intel_psr_exit(intel_dp);
 	intel_psr_wait_exit_locked(intel_dp);
 
-	/* WA 1408330847 */
+	/* Wa_1408330847 */
 	if (intel_dp->psr.psr2_sel_fetch_enabled &&
-	    (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0) ||
-	     IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0)))
+	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
 			     DIS_RAM_BYPASS_PSR2_MAN_TRACK, 0);
 
+	/* Wa_16011168373:adl-p */
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) &&
+	    intel_dp->psr.psr2_enabled)
+		intel_de_rmw(dev_priv,
+			     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
+			     TRANS_SET_CONTEXT_LATENCY_MASK, 0);
+
+	intel_snps_phy_update_psr_power_state(dev_priv, phy, false);
+
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
 
@@ -1397,21 +1537,32 @@ void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_st
 static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
 				  struct drm_rect *clip, bool full_update)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 val = PSR2_MAN_TRK_CTL_ENABLE;
 
 	if (full_update) {
-		val |= PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
+		if (IS_ALDERLAKE_P(dev_priv))
+			val |= ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
+		else
+			val |= PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
+
 		goto exit;
 	}
 
 	if (clip->y1 == -1)
 		goto exit;
 
-	drm_WARN_ON(crtc_state->uapi.crtc->dev, clip->y1 % 4 || clip->y2 % 4);
+	if (IS_ALDERLAKE_P(dev_priv)) {
+		val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1);
+		val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2);
+	} else {
+		drm_WARN_ON(crtc_state->uapi.crtc->dev, clip->y1 % 4 || clip->y2 % 4);
 
-	val |= PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE;
-	val |= PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1 / 4 + 1);
-	val |= PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 / 4 + 1);
+		val |= PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE;
+		val |= PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1 / 4 + 1);
+		val |= PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 / 4 + 1);
+	}
 exit:
 	crtc_state->psr2_man_track_ctl = val;
 }
@@ -1432,6 +1583,20 @@ static void clip_area_update(struct drm_rect *overlap_damage_area,
 		overlap_damage_area->y2 = damage_area->y2;
 }
 
+static void intel_psr2_sel_fetch_pipe_alignment(const struct intel_crtc_state *crtc_state,
+						struct drm_rect *pipe_clip)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	const u16 y_alignment = crtc_state->su_y_granularity;
+
+	pipe_clip->y1 -= pipe_clip->y1 % y_alignment;
+	if (pipe_clip->y2 % y_alignment)
+		pipe_clip->y2 = ((pipe_clip->y2 / y_alignment) + 1) * y_alignment;
+
+	if (IS_ALDERLAKE_P(dev_priv) && crtc_state->dsc.compression_enable)
+		drm_warn(&dev_priv->drm, "Missing PSR2 sel fetch alignment with DSC\n");
+}
+
 int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 				struct intel_crtc *crtc)
 {
@@ -1540,10 +1705,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	if (full_update)
 		goto skip_sel_fetch_set_loop;
 
-	/* It must be aligned to 4 lines */
-	pipe_clip.y1 -= pipe_clip.y1 % 4;
-	if (pipe_clip.y2 % 4)
-		pipe_clip.y2 = ((pipe_clip.y2 / 4) + 1) * 4;
+	intel_psr2_sel_fetch_pipe_alignment(crtc_state, &pipe_clip);
 
 	/*
 	 * Now that we have the pipe damaged area check if it intersect with
@@ -1564,6 +1726,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 		sel_fetch_area = &new_plane_state->psr2_sel_fetch_area;
 		sel_fetch_area->y1 = inter.y1 - new_plane_state->uapi.dst.y1;
 		sel_fetch_area->y2 = inter.y2 - new_plane_state->uapi.dst.y1;
+		crtc_state->update_planes |= BIT(plane->id);
 	}
 
 skip_sel_fetch_set_loop:
diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index 98dd787b00e3..8a52b7a16774 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -53,6 +53,12 @@ static void quirk_increase_ddi_disabled_time(struct drm_i915_private *i915)
 	drm_info(&i915->drm, "Applying Increase DDI Disabled quirk\n");
 }
 
+static void quirk_no_pps_backlight_power_hook(struct drm_i915_private *i915)
+{
+	i915->quirks |= QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK;
+	drm_info(&i915->drm, "Applying no pps backlight power quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -72,6 +78,12 @@ static int intel_dmi_reverse_brightness(const struct dmi_system_id *id)
 	return 1;
 }
 
+static int intel_dmi_no_pps_backlight(const struct dmi_system_id *id)
+{
+	DRM_INFO("No pps backlight support on %s\n", id->ident);
+	return 1;
+}
+
 static const struct intel_dmi_quirk intel_dmi_quirks[] = {
 	{
 		.dmi_id_list = &(const struct dmi_system_id[]) {
@@ -96,6 +108,28 @@ static const struct intel_dmi_quirk intel_dmi_quirks[] = {
 		},
 		.hook = quirk_invert_brightness,
 	},
+	{
+		.dmi_id_list = &(const struct dmi_system_id[]) {
+			{
+				.callback = intel_dmi_no_pps_backlight,
+				.ident = "Google Lillipup sku524294",
+				.matches = {DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Google"),
+					    DMI_EXACT_MATCH(DMI_BOARD_NAME, "Lindar"),
+					    DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "sku524294"),
+				},
+			},
+			{
+				.callback = intel_dmi_no_pps_backlight,
+				.ident = "Google Lillipup sku524295",
+				.matches = {DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Google"),
+					    DMI_EXACT_MATCH(DMI_BOARD_NAME, "Lindar"),
+					    DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "sku524295"),
+				},
+			},
+			{ }
+		},
+		.hook = quirk_no_pps_backlight_power_hook,
+	},
 };
 
 static struct intel_quirk intel_quirks[] = {
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index e4f91d7a5c60..6cb27599ea03 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1824,7 +1824,7 @@ static void intel_enable_sdvo(struct intel_atomic_state *state,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	u32 temp;
 	bool input1, input2;
 	int i;
@@ -1835,7 +1835,7 @@ static void intel_enable_sdvo(struct intel_atomic_state *state,
 	intel_sdvo_write_sdvox(intel_sdvo, temp);
 
 	for (i = 0; i < 2; i++)
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
+		intel_wait_for_vblank(dev_priv, crtc->pipe);
 
 	success = intel_sdvo_get_trained_inputs(intel_sdvo, &input1, &input2);
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c
new file mode 100644
index 000000000000..18b52b64af95
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c
@@ -0,0 +1,862 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/util_macros.h>
+
+#include "intel_de.h"
+#include "intel_display_types.h"
+#include "intel_snps_phy.h"
+
+/**
+ * DOC: Synopsis PHY support
+ *
+ * Synopsis PHYs are primarily programmed by looking up magic register values
+ * in tables rather than calculating the necessary values at runtime.
+ *
+ * Of special note is that the SNPS PHYs include a dedicated port PLL, known as
+ * an "MPLLB."  The MPLLB replaces the shared DPLL functionality used on other
+ * platforms and must be programming directly during the modeset sequence
+ * since it is not handled by the shared DPLL framework as on other platforms.
+ */
+
+void intel_snps_phy_wait_for_calibration(struct drm_i915_private *dev_priv)
+{
+	enum phy phy;
+
+	for_each_phy_masked(phy, ~0) {
+		if (!intel_phy_is_snps(dev_priv, phy))
+			continue;
+
+		if (intel_de_wait_for_clear(dev_priv, ICL_PHY_MISC(phy),
+					    DG2_PHY_DP_TX_ACK_MASK, 25))
+			DRM_ERROR("SNPS PHY %c failed to calibrate after 25ms.\n",
+				  phy);
+	}
+}
+
+void intel_snps_phy_update_psr_power_state(struct drm_i915_private *dev_priv,
+					   enum phy phy, bool enable)
+{
+	u32 val;
+
+	if (!intel_phy_is_snps(dev_priv, phy))
+		return;
+
+	val = REG_FIELD_PREP(SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR,
+			     enable ? 2 : 3);
+	intel_uncore_rmw(&dev_priv->uncore, SNPS_PHY_TX_REQ(phy),
+			 SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR, val);
+}
+
+static const u32 dg2_ddi_translations[] = {
+	/* VS 0, pre-emph 0 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 26),
+
+	/* VS 0, pre-emph 1 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 33) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 6),
+
+	/* VS 0, pre-emph 2 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 38) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 12),
+
+	/* VS 0, pre-emph 3 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 43) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 19),
+
+	/* VS 1, pre-emph 0 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 39),
+
+	/* VS 1, pre-emph 1 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 44) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 8),
+
+	/* VS 1, pre-emph 2 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 47) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 15),
+
+	/* VS 2, pre-emph 0 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 52),
+
+	/* VS 2, pre-emph 1 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 51) |
+		REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, 10),
+
+	/* VS 3, pre-emph 0 */
+	REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, 62),
+};
+
+void intel_snps_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
+					u32 level)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	int n_entries, ln;
+
+	n_entries = ARRAY_SIZE(dg2_ddi_translations);
+	if (level >= n_entries)
+		level = n_entries - 1;
+
+	for (ln = 0; ln < 4; ln++)
+		intel_de_write(dev_priv, SNPS_PHY_TX_EQ(ln, phy),
+			       dg2_ddi_translations[level]);
+}
+
+/*
+ * Basic DP link rates with 100 MHz reference clock.
+ */
+
+static const struct intel_mpllb_state dg2_dp_rbr_100 = {
+	.clock = 162000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 20) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 226),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 39321) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 3),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr1_100 = {
+	.clock = 270000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 20) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 184),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr2_100 = {
+	.clock = 540000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 20) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 184),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr3_100 = {
+	.clock = 810000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 19) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 292),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+};
+
+static const struct intel_mpllb_state *dg2_dp_100_tables[] = {
+	&dg2_dp_rbr_100,
+	&dg2_dp_hbr1_100,
+	&dg2_dp_hbr2_100,
+	&dg2_dp_hbr3_100,
+	NULL,
+};
+
+/*
+ * Basic DP link rates with 38.4 MHz reference clock.
+ */
+
+static const struct intel_mpllb_state dg2_dp_rbr_38_4 = {
+	.clock = 162000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 1),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 25) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 304),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 49152),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr1_38_4 = {
+	.clock = 270000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 1),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 25) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 248),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 40960),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr2_38_4 = {
+	.clock = 540000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 1),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 25) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 248),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 40960),
+};
+
+static const struct intel_mpllb_state dg2_dp_hbr3_38_4 = {
+	.clock = 810000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 1),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 26) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 388),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 1),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 61440),
+};
+
+static const struct intel_mpllb_state *dg2_dp_38_4_tables[] = {
+	&dg2_dp_rbr_38_4,
+	&dg2_dp_hbr1_38_4,
+	&dg2_dp_hbr2_38_4,
+	&dg2_dp_hbr3_38_4,
+	NULL,
+};
+
+/*
+ * eDP link rates with 100 MHz reference clock.
+ */
+
+static const struct intel_mpllb_state dg2_edp_r216 = {
+	.clock = 216000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 19) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 312),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 52428) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 4),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_PEAK, 50961),
+	.mpllb_sscstep =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_STEPSIZE, 65752),
+};
+
+static const struct intel_mpllb_state dg2_edp_r243 = {
+	.clock = 243000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 20) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 356),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_PEAK, 57331),
+	.mpllb_sscstep =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_STEPSIZE, 73971),
+};
+
+static const struct intel_mpllb_state dg2_edp_r324 = {
+	.clock = 324000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 20) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 226),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 39321) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 3),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_PEAK, 38221),
+	.mpllb_sscstep =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_STEPSIZE, 49314),
+};
+
+static const struct intel_mpllb_state dg2_edp_r432 = {
+	.clock = 432000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 19) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 65) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 127),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 312),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 52428) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 4),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_PEAK, 50961),
+	.mpllb_sscstep =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_STEPSIZE, 65752),
+};
+
+static const struct intel_mpllb_state *dg2_edp_tables[] = {
+	&dg2_dp_rbr_100,
+	&dg2_edp_r216,
+	&dg2_edp_r243,
+	&dg2_dp_hbr1_100,
+	&dg2_edp_r324,
+	&dg2_edp_r432,
+	&dg2_dp_hbr2_100,
+	&dg2_dp_hbr3_100,
+	NULL,
+};
+
+/*
+ * HDMI link rates with 100 MHz reference clock.
+ */
+
+static const struct intel_mpllb_state dg2_hdmi_25_175 = {
+	.clock = 25175,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 128) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 143),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 36663) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 71),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1),
+};
+
+static const struct intel_mpllb_state dg2_hdmi_27_0 = {
+	.clock = 27000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 140) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1),
+};
+
+static const struct intel_mpllb_state dg2_hdmi_74_25 = {
+	.clock = 74250,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1),
+};
+
+static const struct intel_mpllb_state dg2_hdmi_148_5 = {
+	.clock = 148500,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1),
+};
+
+static const struct intel_mpllb_state dg2_hdmi_594 = {
+	.clock = 594000,
+	.ref_control =
+		REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3),
+	.mpllb_cp =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 4) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124),
+	.mpllb_div =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3),
+	.mpllb_div2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1),
+	.mpllb_fracn1 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 5),
+	.mpllb_fracn2 =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) |
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2),
+	.mpllb_sscen =
+		REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1),
+};
+
+static const struct intel_mpllb_state *dg2_hdmi_tables[] = {
+	&dg2_hdmi_25_175,
+	&dg2_hdmi_27_0,
+	&dg2_hdmi_74_25,
+	&dg2_hdmi_148_5,
+	&dg2_hdmi_594,
+	NULL,
+};
+
+static const struct intel_mpllb_state **
+intel_mpllb_tables_get(struct intel_crtc_state *crtc_state,
+		       struct intel_encoder *encoder)
+{
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) {
+		return dg2_edp_tables;
+	} else if (intel_crtc_has_dp_encoder(crtc_state)) {
+		/*
+		 * FIXME: Initially we're just enabling the "combo" outputs on
+		 * port A-D.  The MPLLB for those ports takes an input from the
+		 * "Display Filter PLL" which always has an output frequency
+		 * of 100 MHz, hence the use of the _100 tables below.
+		 *
+		 * Once we enable port TC1 it will either use the same 100 MHz
+		 * "Display Filter PLL" (when strapped to support a native
+		 * display connection) or different 38.4 MHz "Filter PLL" when
+		 * strapped to support a USB connection, so we'll need to check
+		 * that to determine which table to use.
+		 */
+		if (0)
+			return dg2_dp_38_4_tables;
+		else
+			return dg2_dp_100_tables;
+	} else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+		return dg2_hdmi_tables;
+	}
+
+	MISSING_CASE(encoder->type);
+	return NULL;
+}
+
+int intel_mpllb_calc_state(struct intel_crtc_state *crtc_state,
+			   struct intel_encoder *encoder)
+{
+	const struct intel_mpllb_state **tables;
+	int i;
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+		if (intel_snps_phy_check_hdmi_link_rate(crtc_state->port_clock)
+		    != MODE_OK) {
+			/*
+			 * FIXME: Can only support fixed HDMI frequencies
+			 * until we have a proper algorithm under a valid
+			 * license.
+			 */
+			DRM_DEBUG_KMS("Can't support HDMI link rate %d\n",
+				      crtc_state->port_clock);
+			return -EINVAL;
+		}
+	}
+
+	tables = intel_mpllb_tables_get(crtc_state, encoder);
+	if (!tables)
+		return -EINVAL;
+
+	for (i = 0; tables[i]; i++) {
+		if (crtc_state->port_clock <= tables[i]->clock) {
+			crtc_state->mpllb_state = *tables[i];
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+void intel_mpllb_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	const struct intel_mpllb_state *pll_state = &crtc_state->mpllb_state;
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	i915_reg_t enable_reg = (phy <= PHY_D ?
+				 DG2_PLL_ENABLE(phy) : MG_PLL_ENABLE(0));
+
+	/*
+	 * 3. Software programs the following PLL registers for the desired
+	 * frequency.
+	 */
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_CP(phy), pll_state->mpllb_cp);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV(phy), pll_state->mpllb_div);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV2(phy), pll_state->mpllb_div2);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_SSCEN(phy), pll_state->mpllb_sscen);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_SSCSTEP(phy), pll_state->mpllb_sscstep);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_FRACN1(phy), pll_state->mpllb_fracn1);
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_FRACN2(phy), pll_state->mpllb_fracn2);
+
+	/*
+	 * 4. If the frequency will result in a change to the voltage
+	 * requirement, follow the Display Voltage Frequency Switching -
+	 * Sequence Before Frequency Change.
+	 *
+	 * We handle this step in bxt_set_cdclk().
+	 */
+
+	/* 5. Software sets DPLL_ENABLE [PLL Enable] to "1". */
+	intel_uncore_rmw(&dev_priv->uncore, enable_reg, 0, PLL_ENABLE);
+
+	/*
+	 * 9. Software sets SNPS_PHY_MPLLB_DIV dp_mpllb_force_en to "1". This
+	 * will keep the PLL running during the DDI lane programming and any
+	 * typeC DP cable disconnect. Do not set the force before enabling the
+	 * PLL because that will start the PLL before it has sampled the
+	 * divider values.
+	 */
+	intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV(phy),
+		       pll_state->mpllb_div | SNPS_PHY_MPLLB_FORCE_EN);
+
+	/*
+	 * 10. Software polls on register DPLL_ENABLE [PLL Lock] to confirm PLL
+	 * is locked at new settings. This register bit is sampling PHY
+	 * dp_mpllb_state interface signal.
+	 */
+	if (intel_de_wait_for_set(dev_priv, enable_reg, PLL_LOCK, 5))
+		DRM_ERROR("Port %c PLL not locked\n", phy_name(phy));
+
+	/*
+	 * 11. If the frequency will result in a change to the voltage
+	 * requirement, follow the Display Voltage Frequency Switching -
+	 * Sequence After Frequency Change.
+	 *
+	 * We handle this step in bxt_set_cdclk().
+	 */
+}
+
+void intel_mpllb_disable(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	i915_reg_t enable_reg = (phy <= PHY_D ?
+				 DG2_PLL_ENABLE(phy) : MG_PLL_ENABLE(0));
+
+	/*
+	 * 1. If the frequency will result in a change to the voltage
+	 * requirement, follow the Display Voltage Frequency Switching -
+	 * Sequence Before Frequency Change.
+	 *
+	 * We handle this step in bxt_set_cdclk().
+	 */
+
+	/* 2. Software programs DPLL_ENABLE [PLL Enable] to "0" */
+	intel_uncore_rmw(&dev_priv->uncore, enable_reg, PLL_ENABLE, 0);
+
+	/*
+	 * 4. Software programs SNPS_PHY_MPLLB_DIV dp_mpllb_force_en to "0".
+	 * This will allow the PLL to stop running.
+	 */
+	intel_uncore_rmw(&dev_priv->uncore, SNPS_PHY_MPLLB_DIV(phy),
+			 SNPS_PHY_MPLLB_FORCE_EN, 0);
+
+	/*
+	 * 5. Software polls DPLL_ENABLE [PLL Lock] for PHY acknowledgment
+	 * (dp_txX_ack) that the new transmitter setting request is completed.
+	 */
+	if (intel_de_wait_for_clear(dev_priv, enable_reg, PLL_LOCK, 5))
+		DRM_ERROR("Port %c PLL not locked\n", phy_name(phy));
+
+	/*
+	 * 6. If the frequency will result in a change to the voltage
+	 * requirement, follow the Display Voltage Frequency Switching -
+	 * Sequence After Frequency Change.
+	 *
+	 * We handle this step in bxt_set_cdclk().
+	 */
+}
+
+int intel_mpllb_calc_port_clock(struct intel_encoder *encoder,
+				const struct intel_mpllb_state *pll_state)
+{
+	unsigned int frac_quot = 0, frac_rem = 0, frac_den = 1;
+	unsigned int multiplier, tx_clk_div, refclk;
+	bool frac_en;
+
+	if (0)
+		refclk = 38400;
+	else
+		refclk = 100000;
+
+	refclk >>= REG_FIELD_GET(SNPS_PHY_MPLLB_REF_CLK_DIV, pll_state->mpllb_div2) - 1;
+
+	frac_en = REG_FIELD_GET(SNPS_PHY_MPLLB_FRACN_EN, pll_state->mpllb_fracn1);
+
+	if (frac_en) {
+		frac_quot = REG_FIELD_GET(SNPS_PHY_MPLLB_FRACN_QUOT, pll_state->mpllb_fracn2);
+		frac_rem = REG_FIELD_GET(SNPS_PHY_MPLLB_FRACN_REM, pll_state->mpllb_fracn2);
+		frac_den = REG_FIELD_GET(SNPS_PHY_MPLLB_FRACN_DEN, pll_state->mpllb_fracn1);
+	}
+
+	multiplier = REG_FIELD_GET(SNPS_PHY_MPLLB_MULTIPLIER, pll_state->mpllb_div2) / 2 + 16;
+
+	tx_clk_div = REG_FIELD_GET(SNPS_PHY_MPLLB_TX_CLK_DIV, pll_state->mpllb_div);
+
+	return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(refclk, (multiplier << 16) + frac_quot) +
+				     DIV_ROUND_CLOSEST(refclk * frac_rem, frac_den),
+				     10 << (tx_clk_div + 16));
+}
+
+void intel_mpllb_readout_hw_state(struct intel_encoder *encoder,
+				  struct intel_mpllb_state *pll_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+
+	pll_state->mpllb_cp = intel_de_read(dev_priv, SNPS_PHY_MPLLB_CP(phy));
+	pll_state->mpllb_div = intel_de_read(dev_priv, SNPS_PHY_MPLLB_DIV(phy));
+	pll_state->mpllb_div2 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_DIV2(phy));
+	pll_state->mpllb_sscen = intel_de_read(dev_priv, SNPS_PHY_MPLLB_SSCEN(phy));
+	pll_state->mpllb_sscstep = intel_de_read(dev_priv, SNPS_PHY_MPLLB_SSCSTEP(phy));
+	pll_state->mpllb_fracn1 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_FRACN1(phy));
+	pll_state->mpllb_fracn2 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_FRACN2(phy));
+
+	/*
+	 * REF_CONTROL is under firmware control and never programmed by the
+	 * driver; we read it only for sanity checking purposes.  The bspec
+	 * only tells us the expected value for one field in this register,
+	 * so we'll only read out those specific bits here.
+	 */
+	pll_state->ref_control = intel_de_read(dev_priv, SNPS_PHY_REF_CONTROL(phy)) &
+		SNPS_PHY_REF_CONTROL_REF_RANGE;
+
+	/*
+	 * MPLLB_DIV is programmed twice, once with the software-computed
+	 * state, then again with the MPLLB_FORCE_EN bit added.  Drop that
+	 * extra bit during readout so that we return the actual expected
+	 * software state.
+	 */
+	pll_state->mpllb_div &= ~SNPS_PHY_MPLLB_FORCE_EN;
+}
+
+int intel_snps_phy_check_hdmi_link_rate(int clock)
+{
+	const struct intel_mpllb_state **tables = dg2_hdmi_tables;
+	int i;
+
+	for (i = 0; tables[i]; i++) {
+		if (clock == tables[i]->clock)
+			return MODE_OK;
+	}
+
+	return MODE_CLOCK_RANGE;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.h b/drivers/gpu/drm/i915/display/intel_snps_phy.h
new file mode 100644
index 000000000000..6261ff88ef5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_snps_phy.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_SNPS_PHY_H__
+#define __INTEL_SNPS_PHY_H__
+
+#include <linux/types.h>
+
+struct drm_i915_private;
+struct intel_encoder;
+struct intel_crtc_state;
+struct intel_mpllb_state;
+enum phy;
+
+void intel_snps_phy_wait_for_calibration(struct drm_i915_private *dev_priv);
+void intel_snps_phy_update_psr_power_state(struct drm_i915_private *dev_priv,
+					   enum phy phy, bool enable);
+
+int intel_mpllb_calc_state(struct intel_crtc_state *crtc_state,
+			   struct intel_encoder *encoder);
+void intel_mpllb_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *crtc_state);
+void intel_mpllb_disable(struct intel_encoder *encoder);
+void intel_mpllb_readout_hw_state(struct intel_encoder *encoder,
+				  struct intel_mpllb_state *pll_state);
+int intel_mpllb_calc_port_clock(struct intel_encoder *encoder,
+				const struct intel_mpllb_state *pll_state);
+
+int intel_snps_phy_check_hdmi_link_rate(int clock);
+void intel_snps_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
+					u32 level);
+
+#endif /* __INTEL_SNPS_PHY_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 4ae9a7455b23..08116f41da26 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1856,7 +1856,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 	zpos = sprite + 1;
 	drm_plane_create_zpos_immutable_property(&plane->base, zpos);
 
-	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
+	intel_plane_helper_add(plane);
 
 	return plane;
 
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index c23c210a55f5..3ffece568ed9 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -556,7 +556,7 @@ intel_tc_port_get_target_mode(struct intel_digital_port *dig_port)
 }
 
 static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port,
-				     int required_lanes)
+				     int required_lanes, bool force_disconnect)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	enum tc_port_mode old_tc_mode = dig_port->tc_mode;
@@ -572,7 +572,8 @@ static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port,
 	}
 
 	icl_tc_phy_disconnect(dig_port);
-	icl_tc_phy_connect(dig_port, required_lanes);
+	if (!force_disconnect)
+		icl_tc_phy_connect(dig_port, required_lanes);
 
 	drm_dbg_kms(&i915->drm, "Port %s: TC port mode reset (%s -> %s)\n",
 		    dig_port->tc_port_name,
@@ -662,7 +663,7 @@ bool intel_tc_port_connected(struct intel_encoder *encoder)
 }
 
 static void __intel_tc_port_lock(struct intel_digital_port *dig_port,
-				 int required_lanes)
+				 int required_lanes, bool force_disconnect)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	intel_wakeref_t wakeref;
@@ -676,8 +677,9 @@ static void __intel_tc_port_lock(struct intel_digital_port *dig_port,
 
 		tc_cold_wref = tc_cold_block(dig_port);
 
-		if (intel_tc_port_needs_reset(dig_port))
-			intel_tc_port_reset_mode(dig_port, required_lanes);
+		if (force_disconnect || intel_tc_port_needs_reset(dig_port))
+			intel_tc_port_reset_mode(dig_port, required_lanes,
+						 force_disconnect);
 
 		tc_cold_unblock(dig_port, tc_cold_wref);
 	}
@@ -688,7 +690,7 @@ static void __intel_tc_port_lock(struct intel_digital_port *dig_port,
 
 void intel_tc_port_lock(struct intel_digital_port *dig_port)
 {
-	__intel_tc_port_lock(dig_port, 1);
+	__intel_tc_port_lock(dig_port, 1, false);
 }
 
 void intel_tc_port_unlock(struct intel_digital_port *dig_port)
@@ -702,6 +704,24 @@ void intel_tc_port_unlock(struct intel_digital_port *dig_port)
 				      wakeref);
 }
 
+/**
+ * intel_tc_port_disconnect_phy: disconnect TypeC PHY from display port
+ * @dig_port: digital port
+ *
+ * Disconnect the given digital port from its TypeC PHY (handing back the
+ * control of the PHY to the TypeC subsystem). The only purpose of this
+ * function is to force the disconnect even with a TypeC display output still
+ * plugged to the TypeC connector, which is required by the TypeC firmwares
+ * during system suspend and shutdown. Otherwise - during the unplug event
+ * handling - the PHY ownership is released automatically by
+ * intel_tc_port_reset_mode(), when calling this function is not required.
+ */
+void intel_tc_port_disconnect_phy(struct intel_digital_port *dig_port)
+{
+	__intel_tc_port_lock(dig_port, 1, true);
+	intel_tc_port_unlock(dig_port);
+}
+
 bool intel_tc_port_ref_held(struct intel_digital_port *dig_port)
 {
 	return mutex_is_locked(&dig_port->tc_lock) ||
@@ -711,7 +731,7 @@ bool intel_tc_port_ref_held(struct intel_digital_port *dig_port)
 void intel_tc_port_get_link(struct intel_digital_port *dig_port,
 			    int required_lanes)
 {
-	__intel_tc_port_lock(dig_port, required_lanes);
+	__intel_tc_port_lock(dig_port, required_lanes, false);
 	dig_port->tc_link_refcount++;
 	intel_tc_port_unlock(dig_port);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 0eacbd76ec15..0c881f645e27 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -13,6 +13,8 @@ struct intel_digital_port;
 struct intel_encoder;
 
 bool intel_tc_port_connected(struct intel_encoder *encoder);
+void intel_tc_port_disconnect_phy(struct intel_digital_port *dig_port);
+
 u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port);
 u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port);
 int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port);
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index aa52af7891f0..d02f09f7e750 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -1420,7 +1420,7 @@ static void intel_tv_pre_enable(struct intel_atomic_state *state,
 				const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct intel_tv_connector_state *tv_conn_state =
 		to_intel_tv_connector_state(conn_state);
@@ -1466,7 +1466,7 @@ static void intel_tv_pre_enable(struct intel_atomic_state *state,
 		break;
 	}
 
-	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
+	tv_ctl |= TV_ENC_PIPE_SEL(crtc->pipe);
 
 	switch (tv_mode->oversample) {
 	case 8:
@@ -1571,8 +1571,7 @@ static int
 intel_tv_detect_type(struct intel_tv *intel_tv,
 		      struct drm_connector *connector)
 {
-	struct drm_crtc *crtc = connector->state->crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_crtc *crtc = to_intel_crtc(connector->state->crtc);
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tv_ctl, save_tv_ctl;
@@ -1594,7 +1593,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	/* Poll for TV detection */
 	tv_ctl &= ~(TV_ENC_ENABLE | TV_ENC_PIPE_SEL_MASK | TV_TEST_MODE_MASK);
 	tv_ctl |= TV_TEST_MODE_MONITOR_DETECT;
-	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
+	tv_ctl |= TV_ENC_PIPE_SEL(crtc->pipe);
 
 	tv_dac &= ~(TVDAC_SENSE_MASK | DAC_A_MASK | DAC_B_MASK | DAC_C_MASK);
 	tv_dac |= (TVDAC_STATE_CHG_EN |
@@ -1619,7 +1618,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	intel_de_write(dev_priv, TV_DAC, tv_dac);
 	intel_de_posting_read(dev_priv, TV_DAC);
 
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
+	intel_wait_for_vblank(dev_priv, crtc->pipe);
 
 	type = -1;
 	tv_dac = intel_de_read(dev_priv, TV_DAC);
@@ -1652,7 +1651,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	intel_de_posting_read(dev_priv, TV_CTL);
 
 	/* For unknown reasons the hw barfs if we don't do this vblank wait. */
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
+	intel_wait_for_vblank(dev_priv, crtc->pipe);
 
 	/* Restore interrupt config */
 	if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index dbe24d7e7375..330077c2e588 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -456,7 +456,7 @@ struct child_device_config {
 	u16 dp_gpio_pin_num;					/* 195 */
 	u8 dp_iboost_level:4;					/* 196 */
 	u8 hdmi_iboost_level:4;					/* 196 */
-	u8 dp_max_link_rate:3;					/* 216/230 CNL+ */
+	u8 dp_max_link_rate:3;					/* 216/230 GLK+ */
 	u8 dp_max_link_rate_reserved:5;				/* 216/230 */
 } __packed;
 
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 85749370508c..df3286aa6999 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -348,7 +348,10 @@ bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state)
 	if (DISPLAY_VER(i915) >= 12)
 		return true;
 
-	if ((DISPLAY_VER(i915) >= 11 || IS_CANNONLAKE(i915)) && (pipe != PIPE_A || (cpu_transcoder == TRANSCODER_EDP || cpu_transcoder == TRANSCODER_DSI_0 || cpu_transcoder == TRANSCODER_DSI_1)))
+	if (DISPLAY_VER(i915) >= 11 &&
+	    (pipe != PIPE_A || cpu_transcoder == TRANSCODER_EDP ||
+	     cpu_transcoder == TRANSCODER_DSI_0 ||
+	     cpu_transcoder == TRANSCODER_DSI_1))
 		return true;
 
 	return false;
diff --git a/drivers/gpu/drm/i915/display/intel_vga.c b/drivers/gpu/drm/i915/display/intel_vga.c
index f002b82ba9c0..fa779f7ea415 100644
--- a/drivers/gpu/drm/i915/display/intel_vga.c
+++ b/drivers/gpu/drm/i915/display/intel_vga.c
@@ -29,6 +29,9 @@ void intel_vga_disable(struct drm_i915_private *dev_priv)
 	i915_reg_t vga_reg = intel_vga_cntrl_reg(dev_priv);
 	u8 sr1;
 
+	if (intel_de_read(dev_priv, vga_reg) & VGA_DISP_DISABLE)
+		return;
+
 	/* WaEnableVGAAccessThroughIOPort:ctg,elk,ilk,snb,ivb,vlv,hsw */
 	vga_get_uninterruptible(pdev, VGA_RSRC_LEGACY_IO);
 	outb(SR01, VGA_SR_INDEX);
@@ -121,9 +124,9 @@ intel_vga_set_state(struct drm_i915_private *i915, bool enable_decode)
 }
 
 static unsigned int
-intel_vga_set_decode(void *cookie, bool enable_decode)
+intel_vga_set_decode(struct pci_dev *pdev, bool enable_decode)
 {
-	struct drm_i915_private *i915 = cookie;
+	struct drm_i915_private *i915 = pdev_to_i915(pdev);
 
 	intel_vga_set_state(i915, enable_decode);
 
@@ -136,6 +139,7 @@ intel_vga_set_decode(void *cookie, bool enable_decode)
 
 int intel_vga_register(struct drm_i915_private *i915)
 {
+
 	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
 	int ret;
 
@@ -147,7 +151,7 @@ int intel_vga_register(struct drm_i915_private *i915)
 	 * then we do not take part in VGA arbitration and the
 	 * vga_client_register() fails with -ENODEV.
 	 */
-	ret = vga_client_register(pdev, i915, NULL, intel_vga_set_decode);
+	ret = vga_client_register(pdev, intel_vga_set_decode);
 	if (ret && ret != -ENODEV)
 		return ret;
 
@@ -158,5 +162,5 @@ void intel_vga_unregister(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
 
-	vga_client_register(pdev, NULL, NULL, NULL);
+	vga_client_unregister(pdev);
 }
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 394b7bbf48d8..37eabeff8197 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -96,9 +96,8 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 {
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
 
@@ -141,7 +140,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 			drm_dbg_kms(&dev_priv->drm,
 				    "scaler_user index %u.%u: "
 				    "Staged freeing scaler id %d scaler_users = 0x%x\n",
-				    intel_crtc->pipe, scaler_user, *scaler_id,
+				    crtc->pipe, scaler_user, *scaler_id,
 				    scaler_state->scaler_users);
 			*scaler_id = -1;
 		}
@@ -167,7 +166,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		drm_dbg_kms(&dev_priv->drm,
 			    "scaler_user index %u.%u: src %ux%u dst %ux%u "
 			    "size is out of scaler range\n",
-			    intel_crtc->pipe, scaler_user, src_w, src_h,
+			    crtc->pipe, scaler_user, src_w, src_h,
 			    dst_w, dst_h);
 		return -EINVAL;
 	}
@@ -176,7 +175,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	scaler_state->scaler_users |= (1 << scaler_user);
 	drm_dbg_kms(&dev_priv->drm, "scaler_user index %u.%u: "
 		    "staged scaling request for %ux%u->%ux%u scaler_users = 0x%x\n",
-		    intel_crtc->pipe, scaler_user, src_w, src_h, dst_w, dst_h,
+		    crtc->pipe, scaler_user, src_w, src_h, dst_w, dst_h,
 		    scaler_state->scaler_users);
 
 	return 0;
@@ -295,12 +294,12 @@ int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static int cnl_coef_tap(int i)
+static int glk_coef_tap(int i)
 {
 	return i % 7;
 }
 
-static u16 cnl_nearest_filter_coef(int t)
+static u16 glk_nearest_filter_coef(int t)
 {
 	return t == 3 ? 0x0800 : 0x3000;
 }
@@ -342,29 +341,29 @@ static u16 cnl_nearest_filter_coef(int t)
  *
  */
 
-static void cnl_program_nearest_filter_coefs(struct drm_i915_private *dev_priv,
+static void glk_program_nearest_filter_coefs(struct drm_i915_private *dev_priv,
 					     enum pipe pipe, int id, int set)
 {
 	int i;
 
-	intel_de_write_fw(dev_priv, CNL_PS_COEF_INDEX_SET(pipe, id, set),
+	intel_de_write_fw(dev_priv, GLK_PS_COEF_INDEX_SET(pipe, id, set),
 			  PS_COEE_INDEX_AUTO_INC);
 
 	for (i = 0; i < 17 * 7; i += 2) {
 		u32 tmp;
 		int t;
 
-		t = cnl_coef_tap(i);
-		tmp = cnl_nearest_filter_coef(t);
+		t = glk_coef_tap(i);
+		tmp = glk_nearest_filter_coef(t);
 
-		t = cnl_coef_tap(i + 1);
-		tmp |= cnl_nearest_filter_coef(t) << 16;
+		t = glk_coef_tap(i + 1);
+		tmp |= glk_nearest_filter_coef(t) << 16;
 
-		intel_de_write_fw(dev_priv, CNL_PS_COEF_DATA_SET(pipe, id, set),
+		intel_de_write_fw(dev_priv, GLK_PS_COEF_DATA_SET(pipe, id, set),
 				  tmp);
 	}
 
-	intel_de_write_fw(dev_priv, CNL_PS_COEF_INDEX_SET(pipe, id, set), 0);
+	intel_de_write_fw(dev_priv, GLK_PS_COEF_INDEX_SET(pipe, id, set), 0);
 }
 
 static u32 skl_scaler_get_filter_select(enum drm_scaling_filter filter, int set)
@@ -387,7 +386,7 @@ static void skl_scaler_setup_filter(struct drm_i915_private *dev_priv, enum pipe
 	case DRM_SCALING_FILTER_DEFAULT:
 		break;
 	case DRM_SCALING_FILTER_NEAREST_NEIGHBOR:
-		cnl_program_nearest_filter_coefs(dev_priv, pipe, id, set);
+		glk_program_nearest_filter_coefs(dev_priv, pipe, id, set);
 		break;
 	default:
 		MISSING_CASE(filter);
@@ -515,17 +514,17 @@ skl_program_plane_scaler(struct intel_plane *plane,
 			  (crtc_w << 16) | crtc_h);
 }
 
-static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
+static void skl_detach_scaler(struct intel_crtc *crtc, int id)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
-	intel_de_write_fw(dev_priv, SKL_PS_CTRL(intel_crtc->pipe, id), 0);
-	intel_de_write_fw(dev_priv, SKL_PS_WIN_POS(intel_crtc->pipe, id), 0);
-	intel_de_write_fw(dev_priv, SKL_PS_WIN_SZ(intel_crtc->pipe, id), 0);
+	intel_de_write_fw(dev_priv, SKL_PS_CTRL(crtc->pipe, id), 0);
+	intel_de_write_fw(dev_priv, SKL_PS_WIN_POS(crtc->pipe, id), 0);
+	intel_de_write_fw(dev_priv, SKL_PS_WIN_SZ(crtc->pipe, id), 0);
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
@@ -535,15 +534,15 @@ static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
  */
 void skl_detach_scalers(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	int i;
 
 	/* loop through and disable scalers that aren't in use */
-	for (i = 0; i < intel_crtc->num_scalers; i++) {
+	for (i = 0; i < crtc->num_scalers; i++) {
 		if (!scaler_state->scalers[i].in_use)
-			skl_detach_scaler(intel_crtc, i);
+			skl_detach_scaler(crtc, i);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 92a4fd508e92..724e7b04f3b6 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -835,7 +835,7 @@ static u32 skl_plane_ctl_rotate(unsigned int rotate)
 	return 0;
 }
 
-static u32 cnl_plane_ctl_flip(unsigned int reflect)
+static u32 icl_plane_ctl_flip(unsigned int reflect)
 {
 	switch (reflect) {
 	case 0:
@@ -917,8 +917,8 @@ static u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 	plane_ctl |= skl_plane_ctl_tiling(fb->modifier);
 	plane_ctl |= skl_plane_ctl_rotate(rotation & DRM_MODE_ROTATE_MASK);
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
-		plane_ctl |= cnl_plane_ctl_flip(rotation &
+	if (DISPLAY_VER(dev_priv) >= 11)
+		plane_ctl |= icl_plane_ctl_flip(rotation &
 						DRM_MODE_REFLECT_MASK);
 
 	if (key->flags & I915_SET_COLORKEY_DESTINATION)
@@ -926,7 +926,7 @@ static u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 	else if (key->flags & I915_SET_COLORKEY_SOURCE)
 		plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE;
 
-	/* Wa_22012358565:adlp */
+	/* Wa_22012358565:adl-p */
 	if (DISPLAY_VER(dev_priv) == 13)
 		plane_ctl |= adlp_plane_ctl_arb_slots(plane_state);
 
@@ -1270,7 +1270,7 @@ static int skl_plane_check_dst_coordinates(const struct intel_crtc_state *crtc_s
 	int pipe_src_w = crtc_state->pipe_src_w;
 
 	/*
-	 * Display WA #1175: cnl,glk
+	 * Display WA #1175: glk
 	 * Planes other than the cursor may cause FIFO underflow and display
 	 * corruption if starting less than 4 pixels from the right edge of
 	 * the screen.
@@ -1828,7 +1828,7 @@ static bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 	if (plane_id == PLANE_CURSOR)
 		return false;
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		return true;
 
 	if (IS_GEMINILAKE(dev_priv))
@@ -1910,11 +1910,11 @@ static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv,
 {
 	/* Wa_14010477008:tgl[a0..c0],rkl[all],dg1[all] */
 	if (IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv) ||
-	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0))
+	    IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_D0))
 		return false;
 
 	/* Wa_22011186057 */
-	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0))
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 		return false;
 
 	return plane_id < PLANE_SPRITE4;
@@ -1938,7 +1938,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC:
 		/* Wa_22011186057 */
-		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0))
+		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 			return false;
 		break;
 	default:
@@ -1995,7 +1995,7 @@ static const u64 *gen12_get_plane_modifiers(struct drm_i915_private *dev_priv,
 					    enum plane_id plane_id)
 {
 	/* Wa_22011186057 */
-	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0))
+	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
 		return adlp_step_a_plane_format_modifiers;
 	else if (gen12_plane_supports_mc_ccs(dev_priv, plane_id))
 		return gen12_plane_format_modifiers_mc_ccs;
@@ -2144,7 +2144,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 			DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 |
 			DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270;
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		supported_rotations |= DRM_MODE_REFLECT_X;
 
 	drm_plane_create_rotation_property(&plane->base,
@@ -2174,12 +2174,12 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 	if (DISPLAY_VER(dev_priv) >= 12)
 		drm_plane_enable_fb_damage_clips(&plane->base);
 
-	if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv))
+	if (DISPLAY_VER(dev_priv) >= 11)
 		drm_plane_create_scaling_filter_property(&plane->base,
 						BIT(DRM_SCALING_FILTER_DEFAULT) |
 						BIT(DRM_SCALING_FILTER_NEAREST_NEIGHBOR));
 
-	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
+	intel_plane_helper_add(plane);
 
 	return plane;
 
@@ -2295,7 +2295,7 @@ skl_get_initial_plane_config(struct intel_crtc *crtc,
 		break;
 	}
 
-	if ((DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) && val & PLANE_CTL_FLIP_HORIZONTAL)
+	if (DISPLAY_VER(dev_priv) >= 11 && val & PLANE_CTL_FLIP_HORIZONTAL)
 		plane_config->rotation |= DRM_MODE_REFLECT_X;
 
 	/* 90/270 degree rotation would require extra work */
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 084c9c43b2ed..0ee4ff341e25 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -780,10 +780,9 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 				 const struct drm_connector_state *conn_state)
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	struct drm_crtc *crtc = pipe_config->uapi.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	enum port port;
 	u32 val;
 	bool glk_cold_boot = false;
@@ -1389,7 +1388,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
 	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	enum port port;
@@ -1397,7 +1396,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 	u32 val, tmp;
 	u16 mode_hdisplay;
 
-	drm_dbg_kms(&dev_priv->drm, "pipe %c\n", pipe_name(intel_crtc->pipe));
+	drm_dbg_kms(&dev_priv->drm, "pipe %c\n", pipe_name(crtc->pipe));
 
 	mode_hdisplay = adjusted_mode->crtc_hdisplay;
 
@@ -1424,7 +1423,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 			intel_de_write(dev_priv, MIPI_CTRL(port),
 				       tmp | READ_REQUEST_PRIORITY_HIGH);
 		} else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
-			enum pipe pipe = intel_crtc->pipe;
+			enum pipe pipe = crtc->pipe;
 
 			tmp = intel_de_read(dev_priv, MIPI_CTRL(port));
 			tmp &= ~BXT_PIPE_SELECT_MASK;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index daf9284ef1f5..f0435c6feb68 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -24,13 +24,11 @@ static void __do_clflush(struct drm_i915_gem_object *obj)
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
 }
 
-static int clflush_work(struct dma_fence_work *base)
+static void clflush_work(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
 
 	__do_clflush(clflush->obj);
-
-	return 0;
 }
 
 static void clflush_release(struct dma_fence_work *base)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
deleted file mode 100644
index 44821d94544f..000000000000
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ /dev/null
@@ -1,355 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include "i915_drv.h"
-#include "gt/intel_context.h"
-#include "gt/intel_engine_pm.h"
-#include "i915_gem_client_blt.h"
-#include "i915_gem_object_blt.h"
-
-struct i915_sleeve {
-	struct i915_vma *vma;
-	struct drm_i915_gem_object *obj;
-	struct sg_table *pages;
-	struct i915_page_sizes page_sizes;
-};
-
-static int vma_set_pages(struct i915_vma *vma)
-{
-	struct i915_sleeve *sleeve = vma->private;
-
-	vma->pages = sleeve->pages;
-	vma->page_sizes = sleeve->page_sizes;
-
-	return 0;
-}
-
-static void vma_clear_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(!vma->pages);
-	vma->pages = NULL;
-}
-
-static void vma_bind(struct i915_address_space *vm,
-		     struct i915_vm_pt_stash *stash,
-		     struct i915_vma *vma,
-		     enum i915_cache_level cache_level,
-		     u32 flags)
-{
-	vm->vma_ops.bind_vma(vm, stash, vma, cache_level, flags);
-}
-
-static void vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
-{
-	vm->vma_ops.unbind_vma(vm, vma);
-}
-
-static const struct i915_vma_ops proxy_vma_ops = {
-	.set_pages = vma_set_pages,
-	.clear_pages = vma_clear_pages,
-	.bind_vma = vma_bind,
-	.unbind_vma = vma_unbind,
-};
-
-static struct i915_sleeve *create_sleeve(struct i915_address_space *vm,
-					 struct drm_i915_gem_object *obj,
-					 struct sg_table *pages,
-					 struct i915_page_sizes *page_sizes)
-{
-	struct i915_sleeve *sleeve;
-	struct i915_vma *vma;
-	int err;
-
-	sleeve = kzalloc(sizeof(*sleeve), GFP_KERNEL);
-	if (!sleeve)
-		return ERR_PTR(-ENOMEM);
-
-	vma = i915_vma_instance(obj, vm, NULL);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err_free;
-	}
-
-	vma->private = sleeve;
-	vma->ops = &proxy_vma_ops;
-
-	sleeve->vma = vma;
-	sleeve->pages = pages;
-	sleeve->page_sizes = *page_sizes;
-
-	return sleeve;
-
-err_free:
-	kfree(sleeve);
-	return ERR_PTR(err);
-}
-
-static void destroy_sleeve(struct i915_sleeve *sleeve)
-{
-	kfree(sleeve);
-}
-
-struct clear_pages_work {
-	struct dma_fence dma;
-	struct dma_fence_cb cb;
-	struct i915_sw_fence wait;
-	struct work_struct work;
-	struct irq_work irq_work;
-	struct i915_sleeve *sleeve;
-	struct intel_context *ce;
-	u32 value;
-};
-
-static const char *clear_pages_work_driver_name(struct dma_fence *fence)
-{
-	return DRIVER_NAME;
-}
-
-static const char *clear_pages_work_timeline_name(struct dma_fence *fence)
-{
-	return "clear";
-}
-
-static void clear_pages_work_release(struct dma_fence *fence)
-{
-	struct clear_pages_work *w = container_of(fence, typeof(*w), dma);
-
-	destroy_sleeve(w->sleeve);
-
-	i915_sw_fence_fini(&w->wait);
-
-	BUILD_BUG_ON(offsetof(typeof(*w), dma));
-	dma_fence_free(&w->dma);
-}
-
-static const struct dma_fence_ops clear_pages_work_ops = {
-	.get_driver_name = clear_pages_work_driver_name,
-	.get_timeline_name = clear_pages_work_timeline_name,
-	.release = clear_pages_work_release,
-};
-
-static void clear_pages_signal_irq_worker(struct irq_work *work)
-{
-	struct clear_pages_work *w = container_of(work, typeof(*w), irq_work);
-
-	dma_fence_signal(&w->dma);
-	dma_fence_put(&w->dma);
-}
-
-static void clear_pages_dma_fence_cb(struct dma_fence *fence,
-				     struct dma_fence_cb *cb)
-{
-	struct clear_pages_work *w = container_of(cb, typeof(*w), cb);
-
-	if (fence->error)
-		dma_fence_set_error(&w->dma, fence->error);
-
-	/*
-	 * Push the signalling of the fence into yet another worker to avoid
-	 * the nightmare locking around the fence spinlock.
-	 */
-	irq_work_queue(&w->irq_work);
-}
-
-static void clear_pages_worker(struct work_struct *work)
-{
-	struct clear_pages_work *w = container_of(work, typeof(*w), work);
-	struct drm_i915_gem_object *obj = w->sleeve->vma->obj;
-	struct i915_vma *vma = w->sleeve->vma;
-	struct i915_gem_ww_ctx ww;
-	struct i915_request *rq;
-	struct i915_vma *batch;
-	int err = w->dma.error;
-
-	if (unlikely(err))
-		goto out_signal;
-
-	if (obj->cache_dirty) {
-		if (i915_gem_object_has_struct_page(obj))
-			drm_clflush_sg(w->sleeve->pages);
-		obj->cache_dirty = false;
-	}
-	obj->read_domains = I915_GEM_GPU_DOMAINS;
-	obj->write_domain = 0;
-
-	i915_gem_ww_ctx_init(&ww, false);
-	intel_engine_pm_get(w->ce->engine);
-retry:
-	err = intel_context_pin_ww(w->ce, &ww);
-	if (err)
-		goto out_signal;
-
-	batch = intel_emit_vma_fill_blt(w->ce, vma, &ww, w->value);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_ctx;
-	}
-
-	rq = i915_request_create(w->ce);
-	if (IS_ERR(rq)) {
-		err = PTR_ERR(rq);
-		goto out_batch;
-	}
-
-	/* There's no way the fence has signalled */
-	if (dma_fence_add_callback(&rq->fence, &w->cb,
-				   clear_pages_dma_fence_cb))
-		GEM_BUG_ON(1);
-
-	err = intel_emit_vma_mark_active(batch, rq);
-	if (unlikely(err))
-		goto out_request;
-
-	/*
-	 * w->dma is already exported via (vma|obj)->resv we need only
-	 * keep track of the GPU activity within this vma/request, and
-	 * propagate the signal from the request to w->dma.
-	 */
-	err = __i915_vma_move_to_active(vma, rq);
-	if (err)
-		goto out_request;
-
-	if (rq->engine->emit_init_breadcrumb) {
-		err = rq->engine->emit_init_breadcrumb(rq);
-		if (unlikely(err))
-			goto out_request;
-	}
-
-	err = rq->engine->emit_bb_start(rq,
-					batch->node.start, batch->node.size,
-					0);
-out_request:
-	if (unlikely(err)) {
-		i915_request_set_error_once(rq, err);
-		err = 0;
-	}
-
-	i915_request_add(rq);
-out_batch:
-	intel_emit_vma_release(w->ce, batch);
-out_ctx:
-	intel_context_unpin(w->ce);
-out_signal:
-	if (err == -EDEADLK) {
-		err = i915_gem_ww_ctx_backoff(&ww);
-		if (!err)
-			goto retry;
-	}
-	i915_gem_ww_ctx_fini(&ww);
-
-	i915_vma_unpin(w->sleeve->vma);
-	intel_engine_pm_put(w->ce->engine);
-
-	if (unlikely(err)) {
-		dma_fence_set_error(&w->dma, err);
-		dma_fence_signal(&w->dma);
-		dma_fence_put(&w->dma);
-	}
-}
-
-static int pin_wait_clear_pages_work(struct clear_pages_work *w,
-				     struct intel_context *ce)
-{
-	struct i915_vma *vma = w->sleeve->vma;
-	struct i915_gem_ww_ctx ww;
-	int err;
-
-	i915_gem_ww_ctx_init(&ww, false);
-retry:
-	err = i915_gem_object_lock(vma->obj, &ww);
-	if (err)
-		goto out;
-
-	err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out;
-
-	err = i915_sw_fence_await_reservation(&w->wait,
-					      vma->obj->base.resv, NULL,
-					      true, 0, I915_FENCE_GFP);
-	if (err)
-		goto err_unpin_vma;
-
-	dma_resv_add_excl_fence(vma->obj->base.resv, &w->dma);
-
-err_unpin_vma:
-	if (err)
-		i915_vma_unpin(vma);
-out:
-	if (err == -EDEADLK) {
-		err = i915_gem_ww_ctx_backoff(&ww);
-		if (!err)
-			goto retry;
-	}
-	i915_gem_ww_ctx_fini(&ww);
-	return err;
-}
-
-static int __i915_sw_fence_call
-clear_pages_work_notify(struct i915_sw_fence *fence,
-			enum i915_sw_fence_notify state)
-{
-	struct clear_pages_work *w = container_of(fence, typeof(*w), wait);
-
-	switch (state) {
-	case FENCE_COMPLETE:
-		schedule_work(&w->work);
-		break;
-
-	case FENCE_FREE:
-		dma_fence_put(&w->dma);
-		break;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static DEFINE_SPINLOCK(fence_lock);
-
-/* XXX: better name please */
-int i915_gem_schedule_fill_pages_blt(struct drm_i915_gem_object *obj,
-				     struct intel_context *ce,
-				     struct sg_table *pages,
-				     struct i915_page_sizes *page_sizes,
-				     u32 value)
-{
-	struct clear_pages_work *work;
-	struct i915_sleeve *sleeve;
-	int err;
-
-	sleeve = create_sleeve(ce->vm, obj, pages, page_sizes);
-	if (IS_ERR(sleeve))
-		return PTR_ERR(sleeve);
-
-	work = kmalloc(sizeof(*work), GFP_KERNEL);
-	if (!work) {
-		destroy_sleeve(sleeve);
-		return -ENOMEM;
-	}
-
-	work->value = value;
-	work->sleeve = sleeve;
-	work->ce = ce;
-
-	INIT_WORK(&work->work, clear_pages_worker);
-
-	init_irq_work(&work->irq_work, clear_pages_signal_irq_worker);
-
-	dma_fence_init(&work->dma, &clear_pages_work_ops, &fence_lock, 0, 0);
-	i915_sw_fence_init(&work->wait, clear_pages_work_notify);
-
-	err = pin_wait_clear_pages_work(work, ce);
-	if (err < 0)
-		dma_fence_set_error(&work->dma, err);
-
-	dma_fence_get(&work->dma);
-	i915_sw_fence_commit(&work->wait);
-
-	return err;
-}
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/i915_gem_client_blt.c"
-#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.h b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.h
deleted file mode 100644
index 3dbd28c22ff5..000000000000
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2019 Intel Corporation
- */
-#ifndef __I915_GEM_CLIENT_BLT_H__
-#define __I915_GEM_CLIENT_BLT_H__
-
-#include <linux/types.h>
-
-struct drm_i915_gem_object;
-struct i915_page_sizes;
-struct intel_context;
-struct sg_table;
-
-int i915_gem_schedule_fill_pages_blt(struct drm_i915_gem_object *obj,
-				     struct intel_context *ce,
-				     struct sg_table *pages,
-				     struct i915_page_sizes *page_sizes,
-				     u32 value);
-
-#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 7720b8c22c81..cff72679ad7c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -67,35 +67,32 @@
 #include <linux/log2.h>
 #include <linux/nospec.h>
 
+#include <drm/drm_syncobj.h>
+
 #include "gt/gen6_ppgtt.h"
 #include "gt/intel_context.h"
 #include "gt/intel_context_param.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_engine_user.h"
-#include "gt/intel_execlists_submission.h" /* virtual_engine */
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
 
 #include "i915_gem_context.h"
-#include "i915_globals.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
 
 #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
 
-static struct i915_global_gem_context {
-	struct i915_global base;
-	struct kmem_cache *slab_luts;
-} global;
+static struct kmem_cache *slab_luts;
 
 struct i915_lut_handle *i915_lut_handle_alloc(void)
 {
-	return kmem_cache_alloc(global.slab_luts, GFP_KERNEL);
+	return kmem_cache_alloc(slab_luts, GFP_KERNEL);
 }
 
 void i915_lut_handle_free(struct i915_lut_handle *lut)
 {
-	return kmem_cache_free(global.slab_luts, lut);
+	return kmem_cache_free(slab_luts, lut);
 }
 
 static void lut_close(struct i915_gem_context *ctx)
@@ -167,6 +164,577 @@ lookup_user_engine(struct i915_gem_context *ctx,
 	return i915_gem_context_get_engine(ctx, idx);
 }
 
+static int validate_priority(struct drm_i915_private *i915,
+			     const struct drm_i915_gem_context_param *args)
+{
+	s64 priority = args->value;
+
+	if (args->size)
+		return -EINVAL;
+
+	if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
+		return -ENODEV;
+
+	if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
+	    priority < I915_CONTEXT_MIN_USER_PRIORITY)
+		return -EINVAL;
+
+	if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
+	    !capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	return 0;
+}
+
+static void proto_context_close(struct i915_gem_proto_context *pc)
+{
+	int i;
+
+	if (pc->vm)
+		i915_vm_put(pc->vm);
+	if (pc->user_engines) {
+		for (i = 0; i < pc->num_user_engines; i++)
+			kfree(pc->user_engines[i].siblings);
+		kfree(pc->user_engines);
+	}
+	kfree(pc);
+}
+
+static int proto_context_set_persistence(struct drm_i915_private *i915,
+					 struct i915_gem_proto_context *pc,
+					 bool persist)
+{
+	if (persist) {
+		/*
+		 * Only contexts that are short-lived [that will expire or be
+		 * reset] are allowed to survive past termination. We require
+		 * hangcheck to ensure that the persistent requests are healthy.
+		 */
+		if (!i915->params.enable_hangcheck)
+			return -EINVAL;
+
+		pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
+	} else {
+		/* To cancel a context we use "preempt-to-idle" */
+		if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
+			return -ENODEV;
+
+		/*
+		 * If the cancel fails, we then need to reset, cleanly!
+		 *
+		 * If the per-engine reset fails, all hope is lost! We resort
+		 * to a full GPU reset in that unlikely case, but realistically
+		 * if the engine could not reset, the full reset does not fare
+		 * much better. The damage has been done.
+		 *
+		 * However, if we cannot reset an engine by itself, we cannot
+		 * cleanup a hanging persistent context without causing
+		 * colateral damage, and we should not pretend we can by
+		 * exposing the interface.
+		 */
+		if (!intel_has_reset_engine(&i915->gt))
+			return -ENODEV;
+
+		pc->user_flags &= ~BIT(UCONTEXT_PERSISTENCE);
+	}
+
+	return 0;
+}
+
+static struct i915_gem_proto_context *
+proto_context_create(struct drm_i915_private *i915, unsigned int flags)
+{
+	struct i915_gem_proto_context *pc, *err;
+
+	pc = kzalloc(sizeof(*pc), GFP_KERNEL);
+	if (!pc)
+		return ERR_PTR(-ENOMEM);
+
+	pc->num_user_engines = -1;
+	pc->user_engines = NULL;
+	pc->user_flags = BIT(UCONTEXT_BANNABLE) |
+			 BIT(UCONTEXT_RECOVERABLE);
+	if (i915->params.enable_hangcheck)
+		pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
+	pc->sched.priority = I915_PRIORITY_NORMAL;
+
+	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
+		if (!HAS_EXECLISTS(i915)) {
+			err = ERR_PTR(-EINVAL);
+			goto proto_close;
+		}
+		pc->single_timeline = true;
+	}
+
+	return pc;
+
+proto_close:
+	proto_context_close(pc);
+	return err;
+}
+
+static int proto_context_register_locked(struct drm_i915_file_private *fpriv,
+					 struct i915_gem_proto_context *pc,
+					 u32 *id)
+{
+	int ret;
+	void *old;
+
+	lockdep_assert_held(&fpriv->proto_context_lock);
+
+	ret = xa_alloc(&fpriv->context_xa, id, NULL, xa_limit_32b, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	old = xa_store(&fpriv->proto_context_xa, *id, pc, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		xa_erase(&fpriv->context_xa, *id);
+		return xa_err(old);
+	}
+	WARN_ON(old);
+
+	return 0;
+}
+
+static int proto_context_register(struct drm_i915_file_private *fpriv,
+				  struct i915_gem_proto_context *pc,
+				  u32 *id)
+{
+	int ret;
+
+	mutex_lock(&fpriv->proto_context_lock);
+	ret = proto_context_register_locked(fpriv, pc, id);
+	mutex_unlock(&fpriv->proto_context_lock);
+
+	return ret;
+}
+
+static int set_proto_ctx_vm(struct drm_i915_file_private *fpriv,
+			    struct i915_gem_proto_context *pc,
+			    const struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct i915_address_space *vm;
+
+	if (args->size)
+		return -EINVAL;
+
+	if (!HAS_FULL_PPGTT(i915))
+		return -ENODEV;
+
+	if (upper_32_bits(args->value))
+		return -ENOENT;
+
+	vm = i915_gem_vm_lookup(fpriv, args->value);
+	if (!vm)
+		return -ENOENT;
+
+	if (pc->vm)
+		i915_vm_put(pc->vm);
+	pc->vm = vm;
+
+	return 0;
+}
+
+struct set_proto_ctx_engines {
+	struct drm_i915_private *i915;
+	unsigned num_engines;
+	struct i915_gem_proto_engine *engines;
+};
+
+static int
+set_proto_ctx_engines_balance(struct i915_user_extension __user *base,
+			      void *data)
+{
+	struct i915_context_engines_load_balance __user *ext =
+		container_of_user(base, typeof(*ext), base);
+	const struct set_proto_ctx_engines *set = data;
+	struct drm_i915_private *i915 = set->i915;
+	struct intel_engine_cs **siblings;
+	u16 num_siblings, idx;
+	unsigned int n;
+	int err;
+
+	if (!HAS_EXECLISTS(i915))
+		return -ENODEV;
+
+	if (get_user(idx, &ext->engine_index))
+		return -EFAULT;
+
+	if (idx >= set->num_engines) {
+		drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
+			idx, set->num_engines);
+		return -EINVAL;
+	}
+
+	idx = array_index_nospec(idx, set->num_engines);
+	if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_INVALID) {
+		drm_dbg(&i915->drm,
+			"Invalid placement[%d], already occupied\n", idx);
+		return -EEXIST;
+	}
+
+	if (get_user(num_siblings, &ext->num_siblings))
+		return -EFAULT;
+
+	err = check_user_mbz(&ext->flags);
+	if (err)
+		return err;
+
+	err = check_user_mbz(&ext->mbz64);
+	if (err)
+		return err;
+
+	if (num_siblings == 0)
+		return 0;
+
+	siblings = kmalloc_array(num_siblings, sizeof(*siblings), GFP_KERNEL);
+	if (!siblings)
+		return -ENOMEM;
+
+	for (n = 0; n < num_siblings; n++) {
+		struct i915_engine_class_instance ci;
+
+		if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
+			err = -EFAULT;
+			goto err_siblings;
+		}
+
+		siblings[n] = intel_engine_lookup_user(i915,
+						       ci.engine_class,
+						       ci.engine_instance);
+		if (!siblings[n]) {
+			drm_dbg(&i915->drm,
+				"Invalid sibling[%d]: { class:%d, inst:%d }\n",
+				n, ci.engine_class, ci.engine_instance);
+			err = -EINVAL;
+			goto err_siblings;
+		}
+	}
+
+	if (num_siblings == 1) {
+		set->engines[idx].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
+		set->engines[idx].engine = siblings[0];
+		kfree(siblings);
+	} else {
+		set->engines[idx].type = I915_GEM_ENGINE_TYPE_BALANCED;
+		set->engines[idx].num_siblings = num_siblings;
+		set->engines[idx].siblings = siblings;
+	}
+
+	return 0;
+
+err_siblings:
+	kfree(siblings);
+
+	return err;
+}
+
+static int
+set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
+{
+	struct i915_context_engines_bond __user *ext =
+		container_of_user(base, typeof(*ext), base);
+	const struct set_proto_ctx_engines *set = data;
+	struct drm_i915_private *i915 = set->i915;
+	struct i915_engine_class_instance ci;
+	struct intel_engine_cs *master;
+	u16 idx, num_bonds;
+	int err, n;
+
+	if (get_user(idx, &ext->virtual_index))
+		return -EFAULT;
+
+	if (idx >= set->num_engines) {
+		drm_dbg(&i915->drm,
+			"Invalid index for virtual engine: %d >= %d\n",
+			idx, set->num_engines);
+		return -EINVAL;
+	}
+
+	idx = array_index_nospec(idx, set->num_engines);
+	if (set->engines[idx].type == I915_GEM_ENGINE_TYPE_INVALID) {
+		drm_dbg(&i915->drm, "Invalid engine at %d\n", idx);
+		return -EINVAL;
+	}
+
+	if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_PHYSICAL) {
+		drm_dbg(&i915->drm,
+			"Bonding with virtual engines not allowed\n");
+		return -EINVAL;
+	}
+
+	err = check_user_mbz(&ext->flags);
+	if (err)
+		return err;
+
+	for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
+		err = check_user_mbz(&ext->mbz64[n]);
+		if (err)
+			return err;
+	}
+
+	if (copy_from_user(&ci, &ext->master, sizeof(ci)))
+		return -EFAULT;
+
+	master = intel_engine_lookup_user(i915,
+					  ci.engine_class,
+					  ci.engine_instance);
+	if (!master) {
+		drm_dbg(&i915->drm,
+			"Unrecognised master engine: { class:%u, instance:%u }\n",
+			ci.engine_class, ci.engine_instance);
+		return -EINVAL;
+	}
+
+	if (intel_engine_uses_guc(master)) {
+		DRM_DEBUG("bonding extension not supported with GuC submission");
+		return -ENODEV;
+	}
+
+	if (get_user(num_bonds, &ext->num_bonds))
+		return -EFAULT;
+
+	for (n = 0; n < num_bonds; n++) {
+		struct intel_engine_cs *bond;
+
+		if (copy_from_user(&ci, &ext->engines[n], sizeof(ci)))
+			return -EFAULT;
+
+		bond = intel_engine_lookup_user(i915,
+						ci.engine_class,
+						ci.engine_instance);
+		if (!bond) {
+			drm_dbg(&i915->drm,
+				"Unrecognised engine[%d] for bonding: { class:%d, instance: %d }\n",
+				n, ci.engine_class, ci.engine_instance);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = {
+	[I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance,
+	[I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond,
+};
+
+static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
+			         struct i915_gem_proto_context *pc,
+			         const struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct set_proto_ctx_engines set = { .i915 = i915 };
+	struct i915_context_param_engines __user *user =
+		u64_to_user_ptr(args->value);
+	unsigned int n;
+	u64 extensions;
+	int err;
+
+	if (pc->num_user_engines >= 0) {
+		drm_dbg(&i915->drm, "Cannot set engines twice");
+		return -EINVAL;
+	}
+
+	if (args->size < sizeof(*user) ||
+	    !IS_ALIGNED(args->size - sizeof(*user), sizeof(*user->engines))) {
+		drm_dbg(&i915->drm, "Invalid size for engine array: %d\n",
+			args->size);
+		return -EINVAL;
+	}
+
+	set.num_engines = (args->size - sizeof(*user)) / sizeof(*user->engines);
+	/* RING_MASK has no shift so we can use it directly here */
+	if (set.num_engines > I915_EXEC_RING_MASK + 1)
+		return -EINVAL;
+
+	set.engines = kmalloc_array(set.num_engines, sizeof(*set.engines), GFP_KERNEL);
+	if (!set.engines)
+		return -ENOMEM;
+
+	for (n = 0; n < set.num_engines; n++) {
+		struct i915_engine_class_instance ci;
+		struct intel_engine_cs *engine;
+
+		if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) {
+			kfree(set.engines);
+			return -EFAULT;
+		}
+
+		memset(&set.engines[n], 0, sizeof(set.engines[n]));
+
+		if (ci.engine_class == (u16)I915_ENGINE_CLASS_INVALID &&
+		    ci.engine_instance == (u16)I915_ENGINE_CLASS_INVALID_NONE)
+			continue;
+
+		engine = intel_engine_lookup_user(i915,
+						  ci.engine_class,
+						  ci.engine_instance);
+		if (!engine) {
+			drm_dbg(&i915->drm,
+				"Invalid engine[%d]: { class:%d, instance:%d }\n",
+				n, ci.engine_class, ci.engine_instance);
+			kfree(set.engines);
+			return -ENOENT;
+		}
+
+		set.engines[n].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
+		set.engines[n].engine = engine;
+	}
+
+	err = -EFAULT;
+	if (!get_user(extensions, &user->extensions))
+		err = i915_user_extensions(u64_to_user_ptr(extensions),
+					   set_proto_ctx_engines_extensions,
+					   ARRAY_SIZE(set_proto_ctx_engines_extensions),
+					   &set);
+	if (err) {
+		kfree(set.engines);
+		return err;
+	}
+
+	pc->num_user_engines = set.num_engines;
+	pc->user_engines = set.engines;
+
+	return 0;
+}
+
+static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv,
+			      struct i915_gem_proto_context *pc,
+			      struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct drm_i915_gem_context_param_sseu user_sseu;
+	struct intel_sseu *sseu;
+	int ret;
+
+	if (args->size < sizeof(user_sseu))
+		return -EINVAL;
+
+	if (GRAPHICS_VER(i915) != 11)
+		return -ENODEV;
+
+	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+			   sizeof(user_sseu)))
+		return -EFAULT;
+
+	if (user_sseu.rsvd)
+		return -EINVAL;
+
+	if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
+		return -EINVAL;
+
+	if (!!(user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX) != (pc->num_user_engines >= 0))
+		return -EINVAL;
+
+	if (pc->num_user_engines >= 0) {
+		int idx = user_sseu.engine.engine_instance;
+		struct i915_gem_proto_engine *pe;
+
+		if (idx >= pc->num_user_engines)
+			return -EINVAL;
+
+		pe = &pc->user_engines[idx];
+
+		/* Only render engine supports RPCS configuration. */
+		if (pe->engine->class != RENDER_CLASS)
+			return -EINVAL;
+
+		sseu = &pe->sseu;
+	} else {
+		/* Only render engine supports RPCS configuration. */
+		if (user_sseu.engine.engine_class != I915_ENGINE_CLASS_RENDER)
+			return -EINVAL;
+
+		/* There is only one render engine */
+		if (user_sseu.engine.engine_instance != 0)
+			return -EINVAL;
+
+		sseu = &pc->legacy_rcs_sseu;
+	}
+
+	ret = i915_gem_user_to_context_sseu(&i915->gt, &user_sseu, sseu);
+	if (ret)
+		return ret;
+
+	args->size = sizeof(user_sseu);
+
+	return 0;
+}
+
+static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
+			       struct i915_gem_proto_context *pc,
+			       struct drm_i915_gem_context_param *args)
+{
+	int ret = 0;
+
+	switch (args->param) {
+	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		if (args->size)
+			ret = -EINVAL;
+		else if (args->value)
+			pc->user_flags |= BIT(UCONTEXT_NO_ERROR_CAPTURE);
+		else
+			pc->user_flags &= ~BIT(UCONTEXT_NO_ERROR_CAPTURE);
+		break;
+
+	case I915_CONTEXT_PARAM_BANNABLE:
+		if (args->size)
+			ret = -EINVAL;
+		else if (!capable(CAP_SYS_ADMIN) && !args->value)
+			ret = -EPERM;
+		else if (args->value)
+			pc->user_flags |= BIT(UCONTEXT_BANNABLE);
+		else
+			pc->user_flags &= ~BIT(UCONTEXT_BANNABLE);
+		break;
+
+	case I915_CONTEXT_PARAM_RECOVERABLE:
+		if (args->size)
+			ret = -EINVAL;
+		else if (args->value)
+			pc->user_flags |= BIT(UCONTEXT_RECOVERABLE);
+		else
+			pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE);
+		break;
+
+	case I915_CONTEXT_PARAM_PRIORITY:
+		ret = validate_priority(fpriv->dev_priv, args);
+		if (!ret)
+			pc->sched.priority = args->value;
+		break;
+
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = set_proto_ctx_sseu(fpriv, pc, args);
+		break;
+
+	case I915_CONTEXT_PARAM_VM:
+		ret = set_proto_ctx_vm(fpriv, pc, args);
+		break;
+
+	case I915_CONTEXT_PARAM_ENGINES:
+		ret = set_proto_ctx_engines(fpriv, pc, args);
+		break;
+
+	case I915_CONTEXT_PARAM_PERSISTENCE:
+		if (args->size)
+			ret = -EINVAL;
+		ret = proto_context_set_persistence(fpriv->dev_priv, pc,
+						    args->value);
+		break;
+
+	case I915_CONTEXT_PARAM_NO_ZEROMAP:
+	case I915_CONTEXT_PARAM_BAN_PERIOD:
+	case I915_CONTEXT_PARAM_RINGSIZE:
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static struct i915_address_space *
 context_get_vm_rcu(struct i915_gem_context *ctx)
 {
@@ -205,14 +773,16 @@ context_get_vm_rcu(struct i915_gem_context *ctx)
 	} while (1);
 }
 
-static void intel_context_set_gem(struct intel_context *ce,
-				  struct i915_gem_context *ctx)
+static int intel_context_set_gem(struct intel_context *ce,
+				 struct i915_gem_context *ctx,
+				 struct intel_sseu sseu)
 {
+	int ret = 0;
+
 	GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
 	RCU_INIT_POINTER(ce->gem_context, ctx);
 
-	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
-		ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring_size = SZ_16K;
 
 	if (rcu_access_pointer(ctx->vm)) {
 		struct i915_address_space *vm;
@@ -225,15 +795,23 @@ static void intel_context_set_gem(struct intel_context *ce,
 		ce->vm = vm;
 	}
 
-	GEM_BUG_ON(ce->timeline);
-	if (ctx->timeline)
-		ce->timeline = intel_timeline_get(ctx->timeline);
-
 	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
-	    intel_engine_has_timeslices(ce->engine))
+	    intel_engine_has_timeslices(ce->engine) &&
+	    intel_engine_has_semaphores(ce->engine))
 		__set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
 
-	intel_context_set_watchdog_us(ce, ctx->watchdog.timeout_us);
+	if (IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) &&
+	    ctx->i915->params.request_timeout_ms) {
+		unsigned int timeout_ms = ctx->i915->params.request_timeout_ms;
+
+		intel_context_set_watchdog_us(ce, (u64)timeout_ms * 1000);
+	}
+
+	/* A valid SSEU has no zero fields */
+	if (sseu.slice_mask && !WARN_ON(ce->engine->class != RENDER_CLASS))
+		ret = intel_context_reconfigure_sseu(ce, sseu);
+
+	return ret;
 }
 
 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
@@ -301,11 +879,12 @@ static struct i915_gem_engines *alloc_engines(unsigned int count)
 	return e;
 }
 
-static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
+static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
+						struct intel_sseu rcs_sseu)
 {
 	const struct intel_gt *gt = &ctx->i915->gt;
 	struct intel_engine_cs *engine;
-	struct i915_gem_engines *e;
+	struct i915_gem_engines *e, *err;
 	enum intel_engine_id id;
 
 	e = alloc_engines(I915_NUM_ENGINES);
@@ -314,6 +893,8 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
+		struct intel_sseu sseu = {};
+		int ret;
 
 		if (engine->legacy_idx == INVALID_ENGINE)
 			continue;
@@ -323,18 +904,79 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 
 		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
-			__free_engines(e, e->num_engines + 1);
-			return ERR_CAST(ce);
+			err = ERR_CAST(ce);
+			goto free_engines;
 		}
 
-		intel_context_set_gem(ce, ctx);
-
 		e->engines[engine->legacy_idx] = ce;
-		e->num_engines = max(e->num_engines, engine->legacy_idx);
+		e->num_engines = max(e->num_engines, engine->legacy_idx + 1);
+
+		if (engine->class == RENDER_CLASS)
+			sseu = rcs_sseu;
+
+		ret = intel_context_set_gem(ce, ctx, sseu);
+		if (ret) {
+			err = ERR_PTR(ret);
+			goto free_engines;
+		}
+
+	}
+
+	return e;
+
+free_engines:
+	free_engines(e);
+	return err;
+}
+
+static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
+					     unsigned int num_engines,
+					     struct i915_gem_proto_engine *pe)
+{
+	struct i915_gem_engines *e, *err;
+	unsigned int n;
+
+	e = alloc_engines(num_engines);
+	for (n = 0; n < num_engines; n++) {
+		struct intel_context *ce;
+		int ret;
+
+		switch (pe[n].type) {
+		case I915_GEM_ENGINE_TYPE_PHYSICAL:
+			ce = intel_context_create(pe[n].engine);
+			break;
+
+		case I915_GEM_ENGINE_TYPE_BALANCED:
+			ce = intel_engine_create_virtual(pe[n].siblings,
+							 pe[n].num_siblings);
+			break;
+
+		case I915_GEM_ENGINE_TYPE_INVALID:
+		default:
+			GEM_WARN_ON(pe[n].type != I915_GEM_ENGINE_TYPE_INVALID);
+			continue;
+		}
+
+		if (IS_ERR(ce)) {
+			err = ERR_CAST(ce);
+			goto free_engines;
+		}
+
+		e->engines[n] = ce;
+
+		ret = intel_context_set_gem(ce, ctx, pe->sseu);
+		if (ret) {
+			err = ERR_PTR(ret);
+			goto free_engines;
+		}
 	}
-	e->num_engines++;
+	e->num_engines = num_engines;
 
 	return e;
+
+free_engines:
+	free_engines(e);
+	return err;
 }
 
 void i915_gem_context_release(struct kref *ref)
@@ -347,9 +989,6 @@ void i915_gem_context_release(struct kref *ref)
 	mutex_destroy(&ctx->engines_mutex);
 	mutex_destroy(&ctx->lut_mutex);
 
-	if (ctx->timeline)
-		intel_timeline_put(ctx->timeline);
-
 	put_pid(ctx->pid);
 	mutex_destroy(&ctx->mutex);
 
@@ -441,7 +1080,7 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
 	for_each_gem_engine(ce, engines, it) {
 		struct intel_engine_cs *engine;
 
-		if (ban && intel_context_set_banned(ce))
+		if (ban && intel_context_ban(ce, NULL))
 			continue;
 
 		/*
@@ -566,6 +1205,9 @@ static void context_close(struct i915_gem_context *ctx)
 	if (vm)
 		i915_vm_close(vm);
 
+	if (ctx->syncobj)
+		drm_syncobj_put(ctx->syncobj);
+
 	ctx->file_priv = ERR_PTR(-EBADF);
 
 	/*
@@ -635,57 +1277,6 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
 	return 0;
 }
 
-static struct i915_gem_context *
-__create_context(struct drm_i915_private *i915)
-{
-	struct i915_gem_context *ctx;
-	struct i915_gem_engines *e;
-	int err;
-	int i;
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx)
-		return ERR_PTR(-ENOMEM);
-
-	kref_init(&ctx->ref);
-	ctx->i915 = i915;
-	ctx->sched.priority = I915_PRIORITY_NORMAL;
-	mutex_init(&ctx->mutex);
-	INIT_LIST_HEAD(&ctx->link);
-
-	spin_lock_init(&ctx->stale.lock);
-	INIT_LIST_HEAD(&ctx->stale.engines);
-
-	mutex_init(&ctx->engines_mutex);
-	e = default_engines(ctx);
-	if (IS_ERR(e)) {
-		err = PTR_ERR(e);
-		goto err_free;
-	}
-	RCU_INIT_POINTER(ctx->engines, e);
-
-	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
-	mutex_init(&ctx->lut_mutex);
-
-	/* NB: Mark all slices as needing a remap so that when the context first
-	 * loads it will restore whatever remap state already exists. If there
-	 * is no remap info, it will be a NOP. */
-	ctx->remap_slice = ALL_L3_SLICES(i915);
-
-	i915_gem_context_set_bannable(ctx);
-	i915_gem_context_set_recoverable(ctx);
-	__context_set_persistence(ctx, true /* cgroup hook? */);
-
-	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
-		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
-
-	return ctx;
-
-err_free:
-	kfree(ctx);
-	return ERR_PTR(err);
-}
-
 static inline struct i915_gem_engines *
 __context_engines_await(const struct i915_gem_context *ctx,
 			bool *user_engines)
@@ -714,168 +1305,112 @@ __context_engines_await(const struct i915_gem_context *ctx,
 	return engines;
 }
 
-static int
+static void
 context_apply_all(struct i915_gem_context *ctx,
-		  int (*fn)(struct intel_context *ce, void *data),
+		  void (*fn)(struct intel_context *ce, void *data),
 		  void *data)
 {
 	struct i915_gem_engines_iter it;
 	struct i915_gem_engines *e;
 	struct intel_context *ce;
-	int err = 0;
 
 	e = __context_engines_await(ctx, NULL);
-	for_each_gem_engine(ce, e, it) {
-		err = fn(ce, data);
-		if (err)
-			break;
-	}
+	for_each_gem_engine(ce, e, it)
+		fn(ce, data);
 	i915_sw_fence_complete(&e->fence);
-
-	return err;
-}
-
-static int __apply_ppgtt(struct intel_context *ce, void *vm)
-{
-	i915_vm_put(ce->vm);
-	ce->vm = i915_vm_get(vm);
-	return 0;
-}
-
-static struct i915_address_space *
-__set_ppgtt(struct i915_gem_context *ctx, struct i915_address_space *vm)
-{
-	struct i915_address_space *old;
-
-	old = rcu_replace_pointer(ctx->vm,
-				  i915_vm_open(vm),
-				  lockdep_is_held(&ctx->mutex));
-	GEM_BUG_ON(old && i915_vm_is_4lvl(vm) != i915_vm_is_4lvl(old));
-
-	context_apply_all(ctx, __apply_ppgtt, vm);
-
-	return old;
-}
-
-static void __assign_ppgtt(struct i915_gem_context *ctx,
-			   struct i915_address_space *vm)
-{
-	if (vm == rcu_access_pointer(ctx->vm))
-		return;
-
-	vm = __set_ppgtt(ctx, vm);
-	if (vm)
-		i915_vm_close(vm);
-}
-
-static void __set_timeline(struct intel_timeline **dst,
-			   struct intel_timeline *src)
-{
-	struct intel_timeline *old = *dst;
-
-	*dst = src ? intel_timeline_get(src) : NULL;
-
-	if (old)
-		intel_timeline_put(old);
-}
-
-static int __apply_timeline(struct intel_context *ce, void *timeline)
-{
-	__set_timeline(&ce->timeline, timeline);
-	return 0;
-}
-
-static void __assign_timeline(struct i915_gem_context *ctx,
-			      struct intel_timeline *timeline)
-{
-	__set_timeline(&ctx->timeline, timeline);
-	context_apply_all(ctx, __apply_timeline, timeline);
-}
-
-static int __apply_watchdog(struct intel_context *ce, void *timeout_us)
-{
-	return intel_context_set_watchdog_us(ce, (uintptr_t)timeout_us);
-}
-
-static int
-__set_watchdog(struct i915_gem_context *ctx, unsigned long timeout_us)
-{
-	int ret;
-
-	ret = context_apply_all(ctx, __apply_watchdog,
-				(void *)(uintptr_t)timeout_us);
-	if (!ret)
-		ctx->watchdog.timeout_us = timeout_us;
-
-	return ret;
-}
-
-static void __set_default_fence_expiry(struct i915_gem_context *ctx)
-{
-	struct drm_i915_private *i915 = ctx->i915;
-	int ret;
-
-	if (!IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) ||
-	    !i915->params.request_timeout_ms)
-		return;
-
-	/* Default expiry for user fences. */
-	ret = __set_watchdog(ctx, i915->params.request_timeout_ms * 1000);
-	if (ret)
-		drm_notice(&i915->drm,
-			   "Failed to configure default fence expiry! (%d)",
-			   ret);
 }
 
 static struct i915_gem_context *
-i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
+i915_gem_create_context(struct drm_i915_private *i915,
+			const struct i915_gem_proto_context *pc)
 {
 	struct i915_gem_context *ctx;
+	struct i915_address_space *vm = NULL;
+	struct i915_gem_engines *e;
+	int err;
+	int i;
 
-	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE &&
-	    !HAS_EXECLISTS(i915))
-		return ERR_PTR(-EINVAL);
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
 
-	ctx = __create_context(i915);
-	if (IS_ERR(ctx))
-		return ctx;
+	kref_init(&ctx->ref);
+	ctx->i915 = i915;
+	ctx->sched = pc->sched;
+	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->link);
 
-	if (HAS_FULL_PPGTT(i915)) {
+	spin_lock_init(&ctx->stale.lock);
+	INIT_LIST_HEAD(&ctx->stale.engines);
+
+	if (pc->vm) {
+		vm = i915_vm_get(pc->vm);
+	} else if (HAS_FULL_PPGTT(i915)) {
 		struct i915_ppgtt *ppgtt;
 
 		ppgtt = i915_ppgtt_create(&i915->gt);
 		if (IS_ERR(ppgtt)) {
 			drm_dbg(&i915->drm, "PPGTT setup failed (%ld)\n",
 				PTR_ERR(ppgtt));
-			context_close(ctx);
-			return ERR_CAST(ppgtt);
+			err = PTR_ERR(ppgtt);
+			goto err_ctx;
 		}
+		vm = &ppgtt->vm;
+	}
+	if (vm) {
+		RCU_INIT_POINTER(ctx->vm, i915_vm_open(vm));
 
-		mutex_lock(&ctx->mutex);
-		__assign_ppgtt(ctx, &ppgtt->vm);
-		mutex_unlock(&ctx->mutex);
+		/* i915_vm_open() takes a reference */
+		i915_vm_put(vm);
+	}
 
-		i915_vm_put(&ppgtt->vm);
+	mutex_init(&ctx->engines_mutex);
+	if (pc->num_user_engines >= 0) {
+		i915_gem_context_set_user_engines(ctx);
+		e = user_engines(ctx, pc->num_user_engines, pc->user_engines);
+	} else {
+		i915_gem_context_clear_user_engines(ctx);
+		e = default_engines(ctx, pc->legacy_rcs_sseu);
+	}
+	if (IS_ERR(e)) {
+		err = PTR_ERR(e);
+		goto err_vm;
 	}
+	RCU_INIT_POINTER(ctx->engines, e);
 
-	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
-		struct intel_timeline *timeline;
+	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
+	mutex_init(&ctx->lut_mutex);
 
-		timeline = intel_timeline_create(&i915->gt);
-		if (IS_ERR(timeline)) {
-			context_close(ctx);
-			return ERR_CAST(timeline);
-		}
+	/* NB: Mark all slices as needing a remap so that when the context first
+	 * loads it will restore whatever remap state already exists. If there
+	 * is no remap info, it will be a NOP. */
+	ctx->remap_slice = ALL_L3_SLICES(i915);
 
-		__assign_timeline(ctx, timeline);
-		intel_timeline_put(timeline);
-	}
+	ctx->user_flags = pc->user_flags;
 
-	__set_default_fence_expiry(ctx);
+	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
+		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
+
+	if (pc->single_timeline) {
+		err = drm_syncobj_create(&ctx->syncobj,
+					 DRM_SYNCOBJ_CREATE_SIGNALED,
+					 NULL);
+		if (err)
+			goto err_engines;
+	}
 
 	trace_i915_context_create(ctx);
 
 	return ctx;
+
+err_engines:
+	free_engines(e);
+err_vm:
+	if (ctx->vm)
+		i915_vm_close(ctx->vm);
+err_ctx:
+	kfree(ctx);
+	return ERR_PTR(err);
 }
 
 static void init_contexts(struct i915_gem_contexts *gc)
@@ -889,83 +1424,83 @@ void i915_gem_init__contexts(struct drm_i915_private *i915)
 	init_contexts(&i915->gem.contexts);
 }
 
-static int gem_context_register(struct i915_gem_context *ctx,
-				struct drm_i915_file_private *fpriv,
-				u32 *id)
+static void gem_context_register(struct i915_gem_context *ctx,
+				 struct drm_i915_file_private *fpriv,
+				 u32 id)
 {
 	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_address_space *vm;
-	int ret;
+	void *old;
 
 	ctx->file_priv = fpriv;
 
-	mutex_lock(&ctx->mutex);
-	vm = i915_gem_context_vm(ctx);
-	if (vm)
-		WRITE_ONCE(vm->file, fpriv); /* XXX */
-	mutex_unlock(&ctx->mutex);
-
 	ctx->pid = get_task_pid(current, PIDTYPE_PID);
 	snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
 		 current->comm, pid_nr(ctx->pid));
 
 	/* And finally expose ourselves to userspace via the idr */
-	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
-	if (ret)
-		goto err_pid;
+	old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
+	WARN_ON(old);
 
 	spin_lock(&i915->gem.contexts.lock);
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
-
-	return 0;
-
-err_pid:
-	put_pid(fetch_and_zero(&ctx->pid));
-	return ret;
 }
 
 int i915_gem_context_open(struct drm_i915_private *i915,
 			  struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct i915_gem_proto_context *pc;
 	struct i915_gem_context *ctx;
 	int err;
-	u32 id;
 
-	xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC);
+	mutex_init(&file_priv->proto_context_lock);
+	xa_init_flags(&file_priv->proto_context_xa, XA_FLAGS_ALLOC);
+
+	/* 0 reserved for the default context */
+	xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC1);
 
 	/* 0 reserved for invalid/unassigned ppgtt */
 	xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
 
-	ctx = i915_gem_create_context(i915, 0);
+	pc = proto_context_create(i915, 0);
+	if (IS_ERR(pc)) {
+		err = PTR_ERR(pc);
+		goto err;
+	}
+
+	ctx = i915_gem_create_context(i915, pc);
+	proto_context_close(pc);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err;
 	}
 
-	err = gem_context_register(ctx, file_priv, &id);
-	if (err < 0)
-		goto err_ctx;
+	gem_context_register(ctx, file_priv, 0);
 
-	GEM_BUG_ON(id);
 	return 0;
 
-err_ctx:
-	context_close(ctx);
 err:
 	xa_destroy(&file_priv->vm_xa);
 	xa_destroy(&file_priv->context_xa);
+	xa_destroy(&file_priv->proto_context_xa);
+	mutex_destroy(&file_priv->proto_context_lock);
 	return err;
 }
 
 void i915_gem_context_close(struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct i915_gem_proto_context *pc;
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	unsigned long idx;
 
+	xa_for_each(&file_priv->proto_context_xa, idx, pc)
+		proto_context_close(pc);
+	xa_destroy(&file_priv->proto_context_xa);
+	mutex_destroy(&file_priv->proto_context_lock);
+
 	xa_for_each(&file_priv->context_xa, idx, ctx)
 		context_close(ctx);
 	xa_destroy(&file_priv->context_xa);
@@ -995,8 +1530,6 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
-	ppgtt->vm.file = file_priv;
-
 	if (args->extensions) {
 		err = i915_user_extensions(u64_to_user_ptr(args->extensions),
 					   NULL, 0,
@@ -1040,120 +1573,6 @@ int i915_gem_vm_destroy_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-struct context_barrier_task {
-	struct i915_active base;
-	void (*task)(void *data);
-	void *data;
-};
-
-static void cb_retire(struct i915_active *base)
-{
-	struct context_barrier_task *cb = container_of(base, typeof(*cb), base);
-
-	if (cb->task)
-		cb->task(cb->data);
-
-	i915_active_fini(&cb->base);
-	kfree(cb);
-}
-
-I915_SELFTEST_DECLARE(static intel_engine_mask_t context_barrier_inject_fault);
-static int context_barrier_task(struct i915_gem_context *ctx,
-				intel_engine_mask_t engines,
-				bool (*skip)(struct intel_context *ce, void *data),
-				int (*pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void *data),
-				int (*emit)(struct i915_request *rq, void *data),
-				void (*task)(void *data),
-				void *data)
-{
-	struct context_barrier_task *cb;
-	struct i915_gem_engines_iter it;
-	struct i915_gem_engines *e;
-	struct i915_gem_ww_ctx ww;
-	struct intel_context *ce;
-	int err = 0;
-
-	GEM_BUG_ON(!task);
-
-	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
-	if (!cb)
-		return -ENOMEM;
-
-	i915_active_init(&cb->base, NULL, cb_retire, 0);
-	err = i915_active_acquire(&cb->base);
-	if (err) {
-		kfree(cb);
-		return err;
-	}
-
-	e = __context_engines_await(ctx, NULL);
-	if (!e) {
-		i915_active_release(&cb->base);
-		return -ENOENT;
-	}
-
-	for_each_gem_engine(ce, e, it) {
-		struct i915_request *rq;
-
-		if (I915_SELFTEST_ONLY(context_barrier_inject_fault &
-				       ce->engine->mask)) {
-			err = -ENXIO;
-			break;
-		}
-
-		if (!(ce->engine->mask & engines))
-			continue;
-
-		if (skip && skip(ce, data))
-			continue;
-
-		i915_gem_ww_ctx_init(&ww, true);
-retry:
-		err = intel_context_pin_ww(ce, &ww);
-		if (err)
-			goto err;
-
-		if (pin)
-			err = pin(ce, &ww, data);
-		if (err)
-			goto err_unpin;
-
-		rq = i915_request_create(ce);
-		if (IS_ERR(rq)) {
-			err = PTR_ERR(rq);
-			goto err_unpin;
-		}
-
-		err = 0;
-		if (emit)
-			err = emit(rq, data);
-		if (err == 0)
-			err = i915_active_add_request(&cb->base, rq);
-
-		i915_request_add(rq);
-err_unpin:
-		intel_context_unpin(ce);
-err:
-		if (err == -EDEADLK) {
-			err = i915_gem_ww_ctx_backoff(&ww);
-			if (!err)
-				goto retry;
-		}
-		i915_gem_ww_ctx_fini(&ww);
-
-		if (err)
-			break;
-	}
-	i915_sw_fence_complete(&e->fence);
-
-	cb->task = err ? NULL : task; /* caller needs to unwind instead */
-	cb->data = data;
-
-	i915_active_release(&cb->base);
-
-	return err;
-}
-
 static int get_ppgtt(struct drm_i915_file_private *file_priv,
 		     struct i915_gem_context *ctx,
 		     struct drm_i915_gem_context_param *args)
@@ -1186,211 +1605,6 @@ err_put:
 	return err;
 }
 
-static void set_ppgtt_barrier(void *data)
-{
-	struct i915_address_space *old = data;
-
-	if (GRAPHICS_VER(old->i915) < 8)
-		gen6_ppgtt_unpin_all(i915_vm_to_ppgtt(old));
-
-	i915_vm_close(old);
-}
-
-static int pin_ppgtt_update(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void *data)
-{
-	struct i915_address_space *vm = ce->vm;
-
-	if (!HAS_LOGICAL_RING_CONTEXTS(vm->i915))
-		/* ppGTT is not part of the legacy context image */
-		return gen6_ppgtt_pin(i915_vm_to_ppgtt(vm), ww);
-
-	return 0;
-}
-
-static int emit_ppgtt_update(struct i915_request *rq, void *data)
-{
-	struct i915_address_space *vm = rq->context->vm;
-	struct intel_engine_cs *engine = rq->engine;
-	u32 base = engine->mmio_base;
-	u32 *cs;
-	int i;
-
-	if (i915_vm_is_4lvl(vm)) {
-		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-		const dma_addr_t pd_daddr = px_dma(ppgtt->pd);
-
-		cs = intel_ring_begin(rq, 6);
-		if (IS_ERR(cs))
-			return PTR_ERR(cs);
-
-		*cs++ = MI_LOAD_REGISTER_IMM(2);
-
-		*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0));
-		*cs++ = upper_32_bits(pd_daddr);
-		*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 0));
-		*cs++ = lower_32_bits(pd_daddr);
-
-		*cs++ = MI_NOOP;
-		intel_ring_advance(rq, cs);
-	} else if (HAS_LOGICAL_RING_CONTEXTS(engine->i915)) {
-		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-		int err;
-
-		/* Magic required to prevent forcewake errors! */
-		err = engine->emit_flush(rq, EMIT_INVALIDATE);
-		if (err)
-			return err;
-
-		cs = intel_ring_begin(rq, 4 * GEN8_3LVL_PDPES + 2);
-		if (IS_ERR(cs))
-			return PTR_ERR(cs);
-
-		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED;
-		for (i = GEN8_3LVL_PDPES; i--; ) {
-			const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
-
-			*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i));
-			*cs++ = upper_32_bits(pd_daddr);
-			*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i));
-			*cs++ = lower_32_bits(pd_daddr);
-		}
-		*cs++ = MI_NOOP;
-		intel_ring_advance(rq, cs);
-	}
-
-	return 0;
-}
-
-static bool skip_ppgtt_update(struct intel_context *ce, void *data)
-{
-	if (HAS_LOGICAL_RING_CONTEXTS(ce->engine->i915))
-		return !ce->state;
-	else
-		return !atomic_read(&ce->pin_count);
-}
-
-static int set_ppgtt(struct drm_i915_file_private *file_priv,
-		     struct i915_gem_context *ctx,
-		     struct drm_i915_gem_context_param *args)
-{
-	struct i915_address_space *vm, *old;
-	int err;
-
-	if (args->size)
-		return -EINVAL;
-
-	if (!rcu_access_pointer(ctx->vm))
-		return -ENODEV;
-
-	if (upper_32_bits(args->value))
-		return -ENOENT;
-
-	rcu_read_lock();
-	vm = xa_load(&file_priv->vm_xa, args->value);
-	if (vm && !kref_get_unless_zero(&vm->ref))
-		vm = NULL;
-	rcu_read_unlock();
-	if (!vm)
-		return -ENOENT;
-
-	err = mutex_lock_interruptible(&ctx->mutex);
-	if (err)
-		goto out;
-
-	if (i915_gem_context_is_closed(ctx)) {
-		err = -ENOENT;
-		goto unlock;
-	}
-
-	if (vm == rcu_access_pointer(ctx->vm))
-		goto unlock;
-
-	old = __set_ppgtt(ctx, vm);
-
-	/* Teardown the existing obj:vma cache, it will have to be rebuilt. */
-	lut_close(ctx);
-
-	/*
-	 * We need to flush any requests using the current ppgtt before
-	 * we release it as the requests do not hold a reference themselves,
-	 * only indirectly through the context.
-	 */
-	err = context_barrier_task(ctx, ALL_ENGINES,
-				   skip_ppgtt_update,
-				   pin_ppgtt_update,
-				   emit_ppgtt_update,
-				   set_ppgtt_barrier,
-				   old);
-	if (err) {
-		i915_vm_close(__set_ppgtt(ctx, old));
-		i915_vm_close(old);
-		lut_close(ctx); /* force a rebuild of the old obj:vma cache */
-	}
-
-unlock:
-	mutex_unlock(&ctx->mutex);
-out:
-	i915_vm_put(vm);
-	return err;
-}
-
-static int __apply_ringsize(struct intel_context *ce, void *sz)
-{
-	return intel_context_set_ring_size(ce, (unsigned long)sz);
-}
-
-static int set_ringsize(struct i915_gem_context *ctx,
-			struct drm_i915_gem_context_param *args)
-{
-	if (!HAS_LOGICAL_RING_CONTEXTS(ctx->i915))
-		return -ENODEV;
-
-	if (args->size)
-		return -EINVAL;
-
-	if (!IS_ALIGNED(args->value, I915_GTT_PAGE_SIZE))
-		return -EINVAL;
-
-	if (args->value < I915_GTT_PAGE_SIZE)
-		return -EINVAL;
-
-	if (args->value > 128 * I915_GTT_PAGE_SIZE)
-		return -EINVAL;
-
-	return context_apply_all(ctx,
-				 __apply_ringsize,
-				 __intel_context_ring_size(args->value));
-}
-
-static int __get_ringsize(struct intel_context *ce, void *arg)
-{
-	long sz;
-
-	sz = intel_context_get_ring_size(ce);
-	GEM_BUG_ON(sz > INT_MAX);
-
-	return sz; /* stop on first engine */
-}
-
-static int get_ringsize(struct i915_gem_context *ctx,
-			struct drm_i915_gem_context_param *args)
-{
-	int sz;
-
-	if (!HAS_LOGICAL_RING_CONTEXTS(ctx->i915))
-		return -ENODEV;
-
-	if (args->size)
-		return -EINVAL;
-
-	sz = context_apply_all(ctx, __get_ringsize, NULL);
-	if (sz < 0)
-		return sz;
-
-	args->value = sz;
-	return 0;
-}
-
 int
 i915_gem_user_to_context_sseu(struct intel_gt *gt,
 			      const struct drm_i915_gem_context_param_sseu *user,
@@ -1545,382 +1759,6 @@ out_ce:
 	return ret;
 }
 
-struct set_engines {
-	struct i915_gem_context *ctx;
-	struct i915_gem_engines *engines;
-};
-
-static int
-set_engines__load_balance(struct i915_user_extension __user *base, void *data)
-{
-	struct i915_context_engines_load_balance __user *ext =
-		container_of_user(base, typeof(*ext), base);
-	const struct set_engines *set = data;
-	struct drm_i915_private *i915 = set->ctx->i915;
-	struct intel_engine_cs *stack[16];
-	struct intel_engine_cs **siblings;
-	struct intel_context *ce;
-	u16 num_siblings, idx;
-	unsigned int n;
-	int err;
-
-	if (!HAS_EXECLISTS(i915))
-		return -ENODEV;
-
-	if (intel_uc_uses_guc_submission(&i915->gt.uc))
-		return -ENODEV; /* not implement yet */
-
-	if (get_user(idx, &ext->engine_index))
-		return -EFAULT;
-
-	if (idx >= set->engines->num_engines) {
-		drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
-			idx, set->engines->num_engines);
-		return -EINVAL;
-	}
-
-	idx = array_index_nospec(idx, set->engines->num_engines);
-	if (set->engines->engines[idx]) {
-		drm_dbg(&i915->drm,
-			"Invalid placement[%d], already occupied\n", idx);
-		return -EEXIST;
-	}
-
-	if (get_user(num_siblings, &ext->num_siblings))
-		return -EFAULT;
-
-	err = check_user_mbz(&ext->flags);
-	if (err)
-		return err;
-
-	err = check_user_mbz(&ext->mbz64);
-	if (err)
-		return err;
-
-	siblings = stack;
-	if (num_siblings > ARRAY_SIZE(stack)) {
-		siblings = kmalloc_array(num_siblings,
-					 sizeof(*siblings),
-					 GFP_KERNEL);
-		if (!siblings)
-			return -ENOMEM;
-	}
-
-	for (n = 0; n < num_siblings; n++) {
-		struct i915_engine_class_instance ci;
-
-		if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
-			err = -EFAULT;
-			goto out_siblings;
-		}
-
-		siblings[n] = intel_engine_lookup_user(i915,
-						       ci.engine_class,
-						       ci.engine_instance);
-		if (!siblings[n]) {
-			drm_dbg(&i915->drm,
-				"Invalid sibling[%d]: { class:%d, inst:%d }\n",
-				n, ci.engine_class, ci.engine_instance);
-			err = -EINVAL;
-			goto out_siblings;
-		}
-	}
-
-	ce = intel_execlists_create_virtual(siblings, n);
-	if (IS_ERR(ce)) {
-		err = PTR_ERR(ce);
-		goto out_siblings;
-	}
-
-	intel_context_set_gem(ce, set->ctx);
-
-	if (cmpxchg(&set->engines->engines[idx], NULL, ce)) {
-		intel_context_put(ce);
-		err = -EEXIST;
-		goto out_siblings;
-	}
-
-out_siblings:
-	if (siblings != stack)
-		kfree(siblings);
-
-	return err;
-}
-
-static int
-set_engines__bond(struct i915_user_extension __user *base, void *data)
-{
-	struct i915_context_engines_bond __user *ext =
-		container_of_user(base, typeof(*ext), base);
-	const struct set_engines *set = data;
-	struct drm_i915_private *i915 = set->ctx->i915;
-	struct i915_engine_class_instance ci;
-	struct intel_engine_cs *virtual;
-	struct intel_engine_cs *master;
-	u16 idx, num_bonds;
-	int err, n;
-
-	if (get_user(idx, &ext->virtual_index))
-		return -EFAULT;
-
-	if (idx >= set->engines->num_engines) {
-		drm_dbg(&i915->drm,
-			"Invalid index for virtual engine: %d >= %d\n",
-			idx, set->engines->num_engines);
-		return -EINVAL;
-	}
-
-	idx = array_index_nospec(idx, set->engines->num_engines);
-	if (!set->engines->engines[idx]) {
-		drm_dbg(&i915->drm, "Invalid engine at %d\n", idx);
-		return -EINVAL;
-	}
-	virtual = set->engines->engines[idx]->engine;
-
-	err = check_user_mbz(&ext->flags);
-	if (err)
-		return err;
-
-	for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
-		err = check_user_mbz(&ext->mbz64[n]);
-		if (err)
-			return err;
-	}
-
-	if (copy_from_user(&ci, &ext->master, sizeof(ci)))
-		return -EFAULT;
-
-	master = intel_engine_lookup_user(i915,
-					  ci.engine_class, ci.engine_instance);
-	if (!master) {
-		drm_dbg(&i915->drm,
-			"Unrecognised master engine: { class:%u, instance:%u }\n",
-			ci.engine_class, ci.engine_instance);
-		return -EINVAL;
-	}
-
-	if (get_user(num_bonds, &ext->num_bonds))
-		return -EFAULT;
-
-	for (n = 0; n < num_bonds; n++) {
-		struct intel_engine_cs *bond;
-
-		if (copy_from_user(&ci, &ext->engines[n], sizeof(ci)))
-			return -EFAULT;
-
-		bond = intel_engine_lookup_user(i915,
-						ci.engine_class,
-						ci.engine_instance);
-		if (!bond) {
-			drm_dbg(&i915->drm,
-				"Unrecognised engine[%d] for bonding: { class:%d, instance: %d }\n",
-				n, ci.engine_class, ci.engine_instance);
-			return -EINVAL;
-		}
-
-		/*
-		 * A non-virtual engine has no siblings to choose between; and
-		 * a submit fence will always be directed to the one engine.
-		 */
-		if (intel_engine_is_virtual(virtual)) {
-			err = intel_virtual_engine_attach_bond(virtual,
-							       master,
-							       bond);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-static const i915_user_extension_fn set_engines__extensions[] = {
-	[I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_engines__load_balance,
-	[I915_CONTEXT_ENGINES_EXT_BOND] = set_engines__bond,
-};
-
-static int
-set_engines(struct i915_gem_context *ctx,
-	    const struct drm_i915_gem_context_param *args)
-{
-	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_context_param_engines __user *user =
-		u64_to_user_ptr(args->value);
-	struct set_engines set = { .ctx = ctx };
-	unsigned int num_engines, n;
-	u64 extensions;
-	int err;
-
-	if (!args->size) { /* switch back to legacy user_ring_map */
-		if (!i915_gem_context_user_engines(ctx))
-			return 0;
-
-		set.engines = default_engines(ctx);
-		if (IS_ERR(set.engines))
-			return PTR_ERR(set.engines);
-
-		goto replace;
-	}
-
-	BUILD_BUG_ON(!IS_ALIGNED(sizeof(*user), sizeof(*user->engines)));
-	if (args->size < sizeof(*user) ||
-	    !IS_ALIGNED(args->size, sizeof(*user->engines))) {
-		drm_dbg(&i915->drm, "Invalid size for engine array: %d\n",
-			args->size);
-		return -EINVAL;
-	}
-
-	/*
-	 * Note that I915_EXEC_RING_MASK limits execbuf to only using the
-	 * first 64 engines defined here.
-	 */
-	num_engines = (args->size - sizeof(*user)) / sizeof(*user->engines);
-	set.engines = alloc_engines(num_engines);
-	if (!set.engines)
-		return -ENOMEM;
-
-	for (n = 0; n < num_engines; n++) {
-		struct i915_engine_class_instance ci;
-		struct intel_engine_cs *engine;
-		struct intel_context *ce;
-
-		if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) {
-			__free_engines(set.engines, n);
-			return -EFAULT;
-		}
-
-		if (ci.engine_class == (u16)I915_ENGINE_CLASS_INVALID &&
-		    ci.engine_instance == (u16)I915_ENGINE_CLASS_INVALID_NONE) {
-			set.engines->engines[n] = NULL;
-			continue;
-		}
-
-		engine = intel_engine_lookup_user(ctx->i915,
-						  ci.engine_class,
-						  ci.engine_instance);
-		if (!engine) {
-			drm_dbg(&i915->drm,
-				"Invalid engine[%d]: { class:%d, instance:%d }\n",
-				n, ci.engine_class, ci.engine_instance);
-			__free_engines(set.engines, n);
-			return -ENOENT;
-		}
-
-		ce = intel_context_create(engine);
-		if (IS_ERR(ce)) {
-			__free_engines(set.engines, n);
-			return PTR_ERR(ce);
-		}
-
-		intel_context_set_gem(ce, ctx);
-
-		set.engines->engines[n] = ce;
-	}
-	set.engines->num_engines = num_engines;
-
-	err = -EFAULT;
-	if (!get_user(extensions, &user->extensions))
-		err = i915_user_extensions(u64_to_user_ptr(extensions),
-					   set_engines__extensions,
-					   ARRAY_SIZE(set_engines__extensions),
-					   &set);
-	if (err) {
-		free_engines(set.engines);
-		return err;
-	}
-
-replace:
-	mutex_lock(&ctx->engines_mutex);
-	if (i915_gem_context_is_closed(ctx)) {
-		mutex_unlock(&ctx->engines_mutex);
-		free_engines(set.engines);
-		return -ENOENT;
-	}
-	if (args->size)
-		i915_gem_context_set_user_engines(ctx);
-	else
-		i915_gem_context_clear_user_engines(ctx);
-	set.engines = rcu_replace_pointer(ctx->engines, set.engines, 1);
-	mutex_unlock(&ctx->engines_mutex);
-
-	/* Keep track of old engine sets for kill_context() */
-	engines_idle_release(ctx, set.engines);
-
-	return 0;
-}
-
-static int
-get_engines(struct i915_gem_context *ctx,
-	    struct drm_i915_gem_context_param *args)
-{
-	struct i915_context_param_engines __user *user;
-	struct i915_gem_engines *e;
-	size_t n, count, size;
-	bool user_engines;
-	int err = 0;
-
-	e = __context_engines_await(ctx, &user_engines);
-	if (!e)
-		return -ENOENT;
-
-	if (!user_engines) {
-		i915_sw_fence_complete(&e->fence);
-		args->size = 0;
-		return 0;
-	}
-
-	count = e->num_engines;
-
-	/* Be paranoid in case we have an impedance mismatch */
-	if (!check_struct_size(user, engines, count, &size)) {
-		err = -EINVAL;
-		goto err_free;
-	}
-	if (overflows_type(size, args->size)) {
-		err = -EINVAL;
-		goto err_free;
-	}
-
-	if (!args->size) {
-		args->size = size;
-		goto err_free;
-	}
-
-	if (args->size < size) {
-		err = -EINVAL;
-		goto err_free;
-	}
-
-	user = u64_to_user_ptr(args->value);
-	if (put_user(0, &user->extensions)) {
-		err = -EFAULT;
-		goto err_free;
-	}
-
-	for (n = 0; n < count; n++) {
-		struct i915_engine_class_instance ci = {
-			.engine_class = I915_ENGINE_CLASS_INVALID,
-			.engine_instance = I915_ENGINE_CLASS_INVALID_NONE,
-		};
-
-		if (e->engines[n]) {
-			ci.engine_class = e->engines[n]->engine->uabi_class;
-			ci.engine_instance = e->engines[n]->engine->uabi_instance;
-		}
-
-		if (copy_to_user(&user->engines[n], &ci, sizeof(ci))) {
-			err = -EFAULT;
-			goto err_free;
-		}
-	}
-
-	args->size = size;
-
-err_free:
-	i915_sw_fence_complete(&e->fence);
-	return err;
-}
-
 static int
 set_persistence(struct i915_gem_context *ctx,
 		const struct drm_i915_gem_context_param *args)
@@ -1931,41 +1769,30 @@ set_persistence(struct i915_gem_context *ctx,
 	return __context_set_persistence(ctx, args->value);
 }
 
-static int __apply_priority(struct intel_context *ce, void *arg)
+static void __apply_priority(struct intel_context *ce, void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 
 	if (!intel_engine_has_timeslices(ce->engine))
-		return 0;
+		return;
 
-	if (ctx->sched.priority >= I915_PRIORITY_NORMAL)
+	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
+	    intel_engine_has_semaphores(ce->engine))
 		intel_context_set_use_semaphores(ce);
 	else
 		intel_context_clear_use_semaphores(ce);
-
-	return 0;
 }
 
 static int set_priority(struct i915_gem_context *ctx,
 			const struct drm_i915_gem_context_param *args)
 {
-	s64 priority = args->value;
-
-	if (args->size)
-		return -EINVAL;
-
-	if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
-		return -ENODEV;
-
-	if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
-	    priority < I915_CONTEXT_MIN_USER_PRIORITY)
-		return -EINVAL;
+	int err;
 
-	if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
-	    !capable(CAP_SYS_NICE))
-		return -EPERM;
+	err = validate_priority(ctx->i915, args);
+	if (err)
+		return err;
 
-	ctx->sched.priority = priority;
+	ctx->sched.priority = args->value;
 	context_apply_all(ctx, __apply_priority, ctx);
 
 	return 0;
@@ -1978,15 +1805,6 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 	int ret = 0;
 
 	switch (args->param) {
-	case I915_CONTEXT_PARAM_NO_ZEROMAP:
-		if (args->size)
-			ret = -EINVAL;
-		else if (args->value)
-			set_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
-		else
-			clear_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
-		break;
-
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
 		if (args->size)
 			ret = -EINVAL;
@@ -2024,23 +1842,15 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		ret = set_sseu(ctx, args);
 		break;
 
-	case I915_CONTEXT_PARAM_VM:
-		ret = set_ppgtt(fpriv, ctx, args);
-		break;
-
-	case I915_CONTEXT_PARAM_ENGINES:
-		ret = set_engines(ctx, args);
-		break;
-
 	case I915_CONTEXT_PARAM_PERSISTENCE:
 		ret = set_persistence(ctx, args);
 		break;
 
-	case I915_CONTEXT_PARAM_RINGSIZE:
-		ret = set_ringsize(ctx, args);
-		break;
-
+	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
+	case I915_CONTEXT_PARAM_RINGSIZE:
+	case I915_CONTEXT_PARAM_VM:
+	case I915_CONTEXT_PARAM_ENGINES:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2050,7 +1860,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 }
 
 struct create_ext {
-	struct i915_gem_context *ctx;
+	struct i915_gem_proto_context *pc;
 	struct drm_i915_file_private *fpriv;
 };
 
@@ -2065,233 +1875,84 @@ static int create_setparam(struct i915_user_extension __user *ext, void *data)
 	if (local.param.ctx_id)
 		return -EINVAL;
 
-	return ctx_setparam(arg->fpriv, arg->ctx, &local.param);
+	return set_proto_ctx_param(arg->fpriv, arg->pc, &local.param);
 }
 
-static int copy_ring_size(struct intel_context *dst,
-			  struct intel_context *src)
+static int invalid_ext(struct i915_user_extension __user *ext, void *data)
 {
-	long sz;
-
-	sz = intel_context_get_ring_size(src);
-	if (sz < 0)
-		return sz;
-
-	return intel_context_set_ring_size(dst, sz);
+	return -EINVAL;
 }
 
-static int clone_engines(struct i915_gem_context *dst,
-			 struct i915_gem_context *src)
-{
-	struct i915_gem_engines *clone, *e;
-	bool user_engines;
-	unsigned long n;
-
-	e = __context_engines_await(src, &user_engines);
-	if (!e)
-		return -ENOENT;
-
-	clone = alloc_engines(e->num_engines);
-	if (!clone)
-		goto err_unlock;
-
-	for (n = 0; n < e->num_engines; n++) {
-		struct intel_engine_cs *engine;
-
-		if (!e->engines[n]) {
-			clone->engines[n] = NULL;
-			continue;
-		}
-		engine = e->engines[n]->engine;
-
-		/*
-		 * Virtual engines are singletons; they can only exist
-		 * inside a single context, because they embed their
-		 * HW context... As each virtual context implies a single
-		 * timeline (each engine can only dequeue a single request
-		 * at any time), it would be surprising for two contexts
-		 * to use the same engine. So let's create a copy of
-		 * the virtual engine instead.
-		 */
-		if (intel_engine_is_virtual(engine))
-			clone->engines[n] =
-				intel_execlists_clone_virtual(engine);
-		else
-			clone->engines[n] = intel_context_create(engine);
-		if (IS_ERR_OR_NULL(clone->engines[n])) {
-			__free_engines(clone, n);
-			goto err_unlock;
-		}
-
-		intel_context_set_gem(clone->engines[n], dst);
-
-		/* Copy across the preferred ringsize */
-		if (copy_ring_size(clone->engines[n], e->engines[n])) {
-			__free_engines(clone, n + 1);
-			goto err_unlock;
-		}
-	}
-	clone->num_engines = n;
-	i915_sw_fence_complete(&e->fence);
-
-	/* Serialised by constructor */
-	engines_idle_release(dst, rcu_replace_pointer(dst->engines, clone, 1));
-	if (user_engines)
-		i915_gem_context_set_user_engines(dst);
-	else
-		i915_gem_context_clear_user_engines(dst);
-	return 0;
-
-err_unlock:
-	i915_sw_fence_complete(&e->fence);
-	return -ENOMEM;
-}
-
-static int clone_flags(struct i915_gem_context *dst,
-		       struct i915_gem_context *src)
-{
-	dst->user_flags = src->user_flags;
-	return 0;
-}
-
-static int clone_schedattr(struct i915_gem_context *dst,
-			   struct i915_gem_context *src)
-{
-	dst->sched = src->sched;
-	return 0;
-}
-
-static int clone_sseu(struct i915_gem_context *dst,
-		      struct i915_gem_context *src)
-{
-	struct i915_gem_engines *e = i915_gem_context_lock_engines(src);
-	struct i915_gem_engines *clone;
-	unsigned long n;
-	int err;
-
-	/* no locking required; sole access under constructor*/
-	clone = __context_engines_static(dst);
-	if (e->num_engines != clone->num_engines) {
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	for (n = 0; n < e->num_engines; n++) {
-		struct intel_context *ce = e->engines[n];
-
-		if (clone->engines[n]->engine->class != ce->engine->class) {
-			/* Must have compatible engine maps! */
-			err = -EINVAL;
-			goto unlock;
-		}
-
-		/* serialises with set_sseu */
-		err = intel_context_lock_pinned(ce);
-		if (err)
-			goto unlock;
-
-		clone->engines[n]->sseu = ce->sseu;
-		intel_context_unlock_pinned(ce);
-	}
-
-	err = 0;
-unlock:
-	i915_gem_context_unlock_engines(src);
-	return err;
-}
+static const i915_user_extension_fn create_extensions[] = {
+	[I915_CONTEXT_CREATE_EXT_SETPARAM] = create_setparam,
+	[I915_CONTEXT_CREATE_EXT_CLONE] = invalid_ext,
+};
 
-static int clone_timeline(struct i915_gem_context *dst,
-			  struct i915_gem_context *src)
+static bool client_is_banned(struct drm_i915_file_private *file_priv)
 {
-	if (src->timeline)
-		__assign_timeline(dst, src->timeline);
-
-	return 0;
+	return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
 }
 
-static int clone_vm(struct i915_gem_context *dst,
-		    struct i915_gem_context *src)
+static inline struct i915_gem_context *
+__context_lookup(struct drm_i915_file_private *file_priv, u32 id)
 {
-	struct i915_address_space *vm;
-	int err = 0;
-
-	if (!rcu_access_pointer(src->vm))
-		return 0;
+	struct i915_gem_context *ctx;
 
 	rcu_read_lock();
-	vm = context_get_vm_rcu(src);
+	ctx = xa_load(&file_priv->context_xa, id);
+	if (ctx && !kref_get_unless_zero(&ctx->ref))
+		ctx = NULL;
 	rcu_read_unlock();
 
-	if (!mutex_lock_interruptible(&dst->mutex)) {
-		__assign_ppgtt(dst, vm);
-		mutex_unlock(&dst->mutex);
-	} else {
-		err = -EINTR;
-	}
-
-	i915_vm_put(vm);
-	return err;
+	return ctx;
 }
 
-static int create_clone(struct i915_user_extension __user *ext, void *data)
-{
-	static int (* const fn[])(struct i915_gem_context *dst,
-				  struct i915_gem_context *src) = {
-#define MAP(x, y) [ilog2(I915_CONTEXT_CLONE_##x)] = y
-		MAP(ENGINES, clone_engines),
-		MAP(FLAGS, clone_flags),
-		MAP(SCHEDATTR, clone_schedattr),
-		MAP(SSEU, clone_sseu),
-		MAP(TIMELINE, clone_timeline),
-		MAP(VM, clone_vm),
-#undef MAP
-	};
-	struct drm_i915_gem_context_create_ext_clone local;
-	const struct create_ext *arg = data;
-	struct i915_gem_context *dst = arg->ctx;
-	struct i915_gem_context *src;
-	int err, bit;
+static struct i915_gem_context *
+finalize_create_context_locked(struct drm_i915_file_private *file_priv,
+			       struct i915_gem_proto_context *pc, u32 id)
+{
+	struct i915_gem_context *ctx;
+	void *old;
 
-	if (copy_from_user(&local, ext, sizeof(local)))
-		return -EFAULT;
+	lockdep_assert_held(&file_priv->proto_context_lock);
 
-	BUILD_BUG_ON(GENMASK(BITS_PER_TYPE(local.flags) - 1, ARRAY_SIZE(fn)) !=
-		     I915_CONTEXT_CLONE_UNKNOWN);
+	ctx = i915_gem_create_context(file_priv->dev_priv, pc);
+	if (IS_ERR(ctx))
+		return ctx;
 
-	if (local.flags & I915_CONTEXT_CLONE_UNKNOWN)
-		return -EINVAL;
+	gem_context_register(ctx, file_priv, id);
 
-	if (local.rsvd)
-		return -EINVAL;
+	old = xa_erase(&file_priv->proto_context_xa, id);
+	GEM_BUG_ON(old != pc);
+	proto_context_close(pc);
 
-	rcu_read_lock();
-	src = __i915_gem_context_lookup_rcu(arg->fpriv, local.clone_id);
-	rcu_read_unlock();
-	if (!src)
-		return -ENOENT;
+	/* One for the xarray and one for the caller */
+	return i915_gem_context_get(ctx);
+}
 
-	GEM_BUG_ON(src == dst);
+struct i915_gem_context *
+i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
+{
+	struct i915_gem_proto_context *pc;
+	struct i915_gem_context *ctx;
 
-	for (bit = 0; bit < ARRAY_SIZE(fn); bit++) {
-		if (!(local.flags & BIT(bit)))
-			continue;
+	ctx = __context_lookup(file_priv, id);
+	if (ctx)
+		return ctx;
 
-		err = fn[bit](dst, src);
-		if (err)
-			return err;
+	mutex_lock(&file_priv->proto_context_lock);
+	/* Try one more time under the lock */
+	ctx = __context_lookup(file_priv, id);
+	if (!ctx) {
+		pc = xa_load(&file_priv->proto_context_xa, id);
+		if (!pc)
+			ctx = ERR_PTR(-ENOENT);
+		else
+			ctx = finalize_create_context_locked(file_priv, pc, id);
 	}
+	mutex_unlock(&file_priv->proto_context_lock);
 
-	return 0;
-}
-
-static const i915_user_extension_fn create_extensions[] = {
-	[I915_CONTEXT_CREATE_EXT_SETPARAM] = create_setparam,
-	[I915_CONTEXT_CREATE_EXT_CLONE] = create_clone,
-};
-
-static bool client_is_banned(struct drm_i915_file_private *file_priv)
-{
-	return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
+	return ctx;
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
@@ -2321,9 +1982,9 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 		return -EIO;
 	}
 
-	ext_data.ctx = i915_gem_create_context(i915, args->flags);
-	if (IS_ERR(ext_data.ctx))
-		return PTR_ERR(ext_data.ctx);
+	ext_data.pc = proto_context_create(i915, args->flags);
+	if (IS_ERR(ext_data.pc))
+		return PTR_ERR(ext_data.pc);
 
 	if (args->flags & I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS) {
 		ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
@@ -2331,20 +1992,39 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 					   ARRAY_SIZE(create_extensions),
 					   &ext_data);
 		if (ret)
-			goto err_ctx;
+			goto err_pc;
 	}
 
-	ret = gem_context_register(ext_data.ctx, ext_data.fpriv, &id);
-	if (ret < 0)
-		goto err_ctx;
+	if (GRAPHICS_VER(i915) > 12) {
+		struct i915_gem_context *ctx;
+
+		/* Get ourselves a context ID */
+		ret = xa_alloc(&ext_data.fpriv->context_xa, &id, NULL,
+			       xa_limit_32b, GFP_KERNEL);
+		if (ret)
+			goto err_pc;
+
+		ctx = i915_gem_create_context(i915, ext_data.pc);
+		if (IS_ERR(ctx)) {
+			ret = PTR_ERR(ctx);
+			goto err_pc;
+		}
+
+		proto_context_close(ext_data.pc);
+		gem_context_register(ctx, ext_data.fpriv, id);
+	} else {
+		ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id);
+		if (ret < 0)
+			goto err_pc;
+	}
 
 	args->ctx_id = id;
 	drm_dbg(&i915->drm, "HW context %d created\n", args->ctx_id);
 
 	return 0;
 
-err_ctx:
-	context_close(ext_data.ctx);
+err_pc:
+	proto_context_close(ext_data.pc);
 	return ret;
 }
 
@@ -2353,6 +2033,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_context_destroy *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct i915_gem_proto_context *pc;
 	struct i915_gem_context *ctx;
 
 	if (args->pad != 0)
@@ -2361,11 +2042,24 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	if (!args->ctx_id)
 		return -ENOENT;
 
+	/* We need to hold the proto-context lock here to prevent races
+	 * with finalize_create_context_locked().
+	 */
+	mutex_lock(&file_priv->proto_context_lock);
 	ctx = xa_erase(&file_priv->context_xa, args->ctx_id);
-	if (!ctx)
+	pc = xa_erase(&file_priv->proto_context_xa, args->ctx_id);
+	mutex_unlock(&file_priv->proto_context_lock);
+
+	if (!ctx && !pc)
 		return -ENOENT;
+	GEM_WARN_ON(ctx && pc);
+
+	if (pc)
+		proto_context_close(pc);
+
+	if (ctx)
+		context_close(ctx);
 
-	context_close(ctx);
 	return 0;
 }
 
@@ -2433,15 +2127,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	int ret = 0;
 
 	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
-	if (!ctx)
-		return -ENOENT;
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
 
 	switch (args->param) {
-	case I915_CONTEXT_PARAM_NO_ZEROMAP:
-		args->size = 0;
-		args->value = test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
-		break;
-
 	case I915_CONTEXT_PARAM_GTT_SIZE:
 		args->size = 0;
 		rcu_read_lock();
@@ -2480,20 +2169,15 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		ret = get_ppgtt(file_priv, ctx, args);
 		break;
 
-	case I915_CONTEXT_PARAM_ENGINES:
-		ret = get_engines(ctx, args);
-		break;
-
 	case I915_CONTEXT_PARAM_PERSISTENCE:
 		args->size = 0;
 		args->value = i915_gem_context_is_persistent(ctx);
 		break;
 
-	case I915_CONTEXT_PARAM_RINGSIZE:
-		ret = get_ringsize(ctx, args);
-		break;
-
+	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
+	case I915_CONTEXT_PARAM_ENGINES:
+	case I915_CONTEXT_PARAM_RINGSIZE:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2508,16 +2192,32 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_gem_context_param *args = data;
+	struct i915_gem_proto_context *pc;
 	struct i915_gem_context *ctx;
-	int ret;
+	int ret = 0;
 
-	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
-	if (!ctx)
-		return -ENOENT;
+	mutex_lock(&file_priv->proto_context_lock);
+	ctx = __context_lookup(file_priv, args->ctx_id);
+	if (!ctx) {
+		pc = xa_load(&file_priv->proto_context_xa, args->ctx_id);
+		if (pc) {
+			/* Contexts should be finalized inside
+			 * GEM_CONTEXT_CREATE starting with graphics
+			 * version 13.
+			 */
+			WARN_ON(GRAPHICS_VER(file_priv->dev_priv) > 12);
+			ret = set_proto_ctx_param(file_priv, pc, args);
+		} else {
+			ret = -ENOENT;
+		}
+	}
+	mutex_unlock(&file_priv->proto_context_lock);
 
-	ret = ctx_setparam(file_priv, ctx, args);
+	if (ctx) {
+		ret = ctx_setparam(file_priv, ctx, args);
+		i915_gem_context_put(ctx);
+	}
 
-	i915_gem_context_put(ctx);
 	return ret;
 }
 
@@ -2527,16 +2227,13 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_reset_stats *args = data;
 	struct i915_gem_context *ctx;
-	int ret;
 
 	if (args->flags || args->pad)
 		return -EINVAL;
 
-	ret = -ENOENT;
-	rcu_read_lock();
-	ctx = __i915_gem_context_lookup_rcu(file->driver_priv, args->ctx_id);
-	if (!ctx)
-		goto out;
+	ctx = i915_gem_context_lookup(file->driver_priv, args->ctx_id);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
 
 	/*
 	 * We opt for unserialised reads here. This may result in tearing
@@ -2553,10 +2250,8 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	args->batch_active = atomic_read(&ctx->guilty_count);
 	args->batch_pending = atomic_read(&ctx->active_count);
 
-	ret = 0;
-out:
-	rcu_read_unlock();
-	return ret;
+	i915_gem_context_put(ctx);
+	return 0;
 }
 
 /* GEM context-engines iterator: for_each_gem_engine() */
@@ -2584,27 +2279,16 @@ i915_gem_engines_iter_next(struct i915_gem_engines_iter *it)
 #include "selftests/i915_gem_context.c"
 #endif
 
-static void i915_global_gem_context_shrink(void)
+void i915_gem_context_module_exit(void)
 {
-	kmem_cache_shrink(global.slab_luts);
+	kmem_cache_destroy(slab_luts);
 }
 
-static void i915_global_gem_context_exit(void)
-{
-	kmem_cache_destroy(global.slab_luts);
-}
-
-static struct i915_global_gem_context global = { {
-	.shrink = i915_global_gem_context_shrink,
-	.exit = i915_global_gem_context_exit,
-} };
-
-int __init i915_global_gem_context_init(void)
+int __init i915_gem_context_module_init(void)
 {
-	global.slab_luts = KMEM_CACHE(i915_lut_handle, 0);
-	if (!global.slab_luts)
+	slab_luts = KMEM_CACHE(i915_lut_handle, 0);
+	if (!slab_luts)
 		return -ENOMEM;
 
-	i915_global_register(&global.base);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index b5c908f3f4f2..18060536b0c2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -133,6 +133,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
 				       struct drm_file *file);
 
+struct i915_gem_context *
+i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id);
+
 static inline struct i915_gem_context *
 i915_gem_context_get(struct i915_gem_context *ctx)
 {
@@ -221,6 +224,9 @@ i915_gem_engines_iter_next(struct i915_gem_engines_iter *it);
 	for (i915_gem_engines_iter_init(&(it), (engines)); \
 	     ((ce) = i915_gem_engines_iter_next(&(it)));)
 
+void i915_gem_context_module_exit(void);
+int i915_gem_context_module_init(void);
+
 struct i915_lut_handle *i915_lut_handle_alloc(void);
 void i915_lut_handle_free(struct i915_lut_handle *lut);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 340473aa70de..94c03a97cb77 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -30,33 +30,187 @@ struct i915_address_space;
 struct intel_timeline;
 struct intel_ring;
 
+/**
+ * struct i915_gem_engines - A set of engines
+ */
 struct i915_gem_engines {
 	union {
+		/** @link: Link in i915_gem_context::stale::engines */
 		struct list_head link;
+
+		/** @rcu: RCU to use when freeing */
 		struct rcu_head rcu;
 	};
+
+	/** @fence: Fence used for delayed destruction of engines */
 	struct i915_sw_fence fence;
+
+	/** @ctx: i915_gem_context backpointer */
 	struct i915_gem_context *ctx;
+
+	/** @num_engines: Number of engines in this set */
 	unsigned int num_engines;
+
+	/** @engines: Array of engines */
 	struct intel_context *engines[];
 };
 
+/**
+ * struct i915_gem_engines_iter - Iterator for an i915_gem_engines set
+ */
 struct i915_gem_engines_iter {
+	/** @idx: Index into i915_gem_engines::engines */
 	unsigned int idx;
+
+	/** @engines: Engine set being iterated */
 	const struct i915_gem_engines *engines;
 };
 
 /**
+ * enum i915_gem_engine_type - Describes the type of an i915_gem_proto_engine
+ */
+enum i915_gem_engine_type {
+	/** @I915_GEM_ENGINE_TYPE_INVALID: An invalid engine */
+	I915_GEM_ENGINE_TYPE_INVALID = 0,
+
+	/** @I915_GEM_ENGINE_TYPE_PHYSICAL: A single physical engine */
+	I915_GEM_ENGINE_TYPE_PHYSICAL,
+
+	/** @I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set */
+	I915_GEM_ENGINE_TYPE_BALANCED,
+};
+
+/**
+ * struct i915_gem_proto_engine - prototype engine
+ *
+ * This struct describes an engine that a context may contain.  Engines
+ * have three types:
+ *
+ *  - I915_GEM_ENGINE_TYPE_INVALID: Invalid engines can be created but they
+ *    show up as a NULL in i915_gem_engines::engines[i] and any attempt to
+ *    use them by the user results in -EINVAL.  They are also useful during
+ *    proto-context construction because the client may create invalid
+ *    engines and then set them up later as virtual engines.
+ *
+ *  - I915_GEM_ENGINE_TYPE_PHYSICAL: A single physical engine, described by
+ *    i915_gem_proto_engine::engine.
+ *
+ *  - I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set, described
+ *    i915_gem_proto_engine::num_siblings and i915_gem_proto_engine::siblings.
+ */
+struct i915_gem_proto_engine {
+	/** @type: Type of this engine */
+	enum i915_gem_engine_type type;
+
+	/** @engine: Engine, for physical */
+	struct intel_engine_cs *engine;
+
+	/** @num_siblings: Number of balanced siblings */
+	unsigned int num_siblings;
+
+	/** @siblings: Balanced siblings */
+	struct intel_engine_cs **siblings;
+
+	/** @sseu: Client-set SSEU parameters */
+	struct intel_sseu sseu;
+};
+
+/**
+ * struct i915_gem_proto_context - prototype context
+ *
+ * The struct i915_gem_proto_context represents the creation parameters for
+ * a struct i915_gem_context.  This is used to gather parameters provided
+ * either through creation flags or via SET_CONTEXT_PARAM so that, when we
+ * create the final i915_gem_context, those parameters can be immutable.
+ *
+ * The context uAPI allows for two methods of setting context parameters:
+ * SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM.  The former is
+ * allowed to be called at any time while the later happens as part of
+ * GEM_CONTEXT_CREATE.  When these were initially added, Currently,
+ * everything settable via one is settable via the other.  While some
+ * params are fairly simple and setting them on a live context is harmless
+ * such the context priority, others are far trickier such as the VM or the
+ * set of engines.  To avoid some truly nasty race conditions, we don't
+ * allow setting the VM or the set of engines on live contexts.
+ *
+ * The way we dealt with this without breaking older userspace that sets
+ * the VM or engine set via SET_CONTEXT_PARAM is to delay the creation of
+ * the actual context until after the client is done configuring it with
+ * SET_CONTEXT_PARAM.  From the perspective of the client, it has the same
+ * u32 context ID the whole time.  From the perspective of i915, however,
+ * it's an i915_gem_proto_context right up until the point where we attempt
+ * to do something which the proto-context can't handle at which point the
+ * real context gets created.
+ *
+ * This is accomplished via a little xarray dance.  When GEM_CONTEXT_CREATE
+ * is called, we create a proto-context, reserve a slot in context_xa but
+ * leave it NULL, the proto-context in the corresponding slot in
+ * proto_context_xa.  Then, whenever we go to look up a context, we first
+ * check context_xa.  If it's there, we return the i915_gem_context and
+ * we're done.  If it's not, we look in proto_context_xa and, if we find it
+ * there, we create the actual context and kill the proto-context.
+ *
+ * At the time we made this change (April, 2021), we did a fairly complete
+ * audit of existing userspace to ensure this wouldn't break anything:
+ *
+ *  - Mesa/i965 didn't use the engines or VM APIs at all
+ *
+ *  - Mesa/ANV used the engines API but via CONTEXT_CREATE_EXT_SETPARAM and
+ *    didn't use the VM API.
+ *
+ *  - Mesa/iris didn't use the engines or VM APIs at all
+ *
+ *  - The open-source compute-runtime didn't yet use the engines API but
+ *    did use the VM API via SET_CONTEXT_PARAM.  However, CONTEXT_SETPARAM
+ *    was always the second ioctl on that context, immediately following
+ *    GEM_CONTEXT_CREATE.
+ *
+ *  - The media driver sets engines and bonding/balancing via
+ *    SET_CONTEXT_PARAM.  However, CONTEXT_SETPARAM to set the VM was
+ *    always the second ioctl on that context, immediately following
+ *    GEM_CONTEXT_CREATE and setting engines immediately followed that.
+ *
+ * In order for this dance to work properly, any modification to an
+ * i915_gem_proto_context that is exposed to the client via
+ * drm_i915_file_private::proto_context_xa must be guarded by
+ * drm_i915_file_private::proto_context_lock.  The exception is when a
+ * proto-context has not yet been exposed such as when handling
+ * CONTEXT_CREATE_SET_PARAM during GEM_CONTEXT_CREATE.
+ */
+struct i915_gem_proto_context {
+	/** @vm: See &i915_gem_context.vm */
+	struct i915_address_space *vm;
+
+	/** @user_flags: See &i915_gem_context.user_flags */
+	unsigned long user_flags;
+
+	/** @sched: See &i915_gem_context.sched */
+	struct i915_sched_attr sched;
+
+	/** @num_user_engines: Number of user-specified engines or -1 */
+	int num_user_engines;
+
+	/** @user_engines: User-specified engines */
+	struct i915_gem_proto_engine *user_engines;
+
+	/** @legacy_rcs_sseu: Client-set SSEU parameters for the legacy RCS */
+	struct intel_sseu legacy_rcs_sseu;
+
+	/** @single_timeline: See See &i915_gem_context.syncobj */
+	bool single_timeline;
+};
+
+/**
  * struct i915_gem_context - client state
  *
  * The struct i915_gem_context represents the combined view of the driver and
  * logical hardware state for a particular client.
  */
 struct i915_gem_context {
-	/** i915: i915 device backpointer */
+	/** @i915: i915 device backpointer */
 	struct drm_i915_private *i915;
 
-	/** file_priv: owning file descriptor */
+	/** @file_priv: owning file descriptor */
 	struct drm_i915_file_private *file_priv;
 
 	/**
@@ -81,9 +235,23 @@ struct i915_gem_context {
 	 * CONTEXT_USER_ENGINES flag is set).
 	 */
 	struct i915_gem_engines __rcu *engines;
-	struct mutex engines_mutex; /* guards writes to engines */
 
-	struct intel_timeline *timeline;
+	/** @engines_mutex: guards writes to engines */
+	struct mutex engines_mutex;
+
+	/**
+	 * @syncobj: Shared timeline syncobj
+	 *
+	 * When the SHARED_TIMELINE flag is set on context creation, we
+	 * emulate a single timeline across all engines using this syncobj.
+	 * For every execbuffer2 call, this syncobj is used as both an in-
+	 * and out-fence.  Unlike the real intel_timeline, this doesn't
+	 * provide perfect atomic in-order guarantees if the client races
+	 * with itself by calling execbuffer2 twice concurrently.  However,
+	 * if userspace races with itself, that's not likely to yield well-
+	 * defined results anyway so we choose to not care.
+	 */
+	struct drm_syncobj *syncobj;
 
 	/**
 	 * @vm: unique address space (GTT)
@@ -106,7 +274,7 @@ struct i915_gem_context {
 	 */
 	struct pid *pid;
 
-	/** link: place with &drm_i915_private.context_list */
+	/** @link: place with &drm_i915_private.context_list */
 	struct list_head link;
 
 	/**
@@ -129,7 +297,6 @@ struct i915_gem_context {
 	 * @user_flags: small set of booleans controlled by the user
 	 */
 	unsigned long user_flags;
-#define UCONTEXT_NO_ZEROMAP		0
 #define UCONTEXT_NO_ERROR_CAPTURE	1
 #define UCONTEXT_BANNABLE		2
 #define UCONTEXT_RECOVERABLE		3
@@ -142,11 +309,13 @@ struct i915_gem_context {
 #define CONTEXT_CLOSED			0
 #define CONTEXT_USER_ENGINES		1
 
+	/** @mutex: guards everything that isn't engines or handles_vma */
 	struct mutex mutex;
 
+	/** @sched: scheduler parameters */
 	struct i915_sched_attr sched;
 
-	/** guilty_count: How many times this context has caused a GPU hang. */
+	/** @guilty_count: How many times this context has caused a GPU hang. */
 	atomic_t guilty_count;
 	/**
 	 * @active_count: How many times this context was active during a GPU
@@ -154,25 +323,23 @@ struct i915_gem_context {
 	 */
 	atomic_t active_count;
 
-	struct {
-		u64 timeout_us;
-	} watchdog;
-
 	/**
 	 * @hang_timestamp: The last time(s) this context caused a GPU hang
 	 */
 	unsigned long hang_timestamp[2];
 #define CONTEXT_FAST_HANG_JIFFIES (120 * HZ) /* 3 hangs within 120s? Banned! */
 
-	/** remap_slice: Bitmask of cache lines that need remapping */
+	/** @remap_slice: Bitmask of cache lines that need remapping */
 	u8 remap_slice;
 
 	/**
-	 * handles_vma: rbtree to look up our context specific obj/vma for
+	 * @handles_vma: rbtree to look up our context specific obj/vma for
 	 * the user handle. (user handles are per fd, but the binding is
 	 * per vm, which may be one per context or shared with the global GTT)
 	 */
 	struct radix_tree_root handles_vma;
+
+	/** @lut_mutex: Locks handles_vma */
 	struct mutex lut_mutex;
 
 	/**
@@ -184,8 +351,11 @@ struct i915_gem_context {
 	 */
 	char name[TASK_COMM_LEN + 8];
 
+	/** @stale: tracks stale engines to be destroyed */
 	struct {
+		/** @lock: guards engines */
 		spinlock_t lock;
+		/** @engines: list of stale engines */
 		struct list_head engines;
 	} stale;
 };
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index 548ddf39d853..23fee13a3384 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -11,13 +11,14 @@
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
 
-static u32 object_max_page_size(struct drm_i915_gem_object *obj)
+static u32 object_max_page_size(struct intel_memory_region **placements,
+				unsigned int n_placements)
 {
 	u32 max_page_size = 0;
 	int i;
 
-	for (i = 0; i < obj->mm.n_placements; i++) {
-		struct intel_memory_region *mr = obj->mm.placements[i];
+	for (i = 0; i < n_placements; i++) {
+		struct intel_memory_region *mr = placements[i];
 
 		GEM_BUG_ON(!is_power_of_2(mr->min_page_size));
 		max_page_size = max_t(u32, max_page_size, mr->min_page_size);
@@ -27,10 +28,13 @@ static u32 object_max_page_size(struct drm_i915_gem_object *obj)
 	return max_page_size;
 }
 
-static void object_set_placements(struct drm_i915_gem_object *obj,
-				  struct intel_memory_region **placements,
-				  unsigned int n_placements)
+static int object_set_placements(struct drm_i915_gem_object *obj,
+				 struct intel_memory_region **placements,
+				 unsigned int n_placements)
 {
+	struct intel_memory_region **arr;
+	unsigned int i;
+
 	GEM_BUG_ON(!n_placements);
 
 	/*
@@ -44,9 +48,20 @@ static void object_set_placements(struct drm_i915_gem_object *obj,
 		obj->mm.placements = &i915->mm.regions[mr->id];
 		obj->mm.n_placements = 1;
 	} else {
-		obj->mm.placements = placements;
+		arr = kmalloc_array(n_placements,
+				    sizeof(struct intel_memory_region *),
+				    GFP_KERNEL);
+		if (!arr)
+			return -ENOMEM;
+
+		for (i = 0; i < n_placements; i++)
+			arr[i] = placements[i];
+
+		obj->mm.placements = arr;
 		obj->mm.n_placements = n_placements;
 	}
+
+	return 0;
 }
 
 static int i915_gem_publish(struct drm_i915_gem_object *obj,
@@ -67,40 +82,67 @@ static int i915_gem_publish(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
-static int
-i915_gem_setup(struct drm_i915_gem_object *obj, u64 size)
+/**
+ * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT
+ * @i915: i915 private
+ * @size: size of the buffer, in bytes
+ * @placements: possible placement regions, in priority order
+ * @n_placements: number of possible placement regions
+ *
+ * This function is exposed primarily for selftests and does very little
+ * error checking.  It is assumed that the set of placement regions has
+ * already been verified to be valid.
+ */
+struct drm_i915_gem_object *
+__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size,
+			      struct intel_memory_region **placements,
+			      unsigned int n_placements)
 {
-	struct intel_memory_region *mr = obj->mm.placements[0];
+	struct intel_memory_region *mr = placements[0];
+	struct drm_i915_gem_object *obj;
 	unsigned int flags;
 	int ret;
 
-	size = round_up(size, object_max_page_size(obj));
+	i915_gem_flush_free_objects(i915);
+
+	size = round_up(size, object_max_page_size(placements, n_placements));
 	if (size == 0)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	/* For most of the ABI (e.g. mmap) we think in system pages */
 	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
 
 	if (i915_gem_object_size_2big(size))
-		return -E2BIG;
+		return ERR_PTR(-E2BIG);
+
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	ret = object_set_placements(obj, placements, n_placements);
+	if (ret)
+		goto object_free;
 
 	/*
-	 * For now resort to CPU based clearing for device local-memory, in the
-	 * near future this will use the blitter engine for accelerated, GPU
-	 * based clearing.
+	 * I915_BO_ALLOC_USER will make sure the object is cleared before
+	 * any user access.
 	 */
-	flags = 0;
-	if (mr->type == INTEL_MEMORY_LOCAL)
-		flags = I915_BO_ALLOC_CPU_CLEAR;
+	flags = I915_BO_ALLOC_USER;
 
-	ret = mr->ops->init_object(mr, obj, size, flags);
+	ret = mr->ops->init_object(mr, obj, size, 0, flags);
 	if (ret)
-		return ret;
+		goto object_free;
 
 	GEM_BUG_ON(size != obj->base.size);
 
 	trace_i915_gem_object_create(obj);
-	return 0;
+	return obj;
+
+object_free:
+	if (obj->mm.n_placements > 1)
+		kfree(obj->mm.placements);
+	i915_gem_object_free(obj);
+	return ERR_PTR(ret);
 }
 
 int
@@ -113,7 +155,6 @@ i915_gem_dumb_create(struct drm_file *file,
 	enum intel_memory_type mem_type;
 	int cpp = DIV_ROUND_UP(args->bpp, 8);
 	u32 format;
-	int ret;
 
 	switch (cpp) {
 	case 1:
@@ -146,22 +187,13 @@ i915_gem_dumb_create(struct drm_file *file,
 	if (HAS_LMEM(to_i915(dev)))
 		mem_type = INTEL_MEMORY_LOCAL;
 
-	obj = i915_gem_object_alloc();
-	if (!obj)
-		return -ENOMEM;
-
 	mr = intel_memory_region_by_type(to_i915(dev), mem_type);
-	object_set_placements(obj, &mr, 1);
 
-	ret = i915_gem_setup(obj, args->size);
-	if (ret)
-		goto object_free;
+	obj = __i915_gem_object_create_user(to_i915(dev), args->size, &mr, 1);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	return i915_gem_publish(obj, file, &args->size, &args->handle);
-
-object_free:
-	i915_gem_object_free(obj);
-	return ret;
 }
 
 /**
@@ -178,31 +210,20 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_create *args = data;
 	struct drm_i915_gem_object *obj;
 	struct intel_memory_region *mr;
-	int ret;
-
-	i915_gem_flush_free_objects(i915);
-
-	obj = i915_gem_object_alloc();
-	if (!obj)
-		return -ENOMEM;
 
 	mr = intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM);
-	object_set_placements(obj, &mr, 1);
 
-	ret = i915_gem_setup(obj, args->size);
-	if (ret)
-		goto object_free;
+	obj = __i915_gem_object_create_user(i915, args->size, &mr, 1);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	return i915_gem_publish(obj, file, &args->size, &args->handle);
-
-object_free:
-	i915_gem_object_free(obj);
-	return ret;
 }
 
 struct create_ext {
 	struct drm_i915_private *i915;
-	struct drm_i915_gem_object *vanilla_object;
+	struct intel_memory_region *placements[INTEL_REGION_UNKNOWN];
+	unsigned int n_placements;
 };
 
 static void repr_placements(char *buf, size_t size,
@@ -233,8 +254,7 @@ static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args,
 	struct drm_i915_private *i915 = ext_data->i915;
 	struct drm_i915_gem_memory_class_instance __user *uregions =
 		u64_to_user_ptr(args->regions);
-	struct drm_i915_gem_object *obj = ext_data->vanilla_object;
-	struct intel_memory_region **placements;
+	struct intel_memory_region *placements[INTEL_REGION_UNKNOWN];
 	u32 mask;
 	int i, ret = 0;
 
@@ -248,6 +268,8 @@ static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args,
 		ret = -EINVAL;
 	}
 
+	BUILD_BUG_ON(ARRAY_SIZE(i915->mm.regions) != ARRAY_SIZE(placements));
+	BUILD_BUG_ON(ARRAY_SIZE(ext_data->placements) != ARRAY_SIZE(placements));
 	if (args->num_regions > ARRAY_SIZE(i915->mm.regions)) {
 		drm_dbg(&i915->drm, "num_regions is too large\n");
 		ret = -EINVAL;
@@ -256,21 +278,13 @@ static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args,
 	if (ret)
 		return ret;
 
-	placements = kmalloc_array(args->num_regions,
-				   sizeof(struct intel_memory_region *),
-				   GFP_KERNEL);
-	if (!placements)
-		return -ENOMEM;
-
 	mask = 0;
 	for (i = 0; i < args->num_regions; i++) {
 		struct drm_i915_gem_memory_class_instance region;
 		struct intel_memory_region *mr;
 
-		if (copy_from_user(&region, uregions, sizeof(region))) {
-			ret = -EFAULT;
-			goto out_free;
-		}
+		if (copy_from_user(&region, uregions, sizeof(region)))
+			return -EFAULT;
 
 		mr = intel_memory_region_lookup(i915,
 						region.memory_class,
@@ -296,14 +310,14 @@ static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args,
 		++uregions;
 	}
 
-	if (obj->mm.placements) {
+	if (ext_data->n_placements) {
 		ret = -EINVAL;
 		goto out_dump;
 	}
 
-	object_set_placements(obj, placements, args->num_regions);
-	if (args->num_regions == 1)
-		kfree(placements);
+	ext_data->n_placements = args->num_regions;
+	for (i = 0; i < args->num_regions; i++)
+		ext_data->placements[i] = placements[i];
 
 	return 0;
 
@@ -311,11 +325,11 @@ out_dump:
 	if (1) {
 		char buf[256];
 
-		if (obj->mm.placements) {
+		if (ext_data->n_placements) {
 			repr_placements(buf,
 					sizeof(buf),
-					obj->mm.placements,
-					obj->mm.n_placements);
+					ext_data->placements,
+					ext_data->n_placements);
 			drm_dbg(&i915->drm,
 				"Placements were already set in previous EXT. Existing placements: %s\n",
 				buf);
@@ -325,8 +339,6 @@ out_dump:
 		drm_dbg(&i915->drm, "New placements(so far validated): %s\n", buf);
 	}
 
-out_free:
-	kfree(placements);
 	return ret;
 }
 
@@ -361,44 +373,30 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_create_ext *args = data;
 	struct create_ext ext_data = { .i915 = i915 };
-	struct intel_memory_region **placements_ext;
 	struct drm_i915_gem_object *obj;
 	int ret;
 
 	if (args->flags)
 		return -EINVAL;
 
-	i915_gem_flush_free_objects(i915);
-
-	obj = i915_gem_object_alloc();
-	if (!obj)
-		return -ENOMEM;
-
-	ext_data.vanilla_object = obj;
 	ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
 				   create_extensions,
 				   ARRAY_SIZE(create_extensions),
 				   &ext_data);
-	placements_ext = obj->mm.placements;
 	if (ret)
-		goto object_free;
+		return ret;
 
-	if (!placements_ext) {
-		struct intel_memory_region *mr =
+	if (!ext_data.n_placements) {
+		ext_data.placements[0] =
 			intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM);
-
-		object_set_placements(obj, &mr, 1);
+		ext_data.n_placements = 1;
 	}
 
-	ret = i915_gem_setup(obj, args->size);
-	if (ret)
-		goto object_free;
+	obj = __i915_gem_object_create_user(i915, args->size,
+					    ext_data.placements,
+					    ext_data.n_placements);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	return i915_gem_publish(obj, file, &args->size, &args->handle);
-
-object_free:
-	if (obj->mm.n_placements > 1)
-		kfree(placements_ext);
-	i915_gem_object_free(obj);
-	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 616c3a2f1baf..afa34111de02 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -12,6 +12,8 @@
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 
+I915_SELFTEST_DECLARE(static bool force_different_devices;)
+
 static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
 {
 	return to_intel_bo(buf->priv);
@@ -25,15 +27,11 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
 	struct scatterlist *src, *dst;
 	int ret, i;
 
-	ret = i915_gem_object_pin_pages_unlocked(obj);
-	if (ret)
-		goto err;
-
 	/* Copy sg so that we make an independent mapping */
 	st = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
 	if (st == NULL) {
 		ret = -ENOMEM;
-		goto err_unpin_pages;
+		goto err;
 	}
 
 	ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL);
@@ -58,8 +56,6 @@ err_free_sg:
 	sg_free_table(st);
 err_free:
 	kfree(st);
-err_unpin_pages:
-	i915_gem_object_unpin_pages(obj);
 err:
 	return ERR_PTR(ret);
 }
@@ -68,13 +64,9 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 				   struct sg_table *sg,
 				   enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
-
 	dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC);
 	sg_free_table(sg);
 	kfree(sg);
-
-	i915_gem_object_unpin_pages(obj);
 }
 
 static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
@@ -168,7 +160,46 @@ retry:
 	return err;
 }
 
+static int i915_gem_dmabuf_attach(struct dma_buf *dmabuf,
+				  struct dma_buf_attachment *attach)
+{
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf);
+	struct i915_gem_ww_ctx ww;
+	int err;
+
+	if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM))
+		return -EOPNOTSUPP;
+
+	for_i915_gem_ww(&ww, err, true) {
+		err = i915_gem_object_lock(obj, &ww);
+		if (err)
+			continue;
+
+		err = i915_gem_object_migrate(obj, &ww, INTEL_REGION_SMEM);
+		if (err)
+			continue;
+
+		err = i915_gem_object_wait_migration(obj, 0);
+		if (err)
+			continue;
+
+		err = i915_gem_object_pin_pages(obj);
+	}
+
+	return err;
+}
+
+static void i915_gem_dmabuf_detach(struct dma_buf *dmabuf,
+				   struct dma_buf_attachment *attach)
+{
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf);
+
+	i915_gem_object_unpin_pages(obj);
+}
+
 static const struct dma_buf_ops i915_dmabuf_ops =  {
+	.attach = i915_gem_dmabuf_attach,
+	.detach = i915_gem_dmabuf_detach,
 	.map_dma_buf = i915_gem_map_dma_buf,
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
@@ -204,6 +235,8 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	struct sg_table *pages;
 	unsigned int sg_page_sizes;
 
+	assert_object_held(obj);
+
 	pages = dma_buf_map_attachment(obj->base.import_attach,
 				       DMA_BIDIRECTIONAL);
 	if (IS_ERR(pages))
@@ -241,7 +274,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	if (dma_buf->ops == &i915_dmabuf_ops) {
 		obj = dma_buf_to_obj(dma_buf);
 		/* is it from our device? */
-		if (obj->base.dev == dev) {
+		if (obj->base.dev == dev &&
+		    !I915_SELFTEST_ONLY(force_different_devices)) {
 			/*
 			 * Importing dmabuf exported from out own gem increases
 			 * refcount on gem itself instead of f_count of dmabuf.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 073822100da7..b684a62bf3b0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -268,6 +268,9 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *obj;
 	int err = 0;
 
+	if (IS_DGFX(to_i915(dev)))
+		return -ENODEV;
+
 	rcu_read_lock();
 	obj = i915_gem_object_lookup_rcu(file, args->handle);
 	if (!obj) {
@@ -303,6 +306,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	enum i915_cache_level level;
 	int ret = 0;
 
+	if (IS_DGFX(i915))
+		return -ENODEV;
+
 	switch (args->caching) {
 	case I915_CACHING_NONE:
 		level = I915_CACHE_NONE;
@@ -375,7 +381,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	struct i915_vma *vma;
 	int ret;
 
-	/* Frame buffer must be in LMEM (no migration yet) */
+	/* Frame buffer must be in LMEM */
 	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj))
 		return ERR_PTR(-EINVAL);
 
@@ -484,6 +490,9 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	u32 write_domain = args->write_domain;
 	int err;
 
+	if (IS_DGFX(to_i915(dev)))
+		return -ENODEV;
+
 	/* Only handle setting domains to types used by the CPU. */
 	if ((write_domain | read_domains) & I915_GEM_GPU_DOMAINS)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 4a6419d7be93..1aa249908b64 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -277,18 +277,9 @@ struct i915_execbuffer {
 		bool has_llc : 1;
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
-
-		struct i915_request *rq;
-		u32 *rq_cmd;
-		unsigned int rq_size;
-		struct intel_gt_buffer_pool_node *pool;
 	} reloc_cache;
 
-	struct intel_gt_buffer_pool_node *reloc_pool; /** relocation pool for -EDEADLK handling */
-	struct intel_context *reloc_context;
-
 	u64 invalid_flags; /** Set of execobj.flags that are invalid */
-	u32 context_flags; /** Set of execobj.flags to insert from the ctx */
 
 	u64 batch_len; /** Length of batch within object */
 	u32 batch_start_offset; /** Location within object of batch */
@@ -539,9 +530,6 @@ eb_validate_vma(struct i915_execbuffer *eb,
 			entry->flags |= EXEC_OBJECT_NEEDS_GTT | __EXEC_OBJECT_NEEDS_MAP;
 	}
 
-	if (!(entry->flags & EXEC_OBJECT_PINNED))
-		entry->flags |= eb->context_flags;
-
 	return 0;
 }
 
@@ -741,17 +729,13 @@ static int eb_select_context(struct i915_execbuffer *eb)
 	struct i915_gem_context *ctx;
 
 	ctx = i915_gem_context_lookup(eb->file->driver_priv, eb->args->rsvd1);
-	if (unlikely(!ctx))
-		return -ENOENT;
+	if (unlikely(IS_ERR(ctx)))
+		return PTR_ERR(ctx);
 
 	eb->gem_context = ctx;
 	if (rcu_access_pointer(ctx->vm))
 		eb->invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
 
-	eb->context_flags = 0;
-	if (test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags))
-		eb->context_flags |= __EXEC_OBJECT_NEEDS_BIAS;
-
 	return 0;
 }
 
@@ -920,21 +904,38 @@ err:
 	return err;
 }
 
-static int eb_validate_vmas(struct i915_execbuffer *eb)
+static int eb_lock_vmas(struct i915_execbuffer *eb)
 {
 	unsigned int i;
 	int err;
 
-	INIT_LIST_HEAD(&eb->unbound);
-
 	for (i = 0; i < eb->buffer_count; i++) {
-		struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 		struct eb_vma *ev = &eb->vma[i];
 		struct i915_vma *vma = ev->vma;
 
 		err = i915_gem_object_lock(vma->obj, &eb->ww);
 		if (err)
 			return err;
+	}
+
+	return 0;
+}
+
+static int eb_validate_vmas(struct i915_execbuffer *eb)
+{
+	unsigned int i;
+	int err;
+
+	INIT_LIST_HEAD(&eb->unbound);
+
+	err = eb_lock_vmas(eb);
+	if (err)
+		return err;
+
+	for (i = 0; i < eb->buffer_count; i++) {
+		struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
+		struct eb_vma *ev = &eb->vma[i];
+		struct i915_vma *vma = ev->vma;
 
 		err = eb_pin_vma(eb, entry, ev);
 		if (err == -EDEADLK)
@@ -992,7 +993,7 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
 	}
 }
 
-static void eb_release_vmas(struct i915_execbuffer *eb, bool final, bool release_userptr)
+static void eb_release_vmas(struct i915_execbuffer *eb, bool final)
 {
 	const unsigned int count = eb->buffer_count;
 	unsigned int i;
@@ -1006,11 +1007,6 @@ static void eb_release_vmas(struct i915_execbuffer *eb, bool final, bool release
 
 		eb_unreserve_vma(ev);
 
-		if (release_userptr && ev->flags & __EXEC_OBJECT_USERPTR_INIT) {
-			ev->flags &= ~__EXEC_OBJECT_USERPTR_INIT;
-			i915_gem_object_userptr_submit_fini(vma->obj);
-		}
-
 		if (final)
 			i915_vma_put(vma);
 	}
@@ -1020,8 +1016,6 @@ static void eb_release_vmas(struct i915_execbuffer *eb, bool final, bool release
 
 static void eb_destroy(const struct i915_execbuffer *eb)
 {
-	GEM_BUG_ON(eb->reloc_cache.rq);
-
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -1033,14 +1027,6 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
 	return gen8_canonical_addr((int)reloc->delta + target->node.start);
 }
 
-static void reloc_cache_clear(struct reloc_cache *cache)
-{
-	cache->rq = NULL;
-	cache->rq_cmd = NULL;
-	cache->pool = NULL;
-	cache->rq_size = 0;
-}
-
 static void reloc_cache_init(struct reloc_cache *cache,
 			     struct drm_i915_private *i915)
 {
@@ -1053,7 +1039,6 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->graphics_ver < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
-	reloc_cache_clear(cache);
 }
 
 static inline void *unmask_page(unsigned long p)
@@ -1075,48 +1060,10 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
 	return &i915->ggtt;
 }
 
-static void reloc_cache_put_pool(struct i915_execbuffer *eb, struct reloc_cache *cache)
-{
-	if (!cache->pool)
-		return;
-
-	/*
-	 * This is a bit nasty, normally we keep objects locked until the end
-	 * of execbuffer, but we already submit this, and have to unlock before
-	 * dropping the reference. Fortunately we can only hold 1 pool node at
-	 * a time, so this should be harmless.
-	 */
-	i915_gem_ww_unlock_single(cache->pool->obj);
-	intel_gt_buffer_pool_put(cache->pool);
-	cache->pool = NULL;
-}
-
-static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cache)
-{
-	struct drm_i915_gem_object *obj = cache->rq->batch->obj;
-
-	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
-	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
-
-	i915_gem_object_flush_map(obj);
-	i915_gem_object_unpin_map(obj);
-
-	intel_gt_chipset_flush(cache->rq->engine->gt);
-
-	i915_request_add(cache->rq);
-	reloc_cache_put_pool(eb, cache);
-	reloc_cache_clear(cache);
-
-	eb->reloc_pool = NULL;
-}
-
 static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb)
 {
 	void *vaddr;
 
-	if (cache->rq)
-		reloc_gpu_flush(eb, cache);
-
 	if (!cache->vaddr)
 		return;
 
@@ -1298,295 +1245,6 @@ static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
 		*addr = value;
 }
 
-static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
-{
-	struct drm_i915_gem_object *obj = vma->obj;
-	int err;
-
-	assert_vma_held(vma);
-
-	if (obj->cache_dirty & ~obj->cache_coherent)
-		i915_gem_clflush_object(obj, 0);
-	obj->write_domain = 0;
-
-	err = i915_request_await_object(rq, vma->obj, true);
-	if (err == 0)
-		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-
-	return err;
-}
-
-static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
-			     struct intel_engine_cs *engine,
-			     struct i915_vma *vma,
-			     unsigned int len)
-{
-	struct reloc_cache *cache = &eb->reloc_cache;
-	struct intel_gt_buffer_pool_node *pool = eb->reloc_pool;
-	struct i915_request *rq;
-	struct i915_vma *batch;
-	u32 *cmd;
-	int err;
-
-	if (!pool) {
-		pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE,
-						cache->has_llc ?
-						I915_MAP_WB :
-						I915_MAP_WC);
-		if (IS_ERR(pool))
-			return PTR_ERR(pool);
-	}
-	eb->reloc_pool = NULL;
-
-	err = i915_gem_object_lock(pool->obj, &eb->ww);
-	if (err)
-		goto err_pool;
-
-	cmd = i915_gem_object_pin_map(pool->obj, pool->type);
-	if (IS_ERR(cmd)) {
-		err = PTR_ERR(cmd);
-		goto err_pool;
-	}
-	intel_gt_buffer_pool_mark_used(pool);
-
-	memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
-
-	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto err_unmap;
-	}
-
-	err = i915_vma_pin_ww(batch, &eb->ww, 0, 0, PIN_USER | PIN_NONBLOCK);
-	if (err)
-		goto err_unmap;
-
-	if (engine == eb->context->engine) {
-		rq = i915_request_create(eb->context);
-	} else {
-		struct intel_context *ce = eb->reloc_context;
-
-		if (!ce) {
-			ce = intel_context_create(engine);
-			if (IS_ERR(ce)) {
-				err = PTR_ERR(ce);
-				goto err_unpin;
-			}
-
-			i915_vm_put(ce->vm);
-			ce->vm = i915_vm_get(eb->context->vm);
-			eb->reloc_context = ce;
-		}
-
-		err = intel_context_pin_ww(ce, &eb->ww);
-		if (err)
-			goto err_unpin;
-
-		rq = i915_request_create(ce);
-		intel_context_unpin(ce);
-	}
-	if (IS_ERR(rq)) {
-		err = PTR_ERR(rq);
-		goto err_unpin;
-	}
-
-	err = intel_gt_buffer_pool_mark_active(pool, rq);
-	if (err)
-		goto err_request;
-
-	err = reloc_move_to_gpu(rq, vma);
-	if (err)
-		goto err_request;
-
-	err = eb->engine->emit_bb_start(rq,
-					batch->node.start, PAGE_SIZE,
-					cache->graphics_ver > 5 ? 0 : I915_DISPATCH_SECURE);
-	if (err)
-		goto skip_request;
-
-	assert_vma_held(batch);
-	err = i915_request_await_object(rq, batch->obj, false);
-	if (err == 0)
-		err = i915_vma_move_to_active(batch, rq, 0);
-	if (err)
-		goto skip_request;
-
-	rq->batch = batch;
-	i915_vma_unpin(batch);
-
-	cache->rq = rq;
-	cache->rq_cmd = cmd;
-	cache->rq_size = 0;
-	cache->pool = pool;
-
-	/* Return with batch mapping (cmd) still pinned */
-	return 0;
-
-skip_request:
-	i915_request_set_error_once(rq, err);
-err_request:
-	i915_request_add(rq);
-err_unpin:
-	i915_vma_unpin(batch);
-err_unmap:
-	i915_gem_object_unpin_map(pool->obj);
-err_pool:
-	eb->reloc_pool = pool;
-	return err;
-}
-
-static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
-{
-	return engine->class != VIDEO_DECODE_CLASS || GRAPHICS_VER(engine->i915) != 6;
-}
-
-static u32 *reloc_gpu(struct i915_execbuffer *eb,
-		      struct i915_vma *vma,
-		      unsigned int len)
-{
-	struct reloc_cache *cache = &eb->reloc_cache;
-	u32 *cmd;
-
-	if (cache->rq_size > PAGE_SIZE/sizeof(u32) - (len + 1))
-		reloc_gpu_flush(eb, cache);
-
-	if (unlikely(!cache->rq)) {
-		int err;
-		struct intel_engine_cs *engine = eb->engine;
-
-		/* If we need to copy for the cmdparser, we will stall anyway */
-		if (eb_use_cmdparser(eb))
-			return ERR_PTR(-EWOULDBLOCK);
-
-		if (!reloc_can_use_engine(engine)) {
-			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
-			if (!engine)
-				return ERR_PTR(-ENODEV);
-		}
-
-		err = __reloc_gpu_alloc(eb, engine, vma, len);
-		if (unlikely(err))
-			return ERR_PTR(err);
-	}
-
-	cmd = cache->rq_cmd + cache->rq_size;
-	cache->rq_size += len;
-
-	return cmd;
-}
-
-static inline bool use_reloc_gpu(struct i915_vma *vma)
-{
-	if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
-		return true;
-
-	if (DBG_FORCE_RELOC)
-		return false;
-
-	return !dma_resv_test_signaled(vma->resv, true);
-}
-
-static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
-{
-	struct page *page;
-	unsigned long addr;
-
-	GEM_BUG_ON(vma->pages != vma->obj->mm.pages);
-
-	page = i915_gem_object_get_page(vma->obj, offset >> PAGE_SHIFT);
-	addr = PFN_PHYS(page_to_pfn(page));
-	GEM_BUG_ON(overflows_type(addr, u32)); /* expected dma32 */
-
-	return addr + offset_in_page(offset);
-}
-
-static int __reloc_entry_gpu(struct i915_execbuffer *eb,
-			      struct i915_vma *vma,
-			      u64 offset,
-			      u64 target_addr)
-{
-	const unsigned int ver = eb->reloc_cache.graphics_ver;
-	unsigned int len;
-	u32 *batch;
-	u64 addr;
-
-	if (ver >= 8)
-		len = offset & 7 ? 8 : 5;
-	else if (ver >= 4)
-		len = 4;
-	else
-		len = 3;
-
-	batch = reloc_gpu(eb, vma, len);
-	if (batch == ERR_PTR(-EDEADLK))
-		return -EDEADLK;
-	else if (IS_ERR(batch))
-		return false;
-
-	addr = gen8_canonical_addr(vma->node.start + offset);
-	if (ver >= 8) {
-		if (offset & 7) {
-			*batch++ = MI_STORE_DWORD_IMM_GEN4;
-			*batch++ = lower_32_bits(addr);
-			*batch++ = upper_32_bits(addr);
-			*batch++ = lower_32_bits(target_addr);
-
-			addr = gen8_canonical_addr(addr + 4);
-
-			*batch++ = MI_STORE_DWORD_IMM_GEN4;
-			*batch++ = lower_32_bits(addr);
-			*batch++ = upper_32_bits(addr);
-			*batch++ = upper_32_bits(target_addr);
-		} else {
-			*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
-			*batch++ = lower_32_bits(addr);
-			*batch++ = upper_32_bits(addr);
-			*batch++ = lower_32_bits(target_addr);
-			*batch++ = upper_32_bits(target_addr);
-		}
-	} else if (ver >= 6) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4;
-		*batch++ = 0;
-		*batch++ = addr;
-		*batch++ = target_addr;
-	} else if (IS_I965G(eb->i915)) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4;
-		*batch++ = 0;
-		*batch++ = vma_phys_addr(vma, offset);
-		*batch++ = target_addr;
-	} else if (ver >= 4) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-		*batch++ = 0;
-		*batch++ = addr;
-		*batch++ = target_addr;
-	} else if (ver >= 3 &&
-		   !(IS_I915G(eb->i915) || IS_I915GM(eb->i915))) {
-		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
-		*batch++ = addr;
-		*batch++ = target_addr;
-	} else {
-		*batch++ = MI_STORE_DWORD_IMM;
-		*batch++ = vma_phys_addr(vma, offset);
-		*batch++ = target_addr;
-	}
-
-	return true;
-}
-
-static int reloc_entry_gpu(struct i915_execbuffer *eb,
-			    struct i915_vma *vma,
-			    u64 offset,
-			    u64 target_addr)
-{
-	if (eb->reloc_cache.vaddr)
-		return false;
-
-	if (!use_reloc_gpu(vma))
-		return false;
-
-	return __reloc_entry_gpu(eb, vma, offset, target_addr);
-}
-
 static u64
 relocate_entry(struct i915_vma *vma,
 	       const struct drm_i915_gem_relocation_entry *reloc,
@@ -1595,32 +1253,25 @@ relocate_entry(struct i915_vma *vma,
 {
 	u64 target_addr = relocation_target(reloc, target);
 	u64 offset = reloc->offset;
-	int reloc_gpu = reloc_entry_gpu(eb, vma, offset, target_addr);
-
-	if (reloc_gpu < 0)
-		return reloc_gpu;
-
-	if (!reloc_gpu) {
-		bool wide = eb->reloc_cache.use_64bit_reloc;
-		void *vaddr;
+	bool wide = eb->reloc_cache.use_64bit_reloc;
+	void *vaddr;
 
 repeat:
-		vaddr = reloc_vaddr(vma->obj, eb,
-				    offset >> PAGE_SHIFT);
-		if (IS_ERR(vaddr))
-			return PTR_ERR(vaddr);
-
-		GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
-		clflush_write32(vaddr + offset_in_page(offset),
-				lower_32_bits(target_addr),
-				eb->reloc_cache.vaddr);
-
-		if (wide) {
-			offset += sizeof(u32);
-			target_addr >>= 32;
-			wide = false;
-			goto repeat;
-		}
+	vaddr = reloc_vaddr(vma->obj, eb,
+			    offset >> PAGE_SHIFT);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
+	clflush_write32(vaddr + offset_in_page(offset),
+			lower_32_bits(target_addr),
+			eb->reloc_cache.vaddr);
+
+	if (wide) {
+		offset += sizeof(u32);
+		target_addr >>= 32;
+		wide = false;
+		goto repeat;
 	}
 
 	return target->node.start | UPDATE;
@@ -1992,7 +1643,7 @@ repeat:
 	}
 
 	/* We may process another execbuffer during the unlock... */
-	eb_release_vmas(eb, false, true);
+	eb_release_vmas(eb, false);
 	i915_gem_ww_ctx_fini(&eb->ww);
 
 	if (rq) {
@@ -2061,9 +1712,7 @@ repeat_validate:
 
 	list_for_each_entry(ev, &eb->relocs, reloc_link) {
 		if (!have_copy) {
-			pagefault_disable();
 			err = eb_relocate_vma(eb, ev);
-			pagefault_enable();
 			if (err)
 				break;
 		} else {
@@ -2096,7 +1745,7 @@ repeat_validate:
 
 err:
 	if (err == -EDEADLK) {
-		eb_release_vmas(eb, false, false);
+		eb_release_vmas(eb, false);
 		err = i915_gem_ww_ctx_backoff(&eb->ww);
 		if (!err)
 			goto repeat_validate;
@@ -2193,7 +1842,7 @@ retry:
 
 err:
 	if (err == -EDEADLK) {
-		eb_release_vmas(eb, false, false);
+		eb_release_vmas(eb, false);
 		err = i915_gem_ww_ctx_backoff(&eb->ww);
 		if (!err)
 			goto retry;
@@ -2270,7 +1919,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 
 #ifdef CONFIG_MMU_NOTIFIER
 	if (!err && (eb->args->flags & __EXEC_USERPTR_USED)) {
-		spin_lock(&eb->i915->mm.notifier_lock);
+		read_lock(&eb->i915->mm.notifier_lock);
 
 		/*
 		 * count is always at least 1, otherwise __EXEC_USERPTR_USED
@@ -2288,7 +1937,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 				break;
 		}
 
-		spin_unlock(&eb->i915->mm.notifier_lock);
+		read_unlock(&eb->i915->mm.notifier_lock);
 	}
 #endif
 
@@ -2782,7 +2431,7 @@ __free_fence_array(struct eb_fence *fences, unsigned int n)
 	while (n--) {
 		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
 		dma_fence_put(fences[n].dma_fence);
-		kfree(fences[n].chain_fence);
+		dma_fence_chain_free(fences[n].chain_fence);
 	}
 	kvfree(fences);
 }
@@ -2896,9 +2545,7 @@ add_timeline_fence_array(struct i915_execbuffer *eb,
 				return -EINVAL;
 			}
 
-			f->chain_fence =
-				kmalloc(sizeof(*f->chain_fence),
-					GFP_KERNEL);
+			f->chain_fence = dma_fence_chain_alloc();
 			if (!f->chain_fence) {
 				drm_syncobj_put(syncobj);
 				dma_fence_put(fence);
@@ -3158,8 +2805,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.exec = exec;
 	eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1);
 	eb.vma[0].vma = NULL;
-	eb.reloc_pool = eb.batch_pool = NULL;
-	eb.reloc_context = NULL;
+	eb.batch_pool = NULL;
 
 	eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
 	reloc_cache_init(&eb.reloc_cache, eb.i915);
@@ -3234,7 +2880,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	err = eb_lookup_vmas(&eb);
 	if (err) {
-		eb_release_vmas(&eb, true, true);
+		eb_release_vmas(&eb, true);
 		goto err_engine;
 	}
 
@@ -3257,9 +2903,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	batch = eb.batch->vma;
 
-	/* All GPU relocation batches must be submitted prior to the user rq */
-	GEM_BUG_ON(eb.reloc_cache.rq);
-
 	/* Allocate a request for this batch buffer nice and early. */
 	eb.request = i915_request_create(eb.context);
 	if (IS_ERR(eb.request)) {
@@ -3267,11 +2910,20 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_vma;
 	}
 
+	if (unlikely(eb.gem_context->syncobj)) {
+		struct dma_fence *fence;
+
+		fence = drm_syncobj_fence_get(eb.gem_context->syncobj);
+		err = i915_request_await_dma_fence(eb.request, fence);
+		dma_fence_put(fence);
+		if (err)
+			goto err_ext;
+	}
+
 	if (in_fence) {
 		if (args->flags & I915_EXEC_FENCE_SUBMIT)
 			err = i915_request_await_execution(eb.request,
-							   in_fence,
-							   eb.engine->bond_execute);
+							   in_fence);
 		else
 			err = i915_request_await_dma_fence(eb.request,
 							   in_fence);
@@ -3324,10 +2976,16 @@ err_request:
 			fput(out_fence->file);
 		}
 	}
+
+	if (unlikely(eb.gem_context->syncobj)) {
+		drm_syncobj_replace_fence(eb.gem_context->syncobj,
+					  &eb.request->fence);
+	}
+
 	i915_request_put(eb.request);
 
 err_vma:
-	eb_release_vmas(&eb, true, true);
+	eb_release_vmas(&eb, true);
 	if (eb.trampoline)
 		i915_vma_unpin(eb.trampoline);
 	WARN_ON(err == -EDEADLK);
@@ -3335,10 +2993,6 @@ err_vma:
 
 	if (eb.batch_pool)
 		intel_gt_buffer_pool_put(eb.batch_pool);
-	if (eb.reloc_pool)
-		intel_gt_buffer_pool_put(eb.reloc_pool);
-	if (eb.reloc_context)
-		intel_context_put(eb.reloc_context);
 err_engine:
 	eb_put_engine(&eb);
 err_context:
@@ -3452,7 +3106,3 @@ end:;
 	kvfree(exec2_list);
 	return err;
 }
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/i915_gem_execbuffer.c"
-#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index ce6b664b10aa..13b217f75055 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -177,8 +177,8 @@ i915_gem_object_create_internal(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class,
-			     I915_BO_ALLOC_STRUCT_PAGE);
+	i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class, 0);
+	obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
 
 	/*
 	 * Mark the object as volatile, such that the pages are marked as
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 3b4aa28a076d..eb345305dc52 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -4,74 +4,10 @@
  */
 
 #include "intel_memory_region.h"
-#include "intel_region_ttm.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_lmem.h"
 #include "i915_drv.h"
 
-static void lmem_put_pages(struct drm_i915_gem_object *obj,
-			   struct sg_table *pages)
-{
-	intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
-	obj->mm.dirty = false;
-	sg_free_table(pages);
-	kfree(pages);
-}
-
-static int lmem_get_pages(struct drm_i915_gem_object *obj)
-{
-	unsigned int flags;
-	struct sg_table *pages;
-
-	flags = I915_ALLOC_MIN_PAGE_SIZE;
-	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
-		flags |= I915_ALLOC_CONTIGUOUS;
-
-	obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
-							 obj->base.size,
-							 flags);
-	if (IS_ERR(obj->mm.st_mm_node))
-		return PTR_ERR(obj->mm.st_mm_node);
-
-	/* Range manager is always contigous */
-	if (obj->mm.region->is_range_manager)
-		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
-	pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
-	if (IS_ERR(pages)) {
-		intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
-		return PTR_ERR(pages);
-	}
-
-	__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
-
-	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
-		void __iomem *vaddr =
-			i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
-
-		if (!vaddr) {
-			struct sg_table *pages =
-				__i915_gem_object_unset_pages(obj);
-
-			if (!IS_ERR_OR_NULL(pages))
-				lmem_put_pages(obj, pages);
-		}
-
-		memset_io(vaddr, 0, obj->base.size);
-		io_mapping_unmap(vaddr);
-	}
-
-	return 0;
-}
-
-const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
-	.name = "i915_gem_object_lmem",
-	.flags = I915_GEM_OBJECT_HAS_IOMEM,
-
-	.get_pages = lmem_get_pages,
-	.put_pages = lmem_put_pages,
-	.release = i915_gem_object_release_memory_region,
-};
-
 void __iomem *
 i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 			    unsigned long n,
@@ -87,39 +23,91 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
 }
 
+/**
+ * i915_gem_object_is_lmem - Whether the object is resident in
+ * lmem
+ * @obj: The object to check.
+ *
+ * Even if an object is allowed to migrate and change memory region,
+ * this function checks whether it will always be present in lmem when
+ * valid *or* if that's not the case, whether it's currently resident in lmem.
+ * For migratable and evictable objects, the latter only makes sense when
+ * the object is locked.
+ *
+ * Return: Whether the object migratable but resident in lmem, or not
+ * migratable and will be present in lmem when valid.
+ */
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
-	struct intel_memory_region *mr = obj->mm.region;
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
 
+#ifdef CONFIG_LOCKDEP
+	if (i915_gem_object_migratable(obj) &&
+	    i915_gem_object_evictable(obj))
+		assert_object_held(obj);
+#endif
 	return mr && (mr->type == INTEL_MEMORY_LOCAL ||
 		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
 }
 
+/**
+ * __i915_gem_object_is_lmem - Whether the object is resident in
+ * lmem while in the fence signaling critical path.
+ * @obj: The object to check.
+ *
+ * This function is intended to be called from within the fence signaling
+ * path where the fence keeps the object from being migrated. For example
+ * during gpu reset or similar.
+ *
+ * Return: Whether the object is resident in lmem.
+ */
+bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
+{
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
+
+#ifdef CONFIG_LOCKDEP
+	GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, true));
+#endif
+	return mr && (mr->type == INTEL_MEMORY_LOCAL ||
+		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
+}
+
+/**
+ * __i915_gem_object_create_lmem_with_ps - Create lmem object and force the
+ * minimum page size for the backing pages.
+ * @i915: The i915 instance.
+ * @size: The size in bytes for the object. Note that we need to round the size
+ * up depending on the @page_size. The final object size can be fished out from
+ * the drm GEM object.
+ * @page_size: The requested minimum page size in bytes for this object. This is
+ * useful if we need something bigger than the regions min_page_size due to some
+ * hw restriction, or in some very specialised cases where it needs to be
+ * smaller, where the internal fragmentation cost is too great when rounding up
+ * the object size.
+ * @flags: The optional BO allocation flags.
+ *
+ * Note that this interface assumes you know what you are doing when forcing the
+ * @page_size. If this is smaller than the regions min_page_size then it can
+ * never be inserted into any GTT, otherwise it might lead to undefined
+ * behaviour.
+ *
+ * Return: The object pointer, which might be an ERR_PTR in the case of failure.
+ */
 struct drm_i915_gem_object *
-i915_gem_object_create_lmem(struct drm_i915_private *i915,
-			    resource_size_t size,
-			    unsigned int flags)
+__i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915,
+				      resource_size_t size,
+				      resource_size_t page_size,
+				      unsigned int flags)
 {
 	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
-					     size, flags);
+					     size, page_size, flags);
 }
 
-int __i915_gem_lmem_object_init(struct intel_memory_region *mem,
-				struct drm_i915_gem_object *obj,
-				resource_size_t size,
-				unsigned int flags)
+struct drm_i915_gem_object *
+i915_gem_object_create_lmem(struct drm_i915_private *i915,
+			    resource_size_t size,
+			    unsigned int flags)
 {
-	static struct lock_class_key lock_class;
-	struct drm_i915_private *i915 = mem->i915;
-
-	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &i915_gem_lmem_obj_ops, &lock_class, flags);
-
-	obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;
-
-	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
-
-	i915_gem_object_init_memory_region(obj, mem);
-
-	return 0;
+	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
+					     size, 0, flags);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
index fac6bc5a5ebb..4ee81fc66302 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -21,14 +21,16 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
+bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
+
+struct drm_i915_gem_object *
+__i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915,
+				      resource_size_t size,
+				      resource_size_t page_size,
+				      unsigned int flags);
 struct drm_i915_gem_object *
 i915_gem_object_create_lmem(struct drm_i915_private *i915,
 			    resource_size_t size,
 			    unsigned int flags);
 
-int __i915_gem_lmem_object_init(struct intel_memory_region *mem,
-				struct drm_i915_gem_object *obj,
-				resource_size_t size,
-				unsigned int flags);
-
 #endif /* !__I915_GEM_LMEM_H */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 215326764606..5130e8ed9564 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -19,6 +19,7 @@
 #include "i915_gem_mman.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
+#include "i915_gem_ttm.h"
 #include "i915_vma.h"
 
 static inline bool
@@ -624,6 +625,8 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
 	struct i915_mmap_offset *mmo;
 	int err;
 
+	GEM_BUG_ON(obj->ops->mmap_offset || obj->ops->mmap_ops);
+
 	mmo = lookup_mmo(obj, mmap_type);
 	if (mmo)
 		goto out;
@@ -642,7 +645,8 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
 		goto insert;
 
 	/* Attempt to reap some mmap space from dead objects */
-	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT,
+					       NULL);
 	if (err)
 		goto err;
 
@@ -666,40 +670,58 @@ err:
 }
 
 static int
-__assign_mmap_offset(struct drm_file *file,
-		     u32 handle,
+__assign_mmap_offset(struct drm_i915_gem_object *obj,
 		     enum i915_mmap_type mmap_type,
-		     u64 *offset)
+		     u64 *offset, struct drm_file *file)
 {
-	struct drm_i915_gem_object *obj;
 	struct i915_mmap_offset *mmo;
-	int err;
 
-	obj = i915_gem_object_lookup(file, handle);
-	if (!obj)
-		return -ENOENT;
+	if (i915_gem_object_never_mmap(obj))
+		return -ENODEV;
 
-	if (i915_gem_object_never_mmap(obj)) {
-		err = -ENODEV;
-		goto out;
+	if (obj->ops->mmap_offset)  {
+		if (mmap_type != I915_MMAP_TYPE_FIXED)
+			return -ENODEV;
+
+		*offset = obj->ops->mmap_offset(obj);
+		return 0;
 	}
 
+	if (mmap_type == I915_MMAP_TYPE_FIXED)
+		return -ENODEV;
+
 	if (mmap_type != I915_MMAP_TYPE_GTT &&
 	    !i915_gem_object_has_struct_page(obj) &&
-	    !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM)) {
-		err = -ENODEV;
-		goto out;
-	}
+	    !i915_gem_object_has_iomem(obj))
+		return -ENODEV;
 
 	mmo = mmap_offset_attach(obj, mmap_type, file);
-	if (IS_ERR(mmo)) {
-		err = PTR_ERR(mmo);
-		goto out;
-	}
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
 
 	*offset = drm_vma_node_offset_addr(&mmo->vma_node);
-	err = 0;
-out:
+	return 0;
+}
+
+static int
+__assign_mmap_offset_handle(struct drm_file *file,
+			    u32 handle,
+			    enum i915_mmap_type mmap_type,
+			    u64 *offset)
+{
+	struct drm_i915_gem_object *obj;
+	int err;
+
+	obj = i915_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	err = i915_gem_object_lock_interruptible(obj, NULL);
+	if (err)
+		goto out_put;
+	err = __assign_mmap_offset(obj, mmap_type, offset, file);
+	i915_gem_object_unlock(obj);
+out_put:
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -712,14 +734,16 @@ i915_gem_dumb_mmap_offset(struct drm_file *file,
 {
 	enum i915_mmap_type mmap_type;
 
-	if (boot_cpu_has(X86_FEATURE_PAT))
+	if (HAS_LMEM(to_i915(dev)))
+		mmap_type = I915_MMAP_TYPE_FIXED;
+	else if (boot_cpu_has(X86_FEATURE_PAT))
 		mmap_type = I915_MMAP_TYPE_WC;
 	else if (!i915_ggtt_has_aperture(&to_i915(dev)->ggtt))
 		return -ENODEV;
 	else
 		mmap_type = I915_MMAP_TYPE_GTT;
 
-	return __assign_mmap_offset(file, handle, mmap_type, offset);
+	return __assign_mmap_offset_handle(file, handle, mmap_type, offset);
 }
 
 /**
@@ -783,11 +807,15 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
 		type = I915_MMAP_TYPE_UC;
 		break;
 
+	case I915_MMAP_OFFSET_FIXED:
+		type = I915_MMAP_TYPE_FIXED;
+		break;
+
 	default:
 		return -EINVAL;
 	}
 
-	return __assign_mmap_offset(file, args->handle, type, &args->offset);
+	return __assign_mmap_offset_handle(file, args->handle, type, &args->offset);
 }
 
 static void vm_open(struct vm_area_struct *vma)
@@ -891,8 +919,18 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		 * destroyed and will be invalid when the vma manager lock
 		 * is released.
 		 */
-		mmo = container_of(node, struct i915_mmap_offset, vma_node);
-		obj = i915_gem_object_get_rcu(mmo->obj);
+		if (!node->driver_private) {
+			mmo = container_of(node, struct i915_mmap_offset, vma_node);
+			obj = i915_gem_object_get_rcu(mmo->obj);
+
+			GEM_BUG_ON(obj && obj->ops->mmap_ops);
+		} else {
+			obj = i915_gem_object_get_rcu
+				(container_of(node, struct drm_i915_gem_object,
+					      base.vma_node));
+
+			GEM_BUG_ON(obj && !obj->ops->mmap_ops);
+		}
 	}
 	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
 	rcu_read_unlock();
@@ -913,8 +951,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return PTR_ERR(anon);
 	}
 
-	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_private_data = mmo;
+	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
 
 	/*
 	 * We keep the ref on mmo->obj, not vm_file, but we require
@@ -928,6 +965,15 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	/* Drop the initial creation reference, the vma is now holding one. */
 	fput(anon);
 
+	if (obj->ops->mmap_ops) {
+		vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = obj->ops->mmap_ops;
+		vma->vm_private_data = node->driver_private;
+		return 0;
+	}
+
+	vma->vm_private_data = mmo;
+
 	switch (mmo->mmap_type) {
 	case I915_MMAP_TYPE_WC:
 		vma->vm_page_prot =
@@ -935,6 +981,9 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		vma->vm_ops = &vm_ops_cpu;
 		break;
 
+	case I915_MMAP_TYPE_FIXED:
+		GEM_WARN_ON(1);
+		fallthrough;
 	case I915_MMAP_TYPE_WB:
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 		vma->vm_ops = &vm_ops_cpu;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 5706d471692d..6fb9afb65034 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -30,14 +30,10 @@
 #include "i915_gem_context.h"
 #include "i915_gem_mman.h"
 #include "i915_gem_object.h"
-#include "i915_globals.h"
 #include "i915_memcpy.h"
 #include "i915_trace.h"
 
-static struct i915_global_object {
-	struct i915_global base;
-	struct kmem_cache *slab_objects;
-} global;
+static struct kmem_cache *slab_objects;
 
 static const struct drm_gem_object_funcs i915_gem_object_funcs;
 
@@ -45,7 +41,7 @@ struct drm_i915_gem_object *i915_gem_object_alloc(void)
 {
 	struct drm_i915_gem_object *obj;
 
-	obj = kmem_cache_zalloc(global.slab_objects, GFP_KERNEL);
+	obj = kmem_cache_zalloc(slab_objects, GFP_KERNEL);
 	if (!obj)
 		return NULL;
 	obj->base.funcs = &i915_gem_object_funcs;
@@ -55,7 +51,7 @@ struct drm_i915_gem_object *i915_gem_object_alloc(void)
 
 void i915_gem_object_free(struct drm_i915_gem_object *obj)
 {
-	return kmem_cache_free(global.slab_objects, obj);
+	return kmem_cache_free(slab_objects, obj);
 }
 
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
@@ -172,7 +168,7 @@ static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *f
 	}
 }
 
-static void __i915_gem_free_object_rcu(struct rcu_head *head)
+void __i915_gem_free_object_rcu(struct rcu_head *head)
 {
 	struct drm_i915_gem_object *obj =
 		container_of(head, typeof(*obj), rcu);
@@ -208,59 +204,69 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj)
 	}
 }
 
-static void __i915_gem_free_objects(struct drm_i915_private *i915,
-				    struct llist_node *freed)
+void __i915_gem_free_object(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_gem_object *obj, *on;
+	trace_i915_gem_object_destroy(obj);
 
-	llist_for_each_entry_safe(obj, on, freed, freed) {
-		trace_i915_gem_object_destroy(obj);
+	if (!list_empty(&obj->vma.list)) {
+		struct i915_vma *vma;
+
+		/*
+		 * Note that the vma keeps an object reference while
+		 * it is active, so it *should* not sleep while we
+		 * destroy it. Our debug code errs insits it *might*.
+		 * For the moment, play along.
+		 */
+		spin_lock(&obj->vma.lock);
+		while ((vma = list_first_entry_or_null(&obj->vma.list,
+						       struct i915_vma,
+						       obj_link))) {
+			GEM_BUG_ON(vma->obj != obj);
+			spin_unlock(&obj->vma.lock);
 
-		if (!list_empty(&obj->vma.list)) {
-			struct i915_vma *vma;
+			__i915_vma_put(vma);
 
-			/*
-			 * Note that the vma keeps an object reference while
-			 * it is active, so it *should* not sleep while we
-			 * destroy it. Our debug code errs insits it *might*.
-			 * For the moment, play along.
-			 */
 			spin_lock(&obj->vma.lock);
-			while ((vma = list_first_entry_or_null(&obj->vma.list,
-							       struct i915_vma,
-							       obj_link))) {
-				GEM_BUG_ON(vma->obj != obj);
-				spin_unlock(&obj->vma.lock);
+		}
+		spin_unlock(&obj->vma.lock);
+	}
 
-				__i915_vma_put(vma);
+	__i915_gem_object_free_mmaps(obj);
 
-				spin_lock(&obj->vma.lock);
-			}
-			spin_unlock(&obj->vma.lock);
-		}
+	GEM_BUG_ON(!list_empty(&obj->lut_list));
 
-		__i915_gem_object_free_mmaps(obj);
+	atomic_set(&obj->mm.pages_pin_count, 0);
+	__i915_gem_object_put_pages(obj);
+	GEM_BUG_ON(i915_gem_object_has_pages(obj));
+	bitmap_free(obj->bit_17);
 
-		GEM_BUG_ON(!list_empty(&obj->lut_list));
+	if (obj->base.import_attach)
+		drm_prime_gem_destroy(&obj->base, NULL);
 
-		atomic_set(&obj->mm.pages_pin_count, 0);
-		__i915_gem_object_put_pages(obj);
-		GEM_BUG_ON(i915_gem_object_has_pages(obj));
-		bitmap_free(obj->bit_17);
+	drm_gem_free_mmap_offset(&obj->base);
 
-		if (obj->base.import_attach)
-			drm_prime_gem_destroy(&obj->base, NULL);
+	if (obj->ops->release)
+		obj->ops->release(obj);
 
-		drm_gem_free_mmap_offset(&obj->base);
+	if (obj->mm.n_placements > 1)
+		kfree(obj->mm.placements);
 
-		if (obj->ops->release)
-			obj->ops->release(obj);
+	if (obj->shares_resv_from)
+		i915_vm_resv_put(obj->shares_resv_from);
+}
 
-		if (obj->mm.n_placements > 1)
-			kfree(obj->mm.placements);
+static void __i915_gem_free_objects(struct drm_i915_private *i915,
+				    struct llist_node *freed)
+{
+	struct drm_i915_gem_object *obj, *on;
 
-		if (obj->shares_resv_from)
-			i915_vm_resv_put(obj->shares_resv_from);
+	llist_for_each_entry_safe(obj, on, freed, freed) {
+		might_sleep();
+		if (obj->ops->delayed_free) {
+			obj->ops->delayed_free(obj);
+			continue;
+		}
+		__i915_gem_free_object(obj);
 
 		/* But keep the pointer alive for RCU-protected lookups */
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
@@ -318,6 +324,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	 * worker and performing frees directly from subsequent allocations for
 	 * crude but effective memory throttling.
 	 */
+
 	if (llist_add(&obj->freed, &i915->mm.free_list))
 		queue_work(i915->wq, &i915->mm.free_work);
 }
@@ -410,34 +417,254 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset,
 	return 0;
 }
 
-void i915_gem_init__objects(struct drm_i915_private *i915)
+/**
+ * i915_gem_object_evictable - Whether object is likely evictable after unbind.
+ * @obj: The object to check
+ *
+ * This function checks whether the object is likely unvictable after unbind.
+ * If the object is not locked when checking, the result is only advisory.
+ * If the object is locked when checking, and the function returns true,
+ * then an eviction should indeed be possible. But since unlocked vma
+ * unpinning and unbinding is currently possible, the object can actually
+ * become evictable even if this function returns false.
+ *
+ * Return: true if the object may be evictable. False otherwise.
+ */
+bool i915_gem_object_evictable(struct drm_i915_gem_object *obj)
 {
-	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);
+	struct i915_vma *vma;
+	int pin_count = atomic_read(&obj->mm.pages_pin_count);
+
+	if (!pin_count)
+		return true;
+
+	spin_lock(&obj->vma.lock);
+	list_for_each_entry(vma, &obj->vma.list, obj_link) {
+		if (i915_vma_is_pinned(vma)) {
+			spin_unlock(&obj->vma.lock);
+			return false;
+		}
+		if (atomic_read(&vma->pages_count))
+			pin_count--;
+	}
+	spin_unlock(&obj->vma.lock);
+	GEM_WARN_ON(pin_count < 0);
+
+	return pin_count == 0;
+}
+
+/**
+ * i915_gem_object_migratable - Whether the object is migratable out of the
+ * current region.
+ * @obj: Pointer to the object.
+ *
+ * Return: Whether the object is allowed to be resident in other
+ * regions than the current while pages are present.
+ */
+bool i915_gem_object_migratable(struct drm_i915_gem_object *obj)
+{
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
+
+	if (!mr)
+		return false;
+
+	return obj->mm.n_placements > 1;
 }
 
-static void i915_global_objects_shrink(void)
+/**
+ * i915_gem_object_has_struct_page - Whether the object is page-backed
+ * @obj: The object to query.
+ *
+ * This function should only be called while the object is locked or pinned,
+ * otherwise the page backing may change under the caller.
+ *
+ * Return: True if page-backed, false otherwise.
+ */
+bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 {
-	kmem_cache_shrink(global.slab_objects);
+#ifdef CONFIG_LOCKDEP
+	if (IS_DGFX(to_i915(obj->base.dev)) &&
+	    i915_gem_object_evictable((void __force *)obj))
+		assert_object_held_shared(obj);
+#endif
+	return obj->mem_flags & I915_BO_FLAG_STRUCT_PAGE;
 }
 
-static void i915_global_objects_exit(void)
+/**
+ * i915_gem_object_has_iomem - Whether the object is iomem-backed
+ * @obj: The object to query.
+ *
+ * This function should only be called while the object is locked or pinned,
+ * otherwise the iomem backing may change under the caller.
+ *
+ * Return: True if iomem-backed, false otherwise.
+ */
+bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj)
 {
-	kmem_cache_destroy(global.slab_objects);
+#ifdef CONFIG_LOCKDEP
+	if (IS_DGFX(to_i915(obj->base.dev)) &&
+	    i915_gem_object_evictable((void __force *)obj))
+		assert_object_held_shared(obj);
+#endif
+	return obj->mem_flags & I915_BO_FLAG_IOMEM;
 }
 
-static struct i915_global_object global = { {
-	.shrink = i915_global_objects_shrink,
-	.exit = i915_global_objects_exit,
-} };
+/**
+ * i915_gem_object_can_migrate - Whether an object likely can be migrated
+ *
+ * @obj: The object to migrate
+ * @id: The region intended to migrate to
+ *
+ * Check whether the object backend supports migration to the
+ * given region. Note that pinning may affect the ability to migrate as
+ * returned by this function.
+ *
+ * This function is primarily intended as a helper for checking the
+ * possibility to migrate objects and might be slightly less permissive
+ * than i915_gem_object_migrate() when it comes to objects with the
+ * I915_BO_ALLOC_USER flag set.
+ *
+ * Return: true if migration is possible, false otherwise.
+ */
+bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj,
+				 enum intel_region_id id)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	unsigned int num_allowed = obj->mm.n_placements;
+	struct intel_memory_region *mr;
+	unsigned int i;
+
+	GEM_BUG_ON(id >= INTEL_REGION_UNKNOWN);
+	GEM_BUG_ON(obj->mm.madv != I915_MADV_WILLNEED);
+
+	mr = i915->mm.regions[id];
+	if (!mr)
+		return false;
+
+	if (obj->mm.region == mr)
+		return true;
+
+	if (!i915_gem_object_evictable(obj))
+		return false;
+
+	if (!obj->ops->migrate)
+		return false;
+
+	if (!(obj->flags & I915_BO_ALLOC_USER))
+		return true;
+
+	if (num_allowed == 0)
+		return false;
+
+	for (i = 0; i < num_allowed; ++i) {
+		if (mr == obj->mm.placements[i])
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * i915_gem_object_migrate - Migrate an object to the desired region id
+ * @obj: The object to migrate.
+ * @ww: An optional struct i915_gem_ww_ctx. If NULL, the backend may
+ * not be successful in evicting other objects to make room for this object.
+ * @id: The region id to migrate to.
+ *
+ * Attempt to migrate the object to the desired memory region. The
+ * object backend must support migration and the object may not be
+ * pinned, (explicitly pinned pages or pinned vmas). The object must
+ * be locked.
+ * On successful completion, the object will have pages pointing to
+ * memory in the new region, but an async migration task may not have
+ * completed yet, and to accomplish that, i915_gem_object_wait_migration()
+ * must be called.
+ *
+ * Note: the @ww parameter is not used yet, but included to make sure
+ * callers put some effort into obtaining a valid ww ctx if one is
+ * available.
+ *
+ * Return: 0 on success. Negative error code on failure. In particular may
+ * return -ENXIO on lack of region space, -EDEADLK for deadlock avoidance
+ * if @ww is set, -EINTR or -ERESTARTSYS if signal pending, and
+ * -EBUSY if the object is pinned.
+ */
+int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
+			    struct i915_gem_ww_ctx *ww,
+			    enum intel_region_id id)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_memory_region *mr;
+
+	GEM_BUG_ON(id >= INTEL_REGION_UNKNOWN);
+	GEM_BUG_ON(obj->mm.madv != I915_MADV_WILLNEED);
+	assert_object_held(obj);
+
+	mr = i915->mm.regions[id];
+	GEM_BUG_ON(!mr);
+
+	if (!i915_gem_object_can_migrate(obj, id))
+		return -EINVAL;
+
+	if (!obj->ops->migrate) {
+		if (GEM_WARN_ON(obj->mm.region != mr))
+			return -EINVAL;
+		return 0;
+	}
+
+	return obj->ops->migrate(obj, mr);
+}
+
+/**
+ * i915_gem_object_placement_possible - Check whether the object can be
+ * placed at certain memory type
+ * @obj: Pointer to the object
+ * @type: The memory type to check
+ *
+ * Return: True if the object can be placed in @type. False otherwise.
+ */
+bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj,
+					enum intel_memory_type type)
+{
+	unsigned int i;
+
+	if (!obj->mm.n_placements) {
+		switch (type) {
+		case INTEL_MEMORY_LOCAL:
+			return i915_gem_object_has_iomem(obj);
+		case INTEL_MEMORY_SYSTEM:
+			return i915_gem_object_has_pages(obj);
+		default:
+			/* Ignore stolen for now */
+			GEM_BUG_ON(1);
+			return false;
+		}
+	}
+
+	for (i = 0; i < obj->mm.n_placements; i++) {
+		if (obj->mm.placements[i]->type == type)
+			return true;
+	}
+
+	return false;
+}
+
+void i915_gem_init__objects(struct drm_i915_private *i915)
+{
+	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);
+}
+
+void i915_objects_module_exit(void)
+{
+	kmem_cache_destroy(slab_objects);
+}
 
-int __init i915_global_objects_init(void)
+int __init i915_objects_module_init(void)
 {
-	global.slab_objects =
-		KMEM_CACHE(drm_i915_gem_object, SLAB_HWCACHE_ALIGN);
-	if (!global.slab_objects)
+	slab_objects = KMEM_CACHE(drm_i915_gem_object, SLAB_HWCACHE_ALIGN);
+	if (!slab_objects)
 		return -ENOMEM;
 
-	i915_global_register(&global.base);
 	return 0;
 }
 
@@ -450,6 +677,7 @@ static const struct drm_gem_object_funcs i915_gem_object_funcs = {
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/huge_gem_object.c"
 #include "selftests/huge_pages.c"
+#include "selftests/i915_gem_migrate.c"
 #include "selftests/i915_gem_object.c"
 #include "selftests/i915_gem_coherency.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 7c0eb425cb3b..48112b9d76df 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -12,10 +12,14 @@
 #include <drm/drm_device.h>
 
 #include "display/intel_frontbuffer.h"
+#include "intel_memory_region.h"
 #include "i915_gem_object_types.h"
 #include "i915_gem_gtt.h"
+#include "i915_gem_ww.h"
 #include "i915_vma_types.h"
 
+enum intel_region_id;
+
 /*
  * XXX: There is a prevalence of the assumption that we fit the
  * object's page count inside a 32bit _signed_ variable. Let's document
@@ -44,6 +48,9 @@ static inline bool i915_gem_object_size_2big(u64 size)
 
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
+void i915_objects_module_exit(void);
+int i915_objects_module_init(void);
+
 struct drm_i915_gem_object *i915_gem_object_alloc(void);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 
@@ -57,6 +64,10 @@ i915_gem_object_create_shmem(struct drm_i915_private *i915,
 struct drm_i915_gem_object *
 i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 				       const void *data, resource_size_t size);
+struct drm_i915_gem_object *
+__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size,
+			      struct intel_memory_region **placements,
+			      unsigned int n_placements);
 
 extern const struct drm_i915_gem_object_ops i915_gem_shmem_ops;
 
@@ -147,7 +158,7 @@ i915_gem_object_put(struct drm_i915_gem_object *obj)
 /*
  * If more than one potential simultaneous locker, assert held.
  */
-static inline void assert_object_held_shared(struct drm_i915_gem_object *obj)
+static inline void assert_object_held_shared(const struct drm_i915_gem_object *obj)
 {
 	/*
 	 * Note mm list lookup is protected by
@@ -169,13 +180,17 @@ static inline int __i915_gem_object_lock(struct drm_i915_gem_object *obj,
 	else
 		ret = dma_resv_lock(obj->base.resv, ww ? &ww->ctx : NULL);
 
-	if (!ret && ww)
+	if (!ret && ww) {
+		i915_gem_object_get(obj);
 		list_add_tail(&obj->obj_link, &ww->obj_list);
+	}
 	if (ret == -EALREADY)
 		ret = 0;
 
-	if (ret == -EDEADLK)
+	if (ret == -EDEADLK) {
+		i915_gem_object_get(obj);
 		ww->contended = obj;
+	}
 
 	return ret;
 }
@@ -200,6 +215,9 @@ static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj)
 
 static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj)
 {
+	if (obj->ops->adjust_lru)
+		obj->ops->adjust_lru(obj);
+
 	dma_resv_unlock(obj->base.resv);
 }
 
@@ -258,17 +276,9 @@ i915_gem_object_type_has(const struct drm_i915_gem_object *obj,
 	return obj->ops->flags & flags;
 }
 
-static inline bool
-i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
-{
-	return obj->flags & I915_BO_ALLOC_STRUCT_PAGE;
-}
+bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj);
 
-static inline bool
-i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj)
-{
-	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM);
-}
+bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj);
 
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
@@ -339,22 +349,22 @@ struct scatterlist *
 __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 			 struct i915_gem_object_page_iter *iter,
 			 unsigned int n,
-			 unsigned int *offset, bool allow_alloc);
+			 unsigned int *offset, bool dma);
 
 static inline struct scatterlist *
 i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 		       unsigned int n,
-		       unsigned int *offset, bool allow_alloc)
+		       unsigned int *offset)
 {
-	return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, allow_alloc);
+	return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, false);
 }
 
 static inline struct scatterlist *
 i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj,
 			   unsigned int n,
-			   unsigned int *offset, bool allow_alloc)
+			   unsigned int *offset)
 {
-	return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, allow_alloc);
+	return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, true);
 }
 
 struct page *
@@ -587,6 +597,27 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset,
 
 bool i915_gem_object_is_shmem(const struct drm_i915_gem_object *obj);
 
+void __i915_gem_free_object_rcu(struct rcu_head *head);
+
+void __i915_gem_free_object(struct drm_i915_gem_object *obj);
+
+bool i915_gem_object_evictable(struct drm_i915_gem_object *obj);
+
+bool i915_gem_object_migratable(struct drm_i915_gem_object *obj);
+
+int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
+			    struct i915_gem_ww_ctx *ww,
+			    enum intel_region_id id);
+
+bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj,
+				 enum intel_region_id id);
+
+int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj,
+				   unsigned int flags);
+
+bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj,
+					enum intel_memory_type type);
+
 #ifdef CONFIG_MMU_NOTIFIER
 static inline bool
 i915_gem_object_is_userptr(struct drm_i915_gem_object *obj)
@@ -596,14 +627,12 @@ i915_gem_object_is_userptr(struct drm_i915_gem_object *obj)
 
 int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj);
 int i915_gem_object_userptr_submit_done(struct drm_i915_gem_object *obj);
-void i915_gem_object_userptr_submit_fini(struct drm_i915_gem_object *obj);
 int i915_gem_object_userptr_validate(struct drm_i915_gem_object *obj);
 #else
 static inline bool i915_gem_object_is_userptr(struct drm_i915_gem_object *obj) { return false; }
 
 static inline int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj) { GEM_BUG_ON(1); return -ENODEV; }
 static inline int i915_gem_object_userptr_submit_done(struct drm_i915_gem_object *obj) { GEM_BUG_ON(1); return -ENODEV; }
-static inline void i915_gem_object_userptr_submit_fini(struct drm_i915_gem_object *obj) { GEM_BUG_ON(1); }
 static inline int i915_gem_object_userptr_validate(struct drm_i915_gem_object *obj) { GEM_BUG_ON(1); return -ENODEV; }
 
 #endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
deleted file mode 100644
index 3e28c68fda3e..000000000000
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ /dev/null
@@ -1,461 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include "i915_drv.h"
-#include "gt/intel_context.h"
-#include "gt/intel_engine_pm.h"
-#include "gt/intel_gpu_commands.h"
-#include "gt/intel_gt.h"
-#include "gt/intel_gt_buffer_pool.h"
-#include "gt/intel_ring.h"
-#include "i915_gem_clflush.h"
-#include "i915_gem_object_blt.h"
-
-struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
-					 struct i915_vma *vma,
-					 struct i915_gem_ww_ctx *ww,
-					 u32 value)
-{
-	struct drm_i915_private *i915 = ce->vm->i915;
-	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
-	struct intel_gt_buffer_pool_node *pool;
-	struct i915_vma *batch;
-	u64 offset;
-	u64 count;
-	u64 rem;
-	u32 size;
-	u32 *cmd;
-	int err;
-
-	GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
-	intel_engine_pm_get(ce->engine);
-
-	count = div_u64(round_up(vma->size, block_size), block_size);
-	size = (1 + 8 * count) * sizeof(u32);
-	size = round_up(size, PAGE_SIZE);
-	pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
-	if (IS_ERR(pool)) {
-		err = PTR_ERR(pool);
-		goto out_pm;
-	}
-
-	err = i915_gem_object_lock(pool->obj, ww);
-	if (err)
-		goto out_put;
-
-	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put;
-	}
-
-	err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out_put;
-
-	/* we pinned the pool, mark it as such */
-	intel_gt_buffer_pool_mark_used(pool);
-
-	cmd = i915_gem_object_pin_map(pool->obj, pool->type);
-	if (IS_ERR(cmd)) {
-		err = PTR_ERR(cmd);
-		goto out_unpin;
-	}
-
-	rem = vma->size;
-	offset = vma->node.start;
-
-	do {
-		u32 size = min_t(u64, rem, block_size);
-
-		GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
-
-		if (GRAPHICS_VER(i915) >= 8) {
-			*cmd++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2);
-			*cmd++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
-			*cmd++ = 0;
-			*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
-			*cmd++ = lower_32_bits(offset);
-			*cmd++ = upper_32_bits(offset);
-			*cmd++ = value;
-		} else {
-			*cmd++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
-			*cmd++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
-			*cmd++ = 0;
-			*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
-			*cmd++ = offset;
-			*cmd++ = value;
-		}
-
-		/* Allow ourselves to be preempted in between blocks. */
-		*cmd++ = MI_ARB_CHECK;
-
-		offset += size;
-		rem -= size;
-	} while (rem);
-
-	*cmd = MI_BATCH_BUFFER_END;
-
-	i915_gem_object_flush_map(pool->obj);
-	i915_gem_object_unpin_map(pool->obj);
-
-	intel_gt_chipset_flush(ce->vm->gt);
-
-	batch->private = pool;
-	return batch;
-
-out_unpin:
-	i915_vma_unpin(batch);
-out_put:
-	intel_gt_buffer_pool_put(pool);
-out_pm:
-	intel_engine_pm_put(ce->engine);
-	return ERR_PTR(err);
-}
-
-int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq)
-{
-	int err;
-
-	err = i915_request_await_object(rq, vma->obj, false);
-	if (err == 0)
-		err = i915_vma_move_to_active(vma, rq, 0);
-	if (unlikely(err))
-		return err;
-
-	return intel_gt_buffer_pool_mark_active(vma->private, rq);
-}
-
-void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma)
-{
-	i915_vma_unpin(vma);
-	intel_gt_buffer_pool_put(vma->private);
-	intel_engine_pm_put(ce->engine);
-}
-
-static int
-move_obj_to_gpu(struct drm_i915_gem_object *obj,
-		struct i915_request *rq,
-		bool write)
-{
-	if (obj->cache_dirty & ~obj->cache_coherent)
-		i915_gem_clflush_object(obj, 0);
-
-	return i915_request_await_object(rq, obj, write);
-}
-
-int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
-			     struct intel_context *ce,
-			     u32 value)
-{
-	struct i915_gem_ww_ctx ww;
-	struct i915_request *rq;
-	struct i915_vma *batch;
-	struct i915_vma *vma;
-	int err;
-
-	vma = i915_vma_instance(obj, ce->vm, NULL);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	i915_gem_ww_ctx_init(&ww, true);
-	intel_engine_pm_get(ce->engine);
-retry:
-	err = i915_gem_object_lock(obj, &ww);
-	if (err)
-		goto out;
-
-	err = intel_context_pin_ww(ce, &ww);
-	if (err)
-		goto out;
-
-	err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
-	if (err)
-		goto out_ctx;
-
-	batch = intel_emit_vma_fill_blt(ce, vma, &ww, value);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_vma;
-	}
-
-	rq = i915_request_create(ce);
-	if (IS_ERR(rq)) {
-		err = PTR_ERR(rq);
-		goto out_batch;
-	}
-
-	err = intel_emit_vma_mark_active(batch, rq);
-	if (unlikely(err))
-		goto out_request;
-
-	err = move_obj_to_gpu(vma->obj, rq, true);
-	if (err == 0)
-		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	if (unlikely(err))
-		goto out_request;
-
-	if (ce->engine->emit_init_breadcrumb)
-		err = ce->engine->emit_init_breadcrumb(rq);
-
-	if (likely(!err))
-		err = ce->engine->emit_bb_start(rq,
-						batch->node.start,
-						batch->node.size,
-						0);
-out_request:
-	if (unlikely(err))
-		i915_request_set_error_once(rq, err);
-
-	i915_request_add(rq);
-out_batch:
-	intel_emit_vma_release(ce, batch);
-out_vma:
-	i915_vma_unpin(vma);
-out_ctx:
-	intel_context_unpin(ce);
-out:
-	if (err == -EDEADLK) {
-		err = i915_gem_ww_ctx_backoff(&ww);
-		if (!err)
-			goto retry;
-	}
-	i915_gem_ww_ctx_fini(&ww);
-	intel_engine_pm_put(ce->engine);
-	return err;
-}
-
-/* Wa_1209644611:icl,ehl */
-static bool wa_1209644611_applies(struct drm_i915_private *i915, u32 size)
-{
-	u32 height = size >> PAGE_SHIFT;
-
-	if (GRAPHICS_VER(i915) != 11)
-		return false;
-
-	return height % 4 == 3 && height <= 8;
-}
-
-struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
-					 struct i915_gem_ww_ctx *ww,
-					 struct i915_vma *src,
-					 struct i915_vma *dst)
-{
-	struct drm_i915_private *i915 = ce->vm->i915;
-	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
-	struct intel_gt_buffer_pool_node *pool;
-	struct i915_vma *batch;
-	u64 src_offset, dst_offset;
-	u64 count, rem;
-	u32 size, *cmd;
-	int err;
-
-	GEM_BUG_ON(src->size != dst->size);
-
-	GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
-	intel_engine_pm_get(ce->engine);
-
-	count = div_u64(round_up(dst->size, block_size), block_size);
-	size = (1 + 11 * count) * sizeof(u32);
-	size = round_up(size, PAGE_SIZE);
-	pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
-	if (IS_ERR(pool)) {
-		err = PTR_ERR(pool);
-		goto out_pm;
-	}
-
-	err = i915_gem_object_lock(pool->obj, ww);
-	if (err)
-		goto out_put;
-
-	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put;
-	}
-
-	err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out_put;
-
-	/* we pinned the pool, mark it as such */
-	intel_gt_buffer_pool_mark_used(pool);
-
-	cmd = i915_gem_object_pin_map(pool->obj, pool->type);
-	if (IS_ERR(cmd)) {
-		err = PTR_ERR(cmd);
-		goto out_unpin;
-	}
-
-	rem = src->size;
-	src_offset = src->node.start;
-	dst_offset = dst->node.start;
-
-	do {
-		size = min_t(u64, rem, block_size);
-		GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
-
-		if (GRAPHICS_VER(i915) >= 9 &&
-		    !wa_1209644611_applies(i915, size)) {
-			*cmd++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2);
-			*cmd++ = BLT_DEPTH_32 | PAGE_SIZE;
-			*cmd++ = 0;
-			*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
-			*cmd++ = lower_32_bits(dst_offset);
-			*cmd++ = upper_32_bits(dst_offset);
-			*cmd++ = 0;
-			*cmd++ = PAGE_SIZE;
-			*cmd++ = lower_32_bits(src_offset);
-			*cmd++ = upper_32_bits(src_offset);
-		} else if (GRAPHICS_VER(i915) >= 8) {
-			*cmd++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2);
-			*cmd++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
-			*cmd++ = 0;
-			*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
-			*cmd++ = lower_32_bits(dst_offset);
-			*cmd++ = upper_32_bits(dst_offset);
-			*cmd++ = 0;
-			*cmd++ = PAGE_SIZE;
-			*cmd++ = lower_32_bits(src_offset);
-			*cmd++ = upper_32_bits(src_offset);
-		} else {
-			*cmd++ = SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
-			*cmd++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
-			*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE;
-			*cmd++ = dst_offset;
-			*cmd++ = PAGE_SIZE;
-			*cmd++ = src_offset;
-		}
-
-		/* Allow ourselves to be preempted in between blocks. */
-		*cmd++ = MI_ARB_CHECK;
-
-		src_offset += size;
-		dst_offset += size;
-		rem -= size;
-	} while (rem);
-
-	*cmd = MI_BATCH_BUFFER_END;
-
-	i915_gem_object_flush_map(pool->obj);
-	i915_gem_object_unpin_map(pool->obj);
-
-	intel_gt_chipset_flush(ce->vm->gt);
-	batch->private = pool;
-	return batch;
-
-out_unpin:
-	i915_vma_unpin(batch);
-out_put:
-	intel_gt_buffer_pool_put(pool);
-out_pm:
-	intel_engine_pm_put(ce->engine);
-	return ERR_PTR(err);
-}
-
-int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
-			     struct drm_i915_gem_object *dst,
-			     struct intel_context *ce)
-{
-	struct i915_address_space *vm = ce->vm;
-	struct i915_vma *vma[2], *batch;
-	struct i915_gem_ww_ctx ww;
-	struct i915_request *rq;
-	int err, i;
-
-	vma[0] = i915_vma_instance(src, vm, NULL);
-	if (IS_ERR(vma[0]))
-		return PTR_ERR(vma[0]);
-
-	vma[1] = i915_vma_instance(dst, vm, NULL);
-	if (IS_ERR(vma[1]))
-		return PTR_ERR(vma[1]);
-
-	i915_gem_ww_ctx_init(&ww, true);
-	intel_engine_pm_get(ce->engine);
-retry:
-	err = i915_gem_object_lock(src, &ww);
-	if (!err)
-		err = i915_gem_object_lock(dst, &ww);
-	if (!err)
-		err = intel_context_pin_ww(ce, &ww);
-	if (err)
-		goto out;
-
-	err = i915_vma_pin_ww(vma[0], &ww, 0, 0, PIN_USER);
-	if (err)
-		goto out_ctx;
-
-	err = i915_vma_pin_ww(vma[1], &ww, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out_unpin_src;
-
-	batch = intel_emit_vma_copy_blt(ce, &ww, vma[0], vma[1]);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_unpin_dst;
-	}
-
-	rq = i915_request_create(ce);
-	if (IS_ERR(rq)) {
-		err = PTR_ERR(rq);
-		goto out_batch;
-	}
-
-	err = intel_emit_vma_mark_active(batch, rq);
-	if (unlikely(err))
-		goto out_request;
-
-	for (i = 0; i < ARRAY_SIZE(vma); i++) {
-		err = move_obj_to_gpu(vma[i]->obj, rq, i);
-		if (unlikely(err))
-			goto out_request;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(vma); i++) {
-		unsigned int flags = i ? EXEC_OBJECT_WRITE : 0;
-
-		err = i915_vma_move_to_active(vma[i], rq, flags);
-		if (unlikely(err))
-			goto out_request;
-	}
-
-	if (rq->engine->emit_init_breadcrumb) {
-		err = rq->engine->emit_init_breadcrumb(rq);
-		if (unlikely(err))
-			goto out_request;
-	}
-
-	err = rq->engine->emit_bb_start(rq,
-					batch->node.start, batch->node.size,
-					0);
-
-out_request:
-	if (unlikely(err))
-		i915_request_set_error_once(rq, err);
-
-	i915_request_add(rq);
-out_batch:
-	intel_emit_vma_release(ce, batch);
-out_unpin_dst:
-	i915_vma_unpin(vma[1]);
-out_unpin_src:
-	i915_vma_unpin(vma[0]);
-out_ctx:
-	intel_context_unpin(ce);
-out:
-	if (err == -EDEADLK) {
-		err = i915_gem_ww_ctx_backoff(&ww);
-		if (!err)
-			goto retry;
-	}
-	i915_gem_ww_ctx_fini(&ww);
-	intel_engine_pm_put(ce->engine);
-	return err;
-}
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/i915_gem_object_blt.c"
-#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
deleted file mode 100644
index 2409fdcccf0e..000000000000
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#ifndef __I915_GEM_OBJECT_BLT_H__
-#define __I915_GEM_OBJECT_BLT_H__
-
-#include <linux/types.h>
-
-#include "gt/intel_context.h"
-#include "gt/intel_engine_pm.h"
-#include "i915_vma.h"
-
-struct drm_i915_gem_object;
-struct i915_gem_ww_ctx;
-
-struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
-					 struct i915_vma *vma,
-					 struct i915_gem_ww_ctx *ww,
-					 u32 value);
-
-struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
-					 struct i915_gem_ww_ctx *ww,
-					 struct i915_vma *src,
-					 struct i915_vma *dst);
-
-int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq);
-void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma);
-
-int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
-			     struct intel_context *ce,
-			     u32 value);
-
-int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
-			     struct drm_i915_gem_object *dst,
-			     struct intel_context *ce);
-
-#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index d047ea126029..2471f36aaff3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -18,6 +18,7 @@
 
 struct drm_i915_gem_object;
 struct intel_fronbuffer;
+struct intel_memory_region;
 
 /*
  * struct i915_lut_handle tracks the fast lookups from handle to vma used
@@ -33,10 +34,9 @@ struct i915_lut_handle {
 
 struct drm_i915_gem_object_ops {
 	unsigned int flags;
-#define I915_GEM_OBJECT_HAS_IOMEM	BIT(1)
-#define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(2)
-#define I915_GEM_OBJECT_IS_PROXY	BIT(3)
-#define I915_GEM_OBJECT_NO_MMAP		BIT(4)
+#define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
+#define I915_GEM_OBJECT_IS_PROXY	BIT(2)
+#define I915_GEM_OBJECT_NO_MMAP		BIT(3)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
@@ -61,13 +61,117 @@ struct drm_i915_gem_object_ops {
 		     const struct drm_i915_gem_pread *arg);
 	int (*pwrite)(struct drm_i915_gem_object *obj,
 		      const struct drm_i915_gem_pwrite *arg);
+	u64 (*mmap_offset)(struct drm_i915_gem_object *obj);
 
 	int (*dmabuf_export)(struct drm_i915_gem_object *obj);
+
+	/**
+	 * adjust_lru - notify that the madvise value was updated
+	 * @obj: The gem object
+	 *
+	 * The madvise value may have been updated, or object was recently
+	 * referenced so act accordingly (Perhaps changing an LRU list etc).
+	 */
+	void (*adjust_lru)(struct drm_i915_gem_object *obj);
+
+	/**
+	 * delayed_free - Override the default delayed free implementation
+	 */
+	void (*delayed_free)(struct drm_i915_gem_object *obj);
+
+	/**
+	 * migrate - Migrate object to a different region either for
+	 * pinning or for as long as the object lock is held.
+	 */
+	int (*migrate)(struct drm_i915_gem_object *obj,
+		       struct intel_memory_region *mr);
+
 	void (*release)(struct drm_i915_gem_object *obj);
 
+	const struct vm_operations_struct *mmap_ops;
 	const char *name; /* friendly name for debug, e.g. lockdep classes */
 };
 
+/**
+ * enum i915_cache_level - The supported GTT caching values for system memory
+ * pages.
+ *
+ * These translate to some special GTT PTE bits when binding pages into some
+ * address space. It also determines whether an object, or rather its pages are
+ * coherent with the GPU, when also reading or writing through the CPU cache
+ * with those pages.
+ *
+ * Userspace can also control this through struct drm_i915_gem_caching.
+ */
+enum i915_cache_level {
+	/**
+	 * @I915_CACHE_NONE:
+	 *
+	 * GPU access is not coherent with the CPU cache. If the cache is dirty
+	 * and we need the underlying pages to be coherent with some later GPU
+	 * access then we need to manually flush the pages.
+	 *
+	 * On shared LLC platforms reads and writes through the CPU cache are
+	 * still coherent even with this setting. See also
+	 * &drm_i915_gem_object.cache_coherent for more details. Due to this we
+	 * should only ever use uncached for scanout surfaces, otherwise we end
+	 * up over-flushing in some places.
+	 *
+	 * This is the default on non-LLC platforms.
+	 */
+	I915_CACHE_NONE = 0,
+	/**
+	 * @I915_CACHE_LLC:
+	 *
+	 * GPU access is coherent with the CPU cache. If the cache is dirty,
+	 * then the GPU will ensure that access remains coherent, when both
+	 * reading and writing through the CPU cache. GPU writes can dirty the
+	 * CPU cache.
+	 *
+	 * Not used for scanout surfaces.
+	 *
+	 * Applies to both platforms with shared LLC(HAS_LLC), and snooping
+	 * based platforms(HAS_SNOOP).
+	 *
+	 * This is the default on shared LLC platforms.  The only exception is
+	 * scanout objects, where the display engine is not coherent with the
+	 * CPU cache. For such objects I915_CACHE_NONE or I915_CACHE_WT is
+	 * automatically applied by the kernel in pin_for_display, if userspace
+	 * has not done so already.
+	 */
+	I915_CACHE_LLC,
+	/**
+	 * @I915_CACHE_L3_LLC:
+	 *
+	 * Explicitly enable the Gfx L3 cache, with coherent LLC.
+	 *
+	 * The Gfx L3 sits between the domain specific caches, e.g
+	 * sampler/render caches, and the larger LLC. LLC is coherent with the
+	 * GPU, but L3 is only visible to the GPU, so likely needs to be flushed
+	 * when the workload completes.
+	 *
+	 * Not used for scanout surfaces.
+	 *
+	 * Only exposed on some gen7 + GGTT. More recent hardware has dropped
+	 * this explicit setting, where it should now be enabled by default.
+	 */
+	I915_CACHE_L3_LLC,
+	/**
+	 * @I915_CACHE_WT:
+	 *
+	 * Write-through. Used for scanout surfaces.
+	 *
+	 * The GPU can utilise the caches, while still having the display engine
+	 * be coherent with GPU writes, as a result we don't need to flush the
+	 * CPU caches when moving out of the render domain. This is the default
+	 * setting chosen by the kernel, if supported by the HW, otherwise we
+	 * fallback to I915_CACHE_NONE. On the CPU side writes through the CPU
+	 * cache still need to be flushed, to remain coherent with the display
+	 * engine.
+	 */
+	I915_CACHE_WT,
+};
+
 enum i915_map_type {
 	I915_MAP_WB = 0,
 	I915_MAP_WC,
@@ -81,6 +185,7 @@ enum i915_mmap_type {
 	I915_MMAP_TYPE_WC,
 	I915_MMAP_TYPE_WB,
 	I915_MMAP_TYPE_UC,
+	I915_MMAP_TYPE_FIXED,
 };
 
 struct i915_mmap_offset {
@@ -185,23 +290,138 @@ struct drm_i915_gem_object {
 	unsigned long flags;
 #define I915_BO_ALLOC_CONTIGUOUS BIT(0)
 #define I915_BO_ALLOC_VOLATILE   BIT(1)
-#define I915_BO_ALLOC_STRUCT_PAGE BIT(2)
-#define I915_BO_ALLOC_CPU_CLEAR  BIT(3)
+#define I915_BO_ALLOC_CPU_CLEAR  BIT(2)
+#define I915_BO_ALLOC_USER       BIT(3)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
-			     I915_BO_ALLOC_STRUCT_PAGE | \
-			     I915_BO_ALLOC_CPU_CLEAR)
+			     I915_BO_ALLOC_CPU_CLEAR | \
+			     I915_BO_ALLOC_USER)
 #define I915_BO_READONLY         BIT(4)
 #define I915_TILING_QUIRK_BIT    5 /* unknown swizzling; do not release! */
 
-	/*
-	 * Is the object to be mapped as read-only to the GPU
-	 * Only honoured if hardware has relevant pte bit
+	/**
+	 * @mem_flags - Mutable placement-related flags
+	 *
+	 * These are flags that indicate specifics of the memory region
+	 * the object is currently in. As such they are only stable
+	 * either under the object lock or if the object is pinned.
+	 */
+	unsigned int mem_flags;
+#define I915_BO_FLAG_STRUCT_PAGE BIT(0) /* Object backed by struct pages */
+#define I915_BO_FLAG_IOMEM       BIT(1) /* Object backed by IO memory */
+	/**
+	 * @cache_level: The desired GTT caching level.
+	 *
+	 * See enum i915_cache_level for possible values, along with what
+	 * each does.
 	 */
 	unsigned int cache_level:3;
-	unsigned int cache_coherent:2;
+	/**
+	 * @cache_coherent:
+	 *
+	 * Track whether the pages are coherent with the GPU if reading or
+	 * writing through the CPU caches. The largely depends on the
+	 * @cache_level setting.
+	 *
+	 * On platforms which don't have the shared LLC(HAS_SNOOP), like on Atom
+	 * platforms, coherency must be explicitly requested with some special
+	 * GTT caching bits(see enum i915_cache_level). When enabling coherency
+	 * it does come at a performance and power cost on such platforms. On
+	 * the flip side the kernel does not need to manually flush any buffers
+	 * which need to be coherent with the GPU, if the object is not coherent
+	 * i.e @cache_coherent is zero.
+	 *
+	 * On platforms that share the LLC with the CPU(HAS_LLC), all GT memory
+	 * access will automatically snoop the CPU caches(even with CACHE_NONE).
+	 * The one exception is when dealing with the display engine, like with
+	 * scanout surfaces. To handle this the kernel will always flush the
+	 * surface out of the CPU caches when preparing it for scanout.  Also
+	 * note that since scanout surfaces are only ever read by the display
+	 * engine we only need to care about flushing any writes through the CPU
+	 * cache, reads on the other hand will always be coherent.
+	 *
+	 * Something strange here is why @cache_coherent is not a simple
+	 * boolean, i.e coherent vs non-coherent. The reasoning for this is back
+	 * to the display engine not being fully coherent. As a result scanout
+	 * surfaces will either be marked as I915_CACHE_NONE or I915_CACHE_WT.
+	 * In the case of seeing I915_CACHE_NONE the kernel makes the assumption
+	 * that this is likely a scanout surface, and will set @cache_coherent
+	 * as only I915_BO_CACHE_COHERENT_FOR_READ, on platforms with the shared
+	 * LLC. The kernel uses this to always flush writes through the CPU
+	 * cache as early as possible, where it can, in effect keeping
+	 * @cache_dirty clean, so we can potentially avoid stalling when
+	 * flushing the surface just before doing the scanout.  This does mean
+	 * we might unnecessarily flush non-scanout objects in some places, but
+	 * the default assumption is that all normal objects should be using
+	 * I915_CACHE_LLC, at least on platforms with the shared LLC.
+	 *
+	 * Supported values:
+	 *
+	 * I915_BO_CACHE_COHERENT_FOR_READ:
+	 *
+	 * On shared LLC platforms, we use this for special scanout surfaces,
+	 * where the display engine is not coherent with the CPU cache. As such
+	 * we need to ensure we flush any writes before doing the scanout. As an
+	 * optimisation we try to flush any writes as early as possible to avoid
+	 * stalling later.
+	 *
+	 * Thus for scanout surfaces using I915_CACHE_NONE, on shared LLC
+	 * platforms, we use:
+	 *
+	 *	cache_coherent = I915_BO_CACHE_COHERENT_FOR_READ
+	 *
+	 * While for normal objects that are fully coherent, including special
+	 * scanout surfaces marked as I915_CACHE_WT, we use:
+	 *
+	 *	cache_coherent = I915_BO_CACHE_COHERENT_FOR_READ |
+	 *			 I915_BO_CACHE_COHERENT_FOR_WRITE
+	 *
+	 * And then for objects that are not coherent at all we use:
+	 *
+	 *	cache_coherent = 0
+	 *
+	 * I915_BO_CACHE_COHERENT_FOR_WRITE:
+	 *
+	 * When writing through the CPU cache, the GPU is still coherent. Note
+	 * that this also implies I915_BO_CACHE_COHERENT_FOR_READ.
+	 */
 #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0)
 #define I915_BO_CACHE_COHERENT_FOR_WRITE BIT(1)
+	unsigned int cache_coherent:2;
+
+	/**
+	 * @cache_dirty:
+	 *
+	 * Track if we are we dirty with writes through the CPU cache for this
+	 * object. As a result reading directly from main memory might yield
+	 * stale data.
+	 *
+	 * This also ties into whether the kernel is tracking the object as
+	 * coherent with the GPU, as per @cache_coherent, as it determines if
+	 * flushing might be needed at various points.
+	 *
+	 * Another part of @cache_dirty is managing flushing when first
+	 * acquiring the pages for system memory, at this point the pages are
+	 * considered foreign, so the default assumption is that the cache is
+	 * dirty, for example the page zeroing done by the kernel might leave
+	 * writes though the CPU cache, or swapping-in, while the actual data in
+	 * main memory is potentially stale.  Note that this is a potential
+	 * security issue when dealing with userspace objects and zeroing. Now,
+	 * whether we actually need apply the big sledgehammer of flushing all
+	 * the pages on acquire depends on if @cache_coherent is marked as
+	 * I915_BO_CACHE_COHERENT_FOR_WRITE, i.e that the GPU will be coherent
+	 * for both reads and writes though the CPU cache.
+	 *
+	 * Note that on shared LLC platforms we still apply the heavy flush for
+	 * I915_CACHE_NONE objects, under the assumption that this is going to
+	 * be used for scanout.
+	 *
+	 * Update: On some hardware there is now also the 'Bypass LLC' MOCS
+	 * entry, which defeats our @cache_coherent tracking, since userspace
+	 * can freely bypass the CPU cache when touching the pages with the GPU,
+	 * where the kernel is completely unaware. On such platform we need
+	 * apply the sledgehammer-on-acquire regardless of the @cache_coherent.
+	 */
 	unsigned int cache_dirty:1;
 
 	/**
@@ -247,9 +467,10 @@ struct drm_i915_gem_object {
 		struct intel_memory_region *region;
 
 		/**
-		 * Memory manager node allocated for this object.
+		 * Memory manager resource allocated for this object. Only
+		 * needed for the mock region.
 		 */
-		void *st_mm_node;
+		struct ttm_resource *res;
 
 		/**
 		 * Element within memory_region->objects or region->purgeable
@@ -310,6 +531,12 @@ struct drm_i915_gem_object {
 		bool dirty:1;
 	} mm;
 
+	struct {
+		struct sg_table *cached_io_st;
+		struct i915_gem_object_page_iter get_io_page;
+		bool created:1;
+	} ttm;
+
 	/** Record of address bit 17 of each page at last unbind. */
 	unsigned long *bit_17;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 6444e097016d..8eb1c3a6fc9c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -321,8 +321,7 @@ static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
 	dma_addr_t addr;
 	void *vaddr;
 
-	if (type != I915_MAP_WC)
-		return ERR_PTR(-ENODEV);
+	GEM_BUG_ON(type != I915_MAP_WC);
 
 	if (n_pfn > ARRAY_SIZE(stack)) {
 		/* Too big for stack -- allocate temporary array instead */
@@ -351,7 +350,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	int err;
 
 	if (!i915_gem_object_has_struct_page(obj) &&
-	    !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM))
+	    !i915_gem_object_has_iomem(obj))
 		return ERR_PTR(-ENXIO);
 
 	assert_object_held(obj);
@@ -374,6 +373,34 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	}
 	GEM_BUG_ON(!i915_gem_object_has_pages(obj));
 
+	/*
+	 * For discrete our CPU mappings needs to be consistent in order to
+	 * function correctly on !x86. When mapping things through TTM, we use
+	 * the same rules to determine the caching type.
+	 *
+	 * The caching rules, starting from DG1:
+	 *
+	 *	- If the object can be placed in device local-memory, then the
+	 *	  pages should be allocated and mapped as write-combined only.
+	 *
+	 *	- Everything else is always allocated and mapped as write-back,
+	 *	  with the guarantee that everything is also coherent with the
+	 *	  GPU.
+	 *
+	 * Internal users of lmem are already expected to get this right, so no
+	 * fudging needed there.
+	 */
+	if (i915_gem_object_placement_possible(obj, INTEL_MEMORY_LOCAL)) {
+		if (type != I915_MAP_WC && !obj->mm.n_placements) {
+			ptr = ERR_PTR(-ENODEV);
+			goto err_unpin;
+		}
+
+		type = I915_MAP_WC;
+	} else if (IS_DGFX(to_i915(obj->base.dev))) {
+		type = I915_MAP_WB;
+	}
+
 	ptr = page_unpack_bits(obj->mm.mapping, &has_type);
 	if (ptr && has_type != type) {
 		if (pinned) {
@@ -467,9 +494,8 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 			 struct i915_gem_object_page_iter *iter,
 			 unsigned int n,
 			 unsigned int *offset,
-			 bool allow_alloc)
+			 bool dma)
 {
-	const bool dma = iter == &obj->mm.get_dma_page;
 	struct scatterlist *sg;
 	unsigned int idx, count;
 
@@ -490,9 +516,6 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 	if (n < READ_ONCE(iter->sg_idx))
 		goto lookup;
 
-	if (!allow_alloc)
-		goto manual_lookup;
-
 	mutex_lock(&iter->lock);
 
 	/* We prefer to reuse the last sg so that repeated lookup of this
@@ -542,16 +565,7 @@ scan:
 	if (unlikely(n < idx)) /* insertion completed by another thread */
 		goto lookup;
 
-	goto manual_walk;
-
-manual_lookup:
-	idx = 0;
-	sg = obj->mm.pages->sgl;
-	count = __sg_page_count(sg);
-
-manual_walk:
-	/*
-	 * In case we failed to insert the entry into the radixtree, we need
+	/* In case we failed to insert the entry into the radixtree, we need
 	 * to look beyond the current sg.
 	 */
 	while (idx + count <= n) {
@@ -598,7 +612,7 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n)
 
 	GEM_BUG_ON(!i915_gem_object_has_struct_page(obj));
 
-	sg = i915_gem_object_get_sg(obj, n, &offset, true);
+	sg = i915_gem_object_get_sg(obj, n, &offset);
 	return nth_page(sg_page(sg), offset);
 }
 
@@ -624,7 +638,7 @@ i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 	struct scatterlist *sg;
 	unsigned int offset;
 
-	sg = i915_gem_object_get_sg_dma(obj, n, &offset, true);
+	sg = i915_gem_object_get_sg_dma(obj, n, &offset);
 
 	if (len)
 		*len = sg_dma_len(sg) - (offset << PAGE_SHIFT);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index be72ad0634ba..7986612f48fa 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -76,7 +76,7 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
 
 	/* We're no longer struct page backed */
-	obj->flags &= ~I915_BO_ALLOC_STRUCT_PAGE;
+	obj->mem_flags &= ~I915_BO_FLAG_STRUCT_PAGE;
 	__i915_gem_object_set_pages(obj, st, sg->length);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index f25e6646c5b7..1f557b2178ed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -13,16 +13,8 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
 {
 	obj->mm.region = intel_memory_region_get(mem);
 
-	if (obj->base.size <= mem->min_page_size)
-		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
-
 	mutex_lock(&mem->objects.lock);
-
-	if (obj->flags & I915_BO_ALLOC_VOLATILE)
-		list_add(&obj->mm.region_link, &mem->objects.purgeable);
-	else
-		list_add(&obj->mm.region_link, &mem->objects.list);
-
+	list_add(&obj->mm.region_link, &mem->objects.list);
 	mutex_unlock(&mem->objects.lock);
 }
 
@@ -40,9 +32,11 @@ void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj)
 struct drm_i915_gem_object *
 i915_gem_object_create_region(struct intel_memory_region *mem,
 			      resource_size_t size,
+			      resource_size_t page_size,
 			      unsigned int flags)
 {
 	struct drm_i915_gem_object *obj;
+	resource_size_t default_page_size;
 	int err;
 
 	/*
@@ -56,7 +50,14 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 	if (!mem)
 		return ERR_PTR(-ENODEV);
 
-	size = round_up(size, mem->min_page_size);
+	default_page_size = mem->min_page_size;
+	if (page_size)
+		default_page_size = page_size;
+
+	GEM_BUG_ON(!is_power_of_2_u64(default_page_size));
+	GEM_BUG_ON(default_page_size < PAGE_SIZE);
+
+	size = round_up(size, default_page_size);
 
 	GEM_BUG_ON(!size);
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_MIN_ALIGNMENT));
@@ -68,7 +69,7 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 
-	err = mem->ops->init_object(mem, obj, size, flags);
+	err = mem->ops->init_object(mem, obj, size, page_size, flags);
 	if (err)
 		goto err_object_free;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.h b/drivers/gpu/drm/i915/gem/i915_gem_region.h
index 84fcb3297400..1008e580a89a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.h
@@ -19,6 +19,7 @@ void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj);
 struct drm_i915_gem_object *
 i915_gem_object_create_region(struct intel_memory_region *mem,
 			      resource_size_t size,
+			      resource_size_t page_size,
 			      unsigned int flags);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 5d16c4462fda..11f072193f3b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -182,6 +182,24 @@ rebuild_st:
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj, st);
 
+	/*
+	 * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it
+	 * possible for userspace to bypass the GTT caching bits set by the
+	 * kernel, as per the given object cache_level. This is troublesome
+	 * since the heavy flush we apply when first gathering the pages is
+	 * skipped if the kernel thinks the object is coherent with the GPU. As
+	 * a result it might be possible to bypass the cache and read the
+	 * contents of the page directly, which could be stale data. If it's
+	 * just a case of userspace shooting themselves in the foot then so be
+	 * it, but since i915 takes the stance of always zeroing memory before
+	 * handing it to userspace, we need to prevent this.
+	 *
+	 * By setting cache_dirty here we make the clflush in set_pages
+	 * unconditional on such platforms.
+	 */
+	if (IS_JSL_EHL(i915) && obj->flags & I915_BO_ALLOC_USER)
+		obj->cache_dirty = true;
+
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
 	return 0;
@@ -302,6 +320,7 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_
 	struct pagevec pvec;
 	struct page *page;
 
+	GEM_WARN_ON(IS_DGFX(to_i915(obj->base.dev)));
 	__i915_gem_object_release_shmem(obj, pages, true);
 
 	i915_gem_gtt_finish_pages(obj, pages);
@@ -444,7 +463,7 @@ shmem_pread(struct drm_i915_gem_object *obj,
 
 static void shmem_release(struct drm_i915_gem_object *obj)
 {
-	if (obj->flags & I915_BO_ALLOC_STRUCT_PAGE)
+	if (i915_gem_object_has_struct_page(obj))
 		i915_gem_object_release_memory_region(obj);
 
 	fput(obj->base.filp);
@@ -489,6 +508,7 @@ static int __create_shmem(struct drm_i915_private *i915,
 static int shmem_object_init(struct intel_memory_region *mem,
 			     struct drm_i915_gem_object *obj,
 			     resource_size_t size,
+			     resource_size_t page_size,
 			     unsigned int flags)
 {
 	static struct lock_class_key lock_class;
@@ -513,9 +533,8 @@ static int shmem_object_init(struct intel_memory_region *mem,
 	mapping_set_gfp_mask(mapping, mask);
 	GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
 
-	i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class,
-			     I915_BO_ALLOC_STRUCT_PAGE);
-
+	i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0);
+	obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 
@@ -548,7 +567,7 @@ i915_gem_object_create_shmem(struct drm_i915_private *i915,
 			     resource_size_t size)
 {
 	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM],
-					     size, 0);
+					     size, 0, 0);
 }
 
 /* Allocate a new GEM object and fill it with the supplied data */
@@ -561,6 +580,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
 	resource_size_t offset;
 	int err;
 
+	GEM_WARN_ON(IS_DGFX(dev_priv));
 	obj = i915_gem_object_create_shmem(dev_priv, round_up(size, PAGE_SIZE));
 	if (IS_ERR(obj))
 		return obj;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index b0c3a7dc60d1..ddd37ccb1362 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -447,7 +447,6 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 		break;
 	case 8:
 	case 9:
-	case 10:
 		if (IS_LP(i915))
 			chv_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
@@ -670,6 +669,7 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem,
 static int _i915_gem_object_stolen_init(struct intel_memory_region *mem,
 					struct drm_i915_gem_object *obj,
 					resource_size_t size,
+					resource_size_t page_size,
 					unsigned int flags)
 {
 	struct drm_i915_private *i915 = mem->i915;
@@ -708,7 +708,7 @@ struct drm_i915_gem_object *
 i915_gem_object_create_stolen(struct drm_i915_private *i915,
 			      resource_size_t size)
 {
-	return i915_gem_object_create_region(i915->mm.stolen_region, size, 0);
+	return i915_gem_object_create_region(i915->mm.stolen_region, size, 0, 0);
 }
 
 static int init_stolen_smem(struct intel_memory_region *mem)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
new file mode 100644
index 000000000000..771eb2963123
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -0,0 +1,965 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_placement.h>
+
+#include "i915_drv.h"
+#include "intel_memory_region.h"
+#include "intel_region_ttm.h"
+
+#include "gem/i915_gem_object.h"
+#include "gem/i915_gem_region.h"
+#include "gem/i915_gem_ttm.h"
+#include "gem/i915_gem_mman.h"
+
+#include "gt/intel_migrate.h"
+#include "gt/intel_engine_pm.h"
+
+#define I915_PL_LMEM0 TTM_PL_PRIV
+#define I915_PL_SYSTEM TTM_PL_SYSTEM
+#define I915_PL_STOLEN TTM_PL_VRAM
+#define I915_PL_GGTT TTM_PL_TT
+
+#define I915_TTM_PRIO_PURGE     0
+#define I915_TTM_PRIO_NO_PAGES  1
+#define I915_TTM_PRIO_HAS_PAGES 2
+
+/*
+ * Size of struct ttm_place vector in on-stack struct ttm_placement allocs
+ */
+#define I915_TTM_MAX_PLACEMENTS INTEL_REGION_UNKNOWN
+
+/**
+ * struct i915_ttm_tt - TTM page vector with additional private information
+ * @ttm: The base TTM page vector.
+ * @dev: The struct device used for dma mapping and unmapping.
+ * @cached_st: The cached scatter-gather table.
+ *
+ * Note that DMA may be going on right up to the point where the page-
+ * vector is unpopulated in delayed destroy. Hence keep the
+ * scatter-gather table mapped and cached up to that point. This is
+ * different from the cached gem object io scatter-gather table which
+ * doesn't have an associated dma mapping.
+ */
+struct i915_ttm_tt {
+	struct ttm_tt ttm;
+	struct device *dev;
+	struct sg_table *cached_st;
+};
+
+static const struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = I915_PL_SYSTEM,
+	.flags = 0,
+};
+
+static struct ttm_placement i915_sys_placement = {
+	.num_placement = 1,
+	.placement = &sys_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags,
+};
+
+static int i915_ttm_err_to_gem(int err)
+{
+	/* Fastpath */
+	if (likely(!err))
+		return 0;
+
+	switch (err) {
+	case -EBUSY:
+		/*
+		 * TTM likes to convert -EDEADLK to -EBUSY, and wants us to
+		 * restart the operation, since we don't record the contending
+		 * lock. We use -EAGAIN to restart.
+		 */
+		return -EAGAIN;
+	case -ENOSPC:
+		/*
+		 * Memory type / region is full, and we can't evict.
+		 * Except possibly system, that returns -ENOMEM;
+		 */
+		return -ENXIO;
+	default:
+		break;
+	}
+
+	return err;
+}
+
+static bool gpu_binds_iomem(struct ttm_resource *mem)
+{
+	return mem->mem_type != TTM_PL_SYSTEM;
+}
+
+static bool cpu_maps_iomem(struct ttm_resource *mem)
+{
+	/* Once / if we support GGTT, this is also false for cached ttm_tts */
+	return mem->mem_type != TTM_PL_SYSTEM;
+}
+
+static enum i915_cache_level
+i915_ttm_cache_level(struct drm_i915_private *i915, struct ttm_resource *res,
+		     struct ttm_tt *ttm)
+{
+	return ((HAS_LLC(i915) || HAS_SNOOP(i915)) && !gpu_binds_iomem(res) &&
+		ttm->caching == ttm_cached) ? I915_CACHE_LLC :
+		I915_CACHE_NONE;
+}
+
+static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj);
+
+static enum ttm_caching
+i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
+{
+	/*
+	 * Objects only allowed in system get cached cpu-mappings.
+	 * Other objects get WC mapping for now. Even if in system.
+	 */
+	if (obj->mm.region->type == INTEL_MEMORY_SYSTEM &&
+	    obj->mm.n_placements <= 1)
+		return ttm_cached;
+
+	return ttm_write_combined;
+}
+
+static void
+i915_ttm_place_from_region(const struct intel_memory_region *mr,
+			   struct ttm_place *place,
+			   unsigned int flags)
+{
+	memset(place, 0, sizeof(*place));
+	place->mem_type = intel_region_to_ttm_type(mr);
+
+	if (flags & I915_BO_ALLOC_CONTIGUOUS)
+		place->flags = TTM_PL_FLAG_CONTIGUOUS;
+}
+
+static void
+i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
+			    struct ttm_place *requested,
+			    struct ttm_place *busy,
+			    struct ttm_placement *placement)
+{
+	unsigned int num_allowed = obj->mm.n_placements;
+	unsigned int flags = obj->flags;
+	unsigned int i;
+
+	placement->num_placement = 1;
+	i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
+				   obj->mm.region, requested, flags);
+
+	/* Cache this on object? */
+	placement->num_busy_placement = num_allowed;
+	for (i = 0; i < placement->num_busy_placement; ++i)
+		i915_ttm_place_from_region(obj->mm.placements[i], busy + i, flags);
+
+	if (num_allowed == 0) {
+		*busy = *requested;
+		placement->num_busy_placement = 1;
+	}
+
+	placement->placement = requested;
+	placement->busy_placement = busy;
+}
+
+static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
+					 uint32_t page_flags)
+{
+	struct ttm_resource_manager *man =
+		ttm_manager_type(bo->bdev, bo->resource->mem_type);
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	struct i915_ttm_tt *i915_tt;
+	int ret;
+
+	i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL);
+	if (!i915_tt)
+		return NULL;
+
+	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR &&
+	    man->use_tt)
+		page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
+
+	ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
+			  i915_ttm_select_tt_caching(obj));
+	if (ret) {
+		kfree(i915_tt);
+		return NULL;
+	}
+
+	i915_tt->dev = obj->base.dev->dev;
+
+	return &i915_tt->ttm;
+}
+
+static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
+{
+	struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
+
+	if (i915_tt->cached_st) {
+		dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st,
+				  DMA_BIDIRECTIONAL, 0);
+		sg_free_table(i915_tt->cached_st);
+		kfree(i915_tt->cached_st);
+		i915_tt->cached_st = NULL;
+	}
+	ttm_pool_free(&bdev->pool, ttm);
+}
+
+static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
+{
+	struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
+
+	ttm_tt_destroy_common(bdev, ttm);
+	ttm_tt_fini(ttm);
+	kfree(i915_tt);
+}
+
+static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
+				       const struct ttm_place *place)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+
+	/* Will do for now. Our pinned objects are still on TTM's LRU lists */
+	return i915_gem_object_evictable(obj);
+}
+
+static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
+				 struct ttm_placement *placement)
+{
+	*placement = i915_sys_placement;
+}
+
+static int i915_ttm_move_notify(struct ttm_buffer_object *bo)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	int ret;
+
+	ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE);
+	if (ret)
+		return ret;
+
+	ret = __i915_gem_object_put_pages(obj);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+
+	if (!obj->ttm.cached_io_st)
+		return;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &obj->ttm.get_io_page.radix, &iter, 0)
+		radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index);
+	rcu_read_unlock();
+
+	sg_free_table(obj->ttm.cached_io_st);
+	kfree(obj->ttm.cached_io_st);
+	obj->ttm.cached_io_st = NULL;
+}
+
+static void
+i915_ttm_adjust_domains_after_move(struct drm_i915_gem_object *obj)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+
+	if (cpu_maps_iomem(bo->resource) || bo->ttm->caching != ttm_cached) {
+		obj->write_domain = I915_GEM_DOMAIN_WC;
+		obj->read_domains = I915_GEM_DOMAIN_WC;
+	} else {
+		obj->write_domain = I915_GEM_DOMAIN_CPU;
+		obj->read_domains = I915_GEM_DOMAIN_CPU;
+	}
+}
+
+static void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+	unsigned int cache_level;
+	unsigned int i;
+
+	/*
+	 * If object was moved to an allowable region, update the object
+	 * region to consider it migrated. Note that if it's currently not
+	 * in an allowable region, it's evicted and we don't update the
+	 * object region.
+	 */
+	if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) {
+		for (i = 0; i < obj->mm.n_placements; ++i) {
+			struct intel_memory_region *mr = obj->mm.placements[i];
+
+			if (intel_region_to_ttm_type(mr) == bo->resource->mem_type &&
+			    mr != obj->mm.region) {
+				i915_gem_object_release_memory_region(obj);
+				i915_gem_object_init_memory_region(obj, mr);
+				break;
+			}
+		}
+	}
+
+	obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM);
+
+	obj->mem_flags |= cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM :
+		I915_BO_FLAG_STRUCT_PAGE;
+
+	cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource,
+					   bo->ttm);
+	i915_gem_object_set_cache_coherency(obj, cache_level);
+}
+
+static void i915_ttm_purge(struct drm_i915_gem_object *obj)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false,
+	};
+	struct ttm_placement place = {};
+	int ret;
+
+	if (obj->mm.madv == __I915_MADV_PURGED)
+		return;
+
+	/* TTM's purge interface. Note that we might be reentering. */
+	ret = ttm_bo_validate(bo, &place, &ctx);
+	if (!ret) {
+		obj->write_domain = 0;
+		obj->read_domains = 0;
+		i915_ttm_adjust_gem_after_move(obj);
+		i915_ttm_free_cached_io_st(obj);
+		obj->mm.madv = __I915_MADV_PURGED;
+	}
+}
+
+static void i915_ttm_swap_notify(struct ttm_buffer_object *bo)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	int ret = i915_ttm_move_notify(bo);
+
+	GEM_WARN_ON(ret);
+	GEM_WARN_ON(obj->ttm.cached_io_st);
+	if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
+		i915_ttm_purge(obj);
+}
+
+static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+
+	if (likely(obj)) {
+		/* This releases all gem object bindings to the backend. */
+		i915_ttm_free_cached_io_st(obj);
+		__i915_gem_free_object(obj);
+	}
+}
+
+static struct intel_memory_region *
+i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type)
+{
+	struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev);
+
+	/* There's some room for optimization here... */
+	GEM_BUG_ON(ttm_mem_type != I915_PL_SYSTEM &&
+		   ttm_mem_type < I915_PL_LMEM0);
+	if (ttm_mem_type == I915_PL_SYSTEM)
+		return intel_memory_region_lookup(i915, INTEL_MEMORY_SYSTEM,
+						  0);
+
+	return intel_memory_region_lookup(i915, INTEL_MEMORY_LOCAL,
+					  ttm_mem_type - I915_PL_LMEM0);
+}
+
+static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
+{
+	struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
+	struct scatterlist *sg;
+	struct sg_table *st;
+	int ret;
+
+	if (i915_tt->cached_st)
+		return i915_tt->cached_st;
+
+	st = kzalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return ERR_PTR(-ENOMEM);
+
+	sg = __sg_alloc_table_from_pages
+		(st, ttm->pages, ttm->num_pages, 0,
+		 (unsigned long)ttm->num_pages << PAGE_SHIFT,
+		 i915_sg_segment_size(), NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
+		kfree(st);
+		return ERR_CAST(sg);
+	}
+
+	ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
+	if (ret) {
+		sg_free_table(st);
+		kfree(st);
+		return ERR_PTR(ret);
+	}
+
+	i915_tt->cached_st = st;
+	return st;
+}
+
+static struct sg_table *
+i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
+			 struct ttm_resource *res)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+
+	if (!gpu_binds_iomem(res))
+		return i915_ttm_tt_get_st(bo->ttm);
+
+	/*
+	 * If CPU mapping differs, we need to add the ttm_tt pages to
+	 * the resulting st. Might make sense for GGTT.
+	 */
+	GEM_WARN_ON(!cpu_maps_iomem(res));
+	return intel_region_ttm_resource_to_st(obj->mm.region, res);
+}
+
+static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
+			       struct ttm_resource *dst_mem,
+			       struct sg_table *dst_st)
+{
+	struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
+						     bdev);
+	struct ttm_resource_manager *src_man =
+		ttm_manager_type(bo->bdev, bo->resource->mem_type);
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	struct sg_table *src_st;
+	struct i915_request *rq;
+	struct ttm_tt *ttm = bo->ttm;
+	enum i915_cache_level src_level, dst_level;
+	int ret;
+
+	if (!i915->gt.migrate.context)
+		return -EINVAL;
+
+	dst_level = i915_ttm_cache_level(i915, dst_mem, ttm);
+	if (!ttm || !ttm_tt_is_populated(ttm)) {
+		if (bo->type == ttm_bo_type_kernel)
+			return -EINVAL;
+
+		if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))
+			return 0;
+
+		intel_engine_pm_get(i915->gt.migrate.context->engine);
+		ret = intel_context_migrate_clear(i915->gt.migrate.context, NULL,
+						  dst_st->sgl, dst_level,
+						  gpu_binds_iomem(dst_mem),
+						  0, &rq);
+
+		if (!ret && rq) {
+			i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+			i915_request_put(rq);
+		}
+		intel_engine_pm_put(i915->gt.migrate.context->engine);
+	} else {
+		src_st = src_man->use_tt ? i915_ttm_tt_get_st(ttm) :
+			obj->ttm.cached_io_st;
+
+		src_level = i915_ttm_cache_level(i915, bo->resource, ttm);
+		intel_engine_pm_get(i915->gt.migrate.context->engine);
+		ret = intel_context_migrate_copy(i915->gt.migrate.context,
+						 NULL, src_st->sgl, src_level,
+						 gpu_binds_iomem(bo->resource),
+						 dst_st->sgl, dst_level,
+						 gpu_binds_iomem(dst_mem),
+						 &rq);
+		if (!ret && rq) {
+			i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+			i915_request_put(rq);
+		}
+		intel_engine_pm_put(i915->gt.migrate.context->engine);
+	}
+
+	return ret;
+}
+
+static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
+			 struct ttm_operation_ctx *ctx,
+			 struct ttm_resource *dst_mem,
+			 struct ttm_place *hop)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	struct ttm_resource_manager *dst_man =
+		ttm_manager_type(bo->bdev, dst_mem->mem_type);
+	struct intel_memory_region *dst_reg, *src_reg;
+	union {
+		struct ttm_kmap_iter_tt tt;
+		struct ttm_kmap_iter_iomap io;
+	} _dst_iter, _src_iter;
+	struct ttm_kmap_iter *dst_iter, *src_iter;
+	struct sg_table *dst_st;
+	int ret;
+
+	dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type);
+	src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type);
+	GEM_BUG_ON(!dst_reg || !src_reg);
+
+	/* Sync for now. We could do the actual copy async. */
+	ret = ttm_bo_wait_ctx(bo, ctx);
+	if (ret)
+		return ret;
+
+	ret = i915_ttm_move_notify(bo);
+	if (ret)
+		return ret;
+
+	if (obj->mm.madv != I915_MADV_WILLNEED) {
+		i915_ttm_purge(obj);
+		ttm_resource_free(bo, &dst_mem);
+		return 0;
+	}
+
+	/* Populate ttm with pages if needed. Typically system memory. */
+	if (bo->ttm && (dst_man->use_tt ||
+			(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) {
+		ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
+		if (ret)
+			return ret;
+	}
+
+	dst_st = i915_ttm_resource_get_st(obj, dst_mem);
+	if (IS_ERR(dst_st))
+		return PTR_ERR(dst_st);
+
+	ret = i915_ttm_accel_move(bo, dst_mem, dst_st);
+	if (ret) {
+		/* If we start mapping GGTT, we can no longer use man::use_tt here. */
+		dst_iter = !cpu_maps_iomem(dst_mem) ?
+			ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) :
+			ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
+						 dst_st, dst_reg->region.start);
+
+		src_iter = !cpu_maps_iomem(bo->resource) ?
+			ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
+			ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
+						 obj->ttm.cached_io_st,
+						 src_reg->region.start);
+
+		ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter);
+	}
+	/* Below dst_mem becomes bo->resource. */
+	ttm_bo_move_sync_cleanup(bo, dst_mem);
+	i915_ttm_adjust_domains_after_move(obj);
+	i915_ttm_free_cached_io_st(obj);
+
+	if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) {
+		obj->ttm.cached_io_st = dst_st;
+		obj->ttm.get_io_page.sg_pos = dst_st->sgl;
+		obj->ttm.get_io_page.sg_idx = 0;
+	}
+
+	i915_ttm_adjust_gem_after_move(obj);
+	return 0;
+}
+
+static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem)
+{
+	if (!cpu_maps_iomem(mem))
+		return 0;
+
+	mem->bus.caching = ttm_write_combined;
+	mem->bus.is_iomem = true;
+
+	return 0;
+}
+
+static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
+					 unsigned long page_offset)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	unsigned long base = obj->mm.region->iomap.base - obj->mm.region->region.start;
+	struct scatterlist *sg;
+	unsigned int ofs;
+
+	GEM_WARN_ON(bo->ttm);
+
+	sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true);
+
+	return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs;
+}
+
+static struct ttm_device_funcs i915_ttm_bo_driver = {
+	.ttm_tt_create = i915_ttm_tt_create,
+	.ttm_tt_unpopulate = i915_ttm_tt_unpopulate,
+	.ttm_tt_destroy = i915_ttm_tt_destroy,
+	.eviction_valuable = i915_ttm_eviction_valuable,
+	.evict_flags = i915_ttm_evict_flags,
+	.move = i915_ttm_move,
+	.swap_notify = i915_ttm_swap_notify,
+	.delete_mem_notify = i915_ttm_delete_mem_notify,
+	.io_mem_reserve = i915_ttm_io_mem_reserve,
+	.io_mem_pfn = i915_ttm_io_mem_pfn,
+};
+
+/**
+ * i915_ttm_driver - Return a pointer to the TTM device funcs
+ *
+ * Return: Pointer to statically allocated TTM device funcs.
+ */
+struct ttm_device_funcs *i915_ttm_driver(void)
+{
+	return &i915_ttm_bo_driver;
+}
+
+static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
+				struct ttm_placement *placement)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false,
+	};
+	struct sg_table *st;
+	int real_num_busy;
+	int ret;
+
+	/* First try only the requested placement. No eviction. */
+	real_num_busy = fetch_and_zero(&placement->num_busy_placement);
+	ret = ttm_bo_validate(bo, placement, &ctx);
+	if (ret) {
+		ret = i915_ttm_err_to_gem(ret);
+		/*
+		 * Anything that wants to restart the operation gets to
+		 * do that.
+		 */
+		if (ret == -EDEADLK || ret == -EINTR || ret == -ERESTARTSYS ||
+		    ret == -EAGAIN)
+			return ret;
+
+		/*
+		 * If the initial attempt fails, allow all accepted placements,
+		 * evicting if necessary.
+		 */
+		placement->num_busy_placement = real_num_busy;
+		ret = ttm_bo_validate(bo, placement, &ctx);
+		if (ret)
+			return i915_ttm_err_to_gem(ret);
+	}
+
+	i915_ttm_adjust_lru(obj);
+	if (bo->ttm && !ttm_tt_is_populated(bo->ttm)) {
+		ret = ttm_tt_populate(bo->bdev, bo->ttm, &ctx);
+		if (ret)
+			return ret;
+
+		i915_ttm_adjust_domains_after_move(obj);
+		i915_ttm_adjust_gem_after_move(obj);
+	}
+
+	if (!i915_gem_object_has_pages(obj)) {
+		/* Object either has a page vector or is an iomem object */
+		st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st;
+		if (IS_ERR(st))
+			return PTR_ERR(st);
+
+		__i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl));
+	}
+
+	return ret;
+}
+
+static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
+{
+	struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
+	struct ttm_placement placement;
+
+	GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS);
+
+	/* Move to the requested placement. */
+	i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
+
+	return __i915_ttm_get_pages(obj, &placement);
+}
+
+/**
+ * DOC: Migration vs eviction
+ *
+ * GEM migration may not be the same as TTM migration / eviction. If
+ * the TTM core decides to evict an object it may be evicted to a
+ * TTM memory type that is not in the object's allowable GEM regions, or
+ * in fact theoretically to a TTM memory type that doesn't correspond to
+ * a GEM memory region. In that case the object's GEM region is not
+ * updated, and the data is migrated back to the GEM region at
+ * get_pages time. TTM may however set up CPU ptes to the object even
+ * when it is evicted.
+ * Gem forced migration using the i915_ttm_migrate() op, is allowed even
+ * to regions that are not in the object's list of allowable placements.
+ */
+static int i915_ttm_migrate(struct drm_i915_gem_object *obj,
+			    struct intel_memory_region *mr)
+{
+	struct ttm_place requested;
+	struct ttm_placement placement;
+	int ret;
+
+	i915_ttm_place_from_region(mr, &requested, obj->flags);
+	placement.num_placement = 1;
+	placement.num_busy_placement = 1;
+	placement.placement = &requested;
+	placement.busy_placement = &requested;
+
+	ret = __i915_ttm_get_pages(obj, &placement);
+	if (ret)
+		return ret;
+
+	/*
+	 * Reinitialize the region bindings. This is primarily
+	 * required for objects where the new region is not in
+	 * its allowable placements.
+	 */
+	if (obj->mm.region != mr) {
+		i915_gem_object_release_memory_region(obj);
+		i915_gem_object_init_memory_region(obj, mr);
+	}
+
+	return 0;
+}
+
+static void i915_ttm_put_pages(struct drm_i915_gem_object *obj,
+			       struct sg_table *st)
+{
+	/*
+	 * We're currently not called from a shrinker, so put_pages()
+	 * typically means the object is about to destroyed, or called
+	 * from move_notify(). So just avoid doing much for now.
+	 * If the object is not destroyed next, The TTM eviction logic
+	 * and shrinkers will move it out if needed.
+	 */
+
+	i915_ttm_adjust_lru(obj);
+}
+
+static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
+{
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+
+	/*
+	 * Don't manipulate the TTM LRUs while in TTM bo destruction.
+	 * We're called through i915_ttm_delete_mem_notify().
+	 */
+	if (!kref_read(&bo->kref))
+		return;
+
+	/*
+	 * Put on the correct LRU list depending on the MADV status
+	 */
+	spin_lock(&bo->bdev->lru_lock);
+	if (obj->mm.madv != I915_MADV_WILLNEED) {
+		bo->priority = I915_TTM_PRIO_PURGE;
+	} else if (!i915_gem_object_has_pages(obj)) {
+		if (bo->priority < I915_TTM_PRIO_HAS_PAGES)
+			bo->priority = I915_TTM_PRIO_HAS_PAGES;
+	} else {
+		if (bo->priority > I915_TTM_PRIO_NO_PAGES)
+			bo->priority = I915_TTM_PRIO_NO_PAGES;
+	}
+
+	ttm_bo_move_to_lru_tail(bo, bo->resource, NULL);
+	spin_unlock(&bo->bdev->lru_lock);
+}
+
+/*
+ * TTM-backed gem object destruction requires some clarification.
+ * Basically we have two possibilities here. We can either rely on the
+ * i915 delayed destruction and put the TTM object when the object
+ * is idle. This would be detected by TTM which would bypass the
+ * TTM delayed destroy handling. The other approach is to put the TTM
+ * object early and rely on the TTM destroyed handling, and then free
+ * the leftover parts of the GEM object once TTM's destroyed list handling is
+ * complete. For now, we rely on the latter for two reasons:
+ * a) TTM can evict an object even when it's on the delayed destroy list,
+ * which in theory allows for complete eviction.
+ * b) There is work going on in TTM to allow freeing an object even when
+ * it's not idle, and using the TTM destroyed list handling could help us
+ * benefit from that.
+ */
+static void i915_ttm_delayed_free(struct drm_i915_gem_object *obj)
+{
+	if (obj->ttm.created) {
+		ttm_bo_put(i915_gem_to_ttm(obj));
+	} else {
+		__i915_gem_free_object(obj);
+		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
+	}
+}
+
+static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
+{
+	struct vm_area_struct *area = vmf->vma;
+	struct drm_i915_gem_object *obj =
+		i915_ttm_to_gem(area->vm_private_data);
+
+	/* Sanity check that we allow writing into this object */
+	if (unlikely(i915_gem_object_is_readonly(obj) &&
+		     area->vm_flags & VM_WRITE))
+		return VM_FAULT_SIGBUS;
+
+	return ttm_bo_vm_fault(vmf);
+}
+
+static int
+vm_access_ttm(struct vm_area_struct *area, unsigned long addr,
+	      void *buf, int len, int write)
+{
+	struct drm_i915_gem_object *obj =
+		i915_ttm_to_gem(area->vm_private_data);
+
+	if (i915_gem_object_is_readonly(obj) && write)
+		return -EACCES;
+
+	return ttm_bo_vm_access(area, addr, buf, len, write);
+}
+
+static void ttm_vm_open(struct vm_area_struct *vma)
+{
+	struct drm_i915_gem_object *obj =
+		i915_ttm_to_gem(vma->vm_private_data);
+
+	GEM_BUG_ON(!obj);
+	i915_gem_object_get(obj);
+}
+
+static void ttm_vm_close(struct vm_area_struct *vma)
+{
+	struct drm_i915_gem_object *obj =
+		i915_ttm_to_gem(vma->vm_private_data);
+
+	GEM_BUG_ON(!obj);
+	i915_gem_object_put(obj);
+}
+
+static const struct vm_operations_struct vm_ops_ttm = {
+	.fault = vm_fault_ttm,
+	.access = vm_access_ttm,
+	.open = ttm_vm_open,
+	.close = ttm_vm_close,
+};
+
+static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj)
+{
+	/* The ttm_bo must be allocated with I915_BO_ALLOC_USER */
+	GEM_BUG_ON(!drm_mm_node_allocated(&obj->base.vma_node.vm_node));
+
+	return drm_vma_node_offset_addr(&obj->base.vma_node);
+}
+
+static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = {
+	.name = "i915_gem_object_ttm",
+
+	.get_pages = i915_ttm_get_pages,
+	.put_pages = i915_ttm_put_pages,
+	.truncate = i915_ttm_purge,
+	.adjust_lru = i915_ttm_adjust_lru,
+	.delayed_free = i915_ttm_delayed_free,
+	.migrate = i915_ttm_migrate,
+	.mmap_offset = i915_ttm_mmap_offset,
+	.mmap_ops = &vm_ops_ttm,
+};
+
+void i915_ttm_bo_destroy(struct ttm_buffer_object *bo)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+
+	i915_gem_object_release_memory_region(obj);
+	mutex_destroy(&obj->ttm.get_io_page.lock);
+	if (obj->ttm.created)
+		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
+}
+
+/**
+ * __i915_gem_ttm_object_init - Initialize a ttm-backed i915 gem object
+ * @mem: The initial memory region for the object.
+ * @obj: The gem object.
+ * @size: Object size in bytes.
+ * @flags: gem object flags.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
+			       struct drm_i915_gem_object *obj,
+			       resource_size_t size,
+			       resource_size_t page_size,
+			       unsigned int flags)
+{
+	static struct lock_class_key lock_class;
+	struct drm_i915_private *i915 = mem->i915;
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false,
+	};
+	enum ttm_bo_type bo_type;
+	int ret;
+
+	drm_gem_private_object_init(&i915->drm, &obj->base, size);
+	i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags);
+	i915_gem_object_init_memory_region(obj, mem);
+	i915_gem_object_make_unshrinkable(obj);
+	INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN);
+	mutex_init(&obj->ttm.get_io_page.lock);
+	bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device :
+		ttm_bo_type_kernel;
+
+	obj->base.vma_node.driver_private = i915_gem_to_ttm(obj);
+
+	/* Forcing the page size is kernel internal only */
+	GEM_BUG_ON(page_size && obj->mm.n_placements);
+
+	/*
+	 * If this function fails, it will call the destructor, but
+	 * our caller still owns the object. So no freeing in the
+	 * destructor until obj->ttm.created is true.
+	 * Similarly, in delayed_destroy, we can't call ttm_bo_put()
+	 * until successful initialization.
+	 */
+	ret = ttm_bo_init_reserved(&i915->bdev, i915_gem_to_ttm(obj), size,
+				   bo_type, &i915_sys_placement,
+				   page_size >> PAGE_SHIFT,
+				   &ctx, NULL, NULL, i915_ttm_bo_destroy);
+	if (ret)
+		return i915_ttm_err_to_gem(ret);
+
+	obj->ttm.created = true;
+	i915_ttm_adjust_domains_after_move(obj);
+	i915_ttm_adjust_gem_after_move(obj);
+	i915_gem_object_unlock(obj);
+
+	return 0;
+}
+
+static const struct intel_memory_region_ops ttm_system_region_ops = {
+	.init_object = __i915_gem_ttm_object_init,
+};
+
+struct intel_memory_region *
+i915_gem_ttm_system_setup(struct drm_i915_private *i915,
+			  u16 type, u16 instance)
+{
+	struct intel_memory_region *mr;
+
+	mr = intel_memory_region_create(i915, 0,
+					totalram_pages() << PAGE_SHIFT,
+					PAGE_SIZE, 0,
+					type, instance,
+					&ttm_system_region_ops);
+	if (IS_ERR(mr))
+		return mr;
+
+	intel_memory_region_set_name(mr, "system-ttm");
+	return mr;
+}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
new file mode 100644
index 000000000000..40927f67b6d9
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+#ifndef _I915_GEM_TTM_H_
+#define _I915_GEM_TTM_H_
+
+#include "gem/i915_gem_object_types.h"
+
+/**
+ * i915_gem_to_ttm - Convert a struct drm_i915_gem_object to a
+ * struct ttm_buffer_object.
+ * @obj: Pointer to the gem object.
+ *
+ * Return: Pointer to the embedded struct ttm_buffer_object.
+ */
+static inline struct ttm_buffer_object *
+i915_gem_to_ttm(struct drm_i915_gem_object *obj)
+{
+	return &obj->__do_not_access;
+}
+
+/*
+ * i915 ttm gem object destructor. Internal use only.
+ */
+void i915_ttm_bo_destroy(struct ttm_buffer_object *bo);
+
+/**
+ * i915_ttm_to_gem - Convert a struct ttm_buffer_object to an embedding
+ * struct drm_i915_gem_object.
+ *
+ * Return: Pointer to the embedding struct ttm_buffer_object, or NULL
+ * if the object was not an i915 ttm object.
+ */
+static inline struct drm_i915_gem_object *
+i915_ttm_to_gem(struct ttm_buffer_object *bo)
+{
+	if (GEM_WARN_ON(bo->destroy != i915_ttm_bo_destroy))
+		return NULL;
+
+	return container_of(bo, struct drm_i915_gem_object, __do_not_access);
+}
+
+int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
+			       struct drm_i915_gem_object *obj,
+			       resource_size_t size,
+			       resource_size_t page_size,
+			       unsigned int flags);
+#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 7487bab11f0b..468a7a617fbf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -67,11 +67,11 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni,
 	if (!mmu_notifier_range_blockable(range))
 		return false;
 
-	spin_lock(&i915->mm.notifier_lock);
+	write_lock(&i915->mm.notifier_lock);
 
 	mmu_interval_set_seq(mni, cur_seq);
 
-	spin_unlock(&i915->mm.notifier_lock);
+	write_unlock(&i915->mm.notifier_lock);
 
 	/*
 	 * We don't wait when the process is exiting. This is valid
@@ -107,16 +107,15 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj)
 
 static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct page **pvec = NULL;
 
-	spin_lock(&i915->mm.notifier_lock);
+	assert_object_held_shared(obj);
+
 	if (!--obj->userptr.page_ref) {
 		pvec = obj->userptr.pvec;
 		obj->userptr.pvec = NULL;
 	}
 	GEM_BUG_ON(obj->userptr.page_ref < 0);
-	spin_unlock(&i915->mm.notifier_lock);
 
 	if (pvec) {
 		const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
@@ -128,7 +127,6 @@ static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj)
 
 static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
@@ -141,16 +139,13 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	if (!st)
 		return -ENOMEM;
 
-	spin_lock(&i915->mm.notifier_lock);
-	if (GEM_WARN_ON(!obj->userptr.page_ref)) {
-		spin_unlock(&i915->mm.notifier_lock);
-		ret = -EFAULT;
+	if (!obj->userptr.page_ref) {
+		ret = -EAGAIN;
 		goto err_free;
 	}
 
 	obj->userptr.page_ref++;
 	pvec = obj->userptr.pvec;
-	spin_unlock(&i915->mm.notifier_lock);
 
 alloc_table:
 	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
@@ -241,7 +236,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 	i915_gem_object_userptr_drop_ref(obj);
 }
 
-static int i915_gem_object_userptr_unbind(struct drm_i915_gem_object *obj, bool get_pages)
+static int i915_gem_object_userptr_unbind(struct drm_i915_gem_object *obj)
 {
 	struct sg_table *pages;
 	int err;
@@ -259,15 +254,11 @@ static int i915_gem_object_userptr_unbind(struct drm_i915_gem_object *obj, bool
 	if (!IS_ERR_OR_NULL(pages))
 		i915_gem_userptr_put_pages(obj, pages);
 
-	if (get_pages)
-		err = ____i915_gem_object_get_pages(obj);
-
 	return err;
 }
 
 int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
 	struct page **pvec;
 	unsigned int gup_flags = 0;
@@ -277,39 +268,22 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 	if (obj->userptr.notifier.mm != current->mm)
 		return -EFAULT;
 
+	notifier_seq = mmu_interval_read_begin(&obj->userptr.notifier);
+
 	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		return ret;
 
-	/* optimistically try to preserve current pages while unlocked */
-	if (i915_gem_object_has_pages(obj) &&
-	    !mmu_interval_check_retry(&obj->userptr.notifier,
-				      obj->userptr.notifier_seq)) {
-		spin_lock(&i915->mm.notifier_lock);
-		if (obj->userptr.pvec &&
-		    !mmu_interval_read_retry(&obj->userptr.notifier,
-					     obj->userptr.notifier_seq)) {
-			obj->userptr.page_ref++;
-
-			/* We can keep using the current binding, this is the fastpath */
-			ret = 1;
-		}
-		spin_unlock(&i915->mm.notifier_lock);
+	if (notifier_seq == obj->userptr.notifier_seq && obj->userptr.pvec) {
+		i915_gem_object_unlock(obj);
+		return 0;
 	}
 
-	if (!ret) {
-		/* Make sure userptr is unbound for next attempt, so we don't use stale pages. */
-		ret = i915_gem_object_userptr_unbind(obj, false);
-	}
+	ret = i915_gem_object_userptr_unbind(obj);
 	i915_gem_object_unlock(obj);
-	if (ret < 0)
+	if (ret)
 		return ret;
 
-	if (ret > 0)
-		return 0;
-
-	notifier_seq = mmu_interval_read_begin(&obj->userptr.notifier);
-
 	pvec = kvmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!pvec)
 		return -ENOMEM;
@@ -329,7 +303,9 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 	}
 	ret = 0;
 
-	spin_lock(&i915->mm.notifier_lock);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
+	if (ret)
+		goto out;
 
 	if (mmu_interval_read_retry(&obj->userptr.notifier,
 		!obj->userptr.page_ref ? notifier_seq :
@@ -341,12 +317,14 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 	if (!obj->userptr.page_ref++) {
 		obj->userptr.pvec = pvec;
 		obj->userptr.notifier_seq = notifier_seq;
-
 		pvec = NULL;
+		ret = ____i915_gem_object_get_pages(obj);
 	}
 
+	obj->userptr.page_ref--;
+
 out_unlock:
-	spin_unlock(&i915->mm.notifier_lock);
+	i915_gem_object_unlock(obj);
 
 out:
 	if (pvec) {
@@ -369,11 +347,6 @@ int i915_gem_object_userptr_submit_done(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-void i915_gem_object_userptr_submit_fini(struct drm_i915_gem_object *obj)
-{
-	i915_gem_object_userptr_drop_ref(obj);
-}
-
 int i915_gem_object_userptr_validate(struct drm_i915_gem_object *obj)
 {
 	int err;
@@ -396,7 +369,6 @@ int i915_gem_object_userptr_validate(struct drm_i915_gem_object *obj)
 		i915_gem_object_unlock(obj);
 	}
 
-	i915_gem_object_userptr_submit_fini(obj);
 	return err;
 }
 
@@ -450,6 +422,34 @@ static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 
 #endif
 
+static int
+probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len)
+{
+	const unsigned long end = addr + len;
+	struct vm_area_struct *vma;
+	int ret = -EFAULT;
+
+	mmap_read_lock(mm);
+	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+		/* Check for holes, note that we also update the addr below */
+		if (vma->vm_start > addr)
+			break;
+
+		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
+			break;
+
+		if (vma->vm_end >= end) {
+			ret = 0;
+			break;
+		}
+
+		addr = vma->vm_end;
+	}
+	mmap_read_unlock(mm);
+
+	return ret;
+}
+
 /*
  * Creates a new mm object that wraps some normal memory from the process
  * context - user memory.
@@ -505,7 +505,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 	}
 
 	if (args->flags & ~(I915_USERPTR_READ_ONLY |
-			    I915_USERPTR_UNSYNCHRONIZED))
+			    I915_USERPTR_UNSYNCHRONIZED |
+			    I915_USERPTR_PROBE))
 		return -EINVAL;
 
 	if (i915_gem_object_size_2big(args->user_size))
@@ -532,14 +533,24 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 			return -ENODEV;
 	}
 
+	if (args->flags & I915_USERPTR_PROBE) {
+		/*
+		 * Check that the range pointed to represents real struct
+		 * pages and not iomappings (at this moment in time!)
+		 */
+		ret = probe_range(current->mm, args->user_ptr, args->user_size);
+		if (ret)
+			return ret;
+	}
+
 #ifdef CONFIG_MMU_NOTIFIER
 	obj = i915_gem_object_alloc();
 	if (obj == NULL)
 		return -ENOMEM;
 
 	drm_gem_private_object_init(dev, &obj->base, args->user_size);
-	i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class,
-			     I915_BO_ALLOC_STRUCT_PAGE);
+	i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class, 0);
+	obj->mem_flags = I915_BO_FLAG_STRUCT_PAGE;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
@@ -572,7 +583,7 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 int i915_gem_init_userptr(struct drm_i915_private *dev_priv)
 {
 #ifdef CONFIG_MMU_NOTIFIER
-	spin_lock_init(&dev_priv->mm.notifier_lock);
+	rwlock_init(&dev_priv->mm.notifier_lock);
 #endif
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index 1e97520c62b2..f909aaa09d9c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -104,8 +104,8 @@ static void fence_set_priority(struct dma_fence *fence,
 	engine = rq->engine;
 
 	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
-	if (engine->schedule)
-		engine->schedule(rq, attr);
+	if (engine->sched_engine->schedule)
+		engine->sched_engine->schedule(rq, attr);
 	rcu_read_unlock();
 }
 
@@ -290,3 +290,22 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	i915_gem_object_put(obj);
 	return ret;
 }
+
+/**
+ * i915_gem_object_wait_migration - Sync an accelerated migration operation
+ * @obj: The migrating object.
+ * @flags: waiting flags. Currently supports only I915_WAIT_INTERRUPTIBLE.
+ *
+ * Wait for any pending async migration operation on the object,
+ * whether it's explicitly (i915_gem_object_migrate()) or implicitly
+ * (swapin, initial clearing) initiated.
+ *
+ * Return: 0 if successful, -ERESTARTSYS if a signal was hit during waiting.
+ */
+int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj,
+				   unsigned int flags)
+{
+	might_sleep();
+	/* NOP for now. */
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
index 0c8ecfdf5405..f963b8e1e37b 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
@@ -114,8 +114,8 @@ huge_gem_object(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, dma_size);
-	i915_gem_object_init(obj, &huge_ops, &lock_class,
-			     I915_BO_ALLOC_STRUCT_PAGE);
+	i915_gem_object_init(obj, &huge_ops, &lock_class, 0);
+	obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
 
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index dadd485bc52f..a094f3ce1a90 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -167,9 +167,8 @@ huge_pages_object(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &huge_page_ops, &lock_class,
-			     I915_BO_ALLOC_STRUCT_PAGE);
-
+	i915_gem_object_init(obj, &huge_page_ops, &lock_class, 0);
+	obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
 	i915_gem_object_set_volatile(obj);
 
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
@@ -497,7 +496,8 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(flags); ++i) {
-			obj = i915_gem_object_create_region(mem, page_size,
+			obj = i915_gem_object_create_region(mem,
+							    page_size, page_size,
 							    flags[i]);
 			if (IS_ERR(obj)) {
 				err = PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index 176e6b22f87f..ecbcbb86ae1e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -5,6 +5,7 @@
 
 #include "i915_selftest.h"
 
+#include "gt/intel_context.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gpu_commands.h"
@@ -16,118 +17,6 @@
 #include "huge_gem_object.h"
 #include "mock_context.h"
 
-static int __igt_client_fill(struct intel_engine_cs *engine)
-{
-	struct intel_context *ce = engine->kernel_context;
-	struct drm_i915_gem_object *obj;
-	I915_RND_STATE(prng);
-	IGT_TIMEOUT(end);
-	u32 *vaddr;
-	int err = 0;
-
-	intel_engine_pm_get(engine);
-	do {
-		const u32 max_block_size = S16_MAX * PAGE_SIZE;
-		u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
-		u32 phys_sz = sz % (max_block_size + 1);
-		u32 val = prandom_u32_state(&prng);
-		u32 i;
-
-		sz = round_up(sz, PAGE_SIZE);
-		phys_sz = round_up(phys_sz, PAGE_SIZE);
-
-		pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
-			 phys_sz, sz, val);
-
-		obj = huge_gem_object(engine->i915, phys_sz, sz);
-		if (IS_ERR(obj)) {
-			err = PTR_ERR(obj);
-			goto err_flush;
-		}
-
-		vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto err_put;
-		}
-
-		/*
-		 * XXX: The goal is move this to get_pages, so try to dirty the
-		 * CPU cache first to check that we do the required clflush
-		 * before scheduling the blt for !llc platforms. This matches
-		 * some version of reality where at get_pages the pages
-		 * themselves may not yet be coherent with the GPU(swap-in). If
-		 * we are missing the flush then we should see the stale cache
-		 * values after we do the set_to_cpu_domain and pick it up as a
-		 * test failure.
-		 */
-		memset32(vaddr, val ^ 0xdeadbeaf,
-			 huge_gem_object_phys_size(obj) / sizeof(u32));
-
-		if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
-			obj->cache_dirty = true;
-
-		err = i915_gem_schedule_fill_pages_blt(obj, ce, obj->mm.pages,
-						       &obj->mm.page_sizes,
-						       val);
-		if (err)
-			goto err_unpin;
-
-		i915_gem_object_lock(obj, NULL);
-		err = i915_gem_object_set_to_cpu_domain(obj, false);
-		i915_gem_object_unlock(obj);
-		if (err)
-			goto err_unpin;
-
-		for (i = 0; i < huge_gem_object_phys_size(obj) / sizeof(u32); ++i) {
-			if (vaddr[i] != val) {
-				pr_err("vaddr[%u]=%x, expected=%x\n", i,
-				       vaddr[i], val);
-				err = -EINVAL;
-				goto err_unpin;
-			}
-		}
-
-		i915_gem_object_unpin_map(obj);
-		i915_gem_object_put(obj);
-	} while (!time_after(jiffies, end));
-
-	goto err_flush;
-
-err_unpin:
-	i915_gem_object_unpin_map(obj);
-err_put:
-	i915_gem_object_put(obj);
-err_flush:
-	if (err == -ENOMEM)
-		err = 0;
-	intel_engine_pm_put(engine);
-
-	return err;
-}
-
-static int igt_client_fill(void *arg)
-{
-	int inst = 0;
-
-	do {
-		struct intel_engine_cs *engine;
-		int err;
-
-		engine = intel_engine_lookup_user(arg,
-						  I915_ENGINE_CLASS_COPY,
-						  inst++);
-		if (!engine)
-			return 0;
-
-		err = __igt_client_fill(engine);
-		if (err == -ENOMEM)
-			err = 0;
-		if (err)
-			return err;
-	} while (1);
-}
-
 #define WIDTH 512
 #define HEIGHT 32
 
@@ -693,7 +582,6 @@ static int igt_client_tiled_blits(void *arg)
 int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
-		SUBTEST(igt_client_fill),
 		SUBTEST(igt_client_tiled_blits),
 	};
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index dbcfa28a9d91..8eb5050f8cb3 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -680,7 +680,7 @@ static int igt_ctx_exec(void *arg)
 			struct i915_gem_context *ctx;
 			struct intel_context *ce;
 
-			ctx = kernel_context(i915);
+			ctx = kernel_context(i915, NULL);
 			if (IS_ERR(ctx)) {
 				err = PTR_ERR(ctx);
 				goto out_file;
@@ -813,16 +813,12 @@ static int igt_shared_ctx_exec(void *arg)
 			struct i915_gem_context *ctx;
 			struct intel_context *ce;
 
-			ctx = kernel_context(i915);
+			ctx = kernel_context(i915, ctx_vm(parent));
 			if (IS_ERR(ctx)) {
 				err = PTR_ERR(ctx);
 				goto out_test;
 			}
 
-			mutex_lock(&ctx->mutex);
-			__assign_ppgtt(ctx, ctx_vm(parent));
-			mutex_unlock(&ctx->mutex);
-
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 			GEM_BUG_ON(IS_ERR(ce));
 
@@ -1875,125 +1871,6 @@ out_file:
 	return err;
 }
 
-static bool skip_unused_engines(struct intel_context *ce, void *data)
-{
-	return !ce->state;
-}
-
-static void mock_barrier_task(void *data)
-{
-	unsigned int *counter = data;
-
-	++*counter;
-}
-
-static int mock_context_barrier(void *arg)
-{
-#undef pr_fmt
-#define pr_fmt(x) "context_barrier_task():" # x
-	struct drm_i915_private *i915 = arg;
-	struct i915_gem_context *ctx;
-	struct i915_request *rq;
-	unsigned int counter;
-	int err;
-
-	/*
-	 * The context barrier provides us with a callback after it emits
-	 * a request; useful for retiring old state after loading new.
-	 */
-
-	ctx = mock_context(i915, "mock");
-	if (!ctx)
-		return -ENOMEM;
-
-	counter = 0;
-	err = context_barrier_task(ctx, 0, NULL, NULL, NULL,
-				   mock_barrier_task, &counter);
-	if (err) {
-		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
-		goto out;
-	}
-	if (counter == 0) {
-		pr_err("Did not retire immediately with 0 engines\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	counter = 0;
-	err = context_barrier_task(ctx, ALL_ENGINES, skip_unused_engines,
-				   NULL, NULL, mock_barrier_task, &counter);
-	if (err) {
-		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
-		goto out;
-	}
-	if (counter == 0) {
-		pr_err("Did not retire immediately for all unused engines\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	rq = igt_request_alloc(ctx, i915->gt.engine[RCS0]);
-	if (IS_ERR(rq)) {
-		pr_err("Request allocation failed!\n");
-		goto out;
-	}
-	i915_request_add(rq);
-
-	counter = 0;
-	context_barrier_inject_fault = BIT(RCS0);
-	err = context_barrier_task(ctx, ALL_ENGINES, NULL, NULL, NULL,
-				   mock_barrier_task, &counter);
-	context_barrier_inject_fault = 0;
-	if (err == -ENXIO)
-		err = 0;
-	else
-		pr_err("Did not hit fault injection!\n");
-	if (counter != 0) {
-		pr_err("Invoked callback on error!\n");
-		err = -EIO;
-	}
-	if (err)
-		goto out;
-
-	counter = 0;
-	err = context_barrier_task(ctx, ALL_ENGINES, skip_unused_engines,
-				   NULL, NULL, mock_barrier_task, &counter);
-	if (err) {
-		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
-		goto out;
-	}
-	mock_device_flush(i915);
-	if (counter == 0) {
-		pr_err("Did not retire on each active engines\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-out:
-	mock_context_close(ctx);
-	return err;
-#undef pr_fmt
-#define pr_fmt(x) x
-}
-
-int i915_gem_context_mock_selftests(void)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(mock_context_barrier),
-	};
-	struct drm_i915_private *i915;
-	int err;
-
-	i915 = mock_gem_device();
-	if (!i915)
-		return -ENOMEM;
-
-	err = i915_subtests(tests, i915);
-
-	mock_destroy_device(i915);
-	return err;
-}
-
 int i915_gem_context_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index dd74bc09ec88..ffae7df5e4d7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -35,7 +35,7 @@ static int igt_dmabuf_export(void *arg)
 static int igt_dmabuf_import_self(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj, *import_obj;
 	struct drm_gem_object *import;
 	struct dma_buf *dmabuf;
 	int err;
@@ -65,10 +65,19 @@ static int igt_dmabuf_import_self(void *arg)
 		err = -EINVAL;
 		goto out_import;
 	}
+	import_obj = to_intel_bo(import);
+
+	i915_gem_object_lock(import_obj, NULL);
+	err = __i915_gem_object_get_pages(import_obj);
+	i915_gem_object_unlock(import_obj);
+	if (err) {
+		pr_err("Same object dma-buf get_pages failed!\n");
+		goto out_import;
+	}
 
 	err = 0;
 out_import:
-	i915_gem_object_put(to_intel_bo(import));
+	i915_gem_object_put(import_obj);
 out_dmabuf:
 	dma_buf_put(dmabuf);
 out:
@@ -76,6 +85,180 @@ out:
 	return err;
 }
 
+static int igt_dmabuf_import_same_driver_lmem(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *lmem = i915->mm.regions[INTEL_REGION_LMEM];
+	struct drm_i915_gem_object *obj;
+	struct drm_gem_object *import;
+	struct dma_buf *dmabuf;
+	int err;
+
+	if (!lmem)
+		return 0;
+
+	force_different_devices = true;
+
+	obj = __i915_gem_object_create_user(i915, PAGE_SIZE, &lmem, 1);
+	if (IS_ERR(obj)) {
+		pr_err("__i915_gem_object_create_user failed with err=%ld\n",
+		       PTR_ERR(dmabuf));
+		err = PTR_ERR(obj);
+		goto out_ret;
+	}
+
+	dmabuf = i915_gem_prime_export(&obj->base, 0);
+	if (IS_ERR(dmabuf)) {
+		pr_err("i915_gem_prime_export failed with err=%ld\n",
+		       PTR_ERR(dmabuf));
+		err = PTR_ERR(dmabuf);
+		goto out;
+	}
+
+	/*
+	 * We expect an import of an LMEM-only object to fail with
+	 * -EOPNOTSUPP because it can't be migrated to SMEM.
+	 */
+	import = i915_gem_prime_import(&i915->drm, dmabuf);
+	if (!IS_ERR(import)) {
+		drm_gem_object_put(import);
+		pr_err("i915_gem_prime_import succeeded when it shouldn't have\n");
+		err = -EINVAL;
+	} else if (PTR_ERR(import) != -EOPNOTSUPP) {
+		pr_err("i915_gem_prime_import failed with the wrong err=%ld\n",
+		       PTR_ERR(import));
+		err = PTR_ERR(import);
+	}
+
+	dma_buf_put(dmabuf);
+out:
+	i915_gem_object_put(obj);
+out_ret:
+	force_different_devices = false;
+	return err;
+}
+
+static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
+					 struct intel_memory_region **regions,
+					 unsigned int num_regions)
+{
+	struct drm_i915_gem_object *obj, *import_obj;
+	struct drm_gem_object *import;
+	struct dma_buf *dmabuf;
+	struct dma_buf_attachment *import_attach;
+	struct sg_table *st;
+	long timeout;
+	int err;
+
+	force_different_devices = true;
+
+	obj = __i915_gem_object_create_user(i915, PAGE_SIZE,
+					    regions, num_regions);
+	if (IS_ERR(obj)) {
+		pr_err("__i915_gem_object_create_user failed with err=%ld\n",
+		       PTR_ERR(dmabuf));
+		err = PTR_ERR(obj);
+		goto out_ret;
+	}
+
+	dmabuf = i915_gem_prime_export(&obj->base, 0);
+	if (IS_ERR(dmabuf)) {
+		pr_err("i915_gem_prime_export failed with err=%ld\n",
+		       PTR_ERR(dmabuf));
+		err = PTR_ERR(dmabuf);
+		goto out;
+	}
+
+	import = i915_gem_prime_import(&i915->drm, dmabuf);
+	if (IS_ERR(import)) {
+		pr_err("i915_gem_prime_import failed with err=%ld\n",
+		       PTR_ERR(import));
+		err = PTR_ERR(import);
+		goto out_dmabuf;
+	}
+
+	if (import == &obj->base) {
+		pr_err("i915_gem_prime_import reused gem object!\n");
+		err = -EINVAL;
+		goto out_import;
+	}
+
+	import_obj = to_intel_bo(import);
+
+	i915_gem_object_lock(import_obj, NULL);
+	err = __i915_gem_object_get_pages(import_obj);
+	if (err) {
+		pr_err("Different objects dma-buf get_pages failed!\n");
+		i915_gem_object_unlock(import_obj);
+		goto out_import;
+	}
+
+	/*
+	 * If the exported object is not in system memory, something
+	 * weird is going on. TODO: When p2p is supported, this is no
+	 * longer considered weird.
+	 */
+	if (obj->mm.region != i915->mm.regions[INTEL_REGION_SMEM]) {
+		pr_err("Exported dma-buf is not in system memory\n");
+		err = -EINVAL;
+	}
+
+	i915_gem_object_unlock(import_obj);
+
+	/* Now try a fake an importer */
+	import_attach = dma_buf_attach(dmabuf, obj->base.dev->dev);
+	if (IS_ERR(import_attach)) {
+		err = PTR_ERR(import_attach);
+		goto out_import;
+	}
+
+	st = dma_buf_map_attachment(import_attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(st)) {
+		err = PTR_ERR(st);
+		goto out_detach;
+	}
+
+	timeout = dma_resv_wait_timeout(dmabuf->resv, false, true, 5 * HZ);
+	if (!timeout) {
+		pr_err("dmabuf wait for exclusive fence timed out.\n");
+		timeout = -ETIME;
+	}
+	err = timeout > 0 ? 0 : timeout;
+	dma_buf_unmap_attachment(import_attach, st, DMA_BIDIRECTIONAL);
+out_detach:
+	dma_buf_detach(dmabuf, import_attach);
+out_import:
+	i915_gem_object_put(import_obj);
+out_dmabuf:
+	dma_buf_put(dmabuf);
+out:
+	i915_gem_object_put(obj);
+out_ret:
+	force_different_devices = false;
+	return err;
+}
+
+static int igt_dmabuf_import_same_driver_smem(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *smem = i915->mm.regions[INTEL_REGION_SMEM];
+
+	return igt_dmabuf_import_same_driver(i915, &smem, 1);
+}
+
+static int igt_dmabuf_import_same_driver_lmem_smem(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *regions[2];
+
+	if (!i915->mm.regions[INTEL_REGION_LMEM])
+		return 0;
+
+	regions[0] = i915->mm.regions[INTEL_REGION_LMEM];
+	regions[1] = i915->mm.regions[INTEL_REGION_SMEM];
+	return igt_dmabuf_import_same_driver(i915, regions, 2);
+}
+
 static int igt_dmabuf_import(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -286,6 +469,9 @@ int i915_gem_dmabuf_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_dmabuf_export),
+		SUBTEST(igt_dmabuf_import_same_driver_lmem),
+		SUBTEST(igt_dmabuf_import_same_driver_smem),
+		SUBTEST(igt_dmabuf_import_same_driver_lmem_smem),
 	};
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
new file mode 100644
index 000000000000..28a700f08b49
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020-2021 Intel Corporation
+ */
+
+#include "gt/intel_migrate.h"
+
+static int igt_fill_check_buffer(struct drm_i915_gem_object *obj,
+				 bool fill)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	unsigned int i, count = obj->base.size / sizeof(u32);
+	enum i915_map_type map_type =
+		i915_coherent_map_type(i915, obj, false);
+	u32 *cur;
+	int err = 0;
+
+	assert_object_held(obj);
+	cur = i915_gem_object_pin_map(obj, map_type);
+	if (IS_ERR(cur))
+		return PTR_ERR(cur);
+
+	if (fill)
+		for (i = 0; i < count; ++i)
+			*cur++ = i;
+	else
+		for (i = 0; i < count; ++i)
+			if (*cur++ != i) {
+				pr_err("Object content mismatch at location %d of %d\n", i, count);
+				err = -EINVAL;
+				break;
+			}
+
+	i915_gem_object_unpin_map(obj);
+
+	return err;
+}
+
+static int igt_create_migrate(struct intel_gt *gt, enum intel_region_id src,
+			      enum intel_region_id dst)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_memory_region *src_mr = i915->mm.regions[src];
+	struct drm_i915_gem_object *obj;
+	struct i915_gem_ww_ctx ww;
+	int err = 0;
+
+	GEM_BUG_ON(!src_mr);
+
+	/* Switch object backing-store on create */
+	obj = i915_gem_object_create_region(src_mr, PAGE_SIZE, 0, 0);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	for_i915_gem_ww(&ww, err, true) {
+		err = i915_gem_object_lock(obj, &ww);
+		if (err)
+			continue;
+
+		err = igt_fill_check_buffer(obj, true);
+		if (err)
+			continue;
+
+		err = i915_gem_object_migrate(obj, &ww, dst);
+		if (err)
+			continue;
+
+		err = i915_gem_object_pin_pages(obj);
+		if (err)
+			continue;
+
+		if (i915_gem_object_can_migrate(obj, src))
+			err = -EINVAL;
+
+		i915_gem_object_unpin_pages(obj);
+		err = i915_gem_object_wait_migration(obj, true);
+		if (err)
+			continue;
+
+		err = igt_fill_check_buffer(obj, false);
+	}
+	i915_gem_object_put(obj);
+
+	return err;
+}
+
+static int igt_smem_create_migrate(void *arg)
+{
+	return igt_create_migrate(arg, INTEL_REGION_LMEM, INTEL_REGION_SMEM);
+}
+
+static int igt_lmem_create_migrate(void *arg)
+{
+	return igt_create_migrate(arg, INTEL_REGION_SMEM, INTEL_REGION_LMEM);
+}
+
+static int igt_same_create_migrate(void *arg)
+{
+	return igt_create_migrate(arg, INTEL_REGION_LMEM, INTEL_REGION_LMEM);
+}
+
+static int lmem_pages_migrate_one(struct i915_gem_ww_ctx *ww,
+				  struct drm_i915_gem_object *obj)
+{
+	int err;
+
+	err = i915_gem_object_lock(obj, ww);
+	if (err)
+		return err;
+
+	if (i915_gem_object_is_lmem(obj)) {
+		err = i915_gem_object_migrate(obj, ww, INTEL_REGION_SMEM);
+		if (err) {
+			pr_err("Object failed migration to smem\n");
+			if (err)
+				return err;
+		}
+
+		if (i915_gem_object_is_lmem(obj)) {
+			pr_err("object still backed by lmem\n");
+			err = -EINVAL;
+		}
+
+		if (!i915_gem_object_has_struct_page(obj)) {
+			pr_err("object not backed by struct page\n");
+			err = -EINVAL;
+		}
+
+	} else {
+		err = i915_gem_object_migrate(obj, ww, INTEL_REGION_LMEM);
+		if (err) {
+			pr_err("Object failed migration to lmem\n");
+			if (err)
+				return err;
+		}
+
+		if (i915_gem_object_has_struct_page(obj)) {
+			pr_err("object still backed by struct page\n");
+			err = -EINVAL;
+		}
+
+		if (!i915_gem_object_is_lmem(obj)) {
+			pr_err("object not backed by lmem\n");
+			err = -EINVAL;
+		}
+	}
+
+	return err;
+}
+
+static int igt_lmem_pages_migrate(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct drm_i915_private *i915 = gt->i915;
+	struct drm_i915_gem_object *obj;
+	struct i915_gem_ww_ctx ww;
+	struct i915_request *rq;
+	int err;
+	int i;
+
+	/* From LMEM to shmem and back again */
+
+	obj = i915_gem_object_create_lmem(i915, SZ_2M, 0);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	/* Initial GPU fill, sync, CPU initialization. */
+	for_i915_gem_ww(&ww, err, true) {
+		err = i915_gem_object_lock(obj, &ww);
+		if (err)
+			continue;
+
+		err = ____i915_gem_object_get_pages(obj);
+		if (err)
+			continue;
+
+		err = intel_migrate_clear(&gt->migrate, &ww, NULL,
+					  obj->mm.pages->sgl, obj->cache_level,
+					  i915_gem_object_is_lmem(obj),
+					  0xdeadbeaf, &rq);
+		if (rq) {
+			dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
+			i915_request_put(rq);
+		}
+		if (err)
+			continue;
+
+		err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE,
+					   5 * HZ);
+		if (err)
+			continue;
+
+		err = igt_fill_check_buffer(obj, true);
+		if (err)
+			continue;
+	}
+	if (err)
+		goto out_put;
+
+	/*
+	 * Migrate to and from smem without explicitly syncing.
+	 * Finalize with data in smem for fast readout.
+	 */
+	for (i = 1; i <= 5; ++i) {
+		for_i915_gem_ww(&ww, err, true)
+			err = lmem_pages_migrate_one(&ww, obj);
+		if (err)
+			goto out_put;
+	}
+
+	err = i915_gem_object_lock_interruptible(obj, NULL);
+	if (err)
+		goto out_put;
+
+	/* Finally sync migration and check content. */
+	err = i915_gem_object_wait_migration(obj, true);
+	if (err)
+		goto out_unlock;
+
+	err = igt_fill_check_buffer(obj, false);
+
+out_unlock:
+	i915_gem_object_unlock(obj);
+out_put:
+	i915_gem_object_put(obj);
+
+	return err;
+}
+
+int i915_gem_migrate_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_smem_create_migrate),
+		SUBTEST(igt_lmem_create_migrate),
+		SUBTEST(igt_same_create_migrate),
+		SUBTEST(igt_lmem_pages_migrate),
+	};
+
+	if (!HAS_LMEM(i915))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 5575172c66f5..b20f5621f62b 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -573,21 +573,30 @@ err:
 	return 0;
 }
 
+static enum i915_mmap_type default_mapping(struct drm_i915_private *i915)
+{
+	if (HAS_LMEM(i915))
+		return I915_MMAP_TYPE_FIXED;
+
+	return I915_MMAP_TYPE_GTT;
+}
+
 static bool assert_mmap_offset(struct drm_i915_private *i915,
 			       unsigned long size,
 			       int expected)
 {
 	struct drm_i915_gem_object *obj;
-	struct i915_mmap_offset *mmo;
+	u64 offset;
+	int ret;
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return false;
+		return expected && expected == PTR_ERR(obj);
 
-	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
+	ret = __assign_mmap_offset(obj, default_mapping(i915), &offset, NULL);
 	i915_gem_object_put(obj);
 
-	return PTR_ERR_OR_ZERO(mmo) == expected;
+	return ret == expected;
 }
 
 static void disable_retire_worker(struct drm_i915_private *i915)
@@ -622,8 +631,8 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	struct drm_mm *mm = &i915->drm.vma_offset_manager->vm_addr_space_mm;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *hole, *next;
-	struct i915_mmap_offset *mmo;
 	int loop, err = 0;
+	u64 offset;
 
 	/* Disable background reaper */
 	disable_retire_worker(i915);
@@ -684,13 +693,13 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
+		pr_err("Unable to create object for reclaimed hole\n");
 		goto out;
 	}
 
-	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
-	if (IS_ERR(mmo)) {
+	err = __assign_mmap_offset(obj, default_mapping(i915), &offset, NULL);
+	if (err) {
 		pr_err("Unable to insert object into reclaimed hole\n");
-		err = PTR_ERR(mmo);
 		goto err_obj;
 	}
 
@@ -830,34 +839,25 @@ static int wc_check(struct drm_i915_gem_object *obj)
 
 static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
 {
-	if (type == I915_MMAP_TYPE_GTT &&
-	    !i915_ggtt_has_aperture(&to_i915(obj->base.dev)->ggtt))
-		return false;
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	bool no_map;
 
-	if (type != I915_MMAP_TYPE_GTT &&
-	    !i915_gem_object_has_struct_page(obj) &&
-	    !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM))
+	if (HAS_LMEM(i915))
+		return type == I915_MMAP_TYPE_FIXED;
+	else if (type == I915_MMAP_TYPE_FIXED)
 		return false;
 
-	return true;
-}
-
-static void object_set_placements(struct drm_i915_gem_object *obj,
-				  struct intel_memory_region **placements,
-				  unsigned int n_placements)
-{
-	GEM_BUG_ON(!n_placements);
+	if (type == I915_MMAP_TYPE_GTT &&
+	    !i915_ggtt_has_aperture(&to_i915(obj->base.dev)->ggtt))
+		return false;
 
-	if (n_placements == 1) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
-		struct intel_memory_region *mr = placements[0];
+	i915_gem_object_lock(obj, NULL);
+	no_map = (type != I915_MMAP_TYPE_GTT &&
+		  !i915_gem_object_has_struct_page(obj) &&
+		  !i915_gem_object_has_iomem(obj));
+	i915_gem_object_unlock(obj);
 
-		obj->mm.placements = &i915->mm.regions[mr->id];
-		obj->mm.n_placements = 1;
-	} else {
-		obj->mm.placements = placements;
-		obj->mm.n_placements = n_placements;
-	}
+	return !no_map;
 }
 
 #define expand32(x) (((x) << 0) | ((x) << 8) | ((x) << 16) | ((x) << 24))
@@ -865,10 +865,10 @@ static int __igt_mmap(struct drm_i915_private *i915,
 		      struct drm_i915_gem_object *obj,
 		      enum i915_mmap_type type)
 {
-	struct i915_mmap_offset *mmo;
 	struct vm_area_struct *area;
 	unsigned long addr;
 	int err, i;
+	u64 offset;
 
 	if (!can_mmap(obj, type))
 		return 0;
@@ -879,11 +879,11 @@ static int __igt_mmap(struct drm_i915_private *i915,
 	if (err)
 		return err;
 
-	mmo = mmap_offset_attach(obj, type, NULL);
-	if (IS_ERR(mmo))
-		return PTR_ERR(mmo);
+	err = __assign_mmap_offset(obj, type, &offset, NULL);
+	if (err)
+		return err;
 
-	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED);
 	if (IS_ERR_VALUE(addr))
 		return addr;
 
@@ -897,13 +897,6 @@ static int __igt_mmap(struct drm_i915_private *i915,
 		goto out_unmap;
 	}
 
-	if (area->vm_private_data != mmo) {
-		pr_err("%s: vm_area_struct did not point back to our mmap_offset object!\n",
-		       obj->mm.region->name);
-		err = -EINVAL;
-		goto out_unmap;
-	}
-
 	for (i = 0; i < obj->base.size / sizeof(u32); i++) {
 		u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux)));
 		u32 x;
@@ -961,18 +954,18 @@ static int igt_mmap(void *arg)
 			struct drm_i915_gem_object *obj;
 			int err;
 
-			obj = i915_gem_object_create_region(mr, sizes[i], 0);
+			obj = __i915_gem_object_create_user(i915, sizes[i], &mr, 1);
 			if (obj == ERR_PTR(-ENODEV))
 				continue;
 
 			if (IS_ERR(obj))
 				return PTR_ERR(obj);
 
-			object_set_placements(obj, &mr, 1);
-
 			err = __igt_mmap(i915, obj, I915_MMAP_TYPE_GTT);
 			if (err == 0)
 				err = __igt_mmap(i915, obj, I915_MMAP_TYPE_WC);
+			if (err == 0)
+				err = __igt_mmap(i915, obj, I915_MMAP_TYPE_FIXED);
 
 			i915_gem_object_put(obj);
 			if (err)
@@ -990,26 +983,33 @@ static const char *repr_mmap_type(enum i915_mmap_type type)
 	case I915_MMAP_TYPE_WB: return "wb";
 	case I915_MMAP_TYPE_WC: return "wc";
 	case I915_MMAP_TYPE_UC: return "uc";
+	case I915_MMAP_TYPE_FIXED: return "fixed";
 	default: return "unknown";
 	}
 }
 
-static bool can_access(const struct drm_i915_gem_object *obj)
+static bool can_access(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_object_has_struct_page(obj) ||
-	       i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM);
+	bool access;
+
+	i915_gem_object_lock(obj, NULL);
+	access = i915_gem_object_has_struct_page(obj) ||
+		i915_gem_object_has_iomem(obj);
+	i915_gem_object_unlock(obj);
+
+	return access;
 }
 
 static int __igt_mmap_access(struct drm_i915_private *i915,
 			     struct drm_i915_gem_object *obj,
 			     enum i915_mmap_type type)
 {
-	struct i915_mmap_offset *mmo;
 	unsigned long __user *ptr;
 	unsigned long A, B;
 	unsigned long x, y;
 	unsigned long addr;
 	int err;
+	u64 offset;
 
 	memset(&A, 0xAA, sizeof(A));
 	memset(&B, 0xBB, sizeof(B));
@@ -1017,11 +1017,11 @@ static int __igt_mmap_access(struct drm_i915_private *i915,
 	if (!can_mmap(obj, type) || !can_access(obj))
 		return 0;
 
-	mmo = mmap_offset_attach(obj, type, NULL);
-	if (IS_ERR(mmo))
-		return PTR_ERR(mmo);
+	err = __assign_mmap_offset(obj, type, &offset, NULL);
+	if (err)
+		return err;
 
-	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED);
 	if (IS_ERR_VALUE(addr))
 		return addr;
 	ptr = (unsigned long __user *)addr;
@@ -1081,15 +1081,13 @@ static int igt_mmap_access(void *arg)
 		struct drm_i915_gem_object *obj;
 		int err;
 
-		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		obj = __i915_gem_object_create_user(i915, PAGE_SIZE, &mr, 1);
 		if (obj == ERR_PTR(-ENODEV))
 			continue;
 
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
-		object_set_placements(obj, &mr, 1);
-
 		err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WB);
@@ -1097,6 +1095,8 @@ static int igt_mmap_access(void *arg)
 			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WC);
 		if (err == 0)
 			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_UC);
+		if (err == 0)
+			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_FIXED);
 
 		i915_gem_object_put(obj);
 		if (err)
@@ -1111,11 +1111,11 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 			  enum i915_mmap_type type)
 {
 	struct intel_engine_cs *engine;
-	struct i915_mmap_offset *mmo;
 	unsigned long addr;
 	u32 __user *ux;
 	u32 bbe;
 	int err;
+	u64 offset;
 
 	/*
 	 * Verify that the mmap access into the backing store aligns with
@@ -1132,11 +1132,11 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 	if (err)
 		return err;
 
-	mmo = mmap_offset_attach(obj, type, NULL);
-	if (IS_ERR(mmo))
-		return PTR_ERR(mmo);
+	err = __assign_mmap_offset(obj, type, &offset, NULL);
+	if (err)
+		return err;
 
-	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED);
 	if (IS_ERR_VALUE(addr))
 		return addr;
 
@@ -1226,18 +1226,18 @@ static int igt_mmap_gpu(void *arg)
 		struct drm_i915_gem_object *obj;
 		int err;
 
-		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		obj = __i915_gem_object_create_user(i915, PAGE_SIZE, &mr, 1);
 		if (obj == ERR_PTR(-ENODEV))
 			continue;
 
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
-		object_set_placements(obj, &mr, 1);
-
 		err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_WC);
+		if (err == 0)
+			err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_FIXED);
 
 		i915_gem_object_put(obj);
 		if (err)
@@ -1303,18 +1303,18 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915,
 			     struct drm_i915_gem_object *obj,
 			     enum i915_mmap_type type)
 {
-	struct i915_mmap_offset *mmo;
 	unsigned long addr;
 	int err;
+	u64 offset;
 
 	if (!can_mmap(obj, type))
 		return 0;
 
-	mmo = mmap_offset_attach(obj, type, NULL);
-	if (IS_ERR(mmo))
-		return PTR_ERR(mmo);
+	err = __assign_mmap_offset(obj, type, &offset, NULL);
+	if (err)
+		return err;
 
-	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED);
 	if (IS_ERR_VALUE(addr))
 		return addr;
 
@@ -1350,10 +1350,20 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915,
 		}
 	}
 
-	err = check_absent(addr, obj->base.size);
-	if (err) {
-		pr_err("%s: was not absent\n", obj->mm.region->name);
-		goto out_unmap;
+	if (!obj->ops->mmap_ops) {
+		err = check_absent(addr, obj->base.size);
+		if (err) {
+			pr_err("%s: was not absent\n", obj->mm.region->name);
+			goto out_unmap;
+		}
+	} else {
+		/* ttm allows access to evicted regions by design */
+
+		err = check_present(addr, obj->base.size);
+		if (err) {
+			pr_err("%s: was not present\n", obj->mm.region->name);
+			goto out_unmap;
+		}
 	}
 
 out_unmap:
@@ -1371,18 +1381,18 @@ static int igt_mmap_revoke(void *arg)
 		struct drm_i915_gem_object *obj;
 		int err;
 
-		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		obj = __i915_gem_object_create_user(i915, PAGE_SIZE, &mr, 1);
 		if (obj == ERR_PTR(-ENODEV))
 			continue;
 
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
-		object_set_placements(obj, &mr, 1);
-
 		err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_WC);
+		if (err == 0)
+			err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_FIXED);
 
 		i915_gem_object_put(obj);
 		if (err)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
deleted file mode 100644
index 8c335d1a8406..000000000000
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ /dev/null
@@ -1,597 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include <linux/sort.h>
-
-#include "gt/intel_gt.h"
-#include "gt/intel_engine_user.h"
-
-#include "i915_selftest.h"
-
-#include "gem/i915_gem_context.h"
-#include "selftests/igt_flush_test.h"
-#include "selftests/i915_random.h"
-#include "selftests/mock_drm.h"
-#include "huge_gem_object.h"
-#include "mock_context.h"
-
-static int wrap_ktime_compare(const void *A, const void *B)
-{
-	const ktime_t *a = A, *b = B;
-
-	return ktime_compare(*a, *b);
-}
-
-static int __perf_fill_blt(struct drm_i915_gem_object *obj)
-{
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	int inst = 0;
-
-	do {
-		struct intel_engine_cs *engine;
-		ktime_t t[5];
-		int pass;
-		int err;
-
-		engine = intel_engine_lookup_user(i915,
-						  I915_ENGINE_CLASS_COPY,
-						  inst++);
-		if (!engine)
-			return 0;
-
-		intel_engine_pm_get(engine);
-		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
-			struct intel_context *ce = engine->kernel_context;
-			ktime_t t0, t1;
-
-			t0 = ktime_get();
-
-			err = i915_gem_object_fill_blt(obj, ce, 0);
-			if (err)
-				break;
-
-			err = i915_gem_object_wait(obj,
-						   I915_WAIT_ALL,
-						   MAX_SCHEDULE_TIMEOUT);
-			if (err)
-				break;
-
-			t1 = ktime_get();
-			t[pass] = ktime_sub(t1, t0);
-		}
-		intel_engine_pm_put(engine);
-		if (err)
-			return err;
-
-		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
-		pr_info("%s: blt %zd KiB fill: %lld MiB/s\n",
-			engine->name,
-			obj->base.size >> 10,
-			div64_u64(mul_u32_u32(4 * obj->base.size,
-					      1000 * 1000 * 1000),
-				  t[1] + 2 * t[2] + t[3]) >> 20);
-	} while (1);
-}
-
-static int perf_fill_blt(void *arg)
-{
-	struct drm_i915_private *i915 = arg;
-	static const unsigned long sizes[] = {
-		SZ_4K,
-		SZ_64K,
-		SZ_2M,
-		SZ_64M
-	};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
-		struct drm_i915_gem_object *obj;
-		int err;
-
-		obj = i915_gem_object_create_internal(i915, sizes[i]);
-		if (IS_ERR(obj))
-			return PTR_ERR(obj);
-
-		err = __perf_fill_blt(obj);
-		i915_gem_object_put(obj);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int __perf_copy_blt(struct drm_i915_gem_object *src,
-			   struct drm_i915_gem_object *dst)
-{
-	struct drm_i915_private *i915 = to_i915(src->base.dev);
-	int inst = 0;
-
-	do {
-		struct intel_engine_cs *engine;
-		ktime_t t[5];
-		int pass;
-		int err = 0;
-
-		engine = intel_engine_lookup_user(i915,
-						  I915_ENGINE_CLASS_COPY,
-						  inst++);
-		if (!engine)
-			return 0;
-
-		intel_engine_pm_get(engine);
-		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
-			struct intel_context *ce = engine->kernel_context;
-			ktime_t t0, t1;
-
-			t0 = ktime_get();
-
-			err = i915_gem_object_copy_blt(src, dst, ce);
-			if (err)
-				break;
-
-			err = i915_gem_object_wait(dst,
-						   I915_WAIT_ALL,
-						   MAX_SCHEDULE_TIMEOUT);
-			if (err)
-				break;
-
-			t1 = ktime_get();
-			t[pass] = ktime_sub(t1, t0);
-		}
-		intel_engine_pm_put(engine);
-		if (err)
-			return err;
-
-		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
-		pr_info("%s: blt %zd KiB copy: %lld MiB/s\n",
-			engine->name,
-			src->base.size >> 10,
-			div64_u64(mul_u32_u32(4 * src->base.size,
-					      1000 * 1000 * 1000),
-				  t[1] + 2 * t[2] + t[3]) >> 20);
-	} while (1);
-}
-
-static int perf_copy_blt(void *arg)
-{
-	struct drm_i915_private *i915 = arg;
-	static const unsigned long sizes[] = {
-		SZ_4K,
-		SZ_64K,
-		SZ_2M,
-		SZ_64M
-	};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
-		struct drm_i915_gem_object *src, *dst;
-		int err;
-
-		src = i915_gem_object_create_internal(i915, sizes[i]);
-		if (IS_ERR(src))
-			return PTR_ERR(src);
-
-		dst = i915_gem_object_create_internal(i915, sizes[i]);
-		if (IS_ERR(dst)) {
-			err = PTR_ERR(dst);
-			goto err_src;
-		}
-
-		err = __perf_copy_blt(src, dst);
-
-		i915_gem_object_put(dst);
-err_src:
-		i915_gem_object_put(src);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-struct igt_thread_arg {
-	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
-	struct file *file;
-	struct rnd_state prng;
-	unsigned int n_cpus;
-};
-
-static int igt_fill_blt_thread(void *arg)
-{
-	struct igt_thread_arg *thread = arg;
-	struct intel_engine_cs *engine = thread->engine;
-	struct rnd_state *prng = &thread->prng;
-	struct drm_i915_gem_object *obj;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
-	unsigned int prio;
-	IGT_TIMEOUT(end);
-	u64 total, max;
-	int err;
-
-	ctx = thread->ctx;
-	if (!ctx) {
-		ctx = live_context_for_engine(engine, thread->file);
-		if (IS_ERR(ctx))
-			return PTR_ERR(ctx);
-
-		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-		ctx->sched.priority = prio;
-	}
-
-	ce = i915_gem_context_get_engine(ctx, 0);
-	GEM_BUG_ON(IS_ERR(ce));
-
-	/*
-	 * If we have a tiny shared address space, like for the GGTT
-	 * then we can't be too greedy.
-	 */
-	max = ce->vm->total;
-	if (i915_is_ggtt(ce->vm) || thread->ctx)
-		max = div_u64(max, thread->n_cpus);
-	max >>= 4;
-
-	total = PAGE_SIZE;
-	do {
-		/* Aim to keep the runtime under reasonable bounds! */
-		const u32 max_phys_size = SZ_64K;
-		u32 val = prandom_u32_state(prng);
-		u32 phys_sz;
-		u32 sz;
-		u32 *vaddr;
-		u32 i;
-
-		total = min(total, max);
-		sz = i915_prandom_u32_max_state(total, prng) + 1;
-		phys_sz = sz % max_phys_size + 1;
-
-		sz = round_up(sz, PAGE_SIZE);
-		phys_sz = round_up(phys_sz, PAGE_SIZE);
-		phys_sz = min(phys_sz, sz);
-
-		pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
-			 phys_sz, sz, val);
-
-		obj = huge_gem_object(engine->i915, phys_sz, sz);
-		if (IS_ERR(obj)) {
-			err = PTR_ERR(obj);
-			goto err_flush;
-		}
-
-		vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto err_put;
-		}
-
-		/*
-		 * Make sure the potentially async clflush does its job, if
-		 * required.
-		 */
-		memset32(vaddr, val ^ 0xdeadbeaf,
-			 huge_gem_object_phys_size(obj) / sizeof(u32));
-
-		if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
-			obj->cache_dirty = true;
-
-		err = i915_gem_object_fill_blt(obj, ce, val);
-		if (err)
-			goto err_unpin;
-
-		err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
-		if (err)
-			goto err_unpin;
-
-		for (i = 0; i < huge_gem_object_phys_size(obj) / sizeof(u32); i += 17) {
-			if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
-				drm_clflush_virt_range(&vaddr[i], sizeof(vaddr[i]));
-
-			if (vaddr[i] != val) {
-				pr_err("vaddr[%u]=%x, expected=%x\n", i,
-				       vaddr[i], val);
-				err = -EINVAL;
-				goto err_unpin;
-			}
-		}
-
-		i915_gem_object_unpin_map(obj);
-		i915_gem_object_put(obj);
-
-		total <<= 1;
-	} while (!time_after(jiffies, end));
-
-	goto err_flush;
-
-err_unpin:
-	i915_gem_object_unpin_map(obj);
-err_put:
-	i915_gem_object_put(obj);
-err_flush:
-	if (err == -ENOMEM)
-		err = 0;
-
-	intel_context_put(ce);
-	return err;
-}
-
-static int igt_copy_blt_thread(void *arg)
-{
-	struct igt_thread_arg *thread = arg;
-	struct intel_engine_cs *engine = thread->engine;
-	struct rnd_state *prng = &thread->prng;
-	struct drm_i915_gem_object *src, *dst;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
-	unsigned int prio;
-	IGT_TIMEOUT(end);
-	u64 total, max;
-	int err;
-
-	ctx = thread->ctx;
-	if (!ctx) {
-		ctx = live_context_for_engine(engine, thread->file);
-		if (IS_ERR(ctx))
-			return PTR_ERR(ctx);
-
-		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-		ctx->sched.priority = prio;
-	}
-
-	ce = i915_gem_context_get_engine(ctx, 0);
-	GEM_BUG_ON(IS_ERR(ce));
-
-	/*
-	 * If we have a tiny shared address space, like for the GGTT
-	 * then we can't be too greedy.
-	 */
-	max = ce->vm->total;
-	if (i915_is_ggtt(ce->vm) || thread->ctx)
-		max = div_u64(max, thread->n_cpus);
-	max >>= 4;
-
-	total = PAGE_SIZE;
-	do {
-		/* Aim to keep the runtime under reasonable bounds! */
-		const u32 max_phys_size = SZ_64K;
-		u32 val = prandom_u32_state(prng);
-		u32 phys_sz;
-		u32 sz;
-		u32 *vaddr;
-		u32 i;
-
-		total = min(total, max);
-		sz = i915_prandom_u32_max_state(total, prng) + 1;
-		phys_sz = sz % max_phys_size + 1;
-
-		sz = round_up(sz, PAGE_SIZE);
-		phys_sz = round_up(phys_sz, PAGE_SIZE);
-		phys_sz = min(phys_sz, sz);
-
-		pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
-			 phys_sz, sz, val);
-
-		src = huge_gem_object(engine->i915, phys_sz, sz);
-		if (IS_ERR(src)) {
-			err = PTR_ERR(src);
-			goto err_flush;
-		}
-
-		vaddr = i915_gem_object_pin_map_unlocked(src, I915_MAP_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto err_put_src;
-		}
-
-		memset32(vaddr, val,
-			 huge_gem_object_phys_size(src) / sizeof(u32));
-
-		i915_gem_object_unpin_map(src);
-
-		if (!(src->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
-			src->cache_dirty = true;
-
-		dst = huge_gem_object(engine->i915, phys_sz, sz);
-		if (IS_ERR(dst)) {
-			err = PTR_ERR(dst);
-			goto err_put_src;
-		}
-
-		vaddr = i915_gem_object_pin_map_unlocked(dst, I915_MAP_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto err_put_dst;
-		}
-
-		memset32(vaddr, val ^ 0xdeadbeaf,
-			 huge_gem_object_phys_size(dst) / sizeof(u32));
-
-		if (!(dst->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
-			dst->cache_dirty = true;
-
-		err = i915_gem_object_copy_blt(src, dst, ce);
-		if (err)
-			goto err_unpin;
-
-		err = i915_gem_object_wait(dst, 0, MAX_SCHEDULE_TIMEOUT);
-		if (err)
-			goto err_unpin;
-
-		for (i = 0; i < huge_gem_object_phys_size(dst) / sizeof(u32); i += 17) {
-			if (!(dst->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
-				drm_clflush_virt_range(&vaddr[i], sizeof(vaddr[i]));
-
-			if (vaddr[i] != val) {
-				pr_err("vaddr[%u]=%x, expected=%x\n", i,
-				       vaddr[i], val);
-				err = -EINVAL;
-				goto err_unpin;
-			}
-		}
-
-		i915_gem_object_unpin_map(dst);
-
-		i915_gem_object_put(src);
-		i915_gem_object_put(dst);
-
-		total <<= 1;
-	} while (!time_after(jiffies, end));
-
-	goto err_flush;
-
-err_unpin:
-	i915_gem_object_unpin_map(dst);
-err_put_dst:
-	i915_gem_object_put(dst);
-err_put_src:
-	i915_gem_object_put(src);
-err_flush:
-	if (err == -ENOMEM)
-		err = 0;
-
-	intel_context_put(ce);
-	return err;
-}
-
-static int igt_threaded_blt(struct intel_engine_cs *engine,
-			    int (*blt_fn)(void *arg),
-			    unsigned int flags)
-#define SINGLE_CTX BIT(0)
-{
-	struct igt_thread_arg *thread;
-	struct task_struct **tsk;
-	unsigned int n_cpus, i;
-	I915_RND_STATE(prng);
-	int err = 0;
-
-	n_cpus = num_online_cpus() + 1;
-
-	tsk = kcalloc(n_cpus, sizeof(struct task_struct *), GFP_KERNEL);
-	if (!tsk)
-		return 0;
-
-	thread = kcalloc(n_cpus, sizeof(struct igt_thread_arg), GFP_KERNEL);
-	if (!thread)
-		goto out_tsk;
-
-	thread[0].file = mock_file(engine->i915);
-	if (IS_ERR(thread[0].file)) {
-		err = PTR_ERR(thread[0].file);
-		goto out_thread;
-	}
-
-	if (flags & SINGLE_CTX) {
-		thread[0].ctx = live_context_for_engine(engine, thread[0].file);
-		if (IS_ERR(thread[0].ctx)) {
-			err = PTR_ERR(thread[0].ctx);
-			goto out_file;
-		}
-	}
-
-	for (i = 0; i < n_cpus; ++i) {
-		thread[i].engine = engine;
-		thread[i].file = thread[0].file;
-		thread[i].ctx = thread[0].ctx;
-		thread[i].n_cpus = n_cpus;
-		thread[i].prng =
-			I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
-
-		tsk[i] = kthread_run(blt_fn, &thread[i], "igt/blt-%d", i);
-		if (IS_ERR(tsk[i])) {
-			err = PTR_ERR(tsk[i]);
-			break;
-		}
-
-		get_task_struct(tsk[i]);
-	}
-
-	yield(); /* start all threads before we kthread_stop() */
-
-	for (i = 0; i < n_cpus; ++i) {
-		int status;
-
-		if (IS_ERR_OR_NULL(tsk[i]))
-			continue;
-
-		status = kthread_stop(tsk[i]);
-		if (status && !err)
-			err = status;
-
-		put_task_struct(tsk[i]);
-	}
-
-out_file:
-	fput(thread[0].file);
-out_thread:
-	kfree(thread);
-out_tsk:
-	kfree(tsk);
-	return err;
-}
-
-static int test_copy_engines(struct drm_i915_private *i915,
-			     int (*fn)(void *arg),
-			     unsigned int flags)
-{
-	struct intel_engine_cs *engine;
-	int ret;
-
-	for_each_uabi_class_engine(engine, I915_ENGINE_CLASS_COPY, i915) {
-		ret = igt_threaded_blt(engine, fn, flags);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static int igt_fill_blt(void *arg)
-{
-	return test_copy_engines(arg, igt_fill_blt_thread, 0);
-}
-
-static int igt_fill_blt_ctx0(void *arg)
-{
-	return test_copy_engines(arg, igt_fill_blt_thread, SINGLE_CTX);
-}
-
-static int igt_copy_blt(void *arg)
-{
-	return test_copy_engines(arg, igt_copy_blt_thread, 0);
-}
-
-static int igt_copy_blt_ctx0(void *arg)
-{
-	return test_copy_engines(arg, igt_copy_blt_thread, SINGLE_CTX);
-}
-
-int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(igt_fill_blt),
-		SUBTEST(igt_fill_blt_ctx0),
-		SUBTEST(igt_copy_blt),
-		SUBTEST(igt_copy_blt_ctx0),
-	};
-
-	if (intel_gt_is_wedged(&i915->gt))
-		return 0;
-
-	return i915_live_subtests(tests, i915);
-}
-
-int i915_gem_object_blt_perf_selftests(struct drm_i915_private *i915)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(perf_fill_blt),
-		SUBTEST(perf_copy_blt),
-	};
-
-	if (intel_gt_is_wedged(&i915->gt))
-		return 0;
-
-	return i915_live_subtests(tests, i915);
-}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
index 3a6ce87f8b52..d43d8dae0f69 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
@@ -25,13 +25,14 @@ static int mock_phys_object(void *arg)
 		goto out;
 	}
 
+	i915_gem_object_lock(obj, NULL);
 	if (!i915_gem_object_has_struct_page(obj)) {
+		i915_gem_object_unlock(obj);
 		err = -EINVAL;
 		pr_err("shmem has no struct page\n");
 		goto out_obj;
 	}
 
-	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_attach_phys(obj, PAGE_SIZE);
 	i915_gem_object_unlock(obj);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 51b5a3421b40..fee070df1c97 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -14,6 +14,7 @@ mock_context(struct drm_i915_private *i915,
 {
 	struct i915_gem_context *ctx;
 	struct i915_gem_engines *e;
+	struct intel_sseu null_sseu = {};
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -30,15 +31,6 @@ mock_context(struct drm_i915_private *i915,
 
 	i915_gem_context_set_persistence(ctx);
 
-	mutex_init(&ctx->engines_mutex);
-	e = default_engines(ctx);
-	if (IS_ERR(e))
-		goto err_free;
-	RCU_INIT_POINTER(ctx->engines, e);
-
-	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
-	mutex_init(&ctx->lut_mutex);
-
 	if (name) {
 		struct i915_ppgtt *ppgtt;
 
@@ -46,25 +38,29 @@ mock_context(struct drm_i915_private *i915,
 
 		ppgtt = mock_ppgtt(i915, name);
 		if (!ppgtt)
-			goto err_put;
-
-		mutex_lock(&ctx->mutex);
-		__set_ppgtt(ctx, &ppgtt->vm);
-		mutex_unlock(&ctx->mutex);
+			goto err_free;
 
+		ctx->vm = i915_vm_open(&ppgtt->vm);
 		i915_vm_put(&ppgtt->vm);
 	}
 
+	mutex_init(&ctx->engines_mutex);
+	e = default_engines(ctx, null_sseu);
+	if (IS_ERR(e))
+		goto err_vm;
+	RCU_INIT_POINTER(ctx->engines, e);
+
+	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
+	mutex_init(&ctx->lut_mutex);
+
 	return ctx;
 
+err_vm:
+	if (ctx->vm)
+		i915_vm_close(ctx->vm);
 err_free:
 	kfree(ctx);
 	return NULL;
-
-err_put:
-	i915_gem_context_set_closed(ctx);
-	i915_gem_context_put(ctx);
-	return NULL;
 }
 
 void mock_context_close(struct i915_gem_context *ctx)
@@ -80,20 +76,29 @@ void mock_init_contexts(struct drm_i915_private *i915)
 struct i915_gem_context *
 live_context(struct drm_i915_private *i915, struct file *file)
 {
+	struct drm_i915_file_private *fpriv = to_drm_file(file)->driver_priv;
+	struct i915_gem_proto_context *pc;
 	struct i915_gem_context *ctx;
 	int err;
 	u32 id;
 
-	ctx = i915_gem_create_context(i915, 0);
+	pc = proto_context_create(i915, 0);
+	if (IS_ERR(pc))
+		return ERR_CAST(pc);
+
+	ctx = i915_gem_create_context(i915, pc);
+	proto_context_close(pc);
 	if (IS_ERR(ctx))
 		return ctx;
 
 	i915_gem_context_set_no_error_capture(ctx);
 
-	err = gem_context_register(ctx, to_drm_file(file)->driver_priv, &id);
+	err = xa_alloc(&fpriv->context_xa, &id, NULL, xa_limit_32b, GFP_KERNEL);
 	if (err < 0)
 		goto err_ctx;
 
+	gem_context_register(ctx, fpriv, id);
+
 	return ctx;
 
 err_ctx:
@@ -106,6 +111,7 @@ live_context_for_engine(struct intel_engine_cs *engine, struct file *file)
 {
 	struct i915_gem_engines *engines;
 	struct i915_gem_context *ctx;
+	struct intel_sseu null_sseu = {};
 	struct intel_context *ce;
 
 	engines = alloc_engines(1);
@@ -124,7 +130,7 @@ live_context_for_engine(struct intel_engine_cs *engine, struct file *file)
 		return ERR_CAST(ce);
 	}
 
-	intel_context_set_gem(ce, ctx);
+	intel_context_set_gem(ce, ctx, null_sseu);
 	engines->engines[0] = ce;
 	engines->num_engines = 1;
 
@@ -139,11 +145,24 @@ live_context_for_engine(struct intel_engine_cs *engine, struct file *file)
 }
 
 struct i915_gem_context *
-kernel_context(struct drm_i915_private *i915)
+kernel_context(struct drm_i915_private *i915,
+	       struct i915_address_space *vm)
 {
 	struct i915_gem_context *ctx;
+	struct i915_gem_proto_context *pc;
+
+	pc = proto_context_create(i915, 0);
+	if (IS_ERR(pc))
+		return ERR_CAST(pc);
+
+	if (vm) {
+		if (pc->vm)
+			i915_vm_put(pc->vm);
+		pc->vm = i915_vm_get(vm);
+	}
 
-	ctx = i915_gem_create_context(i915, 0);
+	ctx = i915_gem_create_context(i915, pc);
+	proto_context_close(pc);
 	if (IS_ERR(ctx))
 		return ctx;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.h b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
index 2a6121d33352..7a02fd9b5866 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
@@ -10,6 +10,7 @@
 struct file;
 struct drm_i915_private;
 struct intel_engine_cs;
+struct i915_address_space;
 
 void mock_init_contexts(struct drm_i915_private *i915);
 
@@ -25,7 +26,8 @@ live_context(struct drm_i915_private *i915, struct file *file);
 struct i915_gem_context *
 live_context_for_engine(struct intel_engine_cs *engine, struct file *file);
 
-struct i915_gem_context *kernel_context(struct drm_i915_private *i915);
+struct i915_gem_context *kernel_context(struct drm_i915_private *i915,
+					struct i915_address_space *vm);
 void kernel_context_close(struct i915_gem_context *ctx);
 
 #endif /* !__MOCK_CONTEXT_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
index 4270b5a34a83..d6f5836396f8 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -437,20 +437,20 @@ static int frequency_show(struct seq_file *m, void *unused)
 		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
 		max_freq *= (IS_GEN9_BC(i915) ||
-			     GRAPHICS_VER(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (rp_state_cap & 0xff00) >> 8;
 		max_freq *= (IS_GEN9_BC(i915) ||
-			     GRAPHICS_VER(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 16 :
 			    rp_state_cap >> 0) & 0xff;
 		max_freq *= (IS_GEN9_BC(i915) ||
-			     GRAPHICS_VER(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
@@ -500,7 +500,7 @@ static int llc_show(struct seq_file *m, void *data)
 
 	min_gpu_freq = rps->min_freq;
 	max_gpu_freq = rps->max_freq;
-	if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 10) {
+	if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
 		/* Convert GT frequency to 50 HZ units */
 		min_gpu_freq /= GEN9_FREQ_SCALER;
 		max_gpu_freq /= GEN9_FREQ_SCALER;
@@ -518,7 +518,7 @@ static int llc_show(struct seq_file *m, void *data)
 			   intel_gpu_freq(rps,
 					  (gpu_freq *
 					   (IS_GEN9_BC(i915) ||
-					    GRAPHICS_VER(i915) >= 10 ?
+					    GRAPHICS_VER(i915) >= 11 ?
 					    GEN9_FREQ_SCALER : 1))),
 			   ((ia_freq >> 0) & 0xff) * 100,
 			   ((ia_freq >> 8) & 0xff) * 100);
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 94e0a5669f90..461844dffd7e 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -42,7 +42,7 @@ int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode)
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_B0))
+		if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_C0))
 			dc_flush_wa = true;
 	}
 
@@ -208,7 +208,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		flags |= PIPE_CONTROL_FLUSH_L3;
 		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
-		/* Wa_1409600907:tgl */
+		/* Wa_1409600907:tgl,adl-p */
 		flags |= PIPE_CONTROL_DEPTH_STALL;
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
@@ -279,7 +279,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 	if (mode & EMIT_INVALIDATE)
 		aux_inv = rq->engine->mask & ~BIT(BCS0);
 	if (aux_inv)
-		cmd += 2 * hweight8(aux_inv) + 2;
+		cmd += 2 * hweight32(aux_inv) + 2;
 
 	cs = intel_ring_begin(rq, cmd);
 	if (IS_ERR(cs))
@@ -313,9 +313,8 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 		struct intel_engine_cs *engine;
 		unsigned int tmp;
 
-		*cs++ = MI_LOAD_REGISTER_IMM(hweight8(aux_inv));
-		for_each_engine_masked(engine, rq->engine->gt,
-				       aux_inv, tmp) {
+		*cs++ = MI_LOAD_REGISTER_IMM(hweight32(aux_inv));
+		for_each_engine_masked(engine, rq->engine->gt, aux_inv, tmp) {
 			*cs++ = i915_mmio_reg_offset(aux_inv_reg(engine));
 			*cs++ = AUX_INV;
 		}
@@ -506,7 +505,8 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 	*cs++ = MI_USER_INTERRUPT;
 
 	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
-	if (intel_engine_has_semaphores(rq->engine))
+	if (intel_engine_has_semaphores(rq->engine) &&
+	    !intel_uc_uses_guc_submission(&rq->engine->gt->uc))
 		cs = emit_preempt_busywait(rq, cs);
 
 	rq->tail = intel_ring_offset(rq, cs);
@@ -598,7 +598,8 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 	*cs++ = MI_USER_INTERRUPT;
 
 	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
-	if (intel_engine_has_semaphores(rq->engine))
+	if (intel_engine_has_semaphores(rq->engine) &&
+	    !intel_uc_uses_guc_submission(&rq->engine->gt->uc))
 		cs = gen12_emit_preempt_busywait(rq, cs);
 
 	rq->tail = intel_ring_offset(rq, cs);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index da4f5eb43ac2..6e0e52eeb87a 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -358,6 +358,54 @@ static void gen8_ppgtt_alloc(struct i915_address_space *vm,
 			   &start, start + length, vm->top);
 }
 
+static void __gen8_ppgtt_foreach(struct i915_address_space *vm,
+				 struct i915_page_directory *pd,
+				 u64 *start, u64 end, int lvl,
+				 void (*fn)(struct i915_address_space *vm,
+					    struct i915_page_table *pt,
+					    void *data),
+				 void *data)
+{
+	unsigned int idx, len;
+
+	len = gen8_pd_range(*start, end, lvl--, &idx);
+
+	spin_lock(&pd->lock);
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		atomic_inc(&pt->used);
+		spin_unlock(&pd->lock);
+
+		if (lvl) {
+			__gen8_ppgtt_foreach(vm, as_pd(pt), start, end, lvl,
+					     fn, data);
+		} else {
+			fn(vm, pt, data);
+			*start += gen8_pt_count(*start, end);
+		}
+
+		spin_lock(&pd->lock);
+		atomic_dec(&pt->used);
+	} while (idx++, --len);
+	spin_unlock(&pd->lock);
+}
+
+static void gen8_ppgtt_foreach(struct i915_address_space *vm,
+			       u64 start, u64 length,
+			       void (*fn)(struct i915_address_space *vm,
+					  struct i915_page_table *pt,
+					  void *data),
+			       void *data)
+{
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+
+	__gen8_ppgtt_foreach(vm, i915_vm_to_ppgtt(vm)->pd,
+			     &start, start + length, vm->top,
+			     fn, data);
+}
+
 static __always_inline u64
 gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      struct i915_page_directory *pdp,
@@ -552,6 +600,24 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 	}
 }
 
+static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
+				    dma_addr_t addr,
+				    u64 offset,
+				    enum i915_cache_level level,
+				    u32 flags)
+{
+	u64 idx = offset >> GEN8_PTE_SHIFT;
+	struct i915_page_directory * const pdp =
+		gen8_pdp_for_page_index(vm, idx);
+	struct i915_page_directory *pd =
+		i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	gen8_pte_t *vaddr;
+
+	vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
+	clflush_cache_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
+}
+
 static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	u32 pte_flags;
@@ -731,8 +797,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
 
 	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
+	ppgtt->vm.insert_page = gen8_ppgtt_insert_entry;
 	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
 	ppgtt->vm.clear_range = gen8_ppgtt_clear;
+	ppgtt->vm.foreach = gen8_ppgtt_foreach;
 
 	ppgtt->vm.pte_encode = gen8_pte_encode;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 38cc42783dfb..209cf265bf74 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -15,28 +15,14 @@
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 
-static bool irq_enable(struct intel_engine_cs *engine)
+static bool irq_enable(struct intel_breadcrumbs *b)
 {
-	if (!engine->irq_enable)
-		return false;
-
-	/* Caller disables interrupts */
-	spin_lock(&engine->gt->irq_lock);
-	engine->irq_enable(engine);
-	spin_unlock(&engine->gt->irq_lock);
-
-	return true;
+	return intel_engine_irq_enable(b->irq_engine);
 }
 
-static void irq_disable(struct intel_engine_cs *engine)
+static void irq_disable(struct intel_breadcrumbs *b)
 {
-	if (!engine->irq_disable)
-		return;
-
-	/* Caller disables interrupts */
-	spin_lock(&engine->gt->irq_lock);
-	engine->irq_disable(engine);
-	spin_unlock(&engine->gt->irq_lock);
+	intel_engine_irq_disable(b->irq_engine);
 }
 
 static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
@@ -57,7 +43,7 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 	WRITE_ONCE(b->irq_armed, true);
 
 	/* Requests may have completed before we could enable the interrupt. */
-	if (!b->irq_enabled++ && irq_enable(b->irq_engine))
+	if (!b->irq_enabled++ && b->irq_enable(b))
 		irq_work_queue(&b->irq_work);
 }
 
@@ -76,7 +62,7 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
 {
 	GEM_BUG_ON(!b->irq_enabled);
 	if (!--b->irq_enabled)
-		irq_disable(b->irq_engine);
+		b->irq_disable(b);
 
 	WRITE_ONCE(b->irq_armed, false);
 	intel_gt_pm_put_async(b->irq_engine->gt);
@@ -259,6 +245,9 @@ static void signal_irq_work(struct irq_work *work)
 			llist_entry(signal, typeof(*rq), signal_node);
 		struct list_head cb_list;
 
+		if (rq->engine->sched_engine->retire_inflight_request_prio)
+			rq->engine->sched_engine->retire_inflight_request_prio(rq);
+
 		spin_lock(&rq->lock);
 		list_replace(&rq->fence.cb_list, &cb_list);
 		__dma_fence_signal__timestamp(&rq->fence, timestamp);
@@ -281,7 +270,7 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
 	if (!b)
 		return NULL;
 
-	b->irq_engine = irq_engine;
+	kref_init(&b->ref);
 
 	spin_lock_init(&b->signalers_lock);
 	INIT_LIST_HEAD(&b->signalers);
@@ -290,6 +279,10 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
 	spin_lock_init(&b->irq_lock);
 	init_irq_work(&b->irq_work, signal_irq_work);
 
+	b->irq_engine = irq_engine;
+	b->irq_enable = irq_enable;
+	b->irq_disable = irq_disable;
+
 	return b;
 }
 
@@ -303,9 +296,9 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b)
 	spin_lock_irqsave(&b->irq_lock, flags);
 
 	if (b->irq_enabled)
-		irq_enable(b->irq_engine);
+		b->irq_enable(b);
 	else
-		irq_disable(b->irq_engine);
+		b->irq_disable(b);
 
 	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
@@ -325,11 +318,14 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 	}
 }
 
-void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
+void intel_breadcrumbs_free(struct kref *kref)
 {
+	struct intel_breadcrumbs *b = container_of(kref, typeof(*b), ref);
+
 	irq_work_sync(&b->irq_work);
 	GEM_BUG_ON(!list_empty(&b->signalers));
 	GEM_BUG_ON(b->irq_armed);
+
 	kfree(b);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
index 3ce5ce270b04..be0d4f379a85 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
@@ -9,7 +9,7 @@
 #include <linux/atomic.h>
 #include <linux/irq_work.h>
 
-#include "intel_engine_types.h"
+#include "intel_breadcrumbs_types.h"
 
 struct drm_printer;
 struct i915_request;
@@ -17,7 +17,7 @@ struct intel_breadcrumbs;
 
 struct intel_breadcrumbs *
 intel_breadcrumbs_create(struct intel_engine_cs *irq_engine);
-void intel_breadcrumbs_free(struct intel_breadcrumbs *b);
+void intel_breadcrumbs_free(struct kref *kref);
 
 void intel_breadcrumbs_reset(struct intel_breadcrumbs *b);
 void __intel_breadcrumbs_park(struct intel_breadcrumbs *b);
@@ -48,4 +48,16 @@ void i915_request_cancel_breadcrumb(struct i915_request *request);
 void intel_context_remove_breadcrumbs(struct intel_context *ce,
 				      struct intel_breadcrumbs *b);
 
+static inline struct intel_breadcrumbs *
+intel_breadcrumbs_get(struct intel_breadcrumbs *b)
+{
+	kref_get(&b->ref);
+	return b;
+}
+
+static inline void intel_breadcrumbs_put(struct intel_breadcrumbs *b)
+{
+	kref_put(&b->ref, intel_breadcrumbs_free);
+}
+
 #endif /* __INTEL_BREADCRUMBS__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
index 3a084ce8ff5e..72dfd3748c4c 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
@@ -7,10 +7,13 @@
 #define __INTEL_BREADCRUMBS_TYPES__
 
 #include <linux/irq_work.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
+#include "intel_engine_types.h"
+
 /*
  * Rather than have every client wait upon all user interrupts,
  * with the herd waking after every interrupt and each doing the
@@ -29,6 +32,7 @@
  * the overhead of waking that client is much preferred.
  */
 struct intel_breadcrumbs {
+	struct kref ref;
 	atomic_t active;
 
 	spinlock_t signalers_lock; /* protects the list of signalers */
@@ -42,7 +46,10 @@ struct intel_breadcrumbs {
 	bool irq_armed;
 
 	/* Not all breadcrumbs are attached to physical HW */
+	intel_engine_mask_t	engine_mask;
 	struct intel_engine_cs *irq_engine;
+	bool	(*irq_enable)(struct intel_breadcrumbs *b);
+	void	(*irq_disable)(struct intel_breadcrumbs *b);
 };
 
 #endif /* __INTEL_BREADCRUMBS_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 4033184f13b9..745e84c72c90 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -7,28 +7,26 @@
 #include "gem/i915_gem_pm.h"
 
 #include "i915_drv.h"
-#include "i915_globals.h"
+#include "i915_trace.h"
 
 #include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
 #include "intel_ring.h"
 
-static struct i915_global_context {
-	struct i915_global base;
-	struct kmem_cache *slab_ce;
-} global;
+static struct kmem_cache *slab_ce;
 
 static struct intel_context *intel_context_alloc(void)
 {
-	return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
+	return kmem_cache_zalloc(slab_ce, GFP_KERNEL);
 }
 
 static void rcu_context_free(struct rcu_head *rcu)
 {
 	struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);
 
-	kmem_cache_free(global.slab_ce, ce);
+	trace_intel_context_free(ce);
+	kmem_cache_free(slab_ce, ce);
 }
 
 void intel_context_free(struct intel_context *ce)
@@ -46,6 +44,7 @@ intel_context_create(struct intel_engine_cs *engine)
 		return ERR_PTR(-ENOMEM);
 
 	intel_context_init(ce, engine);
+	trace_intel_context_create(ce);
 	return ce;
 }
 
@@ -80,7 +79,7 @@ static int intel_context_active_acquire(struct intel_context *ce)
 
 	__i915_active_acquire(&ce->active);
 
-	if (intel_context_is_barrier(ce))
+	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine))
 		return 0;
 
 	/* Preallocate tracking nodes */
@@ -268,6 +267,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce,
 
 	GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
 
+	trace_intel_context_do_pin(ce);
+
 err_unlock:
 	mutex_unlock(&ce->pin_mutex);
 err_post_unpin:
@@ -306,9 +307,9 @@ retry:
 	return err;
 }
 
-void intel_context_unpin(struct intel_context *ce)
+void __intel_context_do_unpin(struct intel_context *ce, int sub)
 {
-	if (!atomic_dec_and_test(&ce->pin_count))
+	if (!atomic_sub_and_test(sub, &ce->pin_count))
 		return;
 
 	CE_TRACE(ce, "unpin\n");
@@ -323,6 +324,7 @@ void intel_context_unpin(struct intel_context *ce)
 	 */
 	intel_context_get(ce);
 	intel_context_active_release(ce);
+	trace_intel_context_do_unpin(ce);
 	intel_context_put(ce);
 }
 
@@ -360,6 +362,12 @@ static int __intel_context_active(struct i915_active *active)
 	return 0;
 }
 
+static int sw_fence_dummy_notify(struct i915_sw_fence *sf,
+				 enum i915_sw_fence_notify state)
+{
+	return NOTIFY_DONE;
+}
+
 void
 intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 {
@@ -371,7 +379,8 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 	ce->engine = engine;
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
-	ce->ring = __intel_context_ring_size(SZ_4K);
+	ce->ring = NULL;
+	ce->ring_size = SZ_4K;
 
 	ewma_runtime_init(&ce->runtime.avg);
 
@@ -383,6 +392,22 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 
 	mutex_init(&ce->pin_mutex);
 
+	spin_lock_init(&ce->guc_state.lock);
+	INIT_LIST_HEAD(&ce->guc_state.fences);
+
+	spin_lock_init(&ce->guc_active.lock);
+	INIT_LIST_HEAD(&ce->guc_active.requests);
+
+	ce->guc_id = GUC_INVALID_LRC_ID;
+	INIT_LIST_HEAD(&ce->guc_id_link);
+
+	/*
+	 * Initialize fence to be complete as this is expected to be complete
+	 * unless there is a pending schedule disable outstanding.
+	 */
+	i915_sw_fence_init(&ce->guc_blocked, sw_fence_dummy_notify);
+	i915_sw_fence_commit(&ce->guc_blocked);
+
 	i915_active_init(&ce->active,
 			 __intel_context_active, __intel_context_retire, 0);
 }
@@ -397,28 +422,17 @@ void intel_context_fini(struct intel_context *ce)
 	i915_active_fini(&ce->active);
 }
 
-static void i915_global_context_shrink(void)
-{
-	kmem_cache_shrink(global.slab_ce);
-}
-
-static void i915_global_context_exit(void)
+void i915_context_module_exit(void)
 {
-	kmem_cache_destroy(global.slab_ce);
+	kmem_cache_destroy(slab_ce);
 }
 
-static struct i915_global_context global = { {
-	.shrink = i915_global_context_shrink,
-	.exit = i915_global_context_exit,
-} };
-
-int __init i915_global_context_init(void)
+int __init i915_context_module_init(void)
 {
-	global.slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
-	if (!global.slab_ce)
+	slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
+	if (!slab_ce)
 		return -ENOMEM;
 
-	i915_global_register(&global.base);
 	return 0;
 }
 
@@ -499,6 +513,26 @@ retry:
 	return rq;
 }
 
+struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+{
+	struct i915_request *rq, *active = NULL;
+	unsigned long flags;
+
+	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
+
+	spin_lock_irqsave(&ce->guc_active.lock, flags);
+	list_for_each_entry_reverse(rq, &ce->guc_active.requests,
+				    sched.link) {
+		if (i915_request_completed(rq))
+			break;
+
+		active = rq;
+	}
+	spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+
+	return active;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_context.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index f83a73a2b39f..c41098950746 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -16,6 +16,7 @@
 #include "intel_engine_types.h"
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
+#include "i915_trace.h"
 
 #define CE_TRACE(ce, fmt, ...) do {					\
 	const struct intel_context *ce__ = (ce);			\
@@ -30,6 +31,9 @@ void intel_context_init(struct intel_context *ce,
 			struct intel_engine_cs *engine);
 void intel_context_fini(struct intel_context *ce);
 
+void i915_context_module_exit(void);
+int i915_context_module_init(void);
+
 struct intel_context *
 intel_context_create(struct intel_engine_cs *engine);
 
@@ -69,6 +73,13 @@ intel_context_is_pinned(struct intel_context *ce)
 	return atomic_read(&ce->pin_count);
 }
 
+static inline void intel_context_cancel_request(struct intel_context *ce,
+						struct i915_request *rq)
+{
+	GEM_BUG_ON(!ce->ops->cancel_request);
+	return ce->ops->cancel_request(ce, rq);
+}
+
 /**
  * intel_context_unlock_pinned - Releases the earlier locking of 'pinned' status
  * @ce - the context
@@ -113,7 +124,32 @@ static inline void __intel_context_pin(struct intel_context *ce)
 	atomic_inc(&ce->pin_count);
 }
 
-void intel_context_unpin(struct intel_context *ce);
+void __intel_context_do_unpin(struct intel_context *ce, int sub);
+
+static inline void intel_context_sched_disable_unpin(struct intel_context *ce)
+{
+	__intel_context_do_unpin(ce, 2);
+}
+
+static inline void intel_context_unpin(struct intel_context *ce)
+{
+	if (!ce->ops->sched_disable) {
+		__intel_context_do_unpin(ce, 1);
+	} else {
+		/*
+		 * Move ownership of this pin to the scheduling disable which is
+		 * an async operation. When that operation completes the above
+		 * intel_context_sched_disable_unpin is called potentially
+		 * unpinning the context.
+		 */
+		while (!atomic_add_unless(&ce->pin_count, -1, 1)) {
+			if (atomic_cmpxchg(&ce->pin_count, 1, 2) == 1) {
+				ce->ops->sched_disable(ce);
+				break;
+			}
+		}
+	}
+}
 
 void intel_context_enter_engine(struct intel_context *ce);
 void intel_context_exit_engine(struct intel_context *ce);
@@ -175,10 +211,8 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
-static inline struct intel_ring *__intel_context_ring_size(u64 sz)
-{
-	return u64_to_ptr(struct intel_ring, sz);
-}
+struct i915_request *
+intel_context_find_active_request(struct intel_context *ce);
 
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {
@@ -220,6 +254,18 @@ static inline bool intel_context_set_banned(struct intel_context *ce)
 	return test_and_set_bit(CONTEXT_BANNED, &ce->flags);
 }
 
+static inline bool intel_context_ban(struct intel_context *ce,
+				     struct i915_request *rq)
+{
+	bool ret = intel_context_set_banned(ce);
+
+	trace_intel_context_ban(ce);
+	if (ce->ops->ban)
+		ce->ops->ban(ce, rq);
+
+	return ret;
+}
+
 static inline bool
 intel_context_force_single_submission(const struct intel_context *ce)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_context_param.c b/drivers/gpu/drm/i915/gt/intel_context_param.c
deleted file mode 100644
index 65dcd090245d..000000000000
--- a/drivers/gpu/drm/i915/gt/intel_context_param.c
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include "i915_active.h"
-#include "intel_context.h"
-#include "intel_context_param.h"
-#include "intel_ring.h"
-
-int intel_context_set_ring_size(struct intel_context *ce, long sz)
-{
-	int err;
-
-	if (intel_context_lock_pinned(ce))
-		return -EINTR;
-
-	err = i915_active_wait(&ce->active);
-	if (err < 0)
-		goto unlock;
-
-	if (intel_context_is_pinned(ce)) {
-		err = -EBUSY; /* In active use, come back later! */
-		goto unlock;
-	}
-
-	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
-		struct intel_ring *ring;
-
-		/* Replace the existing ringbuffer */
-		ring = intel_engine_create_ring(ce->engine, sz);
-		if (IS_ERR(ring)) {
-			err = PTR_ERR(ring);
-			goto unlock;
-		}
-
-		intel_ring_put(ce->ring);
-		ce->ring = ring;
-
-		/* Context image will be updated on next pin */
-	} else {
-		ce->ring = __intel_context_ring_size(sz);
-	}
-
-unlock:
-	intel_context_unlock_pinned(ce);
-	return err;
-}
-
-long intel_context_get_ring_size(struct intel_context *ce)
-{
-	long sz = (unsigned long)READ_ONCE(ce->ring);
-
-	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
-		if (intel_context_lock_pinned(ce))
-			return -EINTR;
-
-		sz = ce->ring->size;
-		intel_context_unlock_pinned(ce);
-	}
-
-	return sz;
-}
diff --git a/drivers/gpu/drm/i915/gt/intel_context_param.h b/drivers/gpu/drm/i915/gt/intel_context_param.h
index 3ecacc675f41..0c69cb42d075 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_param.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_param.h
@@ -10,14 +10,10 @@
 
 #include "intel_context.h"
 
