24255 files changed, 3367256 insertions, 1226040 deletions

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 7bdad836fc62..4915a63866b0 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -10,6 +10,12 @@ source "drivers/cxl/Kconfig"
 source "drivers/pcmcia/Kconfig"
 source "drivers/rapidio/Kconfig"
 
+config PC104
+	bool "PC/104 support" if EXPERT
+	help
+	  Expose PC/104 form factor device drivers and options available for
+	  selection and configuration. Enable this option if your target
+	  machine has a PC/104 bus.
 
 source "drivers/base/Kconfig"
 
@@ -21,6 +27,8 @@ source "drivers/connector/Kconfig"
 
 source "drivers/firmware/Kconfig"
 
+source "drivers/fwctl/Kconfig"
+
 source "drivers/gnss/Kconfig"
 
 source "drivers/mtd/Kconfig"
@@ -75,6 +83,8 @@ source "drivers/pps/Kconfig"
 
 source "drivers/ptp/Kconfig"
 
+source "drivers/dpll/Kconfig"
+
 source "drivers/pinctrl/Kconfig"
 
 source "drivers/gpio/Kconfig"
@@ -207,8 +217,6 @@ source "drivers/thunderbolt/Kconfig"
 
 source "drivers/android/Kconfig"
 
-source "drivers/gpu/trace/Kconfig"
-
 source "drivers/nvdimm/Kconfig"
 
 source "drivers/dax/Kconfig"
@@ -243,6 +251,4 @@ source "drivers/hte/Kconfig"
 
 source "drivers/cdx/Kconfig"
 
-source "drivers/dpll/Kconfig"
-
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index d828329c268d..8e1ffa4358d5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -6,11 +6,6 @@
 # Rewritten to use lists instead of if-statements.
 #
 
-# Some driver Makefiles miss $(srctree)/ for include directive.
-ifdef building_out_of_srctree
-MAKEFLAGS += --include-dir=$(srctree)
-endif
-
 obj-y				+= cache/
 obj-y				+= irqchip/
 obj-y				+= bus/
@@ -22,6 +17,9 @@ obj-$(CONFIG_PINCTRL)		+= pinctrl/
 obj-$(CONFIG_GPIOLIB)		+= gpio/
 obj-y				+= pwm/
 
+# LEDs must come before PCI, it is needed by NPEM driver
+obj-y				+= leds/
+
 obj-y				+= pci/
 
 obj-$(CONFIG_PARISC)		+= parisc/
@@ -71,9 +69,8 @@ obj-y				+= gpu/
 
 obj-$(CONFIG_CONNECTOR)		+= connector/
 
-# i810fb and intelfb depend on char/agp/
+# i810fb depends on char/agp/
 obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
-obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
@@ -136,9 +133,9 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-y				+= mmc/
 obj-y				+= ufs/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
-obj-$(CONFIG_NEW_LEDS)		+= leds/
 obj-$(CONFIG_INFINIBAND)	+= infiniband/
 obj-y				+= firmware/
+obj-$(CONFIG_FWCTL)		+= fwctl/
 obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
 obj-y				+= clocksource/
@@ -164,7 +161,7 @@ obj-$(CONFIG_SOUNDWIRE)		+= soundwire/
 
 # Virtualization drivers
 obj-$(CONFIG_VIRT_DRIVERS)	+= virt/
-obj-$(subst m,y,$(CONFIG_HYPERV))	+= hv/
+obj-$(CONFIG_HYPERV)		+= hv/
 
 obj-$(CONFIG_PM_DEVFREQ)	+= devfreq/
 obj-$(CONFIG_EXTCON)		+= extcon/
@@ -198,4 +195,5 @@ obj-$(CONFIG_DRM_ACCEL)		+= accel/
 obj-$(CONFIG_CDX_BUS)		+= cdx/
 obj-$(CONFIG_DPLL)		+= dpll/
 
+obj-$(CONFIG_DIBS)		+= dibs/
 obj-$(CONFIG_S390)		+= s390/
diff --git a/drivers/accel/Kconfig b/drivers/accel/Kconfig
index 64065fb8922b..bb01cebc42bf 100644
--- a/drivers/accel/Kconfig
+++ b/drivers/accel/Kconfig
@@ -24,8 +24,10 @@ menuconfig DRM_ACCEL
 	  different device files, called accel/accel* (in /dev, sysfs
 	  and debugfs).
 
+source "drivers/accel/amdxdna/Kconfig"
 source "drivers/accel/habanalabs/Kconfig"
 source "drivers/accel/ivpu/Kconfig"
 source "drivers/accel/qaic/Kconfig"
+source "drivers/accel/rocket/Kconfig"
 
 endif
diff --git a/drivers/accel/Makefile b/drivers/accel/Makefile
index ab3df932937f..ffc3fa588666 100644
--- a/drivers/accel/Makefile
+++ b/drivers/accel/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+obj-$(CONFIG_DRM_ACCEL_AMDXDNA)		+= amdxdna/
 obj-$(CONFIG_DRM_ACCEL_HABANALABS)	+= habanalabs/
 obj-$(CONFIG_DRM_ACCEL_IVPU)		+= ivpu/
 obj-$(CONFIG_DRM_ACCEL_QAIC)		+= qaic/
+obj-$(CONFIG_DRM_ACCEL_ROCKET)		+= rocket/
\ No newline at end of file
diff --git a/drivers/accel/amdxdna/Kconfig b/drivers/accel/amdxdna/Kconfig
new file mode 100644
index 000000000000..f39d7a87296c
--- /dev/null
+++ b/drivers/accel/amdxdna/Kconfig
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config DRM_ACCEL_AMDXDNA
+	tristate "AMD AI Engine"
+	depends on AMD_IOMMU
+	depends on DRM_ACCEL
+	depends on PCI && HAS_IOMEM
+	depends on X86_64
+	select DRM_SCHED
+	select DRM_GEM_SHMEM_HELPER
+	select FW_LOADER
+	select HMM_MIRROR
+	help
+	  Choose this option to enable support for NPU integrated into AMD
+	  client CPUs like AMD Ryzen AI 300 Series. AMD NPU can be used to
+	  accelerate machine learning applications.
+
+	  If "M" is selected, the driver module will be amdxdna.
diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile
new file mode 100644
index 000000000000..6797dac65efa
--- /dev/null
+++ b/drivers/accel/amdxdna/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+amdxdna-y := \
+	aie2_ctx.o \
+	aie2_error.o \
+	aie2_message.o \
+	aie2_pci.o \
+	aie2_pm.o \
+	aie2_psp.o \
+	aie2_smu.o \
+	aie2_solver.o \
+	amdxdna_ctx.o \
+	amdxdna_gem.o \
+	amdxdna_mailbox.o \
+	amdxdna_mailbox_helper.o \
+	amdxdna_pci_drv.o \
+	amdxdna_sysfs.o \
+	amdxdna_ubuf.o \
+	npu1_regs.o \
+	npu2_regs.o \
+	npu4_regs.o \
+	npu5_regs.o \
+	npu6_regs.o
+obj-$(CONFIG_DRM_ACCEL_AMDXDNA) = amdxdna.o
diff --git a/drivers/accel/amdxdna/TODO b/drivers/accel/amdxdna/TODO
new file mode 100644
index 000000000000..ad8ac6e315b6
--- /dev/null
+++ b/drivers/accel/amdxdna/TODO
@@ -0,0 +1,2 @@
+- Add debugfs support
+- Add debug BO support
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
new file mode 100644
index 000000000000..e9f9b1fa5dc1
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -0,0 +1,944 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_print.h>
+#include <drm/drm_syncobj.h>
+#include <linux/hmm.h>
+#include <linux/types.h>
+#include <linux/xarray.h>
+#include <trace/events/amdxdna.h>
+
+#include "aie2_msg_priv.h"
+#include "aie2_pci.h"
+#include "aie2_solver.h"
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+static bool force_cmdlist;
+module_param(force_cmdlist, bool, 0600);
+MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)");
+
+#define HWCTX_MAX_TIMEOUT	60000 /* milliseconds */
+
+static void aie2_job_release(struct kref *ref)
+{
+	struct amdxdna_sched_job *job;
+
+	job = container_of(ref, struct amdxdna_sched_job, refcnt);
+	amdxdna_sched_job_cleanup(job);
+	atomic64_inc(&job->hwctx->job_free_cnt);
+	wake_up(&job->hwctx->priv->job_free_wq);
+	if (job->out_fence)
+		dma_fence_put(job->out_fence);
+	kfree(job);
+}
+
+static void aie2_job_put(struct amdxdna_sched_job *job)
+{
+	kref_put(&job->refcnt, aie2_job_release);
+}
+
+static void aie2_hwctx_status_shift_stop(struct amdxdna_hwctx *hwctx)
+{
+	 hwctx->old_status = hwctx->status;
+	 hwctx->status = HWCTX_STAT_STOP;
+}
+
+static void aie2_hwctx_status_restore(struct amdxdna_hwctx *hwctx)
+{
+	hwctx->status = hwctx->old_status;
+}
+
+/* The bad_job is used in aie2_sched_job_timedout, otherwise, set it to NULL */
+static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx,
+			    struct drm_sched_job *bad_job)
+{
+	drm_sched_stop(&hwctx->priv->sched, bad_job);
+	aie2_destroy_context(xdna->dev_handle, hwctx);
+}
+
+static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_gem_obj *heap = hwctx->priv->heap;
+	int ret;
+
+	ret = aie2_create_context(xdna->dev_handle, hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Create hwctx failed, ret %d", ret);
+		goto out;
+	}
+
+	ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id,
+				heap->mem.userptr, heap->mem.size);
+	if (ret) {
+		XDNA_ERR(xdna, "Map host buf failed, ret %d", ret);
+		goto out;
+	}
+
+	if (hwctx->status != HWCTX_STAT_READY) {
+		XDNA_DBG(xdna, "hwctx is not ready, status %d", hwctx->status);
+		goto out;
+	}
+
+	ret = aie2_config_cu(hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Config cu failed, ret %d", ret);
+		goto out;
+	}
+
+out:
+	drm_sched_start(&hwctx->priv->sched, 0);
+	XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret);
+	return ret;
+}
+
+static struct dma_fence *aie2_cmd_get_out_fence(struct amdxdna_hwctx *hwctx, u64 seq)
+{
+	struct dma_fence *fence, *out_fence = NULL;
+	int ret;
+
+	fence = drm_syncobj_fence_get(hwctx->priv->syncobj);
+	if (!fence)
+		return NULL;
+
+	ret = dma_fence_chain_find_seqno(&fence,  seq);
+	if (ret)
+		goto out;
+
+	out_fence = dma_fence_get(dma_fence_chain_contained(fence));
+
+out:
+	dma_fence_put(fence);
+	return out_fence;
+}
+
+static void aie2_hwctx_wait_for_idle(struct amdxdna_hwctx *hwctx)
+{
+	struct dma_fence *fence;
+
+	fence = aie2_cmd_get_out_fence(hwctx, hwctx->priv->seq - 1);
+	if (!fence)
+		return;
+
+	/* Wait up to 2 seconds for fw to finish all pending requests */
+	dma_fence_wait_timeout(fence, false, msecs_to_jiffies(2000));
+	dma_fence_put(fence);
+}
+
+static int aie2_hwctx_suspend_cb(struct amdxdna_hwctx *hwctx, void *arg)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+
+	aie2_hwctx_wait_for_idle(hwctx);
+	aie2_hwctx_stop(xdna, hwctx, NULL);
+	aie2_hwctx_status_shift_stop(hwctx);
+
+	return 0;
+}
+
+void aie2_hwctx_suspend(struct amdxdna_client *client)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+
+	/*
+	 * Command timeout is unlikely. But if it happens, it doesn't
+	 * break the system. aie2_hwctx_stop() will destroy mailbox
+	 * and abort all commands.
+	 */
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+	amdxdna_hwctx_walk(client, NULL, aie2_hwctx_suspend_cb);
+}
+
+static int aie2_hwctx_resume_cb(struct amdxdna_hwctx *hwctx, void *arg)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+
+	aie2_hwctx_status_restore(hwctx);
+	return aie2_hwctx_restart(xdna, hwctx);
+}
+
+int aie2_hwctx_resume(struct amdxdna_client *client)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+
+	/*
+	 * The resume path cannot guarantee that mailbox channel can be
+	 * regenerated. If this happen, when submit message to this
+	 * mailbox channel, error will return.
+	 */
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+	return amdxdna_hwctx_walk(client, NULL, aie2_hwctx_resume_cb);
+}
+
+static void
+aie2_sched_notify(struct amdxdna_sched_job *job)
+{
+	struct dma_fence *fence = job->fence;
+
+	trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq);
+	job->hwctx->priv->completed++;
+	dma_fence_signal(fence);
+
+	up(&job->hwctx->priv->job_sem);
+	job->job_done = true;
+	dma_fence_put(fence);
+	mmput_async(job->mm);
+	aie2_job_put(job);
+}
+
+static int
+aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
+{
+	struct amdxdna_sched_job *job = handle;
+	struct amdxdna_gem_obj *cmd_abo;
+	int ret = 0;
+	u32 status;
+
+	cmd_abo = job->cmd_bo;
+
+	if (unlikely(!data))
+		goto out;
+
+	if (unlikely(size != sizeof(u32))) {
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	status = readl(data);
+	XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status);
+	if (status == AIE2_STATUS_SUCCESS)
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED);
+	else
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR);
+
+out:
+	aie2_sched_notify(job);
+	return ret;
+}
+
+static int
+aie2_sched_nocmd_resp_handler(void *handle, void __iomem *data, size_t size)
+{
+	struct amdxdna_sched_job *job = handle;
+	int ret = 0;
+	u32 status;
+
+	if (unlikely(!data))
+		goto out;
+
+	if (unlikely(size != sizeof(u32))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	status = readl(data);
+	XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status);
+
+out:
+	aie2_sched_notify(job);
+	return ret;
+}
+
+static int
+aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size)
+{
+	struct amdxdna_sched_job *job = handle;
+	struct amdxdna_gem_obj *cmd_abo;
+	struct amdxdna_dev *xdna;
+	u32 fail_cmd_status;
+	u32 fail_cmd_idx;
+	u32 cmd_status;
+	int ret = 0;
+
+	cmd_abo = job->cmd_bo;
+	if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) {
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	cmd_status = readl(data + offsetof(struct cmd_chain_resp, status));
+	xdna = job->hwctx->client->xdna;
+	XDNA_DBG(xdna, "Status 0x%x", cmd_status);
+	if (cmd_status == AIE2_STATUS_SUCCESS) {
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED);
+		goto out;
+	}
+
+	/* Slow path to handle error, read from ringbuf on BAR */
+	fail_cmd_idx = readl(data + offsetof(struct cmd_chain_resp, fail_cmd_idx));
+	fail_cmd_status = readl(data + offsetof(struct cmd_chain_resp, fail_cmd_status));
+	XDNA_DBG(xdna, "Failed cmd idx %d, status 0x%x",
+		 fail_cmd_idx, fail_cmd_status);
+
+	if (fail_cmd_status == AIE2_STATUS_SUCCESS) {
+		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		ret = -EINVAL;
+		goto out;
+	}
+	amdxdna_cmd_set_state(cmd_abo, fail_cmd_status);
+
+	if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) {
+		struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL);
+
+		cc->error_index = fail_cmd_idx;
+		if (cc->error_index >= cc->command_count)
+			cc->error_index = 0;
+	}
+out:
+	aie2_sched_notify(job);
+	return ret;
+}
+
+static struct dma_fence *
+aie2_sched_job_run(struct drm_sched_job *sched_job)
+{
+	struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job);
+	struct amdxdna_gem_obj *cmd_abo = job->cmd_bo;
+	struct amdxdna_hwctx *hwctx = job->hwctx;
+	struct dma_fence *fence;
+	int ret;
+
+	if (!mmget_not_zero(job->mm))
+		return ERR_PTR(-ESRCH);
+
+	kref_get(&job->refcnt);
+	fence = dma_fence_get(job->fence);
+
+	if (unlikely(!cmd_abo)) {
+		ret = aie2_sync_bo(hwctx, job, aie2_sched_nocmd_resp_handler);
+		goto out;
+	}
+
+	amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_NEW);
+
+	if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN)
+		ret = aie2_cmdlist_multi_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler);
+	else if (force_cmdlist)
+		ret = aie2_cmdlist_single_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler);
+	else
+		ret = aie2_execbuf(hwctx, job, aie2_sched_resp_handler);
+
+out:
+	if (ret) {
+		dma_fence_put(job->fence);
+		aie2_job_put(job);
+		mmput(job->mm);
+		fence = ERR_PTR(ret);
+	}
+	trace_xdna_job(sched_job, hwctx->name, "sent to device", job->seq);
+
+	return fence;
+}
+
+static void aie2_sched_job_free(struct drm_sched_job *sched_job)
+{
+	struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job);
+	struct amdxdna_hwctx *hwctx = job->hwctx;
+
+	trace_xdna_job(sched_job, hwctx->name, "job free", job->seq);
+	if (!job->job_done)
+		up(&hwctx->priv->job_sem);
+
+	drm_sched_job_cleanup(sched_job);
+	aie2_job_put(job);
+}
+
+static enum drm_gpu_sched_stat
+aie2_sched_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job);
+	struct amdxdna_hwctx *hwctx = job->hwctx;
+	struct amdxdna_dev *xdna;
+
+	xdna = hwctx->client->xdna;
+	trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq);
+	mutex_lock(&xdna->dev_lock);
+	aie2_hwctx_stop(xdna, hwctx, sched_job);
+
+	aie2_hwctx_restart(xdna, hwctx);
+	mutex_unlock(&xdna->dev_lock);
+
+	return DRM_GPU_SCHED_STAT_RESET;
+}
+
+static const struct drm_sched_backend_ops sched_ops = {
+	.run_job = aie2_sched_job_run,
+	.free_job = aie2_sched_job_free,
+	.timedout_job = aie2_sched_job_timedout,
+};
+
+static int aie2_hwctx_col_list(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int start, end, first, last;
+	u32 width = 1, entries = 0;
+	int i;
+
+	if (!hwctx->num_tiles) {
+		XDNA_ERR(xdna, "Number of tiles is zero");
+		return -EINVAL;
+	}
+
+	ndev = xdna->dev_handle;
+	if (unlikely(!ndev->metadata.core.row_count)) {
+		XDNA_WARN(xdna, "Core tile row count is zero");
+		return -EINVAL;
+	}
+
+	hwctx->num_col = hwctx->num_tiles / ndev->metadata.core.row_count;
+	if (!hwctx->num_col || hwctx->num_col > ndev->total_col) {
+		XDNA_ERR(xdna, "Invalid num_col %d", hwctx->num_col);
+		return -EINVAL;
+	}
+
+	if (ndev->priv->col_align == COL_ALIGN_NATURE)
+		width = hwctx->num_col;
+
+	/*
+	 * In range [start, end], find out columns that is multiple of width.
+	 *	'first' is the first column,
+	 *	'last' is the last column,
+	 *	'entries' is the total number of columns.
+	 */
+	start =  xdna->dev_info->first_col;
+	end =  ndev->total_col - hwctx->num_col;
+	if (start > 0 && end == 0) {
+		XDNA_DBG(xdna, "Force start from col 0");
+		start = 0;
+	}
+	first = start + (width - start % width) % width;
+	last = end - end % width;
+	if (last >= first)
+		entries = (last - first) / width + 1;
+	XDNA_DBG(xdna, "start %d end %d first %d last %d",
+		 start, end, first, last);
+
+	if (unlikely(!entries)) {
+		XDNA_ERR(xdna, "Start %d end %d width %d",
+			 start, end, width);
+		return -EINVAL;
+	}
+
+	hwctx->col_list = kmalloc_array(entries, sizeof(*hwctx->col_list), GFP_KERNEL);
+	if (!hwctx->col_list)
+		return -ENOMEM;
+
+	hwctx->col_list_len = entries;
+	hwctx->col_list[0] = first;
+	for (i = 1; i < entries; i++)
+		hwctx->col_list[i] = hwctx->col_list[i - 1] + width;
+
+	print_hex_dump_debug("col_list: ", DUMP_PREFIX_OFFSET, 16, 4, hwctx->col_list,
+			     entries * sizeof(*hwctx->col_list), false);
+	return 0;
+}
+
+static int aie2_alloc_resource(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct alloc_requests *xrs_req;
+	int ret;
+
+	xrs_req = kzalloc(sizeof(*xrs_req), GFP_KERNEL);
+	if (!xrs_req)
+		return -ENOMEM;
+
+	xrs_req->cdo.start_cols = hwctx->col_list;
+	xrs_req->cdo.cols_len = hwctx->col_list_len;
+	xrs_req->cdo.ncols = hwctx->num_col;
+	xrs_req->cdo.qos_cap.opc = hwctx->max_opc;
+
+	xrs_req->rqos.gops = hwctx->qos.gops;
+	xrs_req->rqos.fps = hwctx->qos.fps;
+	xrs_req->rqos.dma_bw = hwctx->qos.dma_bandwidth;
+	xrs_req->rqos.latency = hwctx->qos.latency;
+	xrs_req->rqos.exec_time = hwctx->qos.frame_exec_time;
+	xrs_req->rqos.priority = hwctx->qos.priority;
+
+	xrs_req->rid = (uintptr_t)hwctx;
+
+	ret = xrs_allocate_resource(xdna->xrs_hdl, xrs_req, hwctx);
+	if (ret)
+		XDNA_ERR(xdna, "Allocate AIE resource failed, ret %d", ret);
+
+	kfree(xrs_req);
+	return ret;
+}
+
+static void aie2_release_resource(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	int ret;
+
+	ret = xrs_release_resource(xdna->xrs_hdl, (uintptr_t)hwctx);
+	if (ret)
+		XDNA_ERR(xdna, "Release AIE resource failed, ret %d", ret);
+}
+
+static int aie2_ctx_syncobj_create(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct drm_file *filp = hwctx->client->filp;
+	struct drm_syncobj *syncobj;
+	u32 hdl;
+	int ret;
+
+	hwctx->syncobj_hdl = AMDXDNA_INVALID_FENCE_HANDLE;
+
+	ret = drm_syncobj_create(&syncobj, 0, NULL);
+	if (ret) {
+		XDNA_ERR(xdna, "Create ctx syncobj failed, ret %d", ret);
+		return ret;
+	}
+	ret = drm_syncobj_get_handle(filp, syncobj, &hdl);
+	if (ret) {
+		drm_syncobj_put(syncobj);
+		XDNA_ERR(xdna, "Create ctx syncobj handle failed, ret %d", ret);
+		return ret;
+	}
+	hwctx->priv->syncobj = syncobj;
+	hwctx->syncobj_hdl = hdl;
+
+	return 0;
+}
+
+static void aie2_ctx_syncobj_destroy(struct amdxdna_hwctx *hwctx)
+{
+	/*
+	 * The syncobj_hdl is owned by user space and will be cleaned up
+	 * separately.
+	 */
+	drm_syncobj_put(hwctx->priv->syncobj);
+}
+
+int aie2_hwctx_init(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_client *client = hwctx->client;
+	struct amdxdna_dev *xdna = client->xdna;
+	const struct drm_sched_init_args args = {
+		.ops = &sched_ops,
+		.num_rqs = DRM_SCHED_PRIORITY_COUNT,
+		.credit_limit = HWCTX_MAX_CMDS,
+		.timeout = msecs_to_jiffies(HWCTX_MAX_TIMEOUT),
+		.name = hwctx->name,
+		.dev = xdna->ddev.dev,
+	};
+	struct drm_gpu_scheduler *sched;
+	struct amdxdna_hwctx_priv *priv;
+	struct amdxdna_gem_obj *heap;
+	struct amdxdna_dev_hdl *ndev;
+	int i, ret;
+
+	priv = kzalloc(sizeof(*hwctx->priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	hwctx->priv = priv;
+
+	mutex_lock(&client->mm_lock);
+	heap = client->dev_heap;
+	if (!heap) {
+		XDNA_ERR(xdna, "The client dev heap object not exist");
+		mutex_unlock(&client->mm_lock);
+		ret = -ENOENT;
+		goto free_priv;
+	}
+	drm_gem_object_get(to_gobj(heap));
+	mutex_unlock(&client->mm_lock);
+	priv->heap = heap;
+	sema_init(&priv->job_sem, HWCTX_MAX_CMDS);
+
+	ret = amdxdna_gem_pin(heap);
+	if (ret) {
+		XDNA_ERR(xdna, "Dev heap pin failed, ret %d", ret);
+		goto put_heap;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) {
+		struct amdxdna_gem_obj *abo;
+		struct amdxdna_drm_create_bo args = {
+			.flags = 0,
+			.type = AMDXDNA_BO_DEV,
+			.vaddr = 0,
+			.size = MAX_CHAIN_CMDBUF_SIZE,
+		};
+
+		abo = amdxdna_drm_alloc_dev_bo(&xdna->ddev, &args, client->filp);
+		if (IS_ERR(abo)) {
+			ret = PTR_ERR(abo);
+			goto free_cmd_bufs;
+		}
+
+		XDNA_DBG(xdna, "Command buf %d addr 0x%llx size 0x%lx",
+			 i, abo->mem.dev_addr, abo->mem.size);
+		priv->cmd_buf[i] = abo;
+	}
+
+	sched = &priv->sched;
+	mutex_init(&priv->io_lock);
+
+	fs_reclaim_acquire(GFP_KERNEL);
+	might_lock(&priv->io_lock);
+	fs_reclaim_release(GFP_KERNEL);
+
+	ret = drm_sched_init(sched, &args);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to init DRM scheduler. ret %d", ret);
+		goto free_cmd_bufs;
+	}
+
+	ret = drm_sched_entity_init(&priv->entity, DRM_SCHED_PRIORITY_NORMAL,
+				    &sched, 1, NULL);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to initial sched entiry. ret %d", ret);
+		goto free_sched;
+	}
+
+	ret = aie2_hwctx_col_list(hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Create col list failed, ret %d", ret);
+		goto free_entity;
+	}
+
+	ret = aie2_alloc_resource(hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Alloc hw resource failed, ret %d", ret);
+		goto free_col_list;
+	}
+
+	ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id,
+				heap->mem.userptr, heap->mem.size);
+	if (ret) {
+		XDNA_ERR(xdna, "Map host buffer failed, ret %d", ret);
+		goto release_resource;
+	}
+
+	ret = aie2_ctx_syncobj_create(hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Create syncobj failed, ret %d", ret);
+		goto release_resource;
+	}
+
+	hwctx->status = HWCTX_STAT_INIT;
+	ndev = xdna->dev_handle;
+	ndev->hwctx_num++;
+	init_waitqueue_head(&priv->job_free_wq);
+
+	XDNA_DBG(xdna, "hwctx %s init completed", hwctx->name);
+
+	return 0;
+
+release_resource:
+	aie2_release_resource(hwctx);
+free_col_list:
+	kfree(hwctx->col_list);
+free_entity:
+	drm_sched_entity_destroy(&priv->entity);
+free_sched:
+	drm_sched_fini(&priv->sched);
+free_cmd_bufs:
+	for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) {
+		if (!priv->cmd_buf[i])
+			continue;
+		drm_gem_object_put(to_gobj(priv->cmd_buf[i]));
+	}
+	amdxdna_gem_unpin(heap);
+put_heap:
+	drm_gem_object_put(to_gobj(heap));
+free_priv:
+	kfree(priv);
+	return ret;
+}
+
+void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_dev_hdl *ndev;
+	struct amdxdna_dev *xdna;
+	int idx;
+
+	xdna = hwctx->client->xdna;
+	ndev = xdna->dev_handle;
+	ndev->hwctx_num--;
+
+	XDNA_DBG(xdna, "%s sequence number %lld", hwctx->name, hwctx->priv->seq);
+	drm_sched_entity_destroy(&hwctx->priv->entity);
+
+	aie2_hwctx_wait_for_idle(hwctx);
+
+	/* Request fw to destroy hwctx and cancel the rest pending requests */
+	aie2_release_resource(hwctx);
+
+	/* Wait for all submitted jobs to be completed or canceled */
+	wait_event(hwctx->priv->job_free_wq,
+		   atomic64_read(&hwctx->job_submit_cnt) ==
+		   atomic64_read(&hwctx->job_free_cnt));
+
+	drm_sched_fini(&hwctx->priv->sched);
+	aie2_ctx_syncobj_destroy(hwctx);
+
+	for (idx = 0; idx < ARRAY_SIZE(hwctx->priv->cmd_buf); idx++)
+		drm_gem_object_put(to_gobj(hwctx->priv->cmd_buf[idx]));
+	amdxdna_gem_unpin(hwctx->priv->heap);
+	drm_gem_object_put(to_gobj(hwctx->priv->heap));
+
+	mutex_destroy(&hwctx->priv->io_lock);
+	kfree(hwctx->col_list);
+	kfree(hwctx->priv);
+	kfree(hwctx->cus);
+}
+
+static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size)
+{
+	struct amdxdna_hwctx_param_config_cu *config = buf;
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	u32 total_size;
+	int ret;
+
+	XDNA_DBG(xdna, "Config %d CU to %s", config->num_cus, hwctx->name);
+	if (XDNA_MBZ_DBG(xdna, config->pad, sizeof(config->pad)))
+		return -EINVAL;
+
+	if (hwctx->status != HWCTX_STAT_INIT) {
+		XDNA_ERR(xdna, "Not support re-config CU");
+		return -EINVAL;
+	}
+
+	if (!config->num_cus) {
+		XDNA_ERR(xdna, "Number of CU is zero");
+		return -EINVAL;
+	}
+
+	total_size = struct_size(config, cu_configs, config->num_cus);
+	if (total_size > size) {
+		XDNA_ERR(xdna, "CU config larger than size");
+		return -EINVAL;
+	}
+
+	hwctx->cus = kmemdup(config, total_size, GFP_KERNEL);
+	if (!hwctx->cus)
+		return -ENOMEM;
+
+	ret = aie2_config_cu(hwctx);
+	if (ret) {
+		XDNA_ERR(xdna, "Config CU to firmware failed, ret %d", ret);
+		goto free_cus;
+	}
+
+	wmb(); /* To avoid locking in command submit when check status */
+	hwctx->status = HWCTX_STAT_READY;
+
+	return 0;
+
+free_cus:
+	kfree(hwctx->cus);
+	hwctx->cus = NULL;
+	return ret;
+}
+
+int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+	switch (type) {
+	case DRM_AMDXDNA_HWCTX_CONFIG_CU:
+		return aie2_hwctx_cu_config(hwctx, buf, size);
+	case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF:
+	case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF:
+		return -EOPNOTSUPP;
+	default:
+		XDNA_DBG(xdna, "Not supported type %d", type);
+		return -EOPNOTSUPP;
+	}
+}
+
+static int aie2_populate_range(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	struct amdxdna_umap *mapp;
+	unsigned long timeout;
+	struct mm_struct *mm;
+	bool found;
+	int ret;
+
+	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+again:
+	found = false;
+	down_write(&xdna->notifier_lock);
+	list_for_each_entry(mapp, &abo->mem.umap_list, node) {
+		if (mapp->invalid) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		abo->mem.map_invalid = false;
+		up_write(&xdna->notifier_lock);
+		return 0;
+	}
+	kref_get(&mapp->refcnt);
+	up_write(&xdna->notifier_lock);
+
+	XDNA_DBG(xdna, "populate memory range %lx %lx",
+		 mapp->vma->vm_start, mapp->vma->vm_end);
+	mm = mapp->notifier.mm;
+	if (!mmget_not_zero(mm)) {
+		amdxdna_umap_put(mapp);
+		return -EFAULT;
+	}
+
+	mapp->range.notifier_seq = mmu_interval_read_begin(&mapp->notifier);
+	mmap_read_lock(mm);
+	ret = hmm_range_fault(&mapp->range);
+	mmap_read_unlock(mm);
+	if (ret) {
+		if (time_after(jiffies, timeout)) {
+			ret = -ETIME;
+			goto put_mm;
+		}
+
+		if (ret == -EBUSY) {
+			amdxdna_umap_put(mapp);
+			goto again;
+		}
+
+		goto put_mm;
+	}
+
+	down_write(&xdna->notifier_lock);
+	if (mmu_interval_read_retry(&mapp->notifier, mapp->range.notifier_seq)) {
+		up_write(&xdna->notifier_lock);
+		amdxdna_umap_put(mapp);
+		goto again;
+	}
+	mapp->invalid = false;
+	up_write(&xdna->notifier_lock);
+	amdxdna_umap_put(mapp);
+	goto again;
+
+put_mm:
+	amdxdna_umap_put(mapp);
+	mmput(mm);
+	return ret;
+}
+
+int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct ww_acquire_ctx acquire_ctx;
+	struct dma_fence_chain *chain;
+	struct amdxdna_gem_obj *abo;
+	unsigned long timeout = 0;
+	int ret, i;
+
+	ret = down_interruptible(&hwctx->priv->job_sem);
+	if (ret) {
+		XDNA_ERR(xdna, "Grab job sem failed, ret %d", ret);
+		return ret;
+	}
+
+	chain = dma_fence_chain_alloc();
+	if (!chain) {
+		XDNA_ERR(xdna, "Alloc fence chain failed");
+		ret = -ENOMEM;
+		goto up_sem;
+	}
+
+	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx,
+				 hwctx->client->filp->client_id);
+	if (ret) {
+		XDNA_ERR(xdna, "DRM job init failed, ret %d", ret);
+		goto free_chain;
+	}
+
+retry:
+	ret = drm_gem_lock_reservations(job->bos, job->bo_cnt, &acquire_ctx);
+	if (ret) {
+		XDNA_WARN(xdna, "Failed to lock BOs, ret %d", ret);
+		goto cleanup_job;
+	}
+
+	for (i = 0; i < job->bo_cnt; i++) {
+		ret = dma_resv_reserve_fences(job->bos[i]->resv, 1);
+		if (ret) {
+			XDNA_WARN(xdna, "Failed to reserve fences %d", ret);
+			drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx);
+			goto cleanup_job;
+		}
+	}
+
+	down_read(&xdna->notifier_lock);
+	for (i = 0; i < job->bo_cnt; i++) {
+		abo = to_xdna_obj(job->bos[i]);
+		if (abo->mem.map_invalid) {
+			up_read(&xdna->notifier_lock);
+			drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx);
+			if (!timeout) {
+				timeout = jiffies +
+					msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+			} else if (time_after(jiffies, timeout)) {
+				ret = -ETIME;
+				goto cleanup_job;
+			}
+
+			ret = aie2_populate_range(abo);
+			if (ret)
+				goto cleanup_job;
+			goto retry;
+		}
+	}
+
+	mutex_lock(&hwctx->priv->io_lock);
+	drm_sched_job_arm(&job->base);
+	job->out_fence = dma_fence_get(&job->base.s_fence->finished);
+	for (i = 0; i < job->bo_cnt; i++)
+		dma_resv_add_fence(job->bos[i]->resv, job->out_fence, DMA_RESV_USAGE_WRITE);
+	job->seq = hwctx->priv->seq++;
+	kref_get(&job->refcnt);
+	drm_sched_entity_push_job(&job->base);
+
+	*seq = job->seq;
+	drm_syncobj_add_point(hwctx->priv->syncobj, chain, job->out_fence, *seq);
+	mutex_unlock(&hwctx->priv->io_lock);
+
+	up_read(&xdna->notifier_lock);
+	drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx);
+
+	aie2_job_put(job);
+	atomic64_inc(&hwctx->job_submit_cnt);
+
+	return 0;
+
+cleanup_job:
+	drm_sched_job_cleanup(&job->base);
+free_chain:
+	dma_fence_chain_free(chain);
+up_sem:
+	up(&hwctx->priv->job_sem);
+	job->job_done = true;
+	return ret;
+}
+
+void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo,
+			 unsigned long cur_seq)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	struct drm_gem_object *gobj = to_gobj(abo);
+	long ret;
+
+	ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP,
+				    true, MAX_SCHEDULE_TIMEOUT);
+	if (!ret || ret == -ERESTARTSYS)
+		XDNA_ERR(xdna, "Failed to wait for bo, ret %ld", ret);
+}
diff --git a/drivers/accel/amdxdna/aie2_error.c b/drivers/accel/amdxdna/aie2_error.c
new file mode 100644
index 000000000000..5ee905632a39
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_error.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/drm_cache.h>
+#include <drm/drm_device.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/dma-mapping.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+
+#include "aie2_msg_priv.h"
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+struct async_event {
+	struct amdxdna_dev_hdl		*ndev;
+	struct async_event_msg_resp	resp;
+	struct workqueue_struct		*wq;
+	struct work_struct		work;
+	u8				*buf;
+	dma_addr_t			addr;
+	u32				size;
+};
+
+struct async_events {
+	struct workqueue_struct		*wq;
+	u8				*buf;
+	dma_addr_t			addr;
+	u32				size;
+	u32				event_cnt;
+	struct async_event		event[] __counted_by(event_cnt);
+};
+
+/*
+ * Below enum, struct and lookup tables are porting from XAIE util header file.
+ *
+ * Below data is defined by AIE device and it is used for decode error message
+ * from the device.
+ */
+
+enum aie_module_type {
+	AIE_MEM_MOD = 0,
+	AIE_CORE_MOD,
+	AIE_PL_MOD,
+};
+
+enum aie_error_category {
+	AIE_ERROR_SATURATION = 0,
+	AIE_ERROR_FP,
+	AIE_ERROR_STREAM,
+	AIE_ERROR_ACCESS,
+	AIE_ERROR_BUS,
+	AIE_ERROR_INSTRUCTION,
+	AIE_ERROR_ECC,
+	AIE_ERROR_LOCK,
+	AIE_ERROR_DMA,
+	AIE_ERROR_MEM_PARITY,
+	/* Unknown is not from XAIE, added for better category */
+	AIE_ERROR_UNKNOWN,
+};
+
+/* Don't pack, unless XAIE side changed */
+struct aie_error {
+	__u8			row;
+	__u8			col;
+	__u32			mod_type;
+	__u8			event_id;
+};
+
+struct aie_err_info {
+	u32			err_cnt;
+	u32			ret_code;
+	u32			rsvd;
+	struct aie_error	payload[] __counted_by(err_cnt);
+};
+
+struct aie_event_category {
+	u8			event_id;
+	enum aie_error_category category;
+};
+
+#define EVENT_CATEGORY(id, cat) { id, cat }
+static const struct aie_event_category aie_ml_mem_event_cat[] = {
+	EVENT_CATEGORY(88U,  AIE_ERROR_ECC),
+	EVENT_CATEGORY(90U,  AIE_ERROR_ECC),
+	EVENT_CATEGORY(91U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(92U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(93U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(94U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(95U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(96U,  AIE_ERROR_MEM_PARITY),
+	EVENT_CATEGORY(97U,  AIE_ERROR_DMA),
+	EVENT_CATEGORY(98U,  AIE_ERROR_DMA),
+	EVENT_CATEGORY(99U,  AIE_ERROR_DMA),
+	EVENT_CATEGORY(100U, AIE_ERROR_DMA),
+	EVENT_CATEGORY(101U, AIE_ERROR_LOCK),
+};
+
+static const struct aie_event_category aie_ml_core_event_cat[] = {
+	EVENT_CATEGORY(55U, AIE_ERROR_ACCESS),
+	EVENT_CATEGORY(56U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(57U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(58U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(59U, AIE_ERROR_INSTRUCTION),
+	EVENT_CATEGORY(60U, AIE_ERROR_ACCESS),
+	EVENT_CATEGORY(62U, AIE_ERROR_ECC),
+	EVENT_CATEGORY(64U, AIE_ERROR_ECC),
+	EVENT_CATEGORY(65U, AIE_ERROR_ACCESS),
+	EVENT_CATEGORY(66U, AIE_ERROR_ACCESS),
+	EVENT_CATEGORY(67U, AIE_ERROR_LOCK),
+	EVENT_CATEGORY(70U, AIE_ERROR_INSTRUCTION),
+	EVENT_CATEGORY(71U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(72U, AIE_ERROR_BUS),
+};
+
+static const struct aie_event_category aie_ml_mem_tile_event_cat[] = {
+	EVENT_CATEGORY(130U, AIE_ERROR_ECC),
+	EVENT_CATEGORY(132U, AIE_ERROR_ECC),
+	EVENT_CATEGORY(133U, AIE_ERROR_DMA),
+	EVENT_CATEGORY(134U, AIE_ERROR_DMA),
+	EVENT_CATEGORY(135U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(136U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(137U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(138U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(139U, AIE_ERROR_LOCK),
+};
+
+static const struct aie_event_category aie_ml_shim_tile_event_cat[] = {
+	EVENT_CATEGORY(64U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(65U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(66U, AIE_ERROR_STREAM),
+	EVENT_CATEGORY(67U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(68U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(69U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(70U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(71U, AIE_ERROR_BUS),
+	EVENT_CATEGORY(72U, AIE_ERROR_DMA),
+	EVENT_CATEGORY(73U, AIE_ERROR_DMA),
+	EVENT_CATEGORY(74U, AIE_ERROR_LOCK),
+};
+
+static enum aie_error_category
+aie_get_error_category(u8 row, u8 event_id, enum aie_module_type mod_type)
+{
+	const struct aie_event_category *lut;
+	int num_entry;
+	int i;
+
+	switch (mod_type) {
+	case AIE_PL_MOD:
+		lut = aie_ml_shim_tile_event_cat;
+		num_entry = ARRAY_SIZE(aie_ml_shim_tile_event_cat);
+		break;
+	case AIE_CORE_MOD:
+		lut = aie_ml_core_event_cat;
+		num_entry = ARRAY_SIZE(aie_ml_core_event_cat);
+		break;
+	case AIE_MEM_MOD:
+		if (row == 1) {
+			lut = aie_ml_mem_tile_event_cat;
+			num_entry = ARRAY_SIZE(aie_ml_mem_tile_event_cat);
+		} else {
+			lut = aie_ml_mem_event_cat;
+			num_entry = ARRAY_SIZE(aie_ml_mem_event_cat);
+		}
+		break;
+	default:
+		return AIE_ERROR_UNKNOWN;
+	}
+
+	for (i = 0; i < num_entry; i++) {
+		if (event_id != lut[i].event_id)
+			continue;
+
+		return lut[i].category;
+	}
+
+	return AIE_ERROR_UNKNOWN;
+}
+
+static u32 aie2_error_backtrack(struct amdxdna_dev_hdl *ndev, void *err_info, u32 num_err)
+{
+	struct aie_error *errs = err_info;
+	u32 err_col = 0; /* assume that AIE has less than 32 columns */
+	int i;
+
+	/* Get err column bitmap */
+	for (i = 0; i < num_err; i++) {
+		struct aie_error *err = &errs[i];
+		enum aie_error_category cat;
+
+		cat = aie_get_error_category(err->row, err->event_id, err->mod_type);
+		XDNA_ERR(ndev->xdna, "Row: %d, Col: %d, module %d, event ID %d, category %d",
+			 err->row, err->col, err->mod_type,
+			 err->event_id, cat);
+
+		if (err->col >= 32) {
+			XDNA_WARN(ndev->xdna, "Invalid column number");
+			break;
+		}
+
+		err_col |= (1 << err->col);
+	}
+
+	return err_col;
+}
+
+static int aie2_error_async_cb(void *handle, void __iomem *data, size_t size)
+{
+	struct async_event *e = handle;
+
+	if (data) {
+		e->resp.type = readl(data + offsetof(struct async_event_msg_resp, type));
+		wmb(); /* Update status in the end, so that no lock for here */
+		e->resp.status = readl(data + offsetof(struct async_event_msg_resp, status));
+	}
+	queue_work(e->wq, &e->work);
+	return 0;
+}
+
+static int aie2_error_event_send(struct async_event *e)
+{
+	drm_clflush_virt_range(e->buf, e->size); /* device can access */
+	return aie2_register_asyn_event_msg(e->ndev, e->addr, e->size, e,
+					    aie2_error_async_cb);
+}
+
+static void aie2_error_worker(struct work_struct *err_work)
+{
+	struct aie_err_info *info;
+	struct amdxdna_dev *xdna;
+	struct async_event *e;
+	u32 max_err;
+	u32 err_col;
+
+	e = container_of(err_work, struct async_event, work);
+
+	xdna = e->ndev->xdna;
+
+	if (e->resp.status == MAX_AIE2_STATUS_CODE)
+		return;
+
+	e->resp.status = MAX_AIE2_STATUS_CODE;
+
+	print_hex_dump_debug("AIE error: ", DUMP_PREFIX_OFFSET, 16, 4,
+			     e->buf, 0x100, false);
+
+	info = (struct aie_err_info *)e->buf;
+	XDNA_DBG(xdna, "Error count %d return code %d", info->err_cnt, info->ret_code);
+
+	max_err = (e->size - sizeof(*info)) / sizeof(struct aie_error);
+	if (unlikely(info->err_cnt > max_err)) {
+		WARN_ONCE(1, "Error count too large %d\n", info->err_cnt);
+		return;
+	}
+	err_col = aie2_error_backtrack(e->ndev, info->payload, info->err_cnt);
+	if (!err_col) {
+		XDNA_WARN(xdna, "Did not get error column");
+		return;
+	}
+
+	mutex_lock(&xdna->dev_lock);
+	/* Re-sent this event to firmware */
+	if (aie2_error_event_send(e))
+		XDNA_WARN(xdna, "Unable to register async event");
+	mutex_unlock(&xdna->dev_lock);
+}
+
+int aie2_error_async_events_send(struct amdxdna_dev_hdl *ndev)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct async_event *e;
+	int i, ret;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+	for (i = 0; i < ndev->async_events->event_cnt; i++) {
+		e = &ndev->async_events->event[i];
+		ret = aie2_error_event_send(e);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct async_events *events;
+
+	events = ndev->async_events;
+
+	mutex_unlock(&xdna->dev_lock);
+	destroy_workqueue(events->wq);
+	mutex_lock(&xdna->dev_lock);
+
+	dma_free_noncoherent(xdna->ddev.dev, events->size, events->buf,
+			     events->addr, DMA_FROM_DEVICE);
+	kfree(events);
+}
+
+int aie2_error_async_events_alloc(struct amdxdna_dev_hdl *ndev)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+	u32 total_col = ndev->total_col;
+	u32 total_size = ASYNC_BUF_SIZE * total_col;
+	struct async_events *events;
+	int i, ret;
+
+	events = kzalloc(struct_size(events, event, total_col), GFP_KERNEL);
+	if (!events)
+		return -ENOMEM;
+
+	events->buf = dma_alloc_noncoherent(xdna->ddev.dev, total_size, &events->addr,
+					    DMA_FROM_DEVICE, GFP_KERNEL);
+	if (!events->buf) {
+		ret = -ENOMEM;
+		goto free_events;
+	}
+	events->size = total_size;
+	events->event_cnt = total_col;
+
+	events->wq = alloc_ordered_workqueue("async_wq", 0);
+	if (!events->wq) {
+		ret = -ENOMEM;
+		goto free_buf;
+	}
+
+	for (i = 0; i < events->event_cnt; i++) {
+		struct async_event *e = &events->event[i];
+		u32 offset = i * ASYNC_BUF_SIZE;
+
+		e->ndev = ndev;
+		e->wq = events->wq;
+		e->buf = &events->buf[offset];
+		e->addr = events->addr + offset;
+		e->size = ASYNC_BUF_SIZE;
+		e->resp.status = MAX_AIE2_STATUS_CODE;
+		INIT_WORK(&e->work, aie2_error_worker);
+	}
+
+	ndev->async_events = events;
+
+	XDNA_DBG(xdna, "Async event count %d, buf total size 0x%x",
+		 events->event_cnt, events->size);
+	return 0;
+
+free_buf:
+	dma_free_noncoherent(xdna->ddev.dev, events->size, events->buf,
+			     events->addr, DMA_FROM_DEVICE);
+free_events:
+	kfree(events);
+	return ret;
+}
diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
new file mode 100644
index 000000000000..9caad083543d
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_cache.h>
+#include <drm/drm_device.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/bitfield.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/xarray.h>
+
+#include "aie2_msg_priv.h"
+#include "aie2_pci.h"
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_mailbox_helper.h"
+#include "amdxdna_pci_drv.h"
+
+#define DECLARE_AIE2_MSG(name, op) \
+	DECLARE_XDNA_MSG_COMMON(name, op, MAX_AIE2_STATUS_CODE)
+
+static int aie2_send_mgmt_msg_wait(struct amdxdna_dev_hdl *ndev,
+				   struct xdna_mailbox_msg *msg)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct xdna_notify *hdl = msg->handle;
+	int ret;
+
+	if (!ndev->mgmt_chann)
+		return -ENODEV;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+	ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg);
+	if (ret == -ETIME) {
+		xdna_mailbox_stop_channel(ndev->mgmt_chann);
+		xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+		ndev->mgmt_chann = NULL;
+	}
+
+	if (!ret && *hdl->data != AIE2_STATUS_SUCCESS) {
+		XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x",
+			 msg->opcode, *hdl->data);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev)
+{
+	DECLARE_AIE2_MSG(suspend, MSG_OP_SUSPEND);
+
+	return aie2_send_mgmt_msg_wait(ndev, &msg);
+}
+
+int aie2_resume_fw(struct amdxdna_dev_hdl *ndev)
+{
+	DECLARE_AIE2_MSG(suspend, MSG_OP_RESUME);
+
+	return aie2_send_mgmt_msg_wait(ndev, &msg);
+}
+
+int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value)
+{
+	DECLARE_AIE2_MSG(set_runtime_cfg, MSG_OP_SET_RUNTIME_CONFIG);
+	int ret;
+
+	req.type = type;
+	req.value = value;
+
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Failed to set runtime config, ret %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value)
+{
+	DECLARE_AIE2_MSG(get_runtime_cfg, MSG_OP_GET_RUNTIME_CONFIG);
+	int ret;
+
+	req.type = type;
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Failed to get runtime config, ret %d", ret);
+		return ret;
+	}
+
+	*value = resp.value;
+	return 0;
+}
+
+int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid)
+{
+	DECLARE_AIE2_MSG(assign_mgmt_pasid, MSG_OP_ASSIGN_MGMT_PASID);
+
+	req.pasid = pasid;
+
+	return aie2_send_mgmt_msg_wait(ndev, &msg);
+}
+
+int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version)
+{
+	DECLARE_AIE2_MSG(aie_version_info, MSG_OP_QUERY_AIE_VERSION);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	int ret;
+
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		return ret;
+
+	XDNA_DBG(xdna, "Query AIE version - major: %u minor: %u completed",
+		 resp.major, resp.minor);
+
+	version->major = resp.major;
+	version->minor = resp.minor;
+
+	return 0;
+}
+
+int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata)
+{
+	DECLARE_AIE2_MSG(aie_tile_info, MSG_OP_QUERY_AIE_TILE_INFO);
+	int ret;
+
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		return ret;
+
+	metadata->size = resp.info.size;
+	metadata->cols = resp.info.cols;
+	metadata->rows = resp.info.rows;
+
+	metadata->version.major = resp.info.major;
+	metadata->version.minor = resp.info.minor;
+
+	metadata->core.row_count = resp.info.core_rows;
+	metadata->core.row_start = resp.info.core_row_start;
+	metadata->core.dma_channel_count = resp.info.core_dma_channels;
+	metadata->core.lock_count = resp.info.core_locks;
+	metadata->core.event_reg_count = resp.info.core_events;
+
+	metadata->mem.row_count = resp.info.mem_rows;
+	metadata->mem.row_start = resp.info.mem_row_start;
+	metadata->mem.dma_channel_count = resp.info.mem_dma_channels;
+	metadata->mem.lock_count = resp.info.mem_locks;
+	metadata->mem.event_reg_count = resp.info.mem_events;
+
+	metadata->shim.row_count = resp.info.shim_rows;
+	metadata->shim.row_start = resp.info.shim_row_start;
+	metadata->shim.dma_channel_count = resp.info.shim_dma_channels;
+	metadata->shim.lock_count = resp.info.shim_locks;
+	metadata->shim.event_reg_count = resp.info.shim_events;
+
+	return 0;
+}
+
+int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
+				struct amdxdna_fw_ver *fw_ver)
+{
+	DECLARE_AIE2_MSG(firmware_version, MSG_OP_GET_FIRMWARE_VERSION);
+	int ret;
+
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		return ret;
+
+	fw_ver->major = resp.major;
+	fw_ver->minor = resp.minor;
+	fw_ver->sub = resp.sub;
+	fw_ver->build = resp.build;
+
+	return 0;
+}
+
+int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx)
+{
+	DECLARE_AIE2_MSG(create_ctx, MSG_OP_CREATE_CONTEXT);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct xdna_mailbox_chann_res x2i;
+	struct xdna_mailbox_chann_res i2x;
+	struct cq_pair *cq_pair;
+	u32 intr_reg;
+	int ret;
+
+	req.aie_type = 1;
+	req.start_col = hwctx->start_col;
+	req.num_col = hwctx->num_col;
+	req.num_cq_pairs_requested = 1;
+	req.pasid = hwctx->client->pasid;
+	req.context_priority = 2;
+
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		return ret;
+
+	hwctx->fw_ctx_id = resp.context_id;
+	WARN_ONCE(hwctx->fw_ctx_id == -1, "Unexpected context id");
+
+	cq_pair = &resp.cq_pair[0];
+	x2i.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.head_addr);
+	x2i.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.tail_addr);
+	x2i.rb_start_addr   = AIE2_SRAM_OFF(ndev, cq_pair->x2i_q.buf_addr);
+	x2i.rb_size	    = cq_pair->x2i_q.buf_size;
+
+	i2x.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.head_addr);
+	i2x.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.tail_addr);
+	i2x.rb_start_addr   = AIE2_SRAM_OFF(ndev, cq_pair->i2x_q.buf_addr);
+	i2x.rb_size	    = cq_pair->i2x_q.buf_size;
+
+	ret = pci_irq_vector(to_pci_dev(xdna->ddev.dev), resp.msix_id);
+	if (ret == -EINVAL) {
+		XDNA_ERR(xdna, "not able to create channel");
+		goto out_destroy_context;
+	}
+
+	intr_reg = i2x.mb_head_ptr_reg + 4;
+	hwctx->priv->mbox_chann = xdna_mailbox_create_channel(ndev->mbox, &x2i, &i2x,
+							      intr_reg, ret);
+	if (!hwctx->priv->mbox_chann) {
+		XDNA_ERR(xdna, "not able to create channel");
+		ret = -EINVAL;
+		goto out_destroy_context;
+	}
+
+	XDNA_DBG(xdna, "%s mailbox channel irq: %d, msix_id: %d",
+		 hwctx->name, ret, resp.msix_id);
+	XDNA_DBG(xdna, "%s created fw ctx %d pasid %d", hwctx->name,
+		 hwctx->fw_ctx_id, hwctx->client->pasid);
+
+	return 0;
+
+out_destroy_context:
+	aie2_destroy_context(ndev, hwctx);
+	return ret;
+}
+
+int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx)
+{
+	DECLARE_AIE2_MSG(destroy_ctx, MSG_OP_DESTROY_CONTEXT);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	int ret;
+
+	if (hwctx->fw_ctx_id == -1)
+		return 0;
+
+	xdna_mailbox_stop_channel(hwctx->priv->mbox_chann);
+
+	req.context_id = hwctx->fw_ctx_id;
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		XDNA_WARN(xdna, "%s destroy context failed, ret %d", hwctx->name, ret);
+
+	xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann);
+	XDNA_DBG(xdna, "%s destroyed fw ctx %d", hwctx->name,
+		 hwctx->fw_ctx_id);
+	hwctx->priv->mbox_chann = NULL;
+	hwctx->fw_ctx_id = -1;
+
+	return ret;
+}
+
+int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size)
+{
+	DECLARE_AIE2_MSG(map_host_buffer, MSG_OP_MAP_HOST_BUFFER);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	int ret;
+
+	req.context_id = context_id;
+	req.buf_addr = addr;
+	req.buf_size = size;
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret)
+		return ret;
+
+	XDNA_DBG(xdna, "fw ctx %d map host buf addr 0x%llx size 0x%llx",
+		 context_id, addr, size);
+
+	return 0;
+}
+
+static int amdxdna_hwctx_col_map(struct amdxdna_hwctx *hwctx, void *arg)
+{
+	u32 *bitmap = arg;
+
+	*bitmap |= GENMASK(hwctx->start_col + hwctx->num_col - 1, hwctx->start_col);
+
+	return 0;
+}
+
+int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
+		      u32 size, u32 *cols_filled)
+{
+	DECLARE_AIE2_MSG(aie_column_info, MSG_OP_QUERY_COL_STATUS);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct amdxdna_client *client;
+	dma_addr_t dma_addr;
+	u32 aie_bitmap = 0;
+	u8 *buff_addr;
+	int ret;
+
+	buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr,
+					  DMA_FROM_DEVICE, GFP_KERNEL);
+	if (!buff_addr)
+		return -ENOMEM;
+
+	/* Go through each hardware context and mark the AIE columns that are active */
+	list_for_each_entry(client, &xdna->client_list, node)
+		amdxdna_hwctx_walk(client, &aie_bitmap, amdxdna_hwctx_col_map);
+
+	*cols_filled = 0;
+	req.dump_buff_addr = dma_addr;
+	req.dump_buff_size = size;
+	req.num_cols = hweight32(aie_bitmap);
+	req.aie_bitmap = aie_bitmap;
+
+	drm_clflush_virt_range(buff_addr, size); /* device can access */
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret) {
+		XDNA_ERR(xdna, "Error during NPU query, status %d", ret);
+		goto fail;
+	}
+
+	if (resp.status != AIE2_STATUS_SUCCESS) {
+		XDNA_ERR(xdna, "Query NPU status failed, status 0x%x", resp.status);
+		ret = -EINVAL;
+		goto fail;
+	}
+	XDNA_DBG(xdna, "Query NPU status completed");
+
+	if (size < resp.size) {
+		ret = -EINVAL;
+		XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size);
+		goto fail;
+	}
+
+	if (copy_to_user(buf, buff_addr, resp.size)) {
+		ret = -EFAULT;
+		XDNA_ERR(xdna, "Failed to copy NPU status to user space");
+		goto fail;
+	}
+
+	*cols_filled = aie_bitmap;
+
+fail:
+	dma_free_noncoherent(xdna->ddev.dev, size, buff_addr, dma_addr, DMA_FROM_DEVICE);
+	return ret;
+}
+
+int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size,
+				 void *handle, int (*cb)(void*, void __iomem *, size_t))
+{
+	struct async_event_msg_req req = { 0 };
+	struct xdna_mailbox_msg msg = {
+		.send_data = (u8 *)&req,
+		.send_size = sizeof(req),
+		.handle = handle,
+		.opcode = MSG_OP_REGISTER_ASYNC_EVENT_MSG,
+		.notify_cb = cb,
+	};
+
+	req.buf_addr = addr;
+	req.buf_size = size;
+
+	XDNA_DBG(ndev->xdna, "Register addr 0x%llx size 0x%x", addr, size);
+	return xdna_mailbox_send_msg(ndev->mgmt_chann, &msg, TX_TIMEOUT);
+}
+
+int aie2_config_cu(struct amdxdna_hwctx *hwctx)
+{
+	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	u32 shift = xdna->dev_info->dev_mem_buf_shift;
+	DECLARE_AIE2_MSG(config_cu, MSG_OP_CONFIG_CU);
+	struct drm_gem_object *gobj;
+	struct amdxdna_gem_obj *abo;
+	int ret, i;
+
+	if (!chann)
+		return -ENODEV;
+
+	if (hwctx->cus->num_cus > MAX_NUM_CUS) {
+		XDNA_DBG(xdna, "Exceed maximum CU %d", MAX_NUM_CUS);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < hwctx->cus->num_cus; i++) {
+		struct amdxdna_cu_config *cu = &hwctx->cus->cu_configs[i];
+
+		if (XDNA_MBZ_DBG(xdna, cu->pad, sizeof(cu->pad)))
+			return -EINVAL;
+
+		gobj = drm_gem_object_lookup(hwctx->client->filp, cu->cu_bo);
+		if (!gobj) {
+			XDNA_ERR(xdna, "Lookup GEM object failed");
+			return -EINVAL;
+		}
+		abo = to_xdna_obj(gobj);
+
+		if (abo->type != AMDXDNA_BO_DEV) {
+			drm_gem_object_put(gobj);
+			XDNA_ERR(xdna, "Invalid BO type");
+			return -EINVAL;
+		}
+
+		req.cfgs[i] = FIELD_PREP(AIE2_MSG_CFG_CU_PDI_ADDR,
+					 abo->mem.dev_addr >> shift);
+		req.cfgs[i] |= FIELD_PREP(AIE2_MSG_CFG_CU_FUNC, cu->cu_func);
+		XDNA_DBG(xdna, "CU %d full addr 0x%llx, cfg 0x%x", i,
+			 abo->mem.dev_addr, req.cfgs[i]);
+		drm_gem_object_put(gobj);
+	}
+	req.num_cus = hwctx->cus->num_cus;
+
+	ret = xdna_send_msg_wait(xdna, chann, &msg);
+	if (ret == -ETIME)
+		aie2_destroy_context(xdna->dev_handle, hwctx);
+
+	if (resp.status == AIE2_STATUS_SUCCESS) {
+		XDNA_DBG(xdna, "Configure %d CUs, ret %d", req.num_cus, ret);
+		return 0;
+	}
+
+	XDNA_ERR(xdna, "Command opcode 0x%x failed, status 0x%x ret %d",
+		 msg.opcode, resp.status, ret);
+	return ret;
+}
+
+int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
+		 int (*notify_cb)(void *, void __iomem *, size_t))
+{
+	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct amdxdna_gem_obj *cmd_abo = job->cmd_bo;
+	union {
+		struct execute_buffer_req ebuf;
+		struct exec_dpu_req dpu;
+	} req;
+	struct xdna_mailbox_msg msg;
+	u32 payload_len;
+	void *payload;
+	int cu_idx;
+	int ret;
+	u32 op;
+
+	if (!chann)
+		return -ENODEV;
+
+	payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len);
+	if (!payload) {
+		XDNA_ERR(xdna, "Invalid command, cannot get payload");
+		return -EINVAL;
+	}
+
+	cu_idx = amdxdna_cmd_get_cu_idx(cmd_abo);
+	if (cu_idx < 0) {
+		XDNA_DBG(xdna, "Invalid cu idx");
+		return -EINVAL;
+	}
+
+	op = amdxdna_cmd_get_op(cmd_abo);
+	switch (op) {
+	case ERT_START_CU:
+		if (unlikely(payload_len > sizeof(req.ebuf.payload)))
+			XDNA_DBG(xdna, "Invalid ebuf payload len: %d", payload_len);
+		req.ebuf.cu_idx = cu_idx;
+		memcpy(req.ebuf.payload, payload, sizeof(req.ebuf.payload));
+		msg.send_size = sizeof(req.ebuf);
+		msg.opcode = MSG_OP_EXECUTE_BUFFER_CF;
+		break;
+	case ERT_START_NPU: {
+		struct amdxdna_cmd_start_npu *sn = payload;
+
+		if (unlikely(payload_len - sizeof(*sn) > sizeof(req.dpu.payload)))
+			XDNA_DBG(xdna, "Invalid dpu payload len: %d", payload_len);
+		req.dpu.inst_buf_addr = sn->buffer;
+		req.dpu.inst_size = sn->buffer_size;
+		req.dpu.inst_prop_cnt = sn->prop_count;
+		req.dpu.cu_idx = cu_idx;
+		memcpy(req.dpu.payload, sn->prop_args, sizeof(req.dpu.payload));
+		msg.send_size = sizeof(req.dpu);
+		msg.opcode = MSG_OP_EXEC_DPU;
+		break;
+	}
+	default:
+		XDNA_DBG(xdna, "Invalid ERT cmd op code: %d", op);
+		return -EINVAL;
+	}
+	msg.handle = job;
+	msg.notify_cb = notify_cb;
+	msg.send_data = (u8 *)&req;
+	print_hex_dump_debug("cmd: ", DUMP_PREFIX_OFFSET, 16, 4, &req,
+			     0x40, false);
+
+	ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(xdna, "Send message failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+aie2_cmdlist_fill_one_slot_cf(void *cmd_buf, u32 offset,
+			      struct amdxdna_gem_obj *abo, u32 *size)
+{
+	struct cmd_chain_slot_execbuf_cf *buf = cmd_buf + offset;
+	int cu_idx = amdxdna_cmd_get_cu_idx(abo);
+	u32 payload_len;
+	void *payload;
+
+	if (cu_idx < 0)
+		return -EINVAL;
+
+	payload = amdxdna_cmd_get_payload(abo, &payload_len);
+	if (!payload)
+		return -EINVAL;
+
+	if (!slot_has_space(*buf, offset, payload_len))
+		return -ENOSPC;
+
+	buf->cu_idx = cu_idx;
+	buf->arg_cnt = payload_len / sizeof(u32);
+	memcpy(buf->args, payload, payload_len);
+	/* Accurate buf size to hint firmware to do necessary copy */
+	*size = sizeof(*buf) + payload_len;
+	return 0;
+}
+
+static int
+aie2_cmdlist_fill_one_slot_dpu(void *cmd_buf, u32 offset,
+			       struct amdxdna_gem_obj *abo, u32 *size)
+{
+	struct cmd_chain_slot_dpu *buf = cmd_buf + offset;
+	int cu_idx = amdxdna_cmd_get_cu_idx(abo);
+	struct amdxdna_cmd_start_npu *sn;
+	u32 payload_len;
+	void *payload;
+	u32 arg_sz;
+
+	if (cu_idx < 0)
+		return -EINVAL;
+
+	payload = amdxdna_cmd_get_payload(abo, &payload_len);
+	if (!payload)
+		return -EINVAL;
+	sn = payload;
+	arg_sz = payload_len - sizeof(*sn);
+	if (payload_len < sizeof(*sn) || arg_sz > MAX_DPU_ARGS_SIZE)
+		return -EINVAL;
+
+	if (!slot_has_space(*buf, offset, arg_sz))
+		return -ENOSPC;
+
+	buf->inst_buf_addr = sn->buffer;
+	buf->inst_size = sn->buffer_size;
+	buf->inst_prop_cnt = sn->prop_count;
+	buf->cu_idx = cu_idx;
+	buf->arg_cnt = arg_sz / sizeof(u32);
+	memcpy(buf->args, sn->prop_args, arg_sz);
+
+	/* Accurate buf size to hint firmware to do necessary copy */
+	*size = sizeof(*buf) + arg_sz;
+	return 0;
+}
+
+static int
+aie2_cmdlist_fill_one_slot(u32 op, struct amdxdna_gem_obj *cmdbuf_abo, u32 offset,
+			   struct amdxdna_gem_obj *abo, u32 *size)
+{
+	u32 this_op = amdxdna_cmd_get_op(abo);
+	void *cmd_buf = cmdbuf_abo->mem.kva;
+	int ret;
+
+	if (this_op != op) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	switch (op) {
+	case ERT_START_CU:
+		ret = aie2_cmdlist_fill_one_slot_cf(cmd_buf, offset, abo, size);
+		break;
+	case ERT_START_NPU:
+		ret = aie2_cmdlist_fill_one_slot_dpu(cmd_buf, offset, abo, size);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+done:
+	if (ret) {
+		XDNA_ERR(abo->client->xdna, "Can't fill slot for cmd op %d ret %d",
+			 op, ret);
+	}
+	return ret;
+}
+
+static inline struct amdxdna_gem_obj *
+aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job)
+{
+	int idx = get_job_idx(job->seq);
+
+	return job->hwctx->priv->cmd_buf[idx];
+}
+
+static void
+aie2_cmdlist_prepare_request(struct cmd_chain_req *req,
+			     struct amdxdna_gem_obj *cmdbuf_abo, u32 size, u32 cnt)
+{
+	req->buf_addr = cmdbuf_abo->mem.dev_addr;
+	req->buf_size = size;
+	req->count = cnt;
+	drm_clflush_virt_range(cmdbuf_abo->mem.kva, size);
+	XDNA_DBG(cmdbuf_abo->client->xdna, "Command buf addr 0x%llx size 0x%x count %d",
+		 req->buf_addr, size, cnt);
+}
+
+static inline u32
+aie2_cmd_op_to_msg_op(u32 op)
+{
+	switch (op) {
+	case ERT_START_CU:
+		return MSG_OP_CHAIN_EXEC_BUFFER_CF;
+	case ERT_START_NPU:
+		return MSG_OP_CHAIN_EXEC_DPU;
+	default:
+		return MSG_OP_MAX_OPCODE;
+	}
+}
+
+int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx,
+			       struct amdxdna_sched_job *job,
+			       int (*notify_cb)(void *, void __iomem *, size_t))
+{
+	struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job);
+	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
+	struct amdxdna_client *client = hwctx->client;
+	struct amdxdna_gem_obj *cmd_abo = job->cmd_bo;
+	struct amdxdna_cmd_chain *payload;
+	struct xdna_mailbox_msg msg;
+	struct cmd_chain_req req;
+	u32 payload_len;
+	u32 offset = 0;
+	u32 size;
+	int ret;
+	u32 op;
+	u32 i;
+
+	op = amdxdna_cmd_get_op(cmd_abo);
+	payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len);
+	if (op != ERT_CMD_CHAIN || !payload ||
+	    payload_len < struct_size(payload, data, payload->command_count))
+		return -EINVAL;
+
+	for (i = 0; i < payload->command_count; i++) {
+		u32 boh = (u32)(payload->data[i]);
+		struct amdxdna_gem_obj *abo;
+
+		abo = amdxdna_gem_get_obj(client, boh, AMDXDNA_BO_CMD);
+		if (!abo) {
+			XDNA_ERR(client->xdna, "Failed to find cmd BO %d", boh);
+			return -ENOENT;
+		}
+
+		/* All sub-cmd should have same op, use the first one. */
+		if (i == 0)
+			op = amdxdna_cmd_get_op(abo);
+
+		ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, offset, abo, &size);
+		amdxdna_gem_put_obj(abo);
+		if (ret)
+			return -EINVAL;
+
+		offset += size;
+	}
+
+	/* The offset is the accumulated total size of the cmd buffer */
+	aie2_cmdlist_prepare_request(&req, cmdbuf_abo, offset, payload->command_count);
+
+	msg.opcode = aie2_cmd_op_to_msg_op(op);
+	if (msg.opcode == MSG_OP_MAX_OPCODE)
+		return -EOPNOTSUPP;
+	msg.handle = job;
+	msg.notify_cb = notify_cb;
+	msg.send_data = (u8 *)&req;
+	msg.send_size = sizeof(req);
+	ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(hwctx->client->xdna, "Send message failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx,
+				struct amdxdna_sched_job *job,
+				int (*notify_cb)(void *, void __iomem *, size_t))
+{
+	struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job);
+	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
+	struct amdxdna_gem_obj *cmd_abo = job->cmd_bo;
+	struct xdna_mailbox_msg msg;
+	struct cmd_chain_req req;
+	u32 size;
+	int ret;
+	u32 op;
+
+	op = amdxdna_cmd_get_op(cmd_abo);
+	ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, 0, cmd_abo, &size);
+	if (ret)
+		return ret;
+
+	aie2_cmdlist_prepare_request(&req, cmdbuf_abo, size, 1);
+
+	msg.opcode = aie2_cmd_op_to_msg_op(op);
+	if (msg.opcode == MSG_OP_MAX_OPCODE)
+		return -EOPNOTSUPP;
+	msg.handle = job;
+	msg.notify_cb = notify_cb;
+	msg.send_data = (u8 *)&req;
+	msg.send_size = sizeof(req);
+	ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(hwctx->client->xdna, "Send message failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
+		 int (*notify_cb)(void *, void __iomem *, size_t))
+{
+	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
+	struct amdxdna_gem_obj *abo = to_xdna_obj(job->bos[0]);
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+	struct xdna_mailbox_msg msg;
+	struct sync_bo_req req;
+	int ret = 0;
+
+	req.src_addr = 0;
+	req.dst_addr = abo->mem.dev_addr - hwctx->client->dev_heap->mem.dev_addr;
+	req.size = abo->mem.size;
+
+	/* Device to Host */
+	req.type = FIELD_PREP(AIE2_MSG_SYNC_BO_SRC_TYPE, SYNC_BO_DEV_MEM) |
+		FIELD_PREP(AIE2_MSG_SYNC_BO_DST_TYPE, SYNC_BO_HOST_MEM);
+
+	XDNA_DBG(xdna, "sync %d bytes src(0x%llx) to dst(0x%llx) completed",
+		 req.size, req.src_addr, req.dst_addr);
+
+	msg.handle = job;
+	msg.notify_cb = notify_cb;
+	msg.send_data = (u8 *)&req;
+	msg.send_size = sizeof(req);
+	msg.opcode = MSG_OP_SYNC_BO;
+
+	ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(xdna, "Send message failed");
+		return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h b/drivers/accel/amdxdna/aie2_msg_priv.h
new file mode 100644
index 000000000000..6df9065b13f6
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_msg_priv.h
@@ -0,0 +1,368 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AIE2_MSG_PRIV_H_
+#define _AIE2_MSG_PRIV_H_
+
+enum aie2_msg_opcode {
+	MSG_OP_CREATE_CONTEXT              = 0x2,
+	MSG_OP_DESTROY_CONTEXT             = 0x3,
+	MSG_OP_SYNC_BO			   = 0x7,
+	MSG_OP_EXECUTE_BUFFER_CF           = 0xC,
+	MSG_OP_QUERY_COL_STATUS            = 0xD,
+	MSG_OP_QUERY_AIE_TILE_INFO         = 0xE,
+	MSG_OP_QUERY_AIE_VERSION           = 0xF,
+	MSG_OP_EXEC_DPU                    = 0x10,
+	MSG_OP_CONFIG_CU                   = 0x11,
+	MSG_OP_CHAIN_EXEC_BUFFER_CF        = 0x12,
+	MSG_OP_CHAIN_EXEC_DPU              = 0x13,
+	MSG_OP_MAX_XRT_OPCODE,
+	MSG_OP_SUSPEND                     = 0x101,
+	MSG_OP_RESUME                      = 0x102,
+	MSG_OP_ASSIGN_MGMT_PASID           = 0x103,
+	MSG_OP_INVOKE_SELF_TEST            = 0x104,
+	MSG_OP_MAP_HOST_BUFFER             = 0x106,
+	MSG_OP_GET_FIRMWARE_VERSION        = 0x108,
+	MSG_OP_SET_RUNTIME_CONFIG          = 0x10A,
+	MSG_OP_GET_RUNTIME_CONFIG          = 0x10B,
+	MSG_OP_REGISTER_ASYNC_EVENT_MSG    = 0x10C,
+	MSG_OP_MAX_DRV_OPCODE,
+	MSG_OP_GET_PROTOCOL_VERSION        = 0x301,
+	MSG_OP_MAX_OPCODE
+};
+
+enum aie2_msg_status {
+	AIE2_STATUS_SUCCESS				= 0x0,
+	/* AIE Error codes */
+	AIE2_STATUS_AIE_SATURATION_ERROR		= 0x1000001,
+	AIE2_STATUS_AIE_FP_ERROR			= 0x1000002,
+	AIE2_STATUS_AIE_STREAM_ERROR			= 0x1000003,
+	AIE2_STATUS_AIE_ACCESS_ERROR			= 0x1000004,
+	AIE2_STATUS_AIE_BUS_ERROR			= 0x1000005,
+	AIE2_STATUS_AIE_INSTRUCTION_ERROR		= 0x1000006,
+	AIE2_STATUS_AIE_ECC_ERROR			= 0x1000007,
+	AIE2_STATUS_AIE_LOCK_ERROR			= 0x1000008,
+	AIE2_STATUS_AIE_DMA_ERROR			= 0x1000009,
+	AIE2_STATUS_AIE_MEM_PARITY_ERROR		= 0x100000a,
+	AIE2_STATUS_AIE_PWR_CFG_ERROR			= 0x100000b,
+	AIE2_STATUS_AIE_BACKTRACK_ERROR			= 0x100000c,
+	AIE2_STATUS_MAX_AIE_STATUS_CODE,
+	/* MGMT ERT Error codes */
+	AIE2_STATUS_MGMT_ERT_SELF_TEST_FAILURE		= 0x2000001,
+	AIE2_STATUS_MGMT_ERT_HASH_MISMATCH,
+	AIE2_STATUS_MGMT_ERT_NOAVAIL,
+	AIE2_STATUS_MGMT_ERT_INVALID_PARAM,
+	AIE2_STATUS_MGMT_ERT_ENTER_SUSPEND_FAILURE,
+	AIE2_STATUS_MGMT_ERT_BUSY,
+	AIE2_STATUS_MGMT_ERT_APPLICATION_ACTIVE,
+	MAX_MGMT_ERT_STATUS_CODE,
+	/* APP ERT Error codes */
+	AIE2_STATUS_APP_ERT_FIRST_ERROR			= 0x3000001,
+	AIE2_STATUS_APP_INVALID_INSTR,
+	AIE2_STATUS_APP_LOAD_PDI_FAIL,
+	MAX_APP_ERT_STATUS_CODE,
+	/* NPU RTOS Error Codes */
+	AIE2_STATUS_INVALID_INPUT_BUFFER		= 0x4000001,
+	AIE2_STATUS_INVALID_COMMAND,
+	AIE2_STATUS_INVALID_PARAM,
+	AIE2_STATUS_INVALID_OPERATION			= 0x4000006,
+	AIE2_STATUS_ASYNC_EVENT_MSGS_FULL,
+	AIE2_STATUS_MAX_RTOS_STATUS_CODE,
+	MAX_AIE2_STATUS_CODE
+};
+
+struct assign_mgmt_pasid_req {
+	__u16	pasid;
+	__u16	reserved;
+} __packed;
+
+struct assign_mgmt_pasid_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct map_host_buffer_req {
+	__u32		context_id;
+	__u64		buf_addr;
+	__u64		buf_size;
+} __packed;
+
+struct map_host_buffer_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+#define MAX_CQ_PAIRS		2
+struct cq_info {
+	__u32 head_addr;
+	__u32 tail_addr;
+	__u32 buf_addr;
+	__u32 buf_size;
+};
+
+struct cq_pair {
+	struct cq_info x2i_q;
+	struct cq_info i2x_q;
+};
+
+struct create_ctx_req {
+	__u32	aie_type;
+	__u8	start_col;
+	__u8	num_col;
+	__u16	reserved;
+	__u8	num_cq_pairs_requested;
+	__u8	reserved1;
+	__u16	pasid;
+	__u32	pad[2];
+	__u32	sec_comm_target_type;
+	__u32	context_priority;
+} __packed;
+
+struct create_ctx_resp {
+	enum aie2_msg_status	status;
+	__u32			context_id;
+	__u16			msix_id;
+	__u8			num_cq_pairs_allocated;
+	__u8			reserved;
+	struct cq_pair		cq_pair[MAX_CQ_PAIRS];
+} __packed;
+
+struct destroy_ctx_req {
+	__u32	context_id;
+} __packed;
+
+struct destroy_ctx_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct execute_buffer_req {
+	__u32	cu_idx;
+	__u32	payload[19];
+} __packed;
+
+struct exec_dpu_req {
+	__u64	inst_buf_addr;
+	__u32	inst_size;
+	__u32	inst_prop_cnt;
+	__u32	cu_idx;
+	__u32	payload[35];
+} __packed;
+
+struct execute_buffer_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct aie_tile_info {
+	__u32		size;
+	__u16		major;
+	__u16		minor;
+	__u16		cols;
+	__u16		rows;
+	__u16		core_rows;
+	__u16		mem_rows;
+	__u16		shim_rows;
+	__u16		core_row_start;
+	__u16		mem_row_start;
+	__u16		shim_row_start;
+	__u16		core_dma_channels;
+	__u16		mem_dma_channels;
+	__u16		shim_dma_channels;
+	__u16		core_locks;
+	__u16		mem_locks;
+	__u16		shim_locks;
+	__u16		core_events;
+	__u16		mem_events;
+	__u16		shim_events;
+	__u16		reserved;
+};
+
+struct aie_tile_info_req {
+	__u32	reserved;
+} __packed;
+
+struct aie_tile_info_resp {
+	enum aie2_msg_status	status;
+	struct aie_tile_info	info;
+} __packed;
+
+struct aie_version_info_req {
+	__u32		reserved;
+} __packed;
+
+struct aie_version_info_resp {
+	enum aie2_msg_status	status;
+	__u16			major;
+	__u16			minor;
+} __packed;
+
+struct aie_column_info_req {
+	__u64 dump_buff_addr;
+	__u32 dump_buff_size;
+	__u32 num_cols;
+	__u32 aie_bitmap;
+} __packed;
+
+struct aie_column_info_resp {
+	enum aie2_msg_status	status;
+	__u32 size;
+} __packed;
+
+struct suspend_req {
+	__u32		place_holder;
+} __packed;
+
+struct suspend_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct resume_req {
+	__u32		place_holder;
+} __packed;
+
+struct resume_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct check_header_hash_req {
+	__u64		hash_high;
+	__u64		hash_low;
+} __packed;
+
+struct check_header_hash_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct query_error_req {
+	__u64		buf_addr;
+	__u32		buf_size;
+	__u32		next_row;
+	__u32		next_column;
+	__u32		next_module;
+} __packed;
+
+struct query_error_resp {
+	enum aie2_msg_status	status;
+	__u32			num_err;
+	__u32			has_next_err;
+	__u32			next_row;
+	__u32			next_column;
+	__u32			next_module;
+} __packed;
+
+struct protocol_version_req {
+	__u32		reserved;
+} __packed;
+
+struct protocol_version_resp {
+	enum aie2_msg_status	status;
+	__u32			major;
+	__u32			minor;
+} __packed;
+
+struct firmware_version_req {
+	__u32		reserved;
+} __packed;
+
+struct firmware_version_resp {
+	enum aie2_msg_status	status;
+	__u32			major;
+	__u32			minor;
+	__u32			sub;
+	__u32			build;
+} __packed;
+
+#define MAX_NUM_CUS			32
+#define AIE2_MSG_CFG_CU_PDI_ADDR	GENMASK(16, 0)
+#define AIE2_MSG_CFG_CU_FUNC		GENMASK(24, 17)
+struct config_cu_req {
+	__u32	num_cus;
+	__u32	cfgs[MAX_NUM_CUS];
+} __packed;
+
+struct config_cu_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct set_runtime_cfg_req {
+	__u32	type;
+	__u64	value;
+} __packed;
+
+struct set_runtime_cfg_resp {
+	enum aie2_msg_status	status;
+} __packed;
+
+struct get_runtime_cfg_req {
+	__u32	type;
+} __packed;
+
+struct get_runtime_cfg_resp {
+	enum aie2_msg_status	status;
+	__u64			value;
+} __packed;
+
+enum async_event_type {
+	ASYNC_EVENT_TYPE_AIE_ERROR,
+	ASYNC_EVENT_TYPE_EXCEPTION,
+	MAX_ASYNC_EVENT_TYPE
+};
+
+#define ASYNC_BUF_SIZE SZ_8K
+struct async_event_msg_req {
+	__u64 buf_addr;
+	__u32 buf_size;
+} __packed;
+
+struct async_event_msg_resp {
+	enum aie2_msg_status	status;
+	enum async_event_type	type;
+} __packed;
+
+#define MAX_CHAIN_CMDBUF_SIZE SZ_4K
+#define slot_has_space(slot, offset, payload_size)		\
+	(MAX_CHAIN_CMDBUF_SIZE >= (offset) + (payload_size) +	\
+	 sizeof(typeof(slot)))
+
+struct cmd_chain_slot_execbuf_cf {
+	__u32 cu_idx;
+	__u32 arg_cnt;
+	__u32 args[] __counted_by(arg_cnt);
+};
+
+struct cmd_chain_slot_dpu {
+	__u64 inst_buf_addr;
+	__u32 inst_size;
+	__u32 inst_prop_cnt;
+	__u32 cu_idx;
+	__u32 arg_cnt;
+#define MAX_DPU_ARGS_SIZE (34 * sizeof(__u32))
+	__u32 args[] __counted_by(arg_cnt);
+};
+
+struct cmd_chain_req {
+	__u64 buf_addr;
+	__u32 buf_size;
+	__u32 count;
+} __packed;
+
+struct cmd_chain_resp {
+	enum aie2_msg_status	status;
+	__u32			fail_cmd_idx;
+	enum aie2_msg_status	fail_cmd_status;
+} __packed;
+
+#define AIE2_MSG_SYNC_BO_SRC_TYPE	GENMASK(3, 0)
+#define AIE2_MSG_SYNC_BO_DST_TYPE	GENMASK(7, 4)
+struct sync_bo_req {
+	__u64 src_addr;
+	__u64 dst_addr;
+	__u32 size;
+#define SYNC_BO_DEV_MEM  0
+#define SYNC_BO_HOST_MEM 2
+	__u32 type;
+} __packed;
+
+struct sync_bo_resp {
+	enum aie2_msg_status	status;
+} __packed;
+#endif /* _AIE2_MSG_PRIV_H_ */
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
new file mode 100644
index 000000000000..87c425e3d2b9
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -0,0 +1,1004 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/cleanup.h>
+#include <linux/errno.h>
+#include <linux/firmware.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/pci.h>
+#include <linux/xarray.h>
+
+#include "aie2_msg_priv.h"
+#include "aie2_pci.h"
+#include "aie2_solver.h"
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+static int aie2_max_col = XRS_MAX_COL;
+module_param(aie2_max_col, uint, 0600);
+MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used");
+
+/*
+ * The management mailbox channel is allocated by firmware.
+ * The related register and ring buffer information is on SRAM BAR.
+ * This struct is the register layout.
+ */
+#define MGMT_MBOX_MAGIC 0x55504e5f /* _NPU */
+struct mgmt_mbox_chann_info {
+	__u32	x2i_tail;
+	__u32	x2i_head;
+	__u32	x2i_buf;
+	__u32	x2i_buf_sz;
+	__u32	i2x_tail;
+	__u32	i2x_head;
+	__u32	i2x_buf;
+	__u32	i2x_buf_sz;
+	__u32	magic;
+	__u32	msi_id;
+	__u32	prot_major;
+	__u32	prot_minor;
+	__u32	rsvd[4];
+};
+
+static int aie2_check_protocol(struct amdxdna_dev_hdl *ndev, u32 fw_major, u32 fw_minor)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+
+	/*
+	 * The driver supported mailbox behavior is defined by
+	 * ndev->priv->protocol_major and protocol_minor.
+	 *
+	 * When protocol_major and fw_major are different, it means driver
+	 * and firmware are incompatible.
+	 */
+	if (ndev->priv->protocol_major != fw_major) {
+		XDNA_ERR(xdna, "Incompatible firmware protocol major %d minor %d",
+			 fw_major, fw_minor);
+		return -EINVAL;
+	}
+
+	/*
+	 * When protocol_minor is greater then fw_minor, that means driver
+	 * relies on operation the installed firmware does not support.
+	 */
+	if (ndev->priv->protocol_minor > fw_minor) {
+		XDNA_ERR(xdna, "Firmware minor version smaller than supported");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void aie2_dump_chann_info_debug(struct amdxdna_dev_hdl *ndev)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+
+	XDNA_DBG(xdna, "i2x tail    0x%x", ndev->mgmt_i2x.mb_tail_ptr_reg);
+	XDNA_DBG(xdna, "i2x head    0x%x", ndev->mgmt_i2x.mb_head_ptr_reg);
+	XDNA_DBG(xdna, "i2x ringbuf 0x%x", ndev->mgmt_i2x.rb_start_addr);
+	XDNA_DBG(xdna, "i2x rsize   0x%x", ndev->mgmt_i2x.rb_size);
+	XDNA_DBG(xdna, "x2i tail    0x%x", ndev->mgmt_x2i.mb_tail_ptr_reg);
+	XDNA_DBG(xdna, "x2i head    0x%x", ndev->mgmt_x2i.mb_head_ptr_reg);
+	XDNA_DBG(xdna, "x2i ringbuf 0x%x", ndev->mgmt_x2i.rb_start_addr);
+	XDNA_DBG(xdna, "x2i rsize   0x%x", ndev->mgmt_x2i.rb_size);
+	XDNA_DBG(xdna, "x2i chann index 0x%x", ndev->mgmt_chan_idx);
+	XDNA_DBG(xdna, "mailbox protocol major 0x%x", ndev->mgmt_prot_major);
+	XDNA_DBG(xdna, "mailbox protocol minor 0x%x", ndev->mgmt_prot_minor);
+}
+
+static int aie2_get_mgmt_chann_info(struct amdxdna_dev_hdl *ndev)
+{
+	struct mgmt_mbox_chann_info info_regs;
+	struct xdna_mailbox_chann_res *i2x;
+	struct xdna_mailbox_chann_res *x2i;
+	u32 addr, off;
+	u32 *reg;
+	int ret;
+	int i;
+
+	/*
+	 * Once firmware is alive, it will write management channel
+	 * information in SRAM BAR and write the address of that information
+	 * at FW_ALIVE_OFF offset in SRMA BAR.
+	 *
+	 * Read a non-zero value from FW_ALIVE_OFF implies that firmware
+	 * is alive.
+	 */
+	ret = readx_poll_timeout(readl, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF),
+				 addr, addr, AIE2_INTERVAL, AIE2_TIMEOUT);
+	if (ret || !addr)
+		return -ETIME;
+
+	off = AIE2_SRAM_OFF(ndev, addr);
+	reg = (u32 *)&info_regs;
+	for (i = 0; i < sizeof(info_regs) / sizeof(u32); i++)
+		reg[i] = readl(ndev->sram_base + off + i * sizeof(u32));
+
+	if (info_regs.magic != MGMT_MBOX_MAGIC) {
+		XDNA_ERR(ndev->xdna, "Invalid mbox magic 0x%x", info_regs.magic);
+		ret = -EINVAL;
+		goto done;
+	}
+
+	i2x = &ndev->mgmt_i2x;
+	x2i = &ndev->mgmt_x2i;
+
+	i2x->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_head);
+	i2x->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_tail);
+	i2x->rb_start_addr   = AIE2_SRAM_OFF(ndev, info_regs.i2x_buf);
+	i2x->rb_size         = info_regs.i2x_buf_sz;
+
+	x2i->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_head);
+	x2i->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_tail);
+	x2i->rb_start_addr   = AIE2_SRAM_OFF(ndev, info_regs.x2i_buf);
+	x2i->rb_size         = info_regs.x2i_buf_sz;
+
+	ndev->mgmt_chan_idx  = info_regs.msi_id;
+	ndev->mgmt_prot_major = info_regs.prot_major;
+	ndev->mgmt_prot_minor = info_regs.prot_minor;
+
+	ret = aie2_check_protocol(ndev, ndev->mgmt_prot_major, ndev->mgmt_prot_minor);
+
+done:
+	aie2_dump_chann_info_debug(ndev);
+
+	/* Must clear address at FW_ALIVE_OFF */
+	writel(0, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF));
+
+	return ret;
+}
+
+int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev,
+		     enum rt_config_category category, u32 *val)
+{
+	const struct rt_config *cfg;
+	u32 value;
+	int ret;
+
+	for (cfg = ndev->priv->rt_config; cfg->type; cfg++) {
+		if (cfg->category != category)
+			continue;
+
+		value = val ? *val : cfg->value;
+		ret = aie2_set_runtime_cfg(ndev, cfg->type, value);
+		if (ret) {
+			XDNA_ERR(ndev->xdna, "Set type %d value %d failed",
+				 cfg->type, value);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int aie2_xdna_reset(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ret = aie2_suspend_fw(ndev);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Suspend firmware failed");
+		return ret;
+	}
+
+	ret = aie2_resume_fw(ndev);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Resume firmware failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int aie2_mgmt_fw_init(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ret = aie2_runtime_cfg(ndev, AIE2_RT_CFG_INIT, NULL);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Runtime config failed");
+		return ret;
+	}
+
+	ret = aie2_assign_mgmt_pasid(ndev, 0);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Can not assign PASID");
+		return ret;
+	}
+
+	ret = aie2_xdna_reset(ndev);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Reset firmware failed");
+		return ret;
+	}
+
+	if (!ndev->async_events)
+		return 0;
+
+	ret = aie2_error_async_events_send(ndev);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Send async events failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "query firmware version failed");
+		return ret;
+	}
+
+	ret = aie2_query_aie_version(ndev, &ndev->version);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Query AIE version failed");
+		return ret;
+	}
+
+	ret = aie2_query_aie_metadata(ndev, &ndev->metadata);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Query AIE metadata failed");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void aie2_mgmt_fw_fini(struct amdxdna_dev_hdl *ndev)
+{
+	if (aie2_suspend_fw(ndev))
+		XDNA_ERR(ndev->xdna, "Suspend_fw failed");
+	XDNA_DBG(ndev->xdna, "Firmware suspended");
+}
+
+static int aie2_xrs_load(void *cb_arg, struct xrs_action_load *action)
+{
+	struct amdxdna_hwctx *hwctx = cb_arg;
+	struct amdxdna_dev *xdna;
+	int ret;
+
+	xdna = hwctx->client->xdna;
+
+	hwctx->start_col = action->part.start_col;
+	hwctx->num_col = action->part.ncols;
+	ret = aie2_create_context(xdna->dev_handle, hwctx);
+	if (ret)
+		XDNA_ERR(xdna, "create context failed, ret %d", ret);
+
+	return ret;
+}
+
+static int aie2_xrs_unload(void *cb_arg)
+{
+	struct amdxdna_hwctx *hwctx = cb_arg;
+	struct amdxdna_dev *xdna;
+	int ret;
+
+	xdna = hwctx->client->xdna;
+
+	ret = aie2_destroy_context(xdna->dev_handle, hwctx);
+	if (ret)
+		XDNA_ERR(xdna, "destroy context failed, ret %d", ret);
+
+	return ret;
+}
+
+static int aie2_xrs_set_dft_dpm_level(struct drm_device *ddev, u32 dpm_level)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(ddev);
+	struct amdxdna_dev_hdl *ndev;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	ndev = xdna->dev_handle;
+	ndev->dft_dpm_level = dpm_level;
+	if (ndev->pw_mode != POWER_MODE_DEFAULT || ndev->dpm_level == dpm_level)
+		return 0;
+
+	return ndev->priv->hw_ops.set_dpm(ndev, dpm_level);
+}
+
+static struct xrs_action_ops aie2_xrs_actions = {
+	.load = aie2_xrs_load,
+	.unload = aie2_xrs_unload,
+	.set_dft_dpm_level = aie2_xrs_set_dft_dpm_level,
+};
+
+static void aie2_hw_stop(struct amdxdna_dev *xdna)
+{
+	struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
+	struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
+
+	if (ndev->dev_status <= AIE2_DEV_INIT) {
+		XDNA_ERR(xdna, "device is already stopped");
+		return;
+	}
+
+	aie2_mgmt_fw_fini(ndev);
+	xdna_mailbox_stop_channel(ndev->mgmt_chann);
+	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+	ndev->mgmt_chann = NULL;
+	drmm_kfree(&xdna->ddev, ndev->mbox);
+	ndev->mbox = NULL;
+	aie2_psp_stop(ndev->psp_hdl);
+	aie2_smu_fini(ndev);
+	pci_disable_device(pdev);
+
+	ndev->dev_status = AIE2_DEV_INIT;
+}
+
+static int aie2_hw_start(struct amdxdna_dev *xdna)
+{
+	struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
+	struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
+	struct xdna_mailbox_res mbox_res;
+	u32 xdna_mailbox_intr_reg;
+	int mgmt_mb_irq, ret;
+
+	if (ndev->dev_status >= AIE2_DEV_START) {
+		XDNA_INFO(xdna, "device is already started");
+		return 0;
+	}
+
+	ret = pci_enable_device(pdev);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to enable device, ret %d", ret);
+		return ret;
+	}
+	pci_set_master(pdev);
+
+	ret = aie2_smu_init(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to init smu, ret %d", ret);
+		goto disable_dev;
+	}
+
+	ret = aie2_psp_start(ndev->psp_hdl);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to start psp, ret %d", ret);
+		goto fini_smu;
+	}
+
+	ret = aie2_get_mgmt_chann_info(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "firmware is not alive");
+		goto stop_psp;
+	}
+
+	mbox_res.ringbuf_base = ndev->sram_base;
+	mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar);
+	mbox_res.mbox_base = ndev->mbox_base;
+	mbox_res.mbox_size = MBOX_SIZE(ndev);
+	mbox_res.name = "xdna_mailbox";
+	ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res);
+	if (!ndev->mbox) {
+		XDNA_ERR(xdna, "failed to create mailbox device");
+		ret = -ENODEV;
+		goto stop_psp;
+	}
+
+	mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx);
+	if (mgmt_mb_irq < 0) {
+		ret = mgmt_mb_irq;
+		XDNA_ERR(xdna, "failed to alloc irq vector, ret %d", ret);
+		goto stop_psp;
+	}
+
+	xdna_mailbox_intr_reg = ndev->mgmt_i2x.mb_head_ptr_reg + 4;
+	ndev->mgmt_chann = xdna_mailbox_create_channel(ndev->mbox,
+						       &ndev->mgmt_x2i,
+						       &ndev->mgmt_i2x,
+						       xdna_mailbox_intr_reg,
+						       mgmt_mb_irq);
+	if (!ndev->mgmt_chann) {
+		XDNA_ERR(xdna, "failed to create management mailbox channel");
+		ret = -EINVAL;
+		goto stop_psp;
+	}
+
+	ret = aie2_pm_init(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to init pm, ret %d", ret);
+		goto destroy_mgmt_chann;
+	}
+
+	ret = aie2_mgmt_fw_init(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret);
+		goto destroy_mgmt_chann;
+	}
+
+	ndev->dev_status = AIE2_DEV_START;
+
+	return 0;
+
+destroy_mgmt_chann:
+	xdna_mailbox_stop_channel(ndev->mgmt_chann);
+	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+stop_psp:
+	aie2_psp_stop(ndev->psp_hdl);
+fini_smu:
+	aie2_smu_fini(ndev);
+disable_dev:
+	pci_disable_device(pdev);
+
+	return ret;
+}
+
+static int aie2_hw_suspend(struct amdxdna_dev *xdna)
+{
+	struct amdxdna_client *client;
+
+	guard(mutex)(&xdna->dev_lock);
+	list_for_each_entry(client, &xdna->client_list, node)
+		aie2_hwctx_suspend(client);
+
+	aie2_hw_stop(xdna);
+
+	return 0;
+}
+
+static int aie2_hw_resume(struct amdxdna_dev *xdna)
+{
+	struct amdxdna_client *client;
+	int ret;
+
+	guard(mutex)(&xdna->dev_lock);
+	ret = aie2_hw_start(xdna);
+	if (ret) {
+		XDNA_ERR(xdna, "Start hardware failed, %d", ret);
+		return ret;
+	}
+
+	list_for_each_entry(client, &xdna->client_list, node) {
+		ret = aie2_hwctx_resume(client);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int aie2_init(struct amdxdna_dev *xdna)
+{
+	struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
+	void __iomem *tbl[PCI_NUM_RESOURCES] = {0};
+	struct init_config xrs_cfg = { 0 };
+	struct amdxdna_dev_hdl *ndev;
+	struct psp_config psp_conf;
+	const struct firmware *fw;
+	unsigned long bars = 0;
+	int i, nvec, ret;
+
+	ndev = drmm_kzalloc(&xdna->ddev, sizeof(*ndev), GFP_KERNEL);
+	if (!ndev)
+		return -ENOMEM;
+
+	ndev->priv = xdna->dev_info->dev_priv;
+	ndev->xdna = xdna;
+
+	ret = request_firmware(&fw, ndev->priv->fw_path, &pdev->dev);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to request_firmware %s, ret %d",
+			 ndev->priv->fw_path, ret);
+		return ret;
+	}
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		XDNA_ERR(xdna, "pcim enable device failed, ret %d", ret);
+		goto release_fw;
+	}
+
+	for (i = 0; i < PSP_MAX_REGS; i++)
+		set_bit(PSP_REG_BAR(ndev, i), &bars);
+
+	set_bit(xdna->dev_info->sram_bar, &bars);
+	set_bit(xdna->dev_info->smu_bar, &bars);
+	set_bit(xdna->dev_info->mbox_bar, &bars);
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		if (!test_bit(i, &bars))
+			continue;
+		tbl[i] = pcim_iomap(pdev, i, 0);
+		if (!tbl[i]) {
+			XDNA_ERR(xdna, "map bar %d failed", i);
+			ret = -ENOMEM;
+			goto release_fw;
+		}
+	}
+
+	ndev->sram_base = tbl[xdna->dev_info->sram_bar];
+	ndev->smu_base = tbl[xdna->dev_info->smu_bar];
+	ndev->mbox_base = tbl[xdna->dev_info->mbox_bar];
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to set DMA mask: %d", ret);
+		goto release_fw;
+	}
+
+	nvec = pci_msix_vec_count(pdev);
+	if (nvec <= 0) {
+		XDNA_ERR(xdna, "does not get number of interrupt vector");
+		ret = -EINVAL;
+		goto release_fw;
+	}
+
+	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX);
+	if (ret < 0) {
+		XDNA_ERR(xdna, "failed to alloc irq vectors, ret %d", ret);
+		goto release_fw;
+	}
+
+	psp_conf.fw_size = fw->size;
+	psp_conf.fw_buf = fw->data;
+	for (i = 0; i < PSP_MAX_REGS; i++)
+		psp_conf.psp_regs[i] = tbl[PSP_REG_BAR(ndev, i)] + PSP_REG_OFF(ndev, i);
+	ndev->psp_hdl = aie2m_psp_create(&xdna->ddev, &psp_conf);
+	if (!ndev->psp_hdl) {
+		XDNA_ERR(xdna, "failed to create psp");
+		ret = -ENOMEM;
+		goto release_fw;
+	}
+	xdna->dev_handle = ndev;
+
+	ret = aie2_hw_start(xdna);
+	if (ret) {
+		XDNA_ERR(xdna, "start npu failed, ret %d", ret);
+		goto release_fw;
+	}
+
+	ret = aie2_mgmt_fw_query(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "Query firmware failed, ret %d", ret);
+		goto stop_hw;
+	}
+	ndev->total_col = min(aie2_max_col, ndev->metadata.cols);
+
+	xrs_cfg.clk_list.num_levels = ndev->max_dpm_level + 1;
+	for (i = 0; i < xrs_cfg.clk_list.num_levels; i++)
+		xrs_cfg.clk_list.cu_clk_list[i] = ndev->priv->dpm_clk_tbl[i].hclk;
+	xrs_cfg.sys_eff_factor = 1;
+	xrs_cfg.ddev = &xdna->ddev;
+	xrs_cfg.actions = &aie2_xrs_actions;
+	xrs_cfg.total_col = ndev->total_col;
+
+	xdna->xrs_hdl = xrsm_init(&xrs_cfg);
+	if (!xdna->xrs_hdl) {
+		XDNA_ERR(xdna, "Initialize resolver failed");
+		ret = -EINVAL;
+		goto stop_hw;
+	}
+
+	ret = aie2_error_async_events_alloc(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "Allocate async events failed, ret %d", ret);
+		goto stop_hw;
+	}
+
+	ret = aie2_error_async_events_send(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "Send async events failed, ret %d", ret);
+		goto async_event_free;
+	}
+
+	/* Issue a command to make sure firmware handled async events */
+	ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver);
+	if (ret) {
+		XDNA_ERR(xdna, "Re-query firmware version failed");
+		goto async_event_free;
+	}
+
+	release_firmware(fw);
+	return 0;
+
+async_event_free:
+	aie2_error_async_events_free(ndev);
+stop_hw:
+	aie2_hw_stop(xdna);
+release_fw:
+	release_firmware(fw);
+
+	return ret;
+}
+
+static void aie2_fini(struct amdxdna_dev *xdna)
+{
+	struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
+
+	aie2_hw_stop(xdna);
+	aie2_error_async_events_free(ndev);
+}
+
+static int aie2_get_aie_status(struct amdxdna_client *client,
+			       struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_status status;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret;
+
+	ndev = xdna->dev_handle;
+	if (copy_from_user(&status, u64_to_user_ptr(args->buffer), sizeof(status))) {
+		XDNA_ERR(xdna, "Failed to copy AIE request into kernel");
+		return -EFAULT;
+	}
+
+	if (ndev->metadata.cols * ndev->metadata.size < status.buffer_size) {
+		XDNA_ERR(xdna, "Invalid buffer size. Given Size: %u. Need Size: %u.",
+			 status.buffer_size, ndev->metadata.cols * ndev->metadata.size);
+		return -EINVAL;
+	}
+
+	ret = aie2_query_status(ndev, u64_to_user_ptr(status.buffer),
+				status.buffer_size, &status.cols_filled);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to get AIE status info. Ret: %d", ret);
+		return ret;
+	}
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &status, sizeof(status))) {
+		XDNA_ERR(xdna, "Failed to copy AIE request info to user space");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int aie2_get_aie_metadata(struct amdxdna_client *client,
+				 struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_metadata *meta;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret = 0;
+
+	ndev = xdna->dev_handle;
+	meta = kzalloc(sizeof(*meta), GFP_KERNEL);
+	if (!meta)
+		return -ENOMEM;
+
+	meta->col_size = ndev->metadata.size;
+	meta->cols = ndev->metadata.cols;
+	meta->rows = ndev->metadata.rows;
+
+	meta->version.major = ndev->metadata.version.major;
+	meta->version.minor = ndev->metadata.version.minor;
+
+	meta->core.row_count = ndev->metadata.core.row_count;
+	meta->core.row_start = ndev->metadata.core.row_start;
+	meta->core.dma_channel_count = ndev->metadata.core.dma_channel_count;
+	meta->core.lock_count = ndev->metadata.core.lock_count;
+	meta->core.event_reg_count = ndev->metadata.core.event_reg_count;
+
+	meta->mem.row_count = ndev->metadata.mem.row_count;
+	meta->mem.row_start = ndev->metadata.mem.row_start;
+	meta->mem.dma_channel_count = ndev->metadata.mem.dma_channel_count;
+	meta->mem.lock_count = ndev->metadata.mem.lock_count;
+	meta->mem.event_reg_count = ndev->metadata.mem.event_reg_count;
+
+	meta->shim.row_count = ndev->metadata.shim.row_count;
+	meta->shim.row_start = ndev->metadata.shim.row_start;
+	meta->shim.dma_channel_count = ndev->metadata.shim.dma_channel_count;
+	meta->shim.lock_count = ndev->metadata.shim.lock_count;
+	meta->shim.event_reg_count = ndev->metadata.shim.event_reg_count;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), meta, sizeof(*meta)))
+		ret = -EFAULT;
+
+	kfree(meta);
+	return ret;
+}
+
+static int aie2_get_aie_version(struct amdxdna_client *client,
+				struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_version version;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+
+	ndev = xdna->dev_handle;
+	version.major = ndev->version.major;
+	version.minor = ndev->version.minor;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int aie2_get_firmware_version(struct amdxdna_client *client,
+				     struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_firmware_version version;
+	struct amdxdna_dev *xdna = client->xdna;
+
+	version.major = xdna->fw_ver.major;
+	version.minor = xdna->fw_ver.minor;
+	version.patch = xdna->fw_ver.sub;
+	version.build = xdna->fw_ver.build;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int aie2_get_power_mode(struct amdxdna_client *client,
+			       struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_get_power_mode mode = {};
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+
+	ndev = xdna->dev_handle;
+	mode.power_mode = ndev->pw_mode;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &mode, sizeof(mode)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int aie2_get_clock_metadata(struct amdxdna_client *client,
+				   struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_clock_metadata *clock;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret = 0;
+
+	ndev = xdna->dev_handle;
+	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
+	if (!clock)
+		return -ENOMEM;
+
+	snprintf(clock->mp_npu_clock.name, sizeof(clock->mp_npu_clock.name),
+		 "MP-NPU Clock");
+	clock->mp_npu_clock.freq_mhz = ndev->npuclk_freq;
+	snprintf(clock->h_clock.name, sizeof(clock->h_clock.name), "H Clock");
+	clock->h_clock.freq_mhz = ndev->hclk_freq;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), clock, sizeof(*clock)))
+		ret = -EFAULT;
+
+	kfree(clock);
+	return ret;
+}
+
+static int aie2_hwctx_status_cb(struct amdxdna_hwctx *hwctx, void *arg)
+{
+	struct amdxdna_drm_hwctx_entry *tmp __free(kfree) = NULL;
+	struct amdxdna_drm_get_array *array_args = arg;
+	struct amdxdna_drm_hwctx_entry __user *buf;
+	u32 size;
+
+	if (!array_args->num_element)
+		return -EINVAL;
+
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	tmp->pid = hwctx->client->pid;
+	tmp->context_id = hwctx->id;
+	tmp->start_col = hwctx->start_col;
+	tmp->num_col = hwctx->num_col;
+	tmp->command_submissions = hwctx->priv->seq;
+	tmp->command_completions = hwctx->priv->completed;
+	tmp->pasid = hwctx->client->pasid;
+	tmp->priority = hwctx->qos.priority;
+	tmp->gops = hwctx->qos.gops;
+	tmp->fps = hwctx->qos.fps;
+	tmp->dma_bandwidth = hwctx->qos.dma_bandwidth;
+	tmp->latency = hwctx->qos.latency;
+	tmp->frame_exec_time = hwctx->qos.frame_exec_time;
+	tmp->state = AMDXDNA_HWCTX_STATE_ACTIVE;
+
+	buf = u64_to_user_ptr(array_args->buffer);
+	size = min(sizeof(*tmp), array_args->element_size);
+
+	if (copy_to_user(buf, tmp, size))
+		return -EFAULT;
+
+	array_args->buffer += size;
+	array_args->num_element--;
+
+	return 0;
+}
+
+static int aie2_get_hwctx_status(struct amdxdna_client *client,
+				 struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_get_array array_args;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_client *tmp_client;
+	int ret;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	array_args.element_size = sizeof(struct amdxdna_drm_query_hwctx);
+	array_args.buffer = args->buffer;
+	array_args.num_element = args->buffer_size / array_args.element_size;
+	list_for_each_entry(tmp_client, &xdna->client_list, node) {
+		ret = amdxdna_hwctx_walk(tmp_client, &array_args,
+					 aie2_hwctx_status_cb);
+		if (ret)
+			break;
+	}
+
+	args->buffer_size -= (u32)(array_args.buffer - args->buffer);
+	return ret;
+}
+
+static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	int ret, idx;
+
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return -ENODEV;
+
+	switch (args->param) {
+	case DRM_AMDXDNA_QUERY_AIE_STATUS:
+		ret = aie2_get_aie_status(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_AIE_METADATA:
+		ret = aie2_get_aie_metadata(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_AIE_VERSION:
+		ret = aie2_get_aie_version(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_CLOCK_METADATA:
+		ret = aie2_get_clock_metadata(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_HW_CONTEXTS:
+		ret = aie2_get_hwctx_status(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_FIRMWARE_VERSION:
+		ret = aie2_get_firmware_version(client, args);
+		break;
+	case DRM_AMDXDNA_GET_POWER_MODE:
+		ret = aie2_get_power_mode(client, args);
+		break;
+	default:
+		XDNA_ERR(xdna, "Not supported request parameter %u", args->param);
+		ret = -EOPNOTSUPP;
+	}
+	XDNA_DBG(xdna, "Got param %d", args->param);
+
+	drm_dev_exit(idx);
+	return ret;
+}
+
+static int aie2_query_ctx_status_array(struct amdxdna_client *client,
+				       struct amdxdna_drm_get_array *args)
+{
+	struct amdxdna_drm_get_array array_args;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_client *tmp_client;
+	int ret;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	array_args.element_size = min(args->element_size,
+				      sizeof(struct amdxdna_drm_hwctx_entry));
+	array_args.buffer = args->buffer;
+	array_args.num_element = args->num_element * args->element_size /
+				array_args.element_size;
+	list_for_each_entry(tmp_client, &xdna->client_list, node) {
+		ret = amdxdna_hwctx_walk(tmp_client, &array_args,
+					 aie2_hwctx_status_cb);
+		if (ret)
+			break;
+	}
+
+	args->element_size = array_args.element_size;
+	args->num_element = (u32)((array_args.buffer - args->buffer) /
+				  args->element_size);
+
+	return ret;
+}
+
+static int aie2_get_array(struct amdxdna_client *client,
+			  struct amdxdna_drm_get_array *args)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	int ret, idx;
+
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return -ENODEV;
+
+	switch (args->param) {
+	case DRM_AMDXDNA_HW_CONTEXT_ALL:
+		ret = aie2_query_ctx_status_array(client, args);
+		break;
+	default:
+		XDNA_ERR(xdna, "Not supported request parameter %u", args->param);
+		ret = -EOPNOTSUPP;
+	}
+	XDNA_DBG(xdna, "Got param %d", args->param);
+
+	drm_dev_exit(idx);
+	return ret;
+}
+
+static int aie2_set_power_mode(struct amdxdna_client *client,
+			       struct amdxdna_drm_set_state *args)
+{
+	struct amdxdna_drm_set_power_mode power_state;
+	enum amdxdna_power_mode_type power_mode;
+	struct amdxdna_dev *xdna = client->xdna;
+
+	if (copy_from_user(&power_state, u64_to_user_ptr(args->buffer),
+			   sizeof(power_state))) {
+		XDNA_ERR(xdna, "Failed to copy power mode request into kernel");
+		return -EFAULT;
+	}
+
+	if (XDNA_MBZ_DBG(xdna, power_state.pad, sizeof(power_state.pad)))
+		return -EINVAL;
+
+	power_mode = power_state.power_mode;
+	if (power_mode > POWER_MODE_TURBO) {
+		XDNA_ERR(xdna, "Invalid power mode %d", power_mode);
+		return -EINVAL;
+	}
+
+	return aie2_pm_set_mode(xdna->dev_handle, power_mode);
+}
+
+static int aie2_set_state(struct amdxdna_client *client,
+			  struct amdxdna_drm_set_state *args)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	int ret, idx;
+
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return -ENODEV;
+
+	switch (args->param) {
+	case DRM_AMDXDNA_SET_POWER_MODE:
+		ret = aie2_set_power_mode(client, args);
+		break;
+	default:
+		XDNA_ERR(xdna, "Not supported request parameter %u", args->param);
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	drm_dev_exit(idx);
+	return ret;
+}
+
+const struct amdxdna_dev_ops aie2_ops = {
+	.init = aie2_init,
+	.fini = aie2_fini,
+	.resume = aie2_hw_resume,
+	.suspend = aie2_hw_suspend,
+	.get_aie_info = aie2_get_info,
+	.set_aie_state = aie2_set_state,
+	.hwctx_init = aie2_hwctx_init,
+	.hwctx_fini = aie2_hwctx_fini,
+	.hwctx_config = aie2_hwctx_config,
+	.cmd_submit = aie2_cmd_submit,
+	.hmm_invalidate = aie2_hmm_invalidate,
+	.get_array = aie2_get_array,
+};
diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h
new file mode 100644
index 000000000000..91a8e948f82a
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_pci.h
@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AIE2_PCI_H_
+#define _AIE2_PCI_H_
+
+#include <drm/amdxdna_accel.h>
+#include <linux/semaphore.h>
+
+#include "amdxdna_mailbox.h"
+
+#define AIE2_INTERVAL	20000	/* us */
+#define AIE2_TIMEOUT	1000000	/* us */
+
+/* Firmware determines device memory base address and size */
+#define AIE2_DEVM_BASE	0x4000000
+#define AIE2_DEVM_SIZE	SZ_64M
+
+#define NDEV2PDEV(ndev) (to_pci_dev((ndev)->xdna->ddev.dev))
+
+#define AIE2_SRAM_OFF(ndev, addr) ((addr) - (ndev)->priv->sram_dev_addr)
+#define AIE2_MBOX_OFF(ndev, addr) ((addr) - (ndev)->priv->mbox_dev_addr)
+
+#define PSP_REG_BAR(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].bar_idx)
+#define PSP_REG_OFF(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].offset)
+#define SRAM_REG_OFF(ndev, idx) ((ndev)->priv->sram_offs[(idx)].offset)
+
+#define SMU_REG(ndev, idx) \
+({ \
+	typeof(ndev) _ndev = ndev; \
+	((_ndev)->smu_base + (_ndev)->priv->smu_regs_off[(idx)].offset); \
+})
+#define SRAM_GET_ADDR(ndev, idx) \
+({ \
+	typeof(ndev) _ndev = ndev; \
+	((_ndev)->sram_base + SRAM_REG_OFF((_ndev), (idx))); \
+})
+
+#define CHAN_SLOT_SZ SZ_8K
+#define MBOX_SIZE(ndev) \
+({ \
+	typeof(ndev) _ndev = (ndev); \
+	((_ndev)->priv->mbox_size) ? (_ndev)->priv->mbox_size : \
+	pci_resource_len(NDEV2PDEV(_ndev), (_ndev)->xdna->dev_info->mbox_bar); \
+})
+
+enum aie2_smu_reg_idx {
+	SMU_CMD_REG = 0,
+	SMU_ARG_REG,
+	SMU_INTR_REG,
+	SMU_RESP_REG,
+	SMU_OUT_REG,
+	SMU_MAX_REGS /* Keep this at the end */
+};
+
+enum aie2_sram_reg_idx {
+	MBOX_CHANN_OFF = 0,
+	FW_ALIVE_OFF,
+	SRAM_MAX_INDEX /* Keep this at the end */
+};
+
+enum psp_reg_idx {
+	PSP_CMD_REG = 0,
+	PSP_ARG0_REG,
+	PSP_ARG1_REG,
+	PSP_ARG2_REG,
+	PSP_NUM_IN_REGS, /* number of input registers */
+	PSP_INTR_REG = PSP_NUM_IN_REGS,
+	PSP_STATUS_REG,
+	PSP_RESP_REG,
+	PSP_MAX_REGS /* Keep this at the end */
+};
+
+struct amdxdna_client;
+struct amdxdna_fw_ver;
+struct amdxdna_hwctx;
+struct amdxdna_sched_job;
+
+struct psp_config {
+	const void	*fw_buf;
+	u32		fw_size;
+	void __iomem	*psp_regs[PSP_MAX_REGS];
+};
+
+struct aie_version {
+	u16 major;
+	u16 minor;
+};
+
+struct aie_tile_metadata {
+	u16 row_count;
+	u16 row_start;
+	u16 dma_channel_count;
+	u16 lock_count;
+	u16 event_reg_count;
+};
+
+struct aie_metadata {
+	u32 size;
+	u16 cols;
+	u16 rows;
+	struct aie_version version;
+	struct aie_tile_metadata core;
+	struct aie_tile_metadata mem;
+	struct aie_tile_metadata shim;
+};
+
+enum rt_config_category {
+	AIE2_RT_CFG_INIT,
+	AIE2_RT_CFG_CLK_GATING,
+};
+
+struct rt_config {
+	u32	type;
+	u32	value;
+	u32	category;
+};
+
+struct dpm_clk_freq {
+	u32	npuclk;
+	u32	hclk;
+};
+
+/*
+ * Define the maximum number of pending commands in a hardware context.
+ * Must be power of 2!
+ */
+#define HWCTX_MAX_CMDS		4
+#define get_job_idx(seq) ((seq) & (HWCTX_MAX_CMDS - 1))
+struct amdxdna_hwctx_priv {
+	struct amdxdna_gem_obj		*heap;
+	void				*mbox_chann;
+
+	struct drm_gpu_scheduler	sched;
+	struct drm_sched_entity		entity;
+
+	struct mutex			io_lock; /* protect seq and cmd order */
+	struct wait_queue_head		job_free_wq;
+	u32				num_pending;
+	u64				seq;
+	struct semaphore		job_sem;
+	bool				job_done;
+
+	/* Completed job counter */
+	u64				completed;
+
+	struct amdxdna_gem_obj		*cmd_buf[HWCTX_MAX_CMDS];
+	struct drm_syncobj		*syncobj;
+};
+
+enum aie2_dev_status {
+	AIE2_DEV_UNINIT,
+	AIE2_DEV_INIT,
+	AIE2_DEV_START,
+};
+
+struct amdxdna_dev_hdl {
+	struct amdxdna_dev		*xdna;
+	const struct amdxdna_dev_priv	*priv;
+	void			__iomem *sram_base;
+	void			__iomem *smu_base;
+	void			__iomem *mbox_base;
+	struct psp_device		*psp_hdl;
+
+	struct xdna_mailbox_chann_res	mgmt_x2i;
+	struct xdna_mailbox_chann_res	mgmt_i2x;
+	u32				mgmt_chan_idx;
+	u32				mgmt_prot_major;
+	u32				mgmt_prot_minor;
+
+	u32				total_col;
+	struct aie_version		version;
+	struct aie_metadata		metadata;
+
+	/* power management and clock*/
+	enum amdxdna_power_mode_type	pw_mode;
+	u32				dpm_level;
+	u32				dft_dpm_level;
+	u32				max_dpm_level;
+	u32				clk_gating;
+	u32				npuclk_freq;
+	u32				hclk_freq;
+
+	/* Mailbox and the management channel */
+	struct mailbox			*mbox;
+	struct mailbox_channel		*mgmt_chann;
+	struct async_events		*async_events;
+
+	enum aie2_dev_status		dev_status;
+	u32				hwctx_num;
+};
+
+#define DEFINE_BAR_OFFSET(reg_name, bar, reg_addr) \
+	[reg_name] = {bar##_BAR_INDEX, (reg_addr) - bar##_BAR_BASE}
+
+struct aie2_bar_off_pair {
+	int	bar_idx;
+	u32	offset;
+};
+
+struct aie2_hw_ops {
+	int (*set_dpm)(struct amdxdna_dev_hdl *ndev, u32 dpm_level);
+};
+
+struct amdxdna_dev_priv {
+	const char			*fw_path;
+	u64				protocol_major;
+	u64				protocol_minor;
+	const struct rt_config		*rt_config;
+	const struct dpm_clk_freq	*dpm_clk_tbl;
+
+#define COL_ALIGN_NONE   0
+#define COL_ALIGN_NATURE 1
+	u32				col_align;
+	u32				mbox_dev_addr;
+	/* If mbox_size is 0, use BAR size. See MBOX_SIZE macro */
+	u32				mbox_size;
+	u32				sram_dev_addr;
+	struct aie2_bar_off_pair	sram_offs[SRAM_MAX_INDEX];
+	struct aie2_bar_off_pair	psp_regs_off[PSP_MAX_REGS];
+	struct aie2_bar_off_pair	smu_regs_off[SMU_MAX_REGS];
+	struct aie2_hw_ops		hw_ops;
+};
+
+extern const struct amdxdna_dev_ops aie2_ops;
+
+int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev,
+		     enum rt_config_category category, u32 *val);
+
+/* aie2 npu hw config */
+extern const struct dpm_clk_freq npu1_dpm_clk_table[];
+extern const struct dpm_clk_freq npu4_dpm_clk_table[];
+extern const struct rt_config npu1_default_rt_cfg[];
+extern const struct rt_config npu4_default_rt_cfg[];
+
+/* aie2_smu.c */
+int aie2_smu_init(struct amdxdna_dev_hdl *ndev);
+void aie2_smu_fini(struct amdxdna_dev_hdl *ndev);
+int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level);
+int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level);
+
+/* aie2_pm.c */
+int aie2_pm_init(struct amdxdna_dev_hdl *ndev);
+int aie2_pm_set_mode(struct amdxdna_dev_hdl *ndev, enum amdxdna_power_mode_type target);
+
+/* aie2_psp.c */
+struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf);
+int aie2_psp_start(struct psp_device *psp);
+void aie2_psp_stop(struct psp_device *psp);
+
+/* aie2_error.c */
+int aie2_error_async_events_alloc(struct amdxdna_dev_hdl *ndev);
+void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev);
+int aie2_error_async_events_send(struct amdxdna_dev_hdl *ndev);
+int aie2_error_async_msg_thread(void *data);
+
+/* aie2_message.c */
+int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev);
+int aie2_resume_fw(struct amdxdna_dev_hdl *ndev);
+int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value);
+int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value);
+int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid);
+int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version);
+int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata);
+int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
+				struct amdxdna_fw_ver *fw_ver);
+int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx);
+int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx);
+int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size);
+int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, u32 size, u32 *cols_filled);
+int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size,
+				 void *handle, int (*cb)(void*, void __iomem *, size_t));
+int aie2_config_cu(struct amdxdna_hwctx *hwctx);
+int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
+		 int (*notify_cb)(void *, void __iomem *, size_t));
+int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx,
+				struct amdxdna_sched_job *job,
+				int (*notify_cb)(void *, void __iomem *, size_t));
+int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx,
+			       struct amdxdna_sched_job *job,
+			       int (*notify_cb)(void *, void __iomem *, size_t));
+int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
+		 int (*notify_cb)(void *, void __iomem *, size_t));
+
+/* aie2_hwctx.c */
+int aie2_hwctx_init(struct amdxdna_hwctx *hwctx);
+void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx);
+int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size);
+void aie2_hwctx_suspend(struct amdxdna_client *client);
+int aie2_hwctx_resume(struct amdxdna_client *client);
+int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq);
+void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, unsigned long cur_seq);
+
+#endif /* _AIE2_PCI_H_ */
diff --git a/drivers/accel/amdxdna/aie2_pm.c b/drivers/accel/amdxdna/aie2_pm.c
new file mode 100644
index 000000000000..426c38fce848
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_pm.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_pci_drv.h"
+
+#define AIE2_CLK_GATING_ENABLE	1
+#define AIE2_CLK_GATING_DISABLE	0
+
+static int aie2_pm_set_clk_gating(struct amdxdna_dev_hdl *ndev, u32 val)
+{
+	int ret;
+
+	ret = aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, &val);
+	if (ret)
+		return ret;
+
+	ndev->clk_gating = val;
+	return 0;
+}
+
+int aie2_pm_init(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	if (ndev->dev_status != AIE2_DEV_UNINIT) {
+		/* Resume device */
+		ret = ndev->priv->hw_ops.set_dpm(ndev, ndev->dpm_level);
+		if (ret)
+			return ret;
+
+		ret = aie2_pm_set_clk_gating(ndev, ndev->clk_gating);
+		if (ret)
+			return ret;
+
+		return 0;
+	}
+
+	while (ndev->priv->dpm_clk_tbl[ndev->max_dpm_level].hclk)
+		ndev->max_dpm_level++;
+	ndev->max_dpm_level--;
+
+	ret = ndev->priv->hw_ops.set_dpm(ndev, ndev->max_dpm_level);
+	if (ret)
+		return ret;
+
+	ret = aie2_pm_set_clk_gating(ndev, AIE2_CLK_GATING_ENABLE);
+	if (ret)
+		return ret;
+
+	ndev->pw_mode = POWER_MODE_DEFAULT;
+	ndev->dft_dpm_level = ndev->max_dpm_level;
+
+	return 0;
+}
+
+int aie2_pm_set_mode(struct amdxdna_dev_hdl *ndev, enum amdxdna_power_mode_type target)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+	u32 clk_gating, dpm_level;
+	int ret;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	if (ndev->pw_mode == target)
+		return 0;
+
+	switch (target) {
+	case POWER_MODE_TURBO:
+		if (ndev->hwctx_num) {
+			XDNA_ERR(xdna, "Can not set turbo when there is active hwctx");
+			return -EINVAL;
+		}
+
+		clk_gating = AIE2_CLK_GATING_DISABLE;
+		dpm_level = ndev->max_dpm_level;
+		break;
+	case POWER_MODE_HIGH:
+		clk_gating = AIE2_CLK_GATING_ENABLE;
+		dpm_level = ndev->max_dpm_level;
+		break;
+	case POWER_MODE_DEFAULT:
+		clk_gating = AIE2_CLK_GATING_ENABLE;
+		dpm_level = ndev->dft_dpm_level;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	ret = ndev->priv->hw_ops.set_dpm(ndev, dpm_level);
+	if (ret)
+		return ret;
+
+	ret = aie2_pm_set_clk_gating(ndev, clk_gating);
+	if (ret)
+		return ret;
+
+	ndev->pw_mode = target;
+
+	return 0;
+}
diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c
new file mode 100644
index 000000000000..f28a060a8810
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_psp.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/drm_device.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/bitfield.h>
+#include <linux/iopoll.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+#define PSP_STATUS_READY	BIT(31)
+
+/* PSP commands */
+#define PSP_VALIDATE		1
+#define PSP_START		2
+#define PSP_RELEASE_TMR		3
+
+/* PSP special arguments */
+#define PSP_START_COPY_FW	1
+
+/* PSP response error code */
+#define PSP_ERROR_CANCEL	0xFFFF0002
+#define PSP_ERROR_BAD_STATE	0xFFFF0007
+
+#define PSP_FW_ALIGN		0x10000
+#define PSP_POLL_INTERVAL	20000	/* us */
+#define PSP_POLL_TIMEOUT	1000000	/* us */
+
+#define PSP_REG(p, reg) ((p)->psp_regs[reg])
+
+struct psp_device {
+	struct drm_device	*ddev;
+	struct psp_config	conf;
+	u32			fw_buf_sz;
+	u64			fw_paddr;
+	void			*fw_buffer;
+	void __iomem		*psp_regs[PSP_MAX_REGS];
+};
+
+static int psp_exec(struct psp_device *psp, u32 *reg_vals)
+{
+	u32 resp_code;
+	int ret, i;
+	u32 ready;
+
+	/* Write command and argument registers */
+	for (i = 0; i < PSP_NUM_IN_REGS; i++)
+		writel(reg_vals[i], PSP_REG(psp, i));
+
+	/* clear and set PSP INTR register to kick off */
+	writel(0, PSP_REG(psp, PSP_INTR_REG));
+	writel(1, PSP_REG(psp, PSP_INTR_REG));
+
+	/* PSP should be busy. Wait for ready, so we know task is done. */
+	ret = readx_poll_timeout(readl, PSP_REG(psp, PSP_STATUS_REG), ready,
+				 FIELD_GET(PSP_STATUS_READY, ready),
+				 PSP_POLL_INTERVAL, PSP_POLL_TIMEOUT);
+	if (ret) {
+		drm_err(psp->ddev, "PSP is not ready, ret 0x%x", ret);
+		return ret;
+	}
+
+	resp_code = readl(PSP_REG(psp, PSP_RESP_REG));
+	if (resp_code) {
+		drm_err(psp->ddev, "fw return error 0x%x", resp_code);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+void aie2_psp_stop(struct psp_device *psp)
+{
+	u32 reg_vals[PSP_NUM_IN_REGS] = { PSP_RELEASE_TMR, };
+	int ret;
+
+	ret = psp_exec(psp, reg_vals);
+	if (ret)
+		drm_err(psp->ddev, "release tmr failed, ret %d", ret);
+}
+
+int aie2_psp_start(struct psp_device *psp)
+{
+	u32 reg_vals[PSP_NUM_IN_REGS];
+	int ret;
+
+	reg_vals[0] = PSP_VALIDATE;
+	reg_vals[1] = lower_32_bits(psp->fw_paddr);
+	reg_vals[2] = upper_32_bits(psp->fw_paddr);
+	reg_vals[3] = psp->fw_buf_sz;
+
+	ret = psp_exec(psp, reg_vals);
+	if (ret) {
+		drm_err(psp->ddev, "failed to validate fw, ret %d", ret);
+		return ret;
+	}
+
+	memset(reg_vals, 0, sizeof(reg_vals));
+	reg_vals[0] = PSP_START;
+	reg_vals[1] = PSP_START_COPY_FW;
+	ret = psp_exec(psp, reg_vals);
+	if (ret) {
+		drm_err(psp->ddev, "failed to start fw, ret %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf)
+{
+	struct psp_device *psp;
+	u64 offset;
+
+	psp = drmm_kzalloc(ddev, sizeof(*psp), GFP_KERNEL);
+	if (!psp)
+		return NULL;
+
+	psp->ddev = ddev;
+	memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs));
+
+	psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN);
+	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz + PSP_FW_ALIGN, GFP_KERNEL);
+	if (!psp->fw_buffer) {
+		drm_err(ddev, "no memory for fw buffer");
+		return NULL;
+	}
+
+	/*
+	 * AMD Platform Security Processor(PSP) requires host physical
+	 * address to load NPU firmware.
+	 */
+	psp->fw_paddr = virt_to_phys(psp->fw_buffer);
+	offset = ALIGN(psp->fw_paddr, PSP_FW_ALIGN) - psp->fw_paddr;
+	psp->fw_paddr += offset;
+	memcpy(psp->fw_buffer + offset, conf->fw_buf, conf->fw_size);
+
+	return psp;
+}
diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c
new file mode 100644
index 000000000000..d303701b0ded
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_smu.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/drm_device.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/iopoll.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_pci_drv.h"
+
+#define SMU_RESULT_OK		1
+
+/* SMU commands */
+#define AIE2_SMU_POWER_ON		0x3
+#define AIE2_SMU_POWER_OFF		0x4
+#define AIE2_SMU_SET_MPNPUCLK_FREQ	0x5
+#define AIE2_SMU_SET_HCLK_FREQ		0x6
+#define AIE2_SMU_SET_SOFT_DPMLEVEL	0x7
+#define AIE2_SMU_SET_HARD_DPMLEVEL	0x8
+
+static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd,
+			 u32 reg_arg, u32 *out)
+{
+	u32 resp;
+	int ret;
+
+	writel(0, SMU_REG(ndev, SMU_RESP_REG));
+	writel(reg_arg, SMU_REG(ndev, SMU_ARG_REG));
+	writel(reg_cmd, SMU_REG(ndev, SMU_CMD_REG));
+
+	/* Clear and set SMU_INTR_REG to kick off */
+	writel(0, SMU_REG(ndev, SMU_INTR_REG));
+	writel(1, SMU_REG(ndev, SMU_INTR_REG));
+
+	ret = readx_poll_timeout(readl, SMU_REG(ndev, SMU_RESP_REG), resp,
+				 resp, AIE2_INTERVAL, AIE2_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "smu cmd %d timed out", reg_cmd);
+		return ret;
+	}
+
+	if (out)
+		*out = readl(SMU_REG(ndev, SMU_OUT_REG));
+
+	if (resp != SMU_RESULT_OK) {
+		XDNA_ERR(ndev->xdna, "smu cmd %d failed, 0x%x", reg_cmd, resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
+{
+	u32 freq;
+	int ret;
+
+	ret = aie2_smu_exec(ndev, AIE2_SMU_SET_MPNPUCLK_FREQ,
+			    ndev->priv->dpm_clk_tbl[dpm_level].npuclk, &freq);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Set npu clock to %d failed, ret %d\n",
+			 ndev->priv->dpm_clk_tbl[dpm_level].npuclk, ret);
+		return ret;
+	}
+	ndev->npuclk_freq = freq;
+
+	ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HCLK_FREQ,
+			    ndev->priv->dpm_clk_tbl[dpm_level].hclk, &freq);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Set h clock to %d failed, ret %d\n",
+			 ndev->priv->dpm_clk_tbl[dpm_level].hclk, ret);
+		return ret;
+	}
+	ndev->hclk_freq = freq;
+	ndev->dpm_level = dpm_level;
+
+	XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
+		 ndev->npuclk_freq, ndev->hclk_freq);
+
+	return 0;
+}
+
+int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
+{
+	int ret;
+
+	ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HARD_DPMLEVEL, dpm_level, NULL);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Set hard dpm level %d failed, ret %d ",
+			 dpm_level, ret);
+		return ret;
+	}
+
+	ret = aie2_smu_exec(ndev, AIE2_SMU_SET_SOFT_DPMLEVEL, dpm_level, NULL);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Set soft dpm level %d failed, ret %d",
+			 dpm_level, ret);
+		return ret;
+	}
+
+	ndev->npuclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].npuclk;
+	ndev->hclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].hclk;
+	ndev->dpm_level = dpm_level;
+
+	XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
+		 ndev->npuclk_freq, ndev->hclk_freq);
+
+	return 0;
+}
+
+int aie2_smu_init(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0, NULL);
+	if (ret) {
+		XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void aie2_smu_fini(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ndev->priv->hw_ops.set_dpm(ndev, 0);
+	ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0, NULL);
+	if (ret)
+		XDNA_ERR(ndev->xdna, "Power off failed, ret %d", ret);
+}
diff --git a/drivers/accel/amdxdna/aie2_solver.c b/drivers/accel/amdxdna/aie2_solver.c
new file mode 100644
index 000000000000..2013d1f13aae
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_solver.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/drm_device.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+#include <linux/bitops.h>
+#include <linux/bitmap.h>
+#include <linux/slab.h>
+
+#include "aie2_solver.h"
+
+struct partition_node {
+	struct list_head	list;
+	u32			nshared;	/* # shared requests */
+	u32			start_col;	/* start column */
+	u32			ncols;		/* # columns */
+	bool			exclusive;	/* can not be shared if set */
+};
+
+struct solver_node {
+	struct list_head	list;
+	u64			rid;		/* Request ID from consumer */
+
+	struct partition_node	*pt_node;
+	void			*cb_arg;
+	u32			dpm_level;
+	u32			cols_len;
+	u32			start_cols[] __counted_by(cols_len);
+};
+
+struct solver_rgroup {
+	u32				rgid;
+	u32				nnode;
+	u32				npartition_node;
+
+	DECLARE_BITMAP(resbit, XRS_MAX_COL);
+	struct list_head		node_list;
+	struct list_head		pt_node_list;
+};
+
+struct solver_state {
+	struct solver_rgroup		rgp;
+	struct init_config		cfg;
+	struct xrs_action_ops		*actions;
+};
+
+static u32 calculate_gops(struct aie_qos *rqos)
+{
+	u32 service_rate = 0;
+
+	if (rqos->latency)
+		service_rate = (1000 / rqos->latency);
+
+	if (rqos->fps > service_rate)
+		return rqos->fps * rqos->gops;
+
+	return service_rate * rqos->gops;
+}
+
+/*
+ * qos_meet() - Check the QOS request can be met.
+ */
+static int qos_meet(struct solver_state *xrs, struct aie_qos *rqos, u32 cgops)
+{
+	u32 request_gops = calculate_gops(rqos) * xrs->cfg.sys_eff_factor;
+
+	if (request_gops <= cgops)
+		return 0;
+
+	return -EINVAL;
+}
+
+/*
+ * sanity_check() - Do a basic sanity check on allocation request.
+ */
+static int sanity_check(struct solver_state *xrs, struct alloc_requests *req)
+{
+	struct cdo_parts *cdop = &req->cdo;
+	struct aie_qos *rqos = &req->rqos;
+	u32 cu_clk_freq;
+
+	if (cdop->ncols > xrs->cfg.total_col)
+		return -EINVAL;
+
+	/*
+	 * We can find at least one CDOs groups that meet the
+	 * GOPs requirement.
+	 */
+	cu_clk_freq = xrs->cfg.clk_list.cu_clk_list[xrs->cfg.clk_list.num_levels - 1];
+
+	if (qos_meet(xrs, rqos, cdop->qos_cap.opc * cu_clk_freq / 1000))
+		return -EINVAL;
+
+	return 0;
+}
+
+static bool is_valid_qos_dpm_params(struct aie_qos *rqos)
+{
+	/*
+	 * gops is retrieved from the xmodel, so it's always set
+	 * fps and latency are the configurable params from the application
+	 */
+	if (rqos->gops > 0 && (rqos->fps > 0 ||  rqos->latency > 0))
+		return true;
+
+	return false;
+}
+
+static int set_dpm_level(struct solver_state *xrs, struct alloc_requests *req, u32 *dpm_level)
+{
+	struct solver_rgroup *rgp = &xrs->rgp;
+	struct cdo_parts *cdop = &req->cdo;
+	struct aie_qos *rqos = &req->rqos;
+	u32 freq, max_dpm_level, level;
+	struct solver_node *node;
+
+	max_dpm_level = xrs->cfg.clk_list.num_levels - 1;
+	/* If no QoS parameters are passed, set it to the max DPM level */
+	if (!is_valid_qos_dpm_params(rqos)) {
+		level = max_dpm_level;
+		goto set_dpm;
+	}
+
+	/* Find one CDO group that meet the GOPs requirement. */
+	for (level = 0; level < max_dpm_level; level++) {
+		freq = xrs->cfg.clk_list.cu_clk_list[level];
+		if (!qos_meet(xrs, rqos, cdop->qos_cap.opc * freq / 1000))
+			break;
+	}
+
+	/* set the dpm level which fits all the sessions */
+	list_for_each_entry(node, &rgp->node_list, list) {
+		if (node->dpm_level > level)
+			level = node->dpm_level;
+	}
+
+set_dpm:
+	*dpm_level = level;
+	return xrs->cfg.actions->set_dft_dpm_level(xrs->cfg.ddev, level);
+}
+
+static struct solver_node *rg_search_node(struct solver_rgroup *rgp, u64 rid)
+{
+	struct solver_node *node;
+
+	list_for_each_entry(node, &rgp->node_list, list) {
+		if (node->rid == rid)
+			return node;
+	}
+
+	return NULL;
+}
+
+static void remove_partition_node(struct solver_rgroup *rgp,
+				  struct partition_node *pt_node)
+{
+	pt_node->nshared--;
+	if (pt_node->nshared > 0)
+		return;
+
+	list_del(&pt_node->list);
+	rgp->npartition_node--;
+
+	bitmap_clear(rgp->resbit, pt_node->start_col, pt_node->ncols);
+	kfree(pt_node);
+}
+
+static void remove_solver_node(struct solver_rgroup *rgp,
+			       struct solver_node *node)
+{
+	list_del(&node->list);
+	rgp->nnode--;
+
+	if (node->pt_node)
+		remove_partition_node(rgp, node->pt_node);
+
+	kfree(node);
+}
+
+static int get_free_partition(struct solver_state *xrs,
+			      struct solver_node *snode,
+			      struct alloc_requests *req)
+{
+	struct partition_node *pt_node;
+	u32 ncols = req->cdo.ncols;
+	u32 col, i;
+
+	for (i = 0; i < snode->cols_len; i++) {
+		col = snode->start_cols[i];
+		if (find_next_bit(xrs->rgp.resbit, XRS_MAX_COL, col) >= col + ncols)
+			break;
+	}
+
+	if (i == snode->cols_len)
+		return -ENODEV;
+
+	pt_node = kzalloc(sizeof(*pt_node), GFP_KERNEL);
+	if (!pt_node)
+		return -ENOMEM;
+
+	pt_node->nshared = 1;
+	pt_node->start_col = col;
+	pt_node->ncols = ncols;
+
+	/*
+	 * Always set exclusive to false for now.
+	 */
+	pt_node->exclusive = false;
+
+	list_add_tail(&pt_node->list, &xrs->rgp.pt_node_list);
+	xrs->rgp.npartition_node++;
+	bitmap_set(xrs->rgp.resbit, pt_node->start_col, pt_node->ncols);
+
+	snode->pt_node = pt_node;
+
+	return 0;
+}
+
+static int allocate_partition(struct solver_state *xrs,
+			      struct solver_node *snode,
+			      struct alloc_requests *req)
+{
+	struct partition_node *pt_node, *rpt_node = NULL;
+	int idx, ret;
+
+	ret = get_free_partition(xrs, snode, req);
+	if (!ret)
+		return ret;
+
+	/* try to get a share-able partition */
+	list_for_each_entry(pt_node, &xrs->rgp.pt_node_list, list) {
+		if (pt_node->exclusive)
+			continue;
+
+		if (rpt_node && pt_node->nshared >= rpt_node->nshared)
+			continue;
+
+		for (idx = 0; idx < snode->cols_len; idx++) {
+			if (snode->start_cols[idx] != pt_node->start_col)
+				continue;
+
+			if (req->cdo.ncols != pt_node->ncols)
+				continue;
+
+			rpt_node = pt_node;
+			break;
+		}
+	}
+
+	if (!rpt_node)
+		return -ENODEV;
+
+	rpt_node->nshared++;
+	snode->pt_node = rpt_node;
+
+	return 0;
+}
+
+static struct solver_node *create_solver_node(struct solver_state *xrs,
+					      struct alloc_requests *req)
+{
+	struct cdo_parts *cdop = &req->cdo;
+	struct solver_node *node;
+	int ret;
+
+	node = kzalloc(struct_size(node, start_cols, cdop->cols_len), GFP_KERNEL);
+	if (!node)
+		return ERR_PTR(-ENOMEM);
+
+	node->rid = req->rid;
+	node->cols_len = cdop->cols_len;
+	memcpy(node->start_cols, cdop->start_cols, cdop->cols_len * sizeof(u32));
+
+	ret = allocate_partition(xrs, node, req);
+	if (ret)
+		goto free_node;
+
+	list_add_tail(&node->list, &xrs->rgp.node_list);
+	xrs->rgp.nnode++;
+	return node;
+
+free_node:
+	kfree(node);
+	return ERR_PTR(ret);
+}
+
+static void fill_load_action(struct solver_state *xrs,
+			     struct solver_node *snode,
+			     struct xrs_action_load *action)
+{
+	action->rid = snode->rid;
+	action->part.start_col = snode->pt_node->start_col;
+	action->part.ncols = snode->pt_node->ncols;
+}
+
+int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_arg)
+{
+	struct xrs_action_load load_act;
+	struct solver_node *snode;
+	struct solver_state *xrs;
+	u32 dpm_level;
+	int ret;
+
+	xrs = (struct solver_state *)hdl;
+
+	ret = sanity_check(xrs, req);
+	if (ret) {
+		drm_err(xrs->cfg.ddev, "invalid request");
+		return ret;
+	}
+
+	if (rg_search_node(&xrs->rgp, req->rid)) {
+		drm_err(xrs->cfg.ddev, "rid %lld is in-use", req->rid);
+		return -EEXIST;
+	}
+
+	snode = create_solver_node(xrs, req);
+	if (IS_ERR(snode))
+		return PTR_ERR(snode);
+
+	fill_load_action(xrs, snode, &load_act);
+	ret = xrs->cfg.actions->load(cb_arg, &load_act);
+	if (ret)
+		goto free_node;
+
+	ret = set_dpm_level(xrs, req, &dpm_level);
+	if (ret)
+		goto free_node;
+
+	snode->dpm_level = dpm_level;
+	snode->cb_arg = cb_arg;
+
+	drm_dbg(xrs->cfg.ddev, "start col %d ncols %d\n",
+		snode->pt_node->start_col, snode->pt_node->ncols);
+
+	return 0;
+
+free_node:
+	remove_solver_node(&xrs->rgp, snode);
+
+	return ret;
+}
+
+int xrs_release_resource(void *hdl, u64 rid)
+{
+	struct solver_state *xrs = hdl;
+	struct solver_node *node;
+
+	node = rg_search_node(&xrs->rgp, rid);
+	if (!node) {
+		drm_err(xrs->cfg.ddev, "node not exist");
+		return -ENODEV;
+	}
+
+	xrs->cfg.actions->unload(node->cb_arg);
+	remove_solver_node(&xrs->rgp, node);
+
+	return 0;
+}
+
+void *xrsm_init(struct init_config *cfg)
+{
+	struct solver_rgroup *rgp;
+	struct solver_state *xrs;
+
+	xrs = drmm_kzalloc(cfg->ddev, sizeof(*xrs), GFP_KERNEL);
+	if (!xrs)
+		return NULL;
+
+	memcpy(&xrs->cfg, cfg, sizeof(*cfg));
+
+	rgp = &xrs->rgp;
+	INIT_LIST_HEAD(&rgp->node_list);
+	INIT_LIST_HEAD(&rgp->pt_node_list);
+
+	return xrs;
+}
diff --git a/drivers/accel/amdxdna/aie2_solver.h b/drivers/accel/amdxdna/aie2_solver.h
new file mode 100644
index 000000000000..a2e3c52229e9
--- /dev/null
+++ b/drivers/accel/amdxdna/aie2_solver.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AIE2_SOLVER_H
+#define _AIE2_SOLVER_H
+
+#define XRS_MAX_COL 128
+
+/*
+ * Structure used to describe a partition. A partition is column based
+ * allocation unit described by its start column and number of columns.
+ */
+struct aie_part {
+	u32	start_col;
+	u32	ncols;
+};
+
+/*
+ * The QoS capabilities of a given AIE partition.
+ */
+struct aie_qos_cap {
+	u32     opc;            /* operations per cycle */
+	u32     dma_bw;         /* DMA bandwidth */
+};
+
+/*
+ * QoS requirement of a resource allocation.
+ */
+struct aie_qos {
+	u32	gops;		/* Giga operations */
+	u32	fps;		/* Frames per second */
+	u32	dma_bw;		/* DMA bandwidth */
+	u32	latency;	/* Frame response latency */
+	u32	exec_time;	/* Frame execution time */
+	u32	priority;	/* Request priority */
+};
+
+/*
+ * Structure used to describe a relocatable CDO (Configuration Data Object).
+ */
+struct cdo_parts {
+	u32		   *start_cols;		/* Start column array */
+	u32		   cols_len;		/* Length of start column array */
+	u32		   ncols;		/* # of column */
+	struct aie_qos_cap qos_cap;		/* CDO QoS capabilities */
+};
+
+/*
+ * Structure used to describe a request to allocate.
+ */
+struct alloc_requests {
+	u64			rid;
+	struct cdo_parts	cdo;
+	struct aie_qos		rqos;		/* Requested QoS */
+};
+
+/*
+ * Load callback argument
+ */
+struct xrs_action_load {
+	u32                     rid;
+	struct aie_part         part;
+};
+
+/*
+ * Define the power level available
+ *
+ * POWER_LEVEL_MIN:
+ *     Lowest power level. Usually set when all actions are unloaded.
+ *
+ * POWER_LEVEL_n
+ *     Power levels 0 - n, is a step increase in system frequencies
+ */
+enum power_level {
+	POWER_LEVEL_MIN = 0x0,
+	POWER_LEVEL_0   = 0x1,
+	POWER_LEVEL_1   = 0x2,
+	POWER_LEVEL_2   = 0x3,
+	POWER_LEVEL_3   = 0x4,
+	POWER_LEVEL_4   = 0x5,
+	POWER_LEVEL_5   = 0x6,
+	POWER_LEVEL_6   = 0x7,
+	POWER_LEVEL_7   = 0x8,
+	POWER_LEVEL_NUM,
+};
+
+/*
+ * Structure used to describe the frequency table.
+ * Resource solver chooses the frequency from the table
+ * to meet the QOS requirements.
+ */
+struct clk_list_info {
+	u32        num_levels;                     /* available power levels */
+	u32        cu_clk_list[POWER_LEVEL_NUM];   /* available aie clock frequencies in Mhz*/
+};
+
+struct xrs_action_ops {
+	int (*load)(void *cb_arg, struct xrs_action_load *action);
+	int (*unload)(void *cb_arg);
+	int (*set_dft_dpm_level)(struct drm_device *ddev, u32 level);
+};
+
+/*
+ * Structure used to describe information for solver during initialization.
+ */
+struct init_config {
+	u32			total_col;
+	u32			sys_eff_factor; /* system efficiency factor */
+	u32			latency_adj;    /* latency adjustment in ms */
+	struct clk_list_info	clk_list;       /* List of frequencies available in system */
+	struct drm_device	*ddev;
+	struct xrs_action_ops	*actions;
+};
+
+/*
+ * xrsm_init() - Register resource solver. Resource solver client needs
+ *              to call this function to register itself.
+ *
+ * @cfg:	The system metrics for resource solver to use
+ *
+ * Return:	A resource solver handle
+ *
+ * Note: We should only create one handle per AIE array to be managed.
+ */
+void *xrsm_init(struct init_config *cfg);
+
+/*
+ * xrs_allocate_resource() - Request to allocate resources for a given context
+ *                           and a partition metadata. (See struct part_meta)
+ *
+ * @hdl:	Resource solver handle obtained from xrs_init()
+ * @req:	Input to the Resource solver including request id
+ *		and partition metadata.
+ * @cb_arg:	callback argument pointer
+ *
+ * Return:	0 when successful.
+ *		Or standard error number when failing
+ *
+ * Note:
+ *      There is no lock mechanism inside resource solver. So it is
+ *      the caller's responsibility to lock down XCLBINs and grab
+ *      necessary lock.
+ */
+int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_arg);
+
+/*
+ * xrs_release_resource() - Request to free resources for a given context.
+ *
+ * @hdl:	Resource solver handle obtained from xrs_init()
+ * @rid:	The Request ID to identify the requesting context
+ */
+int xrs_release_resource(void *hdl, u64 rid);
+#endif /* _AIE2_SOLVER_H */
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
new file mode 100644
index 000000000000..4bfe4ef20550
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/xarray.h>
+#include <trace/events/amdxdna.h>
+
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_pci_drv.h"
+
+#define MAX_HWCTX_ID		255
+#define MAX_ARG_COUNT		4095
+
+struct amdxdna_fence {
+	struct dma_fence	base;
+	spinlock_t		lock; /* for base */
+	struct amdxdna_hwctx	*hwctx;
+};
+
+static const char *amdxdna_fence_get_driver_name(struct dma_fence *fence)
+{
+	return KBUILD_MODNAME;
+}
+
+static const char *amdxdna_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct amdxdna_fence *xdna_fence;
+
+	xdna_fence = container_of(fence, struct amdxdna_fence, base);
+
+	return xdna_fence->hwctx->name;
+}
+
+static const struct dma_fence_ops fence_ops = {
+	.get_driver_name = amdxdna_fence_get_driver_name,
+	.get_timeline_name = amdxdna_fence_get_timeline_name,
+};
+
+static struct dma_fence *amdxdna_fence_create(struct amdxdna_hwctx *hwctx)
+{
+	struct amdxdna_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return NULL;
+
+	fence->hwctx = hwctx;
+	spin_lock_init(&fence->lock);
+	dma_fence_init(&fence->base, &fence_ops, &fence->lock, hwctx->id, 0);
+	return &fence->base;
+}
+
+static void amdxdna_hwctx_destroy_rcu(struct amdxdna_hwctx *hwctx,
+				      struct srcu_struct *ss)
+{
+	struct amdxdna_dev *xdna = hwctx->client->xdna;
+
+	synchronize_srcu(ss);
+
+	/* At this point, user is not able to submit new commands */
+	xdna->dev_info->ops->hwctx_fini(hwctx);
+
+	kfree(hwctx->name);
+	kfree(hwctx);
+}
+
+int amdxdna_hwctx_walk(struct amdxdna_client *client, void *arg,
+		       int (*walk)(struct amdxdna_hwctx *hwctx, void *arg))
+{
+	struct amdxdna_hwctx *hwctx;
+	unsigned long hwctx_id;
+	int ret = 0, idx;
+
+	idx = srcu_read_lock(&client->hwctx_srcu);
+	amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
+		ret = walk(hwctx, arg);
+		if (ret)
+			break;
+	}
+	srcu_read_unlock(&client->hwctx_srcu, idx);
+
+	return ret;
+}
+
+void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size)
+{
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+	u32 num_masks, count;
+
+	if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN)
+		num_masks = 0;
+	else
+		num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header);
+
+	if (size) {
+		count = FIELD_GET(AMDXDNA_CMD_COUNT, cmd->header);
+		if (unlikely(count <= num_masks)) {
+			*size = 0;
+			return NULL;
+		}
+		*size = (count - num_masks) * sizeof(u32);
+	}
+	return &cmd->data[num_masks];
+}
+
+int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+	u32 num_masks, i;
+	u32 *cu_mask;
+
+	if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN)
+		return -1;
+
+	num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header);
+	cu_mask = cmd->data;
+	for (i = 0; i < num_masks; i++) {
+		if (cu_mask[i])
+			return ffs(cu_mask[i]) - 1;
+	}
+
+	return -1;
+}
+
+/*
+ * This should be called in close() and remove(). DO NOT call in other syscalls.
+ * This guarantee that when hwctx and resources will be released, if user
+ * doesn't call amdxdna_drm_destroy_hwctx_ioctl.
+ */
+void amdxdna_hwctx_remove_all(struct amdxdna_client *client)
+{
+	struct amdxdna_hwctx *hwctx;
+	unsigned long hwctx_id;
+
+	amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
+		XDNA_DBG(client->xdna, "PID %d close HW context %d",
+			 client->pid, hwctx->id);
+		xa_erase(&client->hwctx_xa, hwctx->id);
+		amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu);
+	}
+}
+
+int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_drm_create_hwctx *args = data;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_hwctx *hwctx;
+	int ret, idx;
+
+	if (args->ext || args->ext_flags)
+		return -EINVAL;
+
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
+
+	hwctx = kzalloc(sizeof(*hwctx), GFP_KERNEL);
+	if (!hwctx) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	if (copy_from_user(&hwctx->qos, u64_to_user_ptr(args->qos_p), sizeof(hwctx->qos))) {
+		XDNA_ERR(xdna, "Access QoS info failed");
+		ret = -EFAULT;
+		goto free_hwctx;
+	}
+
+	hwctx->client = client;
+	hwctx->fw_ctx_id = -1;
+	hwctx->num_tiles = args->num_tiles;
+	hwctx->mem_size = args->mem_size;
+	hwctx->max_opc = args->max_opc;
+	ret = xa_alloc_cyclic(&client->hwctx_xa, &hwctx->id, hwctx,
+			      XA_LIMIT(AMDXDNA_INVALID_CTX_HANDLE + 1, MAX_HWCTX_ID),
+			      &client->next_hwctxid, GFP_KERNEL);
+	if (ret < 0) {
+		XDNA_ERR(xdna, "Allocate hwctx ID failed, ret %d", ret);
+		goto free_hwctx;
+	}
+
+	hwctx->name = kasprintf(GFP_KERNEL, "hwctx.%d.%d", client->pid, hwctx->id);
+	if (!hwctx->name) {
+		ret = -ENOMEM;
+		goto rm_id;
+	}
+
+	mutex_lock(&xdna->dev_lock);
+	ret = xdna->dev_info->ops->hwctx_init(hwctx);
+	if (ret) {
+		mutex_unlock(&xdna->dev_lock);
+		XDNA_ERR(xdna, "Init hwctx failed, ret %d", ret);
+		goto free_name;
+	}
+	args->handle = hwctx->id;
+	args->syncobj_handle = hwctx->syncobj_hdl;
+	mutex_unlock(&xdna->dev_lock);
+
+	atomic64_set(&hwctx->job_submit_cnt, 0);
+	atomic64_set(&hwctx->job_free_cnt, 0);
+	XDNA_DBG(xdna, "PID %d create HW context %d, ret %d", client->pid, args->handle, ret);
+	drm_dev_exit(idx);
+	return 0;
+
+free_name:
+	kfree(hwctx->name);
+rm_id:
+	xa_erase(&client->hwctx_xa, hwctx->id);
+free_hwctx:
+	kfree(hwctx);
+exit:
+	drm_dev_exit(idx);
+	return ret;
+}
+
+int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_drm_destroy_hwctx *args = data;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_hwctx *hwctx;
+	int ret = 0, idx;
+
+	if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad)))
+		return -EINVAL;
+
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
+
+	mutex_lock(&xdna->dev_lock);
+	hwctx = xa_erase(&client->hwctx_xa, args->handle);
+	if (!hwctx) {
+		ret = -EINVAL;
+		XDNA_DBG(xdna, "PID %d HW context %d not exist",
+			 client->pid, args->handle);
+		goto out;
+	}
+
+	/*
+	 * The pushed jobs are handled by DRM scheduler during destroy.
+	 * SRCU to synchronize with exec command ioctls.
+	 */
+	amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu);
+
+	XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle);
+out:
+	mutex_unlock(&xdna->dev_lock);
+	drm_dev_exit(idx);
+	return ret;
+}
+
+int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_drm_config_hwctx *args = data;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_hwctx *hwctx;
+	int ret, idx;
+	u32 buf_size;
+	void *buf;
+	u64 val;
+
+	if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad)))
+		return -EINVAL;
+
+	if (!xdna->dev_info->ops->hwctx_config)
+		return -EOPNOTSUPP;
+
+	val = args->param_val;
+	buf_size = args->param_val_size;
+
+	switch (args->param_type) {
+	case DRM_AMDXDNA_HWCTX_CONFIG_CU:
+		/* For those types that param_val is pointer */
+		if (buf_size > PAGE_SIZE) {
+			XDNA_ERR(xdna, "Config CU param buffer too large");
+			return -E2BIG;
+		}
+
+		/* Hwctx needs to keep buf */
+		buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		if (copy_from_user(buf, u64_to_user_ptr(val), buf_size)) {
+			kfree(buf);
+			return -EFAULT;
+		}
+
+		break;
+	case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF:
+	case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF:
+		/* For those types that param_val is a value */
+		buf = NULL;
+		buf_size = 0;
+		break;
+	default:
+		XDNA_DBG(xdna, "Unknown HW context config type %d", args->param_type);
+		return -EINVAL;
+	}
+
+	mutex_lock(&xdna->dev_lock);
+	idx = srcu_read_lock(&client->hwctx_srcu);
+	hwctx = xa_load(&client->hwctx_xa, args->handle);
+	if (!hwctx) {
+		XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle);
+		ret = -EINVAL;
+		goto unlock_srcu;
+	}
+
+	ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size);
+
+unlock_srcu:
+	srcu_read_unlock(&client->hwctx_srcu, idx);
+	mutex_unlock(&xdna->dev_lock);
+	kfree(buf);
+	return ret;
+}
+
+static void
+amdxdna_arg_bos_put(struct amdxdna_sched_job *job)
+{
+	int i;
+
+	for (i = 0; i < job->bo_cnt; i++) {
+		if (!job->bos[i])
+			break;
+		drm_gem_object_put(job->bos[i]);
+	}
+}
+
+static int
+amdxdna_arg_bos_lookup(struct amdxdna_client *client,
+		       struct amdxdna_sched_job *job,
+		       u32 *bo_hdls, u32 bo_cnt)
+{
+	struct drm_gem_object *gobj;
+	int i, ret;
+
+	job->bo_cnt = bo_cnt;
+	for (i = 0; i < job->bo_cnt; i++) {
+		struct amdxdna_gem_obj *abo;
+
+		gobj = drm_gem_object_lookup(client->filp, bo_hdls[i]);
+		if (!gobj) {
+			ret = -ENOENT;
+			goto put_shmem_bo;
+		}
+		abo = to_xdna_obj(gobj);
+
+		mutex_lock(&abo->lock);
+		if (abo->pinned) {
+			mutex_unlock(&abo->lock);
+			job->bos[i] = gobj;
+			continue;
+		}
+
+		ret = amdxdna_gem_pin_nolock(abo);
+		if (ret) {
+			mutex_unlock(&abo->lock);
+			drm_gem_object_put(gobj);
+			goto put_shmem_bo;
+		}
+		abo->pinned = true;
+		mutex_unlock(&abo->lock);
+
+		job->bos[i] = gobj;
+	}
+
+	return 0;
+
+put_shmem_bo:
+	amdxdna_arg_bos_put(job);
+	return ret;
+}
+
+void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job)
+{
+	trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release");
+	amdxdna_arg_bos_put(job);
+	amdxdna_gem_put_obj(job->cmd_bo);
+}
+
+int amdxdna_cmd_submit(struct amdxdna_client *client,
+		       u32 cmd_bo_hdl, u32 *arg_bo_hdls, u32 arg_bo_cnt,
+		       u32 hwctx_hdl, u64 *seq)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_sched_job *job;
+	struct amdxdna_hwctx *hwctx;
+	int ret, idx;
+
+	XDNA_DBG(xdna, "Command BO hdl %d, Arg BO count %d", cmd_bo_hdl, arg_bo_cnt);
+	job = kzalloc(struct_size(job, bos, arg_bo_cnt), GFP_KERNEL);
+	if (!job)
+		return -ENOMEM;
+
+	if (cmd_bo_hdl != AMDXDNA_INVALID_BO_HANDLE) {
+		job->cmd_bo = amdxdna_gem_get_obj(client, cmd_bo_hdl, AMDXDNA_BO_CMD);
+		if (!job->cmd_bo) {
+			XDNA_ERR(xdna, "Failed to get cmd bo from %d", cmd_bo_hdl);
+			ret = -EINVAL;
+			goto free_job;
+		}
+	} else {
+		job->cmd_bo = NULL;
+	}
+
+	ret = amdxdna_arg_bos_lookup(client, job, arg_bo_hdls, arg_bo_cnt);
+	if (ret) {
+		XDNA_ERR(xdna, "Argument BOs lookup failed, ret %d", ret);
+		goto cmd_put;
+	}
+
+	idx = srcu_read_lock(&client->hwctx_srcu);
+	hwctx = xa_load(&client->hwctx_xa, hwctx_hdl);
+	if (!hwctx) {
+		XDNA_DBG(xdna, "PID %d failed to get hwctx %d",
+			 client->pid, hwctx_hdl);
+		ret = -EINVAL;
+		goto unlock_srcu;
+	}
+
+	if (hwctx->status != HWCTX_STAT_READY) {
+		XDNA_ERR(xdna, "HW Context is not ready");
+		ret = -EINVAL;
+		goto unlock_srcu;
+	}
+
+	job->hwctx = hwctx;
+	job->mm = current->mm;
+
+	job->fence = amdxdna_fence_create(hwctx);
+	if (!job->fence) {
+		XDNA_ERR(xdna, "Failed to create fence");
+		ret = -ENOMEM;
+		goto unlock_srcu;
+	}
+	kref_init(&job->refcnt);
+
+	ret = xdna->dev_info->ops->cmd_submit(hwctx, job, seq);
+	if (ret)
+		goto put_fence;
+
+	/*
+	 * The amdxdna_hwctx_destroy_rcu() will release hwctx and associated
+	 * resource after synchronize_srcu(). The submitted jobs should be
+	 * handled by the queue, for example DRM scheduler, in device layer.
+	 * For here we can unlock SRCU.
+	 */
+	srcu_read_unlock(&client->hwctx_srcu, idx);
+	trace_amdxdna_debug_point(hwctx->name, *seq, "job pushed");
+
+	return 0;
+
+put_fence:
+	dma_fence_put(job->fence);
+unlock_srcu:
+	srcu_read_unlock(&client->hwctx_srcu, idx);
+	amdxdna_arg_bos_put(job);
+cmd_put:
+	amdxdna_gem_put_obj(job->cmd_bo);
+free_job:
+	kfree(job);
+	return ret;
+}
+
+/*
+ * The submit command ioctl submits a command to firmware. One firmware command
+ * may contain multiple command BOs for processing as a whole.
+ * The command sequence number is returned which can be used for wait command ioctl.
+ */
+static int amdxdna_drm_submit_execbuf(struct amdxdna_client *client,
+				      struct amdxdna_drm_exec_cmd *args)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	u32 *arg_bo_hdls = NULL;
+	u32 cmd_bo_hdl;
+	int ret;
+
+	if (args->arg_count > MAX_ARG_COUNT) {
+		XDNA_ERR(xdna, "Invalid arg bo count %d", args->arg_count);
+		return -EINVAL;
+	}
+
+	/* Only support single command for now. */
+	if (args->cmd_count != 1) {
+		XDNA_ERR(xdna, "Invalid cmd bo count %d", args->cmd_count);
+		return -EINVAL;
+	}
+
+	cmd_bo_hdl = (u32)args->cmd_handles;
+	if (args->arg_count) {
+		arg_bo_hdls = kcalloc(args->arg_count, sizeof(u32), GFP_KERNEL);
+		if (!arg_bo_hdls)
+			return -ENOMEM;
+		ret = copy_from_user(arg_bo_hdls, u64_to_user_ptr(args->args),
+				     args->arg_count * sizeof(u32));
+		if (ret) {
+			ret = -EFAULT;
+			goto free_cmd_bo_hdls;
+		}
+	}
+
+	ret = amdxdna_cmd_submit(client, cmd_bo_hdl, arg_bo_hdls,
+				 args->arg_count, args->hwctx, &args->seq);
+	if (ret)
+		XDNA_DBG(xdna, "Submit cmds failed, ret %d", ret);
+
+free_cmd_bo_hdls:
+	kfree(arg_bo_hdls);
+	if (!ret)
+		XDNA_DBG(xdna, "Pushed cmd %lld to scheduler", args->seq);
+	return ret;
+}
+
+int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_drm_exec_cmd *args = data;
+
+	if (args->ext || args->ext_flags)
+		return -EINVAL;
+
+	switch (args->type) {
+	case AMDXDNA_CMD_SUBMIT_EXEC_BUF:
+		return amdxdna_drm_submit_execbuf(client, args);
+	}
+
+	XDNA_ERR(client->xdna, "Invalid command type %d", args->type);
+	return -EINVAL;
+}
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h
new file mode 100644
index 000000000000..7cd7a55936f0
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_ctx.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AMDXDNA_CTX_H_
+#define _AMDXDNA_CTX_H_
+
+#include <linux/bitfield.h>
+
+#include "amdxdna_gem.h"
+
+struct amdxdna_hwctx_priv;
+
+enum ert_cmd_opcode {
+	ERT_START_CU      = 0,
+	ERT_CMD_CHAIN     = 19,
+	ERT_START_NPU     = 20,
+};
+
+enum ert_cmd_state {
+	ERT_CMD_STATE_INVALID,
+	ERT_CMD_STATE_NEW,
+	ERT_CMD_STATE_QUEUED,
+	ERT_CMD_STATE_RUNNING,
+	ERT_CMD_STATE_COMPLETED,
+	ERT_CMD_STATE_ERROR,
+	ERT_CMD_STATE_ABORT,
+	ERT_CMD_STATE_SUBMITTED,
+	ERT_CMD_STATE_TIMEOUT,
+	ERT_CMD_STATE_NORESPONSE,
+};
+
+/*
+ * Interpretation of the beginning of data payload for ERT_START_NPU in
+ * amdxdna_cmd. The rest of the payload in amdxdna_cmd is regular kernel args.
+ */
+struct amdxdna_cmd_start_npu {
+	u64 buffer;       /* instruction buffer address */
+	u32 buffer_size;  /* size of buffer in bytes */
+	u32 prop_count;	  /* properties count */
+	u32 prop_args[];  /* properties and regular kernel arguments */
+};
+
+/*
+ * Interpretation of the beginning of data payload for ERT_CMD_CHAIN in
+ * amdxdna_cmd. The rest of the payload in amdxdna_cmd is cmd BO handles.
+ */
+struct amdxdna_cmd_chain {
+	u32 command_count;
+	u32 submit_index;
+	u32 error_index;
+	u32 reserved[3];
+	u64 data[] __counted_by(command_count);
+};
+
+/* Exec buffer command header format */
+#define AMDXDNA_CMD_STATE		GENMASK(3, 0)
+#define AMDXDNA_CMD_EXTRA_CU_MASK	GENMASK(11, 10)
+#define AMDXDNA_CMD_COUNT		GENMASK(22, 12)
+#define AMDXDNA_CMD_OPCODE		GENMASK(27, 23)
+struct amdxdna_cmd {
+	u32 header;
+	u32 data[];
+};
+
+struct amdxdna_hwctx {
+	struct amdxdna_client		*client;
+	struct amdxdna_hwctx_priv	*priv;
+	char				*name;
+
+	u32				id;
+	u32				max_opc;
+	u32				num_tiles;
+	u32				mem_size;
+	u32				fw_ctx_id;
+	u32				col_list_len;
+	u32				*col_list;
+	u32				start_col;
+	u32				num_col;
+#define HWCTX_STAT_INIT  0
+#define HWCTX_STAT_READY 1
+#define HWCTX_STAT_STOP  2
+	u32				status;
+	u32				old_status;
+
+	struct amdxdna_qos_info		     qos;
+	struct amdxdna_hwctx_param_config_cu *cus;
+	u32				syncobj_hdl;
+
+	atomic64_t			job_submit_cnt;
+	atomic64_t			job_free_cnt ____cacheline_aligned_in_smp;
+};
+
+#define drm_job_to_xdna_job(j) \
+	container_of(j, struct amdxdna_sched_job, base)
+
+struct amdxdna_sched_job {
+	struct drm_sched_job	base;
+	struct kref		refcnt;
+	struct amdxdna_hwctx	*hwctx;
+	struct mm_struct	*mm;
+	/* The fence to notice DRM scheduler that job is done by hardware */
+	struct dma_fence	*fence;
+	/* user can wait on this fence */
+	struct dma_fence	*out_fence;
+	bool			job_done;
+	u64			seq;
+	struct amdxdna_gem_obj	*cmd_bo;
+	size_t			bo_cnt;
+	struct drm_gem_object	*bos[] __counted_by(bo_cnt);
+};
+
+static inline u32
+amdxdna_cmd_get_op(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+
+	return FIELD_GET(AMDXDNA_CMD_OPCODE, cmd->header);
+}
+
+static inline void
+amdxdna_cmd_set_state(struct amdxdna_gem_obj *abo, enum ert_cmd_state s)
+{
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+
+	cmd->header &= ~AMDXDNA_CMD_STATE;
+	cmd->header |= FIELD_PREP(AMDXDNA_CMD_STATE, s);
+}
+
+static inline enum ert_cmd_state
+amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+
+	return FIELD_GET(AMDXDNA_CMD_STATE, cmd->header);
+}
+
+void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size);
+int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo);
+
+void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job);
+void amdxdna_hwctx_remove_all(struct amdxdna_client *client);
+int amdxdna_hwctx_walk(struct amdxdna_client *client, void *arg,
+		       int (*walk)(struct amdxdna_hwctx *hwctx, void *arg));
+
+int amdxdna_cmd_submit(struct amdxdna_client *client,
+		       u32 cmd_bo_hdls, u32 *arg_bo_hdls, u32 arg_bo_cnt,
+		       u32 hwctx_hdl, u64 *seq);
+
+int amdxdna_cmd_wait(struct amdxdna_client *client, u32 hwctx_hdl,
+		     u64 seq, u32 timeout);
+
+int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+
+#endif /* _AMDXDNA_CTX_H_ */
diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c
new file mode 100644
index 000000000000..d407a36eb412
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_gem.c
@@ -0,0 +1,975 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_cache.h>
+#include <drm/drm_device.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-direct.h>
+#include <linux/iosys-map.h>
+#include <linux/pagemap.h>
+#include <linux/vmalloc.h>
+
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_pci_drv.h"
+#include "amdxdna_ubuf.h"
+
+#define XDNA_MAX_CMD_BO_SIZE	SZ_32K
+
+MODULE_IMPORT_NS("DMA_BUF");
+
+static int
+amdxdna_gem_heap_alloc(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_client *client = abo->client;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_mem *mem = &abo->mem;
+	struct amdxdna_gem_obj *heap;
+	u64 offset;
+	u32 align;
+	int ret;
+
+	mutex_lock(&client->mm_lock);
+
+	heap = client->dev_heap;
+	if (!heap) {
+		ret = -EINVAL;
+		goto unlock_out;
+	}
+
+	if (heap->mem.userptr == AMDXDNA_INVALID_ADDR) {
+		XDNA_ERR(xdna, "Invalid dev heap userptr");
+		ret = -EINVAL;
+		goto unlock_out;
+	}
+
+	if (mem->size == 0 || mem->size > heap->mem.size) {
+		XDNA_ERR(xdna, "Invalid dev bo size 0x%lx, limit 0x%lx",
+			 mem->size, heap->mem.size);
+		ret = -EINVAL;
+		goto unlock_out;
+	}
+
+	align = 1 << max(PAGE_SHIFT, xdna->dev_info->dev_mem_buf_shift);
+	ret = drm_mm_insert_node_generic(&heap->mm, &abo->mm_node,
+					 mem->size, align,
+					 0, DRM_MM_INSERT_BEST);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret);
+		goto unlock_out;
+	}
+
+	mem->dev_addr = abo->mm_node.start;
+	offset = mem->dev_addr - heap->mem.dev_addr;
+	mem->userptr = heap->mem.userptr + offset;
+	mem->kva = heap->mem.kva + offset;
+
+	drm_gem_object_get(to_gobj(heap));
+
+unlock_out:
+	mutex_unlock(&client->mm_lock);
+
+	return ret;
+}
+
+static void
+amdxdna_gem_destroy_obj(struct amdxdna_gem_obj *abo)
+{
+	mutex_destroy(&abo->lock);
+	kfree(abo);
+}
+
+static void
+amdxdna_gem_heap_free(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_gem_obj *heap;
+
+	mutex_lock(&abo->client->mm_lock);
+
+	drm_mm_remove_node(&abo->mm_node);
+
+	heap = abo->client->dev_heap;
+	drm_gem_object_put(to_gobj(heap));
+
+	mutex_unlock(&abo->client->mm_lock);
+}
+
+static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni,
+				   const struct mmu_notifier_range *range,
+				   unsigned long cur_seq)
+{
+	struct amdxdna_umap *mapp = container_of(mni, struct amdxdna_umap, notifier);
+	struct amdxdna_gem_obj *abo = mapp->abo;
+	struct amdxdna_dev *xdna;
+
+	xdna = to_xdna_dev(to_gobj(abo)->dev);
+	XDNA_DBG(xdna, "Invalidating range 0x%lx, 0x%lx, type %d",
+		 mapp->vma->vm_start, mapp->vma->vm_end, abo->type);
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
+	down_write(&xdna->notifier_lock);
+	abo->mem.map_invalid = true;
+	mapp->invalid = true;
+	mmu_interval_set_seq(&mapp->notifier, cur_seq);
+	up_write(&xdna->notifier_lock);
+
+	xdna->dev_info->ops->hmm_invalidate(abo, cur_seq);
+
+	if (range->event == MMU_NOTIFY_UNMAP) {
+		down_write(&xdna->notifier_lock);
+		if (!mapp->unmapped) {
+			queue_work(xdna->notifier_wq, &mapp->hmm_unreg_work);
+			mapp->unmapped = true;
+		}
+		up_write(&xdna->notifier_lock);
+	}
+
+	return true;
+}
+
+static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = {
+	.invalidate = amdxdna_hmm_invalidate,
+};
+
+static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo,
+				   struct vm_area_struct *vma)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	struct amdxdna_umap *mapp;
+
+	down_read(&xdna->notifier_lock);
+	list_for_each_entry(mapp, &abo->mem.umap_list, node) {
+		if (!vma || mapp->vma == vma) {
+			if (!mapp->unmapped) {
+				queue_work(xdna->notifier_wq, &mapp->hmm_unreg_work);
+				mapp->unmapped = true;
+			}
+			if (vma)
+				break;
+		}
+	}
+	up_read(&xdna->notifier_lock);
+}
+
+static void amdxdna_umap_release(struct kref *ref)
+{
+	struct amdxdna_umap *mapp = container_of(ref, struct amdxdna_umap, refcnt);
+	struct vm_area_struct *vma = mapp->vma;
+	struct amdxdna_dev *xdna;
+
+	mmu_interval_notifier_remove(&mapp->notifier);
+	if (is_import_bo(mapp->abo) && vma->vm_file && vma->vm_file->f_mapping)
+		mapping_clear_unevictable(vma->vm_file->f_mapping);
+
+	xdna = to_xdna_dev(to_gobj(mapp->abo)->dev);
+	down_write(&xdna->notifier_lock);
+	list_del(&mapp->node);
+	up_write(&xdna->notifier_lock);
+
+	kvfree(mapp->range.hmm_pfns);
+	kfree(mapp);
+}
+
+void amdxdna_umap_put(struct amdxdna_umap *mapp)
+{
+	kref_put(&mapp->refcnt, amdxdna_umap_release);
+}
+
+static void amdxdna_hmm_unreg_work(struct work_struct *work)
+{
+	struct amdxdna_umap *mapp = container_of(work, struct amdxdna_umap,
+						 hmm_unreg_work);
+
+	amdxdna_umap_put(mapp);
+}
+
+static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo,
+				struct vm_area_struct *vma)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	unsigned long len = vma->vm_end - vma->vm_start;
+	unsigned long addr = vma->vm_start;
+	struct amdxdna_umap *mapp;
+	u32 nr_pages;
+	int ret;
+
+	if (!xdna->dev_info->ops->hmm_invalidate)
+		return 0;
+
+	mapp = kzalloc(sizeof(*mapp), GFP_KERNEL);
+	if (!mapp)
+		return -ENOMEM;
+
+	nr_pages = (PAGE_ALIGN(addr + len) - (addr & PAGE_MASK)) >> PAGE_SHIFT;
+	mapp->range.hmm_pfns = kvcalloc(nr_pages, sizeof(*mapp->range.hmm_pfns),
+					GFP_KERNEL);
+	if (!mapp->range.hmm_pfns) {
+		ret = -ENOMEM;
+		goto free_map;
+	}
+
+	ret = mmu_interval_notifier_insert_locked(&mapp->notifier,
+						  current->mm,
+						  addr,
+						  len,
+						  &amdxdna_hmm_ops);
+	if (ret) {
+		XDNA_ERR(xdna, "Insert mmu notifier failed, ret %d", ret);
+		goto free_pfns;
+	}
+
+	mapp->range.notifier = &mapp->notifier;
+	mapp->range.start = vma->vm_start;
+	mapp->range.end = vma->vm_end;
+	mapp->range.default_flags = HMM_PFN_REQ_FAULT;
+	mapp->vma = vma;
+	mapp->abo = abo;
+	kref_init(&mapp->refcnt);
+
+	if (abo->mem.userptr == AMDXDNA_INVALID_ADDR)
+		abo->mem.userptr = addr;
+	INIT_WORK(&mapp->hmm_unreg_work, amdxdna_hmm_unreg_work);
+	if (is_import_bo(abo) && vma->vm_file && vma->vm_file->f_mapping)
+		mapping_set_unevictable(vma->vm_file->f_mapping);
+
+	down_write(&xdna->notifier_lock);
+	list_add_tail(&mapp->node, &abo->mem.umap_list);
+	up_write(&xdna->notifier_lock);
+
+	return 0;
+
+free_pfns:
+	kvfree(mapp->range.hmm_pfns);
+free_map:
+	kfree(mapp);
+	return ret;
+}
+
+static void amdxdna_gem_dev_obj_free(struct drm_gem_object *gobj)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev);
+	struct amdxdna_gem_obj *abo = to_xdna_obj(gobj);
+
+	XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr);
+	if (abo->pinned)
+		amdxdna_gem_unpin(abo);
+
+	amdxdna_gem_heap_free(abo);
+	drm_gem_object_release(gobj);
+	amdxdna_gem_destroy_obj(abo);
+}
+
+static int amdxdna_insert_pages(struct amdxdna_gem_obj *abo,
+				struct vm_area_struct *vma)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	unsigned long num_pages = vma_pages(vma);
+	unsigned long offset = 0;
+	int ret;
+
+	if (!is_import_bo(abo)) {
+		ret = drm_gem_shmem_mmap(&abo->base, vma);
+		if (ret) {
+			XDNA_ERR(xdna, "Failed shmem mmap %d", ret);
+			return ret;
+		}
+
+		/* The buffer is based on memory pages. Fix the flag. */
+		vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP);
+		ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages,
+				      &num_pages);
+		if (ret) {
+			XDNA_ERR(xdna, "Failed insert pages %d", ret);
+			vma->vm_ops->close(vma);
+			return ret;
+		}
+
+		return 0;
+	}
+
+	vma->vm_private_data = NULL;
+	vma->vm_ops = NULL;
+	ret = dma_buf_mmap(abo->dma_buf, vma, 0);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to mmap dma buf %d", ret);
+		return ret;
+	}
+
+	do {
+		vm_fault_t fault_ret;
+
+		fault_ret = handle_mm_fault(vma, vma->vm_start + offset,
+					    FAULT_FLAG_WRITE, NULL);
+		if (fault_ret & VM_FAULT_ERROR) {
+			vma->vm_ops->close(vma);
+			XDNA_ERR(xdna, "Fault in page failed");
+			return -EFAULT;
+		}
+
+		offset += PAGE_SIZE;
+	} while (--num_pages);
+
+	/* Drop the reference drm_gem_mmap_obj() acquired.*/
+	drm_gem_object_put(to_gobj(abo));
+
+	return 0;
+}
+
+static int amdxdna_gem_obj_mmap(struct drm_gem_object *gobj,
+				struct vm_area_struct *vma)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev);
+	struct amdxdna_gem_obj *abo = to_xdna_obj(gobj);
+	int ret;
+
+	ret = amdxdna_hmm_register(abo, vma);
+	if (ret)
+		return ret;
+
+	ret = amdxdna_insert_pages(abo, vma);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed insert pages, ret %d", ret);
+		goto hmm_unreg;
+	}
+
+	XDNA_DBG(xdna, "BO map_offset 0x%llx type %d userptr 0x%lx size 0x%lx",
+		 drm_vma_node_offset_addr(&gobj->vma_node), abo->type,
+		 vma->vm_start, gobj->size);
+	return 0;
+
+hmm_unreg:
+	amdxdna_hmm_unregister(abo, vma);
+	return ret;
+}
+
+static int amdxdna_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
+{
+	struct drm_gem_object *gobj = dma_buf->priv;
+	struct amdxdna_gem_obj *abo = to_xdna_obj(gobj);
+	unsigned long num_pages = vma_pages(vma);
+	int ret;
+
+	vma->vm_ops = &drm_gem_shmem_vm_ops;
+	vma->vm_private_data = gobj;
+
+	drm_gem_object_get(gobj);
+	ret = drm_gem_shmem_mmap(&abo->base, vma);
+	if (ret)
+		goto put_obj;
+
+	/* The buffer is based on memory pages. Fix the flag. */
+	vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP);
+	ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages,
+			      &num_pages);
+	if (ret)
+		goto close_vma;
+
+	return 0;
+
+close_vma:
+	vma->vm_ops->close(vma);
+put_obj:
+	drm_gem_object_put(gobj);
+	return ret;
+}
+
+static const struct dma_buf_ops amdxdna_dmabuf_ops = {
+	.attach = drm_gem_map_attach,
+	.detach = drm_gem_map_detach,
+	.map_dma_buf = drm_gem_map_dma_buf,
+	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.release = drm_gem_dmabuf_release,
+	.mmap = amdxdna_gem_dmabuf_mmap,
+	.vmap = drm_gem_dmabuf_vmap,
+	.vunmap = drm_gem_dmabuf_vunmap,
+};
+
+static int amdxdna_gem_obj_vmap(struct drm_gem_object *obj, struct iosys_map *map)
+{
+	struct amdxdna_gem_obj *abo = to_xdna_obj(obj);
+
+	iosys_map_clear(map);
+
+	dma_resv_assert_held(obj->resv);
+
+	if (is_import_bo(abo))
+		dma_buf_vmap(abo->dma_buf, map);
+	else
+		drm_gem_shmem_object_vmap(obj, map);
+
+	if (!map->vaddr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void amdxdna_gem_obj_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
+{
+	struct amdxdna_gem_obj *abo = to_xdna_obj(obj);
+
+	dma_resv_assert_held(obj->resv);
+
+	if (is_import_bo(abo))
+		dma_buf_vunmap(abo->dma_buf, map);
+	else
+		drm_gem_shmem_object_vunmap(obj, map);
+}
+
+static struct dma_buf *amdxdna_gem_prime_export(struct drm_gem_object *gobj, int flags)
+{
+	struct amdxdna_gem_obj *abo = to_xdna_obj(gobj);
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+	if (abo->dma_buf) {
+		get_dma_buf(abo->dma_buf);
+		return abo->dma_buf;
+	}
+
+	exp_info.ops = &amdxdna_dmabuf_ops;
+	exp_info.size = gobj->size;
+	exp_info.flags = flags;
+	exp_info.priv = gobj;
+	exp_info.resv = gobj->resv;
+
+	return drm_gem_dmabuf_export(gobj->dev, &exp_info);
+}
+
+static void amdxdna_imported_obj_free(struct amdxdna_gem_obj *abo)
+{
+	dma_buf_unmap_attachment_unlocked(abo->attach, abo->base.sgt, DMA_BIDIRECTIONAL);
+	dma_buf_detach(abo->dma_buf, abo->attach);
+	dma_buf_put(abo->dma_buf);
+	drm_gem_object_release(to_gobj(abo));
+	kfree(abo);
+}
+
+static void amdxdna_gem_obj_free(struct drm_gem_object *gobj)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev);
+	struct amdxdna_gem_obj *abo = to_xdna_obj(gobj);
+	struct iosys_map map = IOSYS_MAP_INIT_VADDR(abo->mem.kva);
+
+	XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr);
+
+	amdxdna_hmm_unregister(abo, NULL);
+	flush_workqueue(xdna->notifier_wq);
+
+	if (abo->pinned)
+		amdxdna_gem_unpin(abo);
+
+	if (abo->type == AMDXDNA_BO_DEV_HEAP)
+		drm_mm_takedown(&abo->mm);
+
+	drm_gem_vunmap(gobj, &map);
+	mutex_destroy(&abo->lock);
+
+	if (is_import_bo(abo)) {
+		amdxdna_imported_obj_free(abo);
+		return;
+	}
+
+	drm_gem_shmem_free(&abo->base);
+}
+
+static const struct drm_gem_object_funcs amdxdna_gem_dev_obj_funcs = {
+	.free = amdxdna_gem_dev_obj_free,
+};
+
+static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = {
+	.free = amdxdna_gem_obj_free,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = amdxdna_gem_obj_vmap,
+	.vunmap = amdxdna_gem_obj_vunmap,
+	.mmap = amdxdna_gem_obj_mmap,
+	.vm_ops = &drm_gem_shmem_vm_ops,
+	.export = amdxdna_gem_prime_export,
+};
+
+static struct amdxdna_gem_obj *
+amdxdna_gem_create_obj(struct drm_device *dev, size_t size)
+{
+	struct amdxdna_gem_obj *abo;
+
+	abo = kzalloc(sizeof(*abo), GFP_KERNEL);
+	if (!abo)
+		return ERR_PTR(-ENOMEM);
+
+	abo->pinned = false;
+	abo->assigned_hwctx = AMDXDNA_INVALID_CTX_HANDLE;
+	mutex_init(&abo->lock);
+
+	abo->mem.userptr = AMDXDNA_INVALID_ADDR;
+	abo->mem.dev_addr = AMDXDNA_INVALID_ADDR;
+	abo->mem.size = size;
+	INIT_LIST_HEAD(&abo->mem.umap_list);
+
+	return abo;
+}
+
+/* For drm_driver->gem_create_object callback */
+struct drm_gem_object *
+amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size)
+{
+	struct amdxdna_gem_obj *abo;
+
+	abo = amdxdna_gem_create_obj(dev, size);
+	if (IS_ERR(abo))
+		return ERR_CAST(abo);
+
+	to_gobj(abo)->funcs = &amdxdna_gem_shmem_funcs;
+
+	return to_gobj(abo);
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_gem_create_shmem_object(struct drm_device *dev, size_t size)
+{
+	struct drm_gem_shmem_object *shmem = drm_gem_shmem_create(dev, size);
+
+	if (IS_ERR(shmem))
+		return ERR_CAST(shmem);
+
+	shmem->map_wc = false;
+	return to_xdna_obj(&shmem->base);
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_gem_create_ubuf_object(struct drm_device *dev, struct amdxdna_drm_create_bo *args)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	enum amdxdna_ubuf_flag flags = 0;
+	struct amdxdna_drm_va_tbl va_tbl;
+	struct drm_gem_object *gobj;
+	struct dma_buf *dma_buf;
+
+	if (copy_from_user(&va_tbl, u64_to_user_ptr(args->vaddr), sizeof(va_tbl))) {
+		XDNA_DBG(xdna, "Access va table failed");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (va_tbl.num_entries) {
+		if (args->type == AMDXDNA_BO_CMD)
+			flags |= AMDXDNA_UBUF_FLAG_MAP_DMA;
+
+		dma_buf = amdxdna_get_ubuf(dev, flags, va_tbl.num_entries,
+					   u64_to_user_ptr(args->vaddr + sizeof(va_tbl)));
+	} else {
+		dma_buf = dma_buf_get(va_tbl.dmabuf_fd);
+	}
+
+	if (IS_ERR(dma_buf))
+		return ERR_CAST(dma_buf);
+
+	gobj = amdxdna_gem_prime_import(dev, dma_buf);
+	if (IS_ERR(gobj)) {
+		dma_buf_put(dma_buf);
+		return ERR_CAST(gobj);
+	}
+
+	dma_buf_put(dma_buf);
+
+	return to_xdna_obj(gobj);
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_gem_create_object(struct drm_device *dev,
+			  struct amdxdna_drm_create_bo *args)
+{
+	size_t aligned_sz = PAGE_ALIGN(args->size);
+
+	if (args->vaddr)
+		return amdxdna_gem_create_ubuf_object(dev, args);
+
+	return amdxdna_gem_create_shmem_object(dev, aligned_sz);
+}
+
+struct drm_gem_object *
+amdxdna_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf)
+{
+	struct dma_buf_attachment *attach;
+	struct amdxdna_gem_obj *abo;
+	struct drm_gem_object *gobj;
+	struct sg_table *sgt;
+	int ret;
+
+	get_dma_buf(dma_buf);
+
+	attach = dma_buf_attach(dma_buf, dev->dev);
+	if (IS_ERR(attach)) {
+		ret = PTR_ERR(attach);
+		goto put_buf;
+	}
+
+	sgt = dma_buf_map_attachment_unlocked(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = PTR_ERR(sgt);
+		goto fail_detach;
+	}
+
+	gobj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
+	if (IS_ERR(gobj)) {
+		ret = PTR_ERR(gobj);
+		goto fail_unmap;
+	}
+
+	abo = to_xdna_obj(gobj);
+	abo->attach = attach;
+	abo->dma_buf = dma_buf;
+
+	return gobj;
+
+fail_unmap:
+	dma_buf_unmap_attachment_unlocked(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+put_buf:
+	dma_buf_put(dma_buf);
+
+	return ERR_PTR(ret);
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_drm_alloc_shmem(struct drm_device *dev,
+			struct amdxdna_drm_create_bo *args,
+			struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_gem_obj *abo;
+
+	abo = amdxdna_gem_create_object(dev, args);
+	if (IS_ERR(abo))
+		return ERR_CAST(abo);
+
+	abo->client = client;
+	abo->type = AMDXDNA_BO_SHMEM;
+
+	return abo;
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_drm_create_dev_heap(struct drm_device *dev,
+			    struct amdxdna_drm_create_bo *args,
+			    struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL);
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_gem_obj *abo;
+	int ret;
+
+	if (args->size > xdna->dev_info->dev_mem_size) {
+		XDNA_DBG(xdna, "Invalid dev heap size 0x%llx, limit 0x%lx",
+			 args->size, xdna->dev_info->dev_mem_size);
+		return ERR_PTR(-EINVAL);
+	}
+
+	mutex_lock(&client->mm_lock);
+	if (client->dev_heap) {
+		XDNA_DBG(client->xdna, "dev heap is already created");
+		ret = -EBUSY;
+		goto mm_unlock;
+	}
+
+	abo = amdxdna_gem_create_object(dev, args);
+	if (IS_ERR(abo)) {
+		ret = PTR_ERR(abo);
+		goto mm_unlock;
+	}
+
+	abo->type = AMDXDNA_BO_DEV_HEAP;
+	abo->client = client;
+	abo->mem.dev_addr = client->xdna->dev_info->dev_mem_base;
+	drm_mm_init(&abo->mm, abo->mem.dev_addr, abo->mem.size);
+
+	ret = drm_gem_vmap(to_gobj(abo), &map);
+	if (ret) {
+		XDNA_ERR(xdna, "Vmap heap bo failed, ret %d", ret);
+		goto release_obj;
+	}
+	abo->mem.kva = map.vaddr;
+
+	client->dev_heap = abo;
+	drm_gem_object_get(to_gobj(abo));
+	mutex_unlock(&client->mm_lock);
+
+	return abo;
+
+release_obj:
+	drm_gem_object_put(to_gobj(abo));
+mm_unlock:
+	mutex_unlock(&client->mm_lock);
+	return ERR_PTR(ret);
+}
+
+struct amdxdna_gem_obj *
+amdxdna_drm_alloc_dev_bo(struct drm_device *dev,
+			 struct amdxdna_drm_create_bo *args,
+			 struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	size_t aligned_sz = PAGE_ALIGN(args->size);
+	struct amdxdna_gem_obj *abo;
+	int ret;
+
+	abo = amdxdna_gem_create_obj(&xdna->ddev, aligned_sz);
+	if (IS_ERR(abo))
+		return abo;
+
+	to_gobj(abo)->funcs = &amdxdna_gem_dev_obj_funcs;
+	abo->type = AMDXDNA_BO_DEV;
+	abo->client = client;
+
+	ret = amdxdna_gem_heap_alloc(abo);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret);
+		amdxdna_gem_destroy_obj(abo);
+		return ERR_PTR(ret);
+	}
+
+	drm_gem_private_object_init(&xdna->ddev, to_gobj(abo), aligned_sz);
+
+	return abo;
+}
+
+static struct amdxdna_gem_obj *
+amdxdna_drm_create_cmd_bo(struct drm_device *dev,
+			  struct amdxdna_drm_create_bo *args,
+			  struct drm_file *filp)
+{
+	struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL);
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_gem_obj *abo;
+	int ret;
+
+	if (args->size > XDNA_MAX_CMD_BO_SIZE) {
+		XDNA_ERR(xdna, "Command bo size 0x%llx too large", args->size);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (args->size < sizeof(struct amdxdna_cmd)) {
+		XDNA_DBG(xdna, "Command BO size 0x%llx too small", args->size);
+		return ERR_PTR(-EINVAL);
+	}
+
+	abo = amdxdna_gem_create_object(dev, args);
+	if (IS_ERR(abo))
+		return ERR_CAST(abo);
+
+	abo->type = AMDXDNA_BO_CMD;
+	abo->client = filp->driver_priv;
+
+	ret = drm_gem_vmap(to_gobj(abo), &map);
+	if (ret) {
+		XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret);
+		goto release_obj;
+	}
+	abo->mem.kva = map.vaddr;
+
+	return abo;
+
+release_obj:
+	drm_gem_object_put(to_gobj(abo));
+	return ERR_PTR(ret);
+}
+
+int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_create_bo *args = data;
+	struct amdxdna_gem_obj *abo;
+	int ret;
+
+	if (args->flags)
+		return -EINVAL;
+
+	XDNA_DBG(xdna, "BO arg type %d vaddr 0x%llx size 0x%llx flags 0x%llx",
+		 args->type, args->vaddr, args->size, args->flags);
+	switch (args->type) {
+	case AMDXDNA_BO_SHMEM:
+		abo = amdxdna_drm_alloc_shmem(dev, args, filp);
+		break;
+	case AMDXDNA_BO_DEV_HEAP:
+		abo = amdxdna_drm_create_dev_heap(dev, args, filp);
+		break;
+	case AMDXDNA_BO_DEV:
+		abo = amdxdna_drm_alloc_dev_bo(dev, args, filp);
+		break;
+	case AMDXDNA_BO_CMD:
+		abo = amdxdna_drm_create_cmd_bo(dev, args, filp);
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (IS_ERR(abo))
+		return PTR_ERR(abo);
+
+	/* ready to publish object to userspace */
+	ret = drm_gem_handle_create(filp, to_gobj(abo), &args->handle);
+	if (ret) {
+		XDNA_ERR(xdna, "Create handle failed");
+		goto put_obj;
+	}
+
+	XDNA_DBG(xdna, "BO hdl %d type %d userptr 0x%llx xdna_addr 0x%llx size 0x%lx",
+		 args->handle, args->type, abo->mem.userptr,
+		 abo->mem.dev_addr, abo->mem.size);
+put_obj:
+	/* Dereference object reference. Handle holds it now. */
+	drm_gem_object_put(to_gobj(abo));
+	return ret;
+}
+
+int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	int ret;
+
+	if (abo->type == AMDXDNA_BO_DEV)
+		abo = abo->client->dev_heap;
+
+	if (is_import_bo(abo))
+		return 0;
+
+	ret = drm_gem_shmem_pin(&abo->base);
+
+	XDNA_DBG(xdna, "BO type %d ret %d", abo->type, ret);
+	return ret;
+}
+
+int amdxdna_gem_pin(struct amdxdna_gem_obj *abo)
+{
+	int ret;
+
+	mutex_lock(&abo->lock);
+	ret = amdxdna_gem_pin_nolock(abo);
+	mutex_unlock(&abo->lock);
+
+	return ret;
+}
+
+void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo)
+{
+	if (abo->type == AMDXDNA_BO_DEV)
+		abo = abo->client->dev_heap;
+
+	if (is_import_bo(abo))
+		return;
+
+	mutex_lock(&abo->lock);
+	drm_gem_shmem_unpin(&abo->base);
+	mutex_unlock(&abo->lock);
+}
+
+struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client,
+					    u32 bo_hdl, u8 bo_type)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_gem_obj *abo;
+	struct drm_gem_object *gobj;
+
+	gobj = drm_gem_object_lookup(client->filp, bo_hdl);
+	if (!gobj) {
+		XDNA_DBG(xdna, "Can not find bo %d", bo_hdl);
+		return NULL;
+	}
+
+	abo = to_xdna_obj(gobj);
+	if (bo_type == AMDXDNA_BO_INVALID || abo->type == bo_type)
+		return abo;
+
+	drm_gem_object_put(gobj);
+	return NULL;
+}
+
+int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_drm_get_bo_info *args = data;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_gem_obj *abo;
+	struct drm_gem_object *gobj;
+	int ret = 0;
+
+	if (args->ext || args->ext_flags || args->pad)
+		return -EINVAL;
+
+	gobj = drm_gem_object_lookup(filp, args->handle);
+	if (!gobj) {
+		XDNA_DBG(xdna, "Lookup GEM object %d failed", args->handle);
+		return -ENOENT;
+	}
+
+	abo = to_xdna_obj(gobj);
+	args->vaddr = abo->mem.userptr;
+	args->xdna_addr = abo->mem.dev_addr;
+
+	if (abo->type != AMDXDNA_BO_DEV)
+		args->map_offset = drm_vma_node_offset_addr(&gobj->vma_node);
+	else
+		args->map_offset = AMDXDNA_INVALID_ADDR;
+
+	XDNA_DBG(xdna, "BO hdl %d map_offset 0x%llx vaddr 0x%llx xdna_addr 0x%llx",
+		 args->handle, args->map_offset, args->vaddr, args->xdna_addr);
+
+	drm_gem_object_put(gobj);
+	return ret;
+}
+
+/*
+ * The sync bo ioctl is to make sure the CPU cache is in sync with memory.
+ * This is required because NPU is not cache coherent device. CPU cache
+ * flushing/invalidation is expensive so it is best to handle this outside
+ * of the command submission path. This ioctl allows explicit cache
+ * flushing/invalidation outside of the critical path.
+ */
+int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev,
+			      void *data, struct drm_file *filp)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_sync_bo *args = data;
+	struct amdxdna_gem_obj *abo;
+	struct drm_gem_object *gobj;
+	int ret;
+
+	gobj = drm_gem_object_lookup(filp, args->handle);
+	if (!gobj) {
+		XDNA_ERR(xdna, "Lookup GEM object failed");
+		return -ENOENT;
+	}
+	abo = to_xdna_obj(gobj);
+
+	ret = amdxdna_gem_pin(abo);
+	if (ret) {
+		XDNA_ERR(xdna, "Pin BO %d failed, ret %d", args->handle, ret);
+		goto put_obj;
+	}
+
+	if (is_import_bo(abo))
+		drm_clflush_sg(abo->base.sgt);
+	else if (abo->mem.kva)
+		drm_clflush_virt_range(abo->mem.kva + args->offset, args->size);
+	else if (abo->base.pages)
+		drm_clflush_pages(abo->base.pages, gobj->size >> PAGE_SHIFT);
+	else
+		drm_WARN(&xdna->ddev, 1, "Can not get flush memory");
+
+	amdxdna_gem_unpin(abo);
+
+	XDNA_DBG(xdna, "Sync bo %d offset 0x%llx, size 0x%llx\n",
+		 args->handle, args->offset, args->size);
+
+put_obj:
+	drm_gem_object_put(gobj);
+	return ret;
+}
diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h
new file mode 100644
index 000000000000..ae29db94a9d3
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_gem.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AMDXDNA_GEM_H_
+#define _AMDXDNA_GEM_H_
+
+#include <linux/hmm.h>
+
+struct amdxdna_umap {
+	struct vm_area_struct		*vma;
+	struct mmu_interval_notifier	notifier;
+	struct hmm_range		range;
+	struct work_struct		hmm_unreg_work;
+	struct amdxdna_gem_obj		*abo;
+	struct list_head		node;
+	struct kref			refcnt;
+	bool				invalid;
+	bool				unmapped;
+};
+
+struct amdxdna_mem {
+	u64				userptr;
+	void				*kva;
+	u64				dev_addr;
+	size_t				size;
+	struct page			**pages;
+	u32				nr_pages;
+	struct list_head		umap_list;
+	bool				map_invalid;
+};
+
+struct amdxdna_gem_obj {
+	struct drm_gem_shmem_object	base;
+	struct amdxdna_client		*client;
+	u8				type;
+	bool				pinned;
+	struct mutex			lock; /* Protects: pinned */
+	struct amdxdna_mem		mem;
+
+	/* Below members is uninitialized when needed */
+	struct drm_mm			mm; /* For AMDXDNA_BO_DEV_HEAP */
+	struct drm_mm_node		mm_node; /* For AMDXDNA_BO_DEV */
+	u32				assigned_hwctx;
+	struct dma_buf			*dma_buf;
+	struct dma_buf_attachment	*attach;
+};
+
+#define to_gobj(obj)    (&(obj)->base.base)
+#define is_import_bo(obj) ((obj)->attach)
+
+static inline struct amdxdna_gem_obj *to_xdna_obj(struct drm_gem_object *gobj)
+{
+	return container_of(gobj, struct amdxdna_gem_obj, base.base);
+}
+
+struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client,
+					    u32 bo_hdl, u8 bo_type);
+static inline void amdxdna_gem_put_obj(struct amdxdna_gem_obj *abo)
+{
+	drm_gem_object_put(to_gobj(abo));
+}
+
+void amdxdna_umap_put(struct amdxdna_umap *mapp);
+
+struct drm_gem_object *
+amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size);
+struct drm_gem_object *
+amdxdna_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf);
+struct amdxdna_gem_obj *
+amdxdna_drm_alloc_dev_bo(struct drm_device *dev,
+			 struct amdxdna_drm_create_bo *args,
+			 struct drm_file *filp);
+
+int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo);
+int amdxdna_gem_pin(struct amdxdna_gem_obj *abo);
+void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo);
+
+int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+
+#endif /* _AMDXDNA_GEM_H_ */
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
new file mode 100644
index 000000000000..da1ac89bb78f
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/drm_device.h>
+#include <drm/drm_managed.h>
+#include <linux/bitfield.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/slab.h>
+#include <linux/xarray.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/amdxdna.h>
+
+#include "amdxdna_mailbox.h"
+
+#define MB_ERR(chann, fmt, args...) \
+({ \
+	typeof(chann) _chann = chann; \
+	dev_err((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \
+		(_chann)->msix_irq, ##args); \
+})
+#define MB_DBG(chann, fmt, args...) \
+({ \
+	typeof(chann) _chann = chann; \
+	dev_dbg((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \
+		(_chann)->msix_irq, ##args); \
+})
+#define MB_WARN_ONCE(chann, fmt, args...) \
+({ \
+	typeof(chann) _chann = chann; \
+	dev_warn_once((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \
+		      (_chann)->msix_irq, ##args); \
+})
+
+#define MAGIC_VAL			0x1D000000U
+#define MAGIC_VAL_MASK			0xFF000000
+#define MAX_MSG_ID_ENTRIES		256
+#define MSG_RX_TIMER			200 /* milliseconds */
+#define MAILBOX_NAME			"xdna_mailbox"
+
+enum channel_res_type {
+	CHAN_RES_X2I,
+	CHAN_RES_I2X,
+	CHAN_RES_NUM
+};
+
+struct mailbox {
+	struct device		*dev;
+	struct xdna_mailbox_res	res;
+};
+
+struct mailbox_channel {
+	struct mailbox			*mb;
+	struct xdna_mailbox_chann_res	res[CHAN_RES_NUM];
+	int				msix_irq;
+	u32				iohub_int_addr;
+	struct xarray			chan_xa;
+	u32				next_msgid;
+	u32				x2i_tail;
+
+	/* Received msg related fields */
+	struct workqueue_struct		*work_q;
+	struct work_struct		rx_work;
+	u32				i2x_head;
+	bool				bad_state;
+};
+
+#define MSG_BODY_SZ		GENMASK(10, 0)
+#define MSG_PROTO_VER		GENMASK(23, 16)
+struct xdna_msg_header {
+	__u32 total_size;
+	__u32 sz_ver;
+	__u32 id;
+	__u32 opcode;
+} __packed;
+
+static_assert(sizeof(struct xdna_msg_header) == 16);
+
+struct mailbox_pkg {
+	struct xdna_msg_header	header;
+	__u32			payload[];
+};
+
+/* The protocol version. */
+#define MSG_PROTOCOL_VERSION	0x1
+/* The tombstone value. */
+#define TOMBSTONE		0xDEADFACE
+
+struct mailbox_msg {
+	void			*handle;
+	int			(*notify_cb)(void *handle, void __iomem *data, size_t size);
+	size_t			pkg_size; /* package size in bytes */
+	struct mailbox_pkg	pkg;
+};
+
+static void mailbox_reg_write(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 data)
+{
+	struct xdna_mailbox_res *mb_res = &mb_chann->mb->res;
+	void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg;
+
+	writel(data, ringbuf_addr);
+}
+
+static u32 mailbox_reg_read(struct mailbox_channel *mb_chann, u32 mbox_reg)
+{
+	struct xdna_mailbox_res *mb_res = &mb_chann->mb->res;
+	void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg;
+
+	return readl(ringbuf_addr);
+}
+
+static int mailbox_reg_read_non_zero(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 *val)
+{
+	struct xdna_mailbox_res *mb_res = &mb_chann->mb->res;
+	void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg;
+	int ret, value;
+
+	/* Poll till value is not zero */
+	ret = readx_poll_timeout(readl, ringbuf_addr, value,
+				 value, 1 /* us */, 100);
+	if (ret < 0)
+		return ret;
+
+	*val = value;
+	return 0;
+}
+
+static inline void
+mailbox_set_headptr(struct mailbox_channel *mb_chann, u32 headptr_val)
+{
+	mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_head_ptr_reg, headptr_val);
+	mb_chann->i2x_head = headptr_val;
+}
+
+static inline void
+mailbox_set_tailptr(struct mailbox_channel *mb_chann, u32 tailptr_val)
+{
+	mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_X2I].mb_tail_ptr_reg, tailptr_val);
+	mb_chann->x2i_tail = tailptr_val;
+}
+
+static inline u32
+mailbox_get_headptr(struct mailbox_channel *mb_chann, enum channel_res_type type)
+{
+	return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_head_ptr_reg);
+}
+
+static inline u32
+mailbox_get_tailptr(struct mailbox_channel *mb_chann, enum channel_res_type type)
+{
+	return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_tail_ptr_reg);
+}
+
+static inline u32
+mailbox_get_ringbuf_size(struct mailbox_channel *mb_chann, enum channel_res_type type)
+{
+	return mb_chann->res[type].rb_size;
+}
+
+static inline int mailbox_validate_msgid(int msg_id)
+{
+	return (msg_id & MAGIC_VAL_MASK) == MAGIC_VAL;
+}
+
+static int mailbox_acquire_msgid(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg)
+{
+	u32 msg_id;
+	int ret;
+
+	ret = xa_alloc_cyclic_irq(&mb_chann->chan_xa, &msg_id, mb_msg,
+				  XA_LIMIT(0, MAX_MSG_ID_ENTRIES - 1),
+				  &mb_chann->next_msgid, GFP_NOWAIT);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Add MAGIC_VAL to the higher bits.
+	 */
+	msg_id |= MAGIC_VAL;
+	return msg_id;
+}
+
+static void mailbox_release_msgid(struct mailbox_channel *mb_chann, int msg_id)
+{
+	msg_id &= ~MAGIC_VAL_MASK;
+	xa_erase_irq(&mb_chann->chan_xa, msg_id);
+}
+
+static void mailbox_release_msg(struct mailbox_channel *mb_chann,
+				struct mailbox_msg *mb_msg)
+{
+	MB_DBG(mb_chann, "msg_id 0x%x msg opcode 0x%x",
+	       mb_msg->pkg.header.id, mb_msg->pkg.header.opcode);
+	mb_msg->notify_cb(mb_msg->handle, NULL, 0);
+	kfree(mb_msg);
+}
+
+static int
+mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg)
+{
+	void __iomem *write_addr;
+	u32 ringbuf_size;
+	u32 head, tail;
+	u32 start_addr;
+	u32 tmp_tail;
+
+	head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I);
+	tail = mb_chann->x2i_tail;
+	ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I);
+	start_addr = mb_chann->res[CHAN_RES_X2I].rb_start_addr;
+	tmp_tail = tail + mb_msg->pkg_size;
+
+	if (tail < head && tmp_tail >= head)
+		goto no_space;
+
+	if (tail >= head && (tmp_tail > ringbuf_size - sizeof(u32) &&
+			     mb_msg->pkg_size >= head))
+		goto no_space;
+
+	if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) {
+		write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail;
+		writel(TOMBSTONE, write_addr);
+
+		/* tombstone is set. Write from the start of the ringbuf */
+		tail = 0;
+	}
+
+	write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail;
+	memcpy_toio(write_addr, &mb_msg->pkg, mb_msg->pkg_size);
+	mailbox_set_tailptr(mb_chann, tail + mb_msg->pkg_size);
+
+	trace_mbox_set_tail(MAILBOX_NAME, mb_chann->msix_irq,
+			    mb_msg->pkg.header.opcode,
+			    mb_msg->pkg.header.id);
+
+	return 0;
+
+no_space:
+	return -ENOSPC;
+}
+
+static int
+mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *header,
+		 void __iomem *data)
+{
+	struct mailbox_msg *mb_msg;
+	int msg_id;
+	int ret;
+
+	msg_id = header->id;
+	if (!mailbox_validate_msgid(msg_id)) {
+		MB_ERR(mb_chann, "Bad message ID 0x%x", msg_id);
+		return -EINVAL;
+	}
+
+	msg_id &= ~MAGIC_VAL_MASK;
+	mb_msg = xa_erase_irq(&mb_chann->chan_xa, msg_id);
+	if (!mb_msg) {
+		MB_ERR(mb_chann, "Cannot find msg 0x%x", msg_id);
+		return -EINVAL;
+	}
+
+	MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x",
+	       header->opcode, header->total_size, header->id);
+	ret = mb_msg->notify_cb(mb_msg->handle, data, header->total_size);
+	if (unlikely(ret))
+		MB_ERR(mb_chann, "Message callback ret %d", ret);
+
+	kfree(mb_msg);
+	return ret;
+}
+
+static int mailbox_get_msg(struct mailbox_channel *mb_chann)
+{
+	struct xdna_msg_header header;
+	void __iomem *read_addr;
+	u32 msg_size, rest;
+	u32 ringbuf_size;
+	u32 head, tail;
+	u32 start_addr;
+	int ret;
+
+	if (mailbox_reg_read_non_zero(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_tail_ptr_reg, &tail))
+		return -EINVAL;
+	head = mb_chann->i2x_head;
+	ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_I2X);
+	start_addr = mb_chann->res[CHAN_RES_I2X].rb_start_addr;
+
+	if (unlikely(tail > ringbuf_size || !IS_ALIGNED(tail, 4))) {
+		MB_WARN_ONCE(mb_chann, "Invalid tail 0x%x", tail);
+		return -EINVAL;
+	}
+
+	/* ringbuf empty */
+	if (head == tail)
+		return -ENOENT;
+
+	if (head == ringbuf_size)
+		head = 0;
+
+	/* Peek size of the message or TOMBSTONE */
+	read_addr = mb_chann->mb->res.ringbuf_base + start_addr + head;
+	header.total_size = readl(read_addr);
+	/* size is TOMBSTONE, set next read from 0 */
+	if (header.total_size == TOMBSTONE) {
+		if (head < tail) {
+			MB_WARN_ONCE(mb_chann, "Tombstone, head 0x%x tail 0x%x",
+				     head, tail);
+			return -EINVAL;
+		}
+		mailbox_set_headptr(mb_chann, 0);
+		return 0;
+	}
+
+	if (unlikely(!header.total_size || !IS_ALIGNED(header.total_size, 4))) {
+		MB_WARN_ONCE(mb_chann, "Invalid total size 0x%x", header.total_size);
+		return -EINVAL;
+	}
+	msg_size = sizeof(header) + header.total_size;
+
+	if (msg_size > ringbuf_size - head || msg_size > tail - head) {
+		MB_WARN_ONCE(mb_chann, "Invalid message size %d, tail %d, head %d",
+			     msg_size, tail, head);
+		return -EINVAL;
+	}
+
+	rest = sizeof(header) - sizeof(u32);
+	read_addr += sizeof(u32);
+	memcpy_fromio((u32 *)&header + 1, read_addr, rest);
+	read_addr += rest;
+
+	ret = mailbox_get_resp(mb_chann, &header, read_addr);
+
+	mailbox_set_headptr(mb_chann, head + msg_size);
+	/* After update head, it can equal to ringbuf_size. This is expected. */
+	trace_mbox_set_head(MAILBOX_NAME, mb_chann->msix_irq,
+			    header.opcode, header.id);
+
+	return ret;
+}
+
+static irqreturn_t mailbox_irq_handler(int irq, void *p)
+{
+	struct mailbox_channel *mb_chann = p;
+
+	trace_mbox_irq_handle(MAILBOX_NAME, irq);
+	/* Schedule a rx_work to call the callback functions */
+	queue_work(mb_chann->work_q, &mb_chann->rx_work);
+
+	return IRQ_HANDLED;
+}
+
+static void mailbox_rx_worker(struct work_struct *rx_work)
+{
+	struct mailbox_channel *mb_chann;
+	int ret;
+
+	mb_chann = container_of(rx_work, struct mailbox_channel, rx_work);
+
+	if (READ_ONCE(mb_chann->bad_state)) {
+		MB_ERR(mb_chann, "Channel in bad state, work aborted");
+		return;
+	}
+
+again:
+	mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0);
+
+	while (1) {
+		/*
+		 * If return is 0, keep consuming next message, until there is
+		 * no messages or an error happened.
+		 */
+		ret = mailbox_get_msg(mb_chann);
+		if (ret == -ENOENT)
+			break;
+
+		/* Other error means device doesn't look good, disable irq. */
+		if (unlikely(ret)) {
+			MB_ERR(mb_chann, "Unexpected ret %d, disable irq", ret);
+			WRITE_ONCE(mb_chann->bad_state, true);
+			return;
+		}
+	}
+
+	/*
+	 * The hardware will not generate interrupt if firmware creates a new
+	 * response right after driver clears interrupt register. Check
+	 * the interrupt register to make sure there is not any new response
+	 * before exiting.
+	 */
+	if (mailbox_reg_read(mb_chann, mb_chann->iohub_int_addr))
+		goto again;
+}
+
+int xdna_mailbox_send_msg(struct mailbox_channel *mb_chann,
+			  const struct xdna_mailbox_msg *msg, u64 tx_timeout)
+{
+	struct xdna_msg_header *header;
+	struct mailbox_msg *mb_msg;
+	size_t pkg_size;
+	int ret;
+
+	pkg_size = sizeof(*header) + msg->send_size;
+	if (pkg_size > mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I)) {
+		MB_ERR(mb_chann, "Message size larger than ringbuf size");
+		return -EINVAL;
+	}
+
+	if (unlikely(!IS_ALIGNED(msg->send_size, 4))) {
+		MB_ERR(mb_chann, "Message must be 4 bytes align");
+		return -EINVAL;
+	}
+
+	/* The fist word in payload can NOT be TOMBSTONE */
+	if (unlikely(((u32 *)msg->send_data)[0] == TOMBSTONE)) {
+		MB_ERR(mb_chann, "Tomb stone in data");
+		return -EINVAL;
+	}
+
+	if (READ_ONCE(mb_chann->bad_state)) {
+		MB_ERR(mb_chann, "Channel in bad state");
+		return -EPIPE;
+	}
+
+	mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL);
+	if (!mb_msg)
+		return -ENOMEM;
+
+	mb_msg->handle = msg->handle;
+	mb_msg->notify_cb = msg->notify_cb;
+	mb_msg->pkg_size = pkg_size;
+
+	header = &mb_msg->pkg.header;
+	/*
+	 * Hardware use total_size and size to split huge message.
+	 * We do not support it here. Thus the values are the same.
+	 */
+	header->total_size = msg->send_size;
+	header->sz_ver = FIELD_PREP(MSG_BODY_SZ, msg->send_size) |
+			FIELD_PREP(MSG_PROTO_VER, MSG_PROTOCOL_VERSION);
+	header->opcode = msg->opcode;
+	memcpy(mb_msg->pkg.payload, msg->send_data, msg->send_size);
+
+	ret = mailbox_acquire_msgid(mb_chann, mb_msg);
+	if (unlikely(ret < 0)) {
+		MB_ERR(mb_chann, "mailbox_acquire_msgid failed");
+		goto msg_id_failed;
+	}
+	header->id = ret;
+
+	MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x",
+	       header->opcode, header->total_size, header->id);
+
+	ret = mailbox_send_msg(mb_chann, mb_msg);
+	if (ret) {
+		MB_DBG(mb_chann, "Error in mailbox send msg, ret %d", ret);
+		goto release_id;
+	}
+
+	return 0;
+
+release_id:
+	mailbox_release_msgid(mb_chann, header->id);
+msg_id_failed:
+	kfree(mb_msg);
+	return ret;
+}
+
+struct mailbox_channel *
+xdna_mailbox_create_channel(struct mailbox *mb,
+			    const struct xdna_mailbox_chann_res *x2i,
+			    const struct xdna_mailbox_chann_res *i2x,
+			    u32 iohub_int_addr,
+			    int mb_irq)
+{
+	struct mailbox_channel *mb_chann;
+	int ret;
+
+	if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) {
+		pr_err("Ring buf size must be power of 2");
+		return NULL;
+	}
+
+	mb_chann = kzalloc(sizeof(*mb_chann), GFP_KERNEL);
+	if (!mb_chann)
+		return NULL;
+
+	mb_chann->mb = mb;
+	mb_chann->msix_irq = mb_irq;
+	mb_chann->iohub_int_addr = iohub_int_addr;
+	memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i));
+	memcpy(&mb_chann->res[CHAN_RES_I2X], i2x, sizeof(*i2x));
+
+	xa_init_flags(&mb_chann->chan_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+	mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I);
+	mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X);
+
+	INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker);
+	mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME);
+	if (!mb_chann->work_q) {
+		MB_ERR(mb_chann, "Create workqueue failed");
+		goto free_and_out;
+	}
+
+	/* Everything look good. Time to enable irq handler */
+	ret = request_irq(mb_irq, mailbox_irq_handler, 0, MAILBOX_NAME, mb_chann);
+	if (ret) {
+		MB_ERR(mb_chann, "Failed to request irq %d ret %d", mb_irq, ret);
+		goto destroy_wq;
+	}
+
+	mb_chann->bad_state = false;
+
+	MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq);
+	return mb_chann;
+
+destroy_wq:
+	destroy_workqueue(mb_chann->work_q);
+free_and_out:
+	kfree(mb_chann);
+	return NULL;
+}
+
+int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann)
+{
+	struct mailbox_msg *mb_msg;
+	unsigned long msg_id;
+
+	MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
+	free_irq(mb_chann->msix_irq, mb_chann);
+	destroy_workqueue(mb_chann->work_q);
+	/* We can clean up and release resources */
+
+	xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg)
+		mailbox_release_msg(mb_chann, mb_msg);
+
+	xa_destroy(&mb_chann->chan_xa);
+
+	MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq);
+	kfree(mb_chann);
+	return 0;
+}
+
+void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann)
+{
+	/* Disable an irq and wait. This might sleep. */
+	disable_irq(mb_chann->msix_irq);
+
+	/* Cancel RX work and wait for it to finish */
+	cancel_work_sync(&mb_chann->rx_work);
+	MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
+}
+
+struct mailbox *xdnam_mailbox_create(struct drm_device *ddev,
+				     const struct xdna_mailbox_res *res)
+{
+	struct mailbox *mb;
+
+	mb = drmm_kzalloc(ddev, sizeof(*mb), GFP_KERNEL);
+	if (!mb)
+		return NULL;
+	mb->dev = ddev->dev;
+
+	/* mailbox and ring buf base and size information */
+	memcpy(&mb->res, res, sizeof(*res));
+
+	return mb;
+}
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h
new file mode 100644
index 000000000000..ea367f2fb738
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AIE2_MAILBOX_H_
+#define _AIE2_MAILBOX_H_
+
+struct mailbox;
+struct mailbox_channel;
+
+/*
+ * xdna_mailbox_msg - message struct
+ *
+ * @opcode:	opcode for firmware
+ * @handle:	handle used for the notify callback
+ * @notify_cb:  callback function to notify the sender when there is response
+ * @send_data:	pointing to sending data
+ * @send_size:	size of the sending data
+ *
+ * The mailbox will split the sending data in to multiple firmware message if
+ * the size of the data is too big. This is transparent to the sender. The
+ * sender will receive one notification.
+ */
+struct xdna_mailbox_msg {
+	u32		opcode;
+	void		*handle;
+	int		(*notify_cb)(void *handle, void __iomem *data, size_t size);
+	u8		*send_data;
+	size_t		send_size;
+};
+
+/*
+ * xdna_mailbox_res - mailbox hardware resource
+ *
+ * @ringbuf_base:	ring buffer base address
+ * @ringbuf_size:	ring buffer size
+ * @mbox_base:		mailbox base address
+ * @mbox_size:		mailbox size
+ */
+struct xdna_mailbox_res {
+	void __iomem	*ringbuf_base;
+	size_t		ringbuf_size;
+	void __iomem	*mbox_base;
+	size_t		mbox_size;
+	const char	*name;
+};
+
+/*
+ * xdna_mailbox_chann_res - resources
+ *
+ * @rb_start_addr:	ring buffer start address
+ * @rb_size:		ring buffer size
+ * @mb_head_ptr_reg:	mailbox head pointer register
+ * @mb_tail_ptr_reg:	mailbox tail pointer register
+ */
+struct xdna_mailbox_chann_res {
+	u32 rb_start_addr;
+	u32 rb_size;
+	u32 mb_head_ptr_reg;
+	u32 mb_tail_ptr_reg;
+};
+
+/*
+ * xdna_mailbox_create() -- create mailbox subsystem and initialize
+ *
+ * @ddev: device pointer
+ * @res: SRAM and mailbox resources
+ *
+ * Return: If success, return a handle of mailbox subsystem.
+ * Otherwise, return NULL pointer.
+ */
+struct mailbox *xdnam_mailbox_create(struct drm_device *ddev,
+				     const struct xdna_mailbox_res *res);
+
+/*
+ * xdna_mailbox_create_channel() -- Create a mailbox channel instance
+ *
+ * @mailbox: the handle return from xdna_mailbox_create()
+ * @x2i: host to firmware mailbox resources
+ * @i2x: firmware to host mailbox resources
+ * @xdna_mailbox_intr_reg: register addr of MSI-X interrupt
+ * @mb_irq: Linux IRQ number associated with mailbox MSI-X interrupt vector index
+ *
+ * Return: If success, return a handle of mailbox channel. Otherwise, return NULL.
+ */
+struct mailbox_channel *
+xdna_mailbox_create_channel(struct mailbox *mailbox,
+			    const struct xdna_mailbox_chann_res *x2i,
+			    const struct xdna_mailbox_chann_res *i2x,
+			    u32 xdna_mailbox_intr_reg,
+			    int mb_irq);
+
+/*
+ * xdna_mailbox_destroy_channel() -- destroy mailbox channel
+ *
+ * @mailbox_chann: the handle return from xdna_mailbox_create_channel()
+ *
+ * Return: if success, return 0. otherwise return error code
+ */
+int xdna_mailbox_destroy_channel(struct mailbox_channel *mailbox_chann);
+
+/*
+ * xdna_mailbox_stop_channel() -- stop mailbox channel
+ *
+ * @mailbox_chann: the handle return from xdna_mailbox_create_channel()
+ *
+ * Return: if success, return 0. otherwise return error code
+ */
+void xdna_mailbox_stop_channel(struct mailbox_channel *mailbox_chann);
+
+/*
+ * xdna_mailbox_send_msg() -- Send a message
+ *
+ * @mailbox_chann: Mailbox channel handle
+ * @msg: message struct for message information
+ * @tx_timeout: the timeout value for sending the message in ms.
+ *
+ * Return: If success return 0, otherwise, return error code
+ */
+int xdna_mailbox_send_msg(struct mailbox_channel *mailbox_chann,
+			  const struct xdna_mailbox_msg *msg, u64 tx_timeout);
+
+#endif /* _AIE2_MAILBOX_ */
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c
new file mode 100644
index 000000000000..6d0c24513476
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_print.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/completion.h>
+
+#include "amdxdna_gem.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_mailbox_helper.h"
+#include "amdxdna_pci_drv.h"
+
+int xdna_msg_cb(void *handle, void __iomem *data, size_t size)
+{
+	struct xdna_notify *cb_arg = handle;
+	int ret;
+
+	if (unlikely(!data))
+		goto out;
+
+	if (unlikely(cb_arg->size != size)) {
+		cb_arg->error = -EINVAL;
+		goto out;
+	}
+
+	memcpy_fromio(cb_arg->data, data, cb_arg->size);
+	print_hex_dump_debug("resp data: ", DUMP_PREFIX_OFFSET,
+			     16, 4, cb_arg->data, cb_arg->size, true);
+out:
+	ret = cb_arg->error;
+	complete(&cb_arg->comp);
+	return ret;
+}
+
+int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann,
+		       struct xdna_mailbox_msg *msg)
+{
+	struct xdna_notify *hdl = msg->handle;
+	int ret;
+
+	ret = xdna_mailbox_send_msg(chann, msg, TX_TIMEOUT);
+	if (ret) {
+		XDNA_ERR(xdna, "Send message failed, ret %d", ret);
+		return ret;
+	}
+
+	ret = wait_for_completion_timeout(&hdl->comp,
+					  msecs_to_jiffies(RX_TIMEOUT));
+	if (!ret) {
+		XDNA_ERR(xdna, "Wait for completion timeout");
+		return -ETIME;
+	}
+
+	return hdl->error;
+}
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.h b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h
new file mode 100644
index 000000000000..710ff8873d61
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AMDXDNA_MAILBOX_HELPER_H
+#define _AMDXDNA_MAILBOX_HELPER_H
+
+#define TX_TIMEOUT 2000 /* milliseconds */
+#define RX_TIMEOUT 5000 /* milliseconds */
+
+struct amdxdna_dev;
+
+struct xdna_notify {
+	struct completion       comp;
+	u32			*data;
+	size_t			size;
+	int			error;
+};
+
+#define DECLARE_XDNA_MSG_COMMON(name, op, status)			\
+	struct name##_req	req = { 0 };				\
+	struct name##_resp	resp = { status	};			\
+	struct xdna_notify	hdl = {					\
+		.error = 0,						\
+		.data = (u32 *)&resp,					\
+		.size = sizeof(resp),					\
+		.comp = COMPLETION_INITIALIZER_ONSTACK(hdl.comp),	\
+	};								\
+	struct xdna_mailbox_msg msg = {					\
+		.send_data = (u8 *)&req,				\
+		.send_size = sizeof(req),				\
+		.handle = &hdl,						\
+		.opcode = op,						\
+		.notify_cb = xdna_msg_cb,				\
+	}
+
+int xdna_msg_cb(void *handle, void __iomem *data, size_t size);
+int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann,
+		       struct xdna_mailbox_msg *msg);
+
+#endif /* _AMDXDNA_MAILBOX_HELPER_H */
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
new file mode 100644
index 000000000000..569cd703729d
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_accel.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_ioctl.h>
+#include <drm/drm_managed.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/iommu.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+
+#include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
+#include "amdxdna_pci_drv.h"
+
+#define AMDXDNA_AUTOSUSPEND_DELAY	5000 /* milliseconds */
+
+MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin");
+
+/*
+ * 0.0: Initial version
+ * 0.1: Support getting all hardware contexts by DRM_IOCTL_AMDXDNA_GET_ARRAY
+ */
+#define AMDXDNA_DRIVER_MAJOR		0
+#define AMDXDNA_DRIVER_MINOR		1
+
+/*
+ * Bind the driver base on (vendor_id, device_id) pair and later use the
+ * (device_id, rev_id) pair as a key to select the devices. The devices with
+ * same device_id have very similar interface to host driver.
+ */
+static const struct pci_device_id pci_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1502) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x17f0) },
+	{0}
+};
+
+MODULE_DEVICE_TABLE(pci, pci_ids);
+
+static const struct amdxdna_device_id amdxdna_ids[] = {
+	{ 0x1502, 0x0,  &dev_npu1_info },
+	{ 0x17f0, 0x0,  &dev_npu2_info },
+	{ 0x17f0, 0x10, &dev_npu4_info },
+	{ 0x17f0, 0x11, &dev_npu5_info },
+	{ 0x17f0, 0x20, &dev_npu6_info },
+	{0}
+};
+
+static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(ddev);
+	struct amdxdna_client *client;
+	int ret;
+
+	ret = pm_runtime_resume_and_get(ddev->dev);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to get rpm, ret %d", ret);
+		return ret;
+	}
+
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
+	if (!client) {
+		ret = -ENOMEM;
+		goto put_rpm;
+	}
+
+	client->pid = pid_nr(rcu_access_pointer(filp->pid));
+	client->xdna = xdna;
+
+	client->sva = iommu_sva_bind_device(xdna->ddev.dev, current->mm);
+	if (IS_ERR(client->sva)) {
+		ret = PTR_ERR(client->sva);
+		XDNA_ERR(xdna, "SVA bind device failed, ret %d", ret);
+		goto failed;
+	}
+	client->pasid = iommu_sva_get_pasid(client->sva);
+	if (client->pasid == IOMMU_PASID_INVALID) {
+		XDNA_ERR(xdna, "SVA get pasid failed");
+		ret = -ENODEV;
+		goto unbind_sva;
+	}
+	init_srcu_struct(&client->hwctx_srcu);
+	xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC);
+	mutex_init(&client->mm_lock);
+
+	mutex_lock(&xdna->dev_lock);
+	list_add_tail(&client->node, &xdna->client_list);
+	mutex_unlock(&xdna->dev_lock);
+
+	filp->driver_priv = client;
+	client->filp = filp;
+
+	XDNA_DBG(xdna, "pid %d opened", client->pid);
+	return 0;
+
+unbind_sva:
+	iommu_sva_unbind_device(client->sva);
+failed:
+	kfree(client);
+put_rpm:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return ret;
+}
+
+static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(ddev);
+
+	XDNA_DBG(xdna, "closing pid %d", client->pid);
+
+	xa_destroy(&client->hwctx_xa);
+	cleanup_srcu_struct(&client->hwctx_srcu);
+	mutex_destroy(&client->mm_lock);
+	if (client->dev_heap)
+		drm_gem_object_put(to_gobj(client->dev_heap));
+
+	iommu_sva_unbind_device(client->sva);
+
+	XDNA_DBG(xdna, "pid %d closed", client->pid);
+	kfree(client);
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+}
+
+static int amdxdna_flush(struct file *f, fl_owner_t id)
+{
+	struct drm_file *filp = f->private_data;
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = client->xdna;
+	int idx;
+
+	XDNA_DBG(xdna, "PID %d flushing...", client->pid);
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return 0;
+
+	mutex_lock(&xdna->dev_lock);
+	list_del_init(&client->node);
+	amdxdna_hwctx_remove_all(client);
+	mutex_unlock(&xdna->dev_lock);
+
+	drm_dev_exit(idx);
+	return 0;
+}
+
+static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_get_info *args = data;
+	int ret;
+
+	if (!xdna->dev_info->ops->get_aie_info)
+		return -EOPNOTSUPP;
+
+	XDNA_DBG(xdna, "Request parameter %u", args->param);
+	mutex_lock(&xdna->dev_lock);
+	ret = xdna->dev_info->ops->get_aie_info(client, args);
+	mutex_unlock(&xdna->dev_lock);
+	return ret;
+}
+
+static int amdxdna_drm_get_array_ioctl(struct drm_device *dev, void *data,
+				       struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_get_array *args = data;
+
+	if (!xdna->dev_info->ops->get_array)
+		return -EOPNOTSUPP;
+
+	if (args->pad || !args->num_element || !args->element_size)
+		return -EINVAL;
+
+	guard(mutex)(&xdna->dev_lock);
+	return xdna->dev_info->ops->get_array(client, args);
+}
+
+static int amdxdna_drm_set_state_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_set_state *args = data;
+	int ret;
+
+	if (!xdna->dev_info->ops->set_aie_state)
+		return -EOPNOTSUPP;
+
+	XDNA_DBG(xdna, "Request parameter %u", args->param);
+	mutex_lock(&xdna->dev_lock);
+	ret = xdna->dev_info->ops->set_aie_state(client, args);
+	mutex_unlock(&xdna->dev_lock);
+
+	return ret;
+}
+
+static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = {
+	/* Context */
+	DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_DESTROY_HWCTX, amdxdna_drm_destroy_hwctx_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_CONFIG_HWCTX, amdxdna_drm_config_hwctx_ioctl, 0),
+	/* BO */
+	DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_BO, amdxdna_drm_create_bo_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_GET_BO_INFO, amdxdna_drm_get_bo_info_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0),
+	/* Execution */
+	DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD, amdxdna_drm_submit_cmd_ioctl, 0),
+	/* AIE hardware */
+	DRM_IOCTL_DEF_DRV(AMDXDNA_GET_INFO, amdxdna_drm_get_info_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_GET_ARRAY, amdxdna_drm_get_array_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(AMDXDNA_SET_STATE, amdxdna_drm_set_state_ioctl, DRM_ROOT_ONLY),
+};
+
+static const struct file_operations amdxdna_fops = {
+	.owner		= THIS_MODULE,
+	.open		= accel_open,
+	.release	= drm_release,
+	.flush		= amdxdna_flush,
+	.unlocked_ioctl	= drm_ioctl,
+	.compat_ioctl	= drm_compat_ioctl,
+	.poll		= drm_poll,
+	.read		= drm_read,
+	.llseek		= noop_llseek,
+	.mmap		= drm_gem_mmap,
+	.fop_flags	= FOP_UNSIGNED_OFFSET,
+};
+
+const struct drm_driver amdxdna_drm_drv = {
+	.driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL |
+		DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE,
+	.fops = &amdxdna_fops,
+	.name = "amdxdna_accel_driver",
+	.desc = "AMD XDNA DRM implementation",
+	.major = AMDXDNA_DRIVER_MAJOR,
+	.minor = AMDXDNA_DRIVER_MINOR,
+	.open = amdxdna_drm_open,
+	.postclose = amdxdna_drm_close,
+	.ioctls = amdxdna_drm_ioctls,
+	.num_ioctls = ARRAY_SIZE(amdxdna_drm_ioctls),
+
+	.gem_create_object = amdxdna_gem_create_object_cb,
+	.gem_prime_import = amdxdna_gem_prime_import,
+};
+
+static const struct amdxdna_dev_info *
+amdxdna_get_dev_info(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(amdxdna_ids); i++) {
+		if (pdev->device == amdxdna_ids[i].device &&
+		    pdev->revision == amdxdna_ids[i].revision)
+			return amdxdna_ids[i].dev_info;
+	}
+	return NULL;
+}
+
+static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct amdxdna_dev *xdna;
+	int ret;
+
+	xdna = devm_drm_dev_alloc(dev, &amdxdna_drm_drv, typeof(*xdna), ddev);
+	if (IS_ERR(xdna))
+		return PTR_ERR(xdna);
+
+	xdna->dev_info = amdxdna_get_dev_info(pdev);
+	if (!xdna->dev_info)
+		return -ENODEV;
+
+	drmm_mutex_init(&xdna->ddev, &xdna->dev_lock);
+	init_rwsem(&xdna->notifier_lock);
+	INIT_LIST_HEAD(&xdna->client_list);
+	pci_set_drvdata(pdev, xdna);
+
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		fs_reclaim_acquire(GFP_KERNEL);
+		might_lock(&xdna->notifier_lock);
+		fs_reclaim_release(GFP_KERNEL);
+	}
+
+	xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", 0);
+	if (!xdna->notifier_wq)
+		return -ENOMEM;
+
+	mutex_lock(&xdna->dev_lock);
+	ret = xdna->dev_info->ops->init(xdna);
+	mutex_unlock(&xdna->dev_lock);
+	if (ret) {
+		XDNA_ERR(xdna, "Hardware init failed, ret %d", ret);
+		goto destroy_notifier_wq;
+	}
+
+	ret = amdxdna_sysfs_init(xdna);
+	if (ret) {
+		XDNA_ERR(xdna, "Create amdxdna attrs failed: %d", ret);
+		goto failed_dev_fini;
+	}
+
+	pm_runtime_set_autosuspend_delay(dev, AMDXDNA_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_allow(dev);
+
+	ret = drm_dev_register(&xdna->ddev, 0);
+	if (ret) {
+		XDNA_ERR(xdna, "DRM register failed, ret %d", ret);
+		pm_runtime_forbid(dev);
+		goto failed_sysfs_fini;
+	}
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+	return 0;
+
+failed_sysfs_fini:
+	amdxdna_sysfs_fini(xdna);
+failed_dev_fini:
+	mutex_lock(&xdna->dev_lock);
+	xdna->dev_info->ops->fini(xdna);
+	mutex_unlock(&xdna->dev_lock);
+destroy_notifier_wq:
+	destroy_workqueue(xdna->notifier_wq);
+	return ret;
+}
+
+static void amdxdna_remove(struct pci_dev *pdev)
+{
+	struct amdxdna_dev *xdna = pci_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	struct amdxdna_client *client;
+
+	destroy_workqueue(xdna->notifier_wq);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_forbid(dev);
+
+	drm_dev_unplug(&xdna->ddev);
+	amdxdna_sysfs_fini(xdna);
+
+	mutex_lock(&xdna->dev_lock);
+	client = list_first_entry_or_null(&xdna->client_list,
+					  struct amdxdna_client, node);
+	while (client) {
+		list_del_init(&client->node);
+		amdxdna_hwctx_remove_all(client);
+
+		client = list_first_entry_or_null(&xdna->client_list,
+						  struct amdxdna_client, node);
+	}
+
+	xdna->dev_info->ops->fini(xdna);
+	mutex_unlock(&xdna->dev_lock);
+}
+
+static int amdxdna_pmops_suspend(struct device *dev)
+{
+	struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev));
+
+	if (!xdna->dev_info->ops->suspend)
+		return -EOPNOTSUPP;
+
+	return xdna->dev_info->ops->suspend(xdna);
+}
+
+static int amdxdna_pmops_resume(struct device *dev)
+{
+	struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev));
+
+	if (!xdna->dev_info->ops->resume)
+		return -EOPNOTSUPP;
+
+	return xdna->dev_info->ops->resume(xdna);
+}
+
+static const struct dev_pm_ops amdxdna_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume)
+	RUNTIME_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume, NULL)
+};
+
+static struct pci_driver amdxdna_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = pci_ids,
+	.probe = amdxdna_probe,
+	.remove = amdxdna_remove,
+	.driver.pm = &amdxdna_pm_ops,
+};
+
+module_pci_driver(amdxdna_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("XRT Team <runtimeca39d@amd.com>");
+MODULE_DESCRIPTION("amdxdna driver");
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
new file mode 100644
index 000000000000..72d6696d49da
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _AMDXDNA_PCI_DRV_H_
+#define _AMDXDNA_PCI_DRV_H_
+
+#include <linux/workqueue.h>
+#include <linux/xarray.h>
+
+#define XDNA_INFO(xdna, fmt, args...)	drm_info(&(xdna)->ddev, fmt, ##args)
+#define XDNA_WARN(xdna, fmt, args...)	drm_warn(&(xdna)->ddev, "%s: "fmt, __func__, ##args)
+#define XDNA_ERR(xdna, fmt, args...)	drm_err(&(xdna)->ddev, "%s: "fmt, __func__, ##args)
+#define XDNA_DBG(xdna, fmt, args...)	drm_dbg(&(xdna)->ddev, fmt, ##args)
+#define XDNA_INFO_ONCE(xdna, fmt, args...) drm_info_once(&(xdna)->ddev, fmt, ##args)
+
+#define XDNA_MBZ_DBG(xdna, ptr, sz)					\
+	({								\
+		int __i;						\
+		int __ret = 0;						\
+		u8 *__ptr = (u8 *)(ptr);				\
+		for (__i = 0; __i < (sz); __i++) {			\
+			if (__ptr[__i]) {				\
+				XDNA_DBG(xdna, "MBZ check failed");	\
+				__ret = -EINVAL;			\
+				break;					\
+			}						\
+		}							\
+		__ret;							\
+	})
+
+#define to_xdna_dev(drm_dev) \
+	((struct amdxdna_dev *)container_of(drm_dev, struct amdxdna_dev, ddev))
+
+extern const struct drm_driver amdxdna_drm_drv;
+
+struct amdxdna_client;
+struct amdxdna_dev;
+struct amdxdna_drm_get_info;
+struct amdxdna_drm_set_state;
+struct amdxdna_gem_obj;
+struct amdxdna_hwctx;
+struct amdxdna_sched_job;
+
+/*
+ * struct amdxdna_dev_ops - Device hardware operation callbacks
+ */
+struct amdxdna_dev_ops {
+	int (*init)(struct amdxdna_dev *xdna);
+	void (*fini)(struct amdxdna_dev *xdna);
+	int (*resume)(struct amdxdna_dev *xdna);
+	int (*suspend)(struct amdxdna_dev *xdna);
+	int (*hwctx_init)(struct amdxdna_hwctx *hwctx);
+	void (*hwctx_fini)(struct amdxdna_hwctx *hwctx);
+	int (*hwctx_config)(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size);
+	void (*hmm_invalidate)(struct amdxdna_gem_obj *abo, unsigned long cur_seq);
+	int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq);
+	int (*get_aie_info)(struct amdxdna_client *client, struct amdxdna_drm_get_info *args);
+	int (*set_aie_state)(struct amdxdna_client *client, struct amdxdna_drm_set_state *args);
+	int (*get_array)(struct amdxdna_client *client, struct amdxdna_drm_get_array *args);
+};
+
+/*
+ * struct amdxdna_dev_info - Device hardware information
+ * Record device static information, like reg, mbox, PSP, SMU bar index
+ */
+struct amdxdna_dev_info {
+	int				reg_bar;
+	int				mbox_bar;
+	int				sram_bar;
+	int				psp_bar;
+	int				smu_bar;
+	int				device_type;
+	int				first_col;
+	u32				dev_mem_buf_shift;
+	u64				dev_mem_base;
+	size_t				dev_mem_size;
+	char				*vbnv;
+	const struct amdxdna_dev_priv	*dev_priv;
+	const struct amdxdna_dev_ops	*ops;
+};
+
+struct amdxdna_fw_ver {
+	u32 major;
+	u32 minor;
+	u32 sub;
+	u32 build;
+};
+
+struct amdxdna_dev {
+	struct drm_device		ddev;
+	struct amdxdna_dev_hdl		*dev_handle;
+	const struct amdxdna_dev_info	*dev_info;
+	void				*xrs_hdl;
+
+	struct mutex			dev_lock; /* per device lock */
+	struct list_head		client_list;
+	struct amdxdna_fw_ver		fw_ver;
+	struct rw_semaphore		notifier_lock; /* for mmu notifier*/
+	struct workqueue_struct		*notifier_wq;
+};
+
+/*
+ * struct amdxdna_device_id - PCI device info
+ */
+struct amdxdna_device_id {
+	unsigned short device;
+	u8 revision;
+	const struct amdxdna_dev_info *dev_info;
+};
+
+/*
+ * struct amdxdna_client - amdxdna client
+ * A per fd data structure for managing context and other user process stuffs.
+ */
+struct amdxdna_client {
+	struct list_head		node;
+	pid_t				pid;
+	struct srcu_struct		hwctx_srcu;
+	struct xarray			hwctx_xa;
+	u32				next_hwctxid;
+	struct amdxdna_dev		*xdna;
+	struct drm_file			*filp;
+
+	struct mutex			mm_lock; /* protect memory related */
+	struct amdxdna_gem_obj		*dev_heap;
+
+	struct iommu_sva		*sva;
+	int				pasid;
+};
+
+#define amdxdna_for_each_hwctx(client, hwctx_id, entry)		\
+	xa_for_each(&(client)->hwctx_xa, hwctx_id, entry)
+
+/* Add device info below */
+extern const struct amdxdna_dev_info dev_npu1_info;
+extern const struct amdxdna_dev_info dev_npu2_info;
+extern const struct amdxdna_dev_info dev_npu4_info;
+extern const struct amdxdna_dev_info dev_npu5_info;
+extern const struct amdxdna_dev_info dev_npu6_info;
+
+int amdxdna_sysfs_init(struct amdxdna_dev *xdna);
+void amdxdna_sysfs_fini(struct amdxdna_dev *xdna);
+
+#endif /* _AMDXDNA_PCI_DRV_H_ */
diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c
new file mode 100644
index 000000000000..f27e4ee960a0
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_sysfs.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/types.h>
+
+#include "amdxdna_gem.h"
+#include "amdxdna_pci_drv.h"
+
+static ssize_t vbnv_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct amdxdna_dev *xdna = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", xdna->dev_info->vbnv);
+}
+static DEVICE_ATTR_RO(vbnv);
+
+static ssize_t device_type_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct amdxdna_dev *xdna = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", xdna->dev_info->device_type);
+}
+static DEVICE_ATTR_RO(device_type);
+
+static ssize_t fw_version_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct amdxdna_dev *xdna = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d.%d.%d.%d\n", xdna->fw_ver.major,
+		       xdna->fw_ver.minor, xdna->fw_ver.sub,
+		       xdna->fw_ver.build);
+}
+static DEVICE_ATTR_RO(fw_version);
+
+static struct attribute *amdxdna_attrs[] = {
+	&dev_attr_device_type.attr,
+	&dev_attr_vbnv.attr,
+	&dev_attr_fw_version.attr,
+	NULL,
+};
+
+static struct attribute_group amdxdna_attr_group = {
+	.attrs = amdxdna_attrs,
+};
+
+int amdxdna_sysfs_init(struct amdxdna_dev *xdna)
+{
+	int ret;
+
+	ret = sysfs_create_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group);
+	if (ret)
+		XDNA_ERR(xdna, "Create attr group failed");
+
+	return ret;
+}
+
+void amdxdna_sysfs_fini(struct amdxdna_dev *xdna)
+{
+	sysfs_remove_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group);
+}
diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.c b/drivers/accel/amdxdna/amdxdna_ubuf.c
new file mode 100644
index 000000000000..077b2261cf2a
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_ubuf.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/drm_print.h>
+#include <linux/dma-buf.h>
+#include <linux/pagemap.h>
+#include <linux/vmalloc.h>
+
+#include "amdxdna_pci_drv.h"
+#include "amdxdna_ubuf.h"
+
+struct amdxdna_ubuf_priv {
+	struct page **pages;
+	u64 nr_pages;
+	enum amdxdna_ubuf_flag flags;
+	struct mm_struct *mm;
+};
+
+static struct sg_table *amdxdna_ubuf_map(struct dma_buf_attachment *attach,
+					 enum dma_data_direction direction)
+{
+	struct amdxdna_ubuf_priv *ubuf = attach->dmabuf->priv;
+	struct sg_table *sg;
+	int ret;
+
+	sg = kzalloc(sizeof(*sg), GFP_KERNEL);
+	if (!sg)
+		return ERR_PTR(-ENOMEM);
+
+	ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->nr_pages, 0,
+					ubuf->nr_pages << PAGE_SHIFT, GFP_KERNEL);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (ubuf->flags & AMDXDNA_UBUF_FLAG_MAP_DMA) {
+		ret = dma_map_sgtable(attach->dev, sg, direction, 0);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	return sg;
+}
+
+static void amdxdna_ubuf_unmap(struct dma_buf_attachment *attach,
+			       struct sg_table *sg,
+			       enum dma_data_direction direction)
+{
+	struct amdxdna_ubuf_priv *ubuf = attach->dmabuf->priv;
+
+	if (ubuf->flags & AMDXDNA_UBUF_FLAG_MAP_DMA)
+		dma_unmap_sgtable(attach->dev, sg, direction, 0);
+
+	sg_free_table(sg);
+	kfree(sg);
+}
+
+static void amdxdna_ubuf_release(struct dma_buf *dbuf)
+{
+	struct amdxdna_ubuf_priv *ubuf = dbuf->priv;
+
+	unpin_user_pages(ubuf->pages, ubuf->nr_pages);
+	kvfree(ubuf->pages);
+	atomic64_sub(ubuf->nr_pages, &ubuf->mm->pinned_vm);
+	mmdrop(ubuf->mm);
+	kfree(ubuf);
+}
+
+static vm_fault_t amdxdna_ubuf_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct amdxdna_ubuf_priv *ubuf;
+	unsigned long pfn;
+	pgoff_t pgoff;
+
+	ubuf = vma->vm_private_data;
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
+
+	pfn = page_to_pfn(ubuf->pages[pgoff]);
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static const struct vm_operations_struct amdxdna_ubuf_vm_ops = {
+	.fault = amdxdna_ubuf_vm_fault,
+};
+
+static int amdxdna_ubuf_mmap(struct dma_buf *dbuf, struct vm_area_struct *vma)
+{
+	struct amdxdna_ubuf_priv *ubuf = dbuf->priv;
+
+	vma->vm_ops = &amdxdna_ubuf_vm_ops;
+	vma->vm_private_data = ubuf;
+	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
+	return 0;
+}
+
+static int amdxdna_ubuf_vmap(struct dma_buf *dbuf, struct iosys_map *map)
+{
+	struct amdxdna_ubuf_priv *ubuf = dbuf->priv;
+	void *kva;
+
+	kva = vmap(ubuf->pages, ubuf->nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!kva)
+		return -EINVAL;
+
+	iosys_map_set_vaddr(map, kva);
+	return 0;
+}
+
+static void amdxdna_ubuf_vunmap(struct dma_buf *dbuf, struct iosys_map *map)
+{
+	vunmap(map->vaddr);
+}
+
+static const struct dma_buf_ops amdxdna_ubuf_dmabuf_ops = {
+	.map_dma_buf = amdxdna_ubuf_map,
+	.unmap_dma_buf = amdxdna_ubuf_unmap,
+	.release = amdxdna_ubuf_release,
+	.mmap = amdxdna_ubuf_mmap,
+	.vmap = amdxdna_ubuf_vmap,
+	.vunmap = amdxdna_ubuf_vunmap,
+};
+
+struct dma_buf *amdxdna_get_ubuf(struct drm_device *dev,
+				 enum amdxdna_ubuf_flag flags,
+				 u32 num_entries, void __user *va_entries)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	unsigned long lock_limit, new_pinned;
+	struct amdxdna_drm_va_entry *va_ent;
+	struct amdxdna_ubuf_priv *ubuf;
+	u32 npages, start = 0;
+	struct dma_buf *dbuf;
+	int i, ret;
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+	if (!can_do_mlock())
+		return ERR_PTR(-EPERM);
+
+	ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
+	if (!ubuf)
+		return ERR_PTR(-ENOMEM);
+
+	ubuf->flags = flags;
+	ubuf->mm = current->mm;
+	mmgrab(ubuf->mm);
+
+	va_ent = kvcalloc(num_entries, sizeof(*va_ent), GFP_KERNEL);
+	if (!va_ent) {
+		ret = -ENOMEM;
+		goto free_ubuf;
+	}
+
+	if (copy_from_user(va_ent, va_entries, sizeof(*va_ent) * num_entries)) {
+		XDNA_DBG(xdna, "Access va entries failed");
+		ret = -EINVAL;
+		goto free_ent;
+	}
+
+	for (i = 0, exp_info.size = 0; i < num_entries; i++) {
+		if (!IS_ALIGNED(va_ent[i].vaddr, PAGE_SIZE) ||
+		    !IS_ALIGNED(va_ent[i].len, PAGE_SIZE)) {
+			XDNA_ERR(xdna, "Invalid address or len %llx, %llx",
+				 va_ent[i].vaddr, va_ent[i].len);
+			ret = -EINVAL;
+			goto free_ent;
+		}
+
+		exp_info.size += va_ent[i].len;
+	}
+
+	ubuf->nr_pages = exp_info.size >> PAGE_SHIFT;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	new_pinned = atomic64_add_return(ubuf->nr_pages, &ubuf->mm->pinned_vm);
+	if (new_pinned > lock_limit && !capable(CAP_IPC_LOCK)) {
+		XDNA_DBG(xdna, "New pin %ld, limit %ld, cap %d",
+			 new_pinned, lock_limit, capable(CAP_IPC_LOCK));
+		ret = -ENOMEM;
+		goto sub_pin_cnt;
+	}
+
+	ubuf->pages = kvmalloc_array(ubuf->nr_pages, sizeof(*ubuf->pages), GFP_KERNEL);
+	if (!ubuf->pages) {
+		ret = -ENOMEM;
+		goto sub_pin_cnt;
+	}
+
+	for (i = 0; i < num_entries; i++) {
+		npages = va_ent[i].len >> PAGE_SHIFT;
+
+		ret = pin_user_pages_fast(va_ent[i].vaddr, npages,
+					  FOLL_WRITE | FOLL_LONGTERM,
+					  &ubuf->pages[start]);
+		if (ret < 0 || ret != npages) {
+			ret = -ENOMEM;
+			XDNA_ERR(xdna, "Failed to pin pages ret %d", ret);
+			goto destroy_pages;
+		}
+
+		start += ret;
+	}
+
+	exp_info.ops = &amdxdna_ubuf_dmabuf_ops;
+	exp_info.priv = ubuf;
+	exp_info.flags = O_RDWR | O_CLOEXEC;
+
+	dbuf = dma_buf_export(&exp_info);
+	if (IS_ERR(dbuf)) {
+		ret = PTR_ERR(dbuf);
+		goto destroy_pages;
+	}
+	kvfree(va_ent);
+
+	return dbuf;
+
+destroy_pages:
+	if (start)
+		unpin_user_pages(ubuf->pages, start);
+	kvfree(ubuf->pages);
+sub_pin_cnt:
+	atomic64_sub(ubuf->nr_pages, &ubuf->mm->pinned_vm);
+free_ent:
+	kvfree(va_ent);
+free_ubuf:
+	mmdrop(ubuf->mm);
+	kfree(ubuf);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.h b/drivers/accel/amdxdna/amdxdna_ubuf.h
new file mode 100644
index 000000000000..e5cb3bdb3ec9
--- /dev/null
+++ b/drivers/accel/amdxdna/amdxdna_ubuf.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ */
+#ifndef _AMDXDNA_UBUF_H_
+#define _AMDXDNA_UBUF_H_
+
+#include <drm/drm_device.h>
+#include <linux/dma-buf.h>
+
+enum amdxdna_ubuf_flag {
+	AMDXDNA_UBUF_FLAG_MAP_DMA = 1,
+};
+
+struct dma_buf *amdxdna_get_ubuf(struct drm_device *dev,
+				 enum amdxdna_ubuf_flag flags,
+				 u32 num_entries, void __user *va_entries);
+
+#endif /* _AMDXDNA_UBUF_H_ */
diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c
new file mode 100644
index 000000000000..e4f6dac7d00f
--- /dev/null
+++ b/drivers/accel/amdxdna/npu1_regs.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/sizes.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+/* Address definition from NPU1 docs */
+#define MPNPU_PUB_SEC_INTR		0x3010090
+#define MPNPU_PUB_PWRMGMT_INTR		0x3010094
+#define MPNPU_PUB_SCRATCH2		0x30100A0
+#define MPNPU_PUB_SCRATCH3		0x30100A4
+#define MPNPU_PUB_SCRATCH4		0x30100A8
+#define MPNPU_PUB_SCRATCH5		0x30100AC
+#define MPNPU_PUB_SCRATCH6		0x30100B0
+#define MPNPU_PUB_SCRATCH7		0x30100B4
+#define MPNPU_PUB_SCRATCH9		0x30100BC
+
+#define MPNPU_SRAM_X2I_MAILBOX_0	0x30A0000
+#define MPNPU_SRAM_X2I_MAILBOX_1	0x30A2000
+#define MPNPU_SRAM_I2X_MAILBOX_15	0x30BF000
+
+#define MPNPU_APERTURE0_BASE		0x3000000
+#define MPNPU_APERTURE1_BASE		0x3080000
+#define MPNPU_APERTURE2_BASE		0x30C0000
+
+/* PCIe BAR Index for NPU1 */
+#define NPU1_REG_BAR_INDEX  0
+#define NPU1_MBOX_BAR_INDEX 4
+#define NPU1_PSP_BAR_INDEX  0
+#define NPU1_SMU_BAR_INDEX  0
+#define NPU1_SRAM_BAR_INDEX 2
+/* Associated BARs and Apertures */
+#define NPU1_REG_BAR_BASE  MPNPU_APERTURE0_BASE
+#define NPU1_MBOX_BAR_BASE MPNPU_APERTURE2_BASE
+#define NPU1_PSP_BAR_BASE  MPNPU_APERTURE0_BASE
+#define NPU1_SMU_BAR_BASE  MPNPU_APERTURE0_BASE
+#define NPU1_SRAM_BAR_BASE MPNPU_APERTURE1_BASE
+
+const struct rt_config npu1_default_rt_cfg[] = {
+	{ 2, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */
+	{ 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+	{ 0 },
+};
+
+const struct dpm_clk_freq npu1_dpm_clk_table[] = {
+	{400, 800},
+	{600, 1024},
+	{600, 1024},
+	{600, 1024},
+	{600, 1024},
+	{720, 1309},
+	{720, 1309},
+	{847, 1600},
+	{ 0 }
+};
+
+static const struct amdxdna_dev_priv npu1_dev_priv = {
+	.fw_path        = "amdnpu/1502_00/npu.sbin",
+	.protocol_major = 0x5,
+	.protocol_minor = 0x7,
+	.rt_config	= npu1_default_rt_cfg,
+	.dpm_clk_tbl	= npu1_dpm_clk_table,
+	.col_align	= COL_ALIGN_NONE,
+	.mbox_dev_addr  = NPU1_MBOX_BAR_BASE,
+	.mbox_size      = 0, /* Use BAR size */
+	.sram_dev_addr  = NPU1_SRAM_BAR_BASE,
+	.sram_offs      = {
+		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU1_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
+		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU1_SRAM, MPNPU_SRAM_I2X_MAILBOX_15),
+	},
+	.psp_regs_off   = {
+		DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU1_PSP, MPNPU_PUB_SCRATCH2),
+		DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU1_PSP, MPNPU_PUB_SCRATCH3),
+		DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU1_PSP, MPNPU_PUB_SCRATCH4),
+		DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU1_PSP, MPNPU_PUB_SCRATCH9),
+		DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU1_PSP, MPNPU_PUB_SEC_INTR),
+		DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU1_PSP, MPNPU_PUB_SCRATCH2),
+		DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU1_PSP, MPNPU_PUB_SCRATCH3),
+	},
+	.smu_regs_off   = {
+		DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU1_SMU, MPNPU_PUB_SCRATCH5),
+		DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU1_SMU, MPNPU_PUB_SCRATCH7),
+		DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU1_SMU, MPNPU_PUB_PWRMGMT_INTR),
+		DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU1_SMU, MPNPU_PUB_SCRATCH6),
+		DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU1_SMU, MPNPU_PUB_SCRATCH7),
+	},
+	.hw_ops		= {
+		.set_dpm = npu1_set_dpm,
+	},
+};
+
+const struct amdxdna_dev_info dev_npu1_info = {
+	.reg_bar           = NPU1_REG_BAR_INDEX,
+	.mbox_bar          = NPU1_MBOX_BAR_INDEX,
+	.sram_bar          = NPU1_SRAM_BAR_INDEX,
+	.psp_bar           = NPU1_PSP_BAR_INDEX,
+	.smu_bar           = NPU1_SMU_BAR_INDEX,
+	.first_col         = 1,
+	.dev_mem_buf_shift = 15, /* 32 KiB aligned */
+	.dev_mem_base      = AIE2_DEVM_BASE,
+	.dev_mem_size      = AIE2_DEVM_SIZE,
+	.vbnv              = "RyzenAI-npu1",
+	.device_type       = AMDXDNA_DEV_TYPE_KMQ,
+	.dev_priv          = &npu1_dev_priv,
+	.ops               = &aie2_ops,
+};
diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c
new file mode 100644
index 000000000000..a081cac75ee0
--- /dev/null
+++ b/drivers/accel/amdxdna/npu2_regs.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/sizes.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */
+#define MPNPU_PUB_SEC_INTR             0x3010060
+#define MPNPU_PUB_PWRMGMT_INTR         0x3010064
+#define MPNPU_PUB_SCRATCH0             0x301006C
+#define MPNPU_PUB_SCRATCH1             0x3010070
+#define MPNPU_PUB_SCRATCH2             0x3010074
+#define MPNPU_PUB_SCRATCH3             0x3010078
+#define MPNPU_PUB_SCRATCH4             0x301007C
+#define MPNPU_PUB_SCRATCH5             0x3010080
+#define MPNPU_PUB_SCRATCH6             0x3010084
+#define MPNPU_PUB_SCRATCH7             0x3010088
+#define MPNPU_PUB_SCRATCH8             0x301008C
+#define MPNPU_PUB_SCRATCH9             0x3010090
+#define MPNPU_PUB_SCRATCH10            0x3010094
+#define MPNPU_PUB_SCRATCH11            0x3010098
+#define MPNPU_PUB_SCRATCH12            0x301009C
+#define MPNPU_PUB_SCRATCH13            0x30100A0
+#define MPNPU_PUB_SCRATCH14            0x30100A4
+#define MPNPU_PUB_SCRATCH15            0x30100A8
+#define MP0_C2PMSG_73                  0x3810A24
+#define MP0_C2PMSG_123                 0x3810AEC
+
+#define MP1_C2PMSG_0                   0x3B10900
+#define MP1_C2PMSG_60                  0x3B109F0
+#define MP1_C2PMSG_61                  0x3B109F4
+
+#define MPNPU_SRAM_X2I_MAILBOX_0       0x3600000
+#define MPNPU_SRAM_X2I_MAILBOX_15      0x361E000
+#define MPNPU_SRAM_X2I_MAILBOX_31      0x363E000
+#define MPNPU_SRAM_I2X_MAILBOX_31      0x363F000
+
+#define MMNPU_APERTURE0_BASE           0x3000000
+#define MMNPU_APERTURE1_BASE           0x3600000
+#define MMNPU_APERTURE3_BASE           0x3810000
+#define MMNPU_APERTURE4_BASE           0x3B10000
+
+/* PCIe BAR Index for NPU2 */
+#define NPU2_REG_BAR_INDEX	0
+#define NPU2_MBOX_BAR_INDEX	0
+#define NPU2_PSP_BAR_INDEX	4
+#define NPU2_SMU_BAR_INDEX	5
+#define NPU2_SRAM_BAR_INDEX	2
+/* Associated BARs and Apertures */
+#define NPU2_REG_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU2_MBOX_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU2_PSP_BAR_BASE	MMNPU_APERTURE3_BASE
+#define NPU2_SMU_BAR_BASE	MMNPU_APERTURE4_BASE
+#define NPU2_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
+
+static const struct amdxdna_dev_priv npu2_dev_priv = {
+	.fw_path        = "amdnpu/17f0_00/npu.sbin",
+	.protocol_major = 0x6,
+	.protocol_minor = 0x6,
+	.rt_config	= npu4_default_rt_cfg,
+	.dpm_clk_tbl	= npu4_dpm_clk_table,
+	.col_align	= COL_ALIGN_NATURE,
+	.mbox_dev_addr  = NPU2_MBOX_BAR_BASE,
+	.mbox_size      = 0, /* Use BAR size */
+	.sram_dev_addr  = NPU2_SRAM_BAR_BASE,
+	.sram_offs      = {
+		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
+		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
+	},
+	.psp_regs_off   = {
+		DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU2_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU2_REG, MPNPU_PUB_SCRATCH3),
+		DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU2_REG, MPNPU_PUB_SCRATCH4),
+		DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU2_REG, MPNPU_PUB_SCRATCH9),
+		DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU2_PSP, MP0_C2PMSG_73),
+		DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU2_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU2_REG, MPNPU_PUB_SCRATCH3),
+	},
+	.smu_regs_off   = {
+		DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU2_SMU, MP1_C2PMSG_0),
+		DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU2_SMU, MP1_C2PMSG_60),
+		DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU2_SMU, MMNPU_APERTURE4_BASE),
+		DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU2_SMU, MP1_C2PMSG_61),
+		DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU2_SMU, MP1_C2PMSG_60),
+	},
+	.hw_ops	=	 {
+		.set_dpm = npu4_set_dpm,
+	},
+};
+
+const struct amdxdna_dev_info dev_npu2_info = {
+	.reg_bar           = NPU2_REG_BAR_INDEX,
+	.mbox_bar          = NPU2_MBOX_BAR_INDEX,
+	.sram_bar          = NPU2_SRAM_BAR_INDEX,
+	.psp_bar           = NPU2_PSP_BAR_INDEX,
+	.smu_bar           = NPU2_SMU_BAR_INDEX,
+	.first_col         = 0,
+	.dev_mem_buf_shift = 15, /* 32 KiB aligned */
+	.dev_mem_base      = AIE2_DEVM_BASE,
+	.dev_mem_size      = AIE2_DEVM_SIZE,
+	.vbnv              = "RyzenAI-npu2",
+	.device_type       = AMDXDNA_DEV_TYPE_KMQ,
+	.dev_priv          = &npu2_dev_priv,
+	.ops               = &aie2_ops, /* NPU2 can share NPU1's callback */
+};
diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c
new file mode 100644
index 000000000000..9f2e33182ec6
--- /dev/null
+++ b/drivers/accel/amdxdna/npu4_regs.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/sizes.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */
+#define MPNPU_PUB_SEC_INTR             0x3010060
+#define MPNPU_PUB_PWRMGMT_INTR         0x3010064
+#define MPNPU_PUB_SCRATCH0             0x301006C
+#define MPNPU_PUB_SCRATCH1             0x3010070
+#define MPNPU_PUB_SCRATCH2             0x3010074
+#define MPNPU_PUB_SCRATCH3             0x3010078
+#define MPNPU_PUB_SCRATCH4             0x301007C
+#define MPNPU_PUB_SCRATCH5             0x3010080
+#define MPNPU_PUB_SCRATCH6             0x3010084
+#define MPNPU_PUB_SCRATCH7             0x3010088
+#define MPNPU_PUB_SCRATCH8             0x301008C
+#define MPNPU_PUB_SCRATCH9             0x3010090
+#define MPNPU_PUB_SCRATCH10            0x3010094
+#define MPNPU_PUB_SCRATCH11            0x3010098
+#define MPNPU_PUB_SCRATCH12            0x301009C
+#define MPNPU_PUB_SCRATCH13            0x30100A0
+#define MPNPU_PUB_SCRATCH14            0x30100A4
+#define MPNPU_PUB_SCRATCH15            0x30100A8
+#define MP0_C2PMSG_73                  0x3810A24
+#define MP0_C2PMSG_123                 0x3810AEC
+
+#define MP1_C2PMSG_0                   0x3B10900
+#define MP1_C2PMSG_60                  0x3B109F0
+#define MP1_C2PMSG_61                  0x3B109F4
+
+#define MPNPU_SRAM_X2I_MAILBOX_0       0x3600000
+#define MPNPU_SRAM_X2I_MAILBOX_15      0x361E000
+#define MPNPU_SRAM_X2I_MAILBOX_31      0x363E000
+#define MPNPU_SRAM_I2X_MAILBOX_31      0x363F000
+
+#define MMNPU_APERTURE0_BASE           0x3000000
+#define MMNPU_APERTURE1_BASE           0x3600000
+#define MMNPU_APERTURE3_BASE           0x3810000
+#define MMNPU_APERTURE4_BASE           0x3B10000
+
+/* PCIe BAR Index for NPU4 */
+#define NPU4_REG_BAR_INDEX	0
+#define NPU4_MBOX_BAR_INDEX	0
+#define NPU4_PSP_BAR_INDEX	4
+#define NPU4_SMU_BAR_INDEX	5
+#define NPU4_SRAM_BAR_INDEX	2
+/* Associated BARs and Apertures */
+#define NPU4_REG_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU4_MBOX_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU4_PSP_BAR_BASE	MMNPU_APERTURE3_BASE
+#define NPU4_SMU_BAR_BASE	MMNPU_APERTURE4_BASE
+#define NPU4_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
+
+const struct rt_config npu4_default_rt_cfg[] = {
+	{ 5, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */
+	{ 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+	{ 2, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+	{ 3, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+	{ 4, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+	{ 0 },
+};
+
+const struct dpm_clk_freq npu4_dpm_clk_table[] = {
+	{396, 792},
+	{600, 1056},
+	{792, 1152},
+	{975, 1267},
+	{975, 1267},
+	{1056, 1408},
+	{1152, 1584},
+	{1267, 1800},
+	{ 0 }
+};
+
+static const struct amdxdna_dev_priv npu4_dev_priv = {
+	.fw_path        = "amdnpu/17f0_10/npu.sbin",
+	.protocol_major = 0x6,
+	.protocol_minor = 12,
+	.rt_config	= npu4_default_rt_cfg,
+	.dpm_clk_tbl	= npu4_dpm_clk_table,
+	.col_align	= COL_ALIGN_NATURE,
+	.mbox_dev_addr  = NPU4_MBOX_BAR_BASE,
+	.mbox_size      = 0, /* Use BAR size */
+	.sram_dev_addr  = NPU4_SRAM_BAR_BASE,
+	.sram_offs      = {
+		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
+		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
+	},
+	.psp_regs_off   = {
+		DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU4_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU4_REG, MPNPU_PUB_SCRATCH3),
+		DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU4_REG, MPNPU_PUB_SCRATCH4),
+		DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU4_REG, MPNPU_PUB_SCRATCH9),
+		DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU4_PSP, MP0_C2PMSG_73),
+		DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU4_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU4_REG, MPNPU_PUB_SCRATCH3),
+	},
+	.smu_regs_off   = {
+		DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU4_SMU, MP1_C2PMSG_0),
+		DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU4_SMU, MP1_C2PMSG_60),
+		DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU4_SMU, MMNPU_APERTURE4_BASE),
+		DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU4_SMU, MP1_C2PMSG_61),
+		DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU4_SMU, MP1_C2PMSG_60),
+	},
+	.hw_ops		= {
+		.set_dpm = npu4_set_dpm,
+	},
+};
+
+const struct amdxdna_dev_info dev_npu4_info = {
+	.reg_bar           = NPU4_REG_BAR_INDEX,
+	.mbox_bar          = NPU4_MBOX_BAR_INDEX,
+	.sram_bar          = NPU4_SRAM_BAR_INDEX,
+	.psp_bar           = NPU4_PSP_BAR_INDEX,
+	.smu_bar           = NPU4_SMU_BAR_INDEX,
+	.first_col         = 0,
+	.dev_mem_buf_shift = 15, /* 32 KiB aligned */
+	.dev_mem_base      = AIE2_DEVM_BASE,
+	.dev_mem_size      = AIE2_DEVM_SIZE,
+	.vbnv              = "RyzenAI-npu4",
+	.device_type       = AMDXDNA_DEV_TYPE_KMQ,
+	.dev_priv          = &npu4_dev_priv,
+	.ops               = &aie2_ops, /* NPU4 can share NPU1's callback */
+};
diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c
new file mode 100644
index 000000000000..5f1cf83461c4
--- /dev/null
+++ b/drivers/accel/amdxdna/npu5_regs.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/sizes.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */
+#define MPNPU_PUB_SEC_INTR             0x3010060
+#define MPNPU_PUB_PWRMGMT_INTR         0x3010064
+#define MPNPU_PUB_SCRATCH0             0x301006C
+#define MPNPU_PUB_SCRATCH1             0x3010070
+#define MPNPU_PUB_SCRATCH2             0x3010074
+#define MPNPU_PUB_SCRATCH3             0x3010078
+#define MPNPU_PUB_SCRATCH4             0x301007C
+#define MPNPU_PUB_SCRATCH5             0x3010080
+#define MPNPU_PUB_SCRATCH6             0x3010084
+#define MPNPU_PUB_SCRATCH7             0x3010088
+#define MPNPU_PUB_SCRATCH8             0x301008C
+#define MPNPU_PUB_SCRATCH9             0x3010090
+#define MPNPU_PUB_SCRATCH10            0x3010094
+#define MPNPU_PUB_SCRATCH11            0x3010098
+#define MPNPU_PUB_SCRATCH12            0x301009C
+#define MPNPU_PUB_SCRATCH13            0x30100A0
+#define MPNPU_PUB_SCRATCH14            0x30100A4
+#define MPNPU_PUB_SCRATCH15            0x30100A8
+#define MP0_C2PMSG_73                  0x3810A24
+#define MP0_C2PMSG_123                 0x3810AEC
+
+#define MP1_C2PMSG_0                   0x3B10900
+#define MP1_C2PMSG_60                  0x3B109F0
+#define MP1_C2PMSG_61                  0x3B109F4
+
+#define MPNPU_SRAM_X2I_MAILBOX_0       0x3600000
+#define MPNPU_SRAM_X2I_MAILBOX_15      0x361E000
+#define MPNPU_SRAM_X2I_MAILBOX_31      0x363E000
+#define MPNPU_SRAM_I2X_MAILBOX_31      0x363F000
+
+#define MMNPU_APERTURE0_BASE           0x3000000
+#define MMNPU_APERTURE1_BASE           0x3600000
+#define MMNPU_APERTURE3_BASE           0x3810000
+#define MMNPU_APERTURE4_BASE           0x3B10000
+
+/* PCIe BAR Index for NPU5 */
+#define NPU5_REG_BAR_INDEX	0
+#define NPU5_MBOX_BAR_INDEX	0
+#define NPU5_PSP_BAR_INDEX	4
+#define NPU5_SMU_BAR_INDEX	5
+#define NPU5_SRAM_BAR_INDEX	2
+/* Associated BARs and Apertures */
+#define NPU5_REG_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU5_MBOX_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU5_PSP_BAR_BASE	MMNPU_APERTURE3_BASE
+#define NPU5_SMU_BAR_BASE	MMNPU_APERTURE4_BASE
+#define NPU5_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
+
+static const struct amdxdna_dev_priv npu5_dev_priv = {
+	.fw_path        = "amdnpu/17f0_11/npu.sbin",
+	.protocol_major = 0x6,
+	.protocol_minor = 12,
+	.rt_config	= npu4_default_rt_cfg,
+	.dpm_clk_tbl	= npu4_dpm_clk_table,
+	.col_align	= COL_ALIGN_NATURE,
+	.mbox_dev_addr  = NPU5_MBOX_BAR_BASE,
+	.mbox_size      = 0, /* Use BAR size */
+	.sram_dev_addr  = NPU5_SRAM_BAR_BASE,
+	.sram_offs      = {
+		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
+		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
+	},
+	.psp_regs_off   = {
+		DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU5_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU5_REG, MPNPU_PUB_SCRATCH3),
+		DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU5_REG, MPNPU_PUB_SCRATCH4),
+		DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU5_REG, MPNPU_PUB_SCRATCH9),
+		DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU5_PSP, MP0_C2PMSG_73),
+		DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU5_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU5_REG, MPNPU_PUB_SCRATCH3),
+	},
+	.smu_regs_off   = {
+		DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU5_SMU, MP1_C2PMSG_0),
+		DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU5_SMU, MP1_C2PMSG_60),
+		DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU5_SMU, MMNPU_APERTURE4_BASE),
+		DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU5_SMU, MP1_C2PMSG_61),
+		DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU5_SMU, MP1_C2PMSG_60),
+	},
+	.hw_ops		= {
+		.set_dpm = npu4_set_dpm,
+	},
+};
+
+const struct amdxdna_dev_info dev_npu5_info = {
+	.reg_bar           = NPU5_REG_BAR_INDEX,
+	.mbox_bar          = NPU5_MBOX_BAR_INDEX,
+	.sram_bar          = NPU5_SRAM_BAR_INDEX,
+	.psp_bar           = NPU5_PSP_BAR_INDEX,
+	.smu_bar           = NPU5_SMU_BAR_INDEX,
+	.first_col         = 0,
+	.dev_mem_buf_shift = 15, /* 32 KiB aligned */
+	.dev_mem_base      = AIE2_DEVM_BASE,
+	.dev_mem_size      = AIE2_DEVM_SIZE,
+	.vbnv              = "RyzenAI-npu5",
+	.device_type       = AMDXDNA_DEV_TYPE_KMQ,
+	.dev_priv          = &npu5_dev_priv,
+	.ops               = &aie2_ops,
+};
diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c
new file mode 100644
index 000000000000..94a7005685a7
--- /dev/null
+++ b/drivers/accel/amdxdna/npu6_regs.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
+
+#include <drm/amdxdna_accel.h>
+#include <drm/drm_device.h>
+#include <drm/gpu_scheduler.h>
+#include <linux/sizes.h>
+
+#include "aie2_pci.h"
+#include "amdxdna_mailbox.h"
+#include "amdxdna_pci_drv.h"
+
+/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */
+#define MPNPU_PUB_SEC_INTR             0x3010060
+#define MPNPU_PUB_PWRMGMT_INTR         0x3010064
+#define MPNPU_PUB_SCRATCH0             0x301006C
+#define MPNPU_PUB_SCRATCH1             0x3010070
+#define MPNPU_PUB_SCRATCH2             0x3010074
+#define MPNPU_PUB_SCRATCH3             0x3010078
+#define MPNPU_PUB_SCRATCH4             0x301007C
+#define MPNPU_PUB_SCRATCH5             0x3010080
+#define MPNPU_PUB_SCRATCH6             0x3010084
+#define MPNPU_PUB_SCRATCH7             0x3010088
+#define MPNPU_PUB_SCRATCH8             0x301008C
+#define MPNPU_PUB_SCRATCH9             0x3010090
+#define MPNPU_PUB_SCRATCH10            0x3010094
+#define MPNPU_PUB_SCRATCH11            0x3010098
+#define MPNPU_PUB_SCRATCH12            0x301009C
+#define MPNPU_PUB_SCRATCH13            0x30100A0
+#define MPNPU_PUB_SCRATCH14            0x30100A4
+#define MPNPU_PUB_SCRATCH15            0x30100A8
+#define MP0_C2PMSG_73                  0x3810A24
+#define MP0_C2PMSG_123                 0x3810AEC
+
+#define MP1_C2PMSG_0                   0x3B10900
+#define MP1_C2PMSG_60                  0x3B109F0
+#define MP1_C2PMSG_61                  0x3B109F4
+
+#define MPNPU_SRAM_X2I_MAILBOX_0       0x3600000
+#define MPNPU_SRAM_X2I_MAILBOX_15      0x361E000
+#define MPNPU_SRAM_X2I_MAILBOX_31      0x363E000
+#define MPNPU_SRAM_I2X_MAILBOX_31      0x363F000
+
+#define MMNPU_APERTURE0_BASE           0x3000000
+#define MMNPU_APERTURE1_BASE           0x3600000
+#define MMNPU_APERTURE3_BASE           0x3810000
+#define MMNPU_APERTURE4_BASE           0x3B10000
+
+/* PCIe BAR Index for NPU6 */
+#define NPU6_REG_BAR_INDEX	0
+#define NPU6_MBOX_BAR_INDEX	0
+#define NPU6_PSP_BAR_INDEX	4
+#define NPU6_SMU_BAR_INDEX	5
+#define NPU6_SRAM_BAR_INDEX	2
+/* Associated BARs and Apertures */
+#define NPU6_REG_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU6_MBOX_BAR_BASE	MMNPU_APERTURE0_BASE
+#define NPU6_PSP_BAR_BASE	MMNPU_APERTURE3_BASE
+#define NPU6_SMU_BAR_BASE	MMNPU_APERTURE4_BASE
+#define NPU6_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
+
+static const struct amdxdna_dev_priv npu6_dev_priv = {
+	.fw_path        = "amdnpu/17f0_10/npu.sbin",
+	.protocol_major = 0x6,
+	.protocol_minor = 12,
+	.rt_config	= npu4_default_rt_cfg,
+	.dpm_clk_tbl	= npu4_dpm_clk_table,
+	.col_align	= COL_ALIGN_NATURE,
+	.mbox_dev_addr  = NPU6_MBOX_BAR_BASE,
+	.mbox_size      = 0, /* Use BAR size */
+	.sram_dev_addr  = NPU6_SRAM_BAR_BASE,
+	.sram_offs      = {
+		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU6_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
+		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU6_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
+	},
+	.psp_regs_off   = {
+		DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU6_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU6_REG, MPNPU_PUB_SCRATCH3),
+		DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU6_REG, MPNPU_PUB_SCRATCH4),
+		DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU6_REG, MPNPU_PUB_SCRATCH9),
+		DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU6_PSP, MP0_C2PMSG_73),
+		DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU6_PSP, MP0_C2PMSG_123),
+		DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU6_REG, MPNPU_PUB_SCRATCH3),
+	},
+	.smu_regs_off   = {
+		DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU6_SMU, MP1_C2PMSG_0),
+		DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU6_SMU, MP1_C2PMSG_60),
+		DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU6_SMU, MMNPU_APERTURE4_BASE),
+		DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU6_SMU, MP1_C2PMSG_61),
+		DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU6_SMU, MP1_C2PMSG_60),
+	},
+	.hw_ops         = {
+		.set_dpm = npu4_set_dpm,
+	},
+
+};
+
+const struct amdxdna_dev_info dev_npu6_info = {
+	.reg_bar           = NPU6_REG_BAR_INDEX,
+	.mbox_bar          = NPU6_MBOX_BAR_INDEX,
+	.sram_bar          = NPU6_SRAM_BAR_INDEX,
+	.psp_bar           = NPU6_PSP_BAR_INDEX,
+	.smu_bar           = NPU6_SMU_BAR_INDEX,
+	.first_col         = 0,
+	.dev_mem_buf_shift = 15, /* 32 KiB aligned */
+	.dev_mem_base      = AIE2_DEVM_BASE,
+	.dev_mem_size      = AIE2_DEVM_SIZE,
+	.vbnv              = "RyzenAI-npu6",
+	.device_type       = AMDXDNA_DEV_TYPE_KMQ,
+	.dev_priv          = &npu6_dev_priv,
+	.ops               = &aie2_ops,
+};
diff --git a/drivers/accel/drm_accel.c b/drivers/accel/drm_accel.c
index 294b572a9c33..ca3357acd127 100644
--- a/drivers/accel/drm_accel.c
+++ b/drivers/accel/drm_accel.c
@@ -8,21 +8,19 @@
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
-#include <linux/idr.h>
+#include <linux/xarray.h>
 