-int intel_context_set_ring_size(struct intel_context *ce, long sz);
-long intel_context_get_ring_size(struct intel_context *ce);
-
-static inline int
+static inline void
 intel_context_set_watchdog_us(struct intel_context *ce, u64 timeout_us)
 {
 	ce->watchdog.timeout_us = timeout_us;
-	return 0;
 }
 
 #endif /* INTEL_CONTEXT_PARAM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index ed8c447a7346..e54351a170e2 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -13,12 +13,14 @@
 #include <linux/types.h>
 
 #include "i915_active_types.h"
+#include "i915_sw_fence.h"
 #include "i915_utils.h"
 #include "intel_engine_types.h"
 #include "intel_sseu.h"
 
-#define CONTEXT_REDZONE POISON_INUSE
+#include "uc/intel_guc_fwif.h"
 
+#define CONTEXT_REDZONE POISON_INUSE
 DECLARE_EWMA(runtime, 3, 8);
 
 struct i915_gem_context;
@@ -35,16 +37,29 @@ struct intel_context_ops {
 
 	int (*alloc)(struct intel_context *ce);
 
+	void (*ban)(struct intel_context *ce, struct i915_request *rq);
+
 	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
 	int (*pin)(struct intel_context *ce, void *vaddr);
 	void (*unpin)(struct intel_context *ce);
 	void (*post_unpin)(struct intel_context *ce);
 
+	void (*cancel_request)(struct intel_context *ce,
+			       struct i915_request *rq);
+
 	void (*enter)(struct intel_context *ce);
 	void (*exit)(struct intel_context *ce);
 
+	void (*sched_disable)(struct intel_context *ce);
+
 	void (*reset)(struct intel_context *ce);
 	void (*destroy)(struct kref *kref);
+
+	/* virtual engine/context interface */
+	struct intel_context *(*create_virtual)(struct intel_engine_cs **engine,
+						unsigned int count);
+	struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine,
+					       unsigned int sibling);
 };
 
 struct intel_context {
@@ -82,6 +97,7 @@ struct intel_context {
 	spinlock_t signal_lock; /* protects signals, the list of requests */
 
 	struct i915_vma *state;
+	u32 ring_size;
 	struct intel_ring *ring;
 	struct intel_timeline *timeline;
 
@@ -95,6 +111,7 @@ struct intel_context {
 #define CONTEXT_BANNED			6
 #define CONTEXT_FORCE_SINGLE_SUBMISSION	7
 #define CONTEXT_NOPREEMPT		8
+#define CONTEXT_LRCA_DIRTY		9
 
 	struct {
 		u64 timeout_us;
@@ -136,6 +153,51 @@ struct intel_context {
 	struct intel_sseu sseu;
 
 	u8 wa_bb_page; /* if set, page num reserved for context workarounds */
+
+	struct {
+		/** lock: protects everything in guc_state */
+		spinlock_t lock;
+		/**
+		 * sched_state: scheduling state of this context using GuC
+		 * submission
+		 */
+		u16 sched_state;
+		/*
+		 * fences: maintains of list of requests that have a submit
+		 * fence related to GuC submission
+		 */
+		struct list_head fences;
+	} guc_state;
+
+	struct {
+		/** lock: protects everything in guc_active */
+		spinlock_t lock;
+		/** requests: active requests on this context */
+		struct list_head requests;
+	} guc_active;
+
+	/* GuC scheduling state flags that do not require a lock. */
+	atomic_t guc_sched_state_no_lock;
+
+	/* GuC LRC descriptor ID */
+	u16 guc_id;
+
+	/* GuC LRC descriptor reference count */
+	atomic_t guc_id_ref;
+
+	/*
+	 * GuC ID link - in list when unpinned but guc_id still valid in GuC
+	 */
+	struct list_head guc_id_link;
+
+	/* GuC context blocked fence */
+	struct i915_sw_fence guc_blocked;
+
+	/*
+	 * GuC priority management
+	 */
+	u8 guc_prio;
+	u32 guc_prio_count[GUC_CLIENT_PRIORITY_NUM];
 };
 
 #endif /* __INTEL_CONTEXT_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 8d9184920c51..87579affb952 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -19,7 +19,9 @@
 #include "intel_workarounds.h"
 
 struct drm_printer;
+struct intel_context;
 struct intel_gt;
+struct lock_class_key;
 
 /* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
  * but keeps the logic simple. Indeed, the whole purpose of this macro is just
@@ -123,20 +125,6 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return active;
 }
 
-static inline void
-execlists_active_lock_bh(struct intel_engine_execlists *execlists)
-{
-	local_bh_disable(); /* prevent local softirq and lock recursion */
-	tasklet_lock(&execlists->tasklet);
-}
-
-static inline void
-execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
-{
-	tasklet_unlock(&execlists->tasklet);
-	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
-}
-
 struct i915_request *
 execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
 
@@ -186,11 +174,12 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_GEM_HWS_PREEMPT_ADDR	(I915_GEM_HWS_PREEMPT * sizeof(u32))
 #define I915_GEM_HWS_SEQNO		0x40
 #define I915_GEM_HWS_SEQNO_ADDR		(I915_GEM_HWS_SEQNO * sizeof(u32))
+#define I915_GEM_HWS_MIGRATE		(0x42 * sizeof(u32))
 #define I915_GEM_HWS_SCRATCH		0x80
 
 #define I915_HWS_CSB_BUF0_INDEX		0x10
 #define I915_HWS_CSB_WRITE_INDEX	0x1f
-#define CNL_HWS_CSB_WRITE_INDEX		0x2f
+#define ICL_HWS_CSB_WRITE_INDEX		0x2f
 
 void intel_engine_stop(struct intel_engine_cs *engine);
 void intel_engine_cleanup(struct intel_engine_cs *engine);
@@ -223,6 +212,9 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 
 void intel_engine_init_execlists(struct intel_engine_cs *engine);
 
+bool intel_engine_irq_enable(struct intel_engine_cs *engine);
+void intel_engine_irq_disable(struct intel_engine_cs *engine);
+
 static inline void __intel_engine_reset(struct intel_engine_cs *engine,
 					bool stalled)
 {
@@ -248,17 +240,27 @@ __printf(3, 4)
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...);
+void intel_engine_dump_active_requests(struct list_head *requests,
+				       struct i915_request *hung_rq,
+				       struct drm_printer *m);
 
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
 				   ktime_t *now);
 
 struct i915_request *
-intel_engine_find_active_request(struct intel_engine_cs *engine);
+intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine);
 
 u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
+struct intel_context *
+intel_engine_create_pinned_context(struct intel_engine_cs *engine,
+				   struct i915_address_space *vm,
+				   unsigned int ring_size,
+				   unsigned int hwsp,
+				   struct lock_class_key *key,
+				   const char *name);
+
+void intel_engine_destroy_pinned_context(struct intel_context *ce);
 
-void intel_engine_init_active(struct intel_engine_cs *engine,
-			      unsigned int subclass);
 #define ENGINE_PHYSICAL	0
 #define ENGINE_MOCK	1
 #define ENGINE_VIRTUAL	2
@@ -277,13 +279,60 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
+struct intel_context *
+intel_engine_create_virtual(struct intel_engine_cs **siblings,
+			    unsigned int count);
+
+static inline bool
+intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine)
+{
+	/*
+	 * For non-GuC submission we expect the back-end to look at the
+	 * heartbeat status of the actual physical engine that the work
+	 * has been (or is being) scheduled on, so we should only reach
+	 * here with GuC submission enabled.
+	 */
+	GEM_BUG_ON(!intel_engine_uses_guc(engine));
+
+	return intel_guc_virtual_engine_has_heartbeat(engine);
+}
+
 static inline bool
 intel_engine_has_heartbeat(const struct intel_engine_cs *engine)
 {
 	if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL))
 		return false;
 
-	return READ_ONCE(engine->props.heartbeat_interval_ms);
+	if (intel_engine_is_virtual(engine))
+		return intel_virtual_engine_has_heartbeat(engine);
+	else
+		return READ_ONCE(engine->props.heartbeat_interval_ms);
+}
+
+static inline struct intel_engine_cs *
+intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling)
+{
+	GEM_BUG_ON(!intel_engine_is_virtual(engine));
+	return engine->cops->get_sibling(engine, sibling);
+}
+
+static inline void
+intel_engine_set_hung_context(struct intel_engine_cs *engine,
+			      struct intel_context *ce)
+{
+	engine->hung_ce = ce;
+}
+
+static inline void
+intel_engine_clear_hung_context(struct intel_engine_cs *engine)
+{
+	intel_engine_set_hung_context(engine, NULL);
+}
+
+static inline struct intel_context *
+intel_engine_get_hung_context(struct intel_engine_cs *engine)
+{
+	return engine->hung_ce;
 }
 
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 7f03df236613..0d9105a31d84 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -35,14 +35,12 @@
 #define DEFAULT_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
 #define GEN8_LR_CONTEXT_RENDER_SIZE	(20 * PAGE_SIZE)
 #define GEN9_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
-#define GEN10_LR_CONTEXT_RENDER_SIZE	(18 * PAGE_SIZE)
 #define GEN11_LR_CONTEXT_RENDER_SIZE	(14 * PAGE_SIZE)
 
 #define GEN8_LR_CONTEXT_OTHER_SIZE	( 2 * PAGE_SIZE)
 
 #define MAX_MMIO_BASES 3
 struct engine_info {
-	unsigned int hw_id;
 	u8 class;
 	u8 instance;
 	/* mmio bases table *must* be sorted in reverse graphics_ver order */
@@ -54,7 +52,6 @@ struct engine_info {
 
 static const struct engine_info intel_engines[] = {
 	[RCS0] = {
-		.hw_id = RCS0_HW,
 		.class = RENDER_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -62,7 +59,6 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[BCS0] = {
-		.hw_id = BCS0_HW,
 		.class = COPY_ENGINE_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -70,7 +66,6 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[VCS0] = {
-		.hw_id = VCS0_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -80,7 +75,6 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[VCS1] = {
-		.hw_id = VCS1_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 1,
 		.mmio_bases = {
@@ -89,7 +83,6 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[VCS2] = {
-		.hw_id = VCS2_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 2,
 		.mmio_bases = {
@@ -97,15 +90,41 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[VCS3] = {
-		.hw_id = VCS3_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 3,
 		.mmio_bases = {
 			{ .graphics_ver = 11, .base = GEN11_BSD4_RING_BASE }
 		},
 	},
+	[VCS4] = {
+		.class = VIDEO_DECODE_CLASS,
+		.instance = 4,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_BSD5_RING_BASE }
+		},
+	},
+	[VCS5] = {
+		.class = VIDEO_DECODE_CLASS,
+		.instance = 5,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_BSD6_RING_BASE }
+		},
+	},
+	[VCS6] = {
+		.class = VIDEO_DECODE_CLASS,
+		.instance = 6,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_BSD7_RING_BASE }
+		},
+	},
+	[VCS7] = {
+		.class = VIDEO_DECODE_CLASS,
+		.instance = 7,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_BSD8_RING_BASE }
+		},
+	},
 	[VECS0] = {
-		.hw_id = VECS0_HW,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -114,13 +133,26 @@ static const struct engine_info intel_engines[] = {
 		},
 	},
 	[VECS1] = {
-		.hw_id = VECS1_HW,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 1,
 		.mmio_bases = {
 			{ .graphics_ver = 11, .base = GEN11_VEBOX2_RING_BASE }
 		},
 	},
+	[VECS2] = {
+		.class = VIDEO_ENHANCEMENT_CLASS,
+		.instance = 2,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_VEBOX3_RING_BASE }
+		},
+	},
+	[VECS3] = {
+		.class = VIDEO_ENHANCEMENT_CLASS,
+		.instance = 3,
+		.mmio_bases = {
+			{ .graphics_ver = 12, .base = XEHP_VEBOX4_RING_BASE }
+		},
+	},
 };
 
 /**
@@ -153,8 +185,6 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
 		case 12:
 		case 11:
 			return GEN11_LR_CONTEXT_RENDER_SIZE;
-		case 10:
-			return GEN10_LR_CONTEXT_RENDER_SIZE;
 		case 9:
 			return GEN9_LR_CONTEXT_RENDER_SIZE;
 		case 8:
@@ -269,6 +299,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 
 	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
 	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
+	BUILD_BUG_ON(I915_MAX_VCS > (MAX_ENGINE_INSTANCE + 1));
+	BUILD_BUG_ON(I915_MAX_VECS > (MAX_ENGINE_INSTANCE + 1));
 
 	if (GEM_DEBUG_WARN_ON(id >= ARRAY_SIZE(gt->engine)))
 		return -EINVAL;
@@ -294,7 +326,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->i915 = i915;
 	engine->gt = gt;
 	engine->uncore = gt->uncore;
-	engine->hw_id = info->hw_id;
 	guc_class = engine_class_to_guc_class(info->class);
 	engine->guc_id = MAKE_GUC_ID(guc_class, info->instance);
 	engine->mmio_base = __engine_mmio_base(i915, info->mmio_bases);
@@ -328,9 +359,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	if (engine->context_size)
 		DRIVER_CAPS(i915)->has_logical_contexts = true;
 
-	/* Nothing to do here, execute in order of dependencies */
-	engine->schedule = NULL;
-
 	ewma__engine_latency_init(&engine->latency);
 	seqcount_init(&engine->stats.lock);
 
@@ -445,6 +473,28 @@ void intel_engines_free(struct intel_gt *gt)
 	}
 }
 
+static
+bool gen11_vdbox_has_sfc(struct drm_i915_private *i915,
+			 unsigned int physical_vdbox,
+			 unsigned int logical_vdbox, u16 vdbox_mask)
+{
+	/*
+	 * In Gen11, only even numbered logical VDBOXes are hooked
+	 * up to an SFC (Scaler & Format Converter) unit.
+	 * In Gen12, Even numbered physical instance always are connected
+	 * to an SFC. Odd numbered physical instances have SFC only if
+	 * previous even instance is fused off.
+	 */
+	if (GRAPHICS_VER(i915) == 12)
+		return (physical_vdbox % 2 == 0) ||
+			!(BIT(physical_vdbox - 1) & vdbox_mask);
+	else if (GRAPHICS_VER(i915) == 11)
+		return logical_vdbox % 2 == 0;
+
+	MISSING_CASE(GRAPHICS_VER(i915));
+	return false;
+}
+
 /*
  * Determine which engines are fused off in our particular hardware.
  * Note that we have a catch-22 situation where we need to be able to access
@@ -471,7 +521,14 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 	if (GRAPHICS_VER(i915) < 11)
 		return info->engine_mask;
 
-	media_fuse = ~intel_uncore_read(uncore, GEN11_GT_VEBOX_VDBOX_DISABLE);
+	/*
+	 * On newer platforms the fusing register is called 'enable' and has
+	 * enable semantics, while on older platforms it is called 'disable'
+	 * and bits have disable semantices.
+	 */
+	media_fuse = intel_uncore_read(uncore, GEN11_GT_VEBOX_VDBOX_DISABLE);
+	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
+		media_fuse = ~media_fuse;
 
 	vdbox_mask = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK;
 	vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >>
@@ -489,13 +546,9 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 			continue;
 		}
 
-		/*
-		 * In Gen11, only even numbered logical VDBOXes are
-		 * hooked up to an SFC (Scaler & Format Converter) unit.
-		 * In TGL each VDBOX has access to an SFC.
-		 */
-		if (GRAPHICS_VER(i915) >= 12 || logical_vdbox++ % 2 == 0)
+		if (gen11_vdbox_has_sfc(i915, i, logical_vdbox, vdbox_mask))
 			gt->info.vdbox_sfc_access |= BIT(i);
+		logical_vdbox++;
 	}
 	drm_dbg(&i915->drm, "vdbox enable: %04x, instances: %04lx\n",
 		vdbox_mask, VDBOX_MASK(gt));
@@ -585,9 +638,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
 	memset(execlists->pending, 0, sizeof(execlists->pending));
 	execlists->active =
 		memset(execlists->inflight, 0, sizeof(execlists->inflight));
-
-	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
 }
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
@@ -714,11 +764,17 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 		goto err_status;
 	}
 
+	engine->sched_engine = i915_sched_engine_create(ENGINE_PHYSICAL);
+	if (!engine->sched_engine) {
+		err = -ENOMEM;
+		goto err_sched_engine;
+	}
+	engine->sched_engine->private_data = engine;
+
 	err = intel_engine_init_cmd_parser(engine);
 	if (err)
 		goto err_cmd_parser;
 
-	intel_engine_init_active(engine, ENGINE_PHYSICAL);
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
@@ -737,7 +793,9 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 	return 0;
 
 err_cmd_parser:
-	intel_breadcrumbs_free(engine->breadcrumbs);
+	i915_sched_engine_put(engine->sched_engine);
+err_sched_engine:
+	intel_breadcrumbs_put(engine->breadcrumbs);
 err_status:
 	cleanup_status_page(engine);
 	return err;
@@ -775,11 +833,11 @@ static int measure_breadcrumb_dw(struct intel_context *ce)
 	frame->rq.ring = &frame->ring;
 
 	mutex_lock(&ce->timeline->mutex);
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 
 	dw = engine->emit_fini_breadcrumb(&frame->rq, frame->cs) - frame->cs;
 
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 	mutex_unlock(&ce->timeline->mutex);
 
 	GEM_BUG_ON(dw & 1); /* RING_TAIL must be qword aligned */
@@ -788,33 +846,13 @@ static int measure_breadcrumb_dw(struct intel_context *ce)
 	return dw;
 }
 
-void
-intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
-{
-	INIT_LIST_HEAD(&engine->active.requests);
-	INIT_LIST_HEAD(&engine->active.hold);
-
-	spin_lock_init(&engine->active.lock);
-	lockdep_set_subclass(&engine->active.lock, subclass);
-
-	/*
-	 * Due to an interesting quirk in lockdep's internal debug tracking,
-	 * after setting a subclass we must ensure the lock is used. Otherwise,
-	 * nr_unused_locks is incremented once too often.
-	 */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	local_irq_disable();
-	lock_map_acquire(&engine->active.lock.dep_map);
-	lock_map_release(&engine->active.lock.dep_map);
-	local_irq_enable();
-#endif
-}
-
-static struct intel_context *
-create_pinned_context(struct intel_engine_cs *engine,
-		      unsigned int hwsp,
-		      struct lock_class_key *key,
-		      const char *name)
+struct intel_context *
+intel_engine_create_pinned_context(struct intel_engine_cs *engine,
+				   struct i915_address_space *vm,
+				   unsigned int ring_size,
+				   unsigned int hwsp,
+				   struct lock_class_key *key,
+				   const char *name)
 {
 	struct intel_context *ce;
 	int err;
@@ -825,6 +863,11 @@ create_pinned_context(struct intel_engine_cs *engine,
 
 	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 	ce->timeline = page_pack_bits(NULL, hwsp);
+	ce->ring = NULL;
+	ce->ring_size = ring_size;
+
+	i915_vm_put(ce->vm);
+	ce->vm = i915_vm_get(vm);
 
 	err = intel_context_pin(ce); /* perma-pin so it is always available */
 	if (err) {
@@ -843,7 +886,7 @@ create_pinned_context(struct intel_engine_cs *engine,
 	return ce;
 }
 
-static void destroy_pinned_context(struct intel_context *ce)
+void intel_engine_destroy_pinned_context(struct intel_context *ce)
 {
 	struct intel_engine_cs *engine = ce->engine;
 	struct i915_vma *hwsp = engine->status_page.vma;
@@ -863,8 +906,9 @@ create_kernel_context(struct intel_engine_cs *engine)
 {
 	static struct lock_class_key kernel;
 
-	return create_pinned_context(engine, I915_GEM_HWS_SEQNO_ADDR,
-				     &kernel, "kernel_context");
+	return intel_engine_create_pinned_context(engine, engine->gt->vm, SZ_4K,
+						  I915_GEM_HWS_SEQNO_ADDR,
+						  &kernel, "kernel_context");
 }
 
 /**
@@ -907,7 +951,7 @@ static int engine_init_common(struct intel_engine_cs *engine)
 	return 0;
 
 err_context:
-	destroy_pinned_context(ce);
+	intel_engine_destroy_pinned_context(ce);
 	return ret;
 }
 
@@ -957,10 +1001,10 @@ int intel_engines_init(struct intel_gt *gt)
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
-	GEM_BUG_ON(!list_empty(&engine->active.requests));
-	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
+	GEM_BUG_ON(!list_empty(&engine->sched_engine->requests));
 
-	intel_breadcrumbs_free(engine->breadcrumbs);
+	i915_sched_engine_put(engine->sched_engine);
+	intel_breadcrumbs_put(engine->breadcrumbs);
 
 	intel_engine_fini_retire(engine);
 	intel_engine_cleanup_cmd_parser(engine);
@@ -969,7 +1013,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 		fput(engine->default_state);
 
 	if (engine->kernel_context)
-		destroy_pinned_context(engine->kernel_context);
+		intel_engine_destroy_pinned_context(engine->kernel_context);
 
 	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
 	cleanup_status_page(engine);
@@ -1105,45 +1149,8 @@ static u32
 read_subslice_reg(const struct intel_engine_cs *engine,
 		  int slice, int subslice, i915_reg_t reg)
 {
-	struct drm_i915_private *i915 = engine->i915;
-	struct intel_uncore *uncore = engine->uncore;
-	u32 mcr_mask, mcr_ss, mcr, old_mcr, val;
-	enum forcewake_domains fw_domains;
-
-	if (GRAPHICS_VER(i915) >= 11) {
-		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
-		mcr_ss = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
-	} else {
-		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
-		mcr_ss = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
-	}
-
-	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
-						    FW_REG_READ);
-	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
-						     GEN8_MCR_SELECTOR,
-						     FW_REG_READ | FW_REG_WRITE);
-
-	spin_lock_irq(&uncore->lock);
-	intel_uncore_forcewake_get__locked(uncore, fw_domains);
-
-	old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
-
-	mcr &= ~mcr_mask;
-	mcr |= mcr_ss;
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
-
-	val = intel_uncore_read_fw(uncore, reg);
-
-	mcr &= ~mcr_mask;
-	mcr |= old_mcr & mcr_mask;
-
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
-
-	intel_uncore_forcewake_put__locked(uncore, fw_domains);
-	spin_unlock_irq(&uncore->lock);
-
-	return val;
+	return intel_uncore_read_with_mcr_steering(engine->uncore, reg,
+						   slice, subslice);
 }
 
 /* NB: please notice the memset */
@@ -1243,7 +1250,7 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 
 void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync)
 {
-	struct tasklet_struct *t = &engine->execlists.tasklet;
+	struct tasklet_struct *t = &engine->sched_engine->tasklet;
 
 	if (!t->callback)
 		return;
@@ -1283,7 +1290,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	intel_engine_flush_submission(engine);
 
 	/* ELSP is empty, but there are ready requests? E.g. after reset */
-	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
+	if (!i915_sched_engine_is_empty(engine->sched_engine))
 		return false;
 
 	/* Ring stopped? */
@@ -1314,6 +1321,30 @@ bool intel_engines_are_idle(struct intel_gt *gt)
 	return true;
 }
 
+bool intel_engine_irq_enable(struct intel_engine_cs *engine)
+{
+	if (!engine->irq_enable)
+		return false;
+
+	/* Caller disables interrupts */
+	spin_lock(&engine->gt->irq_lock);
+	engine->irq_enable(engine);
+	spin_unlock(&engine->gt->irq_lock);
+
+	return true;
+}
+
+void intel_engine_irq_disable(struct intel_engine_cs *engine)
+{
+	if (!engine->irq_disable)
+		return;
+
+	/* Caller disables interrupts */
+	spin_lock(&engine->gt->irq_lock);
+	engine->irq_disable(engine);
+	spin_unlock(&engine->gt->irq_lock);
+}
+
 void intel_engines_reset_default_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
@@ -1349,7 +1380,7 @@ static struct intel_timeline *get_timeline(struct i915_request *rq)
 	struct intel_timeline *tl;
 
 	/*
-	 * Even though we are holding the engine->active.lock here, there
+	 * Even though we are holding the engine->sched_engine->lock here, there
 	 * is no control over the submission queue per-se and we are
 	 * inspecting the active state at a random point in time, with an
 	 * unknown queue. Play safe and make sure the timeline remains valid.
@@ -1504,8 +1535,8 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 		drm_printf(m, "\tExeclist tasklet queued? %s (%s), preempt? %s, timeslice? %s\n",
 			   yesno(test_bit(TASKLET_STATE_SCHED,
-					  &engine->execlists.tasklet.state)),
-			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)),
+					  &engine->sched_engine->tasklet.state)),
+			   enableddisabled(!atomic_read(&engine->sched_engine->tasklet.count)),
 			   repr_timer(&engine->execlists.preempt),
 			   repr_timer(&engine->execlists.timer));
 
@@ -1529,7 +1560,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		execlists_active_lock_bh(execlists);
+		i915_sched_engine_active_lock_bh(engine->sched_engine);
 		rcu_read_lock();
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[160];
@@ -1560,7 +1591,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			i915_request_show(m, rq, hdr, 0);
 		}
 		rcu_read_unlock();
-		execlists_active_unlock_bh(execlists);
+		i915_sched_engine_active_unlock_bh(engine->sched_engine);
 	} else if (GRAPHICS_VER(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1650,6 +1681,98 @@ static void print_properties(struct intel_engine_cs *engine,
 			   read_ul(&engine->defaults, p->offset));
 }
 
+static void engine_dump_request(struct i915_request *rq, struct drm_printer *m, const char *msg)
+{
+	struct intel_timeline *tl = get_timeline(rq);
+
+	i915_request_show(m, rq, msg, 0);
+
+	drm_printf(m, "\t\tring->start:  0x%08x\n",
+		   i915_ggtt_offset(rq->ring->vma));
+	drm_printf(m, "\t\tring->head:   0x%08x\n",
+		   rq->ring->head);
+	drm_printf(m, "\t\tring->tail:   0x%08x\n",
+		   rq->ring->tail);
+	drm_printf(m, "\t\tring->emit:   0x%08x\n",
+		   rq->ring->emit);
+	drm_printf(m, "\t\tring->space:  0x%08x\n",
+		   rq->ring->space);
+
+	if (tl) {
+		drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
+			   tl->hwsp_offset);
+		intel_timeline_put(tl);
+	}
+
+	print_request_ring(m, rq);
+
+	if (rq->context->lrc_reg_state) {
+		drm_printf(m, "Logical Ring Context:\n");
+		hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
+	}
+}
+
+void intel_engine_dump_active_requests(struct list_head *requests,
+				       struct i915_request *hung_rq,
+				       struct drm_printer *m)
+{
+	struct i915_request *rq;
+	const char *msg;
+	enum i915_request_state state;
+
+	list_for_each_entry(rq, requests, sched.link) {
+		if (rq == hung_rq)
+			continue;
+
+		state = i915_test_request_state(rq);
+		if (state < I915_REQUEST_QUEUED)
+			continue;
+
+		if (state == I915_REQUEST_ACTIVE)
+			msg = "\t\tactive on engine";
+		else
+			msg = "\t\tactive in queue";
+
+		engine_dump_request(rq, m, msg);
+	}
+}
+
+static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m)
+{
+	struct i915_request *hung_rq = NULL;
+	struct intel_context *ce;
+	bool guc;
+
+	/*
+	 * No need for an engine->irq_seqno_barrier() before the seqno reads.
+	 * The GPU is still running so requests are still executing and any
+	 * hardware reads will be out of date by the time they are reported.
+	 * But the intention here is just to report an instantaneous snapshot
+	 * so that's fine.
+	 */
+	lockdep_assert_held(&engine->sched_engine->lock);
+
+	drm_printf(m, "\tRequests:\n");
+
+	guc = intel_uc_uses_guc_submission(&engine->gt->uc);
+	if (guc) {
+		ce = intel_engine_get_hung_context(engine);
+		if (ce)
+			hung_rq = intel_context_find_active_request(ce);
+	} else {
+		hung_rq = intel_engine_execlist_find_hung_request(engine);
+	}
+
+	if (hung_rq)
+		engine_dump_request(hung_rq, m, "\t\thung");
+
+	if (guc)
+		intel_guc_dump_active_requests(engine, hung_rq, m);
+	else
+		intel_engine_dump_active_requests(&engine->sched_engine->requests,
+						  hung_rq, m);
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1694,41 +1817,12 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		   i915_reset_count(error));
 	print_properties(engine, m);
 
-	drm_printf(m, "\tRequests:\n");
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
+	engine_dump_active_requests(engine, m);
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	rq = intel_engine_find_active_request(engine);
-	if (rq) {
-		struct intel_timeline *tl = get_timeline(rq);
-
-		i915_request_show(m, rq, "\t\tactive ", 0);
-
-		drm_printf(m, "\t\tring->start:  0x%08x\n",
-			   i915_ggtt_offset(rq->ring->vma));
-		drm_printf(m, "\t\tring->head:   0x%08x\n",
-			   rq->ring->head);
-		drm_printf(m, "\t\tring->tail:   0x%08x\n",
-			   rq->ring->tail);
-		drm_printf(m, "\t\tring->emit:   0x%08x\n",
-			   rq->ring->emit);
-		drm_printf(m, "\t\tring->space:  0x%08x\n",
-			   rq->ring->space);
-
-		if (tl) {
-			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
-				   tl->hwsp_offset);
-			intel_timeline_put(tl);
-		}
-
-		print_request_ring(m, rq);
-
-		if (rq->context->lrc_reg_state) {
-			drm_printf(m, "Logical Ring Context:\n");
-			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
-		}
-	}
-	drm_printf(m, "\tOn hold?: %lu\n", list_count(&engine->active.hold));
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	drm_printf(m, "\tOn hold?: %lu\n",
+		   list_count(&engine->sched_engine->hold));
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 
 	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
 	wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
@@ -1785,19 +1879,33 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 	return total;
 }
 
-static bool match_ring(struct i915_request *rq)
+struct intel_context *
+intel_engine_create_virtual(struct intel_engine_cs **siblings,
+			    unsigned int count)
 {
-	u32 ring = ENGINE_READ(rq->engine, RING_START);
+	if (count == 0)
+		return ERR_PTR(-EINVAL);
+
+	if (count == 1)
+		return intel_context_create(siblings[0]);
 
-	return ring == i915_ggtt_offset(rq->ring->vma);
+	GEM_BUG_ON(!siblings[0]->cops->create_virtual);
+	return siblings[0]->cops->create_virtual(siblings, count);
 }
 
 struct i915_request *
-intel_engine_find_active_request(struct intel_engine_cs *engine)
+intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *request, *active = NULL;
 
 	/*
+	 * This search does not work in GuC submission mode. However, the GuC
+	 * will report the hanging context directly to the driver itself. So
+	 * the driver should never get here when in GuC mode.
+	 */
+	GEM_BUG_ON(intel_uc_uses_guc_submission(&engine->gt->uc));
+
+	/*
 	 * We are called by the error capture, reset and to dump engine
 	 * state at random points in time. In particular, note that neither is
 	 * crucially ordered with an interrupt. After a hang, the GPU is dead
@@ -1808,7 +1916,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
 	 * At all other times, we must assume the GPU is still running, but
 	 * we only care about the snapshot of this moment.
 	 */
-	lockdep_assert_held(&engine->active.lock);
+	lockdep_assert_held(&engine->sched_engine->lock);
 
 	rcu_read_lock();
 	request = execlists_active(&engine->execlists);
@@ -1826,15 +1934,9 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
 	if (active)
 		return active;
 
-	list_for_each_entry(request, &engine->active.requests, sched.link) {
-		if (__i915_request_is_complete(request))
-			continue;
-
-		if (!__i915_request_has_started(request))
-			continue;
-
-		/* More than one preemptible request may match! */
-		if (!match_ring(request))
+	list_for_each_entry(request, &engine->sched_engine->requests,
+			    sched.link) {
+		if (i915_test_request_state(request) != I915_REQUEST_ACTIVE)
 			continue;
 
 		active = request;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index b99ac41695f3..74775ae961b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -70,12 +70,38 @@ static void show_heartbeat(const struct i915_request *rq,
 {
 	struct drm_printer p = drm_debug_printer("heartbeat");
 
-	intel_engine_dump(engine, &p,
-			  "%s heartbeat {seqno:%llx:%lld, prio:%d} not ticking\n",
-			  engine->name,
-			  rq->fence.context,
-			  rq->fence.seqno,
-			  rq->sched.attr.priority);
+	if (!rq) {
+		intel_engine_dump(engine, &p,
+				  "%s heartbeat not ticking\n",
+				  engine->name);
+	} else {
+		intel_engine_dump(engine, &p,
+				  "%s heartbeat {seqno:%llx:%lld, prio:%d} not ticking\n",
+				  engine->name,
+				  rq->fence.context,
+				  rq->fence.seqno,
+				  rq->sched.attr.priority);
+	}
+}
+
+static void
+reset_engine(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		show_heartbeat(rq, engine);
+
+	if (intel_engine_uses_guc(engine))
+		/*
+		 * GuC itself is toast or GuC's hang detection
+		 * is disabled. Either way, need to find the
+		 * hang culprit manually.
+		 */
+		intel_guc_find_hung_context(engine);
+
+	intel_gt_handle_error(engine->gt, engine->mask,
+			      I915_ERROR_CAPTURE,
+			      "stopped heartbeat on %s",
+			      engine->name);
 }
 
 static void heartbeat(struct work_struct *wrk)
@@ -102,6 +128,11 @@ static void heartbeat(struct work_struct *wrk)
 	if (intel_gt_is_wedged(engine->gt))
 		goto out;
 
+	if (i915_sched_engine_disabled(engine->sched_engine)) {
+		reset_engine(engine, engine->heartbeat.systole);
+		goto out;
+	}
+
 	if (engine->heartbeat.systole) {
 		long delay = READ_ONCE(engine->props.heartbeat_interval_ms);
 
@@ -121,7 +152,7 @@ static void heartbeat(struct work_struct *wrk)
 			 * but all other contexts, including the kernel
 			 * context are stuck waiting for the signal.
 			 */
-		} else if (engine->schedule &&
+		} else if (engine->sched_engine->schedule &&
 			   rq->sched.attr.priority < I915_PRIORITY_BARRIER) {
 			/*
 			 * Gradually raise the priority of the heartbeat to
@@ -136,16 +167,10 @@ static void heartbeat(struct work_struct *wrk)
 				attr.priority = I915_PRIORITY_BARRIER;
 
 			local_bh_disable();
-			engine->schedule(rq, &attr);
+			engine->sched_engine->schedule(rq, &attr);
 			local_bh_enable();
 		} else {
-			if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-				show_heartbeat(rq, engine);
-
-			intel_gt_handle_error(engine->gt, engine->mask,
-					      I915_ERROR_CAPTURE,
-					      "stopped heartbeat on %s",
-					      engine->name);
+			reset_engine(engine, rq);
 		}
 
 		rq->emitted_jiffies = jiffies;
@@ -194,6 +219,25 @@ void intel_engine_park_heartbeat(struct intel_engine_cs *engine)
 		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
 }
 
+void intel_gt_unpark_heartbeats(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		if (intel_engine_pm_is_awake(engine))
+			intel_engine_unpark_heartbeat(engine);
+}
+
+void intel_gt_park_heartbeats(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		intel_engine_park_heartbeat(engine);
+}
+
 void intel_engine_init_heartbeat(struct intel_engine_cs *engine)
 {
 	INIT_DELAYED_WORK(&engine->heartbeat.work, heartbeat);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h
index a488ea3e84a3..5da6d809a87a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h
@@ -7,6 +7,7 @@
 #define INTEL_ENGINE_HEARTBEAT_H
 
 struct intel_engine_cs;
+struct intel_gt;
 
 void intel_engine_init_heartbeat(struct intel_engine_cs *engine);
 
@@ -16,6 +17,9 @@ int intel_engine_set_heartbeat(struct intel_engine_cs *engine,
 void intel_engine_park_heartbeat(struct intel_engine_cs *engine);
 void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine);
 
+void intel_gt_park_heartbeats(struct intel_gt *gt);
+void intel_gt_unpark_heartbeats(struct intel_gt *gt);
+
 int intel_engine_pulse(struct intel_engine_cs *engine);
 int intel_engine_flush_barriers(struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 47f4397095e5..1f07ac4e0672 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -275,13 +275,11 @@ static int __engine_park(struct intel_wakeref *wf)
 	intel_breadcrumbs_park(engine->breadcrumbs);
 
 	/* Must be reset upon idling, or we may miss the busy wakeup. */
-	GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
+	GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN);
 
 	if (engine->park)
 		engine->park(engine);
 
-	engine->execlists.no_priolist = false;
-
 	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
 	intel_gt_pm_put_async(engine->gt);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e113f93b3274..ed91bcff20eb 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -21,32 +21,20 @@
 #include "i915_pmu.h"
 #include "i915_priolist_types.h"
 #include "i915_selftest.h"
-#include "intel_breadcrumbs_types.h"
 #include "intel_sseu.h"
 #include "intel_timeline_types.h"
 #include "intel_uncore.h"
 #include "intel_wakeref.h"
 #include "intel_workarounds_types.h"
 
-/* Legacy HW Engine ID */
-
-#define RCS0_HW		0
-#define VCS0_HW		1
-#define BCS0_HW		2
-#define VECS0_HW	3
-#define VCS1_HW		4
-#define VCS2_HW		6
-#define VCS3_HW		7
-#define VECS1_HW	12
-
-/* Gen11+ HW Engine class + instance */
+/* HW Engine class + instance */
 #define RENDER_CLASS		0
 #define VIDEO_DECODE_CLASS	1
 #define VIDEO_ENHANCEMENT_CLASS	2
 #define COPY_ENGINE_CLASS	3
 #define OTHER_CLASS		4
 #define MAX_ENGINE_CLASS	4
-#define MAX_ENGINE_INSTANCE	3
+#define MAX_ENGINE_INSTANCE	7
 
 #define I915_MAX_SLICES	3
 #define I915_MAX_SUBSLICES 8
@@ -59,11 +47,13 @@ struct drm_i915_reg_table;
 struct i915_gem_context;
 struct i915_request;
 struct i915_sched_attr;
+struct i915_sched_engine;
 struct intel_gt;
 struct intel_ring;
 struct intel_uncore;
+struct intel_breadcrumbs;
 
-typedef u8 intel_engine_mask_t;
+typedef u32 intel_engine_mask_t;
 #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
 
 struct intel_hw_status_page {
@@ -100,8 +90,8 @@ struct i915_ctx_workarounds {
 	struct i915_vma *vma;
 };
 
-#define I915_MAX_VCS	4
-#define I915_MAX_VECS	2
+#define I915_MAX_VCS	8
+#define I915_MAX_VECS	4
 
 /*
  * Engine IDs definitions.
@@ -114,9 +104,15 @@ enum intel_engine_id {
 	VCS1,
 	VCS2,
 	VCS3,
+	VCS4,
+	VCS5,
+	VCS6,
+	VCS7,
 #define _VCS(n) (VCS0 + (n))
 	VECS0,
 	VECS1,
+	VECS2,
+	VECS3,
 #define _VECS(n) (VECS0 + (n))
 	I915_NUM_ENGINES
 #define INVALID_ENGINE ((enum intel_engine_id)-1)
@@ -138,11 +134,6 @@ struct st_preempt_hang {
  */
 struct intel_engine_execlists {
 	/**
-	 * @tasklet: softirq tasklet for bottom handler
-	 */
-	struct tasklet_struct tasklet;
-
-	/**
 	 * @timer: kick the current context if its timeslice expires
 	 */
 	struct timer_list timer;
@@ -153,11 +144,6 @@ struct intel_engine_execlists {
 	struct timer_list preempt;
 
 	/**
-	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
-	 */
-	struct i915_priolist default_priolist;
-
-	/**
 	 * @ccid: identifier for contexts submitted to this engine
 	 */
 	u32 ccid;
@@ -192,11 +178,6 @@ struct intel_engine_execlists {
 	u32 reset_ccid;
 
 	/**
-	 * @no_priolist: priority lists disabled
-	 */
-	bool no_priolist;
-
-	/**
 	 * @submit_reg: gen-specific execlist submission register
 	 * set to the ExecList Submission Port (elsp) register pre-Gen11 and to
 	 * the ExecList Submission Queue Contents register array for Gen11+
@@ -238,23 +219,10 @@ struct intel_engine_execlists {
 	unsigned int port_mask;
 
 	/**
-	 * @queue_priority_hint: Highest pending priority.
-	 *
-	 * When we add requests into the queue, or adjust the priority of
-	 * executing requests, we compute the maximum priority of those
-	 * pending requests. We can then use this value to determine if
-	 * we need to preempt the executing requests to service the queue.
-	 * However, since the we may have recorded the priority of an inflight
-	 * request we wanted to preempt but since completed, at the time of
-	 * dequeuing the priority hint may no longer may match the highest
-	 * available request priority.
+	 * @virtual: Queue of requets on a virtual engine, sorted by priority.
+	 * Each RB entry is a struct i915_priolist containing a list of requests
+	 * of the same priority.
 	 */
-	int queue_priority_hint;
-
-	/**
-	 * @queue: queue of requests, in priority lists
-	 */
-	struct rb_root_cached queue;
 	struct rb_root_cached virtual;
 
 	/**
@@ -295,7 +263,6 @@ struct intel_engine_cs {
 	enum intel_engine_id id;
 	enum intel_engine_id legacy_idx;
 
-	unsigned int hw_id;
 	unsigned int guc_id;
 
 	intel_engine_mask_t mask;
@@ -326,15 +293,13 @@ struct intel_engine_cs {
 
 	struct intel_sseu sseu;
 
-	struct {
-		spinlock_t lock;
-		struct list_head requests;
-		struct list_head hold; /* ready requests, but on hold */
-	} active;
+	struct i915_sched_engine *sched_engine;
 
 	/* keep a request in reserve for a [pm] barrier under oom */
 	struct i915_request *request_pool;
 
+	struct intel_context *hung_ce;
+
 	struct llist_head barrier_tasks;
 
 	struct intel_context *kernel_context; /* pinned */
@@ -419,6 +384,8 @@ struct intel_engine_cs {
 	void		(*park)(struct intel_engine_cs *engine);
 	void		(*unpark)(struct intel_engine_cs *engine);
 
+	void		(*bump_serial)(struct intel_engine_cs *engine);
+
 	void		(*set_default_submission)(struct intel_engine_cs *engine);
 
 	const struct intel_context_ops *cops;
@@ -447,22 +414,13 @@ struct intel_engine_cs {
 	 */
 	void		(*submit_request)(struct i915_request *rq);
 
-	/*
-	 * Called on signaling of a SUBMIT_FENCE, passing along the signaling
-	 * request down to the bonded pairs.
-	 */
-	void            (*bond_execute)(struct i915_request *rq,
-					struct dma_fence *signal);
+	void		(*release)(struct intel_engine_cs *engine);
 
 	/*
-	 * Call when the priority on a request has changed and it and its
-	 * dependencies may need rescheduling. Note the request itself may
-	 * not be ready to run!
+	 * Add / remove request from engine active tracking
 	 */
-	void		(*schedule)(struct i915_request *request,
-				    const struct i915_sched_attr *attr);
-
-	void		(*release)(struct intel_engine_cs *engine);
+	void		(*add_active_request)(struct i915_request *rq);
+	void		(*remove_active_request)(struct i915_request *rq);
 
 	struct intel_engine_execlists execlists;
 
@@ -485,6 +443,7 @@ struct intel_engine_cs {
 #define I915_ENGINE_IS_VIRTUAL       BIT(5)
 #define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
 #define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
+#define I915_ENGINE_WANT_FORCED_PREEMPTION BIT(8)
 	unsigned int flags;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 3cca7ea2d6ea..8f8bea08e734 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -11,6 +11,7 @@
 #include "intel_engine.h"
 #include "intel_engine_user.h"
 #include "intel_gt.h"
+#include "uc/intel_guc_submission.h"
 
 struct intel_engine_cs *
 intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
@@ -108,13 +109,16 @@ static void set_scheduler_caps(struct drm_i915_private *i915)
 	for_each_uabi_engine(engine, i915) { /* all engines must agree! */
 		int i;
 
-		if (engine->schedule)
+		if (engine->sched_engine->schedule)
 			enabled |= (I915_SCHEDULER_CAP_ENABLED |
 				    I915_SCHEDULER_CAP_PRIORITY);
 		else
 			disabled |= (I915_SCHEDULER_CAP_ENABLED |
 				     I915_SCHEDULER_CAP_PRIORITY);
 
+		if (intel_uc_uses_guc_submission(&i915->gt.uc))
+			enabled |= I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP;
+
 		for (i = 0; i < ARRAY_SIZE(map); i++) {
 			if (engine->flags & BIT(map[i].engine))
 				enabled |= BIT(map[i].sched);
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index fc77592d88a9..de5f9c86b9a4 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -114,6 +114,7 @@
 #include "gen8_engine_cs.h"
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 #include "intel_engine_stats.h"
 #include "intel_execlists_submission.h"
@@ -153,6 +154,12 @@
 #define GEN12_CSB_CTX_VALID(csb_dw) \
 	(FIELD_GET(GEN12_CSB_SW_CTX_ID_MASK, csb_dw) != GEN12_IDLE_CTX_ID)
 
+#define XEHP_CTX_STATUS_SWITCHED_TO_NEW_QUEUE	BIT(1) /* upper csb dword */
+#define XEHP_CSB_SW_CTX_ID_MASK			GENMASK(31, 10)
+#define XEHP_IDLE_CTX_ID			0xFFFF
+#define XEHP_CSB_CTX_VALID(csb_dw) \
+	(FIELD_GET(XEHP_CSB_SW_CTX_ID_MASK, csb_dw) != XEHP_IDLE_CTX_ID)
+
 /* Typical size of the average request (2 pipecontrols and a MI_BB) */
 #define EXECLISTS_REQUEST_SIZE 64 /* bytes */
 
@@ -182,18 +189,6 @@ struct virtual_engine {
 		int prio;
 	} nodes[I915_NUM_ENGINES];
 
-	/*
-	 * Keep track of bonded pairs -- restrictions upon on our selection
-	 * of physical engines any particular request may be submitted to.
-	 * If we receive a submit-fence from a master engine, we will only
-	 * use one of sibling_mask physical engines.
-	 */
-	struct ve_bond {
-		const struct intel_engine_cs *master;
-		intel_engine_mask_t sibling_mask;
-	} *bonds;
-	unsigned int num_bonds;
-
 	/* And finally, which physical engines this virtual engine maps onto. */
 	unsigned int num_siblings;
 	struct intel_engine_cs *siblings[];
@@ -205,6 +200,9 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
 	return container_of(engine, struct virtual_engine, base);
 }
 
+static struct intel_context *
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
+
 static struct i915_request *
 __active_request(const struct intel_timeline * const tl,
 		 struct i915_request *rq,
@@ -273,11 +271,11 @@ static int effective_prio(const struct i915_request *rq)
 	return prio;
 }
 
-static int queue_prio(const struct intel_engine_execlists *execlists)
+static int queue_prio(const struct i915_sched_engine *sched_engine)
 {
 	struct rb_node *rb;
 
-	rb = rb_first_cached(&execlists->queue);
+	rb = rb_first_cached(&sched_engine->queue);
 	if (!rb)
 		return INT_MIN;
 
@@ -318,14 +316,14 @@ static bool need_preempt(const struct intel_engine_cs *engine,
 	 * to preserve FIFO ordering of dependencies.
 	 */
 	last_prio = max(effective_prio(rq), I915_PRIORITY_NORMAL - 1);
-	if (engine->execlists.queue_priority_hint <= last_prio)
+	if (engine->sched_engine->queue_priority_hint <= last_prio)
 		return false;
 
 	/*
 	 * Check against the first request in ELSP[1], it will, thanks to the
 	 * power of PI, be the highest priority of that context.
 	 */
-	if (!list_is_last(&rq->sched.link, &engine->active.requests) &&
+	if (!list_is_last(&rq->sched.link, &engine->sched_engine->requests) &&
 	    rq_prio(list_next_entry(rq, sched.link)) > last_prio)
 		return true;
 
@@ -340,7 +338,7 @@ static bool need_preempt(const struct intel_engine_cs *engine,
 	 * context, it's priority would not exceed ELSP[0] aka last_prio.
 	 */
 	return max(virtual_prio(&engine->execlists),
-		   queue_prio(&engine->execlists)) > last_prio;
+		   queue_prio(engine->sched_engine)) > last_prio;
 }
 
 __maybe_unused static bool
@@ -367,10 +365,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	struct list_head *pl;
 	int prio = I915_PRIORITY_INVALID;
 
-	lockdep_assert_held(&engine->active.lock);
+	lockdep_assert_held(&engine->sched_engine->lock);
 
 	list_for_each_entry_safe_reverse(rq, rn,
-					 &engine->active.requests,
+					 &engine->sched_engine->requests,
 					 sched.link) {
 		if (__i915_request_is_complete(rq)) {
 			list_del_init(&rq->sched.link);
@@ -382,9 +380,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
 		if (rq_prio(rq) != prio) {
 			prio = rq_prio(rq);
-			pl = i915_sched_lookup_priolist(engine, prio);
+			pl = i915_sched_lookup_priolist(engine->sched_engine,
+							prio);
 		}
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(i915_sched_engine_is_empty(engine->sched_engine));
 
 		list_move(&rq->sched.link, pl);
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
@@ -489,6 +488,16 @@ __execlists_schedule_in(struct i915_request *rq)
 		/* Use a fixed tag for OA and friends */
 		GEM_BUG_ON(ce->tag <= BITS_PER_LONG);
 		ce->lrc.ccid = ce->tag;
+	} else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) {
+		/* We don't need a strict matching tag, just different values */
+		unsigned int tag = ffs(READ_ONCE(engine->context_tag));
+
+		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
+		clear_bit(tag - 1, &engine->context_tag);
+		ce->lrc.ccid = tag << (XEHP_SW_CTX_ID_SHIFT - 32);
+
+		BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID);
+
 	} else {
 		/* We don't need a strict matching tag, just different values */
 		unsigned int tag = __ffs(engine->context_tag);
@@ -534,13 +543,13 @@ resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
 {
 	struct intel_engine_cs *engine = rq->engine;
 
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 
 	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 	WRITE_ONCE(rq->engine, &ve->base);
 	ve->base.submit_request(rq);
 
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 }
 
 static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
@@ -569,7 +578,7 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 		resubmit_virtual_request(rq, ve);
 
 	if (READ_ONCE(ve->request))
-		tasklet_hi_schedule(&ve->base.execlists.tasklet);
+		tasklet_hi_schedule(&ve->base.sched_engine->tasklet);
 }
 
 static void __execlists_schedule_out(struct i915_request * const rq,
@@ -579,7 +588,7 @@ static void __execlists_schedule_out(struct i915_request * const rq,
 	unsigned int ccid;
 
 	/*
-	 * NB process_csb() is not under the engine->active.lock and hence
+	 * NB process_csb() is not under the engine->sched_engine->lock and hence
 	 * schedule_out can race with schedule_in meaning that we should
 	 * refrain from doing non-trivial work here.
 	 */
@@ -599,8 +608,14 @@ static void __execlists_schedule_out(struct i915_request * const rq,
 		intel_engine_add_retire(engine, ce->timeline);
 
 	ccid = ce->lrc.ccid;
-	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
-	ccid &= GEN12_MAX_CONTEXT_HW_ID;
+	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) {
+		ccid >>= XEHP_SW_CTX_ID_SHIFT - 32;
+		ccid &= XEHP_MAX_CONTEXT_HW_ID;
+	} else {
+		ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
+		ccid &= GEN12_MAX_CONTEXT_HW_ID;
+	}
+
 	if (ccid < BITS_PER_LONG) {
 		GEM_BUG_ON(ccid == 0);
 		GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
@@ -738,9 +753,9 @@ trace_ports(const struct intel_engine_execlists *execlists,
 }
 
 static bool
-reset_in_progress(const struct intel_engine_execlists *execlists)
+reset_in_progress(const struct intel_engine_cs *engine)
 {
-	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
+	return unlikely(!__tasklet_is_enabled(&engine->sched_engine->tasklet));
 }
 
 static __maybe_unused noinline bool
@@ -756,7 +771,7 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 	trace_ports(execlists, msg, execlists->pending);
 
 	/* We may be messing around with the lists during reset, lalala */
-	if (reset_in_progress(execlists))
+	if (reset_in_progress(engine))
 		return true;
 
 	if (!execlists->pending[0]) {
@@ -1096,7 +1111,8 @@ static void defer_active(struct intel_engine_cs *engine)
 	if (!rq)
 		return;
 
-	defer_request(rq, i915_sched_lookup_priolist(engine, rq_prio(rq)));
+	defer_request(rq, i915_sched_lookup_priolist(engine->sched_engine,
+						     rq_prio(rq)));
 }
 
 static bool
@@ -1133,13 +1149,14 @@ static bool needs_timeslice(const struct intel_engine_cs *engine,
 		return false;
 
 	/* If ELSP[1] is occupied, always check to see if worth slicing */
-	if (!list_is_last_rcu(&rq->sched.link, &engine->active.requests)) {
+	if (!list_is_last_rcu(&rq->sched.link,
+			      &engine->sched_engine->requests)) {
 		ENGINE_TRACE(engine, "timeslice required for second inflight context\n");
 		return true;
 	}
 
 	/* Otherwise, ELSP[0] is by itself, but may be waiting in the queue */
-	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)) {
+	if (!i915_sched_engine_is_empty(engine->sched_engine)) {
 		ENGINE_TRACE(engine, "timeslice required for queue\n");
 		return true;
 	}
@@ -1187,7 +1204,7 @@ static void start_timeslice(struct intel_engine_cs *engine)
 			 * its timeslice, so recheck.
 			 */
 			if (!timer_pending(&el->timer))
-				tasklet_hi_schedule(&el->tasklet);
+				tasklet_hi_schedule(&engine->sched_engine->tasklet);
 			return;
 		}
 
@@ -1236,6 +1253,7 @@ static bool completed(const struct i915_request *rq)
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_sched_engine * const sched_engine = engine->sched_engine;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
 	struct i915_request *last, * const *active;
@@ -1265,7 +1283,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	spin_lock(&engine->active.lock);
+	spin_lock(&sched_engine->lock);
 
 	/*
 	 * If the queue is higher priority than the last
@@ -1287,7 +1305,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				     last->fence.context,
 				     last->fence.seqno,
 				     last->sched.attr.priority,
-				     execlists->queue_priority_hint);
+				     sched_engine->queue_priority_hint);
 			record_preemption(execlists);
 
 			/*
@@ -1313,7 +1331,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				     yesno(timer_expired(&execlists->timer)),
 				     last->fence.context, last->fence.seqno,
 				     rq_prio(last),
-				     execlists->queue_priority_hint,
+				     sched_engine->queue_priority_hint,
 				     yesno(timeslice_yield(execlists, last)));
 
 			/*
@@ -1365,7 +1383,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				spin_unlock(&engine->active.lock);
+				spin_unlock(&sched_engine->lock);
 				return;
 			}
 		}
@@ -1375,7 +1393,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	while ((ve = first_virtual_engine(engine))) {
 		struct i915_request *rq;
 
-		spin_lock(&ve->base.active.lock);
+		spin_lock(&ve->base.sched_engine->lock);
 
 		rq = ve->request;
 		if (unlikely(!virtual_matches(ve, rq, engine)))
@@ -1384,14 +1402,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq->engine != &ve->base);
 		GEM_BUG_ON(rq->context != &ve->context);
 
-		if (unlikely(rq_prio(rq) < queue_prio(execlists))) {
-			spin_unlock(&ve->base.active.lock);
+		if (unlikely(rq_prio(rq) < queue_prio(sched_engine))) {
+			spin_unlock(&ve->base.sched_engine->lock);
 			break;
 		}
 
 		if (last && !can_merge_rq(last, rq)) {
-			spin_unlock(&ve->base.active.lock);
-			spin_unlock(&engine->active.lock);
+			spin_unlock(&ve->base.sched_engine->lock);
+			spin_unlock(&engine->sched_engine->lock);
 			return; /* leave this for another sibling */
 		}
 
@@ -1405,7 +1423,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			     yesno(engine != ve->siblings[0]));
 
 		WRITE_ONCE(ve->request, NULL);
-		WRITE_ONCE(ve->base.execlists.queue_priority_hint, INT_MIN);
+		WRITE_ONCE(ve->base.sched_engine->queue_priority_hint, INT_MIN);
 
 		rb = &ve->nodes[engine->id].rb;
 		rb_erase_cached(rb, &execlists->virtual);
@@ -1437,7 +1455,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 		i915_request_put(rq);
 unlock:
-		spin_unlock(&ve->base.active.lock);
+		spin_unlock(&ve->base.sched_engine->lock);
 
 		/*
 		 * Hmm, we have a bunch of virtual engine requests,
@@ -1450,7 +1468,7 @@ unlock:
 			break;
 	}
 
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&sched_engine->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -1529,7 +1547,7 @@ unlock:
 			}
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &sched_engine->queue);
 		i915_priolist_free(p);
 	}
 done:
@@ -1551,8 +1569,9 @@ done:
 	 * request triggering preemption on the next dequeue (or subsequent
 	 * interrupt for secondary ports).
 	 */
-	execlists->queue_priority_hint = queue_prio(execlists);
-	spin_unlock(&engine->active.lock);
+	sched_engine->queue_priority_hint = queue_prio(sched_engine);
+	i915_sched_engine_reset_on_empty(sched_engine);
+	spin_unlock(&sched_engine->lock);
 
 	/*
 	 * We can skip poking the HW if we ended up with exactly the same set
@@ -1655,13 +1674,24 @@ static void invalidate_csb_entries(const u64 *first, const u64 *last)
  *     bits 44-46: reserved
  *     bits 47-57: sw context id of the lrc the GT switched away from
  *     bits 58-63: sw counter of the lrc the GT switched away from
+ *
+ * Xe_HP csb shuffles things around compared to TGL:
+ *
+ *     bits 0-3:   context switch detail (same possible values as TGL)
+ *     bits 4-9:   engine instance
+ *     bits 10-25: sw context id of the lrc the GT switched to
+ *     bits 26-31: sw counter of the lrc the GT switched to
+ *     bit  32:    semaphore wait mode (poll or signal), Only valid when
+ *                 switch detail is set to "wait on semaphore"
+ *     bit  33:    switched to new queue
+ *     bits 34-41: wait detail (for switch detail 1 to 4)
+ *     bits 42-57: sw context id of the lrc the GT switched away from
+ *     bits 58-63: sw counter of the lrc the GT switched away from
  */
-static bool gen12_csb_parse(const u64 csb)
+static inline bool
+__gen12_csb_parse(bool ctx_to_valid, bool ctx_away_valid, bool new_queue,
+		  u8 switch_detail)
 {
-	bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(csb));
-	bool new_queue =
-		lower_32_bits(csb) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
-
 	/*
 	 * The context switch detail is not guaranteed to be 5 when a preemption
 	 * occurs, so we can't just check for that. The check below works for
@@ -1670,7 +1700,7 @@ static bool gen12_csb_parse(const u64 csb)
 	 * would require some extra handling, but we don't support that.
 	 */
 	if (!ctx_away_valid || new_queue) {
-		GEM_BUG_ON(!GEN12_CSB_CTX_VALID(lower_32_bits(csb)));
+		GEM_BUG_ON(!ctx_to_valid);
 		return true;
 	}
 
@@ -1679,10 +1709,26 @@ static bool gen12_csb_parse(const u64 csb)
 	 * context switch on an unsuccessful wait instruction since we always
 	 * use polling mode.
 	 */
-	GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_32_bits(csb)));
+	GEM_BUG_ON(switch_detail);
 	return false;
 }
 
+static bool xehp_csb_parse(const u64 csb)
+{
+	return __gen12_csb_parse(XEHP_CSB_CTX_VALID(lower_32_bits(csb)), /* cxt to */
+				 XEHP_CSB_CTX_VALID(upper_32_bits(csb)), /* cxt away */
+				 upper_32_bits(csb) & XEHP_CTX_STATUS_SWITCHED_TO_NEW_QUEUE,
+				 GEN12_CTX_SWITCH_DETAIL(lower_32_bits(csb)));
+}
+
+static bool gen12_csb_parse(const u64 csb)
+{
+	return __gen12_csb_parse(GEN12_CSB_CTX_VALID(lower_32_bits(csb)), /* cxt to */
+				 GEN12_CSB_CTX_VALID(upper_32_bits(csb)), /* cxt away */
+				 lower_32_bits(csb) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE,
+				 GEN12_CTX_SWITCH_DETAIL(upper_32_bits(csb)));
+}
+
 static bool gen8_csb_parse(const u64 csb)
 {
 	return csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED);
@@ -1767,8 +1813,8 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 	 * access. Either we are inside the tasklet, or the tasklet is disabled
 	 * and we assume that is only inside the reset paths and so serialised.
 	 */
-	GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) &&
-		   !reset_in_progress(execlists));
+	GEM_BUG_ON(!tasklet_is_locked(&engine->sched_engine->tasklet) &&
+		   !reset_in_progress(engine));
 
 	/*
 	 * Note that csb_write, csb_status may be either in HWSP or mmio.
@@ -1847,7 +1893,9 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 		ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
 			     head, upper_32_bits(csb), lower_32_bits(csb));
 
-		if (GRAPHICS_VER(engine->i915) >= 12)
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+			promote = xehp_csb_parse(csb);
+		else if (GRAPHICS_VER(engine->i915) >= 12)
 			promote = gen12_csb_parse(csb);
 		else
 			promote = gen8_csb_parse(csb);
@@ -1979,7 +2027,8 @@ static void __execlists_hold(struct i915_request *rq)
 			__i915_request_unsubmit(rq);
 
 		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-		list_move_tail(&rq->sched.link, &rq->engine->active.hold);
+		list_move_tail(&rq->sched.link,
+			       &rq->engine->sched_engine->hold);
 		i915_request_set_hold(rq);
 		RQ_TRACE(rq, "on hold\n");
 
@@ -2016,7 +2065,7 @@ static bool execlists_hold(struct intel_engine_cs *engine,
 	if (i915_request_on_hold(rq))
 		return false;
 
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 
 	if (__i915_request_is_complete(rq)) { /* too late! */
 		rq = NULL;
@@ -2032,10 +2081,10 @@ static bool execlists_hold(struct intel_engine_cs *engine,
 	GEM_BUG_ON(i915_request_on_hold(rq));
 	GEM_BUG_ON(rq->engine != engine);
 	__execlists_hold(rq);
-	GEM_BUG_ON(list_empty(&engine->active.hold));
+	GEM_BUG_ON(list_empty(&engine->sched_engine->hold));
 
 unlock:
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 	return rq;
 }
 
@@ -2079,7 +2128,7 @@ static void __execlists_unhold(struct i915_request *rq)
 
 		i915_request_clear_hold(rq);
 		list_move_tail(&rq->sched.link,
-			       i915_sched_lookup_priolist(rq->engine,
+			       i915_sched_lookup_priolist(rq->engine->sched_engine,
 							  rq_prio(rq)));
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
@@ -2115,7 +2164,7 @@ static void __execlists_unhold(struct i915_request *rq)
 static void execlists_unhold(struct intel_engine_cs *engine,
 			     struct i915_request *rq)
 {
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 
 	/*
 	 * Move this request back to the priority queue, and all of its
@@ -2123,12 +2172,12 @@ static void execlists_unhold(struct intel_engine_cs *engine,
 	 */
 	__execlists_unhold(rq);
 
-	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
-		engine->execlists.queue_priority_hint = rq_prio(rq);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+	if (rq_prio(rq) > engine->sched_engine->queue_priority_hint) {
+		engine->sched_engine->queue_priority_hint = rq_prio(rq);
+		tasklet_hi_schedule(&engine->sched_engine->tasklet);
 	}
 
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 }
 
 struct execlists_capture {
@@ -2258,13 +2307,13 @@ static void execlists_capture(struct intel_engine_cs *engine)
 	if (!cap)
 		return;
 
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 	cap->rq = active_context(engine, active_ccid(engine));
 	if (cap->rq) {
 		cap->rq = active_request(cap->rq->context->timeline, cap->rq);
 		cap->rq = i915_request_get_rcu(cap->rq);
 	}
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 	if (!cap->rq)
 		goto err_free;
 
@@ -2316,13 +2365,13 @@ static void execlists_reset(struct intel_engine_cs *engine, const char *msg)
 	ENGINE_TRACE(engine, "reset for %s\n", msg);
 
 	/* Mark this tasklet as disabled to avoid waiting for it to complete */
-	tasklet_disable_nosync(&engine->execlists.tasklet);
+	tasklet_disable_nosync(&engine->sched_engine->tasklet);
 
 	ring_set_paused(engine, 1); /* Freeze the current request in place */
 	execlists_capture(engine);
 	intel_engine_reset(engine, msg);
 
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->sched_engine->tasklet);
 	clear_and_wake_up_bit(bit, lock);
 }
 
@@ -2345,8 +2394,9 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
  */
 static void execlists_submission_tasklet(struct tasklet_struct *t)
 {
-	struct intel_engine_cs * const engine =
-		from_tasklet(engine, t, execlists.tasklet);
+	struct i915_sched_engine *sched_engine =
+		from_tasklet(sched_engine, t, tasklet);
+	struct intel_engine_cs * const engine = sched_engine->private_data;
 	struct i915_request *post[2 * EXECLIST_MAX_PORTS];
 	struct i915_request **inactive;
 
@@ -2421,13 +2471,16 @@ static void execlists_irq_handler(struct intel_engine_cs *engine, u16 iir)
 		intel_engine_signal_breadcrumbs(engine);
 
 	if (tasklet)
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		tasklet_hi_schedule(&engine->sched_engine->tasklet);
 }
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
 {
+	struct intel_engine_cs *engine =
+		container_of(execlists, typeof(*engine), execlists);
+
 	/* Kick the tasklet for some interrupt coalescing and reset handling */
-	tasklet_hi_schedule(&execlists->tasklet);
+	tasklet_hi_schedule(&engine->sched_engine->tasklet);
 }
 
 #define execlists_kick(t, member) \
@@ -2448,19 +2501,20 @@ static void queue_request(struct intel_engine_cs *engine,
 {
 	GEM_BUG_ON(!list_empty(&rq->sched.link));
 	list_add_tail(&rq->sched.link,
-		      i915_sched_lookup_priolist(engine, rq_prio(rq)));
+		      i915_sched_lookup_priolist(engine->sched_engine,
+						 rq_prio(rq)));
 	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
 static bool submit_queue(struct intel_engine_cs *engine,
 			 const struct i915_request *rq)
 {
-	struct intel_engine_execlists *execlists = &engine->execlists;
+	struct i915_sched_engine *sched_engine = engine->sched_engine;
 
-	if (rq_prio(rq) <= execlists->queue_priority_hint)
+	if (rq_prio(rq) <= sched_engine->queue_priority_hint)
 		return false;
 
-	execlists->queue_priority_hint = rq_prio(rq);
+	sched_engine->queue_priority_hint = rq_prio(rq);
 	return true;
 }
 
@@ -2468,7 +2522,7 @@ static bool ancestor_on_hold(const struct intel_engine_cs *engine,
 			     const struct i915_request *rq)
 {
 	GEM_BUG_ON(i915_request_on_hold(rq));
-	return !list_empty(&engine->active.hold) && hold_request(rq);
+	return !list_empty(&engine->sched_engine->hold) && hold_request(rq);
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -2477,23 +2531,24 @@ static void execlists_submit_request(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	if (unlikely(ancestor_on_hold(engine, request))) {
 		RQ_TRACE(request, "ancestor on hold\n");
-		list_add_tail(&request->sched.link, &engine->active.hold);
+		list_add_tail(&request->sched.link,
+			      &engine->sched_engine->hold);
 		i915_request_set_hold(request);
 	} else {
 		queue_request(engine, request);
 
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(i915_sched_engine_is_empty(engine->sched_engine));
 		GEM_BUG_ON(list_empty(&request->sched.link));
 
 		if (submit_queue(engine, request))
 			__execlists_kick(&engine->execlists);
 	}
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 static int
@@ -2533,11 +2588,26 @@ static int execlists_context_alloc(struct intel_context *ce)
 	return lrc_alloc(ce, ce->engine);
 }
 
+static void execlists_context_cancel_request(struct intel_context *ce,
+					     struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = NULL;
+
+	i915_request_active_engine(rq, &engine);
+
+	if (engine && intel_engine_pulse(engine))
+		intel_gt_handle_error(engine->gt, engine->mask, 0,
+				      "request cancellation by %s",
+				      current->comm);
+}
+
 static const struct intel_context_ops execlists_context_ops = {
 	.flags = COPS_HAS_INFLIGHT,
 
 	.alloc = execlists_context_alloc,
 
+	.cancel_request = execlists_context_cancel_request,
+
 	.pre_pin = execlists_context_pre_pin,
 	.pin = execlists_context_pin,
 	.unpin = lrc_unpin,
@@ -2548,6 +2618,8 @@ static const struct intel_context_ops execlists_context_ops = {
 
 	.reset = lrc_reset,
 	.destroy = lrc_destroy,
+
+	.create_virtual = execlists_create_virtual,
 };
 
 static int emit_pdps(struct i915_request *rq)
@@ -2800,10 +2872,8 @@ static int execlists_resume(struct intel_engine_cs *engine)
 
 static void execlists_reset_prepare(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
 	ENGINE_TRACE(engine, "depth<-%d\n",
-		     atomic_read(&execlists->tasklet.count));
+		     atomic_read(&engine->sched_engine->tasklet.count));
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -2814,8 +2884,8 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	 * Turning off the execlists->tasklet until the reset is over
 	 * prevents the race.
 	 */
-	__tasklet_disable_sync_once(&execlists->tasklet);
-	GEM_BUG_ON(!reset_in_progress(execlists));
+	__tasklet_disable_sync_once(&engine->sched_engine->tasklet);
+	GEM_BUG_ON(!reset_in_progress(engine));
 
 	/*
 	 * We stop engines, otherwise we might get failed reset and a
@@ -2957,24 +3027,26 @@ static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 
 	/* Push back any incomplete requests for replay after the reset. */
 	rcu_read_lock();
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 	__unwind_incomplete_requests(engine);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 	rcu_read_unlock();
 }
 
 static void nop_submission_tasklet(struct tasklet_struct *t)
 {
-	struct intel_engine_cs * const engine =
-		from_tasklet(engine, t, execlists.tasklet);
+	struct i915_sched_engine *sched_engine =
+		from_tasklet(sched_engine, t, tasklet);
+	struct intel_engine_cs * const engine = sched_engine->private_data;
 
 	/* The driver is wedged; don't process any more events. */
-	WRITE_ONCE(engine->execlists.queue_priority_hint, INT_MIN);
+	WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN);
 }
 
 static void execlists_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_sched_engine * const sched_engine = engine->sched_engine;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
@@ -2998,15 +3070,15 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	execlists_reset_csb(engine, true);
 
 	rcu_read_lock();
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link)
+	list_for_each_entry(rq, &engine->sched_engine->requests, sched.link)
 		i915_request_put(i915_request_mark_eio(rq));
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&sched_engine->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		priolist_for_each_request_consume(rq, rn, p) {
@@ -3016,12 +3088,12 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 			}
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &sched_engine->queue);
 		i915_priolist_free(p);
 	}
 
 	/* On-hold requests will be flushed to timeline upon their release */
-	list_for_each_entry(rq, &engine->active.hold, sched.link)
+	list_for_each_entry(rq, &sched_engine->hold, sched.link)
 		i915_request_put(i915_request_mark_eio(rq));
 
 	/* Cancel all attached virtual engines */
@@ -3032,7 +3104,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 		rb_erase_cached(rb, &execlists->virtual);
 		RB_CLEAR_NODE(rb);
 
-		spin_lock(&ve->base.active.lock);
+		spin_lock(&ve->base.sched_engine->lock);
 		rq = fetch_and_zero(&ve->request);
 		if (rq) {
 			if (i915_request_mark_eio(rq)) {
@@ -3042,20 +3114,20 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 			}
 			i915_request_put(rq);
 
-			ve->base.execlists.queue_priority_hint = INT_MIN;
+			ve->base.sched_engine->queue_priority_hint = INT_MIN;
 		}
-		spin_unlock(&ve->base.active.lock);
+		spin_unlock(&ve->base.sched_engine->lock);
 	}
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
+	sched_engine->queue_priority_hint = INT_MIN;
+	sched_engine->queue = RB_ROOT_CACHED;
 
-	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
-	execlists->tasklet.callback = nop_submission_tasklet;
+	GEM_BUG_ON(__tasklet_is_enabled(&engine->sched_engine->tasklet));
+	engine->sched_engine->tasklet.callback = nop_submission_tasklet;
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 	rcu_read_unlock();
 }
 
@@ -3073,14 +3145,14 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	 * reset as the next level of recovery, and as a final resort we
 	 * will declare the device wedged.
 	 */
-	GEM_BUG_ON(!reset_in_progress(execlists));
+	GEM_BUG_ON(!reset_in_progress(engine));
 
 	/* And kick in case we missed a new request submission. */
-	if (__tasklet_enable(&execlists->tasklet))
+	if (__tasklet_enable(&engine->sched_engine->tasklet))
 		__execlists_kick(execlists);
 
 	ENGINE_TRACE(engine, "depth->%d\n",
-		     atomic_read(&execlists->tasklet.count));
+		     atomic_read(&engine->sched_engine->tasklet.count));
 }
 
 static void gen8_logical_ring_enable_irq(struct intel_engine_cs *engine)
@@ -3101,6 +3173,42 @@ static void execlists_park(struct intel_engine_cs *engine)
 	cancel_timer(&engine->execlists.preempt);
 }
 
+static void add_to_engine(struct i915_request *rq)
+{
+	lockdep_assert_held(&rq->engine->sched_engine->lock);
+	list_move_tail(&rq->sched.link, &rq->engine->sched_engine->requests);
+}
+
+static void remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock_irq(&locked->sched_engine->lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->sched_engine->lock);
+		spin_lock(&engine->sched_engine->lock);
+		locked = engine;
+	}
+	list_del_init(&rq->sched.link);
+
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
+
+	/* Prevent further __await_execution() registering a cb, then flush */
+	set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
+
+	spin_unlock_irq(&locked->sched_engine->lock);
+
+	i915_request_notify_execute_cb_imm(rq);
+}
+
 static bool can_preempt(struct intel_engine_cs *engine)
 {
 	if (GRAPHICS_VER(engine->i915) > 8)
@@ -3110,11 +3218,62 @@ static bool can_preempt(struct intel_engine_cs *engine)
 	return engine->class != RENDER_CLASS;
 }
 
+static void kick_execlists(const struct i915_request *rq, int prio)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	struct i915_sched_engine *sched_engine = engine->sched_engine;
+	const struct i915_request *inflight;
+
+	/*
+	 * We only need to kick the tasklet once for the high priority
+	 * new context we add into the queue.
+	 */
+	if (prio <= sched_engine->queue_priority_hint)
+		return;
+
+	rcu_read_lock();
+
+	/* Nothing currently active? We're overdue for a submission! */
+	inflight = execlists_active(&engine->execlists);
+	if (!inflight)
+		goto unlock;
+
+	/*
+	 * If we are already the currently executing context, don't
+	 * bother evaluating if we should preempt ourselves.
+	 */
+	if (inflight->context == rq->context)
+		goto unlock;
+
+	ENGINE_TRACE(engine,
+		     "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
+		     prio,
+		     rq->fence.context, rq->fence.seqno,
+		     inflight->fence.context, inflight->fence.seqno,
+		     inflight->sched.attr.priority);
+
+	sched_engine->queue_priority_hint = prio;
+
+	/*
+	 * Allow preemption of low -> normal -> high, but we do
+	 * not allow low priority tasks to preempt other low priority
+	 * tasks under the impression that latency for low priority
+	 * tasks does not matter (as much as background throughput),
+	 * so kiss.
+	 */
+	if (prio >= max(I915_PRIORITY_NORMAL, rq_prio(inflight)))
+		tasklet_hi_schedule(&sched_engine->tasklet);
+
+unlock:
+	rcu_read_unlock();
+}
+
 static void execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
-	engine->schedule = i915_schedule;
-	engine->execlists.tasklet.callback = execlists_submission_tasklet;
+	engine->sched_engine->schedule = i915_schedule;
+	engine->sched_engine->kick_backend = kick_execlists;
+	engine->sched_engine->tasklet.callback = execlists_submission_tasklet;
 }
 
 static void execlists_shutdown(struct intel_engine_cs *engine)
@@ -3122,7 +3281,7 @@ static void execlists_shutdown(struct intel_engine_cs *engine)
 	/* Synchronise with residual timers and any softirq they raise */
 	del_timer_sync(&engine->execlists.timer);
 	del_timer_sync(&engine->execlists.preempt);
-	tasklet_kill(&engine->execlists.tasklet);
+	tasklet_kill(&engine->sched_engine->tasklet);
 }
 
 static void execlists_release(struct intel_engine_cs *engine)
@@ -3144,6 +3303,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 
 	engine->cops = &execlists_context_ops;
 	engine->request_alloc = execlists_request_alloc;
+	engine->add_active_request = add_to_engine;
+	engine->remove_active_request = remove_from_engine;
 
 	engine->reset.prepare = execlists_reset_prepare;
 	engine->reset.rewind = execlists_reset_rewind;
@@ -3238,7 +3399,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	struct intel_uncore *uncore = engine->uncore;
 	u32 base = engine->mmio_base;
 
-	tasklet_setup(&engine->execlists.tasklet, execlists_submission_tasklet);
+	tasklet_setup(&engine->sched_engine->tasklet, execlists_submission_tasklet);
 	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
 	timer_setup(&engine->execlists.preempt, execlists_preempt, 0);
 
@@ -3255,6 +3416,10 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(base));
 		execlists->ctrl_reg = uncore->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_CONTROL(base));
+
+		engine->fw_domain = intel_uncore_forcewake_for_reg(engine->uncore,
+				    RING_EXECLIST_CONTROL(engine->mmio_base),
+				    FW_REG_WRITE);
 	} else {
 		execlists->submit_reg = uncore->regs +
 			i915_mmio_reg_offset(RING_ELSP(base));
@@ -3272,7 +3437,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 		execlists->csb_size = GEN11_CSB_ENTRIES;
 
 	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
-	if (GRAPHICS_VER(engine->i915) >= 11) {
+	if (GRAPHICS_VER(engine->i915) >= 11 &&
+	    GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 50)) {
 		execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
 		execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32);
 	}
@@ -3286,7 +3452,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 
 static struct list_head *virtual_queue(struct virtual_engine *ve)
 {
-	return &ve->base.execlists.default_priolist.requests;
+	return &ve->base.sched_engine->default_priolist.requests;
 }
 
 static void rcu_virtual_context_destroy(struct work_struct *wrk)
@@ -3301,7 +3467,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 	if (unlikely(ve->request)) {
 		struct i915_request *old;
 
-		spin_lock_irq(&ve->base.active.lock);
+		spin_lock_irq(&ve->base.sched_engine->lock);
 
 		old = fetch_and_zero(&ve->request);
 		if (old) {
@@ -3310,7 +3476,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 			i915_request_put(old);
 		}
 
-		spin_unlock_irq(&ve->base.active.lock);
+		spin_unlock_irq(&ve->base.sched_engine->lock);
 	}
 
 	/*
@@ -3320,7 +3486,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 	 * rbtrees as in the case it is running in parallel, it may reinsert
 	 * the rb_node into a sibling.
 	 */
-	tasklet_kill(&ve->base.execlists.tasklet);
+	tasklet_kill(&ve->base.sched_engine->tasklet);
 
 	/* Decouple ourselves from the siblings, no more access allowed. */
 	for (n = 0; n < ve->num_siblings; n++) {
@@ -3330,24 +3496,26 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 		if (RB_EMPTY_NODE(node))
 			continue;
 
-		spin_lock_irq(&sibling->active.lock);
+		spin_lock_irq(&sibling->sched_engine->lock);
 
-		/* Detachment is lazily performed in the execlists tasklet */
+		/* Detachment is lazily performed in the sched_engine->tasklet */
 		if (!RB_EMPTY_NODE(node))
 			rb_erase_cached(node, &sibling->execlists.virtual);
 
-		spin_unlock_irq(&sibling->active.lock);
+		spin_unlock_irq(&sibling->sched_engine->lock);
 	}
-	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet));
+	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.sched_engine->tasklet));
 	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
 
 	lrc_fini(&ve->context);
 	intel_context_fini(&ve->context);
 
-	intel_breadcrumbs_free(ve->base.breadcrumbs);
+	if (ve->base.breadcrumbs)
+		intel_breadcrumbs_put(ve->base.breadcrumbs);
+	if (ve->base.sched_engine)
+		i915_sched_engine_put(ve->base.sched_engine);
 	intel_engine_free_request_pool(&ve->base);
 
-	kfree(ve->bonds);
 	kfree(ve);
 }
 
@@ -3440,11 +3608,24 @@ static void virtual_context_exit(struct intel_context *ce)
 		intel_engine_pm_put(ve->siblings[n]);
 }
 
+static struct intel_engine_cs *
+virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling)
+{
+	struct virtual_engine *ve = to_virtual_engine(engine);
+
+	if (sibling >= ve->num_siblings)
+		return NULL;
+
+	return ve->siblings[sibling];
+}
+
 static const struct intel_context_ops virtual_context_ops = {
 	.flags = COPS_HAS_INFLIGHT,
 
 	.alloc = virtual_context_alloc,
 
+	.cancel_request = execlists_context_cancel_request,
+
 	.pre_pin = virtual_context_pre_pin,
 	.pin = virtual_context_pin,
 	.unpin = lrc_unpin,
@@ -3454,6 +3635,8 @@ static const struct intel_context_ops virtual_context_ops = {
 	.exit = virtual_context_exit,
 
 	.destroy = virtual_context_destroy,
+
+	.get_sibling = virtual_get_sibling,
 };
 
 static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
@@ -3475,16 +3658,18 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 
 	ENGINE_TRACE(&ve->base, "rq=%llx:%lld, mask=%x, prio=%d\n",
 		     rq->fence.context, rq->fence.seqno,
-		     mask, ve->base.execlists.queue_priority_hint);
+		     mask, ve->base.sched_engine->queue_priority_hint);
 
 	return mask;
 }
 
 static void virtual_submission_tasklet(struct tasklet_struct *t)
 {
+	struct i915_sched_engine *sched_engine =
+		from_tasklet(sched_engine, t, tasklet);
 	struct virtual_engine * const ve =
-		from_tasklet(ve, t, base.execlists.tasklet);
-	const int prio = READ_ONCE(ve->base.execlists.queue_priority_hint);
+		(struct virtual_engine *)sched_engine->private_data;
+	const int prio = READ_ONCE(sched_engine->queue_priority_hint);
 	intel_engine_mask_t mask;
 	unsigned int n;
 
@@ -3503,7 +3688,7 @@ static void virtual_submission_tasklet(struct tasklet_struct *t)
 		if (!READ_ONCE(ve->request))
 			break; /* already handled by a sibling's tasklet */
 
-		spin_lock_irq(&sibling->active.lock);
+		spin_lock_irq(&sibling->sched_engine->lock);
 
 		if (unlikely(!(mask & sibling->mask))) {
 			if (!RB_EMPTY_NODE(&node->rb)) {
@@ -3552,11 +3737,11 @@ static void virtual_submission_tasklet(struct tasklet_struct *t)
 submit_engine:
 		GEM_BUG_ON(RB_EMPTY_NODE(&node->rb));
 		node->prio = prio;
-		if (first && prio > sibling->execlists.queue_priority_hint)
-			tasklet_hi_schedule(&sibling->execlists.tasklet);
+		if (first && prio > sibling->sched_engine->queue_priority_hint)
+			tasklet_hi_schedule(&sibling->sched_engine->tasklet);
 
 unlock_engine:
-		spin_unlock_irq(&sibling->active.lock);
+		spin_unlock_irq(&sibling->sched_engine->lock);
 
 		if (intel_context_inflight(&ve->context))
 			break;
@@ -3574,7 +3759,7 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	spin_lock_irqsave(&ve->base.active.lock, flags);
+	spin_lock_irqsave(&ve->base.sched_engine->lock, flags);
 
 	/* By the time we resubmit a request, it may be completed */
 	if (__i915_request_is_complete(rq)) {
@@ -3588,68 +3773,25 @@ static void virtual_submit_request(struct i915_request *rq)
 		i915_request_put(ve->request);
 	}
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
+	ve->base.sched_engine->queue_priority_hint = rq_prio(rq);
 	ve->request = i915_request_get(rq);
 
 	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
 	list_move_tail(&rq->sched.link, virtual_queue(ve));
 
-	tasklet_hi_schedule(&ve->base.execlists.tasklet);
+	tasklet_hi_schedule(&ve->base.sched_engine->tasklet);
 
 unlock:
-	spin_unlock_irqrestore(&ve->base.active.lock, flags);
+	spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags);
 }
 
-static struct ve_bond *
-virtual_find_bond(struct virtual_engine *ve,
-		  const struct intel_engine_cs *master)
-{
-	int i;
-
-	for (i = 0; i < ve->num_bonds; i++) {
-		if (ve->bonds[i].master == master)
-			return &ve->bonds[i];
-	}
-
-	return NULL;
-}
-
-static void
-virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
-{
-	struct virtual_engine *ve = to_virtual_engine(rq->engine);
-	intel_engine_mask_t allowed, exec;
-	struct ve_bond *bond;
-
-	allowed = ~to_request(signal)->engine->mask;
-
-	bond = virtual_find_bond(ve, to_request(signal)->engine);
-	if (bond)
-		allowed &= bond->sibling_mask;
-
-	/* Restrict the bonded request to run on only the available engines */
-	exec = READ_ONCE(rq->execution_mask);
-	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
-		;
-
-	/* Prevent the master from being re-run on the bonded engines */
-	to_request(signal)->execution_mask &= ~allowed;
-}
-
-struct intel_context *
-intel_execlists_create_virtual(struct intel_engine_cs **siblings,
-			       unsigned int count)
+static struct intel_context *
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
 {
 	struct virtual_engine *ve;
 	unsigned int n;
 	int err;
 
-	if (count == 0)
-		return ERR_PTR(-EINVAL);
-
-	if (count == 1)
-		return intel_context_create(siblings[0]);
-
 	ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL);
 	if (!ve)
 		return ERR_PTR(-ENOMEM);
@@ -3681,19 +3823,24 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
 
-	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_execlists(&ve->base);
 
+	ve->base.sched_engine = i915_sched_engine_create(ENGINE_VIRTUAL);
+	if (!ve->base.sched_engine) {
+		err = -ENOMEM;
+		goto err_put;
+	}
+	ve->base.sched_engine->private_data = &ve->base;
+
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
 
-	ve->base.schedule = i915_schedule;
+	ve->base.sched_engine->schedule = i915_schedule;
+	ve->base.sched_engine->kick_backend = kick_execlists;
 	ve->base.submit_request = virtual_submit_request;
-	ve->base.bond_execute = virtual_bond_execute;
 
 	INIT_LIST_HEAD(virtual_queue(ve));
-	ve->base.execlists.queue_priority_hint = INT_MIN;
-	tasklet_setup(&ve->base.execlists.tasklet, virtual_submission_tasklet);
+	tasklet_setup(&ve->base.sched_engine->tasklet, virtual_submission_tasklet);
 
 	intel_context_init(&ve->context, &ve->base);
 
@@ -3721,7 +3868,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 		 * layering if we handle cloning of the requests and
 		 * submitting a copy into each backend.
 		 */
-		if (sibling->execlists.tasklet.callback !=
+		if (sibling->sched_engine->tasklet.callback !=
 		    execlists_submission_tasklet) {
 			err = -ENODEV;
 			goto err_put;
@@ -3756,6 +3903,8 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			 "v%dx%d", ve->base.class, count);
 		ve->base.context_size = sibling->context_size;
 
+		ve->base.add_active_request = sibling->add_active_request;
+		ve->base.remove_active_request = sibling->remove_active_request;
 		ve->base.emit_bb_start = sibling->emit_bb_start;
 		ve->base.emit_flush = sibling->emit_flush;
 		ve->base.emit_init_breadcrumb = sibling->emit_init_breadcrumb;
@@ -3776,70 +3925,6 @@ err_put:
 	return ERR_PTR(err);
 }
 
-struct intel_context *
-intel_execlists_clone_virtual(struct intel_engine_cs *src)
-{
-	struct virtual_engine *se = to_virtual_engine(src);
-	struct intel_context *dst;
-
-	dst = intel_execlists_create_virtual(se->siblings,
-					     se->num_siblings);
-	if (IS_ERR(dst))
-		return dst;
-
-	if (se->num_bonds) {
-		struct virtual_engine *de = to_virtual_engine(dst->engine);
-
-		de->bonds = kmemdup(se->bonds,
-				    sizeof(*se->bonds) * se->num_bonds,
-				    GFP_KERNEL);
-		if (!de->bonds) {
-			intel_context_put(dst);
-			return ERR_PTR(-ENOMEM);
-		}
-
-		de->num_bonds = se->num_bonds;
-	}
-
-	return dst;
-}
-
-int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
-				     const struct intel_engine_cs *master,
-				     const struct intel_engine_cs *sibling)
-{
-	struct virtual_engine *ve = to_virtual_engine(engine);
-	struct ve_bond *bond;
-	int n;
-
-	/* Sanity check the sibling is part of the virtual engine */
-	for (n = 0; n < ve->num_siblings; n++)
-		if (sibling == ve->siblings[n])
-			break;
-	if (n == ve->num_siblings)
-		return -EINVAL;
-
-	bond = virtual_find_bond(ve, master);
-	if (bond) {
-		bond->sibling_mask |= sibling->mask;
-		return 0;
-	}
-
-	bond = krealloc(ve->bonds,
-			sizeof(*bond) * (ve->num_bonds + 1),
-			GFP_KERNEL);
-	if (!bond)
-		return -ENOMEM;
-
-	bond[ve->num_bonds].master = master;
-	bond[ve->num_bonds].sibling_mask = sibling->mask;
-
-	ve->bonds = bond;
-	ve->num_bonds++;
-
-	return 0;
-}
-
 void intel_execlists_show_requests(struct intel_engine_cs *engine,
 				   struct drm_printer *m,
 				   void (*show_request)(struct drm_printer *m,
@@ -3849,16 +3934,17 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 				   unsigned int max)
 {
 	const struct intel_engine_execlists *execlists = &engine->execlists;
+	struct i915_sched_engine *sched_engine = engine->sched_engine;
 	struct i915_request *rq, *last;
 	unsigned long flags;
 	unsigned int count;
 	struct rb_node *rb;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&sched_engine->lock, flags);
 
 	last = NULL;
 	count = 0;
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
+	list_for_each_entry(rq, &sched_engine->requests, sched.link) {
 		if (count++ < max - 1)
 			show_request(m, rq, "\t\t", 0);
 		else
@@ -3873,13 +3959,13 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 		show_request(m, last, "\t\t", 0);
 	}
 
-	if (execlists->queue_priority_hint != INT_MIN)
+	if (sched_engine->queue_priority_hint != INT_MIN)
 		drm_printf(m, "\t\tQueue priority hint: %d\n",
-			   READ_ONCE(execlists->queue_priority_hint));
+			   READ_ONCE(sched_engine->queue_priority_hint));
 
 	last = NULL;
 	count = 0;
-	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&sched_engine->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
 
 		priolist_for_each_request(rq, p) {
@@ -3921,7 +4007,7 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 		show_request(m, last, "\t\t", 0);
 	}
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
index 4ca9b475e252..a1aa92c983a5 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
@@ -32,15 +32,7 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							int indent),
 				   unsigned int max);
 
-struct intel_context *
-intel_execlists_create_virtual(struct intel_engine_cs **siblings,
-			       unsigned int count);
-
-struct intel_context *
-intel_execlists_clone_virtual(struct intel_engine_cs *src);
-
-int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
-				     const struct intel_engine_cs *master,
-				     const struct intel_engine_cs *sibling);
+bool
+intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
 
 #endif /* __INTEL_EXECLISTS_SUBMISSION_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 20e46b843324..de3ac58fceec 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -826,13 +826,13 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;
 
 	/*
-	 * On BXT+/CNL+ writes larger than 64 bit to the GTT pagetable range
+	 * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
 	 * will be dropped. For WC mappings in general we have 64 byte burst
 	 * writes when the WC buffer is flushed, so we can't use it, but have to
 	 * resort to an uncached mapping. The WC issue is easily caught by the
 	 * readback check when writing GTT PTE entries.
 	 */
-	if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 10)
+	if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11)
 		ggtt->gsm = ioremap(phys_addr, size);
 	else
 		ggtt->gsm = ioremap_wc(phys_addr, size);
@@ -1494,7 +1494,7 @@ intel_partial_pages(const struct i915_ggtt_view *view,
 	if (ret)
 		goto err_sg_alloc;
 
-	iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset, true);
+	iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset);
 	GEM_BUG_ON(!iter);
 
 	sg = st->sgl;
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 2694dbb9967e..1c3af0fc0456 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -123,8 +123,10 @@
 #define   MI_SEMAPHORE_SAD_NEQ_SDD	(5 << 12)
 #define   MI_SEMAPHORE_TOKEN_MASK	REG_GENMASK(9, 5)
 #define   MI_SEMAPHORE_TOKEN_SHIFT	5
+#define MI_STORE_DATA_IMM	MI_INSTR(0x20, 0)
 #define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
 #define MI_STORE_DWORD_IMM_GEN4	MI_INSTR(0x20, 2)
+#define MI_STORE_QWORD_IMM_GEN8 (MI_INSTR(0x20, 3) | REG_BIT(21))
 #define   MI_MEM_VIRTUAL	(1 << 22) /* 945,g33,965 */
 #define   MI_USE_GGTT		(1 << 22) /* g4x+ */
 #define MI_STORE_DWORD_INDEX	MI_INSTR(0x21, 1)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 2161bf01ef8b..62d40c986642 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -13,6 +13,7 @@
 #include "intel_gt_clock_utils.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
+#include "intel_migrate.h"
 #include "intel_mocs.h"
 #include "intel_rc6.h"
 #include "intel_renderstate.h"
@@ -40,8 +41,8 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 	intel_gt_init_timelines(gt);
 	intel_gt_pm_init_early(gt);
 
-	intel_rps_init_early(&gt->rps);
 	intel_uc_init_early(&gt->uc);
+	intel_rps_init_early(&gt->rps);
 }
 
 int intel_gt_probe_lmem(struct intel_gt *gt)
@@ -83,13 +84,73 @@ void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
 	gt->ggtt = ggtt;
 }
 
+static const struct intel_mmio_range icl_l3bank_steering_table[] = {
+	{ 0x00B100, 0x00B3FF },
+	{},
+};
+
+static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = {
+	{ 0x004000, 0x004AFF },
+	{ 0x00C800, 0x00CFFF },
+	{ 0x00DD00, 0x00DDFF },
+	{ 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */
+	{},
+};
+
+static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = {
+	{ 0x00B000, 0x00B0FF },
+	{ 0x00D800, 0x00D8FF },
+	{},
+};
+
+static const struct intel_mmio_range dg2_lncf_steering_table[] = {
+	{ 0x00B000, 0x00B0FF },
+	{ 0x00D880, 0x00D8FF },
+	{},
+};
+
+static u16 slicemask(struct intel_gt *gt, int count)
+{
+	u64 dss_mask = intel_sseu_get_subslices(&gt->info.sseu, 0);
+
+	return intel_slicemask_from_dssmask(dss_mask, count);
+}
+
 int intel_gt_init_mmio(struct intel_gt *gt)
 {
+	struct drm_i915_private *i915 = gt->i915;
+
 	intel_gt_init_clock_frequency(gt);
 
 	intel_uc_init_mmio(&gt->uc);
 	intel_sseu_info_init(gt);
 
+	/*
+	 * An mslice is unavailable only if both the meml3 for the slice is
+	 * disabled *and* all of the DSS in the slice (quadrant) are disabled.
+	 */
+	if (HAS_MSLICES(i915))
+		gt->info.mslice_mask =
+			slicemask(gt, GEN_DSS_PER_MSLICE) |
+			(intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
+			 GEN12_MEML3_EN_MASK);
+
+	if (IS_DG2(i915)) {
+		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
+		gt->steering_table[LNCF] = dg2_lncf_steering_table;
+	} else if (IS_XEHPSDV(i915)) {
+		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
+		gt->steering_table[LNCF] = xehpsdv_lncf_steering_table;
+	} else if (GRAPHICS_VER(i915) >= 11 &&
+		   GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) {
+		gt->steering_table[L3BANK] = icl_l3bank_steering_table;
+		gt->info.l3bank_mask =
+			~intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
+			GEN10_L3BANK_MASK;
+	} else if (HAS_MSLICES(i915)) {
+		MISSING_CASE(INTEL_INFO(i915)->platform);
+	}
+
 	return intel_engines_init_mmio(gt);
 }
 
@@ -192,7 +253,7 @@ static void clear_register(struct intel_uncore *uncore, i915_reg_t reg)
 	intel_uncore_rmw(uncore, reg, 0, 0);
 }
 
-static void gen8_clear_engine_error_register(struct intel_engine_cs *engine)
+static void gen6_clear_engine_error_register(struct intel_engine_cs *engine)
 {
 	GEN6_RING_FAULT_REG_RMW(engine, RING_FAULT_VALID, 0);
 	GEN6_RING_FAULT_REG_POSTING_READ(engine);
@@ -238,7 +299,7 @@ intel_gt_clear_error_registers(struct intel_gt *gt,
 		enum intel_engine_id id;
 
 		for_each_engine_masked(engine, gt, engine_mask, id)
-			gen8_clear_engine_error_register(engine);
+			gen6_clear_engine_error_register(engine);
 	}
 }
 
@@ -572,6 +633,25 @@ static void __intel_gt_disable(struct intel_gt *gt)
 	GEM_BUG_ON(intel_gt_pm_is_awake(gt));
 }
 
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
+{
+	long remaining_timeout;
+
+	/* If the device is asleep, we have no requests outstanding */
+	if (!intel_gt_pm_is_awake(gt))
+		return 0;
+
+	while ((timeout = intel_gt_retire_requests_timeout(gt, timeout,
+							   &remaining_timeout)) > 0) {
+		cond_resched();
+		if (signal_pending(current))
+			return -EINTR;
+	}
+
+	return timeout ? timeout : intel_uc_wait_for_idle(&gt->uc,
+							  remaining_timeout);
+}
+
 int intel_gt_init(struct intel_gt *gt)
 {
 	int err;
@@ -622,10 +702,14 @@ int intel_gt_init(struct intel_gt *gt)
 	if (err)
 		goto err_gt;
 
+	intel_uc_init_late(&gt->uc);
+
 	err = i915_inject_probe_error(gt->i915, -EIO);
 	if (err)
 		goto err_gt;
 
+	intel_migrate_init(&gt->migrate, gt);
+
 	goto out_fw;
 err_gt:
 	__intel_gt_disable(gt);
@@ -649,6 +733,7 @@ void intel_gt_driver_remove(struct intel_gt *gt)
 {
 	__intel_gt_disable(gt);
 
+	intel_migrate_fini(&gt->migrate);
 	intel_uc_driver_remove(&gt->uc);
 
 	intel_engines_release(gt);
@@ -697,6 +782,112 @@ void intel_gt_driver_late_release(struct intel_gt *gt)
 	intel_engines_free(gt);
 }
 
+/**
+ * intel_gt_reg_needs_read_steering - determine whether a register read
+ *     requires explicit steering
+ * @gt: GT structure
+ * @reg: the register to check steering requirements for
+ * @type: type of multicast steering to check
+ *
+ * Determines whether @reg needs explicit steering of a specific type for
+ * reads.
+ *
+ * Returns false if @reg does not belong to a register range of the given
+ * steering type, or if the default (subslice-based) steering IDs are suitable
+ * for @type steering too.
+ */
+static bool intel_gt_reg_needs_read_steering(struct intel_gt *gt,
+					     i915_reg_t reg,
+					     enum intel_steering_type type)
+{
+	const u32 offset = i915_mmio_reg_offset(reg);
+	const struct intel_mmio_range *entry;
+
+	if (likely(!intel_gt_needs_read_steering(gt, type)))
+		return false;
+
+	for (entry = gt->steering_table[type]; entry->end; entry++) {
+		if (offset >= entry->start && offset <= entry->end)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * intel_gt_get_valid_steering - determines valid IDs for a class of MCR steering
+ * @gt: GT structure
+ * @type: multicast register type
+ * @sliceid: Slice ID returned
+ * @subsliceid: Subslice ID returned
+ *
+ * Determines sliceid and subsliceid values that will steer reads
+ * of a specific multicast register class to a valid value.
+ */
+static void intel_gt_get_valid_steering(struct intel_gt *gt,
+					enum intel_steering_type type,
+					u8 *sliceid, u8 *subsliceid)
+{
+	switch (type) {
+	case L3BANK:
+		GEM_DEBUG_WARN_ON(!gt->info.l3bank_mask); /* should be impossible! */
+
+		*sliceid = 0;		/* unused */
+		*subsliceid = __ffs(gt->info.l3bank_mask);
+		break;
+	case MSLICE:
+		GEM_DEBUG_WARN_ON(!gt->info.mslice_mask); /* should be impossible! */
+
+		*sliceid = __ffs(gt->info.mslice_mask);
+		*subsliceid = 0;	/* unused */
+		break;
+	case LNCF:
+		GEM_DEBUG_WARN_ON(!gt->info.mslice_mask); /* should be impossible! */
+
+		/*
+		 * An LNCF is always present if its mslice is present, so we
+		 * can safely just steer to LNCF 0 in all cases.
+		 */
+		*sliceid = __ffs(gt->info.mslice_mask) << 1;
+		*subsliceid = 0;	/* unused */
+		break;
+	default:
+		MISSING_CASE(type);
+		*sliceid = 0;
+		*subsliceid = 0;
+	}
+}
+
+/**
+ * intel_gt_read_register_fw - reads a GT register with support for multicast
+ * @gt: GT structure
+ * @reg: register to read
+ *
+ * This function will read a GT register.  If the register is a multicast
+ * register, the read will be steered to a valid instance (i.e., one that
+ * isn't fused off or powered down by power gating).
+ *
+ * Returns the value from a valid instance of @reg.
+ */
+u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg)
+{
+	int type;
+	u8 sliceid, subsliceid;
+
+	for (type = 0; type < NUM_STEERING_TYPES; type++) {
+		if (intel_gt_reg_needs_read_steering(gt, reg, type)) {
+			intel_gt_get_valid_steering(gt, type, &sliceid,
+						    &subsliceid);
+			return intel_uncore_read_with_mcr_steering_fw(gt->uncore,
+								      reg,
+								      sliceid,
+								      subsliceid);
+		}
+	}
+
+	return intel_uncore_read_fw(gt->uncore, reg);
+}
+
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 7ec395cace69..74e771871a9b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -48,6 +48,8 @@ void intel_gt_driver_release(struct intel_gt *gt);
 
 void intel_gt_driver_late_release(struct intel_gt *gt);
 
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
+
 void intel_gt_check_and_clear_faults(struct intel_gt *gt);
 void intel_gt_clear_error_registers(struct intel_gt *gt,
 				    intel_engine_mask_t engine_mask);
@@ -75,6 +77,14 @@ static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
 	return unlikely(test_bit(I915_WEDGED, &gt->reset.flags));
 }
 
+static inline bool intel_gt_needs_read_steering(struct intel_gt *gt,
+						enum intel_steering_type type)
+{
+	return gt->steering_table[type];
+}
+
+u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg);
+
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 9f0e729d2d15..3513d6f90747 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -24,8 +24,8 @@ static u32 read_reference_ts_freq(struct intel_uncore *uncore)
 	return base_freq + frac_freq;
 }
 
-static u32 gen10_get_crystal_clock_freq(struct intel_uncore *uncore,
-					u32 rpm_config_reg)
+static u32 gen9_get_crystal_clock_freq(struct intel_uncore *uncore,
+				       u32 rpm_config_reg)
 {
 	u32 f19_2_mhz = 19200000;
 	u32 f24_mhz = 24000000;
@@ -128,10 +128,10 @@ static u32 read_clock_frequency(struct intel_uncore *uncore)
 		} else {
 			u32 c0 = intel_uncore_read(uncore, RPM_CONFIG0);
 
-			if (GRAPHICS_VER(uncore->i915) <= 10)
-				freq = gen10_get_crystal_clock_freq(uncore, c0);
-			else
+			if (GRAPHICS_VER(uncore->i915) >= 11)
 				freq = gen11_get_crystal_clock_freq(uncore, c0);
+			else
+				freq = gen9_get_crystal_clock_freq(uncore, c0);
 
 			/*
 			 * Now figure out how the command stream's timestamp
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index c13462274fe8..b2de83be4d97 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -184,7 +184,13 @@ void gen11_gt_irq_reset(struct intel_gt *gt)
 	intel_uncore_write(uncore, GEN11_BCS_RSVD_INTR_MASK,	~0);
 	intel_uncore_write(uncore, GEN11_VCS0_VCS1_INTR_MASK,	~0);
 	intel_uncore_write(uncore, GEN11_VCS2_VCS3_INTR_MASK,	~0);
+	if (HAS_ENGINE(gt, VCS4) || HAS_ENGINE(gt, VCS5))
+		intel_uncore_write(uncore, GEN12_VCS4_VCS5_INTR_MASK,   ~0);
+	if (HAS_ENGINE(gt, VCS6) || HAS_ENGINE(gt, VCS7))
+		intel_uncore_write(uncore, GEN12_VCS6_VCS7_INTR_MASK,   ~0);
 	intel_uncore_write(uncore, GEN11_VECS0_VECS1_INTR_MASK,	~0);
+	if (HAS_ENGINE(gt, VECS2) || HAS_ENGINE(gt, VECS3))
+		intel_uncore_write(uncore, GEN12_VECS2_VECS3_INTR_MASK, ~0);
 
 	intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0);
 	intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
@@ -218,8 +224,13 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	intel_uncore_write(uncore, GEN11_BCS_RSVD_INTR_MASK, ~smask);
 	intel_uncore_write(uncore, GEN11_VCS0_VCS1_INTR_MASK, ~dmask);
 	intel_uncore_write(uncore, GEN11_VCS2_VCS3_INTR_MASK, ~dmask);
+	if (HAS_ENGINE(gt, VCS4) || HAS_ENGINE(gt, VCS5))
+		intel_uncore_write(uncore, GEN12_VCS4_VCS5_INTR_MASK, ~dmask);
+	if (HAS_ENGINE(gt, VCS6) || HAS_ENGINE(gt, VCS7))
+		intel_uncore_write(uncore, GEN12_VCS6_VCS7_INTR_MASK, ~dmask);
 	intel_uncore_write(uncore, GEN11_VECS0_VECS1_INTR_MASK, ~dmask);
-
+	if (HAS_ENGINE(gt, VECS2) || HAS_ENGINE(gt, VECS3))
+		intel_uncore_write(uncore, GEN12_VECS2_VECS3_INTR_MASK, ~dmask);
 	/*
 	 * RPS interrupts will get enabled/disabled on demand when RPS itself
 	 * is enabled/disabled.
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index aef3084e8b16..dea8e2479897 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -6,7 +6,6 @@
 #include <linux/suspend.h>
 
 #include "i915_drv.h"
-#include "i915_globals.h"
 #include "i915_params.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
@@ -67,8 +66,6 @@ static int __gt_unpark(struct intel_wakeref *wf)
 
 	GT_TRACE(gt, "\n");
 
-	i915_globals_unpark();
-
 	/*
 	 * It seems that the DMC likes to transition between the DC states a lot
 	 * when there are no connected displays (no active power domains) during
@@ -116,8 +113,6 @@ static int __gt_park(struct intel_wakeref *wf)
 	GEM_BUG_ON(!wakeref);
 	intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref);
 
-	i915_globals_park();
-
 	return 0;
 }
 
@@ -174,8 +169,6 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 	if (intel_gt_is_wedged(gt))
 		intel_gt_unset_wedged(gt);
 
-	intel_uc_sanitize(&gt->uc);
-
 	for_each_engine(engine, gt, id)
 		if (engine->reset.prepare)
 			engine->reset.prepare(engine);
@@ -191,6 +184,8 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 			__intel_engine_reset(engine, false);
 	}
 
+	intel_uc_reset(&gt->uc, false);
+
 	for_each_engine(engine, gt, id)
 		if (engine->reset.finish)
 			engine->reset.finish(engine);
@@ -243,6 +238,8 @@ int intel_gt_resume(struct intel_gt *gt)
 		goto err_wedged;
 	}
 
+	intel_uc_reset_finish(&gt->uc);
+
 	intel_rps_enable(&gt->rps);
 	intel_llc_enable(&gt->llc);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 647eca9d867a..edb881d75630 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -130,7 +130,8 @@ void intel_engine_fini_retire(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->retire);
 }
 
-long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout,
+				      long *remaining_timeout)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl, *tn;
@@ -195,22 +196,10 @@ out_active:	spin_lock(&timelines->lock);
 	if (flush_submission(gt, timeout)) /* Wait, there's more! */
 		active_count++;
 
-	return active_count ? timeout : 0;
-}
-
-int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
-{
-	/* If the device is asleep, we have no requests outstanding */
-	if (!intel_gt_pm_is_awake(gt))
-		return 0;
-
-	while ((timeout = intel_gt_retire_requests_timeout(gt, timeout)) > 0) {
-		cond_resched();
-		if (signal_pending(current))
-			return -EINTR;
-	}
+	if (remaining_timeout)
+		*remaining_timeout = timeout;
 
-	return timeout;
+	return active_count ? timeout : 0;
 }
 
 static void retire_work_handler(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index fcc30a6e4fe9..51dbe0e3294e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -6,14 +6,17 @@
 #ifndef INTEL_GT_REQUESTS_H
 #define INTEL_GT_REQUESTS_H
 
+#include <stddef.h>
+
 struct intel_engine_cs;
 struct intel_gt;
 struct intel_timeline;
 
-long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout);
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout,
+				      long *remaining_timeout);
 static inline void intel_gt_retire_requests(struct intel_gt *gt)
 {
-	intel_gt_retire_requests_timeout(gt, 0);
+	intel_gt_retire_requests_timeout(gt, 0, NULL);
 }
 
 void intel_engine_init_retire(struct intel_engine_cs *engine);
@@ -21,8 +24,6 @@ void intel_engine_add_retire(struct intel_engine_cs *engine,
 			     struct intel_timeline *tl);
 void intel_engine_fini_retire(struct intel_engine_cs *engine);
 
-int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
-
 void intel_gt_init_requests(struct intel_gt *gt);
 void intel_gt_park_requests(struct intel_gt *gt);
 void intel_gt_unpark_requests(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index fecfacf551d5..a81e21bf1bd1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -24,6 +24,7 @@
 #include "intel_reset_types.h"
 #include "intel_rc6_types.h"
 #include "intel_rps_types.h"
+#include "intel_migrate_types.h"
 #include "intel_wakeref.h"
 
 struct drm_i915_private;
@@ -31,6 +32,33 @@ struct i915_ggtt;
 struct intel_engine_cs;
 struct intel_uncore;
 
+struct intel_mmio_range {
+	u32 start;
+	u32 end;
+};
+
+/*
+ * The hardware has multiple kinds of multicast register ranges that need
+ * special register steering (and future platforms are expected to add
+ * additional types).
+ *
+ * During driver startup, we initialize the steering control register to
+ * direct reads to a slice/subslice that are valid for the 'subslice' class
+ * of multicast registers.  If another type of steering does not have any
+ * overlap in valid steering targets with 'subslice' style registers, we will
+ * need to explicitly re-steer reads of registers of the other type.
+ *
+ * Only the replication types that may need additional non-default steering
+ * are listed here.
+ */
+enum intel_steering_type {
+	L3BANK,
+	MSLICE,
+	LNCF,
+
+	NUM_STEERING_TYPES
+};
+
 enum intel_submission_method {
 	INTEL_SUBMISSION_RING,
 	INTEL_SUBMISSION_ELSP,
@@ -145,8 +173,15 @@ struct intel_gt {
 
 	struct i915_vma *scratch;
 
+	struct intel_migrate migrate;
+
+	const struct intel_mmio_range *steering_table[NUM_STEERING_TYPES];
+
 	struct intel_gt_info {
 		intel_engine_mask_t engine_mask;
+
+		u32 l3bank_mask;
+
 		u8 num_engines;
 
 		/* Media engine access to SFC per instance */
@@ -154,6 +189,8 @@ struct intel_gt {
 
 		/* Slice/subslice/EU info */
 		struct sseu_dev_info sseu;
+
+		unsigned long mslice_mask;
 	} info;
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 084ea65d59c0..e137dd32b5b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -16,7 +16,19 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz)
 {
 	struct drm_i915_gem_object *obj;
 
-	obj = i915_gem_object_create_lmem(vm->i915, sz, 0);
+	/*
+	 * To avoid severe over-allocation when dealing with min_page_size
+	 * restrictions, we override that behaviour here by allowing an object
+	 * size and page layout which can be smaller. In practice this should be
+	 * totally fine, since GTT paging structures are not typically inserted
+	 * into the GTT.
+	 *
+	 * Note that we also hit this path for the scratch page, and for this
+	 * case it might need to be 64K, but that should work fine here since we
+	 * used the passed in size for the page size, which should ensure it
+	 * also has the same alignment.
+	 */
+	obj = __i915_gem_object_create_lmem_with_ps(vm->i915, sz, sz, 0);
 	/*
 	 * Ensure all paging structures for this vm share the same dma-resv
 	 * object underneath, with the idea that one object_lock() will lock
@@ -414,7 +426,7 @@ static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
 }
 
-static void cnl_setup_private_ppat(struct intel_uncore *uncore)
+static void icl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	intel_uncore_write(uncore,
 			   GEN10_PAT_INDEX(0),
@@ -514,8 +526,8 @@ void setup_private_pat(struct intel_uncore *uncore)
 
 	if (GRAPHICS_VER(i915) >= 12)
 		tgl_setup_private_ppat(uncore);
-	else if (GRAPHICS_VER(i915) >= 10)
-		cnl_setup_private_ppat(uncore);
+	else if (GRAPHICS_VER(i915) >= 11)
+		icl_setup_private_ppat(uncore);
 	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
 		chv_setup_private_ppat(uncore);
 	else
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index edea95b97c36..bc7153018ebd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -140,7 +140,6 @@ typedef u64 gen8_pte_t;
 
 enum i915_cache_level;
 
-struct drm_i915_file_private;
 struct drm_i915_gem_object;
 struct i915_fence_reg;
 struct i915_vma;
@@ -220,16 +219,6 @@ struct i915_address_space {
 	struct intel_gt *gt;
 	struct drm_i915_private *i915;
 	struct device *dma;
-	/*
-	 * Every address space belongs to a struct file - except for the global
-	 * GTT that is owned by the driver (and so @file is set to NULL). In
-	 * principle, no information should leak from one context to another
-	 * (or between files/processes etc) unless explicitly shared by the
-	 * owner. Tracking the owner is important in order to free up per-file
-	 * objects along with the file, to aide resource tracking, and to
-	 * assign blame.
-	 */
-	struct drm_i915_file_private *file;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
 
@@ -296,6 +285,13 @@ struct i915_address_space {
 			       u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
 
+	void (*foreach)(struct i915_address_space *vm,
+			u64 start, u64 length,
+			void (*fn)(struct i915_address_space *vm,
+				   struct i915_page_table *pt,
+				   void *data),
+			void *data);
+
 	struct i915_vma_ops vma_ops;
 
 	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a27bac0a4bfb..bb4af4977920 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -70,7 +70,7 @@ static void set_offsets(u32 *regs,
 	if (close) {
 		/* Close the batch; used mainly by live_lrc_layout() */
 		*regs = MI_BATCH_BUFFER_END;
-		if (GRAPHICS_VER(engine->i915) >= 10)
+		if (GRAPHICS_VER(engine->i915) >= 11)
 			*regs |= BIT(0);
 	}
 }
@@ -484,6 +484,47 @@ static const u8 gen12_rcs_offsets[] = {
 	END
 };
 
+static const u8 xehp_rcs_offsets[] = {
+	NOP(1),
+	LRI(13, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+
+	NOP(5),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	LRI(3, POSTED),
+	REG(0x1b0),
+	REG16(0x5a8),
+	REG16(0x5ac),
+
+	NOP(6),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END
+};
+
 #undef END
 #undef REG16
 #undef REG
@@ -502,7 +543,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		   !intel_engine_has_relative_mmio(engine));
 
 	if (engine->class == RENDER_CLASS) {
-		if (GRAPHICS_VER(engine->i915) >= 12)
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+			return xehp_rcs_offsets;
+		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_rcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 11)
 			return gen11_rcs_offsets;
@@ -522,7 +565,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 
 static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
 {
-	if (GRAPHICS_VER(engine->i915) >= 12)
+	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+		return 0x70;
+	else if (GRAPHICS_VER(engine->i915) >= 12)
 		return 0x60;
 	else if (GRAPHICS_VER(engine->i915) >= 9)
 		return 0x54;
@@ -534,7 +579,9 @@ static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
 
 static int lrc_ring_gpr0(const struct intel_engine_cs *engine)
 {
-	if (GRAPHICS_VER(engine->i915) >= 12)
+	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+		return 0x84;
+	else if (GRAPHICS_VER(engine->i915) >= 12)
 		return 0x74;
 	else if (GRAPHICS_VER(engine->i915) >= 9)
 		return 0x68;
@@ -578,10 +625,16 @@ static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
 
 static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
 {
-	if (engine->class != RENDER_CLASS)
-		return -1;
 
-	if (GRAPHICS_VER(engine->i915) >= 12)
+	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+		/*
+		 * Note that the CSFE context has a dummy slot for CMD_BUF_CCTL
+		 * simply to match the RCS context image layout.
+		 */
+		return 0xc6;
+	else if (engine->class != RENDER_CLASS)
+		return -1;
+	else if (GRAPHICS_VER(engine->i915) >= 12)
 		return 0xb6;
 	else if (GRAPHICS_VER(engine->i915) >= 11)
 		return 0xaa;
@@ -600,8 +653,6 @@ lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 		return GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
 	case 11:
 		return GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-	case 10:
-		return GEN10_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
 	case 9:
 		return GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
 	case 8:
@@ -845,7 +896,7 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	ring = intel_engine_create_ring(engine, (unsigned long)ce->ring);
+	ring = intel_engine_create_ring(engine, ce->ring_size);
 	if (IS_ERR(ring)) {
 		err = PTR_ERR(ring);
 		goto err_vma;
@@ -1101,6 +1152,14 @@ setup_indirect_ctx_bb(const struct intel_context *ce,
  *      bits 55-60:    SW counter
  *      bits 61-63:    engine class
  *
+ * On Xe_HP, the upper dword of the descriptor has a new format:
+ *
+ *      bits 32-37:    virtual function number
+ *      bit 38:        mbz, reserved for use by hardware
+ *      bits 39-54:    SW context ID
+ *      bits 55-57:    reserved
+ *      bits 58-63:    SW counter
+ *
  * engine info, SW context ID and SW counter need to form a unique number
  * (Context ID) per lrc.
  */
@@ -1387,40 +1446,6 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
-static u32 *
-gen10_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
-{
-	int i;
-
-	/*
-	 * WaPipeControlBefore3DStateSamplePattern: cnl
-	 *
-	 * Ensure the engine is idle prior to programming a
-	 * 3DSTATE_SAMPLE_PATTERN during a context restore.
-	 */
-	batch = gen8_emit_pipe_control(batch,
-				       PIPE_CONTROL_CS_STALL,
-				       0);
-	/*
-	 * WaPipeControlBefore3DStateSamplePattern says we need 4 dwords for
-	 * the PIPE_CONTROL followed by 12 dwords of 0x0, so 16 dwords in
-	 * total. However, a PIPE_CONTROL is 6 dwords long, not 4, which is
-	 * confusing. Since gen8_emit_pipe_control() already advances the
-	 * batch by 6 dwords, we advance the other 10 here, completing a
-	 * cacheline. It's not clear if the workaround requires this padding
-	 * before other commands, or if it's just the regular padding we would
-	 * already have for the workaround bb, so leave it here for now.
-	 */
-	for (i = 0; i < 10; i++)
-		*batch++ = MI_NOOP;
-
-	/* Pad to end of cacheline */
-	while ((unsigned long)batch % CACHELINE_BYTES)
-		*batch++ = MI_NOOP;
-
-	return batch;
-}
-
 #define CTX_WA_BB_SIZE (PAGE_SIZE)
 
 static int lrc_create_wa_ctx(struct intel_engine_cs *engine)
@@ -1473,10 +1498,6 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine)
 	case 12:
 	case 11:
 		return;
-	case 10:
-		wa_bb_fn[0] = gen10_init_indirectctx_bb;
-		wa_bb_fn[1] = NULL;
-		break;
 	case 9:
 		wa_bb_fn[0] = gen9_init_indirectctx_bb;
 		wa_bb_fn[1] = NULL;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 41e5350a7a05..f785d0ed238f 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -87,9 +87,10 @@
 #define GEN11_CSB_WRITE_PTR_MASK	(GEN11_CSB_PTR_MASK << 0)
 
 #define MAX_CONTEXT_HW_ID	(1 << 21) /* exclusive */
-#define MAX_GUC_CONTEXT_HW_ID	(1 << 20) /* exclusive */
 #define GEN11_MAX_CONTEXT_HW_ID	(1 << 11) /* exclusive */
 /* in Gen12 ID 0x7FF is reserved to indicate idle */
 #define GEN12_MAX_CONTEXT_HW_ID	(GEN11_MAX_CONTEXT_HW_ID - 1)
+/* in Xe_HP ID 0xFFFF is reserved to indicate "invalid context" */
+#define XEHP_MAX_CONTEXT_HW_ID	0xFFFF
 
 #endif /* _INTEL_LRC_REG_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
new file mode 100644
index 000000000000..1dac21aa7e5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -0,0 +1,688 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_context.h"
+#include "intel_gpu_commands.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+#include "intel_migrate.h"
+#include "intel_ring.h"
+
+struct insert_pte_data {
+	u64 offset;
+	bool is_lmem;
+};
+
+#define CHUNK_SZ SZ_8M /* ~1ms at 8GiB/s preemption delay */
+
+static bool engine_supports_migration(struct intel_engine_cs *engine)
+{
+	if (!engine)
+		return false;
+
+	/*
+	 * We need the ability to prevent aribtration (MI_ARB_ON_OFF),
+	 * the ability to write PTE using inline data (MI_STORE_DATA)
+	 * and of course the ability to do the block transfer (blits).
+	 */
+	GEM_BUG_ON(engine->class != COPY_ENGINE_CLASS);
+
+	return true;
+}
+
+static void insert_pte(struct i915_address_space *vm,
+		       struct i915_page_table *pt,
+		       void *data)
+{
+	struct insert_pte_data *d = data;
+
+	vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE,
+			d->is_lmem ? PTE_LM : 0);
+	d->offset += PAGE_SIZE;
+}
+
+static struct i915_address_space *migrate_vm(struct intel_gt *gt)
+{
+	struct i915_vm_pt_stash stash = {};
+	struct i915_ppgtt *vm;
+	int err;
+	int i;
+
+	/*
+	 * We construct a very special VM for use by all migration contexts,
+	 * it is kept pinned so that it can be used at any time. As we need
+	 * to pre-allocate the page directories for the migration VM, this
+	 * limits us to only using a small number of prepared vma.
+	 *
+	 * To be able to pipeline and reschedule migration operations while
+	 * avoiding unnecessary contention on the vm itself, the PTE updates
+	 * are inline with the blits. All the blits use the same fixed
+	 * addresses, with the backing store redirection being updated on the
+	 * fly. Only 2 implicit vma are used for all migration operations.
+	 *
+	 * We lay the ppGTT out as:
+	 *
+	 *	[0, CHUNK_SZ) -> first object
+	 *	[CHUNK_SZ, 2 * CHUNK_SZ) -> second object
+	 *	[2 * CHUNK_SZ, 2 * CHUNK_SZ + 2 * CHUNK_SZ >> 9] -> PTE
+	 *
+	 * By exposing the dma addresses of the page directories themselves
+	 * within the ppGTT, we are then able to rewrite the PTE prior to use.
+	 * But the PTE update and subsequent migration operation must be atomic,
+	 * i.e. within the same non-preemptible window so that we do not switch
+	 * to another migration context that overwrites the PTE.
+	 *
+	 * TODO: Add support for huge LMEM PTEs
+	 */
+
+	vm = i915_ppgtt_create(gt);
+	if (IS_ERR(vm))
+		return ERR_CAST(vm);
+
+	if (!vm->vm.allocate_va_range || !vm->vm.foreach) {
+		err = -ENODEV;
+		goto err_vm;
+	}
+
+	/*
+	 * Each engine instance is assigned its own chunk in the VM, so
+	 * that we can run multiple instances concurrently
+	 */
+	for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+		struct intel_engine_cs *engine;
+		u64 base = (u64)i << 32;
+		struct insert_pte_data d = {};
+		struct i915_gem_ww_ctx ww;
+		u64 sz;
+
+		engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+		if (!engine_supports_migration(engine))
+			continue;
+
+		/*
+		 * We copy in 8MiB chunks. Each PDE covers 2MiB, so we need
+		 * 4x2 page directories for source/destination.
+		 */
+		sz = 2 * CHUNK_SZ;
+		d.offset = base + sz;
+
+		/*
+		 * We need another page directory setup so that we can write
+		 * the 8x512 PTE in each chunk.
+		 */
+		sz += (sz >> 12) * sizeof(u64);
+
+		err = i915_vm_alloc_pt_stash(&vm->vm, &stash, sz);
+		if (err)
+			goto err_vm;
+
+		for_i915_gem_ww(&ww, err, true) {
+			err = i915_vm_lock_objects(&vm->vm, &ww);
+			if (err)
+				continue;
+			err = i915_vm_map_pt_stash(&vm->vm, &stash);
+			if (err)
+				continue;
+
+			vm->vm.allocate_va_range(&vm->vm, &stash, base, sz);
+		}
+		i915_vm_free_pt_stash(&vm->vm, &stash);
+		if (err)
+			goto err_vm;
+
+		/* Now allow the GPU to rewrite the PTE via its own ppGTT */
+		d.is_lmem = i915_gem_object_is_lmem(vm->vm.scratch[0]);
+		vm->vm.foreach(&vm->vm, base, base + sz, insert_pte, &d);
+	}
+
+	return &vm->vm;
+
+err_vm:
+	i915_vm_put(&vm->vm);
+	return ERR_PTR(err);
+}
+
+static struct intel_engine_cs *first_copy_engine(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+		engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+		if (engine_supports_migration(engine))
+			return engine;
+	}
+
+	return NULL;
+}
+
+static struct intel_context *pinned_context(struct intel_gt *gt)
+{
+	static struct lock_class_key key;
+	struct intel_engine_cs *engine;
+	struct i915_address_space *vm;
+	struct intel_context *ce;
+
+	engine = first_copy_engine(gt);
+	if (!engine)
+		return ERR_PTR(-ENODEV);
+
+	vm = migrate_vm(gt);
+	if (IS_ERR(vm))
+		return ERR_CAST(vm);
+
+	ce = intel_engine_create_pinned_context(engine, vm, SZ_512K,
+						I915_GEM_HWS_MIGRATE,
+						&key, "migrate");
+	i915_vm_put(vm);
+	return ce;
+}
+
+int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt)
+{
+	struct intel_context *ce;
+
+	memset(m, 0, sizeof(*m));
+
+	ce = pinned_context(gt);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	m->context = ce;
+	return 0;
+}
+
+static int random_index(unsigned int max)
+{
+	return upper_32_bits(mul_u32_u32(get_random_u32(), max));
+}
+
+static struct intel_context *__migrate_engines(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engines[MAX_ENGINE_INSTANCE];
+	struct intel_engine_cs *engine;
+	unsigned int count, i;
+
+	count = 0;
+	for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+		engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+		if (engine_supports_migration(engine))
+			engines[count++] = engine;
+	}
+
+	return intel_context_create(engines[random_index(count)]);
+}
+
+struct intel_context *intel_migrate_create_context(struct intel_migrate *m)
+{
+	struct intel_context *ce;
+
+	/*
+	 * We randomly distribute contexts across the engines upon constrction,
+	 * as they all share the same pinned vm, and so in order to allow
+	 * multiple blits to run in parallel, we must construct each blit
+	 * to use a different range of the vm for its GTT. This has to be
+	 * known at construction, so we can not use the late greedy load
+	 * balancing of the virtual-engine.
+	 */
+	ce = __migrate_engines(m->context->engine->gt);
+	if (IS_ERR(ce))
+		return ce;
+
+	ce->ring = NULL;
+	ce->ring_size = SZ_256K;
+
+	i915_vm_put(ce->vm);
+	ce->vm = i915_vm_get(m->context->vm);
+
+	return ce;
+}
+
+static inline struct sgt_dma sg_sgt(struct scatterlist *sg)
+{
+	dma_addr_t addr = sg_dma_address(sg);
+
+	return (struct sgt_dma){ sg, addr, addr + sg_dma_len(sg) };
+}
+
+static int emit_no_arbitration(struct i915_request *rq)
+{
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 2);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/* Explicitly disable preemption for this request. */
+	*cs++ = MI_ARB_ON_OFF;
+	*cs++ = MI_NOOP;
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int emit_pte(struct i915_request *rq,
+		    struct sgt_dma *it,
+		    enum i915_cache_level cache_level,
+		    bool is_lmem,
+		    u64 offset,
+		    int length)
+{
+	const u64 encode = rq->context->vm->pte_encode(0, cache_level,
+						       is_lmem ? PTE_LM : 0);
+	struct intel_ring *ring = rq->ring;
+	int total = 0;
+	u32 *hdr, *cs;
+	int pkt;
+
+	GEM_BUG_ON(GRAPHICS_VER(rq->engine->i915) < 8);
+
+	/* Compute the page directory offset for the target address range */
+	offset += (u64)rq->engine->instance << 32;
+	offset >>= 12;
+	offset *= sizeof(u64);
+	offset += 2 * CHUNK_SZ;
+
+	cs = intel_ring_begin(rq, 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/* Pack as many PTE updates as possible into a single MI command */
+	pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5);
+	pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5);
+
+	hdr = cs;
+	*cs++ = MI_STORE_DATA_IMM | REG_BIT(21); /* as qword elements */
+	*cs++ = lower_32_bits(offset);
+	*cs++ = upper_32_bits(offset);
+
+	do {
+		if (cs - hdr >= pkt) {
+			*hdr += cs - hdr - 2;
+			*cs++ = MI_NOOP;
+
+			ring->emit = (void *)cs - ring->vaddr;
+			intel_ring_advance(rq, cs);
+			intel_ring_update_space(ring);
+
+			cs = intel_ring_begin(rq, 6);
+			if (IS_ERR(cs))
+				return PTR_ERR(cs);
+
+			pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5);
+			pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5);
+
+			hdr = cs;
+			*cs++ = MI_STORE_DATA_IMM | REG_BIT(21);
+			*cs++ = lower_32_bits(offset);
+			*cs++ = upper_32_bits(offset);
+		}
+
+		*cs++ = lower_32_bits(encode | it->dma);
+		*cs++ = upper_32_bits(encode | it->dma);
+
+		offset += 8;
+		total += I915_GTT_PAGE_SIZE;
+
+		it->dma += I915_GTT_PAGE_SIZE;
+		if (it->dma >= it->max) {
+			it->sg = __sg_next(it->sg);
+			if (!it->sg || sg_dma_len(it->sg) == 0)
+				break;
+
+			it->dma = sg_dma_address(it->sg);
+			it->max = it->dma + sg_dma_len(it->sg);
+		}
+	} while (total < length);
+
+	*hdr += cs - hdr - 2;
+	*cs++ = MI_NOOP;
+
+	ring->emit = (void *)cs - ring->vaddr;
+	intel_ring_advance(rq, cs);
+	intel_ring_update_space(ring);
+
+	return total;
+}
+
+static bool wa_1209644611_applies(int ver, u32 size)
+{
+	u32 height = size >> PAGE_SHIFT;
+
+	if (ver != 11)
+		return false;
+
+	return height % 4 == 3 && height <= 8;
+}
+
+static int emit_copy(struct i915_request *rq, int size)
+{
+	const int ver = GRAPHICS_VER(rq->engine->i915);
+	u32 instance = rq->engine->instance;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, ver >= 8 ? 10 : 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	if (ver >= 9 && !wa_1209644611_applies(ver, size)) {
+		*cs++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2);
+		*cs++ = BLT_DEPTH_32 | PAGE_SIZE;
+		*cs++ = 0;
+		*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+		*cs++ = CHUNK_SZ; /* dst offset */
+		*cs++ = instance;
+		*cs++ = 0;
+		*cs++ = PAGE_SIZE;
+		*cs++ = 0; /* src offset */
+		*cs++ = instance;
+	} else if (ver >= 8) {
+		*cs++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2);
+		*cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
+		*cs++ = 0;
+		*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+		*cs++ = CHUNK_SZ; /* dst offset */
+		*cs++ = instance;
+		*cs++ = 0;
+		*cs++ = PAGE_SIZE;
+		*cs++ = 0; /* src offset */
+		*cs++ = instance;
+	} else {
+		GEM_BUG_ON(instance);
+		*cs++ = SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
+		*cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
+		*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE;
+		*cs++ = CHUNK_SZ; /* dst offset */
+		*cs++ = PAGE_SIZE;
+		*cs++ = 0; /* src offset */
+	}
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
+int
+intel_context_migrate_copy(struct intel_context *ce,
+			   struct dma_fence *await,
+			   struct scatterlist *src,
+			   enum i915_cache_level src_cache_level,
+			   bool src_is_lmem,
+			   struct scatterlist *dst,
+			   enum i915_cache_level dst_cache_level,
+			   bool dst_is_lmem,
+			   struct i915_request **out)
+{
+	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
+	struct i915_request *rq;
+	int err;
+
+	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
+	*out = NULL;
+
+	GEM_BUG_ON(ce->ring->size < SZ_64K);
+
+	do {
+		int len;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_ce;
+		}
+
+		if (await) {
+			err = i915_request_await_dma_fence(rq, await);
+			if (err)
+				goto out_rq;
+
+			if (rq->engine->emit_init_breadcrumb) {
+				err = rq->engine->emit_init_breadcrumb(rq);
+				if (err)
+					goto out_rq;
+			}
+
+			await = NULL;
+		}
+
+		/* The PTE updates + copy must not be interrupted. */
+		err = emit_no_arbitration(rq);
+		if (err)
+			goto out_rq;
+
+		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, 0,
+			       CHUNK_SZ);
+		if (len <= 0) {
+			err = len;
+			goto out_rq;
+		}
+
+		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
+			       CHUNK_SZ, len);
+		if (err < 0)
+			goto out_rq;
+		if (err < len) {
+			err = -EINVAL;
+			goto out_rq;
+		}
+
+		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+		if (err)
+			goto out_rq;
+
+		err = emit_copy(rq, len);
+
+		/* Arbitration is re-enabled between requests. */
+out_rq:
+		if (*out)
+			i915_request_put(*out);
+		*out = i915_request_get(rq);
+		i915_request_add(rq);
+		if (err || !it_src.sg || !sg_dma_len(it_src.sg))
+			break;
+
+		cond_resched();
+	} while (1);
+
+out_ce:
+	return err;
+}
+
+static int emit_clear(struct i915_request *rq, int size, u32 value)
+{
+	const int ver = GRAPHICS_VER(rq->engine->i915);
+	u32 instance = rq->engine->instance;
+	u32 *cs;
+
+	GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
+
+	cs = intel_ring_begin(rq, ver >= 8 ? 8 : 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	if (ver >= 8) {
+		*cs++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2);
+		*cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
+		*cs++ = 0;
+		*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+		*cs++ = 0; /* offset */
+		*cs++ = instance;
+		*cs++ = value;
+		*cs++ = MI_NOOP;
+	} else {
+		GEM_BUG_ON(instance);
+		*cs++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
+		*cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
+		*cs++ = 0;
+		*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+		*cs++ = 0;
+		*cs++ = value;
+	}
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
+int
+intel_context_migrate_clear(struct intel_context *ce,
+			    struct dma_fence *await,
+			    struct scatterlist *sg,
+			    enum i915_cache_level cache_level,
+			    bool is_lmem,
+			    u32 value,
+			    struct i915_request **out)
+{
+	struct sgt_dma it = sg_sgt(sg);
+	struct i915_request *rq;
+	int err;
+
+	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
+	*out = NULL;
+
+	GEM_BUG_ON(ce->ring->size < SZ_64K);
+
+	do {
+		int len;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_ce;
+		}
+
+		if (await) {
+			err = i915_request_await_dma_fence(rq, await);
+			if (err)
+				goto out_rq;
+
+			if (rq->engine->emit_init_breadcrumb) {
+				err = rq->engine->emit_init_breadcrumb(rq);
+				if (err)
+					goto out_rq;
+			}
+
+			await = NULL;
+		}
+
+		/* The PTE updates + clear must not be interrupted. */
+		err = emit_no_arbitration(rq);
+		if (err)
+			goto out_rq;
+
+		len = emit_pte(rq, &it, cache_level, is_lmem, 0, CHUNK_SZ);
+		if (len <= 0) {
+			err = len;
+			goto out_rq;
+		}
+
+		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+		if (err)
+			goto out_rq;
+
+		err = emit_clear(rq, len, value);
+
+		/* Arbitration is re-enabled between requests. */
+out_rq:
+		if (*out)
+			i915_request_put(*out);
+		*out = i915_request_get(rq);
+		i915_request_add(rq);
+		if (err || !it.sg || !sg_dma_len(it.sg))
+			break;
+
+		cond_resched();
+	} while (1);
+
+out_ce:
+	return err;
+}
+
+int intel_migrate_copy(struct intel_migrate *m,
+		       struct i915_gem_ww_ctx *ww,
+		       struct dma_fence *await,
+		       struct scatterlist *src,
+		       enum i915_cache_level src_cache_level,
+		       bool src_is_lmem,
+		       struct scatterlist *dst,
+		       enum i915_cache_level dst_cache_level,
+		       bool dst_is_lmem,
+		       struct i915_request **out)
+{
+	struct intel_context *ce;
+	int err;
+
+	*out = NULL;
+	if (!m->context)
+		return -ENODEV;
+
+	ce = intel_migrate_create_context(m);
+	if (IS_ERR(ce))
+		ce = intel_context_get(m->context);
+	GEM_BUG_ON(IS_ERR(ce));
+
+	err = intel_context_pin_ww(ce, ww);
+	if (err)
+		goto out;
+
+	err = intel_context_migrate_copy(ce, await,
+					 src, src_cache_level, src_is_lmem,
+					 dst, dst_cache_level, dst_is_lmem,
+					 out);
+
+	intel_context_unpin(ce);
+out:
+	intel_context_put(ce);
+	return err;
+}
+
+int
+intel_migrate_clear(struct intel_migrate *m,
+		    struct i915_gem_ww_ctx *ww,
+		    struct dma_fence *await,
+		    struct scatterlist *sg,
+		    enum i915_cache_level cache_level,
+		    bool is_lmem,
+		    u32 value,
+		    struct i915_request **out)
+{
+	struct intel_context *ce;
+	int err;
+
+	*out = NULL;
+	if (!m->context)
+		return -ENODEV;
+
+	ce = intel_migrate_create_context(m);
+	if (IS_ERR(ce))
+		ce = intel_context_get(m->context);
+	GEM_BUG_ON(IS_ERR(ce));
+
+	err = intel_context_pin_ww(ce, ww);
+	if (err)
+		goto out;
+
+	err = intel_context_migrate_clear(ce, await, sg, cache_level,
+					  is_lmem, value, out);
+
+	intel_context_unpin(ce);
+out:
+	intel_context_put(ce);
+	return err;
+}
+
+void intel_migrate_fini(struct intel_migrate *m)
+{
+	struct intel_context *ce;
+
+	ce = fetch_and_zero(&m->context);
+	if (!ce)
+		return;
+
+	intel_engine_destroy_pinned_context(ce);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_migrate.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.h b/drivers/gpu/drm/i915/gt/intel_migrate.h
new file mode 100644
index 000000000000..4e18e755a00b
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_MIGRATE__
+#define __INTEL_MIGRATE__
+
+#include <linux/types.h>
+
+#include "intel_migrate_types.h"
+
+struct dma_fence;
+struct i915_request;
+struct i915_gem_ww_ctx;
+struct intel_gt;
+struct scatterlist;
+enum i915_cache_level;
+
+int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt);
+
+struct intel_context *intel_migrate_create_context(struct intel_migrate *m);
+
+int intel_migrate_copy(struct intel_migrate *m,
+		       struct i915_gem_ww_ctx *ww,
+		       struct dma_fence *await,
+		       struct scatterlist *src,
+		       enum i915_cache_level src_cache_level,
+		       bool src_is_lmem,
+		       struct scatterlist *dst,
+		       enum i915_cache_level dst_cache_level,
+		       bool dst_is_lmem,
+		       struct i915_request **out);
+
+int intel_context_migrate_copy(struct intel_context *ce,
+			       struct dma_fence *await,
+			       struct scatterlist *src,
+			       enum i915_cache_level src_cache_level,
+			       bool src_is_lmem,
+			       struct scatterlist *dst,
+			       enum i915_cache_level dst_cache_level,
+			       bool dst_is_lmem,
+			       struct i915_request **out);
+
+int
+intel_migrate_clear(struct intel_migrate *m,
+		    struct i915_gem_ww_ctx *ww,
+		    struct dma_fence *await,
+		    struct scatterlist *sg,
+		    enum i915_cache_level cache_level,
+		    bool is_lmem,
+		    u32 value,
+		    struct i915_request **out);
+int
+intel_context_migrate_clear(struct intel_context *ce,
+			    struct dma_fence *await,
+			    struct scatterlist *sg,
+			    enum i915_cache_level cache_level,
+			    bool is_lmem,
+			    u32 value,
+			    struct i915_request **out);
+
+void intel_migrate_fini(struct intel_migrate *m);
+
+#endif /* __INTEL_MIGRATE__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate_types.h b/drivers/gpu/drm/i915/gt/intel_migrate_types.h
new file mode 100644
index 000000000000..d98230597f42
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_migrate_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_MIGRATE_TYPES__
+#define __INTEL_MIGRATE_TYPES__
+
+struct intel_context;
+
+struct intel_migrate {
+	struct intel_context *context;
+};
+
+#endif /* __INTEL_MIGRATE_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 17848807f111..582c4423b95d 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -352,7 +352,7 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
 		table->size  = ARRAY_SIZE(icl_mocs_table);
 		table->table = icl_mocs_table;
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
-	} else if (IS_GEN9_BC(i915) || IS_CANNONLAKE(i915)) {
+	} else if (IS_GEN9_BC(i915)) {
 		table->size  = ARRAY_SIZE(skl_mocs_table);
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
 		table->table = skl_mocs_table;
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 259d7eb4e165..799d382eea79 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -62,20 +62,25 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	u32 pg_enable;
 	int i;
 
-	/* 2b: Program RC6 thresholds.*/
-	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
-	set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
+	/*
+	 * With GuCRC, these parameters are set by GuC
+	 */
+	if (!intel_uc_uses_guc_rc(&gt->uc)) {
+		/* 2b: Program RC6 thresholds.*/
+		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
+		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
 
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+		set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+		set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+		for_each_engine(engine, rc6_to_gt(rc6), id)
+			set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
-	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
+		set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
 
-	set(uncore, GEN6_RC_SLEEP, 0);
+		set(uncore, GEN6_RC_SLEEP, 0);
 
-	set(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+		set(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+	}
 
 	/*
 	 * 2c: Program Coarse Power Gating Policies.
@@ -98,11 +103,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
 	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);
 
-	/* 3a: Enable RC6 */
-	rc6->ctl_enable =
-		GEN6_RC_CTL_HW_ENABLE |
-		GEN6_RC_CTL_RC6_ENABLE |
-		GEN6_RC_CTL_EI_MODE(1);
+	/* 3a: Enable RC6
+	 *
+	 * With GuCRC, we do not enable bit 31 of RC_CTL,
+	 * thus allowing GuC to control RC6 entry/exit fully instead.
+	 * We will not set the HW ENABLE and EI bits
+	 */
+	if (!intel_guc_rc_enable(&gt->uc.guc))
+		rc6->ctl_enable = GEN6_RC_CTL_RC6_ENABLE;
+	else
+		rc6->ctl_enable =
+			GEN6_RC_CTL_HW_ENABLE |
+			GEN6_RC_CTL_RC6_ENABLE |
+			GEN6_RC_CTL_EI_MODE(1);
 
 	pg_enable =
 		GEN9_RENDER_PG_ENABLE |
@@ -126,7 +139,7 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	enum intel_engine_id id;
 
 	/* 2b: Program RC6 thresholds.*/
-	if (GRAPHICS_VER(rc6_to_i915(rc6)) >= 10) {
+	if (GRAPHICS_VER(rc6_to_i915(rc6)) >= 11) {
 		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
 		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
 	} else if (IS_SKYLAKE(rc6_to_i915(rc6))) {
@@ -513,6 +526,10 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6)
 {
 	struct drm_i915_private *i915 = rc6_to_i915(rc6);
 	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_gt *gt = rc6_to_gt(rc6);
+
+	/* Take control of RC6 back from GuC */
+	intel_guc_rc_disable(&gt->uc.guc);
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 	if (GRAPHICS_VER(i915) >= 9)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index f7366b054f8e..a74b72f50cc9 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -9,7 +9,8 @@
 #include "intel_region_ttm.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
-#include "intel_region_lmem.h"
+#include "gem/i915_gem_ttm.h"
+#include "gt/intel_gt.h"
 
 static int init_fake_lmem_bar(struct intel_memory_region *mem)
 {
@@ -107,7 +108,7 @@ out_no_io:
 static const struct intel_memory_region_ops intel_region_lmem_ops = {
 	.init = region_lmem_init,
 	.release = region_lmem_release,
-	.init_object = __i915_gem_lmem_object_init,
+	.init_object = __i915_gem_ttm_object_init,
 };
 
 struct intel_memory_region *
@@ -157,7 +158,7 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt)
 static bool get_legacy_lowmem_region(struct intel_uncore *uncore,
 				     u64 *start, u32 *size)
 {
-	if (!IS_DG1_REVID(uncore->i915, DG1_REVID_A0, DG1_REVID_B0))
+	if (!IS_DG1_GT_STEP(uncore->i915, STEP_A0, STEP_C0))
 		return false;
 
 	*start = 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.h b/drivers/gpu/drm/i915/gt/intel_renderstate.h
index 48f009203917..4da4c5234ef0 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.h
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.h
@@ -8,6 +8,7 @@
 
 #include <linux/types.h>
 #include "i915_gem.h"
+#include "i915_gem_ww.h"
 
 struct i915_request;
 struct intel_context;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 72251638d4ea..91200c43951f 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -22,7 +22,6 @@
 #include "intel_reset.h"
 
 #include "uc/intel_guc.h"
-#include "uc/intel_guc_submission.h"
 
 #define RESET_MAX_RETRIES 3
 
@@ -39,21 +38,6 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 	intel_uncore_rmw_fw(uncore, reg, clr, 0);
 }
 
-static void skip_context(struct i915_request *rq)
-{
-	struct intel_context *hung_ctx = rq->context;
-
-	list_for_each_entry_from_rcu(rq, &hung_ctx->timeline->requests, link) {
-		if (!i915_request_is_active(rq))
-			return;
-
-		if (rq->context == hung_ctx) {
-			i915_request_set_error_once(rq, -EIO);
-			__i915_request_skip(rq);
-		}
-	}
-}
-
 static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
 {
 	struct drm_i915_file_private *file_priv = ctx->file_priv;
@@ -88,10 +72,8 @@ static bool mark_guilty(struct i915_request *rq)
 	bool banned;
 	int i;
 
-	if (intel_context_is_closed(rq->context)) {
-		intel_context_set_banned(rq->context);
+	if (intel_context_is_closed(rq->context))
 		return true;
-	}
 
 	rcu_read_lock();
 	ctx = rcu_dereference(rq->context->gem_context);
@@ -123,11 +105,9 @@ static bool mark_guilty(struct i915_request *rq)
 	banned = !i915_gem_context_is_recoverable(ctx);
 	if (time_before(jiffies, prev_hang + CONTEXT_FAST_HANG_JIFFIES))
 		banned = true;
-	if (banned) {
+	if (banned)
 		drm_dbg(&ctx->i915->drm, "context %s: guilty %d, banned\n",
 			ctx->name, atomic_read(&ctx->guilty_count));
-		intel_context_set_banned(rq->context);
-	}
 
 	client_mark_guilty(ctx, banned);
 
@@ -149,6 +129,8 @@ static void mark_innocent(struct i915_request *rq)
 
 void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
+	bool banned = false;
+
 	RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
 	GEM_BUG_ON(__i915_request_is_complete(rq));
 
@@ -156,13 +138,15 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 	if (guilty) {
 		i915_request_set_error_once(rq, -EIO);
 		__i915_request_skip(rq);
-		if (mark_guilty(rq))
-			skip_context(rq);
+		banned = mark_guilty(rq);
 	} else {
 		i915_request_set_error_once(rq, -EAGAIN);
 		mark_innocent(rq);
 	}
 	rcu_read_unlock();
+
+	if (banned)
+		intel_context_ban(rq->context, rq);
 }
 
 static bool i915_in_reset(struct pci_dev *pdev)
@@ -515,8 +499,14 @@ static int gen11_reset_engines(struct intel_gt *gt,
 		[VCS1]  = GEN11_GRDOM_MEDIA2,
 		[VCS2]  = GEN11_GRDOM_MEDIA3,
 		[VCS3]  = GEN11_GRDOM_MEDIA4,
+		[VCS4]  = GEN11_GRDOM_MEDIA5,
+		[VCS5]  = GEN11_GRDOM_MEDIA6,
+		[VCS6]  = GEN11_GRDOM_MEDIA7,
+		[VCS7]  = GEN11_GRDOM_MEDIA8,
 		[VECS0] = GEN11_GRDOM_VECS,
 		[VECS1] = GEN11_GRDOM_VECS2,
+		[VECS2] = GEN11_GRDOM_VECS3,
+		[VECS3] = GEN11_GRDOM_VECS4,
 	};
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
@@ -826,6 +816,8 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
 	local_bh_enable();
 
+	intel_uc_reset(&gt->uc, true);
+
 	intel_ggtt_restore_fences(gt->ggtt);
 
 	return err;
@@ -850,6 +842,8 @@ static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
 		if (awake & engine->mask)
 			intel_engine_pm_put(engine);
 	}
+
+	intel_uc_reset_finish(&gt->uc);
 }
 
 static void nop_submit_request(struct i915_request *request)
@@ -903,6 +897,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	for_each_engine(engine, gt, id)
 		if (engine->reset.cancel)
 			engine->reset.cancel(engine);
+	intel_uc_cancel_requests(&gt->uc);
 	local_bh_enable();
 
 	reset_finish(gt, awake);
@@ -1191,6 +1186,9 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 	ENGINE_TRACE(engine, "flags=%lx\n", gt->reset.flags);
 	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags));
 
+	if (intel_engine_uses_guc(engine))
+		return -ENODEV;
+
 	if (!intel_engine_pm_get_if_awake(engine))
 		return 0;
 
@@ -1201,13 +1199,10 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 			   "Resetting %s for %s\n", engine->name, msg);
 	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
-	if (intel_engine_uses_guc(engine))
-		ret = intel_guc_reset_engine(&engine->gt->uc.guc, engine);
-	else
-		ret = intel_gt_reset_engine(engine);
+	ret = intel_gt_reset_engine(engine);
 	if (ret) {
 		/* If we fail here, we expect to fallback to a global reset */
-		ENGINE_TRACE(engine, "Failed to reset, err: %d\n", ret);
+		ENGINE_TRACE(engine, "Failed to reset %s, err: %d\n", engine->name, ret);
 		goto out;
 	}
 
@@ -1341,7 +1336,8 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * Try engine reset when available. We fall back to full reset if
 	 * single reset fails.
 	 */
-	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
+	if (!intel_uc_uses_guc_submission(&gt->uc) &&
+	    intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
 		local_bh_disable();
 		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index dbf5f14a136f..1b32dadfb8c3 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -49,6 +49,7 @@ static inline void intel_ring_advance(struct i915_request *rq, u32 *cs)
 	 * intel_ring_begin()).
 	 */
 	GEM_BUG_ON((rq->ring->vaddr + rq->ring->emit) != cs);
+	GEM_BUG_ON(!IS_ALIGNED(rq->ring->emit, 8)); /* RING_TAIL qword align */
 }
 
 static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 37d74d4ed59b..2958e2fae380 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -16,6 +16,7 @@
 #include "intel_reset.h"
 #include "intel_ring.h"
 #include "shmem_utils.h"
+#include "intel_engine_heartbeat.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -342,9 +343,9 @@ static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 	u32 head;
 
 	rq = NULL;
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 	rcu_read_lock();
-	list_for_each_entry(pos, &engine->active.requests, sched.link) {
+	list_for_each_entry(pos, &engine->sched_engine->requests, sched.link) {
 		if (!__i915_request_is_complete(pos)) {
 			rq = pos;
 			break;
@@ -399,7 +400,7 @@ static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 	}
 	engine->legacy.ring->head = intel_ring_wrap(engine->legacy.ring, head);
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 static void reset_finish(struct intel_engine_cs *engine)
@@ -411,16 +412,16 @@ static void reset_cancel(struct intel_engine_cs *engine)
 	struct i915_request *request;
 	unsigned long flags;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	/* Mark all submitted requests as skipped. */
-	list_for_each_entry(request, &engine->active.requests, sched.link)
+	list_for_each_entry(request, &engine->sched_engine->requests, sched.link)
 		i915_request_put(i915_request_mark_eio(request));
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 static void i9xx_submit_request(struct i915_request *request)
@@ -586,9 +587,44 @@ static void ring_context_reset(struct intel_context *ce)
 	clear_bit(CONTEXT_VALID_BIT, &ce->flags);
 }
 
+static void ring_context_ban(struct intel_context *ce,
+			     struct i915_request *rq)
+{
+	struct intel_engine_cs *engine;
+
+	if (!rq || !i915_request_is_active(rq))
+		return;
+
+	engine = rq->engine;
+	lockdep_assert_held(&engine->sched_engine->lock);
+	list_for_each_entry_continue(rq, &engine->sched_engine->requests,
+				     sched.link)
+		if (rq->context == ce) {
+			i915_request_set_error_once(rq, -EIO);
+			__i915_request_skip(rq);
+		}
+}
+
+static void ring_context_cancel_request(struct intel_context *ce,
+					struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = NULL;
+
+	i915_request_active_engine(rq, &engine);
+
+	if (engine && intel_engine_pulse(engine))
+		intel_gt_handle_error(engine->gt, engine->mask, 0,
+				      "request cancellation by %s",
+				      current->comm);
+}
+
 static const struct intel_context_ops ring_context_ops = {
 	.alloc = ring_context_alloc,
 
+	.cancel_request = ring_context_cancel_request,
+
+	.ban = ring_context_ban,
+
 	.pre_pin = ring_context_pre_pin,
 	.pin = ring_context_pin,
 	.unpin = ring_context_unpin,
@@ -1047,6 +1083,25 @@ static void setup_irq(struct intel_engine_cs *engine)
 	}
 }
 
+static void add_to_engine(struct i915_request *rq)
+{
+	lockdep_assert_held(&rq->engine->sched_engine->lock);
+	list_move_tail(&rq->sched.link, &rq->engine->sched_engine->requests);
+}
+
+static void remove_from_engine(struct i915_request *rq)
+{
+	spin_lock_irq(&rq->engine->sched_engine->lock);
+	list_del_init(&rq->sched.link);
+
+	/* Prevent further __await_execution() registering a cb, then flush */
+	set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
+
+	spin_unlock_irq(&rq->engine->sched_engine->lock);
+
+	i915_request_notify_execute_cb_imm(rq);
+}
+
 static void setup_common(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
@@ -1064,6 +1119,9 @@ static void setup_common(struct intel_engine_cs *engine)
 	engine->reset.cancel = reset_cancel;
 	engine->reset.finish = reset_finish;
 
+	engine->add_active_request = add_to_engine;
+	engine->remove_active_request = remove_from_engine;
+
 	engine->cops = &ring_context_ops;
 	engine->request_alloc = ring_request_alloc;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 06e9a8ed4e03..d812b27835f8 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -37,6 +37,20 @@ static struct intel_uncore *rps_to_uncore(struct intel_rps *rps)
 	return rps_to_gt(rps)->uncore;
 }
 
+static struct intel_guc_slpc *rps_to_slpc(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	return &gt->uc.guc.slpc;
+}
+
+static bool rps_uses_slpc(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	return intel_uc_uses_guc_slpc(&gt->uc);
+}
+
 static u32 rps_pm_sanitize_mask(struct intel_rps *rps, u32 mask)
 {
 	return mask & ~rps->pm_intrmsk_mbz;
@@ -167,6 +181,8 @@ static void rps_enable_interrupts(struct intel_rps *rps)
 {
 	struct intel_gt *gt = rps_to_gt(rps);
 
+	GEM_BUG_ON(rps_uses_slpc(rps));
+
 	GT_TRACE(gt, "interrupts:on rps->pm_events: %x, rps_pm_mask:%x\n",
 		 rps->pm_events, rps_pm_mask(rps, rps->last_freq));
 
@@ -771,6 +787,8 @@ static int gen6_rps_set(struct intel_rps *rps, u8 val)
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	u32 swreq;
 
+	GEM_BUG_ON(rps_uses_slpc(rps));
+
 	if (GRAPHICS_VER(i915) >= 9)
 		swreq = GEN9_FREQUENCY(val);
 	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
@@ -861,6 +879,9 @@ void intel_rps_park(struct intel_rps *rps)
 {
 	int adj;
 
+	if (!intel_rps_is_enabled(rps))
+		return;
+
 	GEM_BUG_ON(atomic_read(&rps->num_waiters));
 
 	if (!intel_rps_clear_active(rps))
@@ -999,7 +1020,7 @@ static void gen6_rps_init(struct intel_rps *rps)
 
 	rps->efficient_freq = rps->rp1_freq;
 	if (IS_HASWELL(i915) || IS_BROADWELL(i915) ||
-	    IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 10) {
+	    IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
 		u32 ddcc_status = 0;
 
 		if (sandybridge_pcode_read(i915,
@@ -1012,7 +1033,7 @@ static void gen6_rps_init(struct intel_rps *rps)
 					rps->max_freq);
 	}
 
-	if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 10) {
+	if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
 		/* Store the frequency values in 16.66 MHZ units, which is
 		 * the natural hardware unit for SKL
 		 */
@@ -1356,6 +1377,9 @@ void intel_rps_enable(struct intel_rps *rps)
 	if (!HAS_RPS(i915))
 		return;
 
+	if (rps_uses_slpc(rps))
+		return;
+
 	intel_gt_check_clock_frequency(rps_to_gt(rps));
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
@@ -1829,6 +1853,9 @@ void intel_rps_init(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 
+	if (rps_uses_slpc(rps))
+		return;
+
 	if (IS_CHERRYVIEW(i915))
 		chv_rps_init(rps);
 	else if (IS_VALLEYVIEW(i915))
@@ -1877,10 +1904,17 @@ void intel_rps_init(struct intel_rps *rps)
 
 	if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) < 11)
 		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
+
+	/* GuC needs ARAT expired interrupt unmasked */
+	if (intel_uc_uses_guc_submission(&rps_to_gt(rps)->uc))
+		rps->pm_intrmsk_mbz |= ARAT_EXPIRED_INTRMSK;
 }
 
 void intel_rps_sanitize(struct intel_rps *rps)
 {
+	if (rps_uses_slpc(rps))
+		return;
+
 	if (GRAPHICS_VER(rps_to_i915(rps)) >= 6)
 		rps_disable_interrupts(rps);
 }
@@ -1936,6 +1970,176 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 	return freq;
 }
 
+u32 intel_rps_read_punit_req(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	return intel_uncore_read(uncore, GEN6_RPNSWREQ);
+}
+
+static u32 intel_rps_get_req(u32 pureq)
+{
+	u32 req = pureq >> GEN9_SW_REQ_UNSLICE_RATIO_SHIFT;
+
+	return req;
+}
+
+u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps)
+{
+	u32 freq = intel_rps_get_req(intel_rps_read_punit_req(rps));
+
+	return intel_gpu_freq(rps, freq);
+}
+
+u32 intel_rps_get_requested_frequency(struct intel_rps *rps)
+{
+	if (rps_uses_slpc(rps))
+		return intel_rps_read_punit_req_frequency(rps);
+	else
+		return intel_gpu_freq(rps, rps->cur_freq);
+}
+
+u32 intel_rps_get_max_frequency(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return slpc->max_freq_softlimit;
+	else
+		return intel_gpu_freq(rps, rps->max_freq_softlimit);
+}
+
+u32 intel_rps_get_rp0_frequency(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return slpc->rp0_freq;
+	else
+		return intel_gpu_freq(rps, rps->rp0_freq);
+}
+
+u32 intel_rps_get_rp1_frequency(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return slpc->rp1_freq;
+	else
+		return intel_gpu_freq(rps, rps->rp1_freq);
+}
+
+u32 intel_rps_get_rpn_frequency(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return slpc->min_freq;
+	else
+		return intel_gpu_freq(rps, rps->min_freq);
+}
+
+static int set_max_freq(struct intel_rps *rps, u32 val)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	int ret = 0;
+
+	mutex_lock(&rps->lock);
+
+	val = intel_freq_opcode(rps, val);
+	if (val < rps->min_freq ||
+	    val > rps->max_freq ||
+	    val < rps->min_freq_softlimit) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (val > rps->rp0_freq)
+		drm_dbg(&i915->drm, "User requested overclocking to %d\n",
+			intel_gpu_freq(rps, val));
+
+	rps->max_freq_softlimit = val;
+
+	val = clamp_t(int, rps->cur_freq,
+		      rps->min_freq_softlimit,
+		      rps->max_freq_softlimit);
+
+	/*
+	 * We still need *_set_rps to process the new max_delay and
+	 * update the interrupt limits and PMINTRMSK even though
+	 * frequency request may be unchanged.
+	 */
+	intel_rps_set(rps, val);
+
+unlock:
+	mutex_unlock(&rps->lock);
+
+	return ret;
+}
+
+int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return intel_guc_slpc_set_max_freq(slpc, val);
+	else
+		return set_max_freq(rps, val);
+}
+
+u32 intel_rps_get_min_frequency(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return slpc->min_freq_softlimit;
+	else
+		return intel_gpu_freq(rps, rps->min_freq_softlimit);
+}
+
+static int set_min_freq(struct intel_rps *rps, u32 val)
+{
+	int ret = 0;
+
+	mutex_lock(&rps->lock);
+
+	val = intel_freq_opcode(rps, val);
+	if (val < rps->min_freq ||
+	    val > rps->max_freq ||
+	    val > rps->max_freq_softlimit) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	rps->min_freq_softlimit = val;
+
+	val = clamp_t(int, rps->cur_freq,
+		      rps->min_freq_softlimit,
+		      rps->max_freq_softlimit);
+
+	/*
+	 * We still need *_set_rps to process the new min_delay and
+	 * update the interrupt limits and PMINTRMSK even though
+	 * frequency request may be unchanged.
+	 */
+	intel_rps_set(rps, val);
+
+unlock:
+	mutex_unlock(&rps->lock);
+
+	return ret;
+}
+
+int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+
+	if (rps_uses_slpc(rps))
+		return intel_guc_slpc_set_min_freq(slpc, val);
+	else
+		return set_min_freq(rps, val);
+}
+
 /* External interface for intel_ips.ko */
 
 static struct drm_i915_private __rcu *ips_mchdev;
@@ -2129,4 +2333,5 @@ EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_rps.c"
+#include "selftest_slpc.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 1d2cfc98b510..4213bcce1667 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -31,6 +31,16 @@ int intel_gpu_freq(struct intel_rps *rps, int val);
 int intel_freq_opcode(struct intel_rps *rps, int val);
 u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1);
 u32 intel_rps_read_actual_frequency(struct intel_rps *rps);
+u32 intel_rps_get_requested_frequency(struct intel_rps *rps);
+u32 intel_rps_get_min_frequency(struct intel_rps *rps);
+int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val);
+u32 intel_rps_get_max_frequency(struct intel_rps *rps);
+int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val);
+u32 intel_rps_get_rp0_frequency(struct intel_rps *rps);
+u32 intel_rps_get_rp1_frequency(struct intel_rps *rps);
+u32 intel_rps_get_rpn_frequency(struct intel_rps *rps);
+u32 intel_rps_read_punit_req(struct intel_rps *rps);
+u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps);
 
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 367fd44b81c8..bbd272943c3f 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -139,17 +139,36 @@ static void gen12_sseu_info_init(struct intel_gt *gt)
 	 * Gen12 has Dual-Subslices, which behave similarly to 2 gen11 SS.
 	 * Instead of splitting these, provide userspace with an array
 	 * of DSS to more closely represent the hardware resource.
+	 *
+	 * In addition, the concept of slice has been removed in Xe_HP.
+	 * To be compatible with prior generations, assume a single slice
+	 * across the entire device. Then calculate out the DSS for each
+	 * workload type within that software slice.
 	 */
-	intel_sseu_set_info(sseu, 1, 6, 16);
+	if (IS_DG2(gt->i915) || IS_XEHPSDV(gt->i915))
+		intel_sseu_set_info(sseu, 1, 32, 16);
+	else
+		intel_sseu_set_info(sseu, 1, 6, 16);
 
-	s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
-		GEN11_GT_S_ENA_MASK;
+	/*
+	 * As mentioned above, Xe_HP does not have the concept of a slice.
+	 * Enable one for software backwards compatibility.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+		s_en = 0x1;
+	else
+		s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
+		       GEN11_GT_S_ENA_MASK;
 
 	dss_en = intel_uncore_read(uncore, GEN12_GT_DSS_ENABLE);
 
 	/* one bit per pair of EUs */
-	eu_en_fuse = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
-		       GEN11_EU_DIS_MASK);
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+		eu_en_fuse = intel_uncore_read(uncore, XEHP_EU_ENABLE) & XEHP_EU_ENA_MASK;
+	else
+		eu_en_fuse = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
+			       GEN11_EU_DIS_MASK);
+
 	for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
 		if (eu_en_fuse & BIT(eu))
 			eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
@@ -188,83 +207,6 @@ static void gen11_sseu_info_init(struct intel_gt *gt)
 	sseu->has_eu_pg = 1;
 }
 
-static void gen10_sseu_info_init(struct intel_gt *gt)
-{
-	struct intel_uncore *uncore = gt->uncore;
-	struct sseu_dev_info *sseu = &gt->info.sseu;
-	const u32 fuse2 = intel_uncore_read(uncore, GEN8_FUSE2);
-	const int eu_mask = 0xff;
-	u32 subslice_mask, eu_en;
-	int s, ss;
-
-	intel_sseu_set_info(sseu, 6, 4, 8);
-
-	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
-		GEN10_F2_S_ENA_SHIFT;
-
-	/* Slice0 */
-	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE0);
-	for (ss = 0; ss < sseu->max_subslices; ss++)
-		sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) & eu_mask);
-	/* Slice1 */
-	sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
-	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE1);
-	sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
-	/* Slice2 */
-	sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
-	/* Slice3 */
-	sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
-	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE2);
-	sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
-	/* Slice4 */
-	sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
-	/* Slice5 */
-	sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
-	eu_en = ~intel_uncore_read(uncore, GEN10_EU_DISABLE3);
-	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
-
-	subslice_mask = (1 << 4) - 1;
-	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
-			   GEN10_F2_SS_DIS_SHIFT);
-
-	for (s = 0; s < sseu->max_slices; s++) {
-		u32 subslice_mask_with_eus = subslice_mask;
-
-		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			if (sseu_get_eus(sseu, s, ss) == 0)
-				subslice_mask_with_eus &= ~BIT(ss);
-		}
-
-		/*
-		 * Slice0 can have up to 3 subslices, but there are only 2 in
-		 * slice1/2.
-		 */
-		intel_sseu_set_subslices(sseu, s, s == 0 ?
-					 subslice_mask_with_eus :
-					 subslice_mask_with_eus & 0x3);
-	}
-
-	sseu->eu_total = compute_eu_total(sseu);
-
-	/*
-	 * CNL is expected to always have a uniform distribution
-	 * of EU across subslices with the exception that any one
-	 * EU in any one subslice may be fused off for die
-	 * recovery.
-	 */
-	sseu->eu_per_subslice =
-		intel_sseu_subslice_total(sseu) ?
-		DIV_ROUND_UP(sseu->eu_total, intel_sseu_subslice_total(sseu)) :
-		0;
-
-	/* No restrictions on Power Gating */
-	sseu->has_slice_pg = 1;
-	sseu->has_subslice_pg = 1;
-	sseu->has_eu_pg = 1;
-}
-
 static void cherryview_sseu_info_init(struct intel_gt *gt)
 {
 	struct sseu_dev_info *sseu = &gt->info.sseu;
@@ -592,8 +534,6 @@ void intel_sseu_info_init(struct intel_gt *gt)
 		bdw_sseu_info_init(gt);
 	else if (GRAPHICS_VER(i915) == 9)
 		gen9_sseu_info_init(gt);
-	else if (GRAPHICS_VER(i915) == 10)
-		gen10_sseu_info_init(gt);
 	else if (GRAPHICS_VER(i915) == 11)
 		gen11_sseu_info_init(gt);
 	else if (GRAPHICS_VER(i915) >= 12)
@@ -759,3 +699,21 @@ void intel_sseu_print_topology(const struct sseu_dev_info *sseu,
 		}
 	}
 }
+
+u16 intel_slicemask_from_dssmask(u64 dss_mask, int dss_per_slice)
+{
+	u16 slice_mask = 0;
+	int i;
+
+	WARN_ON(sizeof(dss_mask) * 8 / dss_per_slice > 8 * sizeof(slice_mask));
+
+	for (i = 0; dss_mask; i++) {
+		if (dss_mask & GENMASK(dss_per_slice - 1, 0))
+			slice_mask |= BIT(i);
+
+		dss_mask >>= dss_per_slice;
+	}
+
+	return slice_mask;
+}
+
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 4cd1a8a7298a..22fef98887c0 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -15,13 +15,17 @@ struct drm_i915_private;
 struct intel_gt;
 struct drm_printer;
 
-#define GEN_MAX_SLICES		(6) /* CNL upper bound */
-#define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
+#define GEN_MAX_SLICES		(3) /* SKL upper bound */
+#define GEN_MAX_SUBSLICES	(32) /* XEHPSDV upper bound */
 #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
 #define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
 #define GEN_MAX_EUS		(16) /* TGL upper bound */
 #define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
 
+#define GEN_DSS_PER_GSLICE	4
+#define GEN_DSS_PER_CSLICE	8
+#define GEN_DSS_PER_MSLICE	8
+
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
@@ -104,4 +108,6 @@ void intel_sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p);
 void intel_sseu_print_topology(const struct sseu_dev_info *sseu,
 			       struct drm_printer *p);
 
+u16 intel_slicemask_from_dssmask(u64 dss_mask, int dss_per_slice);
+
 #endif /* __INTEL_SSEU_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
index 714fe8495775..1ba8b7da9d37 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
@@ -50,10 +50,10 @@ static void cherryview_sseu_device_status(struct intel_gt *gt,
 #undef SS_MAX
 }
 
-static void gen10_sseu_device_status(struct intel_gt *gt,
+static void gen11_sseu_device_status(struct intel_gt *gt,
 				     struct sseu_dev_info *sseu)
 {
-#define SS_MAX 6
+#define SS_MAX 8
 	struct intel_uncore *uncore = gt->uncore;
 	const struct intel_gt_info *info = &gt->info;
 	u32 s_reg[SS_MAX], eu_reg[2 * SS_MAX], eu_mask[2];
@@ -267,8 +267,8 @@ int intel_sseu_status(struct seq_file *m, struct intel_gt *gt)
 			bdw_sseu_device_status(gt, &sseu);
 		else if (GRAPHICS_VER(i915) == 9)
 			gen9_sseu_device_status(gt, &sseu);
-		else if (GRAPHICS_VER(i915) >= 10)
-			gen10_sseu_device_status(gt, &sseu);
+		else if (GRAPHICS_VER(i915) >= 11)
+			gen11_sseu_device_status(gt, &sseu);
 	}
 
 	i915_print_sseu_info(m, false, HAS_POOLED_EU(i915), &sseu);
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index b62d1e31a645..aae609d7d85d 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -150,13 +150,14 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
 }
 
 static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
-		   u32 clear, u32 set, u32 read_mask)
+		   u32 clear, u32 set, u32 read_mask, bool masked_reg)
 {
 	struct i915_wa wa = {
 		.reg  = reg,
 		.clr  = clear,
 		.set  = set,
 		.read = read_mask,
+		.masked_reg = masked_reg,
 	};
 
 	_wa_add(wal, &wa);
@@ -165,7 +166,7 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
 static void
 wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
 {
-	wa_add(wal, reg, clear, set, clear);
+	wa_add(wal, reg, clear, set, clear, false);
 }
 
 static void
@@ -200,20 +201,20 @@ wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
 static void
 wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
-	wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val);
+	wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val, true);
 }
 
 static void
 wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
-	wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val);
+	wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true);
 }
 
 static void
 wa_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg,
 		    u32 mask, u32 val)
 {
-	wa_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask);
+	wa_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true);
 }
 
 static void gen6_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -514,53 +515,15 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine,
 		     GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 }
 
-static void cnl_ctx_workarounds_init(struct intel_engine_cs *engine,
-				     struct i915_wa_list *wal)
-{
-	/* WaForceContextSaveRestoreNonCoherent:cnl */
-	wa_masked_en(wal, CNL_HDC_CHICKEN0,
-		     HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
-
-	/* WaDisableReplayBufferBankArbitrationOptimization:cnl */
-	wa_masked_en(wal, COMMON_SLICE_CHICKEN2,
-		     GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	/* WaPushConstantDereferenceHoldDisable:cnl */
-	wa_masked_en(wal, GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
-
-	/* FtrEnableFastAnisoL1BankingFix:cnl */
-	wa_masked_en(wal, HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX);
-
-	/* WaDisable3DMidCmdPreemption:cnl */
-	wa_masked_dis(wal, GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
-
-	/* WaDisableGPGPUMidCmdPreemption:cnl */
-	wa_masked_field_set(wal, GEN8_CS_CHICKEN1,
-			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
-
-	/* WaDisableEarlyEOT:cnl */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT);
-}
-
 static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	struct drm_i915_private *i915 = engine->i915;
-
-	/* WaDisableBankHangMode:icl */
+	/* Wa_1406697149 (WaDisableBankHangMode:icl) */
 	wa_write(wal,
 		 GEN8_L3CNTLREG,
 		 intel_uncore_read(engine->uncore, GEN8_L3CNTLREG) |
 		 GEN8_ERRDETBCTRL);
 
-	/* Wa_1604370585:icl (pre-prod)
-	 * Formerly known as WaPushConstantDereferenceHoldDisable
-	 */
-	if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
-			     PUSH_CONSTANT_DEREF_DISABLE);
-
 	/* WaForceEnableNonCoherent:icl
 	 * This is not the same workaround as in early Gen9 platforms, where
 	 * lacking this could cause system hangs, but coherency performance
@@ -570,23 +533,11 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 */
 	wa_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
 
-	/* Wa_2006611047:icl (pre-prod)
-	 * Formerly known as WaDisableImprovedTdlClkGating
-	 */
-	if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
-			     GEN11_TDL_CLOCK_GATING_FIX_DISABLE);
-
-	/* Wa_2006665173:icl (pre-prod) */
-	if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
-		wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3,
-			     GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
-
 	/* WaEnableFloatBlendOptimization:icl */
-	wa_write_clr_set(wal,
-			 GEN10_CACHE_MODE_SS,
-			 0, /* write-only, so skip validation */
-			 _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE));
+	wa_add(wal, GEN10_CACHE_MODE_SS, 0,
+	       _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE),
+	       0 /* write-only, so skip validation */,
+	       true);
 
 	/* WaDisableGPGPUMidThreadPreemption:icl */
 	wa_masked_field_set(wal, GEN8_CS_CHICKEN1,
@@ -631,7 +582,7 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 	       FF_MODE2,
 	       FF_MODE2_TDS_TIMER_MASK,
 	       FF_MODE2_TDS_TIMER_128,
-	       0);
+	       0, false);
 }
 
 static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -640,15 +591,16 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen12_ctx_gt_tuning_init(engine, wal);
 
 	/*
-	 * Wa_1409142259:tgl
-	 * Wa_1409347922:tgl
-	 * Wa_1409252684:tgl
-	 * Wa_1409217633:tgl
-	 * Wa_1409207793:tgl
-	 * Wa_1409178076:tgl
-	 * Wa_1408979724:tgl
-	 * Wa_14010443199:rkl
-	 * Wa_14010698770:rkl
+	 * Wa_1409142259:tgl,dg1,adl-p
+	 * Wa_1409347922:tgl,dg1,adl-p
+	 * Wa_1409252684:tgl,dg1,adl-p
+	 * Wa_1409217633:tgl,dg1,adl-p
+	 * Wa_1409207793:tgl,dg1,adl-p
+	 * Wa_1409178076:tgl,dg1,adl-p
+	 * Wa_1408979724:tgl,dg1,adl-p
+	 * Wa_14010443199:tgl,rkl,dg1,adl-p
+	 * Wa_14010698770:tgl,rkl,dg1,adl-s,adl-p
+	 * Wa_1409342910:tgl,rkl,dg1,adl-s,adl-p
 	 */
 	wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3,
 		     GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
@@ -668,7 +620,14 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2,
 	       FF_MODE2_GS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224,
-	       0);
+	       0, false);
+
+	/*
+	 * Wa_14012131227:dg1
+	 * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p
+	 */
+	wa_masked_en(wal, GEN7_COMMON_SLICE_CHICKEN1,
+		     GEN9_RHWO_OPTIMIZATION_DISABLE);
 }
 
 static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -703,8 +662,6 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 		gen12_ctx_workarounds_init(engine, wal);
 	else if (GRAPHICS_VER(i915) == 11)
 		icl_ctx_workarounds_init(engine, wal);
-	else if (IS_CANNONLAKE(i915))
-		cnl_ctx_workarounds_init(engine, wal);
 	else if (IS_COFFEELAKE(i915) || IS_COMETLAKE(i915))
 		cfl_ctx_workarounds_init(engine, wal);
 	else if (IS_GEMINILAKE(i915))
@@ -839,7 +796,7 @@ hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	wa_add(wal,
 	       HSW_ROW_CHICKEN3, 0,
 	       _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
-		0 /* XXX does this reg exist? */);
+	       0 /* XXX does this reg exist? */, true);
 
 	/* WaVSRefCountFullforceMissDisable:hsw */
 	wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME);
@@ -882,30 +839,19 @@ skl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaInPlaceDecompressionHang:skl */
-	if (IS_SKL_REVID(i915, SKL_REVID_H0, REVID_FOREVER))
+	if (IS_SKL_GT_STEP(i915, STEP_A0, STEP_H0))
 		wa_write_or(wal,
 			    GEN9_GAMT_ECO_REG_RW_IA,
 			    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
 }
 
 static void
-bxt_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
-{
-	gen9_gt_workarounds_init(i915, wal);
-
-	/* WaInPlaceDecompressionHang:bxt */
-	wa_write_or(wal,
-		    GEN9_GAMT_ECO_REG_RW_IA,
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
-}
-
-static void
 kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
 	gen9_gt_workarounds_init(i915, wal);
 
 	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_GT_STEP(i915, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(i915, 0, STEP_C0))
 		wa_write_or(wal,
 			    GAMT_CHKN_BIT_REG,
 			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
@@ -943,98 +889,144 @@ cfl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
 }
 
+static void __set_mcr_steering(struct i915_wa_list *wal,
+			       i915_reg_t steering_reg,
+			       unsigned int slice, unsigned int subslice)
+{
+	u32 mcr, mcr_mask;
+
+	mcr = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
+	mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
+
+	wa_write_clr_set(wal, steering_reg, mcr_mask, mcr);
+}
+
+static void __add_mcr_wa(struct drm_i915_private *i915, struct i915_wa_list *wal,
+			 unsigned int slice, unsigned int subslice)
+{
+	drm_dbg(&i915->drm, "MCR slice=0x%x, subslice=0x%x\n", slice, subslice);
+
+	__set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice);
+}
+
 static void
-wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
+icl_wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
 	const struct sseu_dev_info *sseu = &i915->gt.info.sseu;
 	unsigned int slice, subslice;
-	u32 l3_en, mcr, mcr_mask;
 
-	GEM_BUG_ON(GRAPHICS_VER(i915) < 10);
+	GEM_BUG_ON(GRAPHICS_VER(i915) < 11);
+	GEM_BUG_ON(hweight8(sseu->slice_mask) > 1);
+	slice = 0;
 
 	/*
-	 * WaProgramMgsrForL3BankSpecificMmioReads: cnl,icl
-	 * L3Banks could be fused off in single slice scenario. If that is
-	 * the case, we might need to program MCR select to a valid L3Bank
-	 * by default, to make sure we correctly read certain registers
-	 * later on (in the range 0xB100 - 0xB3FF).
+	 * Although a platform may have subslices, we need to always steer
+	 * reads to the lowest instance that isn't fused off.  When Render
+	 * Power Gating is enabled, grabbing forcewake will only power up a
+	 * single subslice (the "minconfig") if there isn't a real workload
+	 * that needs to be run; this means that if we steer register reads to
+	 * one of the higher subslices, we run the risk of reading back 0's or
+	 * random garbage.
+	 */
+	subslice = __ffs(intel_sseu_get_subslices(sseu, slice));
+
+	/*
+	 * If the subslice we picked above also steers us to a valid L3 bank,
+	 * then we can just rely on the default steering and won't need to
+	 * worry about explicitly re-steering L3BANK reads later.
+	 */
+	if (i915->gt.info.l3bank_mask & BIT(subslice))
+		i915->gt.steering_table[L3BANK] = NULL;
+
+	__add_mcr_wa(i915, wal, slice, subslice);
+}
+
+static void
+xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	const struct sseu_dev_info *sseu = &gt->info.sseu;
+	unsigned long slice, subslice = 0, slice_mask = 0;
+	u64 dss_mask = 0;
+	u32 lncf_mask = 0;
+	int i;
+
+	/*
+	 * On Xe_HP the steering increases in complexity. There are now several
+	 * more units that require steering and we're not guaranteed to be able
+	 * to find a common setting for all of them. These are:
+	 * - GSLICE (fusable)
+	 * - DSS (sub-unit within gslice; fusable)
+	 * - L3 Bank (fusable)
+	 * - MSLICE (fusable)
+	 * - LNCF (sub-unit within mslice; always present if mslice is present)
 	 *
-	 * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl,icl
-	 * Before any MMIO read into slice/subslice specific registers, MCR
-	 * packet control register needs to be programmed to point to any
-	 * enabled s/ss pair. Otherwise, incorrect values will be returned.
-	 * This means each subsequent MMIO read will be forwarded to an
-	 * specific s/ss combination, but this is OK since these registers
-	 * are consistent across s/ss in almost all cases. In the rare
-	 * occasions, such as INSTDONE, where this value is dependent
-	 * on s/ss combo, the read should be done with read_subslice_reg.
+	 * We'll do our default/implicit steering based on GSLICE (in the
+	 * sliceid field) and DSS (in the subsliceid field).  If we can
+	 * find overlap between the valid MSLICE and/or LNCF values with
+	 * a suitable GSLICE, then we can just re-use the default value and
+	 * skip and explicit steering at runtime.
 	 *
-	 * Since GEN8_MCR_SELECTOR contains dual-purpose bits which select both
-	 * to which subslice, or to which L3 bank, the respective mmio reads
-	 * will go, we have to find a common index which works for both
-	 * accesses.
+	 * We only need to look for overlap between GSLICE/MSLICE/LNCF to find
+	 * a valid sliceid value.  DSS steering is the only type of steering
+	 * that utilizes the 'subsliceid' bits.
 	 *
-	 * Case where we cannot find a common index fortunately should not
-	 * happen in production hardware, so we only emit a warning instead of
-	 * implementing something more complex that requires checking the range
-	 * of every MMIO read.
+	 * Also note that, even though the steering domain is called "GSlice"
+	 * and it is encoded in the register using the gslice format, the spec
+	 * says that the combined (geometry | compute) fuse should be used to
+	 * select the steering.
 	 */
 
-	if (GRAPHICS_VER(i915) >= 10 && is_power_of_2(sseu->slice_mask)) {
-		u32 l3_fuse =
-			intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3) &
-			GEN10_L3BANK_MASK;
+	/* Find the potential gslice candidates */
+	dss_mask = intel_sseu_get_subslices(sseu, 0);
+	slice_mask = intel_slicemask_from_dssmask(dss_mask, GEN_DSS_PER_GSLICE);
 
-		drm_dbg(&i915->drm, "L3 fuse = %x\n", l3_fuse);
-		l3_en = ~(l3_fuse << GEN10_L3BANK_PAIR_COUNT | l3_fuse);
-	} else {
-		l3_en = ~0;
-	}
+	/*
+	 * Find the potential LNCF candidates.  Either LNCF within a valid
+	 * mslice is fine.
+	 */
+	for_each_set_bit(i, &gt->info.mslice_mask, GEN12_MAX_MSLICES)
+		lncf_mask |= (0x3 << (i * 2));
 
-	slice = fls(sseu->slice_mask) - 1;
-	subslice = fls(l3_en & intel_sseu_get_subslices(sseu, slice));
-	if (!subslice) {
-		drm_warn(&i915->drm,
-			 "No common index found between subslice mask %x and L3 bank mask %x!\n",
-			 intel_sseu_get_subslices(sseu, slice), l3_en);
-		subslice = fls(l3_en);
-		drm_WARN_ON(&i915->drm, !subslice);
-	}
-	subslice--;
-
-	if (GRAPHICS_VER(i915) >= 11) {
-		mcr = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
-		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
-	} else {
-		mcr = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
-		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
+	/*
+	 * Are there any sliceid values that work for both GSLICE and LNCF
+	 * steering?
+	 */
+	if (slice_mask & lncf_mask) {
+		slice_mask &= lncf_mask;
+		gt->steering_table[LNCF] = NULL;
 	}
 
-	drm_dbg(&i915->drm, "MCR slice/subslice = %x\n", mcr);
+	/* How about sliceid values that also work for MSLICE steering? */
+	if (slice_mask & gt->info.mslice_mask) {
+		slice_mask &= gt->info.mslice_mask;
+		gt->steering_table[MSLICE] = NULL;
+	}
 
-	wa_write_clr_set(wal, GEN8_MCR_SELECTOR, mcr_mask, mcr);
-}
+	slice = __ffs(slice_mask);
+	subslice = __ffs(dss_mask >> (slice * GEN_DSS_PER_GSLICE));
+	WARN_ON(subslice > GEN_DSS_PER_GSLICE);
+	WARN_ON(dss_mask >> (slice * GEN_DSS_PER_GSLICE) == 0);
 
-static void
-cnl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
-{
-	wa_init_mcr(i915, wal);
+	__add_mcr_wa(i915, wal, slice, subslice);
 
-	/* WaInPlaceDecompressionHang:cnl */
-	wa_write_or(wal,
-		    GEN9_GAMT_ECO_REG_RW_IA,
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+	/*
+	 * SQIDI ranges are special because they use different steering
+	 * registers than everything else we work with.  On XeHP SDV and
+	 * DG2-G10, any value in the steering registers will work fine since
+	 * all instances are present, but DG2-G11 only has SQIDI instances at
+	 * ID's 2 and 3, so we need to steer to one of those.  For simplicity
+	 * we'll just steer to a hardcoded "2" since that value will work
+	 * everywhere.
+	 */
+	__set_mcr_steering(wal, MCFG_MCR_SELECTOR, 0, 2);
+	__set_mcr_steering(wal, SF_MCR_SELECTOR, 0, 2);
 }
 
 static void
 icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
-	wa_init_mcr(i915, wal);
-
-	/* WaInPlaceDecompressionHang:icl */
-	wa_write_or(wal,
-		    GEN9_GAMT_ECO_REG_RW_IA,
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+	icl_wa_init_mcr(i915, wal);
 
 	/* WaModifyGamTlbPartitioning:icl */
 	wa_write_clr_set(wal,
@@ -1057,18 +1049,6 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GEN8_GAMW_ECO_DEV_RW_IA,
 		    GAMW_ECO_DEV_CTX_RELOAD_DISABLE);
 
-	/* Wa_1405779004:icl (pre-prod) */
-	if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
-		wa_write_or(wal,
-			    SLICE_UNIT_LEVEL_CLKGATE,
-			    MSCUNIT_CLKGATE_DIS);
-
-	/* Wa_1406838659:icl (pre-prod) */
-	if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
-		wa_write_or(wal,
-			    INF_UNIT_LEVEL_CLKGATE,
-			    CGPSF_CLKGATE_DIS);
-
 	/* Wa_1406463099:icl
 	 * Formerly known as WaGamTlbPendError
 	 */
@@ -1078,10 +1058,16 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 
 	/* Wa_1607087056:icl,ehl,jsl */
 	if (IS_ICELAKE(i915) ||
-	    IS_JSL_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0))
+	    IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
+
+	/*
+	 * This is not a documented workaround, but rather an optimization
+	 * to reduce sampler power.
+	 */
+	wa_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
 }
 
 /*
@@ -1111,10 +1097,13 @@ static void
 gen12_gt_workarounds_init(struct drm_i915_private *i915,
 			  struct i915_wa_list *wal)
 {
-	wa_init_mcr(i915, wal);
+	icl_wa_init_mcr(i915, wal);
 
-	/* Wa_14011060649:tgl,rkl,dg1,adls */
+	/* Wa_14011060649:tgl,rkl,dg1,adl-s,adl-p */
 	wa_14011060649(i915, wal);
+
+	/* Wa_14011059788:tgl,rkl,adl-s,dg1,adl-p */
+	wa_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
 }
 
 static void
@@ -1123,19 +1112,19 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1409420604:tgl */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
 			    CPSSUNIT_CLKGATE_DIS);
 
 	/* Wa_1607087056:tgl also know as BUG:1409180338 */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 
 	/* Wa_1408615072:tgl[a0] */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
 			    VSUNIT_CLKGATE_DIS_TGL);
 }
@@ -1146,7 +1135,7 @@ dg1_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1607087056:dg1 */
-	if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0))
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
@@ -1165,9 +1154,17 @@ dg1_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 }
 
 static void
+xehpsdv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	xehp_init_mcr(&i915->gt, wal);
+}
+
+static void
 gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
-	if (IS_DG1(i915))
+	if (IS_XEHPSDV(i915))
+		xehpsdv_gt_workarounds_init(i915, wal);
+	else if (IS_DG1(i915))
 		dg1_gt_workarounds_init(i915, wal);
 	else if (IS_TIGERLAKE(i915))
 		tgl_gt_workarounds_init(i915, wal);
@@ -1175,8 +1172,6 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		gen12_gt_workarounds_init(i915, wal);
 	else if (GRAPHICS_VER(i915) == 11)
 		icl_gt_workarounds_init(i915, wal);
-	else if (IS_CANNONLAKE(i915))
-		cnl_gt_workarounds_init(i915, wal);
 	else if (IS_COFFEELAKE(i915) || IS_COMETLAKE(i915))
 		cfl_gt_workarounds_init(i915, wal);
 	else if (IS_GEMINILAKE(i915))
@@ -1184,7 +1179,7 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	else if (IS_KABYLAKE(i915))
 		kbl_gt_workarounds_init(i915, wal);
 	else if (IS_BROXTON(i915))
-		bxt_gt_workarounds_init(i915, wal);
+		gen9_gt_workarounds_init(i915, wal);
 	else if (IS_SKYLAKE(i915))
 		skl_gt_workarounds_init(i915, wal);
 	else if (IS_HASWELL(i915))
@@ -1247,8 +1242,9 @@ wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
 }
 
 static void
-wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
+wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	enum forcewake_domains fw;
 	unsigned long flags;
 	struct i915_wa *wa;
@@ -1263,13 +1259,16 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 	intel_uncore_forcewake_get__locked(uncore, fw);
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
-		if (wa->clr)
-			intel_uncore_rmw_fw(uncore, wa->reg, wa->clr, wa->set);
-		else
-			intel_uncore_write_fw(uncore, wa->reg, wa->set);
+		u32 val, old = 0;
+
+		/* open-coded rmw due to steering */
+		old = wa->clr ? intel_gt_read_register_fw(gt, wa->reg) : 0;
+		val = (old & ~wa->clr) | wa->set;
+		if (val != old || !wa->clr)
+			intel_uncore_write_fw(uncore, wa->reg, val);
+
 		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-			wa_verify(wa,
-				  intel_uncore_read_fw(uncore, wa->reg),
+			wa_verify(wa, intel_gt_read_register_fw(gt, wa->reg),
 				  wal->name, "application");
 	}
 
@@ -1279,28 +1278,39 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 
 void intel_gt_apply_workarounds(struct intel_gt *gt)
 {
-	wa_list_apply(gt->uncore, &gt->i915->gt_wa_list);
+	wa_list_apply(gt, &gt->i915->gt_wa_list);
 }
 
-static bool wa_list_verify(struct intel_uncore *uncore,
+static bool wa_list_verify(struct intel_gt *gt,
 			   const struct i915_wa_list *wal,
 			   const char *from)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	struct i915_wa *wa;
+	enum forcewake_domains fw;
+	unsigned long flags;
 	unsigned int i;
 	bool ok = true;
 
+	fw = wal_get_fw_for_rmw(uncore, wal);
+
+	spin_lock_irqsave(&uncore->lock, flags);
+	intel_uncore_forcewake_get__locked(uncore, fw);
+
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
 		ok &= wa_verify(wa,
-				intel_uncore_read(uncore, wa->reg),
+				intel_gt_read_register_fw(gt, wa->reg),
 				wal->name, from);
 
+	intel_uncore_forcewake_put__locked(uncore, fw);
+	spin_unlock_irqrestore(&uncore->lock, flags);
+
 	return ok;
 }
 
 bool intel_gt_verify_workarounds(struct intel_gt *gt, const char *from)
 {
-	return wa_list_verify(gt->uncore, &gt->i915->gt_wa_list, from);
+	return wa_list_verify(gt, &gt->i915->gt_wa_list, from);
 }
 
 __maybe_unused
@@ -1438,17 +1448,6 @@ static void cml_whitelist_build(struct intel_engine_cs *engine)
 	cfl_whitelist_build(engine);
 }
 
-static void cnl_whitelist_build(struct intel_engine_cs *engine)
-{
-	struct i915_wa_list *w = &engine->whitelist;
-
-	if (engine->class != RENDER_CLASS)
-		return;
-
-	/* WaEnablePreemptionGranularityControlByUMD:cnl */
-	whitelist_reg(w, GEN8_CS_CHICKEN1);
-}
-
 static void icl_whitelist_build(struct intel_engine_cs *engine)
 {
 	struct i915_wa_list *w = &engine->whitelist;
@@ -1542,7 +1541,7 @@ static void dg1_whitelist_build(struct intel_engine_cs *engine)
 	tgl_whitelist_build(engine);
 
 	/* GEN:BUG:1409280441:dg1 */
-	if (IS_DG1_REVID(engine->i915, DG1_REVID_A0, DG1_REVID_A0) &&
+	if (IS_DG1_GT_STEP(engine->i915, STEP_A0, STEP_B0) &&
 	    (engine->class == RENDER_CLASS ||
 	     engine->class == COPY_ENGINE_CLASS))
 		whitelist_reg_ext(w, RING_ID(engine->mmio_base),
@@ -1562,8 +1561,6 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine)
 		tgl_whitelist_build(engine);
 	else if (GRAPHICS_VER(i915) == 11)
 		icl_whitelist_build(engine);
-	else if (IS_CANNONLAKE(i915))
-		cnl_whitelist_build(engine);
 	else if (IS_COMETLAKE(i915))
 		cml_whitelist_build(engine);
 	else if (IS_COFFEELAKE(i915))
@@ -1612,8 +1609,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) ||
-	    IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) {
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
+	    IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) {
 		/*
 		 * Wa_1607138336:tgl[a0],dg1[a0]
 		 * Wa_1607063988:tgl[a0],dg1[a0]
@@ -1623,7 +1620,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 	}
 
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) {
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) {
 		/*
 		 * Wa_1606679103:tgl
 		 * (see also Wa_1606682166:icl)
@@ -1633,44 +1630,46 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN7_DISABLE_SAMPLER_PREFETCH);
 	}
 
-	if (IS_ALDERLAKE_S(i915) || IS_DG1(i915) ||
+	if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
-		/* Wa_1606931601:tgl,rkl,dg1,adl-s */
+		/* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
 
 		/*
 		 * Wa_1407928979:tgl A*
 		 * Wa_18011464164:tgl[B0+],dg1[B0+]
 		 * Wa_22010931296:tgl[B0+],dg1[B0+]
-		 * Wa_14010919138:rkl,dg1,adl-s
+		 * Wa_14010919138:rkl,dg1,adl-s,adl-p
 		 */
 		wa_write_or(wal, GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
 
 		/*
-		 * Wa_1606700617:tgl,dg1
-		 * Wa_22010271021:tgl,rkl,dg1, adl-s
+		 * Wa_1606700617:tgl,dg1,adl-p
+		 * Wa_22010271021:tgl,rkl,dg1,adl-s,adl-p
+		 * Wa_14010826681:tgl,dg1,rkl,adl-p
 		 */
 		wa_masked_en(wal,
 			     GEN9_CS_DEBUG_MODE1,
 			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
-	if (IS_ALDERLAKE_S(i915) || IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) ||
+	if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) ||
+	    IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
-		/* Wa_1409804808:tgl,rkl,dg1[a0],adl-s */
+		/* Wa_1409804808:tgl,rkl,dg1[a0],adl-s,adl-p */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
 			     GEN12_PUSH_CONST_DEREF_HOLD_DIS);
 
 		/*
 		 * Wa_1409085225:tgl
-		 * Wa_14010229206:tgl,rkl,dg1[a0],adl-s
+		 * Wa_14010229206:tgl,rkl,dg1[a0],adl-s,adl-p
 		 */
 		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 	}
 
 
-	if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) ||
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/*
 		 * Wa_1607030317:tgl
@@ -1688,8 +1687,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
 	}
 
-	if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
-		/* Wa_1406941453:tgl,rkl,dg1 */
+	if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) ||
+	    IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) {
+		/* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */
 		wa_masked_en(wal,
 			     GEN10_SAMPLER_MODE,
 			     ENABLE_SMALLPL);
@@ -1701,11 +1701,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     _3D_CHICKEN3,
 			     _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE);
 
-		/* WaPipelineFlushCoherentLines:icl */
-		wa_write_or(wal,
-			    GEN8_L3SQCREG4,
-			    GEN8_LQSC_FLUSH_COHERENT_LINES);
-
 		/*
 		 * Wa_1405543622:icl
 		 * Formerly known as WaGAPZPriorityScheme
@@ -1735,19 +1730,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN8_L3SQCREG4,
 			    GEN11_LQSC_CLEAN_EVICT_DISABLE);
 
-		/* WaForwardProgressSoftReset:icl */
-		wa_write_or(wal,
-			    GEN10_SCRATCH_LNCF2,
-			    PMFLUSHDONE_LNICRSDROP |
-			    PMFLUSH_GAPL3UNBLOCK |
-			    PMFLUSHDONE_LNEBLK);
-
-		/* Wa_1406609255:icl (pre-prod) */
-		if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
-			wa_write_or(wal,
-				    GEN7_SARCHKMD,
-				    GEN7_DISABLE_DEMAND_PREFETCH);
-
 		/* Wa_1606682166:icl */
 		wa_write_or(wal,
 			    GEN7_SARCHKMD,
@@ -1947,10 +1929,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * disable bit, which we don't touch here, but it's good
 		 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
 		 */
-		wa_add(wal, GEN7_GT_MODE, 0,
-		       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK,
-				     GEN6_WIZ_HASHING_16x4),
-		       GEN6_WIZ_HASHING_16x4);
+		wa_masked_field_set(wal,
+				    GEN7_GT_MODE,
+				    GEN6_WIZ_HASHING_MASK,
+				    GEN6_WIZ_HASHING_16x4);
 	}
 
 	if (IS_GRAPHICS_VER(i915, 6, 7))
@@ -2000,10 +1982,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * disable bit, which we don't touch here, but it's good
 		 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
 		 */
-		wa_add(wal,
-		       GEN6_GT_MODE, 0,
-		       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
-		       GEN6_WIZ_HASHING_16x4);
+		wa_masked_field_set(wal,
+				    GEN6_GT_MODE,
+				    GEN6_WIZ_HASHING_MASK,
+				    GEN6_WIZ_HASHING_16x4);
 
 		/* WaDisable_RenderCache_OperationalFlush:snb */
 		wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
@@ -2024,7 +2006,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_add(wal, MI_MODE,
 		       0, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH),
 		       /* XXX bit doesn't stick on Broadwater */
-		       IS_I965G(i915) ? 0 : VS_TIMER_DISPATCH);
+		       IS_I965G(i915) ? 0 : VS_TIMER_DISPATCH, true);
 
 	if (GRAPHICS_VER(i915) == 4)
 		/*
@@ -2039,7 +2021,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 */
 		wa_add(wal, ECOSKPD,
 		       0, _MASKED_BIT_ENABLE(ECO_CONSTANT_BUFFER_SR_DISABLE),
-		       0 /* XXX bit doesn't stick on Broadwater */);
+		       0 /* XXX bit doesn't stick on Broadwater */,
+		       true);
 }
 
 static void
@@ -2048,7 +2031,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	struct drm_i915_private *i915 = engine->i915;
 
 	/* WaKBLVECSSemaphoreWaitPoll:kbl */
-	if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_E0)) {
+	if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_F0)) {
 		wa_write(wal,
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);
@@ -2081,7 +2064,7 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine)
 
 void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
 {
-	wa_list_apply(engine->uncore, &engine->wa_list);
+	wa_list_apply(engine->gt, &engine->wa_list);
 }
 
 struct mcr_range {
@@ -2107,12 +2090,31 @@ static const struct mcr_range mcr_ranges_gen12[] = {
 	{},
 };
 
+static const struct mcr_range mcr_ranges_xehp[] = {
+	{ .start =  0x4000, .end =  0x4aff },
+	{ .start =  0x5200, .end =  0x52ff },
+	{ .start =  0x5400, .end =  0x7fff },
+	{ .start =  0x8140, .end =  0x815f },
+	{ .start =  0x8c80, .end =  0x8dff },
+	{ .start =  0x94d0, .end =  0x955f },
+	{ .start =  0x9680, .end =  0x96ff },
+	{ .start =  0xb000, .end =  0xb3ff },
+	{ .start =  0xc800, .end =  0xcfff },
+	{ .start =  0xd800, .end =  0xd8ff },
+	{ .start =  0xdc00, .end =  0xffff },
+	{ .start = 0x17000, .end = 0x17fff },
+	{ .start = 0x24a00, .end = 0x24a7f },
+	{},
+};
+
 static bool mcr_range(struct drm_i915_private *i915, u32 offset)
 {
 	const struct mcr_range *mcr_ranges;
 	int i;
 
-	if (GRAPHICS_VER(i915) >= 12)
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+		mcr_ranges = mcr_ranges_xehp;
+	else if (GRAPHICS_VER(i915) >= 12)
 		mcr_ranges = mcr_ranges_gen12;
 	else if (GRAPHICS_VER(i915) >= 8)
 		mcr_ranges = mcr_ranges_gen8;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
index c214111ea367..1e873681795d 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
@@ -15,6 +15,7 @@ struct i915_wa {
 	u32		clr;
 	u32		set;
 	u32		read;
+	bool		masked_reg;
 };
 
 struct i915_wa_list {
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 32589c6625e1..2c1af030310c 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -235,6 +235,34 @@ static void mock_submit_request(struct i915_request *request)
 	spin_unlock_irqrestore(&engine->hw_lock, flags);
 }
 
+static void mock_add_to_engine(struct i915_request *rq)
+{
+	lockdep_assert_held(&rq->engine->sched_engine->lock);
+	list_move_tail(&rq->sched.link, &rq->engine->sched_engine->requests);
+}
+
+static void mock_remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+
+	locked = READ_ONCE(rq->engine);
+	spin_lock_irq(&locked->sched_engine->lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->sched_engine->lock);
+		spin_lock(&engine->sched_engine->lock);
+		locked = engine;
+	}
+	list_del_init(&rq->sched.link);
+	spin_unlock_irq(&locked->sched_engine->lock);
+}
+
 static void mock_reset_prepare(struct intel_engine_cs *engine)
 {
 }
@@ -253,10 +281,10 @@ static void mock_reset_cancel(struct intel_engine_cs *engine)
 
 	del_timer_sync(&mock->hw_delay);
 
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	/* Mark all submitted requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link)
+	list_for_each_entry(rq, &engine->sched_engine->requests, sched.link)
 		i915_request_put(i915_request_mark_eio(rq));
 	intel_engine_signal_breadcrumbs(engine);
 
@@ -269,7 +297,7 @@ static void mock_reset_cancel(struct intel_engine_cs *engine)
 	}
 	INIT_LIST_HEAD(&mock->hw_queue);
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 static void mock_reset_finish(struct intel_engine_cs *engine)
@@ -283,7 +311,8 @@ static void mock_engine_release(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
-	intel_breadcrumbs_free(engine->breadcrumbs);
+	i915_sched_engine_put(engine->sched_engine);
+	intel_breadcrumbs_put(engine->breadcrumbs);
 
 	intel_context_unpin(engine->kernel_context);
 	intel_context_put(engine->kernel_context);
@@ -320,6 +349,8 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.emit_flush = mock_emit_flush;
 	engine->base.emit_fini_breadcrumb = mock_emit_breadcrumb;
 	engine->base.submit_request = mock_submit_request;
+	engine->base.add_active_request = mock_add_to_engine;
+	engine->base.remove_active_request = mock_remove_from_engine;
 
 	engine->base.reset.prepare = mock_reset_prepare;
 	engine->base.reset.rewind = mock_reset_rewind;
@@ -345,14 +376,18 @@ int mock_engine_init(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
-	intel_engine_init_active(engine, ENGINE_MOCK);
+	engine->sched_engine = i915_sched_engine_create(ENGINE_MOCK);
+	if (!engine->sched_engine)
+		return -ENOMEM;
+	engine->sched_engine->private_data = engine;
+
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
 
 	engine->breadcrumbs = intel_breadcrumbs_create(NULL);
 	if (!engine->breadcrumbs)
-		return -ENOMEM;
+		goto err_schedule;
 
 	ce = create_kernel_context(engine);
 	if (IS_ERR(ce))
@@ -365,7 +400,9 @@ int mock_engine_init(struct intel_engine_cs *engine)
 	return 0;
 
 err_breadcrumbs:
-	intel_breadcrumbs_free(engine->breadcrumbs);
+	intel_breadcrumbs_put(engine->breadcrumbs);
+err_schedule:
+	i915_sched_engine_put(engine->sched_engine);
 	return -ENOMEM;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 26685b927169..fa7b99a671dd 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -209,7 +209,13 @@ static int __live_active_context(struct intel_engine_cs *engine)
 	 * This test makes sure that the context is kept alive until a
 	 * subsequent idle-barrier (emitted when the engine wakeref hits 0
 	 * with no more outstanding requests).
+	 *
+	 * In GuC submission mode we don't use idle barriers and we instead
+	 * get a message from the GuC to signal that it is safe to unpin the
+	 * context from memory.
 	 */
+	if (intel_engine_uses_guc(engine))
+		return 0;
 
 	if (intel_engine_pm_is_awake(engine)) {
 		pr_err("%s is awake before starting %s!\n",
@@ -357,7 +363,11 @@ static int __live_remote_context(struct intel_engine_cs *engine)
 	 * on the context image remotely (intel_context_prepare_remote_request),
 	 * which inserts foreign fences into intel_context.active, does not
 	 * clobber the idle-barrier.
+	 *
+	 * In GuC submission mode we don't use idle barriers.
 	 */
+	if (intel_engine_uses_guc(engine))
+		return 0;
 
 	if (intel_engine_pm_is_awake(engine)) {
 		pr_err("%s is awake before starting %s!\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index 4896e4ccad50..317eebf086c3 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -405,3 +405,25 @@ void st_engine_heartbeat_enable(struct intel_engine_cs *engine)
 	engine->props.heartbeat_interval_ms =
 		engine->defaults.heartbeat_interval_ms;
 }
+
+void st_engine_heartbeat_disable_no_pm(struct intel_engine_cs *engine)
+{
+	engine->props.heartbeat_interval_ms = 0;
+
+	/*
+	 * Park the heartbeat but without holding the PM lock as that
+	 * makes the engines appear not-idle. Note that if/when unpark
+	 * is called due to the PM lock being acquired later the
+	 * heartbeat still won't be enabled because of the above = 0.
+	 */
+	if (intel_engine_pm_get_if_awake(engine)) {
+		intel_engine_park_heartbeat(engine);
+		intel_engine_pm_put(engine);
+	}
+}
+
+void st_engine_heartbeat_enable_no_pm(struct intel_engine_cs *engine)
+{
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.h b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.h
index cd27113d5400..81da2cd8e406 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.h
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.h
@@ -9,6 +9,8 @@
 struct intel_engine_cs;
 
 void st_engine_heartbeat_disable(struct intel_engine_cs *engine);
+void st_engine_heartbeat_disable_no_pm(struct intel_engine_cs *engine);
 void st_engine_heartbeat_enable(struct intel_engine_cs *engine);
+void st_engine_heartbeat_enable_no_pm(struct intel_engine_cs *engine);
 
 #endif /* SELFTEST_ENGINE_HEARTBEAT_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 72cca3f0da21..75569666105d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -173,8 +173,8 @@ static int __live_engine_timestamps(struct intel_engine_cs *engine)
 	d_ctx = trifilter(s_ctx);
 
 	d_ctx *= engine->gt->clock_frequency;
-	if (IS_ICELAKE(engine->i915))
-		d_ring *= 12500000; /* Fixed 80ns for icl ctx timestamp? */
+	if (GRAPHICS_VER(engine->i915) == 11)
+		d_ring *= 12500000; /* Fixed 80ns for GEN11 ctx timestamp? */
 	else
 		d_ring *= engine->gt->clock_frequency;
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 1c8108d30b85..f12ffe797639 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -43,7 +43,7 @@ static int wait_for_submit(struct intel_engine_cs *engine,
 			   unsigned long timeout)
 {
 	/* Ignore our own attempts to suppress excess tasklets */
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	tasklet_hi_schedule(&engine->sched_engine->tasklet);
 
 	timeout += jiffies;
 	do {
@@ -273,7 +273,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 			};
 
 			/* Alternatively preempt the spinner with ce[1] */
-			engine->schedule(rq[1], &attr);
+			engine->sched_engine->schedule(rq[1], &attr);
 		}
 
 		/* And switch back to ce[0] for good measure */
@@ -553,13 +553,13 @@ static int live_pin_rewind(void *arg)
 
 static int engine_lock_reset_tasklet(struct intel_engine_cs *engine)
 {
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->sched_engine->tasklet);
 	local_bh_disable();
 
 	if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 			     &engine->gt->reset.flags)) {
 		local_bh_enable();
-		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_enable(&engine->sched_engine->tasklet);
 
 		intel_gt_set_wedged(engine->gt);
 		return -EBUSY;
@@ -574,7 +574,7 @@ static void engine_unlock_reset_tasklet(struct intel_engine_cs *engine)
 			      &engine->gt->reset.flags);
 
 	local_bh_enable();
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->sched_engine->tasklet);
 }
 
 static int live_hold_reset(void *arg)
@@ -628,7 +628,7 @@ static int live_hold_reset(void *arg)
 		if (err)
 			goto out;
 
-		engine->execlists.tasklet.callback(&engine->execlists.tasklet);
+		engine->sched_engine->tasklet.callback(&engine->sched_engine->tasklet);
 		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 		i915_request_get(rq);
@@ -917,7 +917,7 @@ release_queue(struct intel_engine_cs *engine,
 	i915_request_add(rq);
 
 	local_bh_disable();
-	engine->schedule(rq, &attr);
+	engine->sched_engine->schedule(rq, &attr);
 	local_bh_enable(); /* kick tasklet */
 
 	i915_request_put(rq);
@@ -1200,7 +1200,7 @@ static int live_timeslice_rewind(void *arg)
 		while (i915_request_is_active(rq[A2])) { /* semaphore yield! */
 			/* Wait for the timeslice to kick in */
 			del_timer(&engine->execlists.timer);
-			tasklet_hi_schedule(&engine->execlists.tasklet);
+			tasklet_hi_schedule(&engine->sched_engine->tasklet);
 			intel_engine_flush_submission(engine);
 		}
 		/* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */
@@ -1342,7 +1342,7 @@ static int live_timeslice_queue(void *arg)
 			err = PTR_ERR(rq);
 			goto err_heartbeat;
 		}
-		engine->schedule(rq, &attr);
+		engine->sched_engine->schedule(rq, &attr);
 		err = wait_for_submit(engine, rq, HZ / 2);
 		if (err) {
 			pr_err("%s: Timed out trying to submit semaphores\n",
@@ -1539,12 +1539,12 @@ static int live_busywait_preempt(void *arg)
 	 * preempt the busywaits used to synchronise between rings.
 	 */
 
-	ctx_hi = kernel_context(gt->i915);
+	ctx_hi = kernel_context(gt->i915, NULL);
 	if (!ctx_hi)
 		return -ENOMEM;
 	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
-	ctx_lo = kernel_context(gt->i915);
+	ctx_lo = kernel_context(gt->i915, NULL);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
@@ -1741,12 +1741,12 @@ static int live_preempt(void *arg)
 	if (igt_spinner_init(&spin_lo, gt))
 		goto err_spin_hi;
 
-	ctx_hi = kernel_context(gt->i915);
+	ctx_hi = kernel_context(gt->i915, NULL);
 	if (!ctx_hi)
 		goto err_spin_lo;
 	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
-	ctx_lo = kernel_context(gt->i915);
+	ctx_lo = kernel_context(gt->i915, NULL);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
@@ -1833,11 +1833,11 @@ static int live_late_preempt(void *arg)
 	if (igt_spinner_init(&spin_lo, gt))
 		goto err_spin_hi;
 
-	ctx_hi = kernel_context(gt->i915);
+	ctx_hi = kernel_context(gt->i915, NULL);
 	if (!ctx_hi)
 		goto err_spin_lo;
 
-	ctx_lo = kernel_context(gt->i915);
+	ctx_lo = kernel_context(gt->i915, NULL);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 
@@ -1884,7 +1884,7 @@ static int live_late_preempt(void *arg)
 		}
 
 		attr.priority = I915_PRIORITY_MAX;
-		engine->schedule(rq, &attr);
+		engine->sched_engine->schedule(rq, &attr);
 
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			pr_err("High priority context failed to preempt the low priority context\n");
@@ -1927,7 +1927,7 @@ struct preempt_client {
 
 static int preempt_client_init(struct intel_gt *gt, struct preempt_client *c)
 {
-	c->ctx = kernel_context(gt->i915);
+	c->ctx = kernel_context(gt->i915, NULL);
 	if (!c->ctx)
 		return -ENOMEM;
 
@@ -2497,7 +2497,7 @@ static int live_suppress_self_preempt(void *arg)
 			i915_request_add(rq_b);
 
 			GEM_BUG_ON(i915_request_completed(rq_a));
-			engine->schedule(rq_a, &attr);
+			engine->sched_engine->schedule(rq_a, &attr);
 			igt_spinner_end(&a.spin);
 
 			if (!igt_wait_for_spinner(&b.spin, rq_b)) {
@@ -2629,7 +2629,7 @@ static int live_chain_preempt(void *arg)
 
 			i915_request_get(rq);
 			i915_request_add(rq);
-			engine->schedule(rq, &attr);
+			engine->sched_engine->schedule(rq, &attr);
 
 			igt_spinner_end(&hi.spin);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
@@ -2810,7 +2810,7 @@ static int __live_preempt_ring(struct intel_engine_cs *engine,
 			goto err_ce;
 		}
 
-		tmp->ring = __intel_context_ring_size(ring_sz);
+		tmp->ring_size = ring_sz;
 
 		err = intel_context_pin(tmp);
 		if (err) {
@@ -2988,7 +2988,7 @@ static int live_preempt_gang(void *arg)
 				break;
 
 			/* Submit each spinner at increasing priority */
-			engine->schedule(rq, &attr);
+			engine->sched_engine->schedule(rq, &attr);
 		} while (prio <= I915_PRIORITY_MAX &&
 			 !__igt_timeout(end_time, NULL));
 		pr_debug("%s: Preempt chain of %d requests\n",
@@ -3236,7 +3236,7 @@ static int preempt_user(struct intel_engine_cs *engine,
 	i915_request_get(rq);
 	i915_request_add(rq);
 
-	engine->schedule(rq, &attr);
+	engine->sched_engine->schedule(rq, &attr);
 
 	if (i915_request_wait(rq, 0, HZ / 2) < 0)
 		err = -ETIME;
@@ -3384,12 +3384,12 @@ static int live_preempt_timeout(void *arg)
 	if (igt_spinner_init(&spin_lo, gt))
 		return -ENOMEM;
 
-	ctx_hi = kernel_context(gt->i915);
+	ctx_hi = kernel_context(gt->i915, NULL);
 	if (!ctx_hi)
 		goto err_spin_lo;
 	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
-	ctx_lo = kernel_context(gt->i915);
+	ctx_lo = kernel_context(gt->i915, NULL);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
@@ -3561,12 +3561,16 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 #define BATCH BIT(0)
 {
 	struct task_struct *tsk[I915_NUM_ENGINES] = {};
-	struct preempt_smoke arg[I915_NUM_ENGINES];
+	struct preempt_smoke *arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	unsigned long count;
 	int err = 0;
 
+	arg = kmalloc_array(I915_NUM_ENGINES, sizeof(*arg), GFP_KERNEL);
+	if (!arg)
+		return -ENOMEM;
+
 	for_each_engine(engine, smoke->gt, id) {
 		arg[id] = *smoke;
 		arg[id].engine = engine;
@@ -3574,7 +3578,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 			arg[id].batch = NULL;
 		arg[id].count = 0;
 
-		tsk[id] = kthread_run(smoke_crescendo_thread, &arg,
+		tsk[id] = kthread_run(smoke_crescendo_thread, arg,
 				      "igt/smoke:%d", id);
 		if (IS_ERR(tsk[id])) {
 			err = PTR_ERR(tsk[id]);
@@ -3603,6 +3607,8 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 
 	pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n",
 		count, flags, smoke->gt->info.num_engines, smoke->ncontext);
+
+	kfree(arg);
 	return 0;
 }
 
@@ -3676,7 +3682,7 @@ static int live_preempt_smoke(void *arg)
 	}
 
 	for (n = 0; n < smoke.ncontext; n++) {
-		smoke.contexts[n] = kernel_context(smoke.gt->i915);
+		smoke.contexts[n] = kernel_context(smoke.gt->i915, NULL);
 		if (!smoke.contexts[n])
 			goto err_ctx;
 	}
@@ -3727,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve));
 
 	for (n = 0; n < nctx; n++) {
-		ve[n] = intel_execlists_create_virtual(siblings, nsibling);
+		ve[n] = intel_engine_create_virtual(siblings, nsibling);
 		if (IS_ERR(ve[n])) {
 			err = PTR_ERR(ve[n]);
 			nctx = n;
@@ -3923,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ve = intel_execlists_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_close;
@@ -4054,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt,
 		i915_request_add(rq);
 	}
 
-	ce = intel_execlists_create_virtual(siblings, nsibling);
+	ce = intel_engine_create_virtual(siblings, nsibling);
 	if (IS_ERR(ce)) {
 		err = PTR_ERR(ce);
 		goto out;
@@ -4106,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt,
 
 	/* XXX We do not handle oversubscription and fairness with normal rq */
 	for (n = 0; n < nsibling; n++) {
-		ce = intel_execlists_create_virtual(siblings, nsibling);
+		ce = intel_engine_create_virtual(siblings, nsibling);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			goto out;
@@ -4208,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 	if (err)
 		goto out_scratch;
 
-	ve = intel_execlists_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_scratch;
@@ -4328,234 +4334,6 @@ static int live_virtual_preserved(void *arg)
 	return 0;
 }
 
-static int bond_virtual_engine(struct intel_gt *gt,
-			       unsigned int class,
-			       struct intel_engine_cs **siblings,
-			       unsigned int nsibling,
-			       unsigned int flags)
-#define BOND_SCHEDULE BIT(0)
-{
-	struct intel_engine_cs *master;
-	struct i915_request *rq[16];
-	enum intel_engine_id id;
-	struct igt_spinner spin;
-	unsigned long n;
-	int err;
-
-	/*
-	 * A set of bonded requests is intended to be run concurrently
-	 * across a number of engines. We use one request per-engine
-	 * and a magic fence to schedule each of the bonded requests
-	 * at the same time. A consequence of our current scheduler is that
-	 * we only move requests to the HW ready queue when the request
-	 * becomes ready, that is when all of its prerequisite fences have
-	 * been signaled. As one of those fences is the master submit fence,
-	 * there is a delay on all secondary fences as the HW may be
-	 * currently busy. Equally, as all the requests are independent,
-	 * they may have other fences that delay individual request
-	 * submission to HW. Ergo, we do not guarantee that all requests are
-	 * immediately submitted to HW at the same time, just that if the
-	 * rules are abided by, they are ready at the same time as the
-	 * first is submitted. Userspace can embed semaphores in its batch
-	 * to ensure parallel execution of its phases as it requires.
-	 * Though naturally it gets requested that perhaps the scheduler should
-	 * take care of parallel execution, even across preemption events on
-	 * different HW. (The proper answer is of course "lalalala".)
-	 *
-	 * With the submit-fence, we have identified three possible phases
-	 * of synchronisation depending on the master fence: queued (not
-	 * ready), executing, and signaled. The first two are quite simple
-	 * and checked below. However, the signaled master fence handling is
-	 * contentious. Currently we do not distinguish between a signaled
-	 * fence and an expired fence, as once signaled it does not convey
-	 * any information about the previous execution. It may even be freed
-	 * and hence checking later it may not exist at all. Ergo we currently
-	 * do not apply the bonding constraint for an already signaled fence,
-	 * as our expectation is that it should not constrain the secondaries
-	 * and is outside of the scope of the bonded request API (i.e. all
-	 * userspace requests are meant to be running in parallel). As
-	 * it imposes no constraint, and is effectively a no-op, we do not
-	 * check below as normal execution flows are checked extensively above.
-	 *
-	 * XXX Is the degenerate handling of signaled submit fences the
-	 * expected behaviour for userpace?
-	 */
-
-	GEM_BUG_ON(nsibling >= ARRAY_SIZE(rq) - 1);
-
-	if (igt_spinner_init(&spin, gt))
-		return -ENOMEM;
-
-	err = 0;
-	rq[0] = ERR_PTR(-ENOMEM);
-	for_each_engine(master, gt, id) {
-		struct i915_sw_fence fence = {};
-		struct intel_context *ce;
-
-		if (master->class == class)
-			continue;
-
-		ce = intel_context_create(master);
-		if (IS_ERR(ce)) {
-			err = PTR_ERR(ce);
-			goto out;
-		}
-
-		memset_p((void *)rq, ERR_PTR(-EINVAL), ARRAY_SIZE(rq));
-
-		rq[0] = igt_spinner_create_request(&spin, ce, MI_NOOP);
-		intel_context_put(ce);
-		if (IS_ERR(rq[0])) {
-			err = PTR_ERR(rq[0]);
-			goto out;
-		}
-		i915_request_get(rq[0]);
-
-		if (flags & BOND_SCHEDULE) {
-			onstack_fence_init(&fence);
-			err = i915_sw_fence_await_sw_fence_gfp(&rq[0]->submit,
-							       &fence,
-							       GFP_KERNEL);
-		}
-
-		i915_request_add(rq[0]);
-		if (err < 0)
-			goto out;
-
-		if (!(flags & BOND_SCHEDULE) &&
-		    !igt_wait_for_spinner(&spin, rq[0])) {
-			err = -EIO;
-			goto out;
-		}
-
-		for (n = 0; n < nsibling; n++) {
-			struct intel_context *ve;
-
-			ve = intel_execlists_create_virtual(siblings, nsibling);
-			if (IS_ERR(ve)) {
-				err = PTR_ERR(ve);
-				onstack_fence_fini(&fence);
-				goto out;
-			}
-
-			err = intel_virtual_engine_attach_bond(ve->engine,
-							       master,
-							       siblings[n]);
-			if (err) {
-				intel_context_put(ve);
-				onstack_fence_fini(&fence);
-				goto out;
-			}
-
-			err = intel_context_pin(ve);
-			intel_context_put(ve);
-			if (err) {
-				onstack_fence_fini(&fence);
-				goto out;
-			}
-
-			rq[n + 1] = i915_request_create(ve);
-			intel_context_unpin(ve);
-			if (IS_ERR(rq[n + 1])) {
-				err = PTR_ERR(rq[n + 1]);
-				onstack_fence_fini(&fence);
-				goto out;
-			}
-			i915_request_get(rq[n + 1]);
-
-			err = i915_request_await_execution(rq[n + 1],
-							   &rq[0]->fence,
-							   ve->engine->bond_execute);
-			i915_request_add(rq[n + 1]);
-			if (err < 0) {
-				onstack_fence_fini(&fence);
-				goto out;
-			}
-		}
-		onstack_fence_fini(&fence);
-		intel_engine_flush_submission(master);
-		igt_spinner_end(&spin);
-
-		if (i915_request_wait(rq[0], 0, HZ / 10) < 0) {
-			pr_err("Master request did not execute (on %s)!\n",
-			       rq[0]->engine->name);
-			err = -EIO;
-			goto out;
-		}
-
-		for (n = 0; n < nsibling; n++) {
-			if (i915_request_wait(rq[n + 1], 0,
-					      MAX_SCHEDULE_TIMEOUT) < 0) {
-				err = -EIO;
-				goto out;
-			}
-
-			if (rq[n + 1]->engine != siblings[n]) {
-				pr_err("Bonded request did not execute on target engine: expected %s, used %s; master was %s\n",
-				       siblings[n]->name,
-				       rq[n + 1]->engine->name,
-				       rq[0]->engine->name);
-				err = -EINVAL;
-				goto out;
-			}
-		}
-
-		for (n = 0; !IS_ERR(rq[n]); n++)
-			i915_request_put(rq[n]);
-		rq[0] = ERR_PTR(-ENOMEM);
-	}
-
-out:
-	for (n = 0; !IS_ERR(rq[n]); n++)
-		i915_request_put(rq[n]);
-	if (igt_flush_test(gt->i915))
-		err = -EIO;
-
-	igt_spinner_fini(&spin);
-	return err;
-}
-
-static int live_virtual_bond(void *arg)
-{
-	static const struct phase {
-		const char *name;
-		unsigned int flags;
-	} phases[] = {
-		{ "", 0 },
-		{ "schedule", BOND_SCHEDULE },
-		{ },
-	};
-	struct intel_gt *gt = arg;
-	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
-	unsigned int class;
-	int err;
-
-	if (intel_uc_uses_guc_submission(&gt->uc))
-		return 0;
-
-	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
-		const struct phase *p;
-		int nsibling;
-
-		nsibling = select_siblings(gt, class, siblings);
-		if (nsibling < 2)
-			continue;
-
-		for (p = phases; p->name; p++) {
-			err = bond_virtual_engine(gt,
-						  class, siblings, nsibling,
-						  p->flags);
-			if (err) {
-				pr_err("%s(%s): failed class=%d, nsibling=%d, err=%d\n",
-				       __func__, p->name, class, nsibling, err);
-				return err;
-			}
-		}
-	}
-
-	return 0;
-}
-
 static int reset_virtual_engine(struct intel_gt *gt,
 				struct intel_engine_cs **siblings,
 				unsigned int nsibling)
@@ -4576,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ve = intel_execlists_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_spin;
@@ -4606,13 +4384,13 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	if (err)
 		goto out_heartbeat;
 
-	engine->execlists.tasklet.callback(&engine->execlists.tasklet);
+	engine->sched_engine->tasklet.callback(&engine->sched_engine->tasklet);
 	GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 	/* Fake a preemption event; failed of course */
-	spin_lock_irq(&engine->active.lock);
+	spin_lock_irq(&engine->sched_engine->lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock_irq(&engine->active.lock);
+	spin_unlock_irq(&engine->sched_engine->lock);
 	GEM_BUG_ON(rq->engine != engine);
 
 	/* Reset the engine while keeping our active request on hold */
@@ -4721,7 +4499,6 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_virtual_mask),
 		SUBTEST(live_virtual_preserved),
 		SUBTEST(live_virtual_slice),
-		SUBTEST(live_virtual_bond),
 		SUBTEST(live_virtual_reset),
 	};
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 853246fad05f..2c1ed32ca5ac 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -17,6 +17,8 @@
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_atomic.h"
+#include "selftests/igt_spinner.h"
+#include "selftests/intel_scheduler_helpers.h"
 
 #include "selftests/mock_drm.h"
 
@@ -42,7 +44,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	memset(h, 0, sizeof(*h));
 	h->gt = gt;
 
-	h->ctx = kernel_context(gt->i915);
+	h->ctx = kernel_context(gt->i915, NULL);
 	if (IS_ERR(h->ctx))
 		return PTR_ERR(h->ctx);
 
@@ -378,6 +380,7 @@ static int igt_reset_nop(void *arg)
 			ce = intel_context_create(engine);
 			if (IS_ERR(ce)) {
 				err = PTR_ERR(ce);
+				pr_err("[%s] Create context failed: %d!\n", engine->name, err);
 				break;
 			}
 
@@ -387,6 +390,8 @@ static int igt_reset_nop(void *arg)
 				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
+					pr_err("[%s] Create request failed: %d!\n",
+					       engine->name, err);
 					break;
 				}
 
@@ -401,24 +406,31 @@ static int igt_reset_nop(void *arg)
 		igt_global_reset_unlock(gt);
 
 		if (intel_gt_is_wedged(gt)) {
+			pr_err("[%s] GT is wedged!\n", engine->name);
 			err = -EIO;
 			break;
 		}
 
 		if (i915_reset_count(global) != reset_count + ++count) {
-			pr_err("Full GPU reset not recorded!\n");
+			pr_err("[%s] Reset not recorded: %d vs %d + %d!\n",
+			       engine->name, i915_reset_count(global), reset_count, count);
 			err = -EINVAL;
 			break;
 		}
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	if (igt_flush_test(gt->i915))
+	if (igt_flush_test(gt->i915)) {
+		pr_err("Post flush failed: %d!\n", err);
 		err = -EIO;
+	}
+
 	return err;
 }
 
@@ -440,9 +452,19 @@ static int igt_reset_nop_engine(void *arg)
 		IGT_TIMEOUT(end_time);
 		int err;
 
+		if (intel_engine_uses_guc(engine)) {
+			/* Engine level resets are triggered by GuC when a hang
+			 * is detected. They can't be triggered by the KMD any
+			 * more. Thus a nop batch cannot be used as a reset test
+			 */
+			continue;
+		}
+
 		ce = intel_context_create(engine);
-		if (IS_ERR(ce))
+		if (IS_ERR(ce)) {
+			pr_err("[%s] Create context failed: %pe!\n", engine->name, ce);
 			return PTR_ERR(ce);
+		}
 
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
@@ -549,9 +571,15 @@ static int igt_reset_fail_engine(void *arg)
 		IGT_TIMEOUT(end_time);
 		int err;
 
+		/* Can't manually break the reset if i915 doesn't perform it */
+		if (intel_engine_uses_guc(engine))
+			continue;
+
 		ce = intel_context_create(engine);
-		if (IS_ERR(ce))
+		if (IS_ERR(ce)) {
+			pr_err("[%s] Create context failed: %pe!\n", engine->name, ce);
 			return PTR_ERR(ce);
+		}
 
 		st_engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
@@ -686,8 +714,12 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
 		unsigned long count;
+		bool using_guc = intel_engine_uses_guc(engine);
 		IGT_TIMEOUT(end_time);
 
+		if (using_guc && !active)
+			continue;
+
 		if (active && !intel_engine_can_store_dword(engine))
 			continue;
 
@@ -705,13 +737,24 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		count = 0;
 		do {
-			if (active) {
-				struct i915_request *rq;
+			struct i915_request *rq = NULL;
+			struct intel_selftest_saved_policy saved;
+			int err2;
+
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				break;
+			}
 
+			if (active) {
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					break;
+					pr_err("[%s] Create hang request failed: %d!\n",
+					       engine->name, err);
+					goto restore;
 				}
 
 				i915_request_get(rq);
@@ -727,34 +770,59 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 					i915_request_put(rq);
 					err = -EIO;
-					break;
+					goto restore;
 				}
+			}
 
-				i915_request_put(rq);
+			if (!using_guc) {
+				err = intel_engine_reset(engine, NULL);
+				if (err) {
+					pr_err("intel_engine_reset(%s) failed, err:%d\n",
+					       engine->name, err);
+					goto skip;
+				}
 			}
 
-			err = intel_engine_reset(engine, NULL);
-			if (err) {
-				pr_err("intel_engine_reset(%s) failed, err:%d\n",
-				       engine->name, err);
-				break;
+			if (rq) {
+				/* Ensure the reset happens and kills the engine */
+				err = intel_selftest_wait_for_rq(rq);
+				if (err)
+					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
+					       engine->name, rq->fence.context,
+					       rq->fence.seqno, rq->context->guc_id, err);
 			}
 
+skip:
+			if (rq)
+				i915_request_put(rq);
+
 			if (i915_reset_count(global) != reset_count) {
 				pr_err("Full GPU reset recorded! (engine reset expected)\n");
 				err = -EINVAL;
-				break;
+				goto restore;
 			}
 
-			if (i915_reset_engine_count(global, engine) !=
-			    ++reset_engine_count) {
-				pr_err("%s engine reset not recorded!\n",
-				       engine->name);
-				err = -EINVAL;
-				break;
+			/* GuC based resets are not logged per engine */
+			if (!using_guc) {
+				if (i915_reset_engine_count(global, engine) !=
+				    ++reset_engine_count) {
+					pr_err("%s engine reset not recorded!\n",
+					       engine->name);
+					err = -EINVAL;
+					goto restore;
+				}
 			}
 
 			count++;
+
+restore:
+			err2 = intel_selftest_restore_policy(engine, &saved);
+			if (err2)
+				pr_err("[%s] Restore policy failed: %d!\n", engine->name, err);
+			if (err == 0)
+				err = err2;
+			if (err)
+				break;
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		st_engine_heartbeat_enable(engine);
@@ -765,12 +833,16 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			break;
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
 
-	if (intel_gt_is_wedged(gt))
+	if (intel_gt_is_wedged(gt)) {
+		pr_err("GT is wedged!\n");
 		err = -EIO;
+	}
 
 	if (active)
 		hang_fini(&h);
@@ -807,7 +879,7 @@ static int active_request_put(struct i915_request *rq)
 	if (!rq)
 		return 0;
 
-	if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
+	if (i915_request_wait(rq, 0, 10 * HZ) < 0) {
 		GEM_TRACE("%s timed out waiting for completion of fence %llx:%lld\n",
 			  rq->engine->name,
 			  rq->fence.context,
@@ -837,6 +909,7 @@ static int active_engine(void *data)
 		ce[count] = intel_context_create(engine);
 		if (IS_ERR(ce[count])) {
 			err = PTR_ERR(ce[count]);
+			pr_err("[%s] Create context #%ld failed: %d!\n", engine->name, count, err);
 			while (--count)
 				intel_context_put(ce[count]);
 			return err;
@@ -852,23 +925,26 @@ static int active_engine(void *data)
 		new = intel_context_create_request(ce[idx]);
 		if (IS_ERR(new)) {
 			err = PTR_ERR(new);
+			pr_err("[%s] Create request #%d failed: %d!\n", engine->name, idx, err);
 			break;
 		}
 
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 
-		if (engine->schedule && arg->flags & TEST_PRIORITY) {
+		if (engine->sched_engine->schedule && arg->flags & TEST_PRIORITY) {
 			struct i915_sched_attr attr = {
 				.priority =
 					i915_prandom_u32_max_state(512, &prng),
 			};
-			engine->schedule(rq[idx], &attr);
+			engine->sched_engine->schedule(rq[idx], &attr);
 		}
 
 		err = active_request_put(old);
-		if (err)
+		if (err) {
+			pr_err("[%s] Request put failed: %d!\n", engine->name, err);
 			break;
+		}
 
 		cond_resched();
 	}
@@ -876,6 +952,9 @@ static int active_engine(void *data)
 	for (count = 0; count < ARRAY_SIZE(rq); count++) {
 		int err__ = active_request_put(rq[count]);
 
+		if (err)
+			pr_err("[%s] Request put #%ld failed: %d!\n", engine->name, count, err);
+
 		/* Keep the first error */
 		if (!err)
 			err = err__;
@@ -916,10 +995,13 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
+		bool using_guc = intel_engine_uses_guc(engine);
 		IGT_TIMEOUT(end_time);
 
-		if (flags & TEST_ACTIVE &&
-		    !intel_engine_can_store_dword(engine))
+		if (flags & TEST_ACTIVE) {
+			if (!intel_engine_can_store_dword(engine))
+				continue;
+		} else if (using_guc)
 			continue;
 
 		if (!wait_for_idle(engine)) {
@@ -949,6 +1031,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 					  "igt/%s", other->name);
 			if (IS_ERR(tsk)) {
 				err = PTR_ERR(tsk);
+				pr_err("[%s] Thread spawn failed: %d!\n", engine->name, err);
 				goto unwind;
 			}
 
@@ -958,16 +1041,27 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		yield(); /* start all threads before we begin */
 
-		st_engine_heartbeat_disable(engine);
+		st_engine_heartbeat_disable_no_pm(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
+			struct intel_selftest_saved_policy saved;
+			int err2;
+
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				break;
+			}
 
 			if (flags & TEST_ACTIVE) {
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					break;
+					pr_err("[%s] Create hang request failed: %d!\n",
+					       engine->name, err);
+					goto restore;
 				}
 
 				i915_request_get(rq);
@@ -983,32 +1077,44 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 					i915_request_put(rq);
 					err = -EIO;
-					break;
+					goto restore;
 				}
+			} else {
+				intel_engine_pm_get(engine);
 			}
 
-			err = intel_engine_reset(engine, NULL);
-			if (err) {
-				pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
-				       engine->name, test_name, err);
-				break;
+			if (!using_guc) {
+				err = intel_engine_reset(engine, NULL);
+				if (err) {
+					pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
+					       engine->name, test_name, err);
+					goto restore;
+				}
+			}
+
+			if (rq) {
+				/* Ensure the reset happens and kills the engine */
+				err = intel_selftest_wait_for_rq(rq);
+				if (err)
+					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
+					       engine->name, rq->fence.context,
+					       rq->fence.seqno, rq->context->guc_id, err);
 			}
 
 			count++;
 
 			if (rq) {
 				if (rq->fence.error != -EIO) {
-					pr_err("i915_reset_engine(%s:%s):"
-					       " failed to reset request %llx:%lld\n",
+					pr_err("i915_reset_engine(%s:%s): failed to reset request %lld:%lld [0x%04X]\n",
 					       engine->name, test_name,
 					       rq->fence.context,
-					       rq->fence.seqno);
+					       rq->fence.seqno, rq->context->guc_id);
 					i915_request_put(rq);
 
 					GEM_TRACE_DUMP();
 					intel_gt_set_wedged(gt);
 					err = -EIO;
-					break;
+					goto restore;
 				}
 
 				if (i915_request_wait(rq, 0, HZ / 5) < 0) {
@@ -1027,12 +1133,15 @@ static int __igt_reset_engines(struct intel_gt *gt,
 					GEM_TRACE_DUMP();
 					intel_gt_set_wedged(gt);
 					err = -EIO;
-					break;
+					goto restore;
 				}
 
 				i915_request_put(rq);
 			}
 
+			if (!(flags & TEST_ACTIVE))
+				intel_engine_pm_put(engine);
+
 			if (!(flags & TEST_SELF) && !wait_for_idle(engine)) {
 				struct drm_printer p =
 					drm_info_printer(gt->i915->drm.dev);
@@ -1044,22 +1153,34 @@ static int __igt_reset_engines(struct intel_gt *gt,
 						  "%s\n", engine->name);
 
 				err = -EIO;
-				break;
+				goto restore;
 			}
+
+restore:
+			err2 = intel_selftest_restore_policy(engine, &saved);
+			if (err2)
+				pr_err("[%s] Restore policy failed: %d!\n", engine->name, err2);
+			if (err == 0)
+				err = err2;
+			if (err)
+				break;
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		st_engine_heartbeat_enable(engine);
+		st_engine_heartbeat_enable_no_pm(engine);
 
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
 
-		reported = i915_reset_engine_count(global, engine);
-		reported -= threads[engine->id].resets;
-		if (reported != count) {
-			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
-			       engine->name, test_name, count, reported);
-			if (!err)
-				err = -EINVAL;
+		/* GuC based resets are not logged per engine */
+		if (!using_guc) {
+			reported = i915_reset_engine_count(global, engine);
+			reported -= threads[engine->id].resets;
+			if (reported != count) {
+				pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
+				       engine->name, test_name, count, reported);
+				if (!err)
+					err = -EINVAL;
+			}
 		}
 
 unwind:
@@ -1078,15 +1199,18 @@ unwind:
 			}
 			put_task_struct(threads[tmp].task);
 
-			if (other->uabi_class != engine->uabi_class &&
-			    threads[tmp].resets !=
-			    i915_reset_engine_count(global, other)) {
-				pr_err("Innocent engine %s was reset (count=%ld)\n",
-				       other->name,
-				       i915_reset_engine_count(global, other) -
-				       threads[tmp].resets);
-				if (!err)
-					err = -EINVAL;
+			/* GuC based resets are not logged per engine */
+			if (!using_guc) {
+				if (other->uabi_class != engine->uabi_class &&
+				    threads[tmp].resets !=
+				    i915_reset_engine_count(global, other)) {
+					pr_err("Innocent engine %s was reset (count=%ld)\n",
+					       other->name,
+					       i915_reset_engine_count(global, other) -
+					       threads[tmp].resets);
+					if (!err)
+						err = -EINVAL;
+				}
 			}
 		}
 
@@ -1101,8 +1225,10 @@ unwind:
 			break;
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
 
 	if (intel_gt_is_wedged(gt))
@@ -1180,12 +1306,15 @@ static int igt_reset_wait(void *arg)
 	igt_global_reset_lock(gt);
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		goto unlock;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto fini;
 	}
 
@@ -1310,12 +1439,15 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	/* Check that we can recover an unbind stuck on a hanging request */
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	obj = i915_gem_object_create_internal(gt->i915, SZ_1M);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
+		pr_err("[%s] Create object failed: %d!\n", engine->name, err);
 		goto fini;
 	}
 
@@ -1330,12 +1462,14 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	arg.vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(arg.vma)) {
 		err = PTR_ERR(arg.vma);
+		pr_err("[%s] VMA instance failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
@@ -1347,6 +1481,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	err = i915_vma_pin(arg.vma, 0, 0, pin_flags);
 	if (err) {
 		i915_request_add(rq);
+		pr_err("[%s] VMA pin failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
@@ -1363,8 +1498,14 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	i915_vma_lock(arg.vma);
 	err = i915_request_await_object(rq, arg.vma->obj,
 					flags & EXEC_OBJECT_WRITE);
-	if (err == 0)
+	if (err == 0) {
 		err = i915_vma_move_to_active(arg.vma, rq, flags);
+		if (err)
+			pr_err("[%s] Move to active failed: %d!\n", engine->name, err);
+	} else {
+		pr_err("[%s] Request await failed: %d!\n", engine->name, err);
+	}
+
 	i915_vma_unlock(arg.vma);
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
@@ -1392,6 +1533,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	tsk = kthread_run(fn, &arg, "igt/evict_vma");
 	if (IS_ERR(tsk)) {
 		err = PTR_ERR(tsk);
+		pr_err("[%s] Thread spawn failed: %d!\n", engine->name, err);
 		tsk = NULL;
 		goto out_reset;
 	}
@@ -1508,17 +1650,29 @@ static int igt_reset_queue(void *arg)
 		goto unlock;
 
 	for_each_engine(engine, gt, id) {
+		struct intel_selftest_saved_policy saved;
 		struct i915_request *prev;
 		IGT_TIMEOUT(end_time);
 		unsigned int count;
+		bool using_guc = intel_engine_uses_guc(engine);
 
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
+		if (using_guc) {
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				goto fini;
+			}
+		}
+
 		prev = hang_create_request(&h, engine);
 		if (IS_ERR(prev)) {
 			err = PTR_ERR(prev);
-			goto fini;
+			pr_err("[%s] Create 'prev' hang request failed: %d!\n", engine->name, err);
+			goto restore;
 		}
 
 		i915_request_get(prev);
@@ -1532,7 +1686,8 @@ static int igt_reset_queue(void *arg)
 			rq = hang_create_request(&h, engine);
 			if (IS_ERR(rq)) {
 				err = PTR_ERR(rq);
-				goto fini;
+				pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
+				goto restore;
 			}
 
 			i915_request_get(rq);
@@ -1557,7 +1712,7 @@ static int igt_reset_queue(void *arg)
 
 				GEM_TRACE_DUMP();
 				intel_gt_set_wedged(gt);
-				goto fini;
+				goto restore;
 			}
 
 			if (!wait_until_running(&h, prev)) {
@@ -1575,7 +1730,7 @@ static int igt_reset_queue(void *arg)
 				intel_gt_set_wedged(gt);
 
 				err = -EIO;
-				goto fini;
+				goto restore;
 			}
 
 			reset_count = fake_hangcheck(gt, BIT(id));
@@ -1586,7 +1741,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			if (rq->fence.error) {
@@ -1595,7 +1750,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			if (i915_reset_count(global) == reset_count) {
@@ -1603,7 +1758,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			i915_request_put(prev);
@@ -1618,9 +1773,24 @@ static int igt_reset_queue(void *arg)
 
 		i915_request_put(prev);
 
-		err = igt_flush_test(gt->i915);
+restore:
+		if (using_guc) {
+			int err2 = intel_selftest_restore_policy(engine, &saved);
+
+			if (err2)
+				pr_err("%s:%d> [%s] Restore policy failed: %d!\n",
+				       __func__, __LINE__, engine->name, err2);
+			if (err == 0)
+				err = err2;
+		}
 		if (err)
+			goto fini;
+
+		err = igt_flush_test(gt->i915);
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
 
 fini:
@@ -1653,12 +1823,15 @@ static int igt_handle_error(void *arg)
 		return 0;
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto err_fini;
 	}
 
@@ -1702,7 +1875,7 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 				     const struct igt_atomic_section *p,
 				     const char *mode)
 {
-	struct tasklet_struct * const t = &engine->execlists.tasklet;
+	struct tasklet_struct * const t = &engine->sched_engine->tasklet;
 	int err;
 
 	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
@@ -1743,12 +1916,15 @@ static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 		return err;
 
 	err = hang_init(&h, engine->gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 3119016d9910..b0977a3b699b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -49,7 +49,7 @@ static int wait_for_submit(struct intel_engine_cs *engine,
 			   unsigned long timeout)
 {
 	/* Ignore our own attempts to suppress excess tasklets */
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	tasklet_hi_schedule(&engine->sched_engine->tasklet);
 
 	timeout += jiffies;
 	do {
@@ -1613,12 +1613,12 @@ static void garbage_reset(struct intel_engine_cs *engine,
 
 	local_bh_disable();
 	if (!test_and_set_bit(bit, lock)) {
-		tasklet_disable(&engine->execlists.tasklet);
+		tasklet_disable(&engine->sched_engine->tasklet);
 
 		if (!rq->fence.error)
 			__intel_engine_reset_bh(engine, NULL);
 
-		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_enable(&engine->sched_engine->tasklet);
 		clear_and_wake_up_bit(bit, lock);
 	}
 	local_bh_enable();
diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c
new file mode 100644
index 000000000000..12ef2837c89b
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c
@@ -0,0 +1,669 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/sort.h>
+
+#include "selftests/i915_random.h"
+
+static const unsigned int sizes[] = {
+	SZ_4K,
+	SZ_64K,
+	SZ_2M,
+	CHUNK_SZ - SZ_4K,
+	CHUNK_SZ,
+	CHUNK_SZ + SZ_4K,
+	SZ_64M,
+};
+
+static struct drm_i915_gem_object *
+create_lmem_or_internal(struct drm_i915_private *i915, size_t size)
+{
+	struct drm_i915_gem_object *obj;
+
+	obj = i915_gem_object_create_lmem(i915, size, 0);
+	if (!IS_ERR(obj))
+		return obj;
+
+	return i915_gem_object_create_internal(i915, size);
+}
+
+static int copy(struct intel_migrate *migrate,
+		int (*fn)(struct intel_migrate *migrate,
+			  struct i915_gem_ww_ctx *ww,
+			  struct drm_i915_gem_object *src,
+			  struct drm_i915_gem_object *dst,
+			  struct i915_request **out),
+		u32 sz, struct rnd_state *prng)
+{
+	struct drm_i915_private *i915 = migrate->context->engine->i915;
+	struct drm_i915_gem_object *src, *dst;
+	struct i915_request *rq;
+	struct i915_gem_ww_ctx ww;
+	u32 *vaddr;
+	int err = 0;
+	int i;
+
+	src = create_lmem_or_internal(i915, sz);
+	if (IS_ERR(src))
+		return 0;
+
+	dst = i915_gem_object_create_internal(i915, sz);
+	if (IS_ERR(dst))
+		goto err_free_src;
+
+	for_i915_gem_ww(&ww, err, true) {
+		err = i915_gem_object_lock(src, &ww);
+		if (err)
+			continue;
+
+		err = i915_gem_object_lock(dst, &ww);
+		if (err)
+			continue;
+
+		vaddr = i915_gem_object_pin_map(src, I915_MAP_WC);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			continue;
+		}
+
+		for (i = 0; i < sz / sizeof(u32); i++)
+			vaddr[i] = i;
+		i915_gem_object_flush_map(src);
+
+		vaddr = i915_gem_object_pin_map(dst, I915_MAP_WC);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto unpin_src;
+		}
+
+		for (i = 0; i < sz / sizeof(u32); i++)
+			vaddr[i] = ~i;
+		i915_gem_object_flush_map(dst);
+
+		err = fn(migrate, &ww, src, dst, &rq);
+		if (!err)
+			continue;
+
+		if (err != -EDEADLK && err != -EINTR && err != -ERESTARTSYS)
+			pr_err("%ps failed, size: %u\n", fn, sz);
+		if (rq) {
+			i915_request_wait(rq, 0, HZ);
+			i915_request_put(rq);
+		}
+		i915_gem_object_unpin_map(dst);
+unpin_src:
+		i915_gem_object_unpin_map(src);
+	}
+	if (err)
+		goto err_out;
+
+	if (rq) {
+		if (i915_request_wait(rq, 0, HZ) < 0) {
+			pr_err("%ps timed out, size: %u\n", fn, sz);
+			err = -ETIME;
+		}
+		i915_request_put(rq);
+	}
+
+	for (i = 0; !err && i < sz / PAGE_SIZE; i++) {
+		int x = i * 1024 + i915_prandom_u32_max_state(1024, prng);
+
+		if (vaddr[x] != x) {
+			pr_err("%ps failed, size: %u, offset: %zu\n",
+			       fn, sz, x * sizeof(u32));
+			igt_hexdump(vaddr + i * 1024, 4096);
+			err = -EINVAL;
+		}
+	}
+
+	i915_gem_object_unpin_map(dst);
+	i915_gem_object_unpin_map(src);
+
+err_out:
+	i915_gem_object_put(dst);
+err_free_src:
+	i915_gem_object_put(src);
+
+	return err;
+}
+
+static int clear(struct intel_migrate *migrate,
+		 int (*fn)(struct intel_migrate *migrate,
+			   struct i915_gem_ww_ctx *ww,
+			   struct drm_i915_gem_object *obj,
+			   u32 value,
+			   struct i915_request **out),
+		 u32 sz, struct rnd_state *prng)
+{
+	struct drm_i915_private *i915 = migrate->context->engine->i915;
+	struct drm_i915_gem_object *obj;
+	struct i915_request *rq;
+	struct i915_gem_ww_ctx ww;
+	u32 *vaddr;
+	int err = 0;
+	int i;
+
+	obj = create_lmem_or_internal(i915, sz);
+	if (IS_ERR(obj))
+		return 0;
+
+	for_i915_gem_ww(&ww, err, true) {
+		err = i915_gem_object_lock(obj, &ww);
+		if (err)
+			continue;
+
+		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			continue;
+		}
+
+		for (i = 0; i < sz / sizeof(u32); i++)
+			vaddr[i] = ~i;
+		i915_gem_object_flush_map(obj);
+
+		err = fn(migrate, &ww, obj, sz, &rq);
+		if (!err)
+			continue;
+
+		if (err != -EDEADLK && err != -EINTR && err != -ERESTARTSYS)
+			pr_err("%ps failed, size: %u\n", fn, sz);
+		if (rq) {
+			i915_request_wait(rq, 0, HZ);
+			i915_request_put(rq);
+		}
+		i915_gem_object_unpin_map(obj);
+	}
+	if (err)
+		goto err_out;
+
+	if (rq) {
+		if (i915_request_wait(rq, 0, HZ) < 0) {
+			pr_err("%ps timed out, size: %u\n", fn, sz);
+			err = -ETIME;
+		}
+		i915_request_put(rq);
+	}
+
+	for (i = 0; !err && i < sz / PAGE_SIZE; i++) {
+		int x = i * 1024 + i915_prandom_u32_max_state(1024, prng);
+
+		if (vaddr[x] != sz) {
+			pr_err("%ps failed, size: %u, offset: %zu\n",
+			       fn, sz, x * sizeof(u32));
+			igt_hexdump(vaddr + i * 1024, 4096);
+			err = -EINVAL;
+		}
+	}
+
+	i915_gem_object_unpin_map(obj);
+err_out:
+	i915_gem_object_put(obj);
+
+	return err;
+}
+
+static int __migrate_copy(struct intel_migrate *migrate,
+			  struct i915_gem_ww_ctx *ww,
+			  struct drm_i915_gem_object *src,
+			  struct drm_i915_gem_object *dst,
+			  struct i915_request **out)
+{
+	return intel_migrate_copy(migrate, ww, NULL,
+				  src->mm.pages->sgl, src->cache_level,
+				  i915_gem_object_is_lmem(src),
+				  dst->mm.pages->sgl, dst->cache_level,
+				  i915_gem_object_is_lmem(dst),
+				  out);
+}
+
+static int __global_copy(struct intel_migrate *migrate,
+			 struct i915_gem_ww_ctx *ww,
+			 struct drm_i915_gem_object *src,
+			 struct drm_i915_gem_object *dst,
+			 struct i915_request **out)
+{
+	return intel_context_migrate_copy(migrate->context, NULL,
+					  src->mm.pages->sgl, src->cache_level,
+					  i915_gem_object_is_lmem(src),
+					  dst->mm.pages->sgl, dst->cache_level,
+					  i915_gem_object_is_lmem(dst),
+					  out);
+}
+
+static int
+migrate_copy(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+	return copy(migrate, __migrate_copy, sz, prng);
+}
+
+static int
+global_copy(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+	return copy(migrate, __global_copy, sz, prng);
+}
+
+static int __migrate_clear(struct intel_migrate *migrate,
+			   struct i915_gem_ww_ctx *ww,
+			   struct drm_i915_gem_object *obj,
+			   u32 value,
+			   struct i915_request **out)
+{
+	return intel_migrate_clear(migrate, ww, NULL,
+				   obj->mm.pages->sgl,
+				   obj->cache_level,
+				   i915_gem_object_is_lmem(obj),
+				   value, out);
+}
+
+static int __global_clear(struct intel_migrate *migrate,
+			  struct i915_gem_ww_ctx *ww,
+			  struct drm_i915_gem_object *obj,
+			  u32 value,
+			  struct i915_request **out)
+{
+	return intel_context_migrate_clear(migrate->context, NULL,
+					   obj->mm.pages->sgl,
+					   obj->cache_level,
+					   i915_gem_object_is_lmem(obj),
+					   value, out);
+}
+
+static int
+migrate_clear(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+	return clear(migrate, __migrate_clear, sz, prng);
+}
+
+static int
+global_clear(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+	return clear(migrate, __global_clear, sz, prng);
+}
+
+static int live_migrate_copy(void *arg)
+{
+	struct intel_migrate *migrate = arg;
+	struct drm_i915_private *i915 = migrate->context->engine->i915;
+	I915_RND_STATE(prng);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		int err;
+
+		err = migrate_copy(migrate, sizes[i], &prng);
+		if (err == 0)
+			err = global_copy(migrate, sizes[i], &prng);
+		i915_gem_drain_freed_objects(i915);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int live_migrate_clear(void *arg)
+{
+	struct intel_migrate *migrate = arg;
+	struct drm_i915_private *i915 = migrate->context->engine->i915;
+	I915_RND_STATE(prng);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		int err;
+
+		err = migrate_clear(migrate, sizes[i], &prng);
+		if (err == 0)
+			err = global_clear(migrate, sizes[i], &prng);
+
+		i915_gem_drain_freed_objects(i915);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+struct threaded_migrate {
+	struct intel_migrate *migrate;
+	struct task_struct *tsk;
+	struct rnd_state prng;
+};
+
+static int threaded_migrate(struct intel_migrate *migrate,
+			    int (*fn)(void *arg),
+			    unsigned int flags)
+{
+	const unsigned int n_cpus = num_online_cpus() + 1;
+	struct threaded_migrate *thread;
+	I915_RND_STATE(prng);
+	unsigned int i;
+	int err = 0;
+
+	thread = kcalloc(n_cpus, sizeof(*thread), GFP_KERNEL);
+	if (!thread)
+		return 0;
+
+	for (i = 0; i < n_cpus; ++i) {
+		struct task_struct *tsk;
+
+		thread[i].migrate = migrate;
+		thread[i].prng =
+			I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
+
+		tsk = kthread_run(fn, &thread[i], "igt-%d", i);
+		if (IS_ERR(tsk)) {
+			err = PTR_ERR(tsk);
+			break;
+		}
+
+		get_task_struct(tsk);
+		thread[i].tsk = tsk;
+	}
+
+	msleep(10); /* start all threads before we kthread_stop() */
+
+	for (i = 0; i < n_cpus; ++i) {
+		struct task_struct *tsk = thread[i].tsk;
+		int status;
+
+		if (IS_ERR_OR_NULL(tsk))
+			continue;
+
+		status = kthread_stop(tsk);
+		if (status && !err)
+			err = status;
+
+		put_task_struct(tsk);
+	}
+
+	kfree(thread);
+	return err;
+}
+
+static int __thread_migrate_copy(void *arg)
+{
+	struct threaded_migrate *tm = arg;
+
+	return migrate_copy(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int thread_migrate_copy(void *arg)
+{
+	return threaded_migrate(arg, __thread_migrate_copy, 0);
+}
+
+static int __thread_global_copy(void *arg)
+{
+	struct threaded_migrate *tm = arg;
+
+	return global_copy(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int thread_global_copy(void *arg)
+{
+	return threaded_migrate(arg, __thread_global_copy, 0);
+}
+
+static int __thread_migrate_clear(void *arg)
+{
+	struct threaded_migrate *tm = arg;
+
+	return migrate_clear(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int __thread_global_clear(void *arg)
+{
+	struct threaded_migrate *tm = arg;
+
+	return global_clear(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int thread_migrate_clear(void *arg)
+{
+	return threaded_migrate(arg, __thread_migrate_clear, 0);
+}
+
+static int thread_global_clear(void *arg)
+{
+	return threaded_migrate(arg, __thread_global_clear, 0);
+}
+
+int intel_migrate_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_migrate_copy),
+		SUBTEST(live_migrate_clear),
+		SUBTEST(thread_migrate_copy),
+		SUBTEST(thread_migrate_clear),
+		SUBTEST(thread_global_copy),
+		SUBTEST(thread_global_clear),
+	};
+	struct intel_gt *gt = &i915->gt;
+
+	if (!gt->migrate.context)
+		return 0;
+
+	return i915_subtests(tests, &gt->migrate);
+}
+
+static struct drm_i915_gem_object *
+create_init_lmem_internal(struct intel_gt *gt, size_t sz, bool try_lmem)
+{
+	struct drm_i915_gem_object *obj = NULL;
+	int err;
+
+	if (try_lmem)
+		obj = i915_gem_object_create_lmem(gt->i915, sz, 0);
+
+	if (IS_ERR_OR_NULL(obj)) {
+		obj = i915_gem_object_create_internal(gt->i915, sz);
+		if (IS_ERR(obj))
+			return obj;
+	}
+
+	i915_gem_object_trylock(obj);
+	err = i915_gem_object_pin_pages(obj);
+	if (err) {
+		i915_gem_object_unlock(obj);
+		i915_gem_object_put(obj);
+		return ERR_PTR(err);
+	}
+
+	return obj;
+}
+
+static int wrap_ktime_compare(const void *A, const void *B)
+{
+	const ktime_t *a = A, *b = B;
+
+	return ktime_compare(*a, *b);
+}
+
+static int __perf_clear_blt(struct intel_context *ce,
+			    struct scatterlist *sg,
+			    enum i915_cache_level cache_level,
+			    bool is_lmem,
+			    size_t sz)
+{
+	ktime_t t[5];
+	int pass;
+	int err = 0;
+
+	for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
+		struct i915_request *rq;
+		ktime_t t0, t1;
+
+		t0 = ktime_get();
+
+		err = intel_context_migrate_clear(ce, NULL, sg, cache_level,
+						  is_lmem, 0, &rq);
+		if (rq) {
+			if (i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+		}
+		if (err)
+			break;
+
+		t1 = ktime_get();
+		t[pass] = ktime_sub(t1, t0);
+	}
+	if (err)
+		return err;
+
+	sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
+	pr_info("%s: %zd KiB fill: %lld MiB/s\n",
+		ce->engine->name, sz >> 10,
+		div64_u64(mul_u32_u32(4 * sz,
+				      1000 * 1000 * 1000),
+			  t[1] + 2 * t[2] + t[3]) >> 20);
+	return 0;
+}
+
+static int perf_clear_blt(void *arg)
+{
+	struct intel_gt *gt = arg;
+	static const unsigned long sizes[] = {
+		SZ_4K,
+		SZ_64K,
+		SZ_2M,
+		SZ_64M
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		struct drm_i915_gem_object *dst;
+		int err;
+
+		dst = create_init_lmem_internal(gt, sizes[i], true);
+		if (IS_ERR(dst))
+			return PTR_ERR(dst);
+
+		err = __perf_clear_blt(gt->migrate.context,
+				       dst->mm.pages->sgl,
+				       I915_CACHE_NONE,
+				       i915_gem_object_is_lmem(dst),
+				       sizes[i]);
+
+		i915_gem_object_unlock(dst);
+		i915_gem_object_put(dst);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int __perf_copy_blt(struct intel_context *ce,
+			   struct scatterlist *src,
+			   enum i915_cache_level src_cache_level,
+			   bool src_is_lmem,
+			   struct scatterlist *dst,
+			   enum i915_cache_level dst_cache_level,
+			   bool dst_is_lmem,
+			   size_t sz)
+{
+	ktime_t t[5];
+	int pass;
+	int err = 0;
+
+	for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
+		struct i915_request *rq;
+		ktime_t t0, t1;
+
+		t0 = ktime_get();
+
+		err = intel_context_migrate_copy(ce, NULL,
+						 src, src_cache_level,
+						 src_is_lmem,
+						 dst, dst_cache_level,
+						 dst_is_lmem,
+						 &rq);
+		if (rq) {
+			if (i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+		}
+		if (err)
+			break;
+
+		t1 = ktime_get();
+		t[pass] = ktime_sub(t1, t0);
+	}
+	if (err)
+		return err;
+
+	sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
+	pr_info("%s: %zd KiB copy: %lld MiB/s\n",
+		ce->engine->name, sz >> 10,
+		div64_u64(mul_u32_u32(4 * sz,
+				      1000 * 1000 * 1000),
+			  t[1] + 2 * t[2] + t[3]) >> 20);
+	return 0;
+}
+
+static int perf_copy_blt(void *arg)
+{
+	struct intel_gt *gt = arg;
+	static const unsigned long sizes[] = {
+		SZ_4K,
+		SZ_64K,
+		SZ_2M,
+		SZ_64M
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		struct drm_i915_gem_object *src, *dst;
+		int err;
+
+		src = create_init_lmem_internal(gt, sizes[i], true);
+		if (IS_ERR(src))
+			return PTR_ERR(src);
+
+		dst = create_init_lmem_internal(gt, sizes[i], false);
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			goto err_src;
+		}
+
+		err = __perf_copy_blt(gt->migrate.context,
+				      src->mm.pages->sgl,
+				      I915_CACHE_NONE,
+				      i915_gem_object_is_lmem(src),
+				      dst->mm.pages->sgl,
+				      I915_CACHE_NONE,
+				      i915_gem_object_is_lmem(dst),
+				      sizes[i]);
+
+		i915_gem_object_unlock(dst);
+		i915_gem_object_put(dst);
+err_src:
+		i915_gem_object_unlock(src);
+		i915_gem_object_put(src);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int intel_migrate_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_clear_blt),
+		SUBTEST(perf_copy_blt),
+	};
+	struct intel_gt *gt = &i915->gt;
+
+	if (intel_gt_is_wedged(gt))
+		return 0;
+
+	if (!gt->migrate.context)
+		return 0;
+
+	return intel_gt_live_subtests(tests, gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
index b9bb0e6e97f7..13d25bf2a94a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_mocs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -10,6 +10,7 @@
 #include "gem/selftests/mock_context.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_spinner.h"
+#include "selftests/intel_scheduler_helpers.h"
 
 struct live_mocs {
 	struct drm_i915_mocs_table table;
@@ -28,7 +29,7 @@ static struct intel_context *mocs_context_create(struct intel_engine_cs *engine)
 		return ce;
 
 	/* We build large requests to read the registers from the ring */
-	ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring_size = SZ_16K;
 
 	return ce;
 }
@@ -318,7 +319,8 @@ static int live_mocs_clean(void *arg)
 }
 
 static int active_engine_reset(struct intel_context *ce,
-			       const char *reason)
+			       const char *reason,
+			       bool using_guc)
 {
 	struct igt_spinner spin;
 	struct i915_request *rq;
@@ -335,9 +337,13 @@ static int active_engine_reset(struct intel_context *ce,
 	}
 
 	err = request_add_spin(rq, &spin);
-	if (err == 0)
+	if (err == 0 && !using_guc)
 		err = intel_engine_reset(ce->engine, reason);
 
+	/* Ensure the reset happens and kills the engine */
+	if (err == 0)
+		err = intel_selftest_wait_for_rq(rq);
+
 	igt_spinner_end(&spin);
 	igt_spinner_fini(&spin);
 
@@ -345,21 +351,23 @@ static int active_engine_reset(struct intel_context *ce,
 }
 
 static int __live_mocs_reset(struct live_mocs *mocs,
-			     struct intel_context *ce)
+			     struct intel_context *ce, bool using_guc)
 {
 	struct intel_gt *gt = ce->engine->gt;
 	int err;
 
 	if (intel_has_reset_engine(gt)) {
-		err = intel_engine_reset(ce->engine, "mocs");
-		if (err)
-			return err;
-
-		err = check_mocs_engine(mocs, ce);
-		if (err)
-			return err;
+		if (!using_guc) {
+			err = intel_engine_reset(ce->engine, "mocs");
+			if (err)
+				return err;
+
+			err = check_mocs_engine(mocs, ce);
+			if (err)
+				return err;
+		}
 
-		err = active_engine_reset(ce, "mocs");
+		err = active_engine_reset(ce, "mocs", using_guc);
 		if (err)
 			return err;
 
@@ -395,19 +403,33 @@ static int live_mocs_reset(void *arg)
 
 	igt_global_reset_lock(gt);
 	for_each_engine(engine, gt, id) {
+		bool using_guc = intel_engine_uses_guc(engine);
+		struct intel_selftest_saved_policy saved;
 		struct intel_context *ce;
+		int err2;
+
+		err = intel_selftest_modify_policy(engine, &saved,
+						   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+		if (err)
+			break;
 
 		ce = mocs_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
-			break;
+			goto restore;
 		}
 
 		intel_engine_pm_get(engine);
-		err = __live_mocs_reset(&mocs, ce);
-		intel_engine_pm_put(engine);
 
+		err = __live_mocs_reset(&mocs, ce, using_guc);
+
+		intel_engine_pm_put(engine);
 		intel_context_put(ce);
+
+restore:
+		err2 = intel_selftest_restore_policy(engine, &saved);
+		if (err == 0)
+			err = err2;
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 8784257ec808..7a50c9f4071b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -321,7 +321,7 @@ static int igt_atomic_engine_reset(void *arg)
 		goto out_unlock;
 
 	for_each_engine(engine, gt, id) {
-		struct tasklet_struct *t = &engine->execlists.tasklet;
+		struct tasklet_struct *t = &engine->sched_engine->tasklet;
 
 		if (t->func)
 			tasklet_disable(t);
diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c
new file mode 100644
index 000000000000..9334bad131a2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#define NUM_STEPS 5
+#define H2G_DELAY 50000
+#define delay_for_h2g() usleep_range(H2G_DELAY, H2G_DELAY + 10000)
+#define FREQUENCY_REQ_UNIT	DIV_ROUND_CLOSEST(GT_FREQUENCY_MULTIPLIER, \
+						  GEN9_FREQ_SCALER)
+
+static int slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 freq)
+{
+	int ret;
+
+	ret = intel_guc_slpc_set_min_freq(slpc, freq);
+	if (ret)
+		pr_err("Could not set min frequency to [%u]\n", freq);
+	else /* Delay to ensure h2g completes */
+		delay_for_h2g();
+
+	return ret;
+}
+
+static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq)
+{
+	int ret;
+
+	ret = intel_guc_slpc_set_max_freq(slpc, freq);
+	if (ret)
+		pr_err("Could not set maximum frequency [%u]\n",
+		       freq);
+	else /* Delay to ensure h2g completes */
+		delay_for_h2g();
+
+	return ret;
+}
+
+static int live_slpc_clamp_min(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = &i915->gt;
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+	struct intel_rps *rps = &gt->rps;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	u32 slpc_min_freq, slpc_max_freq;
+	int err = 0;
+
+	if (!intel_uc_uses_guc_slpc(&gt->uc))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	if (intel_guc_slpc_get_max_freq(slpc, &slpc_max_freq)) {
+		pr_err("Could not get SLPC max freq\n");
+		return -EIO;
+	}
+
+	if (intel_guc_slpc_get_min_freq(slpc, &slpc_min_freq)) {
+		pr_err("Could not get SLPC min freq\n");
+		return -EIO;
+	}
+
+	if (slpc_min_freq == slpc_max_freq) {
+		pr_err("Min/Max are fused to the same value\n");
+		return -EINVAL;
+	}
+
+	intel_gt_pm_wait_for_idle(gt);
+	intel_gt_pm_get(gt);
+	for_each_engine(engine, gt, id) {
+		struct i915_request *rq;
+		u32 step, min_freq, req_freq;
+		u32 act_freq, max_act_freq;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		/* Go from min to max in 5 steps */
+		step = (slpc_max_freq - slpc_min_freq) / NUM_STEPS;
+		max_act_freq = slpc_min_freq;
+		for (min_freq = slpc_min_freq; min_freq < slpc_max_freq;
+					min_freq += step) {
+			err = slpc_set_min_freq(slpc, min_freq);
+			if (err)
+				break;
+
+			st_engine_heartbeat_disable(engine);
+
+			rq = igt_spinner_create_request(&spin,
+							engine->kernel_context,
+							MI_NOOP);
+			if (IS_ERR(rq)) {
+				err = PTR_ERR(rq);
+				st_engine_heartbeat_enable(engine);
+				break;
+			}
+
+			i915_request_add(rq);
+
+			if (!igt_wait_for_spinner(&spin, rq)) {
+				pr_err("%s: Spinner did not start\n",
+				       engine->name);
+				igt_spinner_end(&spin);
+				st_engine_heartbeat_enable(engine);
+				intel_gt_set_wedged(engine->gt);
+				err = -EIO;
+				break;
+			}
+
+			/* Wait for GuC to detect business and raise
+			 * requested frequency if necessary.
+			 */
+			delay_for_h2g();
+
+			req_freq = intel_rps_read_punit_req_frequency(rps);
+
+			/* GuC requests freq in multiples of 50/3 MHz */
+			if (req_freq < (min_freq - FREQUENCY_REQ_UNIT)) {
+				pr_err("SWReq is %d, should be at least %d\n", req_freq,
+				       min_freq - FREQUENCY_REQ_UNIT);
+				igt_spinner_end(&spin);
+				st_engine_heartbeat_enable(engine);
+				err = -EINVAL;
+				break;
+			}
+
+			act_freq =  intel_rps_read_actual_frequency(rps);
+			if (act_freq > max_act_freq)
+				max_act_freq = act_freq;
+
+			igt_spinner_end(&spin);
+			st_engine_heartbeat_enable(engine);
+		}
+
+		pr_info("Max actual frequency for %s was %d\n",
+			engine->name, max_act_freq);
+
+		/* Actual frequency should rise above min */
+		if (max_act_freq == slpc_min_freq) {
+			pr_err("Actual freq did not rise above min\n");
+			err = -EINVAL;
+		}
+
+		if (err)
+			break;
+	}
+
+	/* Restore min/max frequencies */
+	slpc_set_max_freq(slpc, slpc_max_freq);
+	slpc_set_min_freq(slpc, slpc_min_freq);
+
+	if (igt_flush_test(gt->i915))
+		err = -EIO;
+
+	intel_gt_pm_put(gt);
+	igt_spinner_fini(&spin);
+	intel_gt_pm_wait_for_idle(gt);
+
+	return err;
+}
+
+static int live_slpc_clamp_max(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = &i915->gt;
+	struct intel_guc_slpc *slpc;
+	struct intel_rps *rps;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+	u32 slpc_min_freq, slpc_max_freq;
+
+	slpc = &gt->uc.guc.slpc;
+	rps = &gt->rps;
+
+	if (!intel_uc_uses_guc_slpc(&gt->uc))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	if (intel_guc_slpc_get_max_freq(slpc, &slpc_max_freq)) {
+		pr_err("Could not get SLPC max freq\n");
+		return -EIO;
+	}
+
+	if (intel_guc_slpc_get_min_freq(slpc, &slpc_min_freq)) {
+		pr_err("Could not get SLPC min freq\n");
+		return -EIO;
+	}
+
+	if (slpc_min_freq == slpc_max_freq) {
+		pr_err("Min/Max are fused to the same value\n");
+		return -EINVAL;
+	}
+
+	intel_gt_pm_wait_for_idle(gt);
+	intel_gt_pm_get(gt);
+	for_each_engine(engine, gt, id) {
+		struct i915_request *rq;
+		u32 max_freq, req_freq;
+		u32 act_freq, max_act_freq;
+		u32 step;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		/* Go from max to min in 5 steps */
+		step = (slpc_max_freq - slpc_min_freq) / NUM_STEPS;
+		max_act_freq = slpc_min_freq;
+		for (max_freq = slpc_max_freq; max_freq > slpc_min_freq;
+					max_freq -= step) {
+			err = slpc_set_max_freq(slpc, max_freq);
+			if (err)
+				break;
+
+			st_engine_heartbeat_disable(engine);
+
+			rq = igt_spinner_create_request(&spin,
+							engine->kernel_context,
+							MI_NOOP);
+			if (IS_ERR(rq)) {
+				st_engine_heartbeat_enable(engine);
+				err = PTR_ERR(rq);
+				break;
+			}
+
+			i915_request_add(rq);
+
+			if (!igt_wait_for_spinner(&spin, rq)) {
+				pr_err("%s: SLPC spinner did not start\n",
+				       engine->name);
+				igt_spinner_end(&spin);
+				st_engine_heartbeat_enable(engine);
+				intel_gt_set_wedged(engine->gt);
+				err = -EIO;
+				break;
+			}
+
+			delay_for_h2g();
+
+			/* Verify that SWREQ indeed was set to specific value */
+			req_freq = intel_rps_read_punit_req_frequency(rps);
+
+			/* GuC requests freq in multiples of 50/3 MHz */
+			if (req_freq > (max_freq + FREQUENCY_REQ_UNIT)) {
+				pr_err("SWReq is %d, should be at most %d\n", req_freq,
+				       max_freq + FREQUENCY_REQ_UNIT);
+				igt_spinner_end(&spin);
+				st_engine_heartbeat_enable(engine);
+				err = -EINVAL;
+				break;
+			}
+
+			act_freq =  intel_rps_read_actual_frequency(rps);
+			if (act_freq > max_act_freq)
+				max_act_freq = act_freq;
+
+			st_engine_heartbeat_enable(engine);
+			igt_spinner_end(&spin);
+
+			if (err)
+				break;
+		}
+
+		pr_info("Max actual frequency for %s was %d\n",
+			engine->name, max_act_freq);
+
+		/* Actual frequency should rise above min */
+		if (max_act_freq == slpc_min_freq) {
+			pr_err("Actual freq did not rise above min\n");
+			err = -EINVAL;
+		}
+
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+
+		if (err)
+			break;
+	}
+
+	/* Restore min/max freq */
+	slpc_set_max_freq(slpc, slpc_max_freq);
+	slpc_set_min_freq(slpc, slpc_min_freq);
+
+	intel_gt_pm_put(gt);
+	igt_spinner_fini(&spin);
+	intel_gt_pm_wait_for_idle(gt);
+
+	return err;
+}
+
+int intel_slpc_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_slpc_clamp_max),
+		SUBTEST(live_slpc_clamp_min),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 64da0c91dec1..d0b6a3afcf44 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -874,7 +874,7 @@ static int create_watcher(struct hwsp_watcher *w,
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	ce->ring = __intel_context_ring_size(ringsz);
+	ce->ring_size = ringsz;
 	w->rq = intel_context_create_request(ce);
 	intel_context_put(ce);
 	if (IS_ERR(w->rq))
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index c30754daf4b1..e623ac45f4aa 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -12,6 +12,7 @@
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_spinner.h"
+#include "selftests/intel_scheduler_helpers.h"
 #include "selftests/mock_drm.h"
 
 #include "gem/selftests/igt_gem_utils.h"
@@ -261,28 +262,34 @@ static int do_engine_reset(struct intel_engine_cs *engine)
 	return intel_engine_reset(engine, "live_workarounds");
 }
 
+static int do_guc_reset(struct intel_engine_cs *engine)
+{
+	/* Currently a no-op as the reset is handled by GuC */
+	return 0;
+}
+
 static int
 switch_to_scratch_context(struct intel_engine_cs *engine,
-			  struct igt_spinner *spin)
+			  struct igt_spinner *spin,
+			  struct i915_request **rq)
 {
 	struct intel_context *ce;
-	struct i915_request *rq;
 	int err = 0;
 
 	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	rq = igt_spinner_create_request(spin, ce, MI_NOOP);
+	*rq = igt_spinner_create_request(spin, ce, MI_NOOP);
 	intel_context_put(ce);
 
-	if (IS_ERR(rq)) {
+	if (IS_ERR(*rq)) {
 		spin = NULL;
-		err = PTR_ERR(rq);
+		err = PTR_ERR(*rq);
 		goto err;
 	}
 
-	err = request_add_spin(rq, spin);
+	err = request_add_spin(*rq, spin);
 err:
 	if (err && spin)
 		igt_spinner_end(spin);
@@ -296,6 +303,7 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 {
 	struct intel_context *ce, *tmp;
 	struct igt_spinner spin;
+	struct i915_request *rq;
 	intel_wakeref_t wakeref;
 	int err;
 
@@ -316,13 +324,24 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 		goto out_spin;
 	}
 
-	err = switch_to_scratch_context(engine, &spin);
+	err = switch_to_scratch_context(engine, &spin, &rq);
 	if (err)
 		goto out_spin;
 
+	/* Ensure the spinner hasn't aborted */
+	if (i915_request_completed(rq)) {
+		pr_err("%s spinner failed to start\n", name);
+		err = -ETIMEDOUT;
+		goto out_spin;
+	}
+
 	with_intel_runtime_pm(engine->uncore->rpm, wakeref)
 		err = reset(engine);
 
+	/* Ensure the reset happens and kills the engine */
+	if (err == 0)
+		err = intel_selftest_wait_for_rq(rq);
+
 	igt_spinner_end(&spin);
 
 	if (err) {
@@ -787,9 +806,28 @@ static int live_reset_whitelist(void *arg)
 			continue;
 
 		if (intel_has_reset_engine(gt)) {
-			err = check_whitelist_across_reset(engine,
-							   do_engine_reset,
-							   "engine");
+			if (intel_engine_uses_guc(engine)) {
+				struct intel_selftest_saved_policy saved;
+				int err2;
+
+				err = intel_selftest_modify_policy(engine, &saved,
+								   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+				if (err)
+					goto out;
+
+				err = check_whitelist_across_reset(engine,
+								   do_guc_reset,
+								   "guc");
+
+				err2 = intel_selftest_restore_policy(engine, &saved);
+				if (err == 0)
+					err = err2;
+			} else {
+				err = check_whitelist_across_reset(engine,
+								   do_engine_reset,
+								   "engine");
+			}
+
 			if (err)
 				goto out;
 		}
@@ -1147,7 +1185,7 @@ verify_wa_lists(struct intel_gt *gt, struct wa_lists *lists,
 	enum intel_engine_id id;
 	bool ok = true;
 
-	ok &= wa_list_verify(gt->uncore, &lists->gt_wa_list, str);
+	ok &= wa_list_verify(gt, &lists->gt_wa_list, str);
 
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
@@ -1175,31 +1213,36 @@ live_gpu_reset_workarounds(void *arg)
 {
 	struct intel_gt *gt = arg;
 	intel_wakeref_t wakeref;
-	struct wa_lists lists;
+	struct wa_lists *lists;
 	bool ok;
 
 	if (!intel_has_gpu_reset(gt))
 		return 0;
 
+	lists = kzalloc(sizeof(*lists), GFP_KERNEL);
+	if (!lists)
+		return -ENOMEM;
+
 	pr_info("Verifying after GPU reset...\n");
 
 	igt_global_reset_lock(gt);
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
-	reference_lists_init(gt, &lists);
+	reference_lists_init(gt, lists);
 
-	ok = verify_wa_lists(gt, &lists, "before reset");
+	ok = verify_wa_lists(gt, lists, "before reset");
 	if (!ok)
 		goto out;
 
 	intel_gt_reset(gt, ALL_ENGINES, "live_workarounds");
 
-	ok = verify_wa_lists(gt, &lists, "after reset");
+	ok = verify_wa_lists(gt, lists, "after reset");
 
 out:
-	reference_lists_fini(gt, &lists);
+	reference_lists_fini(gt, lists);
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	igt_global_reset_unlock(gt);
+	kfree(lists);
 
 	return ok ? 0 : -ESRCH;
 }
@@ -1214,43 +1257,57 @@ live_engine_reset_workarounds(void *arg)
 	struct igt_spinner spin;
 	struct i915_request *rq;
 	intel_wakeref_t wakeref;
-	struct wa_lists lists;
+	struct wa_lists *lists;
 	int ret = 0;
 
 	if (!intel_has_reset_engine(gt))
 		return 0;
 
+	lists = kzalloc(sizeof(*lists), GFP_KERNEL);
+	if (!lists)
+		return -ENOMEM;
+
 	igt_global_reset_lock(gt);
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
-	reference_lists_init(gt, &lists);
+	reference_lists_init(gt, lists);
 
 	for_each_engine(engine, gt, id) {
+		struct intel_selftest_saved_policy saved;
+		bool using_guc = intel_engine_uses_guc(engine);
 		bool ok;
+		int ret2;
 
 		pr_info("Verifying after %s reset...\n", engine->name);
+		ret = intel_selftest_modify_policy(engine, &saved,
+						   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+		if (ret)
+			break;
+
 		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
-			break;
+			goto restore;
 		}
 
-		ok = verify_wa_lists(gt, &lists, "before reset");
-		if (!ok) {
-			ret = -ESRCH;
-			goto err;
-		}
+		if (!using_guc) {
+			ok = verify_wa_lists(gt, lists, "before reset");
+			if (!ok) {
+				ret = -ESRCH;
+				goto err;
+			}
 
-		ret = intel_engine_reset(engine, "live_workarounds:idle");
-		if (ret) {
-			pr_err("%s: Reset failed while idle\n", engine->name);
-			goto err;
-		}
+			ret = intel_engine_reset(engine, "live_workarounds:idle");
+			if (ret) {
+				pr_err("%s: Reset failed while idle\n", engine->name);
+				goto err;
+			}
 
-		ok = verify_wa_lists(gt, &lists, "after idle reset");
-		if (!ok) {
-			ret = -ESRCH;
-			goto err;
+			ok = verify_wa_lists(gt, lists, "after idle reset");
+			if (!ok) {
+				ret = -ESRCH;
+				goto err;
+			}
 		}
 
 		ret = igt_spinner_init(&spin, engine->gt);
@@ -1271,32 +1328,49 @@ live_engine_reset_workarounds(void *arg)
 			goto err;
 		}
 
-		ret = intel_engine_reset(engine, "live_workarounds:active");
-		if (ret) {
-			pr_err("%s: Reset failed on an active spinner\n",
-			       engine->name);
-			igt_spinner_fini(&spin);
-			goto err;
+		/* Ensure the spinner hasn't aborted */
+		if (i915_request_completed(rq)) {
+			ret = -ETIMEDOUT;
+			goto skip;
 		}
 
+		if (!using_guc) {
+			ret = intel_engine_reset(engine, "live_workarounds:active");
+			if (ret) {
+				pr_err("%s: Reset failed on an active spinner\n",
+				       engine->name);
+				igt_spinner_fini(&spin);
+				goto err;
+			}
+		}
+
+		/* Ensure the reset happens and kills the engine */
+		if (ret == 0)
+			ret = intel_selftest_wait_for_rq(rq);
+
+skip:
 		igt_spinner_end(&spin);
 		igt_spinner_fini(&spin);
 
-		ok = verify_wa_lists(gt, &lists, "after busy reset");
-		if (!ok) {
+		ok = verify_wa_lists(gt, lists, "after busy reset");
+		if (!ok)
 			ret = -ESRCH;
-			goto err;
-		}
 
 err:
 		intel_context_put(ce);
+
+restore:
+		ret2 = intel_selftest_restore_policy(engine, &saved);
+		if (ret == 0)
+			ret = ret2;
 		if (ret)
 			break;
 	}
 
-	reference_lists_fini(gt, &lists);
+	reference_lists_fini(gt, lists);
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	igt_global_reset_unlock(gt);
+	kfree(lists);
 
 	igt_flush_test(gt->i915);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
index 90efef8a73e4..8ff582222aff 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
@@ -6,6 +6,113 @@
 #ifndef _ABI_GUC_ACTIONS_ABI_H
 #define _ABI_GUC_ACTIONS_ABI_H
 
+/**
+ * DOC: HOST2GUC_REGISTER_CTB
+ *
+ * This message is used as part of the `CTB based communication`_ setup.
+ *
+ * This message must be sent as `MMIO HXG Message`_.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_HOST_                                |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | DATA0 = MBZ                                                  |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_REGISTER_CTB` = 0x4505        |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 | 31:12 | RESERVED = MBZ                                               |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  11:8 | **TYPE** - type for the `CT Buffer`_                         |
+ *  |   |       |                                                              |
+ *  |   |       |   - _`GUC_CTB_TYPE_HOST2GUC` = 0                             |
+ *  |   |       |   - _`GUC_CTB_TYPE_GUC2HOST` = 1                             |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |   7:0 | **SIZE** - size of the `CT Buffer`_ in 4K units minus 1      |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 2 |  31:0 | **DESC_ADDR** - GGTT address of the `CTB Descriptor`_        |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 3 |  31:0 | **BUFF_ADDF** - GGTT address of the `CT Buffer`_             |
+ *  +---+-------+--------------------------------------------------------------+
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_GUC_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | DATA0 = MBZ                                                  |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+#define GUC_ACTION_HOST2GUC_REGISTER_CTB		0x4505
+
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_MBZ		(0xfffff << 12)
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE	(0xf << 8)
+#define   GUC_CTB_TYPE_HOST2GUC				0u
+#define   GUC_CTB_TYPE_GUC2HOST				1u
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE	(0xff << 0)
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR	GUC_HXG_REQUEST_MSG_n_DATAn
+#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR	GUC_HXG_REQUEST_MSG_n_DATAn
+
+#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_LEN		GUC_HXG_RESPONSE_MSG_MIN_LEN
+#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_0_MBZ	GUC_HXG_RESPONSE_MSG_0_DATA0
+
+/**
+ * DOC: HOST2GUC_DEREGISTER_CTB
+ *
+ * This message is used as part of the `CTB based communication`_ teardown.
+ *
+ * This message must be sent as `MMIO HXG Message`_.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_HOST_                                |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | DATA0 = MBZ                                                  |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_DEREGISTER_CTB` = 0x4506      |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 | 31:12 | RESERVED = MBZ                                               |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  11:8 | **TYPE** - type of the `CT Buffer`_                          |
+ *  |   |       |                                                              |
+ *  |   |       | see `GUC_ACTION_HOST2GUC_REGISTER_CTB`_                      |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |   7:0 | RESERVED = MBZ                                               |
+ *  +---+-------+--------------------------------------------------------------+
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_GUC_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | DATA0 = MBZ                                                  |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+#define GUC_ACTION_HOST2GUC_DEREGISTER_CTB		0x4506
+
+#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 1u)
+#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_0_MBZ	GUC_HXG_REQUEST_MSG_0_DATA0
+#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ	(0xfffff << 12)
+#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE	(0xf << 8)
+#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ2	(0xff << 0)
+
+#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_LEN	GUC_HXG_RESPONSE_MSG_MIN_LEN
+#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_0_MBZ	GUC_HXG_RESPONSE_MSG_0_DATA0
+
+/* legacy definitions */
+
 enum intel_guc_action {
 	INTEL_GUC_ACTION_DEFAULT = 0x0,
 	INTEL_GUC_ACTION_REQUEST_PREEMPTION = 0x2,
@@ -17,13 +124,33 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_FORCE_LOG_BUFFER_FLUSH = 0x302,
 	INTEL_GUC_ACTION_ENTER_S_STATE = 0x501,
 	INTEL_GUC_ACTION_EXIT_S_STATE = 0x502,
-	INTEL_GUC_ACTION_SLPC_REQUEST = 0x3003,
+	INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506,
+	INTEL_GUC_ACTION_SCHED_CONTEXT = 0x1000,
+	INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001,
+	INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002,
+	INTEL_GUC_ACTION_SCHED_ENGINE_MODE_SET = 0x1003,
+	INTEL_GUC_ACTION_SCHED_ENGINE_MODE_DONE = 0x1004,
+	INTEL_GUC_ACTION_SET_CONTEXT_PRIORITY = 0x1005,
+	INTEL_GUC_ACTION_SET_CONTEXT_EXECUTION_QUANTUM = 0x1006,
+	INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT = 0x1007,
+	INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION = 0x1008,
+	INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION = 0x1009,
+	INTEL_GUC_ACTION_SETUP_PC_GUCRC = 0x3004,
 	INTEL_GUC_ACTION_AUTHENTICATE_HUC = 0x4000,
+	INTEL_GUC_ACTION_REGISTER_CONTEXT = 0x4502,
+	INTEL_GUC_ACTION_DEREGISTER_CONTEXT = 0x4503,
 	INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505,
 	INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
+	INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600,
+	INTEL_GUC_ACTION_RESET_CLIENT = 0x5507,
 	INTEL_GUC_ACTION_LIMIT
 };
 
+enum intel_guc_rc_options {
+	INTEL_GUCRC_HOST_CONTROL,
+	INTEL_GUCRC_FIRMWARE_CONTROL,
+};
+
 enum intel_guc_preempt_options {
 	INTEL_GUC_PREEMPT_OPTION_DROP_WORK_Q = 0x4,
 	INTEL_GUC_PREEMPT_OPTION_DROP_SUBMIT_Q = 0x8,
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
new file mode 100644
index 000000000000..7a8d4bfc5f6a
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
@@ -0,0 +1,235 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _GUC_ACTIONS_SLPC_ABI_H_
+#define _GUC_ACTIONS_SLPC_ABI_H_
+
+#include <linux/types.h>
+#include "i915_reg.h"
+
+/**
+ * DOC: SLPC SHARED DATA STRUCTURE
+ *
+ *  +----+------+--------------------------------------------------------------+
+ *  | CL | Bytes| Description                                                  |
+ *  +====+======+==============================================================+
+ *  | 1  | 0-3  | SHARED DATA SIZE                                             |
+ *  |    +------+--------------------------------------------------------------+
+ *  |    | 4-7  | GLOBAL STATE                                                 |
+ *  |    +------+--------------------------------------------------------------+
+ *  |    | 8-11 | DISPLAY DATA ADDRESS                                         |
+ *  |    +------+--------------------------------------------------------------+
+ *  |    | 12:63| PADDING                                                      |
+ *  +----+------+--------------------------------------------------------------+
+ *  |    | 0:63 | PADDING(PLATFORM INFO)                                       |
+ *  +----+------+--------------------------------------------------------------+
+ *  | 3  | 0-3  | TASK STATE DATA                                              |
+ *  +    +------+--------------------------------------------------------------+
+ *  |    | 4:63 | PADDING                                                      |
+ *  +----+------+--------------------------------------------------------------+
+ *  |4-21|0:1087| OVERRIDE PARAMS AND BIT FIELDS                               |
+ *  +----+------+--------------------------------------------------------------+
+ *  |    |      | PADDING + EXTRA RESERVED PAGE                                |
+ *  +----+------+--------------------------------------------------------------+
+ */
+
+/*
+ * SLPC exposes certain parameters for global configuration by the host.
+ * These are referred to as override parameters, because in most cases
+ * the host will not need to modify the default values used by SLPC.
+ * SLPC remembers the default values which allows the host to easily restore
+ * them by simply unsetting the override. The host can set or unset override
+ * parameters during SLPC (re-)initialization using the SLPC Reset event.
+ * The host can also set or unset override parameters on the fly using the
+ * Parameter Set and Parameter Unset events
+ */
+
+#define SLPC_MAX_OVERRIDE_PARAMETERS		256
+#define SLPC_OVERRIDE_BITFIELD_SIZE \
+		(SLPC_MAX_OVERRIDE_PARAMETERS / 32)
+
+#define SLPC_PAGE_SIZE_BYTES			4096
+#define SLPC_CACHELINE_SIZE_BYTES		64
+#define SLPC_SHARED_DATA_SIZE_BYTE_HEADER	SLPC_CACHELINE_SIZE_BYTES
+#define SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO	SLPC_CACHELINE_SIZE_BYTES
+#define SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE	SLPC_CACHELINE_SIZE_BYTES
+#define SLPC_SHARED_DATA_MODE_DEFN_TABLE_SIZE	SLPC_PAGE_SIZE_BYTES
+#define SLPC_SHARED_DATA_SIZE_BYTE_MAX		(2 * SLPC_PAGE_SIZE_BYTES)
+
+/*
+ * Cacheline size aligned (Total size needed for
+ * SLPM_KMD_MAX_OVERRIDE_PARAMETERS=256 is 1088 bytes)
+ */
+#define SLPC_OVERRIDE_PARAMS_TOTAL_BYTES	(((((SLPC_MAX_OVERRIDE_PARAMETERS * 4) \
+						+ ((SLPC_MAX_OVERRIDE_PARAMETERS / 32) * 4)) \
+		+ (SLPC_CACHELINE_SIZE_BYTES - 1)) / SLPC_CACHELINE_SIZE_BYTES) * \
+					SLPC_CACHELINE_SIZE_BYTES)
+
+#define SLPC_SHARED_DATA_SIZE_BYTE_OTHER	(SLPC_SHARED_DATA_SIZE_BYTE_MAX - \
+					(SLPC_SHARED_DATA_SIZE_BYTE_HEADER \
+					+ SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO \
+					+ SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE \
+					+ SLPC_OVERRIDE_PARAMS_TOTAL_BYTES \
+					+ SLPC_SHARED_DATA_MODE_DEFN_TABLE_SIZE))
+
+enum slpc_task_enable {
+	SLPC_PARAM_TASK_DEFAULT = 0,
+	SLPC_PARAM_TASK_ENABLED,
+	SLPC_PARAM_TASK_DISABLED,
+	SLPC_PARAM_TASK_UNKNOWN
+};
+
+enum slpc_global_state {
+	SLPC_GLOBAL_STATE_NOT_RUNNING = 0,
+	SLPC_GLOBAL_STATE_INITIALIZING = 1,
+	SLPC_GLOBAL_STATE_RESETTING = 2,
+	SLPC_GLOBAL_STATE_RUNNING = 3,
+	SLPC_GLOBAL_STATE_SHUTTING_DOWN = 4,
+	SLPC_GLOBAL_STATE_ERROR = 5
+};
+
+enum slpc_param_id {
+	SLPC_PARAM_TASK_ENABLE_GTPERF = 0,
+	SLPC_PARAM_TASK_DISABLE_GTPERF = 1,
+	SLPC_PARAM_TASK_ENABLE_BALANCER = 2,
+	SLPC_PARAM_TASK_DISABLE_BALANCER = 3,
+	SLPC_PARAM_TASK_ENABLE_DCC = 4,
+	SLPC_PARAM_TASK_DISABLE_DCC = 5,
+	SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ = 6,
+	SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ = 7,
+	SLPC_PARAM_GLOBAL_MIN_GT_SLICE_FREQ_MHZ = 8,
+	SLPC_PARAM_GLOBAL_MAX_GT_SLICE_FREQ_MHZ = 9,
+	SLPC_PARAM_GTPERF_THRESHOLD_MAX_FPS = 10,
+	SLPC_PARAM_GLOBAL_DISABLE_GT_FREQ_MANAGEMENT = 11,
+	SLPC_PARAM_GTPERF_ENABLE_FRAMERATE_STALLING = 12,
+	SLPC_PARAM_GLOBAL_DISABLE_RC6_MODE_CHANGE = 13,
+	SLPC_PARAM_GLOBAL_OC_UNSLICE_FREQ_MHZ = 14,
+	SLPC_PARAM_GLOBAL_OC_SLICE_FREQ_MHZ = 15,
+	SLPC_PARAM_GLOBAL_ENABLE_IA_GT_BALANCING = 16,
+	SLPC_PARAM_GLOBAL_ENABLE_ADAPTIVE_BURST_TURBO = 17,
+	SLPC_PARAM_GLOBAL_ENABLE_EVAL_MODE = 18,
+	SLPC_PARAM_GLOBAL_ENABLE_BALANCER_IN_NON_GAMING_MODE = 19,
+	SLPC_PARAM_GLOBAL_RT_MODE_TURBO_FREQ_DELTA_MHZ = 20,
+	SLPC_PARAM_PWRGATE_RC_MODE = 21,
+	SLPC_PARAM_EDR_MODE_COMPUTE_TIMEOUT_MS = 22,
+	SLPC_PARAM_EDR_QOS_FREQ_MHZ = 23,
+	SLPC_PARAM_MEDIA_FF_RATIO_MODE = 24,
+	SLPC_PARAM_ENABLE_IA_FREQ_LIMITING = 25,
+	SLPC_PARAM_STRATEGIES = 26,
+	SLPC_PARAM_POWER_PROFILE = 27,
+	SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY = 28,
+	SLPC_MAX_PARAM = 32,
+};
+
+enum slpc_event_id {
+	SLPC_EVENT_RESET = 0,
+	SLPC_EVENT_SHUTDOWN = 1,
+	SLPC_EVENT_PLATFORM_INFO_CHANGE = 2,
+	SLPC_EVENT_DISPLAY_MODE_CHANGE = 3,
+	SLPC_EVENT_FLIP_COMPLETE = 4,
+	SLPC_EVENT_QUERY_TASK_STATE = 5,
+	SLPC_EVENT_PARAMETER_SET = 6,
+	SLPC_EVENT_PARAMETER_UNSET = 7,
+};
+
+struct slpc_task_state_data {
+	union {
+		u32 task_status_padding;
+		struct {
+			u32 status;
+#define SLPC_GTPERF_TASK_ENABLED	REG_BIT(0)
+#define SLPC_DCC_TASK_ENABLED		REG_BIT(11)
+#define SLPC_IN_DCC			REG_BIT(12)
+#define SLPC_BALANCER_ENABLED		REG_BIT(15)
+#define SLPC_IBC_TASK_ENABLED		REG_BIT(16)
+#define SLPC_BALANCER_IA_LMT_ENABLED	REG_BIT(17)
+#define SLPC_BALANCER_IA_LMT_ACTIVE	REG_BIT(18)
+		};
+	};
+	union {
+		u32 freq_padding;
+		struct {
+#define SLPC_MAX_UNSLICE_FREQ_MASK	REG_GENMASK(7, 0)
+#define SLPC_MIN_UNSLICE_FREQ_MASK	REG_GENMASK(15, 8)
+#define SLPC_MAX_SLICE_FREQ_MASK	REG_GENMASK(23, 16)
+#define SLPC_MIN_SLICE_FREQ_MASK	REG_GENMASK(31, 24)
+			u32 freq;
+		};
+	};
+} __packed;
+
+struct slpc_shared_data_header {
+	/* Total size in bytes of this shared buffer. */
+	u32 size;
+	u32 global_state;
+	u32 display_data_addr;
+} __packed;
+
+struct slpc_override_params {
+	u32 bits[SLPC_OVERRIDE_BITFIELD_SIZE];
+	u32 values[SLPC_MAX_OVERRIDE_PARAMETERS];
+} __packed;
+
+struct slpc_shared_data {
+	struct slpc_shared_data_header header;
+	u8 shared_data_header_pad[SLPC_SHARED_DATA_SIZE_BYTE_HEADER -
+				sizeof(struct slpc_shared_data_header)];
+
+	u8 platform_info_pad[SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO];
+
+	struct slpc_task_state_data task_state_data;
+	u8 task_state_data_pad[SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE -
+				sizeof(struct slpc_task_state_data)];
+
+	struct slpc_override_params override_params;
+	u8 override_params_pad[SLPC_OVERRIDE_PARAMS_TOTAL_BYTES -
+				sizeof(struct slpc_override_params)];
+
+	u8 shared_data_pad[SLPC_SHARED_DATA_SIZE_BYTE_OTHER];
+
+	/* PAGE 2 (4096 bytes), mode based parameter will be removed soon */
+	u8 reserved_mode_definition[4096];
+} __packed;
+
+/**
+ * DOC: SLPC H2G MESSAGE FORMAT
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_HOST_                                |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | DATA0 = MBZ                                                  |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_PC_SLPM_REQUEST` = 0x3003     |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:8 | **EVENT_ID**                                                 |
+ *  +   +-------+--------------------------------------------------------------+
+ *  |   |   7:0 | **EVENT_ARGC** - number of data arguments                    |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 2 |  31:0 | **EVENT_DATA1**                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ *  |...|  31:0 | ...                                                          |
+ *  +---+-------+--------------------------------------------------------------+
+ *  |2+n|  31:0 | **EVENT_DATAn**                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST		0x3003
+
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_MIN_LEN \
+				(GUC_HXG_REQUEST_MSG_MIN_LEN + 1u)
+#define HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS		9
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_MAX_LEN \
+		(HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \
+			HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xff << 8)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xff << 0)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N	GUC_HXG_REQUEST_MSG_n_DATAn
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
index d38935f47ecf..99e1fad5ca20 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
@@ -7,6 +7,111 @@
 #define _ABI_GUC_COMMUNICATION_CTB_ABI_H
 
 #include <linux/types.h>
+#include <linux/build_bug.h>
+
+#include "guc_messages_abi.h"
+
+/**
+ * DOC: CT Buffer
+ *
+ * Circular buffer used to send `CTB Message`_
+ */
+
+/**
+ * DOC: CTB Descriptor
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |  31:0 | **HEAD** - offset (in dwords) to the last dword that was     |
+ *  |   |       | read from the `CT Buffer`_.                                  |
+ *  |   |       | It can only be updated by the receiver.                      |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 | **TAIL** - offset (in dwords) to the last dword that was     |
+ *  |   |       | written to the `CT Buffer`_.                                 |
+ *  |   |       | It can only be updated by the sender.                        |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 2 |  31:0 | **STATUS** - status of the CTB                               |
+ *  |   |       |                                                              |
+ *  |   |       |   - _`GUC_CTB_STATUS_NO_ERROR` = 0 (normal operation)        |
+ *  |   |       |   - _`GUC_CTB_STATUS_OVERFLOW` = 1 (head/tail too large)     |
+ *  |   |       |   - _`GUC_CTB_STATUS_UNDERFLOW` = 2 (truncated message)      |
+ *  |   |       |   - _`GUC_CTB_STATUS_MISMATCH` = 4 (head/tail modified)      |
+ *  +---+-------+--------------------------------------------------------------+
+ *  |...|       | RESERVED = MBZ                                               |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 15|  31:0 | RESERVED = MBZ                                               |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+struct guc_ct_buffer_desc {
+	u32 head;
+	u32 tail;
+	u32 status;
+#define GUC_CTB_STATUS_NO_ERROR				0
+#define GUC_CTB_STATUS_OVERFLOW				(1 << 0)
+#define GUC_CTB_STATUS_UNDERFLOW			(1 << 1)
+#define GUC_CTB_STATUS_MISMATCH				(1 << 2)
+	u32 reserved[13];
+} __packed;
+static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
+
+/**
+ * DOC: CTB Message
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 | 31:16 | **FENCE** - message identifier                               |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 15:12 | **FORMAT** - format of the CTB message                       |
+ *  |   |       |  - _`GUC_CTB_FORMAT_HXG` = 0 - see `CTB HXG Message`_        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  11:8 | **RESERVED**                                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |   7:0 | **NUM_DWORDS** - length of the CTB message (w/o header)      |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 | optional (depends on FORMAT)                                 |
+ *  +---+-------+                                                              |
+ *  |...|       |                                                              |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_CTB_HDR_LEN				1u
+#define GUC_CTB_MSG_MIN_LEN			GUC_CTB_HDR_LEN
+#define GUC_CTB_MSG_MAX_LEN			256u
+#define GUC_CTB_MSG_0_FENCE			(0xffff << 16)
+#define GUC_CTB_MSG_0_FORMAT			(0xf << 12)
+#define   GUC_CTB_FORMAT_HXG			0u
+#define GUC_CTB_MSG_0_RESERVED			(0xf << 8)
+#define GUC_CTB_MSG_0_NUM_DWORDS		(0xff << 0)
+
+/**
+ * DOC: CTB HXG Message
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 | 31:16 | FENCE                                                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 15:12 | FORMAT = GUC_CTB_FORMAT_HXG_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  11:8 | RESERVED = MBZ                                               |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |   7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message  |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 |  +--------------------------------------------------------+  |
+ *  +---+-------+  |                                                        |  |
+ *  |...|       |  |  Embedded `HXG Message`_                               |  |
+ *  +---+-------+  |                                                        |  |
+ *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_CTB_HXG_MSG_MIN_LEN		(GUC_CTB_MSG_MIN_LEN + GUC_HXG_MSG_MIN_LEN)
+#define GUC_CTB_HXG_MSG_MAX_LEN		GUC_CTB_MSG_MAX_LEN
 
 /**
  * DOC: CTB based communication
@@ -61,28 +166,6 @@
  */
 
 /*
- * Describes single command transport buffer.
- * Used by both guc-master and clients.
- */
-struct guc_ct_buffer_desc {
-	u32 addr;		/* gfx address */
-	u64 host_private;	/* host private data */
-	u32 size;		/* size in bytes */
-	u32 head;		/* offset updated by GuC*/
-	u32 tail;		/* offset updated by owner */
-	u32 is_in_error;	/* error indicator */
-	u32 reserved1;
-	u32 reserved2;
-	u32 owner;		/* id of the channel owner */
-	u32 owner_sub_id;	/* owner-defined field for extra tracking */
-	u32 reserved[5];
-} __packed;
-
-/* Type of command transport buffer */
-#define INTEL_GUC_CT_BUFFER_TYPE_SEND	0x0u
-#define INTEL_GUC_CT_BUFFER_TYPE_RECV	0x1u
-
-/*
  * Definition of the command transport message header (DW0)
  *
  * bit[4..0]	message len (in dwords)
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
index be066a62e9e0..bbf1ddb77434 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
@@ -7,46 +7,43 @@
 #define _ABI_GUC_COMMUNICATION_MMIO_ABI_H
 
 /**
- * DOC: MMIO based communication
+ * DOC: GuC MMIO based communication
  *
- * The MMIO based communication between Host and GuC uses software scratch
- * registers, where first register holds data treated as message header,
- * and other registers are used to hold message payload.
+ * The MMIO based communication between Host and GuC relies on special
+ * hardware registers which format could be defined by the software
+ * (so called scratch registers).
  *
- * For Gen9+, GuC uses software scratch registers 0xC180-0xC1B8,
- * but no H2G command takes more than 8 parameters and the GuC FW
- * itself uses an 8-element array to store the H2G message.
+ * Each MMIO based message, both Host to GuC (H2G) and GuC to Host (G2H)
+ * messages, which maximum length depends on number of available scratch
+ * registers, is directly written into those scratch registers.
  *
- *      +-----------+---------+---------+---------+
- *      |  MMIO[0]  | MMIO[1] |   ...   | MMIO[n] |
- *      +-----------+---------+---------+---------+
- *      | header    |      optional payload       |
- *      +======+====+=========+=========+=========+
- *      | 31:28|type|         |         |         |
- *      +------+----+         |         |         |
- *      | 27:16|data|         |         |         |
- *      +------+----+         |         |         |
- *      |  15:0|code|         |         |         |
- *      +------+----+---------+---------+---------+
+ * For Gen9+, there are 16 software scratch registers 0xC180-0xC1B8,
+ * but no H2G command takes more than 4 parameters and the GuC firmware
+ * itself uses an 4-element array to store the H2G message.
  *
- * The message header consists of:
+ * For Gen11+, there are additional 4 registers 0x190240-0x19024C, which
+ * are, regardless on lower count, preferred over legacy ones.
  *
- * - **type**, indicates message type
- * - **code**, indicates message code, is specific for **type**
- * - **data**, indicates message data, optional, depends on **code**
- *
- * The following message **types** are supported:
- *
- * - **REQUEST**, indicates Host-to-GuC request, requested GuC action code
- *   must be priovided in **code** field. Optional action specific parameters
- *   can be provided in remaining payload registers or **data** field.
- *
- * - **RESPONSE**, indicates GuC-to-Host response from earlier GuC request,
- *   action response status will be provided in **code** field. Optional
- *   response data can be returned in remaining payload registers or **data**
- *   field.
+ * The MMIO based communication is mainly used during driver initialization
+ * phase to setup the `CTB based communication`_ that will be used afterwards.
  */
 
-#define GUC_MAX_MMIO_MSG_LEN		8
+#define GUC_MAX_MMIO_MSG_LEN		4
+
+/**
+ * DOC: MMIO HXG Message
+ *
+ * Format of the MMIO messages follows definitions of `HXG Message`_.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |  31:0 |  +--------------------------------------------------------+  |
+ *  +---+-------+  |                                                        |  |
+ *  |...|       |  |  Embedded `HXG Message`_                               |  |
+ *  +---+-------+  |                                                        |  |
+ *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  +---+-------+--------------------------------------------------------------+
+ */
 
 #endif /* _ABI_GUC_COMMUNICATION_MMIO_ABI_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h
index 775e21f3058c..29ac823acd4c 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h
@@ -6,6 +6,219 @@
 #ifndef _ABI_GUC_MESSAGES_ABI_H
 #define _ABI_GUC_MESSAGES_ABI_H
 
+/**
+ * DOC: HXG Message
+ *
+ * All messages exchanged with GuC are defined using 32 bit dwords.
+ * First dword is treated as a message header. Remaining dwords are optional.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  |   |       |                                                              |
+ *  | 0 |    31 | **ORIGIN** - originator of the message                       |
+ *  |   |       |   - _`GUC_HXG_ORIGIN_HOST` = 0                               |
+ *  |   |       |   - _`GUC_HXG_ORIGIN_GUC` = 1                                |
+ *  |   |       |                                                              |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | **TYPE** - message type                                      |
+ *  |   |       |   - _`GUC_HXG_TYPE_REQUEST` = 0                              |
+ *  |   |       |   - _`GUC_HXG_TYPE_EVENT` = 1                                |
+ *  |   |       |   - _`GUC_HXG_TYPE_NO_RESPONSE_BUSY` = 3                     |
+ *  |   |       |   - _`GUC_HXG_TYPE_NO_RESPONSE_RETRY` = 5                    |
+ *  |   |       |   - _`GUC_HXG_TYPE_RESPONSE_FAILURE` = 6                     |
+ *  |   |       |   - _`GUC_HXG_TYPE_RESPONSE_SUCCESS` = 7                     |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | **AUX** - auxiliary data (depends on TYPE)                   |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | **PAYLOAD** - optional payload (depends on TYPE)             |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_MSG_MIN_LEN			1u
+#define GUC_HXG_MSG_0_ORIGIN			(0x1 << 31)
+#define   GUC_HXG_ORIGIN_HOST			0u
+#define   GUC_HXG_ORIGIN_GUC			1u
+#define GUC_HXG_MSG_0_TYPE			(0x7 << 28)
+#define   GUC_HXG_TYPE_REQUEST			0u
+#define   GUC_HXG_TYPE_EVENT			1u
+#define   GUC_HXG_TYPE_NO_RESPONSE_BUSY		3u
+#define   GUC_HXG_TYPE_NO_RESPONSE_RETRY	5u
+#define   GUC_HXG_TYPE_RESPONSE_FAILURE		6u
+#define   GUC_HXG_TYPE_RESPONSE_SUCCESS		7u
+#define GUC_HXG_MSG_0_AUX			(0xfffffff << 0)
+#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffff << 0)
+
+/**
+ * DOC: HXG Request
+ *
+ * The `HXG Request`_ message should be used to initiate synchronous activity
+ * for which confirmation or return data is expected.
+ *
+ * The recipient of this message shall use `HXG Response`_, `HXG Failure`_
+ * or `HXG Retry`_ message as a definite reply, and may use `HXG Busy`_
+ * message as a intermediate reply.
+ *
+ * Format of @DATA0 and all @DATAn fields depends on the @ACTION code.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | **DATA0** - request data (depends on ACTION)                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | **ACTION** - requested action code                           |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | **DATAn** - optional data (depends on ACTION)                |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_REQUEST_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfff << 16)
+#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_REQUEST_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
+
+/**
+ * DOC: HXG Event
+ *
+ * The `HXG Event`_ message should be used to initiate asynchronous activity
+ * that does not involves immediate confirmation nor data.
+ *
+ * Format of @DATA0 and all @DATAn fields depends on the @ACTION code.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_EVENT_                                   |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | **DATA0** - event data (depends on ACTION)                   |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | **ACTION** - event action code                               |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | **DATAn** - optional event  data (depends on ACTION)         |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_EVENT_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfff << 16)
+#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_EVENT_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
+
+/**
+ * DOC: HXG Busy
+ *
+ * The `HXG Busy`_ message may be used to acknowledge reception of the `HXG Request`_
+ * message if the recipient expects that it processing will be longer than default
+ * timeout.
+ *
+ * The @COUNTER field may be used as a progress indicator.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_NO_RESPONSE_BUSY_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | **COUNTER** - progress indicator                             |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_BUSY_MSG_LEN			GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_BUSY_MSG_0_COUNTER		GUC_HXG_MSG_0_AUX
+
+/**
+ * DOC: HXG Retry
+ *
+ * The `HXG Retry`_ message should be used by recipient to indicate that the
+ * `HXG Request`_ message was dropped and it should be resent again.
+ *
+ * The @REASON field may be used to provide additional information.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_NO_RESPONSE_RETRY_                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | **REASON** - reason for retry                                |
+ *  |   |       |  - _`GUC_HXG_RETRY_REASON_UNSPECIFIED` = 0                   |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_RETRY_MSG_LEN			GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_RETRY_MSG_0_REASON		GUC_HXG_MSG_0_AUX
+#define   GUC_HXG_RETRY_REASON_UNSPECIFIED	0u
+
+/**
+ * DOC: HXG Failure
+ *
+ * The `HXG Failure`_ message shall be used as a reply to the `HXG Request`_
+ * message that could not be processed due to an error.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_FAILURE_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | **HINT** - additional error hint                             |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | **ERROR** - error/result code                                |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_FAILURE_MSG_LEN			GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfff << 16)
+#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffff << 0)
+
+/**
+ * DOC: HXG Response
+ *
+ * The `HXG Response`_ message shall be used as a reply to the `HXG Request`_
+ * message that was successfully processed without an error.
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN                                                       |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | **DATA0** - data (depends on ACTION from `HXG Request`_)     |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | **DATAn** - data (depends on ACTION from `HXG Request`_)     |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_HXG_RESPONSE_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
+#define GUC_HXG_RESPONSE_MSG_0_DATA0		GUC_HXG_MSG_0_AUX
+#define GUC_HXG_RESPONSE_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
+
+/* deprecated */
 #define INTEL_GUC_MSG_TYPE_SHIFT	28
 #define INTEL_GUC_MSG_TYPE_MASK		(0xF << INTEL_GUC_MSG_TYPE_SHIFT)
 #define INTEL_GUC_MSG_DATA_SHIFT	16
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index f147cb389a20..fbfcae727d7f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -7,6 +7,7 @@
 #include "gt/intel_gt_irq.h"
 #include "gt/intel_gt_pm_irq.h"
 #include "intel_guc.h"
+#include "intel_guc_slpc.h"
 #include "intel_guc_ads.h"
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
@@ -157,6 +158,8 @@ void intel_guc_init_early(struct intel_guc *guc)
 	intel_guc_ct_init_early(&guc->ct);
 	intel_guc_log_init_early(&guc->log);
 	intel_guc_submission_init_early(guc);
+	intel_guc_slpc_init_early(&guc->slpc);
+	intel_guc_rc_init_early(guc);
 
 	mutex_init(&guc->send_mutex);
 	spin_lock_init(&guc->irq_lock);
@@ -180,6 +183,11 @@ void intel_guc_init_early(struct intel_guc *guc)
 	}
 }
 
+void intel_guc_init_late(struct intel_guc *guc)
+{
+	intel_guc_ads_init_late(guc);
+}
+
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
 	u32 level = intel_guc_log_get_level(&guc->log);
@@ -201,6 +209,9 @@ static u32 guc_ctl_feature_flags(struct intel_guc *guc)
 	if (!intel_guc_submission_is_used(guc))
 		flags |= GUC_CTL_DISABLE_SCHEDULER;
 
+	if (intel_guc_slpc_is_used(guc))
+		flags |= GUC_CTL_ENABLE_SLPC;
+
 	return flags;
 }
 
@@ -219,24 +230,19 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 
 	BUILD_BUG_ON(!CRASH_BUFFER_SIZE);
 	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT));
-	BUILD_BUG_ON(!DPC_BUFFER_SIZE);
-	BUILD_BUG_ON(!IS_ALIGNED(DPC_BUFFER_SIZE, UNIT));
-	BUILD_BUG_ON(!ISR_BUFFER_SIZE);
-	BUILD_BUG_ON(!IS_ALIGNED(ISR_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!DEBUG_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, UNIT));
 
 	BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) >
 			(GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT));
-	BUILD_BUG_ON((DPC_BUFFER_SIZE / UNIT - 1) >
-			(GUC_LOG_DPC_MASK >> GUC_LOG_DPC_SHIFT));
-	BUILD_BUG_ON((ISR_BUFFER_SIZE / UNIT - 1) >
-			(GUC_LOG_ISR_MASK >> GUC_LOG_ISR_SHIFT));
+	BUILD_BUG_ON((DEBUG_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_DEBUG_MASK >> GUC_LOG_DEBUG_SHIFT));
 
 	flags = GUC_LOG_VALID |
 		GUC_LOG_NOTIFY_ON_HALF_FULL |
 		FLAG |
 		((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
-		((DPC_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DPC_SHIFT) |
-		((ISR_BUFFER_SIZE / UNIT - 1) << GUC_LOG_ISR_SHIFT) |
+		((DEBUG_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DEBUG_SHIFT) |
 		(offset << GUC_LOG_BUF_ADDR_SHIFT);
 
 	#undef UNIT
@@ -331,6 +337,12 @@ int intel_guc_init(struct intel_guc *guc)
 			goto err_ct;
 	}
 
+	if (intel_guc_slpc_is_used(guc)) {
+		ret = intel_guc_slpc_init(&guc->slpc);
+		if (ret)
+			goto err_submission;
+	}
+
 	/* now that everything is perma-pinned, initialize the parameters */
 	guc_init_params(guc);
 
@@ -341,6 +353,8 @@ int intel_guc_init(struct intel_guc *guc)
 
 	return 0;
 
+err_submission:
+	intel_guc_submission_fini(guc);
 err_ct:
 	intel_guc_ct_fini(&guc->ct);
 err_ads:
@@ -363,6 +377,9 @@ void intel_guc_fini(struct intel_guc *guc)
 
 	i915_ggtt_disable_guc(gt->ggtt);
 
+	if (intel_guc_slpc_is_used(guc))
+		intel_guc_slpc_fini(&guc->slpc);
+
 	if (intel_guc_submission_is_used(guc))
 		intel_guc_submission_fini(guc);
 
@@ -376,29 +393,27 @@ void intel_guc_fini(struct intel_guc *guc)
 /*
  * This function implements the MMIO based host to GuC interface.
  */
-int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
+int intel_guc_send_mmio(struct intel_guc *guc, const u32 *request, u32 len,
 			u32 *response_buf, u32 response_buf_size)
 {
+	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 	struct intel_uncore *uncore = guc_to_gt(guc)->uncore;
-	u32 status;
+	u32 header;
 	int i;
 	int ret;
 
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len > guc->send_regs.count);
 
-	/* We expect only action code */
-	GEM_BUG_ON(*action & ~INTEL_GUC_MSG_CODE_MASK);
-
-	/* If CT is available, we expect to use MMIO only during init/fini */
-	GEM_BUG_ON(*action != INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER &&
-		   *action != INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER);
+	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, request[0]) != GUC_HXG_ORIGIN_HOST);
+	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, request[0]) != GUC_HXG_TYPE_REQUEST);
 
 	mutex_lock(&guc->send_mutex);
 	intel_uncore_forcewake_get(uncore, guc->send_regs.fw_domains);
 
+retry:
 	for (i = 0; i < len; i++)
-		intel_uncore_write(uncore, guc_send_reg(guc, i), action[i]);
+		intel_uncore_write(uncore, guc_send_reg(guc, i), request[i]);
 
 	intel_uncore_posting_read(uncore, guc_send_reg(guc, i - 1));
 
@@ -410,30 +425,74 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
 	 */
 	ret = __intel_wait_for_register_fw(uncore,
 					   guc_send_reg(guc, 0),
-					   INTEL_GUC_MSG_TYPE_MASK,
-					   INTEL_GUC_MSG_TYPE_RESPONSE <<
-					   INTEL_GUC_MSG_TYPE_SHIFT,
-					   10, 10, &status);
-	/* If GuC explicitly returned an error, convert it to -EIO */
-	if (!ret && !INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(status))
-		ret = -EIO;
+					   GUC_HXG_MSG_0_ORIGIN,
+					   FIELD_PREP(GUC_HXG_MSG_0_ORIGIN,
+						      GUC_HXG_ORIGIN_GUC),
+					   10, 10, &header);
+	if (unlikely(ret)) {
+timeout:
+		drm_err(&i915->drm, "mmio request %#x: no reply %x\n",
+			request[0], header);
+		goto out;
+	}
 
-	if (ret) {
-		DRM_ERROR("MMIO: GuC action %#x failed with error %d %#x\n",
-			  action[0], ret, status);
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_NO_RESPONSE_BUSY) {
+#define done ({ header = intel_uncore_read(uncore, guc_send_reg(guc, 0)); \
+		FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) != GUC_HXG_ORIGIN_GUC || \
+		FIELD_GET(GUC_HXG_MSG_0_TYPE, header) != GUC_HXG_TYPE_NO_RESPONSE_BUSY; })
+
+		ret = wait_for(done, 1000);
+		if (unlikely(ret))
+			goto timeout;
+		if (unlikely(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) !=
+				       GUC_HXG_ORIGIN_GUC))
+			goto proto;
+#undef done
+	}
+
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) {
+		u32 reason = FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, header);
+
+		drm_dbg(&i915->drm, "mmio request %#x: retrying, reason %u\n",
+			request[0], reason);
+		goto retry;
+	}
+
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_RESPONSE_FAILURE) {
+		u32 hint = FIELD_GET(GUC_HXG_FAILURE_MSG_0_HINT, header);
+		u32 error = FIELD_GET(GUC_HXG_FAILURE_MSG_0_ERROR, header);
+
+		drm_err(&i915->drm, "mmio request %#x: failure %x/%u\n",
+			request[0], error, hint);
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) != GUC_HXG_TYPE_RESPONSE_SUCCESS) {
+proto:
+		drm_err(&i915->drm, "mmio request %#x: unexpected reply %#x\n",
+			request[0], header);
+		ret = -EPROTO;
 		goto out;
 	}
 
 	if (response_buf) {
-		int count = min(response_buf_size, guc->send_regs.count - 1);
+		int count = min(response_buf_size, guc->send_regs.count);
+
+		GEM_BUG_ON(!count);
 
-		for (i = 0; i < count; i++)
+		response_buf[0] = header;
+
+		for (i = 1; i < count; i++)
 			response_buf[i] = intel_uncore_read(uncore,
-							    guc_send_reg(guc, i + 1));
-	}
+							    guc_send_reg(guc, i));
 
-	/* Use data from the GuC response as our return value */
-	ret = INTEL_GUC_MSG_TO_DATA(status);
+		/* Use number of copied dwords as our return value */
+		ret = count;
+	} else {
+		/* Use data from the GuC response as our return value */
+		ret = FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, header);
+	}
 
 out:
 	intel_uncore_forcewake_put(uncore, guc->send_regs.fw_domains);
@@ -487,65 +546,35 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset)
  */
 int intel_guc_suspend(struct intel_guc *guc)
 {
-	struct intel_uncore *uncore = guc_to_gt(guc)->uncore;
 	int ret;
-	u32 status;
 	u32 action[] = {
-		INTEL_GUC_ACTION_ENTER_S_STATE,
-		GUC_POWER_D1, /* any value greater than GUC_POWER_D0 */
+		INTEL_GUC_ACTION_RESET_CLIENT,
 	};
 
-	/*
-	 * If GuC communication is enabled but submission is not supported,
-	 * we do not need to suspend the GuC.
-	 */
-	if (!intel_guc_submission_is_used(guc) || !intel_guc_is_ready(guc))
+	if (!intel_guc_is_ready(guc))
 		return 0;
 
-	/*
-	 * The ENTER_S_STATE action queues the save/restore operation in GuC FW
-	 * and then returns, so waiting on the H2G is not enough to guarantee
-	 * GuC is done. When all the processing is done, GuC writes
-	 * INTEL_GUC_SLEEP_STATE_SUCCESS to scratch register 14, so we can poll
-	 * on that. Note that GuC does not ensure that the value in the register
-	 * is different from INTEL_GUC_SLEEP_STATE_SUCCESS while the action is
-	 * in progress so we need to take care of that ourselves as well.
-	 */
-
-	intel_uncore_write(uncore, SOFT_SCRATCH(14),
-			   INTEL_GUC_SLEEP_STATE_INVALID_MASK);
-
-	ret = intel_guc_send(guc, action, ARRAY_SIZE(action));
-	if (ret)
-		return ret;
-
-	ret = __intel_wait_for_register(uncore, SOFT_SCRATCH(14),
-					INTEL_GUC_SLEEP_STATE_INVALID_MASK,
-					0, 0, 10, &status);
-	if (ret)
-		return ret;
-
-	if (status != INTEL_GUC_SLEEP_STATE_SUCCESS) {
-		DRM_ERROR("GuC failed to change sleep state. "
-			  "action=0x%x, err=%u\n",
-			  action[0], status);
-		return -EIO;
+	if (intel_guc_submission_is_used(guc)) {
+		/*
+		 * This H2G MMIO command tears down the GuC in two steps. First it will
+		 * generate a G2H CTB for every active context indicating a reset. In
+		 * practice the i915 shouldn't ever get a G2H as suspend should only be
+		 * called when the GPU is idle. Next, it tears down the CTBs and this
+		 * H2G MMIO command completes.
+		 *
+		 * Don't abort on a failure code from the GuC. Keep going and do the
+		 * clean up in santize() and re-initialisation on resume and hopefully
+		 * the error here won't be problematic.
+		 */
+		ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
+		if (ret)
+			DRM_ERROR("GuC suspend: RESET_CLIENT action failed with error %d!\n", ret);
 	}
 
-	return 0;
-}
-
-/**
- * intel_guc_reset_engine() - ask GuC to reset an engine
- * @guc:	intel_guc structure
- * @engine:	engine to be reset
- */
-int intel_guc_reset_engine(struct intel_guc *guc,
-			   struct intel_engine_cs *engine)
-{
-	/* XXX: to be implemented with submission interface rework */
+	/* Signal that the GuC isn't running. */
+	intel_guc_sanitize(guc);
 
-	return -ENODEV;
+	return 0;
 }
 
 /**
@@ -554,7 +583,12 @@ int intel_guc_reset_engine(struct intel_guc *guc,
  */
 int intel_guc_resume(struct intel_guc *guc)
 {
-	/* XXX: to be implemented with submission interface rework */
+	/*
+	 * NB: This function can still be called even if GuC submission is
+	 * disabled, e.g. if GuC is enabled for HuC authentication only. Thus,
+	 * if any code is later added here, it must be support doing nothing
+	 * if submission is disabled (as per intel_guc_suspend).
+	 */
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 4abc59f6f3cd..2e27fe59786b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -6,12 +6,16 @@
 #ifndef _INTEL_GUC_H_
 #define _INTEL_GUC_H_
 
+#include <linux/xarray.h>
+#include <linux/delay.h>
+
 #include "intel_uncore.h"
 #include "intel_guc_fw.h"
 #include "intel_guc_fwif.h"
 #include "intel_guc_ct.h"
 #include "intel_guc_log.h"
 #include "intel_guc_reg.h"
+#include "intel_guc_slpc_types.h"
 #include "intel_uc_fw.h"
 #include "i915_utils.h"
 #include "i915_vma.h"
@@ -27,24 +31,47 @@ struct intel_guc {
 	struct intel_uc_fw fw;
 	struct intel_guc_log log;
 	struct intel_guc_ct ct;
+	struct intel_guc_slpc slpc;
+
+	/* Global engine used to submit requests to GuC */
+	struct i915_sched_engine *sched_engine;
+	struct i915_request *stalled_request;
 
 	/* intel_guc_recv interrupt related state */
 	spinlock_t irq_lock;
 	unsigned int msg_enabled_mask;
 
+	atomic_t outstanding_submission_g2h;
+
 	struct {
 		void (*reset)(struct intel_guc *guc);
 		void (*enable)(struct intel_guc *guc);
 		void (*disable)(struct intel_guc *guc);
 	} interrupts;
 
+	/*
+	 * contexts_lock protects the pool of free guc ids and a linked list of
+	 * guc ids available to be stolen
+	 */
+	spinlock_t contexts_lock;
+	struct ida guc_ids;
+	struct list_head guc_id_list;
+
+	bool submission_supported;
 	bool submission_selected;
+	bool rc_supported;
+	bool rc_selected;
 
 	struct i915_vma *ads_vma;
 	struct __guc_ads_blob *ads_blob;
+	u32 ads_regset_size;
+	u32 ads_golden_ctxt_size;
 
-	struct i915_vma *stage_desc_pool;
-	void *stage_desc_pool_vaddr;
+	struct i915_vma *lrc_desc_pool;
+	void *lrc_desc_pool_vaddr;
+
+	/* guc_id to intel_context lookup */
+	struct xarray context_lookup;
 
 	/* Control params for fw initialization */
 	u32 params[GUC_CTL_MAX_DWORDS];
@@ -74,7 +101,15 @@ static inline struct intel_guc *log_to_guc(struct intel_guc_log *log)
 static
 inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len)
 {
-	return intel_guc_ct_send(&guc->ct, action, len, NULL, 0);
+	return intel_guc_ct_send(&guc->ct, action, len, NULL, 0, 0);
+}
+
+static
+inline int intel_guc_send_nb(struct intel_guc *guc, const u32 *action, u32 len,
+			     u32 g2h_len_dw)
+{
+	return intel_guc_ct_send(&guc->ct, action, len, NULL, 0,
+				 MAKE_SEND_FLAGS(g2h_len_dw));
 }
 
 static inline int
@@ -82,7 +117,43 @@ intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len,
 			   u32 *response_buf, u32 response_buf_size)
 {
 	return intel_guc_ct_send(&guc->ct, action, len,
-				 response_buf, response_buf_size);
+				 response_buf, response_buf_size, 0);
+}
+
+static inline int intel_guc_send_busy_loop(struct intel_guc *guc,
+					   const u32 *action,
+					   u32 len,
+					   u32 g2h_len_dw,
+					   bool loop)
+{
+	int err;
+	unsigned int sleep_period_ms = 1;
+	bool not_atomic = !in_atomic() && !irqs_disabled();
+
+	/*
+	 * FIXME: Have caller pass in if we are in an atomic context to avoid
+	 * using in_atomic(). It is likely safe here as we check for irqs
+	 * disabled which basically all the spin locks in the i915 do but
+	 * regardless this should be cleaned up.
+	 */
+
+	/* No sleeping with spin locks, just busy loop */
+	might_sleep_if(loop && not_atomic);
+
+retry:
+	err = intel_guc_send_nb(guc, action, len, g2h_len_dw);
+	if (unlikely(err == -EBUSY && loop)) {
+		if (likely(not_atomic)) {
+			if (msleep_interruptible(sleep_period_ms))
+				return -EINTR;
+			sleep_period_ms = sleep_period_ms << 1;
+		} else {
+			cpu_relax();
+		}
+		goto retry;
+	}
+
+	return err;
 }
 
 static inline void intel_guc_to_host_event_handler(struct intel_guc *guc)
@@ -118,6 +189,7 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 }
 
 void intel_guc_init_early(struct intel_guc *guc);
+void intel_guc_init_late(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_write_params(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
@@ -160,9 +232,25 @@ static inline bool intel_guc_is_ready(struct intel_guc *guc)
 	return intel_guc_is_fw_running(guc) && intel_guc_ct_enabled(&guc->ct);
 }
 
+static inline void intel_guc_reset_interrupts(struct intel_guc *guc)
+{
+	guc->interrupts.reset(guc);
+}
+
+static inline void intel_guc_enable_interrupts(struct intel_guc *guc)
+{
+	guc->interrupts.enable(guc);
+}
+
+static inline void intel_guc_disable_interrupts(struct intel_guc *guc)
+{
+	guc->interrupts.disable(guc);
+}
+
 static inline int intel_guc_sanitize(struct intel_guc *guc)
 {
 	intel_uc_fw_sanitize(&guc->fw);
+	intel_guc_disable_interrupts(guc);
 	intel_guc_ct_sanitize(&guc->ct);
 	guc->mmio_msg = 0;
 
@@ -183,8 +271,27 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask)
 	spin_unlock_irq(&guc->irq_lock);
 }
 
-int intel_guc_reset_engine(struct intel_guc *guc,
-			   struct intel_engine_cs *engine);
+int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout);
+
+int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
+					  const u32 *msg, u32 len);
+int intel_guc_sched_done_process_msg(struct intel_guc *guc,
+				     const u32 *msg, u32 len);
+int intel_guc_context_reset_process_msg(struct intel_guc *guc,
+					const u32 *msg, u32 len);
+int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
+					 const u32 *msg, u32 len);
+
+void intel_guc_find_hung_context(struct intel_engine_cs *engine);
+
+int intel_guc_global_policies_update(struct intel_guc *guc);
+
+void intel_guc_context_ban(struct intel_context *ce, struct i915_request *rq);
+
+void intel_guc_submission_reset_prepare(struct intel_guc *guc);
+void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);
+void intel_guc_submission_reset_finish(struct intel_guc *guc);
+void intel_guc_submission_cancel_requests(struct intel_guc *guc);
 
 void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index 9abfbc6edbd6..6926919bcac6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -3,8 +3,11 @@
  * Copyright © 2014-2019 Intel Corporation
  */
 
+#include <linux/bsearch.h>
+
 #include "gt/intel_gt.h"
 #include "gt/intel_lrc.h"
+#include "gt/shmem_utils.h"
 #include "intel_guc_ads.h"
 #include "intel_guc_fwif.h"
 #include "intel_uc.h"
@@ -23,10 +26,15 @@
  *      | guc_policies                          |
  *      +---------------------------------------+
  *      | guc_gt_system_info                    |
- *      +---------------------------------------+
- *      | guc_clients_info                      |
- *      +---------------------------------------+
- *      | guc_ct_pool_entry[size]               |
+ *      +---------------------------------------+ <== static
+ *      | guc_mmio_reg[countA] (engine 0.0)     |
+ *      | guc_mmio_reg[countB] (engine 0.1)     |
+ *      | guc_mmio_reg[countC] (engine 1.0)     |
+ *      |   ...                                 |
+ *      +---------------------------------------+ <== dynamic
+ *      | padding                               |
+ *      +---------------------------------------+ <== 4K aligned
+ *      | golden contexts                       |
  *      +---------------------------------------+
  *      | padding                               |
  *      +---------------------------------------+ <== 4K aligned
@@ -39,18 +47,49 @@ struct __guc_ads_blob {
 	struct guc_ads ads;
 	struct guc_policies policies;
 	struct guc_gt_system_info system_info;
-	struct guc_clients_info clients_info;
-	struct guc_ct_pool_entry ct_pool[GUC_CT_POOL_SIZE];
+	/* From here on, location is dynamic! Refer to above diagram. */
+	struct guc_mmio_reg regset[0];
 } __packed;
 
+static u32 guc_ads_regset_size(struct intel_guc *guc)
+{
+	GEM_BUG_ON(!guc->ads_regset_size);
+	return guc->ads_regset_size;
+}
+
+static u32 guc_ads_golden_ctxt_size(struct intel_guc *guc)
+{
+	return PAGE_ALIGN(guc->ads_golden_ctxt_size);
+}
+
 static u32 guc_ads_private_data_size(struct intel_guc *guc)
 {
 	return PAGE_ALIGN(guc->fw.private_data_size);
 }
 
+static u32 guc_ads_regset_offset(struct intel_guc *guc)
+{
+	return offsetof(struct __guc_ads_blob, regset);
+}
+
+static u32 guc_ads_golden_ctxt_offset(struct intel_guc *guc)
+{
+	u32 offset;
+
+	offset = guc_ads_regset_offset(guc) +
+		 guc_ads_regset_size(guc);
+
+	return PAGE_ALIGN(offset);
+}
+
 static u32 guc_ads_private_data_offset(struct intel_guc *guc)
 {
-	return PAGE_ALIGN(sizeof(struct __guc_ads_blob));
+	u32 offset;
+
+	offset = guc_ads_golden_ctxt_offset(guc) +
+		 guc_ads_golden_ctxt_size(guc);
+
+	return PAGE_ALIGN(offset);
 }
 
 static u32 guc_ads_blob_size(struct intel_guc *guc)
@@ -59,36 +98,66 @@ static u32 guc_ads_blob_size(struct intel_guc *guc)
 	       guc_ads_private_data_size(guc);
 }
 
-static void guc_policy_init(struct guc_policy *policy)
+static void guc_policies_init(struct intel_guc *guc, struct guc_policies *policies)
 {
-	policy->execution_quantum = POLICY_DEFAULT_EXECUTION_QUANTUM_US;
-	policy->preemption_time = POLICY_DEFAULT_PREEMPTION_TIME_US;
-	policy->fault_time = POLICY_DEFAULT_FAULT_TIME_US;
-	policy->policy_flags = 0;
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct drm_i915_private *i915 = gt->i915;
+
+	policies->dpc_promote_time = GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US;
+	policies->max_num_work_items = GLOBAL_POLICY_MAX_NUM_WI;
+
+	policies->global_flags = 0;
+	if (i915->params.reset < 2)
+		policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET;
+
+	policies->is_valid = 1;
 }
 
-static void guc_policies_init(struct guc_policies *policies)
+void intel_guc_ads_print_policy_info(struct intel_guc *guc,
+				     struct drm_printer *dp)
 {
-	struct guc_policy *policy;
-	u32 p, i;
+	struct __guc_ads_blob *blob = guc->ads_blob;
 
-	policies->dpc_promote_time = POLICY_DEFAULT_DPC_PROMOTE_TIME_US;
-	policies->max_num_work_items = POLICY_MAX_NUM_WI;
+	if (unlikely(!blob))
+		return;
 
-	for (p = 0; p < GUC_CLIENT_PRIORITY_NUM; p++) {
-		for (i = 0; i < GUC_MAX_ENGINE_CLASSES; i++) {
-			policy = &policies->policy[p][i];
+	drm_printf(dp, "Global scheduling policies:\n");
+	drm_printf(dp, "  DPC promote time   = %u\n", blob->policies.dpc_promote_time);
+	drm_printf(dp, "  Max num work items = %u\n", blob->policies.max_num_work_items);
+	drm_printf(dp, "  Flags              = %u\n", blob->policies.global_flags);
+}
 
-			guc_policy_init(policy);
-		}
-	}
+static int guc_action_policies_update(struct intel_guc *guc, u32 policy_offset)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE,
+		policy_offset
+	};
 
-	policies->is_valid = 1;
+	return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
 }
 
-static void guc_ct_pool_entries_init(struct guc_ct_pool_entry *pool, u32 num)
+int intel_guc_global_policies_update(struct intel_guc *guc)
 {
-	memset(pool, 0, num * sizeof(*pool));
+	struct __guc_ads_blob *blob = guc->ads_blob;
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_wakeref_t wakeref;
+	int ret;
+
+	if (!blob)
+		return -EOPNOTSUPP;
+
+	GEM_BUG_ON(!blob->ads.scheduler_policies);
+
+	guc_policies_init(guc, &blob->policies);
+
+	if (!intel_guc_is_ready(guc))
+		return 0;
+
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+		ret = guc_action_policies_update(guc, blob->ads.scheduler_policies);
+
+	return ret;
 }
 
 static void guc_mapping_table_init(struct intel_gt *gt,
@@ -113,53 +182,324 @@ static void guc_mapping_table_init(struct intel_gt *gt,
 }
 
 /*
- * The first 80 dwords of the register state context, containing the
- * execlists and ppgtt registers.
+ * The save/restore register list must be pre-calculated to a temporary
+ * buffer of driver defined size before it can be generated in place
+ * inside the ADS.
  */
-#define LR_HW_CONTEXT_SIZE	(80 * sizeof(u32))
+#define MAX_MMIO_REGS	128	/* Arbitrary size, increase as needed */
+struct temp_regset {
+	struct guc_mmio_reg *registers;
+	u32 used;
+	u32 size;
+};
 
-static void __guc_ads_init(struct intel_guc *guc)
+static int guc_mmio_reg_cmp(const void *a, const void *b)
+{
+	const struct guc_mmio_reg *ra = a;
+	const struct guc_mmio_reg *rb = b;
+
+	return (int)ra->offset - (int)rb->offset;
+}
+
+static void guc_mmio_reg_add(struct temp_regset *regset,
+			     u32 offset, u32 flags)
+{
+	u32 count = regset->used;
+	struct guc_mmio_reg reg = {
+		.offset = offset,
+		.flags = flags,
+	};
+	struct guc_mmio_reg *slot;
+
+	GEM_BUG_ON(count >= regset->size);
+
+	/*
+	 * The mmio list is built using separate lists within the driver.
+	 * It's possible that at some point we may attempt to add the same
+	 * register more than once. Do not consider this an error; silently
+	 * move on if the register is already in the list.
+	 */
+	if (bsearch(&reg, regset->registers, count,
+		    sizeof(reg), guc_mmio_reg_cmp))
+		return;
+
+	slot = &regset->registers[count];
+	regset->used++;
+	*slot = reg;
+
+	while (slot-- > regset->registers) {
+		GEM_BUG_ON(slot[0].offset == slot[1].offset);
+		if (slot[1].offset > slot[0].offset)
+			break;
+
+		swap(slot[1], slot[0]);
+	}
+}
+
+#define GUC_MMIO_REG_ADD(regset, reg, masked) \
+	guc_mmio_reg_add(regset, \
+			 i915_mmio_reg_offset((reg)), \
+			 (masked) ? GUC_REGSET_MASKED : 0)
+
+static void guc_mmio_regset_init(struct temp_regset *regset,
+				 struct intel_engine_cs *engine)
+{
+	const u32 base = engine->mmio_base;
+	struct i915_wa_list *wal = &engine->wa_list;
+	struct i915_wa *wa;
+	unsigned int i;
+
+	regset->used = 0;
+
+	GUC_MMIO_REG_ADD(regset, RING_MODE_GEN7(base), true);
+	GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false);
+	GUC_MMIO_REG_ADD(regset, RING_IMR(base), false);
+
+	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
+		GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg);
+
+	/* Be extra paranoid and include all whitelist registers. */
+	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++)
+		GUC_MMIO_REG_ADD(regset,
+				 RING_FORCE_TO_NONPRIV(base, i),
+				 false);
+
+	/* add in local MOCS registers */
+	for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++)
+		GUC_MMIO_REG_ADD(regset, GEN9_LNCFCMOCS(i), false);
+}
+
+static int guc_mmio_reg_state_query(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
-	struct drm_i915_private *i915 = gt->i915;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct temp_regset temp_set;
+	u32 total;
+
+	/*
+	 * Need to actually build the list in order to filter out
+	 * duplicates and other such data dependent constructions.
+	 */
+	temp_set.size = MAX_MMIO_REGS;
+	temp_set.registers = kmalloc_array(temp_set.size,
+					   sizeof(*temp_set.registers),
+					   GFP_KERNEL);
+	if (!temp_set.registers)
+		return -ENOMEM;
+
+	total = 0;
+	for_each_engine(engine, gt, id) {
+		guc_mmio_regset_init(&temp_set, engine);
+		total += temp_set.used;
+	}
+
+	kfree(temp_set.registers);
+
+	return total * sizeof(struct guc_mmio_reg);
+}
+
+static void guc_mmio_reg_state_init(struct intel_guc *guc,
+				    struct __guc_ads_blob *blob)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct temp_regset temp_set;
+	struct guc_mmio_reg_set *ads_reg_set;
+	u32 addr_ggtt, offset;
+	u8 guc_class;
+
+	offset = guc_ads_regset_offset(guc);
+	addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
+	temp_set.registers = (struct guc_mmio_reg *)(((u8 *)blob) + offset);
+	temp_set.size = guc->ads_regset_size / sizeof(temp_set.registers[0]);
+
+	for_each_engine(engine, gt, id) {
+		/* Class index is checked in class converter */
+		GEM_BUG_ON(engine->instance >= GUC_MAX_INSTANCES_PER_CLASS);
+
+		guc_class = engine_class_to_guc_class(engine->class);
+		ads_reg_set = &blob->ads.reg_state_list[guc_class][engine->instance];
+
+		guc_mmio_regset_init(&temp_set, engine);
+		if (!temp_set.used) {
+			ads_reg_set->address = 0;
+			ads_reg_set->count = 0;
+			continue;
+		}
+
+		ads_reg_set->address = addr_ggtt;
+		ads_reg_set->count = temp_set.used;
+
+		temp_set.size -= temp_set.used;
+		temp_set.registers += temp_set.used;
+		addr_ggtt += temp_set.used * sizeof(struct guc_mmio_reg);
+	}
+
+	GEM_BUG_ON(temp_set.size);
+}
+
+static void fill_engine_enable_masks(struct intel_gt *gt,
+				     struct guc_gt_system_info *info)
+{
+	info->engine_enabled_masks[GUC_RENDER_CLASS] = 1;
+	info->engine_enabled_masks[GUC_BLITTER_CLASS] = 1;
+	info->engine_enabled_masks[GUC_VIDEO_CLASS] = VDBOX_MASK(gt);
+	info->engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt);
+}
+
+static int guc_prep_golden_context(struct intel_guc *guc,
+				   struct __guc_ads_blob *blob)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	u32 addr_ggtt, offset;
+	u32 total_size = 0, alloc_size, real_size;
+	u8 engine_class, guc_class;
+	struct guc_gt_system_info *info, local_info;
+
+	/*
+	 * Reserve the memory for the golden contexts and point GuC at it but
+	 * leave it empty for now. The context data will be filled in later
+	 * once there is something available to put there.
+	 *
+	 * Note that the HWSP and ring context are not included.
+	 *
+	 * Note also that the storage must be pinned in the GGTT, so that the
+	 * address won't change after GuC has been told where to find it. The
+	 * GuC will also validate that the LRC base + size fall within the
+	 * allowed GGTT range.
+	 */
+	if (blob) {
+		offset = guc_ads_golden_ctxt_offset(guc);
+		addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
+		info = &blob->system_info;
+	} else {
+		memset(&local_info, 0, sizeof(local_info));
+		info = &local_info;
+		fill_engine_enable_masks(gt, info);
+	}
+
+	for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) {
+		if (engine_class == OTHER_CLASS)
+			continue;
+
+		guc_class = engine_class_to_guc_class(engine_class);
+
+		if (!info->engine_enabled_masks[guc_class])
+			continue;
+
+		real_size = intel_engine_context_size(gt, engine_class);
+		alloc_size = PAGE_ALIGN(real_size);
+		total_size += alloc_size;
+
+		if (!blob)
+			continue;
+
+		blob->ads.eng_state_size[guc_class] = real_size;
+		blob->ads.golden_context_lrca[guc_class] = addr_ggtt;
+		addr_ggtt += alloc_size;
+	}
+
+	if (!blob)
+		return total_size;
+
+	GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size);
+	return total_size;
+}
+
+static struct intel_engine_cs *find_engine_state(struct intel_gt *gt, u8 engine_class)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id) {
+		if (engine->class != engine_class)
+			continue;
+
+		if (!engine->default_state)
+			continue;
+
+		return engine;
+	}
+
+	return NULL;
+}
+
+static void guc_init_golden_context(struct intel_guc *guc)
+{
 	struct __guc_ads_blob *blob = guc->ads_blob;
-	const u32 skipped_size = LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE;
-	u32 base;
+	struct intel_engine_cs *engine;
+	struct intel_gt *gt = guc_to_gt(guc);
+	u32 addr_ggtt, offset;
+	u32 total_size = 0, alloc_size, real_size;
 	u8 engine_class, guc_class;
+	u8 *ptr;
 
-	/* GuC scheduling policies */
-	guc_policies_init(&blob->policies);
+	/* Skip execlist and PPGTT registers + HWSP */
+	const u32 lr_hw_context_size = 80 * sizeof(u32);
+	const u32 skip_size = LRC_PPHWSP_SZ * PAGE_SIZE +
+		lr_hw_context_size;
+
+	if (!intel_uc_uses_guc_submission(&gt->uc))
+		return;
+
+	GEM_BUG_ON(!blob);
 
 	/*
-	 * GuC expects a per-engine-class context image and size
-	 * (minus hwsp and ring context). The context image will be
-	 * used to reinitialize engines after a reset. It must exist
-	 * and be pinned in the GGTT, so that the address won't change after
-	 * we have told GuC where to find it. The context size will be used
-	 * to validate that the LRC base + size fall within allowed GGTT.
+	 * Go back and fill in the golden context data now that it is
+	 * available.
 	 */
+	offset = guc_ads_golden_ctxt_offset(guc);
+	addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
+	ptr = ((u8 *)blob) + offset;
+
 	for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) {
 		if (engine_class == OTHER_CLASS)
 			continue;
 
 		guc_class = engine_class_to_guc_class(engine_class);
 
-		/*
-		 * TODO: Set context pointer to default state to allow
-		 * GuC to re-init guilty contexts after internal reset.
-		 */
-		blob->ads.golden_context_lrca[guc_class] = 0;
-		blob->ads.eng_state_size[guc_class] =
-			intel_engine_context_size(guc_to_gt(guc),
-						  engine_class) -
-			skipped_size;
+		if (!blob->system_info.engine_enabled_masks[guc_class])
+			continue;
+
+		real_size = intel_engine_context_size(gt, engine_class);
+		alloc_size = PAGE_ALIGN(real_size);
+		total_size += alloc_size;
+
+		engine = find_engine_state(gt, engine_class);
+		if (!engine) {
+			drm_err(&gt->i915->drm, "No engine state recorded for class %d!\n",
+				engine_class);
+			blob->ads.eng_state_size[guc_class] = 0;
+			blob->ads.golden_context_lrca[guc_class] = 0;
+			continue;
+		}
+
+		GEM_BUG_ON(blob->ads.eng_state_size[guc_class] != real_size);
+		GEM_BUG_ON(blob->ads.golden_context_lrca[guc_class] != addr_ggtt);
+		addr_ggtt += alloc_size;
+
+		shmem_read(engine->default_state, skip_size, ptr + skip_size,
+			   real_size - skip_size);
+		ptr += alloc_size;
 	}
 
+	GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size);
+}
+
+static void __guc_ads_init(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct drm_i915_private *i915 = gt->i915;
+	struct __guc_ads_blob *blob = guc->ads_blob;
+	u32 base;
+
+	/* GuC scheduling policies */
+	guc_policies_init(guc, &blob->policies);
+
 	/* System info */
-	blob->system_info.engine_enabled_masks[GUC_RENDER_CLASS] = 1;
-	blob->system_info.engine_enabled_masks[GUC_BLITTER_CLASS] = 1;
-	blob->system_info.engine_enabled_masks[GUC_VIDEO_CLASS] = VDBOX_MASK(gt);
-	blob->system_info.engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt);
+	fill_engine_enable_masks(gt, &blob->system_info);
 
 	blob->system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_SLICE_ENABLED] =
 		hweight8(gt->info.sseu.slice_mask);
@@ -174,21 +514,19 @@ static void __guc_ads_init(struct intel_guc *guc)
 			 GEN12_DOORBELLS_PER_SQIDI) + 1;
 	}
 
+	/* Golden contexts for re-initialising after a watchdog reset */
+	guc_prep_golden_context(guc, blob);
+
 	guc_mapping_table_init(guc_to_gt(guc), &blob->system_info);
 
 	base = intel_guc_ggtt_offset(guc, guc->ads_vma);
 
-	/* Clients info  */
-	guc_ct_pool_entries_init(blob->ct_pool, ARRAY_SIZE(blob->ct_pool));
-
-	blob->clients_info.clients_num = 1;
-	blob->clients_info.ct_pool_addr = base + ptr_offset(blob, ct_pool);
-	blob->clients_info.ct_pool_count = ARRAY_SIZE(blob->ct_pool);
-
 	/* ADS */
 	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
 	blob->ads.gt_system_info = base + ptr_offset(blob, system_info);
-	blob->ads.clients_info = base + ptr_offset(blob, clients_info);
+
+	/* MMIO save/restore list */
+	guc_mmio_reg_state_init(guc, blob);
 
 	/* Private Data */
 	blob->ads.private_data = base + guc_ads_private_data_offset(guc);
@@ -210,6 +548,19 @@ int intel_guc_ads_create(struct intel_guc *guc)
 
 	GEM_BUG_ON(guc->ads_vma);
 
+	/* Need to calculate the reg state size dynamically: */
+	ret = guc_mmio_reg_state_query(guc);
+	if (ret < 0)
+		return ret;
+	guc->ads_regset_size = ret;
+
+	/* Likewise the golden contexts: */
+	ret = guc_prep_golden_context(guc, NULL);
+	if (ret < 0)
+		return ret;
+	guc->ads_golden_ctxt_size = ret;
+
+	/* Now the total size can be determined: */
 	size = guc_ads_blob_size(guc);
 
 	ret = intel_guc_allocate_and_map_vma(guc, size, &guc->ads_vma,
@@ -222,6 +573,18 @@ int intel_guc_ads_create(struct intel_guc *guc)
 	return 0;
 }
 
+void intel_guc_ads_init_late(struct intel_guc *guc)
+{
+	/*
+	 * The golden context setup requires the saved engine state from
+	 * __engines_record_defaults(). However, that requires engines to be
+	 * operational which means the ADS must already have been configured.
+	 * Fortunately, the golden context state is not needed until a hang
+	 * occurs, so it can be filled in during this late init phase.
+	 */
+	guc_init_golden_context(guc);
+}
+
 void intel_guc_ads_destroy(struct intel_guc *guc)
 {
 	i915_vma_unpin_and_release(&guc->ads_vma, I915_VMA_RELEASE_MAP);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h
index b00d3ae1113a..3d85051d57e4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h
@@ -7,9 +7,13 @@
 #define _INTEL_GUC_ADS_H_
 
 struct intel_guc;
+struct drm_printer;
 
 int intel_guc_ads_create(struct intel_guc *guc);
 void intel_guc_ads_destroy(struct intel_guc *guc);
+void intel_guc_ads_init_late(struct intel_guc *guc);
 void intel_guc_ads_reset(struct intel_guc *guc);
+void intel_guc_ads_print_policy_info(struct intel_guc *guc,
+				     struct drm_printer *p);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 8f7b148fef58..22b4733b55e2 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -3,6 +3,11 @@
  * Copyright © 2016-2019 Intel Corporation
  */
 
+#include <linux/circ_buf.h>
+#include <linux/ktime.h>
+#include <linux/time64.h>
+#include <linux/timekeeping.h>
+
 #include "i915_drv.h"
 #include "intel_guc_ct.h"
 #include "gt/intel_gt.h"
@@ -58,11 +63,17 @@ static inline struct drm_device *ct_to_drm(struct intel_guc_ct *ct)
  *      +--------+-----------------------------------------------+------+
  *
  * Size of each `CT Buffer`_ must be multiple of 4K.
- * As we don't expect too many messages, for now use minimum sizes.
+ * We don't expect too many messages in flight at any time, unless we are
+ * using the GuC submission. In that case each request requires a minimum
+ * 2 dwords which gives us a maximum 256 queue'd requests. Hopefully this
+ * enough space to avoid backpressure on the driver. We increase the size
+ * of the receive buffer (relative to the send) to ensure a G2H response
+ * CTB has a landing spot.
  */
 #define CTB_DESC_SIZE		ALIGN(sizeof(struct guc_ct_buffer_desc), SZ_2K)
 #define CTB_H2G_BUFFER_SIZE	(SZ_4K)
-#define CTB_G2H_BUFFER_SIZE	(SZ_4K)
+#define CTB_G2H_BUFFER_SIZE	(4 * CTB_H2G_BUFFER_SIZE)
+#define G2H_ROOM_BUFFER_SIZE	(CTB_G2H_BUFFER_SIZE / 4)
 
 struct ct_request {
 	struct list_head link;
@@ -98,66 +109,84 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	INIT_LIST_HEAD(&ct->requests.incoming);
 	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 	tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func);
+	init_waitqueue_head(&ct->wq);
 }
 
 static inline const char *guc_ct_buffer_type_to_str(u32 type)
 {
 	switch (type) {
-	case INTEL_GUC_CT_BUFFER_TYPE_SEND:
+	case GUC_CTB_TYPE_HOST2GUC:
 		return "SEND";
-	case INTEL_GUC_CT_BUFFER_TYPE_RECV:
+	case GUC_CTB_TYPE_GUC2HOST:
 		return "RECV";
 	default:
 		return "<invalid>";
 	}
 }
 
-static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc,
-				    u32 cmds_addr, u32 size)
+static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc)
 {
 	memset(desc, 0, sizeof(*desc));
-	desc->addr = cmds_addr;
-	desc->size = size;
-	desc->owner = CTB_OWNER_HOST;
 }
 
-static void guc_ct_buffer_reset(struct intel_guc_ct_buffer *ctb, u32 cmds_addr)
+static void guc_ct_buffer_reset(struct intel_guc_ct_buffer *ctb)
 {
-	guc_ct_buffer_desc_init(ctb->desc, cmds_addr, ctb->size);
+	u32 space;
+
+	ctb->broken = false;
+	ctb->tail = 0;
+	ctb->head = 0;
+	space = CIRC_SPACE(ctb->tail, ctb->head, ctb->size) - ctb->resv_space;
+	atomic_set(&ctb->space, space);
+
+	guc_ct_buffer_desc_init(ctb->desc);
 }
 
 static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb,
 			       struct guc_ct_buffer_desc *desc,
-			       u32 *cmds, u32 size)
+			       u32 *cmds, u32 size_in_bytes, u32 resv_space)
 {
-	GEM_BUG_ON(size % 4);
+	GEM_BUG_ON(size_in_bytes % 4);
 
 	ctb->desc = desc;
 	ctb->cmds = cmds;
-	ctb->size = size;
+	ctb->size = size_in_bytes / 4;
+	ctb->resv_space = resv_space / 4;
 
-	guc_ct_buffer_reset(ctb, 0);
+	guc_ct_buffer_reset(ctb);
 }
 
-static int guc_action_register_ct_buffer(struct intel_guc *guc,
-					 u32 desc_addr,
-					 u32 type)
+static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type,
+					 u32 desc_addr, u32 buff_addr, u32 size)
 {
-	u32 action[] = {
-		INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER,
-		desc_addr,
-		sizeof(struct guc_ct_buffer_desc),
-		type
+	u32 request[HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN] = {
+		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
+		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_REGISTER_CTB),
+		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE, size / SZ_4K - 1) |
+		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE, type),
+		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr),
+		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr),
 	};
 
-	/* Can't use generic send(), CT registration must go over MMIO */
-	return intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
+	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
+	GEM_BUG_ON(size % SZ_4K);
+
+	/* CT registration must go over MMIO */
+	return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
 }
 
-static int ct_register_buffer(struct intel_guc_ct *ct, u32 desc_addr, u32 type)
+static int ct_register_buffer(struct intel_guc_ct *ct, u32 type,
+			      u32 desc_addr, u32 buff_addr, u32 size)
 {
-	int err = guc_action_register_ct_buffer(ct_to_guc(ct), desc_addr, type);
+	int err;
+
+	err = i915_inject_probe_error(guc_to_gt(ct_to_guc(ct))->i915, -ENXIO);
+	if (unlikely(err))
+		return err;
 
+	err = guc_action_register_ct_buffer(ct_to_guc(ct), type,
+					    desc_addr, buff_addr, size);
 	if (unlikely(err))
 		CT_ERROR(ct, "Failed to register %s buffer (err=%d)\n",
 			 guc_ct_buffer_type_to_str(type), err);
@@ -166,14 +195,17 @@ static int ct_register_buffer(struct intel_guc_ct *ct, u32 desc_addr, u32 type)
 
 static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type)
 {
-	u32 action[] = {
-		INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER,
-		CTB_OWNER_HOST,
-		type
+	u32 request[HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN] = {
+		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
+		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB),
+		FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type),
 	};
 
-	/* Can't use generic send(), CT deregistration must go over MMIO */
-	return intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
+	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
+
+	/* CT deregistration must go over MMIO */
+	return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
 }
 
 static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type)
@@ -200,10 +232,15 @@ int intel_guc_ct_init(struct intel_guc_ct *ct)
 	struct guc_ct_buffer_desc *desc;
 	u32 blob_size;
 	u32 cmds_size;
+	u32 resv_space;
 	void *blob;
 	u32 *cmds;
 	int err;
 
+	err = i915_inject_probe_error(guc_to_gt(guc)->i915, -ENXIO);
+	if (err)
+		return err;
+
 	GEM_BUG_ON(ct->vma);
 
 	blob_size = 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE + CTB_G2H_BUFFER_SIZE;
@@ -220,19 +257,23 @@ int intel_guc_ct_init(struct intel_guc_ct *ct)
 	desc = blob;
 	cmds = blob + 2 * CTB_DESC_SIZE;
 	cmds_size = CTB_H2G_BUFFER_SIZE;
-	CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "send",
-		 ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size);
+	resv_space = 0;
+	CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "send",
+		 ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size,
+		 resv_space);
 
-	guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size);
+	guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size, resv_space);
 
 	/* store pointers to desc and cmds for recv ctb */
 	desc = blob + CTB_DESC_SIZE;
 	cmds = blob + 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE;
 	cmds_size = CTB_G2H_BUFFER_SIZE;
-	CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "recv",
-		 ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size);
+	resv_space = G2H_ROOM_BUFFER_SIZE;
+	CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "recv",
+		 ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size,
+		 resv_space);
 
-	guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size);
+	guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size, resv_space);
 
 	return 0;
 }
@@ -261,7 +302,7 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct)
 int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
 	struct intel_guc *guc = ct_to_guc(ct);
-	u32 base, cmds;
+	u32 base, desc, cmds;
 	void *blob;
 	int err;
 
@@ -277,32 +318,36 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 	GEM_BUG_ON(blob != ct->ctbs.send.desc);
 
 	/* (re)initialize descriptors */
-	cmds = base + ptrdiff(ct->ctbs.send.cmds, blob);
-	guc_ct_buffer_reset(&ct->ctbs.send, cmds);
-
-	cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob);
-	guc_ct_buffer_reset(&ct->ctbs.recv, cmds);
+	guc_ct_buffer_reset(&ct->ctbs.send);
+	guc_ct_buffer_reset(&ct->ctbs.recv);
 
 	/*
 	 * Register both CT buffers starting with RECV buffer.
 	 * Descriptors are in first half of the blob.
 	 */
-	err = ct_register_buffer(ct, base + ptrdiff(ct->ctbs.recv.desc, blob),
-				 INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	desc = base + ptrdiff(ct->ctbs.recv.desc, blob);
+	cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob);
+	err = ct_register_buffer(ct, GUC_CTB_TYPE_GUC2HOST,
+				 desc, cmds, ct->ctbs.recv.size * 4);
+
 	if (unlikely(err))
 		goto err_out;
 
-	err = ct_register_buffer(ct, base + ptrdiff(ct->ctbs.send.desc, blob),
-				 INTEL_GUC_CT_BUFFER_TYPE_SEND);
+	desc = base + ptrdiff(ct->ctbs.send.desc, blob);
+	cmds = base + ptrdiff(ct->ctbs.send.cmds, blob);
+	err = ct_register_buffer(ct, GUC_CTB_TYPE_HOST2GUC,
+				 desc, cmds, ct->ctbs.send.size * 4);
+
 	if (unlikely(err))
 		goto err_deregister;
 
 	ct->enabled = true;
+	ct->stall_time = KTIME_MAX;
 
 	return 0;
 
 err_deregister:
-	ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
 err_out:
 	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
 	return err;
@@ -321,8 +366,8 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct)
 	ct->enabled = false;
 
 	if (intel_guc_is_fw_running(guc)) {
-		ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_SEND);
-		ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_RECV);
+		ct_deregister_buffer(ct, GUC_CTB_TYPE_HOST2GUC);
+		ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
 	}
 }
 
@@ -354,81 +399,63 @@ static void write_barrier(struct intel_guc_ct *ct)
 	}
 }
 
-/**
- * DOC: CTB Host to GuC request
- *
- * Format of the CTB Host to GuC request message is as follows::
- *
- *      +------------+---------+---------+---------+---------+
- *      |   msg[0]   |   [1]   |   [2]   |   ...   |  [n-1]  |
- *      +------------+---------+---------+---------+---------+
- *      |   MESSAGE  |       MESSAGE PAYLOAD                 |
- *      +   HEADER   +---------+---------+---------+---------+
- *      |            |    0    |    1    |   ...   |    n    |
- *      +============+=========+=========+=========+=========+
- *      |  len >= 1  |  FENCE  |     request specific data   |
- *      +------+-----+---------+---------+---------+---------+
- *
- *                   ^-----------------len-------------------^
- */
-
 static int ct_write(struct intel_guc_ct *ct,
 		    const u32 *action,
 		    u32 len /* in dwords */,
-		    u32 fence)
+		    u32 fence, u32 flags)
 {
 	struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
 	struct guc_ct_buffer_desc *desc = ctb->desc;
-	u32 head = desc->head;
-	u32 tail = desc->tail;
+	u32 tail = ctb->tail;
 	u32 size = ctb->size;
-	u32 used;
 	u32 header;
+	u32 hxg;
+	u32 type;
 	u32 *cmds = ctb->cmds;
 	unsigned int i;
 
-	if (unlikely(desc->is_in_error))
-		return -EPIPE;
-
-	if (unlikely(!IS_ALIGNED(head | tail, 4) ||
-		     (tail | head) >= size))
+	if (unlikely(desc->status))
 		goto corrupted;
 
-	/* later calculations will be done in dwords */
-	head /= 4;
-	tail /= 4;
-	size /= 4;
-
-	/*
-	 * tail == head condition indicates empty. GuC FW does not support
-	 * using up the entire buffer to get tail == head meaning full.
-	 */
-	if (tail < head)
-		used = (size - head) + tail;
-	else
-		used = tail - head;
+	GEM_BUG_ON(tail > size);
 
-	/* make sure there is a space including extra dw for the fence */
-	if (unlikely(used + len + 1 >= size))
-		return -ENOSPC;
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+	if (unlikely(tail != READ_ONCE(desc->tail))) {
+		CT_ERROR(ct, "Tail was modified %u != %u\n",
+			 desc->tail, tail);
+		desc->status |= GUC_CTB_STATUS_MISMATCH;
+		goto corrupted;
+	}
+	if (unlikely(READ_ONCE(desc->head) >= size)) {
+		CT_ERROR(ct, "Invalid head offset %u >= %u)\n",
+			 desc->head, size);
+		desc->status |= GUC_CTB_STATUS_OVERFLOW;
+		goto corrupted;
+	}
+#endif
 
 	/*
-	 * Write the message. The format is the following:
-	 * DW0: header (including action code)
-	 * DW1: fence
-	 * DW2+: action data
+	 * dw0: CT header (including fence)
+	 * dw1: HXG header (including action code)
+	 * dw2+: action data
 	 */
-	header = (len << GUC_CT_MSG_LEN_SHIFT) |
-		 GUC_CT_MSG_SEND_STATUS |
-		 (action[0] << GUC_CT_MSG_ACTION_SHIFT);
+	header = FIELD_PREP(GUC_CTB_MSG_0_FORMAT, GUC_CTB_FORMAT_HXG) |
+		 FIELD_PREP(GUC_CTB_MSG_0_NUM_DWORDS, len) |
+		 FIELD_PREP(GUC_CTB_MSG_0_FENCE, fence);
 
-	CT_DEBUG(ct, "writing %*ph %*ph %*ph\n",
-		 4, &header, 4, &fence, 4 * (len - 1), &action[1]);
+	type = (flags & INTEL_GUC_CT_SEND_NB) ? GUC_HXG_TYPE_EVENT :
+		GUC_HXG_TYPE_REQUEST;
+	hxg = FIELD_PREP(GUC_HXG_MSG_0_TYPE, type) |
+		FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
+			   GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
+
+	CT_DEBUG(ct, "writing (tail %u) %*ph %*ph %*ph\n",
+		 tail, 4, &header, 4, &hxg, 4 * (len - 1), &action[1]);
 
 	cmds[tail] = header;
 	tail = (tail + 1) % size;
 
-	cmds[tail] = fence;
+	cmds[tail] = hxg;
 	tail = (tail + 1) % size;
 
 	for (i = 1; i < len; i++) {
@@ -443,14 +470,20 @@ static int ct_write(struct intel_guc_ct *ct,
 	 */
 	write_barrier(ct);
 
-	/* now update desc tail (back in bytes) */
-	desc->tail = tail * 4;
+	/* update local copies */
+	ctb->tail = tail;
+	GEM_BUG_ON(atomic_read(&ctb->space) < len + GUC_CTB_HDR_LEN);
+	atomic_sub(len + GUC_CTB_HDR_LEN, &ctb->space);
+
+	/* now update descriptor */
+	WRITE_ONCE(desc->tail, tail);
+
 	return 0;
 
 corrupted:
-	CT_ERROR(ct, "Corrupted descriptor addr=%#x head=%u tail=%u size=%u\n",
-		 desc->addr, desc->head, desc->tail, desc->size);
-	desc->is_in_error = 1;
+	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
+		 desc->head, desc->tail, desc->status);
+	ctb->broken = true;
 	return -EPIPE;
 }
 
@@ -459,7 +492,7 @@ corrupted:
  * @req:	pointer to pending request
  * @status:	placeholder for status
  *
- * For each sent request, Guc shall send bac CT response message.
+ * For each sent request, GuC shall send back CT response message.
  * Our message handler will update status of tracked request once
  * response message with given fence is received. Wait here and
  * check for valid response status value.
@@ -475,12 +508,18 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 	/*
 	 * Fast commands should complete in less than 10us, so sample quickly
 	 * up to that length of time, then switch to a slower sleep-wait loop.
-	 * No GuC command should ever take longer than 10ms.
+	 * No GuC command should ever take longer than 10ms but many GuC
+	 * commands can be inflight at time, so use a 1s timeout on the slower
+	 * sleep-wait loop.
 	 */
-#define done INTEL_GUC_MSG_IS_RESPONSE(READ_ONCE(req->status))
-	err = wait_for_us(done, 10);
+#define GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS 10
+#define GUC_CTB_RESPONSE_TIMEOUT_LONG_MS 1000
+#define done \
+	(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \
+	 GUC_HXG_ORIGIN_GUC)
+	err = wait_for_us(done, GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS);
 	if (err)
-		err = wait_for(done, 10);
+		err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS);
 #undef done
 
 	if (unlikely(err))
@@ -490,6 +529,131 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 	return err;
 }
 
+#define GUC_CTB_TIMEOUT_MS	1500
+static inline bool ct_deadlocked(struct intel_guc_ct *ct)
+{
+	long timeout = GUC_CTB_TIMEOUT_MS;
+	bool ret = ktime_ms_delta(ktime_get(), ct->stall_time) > timeout;
+
+	if (unlikely(ret)) {
+		struct guc_ct_buffer_desc *send = ct->ctbs.send.desc;
+		struct guc_ct_buffer_desc *recv = ct->ctbs.send.desc;
+
+		CT_ERROR(ct, "Communication stalled for %lld ms, desc status=%#x,%#x\n",
+			 ktime_ms_delta(ktime_get(), ct->stall_time),
+			 send->status, recv->status);
+		ct->ctbs.send.broken = true;
+	}
+
+	return ret;
+}
+
+static inline bool g2h_has_room(struct intel_guc_ct *ct, u32 g2h_len_dw)
+{
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs.recv;
+
+	/*
+	 * We leave a certain amount of space in the G2H CTB buffer for
+	 * unexpected G2H CTBs (e.g. logging, engine hang, etc...)
+	 */
+	return !g2h_len_dw || atomic_read(&ctb->space) >= g2h_len_dw;
+}
+
+static inline void g2h_reserve_space(struct intel_guc_ct *ct, u32 g2h_len_dw)
+{
+	lockdep_assert_held(&ct->ctbs.send.lock);
+
+	GEM_BUG_ON(!g2h_has_room(ct, g2h_len_dw));
+
+	if (g2h_len_dw)
+		atomic_sub(g2h_len_dw, &ct->ctbs.recv.space);
+}
+
+static inline void g2h_release_space(struct intel_guc_ct *ct, u32 g2h_len_dw)
+{
+	atomic_add(g2h_len_dw, &ct->ctbs.recv.space);
+}
+
+static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw)
+{
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
+	struct guc_ct_buffer_desc *desc = ctb->desc;
+	u32 head;
+	u32 space;
+
+	if (atomic_read(&ctb->space) >= len_dw)
+		return true;
+
+	head = READ_ONCE(desc->head);
+	if (unlikely(head > ctb->size)) {
+		CT_ERROR(ct, "Invalid head offset %u >= %u)\n",
+			 head, ctb->size);
+		desc->status |= GUC_CTB_STATUS_OVERFLOW;
+		ctb->broken = true;
+		return false;
+	}
+
+	space = CIRC_SPACE(ctb->tail, head, ctb->size);
+	atomic_set(&ctb->space, space);
+
+	return space >= len_dw;
+}
+
+static int has_room_nb(struct intel_guc_ct *ct, u32 h2g_dw, u32 g2h_dw)
+{
+	lockdep_assert_held(&ct->ctbs.send.lock);
+
+	if (unlikely(!h2g_has_room(ct, h2g_dw) || !g2h_has_room(ct, g2h_dw))) {
+		if (ct->stall_time == KTIME_MAX)
+			ct->stall_time = ktime_get();
+
+		if (unlikely(ct_deadlocked(ct)))
+			return -EPIPE;
+		else
+			return -EBUSY;
+	}
+
+	ct->stall_time = KTIME_MAX;
+	return 0;
+}
+
+#define G2H_LEN_DW(f) ({ \
+	typeof(f) f_ = (f); \
+	FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) ? \
+	FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) + \
+	GUC_CTB_HXG_MSG_MIN_LEN : 0; \
+})
+static int ct_send_nb(struct intel_guc_ct *ct,
+		      const u32 *action,
+		      u32 len,
+		      u32 flags)
+{
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
+	unsigned long spin_flags;
+	u32 g2h_len_dw = G2H_LEN_DW(flags);
+	u32 fence;
+	int ret;
+
+	spin_lock_irqsave(&ctb->lock, spin_flags);
+
+	ret = has_room_nb(ct, len + GUC_CTB_HDR_LEN, g2h_len_dw);
+	if (unlikely(ret))
+		goto out;
+
+	fence = ct_get_next_fence(ct);
+	ret = ct_write(ct, action, len, fence, flags);
+	if (unlikely(ret))
+		goto out;
+
+	g2h_reserve_space(ct, g2h_len_dw);
+	intel_guc_notify(ct_to_guc(ct));
+
+out:
+	spin_unlock_irqrestore(&ctb->lock, spin_flags);
+
+	return ret;
+}
+
 static int ct_send(struct intel_guc_ct *ct,
 		   const u32 *action,
 		   u32 len,
@@ -497,8 +661,10 @@ static int ct_send(struct intel_guc_ct *ct,
 		   u32 response_buf_size,
 		   u32 *status)
 {
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
 	struct ct_request request;
 	unsigned long flags;
+	unsigned int sleep_period_ms = 1;
 	u32 fence;
 	int err;
 
@@ -506,8 +672,33 @@ static int ct_send(struct intel_guc_ct *ct,
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK);
 	GEM_BUG_ON(!response_buf && response_buf_size);
+	might_sleep();
+
+	/*
+	 * We use a lazy spin wait loop here as we believe that if the CT
+	 * buffers are sized correctly the flow control condition should be
+	 * rare. Reserving the maximum size in the G2H credits as we don't know
+	 * how big the response is going to be.
+	 */
+retry:
+	spin_lock_irqsave(&ctb->lock, flags);
+	if (unlikely(!h2g_has_room(ct, len + GUC_CTB_HDR_LEN) ||
+		     !g2h_has_room(ct, GUC_CTB_HXG_MSG_MAX_LEN))) {
+		if (ct->stall_time == KTIME_MAX)
+			ct->stall_time = ktime_get();
+		spin_unlock_irqrestore(&ctb->lock, flags);
+
+		if (unlikely(ct_deadlocked(ct)))
+			return -EPIPE;
+
+		if (msleep_interruptible(sleep_period_ms))
+			return -EINTR;
+		sleep_period_ms = sleep_period_ms << 1;
+
+		goto retry;
+	}
 
-	spin_lock_irqsave(&ct->ctbs.send.lock, flags);
+	ct->stall_time = KTIME_MAX;
 
 	fence = ct_get_next_fence(ct);
 	request.fence = fence;
@@ -519,9 +710,10 @@ static int ct_send(struct intel_guc_ct *ct,
 	list_add_tail(&request.link, &ct->requests.pending);
 	spin_unlock(&ct->requests.lock);
 
-	err = ct_write(ct, action, len, fence);
+	err = ct_write(ct, action, len, fence, 0);
+	g2h_reserve_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
 
-	spin_unlock_irqrestore(&ct->ctbs.send.lock, flags);
+	spin_unlock_irqrestore(&ctb->lock, flags);
 
 	if (unlikely(err))
 		goto unlink;
@@ -529,24 +721,25 @@ static int ct_send(struct intel_guc_ct *ct,
 	intel_guc_notify(ct_to_guc(ct));
 
 	err = wait_for_ct_request_update(&request, status);
+	g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
 	if (unlikely(err))
 		goto unlink;
 
-	if (!INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(*status)) {
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) {
 		err = -EIO;
 		goto unlink;
 	}
 
 	if (response_buf) {
 		/* There shall be no data in the status */
-		WARN_ON(INTEL_GUC_MSG_TO_DATA(request.status));
+		WARN_ON(FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, request.status));
 		/* Return actual response len */
 		err = request.response_len;
 	} else {
 		/* There shall be no response payload */
 		WARN_ON(request.response_len);
 		/* Return data decoded from the status dword */
-		err = INTEL_GUC_MSG_TO_DATA(*status);
+		err = FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, *status);
 	}
 
 unlink:
@@ -561,16 +754,25 @@ unlink:
  * Command Transport (CT) buffer based GuC send function.
  */
 int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
-		      u32 *response_buf, u32 response_buf_size)
+		      u32 *response_buf, u32 response_buf_size, u32 flags)
 {
 	u32 status = ~0; /* undefined */
 	int ret;
 
 	if (unlikely(!ct->enabled)) {
-		WARN(1, "Unexpected send: action=%#x\n", *action);
+		struct intel_guc *guc = ct_to_guc(ct);
+		struct intel_uc *uc = container_of(guc, struct intel_uc, guc);
+
+		WARN(!uc->reset_in_progress, "Unexpected send: action=%#x\n", *action);
 		return -ENODEV;
 	}
 
+	if (unlikely(ct->ctbs.send.broken))
+		return -EPIPE;
+
+	if (flags & INTEL_GUC_CT_SEND_NB)
+		return ct_send_nb(ct, action, len, flags);
+
 	ret = ct_send(ct, action, len, response_buf, response_buf_size, &status);
 	if (unlikely(ret < 0)) {
 		CT_ERROR(ct, "Sending action %#x failed (err=%d status=%#X)\n",
@@ -583,21 +785,6 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 	return ret;
 }
 
-static inline unsigned int ct_header_get_len(u32 header)
-{
-	return (header >> GUC_CT_MSG_LEN_SHIFT) & GUC_CT_MSG_LEN_MASK;
-}
-
-static inline unsigned int ct_header_get_action(u32 header)
-{
-	return (header >> GUC_CT_MSG_ACTION_SHIFT) & GUC_CT_MSG_ACTION_MASK;
-}
-
-static inline bool ct_header_is_response(u32 header)
-{
-	return !!(header & GUC_CT_MSG_IS_RESPONSE);
-}
-
 static struct ct_incoming_msg *ct_alloc_msg(u32 num_dwords)
 {
 	struct ct_incoming_msg *msg;
@@ -621,8 +808,8 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 {
 	struct intel_guc_ct_buffer *ctb = &ct->ctbs.recv;
 	struct guc_ct_buffer_desc *desc = ctb->desc;
-	u32 head = desc->head;
-	u32 tail = desc->tail;
+	u32 head = ctb->head;
+	u32 tail = READ_ONCE(desc->tail);
 	u32 size = ctb->size;
 	u32 *cmds = ctb->cmds;
 	s32 available;
@@ -630,17 +817,28 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	unsigned int i;
 	u32 header;
 
-	if (unlikely(desc->is_in_error))
+	if (unlikely(ctb->broken))
 		return -EPIPE;
 
-	if (unlikely(!IS_ALIGNED(head | tail, 4) ||
-		     (tail | head) >= size))
+	if (unlikely(desc->status))
 		goto corrupted;
 
-	/* later calculations will be done in dwords */
-	head /= 4;
-	tail /= 4;
-	size /= 4;
+	GEM_BUG_ON(head > size);
+
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+	if (unlikely(head != READ_ONCE(desc->head))) {
+		CT_ERROR(ct, "Head was modified %u != %u\n",
+			 desc->head, head);
+		desc->status |= GUC_CTB_STATUS_MISMATCH;
+		goto corrupted;
+	}
+#endif
+	if (unlikely(tail >= size)) {
+		CT_ERROR(ct, "Invalid tail offset %u >= %u)\n",
+			 tail, size);
+		desc->status |= GUC_CTB_STATUS_OVERFLOW;
+		goto corrupted;
+	}
 
 	/* tail == head condition indicates empty */
 	available = tail - head;
@@ -652,14 +850,14 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	/* beware of buffer wrap case */
 	if (unlikely(available < 0))
 		available += size;
-	CT_DEBUG(ct, "available %d (%u:%u)\n", available, head, tail);
+	CT_DEBUG(ct, "available %d (%u:%u:%u)\n", available, head, tail, size);
 	GEM_BUG_ON(available < 0);
 
 	header = cmds[head];
 	head = (head + 1) % size;
 
 	/* message len with header */
-	len = ct_header_get_len(header) + 1;
+	len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, header) + GUC_CTB_MSG_MIN_LEN;
 	if (unlikely(len > (u32)available)) {
 		CT_ERROR(ct, "Incomplete message %*ph %*ph %*ph\n",
 			 4, &header,
@@ -667,6 +865,7 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 			      size - head : available - 1), &cmds[head],
 			 4 * (head + available - 1 > size ?
 			      available - 1 - size + head : 0), &cmds[0]);
+		desc->status |= GUC_CTB_STATUS_UNDERFLOW;
 		goto corrupted;
 	}
 
@@ -689,65 +888,39 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	}
 	CT_DEBUG(ct, "received %*ph\n", 4 * len, (*msg)->msg);
 
-	desc->head = head * 4;
+	/* update local copies */
+	ctb->head = head;
+
+	/* now update descriptor */
+	WRITE_ONCE(desc->head, head);
+
 	return available - len;
 
 corrupted:
-	CT_ERROR(ct, "Corrupted descriptor addr=%#x head=%u tail=%u size=%u\n",
-		 desc->addr, desc->head, desc->tail, desc->size);
-	desc->is_in_error = 1;
+	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
+		 desc->head, desc->tail, desc->status);
+	ctb->broken = true;
 	return -EPIPE;
 }
 
-/**
- * DOC: CTB GuC to Host response
- *
- * Format of the CTB GuC to Host response message is as follows::
- *
- *      +------------+---------+---------+---------+---------+---------+
- *      |   msg[0]   |   [1]   |   [2]   |   [3]   |   ...   |  [n-1]  |
- *      +------------+---------+---------+---------+---------+---------+
- *      |   MESSAGE  |       MESSAGE PAYLOAD                           |
- *      +   HEADER   +---------+---------+---------+---------+---------+
- *      |            |    0    |    1    |    2    |   ...   |    n    |
- *      +============+=========+=========+=========+=========+=========+
- *      |  len >= 2  |  FENCE  |  STATUS |   response specific data    |
- *      +------+-----+---------+---------+---------+---------+---------+
- *
- *                   ^-----------------------len-----------------------^
- */
-
 static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *response)
 {
-	u32 header = response->msg[0];
-	u32 len = ct_header_get_len(header);
-	u32 fence;
-	u32 status;
-	u32 datalen;
+	u32 len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, response->msg[0]);
+	u32 fence = FIELD_GET(GUC_CTB_MSG_0_FENCE, response->msg[0]);
+	const u32 *hxg = &response->msg[GUC_CTB_MSG_MIN_LEN];
+	const u32 *data = &hxg[GUC_HXG_MSG_MIN_LEN];
+	u32 datalen = len - GUC_HXG_MSG_MIN_LEN;
 	struct ct_request *req;
 	unsigned long flags;
 	bool found = false;
 	int err = 0;
 
-	GEM_BUG_ON(!ct_header_is_response(header));
-
-	/* Response payload shall at least include fence and status */
-	if (unlikely(len < 2)) {
-		CT_ERROR(ct, "Corrupted response (len %u)\n", len);
-		return -EPROTO;
-	}
-
-	fence = response->msg[1];
-	status = response->msg[2];
-	datalen = len - 2;
-
-	/* Format of the status follows RESPONSE message */
-	if (unlikely(!INTEL_GUC_MSG_IS_RESPONSE(status))) {
-		CT_ERROR(ct, "Corrupted response (status %#x)\n", status);
-		return -EPROTO;
-	}
+	GEM_BUG_ON(len < GUC_HXG_MSG_MIN_LEN);
+	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]) != GUC_HXG_ORIGIN_GUC);
+	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_SUCCESS &&
+		   FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_FAILURE);
 
-	CT_DEBUG(ct, "response fence %u status %#x\n", fence, status);
+	CT_DEBUG(ct, "response fence %u status %#x\n", fence, hxg[0]);
 
 	spin_lock_irqsave(&ct->requests.lock, flags);
 	list_for_each_entry(req, &ct->requests.pending, link) {
@@ -763,18 +936,22 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 			err = -EMSGSIZE;
 		}
 		if (datalen)
-			memcpy(req->response_buf, response->msg + 3, 4 * datalen);
+			memcpy(req->response_buf, data, 4 * datalen);
 		req->response_len = datalen;
-		WRITE_ONCE(req->status, status);
+		WRITE_ONCE(req->status, hxg[0]);
 		found = true;
 		break;
 	}
-	spin_unlock_irqrestore(&ct->requests.lock, flags);
-
 	if (!found) {
 		CT_ERROR(ct, "Unsolicited response (fence %u)\n", fence);
-		return -ENOKEY;
+		CT_ERROR(ct, "Could not find fence=%u, last_fence=%u\n", fence,
+			 ct->requests.last_fence);
+		list_for_each_entry(req, &ct->requests.pending, link)
+			CT_ERROR(ct, "request %u awaits response\n",
+				 req->fence);
+		err = -ENOKEY;
 	}
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	if (unlikely(err))
 		return err;
@@ -786,14 +963,16 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *request)
 {
 	struct intel_guc *guc = ct_to_guc(ct);
-	u32 header, action, len;
+	const u32 *hxg;
 	const u32 *payload;
+	u32 hxg_len, action, len;
 	int ret;
 
-	header = request->msg[0];
-	payload = &request->msg[1];
-	action = ct_header_get_action(header);
-	len = ct_header_get_len(header);
+	hxg = &request->msg[GUC_CTB_MSG_MIN_LEN];
+	hxg_len = request->size - GUC_CTB_MSG_MIN_LEN;
+	payload = &hxg[GUC_HXG_MSG_MIN_LEN];
+	action = FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, hxg[0]);
+	len = hxg_len - GUC_HXG_MSG_MIN_LEN;
 
 	CT_DEBUG(ct, "request %x %*ph\n", action, 4 * len, payload);
 
@@ -801,6 +980,19 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	case INTEL_GUC_ACTION_DEFAULT:
 		ret = intel_guc_to_host_process_recv_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE:
+		ret = intel_guc_deregister_done_process_msg(guc, payload,
+							    len);
+		break;
+	case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE:
+		ret = intel_guc_sched_done_process_msg(guc, payload, len);
+		break;
+	case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION:
+		ret = intel_guc_context_reset_process_msg(guc, payload, len);
+		break;
+	case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION:
+		ret = intel_guc_engine_failure_process_msg(guc, payload, len);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -855,29 +1047,24 @@ static void ct_incoming_request_worker_func(struct work_struct *w)
 		queue_work(system_unbound_wq, &ct->requests.worker);
 }
 
-/**
- * DOC: CTB GuC to Host request
- *
- * Format of the CTB GuC to Host request message is as follows::
- *
- *      +------------+---------+---------+---------+---------+---------+
- *      |   msg[0]   |   [1]   |   [2]   |   [3]   |   ...   |  [n-1]  |
- *      +------------+---------+---------+---------+---------+---------+
- *      |   MESSAGE  |       MESSAGE PAYLOAD                           |
- *      +   HEADER   +---------+---------+---------+---------+---------+
- *      |            |    0    |    1    |    2    |   ...   |    n    |
- *      +============+=========+=========+=========+=========+=========+
- *      |     len    |            request specific data                |
- *      +------+-----+---------+---------+---------+---------+---------+
- *
- *                   ^-----------------------len-----------------------^
- */
-
-static int ct_handle_request(struct intel_guc_ct *ct, struct ct_incoming_msg *request)
+static int ct_handle_event(struct intel_guc_ct *ct, struct ct_incoming_msg *request)
 {
+	const u32 *hxg = &request->msg[GUC_CTB_MSG_MIN_LEN];
+	u32 action = FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, hxg[0]);
 	unsigned long flags;
 
-	GEM_BUG_ON(ct_header_is_response(request->msg[0]));
+	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_EVENT);
+
+	/*
+	 * Adjusting the space must be done in IRQ or deadlock can occur as the
+	 * CTB processing in the below workqueue can send CTBs which creates a
+	 * circular dependency if the space was returned there.
+	 */
+	switch (action) {
+	case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE:
+	case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE:
+		g2h_release_space(ct, request->size);
+	}
 
 	spin_lock_irqsave(&ct->requests.lock, flags);
 	list_add_tail(&request->link, &ct->requests.incoming);
@@ -887,15 +1074,53 @@ static int ct_handle_request(struct intel_guc_ct *ct, struct ct_incoming_msg *re
 	return 0;
 }
 
-static void ct_handle_msg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg)
+static int ct_handle_hxg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg)
 {
-	u32 header = msg->msg[0];
+	u32 origin, type;
+	u32 *hxg;
 	int err;
 
-	if (ct_header_is_response(header))
+	if (unlikely(msg->size < GUC_CTB_HXG_MSG_MIN_LEN))
+		return -EBADMSG;
+
+	hxg = &msg->msg[GUC_CTB_MSG_MIN_LEN];
+
+	origin = FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]);
+	if (unlikely(origin != GUC_HXG_ORIGIN_GUC)) {
+		err = -EPROTO;
+		goto failed;
+	}
+
+	type = FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]);
+	switch (type) {
+	case GUC_HXG_TYPE_EVENT:
+		err = ct_handle_event(ct, msg);
+		break;
+	case GUC_HXG_TYPE_RESPONSE_SUCCESS:
+	case GUC_HXG_TYPE_RESPONSE_FAILURE:
 		err = ct_handle_response(ct, msg);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	if (unlikely(err)) {
+failed:
+		CT_ERROR(ct, "Failed to handle HXG message (%pe) %*ph\n",
+			 ERR_PTR(err), 4 * GUC_HXG_MSG_MIN_LEN, hxg);
+	}
+	return err;
+}
+
+static void ct_handle_msg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg)
+{
+	u32 format = FIELD_GET(GUC_CTB_MSG_0_FORMAT, msg->msg[0]);
+	int err;
+
+	if (format == GUC_CTB_FORMAT_HXG)
+		err = ct_handle_hxg(ct, msg);
 	else
-		err = ct_handle_request(ct, msg);
+		err = -EOPNOTSUPP;
 
 	if (unlikely(err)) {
 		CT_ERROR(ct, "Failed to process CT message (%pe) %*ph\n",
@@ -958,3 +1183,25 @@ void intel_guc_ct_event_handler(struct intel_guc_ct *ct)
 
 	ct_try_receive_message(ct);
 }
+
+void intel_guc_ct_print_info(struct intel_guc_ct *ct,
+			     struct drm_printer *p)
+{
+	drm_printf(p, "CT %s\n", enableddisabled(ct->enabled));
+
+	if (!ct->enabled)
+		return;
+
+	drm_printf(p, "H2G Space: %u\n",
+		   atomic_read(&ct->ctbs.send.space) * 4);
+	drm_printf(p, "Head: %u\n",
+		   ct->ctbs.send.desc->head);
+	drm_printf(p, "Tail: %u\n",
+		   ct->ctbs.send.desc->tail);
+	drm_printf(p, "G2H Space: %u\n",
+		   atomic_read(&ct->ctbs.recv.space) * 4);
+	drm_printf(p, "Head: %u\n",
+		   ct->ctbs.recv.desc->head);
+	drm_printf(p, "Tail: %u\n",
+		   ct->ctbs.recv.desc->tail);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
index cb222f202301..f709a19c7e21 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
@@ -9,11 +9,14 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
+#include <linux/ktime.h>
+#include <linux/wait.h>
 
 #include "intel_guc_fwif.h"
 
 struct i915_vma;
 struct intel_guc;
+struct drm_printer;
 
 /**
  * DOC: Command Transport (CT).
@@ -31,16 +34,25 @@ struct intel_guc;
  * @lock: protects access to the commands buffer and buffer descriptor
  * @desc: pointer to the buffer descriptor
  * @cmds: pointer to the commands buffer
- * @size: size of the commands buffer
+ * @size: size of the commands buffer in dwords
+ * @resv_space: reserved space in buffer in dwords
+ * @head: local shadow copy of head in dwords
+ * @tail: local shadow copy of tail in dwords
+ * @space: local shadow copy of space in dwords
+ * @broken: flag to indicate if descriptor data is broken
  */
 struct intel_guc_ct_buffer {
 	spinlock_t lock;
 	struct guc_ct_buffer_desc *desc;
 	u32 *cmds;
 	u32 size;
+	u32 resv_space;
+	u32 tail;
+	u32 head;
+	atomic_t space;
+	bool broken;
 };
 
-
 /** Top-level structure for Command Transport related data
  *
  * Includes a pair of CT buffers for bi-directional communication and tracking
@@ -58,8 +70,11 @@ struct intel_guc_ct {
 
 	struct tasklet_struct receive_tasklet;
 
+	/** @wq: wait queue for g2h chanenl */
+	wait_queue_head_t wq;
+
 	struct {
-		u32 last_fence; /* last fence used to send request */
+		u16 last_fence; /* last fence used to send request */
 
 		spinlock_t lock; /* protects pending requests list */
 		struct list_head pending; /* requests waiting for response */
@@ -67,6 +82,9 @@ struct intel_guc_ct {
 		struct list_head incoming; /* incoming requests */
 		struct work_struct worker; /* handler for incoming requests */
 	} requests;
+
+	/** @stall_time: time of first time a CTB submission is stalled */
+	ktime_t stall_time;
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);
@@ -85,8 +103,18 @@ static inline bool intel_guc_ct_enabled(struct intel_guc_ct *ct)
 	return ct->enabled;
 }
 
+#define INTEL_GUC_CT_SEND_NB		BIT(31)
+#define INTEL_GUC_CT_SEND_G2H_DW_SHIFT	0
+#define INTEL_GUC_CT_SEND_G2H_DW_MASK	(0xff << INTEL_GUC_CT_SEND_G2H_DW_SHIFT)
+#define MAKE_SEND_FLAGS(len) ({ \
+	typeof(len) len_ = (len); \
+	GEM_BUG_ON(!FIELD_FIT(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_)); \
+	(FIELD_PREP(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_) | INTEL_GUC_CT_SEND_NB); \
+})
 int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
-		      u32 *response_buf, u32 response_buf_size);
+		      u32 *response_buf, u32 response_buf_size, u32 flags);
 void intel_guc_ct_event_handler(struct intel_guc_ct *ct);
 
+void intel_guc_ct_print_info(struct intel_guc_ct *ct, struct drm_printer *p);
+
 #endif /* _INTEL_GUC_CT_H_ */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
index fe7cb7b29a1e..887c8c8f35db 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
@@ -9,6 +9,10 @@
 #include "intel_guc.h"
 #include "intel_guc_debugfs.h"
 #include "intel_guc_log_debugfs.h"
+#include "gt/uc/intel_guc_ct.h"
+#include "gt/uc/intel_guc_ads.h"
+#include "gt/uc/intel_guc_submission.h"
+#include "gt/uc/intel_guc_slpc.h"
 
 static int guc_info_show(struct seq_file *m, void *data)
 {
@@ -22,16 +26,57 @@ static int guc_info_show(struct seq_file *m, void *data)
 	drm_puts(&p, "\n");
 	intel_guc_log_info(&guc->log, &p);
 
-	/* Add more as required ... */
+	if (!intel_guc_submission_is_used(guc))
+		return 0;
+
+	intel_guc_ct_print_info(&guc->ct, &p);
+	intel_guc_submission_print_info(guc, &p);
+	intel_guc_ads_print_policy_info(guc, &p);
 
 	return 0;
 }
 DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info);
 
+static int guc_registered_contexts_show(struct seq_file *m, void *data)
+{
+	struct intel_guc *guc = m->private;
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	if (!intel_guc_submission_is_used(guc))
+		return -ENODEV;
+
+	intel_guc_submission_print_context_info(guc, &p);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_registered_contexts);
+
+static int guc_slpc_info_show(struct seq_file *m, void *unused)
+{
+	struct intel_guc *guc = m->private;
+	struct intel_guc_slpc *slpc = &guc->slpc;
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	if (!intel_guc_slpc_is_used(guc))
+		return -ENODEV;
+
+	return intel_guc_slpc_print_info(slpc, &p);
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_slpc_info);
+
+static bool intel_eval_slpc_support(void *data)
+{
+	struct intel_guc *guc = (struct intel_guc *)data;
+
+	return intel_guc_slpc_is_used(guc);
+}
+
 void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
 {
 	static const struct debugfs_gt_file files[] = {
 		{ "guc_info", &guc_info_fops, NULL },
+		{ "guc_registered_contexts", &guc_registered_contexts_fops, NULL },
+		{ "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support},
 	};
 
 	if (!intel_guc_is_supported(guc))
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index e9a9d85e2aa3..fa4be13c8854 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -12,19 +12,27 @@
 #include "gt/intel_engine_types.h"
 
 #include "abi/guc_actions_abi.h"
+#include "abi/guc_actions_slpc_abi.h"
 #include "abi/guc_errors_abi.h"
 #include "abi/guc_communication_mmio_abi.h"
 #include "abi/guc_communication_ctb_abi.h"
 #include "abi/guc_messages_abi.h"
 
+/* Payload length only i.e. don't include G2H header length */
+#define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET	2
+#define G2H_LEN_DW_DEREGISTER_CONTEXT		1
+
+#define GUC_CONTEXT_DISABLE		0
+#define GUC_CONTEXT_ENABLE		1
+
 #define GUC_CLIENT_PRIORITY_KMD_HIGH	0
 #define GUC_CLIENT_PRIORITY_HIGH	1
 #define GUC_CLIENT_PRIORITY_KMD_NORMAL	2
 #define GUC_CLIENT_PRIORITY_NORMAL	3
 #define GUC_CLIENT_PRIORITY_NUM		4
 
-#define GUC_MAX_STAGE_DESCRIPTORS	1024
-#define	GUC_INVALID_STAGE_ID		GUC_MAX_STAGE_DESCRIPTORS
+#define GUC_MAX_LRC_DESCRIPTORS		65535
+#define	GUC_INVALID_LRC_ID		GUC_MAX_LRC_DESCRIPTORS
 
 #define GUC_RENDER_ENGINE		0
 #define GUC_VIDEO_ENGINE		1
@@ -81,15 +89,14 @@
 #define   GUC_LOG_ALLOC_IN_MEGABYTE	(1 << 3)
 #define   GUC_LOG_CRASH_SHIFT		4
 #define   GUC_LOG_CRASH_MASK		(0x3 << GUC_LOG_CRASH_SHIFT)
-#define   GUC_LOG_DPC_SHIFT		6
-#define   GUC_LOG_DPC_MASK	        (0x7 << GUC_LOG_DPC_SHIFT)
-#define   GUC_LOG_ISR_SHIFT		9
-#define   GUC_LOG_ISR_MASK	        (0x7 << GUC_LOG_ISR_SHIFT)
+#define   GUC_LOG_DEBUG_SHIFT		6
+#define   GUC_LOG_DEBUG_MASK	        (0xF << GUC_LOG_DEBUG_SHIFT)
 #define   GUC_LOG_BUF_ADDR_SHIFT	12
 
 #define GUC_CTL_WA			1
 #define GUC_CTL_FEATURE			2
 #define   GUC_CTL_DISABLE_SCHEDULER	(1 << 14)
+#define   GUC_CTL_ENABLE_SLPC		BIT(2)
 
 #define GUC_CTL_DEBUG			3
 #define   GUC_LOG_VERBOSITY_SHIFT	0
@@ -136,6 +143,11 @@
 #define GUC_ID_TO_ENGINE_INSTANCE(guc_id) \
 	(((guc_id) & GUC_ENGINE_INSTANCE_MASK) >> GUC_ENGINE_INSTANCE_SHIFT)
 
+#define SLPC_EVENT(id, c) (\
+FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID, id) | \
+FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC, c) \
+)
+
 static inline u8 engine_class_to_guc_class(u8 class)
 {
 	BUILD_BUG_ON(GUC_RENDER_CLASS != RENDER_CLASS);
@@ -177,66 +189,40 @@ struct guc_process_desc {
 	u32 reserved[30];
 } __packed;
 
-/* engine id and context id is packed into guc_execlist_context.context_id*/
-#define GUC_ELC_CTXID_OFFSET		0
-#define GUC_ELC_ENGINE_OFFSET		29
+#define CONTEXT_REGISTRATION_FLAG_KMD	BIT(0)
 
-/* The execlist context including software and HW information */
-struct guc_execlist_context {
-	u32 context_desc;
-	u32 context_id;
-	u32 ring_status;
-	u32 ring_lrca;
-	u32 ring_begin;
-	u32 ring_end;
-	u32 ring_next_free_location;
-	u32 ring_current_tail_pointer_value;
-	u8 engine_state_submit_value;
-	u8 engine_state_wait_value;
-	u16 pagefault_count;
-	u16 engine_submit_queue_count;
-} __packed;
+#define CONTEXT_POLICY_DEFAULT_EXECUTION_QUANTUM_US 1000000
+#define CONTEXT_POLICY_DEFAULT_PREEMPTION_TIME_US 500000
+
+/* Preempt to idle on quantum expiry */
+#define CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE	BIT(0)
 
 /*
- * This structure describes a stage set arranged for a particular communication
- * between uKernel (GuC) and Driver (KMD). Technically, this is known as a
- * "GuC Context descriptor" in the specs, but we use the term "stage descriptor"
- * to avoid confusion with all the other things already named "context" in the
- * driver. A static pool of these descriptors are stored inside a GEM object
- * (stage_desc_pool) which is held for the entire lifetime of our interaction
- * with the GuC, being allocated before the GuC is loaded with its firmware.
+ * GuC Context registration descriptor.
+ * FIXME: This is only required to exist during context registration.
+ * The current 1:1 between guc_lrc_desc and LRCs for the lifetime of the LRC
+ * is not required.
  */
-struct guc_stage_desc {
-	u32 sched_common_area;
-	u32 stage_id;
-	u32 pas_id;
-	u8 engines_used;
-	u64 db_trigger_cpu;
-	u32 db_trigger_uk;
-	u64 db_trigger_phy;
-	u16 db_id;
-
-	struct guc_execlist_context lrc[GUC_MAX_ENGINES_NUM];
-
-	u8 attribute;
-
+struct guc_lrc_desc {
+	u32 hw_context_desc;
+	u32 slpm_perf_mode_hint;	/* SPLC v1 only */
+	u32 slpm_freq_hint;
+	u32 engine_submit_mask;		/* In logical space */
+	u8 engine_class;
+	u8 reserved0[3];
 	u32 priority;
-
-	u32 wq_sampled_tail_offset;
-	u32 wq_total_submit_enqueues;
-
 	u32 process_desc;
 	u32 wq_addr;
 	u32 wq_size;
-
-	u32 engine_presence;
-
-	u8 engine_suspended;
-
-	u8 reserved0[3];
-	u64 reserved1[1];
-
-	u64 desc_private;
+	u32 context_flags;		/* CONTEXT_REGISTRATION_* */
+	/* Time for one workload to execute. (in micro seconds) */
+	u32 execution_quantum;
+	/* Time to wait for a preemption request to complete before issuing a
+	 * reset. (in micro seconds).
+	 */
+	u32 preemption_timeout;
+	u32 policy_flags;		/* CONTEXT_POLICY_* */
+	u32 reserved1[19];
 } __packed;
 
 #define GUC_POWER_UNSPECIFIED	0
@@ -247,32 +233,14 @@ struct guc_stage_desc {
 
 /* Scheduling policy settings */
 
-/* Reset engine upon preempt failure */
-#define POLICY_RESET_ENGINE		(1<<0)
-/* Preempt to idle on quantum expiry */
-#define POLICY_PREEMPT_TO_IDLE		(1<<1)
+#define GLOBAL_POLICY_MAX_NUM_WI 15
 
-#define POLICY_MAX_NUM_WI 15
-#define POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000
-#define POLICY_DEFAULT_EXECUTION_QUANTUM_US 1000000
-#define POLICY_DEFAULT_PREEMPTION_TIME_US 500000
-#define POLICY_DEFAULT_FAULT_TIME_US 250000
+/* Don't reset an engine upon preemption failure */
+#define GLOBAL_POLICY_DISABLE_ENGINE_RESET				BIT(0)
 
-struct guc_policy {
-	/* Time for one workload to execute. (in micro seconds) */
-	u32 execution_quantum;
-	/* Time to wait for a preemption request to completed before issuing a
-	 * reset. (in micro seconds). */
-	u32 preemption_time;
-	/* How much time to allow to run after the first fault is observed.
-	 * Then preempt afterwards. (in micro seconds) */
-	u32 fault_time;
-	u32 policy_flags;
-	u32 reserved[8];
-} __packed;
+#define GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000
 
 struct guc_policies {
-	struct guc_policy policy[GUC_CLIENT_PRIORITY_NUM][GUC_MAX_ENGINE_CLASSES];
 	u32 submission_queue_depth[GUC_MAX_ENGINE_CLASSES];
 	/* In micro seconds. How much time to allow before DPC processing is
 	 * called back via interrupt (to prevent DPC queue drain starving).
@@ -286,6 +254,7 @@ struct guc_policies {
 	 * idle. */
 	u32 max_num_work_items;
 
+	u32 global_flags;
 	u32 reserved[4];
 } __packed;
 
@@ -311,29 +280,13 @@ struct guc_gt_system_info {
 	u32 generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_MAX];
 } __packed;
 
-/* Clients info */
-struct guc_ct_pool_entry {
-	struct guc_ct_buffer_desc desc;
-	u32 reserved[7];
-} __packed;
-
-#define GUC_CT_POOL_SIZE	2
-
-struct guc_clients_info {
-	u32 clients_num;
-	u32 reserved0[13];
-	u32 ct_pool_addr;
-	u32 ct_pool_count;
-	u32 reserved[4];
-} __packed;
-
 /* GuC Additional Data Struct */
 struct guc_ads {
 	struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS];
 	u32 reserved0;
 	u32 scheduler_policies;
 	u32 gt_system_info;
-	u32 clients_info;
+	u32 reserved1;
 	u32 control_data;
 	u32 golden_context_lrca[GUC_MAX_ENGINE_CLASSES];
 	u32 eng_state_size[GUC_MAX_ENGINE_CLASSES];
@@ -344,8 +297,7 @@ struct guc_ads {
 /* GuC logging structures */
 
 enum guc_log_buffer_type {
-	GUC_ISR_LOG_BUFFER,
-	GUC_DPC_LOG_BUFFER,
+	GUC_DEBUG_LOG_BUFFER,
 	GUC_CRASH_DUMP_LOG_BUFFER,
 	GUC_MAX_LOG_BUFFER
 };
@@ -414,23 +366,6 @@ struct guc_shared_ctx_data {
 	struct guc_ctx_report preempt_ctx_report[GUC_MAX_ENGINES_NUM];
 } __packed;
 
-#define __INTEL_GUC_MSG_GET(T, m) \
-	(((m) & INTEL_GUC_MSG_ ## T ## _MASK) >> INTEL_GUC_MSG_ ## T ## _SHIFT)
-#define INTEL_GUC_MSG_TO_TYPE(m)	__INTEL_GUC_MSG_GET(TYPE, m)
-#define INTEL_GUC_MSG_TO_DATA(m)	__INTEL_GUC_MSG_GET(DATA, m)
-#define INTEL_GUC_MSG_TO_CODE(m)	__INTEL_GUC_MSG_GET(CODE, m)
-
-#define __INTEL_GUC_MSG_TYPE_IS(T, m) \
-	(INTEL_GUC_MSG_TO_TYPE(m) == INTEL_GUC_MSG_TYPE_ ## T)
-#define INTEL_GUC_MSG_IS_REQUEST(m)	__INTEL_GUC_MSG_TYPE_IS(REQUEST, m)
-#define INTEL_GUC_MSG_IS_RESPONSE(m)	__INTEL_GUC_MSG_TYPE_IS(RESPONSE, m)
-
-#define INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(m) \
-	 (typecheck(u32, (m)) && \
-	  ((m) & (INTEL_GUC_MSG_TYPE_MASK | INTEL_GUC_MSG_CODE_MASK)) == \
-	  ((INTEL_GUC_MSG_TYPE_RESPONSE << INTEL_GUC_MSG_TYPE_SHIFT) | \
-	   (INTEL_GUC_RESPONSE_STATUS_SUCCESS << INTEL_GUC_MSG_CODE_SHIFT)))
-
 /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */
 enum intel_guc_recv_message {
 	INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1),
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index c36d5eb5bbb9..ac0931f0374b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -197,10 +197,8 @@ static bool guc_check_log_buf_overflow(struct intel_guc_log *log,
 static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
 {
 	switch (type) {
-	case GUC_ISR_LOG_BUFFER:
-		return ISR_BUFFER_SIZE;
-	case GUC_DPC_LOG_BUFFER:
-		return DPC_BUFFER_SIZE;
+	case GUC_DEBUG_LOG_BUFFER:
+		return DEBUG_BUFFER_SIZE;
 	case GUC_CRASH_DUMP_LOG_BUFFER:
 		return CRASH_BUFFER_SIZE;
 	default:
@@ -245,7 +243,7 @@ static void guc_read_update_log_buffer(struct intel_guc_log *log)
 	src_data += PAGE_SIZE;
 	dst_data += PAGE_SIZE;
 
-	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
+	for (type = GUC_DEBUG_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
 		/*
 		 * Make a copy of the state structure, inside GuC log buffer
 		 * (which is uncached mapped), on the stack to avoid reading
@@ -463,21 +461,16 @@ int intel_guc_log_create(struct intel_guc_log *log)
 	 *  +===============================+ 00B
 	 *  |    Crash dump state header    |
 	 *  +-------------------------------+ 32B
-	 *  |       DPC state header        |
+	 *  |      Debug state header       |
 	 *  +-------------------------------+ 64B
-	 *  |       ISR state header        |
-	 *  +-------------------------------+ 96B
 	 *  |                               |
 	 *  +===============================+ PAGE_SIZE (4KB)
 	 *  |        Crash Dump logs        |
 	 *  +===============================+ + CRASH_SIZE
-	 *  |           DPC logs            |
-	 *  +===============================+ + DPC_SIZE
-	 *  |           ISR logs            |
-	 *  +===============================+ + ISR_SIZE
+	 *  |          Debug logs           |
+	 *  +===============================+ + DEBUG_SIZE
 	 */
-	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DPC_BUFFER_SIZE +
-			ISR_BUFFER_SIZE;
+	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE;
 
 	vma = intel_guc_allocate_vma(guc, guc_log_size);
 	if (IS_ERR(vma)) {
@@ -675,10 +668,8 @@ static const char *
 stringify_guc_log_type(enum guc_log_buffer_type type)
 {
 	switch (type) {
-	case GUC_ISR_LOG_BUFFER:
-		return "ISR";
-	case GUC_DPC_LOG_BUFFER:
-		return "DPC";
+	case GUC_DEBUG_LOG_BUFFER:
+		return "DEBUG";
 	case GUC_CRASH_DUMP_LOG_BUFFER:
 		return "CRASH";
 	default:
@@ -708,7 +699,7 @@ void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p)
 
 	drm_printf(p, "\tRelay full count: %u\n", log->relay.full_count);
 
-	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
+	for (type = GUC_DEBUG_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
 		drm_printf(p, "\t%s:\tflush count %10u, overflow count %10u\n",
 			   stringify_guc_log_type(type),
 			   log->stats[type].flush,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
index 11fccd0b2294..ac1ee1d5ce10 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
@@ -17,12 +17,10 @@ struct intel_guc;
 
 #ifdef CONFIG_DRM_I915_DEBUG_GUC
 #define CRASH_BUFFER_SIZE	SZ_2M
-#define DPC_BUFFER_SIZE		SZ_8M
-#define ISR_BUFFER_SIZE		SZ_8M
+#define DEBUG_BUFFER_SIZE	SZ_16M
 #else
 #define CRASH_BUFFER_SIZE	SZ_8K
-#define DPC_BUFFER_SIZE		SZ_32K
-#define ISR_BUFFER_SIZE		SZ_32K
+#define DEBUG_BUFFER_SIZE	SZ_64K
 #endif
 
 /*
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
new file mode 100644
index 000000000000..fc805d466d99
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include "intel_guc_rc.h"
+#include "gt/intel_gt.h"
+#include "i915_drv.h"
+
+static bool __guc_rc_supported(struct intel_guc *guc)
+{
+	/* GuC RC is unavailable for pre-Gen12 */
+	return guc->submission_supported &&
+		GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12;
+}
+
+static bool __guc_rc_selected(struct intel_guc *guc)
+{
+	if (!intel_guc_rc_is_supported(guc))
+		return false;
+
+	return guc->submission_selected;
+}
+
+void intel_guc_rc_init_early(struct intel_guc *guc)
+{
+	guc->rc_supported = __guc_rc_supported(guc);
+	guc->rc_selected = __guc_rc_selected(guc);
+}
+
+static int guc_action_control_gucrc(struct intel_guc *guc, bool enable)
+{
+	u32 rc_mode = enable ? INTEL_GUCRC_FIRMWARE_CONTROL :
+				INTEL_GUCRC_HOST_CONTROL;
+	u32 action[] = {
+		INTEL_GUC_ACTION_SETUP_PC_GUCRC,
+		rc_mode
+	};
+	int ret;
+
+	ret = intel_guc_send(guc, action, ARRAY_SIZE(action));
+	ret = ret > 0 ? -EPROTO : ret;
+
+	return ret;
+}
+
+static int __guc_rc_control(struct intel_guc *guc, bool enable)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct drm_device *drm = &guc_to_gt(guc)->i915->drm;
+	int ret;
+
+	if (!intel_uc_uses_guc_rc(&gt->uc))
+		return -EOPNOTSUPP;
+
+	if (!intel_guc_is_ready(guc))
+		return -EINVAL;
+
+	ret = guc_action_control_gucrc(guc, enable);
+	if (ret) {
+		drm_err(drm, "Failed to %s GuC RC (%pe)\n",
+			enabledisable(enable), ERR_PTR(ret));
+		return ret;
+	}
+
+	drm_info(&gt->i915->drm, "GuC RC: %s\n",
+		 enableddisabled(enable));
+
+	return 0;
+}
+
+int intel_guc_rc_enable(struct intel_guc *guc)
+{
+	return __guc_rc_control(guc, true);
+}
+
+int intel_guc_rc_disable(struct intel_guc *guc)
+{
+	return __guc_rc_control(guc, false);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h
new file mode 100644
index 000000000000..57e86c337838
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _INTEL_GUC_RC_H_
+#define _INTEL_GUC_RC_H_
+
+#include "intel_guc_submission.h"
+
+void intel_guc_rc_init_early(struct intel_guc *guc);
+
+static inline bool intel_guc_rc_is_supported(struct intel_guc *guc)
+{
+	return guc->rc_supported;
+}
+
+static inline bool intel_guc_rc_is_wanted(struct intel_guc *guc)
+{
+	return guc->submission_selected && intel_guc_rc_is_supported(guc);
+}
+
+static inline bool intel_guc_rc_is_used(struct intel_guc *guc)
+{
+	return intel_guc_submission_is_used(guc) && intel_guc_rc_is_wanted(guc);
+}
+
+int intel_guc_rc_enable(struct intel_guc *guc);
+int intel_guc_rc_disable(struct intel_guc *guc);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
new file mode 100644
index 000000000000..65a3e7fdb2b2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_guc_slpc.h"
+#include "gt/intel_gt.h"
+
+static inline struct intel_guc *slpc_to_guc(struct intel_guc_slpc *slpc)
+{
+	return container_of(slpc, struct intel_guc, slpc);
+}
+
+static inline struct intel_gt *slpc_to_gt(struct intel_guc_slpc *slpc)
+{
+	return guc_to_gt(slpc_to_guc(slpc));
+}
+
+static inline struct drm_i915_private *slpc_to_i915(struct intel_guc_slpc *slpc)
+{
+	return slpc_to_gt(slpc)->i915;
+}
+
+static bool __detect_slpc_supported(struct intel_guc *guc)
+{
+	/* GuC SLPC is unavailable for pre-Gen12 */
+	return guc->submission_supported &&
+		GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12;
+}
+
+static bool __guc_slpc_selected(struct intel_guc *guc)
+{
+	if (!intel_guc_slpc_is_supported(guc))
+		return false;
+
+	return guc->submission_selected;
+}
+
+void intel_guc_slpc_init_early(struct intel_guc_slpc *slpc)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+
+	slpc->supported = __detect_slpc_supported(guc);
+	slpc->selected = __guc_slpc_selected(guc);
+}
+
+static void slpc_mem_set_param(struct slpc_shared_data *data,
+			       u32 id, u32 value)
+{
+	GEM_BUG_ON(id >= SLPC_MAX_OVERRIDE_PARAMETERS);
+	/*
+	 * When the flag bit is set, corresponding value will be read
+	 * and applied by SLPC.
+	 */
+	data->override_params.bits[id >> 5] |= (1 << (id % 32));
+	data->override_params.values[id] = value;
+}
+
+static void slpc_mem_set_enabled(struct slpc_shared_data *data,
+				 u8 enable_id, u8 disable_id)
+{
+	/*
+	 * Enabling a param involves setting the enable_id
+	 * to 1 and disable_id to 0.
+	 */
+	slpc_mem_set_param(data, enable_id, 1);
+	slpc_mem_set_param(data, disable_id, 0);
+}
+
+static void slpc_mem_set_disabled(struct slpc_shared_data *data,
+				  u8 enable_id, u8 disable_id)
+{
+	/*
+	 * Disabling a param involves setting the enable_id
+	 * to 0 and disable_id to 1.
+	 */
+	slpc_mem_set_param(data, disable_id, 1);
+	slpc_mem_set_param(data, enable_id, 0);
+}
+
+int intel_guc_slpc_init(struct intel_guc_slpc *slpc)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data));
+	int err;
+
+	GEM_BUG_ON(slpc->vma);
+
+	err = intel_guc_allocate_and_map_vma(guc, size, &slpc->vma, (void **)&slpc->vaddr);
+	if (unlikely(err)) {
+		drm_err(&i915->drm,
+			"Failed to allocate SLPC struct (err=%pe)\n",
+			ERR_PTR(err));
+		return err;
+	}
+
+	slpc->max_freq_softlimit = 0;
+	slpc->min_freq_softlimit = 0;
+
+	return err;
+}
+
+static u32 slpc_get_state(struct intel_guc_slpc *slpc)
+{
+	struct slpc_shared_data *data;
+
+	GEM_BUG_ON(!slpc->vma);
+
+	drm_clflush_virt_range(slpc->vaddr, sizeof(u32));
+	data = slpc->vaddr;
+
+	return data->header.global_state;
+}
+
+static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_PARAMETER_SET, 2),
+		id,
+		value,
+	};
+	int ret;
+
+	ret = intel_guc_send(guc, request, ARRAY_SIZE(request));
+
+	return ret > 0 ? -EPROTO : ret;
+}
+
+static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 2),
+		id,
+	};
+
+	return intel_guc_send(guc, request, ARRAY_SIZE(request));
+}
+
+static bool slpc_is_running(struct intel_guc_slpc *slpc)
+{
+	return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING;
+}
+
+static int guc_action_slpc_query(struct intel_guc *guc, u32 offset)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_QUERY_TASK_STATE, 2),
+		offset,
+		0,
+	};
+	int ret;
+
+	ret = intel_guc_send(guc, request, ARRAY_SIZE(request));
+
+	return ret > 0 ? -EPROTO : ret;
+}
+
+static int slpc_query_task_state(struct intel_guc_slpc *slpc)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	u32 offset = intel_guc_ggtt_offset(guc, slpc->vma);
+	int ret;
+
+	ret = guc_action_slpc_query(guc, offset);
+	if (unlikely(ret))
+		drm_err(&i915->drm, "Failed to query task state (%pe)\n",
+			ERR_PTR(ret));
+
+	drm_clflush_virt_range(slpc->vaddr, SLPC_PAGE_SIZE_BYTES);
+
+	return ret;
+}
+
+static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	int ret;
+
+	GEM_BUG_ON(id >= SLPC_MAX_PARAM);
+
+	ret = guc_action_slpc_set_param(guc, id, value);
+	if (ret)
+		drm_err(&i915->drm, "Failed to set param %d to %u (%pe)\n",
+			id, value, ERR_PTR(ret));
+
+	return ret;
+}
+
+static int slpc_unset_param(struct intel_guc_slpc *slpc,
+			    u8 id)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+
+	GEM_BUG_ON(id >= SLPC_MAX_PARAM);
+
+	return guc_action_slpc_unset_param(guc, id);
+}
+
+static const char *slpc_global_state_to_string(enum slpc_global_state state)
+{
+	switch (state) {
+	case SLPC_GLOBAL_STATE_NOT_RUNNING:
+		return "not running";
+	case SLPC_GLOBAL_STATE_INITIALIZING:
+		return "initializing";
+	case SLPC_GLOBAL_STATE_RESETTING:
+		return "resetting";
+	case SLPC_GLOBAL_STATE_RUNNING:
+		return "running";
+	case SLPC_GLOBAL_STATE_SHUTTING_DOWN:
+		return "shutting down";
+	case SLPC_GLOBAL_STATE_ERROR:
+		return "error";
+	default:
+		return "unknown";
+	}
+}
+
+static const char *slpc_get_state_string(struct intel_guc_slpc *slpc)
+{
+	return slpc_global_state_to_string(slpc_get_state(slpc));
+}
+
+static int guc_action_slpc_reset(struct intel_guc *guc, u32 offset)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_RESET, 2),
+		offset,
+		0,
+	};
+	int ret;
+
+	ret = intel_guc_send(guc, request, ARRAY_SIZE(request));
+
+	return ret > 0 ? -EPROTO : ret;
+}
+
+static int slpc_reset(struct intel_guc_slpc *slpc)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	struct intel_guc *guc = slpc_to_guc(slpc);
+	u32 offset = intel_guc_ggtt_offset(guc, slpc->vma);
+	int ret;
+
+	ret = guc_action_slpc_reset(guc, offset);
+
+	if (unlikely(ret < 0)) {
+		drm_err(&i915->drm, "SLPC reset action failed (%pe)\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	if (!ret) {
+		if (wait_for(slpc_is_running(slpc), SLPC_RESET_TIMEOUT_MS)) {
+			drm_err(&i915->drm, "SLPC not enabled! State = %s\n",
+				slpc_get_state_string(slpc));
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static u32 slpc_decode_min_freq(struct intel_guc_slpc *slpc)
+{
+	struct slpc_shared_data *data = slpc->vaddr;
+
+	GEM_BUG_ON(!slpc->vma);
+
+	return	DIV_ROUND_CLOSEST(REG_FIELD_GET(SLPC_MIN_UNSLICE_FREQ_MASK,
+				  data->task_state_data.freq) *
+				  GT_FREQUENCY_MULTIPLIER, GEN9_FREQ_SCALER);
+}
+
+static u32 slpc_decode_max_freq(struct intel_guc_slpc *slpc)
+{
+	struct slpc_shared_data *data = slpc->vaddr;
+
+	GEM_BUG_ON(!slpc->vma);
+
+	return	DIV_ROUND_CLOSEST(REG_FIELD_GET(SLPC_MAX_UNSLICE_FREQ_MASK,
+				  data->task_state_data.freq) *
+				  GT_FREQUENCY_MULTIPLIER, GEN9_FREQ_SCALER);
+}
+
+static void slpc_shared_data_reset(struct slpc_shared_data *data)
+{
+	memset(data, 0, sizeof(struct slpc_shared_data));
+
+	data->header.size = sizeof(struct slpc_shared_data);
+
+	/* Enable only GTPERF task, disable others */
+	slpc_mem_set_enabled(data, SLPC_PARAM_TASK_ENABLE_GTPERF,
+			     SLPC_PARAM_TASK_DISABLE_GTPERF);
+
+	slpc_mem_set_disabled(data, SLPC_PARAM_TASK_ENABLE_BALANCER,
+			      SLPC_PARAM_TASK_DISABLE_BALANCER);
+
+	slpc_mem_set_disabled(data, SLPC_PARAM_TASK_ENABLE_DCC,
+			      SLPC_PARAM_TASK_DISABLE_DCC);
+}
+
+/**
+ * intel_guc_slpc_set_max_freq() - Set max frequency limit for SLPC.
+ * @slpc: pointer to intel_guc_slpc.
+ * @val: frequency (MHz)
+ *
+ * This function will invoke GuC SLPC action to update the max frequency
+ * limit for unslice.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 val)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret;
+
+	if (val < slpc->min_freq ||
+	    val > slpc->rp0_freq ||
+	    val < slpc->min_freq_softlimit)
+		return -EINVAL;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_set_param(slpc,
+				     SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ,
+				     val);
+
+		/* Return standardized err code for sysfs calls */
+		if (ret)
+			ret = -EIO;
+	}
+
+	if (!ret)
+		slpc->max_freq_softlimit = val;
+
+	return ret;
+}
+
+/**
+ * intel_guc_slpc_get_max_freq() - Get max frequency limit for SLPC.
+ * @slpc: pointer to intel_guc_slpc.
+ * @val: pointer to val which will hold max frequency (MHz)
+ *
+ * This function will invoke GuC SLPC action to read the max frequency
+ * limit for unslice.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		/* Force GuC to update task data */
+		ret = slpc_query_task_state(slpc);
+
+		if (!ret)
+			*val = slpc_decode_max_freq(slpc);
+	}
+
+	return ret;
+}
+
+/**
+ * intel_guc_slpc_set_min_freq() - Set min frequency limit for SLPC.
+ * @slpc: pointer to intel_guc_slpc.
+ * @val: frequency (MHz)
+ *
+ * This function will invoke GuC SLPC action to update the min unslice
+ * frequency.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret;
+
+	if (val < slpc->min_freq ||
+	    val > slpc->rp0_freq ||
+	    val > slpc->max_freq_softlimit)
+		return -EINVAL;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_set_param(slpc,
+				     SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
+				     val);
+
+		/* Return standardized err code for sysfs calls */
+		if (ret)
+			ret = -EIO;
+	}
+
+	if (!ret)
+		slpc->min_freq_softlimit = val;
+
+	return ret;
+}
+
+/**
+ * intel_guc_slpc_get_min_freq() - Get min frequency limit for SLPC.
+ * @slpc: pointer to intel_guc_slpc.
+ * @val: pointer to val which will hold min frequency (MHz)
+ *
+ * This function will invoke GuC SLPC action to read the min frequency
+ * limit for unslice.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		/* Force GuC to update task data */
+		ret = slpc_query_task_state(slpc);
+
+		if (!ret)
+			*val = slpc_decode_min_freq(slpc);
+	}
+
+	return ret;
+}
+
+void intel_guc_pm_intrmsk_enable(struct intel_gt *gt)
+{
+	u32 pm_intrmsk_mbz = 0;
+
+	/*
+	 * Allow GuC to receive ARAT timer expiry event.
+	 * This interrupt register is setup by RPS code
+	 * when host based Turbo is enabled.
+	 */
+	pm_intrmsk_mbz |= ARAT_EXPIRED_INTRMSK;
+
+	intel_uncore_rmw(gt->uncore,
+			 GEN6_PMINTRMSK, pm_intrmsk_mbz, 0);
+}
+
+static int slpc_set_softlimits(struct intel_guc_slpc *slpc)
+{
+	int ret = 0;
+
+	/*
+	 * Softlimits are initially equivalent to platform limits
+	 * unless they have deviated from defaults, in which case,
+	 * we retain the values and set min/max accordingly.
+	 */
+	if (!slpc->max_freq_softlimit)
+		slpc->max_freq_softlimit = slpc->rp0_freq;
+	else if (slpc->max_freq_softlimit != slpc->rp0_freq)
+		ret = intel_guc_slpc_set_max_freq(slpc,
+						  slpc->max_freq_softlimit);
+
+	if (unlikely(ret))
+		return ret;
+
+	if (!slpc->min_freq_softlimit)
+		slpc->min_freq_softlimit = slpc->min_freq;
+	else if (slpc->min_freq_softlimit != slpc->min_freq)
+		return intel_guc_slpc_set_min_freq(slpc,
+						   slpc->min_freq_softlimit);
+
+	return 0;
+}
+
+static int slpc_ignore_eff_freq(struct intel_guc_slpc *slpc, bool ignore)
+{
+	int ret = 0;
+
+	if (ignore) {
+		ret = slpc_set_param(slpc,
+				     SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY,
+				     ignore);
+		if (!ret)
+			return slpc_set_param(slpc,
+					      SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
+					      slpc->min_freq);
+	} else {
+		ret = slpc_unset_param(slpc,
+				       SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY);
+		if (!ret)
+			return slpc_unset_param(slpc,
+						SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ);
+	}
+
+	return ret;
+}
+
+static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc)
+{
+	/* Force SLPC to used platform rp0 */
+	return slpc_set_param(slpc,
+			      SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ,
+			      slpc->rp0_freq);
+}
+
+static void slpc_get_rp_values(struct intel_guc_slpc *slpc)
+{
+	u32 rp_state_cap;
+
+	rp_state_cap = intel_uncore_read(slpc_to_gt(slpc)->uncore,
+					 GEN6_RP_STATE_CAP);
+
+	slpc->rp0_freq = REG_FIELD_GET(RP0_CAP_MASK, rp_state_cap) *
+					GT_FREQUENCY_MULTIPLIER;
+	slpc->rp1_freq = REG_FIELD_GET(RP1_CAP_MASK, rp_state_cap) *
+					GT_FREQUENCY_MULTIPLIER;
+	slpc->min_freq = REG_FIELD_GET(RPN_CAP_MASK, rp_state_cap) *
+					GT_FREQUENCY_MULTIPLIER;
+}
+
+/*
+ * intel_guc_slpc_enable() - Start SLPC
+ * @slpc: pointer to intel_guc_slpc.
+ *
+ * SLPC is enabled by setting up the shared data structure and
+ * sending reset event to GuC SLPC. Initial data is setup in
+ * intel_guc_slpc_init. Here we send the reset event. We do
+ * not currently need a slpc_disable since this is taken care
+ * of automatically when a reset/suspend occurs and the GuC
+ * CTB is destroyed.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_enable(struct intel_guc_slpc *slpc)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	int ret;
+
+	GEM_BUG_ON(!slpc->vma);
+
+	slpc_shared_data_reset(slpc->vaddr);
+
+	ret = slpc_reset(slpc);
+	if (unlikely(ret < 0)) {
+		drm_err(&i915->drm, "SLPC Reset event returned (%pe)\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	ret = slpc_query_task_state(slpc);
+	if (unlikely(ret < 0))
+		return ret;
+
+	intel_guc_pm_intrmsk_enable(&i915->gt);
+
+	slpc_get_rp_values(slpc);
+
+	/* Ignore efficient freq and set min to platform min */
+	ret = slpc_ignore_eff_freq(slpc, true);
+	if (unlikely(ret)) {
+		drm_err(&i915->drm, "Failed to set SLPC min to RPn (%pe)\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	/* Set SLPC max limit to RP0 */
+	ret = slpc_use_fused_rp0(slpc);
+	if (unlikely(ret)) {
+		drm_err(&i915->drm, "Failed to set SLPC max to RP0 (%pe)\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	/* Revert SLPC min/max to softlimits if necessary */
+	ret = slpc_set_softlimits(slpc);
+	if (unlikely(ret)) {
+		drm_err(&i915->drm, "Failed to set SLPC softlimits (%pe)\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	return 0;
+}
+
+int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	struct slpc_shared_data *data = slpc->vaddr;
+	struct slpc_task_state_data *slpc_tasks;
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	GEM_BUG_ON(!slpc->vma);
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_query_task_state(slpc);
+
+		if (!ret) {
+			slpc_tasks = &data->task_state_data;
+
+			drm_printf(p, "\tSLPC state: %s\n", slpc_get_state_string(slpc));
+			drm_printf(p, "\tGTPERF task active: %s\n",
+				   yesno(slpc_tasks->status & SLPC_GTPERF_TASK_ENABLED));
+			drm_printf(p, "\tMax freq: %u MHz\n",
+				   slpc_decode_max_freq(slpc));
+			drm_printf(p, "\tMin freq: %u MHz\n",
+				   slpc_decode_min_freq(slpc));
+		}
+	}
+
+	return ret;
+}
+
+void intel_guc_slpc_fini(struct intel_guc_slpc *slpc)
+{
+	if (!slpc->vma)
+		return;
+
+	i915_vma_unpin_and_release(&slpc->vma, I915_VMA_RELEASE_MAP);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
new file mode 100644
index 000000000000..e45054d5b9b4
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _INTEL_GUC_SLPC_H_
+#define _INTEL_GUC_SLPC_H_
+
+#include "intel_guc_submission.h"
+#include "intel_guc_slpc_types.h"
+
+struct intel_gt;
+struct drm_printer;
+
+static inline bool intel_guc_slpc_is_supported(struct intel_guc *guc)
+{
+	return guc->slpc.supported;
+}
+
+static inline bool intel_guc_slpc_is_wanted(struct intel_guc *guc)
+{
+	return guc->slpc.selected;
+}
+
+static inline bool intel_guc_slpc_is_used(struct intel_guc *guc)
+{
+	return intel_guc_submission_is_used(guc) && intel_guc_slpc_is_wanted(guc);
+}
+
+void intel_guc_slpc_init_early(struct intel_guc_slpc *slpc);
+
+int intel_guc_slpc_init(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_enable(struct intel_guc_slpc *slpc);
+void intel_guc_slpc_fini(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 val);
+int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val);
+int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val);
+int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val);
+int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p);
+void intel_guc_pm_intrmsk_enable(struct intel_gt *gt);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
new file mode 100644
index 000000000000..41d13527666f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _INTEL_GUC_SLPC_TYPES_H_
+#define _INTEL_GUC_SLPC_TYPES_H_
+
+#include <linux/types.h>
+
+#define SLPC_RESET_TIMEOUT_MS 5
+
+struct intel_guc_slpc {
+	struct i915_vma *vma;
+	struct slpc_shared_data *vaddr;
+	bool supported;
+	bool selected;
+
+	/* platform frequency limits */
+	u32 min_freq;
+	u32 rp0_freq;
+	u32 rp1_freq;
+
+	/* frequency softlimits */
+	u32 min_freq_softlimit;
+	u32 max_freq_softlimit;
+};
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 7c8ff9792f7b..87d8dc8f51b9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -10,10 +10,13 @@
 #include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_irq.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_requests.h"
 #include "gt/intel_lrc.h"
+#include "gt/intel_lrc_reg.h"
 #include "gt/intel_mocs.h"
 #include "gt/intel_ring.h"
 
@@ -58,244 +61,705 @@
  *
  */
 
+/* GuC Virtual Engine */
+struct guc_virtual_engine {
+	struct intel_engine_cs base;
+	struct intel_context context;
+};
+
+static struct intel_context *
+guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
+
 #define GUC_REQUEST_SIZE 64 /* bytes */
 
-static inline struct i915_priolist *to_priolist(struct rb_node *rb)
+/*
+ * Below is a set of functions which control the GuC scheduling state which do
+ * not require a lock as all state transitions are mutually exclusive. i.e. It
+ * is not possible for the context pinning code and submission, for the same
+ * context, to be executing simultaneously. We still need an atomic as it is
+ * possible for some of the bits to changing at the same time though.
+ */
+#define SCHED_STATE_NO_LOCK_ENABLED			BIT(0)
+#define SCHED_STATE_NO_LOCK_PENDING_ENABLE		BIT(1)
+#define SCHED_STATE_NO_LOCK_REGISTERED			BIT(2)
+static inline bool context_enabled(struct intel_context *ce)
 {
-	return rb_entry(rb, struct i915_priolist, node);
+	return (atomic_read(&ce->guc_sched_state_no_lock) &
+		SCHED_STATE_NO_LOCK_ENABLED);
 }
 
-static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id)
+static inline void set_context_enabled(struct intel_context *ce)
 {
-	struct guc_stage_desc *base = guc->stage_desc_pool_vaddr;
+	atomic_or(SCHED_STATE_NO_LOCK_ENABLED, &ce->guc_sched_state_no_lock);
+}
 
-	return &base[id];
+static inline void clr_context_enabled(struct intel_context *ce)
+{
+	atomic_and((u32)~SCHED_STATE_NO_LOCK_ENABLED,
+		   &ce->guc_sched_state_no_lock);
 }
 
-static int guc_stage_desc_pool_create(struct intel_guc *guc)
+static inline bool context_pending_enable(struct intel_context *ce)
 {
-	u32 size = PAGE_ALIGN(sizeof(struct guc_stage_desc) *
-			      GUC_MAX_STAGE_DESCRIPTORS);
+	return (atomic_read(&ce->guc_sched_state_no_lock) &
+		SCHED_STATE_NO_LOCK_PENDING_ENABLE);
+}
 
-	return intel_guc_allocate_and_map_vma(guc, size, &guc->stage_desc_pool,
-					      &guc->stage_desc_pool_vaddr);
+static inline void set_context_pending_enable(struct intel_context *ce)
+{
+	atomic_or(SCHED_STATE_NO_LOCK_PENDING_ENABLE,
+		  &ce->guc_sched_state_no_lock);
+}
+
+static inline void clr_context_pending_enable(struct intel_context *ce)
+{
+	atomic_and((u32)~SCHED_STATE_NO_LOCK_PENDING_ENABLE,
+		   &ce->guc_sched_state_no_lock);
 }
 
-static void guc_stage_desc_pool_destroy(struct intel_guc *guc)
+static inline bool context_registered(struct intel_context *ce)
 {
-	i915_vma_unpin_and_release(&guc->stage_desc_pool, I915_VMA_RELEASE_MAP);
+	return (atomic_read(&ce->guc_sched_state_no_lock) &
+		SCHED_STATE_NO_LOCK_REGISTERED);
+}
+
+static inline void set_context_registered(struct intel_context *ce)
+{
+	atomic_or(SCHED_STATE_NO_LOCK_REGISTERED,
+		  &ce->guc_sched_state_no_lock);
+}
+
+static inline void clr_context_registered(struct intel_context *ce)
+{
+	atomic_and((u32)~SCHED_STATE_NO_LOCK_REGISTERED,
+		   &ce->guc_sched_state_no_lock);
 }
 
 /*
- * Initialise/clear the stage descriptor shared with the GuC firmware.
- *
- * This descriptor tells the GuC where (in GGTT space) to find the important
- * data structures related to work submission (process descriptor, write queue,
- * etc).
+ * Below is a set of functions which control the GuC scheduling state which
+ * require a lock, aside from the special case where the functions are called
+ * from guc_lrc_desc_pin(). In that case it isn't possible for any other code
+ * path to be executing on the context.
  */
-static void guc_stage_desc_init(struct intel_guc *guc)
+#define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER	BIT(0)
+#define SCHED_STATE_DESTROYED				BIT(1)
+#define SCHED_STATE_PENDING_DISABLE			BIT(2)
+#define SCHED_STATE_BANNED				BIT(3)
+#define SCHED_STATE_BLOCKED_SHIFT			4
+#define SCHED_STATE_BLOCKED		BIT(SCHED_STATE_BLOCKED_SHIFT)
+#define SCHED_STATE_BLOCKED_MASK	(0xfff << SCHED_STATE_BLOCKED_SHIFT)
+static inline void init_sched_state(struct intel_context *ce)
+{
+	/* Only should be called from guc_lrc_desc_pin() */
+	atomic_set(&ce->guc_sched_state_no_lock, 0);
+	ce->guc_state.sched_state = 0;
+}
+
+static inline bool
+context_wait_for_deregister_to_register(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state &
+		SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER;
+}
+
+static inline void
+set_context_wait_for_deregister_to_register(struct intel_context *ce)
 {
-	struct guc_stage_desc *desc;
+	/* Only should be called from guc_lrc_desc_pin() without lock */
+	ce->guc_state.sched_state |=
+		SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER;
+}
 
-	/* we only use 1 stage desc, so hardcode it to 0 */
-	desc = __get_stage_desc(guc, 0);
-	memset(desc, 0, sizeof(*desc));
+static inline void
+clr_context_wait_for_deregister_to_register(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &=
+		~SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER;
+}
 
-	desc->attribute = GUC_STAGE_DESC_ATTR_ACTIVE |
-			  GUC_STAGE_DESC_ATTR_KERNEL;
+static inline bool
+context_destroyed(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_DESTROYED;
+}
 
-	desc->stage_id = 0;
-	desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL;
+static inline void
+set_context_destroyed(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_DESTROYED;
+}
 
-	desc->wq_size = GUC_WQ_SIZE;
+static inline bool context_pending_disable(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_PENDING_DISABLE;
 }
 
-static void guc_stage_desc_fini(struct intel_guc *guc)
+static inline void set_context_pending_disable(struct intel_context *ce)
 {
-	struct guc_stage_desc *desc;
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_PENDING_DISABLE;
+}
 
-	desc = __get_stage_desc(guc, 0);
-	memset(desc, 0, sizeof(*desc));
+static inline void clr_context_pending_disable(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= ~SCHED_STATE_PENDING_DISABLE;
 }
 
-static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
+static inline bool context_banned(struct intel_context *ce)
 {
-	/* Leaving stub as this function will be used in future patches */
+	return ce->guc_state.sched_state & SCHED_STATE_BANNED;
 }
 
-/*
- * When we're doing submissions using regular execlists backend, writing to
- * ELSP from CPU side is enough to make sure that writes to ringbuffer pages
- * pinned in mappable aperture portion of GGTT are visible to command streamer.
- * Writes done by GuC on our behalf are not guaranteeing such ordering,
- * therefore, to ensure the flush, we're issuing a POSTING READ.
- */
-static void flush_ggtt_writes(struct i915_vma *vma)
+static inline void set_context_banned(struct intel_context *ce)
 {
-	if (i915_vma_is_map_and_fenceable(vma))
-		intel_uncore_posting_read_fw(vma->vm->gt->uncore,
-					     GUC_STATUS);
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_BANNED;
 }
 
-static void guc_submit(struct intel_engine_cs *engine,
-		       struct i915_request **out,
-		       struct i915_request **end)
+static inline void clr_context_banned(struct intel_context *ce)
 {
-	struct intel_guc *guc = &engine->gt->uc.guc;
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= ~SCHED_STATE_BANNED;
+}
 
-	do {
-		struct i915_request *rq = *out++;
+static inline u32 context_blocked(struct intel_context *ce)
+{
+	return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >>
+		SCHED_STATE_BLOCKED_SHIFT;
+}
 
-		flush_ggtt_writes(rq->ring->vma);
-		guc_add_request(guc, rq);
-	} while (out != end);
+static inline void incr_context_blocked(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->engine->sched_engine->lock);
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	ce->guc_state.sched_state += SCHED_STATE_BLOCKED;
+
+	GEM_BUG_ON(!context_blocked(ce));	/* Overflow check */
 }
 
-static inline int rq_prio(const struct i915_request *rq)
+static inline void decr_context_blocked(struct intel_context *ce)
 {
-	return rq->sched.attr.priority;
+	lockdep_assert_held(&ce->engine->sched_engine->lock);
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	GEM_BUG_ON(!context_blocked(ce));	/* Underflow check */
+
+	ce->guc_state.sched_state -= SCHED_STATE_BLOCKED;
 }
 
-static struct i915_request *schedule_in(struct i915_request *rq, int idx)
+static inline bool context_guc_id_invalid(struct intel_context *ce)
 {
-	trace_i915_request_in(rq, idx);
+	return ce->guc_id == GUC_INVALID_LRC_ID;
+}
+
+static inline void set_context_guc_id_invalid(struct intel_context *ce)
+{
+	ce->guc_id = GUC_INVALID_LRC_ID;
+}
+
+static inline struct intel_guc *ce_to_guc(struct intel_context *ce)
+{
+	return &ce->engine->gt->uc.guc;
+}
+
+static inline struct i915_priolist *to_priolist(struct rb_node *rb)
+{
+	return rb_entry(rb, struct i915_priolist, node);
+}
+
+static struct guc_lrc_desc *__get_lrc_desc(struct intel_guc *guc, u32 index)
+{
+	struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr;
+
+	GEM_BUG_ON(index >= GUC_MAX_LRC_DESCRIPTORS);
+
+	return &base[index];
+}
+
+static inline struct intel_context *__get_context(struct intel_guc *guc, u32 id)
+{
+	struct intel_context *ce = xa_load(&guc->context_lookup, id);
+
+	GEM_BUG_ON(id >= GUC_MAX_LRC_DESCRIPTORS);
+
+	return ce;
+}
+
+static int guc_lrc_desc_pool_create(struct intel_guc *guc)
+{
+	u32 size;
+	int ret;
+
+	size = PAGE_ALIGN(sizeof(struct guc_lrc_desc) *
+			  GUC_MAX_LRC_DESCRIPTORS);
+	ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool,
+					     (void **)&guc->lrc_desc_pool_vaddr);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void guc_lrc_desc_pool_destroy(struct intel_guc *guc)
+{
+	guc->lrc_desc_pool_vaddr = NULL;
+	i915_vma_unpin_and_release(&guc->lrc_desc_pool, I915_VMA_RELEASE_MAP);
+}
+
+static inline bool guc_submission_initialized(struct intel_guc *guc)
+{
+	return !!guc->lrc_desc_pool_vaddr;
+}
+
+static inline void reset_lrc_desc(struct intel_guc *guc, u32 id)
+{
+	if (likely(guc_submission_initialized(guc))) {
+		struct guc_lrc_desc *desc = __get_lrc_desc(guc, id);
+		unsigned long flags;
+
+		memset(desc, 0, sizeof(*desc));
+
+		/*
+		 * xarray API doesn't have xa_erase_irqsave wrapper, so calling
+		 * the lower level functions directly.
+		 */
+		xa_lock_irqsave(&guc->context_lookup, flags);
+		__xa_erase(&guc->context_lookup, id);
+		xa_unlock_irqrestore(&guc->context_lookup, flags);
+	}
+}
+
+static inline bool lrc_desc_registered(struct intel_guc *guc, u32 id)
+{
+	return __get_context(guc, id);
+}
+
+static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id,
+					   struct intel_context *ce)
+{
+	unsigned long flags;
 
 	/*
-	 * Currently we are not tracking the rq->context being inflight
-	 * (ce->inflight = rq->engine). It is only used by the execlists
-	 * backend at the moment, a similar counting strategy would be
-	 * required if we generalise the inflight tracking.
+	 * xarray API doesn't have xa_save_irqsave wrapper, so calling the
+	 * lower level functions directly.
 	 */
+	xa_lock_irqsave(&guc->context_lookup, flags);
+	__xa_store(&guc->context_lookup, id, ce, GFP_ATOMIC);
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
+}
+
+static int guc_submission_send_busy_loop(struct intel_guc *guc,
+					 const u32 *action,
+					 u32 len,
+					 u32 g2h_len_dw,
+					 bool loop)
+{
+	int err;
+
+	err = intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop);
+
+	if (!err && g2h_len_dw)
+		atomic_inc(&guc->outstanding_submission_g2h);
+
+	return err;
+}
+
+int intel_guc_wait_for_pending_msg(struct intel_guc *guc,
+				   atomic_t *wait_var,
+				   bool interruptible,
+				   long timeout)
+{
+	const int state = interruptible ?
+		TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
+	DEFINE_WAIT(wait);
 
-	__intel_gt_pm_get(rq->engine->gt);
-	return i915_request_get(rq);
+	might_sleep();
+	GEM_BUG_ON(timeout < 0);
+
+	if (!atomic_read(wait_var))
+		return 0;
+
+	if (!timeout)
+		return -ETIME;
+
+	for (;;) {
+		prepare_to_wait(&guc->ct.wq, &wait, state);
+
+		if (!atomic_read(wait_var))
+			break;
+
+		if (signal_pending_state(state, current)) {
+			timeout = -EINTR;
+			break;
+		}
+
+		if (!timeout) {
+			timeout = -ETIME;
+			break;
+		}
+
+		timeout = io_schedule_timeout(timeout);
+	}
+	finish_wait(&guc->ct.wq, &wait);
+
+	return (timeout < 0) ? timeout : 0;
 }
 
-static void schedule_out(struct i915_request *rq)
+int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout)
 {
-	trace_i915_request_out(rq);
+	if (!intel_uc_uses_guc_submission(&guc_to_gt(guc)->uc))
+		return 0;
 
-	intel_gt_pm_put_async(rq->engine->gt);
-	i915_request_put(rq);
+	return intel_guc_wait_for_pending_msg(guc,
+					      &guc->outstanding_submission_g2h,
+					      true, timeout);
 }
 
-static void __guc_dequeue(struct intel_engine_cs *engine)
+static int guc_lrc_desc_pin(struct intel_context *ce, bool loop);
+
+static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct i915_request **first = execlists->inflight;
-	struct i915_request ** const last_port = first + execlists->port_mask;
-	struct i915_request *last = first[0];
-	struct i915_request **port;
-	bool submit = false;
-	struct rb_node *rb;
+	int err = 0;
+	struct intel_context *ce = rq->context;
+	u32 action[3];
+	int len = 0;
+	u32 g2h_len_dw = 0;
+	bool enabled;
 
-	lockdep_assert_held(&engine->active.lock);
+	/*
+	 * Corner case where requests were sitting in the priority list or a
+	 * request resubmitted after the context was banned.
+	 */
+	if (unlikely(intel_context_is_banned(ce))) {
+		i915_request_put(i915_request_mark_eio(rq));
+		intel_engine_signal_breadcrumbs(ce->engine);
+		goto out;
+	}
 
-	if (last) {
-		if (*++first)
-			return;
+	GEM_BUG_ON(!atomic_read(&ce->guc_id_ref));
+	GEM_BUG_ON(context_guc_id_invalid(ce));
 
-		last = NULL;
+	/*
+	 * Corner case where the GuC firmware was blown away and reloaded while
+	 * this context was pinned.
+	 */
+	if (unlikely(!lrc_desc_registered(guc, ce->guc_id))) {
+		err = guc_lrc_desc_pin(ce, false);
+		if (unlikely(err))
+			goto out;
 	}
 
 	/*
-	 * We write directly into the execlists->inflight queue and don't use
-	 * the execlists->pending queue, as we don't have a distinct switch
-	 * event.
+	 * The request / context will be run on the hardware when scheduling
+	 * gets enabled in the unblock.
 	 */
-	port = first;
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	if (unlikely(context_blocked(ce)))
+		goto out;
+
+	enabled = context_enabled(ce);
+
+	if (!enabled) {
+		action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET;
+		action[len++] = ce->guc_id;
+		action[len++] = GUC_CONTEXT_ENABLE;
+		set_context_pending_enable(ce);
+		intel_context_get(ce);
+		g2h_len_dw = G2H_LEN_DW_SCHED_CONTEXT_MODE_SET;
+	} else {
+		action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT;
+		action[len++] = ce->guc_id;
+	}
+
+	err = intel_guc_send_nb(guc, action, len, g2h_len_dw);
+	if (!enabled && !err) {
+		trace_intel_context_sched_enable(ce);
+		atomic_inc(&guc->outstanding_submission_g2h);
+		set_context_enabled(ce);
+	} else if (!enabled) {
+		clr_context_pending_enable(ce);
+		intel_context_put(ce);
+	}
+	if (likely(!err))
+		trace_i915_request_guc_submit(rq);
+
+out:
+	return err;
+}
+
+static inline void guc_set_lrc_tail(struct i915_request *rq)
+{
+	rq->context->lrc_reg_state[CTX_RING_TAIL] =
+		intel_ring_set_tail(rq->ring, rq->tail);
+}
+
+static inline int rq_prio(const struct i915_request *rq)
+{
+	return rq->sched.attr.priority;
+}
+
+static int guc_dequeue_one_context(struct intel_guc *guc)
+{
+	struct i915_sched_engine * const sched_engine = guc->sched_engine;
+	struct i915_request *last = NULL;
+	bool submit = false;
+	struct rb_node *rb;
+	int ret;
+
+	lockdep_assert_held(&sched_engine->lock);
+
+	if (guc->stalled_request) {
+		submit = true;
+		last = guc->stalled_request;
+		goto resubmit;
+	}
+
+	while ((rb = rb_first_cached(&sched_engine->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
 		priolist_for_each_request_consume(rq, rn, p) {
-			if (last && rq->context != last->context) {
-				if (port == last_port)
-					goto done;
-
-				*port = schedule_in(last,
-						    port - execlists->inflight);
-				port++;
-			}
+			if (last && rq->context != last->context)
+				goto done;
 
 			list_del_init(&rq->sched.link);
+
 			__i915_request_submit(rq);
-			submit = true;
+
+			trace_i915_request_in(rq, 0);
 			last = rq;
+			submit = true;
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &sched_engine->queue);
 		i915_priolist_free(p);
 	}
 done:
-	execlists->queue_priority_hint =
-		rb ? to_priolist(rb)->priority : INT_MIN;
 	if (submit) {
-		*port = schedule_in(last, port - execlists->inflight);
-		*++port = NULL;
-		guc_submit(engine, first, port);
+		guc_set_lrc_tail(last);
+resubmit:
+		ret = guc_add_request(guc, last);
+		if (unlikely(ret == -EPIPE))
+			goto deadlk;
+		else if (ret == -EBUSY) {
+			tasklet_schedule(&sched_engine->tasklet);
+			guc->stalled_request = last;
+			return false;
+		}
 	}
-	execlists->active = execlists->inflight;
+
+	guc->stalled_request = NULL;
+	return submit;
+
+deadlk:
+	sched_engine->tasklet.callback = NULL;
+	tasklet_disable_nosync(&sched_engine->tasklet);
+	return false;
 }
 
 static void guc_submission_tasklet(struct tasklet_struct *t)
 {
-	struct intel_engine_cs * const engine =
-		from_tasklet(engine, t, execlists.tasklet);
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct i915_request **port, *rq;
+	struct i915_sched_engine *sched_engine =
+		from_tasklet(sched_engine, t, tasklet);
 	unsigned long flags;
+	bool loop;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-
-	for (port = execlists->inflight; (rq = *port); port++) {
-		if (!i915_request_completed(rq))
-			break;
+	spin_lock_irqsave(&sched_engine->lock, flags);
 
-		schedule_out(rq);
-	}
-	if (port != execlists->inflight) {
-		int idx = port - execlists->inflight;
-		int rem = ARRAY_SIZE(execlists->inflight) - idx;
-		memmove(execlists->inflight, port, rem * sizeof(*port));
-	}
+	do {
+		loop = guc_dequeue_one_context(sched_engine->private_data);
+	} while (loop);
 
-	__guc_dequeue(engine);
+	i915_sched_engine_reset_on_empty(sched_engine);
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
 static void cs_irq_handler(struct intel_engine_cs *engine, u16 iir)
 {
-	if (iir & GT_RENDER_USER_INTERRUPT) {
+	if (iir & GT_RENDER_USER_INTERRUPT)
 		intel_engine_signal_breadcrumbs(engine);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
+static void __guc_context_destroy(struct intel_context *ce);
+static void release_guc_id(struct intel_guc *guc, struct intel_context *ce);
+static void guc_signal_context_fence(struct intel_context *ce);
+static void guc_cancel_context_requests(struct intel_context *ce);
+static void guc_blocked_fence_complete(struct intel_context *ce);
+
+static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
+{
+	struct intel_context *ce;
+	unsigned long index, flags;
+	bool pending_disable, pending_enable, deregister, destroyed, banned;
+
+	xa_for_each(&guc->context_lookup, index, ce) {
+		/* Flush context */
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+		/*
+		 * Once we are at this point submission_disabled() is guaranteed
+		 * to be visible to all callers who set the below flags (see above
+		 * flush and flushes in reset_prepare). If submission_disabled()
+		 * is set, the caller shouldn't set these flags.
+		 */
+
+		destroyed = context_destroyed(ce);
+		pending_enable = context_pending_enable(ce);
+		pending_disable = context_pending_disable(ce);
+		deregister = context_wait_for_deregister_to_register(ce);
+		banned = context_banned(ce);
+		init_sched_state(ce);
+
+		if (pending_enable || destroyed || deregister) {
+			atomic_dec(&guc->outstanding_submission_g2h);
+			if (deregister)
+				guc_signal_context_fence(ce);
+			if (destroyed) {
+				release_guc_id(guc, ce);
+				__guc_context_destroy(ce);
+			}
+			if (pending_enable || deregister)
+				intel_context_put(ce);
+		}
+
+		/* Not mutualy exclusive with above if statement. */
+		if (pending_disable) {
+			guc_signal_context_fence(ce);
+			if (banned) {
+				guc_cancel_context_requests(ce);
+				intel_engine_signal_breadcrumbs(ce->engine);
+			}
+			intel_context_sched_disable_unpin(ce);
+			atomic_dec(&guc->outstanding_submission_g2h);
+			spin_lock_irqsave(&ce->guc_state.lock, flags);
+			guc_blocked_fence_complete(ce);
+			spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+			intel_context_put(ce);
+		}
 	}
 }
 
-static void guc_reset_prepare(struct intel_engine_cs *engine)
+static inline bool
+submission_disabled(struct intel_guc *guc)
+{
+	struct i915_sched_engine * const sched_engine = guc->sched_engine;
+
+	return unlikely(!sched_engine ||
+			!__tasklet_is_enabled(&sched_engine->tasklet));
+}
+
+static void disable_submission(struct intel_guc *guc)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_sched_engine * const sched_engine = guc->sched_engine;
+
+	if (__tasklet_is_enabled(&sched_engine->tasklet)) {
+		GEM_BUG_ON(!guc->ct.enabled);
+		__tasklet_disable_sync_once(&sched_engine->tasklet);
+		sched_engine->tasklet.callback = NULL;
+	}
+}
+
+static void enable_submission(struct intel_guc *guc)
+{
+	struct i915_sched_engine * const sched_engine = guc->sched_engine;
+	unsigned long flags;
 
-	ENGINE_TRACE(engine, "\n");
+	spin_lock_irqsave(&guc->sched_engine->lock, flags);
+	sched_engine->tasklet.callback = guc_submission_tasklet;
+	wmb();	/* Make sure callback visible */
+	if (!__tasklet_is_enabled(&sched_engine->tasklet) &&
+	    __tasklet_enable(&sched_engine->tasklet)) {
+		GEM_BUG_ON(!guc->ct.enabled);
+
+		/* And kick in case we missed a new request submission. */
+		tasklet_hi_schedule(&sched_engine->tasklet);
+	}
+	spin_unlock_irqrestore(&guc->sched_engine->lock, flags);
+}
+
+static void guc_flush_submissions(struct intel_guc *guc)
+{
+	struct i915_sched_engine * const sched_engine = guc->sched_engine;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sched_engine->lock, flags);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
+}
+
+void intel_guc_submission_reset_prepare(struct intel_guc *guc)
+{
+	int i;
+
+	if (unlikely(!guc_submission_initialized(guc))) {
+		/* Reset called during driver load? GuC not yet initialised! */
+		return;
+	}
+
+	intel_gt_park_heartbeats(guc_to_gt(guc));
+	disable_submission(guc);
+	guc->interrupts.disable(guc);
+
+	/* Flush IRQ handler */
+	spin_lock_irq(&guc_to_gt(guc)->irq_lock);
+	spin_unlock_irq(&guc_to_gt(guc)->irq_lock);
+
+	guc_flush_submissions(guc);
 
 	/*
-	 * Prevent request submission to the hardware until we have
-	 * completed the reset in i915_gem_reset_finish(). If a request
-	 * is completed by one engine, it may then queue a request
-	 * to a second via its execlists->tasklet *just* as we are
-	 * calling engine->init_hw() and also writing the ELSP.
-	 * Turning off the execlists->tasklet until the reset is over
-	 * prevents the race.
+	 * Handle any outstanding G2Hs before reset. Call IRQ handler directly
+	 * each pass as interrupt have been disabled. We always scrub for
+	 * outstanding G2H as it is possible for outstanding_submission_g2h to
+	 * be incremented after the context state update.
 	 */
-	__tasklet_disable_sync_once(&execlists->tasklet);
+	for (i = 0; i < 4 && atomic_read(&guc->outstanding_submission_g2h); ++i) {
+		intel_guc_to_host_event_handler(guc);
+#define wait_for_reset(guc, wait_var) \
+		intel_guc_wait_for_pending_msg(guc, wait_var, false, (HZ / 20))
+		do {
+			wait_for_reset(guc, &guc->outstanding_submission_g2h);
+		} while (!list_empty(&guc->ct.requests.incoming));
+	}
+	scrub_guc_desc_for_outstanding_g2h(guc);
+}
+
+static struct intel_engine_cs *
+guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling)
+{
+	struct intel_engine_cs *engine;
+	intel_engine_mask_t tmp, mask = ve->mask;
+	unsigned int num_siblings = 0;
+
+	for_each_engine_masked(engine, ve->gt, mask, tmp)
+		if (num_siblings++ == sibling)
+			return engine;
+
+	return NULL;
+}
+
+static inline struct intel_engine_cs *
+__context_to_physical_engine(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = ce->engine;
+
+	if (intel_engine_is_virtual(engine))
+		engine = guc_virtual_get_sibling(engine, 0);
+
+	return engine;
 }
 
-static void guc_reset_state(struct intel_context *ce,
-			    struct intel_engine_cs *engine,
-			    u32 head,
-			    bool scrub)
+static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub)
 {
+	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
+
+	if (intel_context_is_banned(ce))
+		return;
+
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
 
 	/*
@@ -313,37 +777,132 @@ static void guc_reset_state(struct intel_context *ce,
 	lrc_update_regs(ce, engine, head);
 }
 
-static void guc_reset_rewind(struct intel_engine_cs *engine, bool stalled)
+static void guc_reset_nop(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct i915_request *rq;
+}
+
+static void guc_rewind_nop(struct intel_engine_cs *engine, bool stalled)
+{
+}
+
+static void
+__unwind_incomplete_requests(struct intel_context *ce)
+{
+	struct i915_request *rq, *rn;
+	struct list_head *pl;
+	int prio = I915_PRIORITY_INVALID;
+	struct i915_sched_engine * const sched_engine =
+		ce->engine->sched_engine;
 	unsigned long flags;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&sched_engine->lock, flags);
+	spin_lock(&ce->guc_active.lock);
+	list_for_each_entry_safe(rq, rn,
+				 &ce->guc_active.requests,
+				 sched.link) {
+		if (i915_request_completed(rq))
+			continue;
 
-	/* Push back any incomplete requests for replay after the reset. */
-	rq = execlists_unwind_incomplete_requests(execlists);
-	if (!rq)
-		goto out_unlock;
+		list_del_init(&rq->sched.link);
+		spin_unlock(&ce->guc_active.lock);
+
+		__i915_request_unsubmit(rq);
+
+		/* Push the request back into the queue for later resubmission. */
+		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
+		if (rq_prio(rq) != prio) {
+			prio = rq_prio(rq);
+			pl = i915_sched_lookup_priolist(sched_engine, prio);
+		}
+		GEM_BUG_ON(i915_sched_engine_is_empty(sched_engine));
+
+		list_add_tail(&rq->sched.link, pl);
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+
+		spin_lock(&ce->guc_active.lock);
+	}
+	spin_unlock(&ce->guc_active.lock);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
+}
+
+static void __guc_reset_context(struct intel_context *ce, bool stalled)
+{
+	struct i915_request *rq;
+	u32 head;
+
+	intel_context_get(ce);
+
+	/*
+	 * GuC will implicitly mark the context as non-schedulable
+	 * when it sends the reset notification. Make sure our state
+	 * reflects this change. The context will be marked enabled
+	 * on resubmission.
+	 */
+	clr_context_enabled(ce);
+
+	rq = intel_context_find_active_request(ce);
+	if (!rq) {
+		head = ce->ring->tail;
+		stalled = false;
+		goto out_replay;
+	}
 
 	if (!i915_request_started(rq))
 		stalled = false;
 
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	head = intel_ring_wrap(ce->ring, rq->head);
 	__i915_request_reset(rq, stalled);
-	guc_reset_state(rq->context, engine, rq->head, stalled);
 
-out_unlock:
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+out_replay:
+	guc_reset_state(ce, head, stalled);
+	__unwind_incomplete_requests(ce);
+	intel_context_put(ce);
+}
+
+void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
+{
+	struct intel_context *ce;
+	unsigned long index;
+
+	if (unlikely(!guc_submission_initialized(guc))) {
+		/* Reset called during driver load? GuC not yet initialised! */
+		return;
+	}
+
+	xa_for_each(&guc->context_lookup, index, ce)
+		if (intel_context_is_pinned(ce))
+			__guc_reset_context(ce, stalled);
+
+	/* GuC is blown away, drop all references to contexts */
+	xa_destroy(&guc->context_lookup);
 }
 
-static void guc_reset_cancel(struct intel_engine_cs *engine)
+static void guc_cancel_context_requests(struct intel_context *ce)
+{
+	struct i915_sched_engine *sched_engine = ce_to_guc(ce)->sched_engine;
+	struct i915_request *rq;
+	unsigned long flags;
+
+	/* Mark all executing requests as skipped. */
+	spin_lock_irqsave(&sched_engine->lock, flags);
+	spin_lock(&ce->guc_active.lock);
+	list_for_each_entry(rq, &ce->guc_active.requests, sched.link)
+		i915_request_put(i915_request_mark_eio(rq));
+	spin_unlock(&ce->guc_active.lock);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
+}
+
+static void
+guc_cancel_sched_engine_requests(struct i915_sched_engine *sched_engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	ENGINE_TRACE(engine, "\n");
+	/* Can be called during boot if GuC fails to load */
+	if (!sched_engine)
+		return;
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -359,47 +918,67 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 	 * submission's irq state, we also wish to remind ourselves that
 	 * it is irq state.)
 	 */
-	spin_lock_irqsave(&engine->active.lock, flags);
-
-	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		i915_request_set_error_once(rq, -EIO);
-		i915_request_mark_complete(rq);
-	}
+	spin_lock_irqsave(&sched_engine->lock, flags);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&sched_engine->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		priolist_for_each_request_consume(rq, rn, p) {
 			list_del_init(&rq->sched.link);
+
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
+
+			i915_request_put(i915_request_mark_eio(rq));
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &sched_engine->queue);
 		i915_priolist_free(p);
 	}
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
+	sched_engine->queue_priority_hint = INT_MIN;
+	sched_engine->queue = RB_ROOT_CACHED;
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
-static void guc_reset_finish(struct intel_engine_cs *engine)
+void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct intel_context *ce;
+	unsigned long index;
 
-	if (__tasklet_enable(&execlists->tasklet))
-		/* And kick in case we missed a new request submission. */
-		tasklet_hi_schedule(&execlists->tasklet);
+	xa_for_each(&guc->context_lookup, index, ce)
+		if (intel_context_is_pinned(ce))
+			guc_cancel_context_requests(ce);
+
+	guc_cancel_sched_engine_requests(guc->sched_engine);
 
-	ENGINE_TRACE(engine, "depth->%d\n",
-		     atomic_read(&execlists->tasklet.count));
+	/* GuC is blown away, drop all references to contexts */
+	xa_destroy(&guc->context_lookup);
+}
+
+void intel_guc_submission_reset_finish(struct intel_guc *guc)
+{
+	/* Reset called during driver load or during wedge? */
+	if (unlikely(!guc_submission_initialized(guc) ||
+		     test_bit(I915_WEDGED, &guc_to_gt(guc)->reset.flags))) {
+		return;
+	}
+
+	/*
+	 * Technically possible for either of these values to be non-zero here,
+	 * but very unlikely + harmless. Regardless let's add a warn so we can
+	 * see in CI if this happens frequently / a precursor to taking down the
+	 * machine.
+	 */
+	GEM_WARN_ON(atomic_read(&guc->outstanding_submission_g2h));
+	atomic_set(&guc->outstanding_submission_g2h, 0);
+
+	intel_guc_global_policies_update(guc);
+	enable_submission(guc);
+	intel_gt_unpark_heartbeats(guc_to_gt(guc));
 }
 
 /*
@@ -410,43 +989,986 @@ int intel_guc_submission_init(struct intel_guc *guc)
 {
 	int ret;
 
-	if (guc->stage_desc_pool)
+	if (guc->lrc_desc_pool)
 		return 0;
 
-	ret = guc_stage_desc_pool_create(guc);
+	ret = guc_lrc_desc_pool_create(guc);
 	if (ret)
 		return ret;
 	/*
 	 * Keep static analysers happy, let them know that we allocated the
 	 * vma after testing that it didn't exist earlier.
 	 */
-	GEM_BUG_ON(!guc->stage_desc_pool);
+	GEM_BUG_ON(!guc->lrc_desc_pool);
+
+	xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ);
+
+	spin_lock_init(&guc->contexts_lock);
+	INIT_LIST_HEAD(&guc->guc_id_list);
+	ida_init(&guc->guc_ids);
 
 	return 0;
 }
 
 void intel_guc_submission_fini(struct intel_guc *guc)
 {
-	if (guc->stage_desc_pool) {
-		guc_stage_desc_pool_destroy(guc);
+	if (!guc->lrc_desc_pool)
+		return;
+
+	guc_lrc_desc_pool_destroy(guc);
+	i915_sched_engine_put(guc->sched_engine);
+}
+
+static inline void queue_request(struct i915_sched_engine *sched_engine,
+				 struct i915_request *rq,
+				 int prio)
+{
+	GEM_BUG_ON(!list_empty(&rq->sched.link));
+	list_add_tail(&rq->sched.link,
+		      i915_sched_lookup_priolist(sched_engine, prio));
+	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+}
+
+static int guc_bypass_tasklet_submit(struct intel_guc *guc,
+				     struct i915_request *rq)
+{
+	int ret;
+
+	__i915_request_submit(rq);
+
+	trace_i915_request_in(rq, 0);
+
+	guc_set_lrc_tail(rq);
+	ret = guc_add_request(guc, rq);
+	if (ret == -EBUSY)
+		guc->stalled_request = rq;
+
+	if (unlikely(ret == -EPIPE))
+		disable_submission(guc);
+
+	return ret;
+}
+
+static void guc_submit_request(struct i915_request *rq)
+{
+	struct i915_sched_engine *sched_engine = rq->engine->sched_engine;
+	struct intel_guc *guc = &rq->engine->gt->uc.guc;
+	unsigned long flags;
+
+	/* Will be called from irq-context when using foreign fences. */
+	spin_lock_irqsave(&sched_engine->lock, flags);
+
+	if (submission_disabled(guc) || guc->stalled_request ||
+	    !i915_sched_engine_is_empty(sched_engine))
+		queue_request(sched_engine, rq, rq_prio(rq));
+	else if (guc_bypass_tasklet_submit(guc, rq) == -EBUSY)
+		tasklet_hi_schedule(&sched_engine->tasklet);
+
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
+}
+
+static int new_guc_id(struct intel_guc *guc)
+{
+	return ida_simple_get(&guc->guc_ids, 0,
+			      GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL |
+			      __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+}
+
+static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
+{
+	if (!context_guc_id_invalid(ce)) {
+		ida_simple_remove(&guc->guc_ids, ce->guc_id);
+		reset_lrc_desc(guc, ce->guc_id);
+		set_context_guc_id_invalid(ce);
 	}
+	if (!list_empty(&ce->guc_id_link))
+		list_del_init(&ce->guc_id_link);
 }
 
-static int guc_context_alloc(struct intel_context *ce)
+static void release_guc_id(struct intel_guc *guc, struct intel_context *ce)
 {
-	return lrc_alloc(ce, ce->engine);
+	unsigned long flags;
+
+	spin_lock_irqsave(&guc->contexts_lock, flags);
+	__release_guc_id(guc, ce);
+	spin_unlock_irqrestore(&guc->contexts_lock, flags);
+}
+
+static int steal_guc_id(struct intel_guc *guc)
+{
+	struct intel_context *ce;
+	int guc_id;
+
+	lockdep_assert_held(&guc->contexts_lock);
+
+	if (!list_empty(&guc->guc_id_list)) {
+		ce = list_first_entry(&guc->guc_id_list,
+				      struct intel_context,
+				      guc_id_link);
+
+		GEM_BUG_ON(atomic_read(&ce->guc_id_ref));
+		GEM_BUG_ON(context_guc_id_invalid(ce));
+
+		list_del_init(&ce->guc_id_link);
+		guc_id = ce->guc_id;
+		clr_context_registered(ce);
+		set_context_guc_id_invalid(ce);
+		return guc_id;
+	} else {
+		return -EAGAIN;
+	}
+}
+
+static int assign_guc_id(struct intel_guc *guc, u16 *out)
+{
+	int ret;
+
+	lockdep_assert_held(&guc->contexts_lock);
+
+	ret = new_guc_id(guc);
+	if (unlikely(ret < 0)) {
+		ret = steal_guc_id(guc);
+		if (ret < 0)
+			return ret;
+	}
+
+	*out = ret;
+	return 0;
+}
+
+#define PIN_GUC_ID_TRIES	4
+static int pin_guc_id(struct intel_guc *guc, struct intel_context *ce)
+{
+	int ret = 0;
+	unsigned long flags, tries = PIN_GUC_ID_TRIES;
+
+	GEM_BUG_ON(atomic_read(&ce->guc_id_ref));
+
+try_again:
+	spin_lock_irqsave(&guc->contexts_lock, flags);
+
+	if (context_guc_id_invalid(ce)) {
+		ret = assign_guc_id(guc, &ce->guc_id);
+		if (ret)
+			goto out_unlock;
+		ret = 1;	/* Indidcates newly assigned guc_id */
+	}
+	if (!list_empty(&ce->guc_id_link))
+		list_del_init(&ce->guc_id_link);
+	atomic_inc(&ce->guc_id_ref);
+
+out_unlock:
+	spin_unlock_irqrestore(&guc->contexts_lock, flags);
+
+	/*
+	 * -EAGAIN indicates no guc_ids are available, let's retire any
+	 * outstanding requests to see if that frees up a guc_id. If the first
+	 * retire didn't help, insert a sleep with the timeslice duration before
+	 * attempting to retire more requests. Double the sleep period each
+	 * subsequent pass before finally giving up. The sleep period has max of
+	 * 100ms and minimum of 1ms.
+	 */
+	if (ret == -EAGAIN && --tries) {
+		if (PIN_GUC_ID_TRIES - tries > 1) {
+			unsigned int timeslice_shifted =
+				ce->engine->props.timeslice_duration_ms <<
+				(PIN_GUC_ID_TRIES - tries - 2);
+			unsigned int max = min_t(unsigned int, 100,
+						 timeslice_shifted);
+
+			msleep(max_t(unsigned int, max, 1));
+		}
+		intel_gt_retire_requests(guc_to_gt(guc));
+		goto try_again;
+	}
+
+	return ret;
+}
+
+static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce)
+{
+	unsigned long flags;
+
+	GEM_BUG_ON(atomic_read(&ce->guc_id_ref) < 0);
+
+	if (unlikely(context_guc_id_invalid(ce)))
+		return;
+
+	spin_lock_irqsave(&guc->contexts_lock, flags);
+	if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id_link) &&
+	    !atomic_read(&ce->guc_id_ref))
+		list_add_tail(&ce->guc_id_link, &guc->guc_id_list);
+	spin_unlock_irqrestore(&guc->contexts_lock, flags);
+}
+
+static int __guc_action_register_context(struct intel_guc *guc,
+					 u32 guc_id,
+					 u32 offset,
+					 bool loop)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_REGISTER_CONTEXT,
+		guc_id,
+		offset,
+	};
+
+	return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+					     0, loop);
+}
+
+static int register_context(struct intel_context *ce, bool loop)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) +
+		ce->guc_id * sizeof(struct guc_lrc_desc);
+	int ret;
+
+	trace_intel_context_register(ce);
+
+	ret = __guc_action_register_context(guc, ce->guc_id, offset, loop);
+	if (likely(!ret))
+		set_context_registered(ce);
+
+	return ret;
+}
+
+static int __guc_action_deregister_context(struct intel_guc *guc,
+					   u32 guc_id,
+					   bool loop)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_DEREGISTER_CONTEXT,
+		guc_id,
+	};
+
+	return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+					     G2H_LEN_DW_DEREGISTER_CONTEXT,
+					     loop);
+}
+
+static int deregister_context(struct intel_context *ce, u32 guc_id, bool loop)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+
+	trace_intel_context_deregister(ce);
+
+	return __guc_action_deregister_context(guc, guc_id, loop);
+}
+
+static intel_engine_mask_t adjust_engine_mask(u8 class, intel_engine_mask_t mask)
+{
+	switch (class) {
+	case RENDER_CLASS:
+		return mask >> RCS0;
+	case VIDEO_ENHANCEMENT_CLASS:
+		return mask >> VECS0;
+	case VIDEO_DECODE_CLASS:
+		return mask >> VCS0;
+	case COPY_ENGINE_CLASS:
+		return mask >> BCS0;
+	default:
+		MISSING_CASE(class);
+		return 0;
+	}
+}
+
+static void guc_context_policy_init(struct intel_engine_cs *engine,
+				    struct guc_lrc_desc *desc)
+{
+	desc->policy_flags = 0;
+
+	if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION)
+		desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE;
+
+	/* NB: For both of these, zero means disabled. */
+	desc->execution_quantum = engine->props.timeslice_duration_ms * 1000;
+	desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
+}
+
+static inline u8 map_i915_prio_to_guc_prio(int prio);
+
+static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
+{
+	struct intel_engine_cs *engine = ce->engine;
+	struct intel_runtime_pm *runtime_pm = engine->uncore->rpm;
+	struct intel_guc *guc = &engine->gt->uc.guc;
+	u32 desc_idx = ce->guc_id;
+	struct guc_lrc_desc *desc;
+	const struct i915_gem_context *ctx;
+	int prio = I915_CONTEXT_DEFAULT_PRIORITY;
+	bool context_registered;
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	GEM_BUG_ON(!engine->mask);
+
+	/*
+	 * Ensure LRC + CT vmas are is same region as write barrier is done
+	 * based on CT vma region.
+	 */
+	GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) !=
+		   i915_gem_object_is_lmem(ce->ring->vma->obj));
+
+	context_registered = lrc_desc_registered(guc, desc_idx);
+
+	rcu_read_lock();
+	ctx = rcu_dereference(ce->gem_context);
+	if (ctx)
+		prio = ctx->sched.priority;
+	rcu_read_unlock();
+
+	reset_lrc_desc(guc, desc_idx);
+	set_lrc_desc_registered(guc, desc_idx, ce);
+
+	desc = __get_lrc_desc(guc, desc_idx);
+	desc->engine_class = engine_class_to_guc_class(engine->class);
+	desc->engine_submit_mask = adjust_engine_mask(engine->class,
+						      engine->mask);
+	desc->hw_context_desc = ce->lrc.lrca;
+	ce->guc_prio = map_i915_prio_to_guc_prio(prio);
+	desc->priority = ce->guc_prio;
+	desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
+	guc_context_policy_init(engine, desc);
+	init_sched_state(ce);
+
+	/*
+	 * The context_lookup xarray is used to determine if the hardware
+	 * context is currently registered. There are two cases in which it
+	 * could be registered either the guc_id has been stolen from another
+	 * context or the lrc descriptor address of this context has changed. In
+	 * either case the context needs to be deregistered with the GuC before
+	 * registering this context.
+	 */
+	if (context_registered) {
+		trace_intel_context_steal_guc_id(ce);
+		if (!loop) {
+			set_context_wait_for_deregister_to_register(ce);
+			intel_context_get(ce);
+		} else {
+			bool disabled;
+			unsigned long flags;
+
+			/* Seal race with Reset */
+			spin_lock_irqsave(&ce->guc_state.lock, flags);
+			disabled = submission_disabled(guc);
+			if (likely(!disabled)) {
+				set_context_wait_for_deregister_to_register(ce);
+				intel_context_get(ce);
+			}
+			spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+			if (unlikely(disabled)) {
+				reset_lrc_desc(guc, desc_idx);
+				return 0;	/* Will get registered later */
+			}
+		}
+
+		/*
+		 * If stealing the guc_id, this ce has the same guc_id as the
+		 * context whose guc_id was stolen.
+		 */
+		with_intel_runtime_pm(runtime_pm, wakeref)
+			ret = deregister_context(ce, ce->guc_id, loop);
+		if (unlikely(ret == -EBUSY)) {
+			clr_context_wait_for_deregister_to_register(ce);
+			intel_context_put(ce);
+		} else if (unlikely(ret == -ENODEV)) {
+			ret = 0;	/* Will get registered later */
+		}
+	} else {
+		with_intel_runtime_pm(runtime_pm, wakeref)
+			ret = register_context(ce, loop);
+		if (unlikely(ret == -EBUSY))
+			reset_lrc_desc(guc, desc_idx);
+		else if (unlikely(ret == -ENODEV))
+			ret = 0;	/* Will get registered later */
+	}
+
+	return ret;
+}
+
+static int __guc_context_pre_pin(struct intel_context *ce,
+				 struct intel_engine_cs *engine,
+				 struct i915_gem_ww_ctx *ww,
+				 void **vaddr)
+{
+	return lrc_pre_pin(ce, engine, ww, vaddr);
+}
+
+static int __guc_context_pin(struct intel_context *ce,
+			     struct intel_engine_cs *engine,
+			     void *vaddr)
+{
+	if (i915_ggtt_offset(ce->state) !=
+	    (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK))
+		set_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
+
+	/*
+	 * GuC context gets pinned in guc_request_alloc. See that function for
+	 * explaination of why.
+	 */
+
+	return lrc_pin(ce, engine, vaddr);
 }
 
 static int guc_context_pre_pin(struct intel_context *ce,
 			       struct i915_gem_ww_ctx *ww,
 			       void **vaddr)
 {
-	return lrc_pre_pin(ce, ce->engine, ww, vaddr);
+	return __guc_context_pre_pin(ce, ce->engine, ww, vaddr);
 }
 
 static int guc_context_pin(struct intel_context *ce, void *vaddr)
 {
-	return lrc_pin(ce, ce->engine, vaddr);
+	return __guc_context_pin(ce, ce->engine, vaddr);
+}
+
+static void guc_context_unpin(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+
+	unpin_guc_id(guc, ce);
+	lrc_unpin(ce);
+}
+
+static void guc_context_post_unpin(struct intel_context *ce)
+{
+	lrc_post_unpin(ce);
+}
+
+static void __guc_context_sched_enable(struct intel_guc *guc,
+				       struct intel_context *ce)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET,
+		ce->guc_id,
+		GUC_CONTEXT_ENABLE
+	};
+
+	trace_intel_context_sched_enable(ce);
+
+	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+				      G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true);
+}
+
+static void __guc_context_sched_disable(struct intel_guc *guc,
+					struct intel_context *ce,
+					u16 guc_id)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET,
+		guc_id,	/* ce->guc_id not stable */
+		GUC_CONTEXT_DISABLE
+	};
+
+	GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);
+
+	trace_intel_context_sched_disable(ce);
+
+	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+				      G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true);
+}
+
+static void guc_blocked_fence_complete(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	if (!i915_sw_fence_done(&ce->guc_blocked))
+		i915_sw_fence_complete(&ce->guc_blocked);
+}
+
+static void guc_blocked_fence_reinit(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	GEM_BUG_ON(!i915_sw_fence_done(&ce->guc_blocked));
+
+	/*
+	 * This fence is always complete unless a pending schedule disable is
+	 * outstanding. We arm the fence here and complete it when we receive
+	 * the pending schedule disable complete message.
+	 */
+	i915_sw_fence_fini(&ce->guc_blocked);
+	i915_sw_fence_reinit(&ce->guc_blocked);
+	i915_sw_fence_await(&ce->guc_blocked);
+	i915_sw_fence_commit(&ce->guc_blocked);
+}
+
+static u16 prep_context_pending_disable(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	set_context_pending_disable(ce);
+	clr_context_enabled(ce);
+	guc_blocked_fence_reinit(ce);
+	intel_context_get(ce);
+
+	return ce->guc_id;
+}
+
+static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
+	unsigned long flags;
+	struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm;
+	intel_wakeref_t wakeref;
+	u16 guc_id;
+	bool enabled;
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+
+	/*
+	 * Sync with submission path, increment before below changes to context
+	 * state.
+	 */
+	spin_lock(&sched_engine->lock);
+	incr_context_blocked(ce);
+	spin_unlock(&sched_engine->lock);
+
+	enabled = context_enabled(ce);
+	if (unlikely(!enabled || submission_disabled(guc))) {
+		if (enabled)
+			clr_context_enabled(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		return &ce->guc_blocked;
+	}
+
+	/*
+	 * We add +2 here as the schedule disable complete CTB handler calls
+	 * intel_context_sched_disable_unpin (-2 to pin_count).
+	 */
+	atomic_add(2, &ce->pin_count);
+
+	guc_id = prep_context_pending_disable(ce);
+
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		__guc_context_sched_disable(guc, ce, guc_id);
+
+	return &ce->guc_blocked;
+}
+
+static void guc_context_unblock(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
+	unsigned long flags;
+	struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm;
+	intel_wakeref_t wakeref;
+	bool enable;
+
+	GEM_BUG_ON(context_enabled(ce));
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+
+	if (unlikely(submission_disabled(guc) ||
+		     !intel_context_is_pinned(ce) ||
+		     context_pending_disable(ce) ||
+		     context_blocked(ce) > 1)) {
+		enable = false;
+	} else {
+		enable = true;
+		set_context_pending_enable(ce);
+		set_context_enabled(ce);
+		intel_context_get(ce);
+	}
+
+	/*
+	 * Sync with submission path, decrement after above changes to context
+	 * state.
+	 */
+	spin_lock(&sched_engine->lock);
+	decr_context_blocked(ce);
+	spin_unlock(&sched_engine->lock);
+
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	if (enable) {
+		with_intel_runtime_pm(runtime_pm, wakeref)
+			__guc_context_sched_enable(guc, ce);
+	}
+}
+
+static void guc_context_cancel_request(struct intel_context *ce,
+				       struct i915_request *rq)
+{
+	if (i915_sw_fence_signaled(&rq->submit)) {
+		struct i915_sw_fence *fence = guc_context_block(ce);
+
+		i915_sw_fence_wait(fence);
+		if (!i915_request_completed(rq)) {
+			__i915_request_skip(rq);
+			guc_reset_state(ce, intel_ring_wrap(ce->ring, rq->head),
+					true);
+		}
+		guc_context_unblock(ce);
+	}
+}
+
+static void __guc_context_set_preemption_timeout(struct intel_guc *guc,
+						 u16 guc_id,
+						 u32 preemption_timeout)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT,
+		guc_id,
+		preemption_timeout
+	};
+
+	intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+}
+
+static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	struct intel_runtime_pm *runtime_pm =
+		&ce->engine->gt->i915->runtime_pm;
+	intel_wakeref_t wakeref;
+	unsigned long flags;
+
+	guc_flush_submissions(guc);
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	set_context_banned(ce);
+
+	if (submission_disabled(guc) ||
+	    (!context_enabled(ce) && !context_pending_disable(ce))) {
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+		guc_cancel_context_requests(ce);
+		intel_engine_signal_breadcrumbs(ce->engine);
+	} else if (!context_pending_disable(ce)) {
+		u16 guc_id;
+
+		/*
+		 * We add +2 here as the schedule disable complete CTB handler
+		 * calls intel_context_sched_disable_unpin (-2 to pin_count).
+		 */
+		atomic_add(2, &ce->pin_count);
+
+		guc_id = prep_context_pending_disable(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+		/*
+		 * In addition to disabling scheduling, set the preemption
+		 * timeout to the minimum value (1 us) so the banned context
+		 * gets kicked off the HW ASAP.
+		 */
+		with_intel_runtime_pm(runtime_pm, wakeref) {
+			__guc_context_set_preemption_timeout(guc, guc_id, 1);
+			__guc_context_sched_disable(guc, ce, guc_id);
+		}
+	} else {
+		if (!context_guc_id_invalid(ce))
+			with_intel_runtime_pm(runtime_pm, wakeref)
+				__guc_context_set_preemption_timeout(guc,
+								     ce->guc_id,
+								     1);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+	}
+}
+
+static void guc_context_sched_disable(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	unsigned long flags;
+	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
+	intel_wakeref_t wakeref;
+	u16 guc_id;
+	bool enabled;
+
+	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
+	    !lrc_desc_registered(guc, ce->guc_id)) {
+		clr_context_enabled(ce);
+		goto unpin;
+	}
+
+	if (!context_enabled(ce))
+		goto unpin;
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+
+	/*
+	 * We have to check if the context has been disabled by another thread.
+	 * We also have to check if the context has been pinned again as another
+	 * pin operation is allowed to pass this function. Checking the pin
+	 * count, within ce->guc_state.lock, synchronizes this function with
+	 * guc_request_alloc ensuring a request doesn't slip through the
+	 * 'context_pending_disable' fence. Checking within the spin lock (can't
+	 * sleep) ensures another process doesn't pin this context and generate
+	 * a request before we set the 'context_pending_disable' flag here.
+	 */
+	enabled = context_enabled(ce);
+	if (unlikely(!enabled || submission_disabled(guc))) {
+		if (enabled)
+			clr_context_enabled(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		goto unpin;
+	}
+	if (unlikely(atomic_add_unless(&ce->pin_count, -2, 2))) {
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		return;
+	}
+	guc_id = prep_context_pending_disable(ce);
+
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		__guc_context_sched_disable(guc, ce, guc_id);
+
+	return;
+unpin:
+	intel_context_sched_disable_unpin(ce);
+}
+
+static inline void guc_lrc_desc_unpin(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+
+	GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id));
+	GEM_BUG_ON(ce != __get_context(guc, ce->guc_id));
+	GEM_BUG_ON(context_enabled(ce));
+
+	clr_context_registered(ce);
+	deregister_context(ce, ce->guc_id, true);
+}
+
+static void __guc_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_HIGH] ||
+		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_HIGH] ||
+		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] ||
+		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_NORMAL]);
+
+	lrc_fini(ce);
+	intel_context_fini(ce);
+
+	if (intel_engine_is_virtual(ce->engine)) {
+		struct guc_virtual_engine *ve =
+			container_of(ce, typeof(*ve), context);
+
+		if (ve->base.breadcrumbs)
+			intel_breadcrumbs_put(ve->base.breadcrumbs);
+
+		kfree(ve);
+	} else {
+		intel_context_free(ce);
+	}
+}
+
+static void guc_context_destroy(struct kref *kref)
+{
+	struct intel_context *ce = container_of(kref, typeof(*ce), ref);
+	struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm;
+	struct intel_guc *guc = ce_to_guc(ce);
+	intel_wakeref_t wakeref;
+	unsigned long flags;
+	bool disabled;
+
+	/*
+	 * If the guc_id is invalid this context has been stolen and we can free
+	 * it immediately. Also can be freed immediately if the context is not
+	 * registered with the GuC or the GuC is in the middle of a reset.
+	 */
+	if (context_guc_id_invalid(ce)) {
+		__guc_context_destroy(ce);
+		return;
+	} else if (submission_disabled(guc) ||
+		   !lrc_desc_registered(guc, ce->guc_id)) {
+		release_guc_id(guc, ce);
+		__guc_context_destroy(ce);
+		return;
+	}
+
+	/*
+	 * We have to acquire the context spinlock and check guc_id again, if it
+	 * is valid it hasn't been stolen and needs to be deregistered. We
+	 * delete this context from the list of unpinned guc_ids available to
+	 * steal to seal a race with guc_lrc_desc_pin(). When the G2H CTB
+	 * returns indicating this context has been deregistered the guc_id is
+	 * returned to the pool of available guc_ids.
+	 */
+	spin_lock_irqsave(&guc->contexts_lock, flags);
+	if (context_guc_id_invalid(ce)) {
+		spin_unlock_irqrestore(&guc->contexts_lock, flags);
+		__guc_context_destroy(ce);
+		return;
+	}
+
+	if (!list_empty(&ce->guc_id_link))
+		list_del_init(&ce->guc_id_link);
+	spin_unlock_irqrestore(&guc->contexts_lock, flags);
+
+	/* Seal race with Reset */
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	disabled = submission_disabled(guc);
+	if (likely(!disabled))
+		set_context_destroyed(ce);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+	if (unlikely(disabled)) {
+		release_guc_id(guc, ce);
+		__guc_context_destroy(ce);
+		return;
+	}
+
+	/*
+	 * We defer GuC context deregistration until the context is destroyed
+	 * in order to save on CTBs. With this optimization ideally we only need
+	 * 1 CTB to register the context during the first pin and 1 CTB to
+	 * deregister the context when the context is destroyed. Without this
+	 * optimization, a CTB would be needed every pin & unpin.
+	 *
+	 * XXX: Need to acqiure the runtime wakeref as this can be triggered
+	 * from context_free_worker when runtime wakeref is not held.
+	 * guc_lrc_desc_unpin requires the runtime as a GuC register is written
+	 * in H2G CTB to deregister the context. A future patch may defer this
+	 * H2G CTB if the runtime wakeref is zero.
+	 */
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		guc_lrc_desc_unpin(ce);
+}
+
+static int guc_context_alloc(struct intel_context *ce)
+{
+	return lrc_alloc(ce, ce->engine);
+}
+
+static void guc_context_set_prio(struct intel_guc *guc,
+				 struct intel_context *ce,
+				 u8 prio)
+{
+	u32 action[] = {
+		INTEL_GUC_ACTION_SET_CONTEXT_PRIORITY,
+		ce->guc_id,
+		prio,
+	};
+
+	GEM_BUG_ON(prio < GUC_CLIENT_PRIORITY_KMD_HIGH ||
+		   prio > GUC_CLIENT_PRIORITY_NORMAL);
+
+	if (ce->guc_prio == prio || submission_disabled(guc) ||
+	    !context_registered(ce))
+		return;
+
+	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+
+	ce->guc_prio = prio;
+	trace_intel_context_set_prio(ce);
+}
+
+static inline u8 map_i915_prio_to_guc_prio(int prio)
+{
+	if (prio == I915_PRIORITY_NORMAL)
+		return GUC_CLIENT_PRIORITY_KMD_NORMAL;
+	else if (prio < I915_PRIORITY_NORMAL)
+		return GUC_CLIENT_PRIORITY_NORMAL;
+	else if (prio < I915_PRIORITY_DISPLAY)
+		return GUC_CLIENT_PRIORITY_HIGH;
+	else
+		return GUC_CLIENT_PRIORITY_KMD_HIGH;
+}
+
+static inline void add_context_inflight_prio(struct intel_context *ce,
+					     u8 guc_prio)
+{
+	lockdep_assert_held(&ce->guc_active.lock);
+	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count));
+
+	++ce->guc_prio_count[guc_prio];
+
+	/* Overflow protection */
+	GEM_WARN_ON(!ce->guc_prio_count[guc_prio]);
+}
+
+static inline void sub_context_inflight_prio(struct intel_context *ce,
+					     u8 guc_prio)
+{
+	lockdep_assert_held(&ce->guc_active.lock);
+	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count));
+
+	/* Underflow protection */
+	GEM_WARN_ON(!ce->guc_prio_count[guc_prio]);
+
+	--ce->guc_prio_count[guc_prio];
+}
+
+static inline void update_context_prio(struct intel_context *ce)
+{
+	struct intel_guc *guc = &ce->engine->gt->uc.guc;
+	int i;
+
+	BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH != 0);
+	BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH > GUC_CLIENT_PRIORITY_NORMAL);
+
+	lockdep_assert_held(&ce->guc_active.lock);
+
+	for (i = 0; i < ARRAY_SIZE(ce->guc_prio_count); ++i) {
+		if (ce->guc_prio_count[i]) {
+			guc_context_set_prio(guc, ce, i);
+			break;
+		}
+	}
+}
+
+static inline bool new_guc_prio_higher(u8 old_guc_prio, u8 new_guc_prio)
+{
+	/* Lower value is higher priority */
+	return new_guc_prio < old_guc_prio;
+}
+
+static void add_to_context(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+	u8 new_guc_prio = map_i915_prio_to_guc_prio(rq_prio(rq));
+
+	GEM_BUG_ON(rq->guc_prio == GUC_PRIO_FINI);
+
+	spin_lock(&ce->guc_active.lock);
+	list_move_tail(&rq->sched.link, &ce->guc_active.requests);
+
+	if (rq->guc_prio == GUC_PRIO_INIT) {
+		rq->guc_prio = new_guc_prio;
+		add_context_inflight_prio(ce, rq->guc_prio);
+	} else if (new_guc_prio_higher(rq->guc_prio, new_guc_prio)) {
+		sub_context_inflight_prio(ce, rq->guc_prio);
+		rq->guc_prio = new_guc_prio;
+		add_context_inflight_prio(ce, rq->guc_prio);
+	}
+	update_context_prio(ce);
+
+	spin_unlock(&ce->guc_active.lock);
+}
+
+static void guc_prio_fini(struct i915_request *rq, struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_active.lock);
+
+	if (rq->guc_prio != GUC_PRIO_INIT &&
+	    rq->guc_prio != GUC_PRIO_FINI) {
+		sub_context_inflight_prio(ce, rq->guc_prio);
+		update_context_prio(ce);
+	}
+	rq->guc_prio = GUC_PRIO_FINI;
+}
+
+static void remove_from_context(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+
+	spin_lock_irq(&ce->guc_active.lock);
+
+	list_del_init(&rq->sched.link);
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+
+	/* Prevent further __await_execution() registering a cb, then flush */
+	set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
+
+	guc_prio_fini(rq, ce);
+
+	spin_unlock_irq(&ce->guc_active.lock);
+
+	atomic_dec(&ce->guc_id_ref);
+	i915_request_notify_execute_cb_imm(rq);
 }
 
 static const struct intel_context_ops guc_context_ops = {
@@ -454,28 +1976,71 @@ static const struct intel_context_ops guc_context_ops = {
 
 	.pre_pin = guc_context_pre_pin,
 	.pin = guc_context_pin,
-	.unpin = lrc_unpin,
-	.post_unpin = lrc_post_unpin,
+	.unpin = guc_context_unpin,
+	.post_unpin = guc_context_post_unpin,
+
+	.ban = guc_context_ban,
+
+	.cancel_request = guc_context_cancel_request,
 
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
 
+	.sched_disable = guc_context_sched_disable,
+
 	.reset = lrc_reset,
-	.destroy = lrc_destroy,
+	.destroy = guc_context_destroy,
+
+	.create_virtual = guc_create_virtual,
 };
 
-static int guc_request_alloc(struct i915_request *request)
+static void __guc_signal_context_fence(struct intel_context *ce)
 {
+	struct i915_request *rq;
+
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	if (!list_empty(&ce->guc_state.fences))
+		trace_intel_context_fence_release(ce);
+
+	list_for_each_entry(rq, &ce->guc_state.fences, guc_fence_link)
+		i915_sw_fence_complete(&rq->submit);
+
+	INIT_LIST_HEAD(&ce->guc_state.fences);
+}
+
+static void guc_signal_context_fence(struct intel_context *ce)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	clr_context_wait_for_deregister_to_register(ce);
+	__guc_signal_context_fence(ce);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+}
+
+static bool context_needs_register(struct intel_context *ce, bool new_guc_id)
+{
+	return (new_guc_id || test_bit(CONTEXT_LRCA_DIRTY, &ce->flags) ||
+		!lrc_desc_registered(ce_to_guc(ce), ce->guc_id)) &&
+		!submission_disabled(ce_to_guc(ce));
+}
+
+static int guc_request_alloc(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+	struct intel_guc *guc = ce_to_guc(ce);
+	unsigned long flags;
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->context));
+	GEM_BUG_ON(!intel_context_is_pinned(rq->context));
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
 	 * have to repeat work.
 	 */
-	request->reserved_space += GUC_REQUEST_SIZE;
+	rq->reserved_space += GUC_REQUEST_SIZE;
 
 	/*
 	 * Note that after this point, we have committed to using
@@ -486,40 +2051,232 @@ static int guc_request_alloc(struct i915_request *request)
 	 */
 
 	/* Unconditionally invalidate GPU caches and TLBs. */
-	ret = request->engine->emit_flush(request, EMIT_INVALIDATE);
+	ret = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
 	if (ret)
 		return ret;
 
-	request->reserved_space -= GUC_REQUEST_SIZE;
+	rq->reserved_space -= GUC_REQUEST_SIZE;
+
+	/*
+	 * Call pin_guc_id here rather than in the pinning step as with
+	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
+	 * guc_ids and creating horrible race conditions. This is especially bad
+	 * when guc_ids are being stolen due to over subscription. By the time
+	 * this function is reached, it is guaranteed that the guc_id will be
+	 * persistent until the generated request is retired. Thus, sealing these
+	 * race conditions. It is still safe to fail here if guc_ids are
+	 * exhausted and return -EAGAIN to the user indicating that they can try
+	 * again in the future.
+	 *
+	 * There is no need for a lock here as the timeline mutex ensures at
+	 * most one context can be executing this code path at once. The
+	 * guc_id_ref is incremented once for every request in flight and
+	 * decremented on each retire. When it is zero, a lock around the
+	 * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id.
+	 */
+	if (atomic_add_unless(&ce->guc_id_ref, 1, 0))
+		goto out;
+
+	ret = pin_guc_id(guc, ce);	/* returns 1 if new guc_id assigned */
+	if (unlikely(ret < 0))
+		return ret;
+	if (context_needs_register(ce, !!ret)) {
+		ret = guc_lrc_desc_pin(ce, true);
+		if (unlikely(ret)) {	/* unwind */
+			if (ret == -EPIPE) {
+				disable_submission(guc);
+				goto out;	/* GPU will be reset */
+			}
+			atomic_dec(&ce->guc_id_ref);
+			unpin_guc_id(guc, ce);
+			return ret;
+		}
+	}
+
+	clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
+
+out:
+	/*
+	 * We block all requests on this context if a G2H is pending for a
+	 * schedule disable or context deregistration as the GuC will fail a
+	 * schedule enable or context registration if either G2H is pending
+	 * respectfully. Once a G2H returns, the fence is released that is
+	 * blocking these requests (see guc_signal_context_fence).
+	 *
+	 * We can safely check the below fields outside of the lock as it isn't
+	 * possible for these fields to transition from being clear to set but
+	 * converse is possible, hence the need for the check within the lock.
+	 */
+	if (likely(!context_wait_for_deregister_to_register(ce) &&
+		   !context_pending_disable(ce)))
+		return 0;
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	if (context_wait_for_deregister_to_register(ce) ||
+	    context_pending_disable(ce)) {
+		i915_sw_fence_await(&rq->submit);
+
+		list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences);
+	}
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
 	return 0;
 }
 
-static inline void queue_request(struct intel_engine_cs *engine,
-				 struct i915_request *rq,
-				 int prio)
+static int guc_virtual_context_pre_pin(struct intel_context *ce,
+				       struct i915_gem_ww_ctx *ww,
+				       void **vaddr)
 {
-	GEM_BUG_ON(!list_empty(&rq->sched.link));
-	list_add_tail(&rq->sched.link,
-		      i915_sched_lookup_priolist(engine, prio));
-	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
+
+	return __guc_context_pre_pin(ce, engine, ww, vaddr);
 }
 
-static void guc_submit_request(struct i915_request *rq)
+static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr)
 {
-	struct intel_engine_cs *engine = rq->engine;
-	unsigned long flags;
+	struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
 
-	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	return __guc_context_pin(ce, engine, vaddr);
+}
 
-	queue_request(engine, rq, rq_prio(rq));
+static void guc_virtual_context_enter(struct intel_context *ce)
+{
+	intel_engine_mask_t tmp, mask = ce->engine->mask;
+	struct intel_engine_cs *engine;
 
-	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
-	GEM_BUG_ON(list_empty(&rq->sched.link));
+	for_each_engine_masked(engine, ce->engine->gt, mask, tmp)
+		intel_engine_pm_get(engine);
 
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	intel_timeline_enter(ce->timeline);
+}
+
+static void guc_virtual_context_exit(struct intel_context *ce)
+{
+	intel_engine_mask_t tmp, mask = ce->engine->mask;
+	struct intel_engine_cs *engine;
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	for_each_engine_masked(engine, ce->engine->gt, mask, tmp)
+		intel_engine_pm_put(engine);
+
+	intel_timeline_exit(ce->timeline);
+}
+
+static int guc_virtual_context_alloc(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
+
+	return lrc_alloc(ce, engine);
+}
+
+static const struct intel_context_ops virtual_guc_context_ops = {
+	.alloc = guc_virtual_context_alloc,
+
+	.pre_pin = guc_virtual_context_pre_pin,
+	.pin = guc_virtual_context_pin,
+	.unpin = guc_context_unpin,
+	.post_unpin = guc_context_post_unpin,
+
+	.ban = guc_context_ban,
+
+	.cancel_request = guc_context_cancel_request,
+
+	.enter = guc_virtual_context_enter,
+	.exit = guc_virtual_context_exit,
+
+	.sched_disable = guc_context_sched_disable,
+
+	.destroy = guc_context_destroy,
+
+	.get_sibling = guc_virtual_get_sibling,
+};
+
+static bool
+guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b)
+{
+	struct intel_engine_cs *sibling;
+	intel_engine_mask_t tmp, mask = b->engine_mask;
+	bool result = false;
+
+	for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp)
+		result |= intel_engine_irq_enable(sibling);
+
+	return result;
+}
+
+static void
+guc_irq_disable_breadcrumbs(struct intel_breadcrumbs *b)
+{
+	struct intel_engine_cs *sibling;
+	intel_engine_mask_t tmp, mask = b->engine_mask;
+
+	for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp)
+		intel_engine_irq_disable(sibling);
+}
+
+static void guc_init_breadcrumbs(struct intel_engine_cs *engine)
+{
+	int i;
+
+	/*
+	 * In GuC submission mode we do not know which physical engine a request
+	 * will be scheduled on, this creates a problem because the breadcrumb
+	 * interrupt is per physical engine. To work around this we attach
+	 * requests and direct all breadcrumb interrupts to the first instance
+	 * of an engine per class. In addition all breadcrumb interrupts are
+	 * enabled / disabled across an engine class in unison.
+	 */
+	for (i = 0; i < MAX_ENGINE_INSTANCE; ++i) {
+		struct intel_engine_cs *sibling =
+			engine->gt->engine_class[engine->class][i];
+
+		if (sibling) {
+			if (engine->breadcrumbs != sibling->breadcrumbs) {
+				intel_breadcrumbs_put(engine->breadcrumbs);
+				engine->breadcrumbs =
+					intel_breadcrumbs_get(sibling->breadcrumbs);
+			}
+			break;
+		}
+	}
+
+	if (engine->breadcrumbs) {
+		engine->breadcrumbs->engine_mask |= engine->mask;
+		engine->breadcrumbs->irq_enable = guc_irq_enable_breadcrumbs;
+		engine->breadcrumbs->irq_disable = guc_irq_disable_breadcrumbs;
+	}
+}
+
+static void guc_bump_inflight_request_prio(struct i915_request *rq,
+					   int prio)
+{
+	struct intel_context *ce = rq->context;
+	u8 new_guc_prio = map_i915_prio_to_guc_prio(prio);
+
+	/* Short circuit function */
+	if (prio < I915_PRIORITY_NORMAL ||
+	    rq->guc_prio == GUC_PRIO_FINI ||
+	    (rq->guc_prio != GUC_PRIO_INIT &&
+	     !new_guc_prio_higher(rq->guc_prio, new_guc_prio)))
+		return;
+
+	spin_lock(&ce->guc_active.lock);
+	if (rq->guc_prio != GUC_PRIO_FINI) {
+		if (rq->guc_prio != GUC_PRIO_INIT)
+			sub_context_inflight_prio(ce, rq->guc_prio);
+		rq->guc_prio = new_guc_prio;
+		add_context_inflight_prio(ce, rq->guc_prio);
+		update_context_prio(ce);
+	}
+	spin_unlock(&ce->guc_active.lock);
+}
+
+static void guc_retire_inflight_request_prio(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+
+	spin_lock(&ce->guc_active.lock);
+	guc_prio_fini(rq, ce);
+	spin_unlock(&ce->guc_active.lock);
 }
 
 static void sanitize_hwsp(struct intel_engine_cs *engine)
@@ -588,21 +2345,68 @@ static int guc_resume(struct intel_engine_cs *engine)
 	return 0;
 }
 
+static bool guc_sched_engine_disabled(struct i915_sched_engine *sched_engine)
+{
+	return !sched_engine->tasklet.callback;
+}
+
 static void guc_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = guc_submit_request;
 }
 
+static inline void guc_kernel_context_pin(struct intel_guc *guc,
+					  struct intel_context *ce)
+{
+	if (context_guc_id_invalid(ce))
+		pin_guc_id(guc, ce);
+	guc_lrc_desc_pin(ce, true);
+}
+
+static inline void guc_init_lrc_mapping(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* make sure all descriptors are clean... */
+	xa_destroy(&guc->context_lookup);
+
+	/*
+	 * Some contexts might have been pinned before we enabled GuC
+	 * submission, so we need to add them to the GuC bookeeping.
+	 * Also, after a reset the of the GuC we want to make sure that the
+	 * information shared with GuC is properly reset. The kernel LRCs are
+	 * not attached to the gem_context, so they need to be added separately.
+	 *
+	 * Note: we purposefully do not check the return of guc_lrc_desc_pin,
+	 * because that function can only fail if a reset is just starting. This
+	 * is at the end of reset so presumably another reset isn't happening
+	 * and even it did this code would be run again.
+	 */
+
+	for_each_engine(engine, gt, id)
+		if (engine->kernel_context)
+			guc_kernel_context_pin(guc, engine->kernel_context);
+}
+
 static void guc_release(struct intel_engine_cs *engine)
 {
 	engine->sanitize = NULL; /* no longer in control, nothing to sanitize */
 
-	tasklet_kill(&engine->execlists.tasklet);
-
 	intel_engine_cleanup_common(engine);
 	lrc_fini_wa_ctx(engine);
 }
 
+static void virtual_guc_bump_serial(struct intel_engine_cs *engine)
+{
+	struct intel_engine_cs *e;
+	intel_engine_mask_t tmp, mask = engine->mask;
+
+	for_each_engine_masked(e, engine->gt, mask, tmp)
+		e->serial++;
+}
+
 static void guc_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overridden by each engine. */
@@ -611,13 +2415,15 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 
 	engine->cops = &guc_context_ops;
 	engine->request_alloc = guc_request_alloc;
+	engine->add_active_request = add_to_context;
+	engine->remove_active_request = remove_from_context;
 
-	engine->schedule = i915_schedule;
+	engine->sched_engine->schedule = i915_schedule;
 
-	engine->reset.prepare = guc_reset_prepare;
-	engine->reset.rewind = guc_reset_rewind;
-	engine->reset.cancel = guc_reset_cancel;
-	engine->reset.finish = guc_reset_finish;
+	engine->reset.prepare = guc_reset_nop;
+	engine->reset.rewind = guc_rewind_nop;
+	engine->reset.cancel = guc_reset_nop;
+	engine->reset.finish = guc_reset_nop;
 
 	engine->emit_flush = gen8_emit_flush_xcs;
 	engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb;
@@ -629,13 +2435,13 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 	engine->set_default_submission = guc_set_default_submission;
 
 	engine->flags |= I915_ENGINE_HAS_PREEMPTION;
+	engine->flags |= I915_ENGINE_HAS_TIMESLICES;
 
 	/*
 	 * TODO: GuC supports timeslicing and semaphores as well, but they're
 	 * handled by the firmware so some minor tweaks are required before
 	 * enabling.
 	 *
-	 * engine->flags |= I915_ENGINE_HAS_TIMESLICES;
 	 * engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
 	 */
 
@@ -666,9 +2472,21 @@ static inline void guc_default_irqs(struct intel_engine_cs *engine)
 	intel_engine_set_irq_handler(engine, cs_irq_handler);
 }
 
+static void guc_sched_engine_destroy(struct kref *kref)
+{
+	struct i915_sched_engine *sched_engine =
+		container_of(kref, typeof(*sched_engine), ref);
+	struct intel_guc *guc = sched_engine->private_data;
+
+	guc->sched_engine = NULL;
+	tasklet_kill(&sched_engine->tasklet); /* flush the callback */
+	kfree(sched_engine);
+}
+
 int intel_guc_submission_setup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
+	struct intel_guc *guc = &engine->gt->uc.guc;
 
 	/*
 	 * The setup relies on several assumptions (e.g. irqs always enabled)
@@ -676,10 +2494,28 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
 	 */
 	GEM_BUG_ON(GRAPHICS_VER(i915) < 11);
 
-	tasklet_setup(&engine->execlists.tasklet, guc_submission_tasklet);
+	if (!guc->sched_engine) {
+		guc->sched_engine = i915_sched_engine_create(ENGINE_VIRTUAL);
+		if (!guc->sched_engine)
+			return -ENOMEM;
+
+		guc->sched_engine->schedule = i915_schedule;
+		guc->sched_engine->disabled = guc_sched_engine_disabled;
+		guc->sched_engine->private_data = guc;
+		guc->sched_engine->destroy = guc_sched_engine_destroy;
+		guc->sched_engine->bump_inflight_request_prio =
+			guc_bump_inflight_request_prio;
+		guc->sched_engine->retire_inflight_request_prio =
+			guc_retire_inflight_request_prio;
+		tasklet_setup(&guc->sched_engine->tasklet,
+			      guc_submission_tasklet);
+	}
+	i915_sched_engine_put(engine->sched_engine);
+	engine->sched_engine = i915_sched_engine_get(guc->sched_engine);
 
 	guc_default_vfuncs(engine);
 	guc_default_irqs(engine);
+	guc_init_breadcrumbs(engine);
 
 	if (engine->class == RENDER_CLASS)
 		rcs_submission_override(engine);
@@ -695,18 +2531,19 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
 
 void intel_guc_submission_enable(struct intel_guc *guc)
 {
-	guc_stage_desc_init(guc);
+	guc_init_lrc_mapping(guc);
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
 {
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	GEM_BUG_ON(gt->awake); /* GT should be parked first */
-
 	/* Note: By the time we're here, GuC may have already been reset */
+}
 
-	guc_stage_desc_fini(guc);
+static bool __guc_submission_supported(struct intel_guc *guc)
+{
+	/* GuC submission is unavailable for pre-Gen11 */
+	return intel_guc_is_supported(guc) &&
+	       GRAPHICS_VER(guc_to_gt(guc)->i915) >= 11;
 }
 
 static bool __guc_submission_selected(struct intel_guc *guc)
@@ -721,5 +2558,481 @@ static bool __guc_submission_selected(struct intel_guc *guc)
 
 void intel_guc_submission_init_early(struct intel_guc *guc)
 {
+	guc->submission_supported = __guc_submission_supported(guc);
 	guc->submission_selected = __guc_submission_selected(guc);
 }
+
+static inline struct intel_context *
+g2h_context_lookup(struct intel_guc *guc, u32 desc_idx)
+{
+	struct intel_context *ce;
+
+	if (unlikely(desc_idx >= GUC_MAX_LRC_DESCRIPTORS)) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Invalid desc_idx %u", desc_idx);
+		return NULL;
+	}
+
+	ce = __get_context(guc, desc_idx);
+	if (unlikely(!ce)) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Context is NULL, desc_idx %u", desc_idx);
+		return NULL;
+	}
+
+	return ce;
+}
+
+static void decr_outstanding_submission_g2h(struct intel_guc *guc)
+{
+	if (atomic_dec_and_test(&guc->outstanding_submission_g2h))
+		wake_up_all(&guc->ct.wq);
+}
+
+int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
+					  const u32 *msg,
+					  u32 len)
+{
+	struct intel_context *ce;
+	u32 desc_idx = msg[0];
+
+	if (unlikely(len < 1)) {
+		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	ce = g2h_context_lookup(guc, desc_idx);
+	if (unlikely(!ce))
+		return -EPROTO;
+
+	trace_intel_context_deregister_done(ce);
+
+	if (context_wait_for_deregister_to_register(ce)) {
+		struct intel_runtime_pm *runtime_pm =
+			&ce->engine->gt->i915->runtime_pm;
+		intel_wakeref_t wakeref;
+
+		/*
+		 * Previous owner of this guc_id has been deregistered, now safe
+		 * register this context.
+		 */
+		with_intel_runtime_pm(runtime_pm, wakeref)
+			register_context(ce, true);
+		guc_signal_context_fence(ce);
+		intel_context_put(ce);
+	} else if (context_destroyed(ce)) {
+		/* Context has been destroyed */
+		release_guc_id(guc, ce);
+		__guc_context_destroy(ce);
+	}
+
+	decr_outstanding_submission_g2h(guc);
+
+	return 0;
+}
+
+int intel_guc_sched_done_process_msg(struct intel_guc *guc,
+				     const u32 *msg,
+				     u32 len)
+{
+	struct intel_context *ce;
+	unsigned long flags;
+	u32 desc_idx = msg[0];
+
+	if (unlikely(len < 2)) {
+		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	ce = g2h_context_lookup(guc, desc_idx);
+	if (unlikely(!ce))
+		return -EPROTO;
+
+	if (unlikely(context_destroyed(ce) ||
+		     (!context_pending_enable(ce) &&
+		     !context_pending_disable(ce)))) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Bad context sched_state 0x%x, 0x%x, desc_idx %u",
+			atomic_read(&ce->guc_sched_state_no_lock),
+			ce->guc_state.sched_state, desc_idx);
+		return -EPROTO;
+	}
+
+	trace_intel_context_sched_done(ce);
+
+	if (context_pending_enable(ce)) {
+		clr_context_pending_enable(ce);
+	} else if (context_pending_disable(ce)) {
+		bool banned;
+
+		/*
+		 * Unpin must be done before __guc_signal_context_fence,
+		 * otherwise a race exists between the requests getting
+		 * submitted + retired before this unpin completes resulting in
+		 * the pin_count going to zero and the context still being
+		 * enabled.
+		 */
+		intel_context_sched_disable_unpin(ce);
+
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
+		banned = context_banned(ce);
+		clr_context_banned(ce);
+		clr_context_pending_disable(ce);
+		__guc_signal_context_fence(ce);
+		guc_blocked_fence_complete(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+		if (banned) {
+			guc_cancel_context_requests(ce);
+			intel_engine_signal_breadcrumbs(ce->engine);
+		}
+	}
+
+	decr_outstanding_submission_g2h(guc);
+	intel_context_put(ce);
+
+	return 0;
+}
+
+static void capture_error_state(struct intel_guc *guc,
+				struct intel_context *ce)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
+	intel_wakeref_t wakeref;
+
+	intel_engine_set_hung_context(engine, ce);
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		i915_capture_error_state(gt, engine->mask);
+	atomic_inc(&i915->gpu_error.reset_engine_count[engine->uabi_class]);
+}
+
+static void guc_context_replay(struct intel_context *ce)
+{
+	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
+
+	__guc_reset_context(ce, true);
+	tasklet_hi_schedule(&sched_engine->tasklet);
+}
+
+static void guc_handle_context_reset(struct intel_guc *guc,
+				     struct intel_context *ce)
+{
+	trace_intel_context_reset(ce);
+
+	if (likely(!intel_context_is_banned(ce))) {
+		capture_error_state(guc, ce);
+		guc_context_replay(ce);
+	}
+}
+
+int intel_guc_context_reset_process_msg(struct intel_guc *guc,
+					const u32 *msg, u32 len)
+{
+	struct intel_context *ce;
+	int desc_idx;
+
+	if (unlikely(len != 1)) {
+		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	desc_idx = msg[0];
+	ce = g2h_context_lookup(guc, desc_idx);
+	if (unlikely(!ce))
+		return -EPROTO;
+
+	guc_handle_context_reset(guc, ce);
+
+	return 0;
+}
+
+static struct intel_engine_cs *
+guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	u8 engine_class = guc_class_to_engine_class(guc_class);
+
+	/* Class index is checked in class converter */
+	GEM_BUG_ON(instance > MAX_ENGINE_INSTANCE);
+
+	return gt->engine_class[engine_class][instance];
+}
+
+int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
+					 const u32 *msg, u32 len)
+{
+	struct intel_engine_cs *engine;
+	u8 guc_class, instance;
+	u32 reason;
+
+	if (unlikely(len != 3)) {
+		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	guc_class = msg[0];
+	instance = msg[1];
+	reason = msg[2];
+
+	engine = guc_lookup_engine(guc, guc_class, instance);
+	if (unlikely(!engine)) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Invalid engine %d:%d", guc_class, instance);
+		return -EPROTO;
+	}
+
+	intel_gt_handle_error(guc_to_gt(guc), engine->mask,
+			      I915_ERROR_CAPTURE,
+			      "GuC failed to reset %s (reason=0x%08x)\n",
+			      engine->name, reason);
+
+	return 0;
+}
+
+void intel_guc_find_hung_context(struct intel_engine_cs *engine)
+{
+	struct intel_guc *guc = &engine->gt->uc.guc;
+	struct intel_context *ce;
+	struct i915_request *rq;
+	unsigned long index;
+
+	/* Reset called during driver load? GuC not yet initialised! */
+	if (unlikely(!guc_submission_initialized(guc)))
+		return;
+
+	xa_for_each(&guc->context_lookup, index, ce) {
+		if (!intel_context_is_pinned(ce))
+			continue;
+
+		if (intel_engine_is_virtual(ce->engine)) {
+			if (!(ce->engine->mask & engine->mask))
+				continue;
+		} else {
+			if (ce->engine != engine)
+				continue;
+		}
+
+		list_for_each_entry(rq, &ce->guc_active.requests, sched.link) {
+			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
+				continue;
+
+			intel_engine_set_hung_context(engine, ce);
+
+			/* Can only cope with one hang at a time... */
+			return;
+		}
+	}
+}
+
+void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
+				    struct i915_request *hung_rq,
+				    struct drm_printer *m)
+{
+	struct intel_guc *guc = &engine->gt->uc.guc;
+	struct intel_context *ce;
+	unsigned long index;
+	unsigned long flags;
+
+	/* Reset called during driver load? GuC not yet initialised! */
+	if (unlikely(!guc_submission_initialized(guc)))
+		return;
+
+	xa_for_each(&guc->context_lookup, index, ce) {
+		if (!intel_context_is_pinned(ce))
+			continue;
+
+		if (intel_engine_is_virtual(ce->engine)) {
+			if (!(ce->engine->mask & engine->mask))
+				continue;
+		} else {
+			if (ce->engine != engine)
+				continue;
+		}
+
+		spin_lock_irqsave(&ce->guc_active.lock, flags);
+		intel_engine_dump_active_requests(&ce->guc_active.requests,
+						  hung_rq, m);
+		spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+	}
+}
+
+void intel_guc_submission_print_info(struct intel_guc *guc,
+				     struct drm_printer *p)
+{
+	struct i915_sched_engine *sched_engine = guc->sched_engine;
+	struct rb_node *rb;
+	unsigned long flags;
+
+	if (!sched_engine)
+		return;
+
+	drm_printf(p, "GuC Number Outstanding Submission G2H: %u\n",
+		   atomic_read(&guc->outstanding_submission_g2h));
+	drm_printf(p, "GuC tasklet count: %u\n\n",
+		   atomic_read(&sched_engine->tasklet.count));
+
+	spin_lock_irqsave(&sched_engine->lock, flags);
+	drm_printf(p, "Requests in GuC submit tasklet:\n");
+	for (rb = rb_first_cached(&sched_engine->queue); rb; rb = rb_next(rb)) {
+		struct i915_priolist *pl = to_priolist(rb);
+		struct i915_request *rq;
+
+		priolist_for_each_request(rq, pl)
+			drm_printf(p, "guc_id=%u, seqno=%llu\n",
+				   rq->context->guc_id,
+				   rq->fence.seqno);
+	}
+	spin_unlock_irqrestore(&sched_engine->lock, flags);
+	drm_printf(p, "\n");
+}
+
+static inline void guc_log_context_priority(struct drm_printer *p,
+					    struct intel_context *ce)
+{
+	int i;
+
+	drm_printf(p, "\t\tPriority: %d\n",
+		   ce->guc_prio);
+	drm_printf(p, "\t\tNumber Requests (lower index == higher priority)\n");
+	for (i = GUC_CLIENT_PRIORITY_KMD_HIGH;
+	     i < GUC_CLIENT_PRIORITY_NUM; ++i) {
+		drm_printf(p, "\t\tNumber requests in priority band[%d]: %d\n",
+			   i, ce->guc_prio_count[i]);
+	}
+	drm_printf(p, "\n");
+}
+
+void intel_guc_submission_print_context_info(struct intel_guc *guc,
+					     struct drm_printer *p)
+{
+	struct intel_context *ce;
+	unsigned long index;
+
+	xa_for_each(&guc->context_lookup, index, ce) {
+		drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id);
+		drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
+		drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
+			   ce->ring->head,
+			   ce->lrc_reg_state[CTX_RING_HEAD]);
+		drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n",
+			   ce->ring->tail,
+			   ce->lrc_reg_state[CTX_RING_TAIL]);
+		drm_printf(p, "\t\tContext Pin Count: %u\n",
+			   atomic_read(&ce->pin_count));
+		drm_printf(p, "\t\tGuC ID Ref Count: %u\n",
+			   atomic_read(&ce->guc_id_ref));
+		drm_printf(p, "\t\tSchedule State: 0x%x, 0x%x\n\n",
+			   ce->guc_state.sched_state,
+			   atomic_read(&ce->guc_sched_state_no_lock));
+
+		guc_log_context_priority(p, ce);
+	}
+}
+
+static struct intel_context *
+guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
+{
+	struct guc_virtual_engine *ve;
+	struct intel_guc *guc;
+	unsigned int n;
+	int err;
+
+	ve = kzalloc(sizeof(*ve), GFP_KERNEL);
+	if (!ve)
+		return ERR_PTR(-ENOMEM);
+
+	guc = &siblings[0]->gt->uc.guc;
+
+	ve->base.i915 = siblings[0]->i915;
+	ve->base.gt = siblings[0]->gt;
+	ve->base.uncore = siblings[0]->uncore;
+	ve->base.id = -1;
+
+	ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
+	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+	ve->base.saturated = ALL_ENGINES;
+
+	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
+
+	ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine);
+
+	ve->base.cops = &virtual_guc_context_ops;
+	ve->base.request_alloc = guc_request_alloc;
+	ve->base.bump_serial = virtual_guc_bump_serial;
+
+	ve->base.submit_request = guc_submit_request;
+
+	ve->base.flags = I915_ENGINE_IS_VIRTUAL;
+
+	intel_context_init(&ve->context, &ve->base);
+
+	for (n = 0; n < count; n++) {
+		struct intel_engine_cs *sibling = siblings[n];
+
+		GEM_BUG_ON(!is_power_of_2(sibling->mask));
+		if (sibling->mask & ve->base.mask) {
+			DRM_DEBUG("duplicate %s entry in load balancer\n",
+				  sibling->name);
+			err = -EINVAL;
+			goto err_put;
+		}
+
+		ve->base.mask |= sibling->mask;
+
+		if (n != 0 && ve->base.class != sibling->class) {
+			DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n",
+				  sibling->class, ve->base.class);
+			err = -EINVAL;
+			goto err_put;
+		} else if (n == 0) {
+			ve->base.class = sibling->class;
+			ve->base.uabi_class = sibling->uabi_class;
+			snprintf(ve->base.name, sizeof(ve->base.name),
+				 "v%dx%d", ve->base.class, count);
+			ve->base.context_size = sibling->context_size;
+
+			ve->base.add_active_request =
+				sibling->add_active_request;
+			ve->base.remove_active_request =
+				sibling->remove_active_request;
+			ve->base.emit_bb_start = sibling->emit_bb_start;
+			ve->base.emit_flush = sibling->emit_flush;
+			ve->base.emit_init_breadcrumb =
+				sibling->emit_init_breadcrumb;
+			ve->base.emit_fini_breadcrumb =
+				sibling->emit_fini_breadcrumb;
+			ve->base.emit_fini_breadcrumb_dw =
+				sibling->emit_fini_breadcrumb_dw;
+			ve->base.breadcrumbs =
+				intel_breadcrumbs_get(sibling->breadcrumbs);
+
+			ve->base.flags |= sibling->flags;
+
+			ve->base.props.timeslice_duration_ms =
+				sibling->props.timeslice_duration_ms;
+			ve->base.props.preempt_timeout_ms =
+				sibling->props.preempt_timeout_ms;
+		}
+	}
+
+	return &ve->context;
+
+err_put:
+	intel_context_put(&ve->context);
+	return ERR_PTR(err);
+}
+
+bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve)
+{
+	struct intel_engine_cs *engine;
+	intel_engine_mask_t tmp, mask = ve->mask;
+
+	for_each_engine_masked(engine, ve->gt, mask, tmp)
+		if (READ_ONCE(engine->props.heartbeat_interval_ms))
+			return true;
+
+	return false;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
index 3f7005018939..c7ef44fa0c36 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
@@ -10,6 +10,7 @@
 
 #include "intel_guc.h"
 
+struct drm_printer;
 struct intel_engine_cs;
 
 void intel_guc_submission_init_early(struct intel_guc *guc);
@@ -20,11 +21,24 @@ void intel_guc_submission_fini(struct intel_guc *guc);
 int intel_guc_preempt_work_create(struct intel_guc *guc);
 void intel_guc_preempt_work_destroy(struct intel_guc *guc);
 int intel_guc_submission_setup(struct intel_engine_cs *engine);
+void intel_guc_submission_print_info(struct intel_guc *guc,
+				     struct drm_printer *p);
+void intel_guc_submission_print_context_info(struct intel_guc *guc,
+					     struct drm_printer *p);
+void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
+				    struct i915_request *hung_rq,
+				    struct drm_printer *m);
+
+bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve);
+
+int intel_guc_wait_for_pending_msg(struct intel_guc *guc,
+				   atomic_t *wait_var,
+				   bool interruptible,
+				   long timeout);
 
 static inline bool intel_guc_submission_is_supported(struct intel_guc *guc)
 {
-	/* XXX: GuC submission is unavailable for now */
-	return false;
+	return guc->submission_supported;
 }
 
 static inline bool intel_guc_submission_is_wanted(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 6d8b9233214e..b104fb7607eb 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -34,8 +34,14 @@ static void uc_expand_default_options(struct intel_uc *uc)
 		return;
 	}
 
-	/* Default: enable HuC authentication only */
-	i915->params.enable_guc = ENABLE_GUC_LOAD_HUC;
+	/* Intermediate platforms are HuC authentication only */
+	if (IS_DG1(i915) || IS_ALDERLAKE_S(i915)) {
+		i915->params.enable_guc = ENABLE_GUC_LOAD_HUC;
+		return;
+	}
+
+	/* Default: enable HuC authentication and GuC submission */
+	i915->params.enable_guc = ENABLE_GUC_LOAD_HUC | ENABLE_GUC_SUBMISSION;
 }
 
 /* Reset GuC providing us with fresh state for both GuC and HuC.
@@ -69,16 +75,18 @@ static void __confirm_options(struct intel_uc *uc)
 	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
 
 	drm_dbg(&i915->drm,
-		"enable_guc=%d (guc:%s submission:%s huc:%s)\n",
+		"enable_guc=%d (guc:%s submission:%s huc:%s slpc:%s)\n",
 		i915->params.enable_guc,
 		yesno(intel_uc_wants_guc(uc)),
 		yesno(intel_uc_wants_guc_submission(uc)),
-		yesno(intel_uc_wants_huc(uc)));
+		yesno(intel_uc_wants_huc(uc)),
+		yesno(intel_uc_wants_guc_slpc(uc)));
 
 	if (i915->params.enable_guc == 0) {
 		GEM_BUG_ON(intel_uc_wants_guc(uc));
 		GEM_BUG_ON(intel_uc_wants_guc_submission(uc));
 		GEM_BUG_ON(intel_uc_wants_huc(uc));
+		GEM_BUG_ON(intel_uc_wants_guc_slpc(uc));
 		return;
 	}
 
@@ -120,6 +128,11 @@ void intel_uc_init_early(struct intel_uc *uc)
 		uc->ops = &uc_ops_off;
 }
 
+void intel_uc_init_late(struct intel_uc *uc)
+{
+	intel_guc_init_late(&uc->guc);
+}
+
 void intel_uc_driver_late_release(struct intel_uc *uc)
 {
 }
@@ -207,21 +220,6 @@ static void guc_handle_mmio_msg(struct intel_guc *guc)
 	spin_unlock_irq(&guc->irq_lock);
 }
 
-static void guc_reset_interrupts(struct intel_guc *guc)
-{
-	guc->interrupts.reset(guc);
-}
-
-static void guc_enable_interrupts(struct intel_guc *guc)
-{
-	guc->interrupts.enable(guc);
-}
-
-static void guc_disable_interrupts(struct intel_guc *guc)
-{
-	guc->interrupts.disable(guc);
-}
-
 static int guc_enable_communication(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -242,7 +240,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	guc_get_mmio_msg(guc);
 	guc_handle_mmio_msg(guc);
 
-	guc_enable_interrupts(guc);
+	intel_guc_enable_interrupts(guc);
 
 	/* check for CT messages received before we enabled interrupts */
 	spin_lock_irq(&gt->irq_lock);
@@ -265,7 +263,7 @@ static void guc_disable_communication(struct intel_guc *guc)
 	 */
 	guc_clear_mmio_msg(guc);
 
-	guc_disable_interrupts(guc);
+	intel_guc_disable_interrupts(guc);
 
 	intel_guc_ct_disable(&guc->ct);
 
@@ -323,9 +321,6 @@ static int __uc_init(struct intel_uc *uc)
 	if (i915_inject_probe_failure(uc_to_gt(uc)->i915))
 		return -ENOMEM;
 
-	/* XXX: GuC submission is unavailable for now */
-	GEM_BUG_ON(intel_uc_uses_guc_submission(uc));
-
 	ret = intel_guc_init(guc);
 	if (ret)
 		return ret;
@@ -463,7 +458,7 @@ static int __uc_init_hw(struct intel_uc *uc)
 	if (ret)
 		goto err_out;
 
-	guc_reset_interrupts(guc);
+	intel_guc_reset_interrupts(guc);
 
 	/* WaEnableuKernelHeaderValidFix:skl */
 	/* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */
@@ -505,12 +500,21 @@ static int __uc_init_hw(struct intel_uc *uc)
 	if (intel_uc_uses_guc_submission(uc))
 		intel_guc_submission_enable(guc);
 
+	if (intel_uc_uses_guc_slpc(uc)) {
+		ret = intel_guc_slpc_enable(&guc->slpc);
+		if (ret)
+			goto err_submission;
+	}
+
 	drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
 		 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path,
 		 guc->fw.major_ver_found, guc->fw.minor_ver_found,
 		 "submission",
 		 enableddisabled(intel_uc_uses_guc_submission(uc)));
 
+	drm_info(&i915->drm, "GuC SLPC: %s\n",
+		 enableddisabled(intel_uc_uses_guc_slpc(uc)));
+
 	if (intel_uc_uses_huc(uc)) {
 		drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
 			 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC),
@@ -525,6 +529,8 @@ static int __uc_init_hw(struct intel_uc *uc)
 	/*
 	 * We've failed to load the firmware :(
 	 */
+err_submission:
+	intel_guc_submission_disable(guc);
 err_log_capture:
 	__uc_capture_load_err_log(uc);
 err_out:
@@ -565,23 +571,67 @@ void intel_uc_reset_prepare(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 
-	if (!intel_guc_is_ready(guc))
+	uc->reset_in_progress = true;
+
+	/* Nothing to do if GuC isn't supported */
+	if (!intel_uc_supports_guc(uc))
 		return;
 
+	/* Firmware expected to be running when this function is called */
+	if (!intel_guc_is_ready(guc))
+		goto sanitize;
+
+	if (intel_uc_uses_guc_submission(uc))
+		intel_guc_submission_reset_prepare(guc);
+
+sanitize:
 	__uc_sanitize(uc);
 }
 
+void intel_uc_reset(struct intel_uc *uc, bool stalled)
+{
+	struct intel_guc *guc = &uc->guc;
+
+	/* Firmware can not be running when this function is called  */
+	if (intel_uc_uses_guc_submission(uc))
+		intel_guc_submission_reset(guc, stalled);
+}
+
+void intel_uc_reset_finish(struct intel_uc *uc)
+{
+	struct intel_guc *guc = &uc->guc;
+
+	uc->reset_in_progress = false;
+
+	/* Firmware expected to be running when this function is called */
+	if (intel_guc_is_fw_running(guc) && intel_uc_uses_guc_submission(uc))
+		intel_guc_submission_reset_finish(guc);
+}
+
+void intel_uc_cancel_requests(struct intel_uc *uc)
+{
+	struct intel_guc *guc = &uc->guc;
+
+	/* Firmware can not be running when this function is called  */
+	if (intel_uc_uses_guc_submission(uc))
+		intel_guc_submission_cancel_requests(guc);
+}
+
 void intel_uc_runtime_suspend(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
-	int err;
 
 	if (!intel_guc_is_ready(guc))
 		return;
 
-	err = intel_guc_suspend(guc);
-	if (err)
-		DRM_DEBUG_DRIVER("Failed to suspend GuC, err=%d", err);
+	/*
+	 * Wait for any outstanding CTB before tearing down communication /w the
+	 * GuC.
+	 */
+#define OUTSTANDING_CTB_TIMEOUT_PERIOD	(HZ / 5)
+	intel_guc_wait_for_pending_msg(guc, &guc->outstanding_submission_g2h,
+				       false, OUTSTANDING_CTB_TIMEOUT_PERIOD);
+	GEM_WARN_ON(atomic_read(&guc->outstanding_submission_g2h));
 
 	guc_disable_communication(guc);
 }
@@ -590,17 +640,22 @@ void intel_uc_suspend(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 	intel_wakeref_t wakeref;
+	int err;
 
 	if (!intel_guc_is_ready(guc))
 		return;
 
-	with_intel_runtime_pm(uc_to_gt(uc)->uncore->rpm, wakeref)
-		intel_uc_runtime_suspend(uc);
+	with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref) {
+		err = intel_guc_suspend(guc);
+		if (err)
+			DRM_DEBUG_DRIVER("Failed to suspend GuC, err=%d", err);
+	}
 }
 
 static int __uc_resume(struct intel_uc *uc, bool enable_communication)
 {
 	struct intel_guc *guc = &uc->guc;
+	struct intel_gt *gt = guc_to_gt(guc);
 	int err;
 
 	if (!intel_guc_is_fw_running(guc))
@@ -612,6 +667,13 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication)
 	if (enable_communication)
 		guc_enable_communication(guc);
 
+	/* If we are only resuming GuC communication but not reloading
+	 * GuC, we need to ensure the ARAT timer interrupt is enabled
+	 * again. In case of GuC reload, it is enabled during SLPC enable.
+	 */
+	if (enable_communication && intel_uc_uses_guc_slpc(uc))
+		intel_guc_pm_intrmsk_enable(gt);
+
 	err = intel_guc_resume(guc);
 	if (err) {
 		DRM_DEBUG_DRIVER("Failed to resume GuC, err=%d", err);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
index 9c954c589edf..866b462821c0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
@@ -7,7 +7,9 @@
 #define _INTEL_UC_H_
 
 #include "intel_guc.h"
+#include "intel_guc_rc.h"
 #include "intel_guc_submission.h"
+#include "intel_guc_slpc.h"
 #include "intel_huc.h"
 #include "i915_params.h"
 
@@ -30,13 +32,19 @@ struct intel_uc {
 
 	/* Snapshot of GuC log from last failed load */
 	struct drm_i915_gem_object *load_err_log;
+
+	bool reset_in_progress;
 };
 
 void intel_uc_init_early(struct intel_uc *uc);
+void intel_uc_init_late(struct intel_uc *uc);
 void intel_uc_driver_late_release(struct intel_uc *uc);
 void intel_uc_driver_remove(struct intel_uc *uc);
 void intel_uc_init_mmio(struct intel_uc *uc);
 void intel_uc_reset_prepare(struct intel_uc *uc);
+void intel_uc_reset(struct intel_uc *uc, bool stalled);
+void intel_uc_reset_finish(struct intel_uc *uc);
+void intel_uc_cancel_requests(struct intel_uc *uc);
 void intel_uc_suspend(struct intel_uc *uc);
 void intel_uc_runtime_suspend(struct intel_uc *uc);
 int intel_uc_resume(struct intel_uc *uc);
@@ -77,10 +85,17 @@ __uc_state_checker(x, func, uses, used)
 uc_state_checkers(guc, guc);
 uc_state_checkers(huc, huc);
 uc_state_checkers(guc, guc_submission);
+uc_state_checkers(guc, guc_slpc);
+uc_state_checkers(guc, guc_rc);
 
 #undef uc_state_checkers
 #undef __uc_state_checker
 
+static inline int intel_uc_wait_for_idle(struct intel_uc *uc, long timeout)
+{
+	return intel_guc_wait_for_idle(&uc->guc, timeout);
+}
+
 #define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \
 static inline _TYPE intel_uc_##_NAME(struct intel_uc *uc) \
 { \
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index df647c9a8d56..3a16d08608a5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -48,19 +48,20 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * firmware as TGL.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ALDERLAKE_S, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl,  7, 5, 0)) \
-	fw_def(ROCKETLAKE,  0, guc_def(tgl, 49, 0, 1), huc_def(tgl,  7, 5, 0)) \
-	fw_def(TIGERLAKE,   0, guc_def(tgl, 49, 0, 1), huc_def(tgl,  7, 5, 0)) \
-	fw_def(JASPERLAKE,  0, guc_def(ehl, 49, 0, 1), huc_def(ehl,  9, 0, 0)) \
-	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl,  9, 0, 0)) \
-	fw_def(ICELAKE,     0, guc_def(icl, 49, 0, 1), huc_def(icl,  9, 0, 0)) \
-	fw_def(COMETLAKE,   5, guc_def(cml, 49, 0, 1), huc_def(cml,  4, 0, 0)) \
-	fw_def(COMETLAKE,   0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
-	fw_def(COFFEELAKE,  0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
-	fw_def(GEMINILAKE,  0, guc_def(glk, 49, 0, 1), huc_def(glk,  4, 0, 0)) \
-	fw_def(KABYLAKE,    0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
-	fw_def(BROXTON,     0, guc_def(bxt, 49, 0, 1), huc_def(bxt,  2, 0, 0)) \
-	fw_def(SKYLAKE,     0, guc_def(skl, 49, 0, 1), huc_def(skl,  2, 0, 0))
+	fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3), huc_def(tgl, 7, 9, 3)) \
+	fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl,  7, 9, 3)) \
+	fw_def(ROCKETLAKE,  0, guc_def(tgl, 62, 0, 0), huc_def(tgl,  7, 9, 3)) \
+	fw_def(TIGERLAKE,   0, guc_def(tgl, 62, 0, 0), huc_def(tgl,  7, 9, 3)) \
+	fw_def(JASPERLAKE,  0, guc_def(ehl, 62, 0, 0), huc_def(ehl,  9, 0, 0)) \
+	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl,  9, 0, 0)) \
+	fw_def(ICELAKE,     0, guc_def(icl, 62, 0, 0), huc_def(icl,  9, 0, 0)) \
+	fw_def(COMETLAKE,   5, guc_def(cml, 62, 0, 0), huc_def(cml,  4, 0, 0)) \
+	fw_def(COMETLAKE,   0, guc_def(kbl, 62, 0, 0), huc_def(kbl,  4, 0, 0)) \
+	fw_def(COFFEELAKE,  0, guc_def(kbl, 62, 0, 0), huc_def(kbl,  4, 0, 0)) \
+	fw_def(GEMINILAKE,  0, guc_def(glk, 62, 0, 0), huc_def(glk,  4, 0, 0)) \
+	fw_def(KABYLAKE,    0, guc_def(kbl, 62, 0, 0), huc_def(kbl,  4, 0, 0)) \
+	fw_def(BROXTON,     0, guc_def(bxt, 62, 0, 0), huc_def(bxt,  2, 0, 0)) \
+	fw_def(SKYLAKE,     0, guc_def(skl, 62, 0, 0), huc_def(skl,  2, 0, 0))
 
 #define __MAKE_UC_FW_PATH(prefix_, name_, major_, minor_, patch_) \
 	"i915/" \
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index cc2c05e18206..e5c2fdfc20e3 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1055,7 +1055,7 @@ static bool vgpu_ips_enabled(struct intel_vgpu *vgpu)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
 
-	if (GRAPHICS_VER(dev_priv) == 9 || GRAPHICS_VER(dev_priv) == 10) {
+	if (GRAPHICS_VER(dev_priv) == 9) {
 		u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) &
 			GAMW_ECO_ENABLE_64K_IPS_FIELD;
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 734c37c5e347..b56a8e37a3cd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1409,11 +1409,8 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 		intel_context_set_single_submission(ce);
 
 		/* Max ring buffer size */
-		if (!intel_uc_wants_guc_submission(&engine->gt->uc)) {
-			const unsigned int ring_size = 512 * SZ_4K;
-
-			ce->ring = __intel_context_ring_size(ring_size);
-		}
+		if (!intel_uc_wants_guc_submission(&engine->gt->uc))
+			ce->ring_size = SZ_2M;
 
 		s->shadow[i] = ce;
 	}
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index b1aa1c482c32..3103c1e1fd14 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -13,7 +13,6 @@
 
 #include "i915_drv.h"
 #include "i915_active.h"
-#include "i915_globals.h"
 
 /*
  * Active refs memory management
@@ -22,10 +21,7 @@
  * they idle (when we know the active requests are inactive) and allocate the
  * nodes from a local slab cache to hopefully reduce the fragmentation.
  */
-static struct i915_global_active {
-	struct i915_global base;
-	struct kmem_cache *slab_cache;
-} global;
+static struct kmem_cache *slab_cache;
 
 struct active_node {
 	struct rb_node node;
@@ -174,7 +170,7 @@ __active_retire(struct i915_active *ref)
 	/* Finally free the discarded timeline tree  */
 	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
 		GEM_BUG_ON(i915_active_fence_isset(&it->base));
-		kmem_cache_free(global.slab_cache, it);
+		kmem_cache_free(slab_cache, it);
 	}
 }
 
@@ -322,7 +318,7 @@ active_instance(struct i915_active *ref, u64 idx)
 	 * XXX: We should preallocate this before i915_active_ref() is ever
 	 *  called, but we cannot call into fs_reclaim() anyway, so use GFP_ATOMIC.
 	 */
-	node = kmem_cache_alloc(global.slab_cache, GFP_ATOMIC);
+	node = kmem_cache_alloc(slab_cache, GFP_ATOMIC);
 	if (!node)
 		goto out;
 
@@ -788,7 +784,7 @@ void i915_active_fini(struct i915_active *ref)
 	mutex_destroy(&ref->mutex);
 
 	if (ref->cache)
-		kmem_cache_free(global.slab_cache, ref->cache);
+		kmem_cache_free(slab_cache, ref->cache);
 }
 
 static inline bool is_idle_barrier(struct active_node *node, u64 idx)
@@ -908,7 +904,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 		node = reuse_idle_barrier(ref, idx);
 		rcu_read_unlock();
 		if (!node) {
-			node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
+			node = kmem_cache_alloc(slab_cache, GFP_KERNEL);
 			if (!node)
 				goto unwind;
 
@@ -956,7 +952,7 @@ unwind:
 		atomic_dec(&ref->count);
 		intel_engine_pm_put(barrier_to_engine(node));
 
-		kmem_cache_free(global.slab_cache, node);
+		kmem_cache_free(slab_cache, node);
 	}
 	return -ENOMEM;
 }
@@ -1176,27 +1172,16 @@ struct i915_active *i915_active_create(void)
 #include "selftests/i915_active.c"
 #endif
 
-static void i915_global_active_shrink(void)
+void i915_active_module_exit(void)
 {
-	kmem_cache_shrink(global.slab_cache);
+	kmem_cache_destroy(slab_cache);
 }
 
-static void i915_global_active_exit(void)
+int __init i915_active_module_init(void)
 {
-	kmem_cache_destroy(global.slab_cache);
-}
-
-static struct i915_global_active global = { {
-	.shrink = i915_global_active_shrink,
-	.exit = i915_global_active_exit,
-} };
-
-int __init i915_global_active_init(void)
-{
-	global.slab_cache = KMEM_CACHE(active_node, SLAB_HWCACHE_ALIGN);
-	if (!global.slab_cache)
+	slab_cache = KMEM_CACHE(active_node, SLAB_HWCACHE_ALIGN);
+	if (!slab_cache)
 		return -ENOMEM;
 
-	i915_global_register(&global.base);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index d0feda68b874..5fcdb0e2bc9e 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -247,4 +247,7 @@ static inline int __i915_request_await_exclusive(struct i915_request *rq,
 	return err;
 }
 
+void i915_active_module_exit(void);
+int i915_active_module_init(void);
+
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
new file mode 100644
index 000000000000..7b274c51cac0
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kmemleak.h>
+
+#include "i915_buddy.h"
+
+#include "i915_gem.h"
+#include "i915_utils.h"
+
+static struct kmem_cache *slab_blocks;
+
+static struct i915_buddy_block *i915_block_alloc(struct i915_buddy_mm *mm,
+						 struct i915_buddy_block *parent,
+						 unsigned int order,
+						 u64 offset)
+{
+	struct i915_buddy_block *block;
+
+	GEM_BUG_ON(order > I915_BUDDY_MAX_ORDER);
+
+	block = kmem_cache_zalloc(slab_blocks, GFP_KERNEL);
+	if (!block)
+		return NULL;
+
+	block->header = offset;
+	block->header |= order;
+	block->parent = parent;
+
+	GEM_BUG_ON(block->header & I915_BUDDY_HEADER_UNUSED);
+	return block;
+}
+
+static void i915_block_free(struct i915_buddy_mm *mm,
+			    struct i915_buddy_block *block)
+{
+	kmem_cache_free(slab_blocks, block);
+}
+
+static void mark_allocated(struct i915_buddy_block *block)
+{
+	block->header &= ~I915_BUDDY_HEADER_STATE;
+	block->header |= I915_BUDDY_ALLOCATED;
+
+	list_del(&block->link);
+}
+
+static void mark_free(struct i915_buddy_mm *mm,
+		      struct i915_buddy_block *block)
+{
+	block->header &= ~I915_BUDDY_HEADER_STATE;
+	block->header |= I915_BUDDY_FREE;
+
+	list_add(&block->link,
+		 &mm->free_list[i915_buddy_block_order(block)]);
+}
+
+static void mark_split(struct i915_buddy_block *block)
+{
+	block->header &= ~I915_BUDDY_HEADER_STATE;
+	block->header |= I915_BUDDY_SPLIT;
+
+	list_del(&block->link);
+}
+
+int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size)
+{
+	unsigned int i;
+	u64 offset;
+
+	if (size < chunk_size)
+		return -EINVAL;
+
+	if (chunk_size < PAGE_SIZE)
+		return -EINVAL;
+
+	if (!is_power_of_2(chunk_size))
+		return -EINVAL;
+
+	size = round_down(size, chunk_size);
+
+	mm->size = size;
+	mm->chunk_size = chunk_size;
+	mm->max_order = ilog2(size) - ilog2(chunk_size);
+
+	GEM_BUG_ON(mm->max_order > I915_BUDDY_MAX_ORDER);
+
+	mm->free_list = kmalloc_array(mm->max_order + 1,
+				      sizeof(struct list_head),
+				      GFP_KERNEL);
+	if (!mm->free_list)
+		return -ENOMEM;
+
+	for (i = 0; i <= mm->max_order; ++i)
+		INIT_LIST_HEAD(&mm->free_list[i]);
+
+	mm->n_roots = hweight64(size);
+
+	mm->roots = kmalloc_array(mm->n_roots,
+				  sizeof(struct i915_buddy_block *),
+				  GFP_KERNEL);
+	if (!mm->roots)
+		goto out_free_list;
+
+	offset = 0;
+	i = 0;
+
+	/*
+	 * Split into power-of-two blocks, in case we are given a size that is
+	 * not itself a power-of-two.
+	 */
+	do {
+		struct i915_buddy_block *root;
+		unsigned int order;
+		u64 root_size;
+
+		root_size = rounddown_pow_of_two(size);
+		order = ilog2(root_size) - ilog2(chunk_size);
+
+		root = i915_block_alloc(mm, NULL, order, offset);
+		if (!root)
+			goto out_free_roots;
+
+		mark_free(mm, root);
+
+		GEM_BUG_ON(i > mm->max_order);
+		GEM_BUG_ON(i915_buddy_block_size(mm, root) < chunk_size);
+
+		mm->roots[i] = root;
+
+		offset += root_size;
+		size -= root_size;
+		i++;
+	} while (size);
+
+	return 0;
+
+out_free_roots:
+	while (i--)
+		i915_block_free(mm, mm->roots[i]);
+	kfree(mm->roots);
+out_free_list:
+	kfree(mm->free_list);
+	return -ENOMEM;
+}
+
+void i915_buddy_fini(struct i915_buddy_mm *mm)
+{
+	int i;
+
+	for (i = 0; i < mm->n_roots; ++i) {
+		GEM_WARN_ON(!i915_buddy_block_is_free(mm->roots[i]));
+		i915_block_free(mm, mm->roots[i]);
+	}
+
+	kfree(mm->roots);
+	kfree(mm->free_list);
+}
+
+static int split_block(struct i915_buddy_mm *mm,
+		       struct i915_buddy_block *block)
+{
+	unsigned int block_order = i915_buddy_block_order(block) - 1;
+	u64 offset = i915_buddy_block_offset(block);
+
+	GEM_BUG_ON(!i915_buddy_block_is_free(block));
+	GEM_BUG_ON(!i915_buddy_block_order(block));
+
+	block->left = i915_block_alloc(mm, block, block_order, offset);
+	if (!block->left)
+		return -ENOMEM;
+
+	block->right = i915_block_alloc(mm, block, block_order,
+					offset + (mm->chunk_size << block_order));
+	if (!block->right) {
+		i915_block_free(mm, block->left);
+		return -ENOMEM;
+	}
+
+	mark_free(mm, block->left);
+	mark_free(mm, block->right);
+
+	mark_split(block);
+
+	return 0;
+}
+
+static struct i915_buddy_block *
+get_buddy(struct i915_buddy_block *block)
+{
+	struct i915_buddy_block *parent;
+
+	parent = block->parent;
+	if (!parent)
+		return NULL;
+
+	if (parent->left == block)
+		return parent->right;
+
+	return parent->left;
+}
+
+static void __i915_buddy_free(struct i915_buddy_mm *mm,
+			      struct i915_buddy_block *block)
+{
+	struct i915_buddy_block *parent;
+
+	while ((parent = block->parent)) {
+		struct i915_buddy_block *buddy;
+
+		buddy = get_buddy(block);
+
+		if (!i915_buddy_block_is_free(buddy))
+			break;
+
+		list_del(&buddy->link);
+
+		i915_block_free(mm, block);
+		i915_block_free(mm, buddy);
+
+		block = parent;
+	}
+
+	mark_free(mm, block);
+}
+
+void i915_buddy_free(struct i915_buddy_mm *mm,
+		     struct i915_buddy_block *block)
+{
+	GEM_BUG_ON(!i915_buddy_block_is_allocated(block));
+	__i915_buddy_free(mm, block);
+}
+
+void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects)
+{
+	struct i915_buddy_block *block, *on;
+
+	list_for_each_entry_safe(block, on, objects, link) {
+		i915_buddy_free(mm, block);
+		cond_resched();
+	}
+	INIT_LIST_HEAD(objects);
+}
+
+/*
+ * Allocate power-of-two block. The order value here translates to:
+ *
+ *   0 = 2^0 * mm->chunk_size
+ *   1 = 2^1 * mm->chunk_size
+ *   2 = 2^2 * mm->chunk_size
+ *   ...
+ */
+struct i915_buddy_block *
+i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order)
+{
+	struct i915_buddy_block *block = NULL;
+	unsigned int i;
+	int err;
+
+	for (i = order; i <= mm->max_order; ++i) {
+		block = list_first_entry_or_null(&mm->free_list[i],
+						 struct i915_buddy_block,
+						 link);
+		if (block)
+			break;
+	}
+
+	if (!block)
+		return ERR_PTR(-ENOSPC);
+
+	GEM_BUG_ON(!i915_buddy_block_is_free(block));
+
+	while (i != order) {
+		err = split_block(mm, block);
+		if (unlikely(err))
+			goto out_free;
+
+		/* Go low */
+		block = block->left;
+		i--;
+	}
+
+	mark_allocated(block);
+	kmemleak_update_trace(block);
+	return block;
+
+out_free:
+	if (i != order)
+		__i915_buddy_free(mm, block);
+	return ERR_PTR(err);
+}
+
+static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
+{
+	return s1 <= e2 && e1 >= s2;
+}
+
+static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
+{
+	return s1 <= s2 && e1 >= e2;
+}
+
+/*
+ * Allocate range. Note that it's safe to chain together multiple alloc_ranges
+ * with the same blocks list.
+ *
+ * Intended for pre-allocating portions of the address space, for example to
+ * reserve a block for the initial framebuffer or similar, hence the expectation
+ * here is that i915_buddy_alloc() is still the main vehicle for
+ * allocations, so if that's not the case then the drm_mm range allocator is
+ * probably a much better fit, and so you should probably go use that instead.
+ */
+int i915_buddy_alloc_range(struct i915_buddy_mm *mm,
+			   struct list_head *blocks,
+			   u64 start, u64 size)
+{
+	struct i915_buddy_block *block;
+	struct i915_buddy_block *buddy;
+	LIST_HEAD(allocated);
+	LIST_HEAD(dfs);
+	u64 end;
+	int err;
+	int i;
+
+	if (size < mm->chunk_size)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(size | start, mm->chunk_size))
+		return -EINVAL;
+
+	if (range_overflows(start, size, mm->size))
+		return -EINVAL;
+
+	for (i = 0; i < mm->n_roots; ++i)
+		list_add_tail(&mm->roots[i]->tmp_link, &dfs);
+
+	end = start + size - 1;
+
+	do {
+		u64 block_start;
+		u64 block_end;
+
+		block = list_first_entry_or_null(&dfs,
+						 struct i915_buddy_block,
+						 tmp_link);
+		if (!block)
+			break;
+
+		list_del(&block->tmp_link);
+
+		block_start = i915_buddy_block_offset(block);
+		block_end = block_start + i915_buddy_block_size(mm, block) - 1;
+
+		if (!overlaps(start, end, block_start, block_end))
+			continue;
+
+		if (i915_buddy_block_is_allocated(block)) {
+			err = -ENOSPC;
+			goto err_free;
+		}
+
+		if (contains(start, end, block_start, block_end)) {
+			if (!i915_buddy_block_is_free(block)) {
+				err = -ENOSPC;
+				goto err_free;
+			}
+
+			mark_allocated(block);
+			list_add_tail(&block->link, &allocated);
+			continue;
+		}
+
+		if (!i915_buddy_block_is_split(block)) {
+			err = split_block(mm, block);
+			if (unlikely(err))
+				goto err_undo;
+		}
+
+		list_add(&block->right->tmp_link, &dfs);
+		list_add(&block->left->tmp_link, &dfs);
+	} while (1);
+
+	list_splice_tail(&allocated, blocks);
+	return 0;
+
+err_undo:
+	/*
+	 * We really don't want to leave around a bunch of split blocks, since
+	 * bigger is better, so make sure we merge everything back before we
+	 * free the allocated blocks.
+	 */
+	buddy = get_buddy(block);
+	if (buddy &&
+	    (i915_buddy_block_is_free(block) &&
+	     i915_buddy_block_is_free(buddy)))
+		__i915_buddy_free(mm, block);
+
+err_free:
+	i915_buddy_free_list(mm, &allocated);
+	return err;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_buddy.c"
+#endif
+
+void i915_buddy_module_exit(void)
+{
+	kmem_cache_destroy(slab_blocks);
+}
+
+int __init i915_buddy_module_init(void)
+{
+	slab_blocks = KMEM_CACHE(i915_buddy_block, 0);
+	if (!slab_blocks)
+		return -ENOMEM;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_buddy.h b/drivers/gpu/drm/i915/i915_buddy.h
new file mode 100644
index 000000000000..3940d632f208
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_buddy.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_BUDDY_H__
+#define __I915_BUDDY_H__
+
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+struct i915_buddy_block {
+#define I915_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
+#define I915_BUDDY_HEADER_STATE  GENMASK_ULL(11, 10)
+#define   I915_BUDDY_ALLOCATED	   (1 << 10)
+#define   I915_BUDDY_FREE	   (2 << 10)
+#define   I915_BUDDY_SPLIT	   (3 << 10)
+/* Free to be used, if needed in the future */
+#define I915_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6)
+#define I915_BUDDY_HEADER_ORDER  GENMASK_ULL(5, 0)
+	u64 header;
+
+	struct i915_buddy_block *left;
+	struct i915_buddy_block *right;
+	struct i915_buddy_block *parent;
+
+	void *private; /* owned by creator */
+
+	/*
+	 * While the block is allocated by the user through i915_buddy_alloc*,
+	 * the user has ownership of the link, for example to maintain within
+	 * a list, if so desired. As soon as the block is freed with
+	 * i915_buddy_free* ownership is given back to the mm.
+	 */
+	struct list_head link;
+	struct list_head tmp_link;
+};
+
+/* Order-zero must be at least PAGE_SIZE */
+#define I915_BUDDY_MAX_ORDER (63 - PAGE_SHIFT)
+
+/*
+ * Binary Buddy System.
+ *
+ * Locking should be handled by the user, a simple mutex around
+ * i915_buddy_alloc* and i915_buddy_free* should suffice.
+ */
+struct i915_buddy_mm {
+	/* Maintain a free list for each order. */
+	struct list_head *free_list;
+
+	/*
+	 * Maintain explicit binary tree(s) to track the allocation of the
+	 * address space. This gives us a simple way of finding a buddy block
+	 * and performing the potentially recursive merge step when freeing a
+	 * block.  Nodes are either allocated or free, in which case they will
+	 * also exist on the respective free list.
+	 */
+	struct i915_buddy_block **roots;
+
+	/*
+	 * Anything from here is public, and remains static for the lifetime of
+	 * the mm. Everything above is considered do-not-touch.
+	 */
+	unsigned int n_roots;
+	unsigned int max_order;
+
+	/* Must be at least PAGE_SIZE */
+	u64 chunk_size;
+	u64 size;
+};
+
+static inline u64
+i915_buddy_block_offset(struct i915_buddy_block *block)
+{
+	return block->header & I915_BUDDY_HEADER_OFFSET;
+}
+
+static inline unsigned int
+i915_buddy_block_order(struct i915_buddy_block *block)
+{
+	return block->header & I915_BUDDY_HEADER_ORDER;
+}
+
+static inline unsigned int
+i915_buddy_block_state(struct i915_buddy_block *block)
+{
+	return block->header & I915_BUDDY_HEADER_STATE;
+}
+
+static inline bool
+i915_buddy_block_is_allocated(struct i915_buddy_block *block)
+{
+	return i915_buddy_block_state(block) == I915_BUDDY_ALLOCATED;
+}
+
+static inline bool
+i915_buddy_block_is_free(struct i915_buddy_block *block)
+{
+	return i915_buddy_block_state(block) == I915_BUDDY_FREE;
+}
+
+static inline bool
+i915_buddy_block_is_split(struct i915_buddy_block *block)
+{
+	return i915_buddy_block_state(block) == I915_BUDDY_SPLIT;
+}
+
+static inline u64
+i915_buddy_block_size(struct i915_buddy_mm *mm,
+		      struct i915_buddy_block *block)
+{
+	return mm->chunk_size << i915_buddy_block_order(block);
+}
+
+int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size);
+
+void i915_buddy_fini(struct i915_buddy_mm *mm);
+
+struct i915_buddy_block *
+i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order);
+
+int i915_buddy_alloc_range(struct i915_buddy_mm *mm,
+			   struct list_head *blocks,
+			   u64 start, u64 size);
+
+void i915_buddy_free(struct i915_buddy_mm *mm, struct i915_buddy_block *block);
+
+void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects);
+
+void i915_buddy_module_exit(void);
+int i915_buddy_module_init(void);
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index a3b4d99d64b9..e0403ce9ce69 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1468,42 +1468,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 	 * space. Parsing should be faster in some cases this way.
 	 */
 	batch_end = cmd + batch_length / sizeof(*batch_end);
-	while (*cmd != MI_BATCH_BUFFER_END) {
-		u32 length = 1;
-
-		if (*cmd != MI_NOOP) { /* MI_NOOP == 0 */
-			desc = find_cmd(engine, *cmd, desc, &default_desc);
-			if (!desc) {
-				DRM_DEBUG("CMD: Unrecognized command: 0x%08X\n", *cmd);
-				ret = -EINVAL;
-				break;
-			}
+	do {
+		u32 length;
 
-			if (desc->flags & CMD_DESC_FIXED)
-				length = desc->length.fixed;
-			else
-				length = (*cmd & desc->length.mask) + LENGTH_BIAS;
+		if (*cmd == MI_BATCH_BUFFER_END)
+			break;
 
-			if ((batch_end - cmd) < length) {
-				DRM_DEBUG("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
-					  *cmd,
-					  length,
-					  batch_end - cmd);
-				ret = -EINVAL;
-				break;
-			}
+		desc = find_cmd(engine, *cmd, desc, &default_desc);
+		if (!desc) {
+			DRM_DEBUG("CMD: Unrecognized command: 0x%08X\n", *cmd);
+			ret = -EINVAL;
+			break;
+		}
 
-			if (!check_cmd(engine, desc, cmd, length)) {
-				ret = -EACCES;
-				break;
-			}
+		if (desc->flags & CMD_DESC_FIXED)
+			length = desc->length.fixed;
+		else
+			length = (*cmd & desc->length.mask) + LENGTH_BIAS;
 
-			if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
-				ret = check_bbstart(cmd, offset, length, batch_length,
-						    batch_addr, shadow_addr,
-						    jump_whitelist);
-				break;
-			}
+		if ((batch_end - cmd) < length) {
+			DRM_DEBUG("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
+				  *cmd,
+				  length,
+				  batch_end - cmd);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (!check_cmd(engine, desc, cmd, length)) {
+			ret = -EACCES;
+			break;
+		}
+
+		if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
+			ret = check_bbstart(cmd, offset, length, batch_length,
+					    batch_addr, shadow_addr,
+					    jump_whitelist);
+			break;
 		}
 
 		if (!IS_ERR_OR_NULL(jump_whitelist))
@@ -1516,7 +1517,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			ret = -EINVAL;
 			break;
 		}
-	}
+	} while (1);
 
 	if (trampoline) {
 		/*
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index cc745751ac53..44969f5dde50 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -538,20 +538,20 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (rp_state_cap & 0xff00) >> 8;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 16 :
 			    rp_state_cap >> 0) & 0xff;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
+			     GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   intel_gpu_freq(rps, max_freq));
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
@@ -636,7 +636,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 			   intel_uncore_read16(uncore, C0DRB3_BW));
 		seq_printf(m, "C1DRB3 = 0x%04x\n",
 			   intel_uncore_read16(uncore, C1DRB3_BW));
-	} else if (INTEL_GEN(dev_priv) >= 6) {
+	} else if (GRAPHICS_VER(dev_priv) >= 6) {
 		seq_printf(m, "MAD_DIMM_C0 = 0x%08x\n",
 			   intel_uncore_read(uncore, MAD_DIMM_C0));
 		seq_printf(m, "MAD_DIMM_C1 = 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/i915_debugfs_params.c b/drivers/gpu/drm/i915/i915_debugfs_params.c
index 4e2b077692cb..20424275d41e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs_params.c
+++ b/drivers/gpu/drm/i915/i915_debugfs_params.c
@@ -6,9 +6,21 @@
 #include <linux/kernel.h>
 
 #include "i915_debugfs_params.h"
+#include "gt/intel_gt.h"
+#include "gt/uc/intel_guc.h"
 #include "i915_drv.h"
 #include "i915_params.h"
 
+#define MATCH_DEBUGFS_NODE_NAME(_file, _name) \
+	(strcmp((_file)->f_path.dentry->d_name.name, (_name)) == 0)
+
+#define GET_I915(i915, name, ptr)	\
+	do {	\
+		struct i915_params *params;	\
+		params = container_of(((void *)(ptr)), typeof(*params), name);	\
+		(i915) = container_of(params, typeof(*(i915)), params);	\
+	} while (0)
+
 /* int param */
 static int i915_param_int_show(struct seq_file *m, void *data)
 {
@@ -24,6 +36,16 @@ static int i915_param_int_open(struct inode *inode, struct file *file)
 	return single_open(file, i915_param_int_show, inode->i_private);
 }
 
+static int notify_guc(struct drm_i915_private *i915)
+{
+	int ret = 0;
+
+	if (intel_uc_uses_guc_submission(&i915->gt.uc))
+		ret = intel_guc_global_policies_update(&i915->gt.uc.guc);
+
+	return ret;
+}
+
 static ssize_t i915_param_int_write(struct file *file,
 				    const char __user *ubuf, size_t len,
 				    loff_t *offp)
@@ -81,8 +103,10 @@ static ssize_t i915_param_uint_write(struct file *file,
 				     const char __user *ubuf, size_t len,
 				     loff_t *offp)
 {
+	struct drm_i915_private *i915;
 	struct seq_file *m = file->private_data;
 	unsigned int *value = m->private;
+	unsigned int old = *value;
 	int ret;
 
 	ret = kstrtouint_from_user(ubuf, len, 0, value);
@@ -95,6 +119,14 @@ static ssize_t i915_param_uint_write(struct file *file,
 			*value = b;
 	}
 
+	if (!ret && MATCH_DEBUGFS_NODE_NAME(file, "reset")) {
+		GET_I915(i915, reset, value);
+
+		ret = notify_guc(i915);
+		if (ret)
+			*value = old;
+	}
+
 	return ret ?: len;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 73de45472f60..59fb4c710c8c 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -271,10 +271,11 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv)
 	bool pre = false;
 
 	pre |= IS_HSW_EARLY_SDV(dev_priv);
-	pre |= IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0);
-	pre |= IS_BXT_REVID(dev_priv, 0, BXT_REVID_B_LAST);
-	pre |= IS_KBL_GT_STEP(dev_priv, 0, STEP_A0);
-	pre |= IS_GLK_REVID(dev_priv, 0, GLK_REVID_A2);
+	pre |= IS_SKYLAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x6;
+	pre |= IS_BROXTON(dev_priv) && INTEL_REVID(dev_priv) < 0xA;
+	pre |= IS_KABYLAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x1;
+	pre |= IS_GEMINILAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x3;
+	pre |= IS_ICELAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x7;
 
 	if (pre) {
 		drm_err(&dev_priv->drm, "This is a pre-production stepping. "
@@ -561,7 +562,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_perf;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "inteldrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, dev_priv->drm.driver);
 	if (ret)
 		goto err_ggtt;
 
@@ -619,7 +620,9 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 
 	intel_opregion_setup(dev_priv);
 
-	intel_pcode_init(dev_priv);
+	ret = intel_pcode_init(dev_priv);
+	if (ret)
+		goto err_msi;
 
 	/*
 	 * Fill the dram structure to get the system dram info. This will be
@@ -1230,6 +1233,10 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
+	ret = intel_pcode_init(dev_priv);
+	if (ret)
+		return ret;
+
 	sanitize_gpu(dev_priv);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b30397b04529..005b1cec7007 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -202,6 +202,68 @@ struct drm_i915_file_private {
 		struct rcu_head rcu;
 	};
 
+	/** @proto_context_lock: Guards all struct i915_gem_proto_context
+	 * operations
+	 *
+	 * This not only guards @proto_context_xa, but is always held
+	 * whenever we manipulate any struct i915_gem_proto_context,
+	 * including finalizing it on first actual use of the GEM context.
+	 *
+	 * See i915_gem_proto_context.
+	 */
+	struct mutex proto_context_lock;
+
+	/** @proto_context_xa: xarray of struct i915_gem_proto_context
+	 *
+	 * Historically, the context uAPI allowed for two methods of
+	 * setting context parameters: SET_CONTEXT_PARAM and
+	 * CONTEXT_CREATE_EXT_SETPARAM.  The former is allowed to be called
+	 * at any time while the later happens as part of
+	 * GEM_CONTEXT_CREATE.  Everything settable via one was settable
+	 * via the other.  While some params are fairly simple and setting
+	 * them on a live context is harmless such as the context priority,
+	 * others are far trickier such as the VM or the set of engines.
+	 * In order to swap out the VM, for instance, we have to delay
+	 * until all current in-flight work is complete, swap in the new
+	 * VM, and then continue.  This leads to a plethora of potential
+	 * race conditions we'd really rather avoid.
+	 *
+	 * We have since disallowed setting these more complex parameters
+	 * on active contexts.  This works by delaying the creation of the
+	 * actual context until after the client is done configuring it
+	 * with SET_CONTEXT_PARAM.  From the perspective of the client, it
+	 * has the same u32 context ID the whole time.  From the
+	 * perspective of i915, however, it's a struct i915_gem_proto_context
+	 * right up until the point where we attempt to do something which
+	 * the proto-context can't handle.  Then the struct i915_gem_context
+	 * gets created.
+	 *
+	 * This is accomplished via a little xarray dance.  When
+	 * GEM_CONTEXT_CREATE is called, we create a struct
+	 * i915_gem_proto_context, reserve a slot in @context_xa but leave
+	 * it NULL, and place the proto-context in the corresponding slot
+	 * in @proto_context_xa.  Then, in i915_gem_context_lookup(), we
+	 * first check @context_xa.  If it's there, we return the struct
+	 * i915_gem_context and we're done.  If it's not, we look in
+	 * @proto_context_xa and, if we find it there, we create the actual
+	 * context and kill the proto-context.
+	 *
+	 * In order for this dance to work properly, everything which ever
+	 * touches a struct i915_gem_proto_context is guarded by
+	 * @proto_context_lock, including context creation.  Yes, this
+	 * means context creation now takes a giant global lock but it
+	 * can't really be helped and that should never be on any driver's
+	 * fast-path anyway.
+	 */
+	struct xarray proto_context_xa;
+
+	/** @context_xa: xarray of fully created i915_gem_context
+	 *
+	 * Write access to this xarray is guarded by @proto_context_lock.
+	 * Otherwise, writers may race with finalize_create_context_locked().
+	 *
+	 * See @proto_context_xa.
+	 */
 	struct xarray context_xa;
 	struct xarray vm_xa;
 
@@ -270,8 +332,10 @@ struct drm_i915_display_funcs {
 	int (*bw_calc_min_cdclk)(struct intel_atomic_state *state);
 	int (*get_fifo_size)(struct drm_i915_private *dev_priv,
 			     enum i9xx_plane_id i9xx_plane);
-	int (*compute_pipe_wm)(struct intel_crtc_state *crtc_state);
-	int (*compute_intermediate_wm)(struct intel_crtc_state *crtc_state);
+	int (*compute_pipe_wm)(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc);
+	int (*compute_intermediate_wm)(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc);
 	void (*initial_watermarks)(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc);
 	void (*atomic_update_watermarks)(struct intel_atomic_state *state,
@@ -330,15 +394,6 @@ struct drm_i915_display_funcs {
 	void (*read_luts)(struct intel_crtc_state *crtc_state);
 };
 
-enum i915_cache_level {
-	I915_CACHE_NONE = 0,
-	I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */
-	I915_CACHE_L3_LLC, /* gen7+, L3 sits between the domain specifc
-			      caches, eg sampler/render caches, and the
-			      large Last-Level-Cache. LLC is coherent with
-			      the CPU, but L3 is only visible to the GPU. */
-	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
-};
 
 #define I915_COLOR_UNEVICTABLE (-1) /* a non-vma sharing the address space */
 
@@ -346,13 +401,14 @@ struct intel_fbc {
 	/* This is always the inner lock when overlapping with struct_mutex and
 	 * it's the outer lock when overlapping with stolen_lock. */
 	struct mutex lock;
-	unsigned threshold;
 	unsigned int possible_framebuffer_bits;
 	unsigned int busy_bits;
 	struct intel_crtc *crtc;
 
 	struct drm_mm_node compressed_fb;
-	struct drm_mm_node *compressed_llb;
+	struct drm_mm_node compressed_llb;
+
+	u8 limit;
 
 	bool false_color;
 
@@ -467,6 +523,7 @@ struct i915_drrs {
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
 #define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
+#define QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK (1<<8)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -552,7 +609,7 @@ struct i915_gem_mm {
 	 * notifier_lock for mmu notifiers, memory may not be allocated
 	 * while holding this lock.
 	 */
-	spinlock_t notifier_lock;
+	rwlock_t notifier_lock;
 #endif
 
 	/* shrinker accounting, also useful for userland debugging */
@@ -576,6 +633,9 @@ i915_fence_timeout(const struct drm_i915_private *i915)
 
 #define HAS_HW_SAGV_WM(i915) (DISPLAY_VER(i915) >= 13 && !IS_DGFX(i915))
 
+/* Amount of PSF GV points, BSpec precisely defines this */
+#define I915_NUM_PSF_GV_POINTS 3
+
 struct ddi_vbt_port_info {
 	/* Non-NULL if port present. */
 	struct intel_bios_encoder_data *devdata;
@@ -1089,12 +1149,16 @@ struct drm_i915_private {
 			INTEL_DRAM_LPDDR5,
 		} type;
 		u8 num_qgv_points;
+		u8 num_psf_gv_points;
 	} dram_info;
 
 	struct intel_bw_info {
 		/* for each QGV point */
 		unsigned int deratedbw[I915_NUM_QGV_POINTS];
+		/* for each PSF GV point */
+		unsigned int psf_bw[I915_NUM_PSF_GV_POINTS];
 		u8 num_qgv_points;
+		u8 num_psf_gv_points;
 		u8 num_planes;
 	} max_bw[6];
 
@@ -1134,6 +1198,8 @@ struct drm_i915_private {
 	/* For i915gm/i945gm vblank irq workaround */
 	u8 vblank_enabled;
 
+	bool irq_enabled;
+
 	/* perform PHY state sanity checks? */
 	bool chv_phy_assert[2];
 
@@ -1237,26 +1303,17 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 
 #define INTEL_DEVID(dev_priv)	(RUNTIME_INFO(dev_priv)->device_id)
 
-/*
- * Deprecated: this will be replaced by individual IP checks:
- * GRAPHICS_VER(), MEDIA_VER() and DISPLAY_VER()
- */
-#define INTEL_GEN(dev_priv)		GRAPHICS_VER(dev_priv)
-/*
- * Deprecated: use IS_GRAPHICS_VER(), IS_MEDIA_VER() and IS_DISPLAY_VER() as
- * appropriate.
- */
-#define IS_GEN_RANGE(dev_priv, s, e)	IS_GRAPHICS_VER(dev_priv, (s), (e))
-/*
- * Deprecated: use GRAPHICS_VER(), MEDIA_VER() and DISPLAY_VER() as appropriate.
- */
-#define IS_GEN(dev_priv, n)		(GRAPHICS_VER(dev_priv) == (n))
+#define IP_VER(ver, rel)		((ver) << 8 | (rel))
 
 #define GRAPHICS_VER(i915)		(INTEL_INFO(i915)->graphics_ver)
+#define GRAPHICS_VER_FULL(i915)		IP_VER(INTEL_INFO(i915)->graphics_ver, \
+					       INTEL_INFO(i915)->graphics_rel)
 #define IS_GRAPHICS_VER(i915, from, until) \
 	(GRAPHICS_VER(i915) >= (from) && GRAPHICS_VER(i915) <= (until))
 
 #define MEDIA_VER(i915)			(INTEL_INFO(i915)->media_ver)
+#define MEDIA_VER_FULL(i915)		IP_VER(INTEL_INFO(i915)->media_ver, \
+					       INTEL_INFO(i915)->media_rel)
 #define IS_MEDIA_VER(i915, from, until) \
 	(MEDIA_VER(i915) >= (from) && MEDIA_VER(i915) <= (until))
 
@@ -1264,29 +1321,20 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 #define IS_DISPLAY_VER(i915, from, until) \
 	(DISPLAY_VER(i915) >= (from) && DISPLAY_VER(i915) <= (until))
 
-#define REVID_FOREVER		0xff
 #define INTEL_REVID(dev_priv)	(to_pci_dev((dev_priv)->drm.dev)->revision)
 
 #define HAS_DSB(dev_priv)	(INTEL_INFO(dev_priv)->display.has_dsb)
 
-/*
- * Return true if revision is in range [since,until] inclusive.
- *
- * Use 0 for open-ended since, and REVID_FOREVER for open-ended until.
- */
-#define IS_REVID(p, since, until) \
-	(INTEL_REVID(p) >= (since) && INTEL_REVID(p) <= (until))
-
 #define INTEL_DISPLAY_STEP(__i915) (RUNTIME_INFO(__i915)->step.display_step)
 #define INTEL_GT_STEP(__i915) (RUNTIME_INFO(__i915)->step.gt_step)
 
 #define IS_DISPLAY_STEP(__i915, since, until) \
 	(drm_WARN_ON(&(__i915)->drm, INTEL_DISPLAY_STEP(__i915) == STEP_NONE), \
-	 INTEL_DISPLAY_STEP(__i915) >= (since) && INTEL_DISPLAY_STEP(__i915) <= (until))
+	 INTEL_DISPLAY_STEP(__i915) >= (since) && INTEL_DISPLAY_STEP(__i915) < (until))
 
 #define IS_GT_STEP(__i915, since, until) \
 	(drm_WARN_ON(&(__i915)->drm, INTEL_GT_STEP(__i915) == STEP_NONE), \
-	 INTEL_GT_STEP(__i915) >= (since) && INTEL_GT_STEP(__i915) <= (until))
+	 INTEL_GT_STEP(__i915) >= (since) && INTEL_GT_STEP(__i915) < (until))
 
 static __always_inline unsigned int
 __platform_mask_index(const struct intel_runtime_info *info,
@@ -1385,7 +1433,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_GEMINILAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_GEMINILAKE)
 #define IS_COFFEELAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_COFFEELAKE)
 #define IS_COMETLAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_COMETLAKE)
-#define IS_CANNONLAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_CANNONLAKE)
+#define IS_CANNONLAKE(dev_priv)	0
 #define IS_ICELAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_ICELAKE)
 #define IS_JSL_EHL(dev_priv)	(IS_PLATFORM(dev_priv, INTEL_JASPERLAKE) || \
 				IS_PLATFORM(dev_priv, INTEL_ELKHARTLAKE))
@@ -1394,6 +1442,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_DG1(dev_priv)        IS_PLATFORM(dev_priv, INTEL_DG1)
 #define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, INTEL_ALDERLAKE_S)
 #define IS_ALDERLAKE_P(dev_priv) IS_PLATFORM(dev_priv, INTEL_ALDERLAKE_P)
+#define IS_XEHPSDV(dev_priv) IS_PLATFORM(dev_priv, INTEL_XEHPSDV)
+#define IS_DG2(dev_priv)	IS_PLATFORM(dev_priv, INTEL_DG2)
+#define IS_DG2_G10(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_DG2, INTEL_SUBPLATFORM_G10)
+#define IS_DG2_G11(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_DG2, INTEL_SUBPLATFORM_G11)
 #define IS_HSW_EARLY_SDV(dev_priv) (IS_HASWELL(dev_priv) && \
 				    (INTEL_DEVID(dev_priv) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev_priv) \
@@ -1445,8 +1499,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_CML_GT2(dev_priv)	(IS_COMETLAKE(dev_priv) && \
 				 INTEL_INFO(dev_priv)->gt == 2)
 
-#define IS_CNL_WITH_PORT_F(dev_priv) \
-	IS_SUBPLATFORM(dev_priv, INTEL_CANNONLAKE, INTEL_SUBPLATFORM_PORTF)
 #define IS_ICL_WITH_PORT_F(dev_priv) \
 	IS_SUBPLATFORM(dev_priv, INTEL_ICELAKE, INTEL_SUBPLATFORM_PORTF)
 
@@ -1456,60 +1508,17 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_TGL_Y(dev_priv) \
 	IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULX)
 
-#define SKL_REVID_A0		0x0
-#define SKL_REVID_B0		0x1
-#define SKL_REVID_C0		0x2
-#define SKL_REVID_D0		0x3
-#define SKL_REVID_E0		0x4
-#define SKL_REVID_F0		0x5
-#define SKL_REVID_G0		0x6
-#define SKL_REVID_H0		0x7
-
-#define IS_SKL_REVID(p, since, until) (IS_SKYLAKE(p) && IS_REVID(p, since, until))
-
-#define BXT_REVID_A0		0x0
-#define BXT_REVID_A1		0x1
-#define BXT_REVID_B0		0x3
-#define BXT_REVID_B_LAST	0x8
-#define BXT_REVID_C0		0x9
-
-#define IS_BXT_REVID(dev_priv, since, until) \
-	(IS_BROXTON(dev_priv) && IS_REVID(dev_priv, since, until))
+#define IS_SKL_GT_STEP(p, since, until) (IS_SKYLAKE(p) && IS_GT_STEP(p, since, until))
 
 #define IS_KBL_GT_STEP(dev_priv, since, until) \
 	(IS_KABYLAKE(dev_priv) && IS_GT_STEP(dev_priv, since, until))
 #define IS_KBL_DISPLAY_STEP(dev_priv, since, until) \
 	(IS_KABYLAKE(dev_priv) && IS_DISPLAY_STEP(dev_priv, since, until))
 
-#define GLK_REVID_A0		0x0
-#define GLK_REVID_A1		0x1
-#define GLK_REVID_A2		0x2
-#define GLK_REVID_B0		0x3
-
-#define IS_GLK_REVID(dev_priv, since, until) \
-	(IS_GEMINILAKE(dev_priv) && IS_REVID(dev_priv, since, until))
-
-#define CNL_REVID_A0		0x0
-#define CNL_REVID_B0		0x1
-#define CNL_REVID_C0		0x2
-
-#define IS_CNL_REVID(p, since, until) \
-	(IS_CANNONLAKE(p) && IS_REVID(p, since, until))
-
-#define ICL_REVID_A0		0x0
-#define ICL_REVID_A2		0x1
-#define ICL_REVID_B0		0x3
-#define ICL_REVID_B2		0x4
-#define ICL_REVID_C0		0x5
-
-#define IS_ICL_REVID(p, since, until) \
-	(IS_ICELAKE(p) && IS_REVID(p, since, until))
-
-#define EHL_REVID_A0            0x0
-#define EHL_REVID_B0            0x1
-
-#define IS_JSL_EHL_REVID(p, since, until) \
-	(IS_JSL_EHL(p) && IS_REVID(p, since, until))
+#define IS_JSL_EHL_GT_STEP(p, since, until) \
+	(IS_JSL_EHL(p) && IS_GT_STEP(p, since, until))
+#define IS_JSL_EHL_DISPLAY_STEP(p, since, until) \
+	(IS_JSL_EHL(p) && IS_DISPLAY_STEP(p, since, until))
 
 #define IS_TGL_DISPLAY_STEP(__i915, since, until) \
 	(IS_TIGERLAKE(__i915) && \
@@ -1523,18 +1532,13 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 	(IS_TIGERLAKE(__i915) && !(IS_TGL_U(__i915) || IS_TGL_Y(__i915)) && \
 	 IS_GT_STEP(__i915, since, until))
 
-#define RKL_REVID_A0		0x0
-#define RKL_REVID_B0		0x1
-#define RKL_REVID_C0		0x4
+#define IS_RKL_DISPLAY_STEP(p, since, until) \
+	(IS_ROCKETLAKE(p) && IS_DISPLAY_STEP(p, since, until))
 
-#define IS_RKL_REVID(p, since, until) \
-	(IS_ROCKETLAKE(p) && IS_REVID(p, since, until))
-
-#define DG1_REVID_A0		0x0
-#define DG1_REVID_B0		0x1
-
-#define IS_DG1_REVID(p, since, until) \
-	(IS_DG1(p) && IS_REVID(p, since, until))
+#define IS_DG1_GT_STEP(p, since, until) \
+	(IS_DG1(p) && IS_GT_STEP(p, since, until))
+#define IS_DG1_DISPLAY_STEP(p, since, until) \
+	(IS_DG1(p) && IS_DISPLAY_STEP(p, since, until))
 
 #define IS_ADLS_DISPLAY_STEP(__i915, since, until) \
 	(IS_ALDERLAKE_S(__i915) && \
@@ -1552,6 +1556,31 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 	(IS_ALDERLAKE_P(__i915) && \
 	 IS_GT_STEP(__i915, since, until))
 
+#define IS_XEHPSDV_GT_STEP(__i915, since, until) \
+	(IS_XEHPSDV(__i915) && IS_GT_STEP(__i915, since, until))
+
+/*
+ * DG2 hardware steppings are a bit unusual.  The hardware design was forked
+ * to create two variants (G10 and G11) which have distinct workaround sets.
+ * The G11 fork of the DG2 design resets the GT stepping back to "A0" for its
+ * first iteration, even though it's more similar to a G10 B0 stepping in terms
+ * of functionality and workarounds.  However the display stepping does not
+ * reset in the same manner --- a specific stepping like "B0" has a consistent
+ * meaning regardless of whether it belongs to a G10 or G11 DG2.
+ *
+ * TLDR:  All GT workarounds and stepping-specific logic must be applied in
+ * relation to a specific subplatform (G10 or G11), whereas display workarounds
+ * and stepping-specific logic will be applied with a general DG2-wide stepping
+ * number.
+ */
+#define IS_DG2_GT_STEP(__i915, variant, since, until) \
+	(IS_SUBPLATFORM(__i915, INTEL_DG2, INTEL_SUBPLATFORM_##variant) && \
+	 IS_GT_STEP(__i915, since, until))
+
+#define IS_DG2_DISP_STEP(__i915, since, until) \
+	(IS_DG2(__i915) && \
+	 IS_DISPLAY_STEP(__i915, since, until))
+
 #define IS_LP(dev_priv)		(INTEL_INFO(dev_priv)->is_lp)
 #define IS_GEN9_LP(dev_priv)	(GRAPHICS_VER(dev_priv) == 9 && IS_LP(dev_priv))
 #define IS_GEN9_BC(dev_priv)	(GRAPHICS_VER(dev_priv) == 9 && !IS_LP(dev_priv))
@@ -1589,8 +1618,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_LOGICAL_RING_ELSQ(dev_priv) \
 		(INTEL_INFO(dev_priv)->has_logical_ring_elsq)
 
-#define HAS_MASTER_UNIT_IRQ(dev_priv) (INTEL_INFO(dev_priv)->has_master_unit_irq)
-
 #define HAS_EXECLISTS(dev_priv) HAS_LOGICAL_RING_CONTEXTS(dev_priv)
 
 #define INTEL_PPGTT(dev_priv) (INTEL_INFO(dev_priv)->ppgtt_type)
@@ -1616,12 +1643,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 /* WaRsDisableCoarsePowerGating:skl,cnl */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv)			\
-	(IS_CANNONLAKE(dev_priv) ||					\
-	 IS_SKL_GT3(dev_priv) ||					\
-	 IS_SKL_GT4(dev_priv))
+	(IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
 #define HAS_GMBUS_IRQ(dev_priv) (GRAPHICS_VER(dev_priv) >= 4)
-#define HAS_GMBUS_BURST_READ(dev_priv) (GRAPHICS_VER(dev_priv) >= 10 || \
+#define HAS_GMBUS_BURST_READ(dev_priv) (GRAPHICS_VER(dev_priv) >= 11 || \
 					IS_GEMINILAKE(dev_priv) || \
 					IS_KABYLAKE(dev_priv))
 
@@ -1641,6 +1666,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_DP_MST(dev_priv)	(INTEL_INFO(dev_priv)->display.has_dp_mst)
 
+#define HAS_CDCLK_CRAWL(dev_priv)	 (INTEL_INFO(dev_priv)->display.has_cdclk_crawl)
 #define HAS_DDI(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ddi)
 #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->display.has_fpga_dbg)
 #define HAS_PSR(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_psr)
@@ -1662,6 +1688,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm)
 #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc)
 
+#define HAS_MSLICES(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_mslices)
+
 #define HAS_IPC(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ipc)
 
 #define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i))
@@ -1751,9 +1780,6 @@ void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_init_early(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
 
-struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915,
-						 u16 type, u16 instance);
-
 static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
 {
 	/*
@@ -1850,24 +1876,18 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 
 struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags);
 
-static inline struct i915_gem_context *
-__i915_gem_context_lookup_rcu(struct drm_i915_file_private *file_priv, u32 id)
-{
-	return xa_load(&file_priv->context_xa, id);
-}
-
-static inline struct i915_gem_context *
-i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
+static inline struct i915_address_space *
+i915_gem_vm_lookup(struct drm_i915_file_private *file_priv, u32 id)
 {
-	struct i915_gem_context *ctx;
+	struct i915_address_space *vm;
 
 	rcu_read_lock();
-	ctx = __i915_gem_context_lookup_rcu(file_priv, id);
-	if (ctx && !kref_get_unless_zero(&ctx->ref))
-		ctx = NULL;
+	vm = xa_load(&file_priv->vm_xa, id);
+	if (vm && !kref_get_unless_zero(&vm->ref))
+		vm = NULL;
 	rcu_read_unlock();
 
-	return ctx;
+	return vm;
 }
 
 /* i915_gem_evict.c */
@@ -1934,8 +1954,8 @@ int remap_io_sg(struct vm_area_struct *vma,
 
 static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
 {
-	if (GRAPHICS_VER(i915) >= 10)
-		return CNL_HWS_CSB_WRITE_INDEX;
+	if (GRAPHICS_VER(i915) >= 11)
+		return ICL_HWS_CSB_WRITE_INDEX;
 	else
 		return I915_HWS_CSB_WRITE_INDEX;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 589388dec48a..590efc8b0265 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -469,12 +469,6 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 	if (ret != -ENODEV)
 		goto out;
 
-	ret = -ENODEV;
-	if (obj->ops->pread)
-		ret = obj->ops->pread(obj, args);
-	if (ret != -ENODEV)
-		goto out;
-
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE,
 				   MAX_SCHEDULE_TIMEOUT);
@@ -1005,8 +999,11 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	if (obj->mm.madv != __I915_MADV_PURGED)
+	if (obj->mm.madv != __I915_MADV_PURGED) {
 		obj->mm.madv = args->madv;
+		if (obj->ops->adjust_lru)
+			obj->ops->adjust_lru(obj);
+	}
 
 	if (i915_gem_object_has_pages(obj)) {
 		unsigned long flags;
@@ -1204,58 +1201,6 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	return ret;
 }
 
-void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ww, bool intr)
-{
-	ww_acquire_init(&ww->ctx, &reservation_ww_class);
-	INIT_LIST_HEAD(&ww->obj_list);
-	ww->intr = intr;
-	ww->contended = NULL;
-}
-
-static void i915_gem_ww_ctx_unlock_all(struct i915_gem_ww_ctx *ww)
-{
-	struct drm_i915_gem_object *obj;
-
-	while ((obj = list_first_entry_or_null(&ww->obj_list, struct drm_i915_gem_object, obj_link))) {
-		list_del(&obj->obj_link);
-		i915_gem_object_unlock(obj);
-	}
-}
-
-void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj)
-{
-	list_del(&obj->obj_link);
-	i915_gem_object_unlock(obj);
-}
-
-void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ww)
-{
-	i915_gem_ww_ctx_unlock_all(ww);
-	WARN_ON(ww->contended);
-	ww_acquire_fini(&ww->ctx);
-}
-
-int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ww)
-{
-	int ret = 0;
-
-	if (WARN_ON(!ww->contended))
-		return -EINVAL;
-
-	i915_gem_ww_ctx_unlock_all(ww);
-	if (ww->intr)
-		ret = dma_resv_lock_slow_interruptible(ww->contended->base.resv, &ww->ctx);
-	else
-		dma_resv_lock_slow(ww->contended->base.resv, &ww->ctx);
-
-	if (!ret)
-		list_add_tail(&ww->contended->obj_link, &ww->obj_list);
-
-	ww->contended = NULL;
-
-	return ret;
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_gem_device.c"
 #include "selftests/i915_gem.c"
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 440c35f1abc9..d0752e5553db 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -123,16 +123,4 @@ static inline bool __tasklet_is_scheduled(struct tasklet_struct *t)
 	return test_bit(TASKLET_STATE_SCHED, &t->state);
 }
 
-struct i915_gem_ww_ctx {
-	struct ww_acquire_ctx ctx;
-	struct list_head obj_list;
-	bool intr;
-	struct drm_i915_gem_object *contended;
-};
-
-void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ctx, bool intr);
-void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ctx);
-int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ctx);
-void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj);
-
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 4d2d59a9942b..2b73ddb11c66 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -27,6 +27,7 @@
  */
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/i915_gem_ww.c b/drivers/gpu/drm/i915/i915_gem_ww.c
new file mode 100644
index 000000000000..3f6ff139478e
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_ww.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+#include <linux/dma-resv.h>
+#include "i915_gem_ww.h"
+#include "gem/i915_gem_object.h"
+
+void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ww, bool intr)
+{
+	ww_acquire_init(&ww->ctx, &reservation_ww_class);
+	INIT_LIST_HEAD(&ww->obj_list);
+	ww->intr = intr;
+	ww->contended = NULL;
+}
+
+static void i915_gem_ww_ctx_unlock_all(struct i915_gem_ww_ctx *ww)
+{
+	struct drm_i915_gem_object *obj;
+
+	while ((obj = list_first_entry_or_null(&ww->obj_list, struct drm_i915_gem_object, obj_link))) {
+		list_del(&obj->obj_link);
+		i915_gem_object_unlock(obj);
+		i915_gem_object_put(obj);
+	}
+}
+
+void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj)
+{
+	list_del(&obj->obj_link);
+	i915_gem_object_unlock(obj);
+	i915_gem_object_put(obj);
+}
+
+void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ww)
+{
+	i915_gem_ww_ctx_unlock_all(ww);
+	WARN_ON(ww->contended);
+	ww_acquire_fini(&ww->ctx);
+}
+
+int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ww)
+{
+	int ret = 0;
+
+	if (WARN_ON(!ww->contended))
+		return -EINVAL;
+
+	i915_gem_ww_ctx_unlock_all(ww);
+	if (ww->intr)
+		ret = dma_resv_lock_slow_interruptible(ww->contended->base.resv, &ww->ctx);
+	else
+		dma_resv_lock_slow(ww->contended->base.resv, &ww->ctx);
+
+	if (!ret)
+		list_add_tail(&ww->contended->obj_link, &ww->obj_list);
+	else
+		i915_gem_object_put(ww->contended);
+
+	ww->contended = NULL;
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_ww.h b/drivers/gpu/drm/i915/i915_gem_ww.h
new file mode 100644
index 000000000000..f6b1a796667b
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_ww.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+#ifndef __I915_GEM_WW_H__
+#define __I915_GEM_WW_H__
+
+#include <drm/drm_drv.h>
+
+struct i915_gem_ww_ctx {
+	struct ww_acquire_ctx ctx;
+	struct list_head obj_list;
+	struct drm_i915_gem_object *contended;
+	unsigned short intr;
+	unsigned short loop;
+};
+
+void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ctx, bool intr);
+void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ctx);
+int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ctx);
+void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj);
+
+/* Internal functions used by the inlines! Don't use. */
+static inline int __i915_gem_ww_fini(struct i915_gem_ww_ctx *ww, int err)
+{
+	ww->loop = 0;
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(ww);
+		if (!err)
+			ww->loop = 1;
+	}
+
+	if (!ww->loop)
+		i915_gem_ww_ctx_fini(ww);
+
+	return err;
+}
+
+static inline void
+__i915_gem_ww_init(struct i915_gem_ww_ctx *ww, bool intr)
+{
+	i915_gem_ww_ctx_init(ww, intr);
+	ww->loop = 1;
+}
+
+#define for_i915_gem_ww(_ww, _err, _intr)			\
+	for (__i915_gem_ww_init(_ww, _intr); (_ww)->loop;	\
+	     _err = __i915_gem_ww_fini(_ww, _err))
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 24e18219eb50..77490cb5ff9c 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -15,7 +15,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	const struct sseu_dev_info *sseu = &i915->gt.info.sseu;
 	drm_i915_getparam_t *param = data;
-	int value;
+	int value = 0;
 
 	switch (param->param) {
 	case I915_PARAM_IRQ_ACTIVE:
@@ -134,6 +134,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_FENCE_ARRAY:
 	case I915_PARAM_HAS_EXEC_SUBMIT_FENCE:
 	case I915_PARAM_HAS_EXEC_TIMELINE_FENCES:
+	case I915_PARAM_HAS_USERPTR_PROBE:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
@@ -150,7 +151,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = sseu->subslice_mask[0];
+		/* Only copy bits from the first slice */
+		memcpy(&value, sseu->subslice_mask,
+		       min(sseu->ss_stride, (u8)sizeof(value)));
 		if (!value)
 			return -ENODEV;
 		break;
diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c
deleted file mode 100644
index 3acb0b6be284..000000000000
--- a/drivers/gpu/drm/i915/i915_globals.c
+++ /dev/null
@@ -1,160 +0,0 @@
-/*
- * SPDX-License-Identifier: MIT
- *
- * Copyright © 2019 Intel Corporation
- */
-
-#include <linux/slab.h>
-#include <linux/workqueue.h>
-
-#include "i915_active.h"
-#include "gem/i915_gem_context.h"
-#include "gem/i915_gem_object.h"
-#include "i915_globals.h"
-#include "i915_request.h"
-#include "i915_scheduler.h"
-#include "i915_vma.h"
-
-static LIST_HEAD(globals);
-
-static atomic_t active;
-static atomic_t epoch;
-static struct park_work {
-	struct delayed_work work;
-	struct rcu_head rcu;
-	unsigned long flags;
-#define PENDING 0
-	int epoch;
-} park;
-
-static void i915_globals_shrink(void)
-{
-	struct i915_global *global;
-
-	/*
-	 * kmem_cache_shrink() discards empty slabs and reorders partially
-	 * filled slabs to prioritise allocating from the mostly full slabs,
-	 * with the aim of reducing fragmentation.
-	 */
-	list_for_each_entry(global, &globals, link)
-		global->shrink();
-}
-
-static void __i915_globals_grace(struct rcu_head *rcu)
-{
-	/* Ratelimit parking as shrinking is quite slow */
-	schedule_delayed_work(&park.work, round_jiffies_up_relative(2 * HZ));
-}
-
-static void __i915_globals_queue_rcu(void)
-{
-	park.epoch = atomic_inc_return(&epoch);
-	if (!atomic_read(&active)) {
-		init_rcu_head(&park.rcu);
-		call_rcu(&park.rcu, __i915_globals_grace);
-	}
-}
-
-static void __i915_globals_park(struct work_struct *work)
-{
-	destroy_rcu_head(&park.rcu);
-
-	/* Confirm nothing woke up in the last grace period */
-	if (park.epoch != atomic_read(&epoch)) {
-		__i915_globals_queue_rcu();
-		return;
-	}
-
-	clear_bit(PENDING, &park.flags);
-	i915_globals_shrink();
-}
-
-void __init i915_global_register(struct i915_global *global)
-{
-	GEM_BUG_ON(!global->shrink);
-	GEM_BUG_ON(!global->exit);
-
-	list_add_tail(&global->link, &globals);
-}
-
-static void __i915_globals_cleanup(void)
-{
-	struct i915_global *global, *next;
-
-	list_for_each_entry_safe_reverse(global, next, &globals, link)
-		global->exit();
-}
-
-static __initconst int (* const initfn[])(void) = {
-	i915_global_active_init,
-	i915_global_context_init,
-	i915_global_gem_context_init,
-	i915_global_objects_init,
-	i915_global_request_init,
-	i915_global_scheduler_init,
-	i915_global_vma_init,
-};
-
-int __init i915_globals_init(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(initfn); i++) {
-		int err;
-
-		err = initfn[i]();
-		if (err) {
-			__i915_globals_cleanup();
-			return err;
-		}
-	}
-
-	INIT_DELAYED_WORK(&park.work, __i915_globals_park);
-	return 0;
-}
-
-void i915_globals_park(void)
-{
-	/*
-	 * Defer shrinking the global slab caches (and other work) until
-	 * after a RCU grace period has completed with no activity. This
-	 * is to try and reduce the latency impact on the consumers caused
-	 * by us shrinking the caches the same time as they are trying to
-	 * allocate, with the assumption being that if we idle long enough
-	 * for an RCU grace period to elapse since the last use, it is likely
-	 * to be longer until we need the caches again.
-	 */
-	if (!atomic_dec_and_test(&active))
-		return;
-
-	/* Queue cleanup after the next RCU grace period has freed slabs */
-	if (!test_and_set_bit(PENDING, &park.flags))
-		__i915_globals_queue_rcu();
-}
-
-void i915_globals_unpark(void)
-{
-	atomic_inc(&epoch);
-	atomic_inc(&active);
-}
-
-static void  __i915_globals_flush(void)
-{
-	atomic_inc(&active); /* skip shrinking */
-
-	rcu_barrier(); /* wait for the work to be queued */
-	flush_delayed_work(&park.work);
-
-	atomic_dec(&active);
-}
-
-void i915_globals_exit(void)
-{
-	GEM_BUG_ON(atomic_read(&active));
-
-	__i915_globals_flush();
-	__i915_globals_cleanup();
-
-	/* And ensure that our DESTROY_BY_RCU slabs are truly destroyed */
-	rcu_barrier();
-}
diff --git a/drivers/gpu/drm/i915/i915_globals.h b/drivers/gpu/drm/i915/i915_globals.h
deleted file mode 100644
index 2d199f411a4a..000000000000
--- a/drivers/gpu/drm/i915/i915_globals.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * SPDX-License-Identifier: MIT
- *
- * Copyright © 2019 Intel Corporation
- */
-
-#ifndef _I915_GLOBALS_H_
-#define _I915_GLOBALS_H_
-
-#include <linux/types.h>
-
-typedef void (*i915_global_func_t)(void);
-
-struct i915_global {
-	struct list_head link;
-
-	i915_global_func_t shrink;
-	i915_global_func_t exit;
-};
-
-void i915_global_register(struct i915_global *global);
-
-int i915_globals_init(void);
-void i915_globals_park(void);
-void i915_globals_unpark(void);
-void i915_globals_exit(void);
-
-/* constructors */
-int i915_global_active_init(void);
-int i915_global_context_init(void);
-int i915_global_gem_context_init(void);
-int i915_global_objects_init(void);
-int i915_global_request_init(void);
-int i915_global_scheduler_init(void);
-int i915_global_vma_init(void);
-
-#endif /* _I915_GLOBALS_H_ */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 966664610c8c..9cf6ac575de1 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1048,7 +1048,7 @@ i915_vma_coredump_create(const struct intel_gt *gt,
 			if (ret)
 				break;
 		}
-	} else if (i915_gem_object_is_lmem(vma->obj)) {
+	} else if (__i915_gem_object_is_lmem(vma->obj)) {
 		struct intel_memory_region *mem = vma->obj->mm.region;
 		dma_addr_t dma;
 
@@ -1438,20 +1438,37 @@ capture_engine(struct intel_engine_cs *engine,
 {
 	struct intel_engine_capture_vma *capture = NULL;
 	struct intel_engine_coredump *ee;
-	struct i915_request *rq;
+	struct intel_context *ce;
+	struct i915_request *rq = NULL;
 	unsigned long flags;
 
 	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
 	if (!ee)
 		return NULL;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	rq = intel_engine_find_active_request(engine);
+	ce = intel_engine_get_hung_context(engine);
+	if (ce) {
+		intel_engine_clear_hung_context(engine);
+		rq = intel_context_find_active_request(ce);
+		if (!rq || !i915_request_started(rq))
+			goto no_request_capture;
+	} else {
+		/*
+		 * Getting here with GuC enabled means it is a forced error capture
+		 * with no actual hang. So, no need to attempt the execlist search.
+		 */
+		if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
+			spin_lock_irqsave(&engine->sched_engine->lock, flags);
+			rq = intel_engine_execlist_find_hung_request(engine);
+			spin_unlock_irqrestore(&engine->sched_engine->lock,
+					       flags);
+		}
+	}
 	if (rq)
 		capture = intel_engine_coredump_add_request(ee, rq,
 							    ATOMIC_MAYFAIL);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
 	if (!capture) {
+no_request_capture:
 		kfree(ee);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c3816f5c6900..9bc4f4a8e12e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -207,7 +207,7 @@ static void intel_hpd_init_pins(struct drm_i915_private *dev_priv)
 	    (!HAS_PCH_SPLIT(dev_priv) || HAS_PCH_NOP(dev_priv)))
 		return;
 
-	if (HAS_PCH_DG1(dev_priv))
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_DG1)
 		hpd->pch_hpd = hpd_sde_dg1;
 	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		hpd->pch_hpd = hpd_icp;
@@ -2297,11 +2297,10 @@ static u32 gen8_de_port_aux_mask(struct drm_i915_private *dev_priv)
 			GEN9_AUX_CHANNEL_C |
 			GEN9_AUX_CHANNEL_D;
 
-	if (IS_CNL_WITH_PORT_F(dev_priv) || DISPLAY_VER(dev_priv) == 11)
-		mask |= CNL_AUX_CHANNEL_F;
-
-	if (DISPLAY_VER(dev_priv) == 11)
+	if (DISPLAY_VER(dev_priv) == 11) {
+		mask |= ICL_AUX_CHANNEL_F;
 		mask |= ICL_AUX_CHANNEL_E;
+	}
 
 	return mask;
 }
@@ -2698,11 +2697,9 @@ gen11_display_irq_handler(struct drm_i915_private *i915)
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 }
 
-static __always_inline irqreturn_t
-__gen11_irq_handler(struct drm_i915_private * const i915,
-		    u32 (*intr_disable)(void __iomem * const regs),
-		    void (*intr_enable)(void __iomem * const regs))
+static irqreturn_t gen11_irq_handler(int irq, void *arg)
 {
+	struct drm_i915_private *i915 = arg;
 	void __iomem * const regs = i915->uncore.regs;
 	struct intel_gt *gt = &i915->gt;
 	u32 master_ctl;
@@ -2711,9 +2708,9 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 	if (!intel_irqs_enabled(i915))
 		return IRQ_NONE;
 
-	master_ctl = intr_disable(regs);
+	master_ctl = gen11_master_intr_disable(regs);
 	if (!master_ctl) {
-		intr_enable(regs);
+		gen11_master_intr_enable(regs);
 		return IRQ_NONE;
 	}
 
@@ -2726,7 +2723,7 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 
 	gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl);
 
-	intr_enable(regs);
+	gen11_master_intr_enable(regs);
 
 	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
 
@@ -2735,51 +2732,69 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t gen11_irq_handler(int irq, void *arg)
-{
-	return __gen11_irq_handler(arg,
-				   gen11_master_intr_disable,
-				   gen11_master_intr_enable);
-}
-
-static u32 dg1_master_intr_disable_and_ack(void __iomem * const regs)
+static inline u32 dg1_master_intr_disable(void __iomem * const regs)
 {
 	u32 val;
 
 	/* First disable interrupts */
-	raw_reg_write(regs, DG1_MSTR_UNIT_INTR, 0);
+	raw_reg_write(regs, DG1_MSTR_TILE_INTR, 0);
 
 	/* Get the indication levels and ack the master unit */
-	val = raw_reg_read(regs, DG1_MSTR_UNIT_INTR);
+	val = raw_reg_read(regs, DG1_MSTR_TILE_INTR);
 	if (unlikely(!val))
 		return 0;
 
-	raw_reg_write(regs, DG1_MSTR_UNIT_INTR, val);
-
-	/*
-	 * Now with master disabled, get a sample of level indications
-	 * for this interrupt and ack them right away - we keep GEN11_MASTER_IRQ
-	 * out as this bit doesn't exist anymore for DG1
-	 */
-	val = raw_reg_read(regs, GEN11_GFX_MSTR_IRQ) & ~GEN11_MASTER_IRQ;
-	if (unlikely(!val))
-		return 0;
-
-	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, val);
+	raw_reg_write(regs, DG1_MSTR_TILE_INTR, val);
 
 	return val;
 }
 
 static inline void dg1_master_intr_enable(void __iomem * const regs)
 {
-	raw_reg_write(regs, DG1_MSTR_UNIT_INTR, DG1_MSTR_IRQ);
+	raw_reg_write(regs, DG1_MSTR_TILE_INTR, DG1_MSTR_IRQ);
 }
 
 static irqreturn_t dg1_irq_handler(int irq, void *arg)
 {
-	return __gen11_irq_handler(arg,
-				   dg1_master_intr_disable_and_ack,
-				   dg1_master_intr_enable);
+	struct drm_i915_private * const i915 = arg;
+	struct intel_gt *gt = &i915->gt;
+	void __iomem * const regs = i915->uncore.regs;
+	u32 master_tile_ctl, master_ctl;
+	u32 gu_misc_iir;
+
+	if (!intel_irqs_enabled(i915))
+		return IRQ_NONE;
+
+	master_tile_ctl = dg1_master_intr_disable(regs);
+	if (!master_tile_ctl) {
+		dg1_master_intr_enable(regs);
+		return IRQ_NONE;
+	}
+
+	/* FIXME: we only support tile 0 for now. */
+	if (master_tile_ctl & DG1_MSTR_TILE(0)) {
+		master_ctl = raw_reg_read(regs, GEN11_GFX_MSTR_IRQ);
+		raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, master_ctl);
+	} else {
+		DRM_ERROR("Tile not supported: 0x%08x\n", master_tile_ctl);
+		dg1_master_intr_enable(regs);
+		return IRQ_NONE;
+	}
+
+	gen11_gt_irq_handler(gt, master_ctl);
+
+	if (master_ctl & GEN11_DISPLAY_IRQ)
+		gen11_display_irq_handler(i915);
+
+	gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl);
+
+	dg1_master_intr_enable(regs);
+
+	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
+
+	pmu_irq_stats(i915, IRQ_HANDLED);
+
+	return IRQ_HANDLED;
 }
 
 /* Called from drm generic code, passed 'crtc' which
@@ -2880,14 +2895,14 @@ static bool gen11_dsi_configure_te(struct intel_crtc *intel_crtc,
 	return true;
 }
 
-int bdw_enable_vblank(struct drm_crtc *crtc)
+int bdw_enable_vblank(struct drm_crtc *_crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(_crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	unsigned long irqflags;
 
-	if (gen11_dsi_configure_te(intel_crtc, true))
+	if (gen11_dsi_configure_te(crtc, true))
 		return 0;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2898,7 +2913,7 @@ int bdw_enable_vblank(struct drm_crtc *crtc)
 	 * PSR is active as no frames are generated, so check only for PSR.
 	 */
 	if (HAS_PSR(dev_priv))
-		drm_crtc_vblank_restore(crtc);
+		drm_crtc_vblank_restore(&crtc->base);
 
 	return 0;
 }
@@ -2952,14 +2967,14 @@ void ilk_disable_vblank(struct drm_crtc *crtc)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-void bdw_disable_vblank(struct drm_crtc *crtc)
+void bdw_disable_vblank(struct drm_crtc *_crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(_crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	unsigned long irqflags;
 
-	if (gen11_dsi_configure_te(intel_crtc, false))
+	if (gen11_dsi_configure_te(crtc, false))
 		return;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -3146,10 +3161,20 @@ static void gen11_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
-	if (HAS_MASTER_UNIT_IRQ(dev_priv))
-		dg1_master_intr_disable_and_ack(dev_priv->uncore.regs);
-	else
-		gen11_master_intr_disable(dev_priv->uncore.regs);
+	gen11_master_intr_disable(dev_priv->uncore.regs);
+
+	gen11_gt_irq_reset(&dev_priv->gt);
+	gen11_display_irq_reset(dev_priv);
+
+	GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_);
+	GEN3_IRQ_RESET(uncore, GEN8_PCU_);
+}
+
+static void dg1_irq_reset(struct drm_i915_private *dev_priv)
+{
+	struct intel_uncore *uncore = &dev_priv->uncore;
+
+	dg1_master_intr_disable(dev_priv->uncore.regs);
 
 	gen11_gt_irq_reset(&dev_priv->gt);
 	gen11_display_irq_reset(dev_priv);
@@ -3841,13 +3866,28 @@ static void gen11_irq_postinstall(struct drm_i915_private *dev_priv)
 
 	GEN3_IRQ_INIT(uncore, GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked);
 
-	if (HAS_MASTER_UNIT_IRQ(dev_priv)) {
-		dg1_master_intr_enable(uncore->regs);
-		intel_uncore_posting_read(&dev_priv->uncore, DG1_MSTR_UNIT_INTR);
-	} else {
-		gen11_master_intr_enable(uncore->regs);
-		intel_uncore_posting_read(&dev_priv->uncore, GEN11_GFX_MSTR_IRQ);
+	gen11_master_intr_enable(uncore->regs);
+	intel_uncore_posting_read(&dev_priv->uncore, GEN11_GFX_MSTR_IRQ);
+}
+
+static void dg1_irq_postinstall(struct drm_i915_private *dev_priv)
+{
+	struct intel_uncore *uncore = &dev_priv->uncore;
+	u32 gu_misc_masked = GEN11_GU_MISC_GSE;
+
+	gen11_gt_irq_postinstall(&dev_priv->gt);
+
+	GEN3_IRQ_INIT(uncore, GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked);
+
+	if (HAS_DISPLAY(dev_priv)) {
+		icp_irq_postinstall(dev_priv);
+		gen8_de_irq_postinstall(dev_priv);
+		intel_uncore_write(&dev_priv->uncore, GEN11_DISPLAY_INT_CTL,
+				   GEN11_DISPLAY_IRQ_ENABLE);
 	}
+
+	dg1_master_intr_enable(dev_priv->uncore.regs);
+	intel_uncore_posting_read(&dev_priv->uncore, DG1_MSTR_TILE_INTR);
 }
 
 static void cherryview_irq_postinstall(struct drm_i915_private *dev_priv)
@@ -4386,9 +4426,9 @@ static irq_handler_t intel_irq_handler(struct drm_i915_private *dev_priv)
 		else
 			return i8xx_irq_handler;
 	} else {
-		if (HAS_MASTER_UNIT_IRQ(dev_priv))
+		if (GRAPHICS_VER_FULL(dev_priv) >= IP_VER(12, 10))
 			return dg1_irq_handler;
-		if (GRAPHICS_VER(dev_priv) >= 11)
+		else if (GRAPHICS_VER(dev_priv) >= 11)
 			return gen11_irq_handler;
 		else if (GRAPHICS_VER(dev_priv) >= 8)
 			return gen8_irq_handler;
@@ -4411,7 +4451,9 @@ static void intel_irq_reset(struct drm_i915_private *dev_priv)
 		else
 			i8xx_irq_reset(dev_priv);
 	} else {
-		if (GRAPHICS_VER(dev_priv) >= 11)
+		if (GRAPHICS_VER_FULL(dev_priv) >= IP_VER(12, 10))
+			dg1_irq_reset(dev_priv);
+		else if (GRAPHICS_VER(dev_priv) >= 11)
 			gen11_irq_reset(dev_priv);
 		else if (GRAPHICS_VER(dev_priv) >= 8)
 			gen8_irq_reset(dev_priv);
@@ -4434,7 +4476,9 @@ static void intel_irq_postinstall(struct drm_i915_private *dev_priv)
 		else
 			i8xx_irq_postinstall(dev_priv);
 	} else {
-		if (GRAPHICS_VER(dev_priv) >= 11)
+		if (GRAPHICS_VER_FULL(dev_priv) >= IP_VER(12, 10))
+			dg1_irq_postinstall(dev_priv);
+		else if (GRAPHICS_VER(dev_priv) >= 11)
 			gen11_irq_postinstall(dev_priv);
 		else if (GRAPHICS_VER(dev_priv) >= 8)
 			gen8_irq_postinstall(dev_priv);
@@ -4466,14 +4510,14 @@ int intel_irq_install(struct drm_i915_private *dev_priv)
 	 */
 	dev_priv->runtime_pm.irqs_enabled = true;
 
-	dev_priv->drm.irq_enabled = true;
+	dev_priv->irq_enabled = true;
 
 	intel_irq_reset(dev_priv);
 
 	ret = request_irq(irq, intel_irq_handler(dev_priv),
 			  IRQF_SHARED, DRIVER_NAME, dev_priv);
 	if (ret < 0) {
-		dev_priv->drm.irq_enabled = false;
+		dev_priv->irq_enabled = false;
 		return ret;
 	}
 
@@ -4499,10 +4543,10 @@ void intel_irq_uninstall(struct drm_i915_private *dev_priv)
 	 * intel_modeset_driver_remove() calling us out of sequence.
 	 * Would be nice if it didn't do that...
 	 */
-	if (!dev_priv->drm.irq_enabled)
+	if (!dev_priv->irq_enabled)
 		return;
 
-	dev_priv->drm.irq_enabled = false;
+	dev_priv->irq_enabled = false;
 
 	intel_irq_reset(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c
new file mode 100644
index 000000000000..d8b4482c69d0
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_module.c
@@ -0,0 +1,124 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/console.h>
+
+#include "gem/i915_gem_context.h"
+#include "gem/i915_gem_object.h"
+#include "i915_active.h"
+#include "i915_buddy.h"
+#include "i915_params.h"
+#include "i915_pci.h"
+#include "i915_perf.h"
+#include "i915_request.h"
+#include "i915_scheduler.h"
+#include "i915_selftest.h"
+#include "i915_vma.h"
+
+static int i915_check_nomodeset(void)
+{
+	bool use_kms = true;
+
+	/*
+	 * Enable KMS by default, unless explicitly overriden by
+	 * either the i915.modeset prarameter or by the
+	 * vga_text_mode_force boot option.
+	 */
+
+	if (i915_modparams.modeset == 0)
+		use_kms = false;
+
+	if (vgacon_text_force() && i915_modparams.modeset == -1)
+		use_kms = false;
+
+	if (!use_kms) {
+		/* Silently fail loading to not upset userspace. */
+		DRM_DEBUG_DRIVER("KMS disabled.\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static const struct {
+   int (*init)(void);
+   void (*exit)(void);
+} init_funcs[] = {
+	{ .init = i915_check_nomodeset },
+	{ .init = i915_active_module_init,
+	  .exit = i915_active_module_exit },
+	{ .init = i915_buddy_module_init,
+	  .exit = i915_buddy_module_exit },
+	{ .init = i915_context_module_init,
+	  .exit = i915_context_module_exit },
+	{ .init = i915_gem_context_module_init,
+	  .exit = i915_gem_context_module_exit },
+	{ .init = i915_objects_module_init,
+	  .exit = i915_objects_module_exit },
+	{ .init = i915_request_module_init,
+	  .exit = i915_request_module_exit },
+	{ .init = i915_scheduler_module_init,
+	  .exit = i915_scheduler_module_exit },
+	{ .init = i915_vma_module_init,
+	  .exit = i915_vma_module_exit },
+	{ .init = i915_mock_selftests },
+	{ .init = i915_pmu_init,
+	  .exit = i915_pmu_exit },
+	{ .init = i915_register_pci_driver,
+	  .exit = i915_unregister_pci_driver },
+	{ .init = i915_perf_sysctl_register,
+	  .exit = i915_perf_sysctl_unregister },
+};
+static int init_progress;
+
+static int __init i915_init(void)
+{
+	int err, i;
+
+	for (i = 0; i < ARRAY_SIZE(init_funcs); i++) {
+		err = init_funcs[i].init();
+		if (err < 0) {
+			while (i--) {
+				if (init_funcs[i].exit)
+					init_funcs[i].exit();
+			}
+			return err;
+		} else if (err > 0) {
+			/*
+			 * Early-exit success is reserved for things which
+			 * don't have an exit() function because we have no
+			 * idea how far they got or how to partially tear
+			 * them down.
+			 */
+			WARN_ON(init_funcs[i].exit);
+			break;
+		}
+	}
+
+	init_progress = i;
+
+	return 0;
+}
+
+static void __exit i915_exit(void)
+{
+	int i;
+
+	for (i = init_progress - 1; i >= 0; i--) {
+		GEM_BUG_ON(i >= ARRAY_SIZE(init_funcs));
+		if (init_funcs[i].exit)
+			init_funcs[i].exit();
+	}
+}
+
+module_init(i915_init);
+module_exit(i915_exit);
+
+MODULE_AUTHOR("Tungsten Graphics, Inc.");
+MODULE_AUTHOR("Intel Corporation");
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 2880ec57c97d..1bbd09ad5287 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -22,18 +22,13 @@
  *
  */
 
-#include <linux/console.h>
 #include <linux/vga_switcheroo.h>
 
 #include <drm/drm_drv.h>
 #include <drm/i915_pciids.h>
 
-#include "display/intel_fbdev.h"
-
 #include "i915_drv.h"
-#include "i915_perf.h"
-#include "i915_globals.h"
-#include "i915_selftest.h"
+#include "i915_pci.h"
 
 #define PLATFORM(x) .platform = (x)
 #define GEN(x) \
@@ -787,27 +782,13 @@ static const struct intel_device_info cml_gt2_info = {
 	.gt = 2,
 };
 
-#define GEN10_FEATURES \
-	GEN9_FEATURES, \
-	GEN(10), \
-	.dbuf.size = 1024 - 4, /* 4 blocks for bypass path allocation */ \
-	.display.has_dsc = 1, \
-	.has_coherent_ggtt = false, \
-	GLK_COLORS
-
-static const struct intel_device_info cnl_info = {
-	GEN10_FEATURES,
-	PLATFORM(INTEL_CANNONLAKE),
-	.gt = 2,
-};
-
 #define GEN11_DEFAULT_PAGE_SIZES \
 	.page_sizes = I915_GTT_PAGE_SIZE_4K | \
 		      I915_GTT_PAGE_SIZE_64K | \
 		      I915_GTT_PAGE_SIZE_2M
 
 #define GEN11_FEATURES \
-	GEN10_FEATURES, \
+	GEN9_FEATURES, \
 	GEN11_DEFAULT_PAGE_SIZES, \
 	.abox_mask = BIT(0), \
 	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
@@ -830,10 +811,12 @@ static const struct intel_device_info cnl_info = {
 		[TRANSCODER_DSI_1] = TRANSCODER_DSI1_OFFSET, \
 	}, \
 	GEN(11), \
+	.color = { .degamma_lut_size = 33, .gamma_lut_size = 262145 }, \
 	.dbuf.size = 2048, \
 	.dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2), \
-	.has_logical_ring_elsq = 1, \
-	.color = { .degamma_lut_size = 33, .gamma_lut_size = 262145 }
+	.display.has_dsc = 1, \
+	.has_coherent_ggtt = false, \
+	.has_logical_ring_elsq = 1
 
 static const struct intel_device_info icl_info = {
 	GEN11_FEATURES,
@@ -845,7 +828,6 @@ static const struct intel_device_info icl_info = {
 static const struct intel_device_info ehl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_ELKHARTLAKE),
-	.require_force_probe = 1,
 	.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0),
 	.ppgtt_size = 36,
 };
@@ -853,7 +835,6 @@ static const struct intel_device_info ehl_info = {
 static const struct intel_device_info jsl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_JASPERLAKE),
-	.require_force_probe = 1,
 	.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0),
 	.ppgtt_size = 36,
 };
@@ -909,7 +890,6 @@ static const struct intel_device_info rkl_info = {
 
 #define DGFX_FEATURES \
 	.memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \
-	.has_master_unit_irq = 1, \
 	.has_llc = 0, \
 	.has_snoop = 1, \
 	.is_dgfx = 1
@@ -917,6 +897,7 @@ static const struct intel_device_info rkl_info = {
 static const struct intel_device_info dg1_info __maybe_unused = {
 	GEN12_FEATURES,
 	DGFX_FEATURES,
+	.graphics_rel = 10,
 	PLATFORM(INTEL_DG1),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
 	.require_force_probe = 1,
@@ -936,26 +917,60 @@ static const struct intel_device_info adl_s_info = {
 	.display.has_psr_hw_tracking = 0,
 	.platform_engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
-	.dma_mask_size = 46,
+	.dma_mask_size = 39,
 };
 
+#define XE_LPD_CURSOR_OFFSETS \
+	.cursor_offsets = { \
+		[PIPE_A] = CURSOR_A_OFFSET, \
+		[PIPE_B] = IVB_CURSOR_B_OFFSET, \
+		[PIPE_C] = IVB_CURSOR_C_OFFSET, \
+		[PIPE_D] = TGL_CURSOR_D_OFFSET, \
+	}
+
 #define XE_LPD_FEATURES \
-	.display.ver = 13,						\
-	.display.has_psr_hw_tracking = 0,				\
-	.abox_mask = GENMASK(1, 0),					\
-	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \
-	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |	\
-		BIT(TRANSCODER_C) | BIT(TRANSCODER_D),			\
-	.dbuf.size = 4096,						\
-	.dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4)
+	.abox_mask = GENMASK(1, 0),						\
+	.color = { .degamma_lut_size = 0, .gamma_lut_size = 0 },		\
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |		\
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_D),				\
+	.dbuf.size = 4096,							\
+	.dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) |		\
+		BIT(DBUF_S4),							\
+	.display.has_ddi = 1,							\
+	.display.has_dmc = 1,							\
+	.display.has_dp_mst = 1,						\
+	.display.has_dsb = 1,							\
+	.display.has_dsc = 1,							\
+	.display.has_fbc = 1,							\
+	.display.has_fpga_dbg = 1,						\
+	.display.has_hdcp = 1,							\
+	.display.has_hotplug = 1,						\
+	.display.has_ipc = 1,							\
+	.display.has_psr = 1,							\
+	.display.ver = 13,							\
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),	\
+	.pipe_offsets = {							\
+		[TRANSCODER_A] = PIPE_A_OFFSET,					\
+		[TRANSCODER_B] = PIPE_B_OFFSET,					\
+		[TRANSCODER_C] = PIPE_C_OFFSET,					\
+		[TRANSCODER_D] = PIPE_D_OFFSET,					\
+	},									\
+	.trans_offsets = {							\
+		[TRANSCODER_A] = TRANSCODER_A_OFFSET,				\
+		[TRANSCODER_B] = TRANSCODER_B_OFFSET,				\
+		[TRANSCODER_C] = TRANSCODER_C_OFFSET,				\
+		[TRANSCODER_D] = TRANSCODER_D_OFFSET,				\
+	},									\
+	XE_LPD_CURSOR_OFFSETS
 
 static const struct intel_device_info adl_p_info = {
 	GEN12_FEATURES,
 	XE_LPD_FEATURES,
 	PLATFORM(INTEL_ALDERLAKE_P),
-	.has_cdclk_crawl = 1,
 	.require_force_probe = 1,
+	.display.has_cdclk_crawl = 1,
 	.display.has_modular_fia = 1,
+	.display.has_psr_hw_tracking = 0,
 	.platform_engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
 	.ppgtt_size = 48,
@@ -963,6 +978,67 @@ static const struct intel_device_info adl_p_info = {
 };
 
 #undef GEN
+
+#define XE_HP_PAGE_SIZES \
+	.page_sizes = I915_GTT_PAGE_SIZE_4K | \
+		      I915_GTT_PAGE_SIZE_64K | \
+		      I915_GTT_PAGE_SIZE_2M
+
+#define XE_HP_FEATURES \
+	.graphics_ver = 12, \
+	.graphics_rel = 50, \
+	XE_HP_PAGE_SIZES, \
+	.dma_mask_size = 46, \
+	.has_64bit_reloc = 1, \
+	.has_global_mocs = 1, \
+	.has_gt_uc = 1, \
+	.has_llc = 1, \
+	.has_logical_ring_contexts = 1, \
+	.has_logical_ring_elsq = 1, \
+	.has_mslices = 1, \
+	.has_rc6 = 1, \
+	.has_reset_engine = 1, \
+	.has_rps = 1, \
+	.has_runtime_pm = 1, \
+	.ppgtt_size = 48, \
+	.ppgtt_type = INTEL_PPGTT_FULL
+
+#define XE_HPM_FEATURES \
+	.media_ver = 12, \
+	.media_rel = 50
+
+__maybe_unused
+static const struct intel_device_info xehpsdv_info = {
+	XE_HP_FEATURES,
+	XE_HPM_FEATURES,
+	DGFX_FEATURES,
+	PLATFORM(INTEL_XEHPSDV),
+	.display = { },
+	.pipe_mask = 0,
+	.platform_engine_mask =
+		BIT(RCS0) | BIT(BCS0) |
+		BIT(VECS0) | BIT(VECS1) | BIT(VECS2) | BIT(VECS3) |
+		BIT(VCS0) | BIT(VCS1) | BIT(VCS2) | BIT(VCS3) |
+		BIT(VCS4) | BIT(VCS5) | BIT(VCS6) | BIT(VCS7),
+	.require_force_probe = 1,
+};
+
+__maybe_unused
+static const struct intel_device_info dg2_info = {
+	XE_HP_FEATURES,
+	XE_HPM_FEATURES,
+	XE_LPD_FEATURES,
+	DGFX_FEATURES,
+	.graphics_rel = 55,
+	.media_rel = 55,
+	PLATFORM(INTEL_DG2),
+	.platform_engine_mask =
+		BIT(RCS0) | BIT(BCS0) |
+		BIT(VECS0) | BIT(VECS1) |
+		BIT(VCS0) | BIT(VCS2),
+	.require_force_probe = 1,
+};
+
 #undef PLATFORM
 
 /*
@@ -1032,7 +1108,6 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_CML_GT2_IDS(&cml_gt2_info),
 	INTEL_CML_U_GT1_IDS(&cml_gt1_info),
 	INTEL_CML_U_GT2_IDS(&cml_gt2_info),
-	INTEL_CNL_IDS(&cnl_info),
 	INTEL_ICL_11_IDS(&icl_info),
 	INTEL_EHL_IDS(&ehl_info),
 	INTEL_JSL_IDS(&jsl_info),
@@ -1159,66 +1234,12 @@ static struct pci_driver i915_pci_driver = {
 	.driver.pm = &i915_pm_ops,
 };
 
-static int __init i915_init(void)
+int i915_register_pci_driver(void)
 {
-	bool use_kms = true;
-	int err;
-
-	err = i915_globals_init();
-	if (err)
-		return err;
-
-	err = i915_mock_selftests();
-	if (err)
-		return err > 0 ? 0 : err;
-
-	/*
-	 * Enable KMS by default, unless explicitly overriden by
-	 * either the i915.modeset prarameter or by the
-	 * vga_text_mode_force boot option.
-	 */
-
-	if (i915_modparams.modeset == 0)
-		use_kms = false;
-
-	if (vgacon_text_force() && i915_modparams.modeset == -1)
-		use_kms = false;
-
-	if (!use_kms) {
-		/* Silently fail loading to not upset userspace. */
-		DRM_DEBUG_DRIVER("KMS disabled.\n");
-		return 0;
-	}
-
-	i915_pmu_init();
-
-	err = pci_register_driver(&i915_pci_driver);
-	if (err) {
-		i915_pmu_exit();
-		i915_globals_exit();
-		return err;
-	}
-
-	i915_perf_sysctl_register();
-	return 0;
+	return pci_register_driver(&i915_pci_driver);
 }
 
-static void __exit i915_exit(void)
+void i915_unregister_pci_driver(void)
 {
-	if (!i915_pci_driver.driver.owner)
-		return;
-
-	i915_perf_sysctl_unregister();
 	pci_unregister_driver(&i915_pci_driver);
-	i915_globals_exit();
-	i915_pmu_exit();
 }
-
-module_init(i915_init);
-module_exit(i915_exit);
-
-MODULE_AUTHOR("Tungsten Graphics, Inc.");
-MODULE_AUTHOR("Intel Corporation");
-
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/i915_pci.h b/drivers/gpu/drm/i915/i915_pci.h
new file mode 100644
index 000000000000..b386f319f52e
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_pci.h
@@ -0,0 +1,8 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2021 Intel Corporation
+ */
+
+int i915_register_pci_driver(void);
+void i915_unregister_pci_driver(void);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 9f94914958c3..2f01b8c0284c 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1256,7 +1256,6 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 
 	case 8:
 	case 9:
-	case 10:
 		if (intel_engine_uses_guc(ce->engine)) {
 			/*
 			 * When using GuC, the context descriptor we write in
@@ -1284,17 +1283,26 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		break;
 
 	case 11:
-	case 12: {
-		stream->specific_ctx_id_mask =
-			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		/*
-		 * Pick an unused context id
-		 * 0 - BITS_PER_LONG are used by other contexts
-		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
-		 */
-		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+	case 12:
+		if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 50)) {
+			stream->specific_ctx_id_mask =
+				((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
+				(XEHP_SW_CTX_ID_SHIFT - 32);
+			stream->specific_ctx_id =
+				(XEHP_MAX_CONTEXT_HW_ID - 1) <<
+				(XEHP_SW_CTX_ID_SHIFT - 32);
+		} else {
+			stream->specific_ctx_id_mask =
+				((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+			/*
+			 * Pick an unused context id
+			 * 0 - BITS_PER_LONG are used by other contexts
+			 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
+			 */
+			stream->specific_ctx_id =
+				(GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+		}
 		break;
-	}
 
 	default:
 		MISSING_CASE(GRAPHICS_VER(ce->engine->i915));
@@ -2580,7 +2588,7 @@ static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 	intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0);
 }
 
-static void gen10_disable_metric_set(struct i915_perf_stream *stream)
+static void gen11_disable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -3414,10 +3422,10 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		struct drm_i915_file_private *file_priv = file->driver_priv;
 
 		specific_ctx = i915_gem_context_lookup(file_priv, ctx_handle);
-		if (!specific_ctx) {
+		if (IS_ERR(specific_ctx)) {
 			DRM_DEBUG("Failed to look up context with ID %u for opening perf stream\n",
 				  ctx_handle);
-			ret = -ENOENT;
+			ret = PTR_ERR(specific_ctx);
 			goto err;
 		}
 	}
@@ -3887,7 +3895,7 @@ static bool gen8_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 	       REG_IN_RANGE(addr, RPM_CONFIG0, NOA_CONFIG(8));
 }
 
-static bool gen10_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
+static bool gen11_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return gen8_is_valid_mux_addr(perf, addr) ||
 	       REG_EQUAL(addr, GEN10_NOA_WRITE_HIGH) ||
@@ -4310,7 +4318,6 @@ static void oa_init_supported_formats(struct i915_perf *perf)
 	case INTEL_GEMINILAKE:
 	case INTEL_COFFEELAKE:
 	case INTEL_COMETLAKE:
-	case INTEL_CANNONLAKE:
 	case INTEL_ICELAKE:
 	case INTEL_ELKHARTLAKE:
 	case INTEL_JASPERLAKE:
@@ -4395,27 +4402,23 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 				perf->gen8_valid_ctx_bit = BIT(16);
 			}
-		} else if (IS_GRAPHICS_VER(i915, 10, 11)) {
+		} else if (GRAPHICS_VER(i915) == 11) {
 			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
 			perf->ops.is_valid_mux_reg =
-				gen10_is_valid_mux_addr;
+				gen11_is_valid_mux_addr;
 			perf->ops.is_valid_flex_reg =
 				gen8_is_valid_flex_addr;
 
 			perf->ops.oa_enable = gen8_oa_enable;
 			perf->ops.oa_disable = gen8_oa_disable;
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
-			perf->ops.disable_metric_set = gen10_disable_metric_set;
+			perf->ops.disable_metric_set = gen11_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
-			if (GRAPHICS_VER(i915) == 10) {
-				perf->ctx_oactxctrl_offset = 0x128;
-				perf->ctx_flexeu0_offset = 0x3de;
-			} else {
-				perf->ctx_oactxctrl_offset = 0x124;
-				perf->ctx_flexeu0_offset = 0x78e;
-			}
+			perf->ctx_oactxctrl_offset = 0x124;
+			perf->ctx_flexeu0_offset = 0x78e;
+
 			perf->gen8_valid_ctx_bit = BIT(16);
 		} else if (GRAPHICS_VER(i915) == 12) {
 			perf->ops.is_valid_b_counter_reg =
@@ -4483,9 +4486,10 @@ static int destroy_config(int id, void *p, void *data)
 	return 0;
 }
 
-void i915_perf_sysctl_register(void)
+int i915_perf_sysctl_register(void)
 {
 	sysctl_header = register_sysctl_table(dev_root);
+	return 0;
 }
 
 void i915_perf_sysctl_unregister(void)
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 882fdd0a7680..1d1329e5af3a 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -23,7 +23,7 @@ void i915_perf_fini(struct drm_i915_private *i915);
 void i915_perf_register(struct drm_i915_private *i915);
 void i915_perf_unregister(struct drm_i915_private *i915);
 int i915_perf_ioctl_version(void);
-void i915_perf_sysctl_register(void);
+int i915_perf_sysctl_register(void);
 void i915_perf_sysctl_unregister(void);
 
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 34d37d46a126..0b488d49694c 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -407,7 +407,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 
 	if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) {
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ],
-				intel_gpu_freq(rps, rps->cur_freq),
+				intel_rps_get_requested_frequency(rps),
 				period_ns / 1000);
 	}
 
@@ -1088,7 +1088,7 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 
 static enum cpuhp_state cpuhp_slot = CPUHP_INVALID;
 
-void i915_pmu_init(void)
+int i915_pmu_init(void)
 {
 	int ret;
 
@@ -1101,6 +1101,8 @@ void i915_pmu_init(void)
 			  ret);
 	else
 		cpuhp_slot = ret;
+
+	return 0;
 }
 
 void i915_pmu_exit(void)
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 60f9595f902c..449057648f39 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -147,14 +147,14 @@ struct i915_pmu {
 };
 
 #ifdef CONFIG_PERF_EVENTS
-void i915_pmu_init(void);
+int i915_pmu_init(void);
 void i915_pmu_exit(void);
 void i915_pmu_register(struct drm_i915_private *i915);
 void i915_pmu_unregister(struct drm_i915_private *i915);
 void i915_pmu_gt_parked(struct drm_i915_private *i915);
 void i915_pmu_gt_unparked(struct drm_i915_private *i915);
 #else
-static inline void i915_pmu_init(void) {}
+static inline int i915_pmu_init(void) { return 0; }
 static inline void i915_pmu_exit(void) {}
 static inline void i915_pmu_register(struct drm_i915_private *i915) {}
 static inline void i915_pmu_unregister(struct drm_i915_private *i915) {}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 476bb3b9ad11..664970f2bc62 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -395,10 +395,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN11_GRDOM_MEDIA2		(1 << 6)
 #define  GEN11_GRDOM_MEDIA3		(1 << 7)
 #define  GEN11_GRDOM_MEDIA4		(1 << 8)
+#define  GEN11_GRDOM_MEDIA5		(1 << 9)
+#define  GEN11_GRDOM_MEDIA6		(1 << 10)
+#define  GEN11_GRDOM_MEDIA7		(1 << 11)
+#define  GEN11_GRDOM_MEDIA8		(1 << 12)
 #define  GEN11_GRDOM_VECS		(1 << 13)
 #define  GEN11_GRDOM_VECS2		(1 << 14)
+#define  GEN11_GRDOM_VECS3		(1 << 15)
+#define  GEN11_GRDOM_VECS4		(1 << 16)
 #define  GEN11_GRDOM_SFC0		(1 << 17)
 #define  GEN11_GRDOM_SFC1		(1 << 18)
+#define  GEN11_GRDOM_SFC2		(1 << 19)
+#define  GEN11_GRDOM_SFC3		(1 << 20)
 
 #define  GEN11_VCS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << ((instance) >> 1))
 #define  GEN11_VECS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << (instance))
@@ -1877,7 +1885,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define BXT_PORT_CL1CM_DW30(phy)	_BXT_PHY((phy), _PORT_CL1CM_DW30_BC)
 
 /*
- * CNL/ICL Port/COMBO-PHY Registers
+ * ICL Port/COMBO-PHY Registers
  */
 #define _ICL_COMBOPHY_A			0x162000
 #define _ICL_COMBOPHY_B			0x6C000
@@ -1891,11 +1899,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 					      _RKL_COMBOPHY_D, \
 					      _ADL_COMBOPHY_E)
 
-/* CNL/ICL Port CL_DW registers */
+/* ICL Port CL_DW registers */
 #define _ICL_PORT_CL_DW(dw, phy)	(_ICL_COMBOPHY(phy) + \
 					 4 * (dw))
 
-#define CNL_PORT_CL1CM_DW5		_MMIO(0x162014)
 #define ICL_PORT_CL_DW5(phy)		_MMIO(_ICL_PORT_CL_DW(5, phy))
 #define   CL_POWER_DOWN_ENABLE		(1 << 4)
 #define   SUS_CLOCK_CONFIG		(3 << 0)
@@ -1920,19 +1927,16 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define ICL_PORT_CL_DW12(phy)		_MMIO(_ICL_PORT_CL_DW(12, phy))
 #define   ICL_LANE_ENABLE_AUX		(1 << 0)
 
-/* CNL/ICL Port COMP_DW registers */
+/* ICL Port COMP_DW registers */
 #define _ICL_PORT_COMP			0x100
 #define _ICL_PORT_COMP_DW(dw, phy)	(_ICL_COMBOPHY(phy) + \
 					 _ICL_PORT_COMP + 4 * (dw))
 
-#define CNL_PORT_COMP_DW0		_MMIO(0x162100)
 #define ICL_PORT_COMP_DW0(phy)		_MMIO(_ICL_PORT_COMP_DW(0, phy))
 #define   COMP_INIT			(1 << 31)
 
-#define CNL_PORT_COMP_DW1		_MMIO(0x162104)
 #define ICL_PORT_COMP_DW1(phy)		_MMIO(_ICL_PORT_COMP_DW(1, phy))
 
-#define CNL_PORT_COMP_DW3		_MMIO(0x16210c)
 #define ICL_PORT_COMP_DW3(phy)		_MMIO(_ICL_PORT_COMP_DW(3, phy))
 #define   PROCESS_INFO_DOT_0		(0 << 26)
 #define   PROCESS_INFO_DOT_1		(1 << 26)
@@ -1948,38 +1952,11 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define ICL_PORT_COMP_DW8(phy)		_MMIO(_ICL_PORT_COMP_DW(8, phy))
 #define   IREFGEN			(1 << 24)
 
-#define CNL_PORT_COMP_DW9		_MMIO(0x162124)
 #define ICL_PORT_COMP_DW9(phy)		_MMIO(_ICL_PORT_COMP_DW(9, phy))
 
-#define CNL_PORT_COMP_DW10		_MMIO(0x162128)
 #define ICL_PORT_COMP_DW10(phy)		_MMIO(_ICL_PORT_COMP_DW(10, phy))
 
-/* CNL/ICL Port PCS registers */
-#define _CNL_PORT_PCS_DW1_GRP_AE	0x162304
-#define _CNL_PORT_PCS_DW1_GRP_B		0x162384
-#define _CNL_PORT_PCS_DW1_GRP_C		0x162B04
-#define _CNL_PORT_PCS_DW1_GRP_D		0x162B84
-#define _CNL_PORT_PCS_DW1_GRP_F		0x162A04
-#define _CNL_PORT_PCS_DW1_LN0_AE	0x162404
-#define _CNL_PORT_PCS_DW1_LN0_B		0x162604
-#define _CNL_PORT_PCS_DW1_LN0_C		0x162C04
-#define _CNL_PORT_PCS_DW1_LN0_D		0x162E04
-#define _CNL_PORT_PCS_DW1_LN0_F		0x162804
-#define CNL_PORT_PCS_DW1_GRP(phy)	_MMIO(_PICK(phy, \
-						    _CNL_PORT_PCS_DW1_GRP_AE, \
-						    _CNL_PORT_PCS_DW1_GRP_B, \
-						    _CNL_PORT_PCS_DW1_GRP_C, \
-						    _CNL_PORT_PCS_DW1_GRP_D, \
-						    _CNL_PORT_PCS_DW1_GRP_AE, \
-						    _CNL_PORT_PCS_DW1_GRP_F))
-#define CNL_PORT_PCS_DW1_LN0(phy)	_MMIO(_PICK(phy, \
-						    _CNL_PORT_PCS_DW1_LN0_AE, \
-						    _CNL_PORT_PCS_DW1_LN0_B, \
-						    _CNL_PORT_PCS_DW1_LN0_C, \
-						    _CNL_PORT_PCS_DW1_LN0_D, \
-						    _CNL_PORT_PCS_DW1_LN0_AE, \
-						    _CNL_PORT_PCS_DW1_LN0_F))
-
+/* ICL Port PCS registers */
 #define _ICL_PORT_PCS_AUX		0x300
 #define _ICL_PORT_PCS_GRP		0x600
 #define _ICL_PORT_PCS_LN(ln)		(0x800 + (ln) * 0x100)
@@ -1998,34 +1975,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   LATENCY_OPTIM_MASK		(0x3 << 2)
 #define   LATENCY_OPTIM_VAL(x)		((x) << 2)
 
-/* CNL/ICL Port TX registers */
-#define _CNL_PORT_TX_AE_GRP_OFFSET		0x162340
-#define _CNL_PORT_TX_B_GRP_OFFSET		0x1623C0
-#define _CNL_PORT_TX_C_GRP_OFFSET		0x162B40
-#define _CNL_PORT_TX_D_GRP_OFFSET		0x162BC0
-#define _CNL_PORT_TX_F_GRP_OFFSET		0x162A40
-#define _CNL_PORT_TX_AE_LN0_OFFSET		0x162440
-#define _CNL_PORT_TX_B_LN0_OFFSET		0x162640
-#define _CNL_PORT_TX_C_LN0_OFFSET		0x162C40
-#define _CNL_PORT_TX_D_LN0_OFFSET		0x162E40
-#define _CNL_PORT_TX_F_LN0_OFFSET		0x162840
-#define _CNL_PORT_TX_DW_GRP(dw, port)	(_PICK((port), \
-					       _CNL_PORT_TX_AE_GRP_OFFSET, \
-					       _CNL_PORT_TX_B_GRP_OFFSET, \
-					       _CNL_PORT_TX_B_GRP_OFFSET, \
-					       _CNL_PORT_TX_D_GRP_OFFSET, \
-					       _CNL_PORT_TX_AE_GRP_OFFSET, \
-					       _CNL_PORT_TX_F_GRP_OFFSET) + \
-					       4 * (dw))
-#define _CNL_PORT_TX_DW_LN0(dw, port)	(_PICK((port), \
-					       _CNL_PORT_TX_AE_LN0_OFFSET, \
-					       _CNL_PORT_TX_B_LN0_OFFSET, \
-					       _CNL_PORT_TX_B_LN0_OFFSET, \
-					       _CNL_PORT_TX_D_LN0_OFFSET, \
-					       _CNL_PORT_TX_AE_LN0_OFFSET, \
-					       _CNL_PORT_TX_F_LN0_OFFSET) + \
-					       4 * (dw))
-
+/* ICL Port TX registers */
 #define _ICL_PORT_TX_AUX		0x380
 #define _ICL_PORT_TX_GRP		0x680
 #define _ICL_PORT_TX_LN(ln)		(0x880 + (ln) * 0x100)
@@ -2037,8 +1987,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _ICL_PORT_TX_DW_LN(dw, ln, phy) (_ICL_COMBOPHY(phy) + \
 					  _ICL_PORT_TX_LN(ln) + 4 * (dw))
 
-#define CNL_PORT_TX_DW2_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP(2, port))
-#define CNL_PORT_TX_DW2_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0(2, port))
 #define ICL_PORT_TX_DW2_AUX(phy)	_MMIO(_ICL_PORT_TX_DW_AUX(2, phy))
 #define ICL_PORT_TX_DW2_GRP(phy)	_MMIO(_ICL_PORT_TX_DW_GRP(2, phy))
 #define ICL_PORT_TX_DW2_LN0(phy)	_MMIO(_ICL_PORT_TX_DW_LN(2, 0, phy))
@@ -2051,13 +1999,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RCOMP_SCALAR(x)		((x) << 0)
 #define   RCOMP_SCALAR_MASK		(0xFF << 0)
 
-#define _CNL_PORT_TX_DW4_LN0_AE		0x162450
-#define _CNL_PORT_TX_DW4_LN1_AE		0x1624D0
-#define CNL_PORT_TX_DW4_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP(4, (port)))
-#define CNL_PORT_TX_DW4_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0(4, (port)))
-#define CNL_PORT_TX_DW4_LN(ln, port)   _MMIO(_CNL_PORT_TX_DW_LN0(4, (port)) + \
-					   ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \
-						    _CNL_PORT_TX_DW4_LN0_AE)))
 #define ICL_PORT_TX_DW4_AUX(phy)	_MMIO(_ICL_PORT_TX_DW_AUX(4, phy))
 #define ICL_PORT_TX_DW4_GRP(phy)	_MMIO(_ICL_PORT_TX_DW_GRP(4, phy))
 #define ICL_PORT_TX_DW4_LN0(phy)	_MMIO(_ICL_PORT_TX_DW_LN(4, 0, phy))
@@ -2070,8 +2011,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   CURSOR_COEFF(x)		((x) << 0)
 #define   CURSOR_COEFF_MASK		(0x3F << 0)
 
-#define CNL_PORT_TX_DW5_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP(5, port))
-#define CNL_PORT_TX_DW5_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0(5, port))
 #define ICL_PORT_TX_DW5_AUX(phy)	_MMIO(_ICL_PORT_TX_DW_AUX(5, phy))
 #define ICL_PORT_TX_DW5_GRP(phy)	_MMIO(_ICL_PORT_TX_DW_GRP(5, phy))
 #define ICL_PORT_TX_DW5_LN0(phy)	_MMIO(_ICL_PORT_TX_DW_LN(5, 0, phy))
@@ -2083,8 +2022,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RTERM_SELECT(x)		((x) << 3)
 #define   RTERM_SELECT_MASK		(0x7 << 3)
 
-#define CNL_PORT_TX_DW7_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP(7, (port)))
-#define CNL_PORT_TX_DW7_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0(7, (port)))
 #define ICL_PORT_TX_DW7_AUX(phy)	_MMIO(_ICL_PORT_TX_DW_AUX(7, phy))
 #define ICL_PORT_TX_DW7_GRP(phy)	_MMIO(_ICL_PORT_TX_DW_GRP(7, phy))
 #define ICL_PORT_TX_DW7_LN0(phy)	_MMIO(_ICL_PORT_TX_DW_LN(7, 0, phy))
@@ -2278,6 +2215,68 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   MG_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
 #define   MG_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
 
+/*
+ * DG2 SNPS PHY registers (TC1 = PHY_E)
+ */
+#define _SNPS_PHY_A_BASE			0x168000
+#define _SNPS_PHY_B_BASE			0x169000
+#define _SNPS_PHY(phy)				_PHY(phy, \
+						     _SNPS_PHY_A_BASE, \
+						     _SNPS_PHY_B_BASE)
+#define _SNPS2(phy, reg)			(_SNPS_PHY(phy) - \
+						 _SNPS_PHY_A_BASE + (reg))
+#define _MMIO_SNPS(phy, reg)			_MMIO(_SNPS2(phy, reg))
+#define _MMIO_SNPS_LN(ln, phy, reg)		_MMIO(_SNPS2(phy, \
+							     (reg) + (ln) * 0x10))
+
+#define SNPS_PHY_MPLLB_CP(phy)			_MMIO_SNPS(phy, 0x168000)
+#define   SNPS_PHY_MPLLB_CP_INT			REG_GENMASK(31, 25)
+#define   SNPS_PHY_MPLLB_CP_INT_GS		REG_GENMASK(23, 17)
+#define   SNPS_PHY_MPLLB_CP_PROP		REG_GENMASK(15, 9)
+#define   SNPS_PHY_MPLLB_CP_PROP_GS		REG_GENMASK(7, 1)
+
+#define SNPS_PHY_MPLLB_DIV(phy)			_MMIO_SNPS(phy, 0x168004)
+#define   SNPS_PHY_MPLLB_FORCE_EN		REG_BIT(31)
+#define   SNPS_PHY_MPLLB_DIV5_CLK_EN		REG_BIT(29)
+#define   SNPS_PHY_MPLLB_V2I			REG_GENMASK(27, 26)
+#define   SNPS_PHY_MPLLB_FREQ_VCO		REG_GENMASK(25, 24)
+#define   SNPS_PHY_MPLLB_PMIX_EN		REG_BIT(10)
+#define   SNPS_PHY_MPLLB_TX_CLK_DIV		REG_GENMASK(7, 5)
+
+#define SNPS_PHY_MPLLB_FRACN1(phy)		_MMIO_SNPS(phy, 0x168008)
+#define   SNPS_PHY_MPLLB_FRACN_EN		REG_BIT(31)
+#define   SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN	REG_BIT(30)
+#define   SNPS_PHY_MPLLB_FRACN_DEN		REG_GENMASK(15, 0)
+
+#define SNPS_PHY_MPLLB_FRACN2(phy)		_MMIO_SNPS(phy, 0x16800C)
+#define   SNPS_PHY_MPLLB_FRACN_REM		REG_GENMASK(31, 16)
+#define   SNPS_PHY_MPLLB_FRACN_QUOT		REG_GENMASK(15, 0)
+
+#define SNPS_PHY_MPLLB_SSCEN(phy)		_MMIO_SNPS(phy, 0x168014)
+#define   SNPS_PHY_MPLLB_SSC_EN			REG_BIT(31)
+#define   SNPS_PHY_MPLLB_SSC_UP_SPREAD		REG_BIT(30)
+#define   SNPS_PHY_MPLLB_SSC_PEAK		REG_GENMASK(29, 10)
+
+#define SNPS_PHY_MPLLB_SSCSTEP(phy)		_MMIO_SNPS(phy, 0x168018)
+#define   SNPS_PHY_MPLLB_SSC_STEPSIZE		REG_GENMASK(31, 11)
+
+#define SNPS_PHY_MPLLB_DIV2(phy)		_MMIO_SNPS(phy, 0x16801C)
+#define   SNPS_PHY_MPLLB_HDMI_PIXEL_CLK_DIV	REG_GENMASK(19, 18)
+#define   SNPS_PHY_MPLLB_HDMI_DIV		REG_GENMASK(17, 15)
+#define   SNPS_PHY_MPLLB_REF_CLK_DIV		REG_GENMASK(14, 12)
+#define   SNPS_PHY_MPLLB_MULTIPLIER		REG_GENMASK(11, 0)
+
+#define SNPS_PHY_REF_CONTROL(phy)		_MMIO_SNPS(phy, 0x168188)
+#define   SNPS_PHY_REF_CONTROL_REF_RANGE	REG_GENMASK(31, 27)
+
+#define SNPS_PHY_TX_REQ(phy)			_MMIO_SNPS(phy, 0x168200)
+#define   SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR	REG_GENMASK(31, 30)
+
+#define SNPS_PHY_TX_EQ(ln, phy)			_MMIO_SNPS_LN(ln, phy, 0x168300)
+#define   SNPS_PHY_TX_EQ_MAIN			REG_GENMASK(23, 18)
+#define   SNPS_PHY_TX_EQ_POST			REG_GENMASK(15, 10)
+#define   SNPS_PHY_TX_EQ_PRE			REG_GENMASK(7, 2)
+
 /* The spec defines this only for BXT PHY0, but lets assume that this
  * would exist for PHY1 too if it had a second channel.
  */
@@ -2516,9 +2515,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN11_BSD2_RING_BASE	0x1c4000
 #define GEN11_BSD3_RING_BASE	0x1d0000
 #define GEN11_BSD4_RING_BASE	0x1d4000
+#define XEHP_BSD5_RING_BASE	0x1e0000
+#define XEHP_BSD6_RING_BASE	0x1e4000
+#define XEHP_BSD7_RING_BASE	0x1f0000
+#define XEHP_BSD8_RING_BASE	0x1f4000
 #define VEBOX_RING_BASE		0x1a000
 #define GEN11_VEBOX_RING_BASE		0x1c8000
 #define GEN11_VEBOX2_RING_BASE		0x1d8000
+#define XEHP_VEBOX3_RING_BASE		0x1e8000
+#define XEHP_VEBOX4_RING_BASE		0x1f8000
 #define BLT_RING_BASE		0x22000
 #define RING_TAIL(base)		_MMIO((base) + 0x30)
 #define RING_HEAD(base)		_MMIO((base) + 0x34)
@@ -2572,7 +2577,16 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ARB_MODE_BWGTLB_DISABLE (1 << 9)
 #define   ARB_MODE_SWIZZLE_BDW	(1 << 1)
 #define RENDER_HWS_PGA_GEN7	_MMIO(0x04080)
-#define RING_FAULT_REG(engine)	_MMIO(0x4094 + 0x100 * (engine)->hw_id)
+
+#define _RING_FAULT_REG_RCS        0x4094
+#define _RING_FAULT_REG_VCS        0x4194
+#define _RING_FAULT_REG_BCS        0x4294
+#define _RING_FAULT_REG_VECS       0x4394
+#define RING_FAULT_REG(engine)     _MMIO(_PICK((engine)->class, \
+					       _RING_FAULT_REG_RCS, \
+					       _RING_FAULT_REG_VCS, \
+					       _RING_FAULT_REG_VECS, \
+					       _RING_FAULT_REG_BCS))
 #define GEN8_RING_FAULT_REG	_MMIO(0x4094)
 #define GEN12_RING_FAULT_REG	_MMIO(0xcec4)
 #define   GEN8_RING_FAULT_ENGINE_ID(x)	(((x) >> 12) & 0x7)
@@ -2672,6 +2686,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN12_SC_INSTDONE_EXTRA2	_MMIO(0x7108)
 #define GEN7_SAMPLER_INSTDONE	_MMIO(0xe160)
 #define GEN7_ROW_INSTDONE	_MMIO(0xe164)
+#define MCFG_MCR_SELECTOR		_MMIO(0xfd0)
+#define SF_MCR_SELECTOR			_MMIO(0xfd8)
 #define GEN8_MCR_SELECTOR		_MMIO(0xfdc)
 #define   GEN8_MCR_SLICE(slice)		(((slice) & 3) << 26)
 #define   GEN8_MCR_SLICE_MASK		GEN8_MCR_SLICE(3)
@@ -3099,6 +3115,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define	GEN10_MIRROR_FUSE3		_MMIO(0x9118)
 #define GEN10_L3BANK_PAIR_COUNT     4
 #define GEN10_L3BANK_MASK   0x0F
+/* on Xe_HP the same fuses indicates mslices instead of L3 banks */
+#define GEN12_MAX_MSLICES 4
+#define GEN12_MEML3_EN_MASK 0x0F
 
 #define GEN8_EU_DISABLE0		_MMIO(0x9134)
 #define   GEN8_EU_DIS0_S0_MASK		0xffffff
@@ -3133,6 +3152,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN12_GT_DSS_ENABLE _MMIO(0x913C)
 
+#define XEHP_EU_ENABLE			_MMIO(0x9134)
+#define XEHP_EU_ENA_MASK		0xFF
+
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	_MMIO(0x12050)
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN6_BSD_SLEEP_FLUSH_DISABLE	(1 << 2)
@@ -4086,6 +4108,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define BXT_GT_PERF_STATUS      _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7070)
 #define GEN6_RP_STATE_LIMITS	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
 #define GEN6_RP_STATE_CAP	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
+#define   RP0_CAP_MASK		REG_GENMASK(7, 0)
+#define   RP1_CAP_MASK		REG_GENMASK(15, 8)
+#define   RPN_CAP_MASK		REG_GENMASK(23, 16)
 #define BXT_RP_STATE_CAP        _MMIO(0x138170)
 #define GEN9_RP_STATE_LIMITS	_MMIO(0x138148)
 
@@ -4142,6 +4167,7 @@ enum {
 	FAULT_AND_CONTINUE /* Unsupported */
 };
 
+#define CTX_GTT_ADDRESS_MASK GENMASK(31, 12)
 #define GEN8_CTX_VALID (1 << 0)
 #define GEN8_CTX_FORCE_PD_RESTORE (1 << 1)
 #define GEN8_CTX_FORCE_RESTORE (1 << 2)
@@ -4158,6 +4184,11 @@ enum {
 #define GEN11_ENGINE_INSTANCE_SHIFT 48
 #define GEN11_ENGINE_INSTANCE_WIDTH 6
 
+#define XEHP_SW_CTX_ID_SHIFT 39
+#define XEHP_SW_CTX_ID_WIDTH 16
+#define XEHP_SW_COUNTER_SHIFT 58
+#define XEHP_SW_COUNTER_WIDTH 6
+
 #define CHV_CLK_CTL1			_MMIO(0x101100)
 #define VLV_CLK_CTL2			_MMIO(0x101104)
 #define   CLK_CTL2_CZCOUNT_30NS_SHIFT	28
@@ -4586,23 +4617,26 @@ enum {
 #define _PSR2_CTL_EDP				0x6f900
 #define EDP_PSR2_CTL(tran)			_MMIO_TRANS2(tran, _PSR2_CTL_A)
 #define   EDP_PSR2_ENABLE			(1 << 31)
-#define   EDP_SU_TRACK_ENABLE			(1 << 30)
+#define   EDP_SU_TRACK_ENABLE			(1 << 30) /* up to adl-p */
 #define   TGL_EDP_PSR2_BLOCK_COUNT_NUM_2	(0 << 28)
 #define   TGL_EDP_PSR2_BLOCK_COUNT_NUM_3	(1 << 28)
 #define   EDP_Y_COORDINATE_ENABLE		REG_BIT(25) /* display 10, 11 and 12 */
+#define   EDP_PSR2_SU_SDP_SCANLINE		REG_BIT(25) /* display 13+ */
 #define   EDP_MAX_SU_DISABLE_TIME(t)		((t) << 20)
 #define   EDP_MAX_SU_DISABLE_TIME_MASK		(0x1f << 20)
 #define   EDP_PSR2_IO_BUFFER_WAKE_MAX_LINES	8
 #define   EDP_PSR2_IO_BUFFER_WAKE(lines)	((EDP_PSR2_IO_BUFFER_WAKE_MAX_LINES - (lines)) << 13)
 #define   EDP_PSR2_IO_BUFFER_WAKE_MASK		(3 << 13)
 #define   TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES	5
-#define   TGL_EDP_PSR2_IO_BUFFER_WAKE(lines)	(((lines) - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES) << 13)
+#define   TGL_EDP_PSR2_IO_BUFFER_WAKE_SHIFT	13
+#define   TGL_EDP_PSR2_IO_BUFFER_WAKE(lines)	(((lines) - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES) << TGL_EDP_PSR2_IO_BUFFER_WAKE_SHIFT)
 #define   TGL_EDP_PSR2_IO_BUFFER_WAKE_MASK	(7 << 13)
 #define   EDP_PSR2_FAST_WAKE_MAX_LINES		8
 #define   EDP_PSR2_FAST_WAKE(lines)		((EDP_PSR2_FAST_WAKE_MAX_LINES - (lines)) << 11)
 #define   EDP_PSR2_FAST_WAKE_MASK		(3 << 11)
 #define   TGL_EDP_PSR2_FAST_WAKE_MIN_LINES	5
-#define   TGL_EDP_PSR2_FAST_WAKE(lines)		(((lines) - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES) << 10)
+#define   TGL_EDP_PSR2_FAST_WAKE_MIN_SHIFT	10
+#define   TGL_EDP_PSR2_FAST_WAKE(lines)		(((lines) - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES) << TGL_EDP_PSR2_FAST_WAKE_MIN_SHIFT)
 #define   TGL_EDP_PSR2_FAST_WAKE_MASK		(7 << 10)
 #define   EDP_PSR2_TP2_TIME_500us		(0 << 8)
 #define   EDP_PSR2_TP2_TIME_100us		(1 << 8)
@@ -4652,17 +4686,23 @@ enum {
 #define PSR2_SU_STATUS_MASK(frame)	(0x3ff << PSR2_SU_STATUS_SHIFT(frame))
 #define PSR2_SU_STATUS_FRAMES		8
 
-#define _PSR2_MAN_TRK_CTL_A				0x60910
-#define _PSR2_MAN_TRK_CTL_EDP				0x6f910
-#define PSR2_MAN_TRK_CTL(tran)				_MMIO_TRANS2(tran, _PSR2_MAN_TRK_CTL_A)
-#define  PSR2_MAN_TRK_CTL_ENABLE			REG_BIT(31)
-#define  PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK	REG_GENMASK(30, 21)
-#define  PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(val)	REG_FIELD_PREP(PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK, val)
+#define _PSR2_MAN_TRK_CTL_A					0x60910
+#define _PSR2_MAN_TRK_CTL_EDP					0x6f910
+#define PSR2_MAN_TRK_CTL(tran)					_MMIO_TRANS2(tran, _PSR2_MAN_TRK_CTL_A)
+#define  PSR2_MAN_TRK_CTL_ENABLE				REG_BIT(31)
+#define  PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK		REG_GENMASK(30, 21)
+#define  PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(val)		REG_FIELD_PREP(PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK, val)
 #define  PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK		REG_GENMASK(20, 11)
 #define  PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(val)		REG_FIELD_PREP(PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK, val)
-#define  PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME		REG_BIT(3)
-#define  PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME	REG_BIT(2)
-#define  PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE	REG_BIT(1)
+#define  PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME			REG_BIT(3)
+#define  PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME		REG_BIT(2)
+#define  PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE		REG_BIT(1)
+#define  ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK	REG_GENMASK(28, 16)
+#define  ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(val)	REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK, val)
+#define  ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK		REG_GENMASK(12, 0)
+#define  ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(val)		REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK, val)
+#define  ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME		REG_BIT(14)
+#define  ADLP_PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME		REG_BIT(13)
 
 /* Icelake DSC Rate Control Range Parameter Registers */
 #define DSCA_RC_RANGE_PARAMETERS_0		_MMIO(0x6B240)
@@ -7717,11 +7757,11 @@ enum {
 #define SKL_PS_ECC_STAT(pipe, id)  _MMIO_PIPE(pipe,     \
 			_ID(id, _PS_ECC_STAT_1A, _PS_ECC_STAT_2A),   \
 			_ID(id, _PS_ECC_STAT_1B, _PS_ECC_STAT_2B))
-#define CNL_PS_COEF_INDEX_SET(pipe, id, set)  _MMIO_PIPE(pipe,    \
+#define GLK_PS_COEF_INDEX_SET(pipe, id, set)  _MMIO_PIPE(pipe,    \
 			_ID(id, _PS_COEF_SET0_INDEX_1A, _PS_COEF_SET0_INDEX_2A) + (set) * 8, \
 			_ID(id, _PS_COEF_SET0_INDEX_1B, _PS_COEF_SET0_INDEX_2B) + (set) * 8)
 
-#define CNL_PS_COEF_DATA_SET(pipe, id, set)  _MMIO_PIPE(pipe,     \
+#define GLK_PS_COEF_DATA_SET(pipe, id, set)  _MMIO_PIPE(pipe,     \
 			_ID(id, _PS_COEF_SET0_DATA_1A, _PS_COEF_SET0_DATA_2A) + (set) * 8, \
 			_ID(id, _PS_COEF_SET0_DATA_1B, _PS_COEF_SET0_DATA_2B) + (set) * 8)
 /* legacy palette */
@@ -7757,7 +7797,7 @@ enum {
 #define  GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED	(3 << 0) /* icl + */
 
 /* DMC */
-#define DMC_PROGRAM(i)		_MMIO(0x80000 + (i) * 4)
+#define DMC_PROGRAM(addr, i)	_MMIO((addr) + (i) * 4)
 #define DMC_SSP_BASE_ADDR_GEN9	0x00002FC0
 #define DMC_HTP_ADDR_SKL	0x00500034
 #define DMC_SSP_BASE		_MMIO(0x8F074)
@@ -7936,7 +7976,7 @@ enum {
 #define  DSI1_NON_TE			(1 << 31)
 #define  DSI0_NON_TE			(1 << 30)
 #define  ICL_AUX_CHANNEL_E		(1 << 29)
-#define  CNL_AUX_CHANNEL_F		(1 << 28)
+#define  ICL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
 #define  GEN9_AUX_CHANNEL_B		(1 << 25)
@@ -7988,9 +8028,9 @@ enum {
 #define  GEN11_GT_DW1_IRQ		(1 << 1)
 #define  GEN11_GT_DW0_IRQ		(1 << 0)
 
-#define DG1_MSTR_UNIT_INTR		_MMIO(0x190008)
+#define DG1_MSTR_TILE_INTR		_MMIO(0x190008)
 #define   DG1_MSTR_IRQ			REG_BIT(31)
-#define   DG1_MSTR_UNIT(u)		REG_BIT(u)
+#define   DG1_MSTR_TILE(t)		REG_BIT(t)
 
 #define GEN11_DISPLAY_INT_CTL		_MMIO(0x44200)
 #define  GEN11_DISPLAY_IRQ_ENABLE	(1 << 31)
@@ -8073,7 +8113,10 @@ enum {
 #define GEN11_BCS_RSVD_INTR_MASK	_MMIO(0x1900a0)
 #define GEN11_VCS0_VCS1_INTR_MASK	_MMIO(0x1900a8)
 #define GEN11_VCS2_VCS3_INTR_MASK	_MMIO(0x1900ac)
+#define GEN12_VCS4_VCS5_INTR_MASK	_MMIO(0x1900b0)
+#define GEN12_VCS6_VCS7_INTR_MASK	_MMIO(0x1900b4)
 #define GEN11_VECS0_VECS1_INTR_MASK	_MMIO(0x1900d0)
+#define GEN12_VECS2_VECS3_INTR_MASK	_MMIO(0x1900d4)
 #define GEN11_GUC_SG_INTR_MASK		_MMIO(0x1900e8)
 #define GEN11_GPM_WGBOXPERF_INTR_MASK	_MMIO(0x1900ec)
 #define GEN11_CRYPTO_RSVD_INTR_MASK	_MMIO(0x1900f0)
@@ -8113,6 +8156,7 @@ enum {
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
 #define CHICKEN_PAR1_1			_MMIO(0x42080)
+#define  IGNORE_KVMR_PIPE_A		REG_BIT(23)
 #define  KBL_ARB_FILL_SPARE_22		REG_BIT(22)
 #define  DIS_RAM_BYPASS_PSR2_MAN_TRACK	(1 << 16)
 #define  SKL_DE_COMPRESSED_HASH_MODE	(1 << 15)
@@ -8125,7 +8169,6 @@ enum {
 #define  KVM_CONFIG_CHANGE_NOTIFICATION_SELECT	(1 << 14)
 
 #define CHICKEN_MISC_2		_MMIO(0x42084)
-#define  CNL_COMP_PWR_DOWN	(1 << 23)
 #define  KBL_ARB_FILL_SPARE_14	REG_BIT(14)
 #define  KBL_ARB_FILL_SPARE_13	REG_BIT(13)
 #define  GLK_CL2_PWR_DOWN	(1 << 12)
@@ -8163,15 +8206,16 @@ enum {
 					    [TRANSCODER_B] = _CHICKEN_TRANS_B, \
 					    [TRANSCODER_C] = _CHICKEN_TRANS_C, \
 					    [TRANSCODER_D] = _CHICKEN_TRANS_D))
-#define  HSW_FRAME_START_DELAY_MASK	(3 << 27)
-#define  HSW_FRAME_START_DELAY(x)	((x) << 27) /* 0-3 */
-#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
-#define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
-#define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
-#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1 << 17) /* CHICKEN_TRANS_A only */
-#define  DDIE_TRAINING_OVERRIDE_VALUE	(1 << 16) /* CHICKEN_TRANS_A only */
-#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1 << 15)
-#define  PSR2_VSC_ENABLE_PROG_HEADER    (1 << 12)
+#define  HSW_FRAME_START_DELAY_MASK	REG_GENMASK(28, 27)
+#define  HSW_FRAME_START_DELAY(x)	REG_FIELD_PREP(HSW_FRAME_START_DELAY_MASK, x)
+#define  VSC_DATA_SEL_SOFTWARE_CONTROL	REG_BIT(25) /* GLK */
+#define  FECSTALL_DIS_DPTSTREAM_DPTTG	REG_BIT(23)
+#define  DDI_TRAINING_OVERRIDE_ENABLE	REG_BIT(19)
+#define  DDI_TRAINING_OVERRIDE_VALUE	REG_BIT(18)
+#define  DDIE_TRAINING_OVERRIDE_ENABLE	REG_BIT(17) /* CHICKEN_TRANS_A only */
+#define  DDIE_TRAINING_OVERRIDE_VALUE	REG_BIT(16) /* CHICKEN_TRANS_A only */
+#define  PSR2_ADD_VERTICAL_LINE_COUNT	REG_BIT(15)
+#define  PSR2_VSC_ENABLE_PROG_HEADER	REG_BIT(12)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
 #define  DISP_FBC_MEMORY_WAKE		(1 << 31)
@@ -8229,9 +8273,8 @@ enum {
 
 #define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
 #define   SKL_SELECT_ALTERNATE_DC_EXIT	(1 << 30)
-#define   CNL_DELAY_PMRSP		(1 << 22)
+#define   ICL_DELAY_PMRSP		(1 << 22)
 #define   MASK_WAKEMEM			(1 << 13)
-#define   CNL_DDI_CLOCK_REG_ACCESS_ON	(1 << 7)
 
 #define GEN11_CHICKEN_DCPR_2			_MMIO(0x46434)
 #define   DCPR_MASK_MAXLATENCY_MEMUP_CLR	REG_BIT(27)
@@ -8252,10 +8295,9 @@ enum {
 #define   SKL_DFSM_PIPE_B_DISABLE	(1 << 21)
 #define   SKL_DFSM_PIPE_C_DISABLE	(1 << 28)
 #define   TGL_DFSM_PIPE_D_DISABLE	(1 << 22)
-#define   CNL_DFSM_DISPLAY_DSC_DISABLE	(1 << 7)
+#define   GLK_DFSM_DISPLAY_DSC_DISABLE	(1 << 7)
 
 #define SKL_DSSM				_MMIO(0x51004)
-#define CNL_DSSM_CDCLK_PLL_REFCLK_24MHz		(1 << 31)
 #define ICL_DSSM_CDCLK_PLL_REFCLK_MASK		(7 << 29)
 #define ICL_DSSM_CDCLK_PLL_REFCLK_24MHz		(0 << 29)
 #define ICL_DSSM_CDCLK_PLL_REFCLK_19_2MHz	(1 << 29)
@@ -8354,7 +8396,6 @@ enum {
 
 /* GEN8 chicken */
 #define HDC_CHICKEN0				_MMIO(0x7300)
-#define CNL_HDC_CHICKEN0			_MMIO(0xE5F0)
 #define ICL_HDC_MODE				_MMIO(0xE5F4)
 #define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1 << 15)
 #define  HDC_FENCE_DEST_SLM_DISABLE		(1 << 14)
@@ -8388,7 +8429,8 @@ enum {
 #define _PIPEC_CHICKEN				0x72038
 #define PIPE_CHICKEN(pipe)			_MMIO_PIPE(pipe, _PIPEA_CHICKEN,\
 							   _PIPEB_CHICKEN)
-#define   UNDERRUN_RECOVERY_DISABLE		REG_BIT(30)
+#define   UNDERRUN_RECOVERY_DISABLE_ADLP	REG_BIT(30)
+#define   UNDERRUN_RECOVERY_ENABLE_DG2		REG_BIT(30)
 #define   PIXEL_ROUNDING_TRUNC_FB_PASSTHRU 	(1 << 15)
 #define   PER_PIXEL_ALPHA_BYPASS_EN		(1 << 7)
 
@@ -9200,6 +9242,8 @@ enum {
 #define   GEN9_FREQUENCY(x)			((x) << 23)
 #define   GEN6_OFFSET(x)			((x) << 19)
 #define   GEN6_AGGRESSIVE_TURBO			(0 << 15)
+#define   GEN9_SW_REQ_UNSLICE_RATIO_SHIFT	23
+
 #define GEN6_RC_VIDEO_FREQ			_MMIO(0xA00C)
 #define GEN6_RC_CONTROL				_MMIO(0xA090)
 #define   GEN6_RC_CTL_RC6pp_ENABLE		(1 << 16)
@@ -9368,9 +9412,13 @@ enum {
 #define   ICL_PCODE_MEM_SUBSYSYSTEM_INFO	0xd
 #define     ICL_PCODE_MEM_SS_READ_GLOBAL_INFO	(0x0 << 8)
 #define     ICL_PCODE_MEM_SS_READ_QGV_POINT_INFO(point)	(((point) << 16) | (0x1 << 8))
+#define     ADL_PCODE_MEM_SS_READ_PSF_GV_INFO	((0) | (0x2 << 8))
 #define   ICL_PCODE_SAGV_DE_MEM_SS_CONFIG	0xe
 #define     ICL_PCODE_POINTS_RESTRICTED		0x0
-#define     ICL_PCODE_POINTS_RESTRICTED_MASK	0x1
+#define     ICL_PCODE_POINTS_RESTRICTED_MASK	0xf
+#define   ADLS_PSF_PT_SHIFT			8
+#define   ADLS_QGV_PT_MASK			REG_GENMASK(7, 0)
+#define   ADLS_PSF_PT_MASK			REG_GENMASK(10, 8)
 #define   GEN6_PCODE_READ_D_COMP		0x10
 #define   GEN6_PCODE_WRITE_D_COMP		0x11
 #define   ICL_PCODE_EXIT_TCCOLD			0x12
@@ -9530,7 +9578,6 @@ enum {
 #define   HSW_SAMPLE_C_PERFORMANCE	(1 << 9)
 #define   GEN8_CENTROID_PIXEL_OPT_DIS	(1 << 8)
 #define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
-#define   CNL_FAST_ANISO_L1_BANKING_FIX	(1 << 4)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1 << 1)
 
 #define GEN9_HALF_SLICE_CHICKEN7	_MMIO(0xe194)
@@ -9711,15 +9758,12 @@ enum {
 /* HSW/BDW power well */
 #define   HSW_PW_CTL_IDX_GLOBAL			15
 
-/* SKL/BXT/GLK/CNL power wells */
+/* SKL/BXT/GLK power wells */
 #define   SKL_PW_CTL_IDX_PW_2			15
 #define   SKL_PW_CTL_IDX_PW_1			14
-#define   CNL_PW_CTL_IDX_AUX_F			12
-#define   CNL_PW_CTL_IDX_AUX_D			11
 #define   GLK_PW_CTL_IDX_AUX_C			10
 #define   GLK_PW_CTL_IDX_AUX_B			9
 #define   GLK_PW_CTL_IDX_AUX_A			8
-#define   CNL_PW_CTL_IDX_DDI_F			6
 #define   SKL_PW_CTL_IDX_DDI_D			4
 #define   SKL_PW_CTL_IDX_DDI_C			3
 #define   SKL_PW_CTL_IDX_DDI_B			2
@@ -9818,19 +9862,6 @@ enum skl_power_gate {
 	((pw_idx) - ICL_PW_CTL_IDX_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
 
-#define _CNL_AUX_REG_IDX(pw_idx)	((pw_idx) - GLK_PW_CTL_IDX_AUX_B)
-#define _CNL_AUX_ANAOVRD1_B		0x162250
-#define _CNL_AUX_ANAOVRD1_C		0x162210
-#define _CNL_AUX_ANAOVRD1_D		0x1622D0
-#define _CNL_AUX_ANAOVRD1_F		0x162A90
-#define CNL_AUX_ANAOVRD1(pw_idx)	_MMIO(_PICK(_CNL_AUX_REG_IDX(pw_idx), \
-						    _CNL_AUX_ANAOVRD1_B, \
-						    _CNL_AUX_ANAOVRD1_C, \
-						    _CNL_AUX_ANAOVRD1_D, \
-						    _CNL_AUX_ANAOVRD1_F))
-#define   CNL_AUX_ANAOVRD1_ENABLE	(1 << 16)
-#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1 << 23)
-
 #define _ICL_AUX_REG_IDX(pw_idx)	((pw_idx) - ICL_PW_CTL_IDX_AUX_A)
 #define _ICL_AUX_ANAOVRD1_A		0x162398
 #define _ICL_AUX_ANAOVRD1_B		0x6C398
@@ -10130,11 +10161,11 @@ enum skl_power_gate {
 #define  TRANS_DDI_BPC_10		(1 << 20)
 #define  TRANS_DDI_BPC_6		(2 << 20)
 #define  TRANS_DDI_BPC_12		(3 << 20)
-#define  TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK	REG_GENMASK(19, 18) /* bdw-cnl */
+#define  TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK	REG_GENMASK(19, 18)
 #define  TRANS_DDI_PORT_SYNC_MASTER_SELECT(x)	REG_FIELD_PREP(TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK, (x))
 #define  TRANS_DDI_PVSYNC		(1 << 17)
 #define  TRANS_DDI_PHSYNC		(1 << 16)
-#define  TRANS_DDI_PORT_SYNC_ENABLE	REG_BIT(15) /* bdw-cnl */
+#define  TRANS_DDI_PORT_SYNC_ENABLE	REG_BIT(15)
 #define  TRANS_DDI_EDP_INPUT_MASK	(7 << 12)
 #define  TRANS_DDI_EDP_INPUT_A_ON	(0 << 12)
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
@@ -10167,6 +10198,9 @@ enum skl_power_gate {
 #define  PORT_SYNC_MODE_MASTER_SELECT_MASK	REG_GENMASK(2, 0)
 #define  PORT_SYNC_MODE_MASTER_SELECT(x)	REG_FIELD_PREP(PORT_SYNC_MODE_MASTER_SELECT_MASK, (x))
 
+#define TRANS_CMTG_CHICKEN		_MMIO(0x6fa90)
+#define  DISABLE_DPT_CLK_GATING		REG_BIT(1)
+
 /* DisplayPort Transport Control */
 #define _DP_TP_CTL_A			0x64040
 #define _DP_TP_CTL_B			0x64140
@@ -10371,6 +10405,14 @@ enum skl_power_gate {
 #define TRANS_MSA_MISC(tran) _MMIO_TRANS2(tran, _TRANSA_MSA_MISC)
 /* See DP_MSA_MISC_* for the bit definitions */
 
+#define _TRANS_A_SET_CONTEXT_LATENCY		0x6007C
+#define _TRANS_B_SET_CONTEXT_LATENCY		0x6107C
+#define _TRANS_C_SET_CONTEXT_LATENCY		0x6207C
+#define _TRANS_D_SET_CONTEXT_LATENCY		0x6307C
+#define TRANS_SET_CONTEXT_LATENCY(tran)		_MMIO_TRANS2(tran, _TRANS_A_SET_CONTEXT_LATENCY)
+#define  TRANS_SET_CONTEXT_LATENCY_MASK		REG_GENMASK(15, 0)
+#define  TRANS_SET_CONTEXT_LATENCY_VALUE(x)	REG_FIELD_PREP(TRANS_SET_CONTEXT_LATENCY_MASK, (x))
+
 /* LCPLL Control */
 #define LCPLL_CTL			_MMIO(0x130040)
 #define  LCPLL_PLL_DISABLE		(1 << 31)
@@ -10482,17 +10524,6 @@ enum skl_power_gate {
 #define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
 #define DPLL_CFGCR2(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR2, _DPLL2_CFGCR2)
 
-/*
- * CNL Clocks
- */
-#define DPCLKA_CFGCR0				_MMIO(0x6C200)
-#define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port) ==  PORT_F ? 23 : \
-						      (port) + 10))
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port) == PORT_F ? 21 : \
-						(port) * 2)
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)	(3 << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL(pll, port)	((pll) << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
-
 /* ICL Clocks */
 #define ICL_DPCLKA_CFGCR0			_MMIO(0x164280)
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)	(1 << _PICK(phy, 10, 11, 24, 4, 5))
@@ -10548,7 +10579,7 @@ enum skl_power_gate {
 							ADLS_DPCLKA_DDIJ_SEL_MASK, \
 							ADLS_DPCLKA_DDIK_SEL_MASK)
 
-/* CNL PLL */
+/* ICL PLL */
 #define DPLL0_ENABLE		0x46010
 #define DPLL1_ENABLE		0x46014
 #define _ADLS_DPLL2_ENABLE	0x46018
@@ -10557,9 +10588,14 @@ enum skl_power_gate {
 #define  PLL_LOCK		(1 << 30)
 #define  PLL_POWER_ENABLE	(1 << 27)
 #define  PLL_POWER_STATE	(1 << 26)
-#define CNL_DPLL_ENABLE(pll)	_MMIO_PLL3(pll, DPLL0_ENABLE, DPLL1_ENABLE, \
+#define ICL_DPLL_ENABLE(pll)	_MMIO_PLL3(pll, DPLL0_ENABLE, DPLL1_ENABLE, \
 					   _ADLS_DPLL2_ENABLE, _ADLS_DPLL3_ENABLE)
 
+#define _DG2_PLL3_ENABLE	0x4601C
+
+#define DG2_PLL_ENABLE(pll) _MMIO_PLL3(pll, DPLL0_ENABLE, DPLL1_ENABLE, \
+				       _ADLS_DPLL2_ENABLE, _DG2_PLL3_ENABLE)
+
 #define TBT_PLL_ENABLE		_MMIO(0x46020)
 
 #define _MG_PLL1_ENABLE		0x46030
@@ -10725,60 +10761,52 @@ enum skl_power_gate {
 						   _MG_PLL_TDC_COLDST_BIAS_PORT1, \
 						   _MG_PLL_TDC_COLDST_BIAS_PORT2)
 
-#define _CNL_DPLL0_CFGCR0		0x6C000
-#define _CNL_DPLL1_CFGCR0		0x6C080
-#define  DPLL_CFGCR0_HDMI_MODE		(1 << 30)
-#define  DPLL_CFGCR0_SSC_ENABLE		(1 << 29)
-#define  DPLL_CFGCR0_SSC_ENABLE_ICL	(1 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_MASK	(0xf << 25)
-#define  DPLL_CFGCR0_LINK_RATE_2700	(0 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_1350	(1 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_810	(2 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_1620	(3 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_1080	(4 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_2160	(5 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_3240	(6 << 25)
-#define  DPLL_CFGCR0_LINK_RATE_4050	(7 << 25)
-#define  DPLL_CFGCR0_DCO_FRACTION_MASK	(0x7fff << 10)
-#define  DPLL_CFGCR0_DCO_FRACTION_SHIFT	(10)
-#define  DPLL_CFGCR0_DCO_FRACTION(x)	((x) << 10)
-#define  DPLL_CFGCR0_DCO_INTEGER_MASK	(0x3ff)
-#define CNL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _CNL_DPLL0_CFGCR0, _CNL_DPLL1_CFGCR0)
-
-#define _CNL_DPLL0_CFGCR1		0x6C004
-#define _CNL_DPLL1_CFGCR1		0x6C084
-#define  DPLL_CFGCR1_QDIV_RATIO_MASK	(0xff << 10)
-#define  DPLL_CFGCR1_QDIV_RATIO_SHIFT	(10)
-#define  DPLL_CFGCR1_QDIV_RATIO(x)	((x) << 10)
-#define  DPLL_CFGCR1_QDIV_MODE_SHIFT	(9)
-#define  DPLL_CFGCR1_QDIV_MODE(x)	((x) << 9)
-#define  DPLL_CFGCR1_KDIV_MASK		(7 << 6)
-#define  DPLL_CFGCR1_KDIV_SHIFT		(6)
-#define  DPLL_CFGCR1_KDIV(x)		((x) << 6)
-#define  DPLL_CFGCR1_KDIV_1		(1 << 6)
-#define  DPLL_CFGCR1_KDIV_2		(2 << 6)
-#define  DPLL_CFGCR1_KDIV_3		(4 << 6)
-#define  DPLL_CFGCR1_PDIV_MASK		(0xf << 2)
-#define  DPLL_CFGCR1_PDIV_SHIFT		(2)
-#define  DPLL_CFGCR1_PDIV(x)		((x) << 2)
-#define  DPLL_CFGCR1_PDIV_2		(1 << 2)
-#define  DPLL_CFGCR1_PDIV_3		(2 << 2)
-#define  DPLL_CFGCR1_PDIV_5		(4 << 2)
-#define  DPLL_CFGCR1_PDIV_7		(8 << 2)
-#define  DPLL_CFGCR1_CENTRAL_FREQ	(3 << 0)
-#define  DPLL_CFGCR1_CENTRAL_FREQ_8400	(3 << 0)
-#define  TGL_DPLL_CFGCR1_CFSELOVRD_NORMAL_XTAL	(0 << 0)
-#define CNL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _CNL_DPLL0_CFGCR1, _CNL_DPLL1_CFGCR1)
-
 #define _ICL_DPLL0_CFGCR0		0x164000
 #define _ICL_DPLL1_CFGCR0		0x164080
 #define ICL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _ICL_DPLL0_CFGCR0, \
 						  _ICL_DPLL1_CFGCR0)
+#define   DPLL_CFGCR0_HDMI_MODE		(1 << 30)
+#define   DPLL_CFGCR0_SSC_ENABLE	(1 << 29)
+#define   DPLL_CFGCR0_SSC_ENABLE_ICL	(1 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_MASK	(0xf << 25)
+#define   DPLL_CFGCR0_LINK_RATE_2700	(0 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_1350	(1 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_810	(2 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_1620	(3 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_1080	(4 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_2160	(5 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_3240	(6 << 25)
+#define   DPLL_CFGCR0_LINK_RATE_4050	(7 << 25)
+#define   DPLL_CFGCR0_DCO_FRACTION_MASK	(0x7fff << 10)
+#define   DPLL_CFGCR0_DCO_FRACTION_SHIFT	(10)
+#define   DPLL_CFGCR0_DCO_FRACTION(x)	((x) << 10)
+#define   DPLL_CFGCR0_DCO_INTEGER_MASK	(0x3ff)
 
 #define _ICL_DPLL0_CFGCR1		0x164004
 #define _ICL_DPLL1_CFGCR1		0x164084
 #define ICL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _ICL_DPLL0_CFGCR1, \
 						  _ICL_DPLL1_CFGCR1)
+#define   DPLL_CFGCR1_QDIV_RATIO_MASK	(0xff << 10)
+#define   DPLL_CFGCR1_QDIV_RATIO_SHIFT	(10)
+#define   DPLL_CFGCR1_QDIV_RATIO(x)	((x) << 10)
+#define   DPLL_CFGCR1_QDIV_MODE_SHIFT	(9)
+#define   DPLL_CFGCR1_QDIV_MODE(x)	((x) << 9)
+#define   DPLL_CFGCR1_KDIV_MASK		(7 << 6)
+#define   DPLL_CFGCR1_KDIV_SHIFT		(6)
+#define   DPLL_CFGCR1_KDIV(x)		((x) << 6)
+#define   DPLL_CFGCR1_KDIV_1		(1 << 6)
+#define   DPLL_CFGCR1_KDIV_2		(2 << 6)
+#define   DPLL_CFGCR1_KDIV_3		(4 << 6)
+#define   DPLL_CFGCR1_PDIV_MASK		(0xf << 2)
+#define   DPLL_CFGCR1_PDIV_SHIFT		(2)
+#define   DPLL_CFGCR1_PDIV(x)		((x) << 2)
+#define   DPLL_CFGCR1_PDIV_2		(1 << 2)
+#define   DPLL_CFGCR1_PDIV_3		(2 << 2)
+#define   DPLL_CFGCR1_PDIV_5		(4 << 2)
+#define   DPLL_CFGCR1_PDIV_7		(8 << 2)
+#define   DPLL_CFGCR1_CENTRAL_FREQ	(3 << 0)
+#define   DPLL_CFGCR1_CENTRAL_FREQ_8400	(3 << 0)
+#define   TGL_DPLL_CFGCR1_CFSELOVRD_NORMAL_XTAL	(0 << 0)
 
 #define _TGL_DPLL0_CFGCR0		0x164284
 #define _TGL_DPLL1_CFGCR0		0x16428C
@@ -10998,8 +11026,8 @@ enum skl_power_gate {
 #define   BXT_DE_PLL_LOCK		(1 << 30)
 #define   BXT_DE_PLL_FREQ_REQ		(1 << 23)
 #define   BXT_DE_PLL_FREQ_REQ_ACK	(1 << 22)
-#define   CNL_CDCLK_PLL_RATIO(x)	(x)
-#define   CNL_CDCLK_PLL_RATIO_MASK	0xff
+#define   ICL_CDCLK_PLL_RATIO(x)	(x)
+#define   ICL_CDCLK_PLL_RATIO_MASK	0xff
 
 /* GEN9 DC */
 #define DC_STATE_EN			_MMIO(0x45504)
@@ -11054,6 +11082,7 @@ enum skl_power_gate {
 #define SKL_MEMORY_FREQ_MULTIPLIER_HZ		266666666
 #define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5E04)
 #define  SKL_REQ_DATA_MASK			(0xF << 0)
+#define  DG1_GEAR_TYPE				REG_BIT(16)
 
 #define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000)
 #define  SKL_DRAM_DDR_TYPE_MASK			(0x3 << 0)
@@ -11076,18 +11105,29 @@ enum skl_power_gate {
 #define  SKL_DRAM_RANK_1			(0x0 << 10)
 #define  SKL_DRAM_RANK_2			(0x1 << 10)
 #define  SKL_DRAM_RANK_MASK			(0x1 << 10)
-#define  CNL_DRAM_SIZE_MASK			0x7F
-#define  CNL_DRAM_WIDTH_MASK			(0x3 << 7)
-#define  CNL_DRAM_WIDTH_SHIFT			7
-#define  CNL_DRAM_WIDTH_X8			(0x0 << 7)
-#define  CNL_DRAM_WIDTH_X16			(0x1 << 7)
-#define  CNL_DRAM_WIDTH_X32			(0x2 << 7)
-#define  CNL_DRAM_RANK_MASK			(0x3 << 9)
-#define  CNL_DRAM_RANK_SHIFT			9
-#define  CNL_DRAM_RANK_1			(0x0 << 9)
-#define  CNL_DRAM_RANK_2			(0x1 << 9)
-#define  CNL_DRAM_RANK_3			(0x2 << 9)
-#define  CNL_DRAM_RANK_4			(0x3 << 9)
+#define  ICL_DRAM_SIZE_MASK			0x7F
+#define  ICL_DRAM_WIDTH_MASK			(0x3 << 7)
+#define  ICL_DRAM_WIDTH_SHIFT			7
+#define  ICL_DRAM_WIDTH_X8			(0x0 << 7)
+#define  ICL_DRAM_WIDTH_X16			(0x1 << 7)
+#define  ICL_DRAM_WIDTH_X32			(0x2 << 7)
+#define  ICL_DRAM_RANK_MASK			(0x3 << 9)
+#define  ICL_DRAM_RANK_SHIFT			9
+#define  ICL_DRAM_RANK_1			(0x0 << 9)
+#define  ICL_DRAM_RANK_2			(0x1 << 9)
+#define  ICL_DRAM_RANK_3			(0x2 << 9)
+#define  ICL_DRAM_RANK_4			(0x3 << 9)
+
+#define SA_PERF_STATUS_0_0_0_MCHBAR_PC		_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5918)
+#define  DG1_QCLK_RATIO_MASK			REG_GENMASK(9, 2)
+#define  DG1_QCLK_REFERENCE			REG_BIT(10)
+
+#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4000)
+#define   DG1_DRAM_T_RDPRE_MASK			REG_GENMASK(16, 11)
+#define   DG1_DRAM_T_RP_MASK			REG_GENMASK(6, 0)
+#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR_HIGH	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4004)
+#define   DG1_DRAM_T_RCD_MASK			REG_GENMASK(15, 9)
+#define   DG1_DRAM_T_RAS_MASK			REG_GENMASK(8, 1)
 
 /*
  * Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
@@ -12290,6 +12330,7 @@ enum skl_power_gate {
 
 /* MOCS (Memory Object Control State) registers */
 #define GEN9_LNCFCMOCS(i)	_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
+#define GEN9_LNCFCMOCS_REG_COUNT	32
 
 #define __GEN9_RCS0_MOCS0	0xc800
 #define GEN9_GFX_MOCS(i)	_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
@@ -12337,6 +12378,7 @@ enum skl_power_gate {
 						 _ICL_PHY_MISC_B)
 #define  ICL_PHY_MISC_MUX_DDID			(1 << 28)
 #define  ICL_PHY_MISC_DE_IO_COMP_PWR_DOWN	(1 << 23)
+#define  DG2_PHY_DP_TX_ACK_MASK			REG_GENMASK(23, 20)
 
 /* Icelake Display Stream Compression Registers */
 #define DSCA_PICTURE_PARAMETER_SET_0		_MMIO(0x6B200)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 37aef1308573..ce446716d092 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -42,22 +42,17 @@
 
 #include "i915_active.h"
 #include "i915_drv.h"
-#include "i915_globals.h"
 #include "i915_trace.h"
 #include "intel_pm.h"
 
 struct execute_cb {
 	struct irq_work work;
 	struct i915_sw_fence *fence;
-	void (*hook)(struct i915_request *rq, struct dma_fence *signal);
 	struct i915_request *signal;
 };
 
-static struct i915_global_request {
-	struct i915_global base;
-	struct kmem_cache *slab_requests;
-	struct kmem_cache *slab_execute_cbs;
-} global;
+static struct kmem_cache *slab_requests;
+static struct kmem_cache *slab_execute_cbs;
 
 static const char *i915_fence_get_driver_name(struct dma_fence *fence)
 {
@@ -108,13 +103,16 @@ static signed long i915_fence_wait(struct dma_fence *fence,
 
 struct kmem_cache *i915_request_slab_cache(void)
 {
-	return global.slab_requests;
+	return slab_requests;
 }
 
 static void i915_fence_release(struct dma_fence *fence)
 {
 	struct i915_request *rq = to_request(fence);
 
+	GEM_BUG_ON(rq->guc_prio != GUC_PRIO_INIT &&
+		   rq->guc_prio != GUC_PRIO_FINI);
+
 	/*
 	 * The request is put onto a RCU freelist (i.e. the address
 	 * is immediately reused), mark the fences as being freed now.
@@ -126,41 +124,19 @@ static void i915_fence_release(struct dma_fence *fence)
 	i915_sw_fence_fini(&rq->semaphore);
 
 	/*
-	 * Keep one request on each engine for reserved use under mempressure
-	 *
-	 * We do not hold a reference to the engine here and so have to be
-	 * very careful in what rq->engine we poke. The virtual engine is
-	 * referenced via the rq->context and we released that ref during
-	 * i915_request_retire(), ergo we must not dereference a virtual
-	 * engine here. Not that we would want to, as the only consumer of
-	 * the reserved engine->request_pool is the power management parking,
-	 * which must-not-fail, and that is only run on the physical engines.
-	 *
-	 * Since the request must have been executed to be have completed,
-	 * we know that it will have been processed by the HW and will
-	 * not be unsubmitted again, so rq->engine and rq->execution_mask
-	 * at this point is stable. rq->execution_mask will be a single
-	 * bit if the last and _only_ engine it could execution on was a
-	 * physical engine, if it's multiple bits then it started on and
-	 * could still be on a virtual engine. Thus if the mask is not a
-	 * power-of-two we assume that rq->engine may still be a virtual
-	 * engine and so a dangling invalid pointer that we cannot dereference
-	 *
-	 * For example, consider the flow of a bonded request through a virtual
-	 * engine. The request is created with a wide engine mask (all engines
-	 * that we might execute on). On processing the bond, the request mask
-	 * is reduced to one or more engines. If the request is subsequently
-	 * bound to a single engine, it will then be constrained to only
-	 * execute on that engine and never returned to the virtual engine
-	 * after timeslicing away, see __unwind_incomplete_requests(). Thus we
-	 * know that if the rq->execution_mask is a single bit, rq->engine
-	 * can be a physical engine with the exact corresponding mask.
+	 * Keep one request on each engine for reserved use under mempressure,
+	 * do not use with virtual engines as this really is only needed for
+	 * kernel contexts.
 	 */
-	if (is_power_of_2(rq->execution_mask) &&
-	    !cmpxchg(&rq->engine->request_pool, NULL, rq))
+	if (!intel_engine_is_virtual(rq->engine) &&
+	    !cmpxchg(&rq->engine->request_pool, NULL, rq)) {
+		intel_context_put(rq->context);
 		return;
+	}
+
+	intel_context_put(rq->context);
 
-	kmem_cache_free(global.slab_requests, rq);
+	kmem_cache_free(slab_requests, rq);
 }
 
 const struct dma_fence_ops i915_fence_ops = {
@@ -177,18 +153,7 @@ static void irq_execute_cb(struct irq_work *wrk)
 	struct execute_cb *cb = container_of(wrk, typeof(*cb), work);
 
 	i915_sw_fence_complete(cb->fence);
-	kmem_cache_free(global.slab_execute_cbs, cb);
-}
-
-static void irq_execute_cb_hook(struct irq_work *wrk)
-{
-	struct execute_cb *cb = container_of(wrk, typeof(*cb), work);
-
-	cb->hook(container_of(cb->fence, struct i915_request, submit),
-		 &cb->signal->fence);
-	i915_request_put(cb->signal);
-
-	irq_execute_cb(wrk);
+	kmem_cache_free(slab_execute_cbs, cb);
 }
 
 static __always_inline void
@@ -216,7 +181,7 @@ static bool irq_work_imm(struct irq_work *wrk)
 	return false;
 }
 
-static void __notify_execute_cb_imm(struct i915_request *rq)
+void i915_request_notify_execute_cb_imm(struct i915_request *rq)
 {
 	__notify_execute_cb(rq, irq_work_imm);
 }
@@ -272,11 +237,11 @@ i915_request_active_engine(struct i915_request *rq,
 	 * check that we have acquired the lock on the final engine.
 	 */
 	locked = READ_ONCE(rq->engine);
-	spin_lock_irq(&locked->active.lock);
+	spin_lock_irq(&locked->sched_engine->lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
-		spin_unlock(&locked->active.lock);
+		spin_unlock(&locked->sched_engine->lock);
 		locked = engine;
-		spin_lock(&locked->active.lock);
+		spin_lock(&locked->sched_engine->lock);
 	}
 
 	if (i915_request_is_active(rq)) {
@@ -285,42 +250,11 @@ i915_request_active_engine(struct i915_request *rq,
 		ret = true;
 	}
 
-	spin_unlock_irq(&locked->active.lock);
+	spin_unlock_irq(&locked->sched_engine->lock);
 
 	return ret;
 }
 
-
-static void remove_from_engine(struct i915_request *rq)
-{
-	struct intel_engine_cs *engine, *locked;
-
-	/*
-	 * Virtual engines complicate acquiring the engine timeline lock,
-	 * as their rq->engine pointer is not stable until under that
-	 * engine lock. The simple ploy we use is to take the lock then
-	 * check that the rq still belongs to the newly locked engine.
-	 */
-	locked = READ_ONCE(rq->engine);
-	spin_lock_irq(&locked->active.lock);
-	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
-		spin_unlock(&locked->active.lock);
-		spin_lock(&engine->active.lock);
-		locked = engine;
-	}
-	list_del_init(&rq->sched.link);
-
-	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
-
-	/* Prevent further __await_execution() registering a cb, then flush */
-	set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
-
-	spin_unlock_irq(&locked->active.lock);
-
-	__notify_execute_cb_imm(rq);
-}
-
 static void __rq_init_watchdog(struct i915_request *rq)
 {
 	rq->watchdog.timer.function = NULL;
@@ -417,8 +351,7 @@ bool i915_request_retire(struct i915_request *rq)
 	 * after removing the breadcrumb and signaling it, so that we do not
 	 * inadvertently attach the breadcrumb to a completed request.
 	 */
-	if (!list_empty(&rq->sched.link))
-		remove_from_engine(rq);
+	rq->engine->remove_active_request(rq);
 	GEM_BUG_ON(!llist_empty(&rq->execute_cb));
 
 	__list_del_entry(&rq->link); /* poison neither prev/next (RCU walks) */
@@ -443,6 +376,7 @@ void i915_request_retire_upto(struct i915_request *rq)
 
 	do {
 		tmp = list_first_entry(&tl->requests, typeof(*tmp), link);
+		GEM_BUG_ON(!i915_request_completed(tmp));
 	} while (i915_request_retire(tmp) && tmp != rq);
 }
 
@@ -517,19 +451,14 @@ static bool __request_in_flight(const struct i915_request *signal)
 static int
 __await_execution(struct i915_request *rq,
 		  struct i915_request *signal,
-		  void (*hook)(struct i915_request *rq,
-			       struct dma_fence *signal),
 		  gfp_t gfp)
 {
 	struct execute_cb *cb;
 
-	if (i915_request_is_active(signal)) {
-		if (hook)
-			hook(rq, &signal->fence);
+	if (i915_request_is_active(signal))
 		return 0;
-	}
 
-	cb = kmem_cache_alloc(global.slab_execute_cbs, gfp);
+	cb = kmem_cache_alloc(slab_execute_cbs, gfp);
 	if (!cb)
 		return -ENOMEM;
 
@@ -537,12 +466,6 @@ __await_execution(struct i915_request *rq,
 	i915_sw_fence_await(cb->fence);
 	init_irq_work(&cb->work, irq_execute_cb);
 
-	if (hook) {
-		cb->hook = hook;
-		cb->signal = i915_request_get(signal);
-		cb->work.func = irq_execute_cb_hook;
-	}
-
 	/*
 	 * Register the callback first, then see if the signaler is already
 	 * active. This ensures that if we race with the
@@ -559,7 +482,7 @@ __await_execution(struct i915_request *rq,
 	if (llist_add(&cb->work.node.llist, &signal->execute_cb)) {
 		if (i915_request_is_active(signal) ||
 		    __request_in_flight(signal))
-			__notify_execute_cb_imm(signal);
+			i915_request_notify_execute_cb_imm(signal);
 	}
 
 	return 0;
@@ -637,7 +560,7 @@ bool __i915_request_submit(struct i915_request *request)
 	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
-	lockdep_assert_held(&engine->active.lock);
+	lockdep_assert_held(&engine->sched_engine->lock);
 
 	/*
 	 * With the advent of preempt-to-busy, we frequently encounter
@@ -649,7 +572,7 @@ bool __i915_request_submit(struct i915_request *request)
 	 *
 	 * We must remove the request from the caller's priority queue,
 	 * and the caller must only call us when the request is in their
-	 * priority queue, under the active.lock. This ensures that the
+	 * priority queue, under the sched_engine->lock. This ensures that the
 	 * request has *not* yet been retired and we can safely move
 	 * the request into the engine->active.list where it will be
 	 * dropped upon retiring. (Otherwise if resubmit a *retired*
@@ -690,11 +613,15 @@ bool __i915_request_submit(struct i915_request *request)
 				     request->ring->vaddr + request->postfix);
 
 	trace_i915_request_execute(request);
-	engine->serial++;
+	if (engine->bump_serial)
+		engine->bump_serial(engine);
+	else
+		engine->serial++;
+
 	result = true;
 
 	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	list_move_tail(&request->sched.link, &engine->active.requests);
+	engine->add_active_request(request);
 active:
 	clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
 	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
@@ -724,11 +651,11 @@ void i915_request_submit(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	__i915_request_submit(request);
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 void __i915_request_unsubmit(struct i915_request *request)
@@ -742,7 +669,7 @@ void __i915_request_unsubmit(struct i915_request *request)
 	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
-	lockdep_assert_held(&engine->active.lock);
+	lockdep_assert_held(&engine->sched_engine->lock);
 
 	/*
 	 * Before we remove this breadcrumb from the signal list, we have
@@ -775,23 +702,11 @@ void i915_request_unsubmit(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 
 	__i915_request_unsubmit(request);
 
-	spin_unlock_irqrestore(&engine->active.lock, flags);
-}
-
-static void __cancel_request(struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = NULL;
-
-	i915_request_active_engine(rq, &engine);
-
-	if (engine && intel_engine_pulse(engine))
-		intel_gt_handle_error(engine->gt, engine->mask, 0,
-				      "request cancellation by %s",
-				      current->comm);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 }
 
 void i915_request_cancel(struct i915_request *rq, int error)
@@ -801,7 +716,7 @@ void i915_request_cancel(struct i915_request *rq, int error)
 
 	set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
 
-	__cancel_request(rq);
+	intel_context_cancel_request(rq->context, rq);
 }
 
 static int __i915_sw_fence_call
@@ -889,7 +804,7 @@ request_alloc_slow(struct intel_timeline *tl,
 	rq = list_first_entry(&tl->requests, typeof(*rq), link);
 	i915_request_retire(rq);
 
-	rq = kmem_cache_alloc(global.slab_requests,
+	rq = kmem_cache_alloc(slab_requests,
 			      gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (rq)
 		return rq;
@@ -902,7 +817,7 @@ request_alloc_slow(struct intel_timeline *tl,
 	retire_requests(tl);
 
 out:
-	return kmem_cache_alloc(global.slab_requests, gfp);
+	return kmem_cache_alloc(slab_requests, gfp);
 }
 
 static void __i915_request_ctor(void *arg)
@@ -963,7 +878,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	 *
 	 * Do not use kmem_cache_zalloc() here!
 	 */
-	rq = kmem_cache_alloc(global.slab_requests,
+	rq = kmem_cache_alloc(slab_requests,
 			      gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (unlikely(!rq)) {
 		rq = request_alloc_slow(tl, &ce->engine->request_pool, gfp);
@@ -973,7 +888,19 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 		}
 	}
 
-	rq->context = ce;
+	/*
+	 * Hold a reference to the intel_context over life of an i915_request.
+	 * Without this an i915_request can exist after the context has been
+	 * destroyed (e.g. request retired, context closed, but user space holds
+	 * a reference to the request from an out fence). In the case of GuC
+	 * submission + virtual engine, the engine that the request references
+	 * is also destroyed which can trigger bad pointer dref in fence ops
+	 * (e.g. i915_fence_get_driver_name). We could likely change these
+	 * functions to avoid touching the engine but let's just be safe and
+	 * hold the intel_context reference. In execlist mode the request always
+	 * eventually points to a physical engine so this isn't an issue.
+	 */
+	rq->context = intel_context_get(ce);
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
@@ -996,6 +923,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
+	rq->guc_prio = GUC_PRIO_INIT;
+
 	/* We bump the ref for the fence chain */
 	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
 	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
@@ -1050,7 +979,8 @@ err_unwind:
 	GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
 
 err_free:
-	kmem_cache_free(global.slab_requests, rq);
+	intel_context_put(ce);
+	kmem_cache_free(slab_requests, rq);
 err_unreserve:
 	intel_context_unpin(ce);
 	return ERR_PTR(ret);
@@ -1253,7 +1183,7 @@ emit_semaphore_wait(struct i915_request *to,
 		goto await_fence;
 
 	/* Only submit our spinner after the signaler is running! */
-	if (__await_execution(to, from, NULL, gfp))
+	if (__await_execution(to, from, gfp))
 		goto await_fence;
 
 	if (__emit_semaphore_wait(to, from, from->fence.seqno))
@@ -1284,16 +1214,14 @@ static int intel_timeline_sync_set_start(struct intel_timeline *tl,
 
 static int
 __i915_request_await_execution(struct i915_request *to,
-			       struct i915_request *from,
-			       void (*hook)(struct i915_request *rq,
-					    struct dma_fence *signal))
+			       struct i915_request *from)
 {
 	int err;
 
 	GEM_BUG_ON(intel_context_is_barrier(from->context));
 
 	/* Submit both requests at the same time */
-	err = __await_execution(to, from, hook, I915_FENCE_GFP);
+	err = __await_execution(to, from, I915_FENCE_GFP);
 	if (err)
 		return err;
 
@@ -1343,7 +1271,7 @@ __i915_request_await_execution(struct i915_request *to,
 	}
 
 	/* Couple the dependency tree for PI on this exposed to->fence */
-	if (to->engine->schedule) {
+	if (to->engine->sched_engine->schedule) {
 		err = i915_sched_node_add_dependency(&to->sched,
 						     &from->sched,
 						     I915_DEPENDENCY_WEAK);
@@ -1406,9 +1334,7 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
 
 int
 i915_request_await_execution(struct i915_request *rq,
-			     struct dma_fence *fence,
-			     void (*hook)(struct i915_request *rq,
-					  struct dma_fence *signal))
+			     struct dma_fence *fence)
 {
 	struct dma_fence **child = &fence;
 	unsigned int nchild = 1;
@@ -1439,8 +1365,7 @@ i915_request_await_execution(struct i915_request *rq,
 
 		if (dma_fence_is_i915(fence))
 			ret = __i915_request_await_execution(rq,
-							     to_request(fence),
-							     hook);
+							     to_request(fence));
 		else
 			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
@@ -1466,7 +1391,7 @@ await_request_submit(struct i915_request *to, struct i915_request *from)
 							&from->submit,
 							I915_FENCE_GFP);
 	else
-		return __i915_request_await_execution(to, from, NULL);
+		return __i915_request_await_execution(to, from);
 }
 
 static int
@@ -1482,7 +1407,7 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 		return 0;
 	}
 
-	if (to->engine->schedule) {
+	if (to->engine->sched_engine->schedule) {
 		ret = i915_sched_node_add_dependency(&to->sched,
 						     &from->sched,
 						     I915_DEPENDENCY_EXTERNAL);
@@ -1490,7 +1415,8 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 			return ret;
 	}
 
-	if (is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask)))
+	if (!intel_engine_uses_guc(to->engine) &&
+	    is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask)))
 		ret = await_request_submit(to, from);
 	else
 		ret = emit_semaphore_wait(to, from, I915_FENCE_GFP);
@@ -1649,6 +1575,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	prev = to_request(__i915_active_fence_set(&timeline->last_request,
 						  &rq->fence));
 	if (prev && !__i915_request_is_complete(prev)) {
+		bool uses_guc = intel_engine_uses_guc(rq->engine);
+
 		/*
 		 * The requests are supposed to be kept in order. However,
 		 * we need to be wary in case the timeline->last_request
@@ -1659,7 +1587,9 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 			   i915_seqno_passed(prev->fence.seqno,
 					     rq->fence.seqno));
 
-		if (is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask))
+		if ((!uses_guc &&
+		     is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) ||
+		    (uses_guc && prev->context == rq->context))
 			i915_sw_fence_await_sw_fence(&rq->submit,
 						     &prev->submit,
 						     &rq->submitq);
@@ -1667,7 +1597,7 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 			__i915_sw_fence_await_dma_fence(&rq->submit,
 							&prev->fence,
 							&rq->dmaq);
-		if (rq->engine->schedule)
+		if (rq->engine->sched_engine->schedule)
 			__i915_sched_node_add_dependency(&rq->sched,
 							 &prev->sched,
 							 &rq->dep,
@@ -1739,8 +1669,8 @@ void __i915_request_queue(struct i915_request *rq,
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	if (attr && rq->engine->schedule)
-		rq->engine->schedule(rq, attr);
+	if (attr && rq->engine->sched_engine->schedule)
+		rq->engine->sched_engine->schedule(rq, attr);
 
 	local_bh_disable();
 	__i915_request_queue_bh(rq);
@@ -2100,31 +2030,61 @@ void i915_request_show(struct drm_printer *m,
 		   name);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_request.c"
-#include "selftests/i915_request.c"
-#endif
+static bool engine_match_ring(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	u32 ring = ENGINE_READ(engine, RING_START);
+
+	return ring == i915_ggtt_offset(rq->ring->vma);
+}
 
-static void i915_global_request_shrink(void)
+static bool match_ring(struct i915_request *rq)
 {
-	kmem_cache_shrink(global.slab_execute_cbs);
-	kmem_cache_shrink(global.slab_requests);
+	struct intel_engine_cs *engine;
+	bool found;
+	int i;
+
+	if (!intel_engine_is_virtual(rq->engine))
+		return engine_match_ring(rq->engine, rq);
+
+	found = false;
+	i = 0;
+	while ((engine = intel_engine_get_sibling(rq->engine, i++))) {
+		found = engine_match_ring(engine, rq);
+		if (found)
+			break;
+	}
+
+	return found;
 }
 
-static void i915_global_request_exit(void)
+enum i915_request_state i915_test_request_state(struct i915_request *rq)
 {
-	kmem_cache_destroy(global.slab_execute_cbs);
-	kmem_cache_destroy(global.slab_requests);
+	if (i915_request_completed(rq))
+		return I915_REQUEST_COMPLETE;
+
+	if (!i915_request_started(rq))
+		return I915_REQUEST_PENDING;
+
+	if (match_ring(rq))
+		return I915_REQUEST_ACTIVE;
+
+	return I915_REQUEST_QUEUED;
 }
 
-static struct i915_global_request global = { {
-	.shrink = i915_global_request_shrink,
-	.exit = i915_global_request_exit,
-} };
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/mock_request.c"
+#include "selftests/i915_request.c"
+#endif
+
+void i915_request_module_exit(void)
+{
+	kmem_cache_destroy(slab_execute_cbs);
+	kmem_cache_destroy(slab_requests);
+}
 
-int __init i915_global_request_init(void)
+int __init i915_request_module_init(void)
 {
-	global.slab_requests =
+	slab_requests =
 		kmem_cache_create("i915_request",
 				  sizeof(struct i915_request),
 				  __alignof__(struct i915_request),
@@ -2132,20 +2092,19 @@ int __init i915_global_request_init(void)
 				  SLAB_RECLAIM_ACCOUNT |
 				  SLAB_TYPESAFE_BY_RCU,
 				  __i915_request_ctor);
-	if (!global.slab_requests)
+	if (!slab_requests)
 		return -ENOMEM;
 
-	global.slab_execute_cbs = KMEM_CACHE(execute_cb,
+	slab_execute_cbs = KMEM_CACHE(execute_cb,
 					     SLAB_HWCACHE_ALIGN |
 					     SLAB_RECLAIM_ACCOUNT |
 					     SLAB_TYPESAFE_BY_RCU);
-	if (!global.slab_execute_cbs)
+	if (!slab_execute_cbs)
 		goto err_requests;
 
-	i915_global_register(&global.base);
 	return 0;
 
 err_requests:
-	kmem_cache_destroy(global.slab_requests);
+	kmem_cache_destroy(slab_requests);
 	return -ENOMEM;
 }
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 270f6cd37650..1bc1349ba3c2 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -285,6 +285,23 @@ struct i915_request {
 		struct hrtimer timer;
 	} watchdog;
 
+	/*
+	 * Requests may need to be stalled when using GuC submission waiting for
+	 * certain GuC operations to complete. If that is the case, stalled
+	 * requests are added to a per context list of stalled requests. The
+	 * below list_head is the link in that list.
+	 */
+	struct list_head guc_fence_link;
+
+	/**
+	 * Priority level while the request is inflight. Differs from i915
+	 * scheduler priority. See comment above
+	 * I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP for details.
+	 */
+#define	GUC_PRIO_INIT	0xff
+#define	GUC_PRIO_FINI	0xfe
+	u8 guc_prio;
+
 	I915_SELFTEST_DECLARE(struct {
 		struct list_head link;
 		unsigned long delay;
@@ -352,9 +369,7 @@ int i915_request_await_object(struct i915_request *to,
 int i915_request_await_dma_fence(struct i915_request *rq,
 				 struct dma_fence *fence);
 int i915_request_await_execution(struct i915_request *rq,
-				 struct dma_fence *fence,
-				 void (*hook)(struct i915_request *rq,
-					      struct dma_fence *signal));
+				 struct dma_fence *fence);
 
 void i915_request_add(struct i915_request *rq);
 
@@ -613,7 +628,7 @@ i915_request_active_timeline(const struct i915_request *rq)
 	 * this submission.
 	 */
 	return rcu_dereference_protected(rq->timeline,
-					 lockdep_is_held(&rq->engine->active.lock));
+					 lockdep_is_held(&rq->engine->sched_engine->lock));
 }
 
 static inline u32
@@ -641,4 +656,19 @@ bool
 i915_request_active_engine(struct i915_request *rq,
 			   struct intel_engine_cs **active);
 
+void i915_request_notify_execute_cb_imm(struct i915_request *rq);
+
+enum i915_request_state {
+	I915_REQUEST_UNKNOWN = 0,
+	I915_REQUEST_COMPLETE,
+	I915_REQUEST_PENDING,
+	I915_REQUEST_QUEUED,
+	I915_REQUEST_ACTIVE,
+};
+
+enum i915_request_state i915_test_request_state(struct i915_request *rq);
+
+void i915_request_module_exit(void);
+int i915_request_module_init(void);
+
 #endif /* I915_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 69e9e6c3135e..4a6712dca838 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -6,6 +6,9 @@
 
 #include "i915_scatterlist.h"
 
+#include "i915_buddy.h"
+#include "i915_ttm_buddy_manager.h"
+
 #include <drm/drm_mm.h>
 
 #include <linux/slab.h>
@@ -104,6 +107,83 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
 	return st;
 }
 
+/**
+ * i915_sg_from_buddy_resource - Create an sg_table from a struct
+ * i915_buddy_block list
+ * @res: The struct i915_ttm_buddy_resource.
+ * @region_start: An offset to add to the dma addresses of the sg list.
+ *
+ * Create a struct sg_table, initializing it from struct i915_buddy_block list,
+ * taking a maximum segment length into account, splitting into segments
+ * if necessary.
+ *
+ * Return: A pointer to a kmalloced struct sg_table on success, negative
+ * error code cast to an error pointer on failure.
+ */
+struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
+					     u64 region_start)
+{
+	struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
+	const u64 size = res->num_pages << PAGE_SHIFT;
+	const u64 max_segment = rounddown(UINT_MAX, PAGE_SIZE);
+	struct i915_buddy_mm *mm = bman_res->mm;
+	struct list_head *blocks = &bman_res->blocks;
+	struct i915_buddy_block *block;
+	struct scatterlist *sg;
+	struct sg_table *st;
+	resource_size_t prev_end;
+
+	GEM_BUG_ON(list_empty(blocks));
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return ERR_PTR(-ENOMEM);
+
+	if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) {
+		kfree(st);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	sg = st->sgl;
+	st->nents = 0;
+	prev_end = (resource_size_t)-1;
+
+	list_for_each_entry(block, blocks, link) {
+		u64 block_size, offset;
+
+		block_size = min_t(u64, size, i915_buddy_block_size(mm, block));
+		offset = i915_buddy_block_offset(block);
+
+		while (block_size) {
+			u64 len;
+
+			if (offset != prev_end || sg->length >= max_segment) {
+				if (st->nents)
+					sg = __sg_next(sg);
+
+				sg_dma_address(sg) = region_start + offset;
+				sg_dma_len(sg) = 0;
+				sg->length = 0;
+				st->nents++;
+			}
+
+			len = min(block_size, max_segment - sg->length);
+			sg->length += len;
+			sg_dma_len(sg) += len;
+
+			offset += len;
+			block_size -= len;
+
+			prev_end = offset;
+		}
+	}
+
+	sg_mark_end(sg);
+	i915_sg_trim(st);
+
+	return st;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/scatterlist.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 5acca45ea981..b8bd5925b03f 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -14,6 +14,7 @@
 #include "i915_gem.h"
 
 struct drm_mm_node;
+struct ttm_resource;
 
 /*
  * Optimised SGL iterator for GEM objects
@@ -145,4 +146,8 @@ bool i915_sg_trim(struct sg_table *orig_st);
 
 struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
 				      u64 region_start);
+
+struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
+					     u64 region_start);
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index efa638c3acc7..762127dd56c5 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -7,15 +7,11 @@
 #include <linux/mutex.h>
 
 #include "i915_drv.h"
-#include "i915_globals.h"
 #include "i915_request.h"
 #include "i915_scheduler.h"
 
-static struct i915_global_scheduler {
-	struct i915_global base;
-	struct kmem_cache *slab_dependencies;
-	struct kmem_cache *slab_priorities;
-} global;
+static struct kmem_cache *slab_dependencies;
+static struct kmem_cache *slab_priorities;
 
 static DEFINE_SPINLOCK(schedule_lock);
 
@@ -40,7 +36,7 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 	return rb_entry(rb, struct i915_priolist, node);
 }
 
-static void assert_priolists(struct intel_engine_execlists * const execlists)
+static void assert_priolists(struct i915_sched_engine * const sched_engine)
 {
 	struct rb_node *rb;
 	long last_prio;
@@ -48,11 +44,11 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
 
-	GEM_BUG_ON(rb_first_cached(&execlists->queue) !=
-		   rb_first(&execlists->queue.rb_root));
+	GEM_BUG_ON(rb_first_cached(&sched_engine->queue) !=
+		   rb_first(&sched_engine->queue.rb_root));
 
 	last_prio = INT_MAX;
-	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&sched_engine->queue); rb; rb = rb_next(rb)) {
 		const struct i915_priolist *p = to_priolist(rb);
 
 		GEM_BUG_ON(p->priority > last_prio);
@@ -61,23 +57,22 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 }
 
 struct list_head *
-i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
+i915_sched_lookup_priolist(struct i915_sched_engine *sched_engine, int prio)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_priolist *p;
 	struct rb_node **parent, *rb;
 	bool first = true;
 
-	lockdep_assert_held(&engine->active.lock);
-	assert_priolists(execlists);
+	lockdep_assert_held(&sched_engine->lock);
+	assert_priolists(sched_engine);
 
-	if (unlikely(execlists->no_priolist))
+	if (unlikely(sched_engine->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
 