 #include <drm/drm_accel.h>
+#include <drm/drm_auth.h>
 #include <drm/drm_debugfs.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_print.h>
 
-static DEFINE_SPINLOCK(accel_minor_lock);
-static struct idr accel_minors_idr;
+DEFINE_XARRAY_ALLOC(accel_minors_xa);
 
-static struct dentry *accel_debugfs_root;
-
-static struct device_type accel_sysfs_device_minor = {
+static const struct device_type accel_sysfs_device_minor = {
 	.name = "accel_minor"
 };
 
@@ -74,17 +72,6 @@ static const struct drm_info_list accel_debugfs_list[] = {
 #define ACCEL_DEBUGFS_ENTRIES ARRAY_SIZE(accel_debugfs_list)
 
 /**
- * accel_debugfs_init() - Initialize debugfs for device
- * @dev: Pointer to the device instance.
- *
- * This function creates a root directory for the device in debugfs.
- */
-void accel_debugfs_init(struct drm_device *dev)
-{
-	drm_debugfs_dev_init(dev, accel_debugfs_root);
-}
-
-/**
  * accel_debugfs_register() - Register debugfs for device
  * @dev: Pointer to the device instance.
  *
@@ -117,99 +104,6 @@ void accel_set_device_instance_params(struct device *kdev, int index)
 }
 
 /**
- * accel_minor_alloc() - Allocates a new accel minor
- *
- * This function access the accel minors idr and allocates from it
- * a new id to represent a new accel minor
- *
- * Return: A new id on success or error code in case idr_alloc failed
- */
-int accel_minor_alloc(void)
-{
-	unsigned long flags;
-	int r;
-
-	spin_lock_irqsave(&accel_minor_lock, flags);
-	r = idr_alloc(&accel_minors_idr, NULL, 0, ACCEL_MAX_MINORS, GFP_NOWAIT);
-	spin_unlock_irqrestore(&accel_minor_lock, flags);
-
-	return r;
-}
-
-/**
- * accel_minor_remove() - Remove an accel minor
- * @index: The minor id to remove.
- *
- * This function access the accel minors idr and removes from
- * it the member with the id that is passed to this function.
- */
-void accel_minor_remove(int index)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&accel_minor_lock, flags);
-	idr_remove(&accel_minors_idr, index);
-	spin_unlock_irqrestore(&accel_minor_lock, flags);
-}
-
-/**
- * accel_minor_replace() - Replace minor pointer in accel minors idr.
- * @minor: Pointer to the new minor.
- * @index: The minor id to replace.
- *
- * This function access the accel minors idr structure and replaces the pointer
- * that is associated with an existing id. Because the minor pointer can be
- * NULL, we need to explicitly pass the index.
- *
- * Return: 0 for success, negative value for error
- */
-void accel_minor_replace(struct drm_minor *minor, int index)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&accel_minor_lock, flags);
-	idr_replace(&accel_minors_idr, minor, index);
-	spin_unlock_irqrestore(&accel_minor_lock, flags);
-}
-
-/*
- * Looks up the given minor-ID and returns the respective DRM-minor object. The
- * refence-count of the underlying device is increased so you must release this
- * object with accel_minor_release().
- *
- * The object can be only a drm_minor that represents an accel device.
- *
- * As long as you hold this minor, it is guaranteed that the object and the
- * minor->dev pointer will stay valid! However, the device may get unplugged and
- * unregistered while you hold the minor.
- */
-static struct drm_minor *accel_minor_acquire(unsigned int minor_id)
-{
-	struct drm_minor *minor;
-	unsigned long flags;
-
-	spin_lock_irqsave(&accel_minor_lock, flags);
-	minor = idr_find(&accel_minors_idr, minor_id);
-	if (minor)
-		drm_dev_get(minor->dev);
-	spin_unlock_irqrestore(&accel_minor_lock, flags);
-
-	if (!minor) {
-		return ERR_PTR(-ENODEV);
-	} else if (drm_dev_is_unplugged(minor->dev)) {
-		drm_dev_put(minor->dev);
-		return ERR_PTR(-ENODEV);
-	}
-
-	return minor;
-}
-
-static void accel_minor_release(struct drm_minor *minor)
-{
-	drm_dev_put(minor->dev);
-}
-
-/**
  * accel_open - open method for ACCEL file
  * @inode: device inode
  * @filp: file pointer.
@@ -226,7 +120,7 @@ int accel_open(struct inode *inode, struct file *filp)
 	struct drm_minor *minor;
 	int retcode;
 
-	minor = accel_minor_acquire(iminor(inode));
+	minor = drm_minor_acquire(&accel_minors_xa, iminor(inode));
 	if (IS_ERR(minor))
 		return PTR_ERR(minor);
 
@@ -245,7 +139,7 @@ int accel_open(struct inode *inode, struct file *filp)
 
 err_undo:
 	atomic_dec(&dev->open_count);
-	accel_minor_release(minor);
+	drm_minor_release(minor);
 	return retcode;
 }
 EXPORT_SYMBOL_GPL(accel_open);
@@ -256,7 +150,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp)
 	struct drm_minor *minor;
 	int err;
 
-	minor = accel_minor_acquire(iminor(inode));
+	minor = drm_minor_acquire(&accel_minors_xa, iminor(inode));
 	if (IS_ERR(minor))
 		return PTR_ERR(minor);
 
@@ -273,7 +167,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp)
 		err = 0;
 
 out:
-	accel_minor_release(minor);
+	drm_minor_release(minor);
 
 	return err;
 }
@@ -287,25 +181,20 @@ static const struct file_operations accel_stub_fops = {
 void accel_core_exit(void)
 {
 	unregister_chrdev(ACCEL_MAJOR, "accel");
-	debugfs_remove(accel_debugfs_root);
 	accel_sysfs_destroy();
-	idr_destroy(&accel_minors_idr);
+	WARN_ON(!xa_empty(&accel_minors_xa));
 }
 
 int __init accel_core_init(void)
 {
 	int ret;
 
-	idr_init(&accel_minors_idr);
-
 	ret = accel_sysfs_init();
 	if (ret < 0) {
 		DRM_ERROR("Cannot create ACCEL class: %d\n", ret);
 		goto error;
 	}
 
-	accel_debugfs_root = debugfs_create_dir("accel", NULL);
-
 	ret = register_chrdev(ACCEL_MAJOR, "accel", &accel_stub_fops);
 	if (ret < 0)
 		DRM_ERROR("Cannot register ACCEL major: %d\n", ret);
diff --git a/drivers/accel/habanalabs/Kconfig b/drivers/accel/habanalabs/Kconfig
index be85336107f9..6d1506acbd72 100644
--- a/drivers/accel/habanalabs/Kconfig
+++ b/drivers/accel/habanalabs/Kconfig
@@ -6,7 +6,7 @@
 config DRM_ACCEL_HABANALABS
 	tristate "HabanaLabs AI accelerators"
 	depends on DRM_ACCEL
-	depends on X86_64
+	depends on X86 && X86_64
 	depends on PCI && HAS_IOMEM
 	select GENERIC_ALLOCATOR
 	select HWMON
@@ -27,3 +27,26 @@ config DRM_ACCEL_HABANALABS
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called habanalabs.
+
+if DRM_ACCEL_HABANALABS
+
+config HL_HLDIO
+	bool "Habanalabs NVMe Direct I/O (HLDIO)"
+	depends on PCI_P2PDMA
+	depends on BLOCK
+	help
+	  Enable NVMe peer-to-peer direct I/O support for Habanalabs AI
+	  accelerators.
+
+	  This allows direct data transfers between NVMe storage devices
+	  and Habanalabs accelerators without involving system memory,
+	  using PCI peer-to-peer DMA capabilities.
+
+	  Requirements:
+	  - CONFIG_PCI_P2PDMA=y
+	  - NVMe device and Habanalabs accelerator under same PCI root complex
+	  - IOMMU disabled or in passthrough mode
+	  - Hardware supporting PCI P2P DMA
+
+	  If unsure, say N
+endif # DRM_ACCEL_HABANALABS
diff --git a/drivers/accel/habanalabs/common/Makefile b/drivers/accel/habanalabs/common/Makefile
index e6abffea9f87..b6d00de09db5 100644
--- a/drivers/accel/habanalabs/common/Makefile
+++ b/drivers/accel/habanalabs/common/Makefile
@@ -13,3 +13,8 @@ HL_COMMON_FILES := common/habanalabs_drv.o common/device.o common/context.o \
 		common/command_submission.o common/firmware_if.o \
 		common/security.o common/state_dump.o \
 		common/memory_mgr.o common/decoder.o
+
+# Conditionally add HLDIO support
+ifdef CONFIG_HL_HLDIO
+HL_COMMON_FILES += common/hldio.o
+endif
\ No newline at end of file
diff --git a/drivers/accel/habanalabs/common/command_submission.c b/drivers/accel/habanalabs/common/command_submission.c
index 3aa6eeef443b..dee487724918 100644
--- a/drivers/accel/habanalabs/common/command_submission.c
+++ b/drivers/accel/habanalabs/common/command_submission.c
@@ -1360,9 +1360,8 @@ static int hl_cs_sanity_checks(struct hl_fpriv *hpriv, union hl_cs_args *args)
 			return -EINVAL;
 		}
 
-	if (!hl_device_operational(hdev, &status)) {
+	if (!hl_device_operational(hdev, &status))
 		return -EBUSY;
-	}
 
 	if ((args->in.cs_flags & HL_CS_FLAGS_STAGED_SUBMISSION) &&
 			!hdev->supports_staged_submission) {
@@ -2587,7 +2586,7 @@ int hl_cs_ioctl(struct drm_device *ddev, void *data, struct drm_file *file_priv)
 		cs_seq = args->in.seq;
 
 	timeout = flags & HL_CS_FLAGS_CUSTOM_TIMEOUT
-			? msecs_to_jiffies(args->in.timeout * 1000)
+			? secs_to_jiffies(args->in.timeout)
 			: hpriv->hdev->timeout_jiffies;
 
 	switch (cs_type) {
@@ -3285,12 +3284,6 @@ static int ts_get_and_handle_kernel_record(struct hl_device *hdev, struct hl_ctx
 
 	/* In case the node already registered, need to unregister first then re-use */
 	if (req_offset_record->ts_reg_info.in_use) {
-		dev_dbg(data->buf->mmg->dev,
-				"Requested record %p is in use on irq: %u ts addr: %p, unregister first then put on irq: %u\n",
-				req_offset_record,
-				req_offset_record->ts_reg_info.interrupt->interrupt_id,
-				req_offset_record->ts_reg_info.timestamp_kernel_addr,
-				data->interrupt->interrupt_id);
 		/*
 		 * Since interrupt here can be different than the one the node currently registered
 		 * on, and we don't want to lock two lists while we're doing unregister, so
@@ -3346,10 +3339,6 @@ static int _hl_interrupt_ts_reg_ioctl(struct hl_device *hdev, struct hl_ctx *ctx
 		goto put_cq_cb;
 	}
 
-	dev_dbg(hdev->dev, "Timestamp registration: interrupt id: %u, handle: 0x%llx, ts offset: %llu, cq_offset: %llu\n",
-					data->interrupt->interrupt_id, data->ts_handle,
-					data->ts_offset, data->cq_offset);
-
 	data->buf = hl_mmap_mem_buf_get(data->mmg, data->ts_handle);
 	if (!data->buf) {
 		rc = -EINVAL;
@@ -3371,9 +3360,6 @@ static int _hl_interrupt_ts_reg_ioctl(struct hl_device *hdev, struct hl_ctx *ctx
 	if (*pend->cq_kernel_addr >= data->target_value) {
 		spin_unlock_irqrestore(&data->interrupt->ts_list_lock, flags);
 
-		dev_dbg(hdev->dev, "Target value already reached release ts record: pend: %p, offset: %llu, interrupt: %u\n",
-				pend, data->ts_offset, data->interrupt->interrupt_id);
-
 		pend->ts_reg_info.in_use = 0;
 		*status = HL_WAIT_CS_STATUS_COMPLETED;
 		*pend->ts_reg_info.timestamp_kernel_addr = ktime_get_ns();
diff --git a/drivers/accel/habanalabs/common/context.c b/drivers/accel/habanalabs/common/context.c
index b83141f58319..9f212b17611a 100644
--- a/drivers/accel/habanalabs/common/context.c
+++ b/drivers/accel/habanalabs/common/context.c
@@ -199,7 +199,6 @@ out_err:
 
 int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 {
-	char task_comm[TASK_COMM_LEN];
 	int rc = 0, i;
 
 	ctx->hdev = hdev;
@@ -272,7 +271,7 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 		mutex_init(&ctx->ts_reg_lock);
 
 		dev_dbg(hdev->dev, "create user context, comm=\"%s\", asid=%u\n",
-			get_task_comm(task_comm, current), ctx->asid);
+			current->comm, ctx->asid);
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/common/debugfs.c b/drivers/accel/habanalabs/common/debugfs.c
index 01f071d52570..5f0820b19ccb 100644
--- a/drivers/accel/habanalabs/common/debugfs.c
+++ b/drivers/accel/habanalabs/common/debugfs.c
@@ -6,6 +6,7 @@
  */
 
 #include "habanalabs.h"
+#include "hldio.h"
 #include "../include/hw_ip/mmu/mmu_general.h"
 
 #include <linux/pci.h>
@@ -42,9 +43,8 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 	pkt.i2c_reg = i2c_reg;
 	pkt.i2c_len = i2c_len;
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, val);
-	if (rc)
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, val);
+	if (rc && rc != -EAGAIN)
 		dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc);
 
 	return rc;
@@ -75,10 +75,8 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 	pkt.i2c_len = i2c_len;
 	pkt.value = cpu_to_le64(val);
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, NULL);
-
-	if (rc)
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	if (rc && rc != -EAGAIN)
 		dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc);
 
 	return rc;
@@ -99,10 +97,8 @@ static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state)
 	pkt.led_index = cpu_to_le32(led);
 	pkt.value = cpu_to_le64(state);
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, NULL);
-
-	if (rc)
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	if (rc && rc != -EAGAIN)
 		dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc);
 }
 
@@ -484,7 +480,7 @@ static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf,
 	struct hl_debugfs_entry *entry = s->private;
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
-	char kbuf[MMU_KBUF_SIZE];
+	char kbuf[MMU_KBUF_SIZE] = {0};
 	char *c;
 	ssize_t rc;
 
@@ -546,7 +542,7 @@ static ssize_t mmu_ack_error_value_write(struct file *file,
 	struct hl_debugfs_entry *entry = s->private;
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
-	char kbuf[MMU_KBUF_SIZE];
+	char kbuf[MMU_KBUF_SIZE] = {0};
 	ssize_t rc;
 
 	if (count > sizeof(kbuf) - 1)
@@ -607,6 +603,198 @@ static int engines_show(struct seq_file *s, void *data)
 	return 0;
 }
 
+#ifdef CONFIG_HL_HLDIO
+/* DIO debugfs functions following the standard pattern */
+static int dio_ssd2hl_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+
+	if (!hdev->asic_prop.supports_nvme) {
+		seq_puts(s, "NVMe Direct I/O not supported\\n");
+		return 0;
+	}
+
+	seq_puts(s, "Usage: echo \"fd=N va=0xADDR off=N len=N\" > dio_ssd2hl\n");
+	seq_printf(s, "Last transfer: %zu bytes\\n", dev_entry->dio_stats.last_len_read);
+	seq_puts(s, "Note: All parameters must be page-aligned (4KB)\\n");
+
+	return 0;
+}
+
+static ssize_t dio_ssd2hl_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *f_pos)
+{
+	struct seq_file *s = file->private_data;
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+	struct hl_ctx *ctx = hdev->kernel_ctx;
+	char kbuf[128];
+	u64 device_va = 0, off_bytes = 0, len_bytes = 0;
+	u32 fd = 0;
+	size_t len_read = 0;
+	int rc, parsed;
+
+	if (!hdev->asic_prop.supports_nvme)
+		return -EOPNOTSUPP;
+
+	if (count >= sizeof(kbuf))
+		return -EINVAL;
+
+	if (copy_from_user(kbuf, buf, count))
+		return -EFAULT;
+
+	kbuf[count] = 0;
+
+	/* Parse: fd=N va=0xADDR off=N len=N */
+	parsed = sscanf(kbuf, "fd=%u va=0x%llx off=%llu len=%llu",
+			&fd, &device_va, &off_bytes, &len_bytes);
+	if (parsed != 4) {
+		dev_err(hdev->dev, "Invalid format. Expected: fd=N va=0xADDR off=N len=N\\n");
+		return -EINVAL;
+	}
+
+	/* Validate file descriptor */
+	if (fd == 0) {
+		dev_err(hdev->dev, "Invalid file descriptor: %u\\n", fd);
+		return -EINVAL;
+	}
+
+	/* Validate alignment requirements */
+	if (!IS_ALIGNED(device_va, PAGE_SIZE) ||
+	    !IS_ALIGNED(off_bytes, PAGE_SIZE) ||
+	    !IS_ALIGNED(len_bytes, PAGE_SIZE)) {
+		dev_err(hdev->dev,
+			"All parameters must be page-aligned (4KB)\\n");
+		return -EINVAL;
+	}
+
+	/* Validate transfer size */
+	if (len_bytes == 0 || len_bytes > SZ_1G) {
+		dev_err(hdev->dev, "Invalid length: %llu (max 1GB)\\n",
+			len_bytes);
+		return -EINVAL;
+	}
+
+	dev_dbg(hdev->dev, "DIO SSD2HL: fd=%u va=0x%llx off=%llu len=%llu\\n",
+		fd, device_va, off_bytes, len_bytes);
+
+	rc = hl_dio_ssd2hl(hdev, ctx, fd, device_va, off_bytes, len_bytes, &len_read);
+	if (rc < 0) {
+		dev_entry->dio_stats.failed_ops++;
+		dev_err(hdev->dev, "SSD2HL operation failed: %d\\n", rc);
+		return rc;
+	}
+
+	/* Update statistics */
+	dev_entry->dio_stats.total_ops++;
+	dev_entry->dio_stats.successful_ops++;
+	dev_entry->dio_stats.bytes_transferred += len_read;
+	dev_entry->dio_stats.last_len_read = len_read;
+
+	dev_dbg(hdev->dev, "DIO SSD2HL completed: %zu bytes transferred\\n", len_read);
+
+	return count;
+}
+
+static int dio_hl2ssd_show(struct seq_file *s, void *data)
+{
+	seq_puts(s, "HL2SSD (device-to-SSD) transfers not implemented\\n");
+	return 0;
+}
+
+static ssize_t dio_hl2ssd_write(struct file *file, const char __user *buf,
+			       size_t count, loff_t *f_pos)
+{
+	struct seq_file *s = file->private_data;
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+
+	if (!hdev->asic_prop.supports_nvme)
+		return -EOPNOTSUPP;
+
+	dev_dbg(hdev->dev, "HL2SSD operation not implemented\\n");
+	return -EOPNOTSUPP;
+}
+
+static int dio_stats_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+	struct hl_dio_stats *stats = &dev_entry->dio_stats;
+	u64 avg_bytes_per_op = 0, success_rate = 0;
+
+	if (!hdev->asic_prop.supports_nvme) {
+		seq_puts(s, "NVMe Direct I/O not supported\\n");
+		return 0;
+	}
+
+	if (stats->successful_ops > 0)
+		avg_bytes_per_op = stats->bytes_transferred / stats->successful_ops;
+
+	if (stats->total_ops > 0)
+		success_rate = (stats->successful_ops * 100) / stats->total_ops;
+
+	seq_puts(s, "=== Habanalabs Direct I/O Statistics ===\\n");
+	seq_printf(s, "Total operations:     %llu\\n", stats->total_ops);
+	seq_printf(s, "Successful ops:       %llu\\n", stats->successful_ops);
+	seq_printf(s, "Failed ops:           %llu\\n", stats->failed_ops);
+	seq_printf(s, "Success rate:         %llu%%\\n", success_rate);
+	seq_printf(s, "Total bytes:          %llu\\n", stats->bytes_transferred);
+	seq_printf(s, "Avg bytes per op:     %llu\\n", avg_bytes_per_op);
+	seq_printf(s, "Last transfer:        %zu bytes\\n", stats->last_len_read);
+
+	return 0;
+}
+
+static int dio_reset_show(struct seq_file *s, void *data)
+{
+	seq_puts(s, "Write '1' to reset DIO statistics\\n");
+	return 0;
+}
+
+static ssize_t dio_reset_write(struct file *file, const char __user *buf,
+			       size_t count, loff_t *f_pos)
+{
+	struct seq_file *s = file->private_data;
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+	char kbuf[8];
+	unsigned long val;
+	int rc;
+
+	if (!hdev->asic_prop.supports_nvme)
+		return -EOPNOTSUPP;
+
+	if (count >= sizeof(kbuf))
+		return -EINVAL;
+
+	if (copy_from_user(kbuf, buf, count))
+		return -EFAULT;
+
+	kbuf[count] = 0;
+
+	rc = kstrtoul(kbuf, 0, &val);
+	if (rc)
+		return rc;
+
+	if (val == 1) {
+		memset(&dev_entry->dio_stats, 0, sizeof(dev_entry->dio_stats));
+		dev_dbg(hdev->dev, "DIO statistics reset\\n");
+	} else {
+		dev_err(hdev->dev, "Write '1' to reset statistics\\n");
+		return -EINVAL;
+	}
+
+	return count;
+}
+#endif
+
 static ssize_t hl_memory_scrub(struct file *f, const char __user *buf,
 					size_t count, loff_t *ppos)
 {
@@ -793,6 +981,113 @@ static void hl_access_host_mem(struct hl_device *hdev, u64 addr, u64 *val,
 	}
 }
 
+static void dump_cfg_access_entry(struct hl_device *hdev,
+				  struct hl_debugfs_cfg_access_entry *entry)
+{
+	char *access_type = "";
+	struct tm tm;
+
+	switch (entry->debugfs_type) {
+	case DEBUGFS_READ32:
+		access_type = "READ32 from";
+		break;
+	case DEBUGFS_WRITE32:
+		access_type = "WRITE32 to";
+		break;
+	case DEBUGFS_READ64:
+		access_type = "READ64 from";
+		break;
+	case DEBUGFS_WRITE64:
+		access_type = "WRITE64 to";
+		break;
+	default:
+		dev_err(hdev->dev, "Invalid DEBUGFS access type (%u)\n", entry->debugfs_type);
+		return;
+	}
+
+	time64_to_tm(entry->seconds_since_epoch, 0, &tm);
+	dev_info(hdev->dev,
+		"%ld-%02d-%02d %02d:%02d:%02d (UTC): %s %#llx\n", tm.tm_year + 1900, tm.tm_mon + 1,
+		tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, access_type, entry->addr);
+}
+
+void hl_debugfs_cfg_access_history_dump(struct hl_device *hdev)
+{
+	struct hl_debugfs_cfg_access *dbgfs = &hdev->debugfs_cfg_accesses;
+	u32 i, head, count = 0;
+	time64_t entry_time, now;
+	unsigned long flags;
+
+	now = ktime_get_real_seconds();
+
+	spin_lock_irqsave(&dbgfs->lock, flags);
+	head = dbgfs->head;
+	if (head == 0)
+		i = HL_DBGFS_CFG_ACCESS_HIST_LEN - 1;
+	else
+		i = head - 1;
+
+	/* Walk back until timeout or invalid entry */
+	while (dbgfs->cfg_access_list[i].valid) {
+		entry_time = dbgfs->cfg_access_list[i].seconds_since_epoch;
+		/* Stop when entry is older than timeout */
+		if (now - entry_time > HL_DBGFS_CFG_ACCESS_HIST_TIMEOUT_SEC)
+			break;
+
+		/* print single entry under lock */
+		{
+			struct hl_debugfs_cfg_access_entry entry = dbgfs->cfg_access_list[i];
+			/*
+			 * We copy the entry out under lock and then print after
+			 * releasing the lock to minimize time under lock.
+			 */
+			spin_unlock_irqrestore(&dbgfs->lock, flags);
+			dump_cfg_access_entry(hdev, &entry);
+			spin_lock_irqsave(&dbgfs->lock, flags);
+		}
+
+		/* mark consumed */
+		dbgfs->cfg_access_list[i].valid = false;
+
+		if (i == 0)
+			i = HL_DBGFS_CFG_ACCESS_HIST_LEN - 1;
+		else
+			i--;
+		count++;
+		if (count >= HL_DBGFS_CFG_ACCESS_HIST_LEN)
+			break;
+	}
+	spin_unlock_irqrestore(&dbgfs->lock, flags);
+}
+
+static void check_if_cfg_access_and_log(struct hl_device *hdev, u64 addr, size_t access_size,
+					enum debugfs_access_type access_type)
+{
+	struct hl_debugfs_cfg_access *dbgfs_cfg_accesses = &hdev->debugfs_cfg_accesses;
+	struct pci_mem_region *mem_reg = &hdev->pci_mem_region[PCI_REGION_CFG];
+	struct hl_debugfs_cfg_access_entry *new_entry;
+	unsigned long flags;
+
+	/* Check if address is in config memory */
+	if (addr >= mem_reg->region_base &&
+		mem_reg->region_size >= access_size &&
+		addr <= mem_reg->region_base + mem_reg->region_size - access_size) {
+
+		spin_lock_irqsave(&dbgfs_cfg_accesses->lock, flags);
+
+		new_entry = &dbgfs_cfg_accesses->cfg_access_list[dbgfs_cfg_accesses->head];
+		new_entry->seconds_since_epoch = ktime_get_real_seconds();
+		new_entry->addr = addr;
+		new_entry->debugfs_type = access_type;
+		new_entry->valid = true;
+		dbgfs_cfg_accesses->head = (dbgfs_cfg_accesses->head + 1)
+						% HL_DBGFS_CFG_ACCESS_HIST_LEN;
+
+		spin_unlock_irqrestore(&dbgfs_cfg_accesses->lock, flags);
+
+	}
+}
+
 static int hl_access_mem(struct hl_device *hdev, u64 addr, u64 *val,
 				enum debugfs_access_type acc_type)
 {
@@ -810,6 +1105,7 @@ static int hl_access_mem(struct hl_device *hdev, u64 addr, u64 *val,
 			return rc;
 	}
 
+	check_if_cfg_access_and_log(hdev, addr, acc_size, acc_type);
 	rc = hl_access_dev_mem_by_region(hdev, addr, val, acc_type, &found);
 	if (rc) {
 		dev_err(hdev->dev,
@@ -1408,7 +1704,7 @@ static ssize_t hl_timeout_locked_write(struct file *f, const char __user *buf,
 		return rc;
 
 	if (value)
-		hdev->timeout_jiffies = msecs_to_jiffies(value * 1000);
+		hdev->timeout_jiffies = secs_to_jiffies(value);
 	else
 		hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT;
 
@@ -1530,6 +1826,13 @@ static const struct hl_info_list hl_debugfs_list[] = {
 	{"mmu", mmu_show, mmu_asid_va_write},
 	{"mmu_error", mmu_ack_error, mmu_ack_error_value_write},
 	{"engines", engines_show, NULL},
+#ifdef CONFIG_HL_HLDIO
+	/* DIO entries - only created if NVMe is supported */
+	{"dio_ssd2hl", dio_ssd2hl_show, dio_ssd2hl_write},
+	{"dio_stats", dio_stats_show, NULL},
+	{"dio_reset", dio_reset_show, dio_reset_write},
+	{"dio_hl2ssd", dio_hl2ssd_show, dio_hl2ssd_write},
+#endif
 };
 
 static int hl_debugfs_open(struct inode *inode, struct file *file)
@@ -1643,19 +1946,19 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 				&hl_data64b_fops);
 
 	debugfs_create_file("set_power_state",
-				0200,
+				0644,
 				root,
 				dev_entry,
 				&hl_power_fops);
 
 	debugfs_create_file("device",
-				0200,
+				0644,
 				root,
 				dev_entry,
 				&hl_device_fops);
 
 	debugfs_create_file("clk_gate",
-				0200,
+				0644,
 				root,
 				dev_entry,
 				&hl_clk_gate_fops);
@@ -1667,13 +1970,13 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 				&hl_stop_on_err_fops);
 
 	debugfs_create_file("dump_security_violations",
-				0644,
+				0400,
 				root,
 				dev_entry,
 				&hl_security_violations_fops);
 
 	debugfs_create_file("dump_razwi_events",
-				0644,
+				0400,
 				root,
 				dev_entry,
 				&hl_razwi_check_fops);
@@ -1706,7 +2009,7 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 				&hdev->reset_info.skip_reset_on_timeout);
 
 	debugfs_create_file("state_dump",
-				0600,
+				0644,
 				root,
 				dev_entry,
 				&hl_state_dump_fops);
@@ -1722,9 +2025,19 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 				root,
 				&hdev->device_release_watchdog_timeout_sec);
 
+	debugfs_create_u16("server_type",
+				0444,
+				root,
+				&hdev->asic_prop.server_type);
+
 	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
+		/* Skip DIO entries if NVMe is not supported */
+		if (strncmp(hl_debugfs_list[i].name, "dio_", 4) == 0 &&
+		    !hdev->asic_prop.supports_nvme)
+			continue;
+
 		debugfs_create_file(hl_debugfs_list[i].name,
-					0444,
+					0644,
 					root,
 					entry,
 					&hl_debugfs_fops);
@@ -1762,6 +2075,14 @@ int hl_debugfs_device_init(struct hl_device *hdev)
 	spin_lock_init(&dev_entry->userptr_spinlock);
 	mutex_init(&dev_entry->ctx_mem_hash_mutex);
 
+	spin_lock_init(&hdev->debugfs_cfg_accesses.lock);
+	hdev->debugfs_cfg_accesses.head = 0; /* already zero by alloc but explicit init is fine */
+
+#ifdef CONFIG_HL_HLDIO
+	/* Initialize DIO statistics */
+	memset(&dev_entry->dio_stats, 0, sizeof(dev_entry->dio_stats));
+#endif
+
 	return 0;
 }
 
@@ -1780,6 +2101,7 @@ void hl_debugfs_device_fini(struct hl_device *hdev)
 		vfree(entry->state_dump[i]);
 
 	kfree(entry->entry_arr);
+
 }
 
 void hl_debugfs_add_device(struct hl_device *hdev)
@@ -1792,6 +2114,7 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 
 	if (!hdev->asic_prop.fw_security_enabled)
 		add_secured_nodes(dev_entry, dev_entry->root);
+
 }
 
 void hl_debugfs_add_file(struct hl_fpriv *hpriv)
@@ -1924,3 +2247,4 @@ void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
 
 	up_write(&dev_entry->state_dump_sem);
 }
+
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9711e8fc979d..999c92d7036e 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -30,6 +30,8 @@ enum dma_alloc_type {
 
 #define MEM_SCRUB_DEFAULT_VAL 0x1122334455667788
 
+static void hl_device_heartbeat(struct work_struct *work);
+
 /*
  * hl_set_dram_bar- sets the bar to allow later access to address
  *
@@ -55,7 +57,8 @@ static u64 hl_set_dram_bar(struct hl_device *hdev, u64 addr, struct pci_mem_regi
 	if (is_power_of_2(prop->dram_pci_bar_size))
 		bar_base_addr = addr & ~(prop->dram_pci_bar_size - 0x1ull);
 	else
-		bar_base_addr = DIV_ROUND_DOWN_ULL(addr, prop->dram_pci_bar_size) *
+		bar_base_addr = region->region_base +
+				div64_u64((addr - region->region_base), prop->dram_pci_bar_size) *
 				prop->dram_pci_bar_size;
 
 	old_base = hdev->asic_funcs->set_dram_bar_base(hdev, bar_base_addr);
@@ -129,8 +132,8 @@ static void *hl_dma_alloc_common(struct hl_device *hdev, size_t size, dma_addr_t
 	}
 
 	if (trace_habanalabs_dma_alloc_enabled() && !ZERO_OR_NULL_PTR(ptr))
-		trace_habanalabs_dma_alloc(hdev->dev, (u64) (uintptr_t) ptr, *dma_handle, size,
-						caller);
+		trace_habanalabs_dma_alloc(&(hdev)->pdev->dev, (u64) (uintptr_t) ptr, *dma_handle,
+						size, caller);
 
 	return ptr;
 }
@@ -151,7 +154,7 @@ static void hl_asic_dma_free_common(struct hl_device *hdev, size_t size, void *c
 		break;
 	}
 
-	trace_habanalabs_dma_free(hdev->dev, store_cpu_addr, dma_handle, size, caller);
+	trace_habanalabs_dma_free(&(hdev)->pdev->dev, store_cpu_addr, dma_handle, size, caller);
 }
 
 void *hl_asic_dma_alloc_coherent_caller(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle,
@@ -203,15 +206,15 @@ int hl_dma_map_sgtable_caller(struct hl_device *hdev, struct sg_table *sgt,
 		return 0;
 
 	for_each_sgtable_dma_sg(sgt, sg, i)
-		trace_habanalabs_dma_map_page(hdev->dev,
-				page_to_phys(sg_page(sg)),
-				sg->dma_address - prop->device_dma_offset_for_host_access,
+		trace_habanalabs_dma_map_page(&(hdev)->pdev->dev,
+					page_to_phys(sg_page(sg)),
+					sg->dma_address - prop->device_dma_offset_for_host_access,
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
-				sg->dma_length,
+					sg->dma_length,
 #else
-				sg->length,
+					sg->length,
 #endif
-				dir, caller);
+					dir, caller);
 
 	return 0;
 }
@@ -246,7 +249,8 @@ void hl_dma_unmap_sgtable_caller(struct hl_device *hdev, struct sg_table *sgt,
 
 	if (trace_habanalabs_dma_unmap_page_enabled()) {
 		for_each_sgtable_dma_sg(sgt, sg, i)
-			trace_habanalabs_dma_unmap_page(hdev->dev, page_to_phys(sg_page(sg)),
+			trace_habanalabs_dma_unmap_page(&(hdev)->pdev->dev,
+					page_to_phys(sg_page(sg)),
 					sg->dma_address - prop->device_dma_offset_for_host_access,
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 					sg->dma_length,
@@ -438,16 +442,19 @@ static void print_idle_status_mask(struct hl_device *hdev, const char *message,
 					u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE])
 {
 	if (idle_mask[3])
-		dev_err(hdev->dev, "%s (mask %#llx_%016llx_%016llx_%016llx)\n",
-			message, idle_mask[3], idle_mask[2], idle_mask[1], idle_mask[0]);
+		dev_err(hdev->dev, "%s %s (mask %#llx_%016llx_%016llx_%016llx)\n",
+			dev_name(&hdev->pdev->dev), message,
+			idle_mask[3], idle_mask[2], idle_mask[1], idle_mask[0]);
 	else if (idle_mask[2])
-		dev_err(hdev->dev, "%s (mask %#llx_%016llx_%016llx)\n",
-			message, idle_mask[2], idle_mask[1], idle_mask[0]);
+		dev_err(hdev->dev, "%s %s (mask %#llx_%016llx_%016llx)\n",
+			dev_name(&hdev->pdev->dev), message,
+			idle_mask[2], idle_mask[1], idle_mask[0]);
 	else if (idle_mask[1])
-		dev_err(hdev->dev, "%s (mask %#llx_%016llx)\n",
-			message, idle_mask[1], idle_mask[0]);
+		dev_err(hdev->dev, "%s %s (mask %#llx_%016llx)\n",
+			dev_name(&hdev->pdev->dev), message, idle_mask[1], idle_mask[0]);
 	else
-		dev_err(hdev->dev, "%s (mask %#llx)\n", message, idle_mask[0]);
+		dev_err(hdev->dev, "%s %s (mask %#llx)\n", dev_name(&hdev->pdev->dev), message,
+			idle_mask[0]);
 }
 
 static void hpriv_release(struct kref *ref)
@@ -544,7 +551,8 @@ int hl_hpriv_put(struct hl_fpriv *hpriv)
 	return kref_put(&hpriv->refcount, hpriv_release);
 }
 
-static void print_device_in_use_info(struct hl_device *hdev, const char *message)
+static void print_device_in_use_info(struct hl_device *hdev,
+		struct hl_mem_mgr_fini_stats *mm_fini_stats, const char *message)
 {
 	u32 active_cs_num, dmabuf_export_cnt;
 	bool unknown_reason = true;
@@ -568,6 +576,12 @@ static void print_device_in_use_info(struct hl_device *hdev, const char *message
 					dmabuf_export_cnt);
 	}
 
+	if (mm_fini_stats->n_busy_cb) {
+		unknown_reason = false;
+		offset += scnprintf(buf + offset, size - offset, " [%u live CB handles]",
+				mm_fini_stats->n_busy_cb);
+	}
+
 	if (unknown_reason)
 		scnprintf(buf + offset, size - offset, " [unknown reason]");
 
@@ -585,6 +599,7 @@ void hl_device_release(struct drm_device *ddev, struct drm_file *file_priv)
 {
 	struct hl_fpriv *hpriv = file_priv->driver_priv;
 	struct hl_device *hdev = to_hl_device(ddev);
+	struct hl_mem_mgr_fini_stats mm_fini_stats;
 
 	if (!hdev) {
 		pr_crit("Closing FD after device was removed. Memory leak will occur and it is advised to reboot.\n");
@@ -596,12 +611,13 @@ void hl_device_release(struct drm_device *ddev, struct drm_file *file_priv)
 	/* Memory buffers might be still in use at this point and thus the handles IDR destruction
 	 * is postponed to hpriv_release().
 	 */
-	hl_mem_mgr_fini(&hpriv->mem_mgr);
+	hl_mem_mgr_fini(&hpriv->mem_mgr, &mm_fini_stats);
 
 	hdev->compute_ctx_in_release = 1;
 
 	if (!hl_hpriv_put(hpriv)) {
-		print_device_in_use_info(hdev, "User process closed FD but device still in use");
+		print_device_in_use_info(hdev, &mm_fini_stats,
+				"User process closed FD but device still in use");
 		hl_device_reset(hdev, HL_DRV_RESET_HARD);
 	}
 
@@ -801,7 +817,7 @@ static void device_hard_reset_pending(struct work_struct *work)
 		}
 
 		queue_delayed_work(hdev->reset_wq, &device_reset_work->reset_work,
-					msecs_to_jiffies(HL_PENDING_RESET_PER_SEC * 1000));
+					secs_to_jiffies(HL_PENDING_RESET_PER_SEC));
 	}
 }
 
@@ -853,6 +869,13 @@ static int device_early_init(struct hl_device *hdev)
 		gaudi2_set_asic_funcs(hdev);
 		strscpy(hdev->asic_name, "GAUDI2B", sizeof(hdev->asic_name));
 		break;
+	case ASIC_GAUDI2C:
+		gaudi2_set_asic_funcs(hdev);
+		strscpy(hdev->asic_name, "GAUDI2C", sizeof(hdev->asic_name));
+		break;
+	case ASIC_GAUDI2D:
+		gaudi2_set_asic_funcs(hdev);
+		strscpy(hdev->asic_name, "GAUDI2D", sizeof(hdev->asic_name));
 		break;
 	default:
 		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
@@ -942,6 +965,8 @@ static int device_early_init(struct hl_device *hdev)
 		goto free_cb_mgr;
 	}
 
+	INIT_DELAYED_WORK(&hdev->work_heartbeat, hl_device_heartbeat);
+
 	INIT_DELAYED_WORK(&hdev->device_reset_work.reset_work, device_hard_reset_pending);
 	hdev->device_reset_work.hdev = hdev;
 	hdev->device_fini_pending = 0;
@@ -964,7 +989,7 @@ static int device_early_init(struct hl_device *hdev)
 	return 0;
 
 free_cb_mgr:
-	hl_mem_mgr_fini(&hdev->kernel_mem_mgr);
+	hl_mem_mgr_fini(&hdev->kernel_mem_mgr, NULL);
 	hl_mem_mgr_idr_destroy(&hdev->kernel_mem_mgr);
 free_chip_info:
 	kfree(hdev->hl_chip_info);
@@ -1008,7 +1033,7 @@ static void device_early_fini(struct hl_device *hdev)
 
 	mutex_destroy(&hdev->clk_throttling.lock);
 
-	hl_mem_mgr_fini(&hdev->kernel_mem_mgr);
+	hl_mem_mgr_fini(&hdev->kernel_mem_mgr, NULL);
 	hl_mem_mgr_idr_destroy(&hdev->kernel_mem_mgr);
 
 	kfree(hdev->hl_chip_info);
@@ -1031,28 +1056,46 @@ static void device_early_fini(struct hl_device *hdev)
 
 static bool is_pci_link_healthy(struct hl_device *hdev)
 {
-	u16 vendor_id;
+	u16 device_id;
 
 	if (!hdev->pdev)
 		return false;
 
-	pci_read_config_word(hdev->pdev, PCI_VENDOR_ID, &vendor_id);
+	pci_read_config_word(hdev->pdev, PCI_DEVICE_ID, &device_id);
 
-	return (vendor_id == PCI_VENDOR_ID_HABANALABS);
+	return (device_id == hdev->pdev->device);
 }
 
-static void hl_device_eq_heartbeat(struct hl_device *hdev)
+static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 {
-	u64 event_mask = HL_NOTIFIER_EVENT_DEVICE_RESET | HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
+	struct eq_heartbeat_debug_info *heartbeat_debug_info = &hdev->heartbeat_debug_info;
+	u32 cpu_q_id = heartbeat_debug_info->cpu_queue_id, pq_pi_mask = (HL_QUEUE_LENGTH << 1) - 1;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
 	if (!prop->cpucp_info.eq_health_check_supported)
-		return;
+		return true;
 
-	if (hdev->eq_heartbeat_received)
-		hdev->eq_heartbeat_received = false;
-	else
-		hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask);
+	if (!hdev->eq_heartbeat_received) {
+		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
+
+		dev_err(hdev->dev,
+			"EQ: {CI %u, HB counter %u, last HB time: %ptTs}, PQ: {PI: %u, CI: %u (%u), last HB time: %ptTs}\n",
+			hdev->event_queue.ci,
+			heartbeat_debug_info->heartbeat_event_counter,
+			&hdev->heartbeat_debug_info.last_eq_heartbeat_ts,
+			hdev->kernel_queues[cpu_q_id].pi,
+			atomic_read(&hdev->kernel_queues[cpu_q_id].ci),
+			atomic_read(&hdev->kernel_queues[cpu_q_id].ci) & pq_pi_mask,
+			&hdev->heartbeat_debug_info.last_pq_heartbeat_ts);
+
+		hl_eq_dump(hdev, &hdev->event_queue);
+
+		return false;
+	}
+
+	hdev->eq_heartbeat_received = false;
+
+	return true;
 }
 
 static void hl_device_heartbeat(struct work_struct *work)
@@ -1069,10 +1112,9 @@ static void hl_device_heartbeat(struct work_struct *work)
 	/*
 	 * For EQ health check need to check if driver received the heartbeat eq event
 	 * in order to validate the eq is working.
+	 * Only if both the EQ is healthy and we managed to send the next heartbeat reschedule.
 	 */
-	hl_device_eq_heartbeat(hdev);
-
-	if (!hdev->asic_funcs->send_heartbeat(hdev))
+	if (hl_device_eq_heartbeat_received(hdev) && (!hdev->asic_funcs->send_heartbeat(hdev)))
 		goto reschedule;
 
 	if (hl_device_operational(hdev, NULL))
@@ -1126,21 +1168,6 @@ static int device_late_init(struct hl_device *hdev)
 	}
 
 	hdev->high_pll = hdev->asic_prop.high_pll;
-
-	if (hdev->heartbeat) {
-		/*
-		 * Before scheduling the heartbeat driver will check if eq event has received.
-		 * for the first schedule we need to set the indication as true then for the next
-		 * one this indication will be true only if eq event was sent by FW.
-		 */
-		hdev->eq_heartbeat_received = true;
-
-		INIT_DELAYED_WORK(&hdev->work_heartbeat, hl_device_heartbeat);
-
-		schedule_delayed_work(&hdev->work_heartbeat,
-				usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
-	}
-
 	hdev->late_init_done = true;
 
 	return 0;
@@ -1157,9 +1184,6 @@ static void device_late_fini(struct hl_device *hdev)
 	if (!hdev->late_init_done)
 		return;
 
-	if (hdev->heartbeat)
-		cancel_delayed_work_sync(&hdev->work_heartbeat);
-
 	if (hdev->asic_funcs->late_fini)
 		hdev->asic_funcs->late_fini(hdev);
 
@@ -1260,8 +1284,12 @@ static void hl_abort_waiting_for_completions(struct hl_device *hdev)
 static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset,
 				bool skip_wq_flush)
 {
-	if (hard_reset)
+	if (hard_reset) {
+		if (hdev->heartbeat)
+			cancel_delayed_work_sync(&hdev->work_heartbeat);
+
 		device_late_fini(hdev);
+	}
 
 	/*
 	 * Halt the engines and disable interrupts so we won't get any more
@@ -1489,15 +1517,14 @@ static void send_disable_pci_access(struct hl_device *hdev, u32 flags)
 		 * of heartbeat, the device CPU is marked as disable
 		 * so this message won't be sent
 		 */
-		if (hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0)) {
-			dev_warn(hdev->dev, "Failed to disable FW's PCI access\n");
+		if (hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0))
 			return;
-		}
 
-		/* verify that last EQs are handled before disabled is set */
+		/* disable_irq also generates sync irq, this verifies that last EQs are handled
+		 * before disabled is set. The IRQ will be enabled again in request_irq call.
+		 */
 		if (hdev->cpu_queues_enable)
-			synchronize_irq(pci_irq_vector(hdev->pdev,
-					hdev->asic_prop.eq_interrupt_id));
+			disable_irq(pci_irq_vector(hdev->pdev, hdev->asic_prop.eq_interrupt_id));
 	}
 }
 
@@ -1541,6 +1568,31 @@ static void handle_reset_trigger(struct hl_device *hdev, u32 flags)
 	}
 }
 
+static void reset_heartbeat_debug_info(struct hl_device *hdev)
+{
+	hdev->heartbeat_debug_info.last_pq_heartbeat_ts = 0;
+	hdev->heartbeat_debug_info.last_eq_heartbeat_ts = 0;
+	hdev->heartbeat_debug_info.heartbeat_event_counter = 0;
+}
+
+static inline void device_heartbeat_schedule(struct hl_device *hdev)
+{
+	if (!hdev->heartbeat)
+		return;
+
+	reset_heartbeat_debug_info(hdev);
+
+	/*
+	 * Before scheduling the heartbeat driver will check if eq event has received.
+	 * for the first schedule we need to set the indication as true then for the next
+	 * one this indication will be true only if eq event was sent by FW.
+	 */
+	hdev->eq_heartbeat_received = true;
+
+	schedule_delayed_work(&hdev->work_heartbeat,
+			usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
+}
+
 /*
  * hl_device_reset - reset the device
  *
@@ -1578,6 +1630,11 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 	from_watchdog_thread = !!(flags & HL_DRV_RESET_FROM_WD_THR);
 	reset_upon_device_release = hdev->reset_upon_device_release && from_dev_release;
 
+	if (hdev->cpld_shutdown) {
+		dev_err(hdev->dev, "Cannot reset device, cpld is shutdown! Device is NOT usable\n");
+		return -EIO;
+	}
+
 	if (!hard_reset && (hl_device_status(hdev) == HL_DEVICE_STATUS_MALFUNCTION)) {
 		dev_dbg(hdev->dev, "soft-reset isn't supported on a malfunctioning device\n");
 		return 0;
@@ -1763,14 +1820,16 @@ kill_processes:
 		hdev->device_cpu_disabled = false;
 		hdev->reset_info.hard_reset_pending = false;
 
+		/*
+		 * Put the device in an unusable state if there are 2 back to back resets due to
+		 * fatal errors.
+		 */
 		if (hdev->reset_info.reset_trigger_repeated &&
-				(hdev->reset_info.prev_reset_trigger ==
-						HL_DRV_RESET_FW_FATAL_ERR)) {
-			/* if there 2 back to back resets from FW,
-			 * ensure driver puts the driver in a unusable state
-			 */
+				(hdev->reset_info.prev_reset_trigger == HL_DRV_RESET_FW_FATAL_ERR ||
+						hdev->reset_info.prev_reset_trigger ==
+								HL_DRV_RESET_HEARTBEAT)) {
 			dev_crit(hdev->dev,
-				"%s Consecutive FW fatal errors received, stopping hard reset\n",
+				"%s Consecutive fatal errors, stopping hard reset\n",
 				dev_name(&(hdev)->pdev->dev));
 			rc = -EIO;
 			goto out_err;
@@ -1908,6 +1967,8 @@ kill_processes:
 	if (hard_reset) {
 		hdev->reset_info.hard_reset_cnt++;
 
+		device_heartbeat_schedule(hdev);
+
 		/* After reset is done, we are ready to receive events from
 		 * the F/W. We can't do it before because we will ignore events
 		 * and if those events are fatal, we won't know about it and
@@ -2016,7 +2077,7 @@ int hl_device_cond_reset(struct hl_device *hdev, u32 flags, u64 event_mask)
 	dev_dbg(hdev->dev, "Device is going to be hard-reset in %u sec unless being released\n",
 		hdev->device_release_watchdog_timeout_sec);
 	schedule_delayed_work(&hdev->device_release_watchdog_work.reset_work,
-				msecs_to_jiffies(hdev->device_release_watchdog_timeout_sec * 1000));
+				secs_to_jiffies(hdev->device_release_watchdog_timeout_sec));
 	hdev->reset_info.watchdog_active = 1;
 out:
 	spin_unlock(&hdev->reset_info.lock);
@@ -2035,7 +2096,7 @@ device_reset:
 	if (ctx)
 		hl_ctx_put(ctx);
 
-	return hl_device_reset(hdev, flags);
+	return hl_device_reset(hdev, flags | HL_DRV_RESET_HARD);
 }
 
 static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64 event_mask)
@@ -2044,7 +2105,7 @@ static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64
 	notifier_event->events_mask |= event_mask;
 
 	if (notifier_event->eventfd)
-		eventfd_signal(notifier_event->eventfd, 1);
+		eventfd_signal(notifier_event->eventfd);
 
 	mutex_unlock(&notifier_event->lock);
 }
@@ -2342,6 +2403,12 @@ int hl_device_init(struct hl_device *hdev)
 		goto out_disabled;
 	}
 
+	/* Scheduling the EQ heartbeat thread must come after driver is done with all
+	 * initializations, as we want to make sure the FW gets enough time to be prepared
+	 * to respond to heartbeat packets.
+	 */
+	device_heartbeat_schedule(hdev);
+
 	dev_notice(hdev->dev,
 		"Successfully added device %s to habanalabs driver\n",
 		dev_name(&(hdev)->pdev->dev));
@@ -2514,6 +2581,14 @@ void hl_device_fini(struct hl_device *hdev)
 	if (rc)
 		dev_err(hdev->dev, "hw_fini failed in device fini while removing device %d\n", rc);
 
+	/* Reset the H/W (if it accessible). It will be in idle state after this returns */
+	if (!hdev->cpld_shutdown) {
+		rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+		if (rc)
+			dev_err(hdev->dev,
+				"hw_fini failed in device fini while removing device %d\n", rc);
+	}
+
 	hdev->fw_loader.fw_comp_loaded = FW_TYPE_NONE;
 
 	/* Release kernel context */
@@ -2584,7 +2659,7 @@ inline u32 hl_rreg(struct hl_device *hdev, u32 reg)
 	u32 val = readl(hdev->rmmio + reg);
 
 	if (unlikely(trace_habanalabs_rreg32_enabled()))
-		trace_habanalabs_rreg32(hdev->dev, reg, val);
+		trace_habanalabs_rreg32(&(hdev)->pdev->dev, reg, val);
 
 	return val;
 }
@@ -2602,7 +2677,7 @@ inline u32 hl_rreg(struct hl_device *hdev, u32 reg)
 inline void hl_wreg(struct hl_device *hdev, u32 reg, u32 val)
 {
 	if (unlikely(trace_habanalabs_wreg32_enabled()))
-		trace_habanalabs_wreg32(hdev->dev, reg, val);
+		trace_habanalabs_wreg32(&(hdev)->pdev->dev, reg, val);
 
 	writel(val, hdev->rmmio + reg);
 }
@@ -2796,3 +2871,98 @@ void hl_enable_err_info_capture(struct hl_error_info *captured_err_info)
 	atomic_set(&captured_err_info->cs_timeout.write_enable, 1);
 	captured_err_info->undef_opcode.write_enable = true;
 }
+
+void hl_init_cpu_for_irq(struct hl_device *hdev)
+{
+#ifdef CONFIG_NUMA
+	struct cpumask *available_mask = &hdev->irq_affinity_mask;
+	int numa_node = hdev->pdev->dev.numa_node, i;
+	static struct cpumask cpu_mask;
+
+	if (numa_node < 0)
+		return;
+
+	if (!cpumask_and(&cpu_mask, cpumask_of_node(numa_node), cpu_online_mask)) {
+		dev_err(hdev->dev, "No available affinities in current numa node\n");
+		return;
+	}
+
+	/* Remove HT siblings */
+	for_each_cpu(i, &cpu_mask)
+		cpumask_set_cpu(cpumask_first(topology_sibling_cpumask(i)), available_mask);
+#endif
+}
+
+void hl_set_irq_affinity(struct hl_device *hdev, int irq)
+{
+	if (cpumask_empty(&hdev->irq_affinity_mask)) {
+		dev_dbg(hdev->dev, "affinity mask is empty\n");
+		return;
+	}
+
+	if (irq_set_affinity_and_hint(irq, &hdev->irq_affinity_mask))
+		dev_err(hdev->dev, "Failed setting irq %d affinity\n", irq);
+}
+
+void hl_eq_heartbeat_event_handle(struct hl_device *hdev)
+{
+	hdev->heartbeat_debug_info.heartbeat_event_counter++;
+	hdev->heartbeat_debug_info.last_eq_heartbeat_ts = ktime_get_real_seconds();
+	hdev->eq_heartbeat_received = true;
+}
+
+void hl_handle_clk_change_event(struct hl_device *hdev, u16 event_type, u64 *event_mask)
+{
+	struct hl_clk_throttle *clk_throttle = &hdev->clk_throttling;
+	ktime_t zero_time = ktime_set(0, 0);
+
+	mutex_lock(&clk_throttle->lock);
+
+	switch (event_type) {
+	case EQ_EVENT_POWER_EVT_START:
+		clk_throttle->current_reason |= HL_CLK_THROTTLE_POWER;
+		clk_throttle->aggregated_reason |= HL_CLK_THROTTLE_POWER;
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_POWER].start = ktime_get();
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = zero_time;
+		dev_dbg_ratelimited(hdev->dev, "Clock throttling due to power consumption\n");
+		break;
+
+	case EQ_EVENT_POWER_EVT_END:
+		clk_throttle->current_reason &= ~HL_CLK_THROTTLE_POWER;
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = ktime_get();
+		dev_dbg_ratelimited(hdev->dev, "Power envelop is safe, back to optimal clock\n");
+		break;
+
+	case EQ_EVENT_THERMAL_EVT_START:
+		clk_throttle->current_reason |= HL_CLK_THROTTLE_THERMAL;
+		clk_throttle->aggregated_reason |= HL_CLK_THROTTLE_THERMAL;
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get();
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time;
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
+		dev_info_ratelimited(hdev->dev, "Clock throttling due to overheating\n");
+		break;
+
+	case EQ_EVENT_THERMAL_EVT_END:
+		clk_throttle->current_reason &= ~HL_CLK_THROTTLE_THERMAL;
+		clk_throttle->timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get();
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
+		dev_info_ratelimited(hdev->dev, "Thermal envelop is safe, back to optimal clock\n");
+		break;
+
+	default:
+		dev_err(hdev->dev, "Received invalid clock change event %d\n", event_type);
+		break;
+	}
+
+	mutex_unlock(&clk_throttle->lock);
+}
+
+void hl_eq_cpld_shutdown_event_handle(struct hl_device *hdev, u16 event_id, u64 *event_mask)
+{
+	hl_handle_critical_hw_err(hdev, event_id, event_mask);
+	*event_mask |= HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
+
+	/* Avoid any new accesses to the H/W */
+	hdev->disabled = true;
+	hdev->cpld_shutdown = true;
+}
diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 47e8384134aa..eeb6b2a80fc7 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -8,6 +8,7 @@
 #include "habanalabs.h"
 #include <linux/habanalabs/hl_boot_if.h>
 
+#include <linux/pci.h>
 #include <linux/firmware.h>
 #include <linux/crc32.h>
 #include <linux/slab.h>
@@ -40,6 +41,31 @@ static char *comms_sts_str_arr[COMMS_STS_INVLD_LAST] = {
 	[COMMS_STS_TIMEOUT_ERR] = __stringify(COMMS_STS_TIMEOUT_ERR),
 };
 
+/**
+ * hl_fw_version_cmp() - compares the FW version to a specific version
+ *
+ * @hdev: pointer to hl_device structure
+ * @major: major number of a reference version
+ * @minor: minor number of a reference version
+ * @subminor: sub-minor number of a reference version
+ *
+ * Return 1 if FW version greater than the reference version, -1 if it's
+ *         smaller and 0 if versions are identical.
+ */
+int hl_fw_version_cmp(struct hl_device *hdev, u32 major, u32 minor, u32 subminor)
+{
+	if (hdev->fw_sw_major_ver != major)
+		return (hdev->fw_sw_major_ver > major) ? 1 : -1;
+
+	if (hdev->fw_sw_minor_ver != minor)
+		return (hdev->fw_sw_minor_ver > minor) ? 1 : -1;
+
+	if (hdev->fw_sw_sub_minor_ver != subminor)
+		return (hdev->fw_sw_sub_minor_ver > subminor) ? 1 : -1;
+
+	return 0;
+}
+
 static char *extract_fw_ver_from_str(const char *fw_str)
 {
 	char *str, *fw_ver, *whitespace;
@@ -345,43 +371,63 @@ int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,
 int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode, u64 value)
 {
 	struct cpucp_packet pkt = {};
+	int rc;
 
 	pkt.ctl = cpu_to_le32(opcode << CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.value = cpu_to_le64(value);
 
-	return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	if (rc)
+		dev_err(hdev->dev, "Failed to disable FW's PCI access\n");
+
+	return rc;
 }
 
+/**
+ * hl_fw_send_cpu_message() - send CPU message to the device.
+ *
+ * @hdev: pointer to hl_device structure.
+ * @hw_queue_id: HW queue ID
+ * @msg: raw data of the message/packet
+ * @size: size of @msg in bytes
+ * @timeout_us: timeout in usec to wait for CPU reply on the message
+ * @result: return code reported by FW
+ *
+ * send message to the device CPU.
+ *
+ * Return: 0 on success, non-zero for failure.
+ *     -ENOMEM: memory allocation failure
+ *     -EAGAIN: CPU is disabled (try again when enabled)
+ *     -ETIMEDOUT: timeout waiting for FW response
+ *     -EIO: protocol error
+ */
 int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
-				u16 len, u32 timeout, u64 *result)
+				u16 size, u32 timeout_us, u64 *result)
 {
 	struct hl_hw_queue *queue = &hdev->kernel_queues[hw_queue_id];
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u32 tmp, expected_ack_val, pi, opcode;
 	struct cpucp_packet *pkt;
 	dma_addr_t pkt_dma_addr;
 	struct hl_bd *sent_bd;
-	u32 tmp, expected_ack_val, pi, opcode;
-	int rc;
+	int rc = 0, fw_rc;
 
-	pkt = hl_cpu_accessible_dma_pool_alloc(hdev, len, &pkt_dma_addr);
+	pkt = hl_cpu_accessible_dma_pool_alloc(hdev, size, &pkt_dma_addr);
 	if (!pkt) {
-		dev_err(hdev->dev,
-			"Failed to allocate DMA memory for packet to CPU\n");
+		dev_err(hdev->dev, "Failed to allocate DMA memory for packet to CPU\n");
 		return -ENOMEM;
 	}
 
-	memcpy(pkt, msg, len);
+	memcpy(pkt, msg, size);
 
 	mutex_lock(&hdev->send_cpu_message_lock);
 
 	/* CPU-CP messages can be sent during soft-reset */
-	if (hdev->disabled && !hdev->reset_info.in_compute_reset) {
-		rc = 0;
+	if (hdev->disabled && !hdev->reset_info.in_compute_reset)
 		goto out;
-	}
 
 	if (hdev->device_cpu_disabled) {
-		rc = -EIO;
+		rc = -EAGAIN;
 		goto out;
 	}
 
@@ -397,7 +443,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 	 * Which means that we don't need to lock the access to the entire H/W
 	 * queues module when submitting a JOB to the CPU queue.
 	 */
-	hl_hw_queue_submit_bd(hdev, queue, hl_queue_inc_ptr(queue->pi), len, pkt_dma_addr);
+	hl_hw_queue_submit_bd(hdev, queue, hl_queue_inc_ptr(queue->pi), size, pkt_dma_addr);
 
 	if (prop->fw_app_cpu_boot_dev_sts0 & CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN)
 		expected_ack_val = queue->pi;
@@ -406,7 +452,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 
 	rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp,
 				(tmp == expected_ack_val), 1000,
-				timeout, true);
+				timeout_us, true);
 
 	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
 
@@ -414,19 +460,27 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 		/* If FW performed reset just before sending it a packet, we will get a timeout.
 		 * This is expected behavior, hence no need for error message.
 		 */
-		if (!hl_device_operational(hdev, NULL) && !hdev->reset_info.in_compute_reset)
+		if (!hl_device_operational(hdev, NULL) && !hdev->reset_info.in_compute_reset) {
 			dev_dbg(hdev->dev, "Device CPU packet timeout (0x%x) due to FW reset\n",
 					tmp);
-		else
-			dev_err(hdev->dev, "Device CPU packet timeout (status = 0x%x)\n", tmp);
+		} else {
+			struct hl_bd *bd = queue->kernel_address;
+
+			bd += hl_pi_2_offset(pi);
+
+			dev_err(hdev->dev, "Device CPU packet timeout (status = 0x%x)\n"
+				"Pkt info[%u]: dma_addr: 0x%llx, kernel_addr: %p, len:0x%x, ctl: 0x%x, ptr:0x%llx, dram_bd:%u\n",
+				tmp, pi, pkt_dma_addr, (void *)pkt, bd->len, bd->ctl, bd->ptr,
+				queue->dram_bd);
+		}
 		hdev->device_cpu_disabled = true;
 		goto out;
 	}
 
 	tmp = le32_to_cpu(pkt->ctl);
 
-	rc = (tmp & CPUCP_PKT_CTL_RC_MASK) >> CPUCP_PKT_CTL_RC_SHIFT;
-	if (rc) {
+	fw_rc = (tmp & CPUCP_PKT_CTL_RC_MASK) >> CPUCP_PKT_CTL_RC_SHIFT;
+	if (fw_rc) {
 		opcode = (tmp & CPUCP_PKT_CTL_OPCODE_MASK) >> CPUCP_PKT_CTL_OPCODE_SHIFT;
 
 		if (!prop->supports_advanced_cpucp_rc) {
@@ -435,7 +489,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 			goto scrub_descriptor;
 		}
 
-		switch (rc) {
+		switch (fw_rc) {
 		case cpucp_packet_invalid:
 			dev_err(hdev->dev,
 				"CPU packet %d is not supported by F/W\n", opcode);
@@ -460,7 +514,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 
 		/* propagate the return code from the f/w to the callers who want to check it */
 		if (result)
-			*result = rc;
+			*result = fw_rc;
 
 		rc = -EIO;
 
@@ -480,7 +534,7 @@ scrub_descriptor:
 out:
 	mutex_unlock(&hdev->send_cpu_message_lock);
 
-	hl_cpu_accessible_dma_pool_free(hdev, len, pkt);
+	hl_cpu_accessible_dma_pool_free(hdev, size, pkt);
 
 	return rc;
 }
@@ -501,7 +555,7 @@ int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type)
 						0, &result);
 
 	if (rc)
-		dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type);
+		dev_err(hdev->dev, "failed to unmask event %d", event_type);
 
 	return rc;
 }
@@ -540,7 +594,7 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
 						total_pkt_size, 0, &result);
 
 	if (rc)
-		dev_err(hdev->dev, "failed to unmask IRQ array\n");
+		dev_err(hdev->dev, "failed to unmask event array\n");
 
 	kfree(pkt);
 
@@ -550,7 +604,7 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
 int hl_fw_test_cpu_queue(struct hl_device *hdev)
 {
 	struct cpucp_packet test_pkt = {};
-	u64 result;
+	u64 result = 0;
 	int rc;
 
 	test_pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEST <<
@@ -623,16 +677,14 @@ int hl_fw_send_device_activity(struct hl_device *hdev, bool open)
 int hl_fw_send_heartbeat(struct hl_device *hdev)
 {
 	struct cpucp_packet hb_pkt;
-	u64 result;
+	u64 result = 0;
 	int rc;
 
 	memset(&hb_pkt, 0, sizeof(hb_pkt));
-	hb_pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEST <<
-					CPUCP_PKT_CTL_OPCODE_SHIFT);
+	hb_pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEST << CPUCP_PKT_CTL_OPCODE_SHIFT);
 	hb_pkt.value = cpu_to_le64(CPUCP_PACKET_FENCE_VAL);
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt,
-						sizeof(hb_pkt), 0, &result);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, sizeof(hb_pkt), 0, &result);
 
 	if ((rc) || (result != CPUCP_PACKET_FENCE_VAL))
 		return -EIO;
@@ -643,42 +695,32 @@ int hl_fw_send_heartbeat(struct hl_device *hdev)
 		rc = -EIO;
 	}
 
+	hdev->heartbeat_debug_info.last_pq_heartbeat_ts = ktime_get_real_seconds();
+
 	return rc;
 }
 
-static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
-								u32 sts_val)
+static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, u32 sts_val)
 {
 	bool err_exists = false;
 
 	if (!(err_val & CPU_BOOT_ERR0_ENABLED))
 		return false;
 
-	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - DRAM initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL)
+		dev_err(hdev->dev, "Device boot error - DRAM initialization failed\n");
 
-	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED) {
+	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED)
 		dev_err(hdev->dev, "Device boot error - FIT image corrupted\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - Thermal Sensor initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL)
+		dev_err(hdev->dev, "Device boot error - Thermal Sensor initialization failed\n");
 
 	if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED) {
 		if (hdev->bmc_enable) {
-			dev_err(hdev->dev,
-				"Device boot error - Skipped waiting for BMC\n");
-			err_exists = true;
+			dev_err(hdev->dev, "Device boot error - Skipped waiting for BMC\n");
 		} else {
-			dev_info(hdev->dev,
-				"Device boot message - Skipped waiting for BMC\n");
+			dev_info(hdev->dev, "Device boot message - Skipped waiting for BMC\n");
 			/* This is an info so we don't want it to disable the
 			 * device
 			 */
@@ -686,48 +728,29 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
 		}
 	}
 
-	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY) {
-		dev_err(hdev->dev,
-			"Device boot error - Serdes data from BMC not available\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY)
+		dev_err(hdev->dev, "Device boot error - Serdes data from BMC not available\n");
 
-	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - NIC F/W initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL)
+		dev_err(hdev->dev, "Device boot error - NIC F/W initialization failed\n");
 
-	if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) {
-		dev_err(hdev->dev,
-			"Device boot warning - security not ready\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY)
+		dev_err(hdev->dev, "Device boot warning - security not ready\n");
 
-	if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL)
 		dev_err(hdev->dev, "Device boot error - security failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL)
 		dev_err(hdev->dev, "Device boot error - eFuse failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL)
 		dev_err(hdev->dev, "Device boot error - Failed to load preboot secondary image\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_PLL_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_PLL_FAIL)
 		dev_err(hdev->dev, "Device boot error - PLL failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL)
 		dev_err(hdev->dev, "Device boot error - Failed to set threshold for temperature sensor\n");
-		err_exists = true;
-	}
 
 	if (err_val & CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL) {
 		/* Ignore this bit, don't prevent driver loading */
@@ -735,52 +758,32 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
 		err_val &= ~CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL;
 	}
 
-	if (err_val & CPU_BOOT_ERR0_BINNING_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_BINNING_FAIL)
 		dev_err(hdev->dev, "Device boot error - binning failure\n");
-		err_exists = true;
-	}
 
 	if (sts_val & CPU_BOOT_DEV_STS0_ENABLED)
 		dev_dbg(hdev->dev, "Device status0 %#x\n", sts_val);
 
+	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED)
+		dev_err(hdev->dev, "Device boot warning - Skipped DRAM initialization\n");
+
+	if (err_val & CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
+		dev_err(hdev->dev, "Device boot error - ARC memory scrub failed\n");
+
+	/* All warnings should go here in order not to reach the unknown error validation */
 	if (err_val & CPU_BOOT_ERR0_EEPROM_FAIL) {
 		dev_err(hdev->dev, "Device boot error - EEPROM failure detected\n");
 		err_exists = true;
 	}
 
-	/* All warnings should go here in order not to reach the unknown error validation */
-	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) {
-		dev_warn(hdev->dev,
-			"Device boot warning - Skipped DRAM initialization\n");
-		/* This is a warning so we don't want it to disable the
-		 * device
-		 */
-		err_val &= ~CPU_BOOT_ERR0_DRAM_SKIPPED;
-	}
-
-	if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL) {
-		dev_warn(hdev->dev,
-			"Device boot warning - Failed to load preboot primary image\n");
-		/* This is a warning so we don't want it to disable the
-		 * device as we have a secondary preboot image
-		 */
-		err_val &= ~CPU_BOOT_ERR0_PRI_IMG_VER_FAIL;
-	}
+	if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL)
+		dev_warn(hdev->dev, "Device boot warning - Failed to load preboot primary image\n");
 
-	if (err_val & CPU_BOOT_ERR0_TPM_FAIL) {
-		dev_warn(hdev->dev,
-			"Device boot warning - TPM failure\n");
-		/* This is a warning so we don't want it to disable the
-		 * device
-		 */
-		err_val &= ~CPU_BOOT_ERR0_TPM_FAIL;
-	}
+	if (err_val & CPU_BOOT_ERR0_TPM_FAIL)
+		dev_warn(hdev->dev, "Device boot warning - TPM failure\n");
 
-	if (!err_exists && (err_val & ~CPU_BOOT_ERR0_ENABLED)) {
-		dev_err(hdev->dev,
-			"Device boot error - unknown ERR0 error 0x%08x\n", err_val);
+	if (err_val & CPU_BOOT_ERR_FATAL_MASK)
 		err_exists = true;
-	}
 
 	/* return error only if it's in the predefined mask */
 	if (err_exists && ((err_val & ~CPU_BOOT_ERR0_ENABLED) &
@@ -936,7 +939,7 @@ static int hl_fw_send_msi_info_msg(struct hl_device *hdev)
 {
 	struct cpucp_array_data_packet *pkt;
 	size_t total_pkt_size, data_size;
-	u64 result;
+	u64 result = 0;
 	int rc;
 
 	/* skip sending this info for unsupported ASICs */
@@ -1027,11 +1030,10 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_EEPROM_TIMEOUT_USEC, &result);
-
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP EEPROM packet, error %d\n",
-			rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP EEPROM packet, error %d\n", rc);
 		goto out;
 	}
 
@@ -1072,7 +1074,9 @@ int hl_fw_get_monitor_dump(struct hl_device *hdev, void *data)
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 							HL_CPUCP_MON_DUMP_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to handle CPU-CP monitor-dump packet, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP monitor-dump packet, error %d\n", rc);
 		goto out;
 	}
 
@@ -1106,8 +1110,9 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
 		return rc;
 	}
 	counters->rx_throughput = result;
@@ -1121,8 +1126,9 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
 		return rc;
 	}
 	counters->tx_throughput = result;
@@ -1135,8 +1141,9 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP PCI info pkt, error %d\n", rc);
 		return rc;
 	}
 	counters->replay_cnt = (u32) result;
@@ -1156,9 +1163,9 @@ int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CpuCP total energy pkt, error %d\n",
-				rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CpuCP total energy pkt, error %d\n", rc);
 		return rc;
 	}
 
@@ -1234,7 +1241,8 @@ int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to read PLL info, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev, "Failed to read PLL info, error %d\n", rc);
 		return rc;
 	}
 
@@ -1261,7 +1269,8 @@ int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power)
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to read power, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev, "Failed to read power, error %d\n", rc);
 		return rc;
 	}
 
@@ -1298,8 +1307,9 @@ int hl_fw_dram_replaced_row_get(struct hl_device *hdev,
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP replaced rows info pkt, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP replaced rows info pkt, error %d\n", rc);
 		goto out;
 	}
 
@@ -1324,7 +1334,8 @@ int hl_fw_dram_pending_row_get(struct hl_device *hdev, u32 *pend_rows_num)
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result);
 	if (rc) {
-		dev_err(hdev->dev,
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
 				"Failed to handle CPU-CP pending rows info pkt, error %d\n", rc);
 		goto out;
 	}
@@ -1479,7 +1490,7 @@ int hl_fw_wait_preboot_ready(struct hl_device *hdev)
 {
 	struct pre_fw_load_props *pre_fw_load = &hdev->fw_loader.pre_fw_load;
 	u32 status = 0, timeout;
-	int rc, tries = 1;
+	int rc, tries = 1, fw_err = 0;
 	bool preboot_still_runs;
 
 	/* Need to check two possible scenarios:
@@ -1519,18 +1530,18 @@ retry:
 		}
 	}
 
-	if (rc) {
+	/* If we read all FF, then something is totally wrong, no point
+	 * of reading specific errors
+	 */
+	if (status != -1)
+		fw_err = fw_read_errors(hdev, pre_fw_load->boot_err0_reg,
+					pre_fw_load->boot_err1_reg,
+					pre_fw_load->sts_boot_dev_sts0_reg,
+					pre_fw_load->sts_boot_dev_sts1_reg);
+	if (rc || fw_err) {
 		detect_cpu_boot_status(hdev, status);
-		dev_err(hdev->dev, "CPU boot ready timeout (status = %d)\n", status);
-
-		/* If we read all FF, then something is totally wrong, no point
-		 * of reading specific errors
-		 */
-		if (status != -1)
-			fw_read_errors(hdev, pre_fw_load->boot_err0_reg,
-						pre_fw_load->boot_err1_reg,
-						pre_fw_load->sts_boot_dev_sts0_reg,
-						pre_fw_load->sts_boot_dev_sts1_reg);
+		dev_err(hdev->dev, "CPU boot %s (status = %d)\n",
+				fw_err ? "failed due to an error" : "ready timeout", status);
 		return -EIO;
 	}
 
@@ -1801,7 +1812,7 @@ static void hl_fw_dynamic_send_cmd(struct hl_device *hdev,
 	val = FIELD_PREP(COMMS_COMMAND_CMD_MASK, cmd);
 	val |= FIELD_PREP(COMMS_COMMAND_SIZE_MASK, size);
 
-	trace_habanalabs_comms_send_cmd(hdev->dev, comms_cmd_str_arr[cmd]);
+	trace_habanalabs_comms_send_cmd(&hdev->pdev->dev, comms_cmd_str_arr[cmd]);
 	WREG32(le32_to_cpu(dyn_regs->kmd_msg_to_cpu), val);
 }
 
@@ -1859,7 +1870,7 @@ static int hl_fw_dynamic_wait_for_status(struct hl_device *hdev,
 
 	dyn_regs = &fw_loader->dynamic_loader.comm_desc.cpu_dyn_regs;
 
-	trace_habanalabs_comms_wait_status(hdev->dev, comms_sts_str_arr[expected_status]);
+	trace_habanalabs_comms_wait_status(&hdev->pdev->dev, comms_sts_str_arr[expected_status]);
 
 	/* Wait for expected status */
 	rc = hl_poll_timeout(
@@ -1876,7 +1887,8 @@ static int hl_fw_dynamic_wait_for_status(struct hl_device *hdev,
 		return -EIO;
 	}
 
-	trace_habanalabs_comms_wait_status_done(hdev->dev, comms_sts_str_arr[expected_status]);
+	trace_habanalabs_comms_wait_status_done(&hdev->pdev->dev,
+						comms_sts_str_arr[expected_status]);
 
 	/*
 	 * skip storing FW response for NOOP to preserve the actual desired
@@ -1950,7 +1962,7 @@ int hl_fw_dynamic_send_protocol_cmd(struct hl_device *hdev,
 {
 	int rc;
 
-	trace_habanalabs_comms_protocol_cmd(hdev->dev, comms_cmd_str_arr[cmd]);
+	trace_habanalabs_comms_protocol_cmd(&hdev->pdev->dev, comms_cmd_str_arr[cmd]);
 
 	/* first send clear command to clean former commands */
 	rc = hl_fw_dynamic_send_clear_cmd(hdev, fw_loader);
@@ -2089,7 +2101,7 @@ static int hl_fw_dynamic_validate_descriptor(struct hl_device *hdev,
 	 * note that no alignment/stride address issues here as all structures
 	 * are 64 bit padded.
 	 */
-	data_ptr = (u8 *)fw_desc + sizeof(struct comms_desc_header);
+	data_ptr = (u8 *)fw_desc + sizeof(struct comms_msg_header);
 	data_size = le16_to_cpu(fw_desc->header.size);
 
 	data_crc32 = hl_fw_compat_crc32(data_ptr, data_size);
@@ -2243,11 +2255,11 @@ static int hl_fw_dynamic_read_and_validate_descriptor(struct hl_device *hdev,
 	memcpy_fromio(fw_desc, src, sizeof(struct lkd_fw_comms_desc));
 	fw_data_size = le16_to_cpu(fw_desc->header.size);
 
-	temp_fw_desc = vzalloc(sizeof(struct comms_desc_header) + fw_data_size);
+	temp_fw_desc = vzalloc(sizeof(struct comms_msg_header) + fw_data_size);
 	if (!temp_fw_desc)
 		return -ENOMEM;
 
-	memcpy_fromio(temp_fw_desc, src, sizeof(struct comms_desc_header) + fw_data_size);
+	memcpy_fromio(temp_fw_desc, src, sizeof(struct comms_msg_header) + fw_data_size);
 
 	rc = hl_fw_dynamic_validate_descriptor(hdev, fw_loader,
 					(struct lkd_fw_comms_desc *) temp_fw_desc);
@@ -2769,18 +2781,20 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 		hdev->reset_info.curr_reset_cause = HL_RESET_CAUSE_UNKNOWN;
 	}
 
+	rc = hl_fw_dynamic_request_descriptor(hdev, fw_loader, sizeof(struct lkd_msg_comms));
+	if (rc)
+		goto protocol_err;
+
+	if (hdev->asic_prop.support_dynamic_resereved_fw_size)
+		hdev->asic_prop.reserved_fw_mem_size =
+			le32_to_cpu(fw_loader->dynamic_loader.comm_desc.rsvd_mem_size_mb) * SZ_1M;
+
 	if (!(hdev->fw_components & FW_TYPE_BOOT_CPU)) {
 		struct lkd_fw_binning_info *binning_info;
 
-		rc = hl_fw_dynamic_request_descriptor(hdev, fw_loader,
-							sizeof(struct lkd_msg_comms));
-		if (rc)
-			goto protocol_err;
-
 		/* read preboot version */
 		rc = hl_fw_dynamic_read_device_fw_version(hdev, FW_COMP_PREBOOT,
 				fw_loader->dynamic_loader.comm_desc.cur_fw_ver);
-
 		if (rc)
 			return rc;
 
@@ -2807,11 +2821,6 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 				hdev->decoder_binning, hdev->rotator_binning);
 		}
 
-		if (hdev->asic_prop.support_dynamic_resereved_fw_size) {
-			hdev->asic_prop.reserved_fw_mem_size =
-				le32_to_cpu(fw_loader->dynamic_loader.comm_desc.rsvd_mem_size_mb);
-		}
-
 		return 0;
 	}
 
@@ -2846,7 +2855,7 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 	hdev->asic_funcs->init_cpu_scrambler_dram(hdev);
 
 	if (!(hdev->fw_components & FW_TYPE_LINUX)) {
-		dev_info(hdev->dev, "Skip loading Linux F/W\n");
+		dev_dbg(hdev->dev, "Skip loading Linux F/W\n");
 		return 0;
 	}
 
@@ -3176,10 +3185,10 @@ long hl_fw_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 	pkt.pll_index = cpu_to_le32((u32)used_pll_idx);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result);
-
 	if (rc) {
-		dev_err(hdev->dev, "Failed to get frequency of PLL %d, error %d\n",
-			used_pll_idx, rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev, "Failed to get frequency of PLL %d, error %d\n",
+				used_pll_idx, rc);
 		return rc;
 	}
 
@@ -3203,8 +3212,7 @@ void hl_fw_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
 	pkt.value = cpu_to_le64(freq);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
-
-	if (rc)
+	if (rc && rc != -EAGAIN)
 		dev_err(hdev->dev, "Failed to set frequency to PLL %d, error %d\n",
 			used_pll_idx, rc);
 }
@@ -3220,9 +3228,9 @@ long hl_fw_get_max_power(struct hl_device *hdev)
 	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_GET << CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result);
-
 	if (rc) {
-		dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
 		return rc;
 	}
 
@@ -3244,8 +3252,7 @@ void hl_fw_set_max_power(struct hl_device *hdev)
 	pkt.value = cpu_to_le64(hdev->max_power);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
-
-	if (rc)
+	if (rc && rc != -EAGAIN)
 		dev_err(hdev->dev, "Failed to set max power, error %d\n", rc);
 }
 
@@ -3271,11 +3278,11 @@ static int hl_fw_get_sec_attest_data(struct hl_device *hdev, u32 packet_id, void
 	pkt.data_max_size = cpu_to_le32(size);
 	pkt.nonce = cpu_to_le32(nonce);
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					timeout, NULL);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), timeout, NULL);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to handle CPU-CP pkt %u, error %d\n", packet_id, rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to handle CPU-CP pkt %u, error %d\n", packet_id, rc);
 		goto out;
 	}
 
@@ -3295,6 +3302,14 @@ int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_in
 					HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
 }
 
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce)
+{
+	return hl_fw_get_sec_attest_data(hdev, CPUCP_PACKET_INFO_SIGNED_GET, dev_info_signed,
+					 sizeof(struct cpucp_dev_info_signed), nonce,
+					 HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
+}
+
 int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode,
 						dma_addr_t buff, u32 *size)
 {
@@ -3309,10 +3324,12 @@ int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *)&pkt, sizeof(pkt),
 						HL_CPUCP_INFO_TIMEOUT_USEC, &result);
-	if (rc)
-		dev_err(hdev->dev, "failed to send CPUCP data of generic fw pkt\n");
-	else
+	if (rc) {
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev, "failed to send CPUCP data of generic fw pkt\n");
+	} else {
 		dev_dbg(hdev->dev, "generic pkt was successful, result: 0x%llx\n", result);
+	}
 
 	*size = (u32)result;
 
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 1655c101c705..d94c2ba22a6a 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -71,7 +71,7 @@ struct hl_fpriv;
 
 #define HL_DEVICE_TIMEOUT_USEC		1000000 /* 1 s */
 
-#define HL_HEARTBEAT_PER_USEC		5000000 /* 5 s */
+#define HL_HEARTBEAT_PER_USEC		10000000 /* 10 s */
 
 #define HL_PLL_LOW_JOB_FREQ_USEC	5000000 /* 5 s */
 
@@ -90,7 +90,9 @@ struct hl_fpriv;
 #define HL_COMMON_USER_CQ_INTERRUPT_ID	0xFFF
 #define HL_COMMON_DEC_INTERRUPT_ID	0xFFE
 
-#define HL_STATE_DUMP_HIST_LEN		5
+#define HL_STATE_DUMP_HIST_LEN			5
+#define HL_DBGFS_CFG_ACCESS_HIST_LEN		20
+#define HL_DBGFS_CFG_ACCESS_HIST_TIMEOUT_SEC	2 /* 2s */
 
 /* Default value for device reset trigger , an invalid value */
 #define HL_RESET_TRIGGER_DEFAULT	0xFF
@@ -443,18 +445,22 @@ enum hl_collective_mode {
  *                  a CB handle can be provided for jobs on this queue.
  *                  Otherwise, a CB address must be provided.
  * @collective_mode: collective mode of current queue
+ * @q_dram_bd_address: PQ dram address, used when PQ need to reside in DRAM.
  * @driver_only: true if only the driver is allowed to send a job to this queue,
  *               false otherwise.
  * @binned: True if the queue is binned out and should not be used
  * @supports_sync_stream: True if queue supports sync stream
+ * @dram_bd: True if the bd should be copied to dram, needed for PQ which has been allocated on dram
  */
 struct hw_queue_properties {
 	enum hl_queue_type		type;
 	enum queue_cb_alloc_flags	cb_alloc_flags;
 	enum hl_collective_mode		collective_mode;
+	u64				q_dram_bd_address;
 	u8				driver_only;
 	u8				binned;
 	u8				supports_sync_stream;
+	u8				dram_bd;
 };
 
 /**
@@ -590,8 +596,6 @@ struct hl_hints_range {
  *                 we display to the user
  * @mmu_pgt_size: MMU page tables total size.
  * @mmu_pte_size: PTE size in MMU page tables.
- * @mmu_hop_table_size: MMU hop table size.
- * @mmu_hop0_tables_total_size: total size of MMU hop0 tables.
  * @dram_page_size: The DRAM physical page size.
  * @cfg_size: configuration space size on SRAM.
  * @sram_size: total size of SRAM.
@@ -645,10 +649,12 @@ struct hl_hints_range {
  * @num_engine_cores: number of engine cpu cores.
  * @max_num_of_engines: maximum number of all engines in the ASIC.
  * @num_of_special_blocks: special_blocks array size.
- * @glbl_err_cause_num: global err cause number.
+ * @glbl_err_max_cause_num: global err max cause number.
  * @hbw_flush_reg: register to read to generate HBW flush. value of 0 means HBW flush is
  *                 not supported.
- * @reserved_fw_mem_size: size in MB of dram memory reserved for FW.
+ * @reserved_fw_mem_size: size of dram memory reserved for FW.
+ * @fw_event_queue_size: queue size for events from CPU-CP.
+ *                       A value of 0 means using the default HL_EQ_SIZE_IN_BYTES value.
  * @collective_first_sob: first sync object available for collective use
  * @collective_first_mon: first monitor available for collective use
  * @sync_stream_first_sob: first sync object available for sync stream use
@@ -698,6 +704,7 @@ struct hl_hints_range {
  * @supports_advanced_cpucp_rc: true if new cpucp opcodes are supported.
  * @supports_engine_modes: true if changing engines/engine_cores modes is supported.
  * @support_dynamic_resereved_fw_size: true if we support dynamic reserved size for fw.
+ * @supports_nvme: indicates whether the asic supports NVMe P2P DMA.
  */
 struct asic_fixed_properties {
 	struct hw_queue_properties	*hw_queues_props;
@@ -743,8 +750,6 @@ struct asic_fixed_properties {
 	u32				clk_pll_index;
 	u32				mmu_pgt_size;
 	u32				mmu_pte_size;
-	u32				mmu_hop_table_size;
-	u32				mmu_hop0_tables_total_size;
 	u32				dram_page_size;
 	u32				cfg_size;
 	u32				sram_size;
@@ -779,9 +784,10 @@ struct asic_fixed_properties {
 	u32				num_engine_cores;
 	u32				max_num_of_engines;
 	u32				num_of_special_blocks;
-	u32				glbl_err_cause_num;
+	u32				glbl_err_max_cause_num;
 	u32				hbw_flush_reg;
 	u32				reserved_fw_mem_size;
+	u32				fw_event_queue_size;
 	u16				collective_first_sob;
 	u16				collective_first_mon;
 	u16				sync_stream_first_sob;
@@ -819,6 +825,7 @@ struct asic_fixed_properties {
 	u8				supports_advanced_cpucp_rc;
 	u8				supports_engine_modes;
 	u8				support_dynamic_resereved_fw_size;
+	u8				supports_nvme;
 };
 
 /**
@@ -902,6 +909,18 @@ struct hl_mem_mgr {
 };
 
 /**
+ * struct hl_mem_mgr_fini_stats - describes statistics returned during memory manager teardown.
+ * @n_busy_cb: the amount of CB handles that could not be removed
+ * @n_busy_ts: the amount of TS handles that could not be removed
+ * @n_busy_other: the amount of any other type of handles that could not be removed
+ */
+struct hl_mem_mgr_fini_stats {
+	u32 n_busy_cb;
+	u32 n_busy_ts;
+	u32 n_busy_other;
+};
+
+/**
  * struct hl_mmap_mem_buf_behavior - describes unified memory manager buffer behavior
  * @topic: string identifier used for logging
  * @mem_id: memory type identifier, embedded in the handle and used to identify
@@ -1052,6 +1071,8 @@ struct hl_encaps_signals_mgr {
  * @collective_mode: collective mode of current queue
  * @kernel_address: holds the queue's kernel virtual address.
  * @bus_address: holds the queue's DMA address.
+ * @pq_dram_address: hold the dram address when the PQ is allocated, used when dram_bd is true in
+ *                   queue properites.
  * @pi: holds the queue's pi value.
  * @ci: holds the queue's ci value, AS CALCULATED BY THE DRIVER (not real ci).
  * @hw_queue_id: the id of the H/W queue.
@@ -1061,6 +1082,7 @@ struct hl_encaps_signals_mgr {
  * @valid: is the queue valid (we have array of 32 queues, not all of them
  *         exist).
  * @supports_sync_stream: True if queue supports sync stream
+ * @dram_bd: True if the bd should be copied to dram, needed for PQ which has been allocated on dram
  */
 struct hl_hw_queue {
 	struct hl_cs_job			**shadow_queue;
@@ -1069,6 +1091,7 @@ struct hl_hw_queue {
 	enum hl_collective_mode			collective_mode;
 	void					*kernel_address;
 	dma_addr_t				bus_address;
+	u64					pq_dram_address;
 	u32					pi;
 	atomic_t				ci;
 	u32					hw_queue_id;
@@ -1077,6 +1100,7 @@ struct hl_hw_queue {
 	u16					int_queue_len;
 	u8					valid;
 	u8					supports_sync_stream;
+	u8					dram_bd;
 };
 
 /**
@@ -1224,6 +1248,7 @@ struct hl_user_pending_interrupt {
  * @hdev: pointer to the device structure
  * @kernel_address: holds the queue's kernel virtual address
  * @bus_address: holds the queue's DMA address
+ * @size: the event queue size
  * @ci: ci inside the queue
  * @prev_eqe_index: the index of the previous event queue entry. The index of
  *                  the current entry's index must be +1 of the previous one.
@@ -1235,6 +1260,7 @@ struct hl_eq {
 	struct hl_device	*hdev;
 	void			*kernel_address;
 	dma_addr_t		bus_address;
+	u32			size;
 	u32			ci;
 	u32			prev_eqe_index;
 	bool			check_eqe_index;
@@ -1262,14 +1288,19 @@ struct hl_dec {
  * @ASIC_GAUDI_SEC: Gaudi secured device (HL-2000).
  * @ASIC_GAUDI2: Gaudi2 device.
  * @ASIC_GAUDI2B: Gaudi2B device.
+ * @ASIC_GAUDI2C: Gaudi2C device.
+ * @ASIC_GAUDI2D: Gaudi2D device.
  */
 enum hl_asic_type {
 	ASIC_INVALID,
+
 	ASIC_GOYA,
 	ASIC_GAUDI,
 	ASIC_GAUDI_SEC,
 	ASIC_GAUDI2,
 	ASIC_GAUDI2B,
+	ASIC_GAUDI2C,
+	ASIC_GAUDI2D,
 };
 
 struct hl_cs_parser;
@@ -2247,6 +2278,9 @@ struct hl_vm {
 	u8			init_done;
 };
 
+#ifdef CONFIG_HL_HLDIO
+#include "hldio.h"
+#endif
 
 /*
  * DEBUG, PROFILING STRUCTURE
@@ -2317,7 +2351,6 @@ struct hl_fpriv {
 	struct mutex			ctx_lock;
 };
 
-
 /*
  * DebugFS
  */
@@ -2345,6 +2378,7 @@ struct hl_debugfs_entry {
 	struct hl_dbg_device_entry	*dev_entry;
 };
 
+
 /**
  * struct hl_dbg_device_entry - ASIC specific debugfs manager.
  * @root: root dentry.
@@ -2376,6 +2410,7 @@ struct hl_debugfs_entry {
  * @i2c_addr: generic u8 debugfs file for address value to use in i2c_data_read.
  * @i2c_reg: generic u8 debugfs file for register value to use in i2c_data_read.
  * @i2c_len: generic u8 debugfs file for length value to use in i2c_data_read.
+ * @dio_stats: Direct I/O statistics
  */
 struct hl_dbg_device_entry {
 	struct dentry			*root;
@@ -2407,6 +2442,35 @@ struct hl_dbg_device_entry {
 	u8				i2c_addr;
 	u8				i2c_reg;
 	u8				i2c_len;
+#ifdef CONFIG_HL_HLDIO
+	struct hl_dio_stats	dio_stats;
+#endif
+};
+
+/**
+ * struct hl_debugfs_cfg_access_entry - single debugfs config access object, member of
+ * hl_debugfs_cfg_access.
+ * @seconds_since_epoch: seconds since January 1, 1970, used for time comparisons.
+ * @debugfs_type: the debugfs operation requested, can be READ32, WRITE32, READ64 or WRITE64.
+ * @addr: the requested address to access.
+ * @valid: if set, this entry has valid data for dumping at interrupt time.
+ */
+struct hl_debugfs_cfg_access_entry {
+	ktime_t				seconds_since_epoch;
+	enum debugfs_access_type	debugfs_type;
+	u64				addr;
+	bool				valid;
+};
+
+/**
+ * struct hl_debugfs_cfg_access - saves debugfs config region access requests history.
+ * @cfg_access_list: list of objects describing config region access requests.
+ * @head: next valid index to add new entry to in cfg_access_list.
+ */
+struct hl_debugfs_cfg_access {
+	struct hl_debugfs_cfg_access_entry	cfg_access_list[HL_DBGFS_CFG_ACCESS_HIST_LEN];
+	u32					head;
+	spinlock_t			lock; /* protects head and entries */
 };
 
 /**
@@ -2545,7 +2609,7 @@ struct hl_state_dump_specs {
  * DEVICES
  */
 
-#define HL_STR_MAX	32
+#define HL_STR_MAX	64
 
 #define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1)
 
@@ -2702,11 +2766,16 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
  * updated directly by the device. If false, the host memory being polled will
  * be updated by host CPU. Required so host knows whether or not the memory
  * might need to be byte-swapped before returning value to caller.
+ *
+ * On the first 4 polling iterations the macro goes to sleep for short period of
+ * time that gradually increases and reaches sleep_us on the fifth iteration.
  */
 #define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us, \
 				mem_written_by_device) \
 ({ \
+	u64 __sleep_step_us; \
 	ktime_t __timeout; \
+	u8 __step = 8; \
 	\
 	__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	might_sleep_if(sleep_us); \
@@ -2724,8 +2793,10 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 				(val) = le32_to_cpu(*(__le32 *) &(val)); \
 			break; \
 		} \
-		if (sleep_us) \
-			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+		__sleep_step_us = sleep_us >> __step; \
+		if (__sleep_step_us) \
+			usleep_range((__sleep_step_us >> 2) + 1, __sleep_step_us); \
+		__step >>= 1; \
 	} \
 	(cond) ? 0 : -ETIMEDOUT; \
 })
@@ -3168,6 +3239,21 @@ struct hl_reset_info {
 };
 
 /**
+ * struct eq_heartbeat_debug_info - stores debug info to be used upon heartbeat failure.
+ * @last_pq_heartbeat_ts: timestamp of the last test packet that was sent to FW.
+ *                        This packet is the trigger in FW to send the EQ heartbeat event.
+ * @last_eq_heartbeat_ts: timestamp of the last EQ heartbeat event that was received from FW.
+ * @heartbeat_event_counter: number of heartbeat events received.
+ * @cpu_queue_id: used to read the queue pi/ci
+ */
+struct eq_heartbeat_debug_info {
+	time64_t last_pq_heartbeat_ts;
+	time64_t last_eq_heartbeat_ts;
+	u32 heartbeat_event_counter;
+	u32 cpu_queue_id;
+};
+
+/**
  * struct hl_device - habanalabs device structure.
  * @pdev: pointer to PCI device, can be NULL in case of simulator device.
  * @pcie_bar_phys: array of available PCIe bars physical addresses.
@@ -3232,6 +3318,7 @@ struct hl_reset_info {
  * @hl_chip_info: ASIC's sensors information.
  * @device_status_description: device status description.
  * @hl_debugfs: device's debugfs manager.
+ * @debugfs_cfg_accesses: list of last debugfs config region accesses.
  * @cb_pool: list of pre allocated CBs.
  * @cb_pool_lock: protects the CB pool.
  * @internal_cb_pool_virt_addr: internal command buffer pool virtual address.
@@ -3255,6 +3342,9 @@ struct hl_reset_info {
  * @clk_throttling: holds information about current/previous clock throttling events
  * @captured_err_info: holds information about errors.
  * @reset_info: holds current device reset information.
+ * @heartbeat_debug_info: counters used to debug heartbeat failures.
+ * @hldio: describes habanalabs direct storage interaction interface.
+ * @irq_affinity_mask: mask of available CPU cores for user and decoder interrupt handling.
  * @stream_master_qid_arr: pointer to array with QIDs of master streams.
  * @fw_inner_major_ver: the major of current loaded preboot inner version.
  * @fw_inner_minor_ver: the minor of current loaded preboot inner version.
@@ -3306,6 +3396,7 @@ struct hl_reset_info {
  *                    addresses.
  * @is_in_dram_scrub: true if dram scrub operation is on going.
  * @disabled: is device disabled.
+ * @cpld_shutdown: is cpld shutdown.
  * @late_init_done: is late init stage was done during initialization.
  * @hwmon_initialized: is H/W monitor sensors was initialized.
  * @reset_on_lockup: true if a reset should be done in case of stuck CS, false
@@ -3410,6 +3501,7 @@ struct hl_device {
 	struct hwmon_chip_info		*hl_chip_info;
 
 	struct hl_dbg_device_entry	hl_debugfs;
+	struct hl_debugfs_cfg_access	debugfs_cfg_accesses;
 
 	struct list_head		cb_pool;
 	spinlock_t			cb_pool_lock;
@@ -3444,6 +3536,12 @@ struct hl_device {
 
 	struct hl_reset_info		reset_info;
 
+	struct eq_heartbeat_debug_info	heartbeat_debug_info;
+#ifdef CONFIG_HL_HLDIO
+	struct hl_dio			hldio;
+#endif
+	cpumask_t			irq_affinity_mask;
+
 	u32				*stream_master_qid_arr;
 	u32				fw_inner_major_ver;
 	u32				fw_inner_minor_ver;
@@ -3477,6 +3575,7 @@ struct hl_device {
 	u16				cpu_pci_msb_addr;
 	u8				is_in_dram_scrub;
 	u8				disabled;
+	u8				cpld_shutdown;
 	u8				late_init_done;
 	u8				hwmon_initialized;
 	u8				reset_on_lockup;
@@ -3519,6 +3618,9 @@ struct hl_device {
 	u8				heartbeat;
 };
 
+/* Retrieve PCI device name in case of a PCI device or dev name in simulator */
+#define HL_DEV_NAME(hdev)	\
+		((hdev)->pdev ? dev_name(&(hdev)->pdev->dev) : "NA-DEVICE")
 
 /**
  * struct hl_cs_encaps_sig_handle - encapsulated signals handle structure
@@ -3583,17 +3685,6 @@ struct hl_ioctl_desc {
 	hl_ioctl_t *func;
 };
 
-static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major, u32 fw_sw_minor)
-{
-	if (hdev->fw_sw_major_ver < fw_sw_major)
-		return true;
-	if (hdev->fw_sw_major_ver > fw_sw_major)
-		return false;
-	if (hdev->fw_sw_minor_ver < fw_sw_minor)
-		return true;
-	return false;
-}
-
 /*
  * Kernel module functions that can be accessed by entire module
  */
@@ -3719,6 +3810,7 @@ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q);
 void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q);
 void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q);
 void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q);
+void hl_eq_dump(struct hl_device *hdev, struct hl_eq *q);
 irqreturn_t hl_irq_handler_cq(int irq, void *arg);
 irqreturn_t hl_irq_handler_eq(int irq, void *arg);
 irqreturn_t hl_irq_handler_dec_abnrm(int irq, void *arg);
@@ -3873,6 +3965,7 @@ int hl_mmu_hr_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_
 							struct hl_hr_mmu_funcs *hr_func);
 int hl_mmu_if_set_funcs(struct hl_device *hdev);
 void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
+void hl_mmu_v2_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
 void hl_mmu_v2_hr_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
 int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr);
 int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
@@ -3880,7 +3973,24 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 u64 hl_mmu_scramble_addr(struct hl_device *hdev, u64 addr);
 u64 hl_mmu_descramble_addr(struct hl_device *hdev, u64 addr);
 bool hl_is_dram_va(struct hl_device *hdev, u64 virt_addr);
-
+struct pgt_info *hl_mmu_dr_get_pgt_info(struct hl_ctx *ctx, u64 hop_addr);
+void hl_mmu_dr_free_hop(struct hl_ctx *ctx, u64 hop_addr);
+void hl_mmu_dr_free_pgt_node(struct hl_ctx *ctx, struct pgt_info *pgt_info);
+u64 hl_mmu_dr_get_phys_hop0_addr(struct hl_ctx *ctx);
+u64 hl_mmu_dr_get_hop0_addr(struct hl_ctx *ctx);
+void hl_mmu_dr_write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val);
+void hl_mmu_dr_write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val);
+void hl_mmu_dr_clear_pte(struct hl_ctx *ctx, u64 pte_addr);
+u64 hl_mmu_dr_get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr);
+void hl_mmu_dr_get_pte(struct hl_ctx *ctx, u64 hop_addr);
+int hl_mmu_dr_put_pte(struct hl_ctx *ctx, u64 hop_addr);
+u64 hl_mmu_dr_get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte, bool *is_new_hop);
+u64 hl_mmu_dr_alloc_hop(struct hl_ctx *ctx);
+void hl_mmu_dr_flush(struct hl_ctx *ctx);
+int hl_mmu_dr_init(struct hl_device *hdev);
+void hl_mmu_dr_fini(struct hl_device *hdev);
+
+int hl_fw_version_cmp(struct hl_device *hdev, u32 major, u32 minor, u32 subminor);
 int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,
 				void __iomem *dst, u32 src_offset, u32 size);
 int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode, u64 value);
@@ -3954,6 +4064,8 @@ long hl_fw_get_max_power(struct hl_device *hdev);
 void hl_fw_set_max_power(struct hl_device *hdev);
 int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_info *sec_attest_info,
 				u32 nonce);
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce);
 int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_power(struct hl_device *hdev, int sensor_index, u32 attr, long value);
@@ -3993,7 +4105,7 @@ char *hl_format_as_binary(char *buf, size_t buf_len, u32 n);
 const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type);
 
 void hl_mem_mgr_init(struct device *dev, struct hl_mem_mgr *mmg);
-void hl_mem_mgr_fini(struct hl_mem_mgr *mmg);
+void hl_mem_mgr_fini(struct hl_mem_mgr *mmg, struct hl_mem_mgr_fini_stats *stats);
 void hl_mem_mgr_idr_destroy(struct hl_mem_mgr *mmg);
 int hl_mem_mgr_mmap(struct hl_mem_mgr *mmg, struct vm_area_struct *vma,
 		    void *args);
@@ -4017,6 +4129,11 @@ void hl_handle_critical_hw_err(struct hl_device *hdev, u16 event_id, u64 *event_
 void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info);
 void hl_capture_engine_err(struct hl_device *hdev, u16 engine_id, u16 error_count);
 void hl_enable_err_info_capture(struct hl_error_info *captured_err_info);
+void hl_init_cpu_for_irq(struct hl_device *hdev);
+void hl_set_irq_affinity(struct hl_device *hdev, int irq);
+void hl_eq_heartbeat_event_handle(struct hl_device *hdev);
+void hl_handle_clk_change_event(struct hl_device *hdev, u16 event_type, u64 *event_mask);
+void hl_eq_cpld_shutdown_event_handle(struct hl_device *hdev, u16 event_id, u64 *event_mask);
 
 #ifdef CONFIG_DEBUG_FS
 
@@ -4038,6 +4155,7 @@ void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
 void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
 void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
 					unsigned long length);
+void hl_debugfs_cfg_access_history_dump(struct hl_device *hdev);
 
 #else
 
@@ -4113,6 +4231,10 @@ static inline void hl_debugfs_set_state_dump(struct hl_device *hdev,
 {
 }
 
+static inline void hl_debugfs_cfg_access_history_dump(struct hl_device *hdev)
+{
+}
+
 #endif
 
 /* Security */
diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 306a5bc9bf89..0035748f3228 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -101,7 +101,6 @@ static const struct drm_driver hl_driver = {
 	.major = LINUX_VERSION_MAJOR,
 	.minor = LINUX_VERSION_PATCHLEVEL,
 	.patchlevel = LINUX_VERSION_SUBLEVEL,
-	.date = "20190505",
 
 	.fops = &hl_fops,
 	.open = hl_device_open,
@@ -141,6 +140,12 @@ static enum hl_asic_type get_asic_type(struct hl_device *hdev)
 		case REV_ID_B:
 			asic_type = ASIC_GAUDI2B;
 			break;
+		case REV_ID_C:
+			asic_type = ASIC_GAUDI2C;
+			break;
+		case REV_ID_D:
+			asic_type = ASIC_GAUDI2D;
+			break;
 		default:
 			break;
 		}
@@ -257,7 +262,7 @@ int hl_device_open(struct drm_device *ddev, struct drm_file *file_priv)
 
 out_err:
 	mutex_unlock(&hdev->fpriv_list_lock);
-	hl_mem_mgr_fini(&hpriv->mem_mgr);
+	hl_mem_mgr_fini(&hpriv->mem_mgr, NULL);
 	hl_mem_mgr_idr_destroy(&hpriv->mem_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 	mutex_destroy(&hpriv->ctx_lock);
@@ -356,8 +361,7 @@ static void fixup_device_params_per_asic(struct hl_device *hdev, int timeout)
 		 * a different default timeout for Gaudi
 		 */
 		if (timeout == HL_DEFAULT_TIMEOUT_LOCKED)
-			hdev->timeout_jiffies = msecs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED *
-										MSEC_PER_SEC);
+			hdev->timeout_jiffies = secs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED);
 
 		hdev->reset_upon_device_release = 0;
 		break;
@@ -382,7 +386,7 @@ static int fixup_device_params(struct hl_device *hdev)
 	hdev->fw_comms_poll_interval_usec = HL_FW_STATUS_POLL_INTERVAL_USEC;
 
 	if (tmp_timeout)
-		hdev->timeout_jiffies = msecs_to_jiffies(tmp_timeout * MSEC_PER_SEC);
+		hdev->timeout_jiffies = secs_to_jiffies(tmp_timeout);
 	else
 		hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT;
 
@@ -670,6 +674,38 @@ static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+static void hl_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	hdev->disabled = true;
+}
+
+static void hl_pci_reset_done(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+	u32 flags;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	/*
+	 * Schedule a thread to trigger hard reset.
+	 * The reason for this handler, is for rare cases where the driver is up
+	 * and FLR occurs. This is valid only when working with no VM, so FW handles FLR
+	 * and resets the device. FW will go back preboot stage, so driver needs to perform
+	 * hard reset in order to load FW fit again.
+	 */
+	flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW;
+
+	hl_device_reset(hdev, flags);
+}
+
 static const struct dev_pm_ops hl_pm_ops = {
 	.suspend = hl_pmops_suspend,
 	.resume = hl_pmops_resume,
@@ -679,6 +715,8 @@ static const struct pci_error_handlers hl_pci_err_handler = {
 	.error_detected = hl_pci_err_detected,
 	.slot_reset = hl_pci_err_slot_reset,
 	.resume = hl_pci_err_resume,
+	.reset_prepare = hl_pci_reset_prepare,
+	.reset_done = hl_pci_reset_done,
 };
 
 static struct pci_driver hl_pci_driver = {
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 8ef36effb95b..fdfdabc85e54 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -17,7 +17,8 @@
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 
-#include <asm/msr.h>
+/* make sure there is space for all the signed info */
+static_assert(sizeof(struct cpucp_info) <= SEC_DEV_INFO_BUF_SZ);
 
 static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = {
 	[HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr),
@@ -685,7 +686,7 @@ static int sec_attest_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	if (!sec_attest_info)
 		return -ENOMEM;
 
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		rc = -ENOMEM;
 		goto free_sec_attest_info;
@@ -719,6 +720,53 @@ free_sec_attest_info:
 	return rc;
 }
 
+static int dev_info_signed(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	struct cpucp_dev_info_signed *dev_info_signed;
+	struct hl_info_signed *info;
+	u32 max_size = args->return_size;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	dev_info_signed = kzalloc(sizeof(*dev_info_signed), GFP_KERNEL);
+	if (!dev_info_signed)
+		return -ENOMEM;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		rc = -ENOMEM;
+		goto free_dev_info_signed;
+	}
+
+	rc = hl_fw_get_dev_info_signed(hpriv->hdev,
+					dev_info_signed, args->sec_attest_nonce);
+	if (rc)
+		goto free_info;
+
+	info->nonce = le32_to_cpu(dev_info_signed->nonce);
+	info->info_sig_len = dev_info_signed->info_sig_len;
+	info->pub_data_len = le16_to_cpu(dev_info_signed->pub_data_len);
+	info->certificate_len = le16_to_cpu(dev_info_signed->certificate_len);
+	info->dev_info_len = sizeof(struct cpucp_info);
+	memcpy(&info->info_sig, &dev_info_signed->info_sig, sizeof(info->info_sig));
+	memcpy(&info->public_data, &dev_info_signed->public_data, sizeof(info->public_data));
+	memcpy(&info->certificate, &dev_info_signed->certificate, sizeof(info->certificate));
+	memcpy(&info->dev_info, &dev_info_signed->info, info->dev_info_len);
+
+	rc = copy_to_user(out, info, min_t(size_t, max_size, sizeof(*info))) ? -EFAULT : 0;
+
+free_info:
+	kfree(info);
+free_dev_info_signed:
+	kfree(dev_info_signed);
+
+	return rc;
+}
+
+
 static int eventfd_register(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	int rc;
@@ -913,6 +961,12 @@ static int send_fw_generic_request(struct hl_device *hdev, struct hl_info_args *
 	case HL_PASSTHROUGH_VERSIONS:
 		need_input_buff = false;
 		break;
+	case  HL_GET_ERR_COUNTERS_CMD:
+		need_input_buff = true;
+		break;
+	case HL_GET_P_STATE:
+		need_input_buff = false;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1089,6 +1143,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_FW_GENERIC_REQ:
 		return send_fw_generic_request(hdev, args);
 
+	case HL_INFO_DEV_SIGNED:
+		return dev_info_signed(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -EINVAL;
@@ -1226,13 +1283,10 @@ static long _hl_ioctl(struct hl_fpriv *hpriv, unsigned int cmd, unsigned long ar
 		retcode = -EFAULT;
 
 out_err:
-	if (retcode) {
-		char task_comm[TASK_COMM_LEN];
-
+	if (retcode)
 		dev_dbg_ratelimited(dev,
 				"error in ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n",
-				task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr);
-	}
+				task_pid_nr(current), current->comm, cmd, nr);
 
 	if (kdata != stack_kdata)
 		kfree(kdata);
@@ -1255,11 +1309,9 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
 	if (nr == _IOC_NR(DRM_IOCTL_HL_INFO)) {
 		ioctl = &hl_ioctls_control[nr - HL_COMMAND_START];
 	} else {
-		char task_comm[TASK_COMM_LEN];
-
 		dev_dbg_ratelimited(hdev->dev_ctrl,
 				"invalid ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n",
-				task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr);
+				task_pid_nr(current), current->comm, cmd, nr);
 		return -ENOTTY;
 	}
 
diff --git a/drivers/accel/habanalabs/common/hldio.c b/drivers/accel/habanalabs/common/hldio.c
new file mode 100644
index 000000000000..083ae5610875
--- /dev/null
+++ b/drivers/accel/habanalabs/common/hldio.c
@@ -0,0 +1,437 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2024 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+#include "hldio.h"
+#include <generated/uapi/linux/version.h>
+#include <linux/pci-p2pdma.h>
+#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+
+/*
+ * NVMe Direct I/O implementation for habanalabs driver
+ *
+ * ASSUMPTIONS
+ * ===========
+ * 1. No IOMMU (well, technically it can work with IOMMU, but it is *almost useless).
+ * 2. Only READ operations (can extend in the future).
+ * 3. No sparse files (can overcome this in the future).
+ * 4. Kernel version >= 6.9
+ * 5. Requiring page alignment is OK (I don't see a solution to this one right,
+ *    now, how do we read partial pages?)
+ * 6. Kernel compiled with CONFIG_PCI_P2PDMA. This requires a CUSTOM kernel.
+ *    Theoretically I have a slight idea on how this could be solvable, but it
+ *    is probably inacceptable for the upstream. Also may not work in the end.
+ * 7. Either make sure our cards and disks are under the same PCI bridge, or
+ *    compile a custom kernel to hack around this.
+ */
+
+#define IO_STABILIZE_TIMEOUT 10000000 /* 10 seconds in microseconds */
+
+/*
+ * This struct contains all the useful data I could milk out of the file handle
+ * provided by the user.
+ * @TODO: right now it is retrieved on each IO, but can be done once with some
+ * dedicated IOCTL, call it for example HL_REGISTER_HANDLE.
+ */
+struct hl_dio_fd {
+	/* Back pointer in case we need it in async completion */
+	struct hl_ctx *ctx;
+	/* Associated fd struct */
+	struct file *filp;
+};
+
+/*
+ * This is a single IO descriptor
+ */
+struct hl_direct_io {
+	struct hl_dio_fd f;
+	struct kiocb kio;
+	struct bio_vec *bv;
+	struct iov_iter iter;
+	u64 device_va;
+	u64 off_bytes;
+	u64 len_bytes;
+	u32 type;
+};
+
+bool hl_device_supports_nvme(struct hl_device *hdev)
+{
+	return hdev->asic_prop.supports_nvme;
+}
+
+static int hl_dio_fd_register(struct hl_ctx *ctx, int fd, struct hl_dio_fd *f)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct block_device *bd;
+	struct super_block *sb;
+	struct inode *inode;
+	struct gendisk *gd;
+	struct device *disk_dev;
+	int rc;
+
+	f->filp = fget(fd);
+	if (!f->filp) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	if (!(f->filp->f_flags & O_DIRECT)) {
+		dev_err(hdev->dev, "file is not in the direct mode\n");
+		rc = -EINVAL;
+		goto fput;
+	}
+
+	if (!f->filp->f_op->read_iter) {
+		dev_err(hdev->dev, "read iter is not supported, need to fall back to legacy\n");
+		rc = -EINVAL;
+		goto fput;
+	}
+
+	inode = file_inode(f->filp);
+	sb = inode->i_sb;
+	bd = sb->s_bdev;
+	gd = bd->bd_disk;
+
+	if (inode->i_blocks << sb->s_blocksize_bits < i_size_read(inode)) {
+		dev_err(hdev->dev, "sparse files are not currently supported\n");
+		rc = -EINVAL;
+		goto fput;
+	}
+
+	if (!bd || !gd) {
+		dev_err(hdev->dev, "invalid block device\n");
+		rc = -ENODEV;
+		goto fput;
+	}
+	/* Get the underlying device from the block device */
+	disk_dev = disk_to_dev(gd);
+	if (!dma_pci_p2pdma_supported(disk_dev)) {
+		dev_err(hdev->dev, "device does not support PCI P2P DMA\n");
+		rc = -EOPNOTSUPP;
+		goto fput;
+	}
+
+	/*
+	 * @TODO: Maybe we need additional checks here
+	 */
+
+	f->ctx = ctx;
+	rc = 0;
+
+	goto out;
+fput:
+	fput(f->filp);
+out:
+	return rc;
+}
+
+static void hl_dio_fd_unregister(struct hl_dio_fd *f)
+{
+	fput(f->filp);
+}
+
+static long hl_dio_count_io(struct hl_device *hdev)
+{
+	s64 sum = 0;
+	int i;
+
+	for_each_possible_cpu(i)
+		sum += per_cpu(*hdev->hldio.inflight_ios, i);
+
+	return sum;
+}
+
+static bool hl_dio_get_iopath(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	if (hdev->hldio.io_enabled) {
+		this_cpu_inc(*hdev->hldio.inflight_ios);
+
+		/* Avoid race conditions */
+		if (!hdev->hldio.io_enabled) {
+			this_cpu_dec(*hdev->hldio.inflight_ios);
+			return false;
+		}
+
+		hl_ctx_get(ctx);
+
+		return true;
+	}
+
+	return false;
+}
+
+static void hl_dio_put_iopath(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	hl_ctx_put(ctx);
+	this_cpu_dec(*hdev->hldio.inflight_ios);
+}
+
+static void hl_dio_set_io_enabled(struct hl_device *hdev, bool enabled)
+{
+	hdev->hldio.io_enabled = enabled;
+}
+
+static bool hl_dio_validate_io(struct hl_device *hdev, struct hl_direct_io *io)
+{
+	if ((u64)io->device_va & ~PAGE_MASK) {
+		dev_dbg(hdev->dev, "device address must be 4K aligned\n");
+		return false;
+	}
+
+	if (io->len_bytes & ~PAGE_MASK) {
+		dev_dbg(hdev->dev, "IO length must be 4K aligned\n");
+		return false;
+	}
+
+	if (io->off_bytes & ~PAGE_MASK) {
+		dev_dbg(hdev->dev, "IO offset must be 4K aligned\n");
+		return false;
+	}
+
+	return true;
+}
+
+static struct page *hl_dio_va2page(struct hl_device *hdev, struct hl_ctx *ctx, u64 device_va)
+{
+	struct hl_dio *hldio = &hdev->hldio;
+	u64 device_pa;
+	int rc, i;
+
+	rc = hl_mmu_va_to_pa(ctx, device_va, &device_pa);
+	if (rc) {
+		dev_err(hdev->dev, "device virtual address translation error: %#llx (%d)",
+				device_va, rc);
+		return NULL;
+	}
+
+	for (i = 0 ; i < hldio->np2prs ; ++i) {
+		if (device_pa >= hldio->p2prs[i].device_pa &&
+		    device_pa < hldio->p2prs[i].device_pa + hldio->p2prs[i].size)
+			return hldio->p2prs[i].p2ppages[(device_pa - hldio->p2prs[i].device_pa) >>
+				PAGE_SHIFT];
+	}
+
+	return NULL;
+}
+
+static ssize_t hl_direct_io(struct hl_device *hdev, struct hl_direct_io *io)
+{
+	u64 npages, device_va;
+	ssize_t rc;
+	int i;
+
+	if (!hl_dio_validate_io(hdev, io))
+		return -EINVAL;
+
+	if (!hl_dio_get_iopath(io->f.ctx)) {
+		dev_info(hdev->dev, "can't schedule a new IO, IO is disabled\n");
+		return -ESHUTDOWN;
+	}
+
+	init_sync_kiocb(&io->kio, io->f.filp);
+	io->kio.ki_pos = io->off_bytes;
+
+	npages = (io->len_bytes >> PAGE_SHIFT);
+
+	/* @TODO: this can be implemented smarter, vmalloc in iopath is not
+	 * ideal. Maybe some variation of genpool. Number of pages may differ
+	 * greatly, so maybe even use pools of different sizes and chose the
+	 * closest one.
+	 */
+	io->bv = vzalloc(npages * sizeof(struct bio_vec));
+	if (!io->bv)
+		return -ENOMEM;
+
+	for (i = 0, device_va = io->device_va; i < npages ; ++i, device_va += PAGE_SIZE) {
+		io->bv[i].bv_page = hl_dio_va2page(hdev, io->f.ctx, device_va);
+		if (!io->bv[i].bv_page) {
+			dev_err(hdev->dev, "error getting page struct for device va %#llx",
+					device_va);
+			rc = -EFAULT;
+			goto cleanup;
+		}
+		io->bv[i].bv_offset = 0;
+		io->bv[i].bv_len = PAGE_SIZE;
+	}
+
+	iov_iter_bvec(&io->iter, io->type, io->bv, 1, io->len_bytes);
+	if (io->f.filp->f_op && io->f.filp->f_op->read_iter)
+		rc = io->f.filp->f_op->read_iter(&io->kio, &io->iter);
+	else
+		rc = -EINVAL;
+
+cleanup:
+	vfree(io->bv);
+	hl_dio_put_iopath(io->f.ctx);
+
+	dev_dbg(hdev->dev, "IO ended with %ld\n", rc);
+
+	return rc;
+}
+
+/*
+ * @TODO: This function can be used as a callback for io completion under
+ * kio->ki_complete in order to implement async IO.
+ * Note that on more recent kernels there is no ret2.
+ */
+__maybe_unused static void hl_direct_io_complete(struct kiocb *kio, long ret, long ret2)
+{
+	struct hl_direct_io *io = container_of(kio, struct hl_direct_io, kio);
+
+	dev_dbg(io->f.ctx->hdev->dev, "IO completed with %ld\n", ret);
+
+	/* Do something to copy result to user / notify completion */
+
+	hl_dio_put_iopath(io->f.ctx);
+
+	hl_dio_fd_unregister(&io->f);
+}
+
+/*
+ * DMA disk to ASIC, wait for results. Must be invoked from the user context
+ */
+int hl_dio_ssd2hl(struct hl_device *hdev, struct hl_ctx *ctx, int fd,
+		  u64 device_va, off_t off_bytes, size_t len_bytes,
+		  size_t *len_read)
+{
+	struct hl_direct_io *io;
+	ssize_t rc;
+
+	dev_dbg(hdev->dev, "SSD2HL fd=%d va=%#llx len=%#lx\n", fd, device_va, len_bytes);
+
+	io = kzalloc(sizeof(*io), GFP_KERNEL);
+	if (!io) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	*io = (struct hl_direct_io){
+		.device_va = device_va,
+		.len_bytes = len_bytes,
+		.off_bytes = off_bytes,
+		.type = READ,
+	};
+
+	rc = hl_dio_fd_register(ctx, fd, &io->f);
+	if (rc)
+		goto kfree_io;
+
+	rc = hl_direct_io(hdev, io);
+	if (rc >= 0) {
+		*len_read = rc;
+		rc = 0;
+	}
+
+	/* This shall be called only in the case of a sync IO */
+	hl_dio_fd_unregister(&io->f);
+kfree_io:
+	kfree(io);
+out:
+	return rc;
+}
+
+static void hl_p2p_region_fini(struct hl_device *hdev, struct hl_p2p_region *p2pr)
+{
+	if (p2pr->p2ppages) {
+		vfree(p2pr->p2ppages);
+		p2pr->p2ppages = NULL;
+	}
+
+	if (p2pr->p2pmem) {
+		dev_dbg(hdev->dev, "freeing P2P mem from %p, size=%#llx\n",
+				p2pr->p2pmem, p2pr->size);
+		pci_free_p2pmem(hdev->pdev, p2pr->p2pmem, p2pr->size);
+		p2pr->p2pmem = NULL;
+	}
+}
+
+void hl_p2p_region_fini_all(struct hl_device *hdev)
+{
+	int i;
+
+	for (i = 0 ; i < hdev->hldio.np2prs ; ++i)
+		hl_p2p_region_fini(hdev, &hdev->hldio.p2prs[i]);
+
+	kvfree(hdev->hldio.p2prs);
+	hdev->hldio.p2prs = NULL;
+	hdev->hldio.np2prs = 0;
+}
+
+int hl_p2p_region_init(struct hl_device *hdev, struct hl_p2p_region *p2pr)
+{
+	void *addr;
+	int rc, i;
+
+	/* Start by publishing our p2p memory */
+	rc = pci_p2pdma_add_resource(hdev->pdev, p2pr->bar, p2pr->size, p2pr->bar_offset);
+	if (rc) {
+		dev_err(hdev->dev, "error adding p2p resource: %d\n", rc);
+		goto err;
+	}
+
+	/* Alloc all p2p mem */
+	p2pr->p2pmem = pci_alloc_p2pmem(hdev->pdev, p2pr->size);
+	if (!p2pr->p2pmem) {
+		dev_err(hdev->dev, "error allocating p2p memory\n");
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	p2pr->p2ppages = vmalloc((p2pr->size >> PAGE_SHIFT) * sizeof(struct page *));
+	if (!p2pr->p2ppages) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	for (i = 0, addr = p2pr->p2pmem ; i < (p2pr->size >> PAGE_SHIFT) ; ++i, addr += PAGE_SIZE) {
+		p2pr->p2ppages[i] = virt_to_page(addr);
+		if (!p2pr->p2ppages[i]) {
+			rc = -EFAULT;
+			goto err;
+		}
+	}
+
+	return 0;
+err:
+	hl_p2p_region_fini(hdev, p2pr);
+	return rc;
+}
+
+int hl_dio_start(struct hl_device *hdev)
+{
+	dev_dbg(hdev->dev, "initializing HLDIO\n");
+
+	/* Initialize the IO counter and enable IO */
+	hdev->hldio.inflight_ios = alloc_percpu(s64);
+	if (!hdev->hldio.inflight_ios)
+		return -ENOMEM;
+
+	hl_dio_set_io_enabled(hdev, true);
+
+	return 0;
+}
+
+void hl_dio_stop(struct hl_device *hdev)
+{
+	dev_dbg(hdev->dev, "deinitializing HLDIO\n");
+
+	if (hdev->hldio.io_enabled) {
+		/* Wait for all the IO to finish */
+		hl_dio_set_io_enabled(hdev, false);
+		hl_poll_timeout_condition(hdev, !hl_dio_count_io(hdev), 1000, IO_STABILIZE_TIMEOUT);
+	}
+
+	if (hdev->hldio.inflight_ios) {
+		free_percpu(hdev->hldio.inflight_ios);
+		hdev->hldio.inflight_ios = NULL;
+	}
+}
diff --git a/drivers/accel/habanalabs/common/hldio.h b/drivers/accel/habanalabs/common/hldio.h
new file mode 100644
index 000000000000..2874388f2851
--- /dev/null
+++ b/drivers/accel/habanalabs/common/hldio.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * hldio.h - NVMe Direct I/O (HLDIO) infrastructure for Habana Labs Driver
+ *
+ * This feature requires specific hardware setup and must not be built
+ * under COMPILE_TEST.
+ */
+
+#ifndef __HL_HLDIO_H__
+#define __HL_HLDIO_H__
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/ktime.h>     /* ktime functions */
+#include <linux/delay.h>     /* usleep_range */
+#include <linux/kernel.h>    /* might_sleep_if */
+#include <linux/errno.h>     /* error codes */
+
+/* Forward declarations */
+struct hl_device;
+struct file;
+
+/* Enable only if Kconfig selected */
+#ifdef CONFIG_HL_HLDIO
+/**
+ * struct hl_p2p_region - describes a single P2P memory region
+ * @p2ppages: array of page structs for the P2P memory
+ * @p2pmem: virtual address of the P2P memory region
+ * @device_pa: physical address on the device
+ * @bar_offset: offset within the BAR
+ * @size: size of the region in bytes
+ * @bar: BAR number containing this region
+ */
+struct hl_p2p_region {
+	struct page **p2ppages;
+	void *p2pmem;
+	u64 device_pa;
+	u64 bar_offset;
+	u64 size;
+	int bar;
+};
+
+/**
+ * struct hl_dio_stats - Direct I/O statistics
+ * @total_ops: total number of operations attempted
+ * @successful_ops: number of successful operations
+ * @failed_ops: number of failed operations
+ * @bytes_transferred: total bytes successfully transferred
+ * @last_len_read: length of the last read operation
+ */
+struct hl_dio_stats {
+	u64 total_ops;
+	u64 successful_ops;
+	u64 failed_ops;
+	u64 bytes_transferred;
+	size_t last_len_read;
+};
+
+/**
+ * struct hl_dio - describes habanalabs direct storage interaction interface
+ * @p2prs: array of p2p regions
+ * @inflight_ios: percpu counter for inflight ios
+ * @np2prs: number of elements in p2prs
+ * @io_enabled: 1 if io is enabled 0 otherwise
+ */
+struct hl_dio {
+	struct hl_p2p_region *p2prs;
+	s64 __percpu *inflight_ios;
+	u8 np2prs;
+	u8 io_enabled;
+};
+
+int hl_dio_ssd2hl(struct hl_device *hdev, struct hl_ctx *ctx, int fd,
+		  u64 device_va, off_t off_bytes, size_t len_bytes,
+		  size_t *len_read);
+void hl_p2p_region_fini_all(struct hl_device *hdev);
+int hl_p2p_region_init(struct hl_device *hdev, struct hl_p2p_region *p2pr);
+int hl_dio_start(struct hl_device *hdev);
+void hl_dio_stop(struct hl_device *hdev);
+
+/* Init/teardown */
+int hl_hldio_init(struct hl_device *hdev);
+void hl_hldio_fini(struct hl_device *hdev);
+
+/* File operations */
+long hl_hldio_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
+
+/* DebugFS hooks */
+#ifdef CONFIG_DEBUG_FS
+void hl_hldio_debugfs_init(struct hl_device *hdev);
+void hl_hldio_debugfs_fini(struct hl_device *hdev);
+#else
+static inline void hl_hldio_debugfs_init(struct hl_device *hdev) { }
+static inline void hl_hldio_debugfs_fini(struct hl_device *hdev) { }
+#endif
+
+#else /* !CONFIG_HL_HLDIO */
+
+struct hl_p2p_region;
+/* Stubs when HLDIO is disabled */
+static inline int hl_dio_ssd2hl(struct hl_device *hdev, struct hl_ctx *ctx, int fd,
+		  u64 device_va, off_t off_bytes, size_t len_bytes,
+		  size_t *len_read)
+{ return -EOPNOTSUPP; }
+static inline void hl_p2p_region_fini_all(struct hl_device *hdev) {}
+static inline int hl_p2p_region_init(struct hl_device *hdev, struct hl_p2p_region *p2pr)
+{ return -EOPNOTSUPP; }
+static inline int hl_dio_start(struct hl_device *hdev) { return -EOPNOTSUPP; }
+static inline void hl_dio_stop(struct hl_device *hdev) {}
+
+static inline int hl_hldio_init(struct hl_device *hdev) { return 0; }
+static inline void hl_hldio_fini(struct hl_device *hdev) { }
+static inline long hl_hldio_ioctl(struct file *f, unsigned int c,
+				  unsigned long a)
+{ return -ENOTTY; }
+static inline void hl_hldio_debugfs_init(struct hl_device *hdev) { }
+static inline void hl_hldio_debugfs_fini(struct hl_device *hdev) { }
+
+#endif /* CONFIG_HL_HLDIO */
+
+/* Simplified polling macro for HLDIO (no simulator support) */
+#define hl_poll_timeout_condition(hdev, cond, sleep_us, timeout_us) \
+({ \
+	ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \
+	might_sleep_if(sleep_us); \
+	(void)(hdev); /* keep signature consistent, hdev unused */ \
+	for (;;) { \
+		mb(); /* ensure ordering of memory operations */ \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) \
+			break; \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+#ifdef CONFIG_HL_HLDIO
+bool hl_device_supports_nvme(struct hl_device *hdev);
+#else
+static inline bool hl_device_supports_nvme(struct hl_device *hdev) { return false; }
+#endif
+
+#endif /* __HL_HLDIO_H__ */
diff --git a/drivers/accel/habanalabs/common/hw_queue.c b/drivers/accel/habanalabs/common/hw_queue.c
index d0087c0ec48c..3d04a7507cce 100644
--- a/drivers/accel/habanalabs/common/hw_queue.c
+++ b/drivers/accel/habanalabs/common/hw_queue.c
@@ -84,6 +84,8 @@ void hl_hw_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
 		u32 ctl, u32 len, u64 ptr)
 {
 	struct hl_bd *bd;
+	u64 addr;
+	int i;
 
 	bd = q->kernel_address;
 	bd += hl_pi_2_offset(q->pi);
@@ -91,7 +93,16 @@ void hl_hw_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
 	bd->len = cpu_to_le32(len);
 	bd->ptr = cpu_to_le64(ptr);
 
+	if (q->dram_bd)
+		for (i = 0 ; i < 2 ; i++) {
+			addr = q->pq_dram_address +
+			((hl_pi_2_offset(q->pi) * sizeof(struct hl_bd))	+ (i * sizeof(u64)));
+			hdev->asic_funcs->access_dev_mem(hdev, PCI_REGION_DRAM,	addr,
+						(u64 *)(bd) + i, DEBUGFS_WRITE64);
+		}
+
 	q->pi = hl_queue_inc_ptr(q->pi);
+
 	hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi);
 }
 