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_root.rb_node;
+	parent = &sched_engine->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -92,9 +87,9 @@ find_priolist:
 	}
 
 	if (prio == I915_PRIORITY_NORMAL) {
-		p = &execlists->default_priolist;
+		p = &sched_engine->default_priolist;
 	} else {
-		p = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
+		p = kmem_cache_alloc(slab_priorities, GFP_ATOMIC);
 		/* Convert an allocation failure to a priority bump */
 		if (unlikely(!p)) {
 			prio = I915_PRIORITY_NORMAL; /* recurses just once */
@@ -107,7 +102,7 @@ find_priolist:
 			 * requests, so if userspace lied about their
 			 * dependencies that reordering may be visible.
 			 */
-			execlists->no_priolist = true;
+			sched_engine->no_priolist = true;
 			goto find_priolist;
 		}
 	}
@@ -116,27 +111,27 @@ find_priolist:
 	INIT_LIST_HEAD(&p->requests);
 
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color_cached(&p->node, &execlists->queue, first);
+	rb_insert_color_cached(&p->node, &sched_engine->queue, first);
 
 	return &p->requests;
 }
 
 void __i915_priolist_free(struct i915_priolist *p)
 {
-	kmem_cache_free(global.slab_priorities, p);
+	kmem_cache_free(slab_priorities, p);
 }
 
 struct sched_cache {
 	struct list_head *priolist;
 };
 
-static struct intel_engine_cs *
-sched_lock_engine(const struct i915_sched_node *node,
-		  struct intel_engine_cs *locked,
+static struct i915_sched_engine *
+lock_sched_engine(struct i915_sched_node *node,
+		  struct i915_sched_engine *locked,
 		  struct sched_cache *cache)
 {
 	const struct i915_request *rq = node_to_request(node);
-	struct intel_engine_cs *engine;
+	struct i915_sched_engine *sched_engine;
 
 	GEM_BUG_ON(!locked);
 
@@ -146,81 +141,22 @@ sched_lock_engine(const struct i915_sched_node *node,
 	 * engine lock. The simple ploy we use is to take the lock then
 	 * check that the rq still belongs to the newly locked engine.
 	 */
-	while (locked != (engine = READ_ONCE(rq->engine))) {
-		spin_unlock(&locked->active.lock);
+	while (locked != (sched_engine = READ_ONCE(rq->engine)->sched_engine)) {
+		spin_unlock(&locked->lock);
 		memset(cache, 0, sizeof(*cache));
-		spin_lock(&engine->active.lock);
-		locked = engine;
+		spin_lock(&sched_engine->lock);
+		locked = sched_engine;
 	}
 
-	GEM_BUG_ON(locked != engine);
+	GEM_BUG_ON(locked != sched_engine);
 	return locked;
 }
 
-static inline int rq_prio(const struct i915_request *rq)
-{
-	return rq->sched.attr.priority;
-}
-
-static inline bool need_preempt(int prio, int active)
-{
-	/*
-	 * Allow preemption of low -> normal -> high, but we do
-	 * not allow low priority tasks to preempt other low priority
-	 * tasks under the impression that latency for low priority
-	 * tasks does not matter (as much as background throughput),
-	 * so kiss.
-	 */
-	return prio >= max(I915_PRIORITY_NORMAL, active);
-}
-
-static void kick_submission(struct intel_engine_cs *engine,
-			    const struct i915_request *rq,
-			    int prio)
-{
-	const struct i915_request *inflight;
-
-	/*
-	 * We only need to kick the tasklet once for the high priority
-	 * new context we add into the queue.
-	 */
-	if (prio <= engine->execlists.queue_priority_hint)
-		return;
-
-	rcu_read_lock();
-
-	/* Nothing currently active? We're overdue for a submission! */
-	inflight = execlists_active(&engine->execlists);
-	if (!inflight)
-		goto unlock;
-
-	/*
-	 * If we are already the currently executing context, don't
-	 * bother evaluating if we should preempt ourselves.
-	 */
-	if (inflight->context == rq->context)
-		goto unlock;
-
-	ENGINE_TRACE(engine,
-		     "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
-		     prio,
-		     rq->fence.context, rq->fence.seqno,
-		     inflight->fence.context, inflight->fence.seqno,
-		     inflight->sched.attr.priority);
-
-	engine->execlists.queue_priority_hint = prio;
-	if (need_preempt(prio, rq_prio(inflight)))
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-
-unlock:
-	rcu_read_unlock();
-}
-
 static void __i915_schedule(struct i915_sched_node *node,
 			    const struct i915_sched_attr *attr)
 {
 	const int prio = max(attr->priority, node->attr.priority);
-	struct intel_engine_cs *engine;
+	struct i915_sched_engine *sched_engine;
 	struct i915_dependency *dep, *p;
 	struct i915_dependency stack;
 	struct sched_cache cache;
@@ -295,23 +231,31 @@ static void __i915_schedule(struct i915_sched_node *node,
 	}
 
 	memset(&cache, 0, sizeof(cache));
-	engine = node_to_request(node)->engine;
-	spin_lock(&engine->active.lock);
+	sched_engine = node_to_request(node)->engine->sched_engine;
+	spin_lock(&sched_engine->lock);
 
 	/* Fifo and depth-first replacement ensure our deps execute before us */
-	engine = sched_lock_engine(node, engine, &cache);
+	sched_engine = lock_sched_engine(node, sched_engine, &cache);
 	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
+		struct i915_request *from = container_of(dep->signaler,
+							 struct i915_request,
+							 sched);
 		INIT_LIST_HEAD(&dep->dfs_link);
 
 		node = dep->signaler;
-		engine = sched_lock_engine(node, engine, &cache);
-		lockdep_assert_held(&engine->active.lock);
+		sched_engine = lock_sched_engine(node, sched_engine, &cache);
+		lockdep_assert_held(&sched_engine->lock);
 
 		/* Recheck after acquiring the engine->timeline.lock */
 		if (prio <= node->attr.priority || node_signaled(node))
 			continue;
 
-		GEM_BUG_ON(node_to_request(node)->engine != engine);
+		GEM_BUG_ON(node_to_request(node)->engine->sched_engine !=
+			   sched_engine);
+
+		/* Must be called before changing the nodes priority */
+		if (sched_engine->bump_inflight_request_prio)
+			sched_engine->bump_inflight_request_prio(from, prio);
 
 		WRITE_ONCE(node->attr.priority, prio);
 
@@ -329,16 +273,17 @@ static void __i915_schedule(struct i915_sched_node *node,
 		if (i915_request_in_priority_queue(node_to_request(node))) {
 			if (!cache.priolist)
 				cache.priolist =
-					i915_sched_lookup_priolist(engine,
+					i915_sched_lookup_priolist(sched_engine,
 								   prio);
 			list_move_tail(&node->link, cache.priolist);
 		}
 
 		/* Defer (tasklet) submission until after all of our updates. */
-		kick_submission(engine, node_to_request(node), prio);
+		if (sched_engine->kick_backend)
+			sched_engine->kick_backend(node_to_request(node), prio);
 	}
 
-	spin_unlock(&engine->active.lock);
+	spin_unlock(&sched_engine->lock);
 }
 
 void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr)
@@ -371,13 +316,13 @@ void i915_sched_node_reinit(struct i915_sched_node *node)
 static struct i915_dependency *
 i915_dependency_alloc(void)
 {
-	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
+	return kmem_cache_alloc(slab_dependencies, GFP_KERNEL);
 }
 
 static void
 i915_dependency_free(struct i915_dependency *dep)
 {
-	kmem_cache_free(global.slab_dependencies, dep);
+	kmem_cache_free(slab_dependencies, dep);
 }
 
 bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
@@ -489,39 +434,78 @@ void i915_request_show_with_schedule(struct drm_printer *m,
 	rcu_read_unlock();
 }
 
-static void i915_global_scheduler_shrink(void)
+static void default_destroy(struct kref *kref)
+{
+	struct i915_sched_engine *sched_engine =
+		container_of(kref, typeof(*sched_engine), ref);
+
+	tasklet_kill(&sched_engine->tasklet); /* flush the callback */
+	kfree(sched_engine);
+}
+
+static bool default_disabled(struct i915_sched_engine *sched_engine)
 {
-	kmem_cache_shrink(global.slab_dependencies);
-	kmem_cache_shrink(global.slab_priorities);
+	return false;
 }
 
-static void i915_global_scheduler_exit(void)
+struct i915_sched_engine *
+i915_sched_engine_create(unsigned int subclass)
 {
-	kmem_cache_destroy(global.slab_dependencies);
-	kmem_cache_destroy(global.slab_priorities);
+	struct i915_sched_engine *sched_engine;
+
+	sched_engine = kzalloc(sizeof(*sched_engine), GFP_KERNEL);
+	if (!sched_engine)
+		return NULL;
+
+	kref_init(&sched_engine->ref);
+
+	sched_engine->queue = RB_ROOT_CACHED;
+	sched_engine->queue_priority_hint = INT_MIN;
+	sched_engine->destroy = default_destroy;
+	sched_engine->disabled = default_disabled;
+
+	INIT_LIST_HEAD(&sched_engine->requests);
+	INIT_LIST_HEAD(&sched_engine->hold);
+
+	spin_lock_init(&sched_engine->lock);
+	lockdep_set_subclass(&sched_engine->lock, subclass);
+
+	/*
+	 * Due to an interesting quirk in lockdep's internal debug tracking,
+	 * after setting a subclass we must ensure the lock is used. Otherwise,
+	 * nr_unused_locks is incremented once too often.
+	 */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	local_irq_disable();
+	lock_map_acquire(&sched_engine->lock.dep_map);
+	lock_map_release(&sched_engine->lock.dep_map);
+	local_irq_enable();
+#endif
+
+	return sched_engine;
 }
 
-static struct i915_global_scheduler global = { {
-	.shrink = i915_global_scheduler_shrink,
-	.exit = i915_global_scheduler_exit,
-} };
+void i915_scheduler_module_exit(void)
+{
+	kmem_cache_destroy(slab_dependencies);
+	kmem_cache_destroy(slab_priorities);
+}
 
-int __init i915_global_scheduler_init(void)
+int __init i915_scheduler_module_init(void)
 {
-	global.slab_dependencies = KMEM_CACHE(i915_dependency,
+	slab_dependencies = KMEM_CACHE(i915_dependency,
 					      SLAB_HWCACHE_ALIGN |
 					      SLAB_TYPESAFE_BY_RCU);
-	if (!global.slab_dependencies)
+	if (!slab_dependencies)
 		return -ENOMEM;
 
-	global.slab_priorities = KMEM_CACHE(i915_priolist, 0);
-	if (!global.slab_priorities)
+	slab_priorities = KMEM_CACHE(i915_priolist, 0);
+	if (!slab_priorities)
 		goto err_priorities;
 
-	i915_global_register(&global.base);
 	return 0;
 
 err_priorities:
-	kmem_cache_destroy(global.slab_priorities);
+	kmem_cache_destroy(slab_priorities);
 	return -ENOMEM;
 }
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 858a0938f47a..0b9b86af6c7f 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -39,7 +39,7 @@ void i915_schedule(struct i915_request *request,
 		   const struct i915_sched_attr *attr);
 
 struct list_head *
-i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
+i915_sched_lookup_priolist(struct i915_sched_engine *sched_engine, int prio);
 
 void __i915_priolist_free(struct i915_priolist *p);
 static inline void i915_priolist_free(struct i915_priolist *p)
@@ -48,9 +48,61 @@ static inline void i915_priolist_free(struct i915_priolist *p)
 		__i915_priolist_free(p);
 }
 
+struct i915_sched_engine *
+i915_sched_engine_create(unsigned int subclass);
+
+static inline struct i915_sched_engine *
+i915_sched_engine_get(struct i915_sched_engine *sched_engine)
+{
+	kref_get(&sched_engine->ref);
+	return sched_engine;
+}
+
+static inline void
+i915_sched_engine_put(struct i915_sched_engine *sched_engine)
+{
+	kref_put(&sched_engine->ref, sched_engine->destroy);
+}
+
+static inline bool
+i915_sched_engine_is_empty(struct i915_sched_engine *sched_engine)
+{
+	return RB_EMPTY_ROOT(&sched_engine->queue.rb_root);
+}
+
+static inline void
+i915_sched_engine_reset_on_empty(struct i915_sched_engine *sched_engine)
+{
+	if (i915_sched_engine_is_empty(sched_engine))
+		sched_engine->no_priolist = false;
+}
+
+static inline void
+i915_sched_engine_active_lock_bh(struct i915_sched_engine *sched_engine)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&sched_engine->tasklet);
+}
+
+static inline void
+i915_sched_engine_active_unlock_bh(struct i915_sched_engine *sched_engine)
+{
+	tasklet_unlock(&sched_engine->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
 void i915_request_show_with_schedule(struct drm_printer *m,
 				     const struct i915_request *rq,
 				     const char *prefix,
 				     int indent);
 
+static inline bool
+i915_sched_engine_disabled(struct i915_sched_engine *sched_engine)
+{
+	return sched_engine->disabled(sched_engine);
+}
+
+void i915_scheduler_module_exit(void);
+int i915_scheduler_module_init(void);
+
 #endif /* _I915_SCHEDULER_H_ */
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 343ed44d5ed4..b0a1b58c7893 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -91,4 +91,115 @@ struct i915_dependency {
 				&(rq__)->sched.signalers_list, \
 				signal_link)
 
+/**
+ * struct i915_sched_engine - scheduler engine
+ *
+ * A schedule engine represents a submission queue with different priority
+ * bands. It contains all the common state (relative to the backend) to queue,
+ * track, and submit a request.
+ *
+ * This object at the moment is quite i915 specific but will transition into a
+ * container for the drm_gpu_scheduler plus a few other variables once the i915
+ * is integrated with the DRM scheduler.
+ */
+struct i915_sched_engine {
+	/**
+	 * @ref: reference count of schedule engine object
+	 */
+	struct kref ref;
+
+	/**
+	 * @lock: protects requests in priority lists, requests, hold and
+	 * tasklet while running
+	 */
+	spinlock_t lock;
+
+	/**
+	 * @requests: list of requests inflight on this schedule engine
+	 */
+	struct list_head requests;
+
+	/**
+	 * @hold: list of ready requests, but on hold
+	 */
+	struct list_head hold;
+
+	/**
+	 * @tasklet: softirq tasklet for submission
+	 */
+	struct tasklet_struct tasklet;
+
+	/**
+	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
+	 */
+	struct i915_priolist default_priolist;
+
+	/**
+	 * @queue_priority_hint: Highest pending priority.
+	 *
+	 * When we add requests into the queue, or adjust the priority of
+	 * executing requests, we compute the maximum priority of those
+	 * pending requests. We can then use this value to determine if
+	 * we need to preempt the executing requests to service the queue.
+	 * However, since the we may have recorded the priority of an inflight
+	 * request we wanted to preempt but since completed, at the time of
+	 * dequeuing the priority hint may no longer may match the highest
+	 * available request priority.
+	 */
+	int queue_priority_hint;
+
+	/**
+	 * @queue: queue of requests, in priority lists
+	 */
+	struct rb_root_cached queue;
+
+	/**
+	 * @no_priolist: priority lists disabled
+	 */
+	bool no_priolist;
+
+	/**
+	 * @private_data: private data of the submission backend
+	 */
+	void *private_data;
+
+	/**
+	 * @destroy: destroy schedule engine / cleanup in backend
+	 */
+	void	(*destroy)(struct kref *kref);
+
+	/**
+	 * @disabled: check if backend has disabled submission
+	 */
+	bool	(*disabled)(struct i915_sched_engine *sched_engine);
+
+	/**
+	 * @kick_backend: kick backend after a request's priority has changed
+	 */
+	void	(*kick_backend)(const struct i915_request *rq,
+				int prio);
+
+	/**
+	 * @bump_inflight_request_prio: update priority of an inflight request
+	 */
+	void	(*bump_inflight_request_prio)(struct i915_request *rq,
+					      int prio);
+
+	/**
+	 * @retire_inflight_request_prio: indicate request is retired to
+	 * priority tracking
+	 */
+	void	(*retire_inflight_request_prio)(struct i915_request *rq);
+
+	/**
+	 * @schedule: adjust priority of request
+	 *
+	 * Call when the priority on a request has changed and it and its
+	 * dependencies may need rescheduling. Note the request itself may
+	 * not be ready to run!
+	 */
+	void	(*schedule)(struct i915_request *request,
+			    const struct i915_sched_attr *attr);
+};
+
 #endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c
index a3a81bb8f2c3..5b33ef23d54c 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c
@@ -16,11 +16,8 @@ static void fence_complete(struct dma_fence_work *f)
 static void fence_work(struct work_struct *work)
 {
 	struct dma_fence_work *f = container_of(work, typeof(*f), work);
-	int err;
 
-	err = f->ops->work(f);
-	if (err)
-		dma_fence_set_error(&f->dma, err);
+	f->ops->work(f);
 
 	fence_complete(f);
 	dma_fence_put(&f->dma);
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.h b/drivers/gpu/drm/i915/i915_sw_fence_work.h
index 2c409f11c5c5..d56806918d13 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.h
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.h
@@ -17,7 +17,7 @@ struct dma_fence_work;
 
 struct dma_fence_work_ops {
 	const char *name;
-	int (*work)(struct dma_fence_work *f);
+	void (*work)(struct dma_fence_work *f);
 	void (*release)(struct dma_fence_work *f);
 };
 
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 873bf996ceb5..cdf0e9c6fd73 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -272,7 +272,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	struct intel_rps *rps = &i915->gt.rps;
 
-	return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->cur_freq));
+	return sysfs_emit(buf, "%d\n", intel_rps_get_requested_frequency(rps));
 }
 
 static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
@@ -326,9 +326,10 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
 static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct intel_gt *gt = &dev_priv->gt;
+	struct intel_rps *rps = &gt->rps;
 
-	return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->max_freq_softlimit));
+	return sysfs_emit(buf, "%d\n", intel_rps_get_max_frequency(rps));
 }
 
 static ssize_t gt_max_freq_mhz_store(struct device *kdev,
@@ -336,7 +337,8 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 				     const char *buf, size_t count)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct intel_gt *gt = &dev_priv->gt;
+	struct intel_rps *rps = &gt->rps;
 	ssize_t ret;
 	u32 val;
 
@@ -344,53 +346,26 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	if (ret)
 		return ret;
 
-	mutex_lock(&rps->lock);
-
-	val = intel_freq_opcode(rps, val);
-	if (val < rps->min_freq ||
-	    val > rps->max_freq ||
-	    val < rps->min_freq_softlimit) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	if (val > rps->rp0_freq)
-		DRM_DEBUG("User requested overclocking to %d\n",
-			  intel_gpu_freq(rps, val));
-
-	rps->max_freq_softlimit = val;
-
-	val = clamp_t(int, rps->cur_freq,
-		      rps->min_freq_softlimit,
-		      rps->max_freq_softlimit);
-
-	/*
-	 * We still need *_set_rps to process the new max_delay and
-	 * update the interrupt limits and PMINTRMSK even though
-	 * frequency request may be unchanged.
-	 */
-	intel_rps_set(rps, val);
-
-unlock:
-	mutex_unlock(&rps->lock);
+	ret = intel_rps_set_max_frequency(rps, val);
 
 	return ret ?: count;
 }
 
 static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_gt *gt = &i915->gt;
+	struct intel_rps *rps = &gt->rps;
 
-	return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->min_freq_softlimit));
+	return sysfs_emit(buf, "%d\n", intel_rps_get_min_frequency(rps));
 }
 
 static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 				     struct device_attribute *attr,
 				     const char *buf, size_t count)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 	ssize_t ret;
 	u32 val;
 
@@ -398,31 +373,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	if (ret)
 		return ret;
 
-	mutex_lock(&rps->lock);
-
-	val = intel_freq_opcode(rps, val);
-	if (val < rps->min_freq ||
-	    val > rps->max_freq ||
-	    val > rps->max_freq_softlimit) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	rps->min_freq_softlimit = val;
-
-	val = clamp_t(int, rps->cur_freq,
-		      rps->min_freq_softlimit,
-		      rps->max_freq_softlimit);
-
-	/*
-	 * We still need *_set_rps to process the new min_delay and
-	 * update the interrupt limits and PMINTRMSK even though
-	 * frequency request may be unchanged.
-	 */
-	intel_rps_set(rps, val);
-
-unlock:
-	mutex_unlock(&rps->lock);
+	ret = intel_rps_set_min_frequency(rps, val);
 
 	return ret ?: count;
 }
@@ -448,11 +399,11 @@ static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr
 	u32 val;
 
 	if (attr == &dev_attr_gt_RP0_freq_mhz)
-		val = intel_gpu_freq(rps, rps->rp0_freq);
+		val = intel_rps_get_rp0_frequency(rps);
 	else if (attr == &dev_attr_gt_RP1_freq_mhz)
-		val = intel_gpu_freq(rps, rps->rp1_freq);
+		val = intel_rps_get_rp1_frequency(rps);
 	else if (attr == &dev_attr_gt_RPn_freq_mhz)
-		val = intel_gpu_freq(rps, rps->min_freq);
+		val = intel_rps_get_rpn_frequency(rps);
 	else
 		BUG();
 
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 6778ad2a14a4..806ad688274b 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -794,30 +794,40 @@ DECLARE_EVENT_CLASS(i915_request,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u64, ctx)
+			     __field(u32, guc_id)
 			     __field(u16, class)
 			     __field(u16, instance)
 			     __field(u32, seqno)
+			     __field(u32, tail)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = rq->engine->i915->drm.primary->index;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
+			   __entry->guc_id = rq->context->guc_id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
+			   __entry->tail = rq->tail;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u",
+	    TP_printk("dev=%u, engine=%u:%u, guc_id=%u, ctx=%llu, seqno=%u, tail=%u",
 		      __entry->dev, __entry->class, __entry->instance,
-		      __entry->ctx, __entry->seqno)
+		      __entry->guc_id, __entry->ctx, __entry->seqno,
+		      __entry->tail)
 );
 
 DEFINE_EVENT(i915_request, i915_request_add,
-	    TP_PROTO(struct i915_request *rq),
-	    TP_ARGS(rq)
+	     TP_PROTO(struct i915_request *rq),
+	     TP_ARGS(rq)
 );
 
 #if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS)
+DEFINE_EVENT(i915_request, i915_request_guc_submit,
+	     TP_PROTO(struct i915_request *rq),
+	     TP_ARGS(rq)
+);
+
 DEFINE_EVENT(i915_request, i915_request_submit,
 	     TP_PROTO(struct i915_request *rq),
 	     TP_ARGS(rq)
@@ -885,9 +895,117 @@ TRACE_EVENT(i915_request_out,
 			      __entry->ctx, __entry->seqno, __entry->completed)
 );
 
+DECLARE_EVENT_CLASS(intel_context,
+		    TP_PROTO(struct intel_context *ce),
+		    TP_ARGS(ce),
+
+		    TP_STRUCT__entry(
+			     __field(u32, guc_id)
+			     __field(int, pin_count)
+			     __field(u32, sched_state)
+			     __field(u32, guc_sched_state_no_lock)
+			     __field(u8, guc_prio)
+			     ),
+
+		    TP_fast_assign(
+			   __entry->guc_id = ce->guc_id;
+			   __entry->pin_count = atomic_read(&ce->pin_count);
+			   __entry->sched_state = ce->guc_state.sched_state;
+			   __entry->guc_sched_state_no_lock =
+			   atomic_read(&ce->guc_sched_state_no_lock);
+			   __entry->guc_prio = ce->guc_prio;
+			   ),
+
+		    TP_printk("guc_id=%d, pin_count=%d sched_state=0x%x,0x%x, guc_prio=%u",
+			      __entry->guc_id, __entry->pin_count,
+			      __entry->sched_state,
+			      __entry->guc_sched_state_no_lock,
+			      __entry->guc_prio)
+);
+
+DEFINE_EVENT(intel_context, intel_context_set_prio,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_reset,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_ban,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_register,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_deregister,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_deregister_done,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_sched_enable,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_sched_disable,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_sched_done,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_create,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_fence_release,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_free,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_steal_guc_id,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_do_pin,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
+DEFINE_EVENT(intel_context, intel_context_do_unpin,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
 #else
 #if !defined(TRACE_HEADER_MULTI_READ)
 static inline void
+trace_i915_request_guc_submit(struct i915_request *rq)
+{
+}
+
+static inline void
 trace_i915_request_submit(struct i915_request *rq)
 {
 }
@@ -906,6 +1024,81 @@ static inline void
 trace_i915_request_out(struct i915_request *rq)
 {
 }
+
+static inline void
+trace_intel_context_set_prio(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_reset(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_ban(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_register(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_deregister(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_deregister_done(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_sched_enable(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_sched_disable(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_sched_done(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_create(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_fence_release(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_free(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_steal_guc_id(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_do_pin(struct intel_context *ce)
+{
+}
+
+static inline void
+trace_intel_context_do_unpin(struct intel_context *ce)
+{
+}
 #endif
 #endif
 
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
new file mode 100644
index 000000000000..6877362f6b85
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/slab.h>
+
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_placement.h>
+
+#include "i915_ttm_buddy_manager.h"
+
+#include "i915_buddy.h"
+#include "i915_gem.h"
+
+struct i915_ttm_buddy_manager {
+	struct ttm_resource_manager manager;
+	struct i915_buddy_mm mm;
+	struct list_head reserved;
+	struct mutex lock;
+	u64 default_page_size;
+};
+
+static struct i915_ttm_buddy_manager *
+to_buddy_manager(struct ttm_resource_manager *man)
+{
+	return container_of(man, struct i915_ttm_buddy_manager, manager);
+}
+
+static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
+				    struct ttm_buffer_object *bo,
+				    const struct ttm_place *place,
+				    struct ttm_resource **res)
+{
+	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+	struct i915_ttm_buddy_resource *bman_res;
+	struct i915_buddy_mm *mm = &bman->mm;
+	unsigned long n_pages;
+	unsigned int min_order;
+	u64 min_page_size;
+	u64 size;
+	int err;
+
+	GEM_BUG_ON(place->fpfn || place->lpfn);
+
+	bman_res = kzalloc(sizeof(*bman_res), GFP_KERNEL);
+	if (!bman_res)
+		return -ENOMEM;
+
+	ttm_resource_init(bo, place, &bman_res->base);
+	INIT_LIST_HEAD(&bman_res->blocks);
+	bman_res->mm = mm;
+
+	GEM_BUG_ON(!bman_res->base.num_pages);
+	size = bman_res->base.num_pages << PAGE_SHIFT;
+
+	min_page_size = bman->default_page_size;
+	if (bo->page_alignment)
+		min_page_size = bo->page_alignment << PAGE_SHIFT;
+
+	GEM_BUG_ON(min_page_size < mm->chunk_size);
+	min_order = ilog2(min_page_size) - ilog2(mm->chunk_size);
+	if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+		size = roundup_pow_of_two(size);
+		min_order = ilog2(size) - ilog2(mm->chunk_size);
+	}
+
+	if (size > mm->size) {
+		err = -E2BIG;
+		goto err_free_res;
+	}
+
+	n_pages = size >> ilog2(mm->chunk_size);
+
+	do {
+		struct i915_buddy_block *block;
+		unsigned int order;
+
+		order = fls(n_pages) - 1;
+		GEM_BUG_ON(order > mm->max_order);
+		GEM_BUG_ON(order < min_order);
+
+		do {
+			mutex_lock(&bman->lock);
+			block = i915_buddy_alloc(mm, order);
+			mutex_unlock(&bman->lock);
+			if (!IS_ERR(block))
+				break;
+
+			if (order-- == min_order) {
+				err = -ENOSPC;
+				goto err_free_blocks;
+			}
+		} while (1);
+
+		n_pages -= BIT(order);
+
+		list_add_tail(&block->link, &bman_res->blocks);
+
+		if (!n_pages)
+			break;
+	} while (1);
+
+	*res = &bman_res->base;
+	return 0;
+
+err_free_blocks:
+	mutex_lock(&bman->lock);
+	i915_buddy_free_list(mm, &bman_res->blocks);
+	mutex_unlock(&bman->lock);
+err_free_res:
+	kfree(bman_res);
+	return err;
+}
+
+static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man,
+				    struct ttm_resource *res)
+{
+	struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
+	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+
+	mutex_lock(&bman->lock);
+	i915_buddy_free_list(&bman->mm, &bman_res->blocks);
+	mutex_unlock(&bman->lock);
+
+	kfree(bman_res);
+}
+
+static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = {
+	.alloc = i915_ttm_buddy_man_alloc,
+	.free = i915_ttm_buddy_man_free,
+};
+
+
+/**
+ * i915_ttm_buddy_man_init - Setup buddy allocator based ttm manager
+ * @bdev: The ttm device
+ * @type: Memory type we want to manage
+ * @use_tt: Set use_tt for the manager
+ * @size: The size in bytes to manage
+ * @default_page_size: The default minimum page size in bytes for allocations,
+ * this must be at least as large as @chunk_size, and can be overridden by
+ * setting the BO page_alignment, to be larger or smaller as needed.
+ * @chunk_size: The minimum page size in bytes for our allocations i.e
+ * order-zero
+ *
+ * Note that the starting address is assumed to be zero here, since this
+ * simplifies keeping the property where allocated blocks having natural
+ * power-of-two alignment. So long as the real starting address is some large
+ * power-of-two, or naturally start from zero, then this should be fine.  Also
+ * the &i915_ttm_buddy_man_reserve interface can be used to preserve alignment
+ * if say there is some unusable range from the start of the region. We can
+ * revisit this in the future and make the interface accept an actual starting
+ * offset and let it take care of the rest.
+ *
+ * Note that if the @size is not aligned to the @chunk_size then we perform the
+ * required rounding to get the usable size. The final size in pages can be
+ * taken from &ttm_resource_manager.size.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_init(struct ttm_device *bdev,
+			    unsigned int type, bool use_tt,
+			    u64 size, u64 default_page_size,
+			    u64 chunk_size)
+{
+	struct ttm_resource_manager *man;
+	struct i915_ttm_buddy_manager *bman;
+	int err;
+
+	bman = kzalloc(sizeof(*bman), GFP_KERNEL);
+	if (!bman)
+		return -ENOMEM;
+
+	err = i915_buddy_init(&bman->mm, size, chunk_size);
+	if (err)
+		goto err_free_bman;
+
+	mutex_init(&bman->lock);
+	INIT_LIST_HEAD(&bman->reserved);
+	GEM_BUG_ON(default_page_size < chunk_size);
+	bman->default_page_size = default_page_size;
+
+	man = &bman->manager;
+	man->use_tt = use_tt;
+	man->func = &i915_ttm_buddy_manager_func;
+	ttm_resource_manager_init(man, bman->mm.size >> PAGE_SHIFT);
+
+	ttm_resource_manager_set_used(man, true);
+	ttm_set_driver_manager(bdev, type, man);
+
+	return 0;
+
+err_free_bman:
+	kfree(bman);
+	return err;
+}
+
+/**
+ * i915_ttm_buddy_man_fini - Destroy the buddy allocator ttm manager
+ * @bdev: The ttm device
+ * @type: Memory type we want to manage
+ *
+ * Note that if we reserved anything with &i915_ttm_buddy_man_reserve, this will
+ * also be freed for us here.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type)
+{
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, type);
+	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+	struct i915_buddy_mm *mm = &bman->mm;
+	int ret;
+
+	ttm_resource_manager_set_used(man, false);
+
+	ret = ttm_resource_manager_evict_all(bdev, man);
+	if (ret)
+		return ret;
+
+	ttm_set_driver_manager(bdev, type, NULL);
+
+	mutex_lock(&bman->lock);
+	i915_buddy_free_list(mm, &bman->reserved);
+	i915_buddy_fini(mm);
+	mutex_unlock(&bman->lock);
+
+	ttm_resource_manager_cleanup(man);
+	kfree(bman);
+
+	return 0;
+}
+
+/**
+ * i915_ttm_buddy_man_reserve - Reserve address range
+ * @man: The buddy allocator ttm manager
+ * @start: The offset in bytes, where the region start is assumed to be zero
+ * @size: The size in bytes
+ *
+ * Note that the starting address for the region is always assumed to be zero.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man,
+			       u64 start, u64 size)
+{
+	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+	struct i915_buddy_mm *mm = &bman->mm;
+	int ret;
+
+	mutex_lock(&bman->lock);
+	ret = i915_buddy_alloc_range(mm, &bman->reserved, start, size);
+	mutex_unlock(&bman->lock);
+
+	return ret;
+}
+
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
new file mode 100644
index 000000000000..0722d33f3e14
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_TTM_BUDDY_MANAGER_H__
+#define __I915_TTM_BUDDY_MANAGER_H__
+
+#include <linux/list.h>
+#include <linux/types.h>
+
+#include <drm/ttm/ttm_resource.h>
+
+struct ttm_device;
+struct ttm_resource_manager;
+struct i915_buddy_mm;
+
+/**
+ * struct i915_ttm_buddy_resource
+ *
+ * @base: struct ttm_resource base class we extend
+ * @blocks: the list of struct i915_buddy_block for this resource/allocation
+ * @mm: the struct i915_buddy_mm for this resource
+ *
+ * Extends the struct ttm_resource to manage an address space allocation with
+ * one or more struct i915_buddy_block.
+ */
+struct i915_ttm_buddy_resource {
+	struct ttm_resource base;
+	struct list_head blocks;
+	struct i915_buddy_mm *mm;
+};
+
+/**
+ * to_ttm_buddy_resource
+ *
+ * @res: the resource to upcast
+ *
+ * Upcast the struct ttm_resource object into a struct i915_ttm_buddy_resource.
+ */
+static inline struct i915_ttm_buddy_resource *
+to_ttm_buddy_resource(struct ttm_resource *res)
+{
+	return container_of(res, struct i915_ttm_buddy_resource, base);
+}
+
+int i915_ttm_buddy_man_init(struct ttm_device *bdev,
+			    unsigned type, bool use_tt,
+			    u64 size, u64 default_page_size, u64 chunk_size);
+int i915_ttm_buddy_man_fini(struct ttm_device *bdev,
+			    unsigned int type);
+
+int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man,
+			       u64 start, u64 size);
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 0f227f28b280..4b7fc4647e46 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -34,24 +34,20 @@
 #include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
-#include "i915_globals.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 #include "i915_vma.h"
 
-static struct i915_global_vma {
-	struct i915_global base;
-	struct kmem_cache *slab_vmas;
-} global;
+static struct kmem_cache *slab_vmas;
 
 struct i915_vma *i915_vma_alloc(void)
 {
-	return kmem_cache_zalloc(global.slab_vmas, GFP_KERNEL);
+	return kmem_cache_zalloc(slab_vmas, GFP_KERNEL);
 }
 
 void i915_vma_free(struct i915_vma *vma)
 {
-	return kmem_cache_free(global.slab_vmas, vma);
+	return kmem_cache_free(slab_vmas, vma);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_ERRLOG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
@@ -300,14 +296,13 @@ struct i915_vma_work {
 	unsigned int flags;
 };
 
-static int __vma_bind(struct dma_fence_work *work)
+static void __vma_bind(struct dma_fence_work *work)
 {
 	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
 	struct i915_vma *vma = vw->vma;
 
 	vma->ops->bind_vma(vw->vm, &vw->stash,
 			   vma, vw->cache_level, vw->flags);
-	return 0;
 }
 
 static void __vma_release(struct dma_fence_work *work)
@@ -1415,27 +1410,16 @@ void i915_vma_make_purgeable(struct i915_vma *vma)
 #include "selftests/i915_vma.c"
 #endif
 
-static void i915_global_vma_shrink(void)
+void i915_vma_module_exit(void)
 {
-	kmem_cache_shrink(global.slab_vmas);
+	kmem_cache_destroy(slab_vmas);
 }
 
-static void i915_global_vma_exit(void)
-{
-	kmem_cache_destroy(global.slab_vmas);
-}
-
-static struct i915_global_vma global = { {
-	.shrink = i915_global_vma_shrink,
-	.exit = i915_global_vma_exit,
-} };
-
-int __init i915_global_vma_init(void)
+int __init i915_vma_module_init(void)
 {
-	global.slab_vmas = KMEM_CACHE(i915_vma, SLAB_HWCACHE_ALIGN);
-	if (!global.slab_vmas)
+	slab_vmas = KMEM_CACHE(i915_vma, SLAB_HWCACHE_ALIGN);
+	if (!slab_vmas)
 		return -ENOMEM;
 
-	i915_global_register(&global.base);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index eca452a9851f..ed69f66c7ab0 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -426,4 +426,7 @@ static inline int i915_vma_sync(struct i915_vma *vma)
 	return i915_active_wait(&vma->active);
 }
 
+void i915_vma_module_exit(void);
+int i915_vma_module_init(void);
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index e0a10f36acc1..305facedd284 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -59,7 +59,6 @@ static const char * const platform_names[] = {
 	PLATFORM_NAME(GEMINILAKE),
 	PLATFORM_NAME(COFFEELAKE),
 	PLATFORM_NAME(COMETLAKE),
-	PLATFORM_NAME(CANNONLAKE),
 	PLATFORM_NAME(ICELAKE),
 	PLATFORM_NAME(ELKHARTLAKE),
 	PLATFORM_NAME(JASPERLAKE),
@@ -68,6 +67,8 @@ static const char * const platform_names[] = {
 	PLATFORM_NAME(DG1),
 	PLATFORM_NAME(ALDERLAKE_S),
 	PLATFORM_NAME(ALDERLAKE_P),
+	PLATFORM_NAME(XEHPSDV),
+	PLATFORM_NAME(DG2),
 };
 #undef PLATFORM_NAME
 
@@ -96,9 +97,17 @@ static const char *iommu_name(void)
 void intel_device_info_print_static(const struct intel_device_info *info,
 				    struct drm_printer *p)
 {
-	drm_printf(p, "graphics_ver: %u\n", info->graphics_ver);
-	drm_printf(p, "media_ver: %u\n", info->media_ver);
-	drm_printf(p, "display_ver: %u\n", info->display.ver);
+	if (info->graphics_rel)
+		drm_printf(p, "graphics version: %u.%02u\n", info->graphics_ver, info->graphics_rel);
+	else
+		drm_printf(p, "graphics version: %u\n", info->graphics_ver);
+
+	if (info->media_rel)
+		drm_printf(p, "media version: %u.%02u\n", info->media_ver, info->media_rel);
+	else
+		drm_printf(p, "media version: %u\n", info->media_ver);
+
+	drm_printf(p, "display version: %u\n", info->display.ver);
 	drm_printf(p, "gt: %d\n", info->gt);
 	drm_printf(p, "iommu: %s\n", iommu_name());
 	drm_printf(p, "memory-regions: %x\n", info->memory_regions);
@@ -165,7 +174,6 @@ static const u16 subplatform_ulx_ids[] = {
 };
 
 static const u16 subplatform_portf_ids[] = {
-	INTEL_CNL_PORT_F_IDS(0),
 	INTEL_ICL_PORT_F_IDS(0),
 };
 
@@ -253,14 +261,14 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 	struct intel_runtime_info *runtime = RUNTIME_INFO(dev_priv);
 	enum pipe pipe;
 
-	/* Wa_14011765242: adl-s A0 */
-	if (IS_ADLS_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0))
+	/* Wa_14011765242: adl-s A0,A1 */
+	if (IS_ADLS_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A2))
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_scalers[pipe] = 0;
-	else if (GRAPHICS_VER(dev_priv) >= 10) {
+	else if (DISPLAY_VER(dev_priv) >= 11) {
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_scalers[pipe] = 2;
-	} else if (GRAPHICS_VER(dev_priv) == 9) {
+	} else if (DISPLAY_VER(dev_priv) >= 9) {
 		runtime->num_scalers[PIPE_A] = 2;
 		runtime->num_scalers[PIPE_B] = 2;
 		runtime->num_scalers[PIPE_C] = 1;
@@ -271,10 +279,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 	if (DISPLAY_VER(dev_priv) >= 13 || HAS_D12_PLANE_MINIMIZATION(dev_priv))
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_sprites[pipe] = 4;
-	else if (GRAPHICS_VER(dev_priv) >= 11)
+	else if (DISPLAY_VER(dev_priv) >= 11)
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_sprites[pipe] = 6;
-	else if (GRAPHICS_VER(dev_priv) == 10 || IS_GEMINILAKE(dev_priv))
+	else if (DISPLAY_VER(dev_priv) == 10)
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_sprites[pipe] = 3;
 	else if (IS_BROXTON(dev_priv)) {
@@ -293,7 +301,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_sprites[pipe] = 2;
-	} else if (GRAPHICS_VER(dev_priv) >= 5 || IS_G4X(dev_priv)) {
+	} else if (DISPLAY_VER(dev_priv) >= 5 || IS_G4X(dev_priv)) {
 		for_each_pipe(dev_priv, pipe)
 			runtime->num_sprites[pipe] = 1;
 	}
@@ -357,7 +365,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			info->display.has_dmc = 0;
 
 		if (DISPLAY_VER(dev_priv) >= 10 &&
-		    (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE))
+		    (dfsm & GLK_DFSM_DISPLAY_DSC_DISABLE))
 			info->display.has_dsc = 0;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index b326aff65cd6..d328bb95c49b 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -76,8 +76,6 @@ enum intel_platform {
 	INTEL_GEMINILAKE,
 	INTEL_COFFEELAKE,
 	INTEL_COMETLAKE,
-	/* gen10 */
-	INTEL_CANNONLAKE,
 	/* gen11 */
 	INTEL_ICELAKE,
 	INTEL_ELKHARTLAKE,
@@ -88,6 +86,8 @@ enum intel_platform {
 	INTEL_DG1,
 	INTEL_ALDERLAKE_S,
 	INTEL_ALDERLAKE_P,
+	INTEL_XEHPSDV,
+	INTEL_DG2,
 	INTEL_MAX_PLATFORMS
 };
 
@@ -103,9 +103,13 @@ enum intel_platform {
 #define INTEL_SUBPLATFORM_ULT	(0)
 #define INTEL_SUBPLATFORM_ULX	(1)
 
-/* CNL/ICL */
+/* ICL */
 #define INTEL_SUBPLATFORM_PORTF	(0)
 
+/* DG2 */
+#define INTEL_SUBPLATFORM_G10	0
+#define INTEL_SUBPLATFORM_G11	1
+
 enum intel_ppgtt_type {
 	INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE,
 	INTEL_PPGTT_ALIASING = I915_GEM_PPGTT_ALIASING,
@@ -127,7 +131,7 @@ enum intel_ppgtt_type {
 	func(has_llc); \
 	func(has_logical_ring_contexts); \
 	func(has_logical_ring_elsq); \
-	func(has_master_unit_irq); \
+	func(has_mslices); \
 	func(has_pooled_eu); \
 	func(has_rc6); \
 	func(has_rc6p); \
@@ -141,6 +145,7 @@ enum intel_ppgtt_type {
 #define DEV_INFO_DISPLAY_FOR_EACH_FLAG(func) \
 	/* Keep in alphabetical order */ \
 	func(cursor_needs_physical); \
+	func(has_cdclk_crawl); \
 	func(has_dmc); \
 	func(has_ddi); \
 	func(has_dp_mst); \
@@ -162,9 +167,10 @@ enum intel_ppgtt_type {
 
 struct intel_device_info {
 	u8 graphics_ver;
+	u8 graphics_rel;
 	u8 media_ver;
+	u8 media_rel;
 
-	u8 gt; /* GT number, 0 if undefined */
 	intel_engine_mask_t platform_engine_mask; /* Engines supported by the HW */
 
 	enum intel_platform platform;
@@ -180,13 +186,13 @@ struct intel_device_info {
 
 	u32 display_mmio_offset;
 
+	u8 gt; /* GT number, 0 if undefined */
+
 	u8 pipe_mask;
 	u8 cpu_transcoder_mask;
 
 	u8 abox_mask;
 
-	u8 has_cdclk_crawl;  /* does support CDCLK crawling */
-
 #define DEFINE_FLAG(name) u8 name:1
 	DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG);
 #undef DEFINE_FLAG
diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c
index 50fdea84ba70..91866520c173 100644
--- a/drivers/gpu/drm/i915/intel_dram.c
+++ b/drivers/gpu/drm/i915/intel_dram.c
@@ -77,21 +77,21 @@ static int skl_get_dimm_ranks(u16 val)
 }
 
 /* Returns total Gb for the whole DIMM */
-static int cnl_get_dimm_size(u16 val)
+static int icl_get_dimm_size(u16 val)
 {
-	return (val & CNL_DRAM_SIZE_MASK) * 8 / 2;
+	return (val & ICL_DRAM_SIZE_MASK) * 8 / 2;
 }
 
-static int cnl_get_dimm_width(u16 val)
+static int icl_get_dimm_width(u16 val)
 {
-	if (cnl_get_dimm_size(val) == 0)
+	if (icl_get_dimm_size(val) == 0)
 		return 0;
 
-	switch (val & CNL_DRAM_WIDTH_MASK) {
-	case CNL_DRAM_WIDTH_X8:
-	case CNL_DRAM_WIDTH_X16:
-	case CNL_DRAM_WIDTH_X32:
-		val = (val & CNL_DRAM_WIDTH_MASK) >> CNL_DRAM_WIDTH_SHIFT;
+	switch (val & ICL_DRAM_WIDTH_MASK) {
+	case ICL_DRAM_WIDTH_X8:
+	case ICL_DRAM_WIDTH_X16:
+	case ICL_DRAM_WIDTH_X32:
+		val = (val & ICL_DRAM_WIDTH_MASK) >> ICL_DRAM_WIDTH_SHIFT;
 		return 8 << val;
 	default:
 		MISSING_CASE(val);
@@ -99,12 +99,12 @@ static int cnl_get_dimm_width(u16 val)
 	}
 }
 
-static int cnl_get_dimm_ranks(u16 val)
+static int icl_get_dimm_ranks(u16 val)
 {
-	if (cnl_get_dimm_size(val) == 0)
+	if (icl_get_dimm_size(val) == 0)
 		return 0;
 
-	val = (val & CNL_DRAM_RANK_MASK) >> CNL_DRAM_RANK_SHIFT;
+	val = (val & ICL_DRAM_RANK_MASK) >> ICL_DRAM_RANK_SHIFT;
 
 	return val + 1;
 }
@@ -121,10 +121,10 @@ skl_dram_get_dimm_info(struct drm_i915_private *i915,
 		       struct dram_dimm_info *dimm,
 		       int channel, char dimm_name, u16 val)
 {
-	if (GRAPHICS_VER(i915) >= 10) {
-		dimm->size = cnl_get_dimm_size(val);
-		dimm->width = cnl_get_dimm_width(val);
-		dimm->ranks = cnl_get_dimm_ranks(val);
+	if (GRAPHICS_VER(i915) >= 11) {
+		dimm->size = icl_get_dimm_size(val);
+		dimm->width = icl_get_dimm_width(val);
+		dimm->ranks = icl_get_dimm_ranks(val);
 	} else {
 		dimm->size = skl_get_dimm_size(val);
 		dimm->width = skl_get_dimm_width(val);
@@ -468,6 +468,7 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv)
 
 	dram_info->num_channels = (val & 0xf0) >> 4;
 	dram_info->num_qgv_points = (val & 0xf00) >> 8;
+	dram_info->num_psf_gv_points = (val & 0x3000) >> 12;
 
 	return 0;
 }
@@ -484,8 +485,7 @@ static int gen11_get_dram_info(struct drm_i915_private *i915)
 
 static int gen12_get_dram_info(struct drm_i915_private *i915)
 {
-	/* Always needed for GEN12+ */
-	i915->dram_info.wm_lv_0_adjust_needed = true;
+	i915->dram_info.wm_lv_0_adjust_needed = false;
 
 	return icl_pcode_read_mem_global_info(i915);
 }
@@ -495,15 +495,15 @@ void intel_dram_detect(struct drm_i915_private *i915)
 	struct dram_info *dram_info = &i915->dram_info;
 	int ret;
 
+	if (GRAPHICS_VER(i915) < 9 || IS_DG2(i915) || !HAS_DISPLAY(i915))
+		return;
+
 	/*
 	 * Assume level 0 watermark latency adjustment is needed until proven
 	 * otherwise, this w/a is not needed by bxt/glk.
 	 */
 	dram_info->wm_lv_0_adjust_needed = !IS_GEN9_LP(i915);
 
-	if (GRAPHICS_VER(i915) < 9 || !HAS_DISPLAY(i915))
-		return;
-
 	if (GRAPHICS_VER(i915) >= 12)
 		ret = gen12_get_dram_info(i915);
 	else if (GRAPHICS_VER(i915) >= 11)
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index e6024eb7cca4..779eb2fa90b6 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -5,6 +5,7 @@
 
 #include "intel_memory_region.h"
 #include "i915_drv.h"
+#include "i915_ttm_buddy_manager.h"
 
 static const struct {
 	u16 class;
@@ -28,11 +29,6 @@ static const struct {
 	},
 };
 
-struct intel_region_reserve {
-	struct list_head link;
-	struct ttm_resource *res;
-};
-
 struct intel_memory_region *
 intel_memory_region_lookup(struct drm_i915_private *i915,
 			   u16 class, u16 instance)
@@ -64,27 +60,6 @@ intel_memory_region_by_type(struct drm_i915_private *i915,
 }
 
 /**
- * intel_memory_region_unreserve - Unreserve all previously reserved
- * ranges
- * @mem: The region containing the reserved ranges.
- */
-void intel_memory_region_unreserve(struct intel_memory_region *mem)
-{
-	struct intel_region_reserve *reserve, *next;
-
-	if (!mem->priv_ops || !mem->priv_ops->free)
-		return;
-
-	mutex_lock(&mem->mm_lock);
-	list_for_each_entry_safe(reserve, next, &mem->reserved, link) {
-		list_del(&reserve->link);
-		mem->priv_ops->free(mem, reserve->res);
-		kfree(reserve);
-	}
-	mutex_unlock(&mem->mm_lock);
-}
-
-/**
  * intel_memory_region_reserve - Reserve a memory range
  * @mem: The region for which we want to reserve a range.
  * @offset: Start of the range to reserve.
@@ -96,28 +71,11 @@ int intel_memory_region_reserve(struct intel_memory_region *mem,
 				resource_size_t offset,
 				resource_size_t size)
 {
-	int ret;
-	struct intel_region_reserve *reserve;
-
-	if (!mem->priv_ops || !mem->priv_ops->reserve)
-		return -EINVAL;
-
-	reserve = kzalloc(sizeof(*reserve), GFP_KERNEL);
-	if (!reserve)
-		return -ENOMEM;
+	struct ttm_resource_manager *man = mem->region_private;
 
-	reserve->res = mem->priv_ops->reserve(mem, offset, size);
-	if (IS_ERR(reserve->res)) {
-		ret = PTR_ERR(reserve->res);
-		kfree(reserve);
-		return ret;
-	}
-
-	mutex_lock(&mem->mm_lock);
-	list_add_tail(&reserve->link, &mem->reserved);
-	mutex_unlock(&mem->mm_lock);
+	GEM_BUG_ON(mem->is_range_manager);
 
-	return 0;
+	return i915_ttm_buddy_man_reserve(man, offset, size);
 }
 
 struct intel_memory_region *
@@ -149,10 +107,6 @@ intel_memory_region_create(struct drm_i915_private *i915,
 
 	mutex_init(&mem->objects.lock);
 	INIT_LIST_HEAD(&mem->objects.list);
-	INIT_LIST_HEAD(&mem->objects.purgeable);
-	INIT_LIST_HEAD(&mem->reserved);
-
-	mutex_init(&mem->mm_lock);
 
 	if (ops->init) {
 		err = ops->init(mem);
@@ -183,11 +137,9 @@ static void __intel_memory_region_destroy(struct kref *kref)
 	struct intel_memory_region *mem =
 		container_of(kref, typeof(*mem), kref);
 
-	intel_memory_region_unreserve(mem);
 	if (mem->ops->release)
 		mem->ops->release(mem);
 
-	mutex_destroy(&mem->mm_lock);
 	mutex_destroy(&mem->objects.lock);
 	kfree(mem);
 }
@@ -221,7 +173,12 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
 		instance = intel_region_map[i].instance;
 		switch (type) {
 		case INTEL_MEMORY_SYSTEM:
-			mem = i915_gem_shmem_setup(i915, type, instance);
+			if (IS_DGFX(i915))
+				mem = i915_gem_ttm_system_setup(i915, type,
+								instance);
+			else
+				mem = i915_gem_shmem_setup(i915, type,
+							   instance);
 			break;
 		case INTEL_MEMORY_STOLEN_LOCAL:
 			mem = i915_gem_stolen_lmem_setup(i915, type, instance);
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 1f7dac63abb7..1f2b96efa69d 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -40,8 +40,7 @@ enum intel_region_id {
 #define REGION_STOLEN_SMEM   BIT(INTEL_REGION_STOLEN_SMEM)
 #define REGION_STOLEN_LMEM   BIT(INTEL_REGION_STOLEN_LMEM)
 
-#define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
-#define I915_ALLOC_CONTIGUOUS     BIT(1)
+#define I915_ALLOC_CONTIGUOUS     BIT(0)
 
 #define for_each_memory_region(mr, i915, id) \
 	for (id = 0; id < ARRAY_SIZE((i915)->mm.regions); id++) \
@@ -56,22 +55,14 @@ struct intel_memory_region_ops {
 	int (*init_object)(struct intel_memory_region *mem,
 			   struct drm_i915_gem_object *obj,
 			   resource_size_t size,
+			   resource_size_t page_size,
 			   unsigned int flags);
 };
 
-struct intel_memory_region_private_ops {
-	struct ttm_resource *(*reserve)(struct intel_memory_region *mem,
-					resource_size_t offset,
-					resource_size_t size);
-	void (*free)(struct intel_memory_region *mem,
-		     struct ttm_resource *res);
-};
-
 struct intel_memory_region {
 	struct drm_i915_private *i915;
 
 	const struct intel_memory_region_ops *ops;
-	const struct intel_memory_region_private_ops *priv_ops;
 
 	struct io_mapping iomap;
 	struct resource region;
@@ -79,8 +70,6 @@ struct intel_memory_region {
 	/* For fake LMEM */
 	struct drm_mm_node fake_mappable;
 
-	struct mutex mm_lock;
-
 	struct kref kref;
 
 	resource_size_t io_start;
@@ -94,18 +83,13 @@ struct intel_memory_region {
 	char name[16];
 	bool private; /* not for userspace */
 
-	struct list_head reserved;
-
 	dma_addr_t remap_addr;
 
 	struct {
 		struct mutex lock; /* Protects access to objects */
 		struct list_head list;
-		struct list_head purgeable;
 	} objects;
 
-	size_t chunk_size;
-	unsigned int max_order;
 	bool is_range_manager;
 
 	void *region_private;
@@ -139,9 +123,15 @@ __printf(2, 3) void
 intel_memory_region_set_name(struct intel_memory_region *mem,
 			     const char *fmt, ...);
 
-void intel_memory_region_unreserve(struct intel_memory_region *mem);
-
 int intel_memory_region_reserve(struct intel_memory_region *mem,
 				resource_size_t offset,
 				resource_size_t size);
+
+struct intel_memory_region *
+i915_gem_ttm_system_setup(struct drm_i915_private *i915,
+			  u16 type, u16 instance);
+struct intel_memory_region *
+i915_gem_shmem_setup(struct drm_i915_private *i915,
+		     u16 type, u16 instance);
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index 4e92ae19189e..d1d4b97b86f5 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -81,7 +81,6 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 	case INTEL_PCH_CNP_DEVICE_ID_TYPE:
 		drm_dbg_kms(&dev_priv->drm, "Found Cannon Lake PCH (CNP)\n");
 		drm_WARN_ON(&dev_priv->drm,
-			    !IS_CANNONLAKE(dev_priv) &&
 			    !IS_COFFEELAKE(dev_priv) &&
 			    !IS_COMETLAKE(dev_priv));
 		return PCH_CNP;
@@ -89,7 +88,6 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		drm_dbg_kms(&dev_priv->drm,
 			    "Found Cannon Lake LP PCH (CNP-LP)\n");
 		drm_WARN_ON(&dev_priv->drm,
-			    !IS_CANNONLAKE(dev_priv) &&
 			    !IS_COFFEELAKE(dev_priv) &&
 			    !IS_COMETLAKE(dev_priv));
 		return PCH_CNP;
@@ -171,8 +169,7 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv,
 		id = INTEL_PCH_MCC_DEVICE_ID_TYPE;
 	else if (IS_ICELAKE(dev_priv))
 		id = INTEL_PCH_ICP_DEVICE_ID_TYPE;
-	else if (IS_CANNONLAKE(dev_priv) ||
-		 IS_COFFEELAKE(dev_priv) ||
+	else if (IS_COFFEELAKE(dev_priv) ||
 		 IS_COMETLAKE(dev_priv))
 		id = INTEL_PCH_CNP_DEVICE_ID_TYPE;
 	else if (IS_KABYLAKE(dev_priv) || IS_SKYLAKE(dev_priv))
@@ -211,6 +208,9 @@ void intel_detect_pch(struct drm_i915_private *dev_priv)
 	if (IS_DG1(dev_priv)) {
 		dev_priv->pch_type = PCH_DG1;
 		return;
+	} else if (IS_DG2(dev_priv)) {
+		dev_priv->pch_type = PCH_DG2;
+		return;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e2f3f30c6445..7c0d83d292dc 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -30,6 +30,7 @@ enum intel_pch {
 
 	/* Fake PCHs, functionality handled on the same PCI dev */
 	PCH_DG1 = 1024,
+	PCH_DG2,
 };
 
 #define INTEL_PCH_DEVICE_ID_MASK		0xff80
@@ -62,6 +63,7 @@ enum intel_pch {
 
 #define INTEL_PCH_TYPE(dev_priv)		((dev_priv)->pch_type)
 #define INTEL_PCH_ID(dev_priv)			((dev_priv)->pch_id)
+#define HAS_PCH_DG2(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_DG2)
 #define HAS_PCH_ADP(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_ADP)
 #define HAS_PCH_DG1(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_DG1)
 #define HAS_PCH_JSP(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_JSP)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 45fefa0ed160..65bc3709f54c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1370,11 +1370,11 @@ static bool g4x_compute_fbc_en(const struct g4x_wm_state *wm_state,
 	return true;
 }
 
-static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
+static int g4x_compute_pipe_wm(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->uapi.state);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
 	int num_active_planes = hweight8(crtc_state->active_planes &
 					 ~BIT(PLANE_CURSOR));
@@ -1451,20 +1451,21 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	return 0;
 }
 
-static int g4x_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
+static int g4x_compute_intermediate_wm(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
 	struct g4x_wm_state *intermediate = &new_crtc_state->wm.g4x.intermediate;
 	const struct g4x_wm_state *optimal = &new_crtc_state->wm.g4x.optimal;
-	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->uapi.state);
-	const struct intel_crtc_state *old_crtc_state =
-		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct g4x_wm_state *active = &old_crtc_state->wm.g4x.optimal;
 	enum plane_id plane_id;
 
-	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
+	if (!new_crtc_state->hw.active ||
+	    drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -1890,12 +1891,12 @@ static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 		vlv_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level);
 }
 
-static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
+static int vlv_compute_pipe_wm(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->uapi.state);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
@@ -2095,19 +2096,20 @@ static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
 
 #undef VLV_FIFO
 
-static int vlv_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
+static int vlv_compute_intermediate_wm(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
+	struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
 	struct vlv_wm_state *intermediate = &new_crtc_state->wm.vlv.intermediate;
 	const struct vlv_wm_state *optimal = &new_crtc_state->wm.vlv.optimal;
-	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->uapi.state);
-	const struct intel_crtc_state *old_crtc_state =
-		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct vlv_wm_state *active = &old_crtc_state->wm.vlv.optimal;
 	int level;
 
-	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
+	if (!new_crtc_state->hw.active ||
+	    drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -2906,24 +2908,25 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 			if (wm[level] == 0) {
 				for (i = level + 1; i <= max_level; i++)
 					wm[i] = 0;
+
+				max_level = level - 1;
+
 				break;
 			}
 		}
 
 		/*
-		 * WaWmMemoryReadLatency:skl+,glk
+		 * WaWmMemoryReadLatency
 		 *
 		 * punit doesn't take into account the read latency so we need
-		 * to add 2us to the various latency levels we retrieve from the
-		 * punit when level 0 response data us 0us.
+		 * to add proper adjustement to each valid level we retrieve
+		 * from the punit when level 0 response data is 0us.
 		 */
 		if (wm[0] == 0) {
-			wm[0] += 2;
-			for (level = 1; level <= max_level; level++) {
-				if (wm[level] == 0)
-					break;
-				wm[level] += 2;
-			}
+			u8 adjust = DISPLAY_VER(dev_priv) >= 12 ? 3 : 2;
+
+			for (level = 0; level <= max_level; level++)
+				wm[level] += adjust;
 		}
 
 		/*
@@ -2934,7 +2937,6 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 		 */
 		if (dev_priv->dram_info.wm_lv_0_adjust_needed)
 			wm[0] += 1;
-
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		u64 sskpd = intel_uncore_read64(uncore, MCH_SSKPD);
 
@@ -3144,10 +3146,12 @@ static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
 }
 
 /* Compute new watermarks for the pipe */
-static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
+static int ilk_compute_pipe_wm(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_pipe_wm *pipe_wm;
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
@@ -3220,16 +3224,16 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
  * state and the new state.  These can be programmed to the hardware
  * immediately.
  */
-static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
-{
-	struct intel_crtc *intel_crtc = to_intel_crtc(newstate->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
-	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
-	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(newstate->uapi.state);
-	const struct intel_crtc_state *oldstate =
-		intel_atomic_get_old_crtc_state(intel_state, intel_crtc);
-	const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal;
+static int ilk_compute_intermediate_wm(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct intel_pipe_wm *a = &new_crtc_state->wm.ilk.intermediate;
+	const struct intel_pipe_wm *b = &old_crtc_state->wm.ilk.optimal;
 	int level, max_level = ilk_wm_max_level(dev_priv);
 
 	/*
@@ -3237,9 +3241,10 @@ static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 	 * currently active watermarks to get values that are safe both before
 	 * and after the vblank.
 	 */
-	*a = newstate->wm.ilk.optimal;
-	if (!newstate->hw.active || drm_atomic_crtc_needs_modeset(&newstate->uapi) ||
-	    intel_state->skip_intermediate_wm)
+	*a = new_crtc_state->wm.ilk.optimal;
+	if (!new_crtc_state->hw.active ||
+	    drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) ||
+	    state->skip_intermediate_wm)
 		return 0;
 
 	a->pipe_enabled |= b->pipe_enabled;
@@ -3270,8 +3275,8 @@ static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 	 * If our intermediate WM are identical to the final WM, then we can
 	 * omit the post-vblank programming; only update if it's different.
 	 */
-	if (memcmp(a, &newstate->wm.ilk.optimal, sizeof(*a)) != 0)
-		newstate->wm.need_postvbl_update = true;
+	if (memcmp(a, &new_crtc_state->wm.ilk.optimal, sizeof(*a)) != 0)
+		new_crtc_state->wm.need_postvbl_update = true;
 
 	return 0;
 }
@@ -3283,12 +3288,12 @@ static void ilk_merge_wm_level(struct drm_i915_private *dev_priv,
 			       int level,
 			       struct intel_wm_level *ret_wm)
 {
-	const struct intel_crtc *intel_crtc;
+	const struct intel_crtc *crtc;
 
 	ret_wm->enable = true;
 
-	for_each_intel_crtc(&dev_priv->drm, intel_crtc) {
-		const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk;
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		const struct intel_pipe_wm *active = &crtc->wm.active.ilk;
 		const struct intel_wm_level *wm = &active->wm[level];
 
 		if (!active->pipe_enabled)
@@ -3388,7 +3393,7 @@ static void ilk_compute_wm_results(struct drm_i915_private *dev_priv,
 				   enum intel_ddb_partitioning partitioning,
 				   struct ilk_wm_values *results)
 {
-	struct intel_crtc *intel_crtc;
+	struct intel_crtc *crtc;
 	int level, wm_lp;
 
 	results->enable_fbc_wm = merged->fbc_wm_enabled;
@@ -3433,9 +3438,9 @@ static void ilk_compute_wm_results(struct drm_i915_private *dev_priv,
 	}
 
 	/* LP0 register values */
-	for_each_intel_crtc(&dev_priv->drm, intel_crtc) {
-		enum pipe pipe = intel_crtc->pipe;
-		const struct intel_pipe_wm *pipe_wm = &intel_crtc->wm.active.ilk;
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		enum pipe pipe = crtc->pipe;
+		const struct intel_pipe_wm *pipe_wm = &crtc->wm.active.ilk;
 		const struct intel_wm_level *r = &pipe_wm->wm[0];
 
 		if (drm_WARN_ON(&dev_priv->drm, !r->enable))
@@ -4579,6 +4584,117 @@ static const struct dbuf_slice_conf_entry tgl_allowed_dbufs[] =
 	{}
 };
 
+static const struct dbuf_slice_conf_entry dg2_allowed_dbufs[] = {
+	{
+		.active_pipes = BIT(PIPE_A),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_B),
+		.dbuf_mask = {
+			[PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_B),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1),
+			[PIPE_B] = BIT(DBUF_S2),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_C),
+		.dbuf_mask = {
+			[PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_C),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_B) | BIT(PIPE_C),
+		.dbuf_mask = {
+			[PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1),
+			[PIPE_B] = BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_B) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1),
+			[PIPE_B] = BIT(DBUF_S2),
+			[PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_C) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_C] = BIT(DBUF_S3),
+			[PIPE_D] = BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3),
+			[PIPE_D] = BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3),
+			[PIPE_D] = BIT(DBUF_S4),
+		},
+	},
+	{
+		.active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
+		.dbuf_mask = {
+			[PIPE_A] = BIT(DBUF_S1),
+			[PIPE_B] = BIT(DBUF_S2),
+			[PIPE_C] = BIT(DBUF_S3),
+			[PIPE_D] = BIT(DBUF_S4),
+		},
+	},
+	{}
+};
+
 static const struct dbuf_slice_conf_entry adlp_allowed_dbufs[] = {
 	{
 		.active_pipes = BIT(PIPE_A),
@@ -4754,12 +4870,19 @@ static u32 adlp_compute_dbuf_slices(enum pipe pipe, u32 active_pipes)
 	return compute_dbuf_slices(pipe, active_pipes, adlp_allowed_dbufs);
 }
 
+static u32 dg2_compute_dbuf_slices(enum pipe pipe, u32 active_pipes)
+{
+	return compute_dbuf_slices(pipe, active_pipes, dg2_allowed_dbufs);
+}
+
 static u8 skl_compute_dbuf_slices(struct intel_crtc *crtc, u8 active_pipes)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_DG2(dev_priv))
+		return dg2_compute_dbuf_slices(pipe, active_pipes);
+	else if (IS_ALDERLAKE_P(dev_priv))
 		return adlp_compute_dbuf_slices(pipe, active_pipes);
 	else if (DISPLAY_VER(dev_priv) == 12)
 		return tgl_compute_dbuf_slices(pipe, active_pipes);
@@ -7340,30 +7463,24 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN,
 		   ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
 
-	/* This is not an Wa. Enable to reduce Sampler power */
-	intel_uncore_write(&dev_priv->uncore, GEN10_DFR_RATIO_EN_AND_CHICKEN,
-		   intel_uncore_read(&dev_priv->uncore, GEN10_DFR_RATIO_EN_AND_CHICKEN) & ~DFR_DISABLE);
-
 	/*Wa_14010594013:icl, ehl */
 	intel_uncore_rmw(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1,
-			 0, CNL_DELAY_PMRSP);
+			 0, ICL_DELAY_PMRSP);
 }
 
 static void gen12lp_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	/* Wa_1409120013:tgl,rkl,adl_s,dg1 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN,
-			   ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
+	/* Wa_1409120013:tgl,rkl,adl-s,dg1 */
+	if (IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv) ||
+	    IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv))
+		intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN,
+				   ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
 
 	/* Wa_1409825376:tgl (pre-prod)*/
-	if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B1))
+	if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0))
 		intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) |
 			   TGL_VRH_GATING_DIS);
 
-	/* Wa_14011059788:tgl,rkl,adl_s,dg1 */
-	intel_uncore_rmw(&dev_priv->uncore, GEN10_DFR_RATIO_EN_AND_CHICKEN,
-			 0, DFR_DISABLE);
-
 	/* Wa_14013723622:tgl,rkl,dg1,adl-s */
 	if (DISPLAY_VER(dev_priv) == 12)
 		intel_uncore_rmw(&dev_priv->uncore, CLKREQ_POLICY,
@@ -7383,7 +7500,7 @@ static void dg1_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen12lp_init_clock_gating(dev_priv);
 
 	/* Wa_1409836686:dg1[a0] */
-	if (IS_DG1_REVID(dev_priv, DG1_REVID_A0, DG1_REVID_A0))
+	if (IS_DG1_GT_STEP(dev_priv, STEP_A0, STEP_B0))
 		intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) |
 			   DPT_GATING_DIS);
 }
@@ -7398,43 +7515,6 @@ static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
 		   CNP_PWM_CGE_GATING_DISABLE);
 }
 
-static void cnl_init_clock_gating(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-	cnp_init_clock_gating(dev_priv);
-
-	/* This is not an Wa. Enable for better image quality */
-	intel_uncore_write(&dev_priv->uncore, _3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE));
-
-	/* WaEnableChickenDCPR:cnl */
-	intel_uncore_write(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1,
-		   intel_uncore_read(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
-
-	/*
-	 * WaFbcWakeMemOn:cnl
-	 * Display WA #0859: cnl
-	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_MEMORY_WAKE);
-
-	val = intel_uncore_read(&dev_priv->uncore, SLICE_UNIT_LEVEL_CLKGATE);
-	/* ReadHitWriteOnlyDisable:cnl */
-	val |= RCCUNIT_CLKGATE_DIS;
-	intel_uncore_write(&dev_priv->uncore, SLICE_UNIT_LEVEL_CLKGATE, val);
-
-	/* Wa_2201832410:cnl */
-	val = intel_uncore_read(&dev_priv->uncore, SUBSLICE_UNIT_LEVEL_CLKGATE);
-	val |= GWUNIT_CLKGATE_DIS;
-	intel_uncore_write(&dev_priv->uncore, SUBSLICE_UNIT_LEVEL_CLKGATE, val);
-
-	/* WaDisableVFclkgate:cnl */
-	/* WaVFUnitClockGatingDisable:cnl */
-	val = intel_uncore_read(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE);
-	val |= VFUNIT_CLKGATE_DIS;
-	intel_uncore_write(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE, val);
-}
-
 static void cfl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	cnp_init_clock_gating(dev_priv);
@@ -7468,12 +7548,12 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 		   FBC_LLC_FULLY_OPEN);
 
 	/* WaDisableSDEUnitClockGating:kbl */
-	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0))
 		intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
 			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableGamClockGating:kbl */
-	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0))
 		intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) |
 			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
 
@@ -7863,8 +7943,6 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.init_clock_gating = gen12lp_init_clock_gating;
 	else if (GRAPHICS_VER(dev_priv) == 11)
 		dev_priv->display.init_clock_gating = icl_init_clock_gating;
-	else if (IS_CANNONLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = cnl_init_clock_gating;
 	else if (IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv))
 		dev_priv->display.init_clock_gating = cfl_init_clock_gating;
 	else if (IS_SKYLAKE(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 82a6727ede46..98c7339bf8ba 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -8,9 +8,11 @@
 
 #include "i915_drv.h"
 #include "i915_scatterlist.h"
+#include "i915_ttm_buddy_manager.h"
 
 #include "intel_region_ttm.h"
 
+#include "gem/i915_gem_ttm.h" /* For the funcs/ops export only */
 /**
  * DOC: TTM support structure
  *
@@ -20,9 +22,6 @@
  * i915 GEM regions to TTM memory types and resource managers.
  */
 
-/* A Zero-initialized driver for now. We don't have a TTM backend yet. */
-static struct ttm_device_funcs i915_ttm_bo_driver;
-
 /**
  * intel_region_ttm_device_init - Initialize a TTM device
  * @dev_priv: Pointer to an i915 device private structure.
@@ -33,7 +32,7 @@ int intel_region_ttm_device_init(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *drm = &dev_priv->drm;
 
-	return ttm_device_init(&dev_priv->bdev, &i915_ttm_bo_driver,
+	return ttm_device_init(&dev_priv->bdev, i915_ttm_driver(),
 			       drm->dev, drm->anon_inode->i_mapping,
 			       drm->vma_offset_manager, false, false);
 }
@@ -52,12 +51,16 @@ void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv)
  * driver-private types for now, reserving TTM_PL_VRAM for stolen
  * memory and TTM_PL_TT for GGTT use if decided to implement this.
  */
-static int intel_region_to_ttm_type(struct intel_memory_region *mem)
+int intel_region_to_ttm_type(const struct intel_memory_region *mem)
 {
 	int type;
 
 	GEM_BUG_ON(mem->type != INTEL_MEMORY_LOCAL &&
-		   mem->type != INTEL_MEMORY_MOCK);
+		   mem->type != INTEL_MEMORY_MOCK &&
+		   mem->type != INTEL_MEMORY_SYSTEM);
+
+	if (mem->type == INTEL_MEMORY_SYSTEM)
+		return TTM_PL_SYSTEM;
 
 	type = mem->instance + TTM_PL_PRIV;
 	GEM_BUG_ON(type >= TTM_NUM_MEM_TYPES);
@@ -65,72 +68,29 @@ static int intel_region_to_ttm_type(struct intel_memory_region *mem)
 	return type;
 }
 
-static struct ttm_resource *
-intel_region_ttm_node_reserve(struct intel_memory_region *mem,
-			      resource_size_t offset,
-			      resource_size_t size)
-{
-	struct ttm_resource_manager *man = mem->region_private;
-	struct ttm_place place = {};
-	struct ttm_buffer_object mock_bo = {};
-	struct ttm_resource *res;
-	int ret;
-
-	/*
-	 * Having to use a mock_bo is unfortunate but stems from some
-	 * drivers having private managers that insist to know what the
-	 * allocate memory is intended for, using it to send private
-	 * data to the manager. Also recently the bo has been used to send
-	 * alignment info to the manager. Assume that apart from the latter,
-	 * none of the managers we use will ever access the buffer object
-	 * members, hoping we can pass the alignment info in the
-	 * struct ttm_place in the future.
-	 */
-
-	place.fpfn = offset >> PAGE_SHIFT;
-	place.lpfn = place.fpfn + (size >> PAGE_SHIFT);
-	mock_bo.base.size = size;
-	ret = man->func->alloc(man, &mock_bo, &place, &res);
-	if (ret == -ENOSPC)
-		ret = -ENXIO;
-
-	return ret ? ERR_PTR(ret) : res;
-}
-
 /**
- * intel_region_ttm_node_free - Free a node allocated from a resource manager
- * @mem: The region the node was allocated from.
- * @node: The opaque node representing an allocation.
+ * intel_region_ttm_init - Initialize a memory region for TTM.
+ * @mem: The region to initialize.
+ *
+ * This function initializes a suitable TTM resource manager for the
+ * region, and if it's a LMEM region type, attaches it to the TTM
+ * device. MOCK regions are NOT attached to the TTM device, since we don't
+ * have one for the mock selftests.
+ *
+ * Return: 0 on success, negative error code on failure.
  */
-void intel_region_ttm_node_free(struct intel_memory_region *mem,
-				struct ttm_resource *res)
-{
-	struct ttm_resource_manager *man = mem->region_private;
-
-	man->func->free(man, res);
-}
-
-static const struct intel_memory_region_private_ops priv_ops = {
-	.reserve = intel_region_ttm_node_reserve,
-	.free = intel_region_ttm_node_free,
-};
-
 int intel_region_ttm_init(struct intel_memory_region *mem)
 {
 	struct ttm_device *bdev = &mem->i915->bdev;
 	int mem_type = intel_region_to_ttm_type(mem);
 	int ret;
 
-	ret = ttm_range_man_init(bdev, mem_type, false,
-				 resource_size(&mem->region) >> PAGE_SHIFT);
+	ret = i915_ttm_buddy_man_init(bdev, mem_type, false,
+				      resource_size(&mem->region),
+				      mem->min_page_size, PAGE_SIZE);
 	if (ret)
 		return ret;
 
-	mem->chunk_size = PAGE_SIZE;
-	mem->max_order =
-		get_order(rounddown_pow_of_two(resource_size(&mem->region)));
-	mem->is_range_manager = true;
-	mem->priv_ops = &priv_ops;
 	mem->region_private = ttm_manager_type(bdev, mem_type);
 
 	return 0;
@@ -148,17 +108,17 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
 {
 	int ret;
 
-	ret = ttm_range_man_fini(&mem->i915->bdev,
-				 intel_region_to_ttm_type(mem));
+	ret = i915_ttm_buddy_man_fini(&mem->i915->bdev,
+				      intel_region_to_ttm_type(mem));
 	GEM_WARN_ON(ret);
 	mem->region_private = NULL;
 }
 
 /**
- * intel_region_ttm_node_to_st - Convert an opaque TTM resource manager node
+ * intel_region_ttm_resource_to_st - Convert an opaque TTM resource manager resource
  * to an sg_table.
  * @mem: The memory region.
- * @node: The resource manager node obtained from the TTM resource manager.
+ * @res: The resource manager resource obtained from the TTM resource manager.
  *
  * The gem backends typically use sg-tables for operations on the underlying
  * io_memory. So provide a way for the backends to translate the
@@ -166,19 +126,23 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
  *
  * Return: A malloced sg_table on success, an error pointer on failure.
  */
-struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
-					     struct ttm_resource *res)
+struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
+						 struct ttm_resource *res)
 {
-	struct ttm_range_mgr_node *range_node =
-		container_of(res, typeof(*range_node), base);
+	if (mem->is_range_manager) {
+		struct ttm_range_mgr_node *range_node =
+			to_ttm_range_mgr_node(res);
 
-	GEM_WARN_ON(!mem->is_range_manager);
-	return i915_sg_from_mm_node(&range_node->mm_nodes[0],
-				    mem->region.start);
+		return i915_sg_from_mm_node(&range_node->mm_nodes[0],
+					    mem->region.start);
+	} else {
+		return i915_sg_from_buddy_resource(res, mem->region.start);
+	}
 }
 
+#ifdef CONFIG_DRM_I915_SELFTEST
 /**
- * intel_region_ttm_node_alloc - Allocate memory resources from a region
+ * intel_region_ttm_resource_alloc - Allocate memory resources from a region
  * @mem: The memory region,
  * @size: The requested size in bytes
  * @flags: Allocation flags
@@ -187,15 +151,15 @@ struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
  * memory from standalone TTM range managers, without the TTM eviction
  * functionality. Don't use if you are not completely sure that's the
  * case. The returned opaque node can be converted to an sg_table using
- * intel_region_ttm_node_to_st(), and can be freed using
- * intel_region_ttm_node_free().
+ * intel_region_ttm_resource_to_st(), and can be freed using
+ * intel_region_ttm_resource_free().
  *
  * Return: A valid pointer on success, an error pointer on failure.
  */
 struct ttm_resource *
-intel_region_ttm_node_alloc(struct intel_memory_region *mem,
-			    resource_size_t size,
-			    unsigned int flags)
+intel_region_ttm_resource_alloc(struct intel_memory_region *mem,
+				resource_size_t size,
+				unsigned int flags)
 {
 	struct ttm_resource_manager *man = mem->region_private;
 	struct ttm_place place = {};
@@ -203,24 +167,26 @@ intel_region_ttm_node_alloc(struct intel_memory_region *mem,
 	struct ttm_resource *res;
 	int ret;
 
-	/*
-	 * We ignore the flags for now since we're using the range
-	 * manager and contigous and min page size would be fulfilled
-	 * by default if size is min page size aligned.
-	 */
 	mock_bo.base.size = size;
-
-	if (mem->is_range_manager) {
-		if (size >= SZ_1G)
-			mock_bo.page_alignment = SZ_1G >> PAGE_SHIFT;
-		else if (size >= SZ_2M)
-			mock_bo.page_alignment = SZ_2M >> PAGE_SHIFT;
-		else if (size >= SZ_64K)
-			mock_bo.page_alignment = SZ_64K >> PAGE_SHIFT;
-	}
+	place.flags = flags;
 
 	ret = man->func->alloc(man, &mock_bo, &place, &res);
 	if (ret == -ENOSPC)
 		ret = -ENXIO;
 	return ret ? ERR_PTR(ret) : res;
 }
+
+#endif
+
+/**
+ * intel_region_ttm_resource_free - Free a resource allocated from a resource manager
+ * @mem: The region the resource was allocated from.
+ * @res: The opaque resource representing an allocation.
+ */
+void intel_region_ttm_resource_free(struct intel_memory_region *mem,
+				    struct ttm_resource *res)
+{
+	struct ttm_resource_manager *man = mem->region_private;
+
+	man->func->free(man, res);
+}
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
index 11b0574ab791..6f44075920f2 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.h
+++ b/drivers/gpu/drm/i915/intel_region_ttm.h
@@ -12,6 +12,7 @@
 struct drm_i915_private;
 struct intel_memory_region;
 struct ttm_resource;
+struct ttm_device_funcs;
 
 int intel_region_ttm_device_init(struct drm_i915_private *dev_priv);
 
@@ -21,14 +22,20 @@ int intel_region_ttm_init(struct intel_memory_region *mem);
 
 void intel_region_ttm_fini(struct intel_memory_region *mem);
 
-struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
-					     struct ttm_resource *res);
+struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
+						 struct ttm_resource *res);
 
-struct ttm_resource *
-intel_region_ttm_node_alloc(struct intel_memory_region *mem,
-			    resource_size_t size,
-			    unsigned int flags);
+void intel_region_ttm_resource_free(struct intel_memory_region *mem,
+				    struct ttm_resource *res);
+
+int intel_region_to_ttm_type(const struct intel_memory_region *mem);
 
-void intel_region_ttm_node_free(struct intel_memory_region *mem,
-				struct ttm_resource *node);
+struct ttm_device_funcs *i915_ttm_driver(void);
+
+#ifdef CONFIG_DRM_I915_SELFTEST
+struct ttm_resource *
+intel_region_ttm_resource_alloc(struct intel_memory_region *mem,
+				resource_size_t size,
+				unsigned int flags);
+#endif
 #endif /* _INTEL_REGION_TTM_H_ */
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index f0a82b37bd1a..e304bf44e1ff 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -556,17 +556,22 @@ out:
 #undef COND
 }
 
-void intel_pcode_init(struct drm_i915_private *i915)
+int intel_pcode_init(struct drm_i915_private *i915)
 {
-	int ret;
+	int ret = 0;
 
 	if (!IS_DGFX(i915))
-		return;
+		return ret;
 
 	ret = skl_pcode_request(i915, DG1_PCODE_STATUS,
 				DG1_UNCORE_GET_INIT_STATUS,
 				DG1_UNCORE_INIT_STATUS_COMPLETE,
-				DG1_UNCORE_INIT_STATUS_COMPLETE, 50);
+				DG1_UNCORE_INIT_STATUS_COMPLETE, 180000);
+
+	drm_dbg(&i915->drm, "PCODE init status %d\n", ret);
+
 	if (ret)
 		drm_err(&i915->drm, "Pcode did not report uncore initialization completion!\n");
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_sideband.h b/drivers/gpu/drm/i915/intel_sideband.h
index 094c7b19c5d4..d1d14bcb8f56 100644
--- a/drivers/gpu/drm/i915/intel_sideband.h
+++ b/drivers/gpu/drm/i915/intel_sideband.h
@@ -138,6 +138,6 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, u32 mbox,
 int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request,
 		      u32 reply_mask, u32 reply, int timeout_base_ms);
 
-void intel_pcode_init(struct drm_i915_private *i915);
+int intel_pcode_init(struct drm_i915_private *i915);
 
 #endif /* _INTEL_SIDEBAND_H */
diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c
index ba9479a67521..6cf967631395 100644
--- a/drivers/gpu/drm/i915/intel_step.c
+++ b/drivers/gpu/drm/i915/intel_step.c
@@ -7,16 +7,32 @@
 #include "intel_step.h"
 
 /*
- * KBL revision ID ordering is bizarre; higher revision ID's map to lower
- * steppings in some cases.  So rather than test against the revision ID
- * directly, let's map that into our own range of increasing ID's that we
- * can test against in a regular manner.
+ * Some platforms have unusual ways of mapping PCI revision ID to GT/display
+ * steppings.  E.g., in some cases a higher PCI revision may translate to a
+ * lower stepping of the GT and/or display IP.  This file provides lookup
+ * tables to map the PCI revision into a standard set of stepping values that
+ * can be compared numerically.
+ *
+ * Also note that some revisions/steppings may have been set aside as
+ * placeholders but never materialized in real hardware; in those cases there
+ * may be jumps in the revision IDs or stepping values in the tables below.
  */
 
+/*
+ * Some platforms always have the same stepping value for GT and display;
+ * use a macro to define these to make it easier to identify the platforms
+ * where the two steppings can deviate.
+ */
+#define COMMON_STEP(x)  .gt_step = STEP_##x, .display_step = STEP_##x
+
+static const struct intel_step_info skl_revids[] = {
+	[0x6] = { COMMON_STEP(G0) },
+	[0x7] = { COMMON_STEP(H0) },
+	[0x9] = { COMMON_STEP(J0) },
+	[0xA] = { COMMON_STEP(I1) },
+};
 
-/* FIXME: what about REVID_E0 */
 static const struct intel_step_info kbl_revids[] = {
-	[0] = { .gt_step = STEP_A0, .display_step = STEP_A0 },
 	[1] = { .gt_step = STEP_B0, .display_step = STEP_B0 },
 	[2] = { .gt_step = STEP_C0, .display_step = STEP_B0 },
 	[3] = { .gt_step = STEP_D0, .display_step = STEP_B0 },
@@ -26,7 +42,27 @@ static const struct intel_step_info kbl_revids[] = {
 	[7] = { .gt_step = STEP_G0, .display_step = STEP_C0 },
 };
 
-static const struct intel_step_info tgl_uy_revid_step_tbl[] = {
+static const struct intel_step_info bxt_revids[] = {
+	[0xA] = { COMMON_STEP(C0) },
+	[0xB] = { COMMON_STEP(C0) },
+	[0xC] = { COMMON_STEP(D0) },
+	[0xD] = { COMMON_STEP(E0) },
+};
+
+static const struct intel_step_info glk_revids[] = {
+	[3] = { COMMON_STEP(B0) },
+};
+
+static const struct intel_step_info icl_revids[] = {
+	[7] = { COMMON_STEP(D0) },
+};
+
+static const struct intel_step_info jsl_ehl_revids[] = {
+	[0] = { COMMON_STEP(A0) },
+	[1] = { COMMON_STEP(B0) },
+};
+
+static const struct intel_step_info tgl_uy_revids[] = {
 	[0] = { .gt_step = STEP_A0, .display_step = STEP_A0 },
 	[1] = { .gt_step = STEP_B0, .display_step = STEP_C0 },
 	[2] = { .gt_step = STEP_B1, .display_step = STEP_C0 },
@@ -34,12 +70,23 @@ static const struct intel_step_info tgl_uy_revid_step_tbl[] = {
 };
 
 /* Same GT stepping between tgl_uy_revids and tgl_revids don't mean the same HW */
-static const struct intel_step_info tgl_revid_step_tbl[] = {
+static const struct intel_step_info tgl_revids[] = {
 	[0] = { .gt_step = STEP_A0, .display_step = STEP_B0 },
 	[1] = { .gt_step = STEP_B0, .display_step = STEP_D0 },
 };
 
-static const struct intel_step_info adls_revid_step_tbl[] = {
+static const struct intel_step_info rkl_revids[] = {
+	[0] = { COMMON_STEP(A0) },
+	[1] = { COMMON_STEP(B0) },
+	[4] = { COMMON_STEP(C0) },
+};
+
+static const struct intel_step_info dg1_revids[] = {
+	[0] = { COMMON_STEP(A0) },
+	[1] = { COMMON_STEP(B0) },
+};
+
+static const struct intel_step_info adls_revids[] = {
 	[0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 },
 	[0x1] = { .gt_step = STEP_A0, .display_step = STEP_A2 },
 	[0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 },
@@ -47,13 +94,33 @@ static const struct intel_step_info adls_revid_step_tbl[] = {
 	[0xC] = { .gt_step = STEP_D0, .display_step = STEP_C0 },
 };
 
-static const struct intel_step_info adlp_revid_step_tbl[] = {
+static const struct intel_step_info adlp_revids[] = {
 	[0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 },
 	[0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 },
 	[0x8] = { .gt_step = STEP_C0, .display_step = STEP_C0 },
 	[0xC] = { .gt_step = STEP_C0, .display_step = STEP_D0 },
 };
 
+static const struct intel_step_info xehpsdv_revids[] = {
+	[0x0] = { .gt_step = STEP_A0 },
+	[0x1] = { .gt_step = STEP_A1 },
+	[0x4] = { .gt_step = STEP_B0 },
+	[0x8] = { .gt_step = STEP_C0 },
+};
+
+static const struct intel_step_info dg2_g10_revid_step_tbl[] = {
+	[0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 },
+	[0x1] = { .gt_step = STEP_A1, .display_step = STEP_A0 },
+	[0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 },
+	[0x8] = { .gt_step = STEP_C0, .display_step = STEP_C0 },
+};
+
+static const struct intel_step_info dg2_g11_revid_step_tbl[] = {
+	[0x0] = { .gt_step = STEP_A0, .display_step = STEP_B0 },
+	[0x4] = { .gt_step = STEP_B0, .display_step = STEP_C0 },
+	[0x5] = { .gt_step = STEP_B1, .display_step = STEP_C0 },
+};
+
 void intel_step_init(struct drm_i915_private *i915)
 {
 	const struct intel_step_info *revids = NULL;
@@ -61,21 +128,51 @@ void intel_step_init(struct drm_i915_private *i915)
 	int revid = INTEL_REVID(i915);
 	struct intel_step_info step = {};
 
-	if (IS_ALDERLAKE_P(i915)) {
-		revids = adlp_revid_step_tbl;
-		size = ARRAY_SIZE(adlp_revid_step_tbl);
+	if (IS_DG2_G10(i915)) {
+		revids = dg2_g10_revid_step_tbl;
+		size = ARRAY_SIZE(dg2_g10_revid_step_tbl);
+	} else if (IS_DG2_G11(i915)) {
+		revids = dg2_g11_revid_step_tbl;
+		size = ARRAY_SIZE(dg2_g11_revid_step_tbl);
+	} else if (IS_XEHPSDV(i915)) {
+		revids = xehpsdv_revids;
+		size = ARRAY_SIZE(xehpsdv_revids);
+	} else if (IS_ALDERLAKE_P(i915)) {
+		revids = adlp_revids;
+		size = ARRAY_SIZE(adlp_revids);
 	} else if (IS_ALDERLAKE_S(i915)) {
-		revids = adls_revid_step_tbl;
-		size = ARRAY_SIZE(adls_revid_step_tbl);
+		revids = adls_revids;
+		size = ARRAY_SIZE(adls_revids);
+	} else if (IS_DG1(i915)) {
+		revids = dg1_revids;
+		size = ARRAY_SIZE(dg1_revids);
+	} else if (IS_ROCKETLAKE(i915)) {
+		revids = rkl_revids;
+		size = ARRAY_SIZE(rkl_revids);
 	} else if (IS_TGL_U(i915) || IS_TGL_Y(i915)) {
-		revids = tgl_uy_revid_step_tbl;
-		size = ARRAY_SIZE(tgl_uy_revid_step_tbl);
+		revids = tgl_uy_revids;
+		size = ARRAY_SIZE(tgl_uy_revids);
 	} else if (IS_TIGERLAKE(i915)) {
-		revids = tgl_revid_step_tbl;
-		size = ARRAY_SIZE(tgl_revid_step_tbl);
+		revids = tgl_revids;
+		size = ARRAY_SIZE(tgl_revids);
+	} else if (IS_JSL_EHL(i915)) {
+		revids = jsl_ehl_revids;
+		size = ARRAY_SIZE(jsl_ehl_revids);
+	} else if (IS_ICELAKE(i915)) {
+		revids = icl_revids;
+		size = ARRAY_SIZE(icl_revids);
+	} else if (IS_GEMINILAKE(i915)) {
+		revids = glk_revids;
+		size = ARRAY_SIZE(glk_revids);
+	} else if (IS_BROXTON(i915)) {
+		revids = bxt_revids;
+		size = ARRAY_SIZE(bxt_revids);
 	} else if (IS_KABYLAKE(i915)) {
 		revids = kbl_revids;
 		size = ARRAY_SIZE(kbl_revids);
+	} else if (IS_SKYLAKE(i915)) {
+		revids = skl_revids;
+		size = ARRAY_SIZE(skl_revids);
 	}
 
 	/* Not using the stepping scheme for the platform yet. */
@@ -114,3 +211,17 @@ void intel_step_init(struct drm_i915_private *i915)
 
 	RUNTIME_INFO(i915)->step = step;
 }
+
+#define STEP_NAME_CASE(name)	\
+	case STEP_##name:	\
+		return #name;
+
+const char *intel_step_name(enum intel_step step)
+{
+	switch (step) {
+	STEP_NAME_LIST(STEP_NAME_CASE);
+
+	default:
+		return "**";
+	}
+}
diff --git a/drivers/gpu/drm/i915/intel_step.h b/drivers/gpu/drm/i915/intel_step.h
index 958a8bb5d677..f6641e2a3c77 100644
--- a/drivers/gpu/drm/i915/intel_step.h
+++ b/drivers/gpu/drm/i915/intel_step.h
@@ -15,26 +15,39 @@ struct intel_step_info {
 	u8 display_step;
 };
 
+#define STEP_ENUM_VAL(name)  STEP_##name,
+
+#define STEP_NAME_LIST(func)		\
+	func(A0)			\
+	func(A1)			\
+	func(A2)			\
+	func(B0)			\
+	func(B1)			\
+	func(B2)			\
+	func(C0)			\
+	func(C1)			\
+	func(D0)			\
+	func(D1)			\
+	func(E0)			\
+	func(F0)			\
+	func(G0)			\
+	func(H0)			\
+	func(I0)			\
+	func(I1)			\
+	func(J0)
+
 /*
  * Symbolic steppings that do not match the hardware. These are valid both as gt
  * and display steppings as symbolic names.
  */
 enum intel_step {
 	STEP_NONE = 0,
-	STEP_A0,
-	STEP_A2,
-	STEP_B0,
-	STEP_B1,
-	STEP_C0,
-	STEP_D0,
-	STEP_D1,
-	STEP_E0,
-	STEP_F0,
-	STEP_G0,
+	STEP_NAME_LIST(STEP_ENUM_VAL)
 	STEP_FUTURE,
 	STEP_FOREVER,
 };
 
 void intel_step_init(struct drm_i915_private *i915);
+const char *intel_step_name(enum intel_step step);
 
 #endif /* __INTEL_STEP_H__ */
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 1bed8f666048..6b38bc2811c1 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -24,6 +24,8 @@
 #include <linux/pm_runtime.h>
 #include <asm/iosf_mbi.h>
 
+#include "gt/intel_lrc_reg.h" /* for shadow reg list */
+
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
@@ -68,8 +70,14 @@ static const char * const forcewake_domain_names[] = {
 	"vdbox1",
 	"vdbox2",
 	"vdbox3",
+	"vdbox4",
+	"vdbox5",
+	"vdbox6",
+	"vdbox7",
 	"vebox0",
 	"vebox1",
+	"vebox2",
+	"vebox3",
 };
 
 const char *
@@ -952,30 +960,80 @@ static const i915_reg_t gen8_shadowed_regs[] = {
 };
 
 static const i915_reg_t gen11_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),		/* 0x2000 (base) */
-	GEN6_RPNSWREQ,				/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,			/* 0xA00C */
-	RING_TAIL(BLT_RING_BASE),		/* 0x22000 (base) */
-	RING_TAIL(GEN11_BSD_RING_BASE),		/* 0x1C0000 (base) */
-	RING_TAIL(GEN11_BSD2_RING_BASE),	/* 0x1C4000 (base) */
-	RING_TAIL(GEN11_VEBOX_RING_BASE),	/* 0x1C8000 (base) */
-	RING_TAIL(GEN11_BSD3_RING_BASE),	/* 0x1D0000 (base) */
-	RING_TAIL(GEN11_BSD4_RING_BASE),	/* 0x1D4000 (base) */
-	RING_TAIL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8000 (base) */
+	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
+	RING_EXECLIST_CONTROL(RENDER_RING_BASE),        /* 0x2550 */
+	GEN6_RPNSWREQ,					/* 0xA008 */
+	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
+	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
+	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
+	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
+	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
+	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
+	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
+	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
+	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
 	/* TODO: Other registers are not yet used */
 };
 
 static const i915_reg_t gen12_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),		/* 0x2000 (base) */
-	GEN6_RPNSWREQ,				/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,			/* 0xA00C */
-	RING_TAIL(BLT_RING_BASE),		/* 0x22000 (base) */
-	RING_TAIL(GEN11_BSD_RING_BASE),		/* 0x1C0000 (base) */
-	RING_TAIL(GEN11_BSD2_RING_BASE),	/* 0x1C4000 (base) */
-	RING_TAIL(GEN11_VEBOX_RING_BASE),	/* 0x1C8000 (base) */
-	RING_TAIL(GEN11_BSD3_RING_BASE),	/* 0x1D0000 (base) */
-	RING_TAIL(GEN11_BSD4_RING_BASE),	/* 0x1D4000 (base) */
-	RING_TAIL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8000 (base) */
+	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
+	RING_EXECLIST_CONTROL(RENDER_RING_BASE),	/* 0x2550 */
+	GEN6_RPNSWREQ,					/* 0xA008 */
+	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
+	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
+	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
+	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
+	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
+	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
+	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
+	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
+	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
+	/* TODO: Other registers are not yet used */
+};
+
+static const i915_reg_t xehp_shadowed_regs[] = {
+	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
+	RING_EXECLIST_CONTROL(RENDER_RING_BASE),        /* 0x2550 */
+	GEN6_RPNSWREQ,					/* 0xA008 */
+	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
+	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
+	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
+	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
+	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
+	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
+	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
+	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
+	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
+	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
+	RING_TAIL(XEHP_BSD5_RING_BASE),			/* 0x1E0000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_BSD5_RING_BASE),	/* 0x1E0550 */
+	RING_TAIL(XEHP_BSD6_RING_BASE),			/* 0x1E4000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_BSD6_RING_BASE),	/* 0x1E4550 */
+	RING_TAIL(XEHP_VEBOX3_RING_BASE),		/* 0x1E8000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_VEBOX3_RING_BASE),	/* 0x1E8550 */
+	RING_TAIL(XEHP_BSD7_RING_BASE),			/* 0x1F0000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_BSD7_RING_BASE),	/* 0x1F0550 */
+	RING_TAIL(XEHP_BSD8_RING_BASE),			/* 0x1F4000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_BSD8_RING_BASE),	/* 0x1F4550 */
+	RING_TAIL(XEHP_VEBOX4_RING_BASE),		/* 0x1F8000 (base) */
+	RING_EXECLIST_CONTROL(XEHP_VEBOX4_RING_BASE),	/* 0x1F8550 */
 	/* TODO: Other registers are not yet used */
 };
 
@@ -991,17 +1049,18 @@ static int mmio_reg_cmp(u32 key, const i915_reg_t *reg)
 		return 0;
 }
 
-#define __is_genX_shadowed(x) \
-static bool is_gen##x##_shadowed(u32 offset) \
+#define __is_X_shadowed(x) \
+static bool is_##x##_shadowed(u32 offset) \
 { \
-	const i915_reg_t *regs = gen##x##_shadowed_regs; \
-	return BSEARCH(offset, regs, ARRAY_SIZE(gen##x##_shadowed_regs), \
+	const i915_reg_t *regs = x##_shadowed_regs; \
+	return BSEARCH(offset, regs, ARRAY_SIZE(x##_shadowed_regs), \
 		       mmio_reg_cmp); \
 }
 
-__is_genX_shadowed(8)
-__is_genX_shadowed(11)
-__is_genX_shadowed(12)
+__is_X_shadowed(gen8)
+__is_X_shadowed(gen11)
+__is_X_shadowed(gen12)
+__is_X_shadowed(xehp)
 
 static enum forcewake_domains
 gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg)
@@ -1065,6 +1124,15 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = {
 	__fwd; \
 })
 
+#define __xehp_fwtable_reg_write_fw_domains(uncore, offset) \
+({ \
+	enum forcewake_domains __fwd = 0; \
+	const u32 __offset = (offset); \
+	if (!is_xehp_shadowed(__offset)) \
+		__fwd = find_fw_domain(uncore, __offset); \
+	__fwd; \
+})
+
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
 static const struct intel_forcewake_range __gen9_fw_ranges[] = {
 	GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_GT),
@@ -1249,6 +1317,172 @@ static const struct intel_forcewake_range __gen12_fw_ranges[] = {
 		0x1d3f00 - 0x1d3fff: VD2 */
 };
 
+/*
+ * Graphics IP version 12.55 brings a slight change to the 0xd800 range,
+ * switching it from the GT domain to the render domain.
+ *
+ * *Must* be sorted by offset ranges! See intel_fw_table_check().
+ */
+#define XEHP_FWRANGES(FW_RANGE_D800)					\
+	GEN_FW_RANGE(0x0, 0x1fff, 0), /*					\
+		  0x0 -  0xaff: reserved					\
+		0xb00 - 0x1fff: always on */					\
+	GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0x2700, 0x4aff, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0x4b00, 0x51ff, 0), /*					\
+		0x4b00 - 0x4fff: reserved					\
+		0x5000 - 0x51ff: always on */					\
+	GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0x8000, 0x813f, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0x8140, 0x815f, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0x8160, 0x81ff, 0), /*					\
+		0x8160 - 0x817f: reserved					\
+		0x8180 - 0x81ff: always on */					\
+	GEN_FW_RANGE(0x8200, 0x82ff, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0x8300, 0x84ff, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0x8500, 0x8cff, FORCEWAKE_GT), /*				\
+		0x8500 - 0x87ff: gt						\
+		0x8800 - 0x8c7f: reserved					\
+		0x8c80 - 0x8cff: gt (DG2 only) */				\
+	GEN_FW_RANGE(0x8d00, 0x8fff, FORCEWAKE_RENDER), /*			\
+		0x8d00 - 0x8dff: render (DG2 only)				\
+		0x8e00 - 0x8fff: reserved */					\
+	GEN_FW_RANGE(0x9000, 0x94cf, FORCEWAKE_GT), /*				\
+		0x9000 - 0x947f: gt						\
+		0x9480 - 0x94cf: reserved */					\
+	GEN_FW_RANGE(0x94d0, 0x955f, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0x9560, 0x967f, 0), /*					\
+		0x9560 - 0x95ff: always on					\
+		0x9600 - 0x967f: reserved */					\
+	GEN_FW_RANGE(0x9680, 0x97ff, FORCEWAKE_RENDER), /*			\
+		0x9680 - 0x96ff: render (DG2 only)				\
+		0x9700 - 0x97ff: reserved */					\
+	GEN_FW_RANGE(0x9800, 0xcfff, FORCEWAKE_GT), /*				\
+		0x9800 - 0xb4ff: gt						\
+		0xb500 - 0xbfff: reserved					\
+		0xc000 - 0xcfff: gt */						\
+	GEN_FW_RANGE(0xd000, 0xd7ff, 0),					\
+	GEN_FW_RANGE(0xd800, 0xd87f, FW_RANGE_D800),			\
+	GEN_FW_RANGE(0xd880, 0xdbff, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0xdc00, 0xdcff, FORCEWAKE_RENDER),				\
+	GEN_FW_RANGE(0xdd00, 0xde7f, FORCEWAKE_GT), /*				\
+		0xdd00 - 0xddff: gt						\
+		0xde00 - 0xde7f: reserved */					\
+	GEN_FW_RANGE(0xde80, 0xe8ff, FORCEWAKE_RENDER), /*			\
+		0xde80 - 0xdfff: render						\
+		0xe000 - 0xe0ff: reserved					\
+		0xe100 - 0xe8ff: render */					\
+	GEN_FW_RANGE(0xe900, 0xffff, FORCEWAKE_GT), /*				\
+		0xe900 - 0xe9ff: gt						\
+		0xea00 - 0xefff: reserved					\
+		0xf000 - 0xffff: gt */						\
+	GEN_FW_RANGE(0x10000, 0x12fff, 0), /*					\
+		0x10000 - 0x11fff: reserved					\
+		0x12000 - 0x127ff: always on					\
+		0x12800 - 0x12fff: reserved */					\
+	GEN_FW_RANGE(0x13000, 0x131ff, FORCEWAKE_MEDIA_VDBOX0), /* DG2 only */	\
+	GEN_FW_RANGE(0x13200, 0x13fff, FORCEWAKE_MEDIA_VDBOX2), /*		\
+		0x13200 - 0x133ff: VD2 (DG2 only)				\
+		0x13400 - 0x13fff: reserved */					\
+	GEN_FW_RANGE(0x14000, 0x141ff, FORCEWAKE_MEDIA_VDBOX0), /* XEHPSDV only */	\
+	GEN_FW_RANGE(0x14200, 0x143ff, FORCEWAKE_MEDIA_VDBOX2), /* XEHPSDV only */	\
+	GEN_FW_RANGE(0x14400, 0x145ff, FORCEWAKE_MEDIA_VDBOX4), /* XEHPSDV only */	\
+	GEN_FW_RANGE(0x14600, 0x147ff, FORCEWAKE_MEDIA_VDBOX6), /* XEHPSDV only */	\
+	GEN_FW_RANGE(0x14800, 0x14fff, FORCEWAKE_RENDER),			\
+	GEN_FW_RANGE(0x15000, 0x16dff, FORCEWAKE_GT), /*			\
+		0x15000 - 0x15fff: gt (DG2 only)				\
+		0x16000 - 0x16dff: reserved */					\
+	GEN_FW_RANGE(0x16e00, 0x1ffff, FORCEWAKE_RENDER),			\
+	GEN_FW_RANGE(0x20000, 0x21fff, FORCEWAKE_MEDIA_VDBOX0), /*		\
+		0x20000 - 0x20fff: VD0 (XEHPSDV only)				\
+		0x21000 - 0x21fff: reserved */					\
+	GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0x24000, 0x2417f, 0), /*					\
+		0x24000 - 0x2407f: always on					\
+		0x24080 - 0x2417f: reserved */					\
+	GEN_FW_RANGE(0x24180, 0x249ff, FORCEWAKE_GT), /*			\
+		0x24180 - 0x241ff: gt						\
+		0x24200 - 0x249ff: reserved */					\
+	GEN_FW_RANGE(0x24a00, 0x251ff, FORCEWAKE_RENDER), /*			\
+		0x24a00 - 0x24a7f: render					\
+		0x24a80 - 0x251ff: reserved */					\
+	GEN_FW_RANGE(0x25200, 0x25fff, FORCEWAKE_GT), /*			\
+		0x25200 - 0x252ff: gt						\
+		0x25300 - 0x25fff: reserved */					\
+	GEN_FW_RANGE(0x26000, 0x2ffff, FORCEWAKE_RENDER), /*			\
+		0x26000 - 0x27fff: render					\
+		0x28000 - 0x29fff: reserved					\
+		0x2a000 - 0x2ffff: undocumented */				\
+	GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_GT),				\
+	GEN_FW_RANGE(0x40000, 0x1bffff, 0),					\
+	GEN_FW_RANGE(0x1c0000, 0x1c3fff, FORCEWAKE_MEDIA_VDBOX0), /*		\
+		0x1c0000 - 0x1c2bff: VD0					\
+		0x1c2c00 - 0x1c2cff: reserved					\
+		0x1c2d00 - 0x1c2dff: VD0					\
+		0x1c2e00 - 0x1c3eff: VD0 (DG2 only)				\
+		0x1c3f00 - 0x1c3fff: VD0 */					\
+	GEN_FW_RANGE(0x1c4000, 0x1c7fff, FORCEWAKE_MEDIA_VDBOX1), /*		\
+		0x1c4000 - 0x1c6bff: VD1					\
+		0x1c6c00 - 0x1c6cff: reserved					\
+		0x1c6d00 - 0x1c6dff: VD1					\
+		0x1c6e00 - 0x1c7fff: reserved */				\
+	GEN_FW_RANGE(0x1c8000, 0x1cbfff, FORCEWAKE_MEDIA_VEBOX0), /*		\
+		0x1c8000 - 0x1ca0ff: VE0					\
+		0x1ca100 - 0x1cbfff: reserved */				\
+	GEN_FW_RANGE(0x1cc000, 0x1ccfff, FORCEWAKE_MEDIA_VDBOX0),		\
+	GEN_FW_RANGE(0x1cd000, 0x1cdfff, FORCEWAKE_MEDIA_VDBOX2),		\
+	GEN_FW_RANGE(0x1ce000, 0x1cefff, FORCEWAKE_MEDIA_VDBOX4),		\
+	GEN_FW_RANGE(0x1cf000, 0x1cffff, FORCEWAKE_MEDIA_VDBOX6),		\
+	GEN_FW_RANGE(0x1d0000, 0x1d3fff, FORCEWAKE_MEDIA_VDBOX2), /*		\
+		0x1d0000 - 0x1d2bff: VD2					\
+		0x1d2c00 - 0x1d2cff: reserved					\
+		0x1d2d00 - 0x1d2dff: VD2					\
+		0x1d2e00 - 0x1d3dff: VD2 (DG2 only)				\
+		0x1d3e00 - 0x1d3eff: reserved					\
+		0x1d3f00 - 0x1d3fff: VD2 */					\
+	GEN_FW_RANGE(0x1d4000, 0x1d7fff, FORCEWAKE_MEDIA_VDBOX3), /*		\
+		0x1d4000 - 0x1d6bff: VD3					\
+		0x1d6c00 - 0x1d6cff: reserved					\
+		0x1d6d00 - 0x1d6dff: VD3					\
+		0x1d6e00 - 0x1d7fff: reserved */				\
+	GEN_FW_RANGE(0x1d8000, 0x1dffff, FORCEWAKE_MEDIA_VEBOX1), /*		\
+		0x1d8000 - 0x1da0ff: VE1					\
+		0x1da100 - 0x1dffff: reserved */				\
+	GEN_FW_RANGE(0x1e0000, 0x1e3fff, FORCEWAKE_MEDIA_VDBOX4), /*		\
+		0x1e0000 - 0x1e2bff: VD4					\
+		0x1e2c00 - 0x1e2cff: reserved					\
+		0x1e2d00 - 0x1e2dff: VD4					\
+		0x1e2e00 - 0x1e3eff: reserved					\
+		0x1e3f00 - 0x1e3fff: VD4 */					\
+	GEN_FW_RANGE(0x1e4000, 0x1e7fff, FORCEWAKE_MEDIA_VDBOX5), /*		\
+		0x1e4000 - 0x1e6bff: VD5					\
+		0x1e6c00 - 0x1e6cff: reserved					\
+		0x1e6d00 - 0x1e6dff: VD5					\
+		0x1e6e00 - 0x1e7fff: reserved */				\
+	GEN_FW_RANGE(0x1e8000, 0x1effff, FORCEWAKE_MEDIA_VEBOX2), /*		\
+		0x1e8000 - 0x1ea0ff: VE2					\
+		0x1ea100 - 0x1effff: reserved */				\
+	GEN_FW_RANGE(0x1f0000, 0x1f3fff, FORCEWAKE_MEDIA_VDBOX6), /*		\
+		0x1f0000 - 0x1f2bff: VD6					\
+		0x1f2c00 - 0x1f2cff: reserved					\
+		0x1f2d00 - 0x1f2dff: VD6					\
+		0x1f2e00 - 0x1f3eff: reserved					\
+		0x1f3f00 - 0x1f3fff: VD6 */					\
+	GEN_FW_RANGE(0x1f4000, 0x1f7fff, FORCEWAKE_MEDIA_VDBOX7), /*		\
+		0x1f4000 - 0x1f6bff: VD7					\
+		0x1f6c00 - 0x1f6cff: reserved					\
+		0x1f6d00 - 0x1f6dff: VD7					\
+		0x1f6e00 - 0x1f7fff: reserved */				\
+	GEN_FW_RANGE(0x1f8000, 0x1fa0ff, FORCEWAKE_MEDIA_VEBOX3),
+
+static const struct intel_forcewake_range __xehp_fw_ranges[] = {
+	XEHP_FWRANGES(FORCEWAKE_GT)
+};
+
+static const struct intel_forcewake_range __dg2_fw_ranges[] = {
+	XEHP_FWRANGES(FORCEWAKE_RENDER)
+};
+
 static void
 ilk_dummy_write(struct intel_uncore *uncore)
 {
@@ -1502,6 +1736,7 @@ __gen_write(func, 8) \
 __gen_write(func, 16) \
 __gen_write(func, 32)
 
+__gen_reg_write_funcs(xehp_fwtable);
 __gen_reg_write_funcs(gen12_fwtable);
 __gen_reg_write_funcs(gen11_fwtable);
 __gen_reg_write_funcs(fwtable);
@@ -1582,8 +1817,14 @@ static int __fw_domain_init(struct intel_uncore *uncore,
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX1 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX1));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX2 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX2));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX3 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX3));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX4 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX4));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX5 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX5));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX6 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX6));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VDBOX7 != (1 << FW_DOMAIN_ID_MEDIA_VDBOX7));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX0 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX0));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX1 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX1));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX2 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX2));
+	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX3 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX3));
 
 	d->mask = BIT(domain_id);
 
@@ -1870,36 +2111,40 @@ static int uncore_forcewake_init(struct intel_uncore *uncore)
 		return ret;
 	forcewake_early_sanitize(uncore, 0);
 
-	if (IS_GRAPHICS_VER(i915, 6, 7)) {
-		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6);
-
-		if (IS_VALLEYVIEW(i915)) {
-			ASSIGN_FW_DOMAINS_TABLE(uncore, __vlv_fw_ranges);
-			ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
-		} else {
-			ASSIGN_READ_MMIO_VFUNCS(uncore, gen6);
-		}
-	} else if (GRAPHICS_VER(i915) == 8) {
-		if (IS_CHERRYVIEW(i915)) {
-			ASSIGN_FW_DOMAINS_TABLE(uncore, __chv_fw_ranges);
-			ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
-			ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
-		} else {
-			ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen8);
-			ASSIGN_READ_MMIO_VFUNCS(uncore, gen6);
-		}
-	} else if (IS_GRAPHICS_VER(i915, 9, 10)) {
-		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen9_fw_ranges);
-		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
-		ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
-	} else if (GRAPHICS_VER(i915) == 11) {
-		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges);
-		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable);
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __dg2_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, xehp_fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
-	} else {
+	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __xehp_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, xehp_fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
+	} else if (GRAPHICS_VER(i915) >= 12) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen12_fw_ranges);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, gen12_fwtable);
+	} else if (GRAPHICS_VER(i915) == 11) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
+	} else if (IS_GRAPHICS_VER(i915, 9, 10)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen9_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
+	} else if (IS_CHERRYVIEW(i915)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __chv_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
+	} else if (GRAPHICS_VER(i915) == 8) {
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen8);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen6);
+	} else if (IS_VALLEYVIEW(i915)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __vlv_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
+	} else if (IS_GRAPHICS_VER(i915, 6, 7)) {
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen6);
 	}
 
 	uncore->pmic_bus_access_nb.notifier_call = i915_pmic_bus_access_notifier;
@@ -1929,7 +2174,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore)
 		return -ENODEV;
 	}
 
-	if (INTEL_GEN(i915) > 5 && !intel_vgpu_active(i915))
+	if (GRAPHICS_VER(i915) > 5 && !intel_vgpu_active(i915))
 		uncore->flags |= UNCORE_HAS_FORCEWAKE;
 
 	if (!intel_uncore_has_forcewake(uncore)) {
@@ -1988,6 +2233,22 @@ void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
 		if (HAS_ENGINE(gt, _VCS(i)))
 			continue;
 
+		/*
+		 * Starting with XeHP, the power well for an even-numbered
+		 * VDBOX is also used for shared units within the
+		 * media slice such as SFC.  So even if the engine
+		 * itself is fused off, we still need to initialize
+		 * the forcewake domain if any of the other engines
+		 * in the same media slice are present.
+		 */
+		if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 50) && i % 2 == 0) {
+			if ((i + 1 < I915_MAX_VCS) && HAS_ENGINE(gt, _VCS(i + 1)))
+				continue;
+
+			if (HAS_ENGINE(gt, _VECS(i / 2)))
+				continue;
+		}
+
 		if (fw_domains & BIT(domain_id))
 			fw_domain_fini(uncore, domain_id);
 	}
@@ -2277,6 +2538,61 @@ intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
 	return fw_domains;
 }
 
+u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
+					   i915_reg_t reg,
+					   int slice, int subslice)
+{
+	u32 mcr_mask, mcr_ss, mcr, old_mcr, val;
+
+	lockdep_assert_held(&uncore->lock);
+
+	if (GRAPHICS_VER(uncore->i915) >= 11) {
+		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
+		mcr_ss = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
+	} else {
+		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
+		mcr_ss = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
+	}
+
+	old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+
+	mcr &= ~mcr_mask;
+	mcr |= mcr_ss;
+	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+
+	val = intel_uncore_read_fw(uncore, reg);
+
+	mcr &= ~mcr_mask;
+	mcr |= old_mcr & mcr_mask;
+
+	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+
+	return val;
+}
+
+u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
+					i915_reg_t reg, int slice, int subslice)
+{
+	enum forcewake_domains fw_domains;
+	u32 val;
+
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
+						    FW_REG_READ);
+	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
+						     GEN8_MCR_SELECTOR,
+						     FW_REG_READ | FW_REG_WRITE);
+
+	spin_lock_irq(&uncore->lock);
+	intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+	val = intel_uncore_read_with_mcr_steering_fw(uncore, reg, slice, subslice);
+
+	intel_uncore_forcewake_put__locked(uncore, fw_domains);
+	spin_unlock_irq(&uncore->lock);
+
+	return val;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_uncore.c"
 #include "selftests/intel_uncore.c"
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 59f0da8f1fbb..3c0b0a8b5250 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -52,8 +52,14 @@ enum forcewake_domain_id {
 	FW_DOMAIN_ID_MEDIA_VDBOX1,
 	FW_DOMAIN_ID_MEDIA_VDBOX2,
 	FW_DOMAIN_ID_MEDIA_VDBOX3,
+	FW_DOMAIN_ID_MEDIA_VDBOX4,
+	FW_DOMAIN_ID_MEDIA_VDBOX5,
+	FW_DOMAIN_ID_MEDIA_VDBOX6,
+	FW_DOMAIN_ID_MEDIA_VDBOX7,
 	FW_DOMAIN_ID_MEDIA_VEBOX0,
 	FW_DOMAIN_ID_MEDIA_VEBOX1,
+	FW_DOMAIN_ID_MEDIA_VEBOX2,
+	FW_DOMAIN_ID_MEDIA_VEBOX3,
 
 	FW_DOMAIN_ID_COUNT
 };
@@ -66,10 +72,16 @@ enum forcewake_domains {
 	FORCEWAKE_MEDIA_VDBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX1),
 	FORCEWAKE_MEDIA_VDBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX2),
 	FORCEWAKE_MEDIA_VDBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX3),
+	FORCEWAKE_MEDIA_VDBOX4	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX4),
+	FORCEWAKE_MEDIA_VDBOX5	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX5),
+	FORCEWAKE_MEDIA_VDBOX6	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX6),
+	FORCEWAKE_MEDIA_VDBOX7	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX7),
 	FORCEWAKE_MEDIA_VEBOX0	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX0),
 	FORCEWAKE_MEDIA_VEBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX1),
+	FORCEWAKE_MEDIA_VEBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX2),
+	FORCEWAKE_MEDIA_VEBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX3),
 
-	FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1
+	FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1,
 };
 
 struct intel_uncore_funcs {
@@ -182,6 +194,12 @@ intel_uncore_has_fifo(const struct intel_uncore *uncore)
 	return uncore->flags & UNCORE_HAS_FIFO;
 }
 
+u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
+					   i915_reg_t reg,
+					   int slice, int subslice);
+u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
+					i915_reg_t reg,	int slice, int subslice);
+
 void
 intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug);
 void intel_uncore_init_early(struct intel_uncore *uncore,
diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c
index 8309455f13ea..5e511bb891f9 100644
--- a/drivers/gpu/drm/i915/intel_wopcm.c
+++ b/drivers/gpu/drm/i915/intel_wopcm.c
@@ -56,8 +56,8 @@
 
 /* 24KB at the end of WOPCM is reserved for RC6 CTX on BXT. */
 #define BXT_WOPCM_RC6_CTX_RESERVED	(SZ_16K + SZ_8K)
-/* 36KB WOPCM reserved at the end of WOPCM on CNL. */
-#define CNL_WOPCM_HW_CTX_RESERVED	(SZ_32K + SZ_4K)
+/* 36KB WOPCM reserved at the end of WOPCM on ICL. */
+#define ICL_WOPCM_HW_CTX_RESERVED	(SZ_32K + SZ_4K)
 
 /* 128KB from GUC_WOPCM_RESERVED is reserved for FW on Gen9. */
 #define GEN9_GUC_FW_RESERVED	SZ_128K
@@ -93,8 +93,8 @@ static u32 context_reserved_size(struct drm_i915_private *i915)
 {
 	if (IS_GEN9_LP(i915))
 		return BXT_WOPCM_RC6_CTX_RESERVED;
-	else if (GRAPHICS_VER(i915) >= 10)
-		return CNL_WOPCM_HW_CTX_RESERVED;
+	else if (GRAPHICS_VER(i915) >= 11)
+		return ICL_WOPCM_HW_CTX_RESERVED;
 	else
 		return 0;
 }
@@ -126,7 +126,7 @@ static bool gen9_check_huc_fw_fits(struct drm_i915_private *i915,
 				   u32 guc_wopcm_size, u32 huc_fw_size)
 {
 	/*
-	 * On Gen9 & CNL A0, hardware requires the total available GuC WOPCM
+	 * On Gen9, hardware requires the total available GuC WOPCM
 	 * size to be larger than or equal to HuC firmware size. Otherwise,
 	 * firmware uploading would fail.
 	 */
diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c
new file mode 100644
index 000000000000..d61ec9c951bf
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c
@@ -0,0 +1,787 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/prime_numbers.h>
+
+#include "../i915_selftest.h"
+#include "i915_random.h"
+
+static void __igt_dump_block(struct i915_buddy_mm *mm,
+			     struct i915_buddy_block *block,
+			     bool buddy)
+{
+	pr_err("block info: header=%llx, state=%u, order=%d, offset=%llx size=%llx root=%s buddy=%s\n",
+	       block->header,
+	       i915_buddy_block_state(block),
+	       i915_buddy_block_order(block),
+	       i915_buddy_block_offset(block),
+	       i915_buddy_block_size(mm, block),
+	       yesno(!block->parent),
+	       yesno(buddy));
+}
+
+static void igt_dump_block(struct i915_buddy_mm *mm,
+			   struct i915_buddy_block *block)
+{
+	struct i915_buddy_block *buddy;
+
+	__igt_dump_block(mm, block, false);
+
+	buddy = get_buddy(block);
+	if (buddy)
+		__igt_dump_block(mm, buddy, true);
+}
+
+static int igt_check_block(struct i915_buddy_mm *mm,
+			   struct i915_buddy_block *block)
+{
+	struct i915_buddy_block *buddy;
+	unsigned int block_state;
+	u64 block_size;
+	u64 offset;
+	int err = 0;
+
+	block_state = i915_buddy_block_state(block);
+
+	if (block_state != I915_BUDDY_ALLOCATED &&
+	    block_state != I915_BUDDY_FREE &&
+	    block_state != I915_BUDDY_SPLIT) {
+		pr_err("block state mismatch\n");
+		err = -EINVAL;
+	}
+
+	block_size = i915_buddy_block_size(mm, block);
+	offset = i915_buddy_block_offset(block);
+
+	if (block_size < mm->chunk_size) {
+		pr_err("block size smaller than min size\n");
+		err = -EINVAL;
+	}
+
+	if (!is_power_of_2(block_size)) {
+		pr_err("block size not power of two\n");
+		err = -EINVAL;
+	}
+
+	if (!IS_ALIGNED(block_size, mm->chunk_size)) {
+		pr_err("block size not aligned to min size\n");
+		err = -EINVAL;
+	}
+
+	if (!IS_ALIGNED(offset, mm->chunk_size)) {
+		pr_err("block offset not aligned to min size\n");
+		err = -EINVAL;
+	}
+
+	if (!IS_ALIGNED(offset, block_size)) {
+		pr_err("block offset not aligned to block size\n");
+		err = -EINVAL;
+	}
+
+	buddy = get_buddy(block);
+
+	if (!buddy && block->parent) {
+		pr_err("buddy has gone fishing\n");
+		err = -EINVAL;
+	}
+
+	if (buddy) {
+		if (i915_buddy_block_offset(buddy) != (offset ^ block_size)) {
+			pr_err("buddy has wrong offset\n");
+			err = -EINVAL;
+		}
+
+		if (i915_buddy_block_size(mm, buddy) != block_size) {
+			pr_err("buddy size mismatch\n");
+			err = -EINVAL;
+		}
+
+		if (i915_buddy_block_state(buddy) == block_state &&
+		    block_state == I915_BUDDY_FREE) {
+			pr_err("block and its buddy are free\n");
+			err = -EINVAL;
+		}
+	}
+
+	return err;
+}
+
+static int igt_check_blocks(struct i915_buddy_mm *mm,
+			    struct list_head *blocks,
+			    u64 expected_size,
+			    bool is_contiguous)
+{
+	struct i915_buddy_block *block;
+	struct i915_buddy_block *prev;
+	u64 total;
+	int err = 0;
+
+	block = NULL;
+	prev = NULL;
+	total = 0;
+
+	list_for_each_entry(block, blocks, link) {
+		err = igt_check_block(mm, block);
+
+		if (!i915_buddy_block_is_allocated(block)) {
+			pr_err("block not allocated\n"),
+			err = -EINVAL;
+		}
+
+		if (is_contiguous && prev) {
+			u64 prev_block_size;
+			u64 prev_offset;
+			u64 offset;
+
+			prev_offset = i915_buddy_block_offset(prev);
+			prev_block_size = i915_buddy_block_size(mm, prev);
+			offset = i915_buddy_block_offset(block);
+
+			if (offset != (prev_offset + prev_block_size)) {
+				pr_err("block offset mismatch\n");
+				err = -EINVAL;
+			}
+		}
+
+		if (err)
+			break;
+
+		total += i915_buddy_block_size(mm, block);
+		prev = block;
+	}
+
+	if (!err) {
+		if (total != expected_size) {
+			pr_err("size mismatch, expected=%llx, found=%llx\n",
+			       expected_size, total);
+			err = -EINVAL;
+		}
+		return err;
+	}
+
+	if (prev) {
+		pr_err("prev block, dump:\n");
+		igt_dump_block(mm, prev);
+	}
+
+	pr_err("bad block, dump:\n");
+	igt_dump_block(mm, block);
+
+	return err;
+}
+
+static int igt_check_mm(struct i915_buddy_mm *mm)
+{
+	struct i915_buddy_block *root;
+	struct i915_buddy_block *prev;
+	unsigned int i;
+	u64 total;
+	int err = 0;
+
+	if (!mm->n_roots) {
+		pr_err("n_roots is zero\n");
+		return -EINVAL;
+	}
+
+	if (mm->n_roots != hweight64(mm->size)) {
+		pr_err("n_roots mismatch, n_roots=%u, expected=%lu\n",
+		       mm->n_roots, hweight64(mm->size));
+		return -EINVAL;
+	}
+
+	root = NULL;
+	prev = NULL;
+	total = 0;
+
+	for (i = 0; i < mm->n_roots; ++i) {
+		struct i915_buddy_block *block;
+		unsigned int order;
+
+		root = mm->roots[i];
+		if (!root) {
+			pr_err("root(%u) is NULL\n", i);
+			err = -EINVAL;
+			break;
+		}
+
+		err = igt_check_block(mm, root);
+
+		if (!i915_buddy_block_is_free(root)) {
+			pr_err("root not free\n");
+			err = -EINVAL;
+		}
+
+		order = i915_buddy_block_order(root);
+
+		if (!i) {
+			if (order != mm->max_order) {
+				pr_err("max order root missing\n");
+				err = -EINVAL;
+			}
+		}
+
+		if (prev) {
+			u64 prev_block_size;
+			u64 prev_offset;
+			u64 offset;
+
+			prev_offset = i915_buddy_block_offset(prev);
+			prev_block_size = i915_buddy_block_size(mm, prev);
+			offset = i915_buddy_block_offset(root);
+
+			if (offset != (prev_offset + prev_block_size)) {
+				pr_err("root offset mismatch\n");
+				err = -EINVAL;
+			}
+		}
+
+		block = list_first_entry_or_null(&mm->free_list[order],
+						 struct i915_buddy_block,
+						 link);
+		if (block != root) {
+			pr_err("root mismatch at order=%u\n", order);
+			err = -EINVAL;
+		}
+
+		if (err)
+			break;
+
+		prev = root;
+		total += i915_buddy_block_size(mm, root);
+	}
+
+	if (!err) {
+		if (total != mm->size) {
+			pr_err("expected mm size=%llx, found=%llx\n", mm->size,
+			       total);
+			err = -EINVAL;
+		}
+		return err;
+	}
+
+	if (prev) {
+		pr_err("prev root(%u), dump:\n", i - 1);
+		igt_dump_block(mm, prev);
+	}
+
+	if (root) {
+		pr_err("bad root(%u), dump:\n", i);
+		igt_dump_block(mm, root);
+	}
+
+	return err;
+}
+
+static void igt_mm_config(u64 *size, u64 *chunk_size)
+{
+	I915_RND_STATE(prng);
+	u32 s, ms;
+
+	/* Nothing fancy, just try to get an interesting bit pattern */
+
+	prandom_seed_state(&prng, i915_selftest.random_seed);
+
+	/* Let size be a random number of pages up to 8 GB (2M pages) */
+	s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng);
+	/* Let the chunk size be a random power of 2 less than size */
+	ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng));
+	/* Round size down to the chunk size */
+	s &= -ms;
+
+	/* Convert from pages to bytes */
+	*chunk_size = (u64)ms << 12;
+	*size = (u64)s << 12;
+}
+
+static int igt_buddy_alloc_smoke(void *arg)
+{
+	struct i915_buddy_mm mm;
+	IGT_TIMEOUT(end_time);
+	I915_RND_STATE(prng);
+	u64 chunk_size;
+	u64 mm_size;
+	int *order;
+	int err, i;
+
+	igt_mm_config(&mm_size, &chunk_size);
+
+	pr_info("buddy_init with size=%llx, chunk_size=%llx\n", mm_size, chunk_size);
+
+	err = i915_buddy_init(&mm, mm_size, chunk_size);
+	if (err) {
+		pr_err("buddy_init failed(%d)\n", err);
+		return err;
+	}
+
+	order = i915_random_order(mm.max_order + 1, &prng);
+	if (!order)
+		goto out_fini;
+
+	for (i = 0; i <= mm.max_order; ++i) {
+		struct i915_buddy_block *block;
+		int max_order = order[i];
+		bool timeout = false;
+		LIST_HEAD(blocks);
+		int order;
+		u64 total;
+
+		err = igt_check_mm(&mm);
+		if (err) {
+			pr_err("pre-mm check failed, abort\n");
+			break;
+		}
+
+		pr_info("filling from max_order=%u\n", max_order);
+
+		order = max_order;
+		total = 0;
+
+		do {
+retry:
+			block = i915_buddy_alloc(&mm, order);
+			if (IS_ERR(block)) {
+				err = PTR_ERR(block);
+				if (err == -ENOMEM) {
+					pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
+						order);
+				} else {
+					if (order--) {
+						err = 0;
+						goto retry;
+					}
+
+					pr_err("buddy_alloc with order=%d failed(%d)\n",
+					       order, err);
+				}
+
+				break;
+			}
+
+			list_add_tail(&block->link, &blocks);
+
+			if (i915_buddy_block_order(block) != order) {
+				pr_err("buddy_alloc order mismatch\n");
+				err = -EINVAL;
+				break;
+			}
+
+			total += i915_buddy_block_size(&mm, block);
+
+			if (__igt_timeout(end_time, NULL)) {
+				timeout = true;
+				break;
+			}
+		} while (total < mm.size);
+
+		if (!err)
+			err = igt_check_blocks(&mm, &blocks, total, false);
+
+		i915_buddy_free_list(&mm, &blocks);
+
+		if (!err) {
+			err = igt_check_mm(&mm);
+			if (err)
+				pr_err("post-mm check failed\n");
+		}
+
+		if (err || timeout)
+			break;
+
+		cond_resched();
+	}
+
+	if (err == -ENOMEM)
+		err = 0;
+
+	kfree(order);
+out_fini:
+	i915_buddy_fini(&mm);
+
+	return err;
+}
+
+static int igt_buddy_alloc_pessimistic(void *arg)
+{
+	const unsigned int max_order = 16;
+	struct i915_buddy_block *block, *bn;
+	struct i915_buddy_mm mm;
+	unsigned int order;
+	LIST_HEAD(blocks);
+	int err;
+
+	/*
+	 * Create a pot-sized mm, then allocate one of each possible
+	 * order within. This should leave the mm with exactly one
+	 * page left.
+	 */
+
+	err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE);
+	if (err) {
+		pr_err("buddy_init failed(%d)\n", err);
+		return err;
+	}
+	GEM_BUG_ON(mm.max_order != max_order);
+
+	for (order = 0; order < max_order; order++) {
+		block = i915_buddy_alloc(&mm, order);
+		if (IS_ERR(block)) {
+			pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
+				order);
+			err = PTR_ERR(block);
+			goto err;
+		}
+
+		list_add_tail(&block->link, &blocks);
+	}
+
+	/* And now the last remaining block available */
+	block = i915_buddy_alloc(&mm, 0);
+	if (IS_ERR(block)) {
+		pr_info("buddy_alloc hit -ENOMEM on final alloc\n");
+		err = PTR_ERR(block);
+		goto err;
+	}
+	list_add_tail(&block->link, &blocks);
+
+	/* Should be completely full! */
+	for (order = max_order; order--; ) {
+		block = i915_buddy_alloc(&mm, order);
+		if (!IS_ERR(block)) {
+			pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!",
+				order);
+			list_add_tail(&block->link, &blocks);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+	block = list_last_entry(&blocks, typeof(*block), link);
+	list_del(&block->link);
+	i915_buddy_free(&mm, block);
+
+	/* As we free in increasing size, we make available larger blocks */
+	order = 1;
+	list_for_each_entry_safe(block, bn, &blocks, link) {
+		list_del(&block->link);
+		i915_buddy_free(&mm, block);
+
+		block = i915_buddy_alloc(&mm, order);
+		if (IS_ERR(block)) {
+			pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
+				order);
+			err = PTR_ERR(block);
+			goto err;
+		}
+		i915_buddy_free(&mm, block);
+		order++;
+	}
+
+	/* To confirm, now the whole mm should be available */
+	block = i915_buddy_alloc(&mm, max_order);
+	if (IS_ERR(block)) {
+		pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
+			max_order);
+		err = PTR_ERR(block);
+		goto err;
+	}
+	i915_buddy_free(&mm, block);
+
+err:
+	i915_buddy_free_list(&mm, &blocks);
+	i915_buddy_fini(&mm);
+	return err;
+}
+
+static int igt_buddy_alloc_optimistic(void *arg)
+{
+	const int max_order = 16;
+	struct i915_buddy_block *block;
+	struct i915_buddy_mm mm;
+	LIST_HEAD(blocks);
+	int order;
+	int err;
+
+	/*
+	 * Create a mm with one block of each order available, and
+	 * try to allocate them all.
+	 */
+
+	err = i915_buddy_init(&mm,
+			      PAGE_SIZE * ((1 << (max_order + 1)) - 1),
+			      PAGE_SIZE);
+	if (err) {
+		pr_err("buddy_init failed(%d)\n", err);
+		return err;
+	}
+	GEM_BUG_ON(mm.max_order != max_order);
+
+	for (order = 0; order <= max_order; order++) {
+		block = i915_buddy_alloc(&mm, order);
+		if (IS_ERR(block)) {
+			pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
+				order);
+			err = PTR_ERR(block);
+			goto err;
+		}
+
+		list_add_tail(&block->link, &blocks);
+	}
+
+	/* Should be completely full! */
+	block = i915_buddy_alloc(&mm, 0);
+	if (!IS_ERR(block)) {
+		pr_info("buddy_alloc unexpectedly succeeded, it should be full!");
+		list_add_tail(&block->link, &blocks);
+		err = -EINVAL;
+		goto err;
+	}
+
+err:
+	i915_buddy_free_list(&mm, &blocks);
+	i915_buddy_fini(&mm);
+	return err;
+}
+
+static int igt_buddy_alloc_pathological(void *arg)
+{
+	const int max_order = 16;
+	struct i915_buddy_block *block;
+	struct i915_buddy_mm mm;
+	LIST_HEAD(blocks);
+	LIST_HEAD(holes);
+	int order, top;
+	int err;
+
+	/*
+	 * Create a pot-sized mm, then allocate one of each possible
+	 * order within. This should leave the mm with exactly one
+	 * page left. Free the largest block, then whittle down again.
+	 * Eventually we will have a fully 50% fragmented mm.
+	 */
+
+	err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE);
+	if (err) {
+		pr_err("buddy_init failed(%d)\n", err);
+		return err;
+	}
+	GEM_BUG_ON(mm.max_order != max_order);
+
+	for (top = max_order; top; top--) {
+		/* Make room by freeing the largest allocated block */
+		block = list_first_entry_or_null(&blocks, typeof(*block), link);
+		if (block) {
+			list_del(&block->link);
+			i915_buddy_free(&mm, block);
+		}
+
+		for (order = top; order--; ) {
+			block = i915_buddy_alloc(&mm, order);
+			if (IS_ERR(block)) {
+				pr_info("buddy_alloc hit -ENOMEM with order=%d, top=%d\n",
+					order, top);
+				err = PTR_ERR(block);
+				goto err;
+			}
+			list_add_tail(&block->link, &blocks);
+		}
+
+		/* There should be one final page for this sub-allocation */
+		block = i915_buddy_alloc(&mm, 0);
+		if (IS_ERR(block)) {
+			pr_info("buddy_alloc hit -ENOMEM for hole\n");
+			err = PTR_ERR(block);
+			goto err;
+		}
+		list_add_tail(&block->link, &holes);
+
+		block = i915_buddy_alloc(&mm, top);
+		if (!IS_ERR(block)) {
+			pr_info("buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!",
+				top, max_order);
+			list_add_tail(&block->link, &blocks);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+	i915_buddy_free_list(&mm, &holes);
+
+	/* Nothing larger than blocks of chunk_size now available */
+	for (order = 1; order <= max_order; order++) {
+		block = i915_buddy_alloc(&mm, order);
+		if (!IS_ERR(block)) {
+			pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!",
+				order);
+			list_add_tail(&block->link, &blocks);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+err:
+	list_splice_tail(&holes, &blocks);
+	i915_buddy_free_list(&mm, &blocks);
+	i915_buddy_fini(&mm);
+	return err;
+}
+
+static int igt_buddy_alloc_range(void *arg)
+{
+	struct i915_buddy_mm mm;
+	unsigned long page_num;
+	LIST_HEAD(blocks);
+	u64 chunk_size;
+	u64 offset;
+	u64 size;
+	u64 rem;
+	int err;
+
+	igt_mm_config(&size, &chunk_size);
+
+	pr_info("buddy_init with size=%llx, chunk_size=%llx\n", size, chunk_size);
+
+	err = i915_buddy_init(&mm, size, chunk_size);
+	if (err) {
+		pr_err("buddy_init failed(%d)\n", err);
+		return err;
+	}
+
+	err = igt_check_mm(&mm);
+	if (err) {
+		pr_err("pre-mm check failed, abort, abort, abort!\n");
+		goto err_fini;
+	}
+
+	rem = mm.size;
+	offset = 0;
+
+	for_each_prime_number_from(page_num, 1, ULONG_MAX - 1) {
+		struct i915_buddy_block *block;
+		LIST_HEAD(tmp);
+
+		size = min(page_num * mm.chunk_size, rem);
+
+		err = i915_buddy_alloc_range(&mm, &tmp, offset, size);
+		if (err) {
+			if (err == -ENOMEM) {
+				pr_info("alloc_range hit -ENOMEM with size=%llx\n",
+					size);
+			} else {
+				pr_err("alloc_range with offset=%llx, size=%llx failed(%d)\n",
+				       offset, size, err);
+			}
+
+			break;
+		}
+
+		block = list_first_entry_or_null(&tmp,
+						 struct i915_buddy_block,
+						 link);
+		if (!block) {
+			pr_err("alloc_range has no blocks\n");
+			err = -EINVAL;
+			break;
+		}
+
+		if (i915_buddy_block_offset(block) != offset) {
+			pr_err("alloc_range start offset mismatch, found=%llx, expected=%llx\n",
+			       i915_buddy_block_offset(block), offset);
+			err = -EINVAL;
+		}
+
+		if (!err)
+			err = igt_check_blocks(&mm, &tmp, size, true);
+
+		list_splice_tail(&tmp, &blocks);
+
+		if (err)
+			break;
+
+		offset += size;
+
+		rem -= size;
+		if (!rem)
+			break;
+
+		cond_resched();
+	}
+
+	if (err == -ENOMEM)
+		err = 0;
+
+	i915_buddy_free_list(&mm, &blocks);
+
+	if (!err) {
+		err = igt_check_mm(&mm);
+		if (err)
+			pr_err("post-mm check failed\n");
+	}
+
+err_fini:
+	i915_buddy_fini(&mm);
+
+	return err;
+}
+
+static int igt_buddy_alloc_limit(void *arg)
+{
+	struct i915_buddy_block *block;
+	struct i915_buddy_mm mm;
+	const u64 size = U64_MAX;
+	int err;
+
+	err = i915_buddy_init(&mm, size, PAGE_SIZE);
+	if (err)
+		return err;
+
+	if (mm.max_order != I915_BUDDY_MAX_ORDER) {
+		pr_err("mm.max_order(%d) != %d\n",
+		       mm.max_order, I915_BUDDY_MAX_ORDER);
+		err = -EINVAL;
+		goto out_fini;
+	}
+
+	block = i915_buddy_alloc(&mm, mm.max_order);
+	if (IS_ERR(block)) {
+		err = PTR_ERR(block);
+		goto out_fini;
+	}
+
+	if (i915_buddy_block_order(block) != mm.max_order) {
+		pr_err("block order(%d) != %d\n",
+		       i915_buddy_block_order(block), mm.max_order);
+		err = -EINVAL;
+		goto out_free;
+	}
+
+	if (i915_buddy_block_size(&mm, block) !=
+	    BIT_ULL(mm.max_order) * PAGE_SIZE) {
+		pr_err("block size(%llu) != %llu\n",
+		       i915_buddy_block_size(&mm, block),
+		       BIT_ULL(mm.max_order) * PAGE_SIZE);
+		err = -EINVAL;
+		goto out_free;
+	}
+
+out_free:
+	i915_buddy_free(&mm, block);
+out_fini:
+	i915_buddy_fini(&mm);
+	return err;
+}
+
+int i915_buddy_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_buddy_alloc_pessimistic),
+		SUBTEST(igt_buddy_alloc_optimistic),
+		SUBTEST(igt_buddy_alloc_pathological),
+		SUBTEST(igt_buddy_alloc_smoke),
+		SUBTEST(igt_buddy_alloc_range),
+		SUBTEST(igt_buddy_alloc_limit),
+	};
+
+	return i915_subtests(tests, NULL);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index a92c0e9b7e6b..cfa5c4165a4f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -26,6 +26,7 @@ selftest(gt_mocs, intel_mocs_live_selftests)
 selftest(gt_pm, intel_gt_pm_live_selftests)
 selftest(gt_heartbeat, intel_heartbeat_live_selftests)
 selftest(requests, i915_request_live_selftests)
+selftest(migrate, intel_migrate_live_selftests)
 selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
 selftest(mman, i915_gem_mman_live_selftests)
@@ -37,14 +38,14 @@ selftest(gem, i915_gem_live_selftests)
 selftest(evict, i915_gem_evict_live_selftests)
 selftest(hugepages, i915_gem_huge_page_live_selftests)
 selftest(gem_contexts, i915_gem_context_live_selftests)
-selftest(gem_execbuf, i915_gem_execbuffer_live_selftests)
-selftest(blt, i915_gem_object_blt_live_selftests)
 selftest(client, i915_gem_client_blt_live_selftests)
+selftest(gem_migrate, i915_gem_migrate_live_selftests)
 selftest(reset, intel_reset_live_selftests)
 selftest(memory_region, intel_memory_region_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
 selftest(ring_submission, intel_ring_submission_live_selftests)
 selftest(perf, i915_perf_live_selftests)
+selftest(slpc, intel_slpc_live_selftests)
 /* Here be dragons: keep last to run last! */
 selftest(late_gt_pm, intel_gt_pm_late_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 34e5caf38093..793fb28a770d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -32,5 +32,5 @@ selftest(vma, i915_vma_mock_selftests)
 selftest(evict, i915_gem_evict_mock_selftests)
 selftest(gtt, i915_gem_gtt_mock_selftests)
 selftest(hugepages, i915_gem_huge_page_mock_selftests)
-selftest(contexts, i915_gem_context_mock_selftests)
 selftest(memory_region, intel_memory_region_mock_selftests)
+selftest(buddy, i915_buddy_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
index c2389f8a257d..058450d351f7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
@@ -17,5 +17,5 @@
  */
 selftest(engine_cs, intel_engine_cs_perf_selftests)
 selftest(request, i915_request_perf_selftests)
-selftest(blt, i915_gem_object_blt_perf_selftests)
+selftest(migrate, intel_migrate_perf_selftests)
 selftest(region, intel_memory_region_perf_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index bd5c96a77ba3..d67710d10615 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -1313,7 +1313,7 @@ static int __live_parallel_engine1(void *arg)
 		i915_request_add(rq);
 
 		err = 0;
-		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		if (i915_request_wait(rq, 0, HZ) < 0)
 			err = -ETIME;
 		i915_request_put(rq);
 		if (err)
@@ -1419,7 +1419,7 @@ static int __live_parallel_spin(void *arg)
 	}
 	igt_spinner_end(&spin);
 
-	if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0)
+	if (err == 0 && i915_request_wait(rq, 0, HZ) < 0)
 		err = -EIO;
 	i915_request_put(rq);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index 1bc11c09faef..484759c9409c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -187,7 +187,7 @@ int i915_mock_selftests(void)
 	err = run_selftests(mock, NULL);
 	if (err) {
 		i915_selftest.mock = err;
-		return err;
+		return 1;
 	}
 
 	if (i915_selftest.mock < 0) {
@@ -430,7 +430,7 @@ module_param_named(st_timeout, i915_selftest.timeout_ms, uint, 0400);
 module_param_named(st_filter, i915_selftest.filter, charp, 0400);
 
 module_param_named_unsafe(mock_selftests, i915_selftest.mock, int, 0400);
-MODULE_PARM_DESC(mock_selftests, "Run selftests before loading, using mock hardware (0:disabled [default], 1:run tests then load driver, -1:run tests then exit module)");
+MODULE_PARM_DESC(mock_selftests, "Run selftests before loading, using mock hardware (0:disabled [default], 1:run tests then load driver, -1:run tests then leave dummy module)");
 
 module_param_named_unsafe(live_selftests, i915_selftest.live, int, 0400);
 MODULE_PARM_DESC(live_selftests, "Run selftests after driver initialisation on the live system (0:disabled [default], 1:run tests then continue, -1:run tests then exit module)");
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 7b0939e3f007..a6c71fca61aa 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -19,7 +19,7 @@ int igt_flush_test(struct drm_i915_private *i915)
 
 	cond_resched();
 
-	if (intel_gt_wait_for_idle(gt, HZ / 5) == -ETIME) {
+	if (intel_gt_wait_for_idle(gt, HZ) == -ETIME) {
 		pr_err("%pS timed out, cancelling all further testing.\n",
 		       __builtin_return_address(0));
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index c130010a7033..1c721542e277 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -5,7 +5,7 @@
  */
 
 #include "i915_drv.h"
-#include "gt/intel_gt_requests.h"
+#include "gt/intel_gt.h"
 
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.c b/drivers/gpu/drm/i915/selftests/igt_mmap.c
index 583a4ff8b8c9..e920a461bd36 100644
--- a/drivers/gpu/drm/i915/selftests/igt_mmap.c
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.c
@@ -9,15 +9,28 @@
 #include "i915_drv.h"
 #include "igt_mmap.h"
 
-unsigned long igt_mmap_node(struct drm_i915_private *i915,
-			    struct drm_vma_offset_node *node,
-			    unsigned long addr,
-			    unsigned long prot,
-			    unsigned long flags)
+unsigned long igt_mmap_offset(struct drm_i915_private *i915,
+			      u64 offset,
+			      unsigned long size,
+			      unsigned long prot,
+			      unsigned long flags)
 {
+	struct drm_vma_offset_node *node;
 	struct file *file;
+	unsigned long addr;
 	int err;
 
+	/* no need to refcount, we own this object */
+	drm_vma_offset_lock_lookup(i915->drm.vma_offset_manager);
+	node = drm_vma_offset_exact_lookup_locked(i915->drm.vma_offset_manager,
+						  offset / PAGE_SIZE, size / PAGE_SIZE);
+	drm_vma_offset_unlock_lookup(i915->drm.vma_offset_manager);
+
+	if (GEM_WARN_ON(!node)) {
+		pr_info("Failed to lookup %llx\n", offset);
+		return -ENOENT;
+	}
+
 	/* Pretend to open("/dev/dri/card0") */
 	file = mock_drm_getfile(i915->drm.primary, O_RDWR);
 	if (IS_ERR(file))
@@ -29,7 +42,7 @@ unsigned long igt_mmap_node(struct drm_i915_private *i915,
 		goto out_file;
 	}
 
-	addr = vm_mmap(file, addr, drm_vma_node_size(node) << PAGE_SHIFT,
+	addr = vm_mmap(file, 0, drm_vma_node_size(node) << PAGE_SHIFT,
 		       prot, flags, drm_vma_node_offset_addr(node));
 
 	drm_vma_node_revoke(node, file->private_data);
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.h b/drivers/gpu/drm/i915/selftests/igt_mmap.h
index 6e716cb59d7e..acbe34d81a6d 100644
--- a/drivers/gpu/drm/i915/selftests/igt_mmap.h
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.h
@@ -7,13 +7,15 @@
 #ifndef IGT_MMAP_H
 #define IGT_MMAP_H
 
+#include <linux/types.h>
+
 struct drm_i915_private;
 struct drm_vma_offset_node;
 
-unsigned long igt_mmap_node(struct drm_i915_private *i915,
-			    struct drm_vma_offset_node *node,
-			    unsigned long addr,
-			    unsigned long prot,
-			    unsigned long flags);
+unsigned long igt_mmap_offset(struct drm_i915_private *i915,
+			      u64 offset,
+			      unsigned long size,
+			      unsigned long prot,
+			      unsigned long flags);
 
 #endif /* IGT_MMAP_H */
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index c85d516b85cd..418caae84759 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -15,12 +15,15 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
-#include "gem/i915_gem_object_blt.h"
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
+#include "i915_buddy.h"
+#include "gt/intel_migrate.h"
 #include "i915_memcpy.h"
+#include "i915_ttm_buddy_manager.h"
 #include "selftests/igt_flush_test.h"
 #include "selftests/i915_random.h"
 
@@ -57,16 +60,15 @@ static int igt_mock_fill(void *arg)
 	LIST_HEAD(objects);
 	int err = 0;
 
-	page_size = mem->chunk_size;
+	page_size = PAGE_SIZE;
+	max_pages = div64_u64(total, page_size);
 	rem = total;
-retry:
-	max_pages = div64_u64(rem, page_size);
 
 	for_each_prime_number_from(page_num, 1, max_pages) {
 		resource_size_t size = page_num * page_size;
 		struct drm_i915_gem_object *obj;
 
-		obj = i915_gem_object_create_region(mem, size, 0);
+		obj = i915_gem_object_create_region(mem, size, 0, 0);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
 			break;
@@ -86,11 +88,6 @@ retry:
 		err = 0;
 	if (err == -ENXIO) {
 		if (page_num * page_size <= rem) {
-			if (mem->is_range_manager && max_pages > 1) {
-				max_pages >>= 1;
-				goto retry;
-			}
-
 			pr_err("%s failed, space still left in region\n",
 			       __func__);
 			err = -EINVAL;
@@ -113,7 +110,7 @@ igt_object_create(struct intel_memory_region *mem,
 	struct drm_i915_gem_object *obj;
 	int err;
 
-	obj = i915_gem_object_create_region(mem, size, flags);
+	obj = i915_gem_object_create_region(mem, size, 0, flags);
 	if (IS_ERR(obj))
 		return obj;
 
@@ -157,6 +154,7 @@ static bool is_contiguous(struct drm_i915_gem_object *obj)
 static int igt_mock_reserve(void *arg)
 {
 	struct intel_memory_region *mem = arg;
+	struct drm_i915_private *i915 = mem->i915;
 	resource_size_t avail = resource_size(&mem->region);
 	struct drm_i915_gem_object *obj;
 	const u32 chunk_size = SZ_32M;
@@ -166,16 +164,18 @@ static int igt_mock_reserve(void *arg)
 	LIST_HEAD(objects);
 	int err = 0;
 
-	if (!list_empty(&mem->reserved)) {
-		pr_err("%s region reserved list is not empty\n", __func__);
-		return -EINVAL;
-	}
-
 	count = avail / chunk_size;
 	order = i915_random_order(count, &prng);
 	if (!order)
 		return 0;
 
+	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+	if (IS_ERR(mem)) {
+		pr_err("failed to create memory region\n");
+		err = PTR_ERR(mem);
+		goto out_free_order;
+	}
+
 	/* Reserve a bunch of ranges within the region */
 	for (i = 0; i < count; ++i) {
 		u64 start = order[i] * chunk_size;
@@ -205,18 +205,12 @@ static int igt_mock_reserve(void *arg)
 	do {
 		u32 size = i915_prandom_u32_max_state(cur_avail, &prng);
 
-retry:
 		size = max_t(u32, round_up(size, PAGE_SIZE), PAGE_SIZE);
 		obj = igt_object_create(mem, &objects, size, 0);
 		if (IS_ERR(obj)) {
-			if (PTR_ERR(obj) == -ENXIO) {
-				if (mem->is_range_manager &&
-				    size > mem->chunk_size) {
-					size >>= 1;
-					goto retry;
-				}
+			if (PTR_ERR(obj) == -ENXIO)
 				break;
-			}
+
 			err = PTR_ERR(obj);
 			goto out_close;
 		}
@@ -230,9 +224,10 @@ retry:
 	}
 
 out_close:
-	kfree(order);
 	close_objects(mem, &objects);
-	intel_memory_region_unreserve(mem);
+	intel_memory_region_put(mem);
+out_free_order:
+	kfree(order);
 	return err;
 }
 
@@ -252,7 +247,7 @@ static int igt_mock_contiguous(void *arg)
 	total = resource_size(&mem->region);
 
 	/* Min size */
-	obj = igt_object_create(mem, &objects, mem->chunk_size,
+	obj = igt_object_create(mem, &objects, PAGE_SIZE,
 				I915_BO_ALLOC_CONTIGUOUS);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
@@ -333,17 +328,15 @@ static int igt_mock_contiguous(void *arg)
 	min = target;
 	target = total >> 1;
 
-	if (!mem->is_range_manager) {
-		/* Make sure we can still allocate all the fragmented space */
-		obj = igt_object_create(mem, &objects, target, 0);
-		if (IS_ERR(obj)) {
-			err = PTR_ERR(obj);
-			goto err_close_objects;
-		}
-
-		igt_object_release(obj);
+	/* Make sure we can still allocate all the fragmented space */
+	obj = igt_object_create(mem, &objects, target, 0);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto err_close_objects;
 	}
 
+	igt_object_release(obj);
+
 	/*
 	 * Even though we have enough free space, we don't have a big enough
 	 * contiguous block. Make sure that holds true.
@@ -362,7 +355,7 @@ static int igt_mock_contiguous(void *arg)
 		}
 
 		target >>= 1;
-	} while (target >= mem->chunk_size);
+	} while (target >= PAGE_SIZE);
 
 err_close_objects:
 	list_splice_tail(&holes, &objects);
@@ -374,7 +367,9 @@ static int igt_mock_splintered_region(void *arg)
 {
 	struct intel_memory_region *mem = arg;
 	struct drm_i915_private *i915 = mem->i915;
+	struct i915_ttm_buddy_resource *res;
 	struct drm_i915_gem_object *obj;
+	struct i915_buddy_mm *mm;
 	unsigned int expected_order;
 	LIST_HEAD(objects);
 	u64 size;
@@ -382,7 +377,7 @@ static int igt_mock_splintered_region(void *arg)
 
 	/*
 	 * Sanity check we can still allocate everything even if the
-	 * max_order != mm.size. i.e our starting address space size is not a
+	 * mm.max_order != mm.size. i.e our starting address space size is not a
 	 * power-of-two.
 	 */
 
@@ -391,20 +386,29 @@ static int igt_mock_splintered_region(void *arg)
 	if (IS_ERR(mem))
 		return PTR_ERR(mem);
 
-	expected_order = get_order(rounddown_pow_of_two(size));
-	if (mem->max_order != expected_order) {
-		pr_err("%s order mismatch(%u != %u)\n",
-		       __func__, mem->max_order, expected_order);
-		err = -EINVAL;
-		goto out_put;
-	}
-
 	obj = igt_object_create(mem, &objects, size, 0);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto out_close;
 	}
 
+	res = to_ttm_buddy_resource(obj->mm.res);
+	mm = res->mm;
+	if (mm->size != size) {
+		pr_err("%s size mismatch(%llu != %llu)\n",
+		       __func__, mm->size, size);
+		err = -EINVAL;
+		goto out_put;
+	}
+
+	expected_order = get_order(rounddown_pow_of_two(size));
+	if (mm->max_order != expected_order) {
+		pr_err("%s order mismatch(%u != %u)\n",
+		       __func__, mm->max_order, expected_order);
+		err = -EINVAL;
+		goto out_put;
+	}
+
 	close_objects(mem, &objects);
 
 	/*
@@ -415,15 +419,12 @@ static int igt_mock_splintered_region(void *arg)
 	 * sure that does indeed hold true.
 	 */
 
-	if (!mem->is_range_manager) {
-		obj = igt_object_create(mem, &objects, size,
-					I915_BO_ALLOC_CONTIGUOUS);
-		if (!IS_ERR(obj)) {
-			pr_err("%s too large contiguous allocation was not rejected\n",
-			       __func__);
-			err = -EINVAL;
-			goto out_close;
-		}
+	obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS);
+	if (!IS_ERR(obj)) {
+		pr_err("%s too large contiguous allocation was not rejected\n",
+		       __func__);
+		err = -EINVAL;
+		goto out_close;
 	}
 
 	obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size),
@@ -442,6 +443,74 @@ out_put:
 	return err;
 }
 
+#ifndef SZ_8G
+#define SZ_8G BIT_ULL(33)
+#endif
+
+static int igt_mock_max_segment(void *arg)
+{
+	const unsigned int max_segment = rounddown(UINT_MAX, PAGE_SIZE);
+	struct intel_memory_region *mem = arg;
+	struct drm_i915_private *i915 = mem->i915;
+	struct i915_ttm_buddy_resource *res;
+	struct drm_i915_gem_object *obj;
+	struct i915_buddy_block *block;
+	struct i915_buddy_mm *mm;
+	struct list_head *blocks;
+	struct scatterlist *sg;
+	LIST_HEAD(objects);
+	u64 size;
+	int err = 0;
+
+	/*
+	 * While we may create very large contiguous blocks, we may need
+	 * to break those down for consumption elsewhere. In particular,
+	 * dma-mapping with scatterlist elements have an implicit limit of
+	 * UINT_MAX on each element.
+	 */
+
+	size = SZ_8G;
+	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
+	obj = igt_object_create(mem, &objects, size, 0);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto out_put;
+	}
+
+	res = to_ttm_buddy_resource(obj->mm.res);
+	blocks = &res->blocks;
+	mm = res->mm;
+	size = 0;
+	list_for_each_entry(block, blocks, link) {
+		if (i915_buddy_block_size(mm, block) > size)
+			size = i915_buddy_block_size(mm, block);
+	}
+	if (size < max_segment) {
+		pr_err("%s: Failed to create a huge contiguous block [> %u], largest block %lld\n",
+		       __func__, max_segment, size);
+		err = -EINVAL;
+		goto out_close;
+	}
+
+	for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) {
+		if (sg->length > max_segment) {
+			pr_err("%s: Created an oversized scatterlist entry, %u > %u\n",
+			       __func__, sg->length, max_segment);
+			err = -EINVAL;
+			goto out_close;
+		}
+	}
+
+out_close:
+	close_objects(mem, &objects);
+out_put:
+	intel_memory_region_put(mem);
+	return err;
+}
+
 static int igt_gpu_write_dw(struct intel_context *ce,
 			    struct i915_vma *vma,
 			    u32 dword,
@@ -579,6 +648,62 @@ out_put:
 	return err;
 }
 
+static int igt_lmem_create_with_ps(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	int err = 0;
+	u32 ps;
+
+	for (ps = PAGE_SIZE; ps <= SZ_1G; ps <<= 1) {
+		struct drm_i915_gem_object *obj;
+		dma_addr_t daddr;
+
+		obj = __i915_gem_object_create_lmem_with_ps(i915, ps, ps, 0);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			if (err == -ENXIO || err == -E2BIG) {
+				pr_info("%s not enough lmem for ps(%u) err=%d\n",
+					__func__, ps, err);
+				err = 0;
+			}
+
+			break;
+		}
+
+		if (obj->base.size != ps) {
+			pr_err("%s size(%zu) != ps(%u)\n",
+			       __func__, obj->base.size, ps);
+			err = -EINVAL;
+			goto out_put;
+		}
+
+		i915_gem_object_lock(obj, NULL);
+		err = i915_gem_object_pin_pages(obj);
+		if (err)
+			goto out_put;
+
+		daddr = i915_gem_object_get_dma_address(obj, 0);
+		if (!IS_ALIGNED(daddr, ps)) {
+			pr_err("%s daddr(%pa) not aligned with ps(%u)\n",
+			       __func__, &daddr, ps);
+			err = -EINVAL;
+			goto out_unpin;
+		}
+
+out_unpin:
+		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj);
+out_put:
+		i915_gem_object_unlock(obj);
+		i915_gem_object_put(obj);
+
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
 static int igt_lmem_create_cleared_cpu(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -741,6 +866,7 @@ static int igt_lmem_write_cpu(void *arg)
 		PAGE_SIZE - 64,
 	};
 	struct intel_engine_cs *engine;
+	struct i915_request *rq;
 	u32 *vaddr;
 	u32 sz;
 	u32 i;
@@ -767,15 +893,20 @@ static int igt_lmem_write_cpu(void *arg)
 		goto out_put;
 	}
 
+	i915_gem_object_lock(obj, NULL);
 	/* Put the pages into a known state -- from the gpu for added fun */
 	intel_engine_pm_get(engine);
-	err = i915_gem_object_fill_blt(obj, engine->kernel_context, 0xdeadbeaf);
-	intel_engine_pm_put(engine);
-	if (err)
-		goto out_unpin;
+	err = intel_context_migrate_clear(engine->gt->migrate.context, NULL,
+					  obj->mm.pages->sgl, I915_CACHE_NONE,
+					  true, 0xdeadbeaf, &rq);
+	if (rq) {
+		dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
+		i915_request_put(rq);
+	}
 
-	i915_gem_object_lock(obj, NULL);
-	err = i915_gem_object_set_to_wc_domain(obj, true);
+	intel_engine_pm_put(engine);
+	if (!err)
+		err = i915_gem_object_set_to_wc_domain(obj, true);
 	i915_gem_object_unlock(obj);
 	if (err)
 		goto out_unpin;
@@ -858,7 +989,7 @@ create_region_for_mapping(struct intel_memory_region *mr, u64 size, u32 type,
 	struct drm_i915_gem_object *obj;
 	void *addr;
 
-	obj = i915_gem_object_create_region(mr, size, 0);
+	obj = i915_gem_object_create_region(mr, size, 0, 0);
 	if (IS_ERR(obj)) {
 		if (PTR_ERR(obj) == -ENOSPC) /* Stolen memory */
 			return ERR_PTR(-ENODEV);
@@ -1046,6 +1177,7 @@ int intel_memory_region_mock_selftests(void)
 		SUBTEST(igt_mock_fill),
 		SUBTEST(igt_mock_contiguous),
 		SUBTEST(igt_mock_splintered_region),
+		SUBTEST(igt_mock_max_segment),
 	};
 	struct intel_memory_region *mem;
 	struct drm_i915_private *i915;
@@ -1074,6 +1206,7 @@ int intel_memory_region_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_lmem_create),
+		SUBTEST(igt_lmem_create_with_ps),
 		SUBTEST(igt_lmem_create_cleared_cpu),
 		SUBTEST(igt_lmem_write_cpu),
 		SUBTEST(igt_lmem_write_gpu),
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
new file mode 100644
index 000000000000..4b328346b48a
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+//#include "gt/intel_engine_user.h"
+#include "gt/intel_gt.h"
+#include "i915_drv.h"
+#include "i915_selftest.h"
+
+#include "selftests/intel_scheduler_helpers.h"
+
+#define REDUCED_TIMESLICE	5
+#define REDUCED_PREEMPT		10
+#define WAIT_FOR_RESET_TIME	10000
+
+int intel_selftest_modify_policy(struct intel_engine_cs *engine,
+				 struct intel_selftest_saved_policy *saved,
+				 u32 modify_type)
+
+{
+	int err;
+
+	saved->reset = engine->i915->params.reset;
+	saved->flags = engine->flags;
+	saved->timeslice = engine->props.timeslice_duration_ms;
+	saved->preempt_timeout = engine->props.preempt_timeout_ms;
+
+	switch (modify_type) {
+	case SELFTEST_SCHEDULER_MODIFY_FAST_RESET:
+		/*
+		 * Enable force pre-emption on time slice expiration
+		 * together with engine reset on pre-emption timeout.
+		 * This is required to make the GuC notice and reset
+		 * the single hanging context.
+		 * Also, reduce the preemption timeout to something
+		 * small to speed the test up.
+		 */
+		engine->i915->params.reset = 2;
+		engine->flags |= I915_ENGINE_WANT_FORCED_PREEMPTION;
+		engine->props.timeslice_duration_ms = REDUCED_TIMESLICE;
+		engine->props.preempt_timeout_ms = REDUCED_PREEMPT;
+		break;
+
+	case SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK:
+		engine->props.preempt_timeout_ms = 0;
+		break;
+
+	default:
+		pr_err("Invalid scheduler policy modification type: %d!\n", modify_type);
+		return -EINVAL;
+	}
+
+	if (!intel_engine_uses_guc(engine))
+		return 0;
+
+	err = intel_guc_global_policies_update(&engine->gt->uc.guc);
+	if (err)
+		intel_selftest_restore_policy(engine, saved);
+
+	return err;
+}
+
+int intel_selftest_restore_policy(struct intel_engine_cs *engine,
+				  struct intel_selftest_saved_policy *saved)
+{
+	/* Restore the original policies */
+	engine->i915->params.reset = saved->reset;
+	engine->flags = saved->flags;
+	engine->props.timeslice_duration_ms = saved->timeslice;
+	engine->props.preempt_timeout_ms = saved->preempt_timeout;
+
+	if (!intel_engine_uses_guc(engine))
+		return 0;
+
+	return intel_guc_global_policies_update(&engine->gt->uc.guc);
+}
+
+int intel_selftest_wait_for_rq(struct i915_request *rq)
+{
+	long ret;
+
+	ret = i915_request_wait(rq, 0, WAIT_FOR_RESET_TIME);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
new file mode 100644
index 000000000000..35c098601ac0
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _INTEL_SELFTEST_SCHEDULER_HELPERS_H_
+#define _INTEL_SELFTEST_SCHEDULER_HELPERS_H_
+
+#include <linux/types.h>
+
+struct i915_request;
+struct intel_engine_cs;
+
+struct intel_selftest_saved_policy {
+	u32 flags;
+	u32 reset;
+	u64 timeslice;
+	u64 preempt_timeout;
+};
+
+enum selftest_scheduler_modify {
+	SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK = 0,
+	SELFTEST_SCHEDULER_MODIFY_FAST_RESET,
+};
+
+int intel_selftest_modify_policy(struct intel_engine_cs *engine,
+				 struct intel_selftest_saved_policy *saved,
+				 enum selftest_scheduler_modify modify_type);
+int intel_selftest_restore_policy(struct intel_engine_cs *engine,
+				  struct intel_selftest_saved_policy *saved);
+int intel_selftest_wait_for_rq(struct i915_request *rq);
+
+#endif
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 8ef9e6a4ad05..720b60853f8b 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -68,6 +68,7 @@ static int intel_shadow_table_check(void)
 		{ gen8_shadowed_regs, ARRAY_SIZE(gen8_shadowed_regs) },
 		{ gen11_shadowed_regs, ARRAY_SIZE(gen11_shadowed_regs) },
 		{ gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) },
+		{ xehp_shadowed_regs, ARRAY_SIZE(xehp_shadowed_regs) },
 	};
 	const i915_reg_t *reg;
 	unsigned int i, j;
@@ -103,6 +104,7 @@ int intel_uncore_mock_selftests(void)
 		{ __gen9_fw_ranges, ARRAY_SIZE(__gen9_fw_ranges), true },
 		{ __gen11_fw_ranges, ARRAY_SIZE(__gen11_fw_ranges), true },
 		{ __gen12_fw_ranges, ARRAY_SIZE(__gen12_fw_ranges), true },
+		{ __xehp_fw_ranges, ARRAY_SIZE(__xehp_fw_ranges), true },
 	};
 	int err, i;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index d189c4bd4bef..4f8180146888 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -52,7 +52,8 @@ void mock_device_flush(struct drm_i915_private *i915)
 	do {
 		for_each_engine(engine, gt, id)
 			mock_engine_flush(engine);
-	} while (intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT));
+	} while (intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT,
+						  NULL));
 }
 
 static void mock_device_release(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 5c7ae40bba63..cc047ec594f9 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -73,7 +73,6 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 	ppgtt->vm.gt = &i915->gt;
 	ppgtt->vm.i915 = i915;
 	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
-	ppgtt->vm.file = ERR_PTR(-ENODEV);
 	ppgtt->vm.dma = i915->drm.dev;
 
 	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index eafc5a04975c..efa86dffe3c6 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -3,6 +3,7 @@
  * Copyright © 2019-2021 Intel Corporation
  */
 
+#include <drm/ttm/ttm_placement.h>
 #include <linux/scatterlist.h>
 
 #include <drm/ttm/ttm_placement.h>
@@ -16,7 +17,7 @@
 static void mock_region_put_pages(struct drm_i915_gem_object *obj,
 				  struct sg_table *pages)
 {
-	intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+	intel_region_ttm_resource_free(obj->mm.region, obj->mm.res);
 	sg_free_table(pages);
 	kfree(pages);
 }
@@ -25,26 +26,31 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
 {
 	unsigned int flags;
 	struct sg_table *pages;
+	int err;
 
-	flags = I915_ALLOC_MIN_PAGE_SIZE;
+	flags = 0;
 	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
-		flags |= I915_ALLOC_CONTIGUOUS;
+		flags |= TTM_PL_FLAG_CONTIGUOUS;
 
-	obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
-							 obj->base.size,
-							 flags);
-	if (IS_ERR(obj->mm.st_mm_node))
-		return PTR_ERR(obj->mm.st_mm_node);
+	obj->mm.res = intel_region_ttm_resource_alloc(obj->mm.region,
+						      obj->base.size,
+						      flags);
+	if (IS_ERR(obj->mm.res))
+		return PTR_ERR(obj->mm.res);
 
-	pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
+	pages = intel_region_ttm_resource_to_st(obj->mm.region, obj->mm.res);
 	if (IS_ERR(pages)) {
-		intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
-		return PTR_ERR(pages);
+		err = PTR_ERR(pages);
+		goto err_free_resource;
 	}
 
 	__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
 
 	return 0;
+
+err_free_resource:
+	intel_region_ttm_resource_free(obj->mm.region, obj->mm.res);
+	return err;
 }
 
 static const struct drm_i915_gem_object_ops mock_region_obj_ops = {
@@ -57,6 +63,7 @@ static const struct drm_i915_gem_object_ops mock_region_obj_ops = {
 static int mock_object_init(struct intel_memory_region *mem,
 			    struct drm_i915_gem_object *obj,
 			    resource_size_t size,
+			    resource_size_t page_size,
 			    unsigned int flags)
 {
 	static struct lock_class_key lock_class;
diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c
index 37ae68a7fba5..9b84df34a6a1 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-kms.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c
@@ -93,11 +93,8 @@ static int dcss_kms_bridge_connector_init(struct dcss_kms_dev *kms)
 
 	ret = drm_bridge_attach(encoder, bridge, NULL,
 				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
-	if (ret < 0) {
-		dev_err(ddev->dev, "Unable to attach bridge %pOF\n",
-			bridge->of_node);
+	if (ret < 0)
 		return ret;
-	}
 
 	kms->connector = drm_bridge_connector_init(ddev, encoder);
 	if (IS_ERR(kms->connector)) {
@@ -133,8 +130,6 @@ struct dcss_kms_dev *dcss_kms_attach(struct dcss_dev *dcss)
 	if (ret)
 		goto cleanup_mode_config;
 
-	drm->irq_enabled = true;
-
 	ret = dcss_kms_bridge_connector_init(kms);
 	if (ret)
 		goto cleanup_mode_config;
@@ -178,7 +173,6 @@ void dcss_kms_detach(struct dcss_kms_dev *kms)
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
 	drm_crtc_vblank_off(&kms->crtc.base);
-	drm->irq_enabled = false;
 	drm_mode_config_cleanup(drm);
 	dcss_crtc_deinit(&kms->crtc, drm);
 	drm->dev_private = NULL;
diff --git a/drivers/gpu/drm/imx/dcss/dcss-plane.c b/drivers/gpu/drm/imx/dcss/dcss-plane.c
index 044d3bdf313c..ac45d54acd4e 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-plane.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-plane.c
@@ -361,7 +361,6 @@ static void dcss_plane_atomic_disable(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs dcss_plane_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = dcss_plane_atomic_check,
 	.atomic_update = dcss_plane_atomic_update,
 	.atomic_disable = dcss_plane_atomic_disable,
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 76819a8ac37f..9558e9e1b431 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -208,17 +208,6 @@ static int imx_drm_bind(struct device *dev)
 		return PTR_ERR(drm);
 
 	/*
-	 * enable drm irq mode.
-	 * - with irq_enabled = true, we can use the vblank feature.
-	 *
-	 * P.S. note that we wouldn't use drm irq handler but
-	 *      just specific driver own one instead because
-	 *      drm framework supports only one irq handler and
-	 *      drivers can well take care of their interrupts
-	 */
-	drm->irq_enabled = true;
-
-	/*
 	 * set max width and height as default value(4096x4096).
 	 * this value would be used to check framebuffer size limitation
 	 * at drm_mode_addfb().
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 53132ddf9587..e5078d03020d 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -465,10 +465,8 @@ static int imx_ldb_register(struct drm_device *drm,
 
 	if (imx_ldb_ch->bridge) {
 		ret = drm_bridge_attach(encoder, imx_ldb_ch->bridge, NULL, 0);
-		if (ret) {
-			DRM_ERROR("Failed to initialize bridge with drm\n");
+		if (ret)
 			return ret;
-		}
 	} else {
 		/*
 		 * We want to add the connector whenever there is no bridge
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index bd1f9f0366d3..846c1aae69c8 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -772,7 +772,6 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs ipu_plane_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = ipu_plane_atomic_check,
 	.atomic_disable = ipu_plane_atomic_disable,
 	.atomic_update = ipu_plane_atomic_update,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index e0412e694fd9..a8aba0141ce7 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -294,11 +294,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 
 	if (imxpd->next_bridge) {
 		ret = drm_bridge_attach(encoder, imxpd->next_bridge, bridge, 0);
-		if (ret < 0) {
-			dev_err(imxpd->dev, "failed to attach bridge: %d\n",
-				ret);
+		if (ret < 0)
 			return ret;
-		}
 	} else {
 		drm_connector_helper_add(connector,
 					 &imx_pd_connector_helper_funcs);
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
index 5244f4763477..a5df1c8d34cd 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
@@ -33,7 +33,6 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_of.h>
 #include <drm/drm_panel.h>
@@ -702,29 +701,6 @@ static int ingenic_drm_encoder_atomic_check(struct drm_encoder *encoder,
 	}
 }
 
-static void ingenic_drm_atomic_helper_commit_tail(struct drm_atomic_state *old_state)
-{
-	/*
-	 * Just your regular drm_atomic_helper_commit_tail(), but only calls
-	 * drm_atomic_helper_wait_for_vblanks() if priv->no_vblank.
-	 */
-	struct drm_device *dev = old_state->dev;
-	struct ingenic_drm *priv = drm_device_get_priv(dev);
-
-	drm_atomic_helper_commit_modeset_disables(dev, old_state);
-
-	drm_atomic_helper_commit_planes(dev, old_state, 0);
-
-	drm_atomic_helper_commit_modeset_enables(dev, old_state);
-
-	drm_atomic_helper_commit_hw_done(old_state);
-
-	if (!priv->no_vblank)
-		drm_atomic_helper_wait_for_vblanks(dev, old_state);
-
-	drm_atomic_helper_cleanup_planes(dev, old_state);
-}
-
 static irqreturn_t ingenic_drm_irq_handler(int irq, void *arg)
 {
 	struct ingenic_drm *priv = drm_device_get_priv(arg);
@@ -745,6 +721,9 @@ static int ingenic_drm_enable_vblank(struct drm_crtc *crtc)
 {
 	struct ingenic_drm *priv = drm_crtc_get_priv(crtc);
 
+	if (priv->no_vblank)
+		return -EINVAL;
+
 	regmap_update_bits(priv->map, JZ_REG_LCD_CTRL,
 			   JZ_LCD_CTRL_EOF_IRQ, JZ_LCD_CTRL_EOF_IRQ);
 
@@ -799,8 +778,6 @@ static const struct drm_driver ingenic_drm_driver_data = {
 	.fops			= &ingenic_drm_fops,
 	.gem_create_object	= ingenic_drm_gem_create_object,
 	DRM_GEM_CMA_DRIVER_OPS,
-
-	.irq_handler		= ingenic_drm_irq_handler,
 };
 
 static const struct drm_plane_funcs ingenic_drm_primary_plane_funcs = {
@@ -830,7 +807,6 @@ static const struct drm_plane_helper_funcs ingenic_drm_plane_helper_funcs = {
 	.atomic_update		= ingenic_drm_plane_atomic_update,
 	.atomic_check		= ingenic_drm_plane_atomic_check,
 	.atomic_disable		= ingenic_drm_plane_atomic_disable,
-	.prepare_fb		= drm_gem_plane_helper_prepare_fb,
 };
 
 static const struct drm_crtc_helper_funcs ingenic_drm_crtc_helper_funcs = {
@@ -855,7 +831,7 @@ static const struct drm_mode_config_funcs ingenic_drm_mode_config_funcs = {
 };
 
 static struct drm_mode_config_helper_funcs ingenic_drm_mode_config_helpers = {
-	.atomic_commit_tail = ingenic_drm_atomic_helper_commit_tail,
+	.atomic_commit_tail = drm_atomic_helper_commit_tail,
 };
 
 static void ingenic_drm_unbind_all(void *d)
@@ -988,9 +964,6 @@ static int ingenic_drm_bind(struct device *dev, bool has_components)
 	priv->dma_hwdescs->hwdesc_pal.cmd = JZ_LCD_CMD_ENABLE_PAL
 		| (sizeof(priv->dma_hwdescs->palette) / 4);
 
-	if (soc_info->has_osd)
-		priv->ipu_plane = drm_plane_from_index(drm, 0);
-
 	primary = priv->soc_info->has_osd ? &priv->f1 : &priv->f0;
 
 	drm_plane_helper_add(primary, &ingenic_drm_plane_helper_funcs);
@@ -1085,10 +1058,8 @@ static int ingenic_drm_bind(struct device *dev, bool has_components)
 		drm_encoder_helper_add(encoder, &ingenic_drm_encoder_helper_funcs);
 
 		ret = drm_bridge_attach(encoder, bridge, NULL, 0);
-		if (ret) {
-			dev_err(dev, "Unable to attach bridge\n");
+		if (ret)
 			return ret;
-		}
 	}
 
 	drm_for_each_encoder(encoder, drm) {
@@ -1099,7 +1070,7 @@ static int ingenic_drm_bind(struct device *dev, bool has_components)
 		encoder->possible_clones = clone_mask;
 	}
 
-	ret = drm_irq_install(drm, irq);
+	ret = devm_request_irq(dev, irq, ingenic_drm_irq_handler, 0, drm->driver->name, drm);
 	if (ret) {
 		dev_err(dev, "Unable to install IRQ handler\n");
 		return ret;
diff --git a/drivers/gpu/drm/ingenic/ingenic-ipu.c b/drivers/gpu/drm/ingenic/ingenic-ipu.c
index 61b6d9fdbba1..aeb8a757d213 100644
--- a/drivers/gpu/drm/ingenic/ingenic-ipu.c
+++ b/drivers/gpu/drm/ingenic/ingenic-ipu.c
@@ -625,7 +625,6 @@ static const struct drm_plane_helper_funcs ingenic_ipu_plane_helper_funcs = {
 	.atomic_update		= ingenic_ipu_plane_atomic_update,
 	.atomic_check		= ingenic_ipu_plane_atomic_check,
 	.atomic_disable		= ingenic_ipu_plane_atomic_disable,
-	.prepare_fb		= drm_gem_plane_helper_prepare_fb,
 };
 
 static int
diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c
index f54392ec4fab..1c2f4799f421 100644
--- a/drivers/gpu/drm/kmb/kmb_drv.c
+++ b/drivers/gpu/drm/kmb/kmb_drv.c
@@ -17,7 +17,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 
@@ -413,14 +412,29 @@ static void kmb_irq_reset(struct drm_device *drm)
 	kmb_write_lcd(to_kmb(drm), LCD_INT_ENABLE, 0);
 }
 
+static int kmb_irq_install(struct drm_device *drm, unsigned int irq)
+{
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	kmb_irq_reset(drm);
+
+	return request_irq(irq, kmb_isr, 0, drm->driver->name, drm);
+}
+
+static void kmb_irq_uninstall(struct drm_device *drm)
+{
+	struct kmb_drm_private *kmb = to_kmb(drm);
+
+	kmb_irq_reset(drm);
+	free_irq(kmb->irq_lcd, drm);
+}
+
 DEFINE_DRM_GEM_CMA_FOPS(fops);
 
 static const struct drm_driver kmb_driver = {
 	.driver_features = DRIVER_GEM |
 	    DRIVER_MODESET | DRIVER_ATOMIC,
-	.irq_handler = kmb_isr,
-	.irq_preinstall = kmb_irq_reset,
-	.irq_uninstall = kmb_irq_reset,
 	/* GEM Operations */
 	.fops = &fops,
 	DRM_GEM_CMA_DRIVER_OPS_VMAP,
@@ -442,7 +456,7 @@ static int kmb_remove(struct platform_device *pdev)
 	of_node_put(kmb->crtc.port);
 	kmb->crtc.port = NULL;
 	pm_runtime_get_sync(drm->dev);
-	drm_irq_uninstall(drm);
+	kmb_irq_uninstall(drm);
 	pm_runtime_put_sync(drm->dev);
 	pm_runtime_disable(drm->dev);
 
@@ -532,7 +546,7 @@ static int kmb_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_free;
 
-	ret = drm_irq_install(&kmb->drm, kmb->irq_lcd);
+	ret = kmb_irq_install(&kmb->drm, kmb->irq_lcd);
 	if (ret < 0) {
 		drm_err(&kmb->drm, "failed to install IRQ handler\n");
 		goto err_irq;
diff --git a/drivers/gpu/drm/kmb/kmb_dsi.c b/drivers/gpu/drm/kmb/kmb_dsi.c
index 231041b269f5..1793cd31b117 100644
--- a/drivers/gpu/drm/kmb/kmb_dsi.c
+++ b/drivers/gpu/drm/kmb/kmb_dsi.c
@@ -1441,7 +1441,6 @@ int kmb_dsi_encoder_init(struct drm_device *dev, struct kmb_dsi *kmb_dsi)
 	ret = drm_bridge_attach(encoder, adv_bridge, NULL,
 				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 	if (ret) {
-		DRM_ERROR("failed to attach bridge to MIPI\n");
 		drm_encoder_cleanup(encoder);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
index ecf3267334ff..dba8329937a3 100644
--- a/drivers/gpu/drm/lima/lima_sched.c
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -508,7 +508,8 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 	INIT_WORK(&pipe->recover_work, lima_sched_recover_work);
 
 	return drm_sched_init(&pipe->base, &lima_sched_ops, 1,
-			      lima_job_hang_limit, msecs_to_jiffies(timeout),
+			      lima_job_hang_limit,
+			      msecs_to_jiffies(timeout), NULL,
 			      NULL, name);
 }
 
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 4ddc55d58f38..ce12a36e2db4 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -1479,7 +1479,6 @@ static struct drm_simple_display_pipe_funcs mcde_display_funcs = {
 	.update = mcde_display_update,
 	.enable_vblank = mcde_display_enable_vblank,
 	.disable_vblank = mcde_display_disable_vblank,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 int mcde_display_init(struct drm_device *drm)
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index 34a00d7e9c38..180ebbccbeda 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -760,7 +760,7 @@ static void mcde_dsi_start(struct mcde_dsi *d)
 		DSI_MCTL_MAIN_DATA_CTL_BTA_EN |
 		DSI_MCTL_MAIN_DATA_CTL_READ_EN |
 		DSI_MCTL_MAIN_DATA_CTL_REG_TE_EN;
-	if (!(d->mdsi->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(d->mdsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		val |= DSI_MCTL_MAIN_DATA_CTL_HOST_EOT_GEN;
 	writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
 
@@ -1052,7 +1052,6 @@ static int mcde_dsi_bridge_attach(struct drm_bridge *bridge,
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
 	struct drm_device *drm = bridge->dev;
-	int ret;
 
 	if (!drm_core_check_feature(drm, DRIVER_ATOMIC)) {
 		dev_err(d->dev, "we need atomic updates\n");
@@ -1060,13 +1059,7 @@ static int mcde_dsi_bridge_attach(struct drm_bridge *bridge,
 	}
 
 	/* Attach the DSI bridge to the output (panel etc) bridge */
-	ret = drm_bridge_attach(bridge->encoder, d->bridge_out, bridge, flags);
-	if (ret) {
-		dev_err(d->dev, "failed to attach the DSI bridge\n");
-		return ret;
-	}
-
-	return 0;
+	return drm_bridge_attach(bridge->encoder, d->bridge_out, bridge, flags);
 }
 
 static const struct drm_bridge_funcs mcde_dsi_bridge_funcs = {
diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index dc54a7a69005..29098d7c8307 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
-mediatek-drm-y := mtk_disp_ccorr.o \
+mediatek-drm-y := mtk_disp_aal.o \
+		  mtk_disp_ccorr.o \
 		  mtk_disp_color.o \
 		  mtk_disp_gamma.o \
 		  mtk_disp_ovl.o \
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_aal.c b/drivers/gpu/drm/mediatek/mtk_disp_aal.c
new file mode 100644
index 000000000000..f46d4ab73d6a
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_disp_aal.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 MediaTek Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
+
+#include "mtk_disp_drv.h"
+#include "mtk_drm_crtc.h"
+#include "mtk_drm_ddp_comp.h"
+
+#define DISP_AAL_EN				0x0000
+#define AAL_EN						BIT(0)
+#define DISP_AAL_SIZE				0x0030
+#define DISP_AAL_OUTPUT_SIZE			0x04d8
+
+
+struct mtk_disp_aal_data {
+	bool has_gamma;
+};
+
+/**
+ * struct mtk_disp_aal - DISP_AAL driver structure
+ * @ddp_comp - structure containing type enum and hardware resources
+ * @crtc - associated crtc to report irq events to
+ */
+struct mtk_disp_aal {
+	struct clk *clk;
+	void __iomem *regs;
+	struct cmdq_client_reg cmdq_reg;
+	const struct mtk_disp_aal_data *data;
+};
+
+int mtk_aal_clk_enable(struct device *dev)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	return clk_prepare_enable(aal->clk);
+}
+
+void mtk_aal_clk_disable(struct device *dev)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(aal->clk);
+}
+
+void mtk_aal_config(struct device *dev, unsigned int w,
+			   unsigned int h, unsigned int vrefresh,
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, &aal->cmdq_reg, aal->regs, DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, &aal->cmdq_reg, aal->regs, DISP_AAL_OUTPUT_SIZE);
+}
+
+void mtk_aal_gamma_set(struct device *dev, struct drm_crtc_state *state)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	if (aal->data && aal->data->has_gamma)
+		mtk_gamma_set_common(aal->regs, state);
+}
+
+void mtk_aal_start(struct device *dev)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	writel(AAL_EN, aal->regs + DISP_AAL_EN);
+}
+
+void mtk_aal_stop(struct device *dev)
+{
+	struct mtk_disp_aal *aal = dev_get_drvdata(dev);
+
+	writel_relaxed(0x0, aal->regs + DISP_AAL_EN);
+}
+
+static int mtk_disp_aal_bind(struct device *dev, struct device *master,
+			       void *data)
+{
+	return 0;
+}
+
+static void mtk_disp_aal_unbind(struct device *dev, struct device *master,
+				  void *data)
+{
+}
+
+static const struct component_ops mtk_disp_aal_component_ops = {
+	.bind	= mtk_disp_aal_bind,
+	.unbind = mtk_disp_aal_unbind,
+};
+
+static int mtk_disp_aal_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_disp_aal *priv;
+	struct resource *res;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(dev, "failed to get aal clk\n");
+		return PTR_ERR(priv->clk);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->regs)) {
+		dev_err(dev, "failed to ioremap aal\n");
+		return PTR_ERR(priv->regs);
+	}
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	ret = cmdq_dev_get_client_reg(dev, &priv->cmdq_reg, 0);
+	if (ret)
+		dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
+#endif
+
+	priv->data = of_device_get_match_data(dev);
+	platform_set_drvdata(pdev, priv);
+
+	ret = component_add(dev, &mtk_disp_aal_component_ops);
+	if (ret)
+		dev_err(dev, "Failed to add component: %d\n", ret);
+
+	return ret;
+}
+
+static int mtk_disp_aal_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &mtk_disp_aal_component_ops);
+
+	return 0;
+}
+
+static const struct mtk_disp_aal_data mt8173_aal_driver_data = {
+	.has_gamma = true,
+};
+
+static const struct of_device_id mtk_disp_aal_driver_dt_match[] = {
+	{ .compatible = "mediatek,mt8173-disp-aal",
+	  .data = &mt8173_aal_driver_data},
+	{ .compatible = "mediatek,mt8183-disp-aal"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_disp_aal_driver_dt_match);
+
+struct platform_driver mtk_disp_aal_driver = {
+	.probe		= mtk_disp_aal_probe,
+	.remove		= mtk_disp_aal_remove,
+	.driver		= {
+		.name	= "mediatek-disp-aal",
+		.owner	= THIS_MODULE,
+		.of_match_table = mtk_disp_aal_driver_dt_match,
+	},
+};
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index cafd9df2d63b..86c3068894b1 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -9,6 +9,15 @@
 #include <linux/soc/mediatek/mtk-cmdq.h>
 #include "mtk_drm_plane.h"
 
+int mtk_aal_clk_enable(struct device *dev);
+void mtk_aal_clk_disable(struct device *dev);
+void mtk_aal_config(struct device *dev, unsigned int w,
+		    unsigned int h, unsigned int vrefresh,
+		    unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
+void mtk_aal_gamma_set(struct device *dev, struct drm_crtc_state *state);
+void mtk_aal_start(struct device *dev);
+void mtk_aal_stop(struct device *dev);
+
 void mtk_ccorr_ctm_set(struct device *dev, struct drm_crtc_state *state);
 int mtk_ccorr_clk_enable(struct device *dev);
 void mtk_ccorr_clk_disable(struct device *dev);
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
index 705f28ceb4dd..75d7f45579e2 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
@@ -162,10 +162,10 @@ void mtk_rdma_config(struct device *dev, unsigned int width,
 	/*
 	 * Enable FIFO underflow since DSI and DPI can't be blocked.
 	 * Keep the FIFO pseudo size reset default of 8 KiB. Set the
-	 * output threshold to 6 microseconds with 7/6 overhead to
-	 * account for blanking, and with a pixel depth of 4 bytes:
+	 * output threshold to 70% of max fifo size to make sure the
+	 * threhold will not overflow
 	 */
-	threshold = width * height * vrefresh * 4 * 7 / 1000000;
+	threshold = rdma_fifo_size * 7 / 10;
 	reg = RDMA_FIFO_UNDERFLOW_EN |
 	      RDMA_FIFO_PSEUDO_SIZE(rdma_fifo_size) |
 	      RDMA_OUTPUT_VALID_FIFO_THRESHOLD(threshold);
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index e94738fe4db8..4554e2de1430 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -718,10 +718,8 @@ static int mtk_dpi_bind(struct device *dev, struct device *master, void *data)
 
 	ret = drm_bridge_attach(&dpi->encoder, &dpi->bridge, NULL,
 				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
-	if (ret) {
-		dev_err(dev, "Failed to attach bridge: %d\n", ret);
+	if (ret)
 		goto err_cleanup;
-	}
 
 	dpi->connector = drm_bridge_connector_init(drm_dev, &dpi->encoder);
 	if (IS_ERR(dpi->connector)) {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 735efe79f075..5f81489fc60c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -4,6 +4,8 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/mailbox_controller.h>
 #include <linux/pm_runtime.h>
 #include <linux/soc/mediatek/mtk-cmdq.h>
 #include <linux/soc/mediatek/mtk-mmsys.h>
@@ -50,8 +52,11 @@ struct mtk_drm_crtc {
 	bool				pending_async_planes;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct cmdq_client		*cmdq_client;
+	struct mbox_client		cmdq_cl;
+	struct mbox_chan		*cmdq_chan;
+	struct cmdq_pkt			cmdq_handle;
 	u32				cmdq_event;
+	u32				cmdq_vblank_cnt;
 #endif
 
 	struct device			*mmsys_dev;
@@ -222,9 +227,79 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 }
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-static void ddp_cmdq_cb(struct cmdq_cb_data data)
+static int mtk_drm_cmdq_pkt_create(struct mbox_chan *chan, struct cmdq_pkt *pkt,
+				    size_t size)
 {
-	cmdq_pkt_destroy(data.data);
+	struct device *dev;
+	dma_addr_t dma_addr;
+
+	pkt->va_base = kzalloc(size, GFP_KERNEL);
+	if (!pkt->va_base) {
+		kfree(pkt);
+		return -ENOMEM;
+	}
+	pkt->buf_size = size;
+
+	dev = chan->mbox->dev;
+	dma_addr = dma_map_single(dev, pkt->va_base, pkt->buf_size,
+				  DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_addr)) {
+		dev_err(dev, "dma map failed, size=%u\n", (u32)(u64)size);
+		kfree(pkt->va_base);
+		kfree(pkt);
+		return -ENOMEM;
+	}
+
+	pkt->pa_base = dma_addr;
+
+	return 0;
+}
+
+static void mtk_drm_cmdq_pkt_destroy(struct mbox_chan *chan, struct cmdq_pkt *pkt)
+{
+	dma_unmap_single(chan->mbox->dev, pkt->pa_base, pkt->buf_size,
+			 DMA_TO_DEVICE);
+	kfree(pkt->va_base);
+	kfree(pkt);
+}
+
+static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
+{
+	struct mtk_drm_crtc *mtk_crtc = container_of(cl, struct mtk_drm_crtc, cmdq_cl);
+	struct cmdq_cb_data *data = mssg;
+	struct mtk_crtc_state *state;
+	unsigned int i;
+
+	state = to_mtk_crtc_state(mtk_crtc->base.state);
+
+	state->pending_config = false;
+
+	if (mtk_crtc->pending_planes) {
+		for (i = 0; i < mtk_crtc->layer_nr; i++) {
+			struct drm_plane *plane = &mtk_crtc->planes[i];
+			struct mtk_plane_state *plane_state;
+
+			plane_state = to_mtk_plane_state(plane->state);
+
+			plane_state->pending.config = false;
+		}
+		mtk_crtc->pending_planes = false;
+	}
+
+	if (mtk_crtc->pending_async_planes) {
+		for (i = 0; i < mtk_crtc->layer_nr; i++) {
+			struct drm_plane *plane = &mtk_crtc->planes[i];
+			struct mtk_plane_state *plane_state;
+
+			plane_state = to_mtk_plane_state(plane->state);
+
+			plane_state->pending.async_config = false;
+		}
+		mtk_crtc->pending_async_planes = false;
+	}
+
+	mtk_crtc->cmdq_vblank_cnt = 0;
+	mtk_drm_cmdq_pkt_destroy(mtk_crtc->cmdq_chan, data->pkt);
 }
 #endif
 
@@ -378,7 +453,8 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				    state->pending_vrefresh, 0,
 				    cmdq_handle);
 
-		state->pending_config = false;
+		if (!cmdq_handle)
+			state->pending_config = false;
 	}
 
 	if (mtk_crtc->pending_planes) {
@@ -398,9 +474,12 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				mtk_ddp_comp_layer_config(comp, local_layer,
 							  plane_state,
 							  cmdq_handle);
-			plane_state->pending.config = false;
+			if (!cmdq_handle)
+				plane_state->pending.config = false;
 		}
-		mtk_crtc->pending_planes = false;
+
+		if (!cmdq_handle)
+			mtk_crtc->pending_planes = false;
 	}
 
 	if (mtk_crtc->pending_async_planes) {
@@ -420,9 +499,12 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				mtk_ddp_comp_layer_config(comp, local_layer,
 							  plane_state,
 							  cmdq_handle);
-			plane_state->pending.async_config = false;
+			if (!cmdq_handle)
+				plane_state->pending.async_config = false;
 		}
-		mtk_crtc->pending_async_planes = false;
+
+		if (!cmdq_handle)
+			mtk_crtc->pending_async_planes = false;
 	}
 }
 
@@ -430,7 +512,7 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 				       bool needs_vblank)
 {
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct cmdq_pkt *cmdq_handle;
+	struct cmdq_pkt *cmdq_handle = &mtk_crtc->cmdq_handle;
 #endif
 	struct drm_crtc *crtc = &mtk_crtc->base;
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
@@ -468,14 +550,24 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 		mtk_mutex_release(mtk_crtc->mutex);
 	}
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (mtk_crtc->cmdq_client) {
-		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
-		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
+	if (mtk_crtc->cmdq_chan) {
+		mbox_flush(mtk_crtc->cmdq_chan, 2000);
+		cmdq_handle->cmd_buf_size = 0;
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
 		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
 		cmdq_pkt_finalize(cmdq_handle);
-		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
+		dma_sync_single_for_device(mtk_crtc->cmdq_chan->mbox->dev,
+					    cmdq_handle->pa_base,
+					    cmdq_handle->cmd_buf_size,
+					    DMA_TO_DEVICE);
+		/*
+		 * CMDQ command should execute in next vblank,
+		 * If it fail to execute in next 2 vblank, timeout happen.
+		 */
+		mtk_crtc->cmdq_vblank_cnt = 2;
+		mbox_send_message(mtk_crtc->cmdq_chan, cmdq_handle);
+		mbox_client_txdone(mtk_crtc->cmdq_chan, 0);
 	}
 #endif
 	mtk_crtc->config_updating = false;
@@ -489,12 +581,15 @@ static void mtk_crtc_ddp_irq(void *data)
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_chan)
+		mtk_crtc_ddp_config(crtc, NULL);
+	else if (mtk_crtc->cmdq_vblank_cnt > 0 && --mtk_crtc->cmdq_vblank_cnt == 0)
+		DRM_ERROR("mtk_crtc %d CMDQ execute command timeout!\n",
+			  drm_crtc_index(&mtk_crtc->base));
 #else
 	if (!priv->data->shadow_register)
-#endif
 		mtk_crtc_ddp_config(crtc, NULL);
-
+#endif
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
 
@@ -752,14 +847,22 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	for (i = 0; i < path_len; i++) {
 		enum mtk_ddp_comp_id comp_id = path[i];
 		struct device_node *node;
+		struct mtk_ddp_comp *comp;
 
 		node = priv->comp_node[comp_id];
+		comp = &priv->ddp_comp[comp_id];
+
 		if (!node) {
 			dev_info(dev,
 				 "Not creating crtc %d because component %d is disabled or missing\n",
 				 pipe, comp_id);
 			return 0;
 		}
+
+		if (!comp->dev) {
+			dev_err(dev, "Component %pOF not initialized\n", node);
+			return -ENODEV;
+		}
 	}
 
 	mtk_crtc = devm_kzalloc(dev, sizeof(*mtk_crtc), GFP_KERNEL);
@@ -784,16 +887,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		enum mtk_ddp_comp_id comp_id = path[i];
 		struct mtk_ddp_comp *comp;
-		struct device_node *node;
 
-		node = priv->comp_node[comp_id];
 		comp = &priv->ddp_comp[comp_id];
-		if (!comp) {
-			dev_err(dev, "Component %pOF not initialized\n", node);
-			ret = -ENODEV;
-			return ret;
-		}
-
 		mtk_crtc->ddp_comp[i] = comp;
 
 		if (comp->funcs) {
@@ -829,16 +924,20 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	mutex_init(&mtk_crtc->hw_lock);
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	mtk_crtc->cmdq_client =
-			cmdq_mbox_create(mtk_crtc->mmsys_dev,
-					 drm_crtc_index(&mtk_crtc->base));
-	if (IS_ERR(mtk_crtc->cmdq_client)) {
+	mtk_crtc->cmdq_cl.dev = mtk_crtc->mmsys_dev;
+	mtk_crtc->cmdq_cl.tx_block = false;
+	mtk_crtc->cmdq_cl.knows_txdone = true;
+	mtk_crtc->cmdq_cl.rx_callback = ddp_cmdq_cb;
+	mtk_crtc->cmdq_chan =
+			mbox_request_channel(&mtk_crtc->cmdq_cl,
+					      drm_crtc_index(&mtk_crtc->base));
+	if (IS_ERR(mtk_crtc->cmdq_chan)) {
 		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
 			drm_crtc_index(&mtk_crtc->base));
-		mtk_crtc->cmdq_client = NULL;
+		mtk_crtc->cmdq_chan = NULL;
 	}
 
-	if (mtk_crtc->cmdq_client) {
+	if (mtk_crtc->cmdq_chan) {
 		ret = of_property_read_u32_index(priv->mutex_node,
 						 "mediatek,gce-events",
 						 drm_crtc_index(&mtk_crtc->base),
@@ -846,8 +945,18 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		if (ret) {
 			dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
 				drm_crtc_index(&mtk_crtc->base));
-			cmdq_mbox_destroy(mtk_crtc->cmdq_client);
-			mtk_crtc->cmdq_client = NULL;
+			mbox_free_channel(mtk_crtc->cmdq_chan);
+			mtk_crtc->cmdq_chan = NULL;
+		} else {
+			ret = mtk_drm_cmdq_pkt_create(mtk_crtc->cmdq_chan,
+						       &mtk_crtc->cmdq_handle,
+						       PAGE_SIZE);
+			if (ret) {
+				dev_dbg(dev, "mtk_crtc %d failed to create cmdq packet\n",
+					drm_crtc_index(&mtk_crtc->base));
+				mbox_free_channel(mtk_crtc->cmdq_chan);
+				mtk_crtc->cmdq_chan = NULL;
+			}
 		}
 	}
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 50d20562e612..99cbf44463e4 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -32,10 +32,6 @@
 
 #define DISP_REG_UFO_START			0x0000
 
-#define DISP_AAL_EN				0x0000
-#define DISP_AAL_SIZE				0x0030
-#define DISP_AAL_OUTPUT_SIZE			0x04d8
-
 #define DISP_DITHER_EN				0x0000
 #define DITHER_EN				BIT(0)
 #define DISP_DITHER_CFG				0x0020
@@ -49,8 +45,6 @@
 
 #define UFO_BYPASS				BIT(2)
 
-#define AAL_EN					BIT(0)
-
 #define DISP_DITHERING				BIT(2)
 #define DITHER_LSB_ERR_SHIFT_R(x)		(((x) & 0x7) << 28)
 #define DITHER_OVFLW_BIT_R(x)			(((x) & 0x7) << 24)
@@ -191,37 +185,6 @@ static void mtk_ufoe_start(struct device *dev)
 	writel(UFO_BYPASS, priv->regs + DISP_REG_UFO_START);
 }
 
-static void mtk_aal_config(struct device *dev, unsigned int w,
-			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
-{
-	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
-
-	mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_AAL_SIZE);
-	mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_AAL_OUTPUT_SIZE);
-}
-
-static void mtk_aal_gamma_set(struct device *dev, struct drm_crtc_state *state)
-{
-	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
-
-	mtk_gamma_set_common(priv->regs, state);
-}
-
-static void mtk_aal_start(struct device *dev)
-{
-	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
-
-	writel(AAL_EN, priv->regs + DISP_AAL_EN);
-}
-
-static void mtk_aal_stop(struct device *dev)
-{
-	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
-
-	writel_relaxed(0x0, priv->regs + DISP_AAL_EN);
-}
-
 static void mtk_dither_config(struct device *dev, unsigned int w,
 			      unsigned int h, unsigned int vrefresh,
 			      unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
@@ -249,8 +212,8 @@ static void mtk_dither_stop(struct device *dev)
 }
 
 static const struct mtk_ddp_comp_funcs ddp_aal = {
-	.clk_enable = mtk_ddp_clk_enable,
-	.clk_disable = mtk_ddp_clk_disable,
+	.clk_enable = mtk_aal_clk_enable,
+	.clk_disable = mtk_aal_clk_disable,
 	.gamma_set = mtk_aal_gamma_set,
 	.config = mtk_aal_config,
 	.start = mtk_aal_start,
@@ -507,7 +470,8 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp,
 			return ret;
 	}
 
-	if (type == MTK_DISP_BLS ||
+	if (type == MTK_DISP_AAL ||
+	    type == MTK_DISP_BLS ||
 	    type == MTK_DISP_CCORR ||
 	    type == MTK_DISP_COLOR ||
 	    type == MTK_DISP_GAMMA ||
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index b46bdb8985da..aec39724ebeb 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -110,6 +110,17 @@ static const enum mtk_ddp_comp_id mt2712_mtk_ddp_third[] = {
 	DDP_COMPONENT_PWM2,
 };
 
+static enum mtk_ddp_comp_id mt8167_mtk_ddp_main[] = {
+	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_COLOR0,
+	DDP_COMPONENT_CCORR,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_GAMMA,
+	DDP_COMPONENT_DITHER,
+	DDP_COMPONENT_RDMA0,
+	DDP_COMPONENT_DSI0,
+};
+
 static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
@@ -172,6 +183,11 @@ static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = {
 	.third_len = ARRAY_SIZE(mt2712_mtk_ddp_third),
 };
 
+static const struct mtk_mmsys_driver_data mt8167_mmsys_driver_data = {
+	.main_path = mt8167_mtk_ddp_main,
+	.main_len = ARRAY_SIZE(mt8167_mtk_ddp_main),
+};
+
 static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.main_path = mt8173_mtk_ddp_main,
 	.main_len = ARRAY_SIZE(mt8173_mtk_ddp_main),
@@ -270,12 +286,6 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 		goto err_component_unbind;
 	}
 
-	/*
-	 * We don't use the drm_irq_install() helpers provided by the DRM
-	 * core, so we need to set this manually in order to allow the
-	 * DRM_IOCTL_WAIT_VBLANK to operate correctly.
-	 */
-	drm->irq_enabled = true;
 	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret < 0)
 		goto err_component_unbind;
@@ -300,16 +310,7 @@ static void mtk_drm_kms_deinit(struct drm_device *drm)
 	component_unbind_all(drm->dev, drm);
 }
 
-static const struct file_operations mtk_drm_fops = {
-	.owner = THIS_MODULE,
-	.open = drm_open,
-	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
-	.mmap = mtk_drm_gem_mmap,
-	.poll = drm_poll,
-	.read = drm_read,
-	.compat_ioctl = drm_compat_ioctl,
-};
+DEFINE_DRM_GEM_FOPS(mtk_drm_fops);
 
 /*
  * We need to override this because the device used to import the memory is
@@ -332,7 +333,7 @@ static const struct drm_driver mtk_drm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import = mtk_drm_gem_prime_import,
 	.gem_prime_import_sg_table = mtk_gem_prime_import_sg_table,
-	.gem_prime_mmap = mtk_drm_gem_mmap_buf,
+	.gem_prime_mmap = drm_gem_prime_mmap,
 	.fops = &mtk_drm_fops,
 
 	.name = DRIVER_NAME,
@@ -398,6 +399,8 @@ static const struct component_master_ops mtk_drm_ops = {
 static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
 	{ .compatible = "mediatek,mt2701-disp-ovl",
 	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt8167-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
 	{ .compatible = "mediatek,mt8173-disp-ovl",
 	  .data = (void *)MTK_DISP_OVL },
 	{ .compatible = "mediatek,mt8183-disp-ovl",
@@ -406,30 +409,46 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
 	  .data = (void *)MTK_DISP_OVL_2L },
 	{ .compatible = "mediatek,mt2701-disp-rdma",
 	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8167-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
 	{ .compatible = "mediatek,mt8173-disp-rdma",
 	  .data = (void *)MTK_DISP_RDMA },
 	{ .compatible = "mediatek,mt8183-disp-rdma",
 	  .data = (void *)MTK_DISP_RDMA },
 	{ .compatible = "mediatek,mt8173-disp-wdma",
 	  .data = (void *)MTK_DISP_WDMA },
+	{ .compatible = "mediatek,mt8167-disp-ccorr",
+	  .data = (void *)MTK_DISP_CCORR },
 	{ .compatible = "mediatek,mt8183-disp-ccorr",
 	  .data = (void *)MTK_DISP_CCORR },
 	{ .compatible = "mediatek,mt2701-disp-color",
 	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8167-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
 	{ .compatible = "mediatek,mt8173-disp-color",
 	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8167-disp-aal",
+	  .data = (void *)MTK_DISP_AAL},
 	{ .compatible = "mediatek,mt8173-disp-aal",
 	  .data = (void *)MTK_DISP_AAL},
+	{ .compatible = "mediatek,mt8183-disp-aal",
+	  .data = (void *)MTK_DISP_AAL},
+	{ .compatible = "mediatek,mt8167-disp-gamma",
+	  .data = (void *)MTK_DISP_GAMMA, },
 	{ .compatible = "mediatek,mt8173-disp-gamma",
 	  .data = (void *)MTK_DISP_GAMMA, },
 	{ .compatible = "mediatek,mt8183-disp-gamma",
 	  .data = (void *)MTK_DISP_GAMMA, },
+	{ .compatible = "mediatek,mt8167-disp-dither",
+	  .data = (void *)MTK_DISP_DITHER },
 	{ .compatible = "mediatek,mt8183-disp-dither",
 	  .data = (void *)MTK_DISP_DITHER },
 	{ .compatible = "mediatek,mt8173-disp-ufoe",
 	  .data = (void *)MTK_DISP_UFOE },
 	{ .compatible = "mediatek,mt2701-dsi",
 	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8167-dsi",
+	  .data = (void *)MTK_DSI },
 	{ .compatible = "mediatek,mt8173-dsi",
 	  .data = (void *)MTK_DSI },
 	{ .compatible = "mediatek,mt8183-dsi",
@@ -444,12 +463,16 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
 	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt2712-disp-mutex",
 	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt8167-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt8173-disp-mutex",
 	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt8183-disp-mutex",
 	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt2701-disp-pwm",
 	  .data = (void *)MTK_DISP_BLS },
+	{ .compatible = "mediatek,mt8167-disp-pwm",
+	  .data = (void *)MTK_DISP_PWM },
 	{ .compatible = "mediatek,mt8173-disp-pwm",
 	  .data = (void *)MTK_DISP_PWM },
 	{ .compatible = "mediatek,mt8173-disp-od",
@@ -464,6 +487,8 @@ static const struct of_device_id mtk_drm_of_ids[] = {
 	  .data = &mt7623_mmsys_driver_data},
 	{ .compatible = "mediatek,mt2712-mmsys",
 	  .data = &mt2712_mmsys_driver_data},
+	{ .compatible = "mediatek,mt8167-mmsys",
+	  .data = &mt8167_mmsys_driver_data},
 	{ .compatible = "mediatek,mt8173-mmsys",
 	  .data = &mt8173_mmsys_driver_data},
 	{ .compatible = "mediatek,mt8183-mmsys",
@@ -532,11 +557,12 @@ static int mtk_drm_probe(struct platform_device *pdev)
 		private->comp_node[comp_id] = of_node_get(node);
 
 		/*
-		 * Currently only the CCORR, COLOR, GAMMA, OVL, RDMA, DSI, and DPI
+		 * Currently only the AAL, CCORR, COLOR, GAMMA, OVL, RDMA, DSI, and DPI
 		 * blocks have separate component platform drivers and initialize their own
 		 * DDP component structure. The others are initialized here.
 		 */
-		if (comp_type == MTK_DISP_CCORR ||
+		if (comp_type == MTK_DISP_AAL ||
+		    comp_type == MTK_DISP_CCORR ||
 		    comp_type == MTK_DISP_COLOR ||
 		    comp_type == MTK_DISP_GAMMA ||
 		    comp_type == MTK_DISP_OVL ||
@@ -636,6 +662,7 @@ static struct platform_driver mtk_drm_platform_driver = {
 };
 
 static struct platform_driver * const mtk_drm_drivers[] = {
+	&mtk_disp_aal_driver,
 	&mtk_disp_ccorr_driver,
 	&mtk_disp_color_driver,
 	&mtk_disp_gamma_driver,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index 637f5669e895..3e7d1e6fbe01 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -46,6 +46,7 @@ struct mtk_drm_private {
 	struct drm_atomic_state *suspend_state;
 };
 
+extern struct platform_driver mtk_disp_aal_driver;
 extern struct platform_driver mtk_disp_ccorr_driver;
 extern struct platform_driver mtk_disp_color_driver;
 extern struct platform_driver mtk_disp_gamma_driver;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
index 280ea0d5e840..d0544962cfc1 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
@@ -14,11 +14,14 @@
 #include "mtk_drm_drv.h"
 #include "mtk_drm_gem.h"
 
+static int mtk_drm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+
 static const struct drm_gem_object_funcs mtk_drm_gem_object_funcs = {
 	.free = mtk_drm_gem_free_object,
 	.get_sg_table = mtk_gem_prime_get_sg_table,
 	.vmap = mtk_drm_gem_prime_vmap,
 	.vunmap = mtk_drm_gem_prime_vunmap,
+	.mmap = mtk_drm_gem_object_mmap,
 	.vm_ops = &drm_gem_cma_vm_ops,
 };
 
@@ -146,10 +149,18 @@ static int mtk_drm_gem_object_mmap(struct drm_gem_object *obj,
 	struct mtk_drm_private *priv = obj->dev->dev_private;
 
 	/*
+	 * Set vm_pgoff (used as a fake buffer offset by DRM) to 0 and map the
+	 * whole buffer from the start.
+	 */
+	vma->vm_pgoff = 0;
+
+	/*
 	 * dma_alloc_attrs() allocated a struct page table for mtk_gem, so clear
 	 * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
 	 */
-	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
 
 	ret = dma_mmap_attrs(priv->dma_dev, vma, mtk_gem->cookie,
 			     mtk_gem->dma_addr, obj->size, mtk_gem->dma_attrs);
@@ -159,37 +170,6 @@ static int mtk_drm_gem_object_mmap(struct drm_gem_object *obj,
 	return ret;
 }
 
-int mtk_drm_gem_mmap_buf(struct drm_gem_object *obj, struct vm_area_struct *vma)
-{
-	int ret;
-
-	ret = drm_gem_mmap_obj(obj, obj->size, vma);
-	if (ret)
-		return ret;
-
-	return mtk_drm_gem_object_mmap(obj, vma);
-}
-
-int mtk_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	struct drm_gem_object *obj;
-	int ret;
-
-	ret = drm_gem_mmap(filp, vma);
-	if (ret)
-		return ret;
-
-	obj = vma->vm_private_data;
-
-	/*
-	 * Set vm_pgoff (used as a fake buffer offset by DRM) to 0 and map the
-	 * whole buffer from the start.
-	 */
-	vma->vm_pgoff = 0;
-
-	return mtk_drm_gem_object_mmap(obj, vma);
-}
-
 /*
  * Allocate a sg_table for this GEM object.
  * Note: Both the table's contents, and the sg_table itself must be freed by
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.h b/drivers/gpu/drm/mediatek/mtk_drm_gem.h
index 6da5ccb4b933..9a359a06cb73 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.h
@@ -39,9 +39,6 @@ struct mtk_drm_gem_obj *mtk_drm_gem_create(struct drm_device *dev, size_t size,
 					   bool alloc_kmap);
 int mtk_drm_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 			    struct drm_mode_create_dumb *args);
-int mtk_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-int mtk_drm_gem_mmap_buf(struct drm_gem_object *obj,
-			 struct vm_area_struct *vma);
 struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
 			struct dma_buf_attachment *attach, struct sg_table *sg);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index e6dcb34d3052..734a1fb052df 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -235,7 +235,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = mtk_plane_atomic_check,
 	.atomic_update = mtk_plane_atomic_update,
 	.atomic_disable = mtk_plane_atomic_disable,
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index ae403c67cbd9..93b40c245f00 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -404,7 +404,7 @@ static void mtk_dsi_rxtx_control(struct mtk_dsi *dsi)
 	if (dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)
 		tmp_reg |= HSTX_CKLP_EN;
 
-	if (!(dsi->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		tmp_reg |= DIS_EOT;
 
 	writel(tmp_reg, dsi->regs + DSI_TXRX_CTRL);
@@ -481,7 +481,7 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 			  timing->da_hs_zero + timing->da_hs_exit + 3;
 
 	delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12;
-	delta += dsi->mode_flags & MIPI_DSI_MODE_EOT_PACKET ? 2 : 0;
+	delta += dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET ? 2 : 0;
 
 	horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp;
 	horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte;
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index c1651a83700d..5838c44cbf6f 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1293,11 +1293,8 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge,
 	if (hdmi->next_bridge) {
 		ret = drm_bridge_attach(bridge->encoder, hdmi->next_bridge,
 					bridge, flags);
-		if (ret) {
-			dev_err(hdmi->dev,
-				"Failed to attach external bridge: %d\n", ret);
+		if (ret)
 			return ret;
-		}
 	}
 
 	mtk_cec_set_hpd_event(hdmi->cec_dev, mtk_hdmi_hpd_event, hdmi->dev);
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index a7388bf7c838..bc0d60df04ae 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -21,7 +21,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_modeset_helper_vtables.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -94,9 +93,6 @@ DEFINE_DRM_GEM_CMA_FOPS(fops);
 static const struct drm_driver meson_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
 
-	/* IRQ */
-	.irq_handler		= meson_irq,
-
 	/* CMA Ops */
 	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(meson_dumb_create),
 
@@ -285,7 +281,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	 * Remove early framebuffers (ie. simplefb). The framebuffer can be
 	 * located anywhere in RAM
 	 */
-	ret = drm_aperture_remove_framebuffers(false, "meson-drm-fb");
+	ret = drm_aperture_remove_framebuffers(false, &meson_driver);
 	if (ret)
 		goto free_drm;
 
@@ -335,7 +331,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	if (ret)
 		goto free_drm;
 
-	ret = drm_irq_install(drm, priv->vsync_irq);
+	ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm);
 	if (ret)
 		goto free_drm;
 
@@ -354,7 +350,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	return 0;
 
 uninstall_irq:
-	drm_irq_uninstall(drm);
+	free_irq(priv->vsync_irq, drm);
 free_drm:
 	drm_dev_put(drm);
 
@@ -382,7 +378,7 @@ static void meson_drv_unbind(struct device *dev)
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
-	drm_irq_uninstall(drm);
+	free_irq(priv->vsync_irq, drm);
 	drm_dev_put(drm);
 
 	if (priv->afbcd.ops) {
diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c
index ed063152aecd..dfef8afcc245 100644
--- a/drivers/gpu/drm/meson/meson_overlay.c
+++ b/drivers/gpu/drm/meson/meson_overlay.c
@@ -747,7 +747,6 @@ static const struct drm_plane_helper_funcs meson_overlay_helper_funcs = {
 	.atomic_check	= meson_overlay_atomic_check,
 	.atomic_disable	= meson_overlay_atomic_disable,
 	.atomic_update	= meson_overlay_atomic_update,
-	.prepare_fb	= drm_gem_plane_helper_prepare_fb,
 };
 
 static bool meson_overlay_format_mod_supported(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index a18510dae4c8..8640a8a8a469 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -422,7 +422,6 @@ static const struct drm_plane_helper_funcs meson_plane_helper_funcs = {
 	.atomic_check	= meson_plane_atomic_check,
 	.atomic_disable	= meson_plane_atomic_disable,
 	.atomic_update	= meson_plane_atomic_update,
-	.prepare_fb	= drm_gem_plane_helper_prepare_fb,
 };
 
 static bool meson_plane_format_mod_supported(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c
index 403efc1f1a7c..331c2f0da57a 100644
--- a/drivers/gpu/drm/mga/mga_dma.c
+++ b/drivers/gpu/drm/mga/mga_dma.c
@@ -949,7 +949,7 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup)
 	 * is freed, it's too late.
 	 */
 	if (dev->irq_enabled)
-		drm_irq_uninstall(dev);
+		drm_legacy_irq_uninstall(dev);
 
 	if (dev->dev_private) {
 		drm_mga_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index 84395d81ab9b..f61401c70b90 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -38,7 +38,6 @@
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_legacy.h>
 #include <drm/drm_print.h>
 #include <drm/drm_sarea.h>
diff --git a/drivers/gpu/drm/mgag200/Makefile b/drivers/gpu/drm/mgag200/Makefile
index 42fedef53882..d4f766522483 100644
--- a/drivers/gpu/drm/mgag200/Makefile
+++ b/drivers/gpu/drm/mgag200/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-mgag200-y   := mgag200_drv.o mgag200_i2c.o mgag200_mm.o mgag200_mode.o
+mgag200-y   := mgag200_drv.o mgag200_i2c.o mgag200_mm.o mgag200_mode.o mgag200_pll.o
 
 obj-$(CONFIG_DRM_MGAG200) += mgag200.o
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index a701d9563257..6b9243713b3c 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -262,17 +262,26 @@ static void mgag200_g200se_init_unique_id(struct mga_device *mdev)
 		mdev->model.g200se.unique_rev_id);
 }
 
-static int mgag200_device_init(struct mga_device *mdev, unsigned long flags)
+static struct mga_device *
+mgag200_device_create(struct pci_dev *pdev, enum mga_type type, unsigned long flags)
 {
-	struct drm_device *dev = &mdev->base;
+	struct mga_device *mdev;
+	struct drm_device *dev;
 	int ret;
 
-	mdev->flags = mgag200_flags_from_driver_data(flags);
-	mdev->type = mgag200_type_from_driver_data(flags);
+	mdev = devm_drm_dev_alloc(&pdev->dev, &mgag200_driver, struct mga_device, base);
+	if (IS_ERR(mdev))
+		return mdev;
+	dev = &mdev->base;
+
+	pci_set_drvdata(pdev, dev);
+
+	mdev->flags = flags;
+	mdev->type = type;
 
 	ret = mgag200_regs_init(mdev);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	if (mdev->type == G200_PCI || mdev->type == G200_AGP)
 		mgag200_g200_init_refclk(mdev);
@@ -281,33 +290,9 @@ static int mgag200_device_init(struct mga_device *mdev, unsigned long flags)
 
 	ret = mgag200_mm_init(mdev);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	ret = mgag200_modeset_init(mdev);
-	if (ret) {
-		drm_err(dev, "Fatal error during modeset init: %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static struct mga_device *
-mgag200_device_create(struct pci_dev *pdev, unsigned long flags)
-{
-	struct drm_device *dev;
-	struct mga_device *mdev;
-	int ret;
-
-	mdev = devm_drm_dev_alloc(&pdev->dev, &mgag200_driver,
-				  struct mga_device, base);
-	if (IS_ERR(mdev))
-		return mdev;
-	dev = &mdev->base;
-
-	pci_set_drvdata(pdev, dev);
-
-	ret = mgag200_device_init(mdev, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -335,14 +320,27 @@ static const struct pci_device_id mgag200_pciidlist[] = {
 
 MODULE_DEVICE_TABLE(pci, mgag200_pciidlist);
 
+static enum mga_type mgag200_type_from_driver_data(kernel_ulong_t driver_data)
+{
+	return (enum mga_type)(driver_data & MGAG200_TYPE_MASK);
+}
+
+static unsigned long mgag200_flags_from_driver_data(kernel_ulong_t driver_data)
+{
+	return driver_data & MGAG200_FLAG_MASK;
+}
+
 static int
 mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	kernel_ulong_t driver_data = ent->driver_data;
+	enum mga_type type = mgag200_type_from_driver_data(driver_data);
+	unsigned long flags = mgag200_flags_from_driver_data(driver_data);
 	struct mga_device *mdev;
 	struct drm_device *dev;
 	int ret;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "mgag200drmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &mgag200_driver);
 	if (ret)
 		return ret;
 
@@ -350,12 +348,12 @@ mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
-	mdev = mgag200_device_create(pdev, ent->driver_data);
+	mdev = mgag200_device_create(pdev, type, flags);
 	if (IS_ERR(mdev))
 		return PTR_ERR(mdev);
 	dev = &mdev->base;
 
-	ret = drm_dev_register(dev, ent->driver_data);
+	ret = drm_dev_register(dev, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 749a075fe9e4..196f74a0834e 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -43,6 +43,22 @@
 #define ATTR_INDEX 0x1fc0
 #define ATTR_DATA 0x1fc1
 
+#define WREG_MISC(v)						\
+	WREG8(MGA_MISC_OUT, v)
+
+#define RREG_MISC(v)						\
+	((v) = RREG8(MGA_MISC_IN))
+
+#define WREG_MISC_MASKED(v, mask)				\
+	do {							\
+		u8 misc_;					\
+		u8 mask_ = (mask);				\
+		RREG_MISC(misc_);				\
+		misc_ &= ~mask_;				\
+		misc_ |= ((v) & mask_);				\
+		WREG_MISC(misc_);				\
+	} while (0)
+
 #define WREG_ATTR(reg, v)					\
 	do {							\
 		RREG8(0x1fda);					\
@@ -110,6 +126,48 @@
 #define MGAG200_MAX_FB_HEIGHT 4096
 #define MGAG200_MAX_FB_WIDTH 4096
 
+struct mga_device;
+struct mgag200_pll;
+
+/*
+ * Stores parameters for programming the PLLs
+ *
+ * Fref: reference frequency (A: 25.175 Mhz, B: 28.361, C: XX Mhz)
+ * Fo: output frequency
+ * Fvco = Fref * (N / M)
+ * Fo = Fvco / P
+ *
+ * S = [0..3]
+ */
+struct mgag200_pll_values {
+	unsigned int m;
+	unsigned int n;
+	unsigned int p;
+	unsigned int s;
+};
+
+struct mgag200_pll_funcs {
+	int (*compute)(struct mgag200_pll *pll, long clock, struct mgag200_pll_values *pllc);
+	void (*update)(struct mgag200_pll *pll, const struct mgag200_pll_values *pllc);
+};
+
+struct mgag200_pll {
+	struct mga_device *mdev;
+
+	const struct mgag200_pll_funcs *funcs;
+};
+
+struct mgag200_crtc_state {
+	struct drm_crtc_state base;
+
+	struct mgag200_pll_values pixpllc;
+};
+
+static inline struct mgag200_crtc_state *to_mgag200_crtc_state(struct drm_crtc_state *base)
+{
+	return container_of(base, struct mgag200_crtc_state, base);
+}
+
 #define to_mga_connector(x) container_of(x, struct mga_connector, base)
 
 struct mga_i2c_chan {
@@ -166,8 +224,6 @@ struct mga_device {
 
 	enum mga_type			type;
 
-	int bpp_shifts[4];
-
 	int fb_mtrr;
 
 	union {
@@ -182,8 +238,8 @@ struct mga_device {
 		} g200se;
 	} model;
 
-
 	struct mga_connector connector;
+	struct mgag200_pll pixpll;
 	struct drm_simple_display_pipe display_pipe;
 };
 
@@ -192,18 +248,6 @@ static inline struct mga_device *to_mga_device(struct drm_device *dev)
 	return container_of(dev, struct mga_device, base);
 }
 
-static inline enum mga_type
-mgag200_type_from_driver_data(kernel_ulong_t driver_data)
-{
-	return (enum mga_type)(driver_data & MGAG200_TYPE_MASK);
-}
-
-static inline unsigned long
-mgag200_flags_from_driver_data(kernel_ulong_t driver_data)
-{
-	return driver_data & MGAG200_FLAG_MASK;
-}
-
 				/* mgag200_mode.c */
 int mgag200_modeset_init(struct mga_device *mdev);
 
@@ -214,4 +258,7 @@ void mgag200_i2c_destroy(struct mga_i2c_chan *i2c);
 				/* mgag200_mm.c */
 int mgag200_mm_init(struct mga_device *mdev);
 
+				/* mgag200_pll.c */
+int mgag200_pixpll_init(struct mgag200_pll *pixpll, struct mga_device *mdev);
+
 #endif				/* __MGAG200_DRV_H__ */
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 9d576240faed..fd98e8bbc550 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -110,712 +110,6 @@ static inline void mga_wait_busy(struct mga_device *mdev)
 	} while ((status & 0x01) && time_before(jiffies, timeout));
 }
 
-/*
- * PLL setup
- */
-
-static int mgag200_g200_set_plls(struct mga_device *mdev, long clock)
-{
-	struct drm_device *dev = &mdev->base;
-	const int post_div_max = 7;
-	const int in_div_min = 1;
-	const int in_div_max = 6;
-	const int feed_div_min = 7;
-	const int feed_div_max = 127;
-	u8 testm, testn;
-	u8 n = 0, m = 0, p, s;
-	long f_vco;
-	long computed;
-	long delta, tmp_delta;
-	long ref_clk = mdev->model.g200.ref_clk;
-	long p_clk_min = mdev->model.g200.pclk_min;
-	long p_clk_max =  mdev->model.g200.pclk_max;
-
-	if (clock > p_clk_max) {
-		drm_err(dev, "Pixel Clock %ld too high\n", clock);
-		return 1;
-	}
-
-	if (clock < p_clk_min >> 3)
-		clock = p_clk_min >> 3;
-
-	f_vco = clock;
-	for (p = 0;
-	     p <= post_div_max && f_vco < p_clk_min;
-	     p = (p << 1) + 1, f_vco <<= 1)
-		;
-
-	delta = clock;
-
-	for (testm = in_div_min; testm <= in_div_max; testm++) {
-		for (testn = feed_div_min; testn <= feed_div_max; testn++) {
-			computed = ref_clk * (testn + 1) / (testm + 1);
-			if (computed < f_vco)
-				tmp_delta = f_vco - computed;
-			else
-				tmp_delta = computed - f_vco;
-			if (tmp_delta < delta) {
-				delta = tmp_delta;
-				m = testm;
-				n = testn;
-			}
-		}
-	}
-	f_vco = ref_clk * (n + 1) / (m + 1);
-	if (f_vco < 100000)
-		s = 0;
-	else if (f_vco < 140000)
-		s = 1;
-	else if (f_vco < 180000)
-		s = 2;
-	else
-		s = 3;
-
-	drm_dbg_kms(dev, "clock: %ld vco: %ld m: %d n: %d p: %d s: %d\n",
-		    clock, f_vco, m, n, p, s);
-
-	WREG_DAC(MGA1064_PIX_PLLC_M, m);
-	WREG_DAC(MGA1064_PIX_PLLC_N, n);
-	WREG_DAC(MGA1064_PIX_PLLC_P, (p | (s << 3)));
-
-	return 0;
-}
-
-#define P_ARRAY_SIZE 9
-
-static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
-{
-	u32 unique_rev_id = mdev->model.g200se.unique_rev_id;
-	unsigned int vcomax, vcomin, pllreffreq;
-	unsigned int delta, tmpdelta, permitteddelta;
-	unsigned int testp, testm, testn;
-	unsigned int p, m, n;
-	unsigned int computed;
-	unsigned int pvalues_e4[P_ARRAY_SIZE] = {16, 14, 12, 10, 8, 6, 4, 2, 1};
-	unsigned int fvv;
-	unsigned int i;
-
-	if (unique_rev_id <= 0x03) {
-
-		m = n = p = 0;
-		vcomax = 320000;
-		vcomin = 160000;
-		pllreffreq = 25000;
-
-		delta = 0xffffffff;
-		permitteddelta = clock * 5 / 1000;
-
-		for (testp = 8; testp > 0; testp /= 2) {
-			if (clock * testp > vcomax)
-				continue;
-			if (clock * testp < vcomin)
-				continue;
-
-			for (testn = 17; testn < 256; testn++) {
-				for (testm = 1; testm < 32; testm++) {
-					computed = (pllreffreq * testn) /
-						(testm * testp);
-					if (computed > clock)
-						tmpdelta = computed - clock;
-					else
-						tmpdelta = clock - computed;
-					if (tmpdelta < delta) {
-						delta = tmpdelta;
-						m = testm - 1;
-						n = testn - 1;
-						p = testp - 1;
-					}
-				}
-			}
-		}
-	} else {
-
-
-		m = n = p = 0;
-		vcomax        = 1600000;
-		vcomin        = 800000;
-		pllreffreq    = 25000;
-
-		if (clock < 25000)
-			clock = 25000;
-
-		clock = clock * 2;
-
-		delta = 0xFFFFFFFF;
-		/* Permited delta is 0.5% as VESA Specification */
-		permitteddelta = clock * 5 / 1000;
-
-		for (i = 0 ; i < P_ARRAY_SIZE ; i++) {
-			testp = pvalues_e4[i];
-
-			if ((clock * testp) > vcomax)
-				continue;
-			if ((clock * testp) < vcomin)
-				continue;
-
-			for (testn = 50; testn <= 256; testn++) {
-				for (testm = 1; testm <= 32; testm++) {
-					computed = (pllreffreq * testn) /
-						(testm * testp);
-					if (computed > clock)
-						tmpdelta = computed - clock;
-					else
-						tmpdelta = clock - computed;
-
-					if (tmpdelta < delta) {
-						delta = tmpdelta;
-						m = testm - 1;
-						n = testn - 1;
-						p = testp - 1;
-					}
-				}
-			}
-		}
-
-		fvv = pllreffreq * (n + 1) / (m + 1);
-		fvv = (fvv - 800000) / 50000;
-
-		if (fvv > 15)
-			fvv = 15;
-
-		p |= (fvv << 4);
-		m |= 0x80;
-
-		clock = clock / 2;
-	}
-
-	if (delta > permitteddelta) {
-		pr_warn("PLL delta too large\n");
-		return 1;
-	}
-
-	WREG_DAC(MGA1064_PIX_PLLC_M, m);
-	WREG_DAC(MGA1064_PIX_PLLC_N, n);
-	WREG_DAC(MGA1064_PIX_PLLC_P, p);
-
-	if (unique_rev_id >= 0x04) {
-		WREG_DAC(0x1a, 0x09);
-		msleep(20);
-		WREG_DAC(0x1a, 0x01);
-
-	}
-
-	return 0;
-}
-
-static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
-{
-	unsigned int vcomax, vcomin, pllreffreq;
-	unsigned int delta, tmpdelta;
-	unsigned int testp, testm, testn, testp2;
-	unsigned int p, m, n;
-	unsigned int computed;
-	int i, j, tmpcount, vcount;
-	bool pll_locked = false;
-	u8 tmp;
-
-	m = n = p = 0;
-
-	delta = 0xffffffff;
-
-	if (mdev->type == G200_EW3) {
-
-		vcomax = 800000;
-		vcomin = 400000;
-		pllreffreq = 25000;
-
-		for (testp = 1; testp < 8; testp++) {
-			for (testp2 = 1; testp2 < 8; testp2++) {
-				if (testp < testp2)
-					continue;
-				if ((clock * testp * testp2) > vcomax)
-					continue;
-				if ((clock * testp * testp2) < vcomin)
-					continue;
-				for (testm = 1; testm < 26; testm++) {
-					for (testn = 32; testn < 2048 ; testn++) {
-						computed = (pllreffreq * testn) /
-							(testm * testp * testp2);
-						if (computed > clock)
-							tmpdelta = computed - clock;
-						else
-							tmpdelta = clock - computed;
-						if (tmpdelta < delta) {
-							delta = tmpdelta;
-							m = ((testn & 0x100) >> 1) |
-								(testm);
-							n = (testn & 0xFF);
-							p = ((testn & 0x600) >> 3) |
-								(testp2 << 3) |
-								(testp);
-						}
-					}
-				}
-			}
-		}
-	} else {
-
-		vcomax = 550000;
-		vcomin = 150000;
-		pllreffreq = 48000;
-
-		for (testp = 1; testp < 9; testp++) {
-			if (clock * testp > vcomax)
-				continue;
-			if (clock * testp < vcomin)
-				continue;
-
-			for (testm = 1; testm < 17; testm++) {
-				for (testn = 1; testn < 151; testn++) {
-					computed = (pllreffreq * testn) /
-						(testm * testp);
-					if (computed > clock)
-						tmpdelta = computed - clock;
-					else
-						tmpdelta = clock - computed;
-					if (tmpdelta < delta) {
-						delta = tmpdelta;
-						n = testn - 1;
-						m = (testm - 1) |
-							((n >> 1) & 0x80);
-						p = testp - 1;
-					}
-				}
-			}
-		}
-	}
-
-	for (i = 0; i <= 32 && pll_locked == false; i++) {
-		if (i > 0) {
-			WREG8(MGAREG_CRTC_INDEX, 0x1e);
-			tmp = RREG8(MGAREG_CRTC_DATA);
-			if (tmp < 0xff)
-				WREG8(MGAREG_CRTC_DATA, tmp+1);
-		}
-
-		/* set pixclkdis to 1 */
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG8(DAC_DATA, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= MGA1064_REMHEADCTL_CLKDIS;
-		WREG8(DAC_DATA, tmp);
-
-		/* select PLL Set C */
-		tmp = RREG8(MGAREG_MEM_MISC_READ);
-		tmp |= 0x3 << 2;
-		WREG8(MGAREG_MEM_MISC_WRITE, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN | 0x80;
-		WREG8(DAC_DATA, tmp);
-
-		udelay(500);
-
-		/* reset the PLL */
-		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~0x04;
-		WREG8(DAC_DATA, tmp);
-
-		udelay(50);
-
-		/* program pixel pll register */
-		WREG_DAC(MGA1064_WB_PIX_PLLC_N, n);
-		WREG_DAC(MGA1064_WB_PIX_PLLC_M, m);
-		WREG_DAC(MGA1064_WB_PIX_PLLC_P, p);
-
-		udelay(50);
-
-		/* turn pll on */
-		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= 0x04;
-		WREG_DAC(MGA1064_VREF_CTL, tmp);
-
-		udelay(500);
-
-		/* select the pixel pll */
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
-		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG8(DAC_DATA, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~MGA1064_REMHEADCTL_CLKSL_MSK;
-		tmp |= MGA1064_REMHEADCTL_CLKSL_PLL;
-		WREG8(DAC_DATA, tmp);
-
-		/* reset dotclock rate bit */
-		WREG8(MGAREG_SEQ_INDEX, 1);
-		tmp = RREG8(MGAREG_SEQ_DATA);
-		tmp &= ~0x8;
-		WREG8(MGAREG_SEQ_DATA, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG8(DAC_DATA, tmp);
-
-		vcount = RREG8(MGAREG_VCOUNT);
-
-		for (j = 0; j < 30 && pll_locked == false; j++) {
-			tmpcount = RREG8(MGAREG_VCOUNT);
-			if (tmpcount < vcount)
-				vcount = 0;
-			if ((tmpcount - vcount) > 2)
-				pll_locked = true;
-			else
-				udelay(5);
-		}
-	}
-	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
-	tmp = RREG8(DAC_DATA);
-	tmp &= ~MGA1064_REMHEADCTL_CLKDIS;
-	WREG_DAC(MGA1064_REMHEADCTL, tmp);
-	return 0;
-}
-
-static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
-{
-	unsigned int vcomax, vcomin, pllreffreq;
-	unsigned int delta, tmpdelta;
-	unsigned int testp, testm, testn;
-	unsigned int p, m, n;
-	unsigned int computed;
-	u8 tmp;
-
-	m = n = p = 0;
-	vcomax = 550000;
-	vcomin = 150000;
-	pllreffreq = 50000;
-
-	delta = 0xffffffff;
-
-	for (testp = 16; testp > 0; testp--) {
-		if (clock * testp > vcomax)
-			continue;
-		if (clock * testp < vcomin)
-			continue;
-
-		for (testn = 1; testn < 257; testn++) {
-			for (testm = 1; testm < 17; testm++) {
-				computed = (pllreffreq * testn) /
-					(testm * testp);
-				if (computed > clock)
-					tmpdelta = computed - clock;
-				else
-					tmpdelta = clock - computed;
-				if (tmpdelta < delta) {
-					delta = tmpdelta;
-					n = testn - 1;
-					m = testm - 1;
-					p = testp - 1;
-				}
-			}
-		}
-	}
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG8(DAC_DATA, tmp);
-
-	tmp = RREG8(MGAREG_MEM_MISC_READ);
-	tmp |= 0x3 << 2;
-	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
-	tmp = RREG8(DAC_DATA);
-	WREG8(DAC_DATA, tmp & ~0x40);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG8(DAC_DATA, tmp);
-
-	WREG_DAC(MGA1064_EV_PIX_PLLC_M, m);
-	WREG_DAC(MGA1064_EV_PIX_PLLC_N, n);
-	WREG_DAC(MGA1064_EV_PIX_PLLC_P, p);
-
-	udelay(50);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG8(DAC_DATA, tmp);
-
-	udelay(500);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
-	tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-	WREG8(DAC_DATA, tmp);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
-	tmp = RREG8(DAC_DATA);
-	WREG8(DAC_DATA, tmp | 0x40);
-
-	tmp = RREG8(MGAREG_MEM_MISC_READ);
-	tmp |= (0x3 << 2);
-	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG8(DAC_DATA, tmp);
-
-	return 0;
-}
-
-static int mga_g200eh_set_plls(struct mga_device *mdev, long clock)
-{
-	unsigned int vcomax, vcomin, pllreffreq;
-	unsigned int delta, tmpdelta;
-	unsigned int testp, testm, testn;
-	unsigned int p, m, n;
-	unsigned int computed;
-	int i, j, tmpcount, vcount;
-	u8 tmp;
-	bool pll_locked = false;
-
-	m = n = p = 0;
-
-	if (mdev->type == G200_EH3) {
-		vcomax = 3000000;
-		vcomin = 1500000;
-		pllreffreq = 25000;
-
-		delta = 0xffffffff;
-
-		testp = 0;
-
-		for (testm = 150; testm >= 6; testm--) {
-			if (clock * testm > vcomax)
-				continue;
-			if (clock * testm < vcomin)
-				continue;
-			for (testn = 120; testn >= 60; testn--) {
-				computed = (pllreffreq * testn) / testm;
-				if (computed > clock)
-					tmpdelta = computed - clock;
-				else
-					tmpdelta = clock - computed;
-				if (tmpdelta < delta) {
-					delta = tmpdelta;
-					n = testn;
-					m = testm;
-					p = testp;
-				}
-				if (delta == 0)
-					break;
-			}
-			if (delta == 0)
-				break;
-		}
-	} else {
-
-		vcomax = 800000;
-		vcomin = 400000;
-		pllreffreq = 33333;
-
-		delta = 0xffffffff;
-
-		for (testp = 16; testp > 0; testp >>= 1) {
-			if (clock * testp > vcomax)
-				continue;
-			if (clock * testp < vcomin)
-				continue;
-
-			for (testm = 1; testm < 33; testm++) {
-				for (testn = 17; testn < 257; testn++) {
-					computed = (pllreffreq * testn) /
-						(testm * testp);
-					if (computed > clock)
-						tmpdelta = computed - clock;
-					else
-						tmpdelta = clock - computed;
-					if (tmpdelta < delta) {
-						delta = tmpdelta;
-						n = testn - 1;
-						m = (testm - 1);
-						p = testp - 1;
-					}
-					if ((clock * testp) >= 600000)
-						p |= 0x80;
-				}
-			}
-		}
-	}
-	for (i = 0; i <= 32 && pll_locked == false; i++) {
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG8(DAC_DATA, tmp);
-
-		tmp = RREG8(MGAREG_MEM_MISC_READ);
-		tmp |= 0x3 << 2;
-		WREG8(MGAREG_MEM_MISC_WRITE, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG8(DAC_DATA, tmp);
-
-		udelay(500);
-
-		WREG_DAC(MGA1064_EH_PIX_PLLC_M, m);
-		WREG_DAC(MGA1064_EH_PIX_PLLC_N, n);
-		WREG_DAC(MGA1064_EH_PIX_PLLC_P, p);
-
-		udelay(500);
-
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
-		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG8(DAC_DATA, tmp);
-
-		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-		tmp = RREG8(DAC_DATA);
-		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG8(DAC_DATA, tmp);
-
-		vcount = RREG8(MGAREG_VCOUNT);
-
-		for (j = 0; j < 30 && pll_locked == false; j++) {
-			tmpcount = RREG8(MGAREG_VCOUNT);
-			if (tmpcount < vcount)
-				vcount = 0;
-			if ((tmpcount - vcount) > 2)
-				pll_locked = true;
-			else
-				udelay(5);
-		}
-	}
-
-	return 0;
-}
-
-static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
-{
-	static const unsigned int m_div_val[] = { 1, 2, 4, 8 };
-	unsigned int vcomax, vcomin, pllreffreq;
-	unsigned int delta, tmpdelta;
-	int testr, testn, testm, testo;
-	unsigned int p, m, n;
-	unsigned int computed, vco;
-	int tmp;
-
-	m = n = p = 0;
-	vcomax = 1488000;
-	vcomin = 1056000;
-	pllreffreq = 48000;
-
-	delta = 0xffffffff;
-
-	for (testr = 0; testr < 4; testr++) {
-		if (delta == 0)
-			break;
-		for (testn = 5; testn < 129; testn++) {
-			if (delta == 0)
-				break;
-			for (testm = 3; testm >= 0; testm--) {
-				if (delta == 0)
-					break;
-				for (testo = 5; testo < 33; testo++) {
-					vco = pllreffreq * (testn + 1) /
-						(testr + 1);
-					if (vco < vcomin)
-						continue;
-					if (vco > vcomax)
-						continue;
-					computed = vco / (m_div_val[testm] * (testo + 1));
-					if (computed > clock)
-						tmpdelta = computed - clock;
-					else
-						tmpdelta = clock - computed;
-					if (tmpdelta < delta) {
-						delta = tmpdelta;
-						m = testm | (testo << 3);
-						n = testn;
-						p = testr | (testr << 3);
-					}
-				}
-			}
-		}
-	}
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG8(DAC_DATA, tmp);
-
-	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
-	tmp = RREG8(DAC_DATA);
-	tmp |= MGA1064_REMHEADCTL_CLKDIS;
-	WREG8(DAC_DATA, tmp);
-
-	tmp = RREG8(MGAREG_MEM_MISC_READ);
-	tmp |= (0x3<<2) | 0xc0;
-	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
-
-	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
-	tmp = RREG8(DAC_DATA);
-	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG8(DAC_DATA, tmp);
-
-	udelay(500);
-
-	WREG_DAC(MGA1064_ER_PIX_PLLC_N, n);
-	WREG_DAC(MGA1064_ER_PIX_PLLC_M, m);
-	WREG_DAC(MGA1064_ER_PIX_PLLC_P, p);
-
-	udelay(50);
-
-	return 0;
-}
-
-static int mgag200_crtc_set_plls(struct mga_device *mdev, long clock)
-{
-	u8 misc;
-
-	switch(mdev->type) {
-	case G200_PCI:
-	case G200_AGP:
-		return mgag200_g200_set_plls(mdev, clock);
-	case G200_SE_A:
-	case G200_SE_B:
-		return mga_g200se_set_plls(mdev, clock);
-	case G200_WB:
-	case G200_EW3:
-		return mga_g200wb_set_plls(mdev, clock);
-	case G200_EV:
-		return mga_g200ev_set_plls(mdev, clock);
-	case G200_EH:
-	case G200_EH3:
-		return mga_g200eh_set_plls(mdev, clock);
-	case G200_ER:
-		return mga_g200er_set_plls(mdev, clock);
-	}
-
-	misc = RREG8(MGA_MISC_IN);
-	misc &= ~MGAREG_MISC_CLK_SEL_MASK;
-	misc |= MGAREG_MISC_CLK_SEL_MGA_MSK;
-	WREG8(MGA_MISC_OUT, misc);
-
-	return 0;
-}
-
 static void mgag200_g200wb_hold_bmc(struct mga_device *mdev)
 {
 	u8 tmp;
@@ -1137,10 +431,11 @@ static void mgag200_set_mode_regs(struct mga_device *mdev,
 	WREG8(MGA_MISC_OUT, misc);
 }
 
-static u8 mgag200_get_bpp_shift(struct mga_device *mdev,
-				const struct drm_format_info *format)
+static u8 mgag200_get_bpp_shift(const struct drm_format_info *format)
 {
-	return mdev->bpp_shifts[format->cpp[0] - 1];
+	static const u8 bpp_shift[] = {0, 1, 0, 2};
+
+	return bpp_shift[format->cpp[0] - 1];
 }
 
 /*
@@ -1152,7 +447,7 @@ static u32 mgag200_calculate_offset(struct mga_device *mdev,
 				    const struct drm_framebuffer *fb)
 {
 	u32 offset = fb->pitches[0] / fb->format->cpp[0];
-	u8 bppshift = mgag200_get_bpp_shift(mdev, fb->format);
+	u8 bppshift = mgag200_get_bpp_shift(fb->format);
 
 	if (fb->format->cpp[0] * 8 == 24)
 		offset = (offset * 3) >> (4 - bppshift);
@@ -1189,7 +484,7 @@ static void mgag200_set_format_regs(struct mga_device *mdev,
 
 	bpp = format->cpp[0] * 8;
 
-	bppshift = mgag200_get_bpp_shift(mdev, format);
+	bppshift = mgag200_get_bpp_shift(format);
 	switch (bpp) {
 	case 24:
 		scale = ((1 << bppshift) * 3) - 1;
@@ -1569,7 +864,9 @@ mgag200_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *dev = crtc->dev;
 	struct mga_device *mdev = to_mga_device(dev);
+	struct mgag200_pll *pixpll = &mdev->pixpll;
 	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
+	struct mgag200_crtc_state *mgag200_crtc_state = to_mgag200_crtc_state(crtc_state);
 	struct drm_framebuffer *fb = plane_state->fb;
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 	struct drm_rect fullscreen = {
@@ -1584,7 +881,8 @@ mgag200_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	mgag200_set_format_regs(mdev, fb);
 	mgag200_set_mode_regs(mdev, adjusted_mode);
-	mgag200_crtc_set_plls(mdev, adjusted_mode->clock);
+
+	pixpll->funcs->update(pixpll, &mgag200_crtc_state->pixpllc);
 
 	if (mdev->type == G200_ER)
 		mgag200_g200er_reset_tagfifo(mdev);
@@ -1600,7 +898,7 @@ mgag200_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
 	mga_crtc_load_lut(crtc);
 	mgag200_enable_display(mdev);
 
-	mgag200_handle_damage(mdev, fb, &fullscreen, &shadow_plane_state->map[0]);
+	mgag200_handle_damage(mdev, fb, &fullscreen, &shadow_plane_state->data[0]);
 }
 
 static void
@@ -1618,8 +916,13 @@ mgag200_simple_display_pipe_check(struct drm_simple_display_pipe *pipe,
 				  struct drm_crtc_state *crtc_state)
 {
 	struct drm_plane *plane = plane_state->plane;
+	struct drm_device *dev = plane->dev;
+	struct mga_device *mdev = to_mga_device(dev);
+	struct mgag200_pll *pixpll = &mdev->pixpll;
+	struct mgag200_crtc_state *mgag200_crtc_state = to_mgag200_crtc_state(crtc_state);
 	struct drm_framebuffer *new_fb = plane_state->fb;
 	struct drm_framebuffer *fb = NULL;
+	int ret;
 
 	if (!new_fb)
 		return 0;
@@ -1630,6 +933,13 @@ mgag200_simple_display_pipe_check(struct drm_simple_display_pipe *pipe,
 	if (!fb || (fb->format != new_fb->format))
 		crtc_state->mode_changed = true; /* update PLL settings */
 
+	if (crtc_state->mode_changed) {
+		ret = pixpll->funcs->compute(pixpll, crtc_state->mode.clock,
+					     &mgag200_crtc_state->pixpllc);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -1649,7 +959,54 @@ mgag200_simple_display_pipe_update(struct drm_simple_display_pipe *pipe,
 		return;
 
 	if (drm_atomic_helper_damage_merged(old_state, state, &damage))
-		mgag200_handle_damage(mdev, fb, &damage, &shadow_plane_state->map[0]);
+		mgag200_handle_damage(mdev, fb, &damage, &shadow_plane_state->data[0]);
+}
+
+static struct drm_crtc_state *
+mgag200_simple_display_pipe_duplicate_crtc_state(struct drm_simple_display_pipe *pipe)
+{
+	struct drm_crtc *crtc = &pipe->crtc;
+	struct drm_crtc_state *crtc_state = crtc->state;
+	struct mgag200_crtc_state *mgag200_crtc_state = to_mgag200_crtc_state(crtc_state);
+	struct mgag200_crtc_state *new_mgag200_crtc_state;
+
+	if (!crtc_state)
+		return NULL;
+
+	new_mgag200_crtc_state = kzalloc(sizeof(*new_mgag200_crtc_state), GFP_KERNEL);
+	if (!new_mgag200_crtc_state)
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &new_mgag200_crtc_state->base);
+
+	memcpy(&new_mgag200_crtc_state->pixpllc, &mgag200_crtc_state->pixpllc,
+	       sizeof(new_mgag200_crtc_state->pixpllc));
+
+	return &new_mgag200_crtc_state->base;
+}
+
+static void mgag200_simple_display_pipe_destroy_crtc_state(struct drm_simple_display_pipe *pipe,
+							   struct drm_crtc_state *crtc_state)
+{
+	struct mgag200_crtc_state *mgag200_crtc_state = to_mgag200_crtc_state(crtc_state);
+
+	__drm_atomic_helper_crtc_destroy_state(&mgag200_crtc_state->base);
+	kfree(mgag200_crtc_state);
+}
+
+static void mgag200_simple_display_pipe_reset_crtc(struct drm_simple_display_pipe *pipe)
+{
+	struct drm_crtc *crtc = &pipe->crtc;
+	struct mgag200_crtc_state *mgag200_crtc_state;
+
+	if (crtc->state) {
+		mgag200_simple_display_pipe_destroy_crtc_state(pipe, crtc->state);
+		crtc->state = NULL; /* must be set to NULL here */
+	}
+
+	mgag200_crtc_state = kzalloc(sizeof(*mgag200_crtc_state), GFP_KERNEL);
+	if (!mgag200_crtc_state)
+		return;
+	__drm_atomic_helper_crtc_reset(crtc, &mgag200_crtc_state->base);
 }
 
 static const struct drm_simple_display_pipe_funcs
@@ -1659,6 +1016,9 @@ mgag200_simple_display_pipe_funcs = {
 	.disable    = mgag200_simple_display_pipe_disable,
 	.check	    = mgag200_simple_display_pipe_check,
 	.update	    = mgag200_simple_display_pipe_update,
+	.reset_crtc = mgag200_simple_display_pipe_reset_crtc,
+	.duplicate_crtc_state = mgag200_simple_display_pipe_duplicate_crtc_state,
+	.destroy_crtc_state = mgag200_simple_display_pipe_destroy_crtc_state,
 	DRM_GEM_SIMPLE_DISPLAY_PIPE_SHADOW_PLANE_FUNCS,
 };
 
@@ -1699,11 +1059,6 @@ int mgag200_modeset_init(struct mga_device *mdev)
 	size_t format_count = ARRAY_SIZE(mgag200_simple_display_pipe_formats);
 	int ret;
 
-	mdev->bpp_shifts[0] = 0;
-	mdev->bpp_shifts[1] = 1;
-	mdev->bpp_shifts[2] = 0;
-	mdev->bpp_shifts[3] = 2;
-
 	mgag200_init_regs(mdev);
 
 	ret = drmm_mode_config_init(dev);
@@ -1730,6 +1085,10 @@ int mgag200_modeset_init(struct mga_device *mdev)
 		return ret;
 	}
 
+	ret = mgag200_pixpll_init(&mdev->pixpll, mdev);
+	if (ret)
+		return ret;
+
 	ret = drm_simple_display_pipe_init(dev, pipe,
 					   &mgag200_simple_display_pipe_funcs,
 					   mgag200_simple_display_pipe_formats,
diff --git a/drivers/gpu/drm/mgag200/mgag200_pll.c b/drivers/gpu/drm/mgag200/mgag200_pll.c
new file mode 100644
index 000000000000..7c903cf19c0d
--- /dev/null
+++ b/drivers/gpu/drm/mgag200/mgag200_pll.c
@@ -0,0 +1,992 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/delay.h>
+
+#include "mgag200_drv.h"
+
+/*
+ * G200
+ */
+
+static int mgag200_pixpll_compute_g200(struct mgag200_pll *pixpll, long clock,
+				       struct mgag200_pll_values *pixpllc)
+{
+	struct mga_device *mdev = pixpll->mdev;
+	struct drm_device *dev = &mdev->base;
+	const int post_div_max = 7;
+	const int in_div_min = 1;
+	const int in_div_max = 6;
+	const int feed_div_min = 7;
+	const int feed_div_max = 127;
+	u8 testp, testm, testn;
+	u8 n = 0, m = 0, p, s;
+	long f_vco;
+	long computed;
+	long delta, tmp_delta;
+	long ref_clk = mdev->model.g200.ref_clk;
+	long p_clk_min = mdev->model.g200.pclk_min;
+	long p_clk_max =  mdev->model.g200.pclk_max;
+
+	if (clock > p_clk_max) {
+		drm_err(dev, "Pixel Clock %ld too high\n", clock);
+		return -EINVAL;
+	}
+
+	if (clock < p_clk_min >> 3)
+		clock = p_clk_min >> 3;
+
+	f_vco = clock;
+	for (testp = 0;
+	     testp <= post_div_max && f_vco < p_clk_min;
+	     testp = (testp << 1) + 1, f_vco <<= 1)
+		;
+	p = testp + 1;
+
+	delta = clock;
+
+	for (testm = in_div_min; testm <= in_div_max; testm++) {
+		for (testn = feed_div_min; testn <= feed_div_max; testn++) {
+			computed = ref_clk * (testn + 1) / (testm + 1);
+			if (computed < f_vco)
+				tmp_delta = f_vco - computed;
+			else
+				tmp_delta = computed - f_vco;
+			if (tmp_delta < delta) {
+				delta = tmp_delta;
+				m = testm + 1;
+				n = testn + 1;
+			}
+		}
+	}
+	f_vco = ref_clk * n / m;
+	if (f_vco < 100000)
+		s = 0;
+	else if (f_vco < 140000)
+		s = 1;
+	else if (f_vco < 180000)
+		s = 2;
+	else
+		s = 3;
+
+	drm_dbg_kms(dev, "clock: %ld vco: %ld m: %d n: %d p: %d s: %d\n",
+		    clock, f_vco, m, n, p, s);
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void
+mgag200_pixpll_update_g200(struct mgag200_pll *pixpll, const struct mgag200_pll_values *pixpllc)
+{
+	struct mga_device *mdev = pixpll->mdev;
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = pixpllcm;
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	WREG_DAC(MGA1064_PIX_PLLC_M, xpixpllcm);
+	WREG_DAC(MGA1064_PIX_PLLC_N, xpixpllcn);
+	WREG_DAC(MGA1064_PIX_PLLC_P, xpixpllcp);
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200 = {
+	.compute = mgag200_pixpll_compute_g200,
+	.update = mgag200_pixpll_update_g200,
+};
+
+/*
+ * G200SE
+ */
+
+static int mgag200_pixpll_compute_g200se_00(struct mgag200_pll *pixpll, long clock,
+					    struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 320000;
+	static const unsigned int vcomin = 160000;
+	static const unsigned int pllreffreq = 25000;
+
+	unsigned int delta, tmpdelta, permitteddelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	permitteddelta = clock * 5 / 1000;
+
+	for (testp = 8; testp > 0; testp /= 2) {
+		if (clock * testp > vcomax)
+			continue;
+		if (clock * testp < vcomin)
+			continue;
+
+		for (testn = 17; testn < 256; testn++) {
+			for (testm = 1; testm < 32; testm++) {
+				computed = (pllreffreq * testn) / (testm * testp);
+				if (computed > clock)
+					tmpdelta = computed - clock;
+				else
+					tmpdelta = clock - computed;
+				if (tmpdelta < delta) {
+					delta = tmpdelta;
+					m = testm;
+					n = testn;
+					p = testp;
+				}
+			}
+		}
+	}
+
+	if (delta > permitteddelta) {
+		pr_warn("PLL delta too large\n");
+		return -EINVAL;
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void mgag200_pixpll_update_g200se_00(struct mgag200_pll *pixpll,
+					    const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp;
+	struct mga_device *mdev = pixpll->mdev;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = pixpllcm | ((pixpllcn & BIT(8)) >> 1);
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	WREG_DAC(MGA1064_PIX_PLLC_M, xpixpllcm);
+	WREG_DAC(MGA1064_PIX_PLLC_N, xpixpllcn);
+	WREG_DAC(MGA1064_PIX_PLLC_P, xpixpllcp);
+}
+
+static int mgag200_pixpll_compute_g200se_04(struct mgag200_pll *pixpll, long clock,
+					    struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 1600000;
+	static const unsigned int vcomin = 800000;
+	static const unsigned int pllreffreq = 25000;
+	static const unsigned int pvalues_e4[] = {16, 14, 12, 10, 8, 6, 4, 2, 1};
+
+	unsigned int delta, tmpdelta, permitteddelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+	unsigned int fvv;
+	unsigned int i;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	if (clock < 25000)
+		clock = 25000;
+	clock = clock * 2;
+
+	/* Permited delta is 0.5% as VESA Specification */
+	permitteddelta = clock * 5 / 1000;
+
+	for (i = 0 ; i < ARRAY_SIZE(pvalues_e4); i++) {
+		testp = pvalues_e4[i];
+
+		if ((clock * testp) > vcomax)
+			continue;
+		if ((clock * testp) < vcomin)
+			continue;
+
+		for (testn = 50; testn <= 256; testn++) {
+			for (testm = 1; testm <= 32; testm++) {
+				computed = (pllreffreq * testn) / (testm * testp);
+				if (computed > clock)
+					tmpdelta = computed - clock;
+				else
+					tmpdelta = clock - computed;
+
+				if (tmpdelta < delta) {
+					delta = tmpdelta;
+					m = testm;
+					n = testn;
+					p = testp;
+				}
+			}
+		}
+	}
+
+	fvv = pllreffreq * n / m;
+	fvv = (fvv - 800000) / 50000;
+	if (fvv > 15)
+		fvv = 15;
+	s = fvv << 1;
+
+	if (delta > permitteddelta) {
+		pr_warn("PLL delta too large\n");
+		return -EINVAL;
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void mgag200_pixpll_update_g200se_04(struct mgag200_pll *pixpll,
+					    const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp;
+	struct mga_device *mdev = pixpll->mdev;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = pixpllcm | ((pixpllcn & BIT(8)) >> 1);
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	WREG_DAC(MGA1064_PIX_PLLC_M, xpixpllcm);
+	WREG_DAC(MGA1064_PIX_PLLC_N, xpixpllcn);
+	WREG_DAC(MGA1064_PIX_PLLC_P, xpixpllcp);
+
+	WREG_DAC(0x1a, 0x09);
+	msleep(20);
+	WREG_DAC(0x1a, 0x01);
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200se_00 = {
+	.compute = mgag200_pixpll_compute_g200se_00,
+	.update = mgag200_pixpll_update_g200se_00,
+};
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200se_04 = {
+	.compute = mgag200_pixpll_compute_g200se_04,
+	.update = mgag200_pixpll_update_g200se_04,
+};
+
+/*
+ * G200WB
+ */
+
+static int mgag200_pixpll_compute_g200wb(struct mgag200_pll *pixpll, long clock,
+					 struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 550000;
+	static const unsigned int vcomin = 150000;
+	static const unsigned int pllreffreq = 48000;
+
+	unsigned int delta, tmpdelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	for (testp = 1; testp < 9; testp++) {
+		if (clock * testp > vcomax)
+			continue;
+		if (clock * testp < vcomin)
+			continue;
+
+		for (testm = 1; testm < 17; testm++) {
+			for (testn = 1; testn < 151; testn++) {
+				computed = (pllreffreq * testn) / (testm * testp);
+				if (computed > clock)
+					tmpdelta = computed - clock;
+				else
+					tmpdelta = clock - computed;
+				if (tmpdelta < delta) {
+					delta = tmpdelta;
+					n = testn;
+					m = testm;
+					p = testp;
+					s = 0;
+				}
+			}
+		}
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void
+mgag200_pixpll_update_g200wb(struct mgag200_pll *pixpll, const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp, tmp;
+	int i, j, tmpcount, vcount;
+	struct mga_device *mdev = pixpll->mdev;
+	bool pll_locked = false;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = ((pixpllcn & BIT(8)) >> 1) | pixpllcm;
+	xpixpllcn = pixpllcn;
+	xpixpllcp = ((pixpllcn & GENMASK(10, 9)) >> 3) | (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	for (i = 0; i <= 32 && pll_locked == false; i++) {
+		if (i > 0) {
+			WREG8(MGAREG_CRTC_INDEX, 0x1e);
+			tmp = RREG8(MGAREG_CRTC_DATA);
+			if (tmp < 0xff)
+				WREG8(MGAREG_CRTC_DATA, tmp+1);
+		}
+
+		/* set pixclkdis to 1 */
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
+		WREG8(DAC_DATA, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= MGA1064_REMHEADCTL_CLKDIS;
+		WREG8(DAC_DATA, tmp);
+
+		/* select PLL Set C */
+		tmp = RREG8(MGAREG_MEM_MISC_READ);
+		tmp |= 0x3 << 2;
+		WREG8(MGAREG_MEM_MISC_WRITE, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN | 0x80;
+		WREG8(DAC_DATA, tmp);
+
+		udelay(500);
+
+		/* reset the PLL */
+		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~0x04;
+		WREG8(DAC_DATA, tmp);
+
+		udelay(50);
+
+		/* program pixel pll register */
+		WREG_DAC(MGA1064_PIX_PLLC_N, xpixpllcn);
+		WREG_DAC(MGA1064_PIX_PLLC_M, xpixpllcm);
+		WREG_DAC(MGA1064_PIX_PLLC_P, xpixpllcp);
+
+		udelay(50);
+
+		/* turn pll on */
+		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= 0x04;
+		WREG_DAC(MGA1064_VREF_CTL, tmp);
+
+		udelay(500);
+
+		/* select the pixel pll */
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
+		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
+		WREG8(DAC_DATA, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~MGA1064_REMHEADCTL_CLKSL_MSK;
+		tmp |= MGA1064_REMHEADCTL_CLKSL_PLL;
+		WREG8(DAC_DATA, tmp);
+
+		/* reset dotclock rate bit */
+		WREG8(MGAREG_SEQ_INDEX, 1);
+		tmp = RREG8(MGAREG_SEQ_DATA);
+		tmp &= ~0x8;
+		WREG8(MGAREG_SEQ_DATA, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
+		WREG8(DAC_DATA, tmp);
+
+		vcount = RREG8(MGAREG_VCOUNT);
+
+		for (j = 0; j < 30 && pll_locked == false; j++) {
+			tmpcount = RREG8(MGAREG_VCOUNT);
+			if (tmpcount < vcount)
+				vcount = 0;
+			if ((tmpcount - vcount) > 2)
+				pll_locked = true;
+			else
+				udelay(5);
+		}
+	}
+
+	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
+	tmp = RREG8(DAC_DATA);
+	tmp &= ~MGA1064_REMHEADCTL_CLKDIS;
+	WREG_DAC(MGA1064_REMHEADCTL, tmp);
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200wb = {
+	.compute = mgag200_pixpll_compute_g200wb,
+	.update = mgag200_pixpll_update_g200wb,
+};
+
+/*
+ * G200EV
+ */
+
+static int mgag200_pixpll_compute_g200ev(struct mgag200_pll *pixpll, long clock,
+					 struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 550000;
+	static const unsigned int vcomin = 150000;
+	static const unsigned int pllreffreq = 50000;
+
+	unsigned int delta, tmpdelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	for (testp = 16; testp > 0; testp--) {
+		if (clock * testp > vcomax)
+			continue;
+		if (clock * testp < vcomin)
+			continue;
+
+		for (testn = 1; testn < 257; testn++) {
+			for (testm = 1; testm < 17; testm++) {
+				computed = (pllreffreq * testn) /
+					(testm * testp);
+				if (computed > clock)
+					tmpdelta = computed - clock;
+				else
+					tmpdelta = clock - computed;
+				if (tmpdelta < delta) {
+					delta = tmpdelta;
+					n = testn;
+					m = testm;
+					p = testp;
+				}
+			}
+		}
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void
+mgag200_pixpll_update_g200ev(struct mgag200_pll *pixpll, const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp, tmp;
+	struct mga_device *mdev = pixpll->mdev;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = pixpllcm;
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
+	WREG8(DAC_DATA, tmp);
+
+	tmp = RREG8(MGAREG_MEM_MISC_READ);
+	tmp |= 0x3 << 2;
+	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
+	tmp = RREG8(DAC_DATA);
+	WREG8(DAC_DATA, tmp & ~0x40);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
+	WREG8(DAC_DATA, tmp);
+
+	WREG_DAC(MGA1064_EV_PIX_PLLC_M, xpixpllcm);
+	WREG_DAC(MGA1064_EV_PIX_PLLC_N, xpixpllcn);
+	WREG_DAC(MGA1064_EV_PIX_PLLC_P, xpixpllcp);
+
+	udelay(50);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
+	WREG8(DAC_DATA, tmp);
+
+	udelay(500);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
+	tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
+	WREG8(DAC_DATA, tmp);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
+	tmp = RREG8(DAC_DATA);
+	WREG8(DAC_DATA, tmp | 0x40);
+
+	tmp = RREG8(MGAREG_MEM_MISC_READ);
+	tmp |= (0x3 << 2);
+	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
+	WREG8(DAC_DATA, tmp);
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200ev = {
+	.compute = mgag200_pixpll_compute_g200ev,
+	.update = mgag200_pixpll_update_g200ev,
+};
+
+/*
+ * G200EH
+ */
+
+static int mgag200_pixpll_compute_g200eh(struct mgag200_pll *pixpll, long clock,
+					 struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 800000;
+	static const unsigned int vcomin = 400000;
+	static const unsigned int pllreffreq = 33333;
+
+	unsigned int delta, tmpdelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	for (testp = 16; testp > 0; testp >>= 1) {
+		if (clock * testp > vcomax)
+			continue;
+		if (clock * testp < vcomin)
+			continue;
+
+		for (testm = 1; testm < 33; testm++) {
+			for (testn = 17; testn < 257; testn++) {
+				computed = (pllreffreq * testn) / (testm * testp);
+				if (computed > clock)
+					tmpdelta = computed - clock;
+				else
+					tmpdelta = clock - computed;
+				if (tmpdelta < delta) {
+					delta = tmpdelta;
+					n = testn;
+					m = testm;
+					p = testp;
+				}
+			}
+		}
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void
+mgag200_pixpll_update_g200eh(struct mgag200_pll *pixpll, const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp, tmp;
+	int i, j, tmpcount, vcount;
+	struct mga_device *mdev = pixpll->mdev;
+	bool pll_locked = false;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = ((pixpllcn & BIT(8)) >> 1) | pixpllcm;
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	for (i = 0; i <= 32 && pll_locked == false; i++) {
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
+		WREG8(DAC_DATA, tmp);
+
+		tmp = RREG8(MGAREG_MEM_MISC_READ);
+		tmp |= 0x3 << 2;
+		WREG8(MGAREG_MEM_MISC_WRITE, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
+		WREG8(DAC_DATA, tmp);
+
+		udelay(500);
+
+		WREG_DAC(MGA1064_EH_PIX_PLLC_M, xpixpllcm);
+		WREG_DAC(MGA1064_EH_PIX_PLLC_N, xpixpllcn);
+		WREG_DAC(MGA1064_EH_PIX_PLLC_P, xpixpllcp);
+
+		udelay(500);
+
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
+		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
+		WREG8(DAC_DATA, tmp);
+
+		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+		tmp = RREG8(DAC_DATA);
+		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
+		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
+		WREG8(DAC_DATA, tmp);
+
+		vcount = RREG8(MGAREG_VCOUNT);
+
+		for (j = 0; j < 30 && pll_locked == false; j++) {
+			tmpcount = RREG8(MGAREG_VCOUNT);
+			if (tmpcount < vcount)
+				vcount = 0;
+			if ((tmpcount - vcount) > 2)
+				pll_locked = true;
+			else
+				udelay(5);
+		}
+	}
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200eh = {
+	.compute = mgag200_pixpll_compute_g200eh,
+	.update = mgag200_pixpll_update_g200eh,
+};
+
+/*
+ * G200EH3
+ */
+
+static int mgag200_pixpll_compute_g200eh3(struct mgag200_pll *pixpll, long clock,
+					  struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 3000000;
+	static const unsigned int vcomin = 1500000;
+	static const unsigned int pllreffreq = 25000;
+
+	unsigned int delta, tmpdelta;
+	unsigned int testp, testm, testn;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+	testp = 0;
+
+	for (testm = 150; testm >= 6; testm--) {
+		if (clock * testm > vcomax)
+			continue;
+		if (clock * testm < vcomin)
+			continue;
+		for (testn = 120; testn >= 60; testn--) {
+			computed = (pllreffreq * testn) / testm;
+			if (computed > clock)
+				tmpdelta = computed - clock;
+			else
+				tmpdelta = clock - computed;
+			if (tmpdelta < delta) {
+				delta = tmpdelta;
+				n = testn + 1;
+				m = testm + 1;
+				p = testp + 1;
+			}
+			if (delta == 0)
+				break;
+		}
+		if (delta == 0)
+			break;
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200eh3 = {
+	.compute = mgag200_pixpll_compute_g200eh3,
+	.update = mgag200_pixpll_update_g200eh, // same as G200EH
+};
+
+/*
+ * G200ER
+ */
+
+static int mgag200_pixpll_compute_g200er(struct mgag200_pll *pixpll, long clock,
+					 struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 1488000;
+	static const unsigned int vcomin = 1056000;
+	static const unsigned int pllreffreq = 48000;
+	static const unsigned int m_div_val[] = { 1, 2, 4, 8 };
+
+	unsigned int delta, tmpdelta;
+	int testr, testn, testm, testo;
+	unsigned int p, m, n, s;
+	unsigned int computed, vco;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	for (testr = 0; testr < 4; testr++) {
+		if (delta == 0)
+			break;
+		for (testn = 5; testn < 129; testn++) {
+			if (delta == 0)
+				break;
+			for (testm = 3; testm >= 0; testm--) {
+				if (delta == 0)
+					break;
+				for (testo = 5; testo < 33; testo++) {
+					vco = pllreffreq * (testn + 1) /
+						(testr + 1);
+					if (vco < vcomin)
+						continue;
+					if (vco > vcomax)
+						continue;
+					computed = vco / (m_div_val[testm] * (testo + 1));
+					if (computed > clock)
+						tmpdelta = computed - clock;
+					else
+						tmpdelta = clock - computed;
+					if (tmpdelta < delta) {
+						delta = tmpdelta;
+						m = (testm | (testo << 3)) + 1;
+						n = testn + 1;
+						p = testr + 1;
+						s = testr;
+					}
+				}
+			}
+		}
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static void
+mgag200_pixpll_update_g200er(struct mgag200_pll *pixpll, const struct mgag200_pll_values *pixpllc)
+{
+	unsigned int pixpllcm, pixpllcn, pixpllcp, pixpllcs;
+	u8 xpixpllcm, xpixpllcn, xpixpllcp, tmp;
+	struct mga_device *mdev = pixpll->mdev;
+
+	pixpllcm = pixpllc->m - 1;
+	pixpllcn = pixpllc->n - 1;
+	pixpllcp = pixpllc->p - 1;
+	pixpllcs = pixpllc->s;
+
+	xpixpllcm = pixpllcm;
+	xpixpllcn = pixpllcn;
+	xpixpllcp = (pixpllcs << 3) | pixpllcp;
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
+	WREG8(DAC_DATA, tmp);
+
+	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
+	tmp = RREG8(DAC_DATA);
+	tmp |= MGA1064_REMHEADCTL_CLKDIS;
+	WREG8(DAC_DATA, tmp);
+
+	tmp = RREG8(MGAREG_MEM_MISC_READ);
+	tmp |= (0x3<<2) | 0xc0;
+	WREG8(MGAREG_MEM_MISC_WRITE, tmp);
+
+	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
+	tmp = RREG8(DAC_DATA);
+	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
+	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
+	WREG8(DAC_DATA, tmp);
+
+	udelay(500);
+
+	WREG_DAC(MGA1064_ER_PIX_PLLC_N, xpixpllcn);
+	WREG_DAC(MGA1064_ER_PIX_PLLC_M, xpixpllcm);
+	WREG_DAC(MGA1064_ER_PIX_PLLC_P, xpixpllcp);
+
+	udelay(50);
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200er = {
+	.compute = mgag200_pixpll_compute_g200er,
+	.update = mgag200_pixpll_update_g200er,
+};
+
+/*
+ * G200EW3
+ */
+
+static int mgag200_pixpll_compute_g200ew3(struct mgag200_pll *pixpll, long clock,
+					  struct mgag200_pll_values *pixpllc)
+{
+	static const unsigned int vcomax = 800000;
+	static const unsigned int vcomin = 400000;
+	static const unsigned int pllreffreq = 25000;
+
+	unsigned int delta, tmpdelta;
+	unsigned int testp, testm, testn, testp2;
+	unsigned int p, m, n, s;
+	unsigned int computed;
+
+	m = n = p = s = 0;
+	delta = 0xffffffff;
+
+	for (testp = 1; testp < 8; testp++) {
+		for (testp2 = 1; testp2 < 8; testp2++) {
+			if (testp < testp2)
+				continue;
+			if ((clock * testp * testp2) > vcomax)
+				continue;
+			if ((clock * testp * testp2) < vcomin)
+				continue;
+			for (testm = 1; testm < 26; testm++) {
+				for (testn = 32; testn < 2048 ; testn++) {
+					computed = (pllreffreq * testn) / (testm * testp * testp2);
+					if (computed > clock)
+						tmpdelta = computed - clock;
+					else
+						tmpdelta = clock - computed;
+					if (tmpdelta < delta) {
+						delta = tmpdelta;
+						m = testm + 1;
+						n = testn + 1;
+						p = testp + 1;
+						s = testp2;
+					}
+				}
+			}
+		}
+	}
+
+	pixpllc->m = m;
+	pixpllc->n = n;
+	pixpllc->p = p;
+	pixpllc->s = s;
+
+	return 0;
+}
+
+static const struct mgag200_pll_funcs mgag200_pixpll_funcs_g200ew3 = {
+	.compute = mgag200_pixpll_compute_g200ew3,
+	.update = mgag200_pixpll_update_g200wb, // same as G200WB
+};
+
+/*
+ * PLL initialization
+ */
+
+int mgag200_pixpll_init(struct mgag200_pll *pixpll, struct mga_device *mdev)
+{
+	struct drm_device *dev = &mdev->base;
+
+	pixpll->mdev = mdev;
+
+	switch (mdev->type) {
+	case G200_PCI:
+	case G200_AGP:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200;
+		break;
+	case G200_SE_A:
+	case G200_SE_B:
+		if (mdev->model.g200se.unique_rev_id >= 0x04)
+			pixpll->funcs = &mgag200_pixpll_funcs_g200se_04;
+		else
+			pixpll->funcs = &mgag200_pixpll_funcs_g200se_00;
+		break;
+	case G200_WB:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200wb;
+		break;
+	case G200_EV:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200ev;
+		break;
+	case G200_EH:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200eh;
+		break;
+	case G200_EH3:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200eh3;
+		break;
+	case G200_ER:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200er;
+		break;
+	case G200_EW3:
+		pixpll->funcs = &mgag200_pixpll_funcs_g200ew3;
+		break;
+	default:
+		drm_err(dev, "unknown device type %d\n", mdev->type);
+		return -ENODEV;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/mgag200/mgag200_reg.h b/drivers/gpu/drm/mgag200/mgag200_reg.h
index 977be0565c06..60e705283fe8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_reg.h
+++ b/drivers/gpu/drm/mgag200/mgag200_reg.h
@@ -222,11 +222,10 @@
 
 #define MGAREG_MISC_IOADSEL	(0x1 << 0)
 #define MGAREG_MISC_RAMMAPEN	(0x1 << 1)
-#define MGAREG_MISC_CLK_SEL_MASK	GENMASK(3, 2)
-#define MGAREG_MISC_CLK_SEL_VGA25	(0x0 << 2)
-#define MGAREG_MISC_CLK_SEL_VGA28	(0x1 << 2)
-#define MGAREG_MISC_CLK_SEL_MGA_PIX	(0x2 << 2)
-#define MGAREG_MISC_CLK_SEL_MGA_MSK	(0x3 << 2)
+#define MGAREG_MISC_CLKSEL_MASK		GENMASK(3, 2)
+#define MGAREG_MISC_CLKSEL_VGA25	(0x0 << 2)
+#define MGAREG_MISC_CLKSEL_VGA28	(0x1 << 2)
+#define MGAREG_MISC_CLKSEL_MGA		(0x3 << 2)
 #define MGAREG_MISC_VIDEO_DIS	(0x1 << 4)
 #define MGAREG_MISC_HIGH_PG_SEL	(0x1 << 5)
 #define MGAREG_MISC_HSYNCPOL		BIT(6)
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 52536e7adb95..e9c6af78b1d7 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -14,6 +14,7 @@ config DRM_MSM
 	select REGULATOR
 	select DRM_KMS_HELPER
 	select DRM_PANEL
+	select DRM_SCHED
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM if ARCH_QCOM
@@ -115,9 +116,9 @@ config DRM_MSM_DSI_10NM_PHY
 	  Choose this option if DSI PHY on SDM845 is used on the platform.
 
 config DRM_MSM_DSI_7NM_PHY
-	bool "Enable DSI 7nm PHY driver in MSM DRM (used by SM8150/SM8250)"
+	bool "Enable DSI 7nm PHY driver in MSM DRM"
 	depends on DRM_MSM_DSI
 	default y
 	help
-	  Choose this option if DSI PHY on SM8150/SM8250 is used on the
-	  platform.
+	  Choose this option if DSI PHY on SM8150/SM8250/SC7280 is used on
+	  the platform.
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 2c00aa70b708..904535eda0c4 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -90,6 +90,7 @@ msm-y := \
 	msm_gem_submit.o \
 	msm_gem_vma.o \
 	msm_gpu.o \
+	msm_gpu_devfreq.o \
 	msm_iommu.o \
 	msm_perf.o \
 	msm_rd.o \
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
index fc2c905b6c9e..c9d11d57aed6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
@@ -117,13 +117,13 @@ reset_set(void *data, u64 val)
 
 	if (a5xx_gpu->pm4_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pm4_bo);
+		drm_gem_object_put(a5xx_gpu->pm4_bo);
 		a5xx_gpu->pm4_bo = NULL;
 	}
 
 	if (a5xx_gpu->pfp_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pfp_bo);
+		drm_gem_object_put(a5xx_gpu->pfp_bo);
 		a5xx_gpu->pfp_bo = NULL;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 7a271de9a212..5e2750eb3810 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -18,6 +18,18 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+
+	if (a5xx_gpu->has_whereami) {
+		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
+		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
+		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
+	}
+}
+
 void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		bool sync)
 {
@@ -30,11 +42,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	 * Most flush operations need to issue a WHERE_AM_I opcode to sync up
 	 * the rptr shadow
 	 */
-	if (a5xx_gpu->has_whereami && sync) {
-		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
-		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
-		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
-	}
+	if (sync)
+		update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -168,6 +177,16 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	/*
@@ -1415,7 +1434,7 @@ struct a5xx_gpu_state {
 static int a5xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a5xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -1517,7 +1536,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 
 	if (a5xx_crashdumper_run(gpu, &dumper)) {
 		kfree(a5xx_state->hlsqregs);
-		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper.bo, gpu->aspace);
 		return;
 	}
 
@@ -1525,7 +1544,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
 		count * sizeof(u32));
 
-	msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+	msm_gem_kernel_put(dumper.bo, gpu->aspace);
 }
 
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index cdb165236a88..0e63a1429189 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -362,7 +362,7 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	 */
 	bosize = (cmds_size + (cmds_size / TYPE4_MAX_PAYLOAD) + 1) << 2;
 
-	ptr = msm_gem_kernel_new_locked(drm, bosize,
+	ptr = msm_gem_kernel_new(drm, bosize,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace,
 		&a5xx_gpu->gpmu_bo, &a5xx_gpu->gpmu_iova);
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index ee72510ff8ce..8abc9a2b114a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -240,7 +240,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 		A5XX_PREEMPT_COUNTER_SIZE,
 		MSM_BO_WC, gpu->aspace, &counters_bo, &counters_iova);
 	if (IS_ERR(counters)) {
-		msm_gem_kernel_put(bo, gpu->aspace, true);
+		msm_gem_kernel_put(bo, gpu->aspace);
 		return PTR_ERR(counters);
 	}
 
@@ -272,9 +272,8 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	int i;
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
-		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
-			gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], gpu->aspace);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index b349692219b7..a7c58018959f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -519,9 +519,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	if (!pdcptr)
 		goto err;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu))
 		pdc_in_aop = true;
-	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
 	else
 		pdc_address_offset = 0x30080;
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
+	clk_set_rate(gmu->hub_clk, 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -1129,12 +1130,12 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 
 static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu)
 {
-	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->log.obj, gmu->aspace, false);
+	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->log.obj, gmu->aspace);
 
 	gmu->aspace->mmu->funcs->detach(gmu->aspace->mmu);
 	msm_gem_address_space_put(gmu->aspace);
@@ -1393,6 +1394,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
 		gmu->nr_clocks, "gmu");
 
+	gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+		gmu->nr_clocks, "hub");
+
 	return 0;
 }
 
@@ -1504,7 +1508,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	 * are otherwise unused by a660.
 	 */
 	gmu->dummy.size = SZ_4K;
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000);
 		if (ret)
 			goto err_memory;
@@ -1522,7 +1526,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_16M - SZ_16K, 0x04000);
 		if (ret)
 			goto err_memory;
-	} else if (adreno_is_a640(adreno_gpu)) {
+	} else if (adreno_is_a640_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_256K - SZ_16K, 0x04000);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 71dfa60070cc..3c74f64e3126 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -66,6 +66,7 @@ struct a6xx_gmu {
 	int nr_clocks;
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
+	struct clk *hub_clk;
 
 	/* current performance index set externally */
 	int current_perf_index;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 9c5e4618aa0a..40c9fef457a4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -52,21 +52,25 @@ static bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return true;
 }
 
-static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	uint32_t wptr;
-	unsigned long flags;
 
 	/* Expanded APRIV doesn't need to issue the WHERE_AM_I opcode */
 	if (a6xx_gpu->has_whereami && !adreno_gpu->base.hw_apriv) {
-		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-
 		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
 		OUT_RING(ring, lower_32_bits(shadowptr(a6xx_gpu, ring)));
 		OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring)));
 	}
+}
+
+static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	uint32_t wptr;
+	unsigned long flags;
+
+	update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -145,7 +149,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct msm_ringbuffer *ring = submit->ring;
-	unsigned int i;
+	unsigned int i, ibs = 0;
 
 	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
 
@@ -181,8 +185,19 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -652,7 +667,7 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 		regs = a650_protect;
 		count = ARRAY_SIZE(a650_protect);
 		count_max = 48;
-	} else if (adreno_is_a660(adreno_gpu)) {
+	} else if (adreno_is_a660_family(adreno_gpu)) {
 		regs = a660_protect;
 		count = ARRAY_SIZE(a660_protect);
 		count_max = 48;
@@ -683,7 +698,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	if (adreno_is_a618(adreno_gpu))
 		return;
 
-	if (adreno_is_a640(adreno_gpu))
+	if (adreno_is_a640_family(adreno_gpu))
 		amsbc = 1;
 
 	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) {
@@ -694,6 +709,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		uavflagprd_inv = 2;
 	}
 
+	if (adreno_is_7c3(adreno_gpu)) {
+		lower_bit = 1;
+		amsbc = 1;
+		rgb565_predicator = 1;
+		uavflagprd_inv = 2;
+	}
+
 	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
 		rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
@@ -740,6 +762,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	const char *sqe_name = adreno_gpu->info->fw[ADRENO_FW_SQE];
 	u32 *buf = msm_gem_get_vaddr(obj);
 	bool ret = false;
 
@@ -756,8 +779,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	 *
 	 * a660 targets have all the critical security fixes from the start
 	 */
-	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
-		adreno_is_a640(adreno_gpu)) {
+	if (!strcmp(sqe_name, "a630_sqe.fw")) {
 		/*
 		 * If the lowest nibble is 0xa that is an indication that this
 		 * microcode has been patched. The actual version is in dword
@@ -778,7 +800,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		DRM_DEV_ERROR(&gpu->pdev->dev,
 			"a630 SQE ucode is too old. Have version %x need at least %x\n",
 			buf[0] & 0xfff, 0x190);
-	} else if (adreno_is_a650(adreno_gpu)) {
+	} else if (!strcmp(sqe_name, "a650_sqe.fw")) {
 		if ((buf[0] & 0xfff) >= 0x095) {
 			ret = true;
 			goto out;
@@ -787,7 +809,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		DRM_DEV_ERROR(&gpu->pdev->dev,
 			"a650 SQE ucode is too old. Have version %x need at least %x\n",
 			buf[0] & 0xfff, 0x095);
-	} else if (adreno_is_a660(adreno_gpu)) {
+	} else if (!strcmp(sqe_name, "a660_sqe.fw")) {
 		ret = true;
 	} else {
 		DRM_DEV_ERROR(&gpu->pdev->dev,
@@ -897,7 +919,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	a6xx_set_hwcg(gpu, true);
 
 	/* VBIF/GBIF start*/
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) {
+	if (adreno_is_a640_family(adreno_gpu) ||
+	    adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620);
@@ -935,13 +958,14 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
 	gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);
 
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu))
+	if (adreno_is_a640_family(adreno_gpu) ||
+	    adreno_is_a650_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
 	else
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0);
 	gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);
 
-	if (adreno_is_a660(adreno_gpu))
+	if (adreno_is_a660_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020);
 
 	/* Setting the mem pool size */
@@ -952,8 +976,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	*/
 	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
-	else if (adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a640_family(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -990,13 +1016,15 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Protect registers from the CP */
 	a6xx_set_cp_protect(gpu);
 
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
 		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
-		/* Set dualQ + disable afull for A660 GPU but not for A635 */
-		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
 	}
 
+	/* Set dualQ + disable afull for A660 GPU */
+	if (adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+
 	/* Enable expanded apriv for targets that support it */
 	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
@@ -1035,7 +1063,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 
 	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) {
 		if (!a6xx_gpu->shadow_bo) {
-			a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev,
+			a6xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
 				sizeof(u32) * gpu->nr_rings,
 				MSM_BO_WC | MSM_BO_MAP_PRIV,
 				gpu->aspace, &a6xx_gpu->shadow_bo,
@@ -1383,13 +1411,13 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	u32 cntl1_regval = 0;
+	u32 gpu_scid, cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
@@ -1409,26 +1437,34 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 		}
 	}
 
-	if (cntl1_regval) {
+	if (!cntl1_regval)
+		return;
+
+	/*
+	 * Program the slice IDs for the various GPU blocks and GPU MMU
+	 * pagetables
+	 */
+	if (!a6xx_gpu->have_mmu500) {
+		a6xx_llc_write(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
 		/*
-		 * Program the slice IDs for the various GPU blocks and GPU MMU
-		 * pagetables
+		 * Program cacheability overrides to not allocate cache
+		 * lines on a write miss
 		 */
-		if (a6xx_gpu->have_mmu500)
-			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0),
-				cntl1_regval);
-		else {
-			a6xx_llc_write(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
-
-			/*
-			 * Program cacheability overrides to not allocate cache
-			 * lines on a write miss
-			 */
-			a6xx_llc_rmw(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
-		}
+		a6xx_llc_rmw(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		return;
 	}
+
+	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
+
+	/* On A660, the SCID programming for UCHE traffic is done in
+	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+	 */
+	if (adreno_is_a660_family(adreno_gpu))
+		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
@@ -1477,7 +1513,7 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	msm_gpu_resume_devfreq(gpu);
+	msm_devfreq_resume(gpu);
 
 	a6xx_llc_activate(a6xx_gpu);
 
@@ -1494,7 +1530,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	a6xx_llc_deactivate(a6xx_gpu);
 
-	devfreq_suspend_device(gpu->devfreq.devfreq);
+	msm_devfreq_suspend(gpu);
 
 	ret = a6xx_gmu_stop(a6xx_gpu);
 	if (ret)
@@ -1667,11 +1703,11 @@ static u32 a618_get_speed_bin(u32 fuse)
 	return UINT_MAX;
 }
 
-static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
+static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse)
 {
 	u32 val = UINT_MAX;
 
-	if (revn == 618)
+	if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev))
 		val = a618_get_speed_bin(fuse);
 
 	if (val == UINT_MAX) {
@@ -1684,14 +1720,13 @@ static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
 	return (1 << val);
 }
 
-static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
-		u32 revn)
+static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev)
 {
 	u32 supp_hw = UINT_MAX;
-	u16 speedbin;
+	u32 speedbin;
 	int ret;
 
-	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+	ret = nvmem_cell_read_variable_le_u32(dev, "speed_bin", &speedbin);
 	/*
 	 * -ENOENT means that the platform doesn't support speedbin which is
 	 * fine
@@ -1704,9 +1739,8 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 			      ret);
 		goto done;
 	}
-	speedbin = le16_to_cpu(speedbin);
 
-	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
+	supp_hw = fuse_to_supp_hw(dev, rev, speedbin);
 
 done:
 	ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1);
@@ -1772,12 +1806,13 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	 */
 	info = adreno_info(config->rev);
 
-	if (info && (info->revn == 650 || info->revn == 660))
+	if (info && (info->revn == 650 || info->revn == 660 ||
+			adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev)))
 		adreno_gpu->base.hw_apriv = true;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);
 
-	ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
+	ret = a6xx_set_supported_hw(&pdev->dev, config->rev);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index ad4ea0ed5d99..e8f65cd8eca6 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -112,7 +112,7 @@ static void *state_kmemdup(struct a6xx_gpu_state *a6xx_state, void *src,
 static int a6xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a6xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -961,7 +961,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		a6xx_get_clusters(gpu, a6xx_state, dumper);
 		a6xx_get_dbgahb_clusters(gpu, a6xx_state, dumper);
 
-		msm_gem_kernel_put(dumper->bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper->bo, gpu->aspace);
 	}
 
 	if (snapshot_debugbus)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 919433732b43..d4c65bf0a1b7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/*
+	 * Send a single "off" entry just to get things running
+	 * TODO: bus scaling
+	 */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
+
+	msg->ddr_cmds_addrs[0] = 0x50004;
+	msg->ddr_cmds_addrs[1] = 0x50000;
+	msg->ddr_cmds_addrs[2] = 0x50088;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
+	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x5006c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -428,10 +458,12 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 
 	if (adreno_is_a618(adreno_gpu))
 		a618_build_bw_table(&msg);
-	else if (adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a640_family(adreno_gpu))
 		a640_build_bw_table(&msg);
 	else if (adreno_is_a650(adreno_gpu))
 		a650_build_bw_table(&msg);
+	else if (adreno_is_7c3(adreno_gpu))
+		adreno_7c3_build_bw_table(&msg);
 	else if (adreno_is_a660(adreno_gpu))
 		a660_build_bw_table(&msg);
 	else
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 6dad8015c9a1..2a6ce76656aa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -8,8 +8,6 @@
 
 #include "adreno_gpu.h"
 
-#define ANY_ID 0xff
-
 bool hang_debug = false;
 MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
 module_param_named(hang_debug, hang_debug, bool, 0600);
@@ -300,6 +298,30 @@ static const struct adreno_info gpulist[] = {
 		.init = a6xx_gpu_init,
 		.zapfw = "a660_zap.mdt",
 		.hwcg = a660_hwcg,
+	}, {
+		.rev = ADRENO_REV(6, 3, 5, ANY_ID),
+		.name = "Adreno 7c Gen 3",
+		.fw = {
+			[ADRENO_FW_SQE] = "a660_sqe.fw",
+			[ADRENO_FW_GMU] = "a660_gmu.bin",
+		},
+		.gmem = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.hwcg = a660_hwcg,
+	}, {
+		.rev = ADRENO_REV(6, 8, 0, ANY_ID),
+		.revn = 680,
+		.name = "A680",
+		.fw = {
+			[ADRENO_FW_SQE] = "a630_sqe.fw",
+			[ADRENO_FW_GMU] = "a640_gmu.bin",
+		},
+		.gmem = SZ_2M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.zapfw = "a640_zap.mdt",
+		.hwcg = a640_hwcg,
 	},
 };
 
@@ -325,6 +347,15 @@ static inline bool _rev_match(uint8_t entry, uint8_t id)
 	return (entry == ANY_ID) || (entry == id);
 }
 
+bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2)
+{
+
+	return _rev_match(rev1.core, rev2.core) &&
+		_rev_match(rev1.major, rev2.major) &&
+		_rev_match(rev1.minor, rev2.minor) &&
+		_rev_match(rev1.patchid, rev2.patchid);
+}
+
 const struct adreno_info *adreno_info(struct adreno_rev rev)
 {
 	int i;
@@ -332,10 +363,7 @@ const struct adreno_info *adreno_info(struct adreno_rev rev)
 	/* identify gpu: */
 	for (i = 0; i < ARRAY_SIZE(gpulist); i++) {
 		const struct adreno_info *info = &gpulist[i];
-		if (_rev_match(info->rev.core, rev.core) &&
-				_rev_match(info->rev.major, rev.major) &&
-				_rev_match(info->rev.minor, rev.minor) &&
-				_rev_match(info->rev.patchid, rev.patchid))
+		if (adreno_cmp_rev(info->rev, rev))
 			return info;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 9f5a30234b33..748665232d29 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -261,8 +261,8 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 			return ret;
 		}
 		return -EINVAL;
-	case MSM_PARAM_NR_RINGS:
-		*value = gpu->nr_rings;
+	case MSM_PARAM_PRIORITIES:
+		*value = gpu->nr_rings * NR_SCHED_PRIORITIES;
 		return 0;
 	case MSM_PARAM_PP_PGTABLE:
 		*value = 0;
@@ -390,7 +390,7 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
 	struct drm_gem_object *bo;
 	void *ptr;
 
-	ptr = msm_gem_kernel_new_locked(gpu->dev, fw->size - 4,
+	ptr = msm_gem_kernel_new(gpu->dev, fw->size - 4,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &bo, iova);
 
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 8dbe0d157520..225c277a6223 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -42,6 +42,8 @@ struct adreno_rev {
 	uint8_t  patchid;
 };
 
+#define ANY_ID 0xff
+
 #define ADRENO_REV(core, major, minor, patchid) \
 	((struct adreno_rev){ core, major, minor, patchid })
 
@@ -141,6 +143,8 @@ struct adreno_platform_config {
 	__ret;                                             \
 })
 
+bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2);
+
 static inline bool adreno_is_a2xx(struct adreno_gpu *gpu)
 {
 	return (gpu->revn < 300);
@@ -237,9 +241,9 @@ static inline int adreno_is_a630(struct adreno_gpu *gpu)
        return gpu->revn == 630;
 }
 
-static inline int adreno_is_a640(struct adreno_gpu *gpu)
+static inline int adreno_is_a640_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 640;
+	return (gpu->revn == 640) || (gpu->revn == 680);
 }
 
 static inline int adreno_is_a650(struct adreno_gpu *gpu)
@@ -247,15 +251,27 @@ static inline int adreno_is_a650(struct adreno_gpu *gpu)
        return gpu->revn == 650;
 }
 
+static inline int adreno_is_7c3(struct adreno_gpu *gpu)
+{
+	/* The order of args is important here to handle ANY_ID correctly */
+       return adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), gpu->rev);
+}
+
 static inline int adreno_is_a660(struct adreno_gpu *gpu)
 {
        return gpu->revn == 660;
 }
 
+static inline int adreno_is_a660_family(struct adreno_gpu *gpu)
+{
+       return adreno_is_a660(gpu) || adreno_is_7c3(gpu);
+}
+
 /* check for a650, a660, or any derivatives */
 static inline int adreno_is_a650_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660;
+       return gpu->revn == 650 || gpu->revn == 620 ||
+	       adreno_is_a660_family(gpu);
 }
 
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 9a5c70c87cc8..768012243b44 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -30,12 +30,6 @@
 #include "dpu_core_perf.h"
 #include "dpu_trace.h"
 
-#define DPU_DRM_BLEND_OP_NOT_DEFINED    0
-#define DPU_DRM_BLEND_OP_OPAQUE         1
-#define DPU_DRM_BLEND_OP_PREMULTIPLIED  2
-#define DPU_DRM_BLEND_OP_COVERAGE       3
-#define DPU_DRM_BLEND_OP_MAX            4
-
 /* layer mixer index on dpu_crtc */
 #define LEFT_MIXER 0
 #define RIGHT_MIXER 1
@@ -146,20 +140,43 @@ static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
 {
 	struct dpu_hw_mixer *lm = mixer->hw_lm;
 	uint32_t blend_op;
+	uint32_t fg_alpha, bg_alpha;
 
-	/* default to opaque blending */
-	blend_op = DPU_BLEND_FG_ALPHA_FG_CONST |
-		DPU_BLEND_BG_ALPHA_BG_CONST;
+	fg_alpha = pstate->base.alpha >> 8;
+	bg_alpha = 0xff - fg_alpha;
 
-	if (format->alpha_enable) {
+	/* default to opaque blending */
+	if (pstate->base.pixel_blend_mode == DRM_MODE_BLEND_PIXEL_NONE ||
+	    !format->alpha_enable) {
+		blend_op = DPU_BLEND_FG_ALPHA_FG_CONST |
+			DPU_BLEND_BG_ALPHA_BG_CONST;
+	} else if (pstate->base.pixel_blend_mode == DRM_MODE_BLEND_PREMULTI) {
+		blend_op = DPU_BLEND_FG_ALPHA_FG_CONST |
+			DPU_BLEND_BG_ALPHA_FG_PIXEL;
+		if (fg_alpha != 0xff) {
+			bg_alpha = fg_alpha;
+			blend_op |= DPU_BLEND_BG_MOD_ALPHA |
+				    DPU_BLEND_BG_INV_MOD_ALPHA;
+		} else {
+			blend_op |= DPU_BLEND_BG_INV_ALPHA;
+		}
+	} else {
 		/* coverage blending */
 		blend_op = DPU_BLEND_FG_ALPHA_FG_PIXEL |
-			DPU_BLEND_BG_ALPHA_FG_PIXEL |
-			DPU_BLEND_BG_INV_ALPHA;
+			DPU_BLEND_BG_ALPHA_FG_PIXEL;
+		if (fg_alpha != 0xff) {
+			bg_alpha = fg_alpha;
+			blend_op |= DPU_BLEND_FG_MOD_ALPHA |
+				    DPU_BLEND_FG_INV_MOD_ALPHA |
+				    DPU_BLEND_BG_MOD_ALPHA |
+				    DPU_BLEND_BG_INV_MOD_ALPHA;
+		} else {
+			blend_op |= DPU_BLEND_BG_INV_ALPHA;
+		}
 	}
 
 	lm->ops.setup_blend_config(lm, pstate->stage,
-				0xFF, 0, blend_op);
+				fg_alpha, bg_alpha, blend_op);
 
 	DRM_DEBUG_ATOMIC("format:%p4cc, alpha_en:%u blend_op:0x%x\n",
 		  &format->base.pixel_format, format->alpha_enable, blend_op);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 1c04b7cce43e..0e9d3fa1544b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -274,20 +274,20 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 
 	/* return EWOULDBLOCK since we know the wait isn't necessary */
 	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
-		DRM_ERROR("encoder is disabled id=%u, intr=%d, irq=%d",
+		DRM_ERROR("encoder is disabled id=%u, intr=%d, irq=%d\n",
 			  DRMID(phys_enc->parent), intr_idx,
 			  irq->irq_idx);
 		return -EWOULDBLOCK;
 	}
 
 	if (irq->irq_idx < 0) {
-		DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, irq=%s",
+		DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, irq=%s\n",
 			      DRMID(phys_enc->parent), intr_idx,
 			      irq->name);
 		return 0;
 	}
 
-	DRM_DEBUG_KMS("id=%u, intr=%d, irq=%d, pp=%d, pending_cnt=%d",
+	DRM_DEBUG_KMS("id=%u, intr=%d, irq=%d, pp=%d, pending_cnt=%d\n",
 		      DRMID(phys_enc->parent), intr_idx,
 		      irq->irq_idx, phys_enc->hw_pp->idx - PINGPONG_0,
 		      atomic_read(wait_info->atomic_cnt));
@@ -303,8 +303,7 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 		if (irq_status) {
 			unsigned long flags;
 
-			DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, "
-				      "irq=%d, pp=%d, atomic_cnt=%d",
+			DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, irq=%d, pp=%d, atomic_cnt=%d\n",
 				      DRMID(phys_enc->parent), intr_idx,
 				      irq->irq_idx,
 				      phys_enc->hw_pp->idx - PINGPONG_0,
@@ -315,8 +314,7 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 			ret = 0;
 		} else {
 			ret = -ETIMEDOUT;
-			DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, "
-				      "irq=%d, pp=%d, atomic_cnt=%d",
+			DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, irq=%d, pp=%d, atomic_cnt=%d\n",
 				      DRMID(phys_enc->parent), intr_idx,
 				      irq->irq_idx,
 				      phys_enc->hw_pp->idx - PINGPONG_0,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 704dace895cb..b131fd376192 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -974,6 +974,7 @@ static const struct dpu_perf_cfg sdm845_perf_data = {
 	.amortizable_threshold = 25,
 	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xf000, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sdm845_qos_linear),
 		.entries = sdm845_qos_linear
@@ -1001,6 +1002,7 @@ static const struct dpu_perf_cfg sc7180_perf_data = {
 	.min_dram_ib = 1600000,
 	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xff, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xff00, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
 		.entries = sc7180_qos_linear
@@ -1028,6 +1030,7 @@ static const struct dpu_perf_cfg sm8150_perf_data = {
 	.min_dram_ib = 800000,
 	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff8, 0xf000, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sm8150_qos_linear),
 		.entries = sm8150_qos_linear
@@ -1056,6 +1059,7 @@ static const struct dpu_perf_cfg sm8250_perf_data = {
 	.min_dram_ib = 800000,
 	.min_prefill_lines = 35,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xff00, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
 		.entries = sc7180_qos_linear
@@ -1084,6 +1088,7 @@ static const struct dpu_perf_cfg sc7280_perf_data = {
 	.min_dram_ib = 1600000,
 	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xffff, 0xffff, 0x0},
+	.safe_lut_tbl = {0xff00, 0xff00, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
 		.entries = sc7180_qos_macrotile
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index f8a74f6cdc4c..64740ddb983e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -345,10 +345,12 @@ static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
 	int i;
 
 	for (i = 0; i < ctx->mixer_count; i++) {
-		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+		enum dpu_lm mixer_id = ctx->mixer_hw_caps[i].id;
+
+		DPU_REG_WRITE(c, CTL_LAYER(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(mixer_id), 0);
 	}
 
 	DPU_REG_WRITE(c, CTL_FETCH_PIPE_ACTIVE, 0);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 4fd913522931..ae48f41821cf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -471,30 +471,68 @@ static int _dpu_kms_initialize_dsi(struct drm_device *dev,
 				    struct dpu_kms *dpu_kms)
 {
 	struct drm_encoder *encoder = NULL;
+	struct msm_display_info info;
 	int i, rc = 0;
 
 	if (!(priv->dsi[0] || priv->dsi[1]))
 		return rc;
 
-	/*TODO: Support two independent DSI connectors */
-	encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_DSI);
-	if (IS_ERR(encoder)) {
-		DPU_ERROR("encoder init failed for dsi display\n");
-		return PTR_ERR(encoder);
-	}
-
-	priv->encoders[priv->num_encoders++] = encoder;
-
+	/*
+	 * We support following confiurations:
+	 * - Single DSI host (dsi0 or dsi1)
+	 * - Two independent DSI hosts
+	 * - Bonded DSI0 and DSI1 hosts
+	 *
+	 * TODO: Support swapping DSI0 and DSI1 in the bonded setup.
+	 */
 	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		int other = (i + 1) % 2;
+
 		if (!priv->dsi[i])
 			continue;
 
+		if (msm_dsi_is_bonded_dsi(priv->dsi[i]) &&
+		    !msm_dsi_is_master_dsi(priv->dsi[i]))
+			continue;
+
+		encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_DSI);
+		if (IS_ERR(encoder)) {
+			DPU_ERROR("encoder init failed for dsi display\n");
+			return PTR_ERR(encoder);
+		}
+
+		priv->encoders[priv->num_encoders++] = encoder;
+
+		memset(&info, 0, sizeof(info));
+		info.intf_type = encoder->encoder_type;
+
 		rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder);
 		if (rc) {
 			DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
 				i, rc);
 			break;
 		}
+
+		info.h_tile_instance[info.num_of_h_tiles++] = i;
+		info.capabilities = msm_dsi_is_cmd_mode(priv->dsi[i]) ?
+			MSM_DISPLAY_CAP_CMD_MODE :
+			MSM_DISPLAY_CAP_VID_MODE;
+
+		if (msm_dsi_is_bonded_dsi(priv->dsi[i]) && priv->dsi[other]) {
+			rc = msm_dsi_modeset_init(priv->dsi[other], dev, encoder);
+			if (rc) {
+				DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+					other, rc);
+				break;
+			}
+
+			info.h_tile_instance[info.num_of_h_tiles++] = other;
+		}
+
+		rc = dpu_encoder_setup(dev, encoder, &info);
+		if (rc)
+			DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+				  encoder->base.id, rc);
 	}
 
 	return rc;
@@ -505,6 +543,7 @@ static int _dpu_kms_initialize_displayport(struct drm_device *dev,
 					    struct dpu_kms *dpu_kms)
 {
 	struct drm_encoder *encoder = NULL;
+	struct msm_display_info info;
 	int rc = 0;
 
 	if (!priv->dp)
@@ -516,6 +555,7 @@ static int _dpu_kms_initialize_displayport(struct drm_device *dev,
 		return PTR_ERR(encoder);
 	}
 
+	memset(&info, 0, sizeof(info));
 	rc = msm_dp_modeset_init(priv->dp, dev, encoder);
 	if (rc) {
 		DPU_ERROR("modeset_init failed for DP, rc = %d\n", rc);
@@ -524,6 +564,14 @@ static int _dpu_kms_initialize_displayport(struct drm_device *dev,
 	}
 
 	priv->encoders[priv->num_encoders++] = encoder;
+
+	info.num_of_h_tiles = 1;
+	info.capabilities = MSM_DISPLAY_CAP_VID_MODE;
+	info.intf_type = encoder->encoder_type;
+	rc = dpu_encoder_setup(dev, encoder, &info);
+	if (rc)
+		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+			  encoder->base.id, rc);
 	return rc;
 }
 
@@ -726,41 +774,6 @@ static void dpu_kms_destroy(struct msm_kms *kms)
 	msm_kms_destroy(&dpu_kms->base);
 }
 
-static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
-				 struct drm_encoder *encoder,
-				 bool cmd_mode)
-{
-	struct msm_display_info info;
-	struct msm_drm_private *priv = encoder->dev->dev_private;
-	int i, rc = 0;
-
-	memset(&info, 0, sizeof(info));
-
-	info.intf_type = encoder->encoder_type;
-	info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE :
-			MSM_DISPLAY_CAP_VID_MODE;
-
-	switch (info.intf_type) {
-	case DRM_MODE_ENCODER_DSI:
-		/* TODO: No support for DSI swap */
-		for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
-			if (priv->dsi[i]) {
-				info.h_tile_instance[info.num_of_h_tiles] = i;
-				info.num_of_h_tiles++;
-			}
-		}
-		break;
-	case DRM_MODE_ENCODER_TMDS:
-		info.num_of_h_tiles = 1;
-		break;
-	}
-
-	rc = dpu_encoder_setup(encoder->dev, encoder, &info);
-	if (rc)
-		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
-			encoder->base.id, rc);
-}
-
 static irqreturn_t dpu_irq(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
@@ -863,7 +876,6 @@ static const struct msm_kms_funcs kms_funcs = {
 	.get_format      = dpu_get_msm_format,
 	.round_pixclk    = dpu_kms_round_pixclk,
 	.destroy         = dpu_kms_destroy,
-	.set_encoder_mode = _dpu_kms_set_encoder_mode,
 	.snapshot        = dpu_kms_mdp_snapshot,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init    = dpu_kms_debugfs_init,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index ec4a6f04394a..c989621209aa 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1339,9 +1339,7 @@ static void dpu_plane_reset(struct drm_plane *plane)
 		return;
 	}
 
-	pstate->base.plane = plane;
-
-	plane->state = &pstate->base;
+	__drm_atomic_helper_plane_reset(plane, &pstate->base);
 }
 
 #ifdef CONFIG_DEBUG_FS
@@ -1647,6 +1645,12 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev,
 	if (ret)
 		DPU_ERROR("failed to install zpos property, rc = %d\n", ret);
 
+	drm_plane_create_alpha_property(plane);
+	drm_plane_create_blend_mode_property(plane,
+			BIT(DRM_MODE_BLEND_PIXEL_NONE) |
+			BIT(DRM_MODE_BLEND_PREMULTI) |
+			BIT(DRM_MODE_BLEND_COVERAGE));
+
 	drm_plane_create_rotation_property(plane,
 			DRM_MODE_ROTATE_0,
 			DRM_MODE_ROTATE_0 |
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 4a5b518288b0..cdcaf470f148 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -19,30 +19,12 @@ static int mdp4_hw_init(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
 	struct drm_device *dev = mdp4_kms->dev;
-	uint32_t version, major, minor, dmap_cfg, vg_cfg;
+	u32 dmap_cfg, vg_cfg;
 	unsigned long clk;
 	int ret = 0;
 
 	pm_runtime_get_sync(dev->dev);
 
-	mdp4_enable(mdp4_kms);
-	version = mdp4_read(mdp4_kms, REG_MDP4_VERSION);
-	mdp4_disable(mdp4_kms);
-
-	major = FIELD(version, MDP4_VERSION_MAJOR);
-	minor = FIELD(version, MDP4_VERSION_MINOR);
-
-	DBG("found MDP4 version v%d.%d", major, minor);
-
-	if (major != 4) {
-		DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n",
-				major, minor);
-		ret = -ENXIO;
-		goto out;
-	}
-
-	mdp4_kms->rev = minor;
-
 	if (mdp4_kms->rev > 1) {
 		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER0, 0x0707ffff);
 		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER1, 0x03073f3f);
@@ -88,7 +70,6 @@ static int mdp4_hw_init(struct msm_kms *kms)
 	if (mdp4_kms->rev > 1)
 		mdp4_write(mdp4_kms, REG_MDP4_RESET_STATUS, 1);
 
-out:
 	pm_runtime_put_sync(dev->dev);
 
 	return ret;
@@ -108,13 +89,6 @@ static void mdp4_disable_commit(struct msm_kms *kms)
 
 static void mdp4_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
-	int i;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *crtc_state;
-
-	/* see 119ecb7fd */
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
-		drm_crtc_vblank_get(crtc);
 }
 
 static void mdp4_flush_commit(struct msm_kms *kms, unsigned crtc_mask)
@@ -133,12 +107,6 @@ static void mdp4_wait_flush(struct msm_kms *kms, unsigned crtc_mask)
 
 static void mdp4_complete_commit(struct msm_kms *kms, unsigned crtc_mask)
 {
-	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
-	struct drm_crtc *crtc;
-
-	/* see 119ecb7fd */
-	for_each_crtc_mask(mdp4_kms->dev, crtc, crtc_mask)
-		drm_crtc_vblank_put(crtc);
 }
 
 static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
@@ -411,14 +379,32 @@ fail:
 	return ret;
 }
 
+static void read_mdp_hw_revision(struct mdp4_kms *mdp4_kms,
+				 u32 *major, u32 *minor)
+{
+	struct drm_device *dev = mdp4_kms->dev;
+	u32 version;
+
+	mdp4_enable(mdp4_kms);
+	version = mdp4_read(mdp4_kms, REG_MDP4_VERSION);
+	mdp4_disable(mdp4_kms);
+
+	*major = FIELD(version, MDP4_VERSION_MAJOR);
+	*minor = FIELD(version, MDP4_VERSION_MINOR);
+
+	DRM_DEV_INFO(dev->dev, "MDP4 version v%d.%d", *major, *minor);
+}
+
 struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct mdp4_platform_config *config = mdp4_get_config(pdev);
+	struct msm_drm_private *priv = dev->dev_private;
 	struct mdp4_kms *mdp4_kms;
 	struct msm_kms *kms = NULL;
 	struct msm_gem_address_space *aspace;
 	int irq, ret;
+	u32 major, minor;
 
 	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
 	if (!mdp4_kms) {
@@ -433,7 +419,8 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	kms = &mdp4_kms->base.base;
+	priv->kms = &mdp4_kms->base.base;
+	kms = priv->kms;
 
 	mdp4_kms->dev = dev;
 
@@ -479,15 +466,6 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	if (IS_ERR(mdp4_kms->pclk))
 		mdp4_kms->pclk = NULL;
 
-	if (mdp4_kms->rev >= 2) {
-		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
-		if (IS_ERR(mdp4_kms->lut_clk)) {
-			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
-			ret = PTR_ERR(mdp4_kms->lut_clk);
-			goto fail;
-		}
-	}
-
 	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
 	if (IS_ERR(mdp4_kms->axi_clk)) {
 		DRM_DEV_ERROR(dev->dev, "failed to get axi_clk\n");
@@ -496,8 +474,27 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	}
 
 	clk_set_rate(mdp4_kms->clk, config->max_clk);
-	if (mdp4_kms->lut_clk)
+
+	read_mdp_hw_revision(mdp4_kms, &major, &minor);
+
+	if (major != 4) {
+		DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n",
+			      major, minor);
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	mdp4_kms->rev = minor;
+
+	if (mdp4_kms->rev >= 2) {
+		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
+		if (IS_ERR(mdp4_kms->lut_clk)) {
+			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
+			ret = PTR_ERR(mdp4_kms->lut_clk);
+			goto fail;
+		}
 		clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
+	}
 
 	pm_runtime_enable(dev->dev);
 	mdp4_kms->rpm_enabled = true;
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
index 81b0c7cf954e..1220f2b20e05 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
@@ -737,7 +737,7 @@ struct mdp5_ctl_manager *mdp5_ctlm_init(struct drm_device *dev,
 	}
 
 	/*
-	 * In Dual DSI case, CTL0 and CTL1 are always assigned to two DSI
+	 * In bonded DSI case, CTL0 and CTL1 are always assigned to two DSI
 	 * interfaces to support single FLUSH feature (Flush CTL0 and CTL1 when
 	 * only write into CTL0's FLUSH register) to keep two DSI pipes in sync.
 	 * Single FLUSH is supported from hw rev v3.0.
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 15aed45022bc..b3b42672b2d4 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -209,13 +209,6 @@ static int mdp5_set_split_display(struct msm_kms *kms,
 							  slave_encoder);
 }
 
-static void mdp5_set_encoder_mode(struct msm_kms *kms,
-				  struct drm_encoder *encoder,
-				  bool cmd_mode)
-{
-	mdp5_encoder_set_intf_mode(encoder, cmd_mode);
-}
-
 static void mdp5_kms_destroy(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
@@ -287,7 +280,6 @@ static const struct mdp_kms_funcs kms_funcs = {
 		.get_format      = mdp_get_format,
 		.round_pixclk    = mdp5_round_pixclk,
 		.set_split_display = mdp5_set_split_display,
-		.set_encoder_mode = mdp5_set_encoder_mode,
 		.destroy         = mdp5_kms_destroy,
 #ifdef CONFIG_DEBUG_FS
 		.debugfs_init    = mdp5_kms_debugfs_init,
@@ -448,6 +440,9 @@ static int modeset_init_intf(struct mdp5_kms *mdp5_kms,
 		}
 
 		ret = msm_dsi_modeset_init(priv->dsi[dsi_id], dev, encoder);
+		if (!ret)
+			mdp5_encoder_set_intf_mode(encoder, msm_dsi_is_cmd_mode(priv->dsi[dsi_id]));
+
 		break;
 	}
 	default:
diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
index c92a9508c8d3..c22b07f68670 100644
--- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
+++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/ktime.h>
-#include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/dma-buf.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index 4a3293b590b0..eb40d8413bca 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -353,6 +353,9 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 			if (!(aux->retry_cnt % MAX_AUX_RETRIES))
 				dp_catalog_aux_update_cfg(aux->catalog);
 		}
+		/* reset aux if link is in connected state */
+		if (dp_catalog_link_is_connected(aux->catalog))
+			dp_catalog_aux_reset(aux->catalog);
 	} else {
 		aux->retry_cnt = 0;
 		switch (aux->aux_error_num) {
diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c
index c0423e76eed7..cc2bb8295329 100644
--- a/drivers/gpu/drm/msm/dp/dp_catalog.c
+++ b/drivers/gpu/drm/msm/dp/dp_catalog.c
@@ -372,6 +372,7 @@ void dp_catalog_ctrl_mainlink_ctrl(struct dp_catalog *dp_catalog,
 	struct dp_catalog_private *catalog = container_of(dp_catalog,
 				struct dp_catalog_private, dp_catalog);
 
+	DRM_DEBUG_DP("enable=%d\n", enable);
 	if (enable) {
 		/*
 		 * To make sure link reg writes happens before other operation,
@@ -580,6 +581,7 @@ void dp_catalog_hpd_config_intr(struct dp_catalog *dp_catalog,
 
 	config = (en ? config | intr_mask : config & ~intr_mask);
 
+	DRM_DEBUG_DP("intr_mask=%#x config=%#x\n", intr_mask, config);
 	dp_write_aux(catalog, REG_DP_DP_HPD_INT_MASK,
 				config & DP_DP_HPD_INT_MASK);
 }
@@ -610,6 +612,7 @@ u32 dp_catalog_link_is_connected(struct dp_catalog *dp_catalog)
 	u32 status;
 
 	status = dp_read_aux(catalog, REG_DP_DP_HPD_INT_STATUS);
+	DRM_DEBUG_DP("aux status: %#x\n", status);
 	status >>= DP_DP_HPD_STATE_STATUS_BITS_SHIFT;
 	status &= DP_DP_HPD_STATE_STATUS_BITS_MASK;
 
@@ -685,6 +688,7 @@ void dp_catalog_ctrl_send_phy_pattern(struct dp_catalog *dp_catalog,
 	/* Make sure to clear the current pattern before starting a new one */
 	dp_write_link(catalog, REG_DP_STATE_CTRL, 0x0);
 
+	DRM_DEBUG_DP("pattern: %#x\n", pattern);
 	switch (pattern) {
 	case DP_PHY_TEST_PATTERN_D10_2:
 		dp_write_link(catalog, REG_DP_STATE_CTRL,
@@ -745,7 +749,7 @@ void dp_catalog_ctrl_send_phy_pattern(struct dp_catalog *dp_catalog,
 				DP_STATE_CTRL_LINK_TRAINING_PATTERN4);
 		break;
 	default:
-		DRM_DEBUG_DP("No valid test pattern requested:0x%x\n", pattern);
+		DRM_DEBUG_DP("No valid test pattern requested: %#x\n", pattern);
 		break;
 	}
 }
@@ -929,7 +933,7 @@ void dp_catalog_audio_config_acr(struct dp_catalog *dp_catalog)
 	select = dp_catalog->audio_data;
 	acr_ctrl = select << 4 | BIT(31) | BIT(8) | BIT(14);
 
-	DRM_DEBUG_DP("select = 0x%x, acr_ctrl = 0x%x\n", select, acr_ctrl);
+	DRM_DEBUG_DP("select: %#x, acr_ctrl: %#x\n", select, acr_ctrl);
 
 	dp_write_link(catalog, MMSS_DP_AUDIO_ACR_CTRL, acr_ctrl);
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index eaddfd739885..62e75dc8afc6 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -81,13 +81,6 @@ struct dp_ctrl_private {
 	struct completion video_comp;
 };
 
-struct dp_cr_status {
-	u8 lane_0_1;
-	u8 lane_2_3;
-};
-
-#define DP_LANE0_1_CR_DONE	0x11
-
 static int dp_aux_link_configure(struct drm_dp_aux *aux,
 					struct dp_link_info *link)
 {
@@ -120,7 +113,7 @@ void dp_ctrl_push_idle(struct dp_ctrl *dp_ctrl)
 			IDLE_PATTERN_COMPLETION_TIMEOUT_JIFFIES))
 		pr_warn("PUSH_IDLE pattern timedout\n");
 
-	pr_debug("mainlink off done\n");
+	DRM_DEBUG_DP("mainlink off done\n");
 }
 
 static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
@@ -1011,6 +1004,8 @@ static int dp_ctrl_update_vx_px(struct dp_ctrl_private *ctrl)
 	u32 voltage_swing_level = link->phy_params.v_level;
 	u32 pre_emphasis_level = link->phy_params.p_level;
 
+	DRM_DEBUG_DP("voltage level: %d emphasis level: %d\n", voltage_swing_level,
+			pre_emphasis_level);
 	ret = dp_catalog_ctrl_update_vx_px(ctrl->catalog,
 		voltage_swing_level, pre_emphasis_level);
 
@@ -1078,7 +1073,7 @@ static int dp_ctrl_read_link_status(struct dp_ctrl_private *ctrl,
 }
 
 static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl,
-		struct dp_cr_status *cr, int *training_step)
+			int *training_step)
 {
 	int tries, old_v_level, ret = 0;
 	u8 link_status[DP_LINK_STATUS_SIZE];
@@ -1107,9 +1102,6 @@ static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl,
 		if (ret)
 			return ret;
 
-		cr->lane_0_1 = link_status[0];
-		cr->lane_2_3 = link_status[1];
-
 		if (drm_dp_clock_recovery_ok(link_status,
 			ctrl->link->link_params.num_lanes)) {
 			return 0;
@@ -1186,7 +1178,7 @@ static void dp_ctrl_clear_training_pattern(struct dp_ctrl_private *ctrl)
 }
 
 static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
-		struct dp_cr_status *cr, int *training_step)
+			int *training_step)
 {
 	int tries = 0, ret = 0;
 	char pattern;
@@ -1202,10 +1194,6 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
 	else
 		pattern = DP_TRAINING_PATTERN_2;
 
-	ret = dp_ctrl_update_vx_px(ctrl);
-	if (ret)
-		return ret;
-
 	ret = dp_catalog_ctrl_set_pattern(ctrl->catalog, pattern);
 	if (ret)
 		return ret;
@@ -1218,8 +1206,6 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
 		ret = dp_ctrl_read_link_status(ctrl, link_status);
 		if (ret)
 			return ret;
-		cr->lane_0_1 = link_status[0];
-		cr->lane_2_3 = link_status[1];
 
 		if (drm_dp_channel_eq_ok(link_status,
 			ctrl->link->link_params.num_lanes)) {
@@ -1239,7 +1225,7 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
 static int dp_ctrl_reinitialize_mainlink(struct dp_ctrl_private *ctrl);
 
 static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
-		struct dp_cr_status *cr, int *training_step)
+			int *training_step)
 {
 	int ret = 0;
 	u8 encoding = DP_SET_ANSI_8B10B;
@@ -1255,7 +1241,7 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
 	drm_dp_dpcd_write(ctrl->aux, DP_MAIN_LINK_CHANNEL_CODING_SET,
 				&encoding, 1);
 
-	ret = dp_ctrl_link_train_1(ctrl, cr, training_step);
+	ret = dp_ctrl_link_train_1(ctrl, training_step);
 	if (ret) {
 		DRM_ERROR("link training #1 failed. ret=%d\n", ret);
 		goto end;
@@ -1264,7 +1250,7 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
 	/* print success info as this is a result of user initiated action */
 	DRM_DEBUG_DP("link training #1 successful\n");
 
-	ret = dp_ctrl_link_train_2(ctrl, cr, training_step);
+	ret = dp_ctrl_link_train_2(ctrl, training_step);
 	if (ret) {
 		DRM_ERROR("link training #2 failed. ret=%d\n", ret);
 		goto end;
@@ -1280,7 +1266,7 @@ end:
 }
 
 static int dp_ctrl_setup_main_link(struct dp_ctrl_private *ctrl,
-		struct dp_cr_status *cr, int *training_step)
+			int *training_step)
 {
 	int ret = 0;
 
@@ -1295,7 +1281,7 @@ static int dp_ctrl_setup_main_link(struct dp_ctrl_private *ctrl,
 	 * a link training pattern, we have to first do soft reset.
 	 */
 
-	ret = dp_ctrl_link_train(ctrl, cr, training_step);
+	ret = dp_ctrl_link_train(ctrl, training_step);
 
 	return ret;
 }
@@ -1382,6 +1368,7 @@ int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset)
 	if (reset)
 		dp_catalog_ctrl_reset(ctrl->catalog);
 
+	DRM_DEBUG_DP("flip=%d\n", flip);
 	dp_catalog_ctrl_phy_reset(ctrl->catalog);
 	phy_init(phy);
 	dp_catalog_ctrl_enable_irq(ctrl->catalog, true);
@@ -1492,14 +1479,16 @@ static int dp_ctrl_deinitialize_mainlink(struct dp_ctrl_private *ctrl)
 static int dp_ctrl_link_maintenance(struct dp_ctrl_private *ctrl)
 {
 	int ret = 0;
-	struct dp_cr_status cr;
 	int training_step = DP_TRAINING_NONE;
 
 	dp_ctrl_push_idle(&ctrl->dp_ctrl);
 
+	ctrl->link->phy_params.p_level = 0;
+	ctrl->link->phy_params.v_level = 0;
+
 	ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock;
 
-	ret = dp_ctrl_setup_main_link(ctrl, &cr, &training_step);
+	ret = dp_ctrl_setup_main_link(ctrl, &training_step);
 	if (ret)
 		goto end;
 
@@ -1630,6 +1619,35 @@ void dp_ctrl_handle_sink_request(struct dp_ctrl *dp_ctrl)
 	}
 }
 
+static bool dp_ctrl_clock_recovery_any_ok(
+			const u8 link_status[DP_LINK_STATUS_SIZE],
+			int lane_count)
+{
+	int reduced_cnt;
+
+	if (lane_count <= 1)
+		return false;
+
+	/*
+	 * only interested in the lane number after reduced
+	 * lane_count = 4, then only interested in 2 lanes
+	 * lane_count = 2, then only interested in 1 lane
+	 */
+	reduced_cnt = lane_count >> 1;
+
+	return drm_dp_clock_recovery_ok(link_status, reduced_cnt);
+}
+
+static bool dp_ctrl_channel_eq_ok(struct dp_ctrl_private *ctrl)
+{
+	u8 link_status[DP_LINK_STATUS_SIZE];
+	int num_lanes = ctrl->link->link_params.num_lanes;
+
+	dp_ctrl_read_link_status(ctrl, link_status);
+
+	return drm_dp_channel_eq_ok(link_status, num_lanes);
+}
+
 int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 {
 	int rc = 0;
@@ -1637,7 +1655,7 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 	u32 rate = 0;
 	int link_train_max_retries = 5;
 	u32 const phy_cts_pixel_clk_khz = 148500;
-	struct dp_cr_status cr;
+	u8 link_status[DP_LINK_STATUS_SIZE];
 	unsigned int training_step;
 
 	if (!dp_ctrl)
@@ -1664,6 +1682,9 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 		ctrl->link->link_params.rate,
 		ctrl->link->link_params.num_lanes, ctrl->dp_ctrl.pixel_rate);
 
+	ctrl->link->phy_params.p_level = 0;
+	ctrl->link->phy_params.v_level = 0;
+
 	rc = dp_ctrl_enable_mainlink_clocks(ctrl);
 	if (rc)
 		return rc;
@@ -1677,19 +1698,21 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 		}
 
 		training_step = DP_TRAINING_NONE;
-		rc = dp_ctrl_setup_main_link(ctrl, &cr, &training_step);
+		rc = dp_ctrl_setup_main_link(ctrl, &training_step);
 		if (rc == 0) {
 			/* training completed successfully */
 			break;
 		} else if (training_step == DP_TRAINING_1) {
 			/* link train_1 failed */
-			if (!dp_catalog_link_is_connected(ctrl->catalog)) {
+			if (!dp_catalog_link_is_connected(ctrl->catalog))
 				break;
-			}
+
+			dp_ctrl_read_link_status(ctrl, link_status);
 
 			rc = dp_ctrl_link_rate_down_shift(ctrl);
 			if (rc < 0) { /* already in RBR = 1.6G */
-				if (cr.lane_0_1 & DP_LANE0_1_CR_DONE) {
+				if (dp_ctrl_clock_recovery_any_ok(link_status,
+					ctrl->link->link_params.num_lanes)) {
 					/*
 					 * some lanes are ready,
 					 * reduce lane number
@@ -1705,12 +1728,18 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 				}
 			}
 		} else if (training_step == DP_TRAINING_2) {
-			/* link train_2 failed, lower lane rate */
-			if (!dp_catalog_link_is_connected(ctrl->catalog)) {
+			/* link train_2 failed */
+			if (!dp_catalog_link_is_connected(ctrl->catalog))
 				break;
-			}
 
-			rc = dp_ctrl_link_lane_down_shift(ctrl);
+			dp_ctrl_read_link_status(ctrl, link_status);
+
+			if (!drm_dp_clock_recovery_ok(link_status,
+					ctrl->link->link_params.num_lanes))
+				rc = dp_ctrl_link_rate_down_shift(ctrl);
+			else
+				rc = dp_ctrl_link_lane_down_shift(ctrl);
+
 			if (rc < 0) {
 				/* end with failure */
 				break; /* lane == 1 already */
@@ -1721,17 +1750,19 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 	if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN)
 		return rc;
 
-	/* stop txing train pattern */
-	dp_ctrl_clear_training_pattern(ctrl);
+	if (rc == 0) {  /* link train successfully */
+		/*
+		 * do not stop train pattern here
+		 * stop link training at on_stream
+		 * to pass compliance test
+		 */
+	} else  {
+		/*
+		 * link training failed
+		 * end txing train pattern here
+		 */
+		dp_ctrl_clear_training_pattern(ctrl);
 
-	/*
-	 * keep transmitting idle pattern until video ready
-	 * to avoid main link from loss of sync
-	 */
-	if (rc == 0)  /* link train successfully */
-		dp_ctrl_push_idle(dp_ctrl);
-	else  {
-		/* link training failed */
 		dp_ctrl_deinitialize_mainlink(ctrl);
 		rc = -ECONNRESET;
 	}
@@ -1739,9 +1770,15 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl)
 	return rc;
 }
 
+static int dp_ctrl_link_retrain(struct dp_ctrl_private *ctrl)
+{
+	int training_step = DP_TRAINING_NONE;
+
+	return dp_ctrl_setup_main_link(ctrl, &training_step);
+}
+
 int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
 {
-	u32 rate = 0;
 	int ret = 0;
 	bool mainlink_ready = false;
 	struct dp_ctrl_private *ctrl;
@@ -1751,10 +1788,6 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
 
 	ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl);
 
-	rate = ctrl->panel->link_info.rate;
-
-	ctrl->link->link_params.rate = rate;
-	ctrl->link->link_params.num_lanes = ctrl->panel->link_info.num_lanes;
 	ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock;
 
 	DRM_DEBUG_DP("rate=%d, num_lanes=%d, pixel_rate=%d\n",
@@ -1769,6 +1802,12 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
 		}
 	}
 
+	if (!dp_ctrl_channel_eq_ok(ctrl))
+		dp_ctrl_link_retrain(ctrl);
+
+	/* stop txing train pattern to end link training */
+	dp_ctrl_clear_training_pattern(ctrl);
+
 	ret = dp_ctrl_enable_stream_clocks(ctrl);
 	if (ret) {
 		DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret);
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 867388a399ad..fbe4c2cd52a3 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -55,7 +55,6 @@ enum {
 	EV_HPD_INIT_SETUP,
 	EV_HPD_PLUG_INT,
 	EV_IRQ_HPD_INT,
-	EV_HPD_REPLUG_INT,
 	EV_HPD_UNPLUG_INT,
 	EV_USER_NOTIFICATION,
 	EV_CONNECT_PENDING_TIMEOUT,
@@ -102,8 +101,6 @@ struct dp_display_private {
 	struct dp_display_mode dp_mode;
 	struct msm_dp dp_display;
 
-	bool encoder_mode_set;
-
 	/* wait for audio signaling */
 	struct completion audio_comp;
 
@@ -268,6 +265,8 @@ static bool dp_display_is_ds_bridge(struct dp_panel *panel)
 
 static bool dp_display_is_sink_count_zero(struct dp_display_private *dp)
 {
+	DRM_DEBUG_DP("present=%#x sink_count=%d\n", dp->panel->dpcd[DP_DOWNSTREAMPORT_PRESENT],
+		dp->link->sink_count);
 	return dp_display_is_ds_bridge(dp->panel) &&
 		(dp->link->sink_count == 0);
 }
@@ -284,20 +283,6 @@ static void dp_display_send_hpd_event(struct msm_dp *dp_display)
 }
 
 
-static void dp_display_set_encoder_mode(struct dp_display_private *dp)
-{
-	struct msm_drm_private *priv = dp->dp_display.drm_dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	if (!dp->encoder_mode_set && dp->dp_display.encoder &&
-				kms->funcs->set_encoder_mode) {
-		kms->funcs->set_encoder_mode(kms,
-				dp->dp_display.encoder, false);
-
-		dp->encoder_mode_set = true;
-	}
-}
-
 static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 					    bool hpd)
 {
@@ -313,6 +298,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 
 	dp->dp_display.is_connected = hpd;
 
+	DRM_DEBUG_DP("hpd=%d\n", hpd);
 	dp_display_send_hpd_event(&dp->dp_display);
 
 	return 0;
@@ -362,6 +348,7 @@ static void dp_display_host_init(struct dp_display_private *dp, int reset)
 {
 	bool flip = false;
 
+	DRM_DEBUG_DP("core_initialized=%d\n", dp->core_initialized);
 	if (dp->core_initialized) {
 		DRM_DEBUG_DP("DP core already initialized\n");
 		return;
@@ -370,8 +357,6 @@ static void dp_display_host_init(struct dp_display_private *dp, int reset)
 	if (dp->usbpd->orientation == ORIENTATION_CC2)
 		flip = true;
 
-	dp_display_set_encoder_mode(dp);
-
 	dp_power_init(dp->power, flip);
 	dp_ctrl_host_init(dp->ctrl, flip, reset);
 	dp_aux_init(dp->aux);
@@ -466,8 +451,10 @@ static int dp_display_handle_irq_hpd(struct dp_display_private *dp)
 {
 	u32 sink_request = dp->link->sink_request;
 
+	DRM_DEBUG_DP("%d\n", sink_request);
 	if (dp->hpd_state == ST_DISCONNECTED) {
 		if (sink_request & DP_LINK_STATUS_UPDATED) {
+			DRM_DEBUG_DP("Disconnected sink_request: %d\n", sink_request);
 			DRM_ERROR("Disconnected, no DP_LINK_STATUS_UPDATED\n");
 			return -EINVAL;
 		}
@@ -499,6 +486,7 @@ static int dp_display_usbpd_attention_cb(struct device *dev)
 	rc = dp_link_process_request(dp->link);
 	if (!rc) {
 		sink_request = dp->link->sink_request;
+		DRM_DEBUG_DP("hpd_state=%d sink_request=%d\n", dp->hpd_state, sink_request);
 		if (sink_request & DS_PORT_STATUS_CHANGED)
 			rc = dp_display_handle_port_ststus_changed(dp);
 		else
@@ -521,6 +509,7 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data)
 	mutex_lock(&dp->event_mutex);
 
 	state =  dp->hpd_state;
+	DRM_DEBUG_DP("hpd_state=%d\n", state);
 	if (state == ST_DISPLAY_OFF || state == ST_SUSPENDED) {
 		mutex_unlock(&dp->event_mutex);
 		return 0;
@@ -656,6 +645,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 	/* start sentinel checking in case of missing uevent */
 	dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND);
 
+	DRM_DEBUG_DP("hpd_state=%d\n", state);
 	/* signal the disconnect event early to ensure proper teardown */
 	dp_display_handle_plugged_change(g_dp_display, false);
 
@@ -714,6 +704,7 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data)
 	if (ret == -ECONNRESET) { /* cable unplugged */
 		dp->core_initialized = false;
 	}
+	DRM_DEBUG_DP("hpd_state=%d\n", state);
 
 	mutex_unlock(&dp->event_mutex);
 
@@ -855,6 +846,7 @@ static int dp_display_enable(struct dp_display_private *dp, u32 data)
 
 	dp_display = g_dp_display;
 
+	DRM_DEBUG_DP("sink_count=%d\n", dp->link->sink_count);
 	if (dp_display->power_on) {
 		DRM_DEBUG_DP("Link already setup, return\n");
 		return 0;
@@ -916,6 +908,7 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data)
 
 	dp_display->power_on = false;
 
+	DRM_DEBUG_DP("sink count: %d\n", dp->link->sink_count);
 	return 0;
 }
 
@@ -1015,10 +1008,8 @@ int dp_display_get_test_bpp(struct msm_dp *dp)
 void msm_dp_snapshot(struct msm_disp_state *disp_state, struct msm_dp *dp)
 {
 	struct dp_display_private *dp_display;
-	struct drm_device *drm;
 
 	dp_display = container_of(dp, struct dp_display_private, dp_display);
-	drm = dp->drm_dev;
 
 	/*
 	 * if we are reading registers we need the link clocks to be on
@@ -1119,9 +1110,6 @@ static int hpd_event_thread(void *data)
 		case EV_IRQ_HPD_INT:
 			dp_irq_hpd_handle(dp_priv, todo->data);
 			break;
-		case EV_HPD_REPLUG_INT:
-			/* do nothing */
-			break;
 		case EV_USER_NOTIFICATION:
 			dp_display_send_hpd_notification(dp_priv,
 						todo->data);
@@ -1163,12 +1151,11 @@ static irqreturn_t dp_display_irq_handler(int irq, void *dev_id)
 
 	hpd_isr_status = dp_catalog_hpd_get_intr_status(dp->catalog);
 
+	DRM_DEBUG_DP("hpd isr status=%#x\n", hpd_isr_status);
 	if (hpd_isr_status & 0x0F) {
 		/* hpd related interrupts */
-		if (hpd_isr_status & DP_DP_HPD_PLUG_INT_MASK ||
-			hpd_isr_status & DP_DP_HPD_REPLUG_INT_MASK) {
+		if (hpd_isr_status & DP_DP_HPD_PLUG_INT_MASK)
 			dp_add_event(dp, EV_HPD_PLUG_INT, 0, 0);
-		}
 
 		if (hpd_isr_status & DP_DP_IRQ_HPD_INT_MASK) {
 			/* stop sentinel connect pending checking */
@@ -1176,8 +1163,10 @@ static irqreturn_t dp_display_irq_handler(int irq, void *dev_id)
 			dp_add_event(dp, EV_IRQ_HPD_INT, 0, 0);
 		}
 
-		if (hpd_isr_status & DP_DP_HPD_REPLUG_INT_MASK)
-			dp_add_event(dp, EV_HPD_REPLUG_INT, 0, 0);
+		if (hpd_isr_status & DP_DP_HPD_REPLUG_INT_MASK) {
+			dp_add_event(dp, EV_HPD_UNPLUG_INT, 0, 0);
+			dp_add_event(dp, EV_HPD_PLUG_INT, 0, 3);
+		}
 
 		if (hpd_isr_status & DP_DP_HPD_UNPLUG_INT_MASK)
 			dp_add_event(dp, EV_HPD_UNPLUG_INT, 0, 0);
@@ -1286,12 +1275,15 @@ static int dp_pm_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct msm_dp *dp_display = platform_get_drvdata(pdev);
 	struct dp_display_private *dp;
-	u32 status;
+	int sink_count = 0;
 
 	dp = container_of(dp_display, struct dp_display_private, dp_display);
 
 	mutex_lock(&dp->event_mutex);
 
+	DRM_DEBUG_DP("Before, core_inited=%d power_on=%d\n",
+			dp->core_initialized, dp_display->power_on);
+
 	/* start from disconnected state */
 	dp->hpd_state = ST_DISCONNECTED;
 
@@ -1300,14 +1292,25 @@ static int dp_pm_resume(struct device *dev)
 
 	dp_catalog_ctrl_hpd_config(dp->catalog);
 
-	status = dp_catalog_link_is_connected(dp->catalog);
+	/*
+	 * set sink to normal operation mode -- D0
+	 * before dpcd read
+	 */
+	dp_link_psm_config(dp->link, &dp->panel->link_info, false);
+
+	if (dp_catalog_link_is_connected(dp->catalog)) {
+		sink_count = drm_dp_read_sink_count(dp->aux);
+		if (sink_count < 0)
+			sink_count = 0;
+	}
 
+	dp->link->sink_count = sink_count;
 	/*
 	 * can not declared display is connected unless
 	 * HDMI cable is plugged in and sink_count of
 	 * dongle become 1
 	 */
-	if (status && dp->link->sink_count)
+	if (dp->link->sink_count)
 		dp->dp_display.is_connected = true;
 	else
 		dp->dp_display.is_connected = false;
@@ -1315,6 +1318,9 @@ static int dp_pm_resume(struct device *dev)
 	dp_display_handle_plugged_change(g_dp_display,
 				dp->dp_display.is_connected);
 
+	DRM_DEBUG_DP("After, sink_count=%d is_connected=%d core_inited=%d power_on=%d\n",
+			dp->link->sink_count, dp->dp_display.is_connected,
+			dp->core_initialized, dp_display->power_on);
 
 	mutex_unlock(&dp->event_mutex);
 
@@ -1331,6 +1337,9 @@ static int dp_pm_suspend(struct device *dev)
 
 	mutex_lock(&dp->event_mutex);
 
+	DRM_DEBUG_DP("Before, core_inited=%d power_on=%d\n",
+			dp->core_initialized, dp_display->power_on);
+
 	if (dp->core_initialized == true) {
 		/* mainlink enabled */
 		if (dp_power_clk_status(dp->power, DP_CTRL_PM))
@@ -1344,6 +1353,9 @@ static int dp_pm_suspend(struct device *dev)
 	/* host_init will be called at pm_resume */
 	dp->core_initialized = false;
 
+	DRM_DEBUG_DP("After, core_inited=%d power_on=%d\n",
+			dp->core_initialized, dp_display->power_on);
+
 	mutex_unlock(&dp->event_mutex);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 1195044a7a3b..a5bdfc5029de 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -1027,43 +1027,29 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 	if (link->request.test_requested == DP_TEST_LINK_EDID_READ) {
 		dp_link->sink_request |= DP_TEST_LINK_EDID_READ;
-		return ret;
-	}
-
-	ret = dp_link_process_ds_port_status_change(link);
-	if (!ret) {
+	} else if (!dp_link_process_ds_port_status_change(link)) {
 		dp_link->sink_request |= DS_PORT_STATUS_CHANGED;
-		return ret;
-	}
-
-	ret = dp_link_process_link_training_request(link);
-	if (!ret) {
+	} else if (!dp_link_process_link_training_request(link)) {
 		dp_link->sink_request |= DP_TEST_LINK_TRAINING;
-		return ret;
-	}
-
-	ret = dp_link_process_phy_test_pattern_request(link);
-	if (!ret) {
+	} else if (!dp_link_process_phy_test_pattern_request(link)) {
 		dp_link->sink_request |= DP_TEST_LINK_PHY_TEST_PATTERN;
-		return ret;
-	}
-
-	ret = dp_link_process_link_status_update(link);
-	if (!ret) {
-		dp_link->sink_request |= DP_LINK_STATUS_UPDATED;
-		return ret;
-	}
-
-	if (dp_link_is_video_pattern_requested(link)) {
-		ret = 0;
-		dp_link->sink_request |= DP_TEST_LINK_VIDEO_PATTERN;
-	}
-
-	if (dp_link_is_audio_pattern_requested(link)) {
-		dp_link->sink_request |= DP_TEST_LINK_AUDIO_PATTERN;
-		return -EINVAL;
+	} else {
+		ret = dp_link_process_link_status_update(link);
+		if (!ret) {
+			dp_link->sink_request |= DP_LINK_STATUS_UPDATED;
+		} else {
+			if (dp_link_is_video_pattern_requested(link)) {
+				ret = 0;
+				dp_link->sink_request |= DP_TEST_LINK_VIDEO_PATTERN;
+			}
+			if (dp_link_is_audio_pattern_requested(link)) {
+				dp_link->sink_request |= DP_TEST_LINK_AUDIO_PATTERN;
+				ret = -EINVAL;
+			}
+		}
 	}
 
+	DRM_DEBUG_DP("sink request=%#x", dp_link->sink_request);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index 440b32753430..2181b60e1d1d 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -271,7 +271,7 @@ static u8 dp_panel_get_edid_checksum(struct edid *edid)
 {
 	struct edid *last_block;
 	u8 *raw_edid;
-	bool is_edid_corrupt;
+	bool is_edid_corrupt = false;
 
 	if (!edid) {
 		DRM_ERROR("invalid edid input\n");
@@ -303,7 +303,12 @@ void dp_panel_handle_sink_request(struct dp_panel *dp_panel)
 	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 
 	if (panel->link->sink_request & DP_TEST_LINK_EDID_READ) {
-		u8 checksum = dp_panel_get_edid_checksum(dp_panel->edid);
+		u8 checksum;
+
+		if (dp_panel->edid)
+			checksum = dp_panel_get_edid_checksum(dp_panel->edid);
+		else
+			checksum = dp_panel->connector->real_edid_checksum;
 
 		dp_link_send_edid_checksum(panel->link, checksum);
 		dp_link_send_test_response(panel->link);
diff --git a/drivers/gpu/drm/msm/dp/dp_power.c b/drivers/gpu/drm/msm/dp/dp_power.c
index 3961ba4efc3c..b48b45e92bfa 100644
--- a/drivers/gpu/drm/msm/dp/dp_power.c
+++ b/drivers/gpu/drm/msm/dp/dp_power.c
@@ -208,6 +208,9 @@ static int dp_power_clk_set_rate(struct dp_power_private *power,
 
 int dp_power_clk_status(struct dp_power *dp_power, enum dp_pm_type pm_type)
 {
+	DRM_DEBUG_DP("core_clk_on=%d link_clk_on=%d stream_clk_on=%d\n",
+		dp_power->core_clks_on, dp_power->link_clks_on, dp_power->stream_clks_on);
+
 	if (pm_type == DP_CORE_PM)
 		return dp_power->core_clks_on;
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 75afc12a7b25..614dc7f26f2c 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -13,6 +13,13 @@ struct drm_encoder *msm_dsi_get_encoder(struct msm_dsi *msm_dsi)
 	return msm_dsi->encoder;
 }
 
+bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi)
+{
+	unsigned long host_flags = msm_dsi_host_get_mode_flags(msm_dsi->host);
+
+	return !(host_flags & MIPI_DSI_MODE_VIDEO);
+}
+
 static int dsi_get_phy(struct msm_dsi *msm_dsi)
 {
 	struct platform_device *pdev = msm_dsi->pdev;
@@ -26,8 +33,10 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 	}
 
 	phy_pdev = of_find_device_by_node(phy_node);
-	if (phy_pdev)
+	if (phy_pdev) {
 		msm_dsi->phy = platform_get_drvdata(phy_pdev);
+		msm_dsi->phy_dev = &phy_pdev->dev;
+	}
 
 	of_node_put(phy_node);
 
@@ -36,8 +45,6 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 		return -EPROBE_DEFER;
 	}
 
-	msm_dsi->phy_dev = get_device(&phy_pdev->dev);
-
 	return 0;
 }
 
@@ -244,8 +251,6 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
-	msm_dsi_manager_setup_encoder(msm_dsi->id);
-
 	priv->bridges[priv->num_bridges++]       = msm_dsi->bridge;
 	priv->connectors[priv->num_connectors++] = msm_dsi->connector;
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 9b8e9b07eced..b50db91cb8a7 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -80,10 +80,10 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id);
 struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id);
 int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg);
 bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
-void msm_dsi_manager_setup_encoder(int id);
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi);
 void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi);
 bool msm_dsi_manager_validate_current_config(u8 id);
+void msm_dsi_manager_tpg_enable(void);
 
 /* msm dsi */
 static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi)
@@ -109,7 +109,7 @@ int msm_dsi_host_enable(struct mipi_dsi_host *host);
 int msm_dsi_host_disable(struct mipi_dsi_host *host);
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 			struct msm_dsi_phy_shared_timings *phy_shared_timings,
-			bool is_dual_dsi);
+			bool is_bonded_dsi, struct msm_dsi_phy *phy);
 int msm_dsi_host_power_off(struct mipi_dsi_host *host);
 int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 				  const struct drm_display_mode *mode);
@@ -123,7 +123,7 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 void msm_dsi_host_reset_phy(struct mipi_dsi_host *host);
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
 	struct msm_dsi_phy_clk_request *clk_req,
-	bool is_dual_dsi);
+	bool is_bonded_dsi);
 void msm_dsi_host_destroy(struct mipi_dsi_host *host);
 int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev);
@@ -145,9 +145,11 @@ int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova);
 int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova);
 int dsi_clk_init_v2(struct msm_dsi_host *msm_host);
 int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host);
-int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi);
-int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_bonded_dsi);
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi);
 void msm_dsi_host_snapshot(struct msm_disp_state *disp_state, struct mipi_dsi_host *host);
+void msm_dsi_host_test_pattern_en(struct mipi_dsi_host *host);
+
 /* dsi phy */
 struct msm_dsi_phy;
 struct msm_dsi_phy_shared_timings {
@@ -164,10 +166,9 @@ struct msm_dsi_phy_clk_request {
 void msm_dsi_phy_driver_register(void);
 void msm_dsi_phy_driver_unregister(void);
 int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
-			struct msm_dsi_phy_clk_request *clk_req);
+			struct msm_dsi_phy_clk_request *clk_req,
+			struct msm_dsi_phy_shared_timings *shared_timings);
 void msm_dsi_phy_disable(struct msm_dsi_phy *phy);
-void msm_dsi_phy_get_shared_timings(struct msm_dsi_phy *phy,
-			struct msm_dsi_phy_shared_timings *shared_timing);
 void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy,
 			     enum msm_dsi_phy_usecase uc);
 int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy,
@@ -175,6 +176,7 @@ int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy,
 void msm_dsi_phy_pll_save_state(struct msm_dsi_phy *phy);
 int msm_dsi_phy_pll_restore_state(struct msm_dsi_phy *phy);
 void msm_dsi_phy_snapshot(struct msm_disp_state *disp_state, struct msm_dsi_phy *phy);
+bool msm_dsi_phy_set_continuous_clock(struct msm_dsi_phy *phy, bool enable);
 
 #endif /* __DSI_CONNECTOR_H__ */
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h
index eadbcc78fd72..49b551ad1bff 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.xml.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h
@@ -105,6 +105,32 @@ enum dsi_lane_swap {
 	LANE_SWAP_3210 = 7,
 };
 
+enum video_config_bpp {
+	VIDEO_CONFIG_18BPP = 0,
+	VIDEO_CONFIG_24BPP = 1,
+};
+
+enum video_pattern_sel {
+	VID_PRBS = 0,
+	VID_INCREMENTAL = 1,
+	VID_FIXED = 2,
+	VID_MDSS_GENERAL_PATTERN = 3,
+};
+
+enum cmd_mdp_stream0_pattern_sel {
+	CMD_MDP_PRBS = 0,
+	CMD_MDP_INCREMENTAL = 1,
+	CMD_MDP_FIXED = 2,
+	CMD_MDP_MDSS_GENERAL_PATTERN = 3,
+};
+
+enum cmd_dma_pattern_sel {
+	CMD_DMA_PRBS = 0,
+	CMD_DMA_INCREMENTAL = 1,
+	CMD_DMA_FIXED = 2,
+	CMD_DMA_CUSTOM_PATTERN_DMA_FIFO = 3,
+};
+
 #define DSI_IRQ_CMD_DMA_DONE					0x00000001
 #define DSI_IRQ_MASK_CMD_DMA_DONE				0x00000002
 #define DSI_IRQ_CMD_MDP_DONE					0x00000100
@@ -518,6 +544,7 @@ static inline uint32_t DSI_CLKOUT_TIMING_CTRL_T_CLK_POST(uint32_t val)
 #define DSI_LANE_STATUS_DLN0_DIRECTION				0x00010000
 
 #define REG_DSI_LANE_CTRL					0x000000a8
+#define DSI_LANE_CTRL_HS_REQ_SEL_PHY				0x01000000
 #define DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST			0x10000000
 
 #define REG_DSI_LANE_SWAP_CTRL					0x000000ac
@@ -564,6 +591,53 @@ static inline uint32_t DSI_LANE_SWAP_CTRL_DLN_SWAP_SEL(enum dsi_lane_swap val)
 #define REG_DSI_PHY_RESET					0x00000128
 #define DSI_PHY_RESET_RESET					0x00000001
 
+#define REG_DSI_TEST_PATTERN_GEN_VIDEO_INIT_VAL			0x00000160
+
+#define REG_DSI_TPG_MAIN_CONTROL				0x00000198
+#define DSI_TPG_MAIN_CONTROL_CHECKERED_RECTANGLE_PATTERN	0x00000100
+
+#define REG_DSI_TPG_VIDEO_CONFIG				0x000001a0
+#define DSI_TPG_VIDEO_CONFIG_BPP__MASK				0x00000003
+#define DSI_TPG_VIDEO_CONFIG_BPP__SHIFT				0
+static inline uint32_t DSI_TPG_VIDEO_CONFIG_BPP(enum video_config_bpp val)
+{
+	return ((val) << DSI_TPG_VIDEO_CONFIG_BPP__SHIFT) & DSI_TPG_VIDEO_CONFIG_BPP__MASK;
+}
+#define DSI_TPG_VIDEO_CONFIG_RGB				0x00000004
+
+#define REG_DSI_TEST_PATTERN_GEN_CTRL				0x00000158
+#define DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_PATTERN_SEL__MASK	0x00030000
+#define DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_PATTERN_SEL__SHIFT	16
+static inline uint32_t DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_PATTERN_SEL(enum cmd_dma_pattern_sel val)
+{
+	return ((val) << DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_PATTERN_SEL__SHIFT) & DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_PATTERN_SEL__MASK;
+}
+#define DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL__MASK	0x00000300
+#define DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL__SHIFT	8
+static inline uint32_t DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL(enum cmd_mdp_stream0_pattern_sel val)
+{
+	return ((val) << DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL__SHIFT) & DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL__MASK;
+}
+#define DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL__MASK	0x00000030
+#define DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL__SHIFT	4
+static inline uint32_t DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL(enum video_pattern_sel val)
+{
+	return ((val) << DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL__SHIFT) & DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL__MASK;
+}
+#define DSI_TEST_PATTERN_GEN_CTRL_TPG_DMA_FIFO_MODE		0x00000004
+#define DSI_TEST_PATTERN_GEN_CTRL_CMD_DMA_TPG_EN		0x00000002
+#define DSI_TEST_PATTERN_GEN_CTRL_EN				0x00000001
+
+#define REG_DSI_TEST_PATTERN_GEN_CMD_MDP_INIT_VAL0		0x00000168
+
+#define REG_DSI_TEST_PATTERN_GEN_CMD_STREAM0_TRIGGER		0x00000180
+#define DSI_TEST_PATTERN_GEN_CMD_STREAM0_TRIGGER_SW_TRIGGER	0x00000001
+
+#define REG_DSI_TPG_MAIN_CONTROL2				0x0000019c
+#define DSI_TPG_MAIN_CONTROL2_CMD_MDP0_CHECKERED_RECTANGLE_PATTERN	0x00000080
+#define DSI_TPG_MAIN_CONTROL2_CMD_MDP1_CHECKERED_RECTANGLE_PATTERN	0x00010000
+#define DSI_TPG_MAIN_CONTROL2_CMD_MDP2_CHECKERED_RECTANGLE_PATTERN	0x02000000
+
 #define REG_DSI_T_CLK_PRE_EXTEND				0x0000017c
 #define DSI_T_CLK_PRE_EXTEND_INC_BY_2_BYTECLK			0x00000001
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index f3f1c03c7db9..96bbc8b6d009 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -32,9 +32,8 @@ static const char * const dsi_6g_bus_clk_names[] = {
 static const struct msm_dsi_config msm8974_apq8084_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 4,
+		.num = 3,
 		.regs = {
-			{"gdsc", -1, -1},
 			{"vdd", 150000, 100},	/* 3.0 V */
 			{"vdda", 100000, 100},	/* 1.2 V */
 			{"vddio", 100000, 100},	/* 1.8 V */
@@ -53,9 +52,8 @@ static const char * const dsi_8916_bus_clk_names[] = {
 static const struct msm_dsi_config msm8916_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 3,
+		.num = 2,
 		.regs = {
-			{"gdsc", -1, -1},
 			{"vdda", 100000, 100},	/* 1.2 V */
 			{"vddio", 100000, 100},	/* 1.8 V */
 		},
@@ -73,9 +71,8 @@ static const char * const dsi_8976_bus_clk_names[] = {
 static const struct msm_dsi_config msm8976_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 3,
+		.num = 2,
 		.regs = {
-			{"gdsc", -1, -1},
 			{"vdda", 100000, 100},	/* 1.2 V */
 			{"vddio", 100000, 100},	/* 1.8 V */
 		},
@@ -89,9 +86,8 @@ static const struct msm_dsi_config msm8976_dsi_cfg = {
 static const struct msm_dsi_config msm8994_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 7,
+		.num = 6,
 		.regs = {
-			{"gdsc", -1, -1},
 			{"vdda", 100000, 100},	/* 1.25 V */
 			{"vddio", 100000, 100},	/* 1.8 V */
 			{"vcca", 10000, 100},	/* 1.0 V */
@@ -154,7 +150,6 @@ static const struct msm_dsi_config sdm660_dsi_cfg = {
 	.reg_cfg = {
 		.num = 2,
 		.regs = {
-			{"vdd", 73400, 32 },	/* 0.9 V */
 			{"vdda", 12560, 4 },	/* 1.2 V */
 		},
 	},
@@ -200,6 +195,24 @@ static const struct msm_dsi_config sc7180_dsi_cfg = {
 	.num_dsi = 1,
 };
 
+static const char * const dsi_sc7280_bus_clk_names[] = {
+	"iface", "bus",
+};
+
+static const struct msm_dsi_config sc7280_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vdda", 8350, 0 },	/* 1.2 V */
+		},
+	},
+	.bus_clk_names = dsi_sc7280_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_sc7280_bus_clk_names),
+	.io_start = { 0xae94000 },
+	.num_dsi = 1,
+};
+
 static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.link_clk_set_rate = dsi_link_clk_set_rate_v2,
 	.link_clk_enable = dsi_link_clk_enable_v2,
@@ -267,6 +280,8 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1,
 		&sc7180_dsi_cfg, &msm_dsi_6g_v2_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_5_0,
+		&sc7280_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index ade9b609c7d9..41e99a9fb5de 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -24,6 +24,7 @@
 #define MSM_DSI_6G_VER_MINOR_V2_3_0	0x20030000
 #define MSM_DSI_6G_VER_MINOR_V2_4_0	0x20040000
 #define MSM_DSI_6G_VER_MINOR_V2_4_1	0x20040001
+#define MSM_DSI_6G_VER_MINOR_V2_5_0	0x20050000
 
 #define MSM_DSI_V2_VER_MINOR_8064	0x0
 
@@ -47,7 +48,7 @@ struct msm_dsi_host_cfg_ops {
 	void* (*tx_buf_get)(struct msm_dsi_host *msm_host);
 	void (*tx_buf_put)(struct msm_dsi_host *msm_host);
 	int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova);
-	int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+	int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_bonded_dsi);
 };
 
 struct msm_dsi_cfg_handler {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index ed504fe5074f..e269df285136 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -27,6 +27,7 @@
 #include "dsi_cfg.h"
 #include "msm_kms.h"
 #include "msm_gem.h"
+#include "phy/dsi_phy.h"
 
 #define DSI_RESET_TOGGLE_DELAY_MS 20
 
@@ -167,6 +168,9 @@ struct msm_dsi_host {
 	int dlane_swap;
 	int num_data_lanes;
 
+	/* from phy DT */
+	bool cphy_mode;
+
 	u32 dma_cmd_ctrl_restore;
 
 	bool registered;
@@ -203,35 +207,22 @@ static const struct msm_dsi_cfg_handler *dsi_get_config(
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = NULL;
 	struct device *dev = &msm_host->pdev->dev;
-	struct regulator *gdsc_reg;
 	struct clk *ahb_clk;
 	int ret;
 	u32 major = 0, minor = 0;
 
-	gdsc_reg = regulator_get(dev, "gdsc");
-	if (IS_ERR(gdsc_reg)) {
-		pr_err("%s: cannot get gdsc\n", __func__);
-		goto exit;
-	}
-
 	ahb_clk = msm_clk_get(msm_host->pdev, "iface");
 	if (IS_ERR(ahb_clk)) {
 		pr_err("%s: cannot get interface clock\n", __func__);
-		goto put_gdsc;
+		goto exit;
 	}
 
 	pm_runtime_get_sync(dev);
 
-	ret = regulator_enable(gdsc_reg);
-	if (ret) {
-		pr_err("%s: unable to enable gdsc\n", __func__);
-		goto put_gdsc;
-	}
-
 	ret = clk_prepare_enable(ahb_clk);
 	if (ret) {
 		pr_err("%s: unable to enable ahb_clk\n", __func__);
-		goto disable_gdsc;
+		goto runtime_put;
 	}
 
 	ret = dsi_get_version(msm_host->ctrl_base, &major, &minor);
@@ -246,11 +237,8 @@ static const struct msm_dsi_cfg_handler *dsi_get_config(
 
 disable_clks:
 	clk_disable_unprepare(ahb_clk);
-disable_gdsc:
-	regulator_disable(gdsc_reg);
+runtime_put:
 	pm_runtime_put_sync(dev);
-put_gdsc:
-	regulator_put(gdsc_reg);
 exit:
 	return cfg_hnd;
 }
@@ -510,6 +498,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 
 int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host)
 {
+	u32 byte_intf_rate;
 	int ret;
 
 	DBG("Set clk rates: pclk=%d, byteclk=%d",
@@ -529,8 +518,13 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host)
 	}
 
 	if (msm_host->byte_intf_clk) {
-		ret = clk_set_rate(msm_host->byte_intf_clk,
-				   msm_host->byte_clk_rate / 2);
+		/* For CPHY, byte_intf_clk is same as byte_clk */
+		if (msm_host->cphy_mode)
+			byte_intf_rate = msm_host->byte_clk_rate;
+		else
+			byte_intf_rate = msm_host->byte_clk_rate / 2;
+
+		ret = clk_set_rate(msm_host->byte_intf_clk, byte_intf_rate);
 		if (ret) {
 			pr_err("%s: Failed to set rate byte intf clk, %d\n",
 			       __func__, ret);
@@ -679,7 +673,7 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
 	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u32 pclk_rate;
@@ -687,22 +681,22 @@ static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 	pclk_rate = mode->clock * 1000;
 
 	/*
-	 * For dual DSI mode, the current DRM mode has the complete width of the
+	 * For bonded DSI mode, the current DRM mode has the complete width of the
 	 * panel. Since, the complete panel is driven by two DSI controllers,
 	 * the clock rates have to be split between the two dsi controllers.
 	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
 	 */
-	if (is_dual_dsi)
+	if (is_bonded_dsi)
 		pclk_rate /= 2;
 
 	return pclk_rate;
 }
 
-static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
 	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
-	u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_dual_dsi);
+	u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_bonded_dsi);
 	u64 pclk_bpp = (u64)pclk_rate * bpp;
 
 	if (lanes == 0) {
@@ -710,7 +704,11 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 		lanes = 1;
 	}
 
-	do_div(pclk_bpp, (8 * lanes));
+	/* CPHY "byte_clk" is in units of 16 bits */
+	if (msm_host->cphy_mode)
+		do_div(pclk_bpp, (16 * lanes));
+	else
+		do_div(pclk_bpp, (8 * lanes));
 
 	msm_host->pixel_clk_rate = pclk_rate;
 	msm_host->byte_clk_rate = pclk_bpp;
@@ -720,28 +718,28 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 
 }
 
-int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
 	if (!msm_host->mode) {
 		pr_err("%s: mode not set\n", __func__);
 		return -EINVAL;
 	}
 
-	dsi_calc_pclk(msm_host, is_dual_dsi);
+	dsi_calc_pclk(msm_host, is_bonded_dsi);
 	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
 	return 0;
 }
 
-int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
 	u32 bpp = dsi_get_bpp(msm_host->format);
 	u64 pclk_bpp;
 	unsigned int esc_mhz, esc_div;
 	unsigned long byte_mhz;
 
-	dsi_calc_pclk(msm_host, is_dual_dsi);
+	dsi_calc_pclk(msm_host, is_bonded_dsi);
 
-	pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_dual_dsi) * bpp;
+	pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_bonded_dsi) * bpp;
 	do_div(pclk_bpp, 8);
 	msm_host->src_clk_rate = pclk_bpp;
 
@@ -834,7 +832,7 @@ static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt(
 }
 
 static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings)
+			struct msm_dsi_phy_shared_timings *phy_shared_timings, struct msm_dsi_phy *phy)
 {
 	u32 flags = msm_host->mode_flags;
 	enum mipi_dsi_pixel_format mipi_fmt = msm_host->format;
@@ -849,11 +847,11 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	if (flags & MIPI_DSI_MODE_VIDEO) {
 		if (flags & MIPI_DSI_MODE_VIDEO_HSE)
 			data |= DSI_VID_CFG0_PULSE_MODE_HSA_HE;
-		if (flags & MIPI_DSI_MODE_VIDEO_HFP)
+		if (flags & MIPI_DSI_MODE_VIDEO_NO_HFP)
 			data |= DSI_VID_CFG0_HFP_POWER_STOP;
-		if (flags & MIPI_DSI_MODE_VIDEO_HBP)
+		if (flags & MIPI_DSI_MODE_VIDEO_NO_HBP)
 			data |= DSI_VID_CFG0_HBP_POWER_STOP;
-		if (flags & MIPI_DSI_MODE_VIDEO_HSA)
+		if (flags & MIPI_DSI_MODE_VIDEO_NO_HSA)
 			data |= DSI_VID_CFG0_HSA_POWER_STOP;
 		/* Always set low power stop mode for BLLP
 		 * to let command engine send packets
@@ -908,7 +906,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 			  DSI_T_CLK_PRE_EXTEND_INC_BY_2_BYTECLK);
 
 	data = 0;
-	if (!(flags & MIPI_DSI_MODE_EOT_PACKET))
+	if (!(flags & MIPI_DSI_MODE_NO_EOT_PACKET))
 		data |= DSI_EOT_PACKET_CTRL_TX_EOT_APPEND;
 	dsi_write(msm_host, REG_DSI_EOT_PACKET_CTRL, data);
 
@@ -929,6 +927,10 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 
 	if (!(flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) {
 		lane_ctrl = dsi_read(msm_host, REG_DSI_LANE_CTRL);
+
+		if (msm_dsi_phy_set_continuous_clock(phy, enable))
+			lane_ctrl &= ~DSI_LANE_CTRL_HS_REQ_SEL_PHY;
+
 		dsi_write(msm_host, REG_DSI_LANE_CTRL,
 			lane_ctrl | DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST);
 	}
@@ -936,9 +938,12 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	data |= DSI_CTRL_ENABLE;
 
 	dsi_write(msm_host, REG_DSI_CTRL, data);
+
+	if (msm_host->cphy_mode)
+		dsi_write(msm_host, REG_DSI_CPHY_MODE_CTRL, BIT(0));
 }
 
-static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u32 hs_start = 0, vs_start = 0; /* take sync start as 0 */
@@ -956,13 +961,13 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 	DBG("");
 
 	/*
-	 * For dual DSI mode, the current DRM mode has
+	 * For bonded DSI mode, the current DRM mode has
 	 * the complete width of the panel. Since, the complete
 	 * panel is driven by two DSI controllers, the horizontal
 	 * timings have to be split between the two dsi controllers.
 	 * Adjust the DSI host timing values accordingly.
 	 */
-	if (is_dual_dsi) {
+	if (is_bonded_dsi) {
 		h_total /= 2;
 		hs_end /= 2;
 		ha_start /= 2;
@@ -2226,6 +2231,8 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 	struct clk *byte_clk_provider, *pixel_clk_provider;
 	int ret;
 
+	msm_host->cphy_mode = src_phy->cphy_mode;
+
 	ret = msm_dsi_phy_get_clk_provider(src_phy,
 				&byte_clk_provider, &pixel_clk_provider);
 	if (ret) {
@@ -2285,19 +2292,26 @@ void msm_dsi_host_reset_phy(struct mipi_dsi_host *host)
 
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
 			struct msm_dsi_phy_clk_request *clk_req,
-			bool is_dual_dsi)
+			bool is_bonded_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 
-	ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_dual_dsi);
+	ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_bonded_dsi);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
 		return;
 	}
 
-	clk_req->bitclk_rate = msm_host->byte_clk_rate * 8;
+	/* CPHY transmits 16 bits over 7 clock cycles
+	 * "byte_clk" is in units of 16-bits (see dsi_calc_pclk),
+	 * so multiply by 7 to get the "bitclk rate"
+	 */
+	if (msm_host->cphy_mode)
+		clk_req->bitclk_rate = msm_host->byte_clk_rate * 7;
+	else
+		clk_req->bitclk_rate = msm_host->byte_clk_rate * 8;
 	clk_req->escclk_rate = msm_host->esc_clk_rate;
 }
 
@@ -2354,7 +2368,7 @@ static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable)
 
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 			struct msm_dsi_phy_shared_timings *phy_shared_timings,
-			bool is_dual_dsi)
+			bool is_bonded_dsi, struct msm_dsi_phy *phy)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
@@ -2392,9 +2406,9 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 		goto fail_disable_clk;
 	}
 
-	dsi_timing_setup(msm_host, is_dual_dsi);
+	dsi_timing_setup(msm_host, is_bonded_dsi);
 	dsi_sw_reset(msm_host);
-	dsi_ctrl_config(msm_host, true, phy_shared_timings);
+	dsi_ctrl_config(msm_host, true, phy_shared_timings, phy);
 
 	if (msm_host->disp_en_gpio)
 		gpiod_set_value(msm_host->disp_en_gpio, 1);
@@ -2425,7 +2439,7 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 		goto unlock_ret;
 	}
 
-	dsi_ctrl_config(msm_host, false, NULL);
+	dsi_ctrl_config(msm_host, false, NULL, NULL);
 
 	if (msm_host->disp_en_gpio)
 		gpiod_set_value(msm_host->disp_en_gpio, 0);
@@ -2495,3 +2509,64 @@ void msm_dsi_host_snapshot(struct msm_disp_state *disp_state, struct mipi_dsi_ho
 
 	pm_runtime_put_sync(&msm_host->pdev->dev);
 }
+
+static void msm_dsi_host_video_test_pattern_setup(struct msm_dsi_host *msm_host)
+{
+	u32 reg;
+
+	reg = dsi_read(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL);
+
+	dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_VIDEO_INIT_VAL, 0xff);
+	/* draw checkered rectangle pattern */
+	dsi_write(msm_host, REG_DSI_TPG_MAIN_CONTROL,
+			DSI_TPG_MAIN_CONTROL_CHECKERED_RECTANGLE_PATTERN);
+	/* use 24-bit RGB test pttern */
+	dsi_write(msm_host, REG_DSI_TPG_VIDEO_CONFIG,
+			DSI_TPG_VIDEO_CONFIG_BPP(VIDEO_CONFIG_24BPP) |
+			DSI_TPG_VIDEO_CONFIG_RGB);
+
+	reg |= DSI_TEST_PATTERN_GEN_CTRL_VIDEO_PATTERN_SEL(VID_MDSS_GENERAL_PATTERN);
+	dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL, reg);
+
+	DBG("Video test pattern setup done\n");
+}
+
+static void msm_dsi_host_cmd_test_pattern_setup(struct msm_dsi_host *msm_host)
+{
+	u32 reg;
+
+	reg = dsi_read(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL);
+
+	/* initial value for test pattern */
+	dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_CMD_MDP_INIT_VAL0, 0xff);
+
+	reg |= DSI_TEST_PATTERN_GEN_CTRL_CMD_MDP_STREAM0_PATTERN_SEL(CMD_MDP_MDSS_GENERAL_PATTERN);
+
+	dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL, reg);
+	/* draw checkered rectangle pattern */
+	dsi_write(msm_host, REG_DSI_TPG_MAIN_CONTROL2,
+			DSI_TPG_MAIN_CONTROL2_CMD_MDP0_CHECKERED_RECTANGLE_PATTERN);
+
+	DBG("Cmd test pattern setup done\n");
+}
+
+void msm_dsi_host_test_pattern_en(struct mipi_dsi_host *host)
+{
+	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	bool is_video_mode = !!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO);
+	u32 reg;
+
+	if (is_video_mode)
+		msm_dsi_host_video_test_pattern_setup(msm_host);
+	else
+		msm_dsi_host_cmd_test_pattern_setup(msm_host);
+
+	reg = dsi_read(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL);
+	/* enable the test pattern generator */
+	dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_CTRL, (reg | DSI_TEST_PATTERN_GEN_CTRL_EN));
+
+	/* for command mode need to trigger one frame from tpg */
+	if (!is_video_mode)
+		dsi_write(msm_host, REG_DSI_TEST_PATTERN_GEN_CMD_STREAM0_TRIGGER,
+				DSI_TEST_PATTERN_GEN_CMD_STREAM0_TRIGGER_SW_TRIGGER);
+}
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4ebfedc4a9ac..c41d39f5b7cf 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -21,14 +21,14 @@
 struct msm_dsi_manager {
 	struct msm_dsi *dsi[DSI_MAX];
 
-	bool is_dual_dsi;
+	bool is_bonded_dsi;
 	bool is_sync_needed;
 	int master_dsi_link_id;
 };
 
 static struct msm_dsi_manager msm_dsim_glb;
 
-#define IS_DUAL_DSI()		(msm_dsim_glb.is_dual_dsi)
+#define IS_BONDED_DSI()		(msm_dsim_glb.is_bonded_dsi)
 #define IS_SYNC_NEEDED()	(msm_dsim_glb.is_sync_needed)
 #define IS_MASTER_DSI_LINK(id)	(msm_dsim_glb.master_dsi_link_id == id)
 
@@ -42,18 +42,17 @@ static inline struct msm_dsi *dsi_mgr_get_other_dsi(int id)
 	return msm_dsim_glb.dsi[(id + 1) % DSI_MAX];
 }
 
-static int dsi_mgr_parse_dual_dsi(struct device_node *np, int id)
+static int dsi_mgr_parse_of(struct device_node *np, int id)
 {
 	struct msm_dsi_manager *msm_dsim = &msm_dsim_glb;
 
-	/* We assume 2 dsi nodes have the same information of dual-dsi and
-	 * sync-mode, and only one node specifies master in case of dual mode.
+	/* We assume 2 dsi nodes have the same information of bonded dsi and
+	 * sync-mode, and only one node specifies master in case of bonded mode.
 	 */
-	if (!msm_dsim->is_dual_dsi)
-		msm_dsim->is_dual_dsi = of_property_read_bool(
-						np, "qcom,dual-dsi-mode");
+	if (!msm_dsim->is_bonded_dsi)
+		msm_dsim->is_bonded_dsi = of_property_read_bool(np, "qcom,dual-dsi-mode");
 
-	if (msm_dsim->is_dual_dsi) {
+	if (msm_dsim->is_bonded_dsi) {
 		if (of_property_read_bool(np, "qcom,master-dsi"))
 			msm_dsim->master_dsi_link_id = id;
 		if (!msm_dsim->is_sync_needed)
@@ -72,7 +71,7 @@ static int dsi_mgr_setup_components(int id)
 	struct msm_dsi *clk_slave_dsi = dsi_mgr_get_dsi(DSI_CLOCK_SLAVE);
 	int ret;
 
-	if (!IS_DUAL_DSI()) {
+	if (!IS_BONDED_DSI()) {
 		ret = msm_dsi_host_register(msm_dsi->host, true);
 		if (ret)
 			return ret;
@@ -100,7 +99,7 @@ static int dsi_mgr_setup_components(int id)
 		if (ret)
 			return ret;
 
-		/* PLL0 is to drive both 2 DSI link clocks in Dual DSI mode. */
+		/* PLL0 is to drive both 2 DSI link clocks in bonded DSI mode. */
 		msm_dsi_phy_set_usecase(clk_master_dsi->phy,
 					MSM_DSI_PHY_MASTER);
 		msm_dsi_phy_set_usecase(clk_slave_dsi->phy,
@@ -119,12 +118,11 @@ static int enable_phy(struct msm_dsi *msm_dsi,
 {
 	struct msm_dsi_phy_clk_request clk_req;
 	int ret;
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 
-	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi);
+	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_bonded_dsi);
 
-	ret = msm_dsi_phy_enable(msm_dsi->phy, &clk_req);
-	msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings);
+	ret = msm_dsi_phy_enable(msm_dsi->phy, &clk_req, shared_timings);
 
 	return ret;
 }
@@ -138,12 +136,12 @@ dsi_mgr_phy_enable(int id,
 	struct msm_dsi *sdsi = dsi_mgr_get_dsi(DSI_CLOCK_SLAVE);
 	int ret;
 
-	/* In case of dual DSI, some registers in PHY1 have been programmed
+	/* In case of bonded DSI, some registers in PHY1 have been programmed
 	 * during PLL0 clock's set_rate. The PHY1 reset called by host1 here
 	 * will silently reset those PHY1 registers. Therefore we need to reset
 	 * and enable both PHYs before any PLL clock operation.
 	 */
-	if (IS_DUAL_DSI() && mdsi && sdsi) {
+	if (IS_BONDED_DSI() && mdsi && sdsi) {
 		if (!mdsi->phy_enabled && !sdsi->phy_enabled) {
 			msm_dsi_host_reset_phy(mdsi->host);
 			msm_dsi_host_reset_phy(sdsi->host);
@@ -178,11 +176,11 @@ static void dsi_mgr_phy_disable(int id)
 	struct msm_dsi *sdsi = dsi_mgr_get_dsi(DSI_CLOCK_SLAVE);
 
 	/* disable DSI phy
-	 * In dual-dsi configuration, the phy should be disabled for the
+	 * In bonded dsi configuration, the phy should be disabled for the
 	 * first controller only when the second controller is disabled.
 	 */
 	msm_dsi->phy_enabled = false;
-	if (IS_DUAL_DSI() && mdsi && sdsi) {
+	if (IS_BONDED_DSI() && mdsi && sdsi) {
 		if (!mdsi->phy_enabled && !sdsi->phy_enabled) {
 			msm_dsi_phy_disable(sdsi->phy);
 			msm_dsi_phy_disable(mdsi->phy);
@@ -217,24 +215,6 @@ static int dsi_mgr_bridge_get_id(struct drm_bridge *bridge)
 	return dsi_bridge->id;
 }
 
-static bool dsi_mgr_is_cmd_mode(struct msm_dsi *msm_dsi)
-{
-	unsigned long host_flags = msm_dsi_host_get_mode_flags(msm_dsi->host);
-	return !(host_flags & MIPI_DSI_MODE_VIDEO);
-}
-
-void msm_dsi_manager_setup_encoder(int id)
-{
-	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-	struct msm_drm_private *priv = msm_dsi->dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	struct drm_encoder *encoder = msm_dsi_get_encoder(msm_dsi);
-
-	if (encoder && kms->funcs->set_encoder_mode)
-		kms->funcs->set_encoder_mode(kms, encoder,
-					     dsi_mgr_is_cmd_mode(msm_dsi));
-}
-
 static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id)
 {
 	struct msm_drm_private *priv = conn->dev->dev_private;
@@ -244,7 +224,7 @@ static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id)
 	struct msm_dsi *master_dsi, *slave_dsi;
 	struct drm_panel *panel;
 
-	if (IS_DUAL_DSI() && !IS_MASTER_DSI_LINK(id)) {
+	if (IS_BONDED_DSI() && !IS_MASTER_DSI_LINK(id)) {
 		master_dsi = other_dsi;
 		slave_dsi = msm_dsi;
 	} else {
@@ -253,7 +233,7 @@ static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id)
 	}
 
 	/*
-	 * There is only 1 panel in the global panel list for dual DSI mode.
+	 * There is only 1 panel in the global panel list for bonded DSI mode.
 	 * Therefore slave dsi should get the drm_panel instance from master
 	 * dsi.
 	 */
@@ -264,20 +244,20 @@ static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id)
 		return PTR_ERR(panel);
 	}
 
-	if (!panel || !IS_DUAL_DSI())
+	if (!panel || !IS_BONDED_DSI())
 		goto out;
 
 	drm_object_attach_property(&conn->base,
 				   conn->dev->mode_config.tile_property, 0);
 
 	/*
-	 * Set split display info to kms once dual DSI panel is connected to
+	 * Set split display info to kms once bonded DSI panel is connected to
 	 * both hosts.
 	 */
 	if (other_dsi && other_dsi->panel && kms->funcs->set_split_display) {
 		kms->funcs->set_split_display(kms, master_dsi->encoder,
 					      slave_dsi->encoder,
-					      dsi_mgr_is_cmd_mode(msm_dsi));
+					      msm_dsi_is_cmd_mode(msm_dsi));
 	}
 
 out:
@@ -317,7 +297,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 		return 0;
 
 	/*
-	 * In dual DSI mode, we have one connector that can be
+	 * In bonded DSI mode, we have one connector that can be
 	 * attached to the drm_panel.
 	 */
 	num = drm_panel_get_modes(panel, connector);
@@ -366,30 +346,30 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
 	struct msm_dsi_phy_shared_timings phy_shared_timings[DSI_MAX];
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 	int ret;
 
 	DBG("id=%d", id);
 	if (!msm_dsi_device_connected(msm_dsi))
 		return;
 
-	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+	/* Do nothing with the host if it is slave-DSI in case of bonded DSI */
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	ret = dsi_mgr_phy_enable(id, phy_shared_timings);
 	if (ret)
 		goto phy_en_fail;
 
-	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi);
+	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_bonded_dsi, msm_dsi->phy);
 	if (ret) {
 		pr_err("%s: power on host %d failed, %d\n", __func__, id, ret);
 		goto host_on_fail;
 	}
 
-	if (is_dual_dsi && msm_dsi1) {
+	if (is_bonded_dsi && msm_dsi1) {
 		ret = msm_dsi_host_power_on(msm_dsi1->host,
-				&phy_shared_timings[DSI_1], is_dual_dsi);
+				&phy_shared_timings[DSI_1], is_bonded_dsi, msm_dsi1->phy);
 		if (ret) {
 			pr_err("%s: power on host1 failed, %d\n",
 							__func__, ret);
@@ -415,7 +395,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 		goto host_en_fail;
 	}
 
-	if (is_dual_dsi && msm_dsi1) {
+	if (is_bonded_dsi && msm_dsi1) {
 		ret = msm_dsi_host_enable(msm_dsi1->host);
 		if (ret) {
 			pr_err("%s: enable host1 failed, %d\n", __func__, ret);
@@ -431,7 +411,7 @@ host_en_fail:
 	if (panel)
 		drm_panel_unprepare(panel);
 panel_prep_fail:
-	if (is_dual_dsi && msm_dsi1)
+	if (is_bonded_dsi && msm_dsi1)
 		msm_dsi_host_power_off(msm_dsi1->host);
 host1_on_fail:
 	msm_dsi_host_power_off(host);
@@ -441,20 +421,33 @@ phy_en_fail:
 	return;
 }
 
+void msm_dsi_manager_tpg_enable(void)
+{
+	struct msm_dsi *m_dsi = dsi_mgr_get_dsi(DSI_0);
+	struct msm_dsi *s_dsi = dsi_mgr_get_dsi(DSI_1);
+
+	/* if dual dsi, trigger tpg on master first then slave */
+	if (m_dsi) {
+		msm_dsi_host_test_pattern_en(m_dsi->host);
+		if (IS_BONDED_DSI() && s_dsi)
+			msm_dsi_host_test_pattern_en(s_dsi->host);
+	}
+}
+
 static void dsi_mgr_bridge_enable(struct drm_bridge *bridge)
 {
 	int id = dsi_mgr_bridge_get_id(bridge);
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_panel *panel = msm_dsi->panel;
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 	int ret;
 
 	DBG("id=%d", id);
 	if (!msm_dsi_device_connected(msm_dsi))
 		return;
 
-	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+	/* Do nothing with the host if it is slave-DSI in case of bonded DSI */
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	if (panel) {
@@ -471,15 +464,15 @@ static void dsi_mgr_bridge_disable(struct drm_bridge *bridge)
 	int id = dsi_mgr_bridge_get_id(bridge);
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_panel *panel = msm_dsi->panel;
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 	int ret;
 
 	DBG("id=%d", id);
 	if (!msm_dsi_device_connected(msm_dsi))
 		return;
 
-	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+	/* Do nothing with the host if it is slave-DSI in case of bonded DSI */
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	if (panel) {
@@ -497,7 +490,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 	int ret;
 
 	DBG("id=%d", id);
@@ -506,18 +499,18 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 		return;
 
 	/*
-	 * Do nothing with the host if it is slave-DSI in case of dual DSI.
+	 * Do nothing with the host if it is slave-DSI in case of bonded DSI.
 	 * It is safe to call dsi_mgr_phy_disable() here because a single PHY
 	 * won't be diabled until both PHYs request disable.
 	 */
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
 	ret = msm_dsi_host_disable(host);
 	if (ret)
 		pr_err("%s: host %d disable failed, %d\n", __func__, id, ret);
 
-	if (is_dual_dsi && msm_dsi1) {
+	if (is_bonded_dsi && msm_dsi1) {
 		ret = msm_dsi_host_disable(msm_dsi1->host);
 		if (ret)
 			pr_err("%s: host1 disable failed, %d\n", __func__, ret);
@@ -537,7 +530,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
 
-	if (is_dual_dsi && msm_dsi1) {
+	if (is_bonded_dsi && msm_dsi1) {
 		ret = msm_dsi_host_power_off(msm_dsi1->host);
 		if (ret)
 			pr_err("%s: host1 power off failed, %d\n",
@@ -556,15 +549,15 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge,
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct msm_dsi *other_dsi = dsi_mgr_get_other_dsi(id);
 	struct mipi_dsi_host *host = msm_dsi->host;
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 
 	DBG("set mode: " DRM_MODE_FMT, DRM_MODE_ARG(mode));
 
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	msm_dsi_host_set_display_mode(host, adjusted_mode);
-	if (is_dual_dsi && other_dsi)
+	if (is_bonded_dsi && other_dsi)
 		msm_dsi_host_set_display_mode(other_dsi->host, adjusted_mode);
 }
 
@@ -640,15 +633,15 @@ fail:
 
 bool msm_dsi_manager_validate_current_config(u8 id)
 {
-	bool is_dual_dsi = IS_DUAL_DSI();
+	bool is_bonded_dsi = IS_BONDED_DSI();
 
 	/*
-	 * For dual DSI, we only have one drm panel. For this
+	 * For bonded DSI, we only have one drm panel. For this
 	 * use case, we register only one bridge/connector.
 	 * Skip bridge/connector initialisation if it is
-	 * slave-DSI for dual DSI configuration.
+	 * slave-DSI for bonded DSI configuration.
 	 */
-	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) {
+	if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id)) {
 		DBG("Skip bridge registration for slave DSI->id: %d\n", id);
 		return false;
 	}
@@ -740,7 +733,7 @@ int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg)
 	if (!msg->tx_buf || !msg->tx_len)
 		return 0;
 
-	/* In dual master case, panel requires the same commands sent to
+	/* In bonded master case, panel requires the same commands sent to
 	 * both DSI links. Host issues the command trigger to both links
 	 * when DSI_1 calls the cmd transfer function, no matter it happens
 	 * before or after DSI_0 cmd transfer.
@@ -809,9 +802,9 @@ int msm_dsi_manager_register(struct msm_dsi *msm_dsi)
 
 	msm_dsim->dsi[id] = msm_dsi;
 
-	ret = dsi_mgr_parse_dual_dsi(msm_dsi->pdev->dev.of_node, id);
+	ret = dsi_mgr_parse_of(msm_dsi->pdev->dev.of_node, id);
 	if (ret) {
-		pr_err("%s: failed to parse dual DSI info\n", __func__);
+		pr_err("%s: failed to parse OF DSI info\n", __func__);
 		goto fail;
 	}
 
@@ -840,3 +833,12 @@ void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi)
 		msm_dsim->dsi[msm_dsi->id] = NULL;
 }
 
+bool msm_dsi_is_bonded_dsi(struct msm_dsi *msm_dsi)
+{
+	return IS_BONDED_DSI();
+}
+
+bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi)
+{
+	return IS_MASTER_DSI_LINK(msm_dsi->id);
+}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 6ca6bfd4809b..8c65ef6968ca 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -5,6 +5,7 @@
 
 #include <linux/clk-provider.h>
 #include <linux/platform_device.h>
+#include <dt-bindings/phy/phy.h>
 
 #include "dsi_phy.h"
 
@@ -461,6 +462,51 @@ int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
 	return 0;
 }
 
+int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
+	struct msm_dsi_phy_clk_request *clk_req)
+{
+	const unsigned long bit_rate = clk_req->bitclk_rate;
+	const unsigned long esc_rate = clk_req->escclk_rate;
+	s32 ui, ui_x7;
+	s32 tmax, tmin;
+	s32 coeff = 1000; /* Precision, should avoid overflow */
+	s32 temp;
+
+	if (!bit_rate || !esc_rate)
+		return -EINVAL;
+
+	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
+	ui_x7 = ui * 7;
+
+	temp = S_DIV_ROUND_UP(38 * coeff, ui_x7);
+	tmin = max_t(s32, temp, 0);
+	temp = (95 * coeff) / ui_x7;
+	tmax = max_t(s32, temp, 0);
+	timing->clk_prepare = linear_inter(tmax, tmin, 50, 0, false);
+
+	tmin = DIV_ROUND_UP(50 * coeff, ui_x7);
+	tmax = 255;
+	timing->hs_rqst = linear_inter(tmax, tmin, 1, 0, false);
+
+	tmin = DIV_ROUND_UP(100 * coeff, ui_x7) - 1;
+	tmax = 255;
+	timing->hs_exit = linear_inter(tmax, tmin, 10, 0, false);
+
+	tmin = 1;
+	tmax = 32;
+	timing->shared_timings.clk_post = linear_inter(tmax, tmin, 80, 0, false);
+
+	tmin = min_t(s32, 64, S_DIV_ROUND_UP(262 * coeff, ui_x7) - 1);
+	tmax = 64;
+	timing->shared_timings.clk_pre = linear_inter(tmax, tmin, 20, 0, false);
+
+	DBG("%d, %d, %d, %d, %d",
+		timing->shared_timings.clk_pre, timing->shared_timings.clk_post,
+		timing->clk_prepare, timing->hs_exit, timing->hs_rqst);
+
+	return 0;
+}
+
 static int dsi_phy_regulator_init(struct msm_dsi_phy *phy)
 {
 	struct regulator_bulk_data *s = phy->supplies;
@@ -593,6 +639,8 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 	  .data = &dsi_phy_7nm_cfgs },
 	{ .compatible = "qcom,dsi-phy-7nm-8150",
 	  .data = &dsi_phy_7nm_8150_cfgs },
+	{ .compatible = "qcom,sc7280-dsi-phy-7nm",
+	  .data = &dsi_phy_7nm_7280_cfgs },
 #endif
 	{}
 };
@@ -625,17 +673,13 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 {
 	struct msm_dsi_phy *phy;
 	struct device *dev = &pdev->dev;
-	const struct of_device_id *match;
+	u32 phy_type;
 	int ret;
 
 	phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL);
 	if (!phy)
 		return -ENOMEM;
 
-	match = of_match_node(dsi_phy_dt_match, dev->of_node);
-	if (!match)
-		return -ENODEV;
-
 	phy->provided_clocks = devm_kzalloc(dev,
 			struct_size(phy->provided_clocks, hws, NUM_PROVIDED_CLKS),
 			GFP_KERNEL);
@@ -644,7 +688,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 
 	phy->provided_clocks->num = NUM_PROVIDED_CLKS;
 
-	phy->cfg = match->data;
+	phy->cfg = of_device_get_match_data(&pdev->dev);
+	if (!phy->cfg)
+		return -ENODEV;
+
 	phy->pdev = pdev;
 
 	phy->id = dsi_phy_get_id(phy);
@@ -657,6 +704,8 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 
 	phy->regulator_ldo_mode = of_property_read_bool(dev->of_node,
 				"qcom,dsi-phy-regulator-ldo-mode");
+	if (!of_property_read_u32(dev->of_node, "phy-type", &phy_type))
+		phy->cphy_mode = (phy_type == PHY_TYPE_CPHY);
 
 	phy->base = msm_ioremap_size(pdev, "dsi_phy", "DSI_PHY", &phy->base_size);
 	if (IS_ERR(phy->base)) {
@@ -754,7 +803,8 @@ void __exit msm_dsi_phy_driver_unregister(void)
 }
 
 int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
-			struct msm_dsi_phy_clk_request *clk_req)
+			struct msm_dsi_phy_clk_request *clk_req,
+			struct msm_dsi_phy_shared_timings *shared_timings)
 {
 	struct device *dev = &phy->pdev->dev;
 	int ret;
@@ -782,6 +832,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
 		goto phy_en_fail;
 	}
 
+	memcpy(shared_timings, &phy->timing.shared_timings,
+	       sizeof(*shared_timings));
+
 	/*
 	 * Resetting DSI PHY silently changes its PLL registers to reset status,
 	 * which will confuse clock driver and result in wrong output rate of
@@ -821,13 +874,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	dsi_phy_disable_resource(phy);
 }
 
-void msm_dsi_phy_get_shared_timings(struct msm_dsi_phy *phy,
-			struct msm_dsi_phy_shared_timings *shared_timings)
-{
-	memcpy(shared_timings, &phy->timing.shared_timings,
-	       sizeof(*shared_timings));
-}
-
 void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy,
 			     enum msm_dsi_phy_usecase uc)
 {
@@ -835,6 +881,15 @@ void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy,
 		phy->usecase = uc;
 }
 
+/* Returns true if we have to clear DSI_LANE_CTRL.HS_REQ_SEL_PHY */
+bool msm_dsi_phy_set_continuous_clock(struct msm_dsi_phy *phy, bool enable)
+{
+	if (!phy || !phy->cfg->ops.set_continuous_clock)
+		return false;
+
+	return phy->cfg->ops.set_continuous_clock(phy, enable);
+}
+
 int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy,
 	struct clk **byte_clk_provider, struct clk **pixel_clk_provider)
 {
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index 5b0feef87127..b91303ada74f 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -24,6 +24,7 @@ struct msm_dsi_phy_ops {
 	void (*disable)(struct msm_dsi_phy *phy);
 	void (*save_pll_state)(struct msm_dsi_phy *phy);
 	int (*restore_pll_state)(struct msm_dsi_phy *phy);
+	bool (*set_continuous_clock)(struct msm_dsi_phy *phy, bool enable);
 };
 
 struct msm_dsi_phy_cfg {
@@ -51,6 +52,7 @@ extern const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs;
+extern const struct msm_dsi_phy_cfg dsi_phy_7nm_7280_cfgs;
 
 struct msm_dsi_dphy_timing {
 	u32 clk_zero;
@@ -99,6 +101,7 @@ struct msm_dsi_phy {
 
 	enum msm_dsi_phy_usecase usecase;
 	bool regulator_ldo_mode;
+	bool cphy_mode;
 
 	struct clk_hw *vco_hw;
 	bool pll_on;
@@ -119,5 +122,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 				struct msm_dsi_phy_clk_request *clk_req);
 int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
 				struct msm_dsi_phy_clk_request *clk_req);
+int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
+				struct msm_dsi_phy_clk_request *clk_req);
 
 #endif /* __DSI_PHY_H__ */
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index e46b10fc793a..d8128f50b0dd 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -84,7 +84,7 @@ struct dsi_pll_10nm {
 #define to_pll_10nm(x)	container_of(x, struct dsi_pll_10nm, clk_hw)
 
 /*
- * Global list of private DSI PLL struct pointers. We need this for Dual DSI
+ * Global list of private DSI PLL struct pointers. We need this for bonded DSI
  * mode, where the master PLL's clk_ops needs access the slave's private data
  */
 static struct dsi_pll_10nm *pll_10nm_list[DSI_MAX];
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
index a34cf151c517..d13552b2213b 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
@@ -86,7 +86,7 @@ struct dsi_pll_14nm {
 /*
  * Private struct for N1/N2 post-divider clocks. These clocks are similar to
  * the generic clk_divider class of clocks. The only difference is that it
- * also sets the slave DSI PLL's post-dividers if in Dual DSI mode
+ * also sets the slave DSI PLL's post-dividers if in bonded DSI mode
  */
 struct dsi_pll_14nm_postdiv {
 	struct clk_hw hw;
@@ -102,7 +102,7 @@ struct dsi_pll_14nm_postdiv {
 #define to_pll_14nm_postdiv(_hw) container_of(_hw, struct dsi_pll_14nm_postdiv, hw)
 
 /*
- * Global list of private DSI PLL struct pointers. We need this for Dual DSI
+ * Global list of private DSI PLL struct pointers. We need this for bonded DSI
  * mode, where the master PLL's clk_ops needs access the slave's private data
  */
 static struct dsi_pll_14nm *pll_14nm_list[DSI_MAX];
@@ -658,7 +658,7 @@ static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate,
 	val |= value << shift;
 	dsi_phy_write(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, val);
 
-	/* If we're master in dual DSI mode, then the slave PLL's post-dividers
+	/* If we're master in bonded DSI mode, then the slave PLL's post-dividers
 	 * follow the master's post dividers
 	 */
 	if (pll_14nm->phy->usecase == MSM_DSI_PHY_MASTER) {
@@ -1050,7 +1050,7 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = {
 	.reg_cfg = {
 		.num = 1,
 		.regs = {
-			{"vcca", 17000, 32},
+			{"vcca", 73400, 32},
 		},
 	},
 	.ops = {
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 7c23d4c47338..cb297b08458e 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -83,7 +83,7 @@ struct dsi_pll_7nm {
 #define to_pll_7nm(x)	container_of(x, struct dsi_pll_7nm, clk_hw)
 
 /*
- * Global list of private DSI PLL struct pointers. We need this for Dual DSI
+ * Global list of private DSI PLL struct pointers. We need this for bonded DSI
  * mode, where the master PLL's clk_ops needs access the slave's private data
  */
 static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX];
@@ -256,7 +256,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi
 		  (config->frac_div_start & 0x30000) >> 16);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */
+	dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, pll->phy->cphy_mode ? 0x00 : 0x10);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, config->pll_clock_inverters);
 }
 
@@ -642,7 +642,8 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide
 
 	/* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */
 	hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent,
-					  CLK_SET_RATE_PARENT, 1, 8);
+					  CLK_SET_RATE_PARENT, 1,
+					  pll_7nm->phy->cphy_mode ? 7 : 8);
 	if (IS_ERR(hw)) {
 		ret = PTR_ERR(hw);
 		goto fail;
@@ -663,32 +664,47 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide
 	snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id);
 	snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id);
 
-	hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent,
-					  0, 1, 4);
+	if (pll_7nm->phy->cphy_mode)
+		hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 2, 7);
+	else
+		hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 1, 4);
 	if (IS_ERR(hw)) {
 		ret = PTR_ERR(hw);
 		goto fail;
 	}
 
-	snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->phy->id);
-	snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id);
-	snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id);
-	snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id);
-	snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id);
-
-	hw = devm_clk_hw_register_mux(dev, clk_name,
-				 ((const char *[]){
-				 parent, parent2, parent3, parent4
-				 }), 4, 0, pll_7nm->phy->base +
-				 REG_DSI_7nm_PHY_CMN_CLK_CFG1,
-				 0, 2, 0, NULL);
-	if (IS_ERR(hw)) {
-		ret = PTR_ERR(hw);
-		goto fail;
+	/* in CPHY mode, pclk_mux will always have post_out_div as parent
+	 * don't register a pclk_mux clock and just use post_out_div instead
+	 */
+	if (pll_7nm->phy->cphy_mode) {
+		u32 data;
+
+		data = dsi_phy_read(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+		dsi_phy_write(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, data | 3);
+
+		snprintf(parent, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id);
+	} else {
+		snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->phy->id);
+		snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id);
+		snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id);
+		snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id);
+		snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id);
+
+		hw = devm_clk_hw_register_mux(dev, clk_name,
+					((const char *[]){
+					parent, parent2, parent3, parent4
+					}), 4, 0, pll_7nm->phy->base +
+					REG_DSI_7nm_PHY_CMN_CLK_CFG1,
+					0, 2, 0, NULL);
+		if (IS_ERR(hw)) {
+			ret = PTR_ERR(hw);
+			goto fail;
+		}
+
+		snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->phy->id);
 	}
 
 	snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_7nm->phy->id);
-	snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->phy->id);
 
 	/* PIX CLK DIV : DIV_CTRL_7_4*/
 	hw = devm_clk_hw_register_divider(dev, clk_name, parent,
@@ -813,15 +829,21 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	struct msm_dsi_dphy_timing *timing = &phy->timing;
 	void __iomem *base = phy->base;
 	bool less_than_1500_mhz;
-	u32 vreg_ctrl_0, glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0;
+	u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0;
+	u32 glbl_pemph_ctrl_0;
+	u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0;
 	u32 glbl_rescode_top_ctrl, glbl_rescode_bot_ctrl;
 	u32 data;
 
 	DBG("");
 
-	if (msm_dsi_dphy_timing_calc_v4(timing, clk_req)) {
+	if (phy->cphy_mode)
+		ret = msm_dsi_cphy_timing_calc_v4(timing, clk_req);
+	else
+		ret = msm_dsi_dphy_timing_calc_v4(timing, clk_req);
+	if (ret) {
 		DRM_DEV_ERROR(&phy->pdev->dev,
-			"%s: D-PHY timing calculation failed\n", __func__);
+			"%s: PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
 
@@ -842,6 +864,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	/* Alter PHY configurations if data rate less than 1.5GHZ*/
 	less_than_1500_mhz = (clk_req->bitclk_rate <= 1500000000);
 
+	/* For C-PHY, no low power settings for lower clk rate */
+	if (phy->cphy_mode)
+		less_than_1500_mhz = false;
+
 	if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) {
 		vreg_ctrl_0 = less_than_1500_mhz ? 0x53 : 0x52;
 		glbl_rescode_top_ctrl = less_than_1500_mhz ? 0x3d :  0x00;
@@ -856,6 +882,17 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 		glbl_rescode_bot_ctrl = 0x3c;
 	}
 
+	if (phy->cphy_mode) {
+		vreg_ctrl_0 = 0x51;
+		vreg_ctrl_1 = 0x55;
+		glbl_pemph_ctrl_0 = 0x11;
+		lane_ctrl0 = 0x17;
+	} else {
+		vreg_ctrl_1 = 0x5c;
+		glbl_pemph_ctrl_0 = 0x00;
+		lane_ctrl0 = 0x1f;
+	}
+
 	/* de-assert digital and pll power down */
 	data = BIT(6) | BIT(5);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_0, data);
@@ -876,15 +913,22 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CFG0, 0x21);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CFG1, 0x84);
 
+	if (phy->cphy_mode)
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_CTRL, BIT(6));
+
 	/* Enable LDO */
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_VREG_CTRL_0, vreg_ctrl_0);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_VREG_CTRL_1, 0x5c);
+	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_VREG_CTRL_1, vreg_ctrl_1);
+
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_3, 0x00);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_STR_SWI_CAL_SEL_CTRL,
 		      glbl_str_swi_cal_sel_ctrl);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_HSTX_STR_CTRL_0,
 		      glbl_hstx_str_ctrl_0);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_0, 0x00);
+	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_0,
+		      glbl_pemph_ctrl_0);
+	if (phy->cphy_mode)
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_1, 0x01);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_TOP_CTRL,
 		      glbl_rescode_top_ctrl);
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_BOT_CTRL,
@@ -894,10 +938,11 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	/* Remove power down from all blocks */
 	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_0, 0x7f);
 
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0, 0x1f);
+	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0, lane_ctrl0);
 
 	/* Select full-rate mode */
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_2, 0x40);
+	if (!phy->cphy_mode)
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_2, 0x40);
 
 	ret = dsi_7nm_set_usecase(phy);
 	if (ret) {
@@ -907,22 +952,36 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	}
 
 	/* DSI PHY timings */
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0, 0x00);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_1, timing->clk_zero);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_2, timing->clk_prepare);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_3, timing->clk_trail);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4, timing->hs_exit);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5, timing->hs_zero);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6, timing->hs_prepare);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7, timing->hs_trail);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8, timing->hs_rqst);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9, 0x02);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11, 0x00);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_12,
-		      timing->shared_timings.clk_pre);
-	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_13,
-		      timing->shared_timings.clk_post);
+	if (phy->cphy_mode) {
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0, 0x00);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4, timing->hs_exit);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5,
+			timing->shared_timings.clk_pre);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6, timing->clk_prepare);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7,
+			timing->shared_timings.clk_post);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8, timing->hs_rqst);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9, 0x02);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11, 0x00);
+	} else {
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0, 0x00);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_1, timing->clk_zero);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_2, timing->clk_prepare);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_3, timing->clk_trail);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4, timing->hs_exit);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5, timing->hs_zero);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6, timing->hs_prepare);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7, timing->hs_trail);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8, timing->hs_rqst);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9, 0x02);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11, 0x00);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_12,
+			timing->shared_timings.clk_pre);
+		dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_13,
+			timing->shared_timings.clk_post);
+	}
 
 	/* DSI lane settings */
 	dsi_phy_hw_v4_0_lane_settings(phy);
@@ -932,6 +991,21 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	return 0;
 }
 
+static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable)
+{
+	void __iomem *base = phy->base;
+	u32 data;
+
+	data = dsi_phy_read(base + REG_DSI_7nm_PHY_CMN_LANE_CTRL1);
+	if (enable)
+		data |= BIT(5) | BIT(6);
+	else
+		data &= ~(BIT(5) | BIT(6));
+	dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CTRL1, data);
+
+	return enable;
+}
+
 static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 {
 	void __iomem *base = phy->base;
@@ -972,6 +1046,7 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = {
 		.pll_init = dsi_pll_7nm_init,
 		.save_pll_state = dsi_7nm_pll_save_state,
 		.restore_pll_state = dsi_7nm_pll_restore_state,
+		.set_continuous_clock = dsi_7nm_set_continuous_clock,
 	},
 	.min_pll_rate = 600000000UL,
 #ifdef CONFIG_64BIT
@@ -998,9 +1073,36 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = {
 		.pll_init = dsi_pll_7nm_init,
 		.save_pll_state = dsi_7nm_pll_save_state,
 		.restore_pll_state = dsi_7nm_pll_restore_state,
+		.set_continuous_clock = dsi_7nm_set_continuous_clock,
 	},
 	.min_pll_rate = 1000000000UL,
 	.max_pll_rate = 3500000000UL,
 	.io_start = { 0xae94400, 0xae96400 },
 	.num_dsi_phy = 2,
 };
+
+const struct msm_dsi_phy_cfg dsi_phy_7nm_7280_cfgs = {
+	.has_phy_lane = true,
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vdds", 37550, 0},
+		},
+	},
+	.ops = {
+		.enable = dsi_7nm_phy_enable,
+		.disable = dsi_7nm_phy_disable,
+		.pll_init = dsi_pll_7nm_init,
+		.save_pll_state = dsi_7nm_pll_save_state,
+		.restore_pll_state = dsi_7nm_pll_restore_state,
+	},
+	.min_pll_rate = 600000000UL,
+#ifdef CONFIG_64BIT
+	.max_pll_rate = 5000000000ULL,
+#else
+	.max_pll_rate = ULONG_MAX,
+#endif
+	.io_start = { 0xae94400 },
+	.num_dsi_phy = 1,
+	.quirks = DSI_PHY_7NM_QUIRK_V4_1,
+};
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9b8fa2ad0d84..2e6fc185e54d 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -14,7 +14,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_prime.h>
 #include <drm/drm_of.h>
 #include <drm/drm_vblank.h>
@@ -201,6 +200,71 @@ void msm_rmw(void __iomem *addr, u32 mask, u32 or)
 	msm_writel(val | or, addr);
 }
 
+static irqreturn_t msm_irq(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	return kms->funcs->irq(kms);
+}
+
+static void msm_irq_preinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	kms->funcs->irq_preinstall(kms);
+}
+
+static int msm_irq_postinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	if (kms->funcs->irq_postinstall)
+		return kms->funcs->irq_postinstall(kms);
+
+	return 0;
+}
+
+static int msm_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	msm_irq_preinstall(dev);
+
+	ret = request_irq(irq, msm_irq, 0, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	ret = msm_irq_postinstall(dev);
+	if (ret) {
+		free_irq(irq, dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void msm_irq_uninstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	kms->funcs->irq_uninstall(kms);
+	free_irq(kms->irq, dev);
+}
+
 struct msm_vblank_work {
 	struct work_struct work;
 	int crtc_id;
@@ -265,7 +329,7 @@ static int msm_drm_uninit(struct device *dev)
 	}
 
 	/* We must cancel and cleanup any pending vblank enable/disable
-	 * work before drm_irq_uninstall() to avoid work re-enabling an
+	 * work before msm_irq_uninstall() to avoid work re-enabling an
 	 * irq after uninstall has disabled it.
 	 */
 
@@ -294,7 +358,7 @@ static int msm_drm_uninit(struct device *dev)
 	drm_mode_config_cleanup(ddev);
 
 	pm_runtime_get_sync(dev);
-	drm_irq_uninstall(ddev);
+	msm_irq_uninstall(ddev);
 	pm_runtime_put_sync(dev);
 
 	if (kms && kms->funcs)
@@ -539,6 +603,7 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 		if (IS_ERR(priv->event_thread[i].worker)) {
 			ret = PTR_ERR(priv->event_thread[i].worker);
 			DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n");
+			ret = PTR_ERR(priv->event_thread[i].worker);
 			goto err_msm_uninit;
 		}
 
@@ -553,7 +618,7 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 
 	if (kms) {
 		pm_runtime_get_sync(dev);
-		ret = drm_irq_install(ddev, kms->irq);
+		ret = msm_irq_install(ddev, kms->irq);
 		pm_runtime_put_sync(dev);
 		if (ret < 0) {
 			DRM_DEV_ERROR(dev, "failed to install IRQ handler\n");
@@ -662,43 +727,6 @@ static void msm_postclose(struct drm_device *dev, struct drm_file *file)
 	context_close(ctx);
 }
 
-static irqreturn_t msm_irq(int irq, void *arg)
-{
-	struct drm_device *dev = arg;
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	BUG_ON(!kms);
-	return kms->funcs->irq(kms);
-}
-
-static void msm_irq_preinstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	BUG_ON(!kms);
-	kms->funcs->irq_preinstall(kms);
-}
-
-static int msm_irq_postinstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	BUG_ON(!kms);
-
-	if (kms->funcs->irq_postinstall)
-		return kms->funcs->irq_postinstall(kms);
-
-	return 0;
-}
-
-static void msm_irq_uninstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	BUG_ON(!kms);
-	kms->funcs->irq_uninstall(kms);
-}
-
 int msm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -911,6 +939,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	ktime_t timeout = to_ktime(args->timeout);
 	struct msm_gpu_submitqueue *queue;
 	struct msm_gpu *gpu = priv->gpu;
+	struct dma_fence *fence;
 	int ret;
 
 	if (args->pad) {
@@ -925,10 +954,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout,
-		true);
+	/*
+	 * Map submitqueue scoped "seqno" (which is actually an idr key)
+	 * back to underlying dma-fence
+	 *
+	 * The fence is removed from the fence_idr when the submit is
+	 * retired, so if the fence is not found it means there is nothing
+	 * to wait for
+	 */
+	ret = mutex_lock_interruptible(&queue->lock);
+	if (ret)
+		return ret;
+	fence = idr_find(&queue->fence_idr, args->fence);
+	if (fence)
+		fence = dma_fence_get_rcu(fence);
+	mutex_unlock(&queue->lock);
+
+	if (!fence)
+		return 0;
+
+	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
+	if (ret == 0) {
+		ret = -ETIMEDOUT;
+	} else if (ret != -ERESTARTSYS) {
+		ret = 0;
+	}
 
+	dma_fence_put(fence);
 	msm_submitqueue_put(queue);
+
 	return ret;
 }
 
@@ -1004,17 +1058,7 @@ static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_QUERY, msm_ioctl_submitqueue_query, DRM_RENDER_ALLOW),
 };
 
-static const struct file_operations fops = {
-	.owner              = THIS_MODULE,
-	.open               = drm_open,
-	.release            = drm_release,
-	.unlocked_ioctl     = drm_ioctl,
-	.compat_ioctl       = drm_compat_ioctl,
-	.poll               = drm_poll,
-	.read               = drm_read,
-	.llseek             = no_llseek,
-	.mmap               = msm_gem_mmap,
-};
+DEFINE_DRM_GEM_FOPS(fops);
 
 static const struct drm_driver msm_driver = {
 	.driver_features    = DRIVER_GEM |
@@ -1025,16 +1069,12 @@ static const struct drm_driver msm_driver = {
 	.open               = msm_open,
 	.postclose           = msm_postclose,
 	.lastclose          = drm_fb_helper_lastclose,
-	.irq_handler        = msm_irq,
-	.irq_preinstall     = msm_irq_preinstall,
-	.irq_postinstall    = msm_irq_postinstall,
-	.irq_uninstall      = msm_irq_uninstall,
 	.dumb_create        = msm_gem_dumb_create,
 	.dumb_map_offset    = msm_gem_dumb_map_offset,
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import_sg_table = msm_gem_prime_import_sg_table,
-	.gem_prime_mmap     = msm_gem_prime_mmap,
+	.gem_prime_mmap     = drm_gem_prime_mmap,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = msm_debugfs_init,
 #endif
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 1a48a709ffb3..8b005d1ac899 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -309,7 +309,6 @@ void msm_gem_shrinker_cleanup(struct drm_device *dev);
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 int msm_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map);
-int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
@@ -350,7 +349,9 @@ void __exit msm_dsi_unregister(void);
 int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 			 struct drm_encoder *encoder);
 void msm_dsi_snapshot(struct msm_disp_state *disp_state, struct msm_dsi *msm_dsi);
-
+bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi);
+bool msm_dsi_is_bonded_dsi(struct msm_dsi *msm_dsi);
+bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi);
 #else
 static inline void __init msm_dsi_register(void)
 {
@@ -367,7 +368,18 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi,
 static inline void msm_dsi_snapshot(struct msm_disp_state *disp_state, struct msm_dsi *msm_dsi)
 {
 }
-
+static inline bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi)
+{
+	return false;
+}
+static inline bool msm_dsi_is_bonded_dsi(struct msm_dsi *msm_dsi)
+{
+	return false;
+}
+static inline bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi)
+{
+	return false;
+}
 #endif
 
 #ifdef CONFIG_DRM_MSM_DP
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index 227404077e39..0daaeb54ff6f 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -8,13 +8,12 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_prime.h>
 
 #include "msm_drv.h"
 #include "msm_gem.h"
 #include "msm_kms.h"
 
-extern int msm_gem_mmap_obj(struct drm_gem_object *obj,
-					struct vm_area_struct *vma);
 static int msm_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma);
 
 /*
@@ -48,15 +47,8 @@ static int msm_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	struct drm_fb_helper *helper = (struct drm_fb_helper *)info->par;
 	struct msm_fbdev *fbdev = to_msm_fbdev(helper);
 	struct drm_gem_object *bo = msm_framebuffer_bo(fbdev->fb, 0);
-	int ret = 0;
 
-	ret = drm_gem_mmap_obj(bo, bo->size, vma);
-	if (ret) {
-		pr_err("%s:drm_gem_mmap_obj fail\n", __func__);
-		return ret;
-	}
-
-	return msm_gem_mmap_obj(bo, vma);
+	return drm_gem_prime_mmap(bo, vma);
 }
 
 static int msm_fbdev_create(struct drm_fb_helper *helper,
@@ -169,7 +161,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev)
 	}
 
 	/* the fw fb could be anywhere in memory */
-	ret = drm_aperture_remove_framebuffers(false, "msm");
+	ret = drm_aperture_remove_framebuffers(false, dev->driver);
 	if (ret)
 		goto fini;
 
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index cd59a5918038..f2cece542c3f 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -11,7 +11,8 @@
 
 
 struct msm_fence_context *
-msm_fence_context_alloc(struct drm_device *dev, const char *name)
+msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
+		const char *name)
 {
 	struct msm_fence_context *fctx;
 
@@ -22,7 +23,7 @@ msm_fence_context_alloc(struct drm_device *dev, const char *name)
 	fctx->dev = dev;
 	strncpy(fctx->name, name, sizeof(fctx->name));
 	fctx->context = dma_fence_context_alloc(1);
-	init_waitqueue_head(&fctx->event);
+	fctx->fenceptr = fenceptr;
 	spin_lock_init(&fctx->spinlock);
 
 	return fctx;
@@ -35,46 +36,12 @@ void msm_fence_context_free(struct msm_fence_context *fctx)
 
 static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fence)
 {
-	return (int32_t)(fctx->completed_fence - fence) >= 0;
-}
-
-/* legacy path for WAIT_FENCE ioctl: */
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible)
-{
-	int ret;
-
-	if (fence > fctx->last_fence) {
-		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
-				fctx->name, fence, fctx->last_fence);
-		return -EINVAL;
-	}
-
-	if (!timeout) {
-		/* no-wait: */
-		ret = fence_completed(fctx, fence) ? 0 : -EBUSY;
-	} else {
-		unsigned long remaining_jiffies = timeout_to_jiffies(timeout);
-
-		if (interruptible)
-			ret = wait_event_interruptible_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-		else
-			ret = wait_event_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-
-		if (ret == 0) {
-			DBG("timeout waiting for fence: %u (completed: %u)",
-					fence, fctx->completed_fence);
-			ret = -ETIMEDOUT;
-		} else if (ret != -ERESTARTSYS) {
-			ret = 0;
-		}
-	}
-
-	return ret;
+	/*
+	 * Note: Check completed_fence first, as fenceptr is in a write-combine
+	 * mapping, so it will be more expensive to read.
+	 */
+	return (int32_t)(fctx->completed_fence - fence) >= 0 ||
+		(int32_t)(*fctx->fenceptr - fence) >= 0;
 }
 
 /* called from workqueue */
@@ -83,8 +50,6 @@ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 	spin_lock(&fctx->spinlock);
 	fctx->completed_fence = max(fence, fctx->completed_fence);
 	spin_unlock(&fctx->spinlock);
-
-	wake_up_all(&fctx->event);
 }
 
 struct msm_fence {
diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
index 2d9af66dcca5..4783db528bcc 100644
--- a/drivers/gpu/drm/msm/msm_fence.h
+++ b/drivers/gpu/drm/msm/msm_fence.h
@@ -9,23 +9,53 @@
 
 #include "msm_drv.h"
 
+/**
+ * struct msm_fence_context - fence context for gpu
+ *
+ * Each ringbuffer has a single fence context, with the GPU writing an
+ * incrementing fence seqno at the end of each submit
+ */
 struct msm_fence_context {
 	struct drm_device *dev;
+	/** name: human readable name for fence timeline */
 	char name[32];
+	/** context: see dma_fence_context_alloc() */
 	unsigned context;
-	/* last_fence == completed_fence --> no pending work */
-	uint32_t last_fence;          /* last assigned fence */
-	uint32_t completed_fence;     /* last completed fence */
-	wait_queue_head_t event;
+
+	/**
+	 * last_fence:
+	 *
+	 * Last assigned fence, incremented each time a fence is created
+	 * on this fence context.  If last_fence == completed_fence,
+	 * there is no remaining pending work
+	 */
+	uint32_t last_fence;
+
+	/**
+	 * completed_fence:
+	 *
+	 * The last completed fence, updated from the CPU after interrupt
+	 * from GPU
+	 */
+	uint32_t completed_fence;
+
+	/**
+	 * fenceptr:
+	 *
+	 * The address that the GPU directly writes with completed fence
+	 * seqno.  This can be ahead of completed_fence.  We can peek at
+	 * this to see if a fence has already signaled but the CPU hasn't
+	 * gotten around to handling the irq and updating completed_fence
+	 */
+	volatile uint32_t *fenceptr;
+
 	spinlock_t spinlock;
 };
 
 struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
-		const char *name);
+		volatile uint32_t *fenceptr, const char *name);
 void msm_fence_context_free(struct msm_fence_context *fctx);
 
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible);
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
 
 struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 1e8a971a86f2..22308a1b66fc 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -131,7 +131,6 @@ static struct page **get_pages(struct drm_gem_object *obj)
 		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
 			sync_for_device(msm_obj);
 
-		GEM_WARN_ON(msm_obj->active_count);
 		update_inactive(msm_obj);
 	}
 
@@ -218,31 +217,6 @@ static pgprot_t msm_gem_pgprot(struct msm_gem_object *msm_obj, pgprot_t prot)
 	return prot;
 }
 
-int msm_gem_mmap_obj(struct drm_gem_object *obj,
-		struct vm_area_struct *vma)
-{
-	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
-	vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
-
-	return 0;
-}
-
-int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	int ret;
-
-	ret = drm_gem_mmap(filp, vma);
-	if (ret) {
-		DBG("mmap failed: %d", ret);
-		return ret;
-	}
-
-	return msm_gem_mmap_obj(vma->vm_private_data, vma);
-}
-
 static vm_fault_t msm_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -804,41 +778,6 @@ void msm_gem_vunmap(struct drm_gem_object *obj)
 	msm_obj->vaddr = NULL;
 }
 
-/* must be called before _move_to_active().. */
-int msm_gem_sync_object(struct drm_gem_object *obj,
-		struct msm_fence_context *fctx, bool exclusive)
-{
-	struct dma_resv_list *fobj;
-	struct dma_fence *fence;
-	int i, ret;
-
-	fobj = dma_resv_shared_list(obj->resv);
-	if (!fobj || (fobj->shared_count == 0)) {
-		fence = dma_resv_excl_fence(obj->resv);
-		/* don't need to wait on our own fences, since ring is fifo */
-		if (fence && (fence->context != fctx->context)) {
-			ret = dma_fence_wait(fence, true);
-			if (ret)
-				return ret;
-		}
-	}
-
-	if (!exclusive || !fobj)
-		return 0;
-
-	for (i = 0; i < fobj->shared_count; i++) {
-		fence = rcu_dereference_protected(fobj->shared[i],
-						dma_resv_held(obj->resv));
-		if (fence->context != fctx->context) {
-			ret = dma_fence_wait(fence, true);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return 0;
-}
-
 void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -848,14 +787,12 @@ void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 	GEM_WARN_ON(!msm_gem_is_locked(obj));
 	GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED);
 	GEM_WARN_ON(msm_obj->dontneed);
-	GEM_WARN_ON(!msm_obj->sgt);
 
 	if (msm_obj->active_count++ == 0) {
 		mutex_lock(&priv->mm_lock);
 		if (msm_obj->evictable)
 			mark_unevictable(msm_obj);
-		list_del(&msm_obj->mm_list);
-		list_add_tail(&msm_obj->mm_list, &gpu->active_list);
+		list_move_tail(&msm_obj->mm_list, &gpu->active_list);
 		mutex_unlock(&priv->mm_lock);
 	}
 }
@@ -1062,7 +999,7 @@ void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
 }
 #endif
 
-/* don't call directly!  Use drm_gem_object_put_locked() and friends */
+/* don't call directly!  Use drm_gem_object_put() */
 void msm_gem_free_object(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -1114,6 +1051,17 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 	kfree(msm_obj);
 }
 
+static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
+	vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
+
+	return 0;
+}
+
 /* convenience method to construct a GEM buffer object, and userspace handle */
 int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		uint32_t size, uint32_t flags, uint32_t *handle,
@@ -1151,6 +1099,7 @@ static const struct drm_gem_object_funcs msm_gem_object_funcs = {
 	.get_sg_table = msm_gem_prime_get_sg_table,
 	.vmap = msm_gem_prime_vmap,
 	.vunmap = msm_gem_prime_vunmap,
+	.mmap = msm_gem_object_mmap,
 	.vm_ops = &vm_ops,
 };
 
@@ -1183,7 +1132,6 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	msm_obj->flags = flags;
 	msm_obj->madv = MSM_MADV_WILLNEED;
 
-	INIT_LIST_HEAD(&msm_obj->submit_entry);
 	INIT_LIST_HEAD(&msm_obj->vmas);
 
 	*obj = &msm_obj->base;
@@ -1192,8 +1140,7 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	return 0;
 }
 
-static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
-		uint32_t size, uint32_t flags, bool struct_mutex_locked)
+struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32_t flags)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
@@ -1280,26 +1227,10 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	return obj;
 
 fail:
-	if (struct_mutex_locked) {
-		drm_gem_object_put_locked(obj);
-	} else {
-		drm_gem_object_put(obj);
-	}
+	drm_gem_object_put(obj);
 	return ERR_PTR(ret);
 }
 
-struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
-		uint32_t size, uint32_t flags)
-{
-	return _msm_gem_new(dev, size, flags, true);
-}
-
-struct drm_gem_object *msm_gem_new(struct drm_device *dev,
-		uint32_t size, uint32_t flags)
-{
-	return _msm_gem_new(dev, size, flags, false);
-}
-
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt)
 {
@@ -1358,12 +1289,12 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
+void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova, bool locked)
+		struct drm_gem_object **bo, uint64_t *iova)
 {
 	void *vaddr;
-	struct drm_gem_object *obj = _msm_gem_new(dev, size, flags, locked);
+	struct drm_gem_object *obj = msm_gem_new(dev, size, flags);
 	int ret;
 
 	if (IS_ERR(obj))
@@ -1387,42 +1318,21 @@ static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 
 	return vaddr;
 err:
-	if (locked)
-		drm_gem_object_put_locked(obj);
-	else
-		drm_gem_object_put(obj);
+	drm_gem_object_put(obj);
 
 	return ERR_PTR(ret);
 
 }
 
-void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova)
-{
-	return _msm_gem_kernel_new(dev, size, flags, aspace, bo, iova, false);
-}
-
-void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova)
-{
-	return _msm_gem_kernel_new(dev, size, flags, aspace, bo, iova, true);
-}
-
 void msm_gem_kernel_put(struct drm_gem_object *bo,
-		struct msm_gem_address_space *aspace, bool locked)
+		struct msm_gem_address_space *aspace)
 {
 	if (IS_ERR_OR_NULL(bo))
 		return;
 
 	msm_gem_put_vaddr(bo);
 	msm_gem_unpin_iova(bo, aspace);
-
-	if (locked)
-		drm_gem_object_put_locked(bo);
-	else
-		drm_gem_object_put(bo);
+	drm_gem_object_put(bo);
 }
 
 void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...)
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 405f8411e395..e39a8e7ad843 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -9,6 +9,7 @@
 
 #include <linux/kref.h>
 #include <linux/dma-resv.h>
+#include "drm/gpu_scheduler.h"
 #include "msm_drv.h"
 
 /* Make all GEM related WARN_ON()s ratelimited.. when things go wrong they
@@ -87,13 +88,6 @@ struct msm_gem_object {
 	 */
 	struct list_head mm_list;
 
-	/* Transiently in the process of submit ioctl, objects associated
-	 * with the submit are on submit->bo_list.. this only lasts for
-	 * the duration of the ioctl, so one bo can never be on multiple
-	 * submit lists.
-	 */
-	struct list_head submit_entry;
-
 	struct page **pages;
 	struct sg_table *sgt;
 	void *vaddr;
@@ -112,9 +106,6 @@ struct msm_gem_object {
 };
 #define to_msm_bo(x) container_of(x, struct msm_gem_object, base)
 
-int msm_gem_mmap_obj(struct drm_gem_object *obj,
-			struct vm_area_struct *vma);
-int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
 int msm_gem_get_iova(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace, uint64_t *iova);
@@ -143,8 +134,6 @@ void *msm_gem_get_vaddr_active(struct drm_gem_object *obj);
 void msm_gem_put_vaddr_locked(struct drm_gem_object *obj);
 void msm_gem_put_vaddr(struct drm_gem_object *obj);
 int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv);
-int msm_gem_sync_object(struct drm_gem_object *obj,
-		struct msm_fence_context *fctx, bool exclusive);
 void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu);
 void msm_gem_active_put(struct drm_gem_object *obj);
 int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout);
@@ -154,16 +143,11 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		uint32_t size, uint32_t flags, uint32_t *handle, char *name);
 struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 		uint32_t size, uint32_t flags);
-struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
-		uint32_t size, uint32_t flags);
 void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 		uint32_t flags, struct msm_gem_address_space *aspace,
 		struct drm_gem_object **bo, uint64_t *iova);
-void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova);
 void msm_gem_kernel_put(struct drm_gem_object *bo,
-		struct msm_gem_address_space *aspace, bool locked);
+		struct msm_gem_address_space *aspace);
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt);
 __printf(2, 3)
@@ -313,19 +297,34 @@ void msm_gem_vunmap(struct drm_gem_object *obj);
 
 /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
  * associated with the cmdstream submission for synchronization (and
- * make it easier to unwind when things go wrong, etc).  This only
- * lasts for the duration of the submit-ioctl.
+ * make it easier to unwind when things go wrong, etc).
  */
 struct msm_gem_submit {
+	struct drm_sched_job base;
 	struct kref ref;
 	struct drm_device *dev;
 	struct msm_gpu *gpu;
 	struct msm_gem_address_space *aspace;
 	struct list_head node;   /* node in ring submit list */
-	struct list_head bo_list;
 	struct ww_acquire_ctx ticket;
 	uint32_t seqno;		/* Sequence number of the submit on the ring */
-	struct dma_fence *fence;
+
+	/* Array of struct dma_fence * to block on before submitting this job.
+	 */
+	struct xarray deps;
+	unsigned long last_dep;
+
+	/* Hw fence, which is created when the scheduler executes the job, and
+	 * is signaled when the hw finishes (via seqno write from cmdstream)
+	 */
+	struct dma_fence *hw_fence;
+
+	/* Userspace visible fence, which is signaled by the scheduler after
+	 * the hw_fence is signaled.
+	 */
+	struct dma_fence *user_fence;
+
+	int fence_id;       /* key into queue->fence_idr */
 	struct msm_gpu_submitqueue *queue;
 	struct pid *pid;    /* submitting process */
 	bool fault_dumped;  /* Limit devcoredump dumping to one per submit */
@@ -355,6 +354,11 @@ struct msm_gem_submit {
 	} bos[];
 };
 
+static inline struct msm_gem_submit *to_msm_submit(struct drm_sched_job *job)
+{
+	return container_of(job, struct msm_gem_submit, base);
+}
+
 void __msm_gem_submit_destroy(struct kref *kref);
 
 static inline void msm_gem_submit_get(struct msm_gem_submit *submit)
@@ -367,6 +371,8 @@ static inline void msm_gem_submit_put(struct msm_gem_submit *submit)
 	kref_put(&submit->ref, __msm_gem_submit_destroy);
 }
 
+void msm_submit_retire(struct msm_gem_submit *submit);
+
 /* helper to determine of a buffer in submit should be dumped, used for both
  * devcoredump and debugfs cmdstream dumping:
  */
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 9880348a4dc7..fc94e061d6a7 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -39,17 +39,6 @@ void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map)
 	msm_gem_put_vaddr(obj);
 }
 
-int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
-{
-	int ret;
-
-	ret = drm_gem_mmap_obj(obj, obj->size, vma);
-	if (ret < 0)
-		return ret;
-
-	return msm_gem_mmap_obj(vma->vm_private_data, vma);
-}
-
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg)
 {
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 44f84bfd0c0e..fdc5367aecaa 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -23,8 +23,9 @@
 
 /* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
 #define BO_VALID    0x8000   /* is current addr in cmdstream correct/valid? */
-#define BO_LOCKED   0x4000
-#define BO_PINNED   0x2000
+#define BO_LOCKED   0x4000   /* obj lock is held */
+#define BO_ACTIVE   0x2000   /* active refcnt is held */
+#define BO_PINNED   0x1000   /* obj is pinned and on active list */
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gpu *gpu,
@@ -32,32 +33,37 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		uint32_t nr_cmds)
 {
 	struct msm_gem_submit *submit;
-	uint64_t sz = struct_size(submit, bos, nr_bos) +
-				  ((u64)nr_cmds * sizeof(submit->cmd[0]));
+	uint64_t sz;
+	int ret;
+
+	sz = struct_size(submit, bos, nr_bos) +
+			((u64)nr_cmds * sizeof(submit->cmd[0]));
 
 	if (sz > SIZE_MAX)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
-	submit = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	submit = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
 	if (!submit)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
+
+	ret = drm_sched_job_init(&submit->base, &queue->entity, queue);
+	if (ret) {
+		kfree(submit);
+		return ERR_PTR(ret);
+	}
+
+	xa_init_flags(&submit->deps, XA_FLAGS_ALLOC);
 
 	kref_init(&submit->ref);
 	submit->dev = dev;
 	submit->aspace = queue->ctx->aspace;
 	submit->gpu = gpu;
-	submit->fence = NULL;
 	submit->cmd = (void *)&submit->bos[nr_bos];
 	submit->queue = queue;
-	submit->ring = gpu->rb[queue->prio];
+	submit->ring = gpu->rb[queue->ring_nr];
 	submit->fault_dumped = false;
 
-	/* initially, until copy_from_user() and bo lookup succeeds: */
-	submit->nr_bos = 0;
-	submit->nr_cmds = 0;
-
 	INIT_LIST_HEAD(&submit->node);
-	INIT_LIST_HEAD(&submit->bo_list);
 
 	return submit;
 }
@@ -66,9 +72,25 @@ void __msm_gem_submit_destroy(struct kref *kref)
 {
 	struct msm_gem_submit *submit =
 			container_of(kref, struct msm_gem_submit, ref);
+	unsigned long index;
+	struct dma_fence *fence;
 	unsigned i;
 
-	dma_fence_put(submit->fence);
+	if (submit->fence_id) {
+		mutex_lock(&submit->queue->lock);
+		idr_remove(&submit->queue->fence_idr, submit->fence_id);
+		mutex_unlock(&submit->queue->lock);
+	}
+
+	xa_for_each (&submit->deps, index, fence) {
+		dma_fence_put(fence);
+	}
+
+	xa_destroy(&submit->deps);
+
+	dma_fence_put(submit->user_fence);
+	dma_fence_put(submit->hw_fence);
+
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
 
@@ -121,7 +143,6 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 
 	for (i = 0; i < args->nr_bos; i++) {
 		struct drm_gem_object *obj;
-		struct msm_gem_object *msm_obj;
 
 		/* normally use drm_gem_object_lookup(), but for bulk lookup
 		 * all under single table_lock just hit object_idr directly:
@@ -133,20 +154,9 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 			goto out_unlock;
 		}
 
-		msm_obj = to_msm_bo(obj);
-
-		if (!list_empty(&msm_obj->submit_entry)) {
-			DRM_ERROR("handle %u at index %u already on submit list\n",
-					submit->bos[i].handle, i);
-			ret = -EINVAL;
-			goto out_unlock;
-		}
-
 		drm_gem_object_get(obj);
 
-		submit->bos[i].obj = msm_obj;
-
-		list_add_tail(&msm_obj->submit_entry, &submit->bo_list);
+		submit->bos[i].obj = to_msm_bo(obj);
 	}
 
 out_unlock:
@@ -220,21 +230,34 @@ out:
 	return ret;
 }
 
-static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
-		int i, bool backoff)
+/* Unwind bo state, according to cleanup_flags.  In the success case, only
+ * the lock is dropped at the end of the submit (and active/pin ref is dropped
+ * later when the submit is retired).
+ */
+static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
+		unsigned cleanup_flags)
 {
-	struct msm_gem_object *msm_obj = submit->bos[i].obj;
+	struct drm_gem_object *obj = &submit->bos[i].obj->base;
+	unsigned flags = submit->bos[i].flags & cleanup_flags;
 
-	if (submit->bos[i].flags & BO_PINNED)
-		msm_gem_unpin_iova_locked(&msm_obj->base, submit->aspace);
+	if (flags & BO_PINNED)
+		msm_gem_unpin_iova_locked(obj, submit->aspace);
 
-	if (submit->bos[i].flags & BO_LOCKED)
-		dma_resv_unlock(msm_obj->base.resv);
+	if (flags & BO_ACTIVE)
+		msm_gem_active_put(obj);
 
-	if (backoff && !(submit->bos[i].flags & BO_VALID))
-		submit->bos[i].iova = 0;
+	if (flags & BO_LOCKED)
+		dma_resv_unlock(obj->resv);
 
-	submit->bos[i].flags &= ~(BO_LOCKED | BO_PINNED);
+	submit->bos[i].flags &= ~cleanup_flags;
+}
+
+static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
+{
+	submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE | BO_LOCKED);
+
+	if (!(submit->bos[i].flags & BO_VALID))
+		submit->bos[i].iova = 0;
 }
 
 /* This is where we make sure all the bo's are reserved and pin'd: */
@@ -265,11 +288,17 @@ retry:
 	return 0;
 
 fail:
+	if (ret == -EALREADY) {
+		DRM_ERROR("handle %u at index %u already on submit list\n",
+				submit->bos[i].handle, i);
+		ret = -EINVAL;
+	}
+
 	for (; i >= 0; i--)
-		submit_unlock_unpin_bo(submit, i, true);
+		submit_unlock_unpin_bo(submit, i);
 
 	if (slow_locked > 0)
-		submit_unlock_unpin_bo(submit, slow_locked, true);
+		submit_unlock_unpin_bo(submit, slow_locked);
 
 	if (ret == -EDEADLK) {
 		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
@@ -281,6 +310,12 @@ fail:
 			slow_locked = contended;
 			goto retry;
 		}
+
+		/* Not expecting -EALREADY here, if the bo was already
+		 * locked, we should have gotten -EALREADY already from
+		 * the dma_resv_lock_interruptable() call.
+		 */
+		WARN_ON_ONCE(ret == -EALREADY);
 	}
 
 	return ret;
@@ -291,7 +326,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 	int i, ret = 0;
 
 	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 		bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;
 
 		if (!write) {
@@ -300,8 +335,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 			 * strange place to call it.  OTOH this is a
 			 * convenient can-fail point to hook it in.
 			 */
-			ret = dma_resv_reserve_shared(msm_obj->base.resv,
-								1);
+			ret = dma_resv_reserve_shared(obj->resv, 1);
 			if (ret)
 				return ret;
 		}
@@ -309,7 +343,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 		if (no_implicit)
 			continue;
 
-		ret = msm_gem_sync_object(&msm_obj->base, submit->ring->fctx,
+		ret = drm_gem_fence_array_add_implicit(&submit->deps, obj,
 			write);
 		if (ret)
 			break;
@@ -324,12 +358,24 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 
 	submit->valid = true;
 
+	/*
+	 * Increment active_count first, so if under memory pressure, we
+	 * don't inadvertently evict a bo needed by the submit in order
+	 * to pin an earlier bo in the same submit.
+	 */
 	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		msm_gem_active_get(obj, submit->gpu);
+		submit->bos[i].flags |= BO_ACTIVE;
+	}
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 		uint64_t iova;
 
 		/* if locking succeeded, pin bo: */
-		ret = msm_gem_get_and_pin_iova_locked(&msm_obj->base,
+		ret = msm_gem_get_and_pin_iova_locked(obj,
 				submit->aspace, &iova);
 
 		if (ret)
@@ -350,6 +396,20 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 	return ret;
 }
 
+static void submit_attach_object_fences(struct msm_gem_submit *submit)
+{
+	int i;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
+			dma_resv_add_excl_fence(obj->resv, submit->user_fence);
+		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
+			dma_resv_add_shared_fence(obj->resv, submit->user_fence);
+	}
+}
+
 static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
 		struct msm_gem_object **obj, uint64_t *iova, bool *valid)
 {
@@ -444,18 +504,39 @@ out:
 	return ret;
 }
 
-static void submit_cleanup(struct msm_gem_submit *submit)
+/* Cleanup submit at end of ioctl.  In the error case, this also drops
+ * references, unpins, and drops active refcnt.  In the non-error case,
+ * this is done when the submit is retired.
+ */
+static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 {
+	unsigned cleanup_flags = BO_LOCKED;
 	unsigned i;
 
+	if (error)
+		cleanup_flags |= BO_PINNED | BO_ACTIVE;
+
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
-		submit_unlock_unpin_bo(submit, i, false);
-		list_del_init(&msm_obj->submit_entry);
-		drm_gem_object_put_locked(&msm_obj->base);
+		submit_cleanup_bo(submit, i, cleanup_flags);
+		if (error)
+			drm_gem_object_put(&msm_obj->base);
 	}
 }
 
+void msm_submit_retire(struct msm_gem_submit *submit)
+{
+	int i;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		msm_gem_lock(obj);
+		submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE);
+		msm_gem_unlock(obj);
+		drm_gem_object_put(obj);
+	}
+}
 
 struct msm_submit_post_dep {
 	struct drm_syncobj *syncobj;
@@ -463,12 +544,12 @@ struct msm_submit_post_dep {
 	struct dma_fence_chain *chain;
 };
 
-static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
-                                          struct drm_file *file,
-                                          uint64_t in_syncobjs_addr,
-                                          uint32_t nr_in_syncobjs,
-                                          size_t syncobj_stride,
-                                          struct msm_ringbuffer *ring)
+static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit,
+                                           struct drm_file *file,
+                                           uint64_t in_syncobjs_addr,
+                                           uint32_t nr_in_syncobjs,
+                                           size_t syncobj_stride,
+                                           struct msm_ringbuffer *ring)
 {
 	struct drm_syncobj **syncobjs = NULL;
 	struct drm_msm_gem_submit_syncobj syncobj_desc = {0};
@@ -492,7 +573,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
 		}
 
 		if (syncobj_desc.point &&
-		    !drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) {
+		    !drm_core_check_feature(submit->dev, DRIVER_SYNCOBJ_TIMELINE)) {
 			ret = -EOPNOTSUPP;
 			break;
 		}
@@ -507,10 +588,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
 		if (ret)
 			break;
 
-		if (!dma_fence_match_context(fence, ring->fctx->context))
-			ret = dma_fence_wait(fence, true);
-
-		dma_fence_put(fence);
+		ret = drm_gem_fence_array_add(&submit->deps, fence);
 		if (ret)
 			break;
 
@@ -587,9 +665,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev,
 				break;
 			}
 
-			post_deps[i].chain =
-				kmalloc(sizeof(*post_deps[i].chain),
-				        GFP_KERNEL);
+			post_deps[i].chain = dma_fence_chain_alloc();
 			if (!post_deps[i].chain) {
 				ret = -ENOMEM;
 				break;
@@ -606,7 +682,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev,
 
 	if (ret) {
 		for (j = 0; j <= i; ++j) {
-			kfree(post_deps[j].chain);
+			dma_fence_chain_free(post_deps[j].chain);
 			if (post_deps[j].syncobj)
 				drm_syncobj_put(post_deps[j].syncobj);
 		}
@@ -643,9 +719,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_msm_gem_submit *args = data;
 	struct msm_file_private *ctx = file->driver_priv;
-	struct msm_gem_submit *submit;
+	struct msm_gem_submit *submit = NULL;
 	struct msm_gpu *gpu = priv->gpu;
-	struct sync_file *sync_file = NULL;
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
 	struct msm_submit_post_dep *post_deps = NULL;
@@ -655,6 +730,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	bool has_ww_ticket = false;
 	unsigned i;
 	int ret, submitid;
+
 	if (!gpu)
 		return -ENXIO;
 
@@ -683,38 +759,59 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	/* Get a unique identifier for the submission for logging purposes */
 	submitid = atomic_inc_return(&ident) - 1;
 
-	ring = gpu->rb[queue->prio];
+	ring = gpu->rb[queue->ring_nr];
 	trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid,
 		args->nr_bos, args->nr_cmds);
 
+	ret = mutex_lock_interruptible(&queue->lock);
+	if (ret)
+		goto out_post_unlock;
+
+	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
+		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
+		if (out_fence_fd < 0) {
+			ret = out_fence_fd;
+			goto out_unlock;
+		}
+	}
+
+	submit = submit_create(dev, gpu, queue, args->nr_bos,
+		args->nr_cmds);
+	if (IS_ERR(submit)) {
+		ret = PTR_ERR(submit);
+		goto out_unlock;
+	}
+
+	submit->pid = pid;
+	submit->ident = submitid;
+
+	if (args->flags & MSM_SUBMIT_SUDO)
+		submit->in_rb = true;
+
 	if (args->flags & MSM_SUBMIT_FENCE_FD_IN) {
 		struct dma_fence *in_fence;
 
 		in_fence = sync_file_get_fence(args->fence_fd);
 
-		if (!in_fence)
-			return -EINVAL;
-
-		/*
-		 * Wait if the fence is from a foreign context, or if the fence
-		 * array contains any fence from a foreign context.
-		 */
-		ret = 0;
-		if (!dma_fence_match_context(in_fence, ring->fctx->context))
-			ret = dma_fence_wait(in_fence, true);
+		if (!in_fence) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
 
-		dma_fence_put(in_fence);
+		ret = drm_gem_fence_array_add(&submit->deps, in_fence);
 		if (ret)
-			return ret;
+			goto out_unlock;
 	}
 
 	if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) {
-		syncobjs_to_reset = msm_wait_deps(dev, file,
-		                                  args->in_syncobjs,
-		                                  args->nr_in_syncobjs,
-		                                  args->syncobj_stride, ring);
-		if (IS_ERR(syncobjs_to_reset))
-			return PTR_ERR(syncobjs_to_reset);
+		syncobjs_to_reset = msm_parse_deps(submit, file,
+		                                   args->in_syncobjs,
+		                                   args->nr_in_syncobjs,
+		                                   args->syncobj_stride, ring);
+		if (IS_ERR(syncobjs_to_reset)) {
+			ret = PTR_ERR(syncobjs_to_reset);
+			goto out_unlock;
+		}
 	}
 
 	if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) {
@@ -724,51 +821,17 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		                                args->syncobj_stride);
 		if (IS_ERR(post_deps)) {
 			ret = PTR_ERR(post_deps);
-			goto out_post_unlock;
-		}
-	}
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		goto out_post_unlock;
-
-	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
-		if (out_fence_fd < 0) {
-			ret = out_fence_fd;
 			goto out_unlock;
 		}
 	}
 
-	submit = submit_create(dev, gpu, queue, args->nr_bos,
-		args->nr_cmds);
-	if (!submit) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
-
-	submit->pid = pid;
-	submit->ident = submitid;
-
-	if (args->flags & MSM_SUBMIT_SUDO)
-		submit->in_rb = true;
-
 	ret = submit_lookup_objects(submit, args, file);
 	if (ret)
-		goto out_pre_pm;
+		goto out;
 
 	ret = submit_lookup_cmds(submit, args, file);
 	if (ret)
-		goto out_pre_pm;
-
-	/*
-	 * Thanks to dev_pm_opp opp_table_lock interactions with mm->mmap_sem
-	 * in the resume path, we need to to rpm get before we lock objs.
-	 * Which unfortunately might involve powering up the GPU sooner than
-	 * is necessary.  But at least in the explicit fencing case, we will
-	 * have already done all the fence waiting.
-	 */
-	pm_runtime_get_sync(&gpu->pdev->dev);
+		goto out;
 
 	/* copy_*_user while holding a ww ticket upsets lockdep */
 	ww_acquire_init(&submit->ticket, &reservation_ww_class);
@@ -815,47 +878,54 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit->nr_cmds = i;
 
-	submit->fence = msm_fence_alloc(ring->fctx);
-	if (IS_ERR(submit->fence)) {
-		ret = PTR_ERR(submit->fence);
-		submit->fence = NULL;
+	submit->user_fence = dma_fence_get(&submit->base.s_fence->finished);
+
+	/*
+	 * Allocate an id which can be used by WAIT_FENCE ioctl to map back
+	 * to the underlying fence.
+	 */
+	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
+			submit->user_fence, 0, INT_MAX, GFP_KERNEL);
+	if (submit->fence_id < 0) {
+		ret = submit->fence_id = 0;
+		submit->fence_id = 0;
 		goto out;
 	}
 
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		sync_file = sync_file_create(submit->fence);
+		struct sync_file *sync_file = sync_file_create(submit->user_fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 			goto out;
 		}
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
-	msm_gpu_submit(gpu, submit);
+	submit_attach_object_fences(submit);
 
-	args->fence = submit->fence->seqno;
+	/* The scheduler owns a ref now: */
+	msm_gem_submit_get(submit);
 
-	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		fd_install(out_fence_fd, sync_file->file);
-		args->fence_fd = out_fence_fd;
-	}
+	drm_sched_entity_push_job(&submit->base, &queue->entity);
+
+	args->fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
-	                      submit->fence);
+	                      submit->user_fence);
 
 
 out:
-	pm_runtime_put(&gpu->pdev->dev);
-out_pre_pm:
-	submit_cleanup(submit);
+	submit_cleanup(submit, !!ret);
 	if (has_ww_ticket)
 		ww_acquire_fini(&submit->ticket);
-	msm_gem_submit_put(submit);
 out_unlock:
 	if (ret && (out_fence_fd >= 0))
 		put_unused_fd(out_fence_fd);
-	mutex_unlock(&dev->struct_mutex);
-
+	mutex_unlock(&queue->lock);
+	if (submit)
+		msm_gem_submit_put(submit);
 out_post_unlock:
 	if (!IS_ERR_OR_NULL(post_deps)) {
 		for (i = 0; i < args->nr_out_syncobjs; ++i) {
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0ebf7bc6ad09..8a3a592da3a4 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -13,8 +13,6 @@
 
 #include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
-#include <linux/devfreq.h>
-#include <linux/devfreq_cooling.h>
 #include <linux/devcoredump.h>
 #include <linux/sched/task.h>
 
@@ -22,106 +20,6 @@
  * Power Management:
  */
 
-static int msm_devfreq_target(struct device *dev, unsigned long *freq,
-		u32 flags)
-{
-	struct msm_gpu *gpu = dev_to_gpu(dev);
-	struct dev_pm_opp *opp;
-
-	opp = devfreq_recommended_opp(dev, freq, flags);
-
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
-
-	trace_msm_gpu_freq_change(dev_pm_opp_get_freq(opp));
-
-	if (gpu->funcs->gpu_set_freq)
-		gpu->funcs->gpu_set_freq(gpu, opp);
-	else
-		clk_set_rate(gpu->core_clk, *freq);
-
-	dev_pm_opp_put(opp);
-
-	return 0;
-}
-
-static int msm_devfreq_get_dev_status(struct device *dev,
-		struct devfreq_dev_status *status)
-{
-	struct msm_gpu *gpu = dev_to_gpu(dev);
-	ktime_t time;
-
-	if (gpu->funcs->gpu_get_freq)
-		status->current_frequency = gpu->funcs->gpu_get_freq(gpu);
-	else
-		status->current_frequency = clk_get_rate(gpu->core_clk);
-
-	status->busy_time = gpu->funcs->gpu_busy(gpu);
-
-	time = ktime_get();
-	status->total_time = ktime_us_delta(time, gpu->devfreq.time);
-	gpu->devfreq.time = time;
-
-	return 0;
-}
-
-static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq)
-{
-	struct msm_gpu *gpu = dev_to_gpu(dev);
-
-	if (gpu->funcs->gpu_get_freq)
-		*freq = gpu->funcs->gpu_get_freq(gpu);
-	else
-		*freq = clk_get_rate(gpu->core_clk);
-
-	return 0;
-}
-
-static struct devfreq_dev_profile msm_devfreq_profile = {
-	.polling_ms = 10,
-	.target = msm_devfreq_target,
-	.get_dev_status = msm_devfreq_get_dev_status,
-	.get_cur_freq = msm_devfreq_get_cur_freq,
-};
-
-static void msm_devfreq_init(struct msm_gpu *gpu)
-{
-	/* We need target support to do devfreq */
-	if (!gpu->funcs->gpu_busy)
-		return;
-
-	msm_devfreq_profile.initial_freq = gpu->fast_rate;
-
-	/*
-	 * Don't set the freq_table or max_state and let devfreq build the table
-	 * from OPP
-	 * After a deferred probe, these may have be left to non-zero values,
-	 * so set them back to zero before creating the devfreq device
-	 */
-	msm_devfreq_profile.freq_table = NULL;
-	msm_devfreq_profile.max_state = 0;
-
-	gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev,
-			&msm_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND,
-			NULL);
-
-	if (IS_ERR(gpu->devfreq.devfreq)) {
-		DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
-		gpu->devfreq.devfreq = NULL;
-		return;
-	}
-
-	devfreq_suspend_device(gpu->devfreq.devfreq);
-
-	gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node,
-			gpu->devfreq.devfreq);
-	if (IS_ERR(gpu->cooling)) {
-		DRM_DEV_ERROR(&gpu->pdev->dev,
-				"Couldn't register GPU cooling device\n");
-		gpu->cooling = NULL;
-	}
-}
-
 static int enable_pwrrail(struct msm_gpu *gpu)
 {
 	struct drm_device *dev = gpu->dev;
@@ -196,14 +94,6 @@ static int disable_axi(struct msm_gpu *gpu)
 	return 0;
 }
 
-void msm_gpu_resume_devfreq(struct msm_gpu *gpu)
-{
-	gpu->devfreq.busy_cycles = 0;
-	gpu->devfreq.time = ktime_get();
-
-	devfreq_resume_device(gpu->devfreq.devfreq);
-}
-
 int msm_gpu_pm_resume(struct msm_gpu *gpu)
 {
 	int ret;
@@ -223,7 +113,7 @@ int msm_gpu_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	msm_gpu_resume_devfreq(gpu);
+	msm_devfreq_resume(gpu);
 
 	gpu->needs_hw_init = true;
 
@@ -237,7 +127,7 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu)
 	DBG("%s", gpu->name);
 	trace_msm_gpu_suspend(0);
 
-	devfreq_suspend_device(gpu->devfreq.devfreq);
+	msm_devfreq_suspend(gpu);
 
 	ret = disable_axi(gpu);
 	if (ret)
@@ -278,16 +168,18 @@ static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		uint32_t fence)
 {
 	struct msm_gem_submit *submit;
+	unsigned long flags;
 
-	spin_lock(&ring->submit_lock);
+	spin_lock_irqsave(&ring->submit_lock, flags);
 	list_for_each_entry(submit, &ring->submits, node) {
 		if (submit->seqno > fence)
 			break;
 
 		msm_update_fence(submit->ring->fctx,
-			submit->fence->seqno);
+			submit->hw_fence->seqno);
+		dma_fence_signal(submit->hw_fence);
 	}
-	spin_unlock(&ring->submit_lock);
+	spin_unlock_irqrestore(&ring->submit_lock, flags);
 }
 
 #ifdef CONFIG_DEV_COREDUMP
@@ -443,15 +335,16 @@ static struct msm_gem_submit *
 find_submit(struct msm_ringbuffer *ring, uint32_t fence)
 {
 	struct msm_gem_submit *submit;
+	unsigned long flags;
 
-	spin_lock(&ring->submit_lock);
+	spin_lock_irqsave(&ring->submit_lock, flags);
 	list_for_each_entry(submit, &ring->submits, node) {
 		if (submit->seqno == fence) {
-			spin_unlock(&ring->submit_lock);
+			spin_unlock_irqrestore(&ring->submit_lock, flags);
 			return submit;
 		}
 	}
-	spin_unlock(&ring->submit_lock);
+	spin_unlock_irqrestore(&ring->submit_lock, flags);
 
 	return NULL;
 }
@@ -487,10 +380,6 @@ static void recover_worker(struct kthread_work *work)
 			put_task_struct(task);
 		}
 
-		/* msm_rd_dump_submit() needs bo locked to dump: */
-		for (i = 0; i < submit->nr_bos; i++)
-			msm_gem_lock(&submit->bos[i].obj->base);
-
 		if (comm && cmd) {
 			DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
 				gpu->name, comm, cmd);
@@ -500,9 +389,6 @@ static void recover_worker(struct kthread_work *work)
 		} else {
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
 		}
-
-		for (i = 0; i < submit->nr_bos; i++)
-			msm_gem_unlock(&submit->bos[i].obj->base);
 	}
 
 	/* Record the crash state */
@@ -547,11 +433,12 @@ static void recover_worker(struct kthread_work *work)
 		 */
 		for (i = 0; i < gpu->nr_rings; i++) {
 			struct msm_ringbuffer *ring = gpu->rb[i];
+			unsigned long flags;
 
-			spin_lock(&ring->submit_lock);
+			spin_lock_irqsave(&ring->submit_lock, flags);
 			list_for_each_entry(submit, &ring->submits, node)
 				gpu->funcs->submit(gpu, submit);
-			spin_unlock(&ring->submit_lock);
+			spin_unlock_irqrestore(&ring->submit_lock, flags);
 		}
 	}
 
@@ -641,7 +528,7 @@ static void hangcheck_handler(struct timer_list *t)
 		hangcheck_timer_reset(gpu);
 
 	/* workaround for missing irq: */
-	kthread_queue_work(gpu->worker, &gpu->retire_work);
+	msm_gpu_retire(gpu);
 }
 
 /*
@@ -752,7 +639,7 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
 	volatile struct msm_gpu_submit_stats *stats;
 	u64 elapsed, clock = 0;
-	int i;
+	unsigned long flags;
 
 	stats = &ring->memptrs->stats[index];
 	/* Convert 19.2Mhz alwayson ticks to nanoseconds for elapsed time */
@@ -768,22 +655,22 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	trace_msm_gpu_submit_retired(submit, elapsed, clock,
 		stats->alwayson_start, stats->alwayson_end);
 
-	for (i = 0; i < submit->nr_bos; i++) {
-		struct drm_gem_object *obj = &submit->bos[i].obj->base;
-
-		msm_gem_lock(obj);
-		msm_gem_active_put(obj);
-		msm_gem_unpin_iova_locked(obj, submit->aspace);
-		msm_gem_unlock(obj);
-		drm_gem_object_put(obj);
-	}
+	msm_submit_retire(submit);
 
 	pm_runtime_mark_last_busy(&gpu->pdev->dev);
 	pm_runtime_put_autosuspend(&gpu->pdev->dev);
 
-	spin_lock(&ring->submit_lock);
+	spin_lock_irqsave(&ring->submit_lock, flags);
 	list_del(&submit->node);
-	spin_unlock(&ring->submit_lock);
+	spin_unlock_irqrestore(&ring->submit_lock, flags);
+
+	/* Update devfreq on transition from active->idle: */
+	mutex_lock(&gpu->active_lock);
+	gpu->active_submits--;
+	WARN_ON(gpu->active_submits < 0);
+	if (!gpu->active_submits)
+		msm_devfreq_idle(gpu);
+	mutex_unlock(&gpu->active_lock);
 
 	msm_gem_submit_put(submit);
 }
@@ -798,18 +685,19 @@ static void retire_submits(struct msm_gpu *gpu)
 
 		while (true) {
 			struct msm_gem_submit *submit = NULL;
+			unsigned long flags;
 
-			spin_lock(&ring->submit_lock);
+			spin_lock_irqsave(&ring->submit_lock, flags);
 			submit = list_first_entry_or_null(&ring->submits,
 					struct msm_gem_submit, node);
-			spin_unlock(&ring->submit_lock);
+			spin_unlock_irqrestore(&ring->submit_lock, flags);
 
 			/*
 			 * If no submit, we are done.  If submit->fence hasn't
 			 * been signalled, then later submits are not signalled
 			 * either, so we are also done.
 			 */
-			if (submit && dma_fence_is_signaled(submit->fence)) {
+			if (submit && dma_fence_is_signaled(submit->hw_fence)) {
 				retire_submit(gpu, ring, submit);
 			} else {
 				break;
@@ -821,10 +709,6 @@ static void retire_submits(struct msm_gpu *gpu)
 static void retire_worker(struct kthread_work *work)
 {
 	struct msm_gpu *gpu = container_of(work, struct msm_gpu, retire_work);
-	int i;
-
-	for (i = 0; i < gpu->nr_rings; i++)
-		update_fences(gpu, gpu->rb[i], gpu->rb[i]->memptrs->fence);
 
 	retire_submits(gpu);
 }
@@ -832,6 +716,11 @@ static void retire_worker(struct kthread_work *work)
 /* call from irq handler to schedule work to retire bo's */
 void msm_gpu_retire(struct msm_gpu *gpu)
 {
+	int i;
+
+	for (i = 0; i < gpu->nr_rings; i++)
+		update_fences(gpu, gpu->rb[i], gpu->rb[i]->memptrs->fence);
+
 	kthread_queue_work(gpu->worker, &gpu->retire_work);
 	update_sw_cntrs(gpu);
 }
@@ -842,7 +731,7 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct drm_device *dev = gpu->dev;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = submit->ring;
-	int i;
+	unsigned long flags;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
@@ -856,32 +745,22 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 
 	update_sw_cntrs(gpu);
 
-	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
-		struct drm_gem_object *drm_obj = &msm_obj->base;
-		uint64_t iova;
-
-		/* submit takes a reference to the bo and iova until retired: */
-		drm_gem_object_get(&msm_obj->base);
-		msm_gem_get_and_pin_iova_locked(&msm_obj->base, submit->aspace, &iova);
-
-		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(drm_obj->resv, submit->fence);
-		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
-			dma_resv_add_shared_fence(drm_obj->resv, submit->fence);
-
-		msm_gem_active_get(drm_obj, gpu);
-	}
-
 	/*
 	 * ring->submits holds a ref to the submit, to deal with the case
 	 * that a submit completes before msm_ioctl_gem_submit() returns.
 	 */
 	msm_gem_submit_get(submit);
 
-	spin_lock(&ring->submit_lock);
+	spin_lock_irqsave(&ring->submit_lock, flags);
 	list_add_tail(&submit->node, &ring->submits);
-	spin_unlock(&ring->submit_lock);
+	spin_unlock_irqrestore(&ring->submit_lock, flags);
+
+	/* Update devfreq on transition from idle->active: */
+	mutex_lock(&gpu->active_lock);
+	if (!gpu->active_submits)
+		msm_devfreq_active(gpu);
+	gpu->active_submits++;
+	mutex_unlock(&gpu->active_lock);
 
 	gpu->funcs->submit(gpu, submit);
 	priv->lastctx = submit->queue->ctx;
@@ -968,6 +847,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	sched_set_fifo_low(gpu->worker->task);
 
 	INIT_LIST_HEAD(&gpu->active_list);
+	mutex_init(&gpu->active_lock);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
 	kthread_init_work(&gpu->fault_work, fault_worker);
@@ -1078,7 +958,7 @@ fail:
 		gpu->rb[i] = NULL;
 	}
 
-	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace);
 
 	platform_set_drvdata(pdev, NULL);
 	return ret;
@@ -1097,7 +977,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		gpu->rb[i] = NULL;
 	}
 
-	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
@@ -1108,5 +988,5 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		kthread_destroy_worker(gpu->worker);
 	}
 
-	devfreq_cooling_unregister(gpu->cooling);
+	msm_devfreq_cleanup(gpu);
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ef41ec09f59c..0e4b45bff2e6 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -80,6 +80,40 @@ struct msm_gpu_fault_info {
 	const char *block;
 };
 
+/**
+ * struct msm_gpu_devfreq - devfreq related state
+ */
+struct msm_gpu_devfreq {
+	/** devfreq: devfreq instance */
+	struct devfreq *devfreq;
+
+	/**
+	 * busy_cycles:
+	 *
+	 * Used by implementation of gpu->gpu_busy() to track the last
+	 * busy counter value, for calculating elapsed busy cycles since
+	 * last sampling period.
+	 */
+	u64 busy_cycles;
+
+	/** time: Time of last sampling period. */
+	ktime_t time;
+
+	/** idle_time: Time of last transition to idle: */
+	ktime_t idle_time;
+
+	/**
+	 * idle_freq:
+	 *
+	 * Shadow frequency used while the GPU is idle.  From the PoV of
+	 * the devfreq governor, we are continuing to sample busyness and
+	 * adjust frequency while the GPU is idle, but we use this shadow
+	 * value as the GPU is actually clamped to minimum frequency while
+	 * it is inactive.
+	 */
+	unsigned long idle_freq;
+};
+
 struct msm_gpu {
 	const char *name;
 	struct drm_device *dev;
@@ -109,6 +143,19 @@ struct msm_gpu {
 	 */
 	struct list_head active_list;
 
+	/**
+	 * active_submits:
+	 *
+	 * The number of submitted but not yet retired submits, used to
+	 * determine transitions between active and idle.
+	 *
+	 * Protected by lock
+	 */
+	int active_submits;
+
+	/** lock: protects active_submits and idle/active transitions */
+	struct mutex active_lock;
+
 	/* does gpu need hw_init? */
 	bool needs_hw_init;
 
@@ -151,11 +198,7 @@ struct msm_gpu {
 
 	struct drm_gem_object *memptrs_bo;
 
-	struct {
-		struct devfreq *devfreq;
-		u64 busy_cycles;
-		ktime_t time;
-	} devfreq;
+	struct msm_gpu_devfreq devfreq;
 
 	uint32_t suspend_count;
 
@@ -207,14 +250,90 @@ struct msm_gpu_perfcntr {
 	const char *name;
 };
 
+/*
+ * The number of priority levels provided by drm gpu scheduler.  The
+ * DRM_SCHED_PRIORITY_KERNEL priority level is treated specially in some
+ * cases, so we don't use it (no need for kernel generated jobs).
+ */
+#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_MIN)
+
+/**
+ * msm_gpu_convert_priority - Map userspace priority to ring # and sched priority
+ *
+ * @gpu:        the gpu instance
+ * @prio:       the userspace priority level
+ * @ring_nr:    [out] the ringbuffer the userspace priority maps to
+ * @sched_prio: [out] the gpu scheduler priority level which the userspace
+ *              priority maps to
+ *
+ * With drm/scheduler providing it's own level of prioritization, our total
+ * number of available priority levels is (nr_rings * NR_SCHED_PRIORITIES).
+ * Each ring is associated with it's own scheduler instance.  However, our
+ * UABI is that lower numerical values are higher priority.  So mapping the
+ * single userspace priority level into ring_nr and sched_prio takes some
+ * care.  The userspace provided priority (when a submitqueue is created)
+ * is mapped to ring nr and scheduler priority as such:
+ *
+ *   ring_nr    = userspace_prio / NR_SCHED_PRIORITIES
+ *   sched_prio = NR_SCHED_PRIORITIES -
+ *                (userspace_prio % NR_SCHED_PRIORITIES) - 1
+ *
+ * This allows generations without preemption (nr_rings==1) to have some
+ * amount of prioritization, and provides more priority levels for gens
+ * that do have preemption.
+ */
+static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
+		unsigned *ring_nr, enum drm_sched_priority *sched_prio)
+{
+	unsigned rn, sp;
+
+	rn = div_u64_rem(prio, NR_SCHED_PRIORITIES, &sp);
+
+	/* invert sched priority to map to higher-numeric-is-higher-
+	 * priority convention
+	 */
+	sp = NR_SCHED_PRIORITIES - sp - 1;
+
+	if (rn >= gpu->nr_rings)
+		return -EINVAL;
+
+	*ring_nr = rn;
+	*sched_prio = sp;
+
+	return 0;
+}
+
+/**
+ * A submitqueue is associated with a gl context or vk queue (or equiv)
+ * in userspace.
+ *
+ * @id:        userspace id for the submitqueue, unique within the drm_file
+ * @flags:     userspace flags for the submitqueue, specified at creation
+ *             (currently unusued)
+ * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
+ *             by the submitqueue's priority
+ * @faults:    the number of GPU hangs associated with this submitqueue
+ * @ctx:       the per-drm_file context associated with the submitqueue (ie.
+ *             which set of pgtables do submits jobs associated with the
+ *             submitqueue use)
+ * @node:      node in the context's list of submitqueues
+ * @fence_idr: maps fence-id to dma_fence for userspace visible fence
+ *             seqno, protected by submitqueue lock
+ * @lock:      submitqueue lock
+ * @ref:       reference count
+ * @entity: the submit job-queue
+ */
 struct msm_gpu_submitqueue {
 	int id;
 	u32 flags;
-	u32 prio;
+	u32 ring_nr;
 	int faults;
 	struct msm_file_private *ctx;
 	struct list_head node;
+	struct idr fence_idr;
+	struct mutex lock;
 	struct kref ref;
+	struct drm_sched_entity entity;
 };
 
 struct msm_gpu_state_bo {
@@ -301,7 +420,13 @@ static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
 
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
-void msm_gpu_resume_devfreq(struct msm_gpu *gpu);
+
+void msm_devfreq_init(struct msm_gpu *gpu);
+void msm_devfreq_cleanup(struct msm_gpu *gpu);
+void msm_devfreq_resume(struct msm_gpu *gpu);
+void msm_devfreq_suspend(struct msm_gpu *gpu);
+void msm_devfreq_active(struct msm_gpu *gpu);
+void msm_devfreq_idle(struct msm_gpu *gpu);
 
 int msm_gpu_hw_init(struct msm_gpu *gpu);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
new file mode 100644
index 000000000000..0a1ee20296a2
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include "msm_gpu.h"
+#include "msm_gpu_trace.h"
+
+#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
+
+/*
+ * Power Management:
+ */
+
+static int msm_devfreq_target(struct device *dev, unsigned long *freq,
+		u32 flags)
+{
+	struct msm_gpu *gpu = dev_to_gpu(dev);
+	struct dev_pm_opp *opp;
+
+	opp = devfreq_recommended_opp(dev, freq, flags);
+
+	/*
+	 * If the GPU is idle, devfreq is not aware, so just ignore
+	 * it's requests
+	 */
+	if (gpu->devfreq.idle_freq) {
+		gpu->devfreq.idle_freq = *freq;
+		return 0;
+	}
+
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	trace_msm_gpu_freq_change(dev_pm_opp_get_freq(opp));
+
+	if (gpu->funcs->gpu_set_freq)
+		gpu->funcs->gpu_set_freq(gpu, opp);
+	else
+		clk_set_rate(gpu->core_clk, *freq);
+
+	dev_pm_opp_put(opp);
+
+	return 0;
+}
+
+static unsigned long get_freq(struct msm_gpu *gpu)
+{
+	if (gpu->devfreq.idle_freq)
+		return gpu->devfreq.idle_freq;
+
+	if (gpu->funcs->gpu_get_freq)
+		return gpu->funcs->gpu_get_freq(gpu);
+
+	return clk_get_rate(gpu->core_clk);
+}
+
+static int msm_devfreq_get_dev_status(struct device *dev,
+		struct devfreq_dev_status *status)
+{
+	struct msm_gpu *gpu = dev_to_gpu(dev);
+	ktime_t time;
+
+	status->current_frequency = get_freq(gpu);
+	status->busy_time = gpu->funcs->gpu_busy(gpu);
+
+	time = ktime_get();
+	status->total_time = ktime_us_delta(time, gpu->devfreq.time);
+	gpu->devfreq.time = time;
+
+	return 0;
+}
+
+static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq)
+{
+	*freq = get_freq(dev_to_gpu(dev));
+
+	return 0;
+}
+
+static struct devfreq_dev_profile msm_devfreq_profile = {
+	.timer = DEVFREQ_TIMER_DELAYED,
+	.polling_ms = 50,
+	.target = msm_devfreq_target,
+	.get_dev_status = msm_devfreq_get_dev_status,
+	.get_cur_freq = msm_devfreq_get_cur_freq,
+};
+
+void msm_devfreq_init(struct msm_gpu *gpu)
+{
+	/* We need target support to do devfreq */
+	if (!gpu->funcs->gpu_busy)
+		return;
+
+	msm_devfreq_profile.initial_freq = gpu->fast_rate;
+
+	/*
+	 * Don't set the freq_table or max_state and let devfreq build the table
+	 * from OPP
+	 * After a deferred probe, these may have be left to non-zero values,
+	 * so set them back to zero before creating the devfreq device
+	 */
+	msm_devfreq_profile.freq_table = NULL;
+	msm_devfreq_profile.max_state = 0;
+
+	gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev,
+			&msm_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND,
+			NULL);
+
+	if (IS_ERR(gpu->devfreq.devfreq)) {
+		DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
+		gpu->devfreq.devfreq = NULL;
+		return;
+	}
+
+	devfreq_suspend_device(gpu->devfreq.devfreq);
+
+	gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node,
+			gpu->devfreq.devfreq);
+	if (IS_ERR(gpu->cooling)) {
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+				"Couldn't register GPU cooling device\n");
+		gpu->cooling = NULL;
+	}
+}
+
+void msm_devfreq_cleanup(struct msm_gpu *gpu)
+{
+	devfreq_cooling_unregister(gpu->cooling);
+}
+
+void msm_devfreq_resume(struct msm_gpu *gpu)
+{
+	gpu->devfreq.busy_cycles = 0;
+	gpu->devfreq.time = ktime_get();
+
+	devfreq_resume_device(gpu->devfreq.devfreq);
+}
+
+void msm_devfreq_suspend(struct msm_gpu *gpu)
+{
+	devfreq_suspend_device(gpu->devfreq.devfreq);
+}
+
+void msm_devfreq_active(struct msm_gpu *gpu)
+{
+	struct msm_gpu_devfreq *df = &gpu->devfreq;
+	struct devfreq_dev_status status;
+	unsigned int idle_time;
+	unsigned long target_freq = df->idle_freq;
+
+	/*
+	 * Hold devfreq lock to synchronize with get_dev_status()/
+	 * target() callbacks
+	 */
+	mutex_lock(&df->devfreq->lock);
+
+	idle_time = ktime_to_ms(ktime_sub(ktime_get(), df->idle_time));
+
+	/*
+	 * If we've been idle for a significant fraction of a polling
+	 * interval, then we won't meet the threshold of busyness for
+	 * the governor to ramp up the freq.. so give some boost
+	 */
+	if (idle_time > msm_devfreq_profile.polling_ms/2) {
+		target_freq *= 2;
+	}
+
+	df->idle_freq = 0;
+
+	msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0);
+
+	/*
+	 * Reset the polling interval so we aren't inconsistent
+	 * about freq vs busy/total cycles
+	 */
+	msm_devfreq_get_dev_status(&gpu->pdev->dev, &status);
+
+	mutex_unlock(&df->devfreq->lock);
+}
+
+void msm_devfreq_idle(struct msm_gpu *gpu)
+{
+	struct msm_gpu_devfreq *df = &gpu->devfreq;
+	unsigned long idle_freq, target_freq = 0;
+
+	/*
+	 * Hold devfreq lock to synchronize with get_dev_status()/
+	 * target() callbacks
+	 */
+	mutex_lock(&df->devfreq->lock);
+
+	idle_freq = get_freq(gpu);
+
+	msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0);
+
+	df->idle_time = ktime_get();
+	df->idle_freq = idle_freq;
+
+	mutex_unlock(&df->devfreq->lock);
+}
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 086a2d59b8c8..de2bc3467bb5 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -117,9 +117,6 @@ struct msm_kms_funcs {
 			struct drm_encoder *encoder,
 			struct drm_encoder *slave_encoder,
 			bool is_cmd_mode);
-	void (*set_encoder_mode)(struct msm_kms *kms,
-				 struct drm_encoder *encoder,
-				 bool cmd_mode);
 	/* cleanup: */
 	void (*destroy)(struct msm_kms *kms);
 
@@ -150,7 +147,7 @@ struct msm_kms {
 	const struct msm_kms_funcs *funcs;
 	struct drm_device *dev;
 
-	/* irq number to be passed on to drm_irq_install */
+	/* irq number to be passed on to msm_irq_install */
 	int irq;
 
 	/* mapper-id used to request GEM buffer mapped for scanout: */
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index 659e5cc4b40a..b55398a34fa4 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -325,15 +325,19 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ))
 		return;
 
+	msm_gem_lock(&obj->base);
 	buf = msm_gem_get_vaddr_active(&obj->base);
 	if (IS_ERR(buf))
-		return;
+		goto out_unlock;
 
 	buf += offset;
 
 	rd_write_section(rd, RD_BUFFER_CONTENTS, buf, size);
 
 	msm_gem_put_vaddr_locked(&obj->base);
+
+out_unlock:
+	msm_gem_unlock(&obj->base);
 }
 
 /* called under struct_mutex */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4d2a2a4abef8..bd54c1412649 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -7,10 +7,61 @@
 #include "msm_ringbuffer.h"
 #include "msm_gpu.h"
 
+static uint num_hw_submissions = 8;
+MODULE_PARM_DESC(num_hw_submissions, "The max # of jobs to write into ringbuffer (default 8)");
+module_param(num_hw_submissions, uint, 0600);
+
+static struct dma_fence *msm_job_dependency(struct drm_sched_job *job,
+		struct drm_sched_entity *s_entity)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+
+	if (!xa_empty(&submit->deps))
+		return xa_erase(&submit->deps, submit->last_dep++);
+
+	return NULL;
+}
+
+static struct dma_fence *msm_job_run(struct drm_sched_job *job)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+	struct msm_gpu *gpu = submit->gpu;
+
+	submit->hw_fence = msm_fence_alloc(submit->ring->fctx);
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	msm_gpu_submit(gpu, submit);
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	pm_runtime_put(&gpu->pdev->dev);
+
+	return dma_fence_get(submit->hw_fence);
+}
+
+static void msm_job_free(struct drm_sched_job *job)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+
+	drm_sched_job_cleanup(job);
+	msm_gem_submit_put(submit);
+}
+
+const struct drm_sched_backend_ops msm_sched_ops = {
+	.dependency = msm_job_dependency,
+	.run_job = msm_job_run,
+	.free_job = msm_job_free
+};
+
 struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 		void *memptrs, uint64_t memptrs_iova)
 {
 	struct msm_ringbuffer *ring;
+	long sched_timeout;
 	char name[32];
 	int ret;
 
@@ -32,7 +83,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
-		ring->start = 0;
+		ring->start = NULL;
 		goto fail;
 	}
 
@@ -45,13 +96,23 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->memptrs = memptrs;
 	ring->memptrs_iova = memptrs_iova;
 
+	 /* currently managing hangcheck ourselves: */
+	sched_timeout = MAX_SCHEDULE_TIMEOUT;
+
+	ret = drm_sched_init(&ring->sched, &msm_sched_ops,
+			num_hw_submissions, 0, sched_timeout,
+			NULL, NULL, to_msm_bo(ring->bo)->name);
+	if (ret) {
+		goto fail;
+	}
+
 	INIT_LIST_HEAD(&ring->submits);
 	spin_lock_init(&ring->submit_lock);
 	spin_lock_init(&ring->preempt_lock);
 
 	snprintf(name, sizeof(name), "gpu-ring-%d", ring->id);
 
-	ring->fctx = msm_fence_context_alloc(gpu->dev, name);
+	ring->fctx = msm_fence_context_alloc(gpu->dev, &ring->memptrs->fence, name);
 
 	return ring;
 
@@ -65,9 +126,11 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 	if (IS_ERR_OR_NULL(ring))
 		return;
 
+	drm_sched_fini(&ring->sched);
+
 	msm_fence_context_free(ring->fctx);
 
-	msm_gem_kernel_put(ring->bo, ring->gpu->aspace, false);
+	msm_gem_kernel_put(ring->bo, ring->gpu->aspace);
 
 	kfree(ring);
 }
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index fe55d4a1aa16..d8c63df4e9ca 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -7,6 +7,7 @@
 #ifndef __MSM_RINGBUFFER_H__
 #define __MSM_RINGBUFFER_H__
 
+#include "drm/gpu_scheduler.h"
 #include "msm_drv.h"
 
 #define rbmemptr(ring, member)  \
@@ -41,7 +42,18 @@ struct msm_ringbuffer {
 	uint32_t *start, *end, *cur, *next;
 
 	/*
+	 * The job scheduler for this ring.
+	 */
+	struct drm_gpu_scheduler sched;
+
+	/*
 	 * List of in-flight submits on this ring.  Protected by submit_lock.
+	 *
+	 * Currently just submits that are already written into the ring, not
+	 * submits that are still in drm_gpu_scheduler's queues.  At a later
+	 * step we could probably move to letting drm_gpu_scheduler manage
+	 * hangcheck detection and keep track of submit jobs that are in-
+	 * flight.
 	 */
 	struct list_head submits;
 	spinlock_t submit_lock;
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index c3d206105d28..32a55d81b58b 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -12,6 +12,10 @@ void msm_submitqueue_destroy(struct kref *kref)
 	struct msm_gpu_submitqueue *queue = container_of(kref,
 		struct msm_gpu_submitqueue, ref);
 
+	idr_destroy(&queue->fence_idr);
+
+	drm_sched_entity_destroy(&queue->entity);
+
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -62,10 +66,22 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 {
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
+	struct msm_ringbuffer *ring;
+	struct drm_gpu_scheduler *sched;
+	enum drm_sched_priority sched_prio;
+	unsigned ring_nr;
+	int ret;
 
 	if (!ctx)
 		return -ENODEV;
 
+	if (!priv->gpu)
+		return -ENODEV;
+
+	ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio);
+	if (ret)
+		return ret;
+
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 
 	if (!queue)
@@ -73,14 +89,16 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 
 	kref_init(&queue->ref);
 	queue->flags = flags;
+	queue->ring_nr = ring_nr;
 
-	if (priv->gpu) {
-		if (prio >= priv->gpu->nr_rings) {
-			kfree(queue);
-			return -EINVAL;
-		}
+	ring = priv->gpu->rb[ring_nr];
+	sched = &ring->sched;
 
-		queue->prio = prio;
+	ret = drm_sched_entity_init(&queue->entity,
+			sched_prio, &sched, 1, NULL);
+	if (ret) {
+		kfree(queue);
+		return ret;
 	}
 
 	write_lock(&ctx->queuelock);
@@ -91,6 +109,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (id)
 		*id = queue->id;
 
+	idr_init(&queue->fence_idr);
+	mutex_init(&queue->lock);
+
 	list_add_tail(&queue->node, &ctx->submitqueues);
 
 	write_unlock(&ctx->queuelock);
@@ -98,20 +119,26 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	return 0;
 }
 
+/*
+ * Create the default submit-queue (id==0), used for backwards compatibility
+ * for userspace that pre-dates the introduction of submitqueues.
+ */
 int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 {
 	struct msm_drm_private *priv = drm->dev_private;
-	int default_prio;
+	int default_prio, max_priority;
 
-	if (!ctx)
-		return 0;
+	if (!priv->gpu)
+		return -ENODEV;
+
+	max_priority = (priv->gpu->nr_rings * NR_SCHED_PRIORITIES) - 1;
 
 	/*
-	 * Select priority 2 as the "default priority" unless nr_rings is less
-	 * than 2 and then pick the lowest pirority
+	 * Pick a medium priority level as default.  Lower numeric value is
+	 * higher priority, so round-up to pick a priority that is not higher
+	 * than the middle priority level.
 	 */
-	default_prio = priv->gpu ?
-		clamp_t(uint32_t, 2, 0, priv->gpu->nr_rings - 1) : 0;
+	default_prio = DIV_ROUND_UP(max_priority, 2);
 
 	INIT_LIST_HEAD(&ctx->submitqueues);
 
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index 6da93551e2e5..ec0432fe1bdf 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -24,7 +24,6 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_mode_config.h>
 #include <drm/drm_of.h>
 #include <drm/drm_probe_helper.h>
@@ -51,6 +50,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0xff,
 		.hs_wdth_shift	= 24,
 		.has_overlay	= false,
+		.has_ctrl2	= false,
 	},
 	[MXSFB_V4] = {
 		.transfer_count	= LCDC_V4_TRANSFER_COUNT,
@@ -59,6 +59,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0x3fff,
 		.hs_wdth_shift	= 18,
 		.has_overlay	= false,
+		.has_ctrl2	= true,
 	},
 	[MXSFB_V6] = {
 		.transfer_count	= LCDC_V4_TRANSFER_COUNT,
@@ -67,6 +68,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0x3fff,
 		.hs_wdth_shift	= 18,
 		.has_overlay	= true,
+		.has_ctrl2	= true,
 	},
 };
 
@@ -150,6 +152,49 @@ static int mxsfb_attach_bridge(struct mxsfb_drm_private *mxsfb)
 	return 0;
 }
 
+static irqreturn_t mxsfb_irq_handler(int irq, void *data)
+{
+	struct drm_device *drm = data;
+	struct mxsfb_drm_private *mxsfb = drm->dev_private;
+	u32 reg;
+
+	reg = readl(mxsfb->base + LCDC_CTRL1);
+
+	if (reg & CTRL1_CUR_FRAME_DONE_IRQ)
+		drm_crtc_handle_vblank(&mxsfb->crtc);
+
+	writel(CTRL1_CUR_FRAME_DONE_IRQ, mxsfb->base + LCDC_CTRL1 + REG_CLR);
+
+	return IRQ_HANDLED;
+}
+
+static void mxsfb_irq_disable(struct drm_device *drm)
+{
+	struct mxsfb_drm_private *mxsfb = drm->dev_private;
+
+	mxsfb_enable_axi_clk(mxsfb);
+	mxsfb->crtc.funcs->disable_vblank(&mxsfb->crtc);
+	mxsfb_disable_axi_clk(mxsfb);
+}
+
+static int mxsfb_irq_install(struct drm_device *dev, int irq)
+{
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	mxsfb_irq_disable(dev);
+
+	return request_irq(irq, mxsfb_irq_handler, 0,  dev->driver->name, dev);
+}
+
+static void mxsfb_irq_uninstall(struct drm_device *dev)
+{
+	struct mxsfb_drm_private *mxsfb = dev->dev_private;
+
+	mxsfb_irq_disable(dev);
+	free_irq(mxsfb->irq, dev);
+}
+
 static int mxsfb_load(struct drm_device *drm,
 		      const struct mxsfb_devdata *devdata)
 {
@@ -223,8 +268,13 @@ static int mxsfb_load(struct drm_device *drm,
 
 	drm_mode_config_reset(drm);
 
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto err_vblank;
+	mxsfb->irq = ret;
+
 	pm_runtime_get_sync(drm->dev);
-	ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
+	ret = mxsfb_irq_install(drm, mxsfb->irq);
 	pm_runtime_put_sync(drm->dev);
 
 	if (ret < 0) {
@@ -252,7 +302,7 @@ static void mxsfb_unload(struct drm_device *drm)
 	drm_mode_config_cleanup(drm);
 
 	pm_runtime_get_sync(drm->dev);
-	drm_irq_uninstall(drm);
+	mxsfb_irq_uninstall(drm);
 	pm_runtime_put_sync(drm->dev);
 
 	drm->dev_private = NULL;
@@ -260,38 +310,10 @@ static void mxsfb_unload(struct drm_device *drm)
 	pm_runtime_disable(drm->dev);
 }
 
-static void mxsfb_irq_disable(struct drm_device *drm)
-{
-	struct mxsfb_drm_private *mxsfb = drm->dev_private;
-
-	mxsfb_enable_axi_clk(mxsfb);
-	mxsfb->crtc.funcs->disable_vblank(&mxsfb->crtc);
-	mxsfb_disable_axi_clk(mxsfb);
-}
-
-static irqreturn_t mxsfb_irq_handler(int irq, void *data)
-{
-	struct drm_device *drm = data;
-	struct mxsfb_drm_private *mxsfb = drm->dev_private;
-	u32 reg;
-
-	reg = readl(mxsfb->base + LCDC_CTRL1);
-
-	if (reg & CTRL1_CUR_FRAME_DONE_IRQ)
-		drm_crtc_handle_vblank(&mxsfb->crtc);
-
-	writel(CTRL1_CUR_FRAME_DONE_IRQ, mxsfb->base + LCDC_CTRL1 + REG_CLR);
-
-	return IRQ_HANDLED;
-}
-
 DEFINE_DRM_GEM_CMA_FOPS(fops);
 
 static const struct drm_driver mxsfb_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
-	.irq_handler		= mxsfb_irq_handler,
-	.irq_preinstall		= mxsfb_irq_disable,
-	.irq_uninstall		= mxsfb_irq_disable,
 	DRM_GEM_CMA_DRIVER_OPS,
 	.fops	= &fops,
 	.name	= "mxsfb-drm",
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.h b/drivers/gpu/drm/mxsfb/mxsfb_drv.h
index 399d23e91ed1..ddb5b0417a82 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.h
@@ -22,6 +22,7 @@ struct mxsfb_devdata {
 	unsigned int	hs_wdth_mask;
 	unsigned int	hs_wdth_shift;
 	bool		has_overlay;
+	bool		has_ctrl2;
 };
 
 struct mxsfb_drm_private {
@@ -32,6 +33,8 @@ struct mxsfb_drm_private {
 	struct clk			*clk_axi;
 	struct clk			*clk_disp_axi;
 
+	unsigned int			irq;
+
 	struct drm_device		*drm;
 	struct {
 		struct drm_plane	primary;
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
index 300e7bab0f43..89dd618d78f3 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
@@ -47,16 +47,13 @@ static u32 set_hsync_pulse_width(struct mxsfb_drm_private *mxsfb, u32 val)
  * Setup the MXSFB registers for decoding the pixels out of the framebuffer and
  * outputting them on the bus.
  */
-static void mxsfb_set_formats(struct mxsfb_drm_private *mxsfb)
+static void mxsfb_set_formats(struct mxsfb_drm_private *mxsfb,
+			      const u32 bus_format)
 {
 	struct drm_device *drm = mxsfb->drm;
 	const u32 format = mxsfb->crtc.primary->state->fb->format->format;
-	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
 	u32 ctrl, ctrl1;
 
-	if (mxsfb->connector->display_info.num_bus_formats)
-		bus_format = mxsfb->connector->display_info.bus_formats[0];
-
 	DRM_DEV_DEBUG_DRIVER(drm->dev, "Using bus_format: 0x%08X\n",
 			     bus_format);
 
@@ -107,6 +104,14 @@ static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 		clk_prepare_enable(mxsfb->clk_disp_axi);
 	clk_prepare_enable(mxsfb->clk);
 
+	/* Increase number of outstanding requests on all supported IPs */
+	if (mxsfb->devdata->has_ctrl2) {
+		reg = readl(mxsfb->base + LCDC_V4_CTRL2);
+		reg &= ~CTRL2_SET_OUTSTANDING_REQS_MASK;
+		reg |= CTRL2_SET_OUTSTANDING_REQS_16;
+		writel(reg, mxsfb->base + LCDC_V4_CTRL2);
+	}
+
 	/* If it was disabled, re-enable the mode again */
 	writel(CTRL_DOTCLK_MODE, mxsfb->base + LCDC_CTRL + REG_SET);
 
@@ -115,6 +120,35 @@ static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 	reg |= VDCTRL4_SYNC_SIGNALS_ON;
 	writel(reg, mxsfb->base + LCDC_VDCTRL4);
 
+	/*
+	 * Enable recovery on underflow.
+	 *
+	 * There is some sort of corner case behavior of the controller,
+	 * which could rarely be triggered at least on i.MX6SX connected
+	 * to 800x480 DPI panel and i.MX8MM connected to DPI->DSI->LVDS
+	 * bridged 1920x1080 panel (and likely on other setups too), where
+	 * the image on the panel shifts to the right and wraps around.
+	 * This happens either when the controller is enabled on boot or
+	 * even later during run time. The condition does not correct
+	 * itself automatically, i.e. the display image remains shifted.
+	 *
+	 * It seems this problem is known and is due to sporadic underflows
+	 * of the LCDIF FIFO. While the LCDIF IP does have underflow/overflow
+	 * IRQs, neither of the IRQs trigger and neither IRQ status bit is
+	 * asserted when this condition occurs.
+	 *
+	 * All known revisions of the LCDIF IP have CTRL1 RECOVER_ON_UNDERFLOW
+	 * bit, which is described in the reference manual since i.MX23 as
+	 * "
+	 *   Set this bit to enable the LCDIF block to recover in the next
+	 *   field/frame if there was an underflow in the current field/frame.
+	 * "
+	 * Enable this bit to mitigate the sporadic underflows.
+	 */
+	reg = readl(mxsfb->base + LCDC_CTRL1);
+	reg |= CTRL1_RECOVER_ON_UNDERFLOW;
+	writel(reg, mxsfb->base + LCDC_CTRL1);
+
 	writel(CTRL_RUN, mxsfb->base + LCDC_CTRL + REG_SET);
 }
 
@@ -185,7 +219,8 @@ static dma_addr_t mxsfb_get_fb_paddr(struct drm_plane *plane)
 	return gem->paddr;
 }
 
-static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
+static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb,
+				     const u32 bus_format)
 {
 	struct drm_device *drm = mxsfb->crtc.dev;
 	struct drm_display_mode *m = &mxsfb->crtc.state->adjusted_mode;
@@ -206,11 +241,14 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 
 	/* Clear the FIFOs */
 	writel(CTRL1_FIFO_CLEAR, mxsfb->base + LCDC_CTRL1 + REG_SET);
+	readl(mxsfb->base + LCDC_CTRL1);
+	writel(CTRL1_FIFO_CLEAR, mxsfb->base + LCDC_CTRL1 + REG_CLR);
+	readl(mxsfb->base + LCDC_CTRL1);
 
 	if (mxsfb->devdata->has_overlay)
 		writel(0, mxsfb->base + LCDC_AS_CTRL);
 
-	mxsfb_set_formats(mxsfb);
+	mxsfb_set_formats(mxsfb, bus_format);
 
 	clk_set_rate(mxsfb->clk, m->crtc_clock * 1000);
 
@@ -308,7 +346,9 @@ static void mxsfb_crtc_atomic_enable(struct drm_crtc *crtc,
 				     struct drm_atomic_state *state)
 {
 	struct mxsfb_drm_private *mxsfb = to_mxsfb_drm_private(crtc->dev);
+	struct drm_bridge_state *bridge_state;
 	struct drm_device *drm = mxsfb->drm;
+	u32 bus_format = 0;
 	dma_addr_t paddr;
 
 	pm_runtime_get_sync(drm->dev);
@@ -316,7 +356,23 @@ static void mxsfb_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	drm_crtc_vblank_on(crtc);
 
-	mxsfb_crtc_mode_set_nofb(mxsfb);
+	/* If there is a bridge attached to the LCDIF, use its bus format */
+	if (mxsfb->bridge) {
+		bridge_state =
+			drm_atomic_get_new_bridge_state(state,
+							mxsfb->bridge);
+		bus_format = bridge_state->input_bus_cfg.format;
+	}
+
+	/* If there is no bridge, use bus format from connector */
+	if (!bus_format && mxsfb->connector->display_info.num_bus_formats)
+		bus_format = mxsfb->connector->display_info.bus_formats[0];
+
+	/* If all else fails, default to RGB888_1X24 */
+	if (!bus_format)
+		bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+
+	mxsfb_crtc_mode_set_nofb(mxsfb, bus_format);
 
 	/* Write cur_buf as well to avoid an initial corrupt frame */
 	paddr = mxsfb_get_fb_paddr(crtc->primary);
@@ -500,13 +556,11 @@ static bool mxsfb_format_mod_supported(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = mxsfb_plane_atomic_check,
 	.atomic_update = mxsfb_plane_primary_atomic_update,
 };
 
 static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = mxsfb_plane_atomic_check,
 	.atomic_update = mxsfb_plane_overlay_atomic_update,
 };
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
index 55d28a27f912..694fea13e893 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
@@ -15,6 +15,7 @@
 #define LCDC_CTRL			0x00
 #define LCDC_CTRL1			0x10
 #define LCDC_V3_TRANSFER_COUNT		0x20
+#define LCDC_V4_CTRL2			0x20
 #define LCDC_V4_TRANSFER_COUNT		0x30
 #define LCDC_V4_CUR_BUF			0x40
 #define LCDC_V4_NEXT_BUF		0x50
@@ -54,12 +55,20 @@
 #define CTRL_DF24			BIT(1)
 #define CTRL_RUN			BIT(0)
 
+#define CTRL1_RECOVER_ON_UNDERFLOW	BIT(24)
 #define CTRL1_FIFO_CLEAR		BIT(21)
 #define CTRL1_SET_BYTE_PACKAGING(x)	(((x) & 0xf) << 16)
 #define CTRL1_GET_BYTE_PACKAGING(x)	(((x) >> 16) & 0xf)
 #define CTRL1_CUR_FRAME_DONE_IRQ_EN	BIT(13)
 #define CTRL1_CUR_FRAME_DONE_IRQ	BIT(9)
 
+#define CTRL2_SET_OUTSTANDING_REQS_1	0
+#define CTRL2_SET_OUTSTANDING_REQS_2	(0x1 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_4	(0x2 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_8	(0x3 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_16	(0x4 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_MASK	(0x7 << 21)
+
 #define TRANSFER_COUNT_SET_VCOUNT(x)	(((x) & 0xffff) << 16)
 #define TRANSFER_COUNT_GET_VCOUNT(x)	(((x) >> 16) & 0xffff)
 #define TRANSFER_COUNT_SET_HCOUNT(x)	((x) & 0xffff)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index bcb0310a41b6..d7b9f7f8c9e3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -31,6 +31,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/hdmi.h>
 #include <linux/component.h>
+#include <linux/iopoll.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -1649,17 +1650,36 @@ nv50_sor_update(struct nouveau_encoder *nv_encoder, u8 head,
 	core->func->sor->ctrl(core, nv_encoder->or, nv_encoder->ctrl, asyh);
 }
 
+/* TODO: Should we extend this to PWM-only backlights?
+ * As well, should we add a DRM helper for waiting for the backlight to acknowledge
+ * the panel backlight has been shut off? Intel doesn't seem to do this, and uses a
+ * fixed time delay from the vbios…
+ */
 static void
 nv50_sor_atomic_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
 	struct nouveau_connector *nv_connector = nv50_outp_get_old_connector(state, nv_encoder);
+#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
+	struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
+	struct nouveau_backlight *backlight = nv_connector->backlight;
+#endif
 	struct drm_dp_aux *aux = &nv_connector->aux;
+	int ret;
 	u8 pwr;
 
+#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
+	if (backlight && backlight->uses_dpcd) {
+		ret = drm_edp_backlight_disable(aux, &backlight->edp_info);
+		if (ret < 0)
+			NV_ERROR(drm, "Failed to disable backlight on [CONNECTOR:%d:%s]: %d\n",
+				 nv_connector->base.base.id, nv_connector->base.name, ret);
+	}
+#endif
+
 	if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
-		int ret = drm_dp_dpcd_readb(aux, DP_SET_POWER, &pwr);
+		ret = drm_dp_dpcd_readb(aux, DP_SET_POWER, &pwr);
 
 		if (ret == 0) {
 			pwr &= ~DP_SET_POWER_MASK;
@@ -1696,6 +1716,9 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta
 	struct drm_device *dev = encoder->dev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_connector *nv_connector;
+#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
+	struct nouveau_backlight *backlight;
+#endif
 	struct nvbios *bios = &drm->vbios;
 	bool hda = false;
 	u8 proto = NV507D_SOR_SET_CONTROL_PROTOCOL_CUSTOM;
@@ -1770,6 +1793,14 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta
 			proto = NV887D_SOR_SET_CONTROL_PROTOCOL_DP_B;
 
 		nv50_audio_enable(encoder, nv_crtc, nv_connector, state, mode);
+
+#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
+		backlight = nv_connector->backlight;
+		if (backlight && backlight->uses_dpcd)
+			drm_edp_backlight_enable(&nv_connector->aux, &backlight->edp_info,
+						 (u16)backlight->dev->props.brightness);
+#endif
+
 		break;
 	default:
 		BUG();
@@ -2322,6 +2353,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	nv50_crc_atomic_start_reporting(state);
 	if (!flushed)
 		nv50_crc_atomic_release_notifier_contexts(state);
+
 	drm_atomic_helper_commit_hw_done(state);
 	drm_atomic_helper_cleanup_planes(dev, state);
 	drm_atomic_helper_commit_cleanup_done(state);
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 72f35a2babcb..1cbd71abc80a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -42,11 +42,6 @@
 static struct ida bl_ida;
 #define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0'
 
-struct nouveau_backlight {
-	struct backlight_device *dev;
-	int id;
-};
-
 static bool
 nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE],
 			   struct nouveau_backlight *bl)
@@ -148,6 +143,98 @@ static const struct backlight_ops nv50_bl_ops = {
 	.update_status = nv50_set_intensity,
 };
 
+/*
+ * eDP brightness callbacks need to happen under lock, since we need to
+ * enable/disable the backlight ourselves for modesets
+ */
+static int
+nv50_edp_get_brightness(struct backlight_device *bd)
+{
+	struct drm_connector *connector = dev_get_drvdata(bd->dev.parent);
+	struct drm_device *dev = connector->dev;
+	struct drm_crtc *crtc;
+	struct drm_modeset_acquire_ctx ctx;
+	int ret = 0;
+
+	drm_modeset_acquire_init(&ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
+	if (ret == -EDEADLK)
+		goto deadlock;
+	else if (ret < 0)
+		goto out;
+
+	crtc = connector->state->crtc;
+	if (!crtc)
+		goto out;
+
+	ret = drm_modeset_lock(&crtc->mutex, &ctx);
+	if (ret == -EDEADLK)
+		goto deadlock;
+	else if (ret < 0)
+		goto out;
+
+	if (!crtc->state->active)
+		goto out;
+
+	ret = bd->props.brightness;
+out:
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+	return ret;
+deadlock:
+	drm_modeset_backoff(&ctx);
+	goto retry;
+}
+
+static int
+nv50_edp_set_brightness(struct backlight_device *bd)
+{
+	struct drm_connector *connector = dev_get_drvdata(bd->dev.parent);
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
+	struct drm_device *dev = connector->dev;
+	struct drm_crtc *crtc;
+	struct drm_dp_aux *aux = &nv_connector->aux;
+	struct nouveau_backlight *nv_bl = nv_connector->backlight;
+	struct drm_modeset_acquire_ctx ctx;
+	int ret = 0;
+
+	drm_modeset_acquire_init(&ctx, 0);
+retry:
+	ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
+	if (ret == -EDEADLK)
+		goto deadlock;
+	else if (ret < 0)
+		goto out;
+
+	crtc = connector->state->crtc;
+	if (!crtc)
+		goto out;
+
+	ret = drm_modeset_lock(&crtc->mutex, &ctx);
+	if (ret == -EDEADLK)
+		goto deadlock;
+	else if (ret < 0)
+		goto out;
+
+	if (crtc->state->active)
+		ret = drm_edp_backlight_set_level(aux, &nv_bl->edp_info, bd->props.brightness);
+
+out:
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+	return ret;
+deadlock:
+	drm_modeset_backoff(&ctx);
+	goto retry;
+}
+
+static const struct backlight_ops nv50_edp_bl_ops = {
+	.get_brightness = nv50_edp_get_brightness,
+	.update_status = nv50_edp_set_brightness,
+};
+
 static int
 nva3_get_intensity(struct backlight_device *bd)
 {
@@ -194,8 +281,13 @@ static const struct backlight_ops nva3_bl_ops = {
 	.update_status = nva3_set_intensity,
 };
 
+/* FIXME: perform backlight probing for eDP _before_ this, this only gets called after connector
+ * registration which happens after the initial modeset
+ */
 static int
-nv50_backlight_init(struct nouveau_encoder *nv_encoder,
+nv50_backlight_init(struct nouveau_backlight *bl,
+		    struct nouveau_connector *nv_conn,
+		    struct nouveau_encoder *nv_encoder,
 		    struct backlight_properties *props,
 		    const struct backlight_ops **ops)
 {
@@ -205,6 +297,41 @@ nv50_backlight_init(struct nouveau_encoder *nv_encoder,
 	if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1)))
 		return -ENODEV;
 
+	if (nv_conn->type == DCB_CONNECTOR_eDP) {
+		int ret;
+		u16 current_level;
+		u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE];
+		u8 current_mode;
+
+		ret = drm_dp_dpcd_read(&nv_conn->aux, DP_EDP_DPCD_REV, edp_dpcd,
+				       EDP_DISPLAY_CTL_CAP_SIZE);
+		if (ret < 0)
+			return ret;
+
+		if (drm_edp_backlight_supported(edp_dpcd)) {
+			NV_DEBUG(drm, "DPCD backlight controls supported on %s\n",
+				 nv_conn->base.name);
+
+			ret = drm_edp_backlight_init(&nv_conn->aux, &bl->edp_info, 0, edp_dpcd,
+						     &current_level, &current_mode);
+			if (ret < 0)
+				return ret;
+
+			ret = drm_edp_backlight_enable(&nv_conn->aux, &bl->edp_info, current_level);
+			if (ret < 0) {
+				NV_ERROR(drm, "Failed to enable backlight on %s: %d\n",
+					 nv_conn->base.name, ret);
+				return ret;
+			}
+
+			*ops = &nv50_edp_bl_ops;
+			props->brightness = current_level;
+			props->max_brightness = bl->edp_info.max;
+			bl->uses_dpcd = true;
+			return 0;
+		}
+	}
+
 	if (drm->client.device.info.chipset <= 0xa0 ||
 	    drm->client.device.info.chipset == 0xaa ||
 	    drm->client.device.info.chipset == 0xac)
@@ -245,6 +372,10 @@ nouveau_backlight_init(struct drm_connector *connector)
 	if (!nv_encoder)
 		return 0;
 
+	bl = kzalloc(sizeof(*bl), GFP_KERNEL);
+	if (!bl)
+		return -ENOMEM;
+
 	switch (device->info.family) {
 	case NV_DEVICE_INFO_V0_CURIE:
 		ret = nv40_backlight_init(nv_encoder, &props, &ops);
@@ -257,20 +388,19 @@ nouveau_backlight_init(struct drm_connector *connector)
 	case NV_DEVICE_INFO_V0_VOLTA:
 	case NV_DEVICE_INFO_V0_TURING:
 	case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed
-		ret = nv50_backlight_init(nv_encoder, &props, &ops);
+		ret = nv50_backlight_init(bl, nouveau_connector(connector),
+					  nv_encoder, &props, &ops);
 		break;
 	default:
-		return 0;
+		ret = 0;
+		goto fail_alloc;
 	}
 
-	if (ret == -ENODEV)
-		return 0;
-	else if (ret)
-		return ret;
-
-	bl = kzalloc(sizeof(*bl), GFP_KERNEL);
-	if (!bl)
-		return -ENOMEM;
+	if (ret) {
+		if (ret == -ENODEV)
+			ret = 0;
+		goto fail_alloc;
+	}
 
 	if (!nouveau_get_backlight_name(backlight_name, bl)) {
 		NV_ERROR(drm, "Failed to retrieve a unique name for the backlight interface\n");
@@ -287,7 +417,9 @@ nouveau_backlight_init(struct drm_connector *connector)
 	}
 
 	nouveau_connector(connector)->backlight = bl;
-	bl->dev->props.brightness = bl->dev->ops->get_brightness(bl->dev);
+	if (!bl->dev->props.brightness)
+		bl->dev->props.brightness =
+			bl->dev->ops->get_brightness(bl->dev);
 	backlight_update_status(bl->dev);
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index d0b859c4a80e..40f90e353540 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -46,7 +46,14 @@ struct nvkm_i2c_port;
 struct dcb_output;
 
 #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
-struct nouveau_backlight;
+struct nouveau_backlight {
+	struct backlight_device *dev;
+
+	struct drm_edp_backlight_info edp_info;
+	bool uses_dpcd : 1;
+
+	int id;
+};
 #endif
 
 #define nouveau_conn_atom(p)                                                   \
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index ba4cd5f83725..1f828c9f691c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -554,8 +554,6 @@ nouveau_drm_device_init(struct drm_device *dev)
 	if (ret)
 		goto fail_master;
 
-	dev->irq_enabled = true;
-
 	nvxx_client(&drm->client.base)->debug =
 		nvkm_dbgopt(nouveau_debug, "DRM");
 
@@ -739,7 +737,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	nvkm_device_del(&device);
 
 	/* Remove conflicting drivers (vesafb, efifb etc). */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "nouveaufb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver_pci);
 	if (ret)
 		return ret;
 
@@ -796,7 +794,6 @@ nouveau_drm_device_remove(struct drm_device *dev)
 
 	drm_dev_unregister(dev);
 
-	dev->irq_enabled = false;
 	client = nvxx_client(&drm->client.base);
 	device = nvkm_device_find(client->device);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h
index 1ffcc0a491fd..77c2fed76e8b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_encoder.h
+++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h
@@ -30,6 +30,7 @@
 #include <subdev/bios/dcb.h>
 
 #include <drm/drm_encoder_slave.h>
+#include <drm/drm_dp_helper.h>
 #include <drm/drm_dp_mst_helper.h>
 #include "dispnv04/disp.h"
 struct nv50_head_atom;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 6b43918035df..05d0b3eb3690 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -358,7 +358,7 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e
 	fobj = dma_resv_shared_list(resv);
 	fence = dma_resv_excl_fence(resv);
 
-	if (fence && (!exclusive || !fobj || !fobj->shared_count)) {
+	if (fence) {
 		struct nouveau_channel *prev = NULL;
 		bool must_wait = true;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index 7c4b374b3eca..60cd8c0463df 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -11,9 +11,9 @@
 #include "nouveau_vga.h"
 
 static unsigned int
-nouveau_vga_set_decode(void *priv, bool state)
+nouveau_vga_set_decode(struct pci_dev *pdev, bool state)
 {
-	struct nouveau_drm *drm = nouveau_drm(priv);
+	struct nouveau_drm *drm = nouveau_drm(pci_get_drvdata(pdev));
 	struct nvif_object *device = &drm->client.device.object;
 
 	if (drm->client.device.info.family == NV_DEVICE_INFO_V0_CURIE &&
@@ -94,7 +94,7 @@ nouveau_vga_init(struct nouveau_drm *drm)
 		return;
 	pdev = to_pci_dev(dev->dev);
 
-	vga_client_register(pdev, dev, NULL, nouveau_vga_set_decode);
+	vga_client_register(pdev, nouveau_vga_set_decode);
 
 	/* don't register Thunderbolt eGPU with vga_switcheroo */
 	if (pci_is_thunderbolt_attached(pdev))
@@ -118,7 +118,7 @@ nouveau_vga_fini(struct nouveau_drm *drm)
 		return;
 	pdev = to_pci_dev(dev->dev);
 
-	vga_client_register(pdev, NULL, NULL, NULL);
+	vga_client_unregister(pdev);
 
 	if (pci_is_thunderbolt_attached(pdev))
 		return;
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 8632139e0f01..f86e20578143 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -290,12 +290,8 @@ static int omap_modeset_init(struct drm_device *dev)
 			ret = drm_bridge_attach(pipe->encoder,
 						pipe->output->bridge, NULL,
 						DRM_BRIDGE_ATTACH_NO_CONNECTOR);
-			if (ret < 0) {
-				dev_err(priv->dev,
-					"unable to attach bridge %pOF\n",
-					pipe->output->bridge->of_node);
+			if (ret < 0)
 				return ret;
-			}
 		}
 
 		id = omap_display_id(pipe->output);
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index d6f136984da9..591d4c273f02 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -48,6 +48,8 @@ struct omap_drm_private {
 	struct dss_device *dss;
 	struct dispc_device *dispc;
 
+	bool irq_enabled;
+
 	unsigned int num_pipes;
 	struct omap_drm_pipeline pipes[8];
 	struct omap_drm_pipeline *channels[8];
diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c
index 15148d4b35b5..4aca14dab927 100644
--- a/drivers/gpu/drm/omapdrm/omap_irq.c
+++ b/drivers/gpu/drm/omapdrm/omap_irq.c
@@ -253,13 +253,6 @@ static const u32 omap_underflow_irqs[] = {
 	[OMAP_DSS_VIDEO3] = DISPC_IRQ_VID3_FIFO_UNDERFLOW,
 };
 
-/*
- * We need a special version, instead of just using drm_irq_install(),
- * because we need to register the irq via omapdss.  Once omapdss and
- * omapdrm are merged together we can assign the dispc hwmod data to
- * ourselves and drop these and just use drm_irq_{install,uninstall}()
- */
-
 int omap_drm_irq_install(struct drm_device *dev)
 {
 	struct omap_drm_private *priv = dev->dev_private;
@@ -291,7 +284,7 @@ int omap_drm_irq_install(struct drm_device *dev)
 	if (ret < 0)
 		return ret;
 
-	dev->irq_enabled = true;
+	priv->irq_enabled = true;
 
 	return 0;
 }
@@ -300,10 +293,10 @@ void omap_drm_irq_uninstall(struct drm_device *dev)
 {
 	struct omap_drm_private *priv = dev->dev_private;
 
-	if (!dev->irq_enabled)
+	if (!priv->irq_enabled)
 		return;
 
-	dev->irq_enabled = false;
+	priv->irq_enabled = false;
 
 	dispc_free_irq(priv->dispc, dev);
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 801da917507d..512af976b7e9 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -6,6 +6,7 @@
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 
 #include "omap_dmm_tiler.h"
@@ -29,6 +30,8 @@ static int omap_plane_prepare_fb(struct drm_plane *plane,
 	if (!new_state->fb)
 		return 0;
 
+	drm_gem_plane_helper_prepare_fb(plane, new_state);
+
 	return omap_framebuffer_pin(new_state->fb);
 }
 
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index ef87d92cdf49..beb581b96ecd 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -82,6 +82,7 @@ config DRM_PANEL_SIMPLE
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on PM
 	select VIDEOMODE_HELPERS
+	select DRM_DP_AUX_BUS
 	help
 	  DRM panel driver for dumb panels that need at most a regulator and
 	  a GPIO to be powered up. Optionally a backlight can be attached so
@@ -124,6 +125,18 @@ config DRM_PANEL_ILITEK_IL9322
 	  Say Y here if you want to enable support for Ilitek IL9322
 	  QVGA (320x240) RGB, YUV and ITU-T BT.656 panels.
 
+config DRM_PANEL_ILITEK_ILI9341
+	tristate "Ilitek ILI9341 240x320 QVGA panels"
+	depends on OF && SPI
+	depends on DRM_KMS_HELPER
+	depends on DRM_KMS_CMA_HELPER
+	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_MIPI_DBI
+	help
+	  Say Y here if you want to enable support for Ilitek IL9341
+	  QVGA (240x320) RGB panels. support serial & parallel rgb
+	  interface.
+
 config DRM_PANEL_ILITEK_ILI9881C
 	tristate "Ilitek ILI9881C-based panels"
 	depends on OF
@@ -133,6 +146,15 @@ config DRM_PANEL_ILITEK_ILI9881C
 	  Say Y if you want to enable support for panels based on the
 	  Ilitek ILI9881c controller.
 
+config DRM_PANEL_INNOLUX_EJ030NA
+        tristate "Innolux EJ030NA 320x480 LCD panel"
+        depends on OF && SPI
+        select REGMAP_SPI
+        help
+          Say Y here to enable support for the Innolux/Chimei EJ030NA
+          320x480 3.0" panel as found in the RS97 V2.1, RG300(non-ips)
+          and LDK handheld gaming consoles.
+
 config DRM_PANEL_INNOLUX_P079ZCA
 	tristate "Innolux P079ZCA panel"
 	depends on OF
@@ -343,6 +365,27 @@ config DRM_PANEL_RONBO_RB070D30
 	  Say Y here if you want to enable support for Ronbo Electronics
 	  RB070D30 1024x600 DSI panel.
 
+config DRM_PANEL_SAMSUNG_ATNA33XC20
+	tristate "Samsung ATNA33XC20 eDP panel"
+	depends on OF
+	depends on BACKLIGHT_CLASS_DEVICE
+	depends on PM
+	select DRM_DP_AUX_BUS
+	help
+	  DRM panel driver for the Samsung ATNA33XC20 panel. This panel can't
+	  be handled by the DRM_PANEL_SIMPLE driver because its power
+	  sequencing is non-standard.
+
+config DRM_PANEL_SAMSUNG_DB7430
+	tristate "Samsung DB7430-based DPI panels"
+	depends on OF && SPI && GPIOLIB
+	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_MIPI_DBI
+	help
+	  Say Y here if you want to enable support for the Samsung
+	  DB7430 DPI display controller used in such devices as the
+	  LMS397KF04 480x800 DPI panel.
+
 config DRM_PANEL_SAMSUNG_S6D16D0
 	tristate "Samsung S6D16D0 DSI video mode panel"
 	depends on OF
@@ -377,6 +420,7 @@ config DRM_PANEL_SAMSUNG_S6E63M0_SPI
 	depends on SPI
 	depends on DRM_PANEL_SAMSUNG_S6E63M0
 	default DRM_PANEL_SAMSUNG_S6E63M0
+	select DRM_MIPI_DBI
 	help
 	  Say Y here if you want to be able to access the Samsung
 	  S6E63M0 panel using SPI.
@@ -553,6 +597,16 @@ config DRM_PANEL_VISIONOX_RM69299
 	  Say Y here if you want to enable support for Visionox
 	  RM69299  DSI Video Mode panel.
 
+config DRM_PANEL_WIDECHIPS_WS2401
+	tristate "Widechips WS2401 DPI panel driver"
+	depends on SPI && GPIOLIB
+	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_MIPI_DBI
+	help
+	  Say Y here if you want to enable support for the Widechips WS2401 DPI
+	  480x800 display controller used in panels such as Samsung LMS380KF01.
+	  This display is used in the Samsung Galaxy Ace 2 GT-I8160 (Codina).
+
 config DRM_PANEL_XINPENG_XPP055C272
 	tristate "Xinpeng XPP055C272 panel driver"
 	depends on OF
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index cae4d976c069..c8132050bcec 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -11,7 +11,9 @@ obj-$(CONFIG_DRM_PANEL_ELIDA_KD35T133) += panel-elida-kd35t133.o
 obj-$(CONFIG_DRM_PANEL_FEIXIN_K101_IM2BA02) += panel-feixin-k101-im2ba02.o
 obj-$(CONFIG_DRM_PANEL_FEIYANG_FY07024DI26A30D) += panel-feiyang-fy07024di26a30d.o
 obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o
+obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9341) += panel-ilitek-ili9341.o
 obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o
+obj-$(CONFIG_DRM_PANEL_INNOLUX_EJ030NA) += panel-innolux-ej030na.o
 obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o
 obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o
 obj-$(CONFIG_DRM_PANEL_KHADAS_TS050) += panel-khadas-ts050.o
@@ -33,6 +35,8 @@ obj-$(CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN) += panel-raspberrypi-touchscreen
 obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM67191) += panel-raydium-rm67191.o
 obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM68200) += panel-raydium-rm68200.o
 obj-$(CONFIG_DRM_PANEL_RONBO_RB070D30) += panel-ronbo-rb070d30.o
+obj-$(CONFIG_DRM_PANEL_SAMSUNG_ATNA33XC20) += panel-samsung-atna33xc20.o
+obj-$(CONFIG_DRM_PANEL_SAMSUNG_DB7430) += panel-samsung-db7430.o
 obj-$(CONFIG_DRM_PANEL_SAMSUNG_LD9040) += panel-samsung-ld9040.o
 obj-$(CONFIG_DRM_PANEL_SAMSUNG_S6D16D0) += panel-samsung-s6d16d0.o
 obj-$(CONFIG_DRM_PANEL_SAMSUNG_S6E3HA2) += panel-samsung-s6e3ha2.o
@@ -58,4 +62,5 @@ obj-$(CONFIG_DRM_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o
 obj-$(CONFIG_DRM_PANEL_TPO_TPG110) += panel-tpo-tpg110.o
 obj-$(CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA) += panel-truly-nt35597.o
 obj-$(CONFIG_DRM_PANEL_VISIONOX_RM69299) += panel-visionox-rm69299.o
+obj-$(CONFIG_DRM_PANEL_WIDECHIPS_WS2401) += panel-widechips-ws2401.o
 obj-$(CONFIG_DRM_PANEL_XINPENG_XPP055C272) += panel-xinpeng-xpp055c272.o
diff --git a/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c b/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
index e95bc9f60b3f..44674ebedf59 100644
--- a/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
+++ b/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
@@ -302,7 +302,7 @@ static int tm5p5_nt35596_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_MODE_EOT_PACKET |
+			  MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_MODE_NO_EOT_PACKET |
 			  MIPI_DSI_CLOCK_NON_CONTINUOUS | MIPI_DSI_MODE_LPM;
 
 	drm_panel_init(&ctx->panel, dev, &tm5p5_nt35596_panel_funcs,
diff --git a/drivers/gpu/drm/panel/panel-dsi-cm.c b/drivers/gpu/drm/panel/panel-dsi-cm.c
index 5fbfb71ca3d9..da4a69067e18 100644
--- a/drivers/gpu/drm/panel/panel-dsi-cm.c
+++ b/drivers/gpu/drm/panel/panel-dsi-cm.c
@@ -574,7 +574,7 @@ static int dsicm_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 2;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_CLOCK_NON_CONTINUOUS |
-			  MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_NO_EOT_PACKET;
 	dsi->hs_rate = ddata->panel_data->max_hs_rate;
 	dsi->lp_rate = ddata->panel_data->max_lp_rate;
 
diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c
index 4787f0833264..80227617a4d6 100644
--- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c
+++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c
@@ -273,7 +273,7 @@ static int kd35t133_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 1;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET |
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET |
 			  MIPI_DSI_CLOCK_NON_CONTINUOUS;
 
 	drm_panel_init(&ctx->panel, &dsi->dev, &kd35t133_funcs,
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
new file mode 100644
index 000000000000..2c3378a259b1
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Ilitek ILI9341 TFT LCD drm_panel driver.
+ *
+ * This panel can be configured to support:
+ * - 16-bit parallel RGB interface
+ * - 18-bit parallel RGB interface
+ * - 4-line serial spi interface
+ *
+ * Copyright (C) 2021 Dillon Min <dillon.minfei@gmail.com>
+ *
+ * For dbi+dpi part:
+ * Derived from drivers/drm/gpu/panel/panel-ilitek-ili9322.c
+ * the reuse of DBI abstraction part referred from Linus's patch
+ * "drm/panel: s6e63m0: Switch to DBI abstraction for SPI"
+ *
+ * For only-dbi part, copy from David's code (drm/tiny/ili9341.c)
+ * Copyright 2018 David Lechner <david@lechnology.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+
+#include <video/mipi_display.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_atomic_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_mipi_dbi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
+#define ILI9341_RGB_INTERFACE  0xb0   /* RGB Interface Signal Control */
+#define ILI9341_FRC            0xb1   /* Frame Rate Control register */
+#define ILI9341_DFC            0xb6   /* Display Function Control register */
+#define ILI9341_POWER1         0xc0   /* Power Control 1 register */
+#define ILI9341_POWER2         0xc1   /* Power Control 2 register */
+#define ILI9341_VCOM1          0xc5   /* VCOM Control 1 register */
+#define ILI9341_VCOM2          0xc7   /* VCOM Control 2 register */
+#define ILI9341_POWERA         0xcb   /* Power control A register */
+#define ILI9341_POWERB         0xcf   /* Power control B register */
+#define ILI9341_PGAMMA         0xe0   /* Positive Gamma Correction register */
+#define ILI9341_NGAMMA         0xe1   /* Negative Gamma Correction register */
+#define ILI9341_DTCA           0xe8   /* Driver timing control A */
+#define ILI9341_DTCB           0xea   /* Driver timing control B */
+#define ILI9341_POWER_SEQ      0xed   /* Power on sequence register */
+#define ILI9341_3GAMMA_EN      0xf2   /* 3 Gamma enable register */
+#define ILI9341_INTERFACE      0xf6   /* Interface control register */
+#define ILI9341_PRC            0xf7   /* Pump ratio control register */
+#define ILI9341_ETMOD	       0xb7   /* Entry mode set */
+
+#define ILI9341_MADCTL_BGR	BIT(3)
+#define ILI9341_MADCTL_MV	BIT(5)
+#define ILI9341_MADCTL_MX	BIT(6)
+#define ILI9341_MADCTL_MY	BIT(7)
+
+#define ILI9341_POWER_B_LEN	3
+#define ILI9341_POWER_SEQ_LEN	4
+#define ILI9341_DTCA_LEN	3
+#define ILI9341_DTCB_LEN	2
+#define ILI9341_POWER_A_LEN	5
+#define ILI9341_DFC_1_LEN	2
+#define ILI9341_FRC_LEN		2
+#define ILI9341_VCOM_1_LEN	2
+#define ILI9341_DFC_2_LEN	4
+#define ILI9341_COLUMN_ADDR_LEN	4
+#define ILI9341_PAGE_ADDR_LEN	4
+#define ILI9341_INTERFACE_LEN	3
+#define ILI9341_PGAMMA_LEN	15
+#define ILI9341_NGAMMA_LEN	15
+#define ILI9341_CA_LEN		3
+
+#define ILI9341_PIXEL_DPI_16_BITS	(BIT(6) | BIT(4))
+#define ILI9341_PIXEL_DPI_18_BITS	(BIT(6) | BIT(5))
+#define ILI9341_GAMMA_CURVE_1		BIT(0)
+#define ILI9341_IF_WE_MODE		BIT(0)
+#define ILI9341_IF_BIG_ENDIAN		0x00
+#define ILI9341_IF_DM_RGB		BIT(2)
+#define ILI9341_IF_DM_INTERNAL		0x00
+#define ILI9341_IF_DM_VSYNC		BIT(3)
+#define ILI9341_IF_RM_RGB		BIT(1)
+#define ILI9341_IF_RIM_RGB		0x00
+
+#define ILI9341_COLUMN_ADDR		0x00ef
+#define ILI9341_PAGE_ADDR		0x013f
+
+#define ILI9341_RGB_EPL			BIT(0)
+#define ILI9341_RGB_DPL			BIT(1)
+#define ILI9341_RGB_HSPL		BIT(2)
+#define ILI9341_RGB_VSPL		BIT(3)
+#define ILI9341_RGB_DE_MODE		BIT(6)
+#define ILI9341_RGB_DISP_PATH_MEM	BIT(7)
+
+#define ILI9341_DBI_VCOMH_4P6V		0x23
+#define ILI9341_DBI_PWR_2_DEFAULT	0x10
+#define ILI9341_DBI_PRC_NORMAL		0x20
+#define ILI9341_DBI_VCOM_1_VMH_4P25V	0x3e
+#define ILI9341_DBI_VCOM_1_VML_1P5V	0x28
+#define ILI9341_DBI_VCOM_2_DEC_58	0x86
+#define ILI9341_DBI_FRC_DIVA		0x00
+#define ILI9341_DBI_FRC_RTNA		0x1b
+#define ILI9341_DBI_EMS_GAS		BIT(0)
+#define ILI9341_DBI_EMS_DTS		BIT(1)
+#define ILI9341_DBI_EMS_GON		BIT(2)
+
+/* struct ili9341_config - the system specific ILI9341 configuration */
+struct ili9341_config {
+	u32 max_spi_speed;
+	/* mode: the drm display mode */
+	const struct drm_display_mode mode;
+	/* ca: TODO: need comments for this register */
+	u8 ca[ILI9341_CA_LEN];
+	/* power_b: TODO: need comments for this register */
+	u8 power_b[ILI9341_POWER_B_LEN];
+	/* power_seq: TODO: need comments for this register */
+	u8 power_seq[ILI9341_POWER_SEQ_LEN];
+	/* dtca: TODO: need comments for this register */
+	u8 dtca[ILI9341_DTCA_LEN];
+	/* dtcb: TODO: need comments for this register */
+	u8 dtcb[ILI9341_DTCB_LEN];
+	/* power_a: TODO: need comments for this register */
+	u8 power_a[ILI9341_POWER_A_LEN];
+	/* frc: Frame Rate Control (In Normal Mode/Full Colors) (B1h) */
+	u8 frc[ILI9341_FRC_LEN];
+	/* prc: TODO: need comments for this register */
+	u8 prc;
+	/* dfc_1: B6h DISCTRL (Display Function Control) */
+	u8 dfc_1[ILI9341_DFC_1_LEN];
+	/* power_1: Power Control 1 (C0h) */
+	u8 power_1;
+	/* power_2: Power Control 2 (C1h) */
+	u8 power_2;
+	/* vcom_1: VCOM Control 1(C5h) */
+	u8 vcom_1[ILI9341_VCOM_1_LEN];
+	/* vcom_2: VCOM Control 2(C7h) */
+	u8 vcom_2;
+	/* address_mode: Memory Access Control (36h) */
+	u8 address_mode;
+	/* g3amma_en: TODO: need comments for this register */
+	u8 g3amma_en;
+	/* rgb_interface: RGB Interface Signal Control (B0h) */
+	u8 rgb_interface;
+	/* dfc_2: refer to dfc_1 */
+	u8 dfc_2[ILI9341_DFC_2_LEN];
+	/* column_addr: Column Address Set (2Ah) */
+	u8 column_addr[ILI9341_COLUMN_ADDR_LEN];
+	/* page_addr: Page Address Set (2Bh) */
+	u8 page_addr[ILI9341_PAGE_ADDR_LEN];
+	/* interface: Interface Control (F6h) */
+	u8 interface[ILI9341_INTERFACE_LEN];
+	/*
+	 * pixel_format: This command sets the pixel format for the RGB
+	 * image data used by
+	 */
+	u8 pixel_format;
+	/*
+	 * gamma_curve: This command is used to select the desired Gamma
+	 * curve for the
+	 */
+	u8 gamma_curve;
+	/* pgamma: Positive Gamma Correction (E0h) */
+	u8 pgamma[ILI9341_PGAMMA_LEN];
+	/* ngamma: Negative Gamma Correction (E1h) */
+	u8 ngamma[ILI9341_NGAMMA_LEN];
+};
+
+struct ili9341 {
+	struct device *dev;
+	const struct ili9341_config *conf;
+	struct drm_panel panel;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *dc_gpio;
+	struct mipi_dbi *dbi;
+	u32 max_spi_speed;
+	struct regulator_bulk_data supplies[3];
+};
+
+/*
+ * The Stm32f429-disco board has a panel ili9341 connected to ltdc controller
+ */
+static const struct ili9341_config ili9341_stm32f429_disco_data = {
+	.max_spi_speed = 10000000,
+	.mode = {
+		.clock = 6100,
+		.hdisplay = 240,
+		.hsync_start = 240 + 10,/* hfp 10 */
+		.hsync_end = 240 + 10 + 10,/* hsync 10 */
+		.htotal = 240 + 10 + 10 + 20,/* hbp 20 */
+		.vdisplay = 320,
+		.vsync_start = 320 + 4,/* vfp 4 */
+		.vsync_end = 320 + 4 + 2,/* vsync 2 */
+		.vtotal = 320 + 4 + 2 + 2,/* vbp 2 */
+		.flags = 0,
+		.width_mm = 65,
+		.height_mm = 50,
+		.type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
+	},
+	.ca = {0xc3, 0x08, 0x50},
+	.power_b = {0x00, 0xc1, 0x30},
+	.power_seq = {0x64, 0x03, 0x12, 0x81},
+	.dtca = {0x85, 0x00, 0x78},
+	.power_a = {0x39, 0x2c, 0x00, 0x34, 0x02},
+	.prc = 0x20,
+	.dtcb = {0x00, 0x00},
+	/* 0x00 fosc, 0x1b 70hz */
+	.frc = {0x00, 0x1b},
+	/*
+	 * 0x0a Interval scan, AGND AGND AGND AGND
+	 * 0xa2 Normally white, G1 -> G320, S720 -> S1,
+	 *	Scan Cycle 5 frames,85ms
+	 */
+	.dfc_1 = {0x0a, 0xa2},
+	/* 0x10 3.65v */
+	.power_1 = 0x10,
+	/* 0x10 AVDD=vci*2, VGH=vci*7, VGL=-vci*4 */
+	.power_2 = 0x10,
+	/* 0x45 VCOMH 4.425v, 0x15 VCOML -1.975*/
+	.vcom_1 = {0x45, 0x15},
+	/* 0x90 offset voltage, VMH-48, VML-48 */
+	.vcom_2 = 0x90,
+	/*
+	 * 0xc8 Row Address Order, Column Address Order
+	 * BGR 1
+	 */
+	.address_mode = 0xc8,
+	.g3amma_en = 0x00,
+	/*
+	 * 0xc2
+	 * Display Data Path: Memory
+	 * RGB: DE mode
+	 * DOTCLK polarity set (data fetched at the falling time)
+	 */
+	.rgb_interface = ILI9341_RGB_DISP_PATH_MEM |
+			ILI9341_RGB_DE_MODE |
+			ILI9341_RGB_DPL,
+	/*
+	 * 0x0a
+	 * Gate outputs in non-display area: Interval scan
+	 * Determine source/VCOM output in a non-display area in the partial
+	 * display mode: AGND AGND AGND AGND
+	 *
+	 * 0xa7
+	 * Scan Cycle: 15 frames
+	 * fFLM = 60Hz: 255ms
+	 * Liquid crystal type: Normally white
+	 * Gate Output Scan Direction: G1 -> G320
+	 * Source Output Scan Direction: S720 -> S1
+	 *
+	 * 0x27
+	 * LCD Driver Line: 320 lines
+	 *
+	 * 0x04
+	 * PCDIV: 4
+	 */
+	.dfc_2 = {0x0a, 0xa7, 0x27, 0x04},
+	/* column address: 240 */
+	.column_addr = {0x00, 0x00, (ILI9341_COLUMN_ADDR >> 4) & 0xff,
+				ILI9341_COLUMN_ADDR & 0xff},
+	/* page address: 320 */
+	.page_addr = {0x00, 0x00, (ILI9341_PAGE_ADDR >> 4) & 0xff,
+				ILI9341_PAGE_ADDR & 0xff},
+	/*
+	 * Memory write control: When the transfer number of data exceeds
+	 * (EC-SC+1)*(EP-SP+1), the column and page number will be
+	 * reset, and the exceeding data will be written into the following
+	 * column and page.
+	 * Display Operation Mode: RGB Interface Mode
+	 * Interface for RAM Access: RGB interface
+	 * 16- bit RGB interface (1 transfer/pixel)
+	 */
+	.interface = {ILI9341_IF_WE_MODE, 0x00,
+			ILI9341_IF_DM_RGB | ILI9341_IF_RM_RGB},
+	/* DPI: 16 bits / pixel */
+	.pixel_format = ILI9341_PIXEL_DPI_16_BITS,
+	/* Curve Selected: Gamma curve 1 (G2.2) */
+	.gamma_curve = ILI9341_GAMMA_CURVE_1,
+	.pgamma = {0x0f, 0x29, 0x24, 0x0c, 0x0e,
+			0x09, 0x4e, 0x78, 0x3c, 0x09,
+			0x13, 0x05, 0x17, 0x11, 0x00},
+	.ngamma = {0x00, 0x16, 0x1b, 0x04, 0x11,
+			0x07, 0x31, 0x33, 0x42, 0x05,
+			0x0c, 0x0a, 0x28, 0x2f, 0x0f},
+};
+
+static inline struct ili9341 *panel_to_ili9341(struct drm_panel *panel)
+{
+	return container_of(panel, struct ili9341, panel);
+}
+
+static void ili9341_dpi_init(struct ili9341 *ili)
+{
+	struct device *dev = (&ili->panel)->dev;
+	struct mipi_dbi *dbi = ili->dbi;
+	struct ili9341_config *cfg = (struct ili9341_config *)ili->conf;
+
+	/* Power Control */
+	mipi_dbi_command_stackbuf(dbi, 0xca, cfg->ca, ILI9341_CA_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_POWERB, cfg->power_b,
+				  ILI9341_POWER_B_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_POWER_SEQ, cfg->power_seq,
+				  ILI9341_POWER_SEQ_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_DTCA, cfg->dtca,
+				  ILI9341_DTCA_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_POWERA, cfg->power_a,
+				  ILI9341_POWER_A_LEN);
+	mipi_dbi_command(ili->dbi, ILI9341_PRC, cfg->prc);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_DTCB, cfg->dtcb,
+				  ILI9341_DTCB_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_FRC, cfg->frc, ILI9341_FRC_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_DFC, cfg->dfc_1,
+				  ILI9341_DFC_1_LEN);
+	mipi_dbi_command(dbi, ILI9341_POWER1, cfg->power_1);
+	mipi_dbi_command(dbi, ILI9341_POWER2, cfg->power_2);
+
+	/* VCOM */
+	mipi_dbi_command_stackbuf(dbi, ILI9341_VCOM1, cfg->vcom_1,
+				  ILI9341_VCOM_1_LEN);
+	mipi_dbi_command(dbi, ILI9341_VCOM2, cfg->vcom_2);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, cfg->address_mode);
+
+	/* Gamma */
+	mipi_dbi_command(dbi, ILI9341_3GAMMA_EN, cfg->g3amma_en);
+	mipi_dbi_command(dbi, ILI9341_RGB_INTERFACE, cfg->rgb_interface);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_DFC, cfg->dfc_2,
+				  ILI9341_DFC_2_LEN);
+
+	/* Colomn address set */
+	mipi_dbi_command_stackbuf(dbi, MIPI_DCS_SET_COLUMN_ADDRESS,
+				  cfg->column_addr, ILI9341_COLUMN_ADDR_LEN);
+
+	/* Page address set */
+	mipi_dbi_command_stackbuf(dbi, MIPI_DCS_SET_PAGE_ADDRESS,
+				  cfg->page_addr, ILI9341_PAGE_ADDR_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_INTERFACE, cfg->interface,
+				  ILI9341_INTERFACE_LEN);
+
+	/* Format */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_PIXEL_FORMAT, cfg->pixel_format);
+	mipi_dbi_command(dbi, MIPI_DCS_WRITE_MEMORY_START);
+	msleep(200);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_GAMMA_CURVE, cfg->gamma_curve);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_PGAMMA, cfg->pgamma,
+				  ILI9341_PGAMMA_LEN);
+	mipi_dbi_command_stackbuf(dbi, ILI9341_NGAMMA, cfg->ngamma,
+				  ILI9341_NGAMMA_LEN);
+	mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(200);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON);
+	mipi_dbi_command(dbi, MIPI_DCS_WRITE_MEMORY_START);
+
+	dev_info(dev, "Initialized display rgb interface\n");
+}
+
+static int ili9341_dpi_power_on(struct ili9341 *ili)
+{
+	struct device *dev = (&ili->panel)->dev;
+	int ret = 0;
+
+	/* Assert RESET */
+	gpiod_set_value(ili->reset_gpio, 1);
+
+	/* Enable power */
+	ret = regulator_bulk_enable(ARRAY_SIZE(ili->supplies),
+				    ili->supplies);
+	if (ret < 0) {
+		dev_err(dev, "unable to enable vcc\n");
+		return ret;
+	}
+	msleep(20);
+
+	/* De-assert RESET */
+	gpiod_set_value(ili->reset_gpio, 0);
+	msleep(20);
+
+	return 0;
+}
+
+static int ili9341_dpi_power_off(struct ili9341 *ili)
+{
+	/* Assert RESET */
+	gpiod_set_value(ili->reset_gpio, 1);
+
+	/* Disable power */
+	return regulator_bulk_disable(ARRAY_SIZE(ili->supplies),
+				      ili->supplies);
+}
+
+static int ili9341_dpi_disable(struct drm_panel *panel)
+{
+	struct ili9341 *ili = panel_to_ili9341(panel);
+
+	mipi_dbi_command(ili->dbi, MIPI_DCS_SET_DISPLAY_OFF);
+	return 0;
+}
+
+static int ili9341_dpi_unprepare(struct drm_panel *panel)
+{
+	struct ili9341 *ili = panel_to_ili9341(panel);
+
+	return ili9341_dpi_power_off(ili);
+}
+
+static int ili9341_dpi_prepare(struct drm_panel *panel)
+{
+	struct ili9341 *ili = panel_to_ili9341(panel);
+	int ret;
+
+	ret = ili9341_dpi_power_on(ili);
+	if (ret < 0)
+		return ret;
+
+	ili9341_dpi_init(ili);
+
+	return ret;
+}
+
+static int ili9341_dpi_enable(struct drm_panel *panel)
+{
+	struct ili9341 *ili = panel_to_ili9341(panel);
+
+	mipi_dbi_command(ili->dbi, MIPI_DCS_SET_DISPLAY_ON);
+	return 0;
+}
+
+static int ili9341_dpi_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
+{
+	struct ili9341 *ili = panel_to_ili9341(panel);
+	struct drm_device *drm = connector->dev;
+	struct drm_display_mode *mode;
+	struct drm_display_info *info;
+
+	info = &connector->display_info;
+	info->width_mm = ili->conf->mode.width_mm;
+	info->height_mm = ili->conf->mode.height_mm;
+
+	if (ili->conf->rgb_interface & ILI9341_RGB_DPL)
+		info->bus_flags |= DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE;
+	else
+		info->bus_flags |= DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE;
+
+	if (ili->conf->rgb_interface & ILI9341_RGB_EPL)
+		info->bus_flags |= DRM_BUS_FLAG_DE_LOW;
+	else
+		info->bus_flags |= DRM_BUS_FLAG_DE_HIGH;
+
+	mode = drm_mode_duplicate(drm, &ili->conf->mode);
+	if (!mode) {
+		drm_err(drm, "bad mode or failed to add mode\n");
+		return -EINVAL;
+	}
+	drm_mode_set_name(mode);
+
+	/* Set up the polarity */
+	if (ili->conf->rgb_interface & ILI9341_RGB_HSPL)
+		mode->flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		mode->flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (ili->conf->rgb_interface & ILI9341_RGB_VSPL)
+		mode->flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		mode->flags |= DRM_MODE_FLAG_NVSYNC;
+
+	drm_mode_probed_add(connector, mode);
+
+	return 1; /* Number of modes */
+}
+
+static const struct drm_panel_funcs ili9341_dpi_funcs = {
+	.disable = ili9341_dpi_disable,
+	.unprepare = ili9341_dpi_unprepare,
+	.prepare = ili9341_dpi_prepare,
+	.enable = ili9341_dpi_enable,
+	.get_modes = ili9341_dpi_get_modes,
+};
+
+static void ili9341_dbi_enable(struct drm_simple_display_pipe *pipe,
+			       struct drm_crtc_state *crtc_state,
+			       struct drm_plane_state *plane_state)
+{
+	struct mipi_dbi_dev *dbidev = drm_to_mipi_dbi_dev(pipe->crtc.dev);
+	struct mipi_dbi *dbi = &dbidev->dbi;
+	u8 addr_mode;
+	int ret, idx;
+
+	if (!drm_dev_enter(pipe->crtc.dev, &idx))
+		return;
+
+	ret = mipi_dbi_poweron_conditional_reset(dbidev);
+	if (ret < 0)
+		goto out_exit;
+	if (ret == 1)
+		goto out_enable;
+
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_OFF);
+
+	mipi_dbi_command(dbi, ILI9341_POWERB, 0x00, 0xc1, 0x30);
+	mipi_dbi_command(dbi, ILI9341_POWER_SEQ, 0x64, 0x03, 0x12, 0x81);
+	mipi_dbi_command(dbi, ILI9341_DTCA, 0x85, 0x00, 0x78);
+	mipi_dbi_command(dbi, ILI9341_POWERA, 0x39, 0x2c, 0x00, 0x34, 0x02);
+	mipi_dbi_command(dbi, ILI9341_PRC, ILI9341_DBI_PRC_NORMAL);
+	mipi_dbi_command(dbi, ILI9341_DTCB, 0x00, 0x00);
+
+	/* Power Control */
+	mipi_dbi_command(dbi, ILI9341_POWER1, ILI9341_DBI_VCOMH_4P6V);
+	mipi_dbi_command(dbi, ILI9341_POWER2, ILI9341_DBI_PWR_2_DEFAULT);
+	/* VCOM */
+	mipi_dbi_command(dbi, ILI9341_VCOM1, ILI9341_DBI_VCOM_1_VMH_4P25V,
+			 ILI9341_DBI_VCOM_1_VML_1P5V);
+	mipi_dbi_command(dbi, ILI9341_VCOM2, ILI9341_DBI_VCOM_2_DEC_58);
+
+	/* Memory Access Control */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_PIXEL_FORMAT,
+			 MIPI_DCS_PIXEL_FMT_16BIT);
+
+	/* Frame Rate */
+	mipi_dbi_command(dbi, ILI9341_FRC, ILI9341_DBI_FRC_DIVA & 0x03,
+			 ILI9341_DBI_FRC_RTNA & 0x1f);
+
+	/* Gamma */
+	mipi_dbi_command(dbi, ILI9341_3GAMMA_EN, 0x00);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_GAMMA_CURVE, ILI9341_GAMMA_CURVE_1);
+	mipi_dbi_command(dbi, ILI9341_PGAMMA,
+			 0x0f, 0x31, 0x2b, 0x0c, 0x0e, 0x08, 0x4e, 0xf1,
+			 0x37, 0x07, 0x10, 0x03, 0x0e, 0x09, 0x00);
+	mipi_dbi_command(dbi, ILI9341_NGAMMA,
+			 0x00, 0x0e, 0x14, 0x03, 0x11, 0x07, 0x31, 0xc1,
+			 0x48, 0x08, 0x0f, 0x0c, 0x31, 0x36, 0x0f);
+
+	/* DDRAM */
+	mipi_dbi_command(dbi, ILI9341_ETMOD, ILI9341_DBI_EMS_GAS |
+			 ILI9341_DBI_EMS_DTS |
+			 ILI9341_DBI_EMS_GON);
+
+	/* Display */
+	mipi_dbi_command(dbi, ILI9341_DFC, 0x08, 0x82, 0x27, 0x00);
+	mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(100);
+
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON);
+	msleep(100);
+
+out_enable:
+	switch (dbidev->rotation) {
+	default:
+		addr_mode = ILI9341_MADCTL_MX;
+		break;
+	case 90:
+		addr_mode = ILI9341_MADCTL_MV;
+		break;
+	case 180:
+		addr_mode = ILI9341_MADCTL_MY;
+		break;
+	case 270:
+		addr_mode = ILI9341_MADCTL_MV | ILI9341_MADCTL_MY |
+			    ILI9341_MADCTL_MX;
+		break;
+	}
+
+	addr_mode |= ILI9341_MADCTL_BGR;
+	mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, addr_mode);
+	mipi_dbi_enable_flush(dbidev, crtc_state, plane_state);
+	drm_info(&dbidev->drm, "Initialized display serial interface\n");
+out_exit:
+	drm_dev_exit(idx);
+}
+
+static const struct drm_simple_display_pipe_funcs ili9341_dbi_funcs = {
+	.enable = ili9341_dbi_enable,
+	.disable = mipi_dbi_pipe_disable,
+	.update = mipi_dbi_pipe_update,
+	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
+};
+
+static const struct drm_display_mode ili9341_dbi_mode = {
+	DRM_SIMPLE_MODE(240, 320, 37, 49),
+};
+
+DEFINE_DRM_GEM_CMA_FOPS(ili9341_dbi_fops);
+
+static struct drm_driver ili9341_dbi_driver = {
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
+	.fops			= &ili9341_dbi_fops,
+	DRM_GEM_CMA_DRIVER_OPS_VMAP,
+	.debugfs_init		= mipi_dbi_debugfs_init,
+	.name			= "ili9341",
+	.desc			= "Ilitek ILI9341",
+	.date			= "20210716",
+	.major			= 1,
+	.minor			= 0,
+};
+
+static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc,
+			     struct gpio_desc *reset)
+{
+	struct device *dev = &spi->dev;
+	struct mipi_dbi_dev *dbidev;
+	struct mipi_dbi *dbi;
+	struct drm_device *drm;
+	struct regulator *vcc;
+	u32 rotation = 0;
+	int ret;
+
+	vcc = devm_regulator_get_optional(dev, "vcc");
+	if (IS_ERR(vcc))
+		dev_err(dev, "get optional vcc failed\n");
+
+	dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver,
+				    struct mipi_dbi_dev, drm);
+	if (IS_ERR(dbidev))
+		return PTR_ERR(dbidev);
+
+	dbi = &dbidev->dbi;
+	drm = &dbidev->drm;
+	dbi->reset = reset;
+	dbidev->regulator = vcc;
+
+	drm_mode_config_init(drm);
+
+	dbidev->backlight = devm_of_find_backlight(dev);
+	if (IS_ERR(dbidev->backlight))
+		return PTR_ERR(dbidev->backlight);
+
+	device_property_read_u32(dev, "rotation", &rotation);
+
+	ret = mipi_dbi_spi_init(spi, dbi, dc);
+	if (ret)
+		return ret;
+
+	ret = mipi_dbi_dev_init(dbidev, &ili9341_dbi_funcs,
+				&ili9341_dbi_mode, rotation);
+	if (ret)
+		return ret;
+
+	drm_mode_config_reset(drm);
+
+	ret = drm_dev_register(drm, 0);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, drm);
+
+	drm_fbdev_generic_setup(drm, 0);
+
+	return 0;
+}
+
+static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc,
+			     struct gpio_desc *reset)
+{
+	struct device *dev = &spi->dev;
+	struct ili9341 *ili;
+	int ret;
+
+	ili = devm_kzalloc(dev, sizeof(struct ili9341), GFP_KERNEL);
+	if (!ili)
+		return -ENOMEM;
+
+	ili->dbi = devm_kzalloc(dev, sizeof(struct mipi_dbi),
+				GFP_KERNEL);
+	if (!ili->dbi)
+		return -ENOMEM;
+
+	ili->supplies[0].supply = "vci";
+	ili->supplies[1].supply = "vddi";
+	ili->supplies[2].supply = "vddi-led";
+	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ili->supplies),
+				      ili->supplies);
+	if (ret < 0) {
+		dev_err(dev, "failed to get regulators: %d\n", ret);
+		return ret;
+	}
+
+	ret = mipi_dbi_spi_init(spi, ili->dbi, dc);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, ili);
+	ili->reset_gpio = reset;
+	/*
+	 * Every new incarnation of this display must have a unique
+	 * data entry for the system in this driver.
+	 */
+	ili->conf = of_device_get_match_data(dev);
+	if (!ili->conf) {
+		dev_err(dev, "missing device configuration\n");
+		return -ENODEV;
+	}
+
+	ili->max_spi_speed = ili->conf->max_spi_speed;
+	drm_panel_init(&ili->panel, dev, &ili9341_dpi_funcs,
+		       DRM_MODE_CONNECTOR_DPI);
+	drm_panel_add(&ili->panel);
+
+	return 0;
+}
+
+static int ili9341_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct gpio_desc *dc;
+	struct gpio_desc *reset;
+	const struct spi_device_id *id = spi_get_device_id(spi);
+
+	reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(reset))
+		dev_err(dev, "Failed to get gpio 'reset'\n");
+
+	dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
+	if (IS_ERR(dc))
+		dev_err(dev, "Failed to get gpio 'dc'\n");
+
+	if (!strcmp(id->name, "sf-tc240t-9370-t"))
+		return ili9341_dpi_probe(spi, dc, reset);
+	else if (!strcmp(id->name, "yx240qv29"))
+		return ili9341_dbi_probe(spi, dc, reset);
+
+	return -1;
+}
+
+static int ili9341_remove(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct ili9341 *ili = spi_get_drvdata(spi);
+	struct drm_device *drm = spi_get_drvdata(spi);
+
+	if (!strcmp(id->name, "sf-tc240t-9370-t")) {
+		ili9341_dpi_power_off(ili);
+		drm_panel_remove(&ili->panel);
+	} else if (!strcmp(id->name, "yx240qv29")) {
+		drm_dev_unplug(drm);
+		drm_atomic_helper_shutdown(drm);
+	}
+	return 0;
+}
+
+static void ili9341_shutdown(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+
+	if (!strcmp(id->name, "yx240qv29"))
+		drm_atomic_helper_shutdown(spi_get_drvdata(spi));
+}
+
+static const struct of_device_id ili9341_of_match[] = {
+	{
+		.compatible = "st,sf-tc240t-9370-t",
+		.data = &ili9341_stm32f429_disco_data,
+	},
+	{
+		/* porting from tiny/ili9341.c
+		 * for original mipi dbi compitable
+		 */
+		.compatible = "adafruit,yx240qv29",
+		.data = NULL,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ili9341_of_match);
+
+static const struct spi_device_id ili9341_id[] = {
+	{ "yx240qv29", 0 },
+	{ "sf-tc240t-9370-t", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ili9341_id);
+
+static struct spi_driver ili9341_driver = {
+	.probe = ili9341_probe,
+	.remove = ili9341_remove,
+	.shutdown = ili9341_shutdown,
+	.id_table = ili9341_id,
+	.driver = {
+		.name = "panel-ilitek-ili9341",
+		.of_match_table = ili9341_of_match,
+	},
+};
+module_spi_driver(ili9341_driver);
+
+MODULE_AUTHOR("Dillon Min <dillon.minfei@gmail.com>");
+MODULE_DESCRIPTION("ILI9341 LCD panel driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-innolux-ej030na.c b/drivers/gpu/drm/panel/panel-innolux-ej030na.c
new file mode 100644
index 000000000000..34b98f70bd22
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-innolux-ej030na.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Innolux/Chimei EJ030NA TFT LCD panel driver
+ *
+ * Copyright (C) 2020, Paul Cercueil <paul@crapouillou.net>
+ * Copyright (C) 2020, Christophe Branchereau <cbranchereau@gmail.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/media-bus-format.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+
+struct ej030na_info {
+	const struct drm_display_mode *display_modes;
+	unsigned int num_modes;
+	u16 width_mm, height_mm;
+	u32 bus_format, bus_flags;
+};
+
+struct ej030na {
+	struct drm_panel panel;
+	struct spi_device *spi;
+	struct regmap *map;
+
+	const struct ej030na_info *panel_info;
+
+	struct regulator *supply;
+	struct gpio_desc *reset_gpio;
+};
+
+static inline struct ej030na *to_ej030na(struct drm_panel *panel)
+{
+	return container_of(panel, struct ej030na, panel);
+}
+
+static const struct reg_sequence ej030na_init_sequence[] = {
+	{ 0x05, 0x1e },
+	{ 0x05, 0x5c },
+	{ 0x02, 0x14 },
+	{ 0x03, 0x40 },
+	{ 0x04, 0x07 },
+	{ 0x06, 0x12 },
+	{ 0x07, 0xd2 },
+	{ 0x0c, 0x06 },
+	{ 0x0d, 0x40 },
+	{ 0x0e, 0x40 },
+	{ 0x0f, 0x40 },
+	{ 0x10, 0x40 },
+	{ 0x11, 0x40 },
+	{ 0x2f, 0x40 },
+	{ 0x5a, 0x02 },
+
+	{ 0x30, 0x07 },
+	{ 0x31, 0x57 },
+	{ 0x32, 0x53 },
+	{ 0x33, 0x77 },
+	{ 0x34, 0xb8 },
+	{ 0x35, 0xbd },
+	{ 0x36, 0xb8 },
+	{ 0x37, 0xe7 },
+	{ 0x38, 0x04 },
+	{ 0x39, 0xff },
+
+	{ 0x40, 0x0b },
+	{ 0x41, 0xb8 },
+	{ 0x42, 0xab },
+	{ 0x43, 0xb9 },
+	{ 0x44, 0x6a },
+	{ 0x45, 0x56 },
+	{ 0x46, 0x61 },
+	{ 0x47, 0x08 },
+	{ 0x48, 0x0f },
+	{ 0x49, 0x0f },
+
+	{ 0x2b, 0x01 },
+};
+
+static int ej030na_prepare(struct drm_panel *panel)
+{
+	struct ej030na *priv = to_ej030na(panel);
+	struct device *dev = &priv->spi->dev;
+	int err;
+
+	err = regulator_enable(priv->supply);
+	if (err) {
+		dev_err(dev, "Failed to enable power supply: %d\n", err);
+		return err;
+	}
+
+	/* Reset the chip */
+	gpiod_set_value_cansleep(priv->reset_gpio, 1);
+	usleep_range(50, 150);
+	gpiod_set_value_cansleep(priv->reset_gpio, 0);
+	usleep_range(50, 150);
+
+	err = regmap_multi_reg_write(priv->map, ej030na_init_sequence,
+				     ARRAY_SIZE(ej030na_init_sequence));
+	if (err) {
+		dev_err(dev, "Failed to init registers: %d\n", err);
+		goto err_disable_regulator;
+	}
+
+	msleep(120);
+
+	return 0;
+
+err_disable_regulator:
+	regulator_disable(priv->supply);
+	return err;
+}
+
+static int ej030na_unprepare(struct drm_panel *panel)
+{
+	struct ej030na *priv = to_ej030na(panel);
+
+	gpiod_set_value_cansleep(priv->reset_gpio, 1);
+	regulator_disable(priv->supply);
+
+	return 0;
+}
+
+static int ej030na_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
+{
+	struct ej030na *priv = to_ej030na(panel);
+	const struct ej030na_info *panel_info = priv->panel_info;
+	struct drm_display_mode *mode;
+	unsigned int i;
+
+	for (i = 0; i < panel_info->num_modes; i++) {
+		mode = drm_mode_duplicate(connector->dev,
+					  &panel_info->display_modes[i]);
+		if (!mode)
+			return -ENOMEM;
+
+		drm_mode_set_name(mode);
+
+		mode->type = DRM_MODE_TYPE_DRIVER;
+		if (panel_info->num_modes == 1)
+			mode->type |= DRM_MODE_TYPE_PREFERRED;
+
+		drm_mode_probed_add(connector, mode);
+	}
+
+	connector->display_info.bpc = 8;
+	connector->display_info.width_mm = panel_info->width_mm;
+	connector->display_info.height_mm = panel_info->height_mm;
+
+	drm_display_info_set_bus_formats(&connector->display_info,
+					 &panel_info->bus_format, 1);
+	connector->display_info.bus_flags = panel_info->bus_flags;
+
+	return panel_info->num_modes;
+}
+
+static const struct drm_panel_funcs ej030na_funcs = {
+	.prepare	= ej030na_prepare,
+	.unprepare	= ej030na_unprepare,
+	.get_modes	= ej030na_get_modes,
+};
+
+static const struct regmap_config ej030na_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0x5a,
+};
+
+static int ej030na_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct ej030na *priv;
+	int err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->spi = spi;
+	spi_set_drvdata(spi, priv);
+
+	priv->map = devm_regmap_init_spi(spi, &ej030na_regmap_config);
+	if (IS_ERR(priv->map)) {
+		dev_err(dev, "Unable to init regmap\n");
+		return PTR_ERR(priv->map);
+	}
+
+	priv->panel_info = of_device_get_match_data(dev);
+	if (!priv->panel_info)
+		return -EINVAL;
+
+	priv->supply = devm_regulator_get(dev, "power");
+	if (IS_ERR(priv->supply)) {
+		dev_err(dev, "Failed to get power supply\n");
+		return PTR_ERR(priv->supply);
+	}
+
+	priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(priv->reset_gpio)) {
+		dev_err(dev, "Failed to get reset GPIO\n");
+		return PTR_ERR(priv->reset_gpio);
+	}
+
+	drm_panel_init(&priv->panel, dev, &ej030na_funcs,
+		       DRM_MODE_CONNECTOR_DPI);
+
+	err = drm_panel_of_backlight(&priv->panel);
+	if (err)
+		return err;
+
+	drm_panel_add(&priv->panel);
+
+	return 0;
+}
+
+static int ej030na_remove(struct spi_device *spi)
+{
+	struct ej030na *priv = spi_get_drvdata(spi);
+
+	drm_panel_remove(&priv->panel);
+	drm_panel_disable(&priv->panel);
+	drm_panel_unprepare(&priv->panel);
+
+	return 0;
+}
+
+static const struct drm_display_mode ej030na_modes[] = {
+	{ /* 60 Hz */
+		.clock = 14400,
+		.hdisplay = 320,
+		.hsync_start = 320 + 10,
+		.hsync_end = 320 + 10 + 37,
+		.htotal = 320 + 10 + 37 + 33,
+		.vdisplay = 480,
+		.vsync_start = 480 + 102,
+		.vsync_end = 480 + 102 + 9 + 9,
+		.vtotal = 480 + 102 + 9 + 9,
+		.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
+	},
+	{ /* 50 Hz */
+		.clock = 12000,
+		.hdisplay = 320,
+		.hsync_start = 320 + 10,
+		.hsync_end = 320 + 10 + 37,
+		.htotal = 320 + 10 + 37 + 33,
+		.vdisplay = 480,
+		.vsync_start = 480 + 102,
+		.vsync_end = 480 + 102 + 9,
+		.vtotal = 480 + 102 + 9 + 9,
+		.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
+	},
+};
+
+static const struct ej030na_info ej030na_info = {
+	.display_modes = ej030na_modes,
+	.num_modes = ARRAY_SIZE(ej030na_modes),
+	.width_mm = 70,
+	.height_mm = 51,
+	.bus_format = MEDIA_BUS_FMT_RGB888_3X8_DELTA,
+	.bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE | DRM_BUS_FLAG_DE_LOW,
+};
+
+static const struct of_device_id ej030na_of_match[] = {
+	{ .compatible = "innolux,ej030na", .data = &ej030na_info },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ej030na_of_match);
+
+static struct spi_driver ej030na_driver = {
+	.driver = {
+		.name = "panel-innolux-ej030na",
+		.of_match_table = ej030na_of_match,
+	},
+	.probe = ej030na_probe,
+	.remove = ej030na_remove,
+};
+module_spi_driver(ej030na_driver);
+
+MODULE_AUTHOR("Paul Cercueil <paul@crapouillou.net>");
+MODULE_AUTHOR("Christophe Branchereau <cbranchereau@gmail.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-khadas-ts050.c b/drivers/gpu/drm/panel/panel-khadas-ts050.c
index 8f6ac1a40c31..a3ec4cbdbf7a 100644
--- a/drivers/gpu/drm/panel/panel-khadas-ts050.c
+++ b/drivers/gpu/drm/panel/panel-khadas-ts050.c
@@ -809,7 +809,7 @@ static int khadas_ts050_panel_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	khadas_ts050 = devm_kzalloc(&dsi->dev, sizeof(*khadas_ts050),
 				    GFP_KERNEL);
diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
index ed0d5f959037..a5a414920430 100644
--- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
+++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
@@ -593,7 +593,7 @@ static int ltk050h3146w_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	drm_panel_init(&ctx->panel, &dsi->dev, &ltk050h3146w_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c b/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c
index 3c00e4f8f803..21e48923836d 100644
--- a/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c
+++ b/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c
@@ -442,7 +442,7 @@ static int ltk500hd1829_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	drm_panel_init(&ctx->panel, &dsi->dev, &ltk500hd1829_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
index 45b975dee587..198493a6eb6a 100644
--- a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
+++ b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
@@ -184,7 +184,7 @@ static int osd101t2587_panel_probe(struct mipi_dsi_device *dsi)
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO |
 			  MIPI_DSI_MODE_VIDEO_BURST |
 			  MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-			  MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	osd101t2587 = devm_kzalloc(&dsi->dev, sizeof(*osd101t2587), GFP_KERNEL);
 	if (!osd101t2587)
diff --git a/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c
new file mode 100644
index 000000000000..221db6512859
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2021 Google Inc.
+ *
+ * Panel driver for the Samsung ATNA33XC20 panel. This panel can't be handled
+ * by the DRM_PANEL_SIMPLE driver because its power sequencing is non-standard.
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+
+#include <drm/drm_dp_aux_bus.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_panel.h>
+
+struct atana33xc20_panel {
+	struct drm_panel base;
+	bool prepared;
+	bool enabled;
+	bool el3_was_on;
+
+	bool no_hpd;
+	struct gpio_desc *hpd_gpio;
+
+	struct regulator *supply;
+	struct gpio_desc *el_on3_gpio;
+
+	struct edid *edid;
+
+	ktime_t powered_off_time;
+	ktime_t powered_on_time;
+	ktime_t el_on3_off_time;
+};
+
+static inline struct atana33xc20_panel *to_atana33xc20(struct drm_panel *panel)
+{
+	return container_of(panel, struct atana33xc20_panel, base);
+}
+
+static void atana33xc20_wait(ktime_t start_ktime, unsigned int min_ms)
+{
+	ktime_t now_ktime, min_ktime;
+
+	min_ktime = ktime_add(start_ktime, ms_to_ktime(min_ms));
+	now_ktime = ktime_get();
+
+	if (ktime_before(now_ktime, min_ktime))
+		msleep(ktime_to_ms(ktime_sub(min_ktime, now_ktime)) + 1);
+}
+
+static int atana33xc20_suspend(struct device *dev)
+{
+	struct atana33xc20_panel *p = dev_get_drvdata(dev);
+	int ret;
+
+	/*
+	 * Note 3 (Example of power off sequence in detail) in spec
+	 * specifies to wait 150 ms after deasserting EL3_ON before
+	 * powering off.
+	 */
+	if (p->el3_was_on)
+		atana33xc20_wait(p->el_on3_off_time, 150);
+
+	ret = regulator_disable(p->supply);
+	if (ret)
+		return ret;
+	p->powered_off_time = ktime_get();
+	p->el3_was_on = false;
+
+	return 0;
+}
+
+static int atana33xc20_resume(struct device *dev)
+{
+	struct atana33xc20_panel *p = dev_get_drvdata(dev);
+	bool hpd_asserted = false;
+	int ret;
+
+	/* T12 (Power off time) is min 500 ms */
+	atana33xc20_wait(p->powered_off_time, 500);
+
+	ret = regulator_enable(p->supply);
+	if (ret)
+		return ret;
+	p->powered_on_time = ktime_get();
+
+	/*
+	 * Handle HPD. Note: if HPD is hooked up to a dedicated pin on the
+	 * eDP controller then "no_hpd" will be false _and_ "hpd_gpio" will be
+	 * NULL. It's up to the controller driver to wait for HPD after
+	 * preparing the panel in that case.
+	 */
+	if (p->no_hpd) {
+		/* T3 VCC to HPD high is max 200 ms */
+		msleep(200);
+	} else if (p->hpd_gpio) {
+		ret = readx_poll_timeout(gpiod_get_value_cansleep, p->hpd_gpio,
+					 hpd_asserted, hpd_asserted,
+					 1000, 200000);
+		if (!hpd_asserted)
+			dev_warn(dev, "Timeout waiting for HPD\n");
+	}
+
+	return 0;
+}
+
+static int atana33xc20_disable(struct drm_panel *panel)
+{
+	struct atana33xc20_panel *p = to_atana33xc20(panel);
+
+	/* Disabling when already disabled is a no-op */
+	if (!p->enabled)
+		return 0;
+
+	gpiod_set_value_cansleep(p->el_on3_gpio, 0);
+	p->el_on3_off_time = ktime_get();
+	p->enabled = false;
+
+	/*
+	 * Keep track of the fact that EL_ON3 was on but we haven't power
+	 * cycled yet. This lets us know that "el_on3_off_time" is recent (we
+	 * don't need to worry about ktime wraparounds) and also makes it
+	 * obvious if we try to enable again without a power cycle (see the
+	 * warning in atana33xc20_enable()).
+	 */
+	p->el3_was_on = true;
+
+	/*
+	 * Sleeping 20 ms here (after setting the GPIO) avoids a glitch when
+	 * powering off.
+	 */
+	msleep(20);
+
+	return 0;
+}
+
+static int atana33xc20_enable(struct drm_panel *panel)
+{
+	struct atana33xc20_panel *p = to_atana33xc20(panel);
+
+	/* Enabling when already enabled is a no-op */
+	if (p->enabled)
+		return 0;
+
+	/*
+	 * Once EL_ON3 drops we absolutely need a power cycle before the next
+	 * enable or the backlight will never come on again. The code ensures
+	 * this because disable() is _always_ followed by unprepare() and
+	 * unprepare() forces a suspend with pm_runtime_put_sync_suspend(),
+	 * but let's track just to make sure since the requirement is so
+	 * non-obvious.
+	 */
+	if (WARN_ON(p->el3_was_on))
+		return -EIO;
+
+	/*
+	 * Note 2 (Example of power on sequence in detail) in spec specifies
+	 * to wait 400 ms after powering on before asserting EL3_on.
+	 */
+	atana33xc20_wait(p->powered_on_time, 400);
+
+	gpiod_set_value_cansleep(p->el_on3_gpio, 1);
+	p->enabled = true;
+
+	return 0;
+}
+
+static int atana33xc20_unprepare(struct drm_panel *panel)
+{
+	struct atana33xc20_panel *p = to_atana33xc20(panel);
+	int ret;
+
+	/* Unpreparing when already unprepared is a no-op */
+	if (!p->prepared)
+		return 0;
+
+	/*
+	 * Purposely do a put_sync, don't use autosuspend. The panel's tcon
+	 * seems to sometimes crash when you stop giving it data and this is
+	 * the best way to ensure it will come back.
+	 *
+	 * NOTE: we still want autosuspend for cases where we only turn on
+	 * to get the EDID or otherwise send DP AUX commands to the panel.
+	 */
+	ret = pm_runtime_put_sync_suspend(panel->dev);
+	if (ret < 0)
+		return ret;
+	p->prepared = false;
+
+	return 0;
+}
+
+static int atana33xc20_prepare(struct drm_panel *panel)
+{
+	struct atana33xc20_panel *p = to_atana33xc20(panel);
+	int ret;
+
+	/* Preparing when already prepared is a no-op */
+	if (p->prepared)
+		return 0;
+
+	ret = pm_runtime_get_sync(panel->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(panel->dev);
+		return ret;
+	}
+	p->prepared = true;
+
+	return 0;
+}
+
+static int atana33xc20_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
+{
+	struct atana33xc20_panel *p = to_atana33xc20(panel);
+	struct dp_aux_ep_device *aux_ep = to_dp_aux_ep_dev(panel->dev);
+	int num = 0;
+
+	pm_runtime_get_sync(panel->dev);
+
+	if (!p->edid)
+		p->edid = drm_get_edid(connector, &aux_ep->aux->ddc);
+	num = drm_add_edid_modes(connector, p->edid);
+
+	pm_runtime_mark_last_busy(panel->dev);
+	pm_runtime_put_autosuspend(panel->dev);
+
+	return num;
+}
+
+static const struct drm_panel_funcs atana33xc20_funcs = {
+	.disable = atana33xc20_disable,
+	.enable = atana33xc20_enable,
+	.unprepare = atana33xc20_unprepare,
+	.prepare = atana33xc20_prepare,
+	.get_modes = atana33xc20_get_modes,
+};
+
+static void atana33xc20_runtime_disable(void *data)
+{
+	pm_runtime_disable(data);
+}
+
+static void atana33xc20_dont_use_autosuspend(void *data)
+{
+	pm_runtime_dont_use_autosuspend(data);
+}
+
+static int atana33xc20_probe(struct dp_aux_ep_device *aux_ep)
+{
+	struct atana33xc20_panel *panel;
+	struct device *dev = &aux_ep->dev;
+	int ret;
+
+	panel = devm_kzalloc(dev, sizeof(*panel), GFP_KERNEL);
+	if (!panel)
+		return -ENOMEM;
+	dev_set_drvdata(dev, panel);
+
+	panel->supply = devm_regulator_get(dev, "power");
+	if (IS_ERR(panel->supply))
+		return dev_err_probe(dev, PTR_ERR(panel->supply),
+				     "Failed to get power supply\n");
+
+	panel->el_on3_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(panel->el_on3_gpio))
+		return dev_err_probe(dev, PTR_ERR(panel->el_on3_gpio),
+				     "Failed to get enable GPIO\n");
+
+	panel->no_hpd = of_property_read_bool(dev->of_node, "no-hpd");
+	if (!panel->no_hpd) {
+		panel->hpd_gpio = devm_gpiod_get_optional(dev, "hpd", GPIOD_IN);
+		if (IS_ERR(panel->hpd_gpio))
+			return dev_err_probe(dev, PTR_ERR(panel->hpd_gpio),
+					     "Failed to get HPD GPIO\n");
+	}
+
+	pm_runtime_enable(dev);
+	ret = devm_add_action_or_reset(dev,  atana33xc20_runtime_disable, dev);
+	if (ret)
+		return ret;
+	pm_runtime_set_autosuspend_delay(dev, 1000);
+	pm_runtime_use_autosuspend(dev);
+	ret = devm_add_action_or_reset(dev,  atana33xc20_dont_use_autosuspend, dev);
+	if (ret)
+		return ret;
+
+	drm_panel_init(&panel->base, dev, &atana33xc20_funcs, DRM_MODE_CONNECTOR_eDP);
+
+	pm_runtime_get_sync(dev);
+	ret = drm_panel_dp_aux_backlight(&panel->base, aux_ep->aux);
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to register dp aux backlight\n");
+
+	drm_panel_add(&panel->base);
+
+	return 0;
+}
+
+static void atana33xc20_remove(struct dp_aux_ep_device *aux_ep)
+{
+	struct device *dev = &aux_ep->dev;
+	struct atana33xc20_panel *panel = dev_get_drvdata(dev);
+
+	drm_panel_remove(&panel->base);
+	drm_panel_disable(&panel->base);
+	drm_panel_unprepare(&panel->base);
+
+	kfree(panel->edid);
+}
+
+static void atana33xc20_shutdown(struct dp_aux_ep_device *aux_ep)
+{
+	struct device *dev = &aux_ep->dev;
+	struct atana33xc20_panel *panel = dev_get_drvdata(dev);
+
+	drm_panel_disable(&panel->base);
+	drm_panel_unprepare(&panel->base);
+}
+
+static const struct of_device_id atana33xc20_dt_match[] = {
+	{ .compatible = "samsung,atna33xc20", },
+	{ /* sentinal */ }
+};
+MODULE_DEVICE_TABLE(of, atana33xc20_dt_match);
+
+static const struct dev_pm_ops atana33xc20_pm_ops = {
+	SET_RUNTIME_PM_OPS(atana33xc20_suspend, atana33xc20_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static struct dp_aux_ep_driver atana33xc20_driver = {
+	.driver = {
+		.name		= "samsung_atana33xc20",
+		.of_match_table = atana33xc20_dt_match,
+		.pm		= &atana33xc20_pm_ops,
+	},
+	.probe = atana33xc20_probe,
+	.remove = atana33xc20_remove,
+	.shutdown = atana33xc20_shutdown,
+};
+
+static int __init atana33xc20_init(void)
+{
+	return dp_aux_dp_driver_register(&atana33xc20_driver);
+}
+module_init(atana33xc20_init);
+
+static void __exit atana33xc20_exit(void)
+{
+	dp_aux_dp_driver_unregister(&atana33xc20_driver);
+}
+module_exit(atana33xc20_exit);
+
+MODULE_DESCRIPTION("Samsung ATANA33XC20 Panel Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-samsung-db7430.c b/drivers/gpu/drm/panel/panel-samsung-db7430.c
new file mode 100644
index 000000000000..ead479719f00
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-samsung-db7430.c
@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Panel driver for the Samsung LMS397KF04 480x800 DPI RGB panel.
+ * According to the data sheet the display controller is called DB7430.
+ * Found in the Samsung Galaxy Beam GT-I8350 mobile phone.
+ * Linus Walleij <linus.walleij@linaro.org>
+ */
+#include <drm/drm_mipi_dbi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/media-bus-format.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+
+#include <video/mipi_display.h>
+
+#define DB7430_ACCESS_PROT_OFF		0xb0
+#define DB7430_UNKNOWN_B4		0xb4
+#define DB7430_USER_SELECT		0xb5
+#define DB7430_UNKNOWN_B7		0xb7
+#define DB7430_UNKNOWN_B8		0xb8
+#define DB7430_PANEL_DRIVING		0xc0
+#define DB7430_SOURCE_CONTROL		0xc1
+#define DB7430_GATE_INTERFACE		0xc4
+#define DB7430_DISPLAY_H_TIMING		0xc5
+#define DB7430_RGB_SYNC_OPTION		0xc6
+#define DB7430_GAMMA_SET_RED		0xc8
+#define DB7430_GAMMA_SET_GREEN		0xc9
+#define DB7430_GAMMA_SET_BLUE		0xca
+#define DB7430_BIAS_CURRENT_CTRL	0xd1
+#define DB7430_DDV_CTRL			0xd2
+#define DB7430_GAMMA_CTRL_REF		0xd3
+#define DB7430_UNKNOWN_D4		0xd4
+#define DB7430_DCDC_CTRL		0xd5
+#define DB7430_VCL_CTRL			0xd6
+#define DB7430_UNKNOWN_F8		0xf8
+#define DB7430_UNKNOWN_FC		0xfc
+
+#define DATA_MASK	0x100
+
+/**
+ * struct db7430 - state container for a panel controlled by the DB7430
+ * controller
+ */
+struct db7430 {
+	/** @dev: the container device */
+	struct device *dev;
+	/** @dbi: the DBI bus abstraction handle */
+	struct mipi_dbi dbi;
+	/** @panel: the DRM panel instance for this device */
+	struct drm_panel panel;
+	/** @width: the width of this panel in mm */
+	u32 width;
+	/** @height: the height of this panel in mm */
+	u32 height;
+	/** @reset: reset GPIO line */
+	struct gpio_desc *reset;
+	/** @regulators: VCCIO and VIO supply regulators */
+	struct regulator_bulk_data regulators[2];
+};
+
+static const struct drm_display_mode db7430_480_800_mode = {
+	/*
+	 * 31 ns period min (htotal*vtotal*vrefresh)/1000
+	 * gives a Vrefresh of ~71 Hz.
+	 */
+	.clock = 32258,
+	.hdisplay = 480,
+	.hsync_start = 480 + 10,
+	.hsync_end = 480 + 10 + 4,
+	.htotal = 480 + 10 + 4 + 40,
+	.vdisplay = 800,
+	.vsync_start = 800 + 6,
+	.vsync_end = 800 + 6 + 1,
+	.vtotal = 800 + 6 + 1 + 7,
+	.width_mm = 53,
+	.height_mm = 87,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static inline struct db7430 *to_db7430(struct drm_panel *panel)
+{
+	return container_of(panel, struct db7430, panel);
+}
+
+static int db7430_power_on(struct db7430 *db)
+{
+	struct mipi_dbi *dbi = &db->dbi;
+	int ret;
+
+	/* Power up */
+	ret = regulator_bulk_enable(ARRAY_SIZE(db->regulators),
+				    db->regulators);
+	if (ret) {
+		dev_err(db->dev, "failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+	msleep(50);
+
+	/* Assert reset >=1 ms */
+	gpiod_set_value_cansleep(db->reset, 1);
+	usleep_range(1000, 5000);
+	/* De-assert reset */
+	gpiod_set_value_cansleep(db->reset, 0);
+	/* Wait >= 10 ms */
+	msleep(10);
+	dev_dbg(db->dev, "de-asserted RESET\n");
+
+	/*
+	 * This is set to 0x0a (RGB/BGR order + horizontal flip) in order
+	 * to make the display behave normally. If this is not set the displays
+	 * normal output behaviour is horizontally flipped and BGR ordered. Do
+	 * it twice because the first message doesn't always "take".
+	 */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, 0x0a);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, 0x0a);
+	mipi_dbi_command(dbi, DB7430_ACCESS_PROT_OFF, 0x00);
+	mipi_dbi_command(dbi, DB7430_PANEL_DRIVING, 0x28, 0x08);
+	mipi_dbi_command(dbi, DB7430_SOURCE_CONTROL,
+			 0x01, 0x30, 0x15, 0x05, 0x22);
+	mipi_dbi_command(dbi, DB7430_GATE_INTERFACE,
+			 0x10, 0x01, 0x00);
+	mipi_dbi_command(dbi, DB7430_DISPLAY_H_TIMING,
+			 0x06, 0x55, 0x03, 0x07, 0x0b,
+			 0x33, 0x00, 0x01, 0x03);
+	/*
+	 * 0x00 in datasheet 0x01 in vendor code 0x00, it seems 0x01 means
+	 * DE active high and 0x00 means DE active low.
+	 */
+	mipi_dbi_command(dbi, DB7430_RGB_SYNC_OPTION, 0x01);
+	mipi_dbi_command(dbi, DB7430_GAMMA_SET_RED,
+		/* R positive gamma */ 0x00,
+		0x0A, 0x31, 0x3B, 0x4E, 0x58, 0x59, 0x5B, 0x58, 0x5E, 0x62,
+		0x60, 0x61, 0x5E, 0x62, 0x55, 0x55, 0x7F, 0x08,
+		/* R negative gamma */ 0x00,
+		0x0A, 0x31, 0x3B, 0x4E, 0x58, 0x59, 0x5B, 0x58, 0x5E, 0x62,
+		0x60, 0x61, 0x5E, 0x62, 0x55, 0x55, 0x7F, 0x08);
+	mipi_dbi_command(dbi, DB7430_GAMMA_SET_GREEN,
+		/* G positive gamma */ 0x00,
+		0x25, 0x15, 0x28, 0x3D, 0x4A, 0x48, 0x4C, 0x4A, 0x52, 0x59,
+		0x59, 0x5B, 0x56, 0x60, 0x5D, 0x55, 0x7F, 0x0A,
+		/* G negative gamma */ 0x00,
+		0x25, 0x15, 0x28, 0x3D, 0x4A, 0x48, 0x4C, 0x4A, 0x52, 0x59,
+		0x59, 0x5B, 0x56, 0x60, 0x5D, 0x55, 0x7F, 0x0A);
+	mipi_dbi_command(dbi, DB7430_GAMMA_SET_BLUE,
+		/* B positive gamma */ 0x00,
+		0x48, 0x10, 0x1F, 0x2F, 0x35, 0x38, 0x3D, 0x3C, 0x45, 0x4D,
+		0x4E, 0x52, 0x51, 0x60, 0x7F, 0x7E, 0x7F, 0x0C,
+		/* B negative gamma */ 0x00,
+		0x48, 0x10, 0x1F, 0x2F, 0x35, 0x38, 0x3D, 0x3C, 0x45, 0x4D,
+		0x4E, 0x52, 0x51, 0x60, 0x7F, 0x7E, 0x7F, 0x0C);
+	mipi_dbi_command(dbi, DB7430_BIAS_CURRENT_CTRL, 0x33, 0x13);
+	mipi_dbi_command(dbi, DB7430_DDV_CTRL, 0x11, 0x00, 0x00);
+	mipi_dbi_command(dbi, DB7430_GAMMA_CTRL_REF, 0x50, 0x50);
+	mipi_dbi_command(dbi, DB7430_DCDC_CTRL, 0x2f, 0x11, 0x1e, 0x46);
+	mipi_dbi_command(dbi, DB7430_VCL_CTRL, 0x11, 0x0a);
+
+	return 0;
+}
+
+static int db7430_power_off(struct db7430 *db)
+{
+	/* Go into RESET and disable regulators */
+	gpiod_set_value_cansleep(db->reset, 1);
+	return regulator_bulk_disable(ARRAY_SIZE(db->regulators),
+				      db->regulators);
+}
+
+static int db7430_unprepare(struct drm_panel *panel)
+{
+	return db7430_power_off(to_db7430(panel));
+}
+
+static int db7430_disable(struct drm_panel *panel)
+{
+	struct db7430 *db = to_db7430(panel);
+	struct mipi_dbi *dbi = &db->dbi;
+
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_OFF);
+	msleep(25);
+	mipi_dbi_command(dbi, MIPI_DCS_ENTER_SLEEP_MODE);
+	msleep(120);
+
+	return 0;
+}
+
+static int db7430_prepare(struct drm_panel *panel)
+{
+	return db7430_power_on(to_db7430(panel));
+}
+
+static int db7430_enable(struct drm_panel *panel)
+{
+	struct db7430 *db = to_db7430(panel);
+	struct mipi_dbi *dbi = &db->dbi;
+
+	/* Exit sleep mode */
+	mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(20);
+
+	/* NVM (non-volatile memory) load sequence */
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_D4, 0x52, 0x5e);
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_F8, 0x01, 0xf5, 0xf2, 0x71, 0x44);
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_FC, 0x00, 0x08);
+	msleep(150);
+
+	/* CABC turn on sequence (BC = backlight control) */
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_B4, 0x0f, 0x00, 0x50);
+	mipi_dbi_command(dbi, DB7430_USER_SELECT, 0x80);
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_B7, 0x24);
+	mipi_dbi_command(dbi, DB7430_UNKNOWN_B8, 0x01);
+
+	/* Turn on display */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON);
+
+	return 0;
+}
+
+/**
+ * db7430_get_modes() - return the mode
+ * @panel: the panel to get the mode for
+ * @connector: reference to the central DRM connector control structure
+ */
+static int db7430_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
+{
+	struct db7430 *db = to_db7430(panel);
+	struct drm_display_mode *mode;
+	static const u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+
+	mode = drm_mode_duplicate(connector->dev, &db7430_480_800_mode);
+	if (!mode) {
+		dev_err(db->dev, "failed to add mode\n");
+		return -ENOMEM;
+	}
+
+	connector->display_info.bpc = 8;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+	connector->display_info.bus_flags =
+		DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE;
+	drm_display_info_set_bus_formats(&connector->display_info,
+					 &bus_format, 1);
+
+	drm_mode_set_name(mode);
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static const struct drm_panel_funcs db7430_drm_funcs = {
+	.disable = db7430_disable,
+	.unprepare = db7430_unprepare,
+	.prepare = db7430_prepare,
+	.enable = db7430_enable,
+	.get_modes = db7430_get_modes,
+};
+
+static int db7430_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct db7430 *db;
+	int ret;
+
+	db = devm_kzalloc(dev, sizeof(*db), GFP_KERNEL);
+	if (!db)
+		return -ENOMEM;
+	db->dev = dev;
+
+	/*
+	 * VCI   is the analog voltage supply
+	 * VCCIO is the digital I/O voltage supply
+	 */
+	db->regulators[0].supply = "vci";
+	db->regulators[1].supply = "vccio";
+	ret = devm_regulator_bulk_get(dev,
+				      ARRAY_SIZE(db->regulators),
+				      db->regulators);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to get regulators\n");
+
+	db->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(db->reset)) {
+		ret = PTR_ERR(db->reset);
+		return dev_err_probe(dev, ret, "no RESET GPIO\n");
+	}
+
+	ret = mipi_dbi_spi_init(spi, &db->dbi, NULL);
+	if (ret)
+		return dev_err_probe(dev, ret, "MIPI DBI init failed\n");
+
+	drm_panel_init(&db->panel, dev, &db7430_drm_funcs,
+		       DRM_MODE_CONNECTOR_DPI);
+
+	/* FIXME: if no external backlight, use internal backlight */
+	ret = drm_panel_of_backlight(&db->panel);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to add backlight\n");
+
+	spi_set_drvdata(spi, db);
+
+	drm_panel_add(&db->panel);
+	dev_dbg(dev, "added panel\n");
+
+	return 0;
+}
+
+static int db7430_remove(struct spi_device *spi)
+{
+	struct db7430 *db = spi_get_drvdata(spi);
+
+	drm_panel_remove(&db->panel);
+	return 0;
+}
+
+/*
+ * The DB7430 display controller may be used in several display products,
+ * so list the different variants here and add per-variant data if needed.
+ */
+static const struct of_device_id db7430_match[] = {
+	{ .compatible = "samsung,lms397kf04", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, db7430_match);
+
+static struct spi_driver db7430_driver = {
+	.probe		= db7430_probe,
+	.remove		= db7430_remove,
+	.driver		= {
+		.name	= "db7430-panel",
+		.of_match_table = db7430_match,
+	},
+};
+module_spi_driver(db7430_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Samsung DB7430 panel driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
index b962c817fb30..ccc8ed6fe3ae 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
@@ -446,7 +446,7 @@ static int s6e63j0x03_probe(struct mipi_dsi_device *dsi)
 
 	dsi->lanes = 1;
 	dsi->format = MIPI_DSI_FMT_RGB888;
-	dsi->mode_flags = MIPI_DSI_MODE_EOT_PACKET;
+	dsi->mode_flags = MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	ctx->supplies[0].supply = "vdd3";
 	ctx->supplies[1].supply = "vci";
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c
index 07a48f621289..e0b1a7e354f3 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c
@@ -16,7 +16,8 @@
 #define MCS_GLOBAL_PARAM	0xb0
 #define S6E63M0_DSI_MAX_CHUNK	15 /* CMD + 15 bytes max */
 
-static int s6e63m0_dsi_dcs_read(struct device *dev, const u8 cmd, u8 *data)
+static int s6e63m0_dsi_dcs_read(struct device *dev, void *trsp,
+				const u8 cmd, u8 *data)
 {
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
 	int ret;
@@ -32,7 +33,8 @@ static int s6e63m0_dsi_dcs_read(struct device *dev, const u8 cmd, u8 *data)
 	return 0;
 }
 
-static int s6e63m0_dsi_dcs_write(struct device *dev, const u8 *data, size_t len)
+static int s6e63m0_dsi_dcs_write(struct device *dev, void *trsp,
+				 const u8 *data, size_t len)
 {
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
 	const u8 *seqp = data;
@@ -99,8 +101,8 @@ static int s6e63m0_dsi_probe(struct mipi_dsi_device *dsi)
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO |
 		MIPI_DSI_MODE_VIDEO_BURST;
 
-	ret = s6e63m0_probe(dev, s6e63m0_dsi_dcs_read, s6e63m0_dsi_dcs_write,
-			    true);
+	ret = s6e63m0_probe(dev, NULL, s6e63m0_dsi_dcs_read,
+			    s6e63m0_dsi_dcs_write, true);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c
index 326deb3177b6..3669cc3719ce 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c
@@ -5,62 +5,38 @@
 #include <linux/spi/spi.h>
 #include <linux/delay.h>
 
+#include <drm/drm_mipi_dbi.h>
 #include <drm/drm_print.h>
 
 #include "panel-samsung-s6e63m0.h"
 
-#define DATA_MASK	0x100
+static const u8 s6e63m0_dbi_read_commands[] = {
+	MCS_READ_ID1,
+	MCS_READ_ID2,
+	MCS_READ_ID3,
+	0, /* sentinel */
+};
 
-static int s6e63m0_spi_dcs_read(struct device *dev, const u8 cmd, u8 *data)
+static int s6e63m0_spi_dcs_read(struct device *dev, void *trsp,
+				const u8 cmd, u8 *data)
 {
-	struct spi_device *spi = to_spi_device(dev);
-	u16 buf[1];
-	u16 rbuf[1];
+	struct mipi_dbi *dbi = trsp;
 	int ret;
 
-	/* SPI buffers are always in CPU order */
-	buf[0] = (u16)cmd;
-	ret = spi_write_then_read(spi, buf, 2, rbuf, 2);
-	dev_dbg(dev, "READ CMD: %04x RET: %04x\n", buf[0], rbuf[0]);
-	if (!ret)
-		/* These high 8 bits of the 9 contains the readout */
-		*data = (rbuf[0] & 0x1ff) >> 1;
+	ret = mipi_dbi_command_read(dbi, cmd, data);
+	if (ret)
+		dev_err(dev, "error on DBI read command %02x\n", cmd);
 
 	return ret;
 }
 
-static int s6e63m0_spi_write_word(struct device *dev, u16 data)
-{
-	struct spi_device *spi = to_spi_device(dev);
-
-	/* SPI buffers are always in CPU order */
-	return spi_write(spi, &data, 2);
-}
-
-static int s6e63m0_spi_dcs_write(struct device *dev, const u8 *data, size_t len)
+static int s6e63m0_spi_dcs_write(struct device *dev, void *trsp,
+				 const u8 *data, size_t len)
 {
-	int ret = 0;
-
-	dev_dbg(dev, "SPI writing dcs seq: %*ph\n", (int)len, data);
-
-	/*
-	 * This sends 9 bits with the first bit (bit 8) set to 0
-	 * This indicates that this is a command. Anything after the
-	 * command is data.
-	 */
-	ret = s6e63m0_spi_write_word(dev, *data);
-
-	while (!ret && --len) {
-		++data;
-		/* This sends 9 bits with the first bit (bit 8) set to 1 */
-		ret = s6e63m0_spi_write_word(dev, *data | DATA_MASK);
-	}
-
-	if (ret) {
-		dev_err(dev, "SPI error %d writing dcs seq: %*ph\n", ret,
-			(int)len, data);
-	}
+	struct mipi_dbi *dbi = trsp;
+	int ret;
 
+	ret = mipi_dbi_command_stackbuf(dbi, data[0], (data + 1), (len - 1));
 	usleep_range(300, 310);
 
 	return ret;
@@ -69,18 +45,21 @@ static int s6e63m0_spi_dcs_write(struct device *dev, const u8 *data, size_t len)
 static int s6e63m0_spi_probe(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
+	struct mipi_dbi *dbi;
 	int ret;
 
-	spi->bits_per_word = 9;
-	/* Preserve e.g. SPI_3WIRE setting */
-	spi->mode |= SPI_MODE_3;
-	ret = spi_setup(spi);
-	if (ret < 0) {
-		dev_err(dev, "spi setup failed.\n");
-		return ret;
-	}
-	return s6e63m0_probe(dev, s6e63m0_spi_dcs_read, s6e63m0_spi_dcs_write,
-			     false);
+	dbi = devm_kzalloc(dev, sizeof(*dbi), GFP_KERNEL);
+	if (!dbi)
+		return -ENOMEM;
+
+	ret = mipi_dbi_spi_init(spi, dbi, NULL);
+	if (ret)
+		return dev_err_probe(dev, ret, "MIPI DBI init failed\n");
+	/* Register our custom MCS read commands */
+	dbi->read_commands = s6e63m0_dbi_read_commands;
+
+	return s6e63m0_probe(dev, dbi, s6e63m0_spi_dcs_read,
+			     s6e63m0_spi_dcs_write, false);
 }
 
 static int s6e63m0_spi_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
index 603c5dfe8768..35d72ac663d6 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
@@ -22,31 +22,6 @@
 
 #include "panel-samsung-s6e63m0.h"
 
-/* Manufacturer Command Set */
-#define MCS_ELVSS_ON		0xb1
-#define MCS_TEMP_SWIRE		0xb2
-#define MCS_PENTILE_1		0xb3
-#define MCS_PENTILE_2		0xb4
-#define MCS_GAMMA_DELTA_Y_RED	0xb5
-#define MCS_GAMMA_DELTA_X_RED	0xb6
-#define MCS_GAMMA_DELTA_Y_GREEN	0xb7
-#define MCS_GAMMA_DELTA_X_GREEN	0xb8
-#define MCS_GAMMA_DELTA_Y_BLUE	0xb9
-#define MCS_GAMMA_DELTA_X_BLUE	0xba
-#define MCS_MIECTL1		0xc0
-#define MCS_BCMODE		0xc1
-#define MCS_ERROR_CHECK		0xd5
-#define MCS_READ_ID1		0xda
-#define MCS_READ_ID2		0xdb
-#define MCS_READ_ID3		0xdc
-#define MCS_LEVEL_2_KEY		0xf0
-#define MCS_MTP_KEY		0xf1
-#define MCS_DISCTL		0xf2
-#define MCS_SRCCTL		0xf6
-#define MCS_IFCTL		0xf7
-#define MCS_PANELCTL		0xf8
-#define MCS_PGAMMACTL		0xfa
-
 #define S6E63M0_LCD_ID_VALUE_M2		0xA4
 #define S6E63M0_LCD_ID_VALUE_SM2	0xB4
 #define S6E63M0_LCD_ID_VALUE_SM2_1	0xB6
@@ -283,8 +258,9 @@ static u8 const s6e63m0_elvss_per_gamma[NUM_GAMMA_LEVELS] = {
 
 struct s6e63m0 {
 	struct device *dev;
-	int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val);
-	int (*dcs_write)(struct device *dev, const u8 *data, size_t len);
+	void *transport_data;
+	int (*dcs_read)(struct device *dev, void *trsp, const u8 cmd, u8 *val);
+	int (*dcs_write)(struct device *dev, void *trsp, const u8 *data, size_t len);
 	struct drm_panel panel;
 	struct backlight_device *bl_dev;
 	u8 lcd_type;
@@ -340,7 +316,7 @@ static void s6e63m0_dcs_read(struct s6e63m0 *ctx, const u8 cmd, u8 *data)
 	if (ctx->error < 0)
 		return;
 
-	ctx->error = ctx->dcs_read(ctx->dev, cmd, data);
+	ctx->error = ctx->dcs_read(ctx->dev, ctx->transport_data, cmd, data);
 }
 
 static void s6e63m0_dcs_write(struct s6e63m0 *ctx, const u8 *data, size_t len)
@@ -348,7 +324,7 @@ static void s6e63m0_dcs_write(struct s6e63m0 *ctx, const u8 *data, size_t len)
 	if (ctx->error < 0 || len == 0)
 		return;
 
-	ctx->error = ctx->dcs_write(ctx->dev, data, len);
+	ctx->error = ctx->dcs_write(ctx->dev, ctx->transport_data, data, len);
 }
 
 #define s6e63m0_dcs_write_seq_static(ctx, seq ...) \
@@ -713,9 +689,9 @@ static int s6e63m0_backlight_register(struct s6e63m0 *ctx, u32 max_brightness)
 	return ret;
 }
 
-int s6e63m0_probe(struct device *dev,
-		  int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val),
-		  int (*dcs_write)(struct device *dev, const u8 *data, size_t len),
+int s6e63m0_probe(struct device *dev, void *trsp,
+		  int (*dcs_read)(struct device *dev, void *trsp, const u8 cmd, u8 *val),
+		  int (*dcs_write)(struct device *dev, void *trsp, const u8 *data, size_t len),
 		  bool dsi_mode)
 {
 	struct s6e63m0 *ctx;
@@ -726,6 +702,7 @@ int s6e63m0_probe(struct device *dev,
 	if (!ctx)
 		return -ENOMEM;
 
+	ctx->transport_data = trsp;
 	ctx->dsi_mode = dsi_mode;
 	ctx->dcs_read = dcs_read;
 	ctx->dcs_write = dcs_write;
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h
index c669fec91763..306605ed1117 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h
@@ -3,9 +3,36 @@
 #ifndef _PANEL_SAMSUNG_S6E63M0_H
 #define _PANEL_SAMSUNG_S6E63M0_H
 
-int s6e63m0_probe(struct device *dev,
-		  int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val),
-		  int (*dcs_write)(struct device *dev, const u8 *data,
+/* Manufacturer Command Set */
+#define MCS_ELVSS_ON		0xb1
+#define MCS_TEMP_SWIRE		0xb2
+#define MCS_PENTILE_1		0xb3
+#define MCS_PENTILE_2		0xb4
+#define MCS_GAMMA_DELTA_Y_RED	0xb5
+#define MCS_GAMMA_DELTA_X_RED	0xb6
+#define MCS_GAMMA_DELTA_Y_GREEN	0xb7
+#define MCS_GAMMA_DELTA_X_GREEN	0xb8
+#define MCS_GAMMA_DELTA_Y_BLUE	0xb9
+#define MCS_GAMMA_DELTA_X_BLUE	0xba
+#define MCS_MIECTL1		0xc0
+#define MCS_BCMODE		0xc1
+#define MCS_ERROR_CHECK		0xd5
+#define MCS_READ_ID1		0xda
+#define MCS_READ_ID2		0xdb
+#define MCS_READ_ID3		0xdc
+#define MCS_LEVEL_2_KEY		0xf0
+#define MCS_MTP_KEY		0xf1
+#define MCS_DISCTL		0xf2
+#define MCS_SRCCTL		0xf6
+#define MCS_IFCTL		0xf7
+#define MCS_PANELCTL		0xf8
+#define MCS_PGAMMACTL		0xfa
+
+int s6e63m0_probe(struct device *dev, void *trsp,
+		  int (*dcs_read)(struct device *dev, void *trsp,
+				  const u8 cmd, u8 *val),
+		  int (*dcs_write)(struct device *dev, void *trsp,
+				   const u8 *data,
 				   size_t len),
 		  bool dsi_mode);
 int s6e63m0_remove(struct device *dev);
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index 527371120266..9b3599d6d2de 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -990,8 +990,8 @@ static int s6e8aa0_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST
-		| MIPI_DSI_MODE_VIDEO_HFP | MIPI_DSI_MODE_VIDEO_HBP
-		| MIPI_DSI_MODE_VIDEO_HSA | MIPI_DSI_MODE_EOT_PACKET
+		| MIPI_DSI_MODE_VIDEO_NO_HFP | MIPI_DSI_MODE_VIDEO_NO_HBP
+		| MIPI_DSI_MODE_VIDEO_NO_HSA | MIPI_DSI_MODE_NO_EOT_PACKET
 		| MIPI_DSI_MODE_VSYNC_FLUSH | MIPI_DSI_MODE_VIDEO_AUTO_VERT;
 
 	ret = s6e8aa0_parse_dt(ctx);
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
index 16dbf0f353ed..b937e24dac8e 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
@@ -282,7 +282,7 @@ static int sharp_nt_panel_probe(struct mipi_dsi_device *dsi)
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO |
 			MIPI_DSI_MODE_VIDEO_HSE |
 			MIPI_DSI_CLOCK_NON_CONTINUOUS |
-			MIPI_DSI_MODE_EOT_PACKET;
+			MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	sharp_nt = devm_kzalloc(&dsi->dev, sizeof(*sharp_nt), GFP_KERNEL);
 	if (!sharp_nt)
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 1b80290c2b53..9b6c4e6c38a1 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -36,6 +36,8 @@
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
+#include <drm/drm_dp_aux_bus.h>
+#include <drm/drm_dp_helper.h>
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_panel.h>
 
@@ -185,6 +187,7 @@ struct panel_simple {
 
 	struct regulator *supply;
 	struct i2c_adapter *ddc;
+	struct drm_dp_aux *aux;
 
 	struct gpio_desc *enable_gpio;
 	struct gpio_desc *hpd_gpio;
@@ -657,7 +660,8 @@ static void panel_simple_parse_panel_timing_node(struct device *dev,
 		dev_err(dev, "Reject override mode: No display_timing found\n");
 }
 
-static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
+static int panel_simple_probe(struct device *dev, const struct panel_desc *desc,
+			      struct drm_dp_aux *aux)
 {
 	struct panel_simple *panel;
 	struct display_timing dt;
@@ -673,6 +677,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 	panel->enabled = false;
 	panel->prepared_time = 0;
 	panel->desc = desc;
+	panel->aux = aux;
 
 	panel->no_hpd = of_property_read_bool(dev->of_node, "no-hpd");
 	if (!panel->no_hpd) {
@@ -707,6 +712,8 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 
 		if (!panel->ddc)
 			return -EPROBE_DEFER;
+	} else if (aux) {
+		panel->ddc = &aux->ddc;
 	}
 
 	if (desc == &panel_dpi) {
@@ -742,10 +749,8 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 			desc->bpc != 8);
 		break;
 	case DRM_MODE_CONNECTOR_eDP:
-		if (desc->bus_format == 0)
-			dev_warn(dev, "Specify missing bus_format\n");
-		if (desc->bpc != 6 && desc->bpc != 8)
-			dev_warn(dev, "Expected bpc in {6,8} but got: %u\n", desc->bpc);
+		if (desc->bpc != 6 && desc->bpc != 8 && desc->bpc != 10)
+			dev_warn(dev, "Expected bpc in {6,8,10} but got: %u\n", desc->bpc);
 		break;
 	case DRM_MODE_CONNECTOR_DSI:
 		if (desc->bpc != 6 && desc->bpc != 8)
@@ -793,6 +798,15 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 	if (err)
 		goto disable_pm_runtime;
 
+	if (!panel->base.backlight && panel->aux) {
+		pm_runtime_get_sync(dev);
+		err = drm_panel_dp_aux_backlight(&panel->base, panel->aux);
+		pm_runtime_mark_last_busy(dev);
+		pm_runtime_put_autosuspend(dev);
+		if (err)
+			goto disable_pm_runtime;
+	}
+
 	drm_panel_add(&panel->base);
 
 	return 0;
@@ -801,7 +815,7 @@ disable_pm_runtime:
 	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 free_ddc:
-	if (panel->ddc)
+	if (panel->ddc && (!panel->aux || panel->ddc != &panel->aux->ddc))
 		put_device(&panel->ddc->dev);
 
 	return err;
@@ -817,7 +831,7 @@ static int panel_simple_remove(struct device *dev)
 
 	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
-	if (panel->ddc)
+	if (panel->ddc && (!panel->aux || panel->ddc != &panel->aux->ddc))
 		put_device(&panel->ddc->dev);
 
 	return 0;
@@ -1080,6 +1094,36 @@ static const struct panel_desc auo_b133xtn01 = {
 	},
 };
 
+static const struct drm_display_mode auo_b133han05_mode = {
+	.clock = 142600,
+	.hdisplay = 1920,
+	.hsync_start = 1920 + 58,
+	.hsync_end = 1920 + 58 + 42,
+	.htotal = 1920 + 58 + 42 + 60,
+	.vdisplay = 1080,
+	.vsync_start = 1080 + 3,
+	.vsync_end = 1080 + 3 + 5,
+	.vtotal = 1080 + 3 + 5 + 54,
+};
+
+static const struct panel_desc auo_b133han05 = {
+	.modes = &auo_b133han05_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 293,
+		.height = 165,
+	},
+	.delay = {
+		.prepare = 100,
+		.enable = 20,
+		.unprepare = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DATA_MSB_TO_LSB,
+	.connector_type = DRM_MODE_CONNECTOR_eDP,
+};
+
 static const struct drm_display_mode auo_b133htn01_mode = {
 	.clock = 150660,
 	.hdisplay = 1920,
@@ -1107,6 +1151,36 @@ static const struct panel_desc auo_b133htn01 = {
 	},
 };
 
+static const struct drm_display_mode auo_b140han06_mode = {
+	.clock = 141000,
+	.hdisplay = 1920,
+	.hsync_start = 1920 + 16,
+	.hsync_end = 1920 + 16 + 16,
+	.htotal = 1920 + 16 + 16 + 152,
+	.vdisplay = 1080,
+	.vsync_start = 1080 + 3,
+	.vsync_end = 1080 + 3 + 14,
+	.vtotal = 1080 + 3 + 14 + 19,
+};
+
+static const struct panel_desc auo_b140han06 = {
+	.modes = &auo_b140han06_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 309,
+		.height = 174,
+	},
+	.delay = {
+		.prepare = 100,
+		.enable = 20,
+		.unprepare = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DATA_MSB_TO_LSB,
+	.connector_type = DRM_MODE_CONNECTOR_eDP,
+};
+
 static const struct display_timing auo_g070vvn01_timings = {
 	.pixelclock = { 33300000, 34209000, 45000000 },
 	.hactive = { 800, 800, 800 },
@@ -1179,6 +1253,8 @@ static const struct panel_desc auo_g104sn02 = {
 		.width = 211,
 		.height = 158,
 	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
 static const struct drm_display_mode auo_g121ean01_mode = {
@@ -1929,6 +2005,32 @@ static const struct panel_desc edt_et035012dm6 = {
 	.bus_flags = DRM_BUS_FLAG_DE_LOW | DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE,
 };
 
+static const struct drm_display_mode edt_etm0350g0dh6_mode = {
+	.clock = 6520,
+	.hdisplay = 320,
+	.hsync_start = 320 + 20,
+	.hsync_end = 320 + 20 + 68,
+	.htotal = 320 + 20 + 68,
+	.vdisplay = 240,
+	.vsync_start = 240 + 4,
+	.vsync_end = 240 + 4 + 18,
+	.vtotal = 240 + 4 + 18,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc edt_etm0350g0dh6 = {
+	.modes = &edt_etm0350g0dh6_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 70,
+		.height = 53,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
+};
+
 static const struct drm_display_mode edt_etm043080dh6gp_mode = {
 	.clock = 10870,
 	.hdisplay = 480,
@@ -1980,6 +2082,9 @@ static const struct panel_desc edt_etm0430g0dh6 = {
 		.width = 95,
 		.height = 54,
 	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
 };
 
 static const struct drm_display_mode edt_et057090dhu_mode = {
@@ -2044,6 +2149,60 @@ static const struct panel_desc edt_etm0700g0bdh6 = {
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
+};
+
+static const struct drm_display_mode edt_etmv570g2dhu_mode = {
+	.clock = 25175,
+	.hdisplay = 640,
+	.hsync_start = 640,
+	.hsync_end = 640 + 16,
+	.htotal = 640 + 16 + 30 + 114,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 3,
+	.vtotal = 480 + 10 + 3 + 35,
+	.flags = DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_PHSYNC,
+};
+
+static const struct panel_desc edt_etmv570g2dhu = {
+	.modes = &edt_etmv570g2dhu_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 115,
+		.height = 86,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
+};
+
+static const struct display_timing eink_vb3300_kca_timing = {
+	.pixelclock = { 40000000, 40000000, 40000000 },
+	.hactive = { 334, 334, 334 },
+	.hfront_porch = { 1, 1, 1 },
+	.hback_porch = { 1, 1, 1 },
+	.hsync_len = { 1, 1, 1 },
+	.vactive = { 1405, 1405, 1405 },
+	.vfront_porch = { 1, 1, 1 },
+	.vback_porch = { 1, 1, 1 },
+	.vsync_len = { 1, 1, 1 },
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		 DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
+};
+
+static const struct panel_desc eink_vb3300_kca = {
+	.timings = &eink_vb3300_kca_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 157,
+		.height = 209,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
 };
 
 static const struct display_timing evervision_vgg804821_timing = {
@@ -2967,6 +3126,38 @@ static const struct panel_desc logictechno_lt170410_2whc = {
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
+static const struct drm_display_mode logictechno_lttd800480070_l6wh_rt_mode = {
+	.clock = 33000,
+	.hdisplay = 800,
+	.hsync_start = 800 + 154,
+	.hsync_end = 800 + 154 + 3,
+	.htotal = 800 + 154 + 3 + 43,
+	.vdisplay = 480,
+	.vsync_start = 480 + 47,
+	.vsync_end = 480 + 47 + 3,
+	.vtotal = 480 + 47 + 3 + 20,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc logictechno_lttd800480070_l6wh_rt = {
+	.modes = &logictechno_lttd800480070_l6wh_rt_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 45,
+		.enable = 100,
+		.disable = 100,
+		.unprepare = 45
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
+};
+
 static const struct drm_display_mode mitsubishi_aa070mc01_mode = {
 	.clock = 30400,
 	.hdisplay = 800,
@@ -3033,6 +3224,37 @@ static const struct panel_desc mitsubishi_aa070mc01 = {
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 };
 
+static const struct display_timing multi_inno_mi1010ait_1cp_timing = {
+	.pixelclock = { 68900000, 70000000, 73400000 },
+	.hactive = { 1280, 1280, 1280 },
+	.hfront_porch = { 30, 60, 71 },
+	.hback_porch = { 30, 60, 71 },
+	.hsync_len = { 10, 10, 48 },
+	.vactive = { 800, 800, 800 },
+	.vfront_porch = { 5, 10, 10 },
+	.vback_porch = { 5, 10, 10 },
+	.vsync_len = { 5, 6, 13 },
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		 DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc multi_inno_mi1010ait_1cp = {
+	.timings = &multi_inno_mi1010ait_1cp_timing,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 217,
+		.height = 136,
+	},
+	.delay = {
+		.enable = 50,
+		.disable = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+};
+
 static const struct display_timing nec_nl12880bc20_05_timing = {
 	.pixelclock = { 67000000, 71000000, 75000000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -3463,6 +3685,46 @@ static const struct panel_desc qd43003c0_40 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct drm_display_mode qishenglong_gopher2b_lcd_modes[] = {
+	{ /* 60 Hz */
+		.clock = 10800,
+		.hdisplay = 480,
+		.hsync_start = 480 + 77,
+		.hsync_end = 480 + 77 + 41,
+		.htotal = 480 + 77 + 41 + 2,
+		.vdisplay = 272,
+		.vsync_start = 272 + 16,
+		.vsync_end = 272 + 16 + 10,
+		.vtotal = 272 + 16 + 10 + 2,
+		.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+	},
+	{ /* 50 Hz */
+		.clock = 10800,
+		.hdisplay = 480,
+		.hsync_start = 480 + 17,
+		.hsync_end = 480 + 17 + 41,
+		.htotal = 480 + 17 + 41 + 2,
+		.vdisplay = 272,
+		.vsync_start = 272 + 116,
+		.vsync_end = 272 + 116 + 10,
+		.vtotal = 272 + 116 + 10 + 2,
+		.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+	},
+};
+
+static const struct panel_desc qishenglong_gopher2b_lcd = {
+	.modes = qishenglong_gopher2b_lcd_modes,
+	.num_modes = ARRAY_SIZE(qishenglong_gopher2b_lcd_modes),
+	.bpc = 8,
+	.size = {
+		.width = 95,
+		.height = 54,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
+};
+
 static const struct display_timing rocktech_rk070er9427_timing = {
 	.pixelclock = { 26400000, 33300000, 46800000 },
 	.hactive = { 800, 800, 800 },
@@ -4234,9 +4496,15 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "auo,b116xw03",
 		.data = &auo_b116xw03,
 	}, {
+		.compatible = "auo,b133han05",
+		.data = &auo_b133han05,
+	}, {
 		.compatible = "auo,b133htn01",
 		.data = &auo_b133htn01,
 	}, {
+		.compatible = "auo,b140han06",
+		.data = &auo_b140han06,
+	}, {
 		.compatible = "auo,b133xtn01",
 		.data = &auo_b133xtn01,
 	}, {
@@ -4330,6 +4598,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "edt,et035012dm6",
 		.data = &edt_et035012dm6,
 	}, {
+		.compatible = "edt,etm0350g0dh6",
+		.data = &edt_etm0350g0dh6,
+	}, {
 		.compatible = "edt,etm043080dh6gp",
 		.data = &edt_etm043080dh6gp,
 	}, {
@@ -4351,6 +4622,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "edt,etm0700g0edh6",
 		.data = &edt_etm0700g0bdh6,
 	}, {
+		.compatible = "edt,etmv570g2dhu",
+		.data = &edt_etmv570g2dhu,
+	}, {
+		.compatible = "eink,vb3300-kca",
+		.data = &eink_vb3300_kca,
+	}, {
 		.compatible = "evervision,vgg804821",
 		.data = &evervision_vgg804821,
 	}, {
@@ -4462,9 +4739,15 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "logictechno,lt170410-2whc",
 		.data = &logictechno_lt170410_2whc,
 	}, {
+		.compatible = "logictechno,lttd800480070-l6wh-rt",
+		.data = &logictechno_lttd800480070_l6wh_rt,
+	}, {
 		.compatible = "mitsubishi,aa070mc01-ca1",
 		.data = &mitsubishi_aa070mc01,
 	}, {
+		.compatible = "multi-inno,mi1010ait-1cp",
+		.data = &multi_inno_mi1010ait_1cp,
+	}, {
 		.compatible = "nec,nl12880bc20-05",
 		.data = &nec_nl12880bc20_05,
 	}, {
@@ -4516,6 +4799,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "qiaodian,qd43003c0-40",
 		.data = &qd43003c0_40,
 	}, {
+		.compatible = "qishenglong,gopher2b-lcd",
+		.data = &qishenglong_gopher2b_lcd,
+	}, {
 		.compatible = "rocktech,rk070er9427",
 		.data = &rocktech_rk070er9427,
 	}, {
@@ -4632,7 +4918,7 @@ static int panel_simple_platform_probe(struct platform_device *pdev)
 	if (!id)
 		return -ENODEV;
 
-	return panel_simple_probe(&pdev->dev, id->data);
+	return panel_simple_probe(&pdev->dev, id->data, NULL);
 }
 
 static int panel_simple_platform_remove(struct platform_device *pdev)
@@ -4867,7 +5153,7 @@ static const struct panel_desc_dsi osd101t2045_53ts = {
 	},
 	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
 		 MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-		 MIPI_DSI_MODE_EOT_PACKET,
+		 MIPI_DSI_MODE_NO_EOT_PACKET,
 	.format = MIPI_DSI_FMT_RGB888,
 	.lanes = 4,
 };
@@ -4912,7 +5198,7 @@ static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi)
 
 	desc = id->data;
 
-	err = panel_simple_probe(&dsi->dev, &desc->desc);
+	err = panel_simple_probe(&dsi->dev, &desc->desc, NULL);
 	if (err < 0)
 		return err;
 
@@ -4957,6 +5243,38 @@ static struct mipi_dsi_driver panel_simple_dsi_driver = {
 	.shutdown = panel_simple_dsi_shutdown,
 };
 
+static int panel_simple_dp_aux_ep_probe(struct dp_aux_ep_device *aux_ep)
+{
+	const struct of_device_id *id;
+
+	id = of_match_node(platform_of_match, aux_ep->dev.of_node);
+	if (!id)
+		return -ENODEV;
+
+	return panel_simple_probe(&aux_ep->dev, id->data, aux_ep->aux);
+}
+
+static void panel_simple_dp_aux_ep_remove(struct dp_aux_ep_device *aux_ep)
+{
+	panel_simple_remove(&aux_ep->dev);
+}
+
+static void panel_simple_dp_aux_ep_shutdown(struct dp_aux_ep_device *aux_ep)
+{
+	panel_simple_shutdown(&aux_ep->dev);
+}
+
+static struct dp_aux_ep_driver panel_simple_dp_aux_ep_driver = {
+	.driver = {
+		.name = "panel-simple-dp-aux",
+		.of_match_table = platform_of_match,	/* Same as platform one! */
+		.pm = &panel_simple_pm_ops,
+	},
+	.probe = panel_simple_dp_aux_ep_probe,
+	.remove = panel_simple_dp_aux_ep_remove,
+	.shutdown = panel_simple_dp_aux_ep_shutdown,
+};
+
 static int __init panel_simple_init(void)
 {
 	int err;
@@ -4965,15 +5283,25 @@ static int __init panel_simple_init(void)
 	if (err < 0)
 		return err;
 
+	err = dp_aux_dp_driver_register(&panel_simple_dp_aux_ep_driver);
+	if (err < 0)
+		goto err_did_platform_register;
+
 	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) {
 		err = mipi_dsi_driver_register(&panel_simple_dsi_driver);
-		if (err < 0) {
-			platform_driver_unregister(&panel_simple_platform_driver);
-			return err;
-		}
+		if (err < 0)
+			goto err_did_aux_ep_register;
 	}
 
 	return 0;
+
+err_did_aux_ep_register:
+	dp_aux_dp_driver_unregister(&panel_simple_dp_aux_ep_driver);
+
+err_did_platform_register:
+	platform_driver_unregister(&panel_simple_platform_driver);
+
+	return err;
 }
 module_init(panel_simple_init);
 
@@ -4982,6 +5310,7 @@ static void __exit panel_simple_exit(void)
 	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI))
 		mipi_dsi_driver_unregister(&panel_simple_dsi_driver);
 
+	dp_aux_dp_driver_unregister(&panel_simple_dp_aux_ep_driver);
 	platform_driver_unregister(&panel_simple_platform_driver);
 }
 module_exit(panel_simple_exit);
diff --git a/drivers/gpu/drm/panel/panel-sony-acx424akp.c b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
index 95659a4d15e9..9536d56a94a5 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx424akp.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
@@ -40,7 +40,6 @@
 struct acx424akp {
 	struct drm_panel panel;
 	struct device *dev;
-	struct backlight_device *bl;
 	struct regulator *supply;
 	struct gpio_desc *reset_gpio;
 	bool video_mode;
@@ -102,6 +101,18 @@ static int acx424akp_set_brightness(struct backlight_device *bl)
 	u8 par;
 	int ret;
 
+	if (backlight_is_blank(bl)) {
+		/* Disable backlight */
+		par = 0x00;
+		ret = mipi_dsi_dcs_write(dsi, MIPI_DCS_WRITE_CONTROL_DISPLAY,
+					 &par, 1);
+		if (ret) {
+			dev_err(acx->dev, "failed to disable display backlight (%d)\n", ret);
+			return ret;
+		}
+		return 0;
+	}
+
 	/* Calculate the PWM duty cycle in n/256's */
 	pwm_ratio = max(((duty_ns * 256) / period_ns) - 1, 1);
 	pwm_div = max(1,
@@ -172,6 +183,12 @@ static const struct backlight_ops acx424akp_bl_ops = {
 	.update_status = acx424akp_set_brightness,
 };
 
+static const struct backlight_properties acx424akp_bl_props = {
+	.type = BACKLIGHT_RAW,
+	.brightness = 512,
+	.max_brightness = 1023,
+};
+
 static int acx424akp_read_id(struct acx424akp *acx)
 {
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
@@ -310,8 +327,6 @@ static int acx424akp_prepare(struct drm_panel *panel)
 		}
 	}
 
-	acx->bl->props.power = FB_BLANK_NORMAL;
-
 	return 0;
 
 err_power_off:
@@ -323,18 +338,8 @@ static int acx424akp_unprepare(struct drm_panel *panel)
 {
 	struct acx424akp *acx = panel_to_acx424akp(panel);
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
-	u8 par;
 	int ret;
 
-	/* Disable backlight */
-	par = 0x00;
-	ret = mipi_dsi_dcs_write(dsi, MIPI_DCS_WRITE_CONTROL_DISPLAY,
-				 &par, 1);
-	if (ret) {
-		dev_err(acx->dev, "failed to disable display backlight (%d)\n", ret);
-		return ret;
-	}
-
 	ret = mipi_dsi_dcs_set_display_off(dsi);
 	if (ret) {
 		dev_err(acx->dev, "failed to turn display off (%d)\n", ret);
@@ -350,36 +355,10 @@ static int acx424akp_unprepare(struct drm_panel *panel)
 	msleep(85);
 
 	acx424akp_power_off(acx);
-	acx->bl->props.power = FB_BLANK_POWERDOWN;
-
-	return 0;
-}
-
-static int acx424akp_enable(struct drm_panel *panel)
-{
-	struct acx424akp *acx = panel_to_acx424akp(panel);
-
-	/*
-	 * The backlight is on as long as the display is on
-	 * so no use to call backlight_enable() here.
-	 */
-	acx->bl->props.power = FB_BLANK_UNBLANK;
 
 	return 0;
 }
 
-static int acx424akp_disable(struct drm_panel *panel)
-{
-	struct acx424akp *acx = panel_to_acx424akp(panel);
-
-	/*
-	 * The backlight is on as long as the display is on
-	 * so no use to call backlight_disable() here.
-	 */
-	acx->bl->props.power = FB_BLANK_NORMAL;
-
-	return 0;
-}
 
 static int acx424akp_get_modes(struct drm_panel *panel,
 			       struct drm_connector *connector)
@@ -409,10 +388,8 @@ static int acx424akp_get_modes(struct drm_panel *panel,
 }
 
 static const struct drm_panel_funcs acx424akp_drm_funcs = {
-	.disable = acx424akp_disable,
 	.unprepare = acx424akp_unprepare,
 	.prepare = acx424akp_prepare,
-	.enable = acx424akp_enable,
 	.get_modes = acx424akp_get_modes,
 };
 
@@ -458,25 +435,18 @@ static int acx424akp_probe(struct mipi_dsi_device *dsi)
 	/* This asserts RESET by default */
 	acx->reset_gpio = devm_gpiod_get_optional(dev, "reset",
 						  GPIOD_OUT_HIGH);
-	if (IS_ERR(acx->reset_gpio)) {
-		ret = PTR_ERR(acx->reset_gpio);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to request GPIO (%d)\n", ret);
-		return ret;
-	}
+	if (IS_ERR(acx->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(acx->reset_gpio),
+				     "failed to request GPIO\n");
 
 	drm_panel_init(&acx->panel, dev, &acx424akp_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	acx->bl = devm_backlight_device_register(dev, "acx424akp", dev, acx,
-						 &acx424akp_bl_ops, NULL);
-	if (IS_ERR(acx->bl)) {
-		dev_err(dev, "failed to register backlight device\n");
-		return PTR_ERR(acx->bl);
-	}
-	acx->bl->props.max_brightness = 1023;
-	acx->bl->props.brightness = 512;
-	acx->bl->props.power = FB_BLANK_POWERDOWN;
+	acx->panel.backlight = devm_backlight_device_register(dev, "acx424akp", dev, acx,
+					&acx424akp_bl_ops, &acx424akp_bl_props);
+	if (IS_ERR(acx->panel.backlight))
+		return dev_err_probe(dev, PTR_ERR(acx->panel.backlight),
+				     "failed to register backlight device\n");
 
 	drm_panel_add(&acx->panel);
 
diff --git a/drivers/gpu/drm/panel/panel-widechips-ws2401.c b/drivers/gpu/drm/panel/panel-widechips-ws2401.c
new file mode 100644
index 000000000000..8bc976f54b80
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-widechips-ws2401.c
@@ -0,0 +1,441 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Panel driver for the WideChips WS2401 480x800 DPI RGB panel, used in
+ * the Samsung Mobile Display (SMD) LMS380KF01.
+ * Found in the Samsung Galaxy Ace 2 GT-I8160 mobile phone.
+ * Linus Walleij <linus.walleij@linaro.org>
+ * Inspired by code and know-how in the vendor driver by Gareth Phillips.
+ */
+#include <drm/drm_mipi_dbi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/media-bus-format.h>
+#include <linux/module.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+
+#include <video/mipi_display.h>
+
+#define WS2401_RESCTL			0xb8 /* Resolution select control */
+#define WS2401_PSMPS			0xbd /* SMPS positive control */
+#define WS2401_NSMPS			0xbe /* SMPS negative control */
+#define WS2401_SMPS			0xbf
+#define WS2401_BCMODE			0xc1 /* Backlight control mode */
+#define WS2401_WRBLCTL			0xc3 /* Backlight control */
+#define WS2401_WRDISBV			0xc4 /* Write manual brightness */
+#define WS2401_WRCTRLD			0xc6 /* Write BL control */
+#define WS2401_WRMIE			0xc7 /* Write MIE mode */
+#define WS2401_READ_ID1			0xda /* Read panel ID 1 */
+#define WS2401_READ_ID2			0xdb /* Read panel ID 2 */
+#define WS2401_READ_ID3			0xdc /* Read panel ID 3 */
+#define WS2401_GAMMA_R1			0xe7 /* Gamma red 1 */
+#define WS2401_GAMMA_G1			0xe8 /* Gamma green 1 */
+#define WS2401_GAMMA_B1			0xe9 /* Gamma blue 1 */
+#define WS2401_GAMMA_R2			0xea /* Gamma red 2 */
+#define WS2401_GAMMA_G2			0xeb /* Gamma green 2 */
+#define WS2401_GAMMA_B2			0xec /* Gamma blue 2 */
+#define WS2401_PASSWD1			0xf0 /* Password command for level 2 */
+#define WS2401_DISCTL			0xf2 /* Display control */
+#define WS2401_PWRCTL			0xf3 /* Power control */
+#define WS2401_VCOMCTL			0xf4 /* VCOM control */
+#define WS2401_SRCCTL			0xf5 /* Source control */
+#define WS2401_PANELCTL			0xf6 /* Panel control */
+
+static const u8 ws2401_dbi_read_commands[] = {
+	WS2401_READ_ID1,
+	WS2401_READ_ID2,
+	WS2401_READ_ID3,
+	0, /* sentinel */
+};
+
+/**
+ * struct ws2401 - state container for a panel controlled by the WS2401
+ * controller
+ */
+struct ws2401 {
+	/** @dev: the container device */
+	struct device *dev;
+	/** @dbi: the DBI bus abstraction handle */
+	struct mipi_dbi dbi;
+	/** @panel: the DRM panel instance for this device */
+	struct drm_panel panel;
+	/** @width: the width of this panel in mm */
+	u32 width;
+	/** @height: the height of this panel in mm */
+	u32 height;
+	/** @reset: reset GPIO line */
+	struct gpio_desc *reset;
+	/** @regulators: VCCIO and VIO supply regulators */
+	struct regulator_bulk_data regulators[2];
+	/** @internal_bl: If using internal backlight */
+	bool internal_bl;
+};
+
+static const struct drm_display_mode lms380kf01_480_800_mode = {
+	/*
+	 * The vendor driver states that the "SMD panel" has a clock
+	 * frequency of 49920000 Hz / 2 = 24960000 Hz.
+	 */
+	.clock = 24960,
+	.hdisplay = 480,
+	.hsync_start = 480 + 8,
+	.hsync_end = 480 + 8 + 10,
+	.htotal = 480 + 8 + 10 + 8,
+	.vdisplay = 800,
+	.vsync_start = 800 + 8,
+	.vsync_end = 800 + 8 + 2,
+	.vtotal = 800 + 8 + 2 + 18,
+	.width_mm = 50,
+	.height_mm = 84,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static inline struct ws2401 *to_ws2401(struct drm_panel *panel)
+{
+	return container_of(panel, struct ws2401, panel);
+}
+
+static void ws2401_read_mtp_id(struct ws2401 *ws)
+{
+	struct mipi_dbi *dbi = &ws->dbi;
+	u8 id1, id2, id3;
+	int ret;
+
+	ret = mipi_dbi_command_read(dbi, WS2401_READ_ID1, &id1);
+	if (ret) {
+		dev_err(ws->dev, "unable to read MTP ID 1\n");
+		return;
+	}
+	ret = mipi_dbi_command_read(dbi, WS2401_READ_ID2, &id2);
+	if (ret) {
+		dev_err(ws->dev, "unable to read MTP ID 2\n");
+		return;
+	}
+	ret = mipi_dbi_command_read(dbi, WS2401_READ_ID3, &id3);
+	if (ret) {
+		dev_err(ws->dev, "unable to read MTP ID 3\n");
+		return;
+	}
+	dev_info(ws->dev, "MTP ID: %02x %02x %02x\n", id1, id2, id3);
+}
+
+static int ws2401_power_on(struct ws2401 *ws)
+{
+	struct mipi_dbi *dbi = &ws->dbi;
+	int ret;
+
+	/* Power up */
+	ret = regulator_bulk_enable(ARRAY_SIZE(ws->regulators),
+				    ws->regulators);
+	if (ret) {
+		dev_err(ws->dev, "failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+	msleep(10);
+
+	/* Assert reset >=1 ms */
+	gpiod_set_value_cansleep(ws->reset, 1);
+	usleep_range(1000, 5000);
+	/* De-assert reset */
+	gpiod_set_value_cansleep(ws->reset, 0);
+	/* Wait >= 10 ms */
+	msleep(10);
+	dev_dbg(ws->dev, "de-asserted RESET\n");
+
+	/*
+	 * Exit sleep mode and initialize display - some hammering is
+	 * necessary.
+	 */
+	mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE);
+	mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(50);
+
+	/* Magic to unlock level 2 control of the display */
+	mipi_dbi_command(dbi, WS2401_PASSWD1, 0x5a, 0x5a);
+	/* Configure resolution to 480RGBx800 */
+	mipi_dbi_command(dbi, WS2401_RESCTL, 0x12);
+	/* Set addressing mode Flip V(d0), Flip H(d1) RGB/BGR(d3) */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, 0x01);
+	/* Set pixel format: 24 bpp */
+	mipi_dbi_command(dbi, MIPI_DCS_SET_PIXEL_FORMAT, 0x70);
+	mipi_dbi_command(dbi, WS2401_SMPS, 0x00, 0x0f);
+	mipi_dbi_command(dbi, WS2401_PSMPS, 0x06, 0x03, /* DDVDH: 4.6v */
+			 0x7e, 0x03, 0x12, 0x37);
+	mipi_dbi_command(dbi, WS2401_NSMPS, 0x06, 0x03, /* DDVDH: -4.6v */
+			 0x7e, 0x02, 0x15, 0x37);
+	mipi_dbi_command(dbi, WS2401_SMPS, 0x02, 0x0f);
+	mipi_dbi_command(dbi, WS2401_PWRCTL, 0x10, 0xA9, 0x00, 0x01, 0x44,
+			 0xb4,	/* VGH:16.1v, VGL:-13.8v */
+			 0x50,	/* GREFP:4.2v (default) */
+			 0x50,	/* GREFN:-4.2v (default) */
+			 0x00,
+			 0x44);	/* VOUTL:-10v (default) */
+	mipi_dbi_command(dbi, WS2401_DISCTL, 0x01, 0x00, 0x00, 0x00, 0x14,
+			 0x16);
+	mipi_dbi_command(dbi, WS2401_VCOMCTL, 0x30, 0x53, 0x53);
+	mipi_dbi_command(dbi, WS2401_SRCCTL, 0x03, 0x0C, 0x00, 0x00, 0x00,
+			 0x01,	/* 2 dot inversion */
+			 0x01, 0x06, 0x03);
+	mipi_dbi_command(dbi, WS2401_PANELCTL, 0x14, 0x00, 0x80, 0x00);
+	mipi_dbi_command(dbi, WS2401_WRMIE, 0x01);
+
+	/* Set up gamma, probably these are P-gamma and N-gamma for each color */
+	mipi_dbi_command(dbi, WS2401_GAMMA_R1, 0x00,
+			 0x5b, 0x42, 0x41, 0x3f, 0x42, 0x3d, 0x38, 0x2e,
+			 0x2b, 0x2a, 0x27, 0x22, 0x27, 0x0f, 0x00, 0x00);
+	mipi_dbi_command(dbi, WS2401_GAMMA_R2, 0x00,
+			 0x5b, 0x42, 0x41, 0x3f, 0x42, 0x3d, 0x38, 0x2e,
+			 0x2b, 0x2a, 0x27, 0x22, 0x27, 0x0f, 0x00, 0x00);
+	mipi_dbi_command(dbi, WS2401_GAMMA_G1, 0x00,
+			 0x59, 0x40, 0x3f, 0x3e, 0x41, 0x3d, 0x39, 0x2f,
+			 0x2c, 0x2b, 0x29, 0x25, 0x29, 0x19, 0x08, 0x00);
+	mipi_dbi_command(dbi, WS2401_GAMMA_G2, 0x00,
+			 0x59, 0x40, 0x3f, 0x3e, 0x41, 0x3d, 0x39, 0x2f,
+			 0x2c, 0x2b, 0x29, 0x25, 0x29, 0x19, 0x08, 0x00);
+	mipi_dbi_command(dbi, WS2401_GAMMA_B1, 0x00,
+			 0x57, 0x3b, 0x3a, 0x3b, 0x3f, 0x3b, 0x38, 0x27,
+			 0x38, 0x2a, 0x26, 0x22, 0x34, 0x0c, 0x09, 0x00);
+	mipi_dbi_command(dbi, WS2401_GAMMA_B2, 0x00,
+			 0x57, 0x3b, 0x3a, 0x3b, 0x3f, 0x3b, 0x38, 0x27,
+			 0x38, 0x2a, 0x26, 0x22, 0x34, 0x0c, 0x09, 0x00);
+
+	if (ws->internal_bl) {
+		mipi_dbi_command(dbi, WS2401_WRCTRLD, 0x2c);
+	} else {
+		mipi_dbi_command(dbi, WS2401_WRCTRLD, 0x00);
+		/*
+		 * When not using internal backlight we do not need any further
+		 * L2 accesses to the panel so we close the door on our way out.
+		 * Otherwise we need to leave the L2 door open.
+		 */
+		mipi_dbi_command(dbi, WS2401_PASSWD1, 0xa5, 0xa5);
+	}
+
+	return 0;
+}
+
+static int ws2401_power_off(struct ws2401 *ws)
+{
+	/* Go into RESET and disable regulators */
+	gpiod_set_value_cansleep(ws->reset, 1);
+	return regulator_bulk_disable(ARRAY_SIZE(ws->regulators),
+				      ws->regulators);
+}
+
+static int ws2401_unprepare(struct drm_panel *panel)
+{
+	struct ws2401 *ws = to_ws2401(panel);
+	struct mipi_dbi *dbi = &ws->dbi;
+
+	/* Make sure we disable backlight, if any */
+	if (ws->internal_bl)
+		mipi_dbi_command(dbi, WS2401_WRCTRLD, 0x00);
+	mipi_dbi_command(dbi, MIPI_DCS_ENTER_SLEEP_MODE);
+	msleep(120);
+	return ws2401_power_off(to_ws2401(panel));
+}
+
+static int ws2401_disable(struct drm_panel *panel)
+{
+	struct ws2401 *ws = to_ws2401(panel);
+	struct mipi_dbi *dbi = &ws->dbi;
+
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_OFF);
+	msleep(25);
+
+	return 0;
+}
+
+static int ws2401_prepare(struct drm_panel *panel)
+{
+	return ws2401_power_on(to_ws2401(panel));
+}
+
+static int ws2401_enable(struct drm_panel *panel)
+{
+	struct ws2401 *ws = to_ws2401(panel);
+	struct mipi_dbi *dbi = &ws->dbi;
+
+	mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON);
+
+	return 0;
+}
+
+/**
+ * ws2401_get_modes() - return the mode
+ * @panel: the panel to get the mode for
+ * @connector: reference to the central DRM connector control structure
+ */
+static int ws2401_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
+{
+	struct ws2401 *ws = to_ws2401(panel);
+	struct drm_display_mode *mode;
+	static const u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+
+	/*
+	 * We just support the LMS380KF01 so far, if we implement more panels
+	 * this mode, the following connector display_info settings and
+	 * probably the custom DCS sequences needs to selected based on what
+	 * the target panel needs.
+	 */
+	mode = drm_mode_duplicate(connector->dev, &lms380kf01_480_800_mode);
+	if (!mode) {
+		dev_err(ws->dev, "failed to add mode\n");
+		return -ENOMEM;
+	}
+
+	connector->display_info.bpc = 8;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+	connector->display_info.bus_flags =
+		DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE;
+	drm_display_info_set_bus_formats(&connector->display_info,
+					 &bus_format, 1);
+
+	drm_mode_set_name(mode);
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static const struct drm_panel_funcs ws2401_drm_funcs = {
+	.disable = ws2401_disable,
+	.unprepare = ws2401_unprepare,
+	.prepare = ws2401_prepare,
+	.enable = ws2401_enable,
+	.get_modes = ws2401_get_modes,
+};
+
+static int ws2401_set_brightness(struct backlight_device *bl)
+{
+	struct ws2401 *ws = bl_get_data(bl);
+	struct mipi_dbi *dbi = &ws->dbi;
+	u8 brightness = backlight_get_brightness(bl);
+
+	if (backlight_is_blank(bl)) {
+		mipi_dbi_command(dbi, WS2401_WRCTRLD, 0x00);
+	} else {
+		mipi_dbi_command(dbi, WS2401_WRCTRLD, 0x2c);
+		mipi_dbi_command(dbi, WS2401_WRDISBV, brightness);
+	}
+
+	return 0;
+}
+
+static const struct backlight_ops ws2401_bl_ops = {
+	.update_status = ws2401_set_brightness,
+};
+
+static const struct backlight_properties ws2401_bl_props = {
+	.type = BACKLIGHT_PLATFORM,
+	.brightness = 120,
+	.max_brightness = U8_MAX,
+};
+
+static int ws2401_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct ws2401 *ws;
+	int ret;
+
+	ws = devm_kzalloc(dev, sizeof(*ws), GFP_KERNEL);
+	if (!ws)
+		return -ENOMEM;
+	ws->dev = dev;
+
+	/*
+	 * VCI   is the analog voltage supply
+	 * VCCIO is the digital I/O voltage supply
+	 */
+	ws->regulators[0].supply = "vci";
+	ws->regulators[1].supply = "vccio";
+	ret = devm_regulator_bulk_get(dev,
+				      ARRAY_SIZE(ws->regulators),
+				      ws->regulators);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to get regulators\n");
+
+	ws->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(ws->reset)) {
+		ret = PTR_ERR(ws->reset);
+		return dev_err_probe(dev, ret, "no RESET GPIO\n");
+	}
+
+	ret = mipi_dbi_spi_init(spi, &ws->dbi, NULL);
+	if (ret)
+		return dev_err_probe(dev, ret, "MIPI DBI init failed\n");
+	ws->dbi.read_commands = ws2401_dbi_read_commands;
+
+	ws2401_power_on(ws);
+	ws2401_read_mtp_id(ws);
+	ws2401_power_off(ws);
+
+	drm_panel_init(&ws->panel, dev, &ws2401_drm_funcs,
+		       DRM_MODE_CONNECTOR_DPI);
+
+	ret = drm_panel_of_backlight(&ws->panel);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				"failed to get external backlight device\n");
+
+	if (!ws->panel.backlight) {
+		dev_dbg(dev, "no external backlight, using internal backlight\n");
+		ws->panel.backlight =
+			devm_backlight_device_register(dev, "ws2401", dev, ws,
+				&ws2401_bl_ops, &ws2401_bl_props);
+		if (IS_ERR(ws->panel.backlight))
+			return dev_err_probe(dev, PTR_ERR(ws->panel.backlight),
+				"failed to register backlight device\n");
+	} else {
+		dev_dbg(dev, "using external backlight\n");
+	}
+
+	spi_set_drvdata(spi, ws);
+
+	drm_panel_add(&ws->panel);
+	dev_dbg(dev, "added panel\n");
+
+	return 0;
+}
+
+static int ws2401_remove(struct spi_device *spi)
+{
+	struct ws2401 *ws = spi_get_drvdata(spi);
+
+	drm_panel_remove(&ws->panel);
+	return 0;
+}
+
+/*
+ * Samsung LMS380KF01 is the one instance of this display controller that we
+ * know about, but if more are found, the controller can be parameterized
+ * here and used for other configurations.
+ */
+static const struct of_device_id ws2401_match[] = {
+	{ .compatible = "samsung,lms380kf01", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ws2401_match);
+
+static struct spi_driver ws2401_driver = {
+	.probe		= ws2401_probe,
+	.remove		= ws2401_remove,
+	.driver		= {
+		.name	= "ws2401-panel",
+		.of_match_table = ws2401_match,
+	},
+};
+module_spi_driver(ws2401_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Samsung WS2401 panel driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c b/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c
index 55172d63a922..d17aae8b71d7 100644
--- a/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c
+++ b/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c
@@ -311,7 +311,7 @@ static int xpp055c272_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	drm_panel_init(&ctx->panel, &dsi->dev, &xpp055c272_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 3644652f726f..194af7f607a6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -106,7 +106,8 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	if (ret) {
 		/* Continue if the optional regulator is missing */
 		if (ret != -ENODEV) {
-			DRM_DEV_ERROR(dev, "Couldn't set OPP regulators\n");
+			if (ret != -EPROBE_DEFER)
+				DRM_DEV_ERROR(dev, "Couldn't set OPP regulators\n");
 			return ret;
 		}
 	}
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index 125ed973feaa..bd9b7be63b0f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -54,7 +54,8 @@ static int panfrost_clk_init(struct panfrost_device *pfdev)
 	if (IS_ERR(pfdev->bus_clock)) {
 		dev_err(pfdev->dev, "get bus_clock failed %ld\n",
 			PTR_ERR(pfdev->bus_clock));
-		return PTR_ERR(pfdev->bus_clock);
+		err = PTR_ERR(pfdev->bus_clock);
+		goto disable_clock;
 	}
 
 	if (pfdev->bus_clock) {
@@ -291,55 +292,100 @@ void panfrost_device_fini(struct panfrost_device *pfdev)
 	panfrost_clk_fini(pfdev);
 }
 
-const char *panfrost_exception_name(struct panfrost_device *pfdev, u32 exception_code)
-{
-	switch (exception_code) {
-		/* Non-Fault Status code */
-	case 0x00: return "NOT_STARTED/IDLE/OK";
-	case 0x01: return "DONE";
-	case 0x02: return "INTERRUPTED";
-	case 0x03: return "STOPPED";
-	case 0x04: return "TERMINATED";
-	case 0x08: return "ACTIVE";
-		/* Job exceptions */
-	case 0x40: return "JOB_CONFIG_FAULT";
-	case 0x41: return "JOB_POWER_FAULT";
-	case 0x42: return "JOB_READ_FAULT";
-	case 0x43: return "JOB_WRITE_FAULT";
-	case 0x44: return "JOB_AFFINITY_FAULT";
-	case 0x48: return "JOB_BUS_FAULT";
-	case 0x50: return "INSTR_INVALID_PC";
-	case 0x51: return "INSTR_INVALID_ENC";
-	case 0x52: return "INSTR_TYPE_MISMATCH";
-	case 0x53: return "INSTR_OPERAND_FAULT";
-	case 0x54: return "INSTR_TLS_FAULT";
-	case 0x55: return "INSTR_BARRIER_FAULT";
-	case 0x56: return "INSTR_ALIGN_FAULT";
-	case 0x58: return "DATA_INVALID_FAULT";
-	case 0x59: return "TILE_RANGE_FAULT";
-	case 0x5A: return "ADDR_RANGE_FAULT";
-	case 0x60: return "OUT_OF_MEMORY";
-		/* GPU exceptions */
-	case 0x80: return "DELAYED_BUS_FAULT";
-	case 0x88: return "SHAREABILITY_FAULT";
-		/* MMU exceptions */
-	case 0xC1: return "TRANSLATION_FAULT_LEVEL1";
-	case 0xC2: return "TRANSLATION_FAULT_LEVEL2";
-	case 0xC3: return "TRANSLATION_FAULT_LEVEL3";
-	case 0xC4: return "TRANSLATION_FAULT_LEVEL4";
-	case 0xC8: return "PERMISSION_FAULT";
-	case 0xC9 ... 0xCF: return "PERMISSION_FAULT";
-	case 0xD1: return "TRANSTAB_BUS_FAULT_LEVEL1";
-	case 0xD2: return "TRANSTAB_BUS_FAULT_LEVEL2";
-	case 0xD3: return "TRANSTAB_BUS_FAULT_LEVEL3";
-	case 0xD4: return "TRANSTAB_BUS_FAULT_LEVEL4";
-	case 0xD8: return "ACCESS_FLAG";
-	case 0xD9 ... 0xDF: return "ACCESS_FLAG";
-	case 0xE0 ... 0xE7: return "ADDRESS_SIZE_FAULT";
-	case 0xE8 ... 0xEF: return "MEMORY_ATTRIBUTES_FAULT";
+#define PANFROST_EXCEPTION(id) \
+	[DRM_PANFROST_EXCEPTION_ ## id] = { \
+		.name = #id, \
 	}
 
-	return "UNKNOWN";
+struct panfrost_exception_info {
+	const char *name;
+};
+
+static const struct panfrost_exception_info panfrost_exception_infos[] = {
+	PANFROST_EXCEPTION(OK),
+	PANFROST_EXCEPTION(DONE),
+	PANFROST_EXCEPTION(INTERRUPTED),
+	PANFROST_EXCEPTION(STOPPED),
+	PANFROST_EXCEPTION(TERMINATED),
+	PANFROST_EXCEPTION(KABOOM),
+	PANFROST_EXCEPTION(EUREKA),
+	PANFROST_EXCEPTION(ACTIVE),
+	PANFROST_EXCEPTION(JOB_CONFIG_FAULT),
+	PANFROST_EXCEPTION(JOB_POWER_FAULT),
+	PANFROST_EXCEPTION(JOB_READ_FAULT),
+	PANFROST_EXCEPTION(JOB_WRITE_FAULT),
+	PANFROST_EXCEPTION(JOB_AFFINITY_FAULT),
+	PANFROST_EXCEPTION(JOB_BUS_FAULT),
+	PANFROST_EXCEPTION(INSTR_INVALID_PC),
+	PANFROST_EXCEPTION(INSTR_INVALID_ENC),
+	PANFROST_EXCEPTION(INSTR_TYPE_MISMATCH),
+	PANFROST_EXCEPTION(INSTR_OPERAND_FAULT),
+	PANFROST_EXCEPTION(INSTR_TLS_FAULT),
+	PANFROST_EXCEPTION(INSTR_BARRIER_FAULT),
+	PANFROST_EXCEPTION(INSTR_ALIGN_FAULT),
+	PANFROST_EXCEPTION(DATA_INVALID_FAULT),
+	PANFROST_EXCEPTION(TILE_RANGE_FAULT),
+	PANFROST_EXCEPTION(ADDR_RANGE_FAULT),
+	PANFROST_EXCEPTION(IMPRECISE_FAULT),
+	PANFROST_EXCEPTION(OOM),
+	PANFROST_EXCEPTION(OOM_AFBC),
+	PANFROST_EXCEPTION(UNKNOWN),
+	PANFROST_EXCEPTION(DELAYED_BUS_FAULT),
+	PANFROST_EXCEPTION(GPU_SHAREABILITY_FAULT),
+	PANFROST_EXCEPTION(SYS_SHAREABILITY_FAULT),
+	PANFROST_EXCEPTION(GPU_CACHEABILITY_FAULT),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_0),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_1),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_2),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_3),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_4),
+	PANFROST_EXCEPTION(TRANSLATION_FAULT_IDENTITY),
+	PANFROST_EXCEPTION(PERM_FAULT_0),
+	PANFROST_EXCEPTION(PERM_FAULT_1),
+	PANFROST_EXCEPTION(PERM_FAULT_2),
+	PANFROST_EXCEPTION(PERM_FAULT_3),
+	PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_0),
+	PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_1),
+	PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_2),
+	PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_3),
+	PANFROST_EXCEPTION(ACCESS_FLAG_0),
+	PANFROST_EXCEPTION(ACCESS_FLAG_1),
+	PANFROST_EXCEPTION(ACCESS_FLAG_2),
+	PANFROST_EXCEPTION(ACCESS_FLAG_3),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN0),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN1),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN2),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN3),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT0),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT1),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT2),
+	PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT3),
+	PANFROST_EXCEPTION(MEM_ATTR_FAULT_0),
+	PANFROST_EXCEPTION(MEM_ATTR_FAULT_1),
+	PANFROST_EXCEPTION(MEM_ATTR_FAULT_2),
+	PANFROST_EXCEPTION(MEM_ATTR_FAULT_3),
+	PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_0),
+	PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_1),
+	PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_2),
+	PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_3),
+};
+
+const char *panfrost_exception_name(u32 exception_code)
+{
+	if (WARN_ON(exception_code >= ARRAY_SIZE(panfrost_exception_infos) ||
+		    !panfrost_exception_infos[exception_code].name))
+		return "Unknown exception type";
+
+	return panfrost_exception_infos[exception_code].name;
+}
+
+bool panfrost_exception_needs_reset(const struct panfrost_device *pfdev,
+				    u32 exception_code)
+{
+	/* Right now, none of the GPU we support need a reset, but this
+	 * might change.
+	 */
+	return false;
 }
 
 void panfrost_device_reset(struct panfrost_device *pfdev)
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index f614e98771e4..8b25278f34c8 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -97,11 +97,12 @@ struct panfrost_device {
 	spinlock_t as_lock;
 	unsigned long as_in_use_mask;
 	unsigned long as_alloc_mask;
+	unsigned long as_faulty_mask;
 	struct list_head as_lru_list;
 
 	struct panfrost_job_slot *js;
 
-	struct panfrost_job *jobs[NUM_JOB_SLOTS];
+	struct panfrost_job *jobs[NUM_JOB_SLOTS][2];
 	struct list_head scheduled_jobs;
 
 	struct panfrost_perfcnt *perfcnt;
@@ -109,6 +110,7 @@ struct panfrost_device {
 	struct mutex sched_lock;
 
 	struct {
+		struct workqueue_struct *wq;
 		struct work_struct work;
 		atomic_t pending;
 	} reset;
@@ -121,8 +123,12 @@ struct panfrost_device {
 };
 
 struct panfrost_mmu {
+	struct panfrost_device *pfdev;
+	struct kref refcount;
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
+	struct drm_mm mm;
+	spinlock_t mm_lock;
 	int as;
 	atomic_t as_count;
 	struct list_head list;
@@ -133,9 +139,7 @@ struct panfrost_file_priv {
 
 	struct drm_sched_entity sched_entity[NUM_JOB_SLOTS];
 
-	struct panfrost_mmu mmu;
-	struct drm_mm mm;
-	spinlock_t mm_lock;
+	struct panfrost_mmu *mmu;
 };
 
 static inline struct panfrost_device *to_panfrost_device(struct drm_device *ddev)
@@ -171,6 +175,91 @@ void panfrost_device_reset(struct panfrost_device *pfdev);
 int panfrost_device_resume(struct device *dev);
 int panfrost_device_suspend(struct device *dev);
 
-const char *panfrost_exception_name(struct panfrost_device *pfdev, u32 exception_code);
+enum drm_panfrost_exception_type {
+	DRM_PANFROST_EXCEPTION_OK = 0x00,
+	DRM_PANFROST_EXCEPTION_DONE = 0x01,
+	DRM_PANFROST_EXCEPTION_INTERRUPTED = 0x02,
+	DRM_PANFROST_EXCEPTION_STOPPED = 0x03,
+	DRM_PANFROST_EXCEPTION_TERMINATED = 0x04,
+	DRM_PANFROST_EXCEPTION_KABOOM = 0x05,
+	DRM_PANFROST_EXCEPTION_EUREKA = 0x06,
+	DRM_PANFROST_EXCEPTION_ACTIVE = 0x08,
+	DRM_PANFROST_EXCEPTION_MAX_NON_FAULT = 0x3f,
+	DRM_PANFROST_EXCEPTION_JOB_CONFIG_FAULT = 0x40,
+	DRM_PANFROST_EXCEPTION_JOB_POWER_FAULT = 0x41,
+	DRM_PANFROST_EXCEPTION_JOB_READ_FAULT = 0x42,
+	DRM_PANFROST_EXCEPTION_JOB_WRITE_FAULT = 0x43,
+	DRM_PANFROST_EXCEPTION_JOB_AFFINITY_FAULT = 0x44,
+	DRM_PANFROST_EXCEPTION_JOB_BUS_FAULT = 0x48,
+	DRM_PANFROST_EXCEPTION_INSTR_INVALID_PC = 0x50,
+	DRM_PANFROST_EXCEPTION_INSTR_INVALID_ENC = 0x51,
+	DRM_PANFROST_EXCEPTION_INSTR_TYPE_MISMATCH = 0x52,
+	DRM_PANFROST_EXCEPTION_INSTR_OPERAND_FAULT = 0x53,
+	DRM_PANFROST_EXCEPTION_INSTR_TLS_FAULT = 0x54,
+	DRM_PANFROST_EXCEPTION_INSTR_BARRIER_FAULT = 0x55,
+	DRM_PANFROST_EXCEPTION_INSTR_ALIGN_FAULT = 0x56,
+	DRM_PANFROST_EXCEPTION_DATA_INVALID_FAULT = 0x58,
+	DRM_PANFROST_EXCEPTION_TILE_RANGE_FAULT = 0x59,
+	DRM_PANFROST_EXCEPTION_ADDR_RANGE_FAULT = 0x5a,
+	DRM_PANFROST_EXCEPTION_IMPRECISE_FAULT = 0x5b,
+	DRM_PANFROST_EXCEPTION_OOM = 0x60,
+	DRM_PANFROST_EXCEPTION_OOM_AFBC = 0x61,
+	DRM_PANFROST_EXCEPTION_UNKNOWN = 0x7f,
+	DRM_PANFROST_EXCEPTION_DELAYED_BUS_FAULT = 0x80,
+	DRM_PANFROST_EXCEPTION_GPU_SHAREABILITY_FAULT = 0x88,
+	DRM_PANFROST_EXCEPTION_SYS_SHAREABILITY_FAULT = 0x89,
+	DRM_PANFROST_EXCEPTION_GPU_CACHEABILITY_FAULT = 0x8a,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_0 = 0xc0,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_1 = 0xc1,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_2 = 0xc2,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_3 = 0xc3,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_4 = 0xc4,
+	DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_IDENTITY = 0xc7,
+	DRM_PANFROST_EXCEPTION_PERM_FAULT_0 = 0xc8,
+	DRM_PANFROST_EXCEPTION_PERM_FAULT_1 = 0xc9,
+	DRM_PANFROST_EXCEPTION_PERM_FAULT_2 = 0xca,
+	DRM_PANFROST_EXCEPTION_PERM_FAULT_3 = 0xcb,
+	DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_0 = 0xd0,
+	DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_1 = 0xd1,
+	DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_2 = 0xd2,
+	DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_3 = 0xd3,
+	DRM_PANFROST_EXCEPTION_ACCESS_FLAG_0 = 0xd8,
+	DRM_PANFROST_EXCEPTION_ACCESS_FLAG_1 = 0xd9,
+	DRM_PANFROST_EXCEPTION_ACCESS_FLAG_2 = 0xda,
+	DRM_PANFROST_EXCEPTION_ACCESS_FLAG_3 = 0xdb,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN0 = 0xe0,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN1 = 0xe1,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN2 = 0xe2,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN3 = 0xe3,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT0 = 0xe4,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT1 = 0xe5,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT2 = 0xe6,
+	DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT3 = 0xe7,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_0 = 0xe8,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_1 = 0xe9,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_2 = 0xea,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_3 = 0xeb,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_0 = 0xec,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_1 = 0xed,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_2 = 0xee,
+	DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_3 = 0xef,
+};
+
+static inline bool
+panfrost_exception_is_fault(u32 exception_code)
+{
+	return exception_code > DRM_PANFROST_EXCEPTION_MAX_NON_FAULT;
+}
+
+const char *panfrost_exception_name(u32 exception_code);
+bool panfrost_exception_needs_reset(const struct panfrost_device *pfdev,
+				    u32 exception_code);
+
+static inline void
+panfrost_device_schedule_reset(struct panfrost_device *pfdev)
+{
+	atomic_set(&pfdev->reset.pending, 1);
+	queue_work(pfdev->reset.wq, &pfdev->reset.work);
+}
 
 #endif
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 075ec0ef746c..1ffaef5ec5ff 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -138,12 +138,6 @@ panfrost_lookup_bos(struct drm_device *dev,
 	if (!job->bo_count)
 		return 0;
 
-	job->implicit_fences = kvmalloc_array(job->bo_count,
-				  sizeof(struct dma_fence *),
-				  GFP_KERNEL | __GFP_ZERO);
-	if (!job->implicit_fences)
-		return -ENOMEM;
-
 	ret = drm_gem_objects_lookup(file_priv,
 				     (void __user *)(uintptr_t)args->bo_handles,
 				     job->bo_count, &job->bos);
@@ -174,7 +168,7 @@ panfrost_lookup_bos(struct drm_device *dev,
 }
 
 /**
- * panfrost_copy_in_sync() - Sets up job->in_fences[] with the sync objects
+ * panfrost_copy_in_sync() - Sets up job->deps with the sync objects
  * referenced by the job.
  * @dev: DRM device
  * @file_priv: DRM file for this fd
@@ -194,22 +188,14 @@ panfrost_copy_in_sync(struct drm_device *dev,
 {
 	u32 *handles;
 	int ret = 0;
-	int i;
+	int i, in_fence_count;
 
-	job->in_fence_count = args->in_sync_count;
+	in_fence_count = args->in_sync_count;
 
-	if (!job->in_fence_count)
+	if (!in_fence_count)
 		return 0;
 
-	job->in_fences = kvmalloc_array(job->in_fence_count,
-					sizeof(struct dma_fence *),
-					GFP_KERNEL | __GFP_ZERO);
-	if (!job->in_fences) {
-		DRM_DEBUG("Failed to allocate job in fences\n");
-		return -ENOMEM;
-	}
-
-	handles = kvmalloc_array(job->in_fence_count, sizeof(u32), GFP_KERNEL);
+	handles = kvmalloc_array(in_fence_count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
 		DRM_DEBUG("Failed to allocate incoming syncobj handles\n");
@@ -218,16 +204,23 @@ panfrost_copy_in_sync(struct drm_device *dev,
 
 	if (copy_from_user(handles,
 			   (void __user *)(uintptr_t)args->in_syncs,
-			   job->in_fence_count * sizeof(u32))) {
+			   in_fence_count * sizeof(u32))) {
 		ret = -EFAULT;
 		DRM_DEBUG("Failed to copy in syncobj handles\n");
 		goto fail;
 	}
 
-	for (i = 0; i < job->in_fence_count; i++) {
+	for (i = 0; i < in_fence_count; i++) {
+		struct dma_fence *fence;
+
 		ret = drm_syncobj_find_fence(file_priv, handles[i], 0, 0,
-					     &job->in_fences[i]);
-		if (ret == -EINVAL)
+					     &fence);
+		if (ret)
+			goto fail;
+
+		ret = drm_gem_fence_array_add(&job->deps, fence);
+
+		if (ret)
 			goto fail;
 	}
 
@@ -265,6 +258,8 @@ static int panfrost_ioctl_submit(struct drm_device *dev, void *data,
 
 	kref_init(&job->refcount);
 
+	xa_init_flags(&job->deps, XA_FLAGS_ALLOC);
+
 	job->pfdev = pfdev;
 	job->jc = args->jc;
 	job->requirements = args->requirements;
@@ -417,7 +412,7 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
 		 * anyway, so let's not bother.
 		 */
 		if (!list_is_singular(&bo->mappings.list) ||
-		    WARN_ON_ONCE(first->mmu != &priv->mmu)) {
+		    WARN_ON_ONCE(first->mmu != priv->mmu)) {
 			ret = -EINVAL;
 			goto out_unlock_mappings;
 		}
@@ -449,32 +444,6 @@ int panfrost_unstable_ioctl_check(void)
 	return 0;
 }
 
-#define PFN_4G		(SZ_4G >> PAGE_SHIFT)
-#define PFN_4G_MASK	(PFN_4G - 1)
-#define PFN_16M		(SZ_16M >> PAGE_SHIFT)
-
-static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node,
-					 unsigned long color,
-					 u64 *start, u64 *end)
-{
-	/* Executable buffers can't start or end on a 4GB boundary */
-	if (!(color & PANFROST_BO_NOEXEC)) {
-		u64 next_seg;
-
-		if ((*start & PFN_4G_MASK) == 0)
-			(*start)++;
-
-		if ((*end & PFN_4G_MASK) == 0)
-			(*end)--;
-
-		next_seg = ALIGN(*start, PFN_4G);
-		if (next_seg - *start <= PFN_16M)
-			*start = next_seg + 1;
-
-		*end = min(*end, ALIGN(*start, PFN_4G) - 1);
-	}
-}
-
 static int
 panfrost_open(struct drm_device *dev, struct drm_file *file)
 {
@@ -489,15 +458,11 @@ panfrost_open(struct drm_device *dev, struct drm_file *file)
 	panfrost_priv->pfdev = pfdev;
 	file->driver_priv = panfrost_priv;
 
-	spin_lock_init(&panfrost_priv->mm_lock);
-
-	/* 4G enough for now. can be 48-bit */
-	drm_mm_init(&panfrost_priv->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT);
-	panfrost_priv->mm.color_adjust = panfrost_drm_mm_color_adjust;
-
-	ret = panfrost_mmu_pgtable_alloc(panfrost_priv);
-	if (ret)
-		goto err_pgtable;
+	panfrost_priv->mmu = panfrost_mmu_ctx_create(pfdev);
+	if (IS_ERR(panfrost_priv->mmu)) {
+		ret = PTR_ERR(panfrost_priv->mmu);
+		goto err_free;
+	}
 
 	ret = panfrost_job_open(panfrost_priv);
 	if (ret)
@@ -506,9 +471,8 @@ panfrost_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 
 err_job:
-	panfrost_mmu_pgtable_free(panfrost_priv);
-err_pgtable:
-	drm_mm_takedown(&panfrost_priv->mm);
+	panfrost_mmu_ctx_put(panfrost_priv->mmu);
+err_free:
 	kfree(panfrost_priv);
 	return ret;
 }
@@ -521,8 +485,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file)
 	panfrost_perfcnt_close(file);
 	panfrost_job_close(panfrost_priv);
 
-	panfrost_mmu_pgtable_free(panfrost_priv);
-	drm_mm_takedown(&panfrost_priv->mm);
+	panfrost_mmu_ctx_put(panfrost_priv->mmu);
 	kfree(panfrost_priv);
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 3e0723bc36bd..23377481f4e3 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -60,7 +60,7 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 
 	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(iter, &bo->mappings.list, node) {
-		if (iter->mmu == &priv->mmu) {
+		if (iter->mmu == priv->mmu) {
 			kref_get(&iter->refcount);
 			mapping = iter;
 			break;
@@ -74,16 +74,13 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 static void
 panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping)
 {
-	struct panfrost_file_priv *priv;
-
 	if (mapping->active)
 		panfrost_mmu_unmap(mapping);
 
-	priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu);
-	spin_lock(&priv->mm_lock);
+	spin_lock(&mapping->mmu->mm_lock);
 	if (drm_mm_node_allocated(&mapping->mmnode))
 		drm_mm_remove_node(&mapping->mmnode);
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mapping->mmu->mm_lock);
 }
 
 static void panfrost_gem_mapping_release(struct kref *kref)
@@ -94,6 +91,7 @@ static void panfrost_gem_mapping_release(struct kref *kref)
 
 	panfrost_gem_teardown_mapping(mapping);
 	drm_gem_object_put(&mapping->obj->base.base);
+	panfrost_mmu_ctx_put(mapping->mmu);
 	kfree(mapping);
 }
 
@@ -143,11 +141,11 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 	else
 		align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0;
 
-	mapping->mmu = &priv->mmu;
-	spin_lock(&priv->mm_lock);
-	ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode,
+	mapping->mmu = panfrost_mmu_ctx_get(priv->mmu);
+	spin_lock(&mapping->mmu->mm_lock);
+	ret = drm_mm_insert_node_generic(&mapping->mmu->mm, &mapping->mmnode,
 					 size >> PAGE_SHIFT, align, color, 0);
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mapping->mmu->mm_lock);
 	if (ret)
 		goto err;
 
@@ -176,7 +174,7 @@ void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
 
 	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(iter, &bo->mappings.list, node) {
-		if (iter->mmu == &priv->mmu) {
+		if (iter->mmu == priv->mmu) {
 			mapping = iter;
 			list_del(&iter->node);
 			break;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 0e70e27fd8c3..bbe628b306ee 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -33,7 +33,7 @@ static irqreturn_t panfrost_gpu_irq_handler(int irq, void *data)
 		address |= gpu_read(pfdev, GPU_FAULT_ADDRESS_LO);
 
 		dev_warn(pfdev->dev, "GPU Fault 0x%08x (%s) at 0x%016llx\n",
-			 fault_status & 0xFF, panfrost_exception_name(pfdev, fault_status),
+			 fault_status, panfrost_exception_name(fault_status & 0xFF),
 			 address);
 
 		if (state & GPU_IRQ_MULTIPLE_FAULT)
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 2df3e999a38d..71a72fb50e6b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -4,6 +4,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/dma-resv.h>
@@ -25,17 +26,8 @@
 #define job_write(dev, reg, data) writel(data, dev->iomem + (reg))
 #define job_read(dev, reg) readl(dev->iomem + (reg))
 
-enum panfrost_queue_status {
-	PANFROST_QUEUE_STATUS_ACTIVE,
-	PANFROST_QUEUE_STATUS_STOPPED,
-	PANFROST_QUEUE_STATUS_STARTING,
-	PANFROST_QUEUE_STATUS_FAULT_PENDING,
-};
-
 struct panfrost_queue_state {
 	struct drm_gpu_scheduler sched;
-	atomic_t status;
-	struct mutex lock;
 	u64 fence_context;
 	u64 emit_seqno;
 };
@@ -43,6 +35,7 @@ struct panfrost_queue_state {
 struct panfrost_job_slot {
 	struct panfrost_queue_state queue[NUM_JOB_SLOTS];
 	spinlock_t job_lock;
+	int irq;
 };
 
 static struct panfrost_job *
@@ -148,9 +141,52 @@ static void panfrost_job_write_affinity(struct panfrost_device *pfdev,
 	job_write(pfdev, JS_AFFINITY_NEXT_HI(js), affinity >> 32);
 }
 
+static u32
+panfrost_get_job_chain_flag(const struct panfrost_job *job)
+{
+	struct panfrost_fence *f = to_panfrost_fence(job->done_fence);
+
+	if (!panfrost_has_hw_feature(job->pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION))
+		return 0;
+
+	return (f->seqno & 1) ? JS_CONFIG_JOB_CHAIN_FLAG : 0;
+}
+
+static struct panfrost_job *
+panfrost_dequeue_job(struct panfrost_device *pfdev, int slot)
+{
+	struct panfrost_job *job = pfdev->jobs[slot][0];
+
+	WARN_ON(!job);
+	pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
+	pfdev->jobs[slot][1] = NULL;
+
+	return job;
+}
+
+static unsigned int
+panfrost_enqueue_job(struct panfrost_device *pfdev, int slot,
+		     struct panfrost_job *job)
+{
+	if (WARN_ON(!job))
+		return 0;
+
+	if (!pfdev->jobs[slot][0]) {
+		pfdev->jobs[slot][0] = job;
+		return 0;
+	}
+
+	WARN_ON(pfdev->jobs[slot][1]);
+	pfdev->jobs[slot][1] = job;
+	WARN_ON(panfrost_get_job_chain_flag(job) ==
+		panfrost_get_job_chain_flag(pfdev->jobs[slot][0]));
+	return 1;
+}
+
 static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 {
 	struct panfrost_device *pfdev = job->pfdev;
+	unsigned int subslot;
 	u32 cfg;
 	u64 jc_head = job->jc;
 	int ret;
@@ -165,7 +201,7 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 		return;
 	}
 
-	cfg = panfrost_mmu_as_get(pfdev, &job->file_priv->mmu);
+	cfg = panfrost_mmu_as_get(pfdev, job->file_priv->mmu);
 
 	job_write(pfdev, JS_HEAD_NEXT_LO(js), jc_head & 0xFFFFFFFF);
 	job_write(pfdev, JS_HEAD_NEXT_HI(js), jc_head >> 32);
@@ -176,7 +212,8 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	 * start */
 	cfg |= JS_CONFIG_THREAD_PRI(8) |
 		JS_CONFIG_START_FLUSH_CLEAN_INVALIDATE |
-		JS_CONFIG_END_FLUSH_CLEAN_INVALIDATE;
+		JS_CONFIG_END_FLUSH_CLEAN_INVALIDATE |
+		panfrost_get_job_chain_flag(job);
 
 	if (panfrost_has_hw_feature(pfdev, HW_FEATURE_FLUSH_REDUCTION))
 		cfg |= JS_CONFIG_ENABLE_FLUSH_REDUCTION;
@@ -190,20 +227,33 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 		job_write(pfdev, JS_FLUSH_ID_NEXT(js), job->flush_id);
 
 	/* GO ! */
-	dev_dbg(pfdev->dev, "JS: Submitting atom %p to js[%d] with head=0x%llx",
-				job, js, jc_head);
 
-	job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
+	spin_lock(&pfdev->js->job_lock);
+	subslot = panfrost_enqueue_job(pfdev, js, job);
+	/* Don't queue the job if a reset is in progress */
+	if (!atomic_read(&pfdev->reset.pending)) {
+		job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
+		dev_dbg(pfdev->dev,
+			"JS: Submitting atom %p to js[%d][%d] with head=0x%llx AS %d",
+			job, js, subslot, jc_head, cfg & 0xf);
+	}
+	spin_unlock(&pfdev->js->job_lock);
 }
 
-static void panfrost_acquire_object_fences(struct drm_gem_object **bos,
-					   int bo_count,
-					   struct dma_fence **implicit_fences)
+static int panfrost_acquire_object_fences(struct drm_gem_object **bos,
+					  int bo_count,
+					  struct xarray *deps)
 {
-	int i;
+	int i, ret;
 
-	for (i = 0; i < bo_count; i++)
-		implicit_fences[i] = dma_resv_get_excl_unlocked(bos[i]->resv);
+	for (i = 0; i < bo_count; i++) {
+		/* panfrost always uses write mode in its current uapi */
+		ret = drm_gem_fence_array_add_implicit(deps, bos[i], true);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static void panfrost_attach_object_fences(struct drm_gem_object **bos,
@@ -224,14 +274,13 @@ int panfrost_job_push(struct panfrost_job *job)
 	struct ww_acquire_ctx acquire_ctx;
 	int ret = 0;
 
-	mutex_lock(&pfdev->sched_lock);
 
 	ret = drm_gem_lock_reservations(job->bos, job->bo_count,
 					    &acquire_ctx);
-	if (ret) {
-		mutex_unlock(&pfdev->sched_lock);
+	if (ret)
 		return ret;
-	}
+
+	mutex_lock(&pfdev->sched_lock);
 
 	ret = drm_sched_job_init(&job->base, entity, NULL);
 	if (ret) {
@@ -241,10 +290,14 @@ int panfrost_job_push(struct panfrost_job *job)
 
 	job->render_done_fence = dma_fence_get(&job->base.s_fence->finished);
 
-	kref_get(&job->refcount); /* put by scheduler job completion */
+	ret = panfrost_acquire_object_fences(job->bos, job->bo_count,
+					     &job->deps);
+	if (ret) {
+		mutex_unlock(&pfdev->sched_lock);
+		goto unlock;
+	}
 
-	panfrost_acquire_object_fences(job->bos, job->bo_count,
-				       job->implicit_fences);
+	kref_get(&job->refcount); /* put by scheduler job completion */
 
 	drm_sched_entity_push_job(&job->base, entity);
 
@@ -263,18 +316,15 @@ static void panfrost_job_cleanup(struct kref *ref)
 {
 	struct panfrost_job *job = container_of(ref, struct panfrost_job,
 						refcount);
+	struct dma_fence *fence;
+	unsigned long index;
 	unsigned int i;
 
-	if (job->in_fences) {
-		for (i = 0; i < job->in_fence_count; i++)
-			dma_fence_put(job->in_fences[i]);
-		kvfree(job->in_fences);
-	}
-	if (job->implicit_fences) {
-		for (i = 0; i < job->bo_count; i++)
-			dma_fence_put(job->implicit_fences[i]);
-		kvfree(job->implicit_fences);
+	xa_for_each(&job->deps, index, fence) {
+		dma_fence_put(fence);
 	}
+	xa_destroy(&job->deps);
+
 	dma_fence_put(job->done_fence);
 	dma_fence_put(job->render_done_fence);
 
@@ -317,26 +367,9 @@ static struct dma_fence *panfrost_job_dependency(struct drm_sched_job *sched_job
 						 struct drm_sched_entity *s_entity)
 {
 	struct panfrost_job *job = to_panfrost_job(sched_job);
-	struct dma_fence *fence;
-	unsigned int i;
 
-	/* Explicit fences */
-	for (i = 0; i < job->in_fence_count; i++) {
-		if (job->in_fences[i]) {
-			fence = job->in_fences[i];
-			job->in_fences[i] = NULL;
-			return fence;
-		}
-	}
-
-	/* Implicit fences, max. one per BO */
-	for (i = 0; i < job->bo_count; i++) {
-		if (job->implicit_fences[i]) {
-			fence = job->implicit_fences[i];
-			job->implicit_fences[i] = NULL;
-			return fence;
-		}
-	}
+	if (!xa_empty(&job->deps))
+		return xa_erase(&job->deps, job->last_dep++);
 
 	return NULL;
 }
@@ -351,11 +384,15 @@ static struct dma_fence *panfrost_job_run(struct drm_sched_job *sched_job)
 	if (unlikely(job->base.s_fence->finished.error))
 		return NULL;
 
-	pfdev->jobs[slot] = job;
+	/* Nothing to execute: can happen if the job has finished while
+	 * we were resetting the GPU.
+	 */
+	if (!job->jc)
+		return NULL;
 
 	fence = panfrost_fence_create(pfdev, slot);
 	if (IS_ERR(fence))
-		return NULL;
+		return fence;
 
 	if (job->done_fence)
 		dma_fence_put(job->done_fence);
@@ -379,57 +416,314 @@ void panfrost_job_enable_interrupts(struct panfrost_device *pfdev)
 	job_write(pfdev, JOB_INT_MASK, irq_mask);
 }
 
-static bool panfrost_scheduler_stop(struct panfrost_queue_state *queue,
-				    struct drm_sched_job *bad)
+static void panfrost_job_handle_err(struct panfrost_device *pfdev,
+				    struct panfrost_job *job,
+				    unsigned int js)
 {
-	enum panfrost_queue_status old_status;
-	bool stopped = false;
+	u32 js_status = job_read(pfdev, JS_STATUS(js));
+	const char *exception_name = panfrost_exception_name(js_status);
+	bool signal_fence = true;
+
+	if (!panfrost_exception_is_fault(js_status)) {
+		dev_dbg(pfdev->dev, "js event, js=%d, status=%s, head=0x%x, tail=0x%x",
+			js, exception_name,
+			job_read(pfdev, JS_HEAD_LO(js)),
+			job_read(pfdev, JS_TAIL_LO(js)));
+	} else {
+		dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x",
+			js, exception_name,
+			job_read(pfdev, JS_HEAD_LO(js)),
+			job_read(pfdev, JS_TAIL_LO(js)));
+	}
 
-	mutex_lock(&queue->lock);
-	old_status = atomic_xchg(&queue->status,
-				 PANFROST_QUEUE_STATUS_STOPPED);
-	if (old_status == PANFROST_QUEUE_STATUS_STOPPED)
-		goto out;
+	if (js_status == DRM_PANFROST_EXCEPTION_STOPPED) {
+		/* Update the job head so we can resume */
+		job->jc = job_read(pfdev, JS_TAIL_LO(js)) |
+			  ((u64)job_read(pfdev, JS_TAIL_HI(js)) << 32);
+
+		/* The job will be resumed, don't signal the fence */
+		signal_fence = false;
+	} else if (js_status == DRM_PANFROST_EXCEPTION_TERMINATED) {
+		/* Job has been hard-stopped, flag it as canceled */
+		dma_fence_set_error(job->done_fence, -ECANCELED);
+		job->jc = 0;
+	} else if (panfrost_exception_is_fault(js_status)) {
+		/* We might want to provide finer-grained error code based on
+		 * the exception type, but unconditionally setting to EINVAL
+		 * is good enough for now.
+		 */
+		dma_fence_set_error(job->done_fence, -EINVAL);
+		job->jc = 0;
+	}
 
-	WARN_ON(old_status != PANFROST_QUEUE_STATUS_ACTIVE);
-	drm_sched_stop(&queue->sched, bad);
-	if (bad)
-		drm_sched_increase_karma(bad);
+	panfrost_mmu_as_put(pfdev, job->file_priv->mmu);
+	panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
 
-	stopped = true;
+	if (signal_fence)
+		dma_fence_signal_locked(job->done_fence);
 
-	/*
-	 * Set the timeout to max so the timer doesn't get started
-	 * when we return from the timeout handler (restored in
-	 * panfrost_scheduler_start()).
+	pm_runtime_put_autosuspend(pfdev->dev);
+
+	if (panfrost_exception_needs_reset(pfdev, js_status)) {
+		atomic_set(&pfdev->reset.pending, 1);
+		drm_sched_fault(&pfdev->js->queue[js].sched);
+	}
+}
+
+static void panfrost_job_handle_done(struct panfrost_device *pfdev,
+				     struct panfrost_job *job)
+{
+	/* Set ->jc to 0 to avoid re-submitting an already finished job (can
+	 * happen when we receive the DONE interrupt while doing a GPU reset).
+	 */
+	job->jc = 0;
+	panfrost_mmu_as_put(pfdev, job->file_priv->mmu);
+	panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
+
+	dma_fence_signal_locked(job->done_fence);
+	pm_runtime_put_autosuspend(pfdev->dev);
+}
+
+static void panfrost_job_handle_irq(struct panfrost_device *pfdev, u32 status)
+{
+	struct panfrost_job *done[NUM_JOB_SLOTS][2] = {};
+	struct panfrost_job *failed[NUM_JOB_SLOTS] = {};
+	u32 js_state = 0, js_events = 0;
+	unsigned int i, j;
+
+	/* First we collect all failed/done jobs. */
+	while (status) {
+		u32 js_state_mask = 0;
+
+		for (j = 0; j < NUM_JOB_SLOTS; j++) {
+			if (status & MK_JS_MASK(j))
+				js_state_mask |= MK_JS_MASK(j);
+
+			if (status & JOB_INT_MASK_DONE(j)) {
+				if (done[j][0])
+					done[j][1] = panfrost_dequeue_job(pfdev, j);
+				else
+					done[j][0] = panfrost_dequeue_job(pfdev, j);
+			}
+
+			if (status & JOB_INT_MASK_ERR(j)) {
+				/* Cancel the next submission. Will be submitted
+				 * after we're done handling this failure if
+				 * there's no reset pending.
+				 */
+				job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_NOP);
+				failed[j] = panfrost_dequeue_job(pfdev, j);
+			}
+		}
+
+		/* JS_STATE is sampled when JOB_INT_CLEAR is written.
+		 * For each BIT(slot) or BIT(slot + 16) bit written to
+		 * JOB_INT_CLEAR, the corresponding bits in JS_STATE
+		 * (BIT(slot) and BIT(slot + 16)) are updated, but this
+		 * is racy. If we only have one job done at the time we
+		 * read JOB_INT_RAWSTAT but the second job fails before we
+		 * clear the status, we end up with a status containing
+		 * only the DONE bit and consider both jobs as DONE since
+		 * JS_STATE reports both NEXT and CURRENT as inactive.
+		 * To prevent that, let's repeat this clear+read steps
+		 * until status is 0.
+		 */
+		job_write(pfdev, JOB_INT_CLEAR, status);
+		js_state &= ~js_state_mask;
+		js_state |= job_read(pfdev, JOB_INT_JS_STATE) & js_state_mask;
+		js_events |= status;
+		status = job_read(pfdev, JOB_INT_RAWSTAT);
+	}
+
+	/* Then we handle the dequeued jobs. */
+	for (j = 0; j < NUM_JOB_SLOTS; j++) {
+		if (!(js_events & MK_JS_MASK(j)))
+			continue;
+
+		if (failed[j]) {
+			panfrost_job_handle_err(pfdev, failed[j], j);
+		} else if (pfdev->jobs[j][0] && !(js_state & MK_JS_MASK(j))) {
+			/* When the current job doesn't fail, the JM dequeues
+			 * the next job without waiting for an ACK, this means
+			 * we can have 2 jobs dequeued and only catch the
+			 * interrupt when the second one is done. If both slots
+			 * are inactive, but one job remains in pfdev->jobs[j],
+			 * consider it done. Of course that doesn't apply if a
+			 * failure happened since we cancelled execution of the
+			 * job in _NEXT (see above).
+			 */
+			if (WARN_ON(!done[j][0]))
+				done[j][0] = panfrost_dequeue_job(pfdev, j);
+			else
+				done[j][1] = panfrost_dequeue_job(pfdev, j);
+		}
+
+		for (i = 0; i < ARRAY_SIZE(done[0]) && done[j][i]; i++)
+			panfrost_job_handle_done(pfdev, done[j][i]);
+	}
+
+	/* And finally we requeue jobs that were waiting in the second slot
+	 * and have been stopped if we detected a failure on the first slot.
 	 */
-	queue->sched.timeout = MAX_SCHEDULE_TIMEOUT;
+	for (j = 0; j < NUM_JOB_SLOTS; j++) {
+		if (!(js_events & MK_JS_MASK(j)))
+			continue;
+
+		if (!failed[j] || !pfdev->jobs[j][0])
+			continue;
+
+		if (pfdev->jobs[j][0]->jc == 0) {
+			/* The job was cancelled, signal the fence now */
+			struct panfrost_job *canceled = panfrost_dequeue_job(pfdev, j);
+
+			dma_fence_set_error(canceled->done_fence, -ECANCELED);
+			panfrost_job_handle_done(pfdev, canceled);
+		} else if (!atomic_read(&pfdev->reset.pending)) {
+			/* Requeue the job we removed if no reset is pending */
+			job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_START);
+		}
+	}
+}
 
-out:
-	mutex_unlock(&queue->lock);
+static void panfrost_job_handle_irqs(struct panfrost_device *pfdev)
+{
+	u32 status = job_read(pfdev, JOB_INT_RAWSTAT);
+
+	while (status) {
+		pm_runtime_mark_last_busy(pfdev->dev);
 
-	return stopped;
+		spin_lock(&pfdev->js->job_lock);
+		panfrost_job_handle_irq(pfdev, status);
+		spin_unlock(&pfdev->js->job_lock);
+		status = job_read(pfdev, JOB_INT_RAWSTAT);
+	}
 }
 
-static void panfrost_scheduler_start(struct panfrost_queue_state *queue)
+static u32 panfrost_active_slots(struct panfrost_device *pfdev,
+				 u32 *js_state_mask, u32 js_state)
 {
-	enum panfrost_queue_status old_status;
+	u32 rawstat;
 
-	mutex_lock(&queue->lock);
-	old_status = atomic_xchg(&queue->status,
-				 PANFROST_QUEUE_STATUS_STARTING);
-	WARN_ON(old_status != PANFROST_QUEUE_STATUS_STOPPED);
+	if (!(js_state & *js_state_mask))
+		return 0;
 
-	/* Restore the original timeout before starting the scheduler. */
-	queue->sched.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS);
-	drm_sched_resubmit_jobs(&queue->sched);
-	drm_sched_start(&queue->sched, true);
-	old_status = atomic_xchg(&queue->status,
-				 PANFROST_QUEUE_STATUS_ACTIVE);
-	if (old_status == PANFROST_QUEUE_STATUS_FAULT_PENDING)
-		drm_sched_fault(&queue->sched);
+	rawstat = job_read(pfdev, JOB_INT_RAWSTAT);
+	if (rawstat) {
+		unsigned int i;
+
+		for (i = 0; i < NUM_JOB_SLOTS; i++) {
+			if (rawstat & MK_JS_MASK(i))
+				*js_state_mask &= ~MK_JS_MASK(i);
+		}
+	}
 
-	mutex_unlock(&queue->lock);
+	return js_state & *js_state_mask;
+}
+
+static void
+panfrost_reset(struct panfrost_device *pfdev,
+	       struct drm_sched_job *bad)
+{
+	u32 js_state, js_state_mask = 0xffffffff;
+	unsigned int i, j;
+	bool cookie;
+	int ret;
+
+	if (!atomic_read(&pfdev->reset.pending))
+		return;
+
+	/* Stop the schedulers.
+	 *
+	 * FIXME: We temporarily get out of the dma_fence_signalling section
+	 * because the cleanup path generate lockdep splats when taking locks
+	 * to release job resources. We should rework the code to follow this
+	 * pattern:
+	 *
+	 *	try_lock
+	 *	if (locked)
+	 *		release
+	 *	else
+	 *		schedule_work_to_release_later
+	 */
+	for (i = 0; i < NUM_JOB_SLOTS; i++)
+		drm_sched_stop(&pfdev->js->queue[i].sched, bad);
+
+	cookie = dma_fence_begin_signalling();
+
+	if (bad)
+		drm_sched_increase_karma(bad);
+
+	/* Mask job interrupts and synchronize to make sure we won't be
+	 * interrupted during our reset.
+	 */
+	job_write(pfdev, JOB_INT_MASK, 0);
+	synchronize_irq(pfdev->js->irq);
+
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		/* Cancel the next job and soft-stop the running job. */
+		job_write(pfdev, JS_COMMAND_NEXT(i), JS_COMMAND_NOP);
+		job_write(pfdev, JS_COMMAND(i), JS_COMMAND_SOFT_STOP);
+	}
+
+	/* Wait at most 10ms for soft-stops to complete */
+	ret = readl_poll_timeout(pfdev->iomem + JOB_INT_JS_STATE, js_state,
+				 !panfrost_active_slots(pfdev, &js_state_mask, js_state),
+				 10, 10000);
+
+	if (ret)
+		dev_err(pfdev->dev, "Soft-stop failed\n");
+
+	/* Handle the remaining interrupts before we reset. */
+	panfrost_job_handle_irqs(pfdev);
+
+	/* Remaining interrupts have been handled, but we might still have
+	 * stuck jobs. Let's make sure the PM counters stay balanced by
+	 * manually calling pm_runtime_put_noidle() and
+	 * panfrost_devfreq_record_idle() for each stuck job.
+	 */
+	spin_lock(&pfdev->js->job_lock);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) {
+			pm_runtime_put_noidle(pfdev->dev);
+			panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
+		}
+	}
+	memset(pfdev->jobs, 0, sizeof(pfdev->jobs));
+	spin_unlock(&pfdev->js->job_lock);
+
+	/* Proceed with reset now. */
+	panfrost_device_reset(pfdev);
+
+	/* panfrost_device_reset() unmasks job interrupts, but we want to
+	 * keep them masked a bit longer.
+	 */
+	job_write(pfdev, JOB_INT_MASK, 0);
+
+	/* GPU has been reset, we can clear the reset pending bit. */
+	atomic_set(&pfdev->reset.pending, 0);
+
+	/* Now resubmit jobs that were previously queued but didn't have a
+	 * chance to finish.
+	 * FIXME: We temporarily get out of the DMA fence signalling section
+	 * while resubmitting jobs because the job submission logic will
+	 * allocate memory with the GFP_KERNEL flag which can trigger memory
+	 * reclaim and exposes a lock ordering issue.
+	 */
+	dma_fence_end_signalling(cookie);
+	for (i = 0; i < NUM_JOB_SLOTS; i++)
+		drm_sched_resubmit_jobs(&pfdev->js->queue[i].sched);
+	cookie = dma_fence_begin_signalling();
+
+	/* Restart the schedulers */
+	for (i = 0; i < NUM_JOB_SLOTS; i++)
+		drm_sched_start(&pfdev->js->queue[i].sched, true);
+
+	/* Re-enable job interrupts now that everything has been restarted. */
+	job_write(pfdev, JOB_INT_MASK,
+		  GENMASK(16 + NUM_JOB_SLOTS - 1, 16) |
+		  GENMASK(NUM_JOB_SLOTS - 1, 0));
+
+	dma_fence_end_signalling(cookie);
 }
 
 static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job
@@ -454,17 +748,20 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	/* Scheduler is already stopped, nothing to do. */
-	if (!panfrost_scheduler_stop(&pfdev->js->queue[js], sched_job))
-		return DRM_GPU_SCHED_STAT_NOMINAL;
-
-	/* Schedule a reset if there's no reset in progress. */
-	if (!atomic_xchg(&pfdev->reset.pending, 1))
-		schedule_work(&pfdev->reset.work);
+	atomic_set(&pfdev->reset.pending, 1);
+	panfrost_reset(pfdev, sched_job);
 
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
+static void panfrost_reset_work(struct work_struct *work)
+{
+	struct panfrost_device *pfdev;
+
+	pfdev = container_of(work, struct panfrost_device, reset.work);
+	panfrost_reset(pfdev, NULL);
+}
+
 static const struct drm_sched_backend_ops panfrost_sched_ops = {
 	.dependency = panfrost_job_dependency,
 	.run_job = panfrost_job_run,
@@ -472,161 +769,75 @@ static const struct drm_sched_backend_ops panfrost_sched_ops = {
 	.free_job = panfrost_job_free
 };
 
-static irqreturn_t panfrost_job_irq_handler(int irq, void *data)
+static irqreturn_t panfrost_job_irq_handler_thread(int irq, void *data)
 {
 	struct panfrost_device *pfdev = data;
-	u32 status = job_read(pfdev, JOB_INT_STAT);
-	int j;
-
-	dev_dbg(pfdev->dev, "jobslot irq status=%x\n", status);
-
-	if (!status)
-		return IRQ_NONE;
-
-	pm_runtime_mark_last_busy(pfdev->dev);
-
-	for (j = 0; status; j++) {
-		u32 mask = MK_JS_MASK(j);
-
-		if (!(status & mask))
-			continue;
-
-		job_write(pfdev, JOB_INT_CLEAR, mask);
-
-		if (status & JOB_INT_MASK_ERR(j)) {
-			enum panfrost_queue_status old_status;
-
-			job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_NOP);
-
-			dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x",
-				j,
-				panfrost_exception_name(pfdev, job_read(pfdev, JS_STATUS(j))),
-				job_read(pfdev, JS_HEAD_LO(j)),
-				job_read(pfdev, JS_TAIL_LO(j)));
-
-			/*
-			 * When the queue is being restarted we don't report
-			 * faults directly to avoid races between the timeout
-			 * and reset handlers. panfrost_scheduler_start() will
-			 * call drm_sched_fault() after the queue has been
-			 * started if status == FAULT_PENDING.
-			 */
-			old_status = atomic_cmpxchg(&pfdev->js->queue[j].status,
-						    PANFROST_QUEUE_STATUS_STARTING,
-						    PANFROST_QUEUE_STATUS_FAULT_PENDING);
-			if (old_status == PANFROST_QUEUE_STATUS_ACTIVE)
-				drm_sched_fault(&pfdev->js->queue[j].sched);
-		}
-
-		if (status & JOB_INT_MASK_DONE(j)) {
-			struct panfrost_job *job;
-
-			spin_lock(&pfdev->js->job_lock);
-			job = pfdev->jobs[j];
-			/* Only NULL if job timeout occurred */
-			if (job) {
-				pfdev->jobs[j] = NULL;
-
-				panfrost_mmu_as_put(pfdev, &job->file_priv->mmu);
-				panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
-
-				dma_fence_signal_locked(job->done_fence);
-				pm_runtime_put_autosuspend(pfdev->dev);
-			}
-			spin_unlock(&pfdev->js->job_lock);
-		}
-
-		status &= ~mask;
-	}
 
+	panfrost_job_handle_irqs(pfdev);
+	job_write(pfdev, JOB_INT_MASK,
+		  GENMASK(16 + NUM_JOB_SLOTS - 1, 16) |
+		  GENMASK(NUM_JOB_SLOTS - 1, 0));
 	return IRQ_HANDLED;
 }
 
-static void panfrost_reset(struct work_struct *work)
+static irqreturn_t panfrost_job_irq_handler(int irq, void *data)
 {
-	struct panfrost_device *pfdev = container_of(work,
-						     struct panfrost_device,
-						     reset.work);
-	unsigned long flags;
-	unsigned int i;
-	bool cookie;
-
-	cookie = dma_fence_begin_signalling();
-	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		/*
-		 * We want pending timeouts to be handled before we attempt
-		 * to stop the scheduler. If we don't do that and the timeout
-		 * handler is in flight, it might have removed the bad job
-		 * from the list, and we'll lose this job if the reset handler
-		 * enters the critical section in panfrost_scheduler_stop()
-		 * before the timeout handler.
-		 *
-		 * Timeout is set to MAX_SCHEDULE_TIMEOUT - 1 because we need
-		 * something big enough to make sure the timer will not expire
-		 * before we manage to stop the scheduler, but we can't use
-		 * MAX_SCHEDULE_TIMEOUT because drm_sched_get_cleanup_job()
-		 * considers that as 'timer is not running' and will dequeue
-		 * the job without making sure the timeout handler is not
-		 * running.
-		 */
-		pfdev->js->queue[i].sched.timeout = MAX_SCHEDULE_TIMEOUT - 1;
-		cancel_delayed_work_sync(&pfdev->js->queue[i].sched.work_tdr);
-		panfrost_scheduler_stop(&pfdev->js->queue[i], NULL);
-	}
-
-	/* All timers have been stopped, we can safely reset the pending state. */
-	atomic_set(&pfdev->reset.pending, 0);
-
-	spin_lock_irqsave(&pfdev->js->job_lock, flags);
-	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		if (pfdev->jobs[i]) {
-			pm_runtime_put_noidle(pfdev->dev);
-			panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
-			pfdev->jobs[i] = NULL;
-		}
-	}
-	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
-
-	panfrost_device_reset(pfdev);
+	struct panfrost_device *pfdev = data;
+	u32 status = job_read(pfdev, JOB_INT_STAT);
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		panfrost_scheduler_start(&pfdev->js->queue[i]);
+	if (!status)
+		return IRQ_NONE;
 
-	dma_fence_end_signalling(cookie);
+	job_write(pfdev, JOB_INT_MASK, 0);
+	return IRQ_WAKE_THREAD;
 }
 
 int panfrost_job_init(struct panfrost_device *pfdev)
 {
 	struct panfrost_job_slot *js;
-	int ret, j, irq;
+	unsigned int nentries = 2;
+	int ret, j;
 
-	INIT_WORK(&pfdev->reset.work, panfrost_reset);
+	/* All GPUs have two entries per queue, but without jobchain
+	 * disambiguation stopping the right job in the close path is tricky,
+	 * so let's just advertise one entry in that case.
+	 */
+	if (!panfrost_has_hw_feature(pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION))
+		nentries = 1;
 
 	pfdev->js = js = devm_kzalloc(pfdev->dev, sizeof(*js), GFP_KERNEL);
 	if (!js)
 		return -ENOMEM;
 
+	INIT_WORK(&pfdev->reset.work, panfrost_reset_work);
 	spin_lock_init(&js->job_lock);
 
-	irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "job");
-	if (irq <= 0)
+	js->irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "job");
+	if (js->irq <= 0)
 		return -ENODEV;
 
-	ret = devm_request_irq(pfdev->dev, irq, panfrost_job_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME "-job", pfdev);
+	ret = devm_request_threaded_irq(pfdev->dev, js->irq,
+					panfrost_job_irq_handler,
+					panfrost_job_irq_handler_thread,
+					IRQF_SHARED, KBUILD_MODNAME "-job",
+					pfdev);
 	if (ret) {
 		dev_err(pfdev->dev, "failed to request job irq");
 		return ret;
 	}
 
-	for (j = 0; j < NUM_JOB_SLOTS; j++) {
-		mutex_init(&js->queue[j].lock);
+	pfdev->reset.wq = alloc_ordered_workqueue("panfrost-reset", 0);
+	if (!pfdev->reset.wq)
+		return -ENOMEM;
 
+	for (j = 0; j < NUM_JOB_SLOTS; j++) {
 		js->queue[j].fence_context = dma_fence_context_alloc(1);
 
 		ret = drm_sched_init(&js->queue[j].sched,
 				     &panfrost_sched_ops,
-				     1, 0, msecs_to_jiffies(JOB_TIMEOUT_MS),
+				     nentries, 0,
+				     msecs_to_jiffies(JOB_TIMEOUT_MS),
+				     pfdev->reset.wq,
 				     NULL, "pan_js");
 		if (ret) {
 			dev_err(pfdev->dev, "Failed to create scheduler: %d.", ret);
@@ -642,6 +853,7 @@ err_sched:
 	for (j--; j >= 0; j--)
 		drm_sched_fini(&js->queue[j].sched);
 
+	destroy_workqueue(pfdev->reset.wq);
 	return ret;
 }
 
@@ -654,9 +866,10 @@ void panfrost_job_fini(struct panfrost_device *pfdev)
 
 	for (j = 0; j < NUM_JOB_SLOTS; j++) {
 		drm_sched_fini(&js->queue[j].sched);
-		mutex_destroy(&js->queue[j].lock);
 	}
 
+	cancel_work_sync(&pfdev->reset.work);
+	destroy_workqueue(pfdev->reset.wq);
 }
 
 int panfrost_job_open(struct panfrost_file_priv *panfrost_priv)
@@ -679,10 +892,46 @@ int panfrost_job_open(struct panfrost_file_priv *panfrost_priv)
 
 void panfrost_job_close(struct panfrost_file_priv *panfrost_priv)
 {
+	struct panfrost_device *pfdev = panfrost_priv->pfdev;
 	int i;
 
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
 		drm_sched_entity_destroy(&panfrost_priv->sched_entity[i]);
+
+	/* Kill in-flight jobs */
+	spin_lock(&pfdev->js->job_lock);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_sched_entity *entity = &panfrost_priv->sched_entity[i];
+		int j;
+
+		for (j = ARRAY_SIZE(pfdev->jobs[0]) - 1; j >= 0; j--) {
+			struct panfrost_job *job = pfdev->jobs[i][j];
+			u32 cmd;
+
+			if (!job || job->base.entity != entity)
+				continue;
+
+			if (j == 1) {
+				/* Try to cancel the job before it starts */
+				job_write(pfdev, JS_COMMAND_NEXT(i), JS_COMMAND_NOP);
+				/* Reset the job head so it doesn't get restarted if
+				 * the job in the first slot failed.
+				 */
+				job->jc = 0;
+			}
+
+			if (panfrost_has_hw_feature(pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION)) {
+				cmd = panfrost_get_job_chain_flag(job) ?
+				      JS_COMMAND_HARD_STOP_1 :
+				      JS_COMMAND_HARD_STOP_0;
+			} else {
+				cmd = JS_COMMAND_HARD_STOP;
+			}
+
+			job_write(pfdev, JS_COMMAND(i), cmd);
+		}
+	}
+	spin_unlock(&pfdev->js->job_lock);
 }
 
 int panfrost_job_is_idle(struct panfrost_device *pfdev)
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h
index bbd3ba97ff67..82306a03b57e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.h
+++ b/drivers/gpu/drm/panfrost/panfrost_job.h
@@ -19,9 +19,9 @@ struct panfrost_job {
 	struct panfrost_device *pfdev;
 	struct panfrost_file_priv *file_priv;
 
-	/* Optional fences userspace can pass in for the job to depend on. */
-	struct dma_fence **in_fences;
-	u32 in_fence_count;
+	/* Contains both explicit and implicit fences */
+	struct xarray deps;
+	unsigned long last_dep;
 
 	/* Fence to be signaled by IRQ handler when the job is complete. */
 	struct dma_fence *done_fence;
@@ -30,8 +30,6 @@ struct panfrost_job {
 	__u32 requirements;
 	__u32 flush_id;
 
-	/* Exclusive fences we have taken from the BOs to wait for */
-	struct dma_fence **implicit_fences;
 	struct panfrost_gem_mapping **mappings;
 	struct drm_gem_object **bos;
 	u32 bo_count;
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 0581186ebfb3..0da5b3100ab1 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier:	GPL-2.0
 /* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+
+#include <drm/panfrost_drm.h>
+
 #include <linux/atomic.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
@@ -31,10 +34,13 @@ static int wait_ready(struct panfrost_device *pfdev, u32 as_nr)
 	/* Wait for the MMU status to indicate there is no active command, in
 	 * case one is pending. */
 	ret = readl_relaxed_poll_timeout_atomic(pfdev->iomem + AS_STATUS(as_nr),
-		val, !(val & AS_STATUS_AS_ACTIVE), 10, 1000);
+		val, !(val & AS_STATUS_AS_ACTIVE), 10, 100000);
 
-	if (ret)
+	if (ret) {
+		/* The GPU hung, let's trigger a reset */
+		panfrost_device_schedule_reset(pfdev);
 		dev_err(pfdev->dev, "AS_ACTIVE bit stuck\n");
+	}
 
 	return ret;
 }
@@ -151,6 +157,7 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
+		u32 mask = BIT(as) | BIT(16 + as);
 
 		/*
 		 * AS can be retained by active jobs or a perfcnt context,
@@ -159,6 +166,18 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
 		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
+
+		if (pfdev->as_faulty_mask & mask) {
+			/* Unhandled pagefault on this AS, the MMU was
+			 * disabled. We need to re-enable the MMU after
+			 * clearing+unmasking the AS interrupts.
+			 */
+			mmu_write(pfdev, MMU_INT_CLEAR, mask);
+			mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
+			pfdev->as_faulty_mask &= ~mask;
+			panfrost_mmu_enable(pfdev, mmu);
+		}
+
 		goto out;
 	}
 
@@ -208,6 +227,7 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev)
 	spin_lock(&pfdev->as_lock);
 
 	pfdev->as_alloc_mask = 0;
+	pfdev->as_faulty_mask = 0;
 
 	list_for_each_entry_safe(mmu, mmu_tmp, &pfdev->as_lru_list, list) {
 		mmu->as = -1;
@@ -337,7 +357,7 @@ static void mmu_tlb_inv_context_s1(void *cookie)
 
 static void mmu_tlb_sync_context(void *cookie)
 {
-	//struct panfrost_device *pfdev = cookie;
+	//struct panfrost_mmu *mmu = cookie;
 	// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
 }
 
@@ -352,57 +372,10 @@ static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_walk = mmu_tlb_flush_walk,
 };
 
-int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
-{
-	struct panfrost_mmu *mmu = &priv->mmu;
-	struct panfrost_device *pfdev = priv->pfdev;
-
-	INIT_LIST_HEAD(&mmu->list);
-	mmu->as = -1;
-
-	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= SZ_4K | SZ_2M,
-		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
-		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
-		.coherent_walk	= pfdev->coherent,
-		.tlb		= &mmu_tlb_ops,
-		.iommu_dev	= pfdev->dev,
-	};
-
-	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
-					      priv);
-	if (!mmu->pgtbl_ops)
-		return -EINVAL;
-
-	return 0;
-}
-
-void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
-{
-	struct panfrost_device *pfdev = priv->pfdev;
-	struct panfrost_mmu *mmu = &priv->mmu;
-
-	spin_lock(&pfdev->as_lock);
-	if (mmu->as >= 0) {
-		pm_runtime_get_noresume(pfdev->dev);
-		if (pm_runtime_active(pfdev->dev))
-			panfrost_mmu_disable(pfdev, mmu->as);
-		pm_runtime_put_autosuspend(pfdev->dev);
-
-		clear_bit(mmu->as, &pfdev->as_alloc_mask);
-		clear_bit(mmu->as, &pfdev->as_in_use_mask);
-		list_del(&mmu->list);
-	}
-	spin_unlock(&pfdev->as_lock);
-
-	free_io_pgtable_ops(mmu->pgtbl_ops);
-}
-
 static struct panfrost_gem_mapping *
 addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 {
 	struct panfrost_gem_mapping *mapping = NULL;
-	struct panfrost_file_priv *priv;
 	struct drm_mm_node *node;
 	u64 offset = addr >> PAGE_SHIFT;
 	struct panfrost_mmu *mmu;
@@ -415,11 +388,10 @@ addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 	goto out;
 
 found_mmu:
-	priv = container_of(mmu, struct panfrost_file_priv, mmu);
 
-	spin_lock(&priv->mm_lock);
+	spin_lock(&mmu->mm_lock);
 
-	drm_mm_for_each_node(node, &priv->mm) {
+	drm_mm_for_each_node(node, &mmu->mm) {
 		if (offset >= node->start &&
 		    offset < (node->start + node->size)) {
 			mapping = drm_mm_node_to_panfrost_mapping(node);
@@ -429,7 +401,7 @@ found_mmu:
 		}
 	}
 
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mmu->mm_lock);
 out:
 	spin_unlock(&pfdev->as_lock);
 	return mapping;
@@ -542,6 +514,107 @@ err_bo:
 	return ret;
 }
 
+static void panfrost_mmu_release_ctx(struct kref *kref)
+{
+	struct panfrost_mmu *mmu = container_of(kref, struct panfrost_mmu,
+						refcount);
+	struct panfrost_device *pfdev = mmu->pfdev;
+
+	spin_lock(&pfdev->as_lock);
+	if (mmu->as >= 0) {
+		pm_runtime_get_noresume(pfdev->dev);
+		if (pm_runtime_active(pfdev->dev))
+			panfrost_mmu_disable(pfdev, mmu->as);
+		pm_runtime_put_autosuspend(pfdev->dev);
+
+		clear_bit(mmu->as, &pfdev->as_alloc_mask);
+		clear_bit(mmu->as, &pfdev->as_in_use_mask);
+		list_del(&mmu->list);
+	}
+	spin_unlock(&pfdev->as_lock);
+
+	free_io_pgtable_ops(mmu->pgtbl_ops);
+	drm_mm_takedown(&mmu->mm);
+	kfree(mmu);
+}
+
+void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu)
+{
+	kref_put(&mmu->refcount, panfrost_mmu_release_ctx);
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu)
+{
+	kref_get(&mmu->refcount);
+
+	return mmu;
+}
+
+#define PFN_4G		(SZ_4G >> PAGE_SHIFT)
+#define PFN_4G_MASK	(PFN_4G - 1)
+#define PFN_16M		(SZ_16M >> PAGE_SHIFT)
+
+static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node,
+					 unsigned long color,
+					 u64 *start, u64 *end)
+{
+	/* Executable buffers can't start or end on a 4GB boundary */
+	if (!(color & PANFROST_BO_NOEXEC)) {
+		u64 next_seg;
+
+		if ((*start & PFN_4G_MASK) == 0)
+			(*start)++;
+
+		if ((*end & PFN_4G_MASK) == 0)
+			(*end)--;
+
+		next_seg = ALIGN(*start, PFN_4G);
+		if (next_seg - *start <= PFN_16M)
+			*start = next_seg + 1;
+
+		*end = min(*end, ALIGN(*start, PFN_4G) - 1);
+	}
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev)
+{
+	struct panfrost_mmu *mmu;
+
+	mmu = kzalloc(sizeof(*mmu), GFP_KERNEL);
+	if (!mmu)
+		return ERR_PTR(-ENOMEM);
+
+	mmu->pfdev = pfdev;
+	spin_lock_init(&mmu->mm_lock);
+
+	/* 4G enough for now. can be 48-bit */
+	drm_mm_init(&mmu->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT);
+	mmu->mm.color_adjust = panfrost_drm_mm_color_adjust;
+
+	INIT_LIST_HEAD(&mmu->list);
+	mmu->as = -1;
+
+	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= SZ_4K | SZ_2M,
+		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
+		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
+		.coherent_walk	= pfdev->coherent,
+		.tlb		= &mmu_tlb_ops,
+		.iommu_dev	= pfdev->dev,
+	};
+
+	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
+					      mmu);
+	if (!mmu->pgtbl_ops) {
+		kfree(mmu);
+		return ERR_PTR(-EINVAL);
+	}
+
+	kref_init(&mmu->refcount);
+
+	return mmu;
+}
+
 static const char *access_type_name(struct panfrost_device *pfdev,
 		u32 fault_status)
 {
@@ -605,7 +678,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
 		if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0)
 			ret = panfrost_mmu_map_fault_addr(pfdev, as, addr);
 
-		if (ret)
+		if (ret) {
 			/* terminal fault, print info about the fault */
 			dev_err(pfdev->dev,
 				"Unhandled Page fault in AS%d at VA 0x%016llX\n"
@@ -619,18 +692,32 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
 				"TODO",
 				fault_status,
 				(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
-				exception_type, panfrost_exception_name(pfdev, exception_type),
+				exception_type, panfrost_exception_name(exception_type),
 				access_type, access_type_name(pfdev, fault_status),
 				source_id);
 
+			spin_lock(&pfdev->as_lock);
+			/* Ignore MMU interrupts on this AS until it's been
+			 * re-enabled.
+			 */
+			pfdev->as_faulty_mask |= mask;
+
+			/* Disable the MMU to kill jobs on this AS. */
+			panfrost_mmu_disable(pfdev, as);
+			spin_unlock(&pfdev->as_lock);
+		}
+
 		status &= ~mask;
 
 		/* If we received new MMU interrupts, process them before returning. */
 		if (!status)
-			status = mmu_read(pfdev, MMU_INT_RAWSTAT);
+			status = mmu_read(pfdev, MMU_INT_RAWSTAT) & ~pfdev->as_faulty_mask;
 	}
 
-	mmu_write(pfdev, MMU_INT_MASK, ~0);
+	spin_lock(&pfdev->as_lock);
+	mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
+	spin_unlock(&pfdev->as_lock);
+
 	return IRQ_HANDLED;
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h
index 44fc2edf63ce..cc2a0d307feb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h
@@ -18,7 +18,8 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev);
 u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu);
 void panfrost_mmu_as_put(struct panfrost_device *pfdev, struct panfrost_mmu *mmu);
 
-int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv);
-void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv);
+struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu);
+void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu);
+struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev);
 
 #endif
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index dc9df5457f1c..1940ff86e49a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -262,9 +262,6 @@
 #define JS_COMMAND_SOFT_STOP_1		0x06	/* Execute SOFT_STOP if JOB_CHAIN_FLAG is 1 */
 #define JS_COMMAND_HARD_STOP_1		0x07	/* Execute HARD_STOP if JOB_CHAIN_FLAG is 1 */
 
-#define JS_STATUS_EVENT_ACTIVE		0x08
-
-
 /* MMU regs */
 #define MMU_INT_RAWSTAT			0x2000
 #define MMU_INT_CLEAR			0x2004
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 6fd7f13f1aca..443e3b932322 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -11,7 +11,6 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/version.h>
 #include <linux/dma-buf.h>
 #include <linux/of_graph.h>
 
@@ -440,7 +439,6 @@ static struct drm_simple_display_pipe_funcs pl111_display_funcs = {
 	.enable = pl111_display_enable,
 	.disable = pl111_display_disable,
 	.update = pl111_display_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index fa0a737e9dea..520301b405f1 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -44,7 +44,6 @@
 #include <linux/of_reserved_mem.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
-#include <linux/version.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 854e6c5a563f..fc47b0deb021 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -95,7 +95,7 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "qxl");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &qxl_driver);
 	if (ret)
 		goto disable_pci;
 
@@ -281,10 +281,8 @@ static struct drm_driver qxl_driver = {
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
-	.gem_prime_mmap = qxl_gem_prime_mmap,
 	.fops = &qxl_fops,
 	.ioctls = qxl_ioctls,
-	.irq_handler = qxl_irq_handler,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
 	.date = DRIVER_DATE,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index dd6abee55f56..359266d9e860 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -434,12 +434,9 @@ struct drm_gem_object *qxl_gem_prime_import_sg_table(
 int qxl_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map);
 void qxl_gem_prime_vunmap(struct drm_gem_object *obj,
 			  struct dma_buf_map *map);
-int qxl_gem_prime_mmap(struct drm_gem_object *obj,
-				struct vm_area_struct *vma);
 
 /* qxl_irq.c */
 int qxl_irq_init(struct qxl_device *qdev);
-irqreturn_t qxl_irq_handler(int irq, void *arg);
 
 void qxl_debugfs_add_files(struct qxl_device *qdev,
 			   struct drm_info_list *files,
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index d312322cacd1..665278ee3b6d 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -25,11 +25,11 @@
 
 #include <linux/pci.h>
 
-#include <drm/drm_irq.h>
+#include <drm/drm_drv.h>
 
 #include "qxl_drv.h"
 
-irqreturn_t qxl_irq_handler(int irq, void *arg)
+static irqreturn_t qxl_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct qxl_device *qdev = to_qxl(dev);
@@ -81,7 +81,8 @@ static void qxl_client_monitors_config_work_func(struct work_struct *work)
 
 int qxl_irq_init(struct qxl_device *qdev)
 {
-	struct pci_dev *pdev = to_pci_dev(qdev->ddev.dev);
+	struct drm_device *ddev = &qdev->ddev;
+	struct pci_dev *pdev = to_pci_dev(ddev->dev);
 	int ret;
 
 	init_waitqueue_head(&qdev->display_event);
@@ -95,7 +96,7 @@ int qxl_irq_init(struct qxl_device *qdev)
 	atomic_set(&qdev->irq_received_cursor, 0);
 	atomic_set(&qdev->irq_received_io_cmd, 0);
 	qdev->irq_received_error = 0;
-	ret = drm_irq_install(&qdev->ddev, pdev->irq);
+	ret = request_irq(pdev->irq, qxl_irq_handler, IRQF_SHARED, ddev->driver->name, ddev);
 	qdev->ram_header->int_mask = QXL_INTERRUPT_MASK;
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Failed installing irq: %d\n", ret);
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 0628d1cc91fe..4a10cb0a413b 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -73,9 +73,3 @@ void qxl_gem_prime_vunmap(struct drm_gem_object *obj,
 
 	qxl_bo_vunmap(bo);
 }
-
-int qxl_gem_prime_mmap(struct drm_gem_object *obj,
-		       struct vm_area_struct *area)
-{
-	return -ENOSYS;
-}
diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c
index 2a2933c16308..c04d84a69dd2 100644
--- a/drivers/gpu/drm/r128/r128_cce.c
+++ b/drivers/gpu/drm/r128/r128_cce.c
@@ -39,7 +39,6 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_legacy.h>
 #include <drm/drm_print.h>
 #include <drm/r128_drm.h>
@@ -603,7 +602,7 @@ int r128_do_cleanup_cce(struct drm_device *dev)
 	 * is freed, it's too late.
 	 */
 	if (dev->irq_enabled)
-		drm_irq_uninstall(dev);
+		drm_legacy_irq_uninstall(dev);
 
 	if (dev->dev_private) {
 		drm_r128_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 4b86e8b45009..83e8b8547f9b 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -2802,8 +2802,8 @@ ucMaxNBVoltageHigh:     Voltage regulator dependent PWM value. High 8 bits of  t
 ucMinNBVoltageHigh:     Voltage regulator dependent PWM value. High 8 bits of the value for the min voltage.Set this one to 0x00 if VC without PWM or no VC at all.
 