@@ -1087,12 +1098,18 @@ int hl_hw_queues_create(struct hl_device *hdev)
 		q->supports_sync_stream =
 				asic->hw_queues_props[i].supports_sync_stream;
 		q->collective_mode = asic->hw_queues_props[i].collective_mode;
+		q->dram_bd = asic->hw_queues_props[i].dram_bd;
+
 		rc = queue_init(hdev, q, i);
 		if (rc) {
 			dev_err(hdev->dev,
 				"failed to initialize queue %d\n", i);
 			goto release_queues;
 		}
+
+		/* Set DRAM PQ address for the queue if it should be at DRAM */
+		if (q->dram_bd)
+			q->pq_dram_address = asic->hw_queues_props[i].q_dram_bd_address;
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/common/hwmon.c b/drivers/accel/habanalabs/common/hwmon.c
index 8598056216e7..52d1e6bf10dc 100644
--- a/drivers/accel/habanalabs/common/hwmon.c
+++ b/drivers/accel/habanalabs/common/hwmon.c
@@ -46,7 +46,7 @@ static u32 fixup_flags_legacy_fw(struct hl_device *hdev, enum hwmon_sensor_types
 		break;
 
 	default:
-		dev_err(hdev->dev, "unsupported h/w sensor type %d\n", type);
+		dev_err_ratelimited(hdev->dev, "unsupported h/w sensor type %d\n", type);
 		flags = cpucp_flags;
 		break;
 	}
@@ -134,7 +134,7 @@ static u32 adjust_hwmon_flags(struct hl_device *hdev, enum hwmon_sensor_types ty
 			break;
 
 		default:
-			dev_err(hdev->dev, "unsupported h/w sensor type %d\n", type);
+			dev_err_ratelimited(hdev->dev, "unsupported h/w sensor type %d\n", type);
 			flags = cpucp_flags;
 			break;
 		}
@@ -162,7 +162,8 @@ int hl_build_hwmon_channel_info(struct hl_device *hdev, struct cpucp_sensor *sen
 			break;
 
 		if (type >= HWMON_NR_SENSOR_TYPES) {
-			dev_err(hdev->dev, "Got wrong sensor type %d from device\n", type);
+			dev_err_ratelimited(hdev->dev,
+				"Got wrong sensor type %d from device\n", type);
 			return -EINVAL;
 		}
 
@@ -578,19 +579,16 @@ int hl_get_temperature(struct hl_device *hdev,
 				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
-
-	dev_dbg(hdev->dev, "get temp, ctl 0x%x, sensor %d, type %d\n",
-		pkt.ctl, pkt.sensor_index, pkt.type);
-
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, &result);
 
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get temperature from sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get temperature from sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
@@ -613,9 +611,8 @@ int hl_set_temperature(struct hl_device *hdev,
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, NULL);
-
-	if (rc)
-		dev_err(hdev->dev,
+	if (rc && rc != -EAGAIN)
+		dev_err_ratelimited(hdev->dev,
 			"Failed to set temperature of sensor %d, error %d\n",
 			sensor_index, rc);
 
@@ -642,9 +639,10 @@ int hl_get_voltage(struct hl_device *hdev,
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get voltage from sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get voltage from sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
@@ -671,9 +669,10 @@ int hl_get_current(struct hl_device *hdev,
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get current from sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get current from sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
@@ -700,9 +699,10 @@ int hl_get_fan_speed(struct hl_device *hdev,
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get fan speed from sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get fan speed from sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
@@ -729,9 +729,10 @@ int hl_get_pwm_info(struct hl_device *hdev,
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get pwm info from sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get pwm info from sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
@@ -754,9 +755,8 @@ void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, NULL);
-
-	if (rc)
-		dev_err(hdev->dev,
+	if (rc && rc != -EAGAIN)
+		dev_err_ratelimited(hdev->dev,
 			"Failed to set pwm info to sensor %d, error %d\n",
 			sensor_index, rc);
 }
@@ -777,9 +777,8 @@ int hl_set_voltage(struct hl_device *hdev,
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, NULL);
-
-	if (rc)
-		dev_err(hdev->dev,
+	if (rc && rc != -EAGAIN)
+		dev_err_ratelimited(hdev->dev,
 			"Failed to set voltage of sensor %d, error %d\n",
 			sensor_index, rc);
 
@@ -800,11 +799,9 @@ int hl_set_current(struct hl_device *hdev,
 	pkt.type = __cpu_to_le16(attr);
 	pkt.value = __cpu_to_le64(value);
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, NULL);
-
-	if (rc)
-		dev_err(hdev->dev,
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	if (rc && rc != -EAGAIN)
+		dev_err_ratelimited(hdev->dev,
 			"Failed to set current of sensor %d, error %d\n",
 			sensor_index, rc);
 
@@ -833,9 +830,8 @@ int hl_set_power(struct hl_device *hdev,
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, NULL);
-
-	if (rc)
-		dev_err(hdev->dev,
+	if (rc && rc != -EAGAIN)
+		dev_err_ratelimited(hdev->dev,
 			"Failed to set power of sensor %d, error %d\n",
 			sensor_index, rc);
 
@@ -862,9 +858,10 @@ int hl_get_power(struct hl_device *hdev,
 	*value = (long) result;
 
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get power of sensor %d, error %d\n",
-			sensor_index, rc);
+		if (rc != -EAGAIN)
+			dev_err_ratelimited(hdev->dev,
+				"Failed to get power of sensor %d, error %d\n",
+				sensor_index, rc);
 		*value = 0;
 	}
 
diff --git a/drivers/accel/habanalabs/common/irq.c b/drivers/accel/habanalabs/common/irq.c
index 978b7f4d5eeb..7c9f2f6a2870 100644
--- a/drivers/accel/habanalabs/common/irq.c
+++ b/drivers/accel/habanalabs/common/irq.c
@@ -652,14 +652,16 @@ void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q)
  */
 int hl_eq_init(struct hl_device *hdev, struct hl_eq *q)
 {
+	u32 size = hdev->asic_prop.fw_event_queue_size ? : HL_EQ_SIZE_IN_BYTES;
 	void *p;
 
-	p = hl_cpu_accessible_dma_pool_alloc(hdev, HL_EQ_SIZE_IN_BYTES, &q->bus_address);
+	p = hl_cpu_accessible_dma_pool_alloc(hdev, size, &q->bus_address);
 	if (!p)
 		return -ENOMEM;
 
 	q->hdev = hdev;
 	q->kernel_address = p;
+	q->size = size;
 	q->ci = 0;
 	q->prev_eqe_index = 0;
 
@@ -678,7 +680,7 @@ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q)
 {
 	flush_workqueue(hdev->eq_wq);
 
-	hl_cpu_accessible_dma_pool_free(hdev, HL_EQ_SIZE_IN_BYTES, q->kernel_address);
+	hl_cpu_accessible_dma_pool_free(hdev, q->size, q->kernel_address);
 }
 
 void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
@@ -693,5 +695,30 @@ void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
 	 * when the device is operational again
 	 */
 
-	memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
+	memset(q->kernel_address, 0, q->size);
+}
+
+void hl_eq_dump(struct hl_device *hdev, struct hl_eq *q)
+{
+	u32 eq_length, eqe_size, ctl, ready, mode, type, index;
+	struct hl_eq_header *hdr;
+	u8 *ptr;
+	int i;
+
+	eq_length = HL_EQ_LENGTH;
+	eqe_size = q->size / HL_EQ_LENGTH;
+
+	dev_info(hdev->dev, "Contents of EQ entries headers:\n");
+
+	for (i = 0, ptr = q->kernel_address ; i < eq_length ; ++i, ptr += eqe_size) {
+		hdr = (struct hl_eq_header *) ptr;
+		ctl = le32_to_cpu(hdr->ctl);
+		ready = FIELD_GET(EQ_CTL_READY_MASK, ctl);
+		mode = FIELD_GET(EQ_CTL_EVENT_MODE_MASK, ctl);
+		type = FIELD_GET(EQ_CTL_EVENT_TYPE_MASK, ctl);
+		index = FIELD_GET(EQ_CTL_INDEX_MASK, ctl);
+
+		dev_info(hdev->dev, "%02u: %#010x [ready: %u, mode %u, type %04u, index %05u]\n",
+				i, ctl, ready, mode, type, index);
+	}
 }
diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c
index 0b8689fe0b64..633db4bff46f 100644
--- a/drivers/accel/habanalabs/common/memory.c
+++ b/drivers/accel/habanalabs/common/memory.c
@@ -14,7 +14,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pci-p2pdma.h>
 
-MODULE_IMPORT_NS(DMA_BUF);
+MODULE_IMPORT_NS("DMA_BUF");
 
 #define HL_MMU_DEBUG	0
 
@@ -955,8 +955,8 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 				(i + 1) == phys_pg_pack->npages);
 		if (rc) {
 			dev_err(hdev->dev,
-				"map failed for handle %u, npages: %llu, mapped: %llu",
-				phys_pg_pack->handle, phys_pg_pack->npages,
+				"map failed (%d) for handle %u, npages: %llu, mapped: %llu\n",
+				rc, phys_pg_pack->handle, phys_pg_pack->npages,
 				mapped_pg_cnt);
 			goto err;
 		}
@@ -1186,7 +1186,8 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args, u64 *device
 
 	rc = map_phys_pg_pack(ctx, ret_vaddr, phys_pg_pack);
 	if (rc) {
-		dev_err(hdev->dev, "mapping page pack failed for handle %u\n", handle);
+		dev_err(hdev->dev, "mapping page pack failed (%d) for handle %u\n",
+			rc, handle);
 		mutex_unlock(&hdev->mmu_lock);
 		goto map_err;
 	}
@@ -1828,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf)
 	struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv;
 	struct hl_ctx *ctx;
 
-	if (!hl_dmabuf)
-		return;
-
 	ctx = hl_dmabuf->ctx;
 
 	if (hl_dmabuf->memhash_hnode)
@@ -1839,7 +1837,12 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf)
 	atomic_dec(&ctx->hdev->dmabuf_export_cnt);
 	hl_ctx_put(ctx);
 
-	/* Paired with get_file() in export_dmabuf() */
+	/*
+	 * Paired with get_file() in export_dmabuf().
+	 * 'ctx' can be still used here to get the file pointer, even after hl_ctx_put() was called,
+	 * because releasing the compute device file involves another reference decrement, and it
+	 * would be possible only after calling fput().
+	 */
 	fput(ctx->hpriv->file_priv->filp);
 
 	kfree(hl_dmabuf);
@@ -1858,7 +1861,12 @@ static int export_dmabuf(struct hl_ctx *ctx,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct hl_device *hdev = ctx->hdev;
-	int rc, fd;
+	CLASS(get_unused_fd, fd)(flags);
+
+	if (fd < 0) {
+		dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd);
+		return fd;
+	}
 
 	exp_info.ops = &habanalabs_dmabuf_ops;
 	exp_info.size = total_size;
@@ -1871,13 +1879,6 @@ static int export_dmabuf(struct hl_ctx *ctx,
 		return PTR_ERR(hl_dmabuf->dmabuf);
 	}
 
-	fd = dma_buf_fd(hl_dmabuf->dmabuf, flags);
-	if (fd < 0) {
-		dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd);
-		rc = fd;
-		goto err_dma_buf_put;
-	}
-
 	hl_dmabuf->ctx = ctx;
 	hl_ctx_get(hl_dmabuf->ctx);
 	atomic_inc(&ctx->hdev->dmabuf_export_cnt);
@@ -1889,13 +1890,9 @@ static int export_dmabuf(struct hl_ctx *ctx,
 	get_file(ctx->hpriv->file_priv->filp);
 
 	*dmabuf_fd = fd;
+	fd_install(take_fd(fd), hl_dmabuf->dmabuf->file);
 
 	return 0;
-
-err_dma_buf_put:
-	hl_dmabuf->dmabuf->priv = NULL;
-	dma_buf_put(hl_dmabuf->dmabuf);
-	return rc;
 }
 
 static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset)
@@ -2340,7 +2337,7 @@ static int get_user_memory(struct hl_device *hdev, u64 addr, u64 size,
 		if (rc < 0)
 			goto destroy_pages;
 		npages = rc;
-		rc = -EFAULT;
+		rc = -ENOMEM;
 		goto put_pages;
 	}
 	userptr->npages = npages;
diff --git a/drivers/accel/habanalabs/common/memory_mgr.c b/drivers/accel/habanalabs/common/memory_mgr.c
index c4d84df355b0..4401beb99e42 100644
--- a/drivers/accel/habanalabs/common/memory_mgr.c
+++ b/drivers/accel/habanalabs/common/memory_mgr.c
@@ -259,13 +259,8 @@ int hl_mem_mgr_mmap(struct hl_mem_mgr *mmg, struct vm_area_struct *vma,
 		goto put_mem;
 	}
 
-#ifdef _HAS_TYPE_ARG_IN_ACCESS_OK
-	if (!access_ok(VERIFY_WRITE, (void __user *)(uintptr_t)vma->vm_start,
-		       user_mem_size)) {
-#else
 	if (!access_ok((void __user *)(uintptr_t)vma->vm_start,
 		       user_mem_size)) {
-#endif
 		dev_err(mmg->dev, "%s: User pointer is invalid - 0x%lx\n",
 			buf->behavior->topic, vma->vm_start);
 
@@ -318,28 +313,61 @@ void hl_mem_mgr_init(struct device *dev, struct hl_mem_mgr *mmg)
 	idr_init(&mmg->handles);
 }
 
+static void hl_mem_mgr_fini_stats_reset(struct hl_mem_mgr_fini_stats *stats)
+{
+	if (!stats)
+		return;
+
+	memset(stats, 0, sizeof(*stats));
+}
+
+static void hl_mem_mgr_fini_stats_inc(u64 mem_id, struct hl_mem_mgr_fini_stats *stats)
+{
+	if (!stats)
+		return;
+
+	switch (mem_id) {
+	case HL_MMAP_TYPE_CB:
+		++stats->n_busy_cb;
+		break;
+	case HL_MMAP_TYPE_TS_BUFF:
+		++stats->n_busy_ts;
+		break;
+	default:
+		/* we currently store only CB/TS so this shouldn't happen */
+		++stats->n_busy_other;
+	}
+}
+
 /**
  * hl_mem_mgr_fini - release unified memory manager
  *
  * @mmg: parent unified memory manager
+ * @stats: if non-NULL, will return some counters for handles that could not be removed.
  *
  * Release the unified memory manager. Shall be called from an interrupt context.
  */
-void hl_mem_mgr_fini(struct hl_mem_mgr *mmg)
+void hl_mem_mgr_fini(struct hl_mem_mgr *mmg, struct hl_mem_mgr_fini_stats *stats)
 {
 	struct hl_mmap_mem_buf *buf;
 	struct idr *idp;
 	const char *topic;
+	u64 mem_id;
 	u32 id;
 
+	hl_mem_mgr_fini_stats_reset(stats);
+
 	idp = &mmg->handles;
 
 	idr_for_each_entry(idp, buf, id) {
 		topic = buf->behavior->topic;
-		if (hl_mmap_mem_buf_put(buf) != 1)
+		mem_id = buf->behavior->mem_id;
+		if (hl_mmap_mem_buf_put(buf) != 1) {
 			dev_err(mmg->dev,
 				"%s: Buff handle %u for CTX is still alive\n",
 				topic, id);
+			hl_mem_mgr_fini_stats_inc(mem_id, stats);
+		}
 	}
 }
 
diff --git a/drivers/accel/habanalabs/common/mmu/Makefile b/drivers/accel/habanalabs/common/mmu/Makefile
index 1806c524e04a..f4b815bf4f7d 100644
--- a/drivers/accel/habanalabs/common/mmu/Makefile
+++ b/drivers/accel/habanalabs/common/mmu/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 HL_COMMON_MMU_FILES := common/mmu/mmu.o common/mmu/mmu_v1.o \
-			common/mmu/mmu_v2_hr.o
+			common/mmu/mmu_v2.o common/mmu/mmu_v2_hr.o
diff --git a/drivers/accel/habanalabs/common/mmu/mmu.c b/drivers/accel/habanalabs/common/mmu/mmu.c
index b2145716c605..79823facce7f 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/pci.h>
 
 #include "../habanalabs.h"
 
@@ -262,7 +263,7 @@ int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, bool flu
 		mmu_funcs->flush(ctx);
 
 	if (trace_habanalabs_mmu_unmap_enabled() && !rc)
-		trace_habanalabs_mmu_unmap(hdev->dev, virt_addr, 0, page_size, flush_pte);
+		trace_habanalabs_mmu_unmap(&hdev->pdev->dev, virt_addr, 0, page_size, flush_pte);
 
 	return rc;
 }
@@ -349,7 +350,7 @@ int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_s
 	if (flush_pte)
 		mmu_funcs->flush(ctx);
 
-	trace_habanalabs_mmu_map(hdev->dev, virt_addr, phys_addr, page_size, flush_pte);
+	trace_habanalabs_mmu_map(&hdev->pdev->dev, virt_addr, phys_addr, page_size, flush_pte);
 
 	return 0;
 
@@ -585,6 +586,8 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 
 int hl_mmu_if_set_funcs(struct hl_device *hdev)
 {
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+
 	if (hdev->mmu_disable)
 		return 0;
 
@@ -596,8 +599,11 @@ int hl_mmu_if_set_funcs(struct hl_device *hdev)
 		break;
 	case ASIC_GAUDI2:
 	case ASIC_GAUDI2B:
-		/* MMUs in Gaudi2 are always host resident */
-		hl_mmu_v2_hr_set_funcs(hdev, &hdev->mmu_func[MMU_HR_PGT]);
+	case ASIC_GAUDI2C:
+	case ASIC_GAUDI2D:
+		hl_mmu_v2_set_funcs(hdev, &hdev->mmu_func[MMU_DR_PGT]);
+		if (prop->pmmu.host_resident)
+			hl_mmu_v2_hr_set_funcs(hdev, &hdev->mmu_func[MMU_HR_PGT]);
 		break;
 	default:
 		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
@@ -640,7 +646,8 @@ int hl_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, u32 flags)
 	rc = hdev->asic_funcs->mmu_invalidate_cache(hdev, is_hard, flags);
 	if (rc)
 		dev_err_ratelimited(hdev->dev,
-				"%s cache invalidation failed, rc=%d\n",
+				"%s: %s cache invalidation failed, rc=%d\n",
+				dev_name(&hdev->pdev->dev),
 				flags == VM_TYPE_USERPTR ? "PMMU" : "HMMU", rc);
 
 	return rc;
@@ -655,8 +662,9 @@ int hl_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_hard,
 								asid, va, size);
 	if (rc)
 		dev_err_ratelimited(hdev->dev,
-				"%s cache range invalidation failed: va=%#llx, size=%llu, rc=%d",
-				flags == VM_TYPE_USERPTR ? "PMMU" : "HMMU", va, size, rc);
+			"%s: %s cache range invalidation failed: va=%#llx, size=%llu, rc=%d",
+			dev_name(&hdev->pdev->dev), flags == VM_TYPE_USERPTR ? "PMMU" : "HMMU",
+			va, size, rc);
 
 	return rc;
 }
@@ -1208,3 +1216,219 @@ int hl_mmu_hr_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_
 	return 0;
 }
 
+struct pgt_info *hl_mmu_dr_get_pgt_info(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = NULL;
+
+	hash_for_each_possible(ctx->mmu_shadow_hash, pgt_info, node,
+			(unsigned long) hop_addr)
+		if (hop_addr == pgt_info->shadow_addr)
+			break;
+
+	return pgt_info;
+}
+
+void hl_mmu_dr_free_hop(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = hl_mmu_dr_get_pgt_info(ctx, hop_addr);
+
+	hl_mmu_dr_free_pgt_node(ctx, pgt_info);
+}
+
+void hl_mmu_dr_free_pgt_node(struct hl_ctx *ctx, struct pgt_info *pgt_info)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	gen_pool_free(hdev->mmu_priv.dr.mmu_pgt_pool, pgt_info->phys_addr,
+			hdev->asic_prop.dmmu.hop_table_size);
+	hash_del(&pgt_info->node);
+	kfree((u64 *) (uintptr_t) pgt_info->shadow_addr);
+	kfree(pgt_info);
+}
+
+u64 hl_mmu_dr_get_phys_hop0_addr(struct hl_ctx *ctx)
+{
+	return ctx->hdev->asic_prop.mmu_pgt_addr +
+			(ctx->asid * ctx->hdev->asic_prop.dmmu.hop_table_size);
+}
+
+u64 hl_mmu_dr_get_hop0_addr(struct hl_ctx *ctx)
+{
+	return (u64) (uintptr_t) ctx->hdev->mmu_priv.dr.mmu_shadow_hop0 +
+			(ctx->asid * ctx->hdev->asic_prop.dmmu.hop_table_size);
+}
+
+u64 hl_mmu_dr_get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr)
+{
+	u64 page_mask = ctx->hdev->asic_prop.dmmu.hop_table_size - 1;
+	u64 shadow_hop_addr = shadow_addr & (~page_mask);
+	u64 pte_offset = shadow_addr & page_mask;
+	u64 phys_hop_addr;
+
+	if (shadow_hop_addr != hl_mmu_dr_get_hop0_addr(ctx))
+		phys_hop_addr = hl_mmu_dr_get_pgt_info(ctx, shadow_hop_addr)->phys_addr;
+	else
+		phys_hop_addr = hl_mmu_dr_get_phys_hop0_addr(ctx);
+
+	return phys_hop_addr + pte_offset;
+}
+
+void hl_mmu_dr_write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
+{
+	u64 phys_val = hl_mmu_dr_get_phys_addr(ctx, val);
+
+	ctx->hdev->asic_funcs->write_pte(ctx->hdev, hl_mmu_dr_get_phys_addr(ctx, shadow_pte_addr),
+					phys_val);
+
+	*(u64 *) (uintptr_t) shadow_pte_addr = val;
+}
+
+void hl_mmu_dr_write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
+{
+	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
+				hl_mmu_dr_get_phys_addr(ctx, shadow_pte_addr), val);
+	*(u64 *) (uintptr_t) shadow_pte_addr = val;
+}
+
+void hl_mmu_dr_clear_pte(struct hl_ctx *ctx, u64 pte_addr)
+{
+	hl_mmu_dr_write_final_pte(ctx, pte_addr, 0);
+}
+
+void hl_mmu_dr_get_pte(struct hl_ctx *ctx, u64 hop_addr)
+{
+	hl_mmu_dr_get_pgt_info(ctx, hop_addr)->num_of_ptes++;
+}
+
+int hl_mmu_dr_put_pte(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = hl_mmu_dr_get_pgt_info(ctx, hop_addr);
+	int num_of_ptes_left;
+
+	pgt_info->num_of_ptes--;
+
+	/*
+	 * Need to save the number of ptes left because hl_mmu_free_hop might free
+	 * the pgt_info
+	 */
+	num_of_ptes_left = pgt_info->num_of_ptes;
+	if (!num_of_ptes_left)
+		hl_mmu_dr_free_pgt_node(ctx, pgt_info);
+
+	return num_of_ptes_left;
+}
+
+u64 hl_mmu_dr_alloc_hop(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct pgt_info *pgt_info;
+	u64 phys_addr, shadow_addr;
+
+	pgt_info = kmalloc(sizeof(*pgt_info), GFP_KERNEL);
+	if (!pgt_info)
+		return ULLONG_MAX;
+
+	phys_addr = (u64) gen_pool_alloc(hdev->mmu_priv.dr.mmu_pgt_pool,
+					prop->dmmu.hop_table_size);
+	if (!phys_addr) {
+		dev_err(hdev->dev, "failed to allocate page\n");
+		goto pool_add_err;
+	}
+
+	shadow_addr = (u64) (uintptr_t) kzalloc(prop->dmmu.hop_table_size,
+						GFP_KERNEL);
+	if (!shadow_addr)
+		goto shadow_err;
+
+	pgt_info->phys_addr = phys_addr;
+	pgt_info->shadow_addr = shadow_addr;
+	pgt_info->ctx = ctx;
+	pgt_info->num_of_ptes = 0;
+	hash_add(ctx->mmu_shadow_hash, &pgt_info->node, shadow_addr);
+
+	return shadow_addr;
+
+shadow_err:
+	gen_pool_free(hdev->mmu_priv.dr.mmu_pgt_pool,
+			phys_addr, prop->dmmu.hop_table_size);
+pool_add_err:
+	kfree(pgt_info);
+
+	return ULLONG_MAX;
+}
+
+u64 hl_mmu_dr_get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte, bool *is_new_hop)
+{
+	u64 hop_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
+
+	if (hop_addr == ULLONG_MAX) {
+		hop_addr = hl_mmu_dr_alloc_hop(ctx);
+		*is_new_hop = (hop_addr != ULLONG_MAX);
+	}
+
+	return hop_addr;
+}
+
+void hl_mmu_dr_flush(struct hl_ctx *ctx)
+{
+	/* flush all writes from all cores to reach PCI */
+	mb();
+	ctx->hdev->asic_funcs->read_pte(ctx->hdev, hl_mmu_dr_get_phys_hop0_addr(ctx));
+}
+
+int hl_mmu_dr_init(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	hdev->mmu_priv.dr.mmu_pgt_pool =
+			gen_pool_create(__ffs(prop->dmmu.hop_table_size), -1);
+
+	if (!hdev->mmu_priv.dr.mmu_pgt_pool) {
+		dev_err(hdev->dev, "Failed to create page gen pool\n");
+		return -ENOMEM;
+	}
+
+	rc = gen_pool_add(hdev->mmu_priv.dr.mmu_pgt_pool, prop->mmu_pgt_addr +
+			prop->dmmu.hop0_tables_total_size,
+			prop->dmmu.pgt_size - prop->dmmu.hop0_tables_total_size,
+			-1);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to add memory to page gen pool\n");
+		goto err_pool_add;
+	}
+
+	hdev->mmu_priv.dr.mmu_shadow_hop0 = kvcalloc(prop->max_asid,
+						prop->dmmu.hop_table_size, GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0)) {
+		rc = -ENOMEM;
+		goto err_pool_add;
+	}
+
+	/* MMU H/W init will be done in device hw_init() */
+
+	return 0;
+
+err_pool_add:
+	gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
+
+	return rc;
+}
+
+void hl_mmu_dr_fini(struct hl_device *hdev)
+{
+	/* MMU H/W fini was already done in device hw_fini() */
+
+	if (ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0))
+		return;
+
+	kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
+	gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
+
+	/* Make sure that if we arrive here again without init was
+	 * called we won't cause kernel panic. This can happen for
+	 * example if we fail during hard reset code at certain points
+	 */
+	hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
+}
diff --git a/drivers/accel/habanalabs/common/mmu/mmu_v1.c b/drivers/accel/habanalabs/common/mmu/mmu_v1.c
index d925dc4dd097..845d16aaa637 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu_v1.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu_v1.c
@@ -12,166 +12,6 @@
 
 #define MMU_V1_MAX_HOPS	(MMU_HOP4 + 1)
 
-static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr);
-
-static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 hop_addr)
-{
-	struct pgt_info *pgt_info = NULL;
-
-	hash_for_each_possible(ctx->mmu_shadow_hash, pgt_info, node,
-				(unsigned long) hop_addr)
-		if (hop_addr == pgt_info->shadow_addr)
-			break;
-
-	return pgt_info;
-}
-
-static void _free_hop(struct hl_ctx *ctx, struct pgt_info *pgt_info)
-{
-	struct hl_device *hdev = ctx->hdev;
-
-	gen_pool_free(hdev->mmu_priv.dr.mmu_pgt_pool, pgt_info->phys_addr,
-			hdev->asic_prop.mmu_hop_table_size);
-	hash_del(&pgt_info->node);
-	kfree((u64 *) (uintptr_t) pgt_info->shadow_addr);
-	kfree(pgt_info);
-}
-
-static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
-{
-	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
-
-	_free_hop(ctx, pgt_info);
-}
-
-static u64 alloc_hop(struct hl_ctx *ctx)
-{
-	struct hl_device *hdev = ctx->hdev;
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct pgt_info *pgt_info;
-	u64 phys_addr, shadow_addr;
-
-	pgt_info = kmalloc(sizeof(*pgt_info), GFP_KERNEL);
-	if (!pgt_info)
-		return ULLONG_MAX;
-
-	phys_addr = (u64) gen_pool_alloc(hdev->mmu_priv.dr.mmu_pgt_pool,
-					prop->mmu_hop_table_size);
-	if (!phys_addr) {
-		dev_err(hdev->dev, "failed to allocate page\n");
-		goto pool_add_err;
-	}
-
-	shadow_addr = (u64) (uintptr_t) kzalloc(prop->mmu_hop_table_size,
-						GFP_KERNEL);
-	if (!shadow_addr)
-		goto shadow_err;
-
-	pgt_info->phys_addr = phys_addr;
-	pgt_info->shadow_addr = shadow_addr;
-	pgt_info->ctx = ctx;
-	pgt_info->num_of_ptes = 0;
-	hash_add(ctx->mmu_shadow_hash, &pgt_info->node, shadow_addr);
-
-	return shadow_addr;
-
-shadow_err:
-	gen_pool_free(hdev->mmu_priv.dr.mmu_pgt_pool, phys_addr,
-			prop->mmu_hop_table_size);
-pool_add_err:
-	kfree(pgt_info);
-
-	return ULLONG_MAX;
-}
-
-static inline u64 get_phys_hop0_addr(struct hl_ctx *ctx)
-{
-	return ctx->hdev->asic_prop.mmu_pgt_addr +
-			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
-}
-
-static inline u64 get_hop0_addr(struct hl_ctx *ctx)
-{
-	return (u64) (uintptr_t) ctx->hdev->mmu_priv.dr.mmu_shadow_hop0 +
-			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
-}
-
-static void flush(struct hl_ctx *ctx)
-{
-	/* flush all writes from all cores to reach PCI */
-	mb();
-	ctx->hdev->asic_funcs->read_pte(ctx->hdev, get_phys_hop0_addr(ctx));
-}
-
-/* transform the value to physical address when writing to H/W */
-static inline void write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
-{
-	/*
-	 * The value to write is actually the address of the next shadow hop +
-	 * flags at the 12 LSBs.
-	 * Hence in order to get the value to write to the physical PTE, we
-	 * clear the 12 LSBs and translate the shadow hop to its associated
-	 * physical hop, and add back the original 12 LSBs.
-	 */
-	u64 phys_val = get_phys_addr(ctx, val & HOP_PHYS_ADDR_MASK) |
-				(val & FLAGS_MASK);
-
-	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
-					get_phys_addr(ctx, shadow_pte_addr),
-					phys_val);
-
-	*(u64 *) (uintptr_t) shadow_pte_addr = val;
-}
-
-/* do not transform the value to physical address when writing to H/W */
-static inline void write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr,
-					u64 val)
-{
-	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
-					get_phys_addr(ctx, shadow_pte_addr),
-					val);
-	*(u64 *) (uintptr_t) shadow_pte_addr = val;
-}
-
-/* clear the last and present bits */
-static inline void clear_pte(struct hl_ctx *ctx, u64 pte_addr)
-{
-	/* no need to transform the value to physical address */
-	write_final_pte(ctx, pte_addr, 0);
-}
-
-static inline void get_pte(struct hl_ctx *ctx, u64 hop_addr)
-{
-	get_pgt_info(ctx, hop_addr)->num_of_ptes++;
-}
-
-/*
- * put_pte - decrement the num of ptes and free the hop if possible
- *
- * @ctx: pointer to the context structure
- * @hop_addr: addr of the hop
- *
- * This function returns the number of ptes left on this hop. If the number is
- * 0, it means the pte was freed.
- */
-static inline int put_pte(struct hl_ctx *ctx, u64 hop_addr)
-{
-	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
-	int num_of_ptes_left;
-
-	pgt_info->num_of_ptes--;
-
-	/*
-	 * Need to save the number of ptes left because free_hop might free
-	 * the pgt_info
-	 */
-	num_of_ptes_left = pgt_info->num_of_ptes;
-	if (!num_of_ptes_left)
-		_free_hop(ctx, pgt_info);
-
-	return num_of_ptes_left;
-}
-
 static inline u64 get_hop_pte_addr(struct hl_ctx *ctx, struct hl_mmu_properties *mmu_prop,
 					u64 *hop_addr_arr, u64 virt_addr, enum mmu_hop_num hop_idx)
 {
@@ -183,35 +23,6 @@ static inline u64 get_hop_pte_addr(struct hl_ctx *ctx, struct hl_mmu_properties
 			ctx->hdev->asic_prop.mmu_pte_size * ((virt_addr & mask) >> shift);
 }
 
-static inline u64 get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte,
-						bool *is_new_hop)
-{
-	u64 hop_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
-
-	if (hop_addr == ULLONG_MAX) {
-		hop_addr = alloc_hop(ctx);
-		*is_new_hop = (hop_addr != ULLONG_MAX);
-	}
-
-	return hop_addr;
-}
-
-/* translates shadow address inside hop to a physical address */
-static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr)
-{
-	u64 page_mask = (ctx->hdev->asic_prop.mmu_hop_table_size - 1);
-	u64 shadow_hop_addr = shadow_addr & ~page_mask;
-	u64 pte_offset = shadow_addr & page_mask;
-	u64 phys_hop_addr;
-
-	if (shadow_hop_addr != get_hop0_addr(ctx))
-		phys_hop_addr = get_pgt_info(ctx, shadow_hop_addr)->phys_addr;
-	else
-		phys_hop_addr = get_phys_hop0_addr(ctx);
-
-	return phys_hop_addr + pte_offset;
-}
-
 static int dram_default_mapping_init(struct hl_ctx *ctx)
 {
 	struct hl_device *hdev = ctx->hdev;
@@ -232,13 +43,13 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 	/* add hop1 and hop2 */
 	total_hops = num_of_hop3 + 2;
 
-	ctx->dram_default_hops = kzalloc(HL_PTE_SIZE * total_hops,  GFP_KERNEL);
+	ctx->dram_default_hops = kcalloc(total_hops, HL_PTE_SIZE,  GFP_KERNEL);
 	if (!ctx->dram_default_hops)
 		return -ENOMEM;
 
-	hop0_addr = get_hop0_addr(ctx);
+	hop0_addr = hl_mmu_dr_get_hop0_addr(ctx);
 
-	hop1_addr = alloc_hop(ctx);
+	hop1_addr = hl_mmu_dr_alloc_hop(ctx);
 	if (hop1_addr == ULLONG_MAX) {
 		dev_err(hdev->dev, "failed to alloc hop 1\n");
 		rc = -ENOMEM;
@@ -247,7 +58,7 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 
 	ctx->dram_default_hops[total_hops - 1] = hop1_addr;
 
-	hop2_addr = alloc_hop(ctx);
+	hop2_addr = hl_mmu_dr_alloc_hop(ctx);
 	if (hop2_addr == ULLONG_MAX) {
 		dev_err(hdev->dev, "failed to alloc hop 2\n");
 		rc = -ENOMEM;
@@ -257,7 +68,7 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 	ctx->dram_default_hops[total_hops - 2] = hop2_addr;
 
 	for (i = 0 ; i < num_of_hop3 ; i++) {
-		ctx->dram_default_hops[i] = alloc_hop(ctx);
+		ctx->dram_default_hops[i] = hl_mmu_dr_alloc_hop(ctx);
 		if (ctx->dram_default_hops[i] == ULLONG_MAX) {
 			dev_err(hdev->dev, "failed to alloc hop 3, i: %d\n", i);
 			rc = -ENOMEM;
@@ -268,18 +79,18 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 
 	/* need only pte 0 in hops 0 and 1 */
 	pte_val = (hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
-	write_pte(ctx, hop0_addr, pte_val);
+	hl_mmu_dr_write_pte(ctx, hop0_addr, pte_val);
 
 	pte_val = (hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
-	write_pte(ctx, hop1_addr, pte_val);
-	get_pte(ctx, hop1_addr);
+	hl_mmu_dr_write_pte(ctx, hop1_addr, pte_val);
+	hl_mmu_dr_get_pte(ctx, hop1_addr);
 
 	hop2_pte_addr = hop2_addr;
 	for (i = 0 ; i < num_of_hop3 ; i++) {
 		pte_val = (ctx->dram_default_hops[i] & HOP_PHYS_ADDR_MASK) |
 				PAGE_PRESENT_MASK;
-		write_pte(ctx, hop2_pte_addr, pte_val);
-		get_pte(ctx, hop2_addr);
+		hl_mmu_dr_write_pte(ctx, hop2_pte_addr, pte_val);
+		hl_mmu_dr_get_pte(ctx, hop2_addr);
 		hop2_pte_addr += HL_PTE_SIZE;
 	}
 
@@ -289,23 +100,23 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 	for (i = 0 ; i < num_of_hop3 ; i++) {
 		hop3_pte_addr = ctx->dram_default_hops[i];
 		for (j = 0 ; j < HOP_PTE_ENTRIES_512 ; j++) {
-			write_final_pte(ctx, hop3_pte_addr, pte_val);
-			get_pte(ctx, ctx->dram_default_hops[i]);
+			hl_mmu_dr_write_final_pte(ctx, hop3_pte_addr, pte_val);
+			hl_mmu_dr_get_pte(ctx, ctx->dram_default_hops[i]);
 			hop3_pte_addr += HL_PTE_SIZE;
 		}
 	}
 
-	flush(ctx);
+	hl_mmu_dr_flush(ctx);
 
 	return 0;
 
 hop3_err:
 	for (i = 0 ; i < hop3_allocated ; i++)
-		free_hop(ctx, ctx->dram_default_hops[i]);
+		hl_mmu_dr_free_hop(ctx, ctx->dram_default_hops[i]);
 
-	free_hop(ctx, hop2_addr);
+	hl_mmu_dr_free_hop(ctx, hop2_addr);
 hop2_err:
-	free_hop(ctx, hop1_addr);
+	hl_mmu_dr_free_hop(ctx, hop1_addr);
 hop1_err:
 	kfree(ctx->dram_default_hops);
 
@@ -329,7 +140,7 @@ static void dram_default_mapping_fini(struct hl_ctx *ctx)
 	do_div(num_of_hop3, prop->dram_page_size);
 	do_div(num_of_hop3, HOP_PTE_ENTRIES_512);
 
-	hop0_addr = get_hop0_addr(ctx);
+	hop0_addr = hl_mmu_dr_get_hop0_addr(ctx);
 	/* add hop1 and hop2 */
 	total_hops = num_of_hop3 + 2;
 	hop1_addr = ctx->dram_default_hops[total_hops - 1];
@@ -338,101 +149,26 @@ static void dram_default_mapping_fini(struct hl_ctx *ctx)
 	for (i = 0 ; i < num_of_hop3 ; i++) {
 		hop3_pte_addr = ctx->dram_default_hops[i];
 		for (j = 0 ; j < HOP_PTE_ENTRIES_512 ; j++) {
-			clear_pte(ctx, hop3_pte_addr);
-			put_pte(ctx, ctx->dram_default_hops[i]);
+			hl_mmu_dr_clear_pte(ctx, hop3_pte_addr);
+			hl_mmu_dr_put_pte(ctx, ctx->dram_default_hops[i]);
 			hop3_pte_addr += HL_PTE_SIZE;
 		}
 	}
 
 	hop2_pte_addr = hop2_addr;
 	for (i = 0 ; i < num_of_hop3 ; i++) {
-		clear_pte(ctx, hop2_pte_addr);
-		put_pte(ctx, hop2_addr);
+		hl_mmu_dr_clear_pte(ctx, hop2_pte_addr);
+		hl_mmu_dr_put_pte(ctx, hop2_addr);
 		hop2_pte_addr += HL_PTE_SIZE;
 	}
 
-	clear_pte(ctx, hop1_addr);
-	put_pte(ctx, hop1_addr);
-	clear_pte(ctx, hop0_addr);
+	hl_mmu_dr_clear_pte(ctx, hop1_addr);
+	hl_mmu_dr_put_pte(ctx, hop1_addr);
+	hl_mmu_dr_clear_pte(ctx, hop0_addr);
 
 	kfree(ctx->dram_default_hops);
 
-	flush(ctx);
-}
-
-/**
- * hl_mmu_v1_init() - initialize the MMU module.
- * @hdev: habanalabs device structure.
- *
- * This function does the following:
- * - Create a pool of pages for pgt_infos.
- * - Create a shadow table for pgt
- *
- * Return: 0 for success, non-zero for failure.
- */
-static int hl_mmu_v1_init(struct hl_device *hdev)
-{
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	int rc;
-
-	hdev->mmu_priv.dr.mmu_pgt_pool =
-			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);
-
-	if (!hdev->mmu_priv.dr.mmu_pgt_pool) {
-		dev_err(hdev->dev, "Failed to create page gen pool\n");
-		return -ENOMEM;
-	}
-
-	rc = gen_pool_add(hdev->mmu_priv.dr.mmu_pgt_pool, prop->mmu_pgt_addr +
-			prop->mmu_hop0_tables_total_size,
-			prop->mmu_pgt_size - prop->mmu_hop0_tables_total_size,
-			-1);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to add memory to page gen pool\n");
-		goto err_pool_add;
-	}
-
-	hdev->mmu_priv.dr.mmu_shadow_hop0 = kvcalloc(prop->max_asid, prop->mmu_hop_table_size,
-										GFP_KERNEL);
-	if (ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0)) {
-		rc = -ENOMEM;
-		goto err_pool_add;
-	}
-
-	/* MMU H/W init will be done in device hw_init() */
-
-	return 0;
-
-err_pool_add:
-	gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
-
-	return rc;
-}
-
-/**
- * hl_mmu_v1_fini() - release the MMU module.
- * @hdev: habanalabs device structure.
- *
- * This function does the following:
- * - Disable MMU in H/W.
- * - Free the pgt_infos pool.
- *
- * All contexts should be freed before calling this function.
- */
-static void hl_mmu_v1_fini(struct hl_device *hdev)
-{
-	/* MMU H/W fini was already done in device hw_fini() */
-
-	if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0)) {
-		kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
-		gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
-
-		/* Make sure that if we arrive here again without init was
-		 * called we won't cause kernel panic. This can happen for
-		 * example if we fail during hard reset code at certain points
-		 */
-		hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
-	}
+	hl_mmu_dr_flush(ctx);
 }
 
 /**
@@ -476,7 +212,7 @@ static void hl_mmu_v1_ctx_fini(struct hl_ctx *ctx)
 		dev_err_ratelimited(hdev->dev,
 			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
 			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
-		_free_hop(ctx, pgt_info);
+		hl_mmu_dr_free_pgt_node(ctx, pgt_info);
 	}
 }
 
@@ -495,7 +231,7 @@ static int hl_mmu_v1_unmap(struct hl_ctx *ctx,
 
 	for (hop_idx = MMU_HOP0; hop_idx < MMU_HOP4; hop_idx++) {
 		if (hop_idx == MMU_HOP0) {
-			hop_addr[hop_idx] = get_hop0_addr(ctx);
+			hop_addr[hop_idx] = hl_mmu_dr_get_hop0_addr(ctx);
 		} else {
 			hop_addr[hop_idx] = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 			if (hop_addr[hop_idx] == ULLONG_MAX)
@@ -546,30 +282,30 @@ static int hl_mmu_v1_unmap(struct hl_ctx *ctx,
 		}
 
 		hop_idx = MMU_HOP3;
-		write_final_pte(ctx, hop_pte_addr[hop_idx], default_pte);
-		put_pte(ctx, hop_addr[hop_idx]);
+		hl_mmu_dr_write_final_pte(ctx, hop_pte_addr[hop_idx], default_pte);
+		hl_mmu_dr_put_pte(ctx, hop_addr[hop_idx]);
 	} else {
 		if (!(curr_pte & PAGE_PRESENT_MASK))
 			goto not_mapped;
 
 		if (hop_addr[MMU_HOP4])
-			clear_pte(ctx, hop_pte_addr[MMU_HOP4]);
+			hl_mmu_dr_clear_pte(ctx, hop_pte_addr[MMU_HOP4]);
 		else
-			clear_pte(ctx, hop_pte_addr[MMU_HOP3]);
+			hl_mmu_dr_clear_pte(ctx, hop_pte_addr[MMU_HOP3]);
 
-		if (hop_addr[MMU_HOP4] && !put_pte(ctx, hop_addr[MMU_HOP4]))
+		if (hop_addr[MMU_HOP4] && !hl_mmu_dr_put_pte(ctx, hop_addr[MMU_HOP4]))
 			clear_hop3 = true;
 
 		if (!clear_hop3)
 			goto mapped;
 
 		for (hop_idx = MMU_HOP3; hop_idx >= 0; hop_idx--) {
-			clear_pte(ctx, hop_pte_addr[hop_idx]);
+			hl_mmu_dr_clear_pte(ctx, hop_pte_addr[hop_idx]);
 
 			if (hop_idx == MMU_HOP0)
 				break;
 
-			if (put_pte(ctx, hop_addr[hop_idx]))
+			if (hl_mmu_dr_put_pte(ctx, hop_addr[hop_idx]))
 				goto mapped;
 		}
 	}
@@ -616,10 +352,10 @@ static int hl_mmu_v1_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 
 	for (hop_idx = MMU_HOP0; hop_idx < num_hops; hop_idx++) {
 		if (hop_idx == MMU_HOP0) {
-			hop_addr[hop_idx] = get_hop0_addr(ctx);
+			hop_addr[hop_idx] = hl_mmu_dr_get_hop0_addr(ctx);
 		} else {
 			hop_addr[hop_idx] =
-					get_alloc_next_hop_addr(ctx, curr_pte, &hop_new[hop_idx]);
+				hl_mmu_dr_get_alloc_next_hop_addr(ctx, curr_pte, &hop_new[hop_idx]);
 			if (hop_addr[hop_idx] == ULLONG_MAX)
 				goto err;
 		}
@@ -666,27 +402,27 @@ static int hl_mmu_v1_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 	curr_pte = (phys_addr & HOP_PHYS_ADDR_MASK) | mmu_prop->last_mask
 			| PAGE_PRESENT_MASK;
 
-	write_final_pte(ctx, hop_pte_addr[num_hops - 1], curr_pte);
+	hl_mmu_dr_write_final_pte(ctx, hop_pte_addr[num_hops - 1], curr_pte);
 
 	for (hop_idx = MMU_HOP1; hop_idx < num_hops; hop_idx++) {
 		prev_hop = hop_idx - 1;
 
 		if (hop_new[hop_idx]) {
 			curr_pte = (hop_addr[hop_idx] & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
-			write_pte(ctx, hop_pte_addr[prev_hop], curr_pte);
+			hl_mmu_dr_write_pte(ctx, hop_pte_addr[prev_hop], curr_pte);
 			if (hop_idx != MMU_HOP1)
-				get_pte(ctx, hop_addr[prev_hop]);
+				hl_mmu_dr_get_pte(ctx, hop_addr[prev_hop]);
 		}
 	}
 
-	get_pte(ctx, hop_addr[num_hops - 1]);
+	hl_mmu_dr_get_pte(ctx, hop_addr[num_hops - 1]);
 
 	return 0;
 
 err:
 	for (hop_idx = num_hops; hop_idx > MMU_HOP0; hop_idx--) {
 		if (hop_new[hop_idx])
-			free_hop(ctx, hop_addr[hop_idx]);
+			hl_mmu_dr_free_hop(ctx, hop_addr[hop_idx]);
 	}
 
 	return rc;
@@ -752,7 +488,7 @@ static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 	if (is_huge)
 		used_hops--;
 
-	hops->hop_info[0].hop_addr = get_phys_hop0_addr(ctx);
+	hops->hop_info[0].hop_addr = hl_mmu_dr_get_phys_hop0_addr(ctx);
 	hops->hop_info[0].hop_pte_addr =
 			hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, 0,
 					hops->hop_info[0].hop_addr, virt_addr);
@@ -801,13 +537,13 @@ static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
  */
 void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu)
 {
-	mmu->init = hl_mmu_v1_init;
-	mmu->fini = hl_mmu_v1_fini;
+	mmu->init = hl_mmu_dr_init;
+	mmu->fini = hl_mmu_dr_fini;
 	mmu->ctx_init = hl_mmu_v1_ctx_init;
 	mmu->ctx_fini = hl_mmu_v1_ctx_fini;
 	mmu->map = hl_mmu_v1_map;
 	mmu->unmap = hl_mmu_v1_unmap;
-	mmu->flush = flush;
+	mmu->flush = hl_mmu_dr_flush;
 	mmu->swap_out = hl_mmu_v1_swap_out;
 	mmu->swap_in = hl_mmu_v1_swap_in;
 	mmu->get_tlb_info = hl_mmu_v1_get_tlb_info;
diff --git a/drivers/accel/habanalabs/common/mmu/mmu_v2.c b/drivers/accel/habanalabs/common/mmu/mmu_v2.c
new file mode 100644
index 000000000000..4bc0268fff1c
--- /dev/null
+++ b/drivers/accel/habanalabs/common/mmu/mmu_v2.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2020 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "../habanalabs.h"
+#include "../../include/hw_ip/mmu/mmu_general.h"
+#include "../../include/hw_ip/mmu/mmu_v2_0.h"
+
+#include <linux/slab.h>
+
+/**
+ * hl_mmu_v2_ctx_init() - initialize a context for using the MMU module.
+ * @ctx: pointer to the context structure to initialize.
+ *
+ * Initialize a mutex to protect the concurrent mapping flow, a hash to hold all
+ * page tables hops related to this context.
+ * Return: 0 on success, non-zero otherwise.
+ */
+static int hl_mmu_v2_ctx_init(struct hl_ctx *ctx)
+{
+	hash_init(ctx->mmu_shadow_hash);
+
+	return 0;
+}
+
+/*
+ * hl_mmu_v2_ctx_fini - disable a ctx from using the mmu module
+ *
+ * @ctx: pointer to the context structure
+ *
+ * This function does the following:
+ * - Free any pgts which were not freed yet
+ * - Free the mutex
+ * - Free DRAM default page mapping hops
+ */
+static void hl_mmu_v2_ctx_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct pgt_info *pgt_info;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!hash_empty(ctx->mmu_shadow_hash))
+		dev_err(hdev->dev, "ctx %d is freed while it has pgts in use\n",
+			ctx->asid);
+
+	hash_for_each_safe(ctx->mmu_shadow_hash, i, tmp, pgt_info, node) {
+		dev_err_ratelimited(hdev->dev,
+			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
+			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
+		hl_mmu_dr_free_pgt_node(ctx, pgt_info);
+	}
+}
+
+static int hl_mmu_v2_unmap(struct hl_ctx *ctx,	u64 virt_addr, bool is_dram_addr)
+{
+	u64 hop_addr[MMU_ARCH_6_HOPS] = { 0 }, hop_pte_addr[MMU_ARCH_6_HOPS] = { 0 }, curr_pte,
+							scrambled_virt_addr;
+	struct asic_fixed_properties *prop = &ctx->hdev->asic_prop;
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_mmu_properties *mmu_prop;
+	bool is_huge = false;
+	int i, hop_last;
+
+	/* device resident in V2 are allowed only for HMMU */
+	if (!is_dram_addr)
+		return -EINVAL;
+
+	mmu_prop = &prop->dmmu;
+
+	hop_last = mmu_prop->num_hops - 1;
+
+	scrambled_virt_addr = hdev->asic_funcs->scramble_addr(hdev, virt_addr);
+
+	hop_addr[0] = hl_mmu_dr_get_hop0_addr(ctx);
+	hop_pte_addr[0] = hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, 0,
+					hop_addr[0], scrambled_virt_addr);
+	if (hop_pte_addr[0] == U64_MAX)
+		return -EFAULT;
+
+	curr_pte = *(u64 *) (uintptr_t) hop_pte_addr[0];
+
+	for (i = 1 ; i < mmu_prop->num_hops ; i++) {
+		hop_addr[i] = hl_mmu_get_next_hop_addr(ctx, curr_pte);
+		if (hop_addr[i] == ULLONG_MAX)
+			goto not_mapped;
+
+		hop_pte_addr[i] = hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, i,
+					hop_addr[i], scrambled_virt_addr);
+		if (hop_pte_addr[i] == U64_MAX)
+			return -EFAULT;
+
+		curr_pte = *(u64 *) (uintptr_t) hop_pte_addr[i];
+
+		if ((i <= hop_last) && (curr_pte & mmu_prop->last_mask)) {
+			hop_last = i;
+			is_huge = true;
+			break;
+		}
+	}
+
+	if (is_dram_addr && !is_huge) {
+		dev_err(hdev->dev, "DRAM unmapping should use huge pages only\n");
+		return -EFAULT;
+	}
+
+	if (!(curr_pte & PAGE_PRESENT_MASK))
+		goto not_mapped;
+
+	for (i = hop_last ; i > 0 ; i--) {
+		hl_mmu_dr_clear_pte(ctx, hop_pte_addr[i]);
+		if (hl_mmu_dr_put_pte(ctx, hop_addr[i]))
+			goto mapped;
+	}
+	hl_mmu_dr_clear_pte(ctx, hop_pte_addr[0]);
+
+mapped:
+	return 0;
+
+not_mapped:
+	dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n",
+		virt_addr);
+
+	return -EINVAL;
+}
+
+static int hl_mmu_v2_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
+							u32 page_size, bool is_dram_addr)
+{
+	u64 hop_addr[MMU_ARCH_6_HOPS] = { 0 }, hop_pte_addr[MMU_ARCH_6_HOPS] = { 0 },
+			curr_pte = 0, scrambled_virt_addr, scrambled_phys_addr;
+	struct asic_fixed_properties *prop = &ctx->hdev->asic_prop;
+	bool hop_new[MMU_ARCH_6_HOPS] = { false };
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_mmu_properties *mmu_prop;
+	int rc, i, hop_last;
+
+	/* device resident in V2 are allowed only for HMMU */
+	if (!is_dram_addr)
+		return -EINVAL;
+
+	mmu_prop = &prop->dmmu;
+
+	hop_last = mmu_prop->num_hops - 1;
+
+	scrambled_virt_addr = hdev->asic_funcs->scramble_addr(hdev, virt_addr);
+	scrambled_phys_addr = hdev->asic_funcs->scramble_addr(hdev, phys_addr);
+
+	/* First hop is preallocated therefore it is treated differently  */
+	hop_addr[0] = hl_mmu_dr_get_hop0_addr(ctx);
+	hop_pte_addr[0] = hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, 0,
+						hop_addr[0], scrambled_virt_addr);
+	curr_pte = *(u64 *) (uintptr_t) hop_pte_addr[0];
+
+	/* Handle hop1 to hop_last */
+	for (i = 1 ; i <= hop_last ; i++) {
+		hop_addr[i] = hl_mmu_dr_get_alloc_next_hop_addr(ctx, curr_pte, &hop_new[i]);
+		if (hop_addr[i] == ULLONG_MAX) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		hop_pte_addr[i] = hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, i,
+					hop_addr[i], scrambled_virt_addr);
+		if (hop_pte_addr[i] == U64_MAX) {
+			rc = -EINVAL;
+			goto err;
+		}
+
+		if (!hop_pte_addr[i]) {
+			rc = -EINVAL;
+			goto err;
+		}
+
+		curr_pte = *(u64 *) (uintptr_t) hop_pte_addr[i];
+	}
+
+	if (curr_pte & PAGE_PRESENT_MASK) {
+		dev_err(hdev->dev,
+			"mapping already exists for virt_addr 0x%llx\n",
+				virt_addr);
+
+		for (i = 0 ; i <= hop_last ; i++)
+			dev_dbg(hdev->dev, "hop%d pte: 0x%llx (0x%llx)\n",
+				i, *(u64 *) (uintptr_t) hop_pte_addr[i],
+				hop_pte_addr[i]);
+
+		rc = -EINVAL;
+		goto err;
+	}
+
+	curr_pte = (scrambled_phys_addr & HOP_PHYS_ADDR_MASK)
+					| mmu_prop->last_mask | PAGE_PRESENT_MASK;
+
+	/* Write the PTEs */
+	hl_mmu_dr_write_final_pte(ctx, hop_pte_addr[hop_last], curr_pte);
+
+	/* for each new hop, add its address to the table of previous-hop */
+	for (i = 1 ; i <= hop_last ; i++) {
+		if (hop_new[i]) {
+			curr_pte = (hop_addr[i] & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+			hl_mmu_dr_write_pte(ctx, hop_pte_addr[i - 1], curr_pte);
+
+			if (i - 1)
+				hl_mmu_dr_get_pte(ctx, hop_addr[i - 1]);
+		}
+	}
+	hl_mmu_dr_get_pte(ctx, hop_addr[hop_last]);
+
+	return 0;
+
+err:
+	for (i = 1 ; i <= hop_last ; i++)
+		if (hop_new[i] && (hop_addr[i] != U64_MAX))
+			hl_mmu_dr_free_hop(ctx, hop_addr[i]);
+
+	return rc;
+}
+
+/*
+ * hl_mmu_v2_swap_out - marks all mapping of the given ctx as swapped out
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+static void hl_mmu_v2_swap_out(struct hl_ctx *ctx)
+{
+
+}
+
+/*
+ * hl_mmu_v2_swap_in - marks all mapping of the given ctx as swapped in
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+static void hl_mmu_v2_swap_in(struct hl_ctx *ctx)
+{
+
+}
+
+static int hl_mmu_v2_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_info *hops)
+{
+	struct asic_fixed_properties *prop = &ctx->hdev->asic_prop;
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_mmu_properties *mmu_prop;
+	bool is_dram_addr;
+	int i;
+
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+						prop->dmmu.start_addr,
+						prop->dmmu.end_addr);
+
+	/* device resident in V2 are allowed only for HMMU */
+	if (!is_dram_addr)
+		return -EINVAL;
+
+	mmu_prop = &prop->dmmu;
+	hops->range_type = HL_VA_RANGE_TYPE_DRAM;
+
+	hops->scrambled_vaddr = hdev->asic_funcs->scramble_addr(hdev, virt_addr);
+
+	hops->hop_info[0].hop_addr = hl_mmu_dr_get_phys_hop0_addr(ctx);
+	hops->hop_info[0].hop_pte_addr = hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, 0,
+						hops->hop_info[0].hop_addr,
+							hops->scrambled_vaddr);
+	if (hops->hop_info[0].hop_pte_addr == U64_MAX)
+		return -EFAULT;
+
+	hops->hop_info[0].hop_pte_val = hdev->asic_funcs->read_pte(hdev,
+						hops->hop_info[0].hop_pte_addr);
+	if (hops->hop_info[0].hop_pte_val == U64_MAX)
+		return -EFAULT;
+
+	for (i = 1 ; i < mmu_prop->num_hops ; i++) {
+		hops->hop_info[i].hop_addr =
+			hl_mmu_get_next_hop_addr(ctx, hops->hop_info[i - 1].hop_pte_val);
+		if (hops->hop_info[i].hop_addr == ULLONG_MAX)
+			return -EFAULT;
+
+		hops->hop_info[i].hop_pte_addr =
+				hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, i,
+						hops->hop_info[i].hop_addr,
+						hops->scrambled_vaddr);
+		if (hops->hop_info[i].hop_pte_addr == U64_MAX)
+			return -EFAULT;
+
+		hops->hop_info[i].hop_pte_val =
+				hdev->asic_funcs->read_pte(hdev,
+					hops->hop_info[i].hop_pte_addr);
+
+		if (!(hops->hop_info[i].hop_pte_val & PAGE_PRESENT_MASK))
+			return -EFAULT;
+
+		if (hops->hop_info[i].hop_pte_val & mmu_prop->last_mask)
+			break;
+	}
+
+	/* if passed over all hops then no last hop was found */
+	if (i == mmu_prop->num_hops)
+		return -EFAULT;
+
+	if (!(hops->hop_info[i].hop_pte_val & PAGE_PRESENT_MASK))
+		return -EFAULT;
+
+	if (hops->scrambled_vaddr != virt_addr)
+		hops->unscrambled_paddr = hdev->asic_funcs->descramble_addr
+				(hdev, hops->hop_info[i].hop_pte_val);
+	else
+		hops->unscrambled_paddr = hops->hop_info[i].hop_pte_val;
+
+	hops->used_hops = i + 1;
+
+	return 0;
+}
+
+/*
+ * hl_mmu_v2_prepare - prepare mmu_if for working with mmu v2
+ *
+ * @hdev: pointer to the device structure
+ * @mmu_if: pointer to the mmu interface structure
+ */
+void hl_mmu_v2_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu)
+{
+	mmu->init = hl_mmu_dr_init;
+	mmu->fini = hl_mmu_dr_fini;
+	mmu->ctx_init = hl_mmu_v2_ctx_init;
+	mmu->ctx_fini = hl_mmu_v2_ctx_fini;
+	mmu->map = hl_mmu_v2_map;
+	mmu->unmap = hl_mmu_v2_unmap;
+	mmu->flush = hl_mmu_dr_flush;
+	mmu->swap_out = hl_mmu_v2_swap_out;
+	mmu->swap_in = hl_mmu_v2_swap_in;
+	mmu->get_tlb_info = hl_mmu_v2_get_tlb_info;
+}
diff --git a/drivers/accel/habanalabs/common/mmu/mmu_v2_hr.c b/drivers/accel/habanalabs/common/mmu/mmu_v2_hr.c
index afe7ef964f82..31507b2a431b 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu_v2_hr.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu_v2_hr.c
@@ -47,7 +47,7 @@ static inline int hl_mmu_v2_hr_init(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
-	return hl_mmu_hr_init(hdev, &hdev->mmu_priv.hr, prop->mmu_hop_table_size,
+	return hl_mmu_hr_init(hdev, &hdev->mmu_priv.hr, prop->pmmu.hop_table_size,
 				prop->mmu_pgt_size);
 }
 
@@ -65,7 +65,7 @@ static inline void hl_mmu_v2_hr_fini(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
-	hl_mmu_hr_fini(hdev, &hdev->mmu_priv.hr, prop->mmu_hop_table_size);
+	hl_mmu_hr_fini(hdev, &hdev->mmu_priv.hr, prop->pmmu.hop_table_size);
 }
 
 /**
@@ -108,7 +108,7 @@ static void hl_mmu_v2_hr_ctx_fini(struct hl_ctx *ctx)
 			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
 			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
 		hl_mmu_hr_free_hop_remove_pgt(pgt_info, &ctx->hdev->mmu_priv.hr,
-							ctx->hdev->asic_prop.mmu_hop_table_size);
+							ctx->hdev->asic_prop.pmmu.hop_table_size);
 	}
 }
 
@@ -150,7 +150,7 @@ static int _hl_mmu_v2_hr_unmap(struct hl_ctx *ctx,
 
 		curr_pte = *(u64 *) (uintptr_t) hl_mmu_hr_pte_phys_to_virt(ctx, hops_pgt_info[i],
 							hop_pte_phys_addr[i],
-							ctx->hdev->asic_prop.mmu_hop_table_size);
+							ctx->hdev->asic_prop.pmmu.hop_table_size);
 
 		if ((i < hop_last) && (curr_pte & mmu_prop->last_mask)) {
 			hop_last = i;
@@ -169,14 +169,14 @@ static int _hl_mmu_v2_hr_unmap(struct hl_ctx *ctx,
 
 	for (i = hop_last ; i > 0 ; i--) {
 		hl_mmu_hr_clear_pte(ctx, hops_pgt_info[i], hop_pte_phys_addr[i],
-						ctx->hdev->asic_prop.mmu_hop_table_size);
+						ctx->hdev->asic_prop.pmmu.hop_table_size);
 
 		if (hl_mmu_hr_put_pte(ctx, hops_pgt_info[i], &ctx->hdev->mmu_priv.hr,
-						ctx->hdev->asic_prop.mmu_hop_table_size))
+						ctx->hdev->asic_prop.pmmu.hop_table_size))
 			goto mapped;
 	}
 	hl_mmu_hr_clear_pte(ctx, hops_pgt_info[0], hop_pte_phys_addr[0],
-						ctx->hdev->asic_prop.mmu_hop_table_size);
+						ctx->hdev->asic_prop.pmmu.hop_table_size);
 
 mapped:
 	return 0;
@@ -255,7 +255,7 @@ static int _hl_mmu_v2_hr_map(struct hl_ctx *ctx,
 									scrambled_virt_addr);
 		curr_pte = *(u64 *) (uintptr_t) hl_mmu_hr_pte_phys_to_virt(ctx, hops_pgt_info[i],
 							hop_pte_phys_addr[i],
-							ctx->hdev->asic_prop.mmu_hop_table_size);
+							ctx->hdev->asic_prop.pmmu.hop_table_size);
 	}
 
 	if (curr_pte & PAGE_PRESENT_MASK) {
@@ -268,7 +268,7 @@ static int _hl_mmu_v2_hr_map(struct hl_ctx *ctx,
 					*(u64 *) (uintptr_t)
 					hl_mmu_hr_pte_phys_to_virt(ctx, hops_pgt_info[i],
 							hop_pte_phys_addr[i],
-							ctx->hdev->asic_prop.mmu_hop_table_size),
+							ctx->hdev->asic_prop.pmmu.hop_table_size),
 					hop_pte_phys_addr[i]);
 		rc = -EINVAL;
 		goto err;
@@ -279,7 +279,7 @@ static int _hl_mmu_v2_hr_map(struct hl_ctx *ctx,
 
 	/* Write the PTEs */
 	hl_mmu_hr_write_pte(ctx, hops_pgt_info[hop_last], hop_pte_phys_addr[hop_last], curr_pte,
-							ctx->hdev->asic_prop.mmu_hop_table_size);
+							ctx->hdev->asic_prop.pmmu.hop_table_size);
 
 	/* for each new hop, add its address to the table of previous-hop */
 	for (i = 1 ; i <= hop_last ; i++) {
@@ -287,7 +287,7 @@ static int _hl_mmu_v2_hr_map(struct hl_ctx *ctx,
 			curr_pte = (hops_pgt_info[i]->phys_addr & HOP_PHYS_ADDR_MASK) |
 							PAGE_PRESENT_MASK;
 			hl_mmu_hr_write_pte(ctx, hops_pgt_info[i - 1], hop_pte_phys_addr[i - 1],
-						curr_pte, ctx->hdev->asic_prop.mmu_hop_table_size);
+						curr_pte, ctx->hdev->asic_prop.pmmu.hop_table_size);
 			if (i - 1)
 				hl_mmu_hr_get_pte(ctx, &ctx->hdev->mmu_func[MMU_HR_PGT].hr_funcs,
 								hops_pgt_info[i - 1]->phys_addr);
@@ -303,7 +303,7 @@ err:
 	for (i = 1 ; i <= hop_last ; i++)
 		if (hop_new[i] && hops_pgt_info[i])
 			hl_mmu_hr_free_hop_remove_pgt(hops_pgt_info[i], &ctx->hdev->mmu_priv.hr,
-							ctx->hdev->asic_prop.mmu_hop_table_size);
+							ctx->hdev->asic_prop.pmmu.hop_table_size);
 
 	return rc;
 }
diff --git a/drivers/accel/habanalabs/common/pci/pci.c b/drivers/accel/habanalabs/common/pci/pci.c
index 191e0e3cf3a5..81cbd8697d4c 100644
--- a/drivers/accel/habanalabs/common/pci/pci.c
+++ b/drivers/accel/habanalabs/common/pci/pci.c
@@ -123,7 +123,7 @@ int hl_pci_elbi_read(struct hl_device *hdev, u64 addr, u32 *data)
 		pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data);
 
 		if (unlikely(trace_habanalabs_elbi_read_enabled()))
-			trace_habanalabs_elbi_read(hdev->dev, (u32) addr, val);
+			trace_habanalabs_elbi_read(&hdev->pdev->dev, (u32) addr, val);
 
 		return 0;
 	}
@@ -186,7 +186,7 @@ static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data)
 
 	if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE) {
 		if (unlikely(trace_habanalabs_elbi_write_enabled()))
-			trace_habanalabs_elbi_write(hdev->dev, (u32) addr, val);
+			trace_habanalabs_elbi_write(&hdev->pdev->dev, (u32) addr, val);
 		return 0;
 	}
 
diff --git a/drivers/accel/habanalabs/common/security.c b/drivers/accel/habanalabs/common/security.c
index fe913965dbad..5402a3cd0491 100644
--- a/drivers/accel/habanalabs/common/security.c
+++ b/drivers/accel/habanalabs/common/security.c
@@ -7,15 +7,31 @@
 
 #include "habanalabs.h"
 
-static const char * const hl_glbl_error_cause[HL_MAX_NUM_OF_GLBL_ERR_CAUSE] = {
+static const char * const hl_glbl_error_cause[] = {
 	"Error due to un-priv read",
 	"Error due to un-secure read",
 	"Error due to read from unmapped reg",
 	"Error due to un-priv write",
 	"Error due to un-secure write",
 	"Error due to write to unmapped reg",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
 	"External I/F write sec violation",
 	"External I/F write to un-mapped reg",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
+	"N/A",
 	"Read to write only",
 	"Write to read only"
 };
@@ -671,10 +687,11 @@ static bool hl_check_block_range_exclusion(struct hl_device *hdev,
 static int hl_read_glbl_errors(struct hl_device *hdev,
 		u32 blk_idx, u32 major, u32 minor, u32 sub_minor, void *data)
 {
-	struct hl_special_block_info *special_blocks = hdev->asic_prop.special_blocks;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_special_block_info *special_blocks = prop->special_blocks;
 	struct hl_special_block_info *current_block = &special_blocks[blk_idx];
 	u32 glbl_err_addr, glbl_err_cause, addr_val, cause_val, block_base,
-		base = current_block->base_addr - lower_32_bits(hdev->asic_prop.cfg_base_address);
+		base = current_block->base_addr - lower_32_bits(prop->cfg_base_address);
 	int i;
 
 	block_base = base + major * current_block->major_offset +
@@ -689,13 +706,13 @@ static int hl_read_glbl_errors(struct hl_device *hdev,
 	glbl_err_addr = block_base + HL_GLBL_ERR_ADDR_OFFSET;
 	addr_val = RREG32(glbl_err_addr);
 
-	for (i = 0 ; i < hdev->asic_prop.glbl_err_cause_num ; i++) {
+	for (i = 0 ; i <= prop->glbl_err_max_cause_num ; i++) {
 		if (cause_val & BIT(i))
 			dev_err_ratelimited(hdev->dev,
-				"%s, addr %#llx\n",
-				hl_glbl_error_cause[i],
-				hdev->asic_prop.cfg_base_address + block_base +
-				FIELD_GET(HL_GLBL_ERR_ADDRESS_MASK, addr_val));
+					"%s, addr %#llx\n",
+					hl_glbl_error_cause[i],
+					prop->cfg_base_address + block_base +
+						FIELD_GET(HL_GLBL_ERR_ADDRESS_MASK, addr_val));
 	}
 
 	WREG32(glbl_err_cause, cause_val);
diff --git a/drivers/accel/habanalabs/common/security.h b/drivers/accel/habanalabs/common/security.h
index d7a3b3e82ea4..476f70687c09 100644
--- a/drivers/accel/habanalabs/common/security.h
+++ b/drivers/accel/habanalabs/common/security.h
@@ -13,8 +13,7 @@
 struct hl_device;
 
 /* special blocks */
-#define HL_MAX_NUM_OF_GLBL_ERR_CAUSE		10
-#define HL_GLBL_ERR_ADDRESS_MASK		GENMASK(11, 0)
+#define HL_GLBL_ERR_ADDRESS_MASK	GENMASK(11, 0)
 /* GLBL_ERR_ADDR register offset from the start of the block */
 #define HL_GLBL_ERR_ADDR_OFFSET		0xF44
 /* GLBL_ERR_CAUSE register offset from the start of the block */
diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index 01f89f029355..8f55ba3b4e73 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -8,6 +8,7 @@
 #include "habanalabs.h"
 
 #include <linux/pci.h>
+#include <linux/types.h>
 
 static ssize_t clk_max_freq_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -80,14 +81,36 @@ static ssize_t vrm_ver_show(struct device *dev, struct device_attribute *attr, c
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 	struct cpucp_info *cpucp_info;
+	u32 infineon_second_stage_version;
+	u32 infineon_second_stage_first_instance;
+	u32 infineon_second_stage_second_instance;
+	u32 infineon_second_stage_third_instance;
+	u32 mask = 0xff;
 
 	cpucp_info = &hdev->asic_prop.cpucp_info;
 
-	if (cpucp_info->infineon_second_stage_version)
-		return sprintf(buf, "%#04x %#04x\n", le32_to_cpu(cpucp_info->infineon_version),
-				le32_to_cpu(cpucp_info->infineon_second_stage_version));
-	else
+	infineon_second_stage_version = le32_to_cpu(cpucp_info->infineon_second_stage_version);
+	infineon_second_stage_first_instance = infineon_second_stage_version & mask;
+	infineon_second_stage_second_instance =
+					(infineon_second_stage_version >> 8) & mask;
+	infineon_second_stage_third_instance =
+					(infineon_second_stage_version >> 16) & mask;
+
+	if (cpucp_info->infineon_version && cpucp_info->infineon_second_stage_version)
+		return sprintf(buf, "%#04x %#04x:%#04x:%#04x\n",
+				le32_to_cpu(cpucp_info->infineon_version),
+				infineon_second_stage_first_instance,
+				infineon_second_stage_second_instance,
+				infineon_second_stage_third_instance);
+	else if (cpucp_info->infineon_second_stage_version)
+		return sprintf(buf, "%#04x:%#04x:%#04x\n",
+				infineon_second_stage_first_instance,
+				infineon_second_stage_second_instance,
+				infineon_second_stage_third_instance);
+	else if (cpucp_info->infineon_version)
 		return sprintf(buf, "%#04x\n", le32_to_cpu(cpucp_info->infineon_version));
+
+	return 0;
 }
 
 static DEVICE_ATTR_RO(vrm_ver);
@@ -126,8 +149,9 @@ static ssize_t cpld_ver_show(struct device *dev, struct device_attribute *attr,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	return sprintf(buf, "0x%08x\n",
-			le32_to_cpu(hdev->asic_prop.cpucp_info.cpld_version));
+	return sprintf(buf, "0x%08x%08x\n",
+		le32_to_cpu(hdev->asic_prop.cpucp_info.cpld_timestamp),
+		le32_to_cpu(hdev->asic_prop.cpucp_info.cpld_version));
 }
 
 static ssize_t cpucp_kernel_ver_show(struct device *dev,
@@ -251,6 +275,12 @@ static ssize_t device_type_show(struct device *dev,
 	case ASIC_GAUDI2B:
 		str = "GAUDI2B";
 		break;
+	case ASIC_GAUDI2C:
+		str = "GAUDI2C";
+		break;
+	case ASIC_GAUDI2D:
+		str = "GAUDI2D";
+		break;
 	default:
 		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
 				hdev->asic_type);
@@ -345,7 +375,7 @@ out:
 }
 
 static ssize_t eeprom_read_handler(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *attr, char *buf, loff_t offset,
+			const struct bin_attribute *attr, char *buf, loff_t offset,
 			size_t max_size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -383,6 +413,21 @@ static ssize_t security_enabled_show(struct device *dev,
 	return sprintf(buf, "%d\n", hdev->asic_prop.fw_security_enabled);
 }
 
+static ssize_t module_id_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n", le32_to_cpu(hdev->asic_prop.cpucp_info.card_location));
+}
+
+static ssize_t parent_device_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", HL_DEV_NAME(hdev));
+}
+
 static DEVICE_ATTR_RO(armcp_kernel_ver);
 static DEVICE_ATTR_RO(armcp_ver);
 static DEVICE_ATTR_RO(cpld_ver);
@@ -402,8 +447,10 @@ static DEVICE_ATTR_RO(thermal_ver);
 static DEVICE_ATTR_RO(uboot_ver);
 static DEVICE_ATTR_RO(fw_os_ver);
 static DEVICE_ATTR_RO(security_enabled);
+static DEVICE_ATTR_RO(module_id);
+static DEVICE_ATTR_RO(parent_device);
 
-static struct bin_attribute bin_attr_eeprom = {
+static const struct bin_attribute bin_attr_eeprom = {
 	.attr = {.name = "eeprom", .mode = (0444)},
 	.size = PAGE_SIZE,
 	.read = eeprom_read_handler
@@ -427,10 +474,12 @@ static struct attribute *hl_dev_attrs[] = {
 	&dev_attr_uboot_ver.attr,
 	&dev_attr_fw_os_ver.attr,
 	&dev_attr_security_enabled.attr,
+	&dev_attr_module_id.attr,
+	&dev_attr_parent_device.attr,
 	NULL,
 };
 
-static struct bin_attribute *hl_dev_bin_attrs[] = {
+static const struct bin_attribute *const hl_dev_bin_attrs[] = {
 	&bin_attr_eeprom,
 	NULL
 };
diff --git a/drivers/accel/habanalabs/gaudi/gaudi.c b/drivers/accel/habanalabs/gaudi/gaudi.c
index 53292d4c15c8..34771d75da9d 100644
--- a/drivers/accel/habanalabs/gaudi/gaudi.c
+++ b/drivers/accel/habanalabs/gaudi/gaudi.c
@@ -614,8 +614,6 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev)
 	else
 		prop->mmu_pgt_size = MMU_PAGE_TABLES_SIZE;
 	prop->mmu_pte_size = HL_PTE_SIZE;
-	prop->mmu_hop_table_size = HOP_TABLE_SIZE_512_PTE;
-	prop->mmu_hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 	prop->dram_page_size = PAGE_SIZE_2MB;
 	prop->device_mem_alloc_default_page_size = prop->dram_page_size;
 	prop->dram_supports_virtual_memory = false;
@@ -637,8 +635,8 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev)
 	prop->pmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->pmmu.last_mask = LAST_MASK;
 	/* TODO: will be duplicated until implementing per-MMU props */
-	prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
-	prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
+	prop->pmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE;
+	prop->pmmu.hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 
 	/* PMMU and HPMMU are the same except of page size */
 	memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
@@ -649,6 +647,7 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev)
 	prop->dmmu.start_addr = (VA_HOST_SPACE_START + VA_HOST_SPACE_SIZE / 2);
 	prop->dmmu.end_addr = VA_HOST_SPACE_END;
 	prop->dmmu.page_size = PAGE_SIZE_2MB;
+	prop->dmmu.pgt_size = prop->mmu_pgt_size;
 
 	prop->cfg_size = CFG_SIZE;
 	prop->max_asid = MAX_ASID;
@@ -1640,10 +1639,8 @@ static int gaudi_late_init(struct hl_device *hdev)
 	}
 
 	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS, 0x0);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
+	if (rc)
 		return rc;
-	}
 
 	/* Scrub both SRAM and DRAM */
 	rc = hdev->asic_funcs->scrub_device_mem(hdev);
@@ -3652,7 +3649,7 @@ static int gaudi_mmu_init(struct hl_device *hdev)
 
 	for (i = 0 ; i < prop->max_asid ; i++) {
 		hop0_addr = prop->mmu_pgt_addr +
-				(i * prop->mmu_hop_table_size);
+				(i * prop->dmmu.hop_table_size);
 
 		rc = gaudi_mmu_update_asid_hop0_addr(hdev, i, hop0_addr);
 		if (rc) {
@@ -4155,13 +4152,7 @@ skip_reset:
 
 static int gaudi_suspend(struct hl_device *hdev)
 {
-	int rc;
-
-	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
-	if (rc)
-		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
-
-	return rc;
+	return hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
 }
 
 static int gaudi_resume(struct hl_device *hdev)
@@ -4177,10 +4168,29 @@ static int gaudi_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
 			VM_DONTCOPY | VM_NORESERVE);
 
+#ifdef _HAS_DMA_MMAP_COHERENT
+	/*
+	 * If dma_alloc_coherent() returns a vmalloc address, set VM_MIXEDMAP
+	 * so vm_insert_page() can handle it safely. Without this, the kernel
+	 * may BUG_ON due to VM_PFNMAP.
+	 */
+	if (is_vmalloc_addr(cpu_addr))
+		vm_flags_set(vma, VM_MIXEDMAP);
+
 	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr,
 				(dma_addr - HOST_PHYS_BASE), size);
 	if (rc)
 		dev_err(hdev->dev, "dma_mmap_coherent error %d", rc);
+#else
+
+	rc = remap_pfn_range(vma, vma->vm_start,
+				virt_to_phys(cpu_addr) >> PAGE_SHIFT,
+				size, vma->vm_page_prot);
+	if (rc)
+		dev_err(hdev->dev, "remap_pfn_range error %d", rc);
+
+ #endif
+
 
 	return rc;
 }
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 819660c684cf..b8c0689dba64 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -158,11 +158,13 @@
 #define RAZWI_INITIATOR_ID_X_Y(xl, yl, xh) \
 	(RAZWI_INITIATOR_ID_X_Y_LOW(xl, yl) | RAZWI_INITIATOR_ID_X_HIGH(xh))
 
-#define PSOC_RAZWI_ENG_STR_SIZE 128
-#define PSOC_RAZWI_MAX_ENG_PER_RTR 5
+#define PSOC_RAZWI_ENG_STR_SIZE			128
+#define PSOC_RAZWI_MAX_ENG_PER_RTR		5
 
 /* HW scrambles only bits 0-25 */
-#define HW_UNSCRAMBLED_BITS_MASK GENMASK_ULL(63, 26)
+#define HW_UNSCRAMBLED_BITS_MASK		GENMASK_ULL(63, 26)
+
+#define GAUDI2_GLBL_ERR_MAX_CAUSE_NUM		17
 
 struct gaudi2_razwi_info {
 	u32 axuser_xy;
@@ -726,6 +728,354 @@ static const int gaudi2_dma_core_async_event_id[] = {
 	[DMA_CORE_ID_KDMA] = GAUDI2_EVENT_KDMA0_CORE,
 };
 
+const char *gaudi2_engine_id_str[] = {
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_EDMA_0),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_EDMA_1),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_MME),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_0),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_1),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_2),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_3),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_4),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_5),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_DEC_0),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_DEC_1),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_EDMA_0),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_EDMA_1),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_MME),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_0),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_1),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_2),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_3),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_4),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_TPC_5),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_DEC_0),
+	__stringify(GAUDI2_DCORE1_ENGINE_ID_DEC_1),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_EDMA_0),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_EDMA_1),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_MME),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_0),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_1),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_2),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_3),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_4),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_TPC_5),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_DEC_0),
+	__stringify(GAUDI2_DCORE2_ENGINE_ID_DEC_1),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_EDMA_0),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_EDMA_1),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_MME),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_0),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_1),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_2),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_3),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_4),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_TPC_5),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_DEC_0),
+	__stringify(GAUDI2_DCORE3_ENGINE_ID_DEC_1),
+	__stringify(GAUDI2_DCORE0_ENGINE_ID_TPC_6),
+	__stringify(GAUDI2_ENGINE_ID_PDMA_0),
+	__stringify(GAUDI2_ENGINE_ID_PDMA_1),
+	__stringify(GAUDI2_ENGINE_ID_ROT_0),
+	__stringify(GAUDI2_ENGINE_ID_ROT_1),
+	__stringify(GAUDI2_PCIE_ENGINE_ID_DEC_0),
+	__stringify(GAUDI2_PCIE_ENGINE_ID_DEC_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC0_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC0_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC1_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC1_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC2_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC2_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC3_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC3_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC4_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC4_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC5_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC5_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC6_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC6_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC7_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC7_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC8_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC8_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC9_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC9_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC10_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC10_1),
+	__stringify(GAUDI2_ENGINE_ID_NIC11_0),
+	__stringify(GAUDI2_ENGINE_ID_NIC11_1),
+	__stringify(GAUDI2_ENGINE_ID_PCIE),
+	__stringify(GAUDI2_ENGINE_ID_PSOC),
+	__stringify(GAUDI2_ENGINE_ID_ARC_FARM),
+	__stringify(GAUDI2_ENGINE_ID_KDMA),
+	__stringify(GAUDI2_ENGINE_ID_SIZE),
+};
+
+const char *gaudi2_queue_id_str[] = {
+	__stringify(GAUDI2_QUEUE_ID_PDMA_0_0),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_0_1),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_0_2),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_0_3),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_1_0),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_1_1),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_1_2),
+	__stringify(GAUDI2_QUEUE_ID_PDMA_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_MME_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_MME_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_MME_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_MME_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_2_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_2_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_2_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_2_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_3_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_3_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_3_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_3_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_4_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_4_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_4_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_4_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_5_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_5_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_5_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_5_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_6_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_6_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_6_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE0_TPC_6_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_MME_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_MME_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_MME_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_MME_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_2_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_2_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_2_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_2_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_3_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_3_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_3_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_3_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_4_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_4_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_4_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_4_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_5_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_5_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_5_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE1_TPC_5_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_MME_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_MME_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_MME_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_MME_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_2_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_2_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_2_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_2_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_3_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_3_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_3_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_3_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_4_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_4_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_4_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_4_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_5_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_5_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_5_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE2_TPC_5_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_MME_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_MME_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_MME_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_MME_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_0_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_0_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_0_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_0_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_1_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_1_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_1_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_1_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_2_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_2_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_2_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_2_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_3_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_3_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_3_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_3_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_4_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_4_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_4_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_4_3),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_5_0),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_5_1),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_5_2),
+	__stringify(GAUDI2_QUEUE_ID_DCORE3_TPC_5_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_0_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_0_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_0_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_0_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_1_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_1_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_1_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_1_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_2_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_2_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_2_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_2_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_3_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_3_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_3_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_3_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_4_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_4_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_4_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_4_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_5_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_5_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_5_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_5_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_6_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_6_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_6_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_6_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_7_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_7_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_7_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_7_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_8_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_8_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_8_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_8_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_9_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_9_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_9_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_9_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_10_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_10_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_10_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_10_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_11_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_11_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_11_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_11_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_12_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_12_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_12_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_12_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_13_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_13_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_13_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_13_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_14_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_14_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_14_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_14_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_15_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_15_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_15_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_15_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_16_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_16_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_16_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_16_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_17_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_17_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_17_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_17_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_18_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_18_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_18_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_18_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_19_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_19_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_19_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_19_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_20_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_20_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_20_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_20_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_21_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_21_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_21_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_21_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_22_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_22_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_22_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_22_3),
+	__stringify(GAUDI2_QUEUE_ID_NIC_23_0),
+	__stringify(GAUDI2_QUEUE_ID_NIC_23_1),
+	__stringify(GAUDI2_QUEUE_ID_NIC_23_2),
+	__stringify(GAUDI2_QUEUE_ID_NIC_23_3),
+	__stringify(GAUDI2_QUEUE_ID_ROT_0_0),
+	__stringify(GAUDI2_QUEUE_ID_ROT_0_1),
+	__stringify(GAUDI2_QUEUE_ID_ROT_0_2),
+	__stringify(GAUDI2_QUEUE_ID_ROT_0_3),
+	__stringify(GAUDI2_QUEUE_ID_ROT_1_0),
+	__stringify(GAUDI2_QUEUE_ID_ROT_1_1),
+	__stringify(GAUDI2_QUEUE_ID_ROT_1_2),
+	__stringify(GAUDI2_QUEUE_ID_ROT_1_3),
+	__stringify(GAUDI2_QUEUE_ID_CPU_PQ),
+	__stringify(GAUDI2_QUEUE_ID_SIZE),
+};
+
 static const char * const gaudi2_qm_sei_error_cause[GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE] = {
 	"qman sei intr",
 	"arc sei intr"
@@ -2308,11 +2658,26 @@ static int set_number_of_functional_hbms(struct hl_device *hdev)
 	return 0;
 }
 
+static bool gaudi2_is_edma_queue_id(u32 queue_id)
+{
+
+	switch (queue_id) {
+	case GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3:
+	case GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3:
+	case GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3:
+	case GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int gaudi2_set_dram_properties(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	u32 basic_hbm_page_size;
-	int rc;
+	u64 hbm_drv_base_offset = 0, edma_pq_base_addr;
+	u32 basic_hbm_page_size, edma_idx = 0;
+	int rc, i;
 
 	rc = set_number_of_functional_hbms(hdev);
 	if (rc)
@@ -2356,9 +2721,35 @@ static int gaudi2_set_dram_properties(struct hl_device *hdev)
 	prop->dmmu.start_addr = prop->dram_base_address +
 			(prop->dram_page_size *
 				DIV_ROUND_UP_SECTOR_T(prop->dram_size, prop->dram_page_size));
-
 	prop->dmmu.end_addr = prop->dmmu.start_addr + prop->dram_page_size *
 			div_u64((VA_HBM_SPACE_END - prop->dmmu.start_addr), prop->dmmu.page_size);
+	/*
+	 * Driver can't share an (48MB) HBM page with the F/W in order to prevent FW to block
+	 * the driver part by range register, so it must start at the next (48MB) page
+	 */
+	hbm_drv_base_offset = roundup(CPU_FW_IMAGE_SIZE, prop->num_functional_hbms * SZ_8M);
+
+	/*
+	 * The NIC driver section size and the HMMU page tables section in the HBM needs
+	 * to be the remaining size in the first dram page after taking into
+	 * account the F/W image size
+	 */
+
+	/* Reserve region in HBM for HMMU page tables */
+	prop->mmu_pgt_addr = DRAM_PHYS_BASE + hbm_drv_base_offset +
+				((prop->dram_page_size - hbm_drv_base_offset) -
+				(HMMU_PAGE_TABLES_SIZE + EDMA_PQS_SIZE + EDMA_SCRATCHPAD_SIZE));
+
+	/* Set EDMA PQs HBM addresses */
+	edma_pq_base_addr = prop->mmu_pgt_addr + HMMU_PAGE_TABLES_SIZE;
+
+	for (i = 0 ; i < GAUDI2_QUEUE_ID_CPU_PQ ; i++) {
+		if (gaudi2_is_edma_queue_id(i)) {
+			prop->hw_queues_props[i].q_dram_bd_address = edma_pq_base_addr +
+							(edma_idx * HL_QUEUE_SIZE_IN_BYTES);
+			edma_idx++;
+		}
+	}
 
 	return 0;
 }
@@ -2368,7 +2759,7 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct hw_queue_properties *q_props;
 	u32 num_sync_stream_queues = 0;
-	int i;
+	int i, rc;
 
 	prop->max_queues = GAUDI2_QUEUE_ID_SIZE;
 	prop->hw_queues_props = kcalloc(prop->max_queues, sizeof(struct hw_queue_properties),
@@ -2391,6 +2782,9 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
 		}
 
 		q_props[i].cb_alloc_flags = CB_ALLOC_USER;
+
+		if (gaudi2_is_edma_queue_id(i))
+			q_props[i].dram_bd = 1;
 	}
 
 	q_props[GAUDI2_QUEUE_ID_CPU_PQ].type = QUEUE_TYPE_CPU;
@@ -2419,46 +2813,43 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
 
 	prop->rotator_enabled_mask = BIT(NUM_OF_ROT) - 1;
 
-	if (hdev->pldm)
-		prop->mmu_pgt_size = 0x800000; /* 8MB */
-	else
-		prop->mmu_pgt_size = MMU_PAGE_TABLES_INITIAL_SIZE;
+	prop->max_asid = 2;
 
+	prop->dmmu.pgt_size = HMMU_PAGE_TABLES_SIZE;
 	prop->mmu_pte_size = HL_PTE_SIZE;
-	prop->mmu_hop_table_size = HOP_TABLE_SIZE_512_PTE;
-	prop->mmu_hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 
 	prop->dmmu.hop_shifts[MMU_HOP0] = DHOP0_SHIFT;
 	prop->dmmu.hop_shifts[MMU_HOP1] = DHOP1_SHIFT;
 	prop->dmmu.hop_shifts[MMU_HOP2] = DHOP2_SHIFT;
 	prop->dmmu.hop_shifts[MMU_HOP3] = DHOP3_SHIFT;
-	prop->dmmu.hop_shifts[MMU_HOP4] = DHOP4_SHIFT;
 	prop->dmmu.hop_masks[MMU_HOP0] = DHOP0_MASK;
 	prop->dmmu.hop_masks[MMU_HOP1] = DHOP1_MASK;
 	prop->dmmu.hop_masks[MMU_HOP2] = DHOP2_MASK;
 	prop->dmmu.hop_masks[MMU_HOP3] = DHOP3_MASK;
-	prop->dmmu.hop_masks[MMU_HOP4] = DHOP4_MASK;
 	prop->dmmu.page_size = PAGE_SIZE_1GB;
-	prop->dmmu.num_hops = MMU_ARCH_6_HOPS;
+	prop->dmmu.num_hops = MMU_ARCH_4_HOPS;
 	prop->dmmu.last_mask = LAST_MASK;
-	prop->dmmu.host_resident = 1;
-	prop->dmmu.hop_table_size = prop->mmu_hop_table_size;
-	prop->dmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
+	prop->dmmu.host_resident = 0;
+	prop->dmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE;
+	prop->dmmu.hop0_tables_total_size = HOP_TABLE_SIZE_512_PTE * prop->max_asid;
 
-	/*
-	 * this is done in order to be able to validate FW descriptor (i.e. validating that
-	 * the addresses and allocated space for FW image does not cross memory bounds).
-	 * for this reason we set the DRAM size to the minimum possible and later it will
-	 * be modified according to what reported in the cpucp info packet
+	/* As we need to set the pgt address in dram for HMMU init so we cannot
+	 * wait to the fw cpucp info to set the dram props as mmu init comes before
+	 * hw init
 	 */
-	prop->dram_size = (GAUDI2_HBM_NUM - 1) * SZ_16G;
+	rc = hdev->asic_funcs->set_dram_properties(hdev);
+	if (rc)
+		goto free_qprops;
+
+	prop->mmu_pgt_size = PMMU_PAGE_TABLES_SIZE;
 
+	prop->pmmu.pgt_size = prop->mmu_pgt_size;
 	hdev->pmmu_huge_range = true;
 	prop->pmmu.host_resident = 1;
 	prop->pmmu.num_hops = MMU_ARCH_6_HOPS;
 	prop->pmmu.last_mask = LAST_MASK;
-	prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
-	prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
+	prop->pmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE;
+	prop->pmmu.hop0_tables_total_size = HOP_TABLE_SIZE_512_PTE * prop->max_asid;
 
 	prop->hints_host_reserved_va_range.start_addr = RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START;
 	prop->hints_host_reserved_va_range.end_addr = RESERVED_VA_RANGE_FOR_ARC_ON_HOST_END;
@@ -2516,7 +2907,6 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
 	prop->max_num_of_engines = GAUDI2_ENGINE_ID_SIZE;
 	prop->num_engine_cores = CPU_ID_MAX;
 	prop->cfg_size = CFG_SIZE;
-	prop->max_asid = MAX_ASID;
 	prop->num_of_events = GAUDI2_EVENT_SIZE;
 
 	prop->supports_engine_modes = true;
@@ -2559,7 +2949,13 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
 
 	prop->hbw_flush_reg = mmPCIE_WRAP_SPECIAL_GLBL_SPARE_0;
 
+	prop->supports_advanced_cpucp_rc = true;
+
 	return 0;
+
+free_qprops:
+	kfree(prop->hw_queues_props);
+	return rc;
 }
 
 static int gaudi2_pci_bars_map(struct hl_device *hdev)
@@ -3033,6 +3429,25 @@ static int gaudi2_fetch_psoc_frequency(struct hl_device *hdev)
 	return 0;
 }
 
+static int gaudi2_mmu_clear_pgt_range(struct hl_device *hdev)
+{
+	struct gaudi2_device *gaudi2 = hdev->asic_specific;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	if (!(gaudi2->hw_cap_initialized & HW_CAP_MMU_MASK))
+		return 0;
+
+	if (prop->dmmu.host_resident)
+		return 0;
+
+	rc = gaudi2_memset_device_memory(hdev, prop->mmu_pgt_addr, prop->dmmu.pgt_size, 0);
+	if (rc)
+		dev_err(hdev->dev, "Failed to clear mmu pgt");
+
+	return rc;
+}
+
 static int gaudi2_early_init(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
@@ -3083,7 +3498,6 @@ static int gaudi2_early_init(struct hl_device *hdev)
 	rc = hl_fw_read_preboot_status(hdev);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
-			/* we are already on failure flow, so don't check if hw_fini fails. */
 			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
@@ -3095,6 +3509,13 @@ static int gaudi2_early_init(struct hl_device *hdev)
 			dev_err(hdev->dev, "failed to reset HW in dirty state (%d)\n", rc);
 			goto pci_fini;
 		}
+
+		rc = hl_fw_read_preboot_status(hdev);
+		if (rc) {
+			if (hdev->reset_on_preboot_fail)
+				hdev->asic_funcs->hw_fini(hdev, true, false);
+			goto pci_fini;
+		}
 	}
 
 	return 0;
@@ -3243,14 +3664,10 @@ static int gaudi2_late_init(struct hl_device *hdev)
 	struct gaudi2_device *gaudi2 = hdev->asic_specific;
 	int rc;
 
-	hdev->asic_prop.supports_advanced_cpucp_rc = true;
-
 	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS,
 					gaudi2->virt_msix_db_dma_addr);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
+	if (rc)
 		return rc;
-	}
 
 	rc = gaudi2_fetch_psoc_frequency(hdev);
 	if (rc) {
@@ -3258,6 +3675,12 @@ static int gaudi2_late_init(struct hl_device *hdev)
 		goto disable_pci_access;
 	}
 
+	rc = gaudi2_mmu_clear_pgt_range(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to clear MMU page tables range\n");
+		goto disable_pci_access;
+	}
+
 	gaudi2_init_arcs(hdev);
 
 	rc = gaudi2_scrub_arcs_dccm(hdev);
@@ -3518,7 +3941,7 @@ static int gaudi2_special_blocks_config(struct hl_device *hdev)
 	int i, rc;
 
 	/* Configure Special blocks */
-	prop->glbl_err_cause_num = GAUDI2_NUM_OF_GLBL_ERR_CAUSE;
+	prop->glbl_err_max_cause_num = GAUDI2_GLBL_ERR_MAX_CAUSE_NUM;
 	prop->num_of_special_blocks = ARRAY_SIZE(gaudi2_special_blocks);
 	prop->special_blocks = kmalloc_array(prop->num_of_special_blocks,
 			sizeof(*prop->special_blocks), GFP_KERNEL);
@@ -3697,13 +4120,7 @@ static int gaudi2_sw_init(struct hl_device *hdev)
 
 	spin_lock_init(&gaudi2->hw_queues_lock);
 
-	gaudi2->scratchpad_kernel_address = hl_asic_dma_alloc_coherent(hdev, PAGE_SIZE,
-							&gaudi2->scratchpad_bus_address,
-							GFP_KERNEL | __GFP_ZERO);
-	if (!gaudi2->scratchpad_kernel_address) {
-		rc = -ENOMEM;
-		goto free_virt_msix_db_mem;
-	}
+	gaudi2->scratchpad_bus_address = prop->mmu_pgt_addr + HMMU_PAGE_TABLES_SIZE + EDMA_PQS_SIZE;
 
 	gaudi2_user_mapped_blocks_init(hdev);
 
@@ -3718,7 +4135,7 @@ static int gaudi2_sw_init(struct hl_device *hdev)
 	prop->supports_compute_reset = true;
 
 	/* Event queue sanity check added in FW version 1.11 */
-	if (hl_is_fw_sw_ver_below(hdev, 1, 11))
+	if (hl_fw_version_cmp(hdev, 1, 11, 0) < 0)
 		hdev->event_queue.check_eqe_index = false;
 	else
 		hdev->event_queue.check_eqe_index = true;
@@ -3727,19 +4144,18 @@ static int gaudi2_sw_init(struct hl_device *hdev)
 
 	rc = gaudi2_special_blocks_iterator_config(hdev);
 	if (rc)
-		goto free_scratchpad_mem;
+		goto free_virt_msix_db_mem;
 
 	rc = gaudi2_test_queues_msgs_alloc(hdev);
 	if (rc)
 		goto special_blocks_free;
 
+	hdev->heartbeat_debug_info.cpu_queue_id = GAUDI2_QUEUE_ID_CPU_PQ;
+
 	return 0;
 
 special_blocks_free:
 	gaudi2_special_blocks_iterator_free(hdev);
-free_scratchpad_mem:
-	hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
-				  gaudi2->scratchpad_bus_address);
 free_virt_msix_db_mem:
 	hl_cpu_accessible_dma_pool_free(hdev, prop->pmmu.page_size, gaudi2->virt_msix_db_cpu_addr);
 free_cpu_accessible_dma_pool:
@@ -3770,9 +4186,6 @@ static int gaudi2_sw_fini(struct hl_device *hdev)
 	hl_asic_dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem,
 						hdev->cpu_accessible_dma_address);
 
-	hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
-					gaudi2->scratchpad_bus_address);
-
 	dma_pool_destroy(hdev->dma_pool);
 
 	kfree(gaudi2);
@@ -4254,6 +4667,8 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
 	if (gaudi2->hw_cap_initialized & HW_CAP_MSIX)
 		return 0;
 
+	hl_init_cpu_for_irq(hdev);
+
 	rc = pci_alloc_irq_vectors(hdev->pdev, GAUDI2_MSIX_ENTRIES, GAUDI2_MSIX_ENTRIES,
 					PCI_IRQ_MSIX);
 	if (rc < 0) {
@@ -4307,6 +4722,7 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
 			i++, j++, user_irq_init_cnt++) {
 
 		irq = pci_irq_vector(hdev->pdev, i);
+		hl_set_irq_affinity(hdev, irq);
 		rc = request_irq(irq, hl_irq_user_interrupt_handler, 0, gaudi2_irq_name(i),
 				&hdev->user_interrupt[j]);
 		if (rc) {
@@ -4333,6 +4749,7 @@ free_user_irq:
 			i < GAUDI2_IRQ_NUM_USER_FIRST + user_irq_init_cnt ; i++, j++) {
 
 		irq = pci_irq_vector(hdev->pdev, i);
+		irq_set_affinity_and_hint(irq, NULL);
 		free_irq(irq, &hdev->user_interrupt[j]);
 	}
 	irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
@@ -4413,6 +4830,7 @@ static void gaudi2_disable_msix(struct hl_device *hdev)
 			k < hdev->asic_prop.user_interrupt_count ; i++, j++, k++) {
 
 		irq = pci_irq_vector(hdev->pdev, i);
+		irq_set_affinity_and_hint(irq, NULL);
 		free_irq(irq, &hdev->user_interrupt[j]);
 	}
 
@@ -4772,7 +5190,7 @@ static void gaudi2_halt_engines(struct hl_device *hdev, bool hard_reset, bool fw
 	else
 		wait_timeout_ms = GAUDI2_RESET_WAIT_MSEC;
 
-	if (fw_reset)
+	if (fw_reset || hdev->cpld_shutdown)
 		goto skip_engines;
 
 	gaudi2_stop_dma_qmans(hdev);
@@ -4957,10 +5375,17 @@ static void gaudi2_init_qman_pq(struct hl_device *hdev, u32 reg_base,
 		q = &hdev->kernel_queues[queue_id_base + pq_id];
 		pq_offset = pq_id * 4;
 
-		WREG32(reg_base + QM_PQ_BASE_LO_0_OFFSET + pq_offset,
-				lower_32_bits(q->bus_address));
-		WREG32(reg_base + QM_PQ_BASE_HI_0_OFFSET + pq_offset,
-				upper_32_bits(q->bus_address));
+		if (q->dram_bd) {
+			WREG32(reg_base + QM_PQ_BASE_LO_0_OFFSET + pq_offset,
+					lower_32_bits(q->pq_dram_address));
+			WREG32(reg_base + QM_PQ_BASE_HI_0_OFFSET + pq_offset,
+					upper_32_bits(q->pq_dram_address));
+		} else {
+			WREG32(reg_base + QM_PQ_BASE_LO_0_OFFSET + pq_offset,
+					lower_32_bits(q->bus_address));
+			WREG32(reg_base + QM_PQ_BASE_HI_0_OFFSET + pq_offset,
+					upper_32_bits(q->bus_address));
+		}
 		WREG32(reg_base + QM_PQ_SIZE_0_OFFSET + pq_offset, ilog2(HL_QUEUE_LENGTH));
 		WREG32(reg_base + QM_PQ_PI_0_OFFSET + pq_offset, 0);
 		WREG32(reg_base + QM_PQ_CI_0_OFFSET + pq_offset, 0);
@@ -5847,7 +6272,8 @@ static int gaudi2_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_har
 	return rc;
 }
 
-static int gaudi2_mmu_update_hop0_addr(struct hl_device *hdev, u32 stlb_base)
+static int gaudi2_mmu_update_hop0_addr(struct hl_device *hdev, u32 stlb_base,
+									bool host_resident_pgt)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u64 hop0_addr;
@@ -5859,7 +6285,11 @@ static int gaudi2_mmu_update_hop0_addr(struct hl_device *hdev, u32 stlb_base)
 		max_asid = min((u32) 8, max_asid);
 
 	for (asid = 0 ; asid < max_asid ; asid++) {
-		hop0_addr = hdev->mmu_priv.hr.mmu_asid_hop0[asid].phys_addr;
+		if (host_resident_pgt)
+			hop0_addr = hdev->mmu_priv.hr.mmu_asid_hop0[asid].phys_addr;
+		else
+			hop0_addr = prop->mmu_pgt_addr + (asid * prop->dmmu.hop_table_size);
+
 		rc = gaudi2_mmu_update_asid_hop0_addr(hdev, stlb_base, asid, hop0_addr);
 		if (rc) {
 			dev_err(hdev->dev, "failed to set hop0 addr for asid %d\n", asid);
@@ -5870,7 +6300,8 @@ static int gaudi2_mmu_update_hop0_addr(struct hl_device *hdev, u32 stlb_base)
 	return 0;
 }
 
-static int gaudi2_mmu_init_common(struct hl_device *hdev, u32 mmu_base, u32 stlb_base)
+static int gaudi2_mmu_init_common(struct hl_device *hdev, u32 mmu_base, u32 stlb_base,
+								bool host_resident_pgt)
 {
 	u32 status, timeout_usec;
 	int rc;
@@ -5893,7 +6324,7 @@ static int gaudi2_mmu_init_common(struct hl_device *hdev, u32 mmu_base, u32 stlb
 	if (rc)
 		dev_notice_ratelimited(hdev->dev, "Timeout when waiting for MMU SRAM init\n");
 
-	rc = gaudi2_mmu_update_hop0_addr(hdev, stlb_base);
+	rc = gaudi2_mmu_update_hop0_addr(hdev, stlb_base, host_resident_pgt);
 	if (rc)
 		return rc;
 
@@ -5917,6 +6348,7 @@ static int gaudi2_mmu_init_common(struct hl_device *hdev, u32 mmu_base, u32 stlb
 
 static int gaudi2_pci_mmu_init(struct hl_device *hdev)
 {
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct gaudi2_device *gaudi2 = hdev->asic_specific;
 	u32 mmu_base, stlb_base;
 	int rc;
@@ -5956,7 +6388,7 @@ static int gaudi2_pci_mmu_init(struct hl_device *hdev)
 
 	WREG32(mmu_base + MMU_SPI_SEI_MASK_OFFSET, GAUDI2_PMMU_SPI_SEI_ENABLE_MASK);
 
-	rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base);
+	rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base, prop->pmmu.host_resident);
 	if (rc)
 		return rc;
 
@@ -6008,7 +6440,7 @@ static int gaudi2_dcore_hmmu_init(struct hl_device *hdev, int dcore_id,
 
 	WREG32(mmu_base + MMU_SPI_SEI_MASK_OFFSET, GAUDI2_HMMU_SPI_SEI_ENABLE_MASK);
 
-	rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base);
+	rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base, prop->dmmu.host_resident);
 	if (rc)
 		return rc;
 
@@ -6236,26 +6668,6 @@ static void gaudi2_execute_hard_reset(struct hl_device *hdev)
 	WREG32(mmPSOC_RESET_CONF_SW_ALL_RST, 1);
 }
 
-static int gaudi2_get_soft_rst_done_indication(struct hl_device *hdev, u32 poll_timeout_us)
-{
-	int i, rc = 0;
-	u32 reg_val;
-
-	for (i = 0 ; i < GAUDI2_RESET_POLL_CNT ; i++)
-		rc = hl_poll_timeout(
-			hdev,
-			mmCPU_RST_STATUS_TO_HOST,
-			reg_val,
-			reg_val == CPU_RST_STATUS_SOFT_RST_DONE,
-			1000,
-			poll_timeout_us);
-
-	if (rc)
-		dev_err(hdev->dev, "Timeout while waiting for FW to complete soft reset (0x%x)\n",
-				reg_val);
-	return rc;
-}
-
 /**
  * gaudi2_execute_soft_reset - execute soft reset by driver/FW
  *
@@ -6268,23 +6680,8 @@ static int gaudi2_get_soft_rst_done_indication(struct hl_device *hdev, u32 poll_
 static int gaudi2_execute_soft_reset(struct hl_device *hdev, bool driver_performs_reset,
 						u32 poll_timeout_us)
 {
-	int rc;
-
-	if (!driver_performs_reset) {
-		if (hl_is_fw_sw_ver_below(hdev, 1, 10)) {
-			/* set SP to indicate reset request sent to FW */
-			WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
-
-			WREG32(mmGIC_HOST_SOFT_RST_IRQ_POLL_REG,
-				gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
-
-			/* wait for f/w response */
-			rc = gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
-		} else {
-			rc = hl_fw_send_soft_reset(hdev);
-		}
-		return rc;
-	}
+	if (!driver_performs_reset)
+		return hl_fw_send_soft_reset(hdev);
 
 	/* Block access to engines, QMANs and SM during reset, these
 	 * RRs will be reconfigured after soft reset.
@@ -6424,13 +6821,7 @@ skip_reset:
 
 static int gaudi2_suspend(struct hl_device *hdev)
 {
-	int rc;
-
-	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
-	if (rc)
-		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
-
-	return rc;
+	return hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
 }
 
 static int gaudi2_resume(struct hl_device *hdev)
@@ -6447,6 +6838,13 @@ static int gaudi2_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 			VM_DONTCOPY | VM_NORESERVE);
 
 #ifdef _HAS_DMA_MMAP_COHERENT
+	/*
+	 * If dma_alloc_coherent() returns a vmalloc address, set VM_MIXEDMAP
+	 * so vm_insert_page() can handle it safely. Without this, the kernel
+	 * may BUG_ON due to VM_PFNMAP.
+	 */
+	if (is_vmalloc_addr(cpu_addr))
+		vm_flags_set(vma, VM_MIXEDMAP);
 
 	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size);
 	if (rc)
@@ -6737,7 +7135,8 @@ static int gaudi2_validate_cb_address(struct hl_device *hdev, struct hl_cs_parse
 	struct gaudi2_device *gaudi2 = hdev->asic_specific;
 
 	if (!gaudi2_is_queue_enabled(hdev, parser->hw_queue_id)) {
-		dev_err(hdev->dev, "h/w queue %d is disabled\n", parser->hw_queue_id);
+		dev_err(hdev->dev, "h/w queue %s is disabled\n",
+		GAUDI2_QUEUE_ID_TO_STR(parser->hw_queue_id));
 		return -EINVAL;
 	}
 
@@ -6989,7 +7388,8 @@ static int gaudi2_test_queue_send_msg_short(struct hl_device *hdev, u32 hw_queue
 	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, pkt_size, msg_info->dma_addr);
 	if (rc)
 		dev_err(hdev->dev,
-			"Failed to send msg_short packet to H/W queue %d\n", hw_queue_id);
+			"Failed to send msg_short packet to H/W queue %s\n",
+			GAUDI2_QUEUE_ID_TO_STR(hw_queue_id));
 
 	return rc;
 }
@@ -7015,8 +7415,8 @@ static int gaudi2_test_queue_wait_completion(struct hl_device *hdev, u32 hw_queu
 			timeout_usec);
 
 	if (rc == -ETIMEDOUT) {
-		dev_err(hdev->dev, "H/W queue %d test failed (SOB_OBJ_0 == 0x%x)\n",
-			hw_queue_id, tmp);
+		dev_err(hdev->dev, "H/W queue %s test failed (SOB_OBJ_0 == 0x%x)\n",
+			GAUDI2_QUEUE_ID_TO_STR(hw_queue_id), tmp);
 		rc = -EIO;
 	}
 
@@ -7046,7 +7446,7 @@ static int gaudi2_test_queues(struct hl_device *hdev)
 
 	/* send test message on all enabled Qs */
 	for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ; i++) {
-		if (!gaudi2_is_queue_enabled(hdev, i))
+		if (!gaudi2_is_queue_enabled(hdev, i) || gaudi2_is_edma_queue_id(i))
 			continue;
 
 		msg_info = &gaudi2->queues_test_info[i - GAUDI2_QUEUE_ID_PDMA_0_0];
@@ -7063,7 +7463,7 @@ static int gaudi2_test_queues(struct hl_device *hdev)
 
 	/* verify that all messages were processed */
 	for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ; i++) {
-		if (!gaudi2_is_queue_enabled(hdev, i))
+		if (!gaudi2_is_queue_enabled(hdev, i) || gaudi2_is_edma_queue_id(i))
 			continue;
 
 		rc = gaudi2_test_queue_wait_completion(hdev, i, sob_val);
@@ -7836,7 +8236,7 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 	bool has_block_id = false;
 	u16 block_id;
 
-	if (!hl_is_fw_sw_ver_below(hdev, 1, 12))
+	if (hl_fw_version_cmp(hdev, 1, 12, 0) >= 0)
 		has_block_id = true;
 
 	ecc_address = le64_to_cpu(ecc_data->ecc_address);
@@ -7858,39 +8258,44 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 	return !!ecc_data->is_critical;
 }
 
-static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u64 event_mask)
+static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u32 engine_id)
 {
-	u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
-	u64 cq_ptr, arc_cq_ptr, cp_current_inst;
+	struct undefined_opcode_info *undef_opcode = &hdev->captured_err_info.undef_opcode;
+	u64 cq_ptr, cp_current_inst;
+	u32 lo, hi, cq_size, cp_sts;
+	bool is_arc_cq;
 
-	lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
-	hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
-	cq_ptr = ((u64) hi) << 32 | lo;
-	cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
+	cp_sts = RREG32(qman_base + QM_CP_STS_4_OFFSET);
+	is_arc_cq = FIELD_GET(PDMA0_QM_CP_STS_CUR_CQ_MASK, cp_sts); /* 0 - legacy CQ, 1 - ARC_CQ */
 
-	lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
-	hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
-	arc_cq_ptr = ((u64) hi) << 32 | lo;
-	arc_cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
+	if (is_arc_cq) {
+		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_STS_OFFSET);
+		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_STS_OFFSET);
+		cq_ptr = ((u64) hi) << 32 | lo;
+		cq_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_STS_OFFSET);
+	} else {
+		lo = RREG32(qman_base + QM_CQ_PTR_LO_STS_4_OFFSET);
+		hi = RREG32(qman_base + QM_CQ_PTR_HI_STS_4_OFFSET);
+		cq_ptr = ((u64) hi) << 32 | lo;
+		cq_size = RREG32(qman_base + QM_CQ_TSIZE_STS_4_OFFSET);
+	}
 
 	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
 	hi = RREG32(qman_base + QM_CP_CURRENT_INST_HI_4_OFFSET);
 	cp_current_inst = ((u64) hi) << 32 | lo;
 
 	dev_info(hdev->dev,
-		"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
-		cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
+		"LowerQM. %sCQ: {ptr %#llx, size %u}, CP: {instruction %#018llx}\n",
+		is_arc_cq ? "ARC_" : "", cq_ptr, cq_size, cp_current_inst);
 
-	if (event_mask & HL_NOTIFIER_EVENT_UNDEFINED_OPCODE) {
-		if (arc_cq_ptr) {
-			hdev->captured_err_info.undef_opcode.cq_addr = arc_cq_ptr;
-			hdev->captured_err_info.undef_opcode.cq_size = arc_cq_ptr_size;
-		} else {
-			hdev->captured_err_info.undef_opcode.cq_addr = cq_ptr;
-			hdev->captured_err_info.undef_opcode.cq_size = cq_ptr_size;
-		}
-
-		hdev->captured_err_info.undef_opcode.stream_id = QMAN_STREAMS;
+	if (undef_opcode->write_enable) {
+		memset(undef_opcode, 0, sizeof(*undef_opcode));
+		undef_opcode->timestamp = ktime_get();
+		undef_opcode->cq_addr = cq_ptr;
+		undef_opcode->cq_size = cq_size;
+		undef_opcode->engine_id = engine_id;
+		undef_opcode->stream_id = QMAN_STREAMS;
+		undef_opcode->write_enable = 0;
 	}
 }
 
@@ -7929,21 +8334,12 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
 				error_count++;
 			}
 
-		if (i == QMAN_STREAMS && error_count) {
-			/* check for undefined opcode */
-			if (glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK &&
-					hdev->captured_err_info.undef_opcode.write_enable) {
-				memset(&hdev->captured_err_info.undef_opcode, 0,
-						sizeof(hdev->captured_err_info.undef_opcode));
-
-				hdev->captured_err_info.undef_opcode.write_enable = false;
-				hdev->captured_err_info.undef_opcode.timestamp = ktime_get();
-				hdev->captured_err_info.undef_opcode.engine_id =
-							gaudi2_queue_id_to_engine_id[qid_base];
-				*event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
-			}
-
-			handle_lower_qman_data_on_err(hdev, qman_base, *event_mask);
+		/* Check for undefined opcode error in lower QM */
+		if ((i == QMAN_STREAMS) &&
+				(glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK)) {
+			handle_lower_qman_data_on_err(hdev, qman_base,
+							gaudi2_queue_id_to_engine_id[qid_base]);
+			*event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
 		}
 	}
 
@@ -8091,13 +8487,7 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
 		}
 
 		hbw_rtr_id = gaudi2_tpc_initiator_hbw_rtr_id[module_idx];
-
-		if (hl_is_fw_sw_ver_below(hdev, 1, 9) &&
-				!hdev->asic_prop.fw_security_enabled &&
-				((module_idx == 0) || (module_idx == 1)))
-			lbw_rtr_id = DCORE0_RTR0;
-		else
-			lbw_rtr_id = gaudi2_tpc_initiator_lbw_rtr_id[module_idx];
+		lbw_rtr_id = gaudi2_tpc_initiator_lbw_rtr_id[module_idx];
 		break;
 	case RAZWI_MME:
 		sprintf(initiator_name, "MME_%u", module_idx);
@@ -8911,9 +9301,6 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
 	u32 error_count = 0;
 	int i;
 
-	gaudi2_print_event(hdev, event_type, true,
-		"intr_cause_data: %#llx", intr_cause_data);
-
 	for (i = 0 ; i < GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE ; i++) {
 		if (!(intr_cause_data & BIT_ULL(i)))
 			continue;
@@ -8922,15 +9309,16 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
 			"err cause: %s", gaudi2_pcie_addr_dec_error_cause[i]);
 		error_count++;
 
-		/*
-		 * Always check for LBW and HBW additional info as the indication itself is
-		 * sometimes missing
-		 */
+		switch (intr_cause_data & BIT_ULL(i)) {
+		case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_AXI_LBW_ERR_INTR_MASK:
+			hl_check_for_glbl_errors(hdev);
+			break;
+		case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_BAD_ACCESS_INTR_MASK:
+			gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
+			break;
+		}
 	}
 
-	hl_check_for_glbl_errors(hdev);
-	gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
-
 	return error_count;
 }
 
@@ -8987,7 +9375,6 @@ static void gaudi2_handle_page_error(struct hl_device *hdev, u64 mmu_base, bool
 	if (is_pmmu) {
 		dev_err_ratelimited(hdev->dev, "PMMU page fault on va 0x%llx\n", addr);
 	} else {
-
 		addr = gaudi2_mmu_descramble_addr(hdev, addr);
 		addr &= HW_UNSCRAMBLED_BITS_MASK;
 		dev_err_ratelimited(hdev->dev, "HMMU page fault on va range 0x%llx - 0x%llx\n",
@@ -9239,8 +9626,8 @@ static int gaudi2_handle_mmu_spi_sei_err(struct hl_device *hdev, u16 event_type,
 static bool gaudi2_hbm_sei_handle_read_err(struct hl_device *hdev,
 			struct hl_eq_hbm_sei_read_err_intr_info *rd_err_data, u32 err_cnt)
 {
+	bool require_hard_reset = false;
 	u32 addr, beat, beat_shift;
-	bool rc = false;
 
 	dev_err_ratelimited(hdev->dev,
 			"READ ERROR count: ECC SERR: %d, ECC DERR: %d, RD_PARITY: %d\n",
@@ -9272,7 +9659,7 @@ static bool gaudi2_hbm_sei_handle_read_err(struct hl_device *hdev,
 						beat,
 						le32_to_cpu(rd_err_data->dbg_rd_err_dm),
 						le32_to_cpu(rd_err_data->dbg_rd_err_syndrome));
-			rc |= true;
+			require_hard_reset = true;
 		}
 
 		beat_shift = beat * HBM_RD_ERR_BEAT_SHIFT;
@@ -9285,7 +9672,7 @@ static bool gaudi2_hbm_sei_handle_read_err(struct hl_device *hdev,
 					(le32_to_cpu(rd_err_data->dbg_rd_err_misc) &
 						(HBM_RD_ERR_PAR_DATA_BEAT0_MASK << beat_shift)) >>
 						(HBM_RD_ERR_PAR_DATA_BEAT0_SHIFT + beat_shift));
-			rc |= true;
+			require_hard_reset = true;
 		}
 
 		dev_err_ratelimited(hdev->dev, "Beat%d DQ data:\n", beat);
@@ -9295,7 +9682,7 @@ static bool gaudi2_hbm_sei_handle_read_err(struct hl_device *hdev,
 					le32_to_cpu(rd_err_data->dbg_rd_err_data[beat * 2 + 1]));
 	}
 
-	return rc;
+	return require_hard_reset;
 }
 
 static void gaudi2_hbm_sei_print_wr_par_info(struct hl_device *hdev,
@@ -9518,25 +9905,17 @@ static int gaudi2_handle_pcie_p2p_msix(struct hl_device *hdev, u16 event_type)
 static int gaudi2_handle_pcie_drain(struct hl_device *hdev,
 			struct hl_eq_pcie_drain_ind_data *drain_data)
 {
-	u64 lbw_rd, lbw_wr, hbw_rd, hbw_wr, cause, error_count = 0;
+	u64 cause, error_count = 0;
 
 	cause = le64_to_cpu(drain_data->intr_cause.intr_cause_data);
-	lbw_rd = le64_to_cpu(drain_data->drain_rd_addr_lbw);
-	lbw_wr = le64_to_cpu(drain_data->drain_wr_addr_lbw);
-	hbw_rd = le64_to_cpu(drain_data->drain_rd_addr_hbw);
-	hbw_wr = le64_to_cpu(drain_data->drain_wr_addr_hbw);
 
 	if (cause & BIT_ULL(0)) {
-		dev_err_ratelimited(hdev->dev,
-			"PCIE AXI drain LBW completed, read_err %u, write_err %u\n",
-			!!lbw_rd, !!lbw_wr);
+		dev_err_ratelimited(hdev->dev, "PCIE AXI drain LBW completed\n");
 		error_count++;
 	}
 
 	if (cause & BIT_ULL(1)) {
-		dev_err_ratelimited(hdev->dev,
-			"PCIE AXI drain HBW completed, raddr %#llx, waddr %#llx\n",
-			hbw_rd, hbw_wr);
+		dev_err_ratelimited(hdev->dev, "PCIE AXI drain HBW completed\n");
 		error_count++;
 	}
 
@@ -9587,8 +9966,8 @@ static int hl_arc_event_handle(struct hl_device *hdev, u16 event_type,
 		q = (struct hl_engine_arc_dccm_queue_full_irq *) &payload;
 
 		gaudi2_print_event(hdev, event_type, true,
-				"ARC DCCM Full event: EngId: %u, Intr_type: %u, Qidx: %u",
-				engine_id, intr_type, q->queue_index);
+				"ARC DCCM Full event: Eng: %s, Intr_type: %u, Qidx: %u",
+				GAUDI2_ENG_ID_TO_STR(engine_id), intr_type, q->queue_index);
 		return 1;
 	default:
 		gaudi2_print_event(hdev, event_type, true, "Unknown ARC event type");
@@ -9761,11 +10140,6 @@ static u16 event_id_to_engine_id(struct hl_device *hdev, u16 event_type)
 	return U16_MAX;
 }
 
-static void hl_eq_heartbeat_event_handle(struct hl_device *hdev)
-{
-	hdev->eq_heartbeat_received = true;
-}
-
 static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 {
 	struct gaudi2_device *gaudi2 = hdev->asic_specific;
@@ -9987,6 +10361,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		if (gaudi2_handle_hbm_mc_sei_err(hdev, event_type, &eq_entry->sei_data)) {
 			reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
 			reset_required = true;
+			is_critical = eq_entry->sei_data.hdr.is_critical;
 		}
 		error_count++;
 		break;
@@ -10007,6 +10382,8 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		error_count = gaudi2_handle_pcie_drain(hdev, &eq_entry->pcie_drain_ind_data);
 		reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
 		event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
+		if (hl_fw_version_cmp(hdev, 1, 13, 0) >= 0)
+			is_critical = true;
 		break;
 
 	case GAUDI2_EVENT_PSOC59_RPM_ERROR_OR_DRAIN:
@@ -10158,7 +10535,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		dev_err(hdev->dev, "CPLD shutdown event, reset reason: 0x%llx\n",
 						le64_to_cpu(eq_entry->data[0]));
 		error_count = GAUDI2_NA_EVENT_CAUSE;
-		event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
+		hl_eq_cpld_shutdown_event_handle(hdev, event_type, &event_mask);
 		break;
 
 	case GAUDI2_EVENT_CPU_PKT_SANITY_FAILED:
@@ -10216,8 +10593,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		gaudi2_print_event(hdev, event_type, true,
 				"No error cause for H/W event %u", event_type);
 
-	if ((gaudi2_irq_map_table[event_type].reset != EVENT_RESET_TYPE_NONE) ||
-				reset_required) {
+	if ((gaudi2_irq_map_table[event_type].reset != EVENT_RESET_TYPE_NONE) || reset_required) {
 		if (reset_required ||
 				(gaudi2_irq_map_table[event_type].reset == EVENT_RESET_TYPE_HARD))
 			reset_flags |= HL_DRV_RESET_HARD;
@@ -10247,16 +10623,17 @@ reset_device:
 	if (event_mask & HL_NOTIFIER_EVENT_GENERAL_HW_ERR)
 		hl_handle_critical_hw_err(hdev, event_type, &event_mask);
 
+	hl_debugfs_cfg_access_history_dump(hdev);
 	event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;
 	hl_device_cond_reset(hdev, reset_flags, event_mask);
 }
 
 static int gaudi2_memset_memory_chunk_using_edma_qm(struct hl_device *hdev,
-			struct packet_lin_dma *lin_dma_pkt, dma_addr_t pkt_dma_addr,
-			u32 hw_queue_id, u32 size, u64 addr, u32 val)
+			struct packet_lin_dma *lin_dma_pkt,
+			u64 phys_addr, u32 hw_queue_id, u32 size, u64 addr, u32 val)
 {
 	u32 ctl, pkt_size;
-	int rc = 0;
+	int rc = 0, i;
 
 	ctl = FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_LIN_DMA);
 	ctl |= FIELD_PREP(GAUDI2_PKT_LIN_DMA_CTL_MEMSET_MASK, 1);
@@ -10270,10 +10647,21 @@ static int gaudi2_memset_memory_chunk_using_edma_qm(struct hl_device *hdev,
 
 	pkt_size = sizeof(struct packet_lin_dma);
 
-	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, pkt_size, pkt_dma_addr);
+	for (i = 0; i < 3; i++) {
+		rc = hdev->asic_funcs->access_dev_mem(hdev, PCI_REGION_DRAM,
+				phys_addr + (i * sizeof(u64)),
+				((u64 *)(lin_dma_pkt)) + i, DEBUGFS_WRITE64);
+		if (rc) {
+			dev_err(hdev->dev, "Failed to copy lin_dma packet to HBM (%#llx)\n",
+				phys_addr);
+			return rc;
+		}
+	}
+
+	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, pkt_size, phys_addr);
 	if (rc)
-		dev_err(hdev->dev, "Failed to send lin dma packet to H/W queue %d\n",
-				hw_queue_id);
+		dev_err(hdev->dev, "Failed to send lin_dma packet to H/W queue %s\n",
+				GAUDI2_QUEUE_ID_TO_STR(hw_queue_id));
 
 	return rc;
 }
@@ -10285,12 +10673,11 @@ static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 siz
 					GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0,
 					GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0};
 	u32 chunk_size, dcore, edma_idx, sob_offset, sob_addr, comp_val,
-		old_mmubp, mmubp, num_of_pkts, busy, pkt_size;
+		old_mmubp, mmubp, num_of_pkts, busy, pkt_size, cb_len;
 	u64 comp_addr, cur_addr = addr, end_addr = addr + size;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc = 0, dma_num = 0, i;
 	void *lin_dma_pkts_arr;
-	dma_addr_t pkt_dma_addr;
-	int rc = 0, dma_num = 0;
 
 	if (prop->edma_enabled_mask == 0) {
 		dev_info(hdev->dev, "non of the EDMA engines is enabled - skip dram scrubbing\n");
@@ -10308,9 +10695,19 @@ static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 siz
 	/* Calculate how many lin dma pkts we'll need */
 	num_of_pkts = div64_u64(round_up(size, SZ_2G), SZ_2G);
 	pkt_size = sizeof(struct packet_lin_dma);
+	cb_len = pkt_size * num_of_pkts;
+
+	/*
+	 * if we're not scrubing HMMU or NIC reserved sections in hbm,
+	 * then it the scrubing of the user section, as we use the start of the user section
+	 * to store the CB of the EDMA QM, so shift the start address of the scrubbing accordingly
+	 * and scrub the CB section before leaving this function.
+	 */
+	if ((addr >= prop->dram_user_base_address) &&
+				(addr < prop->dram_user_base_address + cb_len))
+		cur_addr += (prop->dram_user_base_address + cb_len) - addr;
 
-	lin_dma_pkts_arr = hl_asic_dma_alloc_coherent(hdev, pkt_size * num_of_pkts,
-					&pkt_dma_addr, GFP_KERNEL);
+	lin_dma_pkts_arr = kvcalloc(num_of_pkts, pkt_size, GFP_KERNEL);
 	if (!lin_dma_pkts_arr)
 		return -ENOMEM;
 
@@ -10356,7 +10753,7 @@ static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 siz
 
 				rc = gaudi2_memset_memory_chunk_using_edma_qm(hdev,
 					(struct packet_lin_dma *)lin_dma_pkts_arr + dma_num,
-					pkt_dma_addr + dma_num * pkt_size,
+					prop->dram_user_base_address + (dma_num * pkt_size),
 					edma_queues_id[dcore] + edma_idx * 4,
 					chunk_size, cur_addr, val);
 				if (rc)
@@ -10365,14 +10762,16 @@ static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 siz
 				dma_num++;
 				cur_addr += chunk_size;
 				if (cur_addr == end_addr)
-					break;
+					goto edma_wait;
 			}
 		}
 	}
 
+edma_wait:
 	rc = hl_poll_timeout(hdev, sob_addr, busy, (busy == dma_num), 1000, 1000000);
 	if (rc) {
-		dev_err(hdev->dev, "DMA Timeout during HBM scrubbing\n");
+		dev_err(hdev->dev, "DMA Timeout during HBM scrubbing(sob: 0x%x, dma_num: 0x%x)\n",
+						busy, dma_num);
 		goto end;
 	}
 end:
@@ -10393,8 +10792,16 @@ end:
 		}
 	}
 
+	memset(lin_dma_pkts_arr, 0, sizeof(u64));
+
+	/* Zero the HBM area where we copied the CB */
+	for (i = 0; i < cb_len / sizeof(u64); i += sizeof(u64))
+		rc = hdev->asic_funcs->access_dev_mem(hdev, PCI_REGION_DRAM,
+			prop->dram_user_base_address + i,
+				(u64 *)(lin_dma_pkts_arr), DEBUGFS_WRITE64);
 	WREG32(sob_addr, 0);
-	hl_asic_dma_free_coherent(hdev, pkt_size * num_of_pkts, lin_dma_pkts_arr, pkt_dma_addr);
+
+	kvfree(lin_dma_pkts_arr);
 
 	return rc;
 }
@@ -11452,7 +11859,7 @@ static int gaudi2_mmu_get_real_page_size(struct hl_device *hdev, struct hl_mmu_p
 	return 0;
 
 page_size_err:
-	dev_err(hdev->dev, "page size of %u is not %uKB aligned, can't map\n",
+	dev_err(hdev->dev, "page size of 0x%X is not 0x%X aligned, can't map\n",
 							page_size, mmu_prop->page_size >> 10);
 	return -EFAULT;
 }
@@ -11472,6 +11879,29 @@ int gaudi2_send_device_activity(struct hl_device *hdev, bool open)
 	return hl_fw_send_device_activity(hdev, open);
 }
 
+static u64 gaudi2_read_pte(struct hl_device *hdev, u64 addr)
+{
+	struct gaudi2_device *gaudi2 = hdev->asic_specific;
+	u64 val;
+
+	if (hdev->reset_info.hard_reset_pending)
+		return U64_MAX;
+
+	val = readq(hdev->pcie_bar[DRAM_BAR_ID] + (addr - gaudi2->dram_bar_cur_addr));
+
+	return val;
+}
+
+static void gaudi2_write_pte(struct hl_device *hdev, u64 addr, u64 val)
+{
+	struct gaudi2_device *gaudi2 = hdev->asic_specific;
+
+	if (hdev->reset_info.hard_reset_pending)
+		return;
+
+	writeq(val, hdev->pcie_bar[DRAM_BAR_ID] + (addr - gaudi2->dram_bar_cur_addr));
+}
+
 static const struct hl_asic_funcs gaudi2_funcs = {
 	.early_init = gaudi2_early_init,
 	.early_fini = gaudi2_early_fini,
@@ -11508,8 +11938,8 @@ static const struct hl_asic_funcs gaudi2_funcs = {
 	.add_device_attr = gaudi2_add_device_attr,
 	.handle_eqe = gaudi2_handle_eqe,
 	.get_events_stat = gaudi2_get_events_stat,
-	.read_pte = NULL,
-	.write_pte = NULL,
+	.read_pte = gaudi2_read_pte,
+	.write_pte = gaudi2_write_pte,
 	.mmu_invalidate_cache = gaudi2_mmu_invalidate_cache,
 	.mmu_invalidate_cache_range = gaudi2_mmu_invalidate_cache_range,
 	.mmu_prefetch_cache_range = NULL,
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2P.h b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
index 9b9eef0d97d6..bdf5c1bd2d63 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2P.h
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
@@ -19,8 +19,6 @@
 #define GAUDI2_LINUX_FW_FILE	"habanalabs/gaudi2/gaudi2-fit.itb"
 #define GAUDI2_BOOT_FIT_FILE	"habanalabs/gaudi2/gaudi2-boot-fit.itb"
 
-#define MMU_PAGE_TABLES_INITIAL_SIZE	0x10000000	/* 256MB */
-
 #define GAUDI2_CPU_TIMEOUT_USEC		30000000	/* 30s */
 
 #define NUMBER_OF_PDMA_QUEUES		2
@@ -109,13 +107,11 @@
 /* DRAM Memory Map */
 
 #define CPU_FW_IMAGE_SIZE			0x10000000	/* 256MB */
-
-/* This define should be used only when working in a debug mode without dram.
- * When working with dram, the driver size will be calculated dynamically.
- */
-#define NIC_DEFAULT_DRV_SIZE			0x20000000	/* 512MB */
-
 #define CPU_FW_IMAGE_ADDR			DRAM_PHYS_BASE
+#define PMMU_PAGE_TABLES_SIZE			0x10000000      /* 256MB */
+#define EDMA_PQS_SIZE				SZ_2M
+#define EDMA_SCRATCHPAD_SIZE			SZ_1M
+#define HMMU_PAGE_TABLES_SIZE			SZ_1M
 
 #define NIC_NUMBER_OF_PORTS			NIC_NUMBER_OF_ENGINES
 
@@ -241,9 +237,17 @@
 #define GAUDI2_SOB_INCREMENT_BY_ONE	(FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_VAL_MASK, 1) | \
 					FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_INC_MASK, 1))
 
-#define GAUDI2_NUM_TESTED_QS (GAUDI2_QUEUE_ID_CPU_PQ - GAUDI2_QUEUE_ID_PDMA_0_0)
+#define GAUDI2_NUM_TESTED_QS		(GAUDI2_QUEUE_ID_CPU_PQ - GAUDI2_QUEUE_ID_PDMA_0_0)
+
 
-#define GAUDI2_NUM_OF_GLBL_ERR_CAUSE		8
+extern const char *gaudi2_engine_id_str[];
+extern const char *gaudi2_queue_id_str[];
+
+#define GAUDI2_ENG_ID_TO_STR(initiator) ((initiator) >= GAUDI2_ENGINE_ID_SIZE ? "not found" :	\
+						gaudi2_engine_id_str[initiator])
+
+#define GAUDI2_QUEUE_ID_TO_STR(initiator) ((initiator) >= GAUDI2_QUEUE_ID_SIZE ? "not found" :	\
+						gaudi2_queue_id_str[initiator])
 
 enum gaudi2_reserved_sob_id {
 	GAUDI2_RESERVED_SOB_CS_COMPLETION_FIRST,
@@ -389,7 +393,7 @@ enum gaudi2_edma_id {
 /* User interrupt count is aligned with HW CQ count.
  * We have 64 CQ's per dcore, CQ0 in dcore 0 is reserved for legacy mode
  */
-#define GAUDI2_NUM_USER_INTERRUPTS 255
+#define GAUDI2_NUM_USER_INTERRUPTS 64
 #define GAUDI2_NUM_RESERVED_INTERRUPTS 1
 #define GAUDI2_TOTAL_USER_INTERRUPTS (GAUDI2_NUM_USER_INTERRUPTS + GAUDI2_NUM_RESERVED_INTERRUPTS)
 
@@ -421,11 +425,11 @@ enum gaudi2_irq_num {
 	GAUDI2_IRQ_NUM_NIC_PORT_LAST = (GAUDI2_IRQ_NUM_NIC_PORT_FIRST + NIC_NUMBER_OF_PORTS - 1),
 	GAUDI2_IRQ_NUM_TPC_ASSERT,
 	GAUDI2_IRQ_NUM_EQ_ERROR,
+	GAUDI2_IRQ_NUM_USER_FIRST,
+	GAUDI2_IRQ_NUM_USER_LAST = (GAUDI2_IRQ_NUM_USER_FIRST + GAUDI2_NUM_USER_INTERRUPTS - 1),
 	GAUDI2_IRQ_NUM_RESERVED_FIRST,
-	GAUDI2_IRQ_NUM_RESERVED_LAST = (GAUDI2_MSIX_ENTRIES - GAUDI2_TOTAL_USER_INTERRUPTS - 1),
+	GAUDI2_IRQ_NUM_RESERVED_LAST = (GAUDI2_MSIX_ENTRIES - GAUDI2_NUM_RESERVED_INTERRUPTS - 1),
 	GAUDI2_IRQ_NUM_UNEXPECTED_ERROR = RESERVED_MSIX_UNEXPECTED_USER_ERROR_INTERRUPT,
-	GAUDI2_IRQ_NUM_USER_FIRST = GAUDI2_IRQ_NUM_UNEXPECTED_ERROR + 1,
-	GAUDI2_IRQ_NUM_USER_LAST = (GAUDI2_IRQ_NUM_USER_FIRST + GAUDI2_NUM_USER_INTERRUPTS - 1),
 	GAUDI2_IRQ_NUM_LAST = (GAUDI2_MSIX_ENTRIES - 1)
 };
 
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_coresight.c b/drivers/accel/habanalabs/gaudi2/gaudi2_coresight.c
index 2423620ff358..bc3c57bda5cd 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2_coresight.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2_coresight.c
@@ -2426,7 +2426,7 @@ static int gaudi2_config_bmon(struct hl_device *hdev, struct hl_debug_params *pa
 		WREG32(base_reg + mmBMON_ADDRH_E3_OFFSET, 0);
 		WREG32(base_reg + mmBMON_REDUCTION_OFFSET, 0);
 		WREG32(base_reg + mmBMON_STM_TRC_OFFSET, 0x7 | (0xA << 8));
-		WREG32(base_reg + mmBMON_CR_OFFSET, 0x77 | 0xf << 24);
+		WREG32(base_reg + mmBMON_CR_OFFSET, 0x41);
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
index 34bf80c5a44b..307ccb912ccd 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
@@ -479,6 +479,7 @@ static const u32 gaudi2_pb_dcr0_edma0_unsecured_regs[] = {
 	mmDCORE0_EDMA0_CORE_CTX_TE_NUMROWS,
 	mmDCORE0_EDMA0_CORE_CTX_IDX,
 	mmDCORE0_EDMA0_CORE_CTX_IDX_INC,
+	mmDCORE0_EDMA0_CORE_WR_COMP_MAX_OUTSTAND,
 	mmDCORE0_EDMA0_CORE_RD_LBW_RATE_LIM_CFG,
 	mmDCORE0_EDMA0_QM_CQ_CFG0_0,
 	mmDCORE0_EDMA0_QM_CQ_CFG0_1,
diff --git a/drivers/accel/habanalabs/goya/goya.c b/drivers/accel/habanalabs/goya/goya.c
index 1322cb330c57..84768e306269 100644
--- a/drivers/accel/habanalabs/goya/goya.c
+++ b/drivers/accel/habanalabs/goya/goya.c
@@ -413,8 +413,6 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 	else
 		prop->mmu_pgt_size = MMU_PAGE_TABLES_SIZE;
 	prop->mmu_pte_size = HL_PTE_SIZE;
-	prop->mmu_hop_table_size = HOP_TABLE_SIZE_512_PTE;
-	prop->mmu_hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 	prop->dram_page_size = PAGE_SIZE_2MB;
 	prop->device_mem_alloc_default_page_size = prop->dram_page_size;
 	prop->dram_supports_virtual_memory = true;
@@ -435,8 +433,8 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 	prop->dmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->dmmu.last_mask = LAST_MASK;
 	/* TODO: will be duplicated until implementing per-MMU props */
-	prop->dmmu.hop_table_size = prop->mmu_hop_table_size;
-	prop->dmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
+	prop->dmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE;
+	prop->dmmu.hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 
 	/* shifts and masks are the same in PMMU and DMMU */
 	memcpy(&prop->pmmu, &prop->dmmu, sizeof(prop->dmmu));
@@ -446,8 +444,8 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 	prop->pmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->pmmu.last_mask = LAST_MASK;
 	/* TODO: will be duplicated until implementing per-MMU props */
-	prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
-	prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
+	prop->pmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE;
+	prop->pmmu.hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
 
 	/* PMMU and HPMMU are the same except of page size */
 	memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
@@ -895,11 +893,8 @@ int goya_late_init(struct hl_device *hdev)
 	WREG32(mmMMU_LOG2_DDR_SIZE, ilog2(prop->dram_size));
 
 	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS, 0x0);
-	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to enable PCI access from CPU %d\n", rc);
+	if (rc)
 		return rc;
-	}
 
 	/* force setting to low frequency */
 	goya->curr_pll_profile = PLL_LOW;
@@ -2678,7 +2673,7 @@ int goya_mmu_init(struct hl_device *hdev)
 
 	for (i = 0 ; i < prop->max_asid ; i++) {
 		hop0_addr = prop->mmu_pgt_addr +
-				(i * prop->mmu_hop_table_size);
+				(i * prop->dmmu.hop_table_size);
 
 		rc = goya_mmu_update_asid_hop0_addr(hdev, i, hop0_addr);
 		if (rc) {
@@ -2866,13 +2861,7 @@ static int goya_hw_fini(struct hl_device *hdev, bool hard_reset, bool fw_reset)
 
 int goya_suspend(struct hl_device *hdev)
 {
-	int rc;
-
-	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
-	if (rc)
-		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
-
-	return rc;
+	return hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
 }
 
 int goya_resume(struct hl_device *hdev)
diff --git a/drivers/accel/habanalabs/goya/goya_coresight.c b/drivers/accel/habanalabs/goya/goya_coresight.c
index 41cae5fd843b..3827ea4c02f7 100644
--- a/drivers/accel/habanalabs/goya/goya_coresight.c
+++ b/drivers/accel/habanalabs/goya/goya_coresight.c
@@ -576,7 +576,6 @@ static int goya_config_spmu(struct hl_device *hdev,
 		struct hl_debug_params *params)
 {
 	u64 base_reg;
-	struct hl_debug_params_spmu *input = params->input;
 	u64 *output;
 	u32 output_arr_len;
 	u32 events_num;
@@ -592,7 +591,7 @@ static int goya_config_spmu(struct hl_device *hdev,
 	base_reg = debug_spmu_regs[params->reg_idx] - CFG_BASE;
 
 	if (params->enable) {
-		input = params->input;
+		struct hl_debug_params_spmu *input = params->input;
 
 		if (!input)
 			return -EINVAL;
diff --git a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
index a08378d0802b..d21fcd3880b4 100644
--- a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
+++ b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
@@ -242,14 +242,15 @@
 #define QM_FENCE2_OFFSET		(mmPDMA0_QM_CP_FENCE2_RDATA_0 - mmPDMA0_QM_BASE)
 #define QM_SEI_STATUS_OFFSET		(mmPDMA0_QM_SEI_STATUS - mmPDMA0_QM_BASE)
 
-#define QM_CQ_PTR_LO_4_OFFSET		(mmPDMA0_QM_CQ_PTR_LO_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_PTR_HI_4_OFFSET		(mmPDMA0_QM_CQ_PTR_HI_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_TSIZE_4_OFFSET		(mmPDMA0_QM_CQ_TSIZE_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_TSIZE_STS_4_OFFSET	(mmPDMA0_QM_CQ_TSIZE_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_LO_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_LO_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_HI_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_HI_STS_4 - mmPDMA0_QM_BASE)
 
-#define QM_ARC_CQ_PTR_LO_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_LO - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_PTR_HI_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_TSIZE_OFFSET		(mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_TSIZE_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_TSIZE_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_LO_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_LO_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_HI_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_HI_STS - mmPDMA0_QM_BASE)
 
+#define QM_CP_STS_4_OFFSET		(mmPDMA0_QM_CP_STS_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_LO_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_HI_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_HI_4 - mmPDMA0_QM_BASE)
 
diff --git a/drivers/accel/habanalabs/include/gaudi2/gaudi2.h b/drivers/accel/habanalabs/include/gaudi2/gaudi2.h
index 0231d6c55b4a..753d46a2836b 100644
--- a/drivers/accel/habanalabs/include/gaudi2/gaudi2.h
+++ b/drivers/accel/habanalabs/include/gaudi2/gaudi2.h
@@ -63,9 +63,9 @@
 #define RESERVED_VA_RANGE_FOR_ARC_ON_HOST_HPAGE_START	0xFFF0F80000000000ull
 #define RESERVED_VA_RANGE_FOR_ARC_ON_HOST_HPAGE_END	0xFFF0FFFFFFFFFFFFull
 
-#define RESERVED_MSIX_UNEXPECTED_USER_ERROR_INTERRUPT	256
+#define RESERVED_MSIX_UNEXPECTED_USER_ERROR_INTERRUPT	127
 
-#define GAUDI2_MSIX_ENTRIES	512
+#define GAUDI2_MSIX_ENTRIES	128
 
 #define QMAN_PQ_ENTRY_SIZE	16			/* Bytes */
 
diff --git a/drivers/accel/habanalabs/include/gaudi2/gaudi2_async_ids_map_extended.h b/drivers/accel/habanalabs/include/gaudi2/gaudi2_async_ids_map_extended.h
index b2dbe1f64430..82d639990cca 100644
--- a/drivers/accel/habanalabs/include/gaudi2/gaudi2_async_ids_map_extended.h
+++ b/drivers/accel/habanalabs/include/gaudi2/gaudi2_async_ids_map_extended.h
@@ -330,9 +330,9 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 	{ .fc_id = 149, .cpu_id = 48, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "EDMA7_ECC_SERR" },
 	{ .fc_id = 150, .cpu_id = 48, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "HDMA4_ECC_SERR" },
+		 .name = "EDMA4_ECC_SERR" },
 	{ .fc_id = 151, .cpu_id = 48, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "HDMA5_ECC_SERR" },
+		 .name = "EDMA5_ECC_SERR" },
 	{ .fc_id = 152, .cpu_id = 49, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "EDMA2_ECC_DERR" },
 	{ .fc_id = 153, .cpu_id = 49, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
@@ -856,55 +856,55 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 	{ .fc_id = 412, .cpu_id = 84, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PCIE_ADDR_DEC_ERR" },
 	{ .fc_id = 413, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC0_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC0_AXI_ERR_RSP" },
 	{ .fc_id = 414, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC1_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC1_AXI_ERR_RSP" },
 	{ .fc_id = 415, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC2_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC2_AXI_ERR_RSP" },
 	{ .fc_id = 416, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC3_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC3_AXI_ERR_RSP" },
 	{ .fc_id = 417, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC4_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC4_AXI_ERR_RSP" },
 	{ .fc_id = 418, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC5_AXI_ERR_RSP" },
+		 .name = "DCORE0_TPC5_AXI_ERR_RSP" },
 	{ .fc_id = 419, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC6_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC0_AXI_ERR_RSP" },
 	{ .fc_id = 420, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC7_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC1_AXI_ERR_RSP" },
 	{ .fc_id = 421, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC8_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC2_AXI_ERR_RSP" },
 	{ .fc_id = 422, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC9_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC3_AXI_ERR_RSP" },
 	{ .fc_id = 423, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC10_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC4_AXI_ERR_RSP" },
 	{ .fc_id = 424, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC11_AXI_ERR_RSP" },
+		 .name = "DCORE1_TPC5_AXI_ERR_RSP" },
 	{ .fc_id = 425, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC12_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC0_AXI_ERR_RSP" },
 	{ .fc_id = 426, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC13_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC1_AXI_ERR_RSP" },
 	{ .fc_id = 427, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC14_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC2_AXI_ERR_RSP" },
 	{ .fc_id = 428, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC15_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC3_AXI_ERR_RSP" },
 	{ .fc_id = 429, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC16_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC4_AXI_ERR_RSP" },
 	{ .fc_id = 430, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC17_AXI_ERR_RSP" },
+		 .name = "DCORE2_TPC5_AXI_ERR_RSP" },
 	{ .fc_id = 431, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC18_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC0_AXI_ERR_RSP" },
 	{ .fc_id = 432, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC19_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC1_AXI_ERR_RSP" },
 	{ .fc_id = 433, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC20_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC2_AXI_ERR_RSP" },
 	{ .fc_id = 434, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC21_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC3_AXI_ERR_RSP" },
 	{ .fc_id = 435, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC22_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC4_AXI_ERR_RSP" },
 	{ .fc_id = 436, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC23_AXI_ERR_RSP" },
+		 .name = "DCORE3_TPC5_AXI_ERR_RSP" },
 	{ .fc_id = 437, .cpu_id = 85, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC24_AXI_ERR_RSP" },
+		 .name = "DCORE4_TPC0_AXI_ERR_RSP" },
 	{ .fc_id = 438, .cpu_id = 86, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "AXI_ECC" },
 	{ .fc_id = 439, .cpu_id = 87, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
@@ -965,73 +965,73 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 		 .name = "MME3_CTRL_AXI_ERROR_RESPONSE" },
 	{ .fc_id = 467, .cpu_id = 91, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
 		 .name = "MME3_QMAN_SW_ERROR" },
-	{ .fc_id = 468, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 468, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PSOC_MME_PLL_LOCK_ERR" },
-	{ .fc_id = 469, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 469, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PSOC_CPU_PLL_LOCK_ERR" },
-	{ .fc_id = 470, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 470, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_TPC_PLL_LOCK_ERR" },
-	{ .fc_id = 471, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 471, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_NIC_PLL_LOCK_ERR" },
-	{ .fc_id = 472, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 472, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_XBAR_MMU_PLL_LOCK_ERR" },
-	{ .fc_id = 473, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 473, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_XBAR_DMA_PLL_LOCK_ERR" },
-	{ .fc_id = 474, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 474, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_XBAR_IF_PLL_LOCK_ERR" },
-	{ .fc_id = 475, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 475, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_XBAR_BANK_PLL_LOCK_ERR" },
-	{ .fc_id = 476, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 476, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_XBAR_MMU_PLL_LOCK_ERR" },
-	{ .fc_id = 477, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 477, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_XBAR_DMA_PLL_LOCK_ERR" },
-	{ .fc_id = 478, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 478, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_XBAR_IF_PLL_LOCK_ERR" },
-	{ .fc_id = 479, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 479, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_XBAR_MESH_PLL_LOCK_ERR" },
-	{ .fc_id = 480, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 480, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_TPC_PLL_LOCK_ERR" },
-	{ .fc_id = 481, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 481, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_NIC_PLL_LOCK_ERR" },
-	{ .fc_id = 482, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 482, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PMMU_MME_PLL_LOCK_ERR" },
-	{ .fc_id = 483, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 483, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_TPC_PLL_LOCK_ERR" },
-	{ .fc_id = 484, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 484, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_PCI_PLL_LOCK_ERR" },
-	{ .fc_id = 485, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 485, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_XBAR_MMU_PLL_LOCK_ERR" },
-	{ .fc_id = 486, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 486, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_XBAR_DMA_PLL_LOCK_ERR" },
-	{ .fc_id = 487, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 487, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_XBAR_IF_PLL_LOCK_ERR" },
-	{ .fc_id = 488, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 488, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_XBAR_MESH_PLL_LOCK_ERR" },
-	{ .fc_id = 489, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 489, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_XBAR_MMU_PLL_LOCK_ERR" },
-	{ .fc_id = 490, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 490, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_XBAR_DMA_PLL_LOCK_ERR" },
-	{ .fc_id = 491, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 491, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_XBAR_IF_PLL_LOCK_ERR" },
-	{ .fc_id = 492, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 492, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_XBAR_BANK_PLL_LOCK_ERR" },
-	{ .fc_id = 493, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 493, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_TPC_PLL_LOCK_ERR" },
-	{ .fc_id = 494, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 494, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PSOC_VID_PLL_LOCK_ERR" },
-	{ .fc_id = 495, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 495, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "PMMU_VID_PLL_LOCK_ERR" },
-	{ .fc_id = 496, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 496, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE3_HBM_PLL_LOCK_ERR" },
-	{ .fc_id = 497, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 497, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_XBAR_HBM_PLL_LOCK_ERR" },
-	{ .fc_id = 498, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 498, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE1_HBM_PLL_LOCK_ERR" },
-	{ .fc_id = 499, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 499, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE0_HBM_PLL_LOCK_ERR" },
-	{ .fc_id = 500, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 500, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_XBAR_HBM_PLL_LOCK_ERR" },
-	{ .fc_id = 501, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+	{ .fc_id = 501, .cpu_id = 92, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DCORE2_HBM_PLL_LOCK_ERR" },
 	{ .fc_id = 502, .cpu_id = 93, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "CPU_AXI_ERR_RSP" },
@@ -1298,103 +1298,103 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 	{ .fc_id = 633, .cpu_id = 130, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC0_BMON_SPMU" },
 	{ .fc_id = 634, .cpu_id = 131, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC0_KERNEL_ERR" },
+		 .name = "DCORE0_TPC0_KERNEL_ERR" },
 	{ .fc_id = 635, .cpu_id = 132, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC1_BMON_SPMU" },
 	{ .fc_id = 636, .cpu_id = 133, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC1_KERNEL_ERR" },
+		 .name = "DCORE0_TPC1_KERNEL_ERR" },
 	{ .fc_id = 637, .cpu_id = 134, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC2_BMON_SPMU" },
 	{ .fc_id = 638, .cpu_id = 135, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC2_KERNEL_ERR" },
+		 .name = "DCORE0_TPC2_KERNEL_ERR" },
 	{ .fc_id = 639, .cpu_id = 136, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC3_BMON_SPMU" },
 	{ .fc_id = 640, .cpu_id = 137, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC3_KERNEL_ERR" },
+		 .name = "DCORE0_TPC3_KERNEL_ERR" },
 	{ .fc_id = 641, .cpu_id = 138, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC4_BMON_SPMU" },
 	{ .fc_id = 642, .cpu_id = 139, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC4_KERNEL_ERR" },
+		 .name = "DCORE0_TPC4_KERNEL_ERR" },
 	{ .fc_id = 643, .cpu_id = 140, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC5_BMON_SPMU" },
 	{ .fc_id = 644, .cpu_id = 141, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC5_KERNEL_ERR" },
+		 .name = "DCORE0_TPC5_KERNEL_ERR" },
 	{ .fc_id = 645, .cpu_id = 150, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC6_BMON_SPMU" },
 	{ .fc_id = 646, .cpu_id = 151, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC6_KERNEL_ERR" },
+		 .name = "DCORE1_TPC0_KERNEL_ERR" },
 	{ .fc_id = 647, .cpu_id = 152, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC7_BMON_SPMU" },
 	{ .fc_id = 648, .cpu_id = 153, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC7_KERNEL_ERR" },
+		 .name = "DCORE1_TPC1_KERNEL_ERR" },
 	{ .fc_id = 649, .cpu_id = 146, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC8_BMON_SPMU" },
 	{ .fc_id = 650, .cpu_id = 147, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC8_KERNEL_ERR" },
+		 .name = "DCORE1_TPC2_KERNEL_ERR" },
 	{ .fc_id = 651, .cpu_id = 148, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC9_BMON_SPMU" },
 	{ .fc_id = 652, .cpu_id = 149, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC9_KERNEL_ERR" },
+		 .name = "DCORE1_TPC3_KERNEL_ERR" },
 	{ .fc_id = 653, .cpu_id = 142, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC10_BMON_SPMU" },
 	{ .fc_id = 654, .cpu_id = 143, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC10_KERNEL_ERR" },
+		 .name = "DCORE1_TPC4_KERNEL_ERR" },
 	{ .fc_id = 655, .cpu_id = 144, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC11_BMON_SPMU" },
 	{ .fc_id = 656, .cpu_id = 145, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC11_KERNEL_ERR" },
+		 .name = "DCORE1_TPC5_KERNEL_ERR" },
 	{ .fc_id = 657, .cpu_id = 162, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC12_BMON_SPMU" },
 	{ .fc_id = 658, .cpu_id = 163, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC12_KERNEL_ERR" },
+		 .name = "DCORE2_TPC0_KERNEL_ERR" },
 	{ .fc_id = 659, .cpu_id = 164, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC13_BMON_SPMU" },
 	{ .fc_id = 660, .cpu_id = 165, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC13_KERNEL_ERR" },
+		 .name = "DCORE2_TPC1_KERNEL_ERR" },
 	{ .fc_id = 661, .cpu_id = 158, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC14_BMON_SPMU" },
 	{ .fc_id = 662, .cpu_id = 159, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC14_KERNEL_ERR" },
+		 .name = "DCORE2_TPC2_KERNEL_ERR" },
 	{ .fc_id = 663, .cpu_id = 160, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC15_BMON_SPMU" },
 	{ .fc_id = 664, .cpu_id = 161, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC15_KERNEL_ERR" },
+		 .name = "DCORE2_TPC3_KERNEL_ERR" },
 	{ .fc_id = 665, .cpu_id = 154, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC16_BMON_SPMU" },
 	{ .fc_id = 666, .cpu_id = 155, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC16_KERNEL_ERR" },
+		 .name = "DCORE2_TPC4_KERNEL_ERR" },
 	{ .fc_id = 667, .cpu_id = 156, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC17_BMON_SPMU" },
 	{ .fc_id = 668, .cpu_id = 157, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC17_KERNEL_ERR" },
+		 .name = "DCORE2_TPC5_KERNEL_ERR" },
 	{ .fc_id = 669, .cpu_id = 166, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC18_BMON_SPMU" },
 	{ .fc_id = 670, .cpu_id = 167, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC18_KERNEL_ERR" },
+		 .name = "DCORE3_TPC0_KERNEL_ERR" },
 	{ .fc_id = 671, .cpu_id = 168, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC19_BMON_SPMU" },
 	{ .fc_id = 672, .cpu_id = 169, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC19_KERNEL_ERR" },
+		 .name = "DCORE3_TPC1_KERNEL_ERR" },
 	{ .fc_id = 673, .cpu_id = 170, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC20_BMON_SPMU" },
 	{ .fc_id = 674, .cpu_id = 171, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC20_KERNEL_ERR" },
+		 .name = "DCORE3_TPC2_KERNEL_ERR" },
 	{ .fc_id = 675, .cpu_id = 172, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC21_BMON_SPMU" },
 	{ .fc_id = 676, .cpu_id = 173, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC21_KERNEL_ERR" },
+		 .name = "DCORE3_TPC3_KERNEL_ERR" },
 	{ .fc_id = 677, .cpu_id = 174, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC22_BMON_SPMU" },
 	{ .fc_id = 678, .cpu_id = 175, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC22_KERNEL_ERR" },
+		 .name = "DCORE3_TPC4_KERNEL_ERR" },
 	{ .fc_id = 679, .cpu_id = 176, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC23_BMON_SPMU" },
 	{ .fc_id = 680, .cpu_id = 177, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC23_KERNEL_ERR" },
+		 .name = "DCORE3_TPC5_KERNEL_ERR" },
 	{ .fc_id = 681, .cpu_id = 178, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "TPC24_BMON_SPMU" },
 	{ .fc_id = 682, .cpu_id = 179, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC24_KERNEL_ERR" },
+		 .name = "DCORE4_TPC0_KERNEL_ERR" },
 	{ .fc_id = 683, .cpu_id = 180, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "" },
 	{ .fc_id = 684, .cpu_id = 180, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
@@ -1827,8 +1827,8 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 		 .name = "DEC0_BMON_SPMU" },
 	{ .fc_id = 898, .cpu_id = 330, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
 		 .name = "DEC1_SPI" },
-	{ .fc_id = 899, .cpu_id = 330, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "DEC1_SPI" },
+	{ .fc_id = 899, .cpu_id = 330, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
+		 .name = "DEC1_BMON_SPMU" },
 	{ .fc_id = 900, .cpu_id = 331, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_COMPUTE,
 		 .name = "DEC2_SPI" },
 	{ .fc_id = 901, .cpu_id = 331, .valid = 1, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
@@ -2377,8 +2377,8 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 		 .name = "" },
 	{ .fc_id = 1173, .cpu_id = 479, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "" },
-	{ .fc_id = 1174, .cpu_id = 480, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "" },
+	{ .fc_id = 1174, .cpu_id = 480, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
+		 .name = "PSOC_DMA_QM" },
 	{ .fc_id = 1175, .cpu_id = 481, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "" },
 	{ .fc_id = 1176, .cpu_id = 482, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
@@ -2442,55 +2442,55 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 	{ .fc_id = 1205, .cpu_id = 511, .valid = 0, .msg = 0, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "" },
 	{ .fc_id = 1206, .cpu_id = 512, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC0_QM" },
+		 .name = "DCORE0_TPC0_QM" },
 	{ .fc_id = 1207, .cpu_id = 513, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC1_QM" },
+		 .name = "DCORE0_TPC1_QM" },
 	{ .fc_id = 1208, .cpu_id = 514, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC2_QM" },
+		 .name = "DCORE0_TPC2_QM" },
 	{ .fc_id = 1209, .cpu_id = 515, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC3_QM" },
+		 .name = "DCORE0_TPC3_QM" },
 	{ .fc_id = 1210, .cpu_id = 516, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC4_QM" },
+		 .name = "DCORE0_TPC4_QM" },
 	{ .fc_id = 1211, .cpu_id = 517, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC5_QM" },
+		 .name = "DCORE0_TPC5_QM" },
 	{ .fc_id = 1212, .cpu_id = 518, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC6_QM" },
+		 .name = "DCORE1_TPC0_QM" },
 	{ .fc_id = 1213, .cpu_id = 519, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC7_QM" },
+		 .name = "DCORE1_TPC1_QM" },
 	{ .fc_id = 1214, .cpu_id = 520, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC8_QM" },
+		 .name = "DCORE1_TPC2_QM" },
 	{ .fc_id = 1215, .cpu_id = 521, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC9_QM" },
+		 .name = "DCORE1_TPC3_QM" },
 	{ .fc_id = 1216, .cpu_id = 522, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC10_QM" },
+		 .name = "DCORE1_TPC4_QM" },
 	{ .fc_id = 1217, .cpu_id = 523, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC11_QM" },
+		 .name = "DCORE1_TPC5_QM" },
 	{ .fc_id = 1218, .cpu_id = 524, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC12_QM" },
+		 .name = "DCORE2_TPC0_QM" },
 	{ .fc_id = 1219, .cpu_id = 525, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC13_QM" },
+		 .name = "DCORE2_TPC1_QM" },
 	{ .fc_id = 1220, .cpu_id = 526, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC14_QM" },
+		 .name = "DCORE2_TPC2_QM" },
 	{ .fc_id = 1221, .cpu_id = 527, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC15_QM" },
+		 .name = "DCORE2_TPC3_QM" },
 	{ .fc_id = 1222, .cpu_id = 528, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC16_QM" },
+		 .name = "DCORE2_TPC4_QM" },
 	{ .fc_id = 1223, .cpu_id = 529, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC17_QM" },
+		 .name = "DCORE2_TPC5_QM" },
 	{ .fc_id = 1224, .cpu_id = 530, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC18_QM" },
+		 .name = "DCORE3_TPC0_QM" },
 	{ .fc_id = 1225, .cpu_id = 531, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC19_QM" },
+		 .name = "DCORE3_TPC1_QM" },
 	{ .fc_id = 1226, .cpu_id = 532, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC20_QM" },
+		 .name = "DCORE3_TPC2_QM" },
 	{ .fc_id = 1227, .cpu_id = 533, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC21_QM" },
+		 .name = "DCORE3_TPC3_QM" },
 	{ .fc_id = 1228, .cpu_id = 534, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC22_QM" },
+		 .name = "DCORE3_TPC4_QM" },
 	{ .fc_id = 1229, .cpu_id = 535, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC23_QM" },
+		 .name = "DCORE3_TPC5_QM" },
 	{ .fc_id = 1230, .cpu_id = 536, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
-		 .name = "TPC24_QM" },
+		 .name = "DCORE4_TPC0_QM" },
 	{ .fc_id = 1231, .cpu_id = 537, .valid = 0, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
 		 .name = "" },
 	{ .fc_id = 1232, .cpu_id = 538, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_COMPUTE,
@@ -2674,19 +2674,19 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 	{ .fc_id = 1321, .cpu_id = 627, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_HARD,
 		 .name = "DEV_RESET_REQ" },
 	{ .fc_id = 1322, .cpu_id = 628, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_BRK_ENTRY" },
+		 .name = "PWR_BRK_ENTRY" },
 	{ .fc_id = 1323, .cpu_id = 629, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_BRK_EXT" },
+		 .name = "PWR_BRK_EXT" },
 	{ .fc_id = 1324, .cpu_id = 630, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_RD_MODE0" },
+		 .name = "PWR_RD_MODE0" },
 	{ .fc_id = 1325, .cpu_id = 631, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_RD_MODE1" },
+		 .name = "PWR_RD_MODE1" },
 	{ .fc_id = 1326, .cpu_id = 632, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_RD_MODE2" },
+		 .name = "PWR_RD_MODE2" },
 	{ .fc_id = 1327, .cpu_id = 633, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_PWR_RD_MODE3" },
+		 .name = "PWR_RD_MODE3" },
 	{ .fc_id = 1328, .cpu_id = 634, .valid = 1, .msg = 1, .reset = EVENT_RESET_TYPE_NONE,
-		 .name = "ARC_EQ_HEARTBEAT" },
+		 .name = "EQ_HEARTBEAT" },
 };
 
 #endif /* __GAUDI2_ASYNC_IDS_MAP_EVENTS_EXT_H_ */
diff --git a/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h b/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
index 18ca147b1c86..6ea936c9594e 100644
--- a/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
+++ b/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
@@ -45,6 +45,13 @@
 #define GAUDI2_ARM_RX_MB_OFFSET		(GAUDI2_ARM_RX_MB_ADDR - \
 					GAUDI2_SP_SRAM_BASE_ADDR)
 
+#define POWER_MODE_LEVELS	{	\
+	150000,		/* 00 */	\
+	250000,		/* 01 */	\
+	400000,		/* 10 */	\
+	/* 11: Normal mode */		\
+}
+
 enum gaudi2_fw_status {
 	GAUDI2_PID_STATUS_UP = 0x1,	/* PID on ARC0 is up */
 	GAUDI2_ARM_STATUS_UP = 0x2,	/* ARM Linux Boot complete */
@@ -52,26 +59,6 @@ enum gaudi2_fw_status {
 	GAUDI2_STATUS_LAST = 0xFF
 };
 
-struct gaudi2_cold_rst_data {
-	union {
-		struct {
-			u32 recovery_flag: 1;
-			u32 validation_flag: 1;
-			u32 efuse_read_flag: 1;
-			u32 spsram_init_done : 1;
-			u32 fake_security_enable : 1;
-			u32 fake_sig_validation_en : 1;
-			u32 bist_skip_enable : 1;
-			u32 reserved1 : 1;
-			u32 fake_bis_compliant : 1;
-			u32 wd_rst_cause_arm : 1;
-			u32 wd_rst_cause_arcpid : 1;
-			u32 reserved : 21;
-		};
-		__le32 data;
-	};
-};
-
 enum gaudi2_rst_src {
 	HL_COLD_RST = 1,
 	HL_MANUAL_RST = 2,
diff --git a/drivers/accel/habanalabs/include/gaudi2/gaudi2_reg_map.h b/drivers/accel/habanalabs/include/gaudi2/gaudi2_reg_map.h
index f3eaeb6d9b7e..1e9c056e437d 100644
--- a/drivers/accel/habanalabs/include/gaudi2/gaudi2_reg_map.h
+++ b/drivers/accel/habanalabs/include/gaudi2/gaudi2_reg_map.h
@@ -58,4 +58,12 @@
 #define mmWD_GPIO_DATAOUT_REG			mmPSOC_GPIO3_DATAOUT
 #define mmSTM_PROFILER_SPE_REG			mmPSOC_STM_STMSPER
 
+/* Registers below are used to pass the boot_if data between ARM and ARC1 */
+#define mmARM_MSG_BOOT_ERR_SET			mmCPU_IF_SPECIAL_GLBL_SPARE_0
+#define mmARM_MSG_BOOT_ERR_CLR			mmCPU_IF_SPECIAL_GLBL_SPARE_1
+#define mmARM_MSG_BOOT_DEV_STS_SET		mmCPU_IF_SPECIAL_GLBL_SPARE_2
+#define mmARM_MSG_BOOT_DEV_STS_CLR		mmCPU_IF_SPECIAL_GLBL_SPARE_3
+#define mmMGMT_MSG_BOOT_ERR			mmCPU_MSTR_IF_SPECIAL_GLBL_SPARE_0
+#define mmMGMT_MSG_BOOT_DEV_STS			mmCPU_MSTR_IF_SPECIAL_GLBL_SPARE_1
+
 #endif /* GAUDI2_REG_MAP_H_ */
diff --git a/drivers/accel/habanalabs/include/hw_ip/mmu/mmu_general.h b/drivers/accel/habanalabs/include/hw_ip/mmu/mmu_general.h
index d408feecd483..b4a5e95be354 100644
--- a/drivers/accel/habanalabs/include/hw_ip/mmu/mmu_general.h
+++ b/drivers/accel/habanalabs/include/hw_ip/mmu/mmu_general.h
@@ -26,6 +26,8 @@
 #define LAST_MASK			0x0000000000800ull
 #define FLAGS_MASK			0x0000000000FFFull
 
+#define MMU_ARCH_3_HOPS			3
+#define MMU_ARCH_4_HOPS			4
 #define MMU_ARCH_5_HOPS			5
 #define MMU_ARCH_6_HOPS			6
 
diff --git a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
index f5d497dc9bdc..a75faa00197f 100644
--- a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
+++ b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
@@ -25,6 +25,8 @@ enum hl_revision_id {
 	REV_ID_INVALID				= 0x00,
 	REV_ID_A				= 0x01,
 	REV_ID_B				= 0x02,
+	REV_ID_C				= 0x03,
+	REV_ID_D				= 0x04
 };
 
 #endif /* INCLUDE_PCI_GENERAL_H_ */
diff --git a/drivers/accel/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig
index 1a4c4ed9d113..9e055b5ce03d 100644
--- a/drivers/accel/ivpu/Kconfig
+++ b/drivers/accel/ivpu/Kconfig
@@ -1,16 +1,27 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 config DRM_ACCEL_IVPU
-	tristate "Intel VPU for Meteor Lake and newer"
+	tristate "Intel NPU (Neural Processing Unit)"
 	depends on DRM_ACCEL
 	depends on X86_64 && !UML
 	depends on PCI && PCI_MSI
 	select FW_LOADER
-	select SHMEM
+	select DRM_GEM_SHMEM_HELPER
 	select GENERIC_ALLOCATOR
+	select WANT_DEV_COREDUMP
 	help
-	  Choose this option if you have a system that has an 14th generation Intel CPU
-	  or newer. VPU stands for Versatile Processing Unit and it's a CPU-integrated
-	  inference accelerator for Computer Vision and Deep Learning applications.
+	  Choose this option if you have a system with an 14th generation
+	  Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU)
+	  is a CPU-integrated inference accelerator for Computer Vision
+	  and Deep Learning applications.
 
 	  If "M" is selected, the module will be called intel_vpu.
+
+config DRM_ACCEL_IVPU_DEBUG
+	bool "Intel NPU debug mode"
+	depends on DRM_ACCEL_IVPU
+	help
+	  Choose this option to enable additional
+	  debug features for the Intel NPU driver:
+	  - Always print debug messages regardless of dyndbg config,
+	  - Enable unsafe module params.
diff --git a/drivers/accel/ivpu/Makefile b/drivers/accel/ivpu/Makefile
index 95ff7ad16338..1029e0bab061 100644
--- a/drivers/accel/ivpu/Makefile
+++ b/drivers/accel/ivpu/Makefile
@@ -1,20 +1,29 @@
 # SPDX-License-Identifier: GPL-2.0-only
-# Copyright (C) 2023 Intel Corporation
+# Copyright (C) 2023-2024 Intel Corporation
 
 intel_vpu-y := \
 	ivpu_drv.o \
 	ivpu_fw.o \
 	ivpu_fw_log.o \
 	ivpu_gem.o \
-	ivpu_hw_37xx.o \
-	ivpu_hw_40xx.o \
+	ivpu_hw.o \
+	ivpu_hw_btrs.o \
+	ivpu_hw_ip.o \
 	ivpu_ipc.o \
 	ivpu_job.o \
 	ivpu_jsm_msg.o \
 	ivpu_mmu.o \
 	ivpu_mmu_context.o \
-	ivpu_pm.o
+	ivpu_ms.o \
+	ivpu_pm.o \
+	ivpu_sysfs.o \
+	ivpu_trace_points.o
 
 intel_vpu-$(CONFIG_DEBUG_FS) += ivpu_debugfs.o
+intel_vpu-$(CONFIG_DEV_COREDUMP) += ivpu_coredump.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o
+
+subdir-ccflags-$(CONFIG_DRM_ACCEL_IVPU_DEBUG) += -DDEBUG
+
+CFLAGS_ivpu_trace_points.o = -I$(src)
diff --git a/drivers/accel/ivpu/ivpu_coredump.c b/drivers/accel/ivpu/ivpu_coredump.c
new file mode 100644
index 000000000000..16ad0c30818c
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_coredump.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+
+#include "ivpu_coredump.h"
+#include "ivpu_fw.h"
+#include "ivpu_gem.h"
+#include "vpu_boot_api.h"
+
+#define CRASH_DUMP_HEADER "Intel NPU crash dump"
+#define CRASH_DUMP_HEADERS_SIZE SZ_4K
+
+void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_print_iterator pi = {};
+	struct drm_printer p;
+	size_t coredump_size;
+	char *coredump;
+
+	coredump_size = CRASH_DUMP_HEADERS_SIZE + FW_VERSION_HEADER_SIZE +
+			ivpu_bo_size(vdev->fw->mem_log_crit) + ivpu_bo_size(vdev->fw->mem_log_verb);
+	coredump = vmalloc(coredump_size);
+	if (!coredump)
+		return;
+
+	pi.data = coredump;
+	pi.remain = coredump_size;
+	p = drm_coredump_printer(&pi);
+
+	drm_printf(&p, "%s\n", CRASH_DUMP_HEADER);
+	drm_printf(&p, "FW version: %s\n", vdev->fw->version);
+	ivpu_fw_log_print(vdev, false, &p);
+
+	dev_coredumpv(vdev->drm.dev, coredump, pi.offset, GFP_KERNEL);
+}
diff --git a/drivers/accel/ivpu/ivpu_coredump.h b/drivers/accel/ivpu/ivpu_coredump.h
new file mode 100644
index 000000000000..8efb09d02441
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_coredump.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __IVPU_COREDUMP_H__
+#define __IVPU_COREDUMP_H__
+
+#include <drm/drm_print.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_fw_log.h"
+
+#ifdef CONFIG_DEV_COREDUMP
+void ivpu_dev_coredump(struct ivpu_device *vdev);
+#else
+static inline void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_printer p = drm_info_printer(vdev->drm.dev);
+
+	ivpu_fw_log_print(vdev, false, &p);
+}
+#endif
+
+#endif /* __IVPU_COREDUMP_H__ */
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index ea453b985b49..cd24ccd20ba6 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -1,8 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
+#include <linux/debugfs.h>
+#include <linux/fault-inject.h>
+
 #include <drm/drm_debugfs.h>
 #include <drm/drm_file.h>
 #include <drm/drm_print.h>
@@ -14,6 +17,7 @@
 #include "ivpu_fw.h"
 #include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
+#include "ivpu_hw.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_pm.h"
 
@@ -42,6 +46,14 @@ static int fw_name_show(struct seq_file *s, void *v)
 	return 0;
 }
 
+static int fw_version_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = seq_to_ivpu(s);
+
+	seq_printf(s, "%s\n", vdev->fw->version);
+	return 0;
+}
+
 static int fw_trace_capability_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = seq_to_ivpu(s);
@@ -101,18 +113,70 @@ static int reset_pending_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = seq_to_ivpu(s);
 
-	seq_printf(s, "%d\n", atomic_read(&vdev->pm->in_reset));
+	seq_printf(s, "%d\n", atomic_read(&vdev->pm->reset_pending));
+	return 0;
+}
+
+static int firewall_irq_counter_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = seq_to_ivpu(s);
+
+	seq_printf(s, "%d\n", atomic_read(&vdev->hw->firewall_irq_counter));
 	return 0;
 }
 
 static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"bo_list", bo_list_show, 0},
 	{"fw_name", fw_name_show, 0},
+	{"fw_version", fw_version_show, 0},
 	{"fw_trace_capability", fw_trace_capability_show, 0},
 	{"fw_trace_config", fw_trace_config_show, 0},
 	{"last_bootmode", last_bootmode_show, 0},
 	{"reset_counter", reset_counter_show, 0},
 	{"reset_pending", reset_pending_show, 0},
+	{"firewall_irq_counter", firewall_irq_counter_show, 0},
+};
+
+static int dvfs_mode_get(void *data, u64 *dvfs_mode)
+{
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
+
+	*dvfs_mode = vdev->fw->dvfs_mode;
+	return 0;
+}
+
+static int dvfs_mode_set(void *data, u64 dvfs_mode)
+{
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
+
+	vdev->fw->dvfs_mode = (u32)dvfs_mode;
+	return pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(dvfs_mode_fops, dvfs_mode_get, dvfs_mode_set, "%llu\n");
+
+static ssize_t
+fw_dyndbg_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+{
+	struct ivpu_device *vdev = file->private_data;
+	char buffer[VPU_DYNDBG_CMD_MAX_LEN] = {};
+	int ret;
+
+	if (size >= VPU_DYNDBG_CMD_MAX_LEN)
+		return -EINVAL;
+
+	ret = strncpy_from_user(buffer, user_buf, size);
+	if (ret < 0)
+		return ret;
+
+	ivpu_jsm_dyndbg_control(vdev, buffer, size);
+	return size;
+}
+
+static const struct file_operations fw_dyndbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = fw_dyndbg_fops_write,
 };
 
 static int fw_log_show(struct seq_file *s, void *v)
@@ -138,7 +202,7 @@ fw_log_fops_write(struct file *file, const char __user *user_buf, size_t size, l
 	if (!size)
 		return -EINVAL;
 
-	ivpu_fw_log_clear(vdev);
+	ivpu_fw_log_mark_read(vdev);
 	return size;
 }
 
@@ -152,6 +216,33 @@ static const struct file_operations fw_log_fops = {
 };
 
 static ssize_t
+fw_profiling_freq_fops_write(struct file *file, const char __user *user_buf,
+			     size_t size, loff_t *pos)
+{
+	struct ivpu_device *vdev = file->private_data;
+	bool enable;
+	int ret;
+
+	ret = kstrtobool_from_user(user_buf, size, &enable);
+	if (ret < 0)
+		return ret;
+
+	ivpu_hw_profiling_freq_drive(vdev, enable);
+
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
+
+	return size;
+}
+
+static const struct file_operations fw_profiling_freq_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = fw_profiling_freq_fops_write,
+};
+
+static ssize_t
 fw_trace_destination_mask_fops_write(struct file *file, const char __user *user_buf,
 				     size_t size, loff_t *pos)
 {
@@ -232,43 +323,161 @@ static const struct file_operations fw_trace_level_fops = {
 };
 
 static ssize_t
-ivpu_reset_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
 {
 	struct ivpu_device *vdev = file->private_data;
+	int ret;
 
 	if (!size)
 		return -EINVAL;
 
-	if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COMPUTE))
-		return -ENODEV;
-	if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COPY))
-		return -ENODEV;
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
 
+	ivpu_pm_trigger_recovery(vdev, "debugfs");
+	flush_work(&vdev->pm->recovery_work);
+	ivpu_rpm_put(vdev);
 	return size;
 }
 
+static const struct file_operations ivpu_force_recovery_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = ivpu_force_recovery_fn,
+};
+
+static int ivpu_reset_engine_fn(void *data, u64 val)
+{
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
+
+	return ivpu_jsm_reset_engine(vdev, (u32)val);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_reset_engine_fops, NULL, ivpu_reset_engine_fn, "0x%02llx\n");
+
+static int ivpu_resume_engine_fn(void *data, u64 val)
+{
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
+
+	return ivpu_jsm_hws_resume_engine(vdev, (u32)val);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_resume_engine_fops, NULL, ivpu_resume_engine_fn, "0x%02llx\n");
+
+static int dct_active_get(void *data, u64 *active_percent)
+{
+	struct ivpu_device *vdev = data;
+
+	*active_percent = vdev->pm->dct_active_percent;
+
+	return 0;
+}
+
+static int dct_active_set(void *data, u64 active_percent)
+{
+	struct ivpu_device *vdev = data;
+	int ret;
+
+	if (active_percent > 100)
+		return -EINVAL;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	if (active_percent)
+		ret = ivpu_pm_dct_enable(vdev, active_percent);
+	else
+		ret = ivpu_pm_dct_disable(vdev);
+
+	ivpu_rpm_put(vdev);
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_dct_fops, dct_active_get, dct_active_set, "%llu\n");
+
+static int priority_bands_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = s->private;
+	struct ivpu_hw_info *hw = vdev->hw;
+
+	for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE;
+	     band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) {
+		switch (band) {
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE:
+			seq_puts(s, "Idle:     ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL:
+			seq_puts(s, "Normal:   ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS:
+			seq_puts(s, "Focus:    ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME:
+			seq_puts(s, "Realtime: ");
+			break;
+		}
+
+		seq_printf(s, "grace_period %9u process_grace_period %9u process_quantum %9u\n",
+			   hw->hws.grace_period[band], hw->hws.process_grace_period[band],
+			   hw->hws.process_quantum[band]);
+	}
+
+	return 0;
+}
+
+static int priority_bands_fops_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, priority_bands_show, inode->i_private);
+}
+
 static ssize_t
-ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
 {
-	struct ivpu_device *vdev = file->private_data;
+	struct seq_file *s = file->private_data;
+	struct ivpu_device *vdev = s->private;
+	char buf[64];
+	u32 grace_period;
+	u32 process_grace_period;
+	u32 process_quantum;
+	u32 band;
+	int ret;
 
-	if (!size)
+	if (size >= sizeof(buf))
+		return -EINVAL;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf) - 1, pos, user_buf, size);
+	if (ret < 0)
+		return ret;
+
+	buf[ret] = '\0';
+	ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period,
+		     &process_quantum);
+	if (ret != 4)
 		return -EINVAL;
 
-	ivpu_pm_schedule_recovery(vdev);
+	if (band >= VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT)
+		return -EINVAL;
+
+	vdev->hw->hws.grace_period[band] = grace_period;
+	vdev->hw->hws.process_grace_period[band] = process_grace_period;
+	vdev->hw->hws.process_quantum[band] = process_quantum;
+
 	return size;
 }
 
-static const struct file_operations ivpu_force_recovery_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_force_recovery_fn,
-};
-
-static const struct file_operations ivpu_reset_engine_fops = {
+static const struct file_operations ivpu_hws_priority_bands_fops = {
 	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_reset_engine_fn,
+	.open = priority_bands_fops_open,
+	.write = priority_bands_fops_write,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
 };
 
 void ivpu_debugfs_init(struct ivpu_device *vdev)
@@ -280,6 +489,11 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 	debugfs_create_file("force_recovery", 0200, debugfs_root, vdev,
 			    &ivpu_force_recovery_fops);
 
+	debugfs_create_file("dvfs_mode", 0644, debugfs_root, vdev,
+			    &dvfs_mode_fops);
+
+	debugfs_create_file("fw_dyndbg", 0200, debugfs_root, vdev,
+			    &fw_dyndbg_fops);
 	debugfs_create_file("fw_log", 0644, debugfs_root, vdev,
 			    &fw_log_fops);
 	debugfs_create_file("fw_trace_destination_mask", 0200, debugfs_root, vdev,
@@ -288,7 +502,21 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 			    &fw_trace_hw_comp_mask_fops);
 	debugfs_create_file("fw_trace_level", 0200, debugfs_root, vdev,
 			    &fw_trace_level_fops);
+	debugfs_create_file("hws_priority_bands", 0200, debugfs_root, vdev,
+			    &ivpu_hws_priority_bands_fops);
 
 	debugfs_create_file("reset_engine", 0200, debugfs_root, vdev,
 			    &ivpu_reset_engine_fops);
+	debugfs_create_file("resume_engine", 0200, debugfs_root, vdev,
+			    &ivpu_resume_engine_fops);
+
+	if (ivpu_hw_ip_gen(vdev) >= IVPU_HW_IP_40XX) {
+		debugfs_create_file("fw_profiling_freq_drive", 0200,
+				    debugfs_root, vdev, &fw_profiling_freq_fops);
+		debugfs_create_file("dct", 0644, debugfs_root, vdev, &ivpu_dct_fops);
+	}
+
+#ifdef CONFIG_FAULT_INJECTION
+	fault_create_debugfs_attr("fail_hw", debugfs_root, &ivpu_hw_failure);
+#endif
 }
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 790603017653..3289751b4757 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,11 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/workqueue.h>
+#include <generated/utsrelease.h>
 
 #include <drm/drm_accel.h>
 #include <drm/drm_file.h>
@@ -13,10 +16,11 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_prime.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
@@ -24,37 +28,45 @@
 #include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
+#include "ivpu_ms.h"
 #include "ivpu_pm.h"
+#include "ivpu_sysfs.h"
+#include "vpu_boot_api.h"
 
 #ifndef DRIVER_VERSION_STR
-#define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
-			   __stringify(DRM_IVPU_DRIVER_MINOR) "."
+#define DRIVER_VERSION_STR "1.0.0 " UTS_RELEASE
 #endif
 
-static const struct drm_driver driver;
-
-static struct lock_class_key submitted_jobs_xa_lock_class_key;
-
 int ivpu_dbg_mask;
 module_param_named(dbg_mask, ivpu_dbg_mask, int, 0644);
 MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
 
 int ivpu_test_mode;
+#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG)
 module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644);
-MODULE_PARM_DESC(test_mode, "Test mode: 0 - normal operation, 1 - fw unit test, 2 - null hw");
+MODULE_PARM_DESC(test_mode, "Test mode mask. See IVPU_TEST_MODE_* macros.");
+#endif
 
 u8 ivpu_pll_min_ratio;
 module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
-MODULE_PARM_DESC(pll_min_ratio, "Minimum PLL ratio used to set VPU frequency");
+MODULE_PARM_DESC(pll_min_ratio, "Minimum PLL ratio used to set NPU frequency");
 
 u8 ivpu_pll_max_ratio = U8_MAX;
 module_param_named(pll_max_ratio, ivpu_pll_max_ratio, byte, 0644);
-MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set VPU frequency");
+MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set NPU frequency");
+
+int ivpu_sched_mode = IVPU_SCHED_MODE_AUTO;
+module_param_named(sched_mode, ivpu_sched_mode, int, 0444);
+MODULE_PARM_DESC(sched_mode, "Scheduler mode: -1 - Use default scheduler, 0 - Use OS scheduler, 1 - Use HW scheduler");
 
 bool ivpu_disable_mmu_cont_pages;
-module_param_named(disable_mmu_cont_pages, ivpu_disable_mmu_cont_pages, bool, 0644);
+module_param_named(disable_mmu_cont_pages, ivpu_disable_mmu_cont_pages, bool, 0444);
 MODULE_PARM_DESC(disable_mmu_cont_pages, "Disable MMU contiguous pages optimization");
 
+bool ivpu_force_snoop;
+module_param_named(force_snoop, ivpu_force_snoop, bool, 0444);
+MODULE_PARM_DESC(force_snoop, "Force snooping for NPU host memory access");
+
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
@@ -67,22 +79,19 @@ struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 	return file_priv;
 }
 
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id)
+static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *file_priv)
 {
-	struct ivpu_file_priv *file_priv;
-
-	xa_lock_irq(&vdev->context_xa);
-	file_priv = xa_load(&vdev->context_xa, id);
-	/* file_priv may still be in context_xa during file_priv_release() */
-	if (file_priv && !kref_get_unless_zero(&file_priv->ref))
-		file_priv = NULL;
-	xa_unlock_irq(&vdev->context_xa);
-
-	if (file_priv)
-		ivpu_dbg(vdev, KREF, "file_priv get by id: ctx %u refcount %u\n",
-			 file_priv->ctx.id, kref_read(&file_priv->ref));
-
-	return file_priv;
+	mutex_lock(&file_priv->lock);
+	if (file_priv->bound) {
+		ivpu_dbg(vdev, FILE, "file_priv unbind: ctx %u\n", file_priv->ctx.id);
+
+		ivpu_cmdq_release_all_locked(file_priv);
+		ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx);
+		ivpu_mmu_context_fini(vdev, &file_priv->ctx);
+		file_priv->bound = false;
+		drm_WARN_ON(&vdev->drm, !xa_erase_irq(&vdev->context_xa, file_priv->ctx.id));
+	}
+	mutex_unlock(&file_priv->lock);
 }
 
 static void file_priv_release(struct kref *ref)
@@ -90,13 +99,18 @@ static void file_priv_release(struct kref *ref)
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
 	struct ivpu_device *vdev = file_priv->vdev;
 
-	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u bound %d\n",
+		 file_priv->ctx.id, (bool)file_priv->bound);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	mutex_lock(&vdev->context_list_lock);
+	file_priv_unbind(vdev, file_priv);
+	drm_WARN_ON(&vdev->drm, !xa_empty(&file_priv->cmdq_xa));
+	xa_destroy(&file_priv->cmdq_xa);
+	mutex_unlock(&vdev->context_list_lock);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 
-	ivpu_cmdq_release_all(file_priv);
-	ivpu_bo_remove_all_bos_from_context(&file_priv->ctx);
-	ivpu_jsm_context_release(vdev, file_priv->ctx.id);
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-	drm_WARN_ON(&vdev->drm, xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
+	mutex_destroy(&file_priv->ms_lock);
 	mutex_destroy(&file_priv->lock);
 	kfree(file_priv);
 }
@@ -106,8 +120,6 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link)
 	struct ivpu_file_priv *file_priv = *link;
 	struct ivpu_device *vdev = file_priv->vdev;
 
-	drm_WARN_ON(&vdev->drm, !file_priv);
-
 	ivpu_dbg(vdev, KREF, "file_priv put: ctx %u refcount %u\n",
 		 file_priv->ctx.id, kref_read(&file_priv->ref));
 
@@ -115,36 +127,18 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link)
 	kref_put(&file_priv->ref, file_priv_release);
 }
 
-static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param *args)
+bool ivpu_is_capable(struct ivpu_device *vdev, u32 capability)
 {
-	switch (args->index) {
+	switch (capability) {
 	case DRM_IVPU_CAP_METRIC_STREAMER:
-		args->value = 0;
-		break;
+		return true;
 	case DRM_IVPU_CAP_DMA_MEMORY_RANGE:
-		args->value = 1;
-		break;
+		return true;
+	case DRM_IVPU_CAP_MANAGE_CMDQ:
+		return vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW;
 	default:
-		return -EINVAL;
+		return false;
 	}
-
-	return 0;
-}
-
-static int ivpu_get_core_clock_rate(struct ivpu_device *vdev, u64 *clk_rate)
-{
-	int ret;
-
-	ret = ivpu_rpm_get_if_active(vdev);
-	if (ret < 0)
-		return ret;
-
-	*clk_rate = ret ? ivpu_hw_reg_pll_freq_get(vdev) : 0;
-
-	if (ret)
-		ivpu_rpm_put(vdev);
-
-	return 0;
 }
 
 static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
@@ -170,7 +164,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = vdev->platform;
 		break;
 	case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
-		ret = ivpu_get_core_clock_rate(vdev, &args->value);
+		args->value = ivpu_hw_dpu_max_freq_get(vdev);
 		break;
 	case DRM_IVPU_PARAM_NUM_CONTEXTS:
 		args->value = ivpu_get_context_count(vdev);
@@ -178,9 +172,6 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 		args->value = vdev->hw->ranges.user.start;
 		break;
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		args->value = file_priv->priority;
-		break;
 	case DRM_IVPU_PARAM_CONTEXT_ID:
 		args->value = file_priv->ctx.id;
 		break;
@@ -207,7 +198,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = vdev->hw->sku;
 		break;
 	case DRM_IVPU_PARAM_CAPABILITIES:
-		ret = ivpu_get_capabilities(vdev, args);
+		args->value = ivpu_is_capable(vdev, args->index);
 		break;
 	default:
 		ret = -EINVAL;
@@ -220,17 +211,10 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 
 static int ivpu_set_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_param *args = data;
 	int ret = 0;
 
 	switch (args->param) {
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		if (args->value <= DRM_IVPU_CONTEXT_PRIORITY_REALTIME)
-			file_priv->priority = args->value;
-		else
-			ret = -EINVAL;
-		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -243,50 +227,60 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
 	u32 ctx_id;
-	void *old;
-	int ret;
+	int idx, ret;
 
-	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
-		return ret;
-	}
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
 	if (!file_priv) {
 		ret = -ENOMEM;
-		goto err_xa_erase;
+		goto err_dev_exit;
 	}
 
+	INIT_LIST_HEAD(&file_priv->ms_instance_list);
+
 	file_priv->vdev = vdev;
-	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
+	file_priv->bound = true;
 	kref_init(&file_priv->ref);
 	mutex_init(&file_priv->lock);
+	mutex_init(&file_priv->ms_lock);
 
-	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
-	if (ret)
-		goto err_mutex_destroy;
+	mutex_lock(&vdev->context_list_lock);
 
-	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
-	if (xa_is_err(old)) {
-		ret = xa_err(old);
-		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
-		goto err_ctx_fini;
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, file_priv,
+			   vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		goto err_unlock;
 	}
 
+	ivpu_mmu_context_init(vdev, &file_priv->ctx, ctx_id);
+
+	file_priv->job_limit.min = FIELD_PREP(IVPU_JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
+	file_priv->job_limit.max = file_priv->job_limit.min | IVPU_JOB_ID_JOB_MASK;
+
+	xa_init_flags(&file_priv->cmdq_xa, XA_FLAGS_ALLOC1);
+	file_priv->cmdq_limit.min = IVPU_CMDQ_MIN_ID;
+	file_priv->cmdq_limit.max = IVPU_CMDQ_MAX_ID;
+
+	mutex_unlock(&vdev->context_list_lock);
+	drm_dev_exit(idx);
+
+	file->driver_priv = file_priv;
+
 	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
 		 ctx_id, current->comm, task_pid_nr(current));
 
-	file->driver_priv = file_priv;
 	return 0;
 
-err_ctx_fini:
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-err_mutex_destroy:
+err_unlock:
+	mutex_unlock(&vdev->context_list_lock);
+	mutex_destroy(&file_priv->ms_lock);
 	mutex_destroy(&file_priv->lock);
 	kfree(file_priv);
-err_xa_erase:
-	xa_erase_irq(&vdev->context_xa, ctx_id);
+err_dev_exit:
+	drm_dev_exit(idx);
 	return ret;
 }
 
@@ -298,6 +292,7 @@ static void ivpu_postclose(struct drm_device *dev, struct drm_file *file)
 	ivpu_dbg(vdev, FILE, "file_priv close: ctx %u process %s pid %d\n",
 		 file_priv->ctx.id, current->comm, task_pid_nr(current));
 
+	ivpu_ms_cleanup(file_priv);
 	ivpu_file_priv_put(&file_priv);
 }
 
@@ -308,6 +303,13 @@ static const struct drm_ioctl_desc ivpu_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(IVPU_BO_INFO, ivpu_bo_info_ioctl, 0),
 	DRM_IOCTL_DEF_DRV(IVPU_SUBMIT, ivpu_submit_ioctl, 0),
 	DRM_IOCTL_DEF_DRV(IVPU_BO_WAIT, ivpu_bo_wait_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_START, ivpu_ms_start_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_GET_DATA, ivpu_ms_get_data_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_STOP, ivpu_ms_stop_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_GET_INFO, ivpu_ms_get_info_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_CMDQ_CREATE, ivpu_cmdq_create_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_CMDQ_DESTROY, ivpu_cmdq_destroy_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_CMDQ_SUBMIT, ivpu_cmdq_submit_ioctl, 0),
 };
 
 static int ivpu_wait_for_ready(struct ivpu_device *vdev)
@@ -317,16 +319,14 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 	unsigned long timeout;
 	int ret;
 
-	if (ivpu_test_mode == IVPU_TEST_MODE_FW_TEST)
+	if (ivpu_test_mode & IVPU_TEST_MODE_FW_TEST)
 		return 0;
 
-	ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG);
+	ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG, NULL);
 
 	timeout = jiffies + msecs_to_jiffies(vdev->timeout.boot);
 	while (1) {
-		ret = ivpu_ipc_irq_handler(vdev);
-		if (ret)
-			break;
+		ivpu_ipc_irq_handler(vdev);
 		ret = ivpu_ipc_receive(vdev, &cons, &ipc_hdr, NULL, 0);
 		if (ret != -ETIMEDOUT || time_after_eq(jiffies, timeout))
 			break;
@@ -337,15 +337,28 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 	ivpu_ipc_consumer_del(vdev, &cons);
 
 	if (!ret && ipc_hdr.data_addr != IVPU_IPC_BOOT_MSG_DATA_ADDR) {
-		ivpu_err(vdev, "Invalid VPU ready message: 0x%x\n",
+		ivpu_err(vdev, "Invalid NPU ready message: 0x%x\n",
 			 ipc_hdr.data_addr);
 		return -EIO;
 	}
 
 	if (!ret)
-		ivpu_dbg(vdev, PM, "VPU ready message received successfully\n");
-	else
-		ivpu_hw_diagnose_failure(vdev);
+		ivpu_dbg(vdev, PM, "NPU ready message received successfully\n");
+
+	return ret;
+}
+
+static int ivpu_hw_sched_init(struct ivpu_device *vdev)
+{
+	int ret = 0;
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		ret = ivpu_jsm_hws_setup_priority_bands(vdev);
+		if (ret) {
+			ivpu_err(vdev, "Failed to enable hw scheduler: %d", ret);
+			return ret;
+		}
+	}
 
 	return ret;
 }
@@ -361,8 +374,11 @@ int ivpu_boot(struct ivpu_device *vdev)
 {
 	int ret;
 
+	drm_WARN_ON(&vdev->drm, atomic_read(&vdev->job_timeout_counter));
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa));
+
 	/* Update boot params located at first 4KB of FW memory */
-	ivpu_fw_boot_params_setup(vdev, vdev->fw->mem->kvaddr);
+	ivpu_fw_boot_params_setup(vdev, ivpu_bo_vaddr(vdev->fw->mem));
 
 	ret = ivpu_hw_boot_fw(vdev);
 	if (ret) {
@@ -373,20 +389,44 @@ int ivpu_boot(struct ivpu_device *vdev)
 	ret = ivpu_wait_for_ready(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
-		return ret;
+		goto err_diagnose_failure;
 	}
 
 	ivpu_hw_irq_clear(vdev);
 	enable_irq(vdev->irq);
 	ivpu_hw_irq_enable(vdev);
 	ivpu_ipc_enable(vdev);
+
+	if (ivpu_fw_is_cold_boot(vdev)) {
+		ret = ivpu_pm_dct_init(vdev);
+		if (ret)
+			goto err_disable_ipc;
+
+		ret = ivpu_hw_sched_init(vdev);
+		if (ret)
+			goto err_disable_ipc;
+	}
+
 	return 0;
+
+err_disable_ipc:
+	ivpu_ipc_disable(vdev);
+	ivpu_hw_irq_disable(vdev);
+	disable_irq(vdev->irq);
+err_diagnose_failure:
+	ivpu_hw_diagnose_failure(vdev);
+	ivpu_mmu_evtq_dump(vdev);
+	ivpu_dev_coredump(vdev);
+	return ret;
 }
 
 void ivpu_prepare_for_reset(struct ivpu_device *vdev)
 {
 	ivpu_hw_irq_disable(vdev);
 	disable_irq(vdev->irq);
+	flush_work(&vdev->irq_ipc_work);
+	flush_work(&vdev->irq_dct_work);
+	flush_work(&vdev->context_abort_work);
 	ivpu_ipc_disable(vdev);
 	ivpu_mmu_disable(vdev);
 }
@@ -395,12 +435,15 @@ int ivpu_shutdown(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ivpu_prepare_for_reset(vdev);
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
 
 	ret = ivpu_hw_power_down(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to power down HW: %d\n", ret);
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
 	return ret;
 }
 
@@ -414,6 +457,8 @@ static const struct drm_driver driver = {
 
 	.open = ivpu_open,
 	.postclose = ivpu_postclose,
+
+	.gem_create_object = ivpu_gem_create_object,
 	.gem_prime_import = ivpu_gem_prime_import,
 
 	.ioctls = ivpu_drm_ioctls,
@@ -422,9 +467,8 @@ static const struct drm_driver driver = {
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
-	.date = DRIVER_DATE,
-	.major = DRM_IVPU_DRIVER_MAJOR,
-	.minor = DRM_IVPU_DRIVER_MINOR,
+
+	.major = 1,
 };
 
 static int ivpu_irq_init(struct ivpu_device *vdev)
@@ -438,9 +482,15 @@ static int ivpu_irq_init(struct ivpu_device *vdev)
 		return ret;
 	}
 
+	INIT_WORK(&vdev->irq_ipc_work, ivpu_ipc_irq_work_fn);
+	INIT_WORK(&vdev->irq_dct_work, ivpu_pm_irq_dct_work_fn);
+	INIT_WORK(&vdev->context_abort_work, ivpu_context_abort_work_fn);
+
+	ivpu_irq_handlers_init(vdev);
+
 	vdev->irq = pci_irq_vector(pdev, 0);
 
-	ret = devm_request_irq(vdev->drm.dev, vdev->irq, vdev->hw->ops->irq_handler,
+	ret = devm_request_irq(vdev->drm.dev, vdev->irq, ivpu_hw_irq_handler,
 			       IRQF_NO_AUTOEN, DRIVER_NAME, vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to request an IRQ %d\n", ret);
@@ -479,9 +529,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
@@ -518,21 +567,35 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (!vdev->pm)
 		return -ENOMEM;
 
-	if (ivpu_hw_gen(vdev) >= IVPU_HW_40XX) {
-		vdev->hw->ops = &ivpu_hw_40xx_ops;
+	if (ivpu_hw_ip_gen(vdev) >= IVPU_HW_IP_40XX)
 		vdev->hw->dma_bits = 48;
-	} else {
-		vdev->hw->ops = &ivpu_hw_37xx_ops;
+	else
 		vdev->hw->dma_bits = 38;
-	}
 
 	vdev->platform = IVPU_PLATFORM_INVALID;
 	vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
 	vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
 	atomic64_set(&vdev->unique_id_counter, 0);
-	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
+	atomic_set(&vdev->job_timeout_counter, 0);
+	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
+	xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
+	INIT_LIST_HEAD(&vdev->bo_list);
+
+	vdev->db_limit.min = IVPU_MIN_DB;
+	vdev->db_limit.max = IVPU_MAX_DB;
+
+	ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock);
+	if (ret)
+		goto err_xa_destroy;
+
+	ret = drmm_mutex_init(&vdev->drm, &vdev->submitted_jobs_lock);
+	if (ret)
+		goto err_xa_destroy;
+
+	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
+	if (ret)
+		goto err_xa_destroy;
 
 	ret = ivpu_pci_init(vdev);
 	if (ret)
@@ -543,18 +606,16 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 		goto err_xa_destroy;
 
 	/* Init basic HW info based on buttress registers which are accessible before power up */
-	ret = ivpu_hw_info_init(vdev);
+	ret = ivpu_hw_init(vdev);
 	if (ret)
 		goto err_xa_destroy;
 
 	/* Power up early so the rest of init code can access VPU registers */
 	ret = ivpu_hw_power_up(vdev);
 	if (ret)
-		goto err_xa_destroy;
+		goto err_shutdown;
 
-	ret = ivpu_mmu_global_context_init(vdev);
-	if (ret)
-		goto err_power_down;
+	ivpu_mmu_global_context_init(vdev);
 
 	ret = ivpu_mmu_init(vdev);
 	if (ret)
@@ -574,20 +635,15 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 
 	ivpu_pm_init(vdev);
 
-	ret = ivpu_job_done_thread_init(vdev);
-	if (ret)
-		goto err_ipc_fini;
-
 	ret = ivpu_boot(vdev);
 	if (ret)
-		goto err_job_done_thread_fini;
+		goto err_ipc_fini;
 
+	ivpu_job_done_consumer_init(vdev);
 	ivpu_pm_enable(vdev);
 
 	return 0;
 
-err_job_done_thread_fini:
-	ivpu_job_done_thread_fini(vdev);
 err_ipc_fini:
 	ivpu_ipc_fini(vdev);
 err_fw_fini:
@@ -596,30 +652,47 @@ err_mmu_rctx_fini:
 	ivpu_mmu_reserved_context_fini(vdev);
 err_mmu_gctx_fini:
 	ivpu_mmu_global_context_fini(vdev);
-err_power_down:
-	ivpu_hw_power_down(vdev);
-	if (IVPU_WA(d3hot_after_power_off))
-		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+err_shutdown:
+	ivpu_shutdown(vdev);
 err_xa_destroy:
+	xa_destroy(&vdev->db_xa);
 	xa_destroy(&vdev->submitted_jobs_xa);
 	xa_destroy(&vdev->context_xa);
 	return ret;
 }
 
+static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
+{
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+
+	mutex_lock(&vdev->context_list_lock);
+
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		file_priv_unbind(vdev, file_priv);
+
+	mutex_unlock(&vdev->context_list_lock);
+}
+
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
+	ivpu_jobs_abort_all(vdev);
+	ivpu_pm_disable_recovery(vdev);
 	ivpu_pm_disable(vdev);
+	ivpu_prepare_for_reset(vdev);
 	ivpu_shutdown(vdev);
-	if (IVPU_WA(d3hot_after_power_off))
-		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
-	ivpu_job_done_thread_fini(vdev);
-	ivpu_pm_cancel_recovery(vdev);
+
+	ivpu_ms_cleanup_all(vdev);
+	ivpu_job_done_consumer_fini(vdev);
+	ivpu_bo_unbind_all_user_contexts(vdev);
 
 	ivpu_ipc_fini(vdev);
 	ivpu_fw_fini(vdev);
 	ivpu_mmu_reserved_context_fini(vdev);
 	ivpu_mmu_global_context_fini(vdev);
 
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->db_xa));
+	xa_destroy(&vdev->db_xa);
 	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa));
 	xa_destroy(&vdev->submitted_jobs_xa);
 	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->context_xa));
@@ -630,6 +703,8 @@ static struct pci_device_id ivpu_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_ARL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PTL_P) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_WCL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, ivpu_pci_ids);
@@ -650,6 +725,7 @@ static int ivpu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	ivpu_debugfs_init(vdev);
+	ivpu_sysfs_init(vdev);
 
 	ret = drm_dev_register(&vdev->drm, 0);
 	if (ret) {
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 417ddeca8517..62ab1c654e63 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_DRV_H__
@@ -17,17 +17,26 @@
 #include <uapi/drm/ivpu_accel.h>
 
 #include "ivpu_mmu_context.h"
+#include "ivpu_ipc.h"
 
 #define DRIVER_NAME "intel_vpu"
-#define DRIVER_DESC "Driver for Intel Versatile Processing Unit (VPU)"
-#define DRIVER_DATE "20230117"
+#define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)"
 
-#define PCI_DEVICE_ID_MTL   0x7d1d
-#define PCI_DEVICE_ID_ARL   0xad1d
-#define PCI_DEVICE_ID_LNL   0x643e
+#define PCI_DEVICE_ID_MTL	0x7d1d
+#define PCI_DEVICE_ID_ARL	0xad1d
+#define PCI_DEVICE_ID_LNL	0x643e
+#define PCI_DEVICE_ID_PTL_P	0xb03e
+#define PCI_DEVICE_ID_WCL	0xfd3e
 
-#define IVPU_HW_37XX	37
-#define IVPU_HW_40XX	40
+#define IVPU_HW_IP_37XX 37
+#define IVPU_HW_IP_40XX 40
+#define IVPU_HW_IP_50XX 50
+#define IVPU_HW_IP_60XX 60
+
+#define IVPU_HW_IP_REV_LNL_B0 4
+
+#define IVPU_HW_BTRS_MTL 1
+#define IVPU_HW_BTRS_LNL 2
 
 #define IVPU_GLOBAL_CONTEXT_MMU_SSID   0
 /* SSID 1 is used by the VPU to represent reserved context */
@@ -35,13 +44,26 @@
 #define IVPU_USER_CONTEXT_MIN_SSID     2
 #define IVPU_USER_CONTEXT_MAX_SSID     (IVPU_USER_CONTEXT_MIN_SSID + 63)
 