 
-usInterNBVoltageLow:    Voltage regulator dependent PWM value. The value makes the the voltage >=Min NB voltage but <=InterNBVoltageHigh. Set this to 0x0000 if VC without PWM or no VC at all.
-usInterNBVoltageHigh:   Voltage regulator dependent PWM value. The value makes the the voltage >=InterNBVoltageLow but <=Max NB voltage.Set this to 0x0000 if VC without PWM or no VC at all.
+usInterNBVoltageLow:    Voltage regulator dependent PWM value. The value makes the voltage >=Min NB voltage but <=InterNBVoltageHigh. Set this to 0x0000 if VC without PWM or no VC at all.
+usInterNBVoltageHigh:   Voltage regulator dependent PWM value. The value makes the voltage >=InterNBVoltageLow but <=Max NB voltage.Set this to 0x0000 if VC without PWM or no VC at all.
 */
 
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 36a888e1b179..eeb590d2dec2 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -28,6 +28,7 @@
 
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "avivod.h"
@@ -1414,10 +1415,15 @@ void evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base,
 			 bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(EVERGREEN_GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? EVERGREEN_GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(EVERGREEN_GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ba724198b72e..2dd85ba1faa2 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -162,6 +162,8 @@ void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
 void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	uint32_t crtc_pitch, pitch_pixels;
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
 	int i;
 
@@ -169,6 +171,13 @@ void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool
 	/* update the scanout addresses */
 	WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
 
+	/* update pitch */
+	pitch_pixels = fb->pitches[0] / fb->format->cpp[0];
+	crtc_pitch = DIV_ROUND_UP(pitch_pixels * fb->format->cpp[0] * 8,
+				  fb->format->cpp[0] * 8 * 8);
+	crtc_pitch |= crtc_pitch << 16;
+	WREG32(RADEON_CRTC_PITCH + radeon_crtc->crtc_offset, crtc_pitch);
+
 	/* Wait for update_pending to go high. */
 	for (i = 0; i < rdev->usec_timeout; i++) {
 		if (RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET)
diff --git a/drivers/gpu/drm/radeon/r300_reg.h b/drivers/gpu/drm/radeon/r300_reg.h
index 00c0d2ba22d3..60d5413bafa1 100644
--- a/drivers/gpu/drm/radeon/r300_reg.h
+++ b/drivers/gpu/drm/radeon/r300_reg.h
@@ -353,7 +353,7 @@
 #       define R300_PVS_CNTL_1_PROGRAM_START_SHIFT   0
 #       define R300_PVS_CNTL_1_POS_END_SHIFT         10
 #       define R300_PVS_CNTL_1_PROGRAM_END_SHIFT     20
-/* Addresses are relative the the vertex program parameters area. */
+/* Addresses are relative the vertex program parameters area. */
 #define R300_VAP_PVS_CNTL_2                 0x22D4
 #       define R300_PVS_CNTL_2_PARAM_OFFSET_SHIFT 0
 #       define R300_PVS_CNTL_2_PARAM_COUNT_SHIFT  16
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 46eea01950cb..4f0fbf667431 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -406,7 +406,7 @@ void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell)
 
 /*
  * radeon_wb_*()
- * Writeback is the the method by which the the GPU updates special pages
+ * Writeback is the method by which the GPU updates special pages
  * in memory with the status of certain GPU events (fences, ring pointers,
  * etc.).
  */
@@ -785,7 +785,7 @@ int radeon_dummy_page_init(struct radeon_device *rdev)
 	if (rdev->dummy_page.page == NULL)
 		return -ENOMEM;
 	rdev->dummy_page.addr = dma_map_page(&rdev->pdev->dev, rdev->dummy_page.page,
-					0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+					0, PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(&rdev->pdev->dev, rdev->dummy_page.addr)) {
 		dev_err(&rdev->pdev->dev, "Failed to DMA MAP the dummy page\n");
 		__free_page(rdev->dummy_page.page);
@@ -808,8 +808,8 @@ void radeon_dummy_page_fini(struct radeon_device *rdev)
 {
 	if (rdev->dummy_page.page == NULL)
 		return;
-	pci_unmap_page(rdev->pdev, rdev->dummy_page.addr,
-			PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_page(&rdev->pdev->dev, rdev->dummy_page.addr, PAGE_SIZE,
+		       DMA_BIDIRECTIONAL);
 	__free_page(rdev->dummy_page.page);
 	rdev->dummy_page.page = NULL;
 }
@@ -1067,15 +1067,16 @@ void radeon_combios_fini(struct radeon_device *rdev)
 /**
  * radeon_vga_set_decode - enable/disable vga decode
  *
- * @cookie: radeon_device pointer
+ * @pdev: PCI device
  * @state: enable/disable vga decode
  *
  * Enable/disable vga decode (all asics).
  * Returns VGA resource flags.
  */
-static unsigned int radeon_vga_set_decode(void *cookie, bool state)
+static unsigned int radeon_vga_set_decode(struct pci_dev *pdev, bool state)
 {
-	struct radeon_device *rdev = cookie;
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct radeon_device *rdev = dev->dev_private;
 	radeon_vga_set_state(rdev, state);
 	if (state)
 		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
@@ -1434,7 +1435,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* if we have > 1 VGA cards, then disable the radeon VGA resources */
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
-	vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode);
+	vga_client_register(rdev->pdev, radeon_vga_set_decode);
 
 	if (rdev->flags & RADEON_IS_PX)
 		runtime = true;
@@ -1530,7 +1531,7 @@ void radeon_device_fini(struct radeon_device *rdev)
 		vga_switcheroo_unregister_client(rdev->pdev);
 	if (rdev->flags & RADEON_IS_PX)
 		vga_switcheroo_fini_domain_pm_ops(rdev->dev);
-	vga_client_register(rdev->pdev, NULL, NULL, NULL);
+	vga_client_unregister(rdev->pdev);
 	if (rdev->rio_mem)
 		pci_iounmap(rdev->pdev, rdev->rio_mem);
 	rdev->rio_mem = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 5c23b77cb81a..b74cebca1f89 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -330,7 +330,7 @@ static int radeon_pci_probe(struct pci_dev *pdev,
 		return -EPROBE_DEFER;
 
 	/* Get rid of things like offb */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "radeondrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &kms_driver);
 	if (ret)
 		return ret;
 
@@ -607,10 +607,6 @@ static const struct drm_driver kms_driver = {
 	.postclose = radeon_driver_postclose_kms,
 	.lastclose = radeon_driver_lastclose_kms,
 	.unload = radeon_driver_unload_kms,
-	.irq_preinstall = radeon_driver_irq_preinstall_kms,
-	.irq_postinstall = radeon_driver_irq_postinstall_kms,
-	.irq_uninstall = radeon_driver_irq_uninstall_kms,
-	.irq_handler = radeon_driver_irq_handler_kms,
 	.ioctls = radeon_ioctls_kms,
 	.num_ioctls = ARRAY_SIZE(radeon_ioctls_kms),
 	.dumb_create = radeon_mode_dumb_create,
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 0b206b052972..ca382fbf7a86 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -54,6 +54,7 @@ radeonfb_open(struct fb_info *info, int user)
 	struct radeon_fbdev *rfbdev = info->par;
 	struct radeon_device *rdev = rfbdev->rdev;
 	int ret = pm_runtime_get_sync(rdev->ddev->dev);
+
 	if (ret < 0 && ret != -EACCES) {
 		pm_runtime_mark_last_busy(rdev->ddev->dev);
 		pm_runtime_put_autosuspend(rdev->ddev->dev);
@@ -167,6 +168,7 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
 		break;
 	case 2:
 		tiling_flags |= RADEON_TILING_SWAP_16BIT;
+		break;
 	default:
 		break;
 	}
@@ -196,9 +198,8 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
 		radeon_bo_check_tiling(rbo, 0, 0);
 	ret = radeon_bo_kmap(rbo, NULL);
 	radeon_bo_unreserve(rbo);
-	if (ret) {
+	if (ret)
 		goto out_unref;
-	}
 
 	*gobj_p = gobj;
 	return 0;
@@ -294,9 +295,6 @@ static int radeonfb_create(struct drm_fb_helper *helper,
 	return 0;
 
 out:
-	if (rbo) {
-
-	}
 	if (fb && ret) {
 		drm_gem_object_put(gobj);
 		drm_framebuffer_unregister_private(fb);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index b2ce642ca4fa..e9c47ec28ade 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -50,7 +50,7 @@
  * for GPU/CPU synchronization.  When the fence is written,
  * it is expected that all buffers associated with that fence
  * are no longer in use by the associated ring on the GPU and
- * that the the relevant GPU caches have been flushed.  Whether
+ * that the relevant GPU caches have been flushed.  Whether
  * we use a scratch register or memory location depends on the asic
  * and whether writeback is enabled.
  */
@@ -288,7 +288,7 @@ static void radeon_fence_check_lockup(struct work_struct *work)
 		return;
 	}
 
-	if (fence_drv->delayed_irq && rdev->ddev->irq_enabled) {
+	if (fence_drv->delayed_irq && rdev->irq.installed) {
 		unsigned long irqflags;
 
 		fence_drv->delayed_irq = false;
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 84d0b1a3355f..3907785d0798 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -31,7 +31,7 @@
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_device.h>
-#include <drm/drm_irq.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
@@ -51,7 +51,7 @@
  * radeon_irq_process is a macro that points to the per-asic
  * irq handler callback.
  */
-irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
+static irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct radeon_device *rdev = dev->dev_private;
@@ -118,7 +118,7 @@ static void radeon_dp_work_func(struct work_struct *work)
  * Gets the hw ready to enable irqs (all asics).
  * This function disables all interrupt sources on the GPU.
  */
-void radeon_driver_irq_preinstall_kms(struct drm_device *dev)
+static void radeon_driver_irq_preinstall_kms(struct drm_device *dev)
 {
 	struct radeon_device *rdev = dev->dev_private;
 	unsigned long irqflags;
@@ -150,7 +150,7 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev)
  * Handles stuff to be done after enabling irqs (all asics).
  * Returns 0 on success.
  */
-int radeon_driver_irq_postinstall_kms(struct drm_device *dev)
+static int radeon_driver_irq_postinstall_kms(struct drm_device *dev)
 {
 	struct radeon_device *rdev = dev->dev_private;
 
@@ -169,7 +169,7 @@ int radeon_driver_irq_postinstall_kms(struct drm_device *dev)
  *
  * This function disables all interrupt sources on the GPU (all asics).
  */
-void radeon_driver_irq_uninstall_kms(struct drm_device *dev)
+static void radeon_driver_irq_uninstall_kms(struct drm_device *dev)
 {
 	struct radeon_device *rdev = dev->dev_private;
 	unsigned long irqflags;
@@ -194,6 +194,36 @@ void radeon_driver_irq_uninstall_kms(struct drm_device *dev)
 	spin_unlock_irqrestore(&rdev->irq.lock, irqflags);
 }
 
+static int radeon_irq_install(struct radeon_device *rdev, int irq)
+{
+	struct drm_device *dev = rdev->ddev;
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	radeon_driver_irq_preinstall_kms(dev);
+
+	/* PCI devices require shared interrupts. */
+	ret = request_irq(irq, radeon_driver_irq_handler_kms,
+			  IRQF_SHARED, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	radeon_driver_irq_postinstall_kms(dev);
+
+	return 0;
+}
+
+static void radeon_irq_uninstall(struct radeon_device *rdev)
+{
+	struct drm_device *dev = rdev->ddev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	radeon_driver_irq_uninstall_kms(dev);
+	free_irq(pdev->irq, dev);
+}
+
 /**
  * radeon_msi_ok - asic specific msi checks
  *
@@ -314,7 +344,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
 
 	rdev->irq.installed = true;
-	r = drm_irq_install(rdev->ddev, rdev->pdev->irq);
+	r = radeon_irq_install(rdev, rdev->pdev->irq);
 	if (r) {
 		rdev->irq.installed = false;
 		flush_delayed_work(&rdev->hotplug_work);
@@ -335,7 +365,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 void radeon_irq_kms_fini(struct radeon_device *rdev)
 {
 	if (rdev->irq.installed) {
-		drm_irq_uninstall(rdev->ddev);
+		radeon_irq_uninstall(rdev);
 		rdev->irq.installed = false;
 		if (rdev->msi_enabled)
 			pci_disable_msi(rdev->pdev);
@@ -357,7 +387,7 @@ void radeon_irq_kms_sw_irq_get(struct radeon_device *rdev, int ring)
 {
 	unsigned long irqflags;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	if (atomic_inc_return(&rdev->irq.ring_int[ring]) == 1) {
@@ -396,7 +426,7 @@ void radeon_irq_kms_sw_irq_put(struct radeon_device *rdev, int ring)
 {
 	unsigned long irqflags;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	if (atomic_dec_and_test(&rdev->irq.ring_int[ring])) {
@@ -422,7 +452,7 @@ void radeon_irq_kms_pflip_irq_get(struct radeon_device *rdev, int crtc)
 	if (crtc < 0 || crtc >= rdev->num_crtc)
 		return;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	if (atomic_inc_return(&rdev->irq.pflip[crtc]) == 1) {
@@ -448,7 +478,7 @@ void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc)
 	if (crtc < 0 || crtc >= rdev->num_crtc)
 		return;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	if (atomic_dec_and_test(&rdev->irq.pflip[crtc])) {
@@ -470,7 +500,7 @@ void radeon_irq_kms_enable_afmt(struct radeon_device *rdev, int block)
 {
 	unsigned long irqflags;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	spin_lock_irqsave(&rdev->irq.lock, irqflags);
@@ -492,7 +522,7 @@ void radeon_irq_kms_disable_afmt(struct radeon_device *rdev, int block)
 {
 	unsigned long irqflags;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	spin_lock_irqsave(&rdev->irq.lock, irqflags);
@@ -514,7 +544,7 @@ void radeon_irq_kms_enable_hpd(struct radeon_device *rdev, unsigned hpd_mask)
 	unsigned long irqflags;
 	int i;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	spin_lock_irqsave(&rdev->irq.lock, irqflags);
@@ -537,7 +567,7 @@ void radeon_irq_kms_disable_hpd(struct radeon_device *rdev, unsigned hpd_mask)
 	unsigned long irqflags;
 	int i;
 
-	if (!rdev->ddev->irq_enabled)
+	if (!rdev->irq.installed)
 		return;
 
 	spin_lock_irqsave(&rdev->irq.lock, irqflags);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.h b/drivers/gpu/drm/radeon/radeon_kms.h
index 9b97bf38acd4..36e73cea9215 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.h
+++ b/drivers/gpu/drm/radeon/radeon_kms.h
@@ -31,9 +31,5 @@
 u32 radeon_get_vblank_counter_kms(struct drm_crtc *crtc);
 int radeon_enable_vblank_kms(struct drm_crtc *crtc);
 void radeon_disable_vblank_kms(struct drm_crtc *crtc);
-irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg);
-void radeon_driver_irq_preinstall_kms(struct drm_device *dev);
-int radeon_driver_irq_postinstall_kms(struct drm_device *dev);
-void radeon_driver_irq_uninstall_kms(struct drm_device *dev);
 
 #endif				/* __RADEON_KMS_H__ */
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 36a38adaaea9..bb53016f3138 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -41,7 +41,7 @@
  * (uncached system pages).
  * Each VM has an ID associated with it and there is a page table
  * associated with each VMID.  When execting a command buffer,
- * the kernel tells the the ring what VMID to use for that command
+ * the kernel tells the ring what VMID to use for that command
  * buffer.  VMIDs are allocated dynamically as commands are submitted.
  * The userspace drivers maintain their own address space and the kernel
  * sets up their pages tables accordingly when they submit their
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index b2d22e25eee1..b87dd551e939 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -41,6 +41,7 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "radeon.h"
@@ -118,6 +119,7 @@ void avivo_wait_for_vblank(struct radeon_device *rdev, int crtc)
 void rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
 	int i;
 
@@ -125,9 +127,13 @@ void rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, boo
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(AVIVO_D1GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	WREG32(AVIVO_D1GRPH_SECONDARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
 	       (u32)crtc_base);
 	WREG32(AVIVO_D1GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 74499307285b..e592e57be1bb 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -32,6 +32,7 @@
 
 #include <drm/drm_device.h>
 #include <drm/radeon_drm.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "avivod.h"
@@ -809,6 +810,7 @@ u32 rv770_get_xclk(struct radeon_device *rdev)
 void rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
 	int i;
 
@@ -816,9 +818,13 @@ void rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, boo
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(AVIVO_D1GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	if (radeon_crtc->crtc_id) {
 		WREG32(D2GRPH_SECONDARY_SURFACE_ADDRESS_HIGH, upper_32_bits(crtc_base));
 		WREG32(D2GRPH_PRIMARY_SURFACE_ADDRESS_HIGH, upper_32_bits(crtc_base));
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index bfbff90588cb..4ac26d08ebb4 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -553,14 +553,20 @@ static int rcar_du_remove(struct platform_device *pdev)
 	struct drm_device *ddev = &rcdu->ddev;
 
 	drm_dev_unregister(ddev);
+	drm_atomic_helper_shutdown(ddev);
 
 	drm_kms_helper_poll_fini(ddev);
 
-	drm_dev_put(ddev);
-
 	return 0;
 }
 
+static void rcar_du_shutdown(struct platform_device *pdev)
+{
+	struct rcar_du_device *rcdu = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(&rcdu->ddev);
+}
+
 static int rcar_du_probe(struct platform_device *pdev)
 {
 	struct rcar_du_device *rcdu;
@@ -593,8 +599,6 @@ static int rcar_du_probe(struct platform_device *pdev)
 		goto error;
 	}
 
-	rcdu->ddev.irq_enabled = 1;
-
 	/*
 	 * Register the DRM device with the core and the connectors with
 	 * sysfs.
@@ -617,6 +621,7 @@ error:
 static struct platform_driver rcar_du_platform_driver = {
 	.probe		= rcar_du_probe,
 	.remove		= rcar_du_remove,
+	.shutdown	= rcar_du_shutdown,
 	.driver		= {
 		.name	= "rcar-du",
 		.pm	= &rcar_du_pm_ops,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
index ca3761772211..0daa8bba50f5 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 #include <drm/drm_bridge.h>
+#include <drm/drm_bridge_connector.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_modeset_helper_vtables.h>
@@ -53,7 +54,9 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			 struct device_node *enc_node)
 {
 	struct rcar_du_encoder *renc;
+	struct drm_connector *connector;
 	struct drm_bridge *bridge;
+	int ret;
 
 	/*
 	 * Locate the DRM bridge from the DT node. For the DPAD outputs, if the
@@ -103,9 +106,22 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 
 	renc->output = output;
 
-	/*
-	 * Attach the bridge to the encoder. The bridge will create the
-	 * connector.
-	 */
-	return drm_bridge_attach(&renc->base, bridge, NULL, 0);
+	/* Attach the bridge to the encoder. */
+	ret = drm_bridge_attach(&renc->base, bridge, NULL,
+				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+	if (ret) {
+		dev_err(rcdu->dev, "failed to attach bridge for output %u\n",
+			output);
+		return ret;
+	}
+
+	/* Create the connector for the chain of bridges. */
+	connector = drm_bridge_connector_init(&rcdu->ddev, &renc->base);
+	if (IS_ERR(connector)) {
+		dev_err(rcdu->dev,
+			"failed to created connector for output %u\n", output);
+		return PTR_ERR(connector);
+	}
+
+	return drm_connector_attach_encoder(connector, &renc->base);
 }
diff --git a/drivers/gpu/drm/rcar-du/rcar_dw_hdmi.c b/drivers/gpu/drm/rcar-du/rcar_dw_hdmi.c
index 7b8ec8310699..18ed14911b98 100644
--- a/drivers/gpu/drm/rcar-du/rcar_dw_hdmi.c
+++ b/drivers/gpu/drm/rcar-du/rcar_dw_hdmi.c
@@ -75,6 +75,7 @@ static int rcar_hdmi_phy_configure(struct dw_hdmi *hdmi, void *data,
 }
 
 static const struct dw_hdmi_plat_data rcar_dw_hdmi_plat_data = {
+	.output_port = 1,
 	.mode_valid = rcar_hdmi_mode_valid,
 	.configure_phy	= rcar_hdmi_phy_configure,
 };
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 70dbbe44bb23..d061b8de748f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -63,7 +63,6 @@ struct rcar_lvds {
 	struct drm_bridge bridge;
 
 	struct drm_bridge *next_bridge;
-	struct drm_connector connector;
 	struct drm_panel *panel;
 
 	void __iomem *mmio;
@@ -80,74 +79,12 @@ struct rcar_lvds {
 #define bridge_to_rcar_lvds(b) \
 	container_of(b, struct rcar_lvds, bridge)
 
-#define connector_to_rcar_lvds(c) \
-	container_of(c, struct rcar_lvds, connector)
-
 static void rcar_lvds_write(struct rcar_lvds *lvds, u32 reg, u32 data)
 {
 	iowrite32(data, lvds->mmio + reg);
 }
 
 /* -----------------------------------------------------------------------------
- * Connector & Panel
- */
-
-static int rcar_lvds_connector_get_modes(struct drm_connector *connector)
-{
-	struct rcar_lvds *lvds = connector_to_rcar_lvds(connector);
-
-	return drm_panel_get_modes(lvds->panel, connector);
-}
-
-static int rcar_lvds_connector_atomic_check(struct drm_connector *connector,
-					    struct drm_atomic_state *state)
-{
-	struct rcar_lvds *lvds = connector_to_rcar_lvds(connector);
-	const struct drm_display_mode *panel_mode;
-	struct drm_connector_state *conn_state;
-	struct drm_crtc_state *crtc_state;
-
-	conn_state = drm_atomic_get_new_connector_state(state, connector);
-	if (!conn_state->crtc)
-		return 0;
-
-	if (list_empty(&connector->modes)) {
-		dev_dbg(lvds->dev, "connector: empty modes list\n");
-		return -EINVAL;
-	}
-
-	panel_mode = list_first_entry(&connector->modes,
-				      struct drm_display_mode, head);
-
-	/* We're not allowed to modify the resolution. */
-	crtc_state = drm_atomic_get_crtc_state(state, conn_state->crtc);
-	if (IS_ERR(crtc_state))
-		return PTR_ERR(crtc_state);
-
-	if (crtc_state->mode.hdisplay != panel_mode->hdisplay ||
-	    crtc_state->mode.vdisplay != panel_mode->vdisplay)
-		return -EINVAL;
-
-	/* The flat panel mode is fixed, just copy it to the adjusted mode. */
-	drm_mode_copy(&crtc_state->adjusted_mode, panel_mode);
-
-	return 0;
-}
-
-static const struct drm_connector_helper_funcs rcar_lvds_conn_helper_funcs = {
-	.get_modes = rcar_lvds_connector_get_modes,
-	.atomic_check = rcar_lvds_connector_atomic_check,
-};
-
-static const struct drm_connector_funcs rcar_lvds_conn_funcs = {
-	.reset = drm_atomic_helper_connector_reset,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-/* -----------------------------------------------------------------------------
  * PLL Setup
  */
 
@@ -583,11 +520,6 @@ static void __rcar_lvds_atomic_enable(struct drm_bridge *bridge,
 	/* Turn the output on. */
 	lvdcr0 |= LVDCR0_LVRES;
 	rcar_lvds_write(lvds, LVDCR0, lvdcr0);
-
-	if (lvds->panel) {
-		drm_panel_prepare(lvds->panel);
-		drm_panel_enable(lvds->panel);
-	}
 }
 
 static void rcar_lvds_atomic_enable(struct drm_bridge *bridge,
@@ -609,11 +541,6 @@ static void rcar_lvds_atomic_disable(struct drm_bridge *bridge,
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
 
-	if (lvds->panel) {
-		drm_panel_disable(lvds->panel);
-		drm_panel_unprepare(lvds->panel);
-	}
-
 	rcar_lvds_write(lvds, LVDCR0, 0);
 	rcar_lvds_write(lvds, LVDCR1, 0);
 	rcar_lvds_write(lvds, LVDPLLCR, 0);
@@ -648,45 +575,13 @@ static int rcar_lvds_attach(struct drm_bridge *bridge,
 			    enum drm_bridge_attach_flags flags)
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
-	struct drm_connector *connector = &lvds->connector;
-	struct drm_encoder *encoder = bridge->encoder;
-	int ret;
-
-	/* If we have a next bridge just attach it. */
-	if (lvds->next_bridge)
-		return drm_bridge_attach(bridge->encoder, lvds->next_bridge,
-					 bridge, flags);
-
-	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) {
-		DRM_ERROR("Fix bridge driver to make connector optional!");
-		return -EINVAL;
-	}
-
-	/* Otherwise if we have a panel, create a connector. */
-	if (!lvds->panel)
-		return 0;
-
-	ret = drm_connector_init(bridge->dev, connector, &rcar_lvds_conn_funcs,
-				 DRM_MODE_CONNECTOR_LVDS);
-	if (ret < 0)
-		return ret;
-
-	drm_connector_helper_add(connector, &rcar_lvds_conn_helper_funcs);
-
-	ret = drm_connector_attach_encoder(connector, encoder);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
 
-static void rcar_lvds_detach(struct drm_bridge *bridge)
-{
+	return drm_bridge_attach(bridge->encoder, lvds->next_bridge, bridge,
+				 flags);
 }
 
 static const struct drm_bridge_funcs rcar_lvds_bridge_ops = {
 	.attach = rcar_lvds_attach,
-	.detach = rcar_lvds_detach,
 	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
 	.atomic_reset = drm_atomic_helper_bridge_reset,
@@ -759,7 +654,7 @@ static int rcar_lvds_parse_dt_companion(struct rcar_lvds *lvds)
 		 * that we are expected to generate even pixels from the primary
 		 * encoder, and odd pixels from the companion encoder.
 		 */
-		if (lvds->next_bridge && lvds->next_bridge->timings &&
+		if (lvds->next_bridge->timings &&
 		    lvds->next_bridge->timings->dual_link)
 			lvds->link_type = RCAR_LVDS_DUAL_LINK_EVEN_ODD_PIXELS;
 		else
@@ -811,6 +706,15 @@ static int rcar_lvds_parse_dt(struct rcar_lvds *lvds)
 	if (ret)
 		goto done;
 
+	if (lvds->panel) {
+		lvds->next_bridge = devm_drm_panel_bridge_add(lvds->dev,
+							      lvds->panel);
+		if (IS_ERR_OR_NULL(lvds->next_bridge)) {
+			ret = -EINVAL;
+			goto done;
+		}
+	}
+
 	if (lvds->info->quirks & RCAR_LVDS_QUIRK_DUAL_LINK)
 		ret = rcar_lvds_parse_dt_companion(lvds);
 
@@ -839,9 +743,8 @@ static struct clk *rcar_lvds_get_clock(struct rcar_lvds *lvds, const char *name,
 	if (PTR_ERR(clk) == -ENOENT && optional)
 		return NULL;
 
-	if (PTR_ERR(clk) != -EPROBE_DEFER)
-		dev_err(lvds->dev, "failed to get %s clock\n",
-			name ? name : "module");
+	dev_err_probe(lvds->dev, PTR_ERR(clk), "failed to get %s clock\n",
+		      name ? name : "module");
 
 	return clk;
 }
@@ -919,7 +822,6 @@ static int rcar_lvds_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	lvds->bridge.driver_private = lvds;
 	lvds->bridge.funcs = &rcar_lvds_bridge_ops;
 	lvds->bridge.of_node = pdev->dev.of_node;
 
diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig
index cb25c0e8fc9b..558f1b58bd69 100644
--- a/drivers/gpu/drm/rockchip/Kconfig
+++ b/drivers/gpu/drm/rockchip/Kconfig
@@ -10,6 +10,8 @@ config DRM_ROCKCHIP
 	select DRM_DW_HDMI if ROCKCHIP_DW_HDMI
 	select DRM_DW_MIPI_DSI if ROCKCHIP_DW_MIPI_DSI
 	select DRM_RGB if ROCKCHIP_RGB
+	select GENERIC_PHY if ROCKCHIP_DW_MIPI_DSI
+	select GENERIC_PHY_MIPI_DPHY if ROCKCHIP_DW_MIPI_DSI
 	select SND_SOC_HDMI_CODEC if ROCKCHIP_CDN_DP && SND_SOC
 	help
 	  Choose this option if you have a Rockchip soc chipset.
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
index ec7729d18cb8..a2262bee5aa4 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
@@ -14,6 +14,7 @@
 #include <linux/of_device.h>
 #include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
+#include <linux/phy/phy.h>
 #include <linux/regmap.h>
 
 #include <video/mipi_display.h>
@@ -125,7 +126,9 @@
 #define BANDGAP_AND_BIAS_CONTROL			0x20
 #define TERMINATION_RESISTER_CONTROL			0x21
 #define AFE_BIAS_BANDGAP_ANALOG_PROGRAMMABILITY		0x22
+#define HS_RX_CONTROL_OF_LANE_CLK			0x34
 #define HS_RX_CONTROL_OF_LANE_0				0x44
+#define HS_RX_CONTROL_OF_LANE_1				0x54
 #define HS_TX_CLOCK_LANE_REQUEST_STATE_TIME_CONTROL	0x60
 #define HS_TX_CLOCK_LANE_PREPARE_STATE_TIME_CONTROL	0x61
 #define HS_TX_CLOCK_LANE_HS_ZERO_STATE_TIME_CONTROL	0x62
@@ -137,6 +140,9 @@
 #define HS_TX_DATA_LANE_HS_ZERO_STATE_TIME_CONTROL	0x72
 #define HS_TX_DATA_LANE_TRAIL_STATE_TIME_CONTROL	0x73
 #define HS_TX_DATA_LANE_EXIT_STATE_TIME_CONTROL		0x74
+#define HS_RX_DATA_LANE_THS_SETTLE_CONTROL		0x75
+#define HS_RX_CONTROL_OF_LANE_2				0x84
+#define HS_RX_CONTROL_OF_LANE_3				0x94
 
 #define DW_MIPI_NEEDS_PHY_CFG_CLK	BIT(0)
 #define DW_MIPI_NEEDS_GRF_CLK		BIT(1)
@@ -171,12 +177,20 @@
 #define RK3399_TXRX_MASTERSLAVEZ	BIT(7)
 #define RK3399_TXRX_ENABLECLK		BIT(6)
 #define RK3399_TXRX_BASEDIR		BIT(5)
+#define RK3399_TXRX_SRC_SEL_ISP0	BIT(4)
+#define RK3399_TXRX_TURNREQUEST		GENMASK(3, 0)
 
 #define HIWORD_UPDATE(val, mask)	(val | (mask) << 16)
 
 #define to_dsi(nm)	container_of(nm, struct dw_mipi_dsi_rockchip, nm)
 
 enum {
+	DW_DSI_USAGE_IDLE,
+	DW_DSI_USAGE_DSI,
+	DW_DSI_USAGE_PHY,
+};
+
+enum {
 	BANDGAP_97_07,
 	BANDGAP_98_05,
 	BANDGAP_99_02,
@@ -213,6 +227,10 @@ struct rockchip_dw_dsi_chip_data {
 	u32 lanecfg2_grf_reg;
 	u32 lanecfg2;
 
+	int (*dphy_rx_init)(struct phy *phy);
+	int (*dphy_rx_power_on)(struct phy *phy);
+	int (*dphy_rx_power_off)(struct phy *phy);
+
 	unsigned int flags;
 	unsigned int max_data_lanes;
 };
@@ -223,6 +241,7 @@ struct dw_mipi_dsi_rockchip {
 	void __iomem *base;
 
 	struct regmap *grf_regmap;
+	struct clk *pclk;
 	struct clk *pllref_clk;
 	struct clk *grf_clk;
 	struct clk *phy_cfg_clk;
@@ -235,6 +254,12 @@ struct dw_mipi_dsi_rockchip {
 	struct phy *phy;
 	union phy_configure_opts phy_opts;
 
+	/* being a phy for other mipi hosts */
+	unsigned int usage_mode;
+	struct mutex usage_mutex;
+	struct phy *dphy;
+	struct phy_configure_opts_mipi_dphy dphy_config;
+
 	unsigned int lane_mbps; /* per lane */
 	u16 input_div;
 	u16 feedback_div;
@@ -978,6 +1003,17 @@ static int dw_mipi_dsi_rockchip_host_attach(void *priv_data,
 	struct device *second;
 	int ret;
 
+	mutex_lock(&dsi->usage_mutex);
+
+	if (dsi->usage_mode != DW_DSI_USAGE_IDLE) {
+		DRM_DEV_ERROR(dsi->dev, "dsi controller already in use\n");
+		mutex_unlock(&dsi->usage_mutex);
+		return -EBUSY;
+	}
+
+	dsi->usage_mode = DW_DSI_USAGE_DSI;
+	mutex_unlock(&dsi->usage_mutex);
+
 	ret = component_add(dsi->dev, &dw_mipi_dsi_rockchip_ops);
 	if (ret) {
 		DRM_DEV_ERROR(dsi->dev, "Failed to register component: %d\n",
@@ -1013,6 +1049,10 @@ static int dw_mipi_dsi_rockchip_host_detach(void *priv_data,
 
 	component_del(dsi->dev, &dw_mipi_dsi_rockchip_ops);
 
+	mutex_lock(&dsi->usage_mutex);
+	dsi->usage_mode = DW_DSI_USAGE_IDLE;
+	mutex_unlock(&dsi->usage_mutex);
+
 	return 0;
 }
 
@@ -1021,11 +1061,227 @@ static const struct dw_mipi_dsi_host_ops dw_mipi_dsi_rockchip_host_ops = {
 	.detach = dw_mipi_dsi_rockchip_host_detach,
 };
 
+static int dw_mipi_dsi_rockchip_dphy_bind(struct device *dev,
+					  struct device *master,
+					  void *data)
+{
+	/*
+	 * Nothing to do when used as a dphy.
+	 * Just make the rest of Rockchip-DRM happy
+	 * by being here.
+	 */
+
+	return 0;
+}
+
+static void dw_mipi_dsi_rockchip_dphy_unbind(struct device *dev,
+					     struct device *master,
+					     void *data)
+{
+	/* Nothing to do when used as a dphy. */
+}
+
+static const struct component_ops dw_mipi_dsi_rockchip_dphy_ops = {
+	.bind	= dw_mipi_dsi_rockchip_dphy_bind,
+	.unbind	= dw_mipi_dsi_rockchip_dphy_unbind,
+};
+
+static int dw_mipi_dsi_dphy_init(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+	int ret;
+
+	mutex_lock(&dsi->usage_mutex);
+
+	if (dsi->usage_mode != DW_DSI_USAGE_IDLE) {
+		DRM_DEV_ERROR(dsi->dev, "dsi controller already in use\n");
+		mutex_unlock(&dsi->usage_mutex);
+		return -EBUSY;
+	}
+
+	dsi->usage_mode = DW_DSI_USAGE_PHY;
+	mutex_unlock(&dsi->usage_mutex);
+
+	ret = component_add(dsi->dev, &dw_mipi_dsi_rockchip_dphy_ops);
+	if (ret < 0)
+		goto err_graph;
+
+	if (dsi->cdata->dphy_rx_init) {
+		ret = clk_prepare_enable(dsi->pclk);
+		if (ret < 0)
+			goto err_init;
+
+		ret = clk_prepare_enable(dsi->grf_clk);
+		if (ret) {
+			clk_disable_unprepare(dsi->pclk);
+			goto err_init;
+		}
+
+		ret = dsi->cdata->dphy_rx_init(phy);
+		clk_disable_unprepare(dsi->grf_clk);
+		clk_disable_unprepare(dsi->pclk);
+		if (ret < 0)
+			goto err_init;
+	}
+
+	return 0;
+
+err_init:
+	component_del(dsi->dev, &dw_mipi_dsi_rockchip_dphy_ops);
+err_graph:
+	mutex_lock(&dsi->usage_mutex);
+	dsi->usage_mode = DW_DSI_USAGE_IDLE;
+	mutex_unlock(&dsi->usage_mutex);
+
+	return ret;
+}
+
+static int dw_mipi_dsi_dphy_exit(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+
+	component_del(dsi->dev, &dw_mipi_dsi_rockchip_dphy_ops);
+
+	mutex_lock(&dsi->usage_mutex);
+	dsi->usage_mode = DW_DSI_USAGE_IDLE;
+	mutex_unlock(&dsi->usage_mutex);
+
+	return 0;
+}
+
+static int dw_mipi_dsi_dphy_configure(struct phy *phy, union phy_configure_opts *opts)
+{
+	struct phy_configure_opts_mipi_dphy *config = &opts->mipi_dphy;
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+	int ret;
+
+	ret = phy_mipi_dphy_config_validate(&opts->mipi_dphy);
+	if (ret)
+		return ret;
+
+	dsi->dphy_config = *config;
+	dsi->lane_mbps = div_u64(config->hs_clk_rate, 1000 * 1000 * 1);
+
+	return 0;
+}
+
+static int dw_mipi_dsi_dphy_power_on(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+	int i, ret;
+
+	DRM_DEV_DEBUG(dsi->dev, "lanes %d - data_rate_mbps %u\n",
+		      dsi->dphy_config.lanes, dsi->lane_mbps);
+
+	i = max_mbps_to_parameter(dsi->lane_mbps);
+	if (i < 0) {
+		DRM_DEV_ERROR(dsi->dev, "failed to get parameter for %dmbps clock\n",
+			      dsi->lane_mbps);
+		return i;
+	}
+
+	ret = pm_runtime_get_sync(dsi->dev);
+	if (ret < 0) {
+		DRM_DEV_ERROR(dsi->dev, "failed to enable device: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(dsi->pclk);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "Failed to enable pclk: %d\n", ret);
+		goto err_pclk;
+	}
+
+	ret = clk_prepare_enable(dsi->grf_clk);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "Failed to enable grf_clk: %d\n", ret);
+		goto err_grf_clk;
+	}
+
+	ret = clk_prepare_enable(dsi->phy_cfg_clk);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "Failed to enable phy_cfg_clk: %d\n", ret);
+		goto err_phy_cfg_clk;
+	}
+
+	/* do soc-variant specific init */
+	if (dsi->cdata->dphy_rx_power_on) {
+		ret = dsi->cdata->dphy_rx_power_on(phy);
+		if (ret < 0) {
+			DRM_DEV_ERROR(dsi->dev, "hardware-specific phy bringup failed: %d\n", ret);
+			goto err_pwr_on;
+		}
+	}
+
+	/*
+	 * Configure hsfreqrange according to frequency values
+	 * Set clock lane and hsfreqrange by lane0(test code 0x44)
+	 */
+	dw_mipi_dsi_phy_write(dsi, HS_RX_CONTROL_OF_LANE_CLK, 0);
+	dw_mipi_dsi_phy_write(dsi, HS_RX_CONTROL_OF_LANE_0,
+			      HSFREQRANGE_SEL(dppa_map[i].hsfreqrange));
+	dw_mipi_dsi_phy_write(dsi, HS_RX_CONTROL_OF_LANE_1, 0);
+	dw_mipi_dsi_phy_write(dsi, HS_RX_CONTROL_OF_LANE_2, 0);
+	dw_mipi_dsi_phy_write(dsi, HS_RX_CONTROL_OF_LANE_3, 0);
+
+	/* Normal operation */
+	dw_mipi_dsi_phy_write(dsi, 0x0, 0);
+
+	clk_disable_unprepare(dsi->phy_cfg_clk);
+	clk_disable_unprepare(dsi->grf_clk);
+
+	return ret;
+
+err_pwr_on:
+	clk_disable_unprepare(dsi->phy_cfg_clk);
+err_phy_cfg_clk:
+	clk_disable_unprepare(dsi->grf_clk);
+err_grf_clk:
+	clk_disable_unprepare(dsi->pclk);
+err_pclk:
+	pm_runtime_put(dsi->dev);
+	return ret;
+}
+
+static int dw_mipi_dsi_dphy_power_off(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+	int ret;
+
+	ret = clk_prepare_enable(dsi->grf_clk);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "Failed to enable grf_clk: %d\n", ret);
+		return ret;
+	}
+
+	if (dsi->cdata->dphy_rx_power_off) {
+		ret = dsi->cdata->dphy_rx_power_off(phy);
+		if (ret < 0)
+			DRM_DEV_ERROR(dsi->dev, "hardware-specific phy shutdown failed: %d\n", ret);
+	}
+
+	clk_disable_unprepare(dsi->grf_clk);
+	clk_disable_unprepare(dsi->pclk);
+
+	pm_runtime_put(dsi->dev);
+
+	return ret;
+}
+
+static const struct phy_ops dw_mipi_dsi_dphy_ops = {
+	.configure	= dw_mipi_dsi_dphy_configure,
+	.power_on	= dw_mipi_dsi_dphy_power_on,
+	.power_off	= dw_mipi_dsi_dphy_power_off,
+	.init		= dw_mipi_dsi_dphy_init,
+	.exit		= dw_mipi_dsi_dphy_exit,
+};
+
 static int dw_mipi_dsi_rockchip_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct dw_mipi_dsi_rockchip *dsi;
+	struct phy_provider *phy_provider;
 	struct resource *res;
 	const struct rockchip_dw_dsi_chip_data *cdata =
 				of_device_get_match_data(dev);
@@ -1065,6 +1321,13 @@ static int dw_mipi_dsi_rockchip_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	dsi->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(dsi->pclk)) {
+		ret = PTR_ERR(dsi->pclk);
+		DRM_DEV_ERROR(dev, "Unable to get pclk: %d\n", ret);
+		return ret;
+	}
+
 	dsi->pllref_clk = devm_clk_get(dev, "ref");
 	if (IS_ERR(dsi->pllref_clk)) {
 		if (dsi->phy) {
@@ -1115,6 +1378,19 @@ static int dw_mipi_dsi_rockchip_probe(struct platform_device *pdev)
 	dsi->pdata.priv_data = dsi;
 	platform_set_drvdata(pdev, dsi);
 
+	mutex_init(&dsi->usage_mutex);
+
+	dsi->dphy = devm_phy_create(dev, NULL, &dw_mipi_dsi_dphy_ops);
+	if (IS_ERR(dsi->dphy)) {
+		DRM_DEV_ERROR(&pdev->dev, "failed to create PHY\n");
+		return PTR_ERR(dsi->dphy);
+	}
+
+	phy_set_drvdata(dsi->dphy, dsi);
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	dsi->dmd = dw_mipi_dsi_probe(pdev, &dsi->pdata);
 	if (IS_ERR(dsi->dmd)) {
 		ret = PTR_ERR(dsi->dmd);
@@ -1178,6 +1454,75 @@ static const struct rockchip_dw_dsi_chip_data rk3288_chip_data[] = {
 	{ /* sentinel */ }
 };
 
+static int rk3399_dphy_tx1rx1_init(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+
+	/*
+	 * Set TX1RX1 source to isp1.
+	 * Assume ISP0 is supplied by the RX0 dphy.
+	 */
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(0, RK3399_TXRX_SRC_SEL_ISP0));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(0, RK3399_TXRX_MASTERSLAVEZ));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(0, RK3399_TXRX_BASEDIR));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(0, RK3399_DSI1_ENABLE));
+
+	return 0;
+}
+
+static int rk3399_dphy_tx1rx1_power_on(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+
+	/* tester reset pulse */
+	dsi_write(dsi, DSI_PHY_TST_CTRL0, PHY_TESTCLK | PHY_TESTCLR);
+	usleep_range(100, 150);
+
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(0, RK3399_TXRX_MASTERSLAVEZ));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(RK3399_TXRX_BASEDIR, RK3399_TXRX_BASEDIR));
+
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(0, RK3399_DSI1_FORCERXMODE));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(0, RK3399_DSI1_FORCETXSTOPMODE));
+
+	/* Disable lane turn around, which is ignored in receive mode */
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
+		     HIWORD_UPDATE(0, RK3399_TXRX_TURNREQUEST));
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(RK3399_DSI1_TURNDISABLE,
+				   RK3399_DSI1_TURNDISABLE));
+	usleep_range(100, 150);
+
+	dsi_write(dsi, DSI_PHY_TST_CTRL0, PHY_TESTCLK | PHY_UNTESTCLR);
+	usleep_range(100, 150);
+
+	/* Enable dphy lanes */
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(GENMASK(dsi->dphy_config.lanes - 1, 0),
+				   RK3399_DSI1_ENABLE));
+
+	usleep_range(100, 150);
+
+	return 0;
+}
+
+static int rk3399_dphy_tx1rx1_power_off(struct phy *phy)
+{
+	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
+
+	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
+		     HIWORD_UPDATE(0, RK3399_DSI1_ENABLE));
+
+	return 0;
+}
+
 static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
 	{
 		.reg = 0xff960000,
@@ -1220,6 +1565,10 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
 
 		.flags = DW_MIPI_NEEDS_PHY_CFG_CLK | DW_MIPI_NEEDS_GRF_CLK,
 		.max_data_lanes = 4,
+
+		.dphy_rx_init = rk3399_dphy_tx1rx1_init,
+		.dphy_rx_power_on = rk3399_dphy_tx1rx1_power_on,
+		.dphy_rx_power_off = rk3399_dphy_tx1rx1_power_off,
 	},
 	{ /* sentinel */ }
 };
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index b730b8d5d949..bfba9793d238 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -116,7 +116,7 @@ static int rockchip_drm_bind(struct device *dev)
 	int ret;
 
 	/* Remove existing drivers that may own the framebuffer memory. */
-	ret = drm_aperture_remove_framebuffers(false, "rockchip-drm-fb");
+	ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver);
 	if (ret) {
 		DRM_DEV_ERROR(dev,
 			      "Failed to remove existing framebuffers - %d.\n",
@@ -162,12 +162,6 @@ static int rockchip_drm_bind(struct device *dev)
 
 	drm_mode_config_reset(drm_dev);
 
-	/*
-	 * enable drm irq mode.
-	 * - with irq_enabled = true, we can use the vblank feature.
-	 */
-	drm_dev->irq_enabled = true;
-
 	ret = rockchip_drm_fbdev_init(drm_dev);
 	if (ret)
 		goto err_unbind_all;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index f5b9028a16a3..ba9e14da41b4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1110,7 +1110,6 @@ static const struct drm_plane_helper_funcs plane_helper_funcs = {
 	.atomic_disable = vop_plane_atomic_disable,
 	.atomic_async_check = vop_plane_atomic_async_check,
 	.atomic_async_update = vop_plane_atomic_async_update,
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 };
 
 static const struct drm_plane_funcs vop_plane_funcs = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 489d63c05c0d..551653940e39 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -636,11 +636,8 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		}
 	} else {
 		ret = drm_bridge_attach(encoder, lvds->bridge, NULL, 0);
-		if (ret) {
-			DRM_DEV_ERROR(drm_dev->dev,
-				      "failed to attach bridge: %d\n", ret);
+		if (ret)
 			goto err_free_encoder;
-		}
 	}
 
 	pm_runtime_enable(dev);
diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.c b/drivers/gpu/drm/rockchip/rockchip_rgb.c
index c079714477d8..d691d9bef8e7 100644
--- a/drivers/gpu/drm/rockchip/rockchip_rgb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_rgb.c
@@ -143,11 +143,8 @@ struct rockchip_rgb *rockchip_rgb_init(struct device *dev,
 	rgb->bridge = bridge;
 
 	ret = drm_bridge_attach(encoder, rgb->bridge, NULL, 0);
-	if (ret) {
-		DRM_DEV_ERROR(drm_dev->dev,
-			      "failed to attach bridge: %d\n", ret);
+	if (ret)
 		goto err_free_encoder;
-	}
 
 	return rgb;
 
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index a2a953693b45..67382621b429 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -232,7 +232,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
 {
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    !list_empty(&sched->pending_list))
-		schedule_delayed_work(&sched->work_tdr, sched->timeout);
+		queue_delayed_work(sched->timeout_wq, &sched->work_tdr, sched->timeout);
 }
 
 /**
@@ -244,7 +244,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
  */
 void drm_sched_fault(struct drm_gpu_scheduler *sched)
 {
-	mod_delayed_work(system_wq, &sched->work_tdr, 0);
+	mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
 }
 EXPORT_SYMBOL(drm_sched_fault);
 
@@ -270,7 +270,7 @@ unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched)
 	 * Modify the timeout to an arbitrarily large value. This also prevents
 	 * the timeout to be restarted when new submissions arrive
 	 */
-	if (mod_delayed_work(system_wq, &sched->work_tdr, MAX_SCHEDULE_TIMEOUT)
+	if (mod_delayed_work(sched->timeout_wq, &sched->work_tdr, MAX_SCHEDULE_TIMEOUT)
 			&& time_after(sched_timeout, now))
 		return sched_timeout - now;
 	else
@@ -294,7 +294,7 @@ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched,
 	if (list_empty(&sched->pending_list))
 		cancel_delayed_work(&sched->work_tdr);
 	else
-		mod_delayed_work(system_wq, &sched->work_tdr, remaining);
+		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, remaining);
 
 	spin_unlock(&sched->job_list_lock);
 }
@@ -802,10 +802,10 @@ static int drm_sched_main(void *param)
 
 		sched_job = drm_sched_entity_pop_job(entity);
 
-		complete(&entity->entity_idle);
-
-		if (!sched_job)
+		if (!sched_job) {
+			complete(&entity->entity_idle);
 			continue;
+		}
 
 		s_fence = sched_job->s_fence;
 
@@ -814,6 +814,7 @@ static int drm_sched_main(void *param)
 
 		trace_drm_run_job(sched_job, entity);
 		fence = sched->ops->run_job(sched_job);
+		complete(&entity->entity_idle);
 		drm_sched_fence_scheduled(s_fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {
@@ -846,6 +847,8 @@ static int drm_sched_main(void *param)
  * @hw_submission: number of hw submissions that can be in flight
  * @hang_limit: number of times to allow a job to hang before dropping it
  * @timeout: timeout value in jiffies for the scheduler
+ * @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is
+ *		used
  * @score: optional score atomic shared with other schedulers
  * @name: name used for debugging
  *
@@ -853,7 +856,8 @@ static int drm_sched_main(void *param)
  */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
-		   unsigned hw_submission, unsigned hang_limit, long timeout,
+		   unsigned hw_submission, unsigned hang_limit,
+		   long timeout, struct workqueue_struct *timeout_wq,
 		   atomic_t *score, const char *name)
 {
 	int i, ret;
@@ -861,6 +865,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->hw_submission_limit = hw_submission;
 	sched->name = name;
 	sched->timeout = timeout;
+	sched->timeout_wq = timeout_wq ? : system_wq;
 	sched->hang_limit = hang_limit;
 	sched->score = score ? score : &sched->_score;
 	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
diff --git a/drivers/gpu/drm/selftests/test-drm_damage_helper.c b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
index 9d2bcdf8bc29..1c19a5d3eefb 100644
--- a/drivers/gpu/drm/selftests/test-drm_damage_helper.c
+++ b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
@@ -6,9 +6,37 @@
 #define pr_fmt(fmt) "drm_damage_helper: " fmt
 
 #include <drm/drm_damage_helper.h>
+#include <drm/drm_plane.h>
+#include <drm/drm_drv.h>
 
 #include "test-drm_modeset_common.h"
 
+struct drm_driver mock_driver;
+static struct drm_device mock_device;
+static struct drm_object_properties mock_obj_props;
+static struct drm_plane mock_plane;
+static struct drm_property mock_prop;
+
+static void mock_setup(struct drm_plane_state *state)
+{
+	static bool setup_done = false;
+
+	state->plane = &mock_plane;
+
+	if (setup_done)
+		return;
+
+	/* just enough so that drm_plane_enable_fb_damage_clips() works */
+	mock_device.driver = &mock_driver;
+	mock_device.mode_config.prop_fb_damage_clips = &mock_prop;
+	mock_plane.dev = &mock_device;
+	mock_plane.base.properties = &mock_obj_props;
+	mock_prop.base.id = 1; /* 0 is an invalid id */
+	mock_prop.dev = &mock_device;
+
+	drm_plane_enable_fb_damage_clips(&mock_plane);
+}
+
 static void set_plane_src(struct drm_plane_state *state, int x1, int y1, int x2,
 			  int y2)
 {
@@ -70,23 +98,29 @@ static bool check_damage_clip(struct drm_plane_state *state, struct drm_rect *r,
 	return true;
 }
 
+const struct drm_framebuffer fb = {
+	.width = 2048,
+	.height = 2048
+};
+
+/* common mocked structs many tests need */
+#define MOCK_VARIABLES() \
+	struct drm_plane_state old_state; \
+	struct drm_plane_state state = { \
+		.crtc = ZERO_SIZE_PTR, \
+		.fb = (struct drm_framebuffer *) &fb, \
+		.visible = true, \
+	}; \
+	mock_setup(&old_state); \
+	mock_setup(&state);
+
 int igt_damage_iter_no_damage(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src same as fb size. */
 	set_plane_src(&old_state, 0, 0, fb.width << 16, fb.height << 16);
@@ -104,20 +138,10 @@ int igt_damage_iter_no_damage(void *ignored)
 int igt_damage_iter_no_damage_fractional_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src has fractional part. */
 	set_plane_src(&old_state, 0x3fffe, 0x3fffe,
@@ -137,20 +161,10 @@ int igt_damage_iter_no_damage_fractional_src(void *ignored)
 int igt_damage_iter_no_damage_src_moved(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src moved since old plane state. */
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
@@ -169,20 +183,10 @@ int igt_damage_iter_no_damage_src_moved(void *ignored)
 int igt_damage_iter_no_damage_fractional_src_moved(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src has fractional part and it moved since old plane state. */
 	set_plane_src(&old_state, 0x3fffe, 0x3fffe,
@@ -202,20 +206,14 @@ int igt_damage_iter_no_damage_fractional_src_moved(void *ignored)
 int igt_damage_iter_no_damage_not_visible(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
+	MOCK_VARIABLES();
 
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = false,
-	};
+	state.visible = false;
+
+	mock_setup(&old_state);
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -231,19 +229,12 @@ int igt_damage_iter_no_damage_not_visible(void *ignored)
 int igt_damage_iter_no_damage_no_crtc(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
+	MOCK_VARIABLES();
 
-	struct drm_plane_state state = {
-		.crtc = 0,
-		.fb = &fb,
-	};
+	state.crtc = NULL;
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -268,6 +259,8 @@ int igt_damage_iter_no_damage_no_fb(void *ignored)
 		.fb = 0,
 	};
 
+	mock_setup(&old_state);
+
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
 	drm_atomic_helper_damage_iter_init(&iter, &old_state, &state);
@@ -282,22 +275,12 @@ int igt_damage_iter_no_damage_no_fb(void *ignored)
 int igt_damage_iter_simple_damage(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -318,22 +301,12 @@ int igt_damage_iter_simple_damage(void *ignored)
 int igt_damage_iter_single_damage(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -353,22 +326,12 @@ int igt_damage_iter_single_damage(void *ignored)
 int igt_damage_iter_single_damage_intersect_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -389,22 +352,12 @@ int igt_damage_iter_single_damage_intersect_src(void *ignored)
 int igt_damage_iter_single_damage_outside_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -424,22 +377,12 @@ int igt_damage_iter_single_damage_outside_src(void *ignored)
 int igt_damage_iter_single_damage_fractional_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src has fractional part. */
 	set_plane_src(&old_state, 0x40002, 0x40002,
@@ -462,22 +405,12 @@ int igt_damage_iter_single_damage_fractional_src(void *ignored)
 int igt_damage_iter_single_damage_intersect_fractional_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src has fractional part. */
 	set_plane_src(&old_state, 0x40002, 0x40002,
@@ -501,22 +434,12 @@ int igt_damage_iter_single_damage_intersect_fractional_src(void *ignored)
 int igt_damage_iter_single_damage_outside_fractional_src(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src has fractional part. */
 	set_plane_src(&old_state, 0x40002, 0x40002,
@@ -539,22 +462,12 @@ int igt_damage_iter_single_damage_outside_fractional_src(void *ignored)
 int igt_damage_iter_single_damage_src_moved(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src moved since old plane state. */
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
@@ -576,22 +489,12 @@ int igt_damage_iter_single_damage_src_moved(void *ignored)
 int igt_damage_iter_single_damage_fractional_src_moved(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage;
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	/* Plane src with fractional part moved since old plane state. */
 	set_plane_src(&old_state, 0x3fffe, 0x3fffe,
@@ -615,22 +518,12 @@ int igt_damage_iter_single_damage_fractional_src_moved(void *ignored)
 int igt_damage_iter_damage(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage[2];
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -656,22 +549,12 @@ int igt_damage_iter_damage(void *ignored)
 int igt_damage_iter_damage_one_intersect(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage[2];
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0x40002, 0x40002,
 		      0x40002 + (1024 << 16), 0x40002 + (768 << 16));
@@ -699,22 +582,12 @@ int igt_damage_iter_damage_one_intersect(void *ignored)
 int igt_damage_iter_damage_one_outside(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage[2];
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0, 0, 1024 << 16, 768 << 16);
 	set_plane_src(&state, 0, 0, 1024 << 16, 768 << 16);
@@ -736,22 +609,12 @@ int igt_damage_iter_damage_one_outside(void *ignored)
 int igt_damage_iter_damage_src_moved(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage[2];
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
-
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = true,
-	};
+	MOCK_VARIABLES();
 
 	set_plane_src(&old_state, 0x40002, 0x40002,
 		      0x40002 + (1024 << 16), 0x40002 + (768 << 16));
@@ -775,22 +638,14 @@ int igt_damage_iter_damage_src_moved(void *ignored)
 int igt_damage_iter_damage_not_visible(void *ignored)
 {
 	struct drm_atomic_helper_damage_iter iter;
-	struct drm_plane_state old_state;
 	struct drm_property_blob damage_blob;
 	struct drm_mode_rect damage[2];
 	struct drm_rect clip;
 	uint32_t num_hits = 0;
 
-	struct drm_framebuffer fb = {
-		.width = 2048,
-		.height = 2048
-	};
+	MOCK_VARIABLES();
 
-	struct drm_plane_state state = {
-		.crtc = ZERO_SIZE_PTR,
-		.fb = &fb,
-		.visible = false,
-	};
+	state.visible = false;
 
 	set_plane_src(&old_state, 0x40002, 0x40002,
 		      0x40002 + (1024 << 16), 0x40002 + (768 << 16));
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index 0a02b7092c04..7db01904d18d 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -18,7 +18,6 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_cma_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 
@@ -130,7 +129,6 @@ DEFINE_DRM_GEM_CMA_FOPS(shmob_drm_fops);
 
 static const struct drm_driver shmob_drm_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET,
-	.irq_handler		= shmob_drm_irq,
 	DRM_GEM_CMA_DRIVER_OPS,
 	.fops			= &shmob_drm_fops,
 	.name			= "shmob-drm",
@@ -183,7 +181,7 @@ static int shmob_drm_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(ddev);
 	drm_kms_helper_poll_fini(ddev);
-	drm_irq_uninstall(ddev);
+	free_irq(sdev->irq, ddev);
 	drm_dev_put(ddev);
 
 	return 0;
@@ -258,7 +256,13 @@ static int shmob_drm_probe(struct platform_device *pdev)
 		goto err_modeset_cleanup;
 	}
 
-	ret = drm_irq_install(ddev, platform_get_irq(pdev, 0));
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto err_modeset_cleanup;
+	sdev->irq = ret;
+
+	ret = request_irq(sdev->irq, shmob_drm_irq, 0, ddev->driver->name,
+			  ddev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to install IRQ handler\n");
 		goto err_modeset_cleanup;
@@ -275,7 +279,7 @@ static int shmob_drm_probe(struct platform_device *pdev)
 	return 0;
 
 err_irq_uninstall:
-	drm_irq_uninstall(ddev);
+	free_irq(sdev->irq, ddev);
 err_modeset_cleanup:
 	drm_kms_helper_poll_fini(ddev);
 err_free_drm_dev:
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.h b/drivers/gpu/drm/shmobile/shmob_drm_drv.h
index 80dc4b1020aa..4964ddd5ab74 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.h
@@ -29,6 +29,7 @@ struct shmob_drm_device {
 	u32 lddckr;
 	u32 ldmt1r;
 
+	unsigned int irq;
 	spinlock_t irq_lock;		/* Protects hardware LDINTR register */
 
 	struct drm_device *ddev;
diff --git a/drivers/gpu/drm/sti/sti_compositor.c b/drivers/gpu/drm/sti/sti_compositor.c
index 319962a2c17b..9caaf3ccfabe 100644
--- a/drivers/gpu/drm/sti/sti_compositor.c
+++ b/drivers/gpu/drm/sti/sti_compositor.c
@@ -145,8 +145,6 @@ static int sti_compositor_bind(struct device *dev,
 	}
 
 	drm_vblank_init(drm_dev, crtc_id);
-	/* Allow usage of vblank without having to call drm_irq_install */
-	drm_dev->irq_enabled = 1;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index ddb4184f0726..b6ee8a82e656 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -463,10 +463,8 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data)
 	drm_bridge_add(bridge);
 
 	err = drm_bridge_attach(encoder, bridge, NULL, 0);
-	if (err) {
-		DRM_ERROR("Failed to attach bridge\n");
+	if (err)
 		return err;
-	}
 
 	dvo->bridge = bridge;
 	connector->encoder = encoder;
diff --git a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
index 8399d337589d..32cb41b2202f 100644
--- a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
+++ b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
@@ -309,14 +309,23 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, const struct drm_display_mode *mode,
 	return 0;
 }
 
+#define DSI_PHY_DELAY(fp, vp, mbps) DIV_ROUND_UP((fp) * (mbps) + 1000 * (vp), 8000)
+
 static int
 dw_mipi_dsi_phy_get_timing(void *priv_data, unsigned int lane_mbps,
 			   struct dw_mipi_dsi_dphy_timing *timing)
 {
-	timing->clk_hs2lp = 0x40;
-	timing->clk_lp2hs = 0x40;
-	timing->data_hs2lp = 0x40;
-	timing->data_lp2hs = 0x40;
+	/*
+	 * From STM32MP157 datasheet, valid for STM32F469, STM32F7x9, STM32H747
+	 * phy_clkhs2lp_time = (272+136*UI)/(8*UI)
+	 * phy_clklp2hs_time = (512+40*UI)/(8*UI)
+	 * phy_hs2lp_time = (192+64*UI)/(8*UI)
+	 * phy_lp2hs_time = (256+32*UI)/(8*UI)
+	 */
+	timing->clk_hs2lp = DSI_PHY_DELAY(272, 136, lane_mbps);
+	timing->clk_lp2hs = DSI_PHY_DELAY(512, 40, lane_mbps);
+	timing->data_hs2lp = DSI_PHY_DELAY(192, 64, lane_mbps);
+	timing->data_lp2hs = DSI_PHY_DELAY(256, 32, lane_mbps);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index 08b71248044d..195de30eb90c 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -947,7 +947,6 @@ static const struct drm_plane_funcs ltdc_plane_funcs = {
 };
 
 static const struct drm_plane_helper_funcs ltdc_plane_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = ltdc_plane_atomic_check,
 	.atomic_update = ltdc_plane_atomic_update,
 	.atomic_disable = ltdc_plane_atomic_disable,
@@ -1122,8 +1121,9 @@ static int ltdc_encoder_init(struct drm_device *ddev, struct drm_bridge *bridge)
 
 	ret = drm_bridge_attach(encoder, bridge, NULL, 0);
 	if (ret) {
-		drm_encoder_cleanup(encoder);
-		return -EINVAL;
+		if (ret != -EPROBE_DEFER)
+			drm_encoder_cleanup(encoder);
+		return ret;
 	}
 
 	DRM_DEBUG_DRIVER("Bridge encoder:%d created\n", encoder->base.id);
@@ -1266,7 +1266,8 @@ int ltdc_load(struct drm_device *ddev)
 		if (bridge) {
 			ret = ltdc_encoder_init(ddev, bridge);
 			if (ret) {
-				DRM_ERROR("init encoder endpoint %d\n", i);
+				if (ret != -EPROBE_DEFER)
+					DRM_ERROR("init encoder endpoint %d\n", i);
 				goto err;
 			}
 		}
@@ -1339,9 +1340,6 @@ int ltdc_load(struct drm_device *ddev)
 		goto err;
 	}
 
-	/* Allow usage of vblank without having to call drm_irq_install */
-	ddev->irq_enabled = 1;
-
 	clk_disable_unprepare(ldev->pixel_clk);
 
 	pinctrl_pm_select_sleep_state(ddev->dev);
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index af335f58bdfc..54dd562e294c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -97,10 +97,8 @@ static int sun4i_drv_bind(struct device *dev)
 	if (ret)
 		goto cleanup_mode_config;
 
-	drm->irq_enabled = true;
-
 	/* Remove early framebuffers (ie. simplefb) */
-	ret = drm_aperture_remove_framebuffers(false, "sun4i-drm-fb");
+	ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver);
 	if (ret)
 		goto cleanup_mode_config;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c
index 11771bdd6e7c..929e95f86b5b 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.c
@@ -127,7 +127,6 @@ static bool sun4i_layer_format_mod_supported(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs sun4i_backend_layer_helper_funcs = {
-	.prepare_fb	= drm_gem_plane_helper_prepare_fb,
 	.atomic_disable	= sun4i_backend_layer_atomic_disable,
 	.atomic_update	= sun4i_backend_layer_atomic_update,
 };
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index ac570437172e..6716e895ae8a 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -142,10 +142,8 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 
 	if (bridge) {
 		ret = drm_bridge_attach(encoder, bridge, NULL, 0);
-		if (ret) {
-			dev_err(drm->dev, "Couldn't attach our bridge\n");
+		if (ret)
 			goto err_cleanup_connector;
-		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index e172426eb7e9..dfb6acc42f02 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -234,10 +234,8 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 
 	if (rgb->bridge) {
 		ret = drm_bridge_attach(encoder, rgb->bridge, NULL, 0);
-		if (ret) {
-			dev_err(drm->dev, "Couldn't attach our bridge\n");
+		if (ret)
 			goto err_cleanup_connector;
-		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index e779855bcd6e..7845c2a53a7f 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -332,7 +332,6 @@ static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = {
-	.prepare_fb	= drm_gem_plane_helper_prepare_fb,
 	.atomic_check	= sun8i_ui_layer_atomic_check,
 	.atomic_disable	= sun8i_ui_layer_atomic_disable,
 	.atomic_update	= sun8i_ui_layer_atomic_update,
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 1c86c2dd0bbf..bb7c43036dfa 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -436,7 +436,6 @@ static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = {
-	.prepare_fb	= drm_gem_plane_helper_prepare_fb,
 	.atomic_check	= sun8i_vi_layer_atomic_check,
 	.atomic_disable	= sun8i_vi_layer_atomic_disable,
 	.atomic_update	= sun8i_vi_layer_atomic_update,
diff --git a/drivers/gpu/drm/tegra/Kconfig b/drivers/gpu/drm/tegra/Kconfig
index 5043dcaf1cf9..1650a448eabd 100644
--- a/drivers/gpu/drm/tegra/Kconfig
+++ b/drivers/gpu/drm/tegra/Kconfig
@@ -9,6 +9,7 @@ config DRM_TEGRA
 	select DRM_MIPI_DSI
 	select DRM_PANEL
 	select TEGRA_HOST1X
+	select INTERCONNECT
 	select IOMMU_IOVA
 	select CEC_CORE if CEC_NOTIFIER
 	help
diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile
index d6cf202414f0..d801909182cf 100644
--- a/drivers/gpu/drm/tegra/Makefile
+++ b/drivers/gpu/drm/tegra/Makefile
@@ -3,6 +3,9 @@ ccflags-$(CONFIG_DRM_TEGRA_DEBUG) += -DDEBUG
 
 tegra-drm-y := \
 	drm.o \
+	uapi.o \
+	submit.o \
+	firewall.o \
 	gem.o \
 	fb.o \
 	dp.o \
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 51bbbc42a144..16c7aabb94d3 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -8,6 +8,7 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/iommu.h>
+#include <linux/interconnect.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
@@ -618,9 +619,14 @@ static int tegra_plane_atomic_check(struct drm_plane *plane,
 	struct tegra_dc *dc = to_tegra_dc(new_plane_state->crtc);
 	int err;
 
+	plane_state->peak_memory_bandwidth = 0;
+	plane_state->avg_memory_bandwidth = 0;
+
 	/* no need for further checks if the plane is being disabled */
-	if (!new_plane_state->crtc)
+	if (!new_plane_state->crtc) {
+		plane_state->total_peak_memory_bandwidth = 0;
 		return 0;
+	}
 
 	err = tegra_plane_format(new_plane_state->fb->format->format,
 				 &plane_state->format,
@@ -808,6 +814,12 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm,
 	formats = dc->soc->primary_formats;
 	modifiers = dc->soc->modifiers;
 
+	err = tegra_plane_interconnect_init(plane);
+	if (err) {
+		kfree(plane);
+		return ERR_PTR(err);
+	}
+
 	err = drm_universal_plane_init(drm, &plane->base, possible_crtcs,
 				       &tegra_plane_funcs, formats,
 				       num_formats, modifiers, type, NULL);
@@ -845,12 +857,18 @@ static int tegra_cursor_atomic_check(struct drm_plane *plane,
 {
 	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
 										 plane);
+	struct tegra_plane_state *plane_state = to_tegra_plane_state(new_plane_state);
 	struct tegra_plane *tegra = to_tegra_plane(plane);
 	int err;
 
+	plane_state->peak_memory_bandwidth = 0;
+	plane_state->avg_memory_bandwidth = 0;
+
 	/* no need for further checks if the plane is being disabled */
-	if (!new_plane_state->crtc)
+	if (!new_plane_state->crtc) {
+		plane_state->total_peak_memory_bandwidth = 0;
 		return 0;
+	}
 
 	/* scaling not supported for cursor */
 	if ((new_plane_state->src_w >> 16 != new_plane_state->crtc_w) ||
@@ -1030,6 +1048,12 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm,
 	if (!dc->soc->has_nvdisplay) {
 		num_formats = ARRAY_SIZE(tegra_legacy_cursor_plane_formats);
 		formats = tegra_legacy_cursor_plane_formats;
+
+		err = tegra_plane_interconnect_init(plane);
+		if (err) {
+			kfree(plane);
+			return ERR_PTR(err);
+		}
 	} else {
 		num_formats = ARRAY_SIZE(tegra_cursor_plane_formats);
 		formats = tegra_cursor_plane_formats;
@@ -1149,6 +1173,12 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm,
 	num_formats = dc->soc->num_overlay_formats;
 	formats = dc->soc->overlay_formats;
 
+	err = tegra_plane_interconnect_init(plane);
+	if (err) {
+		kfree(plane);
+		return ERR_PTR(err);
+	}
+
 	if (!cursor)
 		type = DRM_PLANE_TYPE_OVERLAY;
 	else
@@ -1572,6 +1602,11 @@ static int tegra_dc_show_stats(struct seq_file *s, void *data)
 	seq_printf(s, "underflow: %lu\n", dc->stats.underflow);
 	seq_printf(s, "overflow: %lu\n", dc->stats.overflow);
 
+	seq_printf(s, "frames total: %lu\n", dc->stats.frames_total);
+	seq_printf(s, "vblank total: %lu\n", dc->stats.vblank_total);
+	seq_printf(s, "underflow total: %lu\n", dc->stats.underflow_total);
+	seq_printf(s, "overflow total: %lu\n", dc->stats.overflow_total);
+
 	return 0;
 }
 
@@ -1804,6 +1839,106 @@ static int tegra_dc_wait_idle(struct tegra_dc *dc, unsigned long timeout)
 	return -ETIMEDOUT;
 }
 
+static void
+tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc,
+				   struct drm_atomic_state *state,
+				   bool prepare_bandwidth_transition)
+{
+	const struct tegra_plane_state *old_tegra_state, *new_tegra_state;
+	const struct tegra_dc_state *old_dc_state, *new_dc_state;
+	u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw;
+	const struct drm_plane_state *old_plane_state;
+	const struct drm_crtc_state *old_crtc_state;
+	struct tegra_dc_window window, old_window;
+	struct tegra_dc *dc = to_tegra_dc(crtc);
+	struct tegra_plane *tegra;
+	struct drm_plane *plane;
+
+	if (dc->soc->has_nvdisplay)
+		return;
+
+	old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc);
+	old_dc_state = to_const_dc_state(old_crtc_state);
+	new_dc_state = to_const_dc_state(crtc->state);
+
+	if (!crtc->state->active) {
+		if (!old_crtc_state->active)
+			return;
+
+		/*
+		 * When CRTC is disabled on DPMS, the state of attached planes
+		 * is kept unchanged. Hence we need to enforce removal of the
+		 * bandwidths from the ICC paths.
+		 */
+		drm_atomic_crtc_for_each_plane(plane, crtc) {
+			tegra = to_tegra_plane(plane);
+
+			icc_set_bw(tegra->icc_mem, 0, 0);
+			icc_set_bw(tegra->icc_mem_vfilter, 0, 0);
+		}
+
+		return;
+	}
+
+	for_each_old_plane_in_state(old_crtc_state->state, plane,
+				    old_plane_state, i) {
+		old_tegra_state = to_const_tegra_plane_state(old_plane_state);
+		new_tegra_state = to_const_tegra_plane_state(plane->state);
+		tegra = to_tegra_plane(plane);
+
+		/*
+		 * We're iterating over the global atomic state and it contains
+		 * planes from another CRTC, hence we need to filter out the
+		 * planes unrelated to this CRTC.
+		 */
+		if (tegra->dc != dc)
+			continue;
+
+		new_avg_bw = new_tegra_state->avg_memory_bandwidth;
+		old_avg_bw = old_tegra_state->avg_memory_bandwidth;
+
+		new_peak_bw = new_tegra_state->total_peak_memory_bandwidth;
+		old_peak_bw = old_tegra_state->total_peak_memory_bandwidth;
+
+		/*
+		 * See the comment related to !crtc->state->active above,
+		 * which explains why bandwidths need to be updated when
+		 * CRTC is turning ON.
+		 */
+		if (new_avg_bw == old_avg_bw && new_peak_bw == old_peak_bw &&
+		    old_crtc_state->active)
+			continue;
+
+		window.src.h = drm_rect_height(&plane->state->src) >> 16;
+		window.dst.h = drm_rect_height(&plane->state->dst);
+
+		old_window.src.h = drm_rect_height(&old_plane_state->src) >> 16;
+		old_window.dst.h = drm_rect_height(&old_plane_state->dst);
+
+		/*
+		 * During the preparation phase (atomic_begin), the memory
+		 * freq should go high before the DC changes are committed
+		 * if bandwidth requirement goes up, otherwise memory freq
+		 * should to stay high if BW requirement goes down.  The
+		 * opposite applies to the completion phase (post_commit).
+		 */
+		if (prepare_bandwidth_transition) {
+			new_avg_bw = max(old_avg_bw, new_avg_bw);
+			new_peak_bw = max(old_peak_bw, new_peak_bw);
+
+			if (tegra_plane_use_vertical_filtering(tegra, &old_window))
+				window = old_window;
+		}
+
+		icc_set_bw(tegra->icc_mem, new_avg_bw, new_peak_bw);
+
+		if (tegra_plane_use_vertical_filtering(tegra, &window))
+			icc_set_bw(tegra->icc_mem_vfilter, new_avg_bw, new_peak_bw);
+		else
+			icc_set_bw(tegra->icc_mem_vfilter, 0, 0);
+	}
+}
+
 static void tegra_crtc_atomic_disable(struct drm_crtc *crtc,
 				      struct drm_atomic_state *state)
 {
@@ -1985,6 +2120,8 @@ static void tegra_crtc_atomic_begin(struct drm_crtc *crtc,
 {
 	unsigned long flags;
 
+	tegra_crtc_update_memory_bandwidth(crtc, state, true);
+
 	if (crtc->state->event) {
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
@@ -2017,7 +2154,207 @@ static void tegra_crtc_atomic_flush(struct drm_crtc *crtc,
 	value = tegra_dc_readl(dc, DC_CMD_STATE_CONTROL);
 }
 
+static bool tegra_plane_is_cursor(const struct drm_plane_state *state)
+{
+	const struct tegra_dc_soc_info *soc = to_tegra_dc(state->crtc)->soc;
+	const struct drm_format_info *fmt = state->fb->format;
+	unsigned int src_w = drm_rect_width(&state->src) >> 16;
+	unsigned int dst_w = drm_rect_width(&state->dst);
+
+	if (state->plane->type != DRM_PLANE_TYPE_CURSOR)
+		return false;
+
+	if (soc->supports_cursor)
+		return true;
+
+	if (src_w != dst_w || fmt->num_planes != 1 || src_w * fmt->cpp[0] > 256)
+		return false;
+
+	return true;
+}
+
+static unsigned long
+tegra_plane_overlap_mask(struct drm_crtc_state *state,
+			 const struct drm_plane_state *plane_state)
+{
+	const struct drm_plane_state *other_state;
+	const struct tegra_plane *tegra;
+	unsigned long overlap_mask = 0;
+	struct drm_plane *plane;
+	struct drm_rect rect;
+
+	if (!plane_state->visible || !plane_state->fb)
+		return 0;
+
+	/*
+	 * Data-prefetch FIFO will easily help to overcome temporal memory
+	 * pressure if other plane overlaps with the cursor plane.
+	 */
+	if (tegra_plane_is_cursor(plane_state))
+		return 0;
+
+	drm_atomic_crtc_state_for_each_plane_state(plane, other_state, state) {
+		rect = plane_state->dst;
+
+		tegra = to_tegra_plane(other_state->plane);
+
+		if (!other_state->visible || !other_state->fb)
+			continue;
+
+		/*
+		 * Ignore cursor plane overlaps because it's not practical to
+		 * assume that it contributes to the bandwidth in overlapping
+		 * area if window width is small.
+		 */
+		if (tegra_plane_is_cursor(other_state))
+			continue;
+
+		if (drm_rect_intersect(&rect, &other_state->dst))
+			overlap_mask |= BIT(tegra->index);
+	}
+
+	return overlap_mask;
+}
+
+static int tegra_crtc_calculate_memory_bandwidth(struct drm_crtc *crtc,
+						 struct drm_atomic_state *state)
+{
+	ulong overlap_mask[TEGRA_DC_LEGACY_PLANES_NUM] = {}, mask;
+	u32 plane_peak_bw[TEGRA_DC_LEGACY_PLANES_NUM] = {};
+	bool all_planes_overlap_simultaneously = true;
+	const struct tegra_plane_state *tegra_state;
+	const struct drm_plane_state *plane_state;
+	struct tegra_dc *dc = to_tegra_dc(crtc);
+	const struct drm_crtc_state *old_state;
+	struct drm_crtc_state *new_state;
+	struct tegra_plane *tegra;
+	struct drm_plane *plane;
+
+	/*
+	 * The nv-display uses shared planes.  The algorithm below assumes
+	 * maximum 3 planes per-CRTC, this assumption isn't applicable to
+	 * the nv-display.  Note that T124 support has additional windows,
+	 * but currently they aren't supported by the driver.
+	 */
+	if (dc->soc->has_nvdisplay)
+		return 0;
+
+	new_state = drm_atomic_get_new_crtc_state(state, crtc);
+	old_state = drm_atomic_get_old_crtc_state(state, crtc);
+
+	/*
+	 * For overlapping planes pixel's data is fetched for each plane at
+	 * the same time, hence bandwidths are accumulated in this case.
+	 * This needs to be taken into account for calculating total bandwidth
+	 * consumed by all planes.
+	 *
+	 * Here we get the overlapping state of each plane, which is a
+	 * bitmask of plane indices telling with what planes there is an
+	 * overlap. Note that bitmask[plane] includes BIT(plane) in order
+	 * to make further code nicer and simpler.
+	 */
+	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, new_state) {
+		tegra_state = to_const_tegra_plane_state(plane_state);
+		tegra = to_tegra_plane(plane);
+
+		if (WARN_ON_ONCE(tegra->index >= TEGRA_DC_LEGACY_PLANES_NUM))
+			return -EINVAL;
+
+		plane_peak_bw[tegra->index] = tegra_state->peak_memory_bandwidth;
+		mask = tegra_plane_overlap_mask(new_state, plane_state);
+		overlap_mask[tegra->index] = mask;
+
+		if (hweight_long(mask) != 3)
+			all_planes_overlap_simultaneously = false;
+	}
+
+	/*
+	 * Then we calculate maximum bandwidth of each plane state.
+	 * The bandwidth includes the plane BW + BW of the "simultaneously"
+	 * overlapping planes, where "simultaneously" means areas where DC
+	 * fetches from the planes simultaneously during of scan-out process.
+	 *
+	 * For example, if plane A overlaps with planes B and C, but B and C
+	 * don't overlap, then the peak bandwidth will be either in area where
+	 * A-and-B or A-and-C planes overlap.
+	 *
+	 * The plane_peak_bw[] contains peak memory bandwidth values of
+	 * each plane, this information is needed by interconnect provider
+	 * in order to set up latency allowance based on the peak BW, see
+	 * tegra_crtc_update_memory_bandwidth().
+	 */
+	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, new_state) {
+		u32 i, old_peak_bw, new_peak_bw, overlap_bw = 0;
+
+		/*
+		 * Note that plane's atomic check doesn't touch the
+		 * total_peak_memory_bandwidth of enabled plane, hence the
+		 * current state contains the old bandwidth state from the
+		 * previous CRTC commit.
+		 */
+		tegra_state = to_const_tegra_plane_state(plane_state);
+		tegra = to_tegra_plane(plane);
+
+		for_each_set_bit(i, &overlap_mask[tegra->index], 3) {
+			if (i == tegra->index)
+				continue;
+
+			if (all_planes_overlap_simultaneously)
+				overlap_bw += plane_peak_bw[i];
+			else
+				overlap_bw = max(overlap_bw, plane_peak_bw[i]);
+		}
+
+		new_peak_bw = plane_peak_bw[tegra->index] + overlap_bw;
+		old_peak_bw = tegra_state->total_peak_memory_bandwidth;
+
+		/*
+		 * If plane's peak bandwidth changed (for example plane isn't
+		 * overlapped anymore) and plane isn't in the atomic state,
+		 * then add plane to the state in order to have the bandwidth
+		 * updated.
+		 */
+		if (old_peak_bw != new_peak_bw) {
+			struct tegra_plane_state *new_tegra_state;
+			struct drm_plane_state *new_plane_state;
+
+			new_plane_state = drm_atomic_get_plane_state(state, plane);
+			if (IS_ERR(new_plane_state))
+				return PTR_ERR(new_plane_state);
+
+			new_tegra_state = to_tegra_plane_state(new_plane_state);
+			new_tegra_state->total_peak_memory_bandwidth = new_peak_bw;
+		}
+	}
+
+	return 0;
+}
+
+static int tegra_crtc_atomic_check(struct drm_crtc *crtc,
+				   struct drm_atomic_state *state)
+{
+	int err;
+
+	err = tegra_crtc_calculate_memory_bandwidth(crtc, state);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void tegra_crtc_atomic_post_commit(struct drm_crtc *crtc,
+				   struct drm_atomic_state *state)
+{
+	/*
+	 * Display bandwidth is allowed to go down only once hardware state
+	 * is known to be armed, i.e. state was committed and VBLANK event
+	 * received.
+	 */
+	tegra_crtc_update_memory_bandwidth(crtc, state, false);
+}
+
 static const struct drm_crtc_helper_funcs tegra_crtc_helper_funcs = {
+	.atomic_check = tegra_crtc_atomic_check,
 	.atomic_begin = tegra_crtc_atomic_begin,
 	.atomic_flush = tegra_crtc_atomic_flush,
 	.atomic_enable = tegra_crtc_atomic_enable,
@@ -2036,6 +2373,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data)
 		/*
 		dev_dbg(dc->dev, "%s(): frame end\n", __func__);
 		*/
+		dc->stats.frames_total++;
 		dc->stats.frames++;
 	}
 
@@ -2044,6 +2382,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data)
 		dev_dbg(dc->dev, "%s(): vertical blank\n", __func__);
 		*/
 		drm_crtc_handle_vblank(&dc->base);
+		dc->stats.vblank_total++;
 		dc->stats.vblank++;
 	}
 
@@ -2051,6 +2390,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data)
 		/*
 		dev_dbg(dc->dev, "%s(): underflow\n", __func__);
 		*/
+		dc->stats.underflow_total++;
 		dc->stats.underflow++;
 	}
 
@@ -2058,11 +2398,13 @@ static irqreturn_t tegra_dc_irq(int irq, void *data)
 		/*
 		dev_dbg(dc->dev, "%s(): overflow\n", __func__);
 		*/
+		dc->stats.overflow_total++;
 		dc->stats.overflow++;
 	}
 
 	if (status & HEAD_UF_INT) {
 		dev_dbg_ratelimited(dc->dev, "%s(): head underflow\n", __func__);
+		dc->stats.underflow_total++;
 		dc->stats.underflow++;
 	}
 
@@ -2343,7 +2685,9 @@ static const struct tegra_dc_soc_info tegra20_dc_soc_info = {
 	.overlay_formats = tegra20_overlay_formats,
 	.modifiers = tegra20_modifiers,
 	.has_win_a_without_filters = true,
+	.has_win_b_vfilter_mem_client = true,
 	.has_win_c_without_vert_filter = true,
+	.plane_tiled_memory_bandwidth_x2 = false,
 };
 
 static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
@@ -2363,7 +2707,9 @@ static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
 	.overlay_formats = tegra20_overlay_formats,
 	.modifiers = tegra20_modifiers,
 	.has_win_a_without_filters = false,
+	.has_win_b_vfilter_mem_client = true,
 	.has_win_c_without_vert_filter = false,
+	.plane_tiled_memory_bandwidth_x2 = true,
 };
 
 static const struct tegra_dc_soc_info tegra114_dc_soc_info = {
@@ -2383,7 +2729,9 @@ static const struct tegra_dc_soc_info tegra114_dc_soc_info = {
 	.overlay_formats = tegra114_overlay_formats,
 	.modifiers = tegra20_modifiers,
 	.has_win_a_without_filters = false,
+	.has_win_b_vfilter_mem_client = false,
 	.has_win_c_without_vert_filter = false,
+	.plane_tiled_memory_bandwidth_x2 = true,
 };
 
 static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
@@ -2403,7 +2751,9 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
 	.overlay_formats = tegra124_overlay_formats,
 	.modifiers = tegra124_modifiers,
 	.has_win_a_without_filters = false,
+	.has_win_b_vfilter_mem_client = false,
 	.has_win_c_without_vert_filter = false,
+	.plane_tiled_memory_bandwidth_x2 = false,
 };
 
 static const struct tegra_dc_soc_info tegra210_dc_soc_info = {
@@ -2423,7 +2773,9 @@ static const struct tegra_dc_soc_info tegra210_dc_soc_info = {
 	.overlay_formats = tegra114_overlay_formats,
 	.modifiers = tegra124_modifiers,
 	.has_win_a_without_filters = false,
+	.has_win_b_vfilter_mem_client = false,
 	.has_win_c_without_vert_filter = false,
+	.plane_tiled_memory_bandwidth_x2 = false,
 };
 
 static const struct tegra_windowgroup_soc tegra186_dc_wgrps[] = {
@@ -2473,6 +2825,7 @@ static const struct tegra_dc_soc_info tegra186_dc_soc_info = {
 	.has_nvdisplay = true,
 	.wgrps = tegra186_dc_wgrps,
 	.num_wgrps = ARRAY_SIZE(tegra186_dc_wgrps),
+	.plane_tiled_memory_bandwidth_x2 = false,
 };
 
 static const struct tegra_windowgroup_soc tegra194_dc_wgrps[] = {
@@ -2522,6 +2875,7 @@ static const struct tegra_dc_soc_info tegra194_dc_soc_info = {
 	.has_nvdisplay = true,
 	.wgrps = tegra194_dc_wgrps,
 	.num_wgrps = ARRAY_SIZE(tegra194_dc_wgrps),
+	.plane_tiled_memory_bandwidth_x2 = false,
 };
 
 static const struct of_device_id tegra_dc_of_match[] = {
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index 5e13f1cfd749..f0cb691852a1 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -15,6 +15,8 @@
 
 struct tegra_output;
 
+#define TEGRA_DC_LEGACY_PLANES_NUM	7
+
 struct tegra_dc_state {
 	struct drm_crtc_state base;
 
@@ -33,11 +35,22 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state)
 	return NULL;
 }
 
+static inline const struct tegra_dc_state *
+to_const_dc_state(const struct drm_crtc_state *state)
+{
+	return to_dc_state((struct drm_crtc_state *)state);
+}
+
 struct tegra_dc_stats {
 	unsigned long frames;
 	unsigned long vblank;
 	unsigned long underflow;
 	unsigned long overflow;
+
+	unsigned long frames_total;
+	unsigned long vblank_total;
+	unsigned long underflow_total;
+	unsigned long overflow_total;
 };
 
 struct tegra_windowgroup_soc {
@@ -66,7 +79,9 @@ struct tegra_dc_soc_info {
 	unsigned int num_overlay_formats;
 	const u64 *modifiers;
 	bool has_win_a_without_filters;
+	bool has_win_b_vfilter_mem_client;
 	bool has_win_c_without_vert_filter;
+	bool plane_tiled_memory_bandwidth_x2;
 };
 
 struct tegra_dc {
@@ -152,6 +167,8 @@ int tegra_dc_state_setup_clock(struct tegra_dc *dc,
 			       struct drm_crtc_state *crtc_state,
 			       struct clk *clk, unsigned long pclk,
 			       unsigned int div);
+void tegra_crtc_atomic_post_commit(struct drm_crtc *crtc,
+				   struct drm_atomic_state *state);
 
 /* from rgb.c */
 int tegra_dc_rgb_probe(struct tegra_dc *dc);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index f96c237b2242..8d37d6b00562 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -21,24 +21,21 @@
 #include <drm/drm_prime.h>
 #include <drm/drm_vblank.h>
 
+#include "dc.h"
 #include "drm.h"
 #include "gem.h"
+#include "uapi.h"
 
 #define DRIVER_NAME "tegra"
 #define DRIVER_DESC "NVIDIA Tegra graphics"
 #define DRIVER_DATE "20120330"
-#define DRIVER_MAJOR 0
+#define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 #define DRIVER_PATCHLEVEL 0
 
 #define CARVEOUT_SZ SZ_64M
 #define CDMA_GATHER_FETCHES_MAX_NB 16383
 
-struct tegra_drm_file {
-	struct idr contexts;
-	struct mutex lock;
-};
-
 static int tegra_atomic_check(struct drm_device *drm,
 			      struct drm_atomic_state *state)
 {
@@ -60,6 +57,17 @@ static const struct drm_mode_config_funcs tegra_drm_mode_config_funcs = {
 	.atomic_commit = drm_atomic_helper_commit,
 };
 
+static void tegra_atomic_post_commit(struct drm_device *drm,
+				     struct drm_atomic_state *old_state)
+{
+	struct drm_crtc_state *old_crtc_state __maybe_unused;
+	struct drm_crtc *crtc;
+	unsigned int i;
+
+	for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i)
+		tegra_crtc_atomic_post_commit(crtc, old_state);
+}
+
 static void tegra_atomic_commit_tail(struct drm_atomic_state *old_state)
 {
 	struct drm_device *drm = old_state->dev;
@@ -79,6 +87,8 @@ static void tegra_atomic_commit_tail(struct drm_atomic_state *old_state)
 	} else {
 		drm_atomic_helper_commit_tail_rpm(old_state);
 	}
+
+	tegra_atomic_post_commit(drm, old_state);
 }
 
 static const struct drm_mode_config_helper_funcs
@@ -94,7 +104,9 @@ static int tegra_drm_open(struct drm_device *drm, struct drm_file *filp)
 	if (!fpriv)
 		return -ENOMEM;
 
-	idr_init_base(&fpriv->contexts, 1);
+	idr_init_base(&fpriv->legacy_contexts, 1);
+	xa_init_flags(&fpriv->contexts, XA_FLAGS_ALLOC1);
+	xa_init(&fpriv->syncpoints);
 	mutex_init(&fpriv->lock);
 	filp->driver_priv = fpriv;
 
@@ -107,20 +119,6 @@ static void tegra_drm_context_free(struct tegra_drm_context *context)
 	kfree(context);
 }
 
-static struct host1x_bo *
-host1x_bo_lookup(struct drm_file *file, u32 handle)
-{
-	struct drm_gem_object *gem;
-	struct tegra_bo *bo;
-
-	gem = drm_gem_object_lookup(file, handle);
-	if (!gem)
-		return NULL;
-
-	bo = to_tegra_bo(gem);
-	return &bo->base;
-}
-
 static int host1x_reloc_copy_from_user(struct host1x_reloc *dest,
 				       struct drm_tegra_reloc __user *src,
 				       struct drm_device *drm,
@@ -151,11 +149,11 @@ static int host1x_reloc_copy_from_user(struct host1x_reloc *dest,
 
 	dest->flags = HOST1X_RELOC_READ | HOST1X_RELOC_WRITE;
 
-	dest->cmdbuf.bo = host1x_bo_lookup(file, cmdbuf);
+	dest->cmdbuf.bo = tegra_gem_lookup(file, cmdbuf);
 	if (!dest->cmdbuf.bo)
 		return -ENOENT;
 
-	dest->target.bo = host1x_bo_lookup(file, target);
+	dest->target.bo = tegra_gem_lookup(file, target);
 	if (!dest->target.bo)
 		return -ENOENT;
 
@@ -193,7 +191,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		return -EINVAL;
 
 	job = host1x_job_alloc(context->channel, args->num_cmdbufs,
-			       args->num_relocs);
+			       args->num_relocs, false);
 	if (!job)
 		return -ENOMEM;
 
@@ -201,6 +199,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 	job->client = client;
 	job->class = client->class;
 	job->serialize = true;
+	job->syncpt_recovery = true;
 
 	/*
 	 * Track referenced BOs so that they can be unreferenced after the
@@ -237,7 +236,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 			goto fail;
 		}
 
-		bo = host1x_bo_lookup(file, cmdbuf.handle);
+		bo = tegra_gem_lookup(file, cmdbuf.handle);
 		if (!bo) {
 			err = -ENOENT;
 			goto fail;
@@ -432,7 +431,7 @@ static int tegra_client_open(struct tegra_drm_file *fpriv,
 	if (err < 0)
 		return err;
 
-	err = idr_alloc(&fpriv->contexts, context, 1, 0, GFP_KERNEL);
+	err = idr_alloc(&fpriv->legacy_contexts, context, 1, 0, GFP_KERNEL);
 	if (err < 0) {
 		client->ops->close_channel(context);
 		return err;
@@ -487,13 +486,13 @@ static int tegra_close_channel(struct drm_device *drm, void *data,
 
 	mutex_lock(&fpriv->lock);
 
-	context = idr_find(&fpriv->contexts, args->context);
+	context = idr_find(&fpriv->legacy_contexts, args->context);
 	if (!context) {
 		err = -EINVAL;
 		goto unlock;
 	}
 
-	idr_remove(&fpriv->contexts, context->id);
+	idr_remove(&fpriv->legacy_contexts, context->id);
 	tegra_drm_context_free(context);
 
 unlock:
@@ -512,7 +511,7 @@ static int tegra_get_syncpt(struct drm_device *drm, void *data,
 
 	mutex_lock(&fpriv->lock);
 
-	context = idr_find(&fpriv->contexts, args->context);
+	context = idr_find(&fpriv->legacy_contexts, args->context);
 	if (!context) {
 		err = -ENODEV;
 		goto unlock;
@@ -541,7 +540,7 @@ static int tegra_submit(struct drm_device *drm, void *data,
 
 	mutex_lock(&fpriv->lock);
 
-	context = idr_find(&fpriv->contexts, args->context);
+	context = idr_find(&fpriv->legacy_contexts, args->context);
 	if (!context) {
 		err = -ENODEV;
 		goto unlock;
@@ -566,7 +565,7 @@ static int tegra_get_syncpt_base(struct drm_device *drm, void *data,
 
 	mutex_lock(&fpriv->lock);
 
-	context = idr_find(&fpriv->contexts, args->context);
+	context = idr_find(&fpriv->legacy_contexts, args->context);
 	if (!context) {
 		err = -ENODEV;
 		goto unlock;
@@ -735,10 +734,25 @@ static int tegra_gem_get_flags(struct drm_device *drm, void *data,
 
 static const struct drm_ioctl_desc tegra_drm_ioctls[] = {
 #ifdef CONFIG_DRM_TEGRA_STAGING
-	DRM_IOCTL_DEF_DRV(TEGRA_GEM_CREATE, tegra_gem_create,
+	DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_OPEN, tegra_drm_ioctl_channel_open,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_CLOSE, tegra_drm_ioctl_channel_close,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_MAP, tegra_drm_ioctl_channel_map,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_UNMAP, tegra_drm_ioctl_channel_unmap,
 			  DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(TEGRA_GEM_MMAP, tegra_gem_mmap,
+	DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_SUBMIT, tegra_drm_ioctl_channel_submit,
 			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_ALLOCATE, tegra_drm_ioctl_syncpoint_allocate,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_FREE, tegra_drm_ioctl_syncpoint_free,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_WAIT, tegra_drm_ioctl_syncpoint_wait,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(TEGRA_GEM_CREATE, tegra_gem_create, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(TEGRA_GEM_MMAP, tegra_gem_mmap, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(TEGRA_SYNCPT_READ, tegra_syncpt_read,
 			  DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(TEGRA_SYNCPT_INCR, tegra_syncpt_incr,
@@ -792,10 +806,11 @@ static void tegra_drm_postclose(struct drm_device *drm, struct drm_file *file)
 	struct tegra_drm_file *fpriv = file->driver_priv;
 
 	mutex_lock(&fpriv->lock);
-	idr_for_each(&fpriv->contexts, tegra_drm_context_cleanup, NULL);
+	idr_for_each(&fpriv->legacy_contexts, tegra_drm_context_cleanup, NULL);
+	tegra_drm_uapi_close_file(fpriv);
 	mutex_unlock(&fpriv->lock);
 
-	idr_destroy(&fpriv->contexts);
+	idr_destroy(&fpriv->legacy_contexts);
 	mutex_destroy(&fpriv->lock);
 	kfree(fpriv);
 }
@@ -853,7 +868,7 @@ static void tegra_debugfs_init(struct drm_minor *minor)
 
 static const struct drm_driver tegra_drm_driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM |
-			   DRIVER_ATOMIC | DRIVER_RENDER,
+			   DRIVER_ATOMIC | DRIVER_RENDER | DRIVER_SYNCOBJ,
 	.open = tegra_drm_open,
 	.postclose = tegra_drm_postclose,
 	.lastclose = drm_fb_helper_lastclose,
@@ -883,6 +898,14 @@ static const struct drm_driver tegra_drm_driver = {
 int tegra_drm_register_client(struct tegra_drm *tegra,
 			      struct tegra_drm_client *client)
 {
+	/*
+	 * When MLOCKs are implemented, change to allocate a shared channel
+	 * only when MLOCKs are disabled.
+	 */
+	client->shared_channel = host1x_channel_request(&client->base);
+	if (!client->shared_channel)
+		return -EBUSY;
+
 	mutex_lock(&tegra->clients_lock);
 	list_add_tail(&client->list, &tegra->clients);
 	client->drm = tegra;
@@ -899,6 +922,9 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra,
 	client->drm = NULL;
 	mutex_unlock(&tegra->clients_lock);
 
+	if (client->shared_channel)
+		host1x_channel_put(client->shared_channel);
+
 	return 0;
 }
 
@@ -1188,13 +1214,6 @@ static int host1x_drm_probe(struct host1x_device *dev)
 			goto device;
 	}
 
-	/*
-	 * We don't use the drm_irq_install() helpers provided by the DRM
-	 * core, so we need to set this manually in order to allow the
-	 * DRM_IOCTL_WAIT_VBLANK to operate correctly.
-	 */
-	drm->irq_enabled = true;
-
 	/* syncpoints are used for full 32-bit hardware VBLANK counters */
 	drm->max_vblank_count = 0xffffffff;
 
@@ -1204,7 +1223,7 @@ static int host1x_drm_probe(struct host1x_device *dev)
 
 	drm_mode_config_reset(drm);
 
-	err = drm_aperture_remove_framebuffers(false, "tegradrmfb");
+	err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver);
 	if (err < 0)
 		goto hub;
 
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index 0cb868065348..8b28327c931c 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -64,12 +64,22 @@ struct tegra_drm {
 	struct tegra_display_hub *hub;
 };
 
+static inline struct host1x *tegra_drm_to_host1x(struct tegra_drm *tegra)
+{
+	return dev_get_drvdata(tegra->drm->dev->parent);
+}
+
 struct tegra_drm_client;
 
 struct tegra_drm_context {
 	struct tegra_drm_client *client;
 	struct host1x_channel *channel;
+
+	/* Only used by legacy UAPI. */
 	unsigned int id;
+
+	/* Only used by new UAPI. */
+	struct xarray mappings;
 };
 
 struct tegra_drm_client_ops {
@@ -91,7 +101,9 @@ struct tegra_drm_client {
 	struct host1x_client base;
 	struct list_head list;
 	struct tegra_drm *drm;
+	struct host1x_channel *shared_channel;
 
+	/* Set by driver */
 	unsigned int version;
 	const struct tegra_drm_client_ops *ops;
 };
diff --git a/drivers/gpu/drm/tegra/firewall.c b/drivers/gpu/drm/tegra/firewall.c
new file mode 100644
index 000000000000..1824d2db0e2c
--- /dev/null
+++ b/drivers/gpu/drm/tegra/firewall.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2010-2020 NVIDIA Corporation */
+
+#include "drm.h"
+#include "submit.h"
+#include "uapi.h"
+
+struct tegra_drm_firewall {
+	struct tegra_drm_submit_data *submit;
+	struct tegra_drm_client *client;
+	u32 *data;
+	u32 pos;
+	u32 end;
+	u32 class;
+};
+
+static int fw_next(struct tegra_drm_firewall *fw, u32 *word)
+{
+	if (fw->pos == fw->end)
+		return -EINVAL;
+
+	*word = fw->data[fw->pos++];
+
+	return 0;
+}
+
+static bool fw_check_addr_valid(struct tegra_drm_firewall *fw, u32 offset)
+{
+	u32 i;
+
+	for (i = 0; i < fw->submit->num_used_mappings; i++) {
+		struct tegra_drm_mapping *m = fw->submit->used_mappings[i].mapping;
+
+		if (offset >= m->iova && offset <= m->iova_end)
+			return true;
+	}
+
+	return false;
+}
+
+static int fw_check_reg(struct tegra_drm_firewall *fw, u32 offset)
+{
+	bool is_addr;
+	u32 word;
+	int err;
+
+	err = fw_next(fw, &word);
+	if (err)
+		return err;
+
+	if (!fw->client->ops->is_addr_reg)
+		return 0;
+
+	is_addr = fw->client->ops->is_addr_reg(fw->client->base.dev, fw->class,
+					       offset);
+
+	if (!is_addr)
+		return 0;
+
+	if (!fw_check_addr_valid(fw, word))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int fw_check_regs_seq(struct tegra_drm_firewall *fw, u32 offset,
+			     u32 count, bool incr)
+{
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		if (fw_check_reg(fw, offset))
+			return -EINVAL;
+
+		if (incr)
+			offset++;
+	}
+
+	return 0;
+}
+
+static int fw_check_regs_mask(struct tegra_drm_firewall *fw, u32 offset,
+			      u16 mask)
+{
+	unsigned long bmask = mask;
+	unsigned int bit;
+
+	for_each_set_bit(bit, &bmask, 16) {
+		if (fw_check_reg(fw, offset+bit))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int fw_check_regs_imm(struct tegra_drm_firewall *fw, u32 offset)
+{
+	bool is_addr;
+
+	is_addr = fw->client->ops->is_addr_reg(fw->client->base.dev, fw->class,
+					       offset);
+	if (is_addr)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int fw_check_class(struct tegra_drm_firewall *fw, u32 class)
+{
+	if (!fw->client->ops->is_valid_class) {
+		if (class == fw->client->base.class)
+			return 0;
+		else
+			return -EINVAL;
+	}
+
+	if (!fw->client->ops->is_valid_class(class))
+		return -EINVAL;
+
+	return 0;
+}
+
+enum {
+	HOST1X_OPCODE_SETCLASS  = 0x00,
+	HOST1X_OPCODE_INCR      = 0x01,
+	HOST1X_OPCODE_NONINCR   = 0x02,
+	HOST1X_OPCODE_MASK      = 0x03,
+	HOST1X_OPCODE_IMM       = 0x04,
+	HOST1X_OPCODE_RESTART   = 0x05,
+	HOST1X_OPCODE_GATHER    = 0x06,
+	HOST1X_OPCODE_SETSTRMID = 0x07,
+	HOST1X_OPCODE_SETAPPID  = 0x08,
+	HOST1X_OPCODE_SETPYLD   = 0x09,
+	HOST1X_OPCODE_INCR_W    = 0x0a,
+	HOST1X_OPCODE_NONINCR_W = 0x0b,
+	HOST1X_OPCODE_GATHER_W  = 0x0c,
+	HOST1X_OPCODE_RESTART_W = 0x0d,
+	HOST1X_OPCODE_EXTEND    = 0x0e,
+};
+
+int tegra_drm_fw_validate(struct tegra_drm_client *client, u32 *data, u32 start,
+			  u32 words, struct tegra_drm_submit_data *submit,
+			  u32 *job_class)
+{
+	struct tegra_drm_firewall fw = {
+		.submit = submit,
+		.client = client,
+		.data = data,
+		.pos = start,
+		.end = start+words,
+		.class = *job_class,
+	};
+	bool payload_valid = false;
+	u32 payload;
+	int err;
+
+	while (fw.pos != fw.end) {
+		u32 word, opcode, offset, count, mask, class;
+
+		err = fw_next(&fw, &word);
+		if (err)
+			return err;
+
+		opcode = (word & 0xf0000000) >> 28;
+
+		switch (opcode) {
+		case HOST1X_OPCODE_SETCLASS:
+			offset = word >> 16 & 0xfff;
+			mask = word & 0x3f;
+			class = (word >> 6) & 0x3ff;
+			err = fw_check_class(&fw, class);
+			fw.class = class;
+			*job_class = class;
+			if (!err)
+				err = fw_check_regs_mask(&fw, offset, mask);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal SETCLASS(offset=0x%x, mask=0x%x, class=0x%x) at word %u",
+					 offset, mask, class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_INCR:
+			offset = (word >> 16) & 0xfff;
+			count = word & 0xffff;
+			err = fw_check_regs_seq(&fw, offset, count, true);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal INCR(offset=0x%x, count=%u) in class 0x%x at word %u",
+					 offset, count, fw.class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_NONINCR:
+			offset = (word >> 16) & 0xfff;
+			count = word & 0xffff;
+			err = fw_check_regs_seq(&fw, offset, count, false);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal NONINCR(offset=0x%x, count=%u) in class 0x%x at word %u",
+					 offset, count, fw.class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_MASK:
+			offset = (word >> 16) & 0xfff;
+			mask = word & 0xffff;
+			err = fw_check_regs_mask(&fw, offset, mask);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal MASK(offset=0x%x, mask=0x%x) in class 0x%x at word %u",
+					 offset, mask, fw.class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_IMM:
+			/* IMM cannot reasonably be used to write a pointer */
+			offset = (word >> 16) & 0xfff;
+			err = fw_check_regs_imm(&fw, offset);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal IMM(offset=0x%x) in class 0x%x at word %u",
+					 offset, fw.class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_SETPYLD:
+			payload = word & 0xffff;
+			payload_valid = true;
+			break;
+		case HOST1X_OPCODE_INCR_W:
+			if (!payload_valid)
+				return -EINVAL;
+
+			offset = word & 0x3fffff;
+			err = fw_check_regs_seq(&fw, offset, payload, true);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal INCR_W(offset=0x%x) in class 0x%x at word %u",
+					 offset, fw.class, fw.pos-1);
+			break;
+		case HOST1X_OPCODE_NONINCR_W:
+			if (!payload_valid)
+				return -EINVAL;
+
+			offset = word & 0x3fffff;
+			err = fw_check_regs_seq(&fw, offset, payload, false);
+			if (err)
+				dev_warn(client->base.dev,
+					 "illegal NONINCR(offset=0x%x) in class 0x%x at word %u",
+					 offset, fw.class, fw.pos-1);
+			break;
+		default:
+			dev_warn(client->base.dev, "illegal opcode at word %u",
+				 fw.pos-1);
+			return -EINVAL;
+		}
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 26af8daa9a16..6ec598f5d5b3 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -707,3 +707,16 @@ struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm,
 
 	return &bo->gem;
 }
+
+struct host1x_bo *tegra_gem_lookup(struct drm_file *file, u32 handle)
+{
+	struct drm_gem_object *gem;
+	struct tegra_bo *bo;
+
+	gem = drm_gem_object_lookup(file, handle);
+	if (!gem)
+		return NULL;
+
+	bo = to_tegra_bo(gem);
+	return &bo->base;
+}
diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h
index c15fd99d6cb2..cb5146a67668 100644
--- a/drivers/gpu/drm/tegra/gem.h
+++ b/drivers/gpu/drm/tegra/gem.h
@@ -80,4 +80,6 @@ struct dma_buf *tegra_gem_prime_export(struct drm_gem_object *gem,
 struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm,
 					      struct dma_buf *buf);
 
+struct host1x_bo *tegra_gem_lookup(struct drm_file *file, u32 handle);
+
 #endif
diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c
index 2e65b4075ce6..e00ec3f40ec8 100644
--- a/drivers/gpu/drm/tegra/plane.c
+++ b/drivers/gpu/drm/tegra/plane.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/iommu.h>
+#include <linux/interconnect.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -64,6 +65,9 @@ tegra_plane_atomic_duplicate_state(struct drm_plane *plane)
 	copy->reflect_x = state->reflect_x;
 	copy->reflect_y = state->reflect_y;
 	copy->opaque = state->opaque;
+	copy->total_peak_memory_bandwidth = state->total_peak_memory_bandwidth;
+	copy->peak_memory_bandwidth = state->peak_memory_bandwidth;
+	copy->avg_memory_bandwidth = state->avg_memory_bandwidth;
 
 	for (i = 0; i < 2; i++)
 		copy->blending[i] = state->blending[i];
@@ -244,6 +248,78 @@ void tegra_plane_cleanup_fb(struct drm_plane *plane,
 		tegra_dc_unpin(dc, to_tegra_plane_state(state));
 }
 
+static int tegra_plane_calculate_memory_bandwidth(struct drm_plane_state *state)
+{
+	struct tegra_plane_state *tegra_state = to_tegra_plane_state(state);
+	unsigned int i, bpp, dst_w, dst_h, src_w, src_h, mul;
+	const struct tegra_dc_soc_info *soc;
+	const struct drm_format_info *fmt;
+	struct drm_crtc_state *crtc_state;
+	u64 avg_bandwidth, peak_bandwidth;
+
+	if (!state->visible)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
+	if (!crtc_state)
+		return -EINVAL;
+
+	src_w = drm_rect_width(&state->src) >> 16;
+	src_h = drm_rect_height(&state->src) >> 16;
+	dst_w = drm_rect_width(&state->dst);
+	dst_h = drm_rect_height(&state->dst);
+
+	fmt = state->fb->format;
+	soc = to_tegra_dc(state->crtc)->soc;
+
+	/*
+	 * Note that real memory bandwidth vary depending on format and
+	 * memory layout, we are not taking that into account because small
+	 * estimation error isn't important since bandwidth is rounded up
+	 * anyway.
+	 */
+	for (i = 0, bpp = 0; i < fmt->num_planes; i++) {
+		unsigned int bpp_plane = fmt->cpp[i] * 8;
+
+		/*
+		 * Sub-sampling is relevant for chroma planes only and vertical
+		 * readouts are not cached, hence only horizontal sub-sampling
+		 * matters.
+		 */
+		if (i > 0)
+			bpp_plane /= fmt->hsub;
+
+		bpp += bpp_plane;
+	}
+
+	/* average bandwidth in kbytes/sec */
+	avg_bandwidth  = min(src_w, dst_w) * min(src_h, dst_h);
+	avg_bandwidth *= drm_mode_vrefresh(&crtc_state->adjusted_mode);
+	avg_bandwidth  = DIV_ROUND_UP(avg_bandwidth * bpp, 8) + 999;
+	do_div(avg_bandwidth, 1000);
+
+	/* mode.clock in kHz, peak bandwidth in kbytes/sec */
+	peak_bandwidth = DIV_ROUND_UP(crtc_state->adjusted_mode.clock * bpp, 8);
+
+	/*
+	 * Tegra30/114 Memory Controller can't interleave DC memory requests
+	 * for the tiled windows because DC uses 16-bytes atom, while DDR3
+	 * uses 32-bytes atom.  Hence there is x2 memory overfetch for tiled
+	 * framebuffer and DDR3 on these SoCs.
+	 */
+	if (soc->plane_tiled_memory_bandwidth_x2 &&
+	    tegra_state->tiling.mode == TEGRA_BO_TILING_MODE_TILED)
+		mul = 2;
+	else
+		mul = 1;
+
+	/* ICC bandwidth in kbytes/sec */
+	tegra_state->peak_memory_bandwidth = kBps_to_icc(peak_bandwidth) * mul;
+	tegra_state->avg_memory_bandwidth  = kBps_to_icc(avg_bandwidth)  * mul;
+
+	return 0;
+}
+
 int tegra_plane_state_add(struct tegra_plane *plane,
 			  struct drm_plane_state *state)
 {
@@ -262,6 +338,10 @@ int tegra_plane_state_add(struct tegra_plane *plane,
 	if (err < 0)
 		return err;
 
+	err = tegra_plane_calculate_memory_bandwidth(state);
+	if (err < 0)
+		return err;
+
 	tegra = to_dc_state(crtc_state);
 
 	tegra->planes |= WIN_A_ACT_REQ << plane->index;
@@ -646,3 +726,40 @@ int tegra_plane_setup_legacy_state(struct tegra_plane *tegra,
 
 	return 0;
 }
+
+static const char * const tegra_plane_icc_names[TEGRA_DC_LEGACY_PLANES_NUM] = {
+	"wina", "winb", "winc", NULL, NULL, NULL, "cursor",
+};
+
+int tegra_plane_interconnect_init(struct tegra_plane *plane)
+{
+	const char *icc_name = tegra_plane_icc_names[plane->index];
+	struct device *dev = plane->dc->dev;
+	struct tegra_dc *dc = plane->dc;
+	int err;
+
+	if (WARN_ON(plane->index >= TEGRA_DC_LEGACY_PLANES_NUM) ||
+	    WARN_ON(!tegra_plane_icc_names[plane->index]))
+		return -EINVAL;
+
+	plane->icc_mem = devm_of_icc_get(dev, icc_name);
+	err = PTR_ERR_OR_ZERO(plane->icc_mem);
+	if (err) {
+		dev_err_probe(dev, err, "failed to get %s interconnect\n",
+			      icc_name);
+		return err;
+	}
+
+	/* plane B on T20/30 has a dedicated memory client for a 6-tap vertical filter */
+	if (plane->index == 1 && dc->soc->has_win_b_vfilter_mem_client) {
+		plane->icc_mem_vfilter = devm_of_icc_get(dev, "winb-vfilter");
+		err = PTR_ERR_OR_ZERO(plane->icc_mem_vfilter);
+		if (err) {
+			dev_err_probe(dev, err, "failed to get %s interconnect\n",
+				      "winb-vfilter");
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/tegra/plane.h b/drivers/gpu/drm/tegra/plane.h
index 1785c1559c0c..d9470780c803 100644
--- a/drivers/gpu/drm/tegra/plane.h
+++ b/drivers/gpu/drm/tegra/plane.h
@@ -8,6 +8,7 @@
 
 #include <drm/drm_plane.h>
 
+struct icc_path;
 struct tegra_bo;
 struct tegra_dc;
 
@@ -16,6 +17,9 @@ struct tegra_plane {
 	struct tegra_dc *dc;
 	unsigned int offset;
 	unsigned int index;
+
+	struct icc_path *icc_mem;
+	struct icc_path *icc_mem_vfilter;
 };
 
 struct tegra_cursor {
@@ -52,6 +56,11 @@ struct tegra_plane_state {
 	/* used for legacy blending support only */
 	struct tegra_plane_legacy_blending_state blending[2];
 	bool opaque;
+
+	/* bandwidths are in ICC units, i.e. kbytes/sec */
+	u32 total_peak_memory_bandwidth;
+	u32 peak_memory_bandwidth;
+	u32 avg_memory_bandwidth;
 };
 
 static inline struct tegra_plane_state *
@@ -63,6 +72,12 @@ to_tegra_plane_state(struct drm_plane_state *state)
 	return NULL;
 }
 
+static inline const struct tegra_plane_state *
+to_const_tegra_plane_state(const struct drm_plane_state *state)
+{
+	return to_tegra_plane_state((struct drm_plane_state *)state);
+}
+
 extern const struct drm_plane_funcs tegra_plane_funcs;
 
 int tegra_plane_prepare_fb(struct drm_plane *plane,
@@ -78,5 +93,6 @@ bool tegra_plane_format_is_indexed(unsigned int format);
 bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int *bpc);
 int tegra_plane_setup_legacy_state(struct tegra_plane *tegra,
 				   struct tegra_plane_state *state);
+int tegra_plane_interconnect_init(struct tegra_plane *plane);
 
 #endif /* TEGRA_PLANE_H */
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 4142a56ca764..606c78a2b988 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -275,11 +275,8 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc)
 	if (output->bridge) {
 		err = drm_bridge_attach(&output->encoder, output->bridge,
 					NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
-		if (err) {
-			dev_err(output->dev, "failed to attach bridge: %d\n",
-				err);
+		if (err)
 			return err;
-		}
 
 		connector = drm_bridge_connector_init(drm, &output->encoder);
 		if (IS_ERR(connector)) {
diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c
new file mode 100644
index 000000000000..776f825df52f
--- /dev/null
+++ b/drivers/gpu/drm/tegra/submit.c
@@ -0,0 +1,625 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 NVIDIA Corporation */
+
+#include <linux/dma-fence-array.h>
+#include <linux/dma-mapping.h>
+#include <linux/file.h>
+#include <linux/host1x.h>
+#include <linux/iommu.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/nospec.h>
+#include <linux/pm_runtime.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/sync_file.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
+
+#include "drm.h"
+#include "gem.h"
+#include "submit.h"
+#include "uapi.h"
+
+#define SUBMIT_ERR(context, fmt, ...) \
+	dev_err_ratelimited(context->client->base.dev, \
+		"%s: job submission failed: " fmt "\n", \
+		current->comm, ##__VA_ARGS__)
+
+struct gather_bo {
+	struct host1x_bo base;
+
+	struct kref ref;
+
+	struct device *dev;
+	u32 *gather_data;
+	dma_addr_t gather_data_dma;
+	size_t gather_data_words;
+};
+
+static struct host1x_bo *gather_bo_get(struct host1x_bo *host_bo)
+{
+	struct gather_bo *bo = container_of(host_bo, struct gather_bo, base);
+
+	kref_get(&bo->ref);
+
+	return host_bo;
+}
+
+static void gather_bo_release(struct kref *ref)
+{
+	struct gather_bo *bo = container_of(ref, struct gather_bo, ref);
+
+	dma_free_attrs(bo->dev, bo->gather_data_words * 4, bo->gather_data, bo->gather_data_dma,
+		       0);
+	kfree(bo);
+}
+
+static void gather_bo_put(struct host1x_bo *host_bo)
+{
+	struct gather_bo *bo = container_of(host_bo, struct gather_bo, base);
+
+	kref_put(&bo->ref, gather_bo_release);
+}
+
+static struct sg_table *
+gather_bo_pin(struct device *dev, struct host1x_bo *host_bo, dma_addr_t *phys)
+{
+	struct gather_bo *bo = container_of(host_bo, struct gather_bo, base);
+	struct sg_table *sgt;
+	int err;
+
+	sgt = kzalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt)
+		return ERR_PTR(-ENOMEM);
+
+	err = dma_get_sgtable(bo->dev, sgt, bo->gather_data, bo->gather_data_dma,
+			      bo->gather_data_words * 4);
+	if (err) {
+		kfree(sgt);
+		return ERR_PTR(err);
+	}
+
+	return sgt;
+}
+
+static void gather_bo_unpin(struct device *dev, struct sg_table *sgt)
+{
+	if (sgt) {
+		sg_free_table(sgt);
+		kfree(sgt);
+	}
+}
+
+static void *gather_bo_mmap(struct host1x_bo *host_bo)
+{
+	struct gather_bo *bo = container_of(host_bo, struct gather_bo, base);
+
+	return bo->gather_data;
+}
+
+static void gather_bo_munmap(struct host1x_bo *host_bo, void *addr)
+{
+}
+
+const struct host1x_bo_ops gather_bo_ops = {
+	.get = gather_bo_get,
+	.put = gather_bo_put,
+	.pin = gather_bo_pin,
+	.unpin = gather_bo_unpin,
+	.mmap = gather_bo_mmap,
+	.munmap = gather_bo_munmap,
+};
+
+static struct tegra_drm_mapping *
+tegra_drm_mapping_get(struct tegra_drm_context *context, u32 id)
+{
+	struct tegra_drm_mapping *mapping;
+
+	xa_lock(&context->mappings);
+
+	mapping = xa_load(&context->mappings, id);
+	if (mapping)
+		kref_get(&mapping->ref);
+
+	xa_unlock(&context->mappings);
+
+	return mapping;
+}
+
+static void *alloc_copy_user_array(void __user *from, size_t count, size_t size)
+{
+	size_t copy_len;
+	void *data;
+
+	if (check_mul_overflow(count, size, &copy_len))
+		return ERR_PTR(-EINVAL);
+
+	if (copy_len > 0x4000)
+		return ERR_PTR(-E2BIG);
+
+	data = kvmalloc(copy_len, GFP_KERNEL);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(data, from, copy_len)) {
+		kvfree(data);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return data;
+}
+
+static int submit_copy_gather_data(struct gather_bo **pbo, struct device *dev,
+				   struct tegra_drm_context *context,
+				   struct drm_tegra_channel_submit *args)
+{
+	struct gather_bo *bo;
+	size_t copy_len;
+
+	if (args->gather_data_words == 0) {
+		SUBMIT_ERR(context, "gather_data_words cannot be zero");
+		return -EINVAL;
+	}
+
+	if (check_mul_overflow((size_t)args->gather_data_words, (size_t)4, &copy_len)) {
+		SUBMIT_ERR(context, "gather_data_words is too large");
+		return -EINVAL;
+	}
+
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (!bo) {
+		SUBMIT_ERR(context, "failed to allocate memory for bo info");
+		return -ENOMEM;
+	}
+
+	host1x_bo_init(&bo->base, &gather_bo_ops);
+	kref_init(&bo->ref);
+	bo->dev = dev;
+
+	bo->gather_data = dma_alloc_attrs(dev, copy_len, &bo->gather_data_dma,
+					  GFP_KERNEL | __GFP_NOWARN, 0);
+	if (!bo->gather_data) {
+		SUBMIT_ERR(context, "failed to allocate memory for gather data");
+		kfree(bo);
+		return -ENOMEM;
+	}
+
+	if (copy_from_user(bo->gather_data, u64_to_user_ptr(args->gather_data_ptr), copy_len)) {
+		SUBMIT_ERR(context, "failed to copy gather data from userspace");
+		dma_free_attrs(dev, copy_len, bo->gather_data, bo->gather_data_dma, 0);
+		kfree(bo);
+		return -EFAULT;
+	}
+
+	bo->gather_data_words = args->gather_data_words;
+
+	*pbo = bo;
+
+	return 0;
+}
+
+static int submit_write_reloc(struct tegra_drm_context *context, struct gather_bo *bo,
+			      struct drm_tegra_submit_buf *buf, struct tegra_drm_mapping *mapping)
+{
+	/* TODO check that target_offset is within bounds */
+	dma_addr_t iova = mapping->iova + buf->reloc.target_offset;
+	u32 written_ptr;
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	if (buf->flags & DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT)
+		iova |= BIT_ULL(39);
+#endif
+
+	written_ptr = iova >> buf->reloc.shift;
+
+	if (buf->reloc.gather_offset_words >= bo->gather_data_words) {
+		SUBMIT_ERR(context,
+			   "relocation has too large gather offset (%u vs gather length %zu)",
+			   buf->reloc.gather_offset_words, bo->gather_data_words);
+		return -EINVAL;
+	}
+
+	buf->reloc.gather_offset_words = array_index_nospec(buf->reloc.gather_offset_words,
+							    bo->gather_data_words);
+
+	bo->gather_data[buf->reloc.gather_offset_words] = written_ptr;
+
+	return 0;
+}
+
+static int submit_process_bufs(struct tegra_drm_context *context, struct gather_bo *bo,
+			       struct drm_tegra_channel_submit *args,
+			       struct tegra_drm_submit_data *job_data)
+{
+	struct tegra_drm_used_mapping *mappings;
+	struct drm_tegra_submit_buf *bufs;
+	int err;
+	u32 i;
+
+	bufs = alloc_copy_user_array(u64_to_user_ptr(args->bufs_ptr), args->num_bufs,
+				     sizeof(*bufs));
+	if (IS_ERR(bufs)) {
+		SUBMIT_ERR(context, "failed to copy bufs array from userspace");
+		return PTR_ERR(bufs);
+	}
+
+	mappings = kcalloc(args->num_bufs, sizeof(*mappings), GFP_KERNEL);
+	if (!mappings) {
+		SUBMIT_ERR(context, "failed to allocate memory for mapping info");
+		err = -ENOMEM;
+		goto done;
+	}
+
+	for (i = 0; i < args->num_bufs; i++) {
+		struct drm_tegra_submit_buf *buf = &bufs[i];
+		struct tegra_drm_mapping *mapping;
+
+		if (buf->flags & ~DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT) {
+			SUBMIT_ERR(context, "invalid flag specified for buffer");
+			err = -EINVAL;
+			goto drop_refs;
+		}
+
+		mapping = tegra_drm_mapping_get(context, buf->mapping);
+		if (!mapping) {
+			SUBMIT_ERR(context, "invalid mapping ID '%u' for buffer", buf->mapping);
+			err = -EINVAL;
+			goto drop_refs;
+		}
+
+		err = submit_write_reloc(context, bo, buf, mapping);
+		if (err) {
+			tegra_drm_mapping_put(mapping);
+			goto drop_refs;
+		}
+
+		mappings[i].mapping = mapping;
+		mappings[i].flags = buf->flags;
+	}
+
+	job_data->used_mappings = mappings;
+	job_data->num_used_mappings = i;
+
+	err = 0;
+
+	goto done;
+
+drop_refs:
+	while (i--)
+		tegra_drm_mapping_put(mappings[i].mapping);
+
+	kfree(mappings);
+	job_data->used_mappings = NULL;
+
+done:
+	kvfree(bufs);
+
+	return err;
+}
+
+static int submit_get_syncpt(struct tegra_drm_context *context, struct host1x_job *job,
+			     struct xarray *syncpoints, struct drm_tegra_channel_submit *args)
+{
+	struct host1x_syncpt *sp;
+
+	if (args->syncpt.flags) {
+		SUBMIT_ERR(context, "invalid flag specified for syncpt");
+		return -EINVAL;
+	}
+
+	/* Syncpt ref will be dropped on job release */
+	sp = xa_load(syncpoints, args->syncpt.id);
+	if (!sp) {
+		SUBMIT_ERR(context, "syncpoint specified in syncpt was not allocated");
+		return -EINVAL;
+	}
+
+	job->syncpt = host1x_syncpt_get(sp);
+	job->syncpt_incrs = args->syncpt.increments;
+
+	return 0;
+}
+
+static int submit_job_add_gather(struct host1x_job *job, struct tegra_drm_context *context,
+				 struct drm_tegra_submit_cmd_gather_uptr *cmd,
+				 struct gather_bo *bo, u32 *offset,
+				 struct tegra_drm_submit_data *job_data,
+				 u32 *class)
+{
+	u32 next_offset;
+
+	if (cmd->reserved[0] || cmd->reserved[1] || cmd->reserved[2]) {
+		SUBMIT_ERR(context, "non-zero reserved field in GATHER_UPTR command");
+		return -EINVAL;
+	}
+
+	/* Check for maximum gather size */
+	if (cmd->words > 16383) {
+		SUBMIT_ERR(context, "too many words in GATHER_UPTR command");
+		return -EINVAL;
+	}
+
+	if (check_add_overflow(*offset, cmd->words, &next_offset)) {
+		SUBMIT_ERR(context, "too many total words in job");
+		return -EINVAL;
+	}
+
+	if (next_offset > bo->gather_data_words) {
+		SUBMIT_ERR(context, "GATHER_UPTR command overflows gather data");
+		return -EINVAL;
+	}
+
+	if (tegra_drm_fw_validate(context->client, bo->gather_data, *offset,
+				  cmd->words, job_data, class)) {
+		SUBMIT_ERR(context, "job was rejected by firewall");
+		return -EINVAL;
+	}
+
+	host1x_job_add_gather(job, &bo->base, cmd->words, *offset * 4);
+
+	*offset = next_offset;
+
+	return 0;
+}
+
+static struct host1x_job *
+submit_create_job(struct tegra_drm_context *context, struct gather_bo *bo,
+		  struct drm_tegra_channel_submit *args, struct tegra_drm_submit_data *job_data,
+		  struct xarray *syncpoints)
+{
+	struct drm_tegra_submit_cmd *cmds;
+	u32 i, gather_offset = 0, class;
+	struct host1x_job *job;
+	int err;
+
+	/* Set initial class for firewall. */
+	class = context->client->base.class;
+
+	cmds = alloc_copy_user_array(u64_to_user_ptr(args->cmds_ptr), args->num_cmds,
+				     sizeof(*cmds));
+	if (IS_ERR(cmds)) {
+		SUBMIT_ERR(context, "failed to copy cmds array from userspace");
+		return ERR_CAST(cmds);
+	}
+
+	job = host1x_job_alloc(context->channel, args->num_cmds, 0, true);
+	if (!job) {
+		SUBMIT_ERR(context, "failed to allocate memory for job");
+		job = ERR_PTR(-ENOMEM);
+		goto done;
+	}
+
+	err = submit_get_syncpt(context, job, syncpoints, args);
+	if (err < 0)
+		goto free_job;
+
+	job->client = &context->client->base;
+	job->class = context->client->base.class;
+	job->serialize = true;
+
+	for (i = 0; i < args->num_cmds; i++) {
+		struct drm_tegra_submit_cmd *cmd = &cmds[i];
+
+		if (cmd->flags) {
+			SUBMIT_ERR(context, "unknown flags given for cmd");
+			err = -EINVAL;
+			goto free_job;
+		}
+
+		if (cmd->type == DRM_TEGRA_SUBMIT_CMD_GATHER_UPTR) {
+			err = submit_job_add_gather(job, context, &cmd->gather_uptr, bo,
+						    &gather_offset, job_data, &class);
+			if (err)
+				goto free_job;
+		} else if (cmd->type == DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT) {
+			if (cmd->wait_syncpt.reserved[0] || cmd->wait_syncpt.reserved[1]) {
+				SUBMIT_ERR(context, "non-zero reserved value");
+				err = -EINVAL;
+				goto free_job;
+			}
+
+			host1x_job_add_wait(job, cmd->wait_syncpt.id, cmd->wait_syncpt.value,
+					    false, class);
+		} else if (cmd->type == DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT_RELATIVE) {
+			if (cmd->wait_syncpt.reserved[0] || cmd->wait_syncpt.reserved[1]) {
+				SUBMIT_ERR(context, "non-zero reserved value");
+				err = -EINVAL;
+				goto free_job;
+			}
+
+			if (cmd->wait_syncpt.id != args->syncpt.id) {
+				SUBMIT_ERR(context, "syncpoint ID in CMD_WAIT_SYNCPT_RELATIVE is not used by the job");
+				err = -EINVAL;
+				goto free_job;
+			}
+
+			host1x_job_add_wait(job, cmd->wait_syncpt.id, cmd->wait_syncpt.value,
+					    true, class);
+		} else {
+			SUBMIT_ERR(context, "unknown cmd type");
+			err = -EINVAL;
+			goto free_job;
+		}
+	}
+
+	if (gather_offset == 0) {
+		SUBMIT_ERR(context, "job must have at least one gather");
+		err = -EINVAL;
+		goto free_job;
+	}
+
+	goto done;
+
+free_job:
+	host1x_job_put(job);
+	job = ERR_PTR(err);
+
+done:
+	kvfree(cmds);
+
+	return job;
+}
+
+static void release_job(struct host1x_job *job)
+{
+	struct tegra_drm_client *client = container_of(job->client, struct tegra_drm_client, base);
+	struct tegra_drm_submit_data *job_data = job->user_data;
+	u32 i;
+
+	for (i = 0; i < job_data->num_used_mappings; i++)
+		tegra_drm_mapping_put(job_data->used_mappings[i].mapping);
+
+	kfree(job_data->used_mappings);
+	kfree(job_data);
+
+	if (pm_runtime_enabled(client->base.dev))
+		pm_runtime_put_autosuspend(client->base.dev);
+}
+
+int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
+				   struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_channel_submit *args = data;
+	struct tegra_drm_submit_data *job_data;
+	struct drm_syncobj *syncobj = NULL;
+	struct tegra_drm_context *context;
+	struct host1x_job *job;
+	struct gather_bo *bo;
+	u32 i;
+	int err;
+
+	mutex_lock(&fpriv->lock);
+
+	context = xa_load(&fpriv->contexts, args->context);
+	if (!context) {
+		mutex_unlock(&fpriv->lock);
+		pr_err_ratelimited("%s: %s: invalid channel context '%#x'", __func__,
+				   current->comm, args->context);
+		return -EINVAL;
+	}
+
+	if (args->syncobj_in) {
+		struct dma_fence *fence;
+
+		err = drm_syncobj_find_fence(file, args->syncobj_in, 0, 0, &fence);
+		if (err) {
+			SUBMIT_ERR(context, "invalid syncobj_in '%#x'", args->syncobj_in);
+			goto unlock;
+		}
+
+		err = dma_fence_wait_timeout(fence, true, msecs_to_jiffies(10000));
+		dma_fence_put(fence);
+		if (err) {
+			SUBMIT_ERR(context, "wait for syncobj_in timed out");
+			goto unlock;
+		}
+	}
+
+	if (args->syncobj_out) {
+		syncobj = drm_syncobj_find(file, args->syncobj_out);
+		if (!syncobj) {
+			SUBMIT_ERR(context, "invalid syncobj_out '%#x'", args->syncobj_out);
+			err = -ENOENT;
+			goto unlock;
+		}
+	}
+
+	/* Allocate gather BO and copy gather words in. */
+	err = submit_copy_gather_data(&bo, drm->dev, context, args);
+	if (err)
+		goto unlock;
+
+	job_data = kzalloc(sizeof(*job_data), GFP_KERNEL);
+	if (!job_data) {
+		SUBMIT_ERR(context, "failed to allocate memory for job data");
+		err = -ENOMEM;
+		goto put_bo;
+	}
+
+	/* Get data buffer mappings and do relocation patching. */
+	err = submit_process_bufs(context, bo, args, job_data);
+	if (err)
+		goto free_job_data;
+
+	/* Allocate host1x_job and add gathers and waits to it. */
+	job = submit_create_job(context, bo, args, job_data, &fpriv->syncpoints);
+	if (IS_ERR(job)) {
+		err = PTR_ERR(job);
+		goto free_job_data;
+	}
+
+	/* Map gather data for Host1x. */
+	err = host1x_job_pin(job, context->client->base.dev);
+	if (err) {
+		SUBMIT_ERR(context, "failed to pin job: %d", err);
+		goto put_job;
+	}
+
+	/* Boot engine. */
+	if (pm_runtime_enabled(context->client->base.dev)) {
+		err = pm_runtime_resume_and_get(context->client->base.dev);
+		if (err < 0) {
+			SUBMIT_ERR(context, "could not power up engine: %d", err);
+			goto unpin_job;
+		}
+	}
+
+	job->user_data = job_data;
+	job->release = release_job;
+	job->timeout = 10000;
+
+	/*
+	 * job_data is now part of job reference counting, so don't release
+	 * it from here.
+	 */
+	job_data = NULL;
+
+	/* Submit job to hardware. */
+	err = host1x_job_submit(job);
+	if (err) {
+		SUBMIT_ERR(context, "host1x job submission failed: %d", err);
+		goto unpin_job;
+	}
+
+	/* Return postfences to userspace and add fences to DMA reservations. */
+	args->syncpt.value = job->syncpt_end;
+
+	if (syncobj) {
+		struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end);
+		if (IS_ERR(fence)) {
+			err = PTR_ERR(fence);
+			SUBMIT_ERR(context, "failed to create postfence: %d", err);
+		}
+
+		drm_syncobj_replace_fence(syncobj, fence);
+	}
+
+	goto put_job;
+
+unpin_job:
+	host1x_job_unpin(job);
+put_job:
+	host1x_job_put(job);
+free_job_data:
+	if (job_data && job_data->used_mappings) {
+		for (i = 0; i < job_data->num_used_mappings; i++)
+			tegra_drm_mapping_put(job_data->used_mappings[i].mapping);
+
+		kfree(job_data->used_mappings);
+	}
+
+	if (job_data)
+		kfree(job_data);
+put_bo:
+	gather_bo_put(&bo->base);
+unlock:
+	if (syncobj)
+		drm_syncobj_put(syncobj);
+
+	mutex_unlock(&fpriv->lock);
+	return err;
+}
diff --git a/drivers/gpu/drm/tegra/submit.h b/drivers/gpu/drm/tegra/submit.h
new file mode 100644
index 000000000000..cf6a2f0a29fc
--- /dev/null
+++ b/drivers/gpu/drm/tegra/submit.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2020 NVIDIA Corporation */
+
+#ifndef _TEGRA_DRM_UAPI_SUBMIT_H
+#define _TEGRA_DRM_UAPI_SUBMIT_H
+
+struct tegra_drm_used_mapping {
+	struct tegra_drm_mapping *mapping;
+	u32 flags;
+};
+
+struct tegra_drm_submit_data {
+	struct tegra_drm_used_mapping *used_mappings;
+	u32 num_used_mappings;
+};
+
+int tegra_drm_fw_validate(struct tegra_drm_client *client, u32 *data, u32 start,
+			  u32 words, struct tegra_drm_submit_data *submit,
+			  u32 *job_class);
+
+#endif
diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c
new file mode 100644
index 000000000000..dc16a24f4dbe
--- /dev/null
+++ b/drivers/gpu/drm/tegra/uapi.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 NVIDIA Corporation */
+
+#include <linux/host1x.h>
+#include <linux/iommu.h>
+#include <linux/list.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_utils.h>
+
+#include "drm.h"
+#include "uapi.h"
+
+static void tegra_drm_mapping_release(struct kref *ref)
+{
+	struct tegra_drm_mapping *mapping =
+		container_of(ref, struct tegra_drm_mapping, ref);
+
+	if (mapping->sgt)
+		dma_unmap_sgtable(mapping->dev, mapping->sgt, mapping->direction,
+				  DMA_ATTR_SKIP_CPU_SYNC);
+
+	host1x_bo_unpin(mapping->dev, mapping->bo, mapping->sgt);
+	host1x_bo_put(mapping->bo);
+
+	kfree(mapping);
+}
+
+void tegra_drm_mapping_put(struct tegra_drm_mapping *mapping)
+{
+	kref_put(&mapping->ref, tegra_drm_mapping_release);
+}
+
+static void tegra_drm_channel_context_close(struct tegra_drm_context *context)
+{
+	struct tegra_drm_mapping *mapping;
+	unsigned long id;
+
+	xa_for_each(&context->mappings, id, mapping)
+		tegra_drm_mapping_put(mapping);
+
+	xa_destroy(&context->mappings);
+
+	host1x_channel_put(context->channel);
+
+	kfree(context);
+}
+
+void tegra_drm_uapi_close_file(struct tegra_drm_file *file)
+{
+	struct tegra_drm_context *context;
+	struct host1x_syncpt *sp;
+	unsigned long id;
+
+	xa_for_each(&file->contexts, id, context)
+		tegra_drm_channel_context_close(context);
+
+	xa_for_each(&file->syncpoints, id, sp)
+		host1x_syncpt_put(sp);
+
+	xa_destroy(&file->contexts);
+	xa_destroy(&file->syncpoints);
+}
+
+static struct tegra_drm_client *tegra_drm_find_client(struct tegra_drm *tegra, u32 class)
+{
+	struct tegra_drm_client *client;
+
+	list_for_each_entry(client, &tegra->clients, list)
+		if (client->base.class == class)
+			return client;
+
+	return NULL;
+}
+
+int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct tegra_drm *tegra = drm->dev_private;
+	struct drm_tegra_channel_open *args = data;
+	struct tegra_drm_client *client = NULL;
+	struct tegra_drm_context *context;
+	int err;
+
+	if (args->flags)
+		return -EINVAL;
+
+	context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (!context)
+		return -ENOMEM;
+
+	client = tegra_drm_find_client(tegra, args->host1x_class);
+	if (!client) {
+		err = -ENODEV;
+		goto free;
+	}
+
+	if (client->shared_channel) {
+		context->channel = host1x_channel_get(client->shared_channel);
+	} else {
+		context->channel = host1x_channel_request(&client->base);
+		if (!context->channel) {
+			err = -EBUSY;
+			goto free;
+		}
+	}
+
+	err = xa_alloc(&fpriv->contexts, &args->context, context, XA_LIMIT(1, U32_MAX),
+		       GFP_KERNEL);
+	if (err < 0)
+		goto put_channel;
+
+	context->client = client;
+	xa_init_flags(&context->mappings, XA_FLAGS_ALLOC1);
+
+	args->version = client->version;
+	args->capabilities = 0;
+
+	if (device_get_dma_attr(client->base.dev) == DEV_DMA_COHERENT)
+		args->capabilities |= DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT;
+
+	return 0;
+
+put_channel:
+	host1x_channel_put(context->channel);
+free:
+	kfree(context);
+
+	return err;
+}
+
+int tegra_drm_ioctl_channel_close(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_channel_close *args = data;
+	struct tegra_drm_context *context;
+
+	mutex_lock(&fpriv->lock);
+
+	context = xa_load(&fpriv->contexts, args->context);
+	if (!context) {
+		mutex_unlock(&fpriv->lock);
+		return -EINVAL;
+	}
+
+	xa_erase(&fpriv->contexts, args->context);
+
+	mutex_unlock(&fpriv->lock);
+
+	tegra_drm_channel_context_close(context);
+
+	return 0;
+}
+
+int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_channel_map *args = data;
+	struct tegra_drm_mapping *mapping;
+	struct tegra_drm_context *context;
+	int err = 0;
+
+	if (args->flags & ~DRM_TEGRA_CHANNEL_MAP_READ_WRITE)
+		return -EINVAL;
+
+	mutex_lock(&fpriv->lock);
+
+	context = xa_load(&fpriv->contexts, args->context);
+	if (!context) {
+		mutex_unlock(&fpriv->lock);
+		return -EINVAL;
+	}
+
+	mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
+	if (!mapping) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	kref_init(&mapping->ref);
+
+	mapping->dev = context->client->base.dev;
+	mapping->bo = tegra_gem_lookup(file, args->handle);
+	if (!mapping->bo) {
+		err = -EINVAL;
+		goto unlock;
+	}
+
+	if (context->client->base.group) {
+		/* IOMMU domain managed directly using IOMMU API */
+		host1x_bo_pin(mapping->dev, mapping->bo, &mapping->iova);
+	} else {
+		switch (args->flags & DRM_TEGRA_CHANNEL_MAP_READ_WRITE) {
+		case DRM_TEGRA_CHANNEL_MAP_READ_WRITE:
+			mapping->direction = DMA_BIDIRECTIONAL;
+			break;
+
+		case DRM_TEGRA_CHANNEL_MAP_WRITE:
+			mapping->direction = DMA_FROM_DEVICE;
+			break;
+
+		case DRM_TEGRA_CHANNEL_MAP_READ:
+			mapping->direction = DMA_TO_DEVICE;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+
+		mapping->sgt = host1x_bo_pin(mapping->dev, mapping->bo, NULL);
+		if (IS_ERR(mapping->sgt)) {
+			err = PTR_ERR(mapping->sgt);
+			goto put_gem;
+		}
+
+		err = dma_map_sgtable(mapping->dev, mapping->sgt, mapping->direction,
+				      DMA_ATTR_SKIP_CPU_SYNC);
+		if (err)
+			goto unpin;
+
+		mapping->iova = sg_dma_address(mapping->sgt->sgl);
+	}
+
+	mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size;
+
+	err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX),
+		       GFP_KERNEL);
+	if (err < 0)
+		goto unmap;
+
+	mutex_unlock(&fpriv->lock);
+
+	return 0;
+
+unmap:
+	if (mapping->sgt) {
+		dma_unmap_sgtable(mapping->dev, mapping->sgt, mapping->direction,
+				  DMA_ATTR_SKIP_CPU_SYNC);
+	}
+unpin:
+	host1x_bo_unpin(mapping->dev, mapping->bo, mapping->sgt);
+put_gem:
+	host1x_bo_put(mapping->bo);
+	kfree(mapping);
+unlock:
+	mutex_unlock(&fpriv->lock);
+	return err;
+}
+
+int tegra_drm_ioctl_channel_unmap(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_channel_unmap *args = data;
+	struct tegra_drm_mapping *mapping;
+	struct tegra_drm_context *context;
+
+	mutex_lock(&fpriv->lock);
+
+	context = xa_load(&fpriv->contexts, args->context);
+	if (!context) {
+		mutex_unlock(&fpriv->lock);
+		return -EINVAL;
+	}
+
+	mapping = xa_erase(&context->mappings, args->mapping);
+
+	mutex_unlock(&fpriv->lock);
+
+	if (!mapping)
+		return -EINVAL;
+
+	tegra_drm_mapping_put(mapping);
+	return 0;
+}
+
+int tegra_drm_ioctl_syncpoint_allocate(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct host1x *host1x = tegra_drm_to_host1x(drm->dev_private);
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_syncpoint_allocate *args = data;
+	struct host1x_syncpt *sp;
+	int err;
+
+	if (args->id)
+		return -EINVAL;
+
+	sp = host1x_syncpt_alloc(host1x, HOST1X_SYNCPT_CLIENT_MANAGED, current->comm);
+	if (!sp)
+		return -EBUSY;
+
+	args->id = host1x_syncpt_id(sp);
+
+	err = xa_insert(&fpriv->syncpoints, args->id, sp, GFP_KERNEL);
+	if (err) {
+		host1x_syncpt_put(sp);
+		return err;
+	}
+
+	return 0;
+}
+
+int tegra_drm_ioctl_syncpoint_free(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_syncpoint_allocate *args = data;
+	struct host1x_syncpt *sp;
+
+	mutex_lock(&fpriv->lock);
+	sp = xa_erase(&fpriv->syncpoints, args->id);
+	mutex_unlock(&fpriv->lock);
+
+	if (!sp)
+		return -EINVAL;
+
+	host1x_syncpt_put(sp);
+
+	return 0;
+}
+
+int tegra_drm_ioctl_syncpoint_wait(struct drm_device *drm, void *data, struct drm_file *file)
+{
+	struct host1x *host1x = tegra_drm_to_host1x(drm->dev_private);
+	struct drm_tegra_syncpoint_wait *args = data;
+	signed long timeout_jiffies;
+	struct host1x_syncpt *sp;
+
+	if (args->padding != 0)
+		return -EINVAL;
+
+	sp = host1x_syncpt_get_by_id_noref(host1x, args->id);
+	if (!sp)
+		return -EINVAL;
+
+	timeout_jiffies = drm_timeout_abs_to_jiffies(args->timeout_ns);
+
+	return host1x_syncpt_wait(sp, args->threshold, timeout_jiffies, &args->value);
+}
diff --git a/drivers/gpu/drm/tegra/uapi.h b/drivers/gpu/drm/tegra/uapi.h
new file mode 100644
index 000000000000..12adad770ad3
--- /dev/null
+++ b/drivers/gpu/drm/tegra/uapi.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2020 NVIDIA Corporation */
+
+#ifndef _TEGRA_DRM_UAPI_H
+#define _TEGRA_DRM_UAPI_H
+
+#include <linux/dma-mapping.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+#include <linux/xarray.h>
+
+#include <drm/drm.h>
+
+struct drm_file;
+struct drm_device;
+
+struct tegra_drm_file {
+	/* Legacy UAPI state */
+	struct idr legacy_contexts;
+	struct mutex lock;
+
+	/* New UAPI state */
+	struct xarray contexts;
+	struct xarray syncpoints;
+};
+
+struct tegra_drm_mapping {
+	struct kref ref;
+
+	struct device *dev;
+	struct host1x_bo *bo;
+	struct sg_table *sgt;
+	enum dma_data_direction direction;
+	dma_addr_t iova;
+	dma_addr_t iova_end;
+};
+
+int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data,
+				 struct drm_file *file);
+int tegra_drm_ioctl_channel_close(struct drm_device *drm, void *data,
+				  struct drm_file *file);
+int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data,
+				struct drm_file *file);
+int tegra_drm_ioctl_channel_unmap(struct drm_device *drm, void *data,
+				  struct drm_file *file);
+int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
+				   struct drm_file *file);
+int tegra_drm_ioctl_syncpoint_allocate(struct drm_device *drm, void *data,
+				       struct drm_file *file);
+int tegra_drm_ioctl_syncpoint_free(struct drm_device *drm, void *data,
+				   struct drm_file *file);
+int tegra_drm_ioctl_syncpoint_wait(struct drm_device *drm, void *data,
+				   struct drm_file *file);
+
+void tegra_drm_uapi_close_file(struct tegra_drm_file *file);
+void tegra_drm_mapping_put(struct tegra_drm_mapping *mapping);
+
+#endif
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index c9d55a9a3180..c02010ff2b7f 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -29,7 +29,6 @@ struct vic_config {
 
 struct vic {
 	struct falcon falcon;
-	bool booted;
 
 	void __iomem *regs;
 	struct tegra_drm_client client;
@@ -52,48 +51,6 @@ static void vic_writel(struct vic *vic, u32 value, unsigned int offset)
 	writel(value, vic->regs + offset);
 }
 
-static int vic_runtime_resume(struct device *dev)
-{
-	struct vic *vic = dev_get_drvdata(dev);
-	int err;
-
-	err = clk_prepare_enable(vic->clk);
-	if (err < 0)
-		return err;
-
-	usleep_range(10, 20);
-
-	err = reset_control_deassert(vic->rst);
-	if (err < 0)
-		goto disable;
-
-	usleep_range(10, 20);
-
-	return 0;
-
-disable:
-	clk_disable_unprepare(vic->clk);
-	return err;
-}
-
-static int vic_runtime_suspend(struct device *dev)
-{
-	struct vic *vic = dev_get_drvdata(dev);
-	int err;
-
-	err = reset_control_assert(vic->rst);
-	if (err < 0)
-		return err;
-
-	usleep_range(2000, 4000);
-
-	clk_disable_unprepare(vic->clk);
-
-	vic->booted = false;
-
-	return 0;
-}
-
 static int vic_boot(struct vic *vic)
 {
 #ifdef CONFIG_IOMMU_API
@@ -103,9 +60,6 @@ static int vic_boot(struct vic *vic)
 	void *hdr;
 	int err = 0;
 
-	if (vic->booted)
-		return 0;
-
 #ifdef CONFIG_IOMMU_API
 	if (vic->config->supports_sid && spec) {
 		u32 value;
@@ -168,8 +122,6 @@ static int vic_boot(struct vic *vic)
 		return err;
 	}
 
-	vic->booted = true;
-
 	return 0;
 }
 
@@ -323,35 +275,74 @@ cleanup:
 	return err;
 }
 
-static int vic_open_channel(struct tegra_drm_client *client,
-			    struct tegra_drm_context *context)
+
+static int vic_runtime_resume(struct device *dev)
 {
-	struct vic *vic = to_vic(client);
+	struct vic *vic = dev_get_drvdata(dev);
 	int err;
 
-	err = pm_runtime_resume_and_get(vic->dev);
+	err = clk_prepare_enable(vic->clk);
 	if (err < 0)
 		return err;
 
+	usleep_range(10, 20);
+
+	err = reset_control_deassert(vic->rst);
+	if (err < 0)
+		goto disable;
+
+	usleep_range(10, 20);
+
 	err = vic_load_firmware(vic);
 	if (err < 0)
-		goto rpm_put;
+		goto assert;
 
 	err = vic_boot(vic);
 	if (err < 0)
-		goto rpm_put;
+		goto assert;
+
+	return 0;
+
+assert:
+	reset_control_assert(vic->rst);
+disable:
+	clk_disable_unprepare(vic->clk);
+	return err;
+}
+
+static int vic_runtime_suspend(struct device *dev)
+{
+	struct vic *vic = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_assert(vic->rst);
+	if (err < 0)
+		return err;
+
+	usleep_range(2000, 4000);
+
+	clk_disable_unprepare(vic->clk);
+
+	return 0;
+}
+
+static int vic_open_channel(struct tegra_drm_client *client,
+			    struct tegra_drm_context *context)
+{
+	struct vic *vic = to_vic(client);
+	int err;
+
+	err = pm_runtime_resume_and_get(vic->dev);
+	if (err < 0)
+		return err;
 
 	context->channel = host1x_channel_get(vic->channel);
 	if (!context->channel) {
-		err = -ENOMEM;
-		goto rpm_put;
+		pm_runtime_put(vic->dev);
+		return -ENOMEM;
 	}
 
 	return 0;
-
-rpm_put:
-	pm_runtime_put(vic->dev);
-	return err;
 }
 
 static void vic_close_channel(struct tegra_drm_context *context)
@@ -359,7 +350,6 @@ static void vic_close_channel(struct tegra_drm_context *context)
 	struct vic *vic = to_vic(context->client);
 
 	host1x_channel_put(context->channel);
-
 	pm_runtime_put(vic->dev);
 }
 
diff --git a/drivers/gpu/drm/tidss/tidss_drv.c b/drivers/gpu/drm/tidss/tidss_drv.c
index 66e3c86eb5c7..d620f35688da 100644
--- a/drivers/gpu/drm/tidss/tidss_drv.c
+++ b/drivers/gpu/drm/tidss/tidss_drv.c
@@ -16,7 +16,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_probe_helper.h>
 
@@ -118,11 +117,6 @@ static const struct drm_driver tidss_driver = {
 	.date			= "20180215",
 	.major			= 1,
 	.minor			= 0,
-
-	.irq_preinstall		= tidss_irq_preinstall,
-	.irq_postinstall	= tidss_irq_postinstall,
-	.irq_handler		= tidss_irq_handler,
-	.irq_uninstall		= tidss_irq_uninstall,
 };
 
 static int tidss_probe(struct platform_device *pdev)
@@ -172,10 +166,11 @@ static int tidss_probe(struct platform_device *pdev)
 		ret = irq;
 		goto err_runtime_suspend;
 	}
+	tidss->irq = irq;
 
-	ret = drm_irq_install(ddev, irq);
+	ret = tidss_irq_install(ddev, irq);
 	if (ret) {
-		dev_err(dev, "drm_irq_install failed: %d\n", ret);
+		dev_err(dev, "tidss_irq_install failed: %d\n", ret);
 		goto err_runtime_suspend;
 	}
 
@@ -196,7 +191,7 @@ static int tidss_probe(struct platform_device *pdev)
 	return 0;
 
 err_irq_uninstall:
-	drm_irq_uninstall(ddev);
+	tidss_irq_uninstall(ddev);
 
 err_runtime_suspend:
 #ifndef CONFIG_PM
@@ -219,7 +214,7 @@ static int tidss_remove(struct platform_device *pdev)
 
 	drm_atomic_helper_shutdown(ddev);
 
-	drm_irq_uninstall(ddev);
+	tidss_irq_uninstall(ddev);
 
 #ifndef CONFIG_PM
 	/* If we don't have PM, we need to call suspend manually */
diff --git a/drivers/gpu/drm/tidss/tidss_drv.h b/drivers/gpu/drm/tidss/tidss_drv.h
index 7de4bba52e6f..d7f27b0b0315 100644
--- a/drivers/gpu/drm/tidss/tidss_drv.h
+++ b/drivers/gpu/drm/tidss/tidss_drv.h
@@ -27,6 +27,8 @@ struct tidss_device {
 	unsigned int num_planes;
 	struct drm_plane *planes[TIDSS_MAX_PLANES];
 
+	unsigned int irq;
+
 	spinlock_t wait_lock;	/* protects the irq masks */
 	dispc_irq_t irq_mask;	/* enabled irqs in addition to wait_list */
 };
diff --git a/drivers/gpu/drm/tidss/tidss_irq.c b/drivers/gpu/drm/tidss/tidss_irq.c
index a5ec7931ef6b..0c681c7600bc 100644
--- a/drivers/gpu/drm/tidss/tidss_irq.c
+++ b/drivers/gpu/drm/tidss/tidss_irq.c
@@ -4,6 +4,9 @@
  * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  */
 
+#include <linux/platform_device.h>
+
+#include <drm/drm_drv.h>
 #include <drm/drm_print.h>
 
 #include "tidss_crtc.h"
@@ -50,16 +53,13 @@ void tidss_irq_disable_vblank(struct drm_crtc *crtc)
 	spin_unlock_irqrestore(&tidss->wait_lock, flags);
 }
 
-irqreturn_t tidss_irq_handler(int irq, void *arg)
+static irqreturn_t tidss_irq_handler(int irq, void *arg)
 {
 	struct drm_device *ddev = (struct drm_device *)arg;
 	struct tidss_device *tidss = to_tidss(ddev);
 	unsigned int id;
 	dispc_irq_t irqstatus;
 
-	if (WARN_ON(!ddev->irq_enabled))
-		return IRQ_NONE;
-
 	irqstatus = dispc_read_and_clear_irqstatus(tidss->dispc);
 
 	for (id = 0; id < tidss->num_crtcs; id++) {
@@ -93,7 +93,7 @@ void tidss_irq_resume(struct tidss_device *tidss)
 	spin_unlock_irqrestore(&tidss->wait_lock, flags);
 }
 
-void tidss_irq_preinstall(struct drm_device *ddev)
+static void tidss_irq_preinstall(struct drm_device *ddev)
 {
 	struct tidss_device *tidss = to_tidss(ddev);
 
@@ -107,7 +107,7 @@ void tidss_irq_preinstall(struct drm_device *ddev)
 	tidss_runtime_put(tidss);
 }
 
-int tidss_irq_postinstall(struct drm_device *ddev)
+static void tidss_irq_postinstall(struct drm_device *ddev)
 {
 	struct tidss_device *tidss = to_tidss(ddev);
 	unsigned long flags;
@@ -132,6 +132,22 @@ int tidss_irq_postinstall(struct drm_device *ddev)
 	spin_unlock_irqrestore(&tidss->wait_lock, flags);
 
 	tidss_runtime_put(tidss);
+}
+
+int tidss_irq_install(struct drm_device *ddev, unsigned int irq)
+{
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	tidss_irq_preinstall(ddev);
+
+	ret = request_irq(irq, tidss_irq_handler, 0, ddev->driver->name, ddev);
+	if (ret)
+		return ret;
+
+	tidss_irq_postinstall(ddev);
 
 	return 0;
 }
@@ -143,4 +159,6 @@ void tidss_irq_uninstall(struct drm_device *ddev)
 	tidss_runtime_get(tidss);
 	dispc_set_irqenable(tidss->dispc, 0);
 	tidss_runtime_put(tidss);
+
+	free_irq(tidss->irq, ddev);
 }
diff --git a/drivers/gpu/drm/tidss/tidss_irq.h b/drivers/gpu/drm/tidss/tidss_irq.h
index 4aaad5dfd7c2..b512614d5863 100644
--- a/drivers/gpu/drm/tidss/tidss_irq.h
+++ b/drivers/gpu/drm/tidss/tidss_irq.h
@@ -67,10 +67,8 @@ struct tidss_device;
 void tidss_irq_enable_vblank(struct drm_crtc *crtc);
 void tidss_irq_disable_vblank(struct drm_crtc *crtc);
 
-void tidss_irq_preinstall(struct drm_device *ddev);
-int tidss_irq_postinstall(struct drm_device *ddev);
+int tidss_irq_install(struct drm_device *ddev, unsigned int irq);
 void tidss_irq_uninstall(struct drm_device *ddev);
-irqreturn_t tidss_irq_handler(int irq, void *arg);
 
 void tidss_irq_resume(struct tidss_device *tidss);
 
diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c
index 95f8e0f78e32..666e527a0acf 100644
--- a/drivers/gpu/drm/tidss/tidss_kms.c
+++ b/drivers/gpu/drm/tidss/tidss_kms.c
@@ -227,10 +227,8 @@ static int tidss_dispc_modeset_init(struct tidss_device *tidss)
 		}
 
 		ret = drm_bridge_attach(enc, pipes[i].bridge, NULL, 0);
-		if (ret) {
-			dev_err(tidss->dev, "bridge attach failed: %d\n", ret);
+		if (ret)
 			return ret;
-		}
 	}
 
 	/* create overlay planes of the leftover planes */
diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c
index 1acd15aa4193..217415ec8eea 100644
--- a/drivers/gpu/drm/tidss/tidss_plane.c
+++ b/drivers/gpu/drm/tidss/tidss_plane.c
@@ -158,7 +158,6 @@ static void drm_plane_destroy(struct drm_plane *plane)
 }
 
 static const struct drm_plane_helper_funcs tidss_plane_helper_funcs = {
-	.prepare_fb = drm_gem_plane_helper_prepare_fb,
 	.atomic_check = tidss_plane_atomic_check,
 	.atomic_update = tidss_plane_atomic_update,
 	.atomic_disable = tidss_plane_atomic_disable,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index f1d3a9f919fd..6b03f89a98d4 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -20,7 +20,6 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_mm.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -124,6 +123,39 @@ static int cpufreq_transition(struct notifier_block *nb,
 }
 #endif
 
+static irqreturn_t tilcdc_irq(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct tilcdc_drm_private *priv = dev->dev_private;
+
+	return tilcdc_crtc_irq(priv->crtc);
+}
+
+static int tilcdc_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	struct tilcdc_drm_private *priv = dev->dev_private;
+	int ret;
+
+	ret = request_irq(irq, tilcdc_irq, 0, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	priv->irq_enabled = false;
+
+	return 0;
+}
+
+static void tilcdc_irq_uninstall(struct drm_device *dev)
+{
+	struct tilcdc_drm_private *priv = dev->dev_private;
+
+	if (!priv->irq_enabled)
+		return;
+
+	free_irq(priv->irq, dev);
+	priv->irq_enabled = false;
+}
+
 /*
  * DRM operations:
  */
@@ -145,7 +177,7 @@ static void tilcdc_fini(struct drm_device *dev)
 		drm_dev_unregister(dev);
 
 	drm_kms_helper_poll_fini(dev);
-	drm_irq_uninstall(dev);
+	tilcdc_irq_uninstall(dev);
 	drm_mode_config_cleanup(dev);
 
 	if (priv->clk)
@@ -336,7 +368,12 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev)
 		goto init_failed;
 	}
 
-	ret = drm_irq_install(ddev, platform_get_irq(pdev, 0));
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto init_failed;
+	priv->irq = ret;
+
+	ret = tilcdc_irq_install(ddev, priv->irq);
 	if (ret < 0) {
 		dev_err(dev, "failed to install IRQ handler\n");
 		goto init_failed;
@@ -360,13 +397,6 @@ init_failed:
 	return ret;
 }
 
-static irqreturn_t tilcdc_irq(int irq, void *arg)
-{
-	struct drm_device *dev = arg;
-	struct tilcdc_drm_private *priv = dev->dev_private;
-	return tilcdc_crtc_irq(priv->crtc);
-}
-
 #if defined(CONFIG_DEBUG_FS)
 static const struct {
 	const char *name;
@@ -454,7 +484,6 @@ DEFINE_DRM_GEM_CMA_FOPS(fops);
 
 static const struct drm_driver tilcdc_driver = {
 	.driver_features    = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
-	.irq_handler        = tilcdc_irq,
 	DRM_GEM_CMA_DRIVER_OPS,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = tilcdc_debugfs_init,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.h b/drivers/gpu/drm/tilcdc/tilcdc_drv.h
index d29806ca8817..b818448c83f6 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.h
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.h
@@ -46,6 +46,8 @@ struct tilcdc_drm_private {
 	struct clk *clk;         /* functional clock */
 	int rev;                 /* IP revision */
 
+	unsigned int irq;
+
 	/* don't attempt resolutions w/ higher W * H * Hz: */
 	uint32_t max_bandwidth;
 	/*
@@ -82,6 +84,7 @@ struct tilcdc_drm_private {
 
 	bool is_registered;
 	bool is_componentized;
+	bool irq_enabled;
 };
 
 /* Sub-module for display.  Since we don't know at compile time what panels
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_external.c b/drivers/gpu/drm/tilcdc/tilcdc_external.c
index b177525588c1..7594cf6e186e 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_external.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_external.c
@@ -93,10 +93,8 @@ int tilcdc_attach_bridge(struct drm_device *ddev, struct drm_bridge *bridge)
 	priv->external_encoder->possible_crtcs = BIT(0);
 
 	ret = drm_bridge_attach(priv->external_encoder, bridge, NULL, 0);
-	if (ret) {
-		dev_err(ddev->dev, "drm_bridge_attach() failed %d\n", ret);
+	if (ret)
 		return ret;
-	}
 
 	tilcdc_crtc_set_panel_info(priv->crtc, &panel_info_default);
 
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index d46f95d9196d..d31be274a2bd 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -10,6 +10,19 @@ config DRM_ARCPGU
 
 	  If M is selected the module will be called arcpgu.
 
+config DRM_BOCHS
+	tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
+	depends on DRM && PCI && MMU
+	select DRM_KMS_HELPER
+	select DRM_VRAM_HELPER
+	select DRM_TTM
+	select DRM_TTM_HELPER
+	help
+	  This is a KMS driver for qemu's stdvga output. Choose this option
+	  for qemu.
+
+	  If M is selected the module will be called bochs.
+
 config DRM_CIRRUS_QEMU
 	tristate "Cirrus driver for QEMU emulated device"
 	depends on DRM && PCI && MMU
@@ -51,8 +64,8 @@ config DRM_SIMPLEDRM
 	  buffer, size, and display format must be provided via device tree,
 	  UEFI, VESA, etc.
 
-	  On x86 and compatible, you should also select CONFIG_X86_SYSFB to
-	  use UEFI and VESA framebuffers.
+	  On x86 BIOS or UEFI systems, you should also select SYSFB_SIMPLEFB
+	  to use UEFI and VESA framebuffers.
 
 config TINYDRM_HX8357D
 	tristate "DRM support for HX8357D display panels"
diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile
index 9cc847e756da..e09942895c77 100644
--- a/drivers/gpu/drm/tiny/Makefile
+++ b/drivers/gpu/drm/tiny/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 obj-$(CONFIG_DRM_ARCPGU)		+= arcpgu.o
+obj-$(CONFIG_DRM_BOCHS)			+= bochs.o
 obj-$(CONFIG_DRM_CIRRUS_QEMU)		+= cirrus.o
 obj-$(CONFIG_DRM_GM12U320)		+= gm12u320.o
 obj-$(CONFIG_DRM_SIMPLEDRM)		+= simpledrm.o
diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
new file mode 100644
index 000000000000..73415fa9ae0f
--- /dev/null
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -0,0 +1,733 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/console.h>
+#include <linux/pci.h>
+
+#include <drm/drm_aperture.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_gem_vram_helper.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+
+#include <video/vga.h>
+
+/* ---------------------------------------------------------------------- */
+
+#define VBE_DISPI_IOPORT_INDEX           0x01CE
+#define VBE_DISPI_IOPORT_DATA            0x01CF
+
+#define VBE_DISPI_INDEX_ID               0x0
+#define VBE_DISPI_INDEX_XRES             0x1
+#define VBE_DISPI_INDEX_YRES             0x2
+#define VBE_DISPI_INDEX_BPP              0x3
+#define VBE_DISPI_INDEX_ENABLE           0x4
+#define VBE_DISPI_INDEX_BANK             0x5
+#define VBE_DISPI_INDEX_VIRT_WIDTH       0x6
+#define VBE_DISPI_INDEX_VIRT_HEIGHT      0x7
+#define VBE_DISPI_INDEX_X_OFFSET         0x8
+#define VBE_DISPI_INDEX_Y_OFFSET         0x9
+#define VBE_DISPI_INDEX_VIDEO_MEMORY_64K 0xa
+
+#define VBE_DISPI_ID0                    0xB0C0
+#define VBE_DISPI_ID1                    0xB0C1
+#define VBE_DISPI_ID2                    0xB0C2
+#define VBE_DISPI_ID3                    0xB0C3
+#define VBE_DISPI_ID4                    0xB0C4
+#define VBE_DISPI_ID5                    0xB0C5
+
+#define VBE_DISPI_DISABLED               0x00
+#define VBE_DISPI_ENABLED                0x01
+#define VBE_DISPI_GETCAPS                0x02
+#define VBE_DISPI_8BIT_DAC               0x20
+#define VBE_DISPI_LFB_ENABLED            0x40
+#define VBE_DISPI_NOCLEARMEM             0x80
+
+static int bochs_modeset = -1;
+static int defx = 1024;
+static int defy = 768;
+
+module_param_named(modeset, bochs_modeset, int, 0444);
+MODULE_PARM_DESC(modeset, "enable/disable kernel modesetting");
+
+module_param(defx, int, 0444);
+module_param(defy, int, 0444);
+MODULE_PARM_DESC(defx, "default x resolution");
+MODULE_PARM_DESC(defy, "default y resolution");
+
+/* ---------------------------------------------------------------------- */
+
+enum bochs_types {
+	BOCHS_QEMU_STDVGA,
+	BOCHS_UNKNOWN,
+};
+
+struct bochs_device {
+	/* hw */
+	void __iomem   *mmio;
+	int            ioports;
+	void __iomem   *fb_map;
+	unsigned long  fb_base;
+	unsigned long  fb_size;
+	unsigned long  qext_size;
+
+	/* mode */
+	u16 xres;
+	u16 yres;
+	u16 yres_virtual;
+	u32 stride;
+	u32 bpp;
+	struct edid *edid;
+
+	/* drm */
+	struct drm_device *dev;
+	struct drm_simple_display_pipe pipe;
+	struct drm_connector connector;
+};
+
+/* ---------------------------------------------------------------------- */
+
+static void bochs_vga_writeb(struct bochs_device *bochs, u16 ioport, u8 val)
+{
+	if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df))
+		return;
+
+	if (bochs->mmio) {
+		int offset = ioport - 0x3c0 + 0x400;
+
+		writeb(val, bochs->mmio + offset);
+	} else {
+		outb(val, ioport);
+	}
+}
+
+static u8 bochs_vga_readb(struct bochs_device *bochs, u16 ioport)
+{
+	if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df))
+		return 0xff;
+
+	if (bochs->mmio) {
+		int offset = ioport - 0x3c0 + 0x400;
+
+		return readb(bochs->mmio + offset);
+	} else {
+		return inb(ioport);
+	}
+}
+
+static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg)
+{
+	u16 ret = 0;
+
+	if (bochs->mmio) {
+		int offset = 0x500 + (reg << 1);
+
+		ret = readw(bochs->mmio + offset);
+	} else {
+		outw(reg, VBE_DISPI_IOPORT_INDEX);
+		ret = inw(VBE_DISPI_IOPORT_DATA);
+	}
+	return ret;
+}
+
+static void bochs_dispi_write(struct bochs_device *bochs, u16 reg, u16 val)
+{
+	if (bochs->mmio) {
+		int offset = 0x500 + (reg << 1);
+
+		writew(val, bochs->mmio + offset);
+	} else {
+		outw(reg, VBE_DISPI_IOPORT_INDEX);
+		outw(val, VBE_DISPI_IOPORT_DATA);
+	}
+}
+
+static void bochs_hw_set_big_endian(struct bochs_device *bochs)
+{
+	if (bochs->qext_size < 8)
+		return;
+
+	writel(0xbebebebe, bochs->mmio + 0x604);
+}
+
+static void bochs_hw_set_little_endian(struct bochs_device *bochs)
+{
+	if (bochs->qext_size < 8)
+		return;
+
+	writel(0x1e1e1e1e, bochs->mmio + 0x604);
+}
+
+#ifdef __BIG_ENDIAN
+#define bochs_hw_set_native_endian(_b) bochs_hw_set_big_endian(_b)
+#else
+#define bochs_hw_set_native_endian(_b) bochs_hw_set_little_endian(_b)
+#endif
+
+static int bochs_get_edid_block(void *data, u8 *buf,
+				unsigned int block, size_t len)
+{
+	struct bochs_device *bochs = data;
+	size_t i, start = block * EDID_LENGTH;
+
+	if (start + len > 0x400 /* vga register offset */)
+		return -1;
+
+	for (i = 0; i < len; i++)
+		buf[i] = readb(bochs->mmio + start + i);
+
+	return 0;
+}
+
+static int bochs_hw_load_edid(struct bochs_device *bochs)
+{
+	u8 header[8];
+
+	if (!bochs->mmio)
+		return -1;
+
+	/* check header to detect whenever edid support is enabled in qemu */
+	bochs_get_edid_block(bochs, header, 0, ARRAY_SIZE(header));
+	if (drm_edid_header_is_valid(header) != 8)
+		return -1;
+
+	kfree(bochs->edid);
+	bochs->edid = drm_do_get_edid(&bochs->connector,
+				      bochs_get_edid_block, bochs);
+	if (bochs->edid == NULL)
+		return -1;
+
+	return 0;
+}
+
+static int bochs_hw_init(struct drm_device *dev)
+{
+	struct bochs_device *bochs = dev->dev_private;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	unsigned long addr, size, mem, ioaddr, iosize;
+	u16 id;
+
+	if (pdev->resource[2].flags & IORESOURCE_MEM) {
+		/* mmio bar with vga and bochs registers present */
+		if (pci_request_region(pdev, 2, "bochs-drm") != 0) {
+			DRM_ERROR("Cannot request mmio region\n");
+			return -EBUSY;
+		}
+		ioaddr = pci_resource_start(pdev, 2);
+		iosize = pci_resource_len(pdev, 2);
+		bochs->mmio = ioremap(ioaddr, iosize);
+		if (bochs->mmio == NULL) {
+			DRM_ERROR("Cannot map mmio region\n");
+			return -ENOMEM;
+		}
+	} else {
+		ioaddr = VBE_DISPI_IOPORT_INDEX;
+		iosize = 2;
+		if (!request_region(ioaddr, iosize, "bochs-drm")) {
+			DRM_ERROR("Cannot request ioports\n");
+			return -EBUSY;
+		}
+		bochs->ioports = 1;
+	}
+
+	id = bochs_dispi_read(bochs, VBE_DISPI_INDEX_ID);
+	mem = bochs_dispi_read(bochs, VBE_DISPI_INDEX_VIDEO_MEMORY_64K)
+		* 64 * 1024;
+	if ((id & 0xfff0) != VBE_DISPI_ID0) {
+		DRM_ERROR("ID mismatch\n");
+		return -ENODEV;
+	}
+
+	if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0)
+		return -ENODEV;
+	addr = pci_resource_start(pdev, 0);
+	size = pci_resource_len(pdev, 0);
+	if (addr == 0)
+		return -ENODEV;
+	if (size != mem) {
+		DRM_ERROR("Size mismatch: pci=%ld, bochs=%ld\n",
+			size, mem);
+		size = min(size, mem);
+	}
+
+	if (pci_request_region(pdev, 0, "bochs-drm") != 0)
+		DRM_WARN("Cannot request framebuffer, boot fb still active?\n");
+
+	bochs->fb_map = ioremap(addr, size);
+	if (bochs->fb_map == NULL) {
+		DRM_ERROR("Cannot map framebuffer\n");
+		return -ENOMEM;
+	}
+	bochs->fb_base = addr;
+	bochs->fb_size = size;
+
+	DRM_INFO("Found bochs VGA, ID 0x%x.\n", id);
+	DRM_INFO("Framebuffer size %ld kB @ 0x%lx, %s @ 0x%lx.\n",
+		 size / 1024, addr,
+		 bochs->ioports ? "ioports" : "mmio",
+		 ioaddr);
+
+	if (bochs->mmio && pdev->revision >= 2) {
+		bochs->qext_size = readl(bochs->mmio + 0x600);
+		if (bochs->qext_size < 4 || bochs->qext_size > iosize) {
+			bochs->qext_size = 0;
+			goto noext;
+		}
+		DRM_DEBUG("Found qemu ext regs, size %ld\n",
+			  bochs->qext_size);
+		bochs_hw_set_native_endian(bochs);
+	}
+
+noext:
+	return 0;
+}
+
+static void bochs_hw_fini(struct drm_device *dev)
+{
+	struct bochs_device *bochs = dev->dev_private;
+
+	/* TODO: shot down existing vram mappings */
+
+	if (bochs->mmio)
+		iounmap(bochs->mmio);
+	if (bochs->ioports)
+		release_region(VBE_DISPI_IOPORT_INDEX, 2);
+	if (bochs->fb_map)
+		iounmap(bochs->fb_map);
+	pci_release_regions(to_pci_dev(dev->dev));
+	kfree(bochs->edid);
+}
+
+static void bochs_hw_blank(struct bochs_device *bochs, bool blank)
+{
+	DRM_DEBUG_DRIVER("hw_blank %d\n", blank);
+	/* discard ar_flip_flop */
+	(void)bochs_vga_readb(bochs, VGA_IS1_RC);
+	/* blank or unblank; we need only update index and set 0x20 */
+	bochs_vga_writeb(bochs, VGA_ATT_W, blank ? 0 : 0x20);
+}
+
+static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode *mode)
+{
+	int idx;
+
+	if (!drm_dev_enter(bochs->dev, &idx))
+		return;
+
+	bochs->xres = mode->hdisplay;
+	bochs->yres = mode->vdisplay;
+	bochs->bpp = 32;
+	bochs->stride = mode->hdisplay * (bochs->bpp / 8);
+	bochs->yres_virtual = bochs->fb_size / bochs->stride;
+
+	DRM_DEBUG_DRIVER("%dx%d @ %d bpp, vy %d\n",
+			 bochs->xres, bochs->yres, bochs->bpp,
+			 bochs->yres_virtual);
+
+	bochs_hw_blank(bochs, false);
+
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,      0);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP,         bochs->bpp);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES,        bochs->xres);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_YRES,        bochs->yres);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BANK,        0);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH,  bochs->xres);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_HEIGHT,
+			  bochs->yres_virtual);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET,    0);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET,    0);
+
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,
+			  VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED);
+
+	drm_dev_exit(idx);
+}
+
+static void bochs_hw_setformat(struct bochs_device *bochs, const struct drm_format_info *format)
+{
+	int idx;
+
+	if (!drm_dev_enter(bochs->dev, &idx))
+		return;
+
+	DRM_DEBUG_DRIVER("format %c%c%c%c\n",
+			 (format->format >>  0) & 0xff,
+			 (format->format >>  8) & 0xff,
+			 (format->format >> 16) & 0xff,
+			 (format->format >> 24) & 0xff);
+
+	switch (format->format) {
+	case DRM_FORMAT_XRGB8888:
+		bochs_hw_set_little_endian(bochs);
+		break;
+	case DRM_FORMAT_BGRX8888:
+		bochs_hw_set_big_endian(bochs);
+		break;
+	default:
+		/* should not happen */
+		DRM_ERROR("%s: Huh? Got framebuffer format 0x%x",
+			  __func__, format->format);
+		break;
+	}
+
+	drm_dev_exit(idx);
+}
+
+static void bochs_hw_setbase(struct bochs_device *bochs, int x, int y, int stride, u64 addr)
+{
+	unsigned long offset;
+	unsigned int vx, vy, vwidth, idx;
+
+	if (!drm_dev_enter(bochs->dev, &idx))
+		return;
+
+	bochs->stride = stride;
+	offset = (unsigned long)addr +
+		y * bochs->stride +
+		x * (bochs->bpp / 8);
+	vy = offset / bochs->stride;
+	vx = (offset % bochs->stride) * 8 / bochs->bpp;
+	vwidth = stride * 8 / bochs->bpp;
+
+	DRM_DEBUG_DRIVER("x %d, y %d, addr %llx -> offset %lx, vx %d, vy %d\n",
+			 x, y, addr, offset, vx, vy);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx);
+	bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy);
+
+	drm_dev_exit(idx);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static const uint32_t bochs_formats[] = {
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_BGRX8888,
+};
+
+static void bochs_plane_update(struct bochs_device *bochs, struct drm_plane_state *state)
+{
+	struct drm_gem_vram_object *gbo;
+	s64 gpu_addr;
+
+	if (!state->fb || !bochs->stride)
+		return;
+
+	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
+	gpu_addr = drm_gem_vram_offset(gbo);
+	if (WARN_ON_ONCE(gpu_addr < 0))
+		return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
+
+	bochs_hw_setbase(bochs,
+			 state->crtc_x,
+			 state->crtc_y,
+			 state->fb->pitches[0],
+			 state->fb->offsets[0] + gpu_addr);
+	bochs_hw_setformat(bochs, state->fb->format);
+}
+
+static void bochs_pipe_enable(struct drm_simple_display_pipe *pipe,
+			      struct drm_crtc_state *crtc_state,
+			      struct drm_plane_state *plane_state)
+{
+	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
+
+	bochs_hw_setmode(bochs, &crtc_state->mode);
+	bochs_plane_update(bochs, plane_state);
+}
+
+static void bochs_pipe_disable(struct drm_simple_display_pipe *pipe)
+{
+	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
+
+	bochs_hw_blank(bochs, true);
+}
+
+static void bochs_pipe_update(struct drm_simple_display_pipe *pipe,
+			      struct drm_plane_state *old_state)
+{
+	struct bochs_device *bochs = pipe->crtc.dev->dev_private;
+
+	bochs_plane_update(bochs, pipe->plane.state);
+}
+
+static const struct drm_simple_display_pipe_funcs bochs_pipe_funcs = {
+	.enable	    = bochs_pipe_enable,
+	.disable    = bochs_pipe_disable,
+	.update	    = bochs_pipe_update,
+	.prepare_fb = drm_gem_vram_simple_display_pipe_prepare_fb,
+	.cleanup_fb = drm_gem_vram_simple_display_pipe_cleanup_fb,
+};
+
+static int bochs_connector_get_modes(struct drm_connector *connector)
+{
+	struct bochs_device *bochs =
+		container_of(connector, struct bochs_device, connector);
+	int count = 0;
+
+	if (bochs->edid)
+		count = drm_add_edid_modes(connector, bochs->edid);
+
+	if (!count) {
+		count = drm_add_modes_noedid(connector, 8192, 8192);
+		drm_set_preferred_mode(connector, defx, defy);
+	}
+	return count;
+}
+
+static const struct drm_connector_helper_funcs bochs_connector_connector_helper_funcs = {
+	.get_modes = bochs_connector_get_modes,
+};
+
+static const struct drm_connector_funcs bochs_connector_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static void bochs_connector_init(struct drm_device *dev)
+{
+	struct bochs_device *bochs = dev->dev_private;
+	struct drm_connector *connector = &bochs->connector;
+
+	drm_connector_init(dev, connector, &bochs_connector_connector_funcs,
+			   DRM_MODE_CONNECTOR_VIRTUAL);
+	drm_connector_helper_add(connector, &bochs_connector_connector_helper_funcs);
+
+	bochs_hw_load_edid(bochs);
+	if (bochs->edid) {
+		DRM_INFO("Found EDID data blob.\n");
+		drm_connector_attach_edid_property(connector);
+		drm_connector_update_edid_property(connector, bochs->edid);
+	}
+}
+
+static struct drm_framebuffer *
+bochs_gem_fb_create(struct drm_device *dev, struct drm_file *file,
+		    const struct drm_mode_fb_cmd2 *mode_cmd)
+{
+	if (mode_cmd->pixel_format != DRM_FORMAT_XRGB8888 &&
+	    mode_cmd->pixel_format != DRM_FORMAT_BGRX8888)
+		return ERR_PTR(-EINVAL);
+
+	return drm_gem_fb_create(dev, file, mode_cmd);
+}
+
+static const struct drm_mode_config_funcs bochs_mode_funcs = {
+	.fb_create = bochs_gem_fb_create,
+	.mode_valid = drm_vram_helper_mode_valid,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int bochs_kms_init(struct bochs_device *bochs)
+{
+	int ret;
+
+	ret = drmm_mode_config_init(bochs->dev);
+	if (ret)
+		return ret;
+
+	bochs->dev->mode_config.max_width = 8192;
+	bochs->dev->mode_config.max_height = 8192;
+
+	bochs->dev->mode_config.fb_base = bochs->fb_base;
+	bochs->dev->mode_config.preferred_depth = 24;
+	bochs->dev->mode_config.prefer_shadow = 0;
+	bochs->dev->mode_config.prefer_shadow_fbdev = 1;
+	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
+
+	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
+
+	bochs_connector_init(bochs->dev);
+	drm_simple_display_pipe_init(bochs->dev,
+				     &bochs->pipe,
+				     &bochs_pipe_funcs,
+				     bochs_formats,
+				     ARRAY_SIZE(bochs_formats),
+				     NULL,
+				     &bochs->connector);
+
+	drm_mode_config_reset(bochs->dev);
+
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+/* drm interface                                                          */
+
+static int bochs_load(struct drm_device *dev)
+{
+	struct bochs_device *bochs;
+	int ret;
+
+	bochs = drmm_kzalloc(dev, sizeof(*bochs), GFP_KERNEL);
+	if (bochs == NULL)
+		return -ENOMEM;
+	dev->dev_private = bochs;
+	bochs->dev = dev;
+
+	ret = bochs_hw_init(dev);
+	if (ret)
+		return ret;
+
+	ret = drmm_vram_helper_init(dev, bochs->fb_base, bochs->fb_size);
+	if (ret)
+		return ret;
+
+	ret = bochs_kms_init(bochs);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+DEFINE_DRM_GEM_FOPS(bochs_fops);
+
+static const struct drm_driver bochs_driver = {
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
+	.fops			= &bochs_fops,
+	.name			= "bochs-drm",
+	.desc			= "bochs dispi vga interface (qemu stdvga)",
+	.date			= "20130925",
+	.major			= 1,
+	.minor			= 0,
+	DRM_GEM_VRAM_DRIVER,
+};
+
+/* ---------------------------------------------------------------------- */
+/* pm interface                                                           */
+
+#ifdef CONFIG_PM_SLEEP
+static int bochs_pm_suspend(struct device *dev)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+
+	return drm_mode_config_helper_suspend(drm_dev);
+}
+
+static int bochs_pm_resume(struct device *dev)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+
+	return drm_mode_config_helper_resume(drm_dev);
+}
+#endif
+
+static const struct dev_pm_ops bochs_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend,
+				bochs_pm_resume)
+};
+
+/* ---------------------------------------------------------------------- */
+/* pci interface                                                          */
+
+static int bochs_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct drm_device *dev;
+	unsigned long fbsize;
+	int ret;
+
+	fbsize = pci_resource_len(pdev, 0);
+	if (fbsize < 4 * 1024 * 1024) {
+		DRM_ERROR("less than 4 MB video memory, ignoring device\n");
+		return -ENOMEM;
+	}
+
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &bochs_driver);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&bochs_driver, &pdev->dev);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		goto err_free_dev;
+
+	pci_set_drvdata(pdev, dev);
+
+	ret = bochs_load(dev);
+	if (ret)
+		goto err_free_dev;
+
+	ret = drm_dev_register(dev, 0);
+	if (ret)
+		goto err_free_dev;
+
+	drm_fbdev_generic_setup(dev, 32);
+	return ret;
+
+err_free_dev:
+	drm_dev_put(dev);
+	return ret;
+}
+
+static void bochs_pci_remove(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	drm_dev_unplug(dev);
+	drm_atomic_helper_shutdown(dev);
+	bochs_hw_fini(dev);
+	drm_dev_put(dev);
+}
+
+static const struct pci_device_id bochs_pci_tbl[] = {
+	{
+		.vendor      = 0x1234,
+		.device      = 0x1111,
+		.subvendor   = PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
+		.subdevice   = PCI_SUBDEVICE_ID_QEMU,
+		.driver_data = BOCHS_QEMU_STDVGA,
+	},
+	{
+		.vendor      = 0x1234,
+		.device      = 0x1111,
+		.subvendor   = PCI_ANY_ID,
+		.subdevice   = PCI_ANY_ID,
+		.driver_data = BOCHS_UNKNOWN,
+	},
+	{ /* end of list */ }
+};
+
+static struct pci_driver bochs_pci_driver = {
+	.name =		"bochs-drm",
+	.id_table =	bochs_pci_tbl,
+	.probe =	bochs_pci_probe,
+	.remove =	bochs_pci_remove,
+	.driver.pm =    &bochs_pm_ops,
+};
+
+/* ---------------------------------------------------------------------- */
+/* module init/exit                                                       */
+
+static int __init bochs_init(void)
+{
+	if (vgacon_text_force() && bochs_modeset == -1)
+		return -EINVAL;
+
+	if (bochs_modeset == 0)
+		return -EINVAL;
+
+	return pci_register_driver(&bochs_pci_driver);
+}
+
+static void __exit bochs_exit(void)
+{
+	pci_unregister_driver(&bochs_pci_driver);
+}
+
+module_init(bochs_init);
+module_exit(bochs_exit);
+
+MODULE_DEVICE_TABLE(pci, bochs_pci_tbl);
+MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c
index 42611dacde88..4611ec408506 100644
--- a/drivers/gpu/drm/tiny/cirrus.c
+++ b/drivers/gpu/drm/tiny/cirrus.c
@@ -435,7 +435,7 @@ static void cirrus_pipe_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 
 	cirrus_mode_set(cirrus, &crtc_state->mode, plane_state->fb);
-	cirrus_fb_blit_fullscreen(plane_state->fb, &shadow_plane_state->map[0]);
+	cirrus_fb_blit_fullscreen(plane_state->fb, &shadow_plane_state->data[0]);
 }
 
 static void cirrus_pipe_update(struct drm_simple_display_pipe *pipe,
@@ -451,7 +451,7 @@ static void cirrus_pipe_update(struct drm_simple_display_pipe *pipe,
 		cirrus_mode_set(cirrus, &crtc->mode, state->fb);
 
 	if (drm_atomic_helper_damage_merged(old_state, state, &rect))
-		cirrus_fb_blit_rect(state->fb, &shadow_plane_state->map[0], &rect);
+		cirrus_fb_blit_rect(state->fb, &shadow_plane_state->data[0], &rect);
 }
 
 static const struct drm_simple_display_pipe_funcs cirrus_pipe_funcs = {
@@ -550,7 +550,7 @@ static int cirrus_pci_probe(struct pci_dev *pdev,
 	struct cirrus_device *cirrus;
 	int ret;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "cirrusdrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &cirrus_driver);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c
index a233c86d428b..6bc0c298739c 100644
--- a/drivers/gpu/drm/tiny/gm12u320.c
+++ b/drivers/gpu/drm/tiny/gm12u320.c
@@ -3,7 +3,6 @@
  * Copyright 2019 Hans de Goede <hdegoede@redhat.com>
  */
 
-#include <linux/dma-buf.h>
 #include <linux/module.h>
 #include <linux/usb.h>
 
@@ -268,13 +267,10 @@ static void gm12u320_copy_fb_to_blocks(struct gm12u320_device *gm12u320)
 	y2 = gm12u320->fb_update.rect.y2;
 	vaddr = gm12u320->fb_update.src_map.vaddr; /* TODO: Use mapping abstraction properly */
 
-	if (fb->obj[0]->import_attach) {
-		ret = dma_buf_begin_cpu_access(
-			fb->obj[0]->import_attach->dmabuf, DMA_FROM_DEVICE);
-		if (ret) {
-			GM12U320_ERR("dma_buf_begin_cpu_access err: %d\n", ret);
-			goto put_fb;
-		}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret) {
+		GM12U320_ERR("drm_gem_fb_begin_cpu_access err: %d\n", ret);
+		goto put_fb;
 	}
 
 	src = vaddr + y1 * fb->pitches[0] + x1 * 4;
@@ -311,12 +307,7 @@ static void gm12u320_copy_fb_to_blocks(struct gm12u320_device *gm12u320)
 		src += fb->pitches[0];
 	}
 
-	if (fb->obj[0]->import_attach) {
-		ret = dma_buf_end_cpu_access(fb->obj[0]->import_attach->dmabuf,
-					     DMA_FROM_DEVICE);
-		if (ret)
-			GM12U320_ERR("dma_buf_end_cpu_access err: %d\n", ret);
-	}
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 put_fb:
 	drm_framebuffer_put(fb);
 	gm12u320->fb_update.fb = NULL;
@@ -563,7 +554,7 @@ static void gm12u320_pipe_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 
 	gm12u320->fb_update.draw_status_timeout = FIRST_FRAME_TIMEOUT;
-	gm12u320_fb_mark_dirty(plane_state->fb, &shadow_plane_state->map[0], &rect);
+	gm12u320_fb_mark_dirty(plane_state->fb, &shadow_plane_state->data[0], &rect);
 }
 
 static void gm12u320_pipe_disable(struct drm_simple_display_pipe *pipe)
@@ -581,7 +572,7 @@ static void gm12u320_pipe_update(struct drm_simple_display_pipe *pipe,
 	struct drm_rect rect;
 
 	if (drm_atomic_helper_damage_merged(old_state, state, &rect))
-		gm12u320_fb_mark_dirty(state->fb, &shadow_plane_state->map[0], &rect);
+		gm12u320_fb_mark_dirty(state->fb, &shadow_plane_state->data[0], &rect);
 }
 
 static const struct drm_simple_display_pipe_funcs gm12u320_pipe_funcs = {
diff --git a/drivers/gpu/drm/tiny/hx8357d.c b/drivers/gpu/drm/tiny/hx8357d.c
index da5df93450de..9b33c05732aa 100644
--- a/drivers/gpu/drm/tiny/hx8357d.c
+++ b/drivers/gpu/drm/tiny/hx8357d.c
@@ -184,7 +184,6 @@ static const struct drm_simple_display_pipe_funcs hx8357d_pipe_funcs = {
 	.enable = yx240qv29_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = mipi_dbi_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode yx350hv15_mode = {
diff --git a/drivers/gpu/drm/tiny/ili9225.c b/drivers/gpu/drm/tiny/ili9225.c
index 69265d8a3beb..976d3209f164 100644
--- a/drivers/gpu/drm/tiny/ili9225.c
+++ b/drivers/gpu/drm/tiny/ili9225.c
@@ -328,7 +328,6 @@ static const struct drm_simple_display_pipe_funcs ili9225_pipe_funcs = {
 	.enable		= ili9225_pipe_enable,
 	.disable	= ili9225_pipe_disable,
 	.update		= ili9225_pipe_update,
-	.prepare_fb	= drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode ili9225_mode = {
diff --git a/drivers/gpu/drm/tiny/ili9341.c b/drivers/gpu/drm/tiny/ili9341.c
index ad9ce7b4f76f..37e0c33399c8 100644
--- a/drivers/gpu/drm/tiny/ili9341.c
+++ b/drivers/gpu/drm/tiny/ili9341.c
@@ -140,7 +140,6 @@ static const struct drm_simple_display_pipe_funcs ili9341_pipe_funcs = {
 	.enable = yx240qv29_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = mipi_dbi_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode yx240qv29_mode = {
diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c
index 75aa1476c66c..e9a63f4b2993 100644
--- a/drivers/gpu/drm/tiny/ili9486.c
+++ b/drivers/gpu/drm/tiny/ili9486.c
@@ -153,7 +153,6 @@ static const struct drm_simple_display_pipe_funcs waveshare_pipe_funcs = {
 	.enable = waveshare_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = mipi_dbi_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode waveshare_mode = {
diff --git a/drivers/gpu/drm/tiny/mi0283qt.c b/drivers/gpu/drm/tiny/mi0283qt.c
index 82fd1ad3413f..023de49e7a8e 100644
--- a/drivers/gpu/drm/tiny/mi0283qt.c
+++ b/drivers/gpu/drm/tiny/mi0283qt.c
@@ -144,7 +144,6 @@ static const struct drm_simple_display_pipe_funcs mi0283qt_pipe_funcs = {
 	.enable = mi0283qt_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = mipi_dbi_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode mi0283qt_mode = {
diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c
index 2cee07a2e00b..4d07b21a16e6 100644
--- a/drivers/gpu/drm/tiny/repaper.c
+++ b/drivers/gpu/drm/tiny/repaper.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-buf.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/property.h>
@@ -532,7 +531,6 @@ static void repaper_gray8_to_mono_reversed(u8 *buf, u32 width, u32 height)
 static int repaper_fb_dirty(struct drm_framebuffer *fb)
 {
 	struct drm_gem_cma_object *cma_obj = drm_fb_cma_get_gem_obj(fb, 0);
-	struct dma_buf_attachment *import_attach = cma_obj->base.import_attach;
 	struct repaper_epd *epd = drm_to_epd(fb->dev);
 	struct drm_rect clip;
 	int idx, ret = 0;
@@ -558,21 +556,13 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb)
 		goto out_exit;
 	}
 
-	if (import_attach) {
-		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
-					       DMA_FROM_DEVICE);
-		if (ret)
-			goto out_free;
-	}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret)
+		goto out_free;
 
 	drm_fb_xrgb8888_to_gray8(buf, cma_obj->vaddr, fb, &clip);
 
-	if (import_attach) {
-		ret = dma_buf_end_cpu_access(import_attach->dmabuf,
-					     DMA_FROM_DEVICE);
-		if (ret)
-			goto out_free;
-	}
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 
 	repaper_gray8_to_mono_reversed(buf, fb->width, fb->height);
 
@@ -861,7 +851,6 @@ static const struct drm_simple_display_pipe_funcs repaper_pipe_funcs = {
 	.enable = repaper_pipe_enable,
 	.disable = repaper_pipe_disable,
 	.update = repaper_pipe_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static int repaper_connector_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 08ae66b1e6f5..481b48bde047 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -639,7 +639,7 @@ simpledrm_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
 	struct simpledrm_device *sdev = simpledrm_device_of_dev(pipe->crtc.dev);
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 	struct drm_framebuffer *fb = plane_state->fb;
-	void *vmap = shadow_plane_state->map[0].vaddr; /* TODO: Use mapping abstraction properly */
+	void *vmap = shadow_plane_state->data[0].vaddr; /* TODO: Use mapping abstraction */
 	struct drm_device *dev = &sdev->dev;
 	int idx;
 
@@ -677,7 +677,7 @@ simpledrm_simple_display_pipe_update(struct drm_simple_display_pipe *pipe,
 	struct simpledrm_device *sdev = simpledrm_device_of_dev(pipe->crtc.dev);
 	struct drm_plane_state *plane_state = pipe->plane.state;
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
-	void *vmap = shadow_plane_state->map[0].vaddr; /* TODO: Use mapping abstraction properly */
+	void *vmap = shadow_plane_state->data[0].vaddr; /* TODO: Use mapping abstraction */
 	struct drm_framebuffer *fb = plane_state->fb;
 	struct drm_device *dev = &sdev->dev;
 	struct drm_rect clip;
diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c
index 05db980cc047..ad0faa8723c2 100644
--- a/drivers/gpu/drm/tiny/st7586.c
+++ b/drivers/gpu/drm/tiny/st7586.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-buf.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/property.h>
@@ -21,6 +20,7 @@
 #include <drm/drm_format_helper.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_mipi_dbi.h>
 #include <drm/drm_rect.h>
@@ -92,24 +92,18 @@ static int st7586_buf_copy(void *dst, struct drm_framebuffer *fb,
 			   struct drm_rect *clip)
 {
 	struct drm_gem_cma_object *cma_obj = drm_fb_cma_get_gem_obj(fb, 0);
-	struct dma_buf_attachment *import_attach = cma_obj->base.import_attach;
 	void *src = cma_obj->vaddr;
 	int ret = 0;
 
-	if (import_attach) {
-		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
-					       DMA_FROM_DEVICE);
-		if (ret)
-			return ret;
-	}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret)
+		return ret;
 
 	st7586_xrgb8888_to_gray332(dst, src, fb, clip);
 
-	if (import_attach)
-		ret = dma_buf_end_cpu_access(import_attach->dmabuf,
-					     DMA_FROM_DEVICE);
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 
-	return ret;
+	return 0;
 }
 
 static void st7586_fb_dirty(struct drm_framebuffer *fb, struct drm_rect *rect)
@@ -268,7 +262,6 @@ static const struct drm_simple_display_pipe_funcs st7586_pipe_funcs = {
 	.enable		= st7586_pipe_enable,
 	.disable	= st7586_pipe_disable,
 	.update		= st7586_pipe_update,
-	.prepare_fb	= drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode st7586_mode = {
diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c
index e8b7815d8cae..fc40dd10efa8 100644
--- a/drivers/gpu/drm/tiny/st7735r.c
+++ b/drivers/gpu/drm/tiny/st7735r.c
@@ -136,7 +136,6 @@ static const struct drm_simple_display_pipe_funcs st7735r_pipe_funcs = {
 	.enable		= st7735r_pipe_enable,
 	.disable	= mipi_dbi_pipe_disable,
 	.update		= mipi_dbi_pipe_update,
-	.prepare_fb	= drm_gem_simple_display_pipe_prepare_fb,
 };
 
 static const struct st7735r_cfg jd_t18003_t01_cfg = {
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d7fd65ccced..ea4add2b9717 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -488,6 +488,31 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_device *bdev, int resched)
 }
 EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue);
 
+static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
+				     struct ttm_resource **mem,
+				     struct ttm_operation_ctx *ctx,
+				     struct ttm_place *hop)
+{
+	struct ttm_placement hop_placement;
+	struct ttm_resource *hop_mem;
+	int ret;
+
+	hop_placement.num_placement = hop_placement.num_busy_placement = 1;
+	hop_placement.placement = hop_placement.busy_placement = hop;
+
+	/* find space in the bounce domain */
+	ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx);
+	if (ret)
+		return ret;
+	/* move to the bounce domain */
+	ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL);
+	if (ret) {
+		ttm_resource_free(bo, &hop_mem);
+		return ret;
+	}
+	return 0;
+}
+
 static int ttm_bo_evict(struct ttm_buffer_object *bo,
 			struct ttm_operation_ctx *ctx)
 {
@@ -527,12 +552,17 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 		goto out;
 	}
 
+bounce:
 	ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop);
-	if (unlikely(ret)) {
-		WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n");
-		if (ret != -ERESTARTSYS)
+	if (ret == -EMULTIHOP) {
+		ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop);
+		if (ret) {
 			pr_err("Buffer eviction failed\n");
-		ttm_resource_free(bo, &evict_mem);
+			ttm_resource_free(bo, &evict_mem);
+			goto out;
+		}
+		/* try and move to final place now. */
+		goto bounce;
 	}
 out:
 	return ret;
@@ -847,31 +877,6 @@ error:
 }
 EXPORT_SYMBOL(ttm_bo_mem_space);
 
-static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
-				     struct ttm_resource **mem,
-				     struct ttm_operation_ctx *ctx,
-				     struct ttm_place *hop)
-{
-	struct ttm_placement hop_placement;
-	struct ttm_resource *hop_mem;
-	int ret;
-
-	hop_placement.num_placement = hop_placement.num_busy_placement = 1;
-	hop_placement.placement = hop_placement.busy_placement = hop;
-
-	/* find space in the bounce domain */
-	ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx);
-	if (ret)
-		return ret;
-	/* move to the bounce domain */
-	ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL);
-	if (ret) {
-		ttm_resource_free(bo, &hop_mem);
-		return ret;
-	}
-	return 0;
-}
-
 static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 			      struct ttm_placement *placement,
 			      struct ttm_operation_ctx *ctx)
@@ -916,6 +921,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places,
 {
 	unsigned i;
 
+	if (mem->placement & TTM_PL_FLAG_TEMPORARY)
+		return false;
+
 	for (i = 0; i < num_placement; i++) {
 		const struct ttm_place *heap = &places[i];
 
diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c
index 50e1fb71869f..17b8c8dd169d 100644
--- a/drivers/gpu/drm/tve200/tve200_display.c
+++ b/drivers/gpu/drm/tve200/tve200_display.c
@@ -316,7 +316,6 @@ static const struct drm_simple_display_pipe_funcs tve200_display_funcs = {
 	.enable = tve200_display_enable,
 	.disable = tve200_display_disable,
 	.update = tve200_display_update,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 	.enable_vblank = tve200_display_enable_vblank,
 	.disable_vblank = tve200_display_disable_vblank,
 };
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index 8d98bf69d075..32232228dae9 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -6,11 +6,8 @@
  * Copyright (C) 2009 Roberto De Ioris <roberto@unbit.it>
  * Copyright (C) 2009 Jaya Kumar <jayakumar.lkml@gmail.com>
  * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com>
-
  */
 
-#include <linux/dma-buf.h>
-
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_damage_helper.h>
@@ -271,9 +268,8 @@ static int udl_handle_damage(struct drm_framebuffer *fb, const struct dma_buf_ma
 			     int x, int y, int width, int height)
 {
 	struct drm_device *dev = fb->dev;
-	struct dma_buf_attachment *import_attach = fb->obj[0]->import_attach;
 	void *vaddr = map->vaddr; /* TODO: Use mapping abstraction properly */
-	int i, ret, tmp_ret;
+	int i, ret;
 	char *cmd;
 	struct urb *urb;
 	struct drm_rect clip;
@@ -290,17 +286,14 @@ static int udl_handle_damage(struct drm_framebuffer *fb, const struct dma_buf_ma
 	else if ((clip.x2 > fb->width) || (clip.y2 > fb->height))
 		return -EINVAL;
 
-	if (import_attach) {
-		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
-					       DMA_FROM_DEVICE);
-		if (ret)
-			return ret;
-	}
+	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
+	if (ret)
+		return ret;
 
 	urb = udl_get_urb(dev);
 	if (!urb) {
 		ret = -ENOMEM;
-		goto out_dma_buf_end_cpu_access;
+		goto out_drm_gem_fb_end_cpu_access;
 	}
 	cmd = urb->transfer_buffer;
 
@@ -313,7 +306,7 @@ static int udl_handle_damage(struct drm_framebuffer *fb, const struct dma_buf_ma
 				       &cmd, byte_offset, dev_byte_offset,
 				       byte_width);
 		if (ret)
-			goto out_dma_buf_end_cpu_access;
+			goto out_drm_gem_fb_end_cpu_access;
 	}
 
 	if (cmd > (char *)urb->transfer_buffer) {
@@ -329,14 +322,8 @@ static int udl_handle_damage(struct drm_framebuffer *fb, const struct dma_buf_ma
 
 	ret = 0;
 
-out_dma_buf_end_cpu_access:
-	if (import_attach) {
-		tmp_ret = dma_buf_end_cpu_access(import_attach->dmabuf,
-						 DMA_FROM_DEVICE);
-		if (tmp_ret && !ret)
-			ret = tmp_ret; /* only update ret if not set yet */
-	}
-
+out_drm_gem_fb_end_cpu_access:
+	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 	return ret;
 }
 
@@ -392,7 +379,7 @@ udl_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	udl->mode_buf_len = wrptr - buf;
 
-	udl_handle_damage(fb, &shadow_plane_state->map[0], 0, 0, fb->width, fb->height);
+	udl_handle_damage(fb, &shadow_plane_state->data[0], 0, 0, fb->width, fb->height);
 
 	if (!crtc_state->mode_changed)
 		return;
@@ -435,7 +422,7 @@ udl_simple_display_pipe_update(struct drm_simple_display_pipe *pipe,
 		return;
 
 	if (drm_atomic_helper_damage_merged(old_plane_state, state, &rect))
-		udl_handle_damage(fb, &shadow_plane_state->map[0], rect.x1, rect.y1,
+		udl_handle_damage(fb, &shadow_plane_state->data[0], rect.x1, rect.y1,
 				  rect.x2 - rect.x1, rect.y2 - rect.y1);
 }
 
diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile
index db4cfc155821..e8b314137020 100644
--- a/drivers/gpu/drm/v3d/Makefile
+++ b/drivers/gpu/drm/v3d/Makefile
@@ -9,6 +9,7 @@ v3d-y := \
 	v3d_gem.o \
 	v3d_irq.o \
 	v3d_mmu.o \
+	v3d_perfmon.o \
 	v3d_trace_points.o \
 	v3d_sched.o
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 99e22beea90b..9403c3b36aca 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -94,6 +94,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 	case DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH:
 		args->value = 1;
 		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_PERFMON:
+		args->value = (v3d->ver >= 40);
+		return 0;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", args->param);
 		return -EINVAL;
@@ -121,6 +124,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 				      1, NULL);
 	}
 
+	v3d_perfmon_open_file(v3d_priv);
 	file->driver_priv = v3d_priv;
 
 	return 0;
@@ -136,6 +140,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file)
 		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
 	}
 
+	v3d_perfmon_close_file(v3d_priv);
 	kfree(v3d_priv);
 }
 
@@ -156,6 +161,9 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(V3D_GET_BO_OFFSET, v3d_get_bo_offset_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_TFU, v3d_submit_tfu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CSD, v3d_submit_csd_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_CREATE, v3d_perfmon_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_DESTROY, v3d_perfmon_destroy_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
 };
 
 static const struct drm_driver v3d_drm_driver = {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 8a390738d65b..270134779073 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -37,6 +37,40 @@ struct v3d_queue_state {
 	u64 emit_seqno;
 };
 
+/* Performance monitor object. The perform lifetime is controlled by userspace
+ * using perfmon related ioctls. A perfmon can be attached to a submit_cl
+ * request, and when this is the case, HW perf counters will be activated just
+ * before the submit_cl is submitted to the GPU and disabled when the job is
+ * done. This way, only events related to a specific job will be counted.
+ */
+struct v3d_perfmon {
+	/* Tracks the number of users of the perfmon, when this counter reaches
+	 * zero the perfmon is destroyed.
+	 */
+	refcount_t refcnt;
+
+	/* Protects perfmon stop, as it can be invoked from multiple places. */
+	struct mutex lock;
+
+	/* Number of counters activated in this perfmon instance
+	 * (should be less than DRM_V3D_MAX_PERF_COUNTERS).
+	 */
+	u8 ncounters;
+
+	/* Events counted by the HW perf counters. */
+	u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+
+	/* Storage for counter values. Counters are incremented by the
+	 * HW perf counter values every time the perfmon is attached
+	 * to a GPU job.  This way, perfmon users don't have to
+	 * retrieve the results after each job if they want to track
+	 * events covering several submissions.  Note that counter
+	 * values can't be reset, but you can fake a reset by
+	 * destroying the perfmon and creating a new one.
+	 */
+	u64 values[];
+};
+
 struct v3d_dev {
 	struct drm_device drm;
 
@@ -89,6 +123,9 @@ struct v3d_dev {
 	 */
 	spinlock_t job_lock;
 
+	/* Used to track the active perfmon if any. */
+	struct v3d_perfmon *active_perfmon;
+
 	/* Protects bo_stats */
 	struct mutex bo_lock;
 
@@ -133,6 +170,11 @@ v3d_has_csd(struct v3d_dev *v3d)
 struct v3d_file_priv {
 	struct v3d_dev *v3d;
 
+	struct {
+		struct idr idr;
+		struct mutex lock;
+	} perfmon;
+
 	struct drm_sched_entity sched_entity[V3D_MAX_QUEUES];
 };
 
@@ -205,6 +247,11 @@ struct v3d_job {
 	 */
 	struct dma_fence *done_fence;
 
+	/* Pointer to a performance monitor object if the user requested it,
+	 * NULL otherwise.
+	 */
+	struct v3d_perfmon *perfmon;
+
 	/* Callback for the freeing of the job on refcount going to 0. */
 	void (*free)(struct kref *ref);
 };
@@ -353,3 +400,19 @@ void v3d_mmu_remove_ptes(struct v3d_bo *bo);
 /* v3d_sched.c */
 int v3d_sched_init(struct v3d_dev *v3d);
 void v3d_sched_fini(struct v3d_dev *v3d);
+
+/* v3d_perfmon.c */
+void v3d_perfmon_get(struct v3d_perfmon *perfmon);
+void v3d_perfmon_put(struct v3d_perfmon *perfmon);
+void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon);
+void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
+		      bool capture);
+struct v3d_perfmon *v3d_perfmon_find(struct v3d_file_priv *v3d_priv, int id);
+void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv);
+void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv);
+int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv);
+int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 4eb354226972..5689da118197 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -126,6 +126,8 @@ v3d_reset(struct v3d_dev *v3d)
 	v3d_mmu_set_page_table(v3d);
 	v3d_irq_reset(v3d);
 
+	v3d_perfmon_stop(v3d, v3d->active_perfmon, false);
+
 	trace_v3d_reset_end(dev);
 }
 
@@ -375,6 +377,9 @@ v3d_job_free(struct kref *ref)
 	pm_runtime_mark_last_busy(job->v3d->drm.dev);
 	pm_runtime_put_autosuspend(job->v3d->drm.dev);
 
+	if (job->perfmon)
+		v3d_perfmon_put(job->perfmon);
+
 	kfree(job);
 }
 
@@ -539,6 +544,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	if (args->flags != 0 &&
 	    args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) {
 		DRM_INFO("invalid flags: %d\n", args->flags);
@@ -611,8 +619,20 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmon_id) {
+		render->base.perfmon = v3d_perfmon_find(v3d_priv,
+							args->perfmon_id);
+
+		if (!render->base.perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	mutex_lock(&v3d->sched_lock);
 	if (bin) {
+		bin->base.perfmon = render->base.perfmon;
+		v3d_perfmon_get(bin->base.perfmon);
 		ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
 		if (ret)
 			goto fail_unreserve;
@@ -633,6 +653,8 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 		ret = drm_gem_fence_array_add(&clean_job->deps, render_fence);
 		if (ret)
 			goto fail_unreserve;
+		clean_job->perfmon = render->base.perfmon;
+		v3d_perfmon_get(clean_job->perfmon);
 		ret = v3d_push_job(v3d_priv, clean_job, V3D_CACHE_CLEAN);
 		if (ret)
 			goto fail_unreserve;
@@ -827,6 +849,15 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmon_id) {
+		job->base.perfmon = v3d_perfmon_find(v3d_priv,
+						     args->perfmon_id);
+		if (!job->base.perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	mutex_lock(&v3d->sched_lock);
 	ret = v3d_push_job(v3d_priv, &job->base, V3D_CSD);
 	if (ret)
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
new file mode 100644
index 000000000000..0288ef063513
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Raspberry Pi
+ */
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define V3D_PERFMONID_MIN	1
+#define V3D_PERFMONID_MAX	U32_MAX
+
+void v3d_perfmon_get(struct v3d_perfmon *perfmon)
+{
+	if (perfmon)
+		refcount_inc(&perfmon->refcnt);
+}
+
+void v3d_perfmon_put(struct v3d_perfmon *perfmon)
+{
+	if (perfmon && refcount_dec_and_test(&perfmon->refcnt))
+		kfree(perfmon);
+}
+
+void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon)
+{
+	unsigned int i;
+	u32 mask;
+	u8 ncounters = perfmon->ncounters;
+
+	if (WARN_ON_ONCE(!perfmon || v3d->active_perfmon))
+		return;
+
+	mask = GENMASK(ncounters - 1, 0);
+
+	for (i = 0; i < ncounters; i++) {
+		u32 source = i / 4;
+		u32 channel = V3D_SET_FIELD(perfmon->counters[i], V3D_PCTR_S0);
+
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S1);
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S2);
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S3);
+		V3D_CORE_WRITE(0, V3D_V4_PCTR_0_SRC_X(source), channel);
+	}
+
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_CLR, mask);
+	V3D_CORE_WRITE(0, V3D_PCTR_0_OVERFLOW, mask);
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_EN, mask);
+
+	v3d->active_perfmon = perfmon;
+}
+
+void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
+		      bool capture)
+{
+	unsigned int i;
+
+	if (!perfmon || !v3d->active_perfmon)
+		return;
+
+	mutex_lock(&perfmon->lock);
+	if (perfmon != v3d->active_perfmon) {
+		mutex_unlock(&perfmon->lock);
+		return;
+	}
+
+	if (capture)
+		for (i = 0; i < perfmon->ncounters; i++)
+			perfmon->values[i] += V3D_CORE_READ(0, V3D_PCTR_0_PCTRX(i));
+
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_EN, 0);
+
+	v3d->active_perfmon = NULL;
+	mutex_unlock(&perfmon->lock);
+}
+
+struct v3d_perfmon *v3d_perfmon_find(struct v3d_file_priv *v3d_priv, int id)
+{
+	struct v3d_perfmon *perfmon;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_find(&v3d_priv->perfmon.idr, id);
+	v3d_perfmon_get(perfmon);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	return perfmon;
+}
+
+void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv)
+{
+	mutex_init(&v3d_priv->perfmon.lock);
+	idr_init(&v3d_priv->perfmon.idr);
+}
+
+static int v3d_perfmon_idr_del(int id, void *elem, void *data)
+{
+	struct v3d_perfmon *perfmon = elem;
+
+	v3d_perfmon_put(perfmon);
+
+	return 0;
+}
+
+void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv)
+{
+	mutex_lock(&v3d_priv->perfmon.lock);
+	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, NULL);
+	idr_destroy(&v3d_priv->perfmon.idr);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+}
+
+int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_create *req = data;
+	struct v3d_perfmon *perfmon;
+	unsigned int i;
+	int ret;
+
+	/* Number of monitored counters cannot exceed HW limits. */
+	if (req->ncounters > DRM_V3D_MAX_PERF_COUNTERS ||
+	    !req->ncounters)
+		return -EINVAL;
+
+	/* Make sure all counters are valid. */
+	for (i = 0; i < req->ncounters; i++) {
+		if (req->counters[i] >= V3D_PERFCNT_NUM)
+			return -EINVAL;
+	}
+
+	perfmon = kzalloc(struct_size(perfmon, values, req->ncounters),
+			  GFP_KERNEL);
+	if (!perfmon)
+		return -ENOMEM;
+
+	for (i = 0; i < req->ncounters; i++)
+		perfmon->counters[i] = req->counters[i];
+
+	perfmon->ncounters = req->ncounters;
+
+	refcount_set(&perfmon->refcnt, 1);
+	mutex_init(&perfmon->lock);
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	ret = idr_alloc(&v3d_priv->perfmon.idr, perfmon, V3D_PERFMONID_MIN,
+			V3D_PERFMONID_MAX, GFP_KERNEL);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (ret < 0) {
+		kfree(perfmon);
+		return ret;
+	}
+
+	req->id = ret;
+
+	return 0;
+}
+
+int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_destroy *req = data;
+	struct v3d_perfmon *perfmon;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_remove(&v3d_priv->perfmon.idr, req->id);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	v3d_perfmon_put(perfmon);
+
+	return 0;
+}
+
+int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_get_values *req = data;
+	struct v3d_perfmon *perfmon;
+	int ret = 0;
+
+	if (req->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_find(&v3d_priv->perfmon.idr, req->id);
+	v3d_perfmon_get(perfmon);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	v3d_perfmon_stop(v3d, perfmon, true);
+
+	if (copy_to_user(u64_to_user_ptr(req->values_ptr), perfmon->values,
+			 perfmon->ncounters * sizeof(u64)))
+		ret = -EFAULT;
+
+	v3d_perfmon_put(perfmon);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index 9bcb57781d31..3663e0d6bf76 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -347,6 +347,8 @@
 /* Each src reg muxes four counters each. */
 #define V3D_V4_PCTR_0_SRC_0_3                          0x00660
 #define V3D_V4_PCTR_0_SRC_28_31                        0x0067c
+#define V3D_V4_PCTR_0_SRC_X(x)                         (V3D_V4_PCTR_0_SRC_0_3 + \
+							4 * (x))
 # define V3D_PCTR_S0_MASK                              V3D_MASK(6, 0)
 # define V3D_PCTR_S0_SHIFT                             0
 # define V3D_PCTR_S1_MASK                              V3D_MASK(14, 8)
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 8992480c88fa..dd7fcc36d726 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -63,6 +63,16 @@ v3d_job_free(struct drm_sched_job *sched_job)
 	v3d_job_put(job);
 }
 
+static void
+v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
+{
+	if (job->perfmon != v3d->active_perfmon)
+		v3d_perfmon_stop(v3d, v3d->active_perfmon, true);
+
+	if (job->perfmon && v3d->active_perfmon != job->perfmon)
+		v3d_perfmon_start(v3d, job->perfmon);
+}
+
 /*
  * Returns the fences that the job depends on, one by one.
  *
@@ -120,6 +130,8 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
+	v3d_switch_perfmon(v3d, &job->base);
+
 	/* Set the current and end address of the control list.
 	 * Writing the end register is what starts the job.
 	 */
@@ -169,6 +181,8 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
+	v3d_switch_perfmon(v3d, &job->base);
+
 	/* XXX: Set the QCFG */
 
 	/* Set the current and end address of the control list.
@@ -240,6 +254,8 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 
 	trace_v3d_submit_csd(dev, to_v3d_fence(fence)->seqno);
 
+	v3d_switch_perfmon(v3d, &job->base);
+
 	for (i = 1; i <= 6; i++)
 		V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0 + 4 * i, job->args.cfg[i]);
 	/* CFG0 write kicks off the job. */
@@ -402,7 +418,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
 			     &v3d_bin_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
-			     msecs_to_jiffies(hang_limit_ms),
+			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_bin");
 	if (ret) {
 		dev_err(v3d->drm.dev, "Failed to create bin scheduler: %d.", ret);
@@ -412,7 +428,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
 			     &v3d_render_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
-			     msecs_to_jiffies(hang_limit_ms),
+			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_render");
 	if (ret) {
 		dev_err(v3d->drm.dev, "Failed to create render scheduler: %d.",
@@ -424,7 +440,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	ret = drm_sched_init(&v3d->queue[V3D_TFU].sched,
 			     &v3d_tfu_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
-			     msecs_to_jiffies(hang_limit_ms),
+			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_tfu");
 	if (ret) {
 		dev_err(v3d->drm.dev, "Failed to create TFU scheduler: %d.",
@@ -437,7 +453,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 		ret = drm_sched_init(&v3d->queue[V3D_CSD].sched,
 				     &v3d_csd_sched_ops,
 				     hw_jobs_limit, job_hang_limit,
-				     msecs_to_jiffies(hang_limit_ms),
+				     msecs_to_jiffies(hang_limit_ms), NULL,
 				     NULL, "v3d_csd");
 		if (ret) {
 			dev_err(v3d->drm.dev, "Failed to create CSD scheduler: %d.",
@@ -449,7 +465,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 		ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
 				     &v3d_cache_clean_sched_ops,
 				     hw_jobs_limit, job_hang_limit,
-				     msecs_to_jiffies(hang_limit_ms),
+				     msecs_to_jiffies(hang_limit_ms), NULL,
 				     NULL, "v3d_cache_clean");
 		if (ret) {
 			dev_err(v3d->drm.dev, "Failed to create CACHE_CLEAN scheduler: %d.",
diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c
index 6d4b32da9866..2b81cb259d23 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_drv.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c
@@ -43,7 +43,7 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!vbox_check_supported(VBE_DISPI_ID_HGSMI))
 		return -ENODEV;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "vboxvideodrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver);
 	if (ret)
 		return ret;
 
@@ -184,7 +184,6 @@ static const struct drm_driver driver = {
 	.lastclose = drm_fb_helper_lastclose,
 
 	.fops = &vbox_fops,
-	.irq_handler = vbox_irq_handler,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
 	.date = DRIVER_DATE,
diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.h b/drivers/gpu/drm/vboxvideo/vbox_drv.h
index ac7c2effc46f..4903b91d7fe4 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_drv.h
+++ b/drivers/gpu/drm/vboxvideo/vbox_drv.h
@@ -145,7 +145,6 @@ void vbox_mm_fini(struct vbox_private *vbox);
 int vbox_irq_init(struct vbox_private *vbox);
 void vbox_irq_fini(struct vbox_private *vbox);
 void vbox_report_hotplug(struct vbox_private *vbox);
-irqreturn_t vbox_irq_handler(int irq, void *arg);
 
 /* vbox_hgsmi.c */
 void *hgsmi_buffer_alloc(struct gen_pool *guest_pool, size_t size,
diff --git a/drivers/gpu/drm/vboxvideo/vbox_irq.c b/drivers/gpu/drm/vboxvideo/vbox_irq.c
index b3ded68603ba..903a6c48ee8b 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_irq.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_irq.c
@@ -10,7 +10,8 @@
  */
 
 #include <linux/pci.h>
-#include <drm/drm_irq.h>
+
+#include <drm/drm_drv.h>
 #include <drm/drm_probe_helper.h>
 
 #include "vbox_drv.h"
@@ -31,7 +32,7 @@ void vbox_report_hotplug(struct vbox_private *vbox)
 	schedule_work(&vbox->hotplug_work);
 }
 
-irqreturn_t vbox_irq_handler(int irq, void *arg)
+static irqreturn_t vbox_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *)arg;
 	struct vbox_private *vbox = to_vbox_dev(dev);
@@ -170,16 +171,21 @@ static void vbox_hotplug_worker(struct work_struct *work)
 
 int vbox_irq_init(struct vbox_private *vbox)
 {
-	struct pci_dev *pdev = to_pci_dev(vbox->ddev.dev);
+	struct drm_device *dev = &vbox->ddev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	INIT_WORK(&vbox->hotplug_work, vbox_hotplug_worker);
 	vbox_update_mode_hints(vbox);
 
-	return drm_irq_install(&vbox->ddev, pdev->irq);
+	/* PCI devices require shared interrupts. */
+	return request_irq(pdev->irq, vbox_irq_handler, IRQF_SHARED, dev->driver->name, dev);
 }
 
 void vbox_irq_fini(struct vbox_private *vbox)
 {
-	drm_irq_uninstall(&vbox->ddev);
+	struct drm_device *dev = &vbox->ddev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	free_irq(pdev->irq, dev);
 	flush_work(&vbox->hotplug_work);
 }
diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c
index 964381d55fc1..4227a915b06a 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_mode.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c
@@ -398,7 +398,7 @@ static void vbox_cursor_atomic_update(struct drm_plane *plane,
 	u32 height = new_state->crtc_h;
 	struct drm_shadow_plane_state *shadow_plane_state =
 		to_drm_shadow_plane_state(new_state);
-	struct dma_buf_map map = shadow_plane_state->map[0];
+	struct dma_buf_map map = shadow_plane_state->data[0];
 	u8 *src = map.vaddr; /* TODO: Use mapping abstraction properly */
 	size_t data_size, mask_size;
 	u32 flags;
@@ -488,8 +488,7 @@ static const struct drm_plane_helper_funcs vbox_primary_helper_funcs = {
 	.atomic_check = vbox_primary_atomic_check,
 	.atomic_update = vbox_primary_atomic_update,
 	.atomic_disable = vbox_primary_atomic_disable,
-	.prepare_fb	= drm_gem_vram_plane_helper_prepare_fb,
-	.cleanup_fb	= drm_gem_vram_plane_helper_cleanup_fb,
+	DRM_GEM_VRAM_PLANE_HELPER_FUNCS,
 };
 
 static const struct drm_plane_funcs vbox_primary_plane_funcs = {
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 118e8a426b1a..345a5570a3da 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -12,6 +12,7 @@ config DRM_VC4
 	select SND_PCM
 	select SND_PCM_ELD
 	select SND_SOC_GENERIC_DMAENGINE_PCM
+	select SND_SOC_HDMI_CODEC
 	select DRM_MIPI_DSI
 	help
 	  Choose this option if you have a system that has a Broadcom
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 8a60fb8ad370..f6c16c5aee68 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -168,10 +168,6 @@ static struct drm_driver vc4_drm_driver = {
 			    DRIVER_SYNCOBJ),
 	.open = vc4_open,
 	.postclose = vc4_close,
-	.irq_handler = vc4_irq,
-	.irq_preinstall = vc4_irq_preinstall,
-	.irq_postinstall = vc4_irq_postinstall,
-	.irq_uninstall = vc4_irq_uninstall,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = vc4_debugfs_init,
@@ -265,7 +261,7 @@ static int vc4_drm_bind(struct device *dev)
 	if (ret)
 		goto unbind_all;
 
-	ret = drm_aperture_remove_framebuffers(false, "vc4drmfb");
+	ret = drm_aperture_remove_framebuffers(false, &vc4_drm_driver);
 	if (ret)
 		goto unbind_all;
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 5dceadc61600..ef73e0aaf726 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -74,6 +74,8 @@ struct vc4_perfmon {
 struct vc4_dev {
 	struct drm_device base;
 
+	unsigned int irq;
+
 	struct vc4_hvs *hvs;
 	struct vc4_v3d *v3d;
 	struct vc4_dpi *dpi;
@@ -895,9 +897,9 @@ extern struct platform_driver vc4_vec_driver;
 extern struct platform_driver vc4_txp_driver;
 
 /* vc4_irq.c */
-irqreturn_t vc4_irq(int irq, void *arg);
-void vc4_irq_preinstall(struct drm_device *dev);
-int vc4_irq_postinstall(struct drm_device *dev);
+void vc4_irq_enable(struct drm_device *dev);
+void vc4_irq_disable(struct drm_device *dev);
+int vc4_irq_install(struct drm_device *dev, int irq);
 void vc4_irq_uninstall(struct drm_device *dev);
 void vc4_irq_reset(struct drm_device *dev);
 
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index a55256ed0955..a185027911ce 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -1646,10 +1646,8 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	drm_encoder_helper_add(dsi->encoder, &vc4_dsi_encoder_helper_funcs);
 
 	ret = drm_bridge_attach(dsi->encoder, dsi->bridge, NULL, 0);
-	if (ret) {
-		dev_err(dev, "bridge attach failed: %d\n", ret);
+	if (ret)
 		return ret;
-	}
 	/* Disable the atomic helper calls into the bridge.  We
 	 * manually call the bridge pre_enable / enable / etc. calls
 	 * from our driver, since we need to sequence them within the
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index c2876731ee2d..b7dc32a0c9bb 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -46,6 +46,7 @@
 #include <linux/rational.h>
 #include <linux/reset.h>
 #include <sound/dmaengine_pcm.h>
+#include <sound/hdmi-codec.h>
 #include <sound/pcm_drm_eld.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -435,7 +436,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder)
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	struct drm_connector *connector = &vc4_hdmi->connector;
 	struct drm_connector_state *cstate = connector->state;
-	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_crtc *crtc = cstate->crtc;
 	const struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 	union hdmi_infoframe frame;
 	int ret;
@@ -477,15 +478,10 @@ static void vc4_hdmi_set_spd_infoframe(struct drm_encoder *encoder)
 static void vc4_hdmi_set_audio_infoframe(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct hdmi_audio_infoframe *audio = &vc4_hdmi->audio.infoframe;
 	union hdmi_infoframe frame;
 
-	hdmi_audio_infoframe_init(&frame.audio);
-
-	frame.audio.coding_type = HDMI_AUDIO_CODING_TYPE_STREAM;
-	frame.audio.sample_frequency = HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM;
-	frame.audio.sample_size = HDMI_AUDIO_SAMPLE_SIZE_STREAM;
-	frame.audio.channels = vc4_hdmi->audio.channels;
-
+	memcpy(&frame.audio, audio, sizeof(*audio));
 	vc4_hdmi_write_infoframe(encoder, &frame);
 }
 
@@ -545,8 +541,11 @@ static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder,
 
 static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 {
-	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_connector *connector = &vc4_hdmi->connector;
+	struct drm_connector_state *cstate = connector->state;
+	struct drm_crtc *crtc = cstate->crtc;
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 
 	if (!vc4_hdmi_supports_scrambling(encoder, mode))
 		return;
@@ -567,17 +566,18 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
-	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_connector *connector = &vc4_hdmi->connector;
+	struct drm_connector_state *cstate = connector->state;
 
 	/*
-	 * At boot, encoder->crtc will be NULL. Since we don't know the
+	 * At boot, connector->state will be NULL. Since we don't know the
 	 * state of the scrambler and in order to avoid any
 	 * inconsistency, let's disable it all the time.
 	 */
-	if (crtc && !vc4_hdmi_supports_scrambling(encoder, &crtc->mode))
+	if (cstate && !vc4_hdmi_supports_scrambling(encoder, &cstate->crtc->mode))
 		return;
 
-	if (crtc && !vc4_hdmi_mode_needs_scrambling(&crtc->mode))
+	if (cstate && !vc4_hdmi_mode_needs_scrambling(&cstate->crtc->mode))
 		return;
 
 	if (delayed_work_pending(&vc4_hdmi->scrambling_work))
@@ -613,12 +613,12 @@ static void vc4_hdmi_encoder_post_crtc_disable(struct drm_encoder *encoder,
 
 	HDMI_WRITE(HDMI_RAM_PACKET_CONFIG, 0);
 
-	HDMI_WRITE(HDMI_VID_CTL, HDMI_READ(HDMI_VID_CTL) |
-		   VC4_HD_VID_CTL_CLRRGB | VC4_HD_VID_CTL_CLRSYNC);
+	HDMI_WRITE(HDMI_VID_CTL, HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_CLRRGB);
 
-	HDMI_WRITE(HDMI_VID_CTL,
-		   HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_BLANKPIX);
+	mdelay(1);
 
+	HDMI_WRITE(HDMI_VID_CTL,
+		   HDMI_READ(HDMI_VID_CTL) & ~VC4_HD_VID_CTL_ENABLE);
 	vc4_hdmi_disable_scrambling(encoder);
 }
 
@@ -628,12 +628,12 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder,
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	int ret;
 
+	HDMI_WRITE(HDMI_VID_CTL,
+		   HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_BLANKPIX);
+
 	if (vc4_hdmi->variant->phy_disable)
 		vc4_hdmi->variant->phy_disable(vc4_hdmi);
 
-	HDMI_WRITE(HDMI_VID_CTL,
-		   HDMI_READ(HDMI_VID_CTL) & ~VC4_HD_VID_CTL_ENABLE);
-
 	clk_disable_unprepare(vc4_hdmi->pixel_bvb_clock);
 	clk_disable_unprepare(vc4_hdmi->pixel_clock);
 
@@ -898,7 +898,9 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 		vc4_hdmi_encoder_get_connector_state(encoder, state);
 	struct vc4_hdmi_connector_state *vc4_conn_state =
 		conn_state_to_vc4_hdmi_conn_state(conn_state);
-	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
+	struct drm_crtc_state *crtc_state =
+		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
+	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	unsigned long bvb_rate, pixel_rate, hsm_rate;
 	int ret;
@@ -983,7 +985,11 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 					     struct drm_atomic_state *state)
 {
-	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
+	struct drm_connector_state *conn_state =
+		vc4_hdmi_encoder_get_connector_state(encoder, state);
+	struct drm_crtc_state *crtc_state =
+		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
+	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 
@@ -1006,7 +1012,11 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 					      struct drm_atomic_state *state)
 {
-	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
+	struct drm_connector_state *conn_state =
+		vc4_hdmi_encoder_get_connector_state(encoder, state);
+	struct drm_crtc_state *crtc_state =
+		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
+	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC;
@@ -1015,6 +1025,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 
 	HDMI_WRITE(HDMI_VID_CTL,
 		   VC4_HD_VID_CTL_ENABLE |
+		   VC4_HD_VID_CTL_CLRRGB |
 		   VC4_HD_VID_CTL_UNDERFLOW_ENABLE |
 		   VC4_HD_VID_CTL_FRAME_COUNTER_RESET |
 		   (vsync_pos ? 0 : VC4_HD_VID_CTL_VSYNC_LOW) |
@@ -1173,12 +1184,13 @@ static u32 vc5_hdmi_channel_map(struct vc4_hdmi *vc4_hdmi, u32 channel_mask)
 }
 
 /* HDMI audio codec callbacks */
-static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi)
+static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi,
+					 unsigned int samplerate)
 {
 	u32 hsm_clock = clk_get_rate(vc4_hdmi->audio_clock);
 	unsigned long n, m;
 
-	rational_best_approximation(hsm_clock, vc4_hdmi->audio.samplerate,
+	rational_best_approximation(hsm_clock, samplerate,
 				    VC4_HD_MAI_SMP_N_MASK >>
 				    VC4_HD_MAI_SMP_N_SHIFT,
 				    (VC4_HD_MAI_SMP_M_MASK >>
@@ -1190,12 +1202,11 @@ static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi)
 		   VC4_SET_FIELD(m - 1, VC4_HD_MAI_SMP_M));
 }
 
-static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi)
+static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi, unsigned int samplerate)
 {
-	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
-	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_connector *connector = &vc4_hdmi->connector;
+	struct drm_crtc *crtc = connector->state->crtc;
 	const struct drm_display_mode *mode = &crtc->state->adjusted_mode;
-	u32 samplerate = vc4_hdmi->audio.samplerate;
 	u32 n, cts;
 	u64 tmp;
 
@@ -1224,36 +1235,31 @@ static inline struct vc4_hdmi *dai_to_hdmi(struct snd_soc_dai *dai)
 	return snd_soc_card_get_drvdata(card);
 }
 
-static int vc4_hdmi_audio_startup(struct snd_pcm_substream *substream,
-				  struct snd_soc_dai *dai)
+static int vc4_hdmi_audio_startup(struct device *dev, void *data)
 {
-	struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
-	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
+	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 	struct drm_connector *connector = &vc4_hdmi->connector;
-	int ret;
-
-	if (vc4_hdmi->audio.substream && vc4_hdmi->audio.substream != substream)
-		return -EINVAL;
-
-	vc4_hdmi->audio.substream = substream;
 
 	/*
 	 * If the HDMI encoder hasn't probed, or the encoder is
 	 * currently in DVI mode, treat the codec dai as missing.
 	 */
-	if (!encoder->crtc || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) &
+	if (!connector->state || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) &
 				VC4_HDMI_RAM_PACKET_ENABLE))
 		return -ENODEV;
 
-	ret = snd_pcm_hw_constraint_eld(substream->runtime, connector->eld);
-	if (ret)
-		return ret;
+	vc4_hdmi->audio.streaming = true;
 
-	return 0;
-}
+	HDMI_WRITE(HDMI_MAI_CTL,
+		   VC4_HD_MAI_CTL_RESET |
+		   VC4_HD_MAI_CTL_FLUSH |
+		   VC4_HD_MAI_CTL_DLATE |
+		   VC4_HD_MAI_CTL_ERRORE |
+		   VC4_HD_MAI_CTL_ERRORF);
+
+	if (vc4_hdmi->variant->phy_rng_enable)
+		vc4_hdmi->variant->phy_rng_enable(vc4_hdmi);
 
-static int vc4_hdmi_audio_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
-{
 	return 0;
 }
 
@@ -1273,48 +1279,96 @@ static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi)
 	HDMI_WRITE(HDMI_MAI_CTL, VC4_HD_MAI_CTL_FLUSH);
 }
 
-static void vc4_hdmi_audio_shutdown(struct snd_pcm_substream *substream,
-				    struct snd_soc_dai *dai)
+static void vc4_hdmi_audio_shutdown(struct device *dev, void *data)
 {
-	struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
+	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
-	if (substream != vc4_hdmi->audio.substream)
-		return;
+	HDMI_WRITE(HDMI_MAI_CTL,
+		   VC4_HD_MAI_CTL_DLATE |
+		   VC4_HD_MAI_CTL_ERRORE |
+		   VC4_HD_MAI_CTL_ERRORF);
+
+	if (vc4_hdmi->variant->phy_rng_disable)
+		vc4_hdmi->variant->phy_rng_disable(vc4_hdmi);
 
+	vc4_hdmi->audio.streaming = false;
 	vc4_hdmi_audio_reset(vc4_hdmi);
+}
 
-	vc4_hdmi->audio.substream = NULL;
+static int sample_rate_to_mai_fmt(int samplerate)
+{
+	switch (samplerate) {
+	case 8000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_8000;
+	case 11025:
+		return VC4_HDMI_MAI_SAMPLE_RATE_11025;
+	case 12000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_12000;
+	case 16000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_16000;
+	case 22050:
+		return VC4_HDMI_MAI_SAMPLE_RATE_22050;
+	case 24000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_24000;
+	case 32000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_32000;
+	case 44100:
+		return VC4_HDMI_MAI_SAMPLE_RATE_44100;
+	case 48000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_48000;
+	case 64000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_64000;
+	case 88200:
+		return VC4_HDMI_MAI_SAMPLE_RATE_88200;
+	case 96000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_96000;
+	case 128000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_128000;
+	case 176400:
+		return VC4_HDMI_MAI_SAMPLE_RATE_176400;
+	case 192000:
+		return VC4_HDMI_MAI_SAMPLE_RATE_192000;
+	default:
+		return VC4_HDMI_MAI_SAMPLE_RATE_NOT_INDICATED;
+	}
 }
 
 /* HDMI audio codec callbacks */
-static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream,
-				    struct snd_pcm_hw_params *params,
-				    struct snd_soc_dai *dai)
+static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
+				  struct hdmi_codec_daifmt *daifmt,
+				  struct hdmi_codec_params *params)
 {
-	struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
+	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
-	struct device *dev = &vc4_hdmi->pdev->dev;
+	unsigned int sample_rate = params->sample_rate;
+	unsigned int channels = params->channels;
 	u32 audio_packet_config, channel_mask;
 	u32 channel_map;
-
-	if (substream != vc4_hdmi->audio.substream)
-		return -EINVAL;
+	u32 mai_audio_format;
+	u32 mai_sample_rate;
 
 	dev_dbg(dev, "%s: %u Hz, %d bit, %d channels\n", __func__,
-		params_rate(params), params_width(params),
-		params_channels(params));
-
-	vc4_hdmi->audio.channels = params_channels(params);
-	vc4_hdmi->audio.samplerate = params_rate(params);
+		sample_rate, params->sample_width, channels);
 
 	HDMI_WRITE(HDMI_MAI_CTL,
-		   VC4_HD_MAI_CTL_RESET |
-		   VC4_HD_MAI_CTL_FLUSH |
-		   VC4_HD_MAI_CTL_DLATE |
-		   VC4_HD_MAI_CTL_ERRORE |
-		   VC4_HD_MAI_CTL_ERRORF);
+		   VC4_SET_FIELD(channels, VC4_HD_MAI_CTL_CHNUM) |
+		   VC4_HD_MAI_CTL_WHOLSMP |
+		   VC4_HD_MAI_CTL_CHALIGN |
+		   VC4_HD_MAI_CTL_ENABLE);
+
+	vc4_hdmi_audio_set_mai_clock(vc4_hdmi, sample_rate);
 
-	vc4_hdmi_audio_set_mai_clock(vc4_hdmi);
+	mai_sample_rate = sample_rate_to_mai_fmt(sample_rate);
+	if (params->iec.status[0] & IEC958_AES0_NONAUDIO &&
+	    params->channels == 8)
+		mai_audio_format = VC4_HDMI_MAI_FORMAT_HBR;
+	else
+		mai_audio_format = VC4_HDMI_MAI_FORMAT_PCM;
+	HDMI_WRITE(HDMI_MAI_FMT,
+		   VC4_SET_FIELD(mai_sample_rate,
+				 VC4_HDMI_MAI_FORMAT_SAMPLE_RATE) |
+		   VC4_SET_FIELD(mai_audio_format,
+				 VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT));
 
 	/* The B frame identifier should match the value used by alsa-lib (8) */
 	audio_packet_config =
@@ -1322,122 +1376,33 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream,
 		VC4_HDMI_AUDIO_PACKET_ZERO_DATA_ON_INACTIVE_CHANNELS |
 		VC4_SET_FIELD(0x8, VC4_HDMI_AUDIO_PACKET_B_FRAME_IDENTIFIER);
 
-	channel_mask = GENMASK(vc4_hdmi->audio.channels - 1, 0);
+	channel_mask = GENMASK(channels - 1, 0);
 	audio_packet_config |= VC4_SET_FIELD(channel_mask,
 					     VC4_HDMI_AUDIO_PACKET_CEA_MASK);
 
-	/* Set the MAI threshold.  This logic mimics the firmware's. */
-	if (vc4_hdmi->audio.samplerate > 96000) {
-		HDMI_WRITE(HDMI_MAI_THR,
-			   VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQHIGH) |
-			   VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQLOW));
-	} else if (vc4_hdmi->audio.samplerate > 48000) {
-		HDMI_WRITE(HDMI_MAI_THR,
-			   VC4_SET_FIELD(0x14, VC4_HD_MAI_THR_DREQHIGH) |
-			   VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQLOW));
-	} else {
-		HDMI_WRITE(HDMI_MAI_THR,
-			   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICHIGH) |
-			   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICLOW) |
-			   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQHIGH) |
-			   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQLOW));
-	}
+	/* Set the MAI threshold */
+	HDMI_WRITE(HDMI_MAI_THR,
+		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICHIGH) |
+		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICLOW) |
+		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQHIGH) |
+		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQLOW));
 
 	HDMI_WRITE(HDMI_MAI_CONFIG,
 		   VC4_HDMI_MAI_CONFIG_BIT_REVERSE |
+		   VC4_HDMI_MAI_CONFIG_FORMAT_REVERSE |
 		   VC4_SET_FIELD(channel_mask, VC4_HDMI_MAI_CHANNEL_MASK));
 
 	channel_map = vc4_hdmi->variant->channel_map(vc4_hdmi, channel_mask);
 	HDMI_WRITE(HDMI_MAI_CHANNEL_MAP, channel_map);
 	HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config);
-	vc4_hdmi_set_n_cts(vc4_hdmi);
+	vc4_hdmi_set_n_cts(vc4_hdmi, sample_rate);
 
+	memcpy(&vc4_hdmi->audio.infoframe, &params->cea, sizeof(params->cea));
 	vc4_hdmi_set_audio_infoframe(encoder);
 
 	return 0;
 }
 
-static int vc4_hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd,
-				  struct snd_soc_dai *dai)
-{
-	struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
-
-	switch (cmd) {
-	case SNDRV_PCM_TRIGGER_START:
-		vc4_hdmi->audio.streaming = true;
-
-		if (vc4_hdmi->variant->phy_rng_enable)
-			vc4_hdmi->variant->phy_rng_enable(vc4_hdmi);
-
-		HDMI_WRITE(HDMI_MAI_CTL,
-			   VC4_SET_FIELD(vc4_hdmi->audio.channels,
-					 VC4_HD_MAI_CTL_CHNUM) |
-			   VC4_HD_MAI_CTL_ENABLE);
-		break;
-	case SNDRV_PCM_TRIGGER_STOP:
-		HDMI_WRITE(HDMI_MAI_CTL,
-			   VC4_HD_MAI_CTL_DLATE |
-			   VC4_HD_MAI_CTL_ERRORE |
-			   VC4_HD_MAI_CTL_ERRORF);
-
-		if (vc4_hdmi->variant->phy_rng_disable)
-			vc4_hdmi->variant->phy_rng_disable(vc4_hdmi);
-
-		vc4_hdmi->audio.streaming = false;
-
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static inline struct vc4_hdmi *
-snd_component_to_hdmi(struct snd_soc_component *component)
-{
-	struct snd_soc_card *card = snd_soc_component_get_drvdata(component);
-
-	return snd_soc_card_get_drvdata(card);
-}
-
-static int vc4_hdmi_audio_eld_ctl_info(struct snd_kcontrol *kcontrol,
-				       struct snd_ctl_elem_info *uinfo)
-{
-	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	struct vc4_hdmi *vc4_hdmi = snd_component_to_hdmi(component);
-	struct drm_connector *connector = &vc4_hdmi->connector;
-
-	uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES;
-	uinfo->count = sizeof(connector->eld);
-
-	return 0;
-}
-
-static int vc4_hdmi_audio_eld_ctl_get(struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	struct vc4_hdmi *vc4_hdmi = snd_component_to_hdmi(component);
-	struct drm_connector *connector = &vc4_hdmi->connector;
-
-	memcpy(ucontrol->value.bytes.data, connector->eld,
-	       sizeof(connector->eld));
-
-	return 0;
-}
-
-static const struct snd_kcontrol_new vc4_hdmi_audio_controls[] = {
-	{
-		.access = SNDRV_CTL_ELEM_ACCESS_READ |
-			  SNDRV_CTL_ELEM_ACCESS_VOLATILE,
-		.iface = SNDRV_CTL_ELEM_IFACE_PCM,
-		.name = "ELD",
-		.info = vc4_hdmi_audio_eld_ctl_info,
-		.get = vc4_hdmi_audio_eld_ctl_get,
-	},
-};
-
 static const struct snd_soc_dapm_widget vc4_hdmi_audio_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("TX"),
 };
@@ -1446,42 +1411,6 @@ static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = {
 	{ "TX", NULL, "Playback" },
 };
 
-static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = {
-	.name			= "vc4-hdmi-codec-dai-component",
-	.controls		= vc4_hdmi_audio_controls,
-	.num_controls		= ARRAY_SIZE(vc4_hdmi_audio_controls),
-	.dapm_widgets		= vc4_hdmi_audio_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(vc4_hdmi_audio_widgets),
-	.dapm_routes		= vc4_hdmi_audio_routes,
-	.num_dapm_routes	= ARRAY_SIZE(vc4_hdmi_audio_routes),
-	.idle_bias_on		= 1,
-	.use_pmdown_time	= 1,
-	.endianness		= 1,
-	.non_legacy_dai_naming	= 1,
-};
-
-static const struct snd_soc_dai_ops vc4_hdmi_audio_dai_ops = {
-	.startup = vc4_hdmi_audio_startup,
-	.shutdown = vc4_hdmi_audio_shutdown,
-	.hw_params = vc4_hdmi_audio_hw_params,
-	.set_fmt = vc4_hdmi_audio_set_fmt,
-	.trigger = vc4_hdmi_audio_trigger,
-};
-
-static struct snd_soc_dai_driver vc4_hdmi_audio_codec_dai_drv = {
-	.name = "vc4-hdmi-hifi",
-	.playback = {
-		.stream_name = "Playback",
-		.channels_min = 2,
-		.channels_max = 8,
-		.rates = SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 |
-			 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 |
-			 SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 |
-			 SNDRV_PCM_RATE_192000,
-		.formats = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE,
-	},
-};
-
 static const struct snd_soc_component_driver vc4_hdmi_audio_cpu_dai_comp = {
 	.name = "vc4-hdmi-cpu-dai-component",
 };
@@ -1508,7 +1437,6 @@ static struct snd_soc_dai_driver vc4_hdmi_audio_cpu_dai_drv = {
 			 SNDRV_PCM_RATE_192000,
 		.formats = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE,
 	},
-	.ops = &vc4_hdmi_audio_dai_ops,
 };
 
 static const struct snd_dmaengine_pcm_config pcm_conf = {
@@ -1516,6 +1444,30 @@ static const struct snd_dmaengine_pcm_config pcm_conf = {
 	.prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config,
 };
 
+static int vc4_hdmi_audio_get_eld(struct device *dev, void *data,
+				  uint8_t *buf, size_t len)
+{
+	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
+	struct drm_connector *connector = &vc4_hdmi->connector;
+
+	memcpy(buf, connector->eld, min(sizeof(connector->eld), len));
+
+	return 0;
+}
+
+static const struct hdmi_codec_ops vc4_hdmi_codec_ops = {
+	.get_eld = vc4_hdmi_audio_get_eld,
+	.prepare = vc4_hdmi_audio_prepare,
+	.audio_shutdown = vc4_hdmi_audio_shutdown,
+	.audio_startup = vc4_hdmi_audio_startup,
+};
+
+struct hdmi_codec_pdata vc4_hdmi_codec_pdata = {
+	.ops = &vc4_hdmi_codec_ops,
+	.max_i2s_channels = 8,
+	.i2s = 1,
+};
+
 static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 {
 	const struct vc4_hdmi_register *mai_data =
@@ -1523,6 +1475,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	struct snd_soc_dai_link *dai_link = &vc4_hdmi->audio.link;
 	struct snd_soc_card *card = &vc4_hdmi->audio.card;
 	struct device *dev = &vc4_hdmi->pdev->dev;
+	struct platform_device *codec_pdev;
 	const __be32 *addr;
 	int index;
 	int ret;
@@ -1569,12 +1522,13 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 		return ret;
 	}
 
-	/* register component and codec dai */
-	ret = devm_snd_soc_register_component(dev, &vc4_hdmi_audio_component_drv,
-				     &vc4_hdmi_audio_codec_dai_drv, 1);
-	if (ret) {
-		dev_err(dev, "Could not register component: %d\n", ret);
-		return ret;
+	codec_pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME,
+						   PLATFORM_DEVID_AUTO,
+						   &vc4_hdmi_codec_pdata,
+						   sizeof(vc4_hdmi_codec_pdata));
+	if (IS_ERR(codec_pdev)) {
+		dev_err(dev, "Couldn't register the HDMI codec: %ld\n", PTR_ERR(codec_pdev));
+		return PTR_ERR(codec_pdev);
 	}
 
 	dai_link->cpus		= &vc4_hdmi->audio.cpu;
@@ -1587,9 +1541,9 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 
 	dai_link->name = "MAI";
 	dai_link->stream_name = "MAI PCM";
-	dai_link->codecs->dai_name = vc4_hdmi_audio_codec_dai_drv.name;
+	dai_link->codecs->dai_name = "i2s-hifi";
 	dai_link->cpus->dai_name = dev_name(dev);
-	dai_link->codecs->name = dev_name(dev);
+	dai_link->codecs->name = dev_name(&codec_pdev->dev);
 	dai_link->platforms->name = dev_name(dev);
 
 	card->dai_link = dai_link;
@@ -1609,12 +1563,65 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	snd_soc_card_set_drvdata(card, vc4_hdmi);
 	ret = devm_snd_soc_register_card(dev, card);
 	if (ret)
-		dev_err(dev, "Could not register sound card: %d\n", ret);
+		dev_err_probe(dev, ret, "Could not register sound card\n");
 
 	return ret;
 
 }
 
+static irqreturn_t vc4_hdmi_hpd_irq_thread(int irq, void *priv)
+{
+	struct vc4_hdmi *vc4_hdmi = priv;
+	struct drm_device *dev = vc4_hdmi->connector.dev;
+
+	if (dev && dev->registered)
+		drm_kms_helper_hotplug_event(dev);
+
+	return IRQ_HANDLED;
+}
+
+static int vc4_hdmi_hotplug_init(struct vc4_hdmi *vc4_hdmi)
+{
+	struct drm_connector *connector = &vc4_hdmi->connector;
+	struct platform_device *pdev = vc4_hdmi->pdev;
+	int ret;
+
+	if (vc4_hdmi->variant->external_irq_controller) {
+		unsigned int hpd_con = platform_get_irq_byname(pdev, "hpd-connected");
+		unsigned int hpd_rm = platform_get_irq_byname(pdev, "hpd-removed");
+
+		ret = request_threaded_irq(hpd_con,
+					   NULL,
+					   vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
+					   "vc4 hdmi hpd connected", vc4_hdmi);
+		if (ret)
+			return ret;
+
+		ret = request_threaded_irq(hpd_rm,
+					   NULL,
+					   vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
+					   "vc4 hdmi hpd disconnected", vc4_hdmi);
+		if (ret) {
+			free_irq(hpd_con, vc4_hdmi);
+			return ret;
+		}
+
+		connector->polled = DRM_CONNECTOR_POLL_HPD;
+	}
+
+	return 0;
+}
+
+static void vc4_hdmi_hotplug_exit(struct vc4_hdmi *vc4_hdmi)
+{
+	struct platform_device *pdev = vc4_hdmi->pdev;
+
+	if (vc4_hdmi->variant->external_irq_controller) {
+		free_irq(platform_get_irq_byname(pdev, "hpd-connected"), vc4_hdmi);
+		free_irq(platform_get_irq_byname(pdev, "hpd-removed"), vc4_hdmi);
+	}
+}
+
 #ifdef CONFIG_DRM_VC4_HDMI_CEC
 static irqreturn_t vc4_cec_irq_handler_rx_thread(int irq, void *priv)
 {
@@ -2213,10 +2220,14 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		goto err_destroy_encoder;
 
-	ret = vc4_hdmi_cec_init(vc4_hdmi);
+	ret = vc4_hdmi_hotplug_init(vc4_hdmi);
 	if (ret)
 		goto err_destroy_conn;
 
+	ret = vc4_hdmi_cec_init(vc4_hdmi);
+	if (ret)
+		goto err_free_hotplug;
+
 	ret = vc4_hdmi_audio_init(vc4_hdmi);
 	if (ret)
 		goto err_free_cec;
@@ -2229,6 +2240,8 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 
 err_free_cec:
 	vc4_hdmi_cec_exit(vc4_hdmi);
+err_free_hotplug:
+	vc4_hdmi_hotplug_exit(vc4_hdmi);
 err_destroy_conn:
 	vc4_hdmi_connector_destroy(&vc4_hdmi->connector);
 err_destroy_encoder:
@@ -2270,6 +2283,7 @@ static void vc4_hdmi_unbind(struct device *dev, struct device *master,
 	kfree(vc4_hdmi->hd_regset.regs);
 
 	vc4_hdmi_cec_exit(vc4_hdmi);
+	vc4_hdmi_hotplug_exit(vc4_hdmi);
 	vc4_hdmi_connector_destroy(&vc4_hdmi->connector);
 	drm_encoder_cleanup(&vc4_hdmi->encoder.base.base);
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h
index 884d245507a9..33e9f665ab8e 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.h
@@ -111,11 +111,8 @@ struct vc4_hdmi_audio {
 	struct snd_soc_dai_link_component cpu;
 	struct snd_soc_dai_link_component codec;
 	struct snd_soc_dai_link_component platform;
-	int samplerate;
-	int channels;
 	struct snd_dmaengine_dai_dma_data dma_data;
-	struct snd_pcm_substream *substream;
-
+	struct hdmi_audio_infoframe infoframe;
 	bool streaming;
 };
 
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index e226c24e543f..20fa8e34c20b 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -45,6 +45,10 @@
  * current job can make progress.
  */
 
+#include <linux/platform_device.h>
+
+#include <drm/drm_drv.h>
+
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
@@ -192,7 +196,7 @@ vc4_irq_finish_render_job(struct drm_device *dev)
 	schedule_work(&vc4->job_done_work);
 }
 
-irqreturn_t
+static irqreturn_t
 vc4_irq(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
@@ -234,8 +238,8 @@ vc4_irq(int irq, void *arg)
 	return status;
 }
 
-void
-vc4_irq_preinstall(struct drm_device *dev)
+static void
+vc4_irq_prepare(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
@@ -251,24 +255,22 @@ vc4_irq_preinstall(struct drm_device *dev)
 	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
 }
 
-int
-vc4_irq_postinstall(struct drm_device *dev)
+void
+vc4_irq_enable(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
 	if (!vc4->v3d)
-		return 0;
+		return;
 
 	/* Enable the render done interrupts. The out-of-memory interrupt is
 	 * enabled as soon as we have a binner BO allocated.
 	 */
 	V3D_WRITE(V3D_INTENA, V3D_INT_FLDONE | V3D_INT_FRDONE);
-
-	return 0;
 }
 
 void
-vc4_irq_uninstall(struct drm_device *dev)
+vc4_irq_disable(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
@@ -282,11 +284,37 @@ vc4_irq_uninstall(struct drm_device *dev)
 	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
 
 	/* Finish any interrupt handler still in flight. */
-	disable_irq(dev->irq);
+	disable_irq(vc4->irq);
 
 	cancel_work_sync(&vc4->overflow_mem_work);
 }
 
+int vc4_irq_install(struct drm_device *dev, int irq)
+{
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	vc4_irq_prepare(dev);
+
+	ret = request_irq(irq, vc4_irq, 0, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	vc4_irq_enable(dev);
+
+	return 0;
+}
+
+void vc4_irq_uninstall(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	vc4_irq_disable(dev);
+	free_irq(vc4->irq, dev);
+}
+
 /** Reinitializes interrupt registers when a GPU reset is performed. */
 void vc4_irq_reset(struct drm_device *dev)
 {
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 6a1a9e1d72ce..f0b3e4cf5bce 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -880,7 +880,6 @@ int vc4_kms_load(struct drm_device *dev)
 	/* Set support for vblank irq fast disable, before drm_vblank_init() */
 	dev->vblank_disable_immediate = true;
 
-	dev->irq_enabled = true;
 	ret = drm_vblank_init(dev, dev->mode_config.num_crtc);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index be2c32a519b3..489f921ef44d 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -516,6 +516,36 @@
 # define VC4_HDMI_AUDIO_PACKET_CEA_MASK_MASK			VC4_MASK(7, 0)
 # define VC4_HDMI_AUDIO_PACKET_CEA_MASK_SHIFT			0
 
+# define VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT_MASK		VC4_MASK(23, 16)
+# define VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT_SHIFT		16
+
+enum {
+	VC4_HDMI_MAI_FORMAT_PCM = 2,
+	VC4_HDMI_MAI_FORMAT_HBR = 200,
+};
+
+# define VC4_HDMI_MAI_FORMAT_SAMPLE_RATE_MASK		VC4_MASK(15, 8)
+# define VC4_HDMI_MAI_FORMAT_SAMPLE_RATE_SHIFT		8
+
+enum {
+	VC4_HDMI_MAI_SAMPLE_RATE_NOT_INDICATED = 0,
+	VC4_HDMI_MAI_SAMPLE_RATE_8000 = 1,
+	VC4_HDMI_MAI_SAMPLE_RATE_11025 = 2,
+	VC4_HDMI_MAI_SAMPLE_RATE_12000 = 3,
+	VC4_HDMI_MAI_SAMPLE_RATE_16000 = 4,
+	VC4_HDMI_MAI_SAMPLE_RATE_22050 = 5,
+	VC4_HDMI_MAI_SAMPLE_RATE_24000 = 6,
+	VC4_HDMI_MAI_SAMPLE_RATE_32000 = 7,
+	VC4_HDMI_MAI_SAMPLE_RATE_44100 = 8,
+	VC4_HDMI_MAI_SAMPLE_RATE_48000 = 9,
+	VC4_HDMI_MAI_SAMPLE_RATE_64000 = 10,
+	VC4_HDMI_MAI_SAMPLE_RATE_88200 = 11,
+	VC4_HDMI_MAI_SAMPLE_RATE_96000 = 12,
+	VC4_HDMI_MAI_SAMPLE_RATE_128000 = 13,
+	VC4_HDMI_MAI_SAMPLE_RATE_176400 = 14,
+	VC4_HDMI_MAI_SAMPLE_RATE_192000 = 15,
+};
+
 # define VC4_HDMI_RAM_PACKET_ENABLE		BIT(16)
 
 /* When set, the CTS_PERIOD counts based on MAI bus sync pulse instead
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 73d63d72575b..7bb3067f8425 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -10,8 +10,6 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
-#include <drm/drm_irq.h>
-
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
@@ -361,7 +359,7 @@ static int vc4_v3d_runtime_suspend(struct device *dev)
 	struct vc4_v3d *v3d = dev_get_drvdata(dev);
 	struct vc4_dev *vc4 = v3d->vc4;
 
-	vc4_irq_uninstall(&vc4->base);
+	vc4_irq_disable(&vc4->base);
 
 	clk_disable_unprepare(v3d->clk);
 
@@ -381,8 +379,8 @@ static int vc4_v3d_runtime_resume(struct device *dev)
 	vc4_v3d_init_hw(&vc4->base);
 
 	/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
-	enable_irq(vc4->base.irq);
-	vc4_irq_postinstall(&vc4->base);
+	enable_irq(vc4->irq);
+	vc4_irq_enable(&vc4->base);
 
 	return 0;
 }
@@ -448,7 +446,12 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 
 	vc4_v3d_init_hw(drm);
 
-	ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	vc4->irq = ret;
+
+	ret = vc4_irq_install(drm, vc4->irq);
 	if (ret) {
 		DRM_ERROR("Failed to install IRQ handler\n");
 		return ret;
@@ -473,7 +476,7 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 
 	pm_runtime_disable(dev);
 
-	drm_irq_uninstall(drm);
+	vc4_irq_uninstall(drm);
 
 	/* Disable the binner's overflow memory address, so the next
 	 * driver probe (if any) doesn't try to reuse our old
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index dae1bacd86c1..c9afa1a51f23 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -29,7 +29,6 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_irq.h>
 #include <drm/via_drm.h>
 
 #include "via_drv.h"
@@ -86,7 +85,7 @@ int via_final_context(struct drm_device *dev, int context)
 	/* Last context, perform cleanup */
 	if (list_is_singular(&dev->ctxlist)) {
 		DRM_DEBUG("Last Context\n");
-		drm_irq_uninstall(dev);
+		drm_legacy_irq_uninstall(dev);
 		via_cleanup_futex(dev_priv);
 		via_do_cleanup_map(dev);
 	}
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index ca77edbc5ea0..ed85a7863256 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -57,7 +57,7 @@ static int virtio_gpu_pci_quirk(struct drm_device *dev, struct virtio_device *vd
 		 vga ? "virtio-vga" : "virtio-gpu-pci",
 		 pname);
 	if (vga) {
-		ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "virtiodrmfb");
+		ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index d9dbc4f258f3..d4e610a44e12 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -315,7 +315,9 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev,
 				   uint32_t resource_id,
 				   uint32_t x, uint32_t y,
-				   uint32_t width, uint32_t height);
+				   uint32_t width, uint32_t height,
+				   struct virtio_gpu_object_array *objs,
+				   struct virtio_gpu_fence *fence);
 void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev,
 				uint32_t scanout_id, uint32_t resource_id,
 				uint32_t width, uint32_t height,
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 4e1b17548007..a49fd9480381 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -129,6 +129,40 @@ static void virtio_gpu_update_dumb_bo(struct virtio_gpu_device *vgdev,
 					   objs, NULL);
 }
 
+static void virtio_gpu_resource_flush(struct drm_plane *plane,
+				      uint32_t x, uint32_t y,
+				      uint32_t width, uint32_t height)
+{
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_object *bo;
+
+	vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
+	if (vgfb->fence) {
+		struct virtio_gpu_object_array *objs;
+
+		objs = virtio_gpu_array_alloc(1);
+		if (!objs)
+			return;
+		virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
+		virtio_gpu_array_lock_resv(objs);
+		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
+					      width, height, objs, vgfb->fence);
+		virtio_gpu_notify(vgdev);
+
+		dma_fence_wait_timeout(&vgfb->fence->f, true,
+				       msecs_to_jiffies(50));
+		dma_fence_put(&vgfb->fence->f);
+		vgfb->fence = NULL;
+	} else {
+		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
+					      width, height, NULL, NULL);
+		virtio_gpu_notify(vgdev);
+	}
+}
+
 static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 					    struct drm_atomic_state *state)
 {
@@ -198,16 +232,15 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 		}
 	}
 
-	virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle,
-				      rect.x1,
-				      rect.y1,
-				      rect.x2 - rect.x1,
-				      rect.y2 - rect.y1);
-	virtio_gpu_notify(vgdev);
+	virtio_gpu_resource_flush(plane,
+				  rect.x1,
+				  rect.y1,
+				  rect.x2 - rect.x1,
+				  rect.y2 - rect.y1);
 }
 
-static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane,
-					struct drm_plane_state *new_state)
+static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
+				       struct drm_plane_state *new_state)
 {
 	struct drm_device *dev = plane->dev;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
@@ -219,7 +252,10 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane,
 
 	vgfb = to_virtio_gpu_framebuffer(new_state->fb);
 	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
-	if (bo && bo->dumb && (plane->state->fb != new_state->fb)) {
+	if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob))
+		return 0;
+
+	if (bo->dumb && (plane->state->fb != new_state->fb)) {
 		vgfb->fence = virtio_gpu_fence_alloc(vgdev);
 		if (!vgfb->fence)
 			return -ENOMEM;
@@ -228,8 +264,8 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane,
 	return 0;
 }
 
-static void virtio_gpu_cursor_cleanup_fb(struct drm_plane *plane,
-					 struct drm_plane_state *old_state)
+static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane,
+					struct drm_plane_state *old_state)
 {
 	struct virtio_gpu_framebuffer *vgfb;
 
@@ -321,13 +357,15 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs virtio_gpu_primary_helper_funcs = {
+	.prepare_fb		= virtio_gpu_plane_prepare_fb,
+	.cleanup_fb		= virtio_gpu_plane_cleanup_fb,
 	.atomic_check		= virtio_gpu_plane_atomic_check,
 	.atomic_update		= virtio_gpu_primary_plane_update,
 };
 
 static const struct drm_plane_helper_funcs virtio_gpu_cursor_helper_funcs = {
-	.prepare_fb		= virtio_gpu_cursor_prepare_fb,
-	.cleanup_fb		= virtio_gpu_cursor_cleanup_fb,
+	.prepare_fb		= virtio_gpu_plane_prepare_fb,
+	.cleanup_fb		= virtio_gpu_plane_cleanup_fb,
 	.atomic_check		= virtio_gpu_plane_atomic_check,
 	.atomic_update		= virtio_gpu_cursor_plane_update,
 };
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index 807a27a16365..e45dbf14b307 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -98,6 +98,8 @@ struct dma_buf *virtgpu_gem_prime_export(struct drm_gem_object *obj,
 		} else {
 			bo->uuid_state = STATE_ERR;
 		}
+	} else if (!(bo->blob_flags & VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE)) {
+		bo->uuid_state = STATE_ERR;
 	}
 
 	exp_info.ops = &virtgpu_dmabuf_ops.ops;
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index cf84d382dd41..2e71e91278b4 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -576,13 +576,16 @@ void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev,
 				   uint32_t resource_id,
 				   uint32_t x, uint32_t y,
-				   uint32_t width, uint32_t height)
+				   uint32_t width, uint32_t height,
+				   struct virtio_gpu_object_array *objs,
+				   struct virtio_gpu_fence *fence)
 {
 	struct virtio_gpu_resource_flush *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
 
 	cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));
 	memset(cmd_p, 0, sizeof(*cmd_p));
+	vbuf->objs = objs;
 
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_FLUSH);
 	cmd_p->resource_id = cpu_to_le32(resource_id);
@@ -591,7 +594,7 @@ void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev,
 	cmd_p->r.x = cpu_to_le32(x);
 	cmd_p->r.y = cpu_to_le32(y);
 
-	virtio_gpu_queue_ctrl_buffer(vgdev, vbuf);
+	virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, fence);
 }
 
 void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index e49523866e1d..9e8204be9a14 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -6,7 +6,6 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_vblank.h>
 
 #include "vkms_drv.h"
@@ -154,24 +153,21 @@ static void compose_plane(struct vkms_composer *primary_composer,
 			  struct vkms_composer *plane_composer,
 			  void *vaddr_out)
 {
-	struct drm_gem_object *plane_obj;
-	struct drm_gem_shmem_object *plane_shmem_obj;
 	struct drm_framebuffer *fb = &plane_composer->fb;
+	void *vaddr;
 	void (*pixel_blend)(const u8 *p_src, u8 *p_dst);
 
-	plane_obj = drm_gem_fb_get_obj(&plane_composer->fb, 0);
-	plane_shmem_obj = to_drm_gem_shmem_obj(plane_obj);
-
-	if (WARN_ON(!plane_shmem_obj->vaddr))
+	if (WARN_ON(dma_buf_map_is_null(&primary_composer->map[0])))
 		return;
 
+	vaddr = plane_composer->map[0].vaddr;
+
 	if (fb->format->format == DRM_FORMAT_ARGB8888)
 		pixel_blend = &alpha_blend;
 	else
 		pixel_blend = &x_blend;
 
-	blend(vaddr_out, plane_shmem_obj->vaddr, primary_composer,
-	      plane_composer, pixel_blend);
+	blend(vaddr_out, vaddr, primary_composer, plane_composer, pixel_blend);
 }
 
 static int compose_active_planes(void **vaddr_out,
@@ -180,21 +176,23 @@ static int compose_active_planes(void **vaddr_out,
 {
 	struct drm_framebuffer *fb = &primary_composer->fb;
 	struct drm_gem_object *gem_obj = drm_gem_fb_get_obj(fb, 0);
-	struct drm_gem_shmem_object *shmem_obj = to_drm_gem_shmem_obj(gem_obj);
+	const void *vaddr;
 	int i;
 
 	if (!*vaddr_out) {
-		*vaddr_out = kzalloc(shmem_obj->base.size, GFP_KERNEL);
+		*vaddr_out = kzalloc(gem_obj->size, GFP_KERNEL);
 		if (!*vaddr_out) {
 			DRM_ERROR("Cannot allocate memory for output frame.");
 			return -ENOMEM;
 		}
 	}
 
-	if (WARN_ON(!shmem_obj->vaddr))
+	if (WARN_ON(dma_buf_map_is_null(&primary_composer->map[0])))
 		return -EINVAL;
 
-	memcpy(*vaddr_out, shmem_obj->vaddr, shmem_obj->base.size);
+	vaddr = primary_composer->map[0].vaddr;
+
+	memcpy(*vaddr_out, vaddr, gem_obj->size);
 
 	/* If there are other planes besides primary, we consider the active
 	 * planes should be in z-order and compose them associatively:
@@ -251,7 +249,7 @@ void vkms_composer_worker(struct work_struct *work)
 
 	if (crtc_state->num_active_planes >= 1) {
 		act_plane = crtc_state->active_planes[0];
-		if (act_plane->base.plane->type == DRM_PLANE_TYPE_PRIMARY)
+		if (act_plane->base.base.plane->type == DRM_PLANE_TYPE_PRIMARY)
 			primary_composer = act_plane->composer;
 	}
 
@@ -259,7 +257,7 @@ void vkms_composer_worker(struct work_struct *work)
 		return;
 
 	if (wb_pending)
-		vaddr_out = crtc_state->active_writeback;
+		vaddr_out = crtc_state->active_writeback->data[0].vaddr;
 
 	ret = compose_active_planes(&vaddr_out, primary_composer,
 				    crtc_state);
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 027ffe759440..0ffe5f0e33f7 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -28,6 +28,9 @@
 
 #include "vkms_drv.h"
 
+#include <drm/drm_print.h>
+#include <drm/drm_debugfs.h>
+
 #define DRIVER_NAME	"vkms"
 #define DRIVER_DESC	"Virtual Kernel Mode Setting"
 #define DRIVER_DATE	"20180514"
@@ -52,7 +55,7 @@ DEFINE_DRM_GEM_FOPS(vkms_driver_fops);
 
 static void vkms_release(struct drm_device *dev)
 {
-	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
+	struct vkms_device *vkms = drm_device_to_vkms_device(dev);
 
 	destroy_workqueue(vkms->output.composer_workq);
 }
@@ -86,12 +89,37 @@ static void vkms_atomic_commit_tail(struct drm_atomic_state *old_state)
 	drm_atomic_helper_cleanup_planes(dev, old_state);
 }
 
+static int vkms_config_show(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct vkms_device *vkmsdev = drm_device_to_vkms_device(dev);
+
+	seq_printf(m, "writeback=%d\n", vkmsdev->config->writeback);
+	seq_printf(m, "cursor=%d\n", vkmsdev->config->cursor);
+	seq_printf(m, "overlay=%d\n", vkmsdev->config->overlay);
+
+	return 0;
+}
+
+static const struct drm_info_list vkms_config_debugfs_list[] = {
+	{ "vkms_config", vkms_config_show, 0 },
+};
+
+static void vkms_config_debugfs_init(struct drm_minor *minor)
+{
+	drm_debugfs_create_files(vkms_config_debugfs_list, ARRAY_SIZE(vkms_config_debugfs_list),
+				 minor->debugfs_root, minor);
+}
+
 static const struct drm_driver vkms_driver = {
 	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
 	.release		= vkms_release,
 	.fops			= &vkms_driver_fops,
 	DRM_GEM_SHMEM_DRIVER_OPS,
 
+	.debugfs_init           = vkms_config_debugfs_init,
+
 	.name			= DRIVER_NAME,
 	.desc			= DRIVER_DESC,
 	.date			= DRIVER_DATE,
@@ -163,8 +191,6 @@ static int vkms_create(struct vkms_config *config)
 		goto out_devres;
 	}
 
-	vkms_device->drm.irq_enabled = true;
-
 	ret = drm_vblank_init(&vkms_device->drm, 1);
 	if (ret) {
 		DRM_ERROR("Failed to vblank\n");
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index ac8c9c2fa4ed..d48c23d40ce5 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -7,6 +7,7 @@
 
 #include <drm/drm.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_writeback.h>
 
@@ -19,9 +20,15 @@
 #define XRES_MAX  8192
 #define YRES_MAX  8192
 
+struct vkms_writeback_job {
+	struct dma_buf_map map[DRM_FORMAT_MAX_PLANES];
+	struct dma_buf_map data[DRM_FORMAT_MAX_PLANES];
+};
+
 struct vkms_composer {
 	struct drm_framebuffer fb;
 	struct drm_rect src, dst;
+	struct dma_buf_map map[4];
 	unsigned int offset;
 	unsigned int pitch;
 	unsigned int cpp;
@@ -33,7 +40,7 @@ struct vkms_composer {
  * @composer: data required for composing computation
  */
 struct vkms_plane_state {
-	struct drm_plane_state base;
+	struct drm_shadow_plane_state base;
 	struct vkms_composer *composer;
 };
 
@@ -55,7 +62,7 @@ struct vkms_crtc_state {
 	int num_active_planes;
 	/* stack of active planes for crc computation, should be in z order */
 	struct vkms_plane_state **active_planes;
-	void *active_writeback;
+	struct vkms_writeback_job *active_writeback;
 
 	/* below four are protected by vkms_output.composer_lock */
 	bool crc_pending;
@@ -111,7 +118,7 @@ struct vkms_device {
 	container_of(target, struct vkms_crtc_state, base)
 
 #define to_vkms_plane_state(target)\
-	container_of(target, struct vkms_plane_state, base)
+	container_of(target, struct vkms_plane_state, base.base)
 
 /* CRTC */
 int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
index 107521ace597..32409e15244b 100644
--- a/drivers/gpu/drm/vkms/vkms_plane.c
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -8,7 +8,6 @@
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_plane_helper.h>
-#include <drm/drm_gem_shmem_helper.h>
 
 #include "vkms_drv.h"
 
@@ -40,17 +39,16 @@ vkms_plane_duplicate_state(struct drm_plane *plane)
 
 	vkms_state->composer = composer;
 
-	__drm_atomic_helper_plane_duplicate_state(plane,
-						  &vkms_state->base);
+	__drm_gem_duplicate_shadow_plane_state(plane, &vkms_state->base);
 
-	return &vkms_state->base;
+	return &vkms_state->base.base;
 }
 
 static void vkms_plane_destroy_state(struct drm_plane *plane,
 				     struct drm_plane_state *old_state)
 {
 	struct vkms_plane_state *vkms_state = to_vkms_plane_state(old_state);
-	struct drm_crtc *crtc = vkms_state->base.crtc;
+	struct drm_crtc *crtc = vkms_state->base.base.crtc;
 
 	if (crtc) {
 		/* dropping the reference we acquired in
@@ -63,7 +61,7 @@ static void vkms_plane_destroy_state(struct drm_plane *plane,
 	kfree(vkms_state->composer);
 	vkms_state->composer = NULL;
 
-	__drm_atomic_helper_plane_destroy_state(old_state);
+	__drm_gem_destroy_shadow_plane_state(&vkms_state->base);
 	kfree(vkms_state);
 }
 
@@ -71,8 +69,10 @@ static void vkms_plane_reset(struct drm_plane *plane)
 {
 	struct vkms_plane_state *vkms_state;
 
-	if (plane->state)
+	if (plane->state) {
 		vkms_plane_destroy_state(plane, plane->state);
+		plane->state = NULL; /* must be set to NULL here */
+	}
 
 	vkms_state = kzalloc(sizeof(*vkms_state), GFP_KERNEL);
 	if (!vkms_state) {
@@ -80,8 +80,7 @@ static void vkms_plane_reset(struct drm_plane *plane)
 		return;
 	}
 
-	plane->state = &vkms_state->base;
-	plane->state->plane = plane;
+	__drm_gem_reset_shadow_plane(plane, &vkms_state->base);
 }
 
 static const struct drm_plane_funcs vkms_plane_funcs = {
@@ -98,6 +97,7 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state,
 									   plane);
 	struct vkms_plane_state *vkms_plane_state;
+	struct drm_shadow_plane_state *shadow_plane_state;
 	struct drm_framebuffer *fb = new_state->fb;
 	struct vkms_composer *composer;
 
@@ -105,11 +105,13 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 		return;
 
 	vkms_plane_state = to_vkms_plane_state(new_state);
+	shadow_plane_state = &vkms_plane_state->base;
 
 	composer = vkms_plane_state->composer;
 	memcpy(&composer->src, &new_state->src, sizeof(struct drm_rect));
 	memcpy(&composer->dst, &new_state->dst, sizeof(struct drm_rect));
 	memcpy(&composer->fb, fb, sizeof(struct drm_framebuffer));
+	memcpy(&composer->map, &shadow_plane_state->data, sizeof(composer->map));
 	drm_framebuffer_get(&composer->fb);
 	composer->offset = fb->offsets[0];
 	composer->pitch = fb->pitches[0];
@@ -150,45 +152,10 @@ static int vkms_plane_atomic_check(struct drm_plane *plane,
 	return 0;
 }
 
-static int vkms_prepare_fb(struct drm_plane *plane,
-			   struct drm_plane_state *state)
-{
-	struct drm_gem_object *gem_obj;
-	struct dma_buf_map map;
-	int ret;
-
-	if (!state->fb)
-		return 0;
-
-	gem_obj = drm_gem_fb_get_obj(state->fb, 0);
-	ret = drm_gem_shmem_vmap(gem_obj, &map);
-	if (ret)
-		DRM_ERROR("vmap failed: %d\n", ret);
-
-	return drm_gem_plane_helper_prepare_fb(plane, state);
-}
-
-static void vkms_cleanup_fb(struct drm_plane *plane,
-			    struct drm_plane_state *old_state)
-{
-	struct drm_gem_object *gem_obj;
-	struct drm_gem_shmem_object *shmem_obj;
-	struct dma_buf_map map;
-
-	if (!old_state->fb)
-		return;
-
-	gem_obj = drm_gem_fb_get_obj(old_state->fb, 0);
-	shmem_obj = to_drm_gem_shmem_obj(drm_gem_fb_get_obj(old_state->fb, 0));
-	dma_buf_map_set_vaddr(&map, shmem_obj->vaddr);
-	drm_gem_shmem_vunmap(gem_obj, &map);
-}
-
 static const struct drm_plane_helper_funcs vkms_primary_helper_funcs = {
 	.atomic_update		= vkms_plane_atomic_update,
 	.atomic_check		= vkms_plane_atomic_check,
-	.prepare_fb		= vkms_prepare_fb,
-	.cleanup_fb		= vkms_cleanup_fb,
+	DRM_GEM_SHADOW_PLANE_HELPER_FUNCS,
 };
 
 struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev,
diff --git a/drivers/gpu/drm/vkms/vkms_writeback.c b/drivers/gpu/drm/vkms/vkms_writeback.c
index 0935686475a0..8694227f555f 100644
--- a/drivers/gpu/drm/vkms/vkms_writeback.c
+++ b/drivers/gpu/drm/vkms/vkms_writeback.c
@@ -65,41 +65,45 @@ static int vkms_wb_connector_get_modes(struct drm_connector *connector)
 static int vkms_wb_prepare_job(struct drm_writeback_connector *wb_connector,
 			       struct drm_writeback_job *job)
 {
-	struct drm_gem_object *gem_obj;
-	struct dma_buf_map map;
+	struct vkms_writeback_job *vkmsjob;
 	int ret;
 
 	if (!job->fb)
 		return 0;
 
-	gem_obj = drm_gem_fb_get_obj(job->fb, 0);
-	ret = drm_gem_shmem_vmap(gem_obj, &map);
+	vkmsjob = kzalloc(sizeof(*vkmsjob), GFP_KERNEL);
+	if (!vkmsjob)
+		return -ENOMEM;
+
+	ret = drm_gem_fb_vmap(job->fb, vkmsjob->map, vkmsjob->data);
 	if (ret) {
 		DRM_ERROR("vmap failed: %d\n", ret);
-		return ret;
+		goto err_kfree;
 	}
 
-	job->priv = map.vaddr;
+	job->priv = vkmsjob;
 
 	return 0;
+
+err_kfree:
+	kfree(vkmsjob);
+	return ret;
 }
 
 static void vkms_wb_cleanup_job(struct drm_writeback_connector *connector,
 				struct drm_writeback_job *job)
 {
-	struct drm_gem_object *gem_obj;
+	struct vkms_writeback_job *vkmsjob = job->priv;
 	struct vkms_device *vkmsdev;
-	struct dma_buf_map map;
 
 	if (!job->fb)
 		return;
 
-	gem_obj = drm_gem_fb_get_obj(job->fb, 0);
-	dma_buf_map_set_vaddr(&map, job->priv);
-	drm_gem_shmem_vunmap(gem_obj, &map);
+	drm_gem_fb_vunmap(job->fb, vkmsjob->map);
 
-	vkmsdev = drm_device_to_vkms_device(gem_obj->dev);
+	vkmsdev = drm_device_to_vkms_device(job->fb->dev);
 	vkms_set_composer(&vkmsdev->output, false);
+	kfree(vkmsjob);
 }
 
 static void vkms_wb_atomic_commit(struct drm_connector *conn,
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 0060ef842b5a..c9ce47c448e0 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -22,3 +22,11 @@ config DRM_VMWGFX_FBCON
 	   Choose this option if you are shipping a new vmwgfx
 	   userspace driver that supports using the kernel driver.
 
+config DRM_VMWGFX_MKSSTATS
+	bool "Enable mksGuestStats instrumentation of vmwgfx by default"
+	depends on DRM_VMWGFX
+	depends on X86
+	default n
+	help
+	   Choose this option to instrument the kernel driver for mksGuestStats.
+
diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile
index 09f6dcac768b..bc323f7d4032 100644
--- a/drivers/gpu/drm/vmwgfx/Makefile
+++ b/drivers/gpu/drm/vmwgfx/Makefile
@@ -9,7 +9,7 @@ vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \
 	    vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \
 	    vmwgfx_simple_resource.o vmwgfx_va.o vmwgfx_blit.o \
 	    vmwgfx_validation.o vmwgfx_page_dirty.o vmwgfx_streamoutput.o \
-	    ttm_object.o ttm_memory.o
+            vmwgfx_devcaps.o ttm_object.o ttm_memory.o
 
 vmwgfx-$(CONFIG_DRM_FBDEV_EMULATION) += vmwgfx_fb.o
 vmwgfx-$(CONFIG_TRANSPARENT_HUGEPAGE) += vmwgfx_thp.o
diff --git a/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h b/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h
deleted file mode 100644
index 8cce7f15b6eb..000000000000
--- a/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * Intentionally empty file.
- */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
deleted file mode 100644
index 69c4253fbfbb..000000000000
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
-/**********************************************************
- * Copyright 2007-2015 VMware, Inc.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
-
-/*
- * svga3d_caps.h --
- *
- *       Definitions for SVGA3D hardware capabilities.  Capabilities
- *       are used to query for optional rendering features during
- *       driver initialization. The capability data is stored as very
- *       basic key/value dictionary within the "FIFO register" memory
- *       area at the beginning of BAR2.
- *
- *       Note that these definitions are only for 3D capabilities.
- *       The SVGA device also has "device capabilities" and "FIFO
- *       capabilities", which are non-3D-specific and are stored as
- *       bitfields rather than key/value pairs.
- */
-
-#ifndef _SVGA3D_CAPS_H_
-#define _SVGA3D_CAPS_H_
-
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-
-#include "includeCheck.h"
-
-#include "svga_reg.h"
-
-#define SVGA_FIFO_3D_CAPS_SIZE   (SVGA_FIFO_3D_CAPS_LAST - \
-                                  SVGA_FIFO_3D_CAPS + 1)
-
-
-/*
- * SVGA3dCapsRecordType
- *
- *    Record types that can be found in the caps block.
- *    Related record types are grouped together numerically so that
- *    SVGA3dCaps_FindRecord() can be applied on a range of record
- *    types.
- */
-
-typedef enum {
-   SVGA3DCAPS_RECORD_UNKNOWN        = 0,
-   SVGA3DCAPS_RECORD_DEVCAPS_MIN    = 0x100,
-   SVGA3DCAPS_RECORD_DEVCAPS        = 0x100,
-   SVGA3DCAPS_RECORD_DEVCAPS_MAX    = 0x1ff,
-} SVGA3dCapsRecordType;
-
-
-/*
- * SVGA3dCapsRecordHeader
- *
- *    Header field leading each caps block record. Contains the offset (in
- *    register words, NOT bytes) to the next caps block record (or the end
- *    of caps block records which will be a zero word) and the record type
- *    as defined above.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCapsRecordHeader {
-   uint32 length;
-   SVGA3dCapsRecordType type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCapsRecordHeader;
-
-
-/*
- * SVGA3dCapsRecord
- *
- *    Caps block record; "data" is a placeholder for the actual data structure
- *    contained within the record;
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCapsRecord {
-   SVGA3dCapsRecordHeader header;
-   uint32 data[1];
-}
-#include "vmware_pack_end.h"
-SVGA3dCapsRecord;
-
-
-typedef uint32 SVGA3dCapPair[2];
-
-#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
index 799bc0963f7a..945c84b27e81 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2020 VMware, Inc.
+ * Copyright 2012-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,2249 +27,1487 @@
 /*
  * svga3d_cmd.h --
  *
- *       SVGA 3d hardware cmd definitions
+ *    SVGA 3d hardware cmd definitions
  */
 
+
+
 #ifndef _SVGA3D_CMD_H_
 #define _SVGA3D_CMD_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
-
-#include "includeCheck.h"
 #include "svga3d_types.h"
-
-/*
- * Identifiers for commands in the command FIFO.
- *
- * IDs between 1000 and 1039 (inclusive) were used by obsolete versions of
- * the SVGA3D protocol and remain reserved; they should not be used in the
- * future.
- *
- * IDs between 1040 and 2999 (inclusive) are available for use by the
- * current SVGA3D protocol.
- *
- * FIFO clients other than SVGA3D should stay below 1000, or at 3000
- * and up.
- */
-
-typedef enum {
-   SVGA_3D_CMD_LEGACY_BASE                                = 1000,
-   SVGA_3D_CMD_BASE                                       = 1040,
-
-   SVGA_3D_CMD_SURFACE_DEFINE                             = 1040,
-   SVGA_3D_CMD_SURFACE_DESTROY                            = 1041,
-   SVGA_3D_CMD_SURFACE_COPY                               = 1042,
-   SVGA_3D_CMD_SURFACE_STRETCHBLT                         = 1043,
-   SVGA_3D_CMD_SURFACE_DMA                                = 1044,
-   SVGA_3D_CMD_CONTEXT_DEFINE                             = 1045,
-   SVGA_3D_CMD_CONTEXT_DESTROY                            = 1046,
-   SVGA_3D_CMD_SETTRANSFORM                               = 1047,
-   SVGA_3D_CMD_SETZRANGE                                  = 1048,
-   SVGA_3D_CMD_SETRENDERSTATE                             = 1049,
-   SVGA_3D_CMD_SETRENDERTARGET                            = 1050,
-   SVGA_3D_CMD_SETTEXTURESTATE                            = 1051,
-   SVGA_3D_CMD_SETMATERIAL                                = 1052,
-   SVGA_3D_CMD_SETLIGHTDATA                               = 1053,
-   SVGA_3D_CMD_SETLIGHTENABLED                            = 1054,
-   SVGA_3D_CMD_SETVIEWPORT                                = 1055,
-   SVGA_3D_CMD_SETCLIPPLANE                               = 1056,
-   SVGA_3D_CMD_CLEAR                                      = 1057,
-   SVGA_3D_CMD_PRESENT                                    = 1058,
-   SVGA_3D_CMD_SHADER_DEFINE                              = 1059,
-   SVGA_3D_CMD_SHADER_DESTROY                             = 1060,
-   SVGA_3D_CMD_SET_SHADER                                 = 1061,
-   SVGA_3D_CMD_SET_SHADER_CONST                           = 1062,
-   SVGA_3D_CMD_DRAW_PRIMITIVES                            = 1063,
-   SVGA_3D_CMD_SETSCISSORRECT                             = 1064,
-   SVGA_3D_CMD_BEGIN_QUERY                                = 1065,
-   SVGA_3D_CMD_END_QUERY                                  = 1066,
-   SVGA_3D_CMD_WAIT_FOR_QUERY                             = 1067,
-   SVGA_3D_CMD_PRESENT_READBACK                           = 1068,
-   SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN                     = 1069,
-   SVGA_3D_CMD_SURFACE_DEFINE_V2                          = 1070,
-   SVGA_3D_CMD_GENERATE_MIPMAPS                           = 1071,
-   SVGA_3D_CMD_DEAD4                                      = 1072,
-   SVGA_3D_CMD_DEAD5                                      = 1073,
-   SVGA_3D_CMD_DEAD6                                      = 1074,
-   SVGA_3D_CMD_DEAD7                                      = 1075,
-   SVGA_3D_CMD_DEAD8                                      = 1076,
-   SVGA_3D_CMD_DEAD9                                      = 1077,
-   SVGA_3D_CMD_DEAD10                                     = 1078,
-   SVGA_3D_CMD_DEAD11                                     = 1079,
-   SVGA_3D_CMD_ACTIVATE_SURFACE                           = 1080,
-   SVGA_3D_CMD_DEACTIVATE_SURFACE                         = 1081,
-   SVGA_3D_CMD_SCREEN_DMA                                 = 1082,
-   SVGA_3D_CMD_DEAD1                                      = 1083,
-   SVGA_3D_CMD_DEAD2                                      = 1084,
-
-   SVGA_3D_CMD_DEAD12                                     = 1085,
-   SVGA_3D_CMD_DEAD13                                     = 1086,
-   SVGA_3D_CMD_DEAD14                                     = 1087,
-   SVGA_3D_CMD_DEAD15                                     = 1088,
-   SVGA_3D_CMD_DEAD16                                     = 1089,
-   SVGA_3D_CMD_DEAD17                                     = 1090,
-
-   SVGA_3D_CMD_SET_OTABLE_BASE                            = 1091,
-   SVGA_3D_CMD_READBACK_OTABLE                            = 1092,
-
-   SVGA_3D_CMD_DEFINE_GB_MOB                              = 1093,
-   SVGA_3D_CMD_DESTROY_GB_MOB                             = 1094,
-   SVGA_3D_CMD_DEAD3                                      = 1095,
-   SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING                      = 1096,
-
-   SVGA_3D_CMD_DEFINE_GB_SURFACE                          = 1097,
-   SVGA_3D_CMD_DESTROY_GB_SURFACE                         = 1098,
-   SVGA_3D_CMD_BIND_GB_SURFACE                            = 1099,
-   SVGA_3D_CMD_COND_BIND_GB_SURFACE                       = 1100,
-   SVGA_3D_CMD_UPDATE_GB_IMAGE                            = 1101,
-   SVGA_3D_CMD_UPDATE_GB_SURFACE                          = 1102,
-   SVGA_3D_CMD_READBACK_GB_IMAGE                          = 1103,
-   SVGA_3D_CMD_READBACK_GB_SURFACE                        = 1104,
-   SVGA_3D_CMD_INVALIDATE_GB_IMAGE                        = 1105,
-   SVGA_3D_CMD_INVALIDATE_GB_SURFACE                      = 1106,
-
-   SVGA_3D_CMD_DEFINE_GB_CONTEXT                          = 1107,
-   SVGA_3D_CMD_DESTROY_GB_CONTEXT                         = 1108,
-   SVGA_3D_CMD_BIND_GB_CONTEXT                            = 1109,
-   SVGA_3D_CMD_READBACK_GB_CONTEXT                        = 1110,
-   SVGA_3D_CMD_INVALIDATE_GB_CONTEXT                      = 1111,
-
-   SVGA_3D_CMD_DEFINE_GB_SHADER                           = 1112,
-   SVGA_3D_CMD_DESTROY_GB_SHADER                          = 1113,
-   SVGA_3D_CMD_BIND_GB_SHADER                             = 1114,
-
-   SVGA_3D_CMD_SET_OTABLE_BASE64                          = 1115,
-
-   SVGA_3D_CMD_BEGIN_GB_QUERY                             = 1116,
-   SVGA_3D_CMD_END_GB_QUERY                               = 1117,
-   SVGA_3D_CMD_WAIT_FOR_GB_QUERY                          = 1118,
-
-   SVGA_3D_CMD_NOP                                        = 1119,
-
-   SVGA_3D_CMD_ENABLE_GART                                = 1120,
-   SVGA_3D_CMD_DISABLE_GART                               = 1121,
-   SVGA_3D_CMD_MAP_MOB_INTO_GART                          = 1122,
-   SVGA_3D_CMD_UNMAP_GART_RANGE                           = 1123,
-
-   SVGA_3D_CMD_DEFINE_GB_SCREENTARGET                     = 1124,
-   SVGA_3D_CMD_DESTROY_GB_SCREENTARGET                    = 1125,
-   SVGA_3D_CMD_BIND_GB_SCREENTARGET                       = 1126,
-   SVGA_3D_CMD_UPDATE_GB_SCREENTARGET                     = 1127,
-
-   SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL                  = 1128,
-   SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL                = 1129,
-
-   SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE                 = 1130,
-
-   SVGA_3D_CMD_GB_SCREEN_DMA                              = 1131,
-   SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH                 = 1132,
-   SVGA_3D_CMD_GB_MOB_FENCE                               = 1133,
-   SVGA_3D_CMD_DEFINE_GB_SURFACE_V2                       = 1134,
-   SVGA_3D_CMD_DEFINE_GB_MOB64                            = 1135,
-   SVGA_3D_CMD_REDEFINE_GB_MOB64                          = 1136,
-   SVGA_3D_CMD_NOP_ERROR                                  = 1137,
-
-   SVGA_3D_CMD_SET_VERTEX_STREAMS                         = 1138,
-   SVGA_3D_CMD_SET_VERTEX_DECLS                           = 1139,
-   SVGA_3D_CMD_SET_VERTEX_DIVISORS                        = 1140,
-   SVGA_3D_CMD_DRAW                                       = 1141,
-   SVGA_3D_CMD_DRAW_INDEXED                               = 1142,
-
-   /*
-    * DX10 Commands
-    */
-   SVGA_3D_CMD_DX_MIN                                     = 1143,
-   SVGA_3D_CMD_DX_DEFINE_CONTEXT                          = 1143,
-   SVGA_3D_CMD_DX_DESTROY_CONTEXT                         = 1144,
-   SVGA_3D_CMD_DX_BIND_CONTEXT                            = 1145,
-   SVGA_3D_CMD_DX_READBACK_CONTEXT                        = 1146,
-   SVGA_3D_CMD_DX_INVALIDATE_CONTEXT                      = 1147,
-   SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER              = 1148,
-   SVGA_3D_CMD_DX_SET_SHADER_RESOURCES                    = 1149,
-   SVGA_3D_CMD_DX_SET_SHADER                              = 1150,
-   SVGA_3D_CMD_DX_SET_SAMPLERS                            = 1151,
-   SVGA_3D_CMD_DX_DRAW                                    = 1152,
-   SVGA_3D_CMD_DX_DRAW_INDEXED                            = 1153,
-   SVGA_3D_CMD_DX_DRAW_INSTANCED                          = 1154,
-   SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED                  = 1155,
-   SVGA_3D_CMD_DX_DRAW_AUTO                               = 1156,
-   SVGA_3D_CMD_DX_SET_INPUT_LAYOUT                        = 1157,
-   SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS                      = 1158,
-   SVGA_3D_CMD_DX_SET_INDEX_BUFFER                        = 1159,
-   SVGA_3D_CMD_DX_SET_TOPOLOGY                            = 1160,
-   SVGA_3D_CMD_DX_SET_RENDERTARGETS                       = 1161,
-   SVGA_3D_CMD_DX_SET_BLEND_STATE                         = 1162,
-   SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE                  = 1163,
-   SVGA_3D_CMD_DX_SET_RASTERIZER_STATE                    = 1164,
-   SVGA_3D_CMD_DX_DEFINE_QUERY                            = 1165,
-   SVGA_3D_CMD_DX_DESTROY_QUERY                           = 1166,
-   SVGA_3D_CMD_DX_BIND_QUERY                              = 1167,
-   SVGA_3D_CMD_DX_SET_QUERY_OFFSET                        = 1168,
-   SVGA_3D_CMD_DX_BEGIN_QUERY                             = 1169,
-   SVGA_3D_CMD_DX_END_QUERY                               = 1170,
-   SVGA_3D_CMD_DX_READBACK_QUERY                          = 1171,
-   SVGA_3D_CMD_DX_SET_PREDICATION                         = 1172,
-   SVGA_3D_CMD_DX_SET_SOTARGETS                           = 1173,
-   SVGA_3D_CMD_DX_SET_VIEWPORTS                           = 1174,
-   SVGA_3D_CMD_DX_SET_SCISSORRECTS                        = 1175,
-   SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW                 = 1176,
-   SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW                 = 1177,
-   SVGA_3D_CMD_DX_PRED_COPY_REGION                        = 1178,
-   SVGA_3D_CMD_DX_PRED_COPY                               = 1179,
-   SVGA_3D_CMD_DX_PRESENTBLT                              = 1180,
-   SVGA_3D_CMD_DX_GENMIPS                                 = 1181,
-   SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE                      = 1182,
-   SVGA_3D_CMD_DX_READBACK_SUBRESOURCE                    = 1183,
-   SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE                  = 1184,
-   SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW              = 1185,
-   SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW             = 1186,
-   SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW                = 1187,
-   SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW               = 1188,
-   SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW                = 1189,
-   SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW               = 1190,
-   SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT                    = 1191,
-   SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT                   = 1192,
-   SVGA_3D_CMD_DX_DEFINE_BLEND_STATE                      = 1193,
-   SVGA_3D_CMD_DX_DESTROY_BLEND_STATE                     = 1194,
-   SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE               = 1195,
-   SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE              = 1196,
-   SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE                 = 1197,
-   SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE                = 1198,
-   SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE                    = 1199,
-   SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE                   = 1200,
-   SVGA_3D_CMD_DX_DEFINE_SHADER                           = 1201,
-   SVGA_3D_CMD_DX_DESTROY_SHADER                          = 1202,
-   SVGA_3D_CMD_DX_BIND_SHADER                             = 1203,
-   SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT                     = 1204,
-   SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT                    = 1205,
-   SVGA_3D_CMD_DX_SET_STREAMOUTPUT                        = 1206,
-   SVGA_3D_CMD_DX_SET_COTABLE                             = 1207,
-   SVGA_3D_CMD_DX_READBACK_COTABLE                        = 1208,
-   SVGA_3D_CMD_DX_BUFFER_COPY                             = 1209,
-   SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER                    = 1210,
-   SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK               = 1211,
-   SVGA_3D_CMD_DX_MOVE_QUERY                              = 1212,
-   SVGA_3D_CMD_DX_BIND_ALL_QUERY                          = 1213,
-   SVGA_3D_CMD_DX_READBACK_ALL_QUERY                      = 1214,
-   SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER               = 1215,
-   SVGA_3D_CMD_DX_MOB_FENCE_64                            = 1216,
-   SVGA_3D_CMD_DX_BIND_ALL_SHADER                         = 1217,
-   SVGA_3D_CMD_DX_HINT                                    = 1218,
-   SVGA_3D_CMD_DX_BUFFER_UPDATE                           = 1219,
-   SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET           = 1220,
-   SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET           = 1221,
-   SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET           = 1222,
-   SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET           = 1223,
-   SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET           = 1224,
-   SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET           = 1225,
-
-   SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER                    = 1226,
-   SVGA_3D_CMD_DX_MAX                                     = 1227,
-
-   SVGA_3D_CMD_SCREEN_COPY                                = 1227,
-
-   SVGA_3D_CMD_RESERVED1                                  = 1228,
-   SVGA_3D_CMD_RESERVED2                                  = 1229,
-   SVGA_3D_CMD_RESERVED3                                  = 1230,
-   SVGA_3D_CMD_RESERVED4                                  = 1231,
-   SVGA_3D_CMD_RESERVED5                                  = 1232,
-   SVGA_3D_CMD_RESERVED6                                  = 1233,
-   SVGA_3D_CMD_RESERVED7                                  = 1234,
-   SVGA_3D_CMD_RESERVED8                                  = 1235,
-
-   SVGA_3D_CMD_GROW_OTABLE                                = 1236,
-   SVGA_3D_CMD_DX_GROW_COTABLE                            = 1237,
-   SVGA_3D_CMD_INTRA_SURFACE_COPY                         = 1238,
-
-   SVGA_3D_CMD_DEFINE_GB_SURFACE_V3                       = 1239,
-
-   SVGA_3D_CMD_DX_RESOLVE_COPY                            = 1240,
-   SVGA_3D_CMD_DX_PRED_RESOLVE_COPY                       = 1241,
-   SVGA_3D_CMD_DX_PRED_CONVERT_REGION                     = 1242,
-   SVGA_3D_CMD_DX_PRED_CONVERT                            = 1243,
-   SVGA_3D_CMD_WHOLE_SURFACE_COPY                         = 1244,
-
-   SVGA_3D_CMD_DX_DEFINE_UA_VIEW                          = 1245,
-   SVGA_3D_CMD_DX_DESTROY_UA_VIEW                         = 1246,
-   SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT                      = 1247,
-   SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT                     = 1248,
-   SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT                    = 1249,
-   SVGA_3D_CMD_DX_SET_UA_VIEWS                            = 1250,
-
-   SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT         = 1251,
-   SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT                 = 1252,
-   SVGA_3D_CMD_DX_DISPATCH                                = 1253,
-   SVGA_3D_CMD_DX_DISPATCH_INDIRECT                       = 1254,
-
-   SVGA_3D_CMD_WRITE_ZERO_SURFACE                         = 1255,
-   SVGA_3D_CMD_HINT_ZERO_SURFACE                          = 1256,
-   SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER                      = 1257,
-   SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT                     = 1258,
-
-   SVGA_3D_CMD_LOGICOPS_BITBLT                            = 1259,
-   SVGA_3D_CMD_LOGICOPS_TRANSBLT                          = 1260,
-   SVGA_3D_CMD_LOGICOPS_STRETCHBLT                        = 1261,
-   SVGA_3D_CMD_LOGICOPS_COLORFILL                         = 1262,
-   SVGA_3D_CMD_LOGICOPS_ALPHABLEND                        = 1263,
-   SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND                    = 1264,
-
-   SVGA_3D_CMD_RESERVED2_1                                = 1265,
-
-   SVGA_3D_CMD_RESERVED2_2                                = 1266,
-   SVGA_3D_CMD_DEFINE_GB_SURFACE_V4                       = 1267,
-   SVGA_3D_CMD_DX_SET_CS_UA_VIEWS                         = 1268,
-   SVGA_3D_CMD_DX_SET_MIN_LOD                             = 1269,
-   SVGA_3D_CMD_RESERVED2_3                                = 1270,
-   SVGA_3D_CMD_RESERVED2_4                                = 1271,
-   SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2             = 1272,
-   SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB            = 1273,
-   SVGA_3D_CMD_DX_SET_SHADER_IFACE                        = 1274,
-   SVGA_3D_CMD_DX_BIND_STREAMOUTPUT                       = 1275,
-   SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS            = 1276,
-   SVGA_3D_CMD_DX_BIND_SHADER_IFACE                       = 1277,
-
-   SVGA_3D_CMD_MAX                                        = 1278,
-   SVGA_3D_CMD_FUTURE_MAX                                 = 3000
+#include "svga3d_limits.h"
+#include "svga_reg.h"
+
+typedef enum SVGAFifo3dCmdId {
+	SVGA_3D_CMD_LEGACY_BASE = 1000,
+	SVGA_3D_CMD_BASE = 1040,
+
+	SVGA_3D_CMD_SURFACE_DEFINE = 1040,
+	SVGA_3D_CMD_SURFACE_DESTROY = 1041,
+	SVGA_3D_CMD_SURFACE_COPY = 1042,
+	SVGA_3D_CMD_SURFACE_STRETCHBLT = 1043,
+	SVGA_3D_CMD_SURFACE_DMA = 1044,
+	SVGA_3D_CMD_CONTEXT_DEFINE = 1045,
+	SVGA_3D_CMD_CONTEXT_DESTROY = 1046,
+	SVGA_3D_CMD_SETTRANSFORM = 1047,
+	SVGA_3D_CMD_SETZRANGE = 1048,
+	SVGA_3D_CMD_SETRENDERSTATE = 1049,
+	SVGA_3D_CMD_SETRENDERTARGET = 1050,
+	SVGA_3D_CMD_SETTEXTURESTATE = 1051,
+	SVGA_3D_CMD_SETMATERIAL = 1052,
+	SVGA_3D_CMD_SETLIGHTDATA = 1053,
+	SVGA_3D_CMD_SETLIGHTENABLED = 1054,
+	SVGA_3D_CMD_SETVIEWPORT = 1055,
+	SVGA_3D_CMD_SETCLIPPLANE = 1056,
+	SVGA_3D_CMD_CLEAR = 1057,
+	SVGA_3D_CMD_PRESENT = 1058,
+	SVGA_3D_CMD_SHADER_DEFINE = 1059,
+	SVGA_3D_CMD_SHADER_DESTROY = 1060,
+	SVGA_3D_CMD_SET_SHADER = 1061,
+	SVGA_3D_CMD_SET_SHADER_CONST = 1062,
+	SVGA_3D_CMD_DRAW_PRIMITIVES = 1063,
+	SVGA_3D_CMD_SETSCISSORRECT = 1064,
+	SVGA_3D_CMD_BEGIN_QUERY = 1065,
+	SVGA_3D_CMD_END_QUERY = 1066,
+	SVGA_3D_CMD_WAIT_FOR_QUERY = 1067,
+	SVGA_3D_CMD_PRESENT_READBACK = 1068,
+	SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN = 1069,
+	SVGA_3D_CMD_SURFACE_DEFINE_V2 = 1070,
+	SVGA_3D_CMD_GENERATE_MIPMAPS = 1071,
+	SVGA_3D_CMD_DEAD4 = 1072,
+	SVGA_3D_CMD_DEAD5 = 1073,
+	SVGA_3D_CMD_DEAD6 = 1074,
+	SVGA_3D_CMD_DEAD7 = 1075,
+	SVGA_3D_CMD_DEAD8 = 1076,
+	SVGA_3D_CMD_DEAD9 = 1077,
+	SVGA_3D_CMD_DEAD10 = 1078,
+	SVGA_3D_CMD_DEAD11 = 1079,
+	SVGA_3D_CMD_ACTIVATE_SURFACE = 1080,
+	SVGA_3D_CMD_DEACTIVATE_SURFACE = 1081,
+	SVGA_3D_CMD_SCREEN_DMA = 1082,
+	SVGA_3D_CMD_DEAD1 = 1083,
+	SVGA_3D_CMD_DEAD2 = 1084,
+
+	SVGA_3D_CMD_DEAD12 = 1085,
+	SVGA_3D_CMD_DEAD13 = 1086,
+	SVGA_3D_CMD_DEAD14 = 1087,
+	SVGA_3D_CMD_DEAD15 = 1088,
+	SVGA_3D_CMD_DEAD16 = 1089,
+	SVGA_3D_CMD_DEAD17 = 1090,
+
+	SVGA_3D_CMD_SET_OTABLE_BASE = 1091,
+	SVGA_3D_CMD_READBACK_OTABLE = 1092,
+
+	SVGA_3D_CMD_DEFINE_GB_MOB = 1093,
+	SVGA_3D_CMD_DESTROY_GB_MOB = 1094,
+	SVGA_3D_CMD_DEAD3 = 1095,
+	SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING = 1096,
+
+	SVGA_3D_CMD_DEFINE_GB_SURFACE = 1097,
+	SVGA_3D_CMD_DESTROY_GB_SURFACE = 1098,
+	SVGA_3D_CMD_BIND_GB_SURFACE = 1099,
+	SVGA_3D_CMD_COND_BIND_GB_SURFACE = 1100,
+	SVGA_3D_CMD_UPDATE_GB_IMAGE = 1101,
+	SVGA_3D_CMD_UPDATE_GB_SURFACE = 1102,
+	SVGA_3D_CMD_READBACK_GB_IMAGE = 1103,
+	SVGA_3D_CMD_READBACK_GB_SURFACE = 1104,
+	SVGA_3D_CMD_INVALIDATE_GB_IMAGE = 1105,
+	SVGA_3D_CMD_INVALIDATE_GB_SURFACE = 1106,
+
+	SVGA_3D_CMD_DEFINE_GB_CONTEXT = 1107,
+	SVGA_3D_CMD_DESTROY_GB_CONTEXT = 1108,
+	SVGA_3D_CMD_BIND_GB_CONTEXT = 1109,
+	SVGA_3D_CMD_READBACK_GB_CONTEXT = 1110,
+	SVGA_3D_CMD_INVALIDATE_GB_CONTEXT = 1111,
+
+	SVGA_3D_CMD_DEFINE_GB_SHADER = 1112,
+	SVGA_3D_CMD_DESTROY_GB_SHADER = 1113,
+	SVGA_3D_CMD_BIND_GB_SHADER = 1114,
+
+	SVGA_3D_CMD_SET_OTABLE_BASE64 = 1115,
+
+	SVGA_3D_CMD_BEGIN_GB_QUERY = 1116,
+	SVGA_3D_CMD_END_GB_QUERY = 1117,
+	SVGA_3D_CMD_WAIT_FOR_GB_QUERY = 1118,
+
+	SVGA_3D_CMD_NOP = 1119,
+
+	SVGA_3D_CMD_ENABLE_GART = 1120,
+	SVGA_3D_CMD_DISABLE_GART = 1121,
+	SVGA_3D_CMD_MAP_MOB_INTO_GART = 1122,
+	SVGA_3D_CMD_UNMAP_GART_RANGE = 1123,
+
+	SVGA_3D_CMD_DEFINE_GB_SCREENTARGET = 1124,
+	SVGA_3D_CMD_DESTROY_GB_SCREENTARGET = 1125,
+	SVGA_3D_CMD_BIND_GB_SCREENTARGET = 1126,
+	SVGA_3D_CMD_UPDATE_GB_SCREENTARGET = 1127,
+
+	SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL = 1128,
+	SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL = 1129,
+
+	SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE = 1130,
+
+	SVGA_3D_CMD_GB_SCREEN_DMA = 1131,
+	SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH = 1132,
+	SVGA_3D_CMD_GB_MOB_FENCE = 1133,
+	SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 = 1134,
+	SVGA_3D_CMD_DEFINE_GB_MOB64 = 1135,
+	SVGA_3D_CMD_REDEFINE_GB_MOB64 = 1136,
+	SVGA_3D_CMD_NOP_ERROR = 1137,
+
+	SVGA_3D_CMD_SET_VERTEX_STREAMS = 1138,
+	SVGA_3D_CMD_SET_VERTEX_DECLS = 1139,
+	SVGA_3D_CMD_SET_VERTEX_DIVISORS = 1140,
+	SVGA_3D_CMD_DRAW = 1141,
+	SVGA_3D_CMD_DRAW_INDEXED = 1142,
+
+	SVGA_3D_CMD_DX_MIN = 1143,
+	SVGA_3D_CMD_DX_DEFINE_CONTEXT = 1143,
+	SVGA_3D_CMD_DX_DESTROY_CONTEXT = 1144,
+	SVGA_3D_CMD_DX_BIND_CONTEXT = 1145,
+	SVGA_3D_CMD_DX_READBACK_CONTEXT = 1146,
+	SVGA_3D_CMD_DX_INVALIDATE_CONTEXT = 1147,
+	SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER = 1148,
+	SVGA_3D_CMD_DX_SET_SHADER_RESOURCES = 1149,
+	SVGA_3D_CMD_DX_SET_SHADER = 1150,
+	SVGA_3D_CMD_DX_SET_SAMPLERS = 1151,
+	SVGA_3D_CMD_DX_DRAW = 1152,
+	SVGA_3D_CMD_DX_DRAW_INDEXED = 1153,
+	SVGA_3D_CMD_DX_DRAW_INSTANCED = 1154,
+	SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED = 1155,
+	SVGA_3D_CMD_DX_DRAW_AUTO = 1156,
+	SVGA_3D_CMD_DX_SET_INPUT_LAYOUT = 1157,
+	SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS = 1158,
+	SVGA_3D_CMD_DX_SET_INDEX_BUFFER = 1159,
+	SVGA_3D_CMD_DX_SET_TOPOLOGY = 1160,
+	SVGA_3D_CMD_DX_SET_RENDERTARGETS = 1161,
+	SVGA_3D_CMD_DX_SET_BLEND_STATE = 1162,
+	SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE = 1163,
+	SVGA_3D_CMD_DX_SET_RASTERIZER_STATE = 1164,
+	SVGA_3D_CMD_DX_DEFINE_QUERY = 1165,
+	SVGA_3D_CMD_DX_DESTROY_QUERY = 1166,
+	SVGA_3D_CMD_DX_BIND_QUERY = 1167,
+	SVGA_3D_CMD_DX_SET_QUERY_OFFSET = 1168,
+	SVGA_3D_CMD_DX_BEGIN_QUERY = 1169,
+	SVGA_3D_CMD_DX_END_QUERY = 1170,
+	SVGA_3D_CMD_DX_READBACK_QUERY = 1171,
+	SVGA_3D_CMD_DX_SET_PREDICATION = 1172,
+	SVGA_3D_CMD_DX_SET_SOTARGETS = 1173,
+	SVGA_3D_CMD_DX_SET_VIEWPORTS = 1174,
+	SVGA_3D_CMD_DX_SET_SCISSORRECTS = 1175,
+	SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW = 1176,
+	SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW = 1177,
+	SVGA_3D_CMD_DX_PRED_COPY_REGION = 1178,
+	SVGA_3D_CMD_DX_PRED_COPY = 1179,
+	SVGA_3D_CMD_DX_PRESENTBLT = 1180,
+	SVGA_3D_CMD_DX_GENMIPS = 1181,
+	SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE = 1182,
+	SVGA_3D_CMD_DX_READBACK_SUBRESOURCE = 1183,
+	SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE = 1184,
+	SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW = 1185,
+	SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW = 1186,
+	SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW = 1187,
+	SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW = 1188,
+	SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW = 1189,
+	SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW = 1190,
+	SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT = 1191,
+	SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT = 1192,
+	SVGA_3D_CMD_DX_DEFINE_BLEND_STATE = 1193,
+	SVGA_3D_CMD_DX_DESTROY_BLEND_STATE = 1194,
+	SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE = 1195,
+	SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE = 1196,
+	SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE = 1197,
+	SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE = 1198,
+	SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE = 1199,
+	SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE = 1200,
+	SVGA_3D_CMD_DX_DEFINE_SHADER = 1201,
+	SVGA_3D_CMD_DX_DESTROY_SHADER = 1202,
+	SVGA_3D_CMD_DX_BIND_SHADER = 1203,
+	SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT = 1204,
+	SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT = 1205,
+	SVGA_3D_CMD_DX_SET_STREAMOUTPUT = 1206,
+	SVGA_3D_CMD_DX_SET_COTABLE = 1207,
+	SVGA_3D_CMD_DX_READBACK_COTABLE = 1208,
+	SVGA_3D_CMD_DX_BUFFER_COPY = 1209,
+	SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER = 1210,
+	SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK = 1211,
+	SVGA_3D_CMD_DX_MOVE_QUERY = 1212,
+	SVGA_3D_CMD_DX_BIND_ALL_QUERY = 1213,
+	SVGA_3D_CMD_DX_READBACK_ALL_QUERY = 1214,
+	SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER = 1215,
+	SVGA_3D_CMD_DX_MOB_FENCE_64 = 1216,
+	SVGA_3D_CMD_DX_BIND_ALL_SHADER = 1217,
+	SVGA_3D_CMD_DX_HINT = 1218,
+	SVGA_3D_CMD_DX_BUFFER_UPDATE = 1219,
+	SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET = 1220,
+	SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET = 1221,
+	SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET = 1222,
+	SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET = 1223,
+	SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET = 1224,
+	SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET = 1225,
+
+	SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER = 1226,
+	SVGA_3D_CMD_DX_MAX = 1227,
+
+	SVGA_3D_CMD_SCREEN_COPY = 1227,
+
+	SVGA_3D_CMD_RESERVED1 = 1228,
+	SVGA_3D_CMD_RESERVED2 = 1229,
+	SVGA_3D_CMD_RESERVED3 = 1230,
+	SVGA_3D_CMD_RESERVED4 = 1231,
+	SVGA_3D_CMD_RESERVED5 = 1232,
+	SVGA_3D_CMD_RESERVED6 = 1233,
+	SVGA_3D_CMD_RESERVED7 = 1234,
+	SVGA_3D_CMD_RESERVED8 = 1235,
+
+	SVGA_3D_CMD_GROW_OTABLE = 1236,
+	SVGA_3D_CMD_DX_GROW_COTABLE = 1237,
+	SVGA_3D_CMD_INTRA_SURFACE_COPY = 1238,
+
+	SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 = 1239,
+
+	SVGA_3D_CMD_DX_RESOLVE_COPY = 1240,
+	SVGA_3D_CMD_DX_PRED_RESOLVE_COPY = 1241,
+	SVGA_3D_CMD_DX_PRED_CONVERT_REGION = 1242,
+	SVGA_3D_CMD_DX_PRED_CONVERT = 1243,
+	SVGA_3D_CMD_WHOLE_SURFACE_COPY = 1244,
+
+	SVGA_3D_CMD_DX_DEFINE_UA_VIEW = 1245,
+	SVGA_3D_CMD_DX_DESTROY_UA_VIEW = 1246,
+	SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT = 1247,
+	SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT = 1248,
+	SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT = 1249,
+	SVGA_3D_CMD_DX_SET_UA_VIEWS = 1250,
+
+	SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT = 1251,
+	SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT = 1252,
+	SVGA_3D_CMD_DX_DISPATCH = 1253,
+	SVGA_3D_CMD_DX_DISPATCH_INDIRECT = 1254,
+
+	SVGA_3D_CMD_WRITE_ZERO_SURFACE = 1255,
+	SVGA_3D_CMD_UPDATE_ZERO_SURFACE = 1256,
+	SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER = 1257,
+	SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT = 1258,
+
+	SVGA_3D_CMD_LOGICOPS_BITBLT = 1259,
+	SVGA_3D_CMD_LOGICOPS_TRANSBLT = 1260,
+	SVGA_3D_CMD_LOGICOPS_STRETCHBLT = 1261,
+	SVGA_3D_CMD_LOGICOPS_COLORFILL = 1262,
+	SVGA_3D_CMD_LOGICOPS_ALPHABLEND = 1263,
+	SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND = 1264,
+
+	SVGA_3D_CMD_DX_COPY_COTABLE_INTO_MOB = 1265,
+
+	SVGA_3D_CMD_UPDATE_GB_SCREENTARGET_V2 = 1266,
+
+	SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 = 1267,
+	SVGA_3D_CMD_DX_SET_CS_UA_VIEWS = 1268,
+	SVGA_3D_CMD_DX_SET_MIN_LOD = 1269,
+
+	SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2 = 1272,
+	SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB = 1273,
+	SVGA_3D_CMD_DX_SET_SHADER_IFACE = 1274,
+	SVGA_3D_CMD_DX_BIND_STREAMOUTPUT = 1275,
+	SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS = 1276,
+	SVGA_3D_CMD_DX_BIND_SHADER_IFACE = 1277,
+
+	SVGA_3D_CMD_UPDATE_GB_SCREENTARGET_MOVE = 1278,
+
+	SVGA_3D_CMD_DX_PRED_STAGING_COPY = 1281,
+	SVGA_3D_CMD_DX_STAGING_COPY = 1282,
+	SVGA_3D_CMD_DX_PRED_STAGING_COPY_REGION = 1283,
+	SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS_V2 = 1284,
+	SVGA_3D_CMD_DX_SET_INDEX_BUFFER_V2 = 1285,
+	SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS_OFFSET_AND_SIZE = 1286,
+	SVGA_3D_CMD_DX_SET_INDEX_BUFFER_OFFSET_AND_SIZE = 1287,
+	SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE_V2 = 1288,
+	SVGA_3D_CMD_DX_PRED_STAGING_CONVERT_REGION = 1289,
+	SVGA_3D_CMD_DX_PRED_STAGING_CONVERT = 1290,
+	SVGA_3D_CMD_DX_STAGING_BUFFER_COPY = 1291,
+
+	SVGA_3D_CMD_MAX = 1303,
+	SVGA_3D_CMD_FUTURE_MAX = 3000
 } SVGAFifo3dCmdId;
 
 #define SVGA_NUM_3D_CMD (SVGA_3D_CMD_MAX - SVGA_3D_CMD_BASE)
 
-/*
- * FIFO command format definitions:
- */
-
-/*
- * The data size header following cmdNum for every 3d command
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               id;
-   uint32               size;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdHeader;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               numMipLevels;
-}
-#include "vmware_pack_end.h"
-SVGA3dSurfaceFace;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                      sid;
-   SVGA3dSurface1Flags         surfaceFlags;
-   SVGA3dSurfaceFormat         format;
-
-   /*
-    * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
-    * structures must have the same value of numMipLevels field.
-    * Otherwise, all but the first SVGA3dSurfaceFace structures must have the
-    * numMipLevels set to 0.
-    */
-   SVGA3dSurfaceFace           face[SVGA3D_MAX_SURFACE_FACES];
-
-   /*
-    * Followed by an SVGA3dSize structure for each mip level in each face.
-    *
-    * A note on surface sizes: Sizes are always specified in pixels,
-    * even if the true surface size is not a multiple of the minimum
-    * block size of the surface's format. For example, a 3x3x1 DXT1
-    * compressed texture would actually be stored as a 4x4x1 image in
-    * memory.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineSurface;       /* SVGA_3D_CMD_SURFACE_DEFINE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                      sid;
-   SVGA3dSurface1Flags         surfaceFlags;
-   SVGA3dSurfaceFormat         format;
-
-   /*
-    * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
-    * structures must have the same value of numMipLevels field.
-    * Otherwise, all but the first SVGA3dSurfaceFace structures must have the
-    * numMipLevels set to 0.
-    */
-   SVGA3dSurfaceFace           face[SVGA3D_MAX_SURFACE_FACES];
-   uint32                      multisampleCount;
-   SVGA3dTextureFilter         autogenFilter;
-
-   /*
-    * Followed by an SVGA3dSize structure for each mip level in each face.
-    *
-    * A note on surface sizes: Sizes are always specified in pixels,
-    * even if the true surface size is not a multiple of the minimum
-    * block size of the surface's format. For example, a 3x3x1 DXT1
-    * compressed texture would actually be stored as a 4x4x1 image in
-    * memory.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineSurface_v2;     /* SVGA_3D_CMD_SURFACE_DEFINE_V2 */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroySurface;      /* SVGA_3D_CMD_SURFACE_DESTROY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineContext;       /* SVGA_3D_CMD_CONTEXT_DEFINE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyContext;      /* SVGA_3D_CMD_CONTEXT_DESTROY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dClearFlag      clearFlag;
-   uint32               color;
-   float                depth;
-   uint32               stencil;
-   /* Followed by variable number of SVGA3dRect structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdClear;               /* SVGA_3D_CMD_CLEAR */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dLightType      type;
-   SVGA3dBool           inWorldSpace;
-   float                diffuse[4];
-   float                specular[4];
-   float                ambient[4];
-   float                position[4];
-   float                direction[4];
-   float                range;
-   float                falloff;
-   float                attenuation0;
-   float                attenuation1;
-   float                attenuation2;
-   float                theta;
-   float                phi;
-}
-#include "vmware_pack_end.h"
-SVGA3dLightData;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               sid;
-   /* Followed by variable number of SVGA3dCopyRect structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdPresent;             /* SVGA_3D_CMD_PRESENT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dRenderStateName   state;
-   union {
-      uint32               uintValue;
-      float                floatValue;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dRenderState;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   /* Followed by variable number of SVGA3dRenderState structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetRenderState;      /* SVGA_3D_CMD_SETRENDERSTATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                 cid;
-   SVGA3dRenderTargetType type;
-   SVGA3dSurfaceImageId   target;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetRenderTarget;     /* SVGA_3D_CMD_SETRENDERTARGET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId  src;
-   SVGA3dSurfaceImageId  dest;
-   /* Followed by variable number of SVGA3dCopyBox structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSurfaceCopy;               /* SVGA_3D_CMD_SURFACE_COPY */
+#pragma pack(push, 1)
+typedef struct {
+	uint32 id;
+	uint32 size;
+} SVGA3dCmdHeader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 numMipLevels;
+} SVGA3dSurfaceFace;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+	SVGA3dSurface1Flags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+
+	SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES];
+
+} SVGA3dCmdDefineSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+	SVGA3dSurface1Flags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+
+	SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES];
+	uint32 multisampleCount;
+	SVGA3dTextureFilter autogenFilter;
+
+} SVGA3dCmdDefineSurface_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+} SVGA3dCmdDestroySurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+} SVGA3dCmdDefineContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+} SVGA3dCmdDestroyContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dClearFlag clearFlag;
+	uint32 color;
+	float depth;
+	uint32 stencil;
+
+} SVGA3dCmdClear;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dLightType type;
+	SVGA3dBool inWorldSpace;
+	float diffuse[4];
+	float specular[4];
+	float ambient[4];
+	float position[4];
+	float direction[4];
+	float range;
+	float falloff;
+	float attenuation0;
+	float attenuation1;
+	float attenuation2;
+	float theta;
+	float phi;
+} SVGA3dLightData;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+
+} SVGA3dCmdPresent;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dRenderStateName state;
+	union {
+		uint32 uintValue;
+		float floatValue;
+	};
+} SVGA3dRenderState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+} SVGA3dCmdSetRenderState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dRenderTargetType type;
+	SVGA3dSurfaceImageId target;
+} SVGA3dCmdSetRenderTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dest;
+
+} SVGA3dCmdSurfaceCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId surface;
+	SVGA3dCopyBox box;
+} SVGA3dCmdIntraSurfaceCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 srcSid;
+	uint32 destSid;
+} SVGA3dCmdWholeSurfaceCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dest;
+	SVGA3dBox boxSrc;
+	SVGA3dBox boxDest;
+} SVGA3dCmdSurfaceStretchBltNonMSToMS;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dest;
+	SVGA3dBox boxSrc;
+	SVGA3dBox boxDest;
+	SVGA3dStretchBltMode mode;
+} SVGA3dCmdSurfaceStretchBlt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 discard : 1;
+
+	uint32 unsynchronized : 1;
+
+	uint32 reserved : 30;
+} SVGA3dSurfaceDMAFlags;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAGuestImage guest;
+	SVGA3dSurfaceImageId host;
+	SVGA3dTransferType transfer;
+
+} SVGA3dCmdSurfaceDMA;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 suffixSize;
+
+	uint32 maximumOffset;
+
+	SVGA3dSurfaceDMAFlags flags;
+} SVGA3dCmdSurfaceDMASuffix;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 first;
+	uint32 last;
+} SVGA3dArrayRangeHint;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 surfaceId;
+	uint32 offset;
+	uint32 stride;
+} SVGA3dArray;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dDeclType type;
+	SVGA3dDeclMethod method;
+	SVGA3dDeclUsage usage;
+	uint32 usageIndex;
+} SVGA3dVertexArrayIdentity;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dVertexDecl {
+	SVGA3dVertexArrayIdentity identity;
+	SVGA3dArray array;
+	SVGA3dArrayRangeHint rangeHint;
+} SVGA3dVertexDecl;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dPrimitiveRange {
+	SVGA3dPrimitiveType primType;
+	uint32 primitiveCount;
+
+	SVGA3dArray indexArray;
+	uint32 indexWidth;
+
+	int32 indexBias;
+} SVGA3dPrimitiveRange;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 numVertexDecls;
+	uint32 numRanges;
+
+} SVGA3dCmdDrawPrimitives;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+	uint32 primitiveCount;
+	uint32 startVertexLocation;
+
+	uint8 primitiveType;
+	uint8 padding[3];
+} SVGA3dCmdDraw;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+	uint8 primitiveType;
+
+	uint32 indexBufferSid;
+	uint32 indexBufferOffset;
+
+	uint8 indexBufferStride;
+
+	int32 baseVertexLocation;
+
+	uint32 primitiveCount;
+	uint32 pad0;
+	uint16 pad1;
+} SVGA3dCmdDrawIndexed;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint16 streamOffset;
+	uint8 stream;
+	uint8 type;
+	uint8 method;
+	uint8 usage;
+	uint8 usageIndex;
+	uint8 padding;
+
+} SVGA3dVertexElement;
+#pragma pack(pop)
 
-/*
- * Perform a surface copy within the same image.
- * The src/dest boxes are allowed to overlap.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId  surface;
-   SVGA3dCopyBox box;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdIntraSurfaceCopy;               /* SVGA_3D_CMD_INTRA_SURFACE_COPY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 srcSid;
-   uint32 destSid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdWholeSurfaceCopy;               /* SVGA_3D_CMD_WHOLE_SURFACE_COPY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId  src;
-   SVGA3dSurfaceImageId  dest;
-   SVGA3dBox boxSrc;
-   SVGA3dBox boxDest;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSurfaceStretchBltNonMSToMS;
-/* SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId  src;
-   SVGA3dSurfaceImageId  dest;
-   SVGA3dBox             boxSrc;
-   SVGA3dBox             boxDest;
-   SVGA3dStretchBltMode  mode;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSurfaceStretchBlt;         /* SVGA_3D_CMD_SURFACE_STRETCHBLT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   /*
-    * If the discard flag is present in a surface DMA operation, the host may
-    * discard the contents of the current mipmap level and face of the target
-    * surface before applying the surface DMA contents.
-    */
-   uint32 discard : 1;
-
-   /*
-    * If the unsynchronized flag is present, the host may perform this upload
-    * without syncing to pending reads on this surface.
-    */
-   uint32 unsynchronized : 1;
-
-   /*
-    * Guests *MUST* set the reserved bits to 0 before submitting the command
-    * suffix as future flags may occupy these bits.
-    */
-   uint32 reserved : 30;
-}
-#include "vmware_pack_end.h"
-SVGA3dSurfaceDMAFlags;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAGuestImage guest;
-   SVGA3dSurfaceImageId host;
-   SVGA3dTransferType transfer;
-
-   /*
-    * Followed by variable number of SVGA3dCopyBox structures. For consistency
-    * in all clipping logic and coordinate translation, we define the
-    * "source" in each copyBox as the guest image and the
-    * "destination" as the host image, regardless of transfer
-    * direction.
-    *
-    * For efficiency, the SVGA3D device is free to copy more data than
-    * specified. For example, it may round copy boxes outwards such
-    * that they lie on particular alignment boundaries.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSurfaceDMA;                /* SVGA_3D_CMD_SURFACE_DMA */
-
-/*
- * SVGA3dCmdSurfaceDMASuffix --
- *
- *    This is a command suffix that will appear after a SurfaceDMA command in
- *    the FIFO.  It contains some extra information that hosts may use to
- *    optimize performance or protect the guest.  This suffix exists to preserve
- *    backwards compatibility while also allowing for new functionality to be
- *    implemented.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 suffixSize;
-
-   /*
-    * The maximum offset is used to determine the maximum offset from the
-    * guestPtr base address that will be accessed or written to during this
-    * surfaceDMA.  If the suffix is supported, the host will respect this
-    * boundary while performing surface DMAs.
-    *
-    * Defaults to MAX_UINT32
-    */
-   uint32 maximumOffset;
-
-   /*
-    * A set of flags that describes optimizations that the host may perform
-    * while performing this surface DMA operation.  The guest should never rely
-    * on behaviour that is different when these flags are set for correctness.
-    *
-    * Defaults to 0
-    */
-   SVGA3dSurfaceDMAFlags flags;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSurfaceDMASuffix;
-
-/*
- * SVGA_3D_CMD_DRAW_PRIMITIVES --
- *
- *   This command is the SVGA3D device's generic drawing entry point.
- *   It can draw multiple ranges of primitives, optionally using an
- *   index buffer, using an arbitrary collection of vertex buffers.
- *
- *   Each SVGA3dVertexDecl defines a distinct vertex array to bind
- *   during this draw call. The declarations specify which surface
- *   the vertex data lives in, what that vertex data is used for,
- *   and how to interpret it.
- *
- *   Each SVGA3dPrimitiveRange defines a collection of primitives
- *   to render using the same vertex arrays. An index buffer is
- *   optional.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   /*
-    * A range hint is an optional specification for the range of indices
-    * in an SVGA3dArray that will be used. If 'last' is zero, it is assumed
-    * that the entire array will be used.
-    *
-    * These are only hints. The SVGA3D device may use them for
-    * performance optimization if possible, but it's also allowed to
-    * ignore these values.
-    */
-   uint32               first;
-   uint32               last;
-}
-#include "vmware_pack_end.h"
-SVGA3dArrayRangeHint;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   /*
-    * Define the origin and shape of a vertex or index array. Both
-    * 'offset' and 'stride' are in bytes. The provided surface will be
-    * reinterpreted as a flat array of bytes in the same format used
-    * by surface DMA operations. To avoid unnecessary conversions, the
-    * surface should be created with the SVGA3D_BUFFER format.
-    *
-    * Index 0 in the array starts 'offset' bytes into the surface.
-    * Index 1 begins at byte 'offset + stride', etc. Array indices may
-    * not be negative.
-    */
-   uint32               surfaceId;
-   uint32               offset;
-   uint32               stride;
-}
-#include "vmware_pack_end.h"
-SVGA3dArray;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   /*
-    * Describe a vertex array's data type, and define how it is to be
-    * used by the fixed function pipeline or the vertex shader. It
-    * isn't useful to have two VertexDecls with the same
-    * VertexArrayIdentity in one draw call.
-    */
-   SVGA3dDeclType       type;
-   SVGA3dDeclMethod     method;
-   SVGA3dDeclUsage      usage;
-   uint32               usageIndex;
-}
-#include "vmware_pack_end.h"
-SVGA3dVertexArrayIdentity;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dVertexDecl {
-   SVGA3dVertexArrayIdentity  identity;
-   SVGA3dArray                array;
-   SVGA3dArrayRangeHint       rangeHint;
-}
-#include "vmware_pack_end.h"
-SVGA3dVertexDecl;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dPrimitiveRange {
-   /*
-    * Define a group of primitives to render, from sequential indices.
-    *
-    * The value of 'primitiveType' and 'primitiveCount' imply the
-    * total number of vertices that will be rendered.
-    */
-   SVGA3dPrimitiveType  primType;
-   uint32               primitiveCount;
-
-   /*
-    * Optional index buffer. If indexArray.surfaceId is
-    * SVGA3D_INVALID_ID, we render without an index buffer. Rendering
-    * without an index buffer is identical to rendering with an index
-    * buffer containing the sequence [0, 1, 2, 3, ...].
-    *
-    * If an index buffer is in use, indexWidth specifies the width in
-    * bytes of each index value. It must be less than or equal to
-    * indexArray.stride.
-    *
-    * (Currently, the SVGA3D device requires index buffers to be tightly
-    * packed. In other words, indexWidth == indexArray.stride)
-    */
-   SVGA3dArray          indexArray;
-   uint32               indexWidth;
-
-   /*
-    * Optional index bias. This number is added to all indices from
-    * indexArray before they are used as vertex array indices. This
-    * can be used in multiple ways:
-    *
-    *  - When not using an indexArray, this bias can be used to
-    *    specify where in the vertex arrays to begin rendering.
-    *
-    *  - A positive number here is equivalent to increasing the
-    *    offset in each vertex array.
-    *
-    *  - A negative number can be used to render using a small
-    *    vertex array and an index buffer that contains large
-    *    values. This may be used by some applications that
-    *    crop a vertex buffer without modifying their index
-    *    buffer.
-    *
-    * Note that rendering with a negative bias value may be slower and
-    * use more memory than rendering with a positive or zero bias.
-    */
-   int32                indexBias;
-}
-#include "vmware_pack_end.h"
-SVGA3dPrimitiveRange;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               numVertexDecls;
-   uint32               numRanges;
-
-   /*
-    * There are two variable size arrays after the
-    * SVGA3dCmdDrawPrimitives structure. In order,
-    * they are:
-    *
-    * 1. SVGA3dVertexDecl, quantity 'numVertexDecls', but no more than
-    *    SVGA3D_MAX_VERTEX_ARRAYS;
-    * 2. SVGA3dPrimitiveRange, quantity 'numRanges', but no more than
-    *    SVGA3D_MAX_DRAW_PRIMITIVE_RANGES;
-    * 3. Optionally, SVGA3dVertexDivisor, quantity 'numVertexDecls' (contains
-    *    the frequency divisor for the corresponding vertex decl).
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDrawPrimitives;      /* SVGA_3D_CMD_DRAWPRIMITIVES */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-
-   uint32 primitiveCount;        /* How many primitives to render */
-   uint32 startVertexLocation;   /* Which vertex do we start rendering at. */
-
-   uint8 primitiveType;          /* SVGA3dPrimitiveType */
-   uint8 padding[3];
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDraw;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-
-   uint8 primitiveType;       /* SVGA3dPrimitiveType */
-
-   uint32 indexBufferSid;     /* Valid index buffer sid. */
-   uint32 indexBufferOffset;  /* Byte offset into the vertex buffer, almost */
-                              /* always 0 for pre SM guests, non-zero for OpenGL */
-                              /* guests.  We can't represent non-multiple of */
-                              /* stride offsets in D3D9Renderer... */
-   uint8 indexBufferStride;   /* Allowable values = 1, 2, or 4 */
-
-   int32 baseVertexLocation;  /* Bias applied to the index when selecting a */
-                              /* vertex from the streams, may be negative */
-
-   uint32 primitiveCount;     /* How many primitives to render */
-   uint32 pad0;
-   uint16 pad1;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDrawIndexed;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   /*
-    * Describe a vertex array's data type, and define how it is to be
-    * used by the fixed function pipeline or the vertex shader. It
-    * isn't useful to have two VertexDecls with the same
-    * VertexArrayIdentity in one draw call.
-    */
-   uint16 streamOffset;
-   uint8 stream;
-   uint8 type;          /* SVGA3dDeclType */
-   uint8 method;        /* SVGA3dDeclMethod */
-   uint8 usage;         /* SVGA3dDeclUsage */
-   uint8 usageIndex;
-   uint8 padding;
-
-}
-#include "vmware_pack_end.h"
-SVGA3dVertexElement;
-
-/*
- * Should the vertex element respect the stream value?  The high bit of the
- * stream should be set to indicate that the stream should be respected.  If
- * the high bit is not set, the stream will be ignored and replaced by the index
- * of the position of the currently considered vertex element.
- *
- * All guests should set this bit and correctly specify the stream going
- * forward.
- */
 #define SVGA3D_VERTEX_ELEMENT_RESPECT_STREAM (1 << 7)
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-
-   uint32 numElements;
-
-   /*
-    * Followed by numElements SVGA3dVertexElement structures.
-    *
-    * If numElements < SVGA3D_MAX_VERTEX_ARRAYS, the remaining elements
-    * are cleared and will not be used by following draws.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetVertexDecls;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-   uint32 stride;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dVertexStream;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-
-   uint32 numStreams;
-   /*
-    * Followed by numStream SVGA3dVertexStream structures.
-    *
-    * If numStreams < SVGA3D_MAX_VERTEX_ARRAYS, the remaining streams
-    * are cleared and will not be used by following draws.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetVertexStreams;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-   uint32 numDivisors;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetVertexDivisors;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                   stage;
-   SVGA3dTextureStateName   name;
-   union {
-      uint32                value;
-      float                 floatValue;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dTextureState;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   /* Followed by variable number of SVGA3dTextureState structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetTextureState;      /* SVGA_3D_CMD_SETTEXTURESTATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                   cid;
-   SVGA3dTransformType      type;
-   float                    matrix[16];
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetTransform;          /* SVGA_3D_CMD_SETTRANSFORM */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   float                min;
-   float                max;
-}
-#include "vmware_pack_end.h"
-SVGA3dZRange;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dZRange         zRange;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetZRange;             /* SVGA_3D_CMD_SETZRANGE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   float                diffuse[4];
-   float                ambient[4];
-   float                specular[4];
-   float                emissive[4];
-   float                shininess;
-}
-#include "vmware_pack_end.h"
-SVGA3dMaterial;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dFace           face;
-   SVGA3dMaterial       material;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetMaterial;           /* SVGA_3D_CMD_SETMATERIAL */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               index;
-   SVGA3dLightData      data;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetLightData;           /* SVGA_3D_CMD_SETLIGHTDATA */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               index;
-   uint32               enabled;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetLightEnabled;      /* SVGA_3D_CMD_SETLIGHTENABLED */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dRect           rect;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetViewport;           /* SVGA_3D_CMD_SETVIEWPORT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dRect           rect;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetScissorRect;         /* SVGA_3D_CMD_SETSCISSORRECT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               index;
-   float                plane[4];
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetClipPlane;           /* SVGA_3D_CMD_SETCLIPPLANE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               shid;
-   SVGA3dShaderType     type;
-   /* Followed by variable number of DWORDs for shader bycode */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineShader;           /* SVGA_3D_CMD_SHADER_DEFINE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   uint32               shid;
-   SVGA3dShaderType     type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyShader;         /* SVGA_3D_CMD_SHADER_DESTROY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                  cid;
-   uint32                  reg;     /* register number */
-   SVGA3dShaderType        type;
-   SVGA3dShaderConstType   ctype;
-   uint32                  values[4];
-
-   /*
-    * Followed by a variable number of additional values.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetShaderConst;        /* SVGA_3D_CMD_SET_SHADER_CONST */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dShaderType     type;
-   uint32               shid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetShader;       /* SVGA_3D_CMD_SET_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dQueryType      type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBeginQuery;           /* SVGA_3D_CMD_BEGIN_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dQueryType      type;
-   SVGAGuestPtr         guestResult;   /* Points to an SVGA3dQueryResult structure */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdEndQuery;                  /* SVGA_3D_CMD_END_QUERY */
-
-
-/*
- * SVGA3D_CMD_WAIT_FOR_QUERY --
- *
- *    Will read the SVGA3dQueryResult structure pointed to by guestResult,
- *    and if the state member is set to anything else than
- *    SVGA3D_QUERYSTATE_PENDING, this command will always be a no-op.
- *
- *    Otherwise, in addition to the query explicitly waited for,
- *    All queries with the same type and issued with the same cid, for which
- *    an SVGA_3D_CMD_END_QUERY command has previously been sent, will
- *    be finished after execution of this command.
- *
- *    A query will be identified by the gmrId and offset of the guestResult
- *    member. If the device can't find an SVGA_3D_CMD_END_QUERY that has
- *    been sent previously with an indentical gmrId and offset, it will
- *    effectively end all queries with an identical type issued with the
- *    same cid, and the SVGA3dQueryResult structure pointed to by
- *    guestResult will not be written to. This property can be used to
- *    implement a query barrier for a given cid and query type.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;        /* Same parameters passed to END_QUERY */
-   SVGA3dQueryType      type;
-   SVGAGuestPtr         guestResult;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdWaitForQuery;              /* SVGA_3D_CMD_WAIT_FOR_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               totalSize;    /* Set by guest before query is ended. */
-   SVGA3dQueryState     state;        /* Set by host or guest. See SVGA3dQueryState. */
-   union {                            /* Set by host on exit from PENDING state */
-      uint32            result32;
-      uint32            queryCookie; /* May be used to identify which QueryGetData this
-                                        result corresponds to. */
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dQueryResult;
-
-
-/*
- * SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN --
- *
- *    This is a blit from an SVGA3D surface to a Screen Object.
- *    This blit must be directed at a specific screen.
- *
- *    The blit copies from a rectangular region of an SVGA3D surface
- *    image to a rectangular region of a screen.
- *
- *    This command takes an optional variable-length list of clipping
- *    rectangles after the body of the command. If no rectangles are
- *    specified, there is no clipping region. The entire destRect is
- *    drawn to. If one or more rectangles are included, they describe
- *    a clipping region. The clip rectangle coordinates are measured
- *    relative to the top-left corner of destRect.
- *
- *    The srcImage must be from mip=0 face=0.
- *
- *    This supports scaling if the src and dest are of different sizes.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId srcImage;
-   SVGASignedRect       srcRect;
-   uint32               destScreenId; /* Screen Object ID */
-   SVGASignedRect       destRect;
-   /* Clipping: zero or more SVGASignedRects follow */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBlitSurfaceToScreen;         /* SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               sid;
-   SVGA3dTextureFilter  filter;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdGenerateMipmaps;             /* SVGA_3D_CMD_GENERATE_MIPMAPS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdActivateSurface;               /* SVGA_3D_CMD_ACTIVATE_SURFACE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDeactivateSurface;             /* SVGA_3D_CMD_DEACTIVATE_SURFACE */
-
-/*
- * Screen DMA command
- *
- * Available with SVGA_FIFO_CAP_SCREEN_OBJECT_2.  The SVGA_CAP_3D device
- * cap bit is not required.
- *
- * - refBuffer and destBuffer are 32bit BGRX; refBuffer and destBuffer could
- *   be different, but it is required that guest makes sure refBuffer has
- *   exactly the same contents that were written to when last time screen DMA
- *   command is received by host.
- *
- * - changemap is generated by lib/blit, and it has the changes from last
- *   received screen DMA or more.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdScreenDMA {
-   uint32 screenId;
-   SVGAGuestImage refBuffer;
-   SVGAGuestImage destBuffer;
-   SVGAGuestImage changeMap;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdScreenDMA;        /* SVGA_3D_CMD_SCREEN_DMA */
-
-/*
- * Logic ops
- */
-
-#define SVGA3D_LOTRANSBLT_HONORALPHA     (0x01)
-#define SVGA3D_LOSTRETCHBLT_MIRRORX      (0x01)
-#define SVGA3D_LOSTRETCHBLT_MIRRORY      (0x02)
-#define SVGA3D_LOALPHABLEND_SRCHASALPHA  (0x01)
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsBitBlt {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId src;
-   SVGA3dSurfaceImageId dst;
-   SVGA3dLogicOp logicOp;
-   SVGA3dLogicOpRop3 logicOpRop3;
-   /* Followed by variable number of SVGA3dCopyBox structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsBitBlt;   /* SVGA_3D_CMD_LOGICOPS_BITBLT */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsTransBlt {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId src;
-   SVGA3dSurfaceImageId dst;
-   uint32 color;
-   uint32 flags;
-   SVGA3dBox srcBox;
-   SVGA3dSignedBox dstBox;
-   SVGA3dBox clipBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsTransBlt;   /* SVGA_3D_CMD_LOGICOPS_TRANSBLT */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsStretchBlt {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId src;
-   SVGA3dSurfaceImageId dst;
-   uint16 mode;
-   uint16 flags;
-   SVGA3dBox srcBox;
-   SVGA3dSignedBox dstBox;
-   SVGA3dBox clipBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsStretchBlt;   /* SVGA_3D_CMD_LOGICOPS_STRETCHBLT */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsColorFill {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId dst;
-   uint32 color;
-   SVGA3dLogicOp logicOp;
-   SVGA3dLogicOpRop3 logicOpRop3;
-   /* Followed by variable number of SVGA3dRect structures. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsColorFill;   /* SVGA_3D_CMD_LOGICOPS_COLORFILL */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsAlphaBlend {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId src;
-   SVGA3dSurfaceImageId dst;
-   uint32 alphaVal;
-   uint32 flags;
-   SVGA3dBox srcBox;
-   SVGA3dSignedBox dstBox;
-   SVGA3dBox clipBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsAlphaBlend;   /* SVGA_3D_CMD_LOGICOPS_ALPHABLEND */
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+	uint32 numElements;
+
+} SVGA3dCmdSetVertexDecls;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+	uint32 stride;
+	uint32 offset;
+} SVGA3dVertexStream;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+	uint32 numStreams;
+
+} SVGA3dCmdSetVertexStreams;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 numDivisors;
+} SVGA3dCmdSetVertexDivisors;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stage;
+	SVGA3dTextureStateName name;
+	union {
+		uint32 value;
+		float floatValue;
+	};
+} SVGA3dTextureState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+
+} SVGA3dCmdSetTextureState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dTransformType type;
+	float matrix[16];
+} SVGA3dCmdSetTransform;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	float min;
+	float max;
+} SVGA3dZRange;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dZRange zRange;
+} SVGA3dCmdSetZRange;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	float diffuse[4];
+	float ambient[4];
+	float specular[4];
+	float emissive[4];
+	float shininess;
+} SVGA3dMaterial;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dFace face;
+	SVGA3dMaterial material;
+} SVGA3dCmdSetMaterial;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 index;
+	SVGA3dLightData data;
+} SVGA3dCmdSetLightData;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 index;
+	uint32 enabled;
+} SVGA3dCmdSetLightEnabled;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dRect rect;
+} SVGA3dCmdSetViewport;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dRect rect;
+} SVGA3dCmdSetScissorRect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 index;
+	float plane[4];
+} SVGA3dCmdSetClipPlane;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 shid;
+	SVGA3dShaderType type;
+
+} SVGA3dCmdDefineShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 shid;
+	SVGA3dShaderType type;
+} SVGA3dCmdDestroyShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 reg;
+	SVGA3dShaderType type;
+	SVGA3dShaderConstType ctype;
+	uint32 values[4];
+
+} SVGA3dCmdSetShaderConst;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dShaderType type;
+	uint32 shid;
+} SVGA3dCmdSetShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+} SVGA3dCmdBeginQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+	SVGAGuestPtr guestResult;
+} SVGA3dCmdEndQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+	SVGAGuestPtr guestResult;
+} SVGA3dCmdWaitForQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 totalSize;
+	SVGA3dQueryState state;
+	union {
+		uint32 result32;
+		uint32 queryCookie;
+	};
+} SVGA3dQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId srcImage;
+	SVGASignedRect srcRect;
+	uint32 destScreenId;
+	SVGASignedRect destRect;
+
+} SVGA3dCmdBlitSurfaceToScreen;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+	SVGA3dTextureFilter filter;
+} SVGA3dCmdGenerateMipmaps;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+} SVGA3dCmdActivateSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+} SVGA3dCmdDeactivateSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdScreenDMA {
+	uint32 screenId;
+	SVGAGuestImage refBuffer;
+	SVGAGuestImage destBuffer;
+	SVGAGuestImage changeMap;
+} SVGA3dCmdScreenDMA;
+#pragma pack(pop)
+
+#define SVGA3D_LOTRANSBLT_HONORALPHA (0x01)
+#define SVGA3D_LOSTRETCHBLT_MIRRORX (0x01)
+#define SVGA3D_LOSTRETCHBLT_MIRRORY (0x02)
+#define SVGA3D_LOALPHABLEND_SRCHASALPHA (0x01)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsBitBlt {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dst;
+	SVGA3dLogicOp logicOp;
+	SVGA3dLogicOpRop3 logicOpRop3;
+
+} SVGA3dCmdLogicOpsBitBlt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsTransBlt {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dst;
+	uint32 color;
+	uint32 flags;
+	SVGA3dBox srcBox;
+	SVGA3dSignedBox dstBox;
+	SVGA3dBox clipBox;
+} SVGA3dCmdLogicOpsTransBlt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsStretchBlt {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dst;
+	uint16 mode;
+	uint16 flags;
+	SVGA3dBox srcBox;
+	SVGA3dSignedBox dstBox;
+	SVGA3dBox clipBox;
+} SVGA3dCmdLogicOpsStretchBlt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsColorFill {
+	SVGA3dSurfaceImageId dst;
+	uint32 color;
+	SVGA3dLogicOp logicOp;
+	SVGA3dLogicOpRop3 logicOpRop3;
+
+} SVGA3dCmdLogicOpsColorFill;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsAlphaBlend {
+	SVGA3dSurfaceImageId src;
+	SVGA3dSurfaceImageId dst;
+	uint32 alphaVal;
+	uint32 flags;
+	SVGA3dBox srcBox;
+	SVGA3dSignedBox dstBox;
+	SVGA3dBox clipBox;
+} SVGA3dCmdLogicOpsAlphaBlend;
+#pragma pack(pop)
 
 #define SVGA3D_CLEARTYPE_INVALID_GAMMA_INDEX 0xFFFFFFFF
 
-#define SVGA3D_CLEARTYPE_GAMMA_WIDTH  512
+#define SVGA3D_CLEARTYPE_GAMMA_WIDTH 512
 #define SVGA3D_CLEARTYPE_GAMMA_HEIGHT 16
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdLogicOpsClearTypeBlend {
-   /*
-    * All LogicOps surfaces are one-level
-    * surfaces so mipmap & face should always
-    * be zero.
-    */
-   SVGA3dSurfaceImageId tmp;
-   SVGA3dSurfaceImageId dst;
-   SVGA3dSurfaceImageId gammaSurf;
-   SVGA3dSurfaceImageId alphaSurf;
-   uint32 gamma;
-   uint32 color;
-   uint32 color2;
-   int32 alphaOffsetX;
-   int32 alphaOffsetY;
-   /* Followed by variable number of SVGA3dBox structures */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdLogicOpsClearTypeBlend;   /* SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND */
-
-
-/*
- * Guest-backed objects definitions.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAMobFormat ptDepth;
-   uint32 sizeInBytes;
-   PPN64 base;
-}
-#include "vmware_pack_end.h"
-SVGAOTableMobEntry;
-#define SVGA3D_OTABLE_MOB_ENTRY_SIZE (sizeof(SVGAOTableMobEntry))
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceFormat format;
-   SVGA3dSurface1Flags surface1Flags;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   SVGAMobId mobid;
-   uint32 arraySize;
-   uint32 mobPitch;
-   SVGA3dSurface2Flags surface2Flags;
-   uint8 multisamplePattern;
-   uint8 qualityLevel;
-   uint16 bufferByteStride;
-   float minLOD;
-   uint32 pad0[2];
-}
-#include "vmware_pack_end.h"
-SVGAOTableSurfaceEntry;
-#define SVGA3D_OTABLE_SURFACE_ENTRY_SIZE (sizeof(SVGAOTableSurfaceEntry))
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGAOTableContextEntry;
-#define SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE (sizeof(SVGAOTableContextEntry))
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dShaderType type;
-   uint32 sizeInBytes;
-   uint32 offsetInBytes;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGAOTableShaderEntry;
-#define SVGA3D_OTABLE_SHADER_ENTRY_SIZE (sizeof(SVGAOTableShaderEntry))
-
-#define SVGA_STFLAG_PRIMARY  (1 << 0)
-#define SVGA_STFLAG_RESERVED (1 << 1) /* Added with cap SVGA_CAP_HP_CMD_QUEUE */
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdLogicOpsClearTypeBlend {
+	SVGA3dSurfaceImageId tmp;
+	SVGA3dSurfaceImageId dst;
+	SVGA3dSurfaceImageId gammaSurf;
+	SVGA3dSurfaceImageId alphaSurf;
+	uint32 gamma;
+	uint32 color;
+	uint32 color2;
+	int32 alphaOffsetX;
+	int32 alphaOffsetY;
+
+} SVGA3dCmdLogicOpsClearTypeBlend;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAMobFormat ptDepth;
+	uint32 sizeInBytes;
+	PPN64 base;
+} SVGAOTableMobEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceFormat format;
+	SVGA3dSurface1Flags surface1Flags;
+	uint32 numMipLevels;
+	uint32 multisampleCount;
+	SVGA3dTextureFilter autogenFilter;
+	SVGA3dSize size;
+	SVGAMobId mobid;
+	uint32 arraySize;
+	uint32 mobPitch;
+	SVGA3dSurface2Flags surface2Flags;
+	uint8 multisamplePattern;
+	uint8 qualityLevel;
+	uint16 bufferByteStride;
+	float minLOD;
+	uint32 pad0[2];
+} SVGAOTableSurfaceEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGAMobId mobid;
+} SVGAOTableContextEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dShaderType type;
+	uint32 sizeInBytes;
+	uint32 offsetInBytes;
+	SVGAMobId mobid;
+} SVGAOTableShaderEntry;
+#pragma pack(pop)
+
+#define SVGA_STFLAG_PRIMARY (1 << 0)
+#define SVGA_STFLAG_RESERVED (1 << 1)
 typedef uint32 SVGAScreenTargetFlags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceImageId image;
-   uint32 width;
-   uint32 height;
-   int32 xRoot;
-   int32 yRoot;
-   SVGAScreenTargetFlags flags;
-   uint32 dpi;
-   uint32 pad[7];
-}
-#include "vmware_pack_end.h"
-SVGAOTableScreenTargetEntry;
-#define SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE \
-	(sizeof(SVGAOTableScreenTargetEntry))
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   float value[4];
-}
-#include "vmware_pack_end.h"
-SVGA3dShaderConstFloat;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   int32 value[4];
-}
-#include "vmware_pack_end.h"
-SVGA3dShaderConstInt;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 value;
-}
-#include "vmware_pack_end.h"
-SVGA3dShaderConstBool;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint16 streamOffset;
-   uint8 stream;
-   uint8 type;
-   uint8 methodUsage;
-   uint8 usageIndex;
-}
-#include "vmware_pack_end.h"
-SVGAGBVertexElement;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-   uint16 stride;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGAGBVertexStream;
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dRect viewport;
-   SVGA3dRect scissorRect;
-   SVGA3dZRange zRange;
-
-   SVGA3dSurfaceImageId renderTargets[SVGA3D_RT_MAX];
-   SVGAGBVertexElement decl1[4];
-
-   uint32 renderStates[SVGA3D_RS_MAX];
-   SVGAGBVertexElement decl2[18];
-   uint32 pad0[2];
-
-   struct {
-      SVGA3dFace face;
-      SVGA3dMaterial material;
-   } material;
-
-   float clipPlanes[SVGA3D_NUM_CLIPPLANES][4];
-   float matrices[SVGA3D_TRANSFORM_MAX][16];
-
-   SVGA3dBool lightEnabled[SVGA3D_NUM_LIGHTS];
-   SVGA3dLightData lightData[SVGA3D_NUM_LIGHTS];
-
-   /*
-    * Shaders currently bound
-    */
-   uint32 shaders[SVGA3D_NUM_SHADERTYPE_PREDX];
-   SVGAGBVertexElement decl3[10];
-   uint32 pad1[3];
-
-   uint32 occQueryActive;
-   uint32 occQueryValue;
-
-   /*
-    * Int/Bool Shader constants
-    */
-   SVGA3dShaderConstInt pShaderIValues[SVGA3D_CONSTINTREG_MAX];
-   SVGA3dShaderConstInt vShaderIValues[SVGA3D_CONSTINTREG_MAX];
-   uint16 pShaderBValues;
-   uint16 vShaderBValues;
-
-
-   SVGAGBVertexStream streams[SVGA3D_MAX_VERTEX_ARRAYS];
-   SVGA3dVertexDivisor divisors[SVGA3D_MAX_VERTEX_ARRAYS];
-   uint32 numVertexDecls;
-   uint32 numVertexStreams;
-   uint32 numVertexDivisors;
-   uint32 pad2[30];
-
-   /*
-    * Texture Stages
-    *
-    * SVGA3D_TS_INVALID through SVGA3D_TS_CONSTANT are in the
-    * textureStages array.
-    * SVGA3D_TS_COLOR_KEY is in tsColorKey.
-    */
-   uint32 tsColorKey[SVGA3D_NUM_TEXTURE_UNITS];
-   uint32 textureStages[SVGA3D_NUM_TEXTURE_UNITS][SVGA3D_TS_CONSTANT + 1];
-   uint32 tsColorKeyEnable[SVGA3D_NUM_TEXTURE_UNITS];
-
-   /*
-    * Float Shader constants.
-    */
-   SVGA3dShaderConstFloat pShaderFValues[SVGA3D_CONSTREG_MAX];
-   SVGA3dShaderConstFloat vShaderFValues[SVGA3D_CONSTREG_MAX];
-}
-#include "vmware_pack_end.h"
-SVGAGBContextData;
-#define SVGA3D_CONTEXT_DATA_SIZE (sizeof(SVGAGBContextData))
-
-/*
- * SVGA3dCmdSetOTableBase --
- *
- * This command allows the guest to specify the base PPN of the
- * specified object table.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAOTableType type;
-   PPN32 baseAddress;
-   uint32 sizeInBytes;
-   uint32 validSizeInBytes;
-   SVGAMobFormat ptDepth;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetOTableBase;  /* SVGA_3D_CMD_SET_OTABLE_BASE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAOTableType type;
-   PPN64 baseAddress;
-   uint32 sizeInBytes;
-   uint32 validSizeInBytes;
-   SVGAMobFormat ptDepth;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetOTableBase64;  /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
-
-/*
- * Guests using SVGA_3D_CMD_GROW_OTABLE are promising that
- * the new OTable contains the same contents as the old one, except possibly
- * for some new invalid entries at the end.
- *
- * (Otherwise, guests should use one of the SetOTableBase commands.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAOTableType type;
-   PPN64 baseAddress;
-   uint32 sizeInBytes;
-   uint32 validSizeInBytes;
-   SVGAMobFormat ptDepth;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdGrowOTable;  /* SVGA_3D_CMD_GROW_OTABLE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAOTableType type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdReadbackOTable;  /* SVGA_3D_CMD_READBACK_OTABLE */
-
-/*
- * Define a memory object (Mob) in the OTable.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBMob {
-   SVGAMobId mobid;
-   SVGAMobFormat ptDepth;
-   PPN32 base;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBMob;   /* SVGA_3D_CMD_DEFINE_GB_MOB */
-
-
-/*
- * Destroys an object in the OTable.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDestroyGBMob {
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyGBMob;   /* SVGA_3D_CMD_DESTROY_GB_MOB */
-
-/*
- * Define a memory object (Mob) in the OTable with a PPN64 base.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBMob64 {
-   SVGAMobId mobid;
-   SVGAMobFormat ptDepth;
-   PPN64 base;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBMob64;   /* SVGA_3D_CMD_DEFINE_GB_MOB64 */
-
-/*
- * Redefine an object in the OTable with PPN64 base.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdRedefineGBMob64 {
-   SVGAMobId mobid;
-   SVGAMobFormat ptDepth;
-   PPN64 base;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdRedefineGBMob64;   /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */
-
-/*
- * Notification that the page tables have been modified.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdUpdateGBMobMapping {
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdUpdateGBMobMapping;   /* SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING */
-
-/*
- * Define a guest-backed surface.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface {
-   uint32 sid;
-   SVGA3dSurface1Flags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
-
-/*
- * Defines a guest-backed surface, adding the arraySize field.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v2 {
-   uint32 sid;
-   SVGA3dSurface1Flags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-   uint32 pad;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
-
-/*
- * Defines a guest-backed surface, adding the larger flags.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v3 {
-   uint32 sid;
-   SVGA3dSurfaceAllFlags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dMSPattern multisamplePattern;
-   SVGA3dMSQualityLevel qualityLevel;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v3;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 */
-
-/*
- * Defines a guest-backed surface, adding buffer byte stride.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v4 {
-   uint32 sid;
-   SVGA3dSurfaceAllFlags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dMSPattern multisamplePattern;
-   SVGA3dMSQualityLevel qualityLevel;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-   uint32 bufferByteStride;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v4;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 */
-
-/*
- * Destroy a guest-backed surface.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDestroyGBSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyGBSurface;   /* SVGA_3D_CMD_DESTROY_GB_SURFACE */
-
-/*
- * Bind a guest-backed surface to a mob.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdBindGBSurface {
-   uint32 sid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBindGBSurface;   /* SVGA_3D_CMD_BIND_GB_SURFACE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdBindGBSurfaceWithPitch {
-   uint32 sid;
-   SVGAMobId mobid;
-   uint32 baseLevelPitch;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBindGBSurfaceWithPitch;   /* SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH */
-
-/*
- * Conditionally bind a mob to a guest-backed surface if testMobid
- * matches the currently bound mob.  Optionally issue a
- * readback/update on the surface while it is still bound to the old
- * mobid if the mobid is changed by this command.
- */
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceImageId image;
+	uint32 width;
+	uint32 height;
+	int32 xRoot;
+	int32 yRoot;
+	SVGAScreenTargetFlags flags;
+	uint32 dpi;
+	uint32 pad[7];
+} SVGAOTableScreenTargetEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	float value[4];
+} SVGA3dShaderConstFloat;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	int32 value[4];
+} SVGA3dShaderConstInt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 value;
+} SVGA3dShaderConstBool;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint16 streamOffset;
+	uint8 stream;
+	uint8 type;
+	uint8 methodUsage;
+	uint8 usageIndex;
+} SVGAGBVertexElement;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+	uint16 stride;
+	uint32 offset;
+} SVGAGBVertexStream;
+#pragma pack(pop)
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dRect viewport;
+	SVGA3dRect scissorRect;
+	SVGA3dZRange zRange;
+
+	SVGA3dSurfaceImageId renderTargets[SVGA3D_RT_MAX];
+	SVGAGBVertexElement decl1[4];
+
+	uint32 renderStates[SVGA3D_RS_MAX];
+	SVGAGBVertexElement decl2[18];
+	uint32 pad0[2];
+
+	struct {
+		SVGA3dFace face;
+		SVGA3dMaterial material;
+	} material;
+
+	float clipPlanes[SVGA3D_MAX_CLIP_PLANES][4];
+	float matrices[SVGA3D_TRANSFORM_MAX][16];
+
+	SVGA3dBool lightEnabled[SVGA3D_NUM_LIGHTS];
+	SVGA3dLightData lightData[SVGA3D_NUM_LIGHTS];
+
+	uint32 shaders[SVGA3D_NUM_SHADERTYPE_PREDX];
+	SVGAGBVertexElement decl3[10];
+	uint32 pad1[3];
+
+	uint32 occQueryActive;
+	uint32 occQueryValue;
+
+	SVGA3dShaderConstInt pShaderIValues[SVGA3D_CONSTINTREG_MAX];
+	SVGA3dShaderConstInt vShaderIValues[SVGA3D_CONSTINTREG_MAX];
+	uint16 pShaderBValues;
+	uint16 vShaderBValues;
+
+	SVGAGBVertexStream streams[SVGA3D_MAX_VERTEX_ARRAYS];
+	SVGA3dVertexDivisor divisors[SVGA3D_MAX_VERTEX_ARRAYS];
+	uint32 numVertexDecls;
+	uint32 numVertexStreams;
+	uint32 numVertexDivisors;
+	uint32 pad2[30];
+
+	uint32 tsColorKey[SVGA3D_NUM_TEXTURE_UNITS];
+	uint32 textureStages[SVGA3D_NUM_TEXTURE_UNITS][SVGA3D_TS_CONSTANT + 1];
+	uint32 tsColorKeyEnable[SVGA3D_NUM_TEXTURE_UNITS];
+
+	SVGA3dShaderConstFloat pShaderFValues[SVGA3D_CONSTREG_MAX];
+	SVGA3dShaderConstFloat vShaderFValues[SVGA3D_CONSTREG_MAX];
+} SVGAGBContextData;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAOTableType type;
+	PPN32 baseAddress;
+	uint32 sizeInBytes;
+	uint32 validSizeInBytes;
+	SVGAMobFormat ptDepth;
+} SVGA3dCmdSetOTableBase;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAOTableType type;
+	PPN64 baseAddress;
+	uint32 sizeInBytes;
+	uint32 validSizeInBytes;
+	SVGAMobFormat ptDepth;
+} SVGA3dCmdSetOTableBase64;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAOTableType type;
+	PPN64 baseAddress;
+	uint32 sizeInBytes;
+	uint32 validSizeInBytes;
+	SVGAMobFormat ptDepth;
+} SVGA3dCmdGrowOTable;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAOTableType type;
+} SVGA3dCmdReadbackOTable;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBMob {
+	SVGAMobId mobid;
+	SVGAMobFormat ptDepth;
+	PPN32 base;
+	uint32 sizeInBytes;
+} SVGA3dCmdDefineGBMob;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDestroyGBMob {
+	SVGAMobId mobid;
+} SVGA3dCmdDestroyGBMob;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBMob64 {
+	SVGAMobId mobid;
+	SVGAMobFormat ptDepth;
+	PPN64 base;
+	uint32 sizeInBytes;
+} SVGA3dCmdDefineGBMob64;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdRedefineGBMob64 {
+	SVGAMobId mobid;
+	SVGAMobFormat ptDepth;
+	PPN64 base;
+	uint32 sizeInBytes;
+} SVGA3dCmdRedefineGBMob64;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdUpdateGBMobMapping {
+	SVGAMobId mobid;
+} SVGA3dCmdUpdateGBMobMapping;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBSurface {
+	uint32 sid;
+	SVGA3dSurface1Flags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+	uint32 numMipLevels;
+	uint32 multisampleCount;
+	SVGA3dTextureFilter autogenFilter;
+	SVGA3dSize size;
+} SVGA3dCmdDefineGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBSurface_v2 {
+	uint32 sid;
+	SVGA3dSurface1Flags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+	uint32 numMipLevels;
+	uint32 multisampleCount;
+	SVGA3dTextureFilter autogenFilter;
+	SVGA3dSize size;
+	uint32 arraySize;
+	uint32 pad;
+} SVGA3dCmdDefineGBSurface_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBSurface_v3 {
+	uint32 sid;
+	SVGA3dSurfaceAllFlags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+	uint32 numMipLevels;
+	uint32 multisampleCount;
+	SVGA3dMSPattern multisamplePattern;
+	SVGA3dMSQualityLevel qualityLevel;
+	SVGA3dTextureFilter autogenFilter;
+	SVGA3dSize size;
+	uint32 arraySize;
+} SVGA3dCmdDefineGBSurface_v3;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBSurface_v4 {
+	uint32 sid;
+	SVGA3dSurfaceAllFlags surfaceFlags;
+	SVGA3dSurfaceFormat format;
+	uint32 numMipLevels;
+	uint32 multisampleCount;
+	SVGA3dMSPattern multisamplePattern;
+	SVGA3dMSQualityLevel qualityLevel;
+	SVGA3dTextureFilter autogenFilter;
+	SVGA3dSize size;
+	uint32 arraySize;
+	uint32 bufferByteStride;
+} SVGA3dCmdDefineGBSurface_v4;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDestroyGBSurface {
+	uint32 sid;
+} SVGA3dCmdDestroyGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdBindGBSurface {
+	uint32 sid;
+	SVGAMobId mobid;
+} SVGA3dCmdBindGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdBindGBSurfaceWithPitch {
+	uint32 sid;
+	SVGAMobId mobid;
+	uint32 baseLevelPitch;
+} SVGA3dCmdBindGBSurfaceWithPitch;
+#pragma pack(pop)
 