-#define IVPU_NUM_ENGINES 2
+#define IVPU_MIN_DB 1
+#define IVPU_MAX_DB 255
+
+#define IVPU_JOB_ID_JOB_MASK		GENMASK(7, 0)
+#define IVPU_JOB_ID_CONTEXT_MASK	GENMASK(31, 8)
+
+#define IVPU_NUM_PRIORITIES    4
+#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_PRIORITIES)
+
+#define IVPU_CMDQ_MIN_ID 1
+#define IVPU_CMDQ_MAX_ID 255
 
 #define IVPU_PLATFORM_SILICON 0
 #define IVPU_PLATFORM_SIMICS  2
 #define IVPU_PLATFORM_FPGA    3
+#define IVPU_PLATFORM_HSLE    4
 #define IVPU_PLATFORM_INVALID 8
 
+#define IVPU_SCHED_MODE_AUTO -1
+
 #define IVPU_DBG_REG	 BIT(0)
 #define IVPU_DBG_IRQ	 BIT(1)
 #define IVPU_DBG_MMU	 BIT(2)
@@ -55,6 +77,7 @@
 #define IVPU_DBG_JSM	 BIT(10)
 #define IVPU_DBG_KREF	 BIT(11)
 #define IVPU_DBG_RPM	 BIT(12)
+#define IVPU_DBG_MMU_MAP BIT(13)
 
 #define ivpu_err(vdev, fmt, ...) \
 	drm_err(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
@@ -85,9 +108,11 @@
 struct ivpu_wa_table {
 	bool punit_disabled;
 	bool clear_runtime_mem;
-	bool d3hot_after_power_off;
 	bool interrupt_clear_with_0;
 	bool disable_clock_relinquish;
+	bool disable_d0i3_msg;
+	bool wp0_during_power_up;
+	bool disable_d0i2;
 };
 
 struct ivpu_hw_info;
@@ -112,20 +137,39 @@ struct ivpu_device {
 
 	struct ivpu_mmu_context gctx;
 	struct ivpu_mmu_context rctx;
+	struct mutex context_list_lock; /* Protects user context addition/removal */
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
+	struct xarray db_xa;
+	struct xa_limit db_limit;
+	u32 db_next;
+
+	struct work_struct irq_ipc_work;
+	struct work_struct irq_dct_work;
+	struct work_struct context_abort_work;
+
+	struct mutex bo_list_lock; /* Protects bo_list */
+	struct list_head bo_list;
+
+	struct mutex submitted_jobs_lock; /* Protects submitted_jobs */
 	struct xarray submitted_jobs_xa;
-	struct task_struct *job_done_thread;
+	struct ivpu_ipc_consumer job_done_consumer;
+	atomic_t job_timeout_counter;
 
 	atomic64_t unique_id_counter;
 
+	ktime_t busy_start_ts;
+	ktime_t busy_time;
+
 	struct {
 		int boot;
 		int jsm;
 		int tdr;
-		int reschedule_suspend;
+		int inference;
 		int autosuspend;
+		int d0i3_entry_msg;
+		int state_dump_msg;
 	} timeout;
 };
 
@@ -137,29 +181,48 @@ struct ivpu_file_priv {
 	struct kref ref;
 	struct ivpu_device *vdev;
 	struct mutex lock; /* Protects cmdq */
-	struct ivpu_cmdq *cmdq[IVPU_NUM_ENGINES];
+	struct xarray cmdq_xa;
 	struct ivpu_mmu_context ctx;
-	u32 priority;
+	struct mutex ms_lock; /* Protects ms_instance_list, ms_info_bo */
+	struct list_head ms_instance_list;
+	struct ivpu_bo *ms_info_bo;
+	struct xa_limit job_limit;
+	u32 job_id_next;
+	struct xa_limit cmdq_limit;
+	u32 cmdq_id_next;
 	bool has_mmu_faults;
+	bool bound;
+	bool aborted;
 };
 
 extern int ivpu_dbg_mask;
 extern u8 ivpu_pll_min_ratio;
 extern u8 ivpu_pll_max_ratio;
+extern int ivpu_sched_mode;
 extern bool ivpu_disable_mmu_cont_pages;
-
-#define IVPU_TEST_MODE_DISABLED  0
-#define IVPU_TEST_MODE_FW_TEST   1
-#define IVPU_TEST_MODE_NULL_HW   2
+extern bool ivpu_force_snoop;
+
+#define IVPU_TEST_MODE_FW_TEST            BIT(0)
+#define IVPU_TEST_MODE_NULL_HW            BIT(1)
+#define IVPU_TEST_MODE_NULL_SUBMISSION    BIT(2)
+#define IVPU_TEST_MODE_D0I3_MSG_DISABLE   BIT(4)
+#define IVPU_TEST_MODE_D0I3_MSG_ENABLE    BIT(5)
+#define IVPU_TEST_MODE_MIP_DISABLE        BIT(6)
+#define IVPU_TEST_MODE_DISABLE_TIMEOUTS   BIT(8)
+#define IVPU_TEST_MODE_TURBO_ENABLE       BIT(9)
+#define IVPU_TEST_MODE_TURBO_DISABLE      BIT(10)
+#define IVPU_TEST_MODE_CLK_RELINQ_DISABLE BIT(11)
+#define IVPU_TEST_MODE_CLK_RELINQ_ENABLE  BIT(12)
+#define IVPU_TEST_MODE_D0I2_DISABLE       BIT(13)
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id);
 void ivpu_file_priv_put(struct ivpu_file_priv **link);
 
 int ivpu_boot(struct ivpu_device *vdev);
 int ivpu_shutdown(struct ivpu_device *vdev);
 void ivpu_prepare_for_reset(struct ivpu_device *vdev);
+bool ivpu_is_capable(struct ivpu_device *vdev, u32 capability);
 
 static inline u8 ivpu_revision(struct ivpu_device *vdev)
 {
@@ -171,16 +234,37 @@ static inline u16 ivpu_device_id(struct ivpu_device *vdev)
 	return to_pci_dev(vdev->drm.dev)->device;
 }
 
-static inline int ivpu_hw_gen(struct ivpu_device *vdev)
+static inline int ivpu_hw_ip_gen(struct ivpu_device *vdev)
+{
+	switch (ivpu_device_id(vdev)) {
+	case PCI_DEVICE_ID_MTL:
+	case PCI_DEVICE_ID_ARL:
+		return IVPU_HW_IP_37XX;
+	case PCI_DEVICE_ID_LNL:
+		return IVPU_HW_IP_40XX;
+	case PCI_DEVICE_ID_PTL_P:
+	case PCI_DEVICE_ID_WCL:
+		return IVPU_HW_IP_50XX;
+	default:
+		dump_stack();
+		ivpu_err(vdev, "Unknown NPU IP generation\n");
+		return 0;
+	}
+}
+
+static inline int ivpu_hw_btrs_gen(struct ivpu_device *vdev)
 {
 	switch (ivpu_device_id(vdev)) {
 	case PCI_DEVICE_ID_MTL:
 	case PCI_DEVICE_ID_ARL:
-		return IVPU_HW_37XX;
+		return IVPU_HW_BTRS_MTL;
 	case PCI_DEVICE_ID_LNL:
-		return IVPU_HW_40XX;
+	case PCI_DEVICE_ID_PTL_P:
+	case PCI_DEVICE_ID_WCL:
+		return IVPU_HW_BTRS_LNL;
 	default:
-		ivpu_err(vdev, "Unknown VPU device\n");
+		dump_stack();
+		ivpu_err(vdev, "Unknown buttress generation\n");
 		return 0;
 	}
 }
@@ -215,7 +299,13 @@ static inline bool ivpu_is_simics(struct ivpu_device *vdev)
 
 static inline bool ivpu_is_fpga(struct ivpu_device *vdev)
 {
-	return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA;
+	return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA ||
+	       ivpu_get_platform(vdev) == IVPU_PLATFORM_HSLE;
+}
+
+static inline bool ivpu_is_force_snoop_enabled(struct ivpu_device *vdev)
+{
+	return ivpu_force_snoop;
 }
 
 #endif /* __IVPU_DRV_H__ */
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 691da521dde5..9db741695401 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -25,7 +25,6 @@
 #define FW_SHAVE_NN_MAX_SIZE	SZ_2M
 #define FW_RUNTIME_MIN_ADDR	(FW_GLOBAL_MEM_START)
 #define FW_RUNTIME_MAX_ADDR	(FW_GLOBAL_MEM_END - FW_SHARED_MEM_SIZE)
-#define FW_VERSION_HEADER_SIZE	SZ_4K
 #define FW_FILE_IMAGE_OFFSET	(VPU_FW_HEADER_SIZE + FW_VERSION_HEADER_SIZE)
 
 #define WATCHDOG_MSS_REDIRECT	32
@@ -33,28 +32,42 @@
 
 #define ADDR_TO_L2_CACHE_CFG(addr) ((addr) >> 31)
 
-#define IVPU_FW_CHECK_API(vdev, fw_hdr, name, min_major) \
+/* Check if FW API is compatible with the driver */
+#define IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, name, min_major) \
 	ivpu_fw_check_api(vdev, fw_hdr, #name, \
 			  VPU_##name##_API_VER_INDEX, \
 			  VPU_##name##_API_VER_MAJOR, \
 			  VPU_##name##_API_VER_MINOR, min_major)
 
+/* Check if API version is lower that the given version */
+#define IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, name, major, minor) \
+	ivpu_fw_check_api_ver_lt(vdev, fw_hdr, #name, VPU_##name##_API_VER_INDEX, major, minor)
+
+#define IVPU_FOCUS_PRESENT_TIMER_MS 1000
+
 static char *ivpu_firmware;
+#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG)
 module_param_named_unsafe(firmware, ivpu_firmware, charp, 0644);
-MODULE_PARM_DESC(firmware, "VPU firmware binary in /lib/firmware/..");
+MODULE_PARM_DESC(firmware, "NPU firmware binary in /lib/firmware/..");
+#endif
 
-/* TODO: Remove mtl_vpu.bin from names after transition to generation based FW names */
 static struct {
 	int gen;
 	const char *name;
 } fw_names[] = {
-	{ IVPU_HW_37XX, "vpu_37xx.bin" },
-	{ IVPU_HW_37XX, "mtl_vpu.bin" },
-	{ IVPU_HW_37XX, "intel/vpu/vpu_37xx_v0.0.bin" },
-	{ IVPU_HW_40XX, "vpu_40xx.bin" },
-	{ IVPU_HW_40XX, "intel/vpu/vpu_40xx_v0.0.bin" },
+	{ IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v1.bin" },
+	{ IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v0.0.bin" },
+	{ IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v1.bin" },
+	{ IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v0.0.bin" },
+	{ IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v1.bin" },
+	{ IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v0.0.bin" },
 };
 
+/* Production fw_names from the table above */
+MODULE_FIRMWARE("intel/vpu/vpu_37xx_v1.bin");
+MODULE_FIRMWARE("intel/vpu/vpu_40xx_v1.bin");
+MODULE_FIRMWARE("intel/vpu/vpu_50xx_v1.bin");
+
 static int ivpu_fw_request(struct ivpu_device *vdev)
 {
 	int ret = -ENOENT;
@@ -68,7 +81,7 @@ static int ivpu_fw_request(struct ivpu_device *vdev)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fw_names); i++) {
-		if (fw_names[i].gen != ivpu_hw_gen(vdev))
+		if (fw_names[i].gen != ivpu_hw_ip_gen(vdev))
 			continue;
 
 		ret = firmware_request_nowarn(&vdev->fw->file, fw_names[i].name, vdev->drm.dev);
@@ -105,6 +118,39 @@ ivpu_fw_check_api(struct ivpu_device *vdev, const struct vpu_firmware_header *fw
 	return 0;
 }
 
+static bool
+ivpu_fw_check_api_ver_lt(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr,
+			 const char *str, int index, u16 major, u16 minor)
+{
+	u16 fw_major = (u16)(fw_hdr->api_version[index] >> 16);
+	u16 fw_minor = (u16)(fw_hdr->api_version[index]);
+
+	if (fw_major < major || (fw_major == major && fw_minor < minor))
+		return true;
+
+	return false;
+}
+
+static bool is_within_range(u64 addr, size_t size, u64 range_start, size_t range_size)
+{
+	if (addr < range_start || addr + size > range_start + range_size)
+		return false;
+
+	return true;
+}
+
+static u32
+ivpu_fw_sched_mode_select(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr)
+{
+	if (ivpu_sched_mode != IVPU_SCHED_MODE_AUTO)
+		return ivpu_sched_mode;
+
+	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, JSM, 3, 24))
+		return VPU_SCHEDULING_MODE_OS;
+
+	return VPU_SCHEDULING_MODE_HW;
+}
+
 static int ivpu_fw_parse(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
@@ -161,12 +207,14 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	ivpu_dbg(vdev, FW_BOOT, "Header version: 0x%x, format 0x%x\n",
 		 fw_hdr->header_version, fw_hdr->image_format);
 
-	ivpu_info(vdev, "Firmware: %s, version: %s", fw->name,
-		  (const char *)fw_hdr + VPU_FW_HEADER_SIZE);
+	if (!scnprintf(fw->version, sizeof(fw->version), "%s", fw->file->data + VPU_FW_HEADER_SIZE))
+		ivpu_warn(vdev, "Missing firmware version\n");
 
-	if (IVPU_FW_CHECK_API(vdev, fw_hdr, BOOT, 3))
+	ivpu_info(vdev, "Firmware: %s, version: %s\n", fw->name, fw->version);
+
+	if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, BOOT, 3))
 		return -EINVAL;
-	if (IVPU_FW_CHECK_API(vdev, fw_hdr, JSM, 3))
+	if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, JSM, 3))
 		return -EINVAL;
 
 	fw->runtime_addr = runtime_addr;
@@ -178,14 +226,45 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	fw->cold_boot_entry_point = fw_hdr->entry_point;
 	fw->entry_point = fw->cold_boot_entry_point;
 
-	fw->trace_level = min_t(u32, ivpu_log_level, IVPU_FW_LOG_FATAL);
+	fw->trace_level = min_t(u32, ivpu_fw_log_level, IVPU_FW_LOG_FATAL);
 	fw->trace_destination_mask = VPU_TRACE_DESTINATION_VERBOSE_TRACING;
 	fw->trace_hw_component_mask = -1;
 
+	fw->dvfs_mode = 0;
+
+	fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr);
+	ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS");
+
+	if (fw_hdr->preemption_buffer_1_max_size)
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_max_size;
+	else
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
+
+	if (fw_hdr->preemption_buffer_2_max_size)
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_max_size;
+	else
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
+	ivpu_dbg(vdev, FW_BOOT, "Preemption buffer sizes: primary %u, secondary %u\n",
+		 fw->primary_preempt_buf_size, fw->secondary_preempt_buf_size);
+
+	if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address,
+								 fw_hdr->ro_section_size,
+								 fw_hdr->image_load_address,
+								 fw_hdr->image_size)) {
+		ivpu_err(vdev, "Invalid read-only section: start address 0x%llx, size %u\n",
+			 fw_hdr->ro_section_start_address, fw_hdr->ro_section_size);
+		return -EINVAL;
+	}
+
+	fw->read_only_addr = fw_hdr->ro_section_start_address;
+	fw->read_only_size = fw_hdr->ro_section_size;
+
 	ivpu_dbg(vdev, FW_BOOT, "Size: file %lu image %u runtime %u shavenn %u\n",
 		 fw->file->size, fw->image_size, fw->runtime_size, fw->shave_nn_size);
 	ivpu_dbg(vdev, FW_BOOT, "Address: runtime 0x%llx, load 0x%llx, entry point 0x%llx\n",
 		 fw->runtime_addr, image_load_addr, fw->entry_point);
+	ivpu_dbg(vdev, FW_BOOT, "Read-only section: address 0x%llx, size %u\n",
+		 fw->read_only_addr, fw->read_only_size);
 
 	return 0;
 }
@@ -195,6 +274,23 @@ static void ivpu_fw_release(struct ivpu_device *vdev)
 	release_firmware(vdev->fw->file);
 }
 
+/* Initialize workarounds that depend on FW version */
+static void
+ivpu_fw_init_wa(struct ivpu_device *vdev)
+{
+	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
+
+	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
+	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
+		vdev->wa.disable_d0i3_msg = true;
+
+	/* Force enable the feature for testing purposes */
+	if (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_ENABLE)
+		vdev->wa.disable_d0i3_msg = false;
+
+	IVPU_PRINT_WA(disable_d0i3_msg);
+}
+
 static int ivpu_fw_update_global_range(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
@@ -206,13 +302,14 @@ static int ivpu_fw_update_global_range(struct ivpu_device *vdev)
 		return -EINVAL;
 	}
 
-	ivpu_hw_init_range(&vdev->hw->ranges.global, start, size);
+	ivpu_hw_range_init(&vdev->hw->ranges.global, start, size);
 	return 0;
 }
 
 static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
+	struct ivpu_addr_range fw_range;
 	int log_verb_size;
 	int ret;
 
@@ -220,37 +317,48 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 	if (ret)
 		return ret;
 
-	fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, DRM_IVPU_BO_WC);
+	fw_range.start = fw->runtime_addr;
+	fw_range.end = fw->runtime_addr + fw->runtime_size;
+	fw->mem = ivpu_bo_create(vdev, &vdev->gctx, &fw_range, fw->runtime_size,
+				 DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!fw->mem) {
-		ivpu_err(vdev, "Failed to allocate firmware runtime memory\n");
+		ivpu_err(vdev, "Failed to create firmware runtime memory buffer\n");
 		return -ENOMEM;
 	}
 
-	fw->mem_log_crit = ivpu_bo_alloc_internal(vdev, 0, IVPU_FW_CRITICAL_BUFFER_SIZE,
-						  DRM_IVPU_BO_CACHED);
+	ret = ivpu_mmu_context_set_pages_ro(vdev, &vdev->gctx, fw->read_only_addr,
+					    fw->read_only_size);
+	if (ret) {
+		ivpu_err(vdev, "Failed to set firmware image read-only\n");
+		goto err_free_fw_mem;
+	}
+
+	fw->mem_log_crit = ivpu_bo_create_global(vdev, IVPU_FW_CRITICAL_BUFFER_SIZE,
+						 DRM_IVPU_BO_CACHED | DRM_IVPU_BO_MAPPABLE);
 	if (!fw->mem_log_crit) {
-		ivpu_err(vdev, "Failed to allocate critical log buffer\n");
+		ivpu_err(vdev, "Failed to create critical log buffer\n");
 		ret = -ENOMEM;
 		goto err_free_fw_mem;
 	}
 
-	if (ivpu_log_level <= IVPU_FW_LOG_INFO)
+	if (ivpu_fw_log_level <= IVPU_FW_LOG_INFO)
 		log_verb_size = IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE;
 	else
 		log_verb_size = IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE;
 
-	fw->mem_log_verb = ivpu_bo_alloc_internal(vdev, 0, log_verb_size, DRM_IVPU_BO_CACHED);
+	fw->mem_log_verb = ivpu_bo_create_global(vdev, log_verb_size,
+						 DRM_IVPU_BO_CACHED | DRM_IVPU_BO_MAPPABLE);
 	if (!fw->mem_log_verb) {
-		ivpu_err(vdev, "Failed to allocate verbose log buffer\n");
+		ivpu_err(vdev, "Failed to create verbose log buffer\n");
 		ret = -ENOMEM;
 		goto err_free_log_crit;
 	}
 
 	if (fw->shave_nn_size) {
-		fw->mem_shave_nn = ivpu_bo_alloc_internal(vdev, vdev->hw->ranges.shave.start,
-							  fw->shave_nn_size, DRM_IVPU_BO_UNCACHED);
+		fw->mem_shave_nn = ivpu_bo_create(vdev, &vdev->gctx, &vdev->hw->ranges.shave,
+						  fw->shave_nn_size, DRM_IVPU_BO_WC);
 		if (!fw->mem_shave_nn) {
-			ivpu_err(vdev, "Failed to allocate shavenn buffer\n");
+			ivpu_err(vdev, "Failed to create shavenn buffer\n");
 			ret = -ENOMEM;
 			goto err_free_log_verb;
 		}
@@ -259,11 +367,11 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 	return 0;
 
 err_free_log_verb:
-	ivpu_bo_free_internal(fw->mem_log_verb);
+	ivpu_bo_free(fw->mem_log_verb);
 err_free_log_crit:
-	ivpu_bo_free_internal(fw->mem_log_crit);
+	ivpu_bo_free(fw->mem_log_crit);
 err_free_fw_mem:
-	ivpu_bo_free_internal(fw->mem);
+	ivpu_bo_free(fw->mem);
 	return ret;
 }
 
@@ -272,13 +380,13 @@ static void ivpu_fw_mem_fini(struct ivpu_device *vdev)
 	struct ivpu_fw_info *fw = vdev->fw;
 
 	if (fw->mem_shave_nn) {
-		ivpu_bo_free_internal(fw->mem_shave_nn);
+		ivpu_bo_free(fw->mem_shave_nn);
 		fw->mem_shave_nn = NULL;
 	}
 
-	ivpu_bo_free_internal(fw->mem_log_verb);
-	ivpu_bo_free_internal(fw->mem_log_crit);
-	ivpu_bo_free_internal(fw->mem);
+	ivpu_bo_free(fw->mem_log_verb);
+	ivpu_bo_free(fw->mem_log_crit);
+	ivpu_bo_free(fw->mem);
 
 	fw->mem_log_verb = NULL;
 	fw->mem_log_crit = NULL;
@@ -297,6 +405,8 @@ int ivpu_fw_init(struct ivpu_device *vdev)
 	if (ret)
 		goto err_fw_release;
 
+	ivpu_fw_init_wa(vdev);
+
 	ret = ivpu_fw_mem_init(vdev);
 	if (ret)
 		goto err_fw_release;
@@ -422,14 +532,40 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 boot_params->punit_telemetry_sram_size);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.vpu_telemetry_enable = 0x%x\n",
 		 boot_params->vpu_telemetry_enable);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.vpu_scheduling_mode = 0x%x\n",
+		 boot_params->vpu_scheduling_mode);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
+		 boot_params->dvfs_mode);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_delayed_entry = %d\n",
+		 boot_params->d0i3_delayed_entry);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+		 boot_params->d0i3_residency_time_us);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+		 boot_params->d0i3_entry_vpu_ts);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.system_time_us = %llu\n",
+		 boot_params->system_time_us);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = 0x%x\n",
+		 boot_params->power_profile);
 }
 
 void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params)
 {
 	struct ivpu_bo *ipc_mem_rx = vdev->ipc->mem_rx;
 
-	/* In case of warm boot we only have to reset the entrypoint addr */
+	/* In case of warm boot only update variable params */
 	if (!ivpu_fw_is_cold_boot(vdev)) {
+		boot_params->d0i3_residency_time_us =
+			ktime_us_delta(ktime_get_boottime(), vdev->hw->d0i3_entry_host_ts);
+		boot_params->d0i3_entry_vpu_ts = vdev->hw->d0i3_entry_vpu_ts;
+		boot_params->system_time_us = ktime_to_us(ktime_get_real());
+
+		ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+			 boot_params->d0i3_residency_time_us);
+		ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+			 boot_params->d0i3_entry_vpu_ts);
+		ivpu_dbg(vdev, FW_BOOT, "boot_params.system_time_us = %llu\n",
+			 boot_params->system_time_us);
+
 		boot_params->save_restore_ret_address = 0;
 		vdev->pm->is_warmboot = true;
 		wmb(); /* Flush WC buffers after writing save_restore_ret_address */
@@ -440,7 +576,13 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 
 	boot_params->magic = VPU_BOOT_PARAMS_MAGIC;
 	boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number;
-	boot_params->frequency = ivpu_hw_reg_pll_freq_get(vdev);
+
+	/*
+	 * This param is a debug firmware feature.  It switches default clock
+	 * to higher resolution one for fine-grained and more accurate firmware
+	 * task profiling.
+	 */
+	boot_params->perf_clk_frequency = ivpu_hw_profiling_freq_get(vdev);
 
 	/*
 	 * Uncached region of VPU address space, covers IPC buffers, job queues
@@ -456,8 +598,10 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->ipc_payload_area_start = ipc_mem_rx->vpu_addr + ivpu_bo_size(ipc_mem_rx) / 2;
 	boot_params->ipc_payload_area_size = ivpu_bo_size(ipc_mem_rx) / 2;
 
-	boot_params->global_aliased_pio_base = vdev->hw->ranges.user.start;
-	boot_params->global_aliased_pio_size = ivpu_hw_range_size(&vdev->hw->ranges.user);
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		boot_params->global_aliased_pio_base = vdev->hw->ranges.user.start;
+		boot_params->global_aliased_pio_size = ivpu_hw_range_size(&vdev->hw->ranges.user);
+	}
 
 	/* Allow configuration for L2C_PAGE_TABLE with boot param value */
 	boot_params->autoconfig = 1;
@@ -490,10 +634,21 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->verbose_tracing_buff_addr = vdev->fw->mem_log_verb->vpu_addr;
 	boot_params->verbose_tracing_buff_size = ivpu_bo_size(vdev->fw->mem_log_verb);
 
-	boot_params->punit_telemetry_sram_base = ivpu_hw_reg_telemetry_offset_get(vdev);
-	boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
-	boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
-
+	boot_params->punit_telemetry_sram_base = ivpu_hw_telemetry_offset_get(vdev);
+	boot_params->punit_telemetry_sram_size = ivpu_hw_telemetry_size_get(vdev);
+	boot_params->vpu_telemetry_enable = ivpu_hw_telemetry_enable_get(vdev);
+	boot_params->vpu_scheduling_mode = vdev->fw->sched_mode;
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+		boot_params->vpu_focus_present_timer_ms = IVPU_FOCUS_PRESENT_TIMER_MS;
+	boot_params->dvfs_mode = vdev->fw->dvfs_mode;
+	if (!IVPU_WA(disable_d0i3_msg))
+		boot_params->d0i3_delayed_entry = 1;
+	boot_params->d0i3_residency_time_us = 0;
+	boot_params->d0i3_entry_vpu_ts = 0;
+	if (IVPU_WA(disable_d0i2))
+		boot_params->power_profile |= BIT(1);
+
+	boot_params->system_time_us = ktime_to_us(ktime_get_real());
 	wmb(); /* Flush WC buffers after writing bootparams */
 
 	ivpu_fw_boot_params_print(vdev, boot_params);
diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h
index 10ae2847f0ef..7081913fb0dd 100644
--- a/drivers/accel/ivpu/ivpu_fw.h
+++ b/drivers/accel/ivpu/ivpu_fw.h
@@ -1,11 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_FW_H__
 #define __IVPU_FW_H__
 
+#include "vpu_jsm_api.h"
+
+#define FW_VERSION_HEADER_SIZE	SZ_4K
+#define FW_VERSION_STR_SIZE	SZ_256
+
 struct ivpu_device;
 struct ivpu_bo;
 struct vpu_boot_params;
@@ -13,6 +18,7 @@ struct vpu_boot_params;
 struct ivpu_fw_info {
 	const struct firmware *file;
 	const char *name;
+	char version[FW_VERSION_STR_SIZE];
 	struct ivpu_bo *mem;
 	struct ivpu_bo *mem_shave_nn;
 	struct ivpu_bo *mem_log_crit;
@@ -27,12 +33,19 @@ struct ivpu_fw_info {
 	u32 trace_level;
 	u32 trace_destination_mask;
 	u64 trace_hw_component_mask;
+	u32 dvfs_mode;
+	u32 primary_preempt_buf_size;
+	u32 secondary_preempt_buf_size;
+	u64 read_only_addr;
+	u32 read_only_size;
+	u32 sched_mode;
+	u64 last_heartbeat;
 };
 
 int ivpu_fw_init(struct ivpu_device *vdev);
 void ivpu_fw_fini(struct ivpu_device *vdev);
 void ivpu_fw_load(struct ivpu_device *vdev);
-void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *bp);
+void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params);
 
 static inline bool ivpu_fw_is_cold_boot(struct ivpu_device *vdev)
 {
diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c
index f6770f5e82a2..337c906b0210 100644
--- a/drivers/accel/ivpu/ivpu_fw_log.c
+++ b/drivers/accel/ivpu/ivpu_fw_log.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/ctype.h>
@@ -15,19 +15,19 @@
 #include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 
-#define IVPU_FW_LOG_LINE_LENGTH	  256
+#define IVPU_FW_LOG_LINE_LENGTH	256
 
-unsigned int ivpu_log_level = IVPU_FW_LOG_ERROR;
-module_param(ivpu_log_level, uint, 0444);
-MODULE_PARM_DESC(ivpu_log_level,
-		 "VPU firmware default trace level: debug=" __stringify(IVPU_FW_LOG_DEBUG)
+unsigned int ivpu_fw_log_level = IVPU_FW_LOG_ERROR;
+module_param_named(fw_log_level, ivpu_fw_log_level, uint, 0444);
+MODULE_PARM_DESC(fw_log_level,
+		 "NPU firmware default log level: debug=" __stringify(IVPU_FW_LOG_DEBUG)
 		 " info=" __stringify(IVPU_FW_LOG_INFO)
 		 " warn=" __stringify(IVPU_FW_LOG_WARN)
 		 " error=" __stringify(IVPU_FW_LOG_ERROR)
 		 " fatal=" __stringify(IVPU_FW_LOG_FATAL));
 
-static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
-		      struct vpu_tracing_buffer_header **log_header)
+static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
+			  struct vpu_tracing_buffer_header **out_log)
 {
 	struct vpu_tracing_buffer_header *log;
 
@@ -48,7 +48,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
 		return -EINVAL;
 	}
 
-	*log_header = log;
+	*out_log = log;
 	*offset += log->size;
 
 	ivpu_dbg(vdev, FW_BOOT,
@@ -59,7 +59,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
 	return 0;
 }
 
-static void buffer_print(char *buffer, u32 size, struct drm_printer *p)
+static void fw_log_print_lines(char *buffer, u32 size, struct drm_printer *p)
 {
 	char line[IVPU_FW_LOG_LINE_LENGTH];
 	u32 index = 0;
@@ -87,56 +87,89 @@ static void buffer_print(char *buffer, u32 size, struct drm_printer *p)
 	}
 	line[index] = 0;
 	if (index != 0)
-		drm_printf(p, "%s\n", line);
+		drm_printf(p, "%s", line);
 }
 
-static void fw_log_print_buffer(struct ivpu_device *vdev, struct vpu_tracing_buffer_header *log,
-				const char *prefix, bool only_new_msgs, struct drm_printer *p)
+static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const char *prefix,
+				bool only_new_msgs, struct drm_printer *p)
 {
-	char *log_buffer = (void *)log + log->header_size;
-	u32 log_size = log->size - log->header_size;
-	u32 log_start = log->read_index;
-	u32 log_end = log->write_index;
-
-	if (!(log->write_index || log->wrap_count) ||
-	    (log->write_index == log->read_index && only_new_msgs)) {
-		drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name);
-		return;
+	char *log_data = (void *)log + log->header_size;
+	u32 data_size = log->size - log->header_size;
+	u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0;
+	u32 log_end = READ_ONCE(log->write_index);
+
+	if (log->wrap_count == log->read_wrap_count) {
+		if (log_end <= log_start) {
+			drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name);
+			return;
+		}
+	} else if (log->wrap_count == log->read_wrap_count + 1) {
+		if (log_end > log_start)
+			log_start = log_end;
+	} else {
+		log_start = log_end;
 	}
 
 	drm_printf(p, "==== %s \"%s\" log start ====\n", prefix, log->name);
-	if (log->write_index > log->read_index) {
-		buffer_print(log_buffer + log_start, log_end - log_start, p);
+	if (log_end > log_start) {
+		fw_log_print_lines(log_data + log_start, log_end - log_start, p);
 	} else {
-		buffer_print(log_buffer + log_end, log_size - log_end, p);
-		buffer_print(log_buffer, log_end, p);
+		fw_log_print_lines(log_data + log_start, data_size - log_start, p);
+		fw_log_print_lines(log_data, log_end, p);
 	}
-	drm_printf(p, "\x1b[0m");
+	drm_printf(p, "\n\x1b[0m"); /* add new line and clear formatting */
 	drm_printf(p, "==== %s \"%s\" log end   ====\n", prefix, log->name);
 }
 
-void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p)
+static void
+fw_log_print_all_in_bo(struct ivpu_device *vdev, const char *name,
+		       struct ivpu_bo *bo, bool only_new_msgs, struct drm_printer *p)
 {
-	struct vpu_tracing_buffer_header *log_header;
+	struct vpu_tracing_buffer_header *log;
 	u32 next = 0;
 
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0)
-		fw_log_print_buffer(vdev, log_header, "VPU critical", only_new_msgs, p);
+	while (fw_log_from_bo(vdev, bo, &next, &log) == 0)
+		fw_log_print_buffer(log, name, only_new_msgs, p);
+}
+
+void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p)
+{
+	fw_log_print_all_in_bo(vdev, "NPU critical", vdev->fw->mem_log_crit, only_new_msgs, p);
+	fw_log_print_all_in_bo(vdev, "NPU verbose", vdev->fw->mem_log_verb, only_new_msgs, p);
+}
+
+void ivpu_fw_log_mark_read(struct ivpu_device *vdev)
+{
+	struct vpu_tracing_buffer_header *log;
+	u32 next;
+
+	next = 0;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) {
+		log->read_index = READ_ONCE(log->write_index);
+		log->read_wrap_count = READ_ONCE(log->wrap_count);
+	}
 
 	next = 0;
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0)
-		fw_log_print_buffer(vdev, log_header, "VPU verbose", only_new_msgs, p);
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) {
+		log->read_index = READ_ONCE(log->write_index);
+		log->read_wrap_count = READ_ONCE(log->wrap_count);
+	}
 }
 
-void ivpu_fw_log_clear(struct ivpu_device *vdev)
+void ivpu_fw_log_reset(struct ivpu_device *vdev)
 {
-	struct vpu_tracing_buffer_header *log_header;
-	u32 next = 0;
+	struct vpu_tracing_buffer_header *log;
+	u32 next;
 
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0)
-		log_header->read_index = log_header->write_index;
+	next = 0;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) {
+		log->read_index = 0;
+		log->read_wrap_count = 0;
+	}
 
 	next = 0;
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0)
-		log_header->read_index = log_header->write_index;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) {
+		log->read_index = 0;
+		log->read_wrap_count = 0;
+	}
 }
diff --git a/drivers/accel/ivpu/ivpu_fw_log.h b/drivers/accel/ivpu/ivpu_fw_log.h
index 0b2573f6f315..8bb528a73cb7 100644
--- a/drivers/accel/ivpu/ivpu_fw_log.h
+++ b/drivers/accel/ivpu/ivpu_fw_log.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_FW_LOG_H__
@@ -8,8 +8,6 @@
 
 #include <linux/types.h>
 
-#include <drm/drm_print.h>
-
 #include "ivpu_drv.h"
 
 #define IVPU_FW_LOG_DEFAULT 0
@@ -19,20 +17,15 @@
 #define IVPU_FW_LOG_ERROR   4
 #define IVPU_FW_LOG_FATAL   5
 
-extern unsigned int ivpu_log_level;
-
 #define IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE	SZ_1M
 #define IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE	SZ_8M
 #define IVPU_FW_CRITICAL_BUFFER_SIZE		SZ_512K
 
-void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p);
-void ivpu_fw_log_clear(struct ivpu_device *vdev);
+extern unsigned int ivpu_fw_log_level;
 
-static inline void ivpu_fw_log_dump(struct ivpu_device *vdev)
-{
-	struct drm_printer p = drm_info_printer(vdev->drm.dev);
+void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p);
+void ivpu_fw_log_mark_read(struct ivpu_device *vdev);
+void ivpu_fw_log_reset(struct ivpu_device *vdev);
 
-	ivpu_fw_log_print(vdev, false, &p);
-}
 
 #endif /* __IVPU_FW_LOG_H__ */
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index c91852f2edc8..59cfcf3eaded 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -20,215 +20,27 @@
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
 
-MODULE_IMPORT_NS(DMA_BUF);
+MODULE_IMPORT_NS("DMA_BUF");
 
 static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
-static struct lock_class_key prime_bo_lock_class_key;
-
-static int __must_check prime_alloc_pages_locked(struct ivpu_bo *bo)
-{
-	/* Pages are managed by the underlying dma-buf */
-	return 0;
-}
-
-static void prime_free_pages_locked(struct ivpu_bo *bo)
-{
-	/* Pages are managed by the underlying dma-buf */
-}
-
-static int prime_map_pages_locked(struct ivpu_bo *bo)
-{
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct sg_table *sgt;
-
-	sgt = dma_buf_map_attachment_unlocked(bo->base.import_attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR(sgt)) {
-		ivpu_err(vdev, "Failed to map attachment: %ld\n", PTR_ERR(sgt));
-		return PTR_ERR(sgt);
-	}
-
-	bo->sgt = sgt;
-	return 0;
-}
-
-static void prime_unmap_pages_locked(struct ivpu_bo *bo)
-{
-	dma_buf_unmap_attachment_unlocked(bo->base.import_attach, bo->sgt, DMA_BIDIRECTIONAL);
-	bo->sgt = NULL;
-}
-
-static const struct ivpu_bo_ops prime_ops = {
-	.type = IVPU_BO_TYPE_PRIME,
-	.name = "prime",
-	.alloc_pages = prime_alloc_pages_locked,
-	.free_pages = prime_free_pages_locked,
-	.map_pages = prime_map_pages_locked,
-	.unmap_pages = prime_unmap_pages_locked,
-};
-
-static int __must_check shmem_alloc_pages_locked(struct ivpu_bo *bo)
-{
-	int npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct page **pages;
-
-	pages = drm_gem_get_pages(&bo->base);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
-
-	if (bo->flags & DRM_IVPU_BO_WC)
-		set_pages_array_wc(pages, npages);
-	else if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		set_pages_array_uc(pages, npages);
-
-	bo->pages = pages;
-	return 0;
-}
-
-static void shmem_free_pages_locked(struct ivpu_bo *bo)
-{
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		set_pages_array_wb(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	drm_gem_put_pages(&bo->base, bo->pages, true, false);
-	bo->pages = NULL;
-}
-
-static int ivpu_bo_map_pages_locked(struct ivpu_bo *bo)
+static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
 {
-	int npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct sg_table *sgt;
-	int ret;
-
-	sgt = drm_prime_pages_to_sg(&vdev->drm, bo->pages, npages);
-	if (IS_ERR(sgt)) {
-		ivpu_err(vdev, "Failed to allocate sgtable\n");
-		return PTR_ERR(sgt);
-	}
-
-	ret = dma_map_sgtable(vdev->drm.dev, sgt, DMA_BIDIRECTIONAL, 0);
-	if (ret) {
-		ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
-		goto err_free_sgt;
-	}
-
-	bo->sgt = sgt;
-	return 0;
-
-err_free_sgt:
-	kfree(sgt);
-	return ret;
+	ivpu_dbg(vdev, BO,
+		 "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n",
+		 action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx_id,
+		 (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc,
+		 (bool)drm_gem_is_imported(&bo->base.base));
 }
 
-static void ivpu_bo_unmap_pages_locked(struct ivpu_bo *bo)
+static inline int ivpu_bo_lock(struct ivpu_bo *bo)
 {
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-
-	dma_unmap_sgtable(vdev->drm.dev, bo->sgt, DMA_BIDIRECTIONAL, 0);
-	sg_free_table(bo->sgt);
-	kfree(bo->sgt);
-	bo->sgt = NULL;
+	return dma_resv_lock(bo->base.base.resv, NULL);
 }
 
-static const struct ivpu_bo_ops shmem_ops = {
-	.type = IVPU_BO_TYPE_SHMEM,
-	.name = "shmem",
-	.alloc_pages = shmem_alloc_pages_locked,
-	.free_pages = shmem_free_pages_locked,
-	.map_pages = ivpu_bo_map_pages_locked,
-	.unmap_pages = ivpu_bo_unmap_pages_locked,
-};
-
-static int __must_check internal_alloc_pages_locked(struct ivpu_bo *bo)
+static inline void ivpu_bo_unlock(struct ivpu_bo *bo)
 {
-	unsigned int i, npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct page **pages;
-	int ret;
-
-	pages = kvmalloc_array(npages, sizeof(*bo->pages), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
-
-	for (i = 0; i < npages; i++) {
-		pages[i] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
-		if (!pages[i]) {
-			ret = -ENOMEM;
-			goto err_free_pages;
-		}
-		cond_resched();
-	}
-
-	bo->pages = pages;
-	return 0;
-
-err_free_pages:
-	while (i--)
-		put_page(pages[i]);
-	kvfree(pages);
-	return ret;
-}
-
-static void internal_free_pages_locked(struct ivpu_bo *bo)
-{
-	unsigned int i, npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		set_pages_array_wb(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	for (i = 0; i < npages; i++)
-		put_page(bo->pages[i]);
-
-	kvfree(bo->pages);
-	bo->pages = NULL;
-}
-
-static const struct ivpu_bo_ops internal_ops = {
-	.type = IVPU_BO_TYPE_INTERNAL,
-	.name = "internal",
-	.alloc_pages = internal_alloc_pages_locked,
-	.free_pages = internal_free_pages_locked,
-	.map_pages = ivpu_bo_map_pages_locked,
-	.unmap_pages = ivpu_bo_unmap_pages_locked,
-};
-
-static int __must_check ivpu_bo_alloc_and_map_pages_locked(struct ivpu_bo *bo)
-{
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	int ret;
-
-	lockdep_assert_held(&bo->lock);
-	drm_WARN_ON(&vdev->drm, bo->sgt);
-
-	ret = bo->ops->alloc_pages(bo);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate pages for BO: %d", ret);
-		return ret;
-	}
-
-	ret = bo->ops->map_pages(bo);
-	if (ret) {
-		ivpu_err(vdev, "Failed to map pages for BO: %d", ret);
-		goto err_free_pages;
-	}
-	return ret;
-
-err_free_pages:
-	bo->ops->free_pages(bo);
-	return ret;
-}
-
-static void ivpu_bo_unmap_and_free_pages(struct ivpu_bo *bo)
-{
-	mutex_lock(&bo->lock);
-
-	WARN_ON(!bo->sgt);
-	bo->ops->unmap_pages(bo);
-	WARN_ON(bo->sgt);
-	bo->ops->free_pages(bo);
-	WARN_ON(bo->pages);
-
-	mutex_unlock(&bo->lock);
+	dma_resv_unlock(bo->base.base.resv);
 }
 
 /*
@@ -241,25 +53,23 @@ static void ivpu_bo_unmap_and_free_pages(struct ivpu_bo *bo)
 int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
+	struct sg_table *sgt;
 	int ret = 0;
 
-	mutex_lock(&bo->lock);
+	ivpu_dbg_bo(vdev, bo, "pin");
 
-	if (!bo->vpu_addr) {
-		ivpu_err(vdev, "vpu_addr not set for BO ctx_id: %d handle: %d\n",
-			 bo->ctx->id, bo->handle);
-		ret = -EINVAL;
-		goto unlock;
+	sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+	if (IS_ERR(sgt)) {
+		ret = PTR_ERR(sgt);
+		ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
+		return ret;
 	}
 
-	if (!bo->sgt) {
-		ret = ivpu_bo_alloc_and_map_pages_locked(bo);
-		if (ret)
-			goto unlock;
-	}
+	ivpu_bo_lock(bo);
 
 	if (!bo->mmu_mapped) {
-		ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, bo->sgt,
+		drm_WARN_ON(&vdev->drm, !bo->ctx);
+		ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt,
 					       ivpu_bo_is_snooped(bo));
 		if (ret) {
 			ivpu_err(vdev, "Failed to map BO in MMU: %d\n", ret);
@@ -269,7 +79,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 	}
 
 unlock:
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	return ret;
 }
@@ -279,250 +89,229 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 		       const struct ivpu_addr_range *range)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	int ret;
+	int idx, ret;
 
-	if (!range) {
-		if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
-			range = &vdev->hw->ranges.shave;
-		else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
-			range = &vdev->hw->ranges.dma;
-		else
-			range = &vdev->hw->ranges.user;
-	}
+	if (!drm_dev_enter(&vdev->drm, &idx))
+		return -ENODEV;
 
-	mutex_lock(&ctx->lock);
-	ret = ivpu_mmu_context_insert_node_locked(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
+	ivpu_bo_lock(bo);
+
+	ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
 	if (!ret) {
 		bo->ctx = ctx;
 		bo->vpu_addr = bo->mm_node.start;
-		list_add_tail(&bo->ctx_node, &ctx->bo_list);
+	} else {
+		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
 	}
-	mutex_unlock(&ctx->lock);
+
+	ivpu_bo_unlock(bo);
+
+	drm_dev_exit(idx);
 
 	return ret;
 }
 
-static void ivpu_bo_free_vpu_addr(struct ivpu_bo *bo)
+static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct ivpu_mmu_context *ctx = bo->ctx;
 
-	ivpu_dbg(vdev, BO, "remove from ctx: ctx %d vpu_addr 0x%llx allocated %d mmu_mapped %d\n",
-		 ctx->id, bo->vpu_addr, (bool)bo->sgt, bo->mmu_mapped);
-
-	mutex_lock(&bo->lock);
+	lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount));
 
 	if (bo->mmu_mapped) {
-		drm_WARN_ON(&vdev->drm, !bo->sgt);
-		ivpu_mmu_context_unmap_sgt(vdev, ctx, bo->vpu_addr, bo->sgt);
+		drm_WARN_ON(&vdev->drm, !bo->ctx);
+		drm_WARN_ON(&vdev->drm, !bo->vpu_addr);
+		drm_WARN_ON(&vdev->drm, !bo->base.sgt);
+		ivpu_mmu_context_unmap_sgt(vdev, bo->ctx, bo->vpu_addr, bo->base.sgt);
 		bo->mmu_mapped = false;
 	}
 
-	mutex_lock(&ctx->lock);
-	list_del(&bo->ctx_node);
-	bo->vpu_addr = 0;
-	bo->ctx = NULL;
-	ivpu_mmu_context_remove_node_locked(ctx, &bo->mm_node);
-	mutex_unlock(&ctx->lock);
+	if (bo->ctx) {
+		ivpu_mmu_context_remove_node(bo->ctx, &bo->mm_node);
+		bo->ctx = NULL;
+	}
+
+	if (drm_gem_is_imported(&bo->base.base))
+		return;
 
-	mutex_unlock(&bo->lock);
+	if (bo->base.sgt) {
+		dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
+		sg_free_table(bo->base.sgt);
+		kfree(bo->base.sgt);
+		bo->base.sgt = NULL;
+	}
 }
 
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_mmu_context *ctx)
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
-	struct ivpu_bo *bo, *tmp;
+	struct ivpu_bo *bo;
 
-	list_for_each_entry_safe(bo, tmp, &ctx->bo_list, ctx_node)
-		ivpu_bo_free_vpu_addr(bo);
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return;
+
+	mutex_lock(&vdev->bo_list_lock);
+	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
+		ivpu_bo_lock(bo);
+		if (bo->ctx == ctx) {
+			ivpu_dbg_bo(vdev, bo, "unbind");
+			ivpu_bo_unbind_locked(bo);
+		}
+		ivpu_bo_unlock(bo);
+	}
+	mutex_unlock(&vdev->bo_list_lock);
 }
 
-static struct ivpu_bo *
-ivpu_bo_alloc(struct ivpu_device *vdev, struct ivpu_mmu_context *mmu_context,
-	      u64 size, u32 flags, const struct ivpu_bo_ops *ops,
-	      const struct ivpu_addr_range *range, u64 user_ptr)
+struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size)
 {
 	struct ivpu_bo *bo;
-	int ret = 0;
 
-	if (drm_WARN_ON(&vdev->drm, size == 0 || !PAGE_ALIGNED(size)))
-		return ERR_PTR(-EINVAL);
-
-	switch (flags & DRM_IVPU_BO_CACHE_MASK) {
-	case DRM_IVPU_BO_CACHED:
-	case DRM_IVPU_BO_UNCACHED:
-	case DRM_IVPU_BO_WC:
-		break;
-	default:
+	if (size == 0 || !PAGE_ALIGNED(size))
 		return ERR_PTR(-EINVAL);
-	}
 
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_init(&bo->lock);
-	bo->base.funcs = &ivpu_gem_funcs;
-	bo->flags = flags;
-	bo->ops = ops;
-	bo->user_ptr = user_ptr;
+	bo->base.base.funcs = &ivpu_gem_funcs;
+	bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */
 
-	if (ops->type == IVPU_BO_TYPE_SHMEM)
-		ret = drm_gem_object_init(&vdev->drm, &bo->base, size);
-	else
-		drm_gem_private_object_init(&vdev->drm, &bo->base, size);
+	INIT_LIST_HEAD(&bo->bo_list_node);
 
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize drm object\n");
-		goto err_free;
-	}
+	return &bo->base.base;
+}
 
-	if (flags & DRM_IVPU_BO_MAPPABLE) {
-		ret = drm_gem_create_mmap_offset(&bo->base);
-		if (ret) {
-			ivpu_err(vdev, "Failed to allocate mmap offset\n");
-			goto err_release;
-		}
+struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev,
+					     struct dma_buf *dma_buf)
+{
+	struct device *attach_dev = dev->dev;
+	struct dma_buf_attachment *attach;
+	struct sg_table *sgt;
+	struct drm_gem_object *obj;
+	int ret;
+
+	attach = dma_buf_attach(dma_buf, attach_dev);
+	if (IS_ERR(attach))
+		return ERR_CAST(attach);
+
+	get_dma_buf(dma_buf);
+
+	sgt = dma_buf_map_attachment_unlocked(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = PTR_ERR(sgt);
+		goto fail_detach;
 	}
 
-	if (mmu_context) {
-		ret = ivpu_bo_alloc_vpu_addr(bo, mmu_context, range);
-		if (ret) {
-			ivpu_err(vdev, "Failed to add BO to context: %d\n", ret);
-			goto err_release;
-		}
+	obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
+	if (IS_ERR(obj)) {
+		ret = PTR_ERR(obj);
+		goto fail_unmap;
 	}
 
-	return bo;
+	obj->import_attach = attach;
+	obj->resv = dma_buf->resv;
+
+	return obj;
+
+fail_unmap:
+	dma_buf_unmap_attachment_unlocked(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+	dma_buf_put(dma_buf);
 
-err_release:
-	drm_gem_object_release(&bo->base);
-err_free:
-	kfree(bo);
 	return ERR_PTR(ret);
 }
 
-static void ivpu_bo_free(struct drm_gem_object *obj)
+static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, u32 ctx_id)
 {
-	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-
-	if (bo->ctx)
-		ivpu_dbg(vdev, BO, "free: ctx %d vpu_addr 0x%llx allocated %d mmu_mapped %d\n",
-			 bo->ctx->id, bo->vpu_addr, (bool)bo->sgt, bo->mmu_mapped);
-	else
-		ivpu_dbg(vdev, BO, "free: ctx (released) allocated %d mmu_mapped %d\n",
-			 (bool)bo->sgt, bo->mmu_mapped);
-
-	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
+	struct drm_gem_shmem_object *shmem;
+	struct ivpu_bo *bo;
 
-	vunmap(bo->kvaddr);
+	switch (flags & DRM_IVPU_BO_CACHE_MASK) {
+	case DRM_IVPU_BO_CACHED:
+	case DRM_IVPU_BO_WC:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
 
-	if (bo->ctx)
-		ivpu_bo_free_vpu_addr(bo);
+	shmem = drm_gem_shmem_create(&vdev->drm, size);
+	if (IS_ERR(shmem))
+		return ERR_CAST(shmem);
 
-	if (bo->sgt)
-		ivpu_bo_unmap_and_free_pages(bo);
+	bo = to_ivpu_bo(&shmem->base);
+	bo->ctx_id = ctx_id;
+	bo->base.map_wc = flags & DRM_IVPU_BO_WC;
+	bo->flags = flags;
 
-	if (bo->base.import_attach)
-		drm_prime_gem_destroy(&bo->base, bo->sgt);
+	mutex_lock(&vdev->bo_list_lock);
+	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
+	mutex_unlock(&vdev->bo_list_lock);
 
-	drm_gem_object_release(&bo->base);
+	ivpu_dbg_bo(vdev, bo, "alloc");
 
-	mutex_destroy(&bo->lock);
-	kfree(bo);
+	return bo;
 }
 
-static int ivpu_bo_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+static int ivpu_gem_bo_open(struct drm_gem_object *obj, struct drm_file *file)
 {
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
+	struct ivpu_addr_range *range;
 
-	ivpu_dbg(vdev, BO, "mmap: ctx %u handle %u vpu_addr 0x%llx size %zu type %s",
-		 bo->ctx->id, bo->handle, bo->vpu_addr, ivpu_bo_size(bo), bo->ops->name);
-
-	if (obj->import_attach) {
-		/* Drop the reference drm_gem_mmap_obj() acquired.*/
-		drm_gem_object_put(obj);
-		vma->vm_private_data = NULL;
-		return dma_buf_mmap(obj->dma_buf, vma, 0);
+	if (bo->ctx) {
+		ivpu_warn(vdev, "Can't add BO to ctx %u: already in ctx %u\n",
+			  file_priv->ctx.id, bo->ctx->id);
+		return -EALREADY;
 	}
 
-	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND);
-	vma->vm_page_prot = ivpu_bo_pgprot(bo, vm_get_page_prot(vma->vm_flags));
+	if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
+		range = &vdev->hw->ranges.shave;
+	else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
+		range = &vdev->hw->ranges.dma;
+	else
+		range = &vdev->hw->ranges.user;
 
-	return 0;
+	return ivpu_bo_alloc_vpu_addr(bo, &file_priv->ctx, range);
 }
 
-static struct sg_table *ivpu_bo_get_sg_table(struct drm_gem_object *obj)
+static void ivpu_gem_bo_free(struct drm_gem_object *obj)
 {
+	struct ivpu_device *vdev = to_ivpu_device(obj->dev);
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	loff_t npages = obj->size >> PAGE_SHIFT;
-	int ret = 0;
 
-	mutex_lock(&bo->lock);
+	ivpu_dbg_bo(vdev, bo, "free");
 
-	if (!bo->sgt)
-		ret = ivpu_bo_alloc_and_map_pages_locked(bo);
+	mutex_lock(&vdev->bo_list_lock);
+	list_del(&bo->bo_list_node);
+	mutex_unlock(&vdev->bo_list_lock);
 
-	mutex_unlock(&bo->lock);
+	drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) &&
+		    !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
+	drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0);
+	drm_WARN_ON(&vdev->drm, bo->base.vaddr);
 
-	if (ret)
-		return ERR_PTR(ret);
+	ivpu_bo_unbind_locked(bo);
+	drm_WARN_ON(&vdev->drm, bo->mmu_mapped);
+	drm_WARN_ON(&vdev->drm, bo->ctx);
 
-	return drm_prime_pages_to_sg(obj->dev, bo->pages, npages);
+	drm_WARN_ON(obj->dev, refcount_read(&bo->base.pages_use_count) > 1);
+	drm_gem_shmem_free(&bo->base);
 }
 
-static vm_fault_t ivpu_vm_fault(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	struct drm_gem_object *obj = vma->vm_private_data;
-	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	loff_t npages = obj->size >> PAGE_SHIFT;
-	pgoff_t page_offset;
-	struct page *page;
-	vm_fault_t ret;
-	int err;
-
-	mutex_lock(&bo->lock);
-
-	if (!bo->sgt) {
-		err = ivpu_bo_alloc_and_map_pages_locked(bo);
-		if (err) {
-			ret = vmf_error(err);
-			goto unlock;
-		}
-	}
-
-	/* We don't use vmf->pgoff since that has the fake offset */
-	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-	if (page_offset >= npages) {
-		ret = VM_FAULT_SIGBUS;
-	} else {
-		page = bo->pages[page_offset];
-		ret = vmf_insert_pfn(vma, vmf->address, page_to_pfn(page));
-	}
-
-unlock:
-	mutex_unlock(&bo->lock);
-
-	return ret;
-}
-
-static const struct vm_operations_struct ivpu_vm_ops = {
-	.fault = ivpu_vm_fault,
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
 static const struct drm_gem_object_funcs ivpu_gem_funcs = {
-	.free = ivpu_bo_free,
-	.mmap = ivpu_bo_mmap,
-	.vm_ops = &ivpu_vm_ops,
-	.get_sg_table = ivpu_bo_get_sg_table,
+	.free = ivpu_gem_bo_free,
+	.open = ivpu_gem_bo_open,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
+	.vm_ops = &drm_gem_shmem_vm_ops,
 };
 
-int
-ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct ivpu_device *vdev = file_priv->vdev;
@@ -537,122 +326,91 @@ ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (size == 0)
 		return -EINVAL;
 
-	bo = ivpu_bo_alloc(vdev, &file_priv->ctx, size, args->flags, &shmem_ops, NULL, 0);
+	bo = ivpu_bo_alloc(vdev, size, args->flags, file_priv->ctx.id);
 	if (IS_ERR(bo)) {
-		ivpu_err(vdev, "Failed to create BO: %pe (ctx %u size %llu flags 0x%x)",
+		ivpu_err(vdev, "Failed to allocate BO: %pe (ctx %u size %llu flags 0x%x)",
 			 bo, file_priv->ctx.id, args->size, args->flags);
 		return PTR_ERR(bo);
 	}
 
-	ret = drm_gem_handle_create(file, &bo->base, &bo->handle);
-	if (!ret) {
+	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+	if (ret)
+		ivpu_err(vdev, "Failed to create handle for BO: %pe (ctx %u size %llu flags 0x%x)",
+			 bo, file_priv->ctx.id, args->size, args->flags);
+	else
 		args->vpu_addr = bo->vpu_addr;
-		args->handle = bo->handle;
-	}
 
-	drm_gem_object_put(&bo->base);
-
-	ivpu_dbg(vdev, BO, "alloc shmem: ctx %u vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 file_priv->ctx.id, bo->vpu_addr, ivpu_bo_size(bo), bo->flags);
+	drm_gem_object_put(&bo->base.base);
 
 	return ret;
 }
 
 struct ivpu_bo *
-ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags)
+ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+	       struct ivpu_addr_range *range, u64 size, u32 flags)
 {
-	const struct ivpu_addr_range *range;
-	struct ivpu_addr_range fixed_range;
+	struct iosys_map map;
 	struct ivpu_bo *bo;
-	pgprot_t prot;
 	int ret;
 
-	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(vpu_addr));
-	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size));
+	if (drm_WARN_ON(&vdev->drm, !range))
+		return NULL;
 
-	if (vpu_addr) {
-		fixed_range.start = vpu_addr;
-		fixed_range.end = vpu_addr + size;
-		range = &fixed_range;
-	} else {
-		range = &vdev->hw->ranges.global;
-	}
+	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->start));
+	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->end));
+	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size));
 
-	bo = ivpu_bo_alloc(vdev, &vdev->gctx, size, flags, &internal_ops, range, 0);
+	bo = ivpu_bo_alloc(vdev, size, flags, IVPU_GLOBAL_CONTEXT_MMU_SSID);
 	if (IS_ERR(bo)) {
-		ivpu_err(vdev, "Failed to create BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
-			 bo, vpu_addr, size, flags);
+		ivpu_err(vdev, "Failed to allocate BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
+			 bo, range->start, size, flags);
 		return NULL;
 	}
 
-	ret = ivpu_bo_pin(bo);
+	ret = ivpu_bo_alloc_vpu_addr(bo, ctx, range);
 	if (ret)
 		goto err_put;
 
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		drm_clflush_pages(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
+	ret = ivpu_bo_pin(bo);
+	if (ret)
+		goto err_put;
 
-	if (bo->flags & DRM_IVPU_BO_WC)
-		set_pages_array_wc(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-	else if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		set_pages_array_uc(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
+	if (flags & DRM_IVPU_BO_MAPPABLE) {
+		ivpu_bo_lock(bo);
+		ret = drm_gem_shmem_vmap_locked(&bo->base, &map);
+		ivpu_bo_unlock(bo);
 
-	prot = ivpu_bo_pgprot(bo, PAGE_KERNEL);
-	bo->kvaddr = vmap(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT, VM_MAP, prot);
-	if (!bo->kvaddr) {
-		ivpu_err(vdev, "Failed to map BO into kernel virtual memory\n");
-		goto err_put;
+		if (ret)
+			goto err_put;
 	}
 
-	ivpu_dbg(vdev, BO, "alloc internal: ctx 0 vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 bo->vpu_addr, ivpu_bo_size(bo), flags);
-
 	return bo;
 
 err_put:
-	drm_gem_object_put(&bo->base);
+	drm_gem_object_put(&bo->base.base);
 	return NULL;
 }
 
-void ivpu_bo_free_internal(struct ivpu_bo *bo)
+struct ivpu_bo *ivpu_bo_create_global(struct ivpu_device *vdev, u64 size, u32 flags)
 {
-	drm_gem_object_put(&bo->base);
+	return ivpu_bo_create(vdev, &vdev->gctx, &vdev->hw->ranges.global, size, flags);
 }
 
-struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *buf)
+void ivpu_bo_free(struct ivpu_bo *bo)
 {
-	struct ivpu_device *vdev = to_ivpu_device(dev);
-	struct dma_buf_attachment *attach;
-	struct ivpu_bo *bo;
+	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
-	attach = dma_buf_attach(buf, dev->dev);
-	if (IS_ERR(attach))
-		return ERR_CAST(attach);
-
-	get_dma_buf(buf);
-
-	bo = ivpu_bo_alloc(vdev, NULL, buf->size, DRM_IVPU_BO_MAPPABLE, &prime_ops, NULL, 0);
-	if (IS_ERR(bo)) {
-		ivpu_err(vdev, "Failed to import BO: %pe (size %lu)", bo, buf->size);
-		goto err_detach;
+	if (bo->flags & DRM_IVPU_BO_MAPPABLE) {
+		ivpu_bo_lock(bo);
+		drm_gem_shmem_vunmap_locked(&bo->base, &map);
+		ivpu_bo_unlock(bo);
 	}
 
-	lockdep_set_class(&bo->lock, &prime_bo_lock_class_key);
-
-	bo->base.import_attach = attach;
-
-	return &bo->base;
-
-err_detach:
-	dma_buf_detach(buf, attach);
-	dma_buf_put(buf);
-	return ERR_CAST(bo);
+	drm_gem_object_put(&bo->base.base);
 }
 
 int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
-	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct drm_ivpu_bo_info *args = data;
 	struct drm_gem_object *obj;
 	struct ivpu_bo *bo;
@@ -664,22 +422,13 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	bo = to_ivpu_bo(obj);
 
-	mutex_lock(&bo->lock);
-
-	if (!bo->ctx) {
-		ret = ivpu_bo_alloc_vpu_addr(bo, &file_priv->ctx, NULL);
-		if (ret) {
-			ivpu_err(vdev, "Failed to allocate vpu_addr: %d\n", ret);
-			goto unlock;
-		}
-	}
-
+	ivpu_bo_lock(bo);
 	args->flags = bo->flags;
 	args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node);
 	args->vpu_addr = bo->vpu_addr;
 	args->size = obj->size;
-unlock:
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
+
 	drm_gem_object_put(obj);
 	return ret;
 }
@@ -693,6 +442,9 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	timeout = drm_timeout_abs_to_jiffies(args->timeout_ns);
 
+	/* Add 1 jiffy to ensure the wait function never times out before intended timeout_ns */
+	timeout += 1;
+
 	obj = drm_gem_object_lookup(file, args->handle);
 	if (!obj)
 		return -EINVAL;
@@ -712,43 +464,38 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 {
-	unsigned long dma_refcount = 0;
+	ivpu_bo_lock(bo);
+
+	drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u",
+		   bo, bo->ctx_id, bo->vpu_addr, bo->base.base.size,
+		   bo->flags, kref_read(&bo->base.base.refcount));
+
+	if (bo->base.pages)
+		drm_printf(p, " has_pages");
 
-	if (bo->base.dma_buf && bo->base.dma_buf->file)
-		dma_refcount = atomic_long_read(&bo->base.dma_buf->file->f_count);
+	if (bo->mmu_mapped)
+		drm_printf(p, " mmu_mapped");
 
-	drm_printf(p, "%5u %6d %16llx %10lu %10u %12lu %14s\n",
-		   bo->ctx->id, bo->handle, bo->vpu_addr, ivpu_bo_size(bo),
-		   kref_read(&bo->base.refcount), dma_refcount, bo->ops->name);
+	if (drm_gem_is_imported(&bo->base.base))
+		drm_printf(p, " imported");
+
+	drm_printf(p, "\n");
+
+	ivpu_bo_unlock(bo);
 }
 
 void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
 {
 	struct ivpu_device *vdev = to_ivpu_device(dev);
-	struct ivpu_file_priv *file_priv;
-	unsigned long ctx_id;
 	struct ivpu_bo *bo;
 
-	drm_printf(p, "%5s %6s %16s %10s %10s %12s %14s\n",
-		   "ctx", "handle", "vpu_addr", "size", "refcount", "dma_refcount", "type");
+	drm_printf(p, "%-9s %-3s %-14s %-10s %-10s %-4s %s\n",
+		   "bo", "ctx", "vpu_addr", "size", "flags", "refs", "attribs");
 
-	mutex_lock(&vdev->gctx.lock);
-	list_for_each_entry(bo, &vdev->gctx.bo_list, ctx_node)
+	mutex_lock(&vdev->bo_list_lock);
+	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
 		ivpu_bo_print_info(bo, p);
-	mutex_unlock(&vdev->gctx.lock);
-
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		file_priv = ivpu_file_priv_get_by_ctx_id(vdev, ctx_id);
-		if (!file_priv)
-			continue;
-
-		mutex_lock(&file_priv->ctx.lock);
-		list_for_each_entry(bo, &file_priv->ctx.bo_list, ctx_node)
-			ivpu_bo_print_info(bo, p);
-		mutex_unlock(&file_priv->ctx.lock);
-
-		ivpu_file_priv_put(&file_priv);
-	}
+	mutex_unlock(&vdev->bo_list_lock);
 }
 
 void ivpu_bo_list_print(struct drm_device *dev)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index a0b4d4a32b3b..aa8ff14f7aae 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -6,84 +6,54 @@
 #define __IVPU_GEM_H__
 
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_mm.h>
 
-struct dma_buf;
-struct ivpu_bo_ops;
 struct ivpu_file_priv;
 
 struct ivpu_bo {
-	struct drm_gem_object base;
-	const struct ivpu_bo_ops *ops;
-
+	struct drm_gem_shmem_object base;
 	struct ivpu_mmu_context *ctx;
-	struct list_head ctx_node;
+	struct list_head bo_list_node;
 	struct drm_mm_node mm_node;
 
-	struct mutex lock; /* Protects: pages, sgt, mmu_mapped */
-	struct sg_table *sgt;
-	struct page **pages;
-	bool mmu_mapped;
-
-	void *kvaddr;
 	u64 vpu_addr;
-	u32 handle;
 	u32 flags;
-	uintptr_t user_ptr;
-	u32 job_status;
-};
-
-enum ivpu_bo_type {
-	IVPU_BO_TYPE_SHMEM = 1,
-	IVPU_BO_TYPE_INTERNAL,
-	IVPU_BO_TYPE_PRIME,
-};
-
-struct ivpu_bo_ops {
-	enum ivpu_bo_type type;
-	const char *name;
-	int (*alloc_pages)(struct ivpu_bo *bo);
-	void (*free_pages)(struct ivpu_bo *bo);
-	int (*map_pages)(struct ivpu_bo *bo);
-	void (*unmap_pages)(struct ivpu_bo *bo);
+	u32 job_status; /* Valid only for command buffer */
+	u32 ctx_id;
+	bool mmu_mapped;
 };
 
 int ivpu_bo_pin(struct ivpu_bo *bo);
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_mmu_context *ctx);
-void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p);
-void ivpu_bo_list_print(struct drm_device *dev);
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 
-struct ivpu_bo *
-ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags);
-void ivpu_bo_free_internal(struct ivpu_bo *bo);
+struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size);
 struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf);
-void ivpu_bo_unmap_sgt_and_remove_from_context(struct ivpu_bo *bo);
+struct ivpu_bo *ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+			       struct ivpu_addr_range *range, u64 size, u32 flags);
+struct ivpu_bo *ivpu_bo_create_global(struct ivpu_device *vdev, u64 size, u32 flags);
+void ivpu_bo_free(struct ivpu_bo *bo);
 
 int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 
+void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p);
+void ivpu_bo_list_print(struct drm_device *dev);
+
 static inline struct ivpu_bo *to_ivpu_bo(struct drm_gem_object *obj)
 {
-	return container_of(obj, struct ivpu_bo, base);
+	return container_of(obj, struct ivpu_bo, base.base);
 }
 
 static inline void *ivpu_bo_vaddr(struct ivpu_bo *bo)
 {
-	return bo->kvaddr;
+	return bo->base.vaddr;
 }
 
 static inline size_t ivpu_bo_size(struct ivpu_bo *bo)
 {
-	return bo->base.size;
-}
-
-static inline struct page *ivpu_bo_get_page(struct ivpu_bo *bo, u64 offset)
-{
-	if (offset > ivpu_bo_size(bo) || !bo->pages)
-		return NULL;
-
-	return bo->pages[offset / PAGE_SIZE];
+	return bo->base.base.size;
 }
 
 static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo)
@@ -91,25 +61,17 @@ static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo)
 	return bo->flags & DRM_IVPU_BO_CACHE_MASK;
 }
 
-static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
+static inline struct ivpu_device *ivpu_bo_to_vdev(struct ivpu_bo *bo)
 {
-	return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
+	return to_ivpu_device(bo->base.base.dev);
 }
 
-static inline pgprot_t ivpu_bo_pgprot(struct ivpu_bo *bo, pgprot_t prot)
+static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
 {
-	if (bo->flags & DRM_IVPU_BO_WC)
-		return pgprot_writecombine(prot);
-
-	if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		return pgprot_noncached(prot);
-
-	return prot;
-}
+	if (ivpu_is_force_snoop_enabled(ivpu_bo_to_vdev(bo)))
+		return true;
 
-static inline struct ivpu_device *ivpu_bo_to_vdev(struct ivpu_bo *bo)
-{
-	return to_ivpu_device(bo->base.dev);
+	return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
 }
 
 static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u32 vpu_addr)
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
new file mode 100644
index 000000000000..08dcc31b56f4
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 - 2024 Intel Corporation
+ */
+
+#include "ivpu_drv.h"
+#include "ivpu_hw.h"
+#include "ivpu_hw_btrs.h"
+#include "ivpu_hw_ip.h"
+
+#include <linux/dmi.h>
+#include <linux/fault-inject.h>
+#include <linux/pm_runtime.h>
+
+#ifdef CONFIG_FAULT_INJECTION
+DECLARE_FAULT_ATTR(ivpu_hw_failure);
+
+static char *ivpu_fail_hw;
+module_param_named_unsafe(fail_hw, ivpu_fail_hw, charp, 0444);
+MODULE_PARM_DESC(fail_hw, "<interval>,<probability>,<space>,<times>");
+#endif
+
+static char *platform_to_str(u32 platform)
+{
+	switch (platform) {
+	case IVPU_PLATFORM_SILICON:
+		return "SILICON";
+	case IVPU_PLATFORM_SIMICS:
+		return "SIMICS";
+	case IVPU_PLATFORM_FPGA:
+		return "FPGA";
+	case IVPU_PLATFORM_HSLE:
+		return "HSLE";
+	default:
+		return "Invalid platform";
+	}
+}
+
+static void platform_init(struct ivpu_device *vdev)
+{
+	int platform = ivpu_hw_btrs_platform_read(vdev);
+
+	ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n", platform_to_str(platform), platform);
+
+	switch (platform) {
+	case IVPU_PLATFORM_SILICON:
+	case IVPU_PLATFORM_SIMICS:
+	case IVPU_PLATFORM_FPGA:
+	case IVPU_PLATFORM_HSLE:
+		vdev->platform = platform;
+		break;
+
+	default:
+		ivpu_err(vdev, "Invalid platform type: %d\n", platform);
+		break;
+	}
+}
+
+static void wa_init(struct ivpu_device *vdev)
+{
+	vdev->wa.punit_disabled = false;
+	vdev->wa.clear_runtime_mem = false;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		vdev->wa.interrupt_clear_with_0 = ivpu_hw_btrs_irqs_clear_with_0_mtl(vdev);
+
+	if (ivpu_device_id(vdev) == PCI_DEVICE_ID_LNL &&
+	    ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0)
+		vdev->wa.disable_clock_relinquish = true;
+
+	if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_ENABLE)
+		vdev->wa.disable_clock_relinquish = false;
+
+	if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_DISABLE)
+		vdev->wa.disable_clock_relinquish = true;
+
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		vdev->wa.wp0_during_power_up = true;
+
+	if (ivpu_test_mode & IVPU_TEST_MODE_D0I2_DISABLE)
+		vdev->wa.disable_d0i2 = true;
+
+	IVPU_PRINT_WA(punit_disabled);
+	IVPU_PRINT_WA(clear_runtime_mem);
+	IVPU_PRINT_WA(interrupt_clear_with_0);
+	IVPU_PRINT_WA(disable_clock_relinquish);
+	IVPU_PRINT_WA(wp0_during_power_up);
+	IVPU_PRINT_WA(disable_d0i2);
+}
+
+static void timeouts_init(struct ivpu_device *vdev)
+{
+	if (ivpu_test_mode & IVPU_TEST_MODE_DISABLE_TIMEOUTS) {
+		vdev->timeout.boot = -1;
+		vdev->timeout.jsm = -1;
+		vdev->timeout.tdr = -1;
+		vdev->timeout.inference = -1;
+		vdev->timeout.autosuspend = -1;
+		vdev->timeout.d0i3_entry_msg = -1;
+	} else if (ivpu_is_fpga(vdev)) {
+		vdev->timeout.boot = 50;
+		vdev->timeout.jsm = 15000;
+		vdev->timeout.tdr = 30000;
+		vdev->timeout.inference = 900000;
+		vdev->timeout.autosuspend = -1;
+		vdev->timeout.d0i3_entry_msg = 500;
+		vdev->timeout.state_dump_msg = 10000;
+	} else if (ivpu_is_simics(vdev)) {
+		vdev->timeout.boot = 50;
+		vdev->timeout.jsm = 500;
+		vdev->timeout.tdr = 10000;
+		vdev->timeout.inference = 300000;
+		vdev->timeout.autosuspend = 100;
+		vdev->timeout.d0i3_entry_msg = 100;
+		vdev->timeout.state_dump_msg = 10;
+	} else {
+		vdev->timeout.boot = 1000;
+		vdev->timeout.jsm = 500;
+		vdev->timeout.tdr = 2000;
+		vdev->timeout.inference = 60000;
+		if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+			vdev->timeout.autosuspend = 10;
+		else
+			vdev->timeout.autosuspend = 100;
+		vdev->timeout.d0i3_entry_msg = 5;
+		vdev->timeout.state_dump_msg = 100;
+	}
+}
+
+static void priority_bands_init(struct ivpu_device *vdev)
+{
+	/* Idle */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 0;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 160000;
+	/* Normal */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 300000;
+	/* Focus */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 200000;
+	/* Realtime */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 0;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 200000;
+}
+
+static void memory_ranges_init(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		ivpu_hw_range_init(&vdev->hw->ranges.global, 0x80000000, SZ_512M);
+		ivpu_hw_range_init(&vdev->hw->ranges.user,   0x88000000, 511 * SZ_1M);
+		ivpu_hw_range_init(&vdev->hw->ranges.shave, 0x180000000, SZ_2G);
+		ivpu_hw_range_init(&vdev->hw->ranges.dma,   0x200000000, SZ_128G);
+	} else {
+		ivpu_hw_range_init(&vdev->hw->ranges.global, 0x80000000, SZ_512M);
+		ivpu_hw_range_init(&vdev->hw->ranges.shave,  0x80000000, SZ_2G);
+		ivpu_hw_range_init(&vdev->hw->ranges.user,  0x100000000, SZ_256G);
+		vdev->hw->ranges.dma = vdev->hw->ranges.user;
+	}
+}
+
+static int wp_enable(struct ivpu_device *vdev)
+{
+	return ivpu_hw_btrs_wp_drive(vdev, true);
+}
+
+static int wp_disable(struct ivpu_device *vdev)
+{
+	return ivpu_hw_btrs_wp_drive(vdev, false);
+}
+
+int ivpu_hw_power_up(struct ivpu_device *vdev)
+{
+	int ret;
+
+	if (IVPU_WA(wp0_during_power_up)) {
+		/* WP requests may fail when powering down, so issue WP 0 here */
+		ret = wp_disable(vdev);
+		if (ret)
+			ivpu_warn(vdev, "Failed to disable workpoint: %d\n", ret);
+	}
+
+	ret = ivpu_hw_btrs_d0i3_disable(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
+
+	ret = wp_enable(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to enable workpoint: %d\n", ret);
+		return ret;
+	}
+
+	if (ivpu_hw_btrs_gen(vdev) >= IVPU_HW_BTRS_LNL) {
+		if (IVPU_WA(disable_clock_relinquish))
+			ivpu_hw_btrs_clock_relinquish_disable_lnl(vdev);
+		ivpu_hw_btrs_profiling_freq_reg_set_lnl(vdev);
+		ivpu_hw_btrs_ats_print_lnl(vdev);
+	}
+
+	ret = ivpu_hw_ip_host_ss_configure(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to configure host SS: %d\n", ret);
+		return ret;
+	}
+
+	ivpu_hw_ip_idle_gen_disable(vdev);
+
+	ret = ivpu_hw_btrs_wait_for_clock_res_own_ack(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for clock resource own ACK\n");
+		return ret;
+	}
+
+	ret = ivpu_hw_ip_pwr_domain_enable(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to enable power domain: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_hw_ip_host_ss_axi_enable(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to enable AXI: %d\n", ret);
+		return ret;
+	}
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_LNL)
+		ivpu_hw_btrs_set_port_arbitration_weights_lnl(vdev);
+
+	ret = ivpu_hw_ip_top_noc_enable(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to enable TOP NOC: %d\n", ret);
+
+	return ret;
+}
+
+static void save_d0i3_entry_timestamp(struct ivpu_device *vdev)
+{
+	vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
+	vdev->hw->d0i3_entry_vpu_ts = ivpu_hw_ip_read_perf_timer_counter(vdev);
+}
+
+int ivpu_hw_reset(struct ivpu_device *vdev)
+{
+	int ret = 0;
+
+	if (ivpu_hw_btrs_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU IP\n");
+		ret = -EIO;
+	}
+
+	if (wp_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable workpoint\n");
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
+int ivpu_hw_power_down(struct ivpu_device *vdev)
+{
+	int ret = 0;
+
+	save_d0i3_entry_timestamp(vdev);
+
+	if (!ivpu_hw_is_idle(vdev))
+		ivpu_warn(vdev, "NPU not idle during power down\n");
+
+	if (ivpu_hw_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU\n");
+		ret = -EIO;
+	}
+
+	if (ivpu_hw_btrs_d0i3_enable(vdev)) {
+		ivpu_err(vdev, "Failed to enter D0I3\n");
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
+int ivpu_hw_init(struct ivpu_device *vdev)
+{
+	ivpu_hw_btrs_info_init(vdev);
+	ivpu_hw_btrs_freq_ratios_init(vdev);
+	priority_bands_init(vdev);
+	memory_ranges_init(vdev);
+	platform_init(vdev);
+	wa_init(vdev);
+	timeouts_init(vdev);
+	atomic_set(&vdev->hw->firewall_irq_counter, 0);
+
+#ifdef CONFIG_FAULT_INJECTION
+	if (ivpu_fail_hw)
+		setup_fault_attr(&ivpu_hw_failure, ivpu_fail_hw);
+#endif
+
+	return 0;
+}
+
+int ivpu_hw_boot_fw(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ivpu_hw_ip_snoop_disable(vdev);
+	ivpu_hw_ip_tbu_mmu_enable(vdev);
+	ret = ivpu_hw_ip_soc_cpu_boot(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to boot SOC CPU: %d\n", ret);
+
+	return ret;
+}
+
+void ivpu_hw_profiling_freq_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		vdev->hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
+		return;
+	}
+
+	if (enable)
+		vdev->hw->pll.profiling_freq = PLL_PROFILING_FREQ_HIGH;
+	else
+		vdev->hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
+}
+
+void ivpu_irq_handlers_init(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		vdev->hw->irq.ip_irq_handler = ivpu_hw_ip_irq_handler_37xx;
+	else
+		vdev->hw->irq.ip_irq_handler = ivpu_hw_ip_irq_handler_40xx;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		vdev->hw->irq.btrs_irq_handler = ivpu_hw_btrs_irq_handler_mtl;
+	else
+		vdev->hw->irq.btrs_irq_handler = ivpu_hw_btrs_irq_handler_lnl;
+}
+
+void ivpu_hw_irq_enable(struct ivpu_device *vdev)
+{
+	ivpu_hw_ip_irq_enable(vdev);
+	ivpu_hw_btrs_irq_enable(vdev);
+}
+
+void ivpu_hw_irq_disable(struct ivpu_device *vdev)
+{
+	ivpu_hw_btrs_irq_disable(vdev);
+	ivpu_hw_ip_irq_disable(vdev);
+}
+
+irqreturn_t ivpu_hw_irq_handler(int irq, void *ptr)
+{
+	struct ivpu_device *vdev = ptr;
+	bool ip_handled, btrs_handled;
+
+	ivpu_hw_btrs_global_int_disable(vdev);
+
+	btrs_handled = ivpu_hw_btrs_irq_handler(vdev, irq);
+	if (!ivpu_hw_is_idle((vdev)) || !btrs_handled)
+		ip_handled = ivpu_hw_ip_irq_handler(vdev, irq);
+	else
+		ip_handled = false;
+
+	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
+	ivpu_hw_btrs_global_int_enable(vdev);
+
+	if (!ip_handled && !btrs_handled)
+		return IRQ_NONE;
+
+	pm_runtime_mark_last_busy(vdev->drm.dev);
+	return IRQ_HANDLED;
+}
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index 1079e06255ba..d79668fe1609 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -1,35 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_H__
 #define __IVPU_HW_H__
 
 #include "ivpu_drv.h"
-
-struct ivpu_hw_ops {
-	int (*info_init)(struct ivpu_device *vdev);
-	int (*power_up)(struct ivpu_device *vdev);
-	int (*boot_fw)(struct ivpu_device *vdev);
-	int (*power_down)(struct ivpu_device *vdev);
-	int (*reset)(struct ivpu_device *vdev);
-	bool (*is_idle)(struct ivpu_device *vdev);
-	void (*wdt_disable)(struct ivpu_device *vdev);
-	void (*diagnose_failure)(struct ivpu_device *vdev);
-	u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
-	u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev);
-	u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev);
-	u32 (*reg_telemetry_enable_get)(struct ivpu_device *vdev);
-	void (*reg_db_set)(struct ivpu_device *vdev, u32 db_id);
-	u32 (*reg_ipc_rx_addr_get)(struct ivpu_device *vdev);
-	u32 (*reg_ipc_rx_count_get)(struct ivpu_device *vdev);
-	void (*reg_ipc_tx_set)(struct ivpu_device *vdev, u32 vpu_addr);
-	void (*irq_clear)(struct ivpu_device *vdev);
-	void (*irq_enable)(struct ivpu_device *vdev);
-	void (*irq_disable)(struct ivpu_device *vdev);
-	irqreturn_t (*irq_handler)(int irq, void *ptr);
-};
+#include "ivpu_hw_btrs.h"
+#include "ivpu_hw_ip.h"
 
 struct ivpu_addr_range {
 	resource_size_t start;
@@ -37,7 +16,10 @@ struct ivpu_addr_range {
 };
 
 struct ivpu_hw_info {
-	const struct ivpu_hw_ops *ops;
+	struct {
+		bool (*btrs_irq_handler)(struct ivpu_device *vdev, int irq);
+		bool (*ip_irq_handler)(struct ivpu_device *vdev, int irq);
+	} irq;
 	struct {
 		struct ivpu_addr_range global;
 		struct ivpu_addr_range user;
@@ -54,126 +36,121 @@ struct ivpu_hw_info {
 		u8 pn_ratio;
 		u32 profiling_freq;
 	} pll;
+	struct {
+		u32 grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+	} hws;
 	u32 tile_fuse;
 	u32 sku;
 	u16 config;
 	int dma_bits;
+	ktime_t d0i3_entry_host_ts;
+	u64 d0i3_entry_vpu_ts;
+	atomic_t firewall_irq_counter;
 };
 
-extern const struct ivpu_hw_ops ivpu_hw_37xx_ops;
-extern const struct ivpu_hw_ops ivpu_hw_40xx_ops;
+int ivpu_hw_init(struct ivpu_device *vdev);
+int ivpu_hw_power_up(struct ivpu_device *vdev);
+int ivpu_hw_power_down(struct ivpu_device *vdev);
+int ivpu_hw_reset(struct ivpu_device *vdev);
+int ivpu_hw_boot_fw(struct ivpu_device *vdev);
+void ivpu_hw_profiling_freq_drive(struct ivpu_device *vdev, bool enable);
+void ivpu_irq_handlers_init(struct ivpu_device *vdev);
+void ivpu_hw_irq_enable(struct ivpu_device *vdev);
+void ivpu_hw_irq_disable(struct ivpu_device *vdev);
+irqreturn_t ivpu_hw_irq_handler(int irq, void *ptr);
 
-static inline int ivpu_hw_info_init(struct ivpu_device *vdev)
-{
-	return vdev->hw->ops->info_init(vdev);
-};
-
-static inline int ivpu_hw_power_up(struct ivpu_device *vdev)
-{
-	ivpu_dbg(vdev, PM, "HW power up\n");
-
-	return vdev->hw->ops->power_up(vdev);
-};
-
-static inline int ivpu_hw_boot_fw(struct ivpu_device *vdev)
-{
-	return vdev->hw->ops->boot_fw(vdev);
-};
-
-static inline bool ivpu_hw_is_idle(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_btrs_irq_handler(struct ivpu_device *vdev, int irq)
 {
-	return vdev->hw->ops->is_idle(vdev);
-};
+	return vdev->hw->irq.btrs_irq_handler(vdev, irq);
+}
 
-static inline int ivpu_hw_power_down(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_ip_irq_handler(struct ivpu_device *vdev, int irq)
 {
-	ivpu_dbg(vdev, PM, "HW power down\n");
-
-	return vdev->hw->ops->power_down(vdev);
-};
+	return vdev->hw->irq.ip_irq_handler(vdev, irq);
+}
 
-static inline int ivpu_hw_reset(struct ivpu_device *vdev)
+static inline void ivpu_hw_range_init(struct ivpu_addr_range *range, u64 start, u64 size)
 {
-	ivpu_dbg(vdev, PM, "HW reset\n");
-
-	return vdev->hw->ops->reset(vdev);
-};
+	range->start = start;
+	range->end = start + size;
+}
 
-static inline void ivpu_hw_wdt_disable(struct ivpu_device *vdev)
+static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
 {
-	vdev->hw->ops->wdt_disable(vdev);
-};
+	return range->end - range->start;
+}
 
-/* Register indirect accesses */
-static inline u32 ivpu_hw_reg_pll_freq_get(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_pll_freq_get(vdev);
-};
+	return ivpu_hw_btrs_dpu_max_freq_get(vdev);
+}
 
-static inline u32 ivpu_hw_reg_telemetry_offset_get(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_dpu_freq_get(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_telemetry_offset_get(vdev);
-};
+	return ivpu_hw_btrs_dpu_freq_get(vdev);
+}
 
-static inline u32 ivpu_hw_reg_telemetry_size_get(struct ivpu_device *vdev)
+static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_telemetry_size_get(vdev);
-};
+	ivpu_hw_ip_irq_clear(vdev);
+}
 
-static inline u32 ivpu_hw_reg_telemetry_enable_get(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_telemetry_enable_get(vdev);
-};
+	return vdev->hw->pll.profiling_freq;
+}
 
-static inline void ivpu_hw_reg_db_set(struct ivpu_device *vdev, u32 db_id)
+static inline void ivpu_hw_diagnose_failure(struct ivpu_device *vdev)
 {
-	vdev->hw->ops->reg_db_set(vdev, db_id);
-};
+	ivpu_hw_ip_diagnose_failure(vdev);
+	ivpu_hw_btrs_diagnose_failure(vdev);
+}
 
-static inline u32 ivpu_hw_reg_ipc_rx_addr_get(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_telemetry_offset_get(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_ipc_rx_addr_get(vdev);
-};
+	return ivpu_hw_btrs_telemetry_offset_get(vdev);
+}
 
-static inline u32 ivpu_hw_reg_ipc_rx_count_get(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_telemetry_size_get(struct ivpu_device *vdev)
 {
-	return vdev->hw->ops->reg_ipc_rx_count_get(vdev);
-};
+	return ivpu_hw_btrs_telemetry_size_get(vdev);
+}
 
-static inline void ivpu_hw_reg_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
+static inline u32 ivpu_hw_telemetry_enable_get(struct ivpu_device *vdev)
 {
-	vdev->hw->ops->reg_ipc_tx_set(vdev, vpu_addr);
-};
+	return ivpu_hw_btrs_telemetry_enable_get(vdev);
+}
 
-static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
+static inline bool ivpu_hw_is_idle(struct ivpu_device *vdev)
 {
-	vdev->hw->ops->irq_clear(vdev);
-};
+	return ivpu_hw_btrs_is_idle(vdev);
+}
 
-static inline void ivpu_hw_irq_enable(struct ivpu_device *vdev)
+static inline int ivpu_hw_wait_for_idle(struct ivpu_device *vdev)
 {
-	vdev->hw->ops->irq_enable(vdev);
-};
+	return ivpu_hw_btrs_wait_for_idle(vdev);
+}
 
-static inline void ivpu_hw_irq_disable(struct ivpu_device *vdev)
+static inline void ivpu_hw_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
 {
-	vdev->hw->ops->irq_disable(vdev);
-};
+	ivpu_hw_ip_ipc_tx_set(vdev, vpu_addr);
+}
 
-static inline void ivpu_hw_init_range(struct ivpu_addr_range *range, u64 start, u64 size)
+static inline void ivpu_hw_db_set(struct ivpu_device *vdev, u32 db_id)
 {
-	range->start = start;
-	range->end = start + size;
+	ivpu_hw_ip_db_set(vdev, db_id);
 }
 
-static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
+static inline u32 ivpu_hw_ipc_rx_addr_get(struct ivpu_device *vdev)
 {
-	return range->end - range->start;
+	return ivpu_hw_ip_ipc_rx_addr_get(vdev);
 }
 
-static inline void ivpu_hw_diagnose_failure(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_ipc_rx_count_get(struct ivpu_device *vdev)
 {
-	vdev->hw->ops->diagnose_failure(vdev);
+	return ivpu_hw_ip_ipc_rx_count_get(vdev);
 }
 
 #endif /* __IVPU_HW_H__ */
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
deleted file mode 100644
index 5c0246b9e522..000000000000
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ /dev/null
@@ -1,1013 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2020-2023 Intel Corporation
- */
-
-#include "ivpu_drv.h"
-#include "ivpu_fw.h"
-#include "ivpu_hw_37xx_reg.h"
-#include "ivpu_hw_reg_io.h"
-#include "ivpu_hw.h"
-#include "ivpu_ipc.h"
-#include "ivpu_mmu.h"
-#include "ivpu_pm.h"
-
-#define TILE_FUSE_ENABLE_BOTH        0x0
-#define TILE_SKU_BOTH_MTL            0x3630
-
-/* Work point configuration values */
-#define CONFIG_1_TILE                0x01
-#define CONFIG_2_TILE                0x02
-#define PLL_RATIO_5_3                0x01
-#define PLL_RATIO_4_3                0x02
-#define WP_CONFIG(tile, ratio)       (((tile) << 8) | (ratio))
-#define WP_CONFIG_1_TILE_5_3_RATIO   WP_CONFIG(CONFIG_1_TILE, PLL_RATIO_5_3)
-#define WP_CONFIG_1_TILE_4_3_RATIO   WP_CONFIG(CONFIG_1_TILE, PLL_RATIO_4_3)
-#define WP_CONFIG_2_TILE_5_3_RATIO   WP_CONFIG(CONFIG_2_TILE, PLL_RATIO_5_3)
-#define WP_CONFIG_2_TILE_4_3_RATIO   WP_CONFIG(CONFIG_2_TILE, PLL_RATIO_4_3)
-#define WP_CONFIG_0_TILE_PLL_OFF     WP_CONFIG(0, 0)
-
-#define PLL_REF_CLK_FREQ	     (50 * 1000000)
-#define PLL_SIMULATION_FREQ	     (10 * 1000000)
-#define PLL_DEFAULT_EPP_VALUE	     0x80
-
-#define TIM_SAFE_ENABLE		     0xf1d0dead
-#define TIM_WATCHDOG_RESET_VALUE     0xffffffff
-
-#define TIMEOUT_US		     (150 * USEC_PER_MSEC)
-#define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
-#define PLL_TIMEOUT_US		     (1500 * USEC_PER_MSEC)
-#define IDLE_TIMEOUT_US		     (500 * USEC_PER_MSEC)
-
-#define ICB_0_IRQ_MASK ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT)))
-
-#define ICB_1_IRQ_MASK ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_2_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_3_INT)) | \
-			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_4_INT)))
-
-#define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
-
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \
-			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
-			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR)))
-
-#define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK)
-#define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1)
-
-#define ITF_FIREWALL_VIOLATION_MASK ((REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_ROM_CMX)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_DBG)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_CTRL)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, DEC400)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_NCE)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI)) | \
-				     (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI_CMX)))
-
-static void ivpu_hw_wa_init(struct ivpu_device *vdev)
-{
-	vdev->wa.punit_disabled = false;
-	vdev->wa.clear_runtime_mem = false;
-	vdev->wa.d3hot_after_power_off = true;
-
-	if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4)
-		vdev->wa.interrupt_clear_with_0 = true;
-
-	IVPU_PRINT_WA(punit_disabled);
-	IVPU_PRINT_WA(clear_runtime_mem);
-	IVPU_PRINT_WA(d3hot_after_power_off);
-	IVPU_PRINT_WA(interrupt_clear_with_0);
-}
-
-static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
-{
-	vdev->timeout.boot = 1000;
-	vdev->timeout.jsm = 500;
-	vdev->timeout.tdr = 2000;
-	vdev->timeout.reschedule_suspend = 10;
-	vdev->timeout.autosuspend = 10;
-}
-
-static int ivpu_pll_wait_for_cmd_send(struct ivpu_device *vdev)
-{
-	return REGB_POLL_FLD(VPU_37XX_BUTTRESS_WP_REQ_CMD, SEND, 0, PLL_TIMEOUT_US);
-}
-
-/* Send KMD initiated workpoint change */
-static int ivpu_pll_cmd_send(struct ivpu_device *vdev, u16 min_ratio, u16 max_ratio,
-			     u16 target_ratio, u16 config)
-{
-	int ret;
-	u32 val;
-
-	ret = ivpu_pll_wait_for_cmd_send(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to sync before WP request: %d\n", ret);
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0);
-	val = REG_SET_FLD_NUM(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0, MIN_RATIO, min_ratio, val);
-	val = REG_SET_FLD_NUM(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0, MAX_RATIO, max_ratio, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0, val);
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1);
-	val = REG_SET_FLD_NUM(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1, TARGET_RATIO, target_ratio, val);
-	val = REG_SET_FLD_NUM(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1, EPP, PLL_DEFAULT_EPP_VALUE, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1, val);
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD2);
-	val = REG_SET_FLD_NUM(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD2, CONFIG, config, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD2, val);
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_WP_REQ_CMD);
-	val = REG_SET_FLD(VPU_37XX_BUTTRESS_WP_REQ_CMD, SEND, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_WP_REQ_CMD, val);
-
-	ret = ivpu_pll_wait_for_cmd_send(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to sync after WP request: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_pll_wait_for_lock(struct ivpu_device *vdev, bool enable)
-{
-	u32 exp_val = enable ? 0x1 : 0x0;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
-
-	return REGB_POLL_FLD(VPU_37XX_BUTTRESS_PLL_STATUS, LOCK, exp_val, PLL_TIMEOUT_US);
-}
-
-static int ivpu_pll_wait_for_status_ready(struct ivpu_device *vdev)
-{
-	if (IVPU_WA(punit_disabled))
-		return 0;
-
-	return REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, READY, 1, PLL_TIMEOUT_US);
-}
-
-static void ivpu_pll_init_frequency_ratios(struct ivpu_device *vdev)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-	u8 fuse_min_ratio, fuse_max_ratio, fuse_pn_ratio;
-	u32 fmin_fuse, fmax_fuse;
-
-	fmin_fuse = REGB_RD32(VPU_37XX_BUTTRESS_FMIN_FUSE);
-	fuse_min_ratio = REG_GET_FLD(VPU_37XX_BUTTRESS_FMIN_FUSE, MIN_RATIO, fmin_fuse);
-	fuse_pn_ratio = REG_GET_FLD(VPU_37XX_BUTTRESS_FMIN_FUSE, PN_RATIO, fmin_fuse);
-
-	fmax_fuse = REGB_RD32(VPU_37XX_BUTTRESS_FMAX_FUSE);
-	fuse_max_ratio = REG_GET_FLD(VPU_37XX_BUTTRESS_FMAX_FUSE, MAX_RATIO, fmax_fuse);
-
-	hw->pll.min_ratio = clamp_t(u8, ivpu_pll_min_ratio, fuse_min_ratio, fuse_max_ratio);
-	hw->pll.max_ratio = clamp_t(u8, ivpu_pll_max_ratio, hw->pll.min_ratio, fuse_max_ratio);
-	hw->pll.pn_ratio = clamp_t(u8, fuse_pn_ratio, hw->pll.min_ratio, hw->pll.max_ratio);
-}
-
-static int ivpu_hw_37xx_wait_for_vpuip_bar(struct ivpu_device *vdev)
-{
-	return REGV_POLL_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, AON, 0, 100);
-}
-
-static int ivpu_pll_drive(struct ivpu_device *vdev, bool enable)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-	u16 target_ratio;
-	u16 config;
-	int ret;
-
-	if (IVPU_WA(punit_disabled)) {
-		ivpu_dbg(vdev, PM, "Skipping PLL request\n");
-		return 0;
-	}
-
-	if (enable) {
-		target_ratio = hw->pll.pn_ratio;
-		config = hw->config;
-	} else {
-		target_ratio = 0;
-		config = 0;
-	}
-
-	ivpu_dbg(vdev, PM, "PLL workpoint request: config 0x%04x pll ratio 0x%x\n",
-		 config, target_ratio);
-
-	ret = ivpu_pll_cmd_send(vdev, hw->pll.min_ratio, hw->pll.max_ratio, target_ratio, config);
-	if (ret) {
-		ivpu_err(vdev, "Failed to send PLL workpoint request: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_pll_wait_for_lock(vdev, enable);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for PLL lock\n");
-		return ret;
-	}
-
-	if (enable) {
-		ret = ivpu_pll_wait_for_status_ready(vdev);
-		if (ret) {
-			ivpu_err(vdev, "Timed out waiting for PLL ready status\n");
-			return ret;
-		}
-
-		ret = ivpu_hw_37xx_wait_for_vpuip_bar(vdev);
-		if (ret) {
-			ivpu_err(vdev, "Timed out waiting for VPUIP bar\n");
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int ivpu_pll_enable(struct ivpu_device *vdev)
-{
-	return ivpu_pll_drive(vdev, true);
-}
-
-static int ivpu_pll_disable(struct ivpu_device *vdev)
-{
-	return ivpu_pll_drive(vdev, false);
-}
-
-static void ivpu_boot_host_ss_rst_clr_assert(struct ivpu_device *vdev)
-{
-	u32 val = 0;
-
-	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, TOP_NOC, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, DSS_MAS, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, MSS_MAS, val);
-
-	REGV_WR32(VPU_37XX_HOST_SS_CPR_RST_CLR, val);
-}
-
-static void ivpu_boot_host_ss_rst_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_CPR_RST_SET);
-
-	if (enable) {
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, TOP_NOC, val);
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, DSS_MAS, val);
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, MSS_MAS, val);
-	} else {
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, TOP_NOC, val);
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, DSS_MAS, val);
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, MSS_MAS, val);
-	}
-
-	REGV_WR32(VPU_37XX_HOST_SS_CPR_RST_SET, val);
-}
-
-static void ivpu_boot_host_ss_clk_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_CPR_CLK_SET);
-
-	if (enable) {
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, TOP_NOC, val);
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, DSS_MAS, val);
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, MSS_MAS, val);
-	} else {
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, TOP_NOC, val);
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, DSS_MAS, val);
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, MSS_MAS, val);
-	}
-
-	REGV_WR32(VPU_37XX_HOST_SS_CPR_CLK_SET, val);
-}
-
-static int ivpu_boot_noc_qreqn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QREQN);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QACCEPTN);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QACCEPTN, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QDENY);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QDENY, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qrenqn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QREQN);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QACCEPTN);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QACCEPTN, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QACCEPTN, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QDENY);
-
-	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QDENY, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QDENY, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_host_ss_configure(struct ivpu_device *vdev)
-{
-	ivpu_boot_host_ss_rst_clr_assert(vdev);
-
-	return ivpu_boot_noc_qreqn_check(vdev, 0x0);
-}
-
-static void ivpu_boot_vpu_idle_gen_disable(struct ivpu_device *vdev)
-{
-	REGV_WR32(VPU_37XX_HOST_SS_AON_VPU_IDLE_GEN, 0x0);
-}
-
-static int ivpu_boot_host_ss_axi_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QREQN);
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
-	REGV_WR32(VPU_37XX_HOST_SS_NOC_QREQN, val);
-
-	ret = ivpu_boot_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_noc_qdeny_check(vdev, 0x0);
-	if (ret)
-		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_boot_host_ss_axi_enable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_axi_drive(vdev, true);
-}
-
-static int ivpu_boot_host_ss_top_noc_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	val = REGV_RD32(VPU_37XX_TOP_NOC_QREQN);
-	if (enable) {
-		val = REG_SET_FLD(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, val);
-		val = REG_SET_FLD(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
-	} else {
-		val = REG_CLR_FLD(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, val);
-		val = REG_CLR_FLD(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
-	}
-	REGV_WR32(VPU_37XX_TOP_NOC_QREQN, val);
-
-	ret = ivpu_boot_top_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_top_noc_qdeny_check(vdev, 0x0);
-	if (ret)
-		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_boot_host_ss_top_noc_enable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_top_noc_drive(vdev, true);
-}
-
-static void ivpu_boot_pwr_island_trickle_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, MSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, MSS_CPU, val);
-
-	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, val);
-}
-
-static void ivpu_boot_pwr_island_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, MSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, MSS_CPU, val);
-
-	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, val);
-}
-
-static int ivpu_boot_wait_for_pwr_island_status(struct ivpu_device *vdev, u32 exp_val)
-{
-	return REGV_POLL_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_STATUS0, MSS_CPU,
-			     exp_val, PWR_ISLAND_STATUS_TIMEOUT_US);
-}
-
-static void ivpu_boot_pwr_island_isolation_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, MSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, MSS_CPU, val);
-
-	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, val);
-}
-
-static void ivpu_boot_dpu_active_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, DPU_ACTIVE, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, DPU_ACTIVE, val);
-
-	REGV_WR32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, val);
-}
-
-static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ivpu_boot_pwr_island_trickle_drive(vdev, true);
-	ivpu_boot_pwr_island_drive(vdev, true);
-
-	ret = ivpu_boot_wait_for_pwr_island_status(vdev, 0x1);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for power island status\n");
-		return ret;
-	}
-
-	ret = ivpu_boot_top_noc_qrenqn_check(vdev, 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qrenqn check %d\n", ret);
-		return ret;
-	}
-
-	ivpu_boot_host_ss_clk_drive(vdev, true);
-	ivpu_boot_pwr_island_isolation_drive(vdev, false);
-	ivpu_boot_host_ss_rst_drive(vdev, true);
-	ivpu_boot_dpu_active_drive(vdev, true);
-
-	return ret;
-}
-
-static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
-
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
-
-	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
-}
-
-static void ivpu_boot_tbu_mmu_enable(struct ivpu_device *vdev)
-{
-	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TBU_MMUSSIDV);
-
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU0_AWMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU0_ARMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU2_AWMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU2_ARMMUSSIDV, val);
-
-	REGV_WR32(VPU_37XX_HOST_IF_TBU_MMUSSIDV, val);
-}
-
-static void ivpu_boot_soc_cpu_boot(struct ivpu_device *vdev)
-{
-	u32 val;
-
-	val = REGV_RD32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC);
-	val = REG_SET_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RSTRUN0, val);
-
-	val = REG_CLR_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RSTVEC, val);
-	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
-
-	val = REG_SET_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RESUME0, val);
-	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
-
-	val = REG_CLR_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RESUME0, val);
-	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
-
-	val = vdev->fw->entry_point >> 9;
-	REGV_WR32(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, val);
-
-	val = REG_SET_FLD(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, DONE, val);
-	REGV_WR32(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, val);
-
-	ivpu_dbg(vdev, PM, "Booting firmware, mode: %s\n",
-		 vdev->fw->entry_point == vdev->fw->cold_boot_entry_point ? "cold boot" : "resume");
-}
-
-static int ivpu_boot_d0i3_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Failed to sync before D0i3 transition: %d\n", ret);
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL);
-	if (enable)
-		val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL, I3, val);
-	else
-		val = REG_CLR_FLD(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL, I3, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL, val);
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
-	if (ret)
-		ivpu_err(vdev, "Failed to sync after D0i3 transition: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-
-	hw->tile_fuse = TILE_FUSE_ENABLE_BOTH;
-	hw->sku = TILE_SKU_BOTH_MTL;
-	hw->config = WP_CONFIG_2_TILE_4_3_RATIO;
-
-	ivpu_pll_init_frequency_ratios(vdev);
-
-	ivpu_hw_init_range(&hw->ranges.global, 0x80000000, SZ_512M);
-	ivpu_hw_init_range(&hw->ranges.user,   0xc0000000, 255 * SZ_1M);
-	ivpu_hw_init_range(&hw->ranges.shave, 0x180000000, SZ_2G);
-	ivpu_hw_init_range(&hw->ranges.dma,   0x200000000, SZ_8G);
-
-	vdev->platform = IVPU_PLATFORM_SILICON;
-	ivpu_hw_wa_init(vdev);
-	ivpu_hw_timeouts_init(vdev);
-
-	return 0;
-}
-
-static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
-{
-	int ret;
-	u32 val;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
-	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
-
-	return ret;
-}
-
-static int ivpu_hw_37xx_d0i3_enable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_boot_d0i3_drive(vdev, true);
-	if (ret)
-		ivpu_err(vdev, "Failed to enable D0i3: %d\n", ret);
-
-	udelay(5); /* VPU requires 5 us to complete the transition */
-
-	return ret;
-}
-
-static int ivpu_hw_37xx_d0i3_disable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_boot_d0i3_drive(vdev, false);
-	if (ret)
-		ivpu_err(vdev, "Failed to disable D0i3: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_hw_37xx_reset(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to reset HW: %d\n", ret);
-
-	ret = ivpu_hw_37xx_d0i3_disable(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
-
-	ret = ivpu_pll_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable PLL: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_host_ss_configure(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to configure host SS: %d\n", ret);
-		return ret;
-	}
-
-	/*
-	 * The control circuitry for vpu_idle indication logic powers up active.
-	 * To ensure unnecessary low power mode signal from LRT during bring up,
-	 * KMD disables the circuitry prior to bringing up the Main Power island.
-	 */
-	ivpu_boot_vpu_idle_gen_disable(vdev);
-
-	ret = ivpu_boot_pwr_domain_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable power domain: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_host_ss_axi_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable AXI: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_host_ss_top_noc_enable(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to enable TOP NOC: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_hw_37xx_boot_fw(struct ivpu_device *vdev)
-{
-	ivpu_boot_no_snoop_enable(vdev);
-	ivpu_boot_tbu_mmu_enable(vdev);
-	ivpu_boot_soc_cpu_boot(vdev);
-
-	return 0;
-}
-
-static bool ivpu_hw_37xx_is_idle(struct ivpu_device *vdev)
-{
-	u32 val;
-
-	if (IVPU_WA(punit_disabled))
-		return true;
-
-	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_STATUS);
-	return REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, READY, val) &&
-	       REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, val);
-}
-
-static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
-{
-	int ret = 0;
-
-	if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev))
-		ivpu_err(vdev, "Failed to reset the VPU\n");
-
-	if (ivpu_pll_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable PLL\n");
-		ret = -EIO;
-	}
-
-	if (ivpu_hw_37xx_d0i3_enable(vdev)) {
-		ivpu_err(vdev, "Failed to enter D0I3\n");
-		ret = -EIO;
-	}
-
-	return ret;
-}
-
-static void ivpu_hw_37xx_wdt_disable(struct ivpu_device *vdev)
-{
-	u32 val;
-
-	/* Enable writing and set non-zero WDT value */
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_WATCHDOG, TIM_WATCHDOG_RESET_VALUE);
-
-	/* Enable writing and disable watchdog timer */
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_WDOG_EN, 0);
-
-	/* Now clear the timeout interrupt */
-	val = REGV_RD32(VPU_37XX_CPU_SS_TIM_GEN_CONFIG);
-	val = REG_CLR_FLD(VPU_37XX_CPU_SS_TIM_GEN_CONFIG, WDOG_TO_INT_CLR, val);
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_GEN_CONFIG, val);
-}
-
-static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config)
-{
-	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
-	u32 cpu_clock;
-
-	if ((config & 0xff) == PLL_RATIO_4_3)
-		cpu_clock = pll_clock * 2 / 4;
-	else
-		cpu_clock = pll_clock * 2 / 5;
-
-	return cpu_clock;
-}
-
-/* Register indirect accesses */
-static u32 ivpu_hw_37xx_reg_pll_freq_get(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_37XX_BUTTRESS_CURRENT_PLL);
-	pll_curr_ratio &= VPU_37XX_BUTTRESS_CURRENT_PLL_RATIO_MASK;
-
-	if (!ivpu_is_silicon(vdev))
-		return PLL_SIMULATION_FREQ;
-
-	return ivpu_hw_37xx_pll_to_freq(pll_curr_ratio, vdev->hw->config);
-}
-
-static u32 ivpu_hw_37xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_37XX_BUTTRESS_VPU_TELEMETRY_OFFSET);
-}
-
-static u32 ivpu_hw_37xx_reg_telemetry_size_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_37XX_BUTTRESS_VPU_TELEMETRY_SIZE);
-}
-
-static u32 ivpu_hw_37xx_reg_telemetry_enable_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_37XX_BUTTRESS_VPU_TELEMETRY_ENABLE);
-}
-
-static void ivpu_hw_37xx_reg_db_set(struct ivpu_device *vdev, u32 db_id)
-{
-	u32 reg_stride = VPU_37XX_CPU_SS_DOORBELL_1 - VPU_37XX_CPU_SS_DOORBELL_0;
-	u32 val = REG_FLD(VPU_37XX_CPU_SS_DOORBELL_0, SET);
-
-	REGV_WR32I(VPU_37XX_CPU_SS_DOORBELL_0, reg_stride, db_id, val);
-}
-
-static u32 ivpu_hw_37xx_reg_ipc_rx_addr_get(struct ivpu_device *vdev)
-{
-	return REGV_RD32(VPU_37XX_HOST_SS_TIM_IPC_FIFO_ATM);
-}
-
-static u32 ivpu_hw_37xx_reg_ipc_rx_count_get(struct ivpu_device *vdev)
-{
-	u32 count = REGV_RD32_SILENT(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT);
-
-	return REG_GET_FLD(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
-}
-
-static void ivpu_hw_37xx_reg_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
-{
-	REGV_WR32(VPU_37XX_CPU_SS_TIM_IPC_FIFO, vpu_addr);
-}
-
-static void ivpu_hw_37xx_irq_clear(struct ivpu_device *vdev)
-{
-	REGV_WR64(VPU_37XX_HOST_SS_ICB_CLEAR_0, ICB_0_1_IRQ_MASK);
-}
-
-static void ivpu_hw_37xx_irq_enable(struct ivpu_device *vdev)
-{
-	REGV_WR32(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, ITF_FIREWALL_VIOLATION_MASK);
-	REGV_WR64(VPU_37XX_HOST_SS_ICB_ENABLE_0, ICB_0_1_IRQ_MASK);
-	REGB_WR32(VPU_37XX_BUTTRESS_LOCAL_INT_MASK, BUTTRESS_IRQ_ENABLE_MASK);
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-}
-
-static void ivpu_hw_37xx_irq_disable(struct ivpu_device *vdev)
-{
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-	REGB_WR32(VPU_37XX_BUTTRESS_LOCAL_INT_MASK, BUTTRESS_IRQ_DISABLE_MASK);
-	REGV_WR64(VPU_37XX_HOST_SS_ICB_ENABLE_0, 0x0ull);
-	REGV_WR32(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, 0x0);
-}
-
-static void ivpu_hw_37xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
-{
-	ivpu_err_ratelimited(vdev, "WDT NCE irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-static void ivpu_hw_37xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
-{
-	ivpu_err_ratelimited(vdev, "WDT MSS irq\n");
-
-	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-static void ivpu_hw_37xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
-{
-	ivpu_err_ratelimited(vdev, "NOC Firewall irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-/* Handler for IRQs from VPU core (irqV) */
-static u32 ivpu_hw_37xx_irqv_handler(struct ivpu_device *vdev, int irq)
-{
-	u32 status = REGV_RD32(VPU_37XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
-
-	REGV_WR32(VPU_37XX_HOST_SS_ICB_CLEAR_0, status);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
-		ivpu_mmu_irq_evtq_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
-		ivpu_ipc_irq_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
-		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT, status))
-		ivpu_mmu_irq_gerr_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, status))
-		ivpu_hw_37xx_irq_wdt_mss_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, status))
-		ivpu_hw_37xx_irq_wdt_nce_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
-		ivpu_hw_37xx_irq_noc_firewall_handler(vdev);
-
-	return status;
-}
-
-/* Handler for IRQs from Buttress core (irqB) */
-static u32 ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
-{
-	u32 status = REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
-	bool schedule_recovery = false;
-
-	if (status == 0)
-		return 0;
-
-	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
-			 REGB_RD32(VPU_37XX_BUTTRESS_CURRENT_PLL));
-
-	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR, status)) {
-		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_37XX_BUTTRESS_ATS_ERR_LOG_0));
-		REGB_WR32(VPU_37XX_BUTTRESS_ATS_ERR_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR, status)) {
-		u32 ufi_log = REGB_RD32(VPU_37XX_BUTTRESS_UFI_ERR_LOG);
-
-		ivpu_err(vdev, "UFI_ERR irq (0x%08x) opcode: 0x%02lx axi_id: 0x%02lx cq_id: 0x%03lx",
-			 ufi_log, REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, OPCODE, ufi_log),
-			 REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, AXI_ID, ufi_log),
-			 REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, CQ_ID, ufi_log));
-		REGB_WR32(VPU_37XX_BUTTRESS_UFI_ERR_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	/* This must be done after interrupts are cleared at the source. */
-	if (IVPU_WA(interrupt_clear_with_0))
-		/*
-		 * Writing 1 triggers an interrupt, so we can't perform read update write.
-		 * Clear local interrupt status by writing 0 to all bits.
-		 */
-		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0);
-	else
-		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, status);
-
-	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
-
-	return status;
-}
-
-static irqreturn_t ivpu_hw_37xx_irq_handler(int irq, void *ptr)
-{
-	struct ivpu_device *vdev = ptr;
-	u32 ret_irqv, ret_irqb;
-
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-
-	ret_irqv = ivpu_hw_37xx_irqv_handler(vdev, irq);
-	ret_irqb = ivpu_hw_37xx_irqb_handler(vdev, irq);
-
-	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-
-	return IRQ_RETVAL(ret_irqb | ret_irqv);
-}
-
-static void ivpu_hw_37xx_diagnose_failure(struct ivpu_device *vdev)
-{
-	u32 irqv = REGV_RD32(VPU_37XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
-	u32 irqb = REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
-
-	if (ivpu_hw_37xx_reg_ipc_rx_count_get(vdev))
-		ivpu_err(vdev, "IPC FIFO queue not empty, missed IPC IRQ");
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, irqv))
-		ivpu_err(vdev, "WDT MSS timeout detected\n");
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, irqv))
-		ivpu_err(vdev, "WDT NCE timeout detected\n");
-
-	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, irqv))
-		ivpu_err(vdev, "NOC Firewall irq detected\n");
-
-	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR, irqb))
-		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_37XX_BUTTRESS_ATS_ERR_LOG_0));
-
-	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR, irqb)) {
-		u32 ufi_log = REGB_RD32(VPU_37XX_BUTTRESS_UFI_ERR_LOG);
-
-		ivpu_err(vdev, "UFI_ERR irq (0x%08x) opcode: 0x%02lx axi_id: 0x%02lx cq_id: 0x%03lx",
-			 ufi_log, REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, OPCODE, ufi_log),
-			 REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, AXI_ID, ufi_log),
-			 REG_GET_FLD(VPU_37XX_BUTTRESS_UFI_ERR_LOG, CQ_ID, ufi_log));
-	}
-}
-
-const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
-	.info_init = ivpu_hw_37xx_info_init,
-	.power_up = ivpu_hw_37xx_power_up,
-	.is_idle = ivpu_hw_37xx_is_idle,
-	.power_down = ivpu_hw_37xx_power_down,
-	.reset = ivpu_hw_37xx_reset,
-	.boot_fw = ivpu_hw_37xx_boot_fw,
-	.wdt_disable = ivpu_hw_37xx_wdt_disable,
-	.diagnose_failure = ivpu_hw_37xx_diagnose_failure,
-	.reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get,
-	.reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get,
-	.reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get,
-	.reg_telemetry_enable_get = ivpu_hw_37xx_reg_telemetry_enable_get,
-	.reg_db_set = ivpu_hw_37xx_reg_db_set,
-	.reg_ipc_rx_addr_get = ivpu_hw_37xx_reg_ipc_rx_addr_get,
-	.reg_ipc_rx_count_get = ivpu_hw_37xx_reg_ipc_rx_count_get,
-	.reg_ipc_tx_set = ivpu_hw_37xx_reg_ipc_tx_set,
-	.irq_clear = ivpu_hw_37xx_irq_clear,
-	.irq_enable = ivpu_hw_37xx_irq_enable,
-	.irq_disable = ivpu_hw_37xx_irq_disable,
-	.irq_handler = ivpu_hw_37xx_irq_handler,
-};
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
index 4083beb5e9db..cf5e2f01049c 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
@@ -8,78 +8,6 @@
 
 #include <linux/bits.h>
 
-#define VPU_37XX_BUTTRESS_INTERRUPT_TYPE				0x00000000u
-
-#define VPU_37XX_BUTTRESS_INTERRUPT_STAT				0x00000004u
-#define VPU_37XX_BUTTRESS_INTERRUPT_STAT_FREQ_CHANGE_MASK		BIT_MASK(0)
-#define VPU_37XX_BUTTRESS_INTERRUPT_STAT_ATS_ERR_MASK			BIT_MASK(1)
-#define VPU_37XX_BUTTRESS_INTERRUPT_STAT_UFI_ERR_MASK			BIT_MASK(2)
-
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0				0x00000008u
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0_MIN_RATIO_MASK		GENMASK(15, 0)
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD0_MAX_RATIO_MASK		GENMASK(31, 16)
-
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1				0x0000000cu
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1_TARGET_RATIO_MASK		GENMASK(15, 0)
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD1_EPP_MASK			GENMASK(31, 16)
-
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD2				0x00000010u
-#define VPU_37XX_BUTTRESS_WP_REQ_PAYLOAD2_CONFIG_MASK			GENMASK(15, 0)
-
-#define VPU_37XX_BUTTRESS_WP_REQ_CMD					0x00000014u
-#define VPU_37XX_BUTTRESS_WP_REQ_CMD_SEND_MASK				BIT_MASK(0)
-
-#define VPU_37XX_BUTTRESS_WP_DOWNLOAD					0x00000018u
-#define VPU_37XX_BUTTRESS_WP_DOWNLOAD_TARGET_RATIO_MASK			GENMASK(15, 0)
-
-#define VPU_37XX_BUTTRESS_CURRENT_PLL					0x0000001cu
-#define VPU_37XX_BUTTRESS_CURRENT_PLL_RATIO_MASK			GENMASK(15, 0)
-
-#define VPU_37XX_BUTTRESS_PLL_ENABLE					0x00000020u
-
-#define VPU_37XX_BUTTRESS_FMIN_FUSE					0x00000024u
-#define VPU_37XX_BUTTRESS_FMIN_FUSE_MIN_RATIO_MASK			GENMASK(7, 0)
-#define VPU_37XX_BUTTRESS_FMIN_FUSE_PN_RATIO_MASK			GENMASK(15, 8)
-
-#define VPU_37XX_BUTTRESS_FMAX_FUSE					0x00000028u
-#define VPU_37XX_BUTTRESS_FMAX_FUSE_MAX_RATIO_MASK			GENMASK(7, 0)
-
-#define VPU_37XX_BUTTRESS_TILE_FUSE					0x0000002cu
-#define VPU_37XX_BUTTRESS_TILE_FUSE_VALID_MASK				BIT_MASK(0)
-#define VPU_37XX_BUTTRESS_TILE_FUSE_SKU_MASK				GENMASK(3, 2)
-
-#define VPU_37XX_BUTTRESS_LOCAL_INT_MASK				0x00000030u
-#define VPU_37XX_BUTTRESS_GLOBAL_INT_MASK				0x00000034u
-
-#define VPU_37XX_BUTTRESS_PLL_STATUS					0x00000040u
-#define VPU_37XX_BUTTRESS_PLL_STATUS_LOCK_MASK				BIT_MASK(1)
-
-#define VPU_37XX_BUTTRESS_VPU_STATUS					0x00000044u
-#define VPU_37XX_BUTTRESS_VPU_STATUS_READY_MASK				BIT_MASK(0)
-#define VPU_37XX_BUTTRESS_VPU_STATUS_IDLE_MASK				BIT_MASK(1)
-
-#define VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL				0x00000060u
-#define VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL_INPROGRESS_MASK		BIT_MASK(0)
-#define VPU_37XX_BUTTRESS_VPU_D0I3_CONTROL_I3_MASK			BIT_MASK(2)
-
-#define VPU_37XX_BUTTRESS_VPU_IP_RESET					0x00000050u
-#define VPU_37XX_BUTTRESS_VPU_IP_RESET_TRIGGER_MASK			BIT_MASK(0)
-
-#define VPU_37XX_BUTTRESS_VPU_TELEMETRY_OFFSET				0x00000080u
-#define VPU_37XX_BUTTRESS_VPU_TELEMETRY_SIZE				0x00000084u
-#define VPU_37XX_BUTTRESS_VPU_TELEMETRY_ENABLE				0x00000088u
-
-#define VPU_37XX_BUTTRESS_ATS_ERR_LOG_0					0x000000a0u
-#define VPU_37XX_BUTTRESS_ATS_ERR_LOG_1					0x000000a4u
-#define VPU_37XX_BUTTRESS_ATS_ERR_CLEAR					0x000000a8u
-
-#define VPU_37XX_BUTTRESS_UFI_ERR_LOG					0x000000b0u
-#define VPU_37XX_BUTTRESS_UFI_ERR_LOG_CQ_ID_MASK			GENMASK(11, 0)
-#define VPU_37XX_BUTTRESS_UFI_ERR_LOG_AXI_ID_MASK			GENMASK(19, 12)
-#define VPU_37XX_BUTTRESS_UFI_ERR_LOG_OPCODE_MASK			GENMASK(24, 20)
-
-#define VPU_37XX_BUTTRESS_UFI_ERR_CLEAR					0x000000b4u
-
 #define VPU_37XX_HOST_SS_CPR_CLK_SET					0x00000084u
 #define VPU_37XX_HOST_SS_CPR_CLK_SET_TOP_NOC_MASK			BIT_MASK(1)
 #define VPU_37XX_HOST_SS_CPR_CLK_SET_DSS_MAS_MASK			BIT_MASK(10)
@@ -240,6 +168,8 @@
 #define VPU_37XX_CPU_SS_TIM_GEN_CONFIG					0x06021008u
 #define VPU_37XX_CPU_SS_TIM_GEN_CONFIG_WDOG_TO_INT_CLR_MASK		BIT_MASK(9)
 
+#define VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT				0x06029000u
+
 #define VPU_37XX_CPU_SS_DOORBELL_0					0x06300000u
 #define VPU_37XX_CPU_SS_DOORBELL_0_SET_MASK				BIT_MASK(0)
 
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
deleted file mode 100644
index e691c49c9841..000000000000
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ /dev/null
@@ -1,1205 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2020-2023 Intel Corporation
- */
-
-#include "ivpu_drv.h"
-#include "ivpu_fw.h"
-#include "ivpu_hw.h"
-#include "ivpu_hw_40xx_reg.h"
-#include "ivpu_hw_reg_io.h"
-#include "ivpu_ipc.h"
-#include "ivpu_mmu.h"
-#include "ivpu_pm.h"
-
-#include <linux/dmi.h>
-
-#define TILE_MAX_NUM                 6
-#define TILE_MAX_MASK                0x3f
-
-#define LNL_HW_ID                    0x4040
-
-#define SKU_TILE_SHIFT               0u
-#define SKU_TILE_MASK                0x0000ffffu
-#define SKU_HW_ID_SHIFT              16u
-#define SKU_HW_ID_MASK               0xffff0000u
-
-#define PLL_CONFIG_DEFAULT           0x1
-#define PLL_CDYN_DEFAULT             0x80
-#define PLL_EPP_DEFAULT              0x80
-#define PLL_REF_CLK_FREQ	     (50 * 1000000)
-#define PLL_RATIO_TO_FREQ(x)	     ((x) * PLL_REF_CLK_FREQ)
-
-#define PLL_PROFILING_FREQ_DEFAULT   38400000
-#define PLL_PROFILING_FREQ_HIGH      400000000
-
-#define TIM_SAFE_ENABLE		     0xf1d0dead
-#define TIM_WATCHDOG_RESET_VALUE     0xffffffff
-
-#define TIMEOUT_US		     (150 * USEC_PER_MSEC)
-#define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
-#define PLL_TIMEOUT_US		     (1500 * USEC_PER_MSEC)
-
-#define WEIGHTS_DEFAULT              0xf711f711u
-#define WEIGHTS_ATS_DEFAULT          0x0000f711u
-
-#define ICB_0_IRQ_MASK ((REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT)))
-
-#define ICB_1_IRQ_MASK ((REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_2_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_3_INT)) | \
-			(REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_4_INT)))
-
-#define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
-
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
-			   (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI0_ERR)) | \
-			   (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI1_ERR)) | \
-			   (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR0_ERR)) | \
-			   (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR1_ERR)) | \
-			   (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, SURV_ERR)))
-
-#define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK)
-#define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1)
-
-#define ITF_FIREWALL_VIOLATION_MASK ((REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_ROM_CMX)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_DBG)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_CTRL)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, DEC400)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_NCE)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI)) | \
-				     (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI_CMX)))
-
-static char *ivpu_platform_to_str(u32 platform)
-{
-	switch (platform) {
-	case IVPU_PLATFORM_SILICON:
-		return "IVPU_PLATFORM_SILICON";
-	case IVPU_PLATFORM_SIMICS:
-		return "IVPU_PLATFORM_SIMICS";
-	case IVPU_PLATFORM_FPGA:
-		return "IVPU_PLATFORM_FPGA";
-	default:
-		return "Invalid platform";
-	}
-}
-
-static const struct dmi_system_id ivpu_dmi_platform_simulation[] = {
-	{
-		.ident = "Intel Simics",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "lnlrvp"),
-			DMI_MATCH(DMI_BOARD_VERSION, "1.0"),
-			DMI_MATCH(DMI_BOARD_SERIAL, "123456789"),
-		},
-	},
-	{
-		.ident = "Intel Simics",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "Simics"),
-		},
-	},
-	{ }
-};
-
-static void ivpu_hw_read_platform(struct ivpu_device *vdev)
-{
-	if (dmi_check_system(ivpu_dmi_platform_simulation))
-		vdev->platform = IVPU_PLATFORM_SIMICS;
-	else
-		vdev->platform = IVPU_PLATFORM_SILICON;
-
-	ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n",
-		 ivpu_platform_to_str(vdev->platform), vdev->platform);
-}
-
-static void ivpu_hw_wa_init(struct ivpu_device *vdev)
-{
-	vdev->wa.punit_disabled = ivpu_is_fpga(vdev);
-	vdev->wa.clear_runtime_mem = false;
-
-	if (ivpu_hw_gen(vdev) == IVPU_HW_40XX)
-		vdev->wa.disable_clock_relinquish = true;
-
-	IVPU_PRINT_WA(punit_disabled);
-	IVPU_PRINT_WA(clear_runtime_mem);
-	IVPU_PRINT_WA(disable_clock_relinquish);
-}
-
-static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
-{
-	if (ivpu_is_fpga(vdev)) {
-		vdev->timeout.boot = 100000;
-		vdev->timeout.jsm = 50000;
-		vdev->timeout.tdr = 2000000;
-		vdev->timeout.reschedule_suspend = 1000;
-		vdev->timeout.autosuspend = -1;
-	} else if (ivpu_is_simics(vdev)) {
-		vdev->timeout.boot = 50;
-		vdev->timeout.jsm = 500;
-		vdev->timeout.tdr = 10000;
-		vdev->timeout.reschedule_suspend = 10;
-		vdev->timeout.autosuspend = -1;
-	} else {
-		vdev->timeout.boot = 1000;
-		vdev->timeout.jsm = 500;
-		vdev->timeout.tdr = 2000;
-		vdev->timeout.reschedule_suspend = 10;
-		vdev->timeout.autosuspend = 10;
-	}
-}
-
-static int ivpu_pll_wait_for_cmd_send(struct ivpu_device *vdev)
-{
-	return REGB_POLL_FLD(VPU_40XX_BUTTRESS_WP_REQ_CMD, SEND, 0, PLL_TIMEOUT_US);
-}
-
-static int ivpu_pll_cmd_send(struct ivpu_device *vdev, u16 min_ratio, u16 max_ratio,
-			     u16 target_ratio, u16 epp, u16 config, u16 cdyn)
-{
-	int ret;
-	u32 val;
-
-	ret = ivpu_pll_wait_for_cmd_send(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to sync before WP request: %d\n", ret);
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0, MIN_RATIO, min_ratio, val);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0, MAX_RATIO, max_ratio, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0, val);
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1, TARGET_RATIO, target_ratio, val);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1, EPP, epp, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1, val);
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2, CONFIG, config, val);
-	val = REG_SET_FLD_NUM(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2, CDYN, cdyn, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2, val);
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_WP_REQ_CMD);
-	val = REG_SET_FLD(VPU_40XX_BUTTRESS_WP_REQ_CMD, SEND, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_WP_REQ_CMD, val);
-
-	ret = ivpu_pll_wait_for_cmd_send(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to sync after WP request: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_pll_wait_for_status_ready(struct ivpu_device *vdev)
-{
-	return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, READY, 1, PLL_TIMEOUT_US);
-}
-
-static int ivpu_wait_for_clock_own_resource_ack(struct ivpu_device *vdev)
-{
-	if (ivpu_is_simics(vdev))
-		return 0;
-
-	return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US);
-}
-
-static void ivpu_pll_init_frequency_ratios(struct ivpu_device *vdev)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-	u8 fuse_min_ratio, fuse_pn_ratio, fuse_max_ratio;
-	u32 fmin_fuse, fmax_fuse;
-
-	fmin_fuse = REGB_RD32(VPU_40XX_BUTTRESS_FMIN_FUSE);
-	fuse_min_ratio = REG_GET_FLD(VPU_40XX_BUTTRESS_FMIN_FUSE, MIN_RATIO, fmin_fuse);
-	fuse_pn_ratio = REG_GET_FLD(VPU_40XX_BUTTRESS_FMIN_FUSE, PN_RATIO, fmin_fuse);
-
-	fmax_fuse = REGB_RD32(VPU_40XX_BUTTRESS_FMAX_FUSE);
-	fuse_max_ratio = REG_GET_FLD(VPU_40XX_BUTTRESS_FMAX_FUSE, MAX_RATIO, fmax_fuse);
-
-	hw->pll.min_ratio = clamp_t(u8, ivpu_pll_min_ratio, fuse_min_ratio, fuse_max_ratio);
-	hw->pll.max_ratio = clamp_t(u8, ivpu_pll_max_ratio, hw->pll.min_ratio, fuse_max_ratio);
-	hw->pll.pn_ratio = clamp_t(u8, fuse_pn_ratio, hw->pll.min_ratio, hw->pll.max_ratio);
-}
-
-static int ivpu_pll_drive(struct ivpu_device *vdev, bool enable)
-{
-	u16 config = enable ? PLL_CONFIG_DEFAULT : 0;
-	u16 cdyn = enable ? PLL_CDYN_DEFAULT : 0;
-	u16 epp = enable ? PLL_EPP_DEFAULT : 0;
-	struct ivpu_hw_info *hw = vdev->hw;
-	u16 target_ratio = hw->pll.pn_ratio;
-	int ret;
-
-	ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, epp: 0x%x, config: 0x%x, cdyn: 0x%x\n",
-		 PLL_RATIO_TO_FREQ(target_ratio), epp, config, cdyn);
-
-	ret = ivpu_pll_cmd_send(vdev, hw->pll.min_ratio, hw->pll.max_ratio,
-				target_ratio, epp, config, cdyn);
-	if (ret) {
-		ivpu_err(vdev, "Failed to send PLL workpoint request: %d\n", ret);
-		return ret;
-	}
-
-	if (enable) {
-		ret = ivpu_pll_wait_for_status_ready(vdev);
-		if (ret) {
-			ivpu_err(vdev, "Timed out waiting for PLL ready status\n");
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int ivpu_pll_enable(struct ivpu_device *vdev)
-{
-	return ivpu_pll_drive(vdev, true);
-}
-
-static int ivpu_pll_disable(struct ivpu_device *vdev)
-{
-	return ivpu_pll_drive(vdev, false);
-}
-
-static void ivpu_boot_host_ss_rst_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_CPR_RST_EN);
-
-	if (enable) {
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, TOP_NOC, val);
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, DSS_MAS, val);
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, CSS_MAS, val);
-	} else {
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, TOP_NOC, val);
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, DSS_MAS, val);
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, CSS_MAS, val);
-	}
-
-	REGV_WR32(VPU_40XX_HOST_SS_CPR_RST_EN, val);
-}
-
-static void ivpu_boot_host_ss_clk_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_CPR_CLK_EN);
-
-	if (enable) {
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, TOP_NOC, val);
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, DSS_MAS, val);
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, CSS_MAS, val);
-	} else {
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, TOP_NOC, val);
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, DSS_MAS, val);
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, CSS_MAS, val);
-	}
-
-	REGV_WR32(VPU_40XX_HOST_SS_CPR_CLK_EN, val);
-}
-
-static int ivpu_boot_noc_qreqn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QREQN);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QACCEPTN);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QACCEPTN, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QDENY);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QDENY, TOP_SOCMMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qrenqn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QREQN);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QACCEPTN);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QACCEPTN, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QACCEPTN, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_top_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QDENY);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QDENY, CPU_CTRL, exp_val, val) ||
-	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QDENY, HOSTIF_L2CACHE, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static void ivpu_boot_idle_gen_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_IDLE_GEN);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_IDLE_GEN, EN, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_IDLE_GEN, EN, val);
-
-	REGV_WR32(VPU_40XX_HOST_SS_AON_IDLE_GEN, val);
-}
-
-static int ivpu_boot_host_ss_check(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_boot_noc_qreqn_check(vdev, 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qreqn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_noc_qacceptn_check(vdev, 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_noc_qdeny_check(vdev, 0x0);
-	if (ret)
-		ivpu_err(vdev, "Failed qdeny check %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_boot_host_ss_axi_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QREQN);
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
-	REGV_WR32(VPU_40XX_HOST_SS_NOC_QREQN, val);
-
-	ret = ivpu_boot_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_noc_qdeny_check(vdev, 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
-		return ret;
-	}
-
-	if (enable) {
-		REGB_WR32(VPU_40XX_BUTTRESS_PORT_ARBITRATION_WEIGHTS, WEIGHTS_DEFAULT);
-		REGB_WR32(VPU_40XX_BUTTRESS_PORT_ARBITRATION_WEIGHTS_ATS, WEIGHTS_ATS_DEFAULT);
-	}
-
-	return ret;
-}
-
-static int ivpu_boot_host_ss_axi_enable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_axi_drive(vdev, true);
-}
-
-static int ivpu_boot_host_ss_top_noc_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	val = REGV_RD32(VPU_40XX_TOP_NOC_QREQN);
-	if (enable) {
-		val = REG_SET_FLD(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, val);
-		val = REG_SET_FLD(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
-	} else {
-		val = REG_CLR_FLD(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, val);
-		val = REG_CLR_FLD(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
-	}
-	REGV_WR32(VPU_40XX_TOP_NOC_QREQN, val);
-
-	ret = ivpu_boot_top_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_top_noc_qdeny_check(vdev, 0x0);
-	if (ret)
-		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_boot_host_ss_top_noc_enable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_top_noc_drive(vdev, true);
-}
-
-static void ivpu_boot_pwr_island_trickle_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, CSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, CSS_CPU, val);
-
-	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, val);
-
-	if (enable)
-		ndelay(500);
-}
-
-static void ivpu_boot_pwr_island_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, CSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, CSS_CPU, val);
-
-	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, val);
-
-	if (!enable)
-		ndelay(500);
-}
-
-static int ivpu_boot_wait_for_pwr_island_status(struct ivpu_device *vdev, u32 exp_val)
-{
-	if (ivpu_is_fpga(vdev))
-		return 0;
-
-	return REGV_POLL_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_STATUS0, CSS_CPU,
-			     exp_val, PWR_ISLAND_STATUS_TIMEOUT_US);
-}
-
-static void ivpu_boot_pwr_island_isolation_drive(struct ivpu_device *vdev, bool enable)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0);
-
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, CSS_CPU, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, CSS_CPU, val);
-
-	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, val);
-}
-
-static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
-
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
-
-	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
-}
-
-static void ivpu_boot_tbu_mmu_enable(struct ivpu_device *vdev)
-{
-	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TBU_MMUSSIDV);
-
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU0_AWMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU0_ARMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU1_AWMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU1_ARMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU2_AWMMUSSIDV, val);
-	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU2_ARMMUSSIDV, val);
-
-	REGV_WR32(VPU_40XX_HOST_IF_TBU_MMUSSIDV, val);
-}
-
-static int ivpu_boot_cpu_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QACCEPTN);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_CPU_SS_CPR_NOC_QACCEPTN, TOP_MMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_cpu_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
-{
-	u32 val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QDENY);
-
-	if (!REG_TEST_FLD_NUM(VPU_40XX_CPU_SS_CPR_NOC_QDENY, TOP_MMIO, exp_val, val))
-		return -EIO;
-
-	return 0;
-}
-
-static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_wait_for_clock_own_resource_ack(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for clock own resource ACK\n");
-		return ret;
-	}
-
-	ivpu_boot_pwr_island_trickle_drive(vdev, true);
-	ivpu_boot_pwr_island_drive(vdev, true);
-
-	ret = ivpu_boot_wait_for_pwr_island_status(vdev, 0x1);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for power island status\n");
-		return ret;
-	}
-
-	ret = ivpu_boot_top_noc_qrenqn_check(vdev, 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qrenqn check %d\n", ret);
-		return ret;
-	}
-
-	ivpu_boot_host_ss_clk_drive(vdev, true);
-	ivpu_boot_host_ss_rst_drive(vdev, true);
-	ivpu_boot_pwr_island_isolation_drive(vdev, false);
-
-	return ret;
-}
-
-static int ivpu_boot_soc_cpu_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QREQN);
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_CPU_SS_CPR_NOC_QREQN, TOP_MMIO, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_CPU_SS_CPR_NOC_QREQN, TOP_MMIO, val);
-	REGV_WR32(VPU_40XX_CPU_SS_CPR_NOC_QREQN, val);
-
-	ret = ivpu_boot_cpu_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
-	if (ret) {
-		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_cpu_noc_qdeny_check(vdev, 0x0);
-	if (ret)
-		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_boot_soc_cpu_enable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_soc_cpu_drive(vdev, true);
-}
-
-static int ivpu_boot_soc_cpu_boot(struct ivpu_device *vdev)
-{
-	int ret;
-	u32 val;
-	u64 val64;
-
-	ret = ivpu_boot_soc_cpu_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable SOC CPU: %d\n", ret);
-		return ret;
-	}
-
-	val64 = vdev->fw->entry_point;
-	val64 <<= ffs(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO_IMAGE_LOCATION_MASK) - 1;
-	REGV_WR64(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, val64);
-
-	val = REGV_RD32(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO);
-	val = REG_SET_FLD(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, DONE, val);
-	REGV_WR32(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, val);
-
-	ivpu_dbg(vdev, PM, "Booting firmware, mode: %s\n",
-		 ivpu_fw_is_cold_boot(vdev) ? "cold boot" : "resume");
-
-	return 0;
-}
-
-static int ivpu_boot_d0i3_drive(struct ivpu_device *vdev, bool enable)
-{
-	int ret;
-	u32 val;
-
-	ret = REGB_POLL_FLD(VPU_40XX_BUTTRESS_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Failed to sync before D0i3 transition: %d\n", ret);
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_D0I3_CONTROL);
-	if (enable)
-		val = REG_SET_FLD(VPU_40XX_BUTTRESS_D0I3_CONTROL, I3, val);
-	else
-		val = REG_CLR_FLD(VPU_40XX_BUTTRESS_D0I3_CONTROL, I3, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_D0I3_CONTROL, val);
-
-	ret = REGB_POLL_FLD(VPU_40XX_BUTTRESS_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Failed to sync after D0i3 transition: %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static bool ivpu_tile_disable_check(u32 config)
-{
-	/* Allowed values: 0 or one bit from range 0-5 (6 tiles) */
-	if (config == 0)
-		return true;
-
-	if (config > BIT(TILE_MAX_NUM - 1))
-		return false;
-
-	if ((config & (config - 1)) == 0)
-		return true;
-
-	return false;
-}
-
-static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-	u32 tile_disable;
-	u32 tile_enable;
-	u32 fuse;
-
-	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
-	if (!REG_TEST_FLD(VPU_40XX_BUTTRESS_TILE_FUSE, VALID, fuse)) {
-		ivpu_err(vdev, "Fuse: invalid (0x%x)\n", fuse);
-		return -EIO;
-	}
-
-	tile_disable = REG_GET_FLD(VPU_40XX_BUTTRESS_TILE_FUSE, CONFIG, fuse);
-	if (!ivpu_tile_disable_check(tile_disable)) {
-		ivpu_err(vdev, "Fuse: Invalid tile disable config (0x%x)\n", tile_disable);
-		return -EIO;
-	}
-
-	if (tile_disable)
-		ivpu_dbg(vdev, MISC, "Fuse: %d tiles enabled. Tile number %d disabled\n",
-			 TILE_MAX_NUM - 1, ffs(tile_disable) - 1);
-	else
-		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
-
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
-	hw->tile_fuse = tile_disable;
-	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
-
-	ivpu_pll_init_frequency_ratios(vdev);
-
-	ivpu_hw_init_range(&vdev->hw->ranges.global, 0x80000000, SZ_512M);
-	ivpu_hw_init_range(&vdev->hw->ranges.user,   0x80000000, SZ_256M);
-	ivpu_hw_init_range(&vdev->hw->ranges.shave,  0x80000000 + SZ_256M, SZ_2G - SZ_256M);
-	ivpu_hw_init_range(&vdev->hw->ranges.dma,   0x200000000, SZ_8G);
-
-	ivpu_hw_read_platform(vdev);
-	ivpu_hw_wa_init(vdev);
-	ivpu_hw_timeouts_init(vdev);
-
-	return 0;
-}
-
-static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
-{
-	int ret;
-	u32 val;
-
-	ret = REGB_POLL_FLD(VPU_40XX_BUTTRESS_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Wait for *_TRIGGER timed out\n");
-		return ret;
-	}
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_IP_RESET);
-	val = REG_SET_FLD(VPU_40XX_BUTTRESS_IP_RESET, TRIGGER, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_IP_RESET, val);
-
-	ret = REGB_POLL_FLD(VPU_40XX_BUTTRESS_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
-
-	return ret;
-}
-
-static int ivpu_hw_40xx_d0i3_enable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
-
-	ret = ivpu_boot_d0i3_drive(vdev, true);
-	if (ret)
-		ivpu_err(vdev, "Failed to enable D0i3: %d\n", ret);
-
-	udelay(5); /* VPU requires 5 us to complete the transition */
-
-	return ret;
-}
-
-static int ivpu_hw_40xx_d0i3_disable(struct ivpu_device *vdev)
-{
-	int ret;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
-
-	ret = ivpu_boot_d0i3_drive(vdev, false);
-	if (ret)
-		ivpu_err(vdev, "Failed to disable D0i3: %d\n", ret);
-
-	return ret;
-}
-
-static void ivpu_hw_40xx_profiling_freq_reg_set(struct ivpu_device *vdev)
-{
-	u32 val = REGB_RD32(VPU_40XX_BUTTRESS_VPU_STATUS);
-
-	if (vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_DEFAULT)
-		val = REG_CLR_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, PERF_CLK, val);
-	else
-		val = REG_SET_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, PERF_CLK, val);
-
-	REGB_WR32(VPU_40XX_BUTTRESS_VPU_STATUS, val);
-}
-
-static void ivpu_hw_40xx_ats_print(struct ivpu_device *vdev)
-{
-	ivpu_dbg(vdev, MISC, "Buttress ATS: %s\n",
-		 REGB_RD32(VPU_40XX_BUTTRESS_HM_ATS) ? "Enable" : "Disable");
-}
-
-static void ivpu_hw_40xx_clock_relinquish_disable(struct ivpu_device *vdev)
-{
-	u32 val = REGB_RD32(VPU_40XX_BUTTRESS_VPU_STATUS);
-
-	val = REG_SET_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, DISABLE_CLK_RELINQUISH, val);
-	REGB_WR32(VPU_40XX_BUTTRESS_VPU_STATUS, val);
-}
-
-static int ivpu_hw_40xx_power_up(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_hw_40xx_reset(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to reset HW: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_hw_40xx_d0i3_disable(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
-
-	ret = ivpu_pll_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable PLL: %d\n", ret);
-		return ret;
-	}
-
-	if (IVPU_WA(disable_clock_relinquish))
-		ivpu_hw_40xx_clock_relinquish_disable(vdev);
-	ivpu_hw_40xx_profiling_freq_reg_set(vdev);
-	ivpu_hw_40xx_ats_print(vdev);
-
-	ret = ivpu_boot_host_ss_check(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to configure host SS: %d\n", ret);
-		return ret;
-	}
-
-	ivpu_boot_idle_gen_drive(vdev, false);
-
-	ret = ivpu_boot_pwr_domain_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable power domain: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_host_ss_axi_enable(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to enable AXI: %d\n", ret);
-		return ret;
-	}
-
-	ret = ivpu_boot_host_ss_top_noc_enable(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to enable TOP NOC: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_hw_40xx_boot_fw(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ivpu_boot_no_snoop_enable(vdev);
-	ivpu_boot_tbu_mmu_enable(vdev);
-
-	ret = ivpu_boot_soc_cpu_boot(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to boot SOC CPU: %d\n", ret);
-
-	return ret;
-}
-
-static bool ivpu_hw_40xx_is_idle(struct ivpu_device *vdev)
-{
-	u32 val;
-
-	if (IVPU_WA(punit_disabled))
-		return true;
-
-	val = REGB_RD32(VPU_40XX_BUTTRESS_VPU_STATUS);
-	return REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, READY, val) &&
-	       REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, val);
-}
-
-static int ivpu_hw_40xx_power_down(struct ivpu_device *vdev)
-{
-	int ret = 0;
-
-	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_reset(vdev))
-		ivpu_warn(vdev, "Failed to reset the VPU\n");
-
-	if (ivpu_pll_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable PLL\n");
-		ret = -EIO;
-	}
-
-	if (ivpu_hw_40xx_d0i3_enable(vdev)) {
-		ivpu_err(vdev, "Failed to enter D0I3\n");
-		ret = -EIO;
-	}
-
-	return ret;
-}
-
-static void ivpu_hw_40xx_wdt_disable(struct ivpu_device *vdev)
-{
-	u32 val;
-
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_WATCHDOG, TIM_WATCHDOG_RESET_VALUE);
-
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_WDOG_EN, 0);
-
-	val = REGV_RD32(VPU_40XX_CPU_SS_TIM_GEN_CONFIG);
-	val = REG_CLR_FLD(VPU_40XX_CPU_SS_TIM_GEN_CONFIG, WDOG_TO_INT_CLR, val);
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_GEN_CONFIG, val);
-}
-
-/* Register indirect accesses */
-static u32 ivpu_hw_40xx_reg_pll_freq_get(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_40XX_BUTTRESS_PLL_FREQ);
-	pll_curr_ratio &= VPU_40XX_BUTTRESS_PLL_FREQ_RATIO_MASK;
-
-	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
-}
-
-static u32 ivpu_hw_40xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET);
-}
-
-static u32 ivpu_hw_40xx_reg_telemetry_size_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_SIZE);
-}
-
-static u32 ivpu_hw_40xx_reg_telemetry_enable_get(struct ivpu_device *vdev)
-{
-	return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_ENABLE);
-}
-
-static void ivpu_hw_40xx_reg_db_set(struct ivpu_device *vdev, u32 db_id)
-{
-	u32 reg_stride = VPU_40XX_CPU_SS_DOORBELL_1 - VPU_40XX_CPU_SS_DOORBELL_0;
-	u32 val = REG_FLD(VPU_40XX_CPU_SS_DOORBELL_0, SET);
-
-	REGV_WR32I(VPU_40XX_CPU_SS_DOORBELL_0, reg_stride, db_id, val);
-}
-
-static u32 ivpu_hw_40xx_reg_ipc_rx_addr_get(struct ivpu_device *vdev)
-{
-	return REGV_RD32(VPU_40XX_HOST_SS_TIM_IPC_FIFO_ATM);
-}
-
-static u32 ivpu_hw_40xx_reg_ipc_rx_count_get(struct ivpu_device *vdev)
-{
-	u32 count = REGV_RD32_SILENT(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT);
-
-	return REG_GET_FLD(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
-}
-
-static void ivpu_hw_40xx_reg_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
-{
-	REGV_WR32(VPU_40XX_CPU_SS_TIM_IPC_FIFO, vpu_addr);
-}
-
-static void ivpu_hw_40xx_irq_clear(struct ivpu_device *vdev)
-{
-	REGV_WR64(VPU_40XX_HOST_SS_ICB_CLEAR_0, ICB_0_1_IRQ_MASK);
-}
-
-static void ivpu_hw_40xx_irq_enable(struct ivpu_device *vdev)
-{
-	REGV_WR32(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, ITF_FIREWALL_VIOLATION_MASK);
-	REGV_WR64(VPU_40XX_HOST_SS_ICB_ENABLE_0, ICB_0_1_IRQ_MASK);
-	REGB_WR32(VPU_40XX_BUTTRESS_LOCAL_INT_MASK, BUTTRESS_IRQ_ENABLE_MASK);
-	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-}
-
-static void ivpu_hw_40xx_irq_disable(struct ivpu_device *vdev)
-{
-	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-	REGB_WR32(VPU_40XX_BUTTRESS_LOCAL_INT_MASK, BUTTRESS_IRQ_DISABLE_MASK);
-	REGV_WR64(VPU_40XX_HOST_SS_ICB_ENABLE_0, 0x0ull);
-	REGV_WR32(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, 0x0ul);
-}
-
-static void ivpu_hw_40xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
-{
-	/* TODO: For LNN hang consider engine reset instead of full recovery */
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-static void ivpu_hw_40xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
-{
-	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-static void ivpu_hw_40xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
-{
-	ivpu_pm_schedule_recovery(vdev);
-}
-
-/* Handler for IRQs from VPU core (irqV) */
-static irqreturn_t ivpu_hw_40xx_irqv_handler(struct ivpu_device *vdev, int irq)
-{
-	u32 status = REGV_RD32(VPU_40XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
-	irqreturn_t ret = IRQ_NONE;
-
-	if (!status)
-		return IRQ_NONE;
-
-	REGV_WR32(VPU_40XX_HOST_SS_ICB_CLEAR_0, status);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
-		ivpu_mmu_irq_evtq_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
-		ret |= ivpu_ipc_irq_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
-		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT, status))
-		ivpu_mmu_irq_gerr_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, status))
-		ivpu_hw_40xx_irq_wdt_mss_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, status))
-		ivpu_hw_40xx_irq_wdt_nce_handler(vdev);
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
-		ivpu_hw_40xx_irq_noc_firewall_handler(vdev);
-
-	return ret;
-}
-
-/* Handler for IRQs from Buttress core (irqB) */
-static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
-{
-	bool schedule_recovery = false;
-	u32 status = REGB_RD32(VPU_40XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
-
-	if (status == 0)
-		return IRQ_NONE;
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE");
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR, status)) {
-		ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
-			 REGB_RD32(VPU_40XX_BUTTRESS_ATS_ERR_LOG1),
-			 REGB_RD32(VPU_40XX_BUTTRESS_ATS_ERR_LOG2));
-		REGB_WR32(VPU_40XX_BUTTRESS_ATS_ERR_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI0_ERR, status)) {
-		ivpu_err(vdev, "CFI0_ERR 0x%08x", REGB_RD32(VPU_40XX_BUTTRESS_CFI0_ERR_LOG));
-		REGB_WR32(VPU_40XX_BUTTRESS_CFI0_ERR_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI1_ERR, status)) {
-		ivpu_err(vdev, "CFI1_ERR 0x%08x", REGB_RD32(VPU_40XX_BUTTRESS_CFI1_ERR_LOG));
-		REGB_WR32(VPU_40XX_BUTTRESS_CFI1_ERR_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR0_ERR, status)) {
-		ivpu_err(vdev, "IMR_ERR_CFI0 LOW: 0x%08x HIGH: 0x%08x",
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI0_LOW),
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI0_HIGH));
-		REGB_WR32(VPU_40XX_BUTTRESS_IMR_ERR_CFI0_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR1_ERR, status)) {
-		ivpu_err(vdev, "IMR_ERR_CFI1 LOW: 0x%08x HIGH: 0x%08x",
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI1_LOW),
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI1_HIGH));
-		REGB_WR32(VPU_40XX_BUTTRESS_IMR_ERR_CFI1_CLEAR, 0x1);
-		schedule_recovery = true;
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, SURV_ERR, status)) {
-		ivpu_err(vdev, "Survivability error detected\n");
-		schedule_recovery = true;
-	}
-
-	/* This must be done after interrupts are cleared at the source. */
-	REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status);
-
-	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ivpu_hw_40xx_irq_handler(int irq, void *ptr)
-{
-	struct ivpu_device *vdev = ptr;
-	irqreturn_t ret = IRQ_NONE;
-
-	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-
-	ret |= ivpu_hw_40xx_irqv_handler(vdev, irq);
-	ret |= ivpu_hw_40xx_irqb_handler(vdev, irq);
-
-	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
-	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-
-	if (ret & IRQ_WAKE_THREAD)
-		return IRQ_WAKE_THREAD;
-
-	return ret;
-}
-
-static void ivpu_hw_40xx_diagnose_failure(struct ivpu_device *vdev)
-{
-	u32 irqv = REGV_RD32(VPU_40XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
-	u32 irqb = REGB_RD32(VPU_40XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
-
-	if (ivpu_hw_40xx_reg_ipc_rx_count_get(vdev))
-		ivpu_err(vdev, "IPC FIFO queue not empty, missed IPC IRQ");
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, irqv))
-		ivpu_err(vdev, "WDT MSS timeout detected\n");
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, irqv))
-		ivpu_err(vdev, "WDT NCE timeout detected\n");
-
-	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, irqv))
-		ivpu_err(vdev, "NOC Firewall irq detected\n");
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR, irqb)) {
-		ivpu_err(vdev, "ATS_ERR_LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
-			 REGB_RD32(VPU_40XX_BUTTRESS_ATS_ERR_LOG1),
-			 REGB_RD32(VPU_40XX_BUTTRESS_ATS_ERR_LOG2));
-	}
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI0_ERR, irqb))
-		ivpu_err(vdev, "CFI0_ERR_LOG 0x%08x\n", REGB_RD32(VPU_40XX_BUTTRESS_CFI0_ERR_LOG));
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI1_ERR, irqb))
-		ivpu_err(vdev, "CFI1_ERR_LOG 0x%08x\n", REGB_RD32(VPU_40XX_BUTTRESS_CFI1_ERR_LOG));
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR0_ERR, irqb))
-		ivpu_err(vdev, "IMR_ERR_CFI0 LOW: 0x%08x HIGH: 0x%08x\n",
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI0_LOW),
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI0_HIGH));
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR1_ERR, irqb))
-		ivpu_err(vdev, "IMR_ERR_CFI1 LOW: 0x%08x HIGH: 0x%08x\n",
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI1_LOW),
-			 REGB_RD32(VPU_40XX_BUTTRESS_IMR_ERR_CFI1_HIGH));
-
-	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, SURV_ERR, irqb))
-		ivpu_err(vdev, "Survivability error detected\n");
-}
-
-const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
-	.info_init = ivpu_hw_40xx_info_init,
-	.power_up = ivpu_hw_40xx_power_up,
-	.is_idle = ivpu_hw_40xx_is_idle,
-	.power_down = ivpu_hw_40xx_power_down,
-	.reset = ivpu_hw_40xx_reset,
-	.boot_fw = ivpu_hw_40xx_boot_fw,
-	.wdt_disable = ivpu_hw_40xx_wdt_disable,
-	.diagnose_failure = ivpu_hw_40xx_diagnose_failure,
-	.reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get,
-	.reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get,
-	.reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get,
-	.reg_telemetry_enable_get = ivpu_hw_40xx_reg_telemetry_enable_get,
-	.reg_db_set = ivpu_hw_40xx_reg_db_set,
-	.reg_ipc_rx_addr_get = ivpu_hw_40xx_reg_ipc_rx_addr_get,
-	.reg_ipc_rx_count_get = ivpu_hw_40xx_reg_ipc_rx_count_get,
-	.reg_ipc_tx_set = ivpu_hw_40xx_reg_ipc_tx_set,
-	.irq_clear = ivpu_hw_40xx_irq_clear,
-	.irq_enable = ivpu_hw_40xx_irq_enable,
-	.irq_disable = ivpu_hw_40xx_irq_disable,
-	.irq_handler = ivpu_hw_40xx_irq_handler,
-};
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
index ff4a5d4f5821..fc0ee8d637f9 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
@@ -8,91 +8,6 @@
 
 #include <linux/bits.h>
 
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT				0x00000000u
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_FREQ_CHANGE_MASK		BIT_MASK(0)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_ATS_ERR_MASK			BIT_MASK(1)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_CFI0_ERR_MASK			BIT_MASK(2)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_CFI1_ERR_MASK			BIT_MASK(3)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_IMR0_ERR_MASK			BIT_MASK(4)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_IMR1_ERR_MASK			BIT_MASK(5)
-#define VPU_40XX_BUTTRESS_INTERRUPT_STAT_SURV_ERR_MASK			BIT_MASK(6)
-
-#define VPU_40XX_BUTTRESS_LOCAL_INT_MASK				0x00000004u
-#define VPU_40XX_BUTTRESS_GLOBAL_INT_MASK				0x00000008u
-
-#define VPU_40XX_BUTTRESS_HM_ATS					0x0000000cu
-
-#define VPU_40XX_BUTTRESS_ATS_ERR_LOG1					0x00000010u
-#define VPU_40XX_BUTTRESS_ATS_ERR_LOG2					0x00000014u
-#define VPU_40XX_BUTTRESS_ATS_ERR_CLEAR					0x00000018u
-
-#define VPU_40XX_BUTTRESS_CFI0_ERR_LOG					0x0000001cu
-#define VPU_40XX_BUTTRESS_CFI0_ERR_CLEAR				0x00000020u
-
-#define VPU_40XX_BUTTRESS_PORT_ARBITRATION_WEIGHTS_ATS			0x00000024u
-
-#define VPU_40XX_BUTTRESS_CFI1_ERR_LOG					0x00000040u
-#define VPU_40XX_BUTTRESS_CFI1_ERR_CLEAR				0x00000044u
-
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI0_LOW				0x00000048u
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI0_HIGH				0x0000004cu
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI0_CLEAR				0x00000050u
-
-#define VPU_40XX_BUTTRESS_PORT_ARBITRATION_WEIGHTS			0x00000054u
-
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI1_LOW				0x00000058u
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI1_HIGH				0x0000005cu
-#define VPU_40XX_BUTTRESS_IMR_ERR_CFI1_CLEAR				0x00000060u
-
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0				0x00000130u
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0_MIN_RATIO_MASK		GENMASK(15, 0)
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD0_MAX_RATIO_MASK		GENMASK(31, 16)
-
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1				0x00000134u
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1_TARGET_RATIO_MASK		GENMASK(15, 0)
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD1_EPP_MASK			GENMASK(31, 16)
-
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2				0x00000138u
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2_CONFIG_MASK			GENMASK(15, 0)
-#define VPU_40XX_BUTTRESS_WP_REQ_PAYLOAD2_CDYN_MASK			GENMASK(31, 16)
-
-#define VPU_40XX_BUTTRESS_WP_REQ_CMD					0x0000013cu
-#define VPU_40XX_BUTTRESS_WP_REQ_CMD_SEND_MASK				BIT_MASK(0)
-
-#define VPU_40XX_BUTTRESS_PLL_FREQ					0x00000148u
-#define VPU_40XX_BUTTRESS_PLL_FREQ_RATIO_MASK				GENMASK(15, 0)
-
-#define VPU_40XX_BUTTRESS_TILE_FUSE					0x00000150u
-#define VPU_40XX_BUTTRESS_TILE_FUSE_VALID_MASK				BIT_MASK(0)
-#define VPU_40XX_BUTTRESS_TILE_FUSE_CONFIG_MASK				GENMASK(6, 1)
-
-#define VPU_40XX_BUTTRESS_VPU_STATUS					0x00000154u
-#define VPU_40XX_BUTTRESS_VPU_STATUS_READY_MASK				BIT_MASK(0)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_IDLE_MASK				BIT_MASK(1)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_DUP_IDLE_MASK			BIT_MASK(2)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_CLOCK_RESOURCE_OWN_ACK_MASK	BIT_MASK(6)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_POWER_RESOURCE_OWN_ACK_MASK	BIT_MASK(7)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_PERF_CLK_MASK			BIT_MASK(11)
-#define VPU_40XX_BUTTRESS_VPU_STATUS_DISABLE_CLK_RELINQUISH_MASK        BIT_MASK(12)
-
-#define VPU_40XX_BUTTRESS_IP_RESET					0x00000160u
-#define VPU_40XX_BUTTRESS_IP_RESET_TRIGGER_MASK				BIT_MASK(0)
-
-#define VPU_40XX_BUTTRESS_D0I3_CONTROL					0x00000164u
-#define VPU_40XX_BUTTRESS_D0I3_CONTROL_INPROGRESS_MASK			BIT_MASK(0)
-#define VPU_40XX_BUTTRESS_D0I3_CONTROL_I3_MASK				BIT_MASK(2)
-
-#define VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET				0x00000168u
-#define VPU_40XX_BUTTRESS_VPU_TELEMETRY_SIZE				0x0000016cu
-#define VPU_40XX_BUTTRESS_VPU_TELEMETRY_ENABLE				0x00000170u
-
-#define VPU_40XX_BUTTRESS_FMIN_FUSE					0x00000174u
-#define VPU_40XX_BUTTRESS_FMIN_FUSE_MIN_RATIO_MASK			GENMASK(7, 0)
-#define VPU_40XX_BUTTRESS_FMIN_FUSE_PN_RATIO_MASK			GENMASK(15, 8)
-
-#define VPU_40XX_BUTTRESS_FMAX_FUSE					0x00000178u
-#define VPU_40XX_BUTTRESS_FMAX_FUSE_MAX_RATIO_MASK			GENMASK(7, 0)
-
 #define VPU_40XX_HOST_SS_CPR_CLK_EN					0x00000080u
 #define VPU_40XX_HOST_SS_CPR_CLK_EN_TOP_NOC_MASK			BIT_MASK(1)
 #define VPU_40XX_HOST_SS_CPR_CLK_EN_DSS_MAS_MASK			BIT_MASK(10)
@@ -198,6 +113,14 @@
 #define VPU_40XX_HOST_SS_AON_PWR_ISLAND_STATUS0				0x0003002cu
 #define VPU_40XX_HOST_SS_AON_PWR_ISLAND_STATUS0_CSS_CPU_MASK		BIT_MASK(3)
 
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY			0x00030068u
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST_DLY_MASK	GENMASK(7, 0)
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST1_DLY_MASK	GENMASK(15, 8)
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST2_DLY_MASK	GENMASK(23, 16)
+
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY			0x0003006cu
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK	GENMASK(7, 0)
+
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN					0x00030200u
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN_EN_MASK				BIT_MASK(0)
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN_HW_PG_EN_MASK			BIT_MASK(1)
@@ -205,6 +128,9 @@
 #define VPU_40XX_HOST_SS_AON_DPU_ACTIVE					0x00030204u
 #define VPU_40XX_HOST_SS_AON_DPU_ACTIVE_DPU_ACTIVE_MASK			BIT_MASK(0)
 
+#define VPU_50XX_HOST_SS_AON_FABRIC_REQ_OVERRIDE			0x00030210u
+#define VPU_50XX_HOST_SS_AON_FABRIC_REQ_OVERRIDE_REQ_OVERRIDE_MASK      BIT_MASK(0)
+
 #define VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO			0x00040040u
 #define VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO_DONE_MASK		BIT_MASK(0)
 #define VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO_IOSF_RS_ID_MASK	GENMASK(2, 1)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c
new file mode 100644
index 000000000000..afdb3b2aa72a
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.c
@@ -0,0 +1,889 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2025 Intel Corporation
+ */
+
+#include <linux/units.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_hw.h"
+#include "ivpu_hw_btrs.h"
+#include "ivpu_hw_btrs_lnl_reg.h"
+#include "ivpu_hw_btrs_mtl_reg.h"
+#include "ivpu_hw_reg_io.h"
+#include "ivpu_pm.h"
+
+#define BTRS_MTL_IRQ_MASK ((REG_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, UFI_ERR)))
+
+#define BTRS_LNL_IRQ_MASK ((REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI0_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI1_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR0_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR1_ERR)) | \
+			   (REG_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, SURV_ERR)))
+
+#define BTRS_MTL_ALL_IRQ_MASK (BTRS_MTL_IRQ_MASK | (REG_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, \
+			       FREQ_CHANGE)))
+
+#define BTRS_IRQ_DISABLE_MASK ((u32)-1)
+
+#define BTRS_LNL_ALL_IRQ_MASK ((u32)-1)
+
+
+#define PLL_CDYN_DEFAULT               0x80
+#define PLL_EPP_DEFAULT                0x80
+#define PLL_REF_CLK_FREQ               50000000ull
+#define PLL_RATIO_TO_FREQ(x)           ((x) * PLL_REF_CLK_FREQ)
+
+#define PLL_TIMEOUT_US		       (1500 * USEC_PER_MSEC)
+#define IDLE_TIMEOUT_US		       (5 * USEC_PER_MSEC)
+#define TIMEOUT_US                     (150 * USEC_PER_MSEC)
+
+/* Work point configuration values */
+#define WP_CONFIG(tile, ratio)         (((tile) << 8) | (ratio))
+#define MTL_CONFIG_1_TILE              0x01
+#define MTL_CONFIG_2_TILE              0x02
+#define MTL_PLL_RATIO_5_3              0x01
+#define MTL_PLL_RATIO_4_3              0x02
+#define BTRS_MTL_TILE_FUSE_ENABLE_BOTH 0x0
+#define BTRS_MTL_TILE_SKU_BOTH         0x3630
+
+#define BTRS_LNL_TILE_MAX_NUM          6
+#define BTRS_LNL_TILE_MAX_MASK         0x3f
+
+#define WEIGHTS_DEFAULT                0xf711f711u
+#define WEIGHTS_ATS_DEFAULT            0x0000f711u
+
+#define DCT_REQ                        0x2
+#define DCT_ENABLE                     0x1
+#define DCT_DISABLE                    0x0
+
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio);
+
+int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev)
+{
+	REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, BTRS_MTL_ALL_IRQ_MASK);
+	if (REGB_RD32(VPU_HW_BTRS_MTL_INTERRUPT_STAT) == BTRS_MTL_ALL_IRQ_MASK) {
+		/* Writing 1s does not clear the interrupt status register */
+		REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, 0x0);
+		return true;
+	}
+
+	return false;
+}
+
+static void freq_ratios_init_mtl(struct ivpu_device *vdev)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+	u32 fmin_fuse, fmax_fuse;
+
+	fmin_fuse = REGB_RD32(VPU_HW_BTRS_MTL_FMIN_FUSE);
+	hw->pll.min_ratio = REG_GET_FLD(VPU_HW_BTRS_MTL_FMIN_FUSE, MIN_RATIO, fmin_fuse);
+	hw->pll.pn_ratio = REG_GET_FLD(VPU_HW_BTRS_MTL_FMIN_FUSE, PN_RATIO, fmin_fuse);
+
+	fmax_fuse = REGB_RD32(VPU_HW_BTRS_MTL_FMAX_FUSE);
+	hw->pll.max_ratio = REG_GET_FLD(VPU_HW_BTRS_MTL_FMAX_FUSE, MAX_RATIO, fmax_fuse);
+}
+
+static void freq_ratios_init_lnl(struct ivpu_device *vdev)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+	u32 fmin_fuse, fmax_fuse;
+
+	fmin_fuse = REGB_RD32(VPU_HW_BTRS_LNL_FMIN_FUSE);
+	hw->pll.min_ratio = REG_GET_FLD(VPU_HW_BTRS_LNL_FMIN_FUSE, MIN_RATIO, fmin_fuse);
+	hw->pll.pn_ratio = REG_GET_FLD(VPU_HW_BTRS_LNL_FMIN_FUSE, PN_RATIO, fmin_fuse);
+
+	fmax_fuse = REGB_RD32(VPU_HW_BTRS_LNL_FMAX_FUSE);
+	hw->pll.max_ratio = REG_GET_FLD(VPU_HW_BTRS_LNL_FMAX_FUSE, MAX_RATIO, fmax_fuse);
+}
+
+void ivpu_hw_btrs_freq_ratios_init(struct ivpu_device *vdev)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		freq_ratios_init_mtl(vdev);
+	else
+		freq_ratios_init_lnl(vdev);
+
+	hw->pll.min_ratio = clamp_t(u8, ivpu_pll_min_ratio, hw->pll.min_ratio, hw->pll.max_ratio);
+	hw->pll.max_ratio = clamp_t(u8, ivpu_pll_max_ratio, hw->pll.min_ratio, hw->pll.max_ratio);
+	hw->pll.pn_ratio = clamp_t(u8, hw->pll.pn_ratio, hw->pll.min_ratio, hw->pll.max_ratio);
+}
+
+static bool tile_disable_check(u32 config)
+{
+	/* Allowed values: 0 or one bit from range 0-5 (6 tiles) */
+	if (config == 0)
+		return true;
+
+	if (config > BIT(BTRS_LNL_TILE_MAX_NUM - 1))
+		return false;
+
+	if ((config & (config - 1)) == 0)
+		return true;
+
+	return false;
+}
+
+static int read_tile_config_fuse(struct ivpu_device *vdev, u32 *tile_fuse_config)
+{
+	u32 fuse;
+	u32 config;
+
+	fuse = REGB_RD32(VPU_HW_BTRS_LNL_TILE_FUSE);
+	if (!REG_TEST_FLD(VPU_HW_BTRS_LNL_TILE_FUSE, VALID, fuse)) {
+		ivpu_err(vdev, "Fuse: invalid (0x%x)\n", fuse);
+		return -EIO;
+	}
+
+	config = REG_GET_FLD(VPU_HW_BTRS_LNL_TILE_FUSE, CONFIG, fuse);
+	if (!tile_disable_check(config))
+		ivpu_warn(vdev, "More than 1 tile disabled, tile fuse config mask: 0x%x\n", config);
+
+	ivpu_dbg(vdev, MISC, "Tile disable config mask: 0x%x\n", config);
+
+	*tile_fuse_config = config;
+	return 0;
+}
+
+static int info_init_mtl(struct ivpu_device *vdev)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+
+	hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH;
+	hw->sku = BTRS_MTL_TILE_SKU_BOTH;
+	hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3);
+
+	return 0;
+}
+
+static int info_init_lnl(struct ivpu_device *vdev)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+	u32 tile_fuse_config;
+	int ret;
+
+	ret = read_tile_config_fuse(vdev, &tile_fuse_config);
+	if (ret)
+		return ret;
+
+	hw->tile_fuse = tile_fuse_config;
+	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
+
+	return 0;
+}
+
+int ivpu_hw_btrs_info_init(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return info_init_mtl(vdev);
+	else
+		return info_init_lnl(vdev);
+}
+
+static int wp_request_sync(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_POLL_FLD(VPU_HW_BTRS_MTL_WP_REQ_CMD, SEND, 0, PLL_TIMEOUT_US);
+	else
+		return REGB_POLL_FLD(VPU_HW_BTRS_LNL_WP_REQ_CMD, SEND, 0, PLL_TIMEOUT_US);
+}
+
+static int wait_for_status_ready(struct ivpu_device *vdev, bool enable)
+{
+	u32 exp_val = enable ? 0x1 : 0x0;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_STATUS, READY, exp_val, PLL_TIMEOUT_US);
+	else
+		return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, READY, exp_val, PLL_TIMEOUT_US);
+}
+
+struct wp_request {
+	u16 min;
+	u16 max;
+	u16 target;
+	u16 cfg;
+	u16 epp;
+	u16 cdyn;
+};
+
+static void wp_request_mtl(struct ivpu_device *vdev, struct wp_request *wp)
+{
+	u32 val;
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0, MIN_RATIO, wp->min, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0, MAX_RATIO, wp->max, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1, TARGET_RATIO, wp->target, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1, EPP, PLL_EPP_DEFAULT, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD2);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD2, CONFIG, wp->cfg, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD2, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_WP_REQ_CMD);
+	val = REG_SET_FLD(VPU_HW_BTRS_MTL_WP_REQ_CMD, SEND, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_WP_REQ_CMD, val);
+}
+
+static void wp_request_lnl(struct ivpu_device *vdev, struct wp_request *wp)
+{
+	u32 val;
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0, MIN_RATIO, wp->min, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0, MAX_RATIO, wp->max, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1, TARGET_RATIO, wp->target, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1, EPP, wp->epp, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2, CONFIG, wp->cfg, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2, CDYN, wp->cdyn, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2, val);
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_WP_REQ_CMD);
+	val = REG_SET_FLD(VPU_HW_BTRS_LNL_WP_REQ_CMD, SEND, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_WP_REQ_CMD, val);
+}
+
+static void wp_request(struct ivpu_device *vdev, struct wp_request *wp)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		wp_request_mtl(vdev, wp);
+	else
+		wp_request_lnl(vdev, wp);
+}
+
+static int wp_request_send(struct ivpu_device *vdev, struct wp_request *wp)
+{
+	int ret;
+
+	ret = wp_request_sync(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to sync before workpoint request: %d\n", ret);
+		return ret;
+	}
+
+	wp_request(vdev, wp);
+
+	ret = wp_request_sync(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to sync after workpoint request: %d\n", ret);
+
+	return ret;
+}
+
+static void prepare_wp_request(struct ivpu_device *vdev, struct wp_request *wp, bool enable)
+{
+	struct ivpu_hw_info *hw = vdev->hw;
+
+	wp->min = hw->pll.min_ratio;
+	wp->max = hw->pll.max_ratio;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) {
+		wp->target = enable ? hw->pll.pn_ratio : 0;
+		wp->cfg = enable ? hw->config : 0;
+		wp->cdyn = 0;
+		wp->epp = 0;
+	} else {
+		wp->target = hw->pll.pn_ratio;
+		wp->cfg = 0;
+		wp->cdyn = enable ? PLL_CDYN_DEFAULT : 0;
+		wp->epp = enable ? PLL_EPP_DEFAULT : 0;
+	}
+}
+
+static int wait_for_pll_lock(struct ivpu_device *vdev, bool enable)
+{
+	u32 exp_val = enable ? 0x1 : 0x0;
+
+	if (ivpu_hw_btrs_gen(vdev) != IVPU_HW_BTRS_MTL)
+		return 0;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	return REGB_POLL_FLD(VPU_HW_BTRS_MTL_PLL_STATUS, LOCK, exp_val, PLL_TIMEOUT_US);
+}
+
+int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable)
+{
+	struct wp_request wp;
+	int ret;
+
+	if (IVPU_WA(punit_disabled)) {
+		ivpu_dbg(vdev, PM, "Skipping workpoint request\n");
+		return 0;
+	}
+
+	prepare_wp_request(vdev, &wp, enable);
+
+	ivpu_dbg(vdev, PM, "PLL workpoint request: %lu MHz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
+		 pll_ratio_to_dpu_freq(vdev, wp.target) / HZ_PER_MHZ, wp.cfg, wp.epp, wp.cdyn);
+
+	ret = wp_request_send(vdev, &wp);
+	if (ret) {
+		ivpu_err(vdev, "Failed to send workpoint request: %d\n", ret);
+		return ret;
+	}
+
+	ret = wait_for_pll_lock(vdev, enable);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for PLL lock\n");
+		return ret;
+	}
+
+	ret = wait_for_status_ready(vdev, enable);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for NPU ready status\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int d0i3_drive_mtl(struct ivpu_device *vdev, bool enable)
+{
+	int ret;
+	u32 val;
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Failed to sync before D0i3 transition: %d\n", ret);
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL);
+	if (enable)
+		val = REG_SET_FLD(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL, I3, val);
+	else
+		val = REG_CLR_FLD(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL, I3, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL, val);
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Failed to sync after D0i3 transition: %d\n", ret);
+
+	return ret;
+}
+
+static int d0i3_drive_lnl(struct ivpu_device *vdev, bool enable)
+{
+	int ret;
+	u32 val;
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_LNL_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Failed to sync before D0i3 transition: %d\n", ret);
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_D0I3_CONTROL);
+	if (enable)
+		val = REG_SET_FLD(VPU_HW_BTRS_LNL_D0I3_CONTROL, I3, val);
+	else
+		val = REG_CLR_FLD(VPU_HW_BTRS_LNL_D0I3_CONTROL, I3, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_D0I3_CONTROL, val);
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_LNL_D0I3_CONTROL, INPROGRESS, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Failed to sync after D0i3 transition: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int d0i3_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return d0i3_drive_mtl(vdev, enable);
+	else
+		return d0i3_drive_lnl(vdev, enable);
+}
+
+int ivpu_hw_btrs_d0i3_enable(struct ivpu_device *vdev)
+{
+	int ret;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = d0i3_drive(vdev, true);
+	if (ret)
+		ivpu_err(vdev, "Failed to enable D0i3: %d\n", ret);
+
+	udelay(5); /* VPU requires 5 us to complete the transition */
+
+	return ret;
+}
+
+int ivpu_hw_btrs_d0i3_disable(struct ivpu_device *vdev)
+{
+	int ret;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = d0i3_drive(vdev, false);
+	if (ret)
+		ivpu_err(vdev, "Failed to disable D0i3: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_hw_btrs_wait_for_clock_res_own_ack(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return 0;
+
+	return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US);
+}
+
+void ivpu_hw_btrs_set_port_arbitration_weights_lnl(struct ivpu_device *vdev)
+{
+	REGB_WR32(VPU_HW_BTRS_LNL_PORT_ARBITRATION_WEIGHTS, WEIGHTS_DEFAULT);
+	REGB_WR32(VPU_HW_BTRS_LNL_PORT_ARBITRATION_WEIGHTS_ATS, WEIGHTS_ATS_DEFAULT);
+}
+
+static int ip_reset_mtl(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_HW_BTRS_MTL_VPU_IP_RESET);
+	val = REG_SET_FLD(VPU_HW_BTRS_MTL_VPU_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_HW_BTRS_MTL_VPU_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
+static int ip_reset_lnl(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	ivpu_hw_btrs_clock_relinquish_disable_lnl(vdev);
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_LNL_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Wait for *_TRIGGER timed out\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_HW_BTRS_LNL_IP_RESET);
+	val = REG_SET_FLD(VPU_HW_BTRS_LNL_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_HW_BTRS_LNL_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
+int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev)
+{
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return ip_reset_mtl(vdev);
+	else
+		return ip_reset_lnl(vdev);
+}
+
+void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev)
+{
+	u32 val = REGB_RD32(VPU_HW_BTRS_LNL_VPU_STATUS);
+
+	if (vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_DEFAULT)
+		val = REG_CLR_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, PERF_CLK, val);
+	else
+		val = REG_SET_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, PERF_CLK, val);
+
+	REGB_WR32(VPU_HW_BTRS_LNL_VPU_STATUS, val);
+}
+
+void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev)
+{
+	ivpu_dbg(vdev, MISC, "Buttress ATS: %s\n",
+		 REGB_RD32(VPU_HW_BTRS_LNL_HM_ATS) ? "Enable" : "Disable");
+}
+
+void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev)
+{
+	u32 val = REGB_RD32(VPU_HW_BTRS_LNL_VPU_STATUS);
+
+	val = REG_SET_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, DISABLE_CLK_RELINQUISH, val);
+	REGB_WR32(VPU_HW_BTRS_LNL_VPU_STATUS, val);
+}
+
+bool ivpu_hw_btrs_is_idle(struct ivpu_device *vdev)
+{
+	u32 val;
+
+	if (IVPU_WA(punit_disabled))
+		return true;
+
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) {
+		val = REGB_RD32(VPU_HW_BTRS_MTL_VPU_STATUS);
+
+		return REG_TEST_FLD(VPU_HW_BTRS_MTL_VPU_STATUS, READY, val) &&
+		       REG_TEST_FLD(VPU_HW_BTRS_MTL_VPU_STATUS, IDLE, val);
+	} else {
+		val = REGB_RD32(VPU_HW_BTRS_LNL_VPU_STATUS);
+
+		return REG_TEST_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, READY, val) &&
+		       REG_TEST_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, val);
+	}
+}
+
+int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_POLL_FLD(VPU_HW_BTRS_MTL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+	else
+		return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+}
+
+static u32 pll_config_get_mtl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
+}
+
+static u32 pll_config_get_lnl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
+}
+
+static u32 pll_ratio_to_dpu_freq_mtl(u16 ratio)
+{
+	return (PLL_RATIO_TO_FREQ(ratio) * 2) / 3;
+}
+
+static u32 pll_ratio_to_dpu_freq_lnl(u16 ratio)
+{
+	return PLL_RATIO_TO_FREQ(ratio) / 2;
+}
+
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return pll_ratio_to_dpu_freq_mtl(ratio);
+	else
+		return pll_ratio_to_dpu_freq_lnl(ratio);
+}
+
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev)
+{
+	return pll_ratio_to_dpu_freq(vdev, vdev->hw->pll.max_ratio);
+}
+
+u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return pll_ratio_to_dpu_freq_mtl(pll_config_get_mtl(vdev));
+	else
+		return pll_ratio_to_dpu_freq_lnl(pll_config_get_lnl(vdev));
+}
+
+/* Handler for IRQs from Buttress core (irqB) */
+bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
+{
+	u32 status = REGB_RD32(VPU_HW_BTRS_MTL_INTERRUPT_STAT) & BTRS_MTL_IRQ_MASK;
+	bool schedule_recovery = false;
+
+	if (!status)
+		return false;
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_mtl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_mtl(pll) / HZ_PER_MHZ);
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, status)) {
+		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0));
+		REGB_WR32(VPU_HW_BTRS_MTL_ATS_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, UFI_ERR, status)) {
+		u32 ufi_log = REGB_RD32(VPU_HW_BTRS_MTL_UFI_ERR_LOG);
+
+		ivpu_err(vdev, "UFI_ERR irq (0x%08x) opcode: 0x%02lx axi_id: 0x%02lx cq_id: 0x%03lx",
+			 ufi_log, REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, OPCODE, ufi_log),
+			 REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, AXI_ID, ufi_log),
+			 REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, CQ_ID, ufi_log));
+		REGB_WR32(VPU_HW_BTRS_MTL_UFI_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	/* This must be done after interrupts are cleared at the source. */
+	if (IVPU_WA(interrupt_clear_with_0))
+		/*
+		 * Writing 1 triggers an interrupt, so we can't perform read update write.
+		 * Clear local interrupt status by writing 0 to all bits.
+		 */
+		REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, 0x0);
+	else
+		REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, status);
+
+	if (schedule_recovery)
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
+
+	return true;
+}
+
+/* Handler for IRQs from Buttress core (irqB) */
+bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq)
+{
+	u32 status = REGB_RD32(VPU_HW_BTRS_LNL_INTERRUPT_STAT) & BTRS_LNL_IRQ_MASK;
+	bool schedule_recovery = false;
+
+	if (!status)
+		return false;
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, SURV_ERR, status)) {
+		ivpu_dbg(vdev, IRQ, "Survivability IRQ\n");
+		queue_work(system_wq, &vdev->irq_dct_work);
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_lnl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_lnl(pll) / HZ_PER_MHZ);
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, status)) {
+		ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
+			 REGB_RD32(VPU_HW_BTRS_LNL_ATS_ERR_LOG1),
+			 REGB_RD32(VPU_HW_BTRS_LNL_ATS_ERR_LOG2));
+		REGB_WR32(VPU_HW_BTRS_LNL_ATS_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI0_ERR, status)) {
+		ivpu_err(vdev, "CFI0_ERR 0x%08x", REGB_RD32(VPU_HW_BTRS_LNL_CFI0_ERR_LOG));
+		REGB_WR32(VPU_HW_BTRS_LNL_CFI0_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI1_ERR, status)) {
+		ivpu_err(vdev, "CFI1_ERR 0x%08x", REGB_RD32(VPU_HW_BTRS_LNL_CFI1_ERR_LOG));
+		REGB_WR32(VPU_HW_BTRS_LNL_CFI1_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR0_ERR, status)) {
+		ivpu_err(vdev, "IMR_ERR_CFI0 LOW: 0x%08x HIGH: 0x%08x",
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI0_LOW),
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI0_HIGH));
+		REGB_WR32(VPU_HW_BTRS_LNL_IMR_ERR_CFI0_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR1_ERR, status)) {
+		ivpu_err(vdev, "IMR_ERR_CFI1 LOW: 0x%08x HIGH: 0x%08x",
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI1_LOW),
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI1_HIGH));
+		REGB_WR32(VPU_HW_BTRS_LNL_IMR_ERR_CFI1_CLEAR, 0x1);
+		schedule_recovery = true;
+	}
+
+	/* This must be done after interrupts are cleared at the source. */
+	REGB_WR32(VPU_HW_BTRS_LNL_INTERRUPT_STAT, status);
+
+	if (schedule_recovery)
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
+
+	return true;
+}
+
+int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable)
+{
+	u32 val = REGB_RD32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW);
+	u32 cmd = REG_GET_FLD(VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW, CMD, val);
+	u32 param1 = REG_GET_FLD(VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW, PARAM1, val);
+
+	if (cmd != DCT_REQ) {
+		ivpu_err_ratelimited(vdev, "Unsupported PCODE command: 0x%x\n", cmd);
+		return -EBADR;
+	}
+
+	switch (param1) {
+	case DCT_ENABLE:
+		*enable = true;
+		return 0;
+	case DCT_DISABLE:
+		*enable = false;
+		return 0;
+	default:
+		ivpu_err_ratelimited(vdev, "Invalid PARAM1 value: %u\n", param1);
+		return -EINVAL;
+	}
+}
+
+void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 active_percent)
+{
+	u32 val = 0;
+	u32 cmd = enable ? DCT_ENABLE : DCT_DISABLE;
+
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, CMD, DCT_REQ, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, PARAM1, cmd, val);
+	val = REG_SET_FLD_NUM(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, PARAM2, active_percent, val);
+
+	REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val);
+}
+
+u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_RD32(VPU_HW_BTRS_MTL_VPU_TELEMETRY_OFFSET);
+	else
+		return REGB_RD32(VPU_HW_BTRS_LNL_VPU_TELEMETRY_OFFSET);
+}
+
+u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_RD32(VPU_HW_BTRS_MTL_VPU_TELEMETRY_SIZE);
+	else
+		return REGB_RD32(VPU_HW_BTRS_LNL_VPU_TELEMETRY_SIZE);
+}
+
+u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return REGB_RD32(VPU_HW_BTRS_MTL_VPU_TELEMETRY_ENABLE);
+	else
+		return REGB_RD32(VPU_HW_BTRS_LNL_VPU_TELEMETRY_ENABLE);
+}
+
+void ivpu_hw_btrs_global_int_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		REGB_WR32(VPU_HW_BTRS_MTL_GLOBAL_INT_MASK, 0x1);
+	else
+		REGB_WR32(VPU_HW_BTRS_LNL_GLOBAL_INT_MASK, 0x1);
+}
+
+void ivpu_hw_btrs_global_int_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		REGB_WR32(VPU_HW_BTRS_MTL_GLOBAL_INT_MASK, 0x0);
+	else
+		REGB_WR32(VPU_HW_BTRS_LNL_GLOBAL_INT_MASK, 0x0);
+}
+
+void ivpu_hw_btrs_irq_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) {
+		REGB_WR32(VPU_HW_BTRS_MTL_LOCAL_INT_MASK, (u32)(~BTRS_MTL_IRQ_MASK));
+		REGB_WR32(VPU_HW_BTRS_MTL_GLOBAL_INT_MASK, 0x0);
+	} else {
+		REGB_WR32(VPU_HW_BTRS_LNL_LOCAL_INT_MASK, (u32)(~BTRS_LNL_IRQ_MASK));
+		REGB_WR32(VPU_HW_BTRS_LNL_GLOBAL_INT_MASK, 0x0);
+	}
+}
+
+void ivpu_hw_btrs_irq_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) {
+		REGB_WR32(VPU_HW_BTRS_MTL_GLOBAL_INT_MASK, 0x1);
+		REGB_WR32(VPU_HW_BTRS_MTL_LOCAL_INT_MASK, BTRS_IRQ_DISABLE_MASK);
+	} else {
+		REGB_WR32(VPU_HW_BTRS_LNL_GLOBAL_INT_MASK, 0x1);
+		REGB_WR32(VPU_HW_BTRS_LNL_LOCAL_INT_MASK, BTRS_IRQ_DISABLE_MASK);
+	}
+}
+
+static void diagnose_failure_mtl(struct ivpu_device *vdev)
+{
+	u32 reg = REGB_RD32(VPU_HW_BTRS_MTL_INTERRUPT_STAT) & BTRS_MTL_IRQ_MASK;
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, reg))
+		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0));
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, UFI_ERR, reg)) {
+		u32 log = REGB_RD32(VPU_HW_BTRS_MTL_UFI_ERR_LOG);
+
+		ivpu_err(vdev, "UFI_ERR irq (0x%08x) opcode: 0x%02lx axi_id: 0x%02lx cq_id: 0x%03lx",
+			 log, REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, OPCODE, log),
+			 REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, AXI_ID, log),
+			 REG_GET_FLD(VPU_HW_BTRS_MTL_UFI_ERR_LOG, CQ_ID, log));
+	}
+}
+
+static void diagnose_failure_lnl(struct ivpu_device *vdev)
+{
+	u32 reg = REGB_RD32(VPU_HW_BTRS_MTL_INTERRUPT_STAT) & BTRS_LNL_IRQ_MASK;
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, reg)) {
+		ivpu_err(vdev, "ATS_ERR_LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
+			 REGB_RD32(VPU_HW_BTRS_LNL_ATS_ERR_LOG1),
+			 REGB_RD32(VPU_HW_BTRS_LNL_ATS_ERR_LOG2));
+	}
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI0_ERR, reg))
+		ivpu_err(vdev, "CFI0_ERR_LOG 0x%08x\n", REGB_RD32(VPU_HW_BTRS_LNL_CFI0_ERR_LOG));
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, CFI1_ERR, reg))
+		ivpu_err(vdev, "CFI1_ERR_LOG 0x%08x\n", REGB_RD32(VPU_HW_BTRS_LNL_CFI1_ERR_LOG));
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR0_ERR, reg))
+		ivpu_err(vdev, "IMR_ERR_CFI0 LOW: 0x%08x HIGH: 0x%08x\n",
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI0_LOW),
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI0_HIGH));
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, IMR1_ERR, reg))
+		ivpu_err(vdev, "IMR_ERR_CFI1 LOW: 0x%08x HIGH: 0x%08x\n",
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI1_LOW),
+			 REGB_RD32(VPU_HW_BTRS_LNL_IMR_ERR_CFI1_HIGH));
+
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, SURV_ERR, reg))
+		ivpu_err(vdev, "Survivability IRQ\n");
+}
+
+void ivpu_hw_btrs_diagnose_failure(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return diagnose_failure_mtl(vdev);
+	else
+		return diagnose_failure_lnl(vdev);
+}
+
+int ivpu_hw_btrs_platform_read(struct ivpu_device *vdev)
+{
+	u32 reg = REGB_RD32(VPU_HW_BTRS_LNL_VPU_STATUS);
+
+	return REG_GET_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, PLATFORM, reg);
+}
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h
new file mode 100644
index 000000000000..032c384ac3d4
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2025 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_BTRS_H__
+#define __IVPU_HW_BTRS_H__
+
+#include "ivpu_drv.h"
+#include "ivpu_hw_37xx_reg.h"
+#include "ivpu_hw_40xx_reg.h"
+#include "ivpu_hw_reg_io.h"
+
+#define PLL_PROFILING_FREQ_DEFAULT   38400000
+#define PLL_PROFILING_FREQ_HIGH      400000000
+
+#define DCT_DEFAULT_ACTIVE_PERCENT 30u
+#define DCT_PERIOD_US		   35300u
+
+int ivpu_hw_btrs_info_init(struct ivpu_device *vdev);
+void ivpu_hw_btrs_freq_ratios_init(struct ivpu_device *vdev);
+int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev);
+int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable);
+int ivpu_hw_btrs_wait_for_clock_res_own_ack(struct ivpu_device *vdev);
+int ivpu_hw_btrs_d0i3_enable(struct ivpu_device *vdev);
+int ivpu_hw_btrs_d0i3_disable(struct ivpu_device *vdev);
+void ivpu_hw_btrs_set_port_arbitration_weights_lnl(struct ivpu_device *vdev);
+bool ivpu_hw_btrs_is_idle(struct ivpu_device *vdev);
+int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev);
+int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev);
+void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev);
+void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev);
+void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev);
+bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq);
+bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq);
+int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable);
+void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 active_percent);
+u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev);
+void ivpu_hw_btrs_global_int_enable(struct ivpu_device *vdev);
+void ivpu_hw_btrs_global_int_disable(struct ivpu_device *vdev);
+void ivpu_hw_btrs_irq_enable(struct ivpu_device *vdev);
+void ivpu_hw_btrs_irq_disable(struct ivpu_device *vdev);
+void ivpu_hw_btrs_diagnose_failure(struct ivpu_device *vdev);
+int ivpu_hw_btrs_platform_read(struct ivpu_device *vdev);
+
+#endif /* __IVPU_HW_BTRS_H__ */
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h b/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h
new file mode 100644
index 000000000000..fff2ef2cada6
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_BTRS_LNL_REG_H__
+#define __IVPU_HW_BTRS_LNL_REG_H__
+
+#include <linux/bits.h>
+
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT				0x00000000u
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_FREQ_CHANGE_MASK		BIT_MASK(0)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_ATS_ERR_MASK		BIT_MASK(1)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_CFI0_ERR_MASK		BIT_MASK(2)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_CFI1_ERR_MASK		BIT_MASK(3)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_IMR0_ERR_MASK		BIT_MASK(4)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_IMR1_ERR_MASK		BIT_MASK(5)
+#define VPU_HW_BTRS_LNL_INTERRUPT_STAT_SURV_ERR_MASK		BIT_MASK(6)
+
+#define VPU_HW_BTRS_LNL_LOCAL_INT_MASK				0x00000004u
+#define VPU_HW_BTRS_LNL_GLOBAL_INT_MASK				0x00000008u
+
+#define VPU_HW_BTRS_LNL_HM_ATS					0x0000000cu
+
+#define VPU_HW_BTRS_LNL_ATS_ERR_LOG1				0x00000010u
+#define VPU_HW_BTRS_LNL_ATS_ERR_LOG2				0x00000014u
+#define VPU_HW_BTRS_LNL_ATS_ERR_CLEAR				0x00000018u
+
+#define VPU_HW_BTRS_LNL_CFI0_ERR_LOG				0x0000001cu
+#define VPU_HW_BTRS_LNL_CFI0_ERR_CLEAR				0x00000020u
+
+#define VPU_HW_BTRS_LNL_PORT_ARBITRATION_WEIGHTS_ATS		0x00000024u
+
+#define VPU_HW_BTRS_LNL_CFI1_ERR_LOG				0x00000040u
+#define VPU_HW_BTRS_LNL_CFI1_ERR_CLEAR				0x00000044u
+
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI0_LOW			0x00000048u
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI0_HIGH			0x0000004cu
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI0_CLEAR			0x00000050u
+
+#define VPU_HW_BTRS_LNL_PORT_ARBITRATION_WEIGHTS		0x00000054u
+
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI1_LOW			0x00000058u
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI1_HIGH			0x0000005cu
+#define VPU_HW_BTRS_LNL_IMR_ERR_CFI1_CLEAR			0x00000060u
+
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS			0x00000070u
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS_CMD_MASK		GENMASK(7, 0)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS_PARAM1_MASK	GENMASK(15, 8)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS_PARAM2_MASK	GENMASK(23, 16)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS_PARAM3_MASK	GENMASK(31, 24)
+
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW			0x00000074u
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW_CMD_MASK		GENMASK(7, 0)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW_PARAM1_MASK	GENMASK(15, 8)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW_PARAM2_MASK	GENMASK(23, 16)
+#define VPU_HW_BTRS_LNL_PCODE_MAILBOX_SHADOW_PARAM3_MASK	GENMASK(31, 24)
+
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0				0x00000130u
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0_MIN_RATIO_MASK		GENMASK(15, 0)
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD0_MAX_RATIO_MASK		GENMASK(31, 16)
+
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1				0x00000134u
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1_TARGET_RATIO_MASK	GENMASK(15, 0)
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD1_EPP_MASK		GENMASK(31, 16)
+
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2				0x00000138u
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2_CONFIG_MASK		GENMASK(15, 0)
+#define VPU_HW_BTRS_LNL_WP_REQ_PAYLOAD2_CDYN_MASK		GENMASK(31, 16)
+
+#define VPU_HW_BTRS_LNL_WP_REQ_CMD				0x0000013cu
+#define VPU_HW_BTRS_LNL_WP_REQ_CMD_SEND_MASK			BIT_MASK(0)
+
+#define VPU_HW_BTRS_LNL_PLL_FREQ				0x00000148u
+#define VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK			GENMASK(15, 0)
+
+#define VPU_HW_BTRS_LNL_TILE_FUSE				0x00000150u
+#define VPU_HW_BTRS_LNL_TILE_FUSE_VALID_MASK			BIT_MASK(0)
+#define VPU_HW_BTRS_LNL_TILE_FUSE_CONFIG_MASK			GENMASK(6, 1)
+
+#define VPU_HW_BTRS_LNL_VPU_STATUS				0x00000154u
+#define VPU_HW_BTRS_LNL_VPU_STATUS_READY_MASK			BIT_MASK(0)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_IDLE_MASK			BIT_MASK(1)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_DUP_IDLE_MASK		BIT_MASK(2)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_CLOCK_RESOURCE_OWN_ACK_MASK	BIT_MASK(6)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_POWER_RESOURCE_OWN_ACK_MASK	BIT_MASK(7)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_PERF_CLK_MASK		BIT_MASK(11)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_DISABLE_CLK_RELINQUISH_MASK  BIT_MASK(12)
+#define VPU_HW_BTRS_LNL_VPU_STATUS_PLATFORM_MASK		GENMASK(31, 29)
+
+#define VPU_HW_BTRS_LNL_IP_RESET				0x00000160u
+#define VPU_HW_BTRS_LNL_IP_RESET_TRIGGER_MASK			BIT_MASK(0)
+
+#define VPU_HW_BTRS_LNL_D0I3_CONTROL				0x00000164u
+#define VPU_HW_BTRS_LNL_D0I3_CONTROL_INPROGRESS_MASK		BIT_MASK(0)
+#define VPU_HW_BTRS_LNL_D0I3_CONTROL_I3_MASK			BIT_MASK(2)
+
+#define VPU_HW_BTRS_LNL_VPU_TELEMETRY_OFFSET			0x00000168u
+#define VPU_HW_BTRS_LNL_VPU_TELEMETRY_SIZE			0x0000016cu
+#define VPU_HW_BTRS_LNL_VPU_TELEMETRY_ENABLE			0x00000170u
+
+#define VPU_HW_BTRS_LNL_FMIN_FUSE				0x00000174u
+#define VPU_HW_BTRS_LNL_FMIN_FUSE_MIN_RATIO_MASK		GENMASK(7, 0)
+#define VPU_HW_BTRS_LNL_FMIN_FUSE_PN_RATIO_MASK			GENMASK(15, 8)
+
+#define VPU_HW_BTRS_LNL_FMAX_FUSE				0x00000178u
+#define VPU_HW_BTRS_LNL_FMAX_FUSE_MAX_RATIO_MASK		GENMASK(7, 0)
+
+#endif /* __IVPU_HW_BTRS_LNL_REG_H__ */
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs_mtl_reg.h b/drivers/accel/ivpu/ivpu_hw_btrs_mtl_reg.h
new file mode 100644
index 000000000000..e93d539e066f
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_btrs_mtl_reg.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_BTRS_MTL_REG_H__
+#define __IVPU_HW_BTRS_MTL_REG_H__
+
+#include <linux/bits.h>
+
+#define VPU_HW_BTRS_MTL_INTERRUPT_TYPE				0x00000000u
+
+#define VPU_HW_BTRS_MTL_INTERRUPT_STAT				0x00000004u
+#define VPU_HW_BTRS_MTL_INTERRUPT_STAT_FREQ_CHANGE_MASK		BIT_MASK(0)
+#define VPU_HW_BTRS_MTL_INTERRUPT_STAT_ATS_ERR_MASK		BIT_MASK(1)
+#define VPU_HW_BTRS_MTL_INTERRUPT_STAT_UFI_ERR_MASK		BIT_MASK(2)
+
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0				0x00000008u
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0_MIN_RATIO_MASK		GENMASK(15, 0)
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD0_MAX_RATIO_MASK		GENMASK(31, 16)
+
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1				0x0000000cu
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1_TARGET_RATIO_MASK	GENMASK(15, 0)
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD1_EPP_MASK		GENMASK(31, 16)
+
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD2				0x00000010u
+#define VPU_HW_BTRS_MTL_WP_REQ_PAYLOAD2_CONFIG_MASK		GENMASK(15, 0)
+
+#define VPU_HW_BTRS_MTL_WP_REQ_CMD				0x00000014u
+#define VPU_HW_BTRS_MTL_WP_REQ_CMD_SEND_MASK			BIT_MASK(0)
+
+#define VPU_HW_BTRS_MTL_WP_DOWNLOAD				0x00000018u
+#define VPU_HW_BTRS_MTL_WP_DOWNLOAD_TARGET_RATIO_MASK		GENMASK(15, 0)
+
+#define VPU_HW_BTRS_MTL_CURRENT_PLL				0x0000001cu
+#define VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK			GENMASK(15, 0)
+
+#define VPU_HW_BTRS_MTL_PLL_ENABLE				0x00000020u
+
+#define VPU_HW_BTRS_MTL_FMIN_FUSE				0x00000024u
+#define VPU_HW_BTRS_MTL_FMIN_FUSE_MIN_RATIO_MASK		GENMASK(7, 0)
+#define VPU_HW_BTRS_MTL_FMIN_FUSE_PN_RATIO_MASK			GENMASK(15, 8)
+
+#define VPU_HW_BTRS_MTL_FMAX_FUSE				0x00000028u
+#define VPU_HW_BTRS_MTL_FMAX_FUSE_MAX_RATIO_MASK		GENMASK(7, 0)
+
+#define VPU_HW_BTRS_MTL_TILE_FUSE				0x0000002cu
+#define VPU_HW_BTRS_MTL_TILE_FUSE_VALID_MASK			BIT_MASK(0)
+#define VPU_HW_BTRS_MTL_TILE_FUSE_SKU_MASK			GENMASK(3, 2)
+
+#define VPU_HW_BTRS_MTL_LOCAL_INT_MASK				0x00000030u
+#define VPU_HW_BTRS_MTL_GLOBAL_INT_MASK				0x00000034u
+
+#define VPU_HW_BTRS_MTL_PLL_STATUS				0x00000040u
+#define VPU_HW_BTRS_MTL_PLL_STATUS_LOCK_MASK			BIT_MASK(1)
+
+#define VPU_HW_BTRS_MTL_VPU_STATUS				0x00000044u
+#define VPU_HW_BTRS_MTL_VPU_STATUS_READY_MASK			BIT_MASK(0)
+#define VPU_HW_BTRS_MTL_VPU_STATUS_IDLE_MASK			BIT_MASK(1)
+
+#define VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL			0x00000060u
+#define VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL_INPROGRESS_MASK	BIT_MASK(0)
+#define VPU_HW_BTRS_MTL_VPU_D0I3_CONTROL_I3_MASK		BIT_MASK(2)
+
+#define VPU_HW_BTRS_MTL_VPU_IP_RESET				0x00000050u
+#define VPU_HW_BTRS_MTL_VPU_IP_RESET_TRIGGER_MASK		BIT_MASK(0)
+
+#define VPU_HW_BTRS_MTL_VPU_TELEMETRY_OFFSET			0x00000080u
+#define VPU_HW_BTRS_MTL_VPU_TELEMETRY_SIZE			0x00000084u
+#define VPU_HW_BTRS_MTL_VPU_TELEMETRY_ENABLE			0x00000088u
+
+#define VPU_HW_BTRS_MTL_ATS_ERR_LOG_0				0x000000a0u
+#define VPU_HW_BTRS_MTL_ATS_ERR_LOG_1				0x000000a4u
+#define VPU_HW_BTRS_MTL_ATS_ERR_CLEAR				0x000000a8u
+
+#define VPU_HW_BTRS_MTL_UFI_ERR_LOG				0x000000b0u
+#define VPU_HW_BTRS_MTL_UFI_ERR_LOG_CQ_ID_MASK			GENMASK(11, 0)
+#define VPU_HW_BTRS_MTL_UFI_ERR_LOG_AXI_ID_MASK			GENMASK(19, 12)
+#define VPU_HW_BTRS_MTL_UFI_ERR_LOG_OPCODE_MASK			GENMASK(24, 20)
+
+#define VPU_HW_BTRS_MTL_UFI_ERR_CLEAR				0x000000b4u
+
+#endif /* __IVPU_HW_BTRS_MTL_REG_H__ */
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c
new file mode 100644
index 000000000000..2bf9882ab52e
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -0,0 +1,1189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#include "ivpu_drv.h"
+#include "ivpu_fw.h"
+#include "ivpu_hw.h"
+#include "ivpu_hw_37xx_reg.h"
+#include "ivpu_hw_40xx_reg.h"
+#include "ivpu_hw_btrs.h"
+#include "ivpu_hw_ip.h"
+#include "ivpu_hw_reg_io.h"
+#include "ivpu_mmu.h"
+#include "ivpu_pm.h"
+
+#define PWR_ISLAND_STATUS_TIMEOUT_US        (5 * USEC_PER_MSEC)
+
+#define TIM_SAFE_ENABLE		            0xf1d0dead
+#define TIM_WATCHDOG_RESET_VALUE            0xffffffff
+
+#define ICB_0_IRQ_MASK_37XX ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT)))
+
+#define ICB_1_IRQ_MASK_37XX ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_2_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_3_INT)) | \
+			     (REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_4_INT)))
+
+#define ICB_0_1_IRQ_MASK_37XX ((((u64)ICB_1_IRQ_MASK_37XX) << 32) | ICB_0_IRQ_MASK_37XX)
+
+#define ICB_0_IRQ_MASK_40XX ((REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT)))
+
+#define ICB_1_IRQ_MASK_40XX ((REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_2_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_3_INT)) | \
+			     (REG_FLD(VPU_40XX_HOST_SS_ICB_STATUS_1, CPU_INT_REDIRECT_4_INT)))
+
+#define ICB_0_1_IRQ_MASK_40XX ((((u64)ICB_1_IRQ_MASK_40XX) << 32) | ICB_0_IRQ_MASK_40XX)
+
+#define ITF_FIREWALL_VIOLATION_MASK_37XX ((REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_ROM_CMX)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_DBG)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, CSS_CTRL)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, DEC400)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_NCE)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI)) | \
+					  (REG_FLD(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI_CMX)))
+
+#define ITF_FIREWALL_VIOLATION_MASK_40XX ((REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_ROM_CMX)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_DBG)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, CSS_CTRL)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, DEC400)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_NCE)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI)) | \
+					  (REG_FLD(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, MSS_MBI_CMX)))
+
+static int wait_for_ip_bar(struct ivpu_device *vdev)
+{
+	return REGV_POLL_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, AON, 0, 100);
+}
+
+static void host_ss_rst_clr(struct ivpu_device *vdev)
+{
+	u32 val = 0;
+
+	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, TOP_NOC, val);
+	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, DSS_MAS, val);
+	val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_CLR, MSS_MAS, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_CPR_RST_CLR, val);
+}
+
+static int host_ss_noc_qreqn_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QREQN);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qreqn_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QREQN);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qreqn_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return host_ss_noc_qreqn_check_37xx(vdev, exp_val);
+	else
+		return host_ss_noc_qreqn_check_40xx(vdev, exp_val);
+}
+
+static int host_ss_noc_qacceptn_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QACCEPTN);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QACCEPTN, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qacceptn_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QACCEPTN);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QACCEPTN, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return host_ss_noc_qacceptn_check_37xx(vdev, exp_val);
+	else
+		return host_ss_noc_qacceptn_check_40xx(vdev, exp_val);
+}
+
+static int host_ss_noc_qdeny_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QDENY);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_HOST_SS_NOC_QDENY, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qdeny_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QDENY);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_HOST_SS_NOC_QDENY, TOP_SOCMMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int host_ss_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return host_ss_noc_qdeny_check_37xx(vdev, exp_val);
+	else
+		return host_ss_noc_qdeny_check_40xx(vdev, exp_val);
+}
+
+static int top_noc_qrenqn_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QREQN);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qrenqn_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QREQN);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qreqn_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return top_noc_qrenqn_check_37xx(vdev, exp_val);
+	else
+		return top_noc_qrenqn_check_40xx(vdev, exp_val);
+}
+
+int ivpu_hw_ip_host_ss_configure(struct ivpu_device *vdev)
+{
+	int ret;
+
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		ret = wait_for_ip_bar(vdev);
+		if (ret) {
+			ivpu_err(vdev, "Timed out waiting for NPU IP bar\n");
+			return ret;
+		}
+		host_ss_rst_clr(vdev);
+	}
+
+	ret = host_ss_noc_qreqn_check(vdev, 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed qreqn check: %d\n", ret);
+		return ret;
+	}
+
+	ret = host_ss_noc_qacceptn_check(vdev, 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
+		return ret;
+	}
+
+	ret = host_ss_noc_qdeny_check(vdev, 0x0);
+	if (ret)
+		ivpu_err(vdev, "Failed qdeny check %d\n", ret);
+
+	return ret;
+}
+
+static void idle_gen_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_VPU_IDLE_GEN);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_VPU_IDLE_GEN, EN, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_VPU_IDLE_GEN, EN, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_AON_VPU_IDLE_GEN, val);
+}
+
+static void idle_gen_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_IDLE_GEN);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_IDLE_GEN, EN, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_IDLE_GEN, EN, val);
+
+	REGV_WR32(VPU_40XX_HOST_SS_AON_IDLE_GEN, val);
+}
+
+void ivpu_hw_ip_idle_gen_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		idle_gen_drive_37xx(vdev, true);
+	else
+		idle_gen_drive_40xx(vdev, true);
+}
+
+void ivpu_hw_ip_idle_gen_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		idle_gen_drive_37xx(vdev, false);
+	else
+		idle_gen_drive_40xx(vdev, false);
+}
+
+static void
+pwr_island_delay_set_50xx(struct ivpu_device *vdev, u32 post, u32 post1, u32 post2, u32 status)
+{
+	u32 val;
+
+	val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST_DLY, post, val);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST1_DLY, post1, val);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST2_DLY, post2, val);
+	REGV_WR32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, val);
+
+	val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY, STATUS_DLY, status, val);
+	REGV_WR32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY, val);
+}
+
+static void pwr_island_trickle_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, MSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, MSS_CPU, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, val);
+}
+
+static void pwr_island_trickle_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, CSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, CSS_CPU, val);
+
+	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, val);
+}
+
+static void pwr_island_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, CSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, CSS_CPU, val);
+
+	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, val);
+}
+
+static void pwr_island_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, MSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, MSS_CPU, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISLAND_EN0, val);
+}
+
+static void pwr_island_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		pwr_island_trickle_drive_37xx(vdev, true);
+		ndelay(500);
+		pwr_island_drive_37xx(vdev, true);
+	} else {
+		pwr_island_trickle_drive_40xx(vdev, true);
+		ndelay(500);
+		pwr_island_drive_40xx(vdev, true);
+	}
+}
+
+static int wait_for_pwr_island_status(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return REGV_POLL_FLD(VPU_37XX_HOST_SS_AON_PWR_ISLAND_STATUS0, MSS_CPU, exp_val,
+				     PWR_ISLAND_STATUS_TIMEOUT_US);
+	else
+		return REGV_POLL_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_STATUS0, CSS_CPU, exp_val,
+				     PWR_ISLAND_STATUS_TIMEOUT_US);
+}
+
+static void pwr_island_isolation_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, MSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, MSS_CPU, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_AON_PWR_ISO_EN0, val);
+}
+
+static void pwr_island_isolation_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, CSS_CPU, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, CSS_CPU, val);
+
+	REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISO_EN0, val);
+}
+
+static void pwr_island_isolation_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		pwr_island_isolation_drive_37xx(vdev, enable);
+	else
+		pwr_island_isolation_drive_40xx(vdev, enable);
+}
+
+static void pwr_island_isolation_disable(struct ivpu_device *vdev)
+{
+	pwr_island_isolation_drive(vdev, false);
+}
+
+static void host_ss_clk_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_CPR_CLK_SET);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, TOP_NOC, val);
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, DSS_MAS, val);
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, MSS_MAS, val);
+	} else {
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, TOP_NOC, val);
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, DSS_MAS, val);
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_CLK_SET, MSS_MAS, val);
+	}
+
+	REGV_WR32(VPU_37XX_HOST_SS_CPR_CLK_SET, val);
+}
+
+static void host_ss_clk_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_CPR_CLK_EN);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, TOP_NOC, val);
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, DSS_MAS, val);
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, CSS_MAS, val);
+	} else {
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, TOP_NOC, val);
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, DSS_MAS, val);
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_CLK_EN, CSS_MAS, val);
+	}
+
+	REGV_WR32(VPU_40XX_HOST_SS_CPR_CLK_EN, val);
+}
+
+static void host_ss_clk_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		host_ss_clk_drive_37xx(vdev, enable);
+	else
+		host_ss_clk_drive_40xx(vdev, enable);
+}
+
+static void host_ss_clk_enable(struct ivpu_device *vdev)
+{
+	host_ss_clk_drive(vdev, true);
+}
+
+static void host_ss_rst_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_CPR_RST_SET);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, TOP_NOC, val);
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, DSS_MAS, val);
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, MSS_MAS, val);
+	} else {
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, TOP_NOC, val);
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, DSS_MAS, val);
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_CPR_RST_SET, MSS_MAS, val);
+	}
+
+	REGV_WR32(VPU_37XX_HOST_SS_CPR_RST_SET, val);
+}
+
+static void host_ss_rst_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_CPR_RST_EN);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, TOP_NOC, val);
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, DSS_MAS, val);
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, CSS_MAS, val);
+	} else {
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, TOP_NOC, val);
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, DSS_MAS, val);
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_CPR_RST_EN, CSS_MAS, val);
+	}
+
+	REGV_WR32(VPU_40XX_HOST_SS_CPR_RST_EN, val);
+}
+
+static void host_ss_rst_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		host_ss_rst_drive_37xx(vdev, enable);
+	else
+		host_ss_rst_drive_40xx(vdev, enable);
+}
+
+static void host_ss_rst_enable(struct ivpu_device *vdev)
+{
+	host_ss_rst_drive(vdev, true);
+}
+
+static void host_ss_noc_qreqn_top_socmmio_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_NOC_QREQN);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
+	REGV_WR32(VPU_37XX_HOST_SS_NOC_QREQN, val);
+}
+
+static void host_ss_noc_qreqn_top_socmmio_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_SS_NOC_QREQN);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_SS_NOC_QREQN, TOP_SOCMMIO, val);
+	REGV_WR32(VPU_40XX_HOST_SS_NOC_QREQN, val);
+}
+
+static void host_ss_noc_qreqn_top_socmmio_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		host_ss_noc_qreqn_top_socmmio_drive_37xx(vdev, enable);
+	else
+		host_ss_noc_qreqn_top_socmmio_drive_40xx(vdev, enable);
+}
+
+static int host_ss_axi_drive(struct ivpu_device *vdev, bool enable)
+{
+	int ret;
+
+	host_ss_noc_qreqn_top_socmmio_drive(vdev, enable);
+
+	ret = host_ss_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed HOST SS NOC QACCEPTN check: %d\n", ret);
+		return ret;
+	}
+
+	ret = host_ss_noc_qdeny_check(vdev, 0x0);
+	if (ret)
+		ivpu_err(vdev, "Failed HOST SS NOC QDENY check: %d\n", ret);
+
+	return ret;
+}
+
+static void top_noc_qreqn_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QREQN);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, val);
+		val = REG_SET_FLD(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
+	} else {
+		val = REG_CLR_FLD(VPU_40XX_TOP_NOC_QREQN, CPU_CTRL, val);
+		val = REG_CLR_FLD(VPU_40XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
+	}
+
+	REGV_WR32(VPU_40XX_TOP_NOC_QREQN, val);
+}
+
+static void top_noc_qreqn_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QREQN);
+
+	if (enable) {
+		val = REG_SET_FLD(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, val);
+		val = REG_SET_FLD(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
+	} else {
+		val = REG_CLR_FLD(VPU_37XX_TOP_NOC_QREQN, CPU_CTRL, val);
+		val = REG_CLR_FLD(VPU_37XX_TOP_NOC_QREQN, HOSTIF_L2CACHE, val);
+	}
+
+	REGV_WR32(VPU_37XX_TOP_NOC_QREQN, val);
+}
+
+static void top_noc_qreqn_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		top_noc_qreqn_drive_37xx(vdev, enable);
+	else
+		top_noc_qreqn_drive_40xx(vdev, enable);
+}
+
+int ivpu_hw_ip_host_ss_axi_enable(struct ivpu_device *vdev)
+{
+	return host_ss_axi_drive(vdev, true);
+}
+
+static int top_noc_qacceptn_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QACCEPTN);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QACCEPTN, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QACCEPTN, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qacceptn_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QACCEPTN);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QACCEPTN, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QACCEPTN, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qacceptn_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return top_noc_qacceptn_check_37xx(vdev, exp_val);
+	else
+		return top_noc_qacceptn_check_40xx(vdev, exp_val);
+}
+
+static int top_noc_qdeny_check_37xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_37XX_TOP_NOC_QDENY);
+
+	if (!REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QDENY, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_37XX_TOP_NOC_QDENY, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qdeny_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_TOP_NOC_QDENY);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QDENY, CPU_CTRL, exp_val, val) ||
+	    !REG_TEST_FLD_NUM(VPU_40XX_TOP_NOC_QDENY, HOSTIF_L2CACHE, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int top_noc_qdeny_check(struct ivpu_device *vdev, u32 exp_val)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return top_noc_qdeny_check_37xx(vdev, exp_val);
+	else
+		return top_noc_qdeny_check_40xx(vdev, exp_val);
+}
+
+static int top_noc_drive(struct ivpu_device *vdev, bool enable)
+{
+	int ret;
+
+	top_noc_qreqn_drive(vdev, enable);
+
+	ret = top_noc_qacceptn_check(vdev, enable ? 0x1 : 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed TOP NOC QACCEPTN check: %d\n", ret);
+		return ret;
+	}
+
+	ret = top_noc_qdeny_check(vdev, 0x0);
+	if (ret)
+		ivpu_err(vdev, "Failed TOP NOC QDENY check: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_hw_ip_top_noc_enable(struct ivpu_device *vdev)
+{
+	return top_noc_drive(vdev, true);
+}
+
+static void dpu_active_drive_37xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, DPU_ACTIVE, val);
+	else
+		val = REG_CLR_FLD(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, DPU_ACTIVE, val);
+
+	REGV_WR32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, val);
+}
+
+static void pwr_island_delay_set(struct ivpu_device *vdev)
+{
+	bool high = vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_HIGH;
+	u32 post, post1, post2, status;
+
+	if (ivpu_hw_ip_gen(vdev) < IVPU_HW_IP_50XX)
+		return;
+
+	switch (ivpu_device_id(vdev)) {
+	case PCI_DEVICE_ID_WCL:
+	case PCI_DEVICE_ID_PTL_P:
+		post = high ? 18 : 0;
+		post1 = 0;
+		post2 = 0;
+		status = high ? 46 : 3;
+		break;
+
+	default:
+		dump_stack();
+		ivpu_err(vdev, "Unknown device ID\n");
+		return;
+	}
+
+	pwr_island_delay_set_50xx(vdev, post, post1, post2, status);
+}
+
+int ivpu_hw_ip_pwr_domain_enable(struct ivpu_device *vdev)
+{
+	int ret;
+
+	pwr_island_delay_set(vdev);
+	pwr_island_enable(vdev);
+
+	ret = wait_for_pwr_island_status(vdev, 0x1);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for power island status\n");
+		return ret;
+	}
+
+	ret = top_noc_qreqn_check(vdev, 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed TOP NOC QREQN check %d\n", ret);
+		return ret;
+	}
+
+	host_ss_clk_enable(vdev);
+	pwr_island_isolation_disable(vdev);
+	host_ss_rst_enable(vdev);
+
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		dpu_active_drive_37xx(vdev, true);
+
+	return ret;
+}
+
+u64 ivpu_hw_ip_read_perf_timer_counter(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return REGV_RD64(VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT);
+	else
+		return REGV_RD64(VPU_40XX_CPU_SS_TIM_PERF_EXT_FREE_CNT);
+}
+
+static void ivpu_hw_ip_snoop_disable_37xx(struct ivpu_device *vdev)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
+
+	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+
+	if (ivpu_is_force_snoop_enabled(vdev))
+		val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
+	else
+		val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
+
+	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
+}
+
+static void ivpu_hw_ip_snoop_disable_40xx(struct ivpu_device *vdev)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
+
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+
+	if (ivpu_is_force_snoop_enabled(vdev))
+		val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
+
+	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
+}
+
+void ivpu_hw_ip_snoop_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return ivpu_hw_ip_snoop_disable_37xx(vdev);
+	else
+		return ivpu_hw_ip_snoop_disable_40xx(vdev);
+}
+
+static void ivpu_hw_ip_tbu_mmu_enable_37xx(struct ivpu_device *vdev)
+{
+	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TBU_MMUSSIDV);
+
+	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU0_AWMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU0_ARMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU2_AWMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_37XX_HOST_IF_TBU_MMUSSIDV, TBU2_ARMMUSSIDV, val);
+
+	REGV_WR32(VPU_37XX_HOST_IF_TBU_MMUSSIDV, val);
+}
+
+static void ivpu_hw_ip_tbu_mmu_enable_40xx(struct ivpu_device *vdev)
+{
+	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TBU_MMUSSIDV);
+
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU0_AWMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU0_ARMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU1_AWMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU1_ARMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU2_AWMMUSSIDV, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TBU_MMUSSIDV, TBU2_ARMMUSSIDV, val);
+
+	REGV_WR32(VPU_40XX_HOST_IF_TBU_MMUSSIDV, val);
+}
+
+void ivpu_hw_ip_tbu_mmu_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return ivpu_hw_ip_tbu_mmu_enable_37xx(vdev);
+	else
+		return ivpu_hw_ip_tbu_mmu_enable_40xx(vdev);
+}
+
+static int soc_cpu_boot_37xx(struct ivpu_device *vdev)
+{
+	u32 val;
+
+	val = REGV_RD32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC);
+	val = REG_SET_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RSTRUN0, val);
+
+	val = REG_CLR_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RSTVEC, val);
+	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
+
+	val = REG_SET_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RESUME0, val);
+	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
+
+	val = REG_CLR_FLD(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, IRQI_RESUME0, val);
+	REGV_WR32(VPU_37XX_CPU_SS_MSSCPU_CPR_LEON_RT_VEC, val);
+
+	val = vdev->fw->entry_point >> 9;
+	REGV_WR32(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, val);
+
+	val = REG_SET_FLD(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, DONE, val);
+	REGV_WR32(VPU_37XX_HOST_SS_LOADING_ADDRESS_LO, val);
+
+	ivpu_dbg(vdev, PM, "Booting firmware, mode: %s\n",
+		 vdev->fw->entry_point == vdev->fw->cold_boot_entry_point ? "cold boot" : "resume");
+
+	return 0;
+}
+
+static int cpu_noc_qacceptn_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QACCEPTN);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_CPU_SS_CPR_NOC_QACCEPTN, TOP_MMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static int cpu_noc_qdeny_check_40xx(struct ivpu_device *vdev, u32 exp_val)
+{
+	u32 val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QDENY);
+
+	if (!REG_TEST_FLD_NUM(VPU_40XX_CPU_SS_CPR_NOC_QDENY, TOP_MMIO, exp_val, val))
+		return -EIO;
+
+	return 0;
+}
+
+static void cpu_noc_top_mmio_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(VPU_40XX_CPU_SS_CPR_NOC_QREQN);
+
+	if (enable)
+		val = REG_SET_FLD(VPU_40XX_CPU_SS_CPR_NOC_QREQN, TOP_MMIO, val);
+	else
+		val = REG_CLR_FLD(VPU_40XX_CPU_SS_CPR_NOC_QREQN, TOP_MMIO, val);
+	REGV_WR32(VPU_40XX_CPU_SS_CPR_NOC_QREQN, val);
+}
+
+static int soc_cpu_drive_40xx(struct ivpu_device *vdev, bool enable)
+{
+	int ret;
+
+	cpu_noc_top_mmio_drive_40xx(vdev, enable);
+
+	ret = cpu_noc_qacceptn_check_40xx(vdev, enable ? 0x1 : 0x0);
+	if (ret) {
+		ivpu_err(vdev, "Failed qacceptn check: %d\n", ret);
+		return ret;
+	}
+
+	ret = cpu_noc_qdeny_check_40xx(vdev, 0x0);
+	if (ret)
+		ivpu_err(vdev, "Failed qdeny check: %d\n", ret);
+
+	return ret;
+}
+
+static int soc_cpu_enable(struct ivpu_device *vdev)
+{
+	return soc_cpu_drive_40xx(vdev, true);
+}
+
+static int soc_cpu_boot_40xx(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+	u64 val64;
+
+	ret = soc_cpu_enable(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to enable SOC CPU: %d\n", ret);
+		return ret;
+	}
+
+	val64 = vdev->fw->entry_point;
+	val64 <<= ffs(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO_IMAGE_LOCATION_MASK) - 1;
+	REGV_WR64(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, val64);
+
+	val = REGV_RD32(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO);
+	val = REG_SET_FLD(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, DONE, val);
+	REGV_WR32(VPU_40XX_HOST_SS_VERIFICATION_ADDRESS_LO, val);
+
+	ivpu_dbg(vdev, PM, "Booting firmware, mode: %s\n",
+		 ivpu_fw_is_cold_boot(vdev) ? "cold boot" : "resume");
+
+	return 0;
+}
+
+int ivpu_hw_ip_soc_cpu_boot(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return soc_cpu_boot_37xx(vdev);
+	else
+		return soc_cpu_boot_40xx(vdev);
+}
+
+static void wdt_disable_37xx(struct ivpu_device *vdev)
+{
+	u32 val;
+
+	/* Enable writing and set non-zero WDT value */
+	REGV_WR32(VPU_37XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
+	REGV_WR32(VPU_37XX_CPU_SS_TIM_WATCHDOG, TIM_WATCHDOG_RESET_VALUE);
+
+	/* Enable writing and disable watchdog timer */
+	REGV_WR32(VPU_37XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
+	REGV_WR32(VPU_37XX_CPU_SS_TIM_WDOG_EN, 0);
+
+	/* Now clear the timeout interrupt */
+	val = REGV_RD32(VPU_37XX_CPU_SS_TIM_GEN_CONFIG);
+	val = REG_CLR_FLD(VPU_37XX_CPU_SS_TIM_GEN_CONFIG, WDOG_TO_INT_CLR, val);
+	REGV_WR32(VPU_37XX_CPU_SS_TIM_GEN_CONFIG, val);
+}
+
+static void wdt_disable_40xx(struct ivpu_device *vdev)
+{
+	u32 val;
+
+	REGV_WR32(VPU_40XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
+	REGV_WR32(VPU_40XX_CPU_SS_TIM_WATCHDOG, TIM_WATCHDOG_RESET_VALUE);
+
+	REGV_WR32(VPU_40XX_CPU_SS_TIM_SAFE, TIM_SAFE_ENABLE);
+	REGV_WR32(VPU_40XX_CPU_SS_TIM_WDOG_EN, 0);
+
+	val = REGV_RD32(VPU_40XX_CPU_SS_TIM_GEN_CONFIG);
+	val = REG_CLR_FLD(VPU_40XX_CPU_SS_TIM_GEN_CONFIG, WDOG_TO_INT_CLR, val);
+	REGV_WR32(VPU_40XX_CPU_SS_TIM_GEN_CONFIG, val);
+}
+
+void ivpu_hw_ip_wdt_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return wdt_disable_37xx(vdev);
+	else
+		return wdt_disable_40xx(vdev);
+}
+
+static u32 ipc_rx_count_get_37xx(struct ivpu_device *vdev)
+{
+	u32 count = readl(vdev->regv + VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT);
+
+	return REG_GET_FLD(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
+}
+
+static u32 ipc_rx_count_get_40xx(struct ivpu_device *vdev)
+{
+	u32 count = readl(vdev->regv + VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT);
+
+	return REG_GET_FLD(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
+}
+
+u32 ivpu_hw_ip_ipc_rx_count_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return ipc_rx_count_get_37xx(vdev);
+	else
+		return ipc_rx_count_get_40xx(vdev);
+}
+
+void ivpu_hw_ip_irq_enable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		REGV_WR32(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, ITF_FIREWALL_VIOLATION_MASK_37XX);
+		REGV_WR64(VPU_37XX_HOST_SS_ICB_ENABLE_0, ICB_0_1_IRQ_MASK_37XX);
+	} else {
+		REGV_WR32(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, ITF_FIREWALL_VIOLATION_MASK_40XX);
+		REGV_WR64(VPU_40XX_HOST_SS_ICB_ENABLE_0, ICB_0_1_IRQ_MASK_40XX);
+	}
+}
+
+void ivpu_hw_ip_irq_disable(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
+		REGV_WR64(VPU_37XX_HOST_SS_ICB_ENABLE_0, 0x0ull);
+		REGV_WR32(VPU_37XX_HOST_SS_FW_SOC_IRQ_EN, 0x0);
+	} else {
+		REGV_WR64(VPU_40XX_HOST_SS_ICB_ENABLE_0, 0x0ull);
+		REGV_WR32(VPU_40XX_HOST_SS_FW_SOC_IRQ_EN, 0x0ul);
+	}
+}
+
+static void diagnose_failure_37xx(struct ivpu_device *vdev)
+{
+	u32 reg = REGV_RD32(VPU_37XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK_37XX;
+
+	if (ipc_rx_count_get_37xx(vdev))
+		ivpu_err(vdev, "IPC FIFO queue not empty, missed IPC IRQ");
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, reg))
+		ivpu_err(vdev, "WDT MSS timeout detected\n");
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, reg))
+		ivpu_err(vdev, "WDT NCE timeout detected\n");
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, reg))
+		ivpu_err(vdev, "NOC Firewall irq detected\n");
+}
+
+static void diagnose_failure_40xx(struct ivpu_device *vdev)
+{
+	u32 reg = REGV_RD32(VPU_40XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK_40XX;
+
+	if (ipc_rx_count_get_40xx(vdev))
+		ivpu_err(vdev, "IPC FIFO queue not empty, missed IPC IRQ");
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, reg))
+		ivpu_err(vdev, "WDT MSS timeout detected\n");
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, reg))
+		ivpu_err(vdev, "WDT NCE timeout detected\n");
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, reg))
+		ivpu_err(vdev, "NOC Firewall irq detected\n");
+}
+
+void ivpu_hw_ip_diagnose_failure(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		diagnose_failure_37xx(vdev);
+	else
+		diagnose_failure_40xx(vdev);
+}
+
+void ivpu_hw_ip_irq_clear(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		REGV_WR64(VPU_37XX_HOST_SS_ICB_CLEAR_0, ICB_0_1_IRQ_MASK_37XX);
+	else
+		REGV_WR64(VPU_40XX_HOST_SS_ICB_CLEAR_0, ICB_0_1_IRQ_MASK_40XX);
+}
+
+static void irq_wdt_nce_handler(struct ivpu_device *vdev)
+{
+	ivpu_pm_trigger_recovery(vdev, "WDT NCE IRQ");
+}
+
+static void irq_wdt_mss_handler(struct ivpu_device *vdev)
+{
+	ivpu_hw_ip_wdt_disable(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT MSS IRQ");
+}
+
+static void irq_noc_firewall_handler(struct ivpu_device *vdev)
+{
+	atomic_inc(&vdev->hw->firewall_irq_counter);
+
+	ivpu_dbg(vdev, IRQ, "NOC Firewall interrupt detected, counter %d\n",
+		 atomic_read(&vdev->hw->firewall_irq_counter));
+}
+
+/* Handler for IRQs from NPU core */
+bool ivpu_hw_ip_irq_handler_37xx(struct ivpu_device *vdev, int irq)
+{
+	u32 status = REGV_RD32(VPU_37XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK_37XX;
+
+	if (!status)
+		return false;
+
+	REGV_WR32(VPU_37XX_HOST_SS_ICB_CLEAR_0, status);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
+		ivpu_mmu_irq_evtq_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
+		ivpu_ipc_irq_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
+		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT, status))
+		ivpu_mmu_irq_gerr_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, status))
+		irq_wdt_mss_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, status))
+		irq_wdt_nce_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
+		irq_noc_firewall_handler(vdev);
+
+	return true;
+}
+
+/* Handler for IRQs from NPU core */
+bool ivpu_hw_ip_irq_handler_40xx(struct ivpu_device *vdev, int irq)
+{
+	u32 status = REGV_RD32(VPU_40XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK_40XX;
+
+	if (!status)
+		return false;
+
+	REGV_WR32(VPU_40XX_HOST_SS_ICB_CLEAR_0, status);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
+		ivpu_mmu_irq_evtq_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
+		ivpu_ipc_irq_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
+		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT, status))
+		ivpu_mmu_irq_gerr_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, status))
+		irq_wdt_mss_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_1_INT, status))
+		irq_wdt_nce_handler(vdev);
+
+	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
+		irq_noc_firewall_handler(vdev);
+
+	return true;
+}
+
+static void db_set_37xx(struct ivpu_device *vdev, u32 db_id)
+{
+	u32 reg_stride = VPU_37XX_CPU_SS_DOORBELL_1 - VPU_37XX_CPU_SS_DOORBELL_0;
+	u32 val = REG_FLD(VPU_37XX_CPU_SS_DOORBELL_0, SET);
+
+	REGV_WR32I(VPU_37XX_CPU_SS_DOORBELL_0, reg_stride, db_id, val);
+}
+
+static void db_set_40xx(struct ivpu_device *vdev, u32 db_id)
+{
+	u32 reg_stride = VPU_40XX_CPU_SS_DOORBELL_1 - VPU_40XX_CPU_SS_DOORBELL_0;
+	u32 val = REG_FLD(VPU_40XX_CPU_SS_DOORBELL_0, SET);
+
+	REGV_WR32I(VPU_40XX_CPU_SS_DOORBELL_0, reg_stride, db_id, val);
+}
+
+void ivpu_hw_ip_db_set(struct ivpu_device *vdev, u32 db_id)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		db_set_37xx(vdev, db_id);
+	else
+		db_set_40xx(vdev, db_id);
+}
+
+u32 ivpu_hw_ip_ipc_rx_addr_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		return REGV_RD32(VPU_37XX_HOST_SS_TIM_IPC_FIFO_ATM);
+	else
+		return REGV_RD32(VPU_40XX_HOST_SS_TIM_IPC_FIFO_ATM);
+}
+
+void ivpu_hw_ip_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
+{
+	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
+		REGV_WR32(VPU_37XX_CPU_SS_TIM_IPC_FIFO, vpu_addr);
+	else
+		REGV_WR32(VPU_40XX_CPU_SS_TIM_IPC_FIFO, vpu_addr);
+}
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.h b/drivers/accel/ivpu/ivpu_hw_ip.h
new file mode 100644
index 000000000000..5b1b391aa577
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_hw_ip.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_IP_H__
+#define __IVPU_HW_IP_H__
+
+#include "ivpu_drv.h"
+
+int ivpu_hw_ip_host_ss_configure(struct ivpu_device *vdev);
+void ivpu_hw_ip_idle_gen_enable(struct ivpu_device *vdev);
+void ivpu_hw_ip_idle_gen_disable(struct ivpu_device *vdev);
+int ivpu_hw_ip_pwr_domain_enable(struct ivpu_device *vdev);
+int ivpu_hw_ip_host_ss_axi_enable(struct ivpu_device *vdev);
+int ivpu_hw_ip_top_noc_enable(struct ivpu_device *vdev);
+u64 ivpu_hw_ip_read_perf_timer_counter(struct ivpu_device *vdev);
+void ivpu_hw_ip_snoop_disable(struct ivpu_device *vdev);
+void ivpu_hw_ip_tbu_mmu_enable(struct ivpu_device *vdev);
+int ivpu_hw_ip_soc_cpu_boot(struct ivpu_device *vdev);
+void ivpu_hw_ip_wdt_disable(struct ivpu_device *vdev);
+void ivpu_hw_ip_diagnose_failure(struct ivpu_device *vdev);
+u32 ivpu_hw_ip_ipc_rx_count_get(struct ivpu_device *vdev);
+void ivpu_hw_ip_irq_clear(struct ivpu_device *vdev);
+bool ivpu_hw_ip_irq_handler_37xx(struct ivpu_device *vdev, int irq);
+bool ivpu_hw_ip_irq_handler_40xx(struct ivpu_device *vdev, int irq);
+void ivpu_hw_ip_db_set(struct ivpu_device *vdev, u32 db_id);
+u32 ivpu_hw_ip_ipc_rx_addr_get(struct ivpu_device *vdev);
+void ivpu_hw_ip_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr);
+void ivpu_hw_ip_irq_enable(struct ivpu_device *vdev);
+void ivpu_hw_ip_irq_disable(struct ivpu_device *vdev);
+void ivpu_hw_ip_diagnose_failure(struct ivpu_device *vdev);
+void ivpu_hw_ip_fabric_req_override_enable_50xx(struct ivpu_device *vdev);
+void ivpu_hw_ip_fabric_req_override_disable_50xx(struct ivpu_device *vdev);
+
+#endif /* __IVPU_HW_IP_H__ */
diff --git a/drivers/accel/ivpu/ivpu_hw_reg_io.h b/drivers/accel/ivpu/ivpu_hw_reg_io.h
index 79b3f441eac4..66259b0ead02 100644
--- a/drivers/accel/ivpu/ivpu_hw_reg_io.h
+++ b/drivers/accel/ivpu/ivpu_hw_reg_io.h
@@ -7,6 +7,7 @@
 #define __IVPU_HW_REG_IO_H__
 
 #include <linux/bitfield.h>
+#include <linux/fault-inject.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
 
@@ -16,13 +17,11 @@
 #define REG_IO_ERROR      0xffffffff
 
 #define REGB_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regb, (reg), #reg, __func__)
-#define REGB_RD32_SILENT(reg)   readl(vdev->regb + (reg))
 #define REGB_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regb, (reg), #reg, __func__)
 #define REGB_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regb, (reg), (val), #reg, __func__)
 #define REGB_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regb, (reg), (val), #reg, __func__)
 
 #define REGV_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regv, (reg), #reg, __func__)
-#define REGV_RD32_SILENT(reg)   readl(vdev->regv + (reg))
 #define REGV_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regv, (reg), #reg, __func__)
 #define REGV_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regv, (reg), (val), #reg, __func__)
 #define REGV_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regv, (reg), (val), #reg, __func__)
@@ -47,31 +46,42 @@
 #define REG_TEST_FLD_NUM(REG, FLD, num, val) \
 	((num) == FIELD_GET(REG##_##FLD##_MASK, val))
 
-#define REGB_POLL_FLD(reg, fld, val, timeout_us) \
-({ \
-	u32 var; \
-	int r; \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \
-		 __func__, #reg, reg, #fld, val); \
-	r = read_poll_timeout(REGB_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\
-			      REG_POLL_SLEEP_US, timeout_us, false, (reg)); \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \
-		 __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \
-	r; \
-})
-
-#define REGV_POLL_FLD(reg, fld, val, timeout_us) \
-({ \
-	u32 var; \
-	int r; \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \
-		 __func__, #reg, reg, #fld, val); \
-	r = read_poll_timeout(REGV_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\
-			      REG_POLL_SLEEP_US, timeout_us, false, (reg)); \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \
-		 __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \
-	r; \
-})
+#define REGB_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \
+	ivpu_hw_reg_poll_fld(vdev, vdev->regb, reg, reg##_##fld##_MASK, \
+			     FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \
+			     __func__, #reg, #fld)
+
+#define REGV_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \
+	ivpu_hw_reg_poll_fld(vdev, vdev->regv, reg, reg##_##fld##_MASK, \
+			     FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \
+			     __func__, #reg, #fld)
+
+extern struct fault_attr ivpu_hw_failure;
+
+static inline int __must_check
+ivpu_hw_reg_poll_fld(struct ivpu_device *vdev, void __iomem *base,
+		     u32 reg_offset, u32 reg_mask, u32 exp_masked_val, u32 timeout_us,
+		     const char *func_name, const char *reg_name, const char *fld_name)
+{
+	u32 reg_val;
+	int ret;
+
+	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s started (exp_val 0x%x)\n",
+		 func_name, reg_name, reg_offset, fld_name, exp_masked_val);
+
+	ret = read_poll_timeout(readl, reg_val, (reg_val & reg_mask) == exp_masked_val,
+				REG_POLL_SLEEP_US, timeout_us, false, base + reg_offset);
+
+#ifdef CONFIG_FAULT_INJECTION
+	if (should_fail(&ivpu_hw_failure, 1))
+		ret = -ETIMEDOUT;
+#endif
+
+	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s %s (reg_val 0x%08x)\n",
+		 func_name, reg_name, reg_offset, fld_name, ret ? "ETIMEDOUT" : "OK", reg_val);
+
+	return ret;
+}
 
 static inline u32
 ivpu_hw_reg_rd32(struct ivpu_device *vdev, void __iomem *base, u32 reg,
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index a4ca40b184d4..5f00809d448a 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
+#include <linux/pm_runtime.h>
 #include <linux/wait.h>
 
 #include "ivpu_drv.h"
@@ -15,21 +15,15 @@
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_pm.h"
+#include "ivpu_trace.h"
 
 #define IPC_MAX_RX_MSG	128
-#define IS_KTHREAD()	(get_current()->flags & PF_KTHREAD)
 
 struct ivpu_ipc_tx_buf {
 	struct ivpu_ipc_hdr ipc;
 	struct vpu_jsm_msg jsm;
 };
 
-struct ivpu_ipc_rx_msg {
-	struct list_head link;
-	struct ivpu_ipc_hdr *ipc_hdr;
-	struct vpu_jsm_msg *jsm_msg;
-};
-
 static void ivpu_ipc_msg_dump(struct ivpu_device *vdev, char *c,
 			      struct ivpu_ipc_hdr *ipc_hdr, u32 vpu_addr)
 {
@@ -65,8 +59,8 @@ static void ivpu_ipc_mem_fini(struct ivpu_device *vdev)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
-	ivpu_bo_free_internal(ipc->mem_rx);
-	ivpu_bo_free_internal(ipc->mem_tx);
+	ivpu_bo_free(ipc->mem_rx);
+	ivpu_bo_free(ipc->mem_tx);
 }
 
 static int
@@ -136,11 +130,51 @@ static void ivpu_ipc_tx_release(struct ivpu_device *vdev, u32 vpu_addr)
 
 static void ivpu_ipc_tx(struct ivpu_device *vdev, u32 vpu_addr)
 {
-	ivpu_hw_reg_ipc_tx_set(vdev, vpu_addr);
+	ivpu_hw_ipc_tx_set(vdev, vpu_addr);
+}
+
+static void
+ivpu_ipc_rx_msg_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
+		    struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
+{
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+	struct ivpu_ipc_rx_msg *rx_msg;
+
+	lockdep_assert_held(&ipc->cons_lock);
+
+	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
+	if (!rx_msg) {
+		ivpu_ipc_rx_mark_free(vdev, ipc_hdr, jsm_msg);
+		return;
+	}
+
+	atomic_inc(&ipc->rx_msg_count);
+
+	rx_msg->ipc_hdr = ipc_hdr;
+	rx_msg->jsm_msg = jsm_msg;
+	rx_msg->callback = cons->rx_callback;
+
+	if (rx_msg->callback) {
+		list_add_tail(&rx_msg->link, &ipc->cb_msg_list);
+	} else {
+		spin_lock(&cons->rx_lock);
+		list_add_tail(&rx_msg->link, &cons->rx_msg_list);
+		spin_unlock(&cons->rx_lock);
+		wake_up(&cons->rx_msg_wq);
+	}
+}
+
+static void
+ivpu_ipc_rx_msg_del(struct ivpu_device *vdev, struct ivpu_ipc_rx_msg *rx_msg)
+{
+	list_del(&rx_msg->link);
+	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+	atomic_dec(&vdev->ipc->rx_msg_count);
+	kfree(rx_msg);
 }
 
-void
-ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, u32 channel)
+void ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
+			   u32 channel, ivpu_ipc_rx_callback_t rx_callback)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
@@ -148,13 +182,15 @@ ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	cons->channel = channel;
 	cons->tx_vpu_addr = 0;
 	cons->request_id = 0;
-	spin_lock_init(&cons->rx_msg_lock);
+	cons->aborted = false;
+	cons->rx_callback = rx_callback;
+	spin_lock_init(&cons->rx_lock);
 	INIT_LIST_HEAD(&cons->rx_msg_list);
 	init_waitqueue_head(&cons->rx_msg_wq);
 
-	spin_lock_irq(&ipc->cons_list_lock);
+	spin_lock_irq(&ipc->cons_lock);
 	list_add_tail(&cons->link, &ipc->cons_list);
-	spin_unlock_irq(&ipc->cons_list_lock);
+	spin_unlock_irq(&ipc->cons_lock);
 }
 
 void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons)
@@ -162,24 +198,19 @@ void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *c
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_rx_msg *rx_msg, *r;
 
-	spin_lock_irq(&ipc->cons_list_lock);
+	spin_lock_irq(&ipc->cons_lock);
 	list_del(&cons->link);
-	spin_unlock_irq(&ipc->cons_list_lock);
-
-	spin_lock_irq(&cons->rx_msg_lock);
-	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link) {
-		list_del(&rx_msg->link);
-		ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
-		atomic_dec(&ipc->rx_msg_count);
-		kfree(rx_msg);
-	}
-	spin_unlock_irq(&cons->rx_msg_lock);
+	spin_unlock_irq(&ipc->cons_lock);
+
+	spin_lock_irq(&cons->rx_lock);
+	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link)
+		ivpu_ipc_rx_msg_del(vdev, rx_msg);
+	spin_unlock_irq(&cons->rx_lock);
 
 	ivpu_ipc_tx_release(vdev, cons->tx_vpu_addr);
 }
 
-static int
-ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, struct vpu_jsm_msg *req)
+int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, struct vpu_jsm_msg *req)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	int ret;
@@ -196,71 +227,84 @@ ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, struct v
 		goto unlock;
 
 	ivpu_ipc_tx(vdev, cons->tx_vpu_addr);
+	trace_jsm("[tx]", req);
 
 unlock:
 	mutex_unlock(&ipc->lock);
 	return ret;
 }
 
+static bool ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
+{
+	bool ret;
+
+	spin_lock_irq(&cons->rx_lock);
+	ret = !list_empty(&cons->rx_msg_list) || cons->aborted;
+	spin_unlock_irq(&cons->rx_lock);
+
+	return ret;
+}
+
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		     struct ivpu_ipc_hdr *ipc_buf,
-		     struct vpu_jsm_msg *ipc_payload, unsigned long timeout_ms)
+		     struct vpu_jsm_msg *jsm_msg, unsigned long timeout_ms)
 {
-	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_rx_msg *rx_msg;
 	int wait_ret, ret = 0;
 
+	if (drm_WARN_ONCE(&vdev->drm, cons->rx_callback, "Consumer works only in async mode\n"))
+		return -EINVAL;
+
 	wait_ret = wait_event_timeout(cons->rx_msg_wq,
-				      (IS_KTHREAD() && kthread_should_stop()) ||
-				      !list_empty(&cons->rx_msg_list),
+				      ivpu_ipc_rx_need_wakeup(cons),
 				      msecs_to_jiffies(timeout_ms));
 
-	if (IS_KTHREAD() && kthread_should_stop())
-		return -EINTR;
-
 	if (wait_ret == 0)
 		return -ETIMEDOUT;
 
-	spin_lock_irq(&cons->rx_msg_lock);
+	spin_lock_irq(&cons->rx_lock);
+	if (cons->aborted) {
+		spin_unlock_irq(&cons->rx_lock);
+		return -ECANCELED;
+	}
 	rx_msg = list_first_entry_or_null(&cons->rx_msg_list, struct ivpu_ipc_rx_msg, link);
 	if (!rx_msg) {
-		spin_unlock_irq(&cons->rx_msg_lock);
+		spin_unlock_irq(&cons->rx_lock);
 		return -EAGAIN;
 	}
-	list_del(&rx_msg->link);
-	spin_unlock_irq(&cons->rx_msg_lock);
 
 	if (ipc_buf)
 		memcpy(ipc_buf, rx_msg->ipc_hdr, sizeof(*ipc_buf));
 	if (rx_msg->jsm_msg) {
-		u32 size = min_t(int, rx_msg->ipc_hdr->data_size, sizeof(*ipc_payload));
+		u32 size = min_t(int, rx_msg->ipc_hdr->data_size, sizeof(*jsm_msg));
 
 		if (rx_msg->jsm_msg->result != VPU_JSM_STATUS_SUCCESS) {
-			ivpu_dbg(vdev, IPC, "IPC resp result error: %d\n", rx_msg->jsm_msg->result);
+			ivpu_err(vdev, "IPC resp result error: %d\n", rx_msg->jsm_msg->result);
 			ret = -EBADMSG;
 		}
 
-		if (ipc_payload)
-			memcpy(ipc_payload, rx_msg->jsm_msg, size);
+		if (jsm_msg)
+			memcpy(jsm_msg, rx_msg->jsm_msg, size);
+		trace_jsm("[rx]", rx_msg->jsm_msg);
 	}
 
-	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
-	atomic_dec(&ipc->rx_msg_count);
-	kfree(rx_msg);
-
+	ivpu_ipc_rx_msg_del(vdev, rx_msg);
+	spin_unlock_irq(&cons->rx_lock);
 	return ret;
 }
 
-static int
+int
 ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 			       enum vpu_ipc_msg_type expected_resp_type,
-			       struct vpu_jsm_msg *resp, u32 channel,
-			       unsigned long timeout_ms)
+			       struct vpu_jsm_msg *resp, u32 channel, unsigned long timeout_ms)
 {
 	struct ivpu_ipc_consumer cons;
 	int ret;
 
-	ivpu_ipc_consumer_add(vdev, &cons, channel);
+	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev) &&
+		    pm_runtime_enabled(vdev->drm.dev));
+
+	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
 
 	ret = ivpu_ipc_send(vdev, &cons, req);
 	if (ret) {
@@ -286,9 +330,8 @@ consumer_del:
 }
 
 int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-			  enum vpu_ipc_msg_type expected_resp_type,
-			  struct vpu_jsm_msg *resp, u32 channel,
-			  unsigned long timeout_ms)
+			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+			  u32 channel, unsigned long timeout_ms)
 {
 	struct vpu_jsm_msg hb_req = { .type = VPU_JSM_MSG_QUERY_ENGINE_HB };
 	struct vpu_jsm_msg hb_resp;
@@ -298,24 +341,47 @@ int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 	if (ret < 0)
 		return ret;
 
-	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp_type, resp,
-					     channel, timeout_ms);
+	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms);
 	if (ret != -ETIMEDOUT)
 		goto rpm_put;
 
 	hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
 						&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
 						vdev->timeout.jsm);
-	if (hb_ret == -ETIMEDOUT) {
-		ivpu_hw_diagnose_failure(vdev);
-		ivpu_pm_schedule_recovery(vdev);
-	}
+	if (hb_ret == -ETIMEDOUT)
+		ivpu_pm_trigger_recovery(vdev, "IPC timeout");
 
 rpm_put:
 	ivpu_rpm_put(vdev);
 	return ret;
 }
 
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms)
+{
+	struct ivpu_ipc_consumer cons;
+	int ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
+
+	ret = ivpu_ipc_send(vdev, &cons, req);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "IPC send failed: %d\n", ret);
+		goto consumer_del;
+	}
+
+	msleep(timeout_ms);
+
+consumer_del:
+	ivpu_ipc_consumer_del(vdev, &cons);
+	ivpu_rpm_put(vdev);
+	return ret;
+}
+
 static bool
 ivpu_ipc_match_consumer(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 			struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
@@ -329,35 +395,7 @@ ivpu_ipc_match_consumer(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons
 	return false;
 }
 
-static void
-ivpu_ipc_dispatch(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-		  struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
-{
-	struct ivpu_ipc_info *ipc = vdev->ipc;
-	struct ivpu_ipc_rx_msg *rx_msg;
-	unsigned long flags;
-
-	lockdep_assert_held(&ipc->cons_list_lock);
-
-	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
-	if (!rx_msg) {
-		ivpu_ipc_rx_mark_free(vdev, ipc_hdr, jsm_msg);
-		return;
-	}
-
-	atomic_inc(&ipc->rx_msg_count);
-
-	rx_msg->ipc_hdr = ipc_hdr;
-	rx_msg->jsm_msg = jsm_msg;
-
-	spin_lock_irqsave(&cons->rx_msg_lock, flags);
-	list_add_tail(&rx_msg->link, &cons->rx_msg_list);
-	spin_unlock_irqrestore(&cons->rx_msg_lock, flags);
-
-	wake_up(&cons->rx_msg_wq);
-}
-
-int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
+void ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_consumer *cons;
@@ -371,11 +409,11 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 	 * Driver needs to purge all messages from IPC FIFO to clear IPC interrupt.
 	 * Without purge IPC FIFO to 0 next IPC interrupts won't be generated.
 	 */
-	while (ivpu_hw_reg_ipc_rx_count_get(vdev)) {
-		vpu_addr = ivpu_hw_reg_ipc_rx_addr_get(vdev);
+	while (ivpu_hw_ipc_rx_count_get(vdev)) {
+		vpu_addr = ivpu_hw_ipc_rx_addr_get(vdev);
 		if (vpu_addr == REG_IO_ERROR) {
 			ivpu_err_ratelimited(vdev, "Failed to read IPC rx addr register\n");
-			return -EIO;
+			return;
 		}
 
 		ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr);
@@ -405,15 +443,15 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		}
 
 		dispatched = false;
-		spin_lock_irqsave(&ipc->cons_list_lock, flags);
+		spin_lock_irqsave(&ipc->cons_lock, flags);
 		list_for_each_entry(cons, &ipc->cons_list, link) {
 			if (ivpu_ipc_match_consumer(vdev, cons, ipc_hdr, jsm_msg)) {
-				ivpu_ipc_dispatch(vdev, cons, ipc_hdr, jsm_msg);
+				ivpu_ipc_rx_msg_add(vdev, cons, ipc_hdr, jsm_msg);
 				dispatched = true;
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
+		spin_unlock_irqrestore(&ipc->cons_lock, flags);
 
 		if (!dispatched) {
 			ivpu_dbg(vdev, IPC, "IPC RX msg 0x%x dropped (no consumer)\n", vpu_addr);
@@ -421,7 +459,26 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		}
 	}
 
-	return 0;
+	queue_work(system_wq, &vdev->irq_ipc_work);
+}
+
+void ivpu_ipc_irq_work_fn(struct work_struct *work)
+{
+	struct ivpu_device *vdev = container_of(work, struct ivpu_device, irq_ipc_work);
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+	struct ivpu_ipc_rx_msg *rx_msg, *r;
+	struct list_head cb_msg_list;
+
+	INIT_LIST_HEAD(&cb_msg_list);
+
+	spin_lock_irq(&ipc->cons_lock);
+	list_splice_tail_init(&ipc->cb_msg_list, &cb_msg_list);
+	spin_unlock_irq(&ipc->cons_lock);
+
+	list_for_each_entry_safe(rx_msg, r, &cb_msg_list, link) {
+		rx_msg->callback(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+		ivpu_ipc_rx_msg_del(vdev, rx_msg);
+	}
 }
 
 int ivpu_ipc_init(struct ivpu_device *vdev)
@@ -429,13 +486,13 @@ int ivpu_ipc_init(struct ivpu_device *vdev)
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	int ret;
 
-	ipc->mem_tx = ivpu_bo_alloc_internal(vdev, 0, SZ_16K, DRM_IVPU_BO_WC);
+	ipc->mem_tx = ivpu_bo_create_global(vdev, SZ_16K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!ipc->mem_tx) {
 		ivpu_err(vdev, "Failed to allocate mem_tx\n");
 		return -ENOMEM;
 	}
 
-	ipc->mem_rx = ivpu_bo_alloc_internal(vdev, 0, SZ_16K, DRM_IVPU_BO_WC);
+	ipc->mem_rx = ivpu_bo_create_global(vdev, SZ_16K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!ipc->mem_rx) {
 		ivpu_err(vdev, "Failed to allocate mem_rx\n");
 		ret = -ENOMEM;
@@ -456,22 +513,32 @@ int ivpu_ipc_init(struct ivpu_device *vdev)
 		goto err_free_rx;
 	}
 
+	spin_lock_init(&ipc->cons_lock);
 	INIT_LIST_HEAD(&ipc->cons_list);
-	spin_lock_init(&ipc->cons_list_lock);
-	drmm_mutex_init(&vdev->drm, &ipc->lock);
-
+	INIT_LIST_HEAD(&ipc->cb_msg_list);
+	ret = drmm_mutex_init(&vdev->drm, &ipc->lock);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize ipc->lock, ret %d\n", ret);
+		goto err_free_rx;
+	}
 	ivpu_ipc_reset(vdev);
 	return 0;
 
 err_free_rx:
-	ivpu_bo_free_internal(ipc->mem_rx);
+	ivpu_bo_free(ipc->mem_rx);
 err_free_tx:
-	ivpu_bo_free_internal(ipc->mem_tx);
+	ivpu_bo_free(ipc->mem_tx);
 	return ret;
 }
 
 void ivpu_ipc_fini(struct ivpu_device *vdev)
 {
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cons_list));
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cb_msg_list));
+	drm_WARN_ON(&vdev->drm, atomic_read(&ipc->rx_msg_count) > 0);
+
 	ivpu_ipc_mem_fini(vdev);
 }
 
@@ -488,16 +555,27 @@ void ivpu_ipc_disable(struct ivpu_device *vdev)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_consumer *cons, *c;
-	unsigned long flags;
+	struct ivpu_ipc_rx_msg *rx_msg, *r;
+
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cb_msg_list));
 
 	mutex_lock(&ipc->lock);
 	ipc->on = false;
 	mutex_unlock(&ipc->lock);
 
-	spin_lock_irqsave(&ipc->cons_list_lock, flags);
-	list_for_each_entry_safe(cons, c, &ipc->cons_list, link)
+	spin_lock_irq(&ipc->cons_lock);
+	list_for_each_entry_safe(cons, c, &ipc->cons_list, link) {
+		spin_lock(&cons->rx_lock);
+		if (!cons->rx_callback)
+			cons->aborted = true;
+		list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link)
+			ivpu_ipc_rx_msg_del(vdev, rx_msg);
+		spin_unlock(&cons->rx_lock);
 		wake_up(&cons->rx_msg_wq);
-	spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
+	}
+	spin_unlock_irq(&ipc->cons_lock);
+
+	drm_WARN_ON(&vdev->drm, atomic_read(&ipc->rx_msg_count) > 0);
 }
 
 void ivpu_ipc_reset(struct ivpu_device *vdev)
@@ -505,6 +583,7 @@ void ivpu_ipc_reset(struct ivpu_device *vdev)
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
 	mutex_lock(&ipc->lock);
+	drm_WARN_ON(&vdev->drm, ipc->on);
 
 	memset(ivpu_bo_vaddr(ipc->mem_tx), 0, ivpu_bo_size(ipc->mem_tx));
 	memset(ivpu_bo_vaddr(ipc->mem_rx), 0, ivpu_bo_size(ipc->mem_rx));
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 68f5b6668e00..b524a1985b9d 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_IPC_H__
@@ -42,13 +42,26 @@ struct ivpu_ipc_hdr {
 	u8 status;
 } __packed __aligned(IVPU_IPC_ALIGNMENT);
 
+typedef void (*ivpu_ipc_rx_callback_t)(struct ivpu_device *vdev,
+				       struct ivpu_ipc_hdr *ipc_hdr,
+				       struct vpu_jsm_msg *jsm_msg);
+
+struct ivpu_ipc_rx_msg {
+	struct list_head link;
+	struct ivpu_ipc_hdr *ipc_hdr;
+	struct vpu_jsm_msg *jsm_msg;
+	ivpu_ipc_rx_callback_t callback;
+};
+
 struct ivpu_ipc_consumer {
 	struct list_head link;
 	u32 channel;
 	u32 tx_vpu_addr;
 	u32 request_id;
+	bool aborted;
+	ivpu_ipc_rx_callback_t rx_callback;
 
-	spinlock_t rx_msg_lock; /* Protects rx_msg_list */
+	spinlock_t rx_lock; /* Protects rx_msg_list and aborted */
 	struct list_head rx_msg_list;
 	wait_queue_head_t rx_msg_wq;
 };
@@ -60,8 +73,9 @@ struct ivpu_ipc_info {
 
 	atomic_t rx_msg_count;
 
-	spinlock_t cons_list_lock; /* Protects cons_list */
+	spinlock_t cons_lock; /* Protects cons_list and cb_msg_list */
 	struct list_head cons_list;
+	struct list_head cb_msg_list;
 
 	atomic_t request_id;
 	struct mutex lock; /* Lock on status */
@@ -75,19 +89,25 @@ void ivpu_ipc_enable(struct ivpu_device *vdev);
 void ivpu_ipc_disable(struct ivpu_device *vdev);
 void ivpu_ipc_reset(struct ivpu_device *vdev);
 
-int ivpu_ipc_irq_handler(struct ivpu_device *vdev);
+void ivpu_ipc_irq_handler(struct ivpu_device *vdev);
+void ivpu_ipc_irq_work_fn(struct work_struct *work);
 
 void ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-			   u32 channel);
+			   u32 channel, ivpu_ipc_rx_callback_t callback);
 void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons);
 
+int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
+		  struct vpu_jsm_msg *req);
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *ipc_payload,
+		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *jsm_msg,
 		     unsigned long timeout_ms);
-
+int ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+				   enum vpu_ipc_msg_type expected_resp_type,
+				   struct vpu_jsm_msg *resp, u32 channel, unsigned long timeout_ms);
 int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-			  enum vpu_ipc_msg_type expected_resp_type,
-			  struct vpu_jsm_msg *resp, u32 channel,
-			  unsigned long timeout_ms);
+			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+			  u32 channel, unsigned long timeout_ms);
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms);
 
 #endif /* __IVPU_IPC_H__ */
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 8983e3a4fdf9..060f1fc031d3 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -1,162 +1,373 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <drm/drm_file.h>
 
 #include <linux/bitfield.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 #include <linux/module.h>
 #include <uapi/drm/ivpu_accel.h>
 
 #include "ivpu_drv.h"
+#include "ivpu_fw.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
+#include "ivpu_mmu.h"
 #include "ivpu_pm.h"
+#include "ivpu_trace.h"
+#include "vpu_boot_api.h"
 
 #define CMD_BUF_IDX	     0
-#define JOB_ID_JOB_MASK	     GENMASK(7, 0)
-#define JOB_ID_CONTEXT_MASK  GENMASK(31, 8)
 #define JOB_MAX_BUFFER_COUNT 65535
 
-static unsigned int ivpu_tdr_timeout_ms;
-module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, uint, 0644);
-MODULE_PARM_DESC(tdr_timeout_ms, "Timeout for device hang detection, in milliseconds, 0 - default");
-
 static void ivpu_cmdq_ring_db(struct ivpu_device *vdev, struct ivpu_cmdq *cmdq)
 {
-	ivpu_hw_reg_db_set(vdev, cmdq->db_id);
+	ivpu_hw_db_set(vdev, cmdq->db_id);
 }
 
-static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv, u16 engine)
+static int ivpu_preemption_buffers_create(struct ivpu_device *vdev,
+					  struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+{
+	u64 primary_size = ALIGN(vdev->fw->primary_preempt_buf_size, PAGE_SIZE);
+	u64 secondary_size = ALIGN(vdev->fw->secondary_preempt_buf_size, PAGE_SIZE);
+
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW ||
+	    ivpu_test_mode & IVPU_TEST_MODE_MIP_DISABLE)
+		return 0;
+
+	cmdq->primary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &vdev->hw->ranges.user,
+						   primary_size, DRM_IVPU_BO_WC);
+	if (!cmdq->primary_preempt_buf) {
+		ivpu_err(vdev, "Failed to create primary preemption buffer\n");
+		return -ENOMEM;
+	}
+
+	cmdq->secondary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &vdev->hw->ranges.dma,
+						     secondary_size, DRM_IVPU_BO_WC);
+	if (!cmdq->secondary_preempt_buf) {
+		ivpu_err(vdev, "Failed to create secondary preemption buffer\n");
+		goto err_free_primary;
+	}
+
+	return 0;
+
+err_free_primary:
+	ivpu_bo_free(cmdq->primary_preempt_buf);
+	cmdq->primary_preempt_buf = NULL;
+	return -ENOMEM;
+}
+
+static void ivpu_preemption_buffers_free(struct ivpu_device *vdev,
+					 struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+{
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
+		return;
+
+	if (cmdq->primary_preempt_buf)
+		ivpu_bo_free(cmdq->primary_preempt_buf);
+	if (cmdq->secondary_preempt_buf)
+		ivpu_bo_free(cmdq->secondary_preempt_buf);
+}
+
+static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
-	struct vpu_job_queue_header *jobq_header;
 	struct ivpu_cmdq *cmdq;
+	int ret;
 
 	cmdq = kzalloc(sizeof(*cmdq), GFP_KERNEL);
 	if (!cmdq)
 		return NULL;
 
-	cmdq->mem = ivpu_bo_alloc_internal(vdev, 0, SZ_4K, DRM_IVPU_BO_WC);
+	cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!cmdq->mem)
-		goto cmdq_free;
-
-	cmdq->db_id = file_priv->ctx.id + engine * ivpu_get_context_count(vdev);
-	cmdq->entry_count = (u32)((ivpu_bo_size(cmdq->mem) - sizeof(struct vpu_job_queue_header)) /
-				  sizeof(struct vpu_job_queue_entry));
+		goto err_free_cmdq;
 
-	cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem);
-	jobq_header = &cmdq->jobq->header;
-	jobq_header->engine_idx = engine;
-	jobq_header->head = 0;
-	jobq_header->tail = 0;
-	wmb(); /* Flush WC buffer for jobq->header */
+	ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq);
+	if (ret)
+		ivpu_warn(vdev, "Failed to allocate preemption buffers, preemption limited\n");
 
 	return cmdq;
 
-cmdq_free:
+err_free_cmdq:
 	kfree(cmdq);
 	return NULL;
 }
 
-static void ivpu_cmdq_free(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+/**
+ * ivpu_cmdq_get_entry_count - Calculate the number of entries in the command queue.
+ * @cmdq: Pointer to the command queue structure.
+ *
+ * Returns the number of entries that can fit in the command queue memory.
+ */
+static inline u32 ivpu_cmdq_get_entry_count(struct ivpu_cmdq *cmdq)
 {
-	if (!cmdq)
-		return;
+	size_t size = ivpu_bo_size(cmdq->mem) - sizeof(struct vpu_job_queue_header);
+
+	return size / sizeof(struct vpu_job_queue_entry);
+}
 
-	ivpu_bo_free_internal(cmdq->mem);
+/**
+ * ivpu_cmdq_get_flags - Get command queue flags based on input flags and test mode.
+ * @vdev: Pointer to the ivpu device structure.
+ * @flags: Input flags to determine the command queue flags.
+ *
+ * Returns the calculated command queue flags, considering both the input flags
+ * and the current test mode settings.
+ */
+static u32 ivpu_cmdq_get_flags(struct ivpu_device *vdev, u32 flags)
+{
+	u32 cmdq_flags = 0;
+
+	if ((flags & DRM_IVPU_CMDQ_FLAG_TURBO) && (ivpu_hw_ip_gen(vdev) >= IVPU_HW_IP_40XX))
+		cmdq_flags |= VPU_JOB_QUEUE_FLAGS_TURBO_MODE;
+
+	/* Test mode can override the TURBO flag coming from the application */
+	if (ivpu_test_mode & IVPU_TEST_MODE_TURBO_ENABLE)
+		cmdq_flags |= VPU_JOB_QUEUE_FLAGS_TURBO_MODE;
+	if (ivpu_test_mode & IVPU_TEST_MODE_TURBO_DISABLE)
+		cmdq_flags &= ~VPU_JOB_QUEUE_FLAGS_TURBO_MODE;
+
+	return cmdq_flags;
+}
+
+static void ivpu_cmdq_free(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+{
+	ivpu_preemption_buffers_free(file_priv->vdev, file_priv, cmdq);
+	ivpu_bo_free(cmdq->mem);
 	kfree(cmdq);
 }
 
-static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u16 engine)
+static struct ivpu_cmdq *ivpu_cmdq_create(struct ivpu_file_priv *file_priv, u8 priority, u32 flags)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[engine];
+	struct ivpu_cmdq *cmdq = NULL;
 	int ret;
 
 	lockdep_assert_held(&file_priv->lock);
 
+	cmdq = ivpu_cmdq_alloc(file_priv);
 	if (!cmdq) {
-		cmdq = ivpu_cmdq_alloc(file_priv, engine);
-		if (!cmdq)
-			return NULL;
-		file_priv->cmdq[engine] = cmdq;
+		ivpu_err(vdev, "Failed to allocate command queue\n");
+		return NULL;
 	}
+	ret = xa_alloc_cyclic(&file_priv->cmdq_xa, &cmdq->id, cmdq, file_priv->cmdq_limit,
+			      &file_priv->cmdq_id_next, GFP_KERNEL);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to allocate command queue ID: %d\n", ret);
+		goto err_free_cmdq;
+	}
+
+	cmdq->entry_count = ivpu_cmdq_get_entry_count(cmdq);
+	cmdq->priority = priority;
 
-	if (cmdq->db_registered)
-		return cmdq;
+	cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem);
+	cmdq->jobq->header.engine_idx = VPU_ENGINE_COMPUTE;
+	cmdq->jobq->header.flags = ivpu_cmdq_get_flags(vdev, flags);
+
+	ivpu_dbg(vdev, JOB, "Command queue %d created, ctx %d, flags 0x%08x\n",
+		 cmdq->id, file_priv->ctx.id, cmdq->jobq->header.flags);
+	return cmdq;
 
-	ret = ivpu_jsm_register_db(vdev, file_priv->ctx.id, cmdq->db_id,
-				   cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
+err_free_cmdq:
+	ivpu_cmdq_free(file_priv, cmdq);
+	return NULL;
+}
+
+static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 engine,
+			      u8 priority)
+{
+	struct ivpu_device *vdev = file_priv->vdev;
+	int ret;
+
+	ret = ivpu_jsm_hws_create_cmdq(vdev, file_priv->ctx.id, file_priv->ctx.id, cmdq->id,
+				       task_pid_nr(current), engine,
+				       cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
 	if (ret)
-		return NULL;
+		return ret;
 
-	cmdq->db_registered = true;
+	ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id,
+							priority);
+	if (ret)
+		return ret;
 
-	return cmdq;
+	return 0;
 }
 
-static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engine)
+static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
 {
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[engine];
+	struct ivpu_device *vdev = file_priv->vdev;
+	int ret;
+
+	ret = xa_alloc_cyclic(&vdev->db_xa, &cmdq->db_id, NULL, vdev->db_limit, &vdev->db_next,
+			      GFP_KERNEL);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to allocate doorbell ID: %d\n", ret);
+		return ret;
+	}
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+		ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->id, cmdq->db_id,
+					       cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
+	else
+		ret = ivpu_jsm_register_db(vdev, file_priv->ctx.id, cmdq->db_id,
+					   cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
+
+	if (!ret)
+		ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d priority %d\n",
+			 cmdq->db_id, cmdq->id, file_priv->ctx.id, cmdq->priority);
+	else
+		xa_erase(&vdev->db_xa, cmdq->db_id);
+
+	return ret;
+}
+
+static void ivpu_cmdq_jobq_reset(struct ivpu_device *vdev, struct vpu_job_queue *jobq)
+{
+	jobq->header.head = 0;
+	jobq->header.tail = 0;
+
+	wmb(); /* Flush WC buffer for jobq->header */
+}
+
+static int ivpu_cmdq_register(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+{
+	struct ivpu_device *vdev = file_priv->vdev;
+	int ret;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	if (cmdq) {
-		file_priv->cmdq[engine] = NULL;
-		if (cmdq->db_registered)
-			ivpu_jsm_unregister_db(file_priv->vdev, cmdq->db_id);
+	if (cmdq->db_id)
+		return 0;
 
-		ivpu_cmdq_free(file_priv, cmdq);
+	ivpu_cmdq_jobq_reset(vdev, cmdq->jobq);
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, cmdq->priority);
+		if (ret)
+			return ret;
 	}
+
+	ret = ivpu_register_db(file_priv, cmdq);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv)
+static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
 {
-	int i;
+	struct ivpu_device *vdev = file_priv->vdev;
+	int ret;
 
-	mutex_lock(&file_priv->lock);
+	lockdep_assert_held(&file_priv->lock);
 
-	for (i = 0; i < IVPU_NUM_ENGINES; i++)
-		ivpu_cmdq_release_locked(file_priv, i);
+	if (!cmdq->db_id)
+		return 0;
 
-	mutex_unlock(&file_priv->lock);
+	ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id);
+	if (!ret)
+		ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id);
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id);
+		if (!ret)
+			ivpu_dbg(vdev, JOB, "Command queue %d destroyed, ctx %d\n",
+				 cmdq->id, file_priv->ctx.id);
+	}
+
+	xa_erase(&file_priv->vdev->db_xa, cmdq->db_id);
+	cmdq->db_id = 0;
+
+	return 0;
 }
 
-/*
- * Mark the doorbell as unregistered and reset job queue pointers.
- * This function needs to be called when the VPU hardware is restarted
- * and FW looses job queue state. The next time job queue is used it
- * will be registered again.
- */
-static void ivpu_cmdq_reset_locked(struct ivpu_file_priv *file_priv, u16 engine)
+static inline u8 ivpu_job_to_jsm_priority(u8 priority)
 {
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[engine];
+	if (priority == DRM_IVPU_JOB_PRIORITY_DEFAULT)
+		return VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL;
+
+	return priority - 1;
+}
+
+static void ivpu_cmdq_destroy(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+{
+	ivpu_cmdq_unregister(file_priv, cmdq);
+	xa_erase(&file_priv->cmdq_xa, cmdq->id);
+	ivpu_cmdq_free(file_priv, cmdq);
+}
+
+static struct ivpu_cmdq *ivpu_cmdq_acquire_legacy(struct ivpu_file_priv *file_priv, u8 priority)
+{
+	struct ivpu_cmdq *cmdq;
+	unsigned long id;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	if (cmdq) {
-		cmdq->db_registered = false;
-		cmdq->jobq->header.head = 0;
-		cmdq->jobq->header.tail = 0;
-		wmb(); /* Flush WC buffer for jobq header */
+	xa_for_each(&file_priv->cmdq_xa, id, cmdq)
+		if (cmdq->is_legacy && cmdq->priority == priority)
+			break;
+
+	if (!cmdq) {
+		cmdq = ivpu_cmdq_create(file_priv, priority, 0);
+		if (!cmdq)
+			return NULL;
+		cmdq->is_legacy = true;
 	}
+
+	return cmdq;
 }
 
-static void ivpu_cmdq_reset_all(struct ivpu_file_priv *file_priv)
+static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u32 cmdq_id)
 {
-	int i;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_cmdq *cmdq;
+
+	lockdep_assert_held(&file_priv->lock);
+
+	cmdq = xa_load(&file_priv->cmdq_xa, cmdq_id);
+	if (!cmdq) {
+		ivpu_warn_ratelimited(vdev, "Failed to find command queue with ID: %u\n", cmdq_id);
+		return NULL;
+	}
+
+	return cmdq;
+}
+
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
+{
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
+
+	lockdep_assert_held(&file_priv->lock);
+
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_destroy(file_priv, cmdq);
+}
+
+/*
+ * Mark the doorbell as unregistered
+ * This function needs to be called when the VPU hardware is restarted
+ * and FW loses job queue state. The next time job queue is used it
+ * will be registered again.
+ */
+static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv)
+{
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
 	mutex_lock(&file_priv->lock);
 
-	for (i = 0; i < IVPU_NUM_ENGINES; i++)
-		ivpu_cmdq_reset_locked(file_priv, i);
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) {
+		xa_erase(&file_priv->vdev->db_xa, cmdq->db_id);
+		cmdq->db_id = 0;
+	}
 
 	mutex_unlock(&file_priv->lock);
 }
@@ -166,15 +377,32 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev)
 	struct ivpu_file_priv *file_priv;
 	unsigned long ctx_id;
 
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		file_priv = ivpu_file_priv_get_by_ctx_id(vdev, ctx_id);
-		if (!file_priv)
-			continue;
+	mutex_lock(&vdev->context_list_lock);
 
-		ivpu_cmdq_reset_all(file_priv);
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		ivpu_cmdq_reset(file_priv);
 
-		ivpu_file_priv_put(&file_priv);
-	}
+	mutex_unlock(&vdev->context_list_lock);
+}
+
+void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv)
+{
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
+
+	lockdep_assert_held(&file_priv->lock);
+	ivpu_dbg(vdev, JOB, "Context ID: %u abort\n", file_priv->ctx.id);
+
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_unregister(file_priv, cmdq);
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_OS)
+		ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+
+	ivpu_mmu_disable_ssid_events(vdev, file_priv->ctx.id);
+
+	file_priv->aborted = true;
 }
 
 static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
@@ -187,15 +415,31 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
 
 	/* Check if there is space left in job queue */
 	if (next_entry == header->head) {
-		ivpu_dbg(vdev, JOB, "Job queue full: ctx %d engine %d db %d head %d tail %d\n",
-			 job->file_priv->ctx.id, job->engine_idx, cmdq->db_id, header->head, tail);
+		ivpu_dbg(vdev, JOB, "Job queue full: ctx %d cmdq %d db %d head %d tail %d\n",
+			 job->file_priv->ctx.id, cmdq->id, cmdq->db_id, header->head, tail);
 		return -EBUSY;
 	}
 
-	entry = &cmdq->jobq->job[tail];
+	entry = &cmdq->jobq->slot[tail].job;
 	entry->batch_buf_addr = job->cmd_buf_vpu_addr;
 	entry->job_id = job->job_id;
 	entry->flags = 0;
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_SUBMISSION))
+		entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		if (cmdq->primary_preempt_buf) {
+			entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr;
+			entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_preempt_buf);
+		}
+
+		if (cmdq->secondary_preempt_buf) {
+			entry->secondary_preempt_buf_addr = cmdq->secondary_preempt_buf->vpu_addr;
+			entry->secondary_preempt_buf_size =
+				ivpu_bo_size(cmdq->secondary_preempt_buf);
+		}
+	}
+
 	wmb(); /* Ensure that tail is updated after filling entry */
 	header->tail = next_entry;
 	wmb(); /* Flush WC buffer for jobq header */
@@ -246,60 +490,32 @@ static struct dma_fence *ivpu_fence_create(struct ivpu_device *vdev)
 	return &fence->base;
 }
 
-static void job_get(struct ivpu_job *job, struct ivpu_job **link)
+static void ivpu_job_destroy(struct ivpu_job *job)
 {
 	struct ivpu_device *vdev = job->vdev;
-
-	kref_get(&job->ref);
-	*link = job;
-
-	ivpu_dbg(vdev, KREF, "Job get: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-}
-
-static void job_release(struct kref *ref)
-{
-	struct ivpu_job *job = container_of(ref, struct ivpu_job, ref);
-	struct ivpu_device *vdev = job->vdev;
 	u32 i;
 
+	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d cmdq_id %u engine %d",
+		 job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx);
+
 	for (i = 0; i < job->bo_count; i++)
 		if (job->bos[i])
-			drm_gem_object_put(&job->bos[i]->base);
+			drm_gem_object_put(&job->bos[i]->base.base);
 
 	dma_fence_put(job->done_fence);
 	ivpu_file_priv_put(&job->file_priv);
-
-	ivpu_dbg(vdev, KREF, "Job released: id %u\n", job->job_id);
 	kfree(job);
-
-	/* Allow the VPU to get suspended, must be called after ivpu_file_priv_put() */
-	ivpu_rpm_put(vdev);
-}
-
-static void job_put(struct ivpu_job *job)
-{
-	struct ivpu_device *vdev = job->vdev;
-
-	ivpu_dbg(vdev, KREF, "Job put: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-	kref_put(&job->ref, job_release);
 }
 
 static struct ivpu_job *
-ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
+ivpu_job_create(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_job *job;
-	int ret;
-
-	ret = ivpu_rpm_get(vdev);
-	if (ret < 0)
-		return NULL;
 
 	job = kzalloc(struct_size(job, bos, bo_count), GFP_KERNEL);
 	if (!job)
-		goto err_rpm_put;
-
-	kref_init(&job->ref);
+		return NULL;
 
 	job->vdev = vdev;
 	job->engine_idx = engine_idx;
@@ -312,113 +528,187 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 
 	job->file_priv = ivpu_file_priv_get(file_priv);
 
+	trace_job("create", job);
 	ivpu_dbg(vdev, JOB, "Job created: ctx %2d engine %d", file_priv->ctx.id, job->engine_idx);
-
 	return job;
 
 err_free_job:
 	kfree(job);
-err_rpm_put:
-	ivpu_rpm_put(vdev);
 	return NULL;
 }
 
-static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
+static struct ivpu_job *ivpu_job_remove_from_submitted_jobs(struct ivpu_device *vdev, u32 job_id)
 {
 	struct ivpu_job *job;
 
+	lockdep_assert_held(&vdev->submitted_jobs_lock);
+
 	job = xa_erase(&vdev->submitted_jobs_xa, job_id);
+	if (xa_empty(&vdev->submitted_jobs_xa) && job) {
+		vdev->busy_time = ktime_add(ktime_sub(ktime_get(), vdev->busy_start_ts),
+					    vdev->busy_time);
+	}
+
+	return job;
+}
+
+static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 job_status)
+{
+	struct ivpu_job *job;
+
+	lockdep_assert_held(&vdev->submitted_jobs_lock);
+
+	job = xa_load(&vdev->submitted_jobs_xa, job_id);
+	if (!job)
+		return -ENOENT;
+
+	if (job_status == VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW) {
+		guard(mutex)(&job->file_priv->lock);
+
+		if (job->file_priv->has_mmu_faults)
+			return 0;
+
+		/*
+		 * Mark context as faulty and defer destruction of the job to jobs abort thread
+		 * handler to synchronize between both faults and jobs returning context violation
+		 * status and ensure both are handled in the same way
+		 */
+		job->file_priv->has_mmu_faults = true;
+		queue_work(system_wq, &vdev->context_abort_work);
+		return 0;
+	}
+
+	job = ivpu_job_remove_from_submitted_jobs(vdev, job_id);
 	if (!job)
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
 
-	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d engine %d status 0x%x\n",
-		 job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status);
+	trace_job("done", job);
+	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d cmdq_id %u engine %d status 0x%x\n",
+		 job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx, job_status);
+
+	ivpu_job_destroy(job);
+	ivpu_stop_job_timeout_detection(vdev);
+
+	ivpu_rpm_put(vdev);
+
+	if (!xa_empty(&vdev->submitted_jobs_xa))
+		ivpu_start_job_timeout_detection(vdev);
 
-	job_put(job);
 	return 0;
 }
 
-static void ivpu_job_done_message(struct ivpu_device *vdev, void *msg)
+void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 {
-	struct vpu_ipc_msg_payload_job_done *payload;
-	struct vpu_jsm_msg *job_ret_msg = msg;
-	int ret;
+	struct ivpu_job *job;
+	unsigned long id;
 
-	payload = (struct vpu_ipc_msg_payload_job_done *)&job_ret_msg->payload;
+	mutex_lock(&vdev->submitted_jobs_lock);
 
-	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
-	if (ret)
-		ivpu_err(vdev, "Failed to finish job %d: %d\n", payload->job_id, ret);
+	xa_for_each(&vdev->submitted_jobs_xa, id, job)
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
+
+	mutex_unlock(&vdev->submitted_jobs_lock);
 }
 
-void ivpu_jobs_abort_all(struct ivpu_device *vdev)
+void ivpu_cmdq_abort_all_jobs(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id)
 {
 	struct ivpu_job *job;
 	unsigned long id;
 
+	mutex_lock(&vdev->submitted_jobs_lock);
+
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_done(vdev, id, VPU_JSM_STATUS_ABORTED);
+		if (job->file_priv->ctx.id == ctx_id && job->cmdq_id == cmdq_id)
+			ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
+
+	mutex_unlock(&vdev->submitted_jobs_lock);
 }
 
-static int ivpu_direct_job_submission(struct ivpu_job *job)
+static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id)
 {
 	struct ivpu_file_priv *file_priv = job->file_priv;
 	struct ivpu_device *vdev = job->vdev;
-	struct xa_limit job_id_range;
 	struct ivpu_cmdq *cmdq;
+	bool is_first_job;
 	int ret;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&vdev->submitted_jobs_lock);
 	mutex_lock(&file_priv->lock);
 
-	cmdq = ivpu_cmdq_acquire(job->file_priv, job->engine_idx);
+	if (cmdq_id == 0)
+		cmdq = ivpu_cmdq_acquire_legacy(file_priv, priority);
+	else
+		cmdq = ivpu_cmdq_acquire(file_priv, cmdq_id);
 	if (!cmdq) {
-		ivpu_warn(vdev, "Failed get job queue, ctx %d engine %d\n",
-			  file_priv->ctx.id, job->engine_idx);
+		ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d\n", file_priv->ctx.id);
 		ret = -EINVAL;
 		goto err_unlock;
 	}
 
-	job_id_range.min = FIELD_PREP(JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
-	job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK;
-
-	job_get(job, &job);
-	ret = xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
+	ret = ivpu_cmdq_register(file_priv, cmdq);
 	if (ret) {
-		ivpu_warn_ratelimited(vdev, "Failed to allocate job id: %d\n", ret);
-		goto err_job_put;
+		ivpu_err(vdev, "Failed to register command queue: %d\n", ret);
+		goto err_unlock;
+	}
+
+	job->cmdq_id = cmdq->id;
+
+	is_first_job = xa_empty(&vdev->submitted_jobs_xa);
+	ret = xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit,
+			      &file_priv->job_id_next, GFP_KERNEL);
+	if (ret < 0) {
+		ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n",
+			 file_priv->ctx.id);
+		ret = -EBUSY;
+		goto err_unlock;
 	}
 
 	ret = ivpu_cmdq_push_job(cmdq, job);
 	if (ret)
-		goto err_xa_erase;
+		goto err_erase_xa;
 
-	ivpu_dbg(vdev, JOB, "Job submitted: id %3u addr 0x%llx ctx %2d engine %d next %d\n",
-		 job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
-		 job->engine_idx, cmdq->jobq->header.tail);
+	ivpu_start_job_timeout_detection(vdev);
 
-	if (ivpu_test_mode == IVPU_TEST_MODE_NULL_HW) {
-		ivpu_job_done(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) {
 		cmdq->jobq->header.head = cmdq->jobq->header.tail;
 		wmb(); /* Flush WC buffer for jobq header */
 	} else {
 		ivpu_cmdq_ring_db(vdev, cmdq);
+		if (is_first_job)
+			vdev->busy_start_ts = ktime_get();
 	}
 
+	trace_job("submit", job);
+	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d cmdq_id %u engine %d prio %d addr 0x%llx next %d\n",
+		 job->job_id, file_priv->ctx.id, cmdq->id, job->engine_idx, cmdq->priority,
+		 job->cmd_buf_vpu_addr, cmdq->jobq->header.tail);
+
 	mutex_unlock(&file_priv->lock);
+
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) {
+		ivpu_job_signal_and_destroy(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+	}
+
+	mutex_unlock(&vdev->submitted_jobs_lock);
+
 	return 0;
 
-err_xa_erase:
+err_erase_xa:
 	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
-err_job_put:
-	job_put(job);
 err_unlock:
 	mutex_unlock(&file_priv->lock);
+	mutex_unlock(&vdev->submitted_jobs_lock);
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -426,7 +716,7 @@ static int
 ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32 *buf_handles,
 				u32 buf_count, u32 commands_offset)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_file_priv *file_priv = job->file_priv;
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ww_acquire_ctx acquire_ctx;
 	enum dma_resv_usage usage;
@@ -448,7 +738,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 	}
 
 	bo = job->bos[CMD_BUF_IDX];
-	if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ)) {
+	if (!dma_resv_test_signaled(bo->base.base.resv, DMA_RESV_USAGE_READ)) {
 		ivpu_warn(vdev, "Buffer is already in use\n");
 		return -EBUSY;
 	}
@@ -468,7 +758,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 	}
 
 	for (i = 0; i < buf_count; i++) {
-		ret = dma_resv_reserve_fences(job->bos[i]->base.resv, 1);
+		ret = dma_resv_reserve_fences(job->bos[i]->base.base.resv, 1);
 		if (ret) {
 			ivpu_warn(vdev, "Failed to reserve fences: %d\n", ret);
 			goto unlock_reservations;
@@ -477,7 +767,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 
 	for (i = 0; i < buf_count; i++) {
 		usage = (i == CMD_BUF_IDX) ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_BOOKKEEP;
-		dma_resv_add_fence(job->bos[i]->base.resv, job->done_fence, usage);
+		dma_resv_add_fence(job->bos[i]->base.base.resv, job->done_fence, usage);
 	}
 
 unlock_reservations:
@@ -488,135 +778,277 @@ unlock_reservations:
 	return ret;
 }
 
-int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+static int ivpu_submit(struct drm_file *file, struct ivpu_file_priv *file_priv, u32 cmdq_id,
+		       u32 buffer_count, u32 engine, void __user *buffers_ptr, u32 cmds_offset,
+		       u8 priority)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct ivpu_device *vdev = file_priv->vdev;
-	struct drm_ivpu_submit *params = data;
 	struct ivpu_job *job;
 	u32 *buf_handles;
 	int idx, ret;
 
-	if (params->engine > DRM_IVPU_ENGINE_COPY)
-		return -EINVAL;
-
-	if (params->buffer_count == 0 || params->buffer_count > JOB_MAX_BUFFER_COUNT)
-		return -EINVAL;
-
-	if (!IS_ALIGNED(params->commands_offset, 8))
-		return -EINVAL;
-
-	if (!file_priv->ctx.id)
-		return -EINVAL;
-
-	if (file_priv->has_mmu_faults)
-		return -EBADFD;
-
-	buf_handles = kcalloc(params->buffer_count, sizeof(u32), GFP_KERNEL);
+	buf_handles = kcalloc(buffer_count, sizeof(u32), GFP_KERNEL);
 	if (!buf_handles)
 		return -ENOMEM;
 
-	ret = copy_from_user(buf_handles,
-			     (void __user *)params->buffers_ptr,
-			     params->buffer_count * sizeof(u32));
+	ret = copy_from_user(buf_handles, buffers_ptr, buffer_count * sizeof(u32));
 	if (ret) {
 		ret = -EFAULT;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
 	if (!drm_dev_enter(&vdev->drm, &idx)) {
 		ret = -ENODEV;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
-	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n",
-		 file_priv->ctx.id, params->buffer_count);
+	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u cmdq_id %u buf_count %u\n",
+		 file_priv->ctx.id, cmdq_id, buffer_count);
 
-	job = ivpu_create_job(file_priv, params->engine, params->buffer_count);
+	job = ivpu_job_create(file_priv, engine, buffer_count);
 	if (!job) {
 		ivpu_err(vdev, "Failed to create job\n");
 		ret = -ENOMEM;
-		goto dev_exit;
+		goto err_exit_dev;
 	}
 
-	ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, params->buffer_count,
-					      params->commands_offset);
+	ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, buffer_count, cmds_offset);
 	if (ret) {
-		ivpu_err(vdev, "Failed to prepare job, ret %d\n", ret);
-		goto job_put;
+		ivpu_err(vdev, "Failed to prepare job: %d\n", ret);
+		goto err_destroy_job;
 	}
 
-	ret = ivpu_direct_job_submission(job);
-	if (ret) {
-		dma_fence_signal(job->done_fence);
-		ivpu_err(vdev, "Failed to submit job to the HW, ret %d\n", ret);
-	}
+	down_read(&vdev->pm->reset_lock);
+	ret = ivpu_job_submit(job, priority, cmdq_id);
+	up_read(&vdev->pm->reset_lock);
+	if (ret)
+		goto err_signal_fence;
 
-job_put:
-	job_put(job);
-dev_exit:
 	drm_dev_exit(idx);
-free_handles:
 	kfree(buf_handles);
+	return ret;
 
+err_signal_fence:
+	dma_fence_signal(job->done_fence);
+err_destroy_job:
+	ivpu_job_destroy(job);
+err_exit_dev:
+	drm_dev_exit(idx);
+err_free_handles:
+	kfree(buf_handles);
 	return ret;
 }
 
-static int ivpu_job_done_thread(void *arg)
+int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct drm_ivpu_submit *args = data;
+	u8 priority;
+
+	if (args->engine != DRM_IVPU_ENGINE_COMPUTE)
+		return -EINVAL;
+
+	if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
+		return -EINVAL;
+
+	if (args->buffer_count == 0 || args->buffer_count > JOB_MAX_BUFFER_COUNT)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(args->commands_offset, 8))
+		return -EINVAL;
+
+	if (!file_priv->ctx.id)
+		return -EINVAL;
+
+	if (file_priv->has_mmu_faults)
+		return -EBADFD;
+
+	priority = ivpu_job_to_jsm_priority(args->priority);
+
+	return ivpu_submit(file, file_priv, 0, args->buffer_count, args->engine,
+			   (void __user *)args->buffers_ptr, args->commands_offset, priority);
+}
+
+int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct drm_ivpu_cmdq_submit *args = data;
+
+	if (!ivpu_is_capable(file_priv->vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
+		return -ENODEV;
+
+	if (args->cmdq_id < IVPU_CMDQ_MIN_ID || args->cmdq_id > IVPU_CMDQ_MAX_ID)
+		return -EINVAL;
+
+	if (args->buffer_count == 0 || args->buffer_count > JOB_MAX_BUFFER_COUNT)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(args->commands_offset, 8))
+		return -EINVAL;
+
+	if (!file_priv->ctx.id)
+		return -EINVAL;
+
+	if (file_priv->has_mmu_faults)
+		return -EBADFD;
+
+	return ivpu_submit(file, file_priv, args->cmdq_id, args->buffer_count, VPU_ENGINE_COMPUTE,
+			   (void __user *)args->buffers_ptr, args->commands_offset, 0);
+}
+
+int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_device *vdev = (struct ivpu_device *)arg;
-	struct ivpu_ipc_consumer cons;
-	struct vpu_jsm_msg jsm_msg;
-	bool jobs_submitted;
-	unsigned int timeout;
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct drm_ivpu_cmdq_create *args = data;
+	struct ivpu_cmdq *cmdq;
 	int ret;
 
-	ivpu_dbg(vdev, JOB, "Started %s\n", __func__);
-
-	ivpu_ipc_consumer_add(vdev, &cons, VPU_IPC_CHAN_JOB_RET);
-
-	while (!kthread_should_stop()) {
-		timeout = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
-		jobs_submitted = !xa_empty(&vdev->submitted_jobs_xa);
-		ret = ivpu_ipc_receive(vdev, &cons, NULL, &jsm_msg, timeout);
-		if (!ret) {
-			ivpu_job_done_message(vdev, &jsm_msg);
-		} else if (ret == -ETIMEDOUT) {
-			if (jobs_submitted && !xa_empty(&vdev->submitted_jobs_xa)) {
-				ivpu_err(vdev, "TDR detected, timeout %d ms", timeout);
-				ivpu_hw_diagnose_failure(vdev);
-				ivpu_pm_schedule_recovery(vdev);
-			}
-		}
+	if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
+		return -ENODEV;
+
+	if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
+		return -EINVAL;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&file_priv->lock);
+
+	cmdq = ivpu_cmdq_create(file_priv, ivpu_job_to_jsm_priority(args->priority), args->flags);
+	if (cmdq)
+		args->cmdq_id = cmdq->id;
+
+	mutex_unlock(&file_priv->lock);
+
+	ivpu_rpm_put(vdev);
+
+	return cmdq ? 0 : -ENOMEM;
+}
+
+int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct drm_ivpu_cmdq_destroy *args = data;
+	struct ivpu_cmdq *cmdq;
+	u32 cmdq_id = 0;
+	int ret;
+
+	if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
+		return -ENODEV;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&file_priv->lock);
+
+	cmdq = xa_load(&file_priv->cmdq_xa, args->cmdq_id);
+	if (!cmdq || cmdq->is_legacy) {
+		ret = -ENOENT;
+	} else {
+		cmdq_id = cmdq->id;
+		ivpu_cmdq_destroy(file_priv, cmdq);
+		ret = 0;
 	}
 
-	ivpu_ipc_consumer_del(vdev, &cons);
+	mutex_unlock(&file_priv->lock);
 
-	ivpu_jobs_abort_all(vdev);
+	/* Abort any pending jobs only if cmdq was destroyed */
+	if (!ret)
+		ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
 
-	ivpu_dbg(vdev, JOB, "Stopped %s\n", __func__);
-	return 0;
+	ivpu_rpm_put(vdev);
+
+	return ret;
 }
 
-int ivpu_job_done_thread_init(struct ivpu_device *vdev)
+static void
+ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
+		       struct vpu_jsm_msg *jsm_msg)
 {
-	struct task_struct *thread;
+	struct vpu_ipc_msg_payload_job_done *payload;
 
-	thread = kthread_run(&ivpu_job_done_thread, (void *)vdev, "ivpu_job_done_thread");
-	if (IS_ERR(thread)) {
-		ivpu_err(vdev, "Failed to start job completion thread\n");
-		return -EIO;
+	if (!jsm_msg) {
+		ivpu_err(vdev, "IPC message has no JSM payload\n");
+		return;
 	}
 
-	get_task_struct(thread);
-	wake_up_process(thread);
+	if (jsm_msg->result != VPU_JSM_STATUS_SUCCESS) {
+		ivpu_err(vdev, "Invalid JSM message result: %d\n", jsm_msg->result);
+		return;
+	}
 
-	vdev->job_done_thread = thread;
+	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
 
-	return 0;
+	mutex_lock(&vdev->submitted_jobs_lock);
+	ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
+	mutex_unlock(&vdev->submitted_jobs_lock);
 }
 
-void ivpu_job_done_thread_fini(struct ivpu_device *vdev)
+void ivpu_job_done_consumer_init(struct ivpu_device *vdev)
 {
-	kthread_stop_put(vdev->job_done_thread);
+	ivpu_ipc_consumer_add(vdev, &vdev->job_done_consumer,
+			      VPU_IPC_CHAN_JOB_RET, ivpu_job_done_callback);
+}
+
+void ivpu_job_done_consumer_fini(struct ivpu_device *vdev)
+{
+	ivpu_ipc_consumer_del(vdev, &vdev->job_done_consumer);
+}
+
+void ivpu_context_abort_work_fn(struct work_struct *work)
+{
+	struct ivpu_device *vdev = container_of(work, struct ivpu_device, context_abort_work);
+	struct ivpu_file_priv *file_priv;
+	struct ivpu_job *job;
+	unsigned long ctx_id;
+	unsigned long id;
+
+	if (drm_WARN_ON(&vdev->drm, pm_runtime_get_if_active(vdev->drm.dev) <= 0))
+		return;
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+		if (ivpu_jsm_reset_engine(vdev, 0))
+			return;
+
+	mutex_lock(&vdev->context_list_lock);
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
+		if (!file_priv->has_mmu_faults || file_priv->aborted)
+			continue;
+
+		mutex_lock(&file_priv->lock);
+		ivpu_context_abort_locked(file_priv);
+		mutex_unlock(&file_priv->lock);
+	}
+	mutex_unlock(&vdev->context_list_lock);
+
+	/*
+	 * We will not receive new MMU event interrupts until existing events are discarded
+	 * however, we want to discard these events only after aborting the faulty context
+	 * to avoid generating new faults from that context
+	 */
+	ivpu_mmu_discard_events(vdev);
+
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
+		goto runtime_put;
+
+	if (ivpu_jsm_hws_resume_engine(vdev, 0))
+		return;
+	/*
+	 * In hardware scheduling mode NPU already has stopped processing jobs
+	 * and won't send us any further notifications, thus we have to free job related resources
+	 * and notify userspace
+	 */
+	mutex_lock(&vdev->submitted_jobs_lock);
+	xa_for_each(&vdev->submitted_jobs_xa, id, job)
+		if (job->file_priv->aborted)
+			ivpu_job_signal_and_destroy(vdev, job->job_id, DRM_IVPU_JOB_STATUS_ABORTED);
+	mutex_unlock(&vdev->submitted_jobs_lock);
+
+runtime_put:
+	pm_runtime_mark_last_busy(vdev->drm.dev);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index 5514c2d8a609..2e301c2eea7b 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_JOB_H__
@@ -24,10 +24,14 @@ struct ivpu_file_priv;
  */
 struct ivpu_cmdq {
 	struct vpu_job_queue *jobq;
+	struct ivpu_bo *primary_preempt_buf;
+	struct ivpu_bo *secondary_preempt_buf;
 	struct ivpu_bo *mem;
 	u32 entry_count;
+	u32 id;
 	u32 db_id;
-	bool db_registered;
+	u8 priority;
+	bool is_legacy;
 };
 
 /**
@@ -43,11 +47,11 @@ struct ivpu_cmdq {
 			  will update the job status
  */
 struct ivpu_job {
-	struct kref ref;
 	struct ivpu_device *vdev;
 	struct ivpu_file_priv *file_priv;
 	struct dma_fence *done_fence;
 	u64 cmd_buf_vpu_addr;
+	u32 cmdq_id;
 	u32 job_id;
 	u32 engine_idx;
 	size_t bo_count;
@@ -55,12 +59,19 @@ struct ivpu_job {
 };
 
 int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv);
+void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv);
+
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv);
 void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
+void ivpu_cmdq_abort_all_jobs(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id);
 
-int ivpu_job_done_thread_init(struct ivpu_device *vdev);
-void ivpu_job_done_thread_fini(struct ivpu_device *vdev);
+void ivpu_job_done_consumer_init(struct ivpu_device *vdev);
+void ivpu_job_done_consumer_fini(struct ivpu_device *vdev);
+void ivpu_context_abort_work_fn(struct work_struct *work);
 
 void ivpu_jobs_abort_all(struct ivpu_device *vdev);
 
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 0c2fe7142024..0256b2dfefc1 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -1,11 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include "ivpu_drv.h"
+#include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
+#include "ivpu_pm.h"
+#include "vpu_jsm_api.h"
 
 const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 {
@@ -36,9 +39,21 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DESTROY_CMD_QUEUE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_REGISTER_DB);
-	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_ENGINE_RESUME);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_JOB_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_RESET_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_PREEMPT_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_REGISTER_DB_DONE);
@@ -65,6 +80,12 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE_DONE);
 	}
 	#undef IVPU_CASE_TO_STR
 
@@ -85,14 +106,10 @@ int ivpu_jsm_register_db(struct ivpu_device *vdev, u32 ctx_id, u32 db_id,
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_REGISTER_DB_DONE, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret) {
-		ivpu_err_ratelimited(vdev, "Failed to register doorbell %d: %d\n", db_id, ret);
-		return ret;
-	}
-
-	ivpu_dbg(vdev, JSM, "Doorbell %d registered to context %d\n", db_id, ctx_id);
+	if (ret)
+		ivpu_err_ratelimited(vdev, "Failed to register doorbell %u: %d\n", db_id, ret);
 
-	return 0;
+	return ret;
 }
 
 int ivpu_jsm_unregister_db(struct ivpu_device *vdev, u32 db_id)
@@ -105,14 +122,10 @@ int ivpu_jsm_unregister_db(struct ivpu_device *vdev, u32 db_id)
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_UNREGISTER_DB_DONE, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret) {
-		ivpu_warn_ratelimited(vdev, "Failed to unregister doorbell %d: %d\n", db_id, ret);
-		return ret;
-	}
-
-	ivpu_dbg(vdev, JSM, "Doorbell %d unregistered\n", db_id);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to unregister doorbell %u: %d\n", db_id, ret);
 
-	return 0;
+	return ret;
 }
 
 int ivpu_jsm_get_heartbeat(struct ivpu_device *vdev, u32 engine, u64 *heartbeat)
@@ -121,7 +134,7 @@ int ivpu_jsm_get_heartbeat(struct ivpu_device *vdev, u32 engine, u64 *heartbeat)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.query_engine_hb.engine_idx = engine;
@@ -144,15 +157,17 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.engine_reset.engine_idx = engine;
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_ENGINE_RESET_DONE, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret)
+	if (ret) {
 		ivpu_err_ratelimited(vdev, "Failed to reset engine %d: %d\n", engine, ret);
+		ivpu_pm_trigger_recovery(vdev, "Engine reset failed");
+	}
 
 	return ret;
 }
@@ -163,7 +178,7 @@ int ivpu_jsm_preempt_engine(struct ivpu_device *vdev, u32 engine, u32 preempt_id
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.engine_preempt.engine_idx = engine;
@@ -186,7 +201,7 @@ int ivpu_jsm_dyndbg_control(struct ivpu_device *vdev, char *command, size_t size
 	strscpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN);
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DYNDBG_CONTROL_RSP, &resp,
-				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+				    VPU_IPC_CHAN_GEN_CMD, vdev->timeout.jsm);
 	if (ret)
 		ivpu_warn_ratelimited(vdev, "Failed to send command \"%s\": ret %d\n",
 				      command, ret);
@@ -237,9 +252,311 @@ int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid)
 {
 	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_SSID_RELEASE };
 	struct vpu_jsm_msg resp;
+	int ret;
 
 	req.payload.ssid_release.host_ssid = host_ssid;
 
-	return ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_SSID_RELEASE_DONE, &resp,
-				     VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_SSID_RELEASE_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to release context: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_PWR_D0I3_ENTER };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	if (IVPU_WA(disable_d0i3_msg))
+		return 0;
+
+	req.payload.pwr_d0i3_enter.send_response = 1;
+
+	ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE, &resp,
+					     VPU_IPC_CHAN_GEN_CMD, vdev->timeout.d0i3_entry_msg);
+	if (ret)
+		return ret;
+
+	return ivpu_hw_wait_for_idle(vdev);
+}
+
+int ivpu_jsm_hws_create_cmdq(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_group, u32 cmdq_id,
+			     u32 pid, u32 engine, u64 cmdq_base, u32 cmdq_size)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_CREATE_CMD_QUEUE };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.hws_create_cmdq.host_ssid = ctx_id;
+	req.payload.hws_create_cmdq.process_id = pid;
+	req.payload.hws_create_cmdq.engine_idx = engine;
+	req.payload.hws_create_cmdq.cmdq_group = cmdq_group;
+	req.payload.hws_create_cmdq.cmdq_id = cmdq_id;
+	req.payload.hws_create_cmdq.cmdq_base = cmdq_base;
+	req.payload.hws_create_cmdq.cmdq_size = cmdq_size;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to create command queue: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_hws_destroy_cmdq(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_DESTROY_CMD_QUEUE };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.hws_destroy_cmdq.host_ssid = ctx_id;
+	req.payload.hws_destroy_cmdq.cmdq_id = cmdq_id;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DESTROY_CMD_QUEUE_RSP, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to destroy command queue: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_hws_register_db(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id, u32 db_id,
+			     u64 cmdq_base, u32 cmdq_size)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_HWS_REGISTER_DB };
+	struct vpu_jsm_msg resp;
+	int ret = 0;
+
+	req.payload.hws_register_db.db_id = db_id;
+	req.payload.hws_register_db.host_ssid = ctx_id;
+	req.payload.hws_register_db.cmdq_id = cmdq_id;
+	req.payload.hws_register_db.cmdq_base = cmdq_base;
+	req.payload.hws_register_db.cmdq_size = cmdq_size;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_REGISTER_DB_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_err_ratelimited(vdev, "Failed to register doorbell %u: %d\n", db_id, ret);
+
+	return ret;
+}
+
+int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_HWS_ENGINE_RESUME };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	if (engine != VPU_ENGINE_COMPUTE)
+		return -EINVAL;
+
+	req.payload.hws_resume_engine.engine_idx = engine;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret) {
+		ivpu_err_ratelimited(vdev, "Failed to resume engine %d: %d\n", engine, ret);
+		ivpu_pm_trigger_recovery(vdev, "Engine resume failed");
+	}
+
+	return ret;
+}
+
+int ivpu_jsm_hws_set_context_sched_properties(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id,
+					      u32 priority)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.hws_set_context_sched_properties.host_ssid = ctx_id;
+	req.payload.hws_set_context_sched_properties.cmdq_id = cmdq_id;
+	req.payload.hws_set_context_sched_properties.priority_band = priority;
+	req.payload.hws_set_context_sched_properties.realtime_priority_level = 0;
+	req.payload.hws_set_context_sched_properties.in_process_priority = 0;
+	req.payload.hws_set_context_sched_properties.context_quantum = 20000;
+	req.payload.hws_set_context_sched_properties.grace_period_same_priority = 10000;
+	req.payload.hws_set_context_sched_properties.grace_period_lower_priority = 0;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to set context sched properties: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_hws_set_scheduling_log(struct ivpu_device *vdev, u32 engine_idx, u32 host_ssid,
+				    u64 vpu_log_buffer_va)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.hws_set_scheduling_log.engine_idx = engine_idx;
+	req.payload.hws_set_scheduling_log.host_ssid = host_ssid;
+	req.payload.hws_set_scheduling_log.vpu_log_buffer_va = vpu_log_buffer_va;
+	req.payload.hws_set_scheduling_log.notify_index = 0;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to set scheduling log: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_hws_setup_priority_bands(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP };
+	struct vpu_jsm_msg resp;
+	struct ivpu_hw_info *hw = vdev->hw;
+	struct vpu_ipc_msg_payload_hws_priority_band_setup *setup =
+		&req.payload.hws_priority_band_setup;
+	int ret;
+
+	for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE;
+	     band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) {
+		setup->grace_period[band] = hw->hws.grace_period[band];
+		setup->process_grace_period[band] = hw->hws.process_grace_period[band];
+		setup->process_quantum[band] = hw->hws.process_quantum[band];
+	}
+	setup->normal_band_percentage = 10;
+
+	ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP,
+					     &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to set priority bands: %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_metric_streamer_start(struct ivpu_device *vdev, u64 metric_group_mask,
+				   u64 sampling_rate, u64 buffer_addr, u64 buffer_size)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_METRIC_STREAMER_START };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.metric_streamer_start.metric_group_mask = metric_group_mask;
+	req.payload.metric_streamer_start.sampling_rate = sampling_rate;
+	req.payload.metric_streamer_start.buffer_addr = buffer_addr;
+	req.payload.metric_streamer_start.buffer_size = buffer_size;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_METRIC_STREAMER_START_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "Failed to start metric streamer: ret %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+int ivpu_jsm_metric_streamer_stop(struct ivpu_device *vdev, u64 metric_group_mask)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_METRIC_STREAMER_STOP };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.metric_streamer_stop.metric_group_mask = metric_group_mask;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_METRIC_STREAMER_STOP_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret)
+		ivpu_warn_ratelimited(vdev, "Failed to stop metric streamer: ret %d\n", ret);
+
+	return ret;
+}
+
+int ivpu_jsm_metric_streamer_update(struct ivpu_device *vdev, u64 metric_group_mask,
+				    u64 buffer_addr, u64 buffer_size, u64 *bytes_written)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_METRIC_STREAMER_UPDATE };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.metric_streamer_update.metric_group_mask = metric_group_mask;
+	req.payload.metric_streamer_update.buffer_addr = buffer_addr;
+	req.payload.metric_streamer_update.buffer_size = buffer_size;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_METRIC_STREAMER_UPDATE_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "Failed to update metric streamer: ret %d\n", ret);
+		return ret;
+	}
+
+	if (buffer_size && resp.payload.metric_streamer_done.bytes_written > buffer_size) {
+		ivpu_warn_ratelimited(vdev, "MS buffer overflow: bytes_written %#llx > buffer_size %#llx\n",
+				      resp.payload.metric_streamer_done.bytes_written, buffer_size);
+		return -EOVERFLOW;
+	}
+
+	*bytes_written = resp.payload.metric_streamer_done.bytes_written;
+
+	return ret;
+}
+
+int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mask, u64 buffer_addr,
+				  u64 buffer_size, u32 *sample_size, u64 *info_size)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_METRIC_STREAMER_INFO };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	req.payload.metric_streamer_start.metric_group_mask = metric_group_mask;
+	req.payload.metric_streamer_start.buffer_addr = buffer_addr;
+	req.payload.metric_streamer_start.buffer_size = buffer_size;
+
+	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_METRIC_STREAMER_INFO_DONE, &resp,
+				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "Failed to get metric streamer info: ret %d\n", ret);
+		return ret;
+	}
+
+	if (!resp.payload.metric_streamer_done.sample_size) {
+		ivpu_warn_ratelimited(vdev, "Invalid sample size\n");
+		return -EBADMSG;
+	}
+
+	if (sample_size)
+		*sample_size = resp.payload.metric_streamer_done.sample_size;
+	if (info_size)
+		*info_size = resp.payload.metric_streamer_done.bytes_written;
+
+	return ret;
+}
+
+int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_DCT_ENABLE };
+	struct vpu_jsm_msg resp;
+
+	req.payload.pwr_dct_control.dct_active_us = active_us;
+	req.payload.pwr_dct_control.dct_inactive_us = inactive_us;
+
+	return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_ENABLE_DONE, &resp,
+					      VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+}
+
+int ivpu_jsm_dct_disable(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_DCT_DISABLE };
+	struct vpu_jsm_msg resp;
+
+	return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE, &resp,
+					      VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+}
+
+int ivpu_jsm_state_dump(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_STATE_DUMP };
+
+	return ivpu_ipc_send_and_wait(vdev, &req, VPU_IPC_CHAN_ASYNC_CMD,
+				      vdev->timeout.state_dump_msg);
 }
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.h b/drivers/accel/ivpu/ivpu_jsm_msg.h
index 66979a948c7c..9e84d3526a14 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.h
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_JSM_MSG_H__
@@ -22,4 +22,27 @@ int ivpu_jsm_trace_get_capability(struct ivpu_device *vdev, u32 *trace_destinati
 int ivpu_jsm_trace_set_config(struct ivpu_device *vdev, u32 trace_level, u32 trace_destination_mask,
 			      u64 trace_hw_component_mask);
 int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid);
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev);
+int ivpu_jsm_hws_create_cmdq(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_group, u32 cmdq_id,
+			     u32 pid, u32 engine, u64 cmdq_base, u32 cmdq_size);
+int ivpu_jsm_hws_destroy_cmdq(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id);
+int ivpu_jsm_hws_register_db(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id, u32 db_id,
+			     u64 cmdq_base, u32 cmdq_size);
+int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine);
+int ivpu_jsm_hws_set_context_sched_properties(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id,
+					      u32 priority);
+int ivpu_jsm_hws_set_scheduling_log(struct ivpu_device *vdev, u32 engine_idx, u32 host_ssid,
+				    u64 vpu_log_buffer_va);
+int ivpu_jsm_hws_setup_priority_bands(struct ivpu_device *vdev);
+int ivpu_jsm_metric_streamer_start(struct ivpu_device *vdev, u64 metric_group_mask,
+				   u64 sampling_rate, u64 buffer_addr, u64 buffer_size);
+int ivpu_jsm_metric_streamer_stop(struct ivpu_device *vdev, u64 metric_group_mask);
+int ivpu_jsm_metric_streamer_update(struct ivpu_device *vdev, u64 metric_group_mask,
+				    u64 buffer_addr, u64 buffer_size, u64 *bytes_written);
+int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mask, u64 buffer_addr,
+				  u64 buffer_size, u32 *sample_size, u64 *info_size);
+int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us);
+int ivpu_jsm_dct_disable(struct ivpu_device *vdev);
+int ivpu_jsm_state_dump(struct ivpu_device *vdev);
+
 #endif
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 2538c78fbebe..5ea010568faa 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -1,12 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/circ_buf.h>
 #include <linux/highmem.h>
 
 #include "ivpu_drv.h"
+#include "ivpu_hw.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
@@ -19,6 +20,12 @@
 #define IVPU_MMU_REG_CR0		      0x00200020u
 #define IVPU_MMU_REG_CR0ACK		      0x00200024u
 #define IVPU_MMU_REG_CR0ACK_VAL_MASK	      GENMASK(31, 0)
+#define IVPU_MMU_REG_CR0_ATSCHK_MASK	      BIT(4)
+#define IVPU_MMU_REG_CR0_CMDQEN_MASK	      BIT(3)
+#define IVPU_MMU_REG_CR0_EVTQEN_MASK	      BIT(2)
+#define IVPU_MMU_REG_CR0_PRIQEN_MASK	      BIT(1)
+#define IVPU_MMU_REG_CR0_SMMUEN_MASK	      BIT(0)
+
 #define IVPU_MMU_REG_CR1		      0x00200028u
 #define IVPU_MMU_REG_CR2		      0x0020002cu
 #define IVPU_MMU_REG_IRQ_CTRL		      0x00200050u
@@ -71,10 +78,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -140,12 +147,6 @@
 #define IVPU_MMU_IRQ_EVTQ_EN		BIT(2)
 #define IVPU_MMU_IRQ_GERROR_EN		BIT(0)
 
-#define IVPU_MMU_CR0_ATSCHK		BIT(4)
-#define IVPU_MMU_CR0_CMDQEN		BIT(3)
-#define IVPU_MMU_CR0_EVTQEN		BIT(2)
-#define IVPU_MMU_CR0_PRIQEN		BIT(1)
-#define IVPU_MMU_CR0_SMMUEN		BIT(0)
-
 #define IVPU_MMU_CR1_TABLE_SH		GENMASK(11, 10)
 #define IVPU_MMU_CR1_TABLE_OC		GENMASK(9, 8)
 #define IVPU_MMU_CR1_TABLE_IC		GENMASK(7, 6)
@@ -230,7 +231,12 @@
 				  (REG_FLD(IVPU_MMU_REG_GERROR, MSI_PRIQ_ABT)) | \
 				  (REG_FLD(IVPU_MMU_REG_GERROR, MSI_ABT)))
 
-static char *ivpu_mmu_event_to_str(u32 cmd)
+#define IVPU_MMU_CERROR_NONE         0x0
+#define IVPU_MMU_CERROR_ILL          0x1
+#define IVPU_MMU_CERROR_ABT          0x2
+#define IVPU_MMU_CERROR_ATC_INV_SYNC 0x3
+
+static const char *ivpu_mmu_event_to_str(u32 cmd)
 {
 	switch (cmd) {
 	case IVPU_MMU_EVT_F_UUT:
@@ -272,7 +278,23 @@ static char *ivpu_mmu_event_to_str(u32 cmd)
 	case IVPU_MMU_EVT_F_VMS_FETCH:
 		return "Fetch of VMS caused external abort";
 	default:
-		return "Unknown CMDQ command";
+		return "Unknown event";
+	}
+}
+
+static const char *ivpu_mmu_cmdq_err_to_str(u32 err)
+{
+	switch (err) {
+	case IVPU_MMU_CERROR_NONE:
+		return "No error";
+	case IVPU_MMU_CERROR_ILL:
+		return "Illegal command";
+	case IVPU_MMU_CERROR_ABT:
+		return "External abort on command queue read";
+	case IVPU_MMU_CERROR_ATC_INV_SYNC:
+		return "Sync failed to complete ATS invalidation";
+	default:
+		return "Unknown error";
 	}
 }
 
@@ -453,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -479,21 +513,27 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 	u64 val;
 	int ret;
 
-	val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_SYNC) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_CS, 0x2) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSH, 0x3) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSI_ATTR, 0xf);
+	val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_SYNC);
 
 	ret = ivpu_mmu_cmdq_cmd_write(vdev, "SYNC", val, 0);
 	if (ret)
 		return ret;
 
-	clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
+	if (!ivpu_is_force_snoop_enabled(vdev))
+		clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
 	REGV_WR32(IVPU_MMU_REG_CMDQ_PROD, q->prod);
 
 	ret = ivpu_mmu_cmdq_wait_for_cons(vdev);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for consumer: %d\n", ret);
+	if (ret) {
+		u32 err;
+
+		val = REGV_RD32(IVPU_MMU_REG_CMDQ_CONS);
+		err = REG_GET_FLD(IVPU_MMU_REG_CMDQ_CONS, ERR, val);
+
+		ivpu_err(vdev, "Timed out waiting for MMU consumer: %d, error: %s\n", ret,
+			 ivpu_mmu_cmdq_err_to_str(err));
+		ivpu_hw_diagnose_failure(vdev);
+	}
 
 	return ret;
 }
@@ -528,12 +568,12 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	int ret;
 
 	memset(mmu->cmdq.base, 0, IVPU_MMU_CMDQ_SIZE);
-	clflush_cache_range(mmu->cmdq.base, IVPU_MMU_CMDQ_SIZE);
+	if (!ivpu_is_force_snoop_enabled(vdev))
+		clflush_cache_range(mmu->cmdq.base, IVPU_MMU_CMDQ_SIZE);
 	mmu->cmdq.prod = 0;
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -556,7 +596,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	REGV_WR32(IVPU_MMU_REG_CMDQ_PROD, 0);
 	REGV_WR32(IVPU_MMU_REG_CMDQ_CONS, 0);
 
-	val = IVPU_MMU_CR0_CMDQEN;
+	val = REG_SET_FLD(IVPU_MMU_REG_CR0, CMDQEN, 0);
 	ret = ivpu_mmu_reg_write_cr0(vdev, val);
 	if (ret)
 		return ret;
@@ -577,12 +617,12 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	REGV_WR32(IVPU_MMU_REG_EVTQ_PROD_SEC, 0);
 	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, 0);
 
-	val |= IVPU_MMU_CR0_EVTQEN;
+	val = REG_SET_FLD(IVPU_MMU_REG_CR0, EVTQEN, val);
 	ret = ivpu_mmu_reg_write_cr0(vdev, val);
 	if (ret)
 		return ret;
 
-	val |= IVPU_MMU_CR0_ATSCHK;
+	val = REG_SET_FLD(IVPU_MMU_REG_CR0, ATSCHK, val);
 	ret = ivpu_mmu_reg_write_cr0(vdev, val);
 	if (ret)
 		return ret;
@@ -591,7 +631,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	if (ret)
 		return ret;
 
-	val |= IVPU_MMU_CR0_SMMUEN;
+	val = REG_SET_FLD(IVPU_MMU_REG_CR0, SMMUEN, val);
 	return ivpu_mmu_reg_write_cr0(vdev, val);
 }
 
@@ -623,7 +663,8 @@ static void ivpu_mmu_strtab_link_cd(struct ivpu_device *vdev, u32 sid)
 	WRITE_ONCE(entry[1], str[1]);
 	WRITE_ONCE(entry[0], str[0]);
 
-	clflush_cache_range(entry, IVPU_MMU_STRTAB_ENT_SIZE);
+	if (!ivpu_is_force_snoop_enabled(vdev))
+		clflush_cache_range(entry, IVPU_MMU_STRTAB_ENT_SIZE);
 
 	ivpu_dbg(vdev, MMU, "STRTAB write entry (SSID=%u): 0x%llx, 0x%llx\n", sid, str[0], str[1]);
 }
@@ -655,7 +696,7 @@ unlock:
 	return ret;
 }
 
-static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
+static int ivpu_mmu_cdtab_entry_set(struct ivpu_device *vdev, u32 ssid, u64 cd_dma, bool valid)
 {
 	struct ivpu_mmu_info *mmu = vdev->mmu;
 	struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab;
@@ -667,40 +708,40 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
 		return -EINVAL;
 
 	entry = cdtab->base + (ssid * IVPU_MMU_CDTAB_ENT_SIZE);
-
-	if (cd_dma != 0) {
-		cd[0] = FIELD_PREP(IVPU_MMU_CD_0_TCR_T0SZ, IVPU_MMU_T0SZ_48BIT) |
-			FIELD_PREP(IVPU_MMU_CD_0_TCR_TG0, 0) |
-			FIELD_PREP(IVPU_MMU_CD_0_TCR_IRGN0, 0) |
-			FIELD_PREP(IVPU_MMU_CD_0_TCR_ORGN0, 0) |
-			FIELD_PREP(IVPU_MMU_CD_0_TCR_SH0, 0) |
-			FIELD_PREP(IVPU_MMU_CD_0_TCR_IPS, IVPU_MMU_IPS_48BIT) |
-			FIELD_PREP(IVPU_MMU_CD_0_ASID, ssid) |
-			IVPU_MMU_CD_0_TCR_EPD1 |
-			IVPU_MMU_CD_0_AA64 |
-			IVPU_MMU_CD_0_R |
-			IVPU_MMU_CD_0_ASET |
-			IVPU_MMU_CD_0_V;
-		cd[1] = cd_dma & IVPU_MMU_CD_1_TTB0_MASK;
-		cd[2] = 0;
-		cd[3] = 0x0000000000007444;
-
-		/* For global context generate memory fault on VPU */
-		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
-			cd[0] |= IVPU_MMU_CD_0_A;
-	} else {
-		memset(cd, 0, sizeof(cd));
-	}
+	drm_WARN_ON(&vdev->drm, (entry[0] & IVPU_MMU_CD_0_V) == valid);
+
+	cd[0] = FIELD_PREP(IVPU_MMU_CD_0_TCR_T0SZ, IVPU_MMU_T0SZ_48BIT) |
+		FIELD_PREP(IVPU_MMU_CD_0_TCR_TG0, 0) |
+		FIELD_PREP(IVPU_MMU_CD_0_TCR_IRGN0, 0) |
+		FIELD_PREP(IVPU_MMU_CD_0_TCR_ORGN0, 0) |
+		FIELD_PREP(IVPU_MMU_CD_0_TCR_SH0, 0) |
+		FIELD_PREP(IVPU_MMU_CD_0_TCR_IPS, IVPU_MMU_IPS_48BIT) |
+		FIELD_PREP(IVPU_MMU_CD_0_ASID, ssid) |
+		IVPU_MMU_CD_0_TCR_EPD1 |
+		IVPU_MMU_CD_0_AA64 |
+		IVPU_MMU_CD_0_R |
+		IVPU_MMU_CD_0_ASET;
+	cd[1] = cd_dma & IVPU_MMU_CD_1_TTB0_MASK;
+	cd[2] = 0;
+	cd[3] = 0x0000000000007444;
+
+	/* For global and reserved contexts generate memory fault on VPU */
+	if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID || ssid == IVPU_RESERVED_CONTEXT_MMU_SSID)
+		cd[0] |= IVPU_MMU_CD_0_A;
+
+	if (valid)
+		cd[0] |= IVPU_MMU_CD_0_V;
 
 	WRITE_ONCE(entry[1], cd[1]);
 	WRITE_ONCE(entry[2], cd[2]);
 	WRITE_ONCE(entry[3], cd[3]);
 	WRITE_ONCE(entry[0], cd[0]);
 
-	clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
+	if (!ivpu_is_force_snoop_enabled(vdev))
+		clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
 
-	ivpu_dbg(vdev, MMU, "CDTAB %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n",
-		 cd_dma ? "write" : "clear", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]);
+	ivpu_dbg(vdev, MMU, "CDTAB set %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n",
+		 valid ? "valid" : "invalid", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]);
 
 	mutex_lock(&mmu->lock);
 	if (!mmu->on)
@@ -708,38 +749,18 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
 
 	ret = ivpu_mmu_cmdq_write_cfgi_all(vdev);
 	if (ret)
-		goto unlock;
+		goto err_invalidate;
 
 	ret = ivpu_mmu_cmdq_sync(vdev);
+	if (ret)
+		goto err_invalidate;
 unlock:
 	mutex_unlock(&mmu->lock);
-	return ret;
-}
-
-static int ivpu_mmu_cd_add_gbl(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ret = ivpu_mmu_cd_add(vdev, 0, vdev->gctx.pgtable.pgd_dma);
-	if (ret)
-		ivpu_err(vdev, "Failed to add global CD entry: %d\n", ret);
-
-	return ret;
-}
-
-static int ivpu_mmu_cd_add_user(struct ivpu_device *vdev, u32 ssid, dma_addr_t cd_dma)
-{
-	int ret;
-
-	if (ssid == 0) {
-		ivpu_err(vdev, "Invalid SSID: %u\n", ssid);
-		return -EINVAL;
-	}
-
-	ret = ivpu_mmu_cd_add(vdev, ssid, cd_dma);
-	if (ret)
-		ivpu_err(vdev, "Failed to add CD entry SSID=%u: %d\n", ssid, ret);
+	return 0;
 
+err_invalidate:
+	WRITE_ONCE(entry[0], 0);
+	mutex_unlock(&mmu->lock);
 	return ret;
 }
 
@@ -750,20 +771,17 @@ int ivpu_mmu_init(struct ivpu_device *vdev)
 
 	ivpu_dbg(vdev, MMU, "Init..\n");
 
-	drmm_mutex_init(&vdev->drm, &mmu->lock);
 	ivpu_mmu_config_check(vdev);
 
-	ret = ivpu_mmu_structs_alloc(vdev);
+	ret = drmm_mutex_init(&vdev->drm, &mmu->lock);
 	if (ret)
 		return ret;
 
-	ret = ivpu_mmu_strtab_init(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret);
+	ret = ivpu_mmu_structs_alloc(vdev);
+	if (ret)
 		return ret;
-	}
 
-	ret = ivpu_mmu_cd_add_gbl(vdev);
+	ret = ivpu_mmu_strtab_init(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret);
 		return ret;
@@ -833,8 +851,9 @@ static void ivpu_mmu_dump_event(struct ivpu_device *vdev, u32 *event)
 	u64 in_addr = ((u64)event[5]) << 32 | event[4];
 	u32 sid = event[1];
 
-	ivpu_err(vdev, "MMU EVTQ: 0x%x (%s) SSID: %d SID: %d, e[2] %08x, e[3] %08x, in addr: 0x%llx, fetch addr: 0x%llx\n",
-		 op, ivpu_mmu_event_to_str(op), ssid, sid, event[2], event[3], in_addr, fetch_addr);
+	ivpu_err_ratelimited(vdev, "MMU EVTQ: 0x%x (%s) SSID: %d SID: %d, e[2] %08x, e[3] %08x, in addr: 0x%llx, fetch addr: 0x%llx\n",
+			     op, ivpu_mmu_event_to_str(op), ssid, sid,
+			     event[2], event[3], in_addr, fetch_addr);
 }
 
 static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
@@ -844,37 +863,122 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
+static int ivpu_mmu_evtq_set(struct ivpu_device *vdev, bool enable)
+{
+	u32 val = REGV_RD32(IVPU_MMU_REG_CR0);
+
+	if (enable)
+		val = REG_SET_FLD(IVPU_MMU_REG_CR0, EVTQEN, val);
+	else
+		val = REG_CLR_FLD(IVPU_MMU_REG_CR0, EVTQEN, val);
+	REGV_WR32(IVPU_MMU_REG_CR0, val);
+
+	return REGV_POLL_FLD(IVPU_MMU_REG_CR0ACK, VAL, val, IVPU_MMU_REG_TIMEOUT_US);
+}
+
+static int ivpu_mmu_evtq_enable(struct ivpu_device *vdev)
+{
+	return ivpu_mmu_evtq_set(vdev, true);
+}
+
+static int ivpu_mmu_evtq_disable(struct ivpu_device *vdev)
+{
+	return ivpu_mmu_evtq_set(vdev, false);
+}
+
+void ivpu_mmu_discard_events(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+
+	mutex_lock(&mmu->lock);
+	/*
+	 * Disable event queue (stop MMU from updating the producer)
+	 * to allow synchronization of consumer and producer indexes
+	 */
+	ivpu_mmu_evtq_disable(vdev);
+
+	vdev->mmu->evtq.cons = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
+	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
+	vdev->mmu->evtq.prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
+
+	ivpu_mmu_evtq_enable(vdev);
+
+	drm_WARN_ON_ONCE(&vdev->drm, vdev->mmu->evtq.cons != vdev->mmu->evtq.prod);
+
+	mutex_unlock(&mmu->lock);
+}
+
+int ivpu_mmu_disable_ssid_events(struct ivpu_device *vdev, u32 ssid)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab;
+	u64 *entry;
+	u64 val;
+
+	if (ssid > IVPU_MMU_CDTAB_ENT_COUNT)
+		return -EINVAL;
+
+	mutex_lock(&mmu->lock);
+
+	entry = cdtab->base + (ssid * IVPU_MMU_CDTAB_ENT_SIZE);
+
+	val = READ_ONCE(entry[0]);
+	val &= ~IVPU_MMU_CD_0_R;
+	WRITE_ONCE(entry[0], val);
+
+	if (!ivpu_is_force_snoop_enabled(vdev))
+		clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
+
+	ivpu_mmu_cmdq_write_cfgi_all(vdev);
+	ivpu_mmu_cmdq_sync(vdev);
+
+	mutex_unlock(&mmu->lock);
+
+	return 0;
+}
+
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 {
-	bool schedule_recovery = false;
+	struct ivpu_file_priv *file_priv;
 	u32 *event;
 	u32 ssid;
 
 	ivpu_dbg(vdev, IRQ, "MMU event queue\n");
 
-	while ((event = ivpu_mmu_get_event(vdev)) != NULL) {
-		ivpu_mmu_dump_event(vdev, event);
-
-		ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, event[0]);
-		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
-			schedule_recovery = true;
-		else
-			ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+	while ((event = ivpu_mmu_get_event(vdev))) {
+		ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, *event);
+		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID ||
+		    ssid == IVPU_RESERVED_CONTEXT_MMU_SSID) {
+			ivpu_mmu_dump_event(vdev, event);
+			ivpu_pm_trigger_recovery(vdev, "MMU event");
+			return;
+		}
+
+		file_priv = xa_load(&vdev->context_xa, ssid);
+		if (file_priv) {
+			if (!READ_ONCE(file_priv->has_mmu_faults)) {
+				ivpu_mmu_dump_event(vdev, event);
+				WRITE_ONCE(file_priv->has_mmu_faults, true);
+			}
+		}
 	}
 
-	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+	queue_work(system_wq, &vdev->context_abort_work);
+}
+
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
+{
+	u32 *event;
+
+	while ((event = ivpu_mmu_get_event(vdev)) != NULL)
+		ivpu_mmu_dump_event(vdev, event);
 }
 
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)
@@ -914,12 +1018,12 @@ void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)
 	REGV_WR32(IVPU_MMU_REG_GERRORN, gerror_val);
 }
 
-int ivpu_mmu_set_pgtable(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable)
+int ivpu_mmu_cd_set(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable)
 {
-	return ivpu_mmu_cd_add_user(vdev, ssid, pgtable->pgd_dma);
+	return ivpu_mmu_cdtab_entry_set(vdev, ssid, pgtable->pgd_dma, true);
 }
 
-void ivpu_mmu_clear_pgtable(struct ivpu_device *vdev, int ssid)
+void ivpu_mmu_cd_clear(struct ivpu_device *vdev, int ssid)
 {
-	ivpu_mmu_cd_add_user(vdev, ssid, 0); /* 0 will clear CD entry */
+	ivpu_mmu_cdtab_entry_set(vdev, ssid, 0, false);
 }
diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h
index cb551126806b..1ce7529746ad 100644
--- a/drivers/accel/ivpu/ivpu_mmu.h
+++ b/drivers/accel/ivpu/ivpu_mmu.h
@@ -40,11 +40,14 @@ struct ivpu_mmu_info {
 int ivpu_mmu_init(struct ivpu_device *vdev);
 void ivpu_mmu_disable(struct ivpu_device *vdev);
 int ivpu_mmu_enable(struct ivpu_device *vdev);
-int ivpu_mmu_set_pgtable(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable);
-void ivpu_mmu_clear_pgtable(struct ivpu_device *vdev, int ssid);
+int ivpu_mmu_cd_set(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable);
+void ivpu_mmu_cd_clear(struct ivpu_device *vdev, int ssid);
 int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid);
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev);
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev);
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev);
+void ivpu_mmu_discard_events(struct ivpu_device *vdev);
+int ivpu_mmu_disable_ssid_events(struct ivpu_device *vdev, u32 ssid);
 
 #endif /* __IVPU_MMU_H__ */
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index c1050a2df954..f0267efa55aa 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -5,6 +5,10 @@
 
 #include <linux/bitfield.h>
 #include <linux/highmem.h>
+#include <linux/set_memory.h>
+#include <linux/vmalloc.h>
+
+#include <drm/drm_cache.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
@@ -20,6 +24,7 @@
 #define IVPU_MMU_ENTRY_FLAG_CONT         BIT(52)
 #define IVPU_MMU_ENTRY_FLAG_NG           BIT(11)
 #define IVPU_MMU_ENTRY_FLAG_AF           BIT(10)
+#define IVPU_MMU_ENTRY_FLAG_RO           BIT(7)
 #define IVPU_MMU_ENTRY_FLAG_USER         BIT(6)
 #define IVPU_MMU_ENTRY_FLAG_LLC_COHERENT BIT(2)
 #define IVPU_MMU_ENTRY_FLAG_TYPE_PAGE    BIT(1)
@@ -39,25 +44,50 @@
 #define IVPU_MMU_ENTRY_MAPPED  (IVPU_MMU_ENTRY_FLAG_AF | IVPU_MMU_ENTRY_FLAG_USER | \
 				IVPU_MMU_ENTRY_FLAG_NG | IVPU_MMU_ENTRY_VALID)
 
-static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
+static void *ivpu_pgtable_alloc_page(struct ivpu_device *vdev, dma_addr_t *dma)
 {
-	dma_addr_t pgd_dma;
+	dma_addr_t dma_addr;
+	struct page *page;
+	void *cpu;
 
-	pgtable->pgd_dma_ptr = dma_alloc_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pgd_dma,
-						  GFP_KERNEL);
-	if (!pgtable->pgd_dma_ptr)
-		return -ENOMEM;
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page)
+		return NULL;
 
-	pgtable->pgd_dma = pgd_dma;
+	set_pages_array_wc(&page, 1);
 
-	return 0;
+	dma_addr = dma_map_page(vdev->drm.dev, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(vdev->drm.dev, dma_addr))
+		goto err_free_page;
+
+	cpu = vmap(&page, 1, VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+	if (!cpu)
+		goto err_dma_unmap_page;
+
+
+	*dma = dma_addr;
+	return cpu;
+
+err_dma_unmap_page:
+	dma_unmap_page(vdev->drm.dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+
+err_free_page:
+	put_page(page);
+	return NULL;
 }
 
-static void ivpu_mmu_pgtable_free(struct ivpu_device *vdev, u64 *cpu_addr, dma_addr_t dma_addr)
+static void ivpu_pgtable_free_page(struct ivpu_device *vdev, u64 *cpu_addr, dma_addr_t dma_addr)
 {
-	if (cpu_addr)
-		dma_free_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, cpu_addr,
-				  dma_addr & ~IVPU_MMU_ENTRY_FLAGS_MASK);
+	struct page *page;
+
+	if (cpu_addr) {
+		page = vmalloc_to_page(cpu_addr);
+		vunmap(cpu_addr);
+		dma_unmap_page(vdev->drm.dev, dma_addr & ~IVPU_MMU_ENTRY_FLAGS_MASK, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
+		set_pages_array_wb(&page, 1);
+		put_page(page);
+	}
 }
 
 static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
@@ -84,19 +114,40 @@ static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgt
 				pte_dma_ptr = pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx];
 				pte_dma = pgtable->pmd_ptrs[pgd_idx][pud_idx][pmd_idx];
 
-				ivpu_mmu_pgtable_free(vdev, pte_dma_ptr, pte_dma);
+				ivpu_pgtable_free_page(vdev, pte_dma_ptr, pte_dma);
 			}
 
 			kfree(pgtable->pte_ptrs[pgd_idx][pud_idx]);
-			ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
+			ivpu_pgtable_free_page(vdev, pmd_dma_ptr, pmd_dma);
 		}
 
 		kfree(pgtable->pmd_ptrs[pgd_idx]);
 		kfree(pgtable->pte_ptrs[pgd_idx]);
-		ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
+		ivpu_pgtable_free_page(vdev, pud_dma_ptr, pud_dma);
 	}
 
-	ivpu_mmu_pgtable_free(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma);
+	ivpu_pgtable_free_page(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma);
+	pgtable->pgd_dma_ptr = NULL;
+	pgtable->pgd_dma = 0;
+}
+
+static u64*
+ivpu_mmu_ensure_pgd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
+{
+	u64 *pgd_dma_ptr = pgtable->pgd_dma_ptr;
+	dma_addr_t pgd_dma;
+
+	if (pgd_dma_ptr)
+		return pgd_dma_ptr;
+
+	pgd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pgd_dma);
+	if (!pgd_dma_ptr)
+		return NULL;
+
+	pgtable->pgd_dma_ptr = pgd_dma_ptr;
+	pgtable->pgd_dma = pgd_dma;
+
+	return pgd_dma_ptr;
 }
 
 static u64*
@@ -108,7 +159,7 @@ ivpu_mmu_ensure_pud(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pud_dma_ptr)
 		return pud_dma_ptr;
 
-	pud_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pud_dma, GFP_KERNEL);
+	pud_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pud_dma);
 	if (!pud_dma_ptr)
 		return NULL;
 
@@ -131,7 +182,7 @@ err_free_pmd_ptrs:
 	kfree(pgtable->pmd_ptrs[pgd_idx]);
 
 err_free_pud_dma_ptr:
-	ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
+	ivpu_pgtable_free_page(vdev, pud_dma_ptr, pud_dma);
 	return NULL;
 }
 
@@ -145,7 +196,7 @@ ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pmd_dma_ptr)
 		return pmd_dma_ptr;
 
-	pmd_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pmd_dma, GFP_KERNEL);
+	pmd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pmd_dma);
 	if (!pmd_dma_ptr)
 		return NULL;
 
@@ -160,7 +211,7 @@ ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	return pmd_dma_ptr;
 
 err_free_pmd_dma_ptr:
-	ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
+	ivpu_pgtable_free_page(vdev, pmd_dma_ptr, pmd_dma);
 	return NULL;
 }
 
@@ -174,7 +225,7 @@ ivpu_mmu_ensure_pte(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pte_dma_ptr)
 		return pte_dma_ptr;
 
-	pte_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pte_dma, GFP_KERNEL);
+	pte_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pte_dma);
 	if (!pte_dma_ptr)
 		return NULL;
 
@@ -194,6 +245,12 @@ ivpu_mmu_context_map_page(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx
 	int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
 	int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
 
+	drm_WARN_ON(&vdev->drm, ctx->id == IVPU_RESERVED_CONTEXT_MMU_SSID);
+
+	/* Allocate PGD - first level page table if needed */
+	if (!ivpu_mmu_ensure_pgd(vdev, &ctx->pgtable))
+		return -ENOMEM;
+
 	/* Allocate PUD - second level page table if needed */
 	if (!ivpu_mmu_ensure_pud(vdev, &ctx->pgtable, pgd_idx))
 		return -ENOMEM;
@@ -249,38 +306,6 @@ static void ivpu_mmu_context_unmap_page(struct ivpu_mmu_context *ctx, u64 vpu_ad
 	ctx->pgtable.pte_ptrs[pgd_idx][pud_idx][pmd_idx][pte_idx] = IVPU_MMU_ENTRY_INVALID;
 }
 
-static void
-ivpu_mmu_context_flush_page_tables(struct ivpu_mmu_context *ctx, u64 vpu_addr, size_t size)
-{
-	struct ivpu_mmu_pgtable *pgtable = &ctx->pgtable;
-	u64 end_addr = vpu_addr + size;
-
-	/* Align to PMD entry (2 MB) */
-	vpu_addr &= ~(IVPU_MMU_PTE_MAP_SIZE - 1);
-
-	while (vpu_addr < end_addr) {
-		int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
-		u64 pud_end = (pgd_idx + 1) * (u64)IVPU_MMU_PUD_MAP_SIZE;
-
-		while (vpu_addr < end_addr && vpu_addr < pud_end) {
-			int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
-			u64 pmd_end = (pud_idx + 1) * (u64)IVPU_MMU_PMD_MAP_SIZE;
-
-			while (vpu_addr < end_addr && vpu_addr < pmd_end) {
-				int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
-
-				clflush_cache_range(pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx],
-						    IVPU_MMU_PGTABLE_SIZE);
-				vpu_addr += IVPU_MMU_PTE_MAP_SIZE;
-			}
-			clflush_cache_range(pgtable->pmd_ptrs[pgd_idx][pud_idx],
-					    IVPU_MMU_PGTABLE_SIZE);
-		}
-		clflush_cache_range(pgtable->pud_ptrs[pgd_idx], IVPU_MMU_PGTABLE_SIZE);
-	}
-	clflush_cache_range(pgtable->pgd_dma_ptr, IVPU_MMU_PGTABLE_SIZE);
-}
-
 static int
 ivpu_mmu_context_map_pages(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			   u64 vpu_addr, dma_addr_t dma_addr, size_t size, u64 prot)
@@ -309,6 +334,91 @@ ivpu_mmu_context_map_pages(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 	return 0;
 }
 
+static void ivpu_mmu_context_set_page_ro(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+					 u64 vpu_addr)
+{
+	int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
+	int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
+	int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
+	int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
+
+	ctx->pgtable.pte_ptrs[pgd_idx][pud_idx][pmd_idx][pte_idx] |= IVPU_MMU_ENTRY_FLAG_RO;
+}
+
+static void ivpu_mmu_context_split_page(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+					u64 vpu_addr)
+{
+	int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
+	int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
+	int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
+	int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
+
+	ctx->pgtable.pte_ptrs[pgd_idx][pud_idx][pmd_idx][pte_idx] &= ~IVPU_MMU_ENTRY_FLAG_CONT;
+}
+
+static void ivpu_mmu_context_split_64k_page(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+					    u64 vpu_addr)
+{
+	u64 start = ALIGN_DOWN(vpu_addr, IVPU_MMU_CONT_PAGES_SIZE);
+	u64 end = ALIGN(vpu_addr, IVPU_MMU_CONT_PAGES_SIZE);
+	u64 offset = 0;
+
+	ivpu_dbg(vdev, MMU_MAP, "Split 64K page ctx: %u vpu_addr: 0x%llx\n", ctx->id, vpu_addr);
+
+	while (start + offset < end) {
+		ivpu_mmu_context_split_page(vdev, ctx, start + offset);
+		offset += IVPU_MMU_PAGE_SIZE;
+	}
+}
+
+int
+ivpu_mmu_context_set_pages_ro(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u64 vpu_addr,
+			      size_t size)
+{
+	u64 end = vpu_addr + size;
+	size_t size_left = size;
+	int ret;
+
+	if (size == 0)
+		return 0;
+
+	if (drm_WARN_ON(&vdev->drm, !IS_ALIGNED(vpu_addr | size, IVPU_MMU_PAGE_SIZE)))
+		return -EINVAL;
+
+	mutex_lock(&ctx->lock);
+
+	ivpu_dbg(vdev, MMU_MAP, "Set read-only pages ctx: %u vpu_addr: 0x%llx size: %lu\n",
+		 ctx->id, vpu_addr, size);
+
+	if (!ivpu_disable_mmu_cont_pages) {
+		/* Split 64K contiguous page at the beginning if needed */
+		if (!IS_ALIGNED(vpu_addr, IVPU_MMU_CONT_PAGES_SIZE))
+			ivpu_mmu_context_split_64k_page(vdev, ctx, vpu_addr);
+
+		/* Split 64K contiguous page at the end if needed */
+		if (!IS_ALIGNED(vpu_addr + size, IVPU_MMU_CONT_PAGES_SIZE))
+			ivpu_mmu_context_split_64k_page(vdev, ctx, vpu_addr + size);
+	}
+
+	while (size_left) {
+		if (vpu_addr < end)
+			ivpu_mmu_context_set_page_ro(vdev, ctx, vpu_addr);
+
+		vpu_addr += IVPU_MMU_PAGE_SIZE;
+		size_left -= IVPU_MMU_PAGE_SIZE;
+	}
+
+	/* Ensure page table modifications are flushed from wc buffers to memory */
+	wmb();
+
+	mutex_unlock(&ctx->lock);
+	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
+	if (ret)
+		ivpu_err(vdev, "Failed to invalidate TLB for ctx %u: %d\n", ctx->id, ret);
+
+	return 0;
+}
+
 static void ivpu_mmu_context_unmap_pages(struct ivpu_mmu_context *ctx, u64 vpu_addr, size_t size)
 {
 	while (size) {
@@ -322,11 +432,15 @@ int
 ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			 u64 vpu_addr, struct sg_table *sgt,  bool llc_coherent)
 {
+	size_t start_vpu_addr = vpu_addr;
 	struct scatterlist *sg;
 	int ret;
 	u64 prot;
 	u64 i;
 
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return -EINVAL;
+
 	if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE))
 		return -EINVAL;
 
@@ -343,21 +457,42 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Map ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ret = ivpu_mmu_context_map_pages(vdev, ctx, vpu_addr, dma_addr, size, prot);
 		if (ret) {
 			ivpu_err(vdev, "Failed to map context pages\n");
-			mutex_unlock(&ctx->lock);
-			return ret;
+			goto err_unmap_pages;
 		}
-		ivpu_mmu_context_flush_page_tables(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
-	mutex_unlock(&ctx->lock);
+	if (!ctx->is_cd_valid) {
+		ret = ivpu_mmu_cd_set(vdev, ctx->id, &ctx->pgtable);
+		if (ret) {
+			ivpu_err(vdev, "Failed to set context descriptor for context %u: %d\n",
+				 ctx->id, ret);
+			goto err_unmap_pages;
+		}
+		ctx->is_cd_valid = true;
+	}
+
+	/* Ensure page table modifications are flushed from wc buffers to memory */
+	wmb();
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
-	if (ret)
+	if (ret) {
 		ivpu_err(vdev, "Failed to invalidate TLB for ctx %u: %d\n", ctx->id, ret);
+		goto err_unmap_pages;
+	}
+
+	mutex_unlock(&ctx->lock);
+	return 0;
+
+err_unmap_pages:
+	ivpu_mmu_context_unmap_pages(ctx, start_vpu_addr, vpu_addr - start_vpu_addr);
+	mutex_unlock(&ctx->lock);
 	return ret;
 }
 
@@ -369,19 +504,25 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 	int ret;
 	u64 i;
 
-	if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE))
-		ivpu_warn(vdev, "Unaligned vpu_addr: 0x%llx\n", vpu_addr);
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return;
 
 	mutex_lock(&ctx->lock);
 
 	for_each_sgtable_dma_sg(sgt, sg, i) {
+		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Unmap ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ivpu_mmu_context_unmap_pages(ctx, vpu_addr, size);
-		ivpu_mmu_context_flush_page_tables(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
+	/* Ensure page table modifications are flushed from wc buffers to memory */
+	wmb();
+
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
@@ -390,134 +531,107 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 }
 
 int
-ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
-				    const struct ivpu_addr_range *range,
-				    u64 size, struct drm_mm_node *node)
+ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range,
+			     u64 size, struct drm_mm_node *node)
 {
-	lockdep_assert_held(&ctx->lock);
+	int ret;
 
+	WARN_ON(!range);
+
+	mutex_lock(&ctx->lock);
 	if (!ivpu_disable_mmu_cont_pages && size >= IVPU_MMU_CONT_PAGES_SIZE) {
-		if (!drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
-						 range->start, range->end, DRM_MM_INSERT_BEST))
-			return 0;
+		ret = drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
+						  range->start, range->end, DRM_MM_INSERT_BEST);
+		if (!ret)
+			goto unlock;
 	}
 
-	return drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE, 0,
-					   range->start, range->end, DRM_MM_INSERT_BEST);
+	ret = drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE, 0,
+					  range->start, range->end, DRM_MM_INSERT_BEST);
+unlock:
+	mutex_unlock(&ctx->lock);
+	return ret;
 }
 
 void
-ivpu_mmu_context_remove_node_locked(struct ivpu_mmu_context *ctx, struct drm_mm_node *node)
+ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *node)
 {
-	lockdep_assert_held(&ctx->lock);
-
+	mutex_lock(&ctx->lock);
 	drm_mm_remove_node(node);
+	mutex_unlock(&ctx->lock);
 }
 
-static int
-ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id)
+void ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id)
 {
 	u64 start, end;
-	int ret;
 
 	mutex_init(&ctx->lock);
-	INIT_LIST_HEAD(&ctx->bo_list);
-
-	ret = ivpu_mmu_pgtable_init(vdev, &ctx->pgtable);
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize pgtable for ctx %u: %d\n", context_id, ret);
-		return ret;
-	}
 
 	if (!context_id) {
 		start = vdev->hw->ranges.global.start;
 		end = vdev->hw->ranges.shave.end;
 	} else {
-		start = vdev->hw->ranges.user.start;
-		end = vdev->hw->ranges.dma.end;
+		start = min_t(u64, vdev->hw->ranges.user.start, vdev->hw->ranges.shave.start);
+		end = max_t(u64, vdev->hw->ranges.user.end, vdev->hw->ranges.dma.end);
 	}
 
 	drm_mm_init(&ctx->mm, start, end - start);
 	ctx->id = context_id;
-
-	return 0;
 }
 
-static void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
+void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
-	if (drm_WARN_ON(&vdev->drm, !ctx->pgtable.pgd_dma_ptr))
-		return;
+	if (ctx->is_cd_valid) {
+		ivpu_mmu_cd_clear(vdev, ctx->id);
+		ctx->is_cd_valid = false;
+	}
 
 	mutex_destroy(&ctx->lock);
 	ivpu_mmu_pgtables_free(vdev, &ctx->pgtable);
 	drm_mm_takedown(&ctx->mm);
-
-	ctx->pgtable.pgd_dma_ptr = NULL;
-	ctx->pgtable.pgd_dma = 0;
 }
 
-int ivpu_mmu_global_context_init(struct ivpu_device *vdev)
+void ivpu_mmu_global_context_init(struct ivpu_device *vdev)
 {
-	return ivpu_mmu_context_init(vdev, &vdev->gctx, IVPU_GLOBAL_CONTEXT_MMU_SSID);
+	ivpu_mmu_context_init(vdev, &vdev->gctx, IVPU_GLOBAL_CONTEXT_MMU_SSID);
 }
 
 void ivpu_mmu_global_context_fini(struct ivpu_device *vdev)
 {
-	return ivpu_mmu_context_fini(vdev, &vdev->gctx);
+	ivpu_mmu_context_fini(vdev, &vdev->gctx);
 }
 
 int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev)
 {
-	return ivpu_mmu_user_context_init(vdev, &vdev->rctx, IVPU_RESERVED_CONTEXT_MMU_SSID);
-}
-
-void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev)
-{
-	return ivpu_mmu_user_context_fini(vdev, &vdev->rctx);
-}
-
-void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid)
-{
-	struct ivpu_file_priv *file_priv;
-
-	xa_lock(&vdev->context_xa);
-
-	file_priv = xa_load(&vdev->context_xa, ssid);
-	if (file_priv)
-		file_priv->has_mmu_faults = true;
-
-	xa_unlock(&vdev->context_xa);
-}
-
-int ivpu_mmu_user_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 ctx_id)
-{
 	int ret;
 
-	drm_WARN_ON(&vdev->drm, !ctx_id);
+	ivpu_mmu_context_init(vdev, &vdev->rctx, IVPU_RESERVED_CONTEXT_MMU_SSID);
 
-	ret = ivpu_mmu_context_init(vdev, ctx, ctx_id);
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize context %u: %d\n", ctx_id, ret);
-		return ret;
+	mutex_lock(&vdev->rctx.lock);
+
+	if (!ivpu_mmu_ensure_pgd(vdev, &vdev->rctx.pgtable)) {
+		ivpu_err(vdev, "Failed to allocate root page table for reserved context\n");
+		ret = -ENOMEM;
+		goto err_ctx_fini;
 	}
 
-	ret = ivpu_mmu_set_pgtable(vdev, ctx_id, &ctx->pgtable);
+	ret = ivpu_mmu_cd_set(vdev, vdev->rctx.id, &vdev->rctx.pgtable);
 	if (ret) {
-		ivpu_err(vdev, "Failed to set page table for context %u: %d\n", ctx_id, ret);
-		goto err_context_fini;
+		ivpu_err(vdev, "Failed to set context descriptor for reserved context\n");
+		goto err_ctx_fini;
 	}
 
-	return 0;
+	mutex_unlock(&vdev->rctx.lock);
+	return ret;
 
-err_context_fini:
-	ivpu_mmu_context_fini(vdev, ctx);
+err_ctx_fini:
+	mutex_unlock(&vdev->rctx.lock);
+	ivpu_mmu_context_fini(vdev, &vdev->rctx);
 	return ret;
 }
 
-void ivpu_mmu_user_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
+void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev)
 {
-	drm_WARN_ON(&vdev->drm, !ctx->id);
-
-	ivpu_mmu_clear_pgtable(vdev, ctx->id);
-	ivpu_mmu_context_fini(vdev, ctx);
+	ivpu_mmu_cd_clear(vdev, vdev->rctx.id);
+	ivpu_mmu_context_fini(vdev, &vdev->rctx);
 }
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.h b/drivers/accel/ivpu/ivpu_mmu_context.h
index f15d8c630d8a..f255310968cf 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.h
+++ b/drivers/accel/ivpu/ivpu_mmu_context.h
@@ -23,31 +23,29 @@ struct ivpu_mmu_pgtable {
 };
 
 struct ivpu_mmu_context {
-	struct mutex lock; /* protects: mm, pgtable, bo_list */
+	struct mutex lock; /* Protects: mm, pgtable, is_cd_valid */
 	struct drm_mm mm;
 	struct ivpu_mmu_pgtable pgtable;
-	struct list_head bo_list;
+	bool is_cd_valid;
 	u32 id;
 };
 
-int ivpu_mmu_global_context_init(struct ivpu_device *vdev);
+void ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id);
+void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
+void ivpu_mmu_global_context_init(struct ivpu_device *vdev);
 void ivpu_mmu_global_context_fini(struct ivpu_device *vdev);
 int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev);
 void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev);
 
-int ivpu_mmu_user_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 ctx_id);
-void ivpu_mmu_user_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
-void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid);
-
-int ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
-					const struct ivpu_addr_range *range,
-					u64 size, struct drm_mm_node *node);
-void ivpu_mmu_context_remove_node_locked(struct ivpu_mmu_context *ctx,
-					 struct drm_mm_node *node);
+int ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range,
+				 u64 size, struct drm_mm_node *node);
+void ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *node);
 
 int ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			     u64 vpu_addr, struct sg_table *sgt, bool llc_coherent);
 void ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 				u64 vpu_addr, struct sg_table *sgt);
+int ivpu_mmu_context_set_pages_ro(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
+				  u64 vpu_addr, size_t size);
 
 #endif /* __IVPU_MMU_CONTEXT_H__ */
diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c
new file mode 100644
index 000000000000..2a043baf10ca
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_ms.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#include <drm/drm_file.h>
+#include <linux/pm_runtime.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_gem.h"
+#include "ivpu_jsm_msg.h"
+#include "ivpu_ms.h"
+#include "ivpu_pm.h"
+
+#define MS_INFO_BUFFER_SIZE	  SZ_64K
+#define MS_NUM_BUFFERS		  2
+#define MS_READ_PERIOD_MULTIPLIER 2
+#define MS_MIN_SAMPLE_PERIOD_NS   1000000
+
+static struct ivpu_ms_instance *
+get_instance_by_mask(struct ivpu_file_priv *file_priv, u64 metric_mask)
+{
+	struct ivpu_ms_instance *ms;
+
+	lockdep_assert_held(&file_priv->ms_lock);
+
+	list_for_each_entry(ms, &file_priv->ms_instance_list, ms_instance_node)
+		if (ms->mask == metric_mask)
+			return ms;
+
+	return NULL;
+}
+
+int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct drm_ivpu_metric_streamer_start *args = data;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_ms_instance *ms;
+	u64 single_buff_size;
+	u32 sample_size;
+	int ret;
+
+	if (!args->metric_group_mask || !args->read_period_samples ||
+	    args->sampling_period_ns < MS_MIN_SAMPLE_PERIOD_NS)
+		return -EINVAL;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&file_priv->ms_lock);
+
+	if (get_instance_by_mask(file_priv, args->metric_group_mask)) {
+		ivpu_err(vdev, "Instance already exists (mask %#llx)\n", args->metric_group_mask);
+		ret = -EALREADY;
+		goto unlock;
+	}
+
+	ms = kzalloc(sizeof(*ms), GFP_KERNEL);
+	if (!ms) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	ms->mask = args->metric_group_mask;
+
+	ret = ivpu_jsm_metric_streamer_info(vdev, ms->mask, 0, 0, &sample_size, NULL);
+	if (ret)
+		goto err_free_ms;
+
+	single_buff_size = sample_size *
+		((u64)args->read_period_samples * MS_READ_PERIOD_MULTIPLIER);
+	ms->bo = ivpu_bo_create_global(vdev, PAGE_ALIGN(single_buff_size * MS_NUM_BUFFERS),
+				       DRM_IVPU_BO_CACHED | DRM_IVPU_BO_MAPPABLE);
+	if (!ms->bo) {
+		ivpu_err(vdev, "Failed to allocate MS buffer (size %llu)\n", single_buff_size);
+		ret = -ENOMEM;
+		goto err_free_ms;
+	}
+
+	ms->buff_size = ivpu_bo_size(ms->bo) / MS_NUM_BUFFERS;
+	ms->active_buff_vpu_addr = ms->bo->vpu_addr;
+	ms->inactive_buff_vpu_addr = ms->bo->vpu_addr + ms->buff_size;
+	ms->active_buff_ptr = ivpu_bo_vaddr(ms->bo);
+	ms->inactive_buff_ptr = ivpu_bo_vaddr(ms->bo) + ms->buff_size;
+
+	ret = ivpu_jsm_metric_streamer_start(vdev, ms->mask, args->sampling_period_ns,
+					     ms->active_buff_vpu_addr, ms->buff_size);
+	if (ret)
+		goto err_free_bo;
+
+	args->sample_size = sample_size;
+	args->max_data_size = ivpu_bo_size(ms->bo);
+	list_add_tail(&ms->ms_instance_node, &file_priv->ms_instance_list);
+	goto unlock;
+
+err_free_bo:
+	ivpu_bo_free(ms->bo);
+err_free_ms:
+	kfree(ms);
+unlock:
+	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
+	return ret;
+}
+
+static int
+copy_leftover_bytes(struct ivpu_ms_instance *ms,
+		    void __user *user_ptr, u64 user_size, u64 *user_bytes_copied)
+{
+	u64 copy_bytes;
+
+	if (ms->leftover_bytes) {
+		copy_bytes = min(user_size - *user_bytes_copied, ms->leftover_bytes);
+		if (copy_to_user(user_ptr + *user_bytes_copied, ms->leftover_addr, copy_bytes))
+			return -EFAULT;
+
+		ms->leftover_bytes -= copy_bytes;
+		ms->leftover_addr += copy_bytes;
+		*user_bytes_copied += copy_bytes;
+	}
+
+	return 0;
+}
+
+static int
+copy_samples_to_user(struct ivpu_device *vdev, struct ivpu_ms_instance *ms,
+		     void __user *user_ptr, u64 user_size, u64 *user_bytes_copied)
+{
+	u64 bytes_written;
+	int ret;
+
+	*user_bytes_copied = 0;
+
+	ret = copy_leftover_bytes(ms, user_ptr, user_size, user_bytes_copied);
+	if (ret)
+		return ret;
+
+	if (*user_bytes_copied == user_size)
+		return 0;
+
+	ret = ivpu_jsm_metric_streamer_update(vdev, ms->mask, ms->inactive_buff_vpu_addr,
+					      ms->buff_size, &bytes_written);
+	if (ret)
+		return ret;
+
+	swap(ms->active_buff_vpu_addr, ms->inactive_buff_vpu_addr);
+	swap(ms->active_buff_ptr, ms->inactive_buff_ptr);
+
+	ms->leftover_bytes = bytes_written;
+	ms->leftover_addr = ms->inactive_buff_ptr;
+
+	return copy_leftover_bytes(ms, user_ptr, user_size, user_bytes_copied);
+}
+
+int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_ivpu_metric_streamer_get_data *args = data;
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_ms_instance *ms;
+	u64 bytes_written;
+	int ret;
+
+	if (!args->metric_group_mask)
+		return -EINVAL;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&file_priv->ms_lock);
+
+	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
+	if (!ms) {
+		ivpu_err(vdev, "Instance doesn't exist for mask: %#llx\n", args->metric_group_mask);
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (!args->buffer_size) {
+		ret = ivpu_jsm_metric_streamer_update(vdev, ms->mask, 0, 0, &bytes_written);
+		if (ret)
+			goto unlock;
+		args->data_size = bytes_written + ms->leftover_bytes;
+		goto unlock;
+	}
+
+	if (!args->buffer_ptr) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ret = copy_samples_to_user(vdev, ms, u64_to_user_ptr(args->buffer_ptr),
+				   args->buffer_size, &args->data_size);
+unlock:
+	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
+	return ret;
+}
+
+static void free_instance(struct ivpu_file_priv *file_priv, struct ivpu_ms_instance *ms)
+{
+	lockdep_assert_held(&file_priv->ms_lock);
+
+	list_del(&ms->ms_instance_node);
+	ivpu_jsm_metric_streamer_stop(file_priv->vdev, ms->mask);
+	ivpu_bo_free(ms->bo);
+	kfree(ms);
+}
+
+int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct drm_ivpu_metric_streamer_stop *args = data;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_ms_instance *ms;
+	int ret;
+
+	if (!args->metric_group_mask)
+		return -EINVAL;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&file_priv->ms_lock);
+
+	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
+	if (ms)
+		free_instance(file_priv, ms);
+
+	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
+	return ms ? 0 : -EINVAL;
+}
+
+static inline struct ivpu_bo *get_ms_info_bo(struct ivpu_file_priv *file_priv)
+{
+	lockdep_assert_held(&file_priv->ms_lock);
+
+	if (file_priv->ms_info_bo)
+		return file_priv->ms_info_bo;
+
+	file_priv->ms_info_bo = ivpu_bo_create_global(file_priv->vdev, MS_INFO_BUFFER_SIZE,
+						      DRM_IVPU_BO_CACHED | DRM_IVPU_BO_MAPPABLE);
+	return file_priv->ms_info_bo;
+}
+
+int ivpu_ms_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_ivpu_metric_streamer_get_data *args = data;
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_bo *bo;
+	u64 info_size;
+	int ret;
+
+	if (!args->metric_group_mask)
+		return -EINVAL;
+
+	if (!args->buffer_size)
+		return ivpu_jsm_metric_streamer_info(vdev, args->metric_group_mask,
+						     0, 0, NULL, &args->data_size);
+	if (!args->buffer_ptr)
+		return -EINVAL;
+
+	mutex_lock(&file_priv->ms_lock);
+
+	bo = get_ms_info_bo(file_priv);
+	if (!bo) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	ret = ivpu_jsm_metric_streamer_info(vdev, args->metric_group_mask, bo->vpu_addr,
+					    ivpu_bo_size(bo), NULL, &info_size);
+	if (ret)
+		goto unlock;
+
+	if (args->buffer_size < info_size) {
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer_ptr), ivpu_bo_vaddr(bo), info_size))
+		ret = -EFAULT;
+
+	args->data_size = info_size;
+unlock:
+	mutex_unlock(&file_priv->ms_lock);
+
+	return ret;
+}
+
+void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
+{
+	struct ivpu_ms_instance *ms, *tmp;
+	struct ivpu_device *vdev = file_priv->vdev;
+
+	pm_runtime_get_sync(vdev->drm.dev);
+
+	mutex_lock(&file_priv->ms_lock);
+
+	if (file_priv->ms_info_bo) {
+		ivpu_bo_free(file_priv->ms_info_bo);
+		file_priv->ms_info_bo = NULL;
+	}
+
+	list_for_each_entry_safe(ms, tmp, &file_priv->ms_instance_list, ms_instance_node)
+		free_instance(file_priv, ms);
+
+	mutex_unlock(&file_priv->ms_lock);
+
+	pm_runtime_put_autosuspend(vdev->drm.dev);
+}
+
+void ivpu_ms_cleanup_all(struct ivpu_device *vdev)
+{
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+
+	mutex_lock(&vdev->context_list_lock);
+
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		ivpu_ms_cleanup(file_priv);
+
+	mutex_unlock(&vdev->context_list_lock);
+}
diff --git a/drivers/accel/ivpu/ivpu_ms.h b/drivers/accel/ivpu/ivpu_ms.h
new file mode 100644
index 000000000000..fbd5ebebc3d9
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_ms.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+#ifndef __IVPU_MS_H__
+#define __IVPU_MS_H__
+
+#include <linux/list.h>
+
+struct drm_device;
+struct drm_file;
+struct ivpu_bo;
+struct ivpu_device;
+struct ivpu_file_priv;
+
+struct ivpu_ms_instance {
+	struct ivpu_bo *bo;
+	struct list_head ms_instance_node;
+	u64 mask;
+	u64 buff_size;
+	u64 active_buff_vpu_addr;
+	u64 inactive_buff_vpu_addr;
+	void *active_buff_ptr;
+	void *inactive_buff_ptr;
+	u64 leftover_bytes;
+	void *leftover_addr;
+};
+
+int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int ivpu_ms_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv);
+void ivpu_ms_cleanup_all(struct ivpu_device *vdev);
+
+#endif /* __IVPU_MS_H__ */
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0ace218783c8..475ddc94f1cf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/highmem.h>
@@ -9,18 +9,33 @@
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_drv.h"
-#include "ivpu_hw.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
+#include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
+#include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
+#include "ivpu_ms.h"
 #include "ivpu_pm.h"
+#include "ivpu_trace.h"
+#include "vpu_boot_api.h"
 
 static bool ivpu_disable_recovery;
+#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG)
 module_param_named_unsafe(disable_recovery, ivpu_disable_recovery, bool, 0644);
-MODULE_PARM_DESC(disable_recovery, "Disables recovery when VPU hang is detected");
+MODULE_PARM_DESC(disable_recovery, "Disables recovery when NPU hang is detected");
+#endif
+
+static unsigned long ivpu_tdr_timeout_ms;
+module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(tdr_timeout_ms, "Timeout for device hang detection, in milliseconds, 0 - default");
+
+static unsigned long ivpu_inference_timeout_ms;
+module_param_named(inference_timeout_ms, ivpu_inference_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(inference_timeout_ms, "Inference maximum duration, in milliseconds, 0 - default");
 
 #define PM_RESCHEDULE_LIMIT     5
 
@@ -30,8 +45,10 @@ static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev)
 
 	ivpu_cmdq_reset_all_contexts(vdev);
 	ivpu_ipc_reset(vdev);
+	ivpu_fw_log_reset(vdev);
 	ivpu_fw_load(vdev);
 	fw->entry_point = fw->cold_boot_entry_point;
+	fw->last_heartbeat = 0;
 }
 
 static void ivpu_pm_prepare_warm_boot(struct ivpu_device *vdev)
@@ -52,11 +69,11 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
+	ivpu_prepare_for_reset(vdev);
+
 	ret = ivpu_shutdown(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		ivpu_err(vdev, "Failed to shutdown NPU: %d\n", ret);
 
 	return ret;
 }
@@ -66,74 +83,156 @@ static int ivpu_resume(struct ivpu_device *vdev)
 	int ret;
 
 retry:
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
+
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
-		return ret;
+		goto err_power_down;
 	}
 
 	ret = ivpu_mmu_enable(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to resume MMU: %d\n", ret);
-		ivpu_hw_power_down(vdev);
-		return ret;
+		goto err_power_down;
 	}
 
 	ret = ivpu_boot(vdev);
-	if (ret) {
-		ivpu_mmu_disable(vdev);
-		ivpu_hw_power_down(vdev);
-		if (!ivpu_fw_is_cold_boot(vdev)) {
-			ivpu_warn(vdev, "Failed to resume the FW: %d. Retrying cold boot..\n", ret);
-			ivpu_pm_prepare_cold_boot(vdev);
-			goto retry;
-		} else {
-			ivpu_err(vdev, "Failed to resume the FW: %d\n", ret);
-		}
+	if (ret)
+		goto err_mmu_disable;
+
+	return 0;
+
+err_mmu_disable:
+	ivpu_mmu_disable(vdev);
+err_power_down:
+	ivpu_hw_power_down(vdev);
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
+	if (!ivpu_fw_is_cold_boot(vdev)) {
+		ivpu_pm_prepare_cold_boot(vdev);
+		goto retry;
+	} else {
+		ivpu_err(vdev, "Failed to resume the FW: %d\n", ret);
 	}
 
 	return ret;
 }
 
+static void ivpu_pm_reset_begin(struct ivpu_device *vdev)
+{
+	pm_runtime_disable(vdev->drm.dev);
+
+	atomic_inc(&vdev->pm->reset_counter);
+	atomic_set(&vdev->pm->reset_pending, 1);
+	down_write(&vdev->pm->reset_lock);
+}
+
+static void ivpu_pm_reset_complete(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ivpu_pm_prepare_cold_boot(vdev);
+	ivpu_jobs_abort_all(vdev);
+	ivpu_ms_cleanup_all(vdev);
+
+	ret = ivpu_resume(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	} else {
+		pm_runtime_set_active(vdev->drm.dev);
+	}
+
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
+
+	pm_runtime_mark_last_busy(vdev->drm.dev);
+	pm_runtime_enable(vdev->drm.dev);
+}
+
 static void ivpu_pm_recovery_work(struct work_struct *work)
 {
 	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
 	struct ivpu_device *vdev = pm->vdev;
 	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
-	int ret;
 
-retry:
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
-		cond_resched();
-		goto retry;
+	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
+
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_jsm_state_dump(vdev);
+		ivpu_dev_coredump(vdev);
+		ivpu_suspend(vdev);
 	}
 
-	if (ret && ret != -EAGAIN)
-		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+	ivpu_pm_reset_complete(vdev);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 }
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
 {
-	struct ivpu_pm_info *pm = vdev->pm;
+	ivpu_err(vdev, "Recovery triggered by %s\n", reason);
 
 	if (ivpu_disable_recovery) {
 		ivpu_err(vdev, "Recovery not available when disable_recovery param is set\n");
 		return;
 	}
 
-	if (ivpu_is_fpga(vdev)) {
-		ivpu_err(vdev, "Recovery not available on FPGA\n");
-		return;
+	/* Trigger recovery if it's not in progress */
+	if (atomic_cmpxchg(&vdev->pm->reset_pending, 0, 1) == 0) {
+		ivpu_hw_diagnose_failure(vdev);
+		ivpu_hw_irq_disable(vdev); /* Disable IRQ early to protect from IRQ storm */
+		queue_work(system_unbound_wq, &vdev->pm->recovery_work);
+	}
+}
+
+static void ivpu_job_timeout_work(struct work_struct *work)
+{
+	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, job_timeout_work.work);
+	struct ivpu_device *vdev = pm->vdev;
+	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
+	unsigned long inference_timeout_ms = ivpu_inference_timeout_ms ? ivpu_inference_timeout_ms :
+					     vdev->timeout.inference;
+	u64 inference_max_retries;
+	u64 heartbeat;
+
+	if (ivpu_jsm_get_heartbeat(vdev, 0, &heartbeat) || heartbeat <= vdev->fw->last_heartbeat) {
+		ivpu_err(vdev, "Job timeout detected, heartbeat not progressed\n");
+		goto recovery;
 	}
 
-	/* Schedule recovery if it's not in progress */
-	if (atomic_cmpxchg(&pm->in_reset, 0, 1) == 0) {
-		ivpu_hw_irq_disable(vdev);
-		queue_work(system_long_wq, &pm->recovery_work);
+	inference_max_retries = DIV_ROUND_UP(inference_timeout_ms, timeout_ms);
+	if (atomic_fetch_inc(&vdev->job_timeout_counter) >= inference_max_retries) {
+		ivpu_err(vdev, "Job timeout detected, heartbeat limit (%lld) exceeded\n",
+			 inference_max_retries);
+		goto recovery;
 	}
+
+	vdev->fw->last_heartbeat = heartbeat;
+	ivpu_start_job_timeout_detection(vdev);
+	return;
+
+recovery:
+	atomic_set(&vdev->job_timeout_counter, 0);
+	ivpu_pm_trigger_recovery(vdev, "TDR");
+}
+
+void ivpu_start_job_timeout_detection(struct ivpu_device *vdev)
+{
+	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
+
+	/* No-op if already queued */
+	queue_delayed_work(system_wq, &vdev->pm->job_timeout_work, msecs_to_jiffies(timeout_ms));
+}
+
+void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev)
+{
+	cancel_delayed_work_sync(&vdev->pm->job_timeout_work);
+	atomic_set(&vdev->job_timeout_counter, 0);
 }
 
 int ivpu_pm_suspend_cb(struct device *dev)
@@ -142,6 +241,7 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	struct ivpu_device *vdev = to_ivpu_device(drm);
 	unsigned long timeout;
 
+	trace_pm("suspend");
 	ivpu_dbg(vdev, PM, "Suspend..\n");
 
 	timeout = jiffies + msecs_to_jiffies(vdev->timeout.tdr);
@@ -153,13 +253,13 @@ int ivpu_pm_suspend_cb(struct device *dev)
 		}
 	}
 
+	ivpu_jsm_pwr_d0i3_enter(vdev);
+
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
-	pci_save_state(to_pci_dev(dev));
-	pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
+	trace_pm("suspend done");
 
 	return 0;
 }
@@ -170,16 +270,15 @@ int ivpu_pm_resume_cb(struct device *dev)
 	struct ivpu_device *vdev = to_ivpu_device(drm);
 	int ret;
 
+	trace_pm("resume");
 	ivpu_dbg(vdev, PM, "Resume..\n");
 
-	pci_set_power_state(to_pci_dev(dev), PCI_D0);
-	pci_restore_state(to_pci_dev(dev));
-
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);
 
 	ivpu_dbg(vdev, PM, "Resume done.\n");
+	trace_pm("resume done");
 
 	return ret;
 }
@@ -188,32 +287,40 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 	struct ivpu_device *vdev = to_ivpu_device(drm);
-	int ret;
+	int ret, ret_d0i3;
+	bool is_idle;
 
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa));
+	drm_WARN_ON(&vdev->drm, work_pending(&vdev->pm->recovery_work));
+
+	trace_pm("runtime suspend");
 	ivpu_dbg(vdev, PM, "Runtime suspend..\n");
 
-	if (!ivpu_hw_is_idle(vdev) && vdev->pm->suspend_reschedule_counter) {
-		ivpu_dbg(vdev, PM, "Failed to enter idle, rescheduling suspend, retries left %d\n",
-			 vdev->pm->suspend_reschedule_counter);
-		pm_schedule_suspend(dev, vdev->timeout.reschedule_suspend);
-		vdev->pm->suspend_reschedule_counter--;
-		return -EAGAIN;
-	}
+	ivpu_mmu_disable(vdev);
+
+	is_idle = ivpu_hw_is_idle(vdev) || vdev->pm->dct_active_percent;
+	if (!is_idle)
+		ivpu_err(vdev, "NPU is not idle before autosuspend\n");
+
+	ret_d0i3 = ivpu_jsm_pwr_d0i3_enter(vdev);
+	if (ret_d0i3)
+		ivpu_err(vdev, "Failed to prepare for d0i3: %d\n", ret_d0i3);
 
 	ret = ivpu_suspend(vdev);
 	if (ret)
-		ivpu_err(vdev, "Failed to set suspend VPU: %d\n", ret);
+		ivpu_err(vdev, "Failed to suspend NPU: %d\n", ret);
 
-	if (!vdev->pm->suspend_reschedule_counter) {
-		ivpu_warn(vdev, "VPU failed to enter idle, force suspended.\n");
+	if (!is_idle || ret_d0i3) {
+		ivpu_err(vdev, "Forcing cold boot due to previous errors\n");
+		atomic_inc(&vdev->pm->reset_counter);
+		ivpu_dev_coredump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);
 	}
 
-	vdev->pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT;
-
 	ivpu_dbg(vdev, PM, "Runtime suspend done.\n");
+	trace_pm("runtime suspend done");
 
 	return 0;
 }
@@ -224,6 +331,7 @@ int ivpu_pm_runtime_resume_cb(struct device *dev)
 	struct ivpu_device *vdev = to_ivpu_device(drm);
 	int ret;
 
+	trace_pm("runtime resume");
 	ivpu_dbg(vdev, PM, "Runtime resume..\n");
 
 	ret = ivpu_resume(vdev);
@@ -231,6 +339,7 @@ int ivpu_pm_runtime_resume_cb(struct device *dev)
 		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
 
 	ivpu_dbg(vdev, PM, "Runtime resume done.\n");
+	trace_pm("runtime resume done");
 
 	return ret;
 }
@@ -240,21 +349,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev)
 	int ret;
 
 	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	if (!drm_WARN_ON(&vdev->drm, ret < 0))
-		vdev->pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT;
-
-	return ret;
-}
-
-int ivpu_rpm_get_if_active(struct ivpu_device *vdev)
-{
-	int ret;
-
-	ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n",
-		 atomic_read(&vdev->drm.dev->power.usage_count));
-
-	ret = pm_runtime_get_if_active(vdev->drm.dev, false);
-	drm_WARN_ON(&vdev->drm, ret < 0);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	}
 
 	return ret;
 }
@@ -269,31 +367,27 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
-	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->in_reset, 1);
-	ivpu_prepare_for_reset(vdev);
-	ivpu_hw_reset(vdev);
-	ivpu_pm_prepare_cold_boot(vdev);
-	ivpu_jobs_abort_all(vdev);
+
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_prepare_for_reset(vdev);
+		ivpu_hw_reset(vdev);
+	}
+
 	ivpu_dbg(vdev, PM, "Pre-reset done.\n");
 }
 
 void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
-	int ret;
 
 	ivpu_dbg(vdev, PM, "Post-reset..\n");
-	ret = ivpu_resume(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	atomic_set(&vdev->pm->in_reset, 0);
-	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	ivpu_pm_reset_complete(vdev);
+
+	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 }
 
 void ivpu_pm_init(struct ivpu_device *vdev)
@@ -303,10 +397,13 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 	int delay;
 
 	pm->vdev = vdev;
-	pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT;
 
-	atomic_set(&pm->in_reset, 0);
+	init_rwsem(&pm->reset_lock);
+	atomic_set(&pm->reset_pending, 0);
+	atomic_set(&pm->reset_counter, 0);
+
 	INIT_WORK(&pm->recovery_work, ivpu_pm_recovery_work);
+	INIT_DELAYED_WORK(&pm->job_timeout_work, ivpu_job_timeout_work);
 
 	if (ivpu_disable_recovery)
 		delay = -1;
@@ -315,20 +412,21 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, delay);
+	pm_runtime_set_active(dev);
 
 	ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay);
 }
 
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev)
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev)
 {
-	cancel_work_sync(&vdev->pm->recovery_work);
+	drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work));
+	disable_work_sync(&vdev->pm->recovery_work);
 }
 
 void ivpu_pm_enable(struct ivpu_device *vdev)
 {
 	struct device *dev = vdev->drm.dev;
 
-	pm_runtime_set_active(dev);
 	pm_runtime_allow(dev);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
@@ -339,3 +437,71 @@ void ivpu_pm_disable(struct ivpu_device *vdev)
 	pm_runtime_get_noresume(vdev->drm.dev);
 	pm_runtime_forbid(vdev->drm.dev);
 }
+
+int ivpu_pm_dct_init(struct ivpu_device *vdev)
+{
+	if (vdev->pm->dct_active_percent)
+		return ivpu_pm_dct_enable(vdev, vdev->pm->dct_active_percent);
+
+	return 0;
+}
+
+int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent)
+{
+	u32 active_us, inactive_us;
+	int ret;
+
+	if (active_percent == 0 || active_percent > 100)
+		return -EINVAL;
+
+	active_us = (DCT_PERIOD_US * active_percent) / 100;
+	inactive_us = DCT_PERIOD_US - active_us;
+
+	vdev->pm->dct_active_percent = active_percent;
+
+	ivpu_dbg(vdev, PM, "DCT requested %u%% (D0: %uus, D0i2: %uus)\n",
+		 active_percent, active_us, inactive_us);
+
+	ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us);
+	if (ret) {
+		ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ivpu_pm_dct_disable(struct ivpu_device *vdev)
+{
+	int ret;
+
+	vdev->pm->dct_active_percent = 0;
+
+	ivpu_dbg(vdev, PM, "DCT requested to be disabled\n");
+
+	ret = ivpu_jsm_dct_disable(vdev);
+	if (ret) {
+		ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void ivpu_pm_irq_dct_work_fn(struct work_struct *work)
+{
+	struct ivpu_device *vdev = container_of(work, struct ivpu_device, irq_dct_work);
+	bool enable;
+	int ret;
+
+	if (ivpu_hw_btrs_dct_get_request(vdev, &enable))
+		return;
+
+	if (enable)
+		ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT);
+	else
+		ret = ivpu_pm_dct_disable(vdev);
+
+	if (!ret)
+		ivpu_hw_btrs_dct_set_status(vdev, enable, vdev->pm->dct_active_percent);
+}
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 044db150be07..a2aa7a27f32e 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -1,28 +1,31 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_PM_H__
 #define __IVPU_PM_H__
 
+#include <linux/rwsem.h>
 #include <linux/types.h>
 
 struct ivpu_device;
 
 struct ivpu_pm_info {
 	struct ivpu_device *vdev;
+	struct delayed_work job_timeout_work;
 	struct work_struct recovery_work;
-	atomic_t in_reset;
+	struct rw_semaphore reset_lock;
 	atomic_t reset_counter;
+	atomic_t reset_pending;
 	bool is_warmboot;
-	u32 suspend_reschedule_counter;
+	u8 dct_active_percent;
 };
 
 void ivpu_pm_init(struct ivpu_device *vdev);
 void ivpu_pm_enable(struct ivpu_device *vdev);
 void ivpu_pm_disable(struct ivpu_device *vdev);
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev);
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev);
 
 int ivpu_pm_suspend_cb(struct device *dev);
 int ivpu_pm_resume_cb(struct device *dev);
@@ -33,9 +36,15 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev);
 void ivpu_pm_reset_done_cb(struct pci_dev *pdev);
 
 int __must_check ivpu_rpm_get(struct ivpu_device *vdev);
-int __must_check ivpu_rpm_get_if_active(struct ivpu_device *vdev);
 void ivpu_rpm_put(struct ivpu_device *vdev);
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev);
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason);
+void ivpu_start_job_timeout_detection(struct ivpu_device *vdev);
+void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev);
+
+int ivpu_pm_dct_init(struct ivpu_device *vdev);
+int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent);
+int ivpu_pm_dct_disable(struct ivpu_device *vdev);
+void ivpu_pm_irq_dct_work_fn(struct work_struct *work);
 
 #endif /* __IVPU_PM_H__ */
diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c
new file mode 100644
index 000000000000..268ab7744a8b
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_sysfs.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/pm_runtime.h>
+#include <linux/units.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_gem.h"
+#include "ivpu_fw.h"
+#include "ivpu_hw.h"
+#include "ivpu_sysfs.h"
+
+/**
+ * DOC: npu_busy_time_us
+ *
+ * npu_busy_time_us is the time that the device spent executing jobs.
+ * The time is counted when and only when there are jobs submitted to firmware.
+ *
+ * This time can be used to measure the utilization of NPU, either by calculating
+ * npu_busy_time_us difference between two timepoints (i.e. measuring the time
+ * that the NPU was active during some workload) or monitoring utilization percentage
+ * by reading npu_busy_time_us periodically.
+ *
+ * When reading the value periodically, it shouldn't be read too often as it may have
+ * an impact on job submission performance. Recommended period is 1 second.
+ */
+static ssize_t
+npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	ktime_t total, now = 0;
+
+	mutex_lock(&vdev->submitted_jobs_lock);
+
+	total = vdev->busy_time;
+	if (!xa_empty(&vdev->submitted_jobs_xa))
+		now = ktime_sub(ktime_get(), vdev->busy_start_ts);
+	mutex_unlock(&vdev->submitted_jobs_lock);
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_us(ktime_add(total, now)));
+}
+
+static DEVICE_ATTR_RO(npu_busy_time_us);
+
+/**
+ * DOC: npu_memory_utilization
+ *
+ * The npu_memory_utilization is used to report in bytes a current NPU memory utilization.
+ *
+ */
+static ssize_t
+npu_memory_utilization_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	struct ivpu_bo *bo;
+	u64 total_npu_memory = 0;
+
+	mutex_lock(&vdev->bo_list_lock);
+	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
+		total_npu_memory += bo->base.base.size;
+	mutex_unlock(&vdev->bo_list_lock);
+
+	return sysfs_emit(buf, "%lld\n", total_npu_memory);
+}
+
+static DEVICE_ATTR_RO(npu_memory_utilization);
+
+/**
+ * DOC: sched_mode
+ *
+ * The sched_mode is used to report current NPU scheduling mode.
+ *
+ * It returns following strings:
+ * - "HW"		- Hardware Scheduler mode
+ * - "OS"		- Operating System Scheduler mode
+ *
+ */
+static ssize_t
+sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+
+	return sysfs_emit(buf, "%s\n", vdev->fw->sched_mode ? "HW" : "OS");
+}
+
+static DEVICE_ATTR_RO(sched_mode);
+
+/**
+ * DOC: npu_max_frequency
+ *
+ * The npu_max_frequency shows maximum frequency in MHz of the NPU's data
+ * processing unit
+ */
+static ssize_t
+npu_max_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	u32 freq = ivpu_hw_dpu_max_freq_get(vdev);
+
+	return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ);
+}
+
+static DEVICE_ATTR_RO(npu_max_frequency_mhz);
+
+/**
+ * DOC: npu_current_frequency_mhz
+ *
+ * The npu_current_frequency_mhz shows current frequency in MHz of the NPU's
+ * data processing unit
+ */
+static ssize_t
+npu_current_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	u32 freq = 0;
+
+	/* Read frequency only if device is active, otherwise frequency is 0 */
+	if (pm_runtime_get_if_active(vdev->drm.dev) > 0) {
+		freq = ivpu_hw_dpu_freq_get(vdev);
+
+		pm_runtime_put_autosuspend(vdev->drm.dev);
+	}
+
+	return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ);
+}
+
+static DEVICE_ATTR_RO(npu_current_frequency_mhz);
+
+static struct attribute *ivpu_dev_attrs[] = {
+	&dev_attr_npu_busy_time_us.attr,
+	&dev_attr_npu_memory_utilization.attr,
+	&dev_attr_sched_mode.attr,
+	&dev_attr_npu_max_frequency_mhz.attr,
+	&dev_attr_npu_current_frequency_mhz.attr,
+	NULL,
+};
+
+static struct attribute_group ivpu_dev_attr_group = {
+	.attrs = ivpu_dev_attrs,
+};
+
+void ivpu_sysfs_init(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ret = devm_device_add_group(vdev->drm.dev, &ivpu_dev_attr_group);
+	if (ret)
+		ivpu_warn(vdev, "Failed to add group to device, ret %d", ret);
+}
diff --git a/drivers/accel/ivpu/ivpu_sysfs.h b/drivers/accel/ivpu/ivpu_sysfs.h
new file mode 100644
index 000000000000..9836f09b35a3
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_sysfs.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+
+#ifndef __IVPU_SYSFS_H__
+#define __IVPU_SYSFS_H__
+
+#include "ivpu_drv.h"
+
+void ivpu_sysfs_init(struct ivpu_device *vdev);
+
+#endif /* __IVPU_SYSFS_H__ */
diff --git a/drivers/accel/ivpu/ivpu_trace.h b/drivers/accel/ivpu/ivpu_trace.h
new file mode 100644
index 000000000000..eb792038e701
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_trace.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#if !defined(__IVPU_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ)
+#define __IVPU_TRACE_H__
+
+#include <linux/tracepoint.h>
+#include "ivpu_drv.h"
+#include "ivpu_job.h"
+#include "vpu_jsm_api.h"
+#include "ivpu_jsm_msg.h"
+#include "ivpu_ipc.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vpu
+#define TRACE_INCLUDE_FILE ivpu_trace
+
+TRACE_EVENT(pm,
+	    TP_PROTO(const char *event),
+	    TP_ARGS(event),
+	    TP_STRUCT__entry(__field(const char *, event)),
+	    TP_fast_assign(__entry->event = event;),
+	    TP_printk("%s", __entry->event)
+);
+
+TRACE_EVENT(job,
+	    TP_PROTO(const char *event, struct ivpu_job *job),
+	    TP_ARGS(event, job),
+	    TP_STRUCT__entry(__field(const char *, event)
+		__field(u32, ctx_id)
+		__field(u32, engine_id)
+		__field(u32, job_id)
+		),
+	    TP_fast_assign(__entry->event = event;
+		__entry->ctx_id = job->file_priv->ctx.id;
+		__entry->engine_id = job->engine_idx;
+		__entry->job_id = job->job_id;),
+	    TP_printk("%s context:%d engine:%d job:%d",
+		      __entry->event,
+		      __entry->ctx_id,
+		      __entry->engine_id,
+		      __entry->job_id)
+);
+
+TRACE_EVENT(jsm,
+	    TP_PROTO(const char *event, struct vpu_jsm_msg *msg),
+	    TP_ARGS(event, msg),
+	    TP_STRUCT__entry(__field(const char *, event)
+		__field(const char *, type)
+		__field(enum vpu_ipc_msg_status, status)
+		__field(u32, request_id)
+		__field(u32, result)
+		),
+	    TP_fast_assign(__entry->event = event;
+		__entry->type = ivpu_jsm_msg_type_to_str(msg->type);
+		__entry->status = msg->status;
+		__entry->request_id = msg->request_id;
+		__entry->result = msg->result;),
+	    TP_printk("%s type:%s, status:%#x, id:%#x, result:%#x",
+		      __entry->event,
+		      __entry->type,
+		      __entry->status,
+		      __entry->request_id,
+		      __entry->result)
+);
+
+#endif /* __IVPU_TRACE_H__ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/accel/ivpu/ivpu_trace_points.c b/drivers/accel/ivpu/ivpu_trace_points.c
new file mode 100644
index 000000000000..f8fb99de0de3
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_trace_points.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "ivpu_trace.h"
+#endif
diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 6b71be92ba65..218468bbbcad 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -1,17 +1,19 @@
 /* SPDX-License-Identifier: MIT */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (c) 2020-2024, Intel Corporation.
  */
 
 #ifndef VPU_BOOT_API_H
 #define VPU_BOOT_API_H
 
 /*
- * =========== FW API version information beginning ================
- *  The bellow values will be used to construct the version info this way:
+ *  The below values will be used to construct the version info this way:
  *  fw_bin_header->api_version[VPU_BOOT_API_VER_ID] = (VPU_BOOT_API_VER_MAJOR << 16) |
  *  VPU_BOOT_API_VER_MINOR;
- *  VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes.
+ *  VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes
+ *  This information is collected by using vpuip_2/application/vpuFirmware/make_std_fw_image.py
+ *  If a header is missing this info we ignore the header, if a header is missing or contains
+ *  partial info a build error will be generated.
  */
 
 /*
@@ -24,21 +26,20 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 12
+#define VPU_BOOT_API_VER_MINOR 28
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
  */
-#define VPU_BOOT_API_VER_PATCH 2
+#define VPU_BOOT_API_VER_PATCH 3
 
 /*
  * Index in the API version table
  * Must be unique for each API
  */
 #define VPU_BOOT_API_VER_INDEX 0
-/* ------------ FW API version information end ---------------------*/
 
-#pragma pack(push, 1)
+#pragma pack(push, 4)
 
 /*
  * Firmware image header format
@@ -63,6 +64,32 @@ struct vpu_firmware_header {
 	/* Size of memory require for firmware execution */
 	u32 runtime_size;
 	u32 shave_nn_fw_size;
+	/*
+	 * Size of primary preemption buffer, assuming a 2-job submission queue.
+	 * NOTE: host driver is expected to adapt size accordingly to actual
+	 * submission queue size and device capabilities.
+	 */
+	u32 preemption_buffer_1_size;
+	/*
+	 * Size of secondary preemption buffer, assuming a 2-job submission queue.
+	 * NOTE: host driver is expected to adapt size accordingly to actual
+	 * submission queue size and device capabilities.
+	 */
+	u32 preemption_buffer_2_size;
+	/*
+	 * Maximum preemption buffer size that the FW can use: no need for the host
+	 * driver to allocate more space than that specified by these fields.
+	 * A value of 0 means no declared limit.
+	 */
+	u32 preemption_buffer_1_max_size;
+	u32 preemption_buffer_2_max_size;
+	/* Space reserved for future preemption-related fields. */
+	u32 preemption_reserved[4];
+	/* FW image read only section start address, 4KB aligned */
+	u64 ro_section_start_address;
+	/* FW image read only section size, 4KB aligned */
+	u32 ro_section_size;
+	u32 reserved;
 };
 
 /*
@@ -89,6 +116,14 @@ enum VPU_BOOT_L2_CACHE_CFG_TYPE {
 	VPU_BOOT_L2_CACHE_CFG_NUM = 2
 };
 
+/** VPU MCA ECC signalling mode. By default, no signalling is used */
+enum VPU_BOOT_MCA_ECC_SIGNAL_TYPE {
+	VPU_BOOT_MCA_ECC_NONE = 0,
+	VPU_BOOT_MCA_ECC_CORR = 1,
+	VPU_BOOT_MCA_ECC_FATAL = 2,
+	VPU_BOOT_MCA_ECC_BOTH = 3
+};
+
 /**
  * Logging destinations.
  *
@@ -106,7 +141,7 @@ enum vpu_trace_destination {
 /*
  * Processor bit shifts (for loggable HW components).
  */
-#define VPU_TRACE_PROC_BIT_ARM	     0
+#define VPU_TRACE_PROC_BIT_RESERVED  0
 #define VPU_TRACE_PROC_BIT_LRT	     1
 #define VPU_TRACE_PROC_BIT_LNN	     2
 #define VPU_TRACE_PROC_BIT_SHV_0     3
@@ -131,9 +166,9 @@ enum vpu_trace_destination {
 #define VPU_TRACE_PROC_BIT_ACT_SHV_3 22
 #define VPU_TRACE_PROC_NO_OF_HW_DEVS 23
 
-/* KMB HW component IDs are sequential, so define first and last IDs. */
-#define VPU_TRACE_PROC_BIT_KMB_FIRST VPU_TRACE_PROC_BIT_LRT
-#define VPU_TRACE_PROC_BIT_KMB_LAST  VPU_TRACE_PROC_BIT_SHV_15
+/* VPU 30xx HW component IDs are sequential, so define first and last IDs. */
+#define VPU_TRACE_PROC_BIT_30XX_FIRST VPU_TRACE_PROC_BIT_LRT
+#define VPU_TRACE_PROC_BIT_30XX_LAST  VPU_TRACE_PROC_BIT_SHV_15
 
 struct vpu_boot_l2_cache_config {
 	u8 use;
@@ -148,6 +183,36 @@ struct vpu_warm_boot_section {
 	u32 is_clear_op;
 };
 
+/*
+ * When HW scheduling mode is enabled, a present period is defined.
+ * It will be used by VPU to swap between normal and focus priorities
+ * to prevent starving of normal priority band (when implemented).
+ * Host must provide a valid value at boot time in
+ * `vpu_focus_present_timer_ms`. If the value provided by the host is not within the
+ * defined range a default value will be used. Here we define the min. and max.
+ * allowed values and the and default value of the present period. Units are milliseconds.
+ */
+#define VPU_PRESENT_CALL_PERIOD_MS_DEFAULT 50
+#define VPU_PRESENT_CALL_PERIOD_MS_MIN	   16
+#define VPU_PRESENT_CALL_PERIOD_MS_MAX	   10000
+
+/**
+ * Macros to enable various power profiles within the NPU.
+ * To be defined as part of 32 bit mask.
+ */
+#define POWER_PROFILE_SURVIVABILITY 0x1
+
+/**
+ * Enum for dvfs_mode boot param.
+ */
+enum vpu_governor {
+	VPU_GOV_DEFAULT = 0, /* Default Governor for the system */
+	VPU_GOV_MAX_PERFORMANCE = 1, /* Maximum performance governor */
+	VPU_GOV_ON_DEMAND = 2, /* On Demand frequency control governor */
+	VPU_GOV_POWER_SAVE = 3, /* Power save governor */
+	VPU_GOV_ON_DEMAND_PRIORITY_AWARE = 4 /* On Demand priority based governor */
+};
+
 struct vpu_boot_params {
 	u32 magic;
 	u32 vpu_id;
@@ -218,6 +283,7 @@ struct vpu_boot_params {
 	 * the threshold will not be logged); applies to every enabled logging
 	 * destination and loggable HW component. See 'mvLog_t' enum for acceptable
 	 * values.
+	 * TODO: EISW-33556: Move log level definition (mvLog_t) to this file.
 	 */
 	u32 default_trace_level;
 	u32 boot_type;
@@ -249,7 +315,58 @@ struct vpu_boot_params {
 	u32 temp_sensor_period_ms;
 	/** PLL ratio for efficient clock frequency */
 	u32 pn_freq_pll_ratio;
-	u32 pad4[28];
+	/**
+	 * DVFS Mode:
+	 * 0 - Default, DVFS mode selected by the firmware
+	 * 1 - Max Performance
+	 * 2 - On Demand
+	 * 3 - Power Save
+	 * 4 - On Demand Priority Aware
+	 */
+	u32 dvfs_mode;
+	/**
+	 * Depending on DVFS Mode:
+	 * On-demand: Default if 0.
+	 *    Bit 0-7   - uint8_t: Highest residency percent
+	 *    Bit 8-15  - uint8_t: High residency percent
+	 *    Bit 16-23 - uint8_t: Low residency percent
+	 *    Bit 24-31 - uint8_t: Lowest residency percent
+	 *    Bit 32-35 - unsigned 4b: PLL Ratio increase amount on highest residency
+	 *    Bit 36-39 - unsigned 4b: PLL Ratio increase amount on high residency
+	 *    Bit 40-43 - unsigned 4b: PLL Ratio decrease amount on low residency
+	 *    Bit 44-47 - unsigned 4b: PLL Ratio decrease amount on lowest frequency
+	 *    Bit 48-55 - uint8_t: Period (ms) for residency decisions
+	 *    Bit 56-63 - uint8_t: Averaging windows (as multiples of period. Max: 30 decimal)
+	 * Power Save/Max Performance: Unused
+	 */
+	u64 dvfs_param;
+	/**
+	 * D0i3 delayed entry
+	 * Bit0: Disable CPU state save on D0i2 entry flow.
+	 *       0: Every D0i2 entry saves state. Save state IPC message ignored.
+	 *       1: IPC message required to save state on D0i3 entry flow.
+	 */
+	u32 d0i3_delayed_entry;
+	/* Time spent by VPU in D0i3 state */
+	u64 d0i3_residency_time_us;
+	/* Value of VPU perf counter at the time of entering D0i3 state . */
+	u64 d0i3_entry_vpu_ts;
+	/*
+	 * The system time of the host operating system in microseconds.
+	 * E.g the number of microseconds since 1st of January 1970, or whatever
+	 * date the host operating system uses to maintain system time.
+	 * This value will be used to track system time on the VPU.
+	 * The KMD is required to update this value on every VPU reset.
+	 */
+	u64 system_time_us;
+	u32 pad4[2];
+	/*
+	 * The delta between device monotonic time and the current value of the
+	 * HW timestamp register, in ticks. Written by the firmware during boot.
+	 * Can be used by the KMD to calculate device time.
+	 */
+	u64 device_time_delta_ticks;
+	u32 pad7[14];
 	/* Warm boot information: 0x400 - 0x43F */
 	u32 warm_boot_sections_count;
 	u32 warm_boot_start_address_reference;
@@ -274,14 +391,19 @@ struct vpu_boot_params {
 	u32 vpu_scheduling_mode;
 	/* Present call period in milliseconds. */
 	u32 vpu_focus_present_timer_ms;
-	/* Unused/reserved: 0x478 - 0xFFF */
-	u32 pad6[738];
+	/* VPU ECC Signaling */
+	u32 vpu_uses_ecc_mca_signal;
+	/* Values defined by POWER_PROFILE* macros */
+	u32 power_profile;
+	/* Microsecond value for DCT active cycle */
+	u32 dct_active_us;
+	/* Microsecond value for DCT inactive cycle */
+	u32 dct_inactive_us;
+	/* Unused/reserved: 0x488 - 0xFFF */
+	u32 pad6[734];
 };
 
-/*
- * Magic numbers set between host and vpu to detect corruptio of tracing init
- */
-
+/* Magic numbers set between host and vpu to detect corruption of tracing init */
 #define VPU_TRACING_BUFFER_CANARY (0xCAFECAFE)
 
 /* Tracing buffer message format definitions */
@@ -301,7 +423,9 @@ struct vpu_tracing_buffer_header {
 	u32 host_canary_start;
 	/* offset from start of buffer for trace entries */
 	u32 read_index;
-	u32 pad_to_cache_line_size_0[14];
+	/* keeps track of wrapping on the reader side */
+	u32 read_wrap_count;
+	u32 pad_to_cache_line_size_0[13];
 	/* End of first cache line */
 
 	/**
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 2949ec8365bd..4b6b2b3d2583 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: MIT */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (c) 2020-2024, Intel Corporation.
  */
 
 /**
@@ -22,12 +22,12 @@
 /*
  * Minor version changes when API backward compatibility is preserved.
  */
-#define VPU_JSM_API_VER_MINOR 0
+#define VPU_JSM_API_VER_MINOR 29
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
  */
-#define VPU_JSM_API_VER_PATCH 1
+#define VPU_JSM_API_VER_PATCH 0
 
 /*
  * Index in the API version table
@@ -36,22 +36,24 @@
 
 /*
  * Number of Priority Bands for Hardware Scheduling
- * Bands: RealTime, Focus, Normal, Idle
+ * Bands: Idle(0), Normal(1), Focus(2), RealTime(3)
  */
 #define VPU_HWS_NUM_PRIORITY_BANDS 4
 
 /* Max number of impacted contexts that can be dealt with the engine reset command */
 #define VPU_MAX_ENGINE_RESET_IMPACTED_CONTEXTS 3
 
-/** Pack the API structures for now, once alignment issues are fixed this can be removed */
-#pragma pack(push, 1)
+/*
+ * Pack the API structures to enforce binary compatibility
+ * Align to 8 bytes for optimal performance
+ */
+#pragma pack(push, 8)
 
 /*
  * Engine indexes.
  */
 #define VPU_ENGINE_COMPUTE 0
-#define VPU_ENGINE_COPY	   1
-#define VPU_ENGINE_NB	   2
+#define VPU_ENGINE_NB	   1
 
 /*
  * VPU status values.
@@ -71,6 +73,7 @@
 #define VPU_JSM_STATUS_MVNCI_INTERNAL_ERROR		 0xCU
 /* Job status returned when the job was preempted mid-inference */
 #define VPU_JSM_STATUS_PREEMPTED_MID_INFERENCE		 0xDU
+#define VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW	 0xEU
 
 /*
  * Host <-> VPU IPC channels.
@@ -83,16 +86,60 @@
 /*
  * Job flags bit masks.
  */
-#define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001
+enum {
+	/*
+	 * Null submission mask.
+	 * When set, batch buffer's commands are not processed but returned as
+	 * successful immediately, except fences and timestamps.
+	 * When cleared, batch buffer's commands are processed normally.
+	 * Used for testing and profiling purposes.
+	 */
+	VPU_JOB_FLAGS_NULL_SUBMISSION_MASK = (1 << 0U),
+	/*
+	 * Inline command mask.
+	 * When set, the object in job queue is an inline command (see struct vpu_inline_cmd below).
+	 * When cleared, the object in job queue is a job (see struct vpu_job_queue_entry below).
+	 */
+	VPU_JOB_FLAGS_INLINE_CMD_MASK = (1 << 1U),
+	/*
+	 * VPU private data mask.
+	 * Reserved for the VPU to store private data about the job (or inline command)
+	 * while being processed.
+	 */
+	VPU_JOB_FLAGS_PRIVATE_DATA_MASK = 0xFFFF0000U
+};
 
 /*
- * Sizes of the reserved areas in jobs, in bytes.
- */
-#define VPU_JOB_RESERVED_BYTES	     16
-/*
- * Sizes of the reserved areas in job queues, in bytes.
+ * Job queue flags bit masks.
  */
-#define VPU_JOB_QUEUE_RESERVED_BYTES 52
+enum {
+	/*
+	 * No job done notification mask.
+	 * When set, indicates that no job done notification should be sent for any
+	 * job from this queue. When cleared, indicates that job done notification
+	 * should be sent for every job completed from this queue.
+	 */
+	VPU_JOB_QUEUE_FLAGS_NO_JOB_DONE_MASK = (1 << 0U),
+	/*
+	 * Native fence usage mask.
+	 * When set, indicates that job queue uses native fences (as inline commands
+	 * in job queue). Such queues may also use legacy fences (as commands in batch buffers).
+	 * When cleared, indicates the job queue only uses legacy fences.
+	 * NOTES:
+	 *   1. For queues using native fences, VPU expects that all jobs in the queue
+	 *      are immediately followed by an inline command object. This object is expected
+	 *      to be a fence signal command in most cases, but can also be a NOP in case the host
+	 *      does not need per-job fence signalling. Other inline commands objects can be
+	 *      inserted between "job and inline command" pairs.
+	 *  2. Native fence queues are only supported on VPU 40xx onwards.
+	 */
+	VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U),
+
+	/*
+	 * Enable turbo mode for testing NPU performance; not recommended for regular usage.
+	 */
+	VPU_JOB_QUEUE_FLAGS_TURBO_MODE = (1 << 2U)
+};
 
 /*
  * Max length (including trailing NULL char) of trace entity name (e.g., the
@@ -109,17 +156,141 @@
 #define VPU_DYNDBG_CMD_MAX_LEN 96
 
 /*
+ * For HWS command queue scheduling, we can prioritise command queues inside the
+ * same process with a relative in-process priority. Valid values for relative
+ * priority are given below - max and min.
+ */
+#define VPU_HWS_COMMAND_QUEUE_MAX_IN_PROCESS_PRIORITY 7
+#define VPU_HWS_COMMAND_QUEUE_MIN_IN_PROCESS_PRIORITY -7
+
+/*
+ * For HWS priority scheduling, we can have multiple realtime priority bands.
+ * They are numbered 0 to a MAX.
+ */
+#define VPU_HWS_MAX_REALTIME_PRIORITY_LEVEL 31U
+
+/*
+ * vpu_jsm_engine_reset_context flag definitions
+ */
+#define VPU_ENGINE_RESET_CONTEXT_FLAG_COLLATERAL_DAMAGE_MASK BIT(0)
+#define VPU_ENGINE_RESET_CONTEXT_HANG_PRIMARY_CAUSE	     0
+#define VPU_ENGINE_RESET_CONTEXT_COLLATERAL_DAMAGE	     1
+
+/*
+ * Invalid command queue handle identifier. Applies to cmdq_id and cmdq_group
+ * in this API.
+ */
+#define VPU_HWS_INVALID_CMDQ_HANDLE 0ULL
+
+/*
+ * Inline commands types.
+ */
+/*
+ * NOP.
+ * VPU does nothing other than consuming the inline command object.
+ */
+#define VPU_INLINE_CMD_TYPE_NOP		 0x0
+/*
+ * Fence wait.
+ * VPU waits for the fence current value to reach monitored value.
+ * Fence wait operations are executed upon job dispatching. While waiting for
+ * the fence to be satisfied, VPU blocks fetching of the next objects in the queue.
+ * Jobs present in the queue prior to the fence wait object may be processed
+ * concurrently.
+ */
+#define VPU_INLINE_CMD_TYPE_FENCE_WAIT	 0x1
+/*
+ * Fence signal.
+ * VPU sets the fence current value to the provided value. If new current value
+ * is equal to or higher than monitored value, VPU sends fence signalled notification
+ * to the host. Fence signal operations are executed upon completion of all the jobs
+ * present in the queue prior to them, and in-order relative to each other in the queue.
+ * But jobs in-between them may be processed concurrently and may complete out-of-order.
+ */
+#define VPU_INLINE_CMD_TYPE_FENCE_SIGNAL 0x2
+
+/*
+ * Job scheduling priority bands for both hardware scheduling and OS scheduling.
+ */
+enum vpu_job_scheduling_priority_band {
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE = 0,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL = 1,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS = 2,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME = 3,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT = 4,
+};
+
+/*
  * Job format.
+ * Jobs defines the actual workloads to be executed by a given engine.
  */
 struct vpu_job_queue_entry {
-	u64 batch_buf_addr; /**< Address of VPU commands batch buffer */
-	u32 job_id;	  /**< Job ID */
-	u32 flags; /**< Flags bit field, see VPU_JOB_FLAGS_* above */
-	u64 root_page_table_addr; /**< Address of root page table to use for this job */
-	u64 root_page_table_update_counter; /**< Page tables update events counter */
-	u64 preemption_buffer_address; /**< Address of the preemption buffer to use for this job */
-	u64 preemption_buffer_size; /**< Size of the preemption buffer to use for this job */
-	u8 reserved_0[VPU_JOB_RESERVED_BYTES];
+	/**< Address of VPU commands batch buffer */
+	u64 batch_buf_addr;
+	/**< Job ID */
+	u32 job_id;
+	/**< Flags bit field, see VPU_JOB_FLAGS_* above */
+	u32 flags;
+	/**
+	 * Doorbell ring timestamp taken by KMD from SoC's global system clock, in
+	 * microseconds. NPU can convert this value to its own fixed clock's timebase,
+	 * to match other profiling timestamps.
+	 */
+	u64 doorbell_timestamp;
+	/**< Extra id for job tracking, used only in the firmware perf traces */
+	u64 host_tracking_id;
+	/**< Address of the primary preemption buffer to use for this job */
+	u64 primary_preempt_buf_addr;
+	/**< Size of the primary preemption buffer to use for this job */
+	u32 primary_preempt_buf_size;
+	/**< Size of secondary preemption buffer to use for this job */
+	u32 secondary_preempt_buf_size;
+	/**< Address of secondary preemption buffer to use for this job */
+	u64 secondary_preempt_buf_addr;
+	u64 reserved_0;
+};
+
+/*
+ * Inline command format.
+ * Inline commands are the commands executed at scheduler level (typically,
+ * synchronization directives). Inline command and job objects must be of
+ * the same size and have flags field at same offset.
+ */
+struct vpu_inline_cmd {
+	u64 reserved_0;
+	/* Inline command type, see VPU_INLINE_CMD_TYPE_* defines. */
+	u32 type;
+	/* Flags bit field, see VPU_JOB_FLAGS_* above. */
+	u32 flags;
+	/* Inline command payload. Depends on inline command type. */
+	union {
+		/* Fence (wait and signal) commands' payload. */
+		struct {
+			/* Fence object handle. */
+			u64 fence_handle;
+			/* User VA of the current fence value. */
+			u64 current_value_va;
+			/* User VA of the monitored fence value (read-only). */
+			u64 monitored_value_va;
+			/* Value to wait for or write in fence location. */
+			u64 value;
+			/* User VA of the log buffer in which to add log entry on completion. */
+			u64 log_buffer_va;
+			/* NPU private data. */
+			u64 npu_private_data;
+		} fence;
+		/* Other commands do not have a payload. */
+		/* Payload definition for future inline commands can be inserted here. */
+		u64 reserved_1[6];
+	} payload;
+};
+
+/*
+ * Job queue slots can be populated either with job objects or inline command objects.
+ */
+union vpu_jobq_slot {
+	struct vpu_job_queue_entry job;
+	struct vpu_inline_cmd inline_cmd;
 };
 
 /*
@@ -129,7 +300,21 @@ struct vpu_job_queue_header {
 	u32 engine_idx;
 	u32 head;
 	u32 tail;
-	u8 reserved_0[VPU_JOB_QUEUE_RESERVED_BYTES];
+	u32 flags;
+	/* Set to 1 to indicate priority_band field is valid */
+	u32 priority_band_valid;
+	/*
+	 * Priority for the work of this job queue, valid only if the HWS is NOT used
+	 * and the `priority_band_valid` is set to 1. It is applied only during
+	 * the VPU_JSM_MSG_REGISTER_DB message processing.
+	 * The device firmware might use the `priority_band` to optimize the power
+	 * management logic, but it will not affect the order of jobs.
+	 * Available priority bands: @see enum vpu_job_scheduling_priority_band
+	 */
+	u32 priority_band;
+	/* Inside realtime band assigns a further priority, limited to 0..31 range */
+	u32 realtime_priority_level;
+	u32 reserved_0[9];
 };
 
 /*
@@ -137,7 +322,7 @@ struct vpu_job_queue_header {
  */
 struct vpu_job_queue {
 	struct vpu_job_queue_header header;
-	struct vpu_job_queue_entry job[];
+	union vpu_jobq_slot slot[];
 };
 
 /**
@@ -153,13 +338,117 @@ enum vpu_trace_entity_type {
 };
 