 #define SVGA3D_COND_BIND_GB_SURFACE_FLAG_READBACK (1 << 0)
-#define SVGA3D_COND_BIND_GB_SURFACE_FLAG_UPDATE   (1 << 1)
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdCondBindGBSurface {
-   uint32 sid;
-   SVGAMobId testMobid;
-   SVGAMobId mobid;
-   uint32 flags;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdCondBindGBSurface;          /* SVGA_3D_CMD_COND_BIND_GB_SURFACE */
-
-/*
- * Update an image in a guest-backed surface.
- * (Inform the device that the guest-contents have been updated.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdUpdateGBImage {
-   SVGA3dSurfaceImageId image;
-   SVGA3dBox box;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdUpdateGBImage;   /* SVGA_3D_CMD_UPDATE_GB_IMAGE */
-
-/*
- * Update an entire guest-backed surface.
- * (Inform the device that the guest-contents have been updated.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdUpdateGBSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdUpdateGBSurface;   /* SVGA_3D_CMD_UPDATE_GB_SURFACE */
-
-/*
- * Readback an image in a guest-backed surface.
- * (Request the device to flush the dirty contents into the guest.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdReadbackGBImage {
-   SVGA3dSurfaceImageId image;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdReadbackGBImage;   /* SVGA_3D_CMD_READBACK_GB_IMAGE */
-
-/*
- * Readback an entire guest-backed surface.
- * (Request the device to flush the dirty contents into the guest.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdReadbackGBSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdReadbackGBSurface;   /* SVGA_3D_CMD_READBACK_GB_SURFACE */
-
-/*
- * Readback a sub rect of an image in a guest-backed surface.  After
- * issuing this command the driver is required to issue an update call
- * of the same region before issuing any other commands that reference
- * this surface or rendering is not guaranteed.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdReadbackGBImagePartial {
-   SVGA3dSurfaceImageId image;
-   SVGA3dBox box;
-   uint32 invertBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */
-
-
-/*
- * Invalidate an image in a guest-backed surface.
- * (Notify the device that the contents can be lost.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdInvalidateGBImage {
-   SVGA3dSurfaceImageId image;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdInvalidateGBImage;   /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */
-
-/*
- * Invalidate an entire guest-backed surface.
- * (Notify the device that the contents if all images can be lost.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdInvalidateGBSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */
-
-/*
- * Invalidate a sub rect of an image in a guest-backed surface.  After
- * issuing this command the driver is required to issue an update call
- * of the same region before issuing any other commands that reference
- * this surface or rendering is not guaranteed.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdInvalidateGBImagePartial {
-   SVGA3dSurfaceImageId image;
-   SVGA3dBox box;
-   uint32 invertBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */
-
-
-/*
- * Define a guest-backed context.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBContext;   /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */
-
-/*
- * Destroy a guest-backed context.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDestroyGBContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyGBContext;   /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */
-
-/*
- * Bind a guest-backed context.
- *
- * validContents should be set to 0 for new contexts,
- * and 1 if this is an old context which is getting paged
- * back on to the device.
- *
- * For new contexts, it is recommended that the driver
- * issue commands to initialize all interesting state
- * prior to rendering.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdBindGBContext {
-   uint32 cid;
-   SVGAMobId mobid;
-   uint32 validContents;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBindGBContext;   /* SVGA_3D_CMD_BIND_GB_CONTEXT */
-
-/*
- * Readback a guest-backed context.
- * (Request that the device flush the contents back into guest memory.)
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdReadbackGBContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdReadbackGBContext;   /* SVGA_3D_CMD_READBACK_GB_CONTEXT */
-
-/*
- * Invalidate a guest-backed context.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdInvalidateGBContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdInvalidateGBContext;   /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */
-
-/*
- * Define a guest-backed shader.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBShader {
-   uint32 shid;
-   SVGA3dShaderType type;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBShader;   /* SVGA_3D_CMD_DEFINE_GB_SHADER */
-
-/*
- * Bind a guest-backed shader.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdBindGBShader {
-   uint32 shid;
-   SVGAMobId mobid;
-   uint32 offsetInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBindGBShader;   /* SVGA_3D_CMD_BIND_GB_SHADER */
-
-/*
- * Destroy a guest-backed shader.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDestroyGBShader {
-   uint32 shid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyGBShader;   /* SVGA_3D_CMD_DESTROY_GB_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32                  cid;
-   uint32                  regStart;
-   SVGA3dShaderType        shaderType;
-   SVGA3dShaderConstType   constType;
-
-   /*
-    * Followed by a variable number of shader constants.
-    *
-    * Note that FLOAT and INT constants are 4-dwords in length, while
-    * BOOL constants are 1-dword in length.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetGBShaderConstInline;   /* SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dQueryType      type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBeginGBQuery;           /* SVGA_3D_CMD_BEGIN_GB_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dQueryType      type;
-   SVGAMobId mobid;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdEndGBQuery;                  /* SVGA_3D_CMD_END_GB_QUERY */
-
-
-/*
- * SVGA_3D_CMD_WAIT_FOR_GB_QUERY --
- *
- *    The semantics of this command are identical to the
- *    SVGA_3D_CMD_WAIT_FOR_QUERY except that the results are written
- *    to a Mob instead of a GMR.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               cid;
-   SVGA3dQueryType      type;
-   SVGAMobId mobid;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdWaitForGBQuery;          /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAMobId mobid;
-   uint32 mustBeZero;
-   uint32 initialized;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdEnableGart;              /* SVGA_3D_CMD_ENABLE_GART */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAMobId mobid;
-   uint32 gartOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdMapMobIntoGart;          /* SVGA_3D_CMD_MAP_MOB_INTO_GART */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 gartOffset;
-   uint32 numPages;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdUnmapGartRange;          /* SVGA_3D_CMD_UNMAP_GART_RANGE */
-
-
-/*
- * Screen Targets
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 stid;
-   uint32 width;
-   uint32 height;
-   int32 xRoot;
-   int32 yRoot;
-   SVGAScreenTargetFlags flags;
-
-   /*
-    * The physical DPI that the guest expects this screen displayed at.
-    *
-    * Guests which are not DPI-aware should set this to zero.
-    */
-   uint32 dpi;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBScreenTarget;    /* SVGA_3D_CMD_DEFINE_GB_SCREENTARGET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 stid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDestroyGBScreenTarget;  /* SVGA_3D_CMD_DESTROY_GB_SCREENTARGET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 stid;
-   SVGA3dSurfaceImageId image;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdBindGBScreenTarget;  /* SVGA_3D_CMD_BIND_GB_SCREENTARGET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 stid;
-   SVGA3dRect rect;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdUpdateGBScreenTarget;  /* SVGA_3D_CMD_UPDATE_GB_SCREENTARGET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdGBScreenDMA {
-   uint32 screenId;
-   uint32 dead;
-   SVGAMobId destMobID;
-   uint32 destPitch;
-   SVGAMobId changeMapMobID;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdGBScreenDMA;        /* SVGA_3D_CMD_GB_SCREEN_DMA */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 value;
-   uint32 mobId;
-   uint32 mobOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 stid;
-   SVGA3dSurfaceImageId dest;
-
-   uint32 statusMobId;
-   uint32 statusMobOffset;
-
-   /* Reserved fields */
-   uint32 mustBeInvalidId;
-   uint32 mustBeZero;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdScreenCopy;  /* SVGA_3D_CMD_SCREEN_COPY */
+#define SVGA3D_COND_BIND_GB_SURFACE_FLAG_UPDATE (1 << 1)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdCondBindGBSurface {
+	uint32 sid;
+	SVGAMobId testMobid;
+	SVGAMobId mobid;
+	uint32 flags;
+} SVGA3dCmdCondBindGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdUpdateGBImage {
+	SVGA3dSurfaceImageId image;
+	SVGA3dBox box;
+} SVGA3dCmdUpdateGBImage;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdUpdateGBSurface {
+	uint32 sid;
+} SVGA3dCmdUpdateGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdReadbackGBImage {
+	SVGA3dSurfaceImageId image;
+} SVGA3dCmdReadbackGBImage;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdReadbackGBSurface {
+	uint32 sid;
+} SVGA3dCmdReadbackGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdReadbackGBImagePartial {
+	SVGA3dSurfaceImageId image;
+	SVGA3dBox box;
+	uint32 invertBox;
+} SVGA3dCmdReadbackGBImagePartial;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdInvalidateGBImage {
+	SVGA3dSurfaceImageId image;
+} SVGA3dCmdInvalidateGBImage;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdInvalidateGBSurface {
+	uint32 sid;
+} SVGA3dCmdInvalidateGBSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdInvalidateGBImagePartial {
+	SVGA3dSurfaceImageId image;
+	SVGA3dBox box;
+	uint32 invertBox;
+} SVGA3dCmdInvalidateGBImagePartial;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBContext {
+	uint32 cid;
+} SVGA3dCmdDefineGBContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDestroyGBContext {
+	uint32 cid;
+} SVGA3dCmdDestroyGBContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdBindGBContext {
+	uint32 cid;
+	SVGAMobId mobid;
+	uint32 validContents;
+} SVGA3dCmdBindGBContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdReadbackGBContext {
+	uint32 cid;
+} SVGA3dCmdReadbackGBContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdInvalidateGBContext {
+	uint32 cid;
+} SVGA3dCmdInvalidateGBContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDefineGBShader {
+	uint32 shid;
+	SVGA3dShaderType type;
+	uint32 sizeInBytes;
+} SVGA3dCmdDefineGBShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdBindGBShader {
+	uint32 shid;
+	SVGAMobId mobid;
+	uint32 offsetInBytes;
+} SVGA3dCmdBindGBShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDestroyGBShader {
+	uint32 shid;
+} SVGA3dCmdDestroyGBShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	uint32 regStart;
+	SVGA3dShaderType shaderType;
+	SVGA3dShaderConstType constType;
+
+} SVGA3dCmdSetGBShaderConstInline;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+} SVGA3dCmdBeginGBQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+	SVGAMobId mobid;
+	uint32 offset;
+} SVGA3dCmdEndGBQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGA3dQueryType type;
+	SVGAMobId mobid;
+	uint32 offset;
+} SVGA3dCmdWaitForGBQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAMobId mobid;
+	uint32 mustBeZero;
+	uint32 initialized;
+} SVGA3dCmdEnableGart;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAMobId mobid;
+	uint32 gartOffset;
+} SVGA3dCmdMapMobIntoGart;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 gartOffset;
+	uint32 numPages;
+} SVGA3dCmdUnmapGartRange;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	uint32 width;
+	uint32 height;
+	int32 xRoot;
+	int32 yRoot;
+	SVGAScreenTargetFlags flags;
+
+	uint32 dpi;
+} SVGA3dCmdDefineGBScreenTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+} SVGA3dCmdDestroyGBScreenTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	SVGA3dSurfaceImageId image;
+} SVGA3dCmdBindGBScreenTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	SVGA3dRect rect;
+} SVGA3dCmdUpdateGBScreenTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	SVGA3dRect rect;
+	SVGA3dFrameUpdateType type;
+} SVGA3dCmdUpdateGBScreenTarget_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	SVGA3dRect rect;
+	SVGA3dFrameUpdateType type;
+	SVGAUnsignedPoint srcPoint;
+} SVGA3dCmdUpdateGBScreenTargetMove;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdGBScreenDMA {
+	uint32 screenId;
+	uint32 dead;
+	SVGAMobId destMobID;
+	uint32 destPitch;
+	SVGAMobId changeMapMobID;
+} SVGA3dCmdGBScreenDMA;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 value;
+	uint32 mobId;
+	uint32 mobOffset;
+} SVGA3dCmdGBMobFence;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 stid;
+	SVGA3dSurfaceImageId dest;
+
+	uint32 statusMobId;
+	uint32 statusMobOffset;
+
+	uint32 mustBeInvalidId;
+	uint32 mustBeZero;
+} SVGA3dCmdScreenCopy;
+#pragma pack(pop)
 
 #define SVGA_SCREEN_COPY_STATUS_FAILURE 0x00
 #define SVGA_SCREEN_COPY_STATUS_SUCCESS 0x01
 #define SVGA_SCREEN_COPY_STATUS_INVALID 0xFFFFFFFF
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdWriteZeroSurface;  /* SVGA_3D_CMD_WRITE_ZERO_SURFACE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdHintZeroSurface;  /* SVGA_3D_CMD_HINT_ZERO_SURFACE */
-
-#endif /* _SVGA3D_CMD_H_ */
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+} SVGA3dCmdWriteZeroSurface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 sid;
+} SVGA3dCmdUpdateZeroSurface;
+#pragma pack(pop)
+
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
index 617b468c626c..379ec15c7758 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2019 VMware, Inc.
+ * Copyright 1998-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,484 +27,345 @@
 /*
  * svga3d_devcaps.h --
  *
- *       SVGA 3d caps definitions
+ *    SVGA 3d caps definitions
  */
 
-#ifndef _SVGA3D_DEVCAPS_H_
-#define _SVGA3D_DEVCAPS_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
 
-#include "includeCheck.h"
+#ifndef _SVGA3D_DEVCAPS_H_
+#define _SVGA3D_DEVCAPS_H_
 
 #include "svga3d_types.h"
 
-/*
- * 3D Hardware Version
- *
- *   The hardware version is stored in the SVGA_FIFO_3D_HWVERSION fifo
- *   register.   Is set by the host and read by the guest.  This lets
- *   us make new guest drivers which are backwards-compatible with old
- *   SVGA hardware revisions.  It does not let us support old guest
- *   drivers.  Good enough for now.
- *
- */
-
-#define SVGA3D_MAKE_HWVERSION(major, minor)      (((major) << 16) | ((minor) & 0xFF))
-#define SVGA3D_MAJOR_HWVERSION(version)          ((version) >> 16)
-#define SVGA3D_MINOR_HWVERSION(version)          ((version) & 0xFF)
+#define SVGA3D_MAKE_HWVERSION(major, minor) (((major) << 16) | ((minor)&0xFF))
+#define SVGA3D_MAJOR_HWVERSION(version) ((version) >> 16)
+#define SVGA3D_MINOR_HWVERSION(version) ((version)&0xFF)
 
 typedef enum {
-   SVGA3D_HWVERSION_WS5_RC1   = SVGA3D_MAKE_HWVERSION(0, 1),
-   SVGA3D_HWVERSION_WS5_RC2   = SVGA3D_MAKE_HWVERSION(0, 2),
-   SVGA3D_HWVERSION_WS51_RC1  = SVGA3D_MAKE_HWVERSION(0, 3),
-   SVGA3D_HWVERSION_WS6_B1    = SVGA3D_MAKE_HWVERSION(1, 1),
-   SVGA3D_HWVERSION_FUSION_11 = SVGA3D_MAKE_HWVERSION(1, 4),
-   SVGA3D_HWVERSION_WS65_B1   = SVGA3D_MAKE_HWVERSION(2, 0),
-   SVGA3D_HWVERSION_WS8_B1    = SVGA3D_MAKE_HWVERSION(2, 1),
-   SVGA3D_HWVERSION_CURRENT   = SVGA3D_HWVERSION_WS8_B1,
+	SVGA3D_HWVERSION_WS5_RC1 = SVGA3D_MAKE_HWVERSION(0, 1),
+	SVGA3D_HWVERSION_WS5_RC2 = SVGA3D_MAKE_HWVERSION(0, 2),
+	SVGA3D_HWVERSION_WS51_RC1 = SVGA3D_MAKE_HWVERSION(0, 3),
+	SVGA3D_HWVERSION_WS6_B1 = SVGA3D_MAKE_HWVERSION(1, 1),
+	SVGA3D_HWVERSION_FUSION_11 = SVGA3D_MAKE_HWVERSION(1, 4),
+	SVGA3D_HWVERSION_WS65_B1 = SVGA3D_MAKE_HWVERSION(2, 0),
+	SVGA3D_HWVERSION_WS8_B1 = SVGA3D_MAKE_HWVERSION(2, 1),
+	SVGA3D_HWVERSION_CURRENT = SVGA3D_HWVERSION_WS8_B1,
 } SVGA3dHardwareVersion;
 
-/*
- * DevCap indexes.
- */
-
 typedef uint32 SVGA3dDevCapIndex;
 
-#define SVGA3D_DEVCAP_INVALID                              ((uint32)-1)
-#define SVGA3D_DEVCAP_3D                                   0
-#define SVGA3D_DEVCAP_MAX_LIGHTS                           1
-
-/*
- * SVGA3D_DEVCAP_MAX_TEXTURES reflects the maximum number of
- * fixed-function texture units available. Each of these units
- * work in both FFP and Shader modes, and they support texture
- * transforms and texture coordinates. The host may have additional
- * texture image units that are only usable with shaders.
- */
-#define SVGA3D_DEVCAP_MAX_TEXTURES                         2
-#define SVGA3D_DEVCAP_MAX_CLIP_PLANES                      3
-#define SVGA3D_DEVCAP_VERTEX_SHADER_VERSION                4
-#define SVGA3D_DEVCAP_VERTEX_SHADER                        5
-#define SVGA3D_DEVCAP_FRAGMENT_SHADER_VERSION              6
-#define SVGA3D_DEVCAP_FRAGMENT_SHADER                      7
-#define SVGA3D_DEVCAP_MAX_RENDER_TARGETS                   8
-#define SVGA3D_DEVCAP_S23E8_TEXTURES                       9
-#define SVGA3D_DEVCAP_S10E5_TEXTURES                       10
-#define SVGA3D_DEVCAP_MAX_FIXED_VERTEXBLEND                11
-#define SVGA3D_DEVCAP_D16_BUFFER_FORMAT                    12
-#define SVGA3D_DEVCAP_D24S8_BUFFER_FORMAT                  13
-#define SVGA3D_DEVCAP_D24X8_BUFFER_FORMAT                  14
-#define SVGA3D_DEVCAP_QUERY_TYPES                          15
-#define SVGA3D_DEVCAP_TEXTURE_GRADIENT_SAMPLING            16
-#define SVGA3D_DEVCAP_MAX_POINT_SIZE                       17
-#define SVGA3D_DEVCAP_MAX_SHADER_TEXTURES                  18
-#define SVGA3D_DEVCAP_MAX_TEXTURE_WIDTH                    19
-#define SVGA3D_DEVCAP_MAX_TEXTURE_HEIGHT                   20
-#define SVGA3D_DEVCAP_MAX_VOLUME_EXTENT                    21
-#define SVGA3D_DEVCAP_MAX_TEXTURE_REPEAT                   22
-#define SVGA3D_DEVCAP_MAX_TEXTURE_ASPECT_RATIO             23
-#define SVGA3D_DEVCAP_MAX_TEXTURE_ANISOTROPY               24
-#define SVGA3D_DEVCAP_MAX_PRIMITIVE_COUNT                  25
-#define SVGA3D_DEVCAP_MAX_VERTEX_INDEX                     26
-#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_INSTRUCTIONS       27
-#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_INSTRUCTIONS     28
-#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEMPS              29
-#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_TEMPS            30
-#define SVGA3D_DEVCAP_TEXTURE_OPS                          31
-#define SVGA3D_DEVCAP_SURFACEFMT_X8R8G8B8                  32
-#define SVGA3D_DEVCAP_SURFACEFMT_A8R8G8B8                  33
-#define SVGA3D_DEVCAP_SURFACEFMT_A2R10G10B10               34
-#define SVGA3D_DEVCAP_SURFACEFMT_X1R5G5B5                  35
-#define SVGA3D_DEVCAP_SURFACEFMT_A1R5G5B5                  36
-#define SVGA3D_DEVCAP_SURFACEFMT_A4R4G4B4                  37
-#define SVGA3D_DEVCAP_SURFACEFMT_R5G6B5                    38
-#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE16               39
-#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8_ALPHA8         40
-#define SVGA3D_DEVCAP_SURFACEFMT_ALPHA8                    41
-#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8                42
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_D16                     43
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8                   44
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24X8                   45
-#define SVGA3D_DEVCAP_SURFACEFMT_DXT1                      46
-#define SVGA3D_DEVCAP_SURFACEFMT_DXT2                      47
-#define SVGA3D_DEVCAP_SURFACEFMT_DXT3                      48
-#define SVGA3D_DEVCAP_SURFACEFMT_DXT4                      49
-#define SVGA3D_DEVCAP_SURFACEFMT_DXT5                      50
-#define SVGA3D_DEVCAP_SURFACEFMT_BUMPX8L8V8U8              51
-#define SVGA3D_DEVCAP_SURFACEFMT_A2W10V10U10               52
-#define SVGA3D_DEVCAP_SURFACEFMT_BUMPU8V8                  53
-#define SVGA3D_DEVCAP_SURFACEFMT_Q8W8V8U8                  54
-#define SVGA3D_DEVCAP_SURFACEFMT_CxV8U8                    55
-#define SVGA3D_DEVCAP_SURFACEFMT_R_S10E5                   56
-#define SVGA3D_DEVCAP_SURFACEFMT_R_S23E8                   57
-#define SVGA3D_DEVCAP_SURFACEFMT_RG_S10E5                  58
-#define SVGA3D_DEVCAP_SURFACEFMT_RG_S23E8                  59
-#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S10E5                60
-#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S23E8                61
-
-/*
- * There is a hole in our devcap definitions for
- * historical reasons.
- *
- * Define a constant just for completeness.
- */
-#define SVGA3D_DEVCAP_MISSING62                            62
-
-#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEXTURES           63
-
-/*
- * Note that MAX_SIMULTANEOUS_RENDER_TARGETS is a maximum count of color
- * render targets.  This does not include the depth or stencil targets.
- */
-#define SVGA3D_DEVCAP_MAX_SIMULTANEOUS_RENDER_TARGETS      64
-
-#define SVGA3D_DEVCAP_SURFACEFMT_V16U16                    65
-#define SVGA3D_DEVCAP_SURFACEFMT_G16R16                    66
-#define SVGA3D_DEVCAP_SURFACEFMT_A16B16G16R16              67
-#define SVGA3D_DEVCAP_SURFACEFMT_UYVY                      68
-#define SVGA3D_DEVCAP_SURFACEFMT_YUY2                      69
-
-/*
- * Deprecated.
- */
-#define SVGA3D_DEVCAP_DEAD4                                70
-#define SVGA3D_DEVCAP_DEAD5                                71
-#define SVGA3D_DEVCAP_DEAD7                                72
-#define SVGA3D_DEVCAP_DEAD6                                73
-
-#define SVGA3D_DEVCAP_AUTOGENMIPMAPS                       74
-#define SVGA3D_DEVCAP_SURFACEFMT_NV12                      75
-#define SVGA3D_DEVCAP_DEAD10                               76
-
-/*
- * This is the maximum number of SVGA context IDs that the guest
- * can define using SVGA_3D_CMD_CONTEXT_DEFINE.
- */
-#define SVGA3D_DEVCAP_MAX_CONTEXT_IDS                      77
-
-/*
- * This is the maximum number of SVGA surface IDs that the guest
- * can define using SVGA_3D_CMD_SURFACE_DEFINE*.
- */
-#define SVGA3D_DEVCAP_MAX_SURFACE_IDS                      78
-
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF16                    79
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF24                    80
-#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8_INT               81
-
-#define SVGA3D_DEVCAP_SURFACEFMT_ATI1                      82
-#define SVGA3D_DEVCAP_SURFACEFMT_ATI2                      83
-
-/*
- * Deprecated.
- */
-#define SVGA3D_DEVCAP_DEAD1                                84
-#define SVGA3D_DEVCAP_DEAD8                                85
-#define SVGA3D_DEVCAP_DEAD9                                86
-
-#define SVGA3D_DEVCAP_LINE_AA                              87  /* boolean */
-#define SVGA3D_DEVCAP_LINE_STIPPLE                         88  /* boolean */
-#define SVGA3D_DEVCAP_MAX_LINE_WIDTH                       89  /* float */
-#define SVGA3D_DEVCAP_MAX_AA_LINE_WIDTH                    90  /* float */
-
-#define SVGA3D_DEVCAP_SURFACEFMT_YV12                      91
-
-/*
- * Deprecated.
- */
-#define SVGA3D_DEVCAP_DEAD3                                92
-
-/*
- * Are TS_CONSTANT, TS_COLOR_KEY, and TS_COLOR_KEY_ENABLE supported?
- */
-#define SVGA3D_DEVCAP_TS_COLOR_KEY                         93 /* boolean */
-
-/*
- * Deprecated.
- */
-#define SVGA3D_DEVCAP_DEAD2                                94
-
-/*
- * Does the device support DXContexts?
- */
-#define SVGA3D_DEVCAP_DXCONTEXT                            95
-
-/*
- * Deprecated.
- */
-#define SVGA3D_DEVCAP_DEAD11                               96
-
-/*
- * What is the maximum number of vertex buffers or vertex input registers
- * that can be expected to work correctly with a DXContext?
- *
- * The guest is allowed to set up to SVGA3D_DX_MAX_VERTEXBUFFERS, but
- * anything in excess of this cap is not guaranteed to render correctly.
- *
- * Similarly, the guest can set up to SVGA3D_DX_MAX_VERTEXINPUTREGISTERS
- * input registers without the SVGA3D_DEVCAP_SM4_1 cap, or
- * SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS with the SVGA3D_DEVCAP_SM4_1,
- * but only the registers up to this cap value are guaranteed to render
- * correctly.
- *
- * If guest-drivers are able to expose a lower-limit, it's recommended
- * that they clamp to this value.  Otherwise, the host will make a
- * best-effort on case-by-case basis if guests exceed this.
- */
-#define SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS                 97
-
-/*
- * What is the maximum number of constant buffers that can be expected to
- * work correctly with a DX context?
- *
- * The guest is allowed to set up to SVGA3D_DX_MAX_CONSTBUFFERS, but
- * anything in excess of this cap is not guaranteed to render correctly.
- *
- * If guest-drivers are able to expose a lower-limit, it's recommended
- * that they clamp to this value.  Otherwise, the host will make a
- * best-effort on case-by-case basis if guests exceed this.
- */
-#define SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS              98
-
-/*
- * Does the device support provoking vertex control?
- *
- * If this cap is present, the provokingVertexLast field in the
- * rasterizer state is enabled.  (Guests can then set it to FALSE,
- * meaning that the first vertex is the provoking vertex, or TRUE,
- * meaning that the last verteix is the provoking vertex.)
- *
- * If this cap is FALSE, then guests should set the provokingVertexLast
- * to FALSE, otherwise rendering behavior is undefined.
- */
-#define SVGA3D_DEVCAP_DX_PROVOKING_VERTEX                  99
-
-#define SVGA3D_DEVCAP_DXFMT_X8R8G8B8                       100
-#define SVGA3D_DEVCAP_DXFMT_A8R8G8B8                       101
-#define SVGA3D_DEVCAP_DXFMT_R5G6B5                         102
-#define SVGA3D_DEVCAP_DXFMT_X1R5G5B5                       103
-#define SVGA3D_DEVCAP_DXFMT_A1R5G5B5                       104
-#define SVGA3D_DEVCAP_DXFMT_A4R4G4B4                       105
-#define SVGA3D_DEVCAP_DXFMT_Z_D32                          106
-#define SVGA3D_DEVCAP_DXFMT_Z_D16                          107
-#define SVGA3D_DEVCAP_DXFMT_Z_D24S8                        108
-#define SVGA3D_DEVCAP_DXFMT_Z_D15S1                        109
-#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8                     110
-#define SVGA3D_DEVCAP_DXFMT_LUMINANCE4_ALPHA4              111
-#define SVGA3D_DEVCAP_DXFMT_LUMINANCE16                    112
-#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8_ALPHA8              113
-#define SVGA3D_DEVCAP_DXFMT_DXT1                           114
-#define SVGA3D_DEVCAP_DXFMT_DXT2                           115
-#define SVGA3D_DEVCAP_DXFMT_DXT3                           116
-#define SVGA3D_DEVCAP_DXFMT_DXT4                           117
-#define SVGA3D_DEVCAP_DXFMT_DXT5                           118
-#define SVGA3D_DEVCAP_DXFMT_BUMPU8V8                       119
-#define SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5                     120
-#define SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8                   121
-#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1                   122
-#define SVGA3D_DEVCAP_DXFMT_ARGB_S10E5                     123
-#define SVGA3D_DEVCAP_DXFMT_ARGB_S23E8                     124
-#define SVGA3D_DEVCAP_DXFMT_A2R10G10B10                    125
-#define SVGA3D_DEVCAP_DXFMT_V8U8                           126
-#define SVGA3D_DEVCAP_DXFMT_Q8W8V8U8                       127
-#define SVGA3D_DEVCAP_DXFMT_CxV8U8                         128
-#define SVGA3D_DEVCAP_DXFMT_X8L8V8U8                       129
-#define SVGA3D_DEVCAP_DXFMT_A2W10V10U10                    130
-#define SVGA3D_DEVCAP_DXFMT_ALPHA8                         131
-#define SVGA3D_DEVCAP_DXFMT_R_S10E5                        132
-#define SVGA3D_DEVCAP_DXFMT_R_S23E8                        133
-#define SVGA3D_DEVCAP_DXFMT_RG_S10E5                       134
-#define SVGA3D_DEVCAP_DXFMT_RG_S23E8                       135
-#define SVGA3D_DEVCAP_DXFMT_BUFFER                         136
-#define SVGA3D_DEVCAP_DXFMT_Z_D24X8                        137
-#define SVGA3D_DEVCAP_DXFMT_V16U16                         138
-#define SVGA3D_DEVCAP_DXFMT_G16R16                         139
-#define SVGA3D_DEVCAP_DXFMT_A16B16G16R16                   140
-#define SVGA3D_DEVCAP_DXFMT_UYVY                           141
-#define SVGA3D_DEVCAP_DXFMT_YUY2                           142
-#define SVGA3D_DEVCAP_DXFMT_NV12                           143
-#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD2                   144
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_TYPELESS          145
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_UINT              146
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_SINT              147
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32_TYPELESS             148
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32_FLOAT                149
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32_UINT                 150
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32_SINT                 151
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_TYPELESS          152
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UINT              153
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SNORM             154
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SINT              155
-#define SVGA3D_DEVCAP_DXFMT_R32G32_TYPELESS                156
-#define SVGA3D_DEVCAP_DXFMT_R32G32_UINT                    157
-#define SVGA3D_DEVCAP_DXFMT_R32G32_SINT                    158
-#define SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS              159
-#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT           160
-#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24                161
-#define SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT                 162
-#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS           163
-#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT               164
-#define SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT                165
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_TYPELESS              166
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM                 167
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM_SRGB            168
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UINT                  169
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SINT                  170
-#define SVGA3D_DEVCAP_DXFMT_R16G16_TYPELESS                171
-#define SVGA3D_DEVCAP_DXFMT_R16G16_UINT                    172
-#define SVGA3D_DEVCAP_DXFMT_R16G16_SINT                    173
-#define SVGA3D_DEVCAP_DXFMT_R32_TYPELESS                   174
-#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT                      175
-#define SVGA3D_DEVCAP_DXFMT_R32_UINT                       176
-#define SVGA3D_DEVCAP_DXFMT_R32_SINT                       177
-#define SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS                 178
-#define SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT              179
-#define SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8                   180
-#define SVGA3D_DEVCAP_DXFMT_X24_G8_UINT                    181
-#define SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS                  182
-#define SVGA3D_DEVCAP_DXFMT_R8G8_UNORM                     183
-#define SVGA3D_DEVCAP_DXFMT_R8G8_UINT                      184
-#define SVGA3D_DEVCAP_DXFMT_R8G8_SINT                      185
-#define SVGA3D_DEVCAP_DXFMT_R16_TYPELESS                   186
-#define SVGA3D_DEVCAP_DXFMT_R16_UNORM                      187
-#define SVGA3D_DEVCAP_DXFMT_R16_UINT                       188
-#define SVGA3D_DEVCAP_DXFMT_R16_SNORM                      189
-#define SVGA3D_DEVCAP_DXFMT_R16_SINT                       190
-#define SVGA3D_DEVCAP_DXFMT_R8_TYPELESS                    191
-#define SVGA3D_DEVCAP_DXFMT_R8_UNORM                       192
-#define SVGA3D_DEVCAP_DXFMT_R8_UINT                        193
-#define SVGA3D_DEVCAP_DXFMT_R8_SNORM                       194
-#define SVGA3D_DEVCAP_DXFMT_R8_SINT                        195
-#define SVGA3D_DEVCAP_DXFMT_P8                             196
-#define SVGA3D_DEVCAP_DXFMT_R9G9B9E5_SHAREDEXP             197
-#define SVGA3D_DEVCAP_DXFMT_R8G8_B8G8_UNORM                198
-#define SVGA3D_DEVCAP_DXFMT_G8R8_G8B8_UNORM                199
-#define SVGA3D_DEVCAP_DXFMT_BC1_TYPELESS                   200
-#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM_SRGB                 201
-#define SVGA3D_DEVCAP_DXFMT_BC2_TYPELESS                   202
-#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM_SRGB                 203
-#define SVGA3D_DEVCAP_DXFMT_BC3_TYPELESS                   204
-#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM_SRGB                 205
-#define SVGA3D_DEVCAP_DXFMT_BC4_TYPELESS                   206
-#define SVGA3D_DEVCAP_DXFMT_ATI1                           207
-#define SVGA3D_DEVCAP_DXFMT_BC4_SNORM                      208
-#define SVGA3D_DEVCAP_DXFMT_BC5_TYPELESS                   209
-#define SVGA3D_DEVCAP_DXFMT_ATI2                           210
-#define SVGA3D_DEVCAP_DXFMT_BC5_SNORM                      211
-#define SVGA3D_DEVCAP_DXFMT_R10G10B10_XR_BIAS_A2_UNORM     212
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_TYPELESS              213
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM_SRGB            214
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_TYPELESS              215
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM_SRGB            216
-#define SVGA3D_DEVCAP_DXFMT_Z_DF16                         217
-#define SVGA3D_DEVCAP_DXFMT_Z_DF24                         218
-#define SVGA3D_DEVCAP_DXFMT_Z_D24S8_INT                    219
-#define SVGA3D_DEVCAP_DXFMT_YV12                           220
-#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_FLOAT             221
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_FLOAT             222
-#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UNORM             223
-#define SVGA3D_DEVCAP_DXFMT_R32G32_FLOAT                   224
-#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UNORM              225
-#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SNORM                 226
-#define SVGA3D_DEVCAP_DXFMT_R16G16_FLOAT                   227
-#define SVGA3D_DEVCAP_DXFMT_R16G16_UNORM                   228
-#define SVGA3D_DEVCAP_DXFMT_R16G16_SNORM                   229
-#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT                      230
-#define SVGA3D_DEVCAP_DXFMT_R8G8_SNORM                     231
-#define SVGA3D_DEVCAP_DXFMT_R16_FLOAT                      232
-#define SVGA3D_DEVCAP_DXFMT_D16_UNORM                      233
-#define SVGA3D_DEVCAP_DXFMT_A8_UNORM                       234
-#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM                      235
-#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM                      236
-#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM                      237
-#define SVGA3D_DEVCAP_DXFMT_B5G6R5_UNORM                   238
-#define SVGA3D_DEVCAP_DXFMT_B5G5R5A1_UNORM                 239
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM                 240
-#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM                 241
-#define SVGA3D_DEVCAP_DXFMT_BC4_UNORM                      242
-#define SVGA3D_DEVCAP_DXFMT_BC5_UNORM                      243
-
-/*
- * Advertises shaderModel 4.1 support, independent blend-states,
- * cube-map arrays, and a higher vertex input registers limit.
- *
- * (See documentation on SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS.)
- */
-#define SVGA3D_DEVCAP_SM41                                 244
-#define SVGA3D_DEVCAP_MULTISAMPLE_2X                       245
-#define SVGA3D_DEVCAP_MULTISAMPLE_4X                       246
-
-/*
- * Indicates that the device has rendering support for
- * the full multisample quality.  If this cap is not present,
- * the host may or may not support full quality rendering.
- *
- * See also SVGA_REG_MS_HINT_RESOLVED.
- */
-#define SVGA3D_DEVCAP_MS_FULL_QUALITY                      247
-
-/*
- * Advertises support for the SVGA3D LogicOps commands.
- */
-#define SVGA3D_DEVCAP_LOGICOPS                             248
-
-/*
- * Advertises support for using logicOps in the DXBlendStates.
- */
-#define SVGA3D_DEVCAP_LOGIC_BLENDOPS                       249
-
-/*
-* Note DXFMT range is now non-contiguous.
-*/
-#define SVGA3D_DEVCAP_RESERVED_1                           250
-#define SVGA3D_DEVCAP_DXFMT_BC6H_TYPELESS                  251
-#define SVGA3D_DEVCAP_DXFMT_BC6H_UF16                      252
-#define SVGA3D_DEVCAP_DXFMT_BC6H_SF16                      253
-#define SVGA3D_DEVCAP_DXFMT_BC7_TYPELESS                   254
-#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM                      255
-#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM_SRGB                 256
-#define SVGA3D_DEVCAP_RESERVED_2                           257
-
-#define SVGA3D_DEVCAP_SM5                                  258
-#define SVGA3D_DEVCAP_MULTISAMPLE_8X                       259
-
-/* This must be the last index. */
-#define SVGA3D_DEVCAP_MAX                                  260
-
-/*
- * Bit definitions for DXFMT devcaps
- *
- *
- * SUPPORTED: Can the format be defined?
- * SHADER_SAMPLE: Can the format be sampled from a shader?
- * COLOR_RENDERTARGET: Can the format be a color render target?
- * DEPTH_RENDERTARGET: Can the format be a depth render target?
- * BLENDABLE: Is the format blendable?
- * MIPS: Does the format support mip levels?
- * ARRAY: Does the format support texture arrays?
- * VOLUME: Does the format support having volume?
- * MULTISAMPLE: Does the format support multisample?
- */
-#define SVGA3D_DXFMT_SUPPORTED                (1 <<  0)
-#define SVGA3D_DXFMT_SHADER_SAMPLE            (1 <<  1)
-#define SVGA3D_DXFMT_COLOR_RENDERTARGET       (1 <<  2)
-#define SVGA3D_DXFMT_DEPTH_RENDERTARGET       (1 <<  3)
-#define SVGA3D_DXFMT_BLENDABLE                (1 <<  4)
-#define SVGA3D_DXFMT_MIPS                     (1 <<  5)
-#define SVGA3D_DXFMT_ARRAY                    (1 <<  6)
-#define SVGA3D_DXFMT_VOLUME                   (1 <<  7)
-#define SVGA3D_DXFMT_DX_VERTEX_BUFFER         (1 <<  8)
-#define SVGA3D_DXFMT_MULTISAMPLE              (1 <<  9)
-#define SVGA3D_DXFMT_MAX                      (1 << 10)
+#define SVGA3D_DEVCAP_INVALID ((uint32)-1)
+#define SVGA3D_DEVCAP_3D 0
+#define SVGA3D_DEVCAP_MAX_LIGHTS 1
+
+#define SVGA3D_DEVCAP_MAX_TEXTURES 2
+#define SVGA3D_DEVCAP_MAX_CLIP_PLANES 3
+#define SVGA3D_DEVCAP_VERTEX_SHADER_VERSION 4
+#define SVGA3D_DEVCAP_VERTEX_SHADER 5
+#define SVGA3D_DEVCAP_FRAGMENT_SHADER_VERSION 6
+#define SVGA3D_DEVCAP_FRAGMENT_SHADER 7
+#define SVGA3D_DEVCAP_MAX_RENDER_TARGETS 8
+#define SVGA3D_DEVCAP_S23E8_TEXTURES 9
+#define SVGA3D_DEVCAP_S10E5_TEXTURES 10
+#define SVGA3D_DEVCAP_MAX_FIXED_VERTEXBLEND 11
+#define SVGA3D_DEVCAP_D16_BUFFER_FORMAT 12
+#define SVGA3D_DEVCAP_D24S8_BUFFER_FORMAT 13
+#define SVGA3D_DEVCAP_D24X8_BUFFER_FORMAT 14
+#define SVGA3D_DEVCAP_QUERY_TYPES 15
+#define SVGA3D_DEVCAP_TEXTURE_GRADIENT_SAMPLING 16
+#define SVGA3D_DEVCAP_MAX_POINT_SIZE 17
+#define SVGA3D_DEVCAP_MAX_SHADER_TEXTURES 18
+#define SVGA3D_DEVCAP_MAX_TEXTURE_WIDTH 19
+#define SVGA3D_DEVCAP_MAX_TEXTURE_HEIGHT 20
+#define SVGA3D_DEVCAP_MAX_VOLUME_EXTENT 21
+#define SVGA3D_DEVCAP_MAX_TEXTURE_REPEAT 22
+#define SVGA3D_DEVCAP_MAX_TEXTURE_ASPECT_RATIO 23
+#define SVGA3D_DEVCAP_MAX_TEXTURE_ANISOTROPY 24
+#define SVGA3D_DEVCAP_MAX_PRIMITIVE_COUNT 25
+#define SVGA3D_DEVCAP_MAX_VERTEX_INDEX 26
+#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_INSTRUCTIONS 27
+#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_INSTRUCTIONS 28
+#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEMPS 29
+#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_TEMPS 30
+#define SVGA3D_DEVCAP_TEXTURE_OPS 31
+#define SVGA3D_DEVCAP_SURFACEFMT_X8R8G8B8 32
+#define SVGA3D_DEVCAP_SURFACEFMT_A8R8G8B8 33
+#define SVGA3D_DEVCAP_SURFACEFMT_A2R10G10B10 34
+#define SVGA3D_DEVCAP_SURFACEFMT_X1R5G5B5 35
+#define SVGA3D_DEVCAP_SURFACEFMT_A1R5G5B5 36
+#define SVGA3D_DEVCAP_SURFACEFMT_A4R4G4B4 37
+#define SVGA3D_DEVCAP_SURFACEFMT_R5G6B5 38
+#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE16 39
+#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8_ALPHA8 40
+#define SVGA3D_DEVCAP_SURFACEFMT_ALPHA8 41
+#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8 42
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_D16 43
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8 44
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24X8 45
+#define SVGA3D_DEVCAP_SURFACEFMT_DXT1 46
+#define SVGA3D_DEVCAP_SURFACEFMT_DXT2 47
+#define SVGA3D_DEVCAP_SURFACEFMT_DXT3 48
+#define SVGA3D_DEVCAP_SURFACEFMT_DXT4 49
+#define SVGA3D_DEVCAP_SURFACEFMT_DXT5 50
+#define SVGA3D_DEVCAP_SURFACEFMT_BUMPX8L8V8U8 51
+#define SVGA3D_DEVCAP_SURFACEFMT_A2W10V10U10 52
+#define SVGA3D_DEVCAP_SURFACEFMT_BUMPU8V8 53
+#define SVGA3D_DEVCAP_SURFACEFMT_Q8W8V8U8 54
+#define SVGA3D_DEVCAP_SURFACEFMT_CxV8U8 55
+#define SVGA3D_DEVCAP_SURFACEFMT_R_S10E5 56
+#define SVGA3D_DEVCAP_SURFACEFMT_R_S23E8 57
+#define SVGA3D_DEVCAP_SURFACEFMT_RG_S10E5 58
+#define SVGA3D_DEVCAP_SURFACEFMT_RG_S23E8 59
+#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S10E5 60
+#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S23E8 61
+
+#define SVGA3D_DEVCAP_MISSING62 62
+
+#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEXTURES 63
+
+#define SVGA3D_DEVCAP_MAX_SIMULTANEOUS_RENDER_TARGETS 64
+
+#define SVGA3D_DEVCAP_SURFACEFMT_V16U16 65
+#define SVGA3D_DEVCAP_SURFACEFMT_G16R16 66
+#define SVGA3D_DEVCAP_SURFACEFMT_A16B16G16R16 67
+#define SVGA3D_DEVCAP_SURFACEFMT_UYVY 68
+#define SVGA3D_DEVCAP_SURFACEFMT_YUY2 69
+
+#define SVGA3D_DEVCAP_DEAD4 70
+#define SVGA3D_DEVCAP_DEAD5 71
+#define SVGA3D_DEVCAP_DEAD7 72
+#define SVGA3D_DEVCAP_DEAD6 73
+
+#define SVGA3D_DEVCAP_AUTOGENMIPMAPS 74
+#define SVGA3D_DEVCAP_SURFACEFMT_NV12 75
+#define SVGA3D_DEVCAP_DEAD10 76
+
+#define SVGA3D_DEVCAP_MAX_CONTEXT_IDS 77
+
+#define SVGA3D_DEVCAP_MAX_SURFACE_IDS 78
+
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF16 79
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF24 80
+#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8_INT 81
+
+#define SVGA3D_DEVCAP_SURFACEFMT_ATI1 82
+#define SVGA3D_DEVCAP_SURFACEFMT_ATI2 83
+
+#define SVGA3D_DEVCAP_DEAD1 84
+#define SVGA3D_DEVCAP_DEAD8 85
+#define SVGA3D_DEVCAP_DEAD9 86
+
+#define SVGA3D_DEVCAP_LINE_AA 87
+#define SVGA3D_DEVCAP_LINE_STIPPLE 88
+#define SVGA3D_DEVCAP_MAX_LINE_WIDTH 89
+#define SVGA3D_DEVCAP_MAX_AA_LINE_WIDTH 90
+
+#define SVGA3D_DEVCAP_SURFACEFMT_YV12 91
+
+#define SVGA3D_DEVCAP_DEAD3 92
+
+#define SVGA3D_DEVCAP_TS_COLOR_KEY 93
+
+#define SVGA3D_DEVCAP_DEAD2 94
+
+#define SVGA3D_DEVCAP_DXCONTEXT 95
+
+#define SVGA3D_DEVCAP_DEAD11 96
+
+#define SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS 97
+
+#define SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS 98
+
+#define SVGA3D_DEVCAP_DX_PROVOKING_VERTEX 99
+
+#define SVGA3D_DEVCAP_DXFMT_X8R8G8B8 100
+#define SVGA3D_DEVCAP_DXFMT_A8R8G8B8 101
+#define SVGA3D_DEVCAP_DXFMT_R5G6B5 102
+#define SVGA3D_DEVCAP_DXFMT_X1R5G5B5 103
+#define SVGA3D_DEVCAP_DXFMT_A1R5G5B5 104
+#define SVGA3D_DEVCAP_DXFMT_A4R4G4B4 105
+#define SVGA3D_DEVCAP_DXFMT_Z_D32 106
+#define SVGA3D_DEVCAP_DXFMT_Z_D16 107
+#define SVGA3D_DEVCAP_DXFMT_Z_D24S8 108
+#define SVGA3D_DEVCAP_DXFMT_Z_D15S1 109
+#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8 110
+#define SVGA3D_DEVCAP_DXFMT_LUMINANCE4_ALPHA4 111
+#define SVGA3D_DEVCAP_DXFMT_LUMINANCE16 112
+#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8_ALPHA8 113
+#define SVGA3D_DEVCAP_DXFMT_DXT1 114
+#define SVGA3D_DEVCAP_DXFMT_DXT2 115
+#define SVGA3D_DEVCAP_DXFMT_DXT3 116
+#define SVGA3D_DEVCAP_DXFMT_DXT4 117
+#define SVGA3D_DEVCAP_DXFMT_DXT5 118
+#define SVGA3D_DEVCAP_DXFMT_BUMPU8V8 119
+#define SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5 120
+#define SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8 121
+#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1 122
+#define SVGA3D_DEVCAP_DXFMT_ARGB_S10E5 123
+#define SVGA3D_DEVCAP_DXFMT_ARGB_S23E8 124
+#define SVGA3D_DEVCAP_DXFMT_A2R10G10B10 125
+#define SVGA3D_DEVCAP_DXFMT_V8U8 126
+#define SVGA3D_DEVCAP_DXFMT_Q8W8V8U8 127
+#define SVGA3D_DEVCAP_DXFMT_CxV8U8 128
+#define SVGA3D_DEVCAP_DXFMT_X8L8V8U8 129
+#define SVGA3D_DEVCAP_DXFMT_A2W10V10U10 130
+#define SVGA3D_DEVCAP_DXFMT_ALPHA8 131
+#define SVGA3D_DEVCAP_DXFMT_R_S10E5 132
+#define SVGA3D_DEVCAP_DXFMT_R_S23E8 133
+#define SVGA3D_DEVCAP_DXFMT_RG_S10E5 134
+#define SVGA3D_DEVCAP_DXFMT_RG_S23E8 135
+#define SVGA3D_DEVCAP_DXFMT_BUFFER 136
+#define SVGA3D_DEVCAP_DXFMT_Z_D24X8 137
+#define SVGA3D_DEVCAP_DXFMT_V16U16 138
+#define SVGA3D_DEVCAP_DXFMT_G16R16 139
+#define SVGA3D_DEVCAP_DXFMT_A16B16G16R16 140
+#define SVGA3D_DEVCAP_DXFMT_UYVY 141
+#define SVGA3D_DEVCAP_DXFMT_YUY2 142
+#define SVGA3D_DEVCAP_DXFMT_NV12 143
+#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD2 144
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_TYPELESS 145
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_UINT 146
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_SINT 147
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32_TYPELESS 148
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32_FLOAT 149
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32_UINT 150
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32_SINT 151
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_TYPELESS 152
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UINT 153
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SNORM 154
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SINT 155
+#define SVGA3D_DEVCAP_DXFMT_R32G32_TYPELESS 156
+#define SVGA3D_DEVCAP_DXFMT_R32G32_UINT 157
+#define SVGA3D_DEVCAP_DXFMT_R32G32_SINT 158
+#define SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS 159
+#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT 160
+#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24 161
+#define SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT 162
+#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS 163
+#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT 164
+#define SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT 165
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_TYPELESS 166
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM 167
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM_SRGB 168
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UINT 169
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SINT 170
+#define SVGA3D_DEVCAP_DXFMT_R16G16_TYPELESS 171
+#define SVGA3D_DEVCAP_DXFMT_R16G16_UINT 172
+#define SVGA3D_DEVCAP_DXFMT_R16G16_SINT 173
+#define SVGA3D_DEVCAP_DXFMT_R32_TYPELESS 174
+#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT 175
+#define SVGA3D_DEVCAP_DXFMT_R32_UINT 176
+#define SVGA3D_DEVCAP_DXFMT_R32_SINT 177
+#define SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS 178
+#define SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT 179
+#define SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8 180
+#define SVGA3D_DEVCAP_DXFMT_X24_G8_UINT 181
+#define SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS 182
+#define SVGA3D_DEVCAP_DXFMT_R8G8_UNORM 183
+#define SVGA3D_DEVCAP_DXFMT_R8G8_UINT 184
+#define SVGA3D_DEVCAP_DXFMT_R8G8_SINT 185
+#define SVGA3D_DEVCAP_DXFMT_R16_TYPELESS 186
+#define SVGA3D_DEVCAP_DXFMT_R16_UNORM 187
+#define SVGA3D_DEVCAP_DXFMT_R16_UINT 188
+#define SVGA3D_DEVCAP_DXFMT_R16_SNORM 189
+#define SVGA3D_DEVCAP_DXFMT_R16_SINT 190
+#define SVGA3D_DEVCAP_DXFMT_R8_TYPELESS 191
+#define SVGA3D_DEVCAP_DXFMT_R8_UNORM 192
+#define SVGA3D_DEVCAP_DXFMT_R8_UINT 193
+#define SVGA3D_DEVCAP_DXFMT_R8_SNORM 194
+#define SVGA3D_DEVCAP_DXFMT_R8_SINT 195
+#define SVGA3D_DEVCAP_DXFMT_P8 196
+#define SVGA3D_DEVCAP_DXFMT_R9G9B9E5_SHAREDEXP 197
+#define SVGA3D_DEVCAP_DXFMT_R8G8_B8G8_UNORM 198
+#define SVGA3D_DEVCAP_DXFMT_G8R8_G8B8_UNORM 199
+#define SVGA3D_DEVCAP_DXFMT_BC1_TYPELESS 200
+#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM_SRGB 201
+#define SVGA3D_DEVCAP_DXFMT_BC2_TYPELESS 202
+#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM_SRGB 203
+#define SVGA3D_DEVCAP_DXFMT_BC3_TYPELESS 204
+#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM_SRGB 205
+#define SVGA3D_DEVCAP_DXFMT_BC4_TYPELESS 206
+#define SVGA3D_DEVCAP_DXFMT_ATI1 207
+#define SVGA3D_DEVCAP_DXFMT_BC4_SNORM 208
+#define SVGA3D_DEVCAP_DXFMT_BC5_TYPELESS 209
+#define SVGA3D_DEVCAP_DXFMT_ATI2 210
+#define SVGA3D_DEVCAP_DXFMT_BC5_SNORM 211
+#define SVGA3D_DEVCAP_DXFMT_R10G10B10_XR_BIAS_A2_UNORM 212
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_TYPELESS 213
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM_SRGB 214
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_TYPELESS 215
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM_SRGB 216
+#define SVGA3D_DEVCAP_DXFMT_Z_DF16 217
+#define SVGA3D_DEVCAP_DXFMT_Z_DF24 218
+#define SVGA3D_DEVCAP_DXFMT_Z_D24S8_INT 219
+#define SVGA3D_DEVCAP_DXFMT_YV12 220
+#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_FLOAT 221
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_FLOAT 222
+#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UNORM 223
+#define SVGA3D_DEVCAP_DXFMT_R32G32_FLOAT 224
+#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UNORM 225
+#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SNORM 226
+#define SVGA3D_DEVCAP_DXFMT_R16G16_FLOAT 227
+#define SVGA3D_DEVCAP_DXFMT_R16G16_UNORM 228
+#define SVGA3D_DEVCAP_DXFMT_R16G16_SNORM 229
+#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT 230
+#define SVGA3D_DEVCAP_DXFMT_R8G8_SNORM 231
+#define SVGA3D_DEVCAP_DXFMT_R16_FLOAT 232
+#define SVGA3D_DEVCAP_DXFMT_D16_UNORM 233
+#define SVGA3D_DEVCAP_DXFMT_A8_UNORM 234
+#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM 235
+#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM 236
+#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM 237
+#define SVGA3D_DEVCAP_DXFMT_B5G6R5_UNORM 238
+#define SVGA3D_DEVCAP_DXFMT_B5G5R5A1_UNORM 239
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM 240
+#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM 241
+#define SVGA3D_DEVCAP_DXFMT_BC4_UNORM 242
+#define SVGA3D_DEVCAP_DXFMT_BC5_UNORM 243
+
+#define SVGA3D_DEVCAP_SM41 244
+#define SVGA3D_DEVCAP_MULTISAMPLE_2X 245
+#define SVGA3D_DEVCAP_MULTISAMPLE_4X 246
+
+#define SVGA3D_DEVCAP_MS_FULL_QUALITY 247
+
+#define SVGA3D_DEVCAP_LOGICOPS 248
+
+#define SVGA3D_DEVCAP_LOGIC_BLENDOPS 249
+
+#define SVGA3D_DEVCAP_DEAD12 250
+
+#define SVGA3D_DEVCAP_DXFMT_BC6H_TYPELESS 251
+#define SVGA3D_DEVCAP_DXFMT_BC6H_UF16 252
+#define SVGA3D_DEVCAP_DXFMT_BC6H_SF16 253
+#define SVGA3D_DEVCAP_DXFMT_BC7_TYPELESS 254
+#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM 255
+#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM_SRGB 256
+
+#define SVGA3D_DEVCAP_DEAD13 257
+
+#define SVGA3D_DEVCAP_SM5 258
+#define SVGA3D_DEVCAP_MULTISAMPLE_8X 259
+
+#define SVGA3D_DEVCAP_MAX 262
+
+#define SVGA3D_DXFMT_SUPPORTED (1 << 0)
+#define SVGA3D_DXFMT_SHADER_SAMPLE (1 << 1)
+#define SVGA3D_DXFMT_COLOR_RENDERTARGET (1 << 2)
+#define SVGA3D_DXFMT_DEPTH_RENDERTARGET (1 << 3)
+#define SVGA3D_DXFMT_BLENDABLE (1 << 4)
+#define SVGA3D_DXFMT_MIPS (1 << 5)
+#define SVGA3D_DXFMT_ARRAY (1 << 6)
+#define SVGA3D_DXFMT_VOLUME (1 << 7)
+#define SVGA3D_DXFMT_DX_VERTEX_BUFFER (1 << 8)
+#define SVGA3D_DXFMT_MULTISAMPLE (1 << 9)
+#define SVGA3D_DXFMT_MAX (1 << 10)
 
 typedef union {
-   SVGA3dBool b;
-   uint32 u;
-   int32 i;
-   float f;
+	SVGA3dBool b;
+	uint32 u;
+	int32 i;
+	float f;
 } SVGA3dDevCapResult;
 
-#endif /* _SVGA3D_DEVCAPS_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
index f703ac2b1768..5af442dad542 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2019 VMware, Inc.
+ * Copyright 2012-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,88 +27,70 @@
 /*
  * svga3d_dx.h --
  *
- *       SVGA 3d hardware definitions for DX10 support.
+ *    SVGA 3d hardware definitions for DX10 support.
  */
 
+
+
 #ifndef _SVGA3D_DX_H_
 #define _SVGA3D_DX_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
-#include "includeCheck.h"
-
+#include "svga_reg.h"
 #include "svga3d_limits.h"
+#include "svga3d_types.h"
 
-#define SVGA3D_INPUT_MIN               0
-#define SVGA3D_INPUT_PER_VERTEX_DATA   0
+#define SVGA3D_INPUT_MIN 0
+#define SVGA3D_INPUT_PER_VERTEX_DATA 0
 #define SVGA3D_INPUT_PER_INSTANCE_DATA 1
-#define SVGA3D_INPUT_MAX               2
+#define SVGA3D_INPUT_MAX 2
 typedef uint32 SVGA3dInputClassification;
 
-#define SVGA3D_RESOURCE_TYPE_MIN      1
-#define SVGA3D_RESOURCE_BUFFER        1
-#define SVGA3D_RESOURCE_TEXTURE1D     2
-#define SVGA3D_RESOURCE_TEXTURE2D     3
-#define SVGA3D_RESOURCE_TEXTURE3D     4
-#define SVGA3D_RESOURCE_TEXTURECUBE   5
-#define SVGA3D_RESOURCE_TYPE_DX10_MAX 6
-#define SVGA3D_RESOURCE_BUFFEREX      6
-#define SVGA3D_RESOURCE_TYPE_MAX      7
-typedef uint32 SVGA3dResourceType;
-
-#define SVGA3D_COLOR_WRITE_ENABLE_RED     (1 << 0)
-#define SVGA3D_COLOR_WRITE_ENABLE_GREEN   (1 << 1)
-#define SVGA3D_COLOR_WRITE_ENABLE_BLUE    (1 << 2)
-#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA   (1 << 3)
-#define SVGA3D_COLOR_WRITE_ENABLE_ALL     (SVGA3D_COLOR_WRITE_ENABLE_RED |   \
-                                           SVGA3D_COLOR_WRITE_ENABLE_GREEN | \
-                                           SVGA3D_COLOR_WRITE_ENABLE_BLUE |  \
-                                           SVGA3D_COLOR_WRITE_ENABLE_ALPHA)
+#define SVGA3D_COLOR_WRITE_ENABLE_RED (1 << 0)
+#define SVGA3D_COLOR_WRITE_ENABLE_GREEN (1 << 1)
+#define SVGA3D_COLOR_WRITE_ENABLE_BLUE (1 << 2)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA (1 << 3)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALL                                          \
+	(SVGA3D_COLOR_WRITE_ENABLE_RED | SVGA3D_COLOR_WRITE_ENABLE_GREEN |     \
+	 SVGA3D_COLOR_WRITE_ENABLE_BLUE | SVGA3D_COLOR_WRITE_ENABLE_ALPHA)
 typedef uint8 SVGA3dColorWriteEnable;
 
-#define SVGA3D_DEPTH_WRITE_MASK_ZERO   0
-#define SVGA3D_DEPTH_WRITE_MASK_ALL    1
+#define SVGA3D_DEPTH_WRITE_MASK_ZERO 0
+#define SVGA3D_DEPTH_WRITE_MASK_ALL 1
 typedef uint8 SVGA3dDepthWriteMask;
 
-#define SVGA3D_FILTER_MIP_LINEAR  (1 << 0)
-#define SVGA3D_FILTER_MAG_LINEAR  (1 << 2)
-#define SVGA3D_FILTER_MIN_LINEAR  (1 << 4)
+#define SVGA3D_FILTER_MIP_LINEAR (1 << 0)
+#define SVGA3D_FILTER_MAG_LINEAR (1 << 2)
+#define SVGA3D_FILTER_MIN_LINEAR (1 << 4)
 #define SVGA3D_FILTER_ANISOTROPIC (1 << 6)
-#define SVGA3D_FILTER_COMPARE     (1 << 7)
+#define SVGA3D_FILTER_COMPARE (1 << 7)
 typedef uint32 SVGA3dFilter;
 
 #define SVGA3D_CULL_INVALID 0
-#define SVGA3D_CULL_MIN     1
-#define SVGA3D_CULL_NONE    1
-#define SVGA3D_CULL_FRONT   2
-#define SVGA3D_CULL_BACK    3
-#define SVGA3D_CULL_MAX     4
+#define SVGA3D_CULL_MIN 1
+#define SVGA3D_CULL_NONE 1
+#define SVGA3D_CULL_FRONT 2
+#define SVGA3D_CULL_BACK 3
+#define SVGA3D_CULL_MAX 4
 typedef uint8 SVGA3dCullMode;
 
-#define SVGA3D_COMPARISON_INVALID         0
-#define SVGA3D_COMPARISON_MIN             1
-#define SVGA3D_COMPARISON_NEVER           1
-#define SVGA3D_COMPARISON_LESS            2
-#define SVGA3D_COMPARISON_EQUAL           3
-#define SVGA3D_COMPARISON_LESS_EQUAL      4
-#define SVGA3D_COMPARISON_GREATER         5
-#define SVGA3D_COMPARISON_NOT_EQUAL       6
-#define SVGA3D_COMPARISON_GREATER_EQUAL   7
-#define SVGA3D_COMPARISON_ALWAYS          8
-#define SVGA3D_COMPARISON_MAX             9
+#define SVGA3D_COMPARISON_INVALID 0
+#define SVGA3D_COMPARISON_MIN 1
+#define SVGA3D_COMPARISON_NEVER 1
+#define SVGA3D_COMPARISON_LESS 2
+#define SVGA3D_COMPARISON_EQUAL 3
+#define SVGA3D_COMPARISON_LESS_EQUAL 4
+#define SVGA3D_COMPARISON_GREATER 5
+#define SVGA3D_COMPARISON_NOT_EQUAL 6
+#define SVGA3D_COMPARISON_GREATER_EQUAL 7
+#define SVGA3D_COMPARISON_ALWAYS 8
+#define SVGA3D_COMPARISON_MAX 9
 typedef uint8 SVGA3dComparisonFunc;
 
-/*
- * SVGA3D_MULTISAMPLE_RAST_DISABLE disables MSAA for all primitives.
- * SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE, which is supported in SM41,
- * disables MSAA for lines only.
- */
-#define SVGA3D_MULTISAMPLE_RAST_DISABLE        0
-#define SVGA3D_MULTISAMPLE_RAST_ENABLE         1
-#define SVGA3D_MULTISAMPLE_RAST_DX_MAX         1
-#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE   2
-#define SVGA3D_MULTISAMPLE_RAST_MAX            2
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE 0
+#define SVGA3D_MULTISAMPLE_RAST_ENABLE 1
+#define SVGA3D_MULTISAMPLE_RAST_DX_MAX 1
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE 2
+#define SVGA3D_MULTISAMPLE_RAST_MAX 2
 typedef uint8 SVGA3dMultisampleRastEnable;
 
 #define SVGA3D_DX_MAX_VERTEXBUFFERS 32
@@ -137,1531 +119,1273 @@ typedef uint32 SVGA3dQueryId;
 typedef uint32 SVGA3dStreamOutputId;
 
 typedef union {
-   struct {
-      float r;
-      float g;
-      float b;
-      float a;
-   };
-
-   float value[4];
-} SVGA3dRGBAFloat;
-
-typedef union {
-   struct {
-      uint32 r;
-      uint32 g;
-      uint32 b;
-      uint32 a;
-   };
-
-   uint32 value[4];
+	struct {
+		uint32 r;
+		uint32 g;
+		uint32 b;
+		uint32 a;
+	};
+
+	uint32 value[4];
 } SVGA3dRGBAUint32;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 cid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGAOTableDXContextEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineContext;   /* SVGA_3D_CMD_DX_DEFINE_CONTEXT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyContext;   /* SVGA_3D_CMD_DX_DESTROY_CONTEXT */
-
-/*
- * Bind a DX context.
- *
- * validContents should be set to 0 for new contexts,
- * and 1 if this is an old context which is getting paged
- * back on to the device.
- *
- * For new contexts, it is recommended that the driver
- * issue commands to initialize all interesting state
- * prior to rendering.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindContext {
-   uint32 cid;
-   SVGAMobId mobid;
-   uint32 validContents;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindContext;   /* SVGA_3D_CMD_DX_BIND_CONTEXT */
-
-/*
- * Readback a DX context.
- * (Request that the device flush the contents back into guest memory.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXReadbackContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXReadbackContext;   /* SVGA_3D_CMD_DX_READBACK_CONTEXT */
-
-/*
- * Invalidate a guest-backed context.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXInvalidateContext {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXInvalidateContext;   /* SVGA_3D_CMD_DX_INVALIDATE_CONTEXT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetSingleConstantBuffer {
-   uint32 slot;
-   SVGA3dShaderType type;
-   SVGA3dSurfaceId sid;
-   uint32 offsetInBytes;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetSingleConstantBuffer;
-/* SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetShaderResources {
-   uint32 startView;
-   SVGA3dShaderType type;
-
-   /*
-    * Followed by a variable number of SVGA3dShaderResourceViewId's.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetShaderResources; /* SVGA_3D_CMD_DX_SET_SHADER_RESOURCES */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetShader {
-   SVGA3dShaderId shaderId;
-   SVGA3dShaderType type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetShader; /* SVGA_3D_CMD_DX_SET_SHADER */
+#pragma pack(push, 1)
+typedef struct {
+	uint32 cid;
+	SVGAMobId mobid;
+} SVGAOTableDXContextEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineContext {
+	uint32 cid;
+} SVGA3dCmdDXDefineContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyContext {
+	uint32 cid;
+} SVGA3dCmdDXDestroyContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindContext {
+	uint32 cid;
+	SVGAMobId mobid;
+	uint32 validContents;
+} SVGA3dCmdDXBindContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXReadbackContext {
+	uint32 cid;
+} SVGA3dCmdDXReadbackContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXInvalidateContext {
+	uint32 cid;
+} SVGA3dCmdDXInvalidateContext;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetSingleConstantBuffer {
+	uint32 slot;
+	SVGA3dShaderType type;
+	SVGA3dSurfaceId sid;
+	uint32 offsetInBytes;
+	uint32 sizeInBytes;
+} SVGA3dCmdDXSetSingleConstantBuffer;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetShaderResources {
+	uint32 startView;
+	SVGA3dShaderType type;
+
+} SVGA3dCmdDXSetShaderResources;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetShader {
+	SVGA3dShaderId shaderId;
+	SVGA3dShaderType type;
+} SVGA3dCmdDXSetShader;
+#pragma pack(pop)
 
 typedef union {
-   struct {
-      uint32 cbOffset : 12;
-      uint32 cbId     : 4;
-      uint32 baseSamp : 4;
-      uint32 baseTex  : 7;
-      uint32 reserved : 5;
-   };
-   uint32 value;
+	struct {
+		uint32 cbOffset : 12;
+		uint32 cbId : 4;
+		uint32 baseSamp : 4;
+		uint32 baseTex : 7;
+		uint32 reserved : 5;
+	};
+	uint32 value;
 } SVGA3dIfaceData;
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetShaderIface {
-   SVGA3dShaderType type;
-   uint32 numClassInstances;
-   uint32 index;
-   uint32 iface;
-   SVGA3dIfaceData data;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetShaderIface; /* SVGA_3D_CMD_DX_SET_SHADER_IFACE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindShaderIface {
-   uint32 cid;
-   SVGAMobId mobid;
-   uint32 offsetInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindShaderIface; /* SVGA_3D_CMD_DX_BIND_SHADER_IFACE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetSamplers {
-   uint32 startSampler;
-   SVGA3dShaderType type;
-
-   /*
-    * Followed by a variable number of SVGA3dSamplerId's.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetSamplers; /* SVGA_3D_CMD_DX_SET_SAMPLERS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDraw {
-   uint32 vertexCount;
-   uint32 startVertexLocation;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDraw; /* SVGA_3D_CMD_DX_DRAW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawIndexed {
-   uint32 indexCount;
-   uint32 startIndexLocation;
-   int32  baseVertexLocation;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawIndexed; /* SVGA_3D_CMD_DX_DRAW_INDEXED */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawInstanced {
-   uint32 vertexCountPerInstance;
-   uint32 instanceCount;
-   uint32 startVertexLocation;
-   uint32 startInstanceLocation;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawInstanced; /* SVGA_3D_CMD_DX_DRAW_INSTANCED */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawIndexedInstanced {
-   uint32 indexCountPerInstance;
-   uint32 instanceCount;
-   uint32 startIndexLocation;
-   int32  baseVertexLocation;
-   uint32 startInstanceLocation;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawIndexedInstanced; /* SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawIndexedInstancedIndirect {
-   SVGA3dSurfaceId argsBufferSid;
-   uint32 byteOffsetForArgs;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawIndexedInstancedIndirect;
-/* SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawInstancedIndirect {
-   SVGA3dSurfaceId argsBufferSid;
-   uint32 byteOffsetForArgs;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawInstancedIndirect;
-/* SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDrawAuto {
-   uint32 pad0;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDrawAuto; /* SVGA_3D_CMD_DX_DRAW_AUTO */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDispatch {
-   uint32 threadGroupCountX;
-   uint32 threadGroupCountY;
-   uint32 threadGroupCountZ;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDispatch;
-/* SVGA_3D_CMD_DX_DISPATCH */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDispatchIndirect {
-   SVGA3dSurfaceId argsBufferSid;
-   uint32 byteOffsetForArgs;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDispatchIndirect;
-/* SVGA_3D_CMD_DX_DISPATCH_INDIRECT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetInputLayout {
-   SVGA3dElementLayoutId elementLayoutId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetInputLayout; /* SVGA_3D_CMD_DX_SET_INPUT_LAYOUT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dVertexBuffer {
-   SVGA3dSurfaceId sid;
-   uint32 stride;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dVertexBuffer;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetVertexBuffers {
-   uint32 startBuffer;
-   /* Followed by a variable number of SVGA3dVertexBuffer's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetVertexBuffers; /* SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetIndexBuffer {
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetIndexBuffer; /* SVGA_3D_CMD_DX_SET_INDEX_BUFFER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetTopology {
-   SVGA3dPrimitiveType topology;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetTopology; /* SVGA_3D_CMD_DX_SET_TOPOLOGY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetRenderTargets {
-   SVGA3dDepthStencilViewId depthStencilViewId;
-   /* Followed by a variable number of SVGA3dRenderTargetViewId's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetRenderTargets; /* SVGA_3D_CMD_DX_SET_RENDERTARGETS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetBlendState {
-   SVGA3dBlendStateId blendId;
-   float blendFactor[4];
-   uint32 sampleMask;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetBlendState; /* SVGA_3D_CMD_DX_SET_BLEND_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetDepthStencilState {
-   SVGA3dDepthStencilStateId depthStencilId;
-   uint32 stencilRef;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetDepthStencilState; /* SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetRasterizerState {
-   SVGA3dRasterizerStateId rasterizerId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetRasterizerState; /* SVGA_3D_CMD_DX_SET_RASTERIZER_STATE */
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetShaderIface {
+	SVGA3dShaderType type;
+	uint32 numClassInstances;
+	uint32 index;
+	uint32 iface;
+	SVGA3dIfaceData data;
+} SVGA3dCmdDXSetShaderIface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindShaderIface {
+	uint32 cid;
+	SVGAMobId mobid;
+	uint32 offsetInBytes;
+} SVGA3dCmdDXBindShaderIface;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetSamplers {
+	uint32 startSampler;
+	SVGA3dShaderType type;
+
+} SVGA3dCmdDXSetSamplers;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDraw {
+	uint32 vertexCount;
+	uint32 startVertexLocation;
+} SVGA3dCmdDXDraw;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawIndexed {
+	uint32 indexCount;
+	uint32 startIndexLocation;
+	int32 baseVertexLocation;
+} SVGA3dCmdDXDrawIndexed;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawInstanced {
+	uint32 vertexCountPerInstance;
+	uint32 instanceCount;
+	uint32 startVertexLocation;
+	uint32 startInstanceLocation;
+} SVGA3dCmdDXDrawInstanced;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawIndexedInstanced {
+	uint32 indexCountPerInstance;
+	uint32 instanceCount;
+	uint32 startIndexLocation;
+	int32 baseVertexLocation;
+	uint32 startInstanceLocation;
+} SVGA3dCmdDXDrawIndexedInstanced;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawIndexedInstancedIndirect {
+	SVGA3dSurfaceId argsBufferSid;
+	uint32 byteOffsetForArgs;
+} SVGA3dCmdDXDrawIndexedInstancedIndirect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawInstancedIndirect {
+	SVGA3dSurfaceId argsBufferSid;
+	uint32 byteOffsetForArgs;
+} SVGA3dCmdDXDrawInstancedIndirect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDrawAuto {
+	uint32 pad0;
+} SVGA3dCmdDXDrawAuto;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDispatch {
+	uint32 threadGroupCountX;
+	uint32 threadGroupCountY;
+	uint32 threadGroupCountZ;
+} SVGA3dCmdDXDispatch;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDispatchIndirect {
+	SVGA3dSurfaceId argsBufferSid;
+	uint32 byteOffsetForArgs;
+} SVGA3dCmdDXDispatchIndirect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetInputLayout {
+	SVGA3dElementLayoutId elementLayoutId;
+} SVGA3dCmdDXSetInputLayout;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dVertexBuffer {
+	SVGA3dSurfaceId sid;
+	uint32 stride;
+	uint32 offset;
+} SVGA3dVertexBuffer;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetVertexBuffers {
+	uint32 startBuffer;
+
+} SVGA3dCmdDXSetVertexBuffers;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dVertexBuffer_v2 {
+	SVGA3dSurfaceId sid;
+	uint32 stride;
+	uint32 offset;
+	uint32 sizeInBytes;
+} SVGA3dVertexBuffer_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetVertexBuffers_v2 {
+	uint32 startBuffer;
+
+} SVGA3dCmdDXSetVertexBuffers_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dVertexBufferOffsetAndSize {
+	uint32 stride;
+	uint32 offset;
+	uint32 sizeInBytes;
+} SVGA3dVertexBufferOffsetAndSize;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetVertexBuffersOffsetAndSize {
+	uint32 startBuffer;
+
+} SVGA3dCmdDXSetVertexBuffersOffsetAndSize;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetIndexBuffer {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	uint32 offset;
+} SVGA3dCmdDXSetIndexBuffer;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetIndexBuffer_v2 {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	uint32 offset;
+	uint32 sizeInBytes;
+} SVGA3dCmdDXSetIndexBuffer_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetIndexBufferOffsetAndSize {
+	SVGA3dSurfaceFormat format;
+	uint32 offset;
+	uint32 sizeInBytes;
+} SVGA3dCmdDXSetIndexBufferOffsetAndSize;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetTopology {
+	SVGA3dPrimitiveType topology;
+} SVGA3dCmdDXSetTopology;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetRenderTargets {
+	SVGA3dDepthStencilViewId depthStencilViewId;
+
+} SVGA3dCmdDXSetRenderTargets;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetBlendState {
+	SVGA3dBlendStateId blendId;
+	float blendFactor[4];
+	uint32 sampleMask;
+} SVGA3dCmdDXSetBlendState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetDepthStencilState {
+	SVGA3dDepthStencilStateId depthStencilId;
+	uint32 stencilRef;
+} SVGA3dCmdDXSetDepthStencilState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetRasterizerState {
+	SVGA3dRasterizerStateId rasterizerId;
+} SVGA3dCmdDXSetRasterizerState;
+#pragma pack(pop)
 
 #define SVGA3D_DXQUERY_FLAG_PREDICATEHINT (1 << 0)
 typedef uint32 SVGA3dDXQueryFlags;
 
-/*
- * The SVGADXQueryDeviceState and SVGADXQueryDeviceBits are used by the device
- * to track query state transitions, but are not intended to be used by the
- * driver.
- */
-#define SVGADX_QDSTATE_INVALID   ((uint8)-1) /* Query has no state */
-#define SVGADX_QDSTATE_MIN       0
-#define SVGADX_QDSTATE_IDLE      0   /* Query hasn't started yet */
-#define SVGADX_QDSTATE_ACTIVE    1   /* Query is actively gathering data */
-#define SVGADX_QDSTATE_PENDING   2   /* Query is waiting for results */
-#define SVGADX_QDSTATE_FINISHED  3   /* Query has completed */
-#define SVGADX_QDSTATE_MAX       4
+#define SVGADX_QDSTATE_INVALID ((uint8)-1)
+#define SVGADX_QDSTATE_MIN 0
+#define SVGADX_QDSTATE_IDLE 0
+#define SVGADX_QDSTATE_ACTIVE 1
+#define SVGADX_QDSTATE_PENDING 2
+#define SVGADX_QDSTATE_FINISHED 3
+#define SVGADX_QDSTATE_MAX 4
 typedef uint8 SVGADXQueryDeviceState;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dQueryTypeUint8 type;
-   uint16 pad0;
-   SVGADXQueryDeviceState state;
-   SVGA3dDXQueryFlags flags;
-   SVGAMobId mobid;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXQueryEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineQuery {
-   SVGA3dQueryId queryId;
-   SVGA3dQueryType type;
-   SVGA3dDXQueryFlags flags;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineQuery; /* SVGA_3D_CMD_DX_DEFINE_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyQuery {
-   SVGA3dQueryId queryId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyQuery; /* SVGA_3D_CMD_DX_DESTROY_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindQuery {
-   SVGA3dQueryId queryId;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindQuery; /* SVGA_3D_CMD_DX_BIND_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetQueryOffset {
-   SVGA3dQueryId queryId;
-   uint32 mobOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetQueryOffset; /* SVGA_3D_CMD_DX_SET_QUERY_OFFSET */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBeginQuery {
-   SVGA3dQueryId queryId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBeginQuery; /* SVGA_3D_CMD_DX_QUERY_BEGIN */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXEndQuery {
-   SVGA3dQueryId queryId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXEndQuery; /* SVGA_3D_CMD_DX_QUERY_END */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXReadbackQuery {
-   SVGA3dQueryId queryId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXReadbackQuery; /* SVGA_3D_CMD_DX_READBACK_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXMoveQuery {
-   SVGA3dQueryId queryId;
-   SVGAMobId mobid;
-   uint32 mobOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXMoveQuery; /* SVGA_3D_CMD_DX_MOVE_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindAllQuery {
-   uint32 cid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindAllQuery; /* SVGA_3D_CMD_DX_BIND_ALL_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXReadbackAllQuery {
-   uint32 cid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXReadbackAllQuery; /* SVGA_3D_CMD_DX_READBACK_ALL_QUERY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetPredication {
-   SVGA3dQueryId queryId;
-   uint32 predicateValue;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetPredication; /* SVGA_3D_CMD_DX_SET_PREDICATION */
-
-typedef
-#include "vmware_pack_begin.h"
-struct MKS3dDXSOState {
-   uint32 offset;       /* Starting offset */
-   uint32 intOffset;    /* Internal offset */
-   uint32 vertexCount;  /* vertices written */
-   uint32 dead;
-}
-#include "vmware_pack_end.h"
-SVGA3dDXSOState;
-
-/* Set the offset field to this value to append SO values to the buffer */
-#define SVGA3D_DX_SO_OFFSET_APPEND ((uint32) ~0u)
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSoTarget {
-   SVGA3dSurfaceId sid;
-   uint32 offset;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dSoTarget;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetSOTargets {
-   uint32 pad0;
-   /* Followed by a variable number of SVGA3dSOTarget's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetSOTargets; /* SVGA_3D_CMD_DX_SET_SOTARGETS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dViewport
-{
-   float x;
-   float y;
-   float width;
-   float height;
-   float minDepth;
-   float maxDepth;
-}
-#include "vmware_pack_end.h"
-SVGA3dViewport;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetViewports {
-   uint32 pad0;
-   /* Followed by a variable number of SVGA3dViewport's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetViewports; /* SVGA_3D_CMD_DX_SET_VIEWPORTS */
-
-#define SVGA3D_DX_MAX_VIEWPORTS  16
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetScissorRects {
-   uint32 pad0;
-   /* Followed by a variable number of SVGASignedRect's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetScissorRects; /* SVGA_3D_CMD_DX_SET_SCISSORRECTS */
-
-#define SVGA3D_DX_MAX_SCISSORRECTS  16
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXClearRenderTargetView {
-   SVGA3dRenderTargetViewId renderTargetViewId;
-   SVGA3dRGBAFloat rgba;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXClearRenderTargetView; /* SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXClearDepthStencilView {
-   uint16 flags;
-   uint16 stencil;
-   SVGA3dDepthStencilViewId depthStencilViewId;
-   float depth;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXClearDepthStencilView; /* SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPredCopyRegion {
-   SVGA3dSurfaceId dstSid;
-   uint32 dstSubResource;
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dCopyBox box;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredCopyRegion;
-/* SVGA_3D_CMD_DX_PRED_COPY_REGION */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPredCopy {
-   SVGA3dSurfaceId dstSid;
-   SVGA3dSurfaceId srcSid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredCopy; /* SVGA_3D_CMD_DX_PRED_COPY */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPredConvertRegion {
-   SVGA3dSurfaceId dstSid;
-   uint32 dstSubResource;
-   SVGA3dBox destBox;
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dBox srcBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredConvertRegion; /* SVGA_3D_CMD_DX_PRED_CONVERT_REGION */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPredConvert {
-   SVGA3dSurfaceId dstSid;
-   SVGA3dSurfaceId srcSid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredConvert; /* SVGA_3D_CMD_DX_PRED_CONVERT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBufferCopy {
-   SVGA3dSurfaceId dest;
-   SVGA3dSurfaceId src;
-   uint32 destX;
-   uint32 srcX;
-   uint32 width;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBufferCopy;
-/* SVGA_3D_CMD_DX_BUFFER_COPY */
-
-/*
- * Perform a surface copy between a multisample, and a non-multisampled
- * surface.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId dstSid;
-   uint32 dstSubResource;
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dSurfaceFormat copyFormat;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXResolveCopy;               /* SVGA_3D_CMD_DX_RESOLVE_COPY */
-
-/*
- * Perform a predicated surface copy between a multisample, and a
- * non-multisampled surface.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId dstSid;
-   uint32 dstSubResource;
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dSurfaceFormat copyFormat;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredResolveCopy;           /* SVGA_3D_CMD_DX_PRED_RESOLVE_COPY */
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dQueryTypeUint8 type;
+	uint16 pad0;
+	SVGADXQueryDeviceState state;
+	SVGA3dDXQueryFlags flags;
+	SVGAMobId mobid;
+	uint32 offset;
+} SVGACOTableDXQueryEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineQuery {
+	SVGA3dQueryId queryId;
+	SVGA3dQueryType type;
+	SVGA3dDXQueryFlags flags;
+} SVGA3dCmdDXDefineQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyQuery {
+	SVGA3dQueryId queryId;
+} SVGA3dCmdDXDestroyQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindQuery {
+	SVGA3dQueryId queryId;
+	SVGAMobId mobid;
+} SVGA3dCmdDXBindQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetQueryOffset {
+	SVGA3dQueryId queryId;
+	uint32 mobOffset;
+} SVGA3dCmdDXSetQueryOffset;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBeginQuery {
+	SVGA3dQueryId queryId;
+} SVGA3dCmdDXBeginQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXEndQuery {
+	SVGA3dQueryId queryId;
+} SVGA3dCmdDXEndQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXReadbackQuery {
+	SVGA3dQueryId queryId;
+} SVGA3dCmdDXReadbackQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXMoveQuery {
+	SVGA3dQueryId queryId;
+	SVGAMobId mobid;
+	uint32 mobOffset;
+} SVGA3dCmdDXMoveQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindAllQuery {
+	uint32 cid;
+	SVGAMobId mobid;
+} SVGA3dCmdDXBindAllQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXReadbackAllQuery {
+	uint32 cid;
+} SVGA3dCmdDXReadbackAllQuery;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetPredication {
+	SVGA3dQueryId queryId;
+	uint32 predicateValue;
+} SVGA3dCmdDXSetPredication;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct MKS3dDXSOState {
+	uint32 offset;
+	uint32 intOffset;
+	uint32 vertexCount;
+	uint32 dead;
+} SVGA3dDXSOState;
+#pragma pack(pop)
+
+#define SVGA3D_DX_SO_OFFSET_APPEND ((uint32)~0u)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dSoTarget {
+	SVGA3dSurfaceId sid;
+	uint32 offset;
+	uint32 sizeInBytes;
+} SVGA3dSoTarget;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetSOTargets {
+	uint32 pad0;
+
+} SVGA3dCmdDXSetSOTargets;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dViewport {
+	float x;
+	float y;
+	float width;
+	float height;
+	float minDepth;
+	float maxDepth;
+} SVGA3dViewport;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetViewports {
+	uint32 pad0;
+
+} SVGA3dCmdDXSetViewports;
+#pragma pack(pop)
+
+#define SVGA3D_DX_MAX_VIEWPORTS 16
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetScissorRects {
+	uint32 pad0;
+
+} SVGA3dCmdDXSetScissorRects;
+#pragma pack(pop)
+
+#define SVGA3D_DX_MAX_SCISSORRECTS 16
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXClearRenderTargetView {
+	SVGA3dRenderTargetViewId renderTargetViewId;
+	SVGA3dRGBAFloat rgba;
+} SVGA3dCmdDXClearRenderTargetView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXClearDepthStencilView {
+	uint16 flags;
+	uint16 stencil;
+	SVGA3dDepthStencilViewId depthStencilViewId;
+	float depth;
+} SVGA3dCmdDXClearDepthStencilView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredCopyRegion {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dCopyBox box;
+} SVGA3dCmdDXPredCopyRegion;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredStagingCopyRegion {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dCopyBox box;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+} SVGA3dCmdDXPredStagingCopyRegion;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredCopy {
+	SVGA3dSurfaceId dstSid;
+	SVGA3dSurfaceId srcSid;
+} SVGA3dCmdDXPredCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredConvertRegion {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dBox destBox;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dBox srcBox;
+} SVGA3dCmdDXPredConvertRegion;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredStagingConvertRegion {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dBox destBox;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dBox srcBox;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+} SVGA3dCmdDXPredStagingConvertRegion;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredConvert {
+	SVGA3dSurfaceId dstSid;
+	SVGA3dSurfaceId srcSid;
+} SVGA3dCmdDXPredConvert;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredStagingConvert {
+	SVGA3dSurfaceId dstSid;
+	SVGA3dSurfaceId srcSid;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+} SVGA3dCmdDXPredStagingConvert;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBufferCopy {
+	SVGA3dSurfaceId dest;
+	SVGA3dSurfaceId src;
+	uint32 destX;
+	uint32 srcX;
+	uint32 width;
+} SVGA3dCmdDXBufferCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXStagingBufferCopy {
+	SVGA3dSurfaceId dest;
+	SVGA3dSurfaceId src;
+	uint32 destX;
+	uint32 srcX;
+	uint32 width;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+} SVGA3dCmdDXStagingBufferCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dSurfaceFormat copyFormat;
+} SVGA3dCmdDXResolveCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId dstSid;
+	uint32 dstSubResource;
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dSurfaceFormat copyFormat;
+} SVGA3dCmdDXPredResolveCopy;
+#pragma pack(pop)
 
 typedef uint32 SVGA3dDXPresentBltMode;
-#define SVGADX_PRESENTBLT_LINEAR           (1 << 0)
-#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB   (1 << 1)
+#define SVGADX_PRESENTBLT_LINEAR (1 << 0)
+#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB (1 << 1)
 #define SVGADX_PRESENTBLT_FORCE_SRC_XRBIAS (1 << 2)
-#define SVGADX_PRESENTBLT_MODE_MAX         (1 << 3)
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPresentBlt {
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dSurfaceId dstSid;
-   uint32 destSubResource;
-   SVGA3dBox boxSrc;
-   SVGA3dBox boxDest;
-   SVGA3dDXPresentBltMode mode;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPresentBlt; /* SVGA_3D_CMD_DX_PRESENTBLT*/
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXGenMips {
-   SVGA3dShaderResourceViewId shaderResourceViewId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXGenMips; /* SVGA_3D_CMD_DX_GENMIPS */
-
-/*
- * Update a sub-resource in a guest-backed resource.
- * (Inform the device that the guest-contents have been updated.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXUpdateSubResource {
-   SVGA3dSurfaceId sid;
-   uint32 subResource;
-   SVGA3dBox box;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXUpdateSubResource;   /* SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE */
-
-/*
- * Readback a subresource in a guest-backed resource.
- * (Request the device to flush the dirty contents into the guest.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXReadbackSubResource {
-   SVGA3dSurfaceId sid;
-   uint32 subResource;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXReadbackSubResource;   /* SVGA_3D_CMD_DX_READBACK_SUBRESOURCE */
-
-/*
- * Invalidate an image in a guest-backed surface.
- * (Notify the device that the contents can be lost.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXInvalidateSubResource {
-   SVGA3dSurfaceId sid;
-   uint32 subResource;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXInvalidateSubResource;   /* SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE */
-
-
-/*
- * Raw byte wise transfer from a buffer surface into another surface
- * of the requested box.  Supported if 3d is enabled and SVGA_CAP_DX
- * is set.  This command does not take a context.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXTransferFromBuffer {
-   SVGA3dSurfaceId srcSid;
-   uint32 srcOffset;
-   uint32 srcPitch;
-   uint32 srcSlicePitch;
-   SVGA3dSurfaceId destSid;
-   uint32 destSubResource;
-   SVGA3dBox destBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXTransferFromBuffer;   /* SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER */
-
-
-#define SVGA3D_TRANSFER_TO_BUFFER_READBACK   (1 << 0)
+#define SVGADX_PRESENTBLT_MODE_MAX (1 << 3)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPresentBlt {
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dSurfaceId dstSid;
+	uint32 destSubResource;
+	SVGA3dBox boxSrc;
+	SVGA3dBox boxDest;
+	SVGA3dDXPresentBltMode mode;
+} SVGA3dCmdDXPresentBlt;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXGenMips {
+	SVGA3dShaderResourceViewId shaderResourceViewId;
+} SVGA3dCmdDXGenMips;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXUpdateSubResource {
+	SVGA3dSurfaceId sid;
+	uint32 subResource;
+	SVGA3dBox box;
+} SVGA3dCmdDXUpdateSubResource;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXReadbackSubResource {
+	SVGA3dSurfaceId sid;
+	uint32 subResource;
+} SVGA3dCmdDXReadbackSubResource;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXInvalidateSubResource {
+	SVGA3dSurfaceId sid;
+	uint32 subResource;
+} SVGA3dCmdDXInvalidateSubResource;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXTransferFromBuffer {
+	SVGA3dSurfaceId srcSid;
+	uint32 srcOffset;
+	uint32 srcPitch;
+	uint32 srcSlicePitch;
+	SVGA3dSurfaceId destSid;
+	uint32 destSubResource;
+	SVGA3dBox destBox;
+} SVGA3dCmdDXTransferFromBuffer;
+#pragma pack(pop)
+
+#define SVGA3D_TRANSFER_TO_BUFFER_READBACK (1 << 0)
 #define SVGA3D_TRANSFER_TO_BUFFER_FLAGS_MASK (1 << 0)
 typedef uint32 SVGA3dTransferToBufferFlags;
 
-/*
- * Raw byte wise transfer to a buffer surface from another surface
- * of the requested box.  Supported if SVGA_CAP_DX2 is set.  This
- * command does not take a context.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXTransferToBuffer {
-   SVGA3dSurfaceId srcSid;
-   uint32 srcSubResource;
-   SVGA3dBox srcBox;
-   SVGA3dSurfaceId destSid;
-   uint32 destOffset;
-   uint32 destPitch;
-   uint32 destSlicePitch;
-   SVGA3dTransferToBufferFlags flags;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXTransferToBuffer;   /* SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER */
-
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXTransferToBuffer {
+	SVGA3dSurfaceId srcSid;
+	uint32 srcSubResource;
+	SVGA3dBox srcBox;
+	SVGA3dSurfaceId destSid;
+	uint32 destOffset;
+	uint32 destPitch;
+	uint32 destSlicePitch;
+	SVGA3dTransferToBufferFlags flags;
+} SVGA3dCmdDXTransferToBuffer;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredTransferFromBuffer {
+	SVGA3dSurfaceId srcSid;
+	uint32 srcOffset;
+	uint32 srcPitch;
+	uint32 srcSlicePitch;
+	SVGA3dSurfaceId destSid;
+	uint32 destSubResource;
+	SVGA3dBox destBox;
+} SVGA3dCmdDXPredTransferFromBuffer;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSurfaceCopyAndReadback {
+	SVGA3dSurfaceId srcSid;
+	SVGA3dSurfaceId destSid;
+	SVGA3dCopyBox box;
+} SVGA3dCmdDXSurfaceCopyAndReadback;
+#pragma pack(pop)
 
-/*
- * Raw byte wise transfer from a buffer surface into another surface
- * of the requested box.  Supported if SVGA3D_DEVCAP_DXCONTEXT is set.
- * The context is implied from the command buffer header.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXPredTransferFromBuffer {
-   SVGA3dSurfaceId srcSid;
-   uint32 srcOffset;
-   uint32 srcPitch;
-   uint32 srcSlicePitch;
-   SVGA3dSurfaceId destSid;
-   uint32 destSubResource;
-   SVGA3dBox destBox;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXPredTransferFromBuffer;
-/* SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER */
-
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSurfaceCopyAndReadback {
-   SVGA3dSurfaceId srcSid;
-   SVGA3dSurfaceId destSid;
-   SVGA3dCopyBox box;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSurfaceCopyAndReadback;
-/* SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK */
-
-/*
- * SVGA_DX_HINT_NONE: Does nothing.
- *
- * SVGA_DX_HINT_PREFETCH_OBJECT:
- * SVGA_DX_HINT_PREEVICT_OBJECT:
- *      Consumes a SVGAObjectRef, and hints that the host should consider
- *      fetching/evicting the specified object.
- *
- *      An id of SVGA3D_INVALID_ID can be used if the guest isn't sure
- *      what object was affected.  (For instance, if the guest knows that
- *      it is about to evict a DXShader, but doesn't know precisely which one,
- *      the device can still use this to help limit it's search, or track
- *      how many page-outs have happened.)
- *
- * SVGA_DX_HINT_PREFETCH_COBJECT:
- * SVGA_DX_HINT_PREEVICT_COBJECT:
- *      Same as the above, except they consume an SVGACObjectRef.
- */
 typedef uint32 SVGADXHintId;
-#define SVGA_DX_HINT_NONE              0
-#define SVGA_DX_HINT_PREFETCH_OBJECT   1
-#define SVGA_DX_HINT_PREEVICT_OBJECT   2
-#define SVGA_DX_HINT_PREFETCH_COBJECT  3
-#define SVGA_DX_HINT_PREEVICT_COBJECT  4
-#define SVGA_DX_HINT_MAX               5
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAObjectRef {
-   SVGAOTableType type;
-   uint32 id;
-}
-#include "vmware_pack_end.h"
-SVGAObjectRef;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGACObjectRef {
-   SVGACOTableType type;
-   uint32 cid;
-   uint32 id;
-}
-#include "vmware_pack_end.h"
-SVGACObjectRef;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXHint {
-   SVGADXHintId hintId;
-
-   /*
-    * Followed by variable sized data depending on the hintId.
-    */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXHint;
-/* SVGA_3D_CMD_DX_HINT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBufferUpdate {
-   SVGA3dSurfaceId sid;
-   uint32 x;
-   uint32 width;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBufferUpdate;
-/* SVGA_3D_CMD_DX_BUFFER_UPDATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetConstantBufferOffset {
-   uint32 slot;
-   uint32 offsetInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetConstantBufferOffset;
+#define SVGA_DX_HINT_NONE 0
+#define SVGA_DX_HINT_PREFETCH_OBJECT 1
+#define SVGA_DX_HINT_PREEVICT_OBJECT 2
+#define SVGA_DX_HINT_PREFETCH_COBJECT 3
+#define SVGA_DX_HINT_PREEVICT_COBJECT 4
+#define SVGA_DX_HINT_MAX 5
+
+#pragma pack(push, 1)
+typedef struct SVGAObjectRef {
+	SVGAOTableType type;
+	uint32 id;
+} SVGAObjectRef;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGACObjectRef {
+	SVGACOTableType type;
+	uint32 cid;
+	uint32 id;
+} SVGACObjectRef;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXHint {
+	SVGADXHintId hintId;
+
+} SVGA3dCmdDXHint;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBufferUpdate {
+	SVGA3dSurfaceId sid;
+	uint32 x;
+	uint32 width;
+} SVGA3dCmdDXBufferUpdate;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetConstantBufferOffset {
+	uint32 slot;
+	uint32 offsetInBytes;
+} SVGA3dCmdDXSetConstantBufferOffset;
+#pragma pack(pop)
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetVSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET */
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetPSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET */
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetGSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET */
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetHSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET */
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetDSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET */
 
 typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetCSConstantBufferOffset;
-/* SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET */
 
-
-#define SVGA3D_BUFFEREX_SRV_RAW        (1 << 0)
-#define SVGA3D_BUFFEREX_SRV_FLAGS_MAX  (1 << 1)
+#define SVGA3D_BUFFEREX_SRV_RAW (1 << 0)
+#define SVGA3D_BUFFEREX_SRV_FLAGS_MAX (1 << 1)
 #define SVGA3D_BUFFEREX_SRV_FLAGS_MASK (SVGA3D_BUFFEREX_SRV_FLAGS_MAX - 1)
 typedef uint32 SVGA3dBufferExFlags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   union {
-      struct {
-         uint32 firstElement;
-         uint32 numElements;
-         uint32 pad0;
-         uint32 pad1;
-      } buffer;
-      struct {
-         uint32 mostDetailedMip;
-         uint32 firstArraySlice;
-         uint32 mipLevels;
-         uint32 arraySize;
-      } tex; /* 1d, 2d, 3d, cube */
-      struct {
-         uint32 firstElement;
-         uint32 numElements;
-         SVGA3dBufferExFlags flags;
-         uint32 pad0;
-      } bufferex;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dShaderResourceViewDesc;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   SVGA3dShaderResourceViewDesc desc;
-   uint32 pad;
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXSRViewEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineShaderResourceView {
-   SVGA3dShaderResourceViewId shaderResourceViewId;
-
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-
-   SVGA3dShaderResourceViewDesc desc;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineShaderResourceView;
-/* SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyShaderResourceView {
-   SVGA3dShaderResourceViewId shaderResourceViewId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyShaderResourceView;
-/* SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dRenderTargetViewDesc {
-   union {
-      struct {
-         uint32 firstElement;
-         uint32 numElements;
-         uint32 padding0;
-      } buffer;
-      struct {
-         uint32 mipSlice;
-         uint32 firstArraySlice;
-         uint32 arraySize;
-      } tex;                    /* 1d, 2d, cube */
-      struct {
-         uint32 mipSlice;
-         uint32 firstW;
-         uint32 wSize;
-      } tex3D;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dRenderTargetViewDesc;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   SVGA3dRenderTargetViewDesc desc;
-   uint32 pad[2];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXRTViewEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineRenderTargetView {
-   SVGA3dRenderTargetViewId renderTargetViewId;
-
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-
-   SVGA3dRenderTargetViewDesc desc;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineRenderTargetView;
-/* SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyRenderTargetView {
-   SVGA3dRenderTargetViewId renderTargetViewId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyRenderTargetView;
-/* SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW */
-
-/*
- */
-#define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_DEPTH   0x01
+#pragma pack(push, 1)
+typedef struct {
+	union {
+		struct {
+			uint32 firstElement;
+			uint32 numElements;
+			uint32 pad0;
+			uint32 pad1;
+		} buffer;
+		struct {
+			uint32 mostDetailedMip;
+			uint32 firstArraySlice;
+			uint32 mipLevels;
+			uint32 arraySize;
+		} tex;
+		struct {
+			uint32 firstElement;
+			uint32 numElements;
+			SVGA3dBufferExFlags flags;
+			uint32 pad0;
+		} bufferex;
+	};
+} SVGA3dShaderResourceViewDesc;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	SVGA3dShaderResourceViewDesc desc;
+	uint32 pad;
+} SVGACOTableDXSRViewEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineShaderResourceView {
+	SVGA3dShaderResourceViewId shaderResourceViewId;
+
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+
+	SVGA3dShaderResourceViewDesc desc;
+} SVGA3dCmdDXDefineShaderResourceView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyShaderResourceView {
+	SVGA3dShaderResourceViewId shaderResourceViewId;
+} SVGA3dCmdDXDestroyShaderResourceView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dRenderTargetViewDesc {
+	union {
+		struct {
+			uint32 firstElement;
+			uint32 numElements;
+			uint32 padding0;
+		} buffer;
+		struct {
+			uint32 mipSlice;
+			uint32 firstArraySlice;
+			uint32 arraySize;
+		} tex;
+		struct {
+			uint32 mipSlice;
+			uint32 firstW;
+			uint32 wSize;
+		} tex3D;
+	};
+} SVGA3dRenderTargetViewDesc;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	SVGA3dRenderTargetViewDesc desc;
+	uint32 pad[2];
+} SVGACOTableDXRTViewEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineRenderTargetView {
+	SVGA3dRenderTargetViewId renderTargetViewId;
+
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+
+	SVGA3dRenderTargetViewDesc desc;
+} SVGA3dCmdDXDefineRenderTargetView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyRenderTargetView {
+	SVGA3dRenderTargetViewId renderTargetViewId;
+} SVGA3dCmdDXDestroyRenderTargetView;
+#pragma pack(pop)
+
+#define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_DEPTH 0x01
 #define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_STENCIL 0x02
-#define SVGA3D_DXDSVIEW_CREATE_FLAG_MASK         0x03
+#define SVGA3D_DXDSVIEW_CREATE_FLAG_MASK 0x03
 typedef uint8 SVGA3DCreateDSViewFlags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   uint32 mipSlice;
-   uint32 firstArraySlice;
-   uint32 arraySize;
-   SVGA3DCreateDSViewFlags flags;
-   uint8 pad0;
-   uint16 pad1;
-   uint32 pad2;
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXDSViewEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineDepthStencilView {
-   SVGA3dDepthStencilViewId depthStencilViewId;
-
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   uint32 mipSlice;
-   uint32 firstArraySlice;
-   uint32 arraySize;
-   SVGA3DCreateDSViewFlags flags;
-   uint8 pad0;
-   uint16 pad1;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineDepthStencilView;
-/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW */
-
-/*
- * Version 2 needed in order to start validating and using the flags
- * field.  Unfortunately the device wasn't validating or using the
- * flags field and the driver wasn't initializing it in shipped code,
- * so a new version of the command is needed to allow that code to
- * continue to work.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineDepthStencilView_v2 {
-   SVGA3dDepthStencilViewId depthStencilViewId;
-
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   uint32 mipSlice;
-   uint32 firstArraySlice;
-   uint32 arraySize;
-   SVGA3DCreateDSViewFlags flags;
-   uint8 pad0;
-   uint16 pad1;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineDepthStencilView_v2;
-/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2 */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyDepthStencilView {
-   SVGA3dDepthStencilViewId depthStencilViewId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyDepthStencilView;
-/* SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW */
-
-
-#define SVGA3D_UABUFFER_RAW     (1 << 0)
-#define SVGA3D_UABUFFER_APPEND  (1 << 1)
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	uint32 mipSlice;
+	uint32 firstArraySlice;
+	uint32 arraySize;
+	SVGA3DCreateDSViewFlags flags;
+	uint8 pad0;
+	uint16 pad1;
+	uint32 pad2;
+} SVGACOTableDXDSViewEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineDepthStencilView {
+	SVGA3dDepthStencilViewId depthStencilViewId;
+
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	uint32 mipSlice;
+	uint32 firstArraySlice;
+	uint32 arraySize;
+	SVGA3DCreateDSViewFlags flags;
+	uint8 pad0;
+	uint16 pad1;
+} SVGA3dCmdDXDefineDepthStencilView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineDepthStencilView_v2 {
+	SVGA3dDepthStencilViewId depthStencilViewId;
+
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	uint32 mipSlice;
+	uint32 firstArraySlice;
+	uint32 arraySize;
+	SVGA3DCreateDSViewFlags flags;
+	uint8 pad0;
+	uint16 pad1;
+} SVGA3dCmdDXDefineDepthStencilView_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyDepthStencilView {
+	SVGA3dDepthStencilViewId depthStencilViewId;
+} SVGA3dCmdDXDestroyDepthStencilView;
+#pragma pack(pop)
+
+#define SVGA3D_UABUFFER_RAW (1 << 0)
+#define SVGA3D_UABUFFER_APPEND (1 << 1)
 #define SVGA3D_UABUFFER_COUNTER (1 << 2)
 typedef uint32 SVGA3dUABufferFlags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   union {
-      struct {
-         uint32 firstElement;
-         uint32 numElements;
-         SVGA3dUABufferFlags flags;
-         uint32 padding0;
-         uint32 padding1;
-      } buffer;
-      struct {
-         uint32 mipSlice;
-         uint32 firstArraySlice;
-         uint32 arraySize;
-         uint32 padding0;
-         uint32 padding1;
-      } tex;  /* 1d, 2d */
-      struct {
-         uint32 mipSlice;
-         uint32 firstW;
-         uint32 wSize;
-         uint32 padding0;
-         uint32 padding1;
-      } tex3D;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dUAViewDesc;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-   SVGA3dUAViewDesc desc;
-   uint32 structureCount;
-   uint32 pad[7];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXUAViewEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineUAView {
-   SVGA3dUAViewId uaViewId;
-
-   SVGA3dSurfaceId sid;
-   SVGA3dSurfaceFormat format;
-   SVGA3dResourceType resourceDimension;
-
-   SVGA3dUAViewDesc desc;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineUAView;
-/* SVGA_3D_CMD_DX_DEFINE_UA_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyUAView {
-   SVGA3dUAViewId uaViewId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyUAView;
-/* SVGA_3D_CMD_DX_DESTROY_UA_VIEW */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXClearUAViewUint {
-   SVGA3dUAViewId uaViewId;
-   SVGA3dRGBAUint32 value;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXClearUAViewUint;
-/* SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXClearUAViewFloat {
-   SVGA3dUAViewId uaViewId;
-   SVGA3dRGBAFloat value;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXClearUAViewFloat;
-/* SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXCopyStructureCount {
-   SVGA3dUAViewId srcUAViewId;
-   SVGA3dSurfaceId destSid;
-   uint32 destByteOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXCopyStructureCount;
-/* SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetStructureCount {
-   SVGA3dUAViewId uaViewId;
-   uint32 structureCount;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetStructureCount;
-/* SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetUAViews {
-   uint32 uavSpliceIndex;
-   /* Followed by a variable number of SVGA3dUAViewId's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetUAViews; /* SVGA_3D_CMD_DX_SET_UA_VIEWS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetCSUAViews {
-   uint32 startIndex;
-   /* Followed by a variable number of SVGA3dUAViewId's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetCSUAViews; /* SVGA_3D_CMD_DX_SET_CS_UA_VIEWS */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dInputElementDesc {
-   uint32 inputSlot;
-   uint32 alignedByteOffset;
-   SVGA3dSurfaceFormat format;
-   SVGA3dInputClassification inputSlotClass;
-   uint32 instanceDataStepRate;
-   uint32 inputRegister;
-}
-#include "vmware_pack_end.h"
-SVGA3dInputElementDesc;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 elid;
-   uint32 numDescs;
-   SVGA3dInputElementDesc descs[32];
-   uint32 pad[62];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXElementLayoutEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineElementLayout {
-   SVGA3dElementLayoutId elementLayoutId;
-   /* Followed by a variable number of SVGA3dInputElementDesc's. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineElementLayout;
-/* SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyElementLayout {
-   SVGA3dElementLayoutId elementLayoutId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyElementLayout;
-/* SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT */
-
+#pragma pack(push, 1)
+typedef struct {
+	union {
+		struct {
+			uint32 firstElement;
+			uint32 numElements;
+			SVGA3dUABufferFlags flags;
+			uint32 padding0;
+			uint32 padding1;
+		} buffer;
+		struct {
+			uint32 mipSlice;
+			uint32 firstArraySlice;
+			uint32 arraySize;
+			uint32 padding0;
+			uint32 padding1;
+		} tex;
+		struct {
+			uint32 mipSlice;
+			uint32 firstW;
+			uint32 wSize;
+			uint32 padding0;
+			uint32 padding1;
+		} tex3D;
+	};
+} SVGA3dUAViewDesc;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+	SVGA3dUAViewDesc desc;
+	uint32 structureCount;
+	uint32 pad[7];
+} SVGACOTableDXUAViewEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineUAView {
+	SVGA3dUAViewId uaViewId;
+
+	SVGA3dSurfaceId sid;
+	SVGA3dSurfaceFormat format;
+	SVGA3dResourceType resourceDimension;
+
+	SVGA3dUAViewDesc desc;
+} SVGA3dCmdDXDefineUAView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyUAView {
+	SVGA3dUAViewId uaViewId;
+} SVGA3dCmdDXDestroyUAView;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXClearUAViewUint {
+	SVGA3dUAViewId uaViewId;
+	SVGA3dRGBAUint32 value;
+} SVGA3dCmdDXClearUAViewUint;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXClearUAViewFloat {
+	SVGA3dUAViewId uaViewId;
+	SVGA3dRGBAFloat value;
+} SVGA3dCmdDXClearUAViewFloat;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXCopyStructureCount {
+	SVGA3dUAViewId srcUAViewId;
+	SVGA3dSurfaceId destSid;
+	uint32 destByteOffset;
+} SVGA3dCmdDXCopyStructureCount;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetStructureCount {
+	SVGA3dUAViewId uaViewId;
+	uint32 structureCount;
+} SVGA3dCmdDXSetStructureCount;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetUAViews {
+	uint32 uavSpliceIndex;
+
+} SVGA3dCmdDXSetUAViews;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetCSUAViews {
+	uint32 startIndex;
+
+} SVGA3dCmdDXSetCSUAViews;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dInputElementDesc {
+	uint32 inputSlot;
+	uint32 alignedByteOffset;
+	SVGA3dSurfaceFormat format;
+	SVGA3dInputClassification inputSlotClass;
+	uint32 instanceDataStepRate;
+	uint32 inputRegister;
+} SVGA3dInputElementDesc;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 elid;
+	uint32 numDescs;
+	SVGA3dInputElementDesc descs[32];
+	uint32 pad[62];
+} SVGACOTableDXElementLayoutEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineElementLayout {
+	SVGA3dElementLayoutId elementLayoutId;
+
+} SVGA3dCmdDXDefineElementLayout;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyElementLayout {
+	SVGA3dElementLayoutId elementLayoutId;
+} SVGA3dCmdDXDestroyElementLayout;
+#pragma pack(pop)
 
 #define SVGA3D_DX_MAX_RENDER_TARGETS 8
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dDXBlendStatePerRT {
-      uint8 blendEnable;
-      uint8 srcBlend;
-      uint8 destBlend;
-      uint8 blendOp;
-      uint8 srcBlendAlpha;
-      uint8 destBlendAlpha;
-      uint8 blendOpAlpha;
-      SVGA3dColorWriteEnable renderTargetWriteMask;
-      uint8 logicOpEnable;
-      uint8 logicOp;
-      uint16 pad0;
-}
-#include "vmware_pack_end.h"
-SVGA3dDXBlendStatePerRT;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint8 alphaToCoverageEnable;
-   uint8 independentBlendEnable;
-   uint16 pad0;
-   SVGA3dDXBlendStatePerRT perRT[SVGA3D_MAX_RENDER_TARGETS];
-   uint32 pad1[7];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXBlendStateEntry;
-
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineBlendState {
-   SVGA3dBlendStateId blendId;
-   uint8 alphaToCoverageEnable;
-   uint8 independentBlendEnable;
-   uint16 pad0;
-   SVGA3dDXBlendStatePerRT perRT[SVGA3D_MAX_RENDER_TARGETS];
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineBlendState; /* SVGA_3D_CMD_DX_DEFINE_BLEND_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyBlendState {
-   SVGA3dBlendStateId blendId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyBlendState; /* SVGA_3D_CMD_DX_DESTROY_BLEND_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint8 depthEnable;
-   SVGA3dDepthWriteMask depthWriteMask;
-   SVGA3dComparisonFunc depthFunc;
-   uint8 stencilEnable;
-   uint8 frontEnable;
-   uint8 backEnable;
-   uint8 stencilReadMask;
-   uint8 stencilWriteMask;
-
-   uint8 frontStencilFailOp;
-   uint8 frontStencilDepthFailOp;
-   uint8 frontStencilPassOp;
-   SVGA3dComparisonFunc frontStencilFunc;
-
-   uint8 backStencilFailOp;
-   uint8 backStencilDepthFailOp;
-   uint8 backStencilPassOp;
-   SVGA3dComparisonFunc backStencilFunc;
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXDepthStencilEntry;
-
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineDepthStencilState {
-   SVGA3dDepthStencilStateId depthStencilId;
-
-   uint8 depthEnable;
-   SVGA3dDepthWriteMask depthWriteMask;
-   SVGA3dComparisonFunc depthFunc;
-   uint8 stencilEnable;
-   uint8 frontEnable;
-   uint8 backEnable;
-   uint8 stencilReadMask;
-   uint8 stencilWriteMask;
-
-   uint8 frontStencilFailOp;
-   uint8 frontStencilDepthFailOp;
-   uint8 frontStencilPassOp;
-   SVGA3dComparisonFunc frontStencilFunc;
-
-   uint8 backStencilFailOp;
-   uint8 backStencilDepthFailOp;
-   uint8 backStencilPassOp;
-   SVGA3dComparisonFunc backStencilFunc;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineDepthStencilState;
-/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyDepthStencilState {
-   SVGA3dDepthStencilStateId depthStencilId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyDepthStencilState;
-/* SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint8 fillMode;
-   SVGA3dCullMode cullMode;
-   uint8 frontCounterClockwise;
-   uint8 provokingVertexLast;
-   int32 depthBias;
-   float depthBiasClamp;
-   float slopeScaledDepthBias;
-   uint8 depthClipEnable;
-   uint8 scissorEnable;
-   SVGA3dMultisampleRastEnable multisampleEnable;
-   uint8 antialiasedLineEnable;
-   float lineWidth;
-   uint8 lineStippleEnable;
-   uint8 lineStippleFactor;
-   uint16 lineStipplePattern;
-   uint8 forcedSampleCount;
-   uint8 mustBeZero[3];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXRasterizerStateEntry;
-
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineRasterizerState {
-   SVGA3dRasterizerStateId rasterizerId;
-
-   uint8 fillMode;
-   SVGA3dCullMode cullMode;
-   uint8 frontCounterClockwise;
-   uint8 provokingVertexLast;
-   int32 depthBias;
-   float depthBiasClamp;
-   float slopeScaledDepthBias;
-   uint8 depthClipEnable;
-   uint8 scissorEnable;
-   SVGA3dMultisampleRastEnable multisampleEnable;
-   uint8 antialiasedLineEnable;
-   float lineWidth;
-   uint8 lineStippleEnable;
-   uint8 lineStippleFactor;
-   uint16 lineStipplePattern;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineRasterizerState;
-/* SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyRasterizerState {
-   SVGA3dRasterizerStateId rasterizerId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyRasterizerState;
-/* SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGA3dFilter filter;
-   uint8 addressU;
-   uint8 addressV;
-   uint8 addressW;
-   uint8 pad0;
-   float mipLODBias;
-   uint8 maxAnisotropy;
-   SVGA3dComparisonFunc comparisonFunc;
-   uint16 pad1;
-   SVGA3dRGBAFloat borderColor;
-   float minLOD;
-   float maxLOD;
-   uint32 pad2[6];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXSamplerEntry;
-
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineSamplerState {
-   SVGA3dSamplerId samplerId;
-   SVGA3dFilter filter;
-   uint8 addressU;
-   uint8 addressV;
-   uint8 addressW;
-   uint8 pad0;
-   float mipLODBias;
-   uint8 maxAnisotropy;
-   SVGA3dComparisonFunc comparisonFunc;
-   uint16 pad1;
-   SVGA3dRGBAFloat borderColor;
-   float minLOD;
-   float maxLOD;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineSamplerState; /* SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroySamplerState {
-   SVGA3dSamplerId samplerId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroySamplerState; /* SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE */
-
-
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_UNDEFINED                          0
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_POSITION                           1
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_CLIP_DISTANCE                      2
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_CULL_DISTANCE                      3
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_RENDER_TARGET_ARRAY_INDEX          4
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_VIEWPORT_ARRAY_INDEX               5
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_VERTEX_ID                          6
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_PRIMITIVE_ID                       7
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_INSTANCE_ID                        8
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_IS_FRONT_FACE                      9
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_SAMPLE_INDEX                       10
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_0_EDGE_TESSFACTOR  11
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_0_EDGE_TESSFACTOR  12
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_1_EDGE_TESSFACTOR  13
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_1_EDGE_TESSFACTOR  14
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_INSIDE_TESSFACTOR     15
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_INSIDE_TESSFACTOR     16
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_U_EQ_0_EDGE_TESSFACTOR   17
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_V_EQ_0_EDGE_TESSFACTOR   18
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_W_EQ_0_EDGE_TESSFACTOR   19
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_INSIDE_TESSFACTOR        20
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DETAIL_TESSFACTOR       21
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DENSITY_TESSFACTOR      22
-#define SVGADX_SIGNATURE_SEMANTIC_NAME_MAX                                23
+#pragma pack(push, 1)
+typedef struct SVGA3dDXBlendStatePerRT {
+	uint8 blendEnable;
+	uint8 srcBlend;
+	uint8 destBlend;
+	uint8 blendOp;
+	uint8 srcBlendAlpha;
+	uint8 destBlendAlpha;
+	uint8 blendOpAlpha;
+	SVGA3dColorWriteEnable renderTargetWriteMask;
+	uint8 logicOpEnable;
+	uint8 logicOp;
+	uint16 pad0;
+} SVGA3dDXBlendStatePerRT;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint8 alphaToCoverageEnable;
+	uint8 independentBlendEnable;
+	uint16 pad0;
+	SVGA3dDXBlendStatePerRT perRT[SVGA3D_DX_MAX_RENDER_TARGETS];
+	uint32 pad1[7];
+} SVGACOTableDXBlendStateEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineBlendState {
+	SVGA3dBlendStateId blendId;
+	uint8 alphaToCoverageEnable;
+	uint8 independentBlendEnable;
+	uint16 pad0;
+	SVGA3dDXBlendStatePerRT perRT[SVGA3D_DX_MAX_RENDER_TARGETS];
+} SVGA3dCmdDXDefineBlendState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyBlendState {
+	SVGA3dBlendStateId blendId;
+} SVGA3dCmdDXDestroyBlendState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint8 depthEnable;
+	SVGA3dDepthWriteMask depthWriteMask;
+	SVGA3dComparisonFunc depthFunc;
+	uint8 stencilEnable;
+	uint8 frontEnable;
+	uint8 backEnable;
+	uint8 stencilReadMask;
+	uint8 stencilWriteMask;
+
+	uint8 frontStencilFailOp;
+	uint8 frontStencilDepthFailOp;
+	uint8 frontStencilPassOp;
+	SVGA3dComparisonFunc frontStencilFunc;
+
+	uint8 backStencilFailOp;
+	uint8 backStencilDepthFailOp;
+	uint8 backStencilPassOp;
+	SVGA3dComparisonFunc backStencilFunc;
+} SVGACOTableDXDepthStencilEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineDepthStencilState {
+	SVGA3dDepthStencilStateId depthStencilId;
+
+	uint8 depthEnable;
+	SVGA3dDepthWriteMask depthWriteMask;
+	SVGA3dComparisonFunc depthFunc;
+	uint8 stencilEnable;
+	uint8 frontEnable;
+	uint8 backEnable;
+	uint8 stencilReadMask;
+	uint8 stencilWriteMask;
+
+	uint8 frontStencilFailOp;
+	uint8 frontStencilDepthFailOp;
+	uint8 frontStencilPassOp;
+	SVGA3dComparisonFunc frontStencilFunc;
+
+	uint8 backStencilFailOp;
+	uint8 backStencilDepthFailOp;
+	uint8 backStencilPassOp;
+	SVGA3dComparisonFunc backStencilFunc;
+} SVGA3dCmdDXDefineDepthStencilState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyDepthStencilState {
+	SVGA3dDepthStencilStateId depthStencilId;
+} SVGA3dCmdDXDestroyDepthStencilState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint8 fillMode;
+	SVGA3dCullMode cullMode;
+	uint8 frontCounterClockwise;
+	uint8 provokingVertexLast;
+	int32 depthBias;
+	float depthBiasClamp;
+	float slopeScaledDepthBias;
+	uint8 depthClipEnable;
+	uint8 scissorEnable;
+	SVGA3dMultisampleRastEnable multisampleEnable;
+	uint8 antialiasedLineEnable;
+	float lineWidth;
+	uint8 lineStippleEnable;
+	uint8 lineStippleFactor;
+	uint16 lineStipplePattern;
+	uint8 forcedSampleCount;
+	uint8 mustBeZero[3];
+} SVGACOTableDXRasterizerStateEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineRasterizerState {
+	SVGA3dRasterizerStateId rasterizerId;
+
+	uint8 fillMode;
+	SVGA3dCullMode cullMode;
+	uint8 frontCounterClockwise;
+	uint8 provokingVertexLast;
+	int32 depthBias;
+	float depthBiasClamp;
+	float slopeScaledDepthBias;
+	uint8 depthClipEnable;
+	uint8 scissorEnable;
+	SVGA3dMultisampleRastEnable multisampleEnable;
+	uint8 antialiasedLineEnable;
+	float lineWidth;
+	uint8 lineStippleEnable;
+	uint8 lineStippleFactor;
+	uint16 lineStipplePattern;
+} SVGA3dCmdDXDefineRasterizerState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineRasterizerState_v2 {
+	SVGA3dRasterizerStateId rasterizerId;
+
+	uint8 fillMode;
+	SVGA3dCullMode cullMode;
+	uint8 frontCounterClockwise;
+	uint8 provokingVertexLast;
+	int32 depthBias;
+	float depthBiasClamp;
+	float slopeScaledDepthBias;
+	uint8 depthClipEnable;
+	uint8 scissorEnable;
+	SVGA3dMultisampleRastEnable multisampleEnable;
+	uint8 antialiasedLineEnable;
+	float lineWidth;
+	uint8 lineStippleEnable;
+	uint8 lineStippleFactor;
+	uint16 lineStipplePattern;
+	uint32 forcedSampleCount;
+} SVGA3dCmdDXDefineRasterizerState_v2;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyRasterizerState {
+	SVGA3dRasterizerStateId rasterizerId;
+} SVGA3dCmdDXDestroyRasterizerState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGA3dFilter filter;
+	uint8 addressU;
+	uint8 addressV;
+	uint8 addressW;
+	uint8 pad0;
+	float mipLODBias;
+	uint8 maxAnisotropy;
+	SVGA3dComparisonFunc comparisonFunc;
+	uint16 pad1;
+	SVGA3dRGBAFloat borderColor;
+	float minLOD;
+	float maxLOD;
+	uint32 pad2[6];
+} SVGACOTableDXSamplerEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineSamplerState {
+	SVGA3dSamplerId samplerId;
+	SVGA3dFilter filter;
+	uint8 addressU;
+	uint8 addressV;
+	uint8 addressW;
+	uint8 pad0;
+	float mipLODBias;
+	uint8 maxAnisotropy;
+	SVGA3dComparisonFunc comparisonFunc;
+	uint16 pad1;
+	SVGA3dRGBAFloat borderColor;
+	float minLOD;
+	float maxLOD;
+} SVGA3dCmdDXDefineSamplerState;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroySamplerState {
+	SVGA3dSamplerId samplerId;
+} SVGA3dCmdDXDestroySamplerState;
+#pragma pack(pop)
+
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_UNDEFINED 0
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_POSITION 1
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_CLIP_DISTANCE 2
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_CULL_DISTANCE 3
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_RENDER_TARGET_ARRAY_INDEX 4
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_VIEWPORT_ARRAY_INDEX 5
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_VERTEX_ID 6
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_PRIMITIVE_ID 7
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_INSTANCE_ID 8
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_IS_FRONT_FACE 9
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_SAMPLE_INDEX 10
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_0_EDGE_TESSFACTOR 11
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_0_EDGE_TESSFACTOR 12
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_1_EDGE_TESSFACTOR 13
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_1_EDGE_TESSFACTOR 14
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_INSIDE_TESSFACTOR 15
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_INSIDE_TESSFACTOR 16
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_U_EQ_0_EDGE_TESSFACTOR 17
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_V_EQ_0_EDGE_TESSFACTOR 18
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_W_EQ_0_EDGE_TESSFACTOR 19
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_INSIDE_TESSFACTOR 20
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DETAIL_TESSFACTOR 21
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DENSITY_TESSFACTOR 22
+#define SVGADX_SIGNATURE_SEMANTIC_NAME_MAX 23
 typedef uint32 SVGA3dDXSignatureSemanticName;
 
 #define SVGADX_SIGNATURE_REGISTER_COMPONENT_UNKNOWN 0
@@ -1670,398 +1394,331 @@ typedef uint32 SVGA3dDXSignatureRegisterComponentType;
 #define SVGADX_SIGNATURE_MIN_PRECISION_DEFAULT 0
 typedef uint32 SVGA3dDXSignatureMinPrecision;
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dDXSignatureEntry {
-   uint32 registerIndex;
-   SVGA3dDXSignatureSemanticName semanticName;
-   uint32 mask; /* Lower 4 bits represent X, Y, Z, W channels */
-   SVGA3dDXSignatureRegisterComponentType componentType;
-   SVGA3dDXSignatureMinPrecision minPrecision;
-}
-#include "vmware_pack_end.h"
-SVGA3dDXShaderSignatureEntry;
+#pragma pack(push, 1)
+typedef struct SVGA3dDXSignatureEntry {
+	uint32 registerIndex;
+	SVGA3dDXSignatureSemanticName semanticName;
+	uint32 mask;
+	SVGA3dDXSignatureRegisterComponentType componentType;
+	SVGA3dDXSignatureMinPrecision minPrecision;
+} SVGA3dDXShaderSignatureEntry;
+#pragma pack(pop)
 
 #define SVGADX_SIGNATURE_HEADER_VERSION_0 0x08a92d12
 
-/*
- * The SVGA3dDXSignatureHeader structure is added after the shader
- * body in the mob that is bound to the shader.  It is followed by the
- * specified number of SVGA3dDXSignatureEntry structures for each of
- * the three types of signatures in the order (input, output, patch
- * constants).
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dDXSignatureHeader {
-   uint32 headerVersion;
-   uint32 numInputSignatures;
-   uint32 numOutputSignatures;
-   uint32 numPatchConstantSignatures;
-}
-#include "vmware_pack_end.h"
-SVGA3dDXShaderSignatureHeader;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineShader {
-   SVGA3dShaderId shaderId;
-   SVGA3dShaderType type;
-   uint32 sizeInBytes; /* Number of bytes of shader text. */
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineShader; /* SVGA_3D_CMD_DX_DEFINE_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGACOTableDXShaderEntry {
-   SVGA3dShaderType type;
-   uint32 sizeInBytes;
-   uint32 offsetInBytes;
-   SVGAMobId mobid;
-   uint32 pad[4];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXShaderEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyShader {
-   SVGA3dShaderId shaderId;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyShader; /* SVGA_3D_CMD_DX_DESTROY_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindShader {
-   uint32 cid;
-   uint32 shid;
-   SVGAMobId mobid;
-   uint32 offsetInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindShader;   /* SVGA_3D_CMD_DX_BIND_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindAllShader {
-   uint32 cid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindAllShader;   /* SVGA_3D_CMD_DX_BIND_ALL_SHADER */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXCondBindAllShader {
-   uint32 cid;
-   SVGAMobId testMobid;
-   SVGAMobId mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXCondBindAllShader;   /* SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER */
+#pragma pack(push, 1)
+typedef struct SVGA3dDXSignatureHeader {
+	uint32 headerVersion;
+	uint32 numInputSignatures;
+	uint32 numOutputSignatures;
+	uint32 numPatchConstantSignatures;
+} SVGA3dDXShaderSignatureHeader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineShader {
+	SVGA3dShaderId shaderId;
+	SVGA3dShaderType type;
+	uint32 sizeInBytes;
+} SVGA3dCmdDXDefineShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGACOTableDXShaderEntry {
+	SVGA3dShaderType type;
+	uint32 sizeInBytes;
+	uint32 offsetInBytes;
+	SVGAMobId mobid;
+	uint32 pad[4];
+} SVGACOTableDXShaderEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyShader {
+	SVGA3dShaderId shaderId;
+} SVGA3dCmdDXDestroyShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindShader {
+	uint32 cid;
+	uint32 shid;
+	SVGAMobId mobid;
+	uint32 offsetInBytes;
+} SVGA3dCmdDXBindShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindAllShader {
+	uint32 cid;
+	SVGAMobId mobid;
+} SVGA3dCmdDXBindAllShader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXCondBindAllShader {
+	uint32 cid;
+	SVGAMobId testMobid;
+	SVGAMobId mobid;
+} SVGA3dCmdDXCondBindAllShader;
+#pragma pack(pop)
 
-/*
- * The maximum number of streamout decl's in each streamout entry.
- */
 #define SVGA3D_MAX_DX10_STREAMOUT_DECLS 64
 #define SVGA3D_MAX_STREAMOUT_DECLS 512
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dStreamOutputDeclarationEntry {
-   uint32 outputSlot;
-   uint32 registerIndex;
-   uint8  registerMask;
-   uint8  pad0;
-   uint16 pad1;
-   uint32 stream;
-}
-#include "vmware_pack_end.h"
-SVGA3dStreamOutputDeclarationEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAOTableStreamOutputEntry {
-   uint32 numOutputStreamEntries;
-   SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS];
-   uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
-   uint32 rasterizedStream;
-   uint32 numOutputStreamStrides;
-   uint32 mobid;
-   uint32 offsetInBytes;
-   uint8 usesMob;
-   uint8 pad0;
-   uint16 pad1;
-   uint32 pad2[246];
-}
-#include "vmware_pack_end.h"
-SVGACOTableDXStreamOutputEntry;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineStreamOutput {
-   SVGA3dStreamOutputId soid;
-   uint32 numOutputStreamEntries;
-   SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS];
-   uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
-   uint32 rasterizedStream;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineStreamOutput; /* SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT */
-
-/*
- * Version 2 needed in order to start validating and using the
- * rasterizedStream field.  Unfortunately the device wasn't validating
- * or using this field and the driver wasn't initializing it in shipped
- * code, so a new version of the command is needed to allow that code
- * to continue to work.  Also added new numOutputStreamStrides field.
- */
+#pragma pack(push, 1)
+typedef struct SVGA3dStreamOutputDeclarationEntry {
+	uint32 outputSlot;
+	uint32 registerIndex;
+	uint8 registerMask;
+	uint8 pad0;
+	uint16 pad1;
+	uint32 stream;
+} SVGA3dStreamOutputDeclarationEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGAOTableStreamOutputEntry {
+	uint32 numOutputStreamEntries;
+	SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS];
+	uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
+	uint32 rasterizedStream;
+	uint32 numOutputStreamStrides;
+	uint32 mobid;
+	uint32 offsetInBytes;
+	uint8 usesMob;
+	uint8 pad0;
+	uint16 pad1;
+	uint32 pad2[246];
+} SVGACOTableDXStreamOutputEntry;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineStreamOutput {
+	SVGA3dStreamOutputId soid;
+	uint32 numOutputStreamEntries;
+	SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS];
+	uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
+	uint32 rasterizedStream;
+} SVGA3dCmdDXDefineStreamOutput;
+#pragma pack(pop)
 
 #define SVGA3D_DX_SO_NO_RASTERIZED_STREAM 0xFFFFFFFF
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDefineStreamOutputWithMob {
-   SVGA3dStreamOutputId soid;
-   uint32 numOutputStreamEntries;
-   uint32 numOutputStreamStrides;
-   uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
-   uint32 rasterizedStream;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDefineStreamOutputWithMob;
-/* SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXBindStreamOutput {
-   SVGA3dStreamOutputId soid;
-   uint32 mobid;
-   uint32 offsetInBytes;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXBindStreamOutput; /* SVGA_3D_CMD_DX_BIND_STREAMOUTPUT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXDestroyStreamOutput {
-   SVGA3dStreamOutputId soid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXDestroyStreamOutput; /* SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetStreamOutput {
-   SVGA3dStreamOutputId soid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetStreamOutput; /* SVGA_3D_CMD_DX_SET_STREAMOUTPUT */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetMinLOD {
-   SVGA3dSurfaceId sid;
-   float minLOD;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetMinLOD; /* SVGA_3D_CMD_DX_SET_MIN_LOD */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 value;
-   uint32 mobId;
-   uint32 mobOffset;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXMobFence64;  /* SVGA_3D_CMD_DX_MOB_FENCE_64 */
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDefineStreamOutputWithMob {
+	SVGA3dStreamOutputId soid;
+	uint32 numOutputStreamEntries;
+	uint32 numOutputStreamStrides;
+	uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS];
+	uint32 rasterizedStream;
+} SVGA3dCmdDXDefineStreamOutputWithMob;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXBindStreamOutput {
+	SVGA3dStreamOutputId soid;
+	uint32 mobid;
+	uint32 offsetInBytes;
+	uint32 sizeInBytes;
+} SVGA3dCmdDXBindStreamOutput;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXDestroyStreamOutput {
+	SVGA3dStreamOutputId soid;
+} SVGA3dCmdDXDestroyStreamOutput;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetStreamOutput {
+	SVGA3dStreamOutputId soid;
+} SVGA3dCmdDXSetStreamOutput;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetMinLOD {
+	SVGA3dSurfaceId sid;
+	float minLOD;
+} SVGA3dCmdDXSetMinLOD;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 value;
+	uint32 mobId;
+	uint32 mobOffset;
+} SVGA3dCmdDXMobFence64;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXSetCOTable {
+	uint32 cid;
+	uint32 mobid;
+	SVGACOTableType type;
+	uint32 validSizeInBytes;
+} SVGA3dCmdDXSetCOTable;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXGrowCOTable {
+	uint32 cid;
+	uint32 mobid;
+	SVGACOTableType type;
+	uint32 validSizeInBytes;
+} SVGA3dCmdDXGrowCOTable;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXReadbackCOTable {
+	uint32 cid;
+	SVGACOTableType type;
+} SVGA3dCmdDXReadbackCOTable;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXCopyCOTableIntoMob {
+	uint32 cid;
+	SVGACOTableType type;
+	uint32 mobid;
+} SVGA3dCmdDXCopyCOTableIntoMob;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXPredStagingCopy {
+	SVGA3dSurfaceId dstSid;
+	SVGA3dSurfaceId srcSid;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+
+} SVGA3dCmdDXPredStagingCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCmdDXStagingCopy {
+	SVGA3dSurfaceId dstSid;
+	SVGA3dSurfaceId srcSid;
+	uint8 readback;
+	uint8 unsynchronized;
+	uint8 mustBeZero[2];
+
+} SVGA3dCmdDXStagingCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCOTableData {
+	uint32 mobid;
+} SVGA3dCOTableData;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dBufferBinding {
+	uint32 bufferId;
+	uint32 stride;
+	uint32 offset;
+} SVGA3dBufferBinding;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dConstantBufferBinding {
+	uint32 sid;
+	uint32 offsetInBytes;
+	uint32 sizeInBytes;
+} SVGA3dConstantBufferBinding;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGADXInputAssemblyMobFormat {
+	uint32 layoutId;
+	SVGA3dBufferBinding vertexBuffers[SVGA3D_DX_MAX_VERTEXBUFFERS];
+	uint32 indexBufferSid;
+	uint32 pad;
+	uint32 indexBufferOffset;
+	uint32 indexBufferFormat;
+	uint32 topology;
+} SVGADXInputAssemblyMobFormat;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGADXContextMobFormat {
+	SVGADXInputAssemblyMobFormat inputAssembly;
+
+	struct {
+		uint32 blendStateId;
+		uint32 blendFactor[4];
+		uint32 sampleMask;
+		uint32 depthStencilStateId;
+		uint32 stencilRef;
+		uint32 rasterizerStateId;
+		uint32 depthStencilViewId;
+		uint32 renderTargetViewIds[SVGA3D_DX_MAX_RENDER_TARGETS];
+	} renderState;
+
+	uint32 pad0[8];
+
+	struct {
+		uint32 targets[SVGA3D_DX_MAX_SOTARGETS];
+		uint32 soid;
+	} streamOut;
+
+	uint32 pad1[10];
+
+	uint32 uavSpliceIndex;
+
+	uint8 numViewports;
+	uint8 numScissorRects;
+	uint16 pad2[1];
+
+	uint32 pad3[3];
+
+	SVGA3dViewport viewports[SVGA3D_DX_MAX_VIEWPORTS];
+	uint32 pad4[32];
+
+	SVGASignedRect scissorRects[SVGA3D_DX_MAX_SCISSORRECTS];
+	uint32 pad5[64];
+
+	struct {
+		uint32 queryID;
+		uint32 value;
+	} predication;
+
+	SVGAMobId shaderIfaceMobid;
+	uint32 shaderIfaceOffset;
+	struct {
+		uint32 shaderId;
+		SVGA3dConstantBufferBinding
+			constantBuffers[SVGA3D_DX_MAX_CONSTBUFFERS];
+		uint32 shaderResources[SVGA3D_DX_MAX_SRVIEWS];
+		uint32 samplers[SVGA3D_DX_MAX_SAMPLERS];
+	} shaderState[SVGA3D_NUM_SHADERTYPE];
+	uint32 pad6[26];
+
+	SVGA3dQueryId queryID[SVGA3D_MAX_QUERY];
+
+	SVGA3dCOTableData cotables[SVGA_COTABLE_MAX];
+
+	uint32 pad7[64];
+
+	uint32 uaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS];
+	uint32 csuaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS];
+
+	uint32 pad8[188];
+} SVGADXContextMobFormat;
+#pragma pack(pop)
 
-/*
- * SVGA3dCmdSetCOTable --
- *
- * This command allows the guest to bind a mob to a context-object table.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXSetCOTable {
-   uint32 cid;
-   uint32 mobid;
-   SVGACOTableType type;
-   uint32 validSizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXSetCOTable; /* SVGA_3D_CMD_DX_SET_COTABLE */
+#define SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED 256
 
-/*
- * Guests using SVGA_3D_CMD_DX_GROW_COTABLE are promising that
- * the new COTable contains the same contents as the old one, except possibly
- * for some new invalid entries at the end.
- *
- * If there is an old cotable mob bound, it also has to still be valid.
- *
- * (Otherwise, guests should use the DXSetCOTableBase command.)
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXGrowCOTable {
-   uint32 cid;
-   uint32 mobid;
-   SVGACOTableType type;
-   uint32 validSizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXGrowCOTable; /* SVGA_3D_CMD_DX_GROW_COTABLE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXReadbackCOTable {
-   uint32 cid;
-   SVGACOTableType type;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXReadbackCOTable; /* SVGA_3D_CMD_DX_READBACK_COTABLE */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCOTableData {
-   uint32 mobid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCOTableData;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dBufferBinding {
-   uint32 bufferId;
-   uint32 stride;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGA3dBufferBinding;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dConstantBufferBinding {
-   uint32 sid;
-   uint32 offsetInBytes;
-   uint32 sizeInBytes;
-}
-#include "vmware_pack_end.h"
-SVGA3dConstantBufferBinding;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGADXInputAssemblyMobFormat {
-   uint32 layoutId;
-   SVGA3dBufferBinding vertexBuffers[SVGA3D_DX_MAX_VERTEXBUFFERS];
-   uint32 indexBufferSid;
-   uint32 pad;
-   uint32 indexBufferOffset;
-   uint32 indexBufferFormat;
-   uint32 topology;
-}
-#include "vmware_pack_end.h"
-SVGADXInputAssemblyMobFormat;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGADXContextMobFormat {
-   SVGADXInputAssemblyMobFormat inputAssembly;
-
-   struct {
-      uint32 blendStateId;
-      uint32 blendFactor[4];
-      uint32 sampleMask;
-      uint32 depthStencilStateId;
-      uint32 stencilRef;
-      uint32 rasterizerStateId;
-      uint32 depthStencilViewId;
-      uint32 renderTargetViewIds[SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS];
-   } renderState;
-
-   uint32 pad0[8];
-
-   struct {
-      uint32 targets[SVGA3D_DX_MAX_SOTARGETS];
-      uint32 soid;
-   } streamOut;
-
-   uint32 pad1[10];
-
-   uint32 uavSpliceIndex;
-
-   uint8 numViewports;
-   uint8 numScissorRects;
-   uint16 pad2[1];
-
-   uint32 pad3[3];
-
-   SVGA3dViewport viewports[SVGA3D_DX_MAX_VIEWPORTS];
-   uint32 pad4[32];
-
-   SVGASignedRect scissorRects[SVGA3D_DX_MAX_SCISSORRECTS];
-   uint32 pad5[64];
-
-   struct {
-      uint32 queryID;
-      uint32 value;
-   } predication;
-
-   SVGAMobId shaderIfaceMobid;
-   uint32 shaderIfaceOffset;
-   struct {
-      uint32 shaderId;
-      SVGA3dConstantBufferBinding constantBuffers[SVGA3D_DX_MAX_CONSTBUFFERS];
-      uint32 shaderResources[SVGA3D_DX_MAX_SRVIEWS];
-      uint32 samplers[SVGA3D_DX_MAX_SAMPLERS];
-   } shaderState[SVGA3D_NUM_SHADERTYPE];
-   uint32 pad6[26];
-
-   SVGA3dQueryId queryID[SVGA3D_MAX_QUERY];
-
-   SVGA3dCOTableData cotables[SVGA_COTABLE_MAX];
-
-   uint32 pad7[64];
-
-   uint32 uaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS];
-   uint32 csuaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS];
-
-   uint32 pad8[188];
-}
-#include "vmware_pack_end.h"
-SVGADXContextMobFormat;
+#pragma pack(push, 1)
+typedef struct SVGADXShaderIfaceMobFormat {
+	struct {
+		uint32 numClassInstances;
+		uint32 iface[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED];
+		SVGA3dIfaceData data[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED];
+	} shaderIfaceState[SVGA3D_NUM_SHADERTYPE];
 
-/*
- * There is conflicting documentation on max class instances (253 vs 256).  The
- * lower value is the one used throughout the device, but since mob format is
- * more involved to increase if needed, conservatively use the higher one here.
- */
-#define SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED 256
+	uint32 pad0[1018];
+} SVGADXShaderIfaceMobFormat;
+#pragma pack(pop)
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGADXShaderIfaceMobFormat {
-   struct {
-      uint32 numClassInstances;
-      uint32 iface[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED];
-      SVGA3dIfaceData data[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED];
-   } shaderIfaceState[SVGA3D_NUM_SHADERTYPE];
-
-   uint32 pad0[1018];
-}
-#include "vmware_pack_end.h"
-SVGADXShaderIfaceMobFormat;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDXTempSetContext {
-   uint32 dxcid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDXTempSetContext; /* SVGA_3D_CMD_DX_TEMP_SET_CONTEXT */
-
-#endif /* _SVGA3D_DX_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
index f4375a41b3aa..35494a728c7a 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2019 VMware, Inc.
+ * Copyright 2012-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,104 +27,59 @@
 /*
  * svga3d_limits.h --
  *
- *       SVGA 3d hardware limits
+ *    SVGA 3d hardware limits
  */
 
-#ifndef _SVGA3D_LIMITS_H_
-#define _SVGA3D_LIMITS_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
 
-#include "includeCheck.h"
+#ifndef _SVGA3D_LIMITS_H_
+#define _SVGA3D_LIMITS_H_
 
-#define SVGA3D_NUM_CLIPPLANES                   6
-#define SVGA3D_MAX_CONTEXT_IDS                  256
-#define SVGA3D_MAX_SURFACE_IDS                  (32 * 1024)
+#define SVGA3D_HB_MAX_CONTEXT_IDS 256
+#define SVGA3D_HB_MAX_SURFACE_IDS (32 * 1024)
 
-/*
- * While there are separate bind-points for RenderTargetViews and
- * UnorderedAccessViews in a DXContext, there is in fact one shared
- * semantic space that the guest-driver can use on any given draw call.
- * So there are really only 8 slots that can be spilt up between them, with the
- * spliceIndex controlling where the UAV's sit in the collapsed array.
- */
-#define SVGA3D_MAX_RENDER_TARGETS               8
-#define SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS  (SVGA3D_MAX_RENDER_TARGETS)
-#define SVGA3D_MAX_UAVIEWS                      8
-#define SVGA3D_DX11_1_MAX_UAVIEWS               64
+#define SVGA3D_DX_MAX_RENDER_TARGETS 8
+#define SVGA3D_DX11_MAX_UAVIEWS 8
+#define SVGA3D_DX11_1_MAX_UAVIEWS 64
+#define SVGA3D_MAX_UAVIEWS (SVGA3D_DX11_1_MAX_UAVIEWS)
+#define SVGA3D_DX11_MAX_SIMULTANEOUS_RTUAV (SVGA3D_DX11_MAX_UAVIEWS)
+#define SVGA3D_DX11_1_MAX_SIMULTANEOUS_RTUAV (SVGA3D_DX11_1_MAX_UAVIEWS)
+#define SVGA3D_MAX_SIMULTANEOUS_RTUAV (SVGA3D_MAX_UAVIEWS)
 
-/*
- * Maximum canonical size of a surface in host-backed mode (pre-GBObjects).
- */
 #define SVGA3D_HB_MAX_SURFACE_SIZE MBYTES_2_BYTES(128)
 
-/*
- * Maximum ID a shader can be assigned on a given context.
- */
-#define SVGA3D_MAX_SHADERIDS                    5000
-/*
- * Maximum number of shaders of a given type that can be defined
- * (including all contexts).
- */
-#define SVGA3D_MAX_SIMULTANEOUS_SHADERS         20000
+#define SVGA3D_MAX_SHADERIDS 5000
 
-#define SVGA3D_NUM_TEXTURE_UNITS                32
-#define SVGA3D_NUM_LIGHTS                       8
+#define SVGA3D_MAX_SIMULTANEOUS_SHADERS 20000
 
-#define SVGA3D_MAX_VIDEOPROCESSOR_SAMPLERS      32
+#define SVGA3D_NUM_TEXTURE_UNITS 32
+#define SVGA3D_NUM_LIGHTS 8
+
+#define SVGA3D_MAX_VIDEOPROCESSOR_SAMPLERS 32
 
-/*
- * Maximum size in dwords of shader text the SVGA device will allow.
- * Currently 8 MB.
- */
 #define SVGA3D_MAX_SHADER_MEMORY_BYTES (8 * 1024 * 1024)
-#define SVGA3D_MAX_SHADER_MEMORY  (SVGA3D_MAX_SHADER_MEMORY_BYTES / \
-                                   sizeof(uint32))
+#define SVGA3D_MAX_SHADER_MEMORY                                               \
+	(SVGA3D_MAX_SHADER_MEMORY_BYTES / sizeof(uint32))
 
-/*
- * The maximum value of threadGroupCount in each dimension
- */
 #define SVGA3D_MAX_SHADER_THREAD_GROUPS 65535
 
-#define SVGA3D_MAX_CLIP_PLANES    6
+#define SVGA3D_MAX_CLIP_PLANES 6
 
-/*
- * This is the limit to the number of fixed-function texture
- * transforms and texture coordinates we can support. It does *not*
- * correspond to the number of texture image units (samplers) we
- * support!
- */
 #define SVGA3D_MAX_TEXTURE_COORDS 8
 
-/*
- * Number of faces in a cubemap.
- */
 #define SVGA3D_MAX_SURFACE_FACES 6
 
-/*
- * Maximum number of array indexes in a GB surface (with DX enabled).
- */
 #define SVGA3D_SM4_MAX_SURFACE_ARRAYSIZE 512
 #define SVGA3D_SM5_MAX_SURFACE_ARRAYSIZE 2048
 #define SVGA3D_MAX_SURFACE_ARRAYSIZE SVGA3D_SM5_MAX_SURFACE_ARRAYSIZE
 
-/*
- * The maximum number of vertex arrays we're guaranteed to support in
- * SVGA_3D_CMD_DRAWPRIMITIVES.
- */
-#define SVGA3D_MAX_VERTEX_ARRAYS   32
+#define SVGA3D_MAX_VERTEX_ARRAYS 32
 
-/*
- * The maximum number of primitive ranges we're guaranteed to support
- * in SVGA_3D_CMD_DRAWPRIMITIVES.
- */
 #define SVGA3D_MAX_DRAW_PRIMITIVE_RANGES 32
 
-/*
- * The maximum number of samples that can be contained in a surface.
- */
 #define SVGA3D_MAX_SAMPLES 8
 
-#endif /* _SVGA3D_LIMITS_H_ */
+#define SVGA3D_MIN_SBX_DATA_SIZE (GBYTES_2_BYTES(1))
+#define SVGA3D_MAX_SBX_DATA_SIZE (GBYTES_2_BYTES(4))
+
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
index bdfc404c91e3..988d8509c472 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
  * Copyright 1998-2015 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,17 +27,13 @@
 /*
  * svga3d_reg.h --
  *
- *       SVGA 3d hardware definitions
+ *    SVGA 3d hardware definitions
  */
 
-#ifndef _SVGA3D_REG_H_
-#define _SVGA3D_REG_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
 
-#include "includeCheck.h"
+#ifndef _SVGA3D_REG_H_
+#define _SVGA3D_REG_H_
 
 #include "svga_reg.h"
 
@@ -47,5 +43,4 @@
 #include "svga3d_dx.h"
 #include "svga3d_devcaps.h"
 
-
-#endif /* _SVGA3D_REG_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index 127eaf0a0a58..7d98fc48414e 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -1,1667 +1,1561 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
-/**************************************************************************
+/**********************************************************
+ * Copyright 2008-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
- * Copyright 2008-2015 VMware, Inc., Palo Alto, CA., USA
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy,
+ * modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
  *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
  *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- **************************************************************************/
+ **********************************************************/
 
 /*
  * svga3d_surfacedefs.h --
  *
- *      Surface definitions and inlineable utilities for SVGA3d.
+ *    Surface definitions for SVGA3d.
  */
 
+
+
 #ifndef _SVGA3D_SURFACEDEFS_H_
 #define _SVGA3D_SURFACEDEFS_H_
 
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_MODULE
-#include "includeCheck.h"
+#include "svga3d_types.h"
 
-#include <linux/kernel.h>
-#include <drm/vmwgfx_drm.h>
+#ifdef __cplusplus
+extern "C" {
+#endif
 
-#include "svga3d_reg.h"
+struct SVGAUseCaps;
 
-#define surf_size_struct struct drm_vmw_size
+#if defined(_WIN32) && !defined(__GNUC__)
 
-/*
- * enum svga3d_block_desc - describes generic properties about formats.
- */
-enum svga3d_block_desc {
-	/* Nothing special can be said about this format. */
-	SVGA3DBLOCKDESC_NONE        = 0,
+#define STATIC_CONST __declspec(selectany) extern const
+#else
+#define STATIC_CONST static const
+#endif
+
+typedef enum SVGA3dBlockDesc {
 
-	/* Format contains Blue/U data */
-	SVGA3DBLOCKDESC_BLUE        = 1 << 0,
-	SVGA3DBLOCKDESC_W           = 1 << 0,
-	SVGA3DBLOCKDESC_BUMP_L      = 1 << 0,
+	SVGA3DBLOCKDESC_NONE = 0,
 
-	/* Format contains Green/V data */
-	SVGA3DBLOCKDESC_GREEN       = 1 << 1,
-	SVGA3DBLOCKDESC_V           = 1 << 1,
+	SVGA3DBLOCKDESC_BLUE = 1 << 0,
+	SVGA3DBLOCKDESC_W = 1 << 0,
+	SVGA3DBLOCKDESC_BUMP_L = 1 << 0,
 
-	/* Format contains Red/W/Luminance data */
-	SVGA3DBLOCKDESC_RED         = 1 << 2,
-	SVGA3DBLOCKDESC_U           = 1 << 2,
-	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,
+	SVGA3DBLOCKDESC_GREEN = 1 << 1,
+	SVGA3DBLOCKDESC_V = 1 << 1,
 
-	/* Format contains Alpha/Q data */
-	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,
-	SVGA3DBLOCKDESC_Q           = 1 << 3,
+	SVGA3DBLOCKDESC_RED = 1 << 2,
+	SVGA3DBLOCKDESC_U = 1 << 2,
+	SVGA3DBLOCKDESC_LUMINANCE = 1 << 2,
 
-	/* Format is a buffer */
-	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,
+	SVGA3DBLOCKDESC_ALPHA = 1 << 3,
+	SVGA3DBLOCKDESC_Q = 1 << 3,
 
-	/* Format is compressed */
-	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,
+	SVGA3DBLOCKDESC_BUFFER = 1 << 4,
 
-	/* Format uses IEEE floating point */
-	SVGA3DBLOCKDESC_FP          = 1 << 6,
+	SVGA3DBLOCKDESC_COMPRESSED = 1 << 5,
 
-	/* Three separate blocks store data. */
-	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 7,
+	SVGA3DBLOCKDESC_FP = 1 << 6,
+
+	SVGA3DBLOCKDESC_PLANAR_YUV = 1 << 7,
 
-	/* 2 planes of Y, UV, e.g., NV12. */
 	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 8,
 
-	/* 3 planes of separate Y, U, V, e.g., YV12. */
 	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 9,
 
-	/* Block with a stencil channel */
-	SVGA3DBLOCKDESC_STENCIL     = 1 << 11,
-
-	/* Typeless format */
-	SVGA3DBLOCKDESC_TYPELESS    = 1 << 12,
-
-	/* Channels are signed integers */
-	SVGA3DBLOCKDESC_SINT        = 1 << 13,
-
-	/* Channels are unsigned integers */
-	SVGA3DBLOCKDESC_UINT        = 1 << 14,
-
-	/* Channels are normalized (when sampling) */
-	SVGA3DBLOCKDESC_NORM        = 1 << 15,
-
-	/* Channels are in SRGB */
-	SVGA3DBLOCKDESC_SRGB        = 1 << 16,
-
-	/* Shared exponent */
-	SVGA3DBLOCKDESC_EXP         = 1 << 17,
-
-	/* Format contains color data. */
-	SVGA3DBLOCKDESC_COLOR       = 1 << 18,
-	/* Format contains depth data. */
-	SVGA3DBLOCKDESC_DEPTH       = 1 << 19,
-	/* Format contains bump data. */
-	SVGA3DBLOCKDESC_BUMP        = 1 << 20,
-
-	/* Format contains YUV video data. */
-	SVGA3DBLOCKDESC_YUV_VIDEO   = 1 << 21,
-
-	/* For mixed unsigned/signed formats. */
-	SVGA3DBLOCKDESC_MIXED       = 1 << 22,
-
-	/* For distingushing CxV8U8. */
-	SVGA3DBLOCKDESC_CX          = 1 << 23,
-
-	/* Different compressed format groups. */
-	SVGA3DBLOCKDESC_BC1         = 1 << 24,
-	SVGA3DBLOCKDESC_BC2         = 1 << 25,
-	SVGA3DBLOCKDESC_BC3         = 1 << 26,
-	SVGA3DBLOCKDESC_BC4         = 1 << 27,
-	SVGA3DBLOCKDESC_BC5         = 1 << 28,
-	SVGA3DBLOCKDESC_BC6H        = 1 << 29,
-	SVGA3DBLOCKDESC_BC7         = 1 << 30,
-
-	SVGA3DBLOCKDESC_A_UINT    = SVGA3DBLOCKDESC_ALPHA |
-				    SVGA3DBLOCKDESC_UINT |
-				    SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_A_UNORM   = SVGA3DBLOCKDESC_A_UINT |
-				    SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_R_UINT    = SVGA3DBLOCKDESC_RED |
-				    SVGA3DBLOCKDESC_UINT |
-				    SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_R_UNORM   = SVGA3DBLOCKDESC_R_UINT |
-				    SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_R_SINT    = SVGA3DBLOCKDESC_RED |
-				    SVGA3DBLOCKDESC_SINT |
-				    SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_R_SNORM   = SVGA3DBLOCKDESC_R_SINT |
-				    SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_G_UINT    = SVGA3DBLOCKDESC_GREEN |
-				    SVGA3DBLOCKDESC_UINT |
-				    SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RG_UINT    = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RG_UNORM   = SVGA3DBLOCKDESC_RG_UINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_RG_SINT    = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_SINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RG_SNORM   = SVGA3DBLOCKDESC_RG_SINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_RGB_UINT   = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGB_SINT   = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_SINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGB_UNORM   = SVGA3DBLOCKDESC_RGB_UINT |
-				      SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_RGB_UNORM_SRGB = SVGA3DBLOCKDESC_RGB_UNORM |
-					 SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_RGBA_UINT  = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGBA_UNORM = SVGA3DBLOCKDESC_RGBA_UINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = SVGA3DBLOCKDESC_RGBA_UNORM |
-					  SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_RGBA_SINT  = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_SINT |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGBA_SNORM = SVGA3DBLOCKDESC_RGBA_SINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_FP |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_UV         = SVGA3DBLOCKDESC_U |
-				     SVGA3DBLOCKDESC_V |
-				     SVGA3DBLOCKDESC_BUMP,
-	SVGA3DBLOCKDESC_UVL        = SVGA3DBLOCKDESC_UV |
-				     SVGA3DBLOCKDESC_BUMP_L |
-				     SVGA3DBLOCKDESC_MIXED |
-				     SVGA3DBLOCKDESC_BUMP,
-	SVGA3DBLOCKDESC_UVW        = SVGA3DBLOCKDESC_UV |
-				     SVGA3DBLOCKDESC_W |
-				     SVGA3DBLOCKDESC_BUMP,
-	SVGA3DBLOCKDESC_UVWA       = SVGA3DBLOCKDESC_UVW |
-				     SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_MIXED |
-				     SVGA3DBLOCKDESC_BUMP,
-	SVGA3DBLOCKDESC_UVWQ       = SVGA3DBLOCKDESC_U |
-				     SVGA3DBLOCKDESC_V |
-				     SVGA3DBLOCKDESC_W |
-				     SVGA3DBLOCKDESC_Q |
-				     SVGA3DBLOCKDESC_BUMP,
-	SVGA3DBLOCKDESC_L_UNORM    = SVGA3DBLOCKDESC_LUMINANCE |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_NORM |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_LA_UNORM   = SVGA3DBLOCKDESC_LUMINANCE |
-				     SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_NORM |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_R_FP       = SVGA3DBLOCKDESC_RED |
-				     SVGA3DBLOCKDESC_FP |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RG_FP      = SVGA3DBLOCKDESC_R_FP |
-				     SVGA3DBLOCKDESC_GREEN |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGB_FP     = SVGA3DBLOCKDESC_RG_FP |
-				     SVGA3DBLOCKDESC_BLUE |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_YUV_VIDEO |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_AYUV       = SVGA3DBLOCKDESC_ALPHA |
-				     SVGA3DBLOCKDESC_YUV_VIDEO |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_RGB_EXP       = SVGA3DBLOCKDESC_RED |
-					SVGA3DBLOCKDESC_GREEN |
-					SVGA3DBLOCKDESC_BLUE |
-					SVGA3DBLOCKDESC_EXP |
-					SVGA3DBLOCKDESC_COLOR,
-
-	SVGA3DBLOCKDESC_COMP_TYPELESS = SVGA3DBLOCKDESC_COMPRESSED |
-					SVGA3DBLOCKDESC_TYPELESS,
-	SVGA3DBLOCKDESC_COMP_UNORM = SVGA3DBLOCKDESC_COMPRESSED |
-				     SVGA3DBLOCKDESC_UINT |
-				     SVGA3DBLOCKDESC_NORM |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_COMP_SNORM = SVGA3DBLOCKDESC_COMPRESSED |
-				     SVGA3DBLOCKDESC_SINT |
-				     SVGA3DBLOCKDESC_NORM |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_COMP_UNORM |
-					  SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = SVGA3DBLOCKDESC_BC1 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC1_COMP_UNORM = SVGA3DBLOCKDESC_BC1 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC1_COMP_UNORM |
-					      SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = SVGA3DBLOCKDESC_BC2 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC2_COMP_UNORM = SVGA3DBLOCKDESC_BC2 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC2_COMP_UNORM |
-					      SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = SVGA3DBLOCKDESC_BC3 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC3_COMP_UNORM = SVGA3DBLOCKDESC_BC3 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC3_COMP_UNORM |
-					      SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = SVGA3DBLOCKDESC_BC4 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC4_COMP_UNORM = SVGA3DBLOCKDESC_BC4 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC4_COMP_SNORM = SVGA3DBLOCKDESC_BC4 |
-					 SVGA3DBLOCKDESC_COMP_SNORM,
-	SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = SVGA3DBLOCKDESC_BC5 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC5_COMP_UNORM = SVGA3DBLOCKDESC_BC5 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC5_COMP_SNORM = SVGA3DBLOCKDESC_BC5 |
-					 SVGA3DBLOCKDESC_COMP_SNORM,
-	SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS = SVGA3DBLOCKDESC_BC6H |
-					     SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC6H_COMP_UF16 = SVGA3DBLOCKDESC_BC6H |
-					 SVGA3DBLOCKDESC_COMPRESSED,
-	SVGA3DBLOCKDESC_BC6H_COMP_SF16 = SVGA3DBLOCKDESC_BC6H |
-					 SVGA3DBLOCKDESC_COMPRESSED,
-	SVGA3DBLOCKDESC_BC7_COMP_TYPELESS = SVGA3DBLOCKDESC_BC7 |
-					    SVGA3DBLOCKDESC_COMP_TYPELESS,
-	SVGA3DBLOCKDESC_BC7_COMP_UNORM = SVGA3DBLOCKDESC_BC7 |
-					 SVGA3DBLOCKDESC_COMP_UNORM,
-	SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC7_COMP_UNORM |
-					      SVGA3DBLOCKDESC_SRGB,
-
-	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
-				     SVGA3DBLOCKDESC_PLANAR_YUV |
-				     SVGA3DBLOCKDESC_2PLANAR_YUV |
-				     SVGA3DBLOCKDESC_COLOR,
-	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
-				     SVGA3DBLOCKDESC_PLANAR_YUV |
-				     SVGA3DBLOCKDESC_3PLANAR_YUV |
-				     SVGA3DBLOCKDESC_COLOR,
-
-	SVGA3DBLOCKDESC_DEPTH_UINT = SVGA3DBLOCKDESC_DEPTH |
-				     SVGA3DBLOCKDESC_UINT,
-	SVGA3DBLOCKDESC_DEPTH_UNORM = SVGA3DBLOCKDESC_DEPTH_UINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_DS      =    SVGA3DBLOCKDESC_DEPTH |
-				     SVGA3DBLOCKDESC_STENCIL,
-	SVGA3DBLOCKDESC_DS_UINT =    SVGA3DBLOCKDESC_DEPTH |
-				     SVGA3DBLOCKDESC_STENCIL |
-				     SVGA3DBLOCKDESC_UINT,
-	SVGA3DBLOCKDESC_DS_UNORM =   SVGA3DBLOCKDESC_DS_UINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_DEPTH_FP   = SVGA3DBLOCKDESC_DEPTH |
-				     SVGA3DBLOCKDESC_FP,
-
-	SVGA3DBLOCKDESC_UV_UINT    = SVGA3DBLOCKDESC_UV |
-				     SVGA3DBLOCKDESC_UINT,
-	SVGA3DBLOCKDESC_UV_SNORM   = SVGA3DBLOCKDESC_UV |
-				     SVGA3DBLOCKDESC_SINT |
-				     SVGA3DBLOCKDESC_NORM,
-	SVGA3DBLOCKDESC_UVCX_SNORM = SVGA3DBLOCKDESC_UV_SNORM |
-				     SVGA3DBLOCKDESC_CX,
+	SVGA3DBLOCKDESC_STENCIL = 1 << 11,
+
+	SVGA3DBLOCKDESC_TYPELESS = 1 << 12,
+
+	SVGA3DBLOCKDESC_SINT = 1 << 13,
+
+	SVGA3DBLOCKDESC_UINT = 1 << 14,
+
+	SVGA3DBLOCKDESC_NORM = 1 << 15,
+
+	SVGA3DBLOCKDESC_SRGB = 1 << 16,
+
+	SVGA3DBLOCKDESC_EXP = 1 << 17,
+
+	SVGA3DBLOCKDESC_COLOR = 1 << 18,
+
+	SVGA3DBLOCKDESC_DEPTH = 1 << 19,
+
+	SVGA3DBLOCKDESC_BUMP = 1 << 20,
+
+	SVGA3DBLOCKDESC_YUV_VIDEO = 1 << 21,
+
+	SVGA3DBLOCKDESC_MIXED = 1 << 22,
+
+	SVGA3DBLOCKDESC_CX = 1 << 23,
+
+	SVGA3DBLOCKDESC_BC1 = 1 << 24,
+	SVGA3DBLOCKDESC_BC2 = 1 << 25,
+	SVGA3DBLOCKDESC_BC3 = 1 << 26,
+	SVGA3DBLOCKDESC_BC4 = 1 << 27,
+	SVGA3DBLOCKDESC_BC5 = 1 << 28,
+	SVGA3DBLOCKDESC_BC6H = 1 << 29,
+	SVGA3DBLOCKDESC_BC7 = 1 << 30,
+	SVGA3DBLOCKDESC_COMPRESSED_MASK =
+		SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_BC2 |
+		SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_BC4 |
+		SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_BC6H |
+		SVGA3DBLOCKDESC_BC7,
+
+	SVGA3DBLOCKDESC_A_UINT = SVGA3DBLOCKDESC_ALPHA | SVGA3DBLOCKDESC_UINT |
+				 SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_A_UNORM = SVGA3DBLOCKDESC_A_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_UINT |
+				 SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_UNORM = SVGA3DBLOCKDESC_R_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_SINT |
+				 SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_SNORM = SVGA3DBLOCKDESC_R_SINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_G_UINT = SVGA3DBLOCKDESC_GREEN | SVGA3DBLOCKDESC_UINT |
+				 SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				  SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UNORM =
+		SVGA3DBLOCKDESC_RG_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RG_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				  SVGA3DBLOCKDESC_SINT | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_SNORM =
+		SVGA3DBLOCKDESC_RG_SINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				   SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_UINT |
+				   SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				   SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_SINT |
+				   SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_UNORM =
+		SVGA3DBLOCKDESC_RGB_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UNORM_SRGB =
+		SVGA3DBLOCKDESC_RGB_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_UINT =
+		SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+		SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA |
+		SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_UNORM =
+		SVGA3DBLOCKDESC_RGBA_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_UNORM_SRGB =
+		SVGA3DBLOCKDESC_RGBA_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_SINT =
+		SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+		SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA |
+		SVGA3DBLOCKDESC_SINT | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_SNORM =
+		SVGA3DBLOCKDESC_RGBA_SINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_FP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				  SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA |
+				  SVGA3DBLOCKDESC_FP | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_UV =
+		SVGA3DBLOCKDESC_U | SVGA3DBLOCKDESC_V | SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_UVL = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_BUMP_L |
+			      SVGA3DBLOCKDESC_MIXED | SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_UVW =
+		SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_W | SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_UVWA = SVGA3DBLOCKDESC_UVW | SVGA3DBLOCKDESC_ALPHA |
+			       SVGA3DBLOCKDESC_MIXED | SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_UVWQ = SVGA3DBLOCKDESC_U | SVGA3DBLOCKDESC_V |
+			       SVGA3DBLOCKDESC_W | SVGA3DBLOCKDESC_Q |
+			       SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_L_UNORM = SVGA3DBLOCKDESC_LUMINANCE |
+				  SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_NORM |
+				  SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_LA_UNORM = SVGA3DBLOCKDESC_LUMINANCE |
+				   SVGA3DBLOCKDESC_ALPHA |
+				   SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_NORM |
+				   SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_FP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_FP |
+			       SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_FP = SVGA3DBLOCKDESC_R_FP | SVGA3DBLOCKDESC_GREEN |
+				SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_FP = SVGA3DBLOCKDESC_RG_FP | SVGA3DBLOCKDESC_BLUE |
+				 SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YUV = SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_AYUV = SVGA3DBLOCKDESC_ALPHA |
+			       SVGA3DBLOCKDESC_YUV_VIDEO |
+			       SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_EXP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN |
+				  SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_EXP |
+				  SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_TYPELESS,
+	SVGA3DBLOCKDESC_COMP_UNORM =
+		SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_UINT |
+		SVGA3DBLOCKDESC_NORM | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_SNORM =
+		SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_SINT |
+		SVGA3DBLOCKDESC_NORM | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_UNORM_SRGB =
+		SVGA3DBLOCKDESC_COMP_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC1_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB =
+		SVGA3DBLOCKDESC_BC1_COMP_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC2_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC2 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC2 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB =
+		SVGA3DBLOCKDESC_BC2_COMP_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC3_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB =
+		SVGA3DBLOCKDESC_BC3_COMP_UNORM | SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC4_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC4_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC4_COMP_SNORM =
+		SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_SNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC5_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_SNORM =
+		SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_SNORM,
+	SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC6H_COMP_UF16 =
+		SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMPRESSED,
+	SVGA3DBLOCKDESC_BC6H_COMP_SF16 =
+		SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMPRESSED,
+	SVGA3DBLOCKDESC_BC7_COMP_TYPELESS =
+		SVGA3DBLOCKDESC_BC7 | SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC7_COMP_UNORM =
+		SVGA3DBLOCKDESC_BC7 | SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB =
+		SVGA3DBLOCKDESC_BC7_COMP_UNORM | SVGA3DBLOCKDESC_SRGB,
+
+	SVGA3DBLOCKDESC_NV12 =
+		SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_PLANAR_YUV |
+		SVGA3DBLOCKDESC_2PLANAR_YUV | SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YV12 =
+		SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_PLANAR_YUV |
+		SVGA3DBLOCKDESC_3PLANAR_YUV | SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_DEPTH_UINT =
+		SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DEPTH_UNORM =
+		SVGA3DBLOCKDESC_DEPTH_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DS = SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_STENCIL,
+	SVGA3DBLOCKDESC_DS_UINT = SVGA3DBLOCKDESC_DEPTH |
+				  SVGA3DBLOCKDESC_STENCIL |
+				  SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DS_UNORM =
+		SVGA3DBLOCKDESC_DS_UINT | SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DEPTH_FP = SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_FP,
+
+	SVGA3DBLOCKDESC_UV_UINT = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_UV_SNORM = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_SINT |
+				   SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_UVCX_SNORM =
+		SVGA3DBLOCKDESC_UV_SNORM | SVGA3DBLOCKDESC_CX,
 	SVGA3DBLOCKDESC_UVWQ_SNORM = SVGA3DBLOCKDESC_UVWQ |
 				     SVGA3DBLOCKDESC_SINT |
 				     SVGA3DBLOCKDESC_NORM,
-};
+} SVGA3dBlockDesc;
 
-struct svga3d_channel_def {
+typedef struct SVGA3dChannelDef {
 	union {
-		u8 blue;
-		u8 w_bump;
-		u8 l_bump;
-		u8 uv_video;
-		u8 u_video;
+		uint8 blue;
+		uint8 w_bump;
+		uint8 l_bump;
+		uint8 uv_video;
+		uint8 u_video;
 	};
 	union {
-		u8 green;
-		u8 stencil;
-		u8 v_bump;
-		u8 v_video;
+		uint8 green;
+		uint8 stencil;
+		uint8 v_bump;
+		uint8 v_video;
 	};
 	union {
-		u8 red;
-		u8 u_bump;
-		u8 luminance;
-		u8 y_video;
-		u8 depth;
-		u8 data;
+		uint8 red;
+		uint8 u_bump;
+		uint8 luminance;
+		uint8 y_video;
+		uint8 depth;
+		uint8 data;
 	};
 	union {
-		u8 alpha;
-		u8 q_bump;
-		u8 exp;
+		uint8 alpha;
+		uint8 q_bump;
+		uint8 exp;
 	};
-};
+} SVGA3dChannelDef;
 
-/*
- * struct svga3d_surface_desc - describes the actual pixel data.
- *
- * @format: Format
- * @block_desc: Block description
- * @block_size: Dimensions in pixels of a block
- * @bytes_per_block: Size of block in bytes
- * @pitch_bytes_per_block: Size of a block in bytes for purposes of pitch
- * @bit_depth: Channel bit depths
- * @bit_offset: Channel bit masks (in bits offset from the start of the pointer)
- */
-struct svga3d_surface_desc {
+typedef struct SVGA3dSurfaceDesc {
 	SVGA3dSurfaceFormat format;
-	enum svga3d_block_desc block_desc;
-
-	surf_size_struct block_size;
-	u32 bytes_per_block;
-	u32 pitch_bytes_per_block;
-
-	struct svga3d_channel_def bit_depth;
-	struct svga3d_channel_def bit_offset;
-};
-
-static const struct svga3d_surface_desc svga3d_surface_descs[] = {
-   {SVGA3D_FORMAT_INVALID, SVGA3DBLOCKDESC_NONE,
-      {1, 1, 1},  0, 0,
-      {{0}, {0}, {0}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB_UNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB_UNORM,
-      {1, 1, 1},  2, 2,
-      {{5}, {6}, {5}, {0}},
-      {{0}, {5}, {11}, {0}}},
-
-   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB_UNORM,
-      {1, 1, 1},  2, 2,
-      {{5}, {5}, {5}, {0}},
-      {{0}, {5}, {10}, {0}}},
-
-   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  2, 2,
-      {{5}, {5}, {5}, {1}},
-      {{0}, {5}, {10}, {15}}},
-
-   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  2, 2,
-      {{4}, {4}, {4}, {4}},
-      {{0}, {4}, {8}, {12}}},
-
-   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {8}, {24}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {1}, {15}, {0}},
-      {{0}, {0}, {1}, {0}}},
-
-   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_L_UNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA_UNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {4}, {4}},
-      {{0}, {0}, {0}, {4}}},
-
-   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_L_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {8}, {8}},
-      {{0}, {0}, {0}, {8}}},
-
-   {SVGA3D_DXT1, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_DXT2, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_DXT3, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_DXT4, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_DXT5, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV_SNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_BUMPL6V5U5, SVGA3DBLOCKDESC_UVL,
-      {1, 1, 1},  2, 2,
-      {{6}, {5}, {5}, {0}},
-      {{10}, {5}, {0}, {0}}},
-
-   {SVGA3D_BUMPX8L8V8U8, SVGA3DBLOCKDESC_UVL,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{16}, {8}, {0}, {0}}},
-
-   {SVGA3D_FORMAT_DEAD1, SVGA3DBLOCKDESC_NONE,
-      {1, 1, 1},  3, 3,
-      {{8}, {8}, {8}, {0}},
-      {{16}, {8}, {0}, {0}}},
-
-   {SVGA3D_ARGB_S10E5, SVGA3DBLOCKDESC_RGBA_FP,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_ARGB_S23E8, SVGA3DBLOCKDESC_RGBA_FP,
-      {1, 1, 1},  16, 16,
-      {{32}, {32}, {32}, {32}},
-      {{64}, {32}, {0}, {96}}},
-
-   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
-
-   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV_SNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ_SNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UVCX_SNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_X8L8V8U8, SVGA3DBLOCKDESC_UVL,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{16}, {8}, {0}, {0}}},
-
-   {SVGA3D_A2W10V10U10, SVGA3DBLOCKDESC_UVWA,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-      {{20}, {10}, {0}, {30}}},
-
-   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_A_UNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {0}, {8}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R_S10E5, SVGA3DBLOCKDESC_R_FP,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R_S23E8, SVGA3DBLOCKDESC_R_FP,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_RG_S10E5, SVGA3DBLOCKDESC_RG_FP,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_RG_S23E8, SVGA3DBLOCKDESC_RG_FP,
-      {1, 1, 1},  8, 8,
-      {{0}, {32}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_BUFFER, SVGA3DBLOCKDESC_BUFFER,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {24}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV_SNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_UYVY, SVGA3DBLOCKDESC_YUV,
-      {2, 1, 1},  4, 4,
-      {{8}, {0}, {8}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_YUY2, SVGA3DBLOCKDESC_YUV,
-      {2, 1, 1},  4, 4,
-      {{8}, {0}, {8}, {0}},
-      {{8}, {0}, {0}, {0}}},
-
-   {SVGA3D_NV12, SVGA3DBLOCKDESC_NV12,
-      {2, 2, 1},  6, 2,
-      {{0}, {0}, {48}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_FORMAT_DEAD2, SVGA3DBLOCKDESC_NONE,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  16, 16,
-      {{32}, {32}, {32}, {32}},
-      {{64}, {32}, {0}, {96}}},
-
-   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
-      {1, 1, 1},  16, 16,
-      {{32}, {32}, {32}, {32}},
-      {{64}, {32}, {0}, {96}}},
-
-   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
-      {1, 1, 1},  16, 16,
-      {{32}, {32}, {32}, {32}},
-      {{64}, {32}, {0}, {96}}},
-
-   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  12, 12,
-      {{32}, {32}, {32}, {0}},
-      {{64}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G32B32_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
-      {1, 1, 1},  12, 12,
-      {{32}, {32}, {32}, {0}},
-      {{64}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB_UINT,
-      {1, 1, 1},  12, 12,
-      {{32}, {32}, {32}, {0}},
-      {{64}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_RGB_SINT,
-      {1, 1, 1},  12, 12,
-      {{32}, {32}, {32}, {0}},
-      {{64}, {32}, {0}, {0}}},
-
-   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  8, 8,
-      {{0}, {32}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG_UINT,
-      {1, 1, 1},  8, 8,
-      {{0}, {32}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_RG_SINT,
-      {1, 1, 1},  8, 8,
-      {{0}, {32}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  8, 8,
-      {{0}, {8}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_D32_FLOAT_S8X24_UINT, SVGA3DBLOCKDESC_DS,
-      {1, 1, 1},  8, 8,
-      {{0}, {8}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R32_FLOAT_X8X24, SVGA3DBLOCKDESC_R_FP,
-      {1, 1, 1},  8, 8,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_X32_G8X24_UINT, SVGA3DBLOCKDESC_G_UINT,
-      {1, 1, 1},  8, 8,
-      {{0}, {8}, {0}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-      {{20}, {10}, {0}, {30}}},
-
-   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-      {{20}, {10}, {0}, {30}}},
-
-   {SVGA3D_R11G11B10_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
-      {1, 1, 1},  4, 4,
-      {{10}, {11}, {11}, {0}},
-      {{22}, {11}, {0}, {0}}},
-
-   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_UINT,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_RG_SINT,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH_FP,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_R_UINT,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_R_SINT,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
-
-   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
-
-   {SVGA3D_R24_UNORM_X8, SVGA3DBLOCKDESC_R_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {24}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_X24_G8_UINT, SVGA3DBLOCKDESC_G_UINT,
-      {1, 1, 1},  4, 4,
-      {{0}, {8}, {0}, {0}},
-      {{0}, {24}, {0}, {0}}},
-
-   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG_UINT,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_RG_SINT,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_R_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_R_UINT,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_R_SNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_R_SINT,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_R_UNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_R_UINT,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_R_SNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_R_SINT,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_P8, SVGA3DBLOCKDESC_NONE,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {8}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGB_EXP,
-      {1, 1, 1},  4, 4,
-      {{9}, {9}, {9}, {5}},
-      {{18}, {9}, {0}, {27}}},
-
-   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_NONE,
-      {2, 1, 1},  4, 4,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_NONE,
-      {2, 1, 1},  4, 4,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_BC1_COMP_TYPELESS,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_BC2_COMP_TYPELESS,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_BC3_COMP_TYPELESS,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_BC4_COMP_TYPELESS,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_ATI1, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_BC4_COMP_SNORM,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_BC5_COMP_TYPELESS,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_ATI2, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_BC5_COMP_SNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-     {{20}, {10}, {0}, {30}}},
-
-   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_UNORM_SRGB,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {24}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {8}, {24}, {0}},
-      {{0}, {0}, {8}, {0}}},
-
-   {SVGA3D_YV12, SVGA3DBLOCKDESC_YV12,
-      {2, 2, 1},  6, 2,
-      {{0}, {0}, {48}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R32G32B32A32_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
-      {1, 1, 1},  16, 16,
-      {{32}, {32}, {32}, {32}},
-      {{64}, {32}, {0}, {96}}},
-
-   {SVGA3D_R16G16B16A16_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  8, 8,
-      {{16}, {16}, {16}, {16}},
-      {{32}, {16}, {0}, {48}}},
-
-   {SVGA3D_R32G32_FLOAT, SVGA3DBLOCKDESC_RG_FP,
-      {1, 1, 1},  8, 8,
-      {{0}, {32}, {32}, {0}},
-      {{0}, {32}, {0}, {0}}},
-
-   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{10}, {10}, {10}, {2}},
-      {{20}, {10}, {0}, {30}}},
-
-   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{16}, {8}, {0}, {24}}},
-
-   {SVGA3D_R16G16_FLOAT, SVGA3DBLOCKDESC_RG_FP,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
-      {1, 1, 1},  4, 4,
-      {{0}, {16}, {16}, {0}},
-      {{0}, {16}, {0}, {0}}},
-
-   {SVGA3D_R32_FLOAT, SVGA3DBLOCKDESC_R_FP,
-      {1, 1, 1},  4, 4,
-      {{0}, {0}, {32}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
-
-   {SVGA3D_R16_FLOAT, SVGA3DBLOCKDESC_R_FP,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH_UNORM,
-      {1, 1, 1},  2, 2,
-      {{0}, {0}, {16}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_A_UNORM,
-      {1, 1, 1},  1, 1,
-      {{0}, {0}, {0}, {8}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
-      {1, 1, 1},  2, 2,
-      {{5}, {6}, {5}, {0}},
-      {{0}, {5}, {11}, {0}}},
-
-   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  2, 2,
-      {{5}, {5}, {5}, {1}},
-      {{0}, {5}, {10}, {15}}},
-
-   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {0}},
-      {{0}, {8}, {16}, {24}}},
-
-   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
-      {4, 4, 1},  8, 8,
-      {{0}, {0}, {64}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_B4G4R4A4_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
-      {1, 1, 1},  2, 2,
-      {{4}, {4}, {4}, {4}},
-      {{0}, {4}, {8}, {12}}},
-
-   {SVGA3D_BC6H_TYPELESS, SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC6H_UF16, SVGA3DBLOCKDESC_BC6H_COMP_UF16,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC6H_SF16, SVGA3DBLOCKDESC_BC6H_COMP_SF16,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC7_TYPELESS, SVGA3DBLOCKDESC_BC7_COMP_TYPELESS,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC7_UNORM, SVGA3DBLOCKDESC_BC7_COMP_UNORM,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_BC7_UNORM_SRGB, SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB,
-      {4, 4, 1},  16, 16,
-      {{0}, {0}, {128}, {0}},
-      {{0}, {0}, {0}, {0}}},
-
-   {SVGA3D_AYUV, SVGA3DBLOCKDESC_AYUV,
-      {1, 1, 1},  4, 4,
-      {{8}, {8}, {8}, {8}},
-      {{0}, {8}, {16}, {24}}},
-};
-
-static inline u32 clamped_umul32(u32 a, u32 b)
-{
-	uint64_t tmp = (uint64_t) a*b;
-	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
-}
-
-/**
- * svga3dsurface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
- * given format.
- */
-static inline const struct svga3d_surface_desc *
-svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
-{
-	if (format < ARRAY_SIZE(svga3d_surface_descs))
-		return &svga3d_surface_descs[format];
-
-	return &svga3d_surface_descs[SVGA3D_FORMAT_INVALID];
-}
-
-/**
- * svga3dsurface_get_mip_size -  Given a base level size and the mip level,
- * compute the size of the mip level.
- */
-static inline surf_size_struct
-svga3dsurface_get_mip_size(surf_size_struct base_level, u32 mip_level)
-{
-	surf_size_struct size;
-
-	size.width = max_t(u32, base_level.width >> mip_level, 1);
-	size.height = max_t(u32, base_level.height >> mip_level, 1);
-	size.depth = max_t(u32, base_level.depth >> mip_level, 1);
-	size.pad64 = 0;
-
-	return size;
-}
-
-static inline void
-svga3dsurface_get_size_in_blocks(const struct svga3d_surface_desc *desc,
-				 const surf_size_struct *pixel_size,
-				 surf_size_struct *block_size)
-{
-	block_size->width = __KERNEL_DIV_ROUND_UP(pixel_size->width,
-						  desc->block_size.width);
-	block_size->height = __KERNEL_DIV_ROUND_UP(pixel_size->height,
-						   desc->block_size.height);
-	block_size->depth = __KERNEL_DIV_ROUND_UP(pixel_size->depth,
-						  desc->block_size.depth);
-}
-
-static inline bool
-svga3dsurface_is_planar_surface(const struct svga3d_surface_desc *desc)
-{
-	return (desc->block_desc & SVGA3DBLOCKDESC_PLANAR_YUV) != 0;
-}
-
-static inline u32
-svga3dsurface_calculate_pitch(const struct svga3d_surface_desc *desc,
-			      const surf_size_struct *size)
-{
-	u32 pitch;
-	surf_size_struct blocks;
-
-	svga3dsurface_get_size_in_blocks(desc, size, &blocks);
-
-	pitch = blocks.width * desc->pitch_bytes_per_block;
-
-	return pitch;
-}
-
-/**
- * svga3dsurface_get_image_buffer_size - Calculates image buffer size.
- *
- * Return the number of bytes of buffer space required to store one image of a
- * surface, optionally using the specified pitch.
- *
- * If pitch is zero, it is assumed that rows are tightly packed.
- *
- * This function is overflow-safe. If the result would have overflowed, instead
- * we return MAX_UINT32.
- */
-static inline u32
-svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
-				    const surf_size_struct *size,
-				    u32 pitch)
-{
-	surf_size_struct image_blocks;
-	u32 slice_size, total_size;
-
-	svga3dsurface_get_size_in_blocks(desc, size, &image_blocks);
-
-	if (svga3dsurface_is_planar_surface(desc)) {
-		total_size = clamped_umul32(image_blocks.width,
-					    image_blocks.height);
-		total_size = clamped_umul32(total_size, image_blocks.depth);
-		total_size = clamped_umul32(total_size, desc->bytes_per_block);
-		return total_size;
-	}
-
-	if (pitch == 0)
-		pitch = svga3dsurface_calculate_pitch(desc, size);
-
-	slice_size = clamped_umul32(image_blocks.height, pitch);
-	total_size = clamped_umul32(slice_size, image_blocks.depth);
-
-	return total_size;
-}
-
-/**
- * svga3dsurface_get_serialized_size - Get the serialized size for the image.
- */
-static inline u32
-svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
-				  surf_size_struct base_level_size,
-				  u32 num_mip_levels,
-				  u32 num_layers)
-{
-	const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format);
-	u32 total_size = 0;
-	u32 mip;
-
-	for (mip = 0; mip < num_mip_levels; mip++) {
-		surf_size_struct size =
-			svga3dsurface_get_mip_size(base_level_size, mip);
-		total_size += svga3dsurface_get_image_buffer_size(desc,
-								  &size, 0);
-	}
-
-	return total_size * num_layers;
-}
-
-/**
- * svga3dsurface_get_serialized_size_extended - Returns the number of bytes
- * required for a surface with given parameters. Support for sample count.
- */
-static inline u32
-svga3dsurface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
-					   surf_size_struct base_level_size,
-					   u32 num_mip_levels,
-					   u32 num_layers,
-					   u32 num_samples)
-{
-	uint64_t total_size =
-		svga3dsurface_get_serialized_size(format,
-						  base_level_size,
-						  num_mip_levels,
-						  num_layers);
-	total_size *= max_t(u32, 1, num_samples);
-
-	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
-}
-
-/**
- * svga3dsurface_get_pixel_offset - Compute the offset (in bytes) to a pixel
- * in an image (or volume).
- *
- * @width: The image width in pixels.
- * @height: The image height in pixels
- */
-static inline u32
-svga3dsurface_get_pixel_offset(SVGA3dSurfaceFormat format,
-			       u32 width, u32 height,
-			       u32 x, u32 y, u32 z)
-{
-	const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format);
-	const u32 bw = desc->block_size.width, bh = desc->block_size.height;
-	const u32 bd = desc->block_size.depth;
-	const u32 rowstride = __KERNEL_DIV_ROUND_UP(width, bw) *
-			      desc->bytes_per_block;
-	const u32 imgstride = __KERNEL_DIV_ROUND_UP(height, bh) * rowstride;
-	const u32 offset = (z / bd * imgstride +
-			    y / bh * rowstride +
-			    x / bw * desc->bytes_per_block);
-	return offset;
-}
-
-static inline u32
-svga3dsurface_get_image_offset(SVGA3dSurfaceFormat format,
-			       surf_size_struct baseLevelSize,
-			       u32 numMipLevels,
-			       u32 face,
-			       u32 mip)
-
-{
-	u32 offset;
-	u32 mipChainBytes;
-	u32 mipChainBytesToLevel;
-	u32 i;
-	const struct svga3d_surface_desc *desc;
-	surf_size_struct mipSize;
-	u32 bytes;
-
-	desc = svga3dsurface_get_desc(format);
-
-	mipChainBytes = 0;
-	mipChainBytesToLevel = 0;
-	for (i = 0; i < numMipLevels; i++) {
-		mipSize = svga3dsurface_get_mip_size(baseLevelSize, i);
-		bytes = svga3dsurface_get_image_buffer_size(desc, &mipSize, 0);
-		mipChainBytes += bytes;
-		if (i < mip)
-			mipChainBytesToLevel += bytes;
-	}
-
-	offset = mipChainBytes * face + mipChainBytesToLevel;
-
-	return offset;
-}
-
-
-/**
- * svga3dsurface_is_gb_screen_target_format - Is the specified format usable as
- *                                            a ScreenTarget?
- *                                            (with just the GBObjects cap-bit
- *                                             set)
- * @format: format to queried
- *
- * RETURNS:
- * true if queried format is valid for screen targets
- */
-static inline bool
-svga3dsurface_is_gb_screen_target_format(SVGA3dSurfaceFormat format)
-{
-	return (format == SVGA3D_X8R8G8B8 ||
-		format == SVGA3D_A8R8G8B8 ||
-		format == SVGA3D_R5G6B5   ||
-		format == SVGA3D_X1R5G5B5 ||
-		format == SVGA3D_A1R5G5B5 ||
-		format == SVGA3D_P8);
-}
-
-
-/**
- * svga3dsurface_is_dx_screen_target_format - Is the specified format usable as
- *                                            a ScreenTarget?
- *                                            (with DX10 enabled)
- *
- * @format: format to queried
- *
- * Results:
- * true if queried format is valid for screen targets
- */
-static inline bool
-svga3dsurface_is_dx_screen_target_format(SVGA3dSurfaceFormat format)
-{
-	return (format == SVGA3D_R8G8B8A8_UNORM ||
-		format == SVGA3D_B8G8R8A8_UNORM ||
-		format == SVGA3D_B8G8R8X8_UNORM);
-}
-
-
-/**
- * svga3dsurface_is_screen_target_format - Is the specified format usable as a
- *                                         ScreenTarget?
- *                                         (for some combination of caps)
- *
- * @format: format to queried
- *
- * Results:
- * true if queried format is valid for screen targets
- */
-static inline bool
-svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format)
-{
-	if (svga3dsurface_is_gb_screen_target_format(format)) {
-		return true;
-	}
-	return svga3dsurface_is_dx_screen_target_format(format);
-}
-
-/**
- * struct svga3dsurface_mip - Mimpmap level information
- * @bytes: Bytes required in the backing store of this mipmap level.
- * @img_stride: Byte stride per image.
- * @row_stride: Byte stride per block row.
- * @size: The size of the mipmap.
- */
-struct svga3dsurface_mip {
-	size_t bytes;
-	size_t img_stride;
-	size_t row_stride;
-	struct drm_vmw_size size;
-
-};
-
-/**
- * struct svga3dsurface_cache - Cached surface information
- * @desc: Pointer to the surface descriptor
- * @mip: Array of mipmap level information. Valid size is @num_mip_levels.
- * @mip_chain_bytes: Bytes required in the backing store for the whole chain
- * of mip levels.
- * @sheet_bytes: Bytes required in the backing store for a sheet
- * representing a single sample.
- * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in
- * a chain.
- * @num_layers: Number of slices in an array texture or number of faces in
- * a cubemap texture.
- */
-struct svga3dsurface_cache {
-	const struct svga3d_surface_desc *desc;
-	struct svga3dsurface_mip mip[DRM_VMW_MAX_MIP_LEVELS];
-	size_t mip_chain_bytes;
-	size_t sheet_bytes;
-	u32 num_mip_levels;
-	u32 num_layers;
-};
-
-/**
- * struct svga3dsurface_loc - Surface location
- * @sheet: The multisample sheet.
- * @sub_resource: Surface subresource. Defined as layer * num_mip_levels +
- * mip_level.
- * @x: X coordinate.
- * @y: Y coordinate.
- * @z: Z coordinate.
- */
-struct svga3dsurface_loc {
-	u32 sheet;
-	u32 sub_resource;
-	u32 x, y, z;
+	SVGA3dBlockDesc blockDesc;
+
+	SVGA3dSize blockSize;
+	uint32 bytesPerBlock;
+	uint32 pitchBytesPerBlock;
+
+	SVGA3dChannelDef bitDepth;
+	SVGA3dChannelDef bitOffset;
+} SVGA3dSurfaceDesc;
+
+STATIC_CONST SVGA3dSurfaceDesc g_SVGA3dSurfaceDescs[] = {
+	{ SVGA3D_FORMAT_INVALID,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 1, 1, 1 },
+	  0,
+	  0,
+	  { { 0 }, { 0 }, { 0 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_X8R8G8B8,
+	  SVGA3DBLOCKDESC_RGB_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_A8R8G8B8,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_R5G6B5,
+	  SVGA3DBLOCKDESC_RGB_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 5 }, { 6 }, { 5 }, { 0 } },
+	  { { 0 }, { 5 }, { 11 }, { 0 } } },
+
+	{ SVGA3D_X1R5G5B5,
+	  SVGA3DBLOCKDESC_RGB_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 5 }, { 5 }, { 5 }, { 0 } },
+	  { { 0 }, { 5 }, { 10 }, { 0 } } },
+
+	{ SVGA3D_A1R5G5B5,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 5 }, { 5 }, { 5 }, { 1 } },
+	  { { 0 }, { 5 }, { 10 }, { 15 } } },
+
+	{ SVGA3D_A4R4G4B4,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 4 }, { 4 }, { 4 }, { 4 } },
+	  { { 0 }, { 4 }, { 8 }, { 12 } } },
+
+	{ SVGA3D_Z_D32,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_Z_D16,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_Z_D24S8,
+	  SVGA3DBLOCKDESC_DS_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 24 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_Z_D15S1,
+	  SVGA3DBLOCKDESC_DS_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 1 }, { 15 }, { 0 } },
+	  { { 0 }, { 0 }, { 1 }, { 0 } } },
+
+	{ SVGA3D_LUMINANCE8,
+	  SVGA3DBLOCKDESC_L_UNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_LUMINANCE4_ALPHA4,
+	  SVGA3DBLOCKDESC_LA_UNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 4 }, { 4 } },
+	  { { 0 }, { 0 }, { 0 }, { 4 } } },
+
+	{ SVGA3D_LUMINANCE16,
+	  SVGA3DBLOCKDESC_L_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_LUMINANCE8_ALPHA8,
+	  SVGA3DBLOCKDESC_LA_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 8 }, { 8 } },
+	  { { 0 }, { 0 }, { 0 }, { 8 } } },
+
+	{ SVGA3D_DXT1,
+	  SVGA3DBLOCKDESC_BC1_COMP_UNORM,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_DXT2,
+	  SVGA3DBLOCKDESC_BC2_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_DXT3,
+	  SVGA3DBLOCKDESC_BC2_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_DXT4,
+	  SVGA3DBLOCKDESC_BC3_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_DXT5,
+	  SVGA3DBLOCKDESC_BC3_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BUMPU8V8,
+	  SVGA3DBLOCKDESC_UV_SNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BUMPL6V5U5,
+	  SVGA3DBLOCKDESC_UVL,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 6 }, { 5 }, { 5 }, { 0 } },
+	  { { 10 }, { 5 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BUMPX8L8V8U8,
+	  SVGA3DBLOCKDESC_UVL,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 16 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_FORMAT_DEAD1,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 1, 1, 1 },
+	  3,
+	  3,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 16 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_ARGB_S10E5,
+	  SVGA3DBLOCKDESC_RGBA_FP,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_ARGB_S23E8,
+	  SVGA3DBLOCKDESC_RGBA_FP,
+	  { 1, 1, 1 },
+	  16,
+	  16,
+	  { { 32 }, { 32 }, { 32 }, { 32 } },
+	  { { 64 }, { 32 }, { 0 }, { 96 } } },
+
+	{ SVGA3D_A2R10G10B10,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 0 }, { 10 }, { 20 }, { 30 } } },
+
+	{ SVGA3D_V8U8,
+	  SVGA3DBLOCKDESC_UV_SNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_Q8W8V8U8,
+	  SVGA3DBLOCKDESC_UVWQ_SNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_CxV8U8,
+	  SVGA3DBLOCKDESC_UVCX_SNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_X8L8V8U8,
+	  SVGA3DBLOCKDESC_UVL,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 16 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_A2W10V10U10,
+	  SVGA3DBLOCKDESC_UVWA,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 20 }, { 10 }, { 0 }, { 30 } } },
+
+	{ SVGA3D_ALPHA8,
+	  SVGA3DBLOCKDESC_A_UNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 0 }, { 8 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R_S10E5,
+	  SVGA3DBLOCKDESC_R_FP,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R_S23E8,
+	  SVGA3DBLOCKDESC_R_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_RG_S10E5,
+	  SVGA3DBLOCKDESC_RG_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_RG_S23E8,
+	  SVGA3DBLOCKDESC_RG_FP,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 32 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BUFFER,
+	  SVGA3DBLOCKDESC_BUFFER,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_Z_D24X8,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 24 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_V16U16,
+	  SVGA3DBLOCKDESC_UV_SNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_G16R16,
+	  SVGA3DBLOCKDESC_RG_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_A16B16G16R16,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_UYVY,
+	  SVGA3DBLOCKDESC_YUV,
+	  { 2, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_YUY2,
+	  SVGA3DBLOCKDESC_YUV,
+	  { 2, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 0 }, { 8 }, { 0 } },
+	  { { 8 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_NV12,
+	  SVGA3DBLOCKDESC_NV12,
+	  { 2, 2, 1 },
+	  6,
+	  2,
+	  { { 0 }, { 0 }, { 48 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_FORMAT_DEAD2,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_R32G32B32A32_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  16,
+	  16,
+	  { { 32 }, { 32 }, { 32 }, { 32 } },
+	  { { 64 }, { 32 }, { 0 }, { 96 } } },
+
+	{ SVGA3D_R32G32B32A32_UINT,
+	  SVGA3DBLOCKDESC_RGBA_UINT,
+	  { 1, 1, 1 },
+	  16,
+	  16,
+	  { { 32 }, { 32 }, { 32 }, { 32 } },
+	  { { 64 }, { 32 }, { 0 }, { 96 } } },
+
+	{ SVGA3D_R32G32B32A32_SINT,
+	  SVGA3DBLOCKDESC_RGBA_SINT,
+	  { 1, 1, 1 },
+	  16,
+	  16,
+	  { { 32 }, { 32 }, { 32 }, { 32 } },
+	  { { 64 }, { 32 }, { 0 }, { 96 } } },
+
+	{ SVGA3D_R32G32B32_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  12,
+	  12,
+	  { { 32 }, { 32 }, { 32 }, { 0 } },
+	  { { 64 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32B32_FLOAT,
+	  SVGA3DBLOCKDESC_RGB_FP,
+	  { 1, 1, 1 },
+	  12,
+	  12,
+	  { { 32 }, { 32 }, { 32 }, { 0 } },
+	  { { 64 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32B32_UINT,
+	  SVGA3DBLOCKDESC_RGB_UINT,
+	  { 1, 1, 1 },
+	  12,
+	  12,
+	  { { 32 }, { 32 }, { 32 }, { 0 } },
+	  { { 64 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32B32_SINT,
+	  SVGA3DBLOCKDESC_RGB_SINT,
+	  { 1, 1, 1 },
+	  12,
+	  12,
+	  { { 32 }, { 32 }, { 32 }, { 0 } },
+	  { { 64 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16G16B16A16_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R16G16B16A16_UINT,
+	  SVGA3DBLOCKDESC_RGBA_UINT,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R16G16B16A16_SNORM,
+	  SVGA3DBLOCKDESC_RGBA_SNORM,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R16G16B16A16_SINT,
+	  SVGA3DBLOCKDESC_RGBA_SINT,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R32G32_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 32 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32_UINT,
+	  SVGA3DBLOCKDESC_RG_UINT,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 32 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32_SINT,
+	  SVGA3DBLOCKDESC_RG_SINT,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 32 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G8X24_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 8 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_D32_FLOAT_S8X24_UINT,
+	  SVGA3DBLOCKDESC_DS,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 8 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32_FLOAT_X8X24,
+	  SVGA3DBLOCKDESC_R_FP,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_X32_G8X24_UINT,
+	  SVGA3DBLOCKDESC_G_UINT,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 8 }, { 0 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R10G10B10A2_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 20 }, { 10 }, { 0 }, { 30 } } },
+
+	{ SVGA3D_R10G10B10A2_UINT,
+	  SVGA3DBLOCKDESC_RGBA_UINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 20 }, { 10 }, { 0 }, { 30 } } },
+
+	{ SVGA3D_R11G11B10_FLOAT,
+	  SVGA3DBLOCKDESC_RGB_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 11 }, { 11 }, { 0 } },
+	  { { 22 }, { 11 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8B8A8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R8G8B8A8_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R8G8B8A8_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R8G8B8A8_UINT,
+	  SVGA3DBLOCKDESC_RGBA_UINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R8G8B8A8_SINT,
+	  SVGA3DBLOCKDESC_RGBA_SINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R16G16_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16G16_UINT,
+	  SVGA3DBLOCKDESC_RG_UINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16G16_SINT,
+	  SVGA3DBLOCKDESC_RG_SINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_D32_FLOAT,
+	  SVGA3DBLOCKDESC_DEPTH_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32_UINT,
+	  SVGA3DBLOCKDESC_R_UINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32_SINT,
+	  SVGA3DBLOCKDESC_R_SINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R24G8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 24 }, { 0 } },
+	  { { 0 }, { 24 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_D24_UNORM_S8_UINT,
+	  SVGA3DBLOCKDESC_DS_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 24 }, { 0 } },
+	  { { 0 }, { 24 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R24_UNORM_X8,
+	  SVGA3DBLOCKDESC_R_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 24 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_X24_G8_UINT,
+	  SVGA3DBLOCKDESC_G_UINT,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 0 }, { 0 } },
+	  { { 0 }, { 24 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8_UNORM,
+	  SVGA3DBLOCKDESC_RG_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8_UINT,
+	  SVGA3DBLOCKDESC_RG_UINT,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8_SINT,
+	  SVGA3DBLOCKDESC_RG_SINT,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_UNORM,
+	  SVGA3DBLOCKDESC_R_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_UINT,
+	  SVGA3DBLOCKDESC_R_UINT,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_SNORM,
+	  SVGA3DBLOCKDESC_R_SNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_SINT,
+	  SVGA3DBLOCKDESC_R_SINT,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8_UNORM,
+	  SVGA3DBLOCKDESC_R_UNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8_UINT,
+	  SVGA3DBLOCKDESC_R_UINT,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8_SNORM,
+	  SVGA3DBLOCKDESC_R_SNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8_SINT,
+	  SVGA3DBLOCKDESC_R_SINT,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_P8,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R9G9B9E5_SHAREDEXP,
+	  SVGA3DBLOCKDESC_RGB_EXP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 9 }, { 9 }, { 9 }, { 5 } },
+	  { { 18 }, { 9 }, { 0 }, { 27 } } },
+
+	{ SVGA3D_R8G8_B8G8_UNORM,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 2, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_G8R8_G8B8_UNORM,
+	  SVGA3DBLOCKDESC_NONE,
+	  { 2, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC1_TYPELESS,
+	  SVGA3DBLOCKDESC_BC1_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC1_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC2_TYPELESS,
+	  SVGA3DBLOCKDESC_BC2_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC2_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC3_TYPELESS,
+	  SVGA3DBLOCKDESC_BC3_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC3_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC4_TYPELESS,
+	  SVGA3DBLOCKDESC_BC4_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_ATI1,
+	  SVGA3DBLOCKDESC_BC4_COMP_UNORM,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC4_SNORM,
+	  SVGA3DBLOCKDESC_BC4_COMP_SNORM,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC5_TYPELESS,
+	  SVGA3DBLOCKDESC_BC5_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_ATI2,
+	  SVGA3DBLOCKDESC_BC5_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC5_SNORM,
+	  SVGA3DBLOCKDESC_BC5_COMP_SNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R10G10B10_XR_BIAS_A2_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 20 }, { 10 }, { 0 }, { 30 } } },
+
+	{ SVGA3D_B8G8R8A8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_B8G8R8A8_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_B8G8R8X8_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_B8G8R8X8_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_RGB_UNORM_SRGB,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_Z_DF16,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_Z_DF24,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 24 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_Z_D24S8_INT,
+	  SVGA3DBLOCKDESC_DS_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 8 }, { 24 }, { 0 } },
+	  { { 0 }, { 0 }, { 8 }, { 0 } } },
+
+	{ SVGA3D_YV12,
+	  SVGA3DBLOCKDESC_YV12,
+	  { 2, 2, 1 },
+	  6,
+	  2,
+	  { { 0 }, { 0 }, { 48 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32G32B32A32_FLOAT,
+	  SVGA3DBLOCKDESC_RGBA_FP,
+	  { 1, 1, 1 },
+	  16,
+	  16,
+	  { { 32 }, { 32 }, { 32 }, { 32 } },
+	  { { 64 }, { 32 }, { 0 }, { 96 } } },
+
+	{ SVGA3D_R16G16B16A16_FLOAT,
+	  SVGA3DBLOCKDESC_RGBA_FP,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R16G16B16A16_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 16 }, { 16 }, { 16 }, { 16 } },
+	  { { 32 }, { 16 }, { 0 }, { 48 } } },
+
+	{ SVGA3D_R32G32_FLOAT,
+	  SVGA3DBLOCKDESC_RG_FP,
+	  { 1, 1, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 32 }, { 32 }, { 0 } },
+	  { { 0 }, { 32 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R10G10B10A2_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 10 }, { 10 }, { 2 } },
+	  { { 20 }, { 10 }, { 0 }, { 30 } } },
+
+	{ SVGA3D_R8G8B8A8_SNORM,
+	  SVGA3DBLOCKDESC_RGBA_SNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 16 }, { 8 }, { 0 }, { 24 } } },
+
+	{ SVGA3D_R16G16_FLOAT,
+	  SVGA3DBLOCKDESC_RG_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16G16_UNORM,
+	  SVGA3DBLOCKDESC_RG_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16G16_SNORM,
+	  SVGA3DBLOCKDESC_RG_SNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 16 }, { 16 }, { 0 } },
+	  { { 0 }, { 16 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R32_FLOAT,
+	  SVGA3DBLOCKDESC_R_FP,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 0 }, { 0 }, { 32 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R8G8_SNORM,
+	  SVGA3DBLOCKDESC_RG_SNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_R16_FLOAT,
+	  SVGA3DBLOCKDESC_R_FP,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_D16_UNORM,
+	  SVGA3DBLOCKDESC_DEPTH_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 0 }, { 0 }, { 16 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_A8_UNORM,
+	  SVGA3DBLOCKDESC_A_UNORM,
+	  { 1, 1, 1 },
+	  1,
+	  1,
+	  { { 0 }, { 0 }, { 0 }, { 8 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC1_UNORM,
+	  SVGA3DBLOCKDESC_BC1_COMP_UNORM,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC2_UNORM,
+	  SVGA3DBLOCKDESC_BC2_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC3_UNORM,
+	  SVGA3DBLOCKDESC_BC3_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_B5G6R5_UNORM,
+	  SVGA3DBLOCKDESC_RGB_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 5 }, { 6 }, { 5 }, { 0 } },
+	  { { 0 }, { 5 }, { 11 }, { 0 } } },
+
+	{ SVGA3D_B5G5R5A1_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 5 }, { 5 }, { 5 }, { 1 } },
+	  { { 0 }, { 5 }, { 10 }, { 15 } } },
+
+	{ SVGA3D_B8G8R8A8_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_B8G8R8X8_UNORM,
+	  SVGA3DBLOCKDESC_RGB_UNORM,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 0 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_BC4_UNORM,
+	  SVGA3DBLOCKDESC_BC4_COMP_UNORM,
+	  { 4, 4, 1 },
+	  8,
+	  8,
+	  { { 0 }, { 0 }, { 64 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC5_UNORM,
+	  SVGA3DBLOCKDESC_BC5_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_B4G4R4A4_UNORM,
+	  SVGA3DBLOCKDESC_RGBA_UNORM,
+	  { 1, 1, 1 },
+	  2,
+	  2,
+	  { { 4 }, { 4 }, { 4 }, { 4 } },
+	  { { 0 }, { 4 }, { 8 }, { 12 } } },
+
+	{ SVGA3D_BC6H_TYPELESS,
+	  SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC6H_UF16,
+	  SVGA3DBLOCKDESC_BC6H_COMP_UF16,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC6H_SF16,
+	  SVGA3DBLOCKDESC_BC6H_COMP_SF16,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC7_TYPELESS,
+	  SVGA3DBLOCKDESC_BC7_COMP_TYPELESS,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC7_UNORM,
+	  SVGA3DBLOCKDESC_BC7_COMP_UNORM,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_BC7_UNORM_SRGB,
+	  SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB,
+	  { 4, 4, 1 },
+	  16,
+	  16,
+	  { { 0 }, { 0 }, { 128 }, { 0 } },
+	  { { 0 }, { 0 }, { 0 }, { 0 } } },
+
+	{ SVGA3D_AYUV,
+	  SVGA3DBLOCKDESC_AYUV,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 8 }, { 8 }, { 8 }, { 8 } },
+	  { { 0 }, { 8 }, { 16 }, { 24 } } },
+
+	{ SVGA3D_R11G11B10_TYPELESS,
+	  SVGA3DBLOCKDESC_TYPELESS,
+	  { 1, 1, 1 },
+	  4,
+	  4,
+	  { { 10 }, { 11 }, { 11 }, { 0 } },
+	  { { 22 }, { 11 }, { 0 }, { 0 } } },
 };
 
-/**
- * svga3dsurface_subres - Compute the subresource from layer and mipmap.
- * @cache: Surface layout data.
- * @mip_level: The mipmap level.
- * @layer: The surface layer (face or array slice).
- *
- * Return: The subresource.
- */
-static inline u32 svga3dsurface_subres(const struct svga3dsurface_cache *cache,
-				       u32 mip_level, u32 layer)
-{
-	return cache->num_mip_levels * layer + mip_level;
-}
-
-/**
- * svga3dsurface_setup_cache - Build a surface cache entry
- * @size: The surface base level dimensions.
- * @format: The surface format.
- * @num_mip_levels: Number of mipmap levels.
- * @num_layers: Number of layers.
- * @cache: Pointer to a struct svga3dsurface_cach object to be filled in.
- *
- * Return: Zero on success, -EINVAL on invalid surface layout.
- */
-static inline int svga3dsurface_setup_cache(const struct drm_vmw_size *size,
-					    SVGA3dSurfaceFormat format,
-					    u32 num_mip_levels,
-					    u32 num_layers,
-					    u32 num_samples,
-					    struct svga3dsurface_cache *cache)
-{
-	const struct svga3d_surface_desc *desc;
-	u32 i;
-
-	memset(cache, 0, sizeof(*cache));
-	cache->desc = desc = svga3dsurface_get_desc(format);
-	cache->num_mip_levels = num_mip_levels;
-	cache->num_layers = num_layers;
-	for (i = 0; i < cache->num_mip_levels; i++) {
-		struct svga3dsurface_mip *mip = &cache->mip[i];
-
-		mip->size = svga3dsurface_get_mip_size(*size, i);
-		mip->bytes = svga3dsurface_get_image_buffer_size
-			(desc, &mip->size, 0);
-		mip->row_stride =
-			__KERNEL_DIV_ROUND_UP(mip->size.width,
-					      desc->block_size.width) *
-			desc->bytes_per_block * num_samples;
-		if (!mip->row_stride)
-			goto invalid_dim;
-
-		mip->img_stride =
-			__KERNEL_DIV_ROUND_UP(mip->size.height,
-					      desc->block_size.height) *
-			mip->row_stride;
-		if (!mip->img_stride)
-			goto invalid_dim;
-
-		cache->mip_chain_bytes += mip->bytes;
-	}
-	cache->sheet_bytes = cache->mip_chain_bytes * num_layers;
-	if (!cache->sheet_bytes)
-		goto invalid_dim;
-
-	return 0;
-
-invalid_dim:
-	VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n");
-	return -EINVAL;
-}
-
-/**
- * svga3dsurface_get_loc - Get a surface location from an offset into the
- * backing store
- * @cache: Surface layout data.
- * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
- * @offset: Offset into the surface backing store.
- */
-static inline void
-svga3dsurface_get_loc(const struct svga3dsurface_cache *cache,
-		      struct svga3dsurface_loc *loc,
-		      size_t offset)
-{
-	const struct svga3dsurface_mip *mip = &cache->mip[0];
-	const struct svga3d_surface_desc *desc = cache->desc;
-	u32 layer;
-	int i;
-
-	loc->sheet = offset / cache->sheet_bytes;
-	offset -= loc->sheet * cache->sheet_bytes;
-
-	layer = offset / cache->mip_chain_bytes;
-	offset -= layer * cache->mip_chain_bytes;
-	for (i = 0; i < cache->num_mip_levels; ++i, ++mip) {
-		if (mip->bytes > offset)
-			break;
-		offset -= mip->bytes;
-	}
-
-	loc->sub_resource = svga3dsurface_subres(cache, i, layer);
-	loc->z = offset / mip->img_stride;
-	offset -= loc->z * mip->img_stride;
-	loc->z *= desc->block_size.depth;
-	loc->y = offset / mip->row_stride;
-	offset -= loc->y * mip->row_stride;
-	loc->y *= desc->block_size.height;
-	loc->x = offset / desc->bytes_per_block;
-	loc->x *= desc->block_size.width;
-}
-
-/**
- * svga3dsurface_inc_loc - Clamp increment a surface location with one block
- * size
- * in each dimension.
- * @loc: Pointer to a struct svga3dsurface_loc to be incremented.
- *
- * When computing the size of a range as size = end - start, the range does not
- * include the end element. However a location representing the last byte
- * of a touched region in the backing store *is* included in the range.
- * This function modifies such a location to match the end definition
- * given as start + size which is the one used in a SVGA3dBox.
- */
-static inline void
-svga3dsurface_inc_loc(const struct svga3dsurface_cache *cache,
-		      struct svga3dsurface_loc *loc)
-{
-	const struct svga3d_surface_desc *desc = cache->desc;
-	u32 mip = loc->sub_resource % cache->num_mip_levels;
-	const struct drm_vmw_size *size = &cache->mip[mip].size;
-
-	loc->sub_resource++;
-	loc->x += desc->block_size.width;
-	if (loc->x > size->width)
-		loc->x = size->width;
-	loc->y += desc->block_size.height;
-	if (loc->y > size->height)
-		loc->y = size->height;
-	loc->z += desc->block_size.depth;
-	if (loc->z > size->depth)
-		loc->z = size->depth;
-}
-
-/**
- * svga3dsurface_min_loc - The start location in a subresource
- * @cache: Surface layout data.
- * @sub_resource: The subresource.
- * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
- */
-static inline void
-svga3dsurface_min_loc(const struct svga3dsurface_cache *cache,
-		      u32 sub_resource,
-		      struct svga3dsurface_loc *loc)
-{
-	loc->sheet = 0;
-	loc->sub_resource = sub_resource;
-	loc->x = loc->y = loc->z = 0;
-}
-
-/**
- * svga3dsurface_min_loc - The end location in a subresource
- * @cache: Surface layout data.
- * @sub_resource: The subresource.
- * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
- *
- * Following the end definition given in svga3dsurface_inc_loc(),
- * Compute the end location of a surface subresource.
- */
-static inline void
-svga3dsurface_max_loc(const struct svga3dsurface_cache *cache,
-		      u32 sub_resource,
-		      struct svga3dsurface_loc *loc)
-{
-	const struct drm_vmw_size *size;
-	u32 mip;
-
-	loc->sheet = 0;
-	loc->sub_resource = sub_resource + 1;
-	mip = sub_resource % cache->num_mip_levels;
-	size = &cache->mip[mip].size;
-	loc->x = size->width;
-	loc->y = size->height;
-	loc->z = size->depth;
+#ifdef __cplusplus
 }
+#endif
 
-#endif /* _SVGA3D_SURFACEDEFS_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
index 77e338a65791..70b88ee16cf6 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2015 VMware, Inc.
+ * Copyright 2012-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -27,1974 +27,1530 @@
 /*
  * svga3d_types.h --
  *
- *       SVGA 3d hardware definitions for basic types
+ *    SVGA 3d hardware definitions for basic types
  */
 
+
+
 #ifndef _SVGA3D_TYPES_H_
 #define _SVGA3D_TYPES_H_
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
-#define INCLUDE_ALLOW_VMCORE
-
-#include "includeCheck.h"
+#include "vm_basic_types.h"
 
-/*
- * Generic Types
- */
+#define SVGA3D_INVALID_ID ((uint32)-1)
 
-#define SVGA3D_INVALID_ID         ((uint32)-1)
+#define SVGA3D_RESOURCE_TYPE_MIN 1
+#define SVGA3D_RESOURCE_BUFFER 1
+#define SVGA3D_RESOURCE_TEXTURE1D 2
+#define SVGA3D_RESOURCE_TEXTURE2D 3
+#define SVGA3D_RESOURCE_TEXTURE3D 4
+#define SVGA3D_RESOURCE_TEXTURECUBE 5
+#define SVGA3D_RESOURCE_TYPE_DX10_MAX 6
+#define SVGA3D_RESOURCE_BUFFEREX 6
+#define SVGA3D_RESOURCE_TYPE_MAX 7
+typedef uint32 SVGA3dResourceType;
 
-typedef uint8 SVGABool8;   /* 8-bit Bool definition */
-typedef uint32 SVGA3dBool; /* 32-bit Bool definition */
-typedef uint32 SVGA3dColor; /* a, r, g, b */
+typedef uint8 SVGABool8;
+typedef uint32 SVGA3dBool;
+typedef uint32 SVGA3dColor;
 
 typedef uint32 SVGA3dSurfaceId;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 numerator;
-   uint32 denominator;
-}
-#include "vmware_pack_end.h"
-SVGA3dFraction64;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCopyRect {
-   uint32               x;
-   uint32               y;
-   uint32               w;
-   uint32               h;
-   uint32               srcx;
-   uint32               srcy;
-}
-#include "vmware_pack_end.h"
-SVGA3dCopyRect;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCopyBox {
-   uint32               x;
-   uint32               y;
-   uint32               z;
-   uint32               w;
-   uint32               h;
-   uint32               d;
-   uint32               srcx;
-   uint32               srcy;
-   uint32               srcz;
-}
-#include "vmware_pack_end.h"
-SVGA3dCopyBox;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dRect {
-   uint32               x;
-   uint32               y;
-   uint32               w;
-   uint32               h;
-}
-#include "vmware_pack_end.h"
-SVGA3dRect;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               x;
-   uint32               y;
-   uint32               z;
-   uint32               w;
-   uint32               h;
-   uint32               d;
-}
-#include "vmware_pack_end.h"
-SVGA3dBox;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   int32                x;
-   int32                y;
-   int32                z;
-   int32                w;
-   int32                h;
-   int32                d;
-}
-#include "vmware_pack_end.h"
-SVGA3dSignedBox;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               x;
-   uint32               y;
-   uint32               z;
-}
-#include "vmware_pack_end.h"
-SVGA3dPoint;
+#pragma pack(push, 1)
+typedef struct {
+	uint32 numerator;
+	uint32 denominator;
+} SVGA3dFraction64;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCopyRect {
+	uint32 x;
+	uint32 y;
+	uint32 w;
+	uint32 h;
+	uint32 srcx;
+	uint32 srcy;
+} SVGA3dCopyRect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dCopyBox {
+	uint32 x;
+	uint32 y;
+	uint32 z;
+	uint32 w;
+	uint32 h;
+	uint32 d;
+	uint32 srcx;
+	uint32 srcy;
+	uint32 srcz;
+} SVGA3dCopyBox;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dRect {
+	uint32 x;
+	uint32 y;
+	uint32 w;
+	uint32 h;
+} SVGA3dRect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 x;
+	uint32 y;
+	uint32 z;
+	uint32 w;
+	uint32 h;
+	uint32 d;
+} SVGA3dBox;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	int32 x;
+	int32 y;
+	int32 z;
+	int32 w;
+	int32 h;
+	int32 d;
+} SVGA3dSignedBox;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 x;
+	uint32 y;
+	uint32 z;
+} SVGA3dPoint;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef union {
+	struct {
+		float r;
+		float g;
+		float b;
+		float a;
+	};
+
+	float value[4];
+} SVGA3dRGBAFloat;
+#pragma pack(pop)
 
-/*
- * Surface formats.
- */
 typedef enum SVGA3dSurfaceFormat {
-   SVGA3D_FORMAT_INVALID               = 0,
-
-   SVGA3D_X8R8G8B8                     = 1,
-   SVGA3D_FORMAT_MIN                   = 1,
-
-   SVGA3D_A8R8G8B8                     = 2,
-
-   SVGA3D_R5G6B5                       = 3,
-   SVGA3D_X1R5G5B5                     = 4,
-   SVGA3D_A1R5G5B5                     = 5,
-   SVGA3D_A4R4G4B4                     = 6,
-
-   SVGA3D_Z_D32                        = 7,
-   SVGA3D_Z_D16                        = 8,
-   SVGA3D_Z_D24S8                      = 9,
-   SVGA3D_Z_D15S1                      = 10,
-
-   SVGA3D_LUMINANCE8                   = 11,
-   SVGA3D_LUMINANCE4_ALPHA4            = 12,
-   SVGA3D_LUMINANCE16                  = 13,
-   SVGA3D_LUMINANCE8_ALPHA8            = 14,
-
-   SVGA3D_DXT1                         = 15,
-   SVGA3D_DXT2                         = 16,
-   SVGA3D_DXT3                         = 17,
-   SVGA3D_DXT4                         = 18,
-   SVGA3D_DXT5                         = 19,
-
-   SVGA3D_BUMPU8V8                     = 20,
-   SVGA3D_BUMPL6V5U5                   = 21,
-   SVGA3D_BUMPX8L8V8U8                 = 22,
-   SVGA3D_FORMAT_DEAD1                 = 23,
-
-   SVGA3D_ARGB_S10E5                   = 24,   /* 16-bit floating-point ARGB */
-   SVGA3D_ARGB_S23E8                   = 25,   /* 32-bit floating-point ARGB */
-
-   SVGA3D_A2R10G10B10                  = 26,
-
-   /* signed formats */
-   SVGA3D_V8U8                         = 27,
-   SVGA3D_Q8W8V8U8                     = 28,
-   SVGA3D_CxV8U8                       = 29,
-
-   /* mixed formats */
-   SVGA3D_X8L8V8U8                     = 30,
-   SVGA3D_A2W10V10U10                  = 31,
-
-   SVGA3D_ALPHA8                       = 32,
-
-   /* Single- and dual-component floating point formats */
-   SVGA3D_R_S10E5                      = 33,
-   SVGA3D_R_S23E8                      = 34,
-   SVGA3D_RG_S10E5                     = 35,
-   SVGA3D_RG_S23E8                     = 36,
-
-   SVGA3D_BUFFER                       = 37,
-
-   SVGA3D_Z_D24X8                      = 38,
-
-   SVGA3D_V16U16                       = 39,
-
-   SVGA3D_G16R16                       = 40,
-   SVGA3D_A16B16G16R16                 = 41,
-
-   /* Packed Video formats */
-   SVGA3D_UYVY                         = 42,
-   SVGA3D_YUY2                         = 43,
-
-   /* Planar video formats */
-   SVGA3D_NV12                         = 44,
-
-   SVGA3D_FORMAT_DEAD2                 = 45,
-
-   SVGA3D_R32G32B32A32_TYPELESS        = 46,
-   SVGA3D_R32G32B32A32_UINT            = 47,
-   SVGA3D_R32G32B32A32_SINT            = 48,
-   SVGA3D_R32G32B32_TYPELESS           = 49,
-   SVGA3D_R32G32B32_FLOAT              = 50,
-   SVGA3D_R32G32B32_UINT               = 51,
-   SVGA3D_R32G32B32_SINT               = 52,
-   SVGA3D_R16G16B16A16_TYPELESS        = 53,
-   SVGA3D_R16G16B16A16_UINT            = 54,
-   SVGA3D_R16G16B16A16_SNORM           = 55,
-   SVGA3D_R16G16B16A16_SINT            = 56,
-   SVGA3D_R32G32_TYPELESS              = 57,
-   SVGA3D_R32G32_UINT                  = 58,
-   SVGA3D_R32G32_SINT                  = 59,
-   SVGA3D_R32G8X24_TYPELESS            = 60,
-   SVGA3D_D32_FLOAT_S8X24_UINT         = 61,
-   SVGA3D_R32_FLOAT_X8X24              = 62,
-   SVGA3D_X32_G8X24_UINT               = 63,
-   SVGA3D_R10G10B10A2_TYPELESS         = 64,
-   SVGA3D_R10G10B10A2_UINT             = 65,
-   SVGA3D_R11G11B10_FLOAT              = 66,
-   SVGA3D_R8G8B8A8_TYPELESS            = 67,
-   SVGA3D_R8G8B8A8_UNORM               = 68,
-   SVGA3D_R8G8B8A8_UNORM_SRGB          = 69,
-   SVGA3D_R8G8B8A8_UINT                = 70,
-   SVGA3D_R8G8B8A8_SINT                = 71,
-   SVGA3D_R16G16_TYPELESS              = 72,
-   SVGA3D_R16G16_UINT                  = 73,
-   SVGA3D_R16G16_SINT                  = 74,
-   SVGA3D_R32_TYPELESS                 = 75,
-   SVGA3D_D32_FLOAT                    = 76,
-   SVGA3D_R32_UINT                     = 77,
-   SVGA3D_R32_SINT                     = 78,
-   SVGA3D_R24G8_TYPELESS               = 79,
-   SVGA3D_D24_UNORM_S8_UINT            = 80,
-   SVGA3D_R24_UNORM_X8                 = 81,
-   SVGA3D_X24_G8_UINT                  = 82,
-   SVGA3D_R8G8_TYPELESS                = 83,
-   SVGA3D_R8G8_UNORM                   = 84,
-   SVGA3D_R8G8_UINT                    = 85,
-   SVGA3D_R8G8_SINT                    = 86,
-   SVGA3D_R16_TYPELESS                 = 87,
-   SVGA3D_R16_UNORM                    = 88,
-   SVGA3D_R16_UINT                     = 89,
-   SVGA3D_R16_SNORM                    = 90,
-   SVGA3D_R16_SINT                     = 91,
-   SVGA3D_R8_TYPELESS                  = 92,
-   SVGA3D_R8_UNORM                     = 93,
-   SVGA3D_R8_UINT                      = 94,
-   SVGA3D_R8_SNORM                     = 95,
-   SVGA3D_R8_SINT                      = 96,
-   SVGA3D_P8                           = 97,
-   SVGA3D_R9G9B9E5_SHAREDEXP           = 98,
-   SVGA3D_R8G8_B8G8_UNORM              = 99,
-   SVGA3D_G8R8_G8B8_UNORM              = 100,
-   SVGA3D_BC1_TYPELESS                 = 101,
-   SVGA3D_BC1_UNORM_SRGB               = 102,
-   SVGA3D_BC2_TYPELESS                 = 103,
-   SVGA3D_BC2_UNORM_SRGB               = 104,
-   SVGA3D_BC3_TYPELESS                 = 105,
-   SVGA3D_BC3_UNORM_SRGB               = 106,
-   SVGA3D_BC4_TYPELESS                 = 107,
-   SVGA3D_ATI1                         = 108,   /* DX9-specific BC4_UNORM */
-   SVGA3D_BC4_SNORM                    = 109,
-   SVGA3D_BC5_TYPELESS                 = 110,
-   SVGA3D_ATI2                         = 111,   /* DX9-specific BC5_UNORM */
-   SVGA3D_BC5_SNORM                    = 112,
-   SVGA3D_R10G10B10_XR_BIAS_A2_UNORM   = 113,
-   SVGA3D_B8G8R8A8_TYPELESS            = 114,
-   SVGA3D_B8G8R8A8_UNORM_SRGB          = 115,
-   SVGA3D_B8G8R8X8_TYPELESS            = 116,
-   SVGA3D_B8G8R8X8_UNORM_SRGB          = 117,
-
-   /* Advanced depth formats. */
-   SVGA3D_Z_DF16                       = 118,
-   SVGA3D_Z_DF24                       = 119,
-   SVGA3D_Z_D24S8_INT                  = 120,
-
-   /* Planar video formats. */
-   SVGA3D_YV12                         = 121,
-
-   SVGA3D_R32G32B32A32_FLOAT           = 122,
-   SVGA3D_R16G16B16A16_FLOAT           = 123,
-   SVGA3D_R16G16B16A16_UNORM           = 124,
-   SVGA3D_R32G32_FLOAT                 = 125,
-   SVGA3D_R10G10B10A2_UNORM            = 126,
-   SVGA3D_R8G8B8A8_SNORM               = 127,
-   SVGA3D_R16G16_FLOAT                 = 128,
-   SVGA3D_R16G16_UNORM                 = 129,
-   SVGA3D_R16G16_SNORM                 = 130,
-   SVGA3D_R32_FLOAT                    = 131,
-   SVGA3D_R8G8_SNORM                   = 132,
-   SVGA3D_R16_FLOAT                    = 133,
-   SVGA3D_D16_UNORM                    = 134,
-   SVGA3D_A8_UNORM                     = 135,
-   SVGA3D_BC1_UNORM                    = 136,
-   SVGA3D_BC2_UNORM                    = 137,
-   SVGA3D_BC3_UNORM                    = 138,
-   SVGA3D_B5G6R5_UNORM                 = 139,
-   SVGA3D_B5G5R5A1_UNORM               = 140,
-   SVGA3D_B8G8R8A8_UNORM               = 141,
-   SVGA3D_B8G8R8X8_UNORM               = 142,
-   SVGA3D_BC4_UNORM                    = 143,
-   SVGA3D_BC5_UNORM                    = 144,
-   SVGA3D_B4G4R4A4_UNORM               = 145,
-   
-   /* DX11 compressed formats */
-   SVGA3D_BC6H_TYPELESS                = 146,
-   SVGA3D_BC6H_UF16                    = 147,
-   SVGA3D_BC6H_SF16                    = 148,
-   SVGA3D_BC7_TYPELESS                 = 149,
-   SVGA3D_BC7_UNORM                    = 150,
-   SVGA3D_BC7_UNORM_SRGB               = 151,
-
-   /* Video format with alpha */
-   SVGA3D_AYUV                         = 152,
-
-   SVGA3D_FORMAT_MAX
+	SVGA3D_FORMAT_INVALID = 0,
+
+	SVGA3D_X8R8G8B8 = 1,
+	SVGA3D_FORMAT_MIN = 1,
+
+	SVGA3D_A8R8G8B8 = 2,
+
+	SVGA3D_R5G6B5 = 3,
+	SVGA3D_X1R5G5B5 = 4,
+	SVGA3D_A1R5G5B5 = 5,
+	SVGA3D_A4R4G4B4 = 6,
+
+	SVGA3D_Z_D32 = 7,
+	SVGA3D_Z_D16 = 8,
+	SVGA3D_Z_D24S8 = 9,
+	SVGA3D_Z_D15S1 = 10,
+
+	SVGA3D_LUMINANCE8 = 11,
+	SVGA3D_LUMINANCE4_ALPHA4 = 12,
+	SVGA3D_LUMINANCE16 = 13,
+	SVGA3D_LUMINANCE8_ALPHA8 = 14,
+
+	SVGA3D_DXT1 = 15,
+	SVGA3D_DXT2 = 16,
+	SVGA3D_DXT3 = 17,
+	SVGA3D_DXT4 = 18,
+	SVGA3D_DXT5 = 19,
+
+	SVGA3D_BUMPU8V8 = 20,
+	SVGA3D_BUMPL6V5U5 = 21,
+	SVGA3D_BUMPX8L8V8U8 = 22,
+	SVGA3D_FORMAT_DEAD1 = 23,
+
+	SVGA3D_ARGB_S10E5 = 24,
+	SVGA3D_ARGB_S23E8 = 25,
+
+	SVGA3D_A2R10G10B10 = 26,
+
+	SVGA3D_V8U8 = 27,
+	SVGA3D_Q8W8V8U8 = 28,
+	SVGA3D_CxV8U8 = 29,
+
+	SVGA3D_X8L8V8U8 = 30,
+	SVGA3D_A2W10V10U10 = 31,
+
+	SVGA3D_ALPHA8 = 32,
+
+	SVGA3D_R_S10E5 = 33,
+	SVGA3D_R_S23E8 = 34,
+	SVGA3D_RG_S10E5 = 35,
+	SVGA3D_RG_S23E8 = 36,
+
+	SVGA3D_BUFFER = 37,
+
+	SVGA3D_Z_D24X8 = 38,
+
+	SVGA3D_V16U16 = 39,
+
+	SVGA3D_G16R16 = 40,
+	SVGA3D_A16B16G16R16 = 41,
+
+	SVGA3D_UYVY = 42,
+	SVGA3D_YUY2 = 43,
+
+	SVGA3D_NV12 = 44,
+
+	SVGA3D_FORMAT_DEAD2 = 45,
+
+	SVGA3D_R32G32B32A32_TYPELESS = 46,
+	SVGA3D_R32G32B32A32_UINT = 47,
+	SVGA3D_R32G32B32A32_SINT = 48,
+	SVGA3D_R32G32B32_TYPELESS = 49,
+	SVGA3D_R32G32B32_FLOAT = 50,
+	SVGA3D_R32G32B32_UINT = 51,
+	SVGA3D_R32G32B32_SINT = 52,
+	SVGA3D_R16G16B16A16_TYPELESS = 53,
+	SVGA3D_R16G16B16A16_UINT = 54,
+	SVGA3D_R16G16B16A16_SNORM = 55,
+	SVGA3D_R16G16B16A16_SINT = 56,
+	SVGA3D_R32G32_TYPELESS = 57,
+	SVGA3D_R32G32_UINT = 58,
+	SVGA3D_R32G32_SINT = 59,
+	SVGA3D_R32G8X24_TYPELESS = 60,
+	SVGA3D_D32_FLOAT_S8X24_UINT = 61,
+	SVGA3D_R32_FLOAT_X8X24 = 62,
+	SVGA3D_X32_G8X24_UINT = 63,
+	SVGA3D_R10G10B10A2_TYPELESS = 64,
+	SVGA3D_R10G10B10A2_UINT = 65,
+	SVGA3D_R11G11B10_FLOAT = 66,
+	SVGA3D_R8G8B8A8_TYPELESS = 67,
+	SVGA3D_R8G8B8A8_UNORM = 68,
+	SVGA3D_R8G8B8A8_UNORM_SRGB = 69,
+	SVGA3D_R8G8B8A8_UINT = 70,
+	SVGA3D_R8G8B8A8_SINT = 71,
+	SVGA3D_R16G16_TYPELESS = 72,
+	SVGA3D_R16G16_UINT = 73,
+	SVGA3D_R16G16_SINT = 74,
+	SVGA3D_R32_TYPELESS = 75,
+	SVGA3D_D32_FLOAT = 76,
+	SVGA3D_R32_UINT = 77,
+	SVGA3D_R32_SINT = 78,
+	SVGA3D_R24G8_TYPELESS = 79,
+	SVGA3D_D24_UNORM_S8_UINT = 80,
+	SVGA3D_R24_UNORM_X8 = 81,
+	SVGA3D_X24_G8_UINT = 82,
+	SVGA3D_R8G8_TYPELESS = 83,
+	SVGA3D_R8G8_UNORM = 84,
+	SVGA3D_R8G8_UINT = 85,
+	SVGA3D_R8G8_SINT = 86,
+	SVGA3D_R16_TYPELESS = 87,
+	SVGA3D_R16_UNORM = 88,
+	SVGA3D_R16_UINT = 89,
+	SVGA3D_R16_SNORM = 90,
+	SVGA3D_R16_SINT = 91,
+	SVGA3D_R8_TYPELESS = 92,
+	SVGA3D_R8_UNORM = 93,
+	SVGA3D_R8_UINT = 94,
+	SVGA3D_R8_SNORM = 95,
+	SVGA3D_R8_SINT = 96,
+	SVGA3D_P8 = 97,
+	SVGA3D_R9G9B9E5_SHAREDEXP = 98,
+	SVGA3D_R8G8_B8G8_UNORM = 99,
+	SVGA3D_G8R8_G8B8_UNORM = 100,
+	SVGA3D_BC1_TYPELESS = 101,
+	SVGA3D_BC1_UNORM_SRGB = 102,
+	SVGA3D_BC2_TYPELESS = 103,
+	SVGA3D_BC2_UNORM_SRGB = 104,
+	SVGA3D_BC3_TYPELESS = 105,
+	SVGA3D_BC3_UNORM_SRGB = 106,
+	SVGA3D_BC4_TYPELESS = 107,
+	SVGA3D_ATI1 = 108,
+	SVGA3D_BC4_SNORM = 109,
+	SVGA3D_BC5_TYPELESS = 110,
+	SVGA3D_ATI2 = 111,
+	SVGA3D_BC5_SNORM = 112,
+	SVGA3D_R10G10B10_XR_BIAS_A2_UNORM = 113,
+	SVGA3D_B8G8R8A8_TYPELESS = 114,
+	SVGA3D_B8G8R8A8_UNORM_SRGB = 115,
+	SVGA3D_B8G8R8X8_TYPELESS = 116,
+	SVGA3D_B8G8R8X8_UNORM_SRGB = 117,
+
+	SVGA3D_Z_DF16 = 118,
+	SVGA3D_Z_DF24 = 119,
+	SVGA3D_Z_D24S8_INT = 120,
+
+	SVGA3D_YV12 = 121,
+
+	SVGA3D_R32G32B32A32_FLOAT = 122,
+	SVGA3D_R16G16B16A16_FLOAT = 123,
+	SVGA3D_R16G16B16A16_UNORM = 124,
+	SVGA3D_R32G32_FLOAT = 125,
+	SVGA3D_R10G10B10A2_UNORM = 126,
+	SVGA3D_R8G8B8A8_SNORM = 127,
+	SVGA3D_R16G16_FLOAT = 128,
+	SVGA3D_R16G16_UNORM = 129,
+	SVGA3D_R16G16_SNORM = 130,
+	SVGA3D_R32_FLOAT = 131,
+	SVGA3D_R8G8_SNORM = 132,
+	SVGA3D_R16_FLOAT = 133,
+	SVGA3D_D16_UNORM = 134,
+	SVGA3D_A8_UNORM = 135,
+	SVGA3D_BC1_UNORM = 136,
+	SVGA3D_BC2_UNORM = 137,
+	SVGA3D_BC3_UNORM = 138,
+	SVGA3D_B5G6R5_UNORM = 139,
+	SVGA3D_B5G5R5A1_UNORM = 140,
+	SVGA3D_B8G8R8A8_UNORM = 141,
+	SVGA3D_B8G8R8X8_UNORM = 142,
+	SVGA3D_BC4_UNORM = 143,
+	SVGA3D_BC5_UNORM = 144,
+	SVGA3D_B4G4R4A4_UNORM = 145,
+
+	SVGA3D_BC6H_TYPELESS = 146,
+	SVGA3D_BC6H_UF16 = 147,
+	SVGA3D_BC6H_SF16 = 148,
+	SVGA3D_BC7_TYPELESS = 149,
+	SVGA3D_BC7_UNORM = 150,
+	SVGA3D_BC7_UNORM_SRGB = 151,
+
+	SVGA3D_AYUV = 152,
+
+	SVGA3D_R11G11B10_TYPELESS = 153,
+
+	SVGA3D_FORMAT_MAX
 } SVGA3dSurfaceFormat;
 
-/*
- * SVGA3d Surface Flags --
- */
-#define SVGA3D_SURFACE_CUBEMAP                (1 << 0)
+#define SVGA3D_SURFACE_CUBEMAP (1 << 0)
 
-/*
- * HINT flags are not enforced by the device but are useful for
- * performance.
- */
-#define SVGA3D_SURFACE_HINT_STATIC            (CONST64U(1) << 1)
-#define SVGA3D_SURFACE_HINT_DYNAMIC           (CONST64U(1) << 2)
-#define SVGA3D_SURFACE_HINT_INDEXBUFFER       (CONST64U(1) << 3)
-#define SVGA3D_SURFACE_HINT_VERTEXBUFFER      (CONST64U(1) << 4)
-#define SVGA3D_SURFACE_HINT_TEXTURE           (CONST64U(1) << 5)
-#define SVGA3D_SURFACE_HINT_RENDERTARGET      (CONST64U(1) << 6)
-#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL      (CONST64U(1) << 7)
-#define SVGA3D_SURFACE_HINT_WRITEONLY         (CONST64U(1) << 8)
-#define SVGA3D_SURFACE_DEAD2                  (CONST64U(1) << 9)
-#define SVGA3D_SURFACE_AUTOGENMIPMAPS         (CONST64U(1) << 10)
-
-#define SVGA3D_SURFACE_DEAD1                  (CONST64U(1) << 11)
+#define SVGA3D_SURFACE_HINT_STATIC (CONST64U(1) << 1)
+#define SVGA3D_SURFACE_HINT_DYNAMIC (CONST64U(1) << 2)
+#define SVGA3D_SURFACE_HINT_INDEXBUFFER (CONST64U(1) << 3)
+#define SVGA3D_SURFACE_HINT_VERTEXBUFFER (CONST64U(1) << 4)
+#define SVGA3D_SURFACE_HINT_TEXTURE (CONST64U(1) << 5)
+#define SVGA3D_SURFACE_HINT_RENDERTARGET (CONST64U(1) << 6)
+#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL (CONST64U(1) << 7)
+#define SVGA3D_SURFACE_HINT_WRITEONLY (CONST64U(1) << 8)
+#define SVGA3D_SURFACE_DEAD2 (CONST64U(1) << 9)
+#define SVGA3D_SURFACE_AUTOGENMIPMAPS (CONST64U(1) << 10)
 
-/*
- * Is this surface using a base-level pitch for it's mob backing?
- *
- * This flag is not intended to be set by guest-drivers, but is instead
- * set by the device when the surface is bound to a mob with a specified
- * pitch.
- */
-#define SVGA3D_SURFACE_MOB_PITCH              (CONST64U(1) << 12)
+#define SVGA3D_SURFACE_DEAD1 (CONST64U(1) << 11)
 
-#define SVGA3D_SURFACE_INACTIVE               (CONST64U(1) << 13)
-#define SVGA3D_SURFACE_HINT_RT_LOCKABLE       (CONST64U(1) << 14)
-#define SVGA3D_SURFACE_VOLUME                 (CONST64U(1) << 15)
+#define SVGA3D_SURFACE_MOB_PITCH (CONST64U(1) << 12)
 
-/*
- * Required to be set on a surface to bind it to a screen target.
- */
-#define SVGA3D_SURFACE_SCREENTARGET           (CONST64U(1) << 16)
+#define SVGA3D_SURFACE_INACTIVE (CONST64U(1) << 13)
+#define SVGA3D_SURFACE_HINT_RT_LOCKABLE (CONST64U(1) << 14)
+#define SVGA3D_SURFACE_VOLUME (CONST64U(1) << 15)
 
-/*
- * Align images in the guest-backing mob to 16-bytes.
- */
-#define SVGA3D_SURFACE_ALIGN16                (CONST64U(1) << 17)
+#define SVGA3D_SURFACE_SCREENTARGET (CONST64U(1) << 16)
 
-#define SVGA3D_SURFACE_1D                     (CONST64U(1) << 18)
-#define SVGA3D_SURFACE_ARRAY                  (CONST64U(1) << 19)
+#define SVGA3D_SURFACE_ALIGN16 (CONST64U(1) << 17)
 
-/*
- * Bind flags.
- * These are enforced for any surface defined with DefineGBSurface_v2.
- */
-#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER     (CONST64U(1) << 20)
-#define SVGA3D_SURFACE_BIND_INDEX_BUFFER      (CONST64U(1) << 21)
-#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER   (CONST64U(1) << 22)
-#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE   (CONST64U(1) << 23)
-#define SVGA3D_SURFACE_BIND_RENDER_TARGET     (CONST64U(1) << 24)
-#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL     (CONST64U(1) << 25)
-#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT     (CONST64U(1) << 26)
+#define SVGA3D_SURFACE_1D (CONST64U(1) << 18)
+#define SVGA3D_SURFACE_ARRAY (CONST64U(1) << 19)
 
-/*
- * The STAGING flags notes that the surface will not be used directly by the
- * drawing pipeline, i.e. that it will not be bound to any bind point.
- * Staging surfaces may be used by copy operations to move data in and out
- * of other surfaces.  No bind flags may be set on surfaces with this flag.
- *
- * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
- * updates indirectly, i.e. the surface will not be updated directly, but
- * will receive copies from staging surfaces.
- */
-#define SVGA3D_SURFACE_STAGING_UPLOAD         (CONST64U(1) << 27)
-#define SVGA3D_SURFACE_STAGING_DOWNLOAD       (CONST64U(1) << 28)
-#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE   (CONST64U(1) << 29)
+#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER (CONST64U(1) << 20)
+#define SVGA3D_SURFACE_BIND_INDEX_BUFFER (CONST64U(1) << 21)
+#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER (CONST64U(1) << 22)
+#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE (CONST64U(1) << 23)
+#define SVGA3D_SURFACE_BIND_RENDER_TARGET (CONST64U(1) << 24)
+#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL (CONST64U(1) << 25)
+#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT (CONST64U(1) << 26)
 
-/*
- * Setting this flag allow this surface to be used with the
- * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
- * buffer surfaces, and no bind flags are allowed to be set on surfaces
- * with this flag except SVGA3D_SURFACE_TRANSFER_TO_BUFFER.
- */
-#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   (CONST64U(1) << 30)
+#define SVGA3D_SURFACE_STAGING_UPLOAD (CONST64U(1) << 27)
+#define SVGA3D_SURFACE_STAGING_DOWNLOAD (CONST64U(1) << 28)
+#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE (CONST64U(1) << 29)
 
-/*
- * Reserved for video operations.
- */
-#define SVGA3D_SURFACE_RESERVED1              (CONST64U(1) << 31)
+#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER (CONST64U(1) << 30)
 
-/*
- * Specifies that a surface is multisample, and therefore requires the full
- * mob-backing to store all the samples.
- */
-#define SVGA3D_SURFACE_MULTISAMPLE            (CONST64U(1) << 32)
+#define SVGA3D_SURFACE_RESERVED1 (CONST64U(1) << 31)
+#define SVGA3D_SURFACE_VADECODE SVGA3D_SURFACE_RESERVED1
 
-/*
- * Specified that the surface is allowed to be bound to a UAView.
- */
-#define SVGA3D_SURFACE_BIND_UAVIEW            (CONST64U(1) << 33)
+#define SVGA3D_SURFACE_MULTISAMPLE (CONST64U(1) << 32)
 
-/*
- * Setting this flag allow this surface to be used with the
- * SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER command.  It is only valid for
- * buffer surfaces, and no bind flags are allowed to be set on surfaces
- * with this flag except SVGA3D_SURFACE_TRANSFER_FROM_BUFFER.
- */
-#define SVGA3D_SURFACE_TRANSFER_TO_BUFFER     (CONST64U(1) << 34)
+#define SVGA3D_SURFACE_BIND_UAVIEW (CONST64U(1) << 33)
 
-#define SVGA3D_SURFACE_BIND_LOGICOPS          (CONST64U(1) << 35)
+#define SVGA3D_SURFACE_TRANSFER_TO_BUFFER (CONST64U(1) << 34)
 
-/*
- * Optional flags for use with SVGA3D_SURFACE_BIND_UAVIEW
- */
-#define SVGA3D_SURFACE_BIND_RAW_VIEWS         (CONST64U(1) << 36)
-#define SVGA3D_SURFACE_BUFFER_STRUCTURED      (CONST64U(1) << 37)
+#define SVGA3D_SURFACE_BIND_LOGICOPS (CONST64U(1) << 35)
 
-#define SVGA3D_SURFACE_DRAWINDIRECT_ARGS      (CONST64U(1) << 38)
-#define SVGA3D_SURFACE_RESOURCE_CLAMP         (CONST64U(1) << 39)
+#define SVGA3D_SURFACE_BIND_RAW_VIEWS (CONST64U(1) << 36)
+#define SVGA3D_SURFACE_BUFFER_STRUCTURED (CONST64U(1) << 37)
 
-#define SVGA3D_SURFACE_FLAG_MAX               (CONST64U(1) << 40)
+#define SVGA3D_SURFACE_DRAWINDIRECT_ARGS (CONST64U(1) << 38)
+#define SVGA3D_SURFACE_RESOURCE_CLAMP (CONST64U(1) << 39)
+
+#define SVGA3D_SURFACE_STAGING_COPY (CONST64U(1) << 40)
+
+#define SVGA3D_SURFACE_FLAG_MAX (CONST64U(1) << 44)
 
-/*
- * Surface flags types:
- *
- * SVGA3dSurface1Flags:  Lower 32-bits of flags.
- * SVGA3dSurface2Flags:  Upper 32-bits of flags.
- * SVGA3dSurfaceAllFlags: Full 64-bits of flags.
- */
 typedef uint32 SVGA3dSurface1Flags;
 typedef uint32 SVGA3dSurface2Flags;
 typedef uint64 SVGA3dSurfaceAllFlags;
 
-#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64_t)MAX_UINT32)
+#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64)MAX_UINT32)
 #define SVGA3D_SURFACE_FLAGS2_MASK (MAX_UINT64 & ~SVGA3D_SURFACE_FLAGS1_MASK)
 
-#define SVGA3D_SURFACE_HB_DISALLOWED_MASK        \
-        (  SVGA3D_SURFACE_MOB_PITCH    |         \
-           SVGA3D_SURFACE_SCREENTARGET |         \
-           SVGA3D_SURFACE_ALIGN16 |              \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |   \
-           SVGA3D_SURFACE_STAGING_UPLOAD |       \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
-           SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \
-           SVGA3D_SURFACE_RESERVED1 |             \
-           SVGA3D_SURFACE_MULTISAMPLE |          \
-           SVGA3D_SURFACE_BIND_UAVIEW |          \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |   \
-           SVGA3D_SURFACE_BIND_LOGICOPS |        \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |       \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |    \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |    \
-           SVGA3D_SURFACE_RESOURCE_CLAMP         \
-        )
-
-#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK   \
-       (   SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_RESERVED1 |                \
-           SVGA3D_SURFACE_MULTISAMPLE               \
-        )
-
-#define SVGA3D_SURFACE_2D_DISALLOWED_MASK           \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
-           SVGA3D_SURFACE_RESERVED1 |                \
-           SVGA3D_SURFACE_MULTISAMPLE |             \
-           SVGA3D_SURFACE_BIND_UAVIEW |             \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |          \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |       \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |       \
-           SVGA3D_SURFACE_RESOURCE_CLAMP            \
-        )
-
-#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK     \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_RESERVED1 |                \
-           SVGA3D_SURFACE_MULTISAMPLE               \
-        )
-
-#define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_INACTIVE |                \
-           SVGA3D_SURFACE_STAGING_UPLOAD |          \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD |        \
-           SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |    \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
-           SVGA3D_SURFACE_RESERVED1 |                \
-           SVGA3D_SURFACE_MULTISAMPLE |             \
-           SVGA3D_SURFACE_BIND_UAVIEW |             \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |          \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |       \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |       \
-           SVGA3D_SURFACE_RESOURCE_CLAMP            \
-        )
-
-#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK       \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_DEAD2 |                   \
-           SVGA3D_SURFACE_ARRAY |                   \
-           SVGA3D_SURFACE_MULTISAMPLE |             \
-           SVGA3D_SURFACE_MOB_PITCH |               \
-           SVGA3D_SURFACE_RESOURCE_CLAMP            \
-        )
-
-#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK  \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_SCREENTARGET |            \
-           SVGA3D_SURFACE_MOB_PITCH |               \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
-           SVGA3D_SURFACE_RESERVED1 |                \
-           SVGA3D_SURFACE_BIND_UAVIEW |             \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
-           SVGA3D_SURFACE_BIND_LOGICOPS |           \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |          \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |       \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS         \
-        )
-
-#define SVGA3D_SURFACE_DX_ONLY_MASK              \
-        (  SVGA3D_SURFACE_BIND_STREAM_OUTPUT |   \
-           SVGA3D_SURFACE_STAGING_UPLOAD |       \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER     \
-        )
-
-#define SVGA3D_SURFACE_STAGING_MASK             \
-        (  SVGA3D_SURFACE_STAGING_UPLOAD |      \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD      \
-        )
-
-#define SVGA3D_SURFACE_BIND_MASK                  \
-        (  SVGA3D_SURFACE_BIND_VERTEX_BUFFER   |  \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER    |  \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |  \
-           SVGA3D_SURFACE_BIND_SHADER_RESOURCE |  \
-           SVGA3D_SURFACE_BIND_RENDER_TARGET   |  \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL   |  \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT   |  \
-           SVGA3D_SURFACE_BIND_UAVIEW          |  \
-           SVGA3D_SURFACE_BIND_LOGICOPS        |  \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS          \
-        )
-
-#define SVGA3D_SURFACE_VADECODE_DISALLOWED_MASK     \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_HINT_STATIC |             \
-           SVGA3D_SURFACE_HINT_DYNAMIC |            \
-           SVGA3D_SURFACE_HINT_INDEXBUFFER |        \
-           SVGA3D_SURFACE_HINT_VERTEXBUFFER |       \
-           SVGA3D_SURFACE_HINT_TEXTURE |            \
-           SVGA3D_SURFACE_HINT_RENDERTARGET |       \
-           SVGA3D_SURFACE_HINT_DEPTHSTENCIL |       \
-           SVGA3D_SURFACE_HINT_WRITEONLY |          \
-           SVGA3D_SURFACE_DEAD2 |                   \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_HINT_RT_LOCKABLE |        \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_SCREENTARGET |            \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
-           SVGA3D_SURFACE_BIND_RENDER_TARGET |      \
-           SVGA3D_SURFACE_BIND_SHADER_RESOURCE |    \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_INACTIVE |                \
-           SVGA3D_SURFACE_STAGING_UPLOAD |          \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD |        \
-           SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |    \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  |   \
-           SVGA3D_SURFACE_MULTISAMPLE |             \
-           SVGA3D_SURFACE_BIND_UAVIEW |             \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
-           SVGA3D_SURFACE_BIND_LOGICOPS |           \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |          \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |       \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |       \
-           SVGA3D_SURFACE_RESOURCE_CLAMP            \
-        )
-
-#define SVGA3D_SURFACE_VAPROCESSFRAME_OUTPUT_DISALLOWED_MASK     \
-        (  SVGA3D_SURFACE_HINT_INDEXBUFFER |                     \
-           SVGA3D_SURFACE_HINT_VERTEXBUFFER |                    \
-           SVGA3D_SURFACE_HINT_DEPTHSTENCIL |                    \
-           SVGA3D_SURFACE_DEAD2 |                                \
-           SVGA3D_SURFACE_VOLUME |                               \
-           SVGA3D_SURFACE_1D |                                   \
-           SVGA3D_SURFACE_BIND_VERTEX_BUFFER |                   \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER |                    \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                 \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                   \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |                   \
-           SVGA3D_SURFACE_INACTIVE |                             \
-           SVGA3D_SURFACE_STAGING_UPLOAD |                       \
-           SVGA3D_SURFACE_STAGING_DOWNLOAD |                     \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |                 \
-           SVGA3D_SURFACE_VADECODE |                             \
-           SVGA3D_SURFACE_MULTISAMPLE |                          \
-           SVGA3D_SURFACE_BIND_UAVIEW |                          \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |                   \
-           SVGA3D_SURFACE_BIND_LOGICOPS |                        \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |                       \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |                    \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |                    \
-           SVGA3D_SURFACE_RESOURCE_CLAMP         \
-        )
-
-#define SVGA3D_SURFACE_VAPROCESSFRAME_INPUT_DISALLOWED_MASK     \
-        ( SVGA3D_SURFACE_CUBEMAP |                              \
-          SVGA3D_SURFACE_HINT_INDEXBUFFER |                     \
-          SVGA3D_SURFACE_HINT_VERTEXBUFFER |                    \
-          SVGA3D_SURFACE_HINT_DEPTHSTENCIL |                    \
-          SVGA3D_SURFACE_DEAD2 |                                \
-          SVGA3D_SURFACE_VOLUME |                               \
-          SVGA3D_SURFACE_SCREENTARGET |                         \
-          SVGA3D_SURFACE_1D |                                   \
-          SVGA3D_SURFACE_BIND_VERTEX_BUFFER |                   \
-          SVGA3D_SURFACE_BIND_INDEX_BUFFER |                    \
-          SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                 \
-          SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                   \
-          SVGA3D_SURFACE_BIND_STREAM_OUTPUT |                   \
-          SVGA3D_SURFACE_STAGING_UPLOAD |                       \
-          SVGA3D_SURFACE_STAGING_DOWNLOAD |                     \
-          SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |                 \
-          SVGA3D_SURFACE_MULTISAMPLE |                          \
-          SVGA3D_SURFACE_BIND_UAVIEW |                          \
-          SVGA3D_SURFACE_TRANSFER_TO_BUFFER |                   \
-          SVGA3D_SURFACE_BIND_LOGICOPS |                        \
-          SVGA3D_SURFACE_BIND_RAW_VIEWS |                       \
-          SVGA3D_SURFACE_BUFFER_STRUCTURED |                    \
-          SVGA3D_SURFACE_DRAWINDIRECT_ARGS |                    \
-          SVGA3D_SURFACE_RESOURCE_CLAMP                         \
-        )
-
-#define SVGA3D_SURFACE_LOGICOPS_DISALLOWED_MASK     \
-        (  SVGA3D_SURFACE_CUBEMAP |                 \
-           SVGA3D_SURFACE_DEAD2 |                   \
-           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_VOLUME |                  \
-           SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
-           SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
-           SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
-           SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
-           SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
-           SVGA3D_SURFACE_VADECODE |                \
-           SVGA3D_SURFACE_MULTISAMPLE |             \
-           SVGA3D_SURFACE_BIND_UAVIEW |             \
-           SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
-           SVGA3D_SURFACE_BIND_RAW_VIEWS |          \
-           SVGA3D_SURFACE_BUFFER_STRUCTURED |       \
-           SVGA3D_SURFACE_DRAWINDIRECT_ARGS |       \
-           SVGA3D_SURFACE_RESOURCE_CLAMP            \
-        )
+#define SVGA3D_SURFACE_HB_DISALLOWED_MASK                                      \
+	(SVGA3D_SURFACE_MOB_PITCH | SVGA3D_SURFACE_SCREENTARGET |              \
+	 SVGA3D_SURFACE_ALIGN16 | SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |        \
+	 SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_STAGING_UPLOAD |   \
+	 SVGA3D_SURFACE_STAGING_DOWNLOAD |                                     \
+	 SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |                                 \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE |    \
+	 SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
+	 SVGA3D_SURFACE_BIND_LOGICOPS | SVGA3D_SURFACE_BIND_RAW_VIEWS |        \
+	 SVGA3D_SURFACE_BUFFER_STRUCTURED | SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \
+	 SVGA3D_SURFACE_RESOURCE_CLAMP | SVGA3D_SURFACE_STAGING_COPY |         \
+	 SVGA3D_SURFACE_RESTRICT_UPDATE | SVGA3D_SURFACE_BIND_TENSOR |         \
+	 SVGA3D_SURFACE_LO_STAGING)
+
+#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK                              \
+	(SVGA3D_SURFACE_1D | SVGA3D_SURFACE_MULTISAMPLE |                      \
+	 SVGA3D_SURFACE_STAGING_COPY)
+
+#define SVGA3D_SURFACE_2D_DISALLOWED_MASK                                      \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS |              \
+	 SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D |                           \
+	 SVGA3D_SURFACE_BIND_VERTEX_BUFFER |                                   \
+	 SVGA3D_SURFACE_BIND_INDEX_BUFFER |                                    \
+	 SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                                 \
+	 SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                                   \
+	 SVGA3D_SURFACE_BIND_STREAM_OUTPUT |                                   \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE |    \
+	 SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
+	 SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED |    \
+	 SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP |    \
+	 SVGA3D_SURFACE_BIND_TENSOR)
+
+#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK                                \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS |              \
+	 SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D |                           \
+	 SVGA3D_SURFACE_MULTISAMPLE)
+
+#define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK                            \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS |              \
+	 SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D |                           \
+	 SVGA3D_SURFACE_BIND_VERTEX_BUFFER |                                   \
+	 SVGA3D_SURFACE_BIND_INDEX_BUFFER |                                    \
+	 SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                                 \
+	 SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                                   \
+	 SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_INACTIVE |         \
+	 SVGA3D_SURFACE_STAGING_UPLOAD | SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
+	 SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |                                 \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE |    \
+	 SVGA3D_SURFACE_TRANSFER_TO_BUFFER | SVGA3D_SURFACE_BIND_RAW_VIEWS |   \
+	 SVGA3D_SURFACE_BUFFER_STRUCTURED | SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \
+	 SVGA3D_SURFACE_RESOURCE_CLAMP | SVGA3D_SURFACE_STAGING_COPY |         \
+	 SVGA3D_SURFACE_BIND_TENSOR | SVGA3D_SURFACE_LO_STAGING)
+
+#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK                                  \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS |              \
+	 SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | SVGA3D_SURFACE_DEAD2 |    \
+	 SVGA3D_SURFACE_ARRAY | SVGA3D_SURFACE_MULTISAMPLE |                   \
+	 SVGA3D_SURFACE_MOB_PITCH | SVGA3D_SURFACE_RESOURCE_CLAMP)
+
+#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK                             \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS |              \
+	 SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D |                           \
+	 SVGA3D_SURFACE_SCREENTARGET | SVGA3D_SURFACE_MOB_PITCH |              \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_BIND_UAVIEW |    \
+	 SVGA3D_SURFACE_TRANSFER_TO_BUFFER | SVGA3D_SURFACE_BIND_LOGICOPS |    \
+	 SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED |    \
+	 SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_STAGING_COPY)
+
+#define SVGA3D_SURFACE_DX_ONLY_MASK                                            \
+	(SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_STAGING_UPLOAD |   \
+	 SVGA3D_SURFACE_STAGING_DOWNLOAD |                                     \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |                                 \
+	 SVGA3D_SURFACE_TRANSFER_TO_BUFFER)
+
+#define SVGA3D_SURFACE_ANY_STAGING_MASK                                        \
+	(SVGA3D_SURFACE_STAGING_UPLOAD | SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
+	 SVGA3D_SURFACE_STAGING_COPY | SVGA3D_SURFACE_LO_STAGING)
+
+#define SVGA3D_SURFACE_ANY_NONHINT_STAGING_MASK                                \
+	(SVGA3D_SURFACE_ANY_STAGING_MASK & ~(SVGA3D_SURFACE_LO_STAGING))
+
+#define SVGA3D_SURFACE_BIND_MASK                                               \
+	(SVGA3D_SURFACE_BIND_VERTEX_BUFFER |                                   \
+	 SVGA3D_SURFACE_BIND_INDEX_BUFFER |                                    \
+	 SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                                 \
+	 SVGA3D_SURFACE_BIND_SHADER_RESOURCE |                                 \
+	 SVGA3D_SURFACE_BIND_RENDER_TARGET |                                   \
+	 SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                                   \
+	 SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_BIND_UAVIEW |      \
+	 SVGA3D_SURFACE_BIND_LOGICOPS | SVGA3D_SURFACE_BIND_RAW_VIEWS |        \
+	 SVGA3D_SURFACE_BIND_TENSOR)
+
+#define SVGA3D_SURFACE_STAGING_DISALLOWED_MASK                                 \
+	(SVGA3D_SURFACE_BIND_MASK | SVGA3D_SURFACE_AUTOGENMIPMAPS |            \
+	 SVGA3D_SURFACE_SCREENTARGET | SVGA3D_SURFACE_HINT_RENDERTARGET |      \
+	 SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | SVGA3D_SURFACE_MULTISAMPLE |    \
+	 SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP |    \
+	 SVGA3D_SURFACE_BIND_TENSOR)
+
+#define SVGA3D_SURFACE_STAGING_COPY_DISALLOWED_MASK                            \
+	(SVGA3D_SURFACE_STAGING_DISALLOWED_MASK |                              \
+	 SVGA3D_SURFACE_TRANSFER_TO_BUFFER |                                   \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER)
+
+#define SVGA3D_SURFACE_LOGICOPS_DISALLOWED_MASK                                \
+	(SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_DEAD2 |                       \
+	 SVGA3D_SURFACE_AUTOGENMIPMAPS | SVGA3D_SURFACE_VOLUME |               \
+	 SVGA3D_SURFACE_1D | SVGA3D_SURFACE_BIND_VERTEX_BUFFER |               \
+	 SVGA3D_SURFACE_BIND_INDEX_BUFFER |                                    \
+	 SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |                                 \
+	 SVGA3D_SURFACE_BIND_DEPTH_STENCIL |                                   \
+	 SVGA3D_SURFACE_BIND_STREAM_OUTPUT |                                   \
+	 SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE |    \
+	 SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER |      \
+	 SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED |    \
+	 SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP |    \
+	 SVGA3D_SURFACE_STAGING_COPY)
+
+#define SVGA3D_SURFACE_SM5_MASK                                                \
+	(SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_BUFFER_STRUCTURED | \
+	 SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BIND_UAVIEW |          \
+	 SVGA3D_SURFACE_RESOURCE_CLAMP)
 
 #define SVGA3D_BUFFER_STRUCTURED_STRIDE_MAX 2048
 
-
-/*
- * These are really the D3DFORMAT_OP defines from the wdk. We need
- * them so that we can query the host for what the supported surface
- * operations are (when we're using the D3D backend, in particular),
- * and so we can send those operations to the guest.
- */
 typedef enum {
-   SVGA3DFORMAT_OP_TEXTURE                               = 0x00000001,
-   SVGA3DFORMAT_OP_VOLUMETEXTURE                         = 0x00000002,
-   SVGA3DFORMAT_OP_CUBETEXTURE                           = 0x00000004,
-   SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET                = 0x00000008,
-   SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET              = 0x00000010,
-   SVGA3DFORMAT_OP_ZSTENCIL                              = 0x00000040,
-   SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH   = 0x00000080,
+	SVGA3DFORMAT_OP_TEXTURE = 0x00000001,
+	SVGA3DFORMAT_OP_VOLUMETEXTURE = 0x00000002,
+	SVGA3DFORMAT_OP_CUBETEXTURE = 0x00000004,
+	SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET = 0x00000008,
+	SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET = 0x00000010,
+	SVGA3DFORMAT_OP_ZSTENCIL = 0x00000040,
+	SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH = 0x00000080,
 
-/*
- * This format can be used as a render target if the current display mode
- * is the same depth if the alpha channel is ignored. e.g. if the device
- * can render to A8R8G8B8 when the display mode is X8R8G8B8, then the
- * format op list entry for A8R8G8B8 should have this cap.
- */
-   SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET  = 0x00000100,
+	SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET = 0x00000100,
 
-/*
- * This format contains DirectDraw support (including Flip).  This flag
- * should not to be set on alpha formats.
- */
-   SVGA3DFORMAT_OP_DISPLAYMODE                           = 0x00000400,
+	SVGA3DFORMAT_OP_DISPLAYMODE = 0x00000400,
 
-/*
- * The rasterizer can support some level of Direct3D support in this format
- * and implies that the driver can create a Context in this mode (for some
- * render target format).  When this flag is set, the SVGA3DFORMAT_OP_DISPLAYMODE
- * flag must also be set.
- */
-   SVGA3DFORMAT_OP_3DACCELERATION                        = 0x00000800,
+	SVGA3DFORMAT_OP_3DACCELERATION = 0x00000800,
 
-/*
- * This is set for a private format when the driver has put the bpp in
- * the structure.
- */
-   SVGA3DFORMAT_OP_PIXELSIZE                             = 0x00001000,
+	SVGA3DFORMAT_OP_PIXELSIZE = 0x00001000,
 
-/*
- * Indicates that this format can be converted to any RGB format for which
- * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified.
- */
-   SVGA3DFORMAT_OP_CONVERT_TO_ARGB                       = 0x00002000,
+	SVGA3DFORMAT_OP_CONVERT_TO_ARGB = 0x00002000,
 
-/*
- * Indicates that this format can be used to create offscreen plain surfaces.
- */
-   SVGA3DFORMAT_OP_OFFSCREENPLAIN                        = 0x00004000,
+	SVGA3DFORMAT_OP_OFFSCREENPLAIN = 0x00004000,
 
-/*
- * Indicated that this format can be read as an SRGB texture (meaning that the
- * sampler will linearize the looked up data).
- */
-   SVGA3DFORMAT_OP_SRGBREAD                              = 0x00008000,
+	SVGA3DFORMAT_OP_SRGBREAD = 0x00008000,
 
-/*
- * Indicates that this format can be used in the bumpmap instructions.
- */
-   SVGA3DFORMAT_OP_BUMPMAP                               = 0x00010000,
+	SVGA3DFORMAT_OP_BUMPMAP = 0x00010000,
 
-/*
- * Indicates that this format can be sampled by the displacement map sampler.
- */
-   SVGA3DFORMAT_OP_DMAP                                  = 0x00020000,
+	SVGA3DFORMAT_OP_DMAP = 0x00020000,
 
-/*
- * Indicates that this format cannot be used with texture filtering.
- */
-   SVGA3DFORMAT_OP_NOFILTER                              = 0x00040000,
+	SVGA3DFORMAT_OP_NOFILTER = 0x00040000,
 
-/*
- * Indicates that format conversions are supported to this RGB format if
- * SVGA3DFORMAT_OP_CONVERT_TO_ARGB is specified in the source format.
- */
-   SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB                    = 0x00080000,
+	SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB = 0x00080000,
 
-/*
- * Indicated that this format can be written as an SRGB target
- * (meaning that the pixel pipe will DE-linearize data on output to format)
- */
-   SVGA3DFORMAT_OP_SRGBWRITE                             = 0x00100000,
+	SVGA3DFORMAT_OP_SRGBWRITE = 0x00100000,
 
-/*
- * Indicates that this format cannot be used with alpha blending.
- */
-   SVGA3DFORMAT_OP_NOALPHABLEND                          = 0x00200000,
+	SVGA3DFORMAT_OP_NOALPHABLEND = 0x00200000,
 
-/*
- * Indicates that the device can auto-generated sublevels for resources
- * of this format.
- */
-   SVGA3DFORMAT_OP_AUTOGENMIPMAP                         = 0x00400000,
+	SVGA3DFORMAT_OP_AUTOGENMIPMAP = 0x00400000,
 
-/*
- * Indicates that this format can be used by vertex texture sampler.
- */
-   SVGA3DFORMAT_OP_VERTEXTEXTURE                         = 0x00800000,
+	SVGA3DFORMAT_OP_VERTEXTEXTURE = 0x00800000,
 
-/*
- * Indicates that this format supports neither texture coordinate
- * wrap modes, nor mipmapping.
- */
-   SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP                  = 0x01000000
+	SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP = 0x01000000
 } SVGA3dFormatOp;
 
-#define SVGA3D_FORMAT_POSITIVE                             \
-   (SVGA3DFORMAT_OP_TEXTURE                              | \
-    SVGA3DFORMAT_OP_VOLUMETEXTURE                        | \
-    SVGA3DFORMAT_OP_CUBETEXTURE                          | \
-    SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET               | \
-    SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET             | \
-    SVGA3DFORMAT_OP_ZSTENCIL                             | \
-    SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH  | \
-    SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET | \
-    SVGA3DFORMAT_OP_DISPLAYMODE                          | \
-    SVGA3DFORMAT_OP_3DACCELERATION                       | \
-    SVGA3DFORMAT_OP_PIXELSIZE                            | \
-    SVGA3DFORMAT_OP_CONVERT_TO_ARGB                      | \
-    SVGA3DFORMAT_OP_OFFSCREENPLAIN                       | \
-    SVGA3DFORMAT_OP_SRGBREAD                             | \
-    SVGA3DFORMAT_OP_BUMPMAP                              | \
-    SVGA3DFORMAT_OP_DMAP                                 | \
-    SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB                   | \
-    SVGA3DFORMAT_OP_SRGBWRITE                            | \
-    SVGA3DFORMAT_OP_AUTOGENMIPMAP                        | \
-    SVGA3DFORMAT_OP_VERTEXTEXTURE)
-
-#define SVGA3D_FORMAT_NEGATIVE               \
-   (SVGA3DFORMAT_OP_NOFILTER               | \
-    SVGA3DFORMAT_OP_NOALPHABLEND           | \
-    SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP)
+#define SVGA3D_FORMAT_POSITIVE                                                 \
+	(SVGA3DFORMAT_OP_TEXTURE | SVGA3DFORMAT_OP_VOLUMETEXTURE |             \
+	 SVGA3DFORMAT_OP_CUBETEXTURE |                                         \
+	 SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET |                              \
+	 SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET | SVGA3DFORMAT_OP_ZSTENCIL | \
+	 SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH |                 \
+	 SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET |                \
+	 SVGA3DFORMAT_OP_DISPLAYMODE | SVGA3DFORMAT_OP_3DACCELERATION |        \
+	 SVGA3DFORMAT_OP_PIXELSIZE | SVGA3DFORMAT_OP_CONVERT_TO_ARGB |         \
+	 SVGA3DFORMAT_OP_OFFSCREENPLAIN | SVGA3DFORMAT_OP_SRGBREAD |           \
+	 SVGA3DFORMAT_OP_BUMPMAP | SVGA3DFORMAT_OP_DMAP |                      \
+	 SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB | SVGA3DFORMAT_OP_SRGBWRITE |      \
+	 SVGA3DFORMAT_OP_AUTOGENMIPMAP | SVGA3DFORMAT_OP_VERTEXTEXTURE)
+
+#define SVGA3D_FORMAT_NEGATIVE                                                 \
+	(SVGA3DFORMAT_OP_NOFILTER | SVGA3DFORMAT_OP_NOALPHABLEND |             \
+	 SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP)
 
-/*
- * This structure is a conversion of SVGA3DFORMAT_OP_*
- * Entries must be located at the same position.
- */
 typedef union {
-   uint32 value;
-   struct {
-      uint32 texture : 1;
-      uint32 volumeTexture : 1;
-      uint32 cubeTexture : 1;
-      uint32 offscreenRenderTarget : 1;
-      uint32 sameFormatRenderTarget : 1;
-      uint32 unknown1 : 1;
-      uint32 zStencil : 1;
-      uint32 zStencilArbitraryDepth : 1;
-      uint32 sameFormatUpToAlpha : 1;
-      uint32 unknown2 : 1;
-      uint32 displayMode : 1;
-      uint32 acceleration3d : 1;
-      uint32 pixelSize : 1;
-      uint32 convertToARGB : 1;
-      uint32 offscreenPlain : 1;
-      uint32 sRGBRead : 1;
-      uint32 bumpMap : 1;
-      uint32 dmap : 1;
-      uint32 noFilter : 1;
-      uint32 memberOfGroupARGB : 1;
-      uint32 sRGBWrite : 1;
-      uint32 noAlphaBlend : 1;
-      uint32 autoGenMipMap : 1;
-      uint32 vertexTexture : 1;
-      uint32 noTexCoordWrapNorMip : 1;
-   };
+	uint32 value;
+	struct {
+		uint32 texture : 1;
+		uint32 volumeTexture : 1;
+		uint32 cubeTexture : 1;
+		uint32 offscreenRenderTarget : 1;
+		uint32 sameFormatRenderTarget : 1;
+		uint32 unknown1 : 1;
+		uint32 zStencil : 1;
+		uint32 zStencilArbitraryDepth : 1;
+		uint32 sameFormatUpToAlpha : 1;
+		uint32 unknown2 : 1;
+		uint32 displayMode : 1;
+		uint32 acceleration3d : 1;
+		uint32 pixelSize : 1;
+		uint32 convertToARGB : 1;
+		uint32 offscreenPlain : 1;
+		uint32 sRGBRead : 1;
+		uint32 bumpMap : 1;
+		uint32 dmap : 1;
+		uint32 noFilter : 1;
+		uint32 memberOfGroupARGB : 1;
+		uint32 sRGBWrite : 1;
+		uint32 noAlphaBlend : 1;
+		uint32 autoGenMipMap : 1;
+		uint32 vertexTexture : 1;
+		uint32 noTexCoordWrapNorMip : 1;
+	};
 } SVGA3dSurfaceFormatCaps;
 
-/*
- * SVGA_3D_CMD_SETRENDERSTATE Types.  All value types
- * must fit in a uint32.
- */
-
 typedef enum {
-   SVGA3D_RS_INVALID                   = 0,
-   SVGA3D_RS_MIN                       = 1,
-   SVGA3D_RS_ZENABLE                   = 1,     /* SVGA3dBool */
-   SVGA3D_RS_ZWRITEENABLE              = 2,     /* SVGA3dBool */
-   SVGA3D_RS_ALPHATESTENABLE           = 3,     /* SVGA3dBool */
-   SVGA3D_RS_DITHERENABLE              = 4,     /* SVGA3dBool */
-   SVGA3D_RS_BLENDENABLE               = 5,     /* SVGA3dBool */
-   SVGA3D_RS_FOGENABLE                 = 6,     /* SVGA3dBool */
-   SVGA3D_RS_SPECULARENABLE            = 7,     /* SVGA3dBool */
-   SVGA3D_RS_STENCILENABLE             = 8,     /* SVGA3dBool */
-   SVGA3D_RS_LIGHTINGENABLE            = 9,     /* SVGA3dBool */
-   SVGA3D_RS_NORMALIZENORMALS          = 10,    /* SVGA3dBool */
-   SVGA3D_RS_POINTSPRITEENABLE         = 11,    /* SVGA3dBool */
-   SVGA3D_RS_POINTSCALEENABLE          = 12,    /* SVGA3dBool */
-   SVGA3D_RS_STENCILREF                = 13,    /* uint32 */
-   SVGA3D_RS_STENCILMASK               = 14,    /* uint32 */
-   SVGA3D_RS_STENCILWRITEMASK          = 15,    /* uint32 */
-   SVGA3D_RS_FOGSTART                  = 16,    /* float */
-   SVGA3D_RS_FOGEND                    = 17,    /* float */
-   SVGA3D_RS_FOGDENSITY                = 18,    /* float */
-   SVGA3D_RS_POINTSIZE                 = 19,    /* float */
-   SVGA3D_RS_POINTSIZEMIN              = 20,    /* float */
-   SVGA3D_RS_POINTSIZEMAX              = 21,    /* float */
-   SVGA3D_RS_POINTSCALE_A              = 22,    /* float */
-   SVGA3D_RS_POINTSCALE_B              = 23,    /* float */
-   SVGA3D_RS_POINTSCALE_C              = 24,    /* float */
-   SVGA3D_RS_FOGCOLOR                  = 25,    /* SVGA3dColor */
-   SVGA3D_RS_AMBIENT                   = 26,    /* SVGA3dColor */
-   SVGA3D_RS_CLIPPLANEENABLE           = 27,    /* SVGA3dClipPlanes */
-   SVGA3D_RS_FOGMODE                   = 28,    /* SVGA3dFogMode */
-   SVGA3D_RS_FILLMODE                  = 29,    /* SVGA3dFillMode */
-   SVGA3D_RS_SHADEMODE                 = 30,    /* SVGA3dShadeMode */
-   SVGA3D_RS_LINEPATTERN               = 31,    /* SVGA3dLinePattern */
-   SVGA3D_RS_SRCBLEND                  = 32,    /* SVGA3dBlendOp */
-   SVGA3D_RS_DSTBLEND                  = 33,    /* SVGA3dBlendOp */
-   SVGA3D_RS_BLENDEQUATION             = 34,    /* SVGA3dBlendEquation */
-   SVGA3D_RS_CULLMODE                  = 35,    /* SVGA3dFace */
-   SVGA3D_RS_ZFUNC                     = 36,    /* SVGA3dCmpFunc */
-   SVGA3D_RS_ALPHAFUNC                 = 37,    /* SVGA3dCmpFunc */
-   SVGA3D_RS_STENCILFUNC               = 38,    /* SVGA3dCmpFunc */
-   SVGA3D_RS_STENCILFAIL               = 39,    /* SVGA3dStencilOp */
-   SVGA3D_RS_STENCILZFAIL              = 40,    /* SVGA3dStencilOp */
-   SVGA3D_RS_STENCILPASS               = 41,    /* SVGA3dStencilOp */
-   SVGA3D_RS_ALPHAREF                  = 42,    /* float (0.0 .. 1.0) */
-   SVGA3D_RS_FRONTWINDING              = 43,    /* SVGA3dFrontWinding */
-   SVGA3D_RS_COORDINATETYPE            = 44,    /* SVGA3dCoordinateType */
-   SVGA3D_RS_ZBIAS                     = 45,    /* float */
-   SVGA3D_RS_RANGEFOGENABLE            = 46,    /* SVGA3dBool */
-   SVGA3D_RS_COLORWRITEENABLE          = 47,    /* SVGA3dColorMask */
-   SVGA3D_RS_VERTEXMATERIALENABLE      = 48,    /* SVGA3dBool */
-   SVGA3D_RS_DIFFUSEMATERIALSOURCE     = 49,    /* SVGA3dVertexMaterial */
-   SVGA3D_RS_SPECULARMATERIALSOURCE    = 50,    /* SVGA3dVertexMaterial */
-   SVGA3D_RS_AMBIENTMATERIALSOURCE     = 51,    /* SVGA3dVertexMaterial */
-   SVGA3D_RS_EMISSIVEMATERIALSOURCE    = 52,    /* SVGA3dVertexMaterial */
-   SVGA3D_RS_TEXTUREFACTOR             = 53,    /* SVGA3dColor */
-   SVGA3D_RS_LOCALVIEWER               = 54,    /* SVGA3dBool */
-   SVGA3D_RS_SCISSORTESTENABLE         = 55,    /* SVGA3dBool */
-   SVGA3D_RS_BLENDCOLOR                = 56,    /* SVGA3dColor */
-   SVGA3D_RS_STENCILENABLE2SIDED       = 57,    /* SVGA3dBool */
-   SVGA3D_RS_CCWSTENCILFUNC            = 58,    /* SVGA3dCmpFunc */
-   SVGA3D_RS_CCWSTENCILFAIL            = 59,    /* SVGA3dStencilOp */
-   SVGA3D_RS_CCWSTENCILZFAIL           = 60,    /* SVGA3dStencilOp */
-   SVGA3D_RS_CCWSTENCILPASS            = 61,    /* SVGA3dStencilOp */
-   SVGA3D_RS_VERTEXBLEND               = 62,    /* SVGA3dVertexBlendFlags */
-   SVGA3D_RS_SLOPESCALEDEPTHBIAS       = 63,    /* float */
-   SVGA3D_RS_DEPTHBIAS                 = 64,    /* float */
-
-
-   /*
-    * Output Gamma Level
-    *
-    * Output gamma effects the gamma curve of colors that are output from the
-    * rendering pipeline.  A value of 1.0 specifies a linear color space. If the
-    * value is <= 0.0, gamma correction is ignored and linear color space is
-    * used.
-    */
-
-   SVGA3D_RS_OUTPUTGAMMA               = 65,    /* float */
-   SVGA3D_RS_ZVISIBLE                  = 66,    /* SVGA3dBool */
-   SVGA3D_RS_LASTPIXEL                 = 67,    /* SVGA3dBool */
-   SVGA3D_RS_CLIPPING                  = 68,    /* SVGA3dBool */
-   SVGA3D_RS_WRAP0                     = 69,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP1                     = 70,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP2                     = 71,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP3                     = 72,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP4                     = 73,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP5                     = 74,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP6                     = 75,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP7                     = 76,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP8                     = 77,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP9                     = 78,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP10                    = 79,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP11                    = 80,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP12                    = 81,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP13                    = 82,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP14                    = 83,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_WRAP15                    = 84,    /* SVGA3dWrapFlags */
-   SVGA3D_RS_MULTISAMPLEANTIALIAS      = 85,    /* SVGA3dBool */
-   SVGA3D_RS_MULTISAMPLEMASK           = 86,    /* uint32 */
-   SVGA3D_RS_INDEXEDVERTEXBLENDENABLE  = 87,    /* SVGA3dBool */
-   SVGA3D_RS_TWEENFACTOR               = 88,    /* float */
-   SVGA3D_RS_ANTIALIASEDLINEENABLE     = 89,    /* SVGA3dBool */
-   SVGA3D_RS_COLORWRITEENABLE1         = 90,    /* SVGA3dColorMask */
-   SVGA3D_RS_COLORWRITEENABLE2         = 91,    /* SVGA3dColorMask */
-   SVGA3D_RS_COLORWRITEENABLE3         = 92,    /* SVGA3dColorMask */
-   SVGA3D_RS_SEPARATEALPHABLENDENABLE  = 93,    /* SVGA3dBool */
-   SVGA3D_RS_SRCBLENDALPHA             = 94,    /* SVGA3dBlendOp */
-   SVGA3D_RS_DSTBLENDALPHA             = 95,    /* SVGA3dBlendOp */
-   SVGA3D_RS_BLENDEQUATIONALPHA        = 96,    /* SVGA3dBlendEquation */
-   SVGA3D_RS_TRANSPARENCYANTIALIAS     = 97,    /* SVGA3dTransparencyAntialiasType */
-   SVGA3D_RS_LINEWIDTH                 = 98,    /* float */
-   SVGA3D_RS_MAX
+	SVGA3D_RS_INVALID = 0,
+	SVGA3D_RS_MIN = 1,
+	SVGA3D_RS_ZENABLE = 1,
+	SVGA3D_RS_ZWRITEENABLE = 2,
+	SVGA3D_RS_ALPHATESTENABLE = 3,
+	SVGA3D_RS_DITHERENABLE = 4,
+	SVGA3D_RS_BLENDENABLE = 5,
+	SVGA3D_RS_FOGENABLE = 6,
+	SVGA3D_RS_SPECULARENABLE = 7,
+	SVGA3D_RS_STENCILENABLE = 8,
+	SVGA3D_RS_LIGHTINGENABLE = 9,
+	SVGA3D_RS_NORMALIZENORMALS = 10,
+	SVGA3D_RS_POINTSPRITEENABLE = 11,
+	SVGA3D_RS_POINTSCALEENABLE = 12,
+	SVGA3D_RS_STENCILREF = 13,
+	SVGA3D_RS_STENCILMASK = 14,
+	SVGA3D_RS_STENCILWRITEMASK = 15,
+	SVGA3D_RS_FOGSTART = 16,
+	SVGA3D_RS_FOGEND = 17,
+	SVGA3D_RS_FOGDENSITY = 18,
+	SVGA3D_RS_POINTSIZE = 19,
+	SVGA3D_RS_POINTSIZEMIN = 20,
+	SVGA3D_RS_POINTSIZEMAX = 21,
+	SVGA3D_RS_POINTSCALE_A = 22,
+	SVGA3D_RS_POINTSCALE_B = 23,
+	SVGA3D_RS_POINTSCALE_C = 24,
+	SVGA3D_RS_FOGCOLOR = 25,
+	SVGA3D_RS_AMBIENT = 26,
+	SVGA3D_RS_CLIPPLANEENABLE = 27,
+	SVGA3D_RS_FOGMODE = 28,
+	SVGA3D_RS_FILLMODE = 29,
+	SVGA3D_RS_SHADEMODE = 30,
+	SVGA3D_RS_LINEPATTERN = 31,
+	SVGA3D_RS_SRCBLEND = 32,
+	SVGA3D_RS_DSTBLEND = 33,
+	SVGA3D_RS_BLENDEQUATION = 34,
+	SVGA3D_RS_CULLMODE = 35,
+	SVGA3D_RS_ZFUNC = 36,
+	SVGA3D_RS_ALPHAFUNC = 37,
+	SVGA3D_RS_STENCILFUNC = 38,
+	SVGA3D_RS_STENCILFAIL = 39,
+	SVGA3D_RS_STENCILZFAIL = 40,
+	SVGA3D_RS_STENCILPASS = 41,
+	SVGA3D_RS_ALPHAREF = 42,
+	SVGA3D_RS_FRONTWINDING = 43,
+	SVGA3D_RS_COORDINATETYPE = 44,
+	SVGA3D_RS_ZBIAS = 45,
+	SVGA3D_RS_RANGEFOGENABLE = 46,
+	SVGA3D_RS_COLORWRITEENABLE = 47,
+	SVGA3D_RS_VERTEXMATERIALENABLE = 48,
+	SVGA3D_RS_DIFFUSEMATERIALSOURCE = 49,
+	SVGA3D_RS_SPECULARMATERIALSOURCE = 50,
+	SVGA3D_RS_AMBIENTMATERIALSOURCE = 51,
+	SVGA3D_RS_EMISSIVEMATERIALSOURCE = 52,
+	SVGA3D_RS_TEXTUREFACTOR = 53,
+	SVGA3D_RS_LOCALVIEWER = 54,
+	SVGA3D_RS_SCISSORTESTENABLE = 55,
+	SVGA3D_RS_BLENDCOLOR = 56,
+	SVGA3D_RS_STENCILENABLE2SIDED = 57,
+	SVGA3D_RS_CCWSTENCILFUNC = 58,
+	SVGA3D_RS_CCWSTENCILFAIL = 59,
+	SVGA3D_RS_CCWSTENCILZFAIL = 60,
+	SVGA3D_RS_CCWSTENCILPASS = 61,
+	SVGA3D_RS_VERTEXBLEND = 62,
+	SVGA3D_RS_SLOPESCALEDEPTHBIAS = 63,
+	SVGA3D_RS_DEPTHBIAS = 64,
+
+	SVGA3D_RS_OUTPUTGAMMA = 65,
+	SVGA3D_RS_ZVISIBLE = 66,
+	SVGA3D_RS_LASTPIXEL = 67,
+	SVGA3D_RS_CLIPPING = 68,
+	SVGA3D_RS_WRAP0 = 69,
+	SVGA3D_RS_WRAP1 = 70,
+	SVGA3D_RS_WRAP2 = 71,
+	SVGA3D_RS_WRAP3 = 72,
+	SVGA3D_RS_WRAP4 = 73,
+	SVGA3D_RS_WRAP5 = 74,
+	SVGA3D_RS_WRAP6 = 75,
+	SVGA3D_RS_WRAP7 = 76,
+	SVGA3D_RS_WRAP8 = 77,
+	SVGA3D_RS_WRAP9 = 78,
+	SVGA3D_RS_WRAP10 = 79,
+	SVGA3D_RS_WRAP11 = 80,
+	SVGA3D_RS_WRAP12 = 81,
+	SVGA3D_RS_WRAP13 = 82,
+	SVGA3D_RS_WRAP14 = 83,
+	SVGA3D_RS_WRAP15 = 84,
+	SVGA3D_RS_MULTISAMPLEANTIALIAS = 85,
+	SVGA3D_RS_MULTISAMPLEMASK = 86,
+	SVGA3D_RS_INDEXEDVERTEXBLENDENABLE = 87,
+	SVGA3D_RS_TWEENFACTOR = 88,
+	SVGA3D_RS_ANTIALIASEDLINEENABLE = 89,
+	SVGA3D_RS_COLORWRITEENABLE1 = 90,
+	SVGA3D_RS_COLORWRITEENABLE2 = 91,
+	SVGA3D_RS_COLORWRITEENABLE3 = 92,
+	SVGA3D_RS_SEPARATEALPHABLENDENABLE = 93,
+	SVGA3D_RS_SRCBLENDALPHA = 94,
+	SVGA3D_RS_DSTBLENDALPHA = 95,
+	SVGA3D_RS_BLENDEQUATIONALPHA = 96,
+	SVGA3D_RS_TRANSPARENCYANTIALIAS = 97,
+	SVGA3D_RS_LINEWIDTH = 98,
+	SVGA3D_RS_MAX
 } SVGA3dRenderStateName;
 
 typedef enum {
-   SVGA3D_TRANSPARENCYANTIALIAS_NORMAL            = 0,
-   SVGA3D_TRANSPARENCYANTIALIAS_ALPHATOCOVERAGE   = 1,
-   SVGA3D_TRANSPARENCYANTIALIAS_SUPERSAMPLE       = 2,
-   SVGA3D_TRANSPARENCYANTIALIAS_MAX
+	SVGA3D_TRANSPARENCYANTIALIAS_NORMAL = 0,
+	SVGA3D_TRANSPARENCYANTIALIAS_ALPHATOCOVERAGE = 1,
+	SVGA3D_TRANSPARENCYANTIALIAS_SUPERSAMPLE = 2,
+	SVGA3D_TRANSPARENCYANTIALIAS_MAX
 } SVGA3dTransparencyAntialiasType;
 
 typedef enum {
-   SVGA3D_VERTEXMATERIAL_NONE     = 0,    /* Use the value in the current material */
-   SVGA3D_VERTEXMATERIAL_DIFFUSE  = 1,    /* Use the value in the diffuse component */
-   SVGA3D_VERTEXMATERIAL_SPECULAR = 2,    /* Use the value in the specular component */
-   SVGA3D_VERTEXMATERIAL_MAX      = 3,
+	SVGA3D_VERTEXMATERIAL_NONE = 0,
+	SVGA3D_VERTEXMATERIAL_DIFFUSE = 1,
+	SVGA3D_VERTEXMATERIAL_SPECULAR = 2,
+	SVGA3D_VERTEXMATERIAL_MAX = 3,
 } SVGA3dVertexMaterial;
 
 typedef enum {
-   SVGA3D_FILLMODE_INVALID = 0,
-   SVGA3D_FILLMODE_MIN     = 1,
-   SVGA3D_FILLMODE_POINT   = 1,
-   SVGA3D_FILLMODE_LINE    = 2,
-   SVGA3D_FILLMODE_FILL    = 3,
-   SVGA3D_FILLMODE_MAX
+	SVGA3D_FILLMODE_INVALID = 0,
+	SVGA3D_FILLMODE_MIN = 1,
+	SVGA3D_FILLMODE_POINT = 1,
+	SVGA3D_FILLMODE_LINE = 2,
+	SVGA3D_FILLMODE_FILL = 3,
+	SVGA3D_FILLMODE_MAX
 } SVGA3dFillModeType;
 
-
-typedef
-#include "vmware_pack_begin.h"
-union {
-   struct {
-      uint16   mode;       /* SVGA3dFillModeType */
-      uint16   face;       /* SVGA3dFace */
-   };
-   uint32 uintValue;
-}
-#include "vmware_pack_end.h"
-SVGA3dFillMode;
+#pragma pack(push, 1)
+typedef union {
+	struct {
+		uint16 mode;
+		uint16 face;
+	};
+	uint32 uintValue;
+} SVGA3dFillMode;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA3D_SHADEMODE_INVALID = 0,
-   SVGA3D_SHADEMODE_FLAT    = 1,
-   SVGA3D_SHADEMODE_SMOOTH  = 2,
-   SVGA3D_SHADEMODE_PHONG   = 3,     /* Not supported */
-   SVGA3D_SHADEMODE_MAX
+	SVGA3D_SHADEMODE_INVALID = 0,
+	SVGA3D_SHADEMODE_FLAT = 1,
+	SVGA3D_SHADEMODE_SMOOTH = 2,
+	SVGA3D_SHADEMODE_PHONG = 3,
+	SVGA3D_SHADEMODE_MAX
 } SVGA3dShadeMode;
 
-typedef
-#include "vmware_pack_begin.h"
-union {
-   struct {
-      uint16 repeat;
-      uint16 pattern;
-   };
-   uint32 uintValue;
-}
-#include "vmware_pack_end.h"
-SVGA3dLinePattern;
+#pragma pack(push, 1)
+typedef union {
+	struct {
+		uint16 repeat;
+		uint16 pattern;
+	};
+	uint32 uintValue;
+} SVGA3dLinePattern;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA3D_BLENDOP_INVALID             = 0,
-   SVGA3D_BLENDOP_MIN                 = 1,
-   SVGA3D_BLENDOP_ZERO                = 1,
-   SVGA3D_BLENDOP_ONE                 = 2,
-   SVGA3D_BLENDOP_SRCCOLOR            = 3,
-   SVGA3D_BLENDOP_INVSRCCOLOR         = 4,
-   SVGA3D_BLENDOP_SRCALPHA            = 5,
-   SVGA3D_BLENDOP_INVSRCALPHA         = 6,
-   SVGA3D_BLENDOP_DESTALPHA           = 7,
-   SVGA3D_BLENDOP_INVDESTALPHA        = 8,
-   SVGA3D_BLENDOP_DESTCOLOR           = 9,
-   SVGA3D_BLENDOP_INVDESTCOLOR        = 10,
-   SVGA3D_BLENDOP_SRCALPHASAT         = 11,
-   SVGA3D_BLENDOP_BLENDFACTOR         = 12,
-   SVGA3D_BLENDOP_INVBLENDFACTOR      = 13,
-   SVGA3D_BLENDOP_SRC1COLOR           = 14,
-   SVGA3D_BLENDOP_INVSRC1COLOR        = 15,
-   SVGA3D_BLENDOP_SRC1ALPHA           = 16,
-   SVGA3D_BLENDOP_INVSRC1ALPHA        = 17,
-   SVGA3D_BLENDOP_BLENDFACTORALPHA    = 18,
-   SVGA3D_BLENDOP_INVBLENDFACTORALPHA = 19,
-   SVGA3D_BLENDOP_MAX
+	SVGA3D_BLENDOP_INVALID = 0,
+	SVGA3D_BLENDOP_MIN = 1,
+	SVGA3D_BLENDOP_ZERO = 1,
+	SVGA3D_BLENDOP_ONE = 2,
+	SVGA3D_BLENDOP_SRCCOLOR = 3,
+	SVGA3D_BLENDOP_INVSRCCOLOR = 4,
+	SVGA3D_BLENDOP_SRCALPHA = 5,
+	SVGA3D_BLENDOP_INVSRCALPHA = 6,
+	SVGA3D_BLENDOP_DESTALPHA = 7,
+	SVGA3D_BLENDOP_INVDESTALPHA = 8,
+	SVGA3D_BLENDOP_DESTCOLOR = 9,
+	SVGA3D_BLENDOP_INVDESTCOLOR = 10,
+	SVGA3D_BLENDOP_SRCALPHASAT = 11,
+	SVGA3D_BLENDOP_BLENDFACTOR = 12,
+	SVGA3D_BLENDOP_INVBLENDFACTOR = 13,
+	SVGA3D_BLENDOP_SRC1COLOR = 14,
+	SVGA3D_BLENDOP_INVSRC1COLOR = 15,
+	SVGA3D_BLENDOP_SRC1ALPHA = 16,
+	SVGA3D_BLENDOP_INVSRC1ALPHA = 17,
+	SVGA3D_BLENDOP_BLENDFACTORALPHA = 18,
+	SVGA3D_BLENDOP_INVBLENDFACTORALPHA = 19,
+	SVGA3D_BLENDOP_MAX
 } SVGA3dBlendOp;
 
 typedef enum {
-   SVGA3D_BLENDEQ_INVALID            = 0,
-   SVGA3D_BLENDEQ_MIN                = 1,
-   SVGA3D_BLENDEQ_ADD                = 1,
-   SVGA3D_BLENDEQ_SUBTRACT           = 2,
-   SVGA3D_BLENDEQ_REVSUBTRACT        = 3,
-   SVGA3D_BLENDEQ_MINIMUM            = 4,
-   SVGA3D_BLENDEQ_MAXIMUM            = 5,
-   SVGA3D_BLENDEQ_MAX
+	SVGA3D_BLENDEQ_INVALID = 0,
+	SVGA3D_BLENDEQ_MIN = 1,
+	SVGA3D_BLENDEQ_ADD = 1,
+	SVGA3D_BLENDEQ_SUBTRACT = 2,
+	SVGA3D_BLENDEQ_REVSUBTRACT = 3,
+	SVGA3D_BLENDEQ_MINIMUM = 4,
+	SVGA3D_BLENDEQ_MAXIMUM = 5,
+	SVGA3D_BLENDEQ_MAX
 } SVGA3dBlendEquation;
 
 typedef enum {
-   SVGA3D_DX11_LOGICOP_MIN           = 0,
-   SVGA3D_DX11_LOGICOP_CLEAR         = 0,
-   SVGA3D_DX11_LOGICOP_SET           = 1,
-   SVGA3D_DX11_LOGICOP_COPY          = 2,
-   SVGA3D_DX11_LOGICOP_COPY_INVERTED = 3,
-   SVGA3D_DX11_LOGICOP_NOOP          = 4,
-   SVGA3D_DX11_LOGICOP_INVERT        = 5,
-   SVGA3D_DX11_LOGICOP_AND           = 6,
-   SVGA3D_DX11_LOGICOP_NAND          = 7,
-   SVGA3D_DX11_LOGICOP_OR            = 8,
-   SVGA3D_DX11_LOGICOP_NOR           = 9,
-   SVGA3D_DX11_LOGICOP_XOR           = 10,
-   SVGA3D_DX11_LOGICOP_EQUIV         = 11,
-   SVGA3D_DX11_LOGICOP_AND_REVERSE   = 12,
-   SVGA3D_DX11_LOGICOP_AND_INVERTED  = 13,
-   SVGA3D_DX11_LOGICOP_OR_REVERSE    = 14,
-   SVGA3D_DX11_LOGICOP_OR_INVERTED   = 15,
-   SVGA3D_DX11_LOGICOP_MAX
+	SVGA3D_DX11_LOGICOP_MIN = 0,
+	SVGA3D_DX11_LOGICOP_CLEAR = 0,
+	SVGA3D_DX11_LOGICOP_SET = 1,
+	SVGA3D_DX11_LOGICOP_COPY = 2,
+	SVGA3D_DX11_LOGICOP_COPY_INVERTED = 3,
+	SVGA3D_DX11_LOGICOP_NOOP = 4,
+	SVGA3D_DX11_LOGICOP_INVERT = 5,
+	SVGA3D_DX11_LOGICOP_AND = 6,
+	SVGA3D_DX11_LOGICOP_NAND = 7,
+	SVGA3D_DX11_LOGICOP_OR = 8,
+	SVGA3D_DX11_LOGICOP_NOR = 9,
+	SVGA3D_DX11_LOGICOP_XOR = 10,
+	SVGA3D_DX11_LOGICOP_EQUIV = 11,
+	SVGA3D_DX11_LOGICOP_AND_REVERSE = 12,
+	SVGA3D_DX11_LOGICOP_AND_INVERTED = 13,
+	SVGA3D_DX11_LOGICOP_OR_REVERSE = 14,
+	SVGA3D_DX11_LOGICOP_OR_INVERTED = 15,
+	SVGA3D_DX11_LOGICOP_MAX
 } SVGA3dDX11LogicOp;
 
 typedef enum {
-   SVGA3D_FRONTWINDING_INVALID = 0,
-   SVGA3D_FRONTWINDING_CW      = 1,
-   SVGA3D_FRONTWINDING_CCW     = 2,
-   SVGA3D_FRONTWINDING_MAX
+	SVGA3D_FRONTWINDING_INVALID = 0,
+	SVGA3D_FRONTWINDING_CW = 1,
+	SVGA3D_FRONTWINDING_MIN = 1,
+	SVGA3D_FRONTWINDING_CCW = 2,
+	SVGA3D_FRONTWINDING_MAX
 } SVGA3dFrontWinding;
 
 typedef enum {
-   SVGA3D_FACE_INVALID  = 0,
-   SVGA3D_FACE_NONE     = 1,
-   SVGA3D_FACE_MIN      = 1,
-   SVGA3D_FACE_FRONT    = 2,
-   SVGA3D_FACE_BACK     = 3,
-   SVGA3D_FACE_FRONT_BACK = 4,
-   SVGA3D_FACE_MAX
+	SVGA3D_FACE_INVALID = 0,
+	SVGA3D_FACE_NONE = 1,
+	SVGA3D_FACE_MIN = 1,
+	SVGA3D_FACE_FRONT = 2,
+	SVGA3D_FACE_BACK = 3,
+	SVGA3D_FACE_FRONT_BACK = 4,
+	SVGA3D_FACE_MAX
 } SVGA3dFace;
 
-/*
- * The order and the values should not be changed
- */
-
 typedef enum {
-   SVGA3D_CMP_INVALID              = 0,
-   SVGA3D_CMP_NEVER                = 1,
-   SVGA3D_CMP_LESS                 = 2,
-   SVGA3D_CMP_EQUAL                = 3,
-   SVGA3D_CMP_LESSEQUAL            = 4,
-   SVGA3D_CMP_GREATER              = 5,
-   SVGA3D_CMP_NOTEQUAL             = 6,
-   SVGA3D_CMP_GREATEREQUAL         = 7,
-   SVGA3D_CMP_ALWAYS               = 8,
-   SVGA3D_CMP_MAX
+	SVGA3D_CMP_INVALID = 0,
+	SVGA3D_CMP_NEVER = 1,
+	SVGA3D_CMP_LESS = 2,
+	SVGA3D_CMP_EQUAL = 3,
+	SVGA3D_CMP_LESSEQUAL = 4,
+	SVGA3D_CMP_GREATER = 5,
+	SVGA3D_CMP_NOTEQUAL = 6,
+	SVGA3D_CMP_GREATEREQUAL = 7,
+	SVGA3D_CMP_ALWAYS = 8,
+	SVGA3D_CMP_MAX
 } SVGA3dCmpFunc;
 
-/*
- * SVGA3D_FOGFUNC_* specifies the fog equation, or PER_VERTEX which allows
- * the fog factor to be specified in the alpha component of the specular
- * (a.k.a. secondary) vertex color.
- */
 typedef enum {
-   SVGA3D_FOGFUNC_INVALID          = 0,
-   SVGA3D_FOGFUNC_EXP              = 1,
-   SVGA3D_FOGFUNC_EXP2             = 2,
-   SVGA3D_FOGFUNC_LINEAR           = 3,
-   SVGA3D_FOGFUNC_PER_VERTEX       = 4
+	SVGA3D_FOGFUNC_INVALID = 0,
+	SVGA3D_FOGFUNC_EXP = 1,
+	SVGA3D_FOGFUNC_EXP2 = 2,
+	SVGA3D_FOGFUNC_LINEAR = 3,
+	SVGA3D_FOGFUNC_PER_VERTEX = 4
 } SVGA3dFogFunction;
 
-/*
- * SVGA3D_FOGTYPE_* specifies if fog factors are computed on a per-vertex
- * or per-pixel basis.
- */
 typedef enum {
-   SVGA3D_FOGTYPE_INVALID          = 0,
-   SVGA3D_FOGTYPE_VERTEX           = 1,
-   SVGA3D_FOGTYPE_PIXEL            = 2,
-   SVGA3D_FOGTYPE_MAX              = 3
+	SVGA3D_FOGTYPE_INVALID = 0,
+	SVGA3D_FOGTYPE_VERTEX = 1,
+	SVGA3D_FOGTYPE_PIXEL = 2,
+	SVGA3D_FOGTYPE_MAX = 3
 } SVGA3dFogType;
 
-/*
- * SVGA3D_FOGBASE_* selects depth or range-based fog. Depth-based fog is
- * computed using the eye Z value of each pixel (or vertex), whereas range-
- * based fog is computed using the actual distance (range) to the eye.
- */
 typedef enum {
-   SVGA3D_FOGBASE_INVALID          = 0,
-   SVGA3D_FOGBASE_DEPTHBASED       = 1,
-   SVGA3D_FOGBASE_RANGEBASED       = 2,
-   SVGA3D_FOGBASE_MAX              = 3
+	SVGA3D_FOGBASE_INVALID = 0,
+	SVGA3D_FOGBASE_DEPTHBASED = 1,
+	SVGA3D_FOGBASE_RANGEBASED = 2,
+	SVGA3D_FOGBASE_MAX = 3
 } SVGA3dFogBase;
 
 typedef enum {
-   SVGA3D_STENCILOP_INVALID        = 0,
-   SVGA3D_STENCILOP_MIN            = 1,
-   SVGA3D_STENCILOP_KEEP           = 1,
-   SVGA3D_STENCILOP_ZERO           = 2,
-   SVGA3D_STENCILOP_REPLACE        = 3,
-   SVGA3D_STENCILOP_INCRSAT        = 4,
-   SVGA3D_STENCILOP_DECRSAT        = 5,
-   SVGA3D_STENCILOP_INVERT         = 6,
-   SVGA3D_STENCILOP_INCR           = 7,
-   SVGA3D_STENCILOP_DECR           = 8,
-   SVGA3D_STENCILOP_MAX
+	SVGA3D_STENCILOP_INVALID = 0,
+	SVGA3D_STENCILOP_MIN = 1,
+	SVGA3D_STENCILOP_KEEP = 1,
+	SVGA3D_STENCILOP_ZERO = 2,
+	SVGA3D_STENCILOP_REPLACE = 3,
+	SVGA3D_STENCILOP_INCRSAT = 4,
+	SVGA3D_STENCILOP_DECRSAT = 5,
+	SVGA3D_STENCILOP_INVERT = 6,
+	SVGA3D_STENCILOP_INCR = 7,
+	SVGA3D_STENCILOP_DECR = 8,
+	SVGA3D_STENCILOP_MAX
 } SVGA3dStencilOp;
 
 typedef enum {
-   SVGA3D_CLIPPLANE_0              = (1 << 0),
-   SVGA3D_CLIPPLANE_1              = (1 << 1),
-   SVGA3D_CLIPPLANE_2              = (1 << 2),
-   SVGA3D_CLIPPLANE_3              = (1 << 3),
-   SVGA3D_CLIPPLANE_4              = (1 << 4),
-   SVGA3D_CLIPPLANE_5              = (1 << 5),
+	SVGA3D_CLIPPLANE_0 = (1 << 0),
+	SVGA3D_CLIPPLANE_1 = (1 << 1),
+	SVGA3D_CLIPPLANE_2 = (1 << 2),
+	SVGA3D_CLIPPLANE_3 = (1 << 3),
+	SVGA3D_CLIPPLANE_4 = (1 << 4),
+	SVGA3D_CLIPPLANE_5 = (1 << 5),
 } SVGA3dClipPlanes;
 
 typedef enum {
-   SVGA3D_CLEAR_COLOR              = 0x1,
-   SVGA3D_CLEAR_DEPTH              = 0x2,
-   SVGA3D_CLEAR_STENCIL            = 0x4,
-
-   /*
-    * Hint only, must be used together with SVGA3D_CLEAR_COLOR. If
-    * SVGA3D_CLEAR_DEPTH or SVGA3D_CLEAR_STENCIL bit is set, this
-    * bit will be ignored.
-    */
-   SVGA3D_CLEAR_COLORFILL          = 0x8
+	SVGA3D_CLEAR_COLOR = 0x1,
+	SVGA3D_CLEAR_DEPTH = 0x2,
+	SVGA3D_CLEAR_STENCIL = 0x4,
+
+	SVGA3D_CLEAR_COLORFILL = 0x8
 } SVGA3dClearFlag;
 
 typedef enum {
-   SVGA3D_RT_DEPTH                 = 0,
-   SVGA3D_RT_MIN                   = 0,
-   SVGA3D_RT_STENCIL               = 1,
-   SVGA3D_RT_COLOR0                = 2,
-   SVGA3D_RT_COLOR1                = 3,
-   SVGA3D_RT_COLOR2                = 4,
-   SVGA3D_RT_COLOR3                = 5,
-   SVGA3D_RT_COLOR4                = 6,
-   SVGA3D_RT_COLOR5                = 7,
-   SVGA3D_RT_COLOR6                = 8,
-   SVGA3D_RT_COLOR7                = 9,
-   SVGA3D_RT_MAX,
-   SVGA3D_RT_INVALID               = ((uint32)-1),
+	SVGA3D_RT_DEPTH = 0,
+	SVGA3D_RT_MIN = 0,
+	SVGA3D_RT_STENCIL = 1,
+	SVGA3D_RT_COLOR0 = 2,
+	SVGA3D_RT_COLOR1 = 3,
+	SVGA3D_RT_COLOR2 = 4,
+	SVGA3D_RT_COLOR3 = 5,
+	SVGA3D_RT_COLOR4 = 6,
+	SVGA3D_RT_COLOR5 = 7,
+	SVGA3D_RT_COLOR6 = 8,
+	SVGA3D_RT_COLOR7 = 9,
+	SVGA3D_RT_MAX,
+	SVGA3D_RT_INVALID = ((uint32)-1),
 } SVGA3dRenderTargetType;
 
 #define SVGA3D_MAX_RT_COLOR (SVGA3D_RT_COLOR7 - SVGA3D_RT_COLOR0 + 1)
 
-typedef
-#include "vmware_pack_begin.h"
-union {
-   struct {
-      uint32  red   : 1;
-      uint32  green : 1;
-      uint32  blue  : 1;
-      uint32  alpha : 1;
-   };
-   uint32 uintValue;
-}
-#include "vmware_pack_end.h"
-SVGA3dColorMask;
+#pragma pack(push, 1)
+typedef union {
+	struct {
+		uint32 red : 1;
+		uint32 green : 1;
+		uint32 blue : 1;
+		uint32 alpha : 1;
+	};
+	uint32 uintValue;
+} SVGA3dColorMask;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA3D_VBLEND_DISABLE            = 0,
-   SVGA3D_VBLEND_1WEIGHT            = 1,
-   SVGA3D_VBLEND_2WEIGHT            = 2,
-   SVGA3D_VBLEND_3WEIGHT            = 3,
-   SVGA3D_VBLEND_MAX                = 4,
+	SVGA3D_VBLEND_DISABLE = 0,
+	SVGA3D_VBLEND_1WEIGHT = 1,
+	SVGA3D_VBLEND_2WEIGHT = 2,
+	SVGA3D_VBLEND_3WEIGHT = 3,
+	SVGA3D_VBLEND_MAX = 4,
 } SVGA3dVertexBlendFlags;
 
 typedef enum {
-   SVGA3D_WRAPCOORD_0   = 1 << 0,
-   SVGA3D_WRAPCOORD_1   = 1 << 1,
-   SVGA3D_WRAPCOORD_2   = 1 << 2,
-   SVGA3D_WRAPCOORD_3   = 1 << 3,
-   SVGA3D_WRAPCOORD_ALL = 0xF,
+	SVGA3D_WRAPCOORD_0 = 1 << 0,
+	SVGA3D_WRAPCOORD_1 = 1 << 1,
+	SVGA3D_WRAPCOORD_2 = 1 << 2,
+	SVGA3D_WRAPCOORD_3 = 1 << 3,
+	SVGA3D_WRAPCOORD_ALL = 0xF,
 } SVGA3dWrapFlags;
 
-/*
- * SVGA_3D_CMD_TEXTURESTATE Types.  All value types
- * must fit in a uint32.
- */
-
 typedef enum {
-   SVGA3D_TS_INVALID                    = 0,
-   SVGA3D_TS_MIN                        = 1,
-   SVGA3D_TS_BIND_TEXTURE               = 1,    /* SVGA3dSurfaceId */
-   SVGA3D_TS_COLOROP                    = 2,    /* SVGA3dTextureCombiner */
-   SVGA3D_TS_COLORARG1                  = 3,    /* SVGA3dTextureArgData */
-   SVGA3D_TS_COLORARG2                  = 4,    /* SVGA3dTextureArgData */
-   SVGA3D_TS_ALPHAOP                    = 5,    /* SVGA3dTextureCombiner */
-   SVGA3D_TS_ALPHAARG1                  = 6,    /* SVGA3dTextureArgData */
-   SVGA3D_TS_ALPHAARG2                  = 7,    /* SVGA3dTextureArgData */
-   SVGA3D_TS_ADDRESSU                   = 8,    /* SVGA3dTextureAddress */
-   SVGA3D_TS_ADDRESSV                   = 9,    /* SVGA3dTextureAddress */
-   SVGA3D_TS_MIPFILTER                  = 10,   /* SVGA3dTextureFilter */
-   SVGA3D_TS_MAGFILTER                  = 11,   /* SVGA3dTextureFilter */
-   SVGA3D_TS_MINFILTER                  = 12,   /* SVGA3dTextureFilter */
-   SVGA3D_TS_BORDERCOLOR                = 13,   /* SVGA3dColor */
-   SVGA3D_TS_TEXCOORDINDEX              = 14,   /* uint32 */
-   SVGA3D_TS_TEXTURETRANSFORMFLAGS      = 15,   /* SVGA3dTexTransformFlags */
-   SVGA3D_TS_TEXCOORDGEN                = 16,   /* SVGA3dTextureCoordGen */
-   SVGA3D_TS_BUMPENVMAT00               = 17,   /* float */
-   SVGA3D_TS_BUMPENVMAT01               = 18,   /* float */
-   SVGA3D_TS_BUMPENVMAT10               = 19,   /* float */
-   SVGA3D_TS_BUMPENVMAT11               = 20,   /* float */
-   SVGA3D_TS_TEXTURE_MIPMAP_LEVEL       = 21,   /* uint32 */
-   SVGA3D_TS_TEXTURE_LOD_BIAS           = 22,   /* float */
-   SVGA3D_TS_TEXTURE_ANISOTROPIC_LEVEL  = 23,   /* uint32 */
-   SVGA3D_TS_ADDRESSW                   = 24,   /* SVGA3dTextureAddress */
-
-
-   /*
-    * Sampler Gamma Level
-    *
-    * Sampler gamma effects the color of samples taken from the sampler.  A
-    * value of 1.0 will produce linear samples.  If the value is <= 0.0 the
-    * gamma value is ignored and a linear space is used.
-    */
-
-   SVGA3D_TS_GAMMA                      = 25,   /* float */
-   SVGA3D_TS_BUMPENVLSCALE              = 26,   /* float */
-   SVGA3D_TS_BUMPENVLOFFSET             = 27,   /* float */
-   SVGA3D_TS_COLORARG0                  = 28,   /* SVGA3dTextureArgData */
-   SVGA3D_TS_ALPHAARG0                  = 29,   /* SVGA3dTextureArgData */
-   SVGA3D_TS_PREGB_MAX                  = 30,   /* Max value before GBObjects */
-   SVGA3D_TS_CONSTANT                   = 30,   /* SVGA3dColor */
-   SVGA3D_TS_COLOR_KEY_ENABLE           = 31,   /* SVGA3dBool */
-   SVGA3D_TS_COLOR_KEY                  = 32,   /* SVGA3dColor */
-   SVGA3D_TS_MAX
+	SVGA3D_TS_INVALID = 0,
+	SVGA3D_TS_MIN = 1,
+	SVGA3D_TS_BIND_TEXTURE = 1,
+	SVGA3D_TS_COLOROP = 2,
+	SVGA3D_TS_COLORARG1 = 3,
+	SVGA3D_TS_COLORARG2 = 4,
+	SVGA3D_TS_ALPHAOP = 5,
+	SVGA3D_TS_ALPHAARG1 = 6,
+	SVGA3D_TS_ALPHAARG2 = 7,
+	SVGA3D_TS_ADDRESSU = 8,
+	SVGA3D_TS_ADDRESSV = 9,
+	SVGA3D_TS_MIPFILTER = 10,
+	SVGA3D_TS_MAGFILTER = 11,
+	SVGA3D_TS_MINFILTER = 12,
+	SVGA3D_TS_BORDERCOLOR = 13,
+	SVGA3D_TS_TEXCOORDINDEX = 14,
+	SVGA3D_TS_TEXTURETRANSFORMFLAGS = 15,
+	SVGA3D_TS_TEXCOORDGEN = 16,
+	SVGA3D_TS_BUMPENVMAT00 = 17,
+	SVGA3D_TS_BUMPENVMAT01 = 18,
+	SVGA3D_TS_BUMPENVMAT10 = 19,
+	SVGA3D_TS_BUMPENVMAT11 = 20,
+	SVGA3D_TS_TEXTURE_MIPMAP_LEVEL = 21,
+	SVGA3D_TS_TEXTURE_LOD_BIAS = 22,
+	SVGA3D_TS_TEXTURE_ANISOTROPIC_LEVEL = 23,
+	SVGA3D_TS_ADDRESSW = 24,
+
+	SVGA3D_TS_GAMMA = 25,
+	SVGA3D_TS_BUMPENVLSCALE = 26,
+	SVGA3D_TS_BUMPENVLOFFSET = 27,
+	SVGA3D_TS_COLORARG0 = 28,
+	SVGA3D_TS_ALPHAARG0 = 29,
+	SVGA3D_TS_PREGB_MAX = 30,
+	SVGA3D_TS_CONSTANT = 30,
+	SVGA3D_TS_COLOR_KEY_ENABLE = 31,
+	SVGA3D_TS_COLOR_KEY = 32,
+	SVGA3D_TS_MAX
 } SVGA3dTextureStateName;
 
 typedef enum {
-   SVGA3D_TC_INVALID                   = 0,
-   SVGA3D_TC_DISABLE                   = 1,
-   SVGA3D_TC_SELECTARG1                = 2,
-   SVGA3D_TC_SELECTARG2                = 3,
-   SVGA3D_TC_MODULATE                  = 4,
-   SVGA3D_TC_ADD                       = 5,
-   SVGA3D_TC_ADDSIGNED                 = 6,
-   SVGA3D_TC_SUBTRACT                  = 7,
-   SVGA3D_TC_BLENDTEXTUREALPHA         = 8,
-   SVGA3D_TC_BLENDDIFFUSEALPHA         = 9,
-   SVGA3D_TC_BLENDCURRENTALPHA         = 10,
-   SVGA3D_TC_BLENDFACTORALPHA          = 11,
-   SVGA3D_TC_MODULATE2X                = 12,
-   SVGA3D_TC_MODULATE4X                = 13,
-   SVGA3D_TC_DSDT                      = 14,
-   SVGA3D_TC_DOTPRODUCT3               = 15,
-   SVGA3D_TC_BLENDTEXTUREALPHAPM       = 16,
-   SVGA3D_TC_ADDSIGNED2X               = 17,
-   SVGA3D_TC_ADDSMOOTH                 = 18,
-   SVGA3D_TC_PREMODULATE               = 19,
-   SVGA3D_TC_MODULATEALPHA_ADDCOLOR    = 20,
-   SVGA3D_TC_MODULATECOLOR_ADDALPHA    = 21,
-   SVGA3D_TC_MODULATEINVALPHA_ADDCOLOR = 22,
-   SVGA3D_TC_MODULATEINVCOLOR_ADDALPHA = 23,
-   SVGA3D_TC_BUMPENVMAPLUMINANCE       = 24,
-   SVGA3D_TC_MULTIPLYADD               = 25,
-   SVGA3D_TC_LERP                      = 26,
-   SVGA3D_TC_MAX
+	SVGA3D_TC_INVALID = 0,
+	SVGA3D_TC_DISABLE = 1,
+	SVGA3D_TC_SELECTARG1 = 2,
+	SVGA3D_TC_SELECTARG2 = 3,
+	SVGA3D_TC_MODULATE = 4,
+	SVGA3D_TC_ADD = 5,
+	SVGA3D_TC_ADDSIGNED = 6,
+	SVGA3D_TC_SUBTRACT = 7,
+	SVGA3D_TC_BLENDTEXTUREALPHA = 8,
+	SVGA3D_TC_BLENDDIFFUSEALPHA = 9,
+	SVGA3D_TC_BLENDCURRENTALPHA = 10,
+	SVGA3D_TC_BLENDFACTORALPHA = 11,
+	SVGA3D_TC_MODULATE2X = 12,
+	SVGA3D_TC_MODULATE4X = 13,
+	SVGA3D_TC_DSDT = 14,
+	SVGA3D_TC_DOTPRODUCT3 = 15,
+	SVGA3D_TC_BLENDTEXTUREALPHAPM = 16,
+	SVGA3D_TC_ADDSIGNED2X = 17,
+	SVGA3D_TC_ADDSMOOTH = 18,
+	SVGA3D_TC_PREMODULATE = 19,
+	SVGA3D_TC_MODULATEALPHA_ADDCOLOR = 20,
+	SVGA3D_TC_MODULATECOLOR_ADDALPHA = 21,
+	SVGA3D_TC_MODULATEINVALPHA_ADDCOLOR = 22,
+	SVGA3D_TC_MODULATEINVCOLOR_ADDALPHA = 23,
+	SVGA3D_TC_BUMPENVMAPLUMINANCE = 24,
+	SVGA3D_TC_MULTIPLYADD = 25,
+	SVGA3D_TC_LERP = 26,
+	SVGA3D_TC_MAX
 } SVGA3dTextureCombiner;
 
-#define SVGA3D_TC_CAP_BIT(svga3d_tc_op) (svga3d_tc_op ? (1 << (svga3d_tc_op - 1)) : 0)
+#define SVGA3D_TC_CAP_BIT(svga3d_tc_op)                                        \
+	(svga3d_tc_op ? (1 << (svga3d_tc_op - 1)) : 0)
 
 typedef enum {
-   SVGA3D_TEX_ADDRESS_INVALID    = 0,
-   SVGA3D_TEX_ADDRESS_MIN        = 1,
-   SVGA3D_TEX_ADDRESS_WRAP       = 1,
-   SVGA3D_TEX_ADDRESS_MIRROR     = 2,
-   SVGA3D_TEX_ADDRESS_CLAMP      = 3,
-   SVGA3D_TEX_ADDRESS_BORDER     = 4,
-   SVGA3D_TEX_ADDRESS_MIRRORONCE = 5,
-   SVGA3D_TEX_ADDRESS_EDGE       = 6,
-   SVGA3D_TEX_ADDRESS_MAX
+	SVGA3D_TEX_ADDRESS_INVALID = 0,
+	SVGA3D_TEX_ADDRESS_MIN = 1,
+	SVGA3D_TEX_ADDRESS_WRAP = 1,
+	SVGA3D_TEX_ADDRESS_MIRROR = 2,
+	SVGA3D_TEX_ADDRESS_CLAMP = 3,
+	SVGA3D_TEX_ADDRESS_BORDER = 4,
+	SVGA3D_TEX_ADDRESS_MIRRORONCE = 5,
+	SVGA3D_TEX_ADDRESS_EDGE = 6,
+	SVGA3D_TEX_ADDRESS_MAX
 } SVGA3dTextureAddress;
 
-/*
- * SVGA3D_TEX_FILTER_NONE as the minification filter means mipmapping is
- * disabled, and the rasterizer should use the magnification filter instead.
- */
 typedef enum {
-   SVGA3D_TEX_FILTER_NONE           = 0,
-   SVGA3D_TEX_FILTER_MIN            = 0,
-   SVGA3D_TEX_FILTER_NEAREST        = 1,
-   SVGA3D_TEX_FILTER_LINEAR         = 2,
-   SVGA3D_TEX_FILTER_ANISOTROPIC    = 3,
-   SVGA3D_TEX_FILTER_FLATCUBIC      = 4, /* Deprecated, not implemented */
-   SVGA3D_TEX_FILTER_GAUSSIANCUBIC  = 5, /* Deprecated, not implemented */
-   SVGA3D_TEX_FILTER_PYRAMIDALQUAD  = 6, /* Not currently implemented */
-   SVGA3D_TEX_FILTER_GAUSSIANQUAD   = 7, /* Not currently implemented */
-   SVGA3D_TEX_FILTER_MAX
+	SVGA3D_TEX_FILTER_NONE = 0,
+	SVGA3D_TEX_FILTER_MIN = 0,
+	SVGA3D_TEX_FILTER_NEAREST = 1,
+	SVGA3D_TEX_FILTER_LINEAR = 2,
+	SVGA3D_TEX_FILTER_ANISOTROPIC = 3,
+	SVGA3D_TEX_FILTER_FLATCUBIC = 4,
+	SVGA3D_TEX_FILTER_GAUSSIANCUBIC = 5,
+	SVGA3D_TEX_FILTER_PYRAMIDALQUAD = 6,
+	SVGA3D_TEX_FILTER_GAUSSIANQUAD = 7,
+	SVGA3D_TEX_FILTER_MAX
 } SVGA3dTextureFilter;
 
 typedef enum {
-   SVGA3D_TEX_TRANSFORM_OFF    = 0,
-   SVGA3D_TEX_TRANSFORM_S      = (1 << 0),
-   SVGA3D_TEX_TRANSFORM_T      = (1 << 1),
-   SVGA3D_TEX_TRANSFORM_R      = (1 << 2),
-   SVGA3D_TEX_TRANSFORM_Q      = (1 << 3),
-   SVGA3D_TEX_PROJECTED        = (1 << 15),
+	SVGA3D_TEX_TRANSFORM_OFF = 0,
+	SVGA3D_TEX_TRANSFORM_S = (1 << 0),
+	SVGA3D_TEX_TRANSFORM_T = (1 << 1),
+	SVGA3D_TEX_TRANSFORM_R = (1 << 2),
+	SVGA3D_TEX_TRANSFORM_Q = (1 << 3),
+	SVGA3D_TEX_PROJECTED = (1 << 15),
 } SVGA3dTexTransformFlags;
 
 typedef enum {
-   SVGA3D_TEXCOORD_GEN_OFF              = 0,
-   SVGA3D_TEXCOORD_GEN_EYE_POSITION     = 1,
-   SVGA3D_TEXCOORD_GEN_EYE_NORMAL       = 2,
-   SVGA3D_TEXCOORD_GEN_REFLECTIONVECTOR = 3,
-   SVGA3D_TEXCOORD_GEN_SPHERE           = 4,
-   SVGA3D_TEXCOORD_GEN_MAX
+	SVGA3D_TEXCOORD_GEN_OFF = 0,
+	SVGA3D_TEXCOORD_GEN_EYE_POSITION = 1,
+	SVGA3D_TEXCOORD_GEN_EYE_NORMAL = 2,
+	SVGA3D_TEXCOORD_GEN_REFLECTIONVECTOR = 3,
+	SVGA3D_TEXCOORD_GEN_SPHERE = 4,
+	SVGA3D_TEXCOORD_GEN_MAX
 } SVGA3dTextureCoordGen;
 
-/*
- * Texture argument constants for texture combiner
- */
 typedef enum {
-   SVGA3D_TA_INVALID    = 0,
-   SVGA3D_TA_TFACTOR    = 1,
-   SVGA3D_TA_PREVIOUS   = 2,
-   SVGA3D_TA_DIFFUSE    = 3,
-   SVGA3D_TA_TEXTURE    = 4,
-   SVGA3D_TA_SPECULAR   = 5,
-   SVGA3D_TA_CONSTANT   = 6,
-   SVGA3D_TA_MAX
+	SVGA3D_TA_INVALID = 0,
+	SVGA3D_TA_TFACTOR = 1,
+	SVGA3D_TA_PREVIOUS = 2,
+	SVGA3D_TA_DIFFUSE = 3,
+	SVGA3D_TA_TEXTURE = 4,
+	SVGA3D_TA_SPECULAR = 5,
+	SVGA3D_TA_CONSTANT = 6,
+	SVGA3D_TA_MAX
 } SVGA3dTextureArgData;
 
 #define SVGA3D_TM_MASK_LEN 4
 
-/* Modifiers for texture argument constants defined above. */
 typedef enum {
-   SVGA3D_TM_NONE       = 0,
-   SVGA3D_TM_ALPHA      = (1 << SVGA3D_TM_MASK_LEN),
-   SVGA3D_TM_ONE_MINUS  = (2 << SVGA3D_TM_MASK_LEN),
+	SVGA3D_TM_NONE = 0,
+	SVGA3D_TM_ALPHA = (1 << SVGA3D_TM_MASK_LEN),
+	SVGA3D_TM_ONE_MINUS = (2 << SVGA3D_TM_MASK_LEN),
 } SVGA3dTextureArgModifier;
 
-/*
- * Vertex declarations
- *
- * Notes:
- *
- * SVGA3D_DECLUSAGE_POSITIONT is for pre-transformed vertices. If you
- * draw with any POSITIONT vertex arrays, the programmable vertex
- * pipeline will be implicitly disabled. Drawing will take place as if
- * no vertex shader was bound.
- */
-
 typedef enum {
-   SVGA3D_DECLUSAGE_POSITION     = 0,
-   SVGA3D_DECLUSAGE_BLENDWEIGHT,
-   SVGA3D_DECLUSAGE_BLENDINDICES,
-   SVGA3D_DECLUSAGE_NORMAL,
-   SVGA3D_DECLUSAGE_PSIZE,
-   SVGA3D_DECLUSAGE_TEXCOORD,
-   SVGA3D_DECLUSAGE_TANGENT,
-   SVGA3D_DECLUSAGE_BINORMAL,
-   SVGA3D_DECLUSAGE_TESSFACTOR,
-   SVGA3D_DECLUSAGE_POSITIONT,
-   SVGA3D_DECLUSAGE_COLOR,
-   SVGA3D_DECLUSAGE_FOG,
-   SVGA3D_DECLUSAGE_DEPTH,
-   SVGA3D_DECLUSAGE_SAMPLE,
-   SVGA3D_DECLUSAGE_MAX
+	SVGA3D_DECLUSAGE_POSITION = 0,
+	SVGA3D_DECLUSAGE_BLENDWEIGHT,
+	SVGA3D_DECLUSAGE_BLENDINDICES,
+	SVGA3D_DECLUSAGE_NORMAL,
+	SVGA3D_DECLUSAGE_PSIZE,
+	SVGA3D_DECLUSAGE_TEXCOORD,
+	SVGA3D_DECLUSAGE_TANGENT,
+	SVGA3D_DECLUSAGE_BINORMAL,
+	SVGA3D_DECLUSAGE_TESSFACTOR,
+	SVGA3D_DECLUSAGE_POSITIONT,
+	SVGA3D_DECLUSAGE_COLOR,
+	SVGA3D_DECLUSAGE_FOG,
+	SVGA3D_DECLUSAGE_DEPTH,
+	SVGA3D_DECLUSAGE_SAMPLE,
+	SVGA3D_DECLUSAGE_MAX
 } SVGA3dDeclUsage;
 
 typedef enum {
-   SVGA3D_DECLMETHOD_DEFAULT     = 0,
-   SVGA3D_DECLMETHOD_PARTIALU,
-   SVGA3D_DECLMETHOD_PARTIALV,
-   SVGA3D_DECLMETHOD_CROSSUV,          /* Normal */
-   SVGA3D_DECLMETHOD_UV,
-   SVGA3D_DECLMETHOD_LOOKUP,           /* Lookup a displacement map */
-   SVGA3D_DECLMETHOD_LOOKUPPRESAMPLED, /* Lookup a pre-sampled displacement */
-                                       /* map */
+	SVGA3D_DECLMETHOD_DEFAULT = 0,
+	SVGA3D_DECLMETHOD_PARTIALU,
+	SVGA3D_DECLMETHOD_PARTIALV,
+	SVGA3D_DECLMETHOD_CROSSUV,
+	SVGA3D_DECLMETHOD_UV,
+	SVGA3D_DECLMETHOD_LOOKUP,
+	SVGA3D_DECLMETHOD_LOOKUPPRESAMPLED,
 } SVGA3dDeclMethod;
 
 typedef enum {
-   SVGA3D_DECLTYPE_FLOAT1        =  0,
-   SVGA3D_DECLTYPE_FLOAT2        =  1,
-   SVGA3D_DECLTYPE_FLOAT3        =  2,
-   SVGA3D_DECLTYPE_FLOAT4        =  3,
-   SVGA3D_DECLTYPE_D3DCOLOR      =  4,
-   SVGA3D_DECLTYPE_UBYTE4        =  5,
-   SVGA3D_DECLTYPE_SHORT2        =  6,
-   SVGA3D_DECLTYPE_SHORT4        =  7,
-   SVGA3D_DECLTYPE_UBYTE4N       =  8,
-   SVGA3D_DECLTYPE_SHORT2N       =  9,
-   SVGA3D_DECLTYPE_SHORT4N       = 10,
-   SVGA3D_DECLTYPE_USHORT2N      = 11,
-   SVGA3D_DECLTYPE_USHORT4N      = 12,
-   SVGA3D_DECLTYPE_UDEC3         = 13,
-   SVGA3D_DECLTYPE_DEC3N         = 14,
-   SVGA3D_DECLTYPE_FLOAT16_2     = 15,
-   SVGA3D_DECLTYPE_FLOAT16_4     = 16,
-   SVGA3D_DECLTYPE_MAX,
+	SVGA3D_DECLTYPE_FLOAT1 = 0,
+	SVGA3D_DECLTYPE_FLOAT2 = 1,
+	SVGA3D_DECLTYPE_FLOAT3 = 2,
+	SVGA3D_DECLTYPE_FLOAT4 = 3,
+	SVGA3D_DECLTYPE_D3DCOLOR = 4,
+	SVGA3D_DECLTYPE_UBYTE4 = 5,
+	SVGA3D_DECLTYPE_SHORT2 = 6,
+	SVGA3D_DECLTYPE_SHORT4 = 7,
+	SVGA3D_DECLTYPE_UBYTE4N = 8,
+	SVGA3D_DECLTYPE_SHORT2N = 9,
+	SVGA3D_DECLTYPE_SHORT4N = 10,
+	SVGA3D_DECLTYPE_USHORT2N = 11,
+	SVGA3D_DECLTYPE_USHORT4N = 12,
+	SVGA3D_DECLTYPE_UDEC3 = 13,
+	SVGA3D_DECLTYPE_DEC3N = 14,
+	SVGA3D_DECLTYPE_FLOAT16_2 = 15,
+	SVGA3D_DECLTYPE_FLOAT16_4 = 16,
+	SVGA3D_DECLTYPE_MAX,
 } SVGA3dDeclType;
 
-/*
- * This structure is used for the divisor for geometry instancing;
- * it's a direct translation of the Direct3D equivalent.
- */
 typedef union {
-   struct {
-      /*
-       * For index data, this number represents the number of instances to draw.
-       * For instance data, this number represents the number of
-       * instances/vertex in this stream
-       */
-      uint32 count : 30;
-
-      /*
-       * This is 1 if this is supposed to be the data that is repeated for
-       * every instance.
-       */
-      uint32 indexedData : 1;
-
-      /*
-       * This is 1 if this is supposed to be the per-instance data.
-       */
-      uint32 instanceData : 1;
-   };
-
-   uint32 value;
+	struct {
+		uint32 count : 30;
+
+		uint32 indexedData : 1;
+
+		uint32 instanceData : 1;
+	};
+
+	uint32 value;
 } SVGA3dVertexDivisor;
 
 typedef enum {
-   /*
-    * SVGA3D_PRIMITIVE_INVALID is a valid primitive type.
-    *
-    * List MIN second so debuggers will think INVALID is
-    * the correct name.
-    */
-   SVGA3D_PRIMITIVE_INVALID                     = 0,
-   SVGA3D_PRIMITIVE_MIN                         = 0,
-   SVGA3D_PRIMITIVE_TRIANGLELIST                = 1,
-   SVGA3D_PRIMITIVE_POINTLIST                   = 2,
-   SVGA3D_PRIMITIVE_LINELIST                    = 3,
-   SVGA3D_PRIMITIVE_LINESTRIP                   = 4,
-   SVGA3D_PRIMITIVE_TRIANGLESTRIP               = 5,
-   SVGA3D_PRIMITIVE_TRIANGLEFAN                 = 6,
-   SVGA3D_PRIMITIVE_LINELIST_ADJ                = 7,
-   SVGA3D_PRIMITIVE_PREDX_MAX                   = 7,
-   SVGA3D_PRIMITIVE_LINESTRIP_ADJ               = 8,
-   SVGA3D_PRIMITIVE_TRIANGLELIST_ADJ            = 9,
-   SVGA3D_PRIMITIVE_TRIANGLESTRIP_ADJ           = 10,
-   SVGA3D_PRIMITIVE_DX10_MAX                    = 11,
-   SVGA3D_PRIMITIVE_1_CONTROL_POINT_PATCH       = 11,
-   SVGA3D_PRIMITIVE_2_CONTROL_POINT_PATCH       = 12,
-   SVGA3D_PRIMITIVE_3_CONTROL_POINT_PATCH       = 13,
-   SVGA3D_PRIMITIVE_4_CONTROL_POINT_PATCH       = 14,
-   SVGA3D_PRIMITIVE_5_CONTROL_POINT_PATCH       = 15,
-   SVGA3D_PRIMITIVE_6_CONTROL_POINT_PATCH       = 16,
-   SVGA3D_PRIMITIVE_7_CONTROL_POINT_PATCH       = 17,
-   SVGA3D_PRIMITIVE_8_CONTROL_POINT_PATCH       = 18,
-   SVGA3D_PRIMITIVE_9_CONTROL_POINT_PATCH       = 19,
-   SVGA3D_PRIMITIVE_10_CONTROL_POINT_PATCH      = 20,
-   SVGA3D_PRIMITIVE_11_CONTROL_POINT_PATCH      = 21,
-   SVGA3D_PRIMITIVE_12_CONTROL_POINT_PATCH      = 22,
-   SVGA3D_PRIMITIVE_13_CONTROL_POINT_PATCH      = 23,
-   SVGA3D_PRIMITIVE_14_CONTROL_POINT_PATCH      = 24,
-   SVGA3D_PRIMITIVE_15_CONTROL_POINT_PATCH      = 25,
-   SVGA3D_PRIMITIVE_16_CONTROL_POINT_PATCH      = 26,
-   SVGA3D_PRIMITIVE_17_CONTROL_POINT_PATCH      = 27,
-   SVGA3D_PRIMITIVE_18_CONTROL_POINT_PATCH      = 28,
-   SVGA3D_PRIMITIVE_19_CONTROL_POINT_PATCH      = 29,
-   SVGA3D_PRIMITIVE_20_CONTROL_POINT_PATCH      = 30,
-   SVGA3D_PRIMITIVE_21_CONTROL_POINT_PATCH      = 31,
-   SVGA3D_PRIMITIVE_22_CONTROL_POINT_PATCH      = 32,
-   SVGA3D_PRIMITIVE_23_CONTROL_POINT_PATCH      = 33,
-   SVGA3D_PRIMITIVE_24_CONTROL_POINT_PATCH      = 34,
-   SVGA3D_PRIMITIVE_25_CONTROL_POINT_PATCH      = 35,
-   SVGA3D_PRIMITIVE_26_CONTROL_POINT_PATCH      = 36,
-   SVGA3D_PRIMITIVE_27_CONTROL_POINT_PATCH      = 37,
-   SVGA3D_PRIMITIVE_28_CONTROL_POINT_PATCH      = 38,
-   SVGA3D_PRIMITIVE_29_CONTROL_POINT_PATCH      = 39,
-   SVGA3D_PRIMITIVE_30_CONTROL_POINT_PATCH      = 40,
-   SVGA3D_PRIMITIVE_31_CONTROL_POINT_PATCH      = 41,
-   SVGA3D_PRIMITIVE_32_CONTROL_POINT_PATCH      = 42,
-   SVGA3D_PRIMITIVE_MAX                         = 43
+
+	SVGA3D_PRIMITIVE_INVALID = 0,
+	SVGA3D_PRIMITIVE_MIN = 0,
+	SVGA3D_PRIMITIVE_TRIANGLELIST = 1,
+	SVGA3D_PRIMITIVE_POINTLIST = 2,
+	SVGA3D_PRIMITIVE_LINELIST = 3,
+	SVGA3D_PRIMITIVE_LINESTRIP = 4,
+	SVGA3D_PRIMITIVE_TRIANGLESTRIP = 5,
+	SVGA3D_PRIMITIVE_TRIANGLEFAN = 6,
+	SVGA3D_PRIMITIVE_LINELIST_ADJ = 7,
+	SVGA3D_PRIMITIVE_PREDX_MAX = 7,
+	SVGA3D_PRIMITIVE_LINESTRIP_ADJ = 8,
+	SVGA3D_PRIMITIVE_TRIANGLELIST_ADJ = 9,
+	SVGA3D_PRIMITIVE_TRIANGLESTRIP_ADJ = 10,
+	SVGA3D_PRIMITIVE_DX10_MAX = 11,
+	SVGA3D_PRIMITIVE_1_CONTROL_POINT_PATCH = 11,
+	SVGA3D_PRIMITIVE_2_CONTROL_POINT_PATCH = 12,
+	SVGA3D_PRIMITIVE_3_CONTROL_POINT_PATCH = 13,
+	SVGA3D_PRIMITIVE_4_CONTROL_POINT_PATCH = 14,
+	SVGA3D_PRIMITIVE_5_CONTROL_POINT_PATCH = 15,
+	SVGA3D_PRIMITIVE_6_CONTROL_POINT_PATCH = 16,
+	SVGA3D_PRIMITIVE_7_CONTROL_POINT_PATCH = 17,
+	SVGA3D_PRIMITIVE_8_CONTROL_POINT_PATCH = 18,
+	SVGA3D_PRIMITIVE_9_CONTROL_POINT_PATCH = 19,
+	SVGA3D_PRIMITIVE_10_CONTROL_POINT_PATCH = 20,
+	SVGA3D_PRIMITIVE_11_CONTROL_POINT_PATCH = 21,
+	SVGA3D_PRIMITIVE_12_CONTROL_POINT_PATCH = 22,
+	SVGA3D_PRIMITIVE_13_CONTROL_POINT_PATCH = 23,
+	SVGA3D_PRIMITIVE_14_CONTROL_POINT_PATCH = 24,
+	SVGA3D_PRIMITIVE_15_CONTROL_POINT_PATCH = 25,
+	SVGA3D_PRIMITIVE_16_CONTROL_POINT_PATCH = 26,
+	SVGA3D_PRIMITIVE_17_CONTROL_POINT_PATCH = 27,
+	SVGA3D_PRIMITIVE_18_CONTROL_POINT_PATCH = 28,
+	SVGA3D_PRIMITIVE_19_CONTROL_POINT_PATCH = 29,
+	SVGA3D_PRIMITIVE_20_CONTROL_POINT_PATCH = 30,
+	SVGA3D_PRIMITIVE_21_CONTROL_POINT_PATCH = 31,
+	SVGA3D_PRIMITIVE_22_CONTROL_POINT_PATCH = 32,
+	SVGA3D_PRIMITIVE_23_CONTROL_POINT_PATCH = 33,
+	SVGA3D_PRIMITIVE_24_CONTROL_POINT_PATCH = 34,
+	SVGA3D_PRIMITIVE_25_CONTROL_POINT_PATCH = 35,
+	SVGA3D_PRIMITIVE_26_CONTROL_POINT_PATCH = 36,
+	SVGA3D_PRIMITIVE_27_CONTROL_POINT_PATCH = 37,
+	SVGA3D_PRIMITIVE_28_CONTROL_POINT_PATCH = 38,
+	SVGA3D_PRIMITIVE_29_CONTROL_POINT_PATCH = 39,
+	SVGA3D_PRIMITIVE_30_CONTROL_POINT_PATCH = 40,
+	SVGA3D_PRIMITIVE_31_CONTROL_POINT_PATCH = 41,
+	SVGA3D_PRIMITIVE_32_CONTROL_POINT_PATCH = 42,
+	SVGA3D_PRIMITIVE_MAX = 43
 } SVGA3dPrimitiveType;
 
 typedef enum {
-   SVGA3D_COORDINATE_INVALID                   = 0,
-   SVGA3D_COORDINATE_LEFTHANDED                = 1,
-   SVGA3D_COORDINATE_RIGHTHANDED               = 2,
-   SVGA3D_COORDINATE_MAX
+	SVGA3D_COORDINATE_INVALID = 0,
+	SVGA3D_COORDINATE_LEFTHANDED = 1,
+	SVGA3D_COORDINATE_RIGHTHANDED = 2,
+	SVGA3D_COORDINATE_MAX
 } SVGA3dCoordinateType;
 
 typedef enum {
-   SVGA3D_TRANSFORM_INVALID                     = 0,
-   SVGA3D_TRANSFORM_WORLD                       = 1,
-   SVGA3D_TRANSFORM_MIN                         = 1,
-   SVGA3D_TRANSFORM_VIEW                        = 2,
-   SVGA3D_TRANSFORM_PROJECTION                  = 3,
-   SVGA3D_TRANSFORM_TEXTURE0                    = 4,
-   SVGA3D_TRANSFORM_TEXTURE1                    = 5,
-   SVGA3D_TRANSFORM_TEXTURE2                    = 6,
-   SVGA3D_TRANSFORM_TEXTURE3                    = 7,
-   SVGA3D_TRANSFORM_TEXTURE4                    = 8,
-   SVGA3D_TRANSFORM_TEXTURE5                    = 9,
-   SVGA3D_TRANSFORM_TEXTURE6                    = 10,
-   SVGA3D_TRANSFORM_TEXTURE7                    = 11,
-   SVGA3D_TRANSFORM_WORLD1                      = 12,
-   SVGA3D_TRANSFORM_WORLD2                      = 13,
-   SVGA3D_TRANSFORM_WORLD3                      = 14,
-   SVGA3D_TRANSFORM_MAX
+	SVGA3D_TRANSFORM_INVALID = 0,
+	SVGA3D_TRANSFORM_WORLD = 1,
+	SVGA3D_TRANSFORM_MIN = 1,
+	SVGA3D_TRANSFORM_VIEW = 2,
+	SVGA3D_TRANSFORM_PROJECTION = 3,
+	SVGA3D_TRANSFORM_TEXTURE0 = 4,
+	SVGA3D_TRANSFORM_TEXTURE1 = 5,
+	SVGA3D_TRANSFORM_TEXTURE2 = 6,
+	SVGA3D_TRANSFORM_TEXTURE3 = 7,
+	SVGA3D_TRANSFORM_TEXTURE4 = 8,
+	SVGA3D_TRANSFORM_TEXTURE5 = 9,
+	SVGA3D_TRANSFORM_TEXTURE6 = 10,
+	SVGA3D_TRANSFORM_TEXTURE7 = 11,
+	SVGA3D_TRANSFORM_WORLD1 = 12,
+	SVGA3D_TRANSFORM_WORLD2 = 13,
+	SVGA3D_TRANSFORM_WORLD3 = 14,
+	SVGA3D_TRANSFORM_MAX
 } SVGA3dTransformType;
 
 typedef enum {
-   SVGA3D_LIGHTTYPE_INVALID                     = 0,
-   SVGA3D_LIGHTTYPE_MIN                         = 1,
-   SVGA3D_LIGHTTYPE_POINT                       = 1,
-   SVGA3D_LIGHTTYPE_SPOT1                       = 2, /* 1-cone, in degrees */
-   SVGA3D_LIGHTTYPE_SPOT2                       = 3, /* 2-cone, in radians */
-   SVGA3D_LIGHTTYPE_DIRECTIONAL                 = 4,
-   SVGA3D_LIGHTTYPE_MAX
+	SVGA3D_LIGHTTYPE_INVALID = 0,
+	SVGA3D_LIGHTTYPE_MIN = 1,
+	SVGA3D_LIGHTTYPE_POINT = 1,
+	SVGA3D_LIGHTTYPE_SPOT1 = 2,
+	SVGA3D_LIGHTTYPE_SPOT2 = 3,
+	SVGA3D_LIGHTTYPE_DIRECTIONAL = 4,
+	SVGA3D_LIGHTTYPE_MAX
 } SVGA3dLightType;
 
 typedef enum {
-   SVGA3D_CUBEFACE_POSX                         = 0,
-   SVGA3D_CUBEFACE_NEGX                         = 1,
-   SVGA3D_CUBEFACE_POSY                         = 2,
-   SVGA3D_CUBEFACE_NEGY                         = 3,
-   SVGA3D_CUBEFACE_POSZ                         = 4,
-   SVGA3D_CUBEFACE_NEGZ                         = 5,
+	SVGA3D_CUBEFACE_POSX = 0,
+	SVGA3D_CUBEFACE_NEGX = 1,
+	SVGA3D_CUBEFACE_POSY = 2,
+	SVGA3D_CUBEFACE_NEGY = 3,
+	SVGA3D_CUBEFACE_POSZ = 4,
+	SVGA3D_CUBEFACE_NEGZ = 5,
 } SVGA3dCubeFace;
 
 typedef enum {
-   SVGA3D_SHADERTYPE_INVALID                    = 0,
-   SVGA3D_SHADERTYPE_MIN                        = 1,
-   SVGA3D_SHADERTYPE_VS                         = 1,
-   SVGA3D_SHADERTYPE_PS                         = 2,
-   SVGA3D_SHADERTYPE_PREDX_MAX                  = 3,
-   SVGA3D_SHADERTYPE_GS                         = 3,
-   SVGA3D_SHADERTYPE_DX10_MAX                   = 4,
-   SVGA3D_SHADERTYPE_HS                         = 4,
-   SVGA3D_SHADERTYPE_DS                         = 5,
-   SVGA3D_SHADERTYPE_CS                         = 6,
-   SVGA3D_SHADERTYPE_MAX                        = 7
+	SVGA3D_SHADERTYPE_INVALID = 0,
+	SVGA3D_SHADERTYPE_MIN = 1,
+	SVGA3D_SHADERTYPE_VS = 1,
+	SVGA3D_SHADERTYPE_PS = 2,
+	SVGA3D_SHADERTYPE_PREDX_MAX = 3,
+	SVGA3D_SHADERTYPE_GS = 3,
+	SVGA3D_SHADERTYPE_DX10_MAX = 4,
+	SVGA3D_SHADERTYPE_HS = 4,
+	SVGA3D_SHADERTYPE_DS = 5,
+	SVGA3D_SHADERTYPE_CS = 6,
+	SVGA3D_SHADERTYPE_MAX = 7
 } SVGA3dShaderType;
 
-#define SVGA3D_NUM_SHADERTYPE_PREDX \
-   (SVGA3D_SHADERTYPE_PREDX_MAX - SVGA3D_SHADERTYPE_MIN)
+#define SVGA3D_NUM_SHADERTYPE_PREDX                                            \
+	(SVGA3D_SHADERTYPE_PREDX_MAX - SVGA3D_SHADERTYPE_MIN)
 
-#define SVGA3D_NUM_SHADERTYPE_DX10 \
-   (SVGA3D_SHADERTYPE_DX10_MAX - SVGA3D_SHADERTYPE_MIN)
+#define SVGA3D_NUM_SHADERTYPE_DX10                                             \
+	(SVGA3D_SHADERTYPE_DX10_MAX - SVGA3D_SHADERTYPE_MIN)
 
-#define SVGA3D_NUM_SHADERTYPE \
-   (SVGA3D_SHADERTYPE_MAX - SVGA3D_SHADERTYPE_MIN)
+#define SVGA3D_NUM_SHADERTYPE (SVGA3D_SHADERTYPE_MAX - SVGA3D_SHADERTYPE_MIN)
 
 typedef enum {
-   SVGA3D_CONST_TYPE_MIN                        = 0,
-   SVGA3D_CONST_TYPE_FLOAT                      = 0,
-   SVGA3D_CONST_TYPE_INT                        = 1,
-   SVGA3D_CONST_TYPE_BOOL                       = 2,
-   SVGA3D_CONST_TYPE_MAX                        = 3,
+	SVGA3D_CONST_TYPE_MIN = 0,
+	SVGA3D_CONST_TYPE_FLOAT = 0,
+	SVGA3D_CONST_TYPE_INT = 1,
+	SVGA3D_CONST_TYPE_BOOL = 2,
+	SVGA3D_CONST_TYPE_MAX = 3,
 } SVGA3dShaderConstType;
 
-/*
- * Register limits for shader consts.
- */
-#define SVGA3D_CONSTREG_MAX            256
-#define SVGA3D_CONSTINTREG_MAX         16
-#define SVGA3D_CONSTBOOLREG_MAX        16
+#define SVGA3D_CONSTREG_MAX 256
+#define SVGA3D_CONSTINTREG_MAX 16
+#define SVGA3D_CONSTBOOLREG_MAX 16
 
 typedef enum {
-   SVGA3D_STRETCH_BLT_POINT                     = 0,
-   SVGA3D_STRETCH_BLT_LINEAR                    = 1,
-   SVGA3D_STRETCH_BLT_MAX
+	SVGA3D_STRETCH_BLT_POINT = 0,
+	SVGA3D_STRETCH_BLT_LINEAR = 1,
+	SVGA3D_STRETCH_BLT_MAX
 } SVGA3dStretchBltMode;
 
 typedef enum {
-   SVGA3D_QUERYTYPE_INVALID                     = ((uint8)-1),
-   SVGA3D_QUERYTYPE_MIN                         = 0,
-   SVGA3D_QUERYTYPE_OCCLUSION                   = 0,
-   SVGA3D_QUERYTYPE_TIMESTAMP                   = 1,
-   SVGA3D_QUERYTYPE_TIMESTAMPDISJOINT           = 2,
-   SVGA3D_QUERYTYPE_PIPELINESTATS               = 3,
-   SVGA3D_QUERYTYPE_OCCLUSIONPREDICATE          = 4,
-   SVGA3D_QUERYTYPE_STREAMOUTPUTSTATS           = 5,
-   SVGA3D_QUERYTYPE_STREAMOVERFLOWPREDICATE     = 6,
-   SVGA3D_QUERYTYPE_OCCLUSION64                 = 7,
-   SVGA3D_QUERYTYPE_DX10_MAX                    = 8,
-   SVGA3D_QUERYTYPE_SOSTATS_STREAM0             = 8,
-   SVGA3D_QUERYTYPE_SOSTATS_STREAM1             = 9,
-   SVGA3D_QUERYTYPE_SOSTATS_STREAM2             = 10,
-   SVGA3D_QUERYTYPE_SOSTATS_STREAM3             = 11,
-   SVGA3D_QUERYTYPE_SOP_STREAM0                 = 12,
-   SVGA3D_QUERYTYPE_SOP_STREAM1                 = 13,
-   SVGA3D_QUERYTYPE_SOP_STREAM2                 = 14,
-   SVGA3D_QUERYTYPE_SOP_STREAM3                 = 15,
-   SVGA3D_QUERYTYPE_MAX
+	SVGA3D_QUERYTYPE_INVALID = ((uint8)-1),
+	SVGA3D_QUERYTYPE_MIN = 0,
+	SVGA3D_QUERYTYPE_OCCLUSION = 0,
+	SVGA3D_QUERYTYPE_TIMESTAMP = 1,
+	SVGA3D_QUERYTYPE_TIMESTAMPDISJOINT = 2,
+	SVGA3D_QUERYTYPE_PIPELINESTATS = 3,
+	SVGA3D_QUERYTYPE_OCCLUSIONPREDICATE = 4,
+	SVGA3D_QUERYTYPE_STREAMOUTPUTSTATS = 5,
+	SVGA3D_QUERYTYPE_STREAMOVERFLOWPREDICATE = 6,
+	SVGA3D_QUERYTYPE_OCCLUSION64 = 7,
+	SVGA3D_QUERYTYPE_DX10_MAX = 8,
+	SVGA3D_QUERYTYPE_SOSTATS_STREAM0 = 8,
+	SVGA3D_QUERYTYPE_SOSTATS_STREAM1 = 9,
+	SVGA3D_QUERYTYPE_SOSTATS_STREAM2 = 10,
+	SVGA3D_QUERYTYPE_SOSTATS_STREAM3 = 11,
+	SVGA3D_QUERYTYPE_SOP_STREAM0 = 12,
+	SVGA3D_QUERYTYPE_SOP_STREAM1 = 13,
+	SVGA3D_QUERYTYPE_SOP_STREAM2 = 14,
+	SVGA3D_QUERYTYPE_SOP_STREAM3 = 15,
+	SVGA3D_QUERYTYPE_MAX
 } SVGA3dQueryType;
 
 typedef uint8 SVGA3dQueryTypeUint8;
 
-#define SVGA3D_NUM_QUERYTYPE  (SVGA3D_QUERYTYPE_MAX - SVGA3D_QUERYTYPE_MIN)
+#define SVGA3D_NUM_QUERYTYPE (SVGA3D_QUERYTYPE_MAX - SVGA3D_QUERYTYPE_MIN)
 
-/*
- * This is the maximum number of queries per context that can be active
- * simultaneously between a beginQuery and endQuery.
- */
 #define SVGA3D_MAX_QUERY 64
 
-/*
- * Query result buffer formats
- */
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 samplesRendered;
-}
-#include "vmware_pack_end.h"
-SVGADXOcclusionQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 passed;
-}
-#include "vmware_pack_end.h"
-SVGADXEventQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 timestamp;
-}
-#include "vmware_pack_end.h"
-SVGADXTimestampQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 realFrequency;
-   uint32 disjoint;
-}
-#include "vmware_pack_end.h"
-SVGADXTimestampDisjointQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 inputAssemblyVertices;
-   uint64 inputAssemblyPrimitives;
-   uint64 vertexShaderInvocations;
-   uint64 geometryShaderInvocations;
-   uint64 geometryShaderPrimitives;
-   uint64 clipperInvocations;
-   uint64 clipperPrimitives;
-   uint64 pixelShaderInvocations;
-   uint64 hullShaderInvocations;
-   uint64 domainShaderInvocations;
-   uint64 computeShaderInvocations;
-}
-#include "vmware_pack_end.h"
-SVGADXPipelineStatisticsQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 anySamplesRendered;
-}
-#include "vmware_pack_end.h"
-SVGADXOcclusionPredicateQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 numPrimitivesWritten;
-   uint64 numPrimitivesRequired;
-}
-#include "vmware_pack_end.h"
-SVGADXStreamOutStatisticsQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 overflowed;
-}
-#include "vmware_pack_end.h"
-SVGADXStreamOutPredicateQueryResult;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint64 samplesRendered;
-}
-#include "vmware_pack_end.h"
-SVGADXOcclusion64QueryResult;
-
-/*
- * SVGADXQueryResultUnion is not intended for use in the protocol, but is
- * very helpful when working with queries generically.
- */
-typedef
-#include "vmware_pack_begin.h"
-union SVGADXQueryResultUnion {
-   SVGADXOcclusionQueryResult occ;
-   SVGADXEventQueryResult event;
-   SVGADXTimestampQueryResult ts;
-   SVGADXTimestampDisjointQueryResult tsDisjoint;
-   SVGADXPipelineStatisticsQueryResult pipelineStats;
-   SVGADXOcclusionPredicateQueryResult occPred;
-   SVGADXStreamOutStatisticsQueryResult soStats;
-   SVGADXStreamOutPredicateQueryResult soPred;
-   SVGADXOcclusion64QueryResult occ64;
-}
-#include "vmware_pack_end.h"
-SVGADXQueryResultUnion;
+#pragma pack(push, 1)
+typedef struct {
+	uint32 samplesRendered;
+} SVGADXOcclusionQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 passed;
+} SVGADXEventQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 timestamp;
+} SVGADXTimestampQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 realFrequency;
+	uint32 disjoint;
+} SVGADXTimestampDisjointQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 inputAssemblyVertices;
+	uint64 inputAssemblyPrimitives;
+	uint64 vertexShaderInvocations;
+	uint64 geometryShaderInvocations;
+	uint64 geometryShaderPrimitives;
+	uint64 clipperInvocations;
+	uint64 clipperPrimitives;
+	uint64 pixelShaderInvocations;
+	uint64 hullShaderInvocations;
+	uint64 domainShaderInvocations;
+	uint64 computeShaderInvocations;
+} SVGADXPipelineStatisticsQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 anySamplesRendered;
+} SVGADXOcclusionPredicateQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 numPrimitivesWritten;
+	uint64 numPrimitivesRequired;
+} SVGADXStreamOutStatisticsQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 overflowed;
+} SVGADXStreamOutPredicateQueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint64 samplesRendered;
+} SVGADXOcclusion64QueryResult;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef union SVGADXQueryResultUnion {
+	SVGADXOcclusionQueryResult occ;
+	SVGADXEventQueryResult event;
+	SVGADXTimestampQueryResult ts;
+	SVGADXTimestampDisjointQueryResult tsDisjoint;
+	SVGADXPipelineStatisticsQueryResult pipelineStats;
+	SVGADXOcclusionPredicateQueryResult occPred;
+	SVGADXStreamOutStatisticsQueryResult soStats;
+	SVGADXStreamOutPredicateQueryResult soPred;
+	SVGADXOcclusion64QueryResult occ64;
+} SVGADXQueryResultUnion;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA3D_QUERYSTATE_PENDING     = 0,      /* Query is not finished yet */
-   SVGA3D_QUERYSTATE_SUCCEEDED   = 1,      /* Completed successfully */
-   SVGA3D_QUERYSTATE_FAILED      = 2,      /* Completed unsuccessfully */
-   SVGA3D_QUERYSTATE_NEW         = 3,      /* Never submitted (guest only) */
+	SVGA3D_QUERYSTATE_PENDING = 0,
+	SVGA3D_QUERYSTATE_SUCCEEDED = 1,
+	SVGA3D_QUERYSTATE_FAILED = 2,
+	SVGA3D_QUERYSTATE_NEW = 3,
 } SVGA3dQueryState;
 
 typedef enum {
-   SVGA3D_WRITE_HOST_VRAM        = 1,
-   SVGA3D_READ_HOST_VRAM         = 2,
+	SVGA3D_WRITE_HOST_VRAM = 1,
+	SVGA3D_READ_HOST_VRAM = 2,
 } SVGA3dTransferType;
 
-#define SVGA3D_LOGICOP_INVALID  0
-#define SVGA3D_LOGICOP_MIN      1
-#define SVGA3D_LOGICOP_COPY     1
-#define SVGA3D_LOGICOP_NOT      2
-#define SVGA3D_LOGICOP_AND      3
-#define SVGA3D_LOGICOP_OR       4
-#define SVGA3D_LOGICOP_XOR      5
-#define SVGA3D_LOGICOP_NXOR     6
-#define SVGA3D_LOGICOP_ROP3     7
-#define SVGA3D_LOGICOP_MAX      8
+#define SVGA3D_LOGICOP_INVALID 0
+#define SVGA3D_LOGICOP_COPY 1
+
+#define SVGA3D_LOGICOP_MIN 1
+#define SVGA3D_LOGICOP_NOT 2
+#define SVGA3D_LOGICOP_AND 3
+#define SVGA3D_LOGICOP_OR 4
+#define SVGA3D_LOGICOP_XOR 5
+#define SVGA3D_LOGICOP_NXOR 6
+#define SVGA3D_LOGICOP_ROP3 7
+
+#define SVGA3D_LOGICOP_MAX 8
 
 typedef uint16 SVGA3dLogicOp;
 
-#define SVGA3D_LOGICOP_ROP3_INVALID ((uint16) -1)
-#define SVGA3D_LOGICOP_ROP3_MIN     0
-#define SVGA3D_LOGICOP_ROP3_MAX     256
+#define SVGA3D_LOGICOP_ROP3_INVALID ((uint16)-1)
+#define SVGA3D_LOGICOP_ROP3_MIN 0
+#define SVGA3D_LOGICOP_ROP3_MAX 256
 
 typedef uint16 SVGA3dLogicOpRop3;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   union {
-      struct {
-         uint16  function;       // SVGA3dFogFunction
-         uint8   type;           // SVGA3dFogType
-         uint8   base;           // SVGA3dFogBase
-      };
-      uint32     uintValue;
-   };
-}
-#include "vmware_pack_end.h"
-SVGA3dFogMode;
-
-/*
- * Uniquely identify one image (a 1D/2D/3D array) from a surface. This
- * is a surface ID as well as face/mipmap indices.
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSurfaceImageId {
-   uint32 sid;
-   uint32 face;
-   uint32 mipmap;
-}
-#include "vmware_pack_end.h"
-SVGA3dSurfaceImageId;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSubSurfaceId {
-   uint32 sid;
-   uint32 subResourceId;
-}
-#include "vmware_pack_end.h"
-SVGA3dSubSurfaceId;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32               width;
-   uint32               height;
-   uint32               depth;
-}
-#include "vmware_pack_end.h"
-SVGA3dSize;
+#pragma pack(push, 1)
+typedef struct {
+	union {
+		struct {
+			uint16 function;
+			uint8 type;
+			uint8 base;
+		};
+		uint32 uintValue;
+	};
+} SVGA3dFogMode;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dSurfaceImageId {
+	uint32 sid;
+	uint32 face;
+	uint32 mipmap;
+} SVGA3dSurfaceImageId;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGA3dSubSurfaceId {
+	uint32 sid;
+	uint32 subResourceId;
+} SVGA3dSubSurfaceId;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 width;
+	uint32 height;
+	uint32 depth;
+} SVGA3dSize;
+#pragma pack(pop)
 