 /*
+ * HWS specific log buffer header details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_header {
+	/* Written by VPU after adding a log entry. Initialised by host to 0. */
+	u32 first_free_entry_index;
+	/* Incremented by VPU every time the VPU writes the 0th entry; initialised by host to 0. */
+	u32 wraparound_count;
+	/*
+	 * This is the number of buffers that can be stored in the log buffer provided by the host.
+	 * It is written by host before passing buffer to VPU. VPU should consider it read-only.
+	 */
+	u64 num_of_entries;
+	u64 reserved[2];
+};
+
+/*
+ * HWS specific log buffer entry details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_entry {
+	/* VPU timestamp must be an invariant timer tick (not impacted by DVFS) */
+	u64 vpu_timestamp;
+	/*
+	 * Operation type:
+	 *     0 - context state change
+	 *     1 - queue new work
+	 *     2 - queue unwait sync object
+	 *     3 - queue no more work
+	 *     4 - queue wait sync object
+	 */
+	u32 operation_type;
+	u32 reserved;
+	/* Operation data depends on operation type */
+	u64 operation_data[2];
+};
+
+/* Native fence log buffer types. */
+enum vpu_hws_native_fence_log_type {
+	VPU_HWS_NATIVE_FENCE_LOG_TYPE_WAITS = 1,
+	VPU_HWS_NATIVE_FENCE_LOG_TYPE_SIGNALS = 2
+};
+
+/* HWS native fence log buffer header. */
+struct vpu_hws_native_fence_log_header {
+	union {
+		struct {
+			/* Index of the first free entry in buffer. */
+			u32 first_free_entry_idx;
+			/* Incremented each time NPU wraps around the buffer to write next entry. */
+			u32 wraparound_count;
+		};
+		/* Field allowing atomic update of both fields above. */
+		u64 atomic_wraparound_and_entry_idx;
+	};
+	/* Log buffer type, see enum vpu_hws_native_fence_log_type. */
+	u64 type;
+	/* Allocated number of entries in the log buffer. */
+	u64 entry_nb;
+	u64 reserved[2];
+};
+
+/* Native fence log operation types. */
+enum vpu_hws_native_fence_log_op {
+	VPU_HWS_NATIVE_FENCE_LOG_OP_SIGNAL_EXECUTED = 0,
+	VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED = 1
+};
+
+/* HWS native fence log entry. */
+struct vpu_hws_native_fence_log_entry {
+	/* Newly signaled/unblocked fence value. */
+	u64 fence_value;
+	/* Native fence object handle to which this operation belongs. */
+	u64 fence_handle;
+	/* Operation type, see enum vpu_hws_native_fence_log_op. */
+	u64 op_type;
+	u64 reserved_0;
+	/*
+	 * VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED only: Timestamp at which fence
+	 * wait was started (in NPU SysTime).
+	 */
+	u64 fence_wait_start_ts;
+	u64 reserved_1;
+	/* Timestamp at which fence operation was completed (in NPU SysTime). */
+	u64 fence_end_ts;
+};
+
+/* Native fence log buffer. */
+struct vpu_hws_native_fence_log_buffer {
+	struct vpu_hws_native_fence_log_header header;
+	struct vpu_hws_native_fence_log_entry entry[];
+};
+
+/*
  * Host <-> VPU IPC messages types.
  */
 enum vpu_ipc_msg_type {
 	VPU_JSM_MSG_UNKNOWN = 0xFFFFFFFF,
+
 	/* IPC Host -> Device, Async commands */
 	VPU_JSM_MSG_ASYNC_CMD = 0x1100,
 	VPU_JSM_MSG_ENGINE_RESET = VPU_JSM_MSG_ASYNC_CMD,
+	/**
+	 * Preempt engine. The NPU stops (preempts) all the jobs currently
+	 * executing on the target engine making the engine become idle and ready to
+	 * execute new jobs.
+	 * NOTE: The NPU does not remove unstarted jobs (if any) from job queues of
+	 * the target engine, but it stops processing them (until the queue doorbell
+	 * is rung again); the host is responsible to reset the job queue, either
+	 * after preemption or when resubmitting jobs to the queue.
+	 */
 	VPU_JSM_MSG_ENGINE_PREEMPT = 0x1101,
 	VPU_JSM_MSG_REGISTER_DB = 0x1102,
 	VPU_JSM_MSG_UNREGISTER_DB = 0x1103,
@@ -228,16 +517,42 @@ enum vpu_ipc_msg_type {
 	 * deallocated or reassigned to another context.
 	 */
 	VPU_JSM_MSG_HWS_REGISTER_DB = 0x1117,
+	/** Control command: Log buffer setting */
+	VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG = 0x1118,
+	/* Control command: Suspend command queue. */
+	VPU_JSM_MSG_HWS_SUSPEND_CMDQ = 0x1119,
+	/* Control command: Resume command queue */
+	VPU_JSM_MSG_HWS_RESUME_CMDQ = 0x111a,
+	/* Control command: Resume engine after reset */
+	VPU_JSM_MSG_HWS_ENGINE_RESUME = 0x111b,
+	/* Control command: Enable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_ENABLE = 0x111c,
+	/* Control command: Disable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_DISABLE = 0x111d,
+	/**
+	 * Dump VPU state. To be used for debug purposes only.
+	 * NOTE: Please introduce new ASYNC commands before this one. *
+	 */
+	VPU_JSM_MSG_STATE_DUMP = 0x11FF,
+
 	/* IPC Host -> Device, General commands */
 	VPU_JSM_MSG_GENERAL_CMD = 0x1200,
-	VPU_JSM_MSG_BLOB_DEINIT = VPU_JSM_MSG_GENERAL_CMD,
+	VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED = VPU_JSM_MSG_GENERAL_CMD,
 	/**
 	 * Control dyndbg behavior by executing a dyndbg command; equivalent to
 	 * Linux command: `echo '<dyndbg_cmd>' > <debugfs>/dynamic_debug/control`.
 	 */
 	VPU_JSM_MSG_DYNDBG_CONTROL = 0x1201,
+	/**
+	 * Perform the save procedure for the D0i3 entry
+	 */
+	VPU_JSM_MSG_PWR_D0I3_ENTER = 0x1202,
+
 	/* IPC Device -> Host, Job completion */
 	VPU_JSM_MSG_JOB_DONE = 0x2100,
+	/* IPC Device -> Host, Fence signalled */
+	VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED = 0x2101,
+
 	/* IPC Device -> Host, Async command completion */
 	VPU_JSM_MSG_ASYNC_CMD_DONE = 0x2200,
 	VPU_JSM_MSG_ENGINE_RESET_DONE = VPU_JSM_MSG_ASYNC_CMD_DONE,
@@ -304,11 +619,36 @@ enum vpu_ipc_msg_type {
 	VPU_JSM_MSG_DESTROY_CMD_QUEUE_RSP = 0x2216,
 	/** Response to control command: Set context scheduling properties */
 	VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP = 0x2217,
+	/** Response to control command: Log buffer setting */
+	VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP = 0x2218,
+	/* IPC Device -> Host, HWS notify index entry of log buffer written */
+	VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION = 0x2219,
+	/* IPC Device -> Host, HWS completion of a context suspend request */
+	VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE = 0x221a,
+	/* Response to control command: Resume command queue */
+	VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP = 0x221b,
+	/* Response to control command: Resume engine command response */
+	VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE = 0x221c,
+	/* Response to control command: Enable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_ENABLE_DONE = 0x221d,
+	/* Response to control command: Disable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_DISABLE_DONE = 0x221e,
+	/**
+	 * Response to state dump control command.
+	 * NOTE: Please introduce new ASYNC responses before this one. *
+	 */
+	VPU_JSM_MSG_STATE_DUMP_RSP = 0x22FF,
+
 	/* IPC Device -> Host, General command completion */
 	VPU_JSM_MSG_GENERAL_CMD_DONE = 0x2300,
 	VPU_JSM_MSG_BLOB_DEINIT_DONE = VPU_JSM_MSG_GENERAL_CMD_DONE,
 	/** Response to VPU_JSM_MSG_DYNDBG_CONTROL. */
 	VPU_JSM_MSG_DYNDBG_CONTROL_RSP = 0x2301,
+	/**
+	 * Acknowledgment of completion of the save procedure initiated by
+	 * VPU_JSM_MSG_PWR_D0I3_ENTER
+	 */
+	VPU_JSM_MSG_PWR_D0I3_ENTER_DONE = 0x2302,
 };
 
 enum vpu_ipc_msg_status { VPU_JSM_MSG_FREE, VPU_JSM_MSG_ALLOCATED };
@@ -454,12 +794,22 @@ struct vpu_jsm_metric_streamer_update {
 	/** Metric group mask that identifies metric streamer instance. */
 	u64 metric_group_mask;
 	/**
-	 * Address and size of the buffer where the VPU will write metric data. If
-	 * the buffer address is 0 or same as the currently used buffer the VPU will
-	 * continue writing metric data to the current buffer. In this case the
-	 * buffer size is ignored and the size of the current buffer is unchanged.
-	 * If the address is non-zero and differs from the current buffer address the
-	 * VPU will immediately switch data collection to the new buffer.
+	 * Address and size of the buffer where the VPU will write metric data.
+	 * This member dictates how the update operation should perform:
+	 * 1. client needs information about the number of collected samples and the
+	 *   amount of data written to the current buffer
+	 * 2. client wants to switch to a new buffer
+	 *
+	 * Case 1. is identified by the buffer address being 0 or the same as the
+	 * currently used buffer address. In this case the buffer size is ignored and
+	 * the size of the current buffer is unchanged. The VPU will return an update
+	 * in the vpu_jsm_metric_streamer_done structure. The internal writing position
+	 * into the buffer is not changed.
+	 *
+	 * Case 2. is identified by the address being non-zero and differs from the
+	 * current buffer address. The VPU will immediately switch data collection to
+	 * the new buffer. Then the VPU will return an update in the
+	 * vpu_jsm_metric_streamer_done structure.
 	 */
 	u64 buffer_addr;
 	u64 buffer_size;
@@ -477,11 +827,6 @@ struct vpu_jsm_metric_streamer_update {
 	u64 next_buffer_size;
 };
 
-struct vpu_ipc_msg_payload_blob_deinit {
-	/* 64-bit unique ID for the blob to be de-initialized. */
-	u64 blob_id;
-};
-
 struct vpu_ipc_msg_payload_job_done {
 	/* Engine to which the job was submitted. */
 	u32 engine_idx;
@@ -499,6 +844,21 @@ struct vpu_ipc_msg_payload_job_done {
 	u64 cmdq_id;
 };
 
+/*
+ * Notification message upon native fence signalling.
+ * @see VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED
+ */
+struct vpu_ipc_msg_payload_native_fence_signalled {
+	/* Engine ID. */
+	u32 engine_idx;
+	/* Host SSID. */
+	u32 host_ssid;
+	/* CMDQ ID */
+	u64 cmdq_id;
+	/* Fence object handle. */
+	u64 fence_handle;
+};
+
 struct vpu_jsm_engine_reset_context {
 	/* Host SSID */
 	u32 host_ssid;
@@ -506,7 +866,7 @@ struct vpu_jsm_engine_reset_context {
 	u32 reserved_0;
 	/* Command queue id */
 	u64 cmdq_id;
-	/* Flags: 0: cause of hang; 1: collateral damage of reset */
+	/* See VPU_ENGINE_RESET_CONTEXT_* defines */
 	u64 flags;
 };
 
@@ -577,11 +937,6 @@ struct vpu_ipc_msg_payload_get_power_level_count_done {
 	u8 power_limit[16];
 };
 
-struct vpu_ipc_msg_payload_blob_deinit_done {
-	/* 64-bit unique ID for the blob de-initialized. */
-	u64 blob_id;
-};
-
 /* HWS priority band setup request / response */
 struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	/*
@@ -592,48 +947,66 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	/*
 	 * Default quantum in 100ns units for scheduling across processes
 	 * within a priority band
+	 * Minimum value supported by NPU is 1ms (10000 in 100ns units).
 	 */
-	u64 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+	u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
 	 * Default grace period in 100ns units for processes that preempt each
 	 * other within a priority band
 	 */
-	u64 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+	u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
 	 * For normal priority band, specifies the target VPU percentage
 	 * in situations when it's starved by the focus band.
 	 */
 	u32 normal_band_percentage;
-	/* Reserved */
-	u32 reserved_0;
+	/*
+	 * TDR timeout value in milliseconds. Default value of 0 meaning no timeout.
+	 */
+	u32 tdr_timeout;
 };
 
-/* HWS create command queue request */
+/*
+ * @brief HWS create command queue request.
+ * Host will create a command queue via this command.
+ * Note: Cmdq group is a handle of an object which
+ * may contain one or more command queues.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
 struct vpu_ipc_msg_payload_hws_create_cmdq {
 	/* Process id */
 	u64 process_id;
 	/* Host SSID */
 	u32 host_ssid;
-	/* Zero Padding */
-	u32 reserved;
+	/* Engine for which queue is being created */
+	u32 engine_idx;
+	/* Cmdq group: only used for HWS logging of state changes */
+	u64 cmdq_group;
 	/* Command queue id */
 	u64 cmdq_id;
 	/* Command queue base */
 	u64 cmdq_base;
 	/* Command queue size */
 	u32 cmdq_size;
-	/* Reserved */
+	/* Zero padding */
 	u32 reserved_0;
 };
 
-/* HWS create command queue response */
+/*
+ * @brief HWS create command queue response.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
 struct vpu_ipc_msg_payload_hws_create_cmdq_rsp {
 	/* Process id */
 	u64 process_id;
 	/* Host SSID */
 	u32 host_ssid;
-	/* Zero Padding */
-	u32 reserved;
+	/* Engine for which queue is being created */
+	u32 engine_idx;
+	/* Command queue group */
+	u64 cmdq_group;
 	/* Command queue id */
 	u64 cmdq_id;
 };
@@ -656,15 +1029,21 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
 	u32 reserved_0;
 	/* Command queue id */
 	u64 cmdq_id;
-	/* Priority band to assign to work of this context */
+	/*
+	 * Priority band to assign to work of this context.
+	 * Available priority bands: @see enum vpu_job_scheduling_priority_band
+	 */
 	u32 priority_band;
 	/* Inside realtime band assigns a further priority */
 	u32 realtime_priority_level;
 	/* Priority relative to other contexts in the same process */
-	u32 in_process_priority;
+	s32 in_process_priority;
 	/* Zero padding / Reserved */
 	u32 reserved_1;
-	/* Context quantum relative to other contexts of same priority in the same process */
+	/*
+	 * Context quantum relative to other contexts of same priority in the same process
+	 * Minimum value supported by NPU is 1ms (10000 in 100ns units).
+	 */
 	u64 context_quantum;
 	/* Grace period when preempting context of the same priority within the same process */
 	u64 grace_period_same_priority;
@@ -694,6 +1073,129 @@ struct vpu_jsm_hws_register_db {
 	u64 cmdq_size;
 };
 
+/*
+ * @brief Structure to set another buffer to be used for scheduling-related logging.
+ * The size of the logging buffer and the number of entries is defined as part of the
+ * buffer itself as described next.
+ * The log buffer received from the host is made up of;
+ *   - header:     32 bytes in size, as shown in 'struct vpu_hws_log_buffer_header'.
+ *                 The header contains the number of log entries in the buffer.
+ *   - log entry:  0 to n-1, each log entry is 32 bytes in size, as shown in
+ *                 'struct vpu_hws_log_buffer_entry'.
+ *                 The entry contains the VPU timestamp, operation type and data.
+ * The host should provide the notify index value of log buffer to VPU. This is a
+ * value defined within the log buffer and when written to will generate the
+ * scheduling log notification.
+ * The host should set engine_idx and vpu_log_buffer_va to 0 to disable logging
+ * for a particular engine.
+ * VPU will handle one log buffer for each of supported engines.
+ * VPU should allow the logging to consume one host_ssid.
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ */
+struct vpu_ipc_msg_payload_hws_set_scheduling_log {
+	/* Engine ordinal */
+	u32 engine_idx;
+	/* Host SSID */
+	u32 host_ssid;
+	/*
+	 * VPU log buffer virtual address.
+	 * Set to 0 to disable logging for this engine.
+	 */
+	u64 vpu_log_buffer_va;
+	/*
+	 * Notify index of log buffer. VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+	 * is generated when an event log is written to this index.
+	 */
+	u64 notify_index;
+	/*
+	 * Field is now deprecated, will be removed when KMD is updated to support removal
+	 */
+	u32 enable_extra_events;
+	/* Zero Padding */
+	u32 reserved_0;
+};
+
+/*
+ * @brief The scheduling log notification is generated by VPU when it writes
+ * an event into the log buffer at the notify_index. VPU notifies host with
+ * VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION. This is an asynchronous
+ * message from VPU to host.
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ */
+struct vpu_ipc_msg_payload_hws_scheduling_log_notification {
+	/* Engine ordinal */
+	u32 engine_idx;
+	/* Zero Padding */
+	u32 reserved_0;
+};
+
+/*
+ * @brief HWS suspend command queue request and done structure.
+ * Host will request the suspend of contexts and VPU will;
+ *   - Suspend all work on this context
+ *   - Preempt any running work
+ *   - Asynchronously perform the above and return success immediately once
+ *     all items above are started successfully
+ *   - Notify the host of completion of these operations via
+ *     VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ *   - Reject any other context operations on a context with an in-flight
+ *     suspend request running
+ * Same structure used when VPU notifies host of completion of a context suspend
+ * request. The ids and suspend fence value reported in this command will match
+ * the one in the request from the host to suspend the context. Once suspend is
+ * complete, VPU will not access any data relating to this command queue until
+ * it is resumed.
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ */
+struct vpu_ipc_msg_payload_hws_suspend_cmdq {
+	/* Host SSID */
+	u32 host_ssid;
+	/* Zero Padding */
+	u32 reserved_0;
+	/* Command queue id */
+	u64 cmdq_id;
+	/*
+	 * Suspend fence value - reported by the VPU suspend context
+	 * completed once suspend is complete.
+	 */
+	u64 suspend_fence_value;
+};
+
+/*
+ * @brief HWS Resume command queue request / response structure.
+ * Host will request the resume of a context;
+ *  - VPU will resume all work on this context
+ *  - Scheduler will allow this context to be scheduled
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP
+ */
+struct vpu_ipc_msg_payload_hws_resume_cmdq {
+	/* Host SSID */
+	u32 host_ssid;
+	/* Zero Padding */
+	u32 reserved_0;
+	/* Command queue id */
+	u64 cmdq_id;
+};
+
+/*
+ * @brief HWS Resume engine request / response structure.
+ * After a HWS engine reset, all scheduling is stopped on VPU until a engine resume.
+ * Host shall send this command to resume scheduling of any valid queue.
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE
+ */
+struct vpu_ipc_msg_payload_hws_resume_engine {
+	/* Engine to be resumed */
+	u32 engine_idx;
+	/* Reserved */
+	u32 reserved_0;
+};
+
 /**
  * Payload for VPU_JSM_MSG_TRACE_SET_CONFIG[_RSP] and
  * VPU_JSM_MSG_TRACE_GET_CONFIG_RSP messages.
@@ -938,6 +1440,35 @@ struct vpu_ipc_msg_payload_dyndbg_control {
 	char dyndbg_cmd[VPU_DYNDBG_CMD_MAX_LEN];
 };
 
+/**
+ * Payload for VPU_JSM_MSG_PWR_D0I3_ENTER
+ *
+ * This is a bi-directional payload.
+ */
+struct vpu_ipc_msg_payload_pwr_d0i3_enter {
+	/**
+	 * 0: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is not sent to the host driver
+	 *    The driver will poll for D0i2 Idle state transitions.
+	 * 1: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is sent after VPU state save is complete
+	 */
+	u32 send_response;
+	u32 reserved_0;
+};
+
+/**
+ * Payload for VPU_JSM_MSG_DCT_ENABLE message.
+ *
+ * Default values for DCT active/inactive times are 5.3ms and 30ms respectively,
+ * corresponding to a 85% duty cycle. This payload allows the host to tune these
+ * values according to application requirements.
+ */
+struct vpu_ipc_msg_payload_pwr_dct_control {
+	/** Duty cycle active time in microseconds */
+	u32 dct_active_us;
+	/** Duty cycle inactive time in microseconds */
+	u32 dct_inactive_us;
+};
+
 /*
  * Payloads union, used to define complete message format.
  */
@@ -951,10 +1482,10 @@ union vpu_ipc_msg_payload {
 	struct vpu_jsm_metric_streamer_start metric_streamer_start;
 	struct vpu_jsm_metric_streamer_stop metric_streamer_stop;
 	struct vpu_jsm_metric_streamer_update metric_streamer_update;
-	struct vpu_ipc_msg_payload_blob_deinit blob_deinit;
 	struct vpu_ipc_msg_payload_ssid_release ssid_release;
 	struct vpu_jsm_hws_register_db hws_register_db;
 	struct vpu_ipc_msg_payload_job_done job_done;
+	struct vpu_ipc_msg_payload_native_fence_signalled native_fence_signalled;
 	struct vpu_ipc_msg_payload_engine_reset_done engine_reset_done;
 	struct vpu_ipc_msg_payload_engine_preempt_done engine_preempt_done;
 	struct vpu_ipc_msg_payload_register_db_done register_db_done;
@@ -962,7 +1493,6 @@ union vpu_ipc_msg_payload {
 	struct vpu_ipc_msg_payload_query_engine_hb_done query_engine_hb_done;
 	struct vpu_ipc_msg_payload_get_power_level_count_done get_power_level_count_done;
 	struct vpu_jsm_metric_streamer_done metric_streamer_done;
-	struct vpu_ipc_msg_payload_blob_deinit_done blob_deinit_done;
 	struct vpu_ipc_msg_payload_trace_config trace_config;
 	struct vpu_ipc_msg_payload_trace_capability_rsp trace_capability;
 	struct vpu_ipc_msg_payload_trace_get_name trace_get_name;
@@ -974,6 +1504,13 @@ union vpu_ipc_msg_payload {
 	struct vpu_ipc_msg_payload_hws_destroy_cmdq hws_destroy_cmdq;
 	struct vpu_ipc_msg_payload_hws_set_context_sched_properties
 		hws_set_context_sched_properties;
+	struct vpu_ipc_msg_payload_hws_set_scheduling_log hws_set_scheduling_log;
+	struct vpu_ipc_msg_payload_hws_scheduling_log_notification hws_scheduling_log_notification;
+	struct vpu_ipc_msg_payload_hws_suspend_cmdq hws_suspend_cmdq;
+	struct vpu_ipc_msg_payload_hws_resume_cmdq hws_resume_cmdq;
+	struct vpu_ipc_msg_payload_hws_resume_engine hws_resume_engine;
+	struct vpu_ipc_msg_payload_pwr_d0i3_enter pwr_d0i3_enter;
+	struct vpu_ipc_msg_payload_pwr_dct_control pwr_dct_control;
 };
 
 /*
diff --git a/drivers/accel/qaic/Kconfig b/drivers/accel/qaic/Kconfig
index a9f866230058..5e405a19c157 100644
--- a/drivers/accel/qaic/Kconfig
+++ b/drivers/accel/qaic/Kconfig
@@ -8,7 +8,6 @@ config DRM_ACCEL_QAIC
 	depends on DRM_ACCEL
 	depends on PCI && HAS_IOMEM
 	depends on MHI_BUS
-	depends on MMU
 	select CRC32
 	help
 	  Enables driver for Qualcomm's Cloud AI accelerator PCIe cards that are
diff --git a/drivers/accel/qaic/Makefile b/drivers/accel/qaic/Makefile
index 2418418f7a50..1106b876f737 100644
--- a/drivers/accel/qaic/Makefile
+++ b/drivers/accel/qaic/Makefile
@@ -9,4 +9,9 @@ qaic-y := \
 	mhi_controller.o \
 	qaic_control.o \
 	qaic_data.o \
-	qaic_drv.o
+	qaic_drv.o \
+	qaic_ras.o \
+	qaic_timesync.o \
+	sahara.o
+
+qaic-$(CONFIG_DEBUG_FS) += qaic_debugfs.o
diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 5036e58e7235..13a14c6c6168 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -20,7 +20,12 @@ static unsigned int mhi_timeout_ms = 2000; /* 2 sec default */
 module_param(mhi_timeout_ms, uint, 0600);
 MODULE_PARM_DESC(mhi_timeout_ms, "MHI controller timeout value");
 
-static struct mhi_channel_config aic100_channels[] = {
+static const char *fw_image_paths[FAMILY_MAX] = {
+	[FAMILY_AIC100] = "qcom/aic100/sbl.bin",
+	[FAMILY_AIC200] = "qcom/aic200/sbl.bin",
+};
+
+static const struct mhi_channel_config aic100_channels[] = {
 	{
 		.name = "QAIC_LOOPBACK",
 		.num = 0,
@@ -348,7 +353,7 @@ static struct mhi_channel_config aic100_channels[] = {
 		.local_elements = 0,
 		.event_ring = 0,
 		.dir = DMA_TO_DEVICE,
-		.ee_mask = MHI_CH_EE_SBL | MHI_CH_EE_AMSS,
+		.ee_mask = MHI_CH_EE_SBL,
 		.pollcfg = 0,
 		.doorbell = MHI_DB_BRST_DISABLE,
 		.lpm_notify = false,
@@ -358,13 +363,272 @@ static struct mhi_channel_config aic100_channels[] = {
 		.wake_capable = false,
 	},
 	{
-		.num = 21,
 		.name = "QAIC_TIMESYNC",
+		.num = 21,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_SBL,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num = 22,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num = 23,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "IPCR",
+		.num = 24,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "IPCR",
+		.num = 25,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = true,
+		.wake_capable = false,
+	},
+};
+
+static const struct mhi_channel_config aic200_channels[] = {
+	{
+		.name = "QAIC_LOOPBACK",
+		.num = 0,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_LOOPBACK",
+		.num = 1,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_SAHARA",
+		.num = 2,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_SBL,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_SAHARA",
+		.num = 3,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_SBL,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_SSR",
+		.num = 6,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_SSR",
+		.num = 7,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_CONTROL",
+		.num = 10,
+		.num_elements = 128,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_CONTROL",
+		.num = 11,
+		.num_elements = 128,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_LOGGING",
+		.num = 12,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_SBL,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_LOGGING",
+		.num = 13,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_SBL,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_STATUS",
+		.num = 14,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_STATUS",
+		.num = 15,
 		.num_elements = 32,
 		.local_elements = 0,
 		.event_ring = 0,
 		.dir = DMA_FROM_DEVICE,
-		.ee_mask = MHI_CH_EE_SBL | MHI_CH_EE_AMSS,
+		.ee_mask = MHI_CH_EE_AMSS,
 		.pollcfg = 0,
 		.doorbell = MHI_DB_BRST_DISABLE,
 		.lpm_notify = false,
@@ -373,6 +637,102 @@ static struct mhi_channel_config aic100_channels[] = {
 		.auto_queue = false,
 		.wake_capable = false,
 	},
+	{
+		.name = "QAIC_TELEMETRY",
+		.num = 16,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_TELEMETRY",
+		.num = 17,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num = 22,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num = 23,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "IPCR",
+		.num = 24,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.name = "IPCR",
+		.num = 25,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = true,
+		.wake_capable = false,
+	},
 };
 
 static struct mhi_event_config aic100_events[] = {
@@ -390,22 +750,63 @@ static struct mhi_event_config aic100_events[] = {
 	},
 };
 
-static struct mhi_controller_config aic100_config = {
-	.max_channels = 128,
-	.timeout_ms = 0, /* controlled by mhi_timeout */
-	.buf_len = 0,
-	.num_channels = ARRAY_SIZE(aic100_channels),
-	.ch_cfg = aic100_channels,
-	.num_events = ARRAY_SIZE(aic100_events),
-	.event_cfg = aic100_events,
-	.use_bounce_buf = false,
-	.m2_no_db = false,
+static struct mhi_event_config aic200_events[] = {
+	{
+		.num_elements = 32,
+		.irq_moderation_ms = 0,
+		.irq = 0,
+		.channel = U32_MAX,
+		.priority = 1,
+		.mode = MHI_DB_BRST_DISABLE,
+		.data_type = MHI_ER_CTRL,
+		.hardware_event = false,
+		.client_managed = false,
+		.offload_channel = false,
+	},
+};
+
+static struct mhi_controller_config mhi_cntrl_configs[] = {
+	[FAMILY_AIC100] = {
+		.max_channels = 128,
+		.timeout_ms = 0, /* controlled by mhi_timeout */
+		.buf_len = 0,
+		.num_channels = ARRAY_SIZE(aic100_channels),
+		.ch_cfg = aic100_channels,
+		.num_events = ARRAY_SIZE(aic100_events),
+		.event_cfg = aic100_events,
+		.use_bounce_buf = false,
+		.m2_no_db = false,
+	},
+	[FAMILY_AIC200] = {
+		.max_channels = 128,
+		.timeout_ms = 0, /* controlled by mhi_timeout */
+		.buf_len = 0,
+		.num_channels = ARRAY_SIZE(aic200_channels),
+		.ch_cfg = aic200_channels,
+		.num_events = ARRAY_SIZE(aic200_events),
+		.event_cfg = aic200_events,
+		.use_bounce_buf = false,
+		.m2_no_db = false,
+	},
 };
 
 static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out)
 {
-	u32 tmp = readl_relaxed(addr);
+	u32 tmp;
 
+	/*
+	 * SOC_HW_VERSION quirk
+	 * The SOC_HW_VERSION register (offset 0x224) is not reliable and
+	 * may contain uninitialized values, including 0xFFFFFFFF. This could
+	 * cause a false positive link down error.  Instead, intercept any
+	 * reads and provide the correct value of the register.
+	 */
+	if (addr - mhi_cntrl->regs == 0x224) {
+		*out = 0x60110200;
+		return 0;
+	}
+
+	tmp = readl_relaxed(addr);
 	if (tmp == U32_MAX)
 		return -EIO;
 
@@ -437,7 +838,7 @@ static void mhi_status_cb(struct mhi_controller *mhi_cntrl, enum mhi_callback re
 		pci_err(qdev->pdev, "Fatal error received from device. Attempting to recover\n");
 	/* this event occurs in non-atomic context */
 	if (reason == MHI_CB_SYS_ERROR)
-		qaic_dev_reset_clean_local_state(qdev, true);
+		qaic_dev_reset_clean_local_state(qdev);
 }
 
 static int mhi_reset_and_async_power_up(struct mhi_controller *mhi_cntrl)
@@ -468,8 +869,9 @@ static int mhi_reset_and_async_power_up(struct mhi_controller *mhi_cntrl)
 }
 
 struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar,
-						    int mhi_irq)
+						    int mhi_irq, bool shared_msi, int family)
 {
+	struct mhi_controller_config mhi_config = mhi_cntrl_configs[family];
 	struct mhi_controller *mhi_cntrl;
 	int ret;
 
@@ -500,11 +902,22 @@ struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, voi
 		return ERR_PTR(-ENOMEM);
 
 	mhi_cntrl->irq[0] = mhi_irq;
-	mhi_cntrl->fw_image = "qcom/aic100/sbl.bin";
+
+	if (shared_msi) /* MSI shared with data path, no IRQF_NO_SUSPEND */
+		mhi_cntrl->irq_flags = IRQF_SHARED;
+
+	mhi_cntrl->fw_image = fw_image_paths[family];
+
+	if (family == FAMILY_AIC200) {
+		mhi_cntrl->name = "AIC200";
+		mhi_cntrl->seg_len = SZ_512K;
+	} else {
+		mhi_cntrl->name = "AIC100";
+	}
 
 	/* use latest configured timeout */
-	aic100_config.timeout_ms = mhi_timeout_ms;
-	ret = mhi_register_controller(mhi_cntrl, &aic100_config);
+	mhi_config.timeout_ms = mhi_timeout_ms;
+	ret = mhi_register_controller(mhi_cntrl, &mhi_config);
 	if (ret) {
 		pci_err(pci_dev, "mhi_register_controller failed %d\n", ret);
 		return ERR_PTR(ret);
diff --git a/drivers/accel/qaic/mhi_controller.h b/drivers/accel/qaic/mhi_controller.h
index 2ae45d768e24..8939f6ae185e 100644
--- a/drivers/accel/qaic/mhi_controller.h
+++ b/drivers/accel/qaic/mhi_controller.h
@@ -8,7 +8,7 @@
 #define MHICONTROLLERQAIC_H_
 
 struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar,
-						    int mhi_irq);
+						    int mhi_irq, bool shared_msi, int family);
 void qaic_mhi_free_controller(struct mhi_controller *mhi_cntrl, bool link_up);
 void qaic_mhi_start_reset(struct mhi_controller *mhi_cntrl);
 void qaic_mhi_reset_done(struct mhi_controller *mhi_cntrl);
diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index e3f4c30f3ffd..c31081e42cee 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -30,6 +30,22 @@
 #define to_qaic_drm_device(dev) container_of(dev, struct qaic_drm_device, drm)
 #define to_drm(qddev) (&(qddev)->drm)
 #define to_accel_kdev(qddev) (to_drm(qddev)->accel->kdev) /* Return Linux device of accel node */
+#define to_qaic_device(dev) (to_qaic_drm_device((dev))->qdev)
+
+enum aic_families {
+	FAMILY_AIC100,
+	FAMILY_AIC200,
+	FAMILY_MAX,
+};
+
+enum __packed dev_states {
+	/* Device is offline or will be very soon */
+	QAIC_OFFLINE,
+	/* Device is booting, not clear if it's in a usable state */
+	QAIC_BOOT,
+	/* Device is fully operational */
+	QAIC_ONLINE,
+};
 
 extern bool datapath_polling;
 
@@ -103,10 +119,10 @@ struct qaic_device {
 	struct pci_dev		*pdev;
 	/* Req. ID of request that will be queued next in MHI control device */
 	u32			next_seq_num;
-	/* Base address of bar 0 */
-	void __iomem		*bar_0;
-	/* Base address of bar 2 */
-	void __iomem		*bar_2;
+	/* Base address of the MHI bar */
+	void __iomem		*bar_mhi;
+	/* Base address of the DBCs bar */
+	void __iomem		*bar_dbc;
 	/* Controller structure for MHI devices */
 	struct mhi_controller	*mhi_cntrl;
 	/* MHI control channel device */
@@ -121,8 +137,10 @@ struct qaic_device {
 	struct workqueue_struct	*cntl_wq;
 	/* Synchronizes all the users of device during cleanup */
 	struct srcu_struct	dev_lock;
-	/* true: Device under reset; false: Device not under reset */
-	bool			in_reset;
+	/* Track the state of the device during resets */
+	enum dev_states		dev_state;
+	/* true: single MSI is used to operate device */
+	bool			single_msi;
 	/*
 	 * true: A tx MHI transaction has failed and a rx buffer is still queued
 	 * in control device. Such a buffer is considered lost rx buffer
@@ -137,6 +155,26 @@ struct qaic_device {
 	u32 (*gen_crc)(void *msg);
 	/* Validate the CRC of a control message */
 	bool (*valid_crc)(void *msg);
+	/* MHI "QAIC_TIMESYNC" channel device */
+	struct mhi_device	*qts_ch;
+	/* Work queue for tasks related to MHI "QAIC_TIMESYNC" channel */
+	struct workqueue_struct	*qts_wq;
+	/* Head of list of page allocated by MHI bootlog device */
+	struct list_head        bootlog;
+	/* MHI bootlog channel device */
+	struct mhi_device       *bootlog_ch;
+	/* Work queue for tasks related to MHI bootlog device */
+	struct workqueue_struct *bootlog_wq;
+	/* Synchronizes access of pages in MHI bootlog device */
+	struct mutex            bootlog_mutex;
+	/* MHI RAS channel device */
+	struct mhi_device	*ras_ch;
+	/* Correctable error count */
+	unsigned int		ce_count;
+	/* Un-correctable error count */
+	unsigned int		ue_count;
+	/* Un-correctable non-fatal error count */
+	unsigned int		ue_nf_count;
 };
 
 struct qaic_drm_device {
@@ -176,8 +214,6 @@ struct qaic_bo {
 	u32			nr_slice;
 	/* Number of slice that have been transferred by DMA engine */
 	u32			nr_slice_xfer_done;
-	/* true = BO is queued for execution, true = BO is not queued */
-	bool			queued;
 	/*
 	 * If true then user has attached slicing information to this BO by
 	 * calling DRM_IOCTL_QAIC_ATTACH_SLICE_BO ioctl.
@@ -185,8 +221,6 @@ struct qaic_bo {
 	bool			sliced;
 	/* Request ID of this BO if it is queued for execution */
 	u16			req_id;
-	/* Handle assigned to this BO */
-	u32			handle;
 	/* Wait on this for completion of DMA transfer of this BO */
 	struct completion	xfer_done;
 	/*
@@ -266,9 +300,10 @@ int disable_dbc(struct qaic_device *qdev, u32 dbc_id, struct qaic_user *usr);
 void enable_dbc(struct qaic_device *qdev, u32 dbc_id, struct qaic_user *usr);
 void wakeup_dbc(struct qaic_device *qdev, u32 dbc_id);
 void release_dbc(struct qaic_device *qdev, u32 dbc_id);
+void qaic_data_get_fifo_info(struct dma_bridge_chan *dbc, u32 *head, u32 *tail);
 
 void wake_all_cntl(struct qaic_device *qdev);
-void qaic_dev_reset_clean_local_state(struct qaic_device *qdev, bool exit_reset);
+void qaic_dev_reset_clean_local_state(struct qaic_device *qdev);
 
 struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf);
 
diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 388abd40024b..d8bdab69f800 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -496,7 +496,7 @@ static int encode_addr_size_pairs(struct dma_xfer *xfer, struct wrapper_list *wr
 	nents = sgt->nents;
 	nents_dma = nents;
 	*size = QAIC_MANAGE_EXT_MSG_LENGTH - msg_hdr_len - sizeof(**out_trans);
-	for_each_sgtable_sg(sgt, sg, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		*size -= sizeof(*asp);
 		/* Save 1K for possible follow-up transactions. */
 		if (*size < SZ_1K) {
@@ -1022,7 +1022,8 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u
 	int xfer_count = 0;
 	int retry_count;
 
-	if (qdev->in_reset) {
+	/* Allow QAIC_BOOT state since we need to check control protocol version */
+	if (qdev->dev_state == QAIC_OFFLINE) {
 		mutex_unlock(&qdev->cntl_mutex);
 		return ERR_PTR(-ENODEV);
 	}
@@ -1138,7 +1139,7 @@ static int abort_dma_cont(struct qaic_device *qdev, struct wrapper_list *wrapper
 		if (!list_is_first(&wrapper->list, &wrappers->list))
 			kref_put(&wrapper->ref_count, free_wrapper);
 
-	wrapper = add_wrapper(wrappers, offsetof(struct wrapper_msg, trans) + sizeof(*out_trans));
+	wrapper = add_wrapper(wrappers, sizeof(*wrapper));
 
 	if (!wrapper)
 		return -ENOMEM;
@@ -1306,7 +1307,7 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_
 	qdev = usr->qddev->qdev;
 
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 		srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
 		return -ENODEV;
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 4a8e43a7a6a4..797289e9d780 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -51,6 +51,7 @@
 		})
 #define NUM_EVENTS	128
 #define NUM_DELAYS	10
+#define fifo_at(base, offset) ((base) + (offset) * get_dbc_req_elem_size())
 
 static unsigned int wait_exec_default_timeout_ms = 5000; /* 5 sec default */
 module_param(wait_exec_default_timeout_ms, uint, 0600);
@@ -140,6 +141,11 @@ struct dbc_rsp {
 	__le16	status;
 } __packed;
 
+static inline bool bo_queued(struct qaic_bo *bo)
+{
+	return !list_empty(&bo->xfer_list);
+}
+
 inline int get_dbc_req_elem_size(void)
 {
 	return sizeof(struct dbc_req);
@@ -166,9 +172,10 @@ static void free_slice(struct kref *kref)
 static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_table **sgt_out,
 					struct sg_table *sgt_in, u64 size, u64 offset)
 {
-	int total_len, len, nents, offf = 0, offl = 0;
 	struct scatterlist *sg, *sgn, *sgf, *sgl;
+	unsigned int len, nents, offf, offl;
 	struct sg_table *sgt;
+	size_t total_len;
 	int ret, j;
 
 	/* find out number of relevant nents needed for this mem */
@@ -176,9 +183,11 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl
 	sgf = NULL;
 	sgl = NULL;
 	nents = 0;
+	offf = 0;
+	offl = 0;
 
 	size = size ? size : PAGE_SIZE;
-	for (sg = sgt_in->sgl; sg; sg = sg_next(sg)) {
+	for_each_sgtable_dma_sg(sgt_in, sg, j) {
 		len = sg_dma_len(sg);
 
 		if (!len)
@@ -215,7 +224,7 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl
 
 	/* copy relevant sg node and fix page and length */
 	sgn = sgf;
-	for_each_sgtable_sg(sgt, sg, j) {
+	for_each_sgtable_dma_sg(sgt, sg, j) {
 		memcpy(sg, sgn, sizeof(*sg));
 		if (sgn == sgf) {
 			sg_dma_address(sg) += offf;
@@ -295,7 +304,7 @@ static int encode_reqs(struct qaic_device *qdev, struct bo_slice *slice,
 	 * fence.
 	 */
 	dev_addr = req->dev_addr;
-	for_each_sgtable_sg(slice->sgt, sg, i) {
+	for_each_sgtable_dma_sg(slice->sgt, sg, i) {
 		slice->reqs[i].cmd = cmd;
 		slice->reqs[i].src_addr = cpu_to_le64(slice->dir == DMA_TO_DEVICE ?
 						      sg_dma_address(sg) : dev_addr);
@@ -451,7 +460,7 @@ static int create_sgt(struct qaic_device *qdev, struct sg_table **sgt_out, u64 s
 		 * later
 		 */
 		buf_extra = (PAGE_SIZE - size % PAGE_SIZE) % PAGE_SIZE;
-		max_order = min(MAX_ORDER - 1, get_order(size));
+		max_order = min(MAX_PAGE_ORDER, get_order(size));
 	} else {
 		/* allocate a single page for book keeping */
 		nr_pages = 1;
@@ -548,6 +557,7 @@ static bool invalid_sem(struct qaic_sem *sem)
 static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_entry *slice_ent,
 			     u32 count, u64 total_size)
 {
+	u64 total;
 	int i;
 
 	for (i = 0; i < count; i++) {
@@ -557,7 +567,8 @@ static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_
 		      invalid_sem(&slice_ent[i].sem2) || invalid_sem(&slice_ent[i].sem3))
 			return -EINVAL;
 
-		if (slice_ent[i].offset + slice_ent[i].size > total_size)
+		if (check_add_overflow(slice_ent[i].offset, slice_ent[i].size, &total) ||
+		    total > total_size)
 			return -EINVAL;
 	}
 
@@ -568,6 +579,9 @@ static void qaic_free_sgt(struct sg_table *sgt)
 {
 	struct scatterlist *sg;
 
+	if (!sgt)
+		return;
+
 	for (sg = sgt->sgl; sg; sg = sg_next(sg))
 		if (sg_page(sg))
 			__free_pages(sg_page(sg), get_order(sg->length));
@@ -595,7 +609,7 @@ static int qaic_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc
 	struct scatterlist *sg;
 	int ret = 0;
 
-	if (obj->import_attach)
+	if (drm_gem_is_imported(obj))
 		return -EINVAL;
 
 	for (sg = bo->sgt->sgl; sg; sg = sg_next(sg)) {
@@ -616,7 +630,7 @@ static void qaic_free_object(struct drm_gem_object *obj)
 {
 	struct qaic_bo *bo = to_qaic_bo(obj);
 
-	if (obj->import_attach) {
+	if (drm_gem_is_imported(obj)) {
 		/* DMABUF/PRIME Path */
 		drm_prime_gem_destroy(obj, NULL);
 	} else {
@@ -647,6 +661,7 @@ static void qaic_init_bo(struct qaic_bo *bo, bool reinit)
 	}
 	complete_all(&bo->xfer_done);
 	INIT_LIST_HEAD(&bo->slices);
+	INIT_LIST_HEAD(&bo->xfer_list);
 }
 
 static struct qaic_bo *qaic_alloc_init_bo(void)
@@ -689,7 +704,7 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -708,21 +723,22 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	if (ret)
 		goto free_bo;
 
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto free_bo;
+
 	ret = drm_gem_handle_create(file_priv, obj, &args->handle);
 	if (ret)
-		goto free_sgt;
+		goto free_bo;
 
-	bo->handle = args->handle;
 	drm_gem_object_put(obj);
 	srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 	srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
 
 	return 0;
 
-free_sgt:
-	qaic_free_sgt(bo->sgt);
 free_bo:
-	kfree(bo);
+	drm_gem_object_put(obj);
 unlock_dev_srcu:
 	srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 unlock_usr_srcu:
@@ -737,7 +753,7 @@ int qaic_mmap_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 	struct drm_gem_object *obj;
 	struct qaic_device *qdev;
 	struct qaic_user *usr;
-	int ret;
+	int ret = 0;
 
 	usr = file_priv->driver_priv;
 	usr_rcu_id = srcu_read_lock(&usr->qddev_lock);
@@ -748,7 +764,7 @@ int qaic_mmap_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -759,9 +775,7 @@ int qaic_mmap_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 		goto unlock_dev_srcu;
 	}
 
-	ret = drm_gem_create_mmap_offset(obj);
-	if (ret == 0)
-		args->offset = drm_vma_node_offset_addr(&obj->vma_node);
+	args->offset = drm_vma_node_offset_addr(&obj->vma_node);
 
 	drm_gem_object_put(obj);
 
@@ -777,7 +791,6 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_
 	struct dma_buf_attachment *attach;
 	struct drm_gem_object *obj;
 	struct qaic_bo *bo;
-	size_t size;
 	int ret;
 
 	bo = qaic_alloc_init_bo();
@@ -795,13 +808,12 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_
 		goto attach_fail;
 	}
 
-	size = PAGE_ALIGN(attach->dmabuf->size);
-	if (size == 0) {
+	if (!attach->dmabuf->size) {
 		ret = -EINVAL;
 		goto size_align_fail;
 	}
 
-	drm_gem_private_object_init(dev, obj, size);
+	drm_gem_private_object_init(dev, obj, attach->dmabuf->size);
 	/*
 	 * skipping dma_buf_map_attachment() as we do not know the direction
 	 * just yet. Once the direction is known in the subsequent IOCTL to
@@ -829,9 +841,6 @@ static int qaic_prepare_import_bo(struct qaic_bo *bo, struct qaic_attach_slice_h
 	struct sg_table *sgt;
 	int ret;
 
-	if (obj->import_attach->dmabuf->size < hdr->size)
-		return -EINVAL;
-
 	sgt = dma_buf_map_attachment(obj->import_attach, hdr->dir);
 	if (IS_ERR(sgt)) {
 		ret = PTR_ERR(sgt);
@@ -848,9 +857,6 @@ static int qaic_prepare_export_bo(struct qaic_device *qdev, struct qaic_bo *bo,
 {
 	int ret;
 
-	if (bo->base.size < hdr->size)
-		return -EINVAL;
-
 	ret = dma_map_sgtable(&qdev->pdev->dev, bo->sgt, hdr->dir, 0);
 	if (ret)
 		return -EFAULT;
@@ -863,7 +869,7 @@ static int qaic_prepare_bo(struct qaic_device *qdev, struct qaic_bo *bo,
 {
 	int ret;
 
-	if (bo->base.import_attach)
+	if (drm_gem_is_imported(&bo->base))
 		ret = qaic_prepare_import_bo(bo, hdr);
 	else
 		ret = qaic_prepare_export_bo(qdev, bo, hdr);
@@ -887,7 +893,7 @@ static void qaic_unprepare_export_bo(struct qaic_device *qdev, struct qaic_bo *b
 
 static void qaic_unprepare_bo(struct qaic_device *qdev, struct qaic_bo *bo)
 {
-	if (bo->base.import_attach)
+	if (drm_gem_is_imported(&bo->base))
 		qaic_unprepare_import_bo(bo);
 	else
 		qaic_unprepare_export_bo(qdev, bo);
@@ -951,9 +957,6 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 	if (arg_size / args->hdr.count != sizeof(*slice_ent))
 		return -EINVAL;
 
-	if (args->hdr.size == 0)
-		return -EINVAL;
-
 	if (!(args->hdr.dir == DMA_TO_DEVICE || args->hdr.dir == DMA_FROM_DEVICE))
 		return -EINVAL;
 
@@ -969,7 +972,7 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -993,16 +996,16 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 		goto free_slice_ent;
 	}
 
-	ret = qaic_validate_req(qdev, slice_ent, args->hdr.count, args->hdr.size);
-	if (ret)
-		goto free_slice_ent;
-
 	obj = drm_gem_object_lookup(file_priv, args->hdr.handle);
 	if (!obj) {
 		ret = -ENOENT;
 		goto free_slice_ent;
 	}
 
+	ret = qaic_validate_req(qdev, slice_ent, args->hdr.count, obj->size);
+	if (ret)
+		goto put_bo;
+
 	bo = to_qaic_bo(obj);
 	ret = mutex_lock_interruptible(&bo->lock);
 	if (ret)
@@ -1058,6 +1061,16 @@ unlock_usr_srcu:
 	return ret;
 }
 
+static inline u32 fifo_space_avail(u32 head, u32 tail, u32 q_size)
+{
+	u32 avail = head - tail - 1;
+
+	if (head <= tail)
+		avail += q_size;
+
+	return avail;
+}
+
 static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slice, u32 dbc_id,
 				 u32 head, u32 *ptail)
 {
@@ -1066,27 +1079,20 @@ static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slic
 	u32 tail = *ptail;
 	u32 avail;
 
-	avail = head - tail;
-	if (head <= tail)
-		avail += dbc->nelem;
-
-	--avail;
-
+	avail = fifo_space_avail(head, tail, dbc->nelem);
 	if (avail < slice->nents)
 		return -EAGAIN;
 
 	if (tail + slice->nents > dbc->nelem) {
 		avail = dbc->nelem - tail;
 		avail = min_t(u32, avail, slice->nents);
-		memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-		       sizeof(*reqs) * avail);
+		memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * avail);
 		reqs += avail;
 		avail = slice->nents - avail;
 		if (avail)
 			memcpy(dbc->req_q_base, reqs, sizeof(*reqs) * avail);
 	} else {
-		memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-		       sizeof(*reqs) * slice->nents);
+		memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * slice->nents);
 	}
 
 	*ptail = (tail + slice->nents) % dbc->nelem;
@@ -1094,46 +1100,31 @@ static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slic
 	return 0;
 }
 
-/*
- * Based on the value of resize we may only need to transmit first_n
- * entries and the last entry, with last_bytes to send from the last entry.
- * Note that first_n could be 0.
- */
 static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_slice *slice,
-					 u64 resize, u32 dbc_id, u32 head, u32 *ptail)
+					 u64 resize, struct dma_bridge_chan *dbc, u32 head,
+					 u32 *ptail)
 {
-	struct dma_bridge_chan *dbc = &qdev->dbc[dbc_id];
 	struct dbc_req *reqs = slice->reqs;
 	struct dbc_req *last_req;
 	u32 tail = *ptail;
-	u64 total_bytes;
 	u64 last_bytes;
 	u32 first_n;
 	u32 avail;
-	int ret;
-	int i;
-
-	avail = head - tail;
-	if (head <= tail)
-		avail += dbc->nelem;
 
-	--avail;
+	avail = fifo_space_avail(head, tail, dbc->nelem);
 
-	total_bytes = 0;
-	for (i = 0; i < slice->nents; i++) {
-		total_bytes += le32_to_cpu(reqs[i].len);
-		if (total_bytes >= resize)
+	/*
+	 * After this for loop is complete, first_n represents the index
+	 * of the last DMA request of this slice that needs to be
+	 * transferred after resizing and last_bytes represents DMA size
+	 * of that request.
+	 */
+	last_bytes = resize;
+	for (first_n = 0; first_n < slice->nents; first_n++)
+		if (last_bytes > le32_to_cpu(reqs[first_n].len))
+			last_bytes -= le32_to_cpu(reqs[first_n].len);
+		else
 			break;
-	}
-
-	if (total_bytes < resize) {
-		/* User space should have used the full buffer path. */
-		ret = -EINVAL;
-		return ret;
-	}
-
-	first_n = i;
-	last_bytes = i ? resize + le32_to_cpu(reqs[i].len) - total_bytes : resize;
 
 	if (avail < (first_n + 1))
 		return -EAGAIN;
@@ -1142,22 +1133,21 @@ static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_sli
 		if (tail + first_n > dbc->nelem) {
 			avail = dbc->nelem - tail;
 			avail = min_t(u32, avail, first_n);
-			memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-			       sizeof(*reqs) * avail);
+			memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * avail);
 			last_req = reqs + avail;
 			avail = first_n - avail;
 			if (avail)
 				memcpy(dbc->req_q_base, last_req, sizeof(*reqs) * avail);
 		} else {
-			memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-			       sizeof(*reqs) * first_n);
+			memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * first_n);
 		}
 	}
 
-	/* Copy over the last entry. Here we need to adjust len to the left over
+	/*
+	 * Copy over the last entry. Here we need to adjust len to the left over
 	 * size, and set src and dst to the entry it is copied to.
 	 */
-	last_req = dbc->req_q_base + (tail + first_n) % dbc->nelem * get_dbc_req_elem_size();
+	last_req = fifo_at(dbc->req_q_base, (tail + first_n) % dbc->nelem);
 	memcpy(last_req, reqs + slice->nents - 1, sizeof(*reqs));
 
 	/*
@@ -1168,6 +1158,9 @@ static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_sli
 	last_req->len = cpu_to_le32((u32)last_bytes);
 	last_req->src_addr = reqs[first_n].src_addr;
 	last_req->dest_addr = reqs[first_n].dest_addr;
+	if (!last_bytes)
+		/* Disable DMA transfer */
+		last_req->cmd = GENMASK(7, 2) & reqs[first_n].cmd;
 
 	*ptail = (tail + first_n + 1) % dbc->nelem;
 
@@ -1184,7 +1177,6 @@ static int send_bo_list_to_device(struct qaic_device *qdev, struct drm_file *fil
 	struct bo_slice *slice;
 	unsigned long flags;
 	struct qaic_bo *bo;
-	bool queued;
 	int i, j;
 	int ret;
 
@@ -1216,9 +1208,7 @@ static int send_bo_list_to_device(struct qaic_device *qdev, struct drm_file *fil
 		}
 
 		spin_lock_irqsave(&dbc->xfer_lock, flags);
-		queued = bo->queued;
-		bo->queued = true;
-		if (queued) {
+		if (bo_queued(bo)) {
 			spin_unlock_irqrestore(&dbc->xfer_lock, flags);
 			ret = -EINVAL;
 			goto unlock_bo;
@@ -1227,30 +1217,20 @@ static int send_bo_list_to_device(struct qaic_device *qdev, struct drm_file *fil
 		bo->req_id = dbc->next_req_id++;
 
 		list_for_each_entry(slice, &bo->slices, slice) {
-			/*
-			 * If this slice does not fall under the given
-			 * resize then skip this slice and continue the loop
-			 */
-			if (is_partial && pexec[i].resize && pexec[i].resize <= slice->offset)
-				continue;
-
 			for (j = 0; j < slice->nents; j++)
 				slice->reqs[j].req_id = cpu_to_le16(bo->req_id);
 
-			/*
-			 * If it is a partial execute ioctl call then check if
-			 * resize has cut this slice short then do a partial copy
-			 * else do complete copy
-			 */
-			if (is_partial && pexec[i].resize &&
-			    pexec[i].resize < slice->offset + slice->size)
+			if (is_partial && (!pexec[i].resize || pexec[i].resize <= slice->offset))
+				/* Configure the slice for no DMA transfer */
+				ret = copy_partial_exec_reqs(qdev, slice, 0, dbc, head, tail);
+			else if (is_partial && pexec[i].resize < slice->offset + slice->size)
+				/* Configure the slice to be partially DMA transferred */
 				ret = copy_partial_exec_reqs(qdev, slice,
-							     pexec[i].resize - slice->offset,
-							     dbc->id, head, tail);
+							     pexec[i].resize - slice->offset, dbc,
+							     head, tail);
 			else
 				ret = copy_exec_reqs(qdev, slice, dbc->id, head, tail);
 			if (ret) {
-				bo->queued = false;
 				spin_unlock_irqrestore(&dbc->xfer_lock, flags);
 				goto unlock_bo;
 			}
@@ -1273,8 +1253,7 @@ failed_to_send_bo:
 		spin_lock_irqsave(&dbc->xfer_lock, flags);
 		bo = list_last_entry(&dbc->xfer_list, struct qaic_bo, xfer_list);
 		obj = &bo->base;
-		bo->queued = false;
-		list_del(&bo->xfer_list);
+		list_del_init(&bo->xfer_list);
 		spin_unlock_irqrestore(&dbc->xfer_lock, flags);
 		dma_sync_sgtable_for_cpu(&qdev->pdev->dev, bo->sgt, bo->dir);
 		drm_gem_object_put(obj);
@@ -1359,7 +1338,7 @@ static int __qaic_execute_bo_ioctl(struct drm_device *dev, void *data, struct dr
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1466,6 +1445,16 @@ irqreturn_t dbc_irq_handler(int irq, void *data)
 
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
 
+	if (datapath_polling) {
+		srcu_read_unlock(&dbc->ch_lock, rcu_id);
+		/*
+		 * Normally datapath_polling will not have irqs enabled, but
+		 * when running with only one MSI the interrupt is shared with
+		 * MHI so it cannot be disabled. Return ASAP instead.
+		 */
+		return IRQ_HANDLED;
+	}
+
 	if (!dbc->usr) {
 		srcu_read_unlock(&dbc->ch_lock, rcu_id);
 		return IRQ_HANDLED;
@@ -1488,7 +1477,8 @@ irqreturn_t dbc_irq_handler(int irq, void *data)
 		return IRQ_NONE;
 	}
 
-	disable_irq_nosync(irq);
+	if (!dbc->qdev->single_msi)
+		disable_irq_nosync(irq);
 	srcu_read_unlock(&dbc->ch_lock, rcu_id);
 	return IRQ_WAKE_THREAD;
 }
@@ -1504,7 +1494,7 @@ void irq_polling_work(struct work_struct *work)
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
 
 	while (1) {
-		if (dbc->qdev->in_reset) {
+		if (dbc->qdev->dev_state != QAIC_ONLINE) {
 			srcu_read_unlock(&dbc->ch_lock, rcu_id);
 			return;
 		}
@@ -1559,12 +1549,12 @@ irqreturn_t dbc_irq_threaded_fn(int irq, void *data)
 	u32 tail;
 
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
+	qdev = dbc->qdev;
 
 	head = readl(dbc->dbc_base + RSPHP_OFF);
 	if (head == U32_MAX) /* PCI link error */
 		goto error_out;
 
-	qdev = dbc->qdev;
 read_fifo:
 
 	if (!event_count) {
@@ -1624,8 +1614,7 @@ read_fifo:
 			 */
 			dma_sync_sgtable_for_cpu(&qdev->pdev->dev, bo->sgt, bo->dir);
 			bo->nr_slice_xfer_done = 0;
-			bo->queued = false;
-			list_del(&bo->xfer_list);
+			list_del_init(&bo->xfer_list);
 			bo->perf_stats.req_processed_ts = ktime_get_ns();
 			complete_all(&bo->xfer_done);
 			drm_gem_object_put(&bo->base);
@@ -1645,14 +1634,14 @@ read_fifo:
 	goto read_fifo;
 
 normal_out:
-	if (likely(!datapath_polling))
+	if (!qdev->single_msi && likely(!datapath_polling))
 		enable_irq(irq);
-	else
+	else if (unlikely(datapath_polling))
 		schedule_work(&dbc->poll_work);
 	/* checking the fifo and enabling irqs is a race, missed event check */
 	tail = readl(dbc->dbc_base + RSPTP_OFF);
 	if (tail != U32_MAX && head != tail) {
-		if (likely(!datapath_polling))
+		if (!qdev->single_msi && likely(!datapath_polling))
 			disable_irq_nosync(irq);
 		goto read_fifo;
 	}
@@ -1661,9 +1650,9 @@ normal_out:
 
 error_out:
 	srcu_read_unlock(&dbc->ch_lock, rcu_id);
-	if (likely(!datapath_polling))
+	if (!qdev->single_msi && likely(!datapath_polling))
 		enable_irq(irq);
-	else
+	else if (unlikely(datapath_polling))
 		schedule_work(&dbc->poll_work);
 
 	return IRQ_HANDLED;
@@ -1694,7 +1683,7 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1763,7 +1752,7 @@ int qaic_perf_stats_bo_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1854,7 +1843,7 @@ int qaic_detach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1884,7 +1873,7 @@ int qaic_detach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 
 	/* Check if BO is committed to H/W for DMA */
 	spin_lock_irqsave(&dbc->xfer_lock, flags);
-	if (bo->queued) {
+	if (bo_queued(bo)) {
 		spin_unlock_irqrestore(&dbc->xfer_lock, flags);
 		ret = -EBUSY;
 		goto unlock_ch_srcu;
@@ -1914,8 +1903,7 @@ static void empty_xfer_list(struct qaic_device *qdev, struct dma_bridge_chan *db
 	spin_lock_irqsave(&dbc->xfer_lock, flags);
 	while (!list_empty(&dbc->xfer_list)) {
 		bo = list_first_entry(&dbc->xfer_list, typeof(*bo), xfer_list);
-		bo->queued = false;
-		list_del(&bo->xfer_list);
+		list_del_init(&bo->xfer_list);
 		spin_unlock_irqrestore(&dbc->xfer_lock, flags);
 		bo->nr_slice_xfer_done = 0;
 		bo->req_id = 0;
@@ -1997,3 +1985,12 @@ void release_dbc(struct qaic_device *qdev, u32 dbc_id)
 	dbc->in_use = false;
 	wake_up(&dbc->dbc_release);
 }
+
+void qaic_data_get_fifo_info(struct dma_bridge_chan *dbc, u32 *head, u32 *tail)
+{
+	if (!dbc || !head || !tail)
+		return;
+
+	*head = readl(dbc->dbc_base + REQHP_OFF);
+	*tail = readl(dbc->dbc_base + REQTP_OFF);
+}
diff --git a/drivers/accel/qaic/qaic_debugfs.c b/drivers/accel/qaic/qaic_debugfs.c
new file mode 100644
index 000000000000..a991b8198dc4
--- /dev/null
+++ b/drivers/accel/qaic/qaic_debugfs.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Copyright (c) 2020, The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/mhi.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "qaic.h"
+#include "qaic_debugfs.h"
+
+#define BOOTLOG_POOL_SIZE		16
+#define BOOTLOG_MSG_SIZE		512
+#define QAIC_DBC_DIR_NAME		9
+
+struct bootlog_msg {
+	/* Buffer for bootlog messages */
+	char str[BOOTLOG_MSG_SIZE];
+	/* Root struct of device, used to access device resources */
+	struct qaic_device *qdev;
+	/* Work struct to schedule work coming on QAIC_LOGGING channel */
+	struct work_struct work;
+};
+
+struct bootlog_page {
+	/* Node in list of bootlog pages maintained by root device struct */
+	struct list_head node;
+	/* Total size of the buffer that holds the bootlogs. It is PAGE_SIZE */
+	unsigned int size;
+	/* Offset for the next bootlog */
+	unsigned int offset;
+};
+
+static int bootlog_show(struct seq_file *s, void *unused)
+{
+	struct bootlog_page *page;
+	struct qaic_device *qdev;
+	void *page_end;
+	void *log;
+
+	qdev = s->private;
+	mutex_lock(&qdev->bootlog_mutex);
+	list_for_each_entry(page, &qdev->bootlog, node) {
+		log = page + 1;
+		page_end = (void *)page + page->offset;
+		while (log < page_end) {
+			seq_printf(s, "%s", (char *)log);
+			log += strlen(log) + 1;
+		}
+	}
+	mutex_unlock(&qdev->bootlog_mutex);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(bootlog);
+
+static int fifo_size_show(struct seq_file *s, void *unused)
+{
+	struct dma_bridge_chan *dbc = s->private;
+
+	seq_printf(s, "%u\n", dbc->nelem);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(fifo_size);
+
+static int queued_show(struct seq_file *s, void *unused)
+{
+	struct dma_bridge_chan *dbc = s->private;
+	u32 tail = 0, head = 0;
+
+	qaic_data_get_fifo_info(dbc, &head, &tail);
+
+	if (head == U32_MAX || tail == U32_MAX)
+		seq_printf(s, "%u\n", 0);
+	else if (head > tail)
+		seq_printf(s, "%u\n", dbc->nelem - head + tail);
+	else
+		seq_printf(s, "%u\n", tail - head);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(queued);
+
+void qaic_debugfs_init(struct qaic_drm_device *qddev)
+{
+	struct qaic_device *qdev = qddev->qdev;
+	struct dentry *debugfs_root;
+	struct dentry *debugfs_dir;
+	char name[QAIC_DBC_DIR_NAME];
+	u32 i;
+
+	debugfs_root = to_drm(qddev)->debugfs_root;
+
+	debugfs_create_file("bootlog", 0400, debugfs_root, qdev, &bootlog_fops);
+	/*
+	 * 256 dbcs per device is likely the max we will ever see and lets static checking see a
+	 * reasonable range.
+	 */
+	for (i = 0; i < qdev->num_dbc && i < 256; ++i) {
+		snprintf(name, QAIC_DBC_DIR_NAME, "dbc%03u", i);
+		debugfs_dir = debugfs_create_dir(name, debugfs_root);
+		debugfs_create_file("fifo_size", 0400, debugfs_dir, &qdev->dbc[i], &fifo_size_fops);
+		debugfs_create_file("queued", 0400, debugfs_dir, &qdev->dbc[i], &queued_fops);
+	}
+}
+
+static struct bootlog_page *alloc_bootlog_page(struct qaic_device *qdev)
+{
+	struct bootlog_page *page;
+
+	page = (struct bootlog_page *)devm_get_free_pages(&qdev->pdev->dev, GFP_KERNEL, 0);
+	if (!page)
+		return page;
+
+	page->size = PAGE_SIZE;
+	page->offset = sizeof(*page);
+	list_add_tail(&page->node, &qdev->bootlog);
+
+	return page;
+}
+
+static int reset_bootlog(struct qaic_device *qdev)
+{
+	struct bootlog_page *page;
+	struct bootlog_page *i;
+
+	mutex_lock(&qdev->bootlog_mutex);
+	list_for_each_entry_safe(page, i, &qdev->bootlog, node) {
+		list_del(&page->node);
+		devm_free_pages(&qdev->pdev->dev, (unsigned long)page);
+	}
+
+	page = alloc_bootlog_page(qdev);
+	mutex_unlock(&qdev->bootlog_mutex);
+	if (!page)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void *bootlog_get_space(struct qaic_device *qdev, unsigned int size)
+{
+	struct bootlog_page *page;
+
+	page = list_last_entry(&qdev->bootlog, struct bootlog_page, node);
+
+	if (size_add(size, sizeof(*page)) > page->size)
+		return NULL;
+
+	if (page->offset + size > page->size) {
+		page = alloc_bootlog_page(qdev);
+		if (!page)
+			return NULL;
+	}
+
+	return (void *)page + page->offset;
+}
+
+static void bootlog_commit(struct qaic_device *qdev, unsigned int size)
+{
+	struct bootlog_page *page;
+
+	page = list_last_entry(&qdev->bootlog, struct bootlog_page, node);
+
+	page->offset += size;
+}
+
+static void bootlog_log(struct work_struct *work)
+{
+	struct bootlog_msg *msg = container_of(work, struct bootlog_msg, work);
+	unsigned int len = strlen(msg->str) + 1;
+	struct qaic_device *qdev = msg->qdev;
+	void *log;
+
+	mutex_lock(&qdev->bootlog_mutex);
+	log = bootlog_get_space(qdev, len);
+	if (log) {
+		memcpy(log, msg, len);
+		bootlog_commit(qdev, len);
+	}
+	mutex_unlock(&qdev->bootlog_mutex);
+
+	if (mhi_queue_buf(qdev->bootlog_ch, DMA_FROM_DEVICE, msg, BOOTLOG_MSG_SIZE, MHI_EOT))
+		devm_kfree(&qdev->pdev->dev, msg);
+}
+
+static int qaic_bootlog_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	struct bootlog_msg *msg;
+	int i, ret;
+
+	qdev->bootlog_wq = alloc_ordered_workqueue("qaic_bootlog", 0);
+	if (!qdev->bootlog_wq) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = reset_bootlog(qdev);
+	if (ret)
+		goto destroy_workqueue;
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		goto destroy_workqueue;
+
+	for (i = 0; i < BOOTLOG_POOL_SIZE; i++) {
+		msg = devm_kzalloc(&qdev->pdev->dev, sizeof(*msg), GFP_KERNEL);
+		if (!msg) {
+			ret = -ENOMEM;
+			goto mhi_unprepare;
+		}
+
+		msg->qdev = qdev;
+		INIT_WORK(&msg->work, bootlog_log);
+
+		ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, msg, BOOTLOG_MSG_SIZE, MHI_EOT);
+		if (ret)
+			goto mhi_unprepare;
+	}
+
+	dev_set_drvdata(&mhi_dev->dev, qdev);
+	qdev->bootlog_ch = mhi_dev;
+	return 0;
+
+mhi_unprepare:
+	mhi_unprepare_from_transfer(mhi_dev);
+destroy_workqueue:
+	destroy_workqueue(qdev->bootlog_wq);
+out:
+	return ret;
+}
+
+static void qaic_bootlog_mhi_remove(struct mhi_device *mhi_dev)
+{
+	struct qaic_device *qdev;
+
+	qdev = dev_get_drvdata(&mhi_dev->dev);
+
+	mhi_unprepare_from_transfer(qdev->bootlog_ch);
+	destroy_workqueue(qdev->bootlog_wq);
+	qdev->bootlog_ch = NULL;
+}
+
+static void qaic_bootlog_mhi_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+}
+
+static void qaic_bootlog_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct qaic_device *qdev = dev_get_drvdata(&mhi_dev->dev);
+	struct bootlog_msg *msg = mhi_result->buf_addr;
+
+	if (mhi_result->transaction_status) {
+		devm_kfree(&qdev->pdev->dev, msg);
+		return;
+	}
+
+	/* Force a null at the end of the transferred string */
+	msg->str[mhi_result->bytes_xferd - 1] = 0;
+
+	queue_work(qdev->bootlog_wq, &msg->work);
+}
+
+static const struct mhi_device_id qaic_bootlog_mhi_match_table[] = {
+	{ .chan = "QAIC_LOGGING", },
+	{},
+};
+
+static struct mhi_driver qaic_bootlog_mhi_driver = {
+	.id_table = qaic_bootlog_mhi_match_table,
+	.remove = qaic_bootlog_mhi_remove,
+	.probe = qaic_bootlog_mhi_probe,
+	.ul_xfer_cb = qaic_bootlog_mhi_ul_xfer_cb,
+	.dl_xfer_cb = qaic_bootlog_mhi_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_bootlog",
+	},
+};
+
+int qaic_bootlog_register(void)
+{
+	return mhi_driver_register(&qaic_bootlog_mhi_driver);
+}
+
+void qaic_bootlog_unregister(void)
+{
+	mhi_driver_unregister(&qaic_bootlog_mhi_driver);
+}
diff --git a/drivers/accel/qaic/qaic_debugfs.h b/drivers/accel/qaic/qaic_debugfs.h
new file mode 100644
index 000000000000..05e74f84cf9f
--- /dev/null
+++ b/drivers/accel/qaic/qaic_debugfs.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/* Copyright (c) 2020, The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#ifndef __QAIC_DEBUGFS_H__
+#define __QAIC_DEBUGFS_H__
+
+#include <drm/drm_file.h>
+
+#ifdef CONFIG_DEBUG_FS
+int qaic_bootlog_register(void);
+void qaic_bootlog_unregister(void);
+void qaic_debugfs_init(struct qaic_drm_device *qddev);
+#else
+static inline int qaic_bootlog_register(void) { return 0; }
+static inline void qaic_bootlog_unregister(void) {}
+static inline void qaic_debugfs_init(struct qaic_drm_device *qddev) {}
+#endif /* CONFIG_DEBUG_FS */
+#endif /* __QAIC_DEBUGFS_H__ */
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 6f58095767df..e31bcb0ecfc9 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -8,6 +8,7 @@
 #include <linux/idr.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
+#include <linux/kobject.h>
 #include <linux/kref.h>
 #include <linux/mhi.h>
 #include <linux/module.h>
@@ -27,23 +28,105 @@
 
 #include "mhi_controller.h"
 #include "qaic.h"
+#include "qaic_debugfs.h"
+#include "qaic_ras.h"
+#include "qaic_timesync.h"
+#include "sahara.h"
 
-MODULE_IMPORT_NS(DMA_BUF);
+MODULE_IMPORT_NS("DMA_BUF");
 
-#define PCI_DEV_AIC100			0xa100
+#define PCI_DEVICE_ID_QCOM_AIC080	0xa080
+#define PCI_DEVICE_ID_QCOM_AIC100	0xa100
+#define PCI_DEVICE_ID_QCOM_AIC200	0xa110
 #define QAIC_NAME			"qaic"
 #define QAIC_DESC			"Qualcomm Cloud AI Accelerators"
 #define CNTL_MAJOR			5
 #define CNTL_MINOR			0
 
+struct qaic_device_config {
+	/* Indicates the AIC family the device belongs to */
+	int family;
+	/* A bitmask representing the available BARs */
+	int bar_mask;
+	/* An index value used to identify the MHI controller BAR */
+	unsigned int mhi_bar_idx;
+	/* An index value used to identify the DBCs BAR */
+	unsigned int dbc_bar_idx;
+};
+
+static const struct qaic_device_config aic080_config = {
+	.family = FAMILY_AIC100,
+	.bar_mask = BIT(0) | BIT(2) | BIT(4),
+	.mhi_bar_idx = 0,
+	.dbc_bar_idx = 2,
+};
+
+static const struct qaic_device_config aic100_config = {
+	.family = FAMILY_AIC100,
+	.bar_mask = BIT(0) | BIT(2) | BIT(4),
+	.mhi_bar_idx = 0,
+	.dbc_bar_idx = 2,
+};
+
+static const struct qaic_device_config aic200_config = {
+	.family = FAMILY_AIC200,
+	.bar_mask = BIT(0) | BIT(1) | BIT(2) | BIT(4),
+	.mhi_bar_idx = 1,
+	.dbc_bar_idx = 2,
+};
+
 bool datapath_polling;
 module_param(datapath_polling, bool, 0400);
 MODULE_PARM_DESC(datapath_polling, "Operate the datapath in polling mode");
 static bool link_up;
 static DEFINE_IDA(qaic_usrs);
 
-static int qaic_create_drm_device(struct qaic_device *qdev, s32 partition_id);
-static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id);
+static void qaicm_wq_release(struct drm_device *dev, void *res)
+{
+	struct workqueue_struct *wq = res;
+
+	destroy_workqueue(wq);
+}
+
+static struct workqueue_struct *qaicm_wq_init(struct drm_device *dev, const char *name)
+{
+	struct workqueue_struct *wq;
+	int ret;
+
+	wq = alloc_workqueue("%s", WQ_UNBOUND, 0, name);
+	if (!wq)
+		return ERR_PTR(-ENOMEM);
+	ret = drmm_add_action_or_reset(dev, qaicm_wq_release, wq);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return wq;
+}
+
+static void qaicm_srcu_release(struct drm_device *dev, void *res)
+{
+	struct srcu_struct *lock = res;
+
+	cleanup_srcu_struct(lock);
+}
+
+static int qaicm_srcu_init(struct drm_device *dev, struct srcu_struct *lock)
+{
+	int ret;
+
+	ret = init_srcu_struct(lock);
+	if (ret)
+		return ret;
+
+	return drmm_add_action_or_reset(dev, qaicm_srcu_release, lock);
+}
+
+static void qaicm_pci_release(struct drm_device *dev, void *res)
+{
+	struct qaic_device *qdev = to_qaic_device(dev);
+
+	pci_set_drvdata(qdev->pdev, NULL);
+}
 
 static void free_usr(struct kref *kref)
 {
@@ -63,7 +146,7 @@ static int qaic_open(struct drm_device *dev, struct drm_file *file)
 	int ret;
 
 	rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto dev_unlock;
 	}
@@ -120,7 +203,7 @@ static void qaic_postclose(struct drm_device *dev, struct drm_file *file)
 	if (qddev) {
 		qdev = qddev->qdev;
 		qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-		if (!qdev->in_reset) {
+		if (qdev->dev_state == QAIC_ONLINE) {
 			qaic_release_usr(qdev, usr);
 			for (i = 0; i < qdev->num_dbc; ++i)
 				if (qdev->dbc[i].usr && qdev->dbc[i].usr->handle == usr->handle)
@@ -159,7 +242,6 @@ static const struct drm_driver qaic_accel_driver = {
 
 	.name			= QAIC_NAME,
 	.desc			= QAIC_DESC,
-	.date			= "20190618",
 
 	.fops			= &qaic_accel_fops,
 	.open			= qaic_open,
@@ -182,16 +264,13 @@ static int qaic_create_drm_device(struct qaic_device *qdev, s32 partition_id)
 
 	qddev->partition_id = partition_id;
 
-	/*
-	 * drm_dev_unregister() sets the driver data to NULL and
-	 * drm_dev_register() does not update the driver data. During a SOC
-	 * reset drm dev is unregistered and registered again leaving the
-	 * driver data to NULL.
-	 */
-	dev_set_drvdata(to_accel_kdev(qddev), drm->accel);
 	ret = drm_dev_register(drm, 0);
-	if (ret)
+	if (ret) {
 		pci_dbg(qdev->pdev, "drm_dev_register failed %d\n", ret);
+		return ret;
+	}
+
+	qaic_debugfs_init(qddev);
 
 	return ret;
 }
@@ -202,7 +281,6 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id)
 	struct drm_device *drm = to_drm(qddev);
 	struct qaic_user *usr;
 
-	drm_dev_get(drm);
 	drm_dev_unregister(drm);
 	qddev->partition_id = 0;
 	/*
@@ -231,7 +309,6 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id)
 		mutex_lock(&qddev->users_mutex);
 	}
 	mutex_unlock(&qddev->users_mutex);
-	drm_dev_put(drm);
 }
 
 static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
@@ -253,8 +330,6 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 
 	qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
 
-	qdev->in_reset = false;
-
 	dev_set_drvdata(&mhi_dev->dev, qdev);
 	qdev->cntl_ch = mhi_dev;
 
@@ -264,6 +339,7 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 		return ret;
 	}
 
+	qdev->dev_state = QAIC_BOOT;
 	ret = get_cntl_version(qdev, NULL, &major, &minor);
 	if (ret || major != CNTL_MAJOR || minor > CNTL_MINOR) {
 		pci_err(qdev->pdev, "%s: Control protocol version (%d.%d) not supported. Supported version is (%d.%d). Ret: %d\n",
@@ -271,8 +347,8 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 		ret = -EINVAL;
 		goto close_control;
 	}
-
-	ret = qaic_create_drm_device(qdev, QAIC_NO_PARTITION);
+	qdev->dev_state = QAIC_ONLINE;
+	kobject_uevent(&(to_accel_kdev(qdev->qddev))->kobj, KOBJ_ONLINE);
 
 	return ret;
 
@@ -290,7 +366,8 @@ static void qaic_notify_reset(struct qaic_device *qdev)
 {
 	int i;
 
-	qdev->in_reset = true;
+	kobject_uevent(&(to_accel_kdev(qdev->qddev))->kobj, KOBJ_OFFLINE);
+	qdev->dev_state = QAIC_OFFLINE;
 	/* wake up any waiters to avoid waiting for timeouts at sync */
 	wake_all_cntl(qdev);
 	for (i = 0; i < qdev->num_dbc; ++i)
@@ -298,97 +375,102 @@ static void qaic_notify_reset(struct qaic_device *qdev)
 	synchronize_srcu(&qdev->dev_lock);
 }
 
-void qaic_dev_reset_clean_local_state(struct qaic_device *qdev, bool exit_reset)
+void qaic_dev_reset_clean_local_state(struct qaic_device *qdev)
 {
 	int i;
 
 	qaic_notify_reset(qdev);
 
-	/* remove drmdevs to prevent new users from coming in */
-	qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
-
 	/* start tearing things down */
 	for (i = 0; i < qdev->num_dbc; ++i)
 		release_dbc(qdev, i);
-
-	if (exit_reset)
-		qdev->in_reset = false;
-}
-
-static void cleanup_qdev(struct qaic_device *qdev)
-{
-	int i;
-
-	for (i = 0; i < qdev->num_dbc; ++i)
-		cleanup_srcu_struct(&qdev->dbc[i].ch_lock);
-	cleanup_srcu_struct(&qdev->dev_lock);
-	pci_set_drvdata(qdev->pdev, NULL);
-	destroy_workqueue(qdev->cntl_wq);
 }
 
-static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_device_id *id)
+static struct qaic_device *create_qdev(struct pci_dev *pdev,
+				       const struct qaic_device_config *config)
 {
+	struct device *dev = &pdev->dev;
 	struct qaic_drm_device *qddev;
 	struct qaic_device *qdev;
-	int i;
+	struct drm_device *drm;
+	int i, ret;
 
-	qdev = devm_kzalloc(&pdev->dev, sizeof(*qdev), GFP_KERNEL);
+	qdev = devm_kzalloc(dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return NULL;
 
-	if (id->device == PCI_DEV_AIC100) {
-		qdev->num_dbc = 16;
-		qdev->dbc = devm_kcalloc(&pdev->dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL);
-		if (!qdev->dbc)
-			return NULL;
-	}
+	qdev->dev_state = QAIC_OFFLINE;
+	qdev->num_dbc = 16;
+	qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL);
+	if (!qdev->dbc)
+		return NULL;
 
-	qdev->cntl_wq = alloc_workqueue("qaic_cntl", WQ_UNBOUND, 0);
-	if (!qdev->cntl_wq)
+	qddev = devm_drm_dev_alloc(&pdev->dev, &qaic_accel_driver, struct qaic_drm_device, drm);
+	if (IS_ERR(qddev))
 		return NULL;
 
+	drm = to_drm(qddev);
 	pci_set_drvdata(pdev, qdev);
+
+	ret = drmm_mutex_init(drm, &qddev->users_mutex);
+	if (ret)
+		return NULL;
+	ret = drmm_add_action_or_reset(drm, qaicm_pci_release, NULL);
+	if (ret)
+		return NULL;
+	ret = drmm_mutex_init(drm, &qdev->cntl_mutex);
+	if (ret)
+		return NULL;
+	ret = drmm_mutex_init(drm, &qdev->bootlog_mutex);
+	if (ret)
+		return NULL;
+
+	qdev->cntl_wq = qaicm_wq_init(drm, "qaic_cntl");
+	if (IS_ERR(qdev->cntl_wq))
+		return NULL;
+	qdev->qts_wq = qaicm_wq_init(drm, "qaic_ts");
+	if (IS_ERR(qdev->qts_wq))
+		return NULL;
+
+	ret = qaicm_srcu_init(drm, &qdev->dev_lock);
+	if (ret)
+		return NULL;
+
+	qdev->qddev = qddev;
 	qdev->pdev = pdev;
+	qddev->qdev = qdev;
 
-	mutex_init(&qdev->cntl_mutex);
 	INIT_LIST_HEAD(&qdev->cntl_xfer_list);
-	init_srcu_struct(&qdev->dev_lock);
+	INIT_LIST_HEAD(&qdev->bootlog);
+	INIT_LIST_HEAD(&qddev->users);
 
 	for (i = 0; i < qdev->num_dbc; ++i) {
 		spin_lock_init(&qdev->dbc[i].xfer_lock);
 		qdev->dbc[i].qdev = qdev;
 		qdev->dbc[i].id = i;
 		INIT_LIST_HEAD(&qdev->dbc[i].xfer_list);
-		init_srcu_struct(&qdev->dbc[i].ch_lock);
+		ret = qaicm_srcu_init(drm, &qdev->dbc[i].ch_lock);
+		if (ret)
+			return NULL;
 		init_waitqueue_head(&qdev->dbc[i].dbc_release);
 		INIT_LIST_HEAD(&qdev->dbc[i].bo_lists);
 	}
 
-	qddev = devm_drm_dev_alloc(&pdev->dev, &qaic_accel_driver, struct qaic_drm_device, drm);
-	if (IS_ERR(qddev)) {
-		cleanup_qdev(qdev);
-		return NULL;
-	}
-
-	drmm_mutex_init(to_drm(qddev), &qddev->users_mutex);
-	INIT_LIST_HEAD(&qddev->users);
-	qddev->qdev = qdev;
-	qdev->qddev = qddev;
-
 	return qdev;
 }
 
-static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev)
+static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev,
+		    const struct qaic_device_config *config)
 {
 	int bars;
 	int ret;
 
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	bars = pci_select_bars(pdev, IORESOURCE_MEM) & 0x3f;
 
 	/* make sure the device has the expected BARs */
-	if (bars != (BIT(0) | BIT(2) | BIT(4))) {
-		pci_dbg(pdev, "%s: expected BARs 0, 2, and 4 not found in device. Found 0x%x\n",
-			__func__, bars);
+	if (bars != config->bar_mask) {
+		pci_dbg(pdev, "%s: expected BARs %#x not found in device. Found %#x\n",
+			__func__, config->bar_mask, bars);
 		return -EINVAL;
 	}
 
@@ -399,17 +481,15 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev)
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (ret)
 		return ret;
-	ret = dma_set_max_seg_size(&pdev->dev, UINT_MAX);
-	if (ret)
-		return ret;
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
-	qdev->bar_0 = devm_ioremap_resource(&pdev->dev, &pdev->resource[0]);
-	if (IS_ERR(qdev->bar_0))
-		return PTR_ERR(qdev->bar_0);
+	qdev->bar_mhi = devm_ioremap_resource(&pdev->dev, &pdev->resource[config->mhi_bar_idx]);
+	if (IS_ERR(qdev->bar_mhi))
+		return PTR_ERR(qdev->bar_mhi);
 
-	qdev->bar_2 = devm_ioremap_resource(&pdev->dev, &pdev->resource[2]);
-	if (IS_ERR(qdev->bar_2))
-		return PTR_ERR(qdev->bar_2);
+	qdev->bar_dbc = devm_ioremap_resource(&pdev->dev, &pdev->resource[config->dbc_bar_idx]);
+	if (IS_ERR(qdev->bar_dbc))
+		return PTR_ERR(qdev->bar_dbc);
 
 	/* Managed release since we use pcim_enable_device above */
 	pci_set_master(pdev);
@@ -419,19 +499,31 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev)
 
 static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 {
+	int irq_count = qdev->num_dbc + 1;
 	int mhi_irq;
 	int ret;
 	int i;
 
 	/* Managed release since we use pcim_enable_device */
-	ret = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
-	if (ret < 0)
-		return ret;
+	ret = pci_alloc_irq_vectors(pdev, irq_count, irq_count, PCI_IRQ_MSI | PCI_IRQ_MSIX);
+	if (ret == -ENOSPC) {
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_MSIX);
+		if (ret < 0)
+			return ret;
 
-	if (ret < 32) {
-		pci_err(pdev, "%s: Requested 32 MSIs. Obtained %d MSIs which is less than the 32 required.\n",
-			__func__, ret);
-		return -ENODEV;
+		/*
+		 * Operate in one MSI mode. All interrupts will be directed to
+		 * MSI0; every interrupt will wake up all the interrupt handlers
+		 * (MHI and DBC[0-15]). Since the interrupt is now shared, it is
+		 * not disabled during DBC threaded handler, but only one thread
+		 * will be allowed to run per DBC, so while it can be
+		 * interrupted, it shouldn't race with itself.
+		 */
+		qdev->single_msi = true;
+		pci_info(pdev, "Allocating %d MSIs failed, operating in 1 MSI mode. Performance may be impacted.\n",
+			 irq_count);
+	} else if (ret < 0) {
+		return ret;
 	}
 
 	mhi_irq = pci_irq_vector(pdev, 0);
@@ -439,15 +531,17 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 		return mhi_irq;
 
 	for (i = 0; i < qdev->num_dbc; ++i) {
-		ret = devm_request_threaded_irq(&pdev->dev, pci_irq_vector(pdev, i + 1),
+		ret = devm_request_threaded_irq(&pdev->dev,
+						pci_irq_vector(pdev, qdev->single_msi ? 0 : i + 1),
 						dbc_irq_handler, dbc_irq_threaded_fn, IRQF_SHARED,
 						"qaic_dbc", &qdev->dbc[i]);
 		if (ret)
 			return ret;
 
 		if (datapath_polling) {
-			qdev->dbc[i].irq = pci_irq_vector(pdev, i + 1);
-			disable_irq_nosync(qdev->dbc[i].irq);
+			qdev->dbc[i].irq = pci_irq_vector(pdev, qdev->single_msi ? 0 : i + 1);
+			if (!qdev->single_msi)
+				disable_irq_nosync(qdev->dbc[i].irq);
 			INIT_WORK(&qdev->dbc[i].poll_work, irq_polling_work);
 		}
 	}
@@ -457,39 +551,40 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 
 static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct qaic_device_config *config = (struct qaic_device_config *)id->driver_data;
 	struct qaic_device *qdev;
 	int mhi_irq;
 	int ret;
 	int i;
 
-	qdev = create_qdev(pdev, id);
+	qdev = create_qdev(pdev, config);
 	if (!qdev)
 		return -ENOMEM;
 
-	ret = init_pci(qdev, pdev);
+	ret = init_pci(qdev, pdev, config);
 	if (ret)
-		goto cleanup_qdev;
+		return ret;
 
 	for (i = 0; i < qdev->num_dbc; ++i)
-		qdev->dbc[i].dbc_base = qdev->bar_2 + QAIC_DBC_OFF(i);
+		qdev->dbc[i].dbc_base = qdev->bar_dbc + QAIC_DBC_OFF(i);
 
 	mhi_irq = init_msi(qdev, pdev);
-	if (mhi_irq < 0) {
-		ret = mhi_irq;
-		goto cleanup_qdev;
-	}
+	if (mhi_irq < 0)
+		return mhi_irq;
+
+	ret = qaic_create_drm_device(qdev, QAIC_NO_PARTITION);
+	if (ret)
+		return ret;
 
-	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq);
+	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_mhi, mhi_irq,
+						       qdev->single_msi, config->family);
 	if (IS_ERR(qdev->mhi_cntrl)) {
 		ret = PTR_ERR(qdev->mhi_cntrl);
-		goto cleanup_qdev;
+		qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
+		return ret;
 	}
 
 	return 0;
-
-cleanup_qdev:
-	cleanup_qdev(qdev);
-	return ret;
 }
 
 static void qaic_pci_remove(struct pci_dev *pdev)
@@ -499,9 +594,9 @@ static void qaic_pci_remove(struct pci_dev *pdev)
 	if (!qdev)
 		return;
 
-	qaic_dev_reset_clean_local_state(qdev, false);
+	qaic_dev_reset_clean_local_state(qdev);
 	qaic_mhi_free_controller(qdev->mhi_cntrl, link_up);
-	cleanup_qdev(qdev);
+	qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
 }
 
 static void qaic_pci_shutdown(struct pci_dev *pdev)
@@ -522,14 +617,13 @@ static void qaic_pci_reset_prepare(struct pci_dev *pdev)
 
 	qaic_notify_reset(qdev);
 	qaic_mhi_start_reset(qdev->mhi_cntrl);
-	qaic_dev_reset_clean_local_state(qdev, false);
+	qaic_dev_reset_clean_local_state(qdev);
 }
 
 static void qaic_pci_reset_done(struct pci_dev *pdev)
 {
 	struct qaic_device *qdev = pci_get_drvdata(pdev);
 
-	qdev->in_reset = false;
 	qaic_mhi_reset_done(qdev->mhi_cntrl);
 }
 
@@ -550,7 +644,9 @@ static struct mhi_driver qaic_mhi_driver = {
 };
 
 static const struct pci_device_id qaic_ids[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, PCI_DEV_AIC100), },
+	{ PCI_DEVICE_DATA(QCOM, AIC080, (kernel_ulong_t)&aic080_config), },
+	{ PCI_DEVICE_DATA(QCOM, AIC100, (kernel_ulong_t)&aic100_config), },
+	{ PCI_DEVICE_DATA(QCOM, AIC200, (kernel_ulong_t)&aic200_config), },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, qaic_ids);
@@ -586,8 +682,28 @@ static int __init qaic_init(void)
 		goto free_pci;
 	}
 
+	ret = sahara_register();
+	if (ret) {
+		pr_debug("qaic: sahara_register failed %d\n", ret);
+		goto free_mhi;
+	}
+
+	ret = qaic_timesync_init();
+	if (ret)
+		pr_debug("qaic: qaic_timesync_init failed %d\n", ret);
+
+	ret = qaic_bootlog_register();
+	if (ret)
+		pr_debug("qaic: qaic_bootlog_register failed %d\n", ret);
+
+	ret = qaic_ras_register();
+	if (ret)
+		pr_debug("qaic: qaic_ras_register failed %d\n", ret);
+
 	return 0;
 
+free_mhi:
+	mhi_driver_unregister(&qaic_mhi_driver);
 free_pci:
 	pci_unregister_driver(&qaic_pci_driver);
 	return ret;
@@ -611,6 +727,10 @@ static void __exit qaic_exit(void)
 	 * reinitializing the link_up state after the cleanup is done.
 	 */
 	link_up = true;
+	qaic_ras_unregister();
+	qaic_bootlog_unregister();
+	qaic_timesync_deinit();
+	sahara_unregister();
 	mhi_driver_unregister(&qaic_mhi_driver);
 	pci_unregister_driver(&qaic_pci_driver);
 }
diff --git a/drivers/accel/qaic/qaic_ras.c b/drivers/accel/qaic/qaic_ras.c
new file mode 100644
index 000000000000..914ffc4a9970
--- /dev/null
+++ b/drivers/accel/qaic/qaic_ras.c
@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Copyright (c) 2020-2021, The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+/* Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */
+
+#include <asm/byteorder.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mhi.h>
+
+#include "qaic.h"
+#include "qaic_ras.h"
+
+#define MAGIC		0x55AA
+#define VERSION		0x2
+#define HDR_SZ		12
+#define NUM_TEMP_LVL	3
+#define POWER_BREAK	BIT(0)
+
+enum msg_type {
+	MSG_PUSH, /* async push from device */
+	MSG_REQ,  /* sync request to device */
+	MSG_RESP, /* sync response from device */
+};
+
+enum err_type {
+	CE,	/* correctable error */
+	UE,	/* uncorrectable error */
+	UE_NF,	/* uncorrectable error that is non-fatal, expect a disruption */
+	ERR_TYPE_MAX,
+};
+
+static const char * const err_type_str[] = {
+	[CE]    = "Correctable",
+	[UE]    = "Uncorrectable",
+	[UE_NF] = "Uncorrectable Non-Fatal",
+};
+
+static const char * const err_class_str[] = {
+	[CE]    = "Warning",
+	[UE]    = "Fatal",
+	[UE_NF] = "Warning",
+};
+
+enum err_source {
+	SOC_MEM,
+	PCIE,
+	DDR,
+	SYS_BUS1,
+	SYS_BUS2,
+	NSP_MEM,
+	TSENS,
+};
+
+static const char * const err_src_str[TSENS + 1] = {
+	[SOC_MEM]	= "SoC Memory",
+	[PCIE]		= "PCIE",
+	[DDR]		= "DDR",
+	[SYS_BUS1]	= "System Bus source 1",
+	[SYS_BUS2]	= "System Bus source 2",
+	[NSP_MEM]	= "NSP Memory",
+	[TSENS]		= "Temperature Sensors",
+};
+
+struct ras_data {
+	/* header start */
+	/* Magic number to validate the message */
+	u16 magic;
+	/* RAS version number */
+	u16 ver;
+	u32 seq_num;
+	/* RAS message type */
+	u8  type;
+	u8  id;
+	/* Size of RAS message without the header in byte */
+	u16 len;
+	/* header end */
+	s32 result;
+	/*
+	 * Error source
+	 * 0 : SoC Memory
+	 * 1 : PCIE
+	 * 2 : DDR
+	 * 3 : System Bus source 1
+	 * 4 : System Bus source 2
+	 * 5 : NSP Memory
+	 * 6 : Temperature Sensors
+	 */
+	u32 source;
+	/*
+	 * Stores the error type, there are three types of error in RAS
+	 * 0 : correctable error (CE)
+	 * 1 : uncorrectable error (UE)
+	 * 2 : uncorrectable error that is non-fatal (UE_NF)
+	 */
+	u32 err_type;
+	u32 err_threshold;
+	u32 ce_count;
+	u32 ue_count;
+	u32 intr_num;
+	/* Data specific to error source */
+	u8  syndrome[64];
+} __packed;
+
+struct soc_mem_syndrome {
+	u64 error_address[8];
+} __packed;
+
+struct nsp_mem_syndrome {
+	u32 error_address[8];
+	u8 nsp_id;
+} __packed;
+
+struct ddr_syndrome {
+	u32 count;
+	u32 irq_status;
+	u32 data_31_0[2];
+	u32 data_63_32[2];
+	u32 data_95_64[2];
+	u32 data_127_96[2];
+	u32 addr_lsb;
+	u16 addr_msb;
+	u16 parity_bits;
+	u16 instance;
+	u16 err_type;
+} __packed;
+
+struct tsens_syndrome {
+	u32 threshold_type;
+	s32 temp;
+} __packed;
+
+struct sysbus1_syndrome {
+	u32 slave;
+	u32 err_type;
+	u16 addr[8];
+	u8  instance;
+} __packed;
+
+struct sysbus2_syndrome {
+	u32 lsb3;
+	u32 msb3;
+	u32 lsb2;
+	u32 msb2;
+	u32 ext_id;
+	u16 path;
+	u16 op_type;
+	u16 len;
+	u16 redirect;
+	u8  valid;
+	u8  word_error;
+	u8  non_secure;
+	u8  opc;
+	u8  error_code;
+	u8  trans_type;
+	u8  addr_space;
+	u8  instance;
+} __packed;
+
+struct pcie_syndrome {
+	/* CE info */
+	u32 bad_tlp;
+	u32 bad_dllp;
+	u32 replay_rollover;
+	u32 replay_timeout;
+	u32 rx_err;
+	u32 internal_ce_count;
+	/* UE_NF info */
+	u32 fc_timeout;
+	u32 poison_tlp;
+	u32 ecrc_err;
+	u32 unsupported_req;
+	u32 completer_abort;
+	u32 completion_timeout;
+	/* UE info */
+	u32 addr;
+	u8  index;
+	/*
+	 * Flag to indicate specific event of PCIe
+	 * BIT(0): Power break (low power)
+	 * BIT(1) to BIT(7): Reserved
+	 */
+	u8 flag;
+} __packed;
+
+static const char * const threshold_type_str[NUM_TEMP_LVL] = {
+	[0] = "lower",
+	[1] = "upper",
+	[2] = "critical",
+};
+
+static void ras_msg_to_cpu(struct ras_data *msg)
+{
+	struct sysbus1_syndrome *sysbus1_syndrome = (struct sysbus1_syndrome *)&msg->syndrome[0];
+	struct sysbus2_syndrome *sysbus2_syndrome = (struct sysbus2_syndrome *)&msg->syndrome[0];
+	struct soc_mem_syndrome *soc_syndrome = (struct soc_mem_syndrome *)&msg->syndrome[0];
+	struct nsp_mem_syndrome *nsp_syndrome = (struct nsp_mem_syndrome *)&msg->syndrome[0];
+	struct tsens_syndrome *tsens_syndrome = (struct tsens_syndrome *)&msg->syndrome[0];
+	struct pcie_syndrome *pcie_syndrome = (struct pcie_syndrome *)&msg->syndrome[0];
+	struct ddr_syndrome *ddr_syndrome = (struct ddr_syndrome *)&msg->syndrome[0];
+	int i;
+
+	le16_to_cpus(&msg->magic);
+	le16_to_cpus(&msg->ver);
+	le32_to_cpus(&msg->seq_num);
+	le16_to_cpus(&msg->len);
+	le32_to_cpus(&msg->result);
+	le32_to_cpus(&msg->source);
+	le32_to_cpus(&msg->err_type);
+	le32_to_cpus(&msg->err_threshold);
+	le32_to_cpus(&msg->ce_count);
+	le32_to_cpus(&msg->ue_count);
+	le32_to_cpus(&msg->intr_num);
+
+	switch (msg->source) {
+	case SOC_MEM:
+		for (i = 0; i < 8; i++)
+			le64_to_cpus(&soc_syndrome->error_address[i]);
+		break;
+	case PCIE:
+		le32_to_cpus(&pcie_syndrome->bad_tlp);
+		le32_to_cpus(&pcie_syndrome->bad_dllp);
+		le32_to_cpus(&pcie_syndrome->replay_rollover);
+		le32_to_cpus(&pcie_syndrome->replay_timeout);
+		le32_to_cpus(&pcie_syndrome->rx_err);
+		le32_to_cpus(&pcie_syndrome->internal_ce_count);
+		le32_to_cpus(&pcie_syndrome->fc_timeout);
+		le32_to_cpus(&pcie_syndrome->poison_tlp);
+		le32_to_cpus(&pcie_syndrome->ecrc_err);
+		le32_to_cpus(&pcie_syndrome->unsupported_req);
+		le32_to_cpus(&pcie_syndrome->completer_abort);
+		le32_to_cpus(&pcie_syndrome->completion_timeout);
+		le32_to_cpus(&pcie_syndrome->addr);
+		break;
+	case DDR:
+		le16_to_cpus(&ddr_syndrome->instance);
+		le16_to_cpus(&ddr_syndrome->err_type);
+		le32_to_cpus(&ddr_syndrome->count);
+		le32_to_cpus(&ddr_syndrome->irq_status);
+		le32_to_cpus(&ddr_syndrome->data_31_0[0]);
+		le32_to_cpus(&ddr_syndrome->data_31_0[1]);
+		le32_to_cpus(&ddr_syndrome->data_63_32[0]);
+		le32_to_cpus(&ddr_syndrome->data_63_32[1]);
+		le32_to_cpus(&ddr_syndrome->data_95_64[0]);
+		le32_to_cpus(&ddr_syndrome->data_95_64[1]);
+		le32_to_cpus(&ddr_syndrome->data_127_96[0]);
+		le32_to_cpus(&ddr_syndrome->data_127_96[1]);
+		le16_to_cpus(&ddr_syndrome->parity_bits);
+		le16_to_cpus(&ddr_syndrome->addr_msb);
+		le32_to_cpus(&ddr_syndrome->addr_lsb);
+		break;
+	case SYS_BUS1:
+		le32_to_cpus(&sysbus1_syndrome->slave);
+		le32_to_cpus(&sysbus1_syndrome->err_type);
+		for (i = 0; i < 8; i++)
+			le16_to_cpus(&sysbus1_syndrome->addr[i]);
+		break;
+	case SYS_BUS2:
+		le16_to_cpus(&sysbus2_syndrome->op_type);
+		le16_to_cpus(&sysbus2_syndrome->len);
+		le16_to_cpus(&sysbus2_syndrome->redirect);
+		le16_to_cpus(&sysbus2_syndrome->path);
+		le32_to_cpus(&sysbus2_syndrome->ext_id);
+		le32_to_cpus(&sysbus2_syndrome->lsb2);
+		le32_to_cpus(&sysbus2_syndrome->msb2);
+		le32_to_cpus(&sysbus2_syndrome->lsb3);
+		le32_to_cpus(&sysbus2_syndrome->msb3);
+		break;
+	case NSP_MEM:
+		for (i = 0; i < 8; i++)
+			le32_to_cpus(&nsp_syndrome->error_address[i]);
+		break;
+	case TSENS:
+		le32_to_cpus(&tsens_syndrome->threshold_type);
+		le32_to_cpus(&tsens_syndrome->temp);
+		break;
+	}
+}
+
+static void decode_ras_msg(struct qaic_device *qdev, struct ras_data *msg)
+{
+	struct sysbus1_syndrome *sysbus1_syndrome = (struct sysbus1_syndrome *)&msg->syndrome[0];
+	struct sysbus2_syndrome *sysbus2_syndrome = (struct sysbus2_syndrome *)&msg->syndrome[0];
+	struct soc_mem_syndrome *soc_syndrome = (struct soc_mem_syndrome *)&msg->syndrome[0];
+	struct nsp_mem_syndrome *nsp_syndrome = (struct nsp_mem_syndrome *)&msg->syndrome[0];
+	struct tsens_syndrome *tsens_syndrome = (struct tsens_syndrome *)&msg->syndrome[0];
+	struct pcie_syndrome *pcie_syndrome = (struct pcie_syndrome *)&msg->syndrome[0];
+	struct ddr_syndrome *ddr_syndrome = (struct ddr_syndrome *)&msg->syndrome[0];
+	char *class;
+	char *level;
+
+	if (msg->magic != MAGIC) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid magic %x\n", msg->magic);
+		return;
+	}
+
+	if (!msg->ver || msg->ver > VERSION) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid version %d\n", msg->ver);
+		return;
+	}
+
+	if (msg->type != MSG_PUSH) {
+		pci_warn(qdev->pdev, "Dropping non-PUSH RAS message\n");
+		return;
+	}
+
+	if (msg->len != sizeof(*msg) - HDR_SZ) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid len %d\n", msg->len);
+		return;
+	}
+
+	if (msg->err_type >= ERR_TYPE_MAX) {
+		pci_warn(qdev->pdev, "Dropping RAS message with err type %d\n", msg->err_type);
+		return;
+	}
+
+	if (msg->err_type == UE)
+		level = KERN_ERR;
+	else
+		level = KERN_WARNING;
+
+	switch (msg->source) {
+	case SOC_MEM:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   soc_syndrome->error_address[0],
+			   soc_syndrome->error_address[1],
+			   soc_syndrome->error_address[2],
+			   soc_syndrome->error_address[3],
+			   soc_syndrome->error_address[4],
+			   soc_syndrome->error_address[5],
+			   soc_syndrome->error_address[6],
+			   soc_syndrome->error_address[7]);
+		break;
+	case PCIE:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold);
+
+		switch (msg->err_type) {
+		case CE:
+			/*
+			 * Modeled after AER prints. This continues the dev_printk() from a few
+			 * lines up. We reduce duplication of code, but also avoid re-printing the
+			 * PCI device info so that the end result looks uniform to the log user.
+			 */
+			printk(KERN_WARNING pr_fmt("Syndrome:\n    Bad TLP count %d\n    Bad DLLP count %d\n    Replay Rollover count %d\n    Replay Timeout count %d\n    Recv Error count %d\n    Internal CE count %d\n"),
+			       pcie_syndrome->bad_tlp,
+			       pcie_syndrome->bad_dllp,
+			       pcie_syndrome->replay_rollover,
+			       pcie_syndrome->replay_timeout,
+			       pcie_syndrome->rx_err,
+			       pcie_syndrome->internal_ce_count);
+			if (msg->ver > 0x1)
+				pr_warn("    Power break %s\n",
+					pcie_syndrome->flag & POWER_BREAK ? "ON" : "OFF");
+			break;
+		case UE:
+			printk(KERN_ERR pr_fmt("Syndrome:\n    Index %d\n    Address 0x%x\n"),
+			       pcie_syndrome->index, pcie_syndrome->addr);
+			break;
+		case UE_NF:
+			printk(KERN_WARNING pr_fmt("Syndrome:\n    FC timeout count %d\n    Poisoned TLP count %d\n    ECRC error count %d\n    Unsupported request count %d\n    Completer abort count %d\n    Completion timeout count %d\n"),
+			       pcie_syndrome->fc_timeout,
+			       pcie_syndrome->poison_tlp,
+			       pcie_syndrome->ecrc_err,
+			       pcie_syndrome->unsupported_req,
+			       pcie_syndrome->completer_abort,
+			       pcie_syndrome->completion_timeout);
+			break;
+		default:
+			break;
+		}
+		break;
+	case DDR:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    Instance %d\n    Count %d\n    Data 31_0 0x%x 0x%x\n    Data 63_32 0x%x 0x%x\n    Data 95_64 0x%x 0x%x\n    Data 127_96 0x%x 0x%x\n    Parity bits 0x%x\n    Address msb 0x%x\n    Address lsb 0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   ddr_syndrome->instance,
+			   ddr_syndrome->count,
+			   ddr_syndrome->data_31_0[1],
+			   ddr_syndrome->data_31_0[0],
+			   ddr_syndrome->data_63_32[1],
+			   ddr_syndrome->data_63_32[0],
+			   ddr_syndrome->data_95_64[1],
+			   ddr_syndrome->data_95_64[0],
+			   ddr_syndrome->data_127_96[1],
+			   ddr_syndrome->data_127_96[0],
+			   ddr_syndrome->parity_bits,
+			   ddr_syndrome->addr_msb,
+			   ddr_syndrome->addr_lsb);
+		break;
+	case SYS_BUS1:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    instance %d\n    %s\n    err_type %d\n    address0 0x%x\n    address1 0x%x\n    address2 0x%x\n    address3 0x%x\n    address4 0x%x\n    address5 0x%x\n    address6 0x%x\n    address7 0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   sysbus1_syndrome->instance,
+			   sysbus1_syndrome->slave ? "Slave" : "Master",
+			   sysbus1_syndrome->err_type,
+			   sysbus1_syndrome->addr[0],
+			   sysbus1_syndrome->addr[1],
+			   sysbus1_syndrome->addr[2],
+			   sysbus1_syndrome->addr[3],
+			   sysbus1_syndrome->addr[4],
+			   sysbus1_syndrome->addr[5],
+			   sysbus1_syndrome->addr[6],
+			   sysbus1_syndrome->addr[7]);
+		break;
+	case SYS_BUS2:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    instance %d\n    valid %d\n    word error %d\n    non-secure %d\n    opc %d\n    error code %d\n    transaction type %d\n    address space %d\n    operation type %d\n    len %d\n    redirect %d\n    path %d\n    ext_id %d\n    lsb2 %d\n    msb2 %d\n    lsb3 %d\n    msb3 %d\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   sysbus2_syndrome->instance,
+			   sysbus2_syndrome->valid,
+			   sysbus2_syndrome->word_error,
+			   sysbus2_syndrome->non_secure,
+			   sysbus2_syndrome->opc,
+			   sysbus2_syndrome->error_code,
+			   sysbus2_syndrome->trans_type,
+			   sysbus2_syndrome->addr_space,
+			   sysbus2_syndrome->op_type,
+			   sysbus2_syndrome->len,
+			   sysbus2_syndrome->redirect,
+			   sysbus2_syndrome->path,
+			   sysbus2_syndrome->ext_id,
+			   sysbus2_syndrome->lsb2,
+			   sysbus2_syndrome->msb2,
+			   sysbus2_syndrome->lsb3,
+			   sysbus2_syndrome->msb3);
+		break;
+	case NSP_MEM:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    NSP ID %d\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   nsp_syndrome->nsp_id,
+			   nsp_syndrome->error_address[0],
+			   nsp_syndrome->error_address[1],
+			   nsp_syndrome->error_address[2],
+			   nsp_syndrome->error_address[3],
+			   nsp_syndrome->error_address[4],
+			   nsp_syndrome->error_address[5],
+			   nsp_syndrome->error_address[6],
+			   nsp_syndrome->error_address[7]);
+		break;
+	case TSENS:
+		if (tsens_syndrome->threshold_type >= NUM_TEMP_LVL) {
+			pci_warn(qdev->pdev, "Dropping RAS message with invalid temp threshold %d\n",
+				 tsens_syndrome->threshold_type);
+			break;
+		}
+
+		if (msg->err_type)
+			class = "Fatal";
+		else if (tsens_syndrome->threshold_type)
+			class = "Critical";
+		else
+			class = "Warning";
+
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    %s threshold\n    %d deg C\n",
+			   class,
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   threshold_type_str[tsens_syndrome->threshold_type],
+			   tsens_syndrome->temp);
+		break;
+	}
+
+	/* Uncorrectable errors are fatal */
+	if (msg->err_type == UE)
+		mhi_soc_reset(qdev->mhi_cntrl);
+
+	switch (msg->err_type) {
+	case CE:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ce_count++;
+		break;
+	case UE:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ue_count++;
+		break;
+	case UE_NF:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ue_nf_count++;
+		break;
+	default:
+		/* not possible */
+		break;
+	}
+}
+
+static ssize_t ce_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ce_count);
+}
+
+static ssize_t ue_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ue_count);
+}
+
+static ssize_t ue_nonfatal_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ue_nf_count);
+}
+
+static DEVICE_ATTR_RO(ce_count);
+static DEVICE_ATTR_RO(ue_count);
+static DEVICE_ATTR_RO(ue_nonfatal_count);
+
+static struct attribute *ras_attrs[] = {
+	&dev_attr_ce_count.attr,
+	&dev_attr_ue_count.attr,
+	&dev_attr_ue_nonfatal_count.attr,
+	NULL,
+};
+
+static struct attribute_group ras_group = {
+	.attrs = ras_attrs,
+};
+
+static int qaic_ras_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	struct ras_data *resp;
+	int ret;
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		return ret;
+
+	resp = kzalloc(sizeof(*resp), GFP_KERNEL);
+	if (!resp) {
+		mhi_unprepare_from_transfer(mhi_dev);
+		return -ENOMEM;
+	}
+
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, resp, sizeof(*resp), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		mhi_unprepare_from_transfer(mhi_dev);
+		return ret;
+	}
+
+	ret = device_add_group(&qdev->pdev->dev, &ras_group);
+	if (ret) {
+		mhi_unprepare_from_transfer(mhi_dev);
+		pci_dbg(qdev->pdev, "ras add sysfs failed %d\n", ret);
+		return ret;
+	}
+
+	dev_set_drvdata(&mhi_dev->dev, qdev);
+	qdev->ras_ch = mhi_dev;
+
+	return ret;
+}
+
+static void qaic_ras_mhi_remove(struct mhi_device *mhi_dev)
+{
+	struct qaic_device *qdev;
+
+	qdev = dev_get_drvdata(&mhi_dev->dev);
+	qdev->ras_ch = NULL;
+	device_remove_group(&qdev->pdev->dev, &ras_group);
+	mhi_unprepare_from_transfer(mhi_dev);
+}
+
+static void qaic_ras_mhi_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result) {}
+
+static void qaic_ras_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct qaic_device *qdev = dev_get_drvdata(&mhi_dev->dev);
+	struct ras_data *msg = mhi_result->buf_addr;
+	int ret;
+
+	if (mhi_result->transaction_status) {
+		kfree(msg);
+		return;
+	}
+
+	ras_msg_to_cpu(msg);
+	decode_ras_msg(qdev, msg);
+
+	ret = mhi_queue_buf(qdev->ras_ch, DMA_FROM_DEVICE, msg, sizeof(*msg), MHI_EOT);
+	if (ret) {
+		dev_err(&mhi_dev->dev, "Cannot requeue RAS recv buf %d\n", ret);
+		kfree(msg);
+	}
+}
+
+static const struct mhi_device_id qaic_ras_mhi_match_table[] = {
+	{ .chan = "QAIC_STATUS", },
+	{},
+};
+
+static struct mhi_driver qaic_ras_mhi_driver = {
+	.id_table = qaic_ras_mhi_match_table,
+	.remove = qaic_ras_mhi_remove,
+	.probe = qaic_ras_mhi_probe,
+	.ul_xfer_cb = qaic_ras_mhi_ul_xfer_cb,
+	.dl_xfer_cb = qaic_ras_mhi_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_ras",
+	},
+};
+
+int qaic_ras_register(void)
+{
+	return mhi_driver_register(&qaic_ras_mhi_driver);
+}
+
+void qaic_ras_unregister(void)
+{
+	mhi_driver_unregister(&qaic_ras_mhi_driver);
+}
diff --git a/drivers/accel/qaic/qaic_ras.h b/drivers/accel/qaic/qaic_ras.h
new file mode 100644
index 000000000000..d44a4eeeb060
--- /dev/null
+++ b/drivers/accel/qaic/qaic_ras.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2020, The Linux Foundation. All rights reserved. */
+
+#ifndef __QAIC_RAS_H__
+#define __QAIC_RAS_H__
+
+int qaic_ras_register(void);
+void qaic_ras_unregister(void);
+
+#endif /* __QAIC_RAS_H__ */
diff --git a/drivers/accel/qaic/qaic_timesync.c b/drivers/accel/qaic/qaic_timesync.c
new file mode 100644
index 000000000000..3fac540f8e03
--- /dev/null
+++ b/drivers/accel/qaic/qaic_timesync.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/mhi.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/time64.h>
+#include <linux/timer.h>
+
+#include "qaic.h"
+#include "qaic_timesync.h"
+
+#define QTIMER_REG_OFFSET			0xa28
+#define QAIC_TIMESYNC_SIGNATURE			0x55aa
+#define QAIC_CONV_QTIMER_TO_US(qtimer)		(mul_u64_u32_div(qtimer, 10, 192))
+
+static unsigned int timesync_delay_ms = 1000; /* 1 sec default */
+module_param(timesync_delay_ms, uint, 0600);
+MODULE_PARM_DESC(timesync_delay_ms, "Delay in ms between two consecutive timesync operations");
+
+enum qts_msg_type {
+	QAIC_TS_CMD_TO_HOST,
+	QAIC_TS_SYNC_REQ,
+	QAIC_TS_ACK_TO_HOST,
+	QAIC_TS_MSG_TYPE_MAX
+};
+
+/**
+ * struct qts_hdr - Timesync message header structure.
+ * @signature: Unique signature to identify the timesync message.
+ * @reserved_1: Reserved for future use.
+ * @reserved_2: Reserved for future use.
+ * @msg_type: sub-type of the timesync message.
+ * @reserved_3: Reserved for future use.
+ */
+struct qts_hdr {
+	__le16	signature;
+	__le16	reserved_1;
+	u8	reserved_2;
+	u8	msg_type;
+	__le16	reserved_3;
+} __packed;
+
+/**
+ * struct qts_timeval - Structure to carry time information.
+ * @tv_sec: Seconds part of the time.
+ * @tv_usec: uS (microseconds) part of the time.
+ */
+struct qts_timeval {
+	__le64	tv_sec;
+	__le64	tv_usec;
+} __packed;
+
+/**
+ * struct qts_host_time_sync_msg_data - Structure to denote the timesync message.
+ * @header: Header of the timesync message.
+ * @data: Time information.
+ */
+struct qts_host_time_sync_msg_data {
+	struct	qts_hdr header;
+	struct	qts_timeval data;
+} __packed;
+
+/**
+ * struct mqts_dev - MHI QAIC Timesync Control device.
+ * @qdev: Pointer to the root device struct driven by QAIC driver.
+ * @mhi_dev: Pointer to associated MHI device.
+ * @timer: Timer handle used for timesync.
+ * @qtimer_addr: Device QTimer register pointer.
+ * @buff_in_use: atomic variable to track if the sync_msg buffer is in use.
+ * @dev: Device pointer to qdev->pdev->dev stored for easy access.
+ * @sync_msg: Buffer used to send timesync message over MHI.
+ */
+struct mqts_dev {
+	struct qaic_device *qdev;
+	struct mhi_device *mhi_dev;
+	struct timer_list timer;
+	void __iomem *qtimer_addr;
+	atomic_t buff_in_use;
+	struct device *dev;
+	struct qts_host_time_sync_msg_data *sync_msg;
+};
+
+struct qts_resp_msg {
+	struct qts_hdr	hdr;
+} __packed;
+
+struct qts_resp {
+	struct qts_resp_msg	data;
+	struct work_struct	work;
+	struct qaic_device	*qdev;
+};
+
+#ifdef readq
+static u64 read_qtimer(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#else
+static u64 read_qtimer(const volatile void __iomem *addr)
+{
+	u64 low, high;
+
+	low = readl(addr);
+	high = readl(addr + sizeof(u32));
+	return low | (high << 32);
+}
+#endif
+
+static void qaic_timesync_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	dev_dbg(mqtsdev->dev, "%s status: %d xfer_len: %zu\n", __func__,
+		mhi_result->transaction_status, mhi_result->bytes_xferd);
+
+	atomic_set(&mqtsdev->buff_in_use, 0);
+}
+
+static void qaic_timesync_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	dev_err(mqtsdev->dev, "%s no data expected on dl channel\n", __func__);
+}
+
+static void qaic_timesync_timer(struct timer_list *t)
+{
+	struct mqts_dev *mqtsdev = timer_container_of(mqtsdev, t, timer);
+	struct qts_host_time_sync_msg_data *sync_msg;
+	u64 device_qtimer_us;
+	u64 device_qtimer;
+	u64 host_time_us;
+	u64 offset_us;
+	u64 host_sec;
+	int ret;
+
+	if (atomic_read(&mqtsdev->buff_in_use)) {
+		dev_dbg(mqtsdev->dev, "%s buffer not free, schedule next cycle\n", __func__);
+		goto mod_timer;
+	}
+	atomic_set(&mqtsdev->buff_in_use, 1);
+
+	sync_msg = mqtsdev->sync_msg;
+	sync_msg->header.signature = cpu_to_le16(QAIC_TIMESYNC_SIGNATURE);
+	sync_msg->header.msg_type = QAIC_TS_SYNC_REQ;
+	/* Read host UTC time and convert to uS*/
+	host_time_us = div_u64(ktime_get_real_ns(), NSEC_PER_USEC);
+	device_qtimer = read_qtimer(mqtsdev->qtimer_addr);
+	device_qtimer_us = QAIC_CONV_QTIMER_TO_US(device_qtimer);
+	/* Offset between host UTC and device time */
+	offset_us = host_time_us - device_qtimer_us;
+
+	host_sec = div_u64(offset_us, USEC_PER_SEC);
+	sync_msg->data.tv_usec = cpu_to_le64(offset_us - host_sec * USEC_PER_SEC);
+	sync_msg->data.tv_sec = cpu_to_le64(host_sec);
+	ret = mhi_queue_buf(mqtsdev->mhi_dev, DMA_TO_DEVICE, sync_msg, sizeof(*sync_msg), MHI_EOT);
+	if (ret && (ret != -EAGAIN)) {
+		dev_err(mqtsdev->dev, "%s unable to queue to mhi:%d\n", __func__, ret);
+		return;
+	} else if (ret == -EAGAIN) {
+		atomic_set(&mqtsdev->buff_in_use, 0);
+	}
+
+mod_timer:
+	ret = mod_timer(t, jiffies + msecs_to_jiffies(timesync_delay_ms));
+	if (ret)
+		dev_err(mqtsdev->dev, "%s mod_timer error:%d\n", __func__, ret);
+}
+
+static int qaic_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	struct mqts_dev *mqtsdev;
+	struct timer_list *timer;
+	int ret;
+
+	mqtsdev = kzalloc(sizeof(*mqtsdev), GFP_KERNEL);
+	if (!mqtsdev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	timer = &mqtsdev->timer;
+	mqtsdev->mhi_dev = mhi_dev;
+	mqtsdev->qdev = qdev;
+	mqtsdev->dev = &qdev->pdev->dev;
+
+	mqtsdev->sync_msg = kzalloc(sizeof(*mqtsdev->sync_msg), GFP_KERNEL);
+	if (!mqtsdev->sync_msg) {
+		ret = -ENOMEM;
+		goto free_mqts_dev;
+	}
+	atomic_set(&mqtsdev->buff_in_use, 0);
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		goto free_sync_msg;
+
+	/* Qtimer register pointer */
+	mqtsdev->qtimer_addr = qdev->bar_mhi + QTIMER_REG_OFFSET;
+	timer_setup(timer, qaic_timesync_timer, 0);
+	timer->expires = jiffies + msecs_to_jiffies(timesync_delay_ms);
+	add_timer(timer);
+	dev_set_drvdata(&mhi_dev->dev, mqtsdev);
+
+	return 0;
+
+free_sync_msg:
+	kfree(mqtsdev->sync_msg);
+free_mqts_dev:
+	kfree(mqtsdev);
+out:
+	return ret;
+};
+
+static void qaic_timesync_remove(struct mhi_device *mhi_dev)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	timer_delete_sync(&mqtsdev->timer);
+	mhi_unprepare_from_transfer(mqtsdev->mhi_dev);
+	kfree(mqtsdev->sync_msg);
+	kfree(mqtsdev);
+}
+
+static const struct mhi_device_id qaic_timesync_match_table[] = {
+	{ .chan = "QAIC_TIMESYNC_PERIODIC"},
+	{},
+};
+
+MODULE_DEVICE_TABLE(mhi, qaic_timesync_match_table);
+
+static struct mhi_driver qaic_timesync_driver = {
+	.id_table = qaic_timesync_match_table,
+	.remove = qaic_timesync_remove,
+	.probe = qaic_timesync_probe,
+	.ul_xfer_cb = qaic_timesync_ul_xfer_cb,
+	.dl_xfer_cb = qaic_timesync_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_timesync_periodic",
+	},
+};
+
+static void qaic_boot_timesync_worker(struct work_struct *work)
+{
+	struct qts_resp *resp = container_of(work, struct qts_resp, work);
+	struct qts_host_time_sync_msg_data *req;
+	struct qts_resp_msg data = resp->data;
+	struct qaic_device *qdev = resp->qdev;
+	struct mhi_device *mhi_dev;
+	struct timespec64 ts;
+	int ret;
+
+	mhi_dev = qdev->qts_ch;
+	/* Queue the response message beforehand to avoid race conditions */
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, &resp->data, sizeof(resp->data), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		dev_warn(&mhi_dev->dev, "Failed to re-queue response buffer %d\n", ret);
+		return;
+	}
+
+	switch (data.hdr.msg_type) {
+	case QAIC_TS_CMD_TO_HOST:
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req)
+			break;
+
+		req->header = data.hdr;
+		req->header.msg_type = QAIC_TS_SYNC_REQ;
+		ktime_get_real_ts64(&ts);
+		req->data.tv_sec = cpu_to_le64(ts.tv_sec);
+		req->data.tv_usec = cpu_to_le64(div_u64(ts.tv_nsec, NSEC_PER_USEC));
+
+		ret = mhi_queue_buf(mhi_dev, DMA_TO_DEVICE, req, sizeof(*req), MHI_EOT);
+		if (ret) {
+			kfree(req);
+			dev_dbg(&mhi_dev->dev, "Failed to send request message. Error %d\n", ret);
+		}
+		break;
+	case QAIC_TS_ACK_TO_HOST:
+		dev_dbg(&mhi_dev->dev, "ACK received from device\n");
+		break;
+	default:
+		dev_err(&mhi_dev->dev, "Invalid message type %u.\n", data.hdr.msg_type);
+	}
+}
+
+static int qaic_boot_timesync_queue_resp(struct mhi_device *mhi_dev, struct qaic_device *qdev)
+{
+	struct qts_resp *resp;
+	int ret;
+
+	resp = kzalloc(sizeof(*resp), GFP_KERNEL);
+	if (!resp)
+		return -ENOMEM;
+
+	resp->qdev = qdev;
+	INIT_WORK(&resp->work, qaic_boot_timesync_worker);
+
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, &resp->data, sizeof(resp->data), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		dev_warn(&mhi_dev->dev, "Failed to queue response buffer %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qaic_boot_timesync_remove(struct mhi_device *mhi_dev)
+{
+	struct qaic_device *qdev;
+
+	qdev = dev_get_drvdata(&mhi_dev->dev);
+	mhi_unprepare_from_transfer(qdev->qts_ch);
+	qdev->qts_ch = NULL;
+}
+
+static int qaic_boot_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	int ret;
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		return ret;
+
+	qdev->qts_ch = mhi_dev;
+	dev_set_drvdata(&mhi_dev->dev, qdev);
+
+	ret = qaic_boot_timesync_queue_resp(mhi_dev, qdev);
+	if (ret) {
+		dev_set_drvdata(&mhi_dev->dev, NULL);
+		qdev->qts_ch = NULL;
+		mhi_unprepare_from_transfer(mhi_dev);
+	}
+
+	return ret;
+}
+
+static void qaic_boot_timesync_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	kfree(mhi_result->buf_addr);
+}
+
+static void qaic_boot_timesync_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct qts_resp *resp = container_of(mhi_result->buf_addr, struct qts_resp, data);
+
+	if (mhi_result->transaction_status || mhi_result->bytes_xferd != sizeof(resp->data)) {
+		kfree(resp);
+		return;
+	}
+
+	queue_work(resp->qdev->qts_wq, &resp->work);
+}
+
+static const struct mhi_device_id qaic_boot_timesync_match_table[] = {
+	{ .chan = "QAIC_TIMESYNC"},
+	{},
+};
+
+static struct mhi_driver qaic_boot_timesync_driver = {
+	.id_table = qaic_boot_timesync_match_table,
+	.remove = qaic_boot_timesync_remove,
+	.probe = qaic_boot_timesync_probe,
+	.ul_xfer_cb = qaic_boot_timesync_ul_xfer_cb,
+	.dl_xfer_cb = qaic_boot_timesync_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_timesync",
+	},
+};
+
+int qaic_timesync_init(void)
+{
+	int ret;
+
+	ret = mhi_driver_register(&qaic_timesync_driver);
+	if (ret)
+		return ret;
+	ret = mhi_driver_register(&qaic_boot_timesync_driver);
+
+	return ret;
+}
+
+void qaic_timesync_deinit(void)
+{
+	mhi_driver_unregister(&qaic_boot_timesync_driver);
+	mhi_driver_unregister(&qaic_timesync_driver);
+}
diff --git a/drivers/accel/qaic/qaic_timesync.h b/drivers/accel/qaic/qaic_timesync.h
new file mode 100644
index 000000000000..851b7acd43bb
--- /dev/null
+++ b/drivers/accel/qaic/qaic_timesync.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef __QAIC_TIMESYNC_H__
+#define __QAIC_TIMESYNC_H__
+
+int qaic_timesync_init(void);
+void qaic_timesync_deinit(void);
+#endif /* __QAIC_TIMESYNC_H__ */
diff --git a/drivers/accel/qaic/sahara.c b/drivers/accel/qaic/sahara.c
new file mode 100644
index 000000000000..3ebcc1f7ff58
--- /dev/null
+++ b/drivers/accel/qaic/sahara.c
@@ -0,0 +1,857 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+#include <linux/limits.h>
+#include <linux/mhi.h>
+#include <linux/minmax.h>
+#include <linux/mod_devicetable.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <linux/workqueue.h>
+
+#include "sahara.h"
+
+#define SAHARA_HELLO_CMD		0x1  /* Min protocol version 1.0 */
+#define SAHARA_HELLO_RESP_CMD		0x2  /* Min protocol version 1.0 */
+#define SAHARA_READ_DATA_CMD		0x3  /* Min protocol version 1.0 */
+#define SAHARA_END_OF_IMAGE_CMD		0x4  /* Min protocol version 1.0 */
+#define SAHARA_DONE_CMD			0x5  /* Min protocol version 1.0 */
+#define SAHARA_DONE_RESP_CMD		0x6  /* Min protocol version 1.0 */
+#define SAHARA_RESET_CMD		0x7  /* Min protocol version 1.0 */
+#define SAHARA_RESET_RESP_CMD		0x8  /* Min protocol version 1.0 */
+#define SAHARA_MEM_DEBUG_CMD		0x9  /* Min protocol version 2.0 */
+#define SAHARA_MEM_READ_CMD		0xa  /* Min protocol version 2.0 */
+#define SAHARA_CMD_READY_CMD		0xb  /* Min protocol version 2.1 */
+#define SAHARA_SWITCH_MODE_CMD		0xc  /* Min protocol version 2.1 */
+#define SAHARA_EXECUTE_CMD		0xd  /* Min protocol version 2.1 */
+#define SAHARA_EXECUTE_RESP_CMD		0xe  /* Min protocol version 2.1 */
+#define SAHARA_EXECUTE_DATA_CMD		0xf  /* Min protocol version 2.1 */
+#define SAHARA_MEM_DEBUG64_CMD		0x10 /* Min protocol version 2.5 */
+#define SAHARA_MEM_READ64_CMD		0x11 /* Min protocol version 2.5 */
+#define SAHARA_READ_DATA64_CMD		0x12 /* Min protocol version 2.8 */
+#define SAHARA_RESET_STATE_CMD		0x13 /* Min protocol version 2.9 */
+#define SAHARA_WRITE_DATA_CMD		0x14 /* Min protocol version 3.0 */
+
+#define SAHARA_PACKET_MAX_SIZE		0xffffU /* MHI_MAX_MTU */
+#define SAHARA_TRANSFER_MAX_SIZE	0x80000
+#define SAHARA_READ_MAX_SIZE		0xfff0U /* Avoid unaligned requests */
+#define SAHARA_NUM_TX_BUF		DIV_ROUND_UP(SAHARA_TRANSFER_MAX_SIZE,\
+							SAHARA_PACKET_MAX_SIZE)
+#define SAHARA_IMAGE_ID_NONE		U32_MAX
+
+#define SAHARA_VERSION			2
+#define SAHARA_SUCCESS			0
+#define SAHARA_TABLE_ENTRY_STR_LEN	20
+
+#define SAHARA_MODE_IMAGE_TX_PENDING	0x0
+#define SAHARA_MODE_IMAGE_TX_COMPLETE	0x1
+#define SAHARA_MODE_MEMORY_DEBUG	0x2
+#define SAHARA_MODE_COMMAND		0x3
+
+#define SAHARA_HELLO_LENGTH		0x30
+#define SAHARA_READ_DATA_LENGTH		0x14
+#define SAHARA_END_OF_IMAGE_LENGTH	0x10
+#define SAHARA_DONE_LENGTH		0x8
+#define SAHARA_RESET_LENGTH		0x8
+#define SAHARA_MEM_DEBUG64_LENGTH	0x18
+#define SAHARA_MEM_READ64_LENGTH	0x18
+
+struct sahara_packet {
+	__le32 cmd;
+	__le32 length;
+
+	union {
+		struct {
+			__le32 version;
+			__le32 version_compat;
+			__le32 max_length;
+			__le32 mode;
+		} hello;
+		struct {
+			__le32 version;
+			__le32 version_compat;
+			__le32 status;
+			__le32 mode;
+		} hello_resp;
+		struct {
+			__le32 image;
+			__le32 offset;
+			__le32 length;
+		} read_data;
+		struct {
+			__le32 image;
+			__le32 status;
+		} end_of_image;
+		struct {
+			__le64 table_address;
+			__le64 table_length;
+		} memory_debug64;
+		struct {
+			__le64 memory_address;
+			__le64 memory_length;
+		} memory_read64;
+	};
+};
+
+struct sahara_debug_table_entry64 {
+	__le64	type;
+	__le64	address;
+	__le64	length;
+	char	description[SAHARA_TABLE_ENTRY_STR_LEN];
+	char	filename[SAHARA_TABLE_ENTRY_STR_LEN];
+};
+
+struct sahara_dump_table_entry {
+	u64	type;
+	u64	address;
+	u64	length;
+	char	description[SAHARA_TABLE_ENTRY_STR_LEN];
+	char	filename[SAHARA_TABLE_ENTRY_STR_LEN];
+};
+
+#define SAHARA_DUMP_V1_MAGIC 0x1234567890abcdef
+#define SAHARA_DUMP_V1_VER   1
+struct sahara_memory_dump_meta_v1 {
+	u64	magic;
+	u64	version;
+	u64	dump_size;
+	u64	table_size;
+};
+
+/*
+ * Layout of crashdump provided to user via devcoredump
+ *              +------------------------------------------+
+ *              |         Crashdump Meta structure         |
+ *              | type: struct sahara_memory_dump_meta_v1  |
+ *              +------------------------------------------+
+ *              |             Crashdump Table              |
+ *              | type: array of struct                    |
+ *              |       sahara_dump_table_entry            |
+ *              |                                          |
+ *              |                                          |
+ *              +------------------------------------------+
+ *              |                Crashdump                 |
+ *              |                                          |
+ *              |                                          |
+ *              |                                          |
+ *              |                                          |
+ *              |                                          |
+ *              +------------------------------------------+
+ *
+ * First is the metadata header. Userspace can use the magic number to verify
+ * the content type, and then check the version for the rest of the format.
+ * New versions should keep the magic number location/value, and version
+ * location, but increment the version value.
+ *
+ * For v1, the metadata lists the size of the entire dump (header + table +
+ * dump) and the size of the table. Then the dump image table, which describes
+ * the contents of the dump. Finally all the images are listed in order, with
+ * no deadspace in between. Userspace can use the sizes listed in the image
+ * table to reconstruct the individual images.
+ */
+
+struct sahara_context {
+	struct sahara_packet		*tx[SAHARA_NUM_TX_BUF];
+	struct sahara_packet		*rx;
+	struct work_struct		fw_work;
+	struct work_struct		dump_work;
+	struct mhi_device		*mhi_dev;
+	const char * const		*image_table;
+	u32				table_size;
+	u32				active_image_id;
+	const struct firmware		*firmware;
+	u64				dump_table_address;
+	u64				dump_table_length;
+	size_t				rx_size;
+	size_t				rx_size_requested;
+	void				*mem_dump;
+	size_t				mem_dump_sz;
+	struct sahara_dump_table_entry	*dump_image;
+	u64				dump_image_offset;
+	void				*mem_dump_freespace;
+	u64				dump_images_left;
+	bool				is_mem_dump_mode;
+};
+
+static const char * const aic100_image_table[] = {
+	[1]  = "qcom/aic100/fw1.bin",
+	[2]  = "qcom/aic100/fw2.bin",
+	[4]  = "qcom/aic100/fw4.bin",
+	[5]  = "qcom/aic100/fw5.bin",
+	[6]  = "qcom/aic100/fw6.bin",
+	[8]  = "qcom/aic100/fw8.bin",
+	[9]  = "qcom/aic100/fw9.bin",
+	[10] = "qcom/aic100/fw10.bin",
+};
+
+static const char * const aic200_image_table[] = {
+	[5]  = "qcom/aic200/uefi.elf",
+	[12] = "qcom/aic200/aic200-nsp.bin",
+	[23] = "qcom/aic200/aop.mbn",
+	[32] = "qcom/aic200/tz.mbn",
+	[33] = "qcom/aic200/hypvm.mbn",
+	[39] = "qcom/aic200/aic200_abl.elf",
+	[40] = "qcom/aic200/apdp.mbn",
+	[41] = "qcom/aic200/devcfg.mbn",
+	[42] = "qcom/aic200/sec.elf",
+	[43] = "qcom/aic200/aic200-hlos.elf",
+	[49] = "qcom/aic200/shrm.elf",
+	[50] = "qcom/aic200/cpucp.elf",
+	[51] = "qcom/aic200/aop_devcfg.mbn",
+	[57] = "qcom/aic200/cpucp_dtbs.elf",
+	[62] = "qcom/aic200/uefi_dtbs.elf",
+	[63] = "qcom/aic200/xbl_ac_config.mbn",
+	[64] = "qcom/aic200/tz_ac_config.mbn",
+	[65] = "qcom/aic200/hyp_ac_config.mbn",
+	[66] = "qcom/aic200/pdp.elf",
+	[67] = "qcom/aic200/pdp_cdb.elf",
+	[68] = "qcom/aic200/sdi.mbn",
+	[69] = "qcom/aic200/dcd.mbn",
+	[73] = "qcom/aic200/gearvm.mbn",
+	[74] = "qcom/aic200/sti.bin",
+	[75] = "qcom/aic200/pvs.bin",
+};
+
+static int sahara_find_image(struct sahara_context *context, u32 image_id)
+{
+	int ret;
+
+	if (image_id == context->active_image_id)
+		return 0;
+
+	if (context->active_image_id != SAHARA_IMAGE_ID_NONE) {
+		dev_err(&context->mhi_dev->dev, "image id %d is not valid as %d is active\n",
+			image_id, context->active_image_id);
+		return -EINVAL;
+	}
+
+	if (image_id >= context->table_size || !context->image_table[image_id]) {
+		dev_err(&context->mhi_dev->dev, "request for unknown image: %d\n", image_id);
+		return -EINVAL;
+	}
+
+	/*
+	 * This image might be optional. The device may continue without it.
+	 * Only the device knows. Suppress error messages that could suggest an
+	 * a problem when we were actually able to continue.
+	 */
+	ret = firmware_request_nowarn(&context->firmware,
+				      context->image_table[image_id],
+				      &context->mhi_dev->dev);
+	if (ret) {
+		dev_dbg(&context->mhi_dev->dev, "request for image id %d / file %s failed %d\n",
+			image_id, context->image_table[image_id], ret);
+		return ret;
+	}
+
+	context->active_image_id = image_id;
+
+	return 0;
+}
+
+static void sahara_release_image(struct sahara_context *context)
+{
+	if (context->active_image_id != SAHARA_IMAGE_ID_NONE)
+		release_firmware(context->firmware);
+	context->active_image_id = SAHARA_IMAGE_ID_NONE;
+}
+
+static void sahara_send_reset(struct sahara_context *context)
+{
+	int ret;
+
+	context->is_mem_dump_mode = false;
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_RESET_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_RESET_LENGTH);
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_RESET_LENGTH, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to send reset response %d\n", ret);
+}
+
+static void sahara_hello(struct sahara_context *context)
+{
+	int ret;
+
+	dev_dbg(&context->mhi_dev->dev,
+		"HELLO cmd received. length:%d version:%d version_compat:%d max_length:%d mode:%d\n",
+		le32_to_cpu(context->rx->length),
+		le32_to_cpu(context->rx->hello.version),
+		le32_to_cpu(context->rx->hello.version_compat),
+		le32_to_cpu(context->rx->hello.max_length),
+		le32_to_cpu(context->rx->hello.mode));
+
+	if (le32_to_cpu(context->rx->length) != SAHARA_HELLO_LENGTH) {
+		dev_err(&context->mhi_dev->dev, "Malformed hello packet - length %d\n",
+			le32_to_cpu(context->rx->length));
+		return;
+	}
+	if (le32_to_cpu(context->rx->hello.version) != SAHARA_VERSION) {
+		dev_err(&context->mhi_dev->dev, "Unsupported hello packet - version %d\n",
+			le32_to_cpu(context->rx->hello.version));
+		return;
+	}
+
+	if (le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_IMAGE_TX_PENDING &&
+	    le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_IMAGE_TX_COMPLETE &&
+	    le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_MEMORY_DEBUG) {
+		dev_err(&context->mhi_dev->dev, "Unsupported hello packet - mode %d\n",
+			le32_to_cpu(context->rx->hello.mode));
+		return;
+	}
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_HELLO_RESP_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_HELLO_LENGTH);
+	context->tx[0]->hello_resp.version = cpu_to_le32(SAHARA_VERSION);
+	context->tx[0]->hello_resp.version_compat = cpu_to_le32(SAHARA_VERSION);
+	context->tx[0]->hello_resp.status = cpu_to_le32(SAHARA_SUCCESS);
+	context->tx[0]->hello_resp.mode = context->rx->hello_resp.mode;
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_HELLO_LENGTH, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to send hello response %d\n", ret);
+}
+
+static void sahara_read_data(struct sahara_context *context)
+{
+	u32 image_id, data_offset, data_len, pkt_data_len;
+	int ret;
+	int i;
+
+	dev_dbg(&context->mhi_dev->dev,
+		"READ_DATA cmd received. length:%d image:%d offset:%d data_length:%d\n",
+		le32_to_cpu(context->rx->length),
+		le32_to_cpu(context->rx->read_data.image),
+		le32_to_cpu(context->rx->read_data.offset),
+		le32_to_cpu(context->rx->read_data.length));
+
+	if (le32_to_cpu(context->rx->length) != SAHARA_READ_DATA_LENGTH) {
+		dev_err(&context->mhi_dev->dev, "Malformed read_data packet - length %d\n",
+			le32_to_cpu(context->rx->length));
+		return;
+	}
+
+	image_id = le32_to_cpu(context->rx->read_data.image);
+	data_offset = le32_to_cpu(context->rx->read_data.offset);
+	data_len = le32_to_cpu(context->rx->read_data.length);
+
+	ret = sahara_find_image(context, image_id);
+	if (ret) {
+		sahara_send_reset(context);
+		return;
+	}
+
+	/*
+	 * Image is released when the device is done with it via
+	 * SAHARA_END_OF_IMAGE_CMD. sahara_send_reset() will either cause the
+	 * device to retry the operation with a modification, or decide to be
+	 * done with the image and trigger SAHARA_END_OF_IMAGE_CMD.
+	 * release_image() is called from SAHARA_END_OF_IMAGE_CMD. processing
+	 * and is not needed here on error.
+	 */
+
+	if (data_len > SAHARA_TRANSFER_MAX_SIZE) {
+		dev_err(&context->mhi_dev->dev, "Malformed read_data packet - data len %d exceeds max xfer size %d\n",
+			data_len, SAHARA_TRANSFER_MAX_SIZE);
+		sahara_send_reset(context);
+		return;
+	}
+
+	if (data_offset >= context->firmware->size) {
+		dev_err(&context->mhi_dev->dev, "Malformed read_data packet - data offset %d exceeds file size %zu\n",
+			data_offset, context->firmware->size);
+		sahara_send_reset(context);
+		return;
+	}
+
+	if (size_add(data_offset, data_len) > context->firmware->size) {
+		dev_err(&context->mhi_dev->dev, "Malformed read_data packet - data offset %d and length %d exceeds file size %zu\n",
+			data_offset, data_len, context->firmware->size);
+		sahara_send_reset(context);
+		return;
+	}
+
+	for (i = 0; i < SAHARA_NUM_TX_BUF && data_len; ++i) {
+		pkt_data_len = min(data_len, SAHARA_PACKET_MAX_SIZE);
+
+		memcpy(context->tx[i], &context->firmware->data[data_offset], pkt_data_len);
+
+		data_offset += pkt_data_len;
+		data_len -= pkt_data_len;
+
+		ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE,
+				    context->tx[i], pkt_data_len,
+				    !data_len ? MHI_EOT : MHI_CHAIN);
+		if (ret) {
+			dev_err(&context->mhi_dev->dev, "Unable to send read_data response %d\n",
+				ret);
+			return;
+		}
+	}
+}
+
+static void sahara_end_of_image(struct sahara_context *context)
+{
+	int ret;
+
+	dev_dbg(&context->mhi_dev->dev,
+		"END_OF_IMAGE cmd received. length:%d image:%d status:%d\n",
+		le32_to_cpu(context->rx->length),
+		le32_to_cpu(context->rx->end_of_image.image),
+		le32_to_cpu(context->rx->end_of_image.status));
+
+	if (le32_to_cpu(context->rx->length) != SAHARA_END_OF_IMAGE_LENGTH) {
+		dev_err(&context->mhi_dev->dev, "Malformed end_of_image packet - length %d\n",
+			le32_to_cpu(context->rx->length));
+		return;
+	}
+
+	if (context->active_image_id != SAHARA_IMAGE_ID_NONE &&
+	    le32_to_cpu(context->rx->end_of_image.image) != context->active_image_id) {
+		dev_err(&context->mhi_dev->dev, "Malformed end_of_image packet - image %d is not the active image\n",
+			le32_to_cpu(context->rx->end_of_image.image));
+		return;
+	}
+
+	sahara_release_image(context);
+
+	if (le32_to_cpu(context->rx->end_of_image.status))
+		return;
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_DONE_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_DONE_LENGTH);
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_DONE_LENGTH, MHI_EOT);
+	if (ret)
+		dev_dbg(&context->mhi_dev->dev, "Unable to send done response %d\n", ret);
+}
+
+static void sahara_memory_debug64(struct sahara_context *context)
+{
+	int ret;
+
+	dev_dbg(&context->mhi_dev->dev,
+		"MEMORY DEBUG64 cmd received. length:%d table_address:%#llx table_length:%#llx\n",
+		le32_to_cpu(context->rx->length),
+		le64_to_cpu(context->rx->memory_debug64.table_address),
+		le64_to_cpu(context->rx->memory_debug64.table_length));
+
+	if (le32_to_cpu(context->rx->length) != SAHARA_MEM_DEBUG64_LENGTH) {
+		dev_err(&context->mhi_dev->dev, "Malformed memory debug64 packet - length %d\n",
+			le32_to_cpu(context->rx->length));
+		return;
+	}
+
+	context->dump_table_address = le64_to_cpu(context->rx->memory_debug64.table_address);
+	context->dump_table_length = le64_to_cpu(context->rx->memory_debug64.table_length);
+
+	if (context->dump_table_length % sizeof(struct sahara_debug_table_entry64) != 0 ||
+	    !context->dump_table_length) {
+		dev_err(&context->mhi_dev->dev, "Malformed memory debug64 packet - table length %lld\n",
+			context->dump_table_length);
+		return;
+	}
+
+	/*
+	 * From this point, the protocol flips. We make memory_read requests to
+	 * the device, and the device responds with the raw data. If the device
+	 * has an error, it will send an End of Image command. First we need to
+	 * request the memory dump table so that we know where all the pieces
+	 * of the dump are that we can consume.
+	 */
+
+	context->is_mem_dump_mode = true;
+
+	/*
+	 * Assume that the table is smaller than our MTU so that we can read it
+	 * in one shot. The spec does not put an upper limit on the table, but
+	 * no known device will exceed this.
+	 */
+	if (context->dump_table_length > SAHARA_PACKET_MAX_SIZE) {
+		dev_err(&context->mhi_dev->dev, "Memory dump table length %lld exceeds supported size. Discarding dump\n",
+			context->dump_table_length);
+		sahara_send_reset(context);
+		return;
+	}
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH);
+	context->tx[0]->memory_read64.memory_address = cpu_to_le64(context->dump_table_address);
+	context->tx[0]->memory_read64.memory_length = cpu_to_le64(context->dump_table_length);
+
+	context->rx_size_requested = context->dump_table_length;
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_MEM_READ64_LENGTH, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to send read for dump table %d\n", ret);
+}
+
+static void sahara_processing(struct work_struct *work)
+{
+	struct sahara_context *context = container_of(work, struct sahara_context, fw_work);
+	int ret;
+
+	switch (le32_to_cpu(context->rx->cmd)) {
+	case SAHARA_HELLO_CMD:
+		sahara_hello(context);
+		break;
+	case SAHARA_READ_DATA_CMD:
+		sahara_read_data(context);
+		break;
+	case SAHARA_END_OF_IMAGE_CMD:
+		sahara_end_of_image(context);
+		break;
+	case SAHARA_DONE_RESP_CMD:
+		/* Intentional do nothing as we don't need to exit an app */
+		break;
+	case SAHARA_RESET_RESP_CMD:
+		/* Intentional do nothing as we don't need to exit an app */
+		break;
+	case SAHARA_MEM_DEBUG64_CMD:
+		sahara_memory_debug64(context);
+		break;
+	default:
+		dev_err(&context->mhi_dev->dev, "Unknown command %d\n",
+			le32_to_cpu(context->rx->cmd));
+		break;
+	}
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_FROM_DEVICE, context->rx,
+			    SAHARA_PACKET_MAX_SIZE, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to requeue rx buf %d\n", ret);
+}
+
+static void sahara_parse_dump_table(struct sahara_context *context)
+{
+	struct sahara_dump_table_entry *image_out_table;
+	struct sahara_debug_table_entry64 *dev_table;
+	struct sahara_memory_dump_meta_v1 *dump_meta;
+	u64 table_nents;
+	u64 dump_length;
+	int ret;
+	u64 i;
+
+	table_nents = context->dump_table_length / sizeof(*dev_table);
+	context->dump_images_left = table_nents;
+	dump_length = 0;
+
+	dev_table = (struct sahara_debug_table_entry64 *)(context->rx);
+	for (i = 0; i < table_nents; ++i) {
+		/* Do not trust the device, ensure the strings are terminated */
+		dev_table[i].description[SAHARA_TABLE_ENTRY_STR_LEN - 1] = 0;
+		dev_table[i].filename[SAHARA_TABLE_ENTRY_STR_LEN - 1] = 0;
+
+		dump_length = size_add(dump_length, le64_to_cpu(dev_table[i].length));
+		if (dump_length == SIZE_MAX) {
+			/* Discard the dump */
+			sahara_send_reset(context);
+			return;
+		}
+
+		dev_dbg(&context->mhi_dev->dev,
+			"Memory dump table entry %lld type: %lld address: %#llx length: %#llx description: \"%s\" filename \"%s\"\n",
+			i,
+			le64_to_cpu(dev_table[i].type),
+			le64_to_cpu(dev_table[i].address),
+			le64_to_cpu(dev_table[i].length),
+			dev_table[i].description,
+			dev_table[i].filename);
+	}
+
+	dump_length = size_add(dump_length, sizeof(*dump_meta));
+	if (dump_length == SIZE_MAX) {
+		/* Discard the dump */
+		sahara_send_reset(context);
+		return;
+	}
+	dump_length = size_add(dump_length, size_mul(sizeof(*image_out_table), table_nents));
+	if (dump_length == SIZE_MAX) {
+		/* Discard the dump */
+		sahara_send_reset(context);
+		return;
+	}
+
+	context->mem_dump_sz = dump_length;
+	context->mem_dump = vzalloc(dump_length);
+	if (!context->mem_dump) {
+		/* Discard the dump */
+		sahara_send_reset(context);
+		return;
+	}
+
+	/* Populate the dump metadata and table for userspace */
+	dump_meta = context->mem_dump;
+	dump_meta->magic = SAHARA_DUMP_V1_MAGIC;
+	dump_meta->version = SAHARA_DUMP_V1_VER;
+	dump_meta->dump_size = dump_length;
+	dump_meta->table_size = context->dump_table_length;
+
+	image_out_table = context->mem_dump + sizeof(*dump_meta);
+	for (i = 0; i < table_nents; ++i) {
+		image_out_table[i].type = le64_to_cpu(dev_table[i].type);
+		image_out_table[i].address = le64_to_cpu(dev_table[i].address);
+		image_out_table[i].length = le64_to_cpu(dev_table[i].length);
+		strscpy(image_out_table[i].description, dev_table[i].description,
+			SAHARA_TABLE_ENTRY_STR_LEN);
+		strscpy(image_out_table[i].filename,
+			dev_table[i].filename,
+			SAHARA_TABLE_ENTRY_STR_LEN);
+	}
+
+	context->mem_dump_freespace = &image_out_table[i];
+
+	/* Done parsing the table, switch to image dump mode */
+	context->dump_table_length = 0;
+
+	/* Request the first chunk of the first image */
+	context->dump_image = &image_out_table[0];
+	dump_length = min(context->dump_image->length, SAHARA_READ_MAX_SIZE);
+	/* Avoid requesting EOI sized data so that we can identify errors */
+	if (dump_length == SAHARA_END_OF_IMAGE_LENGTH)
+		dump_length = SAHARA_END_OF_IMAGE_LENGTH / 2;
+
+	context->dump_image_offset = dump_length;
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH);
+	context->tx[0]->memory_read64.memory_address = cpu_to_le64(context->dump_image->address);
+	context->tx[0]->memory_read64.memory_length = cpu_to_le64(dump_length);
+
+	context->rx_size_requested = dump_length;
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_MEM_READ64_LENGTH, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to send read for dump content %d\n", ret);
+}
+
+static void sahara_parse_dump_image(struct sahara_context *context)
+{
+	u64 dump_length;
+	int ret;
+
+	memcpy(context->mem_dump_freespace, context->rx, context->rx_size);
+	context->mem_dump_freespace += context->rx_size;
+
+	if (context->dump_image_offset >= context->dump_image->length) {
+		/* Need to move to next image */
+		context->dump_image++;
+		context->dump_images_left--;
+		context->dump_image_offset = 0;
+
+		if (!context->dump_images_left) {
+			/* Dump done */
+			dev_coredumpv(context->mhi_dev->mhi_cntrl->cntrl_dev,
+				      context->mem_dump,
+				      context->mem_dump_sz,
+				      GFP_KERNEL);
+			context->mem_dump = NULL;
+			sahara_send_reset(context);
+			return;
+		}
+	}
+
+	/* Get next image chunk */
+	dump_length = context->dump_image->length - context->dump_image_offset;
+	dump_length = min(dump_length, SAHARA_READ_MAX_SIZE);
+	/* Avoid requesting EOI sized data so that we can identify errors */
+	if (dump_length == SAHARA_END_OF_IMAGE_LENGTH)
+		dump_length = SAHARA_END_OF_IMAGE_LENGTH / 2;
+
+	context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD);
+	context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH);
+	context->tx[0]->memory_read64.memory_address =
+		cpu_to_le64(context->dump_image->address + context->dump_image_offset);
+	context->tx[0]->memory_read64.memory_length = cpu_to_le64(dump_length);
+
+	context->dump_image_offset += dump_length;
+	context->rx_size_requested = dump_length;
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0],
+			    SAHARA_MEM_READ64_LENGTH, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev,
+			"Unable to send read for dump content %d\n", ret);
+}
+
+static void sahara_dump_processing(struct work_struct *work)
+{
+	struct sahara_context *context = container_of(work, struct sahara_context, dump_work);
+	int ret;
+
+	/*
+	 * We should get the expected raw data, but if the device has an error
+	 * it is supposed to send EOI with an error code.
+	 */
+	if (context->rx_size != context->rx_size_requested &&
+	    context->rx_size != SAHARA_END_OF_IMAGE_LENGTH) {
+		dev_err(&context->mhi_dev->dev,
+			"Unexpected response to read_data. Expected size: %#zx got: %#zx\n",
+			context->rx_size_requested,
+			context->rx_size);
+		goto error;
+	}
+
+	if (context->rx_size == SAHARA_END_OF_IMAGE_LENGTH &&
+	    le32_to_cpu(context->rx->cmd) == SAHARA_END_OF_IMAGE_CMD) {
+		dev_err(&context->mhi_dev->dev,
+			"Unexpected EOI response to read_data. Status: %d\n",
+			le32_to_cpu(context->rx->end_of_image.status));
+		goto error;
+	}
+
+	if (context->rx_size == SAHARA_END_OF_IMAGE_LENGTH &&
+	    le32_to_cpu(context->rx->cmd) != SAHARA_END_OF_IMAGE_CMD) {
+		dev_err(&context->mhi_dev->dev,
+			"Invalid EOI response to read_data. CMD: %d\n",
+			le32_to_cpu(context->rx->cmd));
+		goto error;
+	}
+
+	/*
+	 * Need to know if we received the dump table, or part of a dump image.
+	 * Since we get raw data, we cannot tell from the data itself. Instead,
+	 * we use the stored dump_table_length, which we zero after we read and
+	 * process the entire table.
+	 */
+	if (context->dump_table_length)
+		sahara_parse_dump_table(context);
+	else
+		sahara_parse_dump_image(context);
+
+	ret = mhi_queue_buf(context->mhi_dev, DMA_FROM_DEVICE, context->rx,
+			    SAHARA_PACKET_MAX_SIZE, MHI_EOT);
+	if (ret)
+		dev_err(&context->mhi_dev->dev, "Unable to requeue rx buf %d\n", ret);
+
+	return;
+
+error:
+	vfree(context->mem_dump);
+	context->mem_dump = NULL;
+	sahara_send_reset(context);
+}
+
+static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct sahara_context *context;
+	int ret;
+	int i;
+
+	context = devm_kzalloc(&mhi_dev->dev, sizeof(*context), GFP_KERNEL);
+	if (!context)
+		return -ENOMEM;
+
+	context->rx = devm_kzalloc(&mhi_dev->dev, SAHARA_PACKET_MAX_SIZE, GFP_KERNEL);
+	if (!context->rx)
+		return -ENOMEM;
+
+	/*
+	 * AIC100 defines SAHARA_TRANSFER_MAX_SIZE as the largest value it
+	 * will request for READ_DATA. This is larger than
+	 * SAHARA_PACKET_MAX_SIZE, and we need 9x SAHARA_PACKET_MAX_SIZE to
+	 * cover SAHARA_TRANSFER_MAX_SIZE. When the remote side issues a
+	 * READ_DATA, it requires a transfer of the exact size requested. We
+	 * can use MHI_CHAIN to link multiple buffers into a single transfer
+	 * but the remote side will not consume the buffers until it sees an
+	 * EOT, thus we need to allocate enough buffers to put in the tx fifo
+	 * to cover an entire READ_DATA request of the max size.
+	 */
+	for (i = 0; i < SAHARA_NUM_TX_BUF; ++i) {
+		context->tx[i] = devm_kzalloc(&mhi_dev->dev, SAHARA_PACKET_MAX_SIZE, GFP_KERNEL);
+		if (!context->tx[i])
+			return -ENOMEM;
+	}
+
+	context->mhi_dev = mhi_dev;
+	INIT_WORK(&context->fw_work, sahara_processing);
+	INIT_WORK(&context->dump_work, sahara_dump_processing);
+
+	if (!strcmp(mhi_dev->mhi_cntrl->name, "AIC200")) {
+		context->image_table = aic200_image_table;
+		context->table_size = ARRAY_SIZE(aic200_image_table);
+	} else {
+		context->image_table = aic100_image_table;
+		context->table_size = ARRAY_SIZE(aic100_image_table);
+	}
+
+	context->active_image_id = SAHARA_IMAGE_ID_NONE;
+	dev_set_drvdata(&mhi_dev->dev, context);
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		return ret;
+
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, context->rx, SAHARA_PACKET_MAX_SIZE, MHI_EOT);
+	if (ret) {
+		mhi_unprepare_from_transfer(mhi_dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void sahara_mhi_remove(struct mhi_device *mhi_dev)
+{
+	struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev);
+
+	cancel_work_sync(&context->fw_work);
+	cancel_work_sync(&context->dump_work);
+	vfree(context->mem_dump);
+	sahara_release_image(context);
+	mhi_unprepare_from_transfer(mhi_dev);
+}
+
+static void sahara_mhi_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+}
+
+static void sahara_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev);
+
+	if (!mhi_result->transaction_status) {
+		context->rx_size = mhi_result->bytes_xferd;
+		if (context->is_mem_dump_mode)
+			schedule_work(&context->dump_work);
+		else
+			schedule_work(&context->fw_work);
+	}
+
+}
+
+static const struct mhi_device_id sahara_mhi_match_table[] = {
+	{ .chan = "QAIC_SAHARA", },
+	{},
+};
+
+static struct mhi_driver sahara_mhi_driver = {
+	.id_table = sahara_mhi_match_table,
+	.remove = sahara_mhi_remove,
+	.probe = sahara_mhi_probe,
+	.ul_xfer_cb = sahara_mhi_ul_xfer_cb,
+	.dl_xfer_cb = sahara_mhi_dl_xfer_cb,
+	.driver = {
+		.name = "sahara",
+	},
+};
+
+int sahara_register(void)
+{
+	return mhi_driver_register(&sahara_mhi_driver);
+}
+
+void sahara_unregister(void)
+{
+	mhi_driver_unregister(&sahara_mhi_driver);
+}
diff --git a/drivers/accel/qaic/sahara.h b/drivers/accel/qaic/sahara.h
new file mode 100644
index 000000000000..640208acc0d1
--- /dev/null
+++ b/drivers/accel/qaic/sahara.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/* Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#ifndef __SAHARA_H__
+#define __SAHARA_H__
+
+int sahara_register(void);
+void sahara_unregister(void);
+#endif /* __SAHARA_H__ */
diff --git a/drivers/accel/rocket/Kconfig b/drivers/accel/rocket/Kconfig
new file mode 100644
index 000000000000..16465abe0660
--- /dev/null
+++ b/drivers/accel/rocket/Kconfig
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config DRM_ACCEL_ROCKET
+	tristate "Rocket (support for Rockchip NPUs)"
+	depends on DRM_ACCEL
+	depends on (ARCH_ROCKCHIP && ARM64) || COMPILE_TEST
+	depends on ROCKCHIP_IOMMU || COMPILE_TEST
+	depends on MMU
+	select DRM_SCHED
+	select DRM_GEM_SHMEM_HELPER
+	help
+	  Choose this option if you have a Rockchip SoC that contains a
+	  compatible Neural Processing Unit (NPU), such as the RK3588. Called by
+	  Rockchip either RKNN or RKNPU, it accelerates inference of neural
+	  networks.
+
+	  The interface exposed to userspace is described in
+	  include/uapi/drm/rocket_accel.h and is used by the Rocket userspace
+	  driver in Mesa3D.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rocket.
diff --git a/drivers/accel/rocket/Makefile b/drivers/accel/rocket/Makefile
new file mode 100644
index 000000000000..3713dfe223d6
--- /dev/null
+++ b/drivers/accel/rocket/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_DRM_ACCEL_ROCKET) := rocket.o
+
+rocket-y := \
+	rocket_core.o \
+	rocket_device.o \
+	rocket_drv.o \
+	rocket_gem.o \
+	rocket_job.o
diff --git a/drivers/accel/rocket/rocket_core.c b/drivers/accel/rocket/rocket_core.c
new file mode 100644
index 000000000000..abe7719c1db4
--- /dev/null
+++ b/drivers/accel/rocket/rocket_core.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/iommu.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include "rocket_core.h"
+#include "rocket_job.h"
+
+int rocket_core_init(struct rocket_core *core)
+{
+	struct device *dev = core->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	u32 version;
+	int err = 0;
+
+	core->resets[0].id = "srst_a";
+	core->resets[1].id = "srst_h";
+	err = devm_reset_control_bulk_get_exclusive(&pdev->dev, ARRAY_SIZE(core->resets),
+						    core->resets);
+	if (err)
+		return dev_err_probe(dev, err, "failed to get resets for core %d\n", core->index);
+
+	err = devm_clk_bulk_get(dev, ARRAY_SIZE(core->clks), core->clks);
+	if (err)
+		return dev_err_probe(dev, err, "failed to get clocks for core %d\n", core->index);
+
+	core->pc_iomem = devm_platform_ioremap_resource_byname(pdev, "pc");
+	if (IS_ERR(core->pc_iomem)) {
+		dev_err(dev, "couldn't find PC registers %ld\n", PTR_ERR(core->pc_iomem));
+		return PTR_ERR(core->pc_iomem);
+	}
+
+	core->cna_iomem = devm_platform_ioremap_resource_byname(pdev, "cna");
+	if (IS_ERR(core->cna_iomem)) {
+		dev_err(dev, "couldn't find CNA registers %ld\n", PTR_ERR(core->cna_iomem));
+		return PTR_ERR(core->cna_iomem);
+	}
+
+	core->core_iomem = devm_platform_ioremap_resource_byname(pdev, "core");
+	if (IS_ERR(core->core_iomem)) {
+		dev_err(dev, "couldn't find CORE registers %ld\n", PTR_ERR(core->core_iomem));
+		return PTR_ERR(core->core_iomem);
+	}
+
+	dma_set_max_seg_size(dev, UINT_MAX);
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
+	if (err)
+		return err;
+
+	core->iommu_group = iommu_group_get(dev);
+
+	err = rocket_job_init(core);
+	if (err)
+		return err;
+
+	pm_runtime_use_autosuspend(dev);
+
+	/*
+	 * As this NPU will be most often used as part of a media pipeline that
+	 * ends presenting in a display, choose 50 ms (~3 frames at 60Hz) as an
+	 * autosuspend delay as that will keep the device powered up while the
+	 * pipeline is running.
+	 */
+	pm_runtime_set_autosuspend_delay(dev, 50);
+
+	pm_runtime_enable(dev);
+
+	err = pm_runtime_resume_and_get(dev);
+	if (err) {
+		rocket_job_fini(core);
+		return err;
+	}
+
+	version = rocket_pc_readl(core, VERSION);
+	version += rocket_pc_readl(core, VERSION_NUM) & 0xffff;
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	dev_info(dev, "Rockchip NPU core %d version: %d\n", core->index, version);
+
+	return 0;
+}
+
+void rocket_core_fini(struct rocket_core *core)
+{
+	pm_runtime_dont_use_autosuspend(core->dev);
+	pm_runtime_disable(core->dev);
+	iommu_group_put(core->iommu_group);
+	core->iommu_group = NULL;
+	rocket_job_fini(core);
+}
+
+void rocket_core_reset(struct rocket_core *core)
+{
+	reset_control_bulk_assert(ARRAY_SIZE(core->resets), core->resets);
+
+	udelay(10);
+
+	reset_control_bulk_deassert(ARRAY_SIZE(core->resets), core->resets);
+}
diff --git a/drivers/accel/rocket/rocket_core.h b/drivers/accel/rocket/rocket_core.h
new file mode 100644
index 000000000000..f6d7382854ca
--- /dev/null
+++ b/drivers/accel/rocket/rocket_core.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_CORE_H__
+#define __ROCKET_CORE_H__
+
+#include <drm/gpu_scheduler.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/mutex_types.h>
+#include <linux/reset.h>
+
+#include "rocket_registers.h"
+
+#define rocket_pc_readl(core, reg) \
+	readl((core)->pc_iomem + (REG_PC_##reg))
+#define rocket_pc_writel(core, reg, value) \
+	writel(value, (core)->pc_iomem + (REG_PC_##reg))
+
+#define rocket_cna_readl(core, reg) \
+	readl((core)->cna_iomem + (REG_CNA_##reg) - REG_CNA_S_STATUS)
+#define rocket_cna_writel(core, reg, value) \
+	writel(value, (core)->cna_iomem + (REG_CNA_##reg) - REG_CNA_S_STATUS)
+
+#define rocket_core_readl(core, reg) \
+	readl((core)->core_iomem + (REG_CORE_##reg) - REG_CORE_S_STATUS)
+#define rocket_core_writel(core, reg, value) \
+	writel(value, (core)->core_iomem + (REG_CORE_##reg) - REG_CORE_S_STATUS)
+
+struct rocket_core {
+	struct device *dev;
+	struct rocket_device *rdev;
+	unsigned int index;
+
+	int irq;
+	void __iomem *pc_iomem;
+	void __iomem *cna_iomem;
+	void __iomem *core_iomem;
+	struct clk_bulk_data clks[4];
+	struct reset_control_bulk_data resets[2];
+
+	struct iommu_group *iommu_group;
+
+	struct mutex job_lock;
+	struct rocket_job *in_flight_job;
+
+	spinlock_t fence_lock;
+
+	struct {
+		struct workqueue_struct *wq;
+		struct work_struct work;
+		atomic_t pending;
+	} reset;
+
+	struct drm_gpu_scheduler sched;
+	u64 fence_context;
+	u64 emit_seqno;
+};
+
+int rocket_core_init(struct rocket_core *core);
+void rocket_core_fini(struct rocket_core *core);
+void rocket_core_reset(struct rocket_core *core);
+
+#endif
diff --git a/drivers/accel/rocket/rocket_device.c b/drivers/accel/rocket/rocket_device.c
new file mode 100644
index 000000000000..46e6ee1e72c5
--- /dev/null
+++ b/drivers/accel/rocket/rocket_device.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <drm/drm_drv.h>
+#include <linux/array_size.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+
+#include "rocket_device.h"
+
+struct rocket_device *rocket_device_init(struct platform_device *pdev,
+					 const struct drm_driver *rocket_drm_driver)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *core_node;
+	struct rocket_device *rdev;
+	struct drm_device *ddev;
+	unsigned int num_cores = 0;
+	int err;
+
+	rdev = devm_drm_dev_alloc(dev, rocket_drm_driver, struct rocket_device, ddev);
+	if (IS_ERR(rdev))
+		return rdev;
+
+	ddev = &rdev->ddev;
+	dev_set_drvdata(dev, rdev);
+
+	for_each_compatible_node(core_node, NULL, "rockchip,rk3588-rknn-core")
+		if (of_device_is_available(core_node))
+			num_cores++;
+
+	rdev->cores = devm_kcalloc(dev, num_cores, sizeof(*rdev->cores), GFP_KERNEL);
+	if (!rdev->cores)
+		return ERR_PTR(-ENOMEM);
+
+	dma_set_max_seg_size(dev, UINT_MAX);
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
+	if (err)
+		return ERR_PTR(err);
+
+	err = devm_mutex_init(dev, &rdev->sched_lock);
+	if (err)
+		return ERR_PTR(-ENOMEM);
+
+	err = drm_dev_register(ddev, 0);
+	if (err)
+		return ERR_PTR(err);
+
+	return rdev;
+}
+
+void rocket_device_fini(struct rocket_device *rdev)
+{
+	WARN_ON(rdev->num_cores > 0);
+
+	drm_dev_unregister(&rdev->ddev);
+}
diff --git a/drivers/accel/rocket/rocket_device.h b/drivers/accel/rocket/rocket_device.h
new file mode 100644
index 000000000000..ce662abc01d3
--- /dev/null
+++ b/drivers/accel/rocket/rocket_device.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_DEVICE_H__
+#define __ROCKET_DEVICE_H__
+
+#include <drm/drm_device.h>
+#include <linux/clk.h>
+#include <linux/container_of.h>
+#include <linux/iommu.h>
+#include <linux/platform_device.h>
+
+#include "rocket_core.h"
+
+struct rocket_device {
+	struct drm_device ddev;
+
+	struct mutex sched_lock;
+
+	struct rocket_core *cores;
+	unsigned int num_cores;
+};
+
+struct rocket_device *rocket_device_init(struct platform_device *pdev,
+					 const struct drm_driver *rocket_drm_driver);
+void rocket_device_fini(struct rocket_device *rdev);
+#define to_rocket_device(drm_dev) \
+	((struct rocket_device *)(container_of((drm_dev), struct rocket_device, ddev)))
+
+#endif /* __ROCKET_DEVICE_H__ */
diff --git a/drivers/accel/rocket/rocket_drv.c b/drivers/accel/rocket/rocket_drv.c
new file mode 100644
index 000000000000..5c0b63f0a8f0
--- /dev/null
+++ b/drivers/accel/rocket/rocket_drv.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <drm/drm_accel.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_ioctl.h>
+#include <drm/rocket_accel.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/iommu.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "rocket_drv.h"
+#include "rocket_gem.h"
+#include "rocket_job.h"
+
+/*
+ * Facade device, used to expose a single DRM device to userspace, that
+ * schedules jobs to any RKNN cores in the system.
+ */
+static struct platform_device *drm_dev;
+static struct rocket_device *rdev;
+
+static void
+rocket_iommu_domain_destroy(struct kref *kref)
+{
+	struct rocket_iommu_domain *domain = container_of(kref, struct rocket_iommu_domain, kref);
+
+	iommu_domain_free(domain->domain);
+	domain->domain = NULL;
+	kfree(domain);
+}
+
+static struct rocket_iommu_domain*
+rocket_iommu_domain_create(struct device *dev)
+{
+	struct rocket_iommu_domain *domain = kmalloc(sizeof(*domain), GFP_KERNEL);
+	void *err;
+
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	domain->domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain->domain)) {
+		err = ERR_CAST(domain->domain);
+		kfree(domain);
+		return err;
+	}
+	kref_init(&domain->kref);
+
+	return domain;
+}
+
+struct rocket_iommu_domain *
+rocket_iommu_domain_get(struct rocket_file_priv *rocket_priv)
+{
+	kref_get(&rocket_priv->domain->kref);
+	return rocket_priv->domain;
+}
+
+void
+rocket_iommu_domain_put(struct rocket_iommu_domain *domain)
+{
+	kref_put(&domain->kref, rocket_iommu_domain_destroy);
+}
+
+static int
+rocket_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct rocket_device *rdev = to_rocket_device(dev);
+	struct rocket_file_priv *rocket_priv;
+	u64 start, end;
+	int ret;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	rocket_priv = kzalloc(sizeof(*rocket_priv), GFP_KERNEL);
+	if (!rocket_priv) {
+		ret = -ENOMEM;
+		goto err_put_mod;
+	}
+
+	rocket_priv->rdev = rdev;
+	rocket_priv->domain = rocket_iommu_domain_create(rdev->cores[0].dev);
+	if (IS_ERR(rocket_priv->domain)) {
+		ret = PTR_ERR(rocket_priv->domain);
+		goto err_free;
+	}
+
+	file->driver_priv = rocket_priv;
+
+	start = rocket_priv->domain->domain->geometry.aperture_start;
+	end = rocket_priv->domain->domain->geometry.aperture_end;
+	drm_mm_init(&rocket_priv->mm, start, end - start + 1);
+	mutex_init(&rocket_priv->mm_lock);
+
+	ret = rocket_job_open(rocket_priv);
+	if (ret)
+		goto err_mm_takedown;
+
+	return 0;
+
+err_mm_takedown:
+	mutex_destroy(&rocket_priv->mm_lock);
+	drm_mm_takedown(&rocket_priv->mm);
+	rocket_iommu_domain_put(rocket_priv->domain);
+err_free:
+	kfree(rocket_priv);
+err_put_mod:
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static void
+rocket_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct rocket_file_priv *rocket_priv = file->driver_priv;
+
+	rocket_job_close(rocket_priv);
+	mutex_destroy(&rocket_priv->mm_lock);
+	drm_mm_takedown(&rocket_priv->mm);
+	rocket_iommu_domain_put(rocket_priv->domain);
+	kfree(rocket_priv);
+	module_put(THIS_MODULE);
+}
+
+static const struct drm_ioctl_desc rocket_drm_driver_ioctls[] = {
+#define ROCKET_IOCTL(n, func) \
+	DRM_IOCTL_DEF_DRV(ROCKET_##n, rocket_ioctl_##func, 0)
+
+	ROCKET_IOCTL(CREATE_BO, create_bo),
+	ROCKET_IOCTL(SUBMIT, submit),
+	ROCKET_IOCTL(PREP_BO, prep_bo),
+	ROCKET_IOCTL(FINI_BO, fini_bo),
+};
+
+DEFINE_DRM_ACCEL_FOPS(rocket_accel_driver_fops);
+
+/*
+ * Rocket driver version:
+ * - 1.0 - initial interface
+ */
+static const struct drm_driver rocket_drm_driver = {
+	.driver_features	= DRIVER_COMPUTE_ACCEL | DRIVER_GEM,
+	.open			= rocket_open,
+	.postclose		= rocket_postclose,
+	.gem_create_object	= rocket_gem_create_object,
+	.ioctls			= rocket_drm_driver_ioctls,
+	.num_ioctls		= ARRAY_SIZE(rocket_drm_driver_ioctls),
+	.fops			= &rocket_accel_driver_fops,
+	.name			= "rocket",
+	.desc			= "rocket DRM",
+};
+
+static int rocket_probe(struct platform_device *pdev)
+{
+	if (rdev == NULL) {
+		/* First core probing, initialize DRM device. */
+		rdev = rocket_device_init(drm_dev, &rocket_drm_driver);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to initialize rocket device\n");
+			return PTR_ERR(rdev);
+		}
+	}
+
+	unsigned int core = rdev->num_cores;
+
+	dev_set_drvdata(&pdev->dev, rdev);
+
+	rdev->cores[core].rdev = rdev;
+	rdev->cores[core].dev = &pdev->dev;
+	rdev->cores[core].index = core;
+
+	rdev->num_cores++;
+
+	return rocket_core_init(&rdev->cores[core]);
+}
+
+static void rocket_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	for (unsigned int core = 0; core < rdev->num_cores; core++) {
+		if (rdev->cores[core].dev == dev) {
+			rocket_core_fini(&rdev->cores[core]);
+			rdev->num_cores--;
+			break;
+		}
+	}
+
+	if (rdev->num_cores == 0) {
+		/* Last core removed, deinitialize DRM device. */
+		rocket_device_fini(rdev);
+		rdev = NULL;
+	}
+}
+
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "rockchip,rk3588-rknn-core" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dt_match);
+
+static int find_core_for_dev(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+
+	for (unsigned int core = 0; core < rdev->num_cores; core++) {
+		if (dev == rdev->cores[core].dev)
+			return core;
+	}
+
+	return -1;
+}
+
+static int rocket_device_runtime_resume(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+	int core = find_core_for_dev(dev);
+	int err = 0;
+
+	if (core < 0)
+		return -ENODEV;
+
+	err = clk_bulk_prepare_enable(ARRAY_SIZE(rdev->cores[core].clks), rdev->cores[core].clks);
+	if (err) {
+		dev_err(dev, "failed to enable (%d) clocks for core %d\n", err, core);
+		return err;
+	}
+
+	return 0;
+}
+
+static int rocket_device_runtime_suspend(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+	int core = find_core_for_dev(dev);
+
+	if (core < 0)
+		return -ENODEV;
+
+	if (!rocket_job_is_idle(&rdev->cores[core]))
+		return -EBUSY;
+
+	clk_bulk_disable_unprepare(ARRAY_SIZE(rdev->cores[core].clks), rdev->cores[core].clks);
+
+	return 0;
+}
+
+EXPORT_GPL_DEV_PM_OPS(rocket_pm_ops) = {
+	RUNTIME_PM_OPS(rocket_device_runtime_suspend, rocket_device_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+};
+
+static struct platform_driver rocket_driver = {
+	.probe = rocket_probe,
+	.remove = rocket_remove,
+	.driver	 = {
+		.name = "rocket",
+		.pm = pm_ptr(&rocket_pm_ops),
+		.of_match_table = dt_match,
+	},
+};
+
+static int __init rocket_register(void)
+{
+	drm_dev = platform_device_register_simple("rknn", -1, NULL, 0);
+	if (IS_ERR(drm_dev))
+		return PTR_ERR(drm_dev);
+
+	return platform_driver_register(&rocket_driver);
+}
+
+static void __exit rocket_unregister(void)
+{
+	platform_driver_unregister(&rocket_driver);
+
+	platform_device_unregister(drm_dev);
+}
+
+module_init(rocket_register);
+module_exit(rocket_unregister);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("DRM driver for the Rockchip NPU IP");
+MODULE_AUTHOR("Tomeu Vizoso");
diff --git a/drivers/accel/rocket/rocket_drv.h b/drivers/accel/rocket/rocket_drv.h
new file mode 100644
index 000000000000..2c673bb99ccc
--- /dev/null
+++ b/drivers/accel/rocket/rocket_drv.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_DRV_H__
+#define __ROCKET_DRV_H__
+
+#include <drm/drm_mm.h>
+#include <drm/gpu_scheduler.h>
+
+#include "rocket_device.h"
+
+extern const struct dev_pm_ops rocket_pm_ops;
+
+struct rocket_iommu_domain {
+	struct iommu_domain *domain;
+	struct kref kref;
+};
+
+struct rocket_file_priv {
+	struct rocket_device *rdev;
+
+	struct rocket_iommu_domain *domain;
+	struct drm_mm mm;
+	struct mutex mm_lock;
+
+	struct drm_sched_entity sched_entity;
+};
+
+struct rocket_iommu_domain *rocket_iommu_domain_get(struct rocket_file_priv *rocket_priv);
+void rocket_iommu_domain_put(struct rocket_iommu_domain *domain);
+
+#endif
diff --git a/drivers/accel/rocket/rocket_gem.c b/drivers/accel/rocket/rocket_gem.c
new file mode 100644
index 000000000000..0551e11cc184
--- /dev/null
+++ b/drivers/accel/rocket/rocket_gem.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <drm/drm_device.h>
+#include <drm/drm_utils.h>
+#include <drm/rocket_accel.h>
+#include <linux/dma-mapping.h>
+#include <linux/iommu.h>
+
+#include "rocket_drv.h"
+#include "rocket_gem.h"
+
+static void rocket_gem_bo_free(struct drm_gem_object *obj)
+{
+	struct rocket_gem_object *bo = to_rocket_bo(obj);
+	struct rocket_file_priv *rocket_priv = bo->driver_priv;
+	size_t unmapped;
+
+	drm_WARN_ON(obj->dev, refcount_read(&bo->base.pages_use_count) > 1);
+
+	unmapped = iommu_unmap(bo->domain->domain, bo->mm.start, bo->size);
+	drm_WARN_ON(obj->dev, unmapped != bo->size);
+
+	mutex_lock(&rocket_priv->mm_lock);
+	drm_mm_remove_node(&bo->mm);
+	mutex_unlock(&rocket_priv->mm_lock);
+
+	rocket_iommu_domain_put(bo->domain);
+	bo->domain = NULL;
+
+	drm_gem_shmem_free(&bo->base);
+}
+
+static const struct drm_gem_object_funcs rocket_gem_funcs = {
+	.free = rocket_gem_bo_free,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
+	.vm_ops = &drm_gem_shmem_vm_ops,
+};
+
+struct drm_gem_object *rocket_gem_create_object(struct drm_device *dev, size_t size)
+{
+	struct rocket_gem_object *obj;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	obj->base.base.funcs = &rocket_gem_funcs;
+
+	return &obj->base.base;
+}
+
+int rocket_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct rocket_file_priv *rocket_priv = file->driver_priv;
+	struct drm_rocket_create_bo *args = data;
+	struct drm_gem_shmem_object *shmem_obj;
+	struct rocket_gem_object *rkt_obj;
+	struct drm_gem_object *gem_obj;
+	struct sg_table *sgt;
+	int ret;
+
+	shmem_obj = drm_gem_shmem_create(dev, args->size);
+	if (IS_ERR(shmem_obj))
+		return PTR_ERR(shmem_obj);
+
+	gem_obj = &shmem_obj->base;
+	rkt_obj = to_rocket_bo(gem_obj);
+
+	rkt_obj->driver_priv = rocket_priv;
+	rkt_obj->domain = rocket_iommu_domain_get(rocket_priv);
+	rkt_obj->size = args->size;
+	rkt_obj->offset = 0;
+
+	ret = drm_gem_handle_create(file, gem_obj, &args->handle);
+	drm_gem_object_put(gem_obj);
+	if (ret)
+		goto err;
+
+	sgt = drm_gem_shmem_get_pages_sgt(shmem_obj);
+	if (IS_ERR(sgt)) {
+		ret = PTR_ERR(sgt);
+		goto err;
+	}
+
+	mutex_lock(&rocket_priv->mm_lock);
+	ret = drm_mm_insert_node_generic(&rocket_priv->mm, &rkt_obj->mm,
+					 rkt_obj->size, PAGE_SIZE,
+					 0, 0);
+	mutex_unlock(&rocket_priv->mm_lock);
+
+	ret = iommu_map_sgtable(rocket_priv->domain->domain,
+				rkt_obj->mm.start,
+				shmem_obj->sgt,
+				IOMMU_READ | IOMMU_WRITE);
+	if (ret < 0 || ret < args->size) {
+		drm_err(dev, "failed to map buffer: size=%d request_size=%u\n",
+			ret, args->size);
+		ret = -ENOMEM;
+		goto err_remove_node;
+	}
+
+	/* iommu_map_sgtable might have aligned the size */
+	rkt_obj->size = ret;
+	args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
+	args->dma_address = rkt_obj->mm.start;
+
+	return 0;
+
+err_remove_node:
+	mutex_lock(&rocket_priv->mm_lock);
+	drm_mm_remove_node(&rkt_obj->mm);
+	mutex_unlock(&rocket_priv->mm_lock);
+
+err:
+	drm_gem_shmem_object_free(gem_obj);
+
+	return ret;
+}
+
+int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_rocket_prep_bo *args = data;
+	unsigned long timeout = drm_timeout_abs_to_jiffies(args->timeout_ns);
+	struct drm_gem_object *gem_obj;
+	struct drm_gem_shmem_object *shmem_obj;
+	long ret = 0;
+
+	if (args->reserved != 0) {
+		drm_dbg(dev, "Reserved field in drm_rocket_prep_bo struct should be 0.\n");
+		return -EINVAL;
+	}
+
+	gem_obj = drm_gem_object_lookup(file, args->handle);
+	if (!gem_obj)
+		return -ENOENT;
+
+	ret = dma_resv_wait_timeout(gem_obj->resv, DMA_RESV_USAGE_WRITE, true, timeout);
+	if (!ret)
+		ret = timeout ? -ETIMEDOUT : -EBUSY;
+
+	shmem_obj = &to_rocket_bo(gem_obj)->base;
+
+	dma_sync_sgtable_for_cpu(dev->dev, shmem_obj->sgt, DMA_BIDIRECTIONAL);
+
+	drm_gem_object_put(gem_obj);
+
+	return ret;
+}
+
+int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_rocket_fini_bo *args = data;
+	struct drm_gem_shmem_object *shmem_obj;
+	struct rocket_gem_object *rkt_obj;
+	struct drm_gem_object *gem_obj;
+
+	if (args->reserved != 0) {
+		drm_dbg(dev, "Reserved field in drm_rocket_fini_bo struct should be 0.\n");
+		return -EINVAL;
+	}
+
+	gem_obj = drm_gem_object_lookup(file, args->handle);
+	if (!gem_obj)
+		return -ENOENT;
+
+	rkt_obj = to_rocket_bo(gem_obj);
+	shmem_obj = &rkt_obj->base;
+
+	dma_sync_sgtable_for_device(dev->dev, shmem_obj->sgt, DMA_BIDIRECTIONAL);
+
+	drm_gem_object_put(gem_obj);
+
+	return 0;
+}
diff --git a/drivers/accel/rocket/rocket_gem.h b/drivers/accel/rocket/rocket_gem.h
new file mode 100644
index 000000000000..240430334509
--- /dev/null
+++ b/drivers/accel/rocket/rocket_gem.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_GEM_H__
+#define __ROCKET_GEM_H__
+
+#include <drm/drm_gem_shmem_helper.h>
+
+struct rocket_gem_object {
+	struct drm_gem_shmem_object base;
+
+	struct rocket_file_priv *driver_priv;
+
+	struct rocket_iommu_domain *domain;
+	struct drm_mm_node mm;
+	size_t size;
+	u32 offset;
+};
+
+struct drm_gem_object *rocket_gem_create_object(struct drm_device *dev, size_t size);
+
+int rocket_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file);
+
+int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file);
+
+int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file);
+
+static inline
+struct  rocket_gem_object *to_rocket_bo(struct drm_gem_object *obj)
+{
+	return container_of(to_drm_gem_shmem_obj(obj), struct rocket_gem_object, base);
+}
+
+#endif
diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c
new file mode 100644
index 000000000000..acd606160dc9
--- /dev/null
+++ b/drivers/accel/rocket/rocket_job.c
@@ -0,0 +1,637 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+/* Copyright 2019 Collabora ltd. */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <drm/drm_print.h>
+#include <drm/drm_file.h>
+#include <drm/drm_gem.h>
+#include <drm/rocket_accel.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "rocket_core.h"
+#include "rocket_device.h"
+#include "rocket_drv.h"
+#include "rocket_job.h"
+#include "rocket_registers.h"
+
+#define JOB_TIMEOUT_MS 500
+
+static struct rocket_job *
+to_rocket_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct rocket_job, base);
+}
+
+static const char *rocket_fence_get_driver_name(struct dma_fence *fence)
+{
+	return "rocket";
+}
+
+static const char *rocket_fence_get_timeline_name(struct dma_fence *fence)
+{
+	return "rockchip-npu";
+}
+
+static const struct dma_fence_ops rocket_fence_ops = {
+	.get_driver_name = rocket_fence_get_driver_name,
+	.get_timeline_name = rocket_fence_get_timeline_name,
+};
+
+static struct dma_fence *rocket_fence_create(struct rocket_core *core)
+{
+	struct dma_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return ERR_PTR(-ENOMEM);
+
+	dma_fence_init(fence, &rocket_fence_ops, &core->fence_lock,
+		       core->fence_context, ++core->emit_seqno);
+
+	return fence;
+}
+
+static int
+rocket_copy_tasks(struct drm_device *dev,
+		  struct drm_file *file_priv,
+		  struct drm_rocket_job *job,
+		  struct rocket_job *rjob)
+{
+	int ret = 0;
+
+	if (job->task_struct_size < sizeof(struct drm_rocket_task))
+		return -EINVAL;
+
+	rjob->task_count = job->task_count;
+
+	if (!rjob->task_count)
+		return 0;
+
+	rjob->tasks = kvmalloc_array(job->task_count, sizeof(*rjob->tasks), GFP_KERNEL);
+	if (!rjob->tasks) {
+		drm_dbg(dev, "Failed to allocate task array\n");
+		return -ENOMEM;
+	}
+
+	for (int i = 0; i < rjob->task_count; i++) {
+		struct drm_rocket_task task = {0};
+
+		if (copy_from_user(&task,
+				   u64_to_user_ptr(job->tasks) + i * job->task_struct_size,
+				   sizeof(task))) {
+			drm_dbg(dev, "Failed to copy incoming tasks\n");
+			ret = -EFAULT;
+			goto fail;
+		}
+
+		if (task.regcmd_count == 0) {
+			drm_dbg(dev, "regcmd_count field in drm_rocket_task should be > 0.\n");
+			ret = -EINVAL;
+			goto fail;
+		}
+
+		rjob->tasks[i].regcmd = task.regcmd;
+		rjob->tasks[i].regcmd_count = task.regcmd_count;
+	}
+
+	return 0;
+
+fail:
+	kvfree(rjob->tasks);
+	return ret;
+}
+
+static void rocket_job_hw_submit(struct rocket_core *core, struct rocket_job *job)
+{
+	struct rocket_task *task;
+	unsigned int extra_bit;
+
+	/* Don't queue the job if a reset is in progress */
+	if (atomic_read(&core->reset.pending))
+		return;
+
+	/* GO ! */
+
+	task = &job->tasks[job->next_task_idx];
+	job->next_task_idx++;
+
+	rocket_pc_writel(core, BASE_ADDRESS, 0x1);
+
+	 /* From rknpu, in the TRM this bit is marked as reserved */
+	extra_bit = 0x10000000 * core->index;
+	rocket_cna_writel(core, S_POINTER, CNA_S_POINTER_POINTER_PP_EN(1) |
+					   CNA_S_POINTER_EXECUTER_PP_EN(1) |
+					   CNA_S_POINTER_POINTER_PP_MODE(1) |
+					   extra_bit);
+
+	rocket_core_writel(core, S_POINTER, CORE_S_POINTER_POINTER_PP_EN(1) |
+					    CORE_S_POINTER_EXECUTER_PP_EN(1) |
+					    CORE_S_POINTER_POINTER_PP_MODE(1) |
+					    extra_bit);
+
+	rocket_pc_writel(core, BASE_ADDRESS, task->regcmd);
+	rocket_pc_writel(core, REGISTER_AMOUNTS,
+			 PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT((task->regcmd_count + 1) / 2 - 1));
+
+	rocket_pc_writel(core, INTERRUPT_MASK, PC_INTERRUPT_MASK_DPU_0 | PC_INTERRUPT_MASK_DPU_1);
+	rocket_pc_writel(core, INTERRUPT_CLEAR, PC_INTERRUPT_CLEAR_DPU_0 | PC_INTERRUPT_CLEAR_DPU_1);
+
+	rocket_pc_writel(core, TASK_CON, PC_TASK_CON_RESERVED_0(1) |
+					 PC_TASK_CON_TASK_COUNT_CLEAR(1) |
+					 PC_TASK_CON_TASK_NUMBER(1) |
+					 PC_TASK_CON_TASK_PP_EN(1));
+
+	rocket_pc_writel(core, TASK_DMA_BASE_ADDR, PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR(0x0));
+
+	rocket_pc_writel(core, OPERATION_ENABLE, PC_OPERATION_ENABLE_OP_EN(1));
+
+	dev_dbg(core->dev, "Submitted regcmd at 0x%llx to core %d", task->regcmd, core->index);
+}
+
+static int rocket_acquire_object_fences(struct drm_gem_object **bos,
+					int bo_count,
+					struct drm_sched_job *job,
+					bool is_write)
+{
+	int i, ret;
+
+	for (i = 0; i < bo_count; i++) {
+		ret = dma_resv_reserve_fences(bos[i]->resv, 1);
+		if (ret)
+			return ret;
+
+		ret = drm_sched_job_add_implicit_dependencies(job, bos[i],
+							      is_write);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void rocket_attach_object_fences(struct drm_gem_object **bos,
+					int bo_count,
+					struct dma_fence *fence)
+{
+	int i;
+
+	for (i = 0; i < bo_count; i++)
+		dma_resv_add_fence(bos[i]->resv, fence, DMA_RESV_USAGE_WRITE);
+}
+
+static int rocket_job_push(struct rocket_job *job)
+{
+	struct rocket_device *rdev = job->rdev;
+	struct drm_gem_object **bos;
+	struct ww_acquire_ctx acquire_ctx;
+	int ret = 0;
+
+	bos = kvmalloc_array(job->in_bo_count + job->out_bo_count, sizeof(void *),
+			     GFP_KERNEL);
+	memcpy(bos, job->in_bos, job->in_bo_count * sizeof(void *));
+	memcpy(&bos[job->in_bo_count], job->out_bos, job->out_bo_count * sizeof(void *));
+
+	ret = drm_gem_lock_reservations(bos, job->in_bo_count + job->out_bo_count, &acquire_ctx);
+	if (ret)
+		goto err;
+
+	scoped_guard(mutex, &rdev->sched_lock) {
+		drm_sched_job_arm(&job->base);
+
+		job->inference_done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+		ret = rocket_acquire_object_fences(job->in_bos, job->in_bo_count, &job->base, false);
+		if (ret)
+			goto err_unlock;
+
+		ret = rocket_acquire_object_fences(job->out_bos, job->out_bo_count, &job->base, true);
+		if (ret)
+			goto err_unlock;
+
+		kref_get(&job->refcount); /* put by scheduler job completion */
+
+		drm_sched_entity_push_job(&job->base);
+	}
+
+	rocket_attach_object_fences(job->out_bos, job->out_bo_count, job->inference_done_fence);
+
+err_unlock:
+	drm_gem_unlock_reservations(bos, job->in_bo_count + job->out_bo_count, &acquire_ctx);
+err:
+	kvfree(bos);
+
+	return ret;
+}
+
+static void rocket_job_cleanup(struct kref *ref)
+{
+	struct rocket_job *job = container_of(ref, struct rocket_job,
+						refcount);
+	unsigned int i;
+
+	rocket_iommu_domain_put(job->domain);
+
+	dma_fence_put(job->done_fence);
+	dma_fence_put(job->inference_done_fence);
+
+	if (job->in_bos) {
+		for (i = 0; i < job->in_bo_count; i++)
+			drm_gem_object_put(job->in_bos[i]);
+
+		kvfree(job->in_bos);
+	}
+
+	if (job->out_bos) {
+		for (i = 0; i < job->out_bo_count; i++)
+			drm_gem_object_put(job->out_bos[i]);
+
+		kvfree(job->out_bos);
+	}
+
+	kvfree(job->tasks);
+
+	kfree(job);
+}
+
+static void rocket_job_put(struct rocket_job *job)
+{
+	kref_put(&job->refcount, rocket_job_cleanup);
+}
+
+static void rocket_job_free(struct drm_sched_job *sched_job)
+{
+	struct rocket_job *job = to_rocket_job(sched_job);
+
+	drm_sched_job_cleanup(sched_job);
+
+	rocket_job_put(job);
+}
+
+static struct rocket_core *sched_to_core(struct rocket_device *rdev,
+					 struct drm_gpu_scheduler *sched)
+{
+	unsigned int core;
+
+	for (core = 0; core < rdev->num_cores; core++) {
+		if (&rdev->cores[core].sched == sched)
+			return &rdev->cores[core];
+	}
+
+	return NULL;
+}
+
+static struct dma_fence *rocket_job_run(struct drm_sched_job *sched_job)
+{
+	struct rocket_job *job = to_rocket_job(sched_job);
+	struct rocket_device *rdev = job->rdev;
+	struct rocket_core *core = sched_to_core(rdev, sched_job->sched);
+	struct dma_fence *fence = NULL;
+	int ret;
+
+	if (unlikely(job->base.s_fence->finished.error))
+		return NULL;
+
+	/*
+	 * Nothing to execute: can happen if the job has finished while
+	 * we were resetting the NPU.
+	 */
+	if (job->next_task_idx == job->task_count)
+		return NULL;
+
+	fence = rocket_fence_create(core);
+	if (IS_ERR(fence))
+		return fence;
+
+	if (job->done_fence)
+		dma_fence_put(job->done_fence);
+	job->done_fence = dma_fence_get(fence);
+
+	ret = pm_runtime_get_sync(core->dev);
+	if (ret < 0)
+		return fence;
+
+	ret = iommu_attach_group(job->domain->domain, core->iommu_group);
+	if (ret < 0)
+		return fence;
+
+	scoped_guard(mutex, &core->job_lock) {
+		core->in_flight_job = job;
+		rocket_job_hw_submit(core, job);
+	}
+
+	return fence;
+}
+
+static void rocket_job_handle_irq(struct rocket_core *core)
+{
+	pm_runtime_mark_last_busy(core->dev);
+
+	rocket_pc_writel(core, OPERATION_ENABLE, 0x0);
+	rocket_pc_writel(core, INTERRUPT_CLEAR, 0x1ffff);
+
+	scoped_guard(mutex, &core->job_lock)
+		if (core->in_flight_job) {
+			if (core->in_flight_job->next_task_idx < core->in_flight_job->task_count) {
+				rocket_job_hw_submit(core, core->in_flight_job);
+				return;
+			}
+
+			iommu_detach_group(NULL, iommu_group_get(core->dev));
+			dma_fence_signal(core->in_flight_job->done_fence);
+			pm_runtime_put_autosuspend(core->dev);
+			core->in_flight_job = NULL;
+		}
+}
+
+static void
+rocket_reset(struct rocket_core *core, struct drm_sched_job *bad)
+{
+	if (!atomic_read(&core->reset.pending))
+		return;
+
+	drm_sched_stop(&core->sched, bad);
+
+	/*
+	 * 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().
+	 */
+	scoped_guard(mutex, &core->job_lock) {
+		if (core->in_flight_job)
+			pm_runtime_put_noidle(core->dev);
+
+		iommu_detach_group(NULL, core->iommu_group);
+
+		core->in_flight_job = NULL;
+	}
+
+	/* Proceed with reset now. */
+	rocket_core_reset(core);
+
+	/* NPU has been reset, we can clear the reset pending bit. */
+	atomic_set(&core->reset.pending, 0);
+
+	/* Restart the scheduler */
+	drm_sched_start(&core->sched, 0);
+}
+
+static enum drm_gpu_sched_stat rocket_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct rocket_job *job = to_rocket_job(sched_job);
+	struct rocket_device *rdev = job->rdev;
+	struct rocket_core *core = sched_to_core(rdev, sched_job->sched);
+
+	dev_err(core->dev, "NPU job timed out");
+
+	atomic_set(&core->reset.pending, 1);
+	rocket_reset(core, sched_job);
+
+	return DRM_GPU_SCHED_STAT_RESET;
+}
+
+static void rocket_reset_work(struct work_struct *work)
+{
+	struct rocket_core *core;
+
+	core = container_of(work, struct rocket_core, reset.work);
+	rocket_reset(core, NULL);
+}
+
+static const struct drm_sched_backend_ops rocket_sched_ops = {
+	.run_job = rocket_job_run,
+	.timedout_job = rocket_job_timedout,
+	.free_job = rocket_job_free
+};
+
+static irqreturn_t rocket_job_irq_handler_thread(int irq, void *data)
+{
+	struct rocket_core *core = data;
+
+	rocket_job_handle_irq(core);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t rocket_job_irq_handler(int irq, void *data)
+{
+	struct rocket_core *core = data;
+	u32 raw_status = rocket_pc_readl(core, INTERRUPT_RAW_STATUS);
+
+	WARN_ON(raw_status & PC_INTERRUPT_RAW_STATUS_DMA_READ_ERROR);
+	WARN_ON(raw_status & PC_INTERRUPT_RAW_STATUS_DMA_WRITE_ERROR);
+
+	if (!(raw_status & PC_INTERRUPT_RAW_STATUS_DPU_0 ||
+	      raw_status & PC_INTERRUPT_RAW_STATUS_DPU_1))
+		return IRQ_NONE;
+
+	rocket_pc_writel(core, INTERRUPT_MASK, 0x0);
+
+	return IRQ_WAKE_THREAD;
+}
+
+int rocket_job_init(struct rocket_core *core)
+{
+	struct drm_sched_init_args args = {
+		.ops = &rocket_sched_ops,
+		.num_rqs = DRM_SCHED_PRIORITY_COUNT,
+		.credit_limit = 1,
+		.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS),
+		.name = dev_name(core->dev),
+		.dev = core->dev,
+	};
+	int ret;
+
+	INIT_WORK(&core->reset.work, rocket_reset_work);
+	spin_lock_init(&core->fence_lock);
+	mutex_init(&core->job_lock);
+
+	core->irq = platform_get_irq(to_platform_device(core->dev), 0);
+	if (core->irq < 0)
+		return core->irq;
+
+	ret = devm_request_threaded_irq(core->dev, core->irq,
+					rocket_job_irq_handler,
+					rocket_job_irq_handler_thread,
+					IRQF_SHARED, dev_name(core->dev),
+					core);
+	if (ret) {
+		dev_err(core->dev, "failed to request job irq");
+		return ret;
+	}
+
+	core->reset.wq = alloc_ordered_workqueue("rocket-reset-%d", 0, core->index);
+	if (!core->reset.wq)
+		return -ENOMEM;
+
+	core->fence_context = dma_fence_context_alloc(1);
+
+	args.timeout_wq = core->reset.wq;
+	ret = drm_sched_init(&core->sched, &args);
+	if (ret) {
+		dev_err(core->dev, "Failed to create scheduler: %d.", ret);
+		goto err_sched;
+	}
+
+	return 0;
+
+err_sched:
+	drm_sched_fini(&core->sched);
+
+	destroy_workqueue(core->reset.wq);
+	return ret;
+}
+
+void rocket_job_fini(struct rocket_core *core)
+{
+	drm_sched_fini(&core->sched);
+
+	cancel_work_sync(&core->reset.work);
+	destroy_workqueue(core->reset.wq);
+}
+
+int rocket_job_open(struct rocket_file_priv *rocket_priv)
+{
+	struct rocket_device *rdev = rocket_priv->rdev;
+	struct drm_gpu_scheduler **scheds = kmalloc_array(rdev->num_cores,
+							  sizeof(*scheds),
+							  GFP_KERNEL);
+	unsigned int core;
+	int ret;
+
+	for (core = 0; core < rdev->num_cores; core++)
+		scheds[core] = &rdev->cores[core].sched;
+
+	ret = drm_sched_entity_init(&rocket_priv->sched_entity,
+				    DRM_SCHED_PRIORITY_NORMAL,
+				    scheds,
+				    rdev->num_cores, NULL);
+	if (WARN_ON(ret))
+		return ret;
+
+	return 0;
+}
+
+void rocket_job_close(struct rocket_file_priv *rocket_priv)
+{
+	struct drm_sched_entity *entity = &rocket_priv->sched_entity;
+
+	kfree(entity->sched_list);
+	drm_sched_entity_destroy(entity);
+}
+
+int rocket_job_is_idle(struct rocket_core *core)
+{
+	/* If there are any jobs in this HW queue, we're not idle */
+	if (atomic_read(&core->sched.credit_count))
+		return false;
+
+	return true;
+}
+
+static int rocket_ioctl_submit_job(struct drm_device *dev, struct drm_file *file,
+				   struct drm_rocket_job *job)
+{
+	struct rocket_device *rdev = to_rocket_device(dev);
+	struct rocket_file_priv *file_priv = file->driver_priv;
+	struct rocket_job *rjob = NULL;
+	int ret = 0;
+
+	if (job->task_count == 0)
+		return -EINVAL;
+
+	rjob = kzalloc(sizeof(*rjob), GFP_KERNEL);
+	if (!rjob)
+		return -ENOMEM;
+
+	kref_init(&rjob->refcount);
+
+	rjob->rdev = rdev;
+
+	ret = drm_sched_job_init(&rjob->base,
+				 &file_priv->sched_entity,
+				 1, NULL, file->client_id);
+	if (ret)
+		goto out_put_job;
+
+	ret = rocket_copy_tasks(dev, file, job, rjob);
+	if (ret)
+		goto out_cleanup_job;
+
+	ret = drm_gem_objects_lookup(file, u64_to_user_ptr(job->in_bo_handles),
+				     job->in_bo_handle_count, &rjob->in_bos);
+	if (ret)
+		goto out_cleanup_job;
+
+	rjob->in_bo_count = job->in_bo_handle_count;
+
+	ret = drm_gem_objects_lookup(file, u64_to_user_ptr(job->out_bo_handles),
+				     job->out_bo_handle_count, &rjob->out_bos);
+	if (ret)
+		goto out_cleanup_job;
+
+	rjob->out_bo_count = job->out_bo_handle_count;
+
+	rjob->domain = rocket_iommu_domain_get(file_priv);
+
+	ret = rocket_job_push(rjob);
+	if (ret)
+		goto out_cleanup_job;
+
+out_cleanup_job:
+	if (ret)
+		drm_sched_job_cleanup(&rjob->base);
+out_put_job:
+	rocket_job_put(rjob);
+
+	return ret;
+}
+
+int rocket_ioctl_submit(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_rocket_submit *args = data;
+	struct drm_rocket_job *jobs;
+	int ret = 0;
+	unsigned int i = 0;
+
+	if (args->job_count == 0)
+		return 0;
+
+	if (args->job_struct_size < sizeof(struct drm_rocket_job)) {
+		drm_dbg(dev, "job_struct_size field in drm_rocket_submit struct is too small.\n");
+		return -EINVAL;
+	}
+
+	if (args->reserved != 0) {
+		drm_dbg(dev, "Reserved field in drm_rocket_submit struct should be 0.\n");
+		return -EINVAL;
+	}
+
+	jobs = kvmalloc_array(args->job_count, sizeof(*jobs), GFP_KERNEL);
+	if (!jobs) {
+		drm_dbg(dev, "Failed to allocate incoming job array\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < args->job_count; i++) {
+		if (copy_from_user(&jobs[i],
+				   u64_to_user_ptr(args->jobs) + i * args->job_struct_size,
+				   sizeof(*jobs))) {
+			ret = -EFAULT;
+			drm_dbg(dev, "Failed to copy incoming job array\n");
+			goto exit;
+		}
+	}
+
+
+	for (i = 0; i < args->job_count; i++)
+		rocket_ioctl_submit_job(dev, file, &jobs[i]);
+
+exit:
+	kvfree(jobs);
+
+	return ret;
+}
diff --git a/drivers/accel/rocket/rocket_job.h b/drivers/accel/rocket/rocket_job.h
new file mode 100644
index 000000000000..4ae00feec3b9
--- /dev/null
+++ b/drivers/accel/rocket/rocket_job.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_JOB_H__
+#define __ROCKET_JOB_H__
+
+#include <drm/drm_drv.h>
+#include <drm/gpu_scheduler.h>
+
+#include "rocket_core.h"
+#include "rocket_drv.h"
+
+struct rocket_task {
+	u64 regcmd;
+	u32 regcmd_count;
+};
+
+struct rocket_job {
+	struct drm_sched_job base;
+
+	struct rocket_device *rdev;
+
+	struct drm_gem_object **in_bos;
+	struct drm_gem_object **out_bos;
+
+	u32 in_bo_count;
+	u32 out_bo_count;
+
+	struct rocket_task *tasks;
+	u32 task_count;
+	u32 next_task_idx;
+
+	/* Fence to be signaled by drm-sched once its done with the job */
+	struct dma_fence *inference_done_fence;
+
+	/* Fence to be signaled by IRQ handler when the job is complete. */
+	struct dma_fence *done_fence;
+
+	struct rocket_iommu_domain *domain;
+
+	struct kref refcount;
+};
+
+int rocket_ioctl_submit(struct drm_device *dev, void *data, struct drm_file *file);
+
+int rocket_job_init(struct rocket_core *core);
+void rocket_job_fini(struct rocket_core *core);
+int rocket_job_open(struct rocket_file_priv *rocket_priv);
+void rocket_job_close(struct rocket_file_priv *rocket_priv);
+int rocket_job_is_idle(struct rocket_core *core);
+
+#endif
diff --git a/drivers/accel/rocket/rocket_registers.h b/drivers/accel/rocket/rocket_registers.h
new file mode 100644
index 000000000000..9aef614c3470
--- /dev/null
+++ b/drivers/accel/rocket/rocket_registers.h
@@ -0,0 +1,4404 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+
+#ifndef __ROCKET_REGISTERS_XML__
+#define __ROCKET_REGISTERS_XML__
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng gen_header.py tool in this git repository:
+http://gitlab.freedesktop.org/mesa/mesa/
+git clone https://gitlab.freedesktop.org/mesa/mesa.git
+
+The rules-ng-ng source files this header was generated from are:
+
+- /home/tomeu/src/mesa/src/gallium/drivers/rocket/registers.xml (  60076 bytes, from Wed Jun 12 10:02:25 2024)
+
+Copyright (C) 2024-2025 by the following authors:
+- Tomeu Vizoso <tomeu@tomeuvizoso.net>
+*/
+
+#define REG_PC_VERSION						0x00000000
+#define PC_VERSION_VERSION__MASK				0xffffffff
+#define PC_VERSION_VERSION__SHIFT				0
+static inline uint32_t PC_VERSION_VERSION(uint32_t val)
+{
+	return ((val) << PC_VERSION_VERSION__SHIFT) & PC_VERSION_VERSION__MASK;
+}
+
+#define REG_PC_VERSION_NUM					0x00000004
+#define PC_VERSION_NUM_VERSION_NUM__MASK			0xffffffff
+#define PC_VERSION_NUM_VERSION_NUM__SHIFT			0
+static inline uint32_t PC_VERSION_NUM_VERSION_NUM(uint32_t val)
+{
+	return ((val) << PC_VERSION_NUM_VERSION_NUM__SHIFT) & PC_VERSION_NUM_VERSION_NUM__MASK;
+}
+
+#define REG_PC_OPERATION_ENABLE					0x00000008
+#define PC_OPERATION_ENABLE_RESERVED_0__MASK			0xfffffffe
+#define PC_OPERATION_ENABLE_RESERVED_0__SHIFT			1
+static inline uint32_t PC_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_OPERATION_ENABLE_RESERVED_0__SHIFT) & PC_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define PC_OPERATION_ENABLE_OP_EN__MASK				0x00000001
+#define PC_OPERATION_ENABLE_OP_EN__SHIFT			0
+static inline uint32_t PC_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << PC_OPERATION_ENABLE_OP_EN__SHIFT) & PC_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_PC_BASE_ADDRESS					0x00000010
+#define PC_BASE_ADDRESS_PC_SOURCE_ADDR__MASK			0xfffffff0
+#define PC_BASE_ADDRESS_PC_SOURCE_ADDR__SHIFT			4
+static inline uint32_t PC_BASE_ADDRESS_PC_SOURCE_ADDR(uint32_t val)
+{
+	return ((val) << PC_BASE_ADDRESS_PC_SOURCE_ADDR__SHIFT) & PC_BASE_ADDRESS_PC_SOURCE_ADDR__MASK;
+}
+#define PC_BASE_ADDRESS_RESERVED_0__MASK			0x0000000e
+#define PC_BASE_ADDRESS_RESERVED_0__SHIFT			1
+static inline uint32_t PC_BASE_ADDRESS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_BASE_ADDRESS_RESERVED_0__SHIFT) & PC_BASE_ADDRESS_RESERVED_0__MASK;
+}
+#define PC_BASE_ADDRESS_PC_SEL__MASK				0x00000001
+#define PC_BASE_ADDRESS_PC_SEL__SHIFT				0
+static inline uint32_t PC_BASE_ADDRESS_PC_SEL(uint32_t val)
+{
+	return ((val) << PC_BASE_ADDRESS_PC_SEL__SHIFT) & PC_BASE_ADDRESS_PC_SEL__MASK;
+}
+
+#define REG_PC_REGISTER_AMOUNTS					0x00000014
+#define PC_REGISTER_AMOUNTS_RESERVED_0__MASK			0xffff0000
+#define PC_REGISTER_AMOUNTS_RESERVED_0__SHIFT			16
+static inline uint32_t PC_REGISTER_AMOUNTS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_REGISTER_AMOUNTS_RESERVED_0__SHIFT) & PC_REGISTER_AMOUNTS_RESERVED_0__MASK;
+}
+#define PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT__MASK		0x0000ffff
+#define PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT__SHIFT		0
+static inline uint32_t PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT(uint32_t val)
+{
+	return ((val) << PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT__SHIFT) & PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT__MASK;
+}
+
+#define REG_PC_INTERRUPT_MASK					0x00000020
+#define PC_INTERRUPT_MASK_RESERVED_0__MASK			0xffffc000
+#define PC_INTERRUPT_MASK_RESERVED_0__SHIFT			14
+static inline uint32_t PC_INTERRUPT_MASK_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_INTERRUPT_MASK_RESERVED_0__SHIFT) & PC_INTERRUPT_MASK_RESERVED_0__MASK;
+}
+#define PC_INTERRUPT_MASK_DMA_WRITE_ERROR			0x00002000
+#define PC_INTERRUPT_MASK_DMA_READ_ERROR			0x00001000
+#define PC_INTERRUPT_MASK_PPU_1					0x00000800
+#define PC_INTERRUPT_MASK_PPU_0					0x00000400
+#define PC_INTERRUPT_MASK_DPU_1					0x00000200
+#define PC_INTERRUPT_MASK_DPU_0					0x00000100
+#define PC_INTERRUPT_MASK_CORE_1				0x00000080
+#define PC_INTERRUPT_MASK_CORE_0				0x00000040
+#define PC_INTERRUPT_MASK_CNA_CSC_1				0x00000020
+#define PC_INTERRUPT_MASK_CNA_CSC_0				0x00000010
+#define PC_INTERRUPT_MASK_CNA_WEIGHT_1				0x00000008
+#define PC_INTERRUPT_MASK_CNA_WEIGHT_0				0x00000004
+#define PC_INTERRUPT_MASK_CNA_FEATURE_1				0x00000002
+#define PC_INTERRUPT_MASK_CNA_FEATURE_0				0x00000001
+
+#define REG_PC_INTERRUPT_CLEAR					0x00000024
+#define PC_INTERRUPT_CLEAR_RESERVED_0__MASK			0xffffc000
+#define PC_INTERRUPT_CLEAR_RESERVED_0__SHIFT			14
+static inline uint32_t PC_INTERRUPT_CLEAR_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_INTERRUPT_CLEAR_RESERVED_0__SHIFT) & PC_INTERRUPT_CLEAR_RESERVED_0__MASK;
+}
+#define PC_INTERRUPT_CLEAR_DMA_WRITE_ERROR			0x00002000
+#define PC_INTERRUPT_CLEAR_DMA_READ_ERROR			0x00001000
+#define PC_INTERRUPT_CLEAR_PPU_1				0x00000800
+#define PC_INTERRUPT_CLEAR_PPU_0				0x00000400
+#define PC_INTERRUPT_CLEAR_DPU_1				0x00000200
+#define PC_INTERRUPT_CLEAR_DPU_0				0x00000100
+#define PC_INTERRUPT_CLEAR_CORE_1				0x00000080
+#define PC_INTERRUPT_CLEAR_CORE_0				0x00000040
+#define PC_INTERRUPT_CLEAR_CNA_CSC_1				0x00000020
+#define PC_INTERRUPT_CLEAR_CNA_CSC_0				0x00000010
+#define PC_INTERRUPT_CLEAR_CNA_WEIGHT_1				0x00000008
+#define PC_INTERRUPT_CLEAR_CNA_WEIGHT_0				0x00000004
+#define PC_INTERRUPT_CLEAR_CNA_FEATURE_1			0x00000002
+#define PC_INTERRUPT_CLEAR_CNA_FEATURE_0			0x00000001
+
+#define REG_PC_INTERRUPT_STATUS					0x00000028
+#define PC_INTERRUPT_STATUS_RESERVED_0__MASK			0xffffc000
+#define PC_INTERRUPT_STATUS_RESERVED_0__SHIFT			14
+static inline uint32_t PC_INTERRUPT_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_INTERRUPT_STATUS_RESERVED_0__SHIFT) & PC_INTERRUPT_STATUS_RESERVED_0__MASK;
+}
+#define PC_INTERRUPT_STATUS_DMA_WRITE_ERROR			0x00002000
+#define PC_INTERRUPT_STATUS_DMA_READ_ERROR			0x00001000
+#define PC_INTERRUPT_STATUS_PPU_1				0x00000800
+#define PC_INTERRUPT_STATUS_PPU_0				0x00000400
+#define PC_INTERRUPT_STATUS_DPU_1				0x00000200
+#define PC_INTERRUPT_STATUS_DPU_0				0x00000100
+#define PC_INTERRUPT_STATUS_CORE_1				0x00000080
+#define PC_INTERRUPT_STATUS_CORE_0				0x00000040
+#define PC_INTERRUPT_STATUS_CNA_CSC_1				0x00000020
+#define PC_INTERRUPT_STATUS_CNA_CSC_0				0x00000010
+#define PC_INTERRUPT_STATUS_CNA_WEIGHT_1			0x00000008
+#define PC_INTERRUPT_STATUS_CNA_WEIGHT_0			0x00000004
+#define PC_INTERRUPT_STATUS_CNA_FEATURE_1			0x00000002
+#define PC_INTERRUPT_STATUS_CNA_FEATURE_0			0x00000001
+
+#define REG_PC_INTERRUPT_RAW_STATUS				0x0000002c
+#define PC_INTERRUPT_RAW_STATUS_RESERVED_0__MASK		0xffffc000
+#define PC_INTERRUPT_RAW_STATUS_RESERVED_0__SHIFT		14
+static inline uint32_t PC_INTERRUPT_RAW_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_INTERRUPT_RAW_STATUS_RESERVED_0__SHIFT) & PC_INTERRUPT_RAW_STATUS_RESERVED_0__MASK;
+}
+#define PC_INTERRUPT_RAW_STATUS_DMA_WRITE_ERROR			0x00002000
+#define PC_INTERRUPT_RAW_STATUS_DMA_READ_ERROR			0x00001000
+#define PC_INTERRUPT_RAW_STATUS_PPU_1				0x00000800
+#define PC_INTERRUPT_RAW_STATUS_PPU_0				0x00000400
+#define PC_INTERRUPT_RAW_STATUS_DPU_1				0x00000200
+#define PC_INTERRUPT_RAW_STATUS_DPU_0				0x00000100
+#define PC_INTERRUPT_RAW_STATUS_CORE_1				0x00000080
+#define PC_INTERRUPT_RAW_STATUS_CORE_0				0x00000040
+#define PC_INTERRUPT_RAW_STATUS_CNA_CSC_1			0x00000020
+#define PC_INTERRUPT_RAW_STATUS_CNA_CSC_0			0x00000010
+#define PC_INTERRUPT_RAW_STATUS_CNA_WEIGHT_1			0x00000008
+#define PC_INTERRUPT_RAW_STATUS_CNA_WEIGHT_0			0x00000004
+#define PC_INTERRUPT_RAW_STATUS_CNA_FEATURE_1			0x00000002
+#define PC_INTERRUPT_RAW_STATUS_CNA_FEATURE_0			0x00000001
+
+#define REG_PC_TASK_CON						0x00000030
+#define PC_TASK_CON_RESERVED_0__MASK				0xffffc000
+#define PC_TASK_CON_RESERVED_0__SHIFT				14
+static inline uint32_t PC_TASK_CON_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_TASK_CON_RESERVED_0__SHIFT) & PC_TASK_CON_RESERVED_0__MASK;
+}
+#define PC_TASK_CON_TASK_COUNT_CLEAR__MASK			0x00002000
+#define PC_TASK_CON_TASK_COUNT_CLEAR__SHIFT			13
+static inline uint32_t PC_TASK_CON_TASK_COUNT_CLEAR(uint32_t val)
+{
+	return ((val) << PC_TASK_CON_TASK_COUNT_CLEAR__SHIFT) & PC_TASK_CON_TASK_COUNT_CLEAR__MASK;
+}
+#define PC_TASK_CON_TASK_PP_EN__MASK				0x00001000
+#define PC_TASK_CON_TASK_PP_EN__SHIFT				12
+static inline uint32_t PC_TASK_CON_TASK_PP_EN(uint32_t val)
+{
+	return ((val) << PC_TASK_CON_TASK_PP_EN__SHIFT) & PC_TASK_CON_TASK_PP_EN__MASK;
+}
+#define PC_TASK_CON_TASK_NUMBER__MASK				0x00000fff
+#define PC_TASK_CON_TASK_NUMBER__SHIFT				0
+static inline uint32_t PC_TASK_CON_TASK_NUMBER(uint32_t val)
+{
+	return ((val) << PC_TASK_CON_TASK_NUMBER__SHIFT) & PC_TASK_CON_TASK_NUMBER__MASK;
+}
+
+#define REG_PC_TASK_DMA_BASE_ADDR				0x00000034
+#define PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR__MASK		0xfffffff0
+#define PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR__SHIFT		4
+static inline uint32_t PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR(uint32_t val)
+{
+	return ((val) << PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR__SHIFT) & PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR__MASK;
+}
+#define PC_TASK_DMA_BASE_ADDR_RESERVED_0__MASK			0x0000000f
+#define PC_TASK_DMA_BASE_ADDR_RESERVED_0__SHIFT			0
+static inline uint32_t PC_TASK_DMA_BASE_ADDR_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_TASK_DMA_BASE_ADDR_RESERVED_0__SHIFT) & PC_TASK_DMA_BASE_ADDR_RESERVED_0__MASK;
+}
+
+#define REG_PC_TASK_STATUS					0x0000003c
+#define PC_TASK_STATUS_RESERVED_0__MASK				0xf0000000
+#define PC_TASK_STATUS_RESERVED_0__SHIFT			28
+static inline uint32_t PC_TASK_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PC_TASK_STATUS_RESERVED_0__SHIFT) & PC_TASK_STATUS_RESERVED_0__MASK;
+}
+#define PC_TASK_STATUS_TASK_STATUS__MASK			0x0fffffff
+#define PC_TASK_STATUS_TASK_STATUS__SHIFT			0
+static inline uint32_t PC_TASK_STATUS_TASK_STATUS(uint32_t val)
+{
+	return ((val) << PC_TASK_STATUS_TASK_STATUS__SHIFT) & PC_TASK_STATUS_TASK_STATUS__MASK;
+}
+
+#define REG_CNA_S_STATUS					0x00001000
+#define CNA_S_STATUS_RESERVED_0__MASK				0xfffc0000
+#define CNA_S_STATUS_RESERVED_0__SHIFT				18
+static inline uint32_t CNA_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_S_STATUS_RESERVED_0__SHIFT) & CNA_S_STATUS_RESERVED_0__MASK;
+}
+#define CNA_S_STATUS_STATUS_1__MASK				0x00030000
+#define CNA_S_STATUS_STATUS_1__SHIFT				16
+static inline uint32_t CNA_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << CNA_S_STATUS_STATUS_1__SHIFT) & CNA_S_STATUS_STATUS_1__MASK;
+}
+#define CNA_S_STATUS_RESERVED_1__MASK				0x0000fffc
+#define CNA_S_STATUS_RESERVED_1__SHIFT				2
+static inline uint32_t CNA_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_S_STATUS_RESERVED_1__SHIFT) & CNA_S_STATUS_RESERVED_1__MASK;
+}
+#define CNA_S_STATUS_STATUS_0__MASK				0x00000003
+#define CNA_S_STATUS_STATUS_0__SHIFT				0
+static inline uint32_t CNA_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << CNA_S_STATUS_STATUS_0__SHIFT) & CNA_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_CNA_S_POINTER					0x00001004
+#define CNA_S_POINTER_RESERVED_0__MASK				0xfffe0000
+#define CNA_S_POINTER_RESERVED_0__SHIFT				17
+static inline uint32_t CNA_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_RESERVED_0__SHIFT) & CNA_S_POINTER_RESERVED_0__MASK;
+}
+#define CNA_S_POINTER_EXECUTER__MASK				0x00010000
+#define CNA_S_POINTER_EXECUTER__SHIFT				16
+static inline uint32_t CNA_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_EXECUTER__SHIFT) & CNA_S_POINTER_EXECUTER__MASK;
+}
+#define CNA_S_POINTER_RESERVED_1__MASK				0x0000ffc0
+#define CNA_S_POINTER_RESERVED_1__SHIFT				6
+static inline uint32_t CNA_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_RESERVED_1__SHIFT) & CNA_S_POINTER_RESERVED_1__MASK;
+}
+#define CNA_S_POINTER_EXECUTER_PP_CLEAR__MASK			0x00000020
+#define CNA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT			5
+static inline uint32_t CNA_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & CNA_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define CNA_S_POINTER_POINTER_PP_CLEAR__MASK			0x00000010
+#define CNA_S_POINTER_POINTER_PP_CLEAR__SHIFT			4
+static inline uint32_t CNA_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_POINTER_PP_CLEAR__SHIFT) & CNA_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define CNA_S_POINTER_POINTER_PP_MODE__MASK			0x00000008
+#define CNA_S_POINTER_POINTER_PP_MODE__SHIFT			3
+static inline uint32_t CNA_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_POINTER_PP_MODE__SHIFT) & CNA_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define CNA_S_POINTER_EXECUTER_PP_EN__MASK			0x00000004
+#define CNA_S_POINTER_EXECUTER_PP_EN__SHIFT			2
+static inline uint32_t CNA_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_EXECUTER_PP_EN__SHIFT) & CNA_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define CNA_S_POINTER_POINTER_PP_EN__MASK			0x00000002
+#define CNA_S_POINTER_POINTER_PP_EN__SHIFT			1
+static inline uint32_t CNA_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_POINTER_PP_EN__SHIFT) & CNA_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define CNA_S_POINTER_POINTER__MASK				0x00000001
+#define CNA_S_POINTER_POINTER__SHIFT				0
+static inline uint32_t CNA_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << CNA_S_POINTER_POINTER__SHIFT) & CNA_S_POINTER_POINTER__MASK;
+}
+
+#define REG_CNA_OPERATION_ENABLE				0x00001008
+#define CNA_OPERATION_ENABLE_RESERVED_0__MASK			0xfffffffe
+#define CNA_OPERATION_ENABLE_RESERVED_0__SHIFT			1
+static inline uint32_t CNA_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_OPERATION_ENABLE_RESERVED_0__SHIFT) & CNA_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define CNA_OPERATION_ENABLE_OP_EN__MASK			0x00000001
+#define CNA_OPERATION_ENABLE_OP_EN__SHIFT			0
+static inline uint32_t CNA_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << CNA_OPERATION_ENABLE_OP_EN__SHIFT) & CNA_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_CNA_CONV_CON1					0x0000100c
+#define CNA_CONV_CON1_RESERVED_0__MASK				0x80000000
+#define CNA_CONV_CON1_RESERVED_0__SHIFT				31
+static inline uint32_t CNA_CONV_CON1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_RESERVED_0__SHIFT) & CNA_CONV_CON1_RESERVED_0__MASK;
+}
+#define CNA_CONV_CON1_NONALIGN_DMA__MASK			0x40000000
+#define CNA_CONV_CON1_NONALIGN_DMA__SHIFT			30
+static inline uint32_t CNA_CONV_CON1_NONALIGN_DMA(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_NONALIGN_DMA__SHIFT) & CNA_CONV_CON1_NONALIGN_DMA__MASK;
+}
+#define CNA_CONV_CON1_GROUP_LINE_OFF__MASK			0x20000000
+#define CNA_CONV_CON1_GROUP_LINE_OFF__SHIFT			29
+static inline uint32_t CNA_CONV_CON1_GROUP_LINE_OFF(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_GROUP_LINE_OFF__SHIFT) & CNA_CONV_CON1_GROUP_LINE_OFF__MASK;
+}
+#define CNA_CONV_CON1_RESERVED_1__MASK				0x1ffe0000
+#define CNA_CONV_CON1_RESERVED_1__SHIFT				17
+static inline uint32_t CNA_CONV_CON1_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_RESERVED_1__SHIFT) & CNA_CONV_CON1_RESERVED_1__MASK;
+}
+#define CNA_CONV_CON1_DECONV__MASK				0x00010000
+#define CNA_CONV_CON1_DECONV__SHIFT				16
+static inline uint32_t CNA_CONV_CON1_DECONV(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_DECONV__SHIFT) & CNA_CONV_CON1_DECONV__MASK;
+}
+#define CNA_CONV_CON1_ARGB_IN__MASK				0x0000f000
+#define CNA_CONV_CON1_ARGB_IN__SHIFT				12
+static inline uint32_t CNA_CONV_CON1_ARGB_IN(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_ARGB_IN__SHIFT) & CNA_CONV_CON1_ARGB_IN__MASK;
+}
+#define CNA_CONV_CON1_RESERVED_2__MASK				0x00000c00
+#define CNA_CONV_CON1_RESERVED_2__SHIFT				10
+static inline uint32_t CNA_CONV_CON1_RESERVED_2(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_RESERVED_2__SHIFT) & CNA_CONV_CON1_RESERVED_2__MASK;
+}
+#define CNA_CONV_CON1_PROC_PRECISION__MASK			0x00000380
+#define CNA_CONV_CON1_PROC_PRECISION__SHIFT			7
+static inline uint32_t CNA_CONV_CON1_PROC_PRECISION(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_PROC_PRECISION__SHIFT) & CNA_CONV_CON1_PROC_PRECISION__MASK;
+}
+#define CNA_CONV_CON1_IN_PRECISION__MASK			0x00000070
+#define CNA_CONV_CON1_IN_PRECISION__SHIFT			4
+static inline uint32_t CNA_CONV_CON1_IN_PRECISION(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_IN_PRECISION__SHIFT) & CNA_CONV_CON1_IN_PRECISION__MASK;
+}
+#define CNA_CONV_CON1_CONV_MODE__MASK				0x0000000f
+#define CNA_CONV_CON1_CONV_MODE__SHIFT				0
+static inline uint32_t CNA_CONV_CON1_CONV_MODE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON1_CONV_MODE__SHIFT) & CNA_CONV_CON1_CONV_MODE__MASK;
+}
+
+#define REG_CNA_CONV_CON2					0x00001010
+#define CNA_CONV_CON2_RESERVED_0__MASK				0xff000000
+#define CNA_CONV_CON2_RESERVED_0__SHIFT				24
+static inline uint32_t CNA_CONV_CON2_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_RESERVED_0__SHIFT) & CNA_CONV_CON2_RESERVED_0__MASK;
+}
+#define CNA_CONV_CON2_KERNEL_GROUP__MASK			0x00ff0000
+#define CNA_CONV_CON2_KERNEL_GROUP__SHIFT			16
+static inline uint32_t CNA_CONV_CON2_KERNEL_GROUP(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_KERNEL_GROUP__SHIFT) & CNA_CONV_CON2_KERNEL_GROUP__MASK;
+}
+#define CNA_CONV_CON2_RESERVED_1__MASK				0x0000c000
+#define CNA_CONV_CON2_RESERVED_1__SHIFT				14
+static inline uint32_t CNA_CONV_CON2_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_RESERVED_1__SHIFT) & CNA_CONV_CON2_RESERVED_1__MASK;
+}
+#define CNA_CONV_CON2_FEATURE_GRAINS__MASK			0x00003ff0
+#define CNA_CONV_CON2_FEATURE_GRAINS__SHIFT			4
+static inline uint32_t CNA_CONV_CON2_FEATURE_GRAINS(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_FEATURE_GRAINS__SHIFT) & CNA_CONV_CON2_FEATURE_GRAINS__MASK;
+}
+#define CNA_CONV_CON2_RESERVED_2__MASK				0x00000008
+#define CNA_CONV_CON2_RESERVED_2__SHIFT				3
+static inline uint32_t CNA_CONV_CON2_RESERVED_2(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_RESERVED_2__SHIFT) & CNA_CONV_CON2_RESERVED_2__MASK;
+}
+#define CNA_CONV_CON2_CSC_WO_EN__MASK				0x00000004
+#define CNA_CONV_CON2_CSC_WO_EN__SHIFT				2
+static inline uint32_t CNA_CONV_CON2_CSC_WO_EN(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_CSC_WO_EN__SHIFT) & CNA_CONV_CON2_CSC_WO_EN__MASK;
+}
+#define CNA_CONV_CON2_CSC_DO_EN__MASK				0x00000002
+#define CNA_CONV_CON2_CSC_DO_EN__SHIFT				1
+static inline uint32_t CNA_CONV_CON2_CSC_DO_EN(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_CSC_DO_EN__SHIFT) & CNA_CONV_CON2_CSC_DO_EN__MASK;
+}
+#define CNA_CONV_CON2_CMD_FIFO_SRST__MASK			0x00000001
+#define CNA_CONV_CON2_CMD_FIFO_SRST__SHIFT			0
+static inline uint32_t CNA_CONV_CON2_CMD_FIFO_SRST(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON2_CMD_FIFO_SRST__SHIFT) & CNA_CONV_CON2_CMD_FIFO_SRST__MASK;
+}
+
+#define REG_CNA_CONV_CON3					0x00001014
+#define CNA_CONV_CON3_RESERVED_0__MASK				0x80000000
+#define CNA_CONV_CON3_RESERVED_0__SHIFT				31
+static inline uint32_t CNA_CONV_CON3_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_RESERVED_0__SHIFT) & CNA_CONV_CON3_RESERVED_0__MASK;
+}
+#define CNA_CONV_CON3_NN_MODE__MASK				0x70000000
+#define CNA_CONV_CON3_NN_MODE__SHIFT				28
+static inline uint32_t CNA_CONV_CON3_NN_MODE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_NN_MODE__SHIFT) & CNA_CONV_CON3_NN_MODE__MASK;
+}
+#define CNA_CONV_CON3_RESERVED_1__MASK				0x0c000000
+#define CNA_CONV_CON3_RESERVED_1__SHIFT				26
+static inline uint32_t CNA_CONV_CON3_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_RESERVED_1__SHIFT) & CNA_CONV_CON3_RESERVED_1__MASK;
+}
+#define CNA_CONV_CON3_ATROUS_Y_DILATION__MASK			0x03e00000
+#define CNA_CONV_CON3_ATROUS_Y_DILATION__SHIFT			21
+static inline uint32_t CNA_CONV_CON3_ATROUS_Y_DILATION(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_ATROUS_Y_DILATION__SHIFT) & CNA_CONV_CON3_ATROUS_Y_DILATION__MASK;
+}
+#define CNA_CONV_CON3_ATROUS_X_DILATION__MASK			0x001f0000
+#define CNA_CONV_CON3_ATROUS_X_DILATION__SHIFT			16
+static inline uint32_t CNA_CONV_CON3_ATROUS_X_DILATION(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_ATROUS_X_DILATION__SHIFT) & CNA_CONV_CON3_ATROUS_X_DILATION__MASK;
+}
+#define CNA_CONV_CON3_RESERVED_2__MASK				0x0000c000
+#define CNA_CONV_CON3_RESERVED_2__SHIFT				14
+static inline uint32_t CNA_CONV_CON3_RESERVED_2(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_RESERVED_2__SHIFT) & CNA_CONV_CON3_RESERVED_2__MASK;
+}
+#define CNA_CONV_CON3_DECONV_Y_STRIDE__MASK			0x00003800
+#define CNA_CONV_CON3_DECONV_Y_STRIDE__SHIFT			11
+static inline uint32_t CNA_CONV_CON3_DECONV_Y_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_DECONV_Y_STRIDE__SHIFT) & CNA_CONV_CON3_DECONV_Y_STRIDE__MASK;
+}
+#define CNA_CONV_CON3_DECONV_X_STRIDE__MASK			0x00000700
+#define CNA_CONV_CON3_DECONV_X_STRIDE__SHIFT			8
+static inline uint32_t CNA_CONV_CON3_DECONV_X_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_DECONV_X_STRIDE__SHIFT) & CNA_CONV_CON3_DECONV_X_STRIDE__MASK;
+}
+#define CNA_CONV_CON3_RESERVED_3__MASK				0x000000c0
+#define CNA_CONV_CON3_RESERVED_3__SHIFT				6
+static inline uint32_t CNA_CONV_CON3_RESERVED_3(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_RESERVED_3__SHIFT) & CNA_CONV_CON3_RESERVED_3__MASK;
+}
+#define CNA_CONV_CON3_CONV_Y_STRIDE__MASK			0x00000038
+#define CNA_CONV_CON3_CONV_Y_STRIDE__SHIFT			3
+static inline uint32_t CNA_CONV_CON3_CONV_Y_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_CONV_Y_STRIDE__SHIFT) & CNA_CONV_CON3_CONV_Y_STRIDE__MASK;
+}
+#define CNA_CONV_CON3_CONV_X_STRIDE__MASK			0x00000007
+#define CNA_CONV_CON3_CONV_X_STRIDE__SHIFT			0
+static inline uint32_t CNA_CONV_CON3_CONV_X_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_CONV_CON3_CONV_X_STRIDE__SHIFT) & CNA_CONV_CON3_CONV_X_STRIDE__MASK;
+}
+
+#define REG_CNA_DATA_SIZE0					0x00001020
+#define CNA_DATA_SIZE0_RESERVED_0__MASK				0xf8000000
+#define CNA_DATA_SIZE0_RESERVED_0__SHIFT			27
+static inline uint32_t CNA_DATA_SIZE0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE0_RESERVED_0__SHIFT) & CNA_DATA_SIZE0_RESERVED_0__MASK;
+}
+#define CNA_DATA_SIZE0_DATAIN_WIDTH__MASK			0x07ff0000
+#define CNA_DATA_SIZE0_DATAIN_WIDTH__SHIFT			16
+static inline uint32_t CNA_DATA_SIZE0_DATAIN_WIDTH(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE0_DATAIN_WIDTH__SHIFT) & CNA_DATA_SIZE0_DATAIN_WIDTH__MASK;
+}
+#define CNA_DATA_SIZE0_RESERVED_1__MASK				0x0000f800
+#define CNA_DATA_SIZE0_RESERVED_1__SHIFT			11
+static inline uint32_t CNA_DATA_SIZE0_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE0_RESERVED_1__SHIFT) & CNA_DATA_SIZE0_RESERVED_1__MASK;
+}
+#define CNA_DATA_SIZE0_DATAIN_HEIGHT__MASK			0x000007ff
+#define CNA_DATA_SIZE0_DATAIN_HEIGHT__SHIFT			0
+static inline uint32_t CNA_DATA_SIZE0_DATAIN_HEIGHT(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE0_DATAIN_HEIGHT__SHIFT) & CNA_DATA_SIZE0_DATAIN_HEIGHT__MASK;
+}
+
+#define REG_CNA_DATA_SIZE1					0x00001024
+#define CNA_DATA_SIZE1_RESERVED_0__MASK				0xc0000000
+#define CNA_DATA_SIZE1_RESERVED_0__SHIFT			30
+static inline uint32_t CNA_DATA_SIZE1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE1_RESERVED_0__SHIFT) & CNA_DATA_SIZE1_RESERVED_0__MASK;
+}
+#define CNA_DATA_SIZE1_DATAIN_CHANNEL_REAL__MASK		0x3fff0000
+#define CNA_DATA_SIZE1_DATAIN_CHANNEL_REAL__SHIFT		16
+static inline uint32_t CNA_DATA_SIZE1_DATAIN_CHANNEL_REAL(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE1_DATAIN_CHANNEL_REAL__SHIFT) & CNA_DATA_SIZE1_DATAIN_CHANNEL_REAL__MASK;
+}
+#define CNA_DATA_SIZE1_DATAIN_CHANNEL__MASK			0x0000ffff
+#define CNA_DATA_SIZE1_DATAIN_CHANNEL__SHIFT			0
+static inline uint32_t CNA_DATA_SIZE1_DATAIN_CHANNEL(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE1_DATAIN_CHANNEL__SHIFT) & CNA_DATA_SIZE1_DATAIN_CHANNEL__MASK;
+}
+
+#define REG_CNA_DATA_SIZE2					0x00001028
+#define CNA_DATA_SIZE2_RESERVED_0__MASK				0xfffff800
+#define CNA_DATA_SIZE2_RESERVED_0__SHIFT			11
+static inline uint32_t CNA_DATA_SIZE2_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE2_RESERVED_0__SHIFT) & CNA_DATA_SIZE2_RESERVED_0__MASK;
+}
+#define CNA_DATA_SIZE2_DATAOUT_WIDTH__MASK			0x000007ff
+#define CNA_DATA_SIZE2_DATAOUT_WIDTH__SHIFT			0
+static inline uint32_t CNA_DATA_SIZE2_DATAOUT_WIDTH(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE2_DATAOUT_WIDTH__SHIFT) & CNA_DATA_SIZE2_DATAOUT_WIDTH__MASK;
+}
+
+#define REG_CNA_DATA_SIZE3					0x0000102c
+#define CNA_DATA_SIZE3_RESERVED_0__MASK				0xff000000
+#define CNA_DATA_SIZE3_RESERVED_0__SHIFT			24
+static inline uint32_t CNA_DATA_SIZE3_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE3_RESERVED_0__SHIFT) & CNA_DATA_SIZE3_RESERVED_0__MASK;
+}
+#define CNA_DATA_SIZE3_SURF_MODE__MASK				0x00c00000
+#define CNA_DATA_SIZE3_SURF_MODE__SHIFT				22
+static inline uint32_t CNA_DATA_SIZE3_SURF_MODE(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE3_SURF_MODE__SHIFT) & CNA_DATA_SIZE3_SURF_MODE__MASK;
+}
+#define CNA_DATA_SIZE3_DATAOUT_ATOMICS__MASK			0x003fffff
+#define CNA_DATA_SIZE3_DATAOUT_ATOMICS__SHIFT			0
+static inline uint32_t CNA_DATA_SIZE3_DATAOUT_ATOMICS(uint32_t val)
+{
+	return ((val) << CNA_DATA_SIZE3_DATAOUT_ATOMICS__SHIFT) & CNA_DATA_SIZE3_DATAOUT_ATOMICS__MASK;
+}
+
+#define REG_CNA_WEIGHT_SIZE0					0x00001030
+#define CNA_WEIGHT_SIZE0_WEIGHT_BYTES__MASK			0xffffffff
+#define CNA_WEIGHT_SIZE0_WEIGHT_BYTES__SHIFT			0
+static inline uint32_t CNA_WEIGHT_SIZE0_WEIGHT_BYTES(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE0_WEIGHT_BYTES__SHIFT) & CNA_WEIGHT_SIZE0_WEIGHT_BYTES__MASK;
+}
+
+#define REG_CNA_WEIGHT_SIZE1					0x00001034
+#define CNA_WEIGHT_SIZE1_RESERVED_0__MASK			0xfff80000
+#define CNA_WEIGHT_SIZE1_RESERVED_0__SHIFT			19
+static inline uint32_t CNA_WEIGHT_SIZE1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE1_RESERVED_0__SHIFT) & CNA_WEIGHT_SIZE1_RESERVED_0__MASK;
+}
+#define CNA_WEIGHT_SIZE1_WEIGHT_BYTES_PER_KERNEL__MASK		0x0007ffff
+#define CNA_WEIGHT_SIZE1_WEIGHT_BYTES_PER_KERNEL__SHIFT		0
+static inline uint32_t CNA_WEIGHT_SIZE1_WEIGHT_BYTES_PER_KERNEL(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE1_WEIGHT_BYTES_PER_KERNEL__SHIFT) & CNA_WEIGHT_SIZE1_WEIGHT_BYTES_PER_KERNEL__MASK;
+}
+
+#define REG_CNA_WEIGHT_SIZE2					0x00001038
+#define CNA_WEIGHT_SIZE2_RESERVED_0__MASK			0xe0000000
+#define CNA_WEIGHT_SIZE2_RESERVED_0__SHIFT			29
+static inline uint32_t CNA_WEIGHT_SIZE2_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_RESERVED_0__SHIFT) & CNA_WEIGHT_SIZE2_RESERVED_0__MASK;
+}
+#define CNA_WEIGHT_SIZE2_WEIGHT_WIDTH__MASK			0x1f000000
+#define CNA_WEIGHT_SIZE2_WEIGHT_WIDTH__SHIFT			24
+static inline uint32_t CNA_WEIGHT_SIZE2_WEIGHT_WIDTH(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_WEIGHT_WIDTH__SHIFT) & CNA_WEIGHT_SIZE2_WEIGHT_WIDTH__MASK;
+}
+#define CNA_WEIGHT_SIZE2_RESERVED_1__MASK			0x00e00000
+#define CNA_WEIGHT_SIZE2_RESERVED_1__SHIFT			21
+static inline uint32_t CNA_WEIGHT_SIZE2_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_RESERVED_1__SHIFT) & CNA_WEIGHT_SIZE2_RESERVED_1__MASK;
+}
+#define CNA_WEIGHT_SIZE2_WEIGHT_HEIGHT__MASK			0x001f0000
+#define CNA_WEIGHT_SIZE2_WEIGHT_HEIGHT__SHIFT			16
+static inline uint32_t CNA_WEIGHT_SIZE2_WEIGHT_HEIGHT(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_WEIGHT_HEIGHT__SHIFT) & CNA_WEIGHT_SIZE2_WEIGHT_HEIGHT__MASK;
+}
+#define CNA_WEIGHT_SIZE2_RESERVED_2__MASK			0x0000c000
+#define CNA_WEIGHT_SIZE2_RESERVED_2__SHIFT			14
+static inline uint32_t CNA_WEIGHT_SIZE2_RESERVED_2(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_RESERVED_2__SHIFT) & CNA_WEIGHT_SIZE2_RESERVED_2__MASK;
+}
+#define CNA_WEIGHT_SIZE2_WEIGHT_KERNELS__MASK			0x00003fff
+#define CNA_WEIGHT_SIZE2_WEIGHT_KERNELS__SHIFT			0
+static inline uint32_t CNA_WEIGHT_SIZE2_WEIGHT_KERNELS(uint32_t val)
+{
+	return ((val) << CNA_WEIGHT_SIZE2_WEIGHT_KERNELS__SHIFT) & CNA_WEIGHT_SIZE2_WEIGHT_KERNELS__MASK;
+}
+
+#define REG_CNA_CBUF_CON0					0x00001040
+#define CNA_CBUF_CON0_RESERVED_0__MASK				0xffffc000
+#define CNA_CBUF_CON0_RESERVED_0__SHIFT				14
+static inline uint32_t CNA_CBUF_CON0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_RESERVED_0__SHIFT) & CNA_CBUF_CON0_RESERVED_0__MASK;
+}
+#define CNA_CBUF_CON0_WEIGHT_REUSE__MASK			0x00002000
+#define CNA_CBUF_CON0_WEIGHT_REUSE__SHIFT			13
+static inline uint32_t CNA_CBUF_CON0_WEIGHT_REUSE(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_WEIGHT_REUSE__SHIFT) & CNA_CBUF_CON0_WEIGHT_REUSE__MASK;
+}
+#define CNA_CBUF_CON0_DATA_REUSE__MASK				0x00001000
+#define CNA_CBUF_CON0_DATA_REUSE__SHIFT				12
+static inline uint32_t CNA_CBUF_CON0_DATA_REUSE(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_DATA_REUSE__SHIFT) & CNA_CBUF_CON0_DATA_REUSE__MASK;
+}
+#define CNA_CBUF_CON0_RESERVED_1__MASK				0x00000800
+#define CNA_CBUF_CON0_RESERVED_1__SHIFT				11
+static inline uint32_t CNA_CBUF_CON0_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_RESERVED_1__SHIFT) & CNA_CBUF_CON0_RESERVED_1__MASK;
+}
+#define CNA_CBUF_CON0_FC_DATA_BANK__MASK			0x00000700
+#define CNA_CBUF_CON0_FC_DATA_BANK__SHIFT			8
+static inline uint32_t CNA_CBUF_CON0_FC_DATA_BANK(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_FC_DATA_BANK__SHIFT) & CNA_CBUF_CON0_FC_DATA_BANK__MASK;
+}
+#define CNA_CBUF_CON0_WEIGHT_BANK__MASK				0x000000f0
+#define CNA_CBUF_CON0_WEIGHT_BANK__SHIFT			4
+static inline uint32_t CNA_CBUF_CON0_WEIGHT_BANK(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_WEIGHT_BANK__SHIFT) & CNA_CBUF_CON0_WEIGHT_BANK__MASK;
+}
+#define CNA_CBUF_CON0_DATA_BANK__MASK				0x0000000f
+#define CNA_CBUF_CON0_DATA_BANK__SHIFT				0
+static inline uint32_t CNA_CBUF_CON0_DATA_BANK(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON0_DATA_BANK__SHIFT) & CNA_CBUF_CON0_DATA_BANK__MASK;
+}
+
+#define REG_CNA_CBUF_CON1					0x00001044
+#define CNA_CBUF_CON1_RESERVED_0__MASK				0xffffc000
+#define CNA_CBUF_CON1_RESERVED_0__SHIFT				14
+static inline uint32_t CNA_CBUF_CON1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON1_RESERVED_0__SHIFT) & CNA_CBUF_CON1_RESERVED_0__MASK;
+}
+#define CNA_CBUF_CON1_DATA_ENTRIES__MASK			0x00003fff
+#define CNA_CBUF_CON1_DATA_ENTRIES__SHIFT			0
+static inline uint32_t CNA_CBUF_CON1_DATA_ENTRIES(uint32_t val)
+{
+	return ((val) << CNA_CBUF_CON1_DATA_ENTRIES__SHIFT) & CNA_CBUF_CON1_DATA_ENTRIES__MASK;
+}
+
+#define REG_CNA_CVT_CON0					0x0000104c
+#define CNA_CVT_CON0_RESERVED_0__MASK				0xf0000000
+#define CNA_CVT_CON0_RESERVED_0__SHIFT				28
+static inline uint32_t CNA_CVT_CON0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_RESERVED_0__SHIFT) & CNA_CVT_CON0_RESERVED_0__MASK;
+}
+#define CNA_CVT_CON0_CVT_TRUNCATE_3__MASK			0x0fc00000
+#define CNA_CVT_CON0_CVT_TRUNCATE_3__SHIFT			22
+static inline uint32_t CNA_CVT_CON0_CVT_TRUNCATE_3(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_TRUNCATE_3__SHIFT) & CNA_CVT_CON0_CVT_TRUNCATE_3__MASK;
+}
+#define CNA_CVT_CON0_CVT_TRUNCATE_2__MASK			0x003f0000
+#define CNA_CVT_CON0_CVT_TRUNCATE_2__SHIFT			16
+static inline uint32_t CNA_CVT_CON0_CVT_TRUNCATE_2(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_TRUNCATE_2__SHIFT) & CNA_CVT_CON0_CVT_TRUNCATE_2__MASK;
+}
+#define CNA_CVT_CON0_CVT_TRUNCATE_1__MASK			0x0000fc00
+#define CNA_CVT_CON0_CVT_TRUNCATE_1__SHIFT			10
+static inline uint32_t CNA_CVT_CON0_CVT_TRUNCATE_1(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_TRUNCATE_1__SHIFT) & CNA_CVT_CON0_CVT_TRUNCATE_1__MASK;
+}
+#define CNA_CVT_CON0_CVT_TRUNCATE_0__MASK			0x000003f0
+#define CNA_CVT_CON0_CVT_TRUNCATE_0__SHIFT			4
+static inline uint32_t CNA_CVT_CON0_CVT_TRUNCATE_0(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_TRUNCATE_0__SHIFT) & CNA_CVT_CON0_CVT_TRUNCATE_0__MASK;
+}
+#define CNA_CVT_CON0_DATA_SIGN__MASK				0x00000008
+#define CNA_CVT_CON0_DATA_SIGN__SHIFT				3
+static inline uint32_t CNA_CVT_CON0_DATA_SIGN(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_DATA_SIGN__SHIFT) & CNA_CVT_CON0_DATA_SIGN__MASK;
+}
+#define CNA_CVT_CON0_ROUND_TYPE__MASK				0x00000004
+#define CNA_CVT_CON0_ROUND_TYPE__SHIFT				2
+static inline uint32_t CNA_CVT_CON0_ROUND_TYPE(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_ROUND_TYPE__SHIFT) & CNA_CVT_CON0_ROUND_TYPE__MASK;
+}
+#define CNA_CVT_CON0_CVT_TYPE__MASK				0x00000002
+#define CNA_CVT_CON0_CVT_TYPE__SHIFT				1
+static inline uint32_t CNA_CVT_CON0_CVT_TYPE(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_TYPE__SHIFT) & CNA_CVT_CON0_CVT_TYPE__MASK;
+}
+#define CNA_CVT_CON0_CVT_BYPASS__MASK				0x00000001
+#define CNA_CVT_CON0_CVT_BYPASS__SHIFT				0
+static inline uint32_t CNA_CVT_CON0_CVT_BYPASS(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON0_CVT_BYPASS__SHIFT) & CNA_CVT_CON0_CVT_BYPASS__MASK;
+}
+
+#define REG_CNA_CVT_CON1					0x00001050
+#define CNA_CVT_CON1_CVT_SCALE0__MASK				0xffff0000
+#define CNA_CVT_CON1_CVT_SCALE0__SHIFT				16
+static inline uint32_t CNA_CVT_CON1_CVT_SCALE0(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON1_CVT_SCALE0__SHIFT) & CNA_CVT_CON1_CVT_SCALE0__MASK;
+}
+#define CNA_CVT_CON1_CVT_OFFSET0__MASK				0x0000ffff
+#define CNA_CVT_CON1_CVT_OFFSET0__SHIFT				0
+static inline uint32_t CNA_CVT_CON1_CVT_OFFSET0(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON1_CVT_OFFSET0__SHIFT) & CNA_CVT_CON1_CVT_OFFSET0__MASK;
+}
+
+#define REG_CNA_CVT_CON2					0x00001054
+#define CNA_CVT_CON2_CVT_SCALE1__MASK				0xffff0000
+#define CNA_CVT_CON2_CVT_SCALE1__SHIFT				16
+static inline uint32_t CNA_CVT_CON2_CVT_SCALE1(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON2_CVT_SCALE1__SHIFT) & CNA_CVT_CON2_CVT_SCALE1__MASK;
+}
+#define CNA_CVT_CON2_CVT_OFFSET1__MASK				0x0000ffff
+#define CNA_CVT_CON2_CVT_OFFSET1__SHIFT				0
+static inline uint32_t CNA_CVT_CON2_CVT_OFFSET1(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON2_CVT_OFFSET1__SHIFT) & CNA_CVT_CON2_CVT_OFFSET1__MASK;
+}
+
+#define REG_CNA_CVT_CON3					0x00001058
+#define CNA_CVT_CON3_CVT_SCALE2__MASK				0xffff0000
+#define CNA_CVT_CON3_CVT_SCALE2__SHIFT				16
+static inline uint32_t CNA_CVT_CON3_CVT_SCALE2(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON3_CVT_SCALE2__SHIFT) & CNA_CVT_CON3_CVT_SCALE2__MASK;
+}
+#define CNA_CVT_CON3_CVT_OFFSET2__MASK				0x0000ffff
+#define CNA_CVT_CON3_CVT_OFFSET2__SHIFT				0
+static inline uint32_t CNA_CVT_CON3_CVT_OFFSET2(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON3_CVT_OFFSET2__SHIFT) & CNA_CVT_CON3_CVT_OFFSET2__MASK;
+}
+
+#define REG_CNA_CVT_CON4					0x0000105c
+#define CNA_CVT_CON4_CVT_SCALE3__MASK				0xffff0000
+#define CNA_CVT_CON4_CVT_SCALE3__SHIFT				16
+static inline uint32_t CNA_CVT_CON4_CVT_SCALE3(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON4_CVT_SCALE3__SHIFT) & CNA_CVT_CON4_CVT_SCALE3__MASK;
+}
+#define CNA_CVT_CON4_CVT_OFFSET3__MASK				0x0000ffff
+#define CNA_CVT_CON4_CVT_OFFSET3__SHIFT				0
+static inline uint32_t CNA_CVT_CON4_CVT_OFFSET3(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON4_CVT_OFFSET3__SHIFT) & CNA_CVT_CON4_CVT_OFFSET3__MASK;
+}
+
+#define REG_CNA_FC_CON0						0x00001060
+#define CNA_FC_CON0_FC_SKIP_DATA__MASK				0xffff0000
+#define CNA_FC_CON0_FC_SKIP_DATA__SHIFT				16
+static inline uint32_t CNA_FC_CON0_FC_SKIP_DATA(uint32_t val)
+{
+	return ((val) << CNA_FC_CON0_FC_SKIP_DATA__SHIFT) & CNA_FC_CON0_FC_SKIP_DATA__MASK;
+}
+#define CNA_FC_CON0_RESERVED_0__MASK				0x0000fffe
+#define CNA_FC_CON0_RESERVED_0__SHIFT				1
+static inline uint32_t CNA_FC_CON0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_FC_CON0_RESERVED_0__SHIFT) & CNA_FC_CON0_RESERVED_0__MASK;
+}
+#define CNA_FC_CON0_FC_SKIP_EN__MASK				0x00000001
+#define CNA_FC_CON0_FC_SKIP_EN__SHIFT				0
+static inline uint32_t CNA_FC_CON0_FC_SKIP_EN(uint32_t val)
+{
+	return ((val) << CNA_FC_CON0_FC_SKIP_EN__SHIFT) & CNA_FC_CON0_FC_SKIP_EN__MASK;
+}
+
+#define REG_CNA_FC_CON1						0x00001064
+#define CNA_FC_CON1_RESERVED_0__MASK				0xfffe0000
+#define CNA_FC_CON1_RESERVED_0__SHIFT				17
+static inline uint32_t CNA_FC_CON1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_FC_CON1_RESERVED_0__SHIFT) & CNA_FC_CON1_RESERVED_0__MASK;
+}
+#define CNA_FC_CON1_DATA_OFFSET__MASK				0x0001ffff
+#define CNA_FC_CON1_DATA_OFFSET__SHIFT				0
+static inline uint32_t CNA_FC_CON1_DATA_OFFSET(uint32_t val)
+{
+	return ((val) << CNA_FC_CON1_DATA_OFFSET__SHIFT) & CNA_FC_CON1_DATA_OFFSET__MASK;
+}
+
+#define REG_CNA_PAD_CON0					0x00001068
+#define CNA_PAD_CON0_RESERVED_0__MASK				0xffffff00
+#define CNA_PAD_CON0_RESERVED_0__SHIFT				8
+static inline uint32_t CNA_PAD_CON0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_PAD_CON0_RESERVED_0__SHIFT) & CNA_PAD_CON0_RESERVED_0__MASK;
+}
+#define CNA_PAD_CON0_PAD_LEFT__MASK				0x000000f0
+#define CNA_PAD_CON0_PAD_LEFT__SHIFT				4
+static inline uint32_t CNA_PAD_CON0_PAD_LEFT(uint32_t val)
+{
+	return ((val) << CNA_PAD_CON0_PAD_LEFT__SHIFT) & CNA_PAD_CON0_PAD_LEFT__MASK;
+}
+#define CNA_PAD_CON0_PAD_TOP__MASK				0x0000000f
+#define CNA_PAD_CON0_PAD_TOP__SHIFT				0
+static inline uint32_t CNA_PAD_CON0_PAD_TOP(uint32_t val)
+{
+	return ((val) << CNA_PAD_CON0_PAD_TOP__SHIFT) & CNA_PAD_CON0_PAD_TOP__MASK;
+}
+
+#define REG_CNA_FEATURE_DATA_ADDR				0x00001070
+#define CNA_FEATURE_DATA_ADDR_FEATURE_BASE_ADDR__MASK		0xffffffff
+#define CNA_FEATURE_DATA_ADDR_FEATURE_BASE_ADDR__SHIFT		0
+static inline uint32_t CNA_FEATURE_DATA_ADDR_FEATURE_BASE_ADDR(uint32_t val)
+{
+	return ((val) << CNA_FEATURE_DATA_ADDR_FEATURE_BASE_ADDR__SHIFT) & CNA_FEATURE_DATA_ADDR_FEATURE_BASE_ADDR__MASK;
+}
+
+#define REG_CNA_FC_CON2						0x00001074
+#define CNA_FC_CON2_RESERVED_0__MASK				0xfffe0000
+#define CNA_FC_CON2_RESERVED_0__SHIFT				17
+static inline uint32_t CNA_FC_CON2_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_FC_CON2_RESERVED_0__SHIFT) & CNA_FC_CON2_RESERVED_0__MASK;
+}
+#define CNA_FC_CON2_WEIGHT_OFFSET__MASK				0x0001ffff
+#define CNA_FC_CON2_WEIGHT_OFFSET__SHIFT			0
+static inline uint32_t CNA_FC_CON2_WEIGHT_OFFSET(uint32_t val)
+{
+	return ((val) << CNA_FC_CON2_WEIGHT_OFFSET__SHIFT) & CNA_FC_CON2_WEIGHT_OFFSET__MASK;
+}
+
+#define REG_CNA_DMA_CON0					0x00001078
+#define CNA_DMA_CON0_OV4K_BYPASS__MASK				0x80000000
+#define CNA_DMA_CON0_OV4K_BYPASS__SHIFT				31
+static inline uint32_t CNA_DMA_CON0_OV4K_BYPASS(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON0_OV4K_BYPASS__SHIFT) & CNA_DMA_CON0_OV4K_BYPASS__MASK;
+}
+#define CNA_DMA_CON0_RESERVED_0__MASK				0x7ff00000
+#define CNA_DMA_CON0_RESERVED_0__SHIFT				20
+static inline uint32_t CNA_DMA_CON0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON0_RESERVED_0__SHIFT) & CNA_DMA_CON0_RESERVED_0__MASK;
+}
+#define CNA_DMA_CON0_WEIGHT_BURST_LEN__MASK			0x000f0000
+#define CNA_DMA_CON0_WEIGHT_BURST_LEN__SHIFT			16
+static inline uint32_t CNA_DMA_CON0_WEIGHT_BURST_LEN(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON0_WEIGHT_BURST_LEN__SHIFT) & CNA_DMA_CON0_WEIGHT_BURST_LEN__MASK;
+}
+#define CNA_DMA_CON0_RESERVED_1__MASK				0x0000fff0
+#define CNA_DMA_CON0_RESERVED_1__SHIFT				4
+static inline uint32_t CNA_DMA_CON0_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON0_RESERVED_1__SHIFT) & CNA_DMA_CON0_RESERVED_1__MASK;
+}
+#define CNA_DMA_CON0_DATA_BURST_LEN__MASK			0x0000000f
+#define CNA_DMA_CON0_DATA_BURST_LEN__SHIFT			0
+static inline uint32_t CNA_DMA_CON0_DATA_BURST_LEN(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON0_DATA_BURST_LEN__SHIFT) & CNA_DMA_CON0_DATA_BURST_LEN__MASK;
+}
+
+#define REG_CNA_DMA_CON1					0x0000107c
+#define CNA_DMA_CON1_RESERVED_0__MASK				0xf0000000
+#define CNA_DMA_CON1_RESERVED_0__SHIFT				28
+static inline uint32_t CNA_DMA_CON1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON1_RESERVED_0__SHIFT) & CNA_DMA_CON1_RESERVED_0__MASK;
+}
+#define CNA_DMA_CON1_LINE_STRIDE__MASK				0x0fffffff
+#define CNA_DMA_CON1_LINE_STRIDE__SHIFT				0
+static inline uint32_t CNA_DMA_CON1_LINE_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON1_LINE_STRIDE__SHIFT) & CNA_DMA_CON1_LINE_STRIDE__MASK;
+}
+
+#define REG_CNA_DMA_CON2					0x00001080
+#define CNA_DMA_CON2_RESERVED_0__MASK				0xf0000000
+#define CNA_DMA_CON2_RESERVED_0__SHIFT				28
+static inline uint32_t CNA_DMA_CON2_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON2_RESERVED_0__SHIFT) & CNA_DMA_CON2_RESERVED_0__MASK;
+}
+#define CNA_DMA_CON2_SURF_STRIDE__MASK				0x0fffffff
+#define CNA_DMA_CON2_SURF_STRIDE__SHIFT				0
+static inline uint32_t CNA_DMA_CON2_SURF_STRIDE(uint32_t val)
+{
+	return ((val) << CNA_DMA_CON2_SURF_STRIDE__SHIFT) & CNA_DMA_CON2_SURF_STRIDE__MASK;
+}
+
+#define REG_CNA_FC_DATA_SIZE0					0x00001084
+#define CNA_FC_DATA_SIZE0_RESERVED_0__MASK			0xc0000000
+#define CNA_FC_DATA_SIZE0_RESERVED_0__SHIFT			30
+static inline uint32_t CNA_FC_DATA_SIZE0_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE0_RESERVED_0__SHIFT) & CNA_FC_DATA_SIZE0_RESERVED_0__MASK;
+}
+#define CNA_FC_DATA_SIZE0_DMA_WIDTH__MASK			0x3fff0000
+#define CNA_FC_DATA_SIZE0_DMA_WIDTH__SHIFT			16
+static inline uint32_t CNA_FC_DATA_SIZE0_DMA_WIDTH(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE0_DMA_WIDTH__SHIFT) & CNA_FC_DATA_SIZE0_DMA_WIDTH__MASK;
+}
+#define CNA_FC_DATA_SIZE0_RESERVED_1__MASK			0x0000f800
+#define CNA_FC_DATA_SIZE0_RESERVED_1__SHIFT			11
+static inline uint32_t CNA_FC_DATA_SIZE0_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE0_RESERVED_1__SHIFT) & CNA_FC_DATA_SIZE0_RESERVED_1__MASK;
+}
+#define CNA_FC_DATA_SIZE0_DMA_HEIGHT__MASK			0x000007ff
+#define CNA_FC_DATA_SIZE0_DMA_HEIGHT__SHIFT			0
+static inline uint32_t CNA_FC_DATA_SIZE0_DMA_HEIGHT(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE0_DMA_HEIGHT__SHIFT) & CNA_FC_DATA_SIZE0_DMA_HEIGHT__MASK;
+}
+
+#define REG_CNA_FC_DATA_SIZE1					0x00001088
+#define CNA_FC_DATA_SIZE1_RESERVED_0__MASK			0xffff0000
+#define CNA_FC_DATA_SIZE1_RESERVED_0__SHIFT			16
+static inline uint32_t CNA_FC_DATA_SIZE1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE1_RESERVED_0__SHIFT) & CNA_FC_DATA_SIZE1_RESERVED_0__MASK;
+}
+#define CNA_FC_DATA_SIZE1_DMA_CHANNEL__MASK			0x0000ffff
+#define CNA_FC_DATA_SIZE1_DMA_CHANNEL__SHIFT			0
+static inline uint32_t CNA_FC_DATA_SIZE1_DMA_CHANNEL(uint32_t val)
+{
+	return ((val) << CNA_FC_DATA_SIZE1_DMA_CHANNEL__SHIFT) & CNA_FC_DATA_SIZE1_DMA_CHANNEL__MASK;
+}
+
+#define REG_CNA_CLK_GATE					0x00001090
+#define CNA_CLK_GATE_RESERVED_0__MASK				0xffffffe0
+#define CNA_CLK_GATE_RESERVED_0__SHIFT				5
+static inline uint32_t CNA_CLK_GATE_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_RESERVED_0__SHIFT) & CNA_CLK_GATE_RESERVED_0__MASK;
+}
+#define CNA_CLK_GATE_CBUF_CS_DISABLE_CLKGATE__MASK		0x00000010
+#define CNA_CLK_GATE_CBUF_CS_DISABLE_CLKGATE__SHIFT		4
+static inline uint32_t CNA_CLK_GATE_CBUF_CS_DISABLE_CLKGATE(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_CBUF_CS_DISABLE_CLKGATE__SHIFT) & CNA_CLK_GATE_CBUF_CS_DISABLE_CLKGATE__MASK;
+}
+#define CNA_CLK_GATE_RESERVED_1__MASK				0x00000008
+#define CNA_CLK_GATE_RESERVED_1__SHIFT				3
+static inline uint32_t CNA_CLK_GATE_RESERVED_1(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_RESERVED_1__SHIFT) & CNA_CLK_GATE_RESERVED_1__MASK;
+}
+#define CNA_CLK_GATE_CSC_DISABLE_CLKGATE__MASK			0x00000004
+#define CNA_CLK_GATE_CSC_DISABLE_CLKGATE__SHIFT			2
+static inline uint32_t CNA_CLK_GATE_CSC_DISABLE_CLKGATE(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_CSC_DISABLE_CLKGATE__SHIFT) & CNA_CLK_GATE_CSC_DISABLE_CLKGATE__MASK;
+}
+#define CNA_CLK_GATE_CNA_WEIGHT_DISABLE_CLKGATE__MASK		0x00000002
+#define CNA_CLK_GATE_CNA_WEIGHT_DISABLE_CLKGATE__SHIFT		1
+static inline uint32_t CNA_CLK_GATE_CNA_WEIGHT_DISABLE_CLKGATE(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_CNA_WEIGHT_DISABLE_CLKGATE__SHIFT) & CNA_CLK_GATE_CNA_WEIGHT_DISABLE_CLKGATE__MASK;
+}
+#define CNA_CLK_GATE_CNA_FEATURE_DISABLE_CLKGATE__MASK		0x00000001
+#define CNA_CLK_GATE_CNA_FEATURE_DISABLE_CLKGATE__SHIFT		0
+static inline uint32_t CNA_CLK_GATE_CNA_FEATURE_DISABLE_CLKGATE(uint32_t val)
+{
+	return ((val) << CNA_CLK_GATE_CNA_FEATURE_DISABLE_CLKGATE__SHIFT) & CNA_CLK_GATE_CNA_FEATURE_DISABLE_CLKGATE__MASK;
+}
+
+#define REG_CNA_DCOMP_CTRL					0x00001100
+#define CNA_DCOMP_CTRL_RESERVED_0__MASK				0xfffffff0
+#define CNA_DCOMP_CTRL_RESERVED_0__SHIFT			4
+static inline uint32_t CNA_DCOMP_CTRL_RESERVED_0(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_CTRL_RESERVED_0__SHIFT) & CNA_DCOMP_CTRL_RESERVED_0__MASK;
+}
+#define CNA_DCOMP_CTRL_WT_DEC_BYPASS__MASK			0x00000008
+#define CNA_DCOMP_CTRL_WT_DEC_BYPASS__SHIFT			3
+static inline uint32_t CNA_DCOMP_CTRL_WT_DEC_BYPASS(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_CTRL_WT_DEC_BYPASS__SHIFT) & CNA_DCOMP_CTRL_WT_DEC_BYPASS__MASK;
+}
+#define CNA_DCOMP_CTRL_DECOMP_CONTROL__MASK			0x00000007
+#define CNA_DCOMP_CTRL_DECOMP_CONTROL__SHIFT			0
+static inline uint32_t CNA_DCOMP_CTRL_DECOMP_CONTROL(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_CTRL_DECOMP_CONTROL__SHIFT) & CNA_DCOMP_CTRL_DECOMP_CONTROL__MASK;
+}
+
+#define REG_CNA_DCOMP_REGNUM					0x00001104
+#define CNA_DCOMP_REGNUM_DCOMP_REGNUM__MASK			0xffffffff
+#define CNA_DCOMP_REGNUM_DCOMP_REGNUM__SHIFT			0
+static inline uint32_t CNA_DCOMP_REGNUM_DCOMP_REGNUM(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_REGNUM_DCOMP_REGNUM__SHIFT) & CNA_DCOMP_REGNUM_DCOMP_REGNUM__MASK;
+}
+
+#define REG_CNA_DCOMP_ADDR0					0x00001110
+#define CNA_DCOMP_ADDR0_DECOMPRESS_ADDR0__MASK			0xffffffff
+#define CNA_DCOMP_ADDR0_DECOMPRESS_ADDR0__SHIFT			0
+static inline uint32_t CNA_DCOMP_ADDR0_DECOMPRESS_ADDR0(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_ADDR0_DECOMPRESS_ADDR0__SHIFT) & CNA_DCOMP_ADDR0_DECOMPRESS_ADDR0__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT0					0x00001140
+#define CNA_DCOMP_AMOUNT0_DCOMP_AMOUNT0__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT0_DCOMP_AMOUNT0__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT0_DCOMP_AMOUNT0(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT0_DCOMP_AMOUNT0__SHIFT) & CNA_DCOMP_AMOUNT0_DCOMP_AMOUNT0__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT1					0x00001144
+#define CNA_DCOMP_AMOUNT1_DCOMP_AMOUNT1__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT1_DCOMP_AMOUNT1__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT1_DCOMP_AMOUNT1(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT1_DCOMP_AMOUNT1__SHIFT) & CNA_DCOMP_AMOUNT1_DCOMP_AMOUNT1__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT2					0x00001148
+#define CNA_DCOMP_AMOUNT2_DCOMP_AMOUNT2__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT2_DCOMP_AMOUNT2__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT2_DCOMP_AMOUNT2(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT2_DCOMP_AMOUNT2__SHIFT) & CNA_DCOMP_AMOUNT2_DCOMP_AMOUNT2__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT3					0x0000114c
+#define CNA_DCOMP_AMOUNT3_DCOMP_AMOUNT3__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT3_DCOMP_AMOUNT3__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT3_DCOMP_AMOUNT3(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT3_DCOMP_AMOUNT3__SHIFT) & CNA_DCOMP_AMOUNT3_DCOMP_AMOUNT3__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT4					0x00001150
+#define CNA_DCOMP_AMOUNT4_DCOMP_AMOUNT4__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT4_DCOMP_AMOUNT4__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT4_DCOMP_AMOUNT4(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT4_DCOMP_AMOUNT4__SHIFT) & CNA_DCOMP_AMOUNT4_DCOMP_AMOUNT4__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT5					0x00001154
+#define CNA_DCOMP_AMOUNT5_DCOMP_AMOUNT5__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT5_DCOMP_AMOUNT5__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT5_DCOMP_AMOUNT5(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT5_DCOMP_AMOUNT5__SHIFT) & CNA_DCOMP_AMOUNT5_DCOMP_AMOUNT5__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT6					0x00001158
+#define CNA_DCOMP_AMOUNT6_DCOMP_AMOUNT6__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT6_DCOMP_AMOUNT6__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT6_DCOMP_AMOUNT6(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT6_DCOMP_AMOUNT6__SHIFT) & CNA_DCOMP_AMOUNT6_DCOMP_AMOUNT6__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT7					0x0000115c
+#define CNA_DCOMP_AMOUNT7_DCOMP_AMOUNT7__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT7_DCOMP_AMOUNT7__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT7_DCOMP_AMOUNT7(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT7_DCOMP_AMOUNT7__SHIFT) & CNA_DCOMP_AMOUNT7_DCOMP_AMOUNT7__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT8					0x00001160
+#define CNA_DCOMP_AMOUNT8_DCOMP_AMOUNT8__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT8_DCOMP_AMOUNT8__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT8_DCOMP_AMOUNT8(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT8_DCOMP_AMOUNT8__SHIFT) & CNA_DCOMP_AMOUNT8_DCOMP_AMOUNT8__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT9					0x00001164
+#define CNA_DCOMP_AMOUNT9_DCOMP_AMOUNT9__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT9_DCOMP_AMOUNT9__SHIFT			0
+static inline uint32_t CNA_DCOMP_AMOUNT9_DCOMP_AMOUNT9(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT9_DCOMP_AMOUNT9__SHIFT) & CNA_DCOMP_AMOUNT9_DCOMP_AMOUNT9__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT10					0x00001168
+#define CNA_DCOMP_AMOUNT10_DCOMP_AMOUNT10__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT10_DCOMP_AMOUNT10__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT10_DCOMP_AMOUNT10(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT10_DCOMP_AMOUNT10__SHIFT) & CNA_DCOMP_AMOUNT10_DCOMP_AMOUNT10__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT11					0x0000116c
+#define CNA_DCOMP_AMOUNT11_DCOMP_AMOUNT11__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT11_DCOMP_AMOUNT11__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT11_DCOMP_AMOUNT11(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT11_DCOMP_AMOUNT11__SHIFT) & CNA_DCOMP_AMOUNT11_DCOMP_AMOUNT11__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT12					0x00001170
+#define CNA_DCOMP_AMOUNT12_DCOMP_AMOUNT12__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT12_DCOMP_AMOUNT12__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT12_DCOMP_AMOUNT12(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT12_DCOMP_AMOUNT12__SHIFT) & CNA_DCOMP_AMOUNT12_DCOMP_AMOUNT12__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT13					0x00001174
+#define CNA_DCOMP_AMOUNT13_DCOMP_AMOUNT13__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT13_DCOMP_AMOUNT13__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT13_DCOMP_AMOUNT13(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT13_DCOMP_AMOUNT13__SHIFT) & CNA_DCOMP_AMOUNT13_DCOMP_AMOUNT13__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT14					0x00001178
+#define CNA_DCOMP_AMOUNT14_DCOMP_AMOUNT14__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT14_DCOMP_AMOUNT14__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT14_DCOMP_AMOUNT14(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT14_DCOMP_AMOUNT14__SHIFT) & CNA_DCOMP_AMOUNT14_DCOMP_AMOUNT14__MASK;
+}
+
+#define REG_CNA_DCOMP_AMOUNT15					0x0000117c
+#define CNA_DCOMP_AMOUNT15_DCOMP_AMOUNT15__MASK			0xffffffff
+#define CNA_DCOMP_AMOUNT15_DCOMP_AMOUNT15__SHIFT		0
+static inline uint32_t CNA_DCOMP_AMOUNT15_DCOMP_AMOUNT15(uint32_t val)
+{
+	return ((val) << CNA_DCOMP_AMOUNT15_DCOMP_AMOUNT15__SHIFT) & CNA_DCOMP_AMOUNT15_DCOMP_AMOUNT15__MASK;
+}
+
+#define REG_CNA_CVT_CON5					0x00001180
+#define CNA_CVT_CON5_PER_CHANNEL_CVT_EN__MASK			0xffffffff
+#define CNA_CVT_CON5_PER_CHANNEL_CVT_EN__SHIFT			0
+static inline uint32_t CNA_CVT_CON5_PER_CHANNEL_CVT_EN(uint32_t val)
+{
+	return ((val) << CNA_CVT_CON5_PER_CHANNEL_CVT_EN__SHIFT) & CNA_CVT_CON5_PER_CHANNEL_CVT_EN__MASK;
+}
+
+#define REG_CNA_PAD_CON1					0x00001184
+#define CNA_PAD_CON1_PAD_VALUE__MASK				0xffffffff
+#define CNA_PAD_CON1_PAD_VALUE__SHIFT				0
+static inline uint32_t CNA_PAD_CON1_PAD_VALUE(uint32_t val)
+{
+	return ((val) << CNA_PAD_CON1_PAD_VALUE__SHIFT) & CNA_PAD_CON1_PAD_VALUE__MASK;
+}
+
+#define REG_CORE_S_STATUS					0x00003000
+#define CORE_S_STATUS_RESERVED_0__MASK				0xfffc0000
+#define CORE_S_STATUS_RESERVED_0__SHIFT				18
+static inline uint32_t CORE_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_S_STATUS_RESERVED_0__SHIFT) & CORE_S_STATUS_RESERVED_0__MASK;
+}
+#define CORE_S_STATUS_STATUS_1__MASK				0x00030000
+#define CORE_S_STATUS_STATUS_1__SHIFT				16
+static inline uint32_t CORE_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << CORE_S_STATUS_STATUS_1__SHIFT) & CORE_S_STATUS_STATUS_1__MASK;
+}
+#define CORE_S_STATUS_RESERVED_1__MASK				0x0000fffc
+#define CORE_S_STATUS_RESERVED_1__SHIFT				2
+static inline uint32_t CORE_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << CORE_S_STATUS_RESERVED_1__SHIFT) & CORE_S_STATUS_RESERVED_1__MASK;
+}
+#define CORE_S_STATUS_STATUS_0__MASK				0x00000003
+#define CORE_S_STATUS_STATUS_0__SHIFT				0
+static inline uint32_t CORE_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << CORE_S_STATUS_STATUS_0__SHIFT) & CORE_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_CORE_S_POINTER					0x00003004
+#define CORE_S_POINTER_RESERVED_0__MASK				0xfffe0000
+#define CORE_S_POINTER_RESERVED_0__SHIFT			17
+static inline uint32_t CORE_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_RESERVED_0__SHIFT) & CORE_S_POINTER_RESERVED_0__MASK;
+}
+#define CORE_S_POINTER_EXECUTER__MASK				0x00010000
+#define CORE_S_POINTER_EXECUTER__SHIFT				16
+static inline uint32_t CORE_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_EXECUTER__SHIFT) & CORE_S_POINTER_EXECUTER__MASK;
+}
+#define CORE_S_POINTER_RESERVED_1__MASK				0x0000ffc0
+#define CORE_S_POINTER_RESERVED_1__SHIFT			6
+static inline uint32_t CORE_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_RESERVED_1__SHIFT) & CORE_S_POINTER_RESERVED_1__MASK;
+}
+#define CORE_S_POINTER_EXECUTER_PP_CLEAR__MASK			0x00000020
+#define CORE_S_POINTER_EXECUTER_PP_CLEAR__SHIFT			5
+static inline uint32_t CORE_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & CORE_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define CORE_S_POINTER_POINTER_PP_CLEAR__MASK			0x00000010
+#define CORE_S_POINTER_POINTER_PP_CLEAR__SHIFT			4
+static inline uint32_t CORE_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_POINTER_PP_CLEAR__SHIFT) & CORE_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define CORE_S_POINTER_POINTER_PP_MODE__MASK			0x00000008
+#define CORE_S_POINTER_POINTER_PP_MODE__SHIFT			3
+static inline uint32_t CORE_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_POINTER_PP_MODE__SHIFT) & CORE_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define CORE_S_POINTER_EXECUTER_PP_EN__MASK			0x00000004
+#define CORE_S_POINTER_EXECUTER_PP_EN__SHIFT			2
+static inline uint32_t CORE_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_EXECUTER_PP_EN__SHIFT) & CORE_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define CORE_S_POINTER_POINTER_PP_EN__MASK			0x00000002
+#define CORE_S_POINTER_POINTER_PP_EN__SHIFT			1
+static inline uint32_t CORE_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_POINTER_PP_EN__SHIFT) & CORE_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define CORE_S_POINTER_POINTER__MASK				0x00000001
+#define CORE_S_POINTER_POINTER__SHIFT				0
+static inline uint32_t CORE_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << CORE_S_POINTER_POINTER__SHIFT) & CORE_S_POINTER_POINTER__MASK;
+}
+
+#define REG_CORE_OPERATION_ENABLE				0x00003008
+#define CORE_OPERATION_ENABLE_RESERVED_0__MASK			0xfffffffe
+#define CORE_OPERATION_ENABLE_RESERVED_0__SHIFT			1
+static inline uint32_t CORE_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_OPERATION_ENABLE_RESERVED_0__SHIFT) & CORE_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define CORE_OPERATION_ENABLE_OP_EN__MASK			0x00000001
+#define CORE_OPERATION_ENABLE_OP_EN__SHIFT			0
+static inline uint32_t CORE_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << CORE_OPERATION_ENABLE_OP_EN__SHIFT) & CORE_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_CORE_MAC_GATING					0x0000300c
+#define CORE_MAC_GATING_RESERVED_0__MASK			0xf8000000
+#define CORE_MAC_GATING_RESERVED_0__SHIFT			27
+static inline uint32_t CORE_MAC_GATING_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_MAC_GATING_RESERVED_0__SHIFT) & CORE_MAC_GATING_RESERVED_0__MASK;
+}
+#define CORE_MAC_GATING_SLCG_OP_EN__MASK			0x07ffffff
+#define CORE_MAC_GATING_SLCG_OP_EN__SHIFT			0
+static inline uint32_t CORE_MAC_GATING_SLCG_OP_EN(uint32_t val)
+{
+	return ((val) << CORE_MAC_GATING_SLCG_OP_EN__SHIFT) & CORE_MAC_GATING_SLCG_OP_EN__MASK;
+}
+
+#define REG_CORE_MISC_CFG					0x00003010
+#define CORE_MISC_CFG_RESERVED_0__MASK				0xfff00000
+#define CORE_MISC_CFG_RESERVED_0__SHIFT				20
+static inline uint32_t CORE_MISC_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_RESERVED_0__SHIFT) & CORE_MISC_CFG_RESERVED_0__MASK;
+}
+#define CORE_MISC_CFG_SOFT_GATING__MASK				0x000fc000
+#define CORE_MISC_CFG_SOFT_GATING__SHIFT			14
+static inline uint32_t CORE_MISC_CFG_SOFT_GATING(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_SOFT_GATING__SHIFT) & CORE_MISC_CFG_SOFT_GATING__MASK;
+}
+#define CORE_MISC_CFG_RESERVED_1__MASK				0x00003800
+#define CORE_MISC_CFG_RESERVED_1__SHIFT				11
+static inline uint32_t CORE_MISC_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_RESERVED_1__SHIFT) & CORE_MISC_CFG_RESERVED_1__MASK;
+}
+#define CORE_MISC_CFG_PROC_PRECISION__MASK			0x00000700
+#define CORE_MISC_CFG_PROC_PRECISION__SHIFT			8
+static inline uint32_t CORE_MISC_CFG_PROC_PRECISION(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_PROC_PRECISION__SHIFT) & CORE_MISC_CFG_PROC_PRECISION__MASK;
+}
+#define CORE_MISC_CFG_RESERVED_2__MASK				0x000000fc
+#define CORE_MISC_CFG_RESERVED_2__SHIFT				2
+static inline uint32_t CORE_MISC_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_RESERVED_2__SHIFT) & CORE_MISC_CFG_RESERVED_2__MASK;
+}
+#define CORE_MISC_CFG_DW_EN__MASK				0x00000002
+#define CORE_MISC_CFG_DW_EN__SHIFT				1
+static inline uint32_t CORE_MISC_CFG_DW_EN(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_DW_EN__SHIFT) & CORE_MISC_CFG_DW_EN__MASK;
+}
+#define CORE_MISC_CFG_QD_EN__MASK				0x00000001
+#define CORE_MISC_CFG_QD_EN__SHIFT				0
+static inline uint32_t CORE_MISC_CFG_QD_EN(uint32_t val)
+{
+	return ((val) << CORE_MISC_CFG_QD_EN__SHIFT) & CORE_MISC_CFG_QD_EN__MASK;
+}
+
+#define REG_CORE_DATAOUT_SIZE_0					0x00003014
+#define CORE_DATAOUT_SIZE_0_DATAOUT_HEIGHT__MASK		0xffff0000
+#define CORE_DATAOUT_SIZE_0_DATAOUT_HEIGHT__SHIFT		16
+static inline uint32_t CORE_DATAOUT_SIZE_0_DATAOUT_HEIGHT(uint32_t val)
+{
+	return ((val) << CORE_DATAOUT_SIZE_0_DATAOUT_HEIGHT__SHIFT) & CORE_DATAOUT_SIZE_0_DATAOUT_HEIGHT__MASK;
+}
+#define CORE_DATAOUT_SIZE_0_DATAOUT_WIDTH__MASK			0x0000ffff
+#define CORE_DATAOUT_SIZE_0_DATAOUT_WIDTH__SHIFT		0
+static inline uint32_t CORE_DATAOUT_SIZE_0_DATAOUT_WIDTH(uint32_t val)
+{
+	return ((val) << CORE_DATAOUT_SIZE_0_DATAOUT_WIDTH__SHIFT) & CORE_DATAOUT_SIZE_0_DATAOUT_WIDTH__MASK;
+}
+
+#define REG_CORE_DATAOUT_SIZE_1					0x00003018
+#define CORE_DATAOUT_SIZE_1_RESERVED_0__MASK			0xffff0000
+#define CORE_DATAOUT_SIZE_1_RESERVED_0__SHIFT			16
+static inline uint32_t CORE_DATAOUT_SIZE_1_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_DATAOUT_SIZE_1_RESERVED_0__SHIFT) & CORE_DATAOUT_SIZE_1_RESERVED_0__MASK;
+}
+#define CORE_DATAOUT_SIZE_1_DATAOUT_CHANNEL__MASK		0x0000ffff
+#define CORE_DATAOUT_SIZE_1_DATAOUT_CHANNEL__SHIFT		0
+static inline uint32_t CORE_DATAOUT_SIZE_1_DATAOUT_CHANNEL(uint32_t val)
+{
+	return ((val) << CORE_DATAOUT_SIZE_1_DATAOUT_CHANNEL__SHIFT) & CORE_DATAOUT_SIZE_1_DATAOUT_CHANNEL__MASK;
+}
+
+#define REG_CORE_CLIP_TRUNCATE					0x0000301c
+#define CORE_CLIP_TRUNCATE_RESERVED_0__MASK			0xffffff80
+#define CORE_CLIP_TRUNCATE_RESERVED_0__SHIFT			7
+static inline uint32_t CORE_CLIP_TRUNCATE_RESERVED_0(uint32_t val)
+{
+	return ((val) << CORE_CLIP_TRUNCATE_RESERVED_0__SHIFT) & CORE_CLIP_TRUNCATE_RESERVED_0__MASK;
+}
+#define CORE_CLIP_TRUNCATE_ROUND_TYPE__MASK			0x00000040
+#define CORE_CLIP_TRUNCATE_ROUND_TYPE__SHIFT			6
+static inline uint32_t CORE_CLIP_TRUNCATE_ROUND_TYPE(uint32_t val)
+{
+	return ((val) << CORE_CLIP_TRUNCATE_ROUND_TYPE__SHIFT) & CORE_CLIP_TRUNCATE_ROUND_TYPE__MASK;
+}
+#define CORE_CLIP_TRUNCATE_RESERVED_1__MASK			0x00000020
+#define CORE_CLIP_TRUNCATE_RESERVED_1__SHIFT			5
+static inline uint32_t CORE_CLIP_TRUNCATE_RESERVED_1(uint32_t val)
+{
+	return ((val) << CORE_CLIP_TRUNCATE_RESERVED_1__SHIFT) & CORE_CLIP_TRUNCATE_RESERVED_1__MASK;
+}
+#define CORE_CLIP_TRUNCATE_CLIP_TRUNCATE__MASK			0x0000001f
+#define CORE_CLIP_TRUNCATE_CLIP_TRUNCATE__SHIFT			0
+static inline uint32_t CORE_CLIP_TRUNCATE_CLIP_TRUNCATE(uint32_t val)
+{
+	return ((val) << CORE_CLIP_TRUNCATE_CLIP_TRUNCATE__SHIFT) & CORE_CLIP_TRUNCATE_CLIP_TRUNCATE__MASK;
+}
+
+#define REG_DPU_S_STATUS					0x00004000
+#define DPU_S_STATUS_RESERVED_0__MASK				0xfffc0000
+#define DPU_S_STATUS_RESERVED_0__SHIFT				18
+static inline uint32_t DPU_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_S_STATUS_RESERVED_0__SHIFT) & DPU_S_STATUS_RESERVED_0__MASK;
+}
+#define DPU_S_STATUS_STATUS_1__MASK				0x00030000
+#define DPU_S_STATUS_STATUS_1__SHIFT				16
+static inline uint32_t DPU_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << DPU_S_STATUS_STATUS_1__SHIFT) & DPU_S_STATUS_STATUS_1__MASK;
+}
+#define DPU_S_STATUS_RESERVED_1__MASK				0x0000fffc
+#define DPU_S_STATUS_RESERVED_1__SHIFT				2
+static inline uint32_t DPU_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_S_STATUS_RESERVED_1__SHIFT) & DPU_S_STATUS_RESERVED_1__MASK;
+}
+#define DPU_S_STATUS_STATUS_0__MASK				0x00000003
+#define DPU_S_STATUS_STATUS_0__SHIFT				0
+static inline uint32_t DPU_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << DPU_S_STATUS_STATUS_0__SHIFT) & DPU_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_DPU_S_POINTER					0x00004004
+#define DPU_S_POINTER_RESERVED_0__MASK				0xfffe0000
+#define DPU_S_POINTER_RESERVED_0__SHIFT				17
+static inline uint32_t DPU_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_RESERVED_0__SHIFT) & DPU_S_POINTER_RESERVED_0__MASK;
+}
+#define DPU_S_POINTER_EXECUTER__MASK				0x00010000
+#define DPU_S_POINTER_EXECUTER__SHIFT				16
+static inline uint32_t DPU_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_EXECUTER__SHIFT) & DPU_S_POINTER_EXECUTER__MASK;
+}
+#define DPU_S_POINTER_RESERVED_1__MASK				0x0000ffc0
+#define DPU_S_POINTER_RESERVED_1__SHIFT				6
+static inline uint32_t DPU_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_RESERVED_1__SHIFT) & DPU_S_POINTER_RESERVED_1__MASK;
+}
+#define DPU_S_POINTER_EXECUTER_PP_CLEAR__MASK			0x00000020
+#define DPU_S_POINTER_EXECUTER_PP_CLEAR__SHIFT			5
+static inline uint32_t DPU_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & DPU_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define DPU_S_POINTER_POINTER_PP_CLEAR__MASK			0x00000010
+#define DPU_S_POINTER_POINTER_PP_CLEAR__SHIFT			4
+static inline uint32_t DPU_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_POINTER_PP_CLEAR__SHIFT) & DPU_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define DPU_S_POINTER_POINTER_PP_MODE__MASK			0x00000008
+#define DPU_S_POINTER_POINTER_PP_MODE__SHIFT			3
+static inline uint32_t DPU_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_POINTER_PP_MODE__SHIFT) & DPU_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define DPU_S_POINTER_EXECUTER_PP_EN__MASK			0x00000004
+#define DPU_S_POINTER_EXECUTER_PP_EN__SHIFT			2
+static inline uint32_t DPU_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_EXECUTER_PP_EN__SHIFT) & DPU_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define DPU_S_POINTER_POINTER_PP_EN__MASK			0x00000002
+#define DPU_S_POINTER_POINTER_PP_EN__SHIFT			1
+static inline uint32_t DPU_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_POINTER_PP_EN__SHIFT) & DPU_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define DPU_S_POINTER_POINTER__MASK				0x00000001
+#define DPU_S_POINTER_POINTER__SHIFT				0
+static inline uint32_t DPU_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << DPU_S_POINTER_POINTER__SHIFT) & DPU_S_POINTER_POINTER__MASK;
+}
+
+#define REG_DPU_OPERATION_ENABLE				0x00004008
+#define DPU_OPERATION_ENABLE_RESERVED_0__MASK			0xfffffffe
+#define DPU_OPERATION_ENABLE_RESERVED_0__SHIFT			1
+static inline uint32_t DPU_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_OPERATION_ENABLE_RESERVED_0__SHIFT) & DPU_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define DPU_OPERATION_ENABLE_OP_EN__MASK			0x00000001
+#define DPU_OPERATION_ENABLE_OP_EN__SHIFT			0
+static inline uint32_t DPU_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << DPU_OPERATION_ENABLE_OP_EN__SHIFT) & DPU_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_DPU_FEATURE_MODE_CFG				0x0000400c
+#define DPU_FEATURE_MODE_CFG_COMB_USE__MASK			0x80000000
+#define DPU_FEATURE_MODE_CFG_COMB_USE__SHIFT			31
+static inline uint32_t DPU_FEATURE_MODE_CFG_COMB_USE(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_COMB_USE__SHIFT) & DPU_FEATURE_MODE_CFG_COMB_USE__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_TP_EN__MASK			0x40000000
+#define DPU_FEATURE_MODE_CFG_TP_EN__SHIFT			30
+static inline uint32_t DPU_FEATURE_MODE_CFG_TP_EN(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_TP_EN__SHIFT) & DPU_FEATURE_MODE_CFG_TP_EN__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_RGP_TYPE__MASK			0x3c000000
+#define DPU_FEATURE_MODE_CFG_RGP_TYPE__SHIFT			26
+static inline uint32_t DPU_FEATURE_MODE_CFG_RGP_TYPE(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_RGP_TYPE__SHIFT) & DPU_FEATURE_MODE_CFG_RGP_TYPE__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_NONALIGN__MASK			0x02000000
+#define DPU_FEATURE_MODE_CFG_NONALIGN__SHIFT			25
+static inline uint32_t DPU_FEATURE_MODE_CFG_NONALIGN(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_NONALIGN__SHIFT) & DPU_FEATURE_MODE_CFG_NONALIGN__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_SURF_LEN__MASK			0x01fffe00
+#define DPU_FEATURE_MODE_CFG_SURF_LEN__SHIFT			9
+static inline uint32_t DPU_FEATURE_MODE_CFG_SURF_LEN(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_SURF_LEN__SHIFT) & DPU_FEATURE_MODE_CFG_SURF_LEN__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_BURST_LEN__MASK			0x000001e0
+#define DPU_FEATURE_MODE_CFG_BURST_LEN__SHIFT			5
+static inline uint32_t DPU_FEATURE_MODE_CFG_BURST_LEN(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_BURST_LEN__SHIFT) & DPU_FEATURE_MODE_CFG_BURST_LEN__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_CONV_MODE__MASK			0x00000018
+#define DPU_FEATURE_MODE_CFG_CONV_MODE__SHIFT			3
+static inline uint32_t DPU_FEATURE_MODE_CFG_CONV_MODE(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_CONV_MODE__SHIFT) & DPU_FEATURE_MODE_CFG_CONV_MODE__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_OUTPUT_MODE__MASK			0x00000006
+#define DPU_FEATURE_MODE_CFG_OUTPUT_MODE__SHIFT			1
+static inline uint32_t DPU_FEATURE_MODE_CFG_OUTPUT_MODE(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_OUTPUT_MODE__SHIFT) & DPU_FEATURE_MODE_CFG_OUTPUT_MODE__MASK;
+}
+#define DPU_FEATURE_MODE_CFG_FLYING_MODE__MASK			0x00000001
+#define DPU_FEATURE_MODE_CFG_FLYING_MODE__SHIFT			0
+static inline uint32_t DPU_FEATURE_MODE_CFG_FLYING_MODE(uint32_t val)
+{
+	return ((val) << DPU_FEATURE_MODE_CFG_FLYING_MODE__SHIFT) & DPU_FEATURE_MODE_CFG_FLYING_MODE__MASK;
+}
+
+#define REG_DPU_DATA_FORMAT					0x00004010
+#define DPU_DATA_FORMAT_OUT_PRECISION__MASK			0xe0000000
+#define DPU_DATA_FORMAT_OUT_PRECISION__SHIFT			29
+static inline uint32_t DPU_DATA_FORMAT_OUT_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_OUT_PRECISION__SHIFT) & DPU_DATA_FORMAT_OUT_PRECISION__MASK;
+}
+#define DPU_DATA_FORMAT_IN_PRECISION__MASK			0x1c000000
+#define DPU_DATA_FORMAT_IN_PRECISION__SHIFT			26
+static inline uint32_t DPU_DATA_FORMAT_IN_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_IN_PRECISION__SHIFT) & DPU_DATA_FORMAT_IN_PRECISION__MASK;
+}
+#define DPU_DATA_FORMAT_EW_TRUNCATE_NEG__MASK			0x03ff0000
+#define DPU_DATA_FORMAT_EW_TRUNCATE_NEG__SHIFT			16
+static inline uint32_t DPU_DATA_FORMAT_EW_TRUNCATE_NEG(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_EW_TRUNCATE_NEG__SHIFT) & DPU_DATA_FORMAT_EW_TRUNCATE_NEG__MASK;
+}
+#define DPU_DATA_FORMAT_BN_MUL_SHIFT_VALUE_NEG__MASK		0x0000fc00
+#define DPU_DATA_FORMAT_BN_MUL_SHIFT_VALUE_NEG__SHIFT		10
+static inline uint32_t DPU_DATA_FORMAT_BN_MUL_SHIFT_VALUE_NEG(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_BN_MUL_SHIFT_VALUE_NEG__SHIFT) & DPU_DATA_FORMAT_BN_MUL_SHIFT_VALUE_NEG__MASK;
+}
+#define DPU_DATA_FORMAT_BS_MUL_SHIFT_VALUE_NEG__MASK		0x000003f0
+#define DPU_DATA_FORMAT_BS_MUL_SHIFT_VALUE_NEG__SHIFT		4
+static inline uint32_t DPU_DATA_FORMAT_BS_MUL_SHIFT_VALUE_NEG(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_BS_MUL_SHIFT_VALUE_NEG__SHIFT) & DPU_DATA_FORMAT_BS_MUL_SHIFT_VALUE_NEG__MASK;
+}
+#define DPU_DATA_FORMAT_MC_SURF_OUT__MASK			0x00000008
+#define DPU_DATA_FORMAT_MC_SURF_OUT__SHIFT			3
+static inline uint32_t DPU_DATA_FORMAT_MC_SURF_OUT(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_MC_SURF_OUT__SHIFT) & DPU_DATA_FORMAT_MC_SURF_OUT__MASK;
+}
+#define DPU_DATA_FORMAT_PROC_PRECISION__MASK			0x00000007
+#define DPU_DATA_FORMAT_PROC_PRECISION__SHIFT			0
+static inline uint32_t DPU_DATA_FORMAT_PROC_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_DATA_FORMAT_PROC_PRECISION__SHIFT) & DPU_DATA_FORMAT_PROC_PRECISION__MASK;
+}
+
+#define REG_DPU_OFFSET_PEND					0x00004014
+#define DPU_OFFSET_PEND_RESERVED_0__MASK			0xffff0000
+#define DPU_OFFSET_PEND_RESERVED_0__SHIFT			16
+static inline uint32_t DPU_OFFSET_PEND_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_OFFSET_PEND_RESERVED_0__SHIFT) & DPU_OFFSET_PEND_RESERVED_0__MASK;
+}
+#define DPU_OFFSET_PEND_OFFSET_PEND__MASK			0x0000ffff
+#define DPU_OFFSET_PEND_OFFSET_PEND__SHIFT			0
+static inline uint32_t DPU_OFFSET_PEND_OFFSET_PEND(uint32_t val)
+{
+	return ((val) << DPU_OFFSET_PEND_OFFSET_PEND__SHIFT) & DPU_OFFSET_PEND_OFFSET_PEND__MASK;
+}
+
+#define REG_DPU_DST_BASE_ADDR					0x00004020
+#define DPU_DST_BASE_ADDR_DST_BASE_ADDR__MASK			0xffffffff
+#define DPU_DST_BASE_ADDR_DST_BASE_ADDR__SHIFT			0
+static inline uint32_t DPU_DST_BASE_ADDR_DST_BASE_ADDR(uint32_t val)
+{
+	return ((val) << DPU_DST_BASE_ADDR_DST_BASE_ADDR__SHIFT) & DPU_DST_BASE_ADDR_DST_BASE_ADDR__MASK;
+}
+
+#define REG_DPU_DST_SURF_STRIDE					0x00004024
+#define DPU_DST_SURF_STRIDE_DST_SURF_STRIDE__MASK		0xfffffff0
+#define DPU_DST_SURF_STRIDE_DST_SURF_STRIDE__SHIFT		4
+static inline uint32_t DPU_DST_SURF_STRIDE_DST_SURF_STRIDE(uint32_t val)
+{
+	return ((val) << DPU_DST_SURF_STRIDE_DST_SURF_STRIDE__SHIFT) & DPU_DST_SURF_STRIDE_DST_SURF_STRIDE__MASK;
+}
+#define DPU_DST_SURF_STRIDE_RESERVED_0__MASK			0x0000000f
+#define DPU_DST_SURF_STRIDE_RESERVED_0__SHIFT			0
+static inline uint32_t DPU_DST_SURF_STRIDE_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_DST_SURF_STRIDE_RESERVED_0__SHIFT) & DPU_DST_SURF_STRIDE_RESERVED_0__MASK;
+}
+
+#define REG_DPU_DATA_CUBE_WIDTH					0x00004030
+#define DPU_DATA_CUBE_WIDTH_RESERVED_0__MASK			0xffffe000
+#define DPU_DATA_CUBE_WIDTH_RESERVED_0__SHIFT			13
+static inline uint32_t DPU_DATA_CUBE_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_WIDTH_RESERVED_0__SHIFT) & DPU_DATA_CUBE_WIDTH_RESERVED_0__MASK;
+}
+#define DPU_DATA_CUBE_WIDTH_WIDTH__MASK				0x00001fff
+#define DPU_DATA_CUBE_WIDTH_WIDTH__SHIFT			0
+static inline uint32_t DPU_DATA_CUBE_WIDTH_WIDTH(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_WIDTH_WIDTH__SHIFT) & DPU_DATA_CUBE_WIDTH_WIDTH__MASK;
+}
+
+#define REG_DPU_DATA_CUBE_HEIGHT				0x00004034
+#define DPU_DATA_CUBE_HEIGHT_RESERVED_0__MASK			0xfe000000
+#define DPU_DATA_CUBE_HEIGHT_RESERVED_0__SHIFT			25
+static inline uint32_t DPU_DATA_CUBE_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_HEIGHT_RESERVED_0__SHIFT) & DPU_DATA_CUBE_HEIGHT_RESERVED_0__MASK;
+}
+#define DPU_DATA_CUBE_HEIGHT_MINMAX_CTL__MASK			0x01c00000
+#define DPU_DATA_CUBE_HEIGHT_MINMAX_CTL__SHIFT			22
+static inline uint32_t DPU_DATA_CUBE_HEIGHT_MINMAX_CTL(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_HEIGHT_MINMAX_CTL__SHIFT) & DPU_DATA_CUBE_HEIGHT_MINMAX_CTL__MASK;
+}
+#define DPU_DATA_CUBE_HEIGHT_RESERVED_1__MASK			0x003fe000
+#define DPU_DATA_CUBE_HEIGHT_RESERVED_1__SHIFT			13
+static inline uint32_t DPU_DATA_CUBE_HEIGHT_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_HEIGHT_RESERVED_1__SHIFT) & DPU_DATA_CUBE_HEIGHT_RESERVED_1__MASK;
+}
+#define DPU_DATA_CUBE_HEIGHT_HEIGHT__MASK			0x00001fff
+#define DPU_DATA_CUBE_HEIGHT_HEIGHT__SHIFT			0
+static inline uint32_t DPU_DATA_CUBE_HEIGHT_HEIGHT(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_HEIGHT_HEIGHT__SHIFT) & DPU_DATA_CUBE_HEIGHT_HEIGHT__MASK;
+}
+
+#define REG_DPU_DATA_CUBE_NOTCH_ADDR				0x00004038
+#define DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_0__MASK		0xe0000000
+#define DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_0__SHIFT		29
+static inline uint32_t DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_0__SHIFT) & DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_0__MASK;
+}
+#define DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_1__MASK		0x1fff0000
+#define DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_1__SHIFT		16
+static inline uint32_t DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_1(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_1__SHIFT) & DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_1__MASK;
+}
+#define DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_1__MASK		0x0000e000
+#define DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_1__SHIFT		13
+static inline uint32_t DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_1__SHIFT) & DPU_DATA_CUBE_NOTCH_ADDR_RESERVED_1__MASK;
+}
+#define DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_0__MASK		0x00001fff
+#define DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_0__SHIFT		0
+static inline uint32_t DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_0(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_0__SHIFT) & DPU_DATA_CUBE_NOTCH_ADDR_NOTCH_ADDR_0__MASK;
+}
+
+#define REG_DPU_DATA_CUBE_CHANNEL				0x0000403c
+#define DPU_DATA_CUBE_CHANNEL_RESERVED_0__MASK			0xe0000000
+#define DPU_DATA_CUBE_CHANNEL_RESERVED_0__SHIFT			29
+static inline uint32_t DPU_DATA_CUBE_CHANNEL_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_CHANNEL_RESERVED_0__SHIFT) & DPU_DATA_CUBE_CHANNEL_RESERVED_0__MASK;
+}
+#define DPU_DATA_CUBE_CHANNEL_ORIG_CHANNEL__MASK		0x1fff0000
+#define DPU_DATA_CUBE_CHANNEL_ORIG_CHANNEL__SHIFT		16
+static inline uint32_t DPU_DATA_CUBE_CHANNEL_ORIG_CHANNEL(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_CHANNEL_ORIG_CHANNEL__SHIFT) & DPU_DATA_CUBE_CHANNEL_ORIG_CHANNEL__MASK;
+}
+#define DPU_DATA_CUBE_CHANNEL_RESERVED_1__MASK			0x0000e000
+#define DPU_DATA_CUBE_CHANNEL_RESERVED_1__SHIFT			13
+static inline uint32_t DPU_DATA_CUBE_CHANNEL_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_CHANNEL_RESERVED_1__SHIFT) & DPU_DATA_CUBE_CHANNEL_RESERVED_1__MASK;
+}
+#define DPU_DATA_CUBE_CHANNEL_CHANNEL__MASK			0x00001fff
+#define DPU_DATA_CUBE_CHANNEL_CHANNEL__SHIFT			0
+static inline uint32_t DPU_DATA_CUBE_CHANNEL_CHANNEL(uint32_t val)
+{
+	return ((val) << DPU_DATA_CUBE_CHANNEL_CHANNEL__SHIFT) & DPU_DATA_CUBE_CHANNEL_CHANNEL__MASK;
+}
+
+#define REG_DPU_BS_CFG						0x00004040
+#define DPU_BS_CFG_RESERVED_0__MASK				0xfff00000
+#define DPU_BS_CFG_RESERVED_0__SHIFT				20
+static inline uint32_t DPU_BS_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_RESERVED_0__SHIFT) & DPU_BS_CFG_RESERVED_0__MASK;
+}
+#define DPU_BS_CFG_BS_ALU_ALGO__MASK				0x000f0000
+#define DPU_BS_CFG_BS_ALU_ALGO__SHIFT				16
+static inline uint32_t DPU_BS_CFG_BS_ALU_ALGO(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_ALU_ALGO__SHIFT) & DPU_BS_CFG_BS_ALU_ALGO__MASK;
+}
+#define DPU_BS_CFG_RESERVED_1__MASK				0x0000fe00
+#define DPU_BS_CFG_RESERVED_1__SHIFT				9
+static inline uint32_t DPU_BS_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_RESERVED_1__SHIFT) & DPU_BS_CFG_RESERVED_1__MASK;
+}
+#define DPU_BS_CFG_BS_ALU_SRC__MASK				0x00000100
+#define DPU_BS_CFG_BS_ALU_SRC__SHIFT				8
+static inline uint32_t DPU_BS_CFG_BS_ALU_SRC(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_ALU_SRC__SHIFT) & DPU_BS_CFG_BS_ALU_SRC__MASK;
+}
+#define DPU_BS_CFG_BS_RELUX_EN__MASK				0x00000080
+#define DPU_BS_CFG_BS_RELUX_EN__SHIFT				7
+static inline uint32_t DPU_BS_CFG_BS_RELUX_EN(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_RELUX_EN__SHIFT) & DPU_BS_CFG_BS_RELUX_EN__MASK;
+}
+#define DPU_BS_CFG_BS_RELU_BYPASS__MASK				0x00000040
+#define DPU_BS_CFG_BS_RELU_BYPASS__SHIFT			6
+static inline uint32_t DPU_BS_CFG_BS_RELU_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_RELU_BYPASS__SHIFT) & DPU_BS_CFG_BS_RELU_BYPASS__MASK;
+}
+#define DPU_BS_CFG_BS_MUL_PRELU__MASK				0x00000020
+#define DPU_BS_CFG_BS_MUL_PRELU__SHIFT				5
+static inline uint32_t DPU_BS_CFG_BS_MUL_PRELU(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_MUL_PRELU__SHIFT) & DPU_BS_CFG_BS_MUL_PRELU__MASK;
+}
+#define DPU_BS_CFG_BS_MUL_BYPASS__MASK				0x00000010
+#define DPU_BS_CFG_BS_MUL_BYPASS__SHIFT				4
+static inline uint32_t DPU_BS_CFG_BS_MUL_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_MUL_BYPASS__SHIFT) & DPU_BS_CFG_BS_MUL_BYPASS__MASK;
+}
+#define DPU_BS_CFG_RESERVED_2__MASK				0x0000000c
+#define DPU_BS_CFG_RESERVED_2__SHIFT				2
+static inline uint32_t DPU_BS_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_RESERVED_2__SHIFT) & DPU_BS_CFG_RESERVED_2__MASK;
+}
+#define DPU_BS_CFG_BS_ALU_BYPASS__MASK				0x00000002
+#define DPU_BS_CFG_BS_ALU_BYPASS__SHIFT				1
+static inline uint32_t DPU_BS_CFG_BS_ALU_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_ALU_BYPASS__SHIFT) & DPU_BS_CFG_BS_ALU_BYPASS__MASK;
+}
+#define DPU_BS_CFG_BS_BYPASS__MASK				0x00000001
+#define DPU_BS_CFG_BS_BYPASS__SHIFT				0
+static inline uint32_t DPU_BS_CFG_BS_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BS_CFG_BS_BYPASS__SHIFT) & DPU_BS_CFG_BS_BYPASS__MASK;
+}
+
+#define REG_DPU_BS_ALU_CFG					0x00004044
+#define DPU_BS_ALU_CFG_BS_ALU_OPERAND__MASK			0xffffffff
+#define DPU_BS_ALU_CFG_BS_ALU_OPERAND__SHIFT			0
+static inline uint32_t DPU_BS_ALU_CFG_BS_ALU_OPERAND(uint32_t val)
+{
+	return ((val) << DPU_BS_ALU_CFG_BS_ALU_OPERAND__SHIFT) & DPU_BS_ALU_CFG_BS_ALU_OPERAND__MASK;
+}
+
+#define REG_DPU_BS_MUL_CFG					0x00004048
+#define DPU_BS_MUL_CFG_BS_MUL_OPERAND__MASK			0xffff0000
+#define DPU_BS_MUL_CFG_BS_MUL_OPERAND__SHIFT			16
+static inline uint32_t DPU_BS_MUL_CFG_BS_MUL_OPERAND(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_BS_MUL_OPERAND__SHIFT) & DPU_BS_MUL_CFG_BS_MUL_OPERAND__MASK;
+}
+#define DPU_BS_MUL_CFG_RESERVED_0__MASK				0x0000c000
+#define DPU_BS_MUL_CFG_RESERVED_0__SHIFT			14
+static inline uint32_t DPU_BS_MUL_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_RESERVED_0__SHIFT) & DPU_BS_MUL_CFG_RESERVED_0__MASK;
+}
+#define DPU_BS_MUL_CFG_BS_MUL_SHIFT_VALUE__MASK			0x00003f00
+#define DPU_BS_MUL_CFG_BS_MUL_SHIFT_VALUE__SHIFT		8
+static inline uint32_t DPU_BS_MUL_CFG_BS_MUL_SHIFT_VALUE(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_BS_MUL_SHIFT_VALUE__SHIFT) & DPU_BS_MUL_CFG_BS_MUL_SHIFT_VALUE__MASK;
+}
+#define DPU_BS_MUL_CFG_RESERVED_1__MASK				0x000000fc
+#define DPU_BS_MUL_CFG_RESERVED_1__SHIFT			2
+static inline uint32_t DPU_BS_MUL_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_RESERVED_1__SHIFT) & DPU_BS_MUL_CFG_RESERVED_1__MASK;
+}
+#define DPU_BS_MUL_CFG_BS_TRUNCATE_SRC__MASK			0x00000002
+#define DPU_BS_MUL_CFG_BS_TRUNCATE_SRC__SHIFT			1
+static inline uint32_t DPU_BS_MUL_CFG_BS_TRUNCATE_SRC(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_BS_TRUNCATE_SRC__SHIFT) & DPU_BS_MUL_CFG_BS_TRUNCATE_SRC__MASK;
+}
+#define DPU_BS_MUL_CFG_BS_MUL_SRC__MASK				0x00000001
+#define DPU_BS_MUL_CFG_BS_MUL_SRC__SHIFT			0
+static inline uint32_t DPU_BS_MUL_CFG_BS_MUL_SRC(uint32_t val)
+{
+	return ((val) << DPU_BS_MUL_CFG_BS_MUL_SRC__SHIFT) & DPU_BS_MUL_CFG_BS_MUL_SRC__MASK;
+}
+
+#define REG_DPU_BS_RELUX_CMP_VALUE				0x0000404c
+#define DPU_BS_RELUX_CMP_VALUE_BS_RELUX_CMP_DAT__MASK		0xffffffff
+#define DPU_BS_RELUX_CMP_VALUE_BS_RELUX_CMP_DAT__SHIFT		0
+static inline uint32_t DPU_BS_RELUX_CMP_VALUE_BS_RELUX_CMP_DAT(uint32_t val)
+{
+	return ((val) << DPU_BS_RELUX_CMP_VALUE_BS_RELUX_CMP_DAT__SHIFT) & DPU_BS_RELUX_CMP_VALUE_BS_RELUX_CMP_DAT__MASK;
+}
+
+#define REG_DPU_BS_OW_CFG					0x00004050
+#define DPU_BS_OW_CFG_RGP_CNTER__MASK				0xf0000000
+#define DPU_BS_OW_CFG_RGP_CNTER__SHIFT				28
+static inline uint32_t DPU_BS_OW_CFG_RGP_CNTER(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_RGP_CNTER__SHIFT) & DPU_BS_OW_CFG_RGP_CNTER__MASK;
+}
+#define DPU_BS_OW_CFG_TP_ORG_EN__MASK				0x08000000
+#define DPU_BS_OW_CFG_TP_ORG_EN__SHIFT				27
+static inline uint32_t DPU_BS_OW_CFG_TP_ORG_EN(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_TP_ORG_EN__SHIFT) & DPU_BS_OW_CFG_TP_ORG_EN__MASK;
+}
+#define DPU_BS_OW_CFG_RESERVED_0__MASK				0x07fff800
+#define DPU_BS_OW_CFG_RESERVED_0__SHIFT				11
+static inline uint32_t DPU_BS_OW_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_RESERVED_0__SHIFT) & DPU_BS_OW_CFG_RESERVED_0__MASK;
+}
+#define DPU_BS_OW_CFG_SIZE_E_2__MASK				0x00000700
+#define DPU_BS_OW_CFG_SIZE_E_2__SHIFT				8
+static inline uint32_t DPU_BS_OW_CFG_SIZE_E_2(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_SIZE_E_2__SHIFT) & DPU_BS_OW_CFG_SIZE_E_2__MASK;
+}
+#define DPU_BS_OW_CFG_SIZE_E_1__MASK				0x000000e0
+#define DPU_BS_OW_CFG_SIZE_E_1__SHIFT				5
+static inline uint32_t DPU_BS_OW_CFG_SIZE_E_1(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_SIZE_E_1__SHIFT) & DPU_BS_OW_CFG_SIZE_E_1__MASK;
+}
+#define DPU_BS_OW_CFG_SIZE_E_0__MASK				0x0000001c
+#define DPU_BS_OW_CFG_SIZE_E_0__SHIFT				2
+static inline uint32_t DPU_BS_OW_CFG_SIZE_E_0(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_SIZE_E_0__SHIFT) & DPU_BS_OW_CFG_SIZE_E_0__MASK;
+}
+#define DPU_BS_OW_CFG_OD_BYPASS__MASK				0x00000002
+#define DPU_BS_OW_CFG_OD_BYPASS__SHIFT				1
+static inline uint32_t DPU_BS_OW_CFG_OD_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_OD_BYPASS__SHIFT) & DPU_BS_OW_CFG_OD_BYPASS__MASK;
+}
+#define DPU_BS_OW_CFG_OW_SRC__MASK				0x00000001
+#define DPU_BS_OW_CFG_OW_SRC__SHIFT				0
+static inline uint32_t DPU_BS_OW_CFG_OW_SRC(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_CFG_OW_SRC__SHIFT) & DPU_BS_OW_CFG_OW_SRC__MASK;
+}
+
+#define REG_DPU_BS_OW_OP					0x00004054
+#define DPU_BS_OW_OP_RESERVED_0__MASK				0xffff0000
+#define DPU_BS_OW_OP_RESERVED_0__SHIFT				16
+static inline uint32_t DPU_BS_OW_OP_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_OP_RESERVED_0__SHIFT) & DPU_BS_OW_OP_RESERVED_0__MASK;
+}
+#define DPU_BS_OW_OP_OW_OP__MASK				0x0000ffff
+#define DPU_BS_OW_OP_OW_OP__SHIFT				0
+static inline uint32_t DPU_BS_OW_OP_OW_OP(uint32_t val)
+{
+	return ((val) << DPU_BS_OW_OP_OW_OP__SHIFT) & DPU_BS_OW_OP_OW_OP__MASK;
+}
+
+#define REG_DPU_WDMA_SIZE_0					0x00004058
+#define DPU_WDMA_SIZE_0_RESERVED_0__MASK			0xf0000000
+#define DPU_WDMA_SIZE_0_RESERVED_0__SHIFT			28
+static inline uint32_t DPU_WDMA_SIZE_0_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_0_RESERVED_0__SHIFT) & DPU_WDMA_SIZE_0_RESERVED_0__MASK;
+}
+#define DPU_WDMA_SIZE_0_TP_PRECISION__MASK			0x08000000
+#define DPU_WDMA_SIZE_0_TP_PRECISION__SHIFT			27
+static inline uint32_t DPU_WDMA_SIZE_0_TP_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_0_TP_PRECISION__SHIFT) & DPU_WDMA_SIZE_0_TP_PRECISION__MASK;
+}
+#define DPU_WDMA_SIZE_0_SIZE_C_WDMA__MASK			0x07ff0000
+#define DPU_WDMA_SIZE_0_SIZE_C_WDMA__SHIFT			16
+static inline uint32_t DPU_WDMA_SIZE_0_SIZE_C_WDMA(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_0_SIZE_C_WDMA__SHIFT) & DPU_WDMA_SIZE_0_SIZE_C_WDMA__MASK;
+}
+#define DPU_WDMA_SIZE_0_RESERVED_1__MASK			0x0000e000
+#define DPU_WDMA_SIZE_0_RESERVED_1__SHIFT			13
+static inline uint32_t DPU_WDMA_SIZE_0_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_0_RESERVED_1__SHIFT) & DPU_WDMA_SIZE_0_RESERVED_1__MASK;
+}
+#define DPU_WDMA_SIZE_0_CHANNEL_WDMA__MASK			0x00001fff
+#define DPU_WDMA_SIZE_0_CHANNEL_WDMA__SHIFT			0
+static inline uint32_t DPU_WDMA_SIZE_0_CHANNEL_WDMA(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_0_CHANNEL_WDMA__SHIFT) & DPU_WDMA_SIZE_0_CHANNEL_WDMA__MASK;
+}
+
+#define REG_DPU_WDMA_SIZE_1					0x0000405c
+#define DPU_WDMA_SIZE_1_RESERVED_0__MASK			0xe0000000
+#define DPU_WDMA_SIZE_1_RESERVED_0__SHIFT			29
+static inline uint32_t DPU_WDMA_SIZE_1_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_1_RESERVED_0__SHIFT) & DPU_WDMA_SIZE_1_RESERVED_0__MASK;
+}
+#define DPU_WDMA_SIZE_1_HEIGHT_WDMA__MASK			0x1fff0000
+#define DPU_WDMA_SIZE_1_HEIGHT_WDMA__SHIFT			16
+static inline uint32_t DPU_WDMA_SIZE_1_HEIGHT_WDMA(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_1_HEIGHT_WDMA__SHIFT) & DPU_WDMA_SIZE_1_HEIGHT_WDMA__MASK;
+}
+#define DPU_WDMA_SIZE_1_RESERVED_1__MASK			0x0000e000
+#define DPU_WDMA_SIZE_1_RESERVED_1__SHIFT			13
+static inline uint32_t DPU_WDMA_SIZE_1_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_1_RESERVED_1__SHIFT) & DPU_WDMA_SIZE_1_RESERVED_1__MASK;
+}
+#define DPU_WDMA_SIZE_1_WIDTH_WDMA__MASK			0x00001fff
+#define DPU_WDMA_SIZE_1_WIDTH_WDMA__SHIFT			0
+static inline uint32_t DPU_WDMA_SIZE_1_WIDTH_WDMA(uint32_t val)
+{
+	return ((val) << DPU_WDMA_SIZE_1_WIDTH_WDMA__SHIFT) & DPU_WDMA_SIZE_1_WIDTH_WDMA__MASK;
+}
+
+#define REG_DPU_BN_CFG						0x00004060
+#define DPU_BN_CFG_RESERVED_0__MASK				0xfff00000
+#define DPU_BN_CFG_RESERVED_0__SHIFT				20
+static inline uint32_t DPU_BN_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_RESERVED_0__SHIFT) & DPU_BN_CFG_RESERVED_0__MASK;
+}
+#define DPU_BN_CFG_BN_ALU_ALGO__MASK				0x000f0000
+#define DPU_BN_CFG_BN_ALU_ALGO__SHIFT				16
+static inline uint32_t DPU_BN_CFG_BN_ALU_ALGO(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_ALU_ALGO__SHIFT) & DPU_BN_CFG_BN_ALU_ALGO__MASK;
+}
+#define DPU_BN_CFG_RESERVED_1__MASK				0x0000fe00
+#define DPU_BN_CFG_RESERVED_1__SHIFT				9
+static inline uint32_t DPU_BN_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_RESERVED_1__SHIFT) & DPU_BN_CFG_RESERVED_1__MASK;
+}
+#define DPU_BN_CFG_BN_ALU_SRC__MASK				0x00000100
+#define DPU_BN_CFG_BN_ALU_SRC__SHIFT				8
+static inline uint32_t DPU_BN_CFG_BN_ALU_SRC(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_ALU_SRC__SHIFT) & DPU_BN_CFG_BN_ALU_SRC__MASK;
+}
+#define DPU_BN_CFG_BN_RELUX_EN__MASK				0x00000080
+#define DPU_BN_CFG_BN_RELUX_EN__SHIFT				7
+static inline uint32_t DPU_BN_CFG_BN_RELUX_EN(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_RELUX_EN__SHIFT) & DPU_BN_CFG_BN_RELUX_EN__MASK;
+}
+#define DPU_BN_CFG_BN_RELU_BYPASS__MASK				0x00000040
+#define DPU_BN_CFG_BN_RELU_BYPASS__SHIFT			6
+static inline uint32_t DPU_BN_CFG_BN_RELU_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_RELU_BYPASS__SHIFT) & DPU_BN_CFG_BN_RELU_BYPASS__MASK;
+}
+#define DPU_BN_CFG_BN_MUL_PRELU__MASK				0x00000020
+#define DPU_BN_CFG_BN_MUL_PRELU__SHIFT				5
+static inline uint32_t DPU_BN_CFG_BN_MUL_PRELU(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_MUL_PRELU__SHIFT) & DPU_BN_CFG_BN_MUL_PRELU__MASK;
+}
+#define DPU_BN_CFG_BN_MUL_BYPASS__MASK				0x00000010
+#define DPU_BN_CFG_BN_MUL_BYPASS__SHIFT				4
+static inline uint32_t DPU_BN_CFG_BN_MUL_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_MUL_BYPASS__SHIFT) & DPU_BN_CFG_BN_MUL_BYPASS__MASK;
+}
+#define DPU_BN_CFG_RESERVED_2__MASK				0x0000000c
+#define DPU_BN_CFG_RESERVED_2__SHIFT				2
+static inline uint32_t DPU_BN_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_RESERVED_2__SHIFT) & DPU_BN_CFG_RESERVED_2__MASK;
+}
+#define DPU_BN_CFG_BN_ALU_BYPASS__MASK				0x00000002
+#define DPU_BN_CFG_BN_ALU_BYPASS__SHIFT				1
+static inline uint32_t DPU_BN_CFG_BN_ALU_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_ALU_BYPASS__SHIFT) & DPU_BN_CFG_BN_ALU_BYPASS__MASK;
+}
+#define DPU_BN_CFG_BN_BYPASS__MASK				0x00000001
+#define DPU_BN_CFG_BN_BYPASS__SHIFT				0
+static inline uint32_t DPU_BN_CFG_BN_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_BN_CFG_BN_BYPASS__SHIFT) & DPU_BN_CFG_BN_BYPASS__MASK;
+}
+
+#define REG_DPU_BN_ALU_CFG					0x00004064
+#define DPU_BN_ALU_CFG_BN_ALU_OPERAND__MASK			0xffffffff
+#define DPU_BN_ALU_CFG_BN_ALU_OPERAND__SHIFT			0
+static inline uint32_t DPU_BN_ALU_CFG_BN_ALU_OPERAND(uint32_t val)
+{
+	return ((val) << DPU_BN_ALU_CFG_BN_ALU_OPERAND__SHIFT) & DPU_BN_ALU_CFG_BN_ALU_OPERAND__MASK;
+}
+
+#define REG_DPU_BN_MUL_CFG					0x00004068
+#define DPU_BN_MUL_CFG_BN_MUL_OPERAND__MASK			0xffff0000
+#define DPU_BN_MUL_CFG_BN_MUL_OPERAND__SHIFT			16
+static inline uint32_t DPU_BN_MUL_CFG_BN_MUL_OPERAND(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_BN_MUL_OPERAND__SHIFT) & DPU_BN_MUL_CFG_BN_MUL_OPERAND__MASK;
+}
+#define DPU_BN_MUL_CFG_RESERVED_0__MASK				0x0000c000
+#define DPU_BN_MUL_CFG_RESERVED_0__SHIFT			14
+static inline uint32_t DPU_BN_MUL_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_RESERVED_0__SHIFT) & DPU_BN_MUL_CFG_RESERVED_0__MASK;
+}
+#define DPU_BN_MUL_CFG_BN_MUL_SHIFT_VALUE__MASK			0x00003f00
+#define DPU_BN_MUL_CFG_BN_MUL_SHIFT_VALUE__SHIFT		8
+static inline uint32_t DPU_BN_MUL_CFG_BN_MUL_SHIFT_VALUE(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_BN_MUL_SHIFT_VALUE__SHIFT) & DPU_BN_MUL_CFG_BN_MUL_SHIFT_VALUE__MASK;
+}
+#define DPU_BN_MUL_CFG_RESERVED_1__MASK				0x000000fc
+#define DPU_BN_MUL_CFG_RESERVED_1__SHIFT			2
+static inline uint32_t DPU_BN_MUL_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_RESERVED_1__SHIFT) & DPU_BN_MUL_CFG_RESERVED_1__MASK;
+}
+#define DPU_BN_MUL_CFG_BN_TRUNCATE_SRC__MASK			0x00000002
+#define DPU_BN_MUL_CFG_BN_TRUNCATE_SRC__SHIFT			1
+static inline uint32_t DPU_BN_MUL_CFG_BN_TRUNCATE_SRC(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_BN_TRUNCATE_SRC__SHIFT) & DPU_BN_MUL_CFG_BN_TRUNCATE_SRC__MASK;
+}
+#define DPU_BN_MUL_CFG_BN_MUL_SRC__MASK				0x00000001
+#define DPU_BN_MUL_CFG_BN_MUL_SRC__SHIFT			0
+static inline uint32_t DPU_BN_MUL_CFG_BN_MUL_SRC(uint32_t val)
+{
+	return ((val) << DPU_BN_MUL_CFG_BN_MUL_SRC__SHIFT) & DPU_BN_MUL_CFG_BN_MUL_SRC__MASK;
+}
+
+#define REG_DPU_BN_RELUX_CMP_VALUE				0x0000406c
+#define DPU_BN_RELUX_CMP_VALUE_BN_RELUX_CMP_DAT__MASK		0xffffffff
+#define DPU_BN_RELUX_CMP_VALUE_BN_RELUX_CMP_DAT__SHIFT		0
+static inline uint32_t DPU_BN_RELUX_CMP_VALUE_BN_RELUX_CMP_DAT(uint32_t val)
+{
+	return ((val) << DPU_BN_RELUX_CMP_VALUE_BN_RELUX_CMP_DAT__SHIFT) & DPU_BN_RELUX_CMP_VALUE_BN_RELUX_CMP_DAT__MASK;
+}
+
+#define REG_DPU_EW_CFG						0x00004070
+#define DPU_EW_CFG_EW_CVT_TYPE__MASK				0x80000000
+#define DPU_EW_CFG_EW_CVT_TYPE__SHIFT				31
+static inline uint32_t DPU_EW_CFG_EW_CVT_TYPE(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_CVT_TYPE__SHIFT) & DPU_EW_CFG_EW_CVT_TYPE__MASK;
+}
+#define DPU_EW_CFG_EW_CVT_ROUND__MASK				0x40000000
+#define DPU_EW_CFG_EW_CVT_ROUND__SHIFT				30
+static inline uint32_t DPU_EW_CFG_EW_CVT_ROUND(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_CVT_ROUND__SHIFT) & DPU_EW_CFG_EW_CVT_ROUND__MASK;
+}
+#define DPU_EW_CFG_EW_DATA_MODE__MASK				0x30000000
+#define DPU_EW_CFG_EW_DATA_MODE__SHIFT				28
+static inline uint32_t DPU_EW_CFG_EW_DATA_MODE(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_DATA_MODE__SHIFT) & DPU_EW_CFG_EW_DATA_MODE__MASK;
+}
+#define DPU_EW_CFG_RESERVED_0__MASK				0x0f000000
+#define DPU_EW_CFG_RESERVED_0__SHIFT				24
+static inline uint32_t DPU_EW_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_RESERVED_0__SHIFT) & DPU_EW_CFG_RESERVED_0__MASK;
+}
+#define DPU_EW_CFG_EDATA_SIZE__MASK				0x00c00000
+#define DPU_EW_CFG_EDATA_SIZE__SHIFT				22
+static inline uint32_t DPU_EW_CFG_EDATA_SIZE(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EDATA_SIZE__SHIFT) & DPU_EW_CFG_EDATA_SIZE__MASK;
+}
+#define DPU_EW_CFG_EW_EQUAL_EN__MASK				0x00200000
+#define DPU_EW_CFG_EW_EQUAL_EN__SHIFT				21
+static inline uint32_t DPU_EW_CFG_EW_EQUAL_EN(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_EQUAL_EN__SHIFT) & DPU_EW_CFG_EW_EQUAL_EN__MASK;
+}
+#define DPU_EW_CFG_EW_BINARY_EN__MASK				0x00100000
+#define DPU_EW_CFG_EW_BINARY_EN__SHIFT				20
+static inline uint32_t DPU_EW_CFG_EW_BINARY_EN(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_BINARY_EN__SHIFT) & DPU_EW_CFG_EW_BINARY_EN__MASK;
+}
+#define DPU_EW_CFG_EW_ALU_ALGO__MASK				0x000f0000
+#define DPU_EW_CFG_EW_ALU_ALGO__SHIFT				16
+static inline uint32_t DPU_EW_CFG_EW_ALU_ALGO(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_ALU_ALGO__SHIFT) & DPU_EW_CFG_EW_ALU_ALGO__MASK;
+}
+#define DPU_EW_CFG_RESERVED_1__MASK				0x0000f800
+#define DPU_EW_CFG_RESERVED_1__SHIFT				11
+static inline uint32_t DPU_EW_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_RESERVED_1__SHIFT) & DPU_EW_CFG_RESERVED_1__MASK;
+}
+#define DPU_EW_CFG_EW_RELUX_EN__MASK				0x00000400
+#define DPU_EW_CFG_EW_RELUX_EN__SHIFT				10
+static inline uint32_t DPU_EW_CFG_EW_RELUX_EN(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_RELUX_EN__SHIFT) & DPU_EW_CFG_EW_RELUX_EN__MASK;
+}
+#define DPU_EW_CFG_EW_RELU_BYPASS__MASK				0x00000200
+#define DPU_EW_CFG_EW_RELU_BYPASS__SHIFT			9
+static inline uint32_t DPU_EW_CFG_EW_RELU_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_RELU_BYPASS__SHIFT) & DPU_EW_CFG_EW_RELU_BYPASS__MASK;
+}
+#define DPU_EW_CFG_EW_OP_CVT_BYPASS__MASK			0x00000100
+#define DPU_EW_CFG_EW_OP_CVT_BYPASS__SHIFT			8
+static inline uint32_t DPU_EW_CFG_EW_OP_CVT_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_OP_CVT_BYPASS__SHIFT) & DPU_EW_CFG_EW_OP_CVT_BYPASS__MASK;
+}
+#define DPU_EW_CFG_EW_LUT_BYPASS__MASK				0x00000080
+#define DPU_EW_CFG_EW_LUT_BYPASS__SHIFT				7
+static inline uint32_t DPU_EW_CFG_EW_LUT_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_LUT_BYPASS__SHIFT) & DPU_EW_CFG_EW_LUT_BYPASS__MASK;
+}
+#define DPU_EW_CFG_EW_OP_SRC__MASK				0x00000040
+#define DPU_EW_CFG_EW_OP_SRC__SHIFT				6
+static inline uint32_t DPU_EW_CFG_EW_OP_SRC(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_OP_SRC__SHIFT) & DPU_EW_CFG_EW_OP_SRC__MASK;
+}
+#define DPU_EW_CFG_EW_MUL_PRELU__MASK				0x00000020
+#define DPU_EW_CFG_EW_MUL_PRELU__SHIFT				5
+static inline uint32_t DPU_EW_CFG_EW_MUL_PRELU(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_MUL_PRELU__SHIFT) & DPU_EW_CFG_EW_MUL_PRELU__MASK;
+}
+#define DPU_EW_CFG_RESERVED_2__MASK				0x00000018
+#define DPU_EW_CFG_RESERVED_2__SHIFT				3
+static inline uint32_t DPU_EW_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_RESERVED_2__SHIFT) & DPU_EW_CFG_RESERVED_2__MASK;
+}
+#define DPU_EW_CFG_EW_OP_TYPE__MASK				0x00000004
+#define DPU_EW_CFG_EW_OP_TYPE__SHIFT				2
+static inline uint32_t DPU_EW_CFG_EW_OP_TYPE(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_OP_TYPE__SHIFT) & DPU_EW_CFG_EW_OP_TYPE__MASK;
+}
+#define DPU_EW_CFG_EW_OP_BYPASS__MASK				0x00000002
+#define DPU_EW_CFG_EW_OP_BYPASS__SHIFT				1
+static inline uint32_t DPU_EW_CFG_EW_OP_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_OP_BYPASS__SHIFT) & DPU_EW_CFG_EW_OP_BYPASS__MASK;
+}
+#define DPU_EW_CFG_EW_BYPASS__MASK				0x00000001
+#define DPU_EW_CFG_EW_BYPASS__SHIFT				0
+static inline uint32_t DPU_EW_CFG_EW_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_EW_CFG_EW_BYPASS__SHIFT) & DPU_EW_CFG_EW_BYPASS__MASK;
+}
+
+#define REG_DPU_EW_CVT_OFFSET_VALUE				0x00004074
+#define DPU_EW_CVT_OFFSET_VALUE_EW_OP_CVT_OFFSET__MASK		0xffffffff
+#define DPU_EW_CVT_OFFSET_VALUE_EW_OP_CVT_OFFSET__SHIFT		0
+static inline uint32_t DPU_EW_CVT_OFFSET_VALUE_EW_OP_CVT_OFFSET(uint32_t val)
+{
+	return ((val) << DPU_EW_CVT_OFFSET_VALUE_EW_OP_CVT_OFFSET__SHIFT) & DPU_EW_CVT_OFFSET_VALUE_EW_OP_CVT_OFFSET__MASK;
+}
+
+#define REG_DPU_EW_CVT_SCALE_VALUE				0x00004078
+#define DPU_EW_CVT_SCALE_VALUE_EW_TRUNCATE__MASK		0xffc00000
+#define DPU_EW_CVT_SCALE_VALUE_EW_TRUNCATE__SHIFT		22
+static inline uint32_t DPU_EW_CVT_SCALE_VALUE_EW_TRUNCATE(uint32_t val)
+{
+	return ((val) << DPU_EW_CVT_SCALE_VALUE_EW_TRUNCATE__SHIFT) & DPU_EW_CVT_SCALE_VALUE_EW_TRUNCATE__MASK;
+}
+#define DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SHIFT__MASK		0x003f0000
+#define DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SHIFT__SHIFT		16
+static inline uint32_t DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SHIFT__SHIFT) & DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SHIFT__MASK;
+}
+#define DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SCALE__MASK		0x0000ffff
+#define DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SCALE__SHIFT		0
+static inline uint32_t DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SCALE(uint32_t val)
+{
+	return ((val) << DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SCALE__SHIFT) & DPU_EW_CVT_SCALE_VALUE_EW_OP_CVT_SCALE__MASK;
+}
+
+#define REG_DPU_EW_RELUX_CMP_VALUE				0x0000407c
+#define DPU_EW_RELUX_CMP_VALUE_EW_RELUX_CMP_DAT__MASK		0xffffffff
+#define DPU_EW_RELUX_CMP_VALUE_EW_RELUX_CMP_DAT__SHIFT		0
+static inline uint32_t DPU_EW_RELUX_CMP_VALUE_EW_RELUX_CMP_DAT(uint32_t val)
+{
+	return ((val) << DPU_EW_RELUX_CMP_VALUE_EW_RELUX_CMP_DAT__SHIFT) & DPU_EW_RELUX_CMP_VALUE_EW_RELUX_CMP_DAT__MASK;
+}
+
+#define REG_DPU_OUT_CVT_OFFSET					0x00004080
+#define DPU_OUT_CVT_OFFSET_OUT_CVT_OFFSET__MASK			0xffffffff
+#define DPU_OUT_CVT_OFFSET_OUT_CVT_OFFSET__SHIFT		0
+static inline uint32_t DPU_OUT_CVT_OFFSET_OUT_CVT_OFFSET(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_OFFSET_OUT_CVT_OFFSET__SHIFT) & DPU_OUT_CVT_OFFSET_OUT_CVT_OFFSET__MASK;
+}
+
+#define REG_DPU_OUT_CVT_SCALE					0x00004084
+#define DPU_OUT_CVT_SCALE_RESERVED_0__MASK			0xfffe0000
+#define DPU_OUT_CVT_SCALE_RESERVED_0__SHIFT			17
+static inline uint32_t DPU_OUT_CVT_SCALE_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SCALE_RESERVED_0__SHIFT) & DPU_OUT_CVT_SCALE_RESERVED_0__MASK;
+}
+#define DPU_OUT_CVT_SCALE_FP32TOFP16_EN__MASK			0x00010000
+#define DPU_OUT_CVT_SCALE_FP32TOFP16_EN__SHIFT			16
+static inline uint32_t DPU_OUT_CVT_SCALE_FP32TOFP16_EN(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SCALE_FP32TOFP16_EN__SHIFT) & DPU_OUT_CVT_SCALE_FP32TOFP16_EN__MASK;
+}
+#define DPU_OUT_CVT_SCALE_OUT_CVT_SCALE__MASK			0x0000ffff
+#define DPU_OUT_CVT_SCALE_OUT_CVT_SCALE__SHIFT			0
+static inline uint32_t DPU_OUT_CVT_SCALE_OUT_CVT_SCALE(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SCALE_OUT_CVT_SCALE__SHIFT) & DPU_OUT_CVT_SCALE_OUT_CVT_SCALE__MASK;
+}
+
+#define REG_DPU_OUT_CVT_SHIFT					0x00004088
+#define DPU_OUT_CVT_SHIFT_CVT_TYPE__MASK			0x80000000
+#define DPU_OUT_CVT_SHIFT_CVT_TYPE__SHIFT			31
+static inline uint32_t DPU_OUT_CVT_SHIFT_CVT_TYPE(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SHIFT_CVT_TYPE__SHIFT) & DPU_OUT_CVT_SHIFT_CVT_TYPE__MASK;
+}
+#define DPU_OUT_CVT_SHIFT_CVT_ROUND__MASK			0x40000000
+#define DPU_OUT_CVT_SHIFT_CVT_ROUND__SHIFT			30
+static inline uint32_t DPU_OUT_CVT_SHIFT_CVT_ROUND(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SHIFT_CVT_ROUND__SHIFT) & DPU_OUT_CVT_SHIFT_CVT_ROUND__MASK;
+}
+#define DPU_OUT_CVT_SHIFT_RESERVED_0__MASK			0x3ff00000
+#define DPU_OUT_CVT_SHIFT_RESERVED_0__SHIFT			20
+static inline uint32_t DPU_OUT_CVT_SHIFT_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SHIFT_RESERVED_0__SHIFT) & DPU_OUT_CVT_SHIFT_RESERVED_0__MASK;
+}
+#define DPU_OUT_CVT_SHIFT_MINUS_EXP__MASK			0x000ff000
+#define DPU_OUT_CVT_SHIFT_MINUS_EXP__SHIFT			12
+static inline uint32_t DPU_OUT_CVT_SHIFT_MINUS_EXP(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SHIFT_MINUS_EXP__SHIFT) & DPU_OUT_CVT_SHIFT_MINUS_EXP__MASK;
+}
+#define DPU_OUT_CVT_SHIFT_OUT_CVT_SHIFT__MASK			0x00000fff
+#define DPU_OUT_CVT_SHIFT_OUT_CVT_SHIFT__SHIFT			0
+static inline uint32_t DPU_OUT_CVT_SHIFT_OUT_CVT_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_OUT_CVT_SHIFT_OUT_CVT_SHIFT__SHIFT) & DPU_OUT_CVT_SHIFT_OUT_CVT_SHIFT__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_0					0x00004090
+#define DPU_EW_OP_VALUE_0_EW_OPERAND_0__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_0_EW_OPERAND_0__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_0_EW_OPERAND_0(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_0_EW_OPERAND_0__SHIFT) & DPU_EW_OP_VALUE_0_EW_OPERAND_0__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_1					0x00004094
+#define DPU_EW_OP_VALUE_1_EW_OPERAND_1__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_1_EW_OPERAND_1__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_1_EW_OPERAND_1(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_1_EW_OPERAND_1__SHIFT) & DPU_EW_OP_VALUE_1_EW_OPERAND_1__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_2					0x00004098
+#define DPU_EW_OP_VALUE_2_EW_OPERAND_2__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_2_EW_OPERAND_2__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_2_EW_OPERAND_2(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_2_EW_OPERAND_2__SHIFT) & DPU_EW_OP_VALUE_2_EW_OPERAND_2__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_3					0x0000409c
+#define DPU_EW_OP_VALUE_3_EW_OPERAND_3__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_3_EW_OPERAND_3__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_3_EW_OPERAND_3(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_3_EW_OPERAND_3__SHIFT) & DPU_EW_OP_VALUE_3_EW_OPERAND_3__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_4					0x000040a0
+#define DPU_EW_OP_VALUE_4_EW_OPERAND_4__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_4_EW_OPERAND_4__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_4_EW_OPERAND_4(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_4_EW_OPERAND_4__SHIFT) & DPU_EW_OP_VALUE_4_EW_OPERAND_4__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_5					0x000040a4
+#define DPU_EW_OP_VALUE_5_EW_OPERAND_5__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_5_EW_OPERAND_5__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_5_EW_OPERAND_5(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_5_EW_OPERAND_5__SHIFT) & DPU_EW_OP_VALUE_5_EW_OPERAND_5__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_6					0x000040a8
+#define DPU_EW_OP_VALUE_6_EW_OPERAND_6__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_6_EW_OPERAND_6__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_6_EW_OPERAND_6(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_6_EW_OPERAND_6__SHIFT) & DPU_EW_OP_VALUE_6_EW_OPERAND_6__MASK;
+}
+
+#define REG_DPU_EW_OP_VALUE_7					0x000040ac
+#define DPU_EW_OP_VALUE_7_EW_OPERAND_7__MASK			0xffffffff
+#define DPU_EW_OP_VALUE_7_EW_OPERAND_7__SHIFT			0
+static inline uint32_t DPU_EW_OP_VALUE_7_EW_OPERAND_7(uint32_t val)
+{
+	return ((val) << DPU_EW_OP_VALUE_7_EW_OPERAND_7__SHIFT) & DPU_EW_OP_VALUE_7_EW_OPERAND_7__MASK;
+}
+
+#define REG_DPU_SURFACE_ADD					0x000040c0
+#define DPU_SURFACE_ADD_SURF_ADD__MASK				0xfffffff0
+#define DPU_SURFACE_ADD_SURF_ADD__SHIFT				4
+static inline uint32_t DPU_SURFACE_ADD_SURF_ADD(uint32_t val)
+{
+	return ((val) << DPU_SURFACE_ADD_SURF_ADD__SHIFT) & DPU_SURFACE_ADD_SURF_ADD__MASK;
+}
+#define DPU_SURFACE_ADD_RESERVED_0__MASK			0x0000000f
+#define DPU_SURFACE_ADD_RESERVED_0__SHIFT			0
+static inline uint32_t DPU_SURFACE_ADD_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_SURFACE_ADD_RESERVED_0__SHIFT) & DPU_SURFACE_ADD_RESERVED_0__MASK;
+}
+
+#define REG_DPU_LUT_ACCESS_CFG					0x00004100
+#define DPU_LUT_ACCESS_CFG_RESERVED_0__MASK			0xfffc0000
+#define DPU_LUT_ACCESS_CFG_RESERVED_0__SHIFT			18
+static inline uint32_t DPU_LUT_ACCESS_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_CFG_RESERVED_0__SHIFT) & DPU_LUT_ACCESS_CFG_RESERVED_0__MASK;
+}
+#define DPU_LUT_ACCESS_CFG_LUT_ACCESS_TYPE__MASK		0x00020000
+#define DPU_LUT_ACCESS_CFG_LUT_ACCESS_TYPE__SHIFT		17
+static inline uint32_t DPU_LUT_ACCESS_CFG_LUT_ACCESS_TYPE(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_CFG_LUT_ACCESS_TYPE__SHIFT) & DPU_LUT_ACCESS_CFG_LUT_ACCESS_TYPE__MASK;
+}
+#define DPU_LUT_ACCESS_CFG_LUT_TABLE_ID__MASK			0x00010000
+#define DPU_LUT_ACCESS_CFG_LUT_TABLE_ID__SHIFT			16
+static inline uint32_t DPU_LUT_ACCESS_CFG_LUT_TABLE_ID(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_CFG_LUT_TABLE_ID__SHIFT) & DPU_LUT_ACCESS_CFG_LUT_TABLE_ID__MASK;
+}
+#define DPU_LUT_ACCESS_CFG_RESERVED_1__MASK			0x0000fc00
+#define DPU_LUT_ACCESS_CFG_RESERVED_1__SHIFT			10
+static inline uint32_t DPU_LUT_ACCESS_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_CFG_RESERVED_1__SHIFT) & DPU_LUT_ACCESS_CFG_RESERVED_1__MASK;
+}
+#define DPU_LUT_ACCESS_CFG_LUT_ADDR__MASK			0x000003ff
+#define DPU_LUT_ACCESS_CFG_LUT_ADDR__SHIFT			0
+static inline uint32_t DPU_LUT_ACCESS_CFG_LUT_ADDR(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_CFG_LUT_ADDR__SHIFT) & DPU_LUT_ACCESS_CFG_LUT_ADDR__MASK;
+}
+
+#define REG_DPU_LUT_ACCESS_DATA					0x00004104
+#define DPU_LUT_ACCESS_DATA_RESERVED_0__MASK			0xffff0000
+#define DPU_LUT_ACCESS_DATA_RESERVED_0__SHIFT			16
+static inline uint32_t DPU_LUT_ACCESS_DATA_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_DATA_RESERVED_0__SHIFT) & DPU_LUT_ACCESS_DATA_RESERVED_0__MASK;
+}
+#define DPU_LUT_ACCESS_DATA_LUT_ACCESS_DATA__MASK		0x0000ffff
+#define DPU_LUT_ACCESS_DATA_LUT_ACCESS_DATA__SHIFT		0
+static inline uint32_t DPU_LUT_ACCESS_DATA_LUT_ACCESS_DATA(uint32_t val)
+{
+	return ((val) << DPU_LUT_ACCESS_DATA_LUT_ACCESS_DATA__SHIFT) & DPU_LUT_ACCESS_DATA_LUT_ACCESS_DATA__MASK;
+}
+
+#define REG_DPU_LUT_CFG						0x00004108
+#define DPU_LUT_CFG_RESERVED_0__MASK				0xffffff00
+#define DPU_LUT_CFG_RESERVED_0__SHIFT				8
+static inline uint32_t DPU_LUT_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_RESERVED_0__SHIFT) & DPU_LUT_CFG_RESERVED_0__MASK;
+}
+#define DPU_LUT_CFG_LUT_CAL_SEL__MASK				0x00000080
+#define DPU_LUT_CFG_LUT_CAL_SEL__SHIFT				7
+static inline uint32_t DPU_LUT_CFG_LUT_CAL_SEL(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_CAL_SEL__SHIFT) & DPU_LUT_CFG_LUT_CAL_SEL__MASK;
+}
+#define DPU_LUT_CFG_LUT_HYBRID_PRIORITY__MASK			0x00000040
+#define DPU_LUT_CFG_LUT_HYBRID_PRIORITY__SHIFT			6
+static inline uint32_t DPU_LUT_CFG_LUT_HYBRID_PRIORITY(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_HYBRID_PRIORITY__SHIFT) & DPU_LUT_CFG_LUT_HYBRID_PRIORITY__MASK;
+}
+#define DPU_LUT_CFG_LUT_OFLOW_PRIORITY__MASK			0x00000020
+#define DPU_LUT_CFG_LUT_OFLOW_PRIORITY__SHIFT			5
+static inline uint32_t DPU_LUT_CFG_LUT_OFLOW_PRIORITY(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_OFLOW_PRIORITY__SHIFT) & DPU_LUT_CFG_LUT_OFLOW_PRIORITY__MASK;
+}
+#define DPU_LUT_CFG_LUT_UFLOW_PRIORITY__MASK			0x00000010
+#define DPU_LUT_CFG_LUT_UFLOW_PRIORITY__SHIFT			4
+static inline uint32_t DPU_LUT_CFG_LUT_UFLOW_PRIORITY(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_UFLOW_PRIORITY__SHIFT) & DPU_LUT_CFG_LUT_UFLOW_PRIORITY__MASK;
+}
+#define DPU_LUT_CFG_LUT_LO_LE_MUX__MASK				0x0000000c
+#define DPU_LUT_CFG_LUT_LO_LE_MUX__SHIFT			2
+static inline uint32_t DPU_LUT_CFG_LUT_LO_LE_MUX(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_LO_LE_MUX__SHIFT) & DPU_LUT_CFG_LUT_LO_LE_MUX__MASK;
+}
+#define DPU_LUT_CFG_LUT_EXPAND_EN__MASK				0x00000002
+#define DPU_LUT_CFG_LUT_EXPAND_EN__SHIFT			1
+static inline uint32_t DPU_LUT_CFG_LUT_EXPAND_EN(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_EXPAND_EN__SHIFT) & DPU_LUT_CFG_LUT_EXPAND_EN__MASK;
+}
+#define DPU_LUT_CFG_LUT_ROAD_SEL__MASK				0x00000001
+#define DPU_LUT_CFG_LUT_ROAD_SEL__SHIFT				0
+static inline uint32_t DPU_LUT_CFG_LUT_ROAD_SEL(uint32_t val)
+{
+	return ((val) << DPU_LUT_CFG_LUT_ROAD_SEL__SHIFT) & DPU_LUT_CFG_LUT_ROAD_SEL__MASK;
+}
+
+#define REG_DPU_LUT_INFO					0x0000410c
+#define DPU_LUT_INFO_RESERVED_0__MASK				0xff000000
+#define DPU_LUT_INFO_RESERVED_0__SHIFT				24
+static inline uint32_t DPU_LUT_INFO_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_INFO_RESERVED_0__SHIFT) & DPU_LUT_INFO_RESERVED_0__MASK;
+}
+#define DPU_LUT_INFO_LUT_LO_INDEX_SELECT__MASK			0x00ff0000
+#define DPU_LUT_INFO_LUT_LO_INDEX_SELECT__SHIFT			16
+static inline uint32_t DPU_LUT_INFO_LUT_LO_INDEX_SELECT(uint32_t val)
+{
+	return ((val) << DPU_LUT_INFO_LUT_LO_INDEX_SELECT__SHIFT) & DPU_LUT_INFO_LUT_LO_INDEX_SELECT__MASK;
+}
+#define DPU_LUT_INFO_LUT_LE_INDEX_SELECT__MASK			0x0000ff00
+#define DPU_LUT_INFO_LUT_LE_INDEX_SELECT__SHIFT			8
+static inline uint32_t DPU_LUT_INFO_LUT_LE_INDEX_SELECT(uint32_t val)
+{
+	return ((val) << DPU_LUT_INFO_LUT_LE_INDEX_SELECT__SHIFT) & DPU_LUT_INFO_LUT_LE_INDEX_SELECT__MASK;
+}
+#define DPU_LUT_INFO_RESERVED_1__MASK				0x000000ff
+#define DPU_LUT_INFO_RESERVED_1__SHIFT				0
+static inline uint32_t DPU_LUT_INFO_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_LUT_INFO_RESERVED_1__SHIFT) & DPU_LUT_INFO_RESERVED_1__MASK;
+}
+
+#define REG_DPU_LUT_LE_START					0x00004110
+#define DPU_LUT_LE_START_LUT_LE_START__MASK			0xffffffff
+#define DPU_LUT_LE_START_LUT_LE_START__SHIFT			0
+static inline uint32_t DPU_LUT_LE_START_LUT_LE_START(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_START_LUT_LE_START__SHIFT) & DPU_LUT_LE_START_LUT_LE_START__MASK;
+}
+
+#define REG_DPU_LUT_LE_END					0x00004114
+#define DPU_LUT_LE_END_LUT_LE_END__MASK				0xffffffff
+#define DPU_LUT_LE_END_LUT_LE_END__SHIFT			0
+static inline uint32_t DPU_LUT_LE_END_LUT_LE_END(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_END_LUT_LE_END__SHIFT) & DPU_LUT_LE_END_LUT_LE_END__MASK;
+}
+
+#define REG_DPU_LUT_LO_START					0x00004118
+#define DPU_LUT_LO_START_LUT_LO_START__MASK			0xffffffff
+#define DPU_LUT_LO_START_LUT_LO_START__SHIFT			0
+static inline uint32_t DPU_LUT_LO_START_LUT_LO_START(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_START_LUT_LO_START__SHIFT) & DPU_LUT_LO_START_LUT_LO_START__MASK;
+}
+
+#define REG_DPU_LUT_LO_END					0x0000411c
+#define DPU_LUT_LO_END_LUT_LO_END__MASK				0xffffffff
+#define DPU_LUT_LO_END_LUT_LO_END__SHIFT			0
+static inline uint32_t DPU_LUT_LO_END_LUT_LO_END(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_END_LUT_LO_END__SHIFT) & DPU_LUT_LO_END_LUT_LO_END__MASK;
+}
+
+#define REG_DPU_LUT_LE_SLOPE_SCALE				0x00004120
+#define DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_OFLOW_SCALE__MASK	0xffff0000
+#define DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_OFLOW_SCALE__SHIFT	16
+static inline uint32_t DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_OFLOW_SCALE(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_OFLOW_SCALE__SHIFT) & DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_OFLOW_SCALE__MASK;
+}
+#define DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_UFLOW_SCALE__MASK	0x0000ffff
+#define DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_UFLOW_SCALE__SHIFT	0
+static inline uint32_t DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_UFLOW_SCALE(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_UFLOW_SCALE__SHIFT) & DPU_LUT_LE_SLOPE_SCALE_LUT_LE_SLOPE_UFLOW_SCALE__MASK;
+}
+
+#define REG_DPU_LUT_LE_SLOPE_SHIFT				0x00004124
+#define DPU_LUT_LE_SLOPE_SHIFT_RESERVED_0__MASK			0xfffffc00
+#define DPU_LUT_LE_SLOPE_SHIFT_RESERVED_0__SHIFT		10
+static inline uint32_t DPU_LUT_LE_SLOPE_SHIFT_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_SLOPE_SHIFT_RESERVED_0__SHIFT) & DPU_LUT_LE_SLOPE_SHIFT_RESERVED_0__MASK;
+}
+#define DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_OFLOW_SHIFT__MASK	0x000003e0
+#define DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_OFLOW_SHIFT__SHIFT	5
+static inline uint32_t DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_OFLOW_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_OFLOW_SHIFT__SHIFT) & DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_OFLOW_SHIFT__MASK;
+}
+#define DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_UFLOW_SHIFT__MASK	0x0000001f
+#define DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_UFLOW_SHIFT__SHIFT	0
+static inline uint32_t DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_UFLOW_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_UFLOW_SHIFT__SHIFT) & DPU_LUT_LE_SLOPE_SHIFT_LUT_LE_SLOPE_UFLOW_SHIFT__MASK;
+}
+
+#define REG_DPU_LUT_LO_SLOPE_SCALE				0x00004128
+#define DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_OFLOW_SCALE__MASK	0xffff0000
+#define DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_OFLOW_SCALE__SHIFT	16
+static inline uint32_t DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_OFLOW_SCALE(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_OFLOW_SCALE__SHIFT) & DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_OFLOW_SCALE__MASK;
+}
+#define DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_UFLOW_SCALE__MASK	0x0000ffff
+#define DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_UFLOW_SCALE__SHIFT	0
+static inline uint32_t DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_UFLOW_SCALE(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_UFLOW_SCALE__SHIFT) & DPU_LUT_LO_SLOPE_SCALE_LUT_LO_SLOPE_UFLOW_SCALE__MASK;
+}
+
+#define REG_DPU_LUT_LO_SLOPE_SHIFT				0x0000412c
+#define DPU_LUT_LO_SLOPE_SHIFT_RESERVED_0__MASK			0xfffffc00
+#define DPU_LUT_LO_SLOPE_SHIFT_RESERVED_0__SHIFT		10
+static inline uint32_t DPU_LUT_LO_SLOPE_SHIFT_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_SLOPE_SHIFT_RESERVED_0__SHIFT) & DPU_LUT_LO_SLOPE_SHIFT_RESERVED_0__MASK;
+}
+#define DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_OFLOW_SHIFT__MASK	0x000003e0
+#define DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_OFLOW_SHIFT__SHIFT	5
+static inline uint32_t DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_OFLOW_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_OFLOW_SHIFT__SHIFT) & DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_OFLOW_SHIFT__MASK;
+}
+#define DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_UFLOW_SHIFT__MASK	0x0000001f
+#define DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_UFLOW_SHIFT__SHIFT	0
+static inline uint32_t DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_UFLOW_SHIFT(uint32_t val)
+{
+	return ((val) << DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_UFLOW_SHIFT__SHIFT) & DPU_LUT_LO_SLOPE_SHIFT_LUT_LO_SLOPE_UFLOW_SHIFT__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_S_STATUS				0x00005000
+#define DPU_RDMA_RDMA_S_STATUS_RESERVED_0__MASK			0xfffc0000
+#define DPU_RDMA_RDMA_S_STATUS_RESERVED_0__SHIFT		18
+static inline uint32_t DPU_RDMA_RDMA_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_STATUS_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_S_STATUS_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_S_STATUS_STATUS_1__MASK			0x00030000
+#define DPU_RDMA_RDMA_S_STATUS_STATUS_1__SHIFT			16
+static inline uint32_t DPU_RDMA_RDMA_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_STATUS_STATUS_1__SHIFT) & DPU_RDMA_RDMA_S_STATUS_STATUS_1__MASK;
+}
+#define DPU_RDMA_RDMA_S_STATUS_RESERVED_1__MASK			0x0000fffc
+#define DPU_RDMA_RDMA_S_STATUS_RESERVED_1__SHIFT		2
+static inline uint32_t DPU_RDMA_RDMA_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_STATUS_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_S_STATUS_RESERVED_1__MASK;
+}
+#define DPU_RDMA_RDMA_S_STATUS_STATUS_0__MASK			0x00000003
+#define DPU_RDMA_RDMA_S_STATUS_STATUS_0__SHIFT			0
+static inline uint32_t DPU_RDMA_RDMA_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_STATUS_STATUS_0__SHIFT) & DPU_RDMA_RDMA_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_S_POINTER				0x00005004
+#define DPU_RDMA_RDMA_S_POINTER_RESERVED_0__MASK		0xfffe0000
+#define DPU_RDMA_RDMA_S_POINTER_RESERVED_0__SHIFT		17
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_S_POINTER_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER__MASK			0x00010000
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER__SHIFT			16
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_EXECUTER__SHIFT) & DPU_RDMA_RDMA_S_POINTER_EXECUTER__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_RESERVED_1__MASK		0x0000ffc0
+#define DPU_RDMA_RDMA_S_POINTER_RESERVED_1__SHIFT		6
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_S_POINTER_RESERVED_1__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__MASK		0x00000020
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT	5
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__MASK		0x00000010
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__SHIFT		4
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__SHIFT) & DPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__MASK		0x00000008
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__SHIFT		3
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__SHIFT) & DPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__MASK		0x00000004
+#define DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__SHIFT		2
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__SHIFT) & DPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__MASK		0x00000002
+#define DPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__SHIFT		1
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__SHIFT) & DPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define DPU_RDMA_RDMA_S_POINTER_POINTER__MASK			0x00000001
+#define DPU_RDMA_RDMA_S_POINTER_POINTER__SHIFT			0
+static inline uint32_t DPU_RDMA_RDMA_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_S_POINTER_POINTER__SHIFT) & DPU_RDMA_RDMA_S_POINTER_POINTER__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_OPERATION_ENABLE			0x00005008
+#define DPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__MASK		0xfffffffe
+#define DPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__SHIFT	1
+static inline uint32_t DPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__MASK		0x00000001
+#define DPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__SHIFT) & DPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_DATA_CUBE_WIDTH			0x0000500c
+#define DPU_RDMA_RDMA_DATA_CUBE_WIDTH_RESERVED_0__MASK		0xffffe000
+#define DPU_RDMA_RDMA_DATA_CUBE_WIDTH_RESERVED_0__SHIFT		13
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_WIDTH_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_WIDTH_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_DATA_CUBE_WIDTH_WIDTH__MASK		0x00001fff
+#define DPU_RDMA_RDMA_DATA_CUBE_WIDTH_WIDTH__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_WIDTH_WIDTH(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_WIDTH_WIDTH__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_WIDTH_WIDTH__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_DATA_CUBE_HEIGHT			0x00005010
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_0__MASK		0xe0000000
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_0__SHIFT	29
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_EW_LINE_NOTCH_ADDR__MASK	0x1fff0000
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_EW_LINE_NOTCH_ADDR__SHIFT	16
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_EW_LINE_NOTCH_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_EW_LINE_NOTCH_ADDR__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_EW_LINE_NOTCH_ADDR__MASK;
+}
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_1__MASK		0x0000e000
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_1__SHIFT	13
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_RESERVED_1__MASK;
+}
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_HEIGHT__MASK		0x00001fff
+#define DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_HEIGHT__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_HEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_HEIGHT__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_HEIGHT_HEIGHT__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_DATA_CUBE_CHANNEL			0x00005014
+#define DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_RESERVED_0__MASK	0xffffe000
+#define DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_RESERVED_0__SHIFT	13
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_CHANNEL__MASK		0x00001fff
+#define DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_CHANNEL__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_CHANNEL(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_CHANNEL__SHIFT) & DPU_RDMA_RDMA_DATA_CUBE_CHANNEL_CHANNEL__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_SRC_BASE_ADDR				0x00005018
+#define DPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__MASK		0xffffffff
+#define DPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__SHIFT	0
+static inline uint32_t DPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__SHIFT) & DPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_BRDMA_CFG				0x0000501c
+#define DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_0__MASK		0xffffffe0
+#define DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_0__SHIFT		5
+static inline uint32_t DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_BRDMA_CFG_BRDMA_DATA_USE__MASK		0x0000001e
+#define DPU_RDMA_RDMA_BRDMA_CFG_BRDMA_DATA_USE__SHIFT		1
+static inline uint32_t DPU_RDMA_RDMA_BRDMA_CFG_BRDMA_DATA_USE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_BRDMA_CFG_BRDMA_DATA_USE__SHIFT) & DPU_RDMA_RDMA_BRDMA_CFG_BRDMA_DATA_USE__MASK;
+}
+#define DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_1__MASK		0x00000001
+#define DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_1__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_BRDMA_CFG_RESERVED_1__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_BS_BASE_ADDR				0x00005020
+#define DPU_RDMA_RDMA_BS_BASE_ADDR_BS_BASE_ADDR__MASK		0xffffffff
+#define DPU_RDMA_RDMA_BS_BASE_ADDR_BS_BASE_ADDR__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_BS_BASE_ADDR_BS_BASE_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_BS_BASE_ADDR_BS_BASE_ADDR__SHIFT) & DPU_RDMA_RDMA_BS_BASE_ADDR_BS_BASE_ADDR__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_NRDMA_CFG				0x00005028
+#define DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_0__MASK		0xffffffe0
+#define DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_0__SHIFT		5
+static inline uint32_t DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_NRDMA_CFG_NRDMA_DATA_USE__MASK		0x0000001e
+#define DPU_RDMA_RDMA_NRDMA_CFG_NRDMA_DATA_USE__SHIFT		1
+static inline uint32_t DPU_RDMA_RDMA_NRDMA_CFG_NRDMA_DATA_USE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_NRDMA_CFG_NRDMA_DATA_USE__SHIFT) & DPU_RDMA_RDMA_NRDMA_CFG_NRDMA_DATA_USE__MASK;
+}
+#define DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_1__MASK		0x00000001
+#define DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_1__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_NRDMA_CFG_RESERVED_1__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_BN_BASE_ADDR				0x0000502c
+#define DPU_RDMA_RDMA_BN_BASE_ADDR_BN_BASE_ADDR__MASK		0xffffffff
+#define DPU_RDMA_RDMA_BN_BASE_ADDR_BN_BASE_ADDR__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_BN_BASE_ADDR_BN_BASE_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_BN_BASE_ADDR_BN_BASE_ADDR__SHIFT) & DPU_RDMA_RDMA_BN_BASE_ADDR_BN_BASE_ADDR__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_ERDMA_CFG				0x00005034
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_MODE__MASK		0xc0000000
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_MODE__SHIFT		30
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_MODE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_MODE__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_MODE__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_SURF_MODE__MASK		0x20000000
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_SURF_MODE__SHIFT		29
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_SURF_MODE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_SURF_MODE__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_SURF_MODE__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_NONALIGN__MASK		0x10000000
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_NONALIGN__SHIFT		28
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_NONALIGN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_NONALIGN__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_NONALIGN__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_RESERVED_0__MASK		0x0ffffff0
+#define DPU_RDMA_RDMA_ERDMA_CFG_RESERVED_0__SHIFT		4
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_SIZE__MASK		0x0000000c
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_SIZE__SHIFT		2
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_SIZE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_SIZE__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DATA_SIZE__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_OV4K_BYPASS__MASK		0x00000002
+#define DPU_RDMA_RDMA_ERDMA_CFG_OV4K_BYPASS__SHIFT		1
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_OV4K_BYPASS(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_OV4K_BYPASS__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_OV4K_BYPASS__MASK;
+}
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DISABLE__MASK		0x00000001
+#define DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DISABLE__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DISABLE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DISABLE__SHIFT) & DPU_RDMA_RDMA_ERDMA_CFG_ERDMA_DISABLE__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_EW_BASE_ADDR				0x00005038
+#define DPU_RDMA_RDMA_EW_BASE_ADDR_EW_BASE_ADDR__MASK		0xffffffff
+#define DPU_RDMA_RDMA_EW_BASE_ADDR_EW_BASE_ADDR__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_EW_BASE_ADDR_EW_BASE_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_EW_BASE_ADDR_EW_BASE_ADDR__SHIFT) & DPU_RDMA_RDMA_EW_BASE_ADDR_EW_BASE_ADDR__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_EW_SURF_STRIDE			0x00005040
+#define DPU_RDMA_RDMA_EW_SURF_STRIDE_EW_SURF_STRIDE__MASK	0xfffffff0
+#define DPU_RDMA_RDMA_EW_SURF_STRIDE_EW_SURF_STRIDE__SHIFT	4
+static inline uint32_t DPU_RDMA_RDMA_EW_SURF_STRIDE_EW_SURF_STRIDE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_EW_SURF_STRIDE_EW_SURF_STRIDE__SHIFT) & DPU_RDMA_RDMA_EW_SURF_STRIDE_EW_SURF_STRIDE__MASK;
+}
+#define DPU_RDMA_RDMA_EW_SURF_STRIDE_RESERVED_0__MASK		0x0000000f
+#define DPU_RDMA_RDMA_EW_SURF_STRIDE_RESERVED_0__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_EW_SURF_STRIDE_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_EW_SURF_STRIDE_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_EW_SURF_STRIDE_RESERVED_0__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_FEATURE_MODE_CFG			0x00005044
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_RESERVED_0__MASK		0xfffc0000
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_RESERVED_0__SHIFT	18
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_IN_PRECISION__MASK	0x00038000
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_IN_PRECISION__SHIFT	15
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_IN_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_IN_PRECISION__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_IN_PRECISION__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_BURST_LEN__MASK		0x00007800
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_BURST_LEN__SHIFT		11
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_BURST_LEN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_BURST_LEN__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_BURST_LEN__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_COMB_USE__MASK		0x00000700
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_COMB_USE__SHIFT		8
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_COMB_USE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_COMB_USE__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_COMB_USE__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_PROC_PRECISION__MASK	0x000000e0
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_PROC_PRECISION__SHIFT	5
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_PROC_PRECISION(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_PROC_PRECISION__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_PROC_PRECISION__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_DISABLE__MASK	0x00000010
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_DISABLE__SHIFT	4
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_DISABLE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_DISABLE__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_DISABLE__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_FP16TOFP32_EN__MASK	0x00000008
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_FP16TOFP32_EN__SHIFT	3
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_FP16TOFP32_EN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_FP16TOFP32_EN__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_MRDMA_FP16TOFP32_EN__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_CONV_MODE__MASK		0x00000006
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_CONV_MODE__SHIFT		1
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_CONV_MODE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_CONV_MODE__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_CONV_MODE__MASK;
+}
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_FLYING_MODE__MASK	0x00000001
+#define DPU_RDMA_RDMA_FEATURE_MODE_CFG_FLYING_MODE__SHIFT	0
+static inline uint32_t DPU_RDMA_RDMA_FEATURE_MODE_CFG_FLYING_MODE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_FEATURE_MODE_CFG_FLYING_MODE__SHIFT) & DPU_RDMA_RDMA_FEATURE_MODE_CFG_FLYING_MODE__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_SRC_DMA_CFG				0x00005048
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_LINE_NOTCH_ADDR__MASK		0xfff80000
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_LINE_NOTCH_ADDR__SHIFT	19
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_LINE_NOTCH_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_LINE_NOTCH_ADDR__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_LINE_NOTCH_ADDR__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_RESERVED_0__MASK		0x0007c000
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_RESERVED_0__SHIFT		14
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_POOLING_METHOD__MASK		0x00002000
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_POOLING_METHOD__SHIFT		13
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_POOLING_METHOD(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_POOLING_METHOD__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_POOLING_METHOD__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_UNPOOLING_EN__MASK		0x00001000
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_UNPOOLING_EN__SHIFT		12
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_UNPOOLING_EN(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_UNPOOLING_EN__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_UNPOOLING_EN__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_HEIGHT__MASK	0x00000e00
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_HEIGHT__SHIFT	9
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_HEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_HEIGHT__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_HEIGHT__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_WIDTH__MASK	0x000001c0
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_WIDTH__SHIFT	6
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_WIDTH(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_WIDTH__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_STRIDE_WIDTH__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_HEIGHT__MASK		0x00000038
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_HEIGHT__SHIFT		3
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_HEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_HEIGHT__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_HEIGHT__MASK;
+}
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_WIDTH__MASK		0x00000007
+#define DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_WIDTH__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_WIDTH(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_WIDTH__SHIFT) & DPU_RDMA_RDMA_SRC_DMA_CFG_KERNEL_WIDTH__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_SURF_NOTCH				0x0000504c
+#define DPU_RDMA_RDMA_SURF_NOTCH_SURF_NOTCH_ADDR__MASK		0xfffffff0
+#define DPU_RDMA_RDMA_SURF_NOTCH_SURF_NOTCH_ADDR__SHIFT		4
+static inline uint32_t DPU_RDMA_RDMA_SURF_NOTCH_SURF_NOTCH_ADDR(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SURF_NOTCH_SURF_NOTCH_ADDR__SHIFT) & DPU_RDMA_RDMA_SURF_NOTCH_SURF_NOTCH_ADDR__MASK;
+}
+#define DPU_RDMA_RDMA_SURF_NOTCH_RESERVED_0__MASK		0x0000000f
+#define DPU_RDMA_RDMA_SURF_NOTCH_RESERVED_0__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_SURF_NOTCH_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_SURF_NOTCH_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_SURF_NOTCH_RESERVED_0__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_PAD_CFG				0x00005064
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_VALUE__MASK			0xffff0000
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_VALUE__SHIFT			16
+static inline uint32_t DPU_RDMA_RDMA_PAD_CFG_PAD_VALUE(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_PAD_CFG_PAD_VALUE__SHIFT) & DPU_RDMA_RDMA_PAD_CFG_PAD_VALUE__MASK;
+}
+#define DPU_RDMA_RDMA_PAD_CFG_RESERVED_0__MASK			0x0000ff80
+#define DPU_RDMA_RDMA_PAD_CFG_RESERVED_0__SHIFT			7
+static inline uint32_t DPU_RDMA_RDMA_PAD_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_PAD_CFG_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_PAD_CFG_RESERVED_0__MASK;
+}
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_TOP__MASK			0x00000070
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_TOP__SHIFT			4
+static inline uint32_t DPU_RDMA_RDMA_PAD_CFG_PAD_TOP(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_PAD_CFG_PAD_TOP__SHIFT) & DPU_RDMA_RDMA_PAD_CFG_PAD_TOP__MASK;
+}
+#define DPU_RDMA_RDMA_PAD_CFG_RESERVED_1__MASK			0x00000008
+#define DPU_RDMA_RDMA_PAD_CFG_RESERVED_1__SHIFT			3
+static inline uint32_t DPU_RDMA_RDMA_PAD_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_PAD_CFG_RESERVED_1__SHIFT) & DPU_RDMA_RDMA_PAD_CFG_RESERVED_1__MASK;
+}
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_LEFT__MASK			0x00000007
+#define DPU_RDMA_RDMA_PAD_CFG_PAD_LEFT__SHIFT			0
+static inline uint32_t DPU_RDMA_RDMA_PAD_CFG_PAD_LEFT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_PAD_CFG_PAD_LEFT__SHIFT) & DPU_RDMA_RDMA_PAD_CFG_PAD_LEFT__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_WEIGHT				0x00005068
+#define DPU_RDMA_RDMA_WEIGHT_E_WEIGHT__MASK			0xff000000
+#define DPU_RDMA_RDMA_WEIGHT_E_WEIGHT__SHIFT			24
+static inline uint32_t DPU_RDMA_RDMA_WEIGHT_E_WEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_WEIGHT_E_WEIGHT__SHIFT) & DPU_RDMA_RDMA_WEIGHT_E_WEIGHT__MASK;
+}
+#define DPU_RDMA_RDMA_WEIGHT_N_WEIGHT__MASK			0x00ff0000
+#define DPU_RDMA_RDMA_WEIGHT_N_WEIGHT__SHIFT			16
+static inline uint32_t DPU_RDMA_RDMA_WEIGHT_N_WEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_WEIGHT_N_WEIGHT__SHIFT) & DPU_RDMA_RDMA_WEIGHT_N_WEIGHT__MASK;
+}
+#define DPU_RDMA_RDMA_WEIGHT_B_WEIGHT__MASK			0x0000ff00
+#define DPU_RDMA_RDMA_WEIGHT_B_WEIGHT__SHIFT			8
+static inline uint32_t DPU_RDMA_RDMA_WEIGHT_B_WEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_WEIGHT_B_WEIGHT__SHIFT) & DPU_RDMA_RDMA_WEIGHT_B_WEIGHT__MASK;
+}
+#define DPU_RDMA_RDMA_WEIGHT_M_WEIGHT__MASK			0x000000ff
+#define DPU_RDMA_RDMA_WEIGHT_M_WEIGHT__SHIFT			0
+static inline uint32_t DPU_RDMA_RDMA_WEIGHT_M_WEIGHT(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_WEIGHT_M_WEIGHT__SHIFT) & DPU_RDMA_RDMA_WEIGHT_M_WEIGHT__MASK;
+}
+
+#define REG_DPU_RDMA_RDMA_EW_SURF_NOTCH				0x0000506c
+#define DPU_RDMA_RDMA_EW_SURF_NOTCH_EW_SURF_NOTCH__MASK		0xfffffff0
+#define DPU_RDMA_RDMA_EW_SURF_NOTCH_EW_SURF_NOTCH__SHIFT	4
+static inline uint32_t DPU_RDMA_RDMA_EW_SURF_NOTCH_EW_SURF_NOTCH(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_EW_SURF_NOTCH_EW_SURF_NOTCH__SHIFT) & DPU_RDMA_RDMA_EW_SURF_NOTCH_EW_SURF_NOTCH__MASK;
+}
+#define DPU_RDMA_RDMA_EW_SURF_NOTCH_RESERVED_0__MASK		0x0000000f
+#define DPU_RDMA_RDMA_EW_SURF_NOTCH_RESERVED_0__SHIFT		0
+static inline uint32_t DPU_RDMA_RDMA_EW_SURF_NOTCH_RESERVED_0(uint32_t val)
+{
+	return ((val) << DPU_RDMA_RDMA_EW_SURF_NOTCH_RESERVED_0__SHIFT) & DPU_RDMA_RDMA_EW_SURF_NOTCH_RESERVED_0__MASK;
+}
+
+#define REG_PPU_S_STATUS					0x00006000
+#define PPU_S_STATUS_RESERVED_0__MASK				0xfffc0000
+#define PPU_S_STATUS_RESERVED_0__SHIFT				18
+static inline uint32_t PPU_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_S_STATUS_RESERVED_0__SHIFT) & PPU_S_STATUS_RESERVED_0__MASK;
+}
+#define PPU_S_STATUS_STATUS_1__MASK				0x00030000
+#define PPU_S_STATUS_STATUS_1__SHIFT				16
+static inline uint32_t PPU_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << PPU_S_STATUS_STATUS_1__SHIFT) & PPU_S_STATUS_STATUS_1__MASK;
+}
+#define PPU_S_STATUS_RESERVED_1__MASK				0x0000fffc
+#define PPU_S_STATUS_RESERVED_1__SHIFT				2
+static inline uint32_t PPU_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_S_STATUS_RESERVED_1__SHIFT) & PPU_S_STATUS_RESERVED_1__MASK;
+}
+#define PPU_S_STATUS_STATUS_0__MASK				0x00000003
+#define PPU_S_STATUS_STATUS_0__SHIFT				0
+static inline uint32_t PPU_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << PPU_S_STATUS_STATUS_0__SHIFT) & PPU_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_PPU_S_POINTER					0x00006004
+#define PPU_S_POINTER_RESERVED_0__MASK				0xfffe0000
+#define PPU_S_POINTER_RESERVED_0__SHIFT				17
+static inline uint32_t PPU_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_RESERVED_0__SHIFT) & PPU_S_POINTER_RESERVED_0__MASK;
+}
+#define PPU_S_POINTER_EXECUTER__MASK				0x00010000
+#define PPU_S_POINTER_EXECUTER__SHIFT				16
+static inline uint32_t PPU_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_EXECUTER__SHIFT) & PPU_S_POINTER_EXECUTER__MASK;
+}
+#define PPU_S_POINTER_RESERVED_1__MASK				0x0000ffc0
+#define PPU_S_POINTER_RESERVED_1__SHIFT				6
+static inline uint32_t PPU_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_RESERVED_1__SHIFT) & PPU_S_POINTER_RESERVED_1__MASK;
+}
+#define PPU_S_POINTER_EXECUTER_PP_CLEAR__MASK			0x00000020
+#define PPU_S_POINTER_EXECUTER_PP_CLEAR__SHIFT			5
+static inline uint32_t PPU_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & PPU_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define PPU_S_POINTER_POINTER_PP_CLEAR__MASK			0x00000010
+#define PPU_S_POINTER_POINTER_PP_CLEAR__SHIFT			4
+static inline uint32_t PPU_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_POINTER_PP_CLEAR__SHIFT) & PPU_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define PPU_S_POINTER_POINTER_PP_MODE__MASK			0x00000008
+#define PPU_S_POINTER_POINTER_PP_MODE__SHIFT			3
+static inline uint32_t PPU_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_POINTER_PP_MODE__SHIFT) & PPU_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define PPU_S_POINTER_EXECUTER_PP_EN__MASK			0x00000004
+#define PPU_S_POINTER_EXECUTER_PP_EN__SHIFT			2
+static inline uint32_t PPU_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_EXECUTER_PP_EN__SHIFT) & PPU_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define PPU_S_POINTER_POINTER_PP_EN__MASK			0x00000002
+#define PPU_S_POINTER_POINTER_PP_EN__SHIFT			1
+static inline uint32_t PPU_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_POINTER_PP_EN__SHIFT) & PPU_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define PPU_S_POINTER_POINTER__MASK				0x00000001
+#define PPU_S_POINTER_POINTER__SHIFT				0
+static inline uint32_t PPU_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << PPU_S_POINTER_POINTER__SHIFT) & PPU_S_POINTER_POINTER__MASK;
+}
+
+#define REG_PPU_OPERATION_ENABLE				0x00006008
+#define PPU_OPERATION_ENABLE_RESERVED_0__MASK			0xfffffffe
+#define PPU_OPERATION_ENABLE_RESERVED_0__SHIFT			1
+static inline uint32_t PPU_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_ENABLE_RESERVED_0__SHIFT) & PPU_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define PPU_OPERATION_ENABLE_OP_EN__MASK			0x00000001
+#define PPU_OPERATION_ENABLE_OP_EN__SHIFT			0
+static inline uint32_t PPU_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_ENABLE_OP_EN__SHIFT) & PPU_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_IN_WIDTH				0x0000600c
+#define PPU_DATA_CUBE_IN_WIDTH_RESERVED_0__MASK			0xffffe000
+#define PPU_DATA_CUBE_IN_WIDTH_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_IN_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_WIDTH_RESERVED_0__SHIFT) & PPU_DATA_CUBE_IN_WIDTH_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__MASK		0x00001fff
+#define PPU_DATA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__SHIFT		0
+static inline uint32_t PPU_DATA_CUBE_IN_WIDTH_CUBE_IN_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__SHIFT) & PPU_DATA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_IN_HEIGHT				0x00006010
+#define PPU_DATA_CUBE_IN_HEIGHT_RESERVED_0__MASK		0xffffe000
+#define PPU_DATA_CUBE_IN_HEIGHT_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_IN_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_HEIGHT_RESERVED_0__SHIFT) & PPU_DATA_CUBE_IN_HEIGHT_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__MASK		0x00001fff
+#define PPU_DATA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__SHIFT		0
+static inline uint32_t PPU_DATA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__SHIFT) & PPU_DATA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_IN_CHANNEL				0x00006014
+#define PPU_DATA_CUBE_IN_CHANNEL_RESERVED_0__MASK		0xffffe000
+#define PPU_DATA_CUBE_IN_CHANNEL_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_IN_CHANNEL_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_CHANNEL_RESERVED_0__SHIFT) & PPU_DATA_CUBE_IN_CHANNEL_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__MASK		0x00001fff
+#define PPU_DATA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__SHIFT		0
+static inline uint32_t PPU_DATA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__SHIFT) & PPU_DATA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_OUT_WIDTH				0x00006018
+#define PPU_DATA_CUBE_OUT_WIDTH_RESERVED_0__MASK		0xffffe000
+#define PPU_DATA_CUBE_OUT_WIDTH_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_OUT_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_WIDTH_RESERVED_0__SHIFT) & PPU_DATA_CUBE_OUT_WIDTH_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_OUT_WIDTH_CUBE_OUT_WIDTH__MASK		0x00001fff
+#define PPU_DATA_CUBE_OUT_WIDTH_CUBE_OUT_WIDTH__SHIFT		0
+static inline uint32_t PPU_DATA_CUBE_OUT_WIDTH_CUBE_OUT_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_WIDTH_CUBE_OUT_WIDTH__SHIFT) & PPU_DATA_CUBE_OUT_WIDTH_CUBE_OUT_WIDTH__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_OUT_HEIGHT				0x0000601c
+#define PPU_DATA_CUBE_OUT_HEIGHT_RESERVED_0__MASK		0xffffe000
+#define PPU_DATA_CUBE_OUT_HEIGHT_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_OUT_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_HEIGHT_RESERVED_0__SHIFT) & PPU_DATA_CUBE_OUT_HEIGHT_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_OUT_HEIGHT_CUBE_OUT_HEIGHT__MASK		0x00001fff
+#define PPU_DATA_CUBE_OUT_HEIGHT_CUBE_OUT_HEIGHT__SHIFT		0
+static inline uint32_t PPU_DATA_CUBE_OUT_HEIGHT_CUBE_OUT_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_HEIGHT_CUBE_OUT_HEIGHT__SHIFT) & PPU_DATA_CUBE_OUT_HEIGHT_CUBE_OUT_HEIGHT__MASK;
+}
+
+#define REG_PPU_DATA_CUBE_OUT_CHANNEL				0x00006020
+#define PPU_DATA_CUBE_OUT_CHANNEL_RESERVED_0__MASK		0xffffe000
+#define PPU_DATA_CUBE_OUT_CHANNEL_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_DATA_CUBE_OUT_CHANNEL_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_CHANNEL_RESERVED_0__SHIFT) & PPU_DATA_CUBE_OUT_CHANNEL_RESERVED_0__MASK;
+}
+#define PPU_DATA_CUBE_OUT_CHANNEL_CUBE_OUT_CHANNEL__MASK	0x00001fff
+#define PPU_DATA_CUBE_OUT_CHANNEL_CUBE_OUT_CHANNEL__SHIFT	0
+static inline uint32_t PPU_DATA_CUBE_OUT_CHANNEL_CUBE_OUT_CHANNEL(uint32_t val)
+{
+	return ((val) << PPU_DATA_CUBE_OUT_CHANNEL_CUBE_OUT_CHANNEL__SHIFT) & PPU_DATA_CUBE_OUT_CHANNEL_CUBE_OUT_CHANNEL__MASK;
+}
+
+#define REG_PPU_OPERATION_MODE_CFG				0x00006024
+#define PPU_OPERATION_MODE_CFG_RESERVED_0__MASK			0x80000000
+#define PPU_OPERATION_MODE_CFG_RESERVED_0__SHIFT		31
+static inline uint32_t PPU_OPERATION_MODE_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_RESERVED_0__SHIFT) & PPU_OPERATION_MODE_CFG_RESERVED_0__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_INDEX_EN__MASK			0x40000000
+#define PPU_OPERATION_MODE_CFG_INDEX_EN__SHIFT			30
+static inline uint32_t PPU_OPERATION_MODE_CFG_INDEX_EN(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_INDEX_EN__SHIFT) & PPU_OPERATION_MODE_CFG_INDEX_EN__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_RESERVED_1__MASK			0x20000000
+#define PPU_OPERATION_MODE_CFG_RESERVED_1__SHIFT		29
+static inline uint32_t PPU_OPERATION_MODE_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_RESERVED_1__SHIFT) & PPU_OPERATION_MODE_CFG_RESERVED_1__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_NOTCH_ADDR__MASK			0x1fff0000
+#define PPU_OPERATION_MODE_CFG_NOTCH_ADDR__SHIFT		16
+static inline uint32_t PPU_OPERATION_MODE_CFG_NOTCH_ADDR(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_NOTCH_ADDR__SHIFT) & PPU_OPERATION_MODE_CFG_NOTCH_ADDR__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_RESERVED_2__MASK			0x0000ff00
+#define PPU_OPERATION_MODE_CFG_RESERVED_2__SHIFT		8
+static inline uint32_t PPU_OPERATION_MODE_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_RESERVED_2__SHIFT) & PPU_OPERATION_MODE_CFG_RESERVED_2__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_USE_CNT__MASK			0x000000e0
+#define PPU_OPERATION_MODE_CFG_USE_CNT__SHIFT			5
+static inline uint32_t PPU_OPERATION_MODE_CFG_USE_CNT(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_USE_CNT__SHIFT) & PPU_OPERATION_MODE_CFG_USE_CNT__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_FLYING_MODE__MASK		0x00000010
+#define PPU_OPERATION_MODE_CFG_FLYING_MODE__SHIFT		4
+static inline uint32_t PPU_OPERATION_MODE_CFG_FLYING_MODE(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_FLYING_MODE__SHIFT) & PPU_OPERATION_MODE_CFG_FLYING_MODE__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_RESERVED_3__MASK			0x0000000c
+#define PPU_OPERATION_MODE_CFG_RESERVED_3__SHIFT		2
+static inline uint32_t PPU_OPERATION_MODE_CFG_RESERVED_3(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_RESERVED_3__SHIFT) & PPU_OPERATION_MODE_CFG_RESERVED_3__MASK;
+}
+#define PPU_OPERATION_MODE_CFG_POOLING_METHOD__MASK		0x00000003
+#define PPU_OPERATION_MODE_CFG_POOLING_METHOD__SHIFT		0
+static inline uint32_t PPU_OPERATION_MODE_CFG_POOLING_METHOD(uint32_t val)
+{
+	return ((val) << PPU_OPERATION_MODE_CFG_POOLING_METHOD__SHIFT) & PPU_OPERATION_MODE_CFG_POOLING_METHOD__MASK;
+}
+
+#define REG_PPU_POOLING_KERNEL_CFG				0x00006034
+#define PPU_POOLING_KERNEL_CFG_RESERVED_0__MASK			0xff000000
+#define PPU_POOLING_KERNEL_CFG_RESERVED_0__SHIFT		24
+static inline uint32_t PPU_POOLING_KERNEL_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_RESERVED_0__SHIFT) & PPU_POOLING_KERNEL_CFG_RESERVED_0__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_HEIGHT__MASK	0x00f00000
+#define PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_HEIGHT__SHIFT	20
+static inline uint32_t PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_HEIGHT__SHIFT) & PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_HEIGHT__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_WIDTH__MASK	0x000f0000
+#define PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_WIDTH__SHIFT	16
+static inline uint32_t PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_WIDTH__SHIFT) & PPU_POOLING_KERNEL_CFG_KERNEL_STRIDE_WIDTH__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_RESERVED_1__MASK			0x0000f000
+#define PPU_POOLING_KERNEL_CFG_RESERVED_1__SHIFT		12
+static inline uint32_t PPU_POOLING_KERNEL_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_RESERVED_1__SHIFT) & PPU_POOLING_KERNEL_CFG_RESERVED_1__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_KERNEL_HEIGHT__MASK		0x00000f00
+#define PPU_POOLING_KERNEL_CFG_KERNEL_HEIGHT__SHIFT		8
+static inline uint32_t PPU_POOLING_KERNEL_CFG_KERNEL_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_KERNEL_HEIGHT__SHIFT) & PPU_POOLING_KERNEL_CFG_KERNEL_HEIGHT__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_RESERVED_2__MASK			0x000000f0
+#define PPU_POOLING_KERNEL_CFG_RESERVED_2__SHIFT		4
+static inline uint32_t PPU_POOLING_KERNEL_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_RESERVED_2__SHIFT) & PPU_POOLING_KERNEL_CFG_RESERVED_2__MASK;
+}
+#define PPU_POOLING_KERNEL_CFG_KERNEL_WIDTH__MASK		0x0000000f
+#define PPU_POOLING_KERNEL_CFG_KERNEL_WIDTH__SHIFT		0
+static inline uint32_t PPU_POOLING_KERNEL_CFG_KERNEL_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_POOLING_KERNEL_CFG_KERNEL_WIDTH__SHIFT) & PPU_POOLING_KERNEL_CFG_KERNEL_WIDTH__MASK;
+}
+
+#define REG_PPU_RECIP_KERNEL_WIDTH				0x00006038
+#define PPU_RECIP_KERNEL_WIDTH_RESERVED_0__MASK			0xfffe0000
+#define PPU_RECIP_KERNEL_WIDTH_RESERVED_0__SHIFT		17
+static inline uint32_t PPU_RECIP_KERNEL_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RECIP_KERNEL_WIDTH_RESERVED_0__SHIFT) & PPU_RECIP_KERNEL_WIDTH_RESERVED_0__MASK;
+}
+#define PPU_RECIP_KERNEL_WIDTH_RECIP_KERNEL_WIDTH__MASK		0x0001ffff
+#define PPU_RECIP_KERNEL_WIDTH_RECIP_KERNEL_WIDTH__SHIFT	0
+static inline uint32_t PPU_RECIP_KERNEL_WIDTH_RECIP_KERNEL_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_RECIP_KERNEL_WIDTH_RECIP_KERNEL_WIDTH__SHIFT) & PPU_RECIP_KERNEL_WIDTH_RECIP_KERNEL_WIDTH__MASK;
+}
+
+#define REG_PPU_RECIP_KERNEL_HEIGHT				0x0000603c
+#define PPU_RECIP_KERNEL_HEIGHT_RESERVED_0__MASK		0xfffe0000
+#define PPU_RECIP_KERNEL_HEIGHT_RESERVED_0__SHIFT		17
+static inline uint32_t PPU_RECIP_KERNEL_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RECIP_KERNEL_HEIGHT_RESERVED_0__SHIFT) & PPU_RECIP_KERNEL_HEIGHT_RESERVED_0__MASK;
+}
+#define PPU_RECIP_KERNEL_HEIGHT_RECIP_KERNEL_HEIGHT__MASK	0x0001ffff
+#define PPU_RECIP_KERNEL_HEIGHT_RECIP_KERNEL_HEIGHT__SHIFT	0
+static inline uint32_t PPU_RECIP_KERNEL_HEIGHT_RECIP_KERNEL_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_RECIP_KERNEL_HEIGHT_RECIP_KERNEL_HEIGHT__SHIFT) & PPU_RECIP_KERNEL_HEIGHT_RECIP_KERNEL_HEIGHT__MASK;
+}
+
+#define REG_PPU_POOLING_PADDING_CFG				0x00006040
+#define PPU_POOLING_PADDING_CFG_RESERVED_0__MASK		0xffff8000
+#define PPU_POOLING_PADDING_CFG_RESERVED_0__SHIFT		15
+static inline uint32_t PPU_POOLING_PADDING_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_RESERVED_0__SHIFT) & PPU_POOLING_PADDING_CFG_RESERVED_0__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_PAD_BOTTOM__MASK		0x00007000
+#define PPU_POOLING_PADDING_CFG_PAD_BOTTOM__SHIFT		12
+static inline uint32_t PPU_POOLING_PADDING_CFG_PAD_BOTTOM(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_PAD_BOTTOM__SHIFT) & PPU_POOLING_PADDING_CFG_PAD_BOTTOM__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_RESERVED_1__MASK		0x00000800
+#define PPU_POOLING_PADDING_CFG_RESERVED_1__SHIFT		11
+static inline uint32_t PPU_POOLING_PADDING_CFG_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_RESERVED_1__SHIFT) & PPU_POOLING_PADDING_CFG_RESERVED_1__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_PAD_RIGHT__MASK			0x00000700
+#define PPU_POOLING_PADDING_CFG_PAD_RIGHT__SHIFT		8
+static inline uint32_t PPU_POOLING_PADDING_CFG_PAD_RIGHT(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_PAD_RIGHT__SHIFT) & PPU_POOLING_PADDING_CFG_PAD_RIGHT__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_RESERVED_2__MASK		0x00000080
+#define PPU_POOLING_PADDING_CFG_RESERVED_2__SHIFT		7
+static inline uint32_t PPU_POOLING_PADDING_CFG_RESERVED_2(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_RESERVED_2__SHIFT) & PPU_POOLING_PADDING_CFG_RESERVED_2__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_PAD_TOP__MASK			0x00000070
+#define PPU_POOLING_PADDING_CFG_PAD_TOP__SHIFT			4
+static inline uint32_t PPU_POOLING_PADDING_CFG_PAD_TOP(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_PAD_TOP__SHIFT) & PPU_POOLING_PADDING_CFG_PAD_TOP__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_RESERVED_3__MASK		0x00000008
+#define PPU_POOLING_PADDING_CFG_RESERVED_3__SHIFT		3
+static inline uint32_t PPU_POOLING_PADDING_CFG_RESERVED_3(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_RESERVED_3__SHIFT) & PPU_POOLING_PADDING_CFG_RESERVED_3__MASK;
+}
+#define PPU_POOLING_PADDING_CFG_PAD_LEFT__MASK			0x00000007
+#define PPU_POOLING_PADDING_CFG_PAD_LEFT__SHIFT			0
+static inline uint32_t PPU_POOLING_PADDING_CFG_PAD_LEFT(uint32_t val)
+{
+	return ((val) << PPU_POOLING_PADDING_CFG_PAD_LEFT__SHIFT) & PPU_POOLING_PADDING_CFG_PAD_LEFT__MASK;
+}
+
+#define REG_PPU_PADDING_VALUE_1_CFG				0x00006044
+#define PPU_PADDING_VALUE_1_CFG_PAD_VALUE_0__MASK		0xffffffff
+#define PPU_PADDING_VALUE_1_CFG_PAD_VALUE_0__SHIFT		0
+static inline uint32_t PPU_PADDING_VALUE_1_CFG_PAD_VALUE_0(uint32_t val)
+{
+	return ((val) << PPU_PADDING_VALUE_1_CFG_PAD_VALUE_0__SHIFT) & PPU_PADDING_VALUE_1_CFG_PAD_VALUE_0__MASK;
+}
+
+#define REG_PPU_PADDING_VALUE_2_CFG				0x00006048
+#define PPU_PADDING_VALUE_2_CFG_RESERVED_0__MASK		0xfffffff8
+#define PPU_PADDING_VALUE_2_CFG_RESERVED_0__SHIFT		3
+static inline uint32_t PPU_PADDING_VALUE_2_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_PADDING_VALUE_2_CFG_RESERVED_0__SHIFT) & PPU_PADDING_VALUE_2_CFG_RESERVED_0__MASK;
+}
+#define PPU_PADDING_VALUE_2_CFG_PAD_VALUE_1__MASK		0x00000007
+#define PPU_PADDING_VALUE_2_CFG_PAD_VALUE_1__SHIFT		0
+static inline uint32_t PPU_PADDING_VALUE_2_CFG_PAD_VALUE_1(uint32_t val)
+{
+	return ((val) << PPU_PADDING_VALUE_2_CFG_PAD_VALUE_1__SHIFT) & PPU_PADDING_VALUE_2_CFG_PAD_VALUE_1__MASK;
+}
+
+#define REG_PPU_DST_BASE_ADDR					0x00006070
+#define PPU_DST_BASE_ADDR_DST_BASE_ADDR__MASK			0xfffffff0
+#define PPU_DST_BASE_ADDR_DST_BASE_ADDR__SHIFT			4
+static inline uint32_t PPU_DST_BASE_ADDR_DST_BASE_ADDR(uint32_t val)
+{
+	return ((val) << PPU_DST_BASE_ADDR_DST_BASE_ADDR__SHIFT) & PPU_DST_BASE_ADDR_DST_BASE_ADDR__MASK;
+}
+#define PPU_DST_BASE_ADDR_RESERVED_0__MASK			0x0000000f
+#define PPU_DST_BASE_ADDR_RESERVED_0__SHIFT			0
+static inline uint32_t PPU_DST_BASE_ADDR_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DST_BASE_ADDR_RESERVED_0__SHIFT) & PPU_DST_BASE_ADDR_RESERVED_0__MASK;
+}
+
+#define REG_PPU_DST_SURF_STRIDE					0x0000607c
+#define PPU_DST_SURF_STRIDE_DST_SURF_STRIDE__MASK		0xfffffff0
+#define PPU_DST_SURF_STRIDE_DST_SURF_STRIDE__SHIFT		4
+static inline uint32_t PPU_DST_SURF_STRIDE_DST_SURF_STRIDE(uint32_t val)
+{
+	return ((val) << PPU_DST_SURF_STRIDE_DST_SURF_STRIDE__SHIFT) & PPU_DST_SURF_STRIDE_DST_SURF_STRIDE__MASK;
+}
+#define PPU_DST_SURF_STRIDE_RESERVED_0__MASK			0x0000000f
+#define PPU_DST_SURF_STRIDE_RESERVED_0__SHIFT			0
+static inline uint32_t PPU_DST_SURF_STRIDE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_DST_SURF_STRIDE_RESERVED_0__SHIFT) & PPU_DST_SURF_STRIDE_RESERVED_0__MASK;
+}
+
+#define REG_PPU_DATA_FORMAT					0x00006084
+#define PPU_DATA_FORMAT_INDEX_ADD__MASK				0xfffffff0
+#define PPU_DATA_FORMAT_INDEX_ADD__SHIFT			4
+static inline uint32_t PPU_DATA_FORMAT_INDEX_ADD(uint32_t val)
+{
+	return ((val) << PPU_DATA_FORMAT_INDEX_ADD__SHIFT) & PPU_DATA_FORMAT_INDEX_ADD__MASK;
+}
+#define PPU_DATA_FORMAT_DPU_FLYIN__MASK				0x00000008
+#define PPU_DATA_FORMAT_DPU_FLYIN__SHIFT			3
+static inline uint32_t PPU_DATA_FORMAT_DPU_FLYIN(uint32_t val)
+{
+	return ((val) << PPU_DATA_FORMAT_DPU_FLYIN__SHIFT) & PPU_DATA_FORMAT_DPU_FLYIN__MASK;
+}
+#define PPU_DATA_FORMAT_PROC_PRECISION__MASK			0x00000007
+#define PPU_DATA_FORMAT_PROC_PRECISION__SHIFT			0
+static inline uint32_t PPU_DATA_FORMAT_PROC_PRECISION(uint32_t val)
+{
+	return ((val) << PPU_DATA_FORMAT_PROC_PRECISION__SHIFT) & PPU_DATA_FORMAT_PROC_PRECISION__MASK;
+}
+
+#define REG_PPU_MISC_CTRL					0x000060dc
+#define PPU_MISC_CTRL_SURF_LEN__MASK				0xffff0000
+#define PPU_MISC_CTRL_SURF_LEN__SHIFT				16
+static inline uint32_t PPU_MISC_CTRL_SURF_LEN(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_SURF_LEN__SHIFT) & PPU_MISC_CTRL_SURF_LEN__MASK;
+}
+#define PPU_MISC_CTRL_RESERVED_0__MASK				0x0000fe00
+#define PPU_MISC_CTRL_RESERVED_0__SHIFT				9
+static inline uint32_t PPU_MISC_CTRL_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_RESERVED_0__SHIFT) & PPU_MISC_CTRL_RESERVED_0__MASK;
+}
+#define PPU_MISC_CTRL_MC_SURF_OUT__MASK				0x00000100
+#define PPU_MISC_CTRL_MC_SURF_OUT__SHIFT			8
+static inline uint32_t PPU_MISC_CTRL_MC_SURF_OUT(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_MC_SURF_OUT__SHIFT) & PPU_MISC_CTRL_MC_SURF_OUT__MASK;
+}
+#define PPU_MISC_CTRL_NONALIGN__MASK				0x00000080
+#define PPU_MISC_CTRL_NONALIGN__SHIFT				7
+static inline uint32_t PPU_MISC_CTRL_NONALIGN(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_NONALIGN__SHIFT) & PPU_MISC_CTRL_NONALIGN__MASK;
+}
+#define PPU_MISC_CTRL_RESERVED_1__MASK				0x00000070
+#define PPU_MISC_CTRL_RESERVED_1__SHIFT				4
+static inline uint32_t PPU_MISC_CTRL_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_RESERVED_1__SHIFT) & PPU_MISC_CTRL_RESERVED_1__MASK;
+}
+#define PPU_MISC_CTRL_BURST_LEN__MASK				0x0000000f
+#define PPU_MISC_CTRL_BURST_LEN__SHIFT				0
+static inline uint32_t PPU_MISC_CTRL_BURST_LEN(uint32_t val)
+{
+	return ((val) << PPU_MISC_CTRL_BURST_LEN__SHIFT) & PPU_MISC_CTRL_BURST_LEN__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_S_STATUS				0x00007000
+#define PPU_RDMA_RDMA_S_STATUS_RESERVED_0__MASK			0xfffc0000
+#define PPU_RDMA_RDMA_S_STATUS_RESERVED_0__SHIFT		18
+static inline uint32_t PPU_RDMA_RDMA_S_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_STATUS_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_S_STATUS_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_S_STATUS_STATUS_1__MASK			0x00030000
+#define PPU_RDMA_RDMA_S_STATUS_STATUS_1__SHIFT			16
+static inline uint32_t PPU_RDMA_RDMA_S_STATUS_STATUS_1(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_STATUS_STATUS_1__SHIFT) & PPU_RDMA_RDMA_S_STATUS_STATUS_1__MASK;
+}
+#define PPU_RDMA_RDMA_S_STATUS_RESERVED_1__MASK			0x0000fffc
+#define PPU_RDMA_RDMA_S_STATUS_RESERVED_1__SHIFT		2
+static inline uint32_t PPU_RDMA_RDMA_S_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_STATUS_RESERVED_1__SHIFT) & PPU_RDMA_RDMA_S_STATUS_RESERVED_1__MASK;
+}
+#define PPU_RDMA_RDMA_S_STATUS_STATUS_0__MASK			0x00000003
+#define PPU_RDMA_RDMA_S_STATUS_STATUS_0__SHIFT			0
+static inline uint32_t PPU_RDMA_RDMA_S_STATUS_STATUS_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_STATUS_STATUS_0__SHIFT) & PPU_RDMA_RDMA_S_STATUS_STATUS_0__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_S_POINTER				0x00007004
+#define PPU_RDMA_RDMA_S_POINTER_RESERVED_0__MASK		0xfffe0000
+#define PPU_RDMA_RDMA_S_POINTER_RESERVED_0__SHIFT		17
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_S_POINTER_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER__MASK			0x00010000
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER__SHIFT			16
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_EXECUTER(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_EXECUTER__SHIFT) & PPU_RDMA_RDMA_S_POINTER_EXECUTER__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_RESERVED_1__MASK		0x0000ffc0
+#define PPU_RDMA_RDMA_S_POINTER_RESERVED_1__SHIFT		6
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_RESERVED_1(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_RESERVED_1__SHIFT) & PPU_RDMA_RDMA_S_POINTER_RESERVED_1__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__MASK		0x00000020
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT	5
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__SHIFT) & PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_CLEAR__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__MASK		0x00000010
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__SHIFT		4
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__SHIFT) & PPU_RDMA_RDMA_S_POINTER_POINTER_PP_CLEAR__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__MASK		0x00000008
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__SHIFT		3
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__SHIFT) & PPU_RDMA_RDMA_S_POINTER_POINTER_PP_MODE__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__MASK		0x00000004
+#define PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__SHIFT		2
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__SHIFT) & PPU_RDMA_RDMA_S_POINTER_EXECUTER_PP_EN__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__MASK		0x00000002
+#define PPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__SHIFT		1
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__SHIFT) & PPU_RDMA_RDMA_S_POINTER_POINTER_PP_EN__MASK;
+}
+#define PPU_RDMA_RDMA_S_POINTER_POINTER__MASK			0x00000001
+#define PPU_RDMA_RDMA_S_POINTER_POINTER__SHIFT			0
+static inline uint32_t PPU_RDMA_RDMA_S_POINTER_POINTER(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_S_POINTER_POINTER__SHIFT) & PPU_RDMA_RDMA_S_POINTER_POINTER__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_OPERATION_ENABLE			0x00007008
+#define PPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__MASK		0xfffffffe
+#define PPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__SHIFT	1
+static inline uint32_t PPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__MASK		0x00000001
+#define PPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__SHIFT		0
+static inline uint32_t PPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__SHIFT) & PPU_RDMA_RDMA_OPERATION_ENABLE_OP_EN__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_CUBE_IN_WIDTH				0x0000700c
+#define PPU_RDMA_RDMA_CUBE_IN_WIDTH_RESERVED_0__MASK		0xffffe000
+#define PPU_RDMA_RDMA_CUBE_IN_WIDTH_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_WIDTH_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_WIDTH_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_WIDTH_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__MASK		0x00001fff
+#define PPU_RDMA_RDMA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__SHIFT	0
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_WIDTH_CUBE_IN_WIDTH(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_WIDTH_CUBE_IN_WIDTH__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_CUBE_IN_HEIGHT			0x00007010
+#define PPU_RDMA_RDMA_CUBE_IN_HEIGHT_RESERVED_0__MASK		0xffffe000
+#define PPU_RDMA_RDMA_CUBE_IN_HEIGHT_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_HEIGHT_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_HEIGHT_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_HEIGHT_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__MASK	0x00001fff
+#define PPU_RDMA_RDMA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__SHIFT	0
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_HEIGHT_CUBE_IN_HEIGHT__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_CUBE_IN_CHANNEL			0x00007014
+#define PPU_RDMA_RDMA_CUBE_IN_CHANNEL_RESERVED_0__MASK		0xffffe000
+#define PPU_RDMA_RDMA_CUBE_IN_CHANNEL_RESERVED_0__SHIFT		13
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_CHANNEL_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_CHANNEL_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_CHANNEL_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__MASK	0x00001fff
+#define PPU_RDMA_RDMA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__SHIFT	0
+static inline uint32_t PPU_RDMA_RDMA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__SHIFT) & PPU_RDMA_RDMA_CUBE_IN_CHANNEL_CUBE_IN_CHANNEL__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_SRC_BASE_ADDR				0x0000701c
+#define PPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__MASK		0xffffffff
+#define PPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__SHIFT	0
+static inline uint32_t PPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__SHIFT) & PPU_RDMA_RDMA_SRC_BASE_ADDR_SRC_BASE_ADDR__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_SRC_LINE_STRIDE			0x00007024
+#define PPU_RDMA_RDMA_SRC_LINE_STRIDE_SRC_LINE_STRIDE__MASK	0xfffffff0
+#define PPU_RDMA_RDMA_SRC_LINE_STRIDE_SRC_LINE_STRIDE__SHIFT	4
+static inline uint32_t PPU_RDMA_RDMA_SRC_LINE_STRIDE_SRC_LINE_STRIDE(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_SRC_LINE_STRIDE_SRC_LINE_STRIDE__SHIFT) & PPU_RDMA_RDMA_SRC_LINE_STRIDE_SRC_LINE_STRIDE__MASK;
+}
+#define PPU_RDMA_RDMA_SRC_LINE_STRIDE_RESERVED_0__MASK		0x0000000f
+#define PPU_RDMA_RDMA_SRC_LINE_STRIDE_RESERVED_0__SHIFT		0
+static inline uint32_t PPU_RDMA_RDMA_SRC_LINE_STRIDE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_SRC_LINE_STRIDE_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_SRC_LINE_STRIDE_RESERVED_0__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_SRC_SURF_STRIDE			0x00007028
+#define PPU_RDMA_RDMA_SRC_SURF_STRIDE_SRC_SURF_STRIDE__MASK	0xfffffff0
+#define PPU_RDMA_RDMA_SRC_SURF_STRIDE_SRC_SURF_STRIDE__SHIFT	4
+static inline uint32_t PPU_RDMA_RDMA_SRC_SURF_STRIDE_SRC_SURF_STRIDE(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_SRC_SURF_STRIDE_SRC_SURF_STRIDE__SHIFT) & PPU_RDMA_RDMA_SRC_SURF_STRIDE_SRC_SURF_STRIDE__MASK;
+}
+#define PPU_RDMA_RDMA_SRC_SURF_STRIDE_RESERVED_0__MASK		0x0000000f
+#define PPU_RDMA_RDMA_SRC_SURF_STRIDE_RESERVED_0__SHIFT		0
+static inline uint32_t PPU_RDMA_RDMA_SRC_SURF_STRIDE_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_SRC_SURF_STRIDE_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_SRC_SURF_STRIDE_RESERVED_0__MASK;
+}
+
+#define REG_PPU_RDMA_RDMA_DATA_FORMAT				0x00007030
+#define PPU_RDMA_RDMA_DATA_FORMAT_RESERVED_0__MASK		0xfffffffc
+#define PPU_RDMA_RDMA_DATA_FORMAT_RESERVED_0__SHIFT		2
+static inline uint32_t PPU_RDMA_RDMA_DATA_FORMAT_RESERVED_0(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_DATA_FORMAT_RESERVED_0__SHIFT) & PPU_RDMA_RDMA_DATA_FORMAT_RESERVED_0__MASK;
+}
+#define PPU_RDMA_RDMA_DATA_FORMAT_IN_PRECISION__MASK		0x00000003
+#define PPU_RDMA_RDMA_DATA_FORMAT_IN_PRECISION__SHIFT		0
+static inline uint32_t PPU_RDMA_RDMA_DATA_FORMAT_IN_PRECISION(uint32_t val)
+{
+	return ((val) << PPU_RDMA_RDMA_DATA_FORMAT_IN_PRECISION__SHIFT) & PPU_RDMA_RDMA_DATA_FORMAT_IN_PRECISION__MASK;
+}
+
+#define REG_DDMA_CFG_OUTSTANDING				0x00008000
+#define DDMA_CFG_OUTSTANDING_RESERVED_0__MASK			0xffff0000
+#define DDMA_CFG_OUTSTANDING_RESERVED_0__SHIFT			16
+static inline uint32_t DDMA_CFG_OUTSTANDING_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_OUTSTANDING_RESERVED_0__SHIFT) & DDMA_CFG_OUTSTANDING_RESERVED_0__MASK;
+}
+#define DDMA_CFG_OUTSTANDING_WR_OS_CNT__MASK			0x0000ff00
+#define DDMA_CFG_OUTSTANDING_WR_OS_CNT__SHIFT			8
+static inline uint32_t DDMA_CFG_OUTSTANDING_WR_OS_CNT(uint32_t val)
+{
+	return ((val) << DDMA_CFG_OUTSTANDING_WR_OS_CNT__SHIFT) & DDMA_CFG_OUTSTANDING_WR_OS_CNT__MASK;
+}
+#define DDMA_CFG_OUTSTANDING_RD_OS_CNT__MASK			0x000000ff
+#define DDMA_CFG_OUTSTANDING_RD_OS_CNT__SHIFT			0
+static inline uint32_t DDMA_CFG_OUTSTANDING_RD_OS_CNT(uint32_t val)
+{
+	return ((val) << DDMA_CFG_OUTSTANDING_RD_OS_CNT__SHIFT) & DDMA_CFG_OUTSTANDING_RD_OS_CNT__MASK;
+}
+
+#define REG_DDMA_RD_WEIGHT_0					0x00008004
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__MASK			0xff000000
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__SHIFT			24
+static inline uint32_t DDMA_RD_WEIGHT_0_RD_WEIGHT_PDP(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__SHIFT) & DDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__MASK;
+}
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__MASK			0x00ff0000
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__SHIFT			16
+static inline uint32_t DDMA_RD_WEIGHT_0_RD_WEIGHT_DPU(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__SHIFT) & DDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__MASK;
+}
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__MASK			0x0000ff00
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__SHIFT		8
+static inline uint32_t DDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__SHIFT) & DDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__MASK;
+}
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__MASK		0x000000ff
+#define DDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__SHIFT		0
+static inline uint32_t DDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__SHIFT) & DDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__MASK;
+}
+
+#define REG_DDMA_WR_WEIGHT_0					0x00008008
+#define DDMA_WR_WEIGHT_0_RESERVED_0__MASK			0xffff0000
+#define DDMA_WR_WEIGHT_0_RESERVED_0__SHIFT			16
+static inline uint32_t DDMA_WR_WEIGHT_0_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_WR_WEIGHT_0_RESERVED_0__SHIFT) & DDMA_WR_WEIGHT_0_RESERVED_0__MASK;
+}
+#define DDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__MASK			0x0000ff00
+#define DDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__SHIFT			8
+static inline uint32_t DDMA_WR_WEIGHT_0_WR_WEIGHT_PDP(uint32_t val)
+{
+	return ((val) << DDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__SHIFT) & DDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__MASK;
+}
+#define DDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__MASK			0x000000ff
+#define DDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__SHIFT			0
+static inline uint32_t DDMA_WR_WEIGHT_0_WR_WEIGHT_DPU(uint32_t val)
+{
+	return ((val) << DDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__SHIFT) & DDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__MASK;
+}
+
+#define REG_DDMA_CFG_ID_ERROR					0x0000800c
+#define DDMA_CFG_ID_ERROR_RESERVED_0__MASK			0xfffffc00
+#define DDMA_CFG_ID_ERROR_RESERVED_0__SHIFT			10
+static inline uint32_t DDMA_CFG_ID_ERROR_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_ID_ERROR_RESERVED_0__SHIFT) & DDMA_CFG_ID_ERROR_RESERVED_0__MASK;
+}
+#define DDMA_CFG_ID_ERROR_WR_RESP_ID__MASK			0x000003c0
+#define DDMA_CFG_ID_ERROR_WR_RESP_ID__SHIFT			6
+static inline uint32_t DDMA_CFG_ID_ERROR_WR_RESP_ID(uint32_t val)
+{
+	return ((val) << DDMA_CFG_ID_ERROR_WR_RESP_ID__SHIFT) & DDMA_CFG_ID_ERROR_WR_RESP_ID__MASK;
+}
+#define DDMA_CFG_ID_ERROR_RESERVED_1__MASK			0x00000020
+#define DDMA_CFG_ID_ERROR_RESERVED_1__SHIFT			5
+static inline uint32_t DDMA_CFG_ID_ERROR_RESERVED_1(uint32_t val)
+{
+	return ((val) << DDMA_CFG_ID_ERROR_RESERVED_1__SHIFT) & DDMA_CFG_ID_ERROR_RESERVED_1__MASK;
+}
+#define DDMA_CFG_ID_ERROR_RD_RESP_ID__MASK			0x0000001f
+#define DDMA_CFG_ID_ERROR_RD_RESP_ID__SHIFT			0
+static inline uint32_t DDMA_CFG_ID_ERROR_RD_RESP_ID(uint32_t val)
+{
+	return ((val) << DDMA_CFG_ID_ERROR_RD_RESP_ID__SHIFT) & DDMA_CFG_ID_ERROR_RD_RESP_ID__MASK;
+}
+
+#define REG_DDMA_RD_WEIGHT_1					0x00008010
+#define DDMA_RD_WEIGHT_1_RESERVED_0__MASK			0xffffff00
+#define DDMA_RD_WEIGHT_1_RESERVED_0__SHIFT			8
+static inline uint32_t DDMA_RD_WEIGHT_1_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_1_RESERVED_0__SHIFT) & DDMA_RD_WEIGHT_1_RESERVED_0__MASK;
+}
+#define DDMA_RD_WEIGHT_1_RD_WEIGHT_PC__MASK			0x000000ff
+#define DDMA_RD_WEIGHT_1_RD_WEIGHT_PC__SHIFT			0
+static inline uint32_t DDMA_RD_WEIGHT_1_RD_WEIGHT_PC(uint32_t val)
+{
+	return ((val) << DDMA_RD_WEIGHT_1_RD_WEIGHT_PC__SHIFT) & DDMA_RD_WEIGHT_1_RD_WEIGHT_PC__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_FIFO_CLR				0x00008014
+#define DDMA_CFG_DMA_FIFO_CLR_RESERVED_0__MASK			0xfffffffe
+#define DDMA_CFG_DMA_FIFO_CLR_RESERVED_0__SHIFT			1
+static inline uint32_t DDMA_CFG_DMA_FIFO_CLR_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_FIFO_CLR_RESERVED_0__SHIFT) & DDMA_CFG_DMA_FIFO_CLR_RESERVED_0__MASK;
+}
+#define DDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__MASK		0x00000001
+#define DDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__SHIFT		0
+static inline uint32_t DDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__SHIFT) & DDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_ARB					0x00008018
+#define DDMA_CFG_DMA_ARB_RESERVED_0__MASK			0xfffffc00
+#define DDMA_CFG_DMA_ARB_RESERVED_0__SHIFT			10
+static inline uint32_t DDMA_CFG_DMA_ARB_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_RESERVED_0__SHIFT) & DDMA_CFG_DMA_ARB_RESERVED_0__MASK;
+}
+#define DDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__MASK			0x00000200
+#define DDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__SHIFT			9
+static inline uint32_t DDMA_CFG_DMA_ARB_WR_ARBIT_MODEL(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__SHIFT) & DDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__MASK;
+}
+#define DDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__MASK			0x00000100
+#define DDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__SHIFT			8
+static inline uint32_t DDMA_CFG_DMA_ARB_RD_ARBIT_MODEL(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__SHIFT) & DDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__MASK;
+}
+#define DDMA_CFG_DMA_ARB_RESERVED_1__MASK			0x00000080
+#define DDMA_CFG_DMA_ARB_RESERVED_1__SHIFT			7
+static inline uint32_t DDMA_CFG_DMA_ARB_RESERVED_1(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_RESERVED_1__SHIFT) & DDMA_CFG_DMA_ARB_RESERVED_1__MASK;
+}
+#define DDMA_CFG_DMA_ARB_WR_FIX_ARB__MASK			0x00000070
+#define DDMA_CFG_DMA_ARB_WR_FIX_ARB__SHIFT			4
+static inline uint32_t DDMA_CFG_DMA_ARB_WR_FIX_ARB(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_WR_FIX_ARB__SHIFT) & DDMA_CFG_DMA_ARB_WR_FIX_ARB__MASK;
+}
+#define DDMA_CFG_DMA_ARB_RESERVED_2__MASK			0x00000008
+#define DDMA_CFG_DMA_ARB_RESERVED_2__SHIFT			3
+static inline uint32_t DDMA_CFG_DMA_ARB_RESERVED_2(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_RESERVED_2__SHIFT) & DDMA_CFG_DMA_ARB_RESERVED_2__MASK;
+}
+#define DDMA_CFG_DMA_ARB_RD_FIX_ARB__MASK			0x00000007
+#define DDMA_CFG_DMA_ARB_RD_FIX_ARB__SHIFT			0
+static inline uint32_t DDMA_CFG_DMA_ARB_RD_FIX_ARB(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_ARB_RD_FIX_ARB__SHIFT) & DDMA_CFG_DMA_ARB_RD_FIX_ARB__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_RD_QOS					0x00008020
+#define DDMA_CFG_DMA_RD_QOS_RESERVED_0__MASK			0xfffffc00
+#define DDMA_CFG_DMA_RD_QOS_RESERVED_0__SHIFT			10
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RESERVED_0__SHIFT) & DDMA_CFG_DMA_RD_QOS_RESERVED_0__MASK;
+}
+#define DDMA_CFG_DMA_RD_QOS_RD_PC_QOS__MASK			0x00000300
+#define DDMA_CFG_DMA_RD_QOS_RD_PC_QOS__SHIFT			8
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RD_PC_QOS(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RD_PC_QOS__SHIFT) & DDMA_CFG_DMA_RD_QOS_RD_PC_QOS__MASK;
+}
+#define DDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__MASK			0x000000c0
+#define DDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__SHIFT			6
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RD_PPU_QOS(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__SHIFT) & DDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__MASK;
+}
+#define DDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__MASK			0x00000030
+#define DDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__SHIFT			4
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RD_DPU_QOS(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__SHIFT) & DDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__MASK;
+}
+#define DDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__MASK			0x0000000c
+#define DDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__SHIFT		2
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__SHIFT) & DDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__MASK;
+}
+#define DDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__MASK		0x00000003
+#define DDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__SHIFT		0
+static inline uint32_t DDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__SHIFT) & DDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_RD_CFG					0x00008024
+#define DDMA_CFG_DMA_RD_CFG_RESERVED_0__MASK			0xffffe000
+#define DDMA_CFG_DMA_RD_CFG_RESERVED_0__SHIFT			13
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RESERVED_0__SHIFT) & DDMA_CFG_DMA_RD_CFG_RESERVED_0__MASK;
+}
+#define DDMA_CFG_DMA_RD_CFG_RD_ARLOCK__MASK			0x00001000
+#define DDMA_CFG_DMA_RD_CFG_RD_ARLOCK__SHIFT			12
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RD_ARLOCK(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RD_ARLOCK__SHIFT) & DDMA_CFG_DMA_RD_CFG_RD_ARLOCK__MASK;
+}
+#define DDMA_CFG_DMA_RD_CFG_RD_ARCACHE__MASK			0x00000f00
+#define DDMA_CFG_DMA_RD_CFG_RD_ARCACHE__SHIFT			8
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RD_ARCACHE(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RD_ARCACHE__SHIFT) & DDMA_CFG_DMA_RD_CFG_RD_ARCACHE__MASK;
+}
+#define DDMA_CFG_DMA_RD_CFG_RD_ARPROT__MASK			0x000000e0
+#define DDMA_CFG_DMA_RD_CFG_RD_ARPROT__SHIFT			5
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RD_ARPROT(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RD_ARPROT__SHIFT) & DDMA_CFG_DMA_RD_CFG_RD_ARPROT__MASK;
+}
+#define DDMA_CFG_DMA_RD_CFG_RD_ARBURST__MASK			0x00000018
+#define DDMA_CFG_DMA_RD_CFG_RD_ARBURST__SHIFT			3
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RD_ARBURST(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RD_ARBURST__SHIFT) & DDMA_CFG_DMA_RD_CFG_RD_ARBURST__MASK;
+}
+#define DDMA_CFG_DMA_RD_CFG_RD_ARSIZE__MASK			0x00000007
+#define DDMA_CFG_DMA_RD_CFG_RD_ARSIZE__SHIFT			0
+static inline uint32_t DDMA_CFG_DMA_RD_CFG_RD_ARSIZE(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_RD_CFG_RD_ARSIZE__SHIFT) & DDMA_CFG_DMA_RD_CFG_RD_ARSIZE__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_WR_CFG					0x00008028
+#define DDMA_CFG_DMA_WR_CFG_RESERVED_0__MASK			0xffffe000
+#define DDMA_CFG_DMA_WR_CFG_RESERVED_0__SHIFT			13
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_RESERVED_0__SHIFT) & DDMA_CFG_DMA_WR_CFG_RESERVED_0__MASK;
+}
+#define DDMA_CFG_DMA_WR_CFG_WR_AWLOCK__MASK			0x00001000
+#define DDMA_CFG_DMA_WR_CFG_WR_AWLOCK__SHIFT			12
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_WR_AWLOCK(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_WR_AWLOCK__SHIFT) & DDMA_CFG_DMA_WR_CFG_WR_AWLOCK__MASK;
+}
+#define DDMA_CFG_DMA_WR_CFG_WR_AWCACHE__MASK			0x00000f00
+#define DDMA_CFG_DMA_WR_CFG_WR_AWCACHE__SHIFT			8
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_WR_AWCACHE(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_WR_AWCACHE__SHIFT) & DDMA_CFG_DMA_WR_CFG_WR_AWCACHE__MASK;
+}
+#define DDMA_CFG_DMA_WR_CFG_WR_AWPROT__MASK			0x000000e0
+#define DDMA_CFG_DMA_WR_CFG_WR_AWPROT__SHIFT			5
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_WR_AWPROT(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_WR_AWPROT__SHIFT) & DDMA_CFG_DMA_WR_CFG_WR_AWPROT__MASK;
+}
+#define DDMA_CFG_DMA_WR_CFG_WR_AWBURST__MASK			0x00000018
+#define DDMA_CFG_DMA_WR_CFG_WR_AWBURST__SHIFT			3
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_WR_AWBURST(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_WR_AWBURST__SHIFT) & DDMA_CFG_DMA_WR_CFG_WR_AWBURST__MASK;
+}
+#define DDMA_CFG_DMA_WR_CFG_WR_AWSIZE__MASK			0x00000007
+#define DDMA_CFG_DMA_WR_CFG_WR_AWSIZE__SHIFT			0
+static inline uint32_t DDMA_CFG_DMA_WR_CFG_WR_AWSIZE(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WR_CFG_WR_AWSIZE__SHIFT) & DDMA_CFG_DMA_WR_CFG_WR_AWSIZE__MASK;
+}
+
+#define REG_DDMA_CFG_DMA_WSTRB					0x0000802c
+#define DDMA_CFG_DMA_WSTRB_WR_WSTRB__MASK			0xffffffff
+#define DDMA_CFG_DMA_WSTRB_WR_WSTRB__SHIFT			0
+static inline uint32_t DDMA_CFG_DMA_WSTRB_WR_WSTRB(uint32_t val)
+{
+	return ((val) << DDMA_CFG_DMA_WSTRB_WR_WSTRB__SHIFT) & DDMA_CFG_DMA_WSTRB_WR_WSTRB__MASK;
+}
+
+#define REG_DDMA_CFG_STATUS					0x00008030
+#define DDMA_CFG_STATUS_RESERVED_0__MASK			0xfffffe00
+#define DDMA_CFG_STATUS_RESERVED_0__SHIFT			9
+static inline uint32_t DDMA_CFG_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << DDMA_CFG_STATUS_RESERVED_0__SHIFT) & DDMA_CFG_STATUS_RESERVED_0__MASK;
+}
+#define DDMA_CFG_STATUS_IDEL__MASK				0x00000100
+#define DDMA_CFG_STATUS_IDEL__SHIFT				8
+static inline uint32_t DDMA_CFG_STATUS_IDEL(uint32_t val)
+{
+	return ((val) << DDMA_CFG_STATUS_IDEL__SHIFT) & DDMA_CFG_STATUS_IDEL__MASK;
+}
+#define DDMA_CFG_STATUS_RESERVED_1__MASK			0x000000ff
+#define DDMA_CFG_STATUS_RESERVED_1__SHIFT			0
+static inline uint32_t DDMA_CFG_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << DDMA_CFG_STATUS_RESERVED_1__SHIFT) & DDMA_CFG_STATUS_RESERVED_1__MASK;
+}
+
+#define REG_SDMA_CFG_OUTSTANDING				0x00009000
+#define SDMA_CFG_OUTSTANDING_RESERVED_0__MASK			0xffff0000
+#define SDMA_CFG_OUTSTANDING_RESERVED_0__SHIFT			16
+static inline uint32_t SDMA_CFG_OUTSTANDING_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_OUTSTANDING_RESERVED_0__SHIFT) & SDMA_CFG_OUTSTANDING_RESERVED_0__MASK;
+}
+#define SDMA_CFG_OUTSTANDING_WR_OS_CNT__MASK			0x0000ff00
+#define SDMA_CFG_OUTSTANDING_WR_OS_CNT__SHIFT			8
+static inline uint32_t SDMA_CFG_OUTSTANDING_WR_OS_CNT(uint32_t val)
+{
+	return ((val) << SDMA_CFG_OUTSTANDING_WR_OS_CNT__SHIFT) & SDMA_CFG_OUTSTANDING_WR_OS_CNT__MASK;
+}
+#define SDMA_CFG_OUTSTANDING_RD_OS_CNT__MASK			0x000000ff
+#define SDMA_CFG_OUTSTANDING_RD_OS_CNT__SHIFT			0
+static inline uint32_t SDMA_CFG_OUTSTANDING_RD_OS_CNT(uint32_t val)
+{
+	return ((val) << SDMA_CFG_OUTSTANDING_RD_OS_CNT__SHIFT) & SDMA_CFG_OUTSTANDING_RD_OS_CNT__MASK;
+}
+
+#define REG_SDMA_RD_WEIGHT_0					0x00009004
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__MASK			0xff000000
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__SHIFT			24
+static inline uint32_t SDMA_RD_WEIGHT_0_RD_WEIGHT_PDP(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__SHIFT) & SDMA_RD_WEIGHT_0_RD_WEIGHT_PDP__MASK;
+}
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__MASK			0x00ff0000
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__SHIFT			16
+static inline uint32_t SDMA_RD_WEIGHT_0_RD_WEIGHT_DPU(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__SHIFT) & SDMA_RD_WEIGHT_0_RD_WEIGHT_DPU__MASK;
+}
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__MASK			0x0000ff00
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__SHIFT		8
+static inline uint32_t SDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__SHIFT) & SDMA_RD_WEIGHT_0_RD_WEIGHT_KERNEL__MASK;
+}
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__MASK		0x000000ff
+#define SDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__SHIFT		0
+static inline uint32_t SDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__SHIFT) & SDMA_RD_WEIGHT_0_RD_WEIGHT_FEATURE__MASK;
+}
+
+#define REG_SDMA_WR_WEIGHT_0					0x00009008
+#define SDMA_WR_WEIGHT_0_RESERVED_0__MASK			0xffff0000
+#define SDMA_WR_WEIGHT_0_RESERVED_0__SHIFT			16
+static inline uint32_t SDMA_WR_WEIGHT_0_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_WR_WEIGHT_0_RESERVED_0__SHIFT) & SDMA_WR_WEIGHT_0_RESERVED_0__MASK;
+}
+#define SDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__MASK			0x0000ff00
+#define SDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__SHIFT			8
+static inline uint32_t SDMA_WR_WEIGHT_0_WR_WEIGHT_PDP(uint32_t val)
+{
+	return ((val) << SDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__SHIFT) & SDMA_WR_WEIGHT_0_WR_WEIGHT_PDP__MASK;
+}
+#define SDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__MASK			0x000000ff
+#define SDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__SHIFT			0
+static inline uint32_t SDMA_WR_WEIGHT_0_WR_WEIGHT_DPU(uint32_t val)
+{
+	return ((val) << SDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__SHIFT) & SDMA_WR_WEIGHT_0_WR_WEIGHT_DPU__MASK;
+}
+
+#define REG_SDMA_CFG_ID_ERROR					0x0000900c
+#define SDMA_CFG_ID_ERROR_RESERVED_0__MASK			0xfffffc00
+#define SDMA_CFG_ID_ERROR_RESERVED_0__SHIFT			10
+static inline uint32_t SDMA_CFG_ID_ERROR_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_ID_ERROR_RESERVED_0__SHIFT) & SDMA_CFG_ID_ERROR_RESERVED_0__MASK;
+}
+#define SDMA_CFG_ID_ERROR_WR_RESP_ID__MASK			0x000003c0
+#define SDMA_CFG_ID_ERROR_WR_RESP_ID__SHIFT			6
+static inline uint32_t SDMA_CFG_ID_ERROR_WR_RESP_ID(uint32_t val)
+{
+	return ((val) << SDMA_CFG_ID_ERROR_WR_RESP_ID__SHIFT) & SDMA_CFG_ID_ERROR_WR_RESP_ID__MASK;
+}
+#define SDMA_CFG_ID_ERROR_RESERVED_1__MASK			0x00000020
+#define SDMA_CFG_ID_ERROR_RESERVED_1__SHIFT			5
+static inline uint32_t SDMA_CFG_ID_ERROR_RESERVED_1(uint32_t val)
+{
+	return ((val) << SDMA_CFG_ID_ERROR_RESERVED_1__SHIFT) & SDMA_CFG_ID_ERROR_RESERVED_1__MASK;
+}
+#define SDMA_CFG_ID_ERROR_RD_RESP_ID__MASK			0x0000001f
+#define SDMA_CFG_ID_ERROR_RD_RESP_ID__SHIFT			0
+static inline uint32_t SDMA_CFG_ID_ERROR_RD_RESP_ID(uint32_t val)
+{
+	return ((val) << SDMA_CFG_ID_ERROR_RD_RESP_ID__SHIFT) & SDMA_CFG_ID_ERROR_RD_RESP_ID__MASK;
+}
+
+#define REG_SDMA_RD_WEIGHT_1					0x00009010
+#define SDMA_RD_WEIGHT_1_RESERVED_0__MASK			0xffffff00
+#define SDMA_RD_WEIGHT_1_RESERVED_0__SHIFT			8
+static inline uint32_t SDMA_RD_WEIGHT_1_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_1_RESERVED_0__SHIFT) & SDMA_RD_WEIGHT_1_RESERVED_0__MASK;
+}
+#define SDMA_RD_WEIGHT_1_RD_WEIGHT_PC__MASK			0x000000ff
+#define SDMA_RD_WEIGHT_1_RD_WEIGHT_PC__SHIFT			0
+static inline uint32_t SDMA_RD_WEIGHT_1_RD_WEIGHT_PC(uint32_t val)
+{
+	return ((val) << SDMA_RD_WEIGHT_1_RD_WEIGHT_PC__SHIFT) & SDMA_RD_WEIGHT_1_RD_WEIGHT_PC__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_FIFO_CLR				0x00009014
+#define SDMA_CFG_DMA_FIFO_CLR_RESERVED_0__MASK			0xfffffffe
+#define SDMA_CFG_DMA_FIFO_CLR_RESERVED_0__SHIFT			1
+static inline uint32_t SDMA_CFG_DMA_FIFO_CLR_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_FIFO_CLR_RESERVED_0__SHIFT) & SDMA_CFG_DMA_FIFO_CLR_RESERVED_0__MASK;
+}
+#define SDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__MASK		0x00000001
+#define SDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__SHIFT		0
+static inline uint32_t SDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__SHIFT) & SDMA_CFG_DMA_FIFO_CLR_DMA_FIFO_CLR__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_ARB					0x00009018
+#define SDMA_CFG_DMA_ARB_RESERVED_0__MASK			0xfffffc00
+#define SDMA_CFG_DMA_ARB_RESERVED_0__SHIFT			10
+static inline uint32_t SDMA_CFG_DMA_ARB_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_RESERVED_0__SHIFT) & SDMA_CFG_DMA_ARB_RESERVED_0__MASK;
+}
+#define SDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__MASK			0x00000200
+#define SDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__SHIFT			9
+static inline uint32_t SDMA_CFG_DMA_ARB_WR_ARBIT_MODEL(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__SHIFT) & SDMA_CFG_DMA_ARB_WR_ARBIT_MODEL__MASK;
+}
+#define SDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__MASK			0x00000100
+#define SDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__SHIFT			8
+static inline uint32_t SDMA_CFG_DMA_ARB_RD_ARBIT_MODEL(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__SHIFT) & SDMA_CFG_DMA_ARB_RD_ARBIT_MODEL__MASK;
+}
+#define SDMA_CFG_DMA_ARB_RESERVED_1__MASK			0x00000080
+#define SDMA_CFG_DMA_ARB_RESERVED_1__SHIFT			7
+static inline uint32_t SDMA_CFG_DMA_ARB_RESERVED_1(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_RESERVED_1__SHIFT) & SDMA_CFG_DMA_ARB_RESERVED_1__MASK;
+}
+#define SDMA_CFG_DMA_ARB_WR_FIX_ARB__MASK			0x00000070
+#define SDMA_CFG_DMA_ARB_WR_FIX_ARB__SHIFT			4
+static inline uint32_t SDMA_CFG_DMA_ARB_WR_FIX_ARB(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_WR_FIX_ARB__SHIFT) & SDMA_CFG_DMA_ARB_WR_FIX_ARB__MASK;
+}
+#define SDMA_CFG_DMA_ARB_RESERVED_2__MASK			0x00000008
+#define SDMA_CFG_DMA_ARB_RESERVED_2__SHIFT			3
+static inline uint32_t SDMA_CFG_DMA_ARB_RESERVED_2(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_RESERVED_2__SHIFT) & SDMA_CFG_DMA_ARB_RESERVED_2__MASK;
+}
+#define SDMA_CFG_DMA_ARB_RD_FIX_ARB__MASK			0x00000007
+#define SDMA_CFG_DMA_ARB_RD_FIX_ARB__SHIFT			0
+static inline uint32_t SDMA_CFG_DMA_ARB_RD_FIX_ARB(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_ARB_RD_FIX_ARB__SHIFT) & SDMA_CFG_DMA_ARB_RD_FIX_ARB__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_RD_QOS					0x00009020
+#define SDMA_CFG_DMA_RD_QOS_RESERVED_0__MASK			0xfffffc00
+#define SDMA_CFG_DMA_RD_QOS_RESERVED_0__SHIFT			10
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RESERVED_0__SHIFT) & SDMA_CFG_DMA_RD_QOS_RESERVED_0__MASK;
+}
+#define SDMA_CFG_DMA_RD_QOS_RD_PC_QOS__MASK			0x00000300
+#define SDMA_CFG_DMA_RD_QOS_RD_PC_QOS__SHIFT			8
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RD_PC_QOS(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RD_PC_QOS__SHIFT) & SDMA_CFG_DMA_RD_QOS_RD_PC_QOS__MASK;
+}
+#define SDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__MASK			0x000000c0
+#define SDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__SHIFT			6
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RD_PPU_QOS(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__SHIFT) & SDMA_CFG_DMA_RD_QOS_RD_PPU_QOS__MASK;
+}
+#define SDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__MASK			0x00000030
+#define SDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__SHIFT			4
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RD_DPU_QOS(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__SHIFT) & SDMA_CFG_DMA_RD_QOS_RD_DPU_QOS__MASK;
+}
+#define SDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__MASK			0x0000000c
+#define SDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__SHIFT		2
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__SHIFT) & SDMA_CFG_DMA_RD_QOS_RD_KERNEL_QOS__MASK;
+}
+#define SDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__MASK		0x00000003
+#define SDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__SHIFT		0
+static inline uint32_t SDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__SHIFT) & SDMA_CFG_DMA_RD_QOS_RD_FEATURE_QOS__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_RD_CFG					0x00009024
+#define SDMA_CFG_DMA_RD_CFG_RESERVED_0__MASK			0xffffe000
+#define SDMA_CFG_DMA_RD_CFG_RESERVED_0__SHIFT			13
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RESERVED_0__SHIFT) & SDMA_CFG_DMA_RD_CFG_RESERVED_0__MASK;
+}
+#define SDMA_CFG_DMA_RD_CFG_RD_ARLOCK__MASK			0x00001000
+#define SDMA_CFG_DMA_RD_CFG_RD_ARLOCK__SHIFT			12
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RD_ARLOCK(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RD_ARLOCK__SHIFT) & SDMA_CFG_DMA_RD_CFG_RD_ARLOCK__MASK;
+}
+#define SDMA_CFG_DMA_RD_CFG_RD_ARCACHE__MASK			0x00000f00
+#define SDMA_CFG_DMA_RD_CFG_RD_ARCACHE__SHIFT			8
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RD_ARCACHE(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RD_ARCACHE__SHIFT) & SDMA_CFG_DMA_RD_CFG_RD_ARCACHE__MASK;
+}
+#define SDMA_CFG_DMA_RD_CFG_RD_ARPROT__MASK			0x000000e0
+#define SDMA_CFG_DMA_RD_CFG_RD_ARPROT__SHIFT			5
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RD_ARPROT(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RD_ARPROT__SHIFT) & SDMA_CFG_DMA_RD_CFG_RD_ARPROT__MASK;
+}
+#define SDMA_CFG_DMA_RD_CFG_RD_ARBURST__MASK			0x00000018
+#define SDMA_CFG_DMA_RD_CFG_RD_ARBURST__SHIFT			3
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RD_ARBURST(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RD_ARBURST__SHIFT) & SDMA_CFG_DMA_RD_CFG_RD_ARBURST__MASK;
+}
+#define SDMA_CFG_DMA_RD_CFG_RD_ARSIZE__MASK			0x00000007
+#define SDMA_CFG_DMA_RD_CFG_RD_ARSIZE__SHIFT			0
+static inline uint32_t SDMA_CFG_DMA_RD_CFG_RD_ARSIZE(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_RD_CFG_RD_ARSIZE__SHIFT) & SDMA_CFG_DMA_RD_CFG_RD_ARSIZE__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_WR_CFG					0x00009028
+#define SDMA_CFG_DMA_WR_CFG_RESERVED_0__MASK			0xffffe000
+#define SDMA_CFG_DMA_WR_CFG_RESERVED_0__SHIFT			13
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_RESERVED_0__SHIFT) & SDMA_CFG_DMA_WR_CFG_RESERVED_0__MASK;
+}
+#define SDMA_CFG_DMA_WR_CFG_WR_AWLOCK__MASK			0x00001000
+#define SDMA_CFG_DMA_WR_CFG_WR_AWLOCK__SHIFT			12
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_WR_AWLOCK(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_WR_AWLOCK__SHIFT) & SDMA_CFG_DMA_WR_CFG_WR_AWLOCK__MASK;
+}
+#define SDMA_CFG_DMA_WR_CFG_WR_AWCACHE__MASK			0x00000f00
+#define SDMA_CFG_DMA_WR_CFG_WR_AWCACHE__SHIFT			8
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_WR_AWCACHE(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_WR_AWCACHE__SHIFT) & SDMA_CFG_DMA_WR_CFG_WR_AWCACHE__MASK;
+}
+#define SDMA_CFG_DMA_WR_CFG_WR_AWPROT__MASK			0x000000e0
+#define SDMA_CFG_DMA_WR_CFG_WR_AWPROT__SHIFT			5
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_WR_AWPROT(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_WR_AWPROT__SHIFT) & SDMA_CFG_DMA_WR_CFG_WR_AWPROT__MASK;
+}
+#define SDMA_CFG_DMA_WR_CFG_WR_AWBURST__MASK			0x00000018
+#define SDMA_CFG_DMA_WR_CFG_WR_AWBURST__SHIFT			3
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_WR_AWBURST(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_WR_AWBURST__SHIFT) & SDMA_CFG_DMA_WR_CFG_WR_AWBURST__MASK;
+}
+#define SDMA_CFG_DMA_WR_CFG_WR_AWSIZE__MASK			0x00000007
+#define SDMA_CFG_DMA_WR_CFG_WR_AWSIZE__SHIFT			0
+static inline uint32_t SDMA_CFG_DMA_WR_CFG_WR_AWSIZE(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WR_CFG_WR_AWSIZE__SHIFT) & SDMA_CFG_DMA_WR_CFG_WR_AWSIZE__MASK;
+}
+
+#define REG_SDMA_CFG_DMA_WSTRB					0x0000902c
+#define SDMA_CFG_DMA_WSTRB_WR_WSTRB__MASK			0xffffffff
+#define SDMA_CFG_DMA_WSTRB_WR_WSTRB__SHIFT			0
+static inline uint32_t SDMA_CFG_DMA_WSTRB_WR_WSTRB(uint32_t val)
+{
+	return ((val) << SDMA_CFG_DMA_WSTRB_WR_WSTRB__SHIFT) & SDMA_CFG_DMA_WSTRB_WR_WSTRB__MASK;
+}
+
+#define REG_SDMA_CFG_STATUS					0x00009030
+#define SDMA_CFG_STATUS_RESERVED_0__MASK			0xfffffe00
+#define SDMA_CFG_STATUS_RESERVED_0__SHIFT			9
+static inline uint32_t SDMA_CFG_STATUS_RESERVED_0(uint32_t val)
+{
+	return ((val) << SDMA_CFG_STATUS_RESERVED_0__SHIFT) & SDMA_CFG_STATUS_RESERVED_0__MASK;
+}
+#define SDMA_CFG_STATUS_IDEL__MASK				0x00000100
+#define SDMA_CFG_STATUS_IDEL__SHIFT				8
+static inline uint32_t SDMA_CFG_STATUS_IDEL(uint32_t val)
+{
+	return ((val) << SDMA_CFG_STATUS_IDEL__SHIFT) & SDMA_CFG_STATUS_IDEL__MASK;
+}
+#define SDMA_CFG_STATUS_RESERVED_1__MASK			0x000000ff
+#define SDMA_CFG_STATUS_RESERVED_1__SHIFT			0
+static inline uint32_t SDMA_CFG_STATUS_RESERVED_1(uint32_t val)
+{
+	return ((val) << SDMA_CFG_STATUS_RESERVED_1__SHIFT) & SDMA_CFG_STATUS_RESERVED_1__MASK;
+}
+
+#define REG_GLOBAL_OPERATION_ENABLE				0x0000f008
+#define GLOBAL_OPERATION_ENABLE_RESERVED_0__MASK		0xffffff80
+#define GLOBAL_OPERATION_ENABLE_RESERVED_0__SHIFT		7
+static inline uint32_t GLOBAL_OPERATION_ENABLE_RESERVED_0(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_RESERVED_0__SHIFT) & GLOBAL_OPERATION_ENABLE_RESERVED_0__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_PPU_RDMA_OP_EN__MASK		0x00000040
+#define GLOBAL_OPERATION_ENABLE_PPU_RDMA_OP_EN__SHIFT		6
+static inline uint32_t GLOBAL_OPERATION_ENABLE_PPU_RDMA_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_PPU_RDMA_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_PPU_RDMA_OP_EN__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_PPU_OP_EN__MASK			0x00000020
+#define GLOBAL_OPERATION_ENABLE_PPU_OP_EN__SHIFT		5
+static inline uint32_t GLOBAL_OPERATION_ENABLE_PPU_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_PPU_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_PPU_OP_EN__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_DPU_RDMA_OP_EN__MASK		0x00000010
+#define GLOBAL_OPERATION_ENABLE_DPU_RDMA_OP_EN__SHIFT		4
+static inline uint32_t GLOBAL_OPERATION_ENABLE_DPU_RDMA_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_DPU_RDMA_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_DPU_RDMA_OP_EN__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_DPU_OP_EN__MASK			0x00000008
+#define GLOBAL_OPERATION_ENABLE_DPU_OP_EN__SHIFT		3
+static inline uint32_t GLOBAL_OPERATION_ENABLE_DPU_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_DPU_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_DPU_OP_EN__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_CORE_OP_EN__MASK		0x00000004
+#define GLOBAL_OPERATION_ENABLE_CORE_OP_EN__SHIFT		2
+static inline uint32_t GLOBAL_OPERATION_ENABLE_CORE_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_CORE_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_CORE_OP_EN__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_RESERVED_1__MASK		0x00000002
+#define GLOBAL_OPERATION_ENABLE_RESERVED_1__SHIFT		1
+static inline uint32_t GLOBAL_OPERATION_ENABLE_RESERVED_1(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_RESERVED_1__SHIFT) & GLOBAL_OPERATION_ENABLE_RESERVED_1__MASK;
+}
+#define GLOBAL_OPERATION_ENABLE_CNA_OP_EN__MASK			0x00000001
+#define GLOBAL_OPERATION_ENABLE_CNA_OP_EN__SHIFT		0
+static inline uint32_t GLOBAL_OPERATION_ENABLE_CNA_OP_EN(uint32_t val)
+{
+	return ((val) << GLOBAL_OPERATION_ENABLE_CNA_OP_EN__SHIFT) & GLOBAL_OPERATION_ENABLE_CNA_OP_EN__MASK;
+}
+
+#endif /* __ROCKET_REGISTERS_XML__ */
diff --git a/drivers/accessibility/speakup/Makefile b/drivers/accessibility/speakup/Makefile
index 6f6a83565c0d..14ba1cca87f4 100644
--- a/drivers/accessibility/speakup/Makefile
+++ b/drivers/accessibility/speakup/Makefile
@@ -40,9 +40,7 @@ hostprogs += makemapdata
 makemapdata-objs := makemapdata.o
 