-/*
- * Guest-backed objects definitions.
- */
 typedef enum {
-   SVGA_OTABLE_MOB             = 0,
-   SVGA_OTABLE_MIN             = 0,
-   SVGA_OTABLE_SURFACE         = 1,
-   SVGA_OTABLE_CONTEXT         = 2,
-   SVGA_OTABLE_SHADER          = 3,
-   SVGA_OTABLE_SCREENTARGET    = 4,
-
-   SVGA_OTABLE_DX9_MAX         = 5,
-
-   SVGA_OTABLE_DXCONTEXT       = 5,
-   SVGA_OTABLE_DX_MAX          = 6,
-
-   SVGA_OTABLE_RESERVED1       = 6,
-   SVGA_OTABLE_RESERVED2       = 7,
-
-   /*
-    * Additions to this table need to be tied to HW-version features and
-    * checkpointed accordingly.
-    */
-   SVGA_OTABLE_DEVEL_MAX       = 8,
-   SVGA_OTABLE_MAX             = 8
+	SVGA_OTABLE_MOB = 0,
+	SVGA_OTABLE_MIN = 0,
+	SVGA_OTABLE_SURFACE = 1,
+	SVGA_OTABLE_CONTEXT = 2,
+	SVGA_OTABLE_SHADER = 3,
+	SVGA_OTABLE_SCREENTARGET = 4,
+
+	SVGA_OTABLE_DX9_MAX = 5,
+
+	SVGA_OTABLE_DXCONTEXT = 5,
+	SVGA_OTABLE_DX_MAX = 6,
+
+	SVGA_OTABLE_DEVEL_MAX = 6,
+	SVGA_OTABLE_MAX = 6,
+
+	SVGA_OTABLE_RESERVED1 = 6,
+	SVGA_OTABLE_RESERVED2 = 7,
+	SVGA_OTABLE_BUG_1952836_MAX = 8,
 } SVGAOTableType;
 
 typedef enum {
-   SVGA_COTABLE_MIN             = 0,
-   SVGA_COTABLE_RTVIEW          = 0,
-   SVGA_COTABLE_DSVIEW          = 1,
-   SVGA_COTABLE_SRVIEW          = 2,
-   SVGA_COTABLE_ELEMENTLAYOUT   = 3,
-   SVGA_COTABLE_BLENDSTATE      = 4,
-   SVGA_COTABLE_DEPTHSTENCIL    = 5,
-   SVGA_COTABLE_RASTERIZERSTATE = 6,
-   SVGA_COTABLE_SAMPLER         = 7,
-   SVGA_COTABLE_STREAMOUTPUT    = 8,
-   SVGA_COTABLE_DXQUERY         = 9,
-   SVGA_COTABLE_DXSHADER        = 10,
-   SVGA_COTABLE_DX10_MAX        = 11,
-   SVGA_COTABLE_UAVIEW          = 11,
-   SVGA_COTABLE_MAX             = 12,
+	SVGA_COTABLE_MIN = 0,
+	SVGA_COTABLE_RTVIEW = 0,
+	SVGA_COTABLE_DSVIEW = 1,
+	SVGA_COTABLE_SRVIEW = 2,
+	SVGA_COTABLE_ELEMENTLAYOUT = 3,
+	SVGA_COTABLE_BLENDSTATE = 4,
+	SVGA_COTABLE_DEPTHSTENCIL = 5,
+	SVGA_COTABLE_RASTERIZERSTATE = 6,
+	SVGA_COTABLE_SAMPLER = 7,
+	SVGA_COTABLE_STREAMOUTPUT = 8,
+	SVGA_COTABLE_DXQUERY = 9,
+	SVGA_COTABLE_DXSHADER = 10,
+	SVGA_COTABLE_DX10_MAX = 11,
+	SVGA_COTABLE_UAVIEW = 11,
+	SVGA_COTABLE_MAX = 12,
 } SVGACOTableType;
 
-/*
- * The largest size (number of entries) allowed in a COTable.
- */
 #define SVGA_COTABLE_MAX_IDS (MAX_UINT16 - 2)
 
 typedef enum SVGAMobFormat {
-   SVGA3D_MOBFMT_INVALID     = SVGA3D_INVALID_ID,
-   SVGA3D_MOBFMT_PTDEPTH_0   = 0,
-   SVGA3D_MOBFMT_MIN         = 0,
-   SVGA3D_MOBFMT_PTDEPTH_1   = 1,
-   SVGA3D_MOBFMT_PTDEPTH_2   = 2,
-   SVGA3D_MOBFMT_RANGE       = 3,
-   SVGA3D_MOBFMT_PTDEPTH64_0 = 4,
-   SVGA3D_MOBFMT_PTDEPTH64_1 = 5,
-   SVGA3D_MOBFMT_PTDEPTH64_2 = 6,
-   SVGA3D_MOBFMT_PREDX_MAX   = 7,
-   SVGA3D_MOBFMT_EMPTY       = 7,
-   SVGA3D_MOBFMT_MAX,
-
-   /*
-    * This isn't actually used by the guest, but is a mob-format used
-    * internally by the SVGA device (and is therefore not binary compatible).
-    */
-   SVGA3D_MOBFMT_HB,
+	SVGA3D_MOBFMT_INVALID = SVGA3D_INVALID_ID,
+	SVGA3D_MOBFMT_PT_0 = 0,
+	SVGA3D_MOBFMT_MIN = 0,
+	SVGA3D_MOBFMT_PT_1 = 1,
+	SVGA3D_MOBFMT_PT_2 = 2,
+	SVGA3D_MOBFMT_RANGE = 3,
+	SVGA3D_MOBFMT_PT64_0 = 4,
+	SVGA3D_MOBFMT_PT64_1 = 5,
+	SVGA3D_MOBFMT_PT64_2 = 6,
+	SVGA3D_MOBFMT_PREDX_MAX = 7,
+	SVGA3D_MOBFMT_EMPTY = 7,
+
+	SVGA3D_MOBFMT_MAX,
+
+	SVGA3D_MOBFMT_HB,
 } SVGAMobFormat;
 
 #define SVGA3D_MOB_EMPTY_BASE 1
 
-/*
- * Multisample pattern types.
- */
-
 typedef enum SVGA3dMSPattern {
-   SVGA3D_MS_PATTERN_NONE     = 0,
-   SVGA3D_MS_PATTERN_MIN      = 0,
-   SVGA3D_MS_PATTERN_STANDARD = 1,
-   SVGA3D_MS_PATTERN_CENTER   = 2,
-   SVGA3D_MS_PATTERN_MAX      = 3,
+	SVGA3D_MS_PATTERN_NONE = 0,
+	SVGA3D_MS_PATTERN_MIN = 0,
+	SVGA3D_MS_PATTERN_STANDARD = 1,
+	SVGA3D_MS_PATTERN_CENTER = 2,
+	SVGA3D_MS_PATTERN_MAX = 3,
 } SVGA3dMSPattern;
 
-/*
- * Precision settings for each sample.
- */
-
 typedef enum SVGA3dMSQualityLevel {
-   SVGA3D_MS_QUALITY_NONE = 0,
-   SVGA3D_MS_QUALITY_MIN  = 0,
-   SVGA3D_MS_QUALITY_FULL = 1,
-   SVGA3D_MS_QUALITY_MAX  = 2,
+	SVGA3D_MS_QUALITY_NONE = 0,
+	SVGA3D_MS_QUALITY_MIN = 0,
+	SVGA3D_MS_QUALITY_FULL = 1,
+	SVGA3D_MS_QUALITY_RESOLVED = 2,
+	SVGA3D_MS_QUALITY_MAX = 3,
 } SVGA3dMSQualityLevel;
 
-/*
- * Screen Target Update Flags
- */
-
 typedef enum SVGA3dFrameUpdateType {
-   SVGA3D_FRAME_END     = 0,
-   SVGA3D_FRAME_PARTIAL = 1,
-   SVGA3D_FRAME_UNKNOWN = 2,
-   SVGA3D_FRAME_MAX     = 3,
+	SVGA3D_FRAME_END = 0,
+	SVGA3D_FRAME_MIN = 0,
+	SVGA3D_FRAME_PARTIAL = 1,
+	SVGA3D_FRAME_UNKNOWN = 2,
+	SVGA3D_FRAME_MAX = 3,
 } SVGA3dFrameUpdateType;
 
-#endif /* _SVGA3D_TYPES_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
index acb41e28e46f..bf242c21f352 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.
+ * Copyright 2007,2020 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -30,61 +30,27 @@
  *    Definitions for our own (vendor-specific) SVGA Escape commands.
  */
 
-#ifndef _SVGA_ESCAPE_H_
-#define _SVGA_ESCAPE_H_
 
 
-/*
- * Namespace IDs for the escape command
- */
+#ifndef _SVGA_ESCAPE_H_
+#define _SVGA_ESCAPE_H_
 
 #define SVGA_ESCAPE_NSID_VMWARE 0x00000000
-#define SVGA_ESCAPE_NSID_DEVEL  0xFFFFFFFF
-
+#define SVGA_ESCAPE_NSID_DEVEL 0xFFFFFFFF
 
-/*
- * Within SVGA_ESCAPE_NSID_VMWARE, we multiplex commands according to
- * the first DWORD of escape data (after the nsID and size). As a
- * guideline we're using the high word and low word as a major and
- * minor command number, respectively.
- *
- * Major command number allocation:
- *
- *   0000: Reserved
- *   0001: SVGA_ESCAPE_VMWARE_LOG (svga_binary_logger.h)
- *   0002: SVGA_ESCAPE_VMWARE_VIDEO (svga_overlay.h)
- *   0003: SVGA_ESCAPE_VMWARE_HINT (svga_escape.h)
- */
-
-#define SVGA_ESCAPE_VMWARE_MAJOR_MASK  0xFFFF0000
-
-
-/*
- * SVGA Hint commands.
- *
- * These escapes let the SVGA driver provide optional information to
- * he host about the state of the guest or guest applications. The
- * host can use these hints to make user interface or performance
- * decisions.
- *
- * Notes:
- *
- *   - SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN is deprecated for guests
- *     that use the SVGA Screen Object extension. Instead of sending
- *     this escape, use the SVGA_SCREEN_FULLSCREEN_HINT flag on your
- *     Screen Object.
- */
+#define SVGA_ESCAPE_VMWARE_MAJOR_MASK 0xFFFF0000
 
-#define SVGA_ESCAPE_VMWARE_HINT               0x00030000
-#define SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN    0x00030001  /* Deprecated */
+#define SVGA_ESCAPE_VMWARE_HINT 0x00030000
+#define SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN 0x00030001
 
-typedef
-struct {
-   uint32 command;
-   uint32 fullscreen;
-   struct {
-      int32 x, y;
-   } monitorPosition;
+#pragma pack(push, 1)
+typedef struct {
+	uint32 command;
+	uint32 fullscreen;
+	struct {
+		int32 x, y;
+	} monitorPosition;
 } SVGAEscapeHintFullscreen;
+#pragma pack(pop)
 
-#endif /* _SVGA_ESCAPE_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
index e5385146e7fc..aec17c3c6c29 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.
+ * Copyright 2007-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -30,171 +30,88 @@
  *    Definitions for video-overlay support.
  */
 
+
+
 #ifndef _SVGA_OVERLAY_H_
 #define _SVGA_OVERLAY_H_
 
 #include "svga_reg.h"
 
-/*
- * Video formats we support
- */
+#if defined __cplusplus
+extern "C" {
+#endif
 
-#define VMWARE_FOURCC_YV12 0x32315659 /* 'Y' 'V' '1' '2' */
-#define VMWARE_FOURCC_YUY2 0x32595559 /* 'Y' 'U' 'Y' '2' */
-#define VMWARE_FOURCC_UYVY 0x59565955 /* 'U' 'Y' 'V' 'Y' */
+#define VMWARE_FOURCC_YV12 0x32315659
+#define VMWARE_FOURCC_YUY2 0x32595559
+#define VMWARE_FOURCC_UYVY 0x59565955
 
 typedef enum {
-   SVGA_OVERLAY_FORMAT_INVALID = 0,
-   SVGA_OVERLAY_FORMAT_YV12 = VMWARE_FOURCC_YV12,
-   SVGA_OVERLAY_FORMAT_YUY2 = VMWARE_FOURCC_YUY2,
-   SVGA_OVERLAY_FORMAT_UYVY = VMWARE_FOURCC_UYVY,
+	SVGA_OVERLAY_FORMAT_INVALID = 0,
+	SVGA_OVERLAY_FORMAT_YV12 = VMWARE_FOURCC_YV12,
+	SVGA_OVERLAY_FORMAT_YUY2 = VMWARE_FOURCC_YUY2,
+	SVGA_OVERLAY_FORMAT_UYVY = VMWARE_FOURCC_UYVY,
 } SVGAOverlayFormat;
 
-#define SVGA_VIDEO_COLORKEY_MASK             0x00ffffff
+#define SVGA_VIDEO_COLORKEY_MASK 0x00ffffff
 
-#define SVGA_ESCAPE_VMWARE_VIDEO             0x00020000
+#define SVGA_ESCAPE_VMWARE_VIDEO 0x00020000
 
-#define SVGA_ESCAPE_VMWARE_VIDEO_SET_REGS    0x00020001
-        /* FIFO escape layout:
-         * Type, Stream Id, (Register Id, Value) pairs */
+#define SVGA_ESCAPE_VMWARE_VIDEO_SET_REGS 0x00020001
 
-#define SVGA_ESCAPE_VMWARE_VIDEO_FLUSH       0x00020002
-        /* FIFO escape layout:
-         * Type, Stream Id */
+#define SVGA_ESCAPE_VMWARE_VIDEO_FLUSH 0x00020002
 
-typedef
-struct SVGAEscapeVideoSetRegs {
-   struct {
-      uint32 cmdType;
-      uint32 streamId;
-   } header;
+typedef struct SVGAEscapeVideoSetRegs {
+	struct {
+		uint32 cmdType;
+		uint32 streamId;
+	} header;
 
-   /* May include zero or more items. */
-   struct {
-      uint32 registerId;
-      uint32 value;
-   } items[1];
+	struct {
+		uint32 registerId;
+		uint32 value;
+	} items[1];
 } SVGAEscapeVideoSetRegs;
 
-typedef
-struct SVGAEscapeVideoFlush {
-   uint32 cmdType;
-   uint32 streamId;
+typedef struct SVGAEscapeVideoFlush {
+	uint32 cmdType;
+	uint32 streamId;
 } SVGAEscapeVideoFlush;
 
-
-/*
- * Struct definitions for the video overlay commands built on
- * SVGAFifoCmdEscape.
- */
-typedef
-struct {
-   uint32 command;
-   uint32 overlay;
+#pragma pack(push, 1)
+typedef struct {
+	uint32 command;
+	uint32 overlay;
 } SVGAFifoEscapeCmdVideoBase;
+#pragma pack(pop)
 
-typedef
-struct {
-   SVGAFifoEscapeCmdVideoBase videoCmd;
+#pragma pack(push, 1)
+typedef struct {
+	SVGAFifoEscapeCmdVideoBase videoCmd;
 } SVGAFifoEscapeCmdVideoFlush;
-
-typedef
-struct {
-   SVGAFifoEscapeCmdVideoBase videoCmd;
-   struct {
-      uint32 regId;
-      uint32 value;
-   } items[1];
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAFifoEscapeCmdVideoBase videoCmd;
+	struct {
+		uint32 regId;
+		uint32 value;
+	} items[1];
 } SVGAFifoEscapeCmdVideoSetRegs;
-
-typedef
-struct {
-   SVGAFifoEscapeCmdVideoBase videoCmd;
-   struct {
-      uint32 regId;
-      uint32 value;
-   } items[SVGA_VIDEO_NUM_REGS];
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAFifoEscapeCmdVideoBase videoCmd;
+	struct {
+		uint32 regId;
+		uint32 value;
+	} items[SVGA_VIDEO_NUM_REGS];
 } SVGAFifoEscapeCmdVideoSetAllRegs;
+#pragma pack(pop)
 
-
-/*
- *----------------------------------------------------------------------
- *
- * VMwareVideoGetAttributes --
- *
- *      Computes the size, pitches and offsets for YUV frames.
- *
- * Results:
- *      TRUE on success; otherwise FALSE on failure.
- *
- * Side effects:
- *      Pitches and offsets for the given YUV frame are put in 'pitches'
- *      and 'offsets' respectively. They are both optional though.
- *
- *----------------------------------------------------------------------
- */
-
-static inline bool
-VMwareVideoGetAttributes(const SVGAOverlayFormat format,    /* IN */
-                         uint32 *width,                     /* IN / OUT */
-                         uint32 *height,                    /* IN / OUT */
-                         uint32 *size,                      /* OUT */
-                         uint32 *pitches,                   /* OUT (optional) */
-                         uint32 *offsets)                   /* OUT (optional) */
-{
-    int tmp;
-
-    *width = (*width + 1) & ~1;
-
-    if (offsets) {
-        offsets[0] = 0;
-    }
-
-    switch (format) {
-    case VMWARE_FOURCC_YV12:
-       *height = (*height + 1) & ~1;
-       *size = (*width) * (*height);
-
-       if (pitches) {
-          pitches[0] = *width;
-       }
-
-       if (offsets) {
-          offsets[1] = *size;
-       }
-
-       tmp = *width >> 1;
-
-       if (pitches) {
-          pitches[1] = pitches[2] = tmp;
-       }
-
-       tmp *= (*height >> 1);
-       *size += tmp;
-
-       if (offsets) {
-          offsets[2] = *size;
-       }
-
-       *size += tmp;
-       break;
-
-    case VMWARE_FOURCC_YUY2:
-    case VMWARE_FOURCC_UYVY:
-       *size = *width * 2;
-
-       if (pitches) {
-          pitches[0] = *size;
-       }
-
-       *size *= *height;
-       break;
-
-    default:
-       return false;
-    }
-
-    return true;
+#if defined __cplusplus
 }
+#endif
 
-#endif /* _SVGA_OVERLAY_H_ */
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index 193a57f6aae5..b3602557de2e 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -1,6 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
  * Copyright 1998-2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -30,2277 +30,870 @@
  *    Virtual hardware definitions for the VMware SVGA II device.
  */
 
-#ifndef _SVGA_REG_H_
-#define _SVGA_REG_H_
-#include <linux/pci_ids.h>
 
-#define INCLUDE_ALLOW_MODULE
-#define INCLUDE_ALLOW_USERLEVEL
 
-#define INCLUDE_ALLOW_VMCORE
-#include "includeCheck.h"
+#ifndef _SVGA_REG_H_
+#define _SVGA_REG_H_
 
-#include "svga_types.h"
+#include "vm_basic_types.h"
 
-/*
- * SVGA_REG_ENABLE bit definitions.
- */
 typedef enum {
-   SVGA_REG_ENABLE_DISABLE = 0,
-   SVGA_REG_ENABLE_ENABLE = (1 << 0),
-   SVGA_REG_ENABLE_HIDE = (1 << 1),
+	SVGA_REG_ENABLE_DISABLE = 0,
+	SVGA_REG_ENABLE_ENABLE = (1 << 0),
+	SVGA_REG_ENABLE_HIDE = (1 << 1),
 } SvgaRegEnable;
 
 typedef uint32 SVGAMobId;
 
-/*
- * Arbitrary and meaningless limits. Please ignore these when writing
- * new drivers.
- */
-#define SVGA_MAX_WIDTH                  2560
-#define SVGA_MAX_HEIGHT                 1600
-
+#define SVGA_MAX_WIDTH 2560
+#define SVGA_MAX_HEIGHT 1600
 
-#define SVGA_MAX_BITS_PER_PIXEL         32
-#define SVGA_MAX_DEPTH                  24
-#define SVGA_MAX_DISPLAYS               10
-#define SVGA_MAX_SCREEN_SIZE            8192
+#define SVGA_MAX_BITS_PER_PIXEL 32
+#define SVGA_MAX_DEPTH 24
+#define SVGA_MAX_DISPLAYS 10
+#define SVGA_MAX_SCREEN_SIZE 8192
 #define SVGA_SCREEN_ROOT_LIMIT (SVGA_MAX_SCREEN_SIZE * SVGA_MAX_DISPLAYS)
 
+#define SVGA_CURSOR_ON_HIDE 0x0
+#define SVGA_CURSOR_ON_SHOW 0x1
 
-/*
- * Legal values for the SVGA_REG_CURSOR_ON register in old-fashioned
- * cursor bypass mode.
- */
-#define SVGA_CURSOR_ON_HIDE            0x0
-#define SVGA_CURSOR_ON_SHOW            0x1
-
-/*
- * Remove the cursor from the framebuffer
- * because we need to see what's under it
- */
-#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2
+#define SVGA_CURSOR_ON_REMOVE_FROM_FB 0x2
 
-/* Put the cursor back in the framebuffer so the user can see it */
-#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3
+#define SVGA_CURSOR_ON_RESTORE_TO_FB 0x3
 
-/*
- * The maximum framebuffer size that can traced for guests unless the
- * SVGA_CAP_GBOBJECTS is set in SVGA_REG_CAPABILITIES.  In that case
- * the full framebuffer can be traced independent of this limit.
- */
-#define SVGA_FB_MAX_TRACEABLE_SIZE      0x1000000
+#define SVGA_FB_MAX_TRACEABLE_SIZE 0x1000000
 
-#define SVGA_MAX_PSEUDOCOLOR_DEPTH      8
-#define SVGA_MAX_PSEUDOCOLORS           (1 << SVGA_MAX_PSEUDOCOLOR_DEPTH)
-#define SVGA_NUM_PALETTE_REGS           (3 * SVGA_MAX_PSEUDOCOLORS)
+#define SVGA_MAX_PSEUDOCOLOR_DEPTH 8
+#define SVGA_MAX_PSEUDOCOLORS (1 << SVGA_MAX_PSEUDOCOLOR_DEPTH)
+#define SVGA_NUM_PALETTE_REGS (3 * SVGA_MAX_PSEUDOCOLORS)
 
-#define SVGA_MAGIC         0x900000UL
-#define SVGA_MAKE_ID(ver)  (SVGA_MAGIC << 8 | (ver))
+#define SVGA_MAGIC 0x900000UL
+#define SVGA_MAKE_ID(ver) (SVGA_MAGIC << 8 | (ver))
 
-/* Version 3 has the control bar instead of the FIFO */
-#define SVGA_VERSION_3     3
-#define SVGA_ID_3          SVGA_MAKE_ID(SVGA_VERSION_3)
+#define SVGA_VERSION_3 3
+#define SVGA_ID_3 SVGA_MAKE_ID(SVGA_VERSION_3)
 
-/* Version 2 let the address of the frame buffer be unsigned on Win32 */
-#define SVGA_VERSION_2     2
-#define SVGA_ID_2          SVGA_MAKE_ID(SVGA_VERSION_2)
+#define SVGA_VERSION_2 2
+#define SVGA_ID_2 SVGA_MAKE_ID(SVGA_VERSION_2)
 
-/* Version 1 has new registers starting with SVGA_REG_CAPABILITIES so
-   PALETTE_BASE has moved */
-#define SVGA_VERSION_1     1
-#define SVGA_ID_1          SVGA_MAKE_ID(SVGA_VERSION_1)
+#define SVGA_VERSION_1 1
+#define SVGA_ID_1 SVGA_MAKE_ID(SVGA_VERSION_1)
 
-/* Version 0 is the initial version */
-#define SVGA_VERSION_0     0
-#define SVGA_ID_0          SVGA_MAKE_ID(SVGA_VERSION_0)
+#define SVGA_VERSION_0 0
+#define SVGA_ID_0 SVGA_MAKE_ID(SVGA_VERSION_0)
 
-/*
- * "Invalid" value for all SVGA IDs.
- * (Version ID, screen object ID, surface ID...)
- */
-#define SVGA_ID_INVALID    0xFFFFFFFF
+#define SVGA_ID_INVALID 0xFFFFFFFF
 
-/* Port offsets, relative to BAR0 */
-#define SVGA_INDEX_PORT         0x0
-#define SVGA_VALUE_PORT         0x1
-#define SVGA_BIOS_PORT          0x2
-#define SVGA_IRQSTATUS_PORT     0x8
+#define SVGA_INDEX_PORT 0x0
+#define SVGA_VALUE_PORT 0x1
+#define SVGA_BIOS_PORT 0x2
+#define SVGA_IRQSTATUS_PORT 0x8
 
-/*
- * Interrupt source flags for IRQSTATUS_PORT and IRQMASK.
- *
- * Interrupts are only supported when the
- * SVGA_CAP_IRQMASK capability is present.
- */
-#define SVGA_IRQFLAG_ANY_FENCE            (1 << 0) /* Any fence was passed */
-#define SVGA_IRQFLAG_FIFO_PROGRESS        (1 << 1) /* Made forward progress in the FIFO */
-#define SVGA_IRQFLAG_FENCE_GOAL           (1 << 2) /* SVGA_FIFO_FENCE_GOAL reached */
-#define SVGA_IRQFLAG_COMMAND_BUFFER       (1 << 3) /* Command buffer completed */
-#define SVGA_IRQFLAG_ERROR                (1 << 4) /* Error while processing commands */
-#define SVGA_IRQFLAG_MAX                  (1 << 5)
+#define SVGA_IRQFLAG_ANY_FENCE (1 << 0)
+#define SVGA_IRQFLAG_FIFO_PROGRESS (1 << 1)
+#define SVGA_IRQFLAG_FENCE_GOAL (1 << 2)
+#define SVGA_IRQFLAG_COMMAND_BUFFER (1 << 3)
+#define SVGA_IRQFLAG_ERROR (1 << 4)
+#define SVGA_IRQFLAG_REG_FENCE_GOAL (1 << 5)
+#define SVGA_IRQFLAG_MAX (1 << 6)
 
-/*
- * The byte-size is the size of the actual cursor data,
- * possibly after expanding it to the current bit depth.
- *
- * 40K is sufficient memory for two 32-bit planes for a 64 x 64 cursor.
- *
- * The dimension limit is a bound on the maximum width or height.
- */
-#define SVGA_MAX_CURSOR_CMD_BYTES  (40 * 1024)
+#define SVGA_MAX_CURSOR_CMD_BYTES (40 * 1024)
 #define SVGA_MAX_CURSOR_CMD_DIMENSION 1024
 
-/*
- * Registers
- */
-
 enum {
-   SVGA_REG_ID = 0,
-   SVGA_REG_ENABLE = 1,
-   SVGA_REG_WIDTH = 2,
-   SVGA_REG_HEIGHT = 3,
-   SVGA_REG_MAX_WIDTH = 4,
-   SVGA_REG_MAX_HEIGHT = 5,
-   SVGA_REG_DEPTH = 6,
-   SVGA_REG_BITS_PER_PIXEL = 7,       /* Current bpp in the guest */
-   SVGA_REG_PSEUDOCOLOR = 8,
-   SVGA_REG_RED_MASK = 9,
-   SVGA_REG_GREEN_MASK = 10,
-   SVGA_REG_BLUE_MASK = 11,
-   SVGA_REG_BYTES_PER_LINE = 12,
-   SVGA_REG_FB_START = 13,            /* (Deprecated) */
-   SVGA_REG_FB_OFFSET = 14,
-   SVGA_REG_VRAM_SIZE = 15,
-   SVGA_REG_FB_SIZE = 16,
-
-   /* ID 0 implementation only had the above registers, then the palette */
-   SVGA_REG_ID_0_TOP = 17,
-
-   SVGA_REG_CAPABILITIES = 17,
-   SVGA_REG_MEM_START = 18,           /* (Deprecated) */
-   SVGA_REG_MEM_SIZE = 19,
-   SVGA_REG_CONFIG_DONE = 20,         /* Set when memory area configured */
-   SVGA_REG_SYNC = 21,                /* See "FIFO Synchronization Registers" */
-   SVGA_REG_BUSY = 22,                /* See "FIFO Synchronization Registers" */
-   SVGA_REG_GUEST_ID = 23,            /* (Deprecated) */
-   SVGA_REG_DEAD = 24,                /* Drivers should never write this. */
-   SVGA_REG_CURSOR_X = 25,            /* (Deprecated) */
-   SVGA_REG_CURSOR_Y = 26,            /* (Deprecated) */
-   SVGA_REG_CURSOR_ON = 27,           /* (Deprecated) */
-   SVGA_REG_HOST_BITS_PER_PIXEL = 28, /* (Deprecated) */
-   SVGA_REG_SCRATCH_SIZE = 29,        /* Number of scratch registers */
-   SVGA_REG_MEM_REGS = 30,            /* Number of FIFO registers */
-   SVGA_REG_NUM_DISPLAYS = 31,        /* (Deprecated) */
-   SVGA_REG_PITCHLOCK = 32,           /* Fixed pitch for all modes */
-   SVGA_REG_IRQMASK = 33,             /* Interrupt mask */
-
-   /* Legacy multi-monitor support */
-   SVGA_REG_NUM_GUEST_DISPLAYS = 34,/* Number of guest displays in X/Y direction */
-   SVGA_REG_DISPLAY_ID = 35,        /* Display ID for the following display attributes */
-   SVGA_REG_DISPLAY_IS_PRIMARY = 36,/* Whether this is a primary display */
-   SVGA_REG_DISPLAY_POSITION_X = 37,/* The display position x */
-   SVGA_REG_DISPLAY_POSITION_Y = 38,/* The display position y */
-   SVGA_REG_DISPLAY_WIDTH = 39,     /* The display's width */
-   SVGA_REG_DISPLAY_HEIGHT = 40,    /* The display's height */
-
-   /* See "Guest memory regions" below. */
-   SVGA_REG_GMR_ID = 41,
-   SVGA_REG_GMR_DESCRIPTOR = 42,
-   SVGA_REG_GMR_MAX_IDS = 43,
-   SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH = 44,
-
-   SVGA_REG_TRACES = 45,            /* Enable trace-based updates even when FIFO is on */
-   SVGA_REG_GMRS_MAX_PAGES = 46,    /* Maximum number of 4KB pages for all GMRs */
-   SVGA_REG_MEMORY_SIZE = 47,       /* Total dedicated device memory excluding FIFO */
-   SVGA_REG_COMMAND_LOW = 48,       /* Lower 32 bits and submits commands */
-   SVGA_REG_COMMAND_HIGH = 49,      /* Upper 32 bits of command buffer PA */
-
-   /*
-    * Max primary memory.
-    * See SVGA_CAP_NO_BB_RESTRICTION.
-    */
-   SVGA_REG_MAX_PRIMARY_MEM = 50,
-   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,
-
-   /*
-    * Legacy version of SVGA_REG_GBOBJECT_MEM_SIZE_KB for drivers that
-    * don't know how to convert to a 64-bit byte value without overflowing.
-    * (See SVGA_REG_GBOBJECT_MEM_SIZE_KB).
-    */
-   SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51,
-
-   SVGA_REG_DEV_CAP = 52,           /* Write dev cap index, read value */
-   SVGA_REG_CMD_PREPEND_LOW = 53,
-   SVGA_REG_CMD_PREPEND_HIGH = 54,
-   SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
-   SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
-   SVGA_REG_MOB_MAX_SIZE = 57,
-   SVGA_REG_BLANK_SCREEN_TARGETS = 58,
-   SVGA_REG_CAP2 = 59,
-   SVGA_REG_DEVEL_CAP = 60,
-
-   /*
-    * Allow the guest to hint to the device which driver is running.
-    *
-    * This should not generally change device behavior, but might be
-    * convenient to work-around specific bugs in guest drivers.
-    *
-    * Drivers should first write their id value into SVGA_REG_GUEST_DRIVER_ID,
-    * and then fill out all of the version registers that they have defined.
-    *
-    * After the driver has written all of the registers, they should
-    * then write the value SVGA_REG_GUEST_DRIVER_ID_SUBMIT to the
-    * SVGA_REG_GUEST_DRIVER_ID register, to signal that they have finished.
-    *
-    * The SVGA_REG_GUEST_DRIVER_ID values are defined below by the
-    * SVGARegGuestDriverId enum.
-    *
-    * The SVGA_REG_GUEST_DRIVER_VERSION fields are driver-specific,
-    * but ideally should encode a monotonically increasing number that allows
-    * the device to perform inequality checks against ranges of driver versions.
-    */
-   SVGA_REG_GUEST_DRIVER_ID = 61,
-   SVGA_REG_GUEST_DRIVER_VERSION1 = 62,
-   SVGA_REG_GUEST_DRIVER_VERSION2 = 63,
-   SVGA_REG_GUEST_DRIVER_VERSION3 = 64,
-   SVGA_REG_CURSOR_MOBID = 65,
-   SVGA_REG_CURSOR_MAX_BYTE_SIZE = 66,
-   SVGA_REG_CURSOR_MAX_DIMENSION = 67,
-
-   SVGA_REG_FIFO_CAPS = 68,
-   SVGA_REG_FENCE = 69,
-
-   SVGA_REG_RESERVED1 = 70,
-   SVGA_REG_RESERVED2 = 71,
-   SVGA_REG_RESERVED3 = 72,
-   SVGA_REG_RESERVED4 = 73,
-   SVGA_REG_RESERVED5 = 74,
-   SVGA_REG_SCREENDMA = 75,
-
-   /*
-    * The maximum amount of guest-backed objects that the device can have
-    * resident at a time. Guest-drivers should keep their working set size
-    * below this limit for best performance.
-    *
-    * Note that this value is in kilobytes, and not bytes, because the actual
-    * number of bytes might be larger than can fit in a 32-bit register.
-    *
-    * PLEASE USE A 64-BIT VALUE WHEN CONVERTING THIS INTO BYTES.
-    * (See SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB).
-    */
-   SVGA_REG_GBOBJECT_MEM_SIZE_KB = 76,
-
-   /*
-    +    * These registers are for the addresses of the memory BARs for SVGA3
-    */
-   SVGA_REG_REGS_START_HIGH32 = 77,
-   SVGA_REG_REGS_START_LOW32 = 78,
-   SVGA_REG_FB_START_HIGH32 = 79,
-   SVGA_REG_FB_START_LOW32 = 80,
-
-   /*
-    * A hint register that recommends which quality level the guest should
-    * currently use to define multisample surfaces.
-    *
-    * If the register is SVGA_REG_MSHINT_DISABLED,
-    * the guest is only allowed to use SVGA3D_MS_QUALITY_FULL.
-    *
-    * Otherwise, this is a live value that can change while the VM is
-    * powered on with the hint suggestion for which quality level the guest
-    * should be using.  Guests are free to ignore the hint and use either
-    * RESOLVE or FULL quality.
-    */
-   SVGA_REG_MSHINT = 81,
-
-   SVGA_REG_IRQ_STATUS = 82,
-   SVGA_REG_DIRTY_TRACKING = 83,
-
-   SVGA_REG_TOP = 84,               /* Must be 1 more than the last register */
-
-   SVGA_PALETTE_BASE = 1024,        /* Base of SVGA color map */
-   /* Next 768 (== 256*3) registers exist for colormap */
-   SVGA_SCRATCH_BASE = SVGA_PALETTE_BASE + SVGA_NUM_PALETTE_REGS
-                                    /* Base of scratch registers */
-   /* Next reg[SVGA_REG_SCRATCH_SIZE] registers exist for scratch usage:
-      First 4 are reserved for VESA BIOS Extension; any remaining are for
-      the use of the current SVGA driver. */
-};
+	SVGA_REG_ID = 0,
+	SVGA_REG_ENABLE = 1,
+	SVGA_REG_WIDTH = 2,
+	SVGA_REG_HEIGHT = 3,
+	SVGA_REG_MAX_WIDTH = 4,
+	SVGA_REG_MAX_HEIGHT = 5,
+	SVGA_REG_DEPTH = 6,
+	SVGA_REG_BITS_PER_PIXEL = 7,
+	SVGA_REG_PSEUDOCOLOR = 8,
+	SVGA_REG_RED_MASK = 9,
+	SVGA_REG_GREEN_MASK = 10,
+	SVGA_REG_BLUE_MASK = 11,
+	SVGA_REG_BYTES_PER_LINE = 12,
+	SVGA_REG_FB_START = 13,
+	SVGA_REG_FB_OFFSET = 14,
+	SVGA_REG_VRAM_SIZE = 15,
+	SVGA_REG_FB_SIZE = 16,
+
+	SVGA_REG_ID_0_TOP = 17,
+
+	SVGA_REG_CAPABILITIES = 17,
+	SVGA_REG_MEM_START = 18,
+	SVGA_REG_MEM_SIZE = 19,
+	SVGA_REG_CONFIG_DONE = 20,
+	SVGA_REG_SYNC = 21,
+	SVGA_REG_BUSY = 22,
+	SVGA_REG_GUEST_ID = 23,
+	SVGA_REG_DEAD = 24,
+	SVGA_REG_CURSOR_X = 25,
+	SVGA_REG_CURSOR_Y = 26,
+	SVGA_REG_CURSOR_ON = 27,
+	SVGA_REG_HOST_BITS_PER_PIXEL = 28,
+	SVGA_REG_SCRATCH_SIZE = 29,
+	SVGA_REG_MEM_REGS = 30,
+	SVGA_REG_NUM_DISPLAYS = 31,
+	SVGA_REG_PITCHLOCK = 32,
+	SVGA_REG_IRQMASK = 33,
+
+	SVGA_REG_NUM_GUEST_DISPLAYS = 34,
+	SVGA_REG_DISPLAY_ID = 35,
+	SVGA_REG_DISPLAY_IS_PRIMARY = 36,
+	SVGA_REG_DISPLAY_POSITION_X = 37,
+	SVGA_REG_DISPLAY_POSITION_Y = 38,
+	SVGA_REG_DISPLAY_WIDTH = 39,
+	SVGA_REG_DISPLAY_HEIGHT = 40,
+
+	SVGA_REG_GMR_ID = 41,
+	SVGA_REG_GMR_DESCRIPTOR = 42,
+	SVGA_REG_GMR_MAX_IDS = 43,
+	SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH = 44,
+
+	SVGA_REG_TRACES = 45,
+	SVGA_REG_GMRS_MAX_PAGES = 46,
+	SVGA_REG_MEMORY_SIZE = 47,
+	SVGA_REG_COMMAND_LOW = 48,
+	SVGA_REG_COMMAND_HIGH = 49,
+
+	SVGA_REG_MAX_PRIMARY_MEM = 50,
+
+	SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51,
+
+	SVGA_REG_DEV_CAP = 52,
+	SVGA_REG_CMD_PREPEND_LOW = 53,
+	SVGA_REG_CMD_PREPEND_HIGH = 54,
+	SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
+	SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
+	SVGA_REG_MOB_MAX_SIZE = 57,
+	SVGA_REG_BLANK_SCREEN_TARGETS = 58,
+	SVGA_REG_CAP2 = 59,
+	SVGA_REG_DEVEL_CAP = 60,
+
+	SVGA_REG_GUEST_DRIVER_ID = 61,
+	SVGA_REG_GUEST_DRIVER_VERSION1 = 62,
+	SVGA_REG_GUEST_DRIVER_VERSION2 = 63,
+	SVGA_REG_GUEST_DRIVER_VERSION3 = 64,
+
+	SVGA_REG_CURSOR_MOBID = 65,
+	SVGA_REG_CURSOR_MAX_BYTE_SIZE = 66,
+	SVGA_REG_CURSOR_MAX_DIMENSION = 67,
+
+	SVGA_REG_FIFO_CAPS = 68,
+	SVGA_REG_FENCE = 69,
+
+	SVGA_REG_CURSOR4_ON = 70,
+	SVGA_REG_CURSOR4_X = 71,
+	SVGA_REG_CURSOR4_Y = 72,
+	SVGA_REG_CURSOR4_SCREEN_ID = 73,
+	SVGA_REG_CURSOR4_SUBMIT = 74,
+
+	SVGA_REG_SCREENDMA = 75,
+
+	SVGA_REG_GBOBJECT_MEM_SIZE_KB = 76,
+
+	SVGA_REG_REGS_START_HIGH32 = 77,
+	SVGA_REG_REGS_START_LOW32 = 78,
+	SVGA_REG_FB_START_HIGH32 = 79,
+	SVGA_REG_FB_START_LOW32 = 80,
+
+	SVGA_REG_MSHINT = 81,
+
+	SVGA_REG_IRQ_STATUS = 82,
+
+	SVGA_REG_DIRTY_TRACKING = 83,
+	SVGA_REG_FENCE_GOAL = 84,
+
+	SVGA_REG_TOP = 85,
+
+	SVGA_PALETTE_BASE = 1024,
+
+	SVGA_SCRATCH_BASE = SVGA_PALETTE_BASE + SVGA_NUM_PALETTE_REGS
 
+};
 
-/*
- * Values for SVGA_REG_GUEST_DRIVER_ID.
- */
 typedef enum SVGARegGuestDriverId {
-   SVGA_REG_GUEST_DRIVER_ID_UNKNOWN = 0,
-   SVGA_REG_GUEST_DRIVER_ID_WDDM    = 1,
-   SVGA_REG_GUEST_DRIVER_ID_LINUX   = 2,
-   SVGA_REG_GUEST_DRIVER_ID_MAX,
+	SVGA_REG_GUEST_DRIVER_ID_UNKNOWN = 0,
+	SVGA_REG_GUEST_DRIVER_ID_WDDM = 1,
+	SVGA_REG_GUEST_DRIVER_ID_LINUX = 2,
+	SVGA_REG_GUEST_DRIVER_ID_MAX,
 
-   SVGA_REG_GUEST_DRIVER_ID_SUBMIT  = MAX_UINT32,
+	SVGA_REG_GUEST_DRIVER_ID_SUBMIT = MAX_UINT32,
 } SVGARegGuestDriverId;
 
 typedef enum SVGARegMSHint {
-   SVGA_REG_MSHINT_DISABLED = 0,
-   SVGA_REG_MSHINT_FULL     = 1,
-   SVGA_REG_MSHINT_RESOLVED = 2,
+	SVGA_REG_MSHINT_DISABLED = 0,
+	SVGA_REG_MSHINT_FULL = 1,
+	SVGA_REG_MSHINT_RESOLVED = 2,
 } SVGARegMSHint;
 
 typedef enum SVGARegDirtyTracking {
-   SVGA_REG_DIRTY_TRACKING_PER_IMAGE = 0,
-   SVGA_REG_DIRTY_TRACKING_PER_SURFACE = 1,
+	SVGA_REG_DIRTY_TRACKING_PER_IMAGE = 0,
+	SVGA_REG_DIRTY_TRACKING_PER_SURFACE = 1,
 } SVGARegDirtyTracking;
 
-
-/*
- * Guest memory regions (GMRs):
- *
- * This is a new memory mapping feature available in SVGA devices
- * which have the SVGA_CAP_GMR bit set. Previously, there were two
- * fixed memory regions available with which to share data between the
- * device and the driver: the FIFO ('MEM') and the framebuffer. GMRs
- * are our name for an extensible way of providing arbitrary DMA
- * buffers for use between the driver and the SVGA device. They are a
- * new alternative to framebuffer memory, usable for both 2D and 3D
- * graphics operations.
- *
- * Since GMR mapping must be done synchronously with guest CPU
- * execution, we use a new pair of SVGA registers:
- *
- *   SVGA_REG_GMR_ID --
- *
- *     Read/write.
- *     This register holds the 32-bit ID (a small positive integer)
- *     of a GMR to create, delete, or redefine. Writing this register
- *     has no side-effects.
- *
- *   SVGA_REG_GMR_DESCRIPTOR --
- *
- *     Write-only.
- *     Writing this register will create, delete, or redefine the GMR
- *     specified by the above ID register. If this register is zero,
- *     the GMR is deleted. Any pointers into this GMR (including those
- *     currently being processed by FIFO commands) will be
- *     synchronously invalidated.
- *
- *     If this register is nonzero, it must be the physical page
- *     number (PPN) of a data structure which describes the physical
- *     layout of the memory region this GMR should describe. The
- *     descriptor structure will be read synchronously by the SVGA
- *     device when this register is written. The descriptor need not
- *     remain allocated for the lifetime of the GMR.
- *
- *     The guest driver should write SVGA_REG_GMR_ID first, then
- *     SVGA_REG_GMR_DESCRIPTOR.
- *
- *   SVGA_REG_GMR_MAX_IDS --
- *
- *     Read-only.
- *     The SVGA device may choose to support a maximum number of
- *     user-defined GMR IDs. This register holds the number of supported
- *     IDs. (The maximum supported ID plus 1)
- *
- *   SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH --
- *
- *     Read-only.
- *     The SVGA device may choose to put a limit on the total number
- *     of SVGAGuestMemDescriptor structures it will read when defining
- *     a single GMR.
- *
- * The descriptor structure is an array of SVGAGuestMemDescriptor
- * structures. Each structure may do one of three things:
- *
- *   - Terminate the GMR descriptor list.
- *     (ppn==0, numPages==0)
- *
- *   - Add a PPN or range of PPNs to the GMR's virtual address space.
- *     (ppn != 0, numPages != 0)
- *
- *   - Provide the PPN of the next SVGAGuestMemDescriptor, in order to
- *     support multi-page GMR descriptor tables without forcing the
- *     driver to allocate physically contiguous memory.
- *     (ppn != 0, numPages == 0)
- *
- * Note that each physical page of SVGAGuestMemDescriptor structures
- * can describe at least 2MB of guest memory. If the driver needs to
- * use more than one page of descriptor structures, it must use one of
- * its SVGAGuestMemDescriptors to point to an additional page.  The
- * device will never automatically cross a page boundary.
- *
- * Once the driver has described a GMR, it is immediately available
- * for use via any FIFO command that uses an SVGAGuestPtr structure.
- * These pointers include a GMR identifier plus an offset into that
- * GMR.
- *
- * The driver must check the SVGA_CAP_GMR bit before using the GMR
- * registers.
- */
-
-/*
- * Special GMR IDs, allowing SVGAGuestPtrs to point to framebuffer
- * memory as well.  In the future, these IDs could even be used to
- * allow legacy memory regions to be redefined by the guest as GMRs.
- *
- * Using the guest framebuffer (GFB) at BAR1 for general purpose DMA
- * is being phased out. Please try to use user-defined GMRs whenever
- * possible.
- */
-#define SVGA_GMR_NULL         ((uint32) -1)
-#define SVGA_GMR_FRAMEBUFFER  ((uint32) -2)  /* Guest Framebuffer (GFB) */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAGuestMemDescriptor {
-   uint32 ppn;
-   uint32 numPages;
-}
-#include "vmware_pack_end.h"
-SVGAGuestMemDescriptor;
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAGuestPtr {
-   uint32 gmrId;
-   uint32 offset;
-}
-#include "vmware_pack_end.h"
-SVGAGuestPtr;
-
-/*
- * Register based command buffers --
- *
- * Provide an SVGA device interface that allows the guest to submit
- * command buffers to the SVGA device through an SVGA device register.
- * The metadata for each command buffer is contained in the
- * SVGACBHeader structure along with the return status codes.
- *
- * The SVGA device supports command buffers if
- * SVGA_CAP_COMMAND_BUFFERS is set in the device caps register.  The
- * fifo must be enabled for command buffers to be submitted.
- *
- * Command buffers are submitted when the guest writing the 64 byte
- * aligned physical address into the SVGA_REG_COMMAND_LOW and
- * SVGA_REG_COMMAND_HIGH.  SVGA_REG_COMMAND_HIGH contains the upper 32
- * bits of the physical address.  SVGA_REG_COMMAND_LOW contains the
- * lower 32 bits of the physical address, since the command buffer
- * headers are required to be 64 byte aligned the lower 6 bits are
- * used for the SVGACBContext value.  Writing to SVGA_REG_COMMAND_LOW
- * submits the command buffer to the device and queues it for
- * execution.  The SVGA device supports at least
- * SVGA_CB_MAX_QUEUED_PER_CONTEXT command buffers that can be queued
- * per context and if that limit is reached the device will write the
- * status SVGA_CB_STATUS_QUEUE_FULL to the status value of the command
- * buffer header synchronously and not raise any IRQs.
- *
- * It is invalid to submit a command buffer without a valid physical
- * address and results are undefined.
- *
- * The device guarantees that command buffers of size SVGA_CB_MAX_SIZE
- * will be supported.  If a larger command buffer is submitted results
- * are unspecified and the device will either complete the command
- * buffer or return an error.
- *
- * The device guarantees that any individual command in a command
- * buffer can be up to SVGA_CB_MAX_COMMAND_SIZE in size which is
- * enough to fit a 64x64 color-cursor definition.  If the command is
- * too large the device is allowed to process the command or return an
- * error.
- *
- * The device context is a special SVGACBContext that allows for
- * synchronous register like accesses with the flexibility of
- * commands.  There is a different command set defined by
- * SVGADeviceContextCmdId.  The commands in each command buffer is not
- * allowed to straddle physical pages.
- *
- * The offset field which is available starting with the
- * SVGA_CAP_CMD_BUFFERS_2 cap bit can be set by the guest to bias the
- * start of command processing into the buffer.  If an error is
- * encountered the errorOffset will still be relative to the specific
- * PA, not biased by the offset.  When the command buffer is finished
- * the guest should not read the offset field as there is no guarantee
- * what it will set to.
- *
- * When the SVGA_CAP_HP_CMD_QUEUE cap bit is set a new command queue
- * SVGA_CB_CONTEXT_1 is available.  Commands submitted to this queue
- * will be executed as quickly as possible by the SVGA device
- * potentially before already queued commands on SVGA_CB_CONTEXT_0.
- * The SVGA device guarantees that any command buffers submitted to
- * SVGA_CB_CONTEXT_0 will be executed after any _already_ submitted
- * command buffers to SVGA_CB_CONTEXT_1.
- */
-
-#define SVGA_CB_MAX_SIZE (512 * 1024)  /* 512 KB */
+#define SVGA_GMR_NULL ((uint32)-1)
+#define SVGA_GMR_FRAMEBUFFER ((uint32)-2)
+
+#pragma pack(push, 1)
+typedef struct SVGAGuestMemDescriptor {
+	uint32 ppn;
+	uint32 numPages;
+} SVGAGuestMemDescriptor;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct SVGAGuestPtr {
+	uint32 gmrId;
+	uint32 offset;
+} SVGAGuestPtr;
+#pragma pack(pop)
+
+#define SVGA_CB_MAX_SIZE_DEFAULT (KBYTES_2_BYTES(512))
+#define SVGA_CB_MAX_SIZE_4MB (MBYTES_2_BYTES(4))
+#define SVGA_CB_MAX_SIZE SVGA_CB_MAX_SIZE_4MB
 #define SVGA_CB_MAX_QUEUED_PER_CONTEXT 32
-#define SVGA_CB_MAX_COMMAND_SIZE (32 * 1024) /* 32 KB */
+#define SVGA_CB_MAX_COMMAND_SIZE (32 * 1024)
 
 #define SVGA_CB_CONTEXT_MASK 0x3f
 typedef enum {
-   SVGA_CB_CONTEXT_DEVICE = 0x3f,
-   SVGA_CB_CONTEXT_0      = 0x0,
-   SVGA_CB_CONTEXT_1      = 0x1, /* Supported with SVGA_CAP_HP_CMD_QUEUE */
-   SVGA_CB_CONTEXT_MAX    = 0x2,
+	SVGA_CB_CONTEXT_DEVICE = 0x3f,
+	SVGA_CB_CONTEXT_0 = 0x0,
+	SVGA_CB_CONTEXT_1 = 0x1,
+	SVGA_CB_CONTEXT_MAX = 0x2,
 } SVGACBContext;
 
-
 typedef enum {
-   /*
-    * The guest is supposed to write SVGA_CB_STATUS_NONE to the status
-    * field before submitting the command buffer header, the host will
-    * change the value when it is done with the command buffer.
-    */
-   SVGA_CB_STATUS_NONE             = 0,
-
-   /*
-    * Written by the host when a command buffer completes successfully.
-    * The device raises an IRQ with SVGA_IRQFLAG_COMMAND_BUFFER unless
-    * the SVGA_CB_FLAG_NO_IRQ flag is set.
-    */
-   SVGA_CB_STATUS_COMPLETED        = 1,
-
-   /*
-    * Written by the host synchronously with the command buffer
-    * submission to indicate the command buffer was not submitted.  No
-    * IRQ is raised.
-    */
-   SVGA_CB_STATUS_QUEUE_FULL       = 2,
-
-   /*
-    * Written by the host when an error was detected parsing a command
-    * in the command buffer, errorOffset is written to contain the
-    * offset to the first byte of the failing command.  The device
-    * raises the IRQ with both SVGA_IRQFLAG_ERROR and
-    * SVGA_IRQFLAG_COMMAND_BUFFER.  Some of the commands may have been
-    * processed.
-    */
-   SVGA_CB_STATUS_COMMAND_ERROR    = 3,
-
-   /*
-    * Written by the host if there is an error parsing the command
-    * buffer header.  The device raises the IRQ with both
-    * SVGA_IRQFLAG_ERROR and SVGA_IRQFLAG_COMMAND_BUFFER.  The device
-    * did not processes any of the command buffer.
-    */
-   SVGA_CB_STATUS_CB_HEADER_ERROR  = 4,
-
-   /*
-    * Written by the host if the guest requested the host to preempt
-    * the command buffer.  The device will not raise any IRQs and the
-    * command buffer was not processed.
-    */
-   SVGA_CB_STATUS_PREEMPTED        = 5,
-
-   /*
-    * Written by the host synchronously with the command buffer
-    * submission to indicate the the command buffer was not submitted
-    * due to an error.  No IRQ is raised.
-    */
-   SVGA_CB_STATUS_SUBMISSION_ERROR = 6,
-
-   /*
-    * Written by the host when the host finished a
-    * SVGA_DC_CMD_ASYNC_STOP_QUEUE request for this command buffer
-    * queue.  The offset of the first byte not processed is stored in
-    * the errorOffset field of the command buffer header.  All guest
-    * visible side effects of commands till that point are guaranteed
-    * to be finished before this is written.  The
-    * SVGA_IRQFLAG_COMMAND_BUFFER IRQ is raised as long as the
-    * SVGA_CB_FLAG_NO_IRQ is not set.
-    */
-   SVGA_CB_STATUS_PARTIAL_COMPLETE = 7,
+
+	SVGA_CB_STATUS_NONE = 0,
+
+	SVGA_CB_STATUS_COMPLETED = 1,
+
+	SVGA_CB_STATUS_QUEUE_FULL = 2,
+
+	SVGA_CB_STATUS_COMMAND_ERROR = 3,
+
+	SVGA_CB_STATUS_CB_HEADER_ERROR = 4,
+
+	SVGA_CB_STATUS_PREEMPTED = 5,
+
+	SVGA_CB_STATUS_SUBMISSION_ERROR = 6,
+
+	SVGA_CB_STATUS_PARTIAL_COMPLETE = 7,
 } SVGACBStatus;
 
 typedef enum {
-   SVGA_CB_FLAG_NONE       = 0,
-   SVGA_CB_FLAG_NO_IRQ     = 1 << 0,
-   SVGA_CB_FLAG_DX_CONTEXT = 1 << 1,
-   SVGA_CB_FLAG_MOB        = 1 << 2,
+	SVGA_CB_FLAG_NONE = 0,
+	SVGA_CB_FLAG_NO_IRQ = 1 << 0,
+	SVGA_CB_FLAG_DX_CONTEXT = 1 << 1,
+	SVGA_CB_FLAG_MOB = 1 << 2,
 } SVGACBFlags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   volatile SVGACBStatus status; /* Modified by device. */
-   volatile uint32 errorOffset;  /* Modified by device. */
-   uint64 id;
-   SVGACBFlags flags;
-   uint32 length;
-   union {
-      PA pa;
-      struct {
-         SVGAMobId mobid;
-         uint32 mobOffset;
-      } mob;
-   } ptr;
-   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise,
-                   * modified by device.
-                   */
-   uint32 dxContext; /* Valid if DX_CONTEXT flag set, must be zero otherwise */
-   uint32 mustBeZero[6];
-}
-#include "vmware_pack_end.h"
-SVGACBHeader;
+#pragma pack(push, 1)
+typedef struct {
+	volatile SVGACBStatus status;
+	volatile uint32 errorOffset;
+	uint64 id;
+	SVGACBFlags flags;
+	uint32 length;
+	union {
+		PA pa;
+		struct {
+			SVGAMobId mobid;
+			uint32 mobOffset;
+		} mob;
+	} ptr;
+	uint32 offset;
+	uint32 dxContext;
+	uint32 mustBeZero[6];
+} SVGACBHeader;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA_DC_CMD_NOP                   = 0,
-   SVGA_DC_CMD_START_STOP_CONTEXT    = 1,
-   SVGA_DC_CMD_PREEMPT               = 2,
-   SVGA_DC_CMD_START_QUEUE           = 3, /* Requires SVGA_CAP_HP_CMD_QUEUE */
-   SVGA_DC_CMD_ASYNC_STOP_QUEUE      = 4, /* Requires SVGA_CAP_HP_CMD_QUEUE */
-   SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE   = 5, /* Requires SVGA_CAP_HP_CMD_QUEUE */
-   SVGA_DC_CMD_MAX                   = 6,
+	SVGA_DC_CMD_NOP = 0,
+	SVGA_DC_CMD_START_STOP_CONTEXT = 1,
+	SVGA_DC_CMD_PREEMPT = 2,
+	SVGA_DC_CMD_START_QUEUE = 3,
+	SVGA_DC_CMD_ASYNC_STOP_QUEUE = 4,
+	SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE = 5,
+	SVGA_DC_CMD_MAX = 6
 } SVGADeviceContextCmdId;
 
-/*
- * Starts or stops both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1.
- */
-
 typedef struct SVGADCCmdStartStop {
-   uint32 enable;
-   SVGACBContext context; /* Must be zero */
+	uint32 enable;
+	SVGACBContext context;
 } SVGADCCmdStartStop;
 
-/*
- * SVGADCCmdPreempt --
- *
- * This command allows the guest to request that all command buffers
- * on SVGA_CB_CONTEXT_0 be preempted that can be.  After execution
- * of this command all command buffers that were preempted will
- * already have SVGA_CB_STATUS_PREEMPTED written into the status
- * field.  The device might still be processing a command buffer,
- * assuming execution of it started before the preemption request was
- * received.  Specifying the ignoreIDZero flag to TRUE will cause the
- * device to not preempt command buffers with the id field in the
- * command buffer header set to zero.
- */
-
 typedef struct SVGADCCmdPreempt {
-   SVGACBContext context; /* Must be zero */
-   uint32 ignoreIDZero;
+	SVGACBContext context;
+	uint32 ignoreIDZero;
 } SVGADCCmdPreempt;
 
-/*
- * Starts the requested command buffer processing queue.  Valid only
- * if the SVGA_CAP_HP_CMD_QUEUE cap is set.
- *
- * For a command queue to be considered runnable it must be enabled
- * and any corresponding higher priority queues must also be enabled.
- * For example in order for command buffers to be processed on
- * SVGA_CB_CONTEXT_0 both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1 must
- * be enabled.  But for commands to be runnable on SVGA_CB_CONTEXT_1
- * only that queue must be enabled.
- */
-
 typedef struct SVGADCCmdStartQueue {
-   SVGACBContext context;
+	SVGACBContext context;
 } SVGADCCmdStartQueue;
 
-/*
- * Requests the SVGA device to stop processing the requested command
- * buffer queue as soon as possible.  The guest knows the stop has
- * completed when one of the following happens.
- *
- * 1) A command buffer status of SVGA_CB_STATUS_PARTIAL_COMPLETE is returned
- * 2) A command buffer error is encountered with would stop the queue
- *    regardless of the async stop request.
- * 3) All command buffers that have been submitted complete successfully.
- * 4) The stop completes synchronously if no command buffers are
- *    active on the queue when it is issued.
- *
- * If the command queue is not in a runnable state there is no
- * guarentee this async stop will finish.  For instance if the high
- * priority queue is not enabled and a stop is requested on the low
- * priority queue, the high priority queue must be reenabled to
- * guarantee that the async stop will finish.
- *
- * This command along with SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE can be used
- * to implement mid command buffer preemption.
- *
- * Valid only if the SVGA_CAP_HP_CMD_QUEUE cap is set.
- */
-
 typedef struct SVGADCCmdAsyncStopQueue {
-   SVGACBContext context;
+	SVGACBContext context;
 } SVGADCCmdAsyncStopQueue;
 
-/*
- * Requests the SVGA device to throw away any full command buffers on
- * the requested command queue that have not been started.  For a
- * driver to know which command buffers were thrown away a driver
- * should only issue this command when the queue is stopped, for
- * whatever reason.
- */
-
 typedef struct SVGADCCmdEmptyQueue {
-   SVGACBContext context;
+	SVGACBContext context;
 } SVGADCCmdEmptyQueue;
 
-
-/*
- * SVGAGMRImageFormat --
- *
- *    This is a packed representation of the source 2D image format
- *    for a GMR-to-screen blit. Currently it is defined as an encoding
- *    of the screen's color depth and bits-per-pixel, however, 16 bits
- *    are reserved for future use to identify other encodings (such as
- *    RGBA or higher-precision images).
- *
- *    Currently supported formats:
- *
- *       bpp depth  Format Name
- *       --- -----  -----------
- *        32    24  32-bit BGRX
- *        24    24  24-bit BGR
- *        16    16  RGB 5-6-5
- *        16    15  RGB 5-5-5
- *
- */
-
 typedef struct SVGAGMRImageFormat {
-   union {
-      struct {
-         uint32 bitsPerPixel : 8;
-         uint32 colorDepth   : 8;
-         uint32 reserved     : 16;  /* Must be zero */
-      };
-
-      uint32 value;
-   };
+	union {
+		struct {
+			uint32 bitsPerPixel : 8;
+			uint32 colorDepth : 8;
+			uint32 reserved : 16;
+		};
+
+		uint32 value;
+	};
 } SVGAGMRImageFormat;
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAGuestImage {
-   SVGAGuestPtr         ptr;
-
-   /*
-    * A note on interpretation of pitch: This value of pitch is the
-    * number of bytes between vertically adjacent image
-    * blocks. Normally this is the number of bytes between the first
-    * pixel of two adjacent scanlines. With compressed textures,
-    * however, this may represent the number of bytes between
-    * compression blocks rather than between rows of pixels.
-    *
-    * XXX: Compressed textures currently must be tightly packed in guest memory.
-    *
-    * If the image is 1-dimensional, pitch is ignored.
-    *
-    * If 'pitch' is zero, the SVGA3D device calculates a pitch value
-    * assuming each row of blocks is tightly packed.
-    */
-   uint32 pitch;
-}
-#include "vmware_pack_end.h"
-SVGAGuestImage;
+#pragma pack(push, 1)
+typedef struct SVGAGuestImage {
+	SVGAGuestPtr ptr;
 
-/*
- * SVGAColorBGRX --
- *
- *    A 24-bit color format (BGRX), which does not depend on the
- *    format of the legacy guest framebuffer (GFB) or the current
- *    GMRFB state.
- */
+	uint32 pitch;
+} SVGAGuestImage;
+#pragma pack(pop)
 
 typedef struct SVGAColorBGRX {
-   union {
-      struct {
-         uint32 b : 8;
-         uint32 g : 8;
-         uint32 r : 8;
-	 uint32 x : 8;  /* Unused */
-      };
-
-      uint32 value;
-   };
+	union {
+		struct {
+			uint32 b : 8;
+			uint32 g : 8;
+			uint32 r : 8;
+			uint32 x : 8;
+		};
+
+		uint32 value;
+	};
 } SVGAColorBGRX;
 
-
-/*
- * SVGASignedRect --
- * SVGASignedPoint --
- *
- *    Signed rectangle and point primitives. These are used by the new
- *    2D primitives for drawing to Screen Objects, which can occupy a
- *    signed virtual coordinate space.
- *
- *    SVGASignedRect specifies a half-open interval: the (left, top)
- *    pixel is part of the rectangle, but the (right, bottom) pixel is
- *    not.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   int32  left;
-   int32  top;
-   int32  right;
-   int32  bottom;
-}
-#include "vmware_pack_end.h"
-SVGASignedRect;
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   int32  x;
-   int32  y;
-}
-#include "vmware_pack_end.h"
-SVGASignedPoint;
-
-
-/*
- * SVGA Device Capabilities
- *
- * Note the holes in the bitfield. Missing bits have been deprecated,
- * and must not be reused. Those capabilities will never be reported
- * by new versions of the SVGA device.
- *
- * SVGA_CAP_IRQMASK --
- *    Provides device interrupts.  Adds device register SVGA_REG_IRQMASK
- *    to set interrupt mask and direct I/O port SVGA_IRQSTATUS_PORT to
- *    set/clear pending interrupts.
- *
- * SVGA_CAP_GMR --
- *    Provides synchronous mapping of guest memory regions (GMR).
- *    Adds device registers SVGA_REG_GMR_ID, SVGA_REG_GMR_DESCRIPTOR,
- *    SVGA_REG_GMR_MAX_IDS, and SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH.
- *
- * SVGA_CAP_TRACES --
- *    Allows framebuffer trace-based updates even when FIFO is enabled.
- *    Adds device register SVGA_REG_TRACES.
- *
- * SVGA_CAP_GMR2 --
- *    Provides asynchronous commands to define and remap guest memory
- *    regions.  Adds device registers SVGA_REG_GMRS_MAX_PAGES and
- *    SVGA_REG_MEMORY_SIZE.
- *
- * SVGA_CAP_SCREEN_OBJECT_2 --
- *    Allow screen object support, and require backing stores from the
- *    guest for each screen object.
- *
- * SVGA_CAP_COMMAND_BUFFERS --
- *    Enable register based command buffer submission.
- *
- * SVGA_CAP_DEAD1 --
- *    This cap was incorrectly used by old drivers and should not be
- *    reused.
- *
- * SVGA_CAP_CMD_BUFFERS_2 --
- *    Enable support for the prepend command buffer submision
- *    registers.  SVGA_REG_CMD_PREPEND_LOW and
- *    SVGA_REG_CMD_PREPEND_HIGH.
- *
- * SVGA_CAP_GBOBJECTS --
- *    Enable guest-backed objects and surfaces.
- *
- * SVGA_CAP_DX --
- *    Enable support for DX commands, and command buffers in a mob.
- *
- * SVGA_CAP_HP_CMD_QUEUE --
- *    Enable support for the high priority command queue, and the
- *    ScreenCopy command.
- *
- * SVGA_CAP_NO_BB_RESTRICTION --
- *    Allow ScreenTargets to be defined without regard to the 32-bpp
- *    bounding-box memory restrictions. ie:
- *
- *    The summed memory usage of all screens (assuming they were defined as
- *    32-bpp) must always be less than the value of the
- *    SVGA_REG_MAX_PRIMARY_MEM register.
- *
- *    If this cap is not present, the 32-bpp bounding box around all screens
- *    must additionally be under the value of the SVGA_REG_MAX_PRIMARY_MEM
- *    register.
- *
- *    If the cap is present, the bounding box restriction is lifted (and only
- *    the screen-sum limit applies).
- *
- *    (Note that this is a slight lie... there is still a sanity limit on any
- *     dimension of the topology to be less than SVGA_SCREEN_ROOT_LIMIT, even
- *     when SVGA_CAP_NO_BB_RESTRICTION is present, but that should be
- *     large enough to express any possible topology without holes between
- *     monitors.)
- *
- * SVGA_CAP_CAP2_REGISTER --
- *    If this cap is present, the SVGA_REG_CAP2 register is supported.
- */
-
-#define SVGA_CAP_NONE               0x00000000
-#define SVGA_CAP_RECT_COPY          0x00000002
-#define SVGA_CAP_CURSOR             0x00000020
-#define SVGA_CAP_CURSOR_BYPASS      0x00000040
-#define SVGA_CAP_CURSOR_BYPASS_2    0x00000080
-#define SVGA_CAP_8BIT_EMULATION     0x00000100
-#define SVGA_CAP_ALPHA_CURSOR       0x00000200
-#define SVGA_CAP_3D                 0x00004000
-#define SVGA_CAP_EXTENDED_FIFO      0x00008000
-#define SVGA_CAP_MULTIMON           0x00010000
-#define SVGA_CAP_PITCHLOCK          0x00020000
-#define SVGA_CAP_IRQMASK            0x00040000
-#define SVGA_CAP_DISPLAY_TOPOLOGY   0x00080000
-#define SVGA_CAP_GMR                0x00100000
-#define SVGA_CAP_TRACES             0x00200000
-#define SVGA_CAP_GMR2               0x00400000
-#define SVGA_CAP_SCREEN_OBJECT_2    0x00800000
-#define SVGA_CAP_COMMAND_BUFFERS    0x01000000
-#define SVGA_CAP_DEAD1              0x02000000
-#define SVGA_CAP_CMD_BUFFERS_2      0x04000000
-#define SVGA_CAP_GBOBJECTS          0x08000000
-#define SVGA_CAP_DX                 0x10000000
-#define SVGA_CAP_HP_CMD_QUEUE       0x20000000
-#define SVGA_CAP_NO_BB_RESTRICTION  0x40000000
-#define SVGA_CAP_CAP2_REGISTER      0x80000000
-
-/*
- * The SVGA_REG_CAP2 register is an additional set of SVGA capability bits.
- *
- * SVGA_CAP2_GROW_OTABLE --
- *      Allow the GrowOTable/DXGrowCOTable commands.
- *
- * SVGA_CAP2_INTRA_SURFACE_COPY --
- *      Allow the IntraSurfaceCopy command.
- *
- * SVGA_CAP2_DX2 --
- *      Allow the DefineGBSurface_v3, WholeSurfaceCopy, WriteZeroSurface, and
- *      HintZeroSurface commands, and the SVGA_REG_GUEST_DRIVER_ID register.
- *
- * SVGA_CAP2_GB_MEMSIZE_2 --
- *      Allow the SVGA_REG_GBOBJECT_MEM_SIZE_KB register.
- *
- * SVGA_CAP2_SCREENDMA_REG --
- *      Allow the SVGA_REG_SCREENDMA register.
- *
- * SVGA_CAP2_OTABLE_PTDEPTH_2 --
- *      Allow 2 level page tables for OTable commands.
- *
- * SVGA_CAP2_NON_MS_TO_MS_STRETCHBLT --
- *      Allow a stretch blt from a non-multisampled surface to a multisampled
- *      surface.
- *
- * SVGA_CAP2_CURSOR_MOB --
- *      Allow the SVGA_REG_CURSOR_MOBID register.
- *
- * SVGA_CAP2_MSHINT --
- *      Allow the SVGA_REG_MSHINT register.
- *
- * SVGA_CAP2_DX3 --
- *      Allows the DefineGBSurface_v4 command.
- *      Allows the DXDefineDepthStencilView_v2, DXDefineStreamOutputWithMob,
- *      and DXBindStreamOutput commands if 3D is also available.
- *      Allows the DXPredStagingCopy and DXStagingCopy commands if SM41
- *      is also available.
- *
- * SVGA_CAP2_RESERVED --
- *      Reserve the last bit for extending the SVGA capabilities to some
- *      future mechanisms.
- */
-#define SVGA_CAP2_NONE                    0x00000000
-#define SVGA_CAP2_GROW_OTABLE             0x00000001
-#define SVGA_CAP2_INTRA_SURFACE_COPY      0x00000002
-#define SVGA_CAP2_DX2                     0x00000004
-#define SVGA_CAP2_GB_MEMSIZE_2            0x00000008
-#define SVGA_CAP2_SCREENDMA_REG           0x00000010
-#define SVGA_CAP2_OTABLE_PTDEPTH_2        0x00000020
+#pragma pack(push, 1)
+typedef struct {
+	int32 left;
+	int32 top;
+	int32 right;
+	int32 bottom;
+} SVGASignedRect;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	int32 x;
+	int32 y;
+} SVGASignedPoint;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 x;
+	uint32 y;
+} SVGAUnsignedPoint;
+#pragma pack(pop)
+
+#define SVGA_CAP_NONE 0x00000000
+#define SVGA_CAP_RECT_COPY 0x00000002
+#define SVGA_CAP_CURSOR 0x00000020
+#define SVGA_CAP_CURSOR_BYPASS 0x00000040
+#define SVGA_CAP_CURSOR_BYPASS_2 0x00000080
+#define SVGA_CAP_8BIT_EMULATION 0x00000100
+#define SVGA_CAP_ALPHA_CURSOR 0x00000200
+#define SVGA_CAP_3D 0x00004000
+#define SVGA_CAP_EXTENDED_FIFO 0x00008000
+#define SVGA_CAP_MULTIMON 0x00010000
+#define SVGA_CAP_PITCHLOCK 0x00020000
+#define SVGA_CAP_IRQMASK 0x00040000
+#define SVGA_CAP_DISPLAY_TOPOLOGY 0x00080000
+#define SVGA_CAP_GMR 0x00100000
+#define SVGA_CAP_TRACES 0x00200000
+#define SVGA_CAP_GMR2 0x00400000
+#define SVGA_CAP_SCREEN_OBJECT_2 0x00800000
+#define SVGA_CAP_COMMAND_BUFFERS 0x01000000
+#define SVGA_CAP_DEAD1 0x02000000
+#define SVGA_CAP_CMD_BUFFERS_2 0x04000000
+#define SVGA_CAP_GBOBJECTS 0x08000000
+#define SVGA_CAP_DX 0x10000000
+#define SVGA_CAP_HP_CMD_QUEUE 0x20000000
+#define SVGA_CAP_NO_BB_RESTRICTION 0x40000000
+#define SVGA_CAP_CAP2_REGISTER 0x80000000
+
+#define SVGA_CAP2_NONE 0x00000000
+#define SVGA_CAP2_GROW_OTABLE 0x00000001
+#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002
+#define SVGA_CAP2_DX2 0x00000004
+#define SVGA_CAP2_GB_MEMSIZE_2 0x00000008
+#define SVGA_CAP2_SCREENDMA_REG 0x00000010
+#define SVGA_CAP2_OTABLE_PTDEPTH_2 0x00000020
 #define SVGA_CAP2_NON_MS_TO_MS_STRETCHBLT 0x00000040
-#define SVGA_CAP2_CURSOR_MOB              0x00000080
-#define SVGA_CAP2_MSHINT                  0x00000100
-#define SVGA_CAP2_DX3                     0x00000400
-#define SVGA_CAP2_RESERVED                0x80000000
-
-
-/*
- * The Guest can optionally read some SVGA device capabilities through
- * the backdoor with command BDOOR_CMD_GET_SVGA_CAPABILITIES before
- * the SVGA device is initialized.  The type of capability the guest
- * is requesting from the SVGABackdoorCapType enum should be placed in
- * the upper 16 bits of the backdoor command id (ECX).  On success the
- * the value of EBX will be set to BDOOR_MAGIC and EAX will be set to
- * the requested capability.  If the command is not supported then EBX
- * will be left unchanged and EAX will be set to -1.  Because it is
- * possible that -1 is the value of the requested cap the correct way
- * to check if the command was successful is to check if EBX was changed
- * to BDOOR_MAGIC making sure to initialize the register to something
- * else first.
- */
+#define SVGA_CAP2_CURSOR_MOB 0x00000080
+#define SVGA_CAP2_MSHINT 0x00000100
+#define SVGA_CAP2_CB_MAX_SIZE_4MB 0x00000200
+#define SVGA_CAP2_DX3 0x00000400
+#define SVGA_CAP2_FRAME_TYPE 0x00000800
+#define SVGA_CAP2_COTABLE_COPY 0x00001000
+#define SVGA_CAP2_TRACE_FULL_FB 0x00002000
+#define SVGA_CAP2_EXTRA_REGS 0x00004000
+#define SVGA_CAP2_LO_STAGING 0x00008000
+#define SVGA_CAP2_RESERVED 0x80000000
 
 typedef enum {
-   SVGABackdoorCapDeviceCaps = 0,
-   SVGABackdoorCapFifoCaps = 1,
-   SVGABackdoorCap3dHWVersion = 2,
-   SVGABackdoorCapDeviceCaps2 = 3,
-   SVGABackdoorCapDevelCaps = 4,
-   SVGABackdoorDevelRenderer = 5,
-   SVGABackdoorCapMax = 6,
+	SVGABackdoorCapDeviceCaps = 0,
+	SVGABackdoorCapFifoCaps = 1,
+	SVGABackdoorCap3dHWVersion = 2,
+	SVGABackdoorCapDeviceCaps2 = 3,
+	SVGABackdoorCapDevelCaps = 4,
+	SVGABackdoorDevelRenderer = 5,
+	SVGABackdoorDevelUsingISB = 6,
+	SVGABackdoorCapMax = 7,
 } SVGABackdoorCapType;
 
-
-/*
- * FIFO register indices.
- *
- * The FIFO is a chunk of device memory mapped into guest physmem.  It
- * is always treated as 32-bit words.
- *
- * The guest driver gets to decide how to partition it between
- * - FIFO registers (there are always at least 4, specifying where the
- *   following data area is and how much data it contains; there may be
- *   more registers following these, depending on the FIFO protocol
- *   version in use)
- * - FIFO data, written by the guest and slurped out by the VMX.
- * These indices are 32-bit word offsets into the FIFO.
- */
-
 enum {
-   /*
-    * Block 1 (basic registers): The originally defined FIFO registers.
-    * These exist and are valid for all versions of the FIFO protocol.
-    */
-
-   SVGA_FIFO_MIN = 0,
-   SVGA_FIFO_MAX,       /* The distance from MIN to MAX must be at least 10K */
-   SVGA_FIFO_NEXT_CMD,
-   SVGA_FIFO_STOP,
-
-   /*
-    * Block 2 (extended registers): Mandatory registers for the extended
-    * FIFO.  These exist if the SVGA caps register includes
-    * SVGA_CAP_EXTENDED_FIFO; some of them are valid only if their
-    * associated capability bit is enabled.
-    *
-    * Note that when originally defined, SVGA_CAP_EXTENDED_FIFO implied
-    * support only for (FIFO registers) CAPABILITIES, FLAGS, and FENCE.
-    * This means that the guest has to test individually (in most cases
-    * using FIFO caps) for the presence of registers after this; the VMX
-    * can define "extended FIFO" to mean whatever it wants, and currently
-    * won't enable it unless there's room for that set and much more.
-    */
-
-   SVGA_FIFO_CAPABILITIES = 4,
-   SVGA_FIFO_FLAGS,
-   /* Valid with SVGA_FIFO_CAP_FENCE: */
-   SVGA_FIFO_FENCE,
-
-   /*
-    * Block 3a (optional extended registers): Additional registers for the
-    * extended FIFO, whose presence isn't actually implied by
-    * SVGA_CAP_EXTENDED_FIFO; these exist if SVGA_FIFO_MIN is high enough to
-    * leave room for them.
-    *
-    * These in block 3a, the VMX currently considers mandatory for the
-    * extended FIFO.
-    */
-
-   /* Valid if exists (i.e. if extended FIFO enabled): */
-   SVGA_FIFO_3D_HWVERSION,       /* See SVGA3dHardwareVersion in svga3d_reg.h */
-   /* Valid with SVGA_FIFO_CAP_PITCHLOCK: */
-   SVGA_FIFO_PITCHLOCK,
-
-   /* Valid with SVGA_FIFO_CAP_CURSOR_BYPASS_3: */
-   SVGA_FIFO_CURSOR_ON,          /* Cursor bypass 3 show/hide register */
-   SVGA_FIFO_CURSOR_X,           /* Cursor bypass 3 x register */
-   SVGA_FIFO_CURSOR_Y,           /* Cursor bypass 3 y register */
-   SVGA_FIFO_CURSOR_COUNT,       /* Incremented when any of the other 3 change */
-   SVGA_FIFO_CURSOR_LAST_UPDATED,/* Last time the host updated the cursor */
-
-   /* Valid with SVGA_FIFO_CAP_RESERVE: */
-   SVGA_FIFO_RESERVED,           /* Bytes past NEXT_CMD with real contents */
-
-   /*
-    * Valid with SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2:
-    *
-    * By default this is SVGA_ID_INVALID, to indicate that the cursor
-    * coordinates are specified relative to the virtual root. If this
-    * is set to a specific screen ID, cursor position is reinterpreted
-    * as a signed offset relative to that screen's origin.
-    */
-   SVGA_FIFO_CURSOR_SCREEN_ID,
-
-   /*
-    * Valid with SVGA_FIFO_CAP_DEAD
-    *
-    * An arbitrary value written by the host, drivers should not use it.
-    */
-   SVGA_FIFO_DEAD,
-
-   /*
-    * Valid with SVGA_FIFO_CAP_3D_HWVERSION_REVISED:
-    *
-    * Contains 3D HWVERSION (see SVGA3dHardwareVersion in svga3d_reg.h)
-    * on platforms that can enforce graphics resource limits.
-    */
-   SVGA_FIFO_3D_HWVERSION_REVISED,
-
-   /*
-    * XXX: The gap here, up until SVGA_FIFO_3D_CAPS, can be used for new
-    * registers, but this must be done carefully and with judicious use of
-    * capability bits, since comparisons based on SVGA_FIFO_MIN aren't
-    * enough to tell you whether the register exists: we've shipped drivers
-    * and products that used SVGA_FIFO_3D_CAPS but didn't know about some of
-    * the earlier ones.  The actual order of introduction was:
-    * - PITCHLOCK
-    * - 3D_CAPS
-    * - CURSOR_* (cursor bypass 3)
-    * - RESERVED
-    * So, code that wants to know whether it can use any of the
-    * aforementioned registers, or anything else added after PITCHLOCK and
-    * before 3D_CAPS, needs to reason about something other than
-    * SVGA_FIFO_MIN.
-    */
-
-   /*
-    * 3D caps block space; valid with 3D hardware version >=
-    * SVGA3D_HWVERSION_WS6_B1.
-    */
-   SVGA_FIFO_3D_CAPS      = 32,
-   SVGA_FIFO_3D_CAPS_LAST = 32 + 255,
-
-   /*
-    * End of VMX's current definition of "extended-FIFO registers".
-    * Registers before here are always enabled/disabled as a block; either
-    * the extended FIFO is enabled and includes all preceding registers, or
-    * it's disabled entirely.
-    *
-    * Block 3b (truly optional extended registers): Additional registers for
-    * the extended FIFO, which the VMX already knows how to enable and
-    * disable with correct granularity.
-    *
-    * Registers after here exist if and only if the guest SVGA driver
-    * sets SVGA_FIFO_MIN high enough to leave room for them.
-    */
-
-   /* Valid if register exists: */
-   SVGA_FIFO_GUEST_3D_HWVERSION, /* Guest driver's 3D version */
-   SVGA_FIFO_FENCE_GOAL,         /* Matching target for SVGA_IRQFLAG_FENCE_GOAL */
-   SVGA_FIFO_BUSY,               /* See "FIFO Synchronization Registers" */
-
-   /*
-    * Always keep this last.  This defines the maximum number of
-    * registers we know about.  At power-on, this value is placed in
-    * the SVGA_REG_MEM_REGS register, and we expect the guest driver
-    * to allocate this much space in FIFO memory for registers.
-    */
-    SVGA_FIFO_NUM_REGS
-};
 
+	SVGA_FIFO_MIN = 0,
+	SVGA_FIFO_MAX,
+	SVGA_FIFO_NEXT_CMD,
+	SVGA_FIFO_STOP,
 
-/*
- * Definition of registers included in extended FIFO support.
- *
- * The guest SVGA driver gets to allocate the FIFO between registers
- * and data.  It must always allocate at least 4 registers, but old
- * drivers stopped there.
- *
- * The VMX will enable extended FIFO support if and only if the guest
- * left enough room for all registers defined as part of the mandatory
- * set for the extended FIFO.
- *
- * Note that the guest drivers typically allocate the FIFO only at
- * initialization time, not at mode switches, so it's likely that the
- * number of FIFO registers won't change without a reboot.
- *
- * All registers less than this value are guaranteed to be present if
- * svgaUser->fifo.extended is set. Any later registers must be tested
- * individually for compatibility at each use (in the VMX).
- *
- * This value is used only by the VMX, so it can change without
- * affecting driver compatibility; keep it that way?
- */
-#define SVGA_FIFO_EXTENDED_MANDATORY_REGS  (SVGA_FIFO_3D_CAPS_LAST + 1)
+	SVGA_FIFO_CAPABILITIES = 4,
+	SVGA_FIFO_FLAGS,
 
+	SVGA_FIFO_FENCE,
 
-/*
- * FIFO Synchronization Registers
- *
- *  SVGA_REG_SYNC --
- *
- *       The SYNC register can be used by the guest driver to signal to the
- *       device that the guest driver is waiting for previously submitted
- *       commands to complete.
- *
- *       When the guest driver writes to the SYNC register, the device sets
- *       the BUSY register to TRUE, and starts processing the submitted commands
- *       (if it was not already doing so).  When all previously submitted
- *       commands are finished and the device is idle again, it sets the BUSY
- *       register back to FALSE.  (If the guest driver submits new commands
- *       after writing the SYNC register, the new commands are not guaranteed
- *       to have been procesesd.)
- *
- *       When guest drivers are submitting commands using the FIFO, the device
- *       periodically polls to check for new FIFO commands when idle, which may
- *       introduce a delay in command processing.  If the guest-driver wants
- *       the commands to be processed quickly (which it typically does), it
- *       should write SYNC after each batch of commands is committed to the
- *       FIFO to immediately wake up the device.  For even better performance,
- *       the guest can use the SVGA_FIFO_BUSY register to avoid these extra
- *       SYNC writes if the device is already active, using the technique known
- *       as "Ringing the Doorbell" (described below).  (Note that command
- *       buffer submission implicitly wakes up the device, and so doesn't
- *       suffer from this problem.)
- *
- *       The SYNC register can also be used in combination with BUSY to
- *       synchronously ensure that all SVGA commands are processed (with both
- *       the FIFO and command-buffers).  To do this, the guest driver should
- *       write to SYNC, and then loop reading BUSY until BUSY returns FALSE.
- *       This technique is known as a "Legacy Sync".
- *
- *  SVGA_REG_BUSY --
- *
- *       This register is set to TRUE when SVGA_REG_SYNC is written,
- *       and is set back to FALSE when the device has finished processing
- *       all commands and is idle again.
- *
- *       Every read from the BUSY reigster will block for an undefined
- *       amount of time (normally until the device finishes some interesting
- *       work unit), or the device is idle.
- *
- *       Guest drivers can also do a partial Legacy Sync to check for some
- *       particular condition, for instance by stopping early when a fence
- *       passes before BUSY has been set back to FALSE.  This is particularly
- *       useful if the guest-driver knows that it is blocked waiting on the
- *       device, because it will yield CPU time back to the host.
- *
- *  SVGA_FIFO_BUSY --
- *
- *       The SVGA_FIFO_BUSY register is a fast way for the guest driver to check
- *       whether the device is actively processing FIFO commands before writing
- *       the more expensive SYNC register.
- *
- *       If this register reads as TRUE, the device is actively processing
- *       FIFO commands.
- *
- *       If this register reads as FALSE, the device may not be actively
- *       processing commands, and the guest driver should try
- *       "Ringing the Doorbell".
- *
- *       To Ring the Doorbell, the guest should:
- *
- *       1. Have already written their batch of commands into the FIFO.
- *       2. Check if the SVGA_FIFO_BUSY register is available by reading
- *          SVGA_FIFO_MIN.
- *       3. Read SVGA_FIFO_BUSY.  If it reads as TRUE, the device is actively
- *          processing FIFO commands, and no further action is necessary.
- *       4. If SVGA_FIFO_BUSY was FALSE, write TRUE to SVGA_REG_SYNC.
- *
- *       For maximum performance, this procedure should be followed after
- *       every meaningful batch of commands has been written into the FIFO.
- *       (Normally when the underlying application signals it's finished a
- *       meaningful work unit by calling Flush.)
- */
+	SVGA_FIFO_3D_HWVERSION,
 
+	SVGA_FIFO_PITCHLOCK,
 
-/*
- * FIFO Capabilities
- *
- *      Fence -- Fence register and command are supported
- *      Accel Front -- Front buffer only commands are supported
- *      Pitch Lock -- Pitch lock register is supported
- *      Video -- SVGA Video overlay units are supported
- *      Escape -- Escape command is supported
- *
- * SVGA_FIFO_CAP_SCREEN_OBJECT --
- *
- *    Provides dynamic multi-screen rendering, for improved Unity and
- *    multi-monitor modes. With Screen Object, the guest can
- *    dynamically create and destroy 'screens', which can represent
- *    Unity windows or virtual monitors. Screen Object also provides
- *    strong guarantees that DMA operations happen only when
- *    guest-initiated. Screen Object deprecates the BAR1 guest
- *    framebuffer (GFB) and all commands that work only with the GFB.
- *
- *    New registers:
- *       FIFO_CURSOR_SCREEN_ID, VIDEO_DATA_GMRID, VIDEO_DST_SCREEN_ID
- *
- *    New 2D commands:
- *       DEFINE_SCREEN, DESTROY_SCREEN, DEFINE_GMRFB, BLIT_GMRFB_TO_SCREEN,
- *       BLIT_SCREEN_TO_GMRFB, ANNOTATION_FILL, ANNOTATION_COPY
- *
- *    New 3D commands:
- *       BLIT_SURFACE_TO_SCREEN
- *
- *    New guarantees:
- *
- *       - The host will not read or write guest memory, including the GFB,
- *         except when explicitly initiated by a DMA command.
- *
- *       - All DMA, including legacy DMA like UPDATE and PRESENT_READBACK,
- *         is guaranteed to complete before any subsequent FENCEs.
- *
- *       - All legacy commands which affect a Screen (UPDATE, PRESENT,
- *         PRESENT_READBACK) as well as new Screen blit commands will
- *         all behave consistently as blits, and memory will be read
- *         or written in FIFO order.
- *
- *         For example, if you PRESENT from one SVGA3D surface to multiple
- *         places on the screen, the data copied will always be from the
- *         SVGA3D surface at the time the PRESENT was issued in the FIFO.
- *         This was not necessarily true on devices without Screen Object.
- *
- *         This means that on devices that support Screen Object, the
- *         PRESENT_READBACK command should not be necessary unless you
- *         actually want to read back the results of 3D rendering into
- *         system memory. (And for that, the BLIT_SCREEN_TO_GMRFB
- *         command provides a strict superset of functionality.)
- *
- *       - When a screen is resized, either using Screen Object commands or
- *         legacy multimon registers, its contents are preserved.
- *
- * SVGA_FIFO_CAP_GMR2 --
- *
- *    Provides new commands to define and remap guest memory regions (GMR).
- *
- *    New 2D commands:
- *       DEFINE_GMR2, REMAP_GMR2.
- *
- * SVGA_FIFO_CAP_3D_HWVERSION_REVISED --
- *
- *    Indicates new register SVGA_FIFO_3D_HWVERSION_REVISED exists.
- *    This register may replace SVGA_FIFO_3D_HWVERSION on platforms
- *    that enforce graphics resource limits.  This allows the platform
- *    to clear SVGA_FIFO_3D_HWVERSION and disable 3D in legacy guest
- *    drivers that do not limit their resources.
- *
- *    Note this is an alias to SVGA_FIFO_CAP_GMR2 because these indicators
- *    are codependent (and thus we use a single capability bit).
- *
- * SVGA_FIFO_CAP_SCREEN_OBJECT_2 --
- *
- *    Modifies the DEFINE_SCREEN command to include a guest provided
- *    backing store in GMR memory and the bytesPerLine for the backing
- *    store.  This capability requires the use of a backing store when
- *    creating screen objects.  However if SVGA_FIFO_CAP_SCREEN_OBJECT
- *    is present then backing stores are optional.
- *
- * SVGA_FIFO_CAP_DEAD --
- *
- *    Drivers should not use this cap bit.  This cap bit can not be
- *    reused since some hosts already expose it.
- */
+	SVGA_FIFO_CURSOR_ON,
+	SVGA_FIFO_CURSOR_X,
+	SVGA_FIFO_CURSOR_Y,
+	SVGA_FIFO_CURSOR_COUNT,
+	SVGA_FIFO_CURSOR_LAST_UPDATED,
 
-#define SVGA_FIFO_CAP_NONE                  0
-#define SVGA_FIFO_CAP_FENCE             (1<<0)
-#define SVGA_FIFO_CAP_ACCELFRONT        (1<<1)
-#define SVGA_FIFO_CAP_PITCHLOCK         (1<<2)
-#define SVGA_FIFO_CAP_VIDEO             (1<<3)
-#define SVGA_FIFO_CAP_CURSOR_BYPASS_3   (1<<4)
-#define SVGA_FIFO_CAP_ESCAPE            (1<<5)
-#define SVGA_FIFO_CAP_RESERVE           (1<<6)
-#define SVGA_FIFO_CAP_SCREEN_OBJECT     (1<<7)
-#define SVGA_FIFO_CAP_GMR2              (1<<8)
-#define SVGA_FIFO_CAP_3D_HWVERSION_REVISED  SVGA_FIFO_CAP_GMR2
-#define SVGA_FIFO_CAP_SCREEN_OBJECT_2   (1<<9)
-#define SVGA_FIFO_CAP_DEAD              (1<<10)
+	SVGA_FIFO_RESERVED,
 
+	SVGA_FIFO_CURSOR_SCREEN_ID,
 
-/*
- * FIFO Flags
- *
- *      Accel Front -- Driver should use front buffer only commands
- */
+	SVGA_FIFO_DEAD,
 
-#define SVGA_FIFO_FLAG_NONE                 0
-#define SVGA_FIFO_FLAG_ACCELFRONT       (1<<0)
-#define SVGA_FIFO_FLAG_RESERVED        (1<<31) /* Internal use only */
+	SVGA_FIFO_3D_HWVERSION_REVISED,
 
-/*
- * FIFO reservation sentinel value
- */
+	SVGA_FIFO_3D_CAPS = 32,
+	SVGA_FIFO_3D_CAPS_LAST = 32 + 255,
 
-#define SVGA_FIFO_RESERVED_UNKNOWN      0xffffffff
+	SVGA_FIFO_GUEST_3D_HWVERSION,
+	SVGA_FIFO_FENCE_GOAL,
+	SVGA_FIFO_BUSY,
 
+	SVGA_FIFO_NUM_REGS
+};
 
-/*
- * ScreenDMA Register Values
- */
+#define SVGA_FIFO_3D_CAPS_SIZE (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1)
 
-#define SVGA_SCREENDMA_REG_UNDEFINED    0
-#define SVGA_SCREENDMA_REG_NOT_PRESENT  1
-#define SVGA_SCREENDMA_REG_PRESENT      2
-#define SVGA_SCREENDMA_REG_MAX          3
+#define SVGA3D_FIFO_CAPS_RECORD_DEVCAPS 0x100
+typedef uint32 SVGA3dFifoCapsRecordType;
 
-/*
- * Video overlay support
- */
+typedef uint32 SVGA3dFifoCapPair[2];
 
-#define SVGA_NUM_OVERLAY_UNITS 32
+#pragma pack(push, 1)
+typedef struct SVGA3dFifoCapsRecordHeader {
+	uint32 length;
+	SVGA3dFifoCapsRecordType type;
 
+} SVGA3dFifoCapsRecordHeader;
+#pragma pack(pop)
 
-/*
- * Video capabilities that the guest is currently using
- */
+#define SVGA_FIFO_EXTENDED_MANDATORY_REGS (SVGA_FIFO_3D_CAPS_LAST + 1)
 
-#define SVGA_VIDEO_FLAG_COLORKEY        0x0001
+#define SVGA_FIFO_CAP_NONE 0
+#define SVGA_FIFO_CAP_FENCE (1 << 0)
+#define SVGA_FIFO_CAP_ACCELFRONT (1 << 1)
+#define SVGA_FIFO_CAP_PITCHLOCK (1 << 2)
+#define SVGA_FIFO_CAP_VIDEO (1 << 3)
+#define SVGA_FIFO_CAP_CURSOR_BYPASS_3 (1 << 4)
+#define SVGA_FIFO_CAP_ESCAPE (1 << 5)
+#define SVGA_FIFO_CAP_RESERVE (1 << 6)
+#define SVGA_FIFO_CAP_SCREEN_OBJECT (1 << 7)
+#define SVGA_FIFO_CAP_GMR2 (1 << 8)
+#define SVGA_FIFO_CAP_3D_HWVERSION_REVISED SVGA_FIFO_CAP_GMR2
+#define SVGA_FIFO_CAP_SCREEN_OBJECT_2 (1 << 9)
+#define SVGA_FIFO_CAP_DEAD (1 << 10)
 
+#define SVGA_FIFO_FLAG_NONE 0
+#define SVGA_FIFO_FLAG_ACCELFRONT (1 << 0)
+#define SVGA_FIFO_FLAG_RESERVED (1 << 31)
 
-/*
- * Offsets for the video overlay registers
- */
+#define SVGA_FIFO_RESERVED_UNKNOWN 0xffffffff
 
-enum {
-   SVGA_VIDEO_ENABLED = 0,
-   SVGA_VIDEO_FLAGS,
-   SVGA_VIDEO_DATA_OFFSET,
-   SVGA_VIDEO_FORMAT,
-   SVGA_VIDEO_COLORKEY,
-   SVGA_VIDEO_SIZE,          /* Deprecated */
-   SVGA_VIDEO_WIDTH,
-   SVGA_VIDEO_HEIGHT,
-   SVGA_VIDEO_SRC_X,
-   SVGA_VIDEO_SRC_Y,
-   SVGA_VIDEO_SRC_WIDTH,
-   SVGA_VIDEO_SRC_HEIGHT,
-   SVGA_VIDEO_DST_X,         /* Signed int32 */
-   SVGA_VIDEO_DST_Y,         /* Signed int32 */
-   SVGA_VIDEO_DST_WIDTH,
-   SVGA_VIDEO_DST_HEIGHT,
-   SVGA_VIDEO_PITCH_1,
-   SVGA_VIDEO_PITCH_2,
-   SVGA_VIDEO_PITCH_3,
-   SVGA_VIDEO_DATA_GMRID,    /* Optional, defaults to SVGA_GMR_FRAMEBUFFER */
-   SVGA_VIDEO_DST_SCREEN_ID, /* Optional, defaults to virtual coords */
-                             /* (SVGA_ID_INVALID) */
-   SVGA_VIDEO_NUM_REGS
-};
+#define SVGA_SCREENDMA_REG_UNDEFINED 0
+#define SVGA_SCREENDMA_REG_NOT_PRESENT 1
+#define SVGA_SCREENDMA_REG_PRESENT 2
+#define SVGA_SCREENDMA_REG_MAX 3
 
+#define SVGA_NUM_OVERLAY_UNITS 32
 
-/*
- * SVGA Overlay Units
- *
- *      width and height relate to the entire source video frame.
- *      srcX, srcY, srcWidth and srcHeight represent subset of the source
- *      video frame to be displayed.
- */
+#define SVGA_VIDEO_FLAG_COLORKEY 0x0001
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGAOverlayUnit {
-   uint32 enabled;
-   uint32 flags;
-   uint32 dataOffset;
-   uint32 format;
-   uint32 colorKey;
-   uint32 size;
-   uint32 width;
-   uint32 height;
-   uint32 srcX;
-   uint32 srcY;
-   uint32 srcWidth;
-   uint32 srcHeight;
-   int32  dstX;
-   int32  dstY;
-   uint32 dstWidth;
-   uint32 dstHeight;
-   uint32 pitches[3];
-   uint32 dataGMRId;
-   uint32 dstScreenId;
-}
-#include "vmware_pack_end.h"
-SVGAOverlayUnit;
+enum {
+	SVGA_VIDEO_ENABLED = 0,
+	SVGA_VIDEO_FLAGS,
+	SVGA_VIDEO_DATA_OFFSET,
+	SVGA_VIDEO_FORMAT,
+	SVGA_VIDEO_COLORKEY,
+	SVGA_VIDEO_SIZE,
+	SVGA_VIDEO_WIDTH,
+	SVGA_VIDEO_HEIGHT,
+	SVGA_VIDEO_SRC_X,
+	SVGA_VIDEO_SRC_Y,
+	SVGA_VIDEO_SRC_WIDTH,
+	SVGA_VIDEO_SRC_HEIGHT,
+	SVGA_VIDEO_DST_X,
+	SVGA_VIDEO_DST_Y,
+	SVGA_VIDEO_DST_WIDTH,
+	SVGA_VIDEO_DST_HEIGHT,
+	SVGA_VIDEO_PITCH_1,
+	SVGA_VIDEO_PITCH_2,
+	SVGA_VIDEO_PITCH_3,
+	SVGA_VIDEO_DATA_GMRID,
+	SVGA_VIDEO_DST_SCREEN_ID,
+	SVGA_VIDEO_NUM_REGS
+};
 
+#pragma pack(push, 1)
+typedef struct SVGAOverlayUnit {
+	uint32 enabled;
+	uint32 flags;
+	uint32 dataOffset;
+	uint32 format;
+	uint32 colorKey;
+	uint32 size;
+	uint32 width;
+	uint32 height;
+	uint32 srcX;
+	uint32 srcY;
+	uint32 srcWidth;
+	uint32 srcHeight;
+	int32 dstX;
+	int32 dstY;
+	uint32 dstWidth;
+	uint32 dstHeight;
+	uint32 pitches[3];
+	uint32 dataGMRId;
+	uint32 dstScreenId;
+} SVGAOverlayUnit;
+#pragma pack(pop)
 
-/*
- * Guest display topology
- *
- * XXX: This structure is not part of the SVGA device's interface, and
- * doesn't really belong here.
- */
 #define SVGA_INVALID_DISPLAY_ID ((uint32)-1)
 
 typedef struct SVGADisplayTopology {
-   uint16 displayId;
-   uint16 isPrimary;
-   uint32 width;
-   uint32 height;
-   uint32 positionX;
-   uint32 positionY;
+	uint16 displayId;
+	uint16 isPrimary;
+	uint32 width;
+	uint32 height;
+	uint32 positionX;
+	uint32 positionY;
 } SVGADisplayTopology;
 
-
-/*
- * SVGAScreenObject --
- *
- *    This is a new way to represent a guest's multi-monitor screen or
- *    Unity window. Screen objects are only supported if the
- *    SVGA_FIFO_CAP_SCREEN_OBJECT capability bit is set.
- *
- *    If Screen Objects are supported, they can be used to fully
- *    replace the functionality provided by the framebuffer registers
- *    (SVGA_REG_WIDTH, HEIGHT, etc.) and by SVGA_CAP_DISPLAY_TOPOLOGY.
- *
- *    The screen object is a struct with guaranteed binary
- *    compatibility. New flags can be added, and the struct may grow,
- *    but existing fields must retain their meaning.
- *
- *    Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2 are required fields of
- *    a SVGAGuestPtr that is used to back the screen contents.  This
- *    memory must come from the GFB.  The guest is not allowed to
- *    access the memory and doing so will have undefined results.  The
- *    backing store is required to be page aligned and the size is
- *    padded to the next page boundry.  The number of pages is:
- *       (bytesPerLine * size.width * 4 + PAGE_SIZE - 1) / PAGE_SIZE
- *
- *    The pitch in the backingStore is required to be at least large
- *    enough to hold a 32bbp scanline.  It is recommended that the
- *    driver pad bytesPerLine for a potential performance win.
- *
- *    The cloneCount field is treated as a hint from the guest that
- *    the user wants this display to be cloned, countCount times.  A
- *    value of zero means no cloning should happen.
- */
-
-#define SVGA_SCREEN_MUST_BE_SET     (1 << 0)
-#define SVGA_SCREEN_HAS_ROOT SVGA_SCREEN_MUST_BE_SET /* Deprecated */
-#define SVGA_SCREEN_IS_PRIMARY      (1 << 1)
+#define SVGA_SCREEN_MUST_BE_SET (1 << 0)
+#define SVGA_SCREEN_HAS_ROOT SVGA_SCREEN_MUST_BE_SET
+#define SVGA_SCREEN_IS_PRIMARY (1 << 1)
 #define SVGA_SCREEN_FULLSCREEN_HINT (1 << 2)
 
-/*
- * Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2.  When the screen is
- * deactivated the base layer is defined to lose all contents and
- * become black.  When a screen is deactivated the backing store is
- * optional.  When set backingPtr and bytesPerLine will be ignored.
- */
-#define SVGA_SCREEN_DEACTIVATE  (1 << 3)
+#define SVGA_SCREEN_DEACTIVATE (1 << 3)
 
-/*
- * Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2.  When this flag is set
- * the screen contents will be outputted as all black to the user
- * though the base layer contents is preserved.  The screen base layer
- * can still be read and written to like normal though the no visible
- * effect will be seen by the user.  When the flag is changed the
- * screen will be blanked or redrawn to the current contents as needed
- * without any extra commands from the driver.  This flag only has an
- * effect when the screen is not deactivated.
- */
 #define SVGA_SCREEN_BLANKING (1 << 4)
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 structSize;   /* sizeof(SVGAScreenObject) */
-   uint32 id;
-   uint32 flags;
-   struct {
-      uint32 width;
-      uint32 height;
-   } size;
-   struct {
-      int32 x;
-      int32 y;
-   } root;
-
-   /*
-    * Added and required by SVGA_FIFO_CAP_SCREEN_OBJECT_2, optional
-    * with SVGA_FIFO_CAP_SCREEN_OBJECT.
-    */
-   SVGAGuestImage backingStore;
-
-   /*
-    * The cloneCount field is treated as a hint from the guest that
-    * the user wants this display to be cloned, cloneCount times.
-    *
-    * A value of zero means no cloning should happen.
-    */
-   uint32 cloneCount;
-}
-#include "vmware_pack_end.h"
-SVGAScreenObject;
-
-
-/*
- *  Commands in the command FIFO:
- *
- *  Command IDs defined below are used for the traditional 2D FIFO
- *  communication (not all commands are available for all versions of the
- *  SVGA FIFO protocol).
- *
- *  Note the holes in the command ID numbers: These commands have been
- *  deprecated, and the old IDs must not be reused.
- *
- *  Command IDs from 1000 to 2999 are reserved for use by the SVGA3D
- *  protocol.
- *
- *  Each command's parameters are described by the comments and
- *  structs below.
- */
+#pragma pack(push, 1)
+typedef struct {
+	uint32 structSize;
+	uint32 id;
+	uint32 flags;
+	struct {
+		uint32 width;
+		uint32 height;
+	} size;
+	struct {
+		int32 x;
+		int32 y;
+	} root;
+
+	SVGAGuestImage backingStore;
+
+	uint32 cloneCount;
+} SVGAScreenObject;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA_CMD_INVALID_CMD           = 0,
-   SVGA_CMD_UPDATE                = 1,
-   SVGA_CMD_RECT_COPY             = 3,
-   SVGA_CMD_RECT_ROP_COPY         = 14,
-   SVGA_CMD_DEFINE_CURSOR         = 19,
-   SVGA_CMD_DEFINE_ALPHA_CURSOR   = 22,
-   SVGA_CMD_UPDATE_VERBOSE        = 25,
-   SVGA_CMD_FRONT_ROP_FILL        = 29,
-   SVGA_CMD_FENCE                 = 30,
-   SVGA_CMD_ESCAPE                = 33,
-   SVGA_CMD_DEFINE_SCREEN         = 34,
-   SVGA_CMD_DESTROY_SCREEN        = 35,
-   SVGA_CMD_DEFINE_GMRFB          = 36,
-   SVGA_CMD_BLIT_GMRFB_TO_SCREEN  = 37,
-   SVGA_CMD_BLIT_SCREEN_TO_GMRFB  = 38,
-   SVGA_CMD_ANNOTATION_FILL       = 39,
-   SVGA_CMD_ANNOTATION_COPY       = 40,
-   SVGA_CMD_DEFINE_GMR2           = 41,
-   SVGA_CMD_REMAP_GMR2            = 42,
-   SVGA_CMD_DEAD                  = 43,
-   SVGA_CMD_DEAD_2                = 44,
-   SVGA_CMD_NOP                   = 45,
-   SVGA_CMD_NOP_ERROR             = 46,
-   SVGA_CMD_MAX
+	SVGA_CMD_INVALID_CMD = 0,
+	SVGA_CMD_UPDATE = 1,
+	SVGA_CMD_RECT_COPY = 3,
+	SVGA_CMD_RECT_ROP_COPY = 14,
+	SVGA_CMD_DEFINE_CURSOR = 19,
+	SVGA_CMD_DEFINE_ALPHA_CURSOR = 22,
+	SVGA_CMD_UPDATE_VERBOSE = 25,
+	SVGA_CMD_FRONT_ROP_FILL = 29,
+	SVGA_CMD_FENCE = 30,
+	SVGA_CMD_ESCAPE = 33,
+	SVGA_CMD_DEFINE_SCREEN = 34,
+	SVGA_CMD_DESTROY_SCREEN = 35,
+	SVGA_CMD_DEFINE_GMRFB = 36,
+	SVGA_CMD_BLIT_GMRFB_TO_SCREEN = 37,
+	SVGA_CMD_BLIT_SCREEN_TO_GMRFB = 38,
+	SVGA_CMD_ANNOTATION_FILL = 39,
+	SVGA_CMD_ANNOTATION_COPY = 40,
+	SVGA_CMD_DEFINE_GMR2 = 41,
+	SVGA_CMD_REMAP_GMR2 = 42,
+	SVGA_CMD_DEAD = 43,
+	SVGA_CMD_DEAD_2 = 44,
+	SVGA_CMD_NOP = 45,
+	SVGA_CMD_NOP_ERROR = 46,
+	SVGA_CMD_MAX
 } SVGAFifoCmdId;
 
-#define SVGA_CMD_MAX_DATASIZE       (256 * 1024)
-#define SVGA_CMD_MAX_ARGS           64
-
-
-/*
- * SVGA_CMD_UPDATE --
- *
- *    This is a DMA transfer which copies from the Guest Framebuffer
- *    (GFB) at BAR1 + SVGA_REG_FB_OFFSET to any screens which
- *    intersect with the provided virtual rectangle.
- *
- *    This command does not support using arbitrary guest memory as a
- *    data source- it only works with the pre-defined GFB memory.
- *    This command also does not support signed virtual coordinates.
- *    If you have defined screens (using SVGA_CMD_DEFINE_SCREEN) with
- *    negative root x/y coordinates, the negative portion of those
- *    screens will not be reachable by this command.
- *
- *    This command is not necessary when using framebuffer
- *    traces. Traces are automatically enabled if the SVGA FIFO is
- *    disabled, and you may explicitly enable/disable traces using
- *    SVGA_REG_TRACES. With traces enabled, any write to the GFB will
- *    automatically act as if a subsequent SVGA_CMD_UPDATE was issued.
- *
- *    Traces and SVGA_CMD_UPDATE are the only supported ways to render
- *    pseudocolor screen updates. The newer Screen Object commands
- *    only support true color formats.
- *
- * Availability:
- *    Always available.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 x;
-   uint32 y;
-   uint32 width;
-   uint32 height;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdUpdate;
-
-
-/*
- * SVGA_CMD_RECT_COPY --
- *
- *    Perform a rectangular DMA transfer from one area of the GFB to
- *    another, and copy the result to any screens which intersect it.
- *
- * Availability:
- *    SVGA_CAP_RECT_COPY
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 srcX;
-   uint32 srcY;
-   uint32 destX;
-   uint32 destY;
-   uint32 width;
-   uint32 height;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdRectCopy;
-
-
-/*
- * SVGA_CMD_RECT_ROP_COPY --
- *
- *    Perform a rectangular DMA transfer from one area of the GFB to
- *    another, and copy the result to any screens which intersect it.
- *    The value of ROP may only be SVGA_ROP_COPY, and this command is
- *    only supported for backwards compatibility reasons.
- *
- * Availability:
- *    SVGA_CAP_RECT_COPY
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 srcX;
-   uint32 srcY;
-   uint32 destX;
-   uint32 destY;
-   uint32 width;
-   uint32 height;
-   uint32 rop;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdRectRopCopy;
-
-
-/*
- * SVGA_CMD_DEFINE_CURSOR --
- *
- *    Provide a new cursor image, as an AND/XOR mask.
- *
- *    The recommended way to position the cursor overlay is by using
- *    the SVGA_FIFO_CURSOR_* registers, supported by the
- *    SVGA_FIFO_CAP_CURSOR_BYPASS_3 capability.
- *
- * Availability:
- *    SVGA_CAP_CURSOR
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 id;             /* Reserved, must be zero. */
-   uint32 hotspotX;
-   uint32 hotspotY;
-   uint32 width;
-   uint32 height;
-   uint32 andMaskDepth;   /* Value must be 1 or equal to BITS_PER_PIXEL */
-   uint32 xorMaskDepth;   /* Value must be 1 or equal to BITS_PER_PIXEL */
-   /*
-    * Followed by scanline data for AND mask, then XOR mask.
-    * Each scanline is padded to a 32-bit boundary.
-   */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDefineCursor;
-
-
-/*
- * SVGA_CMD_DEFINE_ALPHA_CURSOR --
- *
- *    Provide a new cursor image, in 32-bit BGRA format.
- *
- *    The recommended way to position the cursor overlay is by using
- *    the SVGA_FIFO_CURSOR_* registers, supported by the
- *    SVGA_FIFO_CAP_CURSOR_BYPASS_3 capability.
- *
- * Availability:
- *    SVGA_CAP_ALPHA_CURSOR
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 id;             /* Reserved, must be zero. */
-   uint32 hotspotX;
-   uint32 hotspotY;
-   uint32 width;
-   uint32 height;
-   /* Followed by scanline data */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDefineAlphaCursor;
-
-
-/*
- *    Provide a new large cursor image, as an AND/XOR mask.
- *
- *    Should only be used for CursorMob functionality
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 hotspotX;
-   uint32 hotspotY;
-   uint32 width;
-   uint32 height;
-   uint32 andMaskDepth;
-   uint32 xorMaskDepth;
-   /*
-    * Followed by scanline data for AND mask, then XOR mask.
-    * Each scanline is padded to a 32-bit boundary.
-   */
-}
-#include "vmware_pack_end.h"
-SVGAGBColorCursorHeader;
-
-
-/*
- *    Provide a new large cursor image, in 32-bit BGRA format.
- *
- *    Should only be used for CursorMob functionality
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 hotspotX;
-   uint32 hotspotY;
-   uint32 width;
-   uint32 height;
-   /* Followed by scanline data */
-}
-#include "vmware_pack_end.h"
-SVGAGBAlphaCursorHeader;
-
- /*
-  * Define the SVGA guest backed cursor types
-  */
+#define SVGA_CMD_MAX_DATASIZE (256 * 1024)
+#define SVGA_CMD_MAX_ARGS 64
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 x;
+	uint32 y;
+	uint32 width;
+	uint32 height;
+} SVGAFifoCmdUpdate;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 srcX;
+	uint32 srcY;
+	uint32 destX;
+	uint32 destY;
+	uint32 width;
+	uint32 height;
+} SVGAFifoCmdRectCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 srcX;
+	uint32 srcY;
+	uint32 destX;
+	uint32 destY;
+	uint32 width;
+	uint32 height;
+	uint32 rop;
+} SVGAFifoCmdRectRopCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 id;
+	uint32 hotspotX;
+	uint32 hotspotY;
+	uint32 width;
+	uint32 height;
+	uint32 andMaskDepth;
+	uint32 xorMaskDepth;
+
+} SVGAFifoCmdDefineCursor;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 id;
+	uint32 hotspotX;
+	uint32 hotspotY;
+	uint32 width;
+	uint32 height;
+
+} SVGAFifoCmdDefineAlphaCursor;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 hotspotX;
+	uint32 hotspotY;
+	uint32 width;
+	uint32 height;
+	uint32 andMaskDepth;
+	uint32 xorMaskDepth;
+
+} SVGAGBColorCursorHeader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 hotspotX;
+	uint32 hotspotY;
+	uint32 width;
+	uint32 height;
+
+} SVGAGBAlphaCursorHeader;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA_COLOR_CURSOR       = 0,
-   SVGA_ALPHA_CURSOR       = 1,
+	SVGA_COLOR_CURSOR = 0,
+	SVGA_ALPHA_CURSOR = 1,
 } SVGAGBCursorType;
 
-/*
- *    Provide a new large cursor image.
- *
- *    Should only be used for CursorMob functionality
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAGBCursorType type;
-   union {
-      SVGAGBColorCursorHeader colorHeader;
-      SVGAGBAlphaCursorHeader alphaHeader;
-   } header;
-   uint32 sizeInBytes;
-   /*
-    * Followed by the cursor data
-    */
-}
-#include "vmware_pack_end.h"
-SVGAGBCursorHeader;
-
-
-/*
- * SVGA_CMD_UPDATE_VERBOSE --
- *
- *    Just like SVGA_CMD_UPDATE, but also provide a per-rectangle
- *    'reason' value, an opaque cookie which is used by internal
- *    debugging tools. Third party drivers should not use this
- *    command.
- *
- * Availability:
- *    SVGA_CAP_EXTENDED_FIFO
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 x;
-   uint32 y;
-   uint32 width;
-   uint32 height;
-   uint32 reason;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdUpdateVerbose;
-
-
-/*
- * SVGA_CMD_FRONT_ROP_FILL --
- *
- *    This is a hint which tells the SVGA device that the driver has
- *    just filled a rectangular region of the GFB with a solid
- *    color. Instead of reading these pixels from the GFB, the device
- *    can assume that they all equal 'color'. This is primarily used
- *    for remote desktop protocols.
- *
- * Availability:
- *    SVGA_FIFO_CAP_ACCELFRONT
- */
-
-#define  SVGA_ROP_COPY                    0x03
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 color;     /* In the same format as the GFB */
-   uint32 x;
-   uint32 y;
-   uint32 width;
-   uint32 height;
-   uint32 rop;       /* Must be SVGA_ROP_COPY */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdFrontRopFill;
-
-
-/*
- * SVGA_CMD_FENCE --
- *
- *    Insert a synchronization fence.  When the SVGA device reaches
- *    this command, it will copy the 'fence' value into the
- *    SVGA_FIFO_FENCE register. It will also compare the fence against
- *    SVGA_FIFO_FENCE_GOAL. If the fence matches the goal and the
- *    SVGA_IRQFLAG_FENCE_GOAL interrupt is enabled, the device will
- *    raise this interrupt.
- *
- * Availability:
- *    SVGA_FIFO_FENCE for this command,
- *    SVGA_CAP_IRQMASK for SVGA_FIFO_FENCE_GOAL.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 fence;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdFence;
-
-
-/*
- * SVGA_CMD_ESCAPE --
- *
- *    Send an extended or vendor-specific variable length command.
- *    This is used for video overlay, third party plugins, and
- *    internal debugging tools. See svga_escape.h
- *
- * Availability:
- *    SVGA_FIFO_CAP_ESCAPE
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 nsid;
-   uint32 size;
-   /* followed by 'size' bytes of data */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdEscape;
-
-
-/*
- * SVGA_CMD_DEFINE_SCREEN --
- *
- *    Define or redefine an SVGAScreenObject. See the description of
- *    SVGAScreenObject above.  The video driver is responsible for
- *    generating new screen IDs. They should be small positive
- *    integers. The virtual device will have an implementation
- *    specific upper limit on the number of screen IDs
- *    supported. Drivers are responsible for recycling IDs. The first
- *    valid ID is zero.
- *
- *    - Interaction with other registers:
- *
- *    For backwards compatibility, when the GFB mode registers (WIDTH,
- *    HEIGHT, PITCHLOCK, BITS_PER_PIXEL) are modified, the SVGA device
- *    deletes all screens other than screen #0, and redefines screen
- *    #0 according to the specified mode. Drivers that use
- *    SVGA_CMD_DEFINE_SCREEN should destroy or redefine screen #0.
- *
- *    If you use screen objects, do not use the legacy multi-mon
- *    registers (SVGA_REG_NUM_GUEST_DISPLAYS, SVGA_REG_DISPLAY_*).
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAScreenObject screen;   /* Variable-length according to version */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDefineScreen;
-
-
-/*
- * SVGA_CMD_DESTROY_SCREEN --
- *
- *    Destroy an SVGAScreenObject. Its ID is immediately available for
- *    re-use.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 screenId;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDestroyScreen;
-
-
-/*
- * SVGA_CMD_DEFINE_GMRFB --
- *
- *    This command sets a piece of SVGA device state called the
- *    Guest Memory Region Framebuffer, or GMRFB. The GMRFB is a
- *    piece of light-weight state which identifies the location and
- *    format of an image in guest memory or in BAR1. The GMRFB has
- *    an arbitrary size, and it doesn't need to match the geometry
- *    of the GFB or any screen object.
- *
- *    The GMRFB can be redefined as often as you like. You could
- *    always use the same GMRFB, you could redefine it before
- *    rendering from a different guest screen, or you could even
- *    redefine it before every blit.
- *
- *    There are multiple ways to use this command. The simplest way is
- *    to use it to move the framebuffer either to elsewhere in the GFB
- *    (BAR1) memory region, or to a user-defined GMR. This lets a
- *    driver use a framebuffer allocated entirely out of normal system
- *    memory, which we encourage.
- *
- *    Another way to use this command is to set up a ring buffer of
- *    updates in GFB memory. If a driver wants to ensure that no
- *    frames are skipped by the SVGA device, it is important that the
- *    driver not modify the source data for a blit until the device is
- *    done processing the command. One efficient way to accomplish
- *    this is to use a ring of small DMA buffers. Each buffer is used
- *    for one blit, then we move on to the next buffer in the
- *    ring. The FENCE mechanism is used to protect each buffer from
- *    re-use until the device is finished with that buffer's
- *    corresponding blit.
- *
- *    This command does not affect the meaning of SVGA_CMD_UPDATE.
- *    UPDATEs always occur from the legacy GFB memory area. This
- *    command has no support for pseudocolor GMRFBs. Currently only
- *    true-color 15, 16, and 24-bit depths are supported. Future
- *    devices may expose capabilities for additional framebuffer
- *    formats.
- *
- *    The default GMRFB value is undefined. Drivers must always send
- *    this command at least once before performing any blit from the
- *    GMRFB.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAGuestPtr        ptr;
-   uint32              bytesPerLine;
-   SVGAGMRImageFormat  format;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDefineGMRFB;
-
-
-/*
- * SVGA_CMD_BLIT_GMRFB_TO_SCREEN --
- *
- *    This is a guest-to-host blit. It performs a DMA operation to
- *    copy a rectangular region of pixels from the current GMRFB to
- *    a ScreenObject.
- *
- *    The destination coordinate may be specified relative to a
- *    screen's origin.  The provided screen ID must be valid.
- *
- *    The SVGA device is guaranteed to finish reading from the GMRFB
- *    by the time any subsequent FENCE commands are reached.
- *
- *    This command consumes an annotation. See the
- *    SVGA_CMD_ANNOTATION_* commands for details.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGASignedPoint  srcOrigin;
-   SVGASignedRect   destRect;
-   uint32           destScreenId;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdBlitGMRFBToScreen;
-
-
-/*
- * SVGA_CMD_BLIT_SCREEN_TO_GMRFB --
- *
- *    This is a host-to-guest blit. It performs a DMA operation to
- *    copy a rectangular region of pixels from a single ScreenObject
- *    back to the current GMRFB.
- *
- *    The source coordinate is specified relative to a screen's
- *    origin.  The provided screen ID must be valid. If any parameters
- *    are invalid, the resulting pixel values are undefined.
- *
- *    The SVGA device is guaranteed to finish writing to the GMRFB by
- *    the time any subsequent FENCE commands are reached.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGASignedPoint  destOrigin;
-   SVGASignedRect   srcRect;
-   uint32           srcScreenId;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdBlitScreenToGMRFB;
-
-
-/*
- * SVGA_CMD_ANNOTATION_FILL --
- *
- *    The annotation commands have been deprecated, should not be used
- *    by new drivers.  They used to provide performance hints to the SVGA
- *    device about the content of screen updates, but newer SVGA devices
- *    ignore these.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGAColorBGRX  color;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdAnnotationFill;
-
-
-/*
- * SVGA_CMD_ANNOTATION_COPY --
- *
- *    The annotation commands have been deprecated, should not be used
- *    by new drivers.  They used to provide performance hints to the SVGA
- *    device about the content of screen updates, but newer SVGA devices
- *    ignore these.
- *
- * Availability:
- *    SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   SVGASignedPoint  srcOrigin;
-   uint32           srcScreenId;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdAnnotationCopy;
-
-
-/*
- * SVGA_CMD_DEFINE_GMR2 --
- *
- *    Define guest memory region v2.  See the description of GMRs above.
- *
- * Availability:
- *    SVGA_CAP_GMR2
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 gmrId;
-   uint32 numPages;
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdDefineGMR2;
-
-
-/*
- * SVGA_CMD_REMAP_GMR2 --
- *
- *    Remap guest memory region v2.  See the description of GMRs above.
- *
- *    This command allows guest to modify a portion of an existing GMR by
- *    invalidating it or reassigning it to different guest physical pages.
- *    The pages are identified by physical page number (PPN).  The pages
- *    are assumed to be pinned and valid for DMA operations.
- *
- *    Description of command flags:
- *
- *    SVGA_REMAP_GMR2_VIA_GMR: If enabled, references a PPN list in a GMR.
- *       The PPN list must not overlap with the remap region (this can be
- *       handled trivially by referencing a separate GMR).  If flag is
- *       disabled, PPN list is appended to SVGARemapGMR command.
- *
- *    SVGA_REMAP_GMR2_PPN64: If set, PPN list is in PPN64 format, otherwise
- *       it is in PPN32 format.
- *
- *    SVGA_REMAP_GMR2_SINGLE_PPN: If set, PPN list contains a single entry.
- *       A single PPN can be used to invalidate a portion of a GMR or
- *       map it to to a single guest scratch page.
- *
- * Availability:
- *    SVGA_CAP_GMR2
- */
+#pragma pack(push, 1)
+typedef struct {
+	SVGAGBCursorType type;
+	union {
+		SVGAGBColorCursorHeader colorHeader;
+		SVGAGBAlphaCursorHeader alphaHeader;
+	} header;
+	uint32 sizeInBytes;
+
+} SVGAGBCursorHeader;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 x;
+	uint32 y;
+	uint32 width;
+	uint32 height;
+	uint32 reason;
+} SVGAFifoCmdUpdateVerbose;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 color;
+	uint32 x;
+	uint32 y;
+	uint32 width;
+	uint32 height;
+	uint32 rop;
+} SVGAFifoCmdFrontRopFill;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 fence;
+} SVGAFifoCmdFence;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 nsid;
+	uint32 size;
+
+} SVGAFifoCmdEscape;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAScreenObject screen;
+} SVGAFifoCmdDefineScreen;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 screenId;
+} SVGAFifoCmdDestroyScreen;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAGuestPtr ptr;
+	uint32 bytesPerLine;
+	SVGAGMRImageFormat format;
+} SVGAFifoCmdDefineGMRFB;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGASignedPoint srcOrigin;
+	SVGASignedRect destRect;
+	uint32 destScreenId;
+} SVGAFifoCmdBlitGMRFBToScreen;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGASignedPoint destOrigin;
+	SVGASignedRect srcRect;
+	uint32 srcScreenId;
+} SVGAFifoCmdBlitScreenToGMRFB;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGAColorBGRX color;
+} SVGAFifoCmdAnnotationFill;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	SVGASignedPoint srcOrigin;
+	uint32 srcScreenId;
+} SVGAFifoCmdAnnotationCopy;
+#pragma pack(pop)
+
+#pragma pack(push, 1)
+typedef struct {
+	uint32 gmrId;
+	uint32 numPages;
+} SVGAFifoCmdDefineGMR2;
+#pragma pack(pop)
 
 typedef enum {
-   SVGA_REMAP_GMR2_PPN32         = 0,
-   SVGA_REMAP_GMR2_VIA_GMR       = (1 << 0),
-   SVGA_REMAP_GMR2_PPN64         = (1 << 1),
-   SVGA_REMAP_GMR2_SINGLE_PPN    = (1 << 2),
+	SVGA_REMAP_GMR2_PPN32 = 0,
+	SVGA_REMAP_GMR2_VIA_GMR = (1 << 0),
+	SVGA_REMAP_GMR2_PPN64 = (1 << 1),
+	SVGA_REMAP_GMR2_SINGLE_PPN = (1 << 2),
 } SVGARemapGMR2Flags;
 
-typedef
-#include "vmware_pack_begin.h"
-struct {
-   uint32 gmrId;
-   SVGARemapGMR2Flags flags;
-   uint32 offsetPages; /* offset in pages to begin remap */
-   uint32 numPages; /* number of pages to remap */
-   /*
-    * Followed by additional data depending on SVGARemapGMR2Flags.
-    *
-    * If flag SVGA_REMAP_GMR2_VIA_GMR is set, single SVGAGuestPtr follows.
-    * Otherwise an array of page descriptors in PPN32 or PPN64 format
-    * (according to flag SVGA_REMAP_GMR2_PPN64) follows.  If flag
-    * SVGA_REMAP_GMR2_SINGLE_PPN is set, array contains a single entry.
-    */
-}
-#include "vmware_pack_end.h"
-SVGAFifoCmdRemapGMR2;
-
-
-/*
- * Size of SVGA device memory such as frame buffer and FIFO.
- */
-#define SVGA_VRAM_MIN_SIZE             (4 * 640 * 480) /* bytes */
-#define SVGA_VRAM_MIN_SIZE_3D       (16 * 1024 * 1024)
-#define SVGA_VRAM_MAX_SIZE         (128 * 1024 * 1024)
-#define SVGA_MEMORY_SIZE_MAX      (1024 * 1024 * 1024)
-#define SVGA_FIFO_SIZE_MAX           (2 * 1024 * 1024)
-#define SVGA_GRAPHICS_MEMORY_KB_MIN     (32 * 1024)
+#pragma pack(push, 1)
+typedef struct {
+	uint32 gmrId;
+	SVGARemapGMR2Flags flags;
+	uint32 offsetPages;
+	uint32 numPages;
+
+} SVGAFifoCmdRemapGMR2;
+#pragma pack(pop)
+
+#define SVGA_VRAM_MIN_SIZE (4 * 640 * 480)
+#define SVGA_VRAM_MIN_SIZE_3D (16 * 1024 * 1024)
+#define SVGA_VRAM_MAX_SIZE (128 * 1024 * 1024)
+#define SVGA_MEMORY_SIZE_MAX (1024 * 1024 * 1024)
+#define SVGA_FIFO_SIZE_MAX (2 * 1024 * 1024)
+#define SVGA_GRAPHICS_MEMORY_KB_MIN (32 * 1024)
 #define SVGA_GRAPHICS_MEMORY_KB_MAX_2GB (2 * 1024 * 1024)
 #define SVGA_GRAPHICS_MEMORY_KB_MAX_3GB (3 * 1024 * 1024)
 #define SVGA_GRAPHICS_MEMORY_KB_MAX_4GB (4 * 1024 * 1024)
 #define SVGA_GRAPHICS_MEMORY_KB_MAX_8GB (8 * 1024 * 1024)
 #define SVGA_GRAPHICS_MEMORY_KB_DEFAULT (256 * 1024)
 
-#define SVGA_VRAM_SIZE_W2K          (64 * 1024 * 1024) /* 64 MB */
+#define SVGA_VRAM_SIZE_W2K (64 * 1024 * 1024)
 
 #if defined(VMX86_SERVER)
-#define SVGA_VRAM_SIZE               (4 * 1024 * 1024)
-#define SVGA_VRAM_SIZE_3D           (64 * 1024 * 1024)
-#define SVGA_FIFO_SIZE                    (256 * 1024)
-#define SVGA_FIFO_SIZE_3D                 (516 * 1024)
-#define SVGA_MEMORY_SIZE_DEFAULT   (160 * 1024 * 1024)
-#define SVGA_AUTODETECT_DEFAULT                  FALSE
+#define SVGA_VRAM_SIZE (4 * 1024 * 1024)
+#define SVGA_VRAM_SIZE_3D (64 * 1024 * 1024)
+#define SVGA_FIFO_SIZE (256 * 1024)
+#define SVGA_FIFO_SIZE_3D (516 * 1024)
+#define SVGA_MEMORY_SIZE_DEFAULT (160 * 1024 * 1024)
+#define SVGA_AUTODETECT_DEFAULT FALSE
 #else
-#define SVGA_VRAM_SIZE              (16 * 1024 * 1024)
-#define SVGA_VRAM_SIZE_3D           SVGA_VRAM_MAX_SIZE
-#define SVGA_FIFO_SIZE               (2 * 1024 * 1024)
-#define SVGA_FIFO_SIZE_3D               SVGA_FIFO_SIZE
-#define SVGA_MEMORY_SIZE_DEFAULT   (768 * 1024 * 1024)
-#define SVGA_AUTODETECT_DEFAULT                   TRUE
+#define SVGA_VRAM_SIZE (16 * 1024 * 1024)
+#define SVGA_VRAM_SIZE_3D SVGA_VRAM_MAX_SIZE
+#define SVGA_FIFO_SIZE (2 * 1024 * 1024)
+#define SVGA_FIFO_SIZE_3D SVGA_FIFO_SIZE
+#define SVGA_MEMORY_SIZE_DEFAULT (768 * 1024 * 1024)
+#define SVGA_AUTODETECT_DEFAULT TRUE
 #endif
 
-#define SVGA_FIFO_SIZE_GBOBJECTS          (256 * 1024)
-#define SVGA_VRAM_SIZE_GBOBJECTS     (4 * 1024 * 1024)
-
-#define SVGA_PCI_REGS_PAGES                        (1)
+#define SVGA_FIFO_SIZE_GBOBJECTS (256 * 1024)
+#define SVGA_VRAM_SIZE_GBOBJECTS (4 * 1024 * 1024)
 
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
deleted file mode 100644
index beddccee40f6..000000000000
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
-/**********************************************************
- * Copyright 2015 VMware, Inc.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
-#ifndef _VM_BASIC_TYPES_H_
-#define _VM_BASIC_TYPES_H_
-#include <linux/kernel.h>
-
-typedef u32 uint32;
-typedef s32 int32;
-typedef u64 uint64;
-typedef u16 uint16;
-typedef s16 int16;
-typedef u8  uint8;
-typedef s8  int8;
-
-typedef uint64 PA;
-typedef uint32 PPN;
-typedef uint32 PPN32;
-typedef uint64 PPN64;
-
-typedef bool Bool;
-
-#define MAX_UINT64 U64_MAX
-#define MAX_UINT32 U32_MAX
-#define MAX_UINT16 U16_MAX
-
-#define CONST64U(x) x##ULL
-
-#endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h b/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h
index 3a195e8106b3..1f6e3bbc6605 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h
@@ -1,7 +1,34 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _VM_BASIC_TYPES_H_
-#define _VM_BASIC_TYPES_H_
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/**********************************************************
+ * Copyright 2015-2021 VMware, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy,
+ * modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ **********************************************************/
+#ifndef VM_BASIC_TYPES_H
+#define VM_BASIC_TYPES_H
+
 #include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/page.h>
 
 typedef u32 uint32;
 typedef s32 int32;
@@ -13,10 +40,107 @@ typedef s8  int8;
 
 typedef uint64 PA;
 typedef uint32 PPN;
+typedef uint32 PPN32;
 typedef uint64 PPN64;
 
 typedef bool Bool;
 
+#define MAX_UINT64 U64_MAX
 #define MAX_UINT32 U32_MAX
+#define MAX_UINT16 U16_MAX
+
+#define CONST64U(x) x##ULL
+
+#ifndef MBYTES_SHIFT
+#define MBYTES_SHIFT 20
+#endif
+#ifndef MBYTES_2_BYTES
+#define MBYTES_2_BYTES(_nbytes) ((uint64)(_nbytes) << MBYTES_SHIFT)
+#endif
+
+/*
+ * MKS Guest Stats types
+ */
+
+typedef struct MKSGuestStatCounter {
+	atomic64_t count;
+} MKSGuestStatCounter;
+
+typedef struct MKSGuestStatCounterTime {
+	MKSGuestStatCounter counter;
+	atomic64_t selfCycles;
+	atomic64_t totalCycles;
+} MKSGuestStatCounterTime;
+
+/*
+ * Flags for MKSGuestStatInfoEntry::flags below
+ */
+
+#define MKS_GUEST_STAT_FLAG_NONE    0
+#define MKS_GUEST_STAT_FLAG_TIME    (1U << 0)
+
+typedef __attribute__((aligned(32))) struct MKSGuestStatInfoEntry {
+	union {
+		const char *s;
+		uint64 u;
+	} name;
+	union {
+		const char *s;
+		uint64 u;
+	} description;
+	uint64 flags;
+	union {
+		MKSGuestStatCounter *counter;
+		MKSGuestStatCounterTime *counterTime;
+		uint64 u;
+	} stat;
+} MKSGuestStatInfoEntry;
+
+#define INVALID_PPN64       ((PPN64)0x000fffffffffffffULL)
+
+#define MKS_GUEST_STAT_INSTANCE_DESC_LENGTH 1024
+#define MKS_GUEST_STAT_INSTANCE_MAX_STATS   4096
+#define MKS_GUEST_STAT_INSTANCE_MAX_STAT_PPNS        \
+	(PFN_UP(MKS_GUEST_STAT_INSTANCE_MAX_STATS *  \
+		sizeof(MKSGuestStatCounterTime)))
+#define MKS_GUEST_STAT_INSTANCE_MAX_INFO_PPNS        \
+	(PFN_UP(MKS_GUEST_STAT_INSTANCE_MAX_STATS *  \
+		sizeof(MKSGuestStatInfoEntry)))
+#define MKS_GUEST_STAT_AVERAGE_NAME_LENGTH  40
+#define MKS_GUEST_STAT_INSTANCE_MAX_STRS_PPNS        \
+	(PFN_UP(MKS_GUEST_STAT_INSTANCE_MAX_STATS *  \
+		MKS_GUEST_STAT_AVERAGE_NAME_LENGTH))
+
+/*
+ * The MKSGuestStatInstanceDescriptor is used as main interface to
+ * communicate guest stats back to the host code.  The guest must
+ * allocate an instance of this structure at the start of a page and
+ * provide the physical address to the host.  From there the host code
+ * can walk this structure to find other (pinned) pages containing the
+ * stats data.
+ *
+ * Since the MKSGuestStatInfoEntry structures contain userlevel
+ * pointers, the InstanceDescriptor also contains pointers to the
+ * begining of these sections allowing the host side code to correctly
+ * interpret the pointers.
+ *
+ * Because the host side code never acknowledges anything back to the
+ * guest there is no strict requirement to maintain compatability
+ * across releases.  If the interface changes the host might not be
+ * able to log stats, but the guest will continue to run normally.
+ */
+
+typedef struct MKSGuestStatInstanceDescriptor {
+	uint64 reservedMBZ; /* must be zero for now. */
+	uint64 statStartVA; /* VA of the start of the stats section. */
+	uint64 strsStartVA; /* VA of the start of the strings section. */
+	uint64 statLength;  /* length of the stats section in bytes. */
+	uint64 infoLength;  /* length of the info entry section in bytes. */
+	uint64 strsLength;  /* length of the strings section in bytes. */
+	PPN64  statPPNs[MKS_GUEST_STAT_INSTANCE_MAX_STAT_PPNS]; /* stat counters */
+	PPN64  infoPPNs[MKS_GUEST_STAT_INSTANCE_MAX_INFO_PPNS]; /* stat info */
+	PPN64  strsPPNs[MKS_GUEST_STAT_INSTANCE_MAX_STRS_PPNS]; /* strings */
+	char   description[MKS_GUEST_STAT_INSTANCE_DESC_LENGTH];
+} MKSGuestStatInstanceDescriptor;
 
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
deleted file mode 100644
index 75308bd0d970..000000000000
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <linux/compiler.h>
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
deleted file mode 100644
index e93d6f28b68c..000000000000
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-__packed
diff --git a/drivers/gpu/drm/vmwgfx/ttm_memory.c b/drivers/gpu/drm/vmwgfx/ttm_memory.c
index aeb0a22a2c34..edd17c30d5a5 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_memory.c
+++ b/drivers/gpu/drm/vmwgfx/ttm_memory.c
@@ -435,8 +435,10 @@ int ttm_mem_global_init(struct ttm_mem_global *glob, struct device *dev)
 
 	si_meminfo(&si);
 
+	spin_lock(&glob->lock);
 	/* set it as 0 by default to keep original behavior of OOM */
 	glob->lower_mem_limit = 0;
+	spin_unlock(&glob->lock);
 
 	ret = ttm_mem_init_kernel_zone(glob, &si);
 	if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
new file mode 100644
index 000000000000..b0d87c5f58d8
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
@@ -0,0 +1,539 @@
+/**********************************************************
+ * Copyright 2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy,
+ * modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ **********************************************************/
+
+#ifndef VMW_SURFACE_CACHE_H
+#define VMW_SURFACE_CACHE_H
+
+#include "device_include/svga3d_surfacedefs.h"
+
+#include <drm/vmwgfx_drm.h>
+
+static inline u32 clamped_umul32(u32 a, u32 b)
+{
+	uint64_t tmp = (uint64_t) a*b;
+	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
+}
+
+/**
+ * vmw_surface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
+ * given format.
+ */
+static inline const SVGA3dSurfaceDesc *
+vmw_surface_get_desc(SVGA3dSurfaceFormat format)
+{
+	if (format < ARRAY_SIZE(g_SVGA3dSurfaceDescs))
+		return &g_SVGA3dSurfaceDescs[format];
+
+	return &g_SVGA3dSurfaceDescs[SVGA3D_FORMAT_INVALID];
+}
+
+/**
+ * vmw_surface_get_mip_size -  Given a base level size and the mip level,
+ * compute the size of the mip level.
+ */
+static inline struct drm_vmw_size
+vmw_surface_get_mip_size(struct drm_vmw_size base_level, u32 mip_level)
+{
+	struct drm_vmw_size size = {
+		.width = max_t(u32, base_level.width >> mip_level, 1),
+		.height = max_t(u32, base_level.height >> mip_level, 1),
+		.depth = max_t(u32, base_level.depth >> mip_level, 1)
+	};
+
+	return size;
+}
+
+static inline void
+vmw_surface_get_size_in_blocks(const SVGA3dSurfaceDesc *desc,
+				 const struct drm_vmw_size *pixel_size,
+				 SVGA3dSize *block_size)
+{
+	block_size->width = __KERNEL_DIV_ROUND_UP(pixel_size->width,
+						  desc->blockSize.width);
+	block_size->height = __KERNEL_DIV_ROUND_UP(pixel_size->height,
+						   desc->blockSize.height);
+	block_size->depth = __KERNEL_DIV_ROUND_UP(pixel_size->depth,
+						  desc->blockSize.depth);
+}
+
+static inline bool
+vmw_surface_is_planar_surface(const SVGA3dSurfaceDesc *desc)
+{
+	return (desc->blockDesc & SVGA3DBLOCKDESC_PLANAR_YUV) != 0;
+}
+
+static inline u32
+vmw_surface_calculate_pitch(const SVGA3dSurfaceDesc *desc,
+			      const struct drm_vmw_size *size)
+{
+	u32 pitch;
+	SVGA3dSize blocks;
+
+	vmw_surface_get_size_in_blocks(desc, size, &blocks);
+
+	pitch = blocks.width * desc->pitchBytesPerBlock;
+
+	return pitch;
+}
+
+/**
+ * vmw_surface_get_image_buffer_size - Calculates image buffer size.
+ *
+ * Return the number of bytes of buffer space required to store one image of a
+ * surface, optionally using the specified pitch.
+ *
+ * If pitch is zero, it is assumed that rows are tightly packed.
+ *
+ * This function is overflow-safe. If the result would have overflowed, instead
+ * we return MAX_UINT32.
+ */
+static inline u32
+vmw_surface_get_image_buffer_size(const SVGA3dSurfaceDesc *desc,
+				    const struct drm_vmw_size *size,
+				    u32 pitch)
+{
+	SVGA3dSize image_blocks;
+	u32 slice_size, total_size;
+
+	vmw_surface_get_size_in_blocks(desc, size, &image_blocks);
+
+	if (vmw_surface_is_planar_surface(desc)) {
+		total_size = clamped_umul32(image_blocks.width,
+					    image_blocks.height);
+		total_size = clamped_umul32(total_size, image_blocks.depth);
+		total_size = clamped_umul32(total_size, desc->bytesPerBlock);
+		return total_size;
+	}
+
+	if (pitch == 0)
+		pitch = vmw_surface_calculate_pitch(desc, size);
+
+	slice_size = clamped_umul32(image_blocks.height, pitch);
+	total_size = clamped_umul32(slice_size, image_blocks.depth);
+
+	return total_size;
+}
+
+/**
+ * vmw_surface_get_serialized_size - Get the serialized size for the image.
+ */
+static inline u32
+vmw_surface_get_serialized_size(SVGA3dSurfaceFormat format,
+				  struct drm_vmw_size base_level_size,
+				  u32 num_mip_levels,
+				  u32 num_layers)
+{
+	const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
+	u32 total_size = 0;
+	u32 mip;
+
+	for (mip = 0; mip < num_mip_levels; mip++) {
+		struct drm_vmw_size size =
+			vmw_surface_get_mip_size(base_level_size, mip);
+		total_size += vmw_surface_get_image_buffer_size(desc,
+								  &size, 0);
+	}
+
+	return total_size * num_layers;
+}
+
+/**
+ * vmw_surface_get_serialized_size_extended - Returns the number of bytes
+ * required for a surface with given parameters. Support for sample count.
+ */
+static inline u32
+vmw_surface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
+					   struct drm_vmw_size base_level_size,
+					   u32 num_mip_levels,
+					   u32 num_layers,
+					   u32 num_samples)
+{
+	uint64_t total_size =
+		vmw_surface_get_serialized_size(format,
+						  base_level_size,
+						  num_mip_levels,
+						  num_layers);
+	total_size *= max_t(u32, 1, num_samples);
+
+	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
+}
+
+/**
+ * vmw_surface_get_pixel_offset - Compute the offset (in bytes) to a pixel
+ * in an image (or volume).
+ *
+ * @width: The image width in pixels.
+ * @height: The image height in pixels
+ */
+static inline u32
+vmw_surface_get_pixel_offset(SVGA3dSurfaceFormat format,
+			       u32 width, u32 height,
+			       u32 x, u32 y, u32 z)
+{
+	const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
+	const u32 bw = desc->blockSize.width, bh = desc->blockSize.height;
+	const u32 bd = desc->blockSize.depth;
+	const u32 rowstride = __KERNEL_DIV_ROUND_UP(width, bw) *
+			      desc->bytesPerBlock;
+	const u32 imgstride = __KERNEL_DIV_ROUND_UP(height, bh) * rowstride;
+	const u32 offset = (z / bd * imgstride +
+			    y / bh * rowstride +
+			    x / bw * desc->bytesPerBlock);
+	return offset;
+}
+
+static inline u32
+vmw_surface_get_image_offset(SVGA3dSurfaceFormat format,
+			       struct drm_vmw_size baseLevelSize,
+			       u32 numMipLevels,
+			       u32 face,
+			       u32 mip)
+
+{
+	u32 offset;
+	u32 mipChainBytes;
+	u32 mipChainBytesToLevel;
+	u32 i;
+	const SVGA3dSurfaceDesc *desc;
+	struct drm_vmw_size mipSize;
+	u32 bytes;
+
+	desc = vmw_surface_get_desc(format);
+
+	mipChainBytes = 0;
+	mipChainBytesToLevel = 0;
+	for (i = 0; i < numMipLevels; i++) {
+		mipSize = vmw_surface_get_mip_size(baseLevelSize, i);
+		bytes = vmw_surface_get_image_buffer_size(desc, &mipSize, 0);
+		mipChainBytes += bytes;
+		if (i < mip)
+			mipChainBytesToLevel += bytes;
+	}
+
+	offset = mipChainBytes * face + mipChainBytesToLevel;
+
+	return offset;
+}
+
+
+/**
+ * vmw_surface_is_gb_screen_target_format - Is the specified format usable as
+ *                                            a ScreenTarget?
+ *                                            (with just the GBObjects cap-bit
+ *                                             set)
+ * @format: format to queried
+ *
+ * RETURNS:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_gb_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	return (format == SVGA3D_X8R8G8B8 ||
+		format == SVGA3D_A8R8G8B8 ||
+		format == SVGA3D_R5G6B5   ||
+		format == SVGA3D_X1R5G5B5 ||
+		format == SVGA3D_A1R5G5B5 ||
+		format == SVGA3D_P8);
+}
+
+
+/**
+ * vmw_surface_is_dx_screen_target_format - Is the specified format usable as
+ *                                            a ScreenTarget?
+ *                                            (with DX10 enabled)
+ *
+ * @format: format to queried
+ *
+ * Results:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_dx_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	return (format == SVGA3D_R8G8B8A8_UNORM ||
+		format == SVGA3D_B8G8R8A8_UNORM ||
+		format == SVGA3D_B8G8R8X8_UNORM);
+}
+
+
+/**
+ * vmw_surface_is_screen_target_format - Is the specified format usable as a
+ *                                         ScreenTarget?
+ *                                         (for some combination of caps)
+ *
+ * @format: format to queried
+ *
+ * Results:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	if (vmw_surface_is_gb_screen_target_format(format)) {
+		return true;
+	}
+	return vmw_surface_is_dx_screen_target_format(format);
+}
+
+/**
+ * struct vmw_surface_mip - Mimpmap level information
+ * @bytes: Bytes required in the backing store of this mipmap level.
+ * @img_stride: Byte stride per image.
+ * @row_stride: Byte stride per block row.
+ * @size: The size of the mipmap.
+ */
+struct vmw_surface_mip {
+	size_t bytes;
+	size_t img_stride;
+	size_t row_stride;
+	struct drm_vmw_size size;
+
+};
+
+/**
+ * struct vmw_surface_cache - Cached surface information
+ * @desc: Pointer to the surface descriptor
+ * @mip: Array of mipmap level information. Valid size is @num_mip_levels.
+ * @mip_chain_bytes: Bytes required in the backing store for the whole chain
+ * of mip levels.
+ * @sheet_bytes: Bytes required in the backing store for a sheet
+ * representing a single sample.
+ * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in
+ * a chain.
+ * @num_layers: Number of slices in an array texture or number of faces in
+ * a cubemap texture.
+ */
+struct vmw_surface_cache {
+	const SVGA3dSurfaceDesc *desc;
+	struct vmw_surface_mip mip[DRM_VMW_MAX_MIP_LEVELS];
+	size_t mip_chain_bytes;
+	size_t sheet_bytes;
+	u32 num_mip_levels;
+	u32 num_layers;
+};
+
+/**
+ * struct vmw_surface_loc - Surface location
+ * @sheet: The multisample sheet.
+ * @sub_resource: Surface subresource. Defined as layer * num_mip_levels +
+ * mip_level.
+ * @x: X coordinate.
+ * @y: Y coordinate.
+ * @z: Z coordinate.
+ */
+struct vmw_surface_loc {
+	u32 sheet;
+	u32 sub_resource;
+	u32 x, y, z;
+};
+
+/**
+ * vmw_surface_subres - Compute the subresource from layer and mipmap.
+ * @cache: Surface layout data.
+ * @mip_level: The mipmap level.
+ * @layer: The surface layer (face or array slice).
+ *
+ * Return: The subresource.
+ */
+static inline u32 vmw_surface_subres(const struct vmw_surface_cache *cache,
+				       u32 mip_level, u32 layer)
+{
+	return cache->num_mip_levels * layer + mip_level;
+}
+
+/**
+ * vmw_surface_setup_cache - Build a surface cache entry
+ * @size: The surface base level dimensions.
+ * @format: The surface format.
+ * @num_mip_levels: Number of mipmap levels.
+ * @num_layers: Number of layers.
+ * @cache: Pointer to a struct vmw_surface_cach object to be filled in.
+ *
+ * Return: Zero on success, -EINVAL on invalid surface layout.
+ */
+static inline int vmw_surface_setup_cache(const struct drm_vmw_size *size,
+					    SVGA3dSurfaceFormat format,
+					    u32 num_mip_levels,
+					    u32 num_layers,
+					    u32 num_samples,
+					    struct vmw_surface_cache *cache)
+{
+	const SVGA3dSurfaceDesc *desc;
+	u32 i;
+
+	memset(cache, 0, sizeof(*cache));
+	cache->desc = desc = vmw_surface_get_desc(format);
+	cache->num_mip_levels = num_mip_levels;
+	cache->num_layers = num_layers;
+	for (i = 0; i < cache->num_mip_levels; i++) {
+		struct vmw_surface_mip *mip = &cache->mip[i];
+
+		mip->size = vmw_surface_get_mip_size(*size, i);
+		mip->bytes = vmw_surface_get_image_buffer_size
+			(desc, &mip->size, 0);
+		mip->row_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.width,
+					      desc->blockSize.width) *
+			desc->bytesPerBlock * num_samples;
+		if (!mip->row_stride)
+			goto invalid_dim;
+
+		mip->img_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.height,
+					      desc->blockSize.height) *
+			mip->row_stride;
+		if (!mip->img_stride)
+			goto invalid_dim;
+
+		cache->mip_chain_bytes += mip->bytes;
+	}
+	cache->sheet_bytes = cache->mip_chain_bytes * num_layers;
+	if (!cache->sheet_bytes)
+		goto invalid_dim;
+
+	return 0;
+
+invalid_dim:
+	VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n");
+	return -EINVAL;
+}
+
+/**
+ * vmw_surface_get_loc - Get a surface location from an offset into the
+ * backing store
+ * @cache: Surface layout data.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ * @offset: Offset into the surface backing store.
+ */
+static inline void
+vmw_surface_get_loc(const struct vmw_surface_cache *cache,
+		      struct vmw_surface_loc *loc,
+		      size_t offset)
+{
+	const struct vmw_surface_mip *mip = &cache->mip[0];
+	const SVGA3dSurfaceDesc *desc = cache->desc;
+	u32 layer;
+	int i;
+
+	loc->sheet = offset / cache->sheet_bytes;
+	offset -= loc->sheet * cache->sheet_bytes;
+
+	layer = offset / cache->mip_chain_bytes;
+	offset -= layer * cache->mip_chain_bytes;
+	for (i = 0; i < cache->num_mip_levels; ++i, ++mip) {
+		if (mip->bytes > offset)
+			break;
+		offset -= mip->bytes;
+	}
+
+	loc->sub_resource = vmw_surface_subres(cache, i, layer);
+	loc->z = offset / mip->img_stride;
+	offset -= loc->z * mip->img_stride;
+	loc->z *= desc->blockSize.depth;
+	loc->y = offset / mip->row_stride;
+	offset -= loc->y * mip->row_stride;
+	loc->y *= desc->blockSize.height;
+	loc->x = offset / desc->bytesPerBlock;
+	loc->x *= desc->blockSize.width;
+}
+
+/**
+ * vmw_surface_inc_loc - Clamp increment a surface location with one block
+ * size
+ * in each dimension.
+ * @loc: Pointer to a struct vmw_surface_loc to be incremented.
+ *
+ * When computing the size of a range as size = end - start, the range does not
+ * include the end element. However a location representing the last byte
+ * of a touched region in the backing store *is* included in the range.
+ * This function modifies such a location to match the end definition
+ * given as start + size which is the one used in a SVGA3dBox.
+ */
+static inline void
+vmw_surface_inc_loc(const struct vmw_surface_cache *cache,
+		      struct vmw_surface_loc *loc)
+{
+	const SVGA3dSurfaceDesc *desc = cache->desc;
+	u32 mip = loc->sub_resource % cache->num_mip_levels;
+	const struct drm_vmw_size *size = &cache->mip[mip].size;
+
+	loc->sub_resource++;
+	loc->x += desc->blockSize.width;
+	if (loc->x > size->width)
+		loc->x = size->width;
+	loc->y += desc->blockSize.height;
+	if (loc->y > size->height)
+		loc->y = size->height;
+	loc->z += desc->blockSize.depth;
+	if (loc->z > size->depth)
+		loc->z = size->depth;
+}
+
+/**
+ * vmw_surface_min_loc - The start location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ */
+static inline void
+vmw_surface_min_loc(const struct vmw_surface_cache *cache,
+		      u32 sub_resource,
+		      struct vmw_surface_loc *loc)
+{
+	loc->sheet = 0;
+	loc->sub_resource = sub_resource;
+	loc->x = loc->y = loc->z = 0;
+}
+
+/**
+ * vmw_surface_min_loc - The end location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ *
+ * Following the end definition given in vmw_surface_inc_loc(),
+ * Compute the end location of a surface subresource.
+ */
+static inline void
+vmw_surface_max_loc(const struct vmw_surface_cache *cache,
+		      u32 sub_resource,
+		      struct vmw_surface_loc *loc)
+{
+	const struct drm_vmw_size *size;
+	u32 mip;
+
+	loc->sheet = 0;
+	loc->sub_resource = sub_resource + 1;
+	mip = sub_resource % cache->num_mip_levels;
+	size = &cache->mip[mip].size;
+	loc->x = size->width;
+	loc->y = size->height;
+	loc->z = size->depth;
+}
+
+
+#endif /* VMW_SURFACE_CACHE_H */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
index 05b324825900..6f27d69bad0e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
@@ -715,7 +715,7 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind)
  * without checking which bindings actually need to be emitted
  *
  * @cbs: Pointer to the context's struct vmw_ctx_binding_state
- * @bi: Pointer to where the binding info array is stored in @cbs
+ * @biv: Pointer to where the binding info array is stored in @cbs
  * @max_num: Maximum number of entries in the @bi array.
  *
  * Scans the @bi array for bindings and builds a buffer of view id data.
@@ -725,11 +725,9 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind)
  * contains the command data.
  */
 static void vmw_collect_view_ids(struct vmw_ctx_binding_state *cbs,
-				 const struct vmw_ctx_bindinfo *bi,
+				 const struct vmw_ctx_bindinfo_view *biv,
 				 u32 max_num)
 {
-	const struct vmw_ctx_bindinfo_view *biv =
-		container_of(bi, struct vmw_ctx_bindinfo_view, bi);
 	unsigned long i;
 
 	cbs->bind_cmd_count = 0;
@@ -838,7 +836,7 @@ static int vmw_emit_set_sr(struct vmw_ctx_binding_state *cbs,
  */
 static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs)
 {
-	const struct vmw_ctx_bindinfo *loc = &cbs->render_targets[0].bi;
+	const struct vmw_ctx_bindinfo_view *loc = &cbs->render_targets[0];
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXSetRenderTargets body;
@@ -846,7 +844,7 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs)
 	size_t cmd_size, view_id_size;
 	const struct vmw_resource *ctx = vmw_cbs_context(cbs);
 
-	vmw_collect_view_ids(cbs, loc, SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS);
+	vmw_collect_view_ids(cbs, loc, SVGA3D_DX_MAX_RENDER_TARGETS);
 	view_id_size = cbs->bind_cmd_count*sizeof(uint32);
 	cmd_size = sizeof(*cmd) + view_id_size;
 	cmd = VMW_CMD_CTX_RESERVE(ctx->dev_priv, cmd_size, ctx->id);
@@ -874,7 +872,7 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs)
  * without checking which bindings actually need to be emitted
  *
  * @cbs: Pointer to the context's struct vmw_ctx_binding_state
- * @bi: Pointer to where the binding info array is stored in @cbs
+ * @biso: Pointer to where the binding info array is stored in @cbs
  * @max_num: Maximum number of entries in the @bi array.
  *
  * Scans the @bi array for bindings and builds a buffer of SVGA3dSoTarget data.
@@ -884,11 +882,9 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs)
  * contains the command data.
  */
 static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs,
-				   const struct vmw_ctx_bindinfo *bi,
+				   const struct vmw_ctx_bindinfo_so_target *biso,
 				   u32 max_num)
 {
-	const struct vmw_ctx_bindinfo_so_target *biso =
-		container_of(bi, struct vmw_ctx_bindinfo_so_target, bi);
 	unsigned long i;
 	SVGA3dSoTarget *so_buffer = (SVGA3dSoTarget *) cbs->bind_cmd_buffer;
 
@@ -919,7 +915,7 @@ static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs,
  */
 static int vmw_emit_set_so_target(struct vmw_ctx_binding_state *cbs)
 {
-	const struct vmw_ctx_bindinfo *loc = &cbs->so_targets[0].bi;
+	const struct vmw_ctx_bindinfo_so_target *loc = &cbs->so_targets[0];
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXSetSOTargets body;
@@ -1066,7 +1062,7 @@ static int vmw_emit_set_vb(struct vmw_ctx_binding_state *cbs)
 
 static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs)
 {
-	const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[0].views[0].bi;
+	const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[0].views[0];
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXSetUAViews body;
@@ -1096,7 +1092,7 @@ static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs)
 
 static int vmw_emit_set_cs_uav(struct vmw_ctx_binding_state *cbs)
 {
-	const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[1].views[0].bi;
+	const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[1].views[0];
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXSetCSUAViews body;
@@ -1444,7 +1440,7 @@ u32 vmw_binding_dirtying(enum vmw_ctx_binding_type binding_type)
 static void vmw_binding_build_asserts(void)
 {
 	BUILD_BUG_ON(SVGA3D_NUM_SHADERTYPE_DX10 != 3);
-	BUILD_BUG_ON(SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS > SVGA3D_RT_MAX);
+	BUILD_BUG_ON(SVGA3D_DX_MAX_RENDER_TARGETS > SVGA3D_RT_MAX);
 	BUILD_BUG_ON(sizeof(uint32) != sizeof(u32));
 
 	/*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 362f56d5b12b..9e3e1429db94 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -405,7 +405,7 @@ static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
 			      bool user)
 {
 	static size_t struct_size, user_struct_size;
-	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t num_pages = PFN_UP(size);
 	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
 
 	if (unlikely(struct_size == 0)) {
@@ -474,7 +474,6 @@ int vmw_bo_create_kernel(struct vmw_private *dev_priv, unsigned long size,
 			 struct ttm_placement *placement,
 			 struct ttm_buffer_object **p_bo)
 {
-	unsigned npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct ttm_operation_ctx ctx = { false, false };
 	struct ttm_buffer_object *bo;
 	size_t acc_size;
@@ -485,7 +484,7 @@ int vmw_bo_create_kernel(struct vmw_private *dev_priv, unsigned long size,
 		return -ENOMEM;
 
 	acc_size = ttm_round_pot(sizeof(*bo));
-	acc_size += ttm_round_pot(npages * sizeof(void *));
+	acc_size += ttm_round_pot(PFN_UP(size) * sizeof(void *));
 	acc_size += ttm_round_pot(sizeof(struct ttm_tt));
 
 	ret = ttm_mem_global_alloc(&ttm_mem_glob, acc_size, &ctx);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c
index 956b85e35cef..67db472d3493 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c
@@ -30,6 +30,7 @@
 #include <drm/ttm/ttm_placement.h>
 
 #include "vmwgfx_drv.h"
+#include "vmwgfx_devcaps.h"
 
 bool vmw_supports_3d(struct vmw_private *dev_priv)
 {
@@ -45,10 +46,7 @@ bool vmw_supports_3d(struct vmw_private *dev_priv)
 		if (!dev_priv->has_mob)
 			return false;
 
-		spin_lock(&dev_priv->cap_lock);
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D);
-		result = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
-		spin_unlock(&dev_priv->cap_lock);
+		result = vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_3D);
 
 		return (result != 0);
 	}
@@ -142,7 +140,8 @@ struct vmw_fifo_state *vmw_fifo_create(struct vmw_private *dev_priv)
 	min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
 	fifo->capabilities = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_CAPABILITIES);
 
-	DRM_INFO("Fifo max 0x%08x min 0x%08x cap 0x%08x\n",
+	drm_info(&dev_priv->drm,
+		 "Fifo max 0x%08x min 0x%08x cap 0x%08x\n",
 		 (unsigned int) max,
 		 (unsigned int) min,
 		 (unsigned int) fifo->capabilities);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 6bb4961e64a5..3c06df2a5474 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -358,8 +358,7 @@ static void vmw_cmdbuf_ctx_submit(struct vmw_cmdbuf_man *man,
 			break;
 		}
 
-		list_del(&entry->list);
-		list_add_tail(&entry->list, &ctx->hw_submitted);
+		list_move_tail(&entry->list, &ctx->hw_submitted);
 		ctx->num_hw_submitted++;
 	}
 
@@ -516,7 +515,7 @@ static void vmw_cmdbuf_work_func(struct work_struct *work)
 	struct vmw_cmdbuf_man *man =
 		container_of(work, struct vmw_cmdbuf_man, work);
 	struct vmw_cmdbuf_header *entry, *next;
-	uint32_t dummy;
+	uint32_t dummy = 0;
 	bool send_fence = false;
 	struct list_head restart_head[SVGA_CB_CONTEXT_MAX];
 	int i;
@@ -802,7 +801,7 @@ static int vmw_cmdbuf_alloc_space(struct vmw_cmdbuf_man *man,
 {
 	struct vmw_cmdbuf_alloc_info info;
 
-	info.page_size = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	info.page_size = PFN_UP(size);
 	info.node = node;
 	info.done = false;
 
@@ -1272,7 +1271,8 @@ int vmw_cmdbuf_set_pool_size(struct vmw_cmdbuf_man *man, size_t size)
 	 * submissions to be able to free up space.
 	 */
 	man->default_size = VMW_CMDBUF_INLINE_SIZE;
-	DRM_INFO("Using command buffers with %s pool.\n",
+	drm_info(&dev_priv->drm,
+		 "Using command buffers with %s pool.\n",
 		 (man->using_mob) ? "MOB" : "DMA");
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index b262d61d839d..8381750db81b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -159,6 +159,7 @@ void vmw_cmdbuf_res_commit(struct list_head *list)
 void vmw_cmdbuf_res_revert(struct list_head *list)
 {
 	struct vmw_cmdbuf_res *entry, *next;
+	int ret;
 
 	list_for_each_entry_safe(entry, next, list, head) {
 		switch (entry->state) {
@@ -166,9 +167,9 @@ void vmw_cmdbuf_res_revert(struct list_head *list)
 			vmw_cmdbuf_res_free(entry->man, entry);
 			break;
 		case VMW_CMDBUF_RES_DEL:
-			drm_ht_insert_item(&entry->man->resources, &entry->hash);
-			list_del(&entry->head);
-			list_add_tail(&entry->head, &entry->man->list);
+			ret = drm_ht_insert_item(&entry->man->resources, &entry->hash);
+			BUG_ON(ret);
+			list_move_tail(&entry->head, &entry->man->list);
 			entry->state = VMW_CMDBUF_RES_COMMITTED;
 			break;
 		default:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index dffe3804ad3e..4446758b6880 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -185,7 +185,7 @@ static int vmw_gb_context_init(struct vmw_private *dev_priv,
 		container_of(res, struct vmw_user_context, res);
 
 	res->backup_size = (dx ? sizeof(SVGADXContextMobFormat) :
-			    SVGA3D_CONTEXT_DATA_SIZE);
+				 sizeof(SVGAGBContextData));
 	ret = vmw_resource_init(dev_priv, res, true,
 				res_free,
 				dx ? &vmw_dx_context_func :
@@ -259,7 +259,7 @@ static int vmw_context_init(struct vmw_private *dev_priv,
 		goto out_early;
 	}
 
-	if (unlikely(res->id >= SVGA3D_MAX_CONTEXT_IDS)) {
+	if (unlikely(res->id >= SVGA3D_HB_MAX_CONTEXT_IDS)) {
 		DRM_ERROR("Out of hw context ids.\n");
 		vmw_resource_unreference(&res);
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index c84a16c1def0..17a98db00017 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -607,8 +607,7 @@ struct vmw_resource *vmw_cotable_alloc(struct vmw_private *dev_priv,
 	if (num_entries < co_info[type].min_initial_entries) {
 		vcotbl->res.backup_size = co_info[type].min_initial_entries *
 			co_info[type].size;
-		vcotbl->res.backup_size =
-			(vcotbl->res.backup_size + PAGE_SIZE - 1) & PAGE_MASK;
+		vcotbl->res.backup_size = PFN_ALIGN(vcotbl->res.backup_size);
 	}
 
 	vcotbl->scrubbed = true;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c
new file mode 100644
index 000000000000..829df395c2ed
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/**************************************************************************
+ *
+ * Copyright 2021 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#include "vmwgfx_devcaps.h"
+
+#include "vmwgfx_drv.h"
+
+
+struct svga_3d_compat_cap {
+	SVGA3dFifoCapsRecordHeader header;
+	SVGA3dFifoCapPair pairs[SVGA3D_DEVCAP_MAX];
+};
+
+
+static u32 vmw_mask_legacy_multisample(unsigned int cap, u32 fmt_value)
+{
+	/*
+	 * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
+	 * to check the sample count supported by virtual device. Since there
+	 * never was support for multisample count for backing MOB return 0.
+	 *
+	 * MULTISAMPLE_MASKABLESAMPLES devcap is marked as deprecated by virtual
+	 * device.
+	 */
+	if (cap == SVGA3D_DEVCAP_DEAD5)
+		return 0;
+
+	return fmt_value;
+}
+
+static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce,
+			       size_t size)
+{
+	struct svga_3d_compat_cap *compat_cap =
+		(struct svga_3d_compat_cap *) bounce;
+	unsigned int i;
+	size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs);
+	unsigned int max_size;
+
+	if (size < pair_offset)
+		return -EINVAL;
+
+	max_size = (size - pair_offset) / sizeof(SVGA3dFifoCapPair);
+
+	if (max_size > SVGA3D_DEVCAP_MAX)
+		max_size = SVGA3D_DEVCAP_MAX;
+
+	compat_cap->header.length =
+		(pair_offset + max_size * sizeof(SVGA3dFifoCapPair)) / sizeof(u32);
+	compat_cap->header.type = SVGA3D_FIFO_CAPS_RECORD_DEVCAPS;
+
+	for (i = 0; i < max_size; ++i) {
+		compat_cap->pairs[i][0] = i;
+		compat_cap->pairs[i][1] = vmw_mask_legacy_multisample
+			(i, dev_priv->devcaps[i]);
+	}
+
+	return 0;
+}
+
+int vmw_devcaps_create(struct vmw_private *vmw)
+{
+	bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
+	uint32_t i;
+
+	if (gb_objects) {
+		vmw->devcaps = vzalloc(sizeof(uint32_t) * SVGA3D_DEVCAP_MAX);
+		if (!vmw->devcaps)
+			return -ENOMEM;
+		for (i = 0; i < SVGA3D_DEVCAP_MAX; ++i) {
+			vmw_write(vmw, SVGA_REG_DEV_CAP, i);
+			vmw->devcaps[i] = vmw_read(vmw, SVGA_REG_DEV_CAP);
+		}
+	}
+	return 0;
+}
+
+void vmw_devcaps_destroy(struct vmw_private *vmw)
+{
+	vfree(vmw->devcaps);
+	vmw->devcaps = NULL;
+}
+
+
+uint32 vmw_devcaps_size(const struct vmw_private *vmw,
+			bool gb_aware)
+{
+	bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
+	if (gb_objects && gb_aware)
+		return SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
+	else if (gb_objects)
+		return  sizeof(struct svga_3d_compat_cap) +
+				sizeof(uint32_t);
+	else if (vmw->fifo_mem != NULL)
+		return (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) *
+				sizeof(uint32_t);
+	else
+		return 0;
+}
+
+int vmw_devcaps_copy(struct vmw_private *vmw, bool gb_aware,
+		     void *dst, uint32_t dst_size)
+{
+	int ret;
+	bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
+	if (gb_objects && gb_aware) {
+		memcpy(dst, vmw->devcaps, dst_size);
+	} else if (gb_objects) {
+		ret = vmw_fill_compat_cap(vmw, dst, dst_size);
+		if (unlikely(ret != 0))
+			return ret;
+	} else if (vmw->fifo_mem) {
+		u32 *fifo_mem = vmw->fifo_mem;
+		memcpy(dst, &fifo_mem[SVGA_FIFO_3D_CAPS], dst_size);
+	} else
+		return -EINVAL;
+	return 0;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h
new file mode 100644
index 000000000000..f70e923ac3e6
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/**************************************************************************
+ *
+ * Copyright 2021 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#ifndef _VMWGFX_DEVCAPS_H_
+#define _VMWGFX_DEVCAPS_H_
+
+#include "vmwgfx_drv.h"
+
+#include "device_include/svga_reg.h"
+
+int vmw_devcaps_create(struct vmw_private *vmw);
+void vmw_devcaps_destroy(struct vmw_private *vmw);
+uint32_t vmw_devcaps_size(const struct vmw_private *vmw, bool gb_aware);
+int vmw_devcaps_copy(struct vmw_private *vmw, bool gb_aware,
+		     void *dst, uint32_t dst_size);
+
+static inline uint32_t vmw_devcap_get(struct vmw_private *vmw,
+				      uint32_t devcap)
+{
+	bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
+	if (gb_objects)
+		return vmw->devcaps[devcap];
+	return 0;
+}
+
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 45aeeca9b8f6..ab9a1750e1df 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -42,7 +42,9 @@
 
 #include "ttm_object.h"
 #include "vmwgfx_binding.h"
+#include "vmwgfx_devcaps.h"
 #include "vmwgfx_drv.h"
+#include "vmwgfx_mksstat.h"
 
 #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices"
 
@@ -148,102 +150,111 @@
 #define DRM_IOCTL_VMW_MSG						\
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_MSG,			\
 		struct drm_vmw_msg_arg)
-
-/*
- * The core DRM version of this macro doesn't account for
- * DRM_COMMAND_BASE.
- */
-
-#define VMW_IOCTL_DEF(ioctl, func, flags) \
-  [DRM_IOCTL_NR(DRM_IOCTL_##ioctl) - DRM_COMMAND_BASE] = {DRM_IOCTL_##ioctl, flags, func}
+#define DRM_IOCTL_VMW_MKSSTAT_RESET				\
+	DRM_IO(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_RESET)
+#define DRM_IOCTL_VMW_MKSSTAT_ADD				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_ADD,	\
+		struct drm_vmw_mksstat_add_arg)
+#define DRM_IOCTL_VMW_MKSSTAT_REMOVE				\
+	DRM_IOW(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_REMOVE,	\
+		struct drm_vmw_mksstat_remove_arg)
 
 /*
  * Ioctl definitions.
  */
 
 static const struct drm_ioctl_desc vmw_ioctls[] = {
-	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
-		      vmw_kms_cursor_bypass_ioctl,
-		      DRM_MASTER),
-
-	VMW_IOCTL_DEF(VMW_CONTROL_STREAM, vmw_overlay_ioctl,
-		      DRM_MASTER),
-	VMW_IOCTL_DEF(VMW_CLAIM_STREAM, vmw_stream_claim_ioctl,
-		      DRM_MASTER),
-	VMW_IOCTL_DEF(VMW_UNREF_STREAM, vmw_stream_unref_ioctl,
-		      DRM_MASTER),
-
-	VMW_IOCTL_DEF(VMW_CREATE_CONTEXT, vmw_context_define_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_CONTEXT, vmw_context_destroy_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_CREATE_SURFACE, vmw_surface_define_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_SURFACE, vmw_surface_destroy_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_REF_SURFACE, vmw_surface_reference_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_EXECBUF, vmw_execbuf_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_FENCE_WAIT, vmw_fence_obj_wait_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_FENCE_SIGNALED,
-		      vmw_fence_obj_signaled_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_FENCE_UNREF, vmw_fence_obj_unref_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_FENCE_EVENT, vmw_fence_event_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_GET_3D_CAP, vmw_get_cap_3d_ioctl,
-		      DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GET_PARAM, vmw_getparam_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_CURSOR_BYPASS,
+			  vmw_kms_cursor_bypass_ioctl,
+			  DRM_MASTER),
+
+	DRM_IOCTL_DEF_DRV(VMW_CONTROL_STREAM, vmw_overlay_ioctl,
+			  DRM_MASTER),
+	DRM_IOCTL_DEF_DRV(VMW_CLAIM_STREAM, vmw_stream_claim_ioctl,
+			  DRM_MASTER),
+	DRM_IOCTL_DEF_DRV(VMW_UNREF_STREAM, vmw_stream_unref_ioctl,
+			  DRM_MASTER),
+
+	DRM_IOCTL_DEF_DRV(VMW_CREATE_CONTEXT, vmw_context_define_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_UNREF_CONTEXT, vmw_context_destroy_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_CREATE_SURFACE, vmw_surface_define_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_UNREF_SURFACE, vmw_surface_destroy_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_REF_SURFACE, vmw_surface_reference_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_EXECBUF, vmw_execbuf_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_FENCE_WAIT, vmw_fence_obj_wait_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_FENCE_SIGNALED,
+			  vmw_fence_obj_signaled_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_FENCE_UNREF, vmw_fence_obj_unref_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_FENCE_EVENT, vmw_fence_event_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GET_3D_CAP, vmw_get_cap_3d_ioctl,
+			  DRM_RENDER_ALLOW),
 
 	/* these allow direct access to the framebuffers mark as master only */
-	VMW_IOCTL_DEF(VMW_PRESENT, vmw_present_ioctl,
-		      DRM_MASTER | DRM_AUTH),
-	VMW_IOCTL_DEF(VMW_PRESENT_READBACK,
-		      vmw_present_readback_ioctl,
-		      DRM_MASTER | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(VMW_PRESENT, vmw_present_ioctl,
+			  DRM_MASTER | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(VMW_PRESENT_READBACK,
+			  vmw_present_readback_ioctl,
+			  DRM_MASTER | DRM_AUTH),
 	/*
 	 * The permissions of the below ioctl are overridden in
 	 * vmw_generic_ioctl(). We require either
 	 * DRM_MASTER or capable(CAP_SYS_ADMIN).
 	 */
-	VMW_IOCTL_DEF(VMW_UPDATE_LAYOUT,
-		      vmw_kms_update_layout_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_CREATE_SHADER,
-		      vmw_shader_define_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_SHADER,
-		      vmw_shader_destroy_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE,
-		      vmw_gb_surface_define_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF,
-		      vmw_gb_surface_reference_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_SYNCCPU,
-		      vmw_user_bo_synccpu_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
-		      vmw_extended_context_define_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT,
-		      vmw_gb_surface_define_ext_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT,
-		      vmw_gb_surface_reference_ext_ioctl,
-		      DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_MSG,
-		      vmw_msg_ioctl,
-		      DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_UPDATE_LAYOUT,
+			  vmw_kms_update_layout_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_CREATE_SHADER,
+			  vmw_shader_define_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_UNREF_SHADER,
+			  vmw_shader_destroy_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GB_SURFACE_CREATE,
+			  vmw_gb_surface_define_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GB_SURFACE_REF,
+			  vmw_gb_surface_reference_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_SYNCCPU,
+			  vmw_user_bo_synccpu_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_CREATE_EXTENDED_CONTEXT,
+			  vmw_extended_context_define_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GB_SURFACE_CREATE_EXT,
+			  vmw_gb_surface_define_ext_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_GB_SURFACE_REF_EXT,
+			  vmw_gb_surface_reference_ext_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_MSG,
+			  vmw_msg_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_MKSSTAT_RESET,
+			  vmw_mksstat_reset_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_MKSSTAT_ADD,
+			  vmw_mksstat_add_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VMW_MKSSTAT_REMOVE,
+			  vmw_mksstat_remove_ioctl,
+			  DRM_RENDER_ALLOW),
 };
 
 static const struct pci_device_id vmw_pci_id_list[] = {
@@ -254,7 +265,6 @@ static const struct pci_device_id vmw_pci_id_list[] = {
 MODULE_DEVICE_TABLE(pci, vmw_pci_id_list);
 
 static int enable_fbdev = IS_ENABLED(CONFIG_DRM_VMWGFX_FBCON);
-static int vmw_force_iommu;
 static int vmw_restrict_iommu;
 static int vmw_force_coherent;
 static int vmw_restrict_dma_mask;
@@ -266,8 +276,6 @@ static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
 
 MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev");
 module_param_named(enable_fbdev, enable_fbdev, int, 0600);
-MODULE_PARM_DESC(force_dma_api, "Force using the DMA API for TTM pages");
-module_param_named(force_dma_api, vmw_force_iommu, int, 0600);
 MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages");
 module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600);
 MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
@@ -278,62 +286,92 @@ MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
 module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
-static void vmw_print_capabilities2(uint32_t capabilities2)
+struct bitmap_name {
+	uint32 value;
+	const char *name;
+};
+
+static const struct bitmap_name cap1_names[] = {
+	{ SVGA_CAP_RECT_COPY, "rect copy" },
+	{ SVGA_CAP_CURSOR, "cursor" },
+	{ SVGA_CAP_CURSOR_BYPASS, "cursor bypass" },
+	{ SVGA_CAP_CURSOR_BYPASS_2, "cursor bypass 2" },
+	{ SVGA_CAP_8BIT_EMULATION, "8bit emulation" },
+	{ SVGA_CAP_ALPHA_CURSOR, "alpha cursor" },
+	{ SVGA_CAP_3D, "3D" },
+	{ SVGA_CAP_EXTENDED_FIFO, "extended fifo" },
+	{ SVGA_CAP_MULTIMON, "multimon" },
+	{ SVGA_CAP_PITCHLOCK, "pitchlock" },
+	{ SVGA_CAP_IRQMASK, "irq mask" },
+	{ SVGA_CAP_DISPLAY_TOPOLOGY, "display topology" },
+	{ SVGA_CAP_GMR, "gmr" },
+	{ SVGA_CAP_TRACES, "traces" },
+	{ SVGA_CAP_GMR2, "gmr2" },
+	{ SVGA_CAP_SCREEN_OBJECT_2, "screen object 2" },
+	{ SVGA_CAP_COMMAND_BUFFERS, "command buffers" },
+	{ SVGA_CAP_CMD_BUFFERS_2, "command buffers 2" },
+	{ SVGA_CAP_GBOBJECTS, "gbobject" },
+	{ SVGA_CAP_DX, "dx" },
+	{ SVGA_CAP_HP_CMD_QUEUE, "hp cmd queue" },
+	{ SVGA_CAP_NO_BB_RESTRICTION, "no bb restriction" },
+	{ SVGA_CAP_CAP2_REGISTER, "cap2 register" },
+};
+
+
+static const struct bitmap_name cap2_names[] = {
+	{ SVGA_CAP2_GROW_OTABLE, "grow otable" },
+	{ SVGA_CAP2_INTRA_SURFACE_COPY, "intra surface copy" },
+	{ SVGA_CAP2_DX2, "dx2" },
+	{ SVGA_CAP2_GB_MEMSIZE_2, "gb memsize 2" },
+	{ SVGA_CAP2_SCREENDMA_REG, "screendma reg" },
+	{ SVGA_CAP2_OTABLE_PTDEPTH_2, "otable ptdepth2" },
+	{ SVGA_CAP2_NON_MS_TO_MS_STRETCHBLT, "non ms to ms stretchblt" },
+	{ SVGA_CAP2_CURSOR_MOB, "cursor mob" },
+	{ SVGA_CAP2_MSHINT, "mshint" },
+	{ SVGA_CAP2_CB_MAX_SIZE_4MB, "cb max size 4mb" },
+	{ SVGA_CAP2_DX3, "dx3" },
+	{ SVGA_CAP2_FRAME_TYPE, "frame type" },
+	{ SVGA_CAP2_COTABLE_COPY, "cotable copy" },
+	{ SVGA_CAP2_TRACE_FULL_FB, "trace full fb" },
+	{ SVGA_CAP2_EXTRA_REGS, "extra regs" },
+	{ SVGA_CAP2_LO_STAGING, "lo staging" },
+};
+
+static void vmw_print_bitmap(struct drm_device *drm,
+			     const char *prefix, uint32_t bitmap,
+			     const struct bitmap_name *bnames,
+			     uint32_t num_names)
 {
-	DRM_INFO("Capabilities2:\n");
-	if (capabilities2 & SVGA_CAP2_GROW_OTABLE)
-		DRM_INFO("  Grow oTable.\n");
-	if (capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY)
-		DRM_INFO("  IntraSurface copy.\n");
-	if (capabilities2 & SVGA_CAP2_DX3)
-		DRM_INFO("  DX3.\n");
+	char buf[512];
+	uint32_t i;
+	uint32_t offset = 0;
+	for (i = 0; i < num_names; ++i) {
+		if ((bitmap & bnames[i].value) != 0) {
+			offset += snprintf(buf + offset,
+					   ARRAY_SIZE(buf) - offset,
+					   "%s, ", bnames[i].name);
+			bitmap &= ~bnames[i].value;
+		}
+	}
+
+	drm_info(drm, "%s: %s\n", prefix, buf);
+	if (bitmap != 0)
+		drm_dbg(drm, "%s: unknown enums: %x\n", prefix, bitmap);
 }
 
-static void vmw_print_capabilities(uint32_t capabilities)
+
+static void vmw_print_sm_type(struct vmw_private *dev_priv)
 {
-	DRM_INFO("Capabilities:\n");
-	if (capabilities & SVGA_CAP_RECT_COPY)
-		DRM_INFO("  Rect copy.\n");
-	if (capabilities & SVGA_CAP_CURSOR)
-		DRM_INFO("  Cursor.\n");
-	if (capabilities & SVGA_CAP_CURSOR_BYPASS)
-		DRM_INFO("  Cursor bypass.\n");
-	if (capabilities & SVGA_CAP_CURSOR_BYPASS_2)
-		DRM_INFO("  Cursor bypass 2.\n");
-	if (capabilities & SVGA_CAP_8BIT_EMULATION)
-		DRM_INFO("  8bit emulation.\n");
-	if (capabilities & SVGA_CAP_ALPHA_CURSOR)
-		DRM_INFO("  Alpha cursor.\n");
-	if (capabilities & SVGA_CAP_3D)
-		DRM_INFO("  3D.\n");
-	if (capabilities & SVGA_CAP_EXTENDED_FIFO)
-		DRM_INFO("  Extended Fifo.\n");
-	if (capabilities & SVGA_CAP_MULTIMON)
-		DRM_INFO("  Multimon.\n");
-	if (capabilities & SVGA_CAP_PITCHLOCK)
-		DRM_INFO("  Pitchlock.\n");
-	if (capabilities & SVGA_CAP_IRQMASK)
-		DRM_INFO("  Irq mask.\n");
-	if (capabilities & SVGA_CAP_DISPLAY_TOPOLOGY)
-		DRM_INFO("  Display Topology.\n");
-	if (capabilities & SVGA_CAP_GMR)
-		DRM_INFO("  GMR.\n");
-	if (capabilities & SVGA_CAP_TRACES)
-		DRM_INFO("  Traces.\n");
-	if (capabilities & SVGA_CAP_GMR2)
-		DRM_INFO("  GMR2.\n");
-	if (capabilities & SVGA_CAP_SCREEN_OBJECT_2)
-		DRM_INFO("  Screen Object 2.\n");
-	if (capabilities & SVGA_CAP_COMMAND_BUFFERS)
-		DRM_INFO("  Command Buffers.\n");
-	if (capabilities & SVGA_CAP_CMD_BUFFERS_2)
-		DRM_INFO("  Command Buffers 2.\n");
-	if (capabilities & SVGA_CAP_GBOBJECTS)
-		DRM_INFO("  Guest Backed Resources.\n");
-	if (capabilities & SVGA_CAP_DX)
-		DRM_INFO("  DX Features.\n");
-	if (capabilities & SVGA_CAP_HP_CMD_QUEUE)
-		DRM_INFO("  HP Command Queue.\n");
+	static const char *names[] = {
+		[VMW_SM_LEGACY] = "Legacy",
+		[VMW_SM_4] = "SM4",
+		[VMW_SM_4_1] = "SM4_1",
+		[VMW_SM_5] = "SM_5",
+		[VMW_SM_MAX] = "Invalid"
+	};
+	BUILD_BUG_ON(ARRAY_SIZE(names) != (VMW_SM_MAX + 1));
+	drm_info(&dev_priv->drm, "Available shader model: %s.\n",
+		 names[dev_priv->sm_type]);
 }
 
 /**
@@ -400,10 +438,6 @@ static int vmw_device_init(struct vmw_private *dev_priv)
 {
 	bool uses_fb_traces = false;
 
-	DRM_INFO("width %d\n", vmw_read(dev_priv, SVGA_REG_WIDTH));
-	DRM_INFO("height %d\n", vmw_read(dev_priv, SVGA_REG_HEIGHT));
-	DRM_INFO("bpp %d\n", vmw_read(dev_priv, SVGA_REG_BITS_PER_PIXEL));
-
 	dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE);
 	dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE);
 	dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES);
@@ -627,7 +661,6 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv)
 static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 {
 	static const char *names[vmw_dma_map_max] = {
-		[vmw_dma_phys] = "Using physical TTM page addresses.",
 		[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
 		[vmw_dma_map_populate] = "Caching DMA mappings.",
 		[vmw_dma_map_bind] = "Giving up DMA mappings early."};
@@ -643,7 +676,8 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 	else
 		dev_priv->map_mode = vmw_dma_map_populate;
 
-	DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]);
+	drm_info(&dev_priv->drm,
+		 "DMA map mode: %s\n", names[dev_priv->map_mode]);
 	return 0;
 }
 
@@ -661,9 +695,9 @@ static int vmw_dma_masks(struct vmw_private *dev_priv)
 	int ret = 0;
 
 	ret = dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64));
-	if (dev_priv->map_mode != vmw_dma_phys &&
-	    (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) {
-		DRM_INFO("Restricting DMA addresses to 44 bits.\n");
+	if (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask) {
+		drm_info(&dev_priv->drm,
+			 "Restricting DMA addresses to 44 bits.\n");
 		return dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(44));
 	}
 
@@ -693,7 +727,7 @@ static void vmw_vram_manager_fini(struct vmw_private *dev_priv)
 }
 
 static int vmw_setup_pci_resources(struct vmw_private *dev,
-				   unsigned long pci_id)
+				   u32 pci_id)
 {
 	resource_size_t rmmio_start;
 	resource_size_t rmmio_size;
@@ -715,13 +749,15 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		dev->vram_start = pci_resource_start(pdev, 2);
 		dev->vram_size = pci_resource_len(pdev, 2);
 
-		DRM_INFO("Register MMIO at 0x%pa size is %llu kiB\n",
+		drm_info(&dev->drm,
+			"Register MMIO at 0x%pa size is %llu kiB\n",
 			 &rmmio_start, (uint64_t)rmmio_size / 1024);
 		dev->rmmio = devm_ioremap(dev->drm.dev,
 					  rmmio_start,
 					  rmmio_size);
 		if (!dev->rmmio) {
-			DRM_ERROR("Failed mapping registers mmio memory.\n");
+			drm_err(&dev->drm,
+				"Failed mapping registers mmio memory.\n");
 			pci_release_regions(pdev);
 			return -ENOMEM;
 		}
@@ -732,7 +768,8 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		fifo_start = pci_resource_start(pdev, 2);
 		fifo_size = pci_resource_len(pdev, 2);
 
-		DRM_INFO("FIFO at %pa size is %llu kiB\n",
+		drm_info(&dev->drm,
+			 "FIFO at %pa size is %llu kiB\n",
 			 &fifo_start, (uint64_t)fifo_size / 1024);
 		dev->fifo_mem = devm_memremap(dev->drm.dev,
 					      fifo_start,
@@ -740,7 +777,8 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 					      MEMREMAP_WB);
 
 		if (IS_ERR(dev->fifo_mem)) {
-			DRM_ERROR("Failed mapping FIFO memory.\n");
+			drm_err(&dev->drm,
+				  "Failed mapping FIFO memory.\n");
 			pci_release_regions(pdev);
 			return PTR_ERR(dev->fifo_mem);
 		}
@@ -755,7 +793,8 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 	 * size will be equal to or bigger than the size reported by
 	 * SVGA_REG_VRAM_SIZE.
 	 */
-	DRM_INFO("VRAM at %pa size is %llu kiB\n",
+	drm_info(&dev->drm,
+		 "VRAM at %pa size is %llu kiB\n",
 		 &dev->vram_start, (uint64_t)dev->vram_size / 1024);
 
 	return 0;
@@ -769,12 +808,14 @@ static int vmw_detect_version(struct vmw_private *dev)
 			  SVGA_ID_3 : SVGA_ID_2);
 	svga_id = vmw_read(dev, SVGA_REG_ID);
 	if (svga_id != SVGA_ID_2 && svga_id != SVGA_ID_3) {
-		DRM_ERROR("Unsupported SVGA ID 0x%x on chipset 0x%x\n",
-			  svga_id, dev->vmw_chipset);
+		drm_err(&dev->drm,
+			"Unsupported SVGA ID 0x%x on chipset 0x%x\n",
+			svga_id, dev->pci_id);
 		return -ENOSYS;
 	}
 	BUG_ON(vmw_is_svga_v3(dev) && (svga_id != SVGA_ID_3));
-	DRM_INFO("Running on SVGA version %d.\n", (svga_id & 0xff));
+	drm_info(&dev->drm,
+		 "Running on SVGA version %d.\n", (svga_id & 0xff));
 	return 0;
 }
 
@@ -785,7 +826,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	bool refuse_dma = false;
 	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
 
-	dev_priv->vmw_chipset = pci_id;
 	dev_priv->drm.dev_private = dev_priv;
 
 	mutex_init(&dev_priv->cmdbuf_mutex);
@@ -793,7 +833,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	spin_lock_init(&dev_priv->resource_lock);
 	spin_lock_init(&dev_priv->hw_lock);
 	spin_lock_init(&dev_priv->waiter_lock);
-	spin_lock_init(&dev_priv->cap_lock);
 	spin_lock_init(&dev_priv->cursor_lock);
 
 	ret = vmw_setup_pci_resources(dev_priv, pci_id);
@@ -830,10 +869,12 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 
 	ret = vmw_dma_select_mode(dev_priv);
 	if (unlikely(ret != 0)) {
-		DRM_INFO("Restricting capabilities since DMA not available.\n");
+		drm_info(&dev_priv->drm,
+			 "Restricting capabilities since DMA not available.\n");
 		refuse_dma = true;
 		if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS)
-			DRM_INFO("Disabling 3D acceleration.\n");
+			drm_info(&dev_priv->drm,
+				 "Disabling 3D acceleration.\n");
 	}
 
 	dev_priv->vram_size = vmw_read(dev_priv, SVGA_REG_VRAM_SIZE);
@@ -879,9 +920,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 			mem_size *= 3;
 
 		dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE;
-		dev_priv->prim_bb_mem =
-			vmw_read(dev_priv,
-				 SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM);
+		dev_priv->max_primary_mem =
+			vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM);
 		dev_priv->max_mob_size =
 			vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE);
 		dev_priv->stdu_max_width =
@@ -900,14 +940,25 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	} else {
 		dev_priv->texture_max_width = 8192;
 		dev_priv->texture_max_height = 8192;
-		dev_priv->prim_bb_mem = dev_priv->vram_size;
+		dev_priv->max_primary_mem = dev_priv->vram_size;
 	}
-
-	vmw_print_capabilities(dev_priv->capabilities);
+	drm_info(&dev_priv->drm,
+		 "Legacy memory limits: VRAM = %llu kB, FIFO = %llu kB, surface = %u kB\n",
+		 (u64)dev_priv->vram_size / 1024,
+		 (u64)dev_priv->fifo_mem_size / 1024,
+		 dev_priv->memory_size / 1024);
+
+	drm_info(&dev_priv->drm,
+		 "MOB limits: max mob size = %u kB, max mob pages = %u\n",
+		 dev_priv->max_mob_size / 1024, dev_priv->max_mob_pages);
+
+	vmw_print_bitmap(&dev_priv->drm, "Capabilities",
+			 dev_priv->capabilities,
+			 cap1_names, ARRAY_SIZE(cap1_names));
 	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER)
-		vmw_print_capabilities2(dev_priv->capabilities2);
-	DRM_INFO("Supports command queues = %d\n",
-		 vmw_cmd_supported((dev_priv)));
+		vmw_print_bitmap(&dev_priv->drm, "Capabilities2",
+				 dev_priv->capabilities2,
+				 cap2_names, ARRAY_SIZE(cap2_names));
 
 	ret = vmw_dma_masks(dev_priv);
 	if (unlikely(ret != 0))
@@ -916,15 +967,16 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	dma_set_max_seg_size(dev_priv->drm.dev, U32_MAX);
 
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
-		DRM_INFO("Max GMR ids is %u\n",
+		drm_info(&dev_priv->drm,
+			 "Max GMR ids is %u\n",
 			 (unsigned)dev_priv->max_gmr_ids);
-		DRM_INFO("Max number of GMR pages is %u\n",
+		drm_info(&dev_priv->drm,
+			 "Max number of GMR pages is %u\n",
 			 (unsigned)dev_priv->max_gmr_pages);
-		DRM_INFO("Max dedicated hypervisor surface memory is %u kiB\n",
-			 (unsigned)dev_priv->memory_size / 1024);
 	}
-	DRM_INFO("Maximum display memory size is %llu kiB\n",
-		 (uint64_t)dev_priv->prim_bb_mem / 1024);
+	drm_info(&dev_priv->drm,
+		 "Maximum display memory size is %llu kiB\n",
+		 (uint64_t)dev_priv->max_primary_mem / 1024);
 
 	/* Need mmio memory to check for fifo pitchlock cap. */
 	if (!(dev_priv->capabilities & SVGA_CAP_DISPLAY_TOPOLOGY) &&
@@ -939,7 +991,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 						&vmw_prime_dmabuf_ops);
 
 	if (unlikely(dev_priv->tdev == NULL)) {
-		DRM_ERROR("Unable to initialize TTM object management.\n");
+		drm_err(&dev_priv->drm,
+			"Unable to initialize TTM object management.\n");
 		ret = -ENOMEM;
 		goto out_err0;
 	}
@@ -947,7 +1000,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK) {
 		ret = vmw_irq_install(&dev_priv->drm, pdev->irq);
 		if (ret != 0) {
-			DRM_ERROR("Failed installing irq: %d\n", ret);
+			drm_err(&dev_priv->drm,
+				"Failed installing irq: %d\n", ret);
 			goto out_no_irq;
 		}
 	}
@@ -968,7 +1022,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 			      dev_priv->map_mode == vmw_dma_alloc_coherent,
 			      false);
 	if (unlikely(ret != 0)) {
-		DRM_ERROR("Failed initializing TTM buffer object driver.\n");
+		drm_err(&dev_priv->drm,
+			"Failed initializing TTM buffer object driver.\n");
 		goto out_no_bdev;
 	}
 
@@ -979,7 +1034,15 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 
 	ret = vmw_vram_manager_init(dev_priv);
 	if (unlikely(ret != 0)) {
-		DRM_ERROR("Failed initializing memory manager for VRAM.\n");
+		drm_err(&dev_priv->drm,
+			"Failed initializing memory manager for VRAM.\n");
+		goto out_no_vram;
+	}
+
+	ret = vmw_devcaps_create(dev_priv);
+	if (unlikely(ret != 0)) {
+		drm_err(&dev_priv->drm,
+			"Failed initializing device caps.\n");
 		goto out_no_vram;
 	}
 
@@ -993,7 +1056,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
 	    refuse_dma ||
 	    vmw_gmrid_man_init(dev_priv, VMW_PL_GMR) != 0) {
-		DRM_INFO("No GMR memory available. "
+		drm_info(&dev_priv->drm,
+			  "No GMR memory available. "
 			 "Graphics memory resources are very limited.\n");
 		dev_priv->has_gmr = false;
 	}
@@ -1002,18 +1066,16 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 		dev_priv->has_mob = true;
 
 		if (vmw_gmrid_man_init(dev_priv, VMW_PL_MOB) != 0) {
-			DRM_INFO("No MOB memory available. "
+			drm_info(&dev_priv->drm,
+				 "No MOB memory available. "
 				 "3D will be disabled.\n");
 			dev_priv->has_mob = false;
 		}
 	}
 
 	if (dev_priv->has_mob && (dev_priv->capabilities & SVGA_CAP_DX)) {
-		spin_lock(&dev_priv->cap_lock);
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DXCONTEXT);
-		if (vmw_read(dev_priv, SVGA_REG_DEV_CAP))
+		if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_DXCONTEXT))
 			dev_priv->sm_type = VMW_SM_4;
-		spin_unlock(&dev_priv->cap_lock);
 	}
 
 	vmw_validation_mem_init_ttm(dev_priv, VMWGFX_VALIDATION_MEM_GRAN);
@@ -1021,15 +1083,11 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	/* SVGA_CAP2_DX2 (DefineGBSurface_v3) is needed for SM4_1 support */
 	if (has_sm4_context(dev_priv) &&
 	    (dev_priv->capabilities2 & SVGA_CAP2_DX2)) {
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_SM41);
-
-		if (vmw_read(dev_priv, SVGA_REG_DEV_CAP))
+		if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_SM41))
 			dev_priv->sm_type = VMW_SM_4_1;
-
 		if (has_sm4_1_context(dev_priv) &&
-		    (dev_priv->capabilities2 & SVGA_CAP2_DX3)) {
-			vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_SM5);
-			if (vmw_read(dev_priv, SVGA_REG_DEV_CAP))
+				(dev_priv->capabilities2 & SVGA_CAP2_DX3)) {
+			if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_SM5))
 				dev_priv->sm_type = VMW_SM_5;
 		}
 	}
@@ -1043,14 +1101,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	if (ret)
 		goto out_no_fifo;
 
-	if (dev_priv->sm_type == VMW_SM_5)
-		DRM_INFO("SM5 support available.\n");
-	if (dev_priv->sm_type == VMW_SM_4_1)
-		DRM_INFO("SM4_1 support available.\n");
-	if (dev_priv->sm_type == VMW_SM_4)
-		DRM_INFO("SM4 support available.\n");
-	DRM_INFO("Running without reservation semaphore\n");
-
+	vmw_print_sm_type(dev_priv);
 	vmw_host_printf("vmwgfx: Module Version: %d.%d.%d (kernel: %s)",
 			VMWGFX_DRIVER_MAJOR, VMWGFX_DRIVER_MINOR,
 			VMWGFX_DRIVER_PATCHLEVEL, UTS_RELEASE);
@@ -1074,6 +1125,7 @@ out_no_kms:
 		vmw_gmrid_man_fini(dev_priv, VMW_PL_MOB);
 	if (dev_priv->has_gmr)
 		vmw_gmrid_man_fini(dev_priv, VMW_PL_GMR);
+	vmw_devcaps_destroy(dev_priv);
 	vmw_vram_manager_fini(dev_priv);
 out_no_vram:
 	ttm_device_fini(&dev_priv->bdev);
@@ -1122,6 +1174,7 @@ static void vmw_driver_unload(struct drm_device *dev)
 	vmw_release_device_early(dev_priv);
 	if (dev_priv->has_mob)
 		vmw_gmrid_man_fini(dev_priv, VMW_PL_MOB);
+	vmw_devcaps_destroy(dev_priv);
 	vmw_vram_manager_fini(dev_priv);
 	ttm_device_fini(&dev_priv->bdev);
 	drm_vma_offset_manager_destroy(&dev_priv->vma_manager);
@@ -1137,6 +1190,8 @@ static void vmw_driver_unload(struct drm_device *dev)
 	for (i = vmw_res_context; i < vmw_res_max; ++i)
 		idr_destroy(&dev_priv->res_idr[i]);
 
+	vmw_mksstat_remove_all(dev_priv);
+
 	pci_release_regions(pdev);
 }
 
@@ -1560,7 +1615,7 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct vmw_private *vmw;
 	int ret;
 
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "svgadrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 5652d982b1ce..a833751099b5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
+ * Copyright 2009-2021 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -54,10 +54,10 @@
 
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20210218"
+#define VMWGFX_DRIVER_DATE "20210722"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 18
-#define VMWGFX_DRIVER_PATCHLEVEL 1
+#define VMWGFX_DRIVER_MINOR 19
+#define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
 #define VMWGFX_MAX_VALIDATIONS 2048
@@ -91,6 +91,9 @@
 #define VMW_RES_FENCE ttm_driver_type3
 #define VMW_RES_SHADER ttm_driver_type4
 
+#define MKSSTAT_CAPACITY_LOG2 5U
+#define MKSSTAT_CAPACITY (1U << MKSSTAT_CAPACITY_LOG2)
+
 struct vmw_fpriv {
 	struct ttm_object_file *tfile;
 	bool gb_aware; /* user-space is guest-backed aware */
@@ -311,7 +314,6 @@ struct vmw_res_cache_entry {
  * enum vmw_dma_map_mode - indicate how to perform TTM page dma mappings.
  */
 enum vmw_dma_map_mode {
-	vmw_dma_phys,           /* Use physical page addresses */
 	vmw_dma_alloc_coherent, /* Use TTM coherent pages */
 	vmw_dma_map_populate,   /* Unmap from DMA just after unpopulate */
 	vmw_dma_map_bind,       /* Unmap from DMA just before unbind */
@@ -356,7 +358,6 @@ struct vmw_piter {
 	unsigned long num_pages;
 	bool (*next)(struct vmw_piter *);
 	dma_addr_t (*dma_address)(struct vmw_piter *);
-	struct page *(*page)(struct vmw_piter *);
 };
 
 /*
@@ -366,7 +367,8 @@ enum vmw_display_unit_type {
 	vmw_du_invalid = 0,
 	vmw_du_legacy,
 	vmw_du_screen_object,
-	vmw_du_screen_target
+	vmw_du_screen_target,
+	vmw_du_max
 };
 
 struct vmw_validation_context;
@@ -486,12 +488,11 @@ struct vmw_private {
 	struct ttm_device bdev;
 
 	struct drm_vma_offset_manager vma_manager;
-	unsigned long pci_id;
-	u32 vmw_chipset;
+	u32 pci_id;
 	resource_size_t io_start;
 	resource_size_t vram_start;
 	resource_size_t vram_size;
-	resource_size_t prim_bb_mem;
+	resource_size_t max_primary_mem;
 	u32 __iomem *rmmio;
 	u32 *fifo_mem;
 	resource_size_t fifo_mem_size;
@@ -513,7 +514,6 @@ struct vmw_private {
 	bool has_gmr;
 	bool has_mob;
 	spinlock_t hw_lock;
-	spinlock_t cap_lock;
 	bool assume_16bpp;
 
 	enum vmw_sm_type sm_type;
@@ -629,6 +629,20 @@ struct vmw_private {
 
 	/* Validation memory reservation */
 	struct vmw_validation_mem vvm;
+
+	uint32 *devcaps;
+
+	/*
+	 * mksGuestStat instance-descriptor and pid arrays
+	 */
+	struct page *mksstat_user_pages[MKSSTAT_CAPACITY];
+	atomic_t mksstat_user_pids[MKSSTAT_CAPACITY];
+
+#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS)
+	struct page *mksstat_kern_pages[MKSSTAT_CAPACITY];
+	u8 mksstat_kern_top_timer[MKSSTAT_CAPACITY];
+	atomic_t mksstat_kern_pids[MKSSTAT_CAPACITY];
+#endif
 };
 
 static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res)
@@ -1073,7 +1087,7 @@ static inline dma_addr_t vmw_piter_dma_addr(struct vmw_piter *viter)
  */
 static inline struct page *vmw_piter_page(struct vmw_piter *viter)
 {
-	return viter->page(viter);
+	return viter->pages[viter->i];
 }
 
 /**
@@ -1281,7 +1295,6 @@ extern struct vmw_cmdbuf_res_manager *
 vmw_context_res_man(struct vmw_resource *ctx);
 extern struct vmw_resource *vmw_context_cotable(struct vmw_resource *ctx,
 						SVGACOTableType cotable_type);
-extern struct list_head *vmw_context_binding_list(struct vmw_resource *ctx);
 struct vmw_ctx_binding_state;
 extern struct vmw_ctx_binding_state *
 vmw_context_binding_state(struct vmw_resource *ctx);
@@ -1502,6 +1515,17 @@ __printf(1, 2) int vmw_host_printf(const char *fmt, ...);
 int vmw_msg_ioctl(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv);
 
+/* Host mksGuestStats -vmwgfx_msg.c: */
+int vmw_mksstat_get_kern_slot(pid_t pid, struct vmw_private *dev_priv);
+
+int vmw_mksstat_reset_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+int vmw_mksstat_remove_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+int vmw_mksstat_remove_all(struct vmw_private *dev_priv);
+
 /* VMW logging */
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index a2b8464b3f56..5f2ffa9de5c8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -32,6 +32,7 @@
 #include <drm/ttm/ttm_placement.h>
 #include "vmwgfx_so.h"
 #include "vmwgfx_binding.h"
+#include "vmwgfx_mksstat.h"
 
 #define VMW_RES_HT_ORDER 12
 
@@ -2364,7 +2365,7 @@ static int vmw_cmd_dx_set_rendertargets(struct vmw_private *dev_priv,
 		sizeof(SVGA3dRenderTargetViewId);
 	int ret;
 
-	if (num_rt_view > SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS) {
+	if (num_rt_view > SVGA3D_DX_MAX_RENDER_TARGETS) {
 		VMW_DEBUG_USER("Invalid DX Rendertarget binding.\n");
 		return -EINVAL;
 	}
@@ -2546,6 +2547,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv,
 
 	so_type = vmw_so_cmd_to_type(header->id);
 	res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
 	cmd = container_of(header, typeof(*cmd), header);
 	ret = vmw_cotable_notify(res, cmd->defined_id);
 
@@ -4406,6 +4409,9 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data,
 	int ret;
 	struct dma_fence *in_fence = NULL;
 
+	MKS_STAT_TIME_DECL(MKSSTAT_KERN_EXECBUF);
+	MKS_STAT_TIME_PUSH(MKSSTAT_KERN_EXECBUF);
+
 	/*
 	 * Extend the ioctl argument while maintaining backwards compatibility:
 	 * We take different code paths depending on the value of arg->version.
@@ -4415,7 +4421,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data,
 	if (unlikely(arg->version > DRM_VMW_EXECBUF_VERSION ||
 		     arg->version == 0)) {
 		VMW_DEBUG_USER("Incorrect execbuf version.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto mksstats_out;
 	}
 
 	switch (arg->version) {
@@ -4435,7 +4442,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data,
 
 		if (!in_fence) {
 			VMW_DEBUG_USER("Cannot get imported fence\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto mksstats_out;
 		}
 
 		ret = vmw_wait_dma_fence(dev_priv->fman, in_fence);
@@ -4458,5 +4466,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data,
 out:
 	if (in_fence)
 		dma_fence_put(in_fence);
+
+mksstats_out:
+	MKS_STAT_TIME_POP(MKSSTAT_KERN_EXECBUF);
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index 28ceb749a733..b2c4af331c9d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -71,8 +71,40 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man,
 
 	if (gman->max_gmr_pages > 0) {
 		gman->used_gmr_pages += (*res)->num_pages;
-		if (unlikely(gman->used_gmr_pages > gman->max_gmr_pages))
-			goto nospace;
+		/*
+		 * Because the graphics memory is a soft limit we can try to
+		 * expand it instead of letting the userspace apps crash.
+		 * We're just going to have a sane limit (half of RAM)
+		 * on the number of MOB's that we create and will try to keep
+		 * the system running until we reach that.
+		 */
+		if (unlikely(gman->used_gmr_pages > gman->max_gmr_pages)) {
+			const unsigned long max_graphics_pages = totalram_pages() / 2;
+			uint32_t new_max_pages = 0;
+
+			DRM_WARN("vmwgfx: mob memory overflow. Consider increasing guest RAM and graphicsMemory.\n");
+			vmw_host_printf("vmwgfx, warning: mob memory overflow. Consider increasing guest RAM and graphicsMemory.\n");
+
+			if (gman->max_gmr_pages > (max_graphics_pages / 2)) {
+				DRM_WARN("vmwgfx: guest requires more than half of RAM for graphics.\n");
+				new_max_pages = max_graphics_pages;
+			} else
+				new_max_pages = gman->max_gmr_pages * 2;
+			if (new_max_pages > gman->max_gmr_pages && new_max_pages >= gman->used_gmr_pages) {
+				DRM_WARN("vmwgfx: increasing guest mob limits to %u kB.\n",
+					 ((new_max_pages) << (PAGE_SHIFT - 10)));
+
+				gman->max_gmr_pages = new_max_pages;
+			} else {
+				char buf[256];
+				snprintf(buf, sizeof(buf),
+					 "vmwgfx, error: guest graphics is out of memory (mob limit at: %ukB).\n",
+					 ((gman->max_gmr_pages) << (PAGE_SHIFT - 10)));
+				vmw_host_printf(buf);
+				DRM_WARN("%s", buf);
+				goto nospace;
+			}
+		}
 	}
 
 	(*res)->start = id;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 4fdacf9924e6..28af34ab6ed6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -26,14 +26,9 @@
  **************************************************************************/
 
 #include "vmwgfx_drv.h"
+#include "vmwgfx_devcaps.h"
 #include <drm/vmwgfx_drm.h>
 #include "vmwgfx_kms.h"
-#include "device_include/svga3d_caps.h"
-
-struct svga_3d_compat_cap {
-	SVGA3dCapsRecordHeader header;
-	SVGA3dCapPair pairs[SVGA3D_DEVCAP_MAX];
-};
 
 int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv)
@@ -63,7 +58,7 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 		param->value = vmw_fifo_caps(dev_priv);
 		break;
 	case DRM_VMW_PARAM_MAX_FB_SIZE:
-		param->value = dev_priv->prim_bb_mem;
+		param->value = dev_priv->max_primary_mem;
 		break;
 	case DRM_VMW_PARAM_FIFO_HW_VERSION:
 	{
@@ -88,16 +83,7 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 			param->value = dev_priv->memory_size;
 		break;
 	case DRM_VMW_PARAM_3D_CAPS_SIZE:
-		if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS) &&
-		    vmw_fp->gb_aware)
-			param->value = SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
-		else if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS)
-			param->value = sizeof(struct svga_3d_compat_cap) +
-				sizeof(uint32_t);
-		else
-			param->value = (SVGA_FIFO_3D_CAPS_LAST -
-					SVGA_FIFO_3D_CAPS + 1) *
-				sizeof(uint32_t);
+		param->value = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware);
 		break;
 	case DRM_VMW_PARAM_MAX_MOB_MEMORY:
 		vmw_fp->gb_aware = true;
@@ -126,55 +112,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-static u32 vmw_mask_legacy_multisample(unsigned int cap, u32 fmt_value)
-{
-	/*
-	 * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
-	 * to check the sample count supported by virtual device. Since there
-	 * never was support for multisample count for backing MOB return 0.
-	 *
-	 * MULTISAMPLE_MASKABLESAMPLES devcap is marked as deprecated by virtual
-	 * device.
-	 */
-	if (cap == SVGA3D_DEVCAP_DEAD5)
-		return 0;
-
-	return fmt_value;
-}
-
-static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce,
-			       size_t size)
-{
-	struct svga_3d_compat_cap *compat_cap =
-		(struct svga_3d_compat_cap *) bounce;
-	unsigned int i;
-	size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs);
-	unsigned int max_size;
-
-	if (size < pair_offset)
-		return -EINVAL;
-
-	max_size = (size - pair_offset) / sizeof(SVGA3dCapPair);
-
-	if (max_size > SVGA3D_DEVCAP_MAX)
-		max_size = SVGA3D_DEVCAP_MAX;
-
-	compat_cap->header.length =
-		(pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32);
-	compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS;
-
-	spin_lock(&dev_priv->cap_lock);
-	for (i = 0; i < max_size; ++i) {
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
-		compat_cap->pairs[i][0] = i;
-		compat_cap->pairs[i][1] = vmw_mask_legacy_multisample
-			(i, vmw_read(dev_priv, SVGA_REG_DEV_CAP));
-	}
-	spin_unlock(&dev_priv->cap_lock);
-
-	return 0;
-}
-
 
 int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv)
@@ -183,11 +120,9 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_get_3d_cap_arg *) data;
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	uint32_t size;
-	u32 *fifo_mem;
 	void __user *buffer = (void __user *)((unsigned long)(arg->buffer));
-	void *bounce;
+	void *bounce = NULL;
 	int ret;
-	bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS);
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
 	if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) {
@@ -195,13 +130,11 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (gb_objects && vmw_fp->gb_aware)
-		size = SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
-	else if (gb_objects)
-		size = sizeof(struct svga_3d_compat_cap) + sizeof(uint32_t);
-	else
-		size = (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) *
-			sizeof(uint32_t);
+	size = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware);
+	if (unlikely(size == 0)) {
+		DRM_ERROR("Failed to figure out the devcaps size (no 3D).\n");
+		return -ENOMEM;
+	}
 
 	if (arg->max_size < size)
 		size = arg->max_size;
@@ -212,29 +145,9 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 
-	if (gb_objects && vmw_fp->gb_aware) {
-		int i, num;
-		uint32_t *bounce32 = (uint32_t *) bounce;
-
-		num = size / sizeof(uint32_t);
-		if (num > SVGA3D_DEVCAP_MAX)
-			num = SVGA3D_DEVCAP_MAX;
-
-		spin_lock(&dev_priv->cap_lock);
-		for (i = 0; i < num; ++i) {
-			vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
-			*bounce32++ = vmw_mask_legacy_multisample
-				(i, vmw_read(dev_priv, SVGA_REG_DEV_CAP));
-		}
-		spin_unlock(&dev_priv->cap_lock);
-	} else if (gb_objects) {
-		ret = vmw_fill_compat_cap(dev_priv, bounce, size);
-		if (unlikely(ret != 0))
-			goto out_err;
-	} else {
-		fifo_mem = dev_priv->fifo_mem;
-		memcpy(bounce, &fifo_mem[SVGA_FIFO_3D_CAPS], size);
-	}
+	ret = vmw_devcaps_copy(dev_priv, vmw_fp->gb_aware, bounce, size);
+	if (unlikely (ret != 0))
+		goto out_err;
 
 	ret = copy_to_user(buffer, bounce, size);
 	if (ret)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
index b9a9b7ddadbd..c5191de365ca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
@@ -25,6 +25,7 @@
  *
  **************************************************************************/
 
+#include <linux/pci.h>
 #include <linux/sched/signal.h>
 
 #include "vmwgfx_drv.h"
@@ -287,21 +288,18 @@ static void vmw_irq_preinstall(struct drm_device *dev)
 void vmw_irq_uninstall(struct drm_device *dev)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	uint32_t status;
 
 	if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK))
 		return;
 
-	if (!dev->irq_enabled)
-		return;
-
 	vmw_write(dev_priv, SVGA_REG_IRQMASK, 0);
 
 	status = vmw_irq_status_read(dev_priv);
 	vmw_irq_status_write(dev_priv, status);
 
-	dev->irq_enabled = false;
-	free_irq(dev->irq, dev);
+	free_irq(pdev->irq, dev);
 }
 
 /**
@@ -313,20 +311,8 @@ void vmw_irq_uninstall(struct drm_device *dev)
  */
 int vmw_irq_install(struct drm_device *dev, int irq)
 {
-	int ret;
-
-	if (dev->irq_enabled)
-		return -EBUSY;
-
 	vmw_irq_preinstall(dev);
 
-	ret = request_threaded_irq(irq, vmw_irq_handler, vmw_thread_fn,
-				   IRQF_SHARED, VMWGFX_DRIVER_NAME, dev);
-	if (ret < 0)
-		return ret;
-
-	dev->irq_enabled = true;
-	dev->irq = irq;
-
-	return ret;
+	return request_threaded_irq(irq, vmw_irq_handler, vmw_thread_fn,
+				    IRQF_SHARED, VMWGFX_DRIVER_NAME, dev);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 220f9fd0d420..74fa41909213 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -100,7 +100,7 @@ static int vmw_cursor_update_bo(struct vmw_private *dev_priv,
 	int ret;
 
 	kmap_offset = 0;
-	kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	kmap_num = PFN_UP(width*height*4);
 
 	ret = ttm_bo_reserve(&bo->base, true, false, NULL);
 	if (unlikely(ret != 0)) {
@@ -1487,7 +1487,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 	 * SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM is not present vram size is
 	 * limit on primary bounding box
 	 */
-	if (pixel_mem > dev_priv->prim_bb_mem) {
+	if (pixel_mem > dev_priv->max_primary_mem) {
 		VMW_DEBUG_KMS("Combined output size too large.\n");
 		return -EINVAL;
 	}
@@ -1497,7 +1497,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 	    !(dev_priv->capabilities & SVGA_CAP_NO_BB_RESTRICTION)) {
 		bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4;
 
-		if (bb_mem > dev_priv->prim_bb_mem) {
+		if (bb_mem > dev_priv->max_primary_mem) {
 			VMW_DEBUG_KMS("Topology is beyond supported limits.\n");
 			return -EINVAL;
 		}
@@ -1793,6 +1793,13 @@ int vmw_kms_init(struct vmw_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	int ret;
+	static const char *display_unit_names[] = {
+		"Invalid",
+		"Legacy",
+		"Screen Object",
+		"Screen Target",
+		"Invalid (max)"
+	};
 
 	drm_mode_config_init(dev);
 	dev->mode_config.funcs = &vmw_kms_funcs;
@@ -1810,6 +1817,9 @@ int vmw_kms_init(struct vmw_private *dev_priv)
 		if (ret) /* Fallback */
 			ret = vmw_kms_ldu_init_display(dev_priv);
 	}
+	BUILD_BUG_ON(ARRAY_SIZE(display_unit_names) != (vmw_du_max + 1));
+	drm_info(&dev_priv->drm, "%s display unit initialized\n",
+		 display_unit_names[dev_priv->active_display_unit]);
 
 	return ret;
 }
@@ -1897,7 +1907,7 @@ bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
 {
 	return ((u64) pitch * (u64) height) < (u64)
 		((dev_priv->active_display_unit == vmw_du_screen_target) ?
-		 dev_priv->prim_bb_mem : dev_priv->vram_size);
+		 dev_priv->max_primary_mem : dev_priv->vram_size);
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index d85c7eab9469..fb58a71c458f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -493,8 +493,7 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 	int i, ret;
 
-	if (dev_priv->ldu_priv) {
-		DRM_INFO("ldu system already on\n");
+	if (unlikely(dev_priv->ldu_priv)) {
 		return -EINVAL;
 	}
 
@@ -527,8 +526,6 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv)
 
 	drm_mode_config_reset(dev);
 
-	DRM_INFO("Legacy Display Unit initialized\n");
-
 	return 0;
 
 err_free:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h b/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h
new file mode 100644
index 000000000000..0509f55f07b4
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/**************************************************************************
+ *
+ * Copyright 2021 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#ifndef _VMWGFX_MKSSTAT_H_
+#define _VMWGFX_MKSSTAT_H_
+
+#include <asm/page.h>
+
+/* Reservation marker for mksstat pid's */
+#define MKSSTAT_PID_RESERVED -1
+
+#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS)
+/*
+ * Kernel-internal mksGuestStat counters. The order of this enum dictates the
+ * order of instantiation of these counters in the mksGuestStat pages.
+ */
+
+typedef enum {
+	MKSSTAT_KERN_EXECBUF, /* vmw_execbuf_ioctl */
+
+	MKSSTAT_KERN_COUNT /* Reserved entry; always last */
+} mksstat_kern_stats_t;
+
+/**
+ * vmw_mksstat_get_kern_pstat: Computes the address of the MKSGuestStatCounterTime
+ * array from the address of the base page.
+ *
+ * @page_addr: Pointer to the base page.
+ * Return: Pointer to the MKSGuestStatCounterTime array.
+ */
+
+static inline void *vmw_mksstat_get_kern_pstat(void *page_addr)
+{
+	return page_addr + PAGE_SIZE * 1;
+}
+
+/**
+ * vmw_mksstat_get_kern_pinfo: Computes the address of the MKSGuestStatInfoEntry
+ * array from the address of the base page.
+ *
+ * @page_addr: Pointer to the base page.
+ * Return: Pointer to the MKSGuestStatInfoEntry array.
+ */
+
+static inline void *vmw_mksstat_get_kern_pinfo(void *page_addr)
+{
+	return page_addr + PAGE_SIZE * 2;
+}
+
+/**
+ * vmw_mksstat_get_kern_pstrs: Computes the address of the mksGuestStat strings
+ * sequence from the address of the base page.
+ *
+ * @page_addr: Pointer to the base page.
+ * Return: Pointer to the mksGuestStat strings sequence.
+ */
+
+static inline void *vmw_mksstat_get_kern_pstrs(void *page_addr)
+{
+	return page_addr + PAGE_SIZE * 3;
+}
+
+/*
+ * MKS_STAT_TIME_DECL/PUSH/POP macros to be used in timer-counted routines.
+ */
+
+struct mksstat_timer_t {
+/* mutable */ mksstat_kern_stats_t old_top;
+	const u64 t0;
+	const int slot;
+};
+
+#define MKS_STAT_TIME_DECL(kern_cntr)                                     \
+	struct mksstat_timer_t _##kern_cntr = {                           \
+		.t0 = rdtsc(),                                            \
+		.slot = vmw_mksstat_get_kern_slot(current->pid, dev_priv) \
+	}
+
+#define MKS_STAT_TIME_PUSH(kern_cntr)                                                               \
+	do {                                                                                        \
+		if (_##kern_cntr.slot >= 0) {                                                       \
+			_##kern_cntr.old_top = dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot]; \
+			dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot] = kern_cntr;            \
+		}                                                                                   \
+	} while (0)
+
+#define MKS_STAT_TIME_POP(kern_cntr)                                                                                                           \
+	do {                                                                                                                                   \
+		if (_##kern_cntr.slot >= 0) {                                                                                                  \
+			const pid_t pid = atomic_cmpxchg(&dev_priv->mksstat_kern_pids[_##kern_cntr.slot], current->pid, MKSSTAT_PID_RESERVED); \
+			dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot] = _##kern_cntr.old_top;                                            \
+			                                                                                                                       \
+			if (pid == current->pid) {                                                                                             \
+				const u64 dt = rdtsc() - _##kern_cntr.t0;                                                                      \
+				MKSGuestStatCounterTime *pstat;                                                                                \
+				                                                                                                               \
+				BUG_ON(!dev_priv->mksstat_kern_pages[_##kern_cntr.slot]);                                                      \
+				                                                                                                               \
+				pstat = vmw_mksstat_get_kern_pstat(page_address(dev_priv->mksstat_kern_pages[_##kern_cntr.slot]));             \
+				                                                                                                               \
+				atomic64_inc(&pstat[kern_cntr].counter.count);                                                                 \
+				atomic64_add(dt, &pstat[kern_cntr].selfCycles);                                                                \
+				atomic64_add(dt, &pstat[kern_cntr].totalCycles);                                                               \
+				                                                                                                               \
+				if (_##kern_cntr.old_top != MKSSTAT_KERN_COUNT)                                                                \
+					atomic64_sub(dt, &pstat[_##kern_cntr.old_top].selfCycles);                                             \
+					                                                                                                       \
+				atomic_set(&dev_priv->mksstat_kern_pids[_##kern_cntr.slot], current->pid);                                     \
+			}                                                                                                                      \
+		}                                                                                                                              \
+	} while (0)
+
+#else
+#define MKS_STAT_TIME_DECL(kern_cntr)
+#define MKS_STAT_TIME_PUSH(kern_cntr)
+#define MKS_STAT_TIME_POP(kern_cntr)
+
+#endif /* IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS */
+
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index f2d625415458..f9394207dd3c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -37,14 +37,14 @@
 
 #ifdef CONFIG_64BIT
 #define VMW_PPN_SIZE 8
-#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PTDEPTH64_0
-#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PTDEPTH64_1
-#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PTDEPTH64_2
+#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PT64_0
+#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PT64_1
+#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PT64_2
 #else
 #define VMW_PPN_SIZE 4
-#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PTDEPTH_0
-#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PTDEPTH_1
-#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PTDEPTH_2
+#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PT_0
+#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PT_1
+#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PT_2
 #endif
 
 /*
@@ -70,20 +70,20 @@ struct vmw_mob {
  * @page_table:     Pointer to a struct vmw_mob holding the page table.
  */
 static const struct vmw_otable pre_dx_tables[] = {
-	{VMWGFX_NUM_MOB * SVGA3D_OTABLE_MOB_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SURFACE * SVGA3D_OTABLE_SURFACE_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_CONTEXT * SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SHADER * SVGA3D_OTABLE_SHADER_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SCREEN_TARGET * SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE,
+	{VMWGFX_NUM_MOB * sizeof(SVGAOTableMobEntry), NULL, true},
+	{VMWGFX_NUM_GB_SURFACE * sizeof(SVGAOTableSurfaceEntry), NULL, true},
+	{VMWGFX_NUM_GB_CONTEXT * sizeof(SVGAOTableContextEntry), NULL, true},
+	{VMWGFX_NUM_GB_SHADER * sizeof(SVGAOTableShaderEntry), NULL, true},
+	{VMWGFX_NUM_GB_SCREEN_TARGET * sizeof(SVGAOTableScreenTargetEntry),
 	 NULL, VMWGFX_ENABLE_SCREEN_TARGET_OTABLE}
 };
 
 static const struct vmw_otable dx_tables[] = {
-	{VMWGFX_NUM_MOB * SVGA3D_OTABLE_MOB_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SURFACE * SVGA3D_OTABLE_SURFACE_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_CONTEXT * SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SHADER * SVGA3D_OTABLE_SHADER_ENTRY_SIZE, NULL, true},
-	{VMWGFX_NUM_GB_SCREEN_TARGET * SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE,
+	{VMWGFX_NUM_MOB * sizeof(SVGAOTableMobEntry), NULL, true},
+	{VMWGFX_NUM_GB_SURFACE * sizeof(SVGAOTableSurfaceEntry), NULL, true},
+	{VMWGFX_NUM_GB_CONTEXT * sizeof(SVGAOTableContextEntry), NULL, true},
+	{VMWGFX_NUM_GB_SHADER * sizeof(SVGAOTableShaderEntry), NULL, true},
+	{VMWGFX_NUM_GB_SCREEN_TARGET * sizeof(SVGAOTableScreenTargetEntry),
 	 NULL, VMWGFX_ENABLE_SCREEN_TARGET_OTABLE},
 	{VMWGFX_NUM_DXCONTEXT * sizeof(SVGAOTableDXContextEntry), NULL, true},
 };
@@ -155,7 +155,7 @@ static int vmw_setup_otable_base(struct vmw_private *dev_priv,
 			goto out_no_populate;
 
 		vmw_mob_pt_setup(mob, iter, otable->size >> PAGE_SHIFT);
-		mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PTDEPTH_1;
+		mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PT_1;
 	}
 
 	cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd));
@@ -256,8 +256,7 @@ static int vmw_otable_batch_setup(struct vmw_private *dev_priv,
 		if (!otables[i].enabled)
 			continue;
 
-		otables[i].size =
-			(otables[i].size + PAGE_SIZE - 1) & PAGE_MASK;
+		otables[i].size = PFN_ALIGN(otables[i].size);
 		bo_size += otables[i].size;
 	}
 
@@ -385,7 +384,7 @@ static unsigned long vmw_mob_calculate_pt_pages(unsigned long data_pages)
 	while (likely(data_size > PAGE_SIZE)) {
 		data_size = DIV_ROUND_UP(data_size, PAGE_SIZE);
 		data_size *= VMW_PPN_SIZE;
-		tot_size += (data_size + PAGE_SIZE - 1) & PAGE_MASK;
+		tot_size += PFN_ALIGN(data_size);
 	}
 
 	return tot_size >> PAGE_SHIFT;
@@ -506,11 +505,13 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob,
 {
 	unsigned long num_pt_pages = 0;
 	struct ttm_buffer_object *bo = mob->pt_bo;
-	struct vmw_piter save_pt_iter;
+	struct vmw_piter save_pt_iter = {0};
 	struct vmw_piter pt_iter;
 	const struct vmw_sg_table *vsgt;
 	int ret;
 
+	BUG_ON(num_data_pages == 0);
+
 	ret = ttm_bo_reserve(bo, false, true, NULL);
 	BUG_ON(ret != 0);
 
@@ -633,7 +634,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv,
 
 		vmw_mob_pt_setup(mob, data_iter, num_data_pages);
 		pt_set_up = true;
-		mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PTDEPTH_1;
+		mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PT_1;
 	}
 
 	vmw_fifo_resource_inc(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 3d08f5700bdb..e50fb82a3030 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -31,10 +31,12 @@
 #include <linux/mem_encrypt.h>
 
 #include <asm/hypervisor.h>
+#include <drm/drm_ioctl.h>
 
 #include "vmwgfx_drv.h"
 #include "vmwgfx_msg_x86.h"
 #include "vmwgfx_msg_arm64.h"
+#include "vmwgfx_mksstat.h"
 
 #define MESSAGE_STATUS_SUCCESS  0x0001
 #define MESSAGE_STATUS_DORECV   0x0002
@@ -56,6 +58,11 @@
 #define VMW_PORT_CMD_RECVSIZE   (MSG_TYPE_RECVSIZE << 16 | VMW_PORT_CMD_MSG)
 #define VMW_PORT_CMD_RECVSTATUS (MSG_TYPE_RECVSTATUS << 16 | VMW_PORT_CMD_MSG)
 
+#define VMW_PORT_CMD_MKS_GUEST_STATS   85
+#define VMW_PORT_CMD_MKSGS_RESET       (0 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS)
+#define VMW_PORT_CMD_MKSGS_ADD_PPN     (1 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS)
+#define VMW_PORT_CMD_MKSGS_REMOVE_PPN  (2 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS)
+
 #define HIGH_WORD(X) ((X & 0xFFFF0000) >> 16)
 
 #define MAX_USER_MSG_LENGTH	PAGE_SIZE
@@ -155,6 +162,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 	/* HB port can't access encrypted memory. */
 	if (hb && !mem_encrypt_active()) {
 		unsigned long bp = channel->cookie_high;
+		u32 channel_id = (channel->channel_id << 16);
 
 		si = (uintptr_t) msg;
 		di = channel->cookie_low;
@@ -162,7 +170,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 		VMW_PORT_HB_OUT(
 			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
 			msg_len, si, di,
-			VMWARE_HYPERVISOR_HB | (channel->channel_id << 16) |
+			VMWARE_HYPERVISOR_HB | channel_id |
 			VMWARE_HYPERVISOR_OUT,
 			VMW_HYPERVISOR_MAGIC, bp,
 			eax, ebx, ecx, edx, si, di);
@@ -210,6 +218,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply,
 	/* HB port can't access encrypted memory */
 	if (hb && !mem_encrypt_active()) {
 		unsigned long bp = channel->cookie_low;
+		u32 channel_id = (channel->channel_id << 16);
 
 		si = channel->cookie_high;
 		di = (uintptr_t) reply;
@@ -217,7 +226,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply,
 		VMW_PORT_HB_IN(
 			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
 			reply_len, si, di,
-			VMWARE_HYPERVISOR_HB | (channel->channel_id << 16),
+			VMWARE_HYPERVISOR_HB | channel_id,
 			VMW_HYPERVISOR_MAGIC, bp,
 			eax, ebx, ecx, edx, si, di);
 
@@ -612,3 +621,569 @@ out_open:
 
 	return -EINVAL;
 }
+
+/**
+ * reset_ppn_array: Resets a PPN64 array to INVALID_PPN64 content
+ *
+ * @arr: Array to reset.
+ * @size: Array length.
+ */
+static inline void reset_ppn_array(PPN64 *arr, size_t size)
+{
+	size_t i;
+
+	BUG_ON(!arr || size == 0);
+
+	for (i = 0; i < size; ++i)
+		arr[i] = INVALID_PPN64;
+}
+
+/**
+ * hypervisor_ppn_reset_all: Removes all mksGuestStat instance descriptors from
+ * the hypervisor. All related pages should be subsequently unpinned or freed.
+ *
+ */
+static inline void hypervisor_ppn_reset_all(void)
+{
+	unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+
+	VMW_PORT(VMW_PORT_CMD_MKSGS_RESET,
+		0, si, di,
+		0,
+		VMW_HYPERVISOR_MAGIC,
+		eax, ebx, ecx, edx, si, di);
+}
+
+/**
+ * hypervisor_ppn_add: Adds a single mksGuestStat instance descriptor to the
+ * hypervisor. Any related userspace pages should be pinned in advance.
+ *
+ * @pfn: Physical page number of the instance descriptor
+ */
+static inline void hypervisor_ppn_add(PPN64 pfn)
+{
+	unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+
+	VMW_PORT(VMW_PORT_CMD_MKSGS_ADD_PPN,
+		(unsigned long)pfn, si, di,
+		0,
+		VMW_HYPERVISOR_MAGIC,
+		eax, ebx, ecx, edx, si, di);
+}
+
+/**
+ * hypervisor_ppn_remove: Removes a single mksGuestStat instance descriptor from
+ * the hypervisor. All related pages should be subsequently unpinned or freed.
+ *
+ * @pfn: Physical page number of the instance descriptor
+ */
+static inline void hypervisor_ppn_remove(PPN64 pfn)
+{
+	unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+
+	VMW_PORT(VMW_PORT_CMD_MKSGS_REMOVE_PPN,
+		(unsigned long)pfn, si, di,
+		0,
+		VMW_HYPERVISOR_MAGIC,
+		eax, ebx, ecx, edx, si, di);
+}
+
+#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS)
+
+/* Order of the total number of pages used for kernel-internal mksGuestStat; at least 2 */
+#define MKSSTAT_KERNEL_PAGES_ORDER 2
+/* Header to the text description of mksGuestStat instance descriptor */
+#define MKSSTAT_KERNEL_DESCRIPTION "vmwgfx"
+
+/* Kernel mksGuestStats counter names and desciptions; same order as enum mksstat_kern_stats_t */
+static const char* const mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
+{
+	{ "vmw_execbuf_ioctl", "vmw_execbuf_ioctl" },
+};
+
+/**
+ * mksstat_init_record: Initializes an MKSGuestStatCounter-based record
+ * for the respective mksGuestStat index.
+ *
+ * @stat_idx: Index of the MKSGuestStatCounter-based mksGuestStat record.
+ * @pstat: Pointer to array of MKSGuestStatCounterTime.
+ * @pinfo: Pointer to array of MKSGuestStatInfoEntry.
+ * @pstrs: Pointer to current end of the name/description sequence.
+ * Return: Pointer to the new end of the names/description sequence.
+ */
+
+static inline char *mksstat_init_record(mksstat_kern_stats_t stat_idx,
+	MKSGuestStatCounterTime *pstat, MKSGuestStatInfoEntry *pinfo, char *pstrs)
+{
+	char *const pstrd = pstrs + strlen(mksstat_kern_name_desc[stat_idx][0]) + 1;
+	strcpy(pstrs, mksstat_kern_name_desc[stat_idx][0]);
+	strcpy(pstrd, mksstat_kern_name_desc[stat_idx][1]);
+
+	pinfo[stat_idx].name.s = pstrs;
+	pinfo[stat_idx].description.s = pstrd;
+	pinfo[stat_idx].flags = MKS_GUEST_STAT_FLAG_NONE;
+	pinfo[stat_idx].stat.counter = (MKSGuestStatCounter *)&pstat[stat_idx];
+
+	return pstrd + strlen(mksstat_kern_name_desc[stat_idx][1]) + 1;
+}
+
+/**
+ * mksstat_init_record_time: Initializes an MKSGuestStatCounterTime-based record
+ * for the respective mksGuestStat index.
+ *
+ * @stat_idx: Index of the MKSGuestStatCounterTime-based mksGuestStat record.
+ * @pstat: Pointer to array of MKSGuestStatCounterTime.
+ * @pinfo: Pointer to array of MKSGuestStatInfoEntry.
+ * @pstrs: Pointer to current end of the name/description sequence.
+ * Return: Pointer to the new end of the names/description sequence.
+ */
+
+static inline char *mksstat_init_record_time(mksstat_kern_stats_t stat_idx,
+	MKSGuestStatCounterTime *pstat, MKSGuestStatInfoEntry *pinfo, char *pstrs)
+{
+	char *const pstrd = pstrs + strlen(mksstat_kern_name_desc[stat_idx][0]) + 1;
+	strcpy(pstrs, mksstat_kern_name_desc[stat_idx][0]);
+	strcpy(pstrd, mksstat_kern_name_desc[stat_idx][1]);
+
+	pinfo[stat_idx].name.s = pstrs;
+	pinfo[stat_idx].description.s = pstrd;
+	pinfo[stat_idx].flags = MKS_GUEST_STAT_FLAG_TIME;
+	pinfo[stat_idx].stat.counterTime = &pstat[stat_idx];
+
+	return pstrd + strlen(mksstat_kern_name_desc[stat_idx][1]) + 1;
+}
+
+/**
+ * mksstat_init_kern_id: Creates a single mksGuestStat instance descriptor and
+ * kernel-internal counters. Adds PFN mapping to the hypervisor.
+ *
+ * Create a single mksGuestStat instance descriptor and corresponding structures
+ * for all kernel-internal counters. The corresponding PFNs are mapped with the
+ * hypervisor.
+ *
+ * @ppage: Output pointer to page containing the instance descriptor.
+ * Return: Zero on success, negative error code on error.
+ */
+
+static int mksstat_init_kern_id(struct page **ppage)
+{
+	MKSGuestStatInstanceDescriptor *pdesc;
+	MKSGuestStatCounterTime *pstat;
+	MKSGuestStatInfoEntry *pinfo;
+	char *pstrs, *pstrs_acc;
+
+	/* Allocate pages for the kernel-internal instance descriptor */
+	struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, MKSSTAT_KERNEL_PAGES_ORDER);
+
+	if (!page)
+		return -ENOMEM;
+
+	pdesc = page_address(page);
+	pstat = vmw_mksstat_get_kern_pstat(pdesc);
+	pinfo = vmw_mksstat_get_kern_pinfo(pdesc);
+	pstrs = vmw_mksstat_get_kern_pstrs(pdesc);
+
+	/* Set up all kernel-internal counters and corresponding structures */
+	pstrs_acc = pstrs;
+	pstrs_acc = mksstat_init_record_time(MKSSTAT_KERN_EXECBUF, pstat, pinfo, pstrs_acc);
+
+	/* Add new counters above, in their order of appearance in mksstat_kern_stats_t */
+
+	BUG_ON(pstrs_acc - pstrs > PAGE_SIZE);
+
+	/* Set up the kernel-internal instance descriptor */
+	pdesc->reservedMBZ = 0;
+	pdesc->statStartVA = (uintptr_t)pstat;
+	pdesc->strsStartVA = (uintptr_t)pstrs;
+	pdesc->statLength = sizeof(*pstat) * MKSSTAT_KERN_COUNT;
+	pdesc->infoLength = sizeof(*pinfo) * MKSSTAT_KERN_COUNT;
+	pdesc->strsLength = pstrs_acc - pstrs;
+	snprintf(pdesc->description, ARRAY_SIZE(pdesc->description) - 1, "%s pid=%d",
+		MKSSTAT_KERNEL_DESCRIPTION, current->pid);
+
+	pdesc->statPPNs[0] = page_to_pfn(virt_to_page(pstat));
+	reset_ppn_array(pdesc->statPPNs + 1, ARRAY_SIZE(pdesc->statPPNs) - 1);
+
+	pdesc->infoPPNs[0] = page_to_pfn(virt_to_page(pinfo));
+	reset_ppn_array(pdesc->infoPPNs + 1, ARRAY_SIZE(pdesc->infoPPNs) - 1);
+
+	pdesc->strsPPNs[0] = page_to_pfn(virt_to_page(pstrs));
+	reset_ppn_array(pdesc->strsPPNs + 1, ARRAY_SIZE(pdesc->strsPPNs) - 1);
+
+	*ppage = page;
+
+	hypervisor_ppn_add((PPN64)page_to_pfn(page));
+
+	return 0;
+}
+
+/**
+ * vmw_mksstat_get_kern_slot: Acquires a slot for a single kernel-internal
+ * mksGuestStat instance descriptor.
+ *
+ * Find a slot for a single kernel-internal mksGuestStat instance descriptor.
+ * In case no such was already present, allocate a new one and set up a kernel-
+ * internal mksGuestStat instance descriptor for the former.
+ *
+ * @pid: Process for which a slot is sought.
+ * @dev_priv: Identifies the drm private device.
+ * Return: Non-negative slot on success, negative error code on error.
+ */
+
+int vmw_mksstat_get_kern_slot(pid_t pid, struct vmw_private *dev_priv)
+{
+	const size_t base = (u32)hash_32(pid, MKSSTAT_CAPACITY_LOG2);
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_kern_pids); ++i) {
+		const size_t slot = (i + base) % ARRAY_SIZE(dev_priv->mksstat_kern_pids);
+
+		/* Check if an instance descriptor for this pid is already present */
+		if (pid == (pid_t)atomic_read(&dev_priv->mksstat_kern_pids[slot]))
+			return (int)slot;
+
+		/* Set up a new instance descriptor for this pid */
+		if (!atomic_cmpxchg(&dev_priv->mksstat_kern_pids[slot], 0, MKSSTAT_PID_RESERVED)) {
+			const int ret = mksstat_init_kern_id(&dev_priv->mksstat_kern_pages[slot]);
+
+			if (!ret) {
+				/* Reset top-timer tracking for this slot */
+				dev_priv->mksstat_kern_top_timer[slot] = MKSSTAT_KERN_COUNT;
+
+				atomic_set(&dev_priv->mksstat_kern_pids[slot], pid);
+				return (int)slot;
+			}
+
+			atomic_set(&dev_priv->mksstat_kern_pids[slot], 0);
+			return ret;
+		}
+	}
+
+	return -ENOSPC;
+}
+
+#endif
+
+/**
+ * vmw_mksstat_cleanup_descriptor: Frees a single userspace-originating
+ * mksGuestStat instance-descriptor page and unpins all related user pages.
+ *
+ * Unpin all user pages realated to this instance descriptor and free
+ * the instance-descriptor page itself.
+ *
+ * @page: Page of the instance descriptor.
+ */
+
+static void vmw_mksstat_cleanup_descriptor(struct page *page)
+{
+	MKSGuestStatInstanceDescriptor *pdesc = page_address(page);
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(pdesc->statPPNs) && pdesc->statPPNs[i] != INVALID_PPN64; ++i)
+		unpin_user_page(pfn_to_page(pdesc->statPPNs[i]));
+
+	for (i = 0; i < ARRAY_SIZE(pdesc->infoPPNs) && pdesc->infoPPNs[i] != INVALID_PPN64; ++i)
+		unpin_user_page(pfn_to_page(pdesc->infoPPNs[i]));
+
+	for (i = 0; i < ARRAY_SIZE(pdesc->strsPPNs) && pdesc->strsPPNs[i] != INVALID_PPN64; ++i)
+		unpin_user_page(pfn_to_page(pdesc->strsPPNs[i]));
+
+	__free_page(page);
+}
+
+/**
+ * vmw_mksstat_remove_all: Resets all mksGuestStat instance descriptors
+ * from the hypervisor.
+ *
+ * Discard all hypervisor PFN mappings, containing active mksGuestState instance
+ * descriptors, unpin the related userspace pages and free the related kernel pages.
+ *
+ * @dev_priv: Identifies the drm private device.
+ * Return: Zero on success, negative error code on error.
+ */
+
+int vmw_mksstat_remove_all(struct vmw_private *dev_priv)
+{
+	int ret = 0;
+	size_t i;
+
+	/* Discard all PFN mappings with the hypervisor */
+	hypervisor_ppn_reset_all();
+
+	/* Discard all userspace-originating instance descriptors and unpin all related pages */
+	for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_user_pids); ++i) {
+		const pid_t pid0 = (pid_t)atomic_read(&dev_priv->mksstat_user_pids[i]);
+
+		if (!pid0)
+			continue;
+
+		if (pid0 != MKSSTAT_PID_RESERVED) {
+			const pid_t pid1 = atomic_cmpxchg(&dev_priv->mksstat_user_pids[i], pid0, MKSSTAT_PID_RESERVED);
+
+			if (!pid1)
+				continue;
+
+			if (pid1 == pid0) {
+				struct page *const page = dev_priv->mksstat_user_pages[i];
+
+				BUG_ON(!page);
+
+				dev_priv->mksstat_user_pages[i] = NULL;
+				atomic_set(&dev_priv->mksstat_user_pids[i], 0);
+
+				vmw_mksstat_cleanup_descriptor(page);
+				continue;
+			}
+		}
+
+		ret = -EAGAIN;
+	}
+
+#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS)
+	/* Discard all kernel-internal instance descriptors and free all related pages */
+	for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_kern_pids); ++i) {
+		const pid_t pid0 = (pid_t)atomic_read(&dev_priv->mksstat_kern_pids[i]);
+
+		if (!pid0)
+			continue;
+
+		if (pid0 != MKSSTAT_PID_RESERVED) {
+			const pid_t pid1 = atomic_cmpxchg(&dev_priv->mksstat_kern_pids[i], pid0, MKSSTAT_PID_RESERVED);
+
+			if (!pid1)
+				continue;
+
+			if (pid1 == pid0) {
+				struct page *const page = dev_priv->mksstat_kern_pages[i];
+
+				BUG_ON(!page);
+
+				dev_priv->mksstat_kern_pages[i] = NULL;
+				atomic_set(&dev_priv->mksstat_kern_pids[i], 0);
+
+				__free_pages(page, MKSSTAT_KERNEL_PAGES_ORDER);
+				continue;
+			}
+		}
+
+		ret = -EAGAIN;
+	}
+
+#endif
+	return ret;
+}
+
+/**
+ * vmw_mksstat_reset_ioctl: Resets all mksGuestStat instance descriptors
+ * from the hypervisor.
+ *
+ * Discard all hypervisor PFN mappings, containing active mksGuestStat instance
+ * descriptors, unpin the related userspace pages and free the related kernel pages.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller; unused.
+ * Return: Zero on success, negative error code on error.
+ */
+
+int vmw_mksstat_reset_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	struct vmw_private *const dev_priv = vmw_priv(dev);
+	return vmw_mksstat_remove_all(dev_priv);
+}
+
+/**
+ * vmw_mksstat_add_ioctl: Creates a single userspace-originating mksGuestStat
+ * instance descriptor and registers that with the hypervisor.
+ *
+ * Create a hypervisor PFN mapping, containing a single mksGuestStat instance
+ * descriptor and pin the corresponding userspace pages.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller; unused.
+ * Return: Zero on success, negative error code on error.
+ */
+
+int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	struct drm_vmw_mksstat_add_arg *arg =
+		(struct drm_vmw_mksstat_add_arg *) data;
+
+	struct vmw_private *const dev_priv = vmw_priv(dev);
+
+	struct page *page;
+	MKSGuestStatInstanceDescriptor *pdesc;
+	const size_t num_pages_stat = PFN_UP(arg->stat_len);
+	const size_t num_pages_info = PFN_UP(arg->info_len);
+	const size_t num_pages_strs = PFN_UP(arg->strs_len);
+	long desc_len;
+	long nr_pinned_stat;
+	long nr_pinned_info;
+	long nr_pinned_strs;
+	struct page *pages_stat[ARRAY_SIZE(pdesc->statPPNs)];
+	struct page *pages_info[ARRAY_SIZE(pdesc->infoPPNs)];
+	struct page *pages_strs[ARRAY_SIZE(pdesc->strsPPNs)];
+	size_t i, slot;
+
+	arg->id = -1;
+
+	if (!arg->stat || !arg->info || !arg->strs)
+		return -EINVAL;
+
+	if (!arg->stat_len || !arg->info_len || !arg->strs_len)
+		return -EINVAL;
+
+	if (!arg->description)
+		return -EINVAL;
+
+	if (num_pages_stat > ARRAY_SIZE(pdesc->statPPNs) ||
+		num_pages_info > ARRAY_SIZE(pdesc->infoPPNs) ||
+		num_pages_strs > ARRAY_SIZE(pdesc->strsPPNs))
+		return -EINVAL;
+
+	/* Find an available slot in the mksGuestStats user array and reserve it */
+	for (slot = 0; slot < ARRAY_SIZE(dev_priv->mksstat_user_pids); ++slot)
+		if (!atomic_cmpxchg(&dev_priv->mksstat_user_pids[slot], 0, MKSSTAT_PID_RESERVED))
+			break;
+
+	if (slot == ARRAY_SIZE(dev_priv->mksstat_user_pids))
+		return -ENOSPC;
+
+	BUG_ON(dev_priv->mksstat_user_pages[slot]);
+
+	/* Allocate a page for the instance descriptor */
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+
+	if (!page) {
+		atomic_set(&dev_priv->mksstat_user_pids[slot], 0);
+		return -ENOMEM;
+	}
+
+	/* Set up the instance descriptor */
+	pdesc = page_address(page);
+
+	pdesc->reservedMBZ = 0;
+	pdesc->statStartVA = arg->stat;
+	pdesc->strsStartVA = arg->strs;
+	pdesc->statLength = arg->stat_len;
+	pdesc->infoLength = arg->info_len;
+	pdesc->strsLength = arg->strs_len;
+	desc_len = strncpy_from_user(pdesc->description, u64_to_user_ptr(arg->description),
+		ARRAY_SIZE(pdesc->description) - 1);
+
+	if (desc_len < 0) {
+		atomic_set(&dev_priv->mksstat_user_pids[slot], 0);
+		return -EFAULT;
+	}
+
+	reset_ppn_array(pdesc->statPPNs, ARRAY_SIZE(pdesc->statPPNs));
+	reset_ppn_array(pdesc->infoPPNs, ARRAY_SIZE(pdesc->infoPPNs));
+	reset_ppn_array(pdesc->strsPPNs, ARRAY_SIZE(pdesc->strsPPNs));
+
+	/* Pin mksGuestStat user pages and store those in the instance descriptor */
+	nr_pinned_stat = pin_user_pages(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat, NULL);
+	if (num_pages_stat != nr_pinned_stat)
+		goto err_pin_stat;
+
+	for (i = 0; i < num_pages_stat; ++i)
+		pdesc->statPPNs[i] = page_to_pfn(pages_stat[i]);
+
+	nr_pinned_info = pin_user_pages(arg->info, num_pages_info, FOLL_LONGTERM, pages_info, NULL);
+	if (num_pages_info != nr_pinned_info)
+		goto err_pin_info;
+
+	for (i = 0; i < num_pages_info; ++i)
+		pdesc->infoPPNs[i] = page_to_pfn(pages_info[i]);
+
+	nr_pinned_strs = pin_user_pages(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs, NULL);
+	if (num_pages_strs != nr_pinned_strs)
+		goto err_pin_strs;
+
+	for (i = 0; i < num_pages_strs; ++i)
+		pdesc->strsPPNs[i] = page_to_pfn(pages_strs[i]);
+
+	/* Send the descriptor to the host via a hypervisor call. The mksGuestStat
+	   pages will remain in use until the user requests a matching remove stats
+	   or a stats reset occurs. */
+	hypervisor_ppn_add((PPN64)page_to_pfn(page));
+
+	dev_priv->mksstat_user_pages[slot] = page;
+	atomic_set(&dev_priv->mksstat_user_pids[slot], task_pgrp_vnr(current));
+
+	arg->id = slot;
+
+	DRM_DEV_INFO(dev->dev, "pid=%d arg.description='%.*s' id=%zu\n", current->pid, (int)desc_len, pdesc->description, slot);
+
+	return 0;
+
+err_pin_strs:
+	if (nr_pinned_strs > 0)
+		unpin_user_pages(pages_strs, nr_pinned_strs);
+
+err_pin_info:
+	if (nr_pinned_info > 0)
+		unpin_user_pages(pages_info, nr_pinned_info);
+
+err_pin_stat:
+	if (nr_pinned_stat > 0)
+		unpin_user_pages(pages_stat, nr_pinned_stat);
+
+	atomic_set(&dev_priv->mksstat_user_pids[slot], 0);
+	__free_page(page);
+	return -ENOMEM;
+}
+
+/**
+ * vmw_mksstat_remove_ioctl: Removes a single userspace-originating mksGuestStat
+ * instance descriptor from the hypervisor.
+ *
+ * Discard a hypervisor PFN mapping, containing a single mksGuestStat instance
+ * descriptor and unpin the corresponding userspace pages.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller; unused.
+ * Return: Zero on success, negative error code on error.
+ */
+
+int vmw_mksstat_remove_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	struct drm_vmw_mksstat_remove_arg *arg =
+		(struct drm_vmw_mksstat_remove_arg *) data;
+
+	struct vmw_private *const dev_priv = vmw_priv(dev);
+
+	const size_t slot = arg->id;
+	pid_t pgid, pid;
+
+	if (slot >= ARRAY_SIZE(dev_priv->mksstat_user_pids))
+		return -EINVAL;
+
+	DRM_DEV_INFO(dev->dev, "pid=%d arg.id=%zu\n", current->pid, slot);
+
+	pgid = task_pgrp_vnr(current);
+	pid = atomic_cmpxchg(&dev_priv->mksstat_user_pids[slot], pgid, MKSSTAT_PID_RESERVED);
+
+	if (!pid)
+		return 0;
+
+	if (pid == pgid) {
+		struct page *const page = dev_priv->mksstat_user_pages[slot];
+
+		BUG_ON(!page);
+
+		dev_priv->mksstat_user_pages[slot] = NULL;
+		atomic_set(&dev_priv->mksstat_user_pids[slot], 0);
+
+		hypervisor_ppn_remove((PPN64)page_to_pfn(page));
+
+		vmw_mksstat_cleanup_descriptor(page);
+		return 0;
+	}
+
+	return -EAGAIN;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 7b45393ad98e..8d1e869cc196 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -114,6 +114,7 @@ static void vmw_resource_release(struct kref *kref)
 	    container_of(kref, struct vmw_resource, kref);
 	struct vmw_private *dev_priv = res->dev_priv;
 	int id;
+	int ret;
 	struct idr *idr = &dev_priv->res_idr[res->func->res_type];
 
 	spin_lock(&dev_priv->resource_lock);
@@ -122,7 +123,8 @@ static void vmw_resource_release(struct kref *kref)
 	if (res->backup) {
 		struct ttm_buffer_object *bo = &res->backup->base;
 
-		ttm_bo_reserve(bo, false, false, NULL);
+		ret = ttm_bo_reserve(bo, false, false, NULL);
+		BUG_ON(ret);
 		if (vmw_resource_mob_attached(res) &&
 		    res->func->unbind != NULL) {
 			struct ttm_validate_buffer val_buf;
@@ -351,8 +353,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 static int vmw_resource_buf_alloc(struct vmw_resource *res,
 				  bool interruptible)
 {
-	unsigned long size =
-		(res->backup_size + PAGE_SIZE - 1) & PAGE_MASK;
+	unsigned long size = PFN_ALIGN(res->backup_size);
 	struct vmw_buffer_object *backup;
 	int ret;
 
@@ -1001,7 +1002,9 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible)
 		if (res->backup) {
 			vbo = res->backup;
 
-			ttm_bo_reserve(&vbo->base, interruptible, false, NULL);
+			ret = ttm_bo_reserve(&vbo->base, interruptible, false, NULL);
+			if (ret)
+				goto out_no_validate;
 			if (!vbo->base.pin_count) {
 				ret = ttm_bo_validate
 					(&vbo->base,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 145430d14219..bd157fb21b45 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -954,8 +954,6 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 	int i, ret;
 
 	if (!(dev_priv->capabilities & SVGA_CAP_SCREEN_OBJECT_2)) {
-		DRM_INFO("Not using screen objects,"
-			 " missing cap SCREEN_OBJECT_2\n");
 		return -ENOSYS;
 	}
 
@@ -972,8 +970,6 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 
 	drm_mode_config_reset(dev);
 
-	DRM_INFO("Screen Objects Display Unit initialized\n");
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index b3c8d2da6f1a..b8dd62529104 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -981,8 +981,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 		goto no_reserve;
 
 	/* Map and copy shader bytecode. */
-	ret = ttm_bo_kmap(&buf->base, 0, PAGE_ALIGN(size) >> PAGE_SHIFT,
-			  &map);
+	ret = ttm_bo_kmap(&buf->base, 0, PFN_UP(size), &map);
 	if (unlikely(ret != 0)) {
 		ttm_bo_unreserve(&buf->base);
 		goto no_reserve;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
index c3a8d6e8380e..9efb4463ce99 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
@@ -539,7 +539,8 @@ const SVGACOTableType vmw_so_cotables[] = {
 	[vmw_so_ds] = SVGA_COTABLE_DEPTHSTENCIL,
 	[vmw_so_rs] = SVGA_COTABLE_RASTERIZERSTATE,
 	[vmw_so_ss] = SVGA_COTABLE_SAMPLER,
-	[vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT
+	[vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT,
+	[vmw_so_max]= SVGA_COTABLE_MAX
 };
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 9e236f9f8a8a..d85310b2608d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -33,7 +33,7 @@
 #include <drm/drm_vblank.h>
 
 #include "vmwgfx_kms.h"
-#include "device_include/svga3d_surfacedefs.h"
+#include "vmw_surface_cache.h"
 
 #define vmw_crtc_to_stdu(x) \
 	container_of(x, struct vmw_screen_target_display_unit, base.crtc)
@@ -1889,14 +1889,13 @@ int vmw_kms_stdu_init_display(struct vmw_private *dev_priv)
 		ret = vmw_stdu_init(dev_priv, i);
 
 		if (unlikely(ret != 0)) {
-			DRM_ERROR("Failed to initialize STDU %d", i);
+			drm_err(&dev_priv->drm,
+				"Failed to initialize STDU %d", i);
 			return ret;
 		}
 	}
 
 	drm_mode_config_reset(dev);
 
-	DRM_INFO("Screen Target Display device initialized\n");
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 0835468bb2ee..5d53a5f9d123 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -31,6 +31,7 @@
 #include "vmwgfx_resource_priv.h"
 #include "vmwgfx_so.h"
 #include "vmwgfx_binding.h"
+#include "vmw_surface_cache.h"
 #include "device_include/svga3d_surfacedefs.h"
 
 #define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
@@ -78,7 +79,7 @@ struct vmw_surface_offset {
  * @boxes: Array of SVGA3dBoxes indicating dirty regions. One per subresource.
  */
 struct vmw_surface_dirty {
-	struct svga3dsurface_cache cache;
+	struct vmw_surface_cache cache;
 	size_t size;
 	u32 num_subres;
 	SVGA3dBox boxes[];
@@ -307,8 +308,8 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf,
 {
 	uint32_t i;
 	struct vmw_surface_dma *cmd = (struct vmw_surface_dma *)cmd_space;
-	const struct svga3d_surface_desc *desc =
-		svga3dsurface_get_desc(srf->metadata.format);
+	const struct SVGA3dSurfaceDesc *desc =
+		vmw_surface_get_desc(srf->metadata.format);
 
 	for (i = 0; i < srf->metadata.num_sizes; ++i) {
 		SVGA3dCmdHeader *header = &cmd->header;
@@ -323,8 +324,7 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf,
 
 		body->guest.ptr = *ptr;
 		body->guest.ptr.offset += cur_offset->bo_offset;
-		body->guest.pitch = svga3dsurface_calculate_pitch(desc,
-								  cur_size);
+		body->guest.pitch = vmw_surface_calculate_pitch(desc, cur_size);
 		body->host.sid = srf->res.id;
 		body->host.face = cur_offset->face;
 		body->host.mipmap = cur_offset->mip;
@@ -342,7 +342,7 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf,
 
 		suffix->suffixSize = sizeof(*suffix);
 		suffix->maximumOffset =
-			svga3dsurface_get_image_buffer_size(desc, cur_size,
+			vmw_surface_get_image_buffer_size(desc, cur_size,
 							    body->guest.pitch);
 		suffix->flags.discard = 0;
 		suffix->flags.unsynchronized = 0;
@@ -432,7 +432,7 @@ static int vmw_legacy_srf_create(struct vmw_resource *res)
 		goto out_no_id;
 	}
 
-	if (unlikely(res->id >= SVGA3D_MAX_SURFACE_IDS)) {
+	if (unlikely(res->id >= SVGA3D_HB_MAX_SURFACE_IDS)) {
 		ret = -EBUSY;
 		goto out_no_fifo;
 	}
@@ -751,7 +751,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	struct vmw_surface_offset *cur_offset;
 	uint32_t num_sizes;
 	uint32_t size;
-	const struct svga3d_surface_desc *desc;
+	const SVGA3dSurfaceDesc *desc;
 
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
@@ -772,8 +772,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 		ttm_round_pot(num_sizes * sizeof(struct drm_vmw_size)) +
 		ttm_round_pot(num_sizes * sizeof(struct vmw_surface_offset));
 
-	desc = svga3dsurface_get_desc(req->format);
-	if (unlikely(desc->block_desc == SVGA3DBLOCKDESC_NONE)) {
+	desc = vmw_surface_get_desc(req->format);
+	if (unlikely(desc->blockDesc == SVGA3DBLOCKDESC_NONE)) {
 		VMW_DEBUG_USER("Invalid format %d for surface creation.\n",
 			       req->format);
 		return -EINVAL;
@@ -833,13 +833,13 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 
 	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) {
 		for (j = 0; j < metadata->mip_levels[i]; ++j) {
-			uint32_t stride = svga3dsurface_calculate_pitch
-				(desc, cur_size);
+			uint32_t stride = vmw_surface_calculate_pitch(
+						  desc, cur_size);
 
 			cur_offset->face = i;
 			cur_offset->mip = j;
 			cur_offset->bo_offset = cur_bo_offset;
-			cur_bo_offset += svga3dsurface_get_image_buffer_size
+			cur_bo_offset += vmw_surface_get_image_buffer_size
 				(desc, cur_size, stride);
 			++cur_offset;
 			++cur_size;
@@ -865,7 +865,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	user_srf->prime.base.shareable = false;
 	user_srf->prime.base.tfile = NULL;
 	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+		user_srf->master = drm_file_get_master(file_priv);
 
 	/**
 	 * From this point, the generic resource management functions
@@ -1534,7 +1534,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 
 	user_srf = container_of(srf, struct vmw_user_surface, srf);
 	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+		user_srf->master = drm_file_get_master(file_priv);
 
 	res = &user_srf->srf.res;
 
@@ -1711,10 +1711,10 @@ out_bad_resource:
  * than partial z slices are dirtied.
  */
 static void vmw_subres_dirty_add(struct vmw_surface_dirty *dirty,
-				 const struct svga3dsurface_loc *loc_start,
-				 const struct svga3dsurface_loc *loc_end)
+				 const struct vmw_surface_loc *loc_start,
+				 const struct vmw_surface_loc *loc_end)
 {
-	const struct svga3dsurface_cache *cache = &dirty->cache;
+	const struct vmw_surface_cache *cache = &dirty->cache;
 	SVGA3dBox *box = &dirty->boxes[loc_start->sub_resource];
 	u32 mip = loc_start->sub_resource % cache->num_mip_levels;
 	const struct drm_vmw_size *size = &cache->mip[mip].size;
@@ -1760,7 +1760,7 @@ static void vmw_subres_dirty_add(struct vmw_surface_dirty *dirty,
  */
 static void vmw_subres_dirty_full(struct vmw_surface_dirty *dirty, u32 subres)
 {
-	const struct svga3dsurface_cache *cache = &dirty->cache;
+	const struct vmw_surface_cache *cache = &dirty->cache;
 	u32 mip = subres % cache->num_mip_levels;
 	const struct drm_vmw_size *size = &cache->mip[mip].size;
 	SVGA3dBox *box = &dirty->boxes[subres];
@@ -1783,15 +1783,15 @@ static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res,
 	struct vmw_surface_dirty *dirty =
 		(struct vmw_surface_dirty *) res->dirty;
 	size_t backup_end = res->backup_offset + res->backup_size;
-	struct svga3dsurface_loc loc1, loc2;
-	const struct svga3dsurface_cache *cache;
+	struct vmw_surface_loc loc1, loc2;
+	const struct vmw_surface_cache *cache;
 
 	start = max_t(size_t, start, res->backup_offset) - res->backup_offset;
 	end = min(end, backup_end) - res->backup_offset;
 	cache = &dirty->cache;
-	svga3dsurface_get_loc(cache, &loc1, start);
-	svga3dsurface_get_loc(cache, &loc2, end - 1);
-	svga3dsurface_inc_loc(cache, &loc2);
+	vmw_surface_get_loc(cache, &loc1, start);
+	vmw_surface_get_loc(cache, &loc2, end - 1);
+	vmw_surface_inc_loc(cache, &loc2);
 
 	if (loc1.sheet != loc2.sheet) {
 		u32 sub_res;
@@ -1811,12 +1811,12 @@ static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res,
 		vmw_subres_dirty_add(dirty, &loc1, &loc2);
 	} else {
 		/* Dirty range covers multiple sub-resources */
-		struct svga3dsurface_loc loc_min, loc_max;
+		struct vmw_surface_loc loc_min, loc_max;
 		u32 sub_res;
 
-		svga3dsurface_max_loc(cache, loc1.sub_resource, &loc_max);
+		vmw_surface_max_loc(cache, loc1.sub_resource, &loc_max);
 		vmw_subres_dirty_add(dirty, &loc1, &loc_max);
-		svga3dsurface_min_loc(cache, loc2.sub_resource - 1, &loc_min);
+		vmw_surface_min_loc(cache, loc2.sub_resource - 1, &loc_min);
 		vmw_subres_dirty_add(dirty, &loc_min, &loc2);
 		for (sub_res = loc1.sub_resource + 1;
 		     sub_res < loc2.sub_resource - 1; ++sub_res)
@@ -1833,7 +1833,7 @@ static void vmw_surface_buf_dirty_range_add(struct vmw_resource *res,
 {
 	struct vmw_surface_dirty *dirty =
 		(struct vmw_surface_dirty *) res->dirty;
-	const struct svga3dsurface_cache *cache = &dirty->cache;
+	const struct vmw_surface_cache *cache = &dirty->cache;
 	size_t backup_end = res->backup_offset + cache->mip_chain_bytes;
 	SVGA3dBox *box = &dirty->boxes[0];
 	u32 box_c2;
@@ -1872,12 +1872,11 @@ static void vmw_surface_dirty_range_add(struct vmw_resource *res, size_t start,
 static int vmw_surface_dirty_sync(struct vmw_resource *res)
 {
 	struct vmw_private *dev_priv = res->dev_priv;
-	bool has_dx = 0;
 	u32 i, num_dirty;
 	struct vmw_surface_dirty *dirty =
 		(struct vmw_surface_dirty *) res->dirty;
 	size_t alloc_size;
-	const struct svga3dsurface_cache *cache = &dirty->cache;
+	const struct vmw_surface_cache *cache = &dirty->cache;
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXUpdateSubResource body;
@@ -1899,7 +1898,7 @@ static int vmw_surface_dirty_sync(struct vmw_resource *res)
 	if (!num_dirty)
 		goto out;
 
-	alloc_size = num_dirty * ((has_dx) ? sizeof(*cmd1) : sizeof(*cmd2));
+	alloc_size = num_dirty * ((has_sm4_context(dev_priv)) ? sizeof(*cmd1) : sizeof(*cmd2));
 	cmd = VMW_CMD_RESERVE(dev_priv, alloc_size);
 	if (!cmd)
 		return -ENOMEM;
@@ -1917,7 +1916,7 @@ static int vmw_surface_dirty_sync(struct vmw_resource *res)
 		 * DX_UPDATE_SUBRESOURCE is aware of array surfaces.
 		 * UPDATE_GB_IMAGE is not.
 		 */
-		if (has_dx) {
+		if (has_sm4_context(dev_priv)) {
 			cmd1->header.id = SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE;
 			cmd1->header.size = sizeof(cmd1->body);
 			cmd1->body.sid = res->id;
@@ -1990,7 +1989,7 @@ static int vmw_surface_dirty_alloc(struct vmw_resource *res)
 	}
 
 	num_samples = max_t(u32, 1, metadata->multisample_count);
-	ret = svga3dsurface_setup_cache(&metadata->base_size, metadata->format,
+	ret = vmw_surface_setup_cache(&metadata->base_size, metadata->format,
 					num_mip, num_layers, num_samples,
 					&dirty->cache);
 	if (ret)
@@ -2081,7 +2080,7 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv,
 	*srf_out = NULL;
 
 	if (req->scanout) {
-		if (!svga3dsurface_is_screen_target_format(req->format)) {
+		if (!vmw_surface_is_screen_target_format(req->format)) {
 			VMW_DEBUG_USER("Invalid Screen Target surface format.");
 			return -EINVAL;
 		}
@@ -2096,10 +2095,10 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv,
 			return -EINVAL;
 		}
 	} else {
-		const struct svga3d_surface_desc *desc =
-			svga3dsurface_get_desc(req->format);
+		const SVGA3dSurfaceDesc *desc =
+			vmw_surface_get_desc(req->format);
 
-		if (desc->block_desc == SVGA3DBLOCKDESC_NONE) {
+		if (desc->blockDesc == SVGA3DBLOCKDESC_NONE) {
 			VMW_DEBUG_USER("Invalid surface format.\n");
 			return -EINVAL;
 		}
@@ -2148,11 +2147,12 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv,
 		sample_count = metadata->multisample_count;
 
 	srf->res.backup_size =
-		svga3dsurface_get_serialized_size_extended(metadata->format,
-							   metadata->base_size,
-							   metadata->mip_levels[0],
-							   num_layers,
-							   sample_count);
+		vmw_surface_get_serialized_size_extended(
+				metadata->format,
+				metadata->base_size,
+				metadata->mip_levels[0],
+				num_layers,
+				sample_count);
 
 	if (metadata->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT)
 		srf->res.backup_size += sizeof(SVGA3dDXSOState);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 0488042fb287..b0973c27e774 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -222,36 +222,6 @@ static bool __vmw_piter_sg_next(struct vmw_piter *viter)
 }
 
 
-/**
- * __vmw_piter_non_sg_page: Helper functions to return a pointer
- * to the current page.
- *
- * @viter: Pointer to the iterator
- *
- * These functions return a pointer to the page currently
- * pointed to by @viter. Functions are selected depending on the
- * current mapping mode.
- */
-static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
-{
-	return viter->pages[viter->i];
-}
-
-/**
- * __vmw_piter_phys_addr: Helper functions to return the DMA
- * address of the current page.
- *
- * @viter: Pointer to the iterator
- *
- * These functions return the DMA address of the page currently
- * pointed to by @viter. Functions are selected depending on the
- * current mapping mode.
- */
-static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter)
-{
-	return page_to_phys(viter->pages[viter->i]);
-}
-
 static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
 {
 	return viter->addrs[viter->i];
@@ -279,13 +249,8 @@ void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
 {
 	viter->i = p_offset - 1;
 	viter->num_pages = vsgt->num_pages;
-	viter->page = &__vmw_piter_non_sg_page;
 	viter->pages = vsgt->pages;
 	switch (vsgt->mode) {
-	case vmw_dma_phys:
-		viter->next = &__vmw_piter_non_sg_next;
-		viter->dma_address = &__vmw_piter_phys_addr;
-		break;
 	case vmw_dma_alloc_coherent:
 		viter->next = &__vmw_piter_non_sg_next;
 		viter->dma_address = &__vmw_piter_dma_addr;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index 8338b1d20f2a..b09094b50c5d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -586,13 +586,13 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr)
 			container_of(entry->base.bo, typeof(*vbo), base);
 
 		if (entry->cpu_blit) {
-			struct ttm_operation_ctx ctx = {
+			struct ttm_operation_ctx ttm_ctx = {
 				.interruptible = intr,
 				.no_wait_gpu = false
 			};
 
 			ret = ttm_bo_validate(entry->base.bo,
-					      &vmw_nonfixed_placement, &ctx);
+					      &vmw_nonfixed_placement, &ttm_ctx);
 		} else {
 			ret = vmw_validation_bo_validate_single
 			(entry->base.bo, intr, entry->as_mob);
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c
index 371202ebe900..cfda74490765 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_kms.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c
@@ -302,7 +302,6 @@ static const struct drm_simple_display_pipe_funcs display_funcs = {
 	.mode_valid = display_mode_valid,
 	.enable = display_enable,
 	.disable = display_disable,
-	.prepare_fb = drm_gem_simple_display_pipe_prepare_fb,
 	.check = display_check,
 	.update = display_update,
 };
diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig
index b52c6cdfc0b8..c3d08269faa9 100644
--- a/drivers/gpu/drm/xlnx/Kconfig
+++ b/drivers/gpu/drm/xlnx/Kconfig
@@ -3,6 +3,8 @@ config DRM_ZYNQMP_DPSUB
 	depends on ARCH_ZYNQMP || COMPILE_TEST
 	depends on COMMON_CLK && DRM && OF
 	depends on DMADEVICES
+	depends on PHY_XILINX_ZYNQMP
+	depends on XILINX_ZYNQMP_DPDMA
 	select DMA_ENGINE
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.c b/drivers/gpu/drm/xlnx/zynqmp_disp.c
index 109d627968ac..ff2b308d8651 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_disp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_disp.c
@@ -91,7 +91,7 @@ struct zynqmp_disp_format {
 };
 
 /**
- * enum zynqmp_disp_id - Layer identifier
+ * enum zynqmp_disp_layer_id - Layer identifier
  * @ZYNQMP_DISP_LAYER_VID: Video layer
  * @ZYNQMP_DISP_LAYER_GFX: Graphics layer
  */
@@ -159,42 +159,16 @@ struct zynqmp_disp_layer {
 };
 
 /**
- * struct zynqmp_disp_blend - Blender
- * @base: Registers I/O base address
- */
-struct zynqmp_disp_blend {
-	void __iomem *base;
-};
-
-/**
- * struct zynqmp_disp_avbuf - Audio/video buffer manager
- * @base: Registers I/O base address
- */
-struct zynqmp_disp_avbuf {
-	void __iomem *base;
-};
-
-/**
- * struct zynqmp_disp_audio - Audio mixer
- * @base: Registers I/O base address
- * @clk: Audio clock
- * @clk_from_ps: True of the audio clock comes from PS, false from PL
- */
-struct zynqmp_disp_audio {
-	void __iomem *base;
-	struct clk *clk;
-	bool clk_from_ps;
-};
-
-/**
  * struct zynqmp_disp - Display controller
  * @dev: Device structure
  * @drm: DRM core
  * @dpsub: Display subsystem
  * @crtc: DRM CRTC
- * @blend: Blender (video rendering pipeline)
- * @avbuf: Audio/video buffer manager
- * @audio: Audio mixer
+ * @blend.base: Register I/O base address for the blender
+ * @avbuf.base: Register I/O base address for the audio/video buffer manager
+ * @audio.base: Registers I/O base address for the audio mixer
+ * @audio.clk: Audio clock
+ * @audio.clk_from_ps: True of the audio clock comes from PS, false from PL
  * @layers: Layers (planes)
  * @event: Pending vblank event request
  * @pclk: Pixel clock
@@ -207,9 +181,17 @@ struct zynqmp_disp {
 
 	struct drm_crtc crtc;
 
-	struct zynqmp_disp_blend blend;
-	struct zynqmp_disp_avbuf avbuf;
-	struct zynqmp_disp_audio audio;
+	struct {
+		void __iomem *base;
+	} blend;
+	struct {
+		void __iomem *base;
+	} avbuf;
+	struct {
+		void __iomem *base;
+		struct clk *clk;
+		bool clk_from_ps;
+	} audio;
 
 	struct zynqmp_disp_layer layers[ZYNQMP_DISP_NUM_LAYERS];
 
@@ -423,51 +405,60 @@ static const struct zynqmp_disp_format avbuf_gfx_fmts[] = {
 	},
 };
 
-static u32 zynqmp_disp_avbuf_read(struct zynqmp_disp_avbuf *avbuf, int reg)
+static u32 zynqmp_disp_avbuf_read(struct zynqmp_disp *disp, int reg)
 {
-	return readl(avbuf->base + reg);
+	return readl(disp->avbuf.base + reg);
 }
 
-static void zynqmp_disp_avbuf_write(struct zynqmp_disp_avbuf *avbuf,
-				    int reg, u32 val)
+static void zynqmp_disp_avbuf_write(struct zynqmp_disp *disp, int reg, u32 val)
 {
-	writel(val, avbuf->base + reg);
+	writel(val, disp->avbuf.base + reg);
+}
+
+static bool zynqmp_disp_layer_is_gfx(const struct zynqmp_disp_layer *layer)
+{
+	return layer->id == ZYNQMP_DISP_LAYER_GFX;
+}
+
+static bool zynqmp_disp_layer_is_video(const struct zynqmp_disp_layer *layer)
+{
+	return layer->id == ZYNQMP_DISP_LAYER_VID;
 }
 
 /**
  * zynqmp_disp_avbuf_set_format - Set the input format for a layer
- * @avbuf: Audio/video buffer manager
- * @layer: The layer ID
+ * @disp: Display controller
+ * @layer: The layer
  * @fmt: The format information
  *
  * Set the video buffer manager format for @layer to @fmt.
  */
-static void zynqmp_disp_avbuf_set_format(struct zynqmp_disp_avbuf *avbuf,
-					 enum zynqmp_disp_layer_id layer,
+static void zynqmp_disp_avbuf_set_format(struct zynqmp_disp *disp,
+					 struct zynqmp_disp_layer *layer,
 					 const struct zynqmp_disp_format *fmt)
 {
 	unsigned int i;
 	u32 val;
 
-	val = zynqmp_disp_avbuf_read(avbuf, ZYNQMP_DISP_AV_BUF_FMT);
-	val &= layer == ZYNQMP_DISP_LAYER_VID
+	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_FMT);
+	val &= zynqmp_disp_layer_is_video(layer)
 	    ? ~ZYNQMP_DISP_AV_BUF_FMT_NL_VID_MASK
 	    : ~ZYNQMP_DISP_AV_BUF_FMT_NL_GFX_MASK;
 	val |= fmt->buf_fmt;
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_FMT, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_FMT, val);
 
 	for (i = 0; i < ZYNQMP_DISP_AV_BUF_NUM_SF; i++) {
-		unsigned int reg = layer == ZYNQMP_DISP_LAYER_VID
+		unsigned int reg = zynqmp_disp_layer_is_video(layer)
 				 ? ZYNQMP_DISP_AV_BUF_VID_COMP_SF(i)
 				 : ZYNQMP_DISP_AV_BUF_GFX_COMP_SF(i);
 
-		zynqmp_disp_avbuf_write(avbuf, reg, fmt->sf[i]);
+		zynqmp_disp_avbuf_write(disp, reg, fmt->sf[i]);
 	}
 }
 
 /**
  * zynqmp_disp_avbuf_set_clocks_sources - Set the clocks sources
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  * @video_from_ps: True if the video clock originates from the PS
  * @audio_from_ps: True if the audio clock originates from the PS
  * @timings_internal: True if video timings are generated internally
@@ -477,7 +468,7 @@ static void zynqmp_disp_avbuf_set_format(struct zynqmp_disp_avbuf *avbuf,
  * generated internally or externally.
  */
 static void
-zynqmp_disp_avbuf_set_clocks_sources(struct zynqmp_disp_avbuf *avbuf,
+zynqmp_disp_avbuf_set_clocks_sources(struct zynqmp_disp *disp,
 				     bool video_from_ps, bool audio_from_ps,
 				     bool timings_internal)
 {
@@ -490,16 +481,16 @@ zynqmp_disp_avbuf_set_clocks_sources(struct zynqmp_disp_avbuf *avbuf,
 	if (timings_internal)
 		val |= ZYNQMP_DISP_AV_BUF_CLK_SRC_VID_INTERNAL_TIMING;
 
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_CLK_SRC, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_CLK_SRC, val);
 }
 
 /**
  * zynqmp_disp_avbuf_enable_channels - Enable buffer channels
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * Enable all (video and audio) buffer channels.
  */
-static void zynqmp_disp_avbuf_enable_channels(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_enable_channels(struct zynqmp_disp *disp)
 {
 	unsigned int i;
 	u32 val;
@@ -509,7 +500,7 @@ static void zynqmp_disp_avbuf_enable_channels(struct zynqmp_disp_avbuf *avbuf)
 	       ZYNQMP_DISP_AV_BUF_CHBUF_BURST_LEN_SHIFT);
 
 	for (i = 0; i < ZYNQMP_DISP_AV_BUF_NUM_VID_GFX_BUFFERS; i++)
-		zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_CHBUF(i),
+		zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_CHBUF(i),
 					val);
 
 	val = ZYNQMP_DISP_AV_BUF_CHBUF_EN |
@@ -517,75 +508,75 @@ static void zynqmp_disp_avbuf_enable_channels(struct zynqmp_disp_avbuf *avbuf)
 	       ZYNQMP_DISP_AV_BUF_CHBUF_BURST_LEN_SHIFT);
 
 	for (; i < ZYNQMP_DISP_AV_BUF_NUM_BUFFERS; i++)
-		zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_CHBUF(i),
+		zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_CHBUF(i),
 					val);
 }
 
 /**
  * zynqmp_disp_avbuf_disable_channels - Disable buffer channels
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * Disable all (video and audio) buffer channels.
  */
-static void zynqmp_disp_avbuf_disable_channels(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_disable_channels(struct zynqmp_disp *disp)
 {
 	unsigned int i;
 
 	for (i = 0; i < ZYNQMP_DISP_AV_BUF_NUM_BUFFERS; i++)
-		zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_CHBUF(i),
+		zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_CHBUF(i),
 					ZYNQMP_DISP_AV_BUF_CHBUF_FLUSH);
 }
 
 /**
  * zynqmp_disp_avbuf_enable_audio - Enable audio
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * Enable all audio buffers with a non-live (memory) source.
  */
-static void zynqmp_disp_avbuf_enable_audio(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_enable_audio(struct zynqmp_disp *disp)
 {
 	u32 val;
 
-	val = zynqmp_disp_avbuf_read(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT);
+	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_OUTPUT);
 	val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_AUD1_MASK;
 	val |= ZYNQMP_DISP_AV_BUF_OUTPUT_AUD1_MEM;
 	val |= ZYNQMP_DISP_AV_BUF_OUTPUT_AUD2_EN;
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
 }
 
 /**
  * zynqmp_disp_avbuf_disable_audio - Disable audio
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * Disable all audio buffers.
  */
-static void zynqmp_disp_avbuf_disable_audio(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_disable_audio(struct zynqmp_disp *disp)
 {
 	u32 val;
 
-	val = zynqmp_disp_avbuf_read(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT);
+	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_OUTPUT);
 	val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_AUD1_MASK;
 	val |= ZYNQMP_DISP_AV_BUF_OUTPUT_AUD1_DISABLE;
 	val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_AUD2_EN;
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
 }
 
 /**
  * zynqmp_disp_avbuf_enable_video - Enable a video layer
- * @avbuf: Audio/video buffer manager
- * @layer: The layer ID
+ * @disp: Display controller
+ * @layer: The layer
  * @mode: Operating mode of layer
  *
  * Enable the video/graphics buffer for @layer.
  */
-static void zynqmp_disp_avbuf_enable_video(struct zynqmp_disp_avbuf *avbuf,
-					   enum zynqmp_disp_layer_id layer,
+static void zynqmp_disp_avbuf_enable_video(struct zynqmp_disp *disp,
+					   struct zynqmp_disp_layer *layer,
 					   enum zynqmp_disp_layer_mode mode)
 {
 	u32 val;
 
-	val = zynqmp_disp_avbuf_read(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT);
-	if (layer == ZYNQMP_DISP_LAYER_VID) {
+	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_OUTPUT);
+	if (zynqmp_disp_layer_is_video(layer)) {
 		val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_MASK;
 		if (mode == ZYNQMP_DISP_LAYER_NONLIVE)
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_MEM;
@@ -599,52 +590,52 @@ static void zynqmp_disp_avbuf_enable_video(struct zynqmp_disp_avbuf *avbuf,
 		else
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_LIVE;
 	}
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
 }
 
 /**
  * zynqmp_disp_avbuf_disable_video - Disable a video layer
- * @avbuf: Audio/video buffer manager
- * @layer: The layer ID
+ * @disp: Display controller
+ * @layer: The layer
  *
  * Disable the video/graphics buffer for @layer.
  */
-static void zynqmp_disp_avbuf_disable_video(struct zynqmp_disp_avbuf *avbuf,
-					    enum zynqmp_disp_layer_id layer)
+static void zynqmp_disp_avbuf_disable_video(struct zynqmp_disp *disp,
+					    struct zynqmp_disp_layer *layer)
 {
 	u32 val;
 
-	val = zynqmp_disp_avbuf_read(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT);
-	if (layer == ZYNQMP_DISP_LAYER_VID) {
+	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_OUTPUT);
+	if (zynqmp_disp_layer_is_video(layer)) {
 		val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_MASK;
 		val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_NONE;
 	} else {
 		val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_MASK;
 		val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_DISABLE;
 	}
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_OUTPUT, val);
 }
 
 /**
  * zynqmp_disp_avbuf_enable - Enable the video pipe
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * De-assert the video pipe reset.
  */
-static void zynqmp_disp_avbuf_enable(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_enable(struct zynqmp_disp *disp)
 {
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_SRST_REG, 0);
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_SRST_REG, 0);
 }
 
 /**
  * zynqmp_disp_avbuf_disable - Disable the video pipe
- * @avbuf: Audio/video buffer manager
+ * @disp: Display controller
  *
  * Assert the video pipe reset.
  */
-static void zynqmp_disp_avbuf_disable(struct zynqmp_disp_avbuf *avbuf)
+static void zynqmp_disp_avbuf_disable(struct zynqmp_disp *disp)
 {
-	zynqmp_disp_avbuf_write(avbuf, ZYNQMP_DISP_AV_BUF_SRST_REG,
+	zynqmp_disp_avbuf_write(disp, ZYNQMP_DISP_AV_BUF_SRST_REG,
 				ZYNQMP_DISP_AV_BUF_SRST_REG_VID_RST);
 }
 
@@ -652,10 +643,9 @@ static void zynqmp_disp_avbuf_disable(struct zynqmp_disp_avbuf *avbuf)
  * Blender (Video Pipeline)
  */
 
-static void zynqmp_disp_blend_write(struct zynqmp_disp_blend *blend,
-				    int reg, u32 val)
+static void zynqmp_disp_blend_write(struct zynqmp_disp *disp, int reg, u32 val)
 {
-	writel(val, blend->base + reg);
+	writel(val, disp->blend.base + reg);
 }
 
 /*
@@ -701,12 +691,12 @@ static const u32 csc_sdtv_to_rgb_offsets[] = {
 
 /**
  * zynqmp_disp_blend_set_output_format - Set the output format of the blender
- * @blend: Blender object
+ * @disp: Display controller
  * @format: Output format
  *
  * Set the output format of the blender to @format.
  */
-static void zynqmp_disp_blend_set_output_format(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_set_output_format(struct zynqmp_disp *disp,
 						enum zynqmp_dpsub_format format)
 {
 	static const unsigned int blend_output_fmts[] = {
@@ -722,7 +712,7 @@ static void zynqmp_disp_blend_set_output_format(struct zynqmp_disp_blend *blend,
 	const u32 *offsets;
 	unsigned int i;
 
-	zynqmp_disp_blend_write(blend, ZYNQMP_DISP_V_BLEND_OUTPUT_VID_FMT, fmt);
+	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_OUTPUT_VID_FMT, fmt);
 	if (fmt == ZYNQMP_DISP_V_BLEND_OUTPUT_VID_FMT_RGB) {
 		coeffs = csc_identity_matrix;
 		offsets = csc_zero_offsets;
@@ -732,19 +722,19 @@ static void zynqmp_disp_blend_set_output_format(struct zynqmp_disp_blend *blend,
 	}
 
 	for (i = 0; i < ZYNQMP_DISP_V_BLEND_NUM_COEFF; i++)
-		zynqmp_disp_blend_write(blend,
+		zynqmp_disp_blend_write(disp,
 					ZYNQMP_DISP_V_BLEND_RGB2YCBCR_COEFF(i),
 					coeffs[i]);
 
 	for (i = 0; i < ZYNQMP_DISP_V_BLEND_NUM_OFFSET; i++)
-		zynqmp_disp_blend_write(blend,
+		zynqmp_disp_blend_write(disp,
 					ZYNQMP_DISP_V_BLEND_OUTCSC_OFFSET(i),
 					offsets[i]);
 }
 
 /**
  * zynqmp_disp_blend_set_bg_color - Set the background color
- * @blend: Blender object
+ * @disp: Display controller
  * @rcr: Red/Cr color component
  * @gy: Green/Y color component
  * @bcb: Blue/Cb color component
@@ -753,31 +743,31 @@ static void zynqmp_disp_blend_set_output_format(struct zynqmp_disp_blend *blend,
  * B or Cr, Y and Cb components respectively depending on the selected output
  * format.
  */
-static void zynqmp_disp_blend_set_bg_color(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_set_bg_color(struct zynqmp_disp *disp,
 					   u32 rcr, u32 gy, u32 bcb)
 {
-	zynqmp_disp_blend_write(blend, ZYNQMP_DISP_V_BLEND_BG_CLR_0, rcr);
-	zynqmp_disp_blend_write(blend, ZYNQMP_DISP_V_BLEND_BG_CLR_1, gy);
-	zynqmp_disp_blend_write(blend, ZYNQMP_DISP_V_BLEND_BG_CLR_2, bcb);
+	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_BG_CLR_0, rcr);
+	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_BG_CLR_1, gy);
+	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_BG_CLR_2, bcb);
 }
 
 /**
  * zynqmp_disp_blend_set_global_alpha - Configure global alpha blending
- * @blend: Blender object
+ * @disp: Display controller
  * @enable: True to enable global alpha blending
  * @alpha: Global alpha value (ignored if @enabled is false)
  */
-static void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp *disp,
 					       bool enable, u32 alpha)
 {
-	zynqmp_disp_blend_write(blend, ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA,
+	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA,
 				ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA_VALUE(alpha) |
 				(enable ? ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA_EN : 0));
 }
 
 /**
  * zynqmp_disp_blend_layer_set_csc - Configure colorspace conversion for layer
- * @blend: Blender object
+ * @disp: Display controller
  * @layer: The layer
  * @coeffs: Colorspace conversion matrix
  * @offsets: Colorspace conversion offsets
@@ -786,7 +776,7 @@ static void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp_blend *blend,
  * Columns of the matrix are automatically swapped based on the input format to
  * handle RGB and YCrCb components permutations.
  */
-static void zynqmp_disp_blend_layer_set_csc(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_layer_set_csc(struct zynqmp_disp *disp,
 					    struct zynqmp_disp_layer *layer,
 					    const u16 *coeffs,
 					    const u32 *offsets)
@@ -807,32 +797,32 @@ static void zynqmp_disp_blend_layer_set_csc(struct zynqmp_disp_blend *blend,
 		}
 	}
 
-	if (layer->id == ZYNQMP_DISP_LAYER_VID)
+	if (zynqmp_disp_layer_is_video(layer))
 		reg = ZYNQMP_DISP_V_BLEND_IN1CSC_COEFF(0);
 	else
 		reg = ZYNQMP_DISP_V_BLEND_IN2CSC_COEFF(0);
 
 	for (i = 0; i < ZYNQMP_DISP_V_BLEND_NUM_COEFF; i += 3, reg += 12) {
-		zynqmp_disp_blend_write(blend, reg + 0, coeffs[i + swap[0]]);
-		zynqmp_disp_blend_write(blend, reg + 4, coeffs[i + swap[1]]);
-		zynqmp_disp_blend_write(blend, reg + 8, coeffs[i + swap[2]]);
+		zynqmp_disp_blend_write(disp, reg + 0, coeffs[i + swap[0]]);
+		zynqmp_disp_blend_write(disp, reg + 4, coeffs[i + swap[1]]);
+		zynqmp_disp_blend_write(disp, reg + 8, coeffs[i + swap[2]]);
 	}
 
-	if (layer->id == ZYNQMP_DISP_LAYER_VID)
+	if (zynqmp_disp_layer_is_video(layer))
 		reg = ZYNQMP_DISP_V_BLEND_IN1CSC_OFFSET(0);
 	else
 		reg = ZYNQMP_DISP_V_BLEND_IN2CSC_OFFSET(0);
 
 	for (i = 0; i < ZYNQMP_DISP_V_BLEND_NUM_OFFSET; i++)
-		zynqmp_disp_blend_write(blend, reg + i * 4, offsets[i]);
+		zynqmp_disp_blend_write(disp, reg + i * 4, offsets[i]);
 }
 
 /**
  * zynqmp_disp_blend_layer_enable - Enable a layer
- * @blend: Blender object
+ * @disp: Display controller
  * @layer: The layer
  */
-static void zynqmp_disp_blend_layer_enable(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_layer_enable(struct zynqmp_disp *disp,
 					   struct zynqmp_disp_layer *layer)
 {
 	const u16 *coeffs;
@@ -844,7 +834,7 @@ static void zynqmp_disp_blend_layer_enable(struct zynqmp_disp_blend *blend,
 	      (layer->drm_fmt->hsub > 1 ?
 	       ZYNQMP_DISP_V_BLEND_LAYER_CONTROL_EN_US : 0);
 
-	zynqmp_disp_blend_write(blend,
+	zynqmp_disp_blend_write(disp,
 				ZYNQMP_DISP_V_BLEND_LAYER_CONTROL(layer->id),
 				val);
 
@@ -856,22 +846,22 @@ static void zynqmp_disp_blend_layer_enable(struct zynqmp_disp_blend *blend,
 		offsets = csc_zero_offsets;
 	}
 
-	zynqmp_disp_blend_layer_set_csc(blend, layer, coeffs, offsets);
+	zynqmp_disp_blend_layer_set_csc(disp, layer, coeffs, offsets);
 }
 
 /**
  * zynqmp_disp_blend_layer_disable - Disable a layer
- * @blend: Blender object
+ * @disp: Display controller
  * @layer: The layer
  */
-static void zynqmp_disp_blend_layer_disable(struct zynqmp_disp_blend *blend,
+static void zynqmp_disp_blend_layer_disable(struct zynqmp_disp *disp,
 					    struct zynqmp_disp_layer *layer)
 {
-	zynqmp_disp_blend_write(blend,
+	zynqmp_disp_blend_write(disp,
 				ZYNQMP_DISP_V_BLEND_LAYER_CONTROL(layer->id),
 				0);
 
-	zynqmp_disp_blend_layer_set_csc(blend, layer, csc_zero_matrix,
+	zynqmp_disp_blend_layer_set_csc(disp, layer, csc_zero_matrix,
 					csc_zero_offsets);
 }
 
@@ -879,57 +869,55 @@ static void zynqmp_disp_blend_layer_disable(struct zynqmp_disp_blend *blend,
  * Audio Mixer
  */
 
-static void zynqmp_disp_audio_write(struct zynqmp_disp_audio *audio,
-				  int reg, u32 val)
+static void zynqmp_disp_audio_write(struct zynqmp_disp *disp, int reg, u32 val)
 {
-	writel(val, audio->base + reg);
+	writel(val, disp->audio.base + reg);
 }
 
 /**
  * zynqmp_disp_audio_enable - Enable the audio mixer
- * @audio: Audio mixer
+ * @disp: Display controller
  *
  * Enable the audio mixer by de-asserting the soft reset. The audio state is set to
  * default values by the reset, set the default mixer volume explicitly.
  */
-static void zynqmp_disp_audio_enable(struct zynqmp_disp_audio *audio)
+static void zynqmp_disp_audio_enable(struct zynqmp_disp *disp)
 {
 	/* Clear the audio soft reset register as it's an non-reset flop. */
-	zynqmp_disp_audio_write(audio, ZYNQMP_DISP_AUD_SOFT_RESET, 0);
-	zynqmp_disp_audio_write(audio, ZYNQMP_DISP_AUD_MIXER_VOLUME,
+	zynqmp_disp_audio_write(disp, ZYNQMP_DISP_AUD_SOFT_RESET, 0);
+	zynqmp_disp_audio_write(disp, ZYNQMP_DISP_AUD_MIXER_VOLUME,
 				ZYNQMP_DISP_AUD_MIXER_VOLUME_NO_SCALE);
 }
 
 /**
  * zynqmp_disp_audio_disable - Disable the audio mixer
- * @audio: Audio mixer
+ * @disp: Display controller
  *
  * Disable the audio mixer by asserting its soft reset.
  */
-static void zynqmp_disp_audio_disable(struct zynqmp_disp_audio *audio)
+static void zynqmp_disp_audio_disable(struct zynqmp_disp *disp)
 {
-	zynqmp_disp_audio_write(audio, ZYNQMP_DISP_AUD_SOFT_RESET,
+	zynqmp_disp_audio_write(disp, ZYNQMP_DISP_AUD_SOFT_RESET,
 				ZYNQMP_DISP_AUD_SOFT_RESET_AUD_SRST);
 }
 
-static void zynqmp_disp_audio_init(struct device *dev,
-				   struct zynqmp_disp_audio *audio)
+static void zynqmp_disp_audio_init(struct zynqmp_disp *disp)
 {
 	/* Try the live PL audio clock. */
-	audio->clk = devm_clk_get(dev, "dp_live_audio_aclk");
-	if (!IS_ERR(audio->clk)) {
-		audio->clk_from_ps = false;
+	disp->audio.clk = devm_clk_get(disp->dev, "dp_live_audio_aclk");
+	if (!IS_ERR(disp->audio.clk)) {
+		disp->audio.clk_from_ps = false;
 		return;
 	}
 
 	/* If the live PL audio clock is not valid, fall back to PS clock. */
-	audio->clk = devm_clk_get(dev, "dp_aud_clk");
-	if (!IS_ERR(audio->clk)) {
-		audio->clk_from_ps = true;
+	disp->audio.clk = devm_clk_get(disp->dev, "dp_aud_clk");
+	if (!IS_ERR(disp->audio.clk)) {
+		disp->audio.clk_from_ps = true;
 		return;
 	}
 
-	dev_err(dev, "audio disabled due to missing clock\n");
+	dev_err(disp->dev, "audio disabled due to missing clock\n");
 }
 
 /* -----------------------------------------------------------------------------
@@ -1025,9 +1013,9 @@ zynqmp_disp_layer_find_format(struct zynqmp_disp_layer *layer,
  */
 static void zynqmp_disp_layer_enable(struct zynqmp_disp_layer *layer)
 {
-	zynqmp_disp_avbuf_enable_video(&layer->disp->avbuf, layer->id,
+	zynqmp_disp_avbuf_enable_video(layer->disp, layer,
 				       ZYNQMP_DISP_LAYER_NONLIVE);
-	zynqmp_disp_blend_layer_enable(&layer->disp->blend, layer);
+	zynqmp_disp_blend_layer_enable(layer->disp, layer);
 
 	layer->mode = ZYNQMP_DISP_LAYER_NONLIVE;
 }
@@ -1046,8 +1034,8 @@ static void zynqmp_disp_layer_disable(struct zynqmp_disp_layer *layer)
 	for (i = 0; i < layer->drm_fmt->num_planes; i++)
 		dmaengine_terminate_sync(layer->dmas[i].chan);
 
-	zynqmp_disp_avbuf_disable_video(&layer->disp->avbuf, layer->id);
-	zynqmp_disp_blend_layer_disable(&layer->disp->blend, layer);
+	zynqmp_disp_avbuf_disable_video(layer->disp, layer);
+	zynqmp_disp_blend_layer_disable(layer->disp, layer);
 }
 
 /**
@@ -1067,8 +1055,7 @@ static void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
 	layer->disp_fmt = zynqmp_disp_layer_find_format(layer, info->format);
 	layer->drm_fmt = info;
 
-	zynqmp_disp_avbuf_set_format(&layer->disp->avbuf, layer->id,
-				     layer->disp_fmt);
+	zynqmp_disp_avbuf_set_format(layer->disp, layer, layer->disp_fmt);
 
 	/*
 	 * Set slave_id for each DMA channel to indicate they're part of a
@@ -1175,6 +1162,10 @@ zynqmp_disp_plane_atomic_disable(struct drm_plane *plane,
 		return;
 
 	zynqmp_disp_layer_disable(layer);
+
+	if (zynqmp_disp_layer_is_gfx(layer))
+		zynqmp_disp_blend_set_global_alpha(layer->disp, false,
+						   plane->state->alpha >> 8);
 }
 
 static void
@@ -1204,6 +1195,10 @@ zynqmp_disp_plane_atomic_update(struct drm_plane *plane,
 
 	zynqmp_disp_layer_update(layer, new_state);
 
+	if (zynqmp_disp_layer_is_gfx(layer))
+		zynqmp_disp_blend_set_global_alpha(layer->disp, true,
+						   plane->state->alpha >> 8);
+
 	/* Enable or re-enable the plane is the format has changed. */
 	if (format_changed)
 		zynqmp_disp_layer_enable(layer);
@@ -1244,8 +1239,8 @@ static int zynqmp_disp_create_planes(struct zynqmp_disp *disp)
 			drm_formats[j] = layer->info->formats[j].drm_fmt;
 
 		/* Graphics layer is primary, and video layer is overlay. */
-		type = i == ZYNQMP_DISP_LAYER_GFX
-		     ? DRM_PLANE_TYPE_PRIMARY : DRM_PLANE_TYPE_OVERLAY;
+		type = zynqmp_disp_layer_is_video(layer)
+		     ? DRM_PLANE_TYPE_OVERLAY : DRM_PLANE_TYPE_PRIMARY;
 		ret = drm_universal_plane_init(disp->drm, &layer->plane, 0,
 					       &zynqmp_disp_plane_funcs,
 					       drm_formats,
@@ -1256,6 +1251,10 @@ static int zynqmp_disp_create_planes(struct zynqmp_disp *disp)
 
 		drm_plane_helper_add(&layer->plane,
 				     &zynqmp_disp_plane_helper_funcs);
+
+		drm_plane_create_zpos_immutable_property(&layer->plane, i);
+		if (zynqmp_disp_layer_is_gfx(layer))
+			drm_plane_create_alpha_property(&layer->plane);
 	}
 
 	return 0;
@@ -1387,14 +1386,14 @@ err:
  */
 static void zynqmp_disp_enable(struct zynqmp_disp *disp)
 {
-	zynqmp_disp_avbuf_enable(&disp->avbuf);
+	zynqmp_disp_avbuf_enable(disp);
 	/* Choose clock source based on the DT clock handle. */
-	zynqmp_disp_avbuf_set_clocks_sources(&disp->avbuf, disp->pclk_from_ps,
+	zynqmp_disp_avbuf_set_clocks_sources(disp, disp->pclk_from_ps,
 					     disp->audio.clk_from_ps, true);
-	zynqmp_disp_avbuf_enable_channels(&disp->avbuf);
-	zynqmp_disp_avbuf_enable_audio(&disp->avbuf);
+	zynqmp_disp_avbuf_enable_channels(disp);
+	zynqmp_disp_avbuf_enable_audio(disp);
 
-	zynqmp_disp_audio_enable(&disp->audio);
+	zynqmp_disp_audio_enable(disp);
 }
 
 /**
@@ -1403,11 +1402,11 @@ static void zynqmp_disp_enable(struct zynqmp_disp *disp)
  */
 static void zynqmp_disp_disable(struct zynqmp_disp *disp)
 {
-	zynqmp_disp_audio_disable(&disp->audio);
+	zynqmp_disp_audio_disable(disp);
 
-	zynqmp_disp_avbuf_disable_audio(&disp->avbuf);
-	zynqmp_disp_avbuf_disable_channels(&disp->avbuf);
-	zynqmp_disp_avbuf_disable(&disp->avbuf);
+	zynqmp_disp_avbuf_disable_audio(disp);
+	zynqmp_disp_avbuf_disable_channels(disp);
+	zynqmp_disp_avbuf_disable(disp);
 }
 
 static inline struct zynqmp_disp *crtc_to_disp(struct drm_crtc *crtc)
@@ -1452,9 +1451,10 @@ zynqmp_disp_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
 	int ret, vrefresh;
 
+	pm_runtime_get_sync(disp->dev);
+
 	zynqmp_disp_crtc_setup_clock(crtc, adjusted_mode);
 
-	pm_runtime_get_sync(disp->dev);
 	ret = clk_prepare_enable(disp->pclk);
 	if (ret) {
 		dev_err(disp->dev, "failed to enable a pixel clock\n");
@@ -1462,10 +1462,8 @@ zynqmp_disp_crtc_atomic_enable(struct drm_crtc *crtc,
 		return;
 	}
 
-	zynqmp_disp_blend_set_output_format(&disp->blend,
-					    ZYNQMP_DPSUB_FORMAT_RGB);
-	zynqmp_disp_blend_set_bg_color(&disp->blend, 0, 0, 0);
-	zynqmp_disp_blend_set_global_alpha(&disp->blend, false, 0);
+	zynqmp_disp_blend_set_output_format(disp, ZYNQMP_DPSUB_FORMAT_RGB);
+	zynqmp_disp_blend_set_bg_color(disp, 0, 0, 0);
 
 	zynqmp_disp_enable(disp);
 
@@ -1674,7 +1672,7 @@ int zynqmp_disp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 		disp->pclk_from_ps = true;
 	}
 
-	zynqmp_disp_audio_init(disp->dev, &disp->audio);
+	zynqmp_disp_audio_init(disp);
 
 	ret = zynqmp_disp_create_layers(disp);
 	if (ret)
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index 82430ca9b913..6f588dc09ba6 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -402,10 +402,6 @@ static int zynqmp_dp_phy_init(struct zynqmp_dp *dp)
 		}
 	}
 
-	ret = zynqmp_dp_reset(dp, false);
-	if (ret < 0)
-		return ret;
-
 	zynqmp_dp_clr(dp, ZYNQMP_DP_PHY_RESET, ZYNQMP_DP_PHY_RESET_ALL_RESET);
 
 	/*
@@ -441,8 +437,6 @@ static void zynqmp_dp_phy_exit(struct zynqmp_dp *dp)
 				ret);
 	}
 
-	zynqmp_dp_reset(dp, true);
-
 	for (i = 0; i < dp->num_lanes; i++) {
 		ret = phy_exit(dp->phy[i]);
 		if (ret)
@@ -1683,9 +1677,13 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 		return PTR_ERR(dp->reset);
 	}
 
+	ret = zynqmp_dp_reset(dp, false);
+	if (ret < 0)
+		return ret;
+
 	ret = zynqmp_dp_phy_probe(dp);
 	if (ret)
-		return ret;
+		goto err_reset;
 
 	/* Initialize the hardware. */
 	zynqmp_dp_write(dp, ZYNQMP_DP_TX_PHY_POWER_DOWN,
@@ -1697,7 +1695,7 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 
 	ret = zynqmp_dp_phy_init(dp);
 	if (ret)
-		return ret;
+		goto err_reset;
 
 	zynqmp_dp_write(dp, ZYNQMP_DP_TRANSMITTER_ENABLE, 1);
 
@@ -1709,15 +1707,18 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 					zynqmp_dp_irq_handler, IRQF_ONESHOT,
 					dev_name(dp->dev), dp);
 	if (ret < 0)
-		goto error;
+		goto err_phy_exit;
 
 	dev_dbg(dp->dev, "ZynqMP DisplayPort Tx probed with %u lanes\n",
 		dp->num_lanes);
 
 	return 0;
 
-error:
+err_phy_exit:
 	zynqmp_dp_phy_exit(dp);
+err_reset:
+	zynqmp_dp_reset(dp, true);
+
 	return ret;
 }
 
@@ -1735,4 +1736,5 @@ void zynqmp_dp_remove(struct zynqmp_dpsub *dpsub)
 	zynqmp_dp_write(dp, ZYNQMP_DP_INT_DS, 0xffffffff);
 
 	zynqmp_dp_phy_exit(dp);
+	zynqmp_dp_reset(dp, true);
 }
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
index 0c1c50271a88..ac37053412a1 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
@@ -111,8 +111,6 @@ static int zynqmp_dpsub_drm_init(struct zynqmp_dpsub *dpsub)
 	if (ret)
 		return ret;
 
-	drm->irq_enabled = 1;
-
 	drm_kms_helper_poll_init(drm);
 
 	/*
diff --git a/drivers/gpu/drm/zte/zx_drm_drv.c b/drivers/gpu/drm/zte/zx_drm_drv.c
index 5506336594e2..064056503ebb 100644
--- a/drivers/gpu/drm/zte/zx_drm_drv.c
+++ b/drivers/gpu/drm/zte/zx_drm_drv.c
@@ -75,12 +75,6 @@ static int zx_drm_bind(struct device *dev)
 		goto out_unbind;
 	}
 
-	/*
-	 * We will manage irq handler on our own.  In this case, irq_enabled
-	 * need to be true for using vblank core support.
-	 */
-	drm->irq_enabled = true;
-
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
 
diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile
index 096017b8789d..d2b6f7de0498 100644
--- a/drivers/gpu/host1x/Makefile
+++ b/drivers/gpu/host1x/Makefile
@@ -9,6 +9,7 @@ host1x-y = \
 	job.o \
 	debug.o \
 	mipi.o \
+	fence.o \
 	hw/host1x01.o \
 	hw/host1x02.o \
 	hw/host1x04.o \
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 6e6ca774f68d..765e5aa64eb6 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -312,10 +312,6 @@ static void update_cdma_locked(struct host1x_cdma *cdma)
 	bool signal = false;
 	struct host1x_job *job, *n;
 
-	/* If CDMA is stopped, queue is cleared and we can return */
-	if (!cdma->running)
-		return;
-
 	/*
 	 * Walk the sync queue, reading the sync point registers as necessary,
 	 * to consume as many sync queue entries as possible without blocking
@@ -324,7 +320,8 @@ static void update_cdma_locked(struct host1x_cdma *cdma)
 		struct host1x_syncpt *sp = job->syncpt;
 
 		/* Check whether this syncpt has completed, and bail if not */
-		if (!host1x_syncpt_is_expired(sp, job->syncpt_end)) {
+		if (!host1x_syncpt_is_expired(sp, job->syncpt_end) &&
+		    !job->cancelled) {
 			/* Start timer on next pending syncpt */
 			if (job->timeout)
 				cdma_start_timer_locked(cdma, job);
@@ -413,8 +410,11 @@ syncpt_incr:
 	else
 		restart_addr = cdma->last_pos;
 
+	if (!job)
+		goto resume;
+
 	/* do CPU increments for the remaining syncpts */
-	if (job) {
+	if (job->syncpt_recovery) {
 		dev_dbg(dev, "%s: perform CPU incr on pending buffers\n",
 			__func__);
 
@@ -433,8 +433,44 @@ syncpt_incr:
 
 		dev_dbg(dev, "%s: finished sync_queue modification\n",
 			__func__);
+	} else {
+		struct host1x_job *failed_job = job;
+
+		host1x_job_dump(dev, job);
+
+		host1x_syncpt_set_locked(job->syncpt);
+		failed_job->cancelled = true;
+
+		list_for_each_entry_continue(job, &cdma->sync_queue, list) {
+			unsigned int i;
+
+			if (job->syncpt != failed_job->syncpt)
+				continue;
+
+			for (i = 0; i < job->num_slots; i++) {
+				unsigned int slot = (job->first_get/8 + i) %
+						    HOST1X_PUSHBUFFER_SLOTS;
+				u32 *mapped = cdma->push_buffer.mapped;
+
+				/*
+				 * Overwrite opcodes with 0 word writes
+				 * to offset 0xbad. This does nothing but
+				 * has a easily detected signature in debug
+				 * traces.
+				 */
+				mapped[2*slot+0] = 0x1bad0000;
+				mapped[2*slot+1] = 0x1bad0000;
+			}
+
+			job->cancelled = true;
+		}
+
+		wmb();
+
+		update_cdma_locked(cdma);
 	}
 
+resume:
 	/* roll back DMAGET and start up channel again */
 	host1x_hw_cdma_resume(host1x, cdma, restart_addr);
 }
@@ -490,6 +526,16 @@ int host1x_cdma_begin(struct host1x_cdma *cdma, struct host1x_job *job)
 
 	mutex_lock(&cdma->lock);
 
+	/*
+	 * Check if syncpoint was locked due to previous job timeout.
+	 * This needs to be done within the cdma lock to avoid a race
+	 * with the timeout handler.
+	 */
+	if (job->syncpt->locked) {
+		mutex_unlock(&cdma->lock);
+		return -EPERM;
+	}
+
 	if (job->timeout) {
 		/* init state on first submit with timeout value */
 		if (!cdma->timeout.initialized) {
diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c
new file mode 100644
index 000000000000..6941add95d0f
--- /dev/null
+++ b/drivers/gpu/host1x/fence.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Syncpoint dma_fence implementation
+ *
+ * Copyright (c) 2020, NVIDIA Corporation.
+ */
+
+#include <linux/dma-fence.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/sync_file.h>
+
+#include "fence.h"
+#include "intr.h"
+#include "syncpt.h"
+
+DEFINE_SPINLOCK(lock);
+
+struct host1x_syncpt_fence {
+	struct dma_fence base;
+
+	atomic_t signaling;
+
+	struct host1x_syncpt *sp;
+	u32 threshold;
+
+	struct host1x_waitlist *waiter;
+	void *waiter_ref;
+
+	struct delayed_work timeout_work;
+};
+
+static const char *host1x_syncpt_fence_get_driver_name(struct dma_fence *f)
+{
+	return "host1x";
+}
+
+static const char *host1x_syncpt_fence_get_timeline_name(struct dma_fence *f)
+{
+	return "syncpoint";
+}
+
+static struct host1x_syncpt_fence *to_host1x_fence(struct dma_fence *f)
+{
+	return container_of(f, struct host1x_syncpt_fence, base);
+}
+
+static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f)
+{
+	struct host1x_syncpt_fence *sf = to_host1x_fence(f);
+	int err;
+
+	if (host1x_syncpt_is_expired(sf->sp, sf->threshold))
+		return false;
+
+	dma_fence_get(f);
+
+	/*
+	 * The dma_fence framework requires the fence driver to keep a
+	 * reference to any fences for which 'enable_signaling' has been
+	 * called (and that have not been signalled).
+	 *
+	 * We provide a userspace API to create arbitrary syncpoint fences,
+	 * so we cannot normally guarantee that all fences get signalled.
+	 * As such, setup a timeout, so that long-lasting fences will get
+	 * reaped eventually.
+	 */
+	schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000));
+
+	err = host1x_intr_add_action(sf->sp->host, sf->sp, sf->threshold,
+				     HOST1X_INTR_ACTION_SIGNAL_FENCE, f,
+				     sf->waiter, &sf->waiter_ref);
+	if (err) {
+		cancel_delayed_work_sync(&sf->timeout_work);
+		dma_fence_put(f);
+		return false;
+	}
+
+	/* intr framework takes ownership of waiter */
+	sf->waiter = NULL;
+
+	/*
+	 * The fence may get signalled at any time after the above call,
+	 * so we need to initialize all state used by signalling
+	 * before it.
+	 */
+
+	return true;
+}
+
+static void host1x_syncpt_fence_release(struct dma_fence *f)
+{
+	struct host1x_syncpt_fence *sf = to_host1x_fence(f);
+
+	if (sf->waiter)
+		kfree(sf->waiter);
+
+	dma_fence_free(f);
+}
+
+const struct dma_fence_ops host1x_syncpt_fence_ops = {
+	.get_driver_name = host1x_syncpt_fence_get_driver_name,
+	.get_timeline_name = host1x_syncpt_fence_get_timeline_name,
+	.enable_signaling = host1x_syncpt_fence_enable_signaling,
+	.release = host1x_syncpt_fence_release,
+};
+
+void host1x_fence_signal(struct host1x_syncpt_fence *f)
+{
+	if (atomic_xchg(&f->signaling, 1))
+		return;
+
+	/*
+	 * Cancel pending timeout work - if it races, it will
+	 * not get 'f->signaling' and return.
+	 */
+	cancel_delayed_work_sync(&f->timeout_work);
+
+	host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, false);
+
+	dma_fence_signal(&f->base);
+	dma_fence_put(&f->base);
+}
+
+static void do_fence_timeout(struct work_struct *work)
+{
+	struct delayed_work *dwork = (struct delayed_work *)work;
+	struct host1x_syncpt_fence *f =
+		container_of(dwork, struct host1x_syncpt_fence, timeout_work);
+
+	if (atomic_xchg(&f->signaling, 1))
+		return;
+
+	/*
+	 * Cancel pending timeout work - if it races, it will
+	 * not get 'f->signaling' and return.
+	 */
+	host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, true);
+
+	dma_fence_set_error(&f->base, -ETIMEDOUT);
+	dma_fence_signal(&f->base);
+	dma_fence_put(&f->base);
+}
+
+struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold)
+{
+	struct host1x_syncpt_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return ERR_PTR(-ENOMEM);
+
+	fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL);
+	if (!fence->waiter)
+		return ERR_PTR(-ENOMEM);
+
+	fence->sp = sp;
+	fence->threshold = threshold;
+
+	dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &lock,
+		       dma_fence_context_alloc(1), 0);
+
+	INIT_DELAYED_WORK(&fence->timeout_work, do_fence_timeout);
+
+	return &fence->base;
+}
+EXPORT_SYMBOL(host1x_fence_create);
diff --git a/drivers/gpu/host1x/fence.h b/drivers/gpu/host1x/fence.h
new file mode 100644
index 000000000000..70c91de82f14
--- /dev/null
+++ b/drivers/gpu/host1x/fence.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020, NVIDIA Corporation.
+ */
+
+#ifndef HOST1X_FENCE_H
+#define HOST1X_FENCE_H
+
+struct host1x_syncpt_fence;
+
+void host1x_fence_signal(struct host1x_syncpt_fence *fence);
+
+#endif
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index d4c28faf27d1..1999780a7203 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -47,39 +47,84 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
 	}
 }
 
-static void submit_gathers(struct host1x_job *job)
+static void submit_wait(struct host1x_cdma *cdma, u32 id, u32 threshold,
+			u32 next_class)
+{
+#if HOST1X_HW >= 2
+	host1x_cdma_push_wide(cdma,
+		host1x_opcode_setclass(
+			HOST1X_CLASS_HOST1X,
+			HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32,
+			/* WAIT_SYNCPT_32 is at SYNCPT_PAYLOAD_32+2 */
+			BIT(0) | BIT(2)
+		),
+		threshold,
+		id,
+		host1x_opcode_setclass(next_class, 0, 0)
+	);
+#else
+	/* TODO add waitchk or use waitbases or other mitigation */
+	host1x_cdma_push(cdma,
+		host1x_opcode_setclass(
+			HOST1X_CLASS_HOST1X,
+			host1x_uclass_wait_syncpt_r(),
+			BIT(0)
+		),
+		host1x_class_host_wait_syncpt(id, threshold)
+	);
+	host1x_cdma_push(cdma,
+		host1x_opcode_setclass(next_class, 0, 0),
+		HOST1X_OPCODE_NOP
+	);
+#endif
+}
+
+static void submit_gathers(struct host1x_job *job, u32 job_syncpt_base)
 {
 	struct host1x_cdma *cdma = &job->channel->cdma;
 #if HOST1X_HW < 6
 	struct device *dev = job->channel->dev;
 #endif
 	unsigned int i;
+	u32 threshold;
 
-	for (i = 0; i < job->num_gathers; i++) {
-		struct host1x_job_gather *g = &job->gathers[i];
-		dma_addr_t addr = g->base + g->offset;
-		u32 op2, op3;
+	for (i = 0; i < job->num_cmds; i++) {
+		struct host1x_job_cmd *cmd = &job->cmds[i];
 
-		op2 = lower_32_bits(addr);
-		op3 = upper_32_bits(addr);
+		if (cmd->is_wait) {
+			if (cmd->wait.relative)
+				threshold = job_syncpt_base + cmd->wait.threshold;
+			else
+				threshold = cmd->wait.threshold;
 
-		trace_write_gather(cdma, g->bo, g->offset, g->words);
+			submit_wait(cdma, cmd->wait.id, threshold, cmd->wait.next_class);
+		} else {
+			struct host1x_job_gather *g = &cmd->gather;
+
+			dma_addr_t addr = g->base + g->offset;
+			u32 op2, op3;
+
+			op2 = lower_32_bits(addr);
+			op3 = upper_32_bits(addr);
 
-		if (op3 != 0) {
+			trace_write_gather(cdma, g->bo, g->offset, g->words);
+
+			if (op3 != 0) {
 #if HOST1X_HW >= 6
-			u32 op1 = host1x_opcode_gather_wide(g->words);
-			u32 op4 = HOST1X_OPCODE_NOP;
+				u32 op1 = host1x_opcode_gather_wide(g->words);
+				u32 op4 = HOST1X_OPCODE_NOP;
 
-			host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
+				host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
 #else
-			dev_err(dev, "invalid gather for push buffer %pad\n",
-				&addr);
-			continue;
+				dev_err(dev, "invalid gather for push buffer %pad\n",
+					&addr);
+				continue;
 #endif
-		} else {
-			u32 op1 = host1x_opcode_gather(g->words);
+			} else {
+				u32 op1 = host1x_opcode_gather(g->words);
 
-			host1x_cdma_push(cdma, op1, op2);
+				host1x_cdma_push(cdma, op1, op2);
+			}
 		}
 	}
 }
@@ -126,7 +171,7 @@ static int channel_submit(struct host1x_job *job)
 	struct host1x *host = dev_get_drvdata(ch->dev->parent);
 
 	trace_host1x_channel_submit(dev_name(ch->dev),
-				    job->num_gathers, job->num_relocs,
+				    job->num_cmds, job->num_relocs,
 				    job->syncpt->id, job->syncpt_incrs);
 
 	/* before error checks, return current max */
@@ -181,7 +226,7 @@ static int channel_submit(struct host1x_job *job)
 				 host1x_opcode_setclass(job->class, 0, 0),
 				 HOST1X_OPCODE_NOP);
 
-	submit_gathers(job);
+	submit_gathers(job, syncval - user_syncpt_incrs);
 
 	/* end CDMA submit & stash pinned hMems into sync queue */
 	host1x_cdma_end(&ch->cdma, job);
@@ -191,7 +236,7 @@ static int channel_submit(struct host1x_job *job)
 	/* schedule a submit complete interrupt */
 	err = host1x_intr_add_action(host, sp, syncval,
 				     HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch,
-				     completed_waiter, NULL);
+				     completed_waiter, &job->waiter);
 	completed_waiter = NULL;
 	WARN(err, "Failed to set submit complete interrupt");
 
diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c
index ceb48229d14b..54e31d81517b 100644
--- a/drivers/gpu/host1x/hw/debug_hw.c
+++ b/drivers/gpu/host1x/hw/debug_hw.c
@@ -156,9 +156,9 @@ static unsigned int show_channel_command(struct output *o, u32 val,
 	}
 }
 
-static void show_gather(struct output *o, phys_addr_t phys_addr,
+static void show_gather(struct output *o, dma_addr_t phys_addr,
 			unsigned int words, struct host1x_cdma *cdma,
-			phys_addr_t pin_addr, u32 *map_addr)
+			dma_addr_t pin_addr, u32 *map_addr)
 {
 	/* Map dmaget cursor to corresponding mem handle */
 	u32 offset = phys_addr - pin_addr;
@@ -176,11 +176,11 @@ static void show_gather(struct output *o, phys_addr_t phys_addr,
 	}
 
 	for (i = 0; i < words; i++) {
-		u32 addr = phys_addr + i * 4;
+		dma_addr_t addr = phys_addr + i * 4;
 		u32 val = *(map_addr + offset / 4 + i);
 
 		if (!data_count) {
-			host1x_debug_output(o, "%08x: %08x: ", addr, val);
+			host1x_debug_output(o, "    %pad: %08x: ", &addr, val);
 			data_count = show_channel_command(o, val, &payload);
 		} else {
 			host1x_debug_cont(o, "%08x%s", val,
@@ -195,23 +195,25 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma)
 	struct push_buffer *pb = &cdma->push_buffer;
 	struct host1x_job *job;
 
-	host1x_debug_output(o, "PUSHBUF at %pad, %u words\n",
-			    &pb->dma, pb->size / 4);
-
-	show_gather(o, pb->dma, pb->size / 4, cdma, pb->dma, pb->mapped);
-
 	list_for_each_entry(job, &cdma->sync_queue, list) {
 		unsigned int i;
 
-		host1x_debug_output(o, "\n%p: JOB, syncpt_id=%d, syncpt_val=%d, first_get=%08x, timeout=%d num_slots=%d, num_handles=%d\n",
-				    job, job->syncpt->id, job->syncpt_end,
-				    job->first_get, job->timeout,
+		host1x_debug_output(o, "JOB, syncpt %u: %u timeout: %u num_slots: %u num_handles: %u\n",
+				    job->syncpt->id, job->syncpt_end, job->timeout,
 				    job->num_slots, job->num_unpins);
 
-		for (i = 0; i < job->num_gathers; i++) {
-			struct host1x_job_gather *g = &job->gathers[i];
+		show_gather(o, pb->dma + job->first_get, job->num_slots * 2, cdma,
+			    pb->dma + job->first_get, pb->mapped + job->first_get);
+
+		for (i = 0; i < job->num_cmds; i++) {
+			struct host1x_job_gather *g;
 			u32 *mapped;
 
+			if (job->cmds[i].is_wait)
+				continue;
+
+			g = &job->cmds[i].gather;
+
 			if (job->gather_copy_mapped)
 				mapped = (u32 *)job->gather_copy_mapped;
 			else
@@ -222,7 +224,7 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma)
 				continue;
 			}
 
-			host1x_debug_output(o, "    GATHER at %pad+%#x, %d words\n",
+			host1x_debug_output(o, "  GATHER at %pad+%#x, %d words\n",
 					    &g->base, g->offset, g->words);
 
 			show_gather(o, g->base + g->offset, g->words, cdma,
diff --git a/drivers/gpu/host1x/hw/debug_hw_1x01.c b/drivers/gpu/host1x/hw/debug_hw_1x01.c
index 02a93305ac7b..85242a59fa6a 100644
--- a/drivers/gpu/host1x/hw/debug_hw_1x01.c
+++ b/drivers/gpu/host1x/hw/debug_hw_1x01.c
@@ -16,10 +16,13 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 					   struct output *o)
 {
 	struct host1x_cdma *cdma = &ch->cdma;
+	dma_addr_t dmastart, dmaend;
 	u32 dmaput, dmaget, dmactrl;
 	u32 cbstat, cbread;
 	u32 val, base, baseval;
 
+	dmastart = host1x_ch_readl(ch, HOST1X_CHANNEL_DMASTART);
+	dmaend = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAEND);
 	dmaput = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAPUT);
 	dmaget = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET);
 	dmactrl = host1x_ch_readl(ch, HOST1X_CHANNEL_DMACTRL);
@@ -56,9 +59,10 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 				    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat),
 				    cbread);
 
-	host1x_debug_output(o, "DMAPUT %08x, DMAGET %08x, DMACTL %08x\n",
+	host1x_debug_output(o, "DMASTART %pad, DMAEND %pad\n", &dmastart, &dmaend);
+	host1x_debug_output(o, "DMAPUT %08x DMAGET %08x DMACTL %08x\n",
 			    dmaput, dmaget, dmactrl);
-	host1x_debug_output(o, "CBREAD %08x, CBSTAT %08x\n", cbread, cbstat);
+	host1x_debug_output(o, "CBREAD %08x CBSTAT %08x\n", cbread, cbstat);
 
 	show_channel_gathers(o, cdma);
 	host1x_debug_output(o, "\n");
diff --git a/drivers/gpu/host1x/hw/debug_hw_1x06.c b/drivers/gpu/host1x/hw/debug_hw_1x06.c
index 6d1b583aa90f..9d0667879a19 100644
--- a/drivers/gpu/host1x/hw/debug_hw_1x06.c
+++ b/drivers/gpu/host1x/hw/debug_hw_1x06.c
@@ -16,10 +16,23 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 					   struct output *o)
 {
 	struct host1x_cdma *cdma = &ch->cdma;
+	dma_addr_t dmastart = 0, dmaend = 0;
 	u32 dmaput, dmaget, dmactrl;
 	u32 offset, class;
 	u32 ch_stat;
 
+#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) && HOST1X_HW >= 6
+	dmastart = host1x_ch_readl(ch, HOST1X_CHANNEL_DMASTART_HI);
+	dmastart <<= 32;
+#endif
+	dmastart |= host1x_ch_readl(ch, HOST1X_CHANNEL_DMASTART);
+
+#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) && HOST1X_HW >= 6
+	dmaend = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAEND_HI);
+	dmaend <<= 32;
+#endif
+	dmaend |= host1x_ch_readl(ch, HOST1X_CHANNEL_DMAEND);
+
 	dmaput = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAPUT);
 	dmaget = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET);
 	dmactrl = host1x_ch_readl(ch, HOST1X_CHANNEL_DMACTRL);
@@ -41,7 +54,8 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 		host1x_debug_output(o, "active class %02x, offset %04x\n",
 				    class, offset);
 
-	host1x_debug_output(o, "DMAPUT %08x, DMAGET %08x, DMACTL %08x\n",
+	host1x_debug_output(o, "DMASTART %pad, DMAEND %pad\n", &dmastart, &dmaend);
+	host1x_debug_output(o, "DMAPUT %08x DMAGET %08x DMACTL %08x\n",
 			    dmaput, dmaget, dmactrl);
 	host1x_debug_output(o, "CHANNELSTAT %02x\n", ch_stat);
 
diff --git a/drivers/gpu/host1x/hw/hw_host1x02_uclass.h b/drivers/gpu/host1x/hw/hw_host1x02_uclass.h
index 4fc51f70496b..0a2ab8f1da6f 100644
--- a/drivers/gpu/host1x/hw/hw_host1x02_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x02_uclass.h
@@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void)
 }
 #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
 	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_load_syncpt_payload_32_r(void)
+{
+	return 0x4e;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \
+	host1x_uclass_load_syncpt_payload_32_r()
+static inline u32 host1x_uclass_wait_syncpt_32_r(void)
+{
+	return 0x50;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_32 \
+	host1x_uclass_wait_syncpt_32_r()
 
 #endif
diff --git a/drivers/gpu/host1x/hw/hw_host1x04_uclass.h b/drivers/gpu/host1x/hw/hw_host1x04_uclass.h
index 9e84a4adca9f..60c692b92955 100644
--- a/drivers/gpu/host1x/hw/hw_host1x04_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x04_uclass.h
@@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void)
 }
 #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
 	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_load_syncpt_payload_32_r(void)
+{
+	return 0x4e;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \
+	host1x_uclass_load_syncpt_payload_32_r()
+static inline u32 host1x_uclass_wait_syncpt_32_r(void)
+{
+	return 0x50;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_32 \
+	host1x_uclass_wait_syncpt_32_r()
 
 #endif
diff --git a/drivers/gpu/host1x/hw/hw_host1x05_uclass.h b/drivers/gpu/host1x/hw/hw_host1x05_uclass.h
index aee5a4e32877..2fcc9a2ad3ef 100644
--- a/drivers/gpu/host1x/hw/hw_host1x05_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x05_uclass.h
@@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void)
 }
 #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
 	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_load_syncpt_payload_32_r(void)
+{
+	return 0x4e;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \
+	host1x_uclass_load_syncpt_payload_32_r()
+static inline u32 host1x_uclass_wait_syncpt_32_r(void)
+{
+	return 0x50;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_32 \
+	host1x_uclass_wait_syncpt_32_r()
 
 #endif
diff --git a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
index c4bacdb7155f..5f831438d19b 100644
--- a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
@@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void)
 }
 #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
 	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_load_syncpt_payload_32_r(void)
+{
+	return 0x4e;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \
+	host1x_uclass_load_syncpt_payload_32_r()
+static inline u32 host1x_uclass_wait_syncpt_32_r(void)
+{
+	return 0x50;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_32 \
+	host1x_uclass_wait_syncpt_32_r()
 
 #endif
diff --git a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
index c74070f3f203..8cd2ef087d5d 100644
--- a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
@@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void)
 }
 #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
 	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_load_syncpt_payload_32_r(void)
+{
+	return 0x4e;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \
+	host1x_uclass_load_syncpt_payload_32_r()
+static inline u32 host1x_uclass_wait_syncpt_32_r(void)
+{
+	return 0x50;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_32 \
+	host1x_uclass_wait_syncpt_32_r()
 
 #endif
diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c
index 6d1f3c0fdbe7..45b6be927ec4 100644
--- a/drivers/gpu/host1x/intr.c
+++ b/drivers/gpu/host1x/intr.c
@@ -13,6 +13,7 @@
 #include <trace/events/host1x.h>
 #include "channel.h"
 #include "dev.h"
+#include "fence.h"
 #include "intr.h"
 
 /* Wait list management */
@@ -121,12 +122,20 @@ static void action_wakeup_interruptible(struct host1x_waitlist *waiter)
 	wake_up_interruptible(wq);
 }
 
+static void action_signal_fence(struct host1x_waitlist *waiter)
+{
+	struct host1x_syncpt_fence *f = waiter->data;
+
+	host1x_fence_signal(f);
+}
+
 typedef void (*action_handler)(struct host1x_waitlist *waiter);
 
 static const action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = {
 	action_submit_complete,
 	action_wakeup,
 	action_wakeup_interruptible,
+	action_signal_fence,
 };
 
 static void run_handlers(struct list_head completed[HOST1X_INTR_ACTION_COUNT])
diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h
index 6ea55e615e3a..e4c346099273 100644
--- a/drivers/gpu/host1x/intr.h
+++ b/drivers/gpu/host1x/intr.h
@@ -33,6 +33,8 @@ enum host1x_intr_action {
 	 */
 	HOST1X_INTR_ACTION_WAKEUP_INTERRUPTIBLE,
 
+	HOST1X_INTR_ACTION_SIGNAL_FENCE,
+
 	HOST1X_INTR_ACTION_COUNT
 };
 
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index adbdc225de8d..0eef6df7c89e 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -24,21 +24,25 @@
 #define HOST1X_WAIT_SYNCPT_OFFSET 0x8
 
 struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
-				    u32 num_cmdbufs, u32 num_relocs)
+				    u32 num_cmdbufs, u32 num_relocs,
+				    bool skip_firewall)
 {
 	struct host1x_job *job = NULL;
 	unsigned int num_unpins = num_relocs;
+	bool enable_firewall;
 	u64 total;
 	void *mem;
 
-	if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+	enable_firewall = IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && !skip_firewall;
+
+	if (!enable_firewall)
 		num_unpins += num_cmdbufs;
 
 	/* Check that we're not going to overflow */
 	total = sizeof(struct host1x_job) +
 		(u64)num_relocs * sizeof(struct host1x_reloc) +
 		(u64)num_unpins * sizeof(struct host1x_job_unpin_data) +
-		(u64)num_cmdbufs * sizeof(struct host1x_job_gather) +
+		(u64)num_cmdbufs * sizeof(struct host1x_job_cmd) +
 		(u64)num_unpins * sizeof(dma_addr_t) +
 		(u64)num_unpins * sizeof(u32 *);
 	if (total > ULONG_MAX)
@@ -48,6 +52,8 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
 	if (!job)
 		return NULL;
 
+	job->enable_firewall = enable_firewall;
+
 	kref_init(&job->ref);
 	job->channel = ch;
 
@@ -57,8 +63,8 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
 	mem += num_relocs * sizeof(struct host1x_reloc);
 	job->unpins = num_unpins ? mem : NULL;
 	mem += num_unpins * sizeof(struct host1x_job_unpin_data);
-	job->gathers = num_cmdbufs ? mem : NULL;
-	mem += num_cmdbufs * sizeof(struct host1x_job_gather);
+	job->cmds = num_cmdbufs ? mem : NULL;
+	mem += num_cmdbufs * sizeof(struct host1x_job_cmd);
 	job->addr_phys = num_unpins ? mem : NULL;
 
 	job->reloc_addr_phys = job->addr_phys;
@@ -79,6 +85,13 @@ static void job_free(struct kref *ref)
 {
 	struct host1x_job *job = container_of(ref, struct host1x_job, ref);
 
+	if (job->release)
+		job->release(job);
+
+	if (job->waiter)
+		host1x_intr_put_ref(job->syncpt->host, job->syncpt->id,
+				    job->waiter, false);
+
 	if (job->syncpt)
 		host1x_syncpt_put(job->syncpt);
 
@@ -94,22 +107,38 @@ EXPORT_SYMBOL(host1x_job_put);
 void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo,
 			   unsigned int words, unsigned int offset)
 {
-	struct host1x_job_gather *gather = &job->gathers[job->num_gathers];
+	struct host1x_job_gather *gather = &job->cmds[job->num_cmds].gather;
 
 	gather->words = words;
 	gather->bo = bo;
 	gather->offset = offset;
 
-	job->num_gathers++;
+	job->num_cmds++;
 }
 EXPORT_SYMBOL(host1x_job_add_gather);
 
+void host1x_job_add_wait(struct host1x_job *job, u32 id, u32 thresh,
+			 bool relative, u32 next_class)
+{
+	struct host1x_job_cmd *cmd = &job->cmds[job->num_cmds];
+
+	cmd->is_wait = true;
+	cmd->wait.id = id;
+	cmd->wait.threshold = thresh;
+	cmd->wait.next_class = next_class;
+	cmd->wait.relative = relative;
+
+	job->num_cmds++;
+}
+EXPORT_SYMBOL(host1x_job_add_wait);
+
 static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 {
 	struct host1x_client *client = job->client;
 	struct device *dev = client->dev;
 	struct host1x_job_gather *g;
 	struct iommu_domain *domain;
+	struct sg_table *sgt;
 	unsigned int i;
 	int err;
 
@@ -119,7 +148,6 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 	for (i = 0; i < job->num_relocs; i++) {
 		struct host1x_reloc *reloc = &job->relocs[i];
 		dma_addr_t phys_addr, *phys;
-		struct sg_table *sgt;
 
 		reloc->target.bo = host1x_bo_get(reloc->target.bo);
 		if (!reloc->target.bo) {
@@ -192,20 +220,23 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 	 * We will copy gathers BO content later, so there is no need to
 	 * hold and pin them.
 	 */
-	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+	if (job->enable_firewall)
 		return 0;
 
-	for (i = 0; i < job->num_gathers; i++) {
+	for (i = 0; i < job->num_cmds; i++) {
 		size_t gather_size = 0;
 		struct scatterlist *sg;
-		struct sg_table *sgt;
 		dma_addr_t phys_addr;
 		unsigned long shift;
 		struct iova *alloc;
 		dma_addr_t *phys;
 		unsigned int j;
 
-		g = &job->gathers[i];
+		if (job->cmds[i].is_wait)
+			continue;
+
+		g = &job->cmds[i].gather;
+
 		g->bo = host1x_bo_get(g->bo);
 		if (!g->bo) {
 			err = -EINVAL;
@@ -296,7 +327,7 @@ static int do_relocs(struct host1x_job *job, struct host1x_job_gather *g)
 		if (cmdbuf != reloc->cmdbuf.bo)
 			continue;
 
-		if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) {
+		if (job->enable_firewall) {
 			target = (u32 *)job->gather_copy_mapped +
 					reloc->cmdbuf.offset / sizeof(u32) +
 						g->offset / sizeof(u32);
@@ -538,8 +569,13 @@ static inline int copy_gathers(struct device *host, struct host1x_job *job,
 	fw.num_relocs = job->num_relocs;
 	fw.class = job->class;
 
-	for (i = 0; i < job->num_gathers; i++) {
-		struct host1x_job_gather *g = &job->gathers[i];
+	for (i = 0; i < job->num_cmds; i++) {
+		struct host1x_job_gather *g;
+
+		if (job->cmds[i].is_wait)
+			continue;
+
+		g = &job->cmds[i].gather;
 
 		size += g->words * sizeof(u32);
 	}
@@ -561,10 +597,14 @@ static inline int copy_gathers(struct device *host, struct host1x_job *job,
 
 	job->gather_copy_size = size;
 
-	for (i = 0; i < job->num_gathers; i++) {
-		struct host1x_job_gather *g = &job->gathers[i];
+	for (i = 0; i < job->num_cmds; i++) {
+		struct host1x_job_gather *g;
 		void *gather;
 
+		if (job->cmds[i].is_wait)
+			continue;
+		g = &job->cmds[i].gather;
+
 		/* Copy the gather */
 		gather = host1x_bo_mmap(g->bo);
 		memcpy(job->gather_copy_mapped + offset, gather + g->offset,
@@ -600,28 +640,33 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev)
 	if (err)
 		goto out;
 
-	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) {
+	if (job->enable_firewall) {
 		err = copy_gathers(host->dev, job, dev);
 		if (err)
 			goto out;
 	}
 
 	/* patch gathers */
-	for (i = 0; i < job->num_gathers; i++) {
-		struct host1x_job_gather *g = &job->gathers[i];
+	for (i = 0; i < job->num_cmds; i++) {
+		struct host1x_job_gather *g;
+
+		if (job->cmds[i].is_wait)
+			continue;
+		g = &job->cmds[i].gather;
 
 		/* process each gather mem only once */
 		if (g->handled)
 			continue;
 
 		/* copy_gathers() sets gathers base if firewall is enabled */
-		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+		if (!job->enable_firewall)
 			g->base = job->gather_addr_phys[i];
 
-		for (j = i + 1; j < job->num_gathers; j++) {
-			if (job->gathers[j].bo == g->bo) {
-				job->gathers[j].handled = true;
-				job->gathers[j].base = g->base;
+		for (j = i + 1; j < job->num_cmds; j++) {
+			if (!job->cmds[j].is_wait &&
+			    job->cmds[j].gather.bo == g->bo) {
+				job->cmds[j].gather.handled = true;
+				job->cmds[j].gather.base = g->base;
 			}
 		}
 
@@ -649,8 +694,7 @@ void host1x_job_unpin(struct host1x_job *job)
 		struct device *dev = unpin->dev ?: host->dev;
 		struct sg_table *sgt = unpin->sgt;
 
-		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) &&
-		    unpin->size && host->domain) {
+		if (!job->enable_firewall && unpin->size && host->domain) {
 			iommu_unmap(host->domain, job->addr_phys[i],
 				    unpin->size);
 			free_iova(&host->iova,
diff --git a/drivers/gpu/host1x/job.h b/drivers/gpu/host1x/job.h
index 94bc2e4ae241..b4428c5495c9 100644
--- a/drivers/gpu/host1x/job.h
+++ b/drivers/gpu/host1x/job.h
@@ -18,6 +18,22 @@ struct host1x_job_gather {
 	bool handled;
 };
 
+struct host1x_job_wait {
+	u32 id;
+	u32 threshold;
+	u32 next_class;
+	bool relative;
+};
+
+struct host1x_job_cmd {
+	bool is_wait;
+
+	union {
+		struct host1x_job_gather gather;
+		struct host1x_job_wait wait;
+	};
+};
+
 struct host1x_job_unpin_data {
 	struct host1x_bo *bo;
 	struct sg_table *sgt;
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index e648ebbb2027..d198a10848c6 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -407,6 +407,8 @@ static void syncpt_release(struct kref *ref)
 
 	atomic_set(&sp->max_val, host1x_syncpt_read(sp));
 
+	sp->locked = false;
+
 	mutex_lock(&sp->host->syncpt_mutex);
 
 	host1x_syncpt_base_free(sp->base);
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index a6766f8d55ee..95cd29b79d6d 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -40,6 +40,13 @@ struct host1x_syncpt {
 
 	/* interrupt data */
 	struct host1x_syncpt_intr intr;
+
+	/*
+	 * If a submission incrementing this syncpoint fails, lock it so that
+	 * further submission cannot be made until application has handled the
+	 * failure.
+	 */
+	bool locked;
 };
 
 /* Initialize sync point array  */
@@ -115,4 +122,9 @@ static inline int host1x_syncpt_is_valid(struct host1x_syncpt *sp)
 	return sp->id < host1x_syncpt_nb_pts(sp->host);
 }
 
+static inline void host1x_syncpt_set_locked(struct host1x_syncpt *sp)
+{
+	sp->locked = true;
+}
+
 #endif
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 949fde433ea2..569930552957 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -72,10 +72,7 @@ struct vga_device {
 	unsigned int io_norm_cnt;	/* normal IO count */
 	unsigned int mem_norm_cnt;	/* normal MEM count */
 	bool bridge_has_one_vga;
-	/* allow IRQ enable/disable hook */
-	void *cookie;
-	void (*irq_set_state)(void *cookie, bool enable);
-	unsigned int (*set_vga_decode)(void *cookie, bool decode);
+	unsigned int (*set_decode)(struct pci_dev *pdev, bool decode);
 };
 
 static LIST_HEAD(vga_list);
@@ -218,13 +215,6 @@ int vga_remove_vgacon(struct pci_dev *pdev)
 #endif
 EXPORT_SYMBOL(vga_remove_vgacon);
 
-static inline void vga_irq_set_state(struct vga_device *vgadev, bool state)
-{
-	if (vgadev->irq_set_state)
-		vgadev->irq_set_state(vgadev->cookie, state);
-}
-
-
 /* If we don't ever use VGA arb we should avoid
    turning off anything anywhere due to old X servers getting
    confused about the boot device not being VGA */
@@ -284,12 +274,6 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev,
 		if (vgadev == conflict)
 			continue;
 
-		/* Check if the architecture allows a conflict between those
-		 * 2 devices or if they are on separate domains
-		 */
-		if (!vga_conflicts(vgadev->pdev, conflict->pdev))
-			continue;
-
 		/* We have a possible conflict. before we go further, we must
 		 * check if we sit on the same bus as the conflicting device.
 		 * if we don't, then we must tie both IO and MEM resources
@@ -331,10 +315,8 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev,
 			if ((match & conflict->decodes) & VGA_RSRC_LEGACY_IO)
 				pci_bits |= PCI_COMMAND_IO;
 
-			if (pci_bits) {
-				vga_irq_set_state(conflict, false);
+			if (pci_bits)
 				flags |= PCI_VGA_STATE_CHANGE_DECODES;
-			}
 		}
 
 		if (change_bridge)
@@ -371,9 +353,6 @@ enable_them:
 
 	pci_set_vga_state(vgadev->pdev, true, pci_bits, flags);
 
-	if (!vgadev->bridge_has_one_vga)
-		vga_irq_set_state(vgadev, true);
-
 	vgadev->owns |= wants;
 lock_them:
 	vgadev->locks |= (rsrc & VGA_RSRC_LEGACY_MASK);
@@ -826,7 +805,7 @@ static void __vga_set_legacy_decoding(struct pci_dev *pdev,
 		goto bail;
 
 	/* don't let userspace futz with kernel driver decodes */
-	if (userspace && vgadev->set_vga_decode)
+	if (userspace && vgadev->set_decode)
 		goto bail;
 
 	/* update the device decodes + counter */
@@ -840,6 +819,17 @@ bail:
 	spin_unlock_irqrestore(&vga_lock, flags);
 }
 
+/**
+ * vga_set_legacy_decoding
+ * @pdev: pci device of the VGA card
+ * @decodes: bit mask of what legacy regions the card decodes
+ *
+ * Indicates to the arbiter if the card decodes legacy VGA IOs, legacy VGA
+ * Memory, both, or none. All cards default to both, the card driver (fbdev for
+ * example) should tell the arbiter if it has disabled legacy decoding, so the
+ * card can be left out of the arbitration process (and can be safe to take
+ * interrupts at any time.
+ */
 void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes)
 {
 	__vga_set_legacy_decoding(pdev, decodes, false);
@@ -849,17 +839,11 @@ EXPORT_SYMBOL(vga_set_legacy_decoding);
 /**
  * vga_client_register - register or unregister a VGA arbitration client
  * @pdev: pci device of the VGA client
- * @cookie: client cookie to be used in callbacks
- * @irq_set_state: irq state change callback
- * @set_vga_decode: vga decode change callback
+ * @set_decode: vga decode change callback
  *
  * Clients have two callback mechanisms they can use.
  *
- * @irq_set_state callback: If a client can't disable its GPUs VGA
- * resources, then we need to be able to ask it to turn off its irqs when we
- * turn off its mem and io decoding.
- *
- * @set_vga_decode callback: If a client can disable its GPU VGA resource, it
+ * @set_decode callback: If a client can disable its GPU VGA resource, it
  * will get a callback from this to set the encode/decode state.
  *
  * Rationale: we cannot disable VGA decode resources unconditionally some single
@@ -872,15 +856,12 @@ EXPORT_SYMBOL(vga_set_legacy_decoding);
  * This function does not check whether a client for @pdev has been registered
  * already.
  *
- * To unregister just call this function with @irq_set_state and @set_vga_decode
- * both set to NULL for the same @pdev as originally used to register them.
+ * To unregister just call vga_client_unregister().
  *
  * Returns: 0 on success, -1 on failure
  */
-int vga_client_register(struct pci_dev *pdev, void *cookie,
-			void (*irq_set_state)(void *cookie, bool state),
-			unsigned int (*set_vga_decode)(void *cookie,
-						       bool decode))
+int vga_client_register(struct pci_dev *pdev,
+		unsigned int (*set_decode)(struct pci_dev *pdev, bool decode))
 {
 	int ret = -ENODEV;
 	struct vga_device *vgadev;
@@ -891,9 +872,7 @@ int vga_client_register(struct pci_dev *pdev, void *cookie,
 	if (!vgadev)
 		goto bail;
 
-	vgadev->irq_set_state = irq_set_state;
-	vgadev->set_vga_decode = set_vga_decode;
-	vgadev->cookie = cookie;
+	vgadev->set_decode = set_decode;
 	ret = 0;
 
 bail:
@@ -1403,9 +1382,9 @@ static void vga_arbiter_notify_clients(void)
 			new_state = false;
 		else
 			new_state = true;
-		if (vgadev->set_vga_decode) {
-			new_decodes = vgadev->set_vga_decode(vgadev->cookie,
-							     new_state);
+		if (vgadev->set_decode) {
+			new_decodes = vgadev->set_decode(vgadev->pdev,
+							 new_state);
 			vga_update_device_decodes(vgadev, new_decodes);
 		}
 	}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 318864d52837..cf27df8048db 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -119,10 +119,9 @@ static bool vfio_pci_is_denylisted(struct pci_dev *pdev)
  * has no way to get to it and routing can be disabled externally at the
  * bridge.
  */
-static unsigned int vfio_pci_set_vga_decode(void *opaque, bool single_vga)
+static unsigned int vfio_pci_set_decode(struct pci_dev *pdev, bool single_vga)
 {
-	struct vfio_pci_device *vdev = opaque;
-	struct pci_dev *tmp = NULL, *pdev = vdev->pdev;
+	struct pci_dev *tmp = NULL;
 	unsigned char max_busnr;
 	unsigned int decodes;
 
@@ -1954,10 +1953,10 @@ static int vfio_pci_vga_init(struct vfio_pci_device *vdev)
 	if (!vfio_pci_is_vga(pdev))
 		return 0;
 
-	ret = vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
+	ret = vga_client_register(pdev, vfio_pci_set_decode);
 	if (ret)
 		return ret;
-	vga_set_legacy_decoding(pdev, vfio_pci_set_vga_decode(vdev, false));
+	vga_set_legacy_decoding(pdev, vfio_pci_set_decode(pdev, false));
 	return 0;
 }
 
@@ -1967,7 +1966,7 @@ static void vfio_pci_vga_uninit(struct vfio_pci_device *vdev)
 
 	if (!vfio_pci_is_vga(pdev))
 		return;
-	vga_client_register(pdev, NULL, NULL, NULL);
+	vga_client_unregister(pdev);
 	vga_set_legacy_decoding(pdev, VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
 					      VGA_RSRC_LEGACY_IO |
 					      VGA_RSRC_LEGACY_MEM);
diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c
index 1447324ed0b6..45e64016db32 100644
--- a/drivers/video/fbdev/arcfb.c
+++ b/drivers/video/fbdev/arcfb.c
@@ -446,7 +446,7 @@ static ssize_t arcfb_write(struct fb_info *info, const char __user *buf,
 	/* modded from epson 1355 */
 
 	unsigned long p;
-	int err=-EINVAL;
+	int err;
 	unsigned int fbmemlength,x,y,w,h, bitppos, startpos, endpos, bitcount;
 	struct arcfb_par *par;
 	unsigned int xres;
diff --git a/drivers/video/fbdev/asiliantfb.c b/drivers/video/fbdev/asiliantfb.c
index 3e006da47752..84c56f525889 100644
--- a/drivers/video/fbdev/asiliantfb.c
+++ b/drivers/video/fbdev/asiliantfb.c
@@ -227,6 +227,9 @@ static int asiliantfb_check_var(struct fb_var_screeninfo *var,
 {
 	unsigned long Ftarget, ratio, remainder;
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	ratio = 1000000 / var->pixclock;
 	remainder = 1000000 % var->pixclock;
 	Ftarget = 1000000 * ratio + (1000000 * remainder) / var->pixclock;
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 1c855145711b..71fb710f1ce3 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -67,7 +67,7 @@ static struct fb_info *get_fb_info(unsigned int idx)
 	mutex_lock(&registration_lock);
 	fb_info = registered_fb[idx];
 	if (fb_info)
-		atomic_inc(&fb_info->count);
+		refcount_inc(&fb_info->count);
 	mutex_unlock(&registration_lock);
 
 	return fb_info;
@@ -75,7 +75,7 @@ static struct fb_info *get_fb_info(unsigned int idx)
 
 static void put_fb_info(struct fb_info *fb_info)
 {
-	if (!atomic_dec_and_test(&fb_info->count))
+	if (!refcount_dec_and_test(&fb_info->count))
 		return;
 	if (fb_info->fbops->fb_destroy)
 		fb_info->fbops->fb_destroy(fb_info);
@@ -1592,7 +1592,7 @@ static int do_register_framebuffer(struct fb_info *fb_info)
 		if (!registered_fb[i])
 			break;
 	fb_info->node = i;
-	atomic_set(&fb_info->count, 1);
+	refcount_set(&fb_info->count, 1);
 	mutex_init(&fb_info->lock);
 	mutex_init(&fb_info->mm_lock);
 
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index ba33b4dce0df..2398b3d48fed 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -548,7 +548,7 @@ static int ep93xxfb_probe(struct platform_device *pdev)
 	}
 
 	ep93xxfb_set_par(info);
-	clk_enable(fbi->clk);
+	clk_prepare_enable(fbi->clk);
 
 	err = register_framebuffer(info);
 	if (err)
@@ -577,7 +577,7 @@ static int ep93xxfb_remove(struct platform_device *pdev)
 	struct ep93xx_fbi *fbi = info->par;
 
 	unregister_framebuffer(info);
-	clk_disable(fbi->clk);
+	clk_disable_unprepare(fbi->clk);
 	ep93xxfb_dealloc_videomem(info);
 	fb_dealloc_cmap(&info->cmap);
 
diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c
index 8fbde92ae8b9..25801e8e3f74 100644
--- a/drivers/video/fbdev/kyro/fbdev.c
+++ b/drivers/video/fbdev/kyro/fbdev.c
@@ -372,6 +372,11 @@ static int kyro_dev_overlay_viewport_set(u32 x, u32 y, u32 ulWidth, u32 ulHeight
 		/* probably haven't called CreateOverlay yet */
 		return -EINVAL;
 
+	if (ulWidth == 0 || ulWidth == 0xffffffff ||
+	    ulHeight == 0 || ulHeight == 0xffffffff ||
+	    (x < 2 && ulWidth + 2 == 0))
+		return -EINVAL;
+
 	/* Stop Ramdac Output */
 	DisableRamdacOutput(deviceInfo.pSTGReg);
 
@@ -394,6 +399,9 @@ static int kyrofb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
 	struct kyrofb_info *par = info->par;
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	if (var->bits_per_pixel != 16 && var->bits_per_pixel != 32) {
 		printk(KERN_WARNING "kyrofb: depth not supported: %u\n", var->bits_per_pixel);
 		return -EINVAL;
diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c
index c0f4f402da3f..966df2a07360 100644
--- a/drivers/video/fbdev/neofb.c
+++ b/drivers/video/fbdev/neofb.c
@@ -585,7 +585,7 @@ neofb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	DBG("neofb_check_var");
 
-	if (PICOS2KHZ(var->pixclock) > par->maxClock)
+	if (var->pixclock && PICOS2KHZ(var->pixclock) > par->maxClock)
 		return -EINVAL;
 
 	/* Is the mode larger than the LCD panel? */
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/apply.c b/drivers/video/fbdev/omap2/omapfb/dss/apply.c
index c71021091828..acca991c7540 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/apply.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/apply.c
@@ -108,7 +108,7 @@ static struct {
 } dss_data;
 
 /* protects dss_data */
-static spinlock_t data_lock;
+static DEFINE_SPINLOCK(data_lock);
 /* lock for blocking functions */
 static DEFINE_MUTEX(apply_lock);
 static DECLARE_COMPLETION(extra_updated_completion);
@@ -131,8 +131,6 @@ static void apply_init_priv(void)
 	struct mgr_priv_data *mp;
 	int i;
 
-	spin_lock_init(&data_lock);
-
 	for (i = 0; i < num_ovls; ++i) {
 		struct ovl_priv_data *op;
 
diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c
index 55554b0433cb..84d5e23ad7d3 100644
--- a/drivers/video/fbdev/riva/fbdev.c
+++ b/drivers/video/fbdev/riva/fbdev.c
@@ -1084,6 +1084,9 @@ static int rivafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 	int mode_valid = 0;
 	
 	NVTRACE_ENTER();
+	if (!var->pixclock)
+		return -EINVAL;
+
 	switch (var->bits_per_pixel) {
 	case 1 ... 8:
 		var->red.offset = var->green.offset = var->blue.offset = 0;
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index eda448b7a0c9..1e2f71c2f8a8 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -82,6 +82,11 @@ struct ssd1307fb_par {
 	struct regulator *vbat_reg;
 	u32 vcomh;
 	u32 width;
+	/* Cached address ranges */
+	u8 col_start;
+	u8 col_end;
+	u8 page_start;
+	u8 page_end;
 };
 
 struct ssd1307fb_array {
@@ -152,17 +157,72 @@ static inline int ssd1307fb_write_cmd(struct i2c_client *client, u8 cmd)
 	return ret;
 }
 
-static void ssd1307fb_update_display(struct ssd1307fb_par *par)
+static int ssd1307fb_set_col_range(struct ssd1307fb_par *par, u8 col_start,
+				   u8 cols)
+{
+	u8 col_end = col_start + cols - 1;
+	int ret;
+
+	if (col_start == par->col_start && col_end == par->col_end)
+		return 0;
+
+	ret = ssd1307fb_write_cmd(par->client, SSD1307FB_SET_COL_RANGE);
+	if (ret < 0)
+		return ret;
+
+	ret = ssd1307fb_write_cmd(par->client, col_start);
+	if (ret < 0)
+		return ret;
+
+	ret = ssd1307fb_write_cmd(par->client, col_end);
+	if (ret < 0)
+		return ret;
+
+	par->col_start = col_start;
+	par->col_end = col_end;
+	return 0;
+}
+
+static int ssd1307fb_set_page_range(struct ssd1307fb_par *par, u8 page_start,
+				    u8 pages)
+{
+	u8 page_end = page_start + pages - 1;
+	int ret;
+
+	if (page_start == par->page_start && page_end == par->page_end)
+		return 0;
+
+	ret = ssd1307fb_write_cmd(par->client, SSD1307FB_SET_PAGE_RANGE);
+	if (ret < 0)
+		return ret;
+
+	ret = ssd1307fb_write_cmd(par->client, page_start);
+	if (ret < 0)
+		return ret;
+
+	ret = ssd1307fb_write_cmd(par->client, page_end);
+	if (ret < 0)
+		return ret;
+
+	par->page_start = page_start;
+	par->page_end = page_end;
+	return 0;
+}
+
+static int ssd1307fb_update_rect(struct ssd1307fb_par *par, unsigned int x,
+				 unsigned int y, unsigned int width,
+				 unsigned int height)
 {
 	struct ssd1307fb_array *array;
 	u8 *vmem = par->info->screen_buffer;
 	unsigned int line_length = par->info->fix.line_length;
-	unsigned int pages = DIV_ROUND_UP(par->height, 8);
-	int i, j, k;
+	unsigned int pages = DIV_ROUND_UP(y % 8 + height, 8);
+	u32 array_idx = 0;
+	int ret, i, j, k;
 
-	array = ssd1307fb_alloc_array(par->width * pages, SSD1307FB_DATA);
+	array = ssd1307fb_alloc_array(width * pages, SSD1307FB_DATA);
 	if (!array)
-		return;
+		return -ENOMEM;
 
 	/*
 	 * The screen is divided in pages, each having a height of 8
@@ -193,27 +253,44 @@ static void ssd1307fb_update_display(struct ssd1307fb_par *par)
 	 *  (5) A4 B4 C4 D4 E4 F4 G4 H4
 	 */
 
-	for (i = 0; i < pages; i++) {
-		for (j = 0; j < par->width; j++) {
-			int m = 8;
-			u32 array_idx = i * par->width + j;
-			array->data[array_idx] = 0;
-			/* Last page may be partial */
-			if (i + 1 == pages && par->height % 8)
-				m = par->height % 8;
+	ret = ssd1307fb_set_col_range(par, par->col_offset + x, width);
+	if (ret < 0)
+		goto out_free;
+
+	ret = ssd1307fb_set_page_range(par, par->page_offset + y / 8, pages);
+	if (ret < 0)
+		goto out_free;
+
+	for (i = y / 8; i < y / 8 + pages; i++) {
+		int m = 8;
+
+		/* Last page may be partial */
+		if (8 * (i + 1) > par->height)
+			m = par->height % 8;
+		for (j = x; j < x + width; j++) {
+			u8 data = 0;
+
 			for (k = 0; k < m; k++) {
 				u8 byte = vmem[(8 * i + k) * line_length +
 					       j / 8];
 				u8 bit = (byte >> (j % 8)) & 1;
-				array->data[array_idx] |= bit << k;
+				data |= bit << k;
 			}
+			array->data[array_idx++] = data;
 		}
 	}
 
-	ssd1307fb_write_array(par->client, array, par->width * pages);
+	ret = ssd1307fb_write_array(par->client, array, width * pages);
+
+out_free:
 	kfree(array);
+	return ret;
 }
 
+static int ssd1307fb_update_display(struct ssd1307fb_par *par)
+{
+	return ssd1307fb_update_rect(par, 0, 0, par->width, par->height);
+}
 
 static ssize_t ssd1307fb_write(struct fb_info *info, const char __user *buf,
 		size_t count, loff_t *ppos)
@@ -222,6 +299,7 @@ static ssize_t ssd1307fb_write(struct fb_info *info, const char __user *buf,
 	unsigned long total_size;
 	unsigned long p = *ppos;
 	void *dst;
+	int ret;
 
 	total_size = info->fix.smem_len;
 
@@ -239,7 +317,9 @@ static ssize_t ssd1307fb_write(struct fb_info *info, const char __user *buf,
 	if (copy_from_user(dst, buf, count))
 		return -EFAULT;
 
-	ssd1307fb_update_display(par);
+	ret = ssd1307fb_update_display(par);
+	if (ret < 0)
+		return ret;
 
 	*ppos += count;
 
@@ -260,21 +340,24 @@ static void ssd1307fb_fillrect(struct fb_info *info, const struct fb_fillrect *r
 {
 	struct ssd1307fb_par *par = info->par;
 	sys_fillrect(info, rect);
-	ssd1307fb_update_display(par);
+	ssd1307fb_update_rect(par, rect->dx, rect->dy, rect->width,
+			      rect->height);
 }
 
 static void ssd1307fb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 {
 	struct ssd1307fb_par *par = info->par;
 	sys_copyarea(info, area);
-	ssd1307fb_update_display(par);
+	ssd1307fb_update_rect(par, area->dx, area->dy, area->width,
+			      area->height);
 }
 
 static void ssd1307fb_imageblit(struct fb_info *info, const struct fb_image *image)
 {
 	struct ssd1307fb_par *par = info->par;
 	sys_imageblit(info, image);
-	ssd1307fb_update_display(par);
+	ssd1307fb_update_rect(par, image->dx, image->dy, image->width,
+			      image->height);
 }
 
 static const struct fb_ops ssd1307fb_ops = {
@@ -454,37 +537,11 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
 	if (ret < 0)
 		return ret;
 
-	/* Set column range */
-	ret = ssd1307fb_write_cmd(par->client, SSD1307FB_SET_COL_RANGE);
-	if (ret < 0)
-		return ret;
-
-	ret = ssd1307fb_write_cmd(par->client, par->col_offset);
-	if (ret < 0)
-		return ret;
-
-	ret = ssd1307fb_write_cmd(par->client, par->col_offset + par->width - 1);
-	if (ret < 0)
-		return ret;
-
-	/* Set page range */
-	ret = ssd1307fb_write_cmd(par->client, SSD1307FB_SET_PAGE_RANGE);
-	if (ret < 0)
-		return ret;
-
-	ret = ssd1307fb_write_cmd(par->client, par->page_offset);
-	if (ret < 0)
-		return ret;
-
-	ret = ssd1307fb_write_cmd(par->client,
-				  par->page_offset +
-				  DIV_ROUND_UP(par->height, 8) - 1);
+	/* Clear the screen */
+	ret = ssd1307fb_update_display(par);
 	if (ret < 0)
 		return ret;
 
-	/* Clear the screen */
-	ssd1307fb_update_display(par);
-
 	/* Turn on the display */
 	ret = ssd1307fb_write_cmd(par->client, SSD1307FB_DISPLAY_ON);
 	if (ret < 0)