 quiet_cmd_mkmap = MKMAP   $@
-      cmd_mkmap = TOPDIR=$(srctree) \
-		  SPKDIR=$(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD),$(srctree)/drivers/accessibility/speakup) \
-		  $(obj)/makemapdata > $@
+      cmd_mkmap = TOPDIR=$(srctree) SPKDIR=$(src) $(obj)/makemapdata > $@
 
 $(obj)/mapdata.h: $(obj)/makemapdata
 	$(call cmd,mkmap)
diff --git a/drivers/accessibility/speakup/devsynth.c b/drivers/accessibility/speakup/devsynth.c
index d30571663585..e3d909bd0480 100644
--- a/drivers/accessibility/speakup/devsynth.c
+++ b/drivers/accessibility/speakup/devsynth.c
@@ -7,9 +7,10 @@
 #include "speakup.h"
 #include "spk_priv.h"
 
-static int misc_registered;
+static int synth_registered, synthu_registered;
 static int dev_opened;
 
+/* Latin1 version */
 static ssize_t speakup_file_write(struct file *fp, const char __user *buffer,
 				  size_t nbytes, loff_t *ppos)
 {
@@ -34,6 +35,65 @@ static ssize_t speakup_file_write(struct file *fp, const char __user *buffer,
 	return (ssize_t)nbytes;
 }
 
+/* UTF-8 version */
+static ssize_t speakup_file_writeu(struct file *fp, const char __user *buffer,
+				   size_t nbytes, loff_t *ppos)
+{
+	size_t count = nbytes, consumed, want;
+	const char __user *ptr = buffer;
+	size_t bytes;
+	unsigned long flags;
+	unsigned char buf[256];
+	u16 ubuf[256];
+	size_t in, out;
+
+	if (!synth)
+		return -ENODEV;
+
+	want = 1;
+	while (count >= want) {
+		/* Copy some UTF-8 piece from userland */
+		bytes = min(count, sizeof(buf));
+		if (copy_from_user(buf, ptr, bytes))
+			return -EFAULT;
+
+		/* Convert to u16 */
+		for (in = 0, out = 0; in < bytes; in += consumed) {
+			s32 value;
+
+			value = synth_utf8_get(buf + in, bytes - in, &consumed, &want);
+			if (value == -1) {
+				/* Invalid or incomplete */
+
+				if (want > bytes - in)
+					/* We don't have it all yet, stop here
+					 * and wait for the rest
+					 */
+					bytes = in;
+
+				continue;
+			}
+
+			if (value < 0x10000)
+				ubuf[out++] = value;
+		}
+
+		count -= bytes;
+		ptr += bytes;
+
+		/* And speak this up */
+		if (out) {
+			spin_lock_irqsave(&speakup_info.spinlock, flags);
+			for (in = 0; in < out; in++)
+				synth_buffer_add(ubuf[in]);
+			synth_start();
+			spin_unlock_irqrestore(&speakup_info.spinlock, flags);
+		}
+	}
+
+	return (ssize_t)(nbytes - count);
+}
+
 static ssize_t speakup_file_read(struct file *fp, char __user *buf,
 				 size_t nbytes, loff_t *ppos)
 {
@@ -62,31 +122,57 @@ static const struct file_operations synth_fops = {
 	.release = speakup_file_release,
 };
 
+static const struct file_operations synthu_fops = {
+	.read = speakup_file_read,
+	.write = speakup_file_writeu,
+	.open = speakup_file_open,
+	.release = speakup_file_release,
+};
+
 static struct miscdevice synth_device = {
 	.minor = MISC_DYNAMIC_MINOR,
 	.name = "synth",
 	.fops = &synth_fops,
 };
 
+static struct miscdevice synthu_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "synthu",
+	.fops = &synthu_fops,
+};
+
 void speakup_register_devsynth(void)
 {
-	if (misc_registered != 0)
-		return;
-/* zero it so if register fails, deregister will not ref invalid ptrs */
-	if (misc_register(&synth_device)) {
-		pr_warn("Couldn't initialize miscdevice /dev/synth.\n");
-	} else {
-		pr_info("initialized device: /dev/synth, node (MAJOR %d, MINOR %d)\n",
-			MISC_MAJOR, synth_device.minor);
-		misc_registered = 1;
+	if (!synth_registered) {
+		if (misc_register(&synth_device)) {
+			pr_warn("Couldn't initialize miscdevice /dev/synth.\n");
+		} else {
+			pr_info("initialized device: /dev/synth, node (MAJOR %d, MINOR %d)\n",
+				MISC_MAJOR, synth_device.minor);
+			synth_registered = 1;
+		}
+	}
+	if (!synthu_registered) {
+		if (misc_register(&synthu_device)) {
+			pr_warn("Couldn't initialize miscdevice /dev/synthu.\n");
+		} else {
+			pr_info("initialized device: /dev/synthu, node (MAJOR %d, MINOR %d)\n",
+				MISC_MAJOR, synthu_device.minor);
+			synthu_registered = 1;
+		}
 	}
 }
 
 void speakup_unregister_devsynth(void)
 {
-	if (!misc_registered)
-		return;
-	pr_info("speakup: unregistering synth device /dev/synth\n");
-	misc_deregister(&synth_device);
-	misc_registered = 0;
+	if (synth_registered) {
+		pr_info("speakup: unregistering synth device /dev/synth\n");
+		misc_deregister(&synth_device);
+		synth_registered = 0;
+	}
+	if (synthu_registered) {
+		pr_info("speakup: unregistering synth device /dev/synthu\n");
+		misc_deregister(&synthu_device);
+		synthu_registered = 0;
+	}
 }
diff --git a/drivers/accessibility/speakup/genmap.c b/drivers/accessibility/speakup/genmap.c
index 0125000e00d9..0882bab10fb8 100644
--- a/drivers/accessibility/speakup/genmap.c
+++ b/drivers/accessibility/speakup/genmap.c
@@ -10,7 +10,6 @@
 #include <stdio.h>
 #include <libgen.h>
 #include <string.h>
-#include <linux/version.h>
 #include <ctype.h>
 #include "utils.h"
 
diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c
index 1fbc9b921c4f..e68cf1d83787 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -574,7 +574,7 @@ static u_long get_word(struct vc_data *vc)
 	}
 	attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr);
 	buf[cnt++] = attr_ch;
-	while (tmpx < vc->vc_cols - 1) {
+	while (tmpx < vc->vc_cols - 1 && cnt < ARRAY_SIZE(buf) - 1) {
 		tmp_pos += 2;
 		tmpx++;
 		ch = get_char(vc, (u_short *)tmp_pos, &temp);
@@ -1172,13 +1172,13 @@ static void do_handle_shift(struct vc_data *vc, u_char value, char up_flag)
 	if (cursor_track == read_all_mode) {
 		switch (value) {
 		case KVAL(K_SHIFT):
-			del_timer(&cursor_timer);
+			timer_delete(&cursor_timer);
 			spk_shut_up &= 0xfe;
 			spk_do_flush();
 			read_all_doc(vc);
 			break;
 		case KVAL(K_CTRL):
-			del_timer(&cursor_timer);
+			timer_delete(&cursor_timer);
 			cursor_track = prev_cursor_track;
 			spk_shut_up &= 0xfe;
 			spk_do_flush();
@@ -1399,7 +1399,7 @@ static void start_read_all_timer(struct vc_data *vc, enum read_all_command comma
 
 static void kbd_fakekey2(struct vc_data *vc, enum read_all_command command)
 {
-	del_timer(&cursor_timer);
+	timer_delete(&cursor_timer);
 	speakup_fake_down_arrow();
 	start_read_all_timer(vc, command);
 }
@@ -1415,7 +1415,7 @@ static void read_all_doc(struct vc_data *vc)
 	cursor_track = read_all_mode;
 	spk_reset_index_count(0);
 	if (get_sentence_buf(vc, 0) == -1) {
-		del_timer(&cursor_timer);
+		timer_delete(&cursor_timer);
 		if (!in_keyboard_notifier)
 			speakup_fake_down_arrow();
 		start_read_all_timer(vc, RA_DOWN_ARROW);
@@ -1428,7 +1428,7 @@ static void read_all_doc(struct vc_data *vc)
 
 static void stop_read_all(struct vc_data *vc)
 {
-	del_timer(&cursor_timer);
+	timer_delete(&cursor_timer);
 	cursor_track = prev_cursor_track;
 	spk_shut_up &= 0xfe;
 	spk_do_flush();
@@ -1528,7 +1528,7 @@ static int pre_handle_cursor(struct vc_data *vc, u_char value, char up_flag)
 			spin_unlock_irqrestore(&speakup_info.spinlock, flags);
 			return NOTIFY_STOP;
 		}
-		del_timer(&cursor_timer);
+		timer_delete(&cursor_timer);
 		spk_shut_up &= 0xfe;
 		spk_do_flush();
 		start_read_all_timer(vc, value + 1);
@@ -1692,7 +1692,7 @@ static void cursor_done(struct timer_list *unused)
 	struct vc_data *vc = vc_cons[cursor_con].d;
 	unsigned long flags;
 
-	del_timer(&cursor_timer);
+	timer_delete(&cursor_timer);
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
 	if (cursor_con != fg_console) {
 		is_cursor = 0;
@@ -2333,7 +2333,7 @@ static void __exit speakup_exit(void)
 	speakup_unregister_devsynth();
 	speakup_cancel_selection();
 	speakup_cancel_paste();
-	del_timer_sync(&cursor_timer);
+	timer_delete_sync(&cursor_timer);
 	kthread_stop(speakup_task);
 	speakup_task = NULL;
 	mutex_lock(&spk_mutex);
@@ -2437,7 +2437,7 @@ error_task:
 
 error_vtnotifier:
 	unregister_keyboard_notifier(&keyboard_notifier_block);
-	del_timer(&cursor_timer);
+	timer_delete(&cursor_timer);
 
 error_kbdnotifier:
 	speakup_unregister_devsynth();
diff --git a/drivers/accessibility/speakup/makemapdata.c b/drivers/accessibility/speakup/makemapdata.c
index d7d41bb9b05f..55e4ef8a93dc 100644
--- a/drivers/accessibility/speakup/makemapdata.c
+++ b/drivers/accessibility/speakup/makemapdata.c
@@ -10,7 +10,6 @@
 #include <stdio.h>
 #include <libgen.h>
 #include <string.h>
-#include <linux/version.h>
 #include <ctype.h>
 #include "utils.h"
 
diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h
index 364fde99749e..54f1226ea061 100644
--- a/drivers/accessibility/speakup/speakup.h
+++ b/drivers/accessibility/speakup/speakup.h
@@ -76,7 +76,9 @@ int speakup_paste_selection(struct tty_struct *tty);
 void speakup_cancel_paste(void);
 void speakup_register_devsynth(void);
 void speakup_unregister_devsynth(void);
+s32 synth_utf8_get(const char *buf, size_t count, size_t *consumed, size_t *want);
 void synth_write(const char *buf, size_t count);
+void synth_writeu(const char *buf, size_t count);
 int synth_supports_indexing(void);
 
 extern struct vc_data *spk_sel_cons;
diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c
index eea2a2fa4f01..d8addbf3ad0d 100644
--- a/drivers/accessibility/speakup/synth.c
+++ b/drivers/accessibility/speakup/synth.c
@@ -208,17 +208,104 @@ void spk_do_flush(void)
 	wake_up_process(speakup_task);
 }
 
-void synth_write(const char *buf, size_t count)
+void synth_write(const char *_buf, size_t count)
 {
+	const unsigned char *buf = (const unsigned char *) _buf;
+
 	while (count--)
 		synth_buffer_add(*buf++);
 	synth_start();
 }
 
+/* Consume one utf-8 character from buf (that contains up to count bytes),
+ * returns the unicode codepoint if valid, -1 otherwise.
+ * In all cases, returns the number of consumed bytes in *consumed,
+ * and the minimum number of bytes that would be needed for the next character
+ * in *want.
+ */
+s32 synth_utf8_get(const char *buf, size_t count, size_t *consumed, size_t *want)
+{
+	unsigned char c = buf[0];
+	int nbytes = 8 - fls(c ^ 0xff);
+	u32 value;
+	size_t i;
+
+	switch (nbytes) {
+	case 8: /* 0xff */
+	case 7: /* 0xfe */
+	case 1: /* 0x80 */
+		/* Invalid, drop */
+		*consumed = 1;
+		*want = 1;
+		return -1;
+
+	case 0:
+		/* ASCII, take as such */
+		*consumed = 1;
+		*want = 1;
+		return c;
+
+	default:
+		/* 2..6-byte UTF-8 */
+
+		if (count < nbytes) {
+			/* We don't have it all */
+			*consumed = 0;
+			*want = nbytes;
+			return -1;
+		}
+
+		/* First byte */
+		value = c & ((1u << (7 - nbytes)) - 1);
+
+		/* Other bytes */
+		for (i = 1; i < nbytes; i++) {
+			c = buf[i];
+			if ((c & 0xc0) != 0x80)	{
+				/* Invalid, drop the head */
+				*consumed = i;
+				*want = 1;
+				return -1;
+			}
+			value = (value << 6) | (c & 0x3f);
+		}
+
+		*consumed = nbytes;
+		*want = 1;
+		return value;
+	}
+}
+
+void synth_writeu(const char *buf, size_t count)
+{
+	size_t i, consumed, want;
+
+	/* Convert to u16 */
+	for (i = 0; i < count; i++) {
+		s32 value;
+
+		value = synth_utf8_get(buf + i, count - i, &consumed, &want);
+		if (value == -1) {
+			/* Invalid or incomplete */
+
+			if (want > count - i)
+				/* We don't have it all, stop */
+				count = i;
+
+			continue;
+		}
+
+		if (value < 0x10000)
+			synth_buffer_add(value);
+	}
+
+	synth_start();
+}
+
 void synth_printf(const char *fmt, ...)
 {
 	va_list args;
-	unsigned char buf[160], *p;
+	unsigned char buf[160];
 	int r;
 
 	va_start(args, fmt);
@@ -227,10 +314,7 @@ void synth_printf(const char *fmt, ...)
 	if (r > sizeof(buf) - 1)
 		r = sizeof(buf) - 1;
 
-	p = buf;
-	while (r--)
-		synth_buffer_add(*p++);
-	synth_start();
+	synth_writeu(buf, r);
 }
 EXPORT_SYMBOL_GPL(synth_printf);
 
@@ -437,7 +521,7 @@ void synth_release(void)
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
 	pr_info("releasing synth %s\n", synth->name);
 	synth->alive = 0;
-	del_timer(&thread_timer);
+	timer_delete(&thread_timer);
 	spin_unlock_irqrestore(&speakup_info.spinlock, flags);
 	if (synth->attributes.name)
 		sysfs_remove_group(speakup_kobj, &synth->attributes);
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f819e760ff19..ca00a5dbcf75 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -61,6 +61,10 @@ config ACPI_CCA_REQUIRED
 config ACPI_TABLE_LIB
 	bool
 
+config ACPI_THERMAL_LIB
+       depends on THERMAL
+       bool
+
 config ACPI_DEBUGGER
 	bool "AML debugger interface"
 	select ACPI_DEBUG
@@ -128,8 +132,17 @@ config ACPI_REV_OVERRIDE_POSSIBLE
 	  makes it possible to force the kernel to return "5" as the supported
 	  ACPI revision via the "acpi_rev_override" command line switch.
 
+config ACPI_EC
+	bool "Embedded Controller"
+	depends on HAS_IOPORT
+	default X86 || LOONGARCH
+	help
+	  This driver handles communication with the microcontroller
+	  on many x86/LoongArch laptops and other machines.
+
 config ACPI_EC_DEBUGFS
 	tristate "EC read/write access through /sys/kernel/debug/ec"
+	depends on ACPI_EC
 	help
 	  Say N to disable Embedded Controller /sys/kernel/debug interface
 
@@ -282,7 +295,7 @@ config ACPI_CPPC_LIB
 
 config ACPI_PROCESSOR
 	tristate "Processor"
-	depends on X86 || ARM64 || LOONGARCH
+	depends on X86 || ARM64 || LOONGARCH || RISCV
 	select ACPI_PROCESSOR_IDLE
 	select ACPI_CPU_FREQ_PSS if X86 || LOONGARCH
 	select THERMAL
@@ -310,7 +323,6 @@ config ACPI_HOTPLUG_CPU
 	bool
 	depends on ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_CONTAINER
-	default y
 
 config ACPI_PROCESSOR_AGGREGATOR
 	tristate "Processor Aggregator"
@@ -327,6 +339,7 @@ config ACPI_THERMAL
 	tristate "Thermal Zone"
 	depends on ACPI_PROCESSOR
 	select THERMAL
+	select ACPI_THERMAL_LIB
 	default y
 	help
 	  This driver supports ACPI thermal zones.  Most mobile and
@@ -381,6 +394,7 @@ config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD
 
 config ACPI_DEBUG
 	bool "Debug Statements"
+	default y
 	help
 	  The ACPI subsystem can produce debug output.  Saying Y enables this
 	  output and increases the kernel size by around 50K.
@@ -429,7 +443,7 @@ config ACPI_HOTPLUG_IOAPIC
 
 config ACPI_SBS
 	tristate "Smart Battery System"
-	depends on X86
+	depends on X86 && ACPI_EC
 	select POWER_SUPPLY
 	help
 	  This driver supports the Smart Battery System, another
@@ -439,29 +453,15 @@ config ACPI_SBS
 	  the modules will be called sbs and sbshc.
 
 config ACPI_HED
-	tristate "Hardware Error Device"
+	bool "Hardware Error Device"
 	help
 	  This driver supports the Hardware Error Device (PNP0C33),
 	  which is used to report some hardware errors notified via
 	  SCI, mainly the corrected errors.
 
-config ACPI_CUSTOM_METHOD
-	tristate "Allow ACPI methods to be inserted/replaced at run time"
-	depends on DEBUG_FS
-	help
-	  This debug facility allows ACPI AML methods to be inserted and/or
-	  replaced without rebooting the system. For details refer to:
-	  Documentation/firmware-guide/acpi/method-customizing.rst.
-
-	  NOTE: This option is security sensitive, because it allows arbitrary
-	  kernel memory to be written to by root (uid=0) users, allowing them
-	  to bypass certain security measures (e.g. if root is not allowed to
-	  load additional kernel modules after boot, this feature may be used
-	  to override that restriction).
-
 config ACPI_BGRT
 	bool "Boottime Graphics Resource Table support"
-	depends on EFI && (X86 || ARM64)
+	depends on EFI
 	help
 	  This driver adds support for exposing the ACPI Boottime Graphics
 	  Resource Table, which allows the operating system to obtain
@@ -470,7 +470,6 @@ config ACPI_BGRT
 
 config ACPI_REDUCED_HARDWARE_ONLY
 	bool "Hardware-reduced ACPI support only" if EXPERT
-	def_bool n
 	help
 	  This config item changes the way the ACPI code is built.  When this
 	  option is selected, the kernel will use a specialized version of
@@ -480,6 +479,9 @@ config ACPI_REDUCED_HARDWARE_ONLY
 
 	  If you are unsure what to do, do not enable this option.
 
+config ACPI_NHLT
+	bool
+
 source "drivers/acpi/nfit/Kconfig"
 source "drivers/acpi/numa/Kconfig"
 source "drivers/acpi/apei/Kconfig"
@@ -545,6 +547,10 @@ if ARM64
 source "drivers/acpi/arm64/Kconfig"
 endif
 
+if RISCV
+source "drivers/acpi/riscv/Kconfig"
+endif
+
 config ACPI_PPTT
 	bool
 
@@ -575,6 +581,9 @@ config ACPI_FFH
 	  Enable this feature if you want to set up and install the FFH Address
 	  Space handler to handle FFH OpRegion in the firmware.
 
+config ACPI_MRRM
+	bool
+
 source "drivers/acpi/pmic/Kconfig"
 
 config ACPI_VIOT
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index eaa09bf52f17..d1b0affb844f 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -5,6 +5,10 @@
 
 ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
 
+ifdef CONFIG_TRACE_BRANCH_PROFILING
+CFLAGS_processor_idle.o += -DDISABLE_BRANCH_PROFILING
+endif
+
 #
 # ACPI Boot-Time Table Parsing
 #
@@ -14,7 +18,6 @@ tables.o: $(src)/../../include/$(CONFIG_ACPI_CUSTOM_DSDT_FILE) ;
 endif
 
 obj-$(CONFIG_ACPI)		+= tables.o
-obj-$(CONFIG_X86)		+= blacklist.o
 
 #
 # ACPI Core Subsystem (Interpreter)
@@ -37,16 +40,15 @@ acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 # ACPI Bus and Device Drivers
 #
 acpi-y				+= bus.o glue.o
-acpi-y				+= scan.o
+acpi-y				+= scan.o mipi-disco-img.o
 acpi-y				+= resource.o
 acpi-y				+= acpi_processor.o
 acpi-y				+= processor_core.o
 acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o
-acpi-y				+= ec.o
+acpi-$(CONFIG_ACPI_EC)		+= ec.o
 acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
 acpi-$(CONFIG_PCI)		+= pci_root.o pci_link.o pci_irq.o
 obj-$(CONFIG_ACPI_MCFG)		+= pci_mcfg.o
-acpi-$(CONFIG_PCI)		+= acpi_lpss.o
 acpi-y				+= acpi_apd.o
 acpi-y				+= acpi_platform.o
 acpi-y				+= acpi_pnp.o
@@ -55,10 +57,6 @@ acpi-y				+= event.o
 acpi-y				+= evged.o
 acpi-y				+= sysfs.o
 acpi-y				+= property.o
-acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
-acpi-$(CONFIG_X86)		+= x86/apple.o
-acpi-$(CONFIG_X86)		+= x86/utils.o
-acpi-$(CONFIG_X86)		+= x86/s2idle.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-y				+= acpi_lpat.o
 acpi-$(CONFIG_ACPI_FPDT)	+= acpi_fpdt.o
@@ -68,6 +66,7 @@ acpi-$(CONFIG_ACPI_WATCHDOG)	+= acpi_watchdog.o
 acpi-$(CONFIG_ACPI_PRMT)	+= prmt.o
 acpi-$(CONFIG_ACPI_PCC)		+= acpi_pcc.o
 acpi-$(CONFIG_ACPI_FFH)		+= acpi_ffh.o
+acpi-$(CONFIG_ACPI_MRRM)	+= acpi_mrrm.o
 
 # Address translation
 acpi-$(CONFIG_ACPI_ADXL)	+= acpi_adxl.o
@@ -83,15 +82,18 @@ obj-$(CONFIG_ACPI_TINY_POWER_BUTTON)	+= tiny-power-button.o
 obj-$(CONFIG_ACPI_FAN)		+= fan.o
 fan-objs			:= fan_core.o
 fan-objs			+= fan_attr.o
+fan-$(CONFIG_HWMON)		+= fan_hwmon.o
 
 obj-$(CONFIG_ACPI_VIDEO)	+= video.o
 obj-$(CONFIG_ACPI_TAD)		+= acpi_tad.o
 obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
 obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
+obj-$(CONFIG_ACPI_THERMAL_LIB)	+= thermal_lib.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_PLATFORM_PROFILE) 	+= platform_profile.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
+obj-$(CONFIG_ACPI_NHLT)		+= nhlt.o
 obj-$(CONFIG_ACPI_NUMA)		+= numa/
 obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
 obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
@@ -100,7 +102,6 @@ obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)		+= sbs.o
 obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
-obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
 obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_acpi.o
 obj-$(CONFIG_ACPI_SPCR_TABLE)	+= spcr.o
@@ -132,3 +133,4 @@ obj-$(CONFIG_ARM64)		+= arm64/
 obj-$(CONFIG_ACPI_VIOT)		+= viot.o
 
 obj-$(CONFIG_RISCV)		+= riscv/
+obj-$(CONFIG_X86)		+= x86/
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 2d4a35e6dd18..1f69be8f51a2 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -112,7 +112,7 @@ static int get_ac_property(struct power_supply *psy,
 	return 0;
 }
 
-static enum power_supply_property ac_props[] = {
+static const enum power_supply_property ac_props[] = {
 	POWER_SUPPLY_PROP_ONLINE,
 };
 
@@ -145,7 +145,7 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 						  dev_name(&adev->dev), event,
 						  (u32) ac->state);
 		acpi_notifier_call_chain(adev, event, (u32) ac->state);
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);
 	}
 }
 
@@ -213,8 +213,8 @@ static int acpi_ac_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ac->device = adev;
-	strcpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME);
-	strcpy(acpi_device_class(adev), ACPI_AC_CLASS);
+	strscpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME);
+	strscpy(acpi_device_class(adev), ACPI_AC_CLASS);
 
 	platform_set_drvdata(pdev, ac);
 
@@ -268,7 +268,7 @@ static int acpi_ac_resume(struct device *dev)
 	if (acpi_ac_get_state(ac))
 		return 0;
 	if (old_state != ac->state)
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);
 
 	return 0;
 }
@@ -290,7 +290,7 @@ static void acpi_ac_remove(struct platform_device *pdev)
 
 static struct platform_driver acpi_ac_driver = {
 	.probe = acpi_ac_probe,
-	.remove_new = acpi_ac_remove,
+	.remove = acpi_ac_remove,
 	.driver = {
 		.name = "ac",
 		.acpi_match_table = ac_device_ids,
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index 80f945cbec8a..49539f7528c6 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -86,7 +86,7 @@ static int fch_misc_setup(struct apd_private_data *pdata)
 		if (!clk_data->name)
 			return -ENOMEM;
 
-		strcpy(clk_data->name, obj->string.pointer);
+		strscpy(clk_data->name, obj->string.pointer, obj->string.length);
 	} else {
 		/* Set default name to mclk if entry missing in firmware */
 		clk_data->name = "mclk";
@@ -118,6 +118,11 @@ static const struct apd_device_desc wt_i2c_desc = {
 	.fixed_clk_rate = 150000000,
 };
 
+static const struct apd_device_desc wt_i3c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 125000000,
+};
+
 static struct property_entry uart_properties[] = {
 	PROPERTY_ENTRY_U32("reg-io-width", 4),
 	PROPERTY_ENTRY_U32("reg-shift", 2),
@@ -231,6 +236,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
 	{ "AMD0030", },
 	{ "AMD0040", APD_ADDR(fch_misc_desc)},
 	{ "AMDI0010", APD_ADDR(wt_i2c_desc) },
+	{ "AMDI0015", APD_ADDR(wt_i3c_desc) },
 	{ "AMDI0019", APD_ADDR(wt_i2c_desc) },
 	{ "AMDI0020", APD_ADDR(cz_uart_desc) },
 	{ "AMDI0022", APD_ADDR(cz_uart_desc) },
diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c
deleted file mode 100644
index 9b55d1593d16..000000000000
--- a/drivers/acpi/acpi_cmos_rtc.c
+++ /dev/null
@@ -1,98 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ACPI support for CMOS RTC Address Space access
- *
- * Copyright (C) 2013, Intel Corporation
- * Authors: Lan Tianyu <tianyu.lan@intel.com>
- */
-
-#define pr_fmt(fmt) "ACPI: " fmt
-
-#include <linux/acpi.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mc146818rtc.h>
-
-#include "internal.h"
-
-static const struct acpi_device_id acpi_cmos_rtc_ids[] = {
-	{ "PNP0B00" },
-	{ "PNP0B01" },
-	{ "PNP0B02" },
-	{}
-};
-
-static acpi_status
-acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address,
-		      u32 bits, u64 *value64,
-		      void *handler_context, void *region_context)
-{
-	int i;
-	u8 *value = (u8 *)value64;
-
-	if (address > 0xff || !value64)
-		return AE_BAD_PARAMETER;
-
-	if (function != ACPI_WRITE && function != ACPI_READ)
-		return AE_BAD_PARAMETER;
-
-	spin_lock_irq(&rtc_lock);
-
-	for (i = 0; i < DIV_ROUND_UP(bits, 8); ++i, ++address, ++value)
-		if (function == ACPI_READ)
-			*value = CMOS_READ(address);
-		else
-			CMOS_WRITE(*value, address);
-
-	spin_unlock_irq(&rtc_lock);
-
-	return AE_OK;
-}
-
-int acpi_install_cmos_rtc_space_handler(acpi_handle handle)
-{
-	acpi_status status;
-
-	status = acpi_install_address_space_handler(handle,
-			ACPI_ADR_SPACE_CMOS,
-			&acpi_cmos_rtc_space_handler,
-			NULL, NULL);
-	if (ACPI_FAILURE(status)) {
-		pr_err("Error installing CMOS-RTC region handler\n");
-		return -ENODEV;
-	}
-
-	return 1;
-}
-EXPORT_SYMBOL_GPL(acpi_install_cmos_rtc_space_handler);
-
-void acpi_remove_cmos_rtc_space_handler(acpi_handle handle)
-{
-	if (ACPI_FAILURE(acpi_remove_address_space_handler(handle,
-			ACPI_ADR_SPACE_CMOS, &acpi_cmos_rtc_space_handler)))
-		pr_err("Error removing CMOS-RTC region handler\n");
-}
-EXPORT_SYMBOL_GPL(acpi_remove_cmos_rtc_space_handler);
-
-static int acpi_cmos_rtc_attach_handler(struct acpi_device *adev, const struct acpi_device_id *id)
-{
-	return acpi_install_cmos_rtc_space_handler(adev->handle);
-}
-
-static void acpi_cmos_rtc_detach_handler(struct acpi_device *adev)
-{
-	acpi_remove_cmos_rtc_space_handler(adev->handle);
-}
-
-static struct acpi_scan_handler cmos_rtc_handler = {
-	.ids = acpi_cmos_rtc_ids,
-	.attach = acpi_cmos_rtc_attach_handler,
-	.detach = acpi_cmos_rtc_detach_handler,
-};
-
-void __init acpi_cmos_rtc_init(void)
-{
-	acpi_scan_add_handler(&cmos_rtc_handler);
-}
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index d50261d05f3a..515b20d0b698 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -569,11 +569,11 @@ static int acpi_aml_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int acpi_aml_read_user(char __user *buf, int len)
+static ssize_t acpi_aml_read_user(char __user *buf, size_t len)
 {
-	int ret;
 	struct circ_buf *crc = &acpi_aml_io.out_crc;
-	int n;
+	ssize_t ret;
+	size_t n;
 	char *p;
 
 	ret = acpi_aml_lock_read(crc, ACPI_AML_OUT_USER);
@@ -582,7 +582,7 @@ static int acpi_aml_read_user(char __user *buf, int len)
 	/* sync head before removing logs */
 	smp_rmb();
 	p = &crc->buf[crc->tail];
-	n = min(len, circ_count_to_end(crc));
+	n = min_t(size_t, len, circ_count_to_end(crc));
 	if (copy_to_user(buf, p, n)) {
 		ret = -EFAULT;
 		goto out;
@@ -599,8 +599,8 @@ out:
 static ssize_t acpi_aml_read(struct file *file, char __user *buf,
 			     size_t count, loff_t *ppos)
 {
-	int ret = 0;
-	int size = 0;
+	ssize_t ret = 0;
+	ssize_t size = 0;
 
 	if (!count)
 		return 0;
@@ -639,11 +639,11 @@ again:
 	return size > 0 ? size : ret;
 }
 
-static int acpi_aml_write_user(const char __user *buf, int len)
+static ssize_t acpi_aml_write_user(const char __user *buf, size_t len)
 {
-	int ret;
 	struct circ_buf *crc = &acpi_aml_io.in_crc;
-	int n;
+	ssize_t ret;
+	size_t n;
 	char *p;
 
 	ret = acpi_aml_lock_write(crc, ACPI_AML_IN_USER);
@@ -652,7 +652,7 @@ static int acpi_aml_write_user(const char __user *buf, int len)
 	/* sync tail before inserting cmds */
 	smp_mb();
 	p = &crc->buf[crc->head];
-	n = min(len, circ_space_to_end(crc));
+	n = min_t(size_t, len, circ_space_to_end(crc));
 	if (copy_from_user(p, buf, n)) {
 		ret = -EFAULT;
 		goto out;
@@ -663,14 +663,14 @@ static int acpi_aml_write_user(const char __user *buf, int len)
 	ret = n;
 out:
 	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0);
-	return n;
+	return ret;
 }
 
 static ssize_t acpi_aml_write(struct file *file, const char __user *buf,
 			      size_t count, loff_t *ppos)
 {
-	int ret = 0;
-	int size = 0;
+	ssize_t ret = 0;
+	ssize_t size = 0;
 
 	if (!count)
 		return 0;
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index e120a96e1eae..f6b9562779de 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -15,6 +15,7 @@
 #include <acpi/ghes.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
+#include <asm/msr.h>
 
 #include "apei/apei-internal.h"
 #include <ras/ras_event.h>
@@ -145,9 +146,14 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
-	if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC))
+	if (!estatus)
 		return NOTIFY_DONE;
 
+	if (mce->kflags & MCE_HANDLED_CEC) {
+		estatus->block_status = 0;
+		return NOTIFY_DONE;
+	}
+
 	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
@@ -229,7 +235,7 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
-	if (rdmsrl_safe(MSR_IA32_MCG_CAP, &cap) ||
+	if (rdmsrq_safe(MSR_IA32_MCG_CAP, &cap) ||
 	    !(cap & MCG_ELOG_P) ||
 	    !extlog_get_l1addr())
 		return -ENODEV;
@@ -246,6 +252,10 @@ static int __init extlog_init(void)
 	}
 
 	extlog_l1_hdr = acpi_os_map_iomem(l1_dirbase, l1_hdr_size);
+	if (!extlog_l1_hdr) {
+		rc = -ENOMEM;
+		goto err_release_l1_hdr;
+	}
 	l1_head = (struct extlog_l1_head *)extlog_l1_hdr;
 	l1_size = l1_head->total_len;
 	l1_percpu_entry = l1_head->entries;
@@ -263,6 +273,10 @@ static int __init extlog_init(void)
 		goto err;
 	}
 	extlog_l1_addr = acpi_os_map_iomem(l1_dirbase, l1_size);
+	if (!extlog_l1_addr) {
+		rc = -ENOMEM;
+		goto err_release_l1_dir;
+	}
 	l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size);
 
 	/* remap elog table */
@@ -274,6 +288,10 @@ static int __init extlog_init(void)
 		goto err_release_l1_dir;
 	}
 	elog_addr = acpi_os_map_iomem(elog_base, elog_size);
+	if (!elog_addr) {
+		rc = -ENOMEM;
+		goto err_release_elog;
+	}
 
 	rc = -ENOMEM;
 	/* allocate buffer to save elog record */
@@ -295,6 +313,8 @@ err_release_l1_dir:
 	if (extlog_l1_addr)
 		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
 	release_mem_region(l1_dirbase, l1_size);
+err_release_l1_hdr:
+	release_mem_region(l1_dirbase, l1_hdr_size);
 err:
 	pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n");
 	return rc;
@@ -303,9 +323,10 @@ err:
 static void __exit extlog_exit(void)
 {
 	mce_unregister_decode_chain(&extlog_mce_dec);
-	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
-	if (extlog_l1_addr)
+	if (extlog_l1_addr) {
+		((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
+	}
 	if (elog_addr)
 		acpi_os_unmap_iomem(elog_addr, elog_size);
 	release_mem_region(elog_base, elog_size);
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index 0555f68c2dfd..5fba4dab5d08 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -22,6 +22,8 @@ MODULE_LICENSE("GPL");
 /* the IPMI timeout is 5s */
 #define IPMI_TIMEOUT			(5000)
 #define ACPI_IPMI_MAX_MSG_LENGTH	64
+/* 2s should be suffient for SMI being selected */
+#define ACPI_IPMI_SMI_SELECTION_TIMEOUT	(2 * HZ)
 
 struct acpi_ipmi_device {
 	/* the device list attached to driver_data.ipmi_devices */
@@ -54,6 +56,7 @@ struct ipmi_driver_data {
 	 * to this selected global IPMI system interface.
 	 */
 	struct acpi_ipmi_device *selected_smi;
+	struct completion smi_selection_done;
 };
 
 struct acpi_ipmi_msg {
@@ -463,8 +466,10 @@ static void ipmi_register_bmc(int iface, struct device *dev)
 		if (temp->handle == handle)
 			goto err_lock;
 	}
-	if (!driver_data.selected_smi)
+	if (!driver_data.selected_smi) {
 		driver_data.selected_smi = ipmi_device;
+		complete(&driver_data.smi_selection_done);
+	}
 	list_add_tail(&ipmi_device->head, &driver_data.ipmi_devices);
 	mutex_unlock(&driver_data.ipmi_lock);
 
@@ -578,6 +583,20 @@ out_msg:
 	return status;
 }
 
+int acpi_wait_for_acpi_ipmi(void)
+{
+	long ret;
+
+	ret = wait_for_completion_interruptible_timeout(&driver_data.smi_selection_done,
+							ACPI_IPMI_SMI_SELECTION_TIMEOUT);
+
+	if (ret <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_wait_for_acpi_ipmi);
+
 static int __init acpi_ipmi_init(void)
 {
 	int result;
@@ -586,6 +605,8 @@ static int __init acpi_ipmi_init(void)
 	if (acpi_disabled)
 		return 0;
 
+	init_completion(&driver_data.smi_selection_done);
+
 	status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT,
 						    ACPI_ADR_SPACE_IPMI,
 						    &acpi_ipmi_space_handler,
diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c
index c5598b6d5db8..b8d98b1b48ae 100644
--- a/drivers/acpi/acpi_lpit.c
+++ b/drivers/acpi/acpi_lpit.c
@@ -39,7 +39,7 @@ static int lpit_read_residency_counter_us(u64 *counter, bool io_mem)
 		return 0;
 	}
 
-	err = rdmsrl_safe(residency_info_ffh.gaddr.address, counter);
+	err = rdmsrq_safe(residency_info_ffh.gaddr.address, counter);
 	if (!err) {
 		u64 mask = GENMASK_ULL(residency_info_ffh.gaddr.bit_offset +
 				       residency_info_ffh.gaddr. bit_width - 1,
@@ -105,7 +105,7 @@ static void lpit_update_residency(struct lpit_residency_info *info,
 		return;
 
 	info->frequency = lpit_native->counter_frequency ?
-				lpit_native->counter_frequency : tsc_khz * 1000;
+				lpit_native->counter_frequency : mul_u32_u32(tsc_khz, 1000U);
 	if (!info->frequency)
 		info->frequency = 1;
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
deleted file mode 100644
index 875de44961bf..000000000000
--- a/drivers/acpi/acpi_lpss.c
+++ /dev/null
@@ -1,1391 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ACPI support for Intel Lynxpoint LPSS.
- *
- * Copyright (C) 2013, Intel Corporation
- * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
- *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- */
-
-#include <linux/acpi.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
-#include <linux/dmi.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-#include <linux/platform_data/x86/clk-lpss.h>
-#include <linux/platform_data/x86/pmc_atom.h>
-#include <linux/pm_domain.h>
-#include <linux/pm_runtime.h>
-#include <linux/pwm.h>
-#include <linux/pxa2xx_ssp.h>
-#include <linux/suspend.h>
-#include <linux/delay.h>
-
-#include "internal.h"
-
-#ifdef CONFIG_X86_INTEL_LPSS
-
-#include <asm/cpu_device_id.h>
-#include <asm/intel-family.h>
-#include <asm/iosf_mbi.h>
-
-#define LPSS_ADDR(desc) ((unsigned long)&desc)
-
-#define LPSS_CLK_SIZE	0x04
-#define LPSS_LTR_SIZE	0x18
-
-/* Offsets relative to LPSS_PRIVATE_OFFSET */
-#define LPSS_CLK_DIVIDER_DEF_MASK	(BIT(1) | BIT(16))
-#define LPSS_RESETS			0x04
-#define LPSS_RESETS_RESET_FUNC		BIT(0)
-#define LPSS_RESETS_RESET_APB		BIT(1)
-#define LPSS_GENERAL			0x08
-#define LPSS_GENERAL_LTR_MODE_SW	BIT(2)
-#define LPSS_GENERAL_UART_RTS_OVRD	BIT(3)
-#define LPSS_SW_LTR			0x10
-#define LPSS_AUTO_LTR			0x14
-#define LPSS_LTR_SNOOP_REQ		BIT(15)
-#define LPSS_LTR_SNOOP_MASK		0x0000FFFF
-#define LPSS_LTR_SNOOP_LAT_1US		0x800
-#define LPSS_LTR_SNOOP_LAT_32US		0xC00
-#define LPSS_LTR_SNOOP_LAT_SHIFT	5
-#define LPSS_LTR_SNOOP_LAT_CUTOFF	3000
-#define LPSS_LTR_MAX_VAL		0x3FF
-#define LPSS_TX_INT			0x20
-#define LPSS_TX_INT_MASK		BIT(1)
-
-#define LPSS_PRV_REG_COUNT		9
-
-/* LPSS Flags */
-#define LPSS_CLK			BIT(0)
-#define LPSS_CLK_GATE			BIT(1)
-#define LPSS_CLK_DIVIDER		BIT(2)
-#define LPSS_LTR			BIT(3)
-#define LPSS_SAVE_CTX			BIT(4)
-/*
- * For some devices the DSDT AML code for another device turns off the device
- * before our suspend handler runs, causing us to read/save all 1-s (0xffffffff)
- * as ctx register values.
- * Luckily these devices always use the same ctx register values, so we can
- * work around this by saving the ctx registers once on activation.
- */
-#define LPSS_SAVE_CTX_ONCE		BIT(5)
-#define LPSS_NO_D3_DELAY		BIT(6)
-
-struct lpss_private_data;
-
-struct lpss_device_desc {
-	unsigned int flags;
-	const char *clk_con_id;
-	unsigned int prv_offset;
-	size_t prv_size_override;
-	const struct property_entry *properties;
-	void (*setup)(struct lpss_private_data *pdata);
-	bool resume_from_noirq;
-};
-
-static const struct lpss_device_desc lpss_dma_desc = {
-	.flags = LPSS_CLK,
-};
-
-struct lpss_private_data {
-	struct acpi_device *adev;
-	void __iomem *mmio_base;
-	resource_size_t mmio_size;
-	unsigned int fixed_clk_rate;
-	struct clk *clk;
-	const struct lpss_device_desc *dev_desc;
-	u32 prv_reg_ctx[LPSS_PRV_REG_COUNT];
-};
-
-/* Devices which need to be in D3 before lpss_iosf_enter_d3_state() proceeds */
-static u32 pmc_atom_d3_mask = 0xfe000ffe;
-
-/* LPSS run time quirks */
-static unsigned int lpss_quirks;
-
-/*
- * LPSS_QUIRK_ALWAYS_POWER_ON: override power state for LPSS DMA device.
- *
- * The LPSS DMA controller has neither _PS0 nor _PS3 method. Moreover
- * it can be powered off automatically whenever the last LPSS device goes down.
- * In case of no power any access to the DMA controller will hang the system.
- * The behaviour is reproduced on some HP laptops based on Intel BayTrail as
- * well as on ASuS T100TA transformer.
- *
- * This quirk overrides power state of entire LPSS island to keep DMA powered
- * on whenever we have at least one other device in use.
- */
-#define LPSS_QUIRK_ALWAYS_POWER_ON	BIT(0)
-
-/* UART Component Parameter Register */
-#define LPSS_UART_CPR			0xF4
-#define LPSS_UART_CPR_AFCE		BIT(4)
-
-static void lpss_uart_setup(struct lpss_private_data *pdata)
-{
-	unsigned int offset;
-	u32 val;
-
-	offset = pdata->dev_desc->prv_offset + LPSS_TX_INT;
-	val = readl(pdata->mmio_base + offset);
-	writel(val | LPSS_TX_INT_MASK, pdata->mmio_base + offset);
-
-	val = readl(pdata->mmio_base + LPSS_UART_CPR);
-	if (!(val & LPSS_UART_CPR_AFCE)) {
-		offset = pdata->dev_desc->prv_offset + LPSS_GENERAL;
-		val = readl(pdata->mmio_base + offset);
-		val |= LPSS_GENERAL_UART_RTS_OVRD;
-		writel(val, pdata->mmio_base + offset);
-	}
-}
-
-static void lpss_deassert_reset(struct lpss_private_data *pdata)
-{
-	unsigned int offset;
-	u32 val;
-
-	offset = pdata->dev_desc->prv_offset + LPSS_RESETS;
-	val = readl(pdata->mmio_base + offset);
-	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
-	writel(val, pdata->mmio_base + offset);
-}
-
-/*
- * BYT PWM used for backlight control by the i915 driver on systems without
- * the Crystal Cove PMIC.
- */
-static struct pwm_lookup byt_pwm_lookup[] = {
-	PWM_LOOKUP_WITH_MODULE("80860F09:00", 0, "0000:00:02.0",
-			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
-			       "pwm-lpss-platform"),
-};
-
-static void byt_pwm_setup(struct lpss_private_data *pdata)
-{
-	u64 uid;
-
-	/* Only call pwm_add_table for the first PWM controller */
-	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
-		return;
-
-	pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
-}
-
-#define LPSS_I2C_ENABLE			0x6c
-
-static void byt_i2c_setup(struct lpss_private_data *pdata)
-{
-	acpi_handle handle = pdata->adev->handle;
-	unsigned long long shared_host = 0;
-	acpi_status status;
-	u64 uid;
-
-	/* Expected to always be successfull, but better safe then sorry */
-	if (!acpi_dev_uid_to_integer(pdata->adev, &uid) && uid) {
-		/* Detect I2C bus shared with PUNIT and ignore its d3 status */
-		status = acpi_evaluate_integer(handle, "_SEM", NULL, &shared_host);
-		if (ACPI_SUCCESS(status) && shared_host)
-			pmc_atom_d3_mask &= ~(BIT_LPSS2_F1_I2C1 << (uid - 1));
-	}
-
-	lpss_deassert_reset(pdata);
-
-	if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset))
-		pdata->fixed_clk_rate = 133000000;
-
-	writel(0, pdata->mmio_base + LPSS_I2C_ENABLE);
-}
-
-/*
- * BSW PWM1 is used for backlight control by the i915 driver
- * BSW PWM2 is used for backlight control for fixed (etched into the glass)
- * touch controls on some models. These touch-controls have specialized
- * drivers which know they need the "pwm_soc_lpss_2" con-id.
- */
-static struct pwm_lookup bsw_pwm_lookup[] = {
-	PWM_LOOKUP_WITH_MODULE("80862288:00", 0, "0000:00:02.0",
-			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
-			       "pwm-lpss-platform"),
-	PWM_LOOKUP_WITH_MODULE("80862289:00", 0, NULL,
-			       "pwm_soc_lpss_2", 0, PWM_POLARITY_NORMAL,
-			       "pwm-lpss-platform"),
-};
-
-static void bsw_pwm_setup(struct lpss_private_data *pdata)
-{
-	u64 uid;
-
-	/* Only call pwm_add_table for the first PWM controller */
-	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
-		return;
-
-	pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
-}
-
-static const struct property_entry lpt_spi_properties[] = {
-	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_LPT_SSP),
-	{ }
-};
-
-static const struct lpss_device_desc lpt_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR
-			| LPSS_SAVE_CTX,
-	.prv_offset = 0x800,
-	.properties = lpt_spi_properties,
-};
-
-static const struct lpss_device_desc lpt_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_LTR | LPSS_SAVE_CTX,
-	.prv_offset = 0x800,
-};
-
-static struct property_entry uart_properties[] = {
-	PROPERTY_ENTRY_U32("reg-io-width", 4),
-	PROPERTY_ENTRY_U32("reg-shift", 2),
-	PROPERTY_ENTRY_BOOL("snps,uart-16550-compatible"),
-	{ },
-};
-
-static const struct lpss_device_desc lpt_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR
-			| LPSS_SAVE_CTX,
-	.clk_con_id = "baudclk",
-	.prv_offset = 0x800,
-	.setup = lpss_uart_setup,
-	.properties = uart_properties,
-};
-
-static const struct lpss_device_desc lpt_sdio_dev_desc = {
-	.flags = LPSS_LTR,
-	.prv_offset = 0x1000,
-	.prv_size_override = 0x1018,
-};
-
-static const struct lpss_device_desc byt_pwm_dev_desc = {
-	.flags = LPSS_SAVE_CTX,
-	.prv_offset = 0x800,
-	.setup = byt_pwm_setup,
-};
-
-static const struct lpss_device_desc bsw_pwm_dev_desc = {
-	.flags = LPSS_SAVE_CTX_ONCE | LPSS_NO_D3_DELAY,
-	.prv_offset = 0x800,
-	.setup = bsw_pwm_setup,
-	.resume_from_noirq = true,
-};
-
-static const struct lpss_device_desc bsw_pwm2_dev_desc = {
-	.flags = LPSS_SAVE_CTX_ONCE | LPSS_NO_D3_DELAY,
-	.prv_offset = 0x800,
-	.resume_from_noirq = true,
-};
-
-static const struct lpss_device_desc byt_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
-	.clk_con_id = "baudclk",
-	.prv_offset = 0x800,
-	.setup = lpss_uart_setup,
-	.properties = uart_properties,
-};
-
-static const struct lpss_device_desc bsw_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
-			| LPSS_NO_D3_DELAY,
-	.clk_con_id = "baudclk",
-	.prv_offset = 0x800,
-	.setup = lpss_uart_setup,
-	.properties = uart_properties,
-};
-
-static const struct property_entry byt_spi_properties[] = {
-	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BYT_SSP),
-	{ }
-};
-
-static const struct lpss_device_desc byt_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
-	.prv_offset = 0x400,
-	.properties = byt_spi_properties,
-};
-
-static const struct lpss_device_desc byt_sdio_dev_desc = {
-	.flags = LPSS_CLK,
-};
-
-static const struct lpss_device_desc byt_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_SAVE_CTX,
-	.prv_offset = 0x800,
-	.setup = byt_i2c_setup,
-	.resume_from_noirq = true,
-};
-
-static const struct lpss_device_desc bsw_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_NO_D3_DELAY,
-	.prv_offset = 0x800,
-	.setup = byt_i2c_setup,
-	.resume_from_noirq = true,
-};
-
-static const struct property_entry bsw_spi_properties[] = {
-	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BSW_SSP),
-	{ }
-};
-
-static const struct lpss_device_desc bsw_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
-			| LPSS_NO_D3_DELAY,
-	.prv_offset = 0x400,
-	.setup = lpss_deassert_reset,
-	.properties = bsw_spi_properties,
-};
-
-static const struct x86_cpu_id lpss_cpu_ids[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	NULL),
-	{}
-};
-
-#else
-
-#define LPSS_ADDR(desc) (0UL)
-
-#endif /* CONFIG_X86_INTEL_LPSS */
-
-static const struct acpi_device_id acpi_lpss_device_ids[] = {
-	/* Generic LPSS devices */
-	{ "INTL9C60", LPSS_ADDR(lpss_dma_desc) },
-
-	/* Lynxpoint LPSS devices */
-	{ "INT33C0", LPSS_ADDR(lpt_spi_dev_desc) },
-	{ "INT33C1", LPSS_ADDR(lpt_spi_dev_desc) },
-	{ "INT33C2", LPSS_ADDR(lpt_i2c_dev_desc) },
-	{ "INT33C3", LPSS_ADDR(lpt_i2c_dev_desc) },
-	{ "INT33C4", LPSS_ADDR(lpt_uart_dev_desc) },
-	{ "INT33C5", LPSS_ADDR(lpt_uart_dev_desc) },
-	{ "INT33C6", LPSS_ADDR(lpt_sdio_dev_desc) },
-
-	/* BayTrail LPSS devices */
-	{ "80860F09", LPSS_ADDR(byt_pwm_dev_desc) },
-	{ "80860F0A", LPSS_ADDR(byt_uart_dev_desc) },
-	{ "80860F0E", LPSS_ADDR(byt_spi_dev_desc) },
-	{ "80860F14", LPSS_ADDR(byt_sdio_dev_desc) },
-	{ "80860F41", LPSS_ADDR(byt_i2c_dev_desc) },
-
-	/* Braswell LPSS devices */
-	{ "80862286", LPSS_ADDR(lpss_dma_desc) },
-	{ "80862288", LPSS_ADDR(bsw_pwm_dev_desc) },
-	{ "80862289", LPSS_ADDR(bsw_pwm2_dev_desc) },
-	{ "8086228A", LPSS_ADDR(bsw_uart_dev_desc) },
-	{ "8086228E", LPSS_ADDR(bsw_spi_dev_desc) },
-	{ "808622C0", LPSS_ADDR(lpss_dma_desc) },
-	{ "808622C1", LPSS_ADDR(bsw_i2c_dev_desc) },
-
-	/* Broadwell LPSS devices */
-	{ "INT3430", LPSS_ADDR(lpt_spi_dev_desc) },
-	{ "INT3431", LPSS_ADDR(lpt_spi_dev_desc) },
-	{ "INT3432", LPSS_ADDR(lpt_i2c_dev_desc) },
-	{ "INT3433", LPSS_ADDR(lpt_i2c_dev_desc) },
-	{ "INT3434", LPSS_ADDR(lpt_uart_dev_desc) },
-	{ "INT3435", LPSS_ADDR(lpt_uart_dev_desc) },
-	{ "INT3436", LPSS_ADDR(lpt_sdio_dev_desc) },
-
-	/* Wildcat Point LPSS devices */
-	{ "INT3438", LPSS_ADDR(lpt_spi_dev_desc) },
-
-	{ }
-};
-
-#ifdef CONFIG_X86_INTEL_LPSS
-
-/* LPSS main clock device. */
-static struct platform_device *lpss_clk_dev;
-
-static inline void lpt_register_clock_device(void)
-{
-	lpss_clk_dev = platform_device_register_simple("clk-lpss-atom",
-						       PLATFORM_DEVID_NONE,
-						       NULL, 0);
-}
-
-static int register_device_clock(struct acpi_device *adev,
-				 struct lpss_private_data *pdata)
-{
-	const struct lpss_device_desc *dev_desc = pdata->dev_desc;
-	const char *devname = dev_name(&adev->dev);
-	struct clk *clk;
-	struct lpss_clk_data *clk_data;
-	const char *parent, *clk_name;
-	void __iomem *prv_base;
-
-	if (!lpss_clk_dev)
-		lpt_register_clock_device();
-
-	if (IS_ERR(lpss_clk_dev))
-		return PTR_ERR(lpss_clk_dev);
-
-	clk_data = platform_get_drvdata(lpss_clk_dev);
-	if (!clk_data)
-		return -ENODEV;
-	clk = clk_data->clk;
-
-	if (!pdata->mmio_base
-	    || pdata->mmio_size < dev_desc->prv_offset + LPSS_CLK_SIZE)
-		return -ENODATA;
-
-	parent = clk_data->name;
-	prv_base = pdata->mmio_base + dev_desc->prv_offset;
-
-	if (pdata->fixed_clk_rate) {
-		clk = clk_register_fixed_rate(NULL, devname, parent, 0,
-					      pdata->fixed_clk_rate);
-		goto out;
-	}
-
-	if (dev_desc->flags & LPSS_CLK_GATE) {
-		clk = clk_register_gate(NULL, devname, parent, 0,
-					prv_base, 0, 0, NULL);
-		parent = devname;
-	}
-
-	if (dev_desc->flags & LPSS_CLK_DIVIDER) {
-		/* Prevent division by zero */
-		if (!readl(prv_base))
-			writel(LPSS_CLK_DIVIDER_DEF_MASK, prv_base);
-
-		clk_name = kasprintf(GFP_KERNEL, "%s-div", devname);
-		if (!clk_name)
-			return -ENOMEM;
-		clk = clk_register_fractional_divider(NULL, clk_name, parent,
-						      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
-						      prv_base, 1, 15, 16, 15, 0, NULL);
-		parent = clk_name;
-
-		clk_name = kasprintf(GFP_KERNEL, "%s-update", devname);
-		if (!clk_name) {
-			kfree(parent);
-			return -ENOMEM;
-		}
-		clk = clk_register_gate(NULL, clk_name, parent,
-					CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
-					prv_base, 31, 0, NULL);
-		kfree(parent);
-		kfree(clk_name);
-	}
-out:
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
-
-	pdata->clk = clk;
-	clk_register_clkdev(clk, dev_desc->clk_con_id, devname);
-	return 0;
-}
-
-struct lpss_device_links {
-	const char *supplier_hid;
-	const char *supplier_uid;
-	const char *consumer_hid;
-	const char *consumer_uid;
-	u32 flags;
-	const struct dmi_system_id *dep_missing_ids;
-};
-
-/* Please keep this list sorted alphabetically by vendor and model */
-static const struct dmi_system_id i2c1_dep_missing_dmi_ids[] = {
-	{
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
-		},
-	},
-	{}
-};
-
-/*
- * The _DEP method is used to identify dependencies but instead of creating
- * device links for every handle in _DEP, only links in the following list are
- * created. That is necessary because, in the general case, _DEP can refer to
- * devices that might not have drivers, or that are on different buses, or where
- * the supplier is not enumerated until after the consumer is probed.
- */
-static const struct lpss_device_links lpss_device_links[] = {
-	/* CHT External sdcard slot controller depends on PMIC I2C ctrl */
-	{"808622C1", "7", "80860F14", "3", DL_FLAG_PM_RUNTIME},
-	/* CHT iGPU depends on PMIC I2C controller */
-	{"808622C1", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
-	/* BYT iGPU depends on the Embedded Controller I2C controller (UID 1) */
-	{"80860F41", "1", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME,
-	 i2c1_dep_missing_dmi_ids},
-	/* BYT CR iGPU depends on PMIC I2C controller (UID 5 on CR) */
-	{"80860F41", "5", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
-	/* BYT iGPU depends on PMIC I2C controller (UID 7 on non CR) */
-	{"80860F41", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
-};
-
-static bool acpi_lpss_is_supplier(struct acpi_device *adev,
-				  const struct lpss_device_links *link)
-{
-	return acpi_dev_hid_uid_match(adev, link->supplier_hid, link->supplier_uid);
-}
-
-static bool acpi_lpss_is_consumer(struct acpi_device *adev,
-				  const struct lpss_device_links *link)
-{
-	return acpi_dev_hid_uid_match(adev, link->consumer_hid, link->consumer_uid);
-}
-
-struct hid_uid {
-	const char *hid;
-	const char *uid;
-};
-
-static int match_hid_uid(struct device *dev, const void *data)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const struct hid_uid *id = data;
-
-	if (!adev)
-		return 0;
-
-	return acpi_dev_hid_uid_match(adev, id->hid, id->uid);
-}
-
-static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
-{
-	struct device *dev;
-
-	struct hid_uid data = {
-		.hid = hid,
-		.uid = uid,
-	};
-
-	dev = bus_find_device(&platform_bus_type, NULL, &data, match_hid_uid);
-	if (dev)
-		return dev;
-
-	return bus_find_device(&pci_bus_type, NULL, &data, match_hid_uid);
-}
-
-static bool acpi_lpss_dep(struct acpi_device *adev, acpi_handle handle)
-{
-	struct acpi_handle_list dep_devices;
-	acpi_status status;
-	bool ret = false;
-	int i;
-
-	if (!acpi_has_method(adev->handle, "_DEP"))
-		return false;
-
-	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
-					 &dep_devices);
-	if (ACPI_FAILURE(status)) {
-		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
-		return false;
-	}
-
-	for (i = 0; i < dep_devices.count; i++) {
-		if (dep_devices.handles[i] == handle) {
-			ret = true;
-			break;
-		}
-	}
-
-	acpi_handle_list_free(&dep_devices);
-	return ret;
-}
-
-static void acpi_lpss_link_consumer(struct device *dev1,
-				    const struct lpss_device_links *link)
-{
-	struct device *dev2;
-
-	dev2 = acpi_lpss_find_device(link->consumer_hid, link->consumer_uid);
-	if (!dev2)
-		return;
-
-	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
-		device_link_add(dev2, dev1, link->flags);
-
-	put_device(dev2);
-}
-
-static void acpi_lpss_link_supplier(struct device *dev1,
-				    const struct lpss_device_links *link)
-{
-	struct device *dev2;
-
-	dev2 = acpi_lpss_find_device(link->supplier_hid, link->supplier_uid);
-	if (!dev2)
-		return;
-
-	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
-		device_link_add(dev1, dev2, link->flags);
-
-	put_device(dev2);
-}
-
-static void acpi_lpss_create_device_links(struct acpi_device *adev,
-					  struct platform_device *pdev)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(lpss_device_links); i++) {
-		const struct lpss_device_links *link = &lpss_device_links[i];
-
-		if (acpi_lpss_is_supplier(adev, link))
-			acpi_lpss_link_consumer(&pdev->dev, link);
-
-		if (acpi_lpss_is_consumer(adev, link))
-			acpi_lpss_link_supplier(&pdev->dev, link);
-	}
-}
-
-static int acpi_lpss_create_device(struct acpi_device *adev,
-				   const struct acpi_device_id *id)
-{
-	const struct lpss_device_desc *dev_desc;
-	struct lpss_private_data *pdata;
-	struct resource_entry *rentry;
-	struct list_head resource_list;
-	struct platform_device *pdev;
-	int ret;
-
-	dev_desc = (const struct lpss_device_desc *)id->driver_data;
-	if (!dev_desc)
-		return -EINVAL;
-
-	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_memory_resources(adev, &resource_list);
-	if (ret < 0)
-		goto err_out;
-
-	rentry = list_first_entry_or_null(&resource_list, struct resource_entry, node);
-	if (rentry) {
-		if (dev_desc->prv_size_override)
-			pdata->mmio_size = dev_desc->prv_size_override;
-		else
-			pdata->mmio_size = resource_size(rentry->res);
-		pdata->mmio_base = ioremap(rentry->res->start, pdata->mmio_size);
-	}
-
-	acpi_dev_free_resource_list(&resource_list);
-
-	if (!pdata->mmio_base) {
-		/* Avoid acpi_bus_attach() instantiating a pdev for this dev. */
-		adev->pnp.type.platform_id = 0;
-		goto out_free;
-	}
-
-	pdata->adev = adev;
-	pdata->dev_desc = dev_desc;
-
-	if (dev_desc->setup)
-		dev_desc->setup(pdata);
-
-	if (dev_desc->flags & LPSS_CLK) {
-		ret = register_device_clock(adev, pdata);
-		if (ret)
-			goto out_free;
-	}
-
-	/*
-	 * This works around a known issue in ACPI tables where LPSS devices
-	 * have _PS0 and _PS3 without _PSC (and no power resources), so
-	 * acpi_bus_init_power() will assume that the BIOS has put them into D0.
-	 */
-	acpi_device_fix_up_power(adev);
-
-	adev->driver_data = pdata;
-	pdev = acpi_create_platform_device(adev, dev_desc->properties);
-	if (IS_ERR_OR_NULL(pdev)) {
-		adev->driver_data = NULL;
-		ret = PTR_ERR(pdev);
-		goto err_out;
-	}
-
-	acpi_lpss_create_device_links(adev, pdev);
-	return 1;
-
-out_free:
-	/* Skip the device, but continue the namespace scan */
-	ret = 0;
-err_out:
-	kfree(pdata);
-	return ret;
-}
-
-static u32 __lpss_reg_read(struct lpss_private_data *pdata, unsigned int reg)
-{
-	return readl(pdata->mmio_base + pdata->dev_desc->prv_offset + reg);
-}
-
-static void __lpss_reg_write(u32 val, struct lpss_private_data *pdata,
-			     unsigned int reg)
-{
-	writel(val, pdata->mmio_base + pdata->dev_desc->prv_offset + reg);
-}
-
-static int lpss_reg_read(struct device *dev, unsigned int reg, u32 *val)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	struct lpss_private_data *pdata;
-	unsigned long flags;
-	int ret;
-
-	if (WARN_ON(!adev))
-		return -ENODEV;
-
-	spin_lock_irqsave(&dev->power.lock, flags);
-	if (pm_runtime_suspended(dev)) {
-		ret = -EAGAIN;
-		goto out;
-	}
-	pdata = acpi_driver_data(adev);
-	if (WARN_ON(!pdata || !pdata->mmio_base)) {
-		ret = -ENODEV;
-		goto out;
-	}
-	*val = __lpss_reg_read(pdata, reg);
-	ret = 0;
-
- out:
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-	return ret;
-}
-
-static ssize_t lpss_ltr_show(struct device *dev, struct device_attribute *attr,
-			     char *buf)
-{
-	u32 ltr_value = 0;
-	unsigned int reg;
-	int ret;
-
-	reg = strcmp(attr->attr.name, "auto_ltr") ? LPSS_SW_LTR : LPSS_AUTO_LTR;
-	ret = lpss_reg_read(dev, reg, &ltr_value);
-	if (ret)
-		return ret;
-
-	return sysfs_emit(buf, "%08x\n", ltr_value);
-}
-
-static ssize_t lpss_ltr_mode_show(struct device *dev,
-				  struct device_attribute *attr, char *buf)
-{
-	u32 ltr_mode = 0;
-	char *outstr;
-	int ret;
-
-	ret = lpss_reg_read(dev, LPSS_GENERAL, &ltr_mode);
-	if (ret)
-		return ret;
-
-	outstr = (ltr_mode & LPSS_GENERAL_LTR_MODE_SW) ? "sw" : "auto";
-	return sprintf(buf, "%s\n", outstr);
-}
-
-static DEVICE_ATTR(auto_ltr, S_IRUSR, lpss_ltr_show, NULL);
-static DEVICE_ATTR(sw_ltr, S_IRUSR, lpss_ltr_show, NULL);
-static DEVICE_ATTR(ltr_mode, S_IRUSR, lpss_ltr_mode_show, NULL);
-
-static struct attribute *lpss_attrs[] = {
-	&dev_attr_auto_ltr.attr,
-	&dev_attr_sw_ltr.attr,
-	&dev_attr_ltr_mode.attr,
-	NULL,
-};
-
-static const struct attribute_group lpss_attr_group = {
-	.attrs = lpss_attrs,
-	.name = "lpss_ltr",
-};
-
-static void acpi_lpss_set_ltr(struct device *dev, s32 val)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	u32 ltr_mode, ltr_val;
-
-	ltr_mode = __lpss_reg_read(pdata, LPSS_GENERAL);
-	if (val < 0) {
-		if (ltr_mode & LPSS_GENERAL_LTR_MODE_SW) {
-			ltr_mode &= ~LPSS_GENERAL_LTR_MODE_SW;
-			__lpss_reg_write(ltr_mode, pdata, LPSS_GENERAL);
-		}
-		return;
-	}
-	ltr_val = __lpss_reg_read(pdata, LPSS_SW_LTR) & ~LPSS_LTR_SNOOP_MASK;
-	if (val >= LPSS_LTR_SNOOP_LAT_CUTOFF) {
-		ltr_val |= LPSS_LTR_SNOOP_LAT_32US;
-		val = LPSS_LTR_MAX_VAL;
-	} else if (val > LPSS_LTR_MAX_VAL) {
-		ltr_val |= LPSS_LTR_SNOOP_LAT_32US | LPSS_LTR_SNOOP_REQ;
-		val >>= LPSS_LTR_SNOOP_LAT_SHIFT;
-	} else {
-		ltr_val |= LPSS_LTR_SNOOP_LAT_1US | LPSS_LTR_SNOOP_REQ;
-	}
-	ltr_val |= val;
-	__lpss_reg_write(ltr_val, pdata, LPSS_SW_LTR);
-	if (!(ltr_mode & LPSS_GENERAL_LTR_MODE_SW)) {
-		ltr_mode |= LPSS_GENERAL_LTR_MODE_SW;
-		__lpss_reg_write(ltr_mode, pdata, LPSS_GENERAL);
-	}
-}
-
-#ifdef CONFIG_PM
-/**
- * acpi_lpss_save_ctx() - Save the private registers of LPSS device
- * @dev: LPSS device
- * @pdata: pointer to the private data of the LPSS device
- *
- * Most LPSS devices have private registers which may loose their context when
- * the device is powered down. acpi_lpss_save_ctx() saves those registers into
- * prv_reg_ctx array.
- */
-static void acpi_lpss_save_ctx(struct device *dev,
-			       struct lpss_private_data *pdata)
-{
-	unsigned int i;
-
-	for (i = 0; i < LPSS_PRV_REG_COUNT; i++) {
-		unsigned long offset = i * sizeof(u32);
-
-		pdata->prv_reg_ctx[i] = __lpss_reg_read(pdata, offset);
-		dev_dbg(dev, "saving 0x%08x from LPSS reg at offset 0x%02lx\n",
-			pdata->prv_reg_ctx[i], offset);
-	}
-}
-
-/**
- * acpi_lpss_restore_ctx() - Restore the private registers of LPSS device
- * @dev: LPSS device
- * @pdata: pointer to the private data of the LPSS device
- *
- * Restores the registers that were previously stored with acpi_lpss_save_ctx().
- */
-static void acpi_lpss_restore_ctx(struct device *dev,
-				  struct lpss_private_data *pdata)
-{
-	unsigned int i;
-
-	for (i = 0; i < LPSS_PRV_REG_COUNT; i++) {
-		unsigned long offset = i * sizeof(u32);
-
-		__lpss_reg_write(pdata->prv_reg_ctx[i], pdata, offset);
-		dev_dbg(dev, "restoring 0x%08x to LPSS reg at offset 0x%02lx\n",
-			pdata->prv_reg_ctx[i], offset);
-	}
-}
-
-static void acpi_lpss_d3_to_d0_delay(struct lpss_private_data *pdata)
-{
-	/*
-	 * The following delay is needed or the subsequent write operations may
-	 * fail. The LPSS devices are actually PCI devices and the PCI spec
-	 * expects 10ms delay before the device can be accessed after D3 to D0
-	 * transition. However some platforms like BSW does not need this delay.
-	 */
-	unsigned int delay = 10;	/* default 10ms delay */
-
-	if (pdata->dev_desc->flags & LPSS_NO_D3_DELAY)
-		delay = 0;
-
-	msleep(delay);
-}
-
-static int acpi_lpss_activate(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	ret = acpi_dev_resume(dev);
-	if (ret)
-		return ret;
-
-	acpi_lpss_d3_to_d0_delay(pdata);
-
-	/*
-	 * This is called only on ->probe() stage where a device is either in
-	 * known state defined by BIOS or most likely powered off. Due to this
-	 * we have to deassert reset line to be sure that ->probe() will
-	 * recognize the device.
-	 */
-	if (pdata->dev_desc->flags & (LPSS_SAVE_CTX | LPSS_SAVE_CTX_ONCE))
-		lpss_deassert_reset(pdata);
-
-#ifdef CONFIG_PM
-	if (pdata->dev_desc->flags & LPSS_SAVE_CTX_ONCE)
-		acpi_lpss_save_ctx(dev, pdata);
-#endif
-
-	return 0;
-}
-
-static void acpi_lpss_dismiss(struct device *dev)
-{
-	acpi_dev_suspend(dev, false);
-}
-
-/* IOSF SB for LPSS island */
-#define LPSS_IOSF_UNIT_LPIOEP		0xA0
-#define LPSS_IOSF_UNIT_LPIO1		0xAB
-#define LPSS_IOSF_UNIT_LPIO2		0xAC
-
-#define LPSS_IOSF_PMCSR			0x84
-#define LPSS_PMCSR_D0			0
-#define LPSS_PMCSR_D3hot		3
-#define LPSS_PMCSR_Dx_MASK		GENMASK(1, 0)
-
-#define LPSS_IOSF_GPIODEF0		0x154
-#define LPSS_GPIODEF0_DMA1_D3		BIT(2)
-#define LPSS_GPIODEF0_DMA2_D3		BIT(3)
-#define LPSS_GPIODEF0_DMA_D3_MASK	GENMASK(3, 2)
-#define LPSS_GPIODEF0_DMA_LLP		BIT(13)
-
-static DEFINE_MUTEX(lpss_iosf_mutex);
-static bool lpss_iosf_d3_entered = true;
-
-static void lpss_iosf_enter_d3_state(void)
-{
-	u32 value1 = 0;
-	u32 mask1 = LPSS_GPIODEF0_DMA_D3_MASK | LPSS_GPIODEF0_DMA_LLP;
-	u32 value2 = LPSS_PMCSR_D3hot;
-	u32 mask2 = LPSS_PMCSR_Dx_MASK;
-	/*
-	 * PMC provides an information about actual status of the LPSS devices.
-	 * Here we read the values related to LPSS power island, i.e. LPSS
-	 * devices, excluding both LPSS DMA controllers, along with SCC domain.
-	 */
-	u32 func_dis, d3_sts_0, pmc_status;
-	int ret;
-
-	ret = pmc_atom_read(PMC_FUNC_DIS, &func_dis);
-	if (ret)
-		return;
-
-	mutex_lock(&lpss_iosf_mutex);
-
-	ret = pmc_atom_read(PMC_D3_STS_0, &d3_sts_0);
-	if (ret)
-		goto exit;
-
-	/*
-	 * Get the status of entire LPSS power island per device basis.
-	 * Shutdown both LPSS DMA controllers if and only if all other devices
-	 * are already in D3hot.
-	 */
-	pmc_status = (~(d3_sts_0 | func_dis)) & pmc_atom_d3_mask;
-	if (pmc_status)
-		goto exit;
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
-			LPSS_IOSF_PMCSR, value2, mask2);
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO2, MBI_CFG_WRITE,
-			LPSS_IOSF_PMCSR, value2, mask2);
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
-			LPSS_IOSF_GPIODEF0, value1, mask1);
-
-	lpss_iosf_d3_entered = true;
-
-exit:
-	mutex_unlock(&lpss_iosf_mutex);
-}
-
-static void lpss_iosf_exit_d3_state(void)
-{
-	u32 value1 = LPSS_GPIODEF0_DMA1_D3 | LPSS_GPIODEF0_DMA2_D3 |
-		     LPSS_GPIODEF0_DMA_LLP;
-	u32 mask1 = LPSS_GPIODEF0_DMA_D3_MASK | LPSS_GPIODEF0_DMA_LLP;
-	u32 value2 = LPSS_PMCSR_D0;
-	u32 mask2 = LPSS_PMCSR_Dx_MASK;
-
-	mutex_lock(&lpss_iosf_mutex);
-
-	if (!lpss_iosf_d3_entered)
-		goto exit;
-
-	lpss_iosf_d3_entered = false;
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
-			LPSS_IOSF_GPIODEF0, value1, mask1);
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO2, MBI_CFG_WRITE,
-			LPSS_IOSF_PMCSR, value2, mask2);
-
-	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
-			LPSS_IOSF_PMCSR, value2, mask2);
-
-exit:
-	mutex_unlock(&lpss_iosf_mutex);
-}
-
-static int acpi_lpss_suspend(struct device *dev, bool wakeup)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
-		acpi_lpss_save_ctx(dev, pdata);
-
-	ret = acpi_dev_suspend(dev, wakeup);
-
-	/*
-	 * This call must be last in the sequence, otherwise PMC will return
-	 * wrong status for devices being about to be powered off. See
-	 * lpss_iosf_enter_d3_state() for further information.
-	 */
-	if (acpi_target_system_state() == ACPI_STATE_S0 &&
-	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
-		lpss_iosf_enter_d3_state();
-
-	return ret;
-}
-
-static int acpi_lpss_resume(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	/*
-	 * This call is kept first to be in symmetry with
-	 * acpi_lpss_runtime_suspend() one.
-	 */
-	if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
-		lpss_iosf_exit_d3_state();
-
-	ret = acpi_dev_resume(dev);
-	if (ret)
-		return ret;
-
-	acpi_lpss_d3_to_d0_delay(pdata);
-
-	if (pdata->dev_desc->flags & (LPSS_SAVE_CTX | LPSS_SAVE_CTX_ONCE))
-		acpi_lpss_restore_ctx(dev, pdata);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int acpi_lpss_do_suspend_late(struct device *dev)
-{
-	int ret;
-
-	if (dev_pm_skip_suspend(dev))
-		return 0;
-
-	ret = pm_generic_suspend_late(dev);
-	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
-}
-
-static int acpi_lpss_suspend_late(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	return acpi_lpss_do_suspend_late(dev);
-}
-
-static int acpi_lpss_suspend_noirq(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	if (pdata->dev_desc->resume_from_noirq) {
-		/*
-		 * The driver's ->suspend_late callback will be invoked by
-		 * acpi_lpss_do_suspend_late(), with the assumption that the
-		 * driver really wanted to run that code in ->suspend_noirq, but
-		 * it could not run after acpi_dev_suspend() and the driver
-		 * expected the latter to be called in the "late" phase.
-		 */
-		ret = acpi_lpss_do_suspend_late(dev);
-		if (ret)
-			return ret;
-	}
-
-	return acpi_subsys_suspend_noirq(dev);
-}
-
-static int acpi_lpss_do_resume_early(struct device *dev)
-{
-	int ret = acpi_lpss_resume(dev);
-
-	return ret ? ret : pm_generic_resume_early(dev);
-}
-
-static int acpi_lpss_resume_early(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	if (dev_pm_skip_resume(dev))
-		return 0;
-
-	return acpi_lpss_do_resume_early(dev);
-}
-
-static int acpi_lpss_resume_noirq(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	/* Follow acpi_subsys_resume_noirq(). */
-	if (dev_pm_skip_resume(dev))
-		return 0;
-
-	ret = pm_generic_resume_noirq(dev);
-	if (ret)
-		return ret;
-
-	if (!pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	/*
-	 * The driver's ->resume_early callback will be invoked by
-	 * acpi_lpss_do_resume_early(), with the assumption that the driver
-	 * really wanted to run that code in ->resume_noirq, but it could not
-	 * run before acpi_dev_resume() and the driver expected the latter to be
-	 * called in the "early" phase.
-	 */
-	return acpi_lpss_do_resume_early(dev);
-}
-
-static int acpi_lpss_do_restore_early(struct device *dev)
-{
-	int ret = acpi_lpss_resume(dev);
-
-	return ret ? ret : pm_generic_restore_early(dev);
-}
-
-static int acpi_lpss_restore_early(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	return acpi_lpss_do_restore_early(dev);
-}
-
-static int acpi_lpss_restore_noirq(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	int ret;
-
-	ret = pm_generic_restore_noirq(dev);
-	if (ret)
-		return ret;
-
-	if (!pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	/* This is analogous to what happens in acpi_lpss_resume_noirq(). */
-	return acpi_lpss_do_restore_early(dev);
-}
-
-static int acpi_lpss_do_poweroff_late(struct device *dev)
-{
-	int ret = pm_generic_poweroff_late(dev);
-
-	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
-}
-
-static int acpi_lpss_poweroff_late(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (dev_pm_skip_suspend(dev))
-		return 0;
-
-	if (pdata->dev_desc->resume_from_noirq)
-		return 0;
-
-	return acpi_lpss_do_poweroff_late(dev);
-}
-
-static int acpi_lpss_poweroff_noirq(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (dev_pm_skip_suspend(dev))
-		return 0;
-
-	if (pdata->dev_desc->resume_from_noirq) {
-		/* This is analogous to the acpi_lpss_suspend_noirq() case. */
-		int ret = acpi_lpss_do_poweroff_late(dev);
-
-		if (ret)
-			return ret;
-	}
-
-	return pm_generic_poweroff_noirq(dev);
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static int acpi_lpss_runtime_suspend(struct device *dev)
-{
-	int ret = pm_generic_runtime_suspend(dev);
-
-	return ret ? ret : acpi_lpss_suspend(dev, true);
-}
-
-static int acpi_lpss_runtime_resume(struct device *dev)
-{
-	int ret = acpi_lpss_resume(dev);
-
-	return ret ? ret : pm_generic_runtime_resume(dev);
-}
-#endif /* CONFIG_PM */
-
-static struct dev_pm_domain acpi_lpss_pm_domain = {
-#ifdef CONFIG_PM
-	.activate = acpi_lpss_activate,
-	.dismiss = acpi_lpss_dismiss,
-#endif
-	.ops = {
-#ifdef CONFIG_PM
-#ifdef CONFIG_PM_SLEEP
-		.prepare = acpi_subsys_prepare,
-		.complete = acpi_subsys_complete,
-		.suspend = acpi_subsys_suspend,
-		.suspend_late = acpi_lpss_suspend_late,
-		.suspend_noirq = acpi_lpss_suspend_noirq,
-		.resume_noirq = acpi_lpss_resume_noirq,
-		.resume_early = acpi_lpss_resume_early,
-		.freeze = acpi_subsys_freeze,
-		.poweroff = acpi_subsys_poweroff,
-		.poweroff_late = acpi_lpss_poweroff_late,
-		.poweroff_noirq = acpi_lpss_poweroff_noirq,
-		.restore_noirq = acpi_lpss_restore_noirq,
-		.restore_early = acpi_lpss_restore_early,
-#endif
-		.runtime_suspend = acpi_lpss_runtime_suspend,
-		.runtime_resume = acpi_lpss_runtime_resume,
-#endif
-	},
-};
-
-static int acpi_lpss_platform_notify(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct platform_device *pdev = to_platform_device(data);
-	struct lpss_private_data *pdata;
-	struct acpi_device *adev;
-	const struct acpi_device_id *id;
-
-	id = acpi_match_device(acpi_lpss_device_ids, &pdev->dev);
-	if (!id || !id->driver_data)
-		return 0;
-
-	adev = ACPI_COMPANION(&pdev->dev);
-	if (!adev)
-		return 0;
-
-	pdata = acpi_driver_data(adev);
-	if (!pdata)
-		return 0;
-
-	if (pdata->mmio_base &&
-	    pdata->mmio_size < pdata->dev_desc->prv_offset + LPSS_LTR_SIZE) {
-		dev_err(&pdev->dev, "MMIO size insufficient to access LTR\n");
-		return 0;
-	}
-
-	switch (action) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		dev_pm_domain_set(&pdev->dev, &acpi_lpss_pm_domain);
-		break;
-	case BUS_NOTIFY_DRIVER_NOT_BOUND:
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		dev_pm_domain_set(&pdev->dev, NULL);
-		break;
-	case BUS_NOTIFY_ADD_DEVICE:
-		dev_pm_domain_set(&pdev->dev, &acpi_lpss_pm_domain);
-		if (pdata->dev_desc->flags & LPSS_LTR)
-			return sysfs_create_group(&pdev->dev.kobj,
-						  &lpss_attr_group);
-		break;
-	case BUS_NOTIFY_DEL_DEVICE:
-		if (pdata->dev_desc->flags & LPSS_LTR)
-			sysfs_remove_group(&pdev->dev.kobj, &lpss_attr_group);
-		dev_pm_domain_set(&pdev->dev, NULL);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static struct notifier_block acpi_lpss_nb = {
-	.notifier_call = acpi_lpss_platform_notify,
-};
-
-static void acpi_lpss_bind(struct device *dev)
-{
-	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-
-	if (!pdata || !pdata->mmio_base || !(pdata->dev_desc->flags & LPSS_LTR))
-		return;
-
-	if (pdata->mmio_size >= pdata->dev_desc->prv_offset + LPSS_LTR_SIZE)
-		dev->power.set_latency_tolerance = acpi_lpss_set_ltr;
-	else
-		dev_err(dev, "MMIO size insufficient to access LTR\n");
-}
-
-static void acpi_lpss_unbind(struct device *dev)
-{
-	dev->power.set_latency_tolerance = NULL;
-}
-
-static struct acpi_scan_handler lpss_handler = {
-	.ids = acpi_lpss_device_ids,
-	.attach = acpi_lpss_create_device,
-	.bind = acpi_lpss_bind,
-	.unbind = acpi_lpss_unbind,
-};
-
-void __init acpi_lpss_init(void)
-{
-	const struct x86_cpu_id *id;
-	int ret;
-
-	ret = lpss_atom_clk_init();
-	if (ret)
-		return;
-
-	id = x86_match_cpu(lpss_cpu_ids);
-	if (id)
-		lpss_quirks |= LPSS_QUIRK_ALWAYS_POWER_ON;
-
-	bus_register_notifier(&platform_bus_type, &acpi_lpss_nb);
-	acpi_scan_add_handler(&lpss_handler);
-}
-
-#else
-
-static struct acpi_scan_handler lpss_handler = {
-	.ids = acpi_lpss_device_ids,
-};
-
-void __init acpi_lpss_init(void)
-{
-	acpi_scan_add_handler(&lpss_handler);
-}
-
-#endif /* CONFIG_X86_INTEL_LPSS */
diff --git a/drivers/acpi/acpi_mrrm.c b/drivers/acpi/acpi_mrrm.c
new file mode 100644
index 000000000000..47ea3ccc2142
--- /dev/null
+++ b/drivers/acpi/acpi_mrrm.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025, Intel Corporation.
+ *
+ * Memory Range and Region Mapping (MRRM) structure
+ *
+ * Parse and report the platform's MRRM table in /sys.
+ */
+
+#define pr_fmt(fmt) "acpi/mrrm: " fmt
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+
+/* Default assume one memory region covering all system memory, per the spec */
+static int max_mem_region = 1;
+
+/* Access for use by resctrl file system */
+int acpi_mrrm_max_mem_region(void)
+{
+	return max_mem_region;
+}
+
+struct mrrm_mem_range_entry {
+	u64 base;
+	u64 length;
+	int node;
+	u8  local_region_id;
+	u8  remote_region_id;
+};
+
+static struct mrrm_mem_range_entry *mrrm_mem_range_entry;
+static u32 mrrm_mem_entry_num;
+
+static int get_node_num(struct mrrm_mem_range_entry *e)
+{
+	unsigned int nid;
+
+	for_each_online_node(nid) {
+		for (int z = 0; z < MAX_NR_ZONES; z++) {
+			struct zone *zone = NODE_DATA(nid)->node_zones + z;
+
+			if (!populated_zone(zone))
+				continue;
+			if (zone_intersects(zone, PHYS_PFN(e->base), PHYS_PFN(e->length)))
+				return zone_to_nid(zone);
+		}
+	}
+
+	return -ENOENT;
+}
+
+static __init int acpi_parse_mrrm(struct acpi_table_header *table)
+{
+	struct acpi_mrrm_mem_range_entry *mre_entry;
+	struct acpi_table_mrrm *mrrm;
+	void *mre, *mrrm_end;
+	int mre_count = 0;
+
+	mrrm = (struct acpi_table_mrrm *)table;
+	if (!mrrm)
+		return -ENODEV;
+
+	if (mrrm->flags & ACPI_MRRM_FLAGS_REGION_ASSIGNMENT_OS)
+		return -EOPNOTSUPP;
+
+	mrrm_end = (void *)mrrm + mrrm->header.length - 1;
+	mre = (void *)mrrm + sizeof(struct acpi_table_mrrm);
+	while (mre < mrrm_end) {
+		mre_entry = mre;
+		mre_count++;
+		mre += mre_entry->header.length;
+	}
+	if (!mre_count) {
+		pr_info(FW_BUG "No ranges listed in MRRM table\n");
+		return -EINVAL;
+	}
+
+	mrrm_mem_range_entry = kmalloc_array(mre_count, sizeof(*mrrm_mem_range_entry),
+					     GFP_KERNEL | __GFP_ZERO);
+	if (!mrrm_mem_range_entry)
+		return -ENOMEM;
+
+	mre = (void *)mrrm + sizeof(struct acpi_table_mrrm);
+	while (mre < mrrm_end) {
+		struct mrrm_mem_range_entry *e;
+
+		mre_entry = mre;
+		e = mrrm_mem_range_entry + mrrm_mem_entry_num;
+
+		e->base = mre_entry->addr_base;
+		e->length = mre_entry->addr_len;
+		e->node = get_node_num(e);
+
+		if (mre_entry->region_id_flags & ACPI_MRRM_VALID_REGION_ID_FLAGS_LOCAL)
+			e->local_region_id = mre_entry->local_region_id;
+		else
+			e->local_region_id = -1;
+		if (mre_entry->region_id_flags & ACPI_MRRM_VALID_REGION_ID_FLAGS_REMOTE)
+			e->remote_region_id = mre_entry->remote_region_id;
+		else
+			e->remote_region_id = -1;
+
+		mrrm_mem_entry_num++;
+		mre += mre_entry->header.length;
+	}
+
+	max_mem_region = mrrm->max_mem_region;
+
+	return 0;
+}
+
+#define RANGE_ATTR(name, fmt)						\
+static ssize_t name##_show(struct kobject *kobj,			\
+			  struct kobj_attribute *attr, char *buf)	\
+{									\
+	struct mrrm_mem_range_entry *mre;				\
+	const char *kname = kobject_name(kobj);				\
+	int n, ret;							\
+									\
+	ret = kstrtoint(kname + 5, 10, &n);				\
+	if (ret)							\
+		return ret;						\
+									\
+	mre = mrrm_mem_range_entry + n;					\
+									\
+	return sysfs_emit(buf, fmt, mre->name);				\
+}									\
+static struct kobj_attribute name##_attr = __ATTR_RO(name)
+
+RANGE_ATTR(base, "0x%llx\n");
+RANGE_ATTR(length, "0x%llx\n");
+RANGE_ATTR(node, "%d\n");
+RANGE_ATTR(local_region_id, "%d\n");
+RANGE_ATTR(remote_region_id, "%d\n");
+
+static struct attribute *memory_range_attrs[] = {
+	&base_attr.attr,
+	&length_attr.attr,
+	&node_attr.attr,
+	&local_region_id_attr.attr,
+	&remote_region_id_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(memory_range);
+
+static __init int add_boot_memory_ranges(void)
+{
+	struct kobject *pkobj, *kobj;
+	int ret = -EINVAL;
+	char *name;
+
+	pkobj = kobject_create_and_add("memory_ranges", acpi_kobj);
+
+	for (int i = 0; i < mrrm_mem_entry_num; i++) {
+		name = kasprintf(GFP_KERNEL, "range%d", i);
+		if (!name) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		kobj = kobject_create_and_add(name, pkobj);
+
+		ret = sysfs_create_groups(kobj, memory_range_groups);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static __init int mrrm_init(void)
+{
+	int ret;
+
+	ret = acpi_table_parse(ACPI_SIG_MRRM, acpi_parse_mrrm);
+	if (ret < 0)
+		return ret;
+
+	return add_boot_memory_ranges();
+}
+device_initcall(mrrm_init);
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index bd1ad07f0290..c9a0bcaba2e4 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -19,16 +19,21 @@
 #include <linux/acpi.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
+#include <asm/cpuid/api.h>
 #include <asm/mwait.h>
 #include <xen/xen.h>
 
 #define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
 #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
+
+#define ACPI_PROCESSOR_AGGREGATOR_STATUS_SUCCESS	0
+#define ACPI_PROCESSOR_AGGREGATOR_STATUS_NO_ACTION	1
+
 static DEFINE_MUTEX(isolated_cpus_lock);
 static DEFINE_MUTEX(round_robin_lock);
 
-static unsigned long power_saving_mwait_eax;
+static unsigned int power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
 static unsigned char tsc_marked_unstable;
@@ -42,10 +47,8 @@ static void power_saving_mwait_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_MWAIT))
 		return;
-	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
-		return;
 
-	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+	cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx);
 
 	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
 	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK))
@@ -132,8 +135,10 @@ static void exit_round_robin(unsigned int tsk_index)
 {
 	struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
 
-	cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
-	tsk_in_cpu[tsk_index] = -1;
+	if (tsk_in_cpu[tsk_index] != -1) {
+		cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
+		tsk_in_cpu[tsk_index] = -1;
+	}
 }
 
 static unsigned int idle_pct = 5; /* percentage */
@@ -382,16 +387,23 @@ static void acpi_pad_handle_notify(acpi_handle handle)
 		.length = 4,
 		.pointer = (void *)&idle_cpus,
 	};
+	u32 status;
 
 	mutex_lock(&isolated_cpus_lock);
 	num_cpus = acpi_pad_pur(handle);
 	if (num_cpus < 0) {
-		mutex_unlock(&isolated_cpus_lock);
-		return;
+		/* The ACPI specification says that if no action was performed when
+		 * processing the _PUR object, _OST should still be evaluated, albeit
+		 * with a different status code.
+		 */
+		status = ACPI_PROCESSOR_AGGREGATOR_STATUS_NO_ACTION;
+	} else {
+		status = ACPI_PROCESSOR_AGGREGATOR_STATUS_SUCCESS;
+		acpi_pad_idle_cpus(num_cpus);
 	}
-	acpi_pad_idle_cpus(num_cpus);
+
 	idle_cpus = acpi_pad_idle_cpus_num();
-	acpi_evaluate_ost(handle, ACPI_PROCESSOR_AGGREGATOR_NOTIFY, 0, &param);
+	acpi_evaluate_ost(handle, ACPI_PROCESSOR_AGGREGATOR_NOTIFY, status, &param);
 	mutex_unlock(&isolated_cpus_lock);
 }
 
@@ -417,8 +429,8 @@ static int acpi_pad_probe(struct platform_device *pdev)
 	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	acpi_status status;
 
-	strcpy(acpi_device_name(adev), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME);
-	strcpy(acpi_device_class(adev), ACPI_PROCESSOR_AGGREGATOR_CLASS);
+	strscpy(acpi_device_name(adev), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME);
+	strscpy(acpi_device_class(adev), ACPI_PROCESSOR_AGGREGATOR_CLASS);
 
 	status = acpi_install_notify_handler(adev->handle,
 		ACPI_DEVICE_NOTIFY, acpi_pad_notify, adev);
@@ -449,7 +461,7 @@ MODULE_DEVICE_TABLE(acpi, pad_device_ids);
 
 static struct platform_driver acpi_pad_driver = {
 	.probe = acpi_pad_probe,
-	.remove_new = acpi_pad_remove,
+	.remove = acpi_pad_remove,
 	.driver = {
 		.dev_groups = acpi_pad_groups,
 		.name = "processor_aggregator",
diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c
index 07a034a53aca..97064e943768 100644
--- a/drivers/acpi/acpi_pcc.c
+++ b/drivers/acpi/acpi_pcc.c
@@ -31,7 +31,6 @@
 
 struct pcc_data {
 	struct pcc_mbox_chan *pcc_chan;
-	void __iomem *pcc_comm_addr;
 	struct completion done;
 	struct mbox_client cl;
 	struct acpi_pcc_info ctx;
@@ -81,14 +80,6 @@ acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function,
 		ret = AE_SUPPORT;
 		goto err_free_channel;
 	}
-	data->pcc_comm_addr = acpi_os_ioremap(pcc_chan->shmem_base_addr,
-					      pcc_chan->shmem_size);
-	if (!data->pcc_comm_addr) {
-		pr_err("Failed to ioremap PCC comm region mem for %d\n",
-		       ctx->subspace_id);
-		ret = AE_NO_MEMORY;
-		goto err_free_channel;
-	}
 
 	*region_context = data;
 	return AE_OK;
@@ -113,7 +104,7 @@ acpi_pcc_address_space_handler(u32 function, acpi_physical_address addr,
 	reinit_completion(&data->done);
 
 	/* Write to Shared Memory */
-	memcpy_toio(data->pcc_comm_addr, (void *)value, data->ctx.length);
+	memcpy_toio(data->pcc_chan->shmem, (void *)value, data->ctx.length);
 
 	ret = mbox_send_message(data->pcc_chan->mchan, NULL);
 	if (ret < 0)
@@ -134,7 +125,7 @@ acpi_pcc_address_space_handler(u32 function, acpi_physical_address addr,
 
 	mbox_chan_txdone(data->pcc_chan->mchan, ret);
 
-	memcpy_fromio(value, data->pcc_comm_addr, data->ctx.length);
+	memcpy_fromio(value, data->pcc_chan->shmem, data->ctx.length);
 
 	return AE_OK;
 }
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index 01abf26764b0..4ad88187dc7a 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -120,8 +120,6 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = {
 	{"IBM0071"},
 	/* smsc-ircc2 */
 	{"SMCf010"},
-	/* sb1000 */
-	{"GIC1000"},
 	/* parport_pc */
 	{"PNP0400"},		/* Standard LPT Printer Port */
 	{"PNP0401"},		/* ECP Printer Port */
@@ -355,8 +353,10 @@ static bool acpi_pnp_match(const char *idstr, const struct acpi_device_id **matc
  * device represented by it.
  */
 static const struct acpi_device_id acpi_nonpnp_device_ids[] = {
+	{"INT3F0D"},
 	{"INTC1080"},
 	{"INTC1081"},
+	{"INTC1099"},
 	{""},
 };
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0f5218e361df..7ec1dc04fd11 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -35,6 +35,17 @@ EXPORT_PER_CPU_SYMBOL(processors);
 struct acpi_processor_errata errata __read_mostly;
 EXPORT_SYMBOL_GPL(errata);
 
+acpi_handle acpi_get_processor_handle(int cpu)
+{
+	struct acpi_processor *pr;
+
+	pr = per_cpu(processors, cpu);
+	if (pr)
+		return pr->handle;
+
+	return NULL;
+}
+
 static int acpi_processor_errata_piix4(struct pci_dev *dev)
 {
 	u8 value1 = 0;
@@ -161,7 +172,7 @@ static void cpufreq_add_device(const char *name)
 
 	pdev = platform_device_register_simple(name, PLATFORM_DEVID_NONE, NULL, 0);
 	if (IS_ERR(pdev))
-		pr_info("%s device creation failed: %ld\n", name, PTR_ERR(pdev));
+		pr_info("%s device creation failed: %pe\n", name, pdev);
 }
 
 #ifdef CONFIG_X86
@@ -183,38 +194,44 @@ static void __init acpi_pcc_cpufreq_init(void) {}
 #endif /* CONFIG_X86 */
 
 /* Initialization */
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-int __weak acpi_map_cpu(acpi_handle handle,
-		phys_cpuid_t physid, u32 acpi_id, int *pcpu)
-{
-	return -ENODEV;
-}
+static DEFINE_PER_CPU(void *, processor_device_array);
 
-int __weak acpi_unmap_cpu(int cpu)
+static int acpi_processor_set_per_cpu(struct acpi_processor *pr,
+				      struct acpi_device *device)
 {
-	return -ENODEV;
-}
+	BUG_ON(pr->id >= nr_cpu_ids);
 
-int __weak arch_register_cpu(int cpu)
-{
-	return -ENODEV;
-}
+	/*
+	 * Buggy BIOS check.
+	 * ACPI id of processors can be reported wrongly by the BIOS.
+	 * Don't trust it blindly
+	 */
+	if (per_cpu(processor_device_array, pr->id) != NULL &&
+	    per_cpu(processor_device_array, pr->id) != device) {
+		dev_warn(&device->dev,
+			 "BIOS reported wrong ACPI id %d for the processor\n",
+			 pr->id);
+		return -EINVAL;
+	}
+	/*
+	 * processor_device_array is not cleared on errors to allow buggy BIOS
+	 * checks.
+	 */
+	per_cpu(processor_device_array, pr->id) = device;
+	per_cpu(processors, pr->id) = pr;
 
-void __weak arch_unregister_cpu(int cpu) {}
+	return 0;
+}
 
-static int acpi_processor_hotadd_init(struct acpi_processor *pr)
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+static int acpi_processor_hotadd_init(struct acpi_processor *pr,
+				      struct acpi_device *device)
 {
-	unsigned long long sta;
-	acpi_status status;
 	int ret;
 
 	if (invalid_phys_cpuid(pr->phys_id))
 		return -ENODEV;
 
-	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
-	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT))
-		return -ENODEV;
-
 	cpu_maps_update_begin();
 	cpus_write_lock();
 
@@ -222,19 +239,26 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	if (ret)
 		goto out;
 
+	ret = acpi_processor_set_per_cpu(pr, device);
+	if (ret) {
+		acpi_unmap_cpu(pr->id);
+		goto out;
+	}
+
 	ret = arch_register_cpu(pr->id);
 	if (ret) {
+		/* Leave the processor device array in place to detect buggy bios */
+		per_cpu(processors, pr->id) = NULL;
 		acpi_unmap_cpu(pr->id);
 		goto out;
 	}
 
 	/*
-	 * CPU got hot-added, but cpu_data is not initialized yet.  Set a flag
-	 * to delay cpu_idle/throttling initialization and do it when the CPU
-	 * gets online for the first time.
+	 * CPU got hot-added, but cpu_data is not initialized yet. Do
+	 * cpu_idle/throttling initialization when the CPU gets online for
+	 * the first time.
 	 */
 	pr_info("CPU%d has been hot-added\n", pr->id);
-	pr->flags.need_hotplug_init = 1;
 
 out:
 	cpus_write_unlock();
@@ -242,7 +266,8 @@ out:
 	return ret;
 }
 #else
-static inline int acpi_processor_hotadd_init(struct acpi_processor *pr)
+static inline int acpi_processor_hotadd_init(struct acpi_processor *pr,
+					     struct acpi_device *device)
 {
 	return -ENODEV;
 }
@@ -250,13 +275,14 @@ static inline int acpi_processor_hotadd_init(struct acpi_processor *pr)
 
 static int acpi_processor_get_info(struct acpi_device *device)
 {
-	union acpi_object object = { 0 };
+	union acpi_object object = { .processor = { 0 } };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
 	int device_declaration = 0;
 	acpi_status status = AE_OK;
 	static int cpu0_initialized;
 	unsigned long long value;
+	int ret;
 
 	acpi_processor_errata();
 
@@ -333,19 +359,19 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	}
 
 	/*
-	 *  Extra Processor objects may be enumerated on MP systems with
-	 *  less than the max # of CPUs. They should be ignored _iff
-	 *  they are physically not present.
-	 *
-	 *  NOTE: Even if the processor has a cpuid, it may not be present
-	 *  because cpuid <-> apicid mapping is persistent now.
+	 *  This code is not called unless we know the CPU is present and
+	 *  enabled. The two paths are:
+	 *  a) Initially present CPUs on architectures that do not defer
+	 *     their arch_register_cpu() calls until this point.
+	 *  b) Hotplugged CPUs (enabled bit in _STA has transitioned from not
+	 *     enabled to enabled)
 	 */
-	if (invalid_logical_cpuid(pr->id) || !cpu_present(pr->id)) {
-		int ret = acpi_processor_hotadd_init(pr);
-
-		if (ret)
-			return ret;
-	}
+	if (!get_cpu_device(pr->id))
+		ret = acpi_processor_hotadd_init(pr, device);
+	else
+		ret = acpi_processor_set_per_cpu(pr, device);
+	if (ret)
+		return ret;
 
 	/*
 	 * On some boxes several processors use the same processor bus id.
@@ -390,8 +416,6 @@ static int acpi_processor_get_info(struct acpi_device *device)
  * (cpu_data(cpu)) values, like CPU feature flags, family, model, etc.
  * Such things have to be put in and set up by the processor driver's .probe().
  */
-static DEFINE_PER_CPU(void *, processor_device_array);
-
 static int acpi_processor_add(struct acpi_device *device,
 					const struct acpi_device_id *id)
 {
@@ -399,6 +423,9 @@ static int acpi_processor_add(struct acpi_device *device,
 	struct device *dev;
 	int result = 0;
 
+	if (!acpi_device_is_enabled(device))
+		return -ENODEV;
+
 	pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
 	if (!pr)
 		return -ENOMEM;
@@ -409,45 +436,23 @@ static int acpi_processor_add(struct acpi_device *device,
 	}
 
 	pr->handle = device->handle;
-	strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
+	strscpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
 	device->driver_data = pr;
 
 	result = acpi_processor_get_info(device);
 	if (result) /* Processor is not physically present or unavailable */
-		return 0;
-
-	BUG_ON(pr->id >= nr_cpu_ids);
-
-	/*
-	 * Buggy BIOS check.
-	 * ACPI id of processors can be reported wrongly by the BIOS.
-	 * Don't trust it blindly
-	 */
-	if (per_cpu(processor_device_array, pr->id) != NULL &&
-	    per_cpu(processor_device_array, pr->id) != device) {
-		dev_warn(&device->dev,
-			"BIOS reported wrong ACPI id %d for the processor\n",
-			pr->id);
-		/* Give up, but do not abort the namespace scan. */
-		goto err;
-	}
-	/*
-	 * processor_device_array is not cleared on errors to allow buggy BIOS
-	 * checks.
-	 */
-	per_cpu(processor_device_array, pr->id) = device;
-	per_cpu(processors, pr->id) = pr;
+		goto err_clear_driver_data;
 
 	dev = get_cpu_device(pr->id);
 	if (!dev) {
 		result = -ENODEV;
-		goto err;
+		goto err_clear_per_cpu;
 	}
 
 	result = acpi_bind_one(dev, device);
 	if (result)
-		goto err;
+		goto err_clear_per_cpu;
 
 	pr->dev = dev;
 
@@ -458,10 +463,11 @@ static int acpi_processor_add(struct acpi_device *device,
 	dev_err(dev, "Processor driver could not be attached\n");
 	acpi_unbind_one(dev);
 
- err:
-	free_cpumask_var(pr->throttling.shared_cpu_map);
-	device->driver_data = NULL;
+ err_clear_per_cpu:
 	per_cpu(processors, pr->id) = NULL;
+ err_clear_driver_data:
+	device->driver_data = NULL;
+	free_cpumask_var(pr->throttling.shared_cpu_map);
  err_free_pr:
 	kfree(pr);
 	return result;
@@ -469,7 +475,7 @@ static int acpi_processor_add(struct acpi_device *device,
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Removal */
-static void acpi_processor_remove(struct acpi_device *device)
+static void acpi_processor_post_eject(struct acpi_device *device)
 {
 	struct acpi_processor *pr;
 
@@ -491,10 +497,6 @@ static void acpi_processor_remove(struct acpi_device *device)
 	device_release_driver(pr->dev);
 	acpi_unbind_one(pr->dev);
 
-	/* Clean up. */
-	per_cpu(processor_device_array, pr->id) = NULL;
-	per_cpu(processors, pr->id) = NULL;
-
 	cpu_maps_update_begin();
 	cpus_write_lock();
 
@@ -502,6 +504,10 @@ static void acpi_processor_remove(struct acpi_device *device)
 	arch_unregister_cpu(pr->id);
 	acpi_unmap_cpu(pr->id);
 
+	/* Clean up. */
+	per_cpu(processor_device_array, pr->id) = NULL;
+	per_cpu(processors, pr->id) = NULL;
+
 	cpus_write_unlock();
 	cpu_maps_update_done();
 
@@ -613,9 +619,9 @@ static bool __init acpi_early_processor_osc(void)
 void __init acpi_early_processor_control_setup(void)
 {
 	if (acpi_early_processor_osc()) {
-		pr_info("_OSC evaluated successfully for all CPUs\n");
+		pr_debug("_OSC evaluated successfully for all CPUs\n");
 	} else {
-		pr_info("_OSC evaluation for CPUs failed, trying _PDC\n");
+		pr_debug("_OSC evaluation for CPUs failed, trying _PDC\n");
 		acpi_early_processor_set_pdc();
 	}
 }
@@ -637,7 +643,7 @@ static struct acpi_scan_handler processor_handler = {
 	.ids = processor_device_ids,
 	.attach = acpi_processor_add,
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
-	.detach = acpi_processor_remove,
+	.post_eject = acpi_processor_post_eject,
 #endif
 	.hotplug = {
 		.enabled = true,
@@ -809,7 +815,7 @@ bool acpi_processor_claim_cst_control(void)
 	cst_control_claimed = true;
 	return true;
 }
-EXPORT_SYMBOL_GPL(acpi_processor_claim_cst_control);
+EXPORT_SYMBOL_NS_GPL(acpi_processor_claim_cst_control, "ACPI_PROCESSOR_IDLE");
 
 /**
  * acpi_processor_evaluate_cst - Evaluate the processor _CST control method.
@@ -979,7 +985,7 @@ int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu,
 		memcpy(&info->states[++last_index], &cx, sizeof(cx));
 	}
 
-	acpi_handle_info(handle, "Found %d idle states\n", last_index);
+	acpi_handle_debug(handle, "Found %d idle states\n", last_index);
 
 	info->count = last_index;
 
@@ -988,5 +994,5 @@ end:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(acpi_processor_evaluate_cst);
+EXPORT_SYMBOL_NS_GPL(acpi_processor_evaluate_cst, "ACPI_PROCESSOR_IDLE");
 #endif /* CONFIG_ACPI_PROCESSOR_CSTATE */
diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c
index 33c3b16af556..33418dd6768a 100644
--- a/drivers/acpi/acpi_tad.c
+++ b/drivers/acpi/acpi_tad.c
@@ -27,6 +27,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/suspend.h>
 
+MODULE_DESCRIPTION("ACPI Time and Alarm (TAD) Device Driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Rafael J. Wysocki");
 
@@ -232,7 +233,7 @@ static ssize_t time_show(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	return sprintf(buf, "%u:%u:%u:%u:%u:%u:%d:%u\n",
+	return sysfs_emit(buf, "%u:%u:%u:%u:%u:%u:%d:%u\n",
 		       rt.year, rt.month, rt.day, rt.hour, rt.minute, rt.second,
 		       rt.tz, rt.daylight);
 }
@@ -427,7 +428,7 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr,
 {
 	struct acpi_tad_driver_data *dd = dev_get_drvdata(dev);
 
-	return sprintf(buf, "0x%02X\n", dd->capabilities);
+	return sysfs_emit(buf, "0x%02X\n", dd->capabilities);
 }
 
 static DEVICE_ATTR_RO(caps);
@@ -554,7 +555,7 @@ static int acpi_tad_disable_timer(struct device *dev, u32 timer_id)
 	return acpi_tad_wake_set(dev, "_STV", timer_id, ACPI_TAD_WAKE_DISABLED);
 }
 
-static int acpi_tad_remove(struct platform_device *pdev)
+static void acpi_tad_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	acpi_handle handle = ACPI_HANDLE(dev);
@@ -564,6 +565,9 @@ static int acpi_tad_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(dev);
 
+	if (dd->capabilities & ACPI_TAD_RT)
+		sysfs_remove_group(&dev->kobj, &acpi_tad_time_attr_group);
+
 	if (dd->capabilities & ACPI_TAD_DC_WAKE)
 		sysfs_remove_group(&dev->kobj, &acpi_tad_dc_attr_group);
 
@@ -579,7 +583,6 @@ static int acpi_tad_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 	acpi_remove_cmos_rtc_space_handler(handle);
-	return 0;
 }
 
 static int acpi_tad_probe(struct platform_device *pdev)
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 0b7a01f38b65..103f29661576 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -27,6 +27,7 @@
 #include <linux/acpi.h>
 #include <acpi/video.h>
 #include <linux/uaccess.h>
+#include <linux/string_choices.h>
 
 #define ACPI_VIDEO_BUS_NAME		"Video Bus"
 #define ACPI_VIDEO_DEVICE_NAME		"Video Device"
@@ -67,7 +68,7 @@ MODULE_PARM_DESC(hw_changes_brightness,
 static bool device_id_scheme = false;
 module_param(device_id_scheme, bool, 0444);
 
-static int only_lcd = -1;
+static int only_lcd;
 module_param(only_lcd, int, 0444);
 
 static bool may_report_brightness_keys;
@@ -253,8 +254,7 @@ static const struct backlight_ops acpi_backlight_ops = {
 static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 
 	*state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
 	return 0;
@@ -263,8 +263,7 @@ static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	unsigned long long level;
 	int offset;
 
@@ -283,8 +282,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 static int
 video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	int level;
 
 	if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL)
@@ -503,6 +501,15 @@ static const struct dmi_system_id video_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"),
 		},
 	},
+	{
+	 .callback = video_set_report_key_events,
+	 .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS),
+	 .ident = "COLORFUL X15 AT 23",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"),
+		},
+	},
 	/*
 	 * Some machines change the brightness themselves when a brightness
 	 * hotkey gets pressed, despite us telling them not to. In this case
@@ -604,43 +611,62 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device,
 	return 0;
 }
 
+/**
+ * acpi_video_device_EDID() - Get EDID from ACPI _DDC
+ * @device: video output device (LCD, CRT, ..)
+ * @edid: address for returned EDID pointer
+ * @length: _DDC length to request (must be a multiple of 128)
+ *
+ * Get EDID from ACPI _DDC. On success, a pointer to the EDID data is written
+ * to the @edid address, and the length of the EDID is returned. The caller is
+ * responsible for freeing the edid pointer.
+ *
+ * Return the length of EDID (positive value) on success or error (negative
+ * value).
+ */
 static int
-acpi_video_device_EDID(struct acpi_video_device *device,
-		       union acpi_object **edid, ssize_t length)
+acpi_video_device_EDID(struct acpi_video_device *device, void **edid, int length)
 {
-	int status;
+	acpi_status status;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *obj;
 	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
 	struct acpi_object_list args = { 1, &arg0 };
-
+	int ret;
 
 	*edid = NULL;
 
 	if (!device)
 		return -ENODEV;
-	if (length == 128)
-		arg0.integer.value = 1;
-	else if (length == 256)
-		arg0.integer.value = 2;
-	else
+	if (!length || (length % 128))
 		return -EINVAL;
 
+	arg0.integer.value = length / 128;
+
 	status = acpi_evaluate_object(device->dev->handle, "_DDC", &args, &buffer);
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
 	obj = buffer.pointer;
 
-	if (obj && obj->type == ACPI_TYPE_BUFFER)
-		*edid = obj;
-	else {
-		acpi_handle_info(device->dev->handle, "Invalid _DDC data\n");
-		status = -EFAULT;
-		kfree(obj);
+	/*
+	 * Some buggy implementations incorrectly return the EDID buffer in an ACPI package.
+	 * In this case, extract the buffer from the package.
+	 */
+	if (obj && obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 1)
+		obj = &obj->package.elements[0];
+
+	if (obj && obj->type == ACPI_TYPE_BUFFER) {
+		*edid = kmemdup(obj->buffer.pointer, obj->buffer.length, GFP_KERNEL);
+		ret = *edid ? obj->buffer.length : -ENOMEM;
+	} else {
+		acpi_handle_debug(device->dev->handle,
+				 "Invalid _DDC data for length %d\n", length);
+		ret = -EFAULT;
 	}
 
-	return status;
+	kfree(buffer.pointer);
+	return ret;
 }
 
 /* bus */
@@ -1123,9 +1149,8 @@ static int acpi_video_bus_get_one_device(struct acpi_device *device, void *arg)
 		return -ENOMEM;
 	}
 
-	strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
-	device->driver_data = data;
+	strscpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
 
 	data->device_id = device_id;
 	data->video = video;
@@ -1431,9 +1456,7 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id,
 {
 	struct acpi_video_bus *video;
 	struct acpi_video_device *video_device;
-	union acpi_object *buffer = NULL;
-	acpi_status status;
-	int i, length;
+	int i, length, ret;
 
 	if (!device || !acpi_driver_data(device))
 		return -EINVAL;
@@ -1442,7 +1465,6 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id,
 
 	for (i = 0; i < video->attached_count; i++) {
 		video_device = video->attached_array[i].bind_info;
-		length = 256;
 
 		if (!video_device)
 			continue;
@@ -1473,21 +1495,11 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id,
 			continue;
 		}
 
-		status = acpi_video_device_EDID(video_device, &buffer, length);
-
-		if (ACPI_FAILURE(status) || !buffer ||
-		    buffer->type != ACPI_TYPE_BUFFER) {
-			length = 128;
-			status = acpi_video_device_EDID(video_device, &buffer,
-							length);
-			if (ACPI_FAILURE(status) || !buffer ||
-			    buffer->type != ACPI_TYPE_BUFFER) {
-				continue;
-			}
+		for (length = 512; length > 0; length -= 128) {
+			ret = acpi_video_device_EDID(video_device, edid, length);
+			if (ret > 0)
+				return ret;
 		}
-
-		*edid = buffer->buffer.pointer;
-		return length;
 	}
 
 	return -ENODEV;
@@ -1717,12 +1729,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 		return;
 	count++;
 
-	acpi_get_parent(device->dev->handle, &acpi_parent);
-
-	pdev = acpi_get_pci_dev(acpi_parent);
-	if (pdev) {
-		parent = &pdev->dev;
-		pci_dev_put(pdev);
+	if (ACPI_SUCCESS(acpi_get_parent(device->dev->handle, &acpi_parent))) {
+		pdev = acpi_get_pci_dev(acpi_parent);
+		if (pdev) {
+			parent = &pdev->dev;
+			pci_dev_put(pdev);
+		}
 	}
 
 	memset(&props, 0, sizeof(struct backlight_properties));
@@ -1747,8 +1759,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 	device->backlight->props.brightness =
 			acpi_video_get_brightness(device->backlight);
 
-	device->cooling_dev = thermal_cooling_device_register("LCD",
-				device->dev, &video_cooling_ops);
+	device->cooling_dev = thermal_cooling_device_register("LCD", device,
+							      &video_cooling_ops);
 	if (IS_ERR(device->cooling_dev)) {
 		/*
 		 * Set cooling_dev to NULL so we don't crash trying to free it.
@@ -2011,8 +2023,8 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	}
 
 	video->device = device;
-	strcpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
-	strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
+	strscpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
+	strscpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
 	device->driver_data = video;
 
 	acpi_video_bus_find_cap(video);
@@ -2031,13 +2043,13 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	 * HP ZBook Fury 16 G10 requires ACPI video's child devices have _PS0
 	 * evaluated to have functional panel brightness control.
 	 */
-	acpi_device_fix_up_power_extended(device);
+	acpi_device_fix_up_power_children(device);
 
 	pr_info("%s [%s] (multi-head: %s  rom: %s  post: %s)\n",
 	       ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
-	       video->flags.multihead ? "yes" : "no",
-	       video->flags.rom ? "yes" : "no",
-	       video->flags.post ? "yes" : "no");
+	       str_yes_no(video->flags.multihead),
+	       str_yes_no(video->flags.rom),
+	       str_yes_no(video->flags.post));
 	mutex_lock(&video_list_lock);
 	list_add_tail(&video->entry, &video_bus_head);
 	mutex_unlock(&video_list_lock);
@@ -2141,57 +2153,6 @@ static int __init intel_opregion_present(void)
 	return opregion;
 }
 
-/* Check if the chassis-type indicates there is no builtin LCD panel */
-static bool dmi_is_desktop(void)
-{
-	const char *chassis_type;
-	unsigned long type;
-
-	chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
-	if (!chassis_type)
-		return false;
-
-	if (kstrtoul(chassis_type, 10, &type) != 0)
-		return false;
-
-	switch (type) {
-	case 0x03: /* Desktop */
-	case 0x04: /* Low Profile Desktop */
-	case 0x05: /* Pizza Box */
-	case 0x06: /* Mini Tower */
-	case 0x07: /* Tower */
-	case 0x10: /* Lunch Box */
-	case 0x11: /* Main Server Chassis */
-		return true;
-	}
-
-	return false;
-}
-
-/*
- * We're seeing a lot of bogus backlight interfaces on newer machines
- * without a LCD such as desktops, servers and HDMI sticks. Checking the
- * lcd flag fixes this, enable this by default on any machines which are:
- * 1.  Win8 ready (where we also prefer the native backlight driver, so
- *     normally the acpi_video code should not register there anyways); *and*
- * 2.1 Report a desktop/server DMI chassis-type, or
- * 2.2 Are an ACPI-reduced-hardware platform (and thus won't use the EC for
-       backlight control)
- */
-static bool should_check_lcd_flag(void)
-{
-	if (!acpi_osi_is_win8())
-		return false;
-
-	if (dmi_is_desktop())
-		return true;
-
-	if (acpi_reduced_hardware())
-		return true;
-
-	return false;
-}
-
 int acpi_video_register(void)
 {
 	int ret = 0;
@@ -2205,9 +2166,6 @@ int acpi_video_register(void)
 		goto leave;
 	}
 
-	if (only_lcd == -1)
-		only_lcd = should_check_lcd_flag();
-
 	dmi_check_system(video_dmi_table);
 
 	ret = acpi_bus_register_driver(&acpi_video_bus);
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index ca28183f4d13..14b24157799c 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -81,7 +81,7 @@ static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
 	return wdat;
 }
 
-/**
+/*
  * Returns true if this system should prefer ACPI based watchdog instead of
  * the native one (which are typically the same hardware).
  */
@@ -179,7 +179,7 @@ void __init acpi_watchdog_init(void)
 	pdev = platform_device_register_simple("wdat_wdt", PLATFORM_DEVID_NONE,
 					       resources, nresources);
 	if (IS_ERR(pdev))
-		pr_err("Device creation failed: %ld\n", PTR_ERR(pdev));
+		pr_err("Device creation failed: %pe\n", pdev);
 
 	kfree(resources);
 
diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index 30f3fc13c29d..8d18af396de9 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -5,6 +5,7 @@
 
 ccflags-y			:= -D_LINUX -DBUILDING_ACPICA
 ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
+CFLAGS_tbfind.o 		+= $(call cc-disable-warning, stringop-truncation)
 
 # use acpi.o to put all files here into acpi.o modparam namespace
 obj-y	+= acpi.o
diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index 9d4cbd956627..d7d4649ce66f 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -3,7 +3,7 @@
  *
  * Module Name: acapps - common include for ACPI applications/tools
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -17,7 +17,7 @@
 /* Common info for tool signons */
 
 #define ACPICA_NAME                 "Intel ACPI Component Architecture"
-#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2022 Intel Corporation"
+#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2025 Intel Corporation"
 
 #if ACPI_MACHINE_WIDTH == 64
 #define ACPI_WIDTH          " (64-bit version)"
diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h
index 4536dc9d3979..662231f4f881 100644
--- a/drivers/acpi/acpica/accommon.h
+++ b/drivers/acpi/acpica/accommon.h
@@ -3,7 +3,7 @@
  *
  * Name: accommon.h - Common include files for generation of ACPICA source
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acconvert.h b/drivers/acpi/acpica/acconvert.h
index c6ba6a36cfb5..24998f2d7539 100644
--- a/drivers/acpi/acpica/acconvert.h
+++ b/drivers/acpi/acpica/acconvert.h
@@ -3,7 +3,7 @@
  *
  * Module Name: acapps - common include for ACPI applications/tools
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 911875c5a5f1..91241bd6917a 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -3,7 +3,7 @@
  *
  * Name: acdebug.h - ACPI/AML debugger
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h
index 73eecbf62f06..5d48a344b35f 100644
--- a/drivers/acpi/acpica/acdispat.h
+++ b/drivers/acpi/acpica/acdispat.h
@@ -3,7 +3,7 @@
  *
  * Name: acdispat.h - dispatcher (parser to interpreter interface)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index ddd072cbc738..b40fb3a5ac8a 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -3,7 +3,7 @@
  *
  * Name: acevents.h - Event subcomponent prototypes and defines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -188,7 +188,7 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
 		      u8 acpi_ns_is_locked);
 
 void
-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
+acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
 			    acpi_adr_space_type space_id, u32 function);
 
 acpi_status
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index f4c90fc99be2..c8a750d2674c 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -3,7 +3,7 @@
  *
  * Name: acglobal.h - Declarations for global variables
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -29,11 +29,7 @@ ACPI_INIT_GLOBAL(u32, acpi_gbl_dsdt_index, ACPI_INVALID_TABLE_INDEX);
 ACPI_INIT_GLOBAL(u32, acpi_gbl_facs_index, ACPI_INVALID_TABLE_INDEX);
 ACPI_INIT_GLOBAL(u32, acpi_gbl_xfacs_index, ACPI_INVALID_TABLE_INDEX);
 ACPI_INIT_GLOBAL(u32, acpi_gbl_fadt_index, ACPI_INVALID_TABLE_INDEX);
-
-#if (!ACPI_REDUCED_HARDWARE)
-ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_FACS);
-
-#endif				/* !ACPI_REDUCED_HARDWARE */
+ACPI_INIT_GLOBAL(struct acpi_table_facs *, acpi_gbl_FACS, NULL);
 
 /* These addresses are calculated from the FADT Event Block addresses */
 
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 79bbfe00d241..6aec56c65fa0 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -3,7 +3,7 @@
  *
  * Name: achware.h -- hardware specific interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -103,8 +103,6 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info,
 
 acpi_status acpi_hw_enable_all_runtime_gpes(void);
 
-acpi_status acpi_hw_enable_all_wakeup_gpes(void);
-
 u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number);
 
 acpi_status
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index 955114c926bd..1ee6ac9b2baf 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -3,7 +3,7 @@
  *
  * Name: acinterp.h - Interpreter subcomponent prototypes and defines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -120,6 +120,9 @@ void
 acpi_ex_trace_point(acpi_trace_event_type type,
 		    u8 begin, u8 *aml, char *pathname);
 
+void
+acpi_ex_trace_args(union acpi_operand_object **params, u32 count);
+
 /*
  * exfield - ACPI AML (p-code) execution - field manipulation
  */
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 82563b44af35..f98640086f4e 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -3,7 +3,7 @@
  *
  * Name: aclocal.h - Internal data types used across the ACPI subsystem
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state);
  * expected_return_btypes - Allowed type(s) for the return value
  */
 struct acpi_name_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	u16 argument_list;
 	u8 expected_btypes;
 };
@@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node *
 					      converted_object);
 
 struct acpi_simple_repair_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	u32 unexpected_btypes;
 	u32 package_index;
 	acpi_object_converter object_converter;
@@ -547,7 +547,7 @@ struct acpi_field_info {
 
 struct acpi_ged_handler_info {
 	struct acpi_ged_handler_info *next;
-	u32 int_id;		/* The interrupt ID that triggers the execution ofthe evt_method. */
+	u32 int_id;		/* The interrupt ID that triggers the execution of the evt_method. */
 	struct acpi_namespace_node *evt_method;	/* The _EVT method to be executed when an interrupt with ID = int_ID is received */
 };
 
@@ -1090,6 +1090,8 @@ struct acpi_port_info {
 #define ACPI_ADDRESS_TYPE_IO_RANGE              1
 #define ACPI_ADDRESS_TYPE_BUS_NUMBER_RANGE      2
 
+#define ACPI_ADDRESS_TYPE_PCC_NUMBER            0xA
+
 /* Resource descriptor types and masks */
 
 #define ACPI_RESOURCE_NAME_LARGE                0x80
@@ -1139,7 +1141,7 @@ struct acpi_port_info {
 #define ACPI_RESOURCE_NAME_PIN_GROUP_FUNCTION   0x91
 #define ACPI_RESOURCE_NAME_PIN_GROUP_CONFIG     0x92
 #define ACPI_RESOURCE_NAME_CLOCK_INPUT          0x93
-#define ACPI_RESOURCE_NAME_LARGE_MAX            0x94
+#define ACPI_RESOURCE_NAME_LARGE_MAX            0x93
 
 /*****************************************************************************
  *
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index de83dd22292b..4e9402c02410 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -3,7 +3,7 @@
  *
  * Name: acmacros.h - C macros for the entire subsystem.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 9448bc026b9b..13f050fecb49 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -3,7 +3,7 @@
  *
  * Name: acnamesp.h - Namespace subcomponent prototypes and defines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index 1bdfeee5d7c5..6ffcc7a0a0c2 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -3,7 +3,7 @@
  *
  * Name: acobject.h - Definition of union acpi_operand_object  (Internal object only)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -48,7 +48,7 @@
 	u8                              descriptor_type;    /* To differentiate various internal objs */\
 	u8                              type;               /* acpi_object_type */\
 	u16                             reference_count;    /* For object deletion management */\
-	u8                              flags;
+	u8                              flags
 	/*
 	 * Note: There are 3 bytes available here before the
 	 * next natural alignment boundary (for both 32/64 cases)
@@ -71,10 +71,12 @@
  *****************************************************************************/
 
 struct acpi_object_common {
-ACPI_OBJECT_COMMON_HEADER};
+	ACPI_OBJECT_COMMON_HEADER;
+};
 
 struct acpi_object_integer {
-	ACPI_OBJECT_COMMON_HEADER u8 fill[3];	/* Prevent warning on some compilers */
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 fill[3];		/* Prevent warning on some compilers */
 	u64 value;
 };
 
@@ -86,23 +88,26 @@ struct acpi_object_integer {
  */
 #define ACPI_COMMON_BUFFER_INFO(_type) \
 	_type                           *pointer; \
-	u32                             length;
+	u32                             length
 
 /* Null terminated, ASCII characters only */
 
 struct acpi_object_string {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_BUFFER_INFO(char)	/* String in AML stream or allocated string */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_BUFFER_INFO(char);	/* String in AML stream or allocated string */
 };
 
 struct acpi_object_buffer {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_BUFFER_INFO(u8)	/* Buffer in AML stream or allocated buffer */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_BUFFER_INFO(u8);	/* Buffer in AML stream or allocated buffer */
 	u32 aml_length;
 	u8 *aml_start;
 	struct acpi_namespace_node *node;	/* Link back to parent node */
 };
 
 struct acpi_object_package {
-	ACPI_OBJECT_COMMON_HEADER struct acpi_namespace_node *node;	/* Link back to parent node */
+	ACPI_OBJECT_COMMON_HEADER;
+	struct acpi_namespace_node *node;	/* Link back to parent node */
 	union acpi_operand_object **elements;	/* Array of pointers to acpi_objects */
 	u8 *aml_start;
 	u32 aml_length;
@@ -116,11 +121,13 @@ struct acpi_object_package {
  *****************************************************************************/
 
 struct acpi_object_event {
-	ACPI_OBJECT_COMMON_HEADER acpi_semaphore os_semaphore;	/* Actual OS synchronization object */
+	ACPI_OBJECT_COMMON_HEADER;
+	acpi_semaphore os_semaphore;	/* Actual OS synchronization object */
 };
 
 struct acpi_object_mutex {
-	ACPI_OBJECT_COMMON_HEADER u8 sync_level;	/* 0-15, specified in Mutex() call */
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 sync_level;		/* 0-15, specified in Mutex() call */
 	u16 acquisition_depth;	/* Allow multiple Acquires, same thread */
 	acpi_mutex os_mutex;	/* Actual OS synchronization object */
 	acpi_thread_id thread_id;	/* Current owner of the mutex */
@@ -132,7 +139,8 @@ struct acpi_object_mutex {
 };
 
 struct acpi_object_region {
-	ACPI_OBJECT_COMMON_HEADER u8 space_id;
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 space_id;
 	struct acpi_namespace_node *node;	/* Containing namespace node */
 	union acpi_operand_object *handler;	/* Handler for region access */
 	union acpi_operand_object *next;
@@ -142,7 +150,8 @@ struct acpi_object_region {
 };
 
 struct acpi_object_method {
-	ACPI_OBJECT_COMMON_HEADER u8 info_flags;
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 info_flags;
 	u8 param_count;
 	u8 sync_level;
 	union acpi_operand_object *mutex;
@@ -178,33 +187,43 @@ struct acpi_object_method {
  */
 #define ACPI_COMMON_NOTIFY_INFO \
 	union acpi_operand_object       *notify_list[2];    /* Handlers for system/device notifies */\
-	union acpi_operand_object       *handler;	/* Handler for Address space */
+	union acpi_operand_object       *handler	/* Handler for Address space */
 
 /* COMMON NOTIFY for POWER, PROCESSOR, DEVICE, and THERMAL */
 
 struct acpi_object_notify_common {
-ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_NOTIFY_INFO};
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_NOTIFY_INFO;
+};
 
 struct acpi_object_device {
-	ACPI_OBJECT_COMMON_HEADER
-	    ACPI_COMMON_NOTIFY_INFO struct acpi_gpe_block_info *gpe_block;
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_NOTIFY_INFO;
+	struct acpi_gpe_block_info *gpe_block;
 };
 
 struct acpi_object_power_resource {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_NOTIFY_INFO u32 system_level;
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_NOTIFY_INFO;
+	u32 system_level;
 	u32 resource_order;
 };
 
 struct acpi_object_processor {
-	ACPI_OBJECT_COMMON_HEADER
-	    /* The next two fields take advantage of the 3-byte space before NOTIFY_INFO */
+	ACPI_OBJECT_COMMON_HEADER;
+
+	/* The next two fields take advantage of the 3-byte space before NOTIFY_INFO */
+
 	u8 proc_id;
 	u8 length;
-	ACPI_COMMON_NOTIFY_INFO acpi_io_address address;
+	ACPI_COMMON_NOTIFY_INFO;
+	acpi_io_address address;
 };
 
 struct acpi_object_thermal_zone {
-ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_NOTIFY_INFO};
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_NOTIFY_INFO;
+};
 
 /******************************************************************************
  *
@@ -226,17 +245,21 @@ ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_NOTIFY_INFO};
 	u32                             base_byte_offset;   /* Byte offset within containing object */\
 	u32                             value;              /* Value to store into the Bank or Index register */\
 	u8                              start_field_bit_offset;/* Bit offset within first field datum (0-63) */\
-	u8                              access_length;	/* For serial regions/fields */
+	u8                              access_length	/* For serial regions/fields */
 
 
 /* COMMON FIELD (for BUFFER, REGION, BANK, and INDEX fields) */
 
 struct acpi_object_field_common {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO union acpi_operand_object *region_obj;	/* Parent Operation Region object (REGION/BANK fields only) */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_FIELD_INFO;
+	union acpi_operand_object *region_obj;	/* Parent Operation Region object (REGION/BANK fields only) */
 };
 
 struct acpi_object_region_field {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length;
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_FIELD_INFO;
+	u16 resource_length;
 	union acpi_operand_object *region_obj;	/* Containing op_region object */
 	u8 *resource_buffer;	/* resource_template for serial regions/fields */
 	u16 pin_number_index;	/* Index relative to previous Connection/Template */
@@ -244,16 +267,20 @@ struct acpi_object_region_field {
 };
 
 struct acpi_object_bank_field {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO union acpi_operand_object *region_obj;	/* Containing op_region object */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_FIELD_INFO;
+	union acpi_operand_object *region_obj;	/* Containing op_region object */
 	union acpi_operand_object *bank_obj;	/* bank_select Register object */
 };
 
 struct acpi_object_index_field {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO
-	    /*
-	     * No "RegionObj" pointer needed since the Index and Data registers
-	     * are each field definitions unto themselves.
-	     */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_FIELD_INFO;
+
+	/*
+	 * No "RegionObj" pointer needed since the Index and Data registers
+	 * are each field definitions unto themselves.
+	 */
 	union acpi_operand_object *index_obj;	/* Index register */
 	union acpi_operand_object *data_obj;	/* Data register */
 };
@@ -261,7 +288,9 @@ struct acpi_object_index_field {
 /* The buffer_field is different in that it is part of a Buffer, not an op_region */
 
 struct acpi_object_buffer_field {
-	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u8 is_create_field;	/* Special case for objects created by create_field() */
+	ACPI_OBJECT_COMMON_HEADER;
+	ACPI_COMMON_FIELD_INFO;
+	u8 is_create_field;	/* Special case for objects created by create_field() */
 	union acpi_operand_object *buffer_obj;	/* Containing Buffer object */
 };
 
@@ -272,7 +301,8 @@ struct acpi_object_buffer_field {
  *****************************************************************************/
 
 struct acpi_object_notify_handler {
-	ACPI_OBJECT_COMMON_HEADER struct acpi_namespace_node *node;	/* Parent device */
+	ACPI_OBJECT_COMMON_HEADER;
+	struct acpi_namespace_node *node;	/* Parent device */
 	u32 handler_type;	/* Type: Device/System/Both */
 	acpi_notify_handler handler;	/* Handler address */
 	void *context;
@@ -280,7 +310,8 @@ struct acpi_object_notify_handler {
 };
 
 struct acpi_object_addr_handler {
-	ACPI_OBJECT_COMMON_HEADER u8 space_id;
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 space_id;
 	u8 handler_flags;
 	acpi_adr_space_handler handler;
 	struct acpi_namespace_node *node;	/* Parent device */
@@ -307,7 +338,8 @@ struct acpi_object_addr_handler {
  * The Reference.Class differentiates these types.
  */
 struct acpi_object_reference {
-	ACPI_OBJECT_COMMON_HEADER u8 class;	/* Reference Class */
+	ACPI_OBJECT_COMMON_HEADER;
+	u8 class;		/* Reference Class */
 	u8 target_type;		/* Used for Index Op */
 	u8 resolved;		/* Reference has been resolved to a value */
 	void *object;		/* name_op=>HANDLE to obj, index_op=>union acpi_operand_object */
@@ -340,7 +372,8 @@ typedef enum {
  * Currently: Region and field_unit types
  */
 struct acpi_object_extra {
-	ACPI_OBJECT_COMMON_HEADER struct acpi_namespace_node *method_REG;	/* _REG method for this region (if any) */
+	ACPI_OBJECT_COMMON_HEADER;
+	struct acpi_namespace_node *method_REG;	/* _REG method for this region (if any) */
 	struct acpi_namespace_node *scope_node;
 	void *region_context;	/* Region-specific data */
 	u8 *aml_start;
@@ -350,14 +383,16 @@ struct acpi_object_extra {
 /* Additional data that can be attached to namespace nodes */
 
 struct acpi_object_data {
-	ACPI_OBJECT_COMMON_HEADER acpi_object_handler handler;
+	ACPI_OBJECT_COMMON_HEADER;
+	acpi_object_handler handler;
 	void *pointer;
 };
 
 /* Structure used when objects are cached for reuse */
 
 struct acpi_object_cache_list {
-	ACPI_OBJECT_COMMON_HEADER union acpi_operand_object *next;	/* Link for object cache and internal lists */
+	ACPI_OBJECT_COMMON_HEADER;
+	union acpi_operand_object *next;	/* Link for object cache and internal lists */
 };
 
 /******************************************************************************
diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h
index da96d80e6b3a..a2a9e51d7ac6 100644
--- a/drivers/acpi/acpica/acopcode.h
+++ b/drivers/acpi/acpica/acopcode.h
@@ -3,7 +3,7 @@
  *
  * Name: acopcode.h - AML opcode information for the AML parser and interpreter
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index 6dad786a382c..65a15dee092b 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -3,7 +3,7 @@
  *
  * Module Name: acparser.h - AML Parser subcomponent prototypes and defines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 2e442f5a3123..da2c45880cc7 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -3,7 +3,7 @@
  *
  * Name: acpredef - Information table for ACPI predefined methods and objects
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -450,7 +450,8 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 
 	{{"_DSM",
 	  METHOD_4ARGS(ACPI_TYPE_BUFFER, ACPI_TYPE_INTEGER, ACPI_TYPE_INTEGER,
-		       ACPI_TYPE_PACKAGE),
+		       ACPI_TYPE_ANY | ACPI_TYPE_PACKAGE) |
+		       ARG_COUNT_IS_MINIMUM,
 	  METHOD_RETURNS(ACPI_RTYPE_ALL)}},	/* Must return a value, but it can be of any type */
 
 	{{"_DSS", METHOD_1ARGS(ACPI_TYPE_INTEGER),
diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h
index d772ff9ca07d..e8a92be5adae 100644
--- a/drivers/acpi/acpica/acresrc.h
+++ b/drivers/acpi/acpica/acresrc.h
@@ -3,7 +3,7 @@
  *
  * Name: acresrc.h - Resource Manager function prototypes
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index f8fee94ba708..e690f604cfa0 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -3,7 +3,7 @@
  *
  * Name: acstruct.h - Internal structs
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index b6ae979b01b6..ebef72bf58d0 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -3,7 +3,7 @@
  *
  * Name: actables.h - ACPI table management
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index edfdbbef81c1..3990d509bbab 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -3,7 +3,7 @@
  *
  * Name: acutils.h -- prototypes for the common (subsystem-wide) procedures
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h
index effe52b40dce..c5b544a006c5 100644
--- a/drivers/acpi/acpica/amlcode.h
+++ b/drivers/acpi/acpica/amlcode.h
@@ -5,7 +5,7 @@
  *                   Declarations and definitions contained herein are derived
  *                   directly from the ACPI specification.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h
index 4e88f9fc2a28..54d6e51e0b9a 100644
--- a/drivers/acpi/acpica/amlresrc.h
+++ b/drivers/acpi/acpica/amlresrc.h
@@ -3,7 +3,7 @@
  *
  * Module Name: amlresrc.h - AML resource descriptors
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -504,10 +504,6 @@ struct aml_resource_pin_group_config {
 
 #define AML_RESOURCE_PIN_GROUP_CONFIG_REVISION    1	/* ACPI 6.2 */
 
-/* restore default alignment */
-
-#pragma pack()
-
 /* Union of all resource descriptors, so we can allocate the worst case */
 
 union aml_resource {
@@ -562,6 +558,10 @@ union aml_resource {
 	u8 byte_item;
 };
 
+/* restore default alignment */
+
+#pragma pack()
+
 /* Interfaces used by both the disassembler and compiler */
 
 void
diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c
index 2b84ac093698..8dbab6932049 100644
--- a/drivers/acpi/acpica/dbconvert.c
+++ b/drivers/acpi/acpica/dbconvert.c
@@ -174,6 +174,8 @@ acpi_status acpi_db_convert_to_package(char *string, union acpi_object *object)
 	elements =
 	    ACPI_ALLOCATE_ZEROED(DB_DEFAULT_PKG_ELEMENTS *
 				 sizeof(union acpi_object));
+	if (!elements)
+		return (AE_NO_MEMORY);
 
 	this = string;
 	for (i = 0; i < (DB_DEFAULT_PKG_ELEMENTS - 1); i++) {
diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c
index e874c1dddefa..554ae35108bd 100644
--- a/drivers/acpi/acpica/dbhistry.c
+++ b/drivers/acpi/acpica/dbhistry.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dbhistry - debugger HISTORY command
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index b91155ea9c34..c9131259f717 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle,
 	ACPI_FREE(buffer.pointer);
 
 	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
-	acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
-
+	status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_os_printf("Could Not evaluate object %p\n",
+			       obj_handle);
+		return (AE_OK);
+	}
 	/*
 	 * Since this is a field unit, surround the output in braces
 	 */
diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c
index 4354c175e12e..e2f00c54cb36 100644
--- a/drivers/acpi/acpica/dsargs.c
+++ b/drivers/acpi/acpica/dsargs.c
@@ -4,7 +4,7 @@
  * Module Name: dsargs - Support for execution of dynamic arguments for static
  *                       objects (regions, fields, buffer fields, etc.)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 80c69af06948..c1f79d7a2026 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -4,7 +4,7 @@
  * Module Name: dscontrol - Support for execution control opcodes -
  *                          if/else/while/return
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c
index c5c8380a3114..274b74255551 100644
--- a/drivers/acpi/acpica/dsdebug.c
+++ b/drivers/acpi/acpica/dsdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsdebug - Parser/Interpreter interface - debugging
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 532401ecdab0..df132c9089c7 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsfield - Dispatcher field routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index 6e0e362e461f..57cd9e2d1109 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsinit - Object initialization namespace walk
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index e809c2aed78a..45ec32e81903 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsmethod - Parser/Interpreter interface - control method parsing
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -462,7 +462,6 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 	struct acpi_walk_state *next_walk_state = NULL;
 	union acpi_operand_object *obj_desc;
 	struct acpi_evaluate_info *info;
-	u32 i;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_call_control_method, this_walk_state);
 
@@ -483,6 +482,20 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 		return_ACPI_STATUS(AE_NULL_OBJECT);
 	}
 
+	if (this_walk_state->num_operands < obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Missing argument(s) for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_TOO_FEW_ARGUMENTS);
+	}
+
+	else if (this_walk_state->num_operands > obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Too many arguments for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_TOO_MANY_ARGUMENTS);
+	}
+
 	/* Init for new method, possibly wait on method mutex */
 
 	status =
@@ -539,14 +552,7 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 	 * Delete the operands on the previous walkstate operand stack
 	 * (they were copied to new objects)
 	 */
-	for (i = 0; i < obj_desc->method.param_count; i++) {
-		acpi_ut_remove_reference(this_walk_state->operands[i]);
-		this_walk_state->operands[i] = NULL;
-	}
-
-	/* Clear the operand stack */
-
-	this_walk_state->num_operands = 0;
+	acpi_ds_clear_operands(this_walk_state);
 
 	ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
 			  "**** Begin nested execution of [%4.4s] **** WalkState=%p\n",
diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c
index eca50517ad82..5393de4dbc4c 100644
--- a/drivers/acpi/acpica/dsmthdat.c
+++ b/drivers/acpi/acpica/dsmthdat.c
@@ -188,6 +188,7 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
 
 		index++;
 	}
+	acpi_ex_trace_args(params, index);
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%u args passed to method\n", index));
 	return_ACPI_STATUS(AE_OK);
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index 555f148d666b..1bf7eec49899 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsobject - Dispatcher object management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index dd3059000885..5699b0872848 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsopcode - Dispatcher support for regions and fields
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c
index ecf793fe9919..1ed2386fab82 100644
--- a/drivers/acpi/acpica/dspkginit.c
+++ b/drivers/acpi/acpica/dspkginit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dspkginit - Completion of deferred package initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index fb9ed5e1da89..baf6a1f27605 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -668,6 +668,8 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 	union acpi_parse_object *arguments[ACPI_OBJ_NUM_OPERANDS];
 	u32 arg_count = 0;
 	u32 index = walk_state->num_operands;
+	u32 prev_num_operands = walk_state->num_operands;
+	u32 new_num_operands;
 	u32 i;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_create_operands, first_arg);
@@ -696,6 +698,7 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 
 	/* Create the interpreter arguments, in reverse order */
 
+	new_num_operands = index;
 	index--;
 	for (i = 0; i < arg_count; i++) {
 		arg = arguments[index];
@@ -720,7 +723,11 @@ cleanup:
 	 * pop everything off of the operand stack and delete those
 	 * objects
 	 */
-	acpi_ds_obj_stack_pop_and_delete(arg_count, walk_state);
+	walk_state->num_operands = (u8)(i);
+	acpi_ds_obj_stack_pop_and_delete(new_num_operands, walk_state);
+
+	/* Restore operand count */
+	walk_state->num_operands = (u8)(prev_num_operands);
 
 	ACPI_EXCEPTION((AE_INFO, status, "While creating Arg %u", index));
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index a43336f05206..5c5c6d8a4e48 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -4,7 +4,7 @@
  * Module Name: dswexec - Dispatcher method execution callbacks;
  *                        dispatch to interpreter.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index f7b8496c8bdd..666419b6a5c6 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswload - Dispatcher first pass namespace load callbacks
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 541235f498c2..bfc54c914757 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswload2 - Dispatcher second pass namespace load callbacks
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index 1fdd07ae862c..375a8fa43d9d 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswscope - Scope stack manipulation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index 75338a13c802..02aaddb89df9 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswstate - Dispatcher parse tree walk management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index 9e78c5b9ad52..6cdd39c987b8 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evevent - Fixed Event handling and dispatch
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
index 989dc01af03f..df2a4ab0e0da 100644
--- a/drivers/acpi/acpica/evglock.c
+++ b/drivers/acpi/acpica/evglock.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evglock - Global Lock support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -42,6 +42,10 @@ acpi_status acpi_ev_init_global_lock_handler(void)
 		return_ACPI_STATUS(AE_OK);
 	}
 
+	if (!acpi_gbl_use_global_lock) {
+		return_ACPI_STATUS(AE_OK);
+	}
+
 	/* Attempt installation of the global lock handler */
 
 	status = acpi_install_fixed_event_handler(ACPI_EVENT_GLOBAL,
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 934b201d3820..ba65b2ea49b2 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpe - General Purpose Event handling and dispatch
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index 58e1890ab25b..fadd93caf1d5 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeblk - GPE block creation and initialization.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 0dbc4d88919a..eb769739420e 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeinit - System GPE initialization and update
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -413,6 +413,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 	gpe_event_info->flags &= ~(ACPI_GPE_DISPATCH_MASK);
 	gpe_event_info->flags |= (u8)(type | ACPI_GPE_DISPATCH_METHOD);
 	gpe_event_info->dispatch.method_node = method_node;
+	walk_info->count++;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_LOAD,
 			  "Registered GPE method %s as GPE number 0x%.2X\n",
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index ee3b1ea656d4..d15b1d75c8ec 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeutil - GPE utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c
index 1c8cb6d924df..5a35dae945e2 100644
--- a/drivers/acpi/acpica/evhandler.c
+++ b/drivers/acpi/acpica/evhandler.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evhandler - Support for Address Space handlers
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index e68e876d3b84..04a23a6c3bb1 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evmisc - Miscellaneous event manager support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 18fdf2bc2d49..fa3475da7ea9 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evregion - Operation Region support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -65,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void)
 						acpi_gbl_default_address_spaces
 						[i])) {
 			acpi_ev_execute_reg_methods(acpi_gbl_root_node,
+						    ACPI_UINT32_MAX,
 						    acpi_gbl_default_address_spaces
 						    [i], ACPI_REG_CONNECT);
 		}
@@ -672,6 +673,7 @@ cleanup1:
  * FUNCTION:    acpi_ev_execute_reg_methods
  *
  * PARAMETERS:  node            - Namespace node for the device
+ *              max_depth       - Depth to which search for _REG
  *              space_id        - The address space ID
  *              function        - Passed to _REG: On (1) or Off (0)
  *
@@ -683,7 +685,7 @@ cleanup1:
  ******************************************************************************/
 
 void
-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
+acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
 			    acpi_adr_space_type space_id, u32 function)
 {
 	struct acpi_reg_walk_info info;
@@ -717,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 	 * regions and _REG methods. (i.e. handlers must be installed for all
 	 * regions of this Space ID before we can run any _REG methods)
 	 */
-	(void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX,
+	(void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth,
 				     ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL,
 				     &info, NULL);
 
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 46d1b3f5582d..b03952798af5 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evrgnini- ACPI address_space (op_region) init
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 24fa6433d562..86a8d41c079c 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxface - External interfaces for ACPI events
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index 48bf845191d2..4b052908d2e7 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxfevnt - External Interfaces, ACPI event disable/enable
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 4eeeb3b7ab7e..60dacec1b121 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxfgpe - External Interfaces for General Purpose Events (GPEs)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index 3197e6303c5b..bccc672c934c 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -4,7 +4,7 @@
  * Module Name: evxfregn - External Interfaces, ACPI Operation Regions and
  *                         Address Spaces.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device,
 	/* Run all _REG methods for this address space */
 
 	if (run_reg) {
-		acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
+		acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id,
+					    ACPI_REG_CONNECT);
 	}
 
 unlock_and_exit:
@@ -231,8 +232,6 @@ acpi_remove_address_space_handler(acpi_handle device,
 
 			/* Now we can delete the handler object */
 
-			acpi_os_release_mutex(handler_obj->address_space.
-					      context_mutex);
 			acpi_ut_remove_reference(handler_obj);
 			goto unlock_and_exit;
 		}
@@ -263,6 +262,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
  * FUNCTION:    acpi_execute_reg_methods
  *
  * PARAMETERS:  device          - Handle for the device
+ *              max_depth       - Depth to which search for _REG
  *              space_id        - The address space ID
  *
  * RETURN:      Status
@@ -271,7 +271,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
  *
  ******************************************************************************/
 acpi_status
-acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
+acpi_execute_reg_methods(acpi_handle device, u32 max_depth,
+			 acpi_adr_space_type space_id)
 {
 	struct acpi_namespace_node *node;
 	acpi_status status;
@@ -296,7 +297,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
 
 		/* Run all _REG methods for this address space */
 
-		acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
+		acpi_ev_execute_reg_methods(node, max_depth, space_id,
+					    ACPI_REG_CONNECT);
 	} else {
 		status = AE_BAD_PARAMETER;
 	}
diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c
index 2fb78b35565b..c248c9b162fa 100644
--- a/drivers/acpi/acpica/exconcat.c
+++ b/drivers/acpi/acpica/exconcat.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconcat - Concatenate-type AML operators
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 473115309860..4d7dd0fc6b07 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconfig - Namespace reconfiguration (Load/Unload opcodes)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index 3729bf3b74f7..fded9bfc2436 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconvrt - Object conversion routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -17,7 +17,8 @@ ACPI_MODULE_NAME("exconvrt")
 
 /* Local prototypes */
 static u32
-acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 max_length);
+acpi_ex_convert_to_ascii(u64 integer,
+			 u16 base, u8 *string, u8 max_length, u8 leading_zeros);
 
 /*******************************************************************************
  *
@@ -225,8 +226,8 @@ acpi_ex_convert_to_buffer(union acpi_operand_object *obj_desc,
 		/* Copy the string to the buffer */
 
 		new_buf = return_desc->buffer.pointer;
-		strncpy((char *)new_buf, (char *)obj_desc->string.pointer,
-			obj_desc->string.length);
+		memcpy((char *)new_buf, (char *)obj_desc->string.pointer,
+		       obj_desc->string.length);
 		break;
 
 	default:
@@ -249,6 +250,7 @@ acpi_ex_convert_to_buffer(union acpi_operand_object *obj_desc,
  *              base            - ACPI_STRING_DECIMAL or ACPI_STRING_HEX
  *              string          - Where the string is returned
  *              data_width      - Size of data item to be converted, in bytes
+ *              leading_zeros   - Allow leading zeros
  *
  * RETURN:      Actual string length
  *
@@ -257,7 +259,8 @@ acpi_ex_convert_to_buffer(union acpi_operand_object *obj_desc,
  ******************************************************************************/
 
 static u32
-acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 data_width)
+acpi_ex_convert_to_ascii(u64 integer,
+			 u16 base, u8 *string, u8 data_width, u8 leading_zeros)
 {
 	u64 digit;
 	u32 i;
@@ -266,7 +269,8 @@ acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 data_width)
 	u32 hex_length;
 	u32 decimal_length;
 	u32 remainder;
-	u8 supress_zeros;
+	u8 supress_zeros = !leading_zeros;
+	u8 hex_char;
 
 	ACPI_FUNCTION_ENTRY();
 
@@ -293,7 +297,6 @@ acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 data_width)
 			break;
 		}
 
-		supress_zeros = TRUE;	/* No leading zeros */
 		remainder = 0;
 
 		for (i = decimal_length; i > 0; i--) {
@@ -328,8 +331,17 @@ acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 data_width)
 
 			/* Get one hex digit, most significant digits first */
 
-			string[k] = (u8)
+			hex_char = (u8)
 			    acpi_ut_hex_to_ascii_char(integer, ACPI_MUL_4(j));
+
+			/* Supress leading zeros until the first non-zero character */
+
+			if (hex_char == ACPI_ASCII_ZERO && supress_zeros) {
+				continue;
+			}
+
+			supress_zeros = FALSE;
+			string[k] = hex_char;
 			k++;
 		}
 		break;
@@ -379,6 +391,7 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 	u32 string_length = 0;
 	u16 base = 16;
 	u8 separator = ',';
+	u8 leading_zeros;
 
 	ACPI_FUNCTION_TRACE_PTR(ex_convert_to_string, obj_desc);
 
@@ -400,14 +413,26 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 			 * Make room for the maximum decimal number size
 			 */
 			string_length = ACPI_MAX_DECIMAL_DIGITS;
+			leading_zeros = FALSE;
 			base = 10;
 			break;
 
+		case ACPI_EXPLICIT_CONVERT_HEX:
+			/*
+			 * From to_hex_string.
+			 *
+			 * Supress leading zeros and append "0x"
+			 */
+			string_length =
+			    ACPI_MUL_2(acpi_gbl_integer_byte_width) + 2;
+			leading_zeros = FALSE;
+			break;
 		default:
 
 			/* Two hex string characters for each integer byte */
 
 			string_length = ACPI_MUL_2(acpi_gbl_integer_byte_width);
+			leading_zeros = TRUE;
 			break;
 		}
 
@@ -422,17 +447,32 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 		}
 
 		new_buf = return_desc->buffer.pointer;
+		if (type == ACPI_EXPLICIT_CONVERT_HEX) {
+
+			/* Append "0x" prefix for explicit hex conversion */
+
+			*new_buf++ = '0';
+			*new_buf++ = 'x';
+		}
 
 		/* Convert integer to string */
 
 		string_length =
 		    acpi_ex_convert_to_ascii(obj_desc->integer.value, base,
 					     new_buf,
-					     acpi_gbl_integer_byte_width);
+					     acpi_gbl_integer_byte_width,
+					     leading_zeros);
 
 		/* Null terminate at the correct place */
 
 		return_desc->string.length = string_length;
+		if (type == ACPI_EXPLICIT_CONVERT_HEX) {
+
+			/* Take "0x" prefix into account */
+
+			return_desc->string.length += 2;
+		}
+
 		new_buf[string_length] = 0;
 		break;
 
@@ -448,6 +488,7 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 			 * From ACPI: "If the input is a buffer, it is converted to a
 			 * a string of decimal values separated by commas."
 			 */
+			leading_zeros = FALSE;
 			base = 10;
 
 			/*
@@ -475,6 +516,7 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 			 *
 			 * Each hex number is prefixed with 0x (11/2018)
 			 */
+			leading_zeros = TRUE;
 			separator = ' ';
 			string_length = (obj_desc->buffer.length * 5);
 			break;
@@ -488,6 +530,7 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 			 *
 			 * Each hex number is prefixed with 0x (11/2018)
 			 */
+			leading_zeros = TRUE;
 			separator = ',';
 			string_length = (obj_desc->buffer.length * 5);
 			break;
@@ -528,7 +571,8 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 
 			new_buf += acpi_ex_convert_to_ascii((u64) obj_desc->
 							    buffer.pointer[i],
-							    base, new_buf, 1);
+							    base, new_buf, 1,
+							    leading_zeros);
 
 			/* Each digit is separated by either a comma or space */
 
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 1bea9d97652c..052c69567997 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -3,7 +3,7 @@
  *
  * Module Name: excreate - Named object creation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index 3f86bfada510..81a07a52b73c 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exdebug - Support for stores to the AML Debug Object
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 2e2da8790224..d8aeebaab70a 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exdump - Interpreter debug output routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index 61ff36189ace..ced3ff9d0a86 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exfield - AML execution - field_unit read/write
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index cf6c812a8b6d..0771934c0455 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exfldio - Aml Field I/O
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index c6f2a9166ac0..07cbac58ed21 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c
index 65c487facdda..1fa013197fcf 100644
--- a/drivers/acpi/acpica/exmutex.c
+++ b/drivers/acpi/acpica/exmutex.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exmutex - ASL Mutex Acquire/Release functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index 9a448165bfeb..76ab73c37e90 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exnames - interpreter/scanner name load/execute
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 20fb34b68bee..6ac7e0ca5c9d 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg1 - AML execution - opcodes with 1 argument
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index 743c258bf2e8..a94fa4d70e99 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg2 - AML execution - opcodes with 2 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index d3091f619909..bf08110ed6d2 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg3 - AML execution - opcodes with 3 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index 1af35e143ba9..cb078e39abf7 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg6 - AML execution - opcodes with 6 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 08196fa17080..1b1a006e82de 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exprep - ACPI AML field prep utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -437,6 +437,9 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 
 		if (info->connection_node) {
 			second_desc = info->connection_node->object;
+			if (second_desc == NULL) {
+				break;
+			}
 			if (!(second_desc->common.flags & AOPOBJ_DATA_VALID)) {
 				status =
 				    acpi_ds_get_buffer_arguments(second_desc);
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index 8907b8bf4267..a390a1c2b0ab 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exregion - ACPI default op_region (address space) handlers
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -44,7 +44,6 @@ acpi_ex_system_memory_space_handler(u32 function,
 	struct acpi_mem_mapping *mm = mem_info->cur_mm;
 	u32 length;
 	acpi_size map_length;
-	acpi_size page_boundary_map_length;
 #ifdef ACPI_MISALIGNMENT_NOT_SUPPORTED
 	u32 remainder;
 #endif
@@ -138,26 +137,8 @@ acpi_ex_system_memory_space_handler(u32 function,
 		map_length = (acpi_size)
 		    ((mem_info->address + mem_info->length) - address);
 
-		/*
-		 * If mapping the entire remaining portion of the region will cross
-		 * a page boundary, just map up to the page boundary, do not cross.
-		 * On some systems, crossing a page boundary while mapping regions
-		 * can cause warnings if the pages have different attributes
-		 * due to resource management.
-		 *
-		 * This has the added benefit of constraining a single mapping to
-		 * one page, which is similar to the original code that used a 4k
-		 * maximum window.
-		 */
-		page_boundary_map_length = (acpi_size)
-		    (ACPI_ROUND_UP(address, ACPI_DEFAULT_PAGE_SIZE) - address);
-		if (page_boundary_map_length == 0) {
-			page_boundary_map_length = ACPI_DEFAULT_PAGE_SIZE;
-		}
-
-		if (map_length > page_boundary_map_length) {
-			map_length = page_boundary_map_length;
-		}
+		if (map_length > ACPI_DEFAULT_PAGE_SIZE)
+			map_length = ACPI_DEFAULT_PAGE_SIZE;
 
 		/* Create a new mapping starting at the address given */
 
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index 873de01b8ad2..dd83631090fc 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresnte - AML Interpreter object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index 24a78b5e266c..4589de3f3012 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresolv - AML Interpreter object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index 3a437e6ace5c..782ee353a709 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresop - AML Interpreter operand/object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c
index 5241f4c01c76..6d2581ec22ad 100644
--- a/drivers/acpi/acpica/exserial.c
+++ b/drivers/acpi/acpica/exserial.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exserial - field_unit support for serial address spaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -201,6 +201,12 @@ acpi_ex_read_serial_bus(union acpi_operand_object *obj_desc,
 		function = ACPI_READ;
 		break;
 
+	case ACPI_ADR_SPACE_FIXED_HARDWARE:
+
+		buffer_length = ACPI_FFH_INPUT_BUFFER_SIZE;
+		function = ACPI_READ;
+		break;
+
 	default:
 		return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID);
 	}
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 575c7a39f1aa..cbc42207496d 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exstore - AML Interpreter object store support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index b01ae015e1b5..0470b2639831 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -4,7 +4,7 @@
  * Module Name: exstoren - AML Interpreter object store support,
  *                        Store to Node (namespace object)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index 37c3131a82fa..5b168fbc03e8 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exstorob - AML object store support, store to object
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index f665ffd9a396..7f843c9d8a06 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exsystem - Interface to OS services
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -133,14 +133,15 @@ acpi_status acpi_ex_system_do_stall(u32 how_long_us)
 		 * (ACPI specifies 100 usec as max, but this gives some slack in
 		 * order to support existing BIOSs)
 		 */
-		ACPI_ERROR((AE_INFO,
-			    "Time parameter is too large (%u)", how_long_us));
+		ACPI_ERROR_ONCE((AE_INFO,
+				 "Time parameter is too large (%u)",
+				 how_long_us));
 		status = AE_AML_OPERAND_VALUE;
 	} else {
 		if (how_long_us > 100) {
-			ACPI_WARNING((AE_INFO,
-				      "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.",
-				      how_long_us));
+			ACPI_WARNING_ONCE((AE_INFO,
+					   "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.",
+					   how_long_us));
 		}
 		acpi_os_stall(how_long_us);
 	}
diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c
index f1730221ff13..36934d4f26fb 100644
--- a/drivers/acpi/acpica/extrace.c
+++ b/drivers/acpi/acpica/extrace.c
@@ -3,7 +3,7 @@
  *
  * Module Name: extrace - Support for interpreter execution tracing
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -136,9 +136,9 @@ acpi_ex_trace_point(acpi_trace_event_type type,
 
 	if (pathname) {
 		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
-				  "%s %s [0x%p:%s] execution.\n",
+				  "%s %s [%s] execution.\n",
 				  acpi_ex_get_trace_event_name(type),
-				  begin ? "Begin" : "End", aml, pathname));
+				  begin ? "Begin" : "End", pathname));
 	} else {
 		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
 				  "%s %s [0x%p] execution.\n",
@@ -149,6 +149,57 @@ acpi_ex_trace_point(acpi_trace_event_type type,
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ex_trace_args
+ *
+ * PARAMETERS:  params            - AML method arguments
+ *              count             - numer of method arguments
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Trace any arguments
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_trace_args(union acpi_operand_object **params, u32 count)
+{
+	u32 i;
+
+	ACPI_FUNCTION_NAME(ex_trace_args);
+
+	for (i = 0; i < count; i++) {
+		union acpi_operand_object *obj_desc = params[i];
+
+		if (!i) {
+			ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT, " "));
+		}
+
+		switch (obj_desc->common.type) {
+		case ACPI_TYPE_INTEGER:
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "%llx", obj_desc->integer.value));
+			break;
+		case ACPI_TYPE_STRING:
+			if (!obj_desc->string.length) {
+				ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "NULL"));
+				continue;
+			}
+			if (ACPI_IS_DEBUG_ENABLED(ACPI_LV_TRACE_POINT, _COMPONENT))
+				acpi_ut_print_string(obj_desc->string.pointer, ACPI_UINT8_MAX);
+			break;
+		default:
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "Unknown"));
+			break;
+		}
+		if (i+1 == count) {
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "\n"));
+		} else {
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, ", "));
+		}
+	}
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ex_start_trace_method
  *
  * PARAMETERS:  method_node         - Node of the method
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index f4d4a033f166..cc10c0732218 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exutils - interpreter/scanner utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index 790f342dcd25..a1e1fa787566 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
index a9ba9190408b..631fd8e2b774 100644
--- a/drivers/acpi/acpica/hwesleep.c
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -4,7 +4,7 @@
  * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the
  *                    extended FADT-V5 sleep registers.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index e0c847ab8324..386f4759c317 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwgpe - Low level GPE enable/disable/clear functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index e0921f08b71a..87d78bef6323 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -4,7 +4,7 @@
  * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the
  *                   original/legacy sleep/PM registers.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 192c04b5a599..a5e0bccae6a4 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -3,7 +3,7 @@
  *
  * Name: hwtimer.c - ACPI Power Management Timer Interface
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index b8de458f0368..496fd9e49f0b 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwvalid - I/O request validation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index c31f803995c6..847cd1b2493d 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwxface - Public ACPICA hardware interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 36ea48f64110..9aabe30416da 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -3,7 +3,7 @@
  *
  * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -16,20 +16,11 @@
 ACPI_MODULE_NAME("hwxfsleep")
 
 /* Local prototypes */
-#if (!ACPI_REDUCED_HARDWARE)
 static acpi_status
 acpi_hw_set_firmware_waking_vector(struct acpi_table_facs *facs,
 				   acpi_physical_address physical_address,
 				   acpi_physical_address physical_address64);
-#endif
-
-/*
- * These functions are removed for the ACPI_REDUCED_HARDWARE case:
- *      acpi_set_firmware_waking_vector
- *      acpi_enter_sleep_state_s4bios
- */
 
-#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_hw_set_firmware_waking_vector
@@ -115,6 +106,12 @@ acpi_set_firmware_waking_vector(acpi_physical_address physical_address,
 
 ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector)
 
+/*
+ * These functions are removed for the ACPI_REDUCED_HARDWARE case:
+ *      acpi_enter_sleep_state_s4bios
+ */
+
+#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_enter_sleep_state_s4bios
diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c
index 3efb46f0dc54..366d54a1d157 100644
--- a/drivers/acpi/acpica/nsarguments.c
+++ b/drivers/acpi/acpica/nsarguments.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsarguments - Validation of args for ACPI predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 7e5a683ae957..f05a92b88642 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -4,7 +4,7 @@
  * Module Name: nsconvert - Object conversions for objects returned by
  *                          predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 90a26cb0c472..6dc20486ad51 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsdump - table dumping routines for debug
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c
index fa116ebe49a3..d5b16aaec233 100644
--- a/drivers/acpi/acpica/nsdumpdv.c
+++ b/drivers/acpi/acpica/nsdumpdv.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsdump - table dumping routines for debug
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 86d126fdb27d..03373e7f7978 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsinit - namespace initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index fcb9de0f77a2..6ec4c646fff7 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsload - namespace loading/expanding/contracting procedures
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index d91153f65700..22aeeeb56cff 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -194,7 +194,7 @@ acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 			      char *full_path, u32 path_size, u8 no_trailing)
 {
 	u32 length = 0, i;
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	u8 do_no_trailing;
 	char c, *left, *right;
 	struct acpi_namespace_node *next_node;
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index 31e551cf4ea6..959e6379bc4c 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsparse - namespace interface to AML parser
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index cf57bd69616d..81995ee48c49 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nspredef - Validation of ACPI predefined methods and objects
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c
index dd37fc108fce..ca137ce5674f 100644
--- a/drivers/acpi/acpica/nsprepkg.c
+++ b/drivers/acpi/acpica/nsprepkg.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsprepkg - Validation of package objects for predefined names
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index b8657004190d..accfdcfb7e62 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsrepair - Repair for objects returned by predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index 1bb7b71f07f1..8dbb870f40d2 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -4,7 +4,7 @@
  * Module Name: nsrepair2 - Repair for objects returned by specific
  *                          predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
 				     return_object_ptr);
 
 typedef struct acpi_repair_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	acpi_repair_function repair_function;
 
 } acpi_repair_info;
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 06ffdb6808f5..49cc07e2ac5a 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -4,7 +4,7 @@
  * Module Name: nsutils - Utilities for accessing ACPI namespace, accessing
  *                        parents and siblings and Scope manipulation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index eee396a77bae..a2ac06a26e92 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nswalk - Functions for walking the ACPI namespace
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 5d5bcf165298..1db831545ec8 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -4,7 +4,7 @@
  * Module Name: nsxfname - Public interfaces to the ACPI subsystem
  *                         ACPI Namespace oriented interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 422c074ed289..6f6ae38ec044 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psargs - Parse AML opcode arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -25,6 +25,8 @@ acpi_ps_get_next_package_length(struct acpi_parse_state *parser_state);
 static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 						       *parser_state);
 
+static void acpi_ps_free_field_list(union acpi_parse_object *start);
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ps_get_next_package_length
@@ -685,6 +687,39 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ps_free_field_list
+ *
+ * PARAMETERS:  start               - First Op in field list
+ *
+ * RETURN:      None.
+ *
+ * DESCRIPTION: Free all Op objects inside a field list.
+ *
+ ******************************************************************************/
+
+static void acpi_ps_free_field_list(union acpi_parse_object *start)
+{
+	union acpi_parse_object *cur = start;
+	union acpi_parse_object *next;
+	union acpi_parse_object *arg;
+
+	while (cur) {
+		next = cur->common.next;
+
+		/* AML_INT_CONNECTION_OP can have a single argument */
+
+		arg = acpi_ps_get_arg(cur, 0);
+		if (arg) {
+			acpi_ps_free_op(arg);
+		}
+
+		acpi_ps_free_op(cur);
+		cur = next;
+	}
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ps_get_next_arg
  *
  * PARAMETERS:  walk_state          - Current state
@@ -751,6 +786,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 			while (parser_state->aml < parser_state->pkg_end) {
 				field = acpi_ps_get_next_field(parser_state);
 				if (!field) {
+					if (arg) {
+						acpi_ps_free_field_list(arg);
+					}
+
 					return_ACPI_STATUS(AE_NO_MEMORY);
 				}
 
@@ -820,6 +859,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 			    acpi_ps_get_next_namepath(walk_state, parser_state,
 						      arg,
 						      ACPI_NOT_METHOD_CALL);
+			if (ACPI_FAILURE(status)) {
+				acpi_ps_free_op(arg);
+				return_ACPI_STATUS(status);
+			}
 		} else {
 			/* Single complex argument, nothing returned */
 
@@ -854,6 +897,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 			    acpi_ps_get_next_namepath(walk_state, parser_state,
 						      arg,
 						      ACPI_POSSIBLE_METHOD_CALL);
+			if (ACPI_FAILURE(status)) {
+				acpi_ps_free_op(arg);
+				return_ACPI_STATUS(status);
+			}
 
 			if (arg->common.aml_opcode == AML_INT_METHODCALL_OP) {
 
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index d0fd55636129..c989cadf271c 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psloop - Main AML parse loop
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 54471083ba54..496a1c1d5b0b 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psobject - Support for parse objects
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -636,7 +636,8 @@ acpi_status
 acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  union acpi_parse_object *op, acpi_status status)
 {
-	acpi_status status2;
+	acpi_status return_status = status;
+	u8 ascending = TRUE;
 
 	ACPI_FUNCTION_TRACE_PTR(ps_complete_final_op, walk_state);
 
@@ -650,7 +651,7 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  op));
 	do {
 		if (op) {
-			if (walk_state->ascending_callback != NULL) {
+			if (ascending && walk_state->ascending_callback != NULL) {
 				walk_state->op = op;
 				walk_state->op_info =
 				    acpi_ps_get_opcode_info(op->common.
@@ -672,49 +673,26 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 				}
 
 				if (status == AE_CTRL_TERMINATE) {
-					status = AE_OK;
-
-					/* Clean up */
-					do {
-						if (op) {
-							status2 =
-							    acpi_ps_complete_this_op
-							    (walk_state, op);
-							if (ACPI_FAILURE
-							    (status2)) {
-								return_ACPI_STATUS
-								    (status2);
-							}
-						}
-
-						acpi_ps_pop_scope(&
-								  (walk_state->
-								   parser_state),
-								  &op,
-								  &walk_state->
-								  arg_types,
-								  &walk_state->
-								  arg_count);
-
-					} while (op);
-
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = AE_CTRL_TERMINATE;
 				}
 
 				else if (ACPI_FAILURE(status)) {
 
 					/* First error is most important */
 
-					(void)
-					    acpi_ps_complete_this_op(walk_state,
-								     op);
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = status;
 				}
 			}
 
-			status2 = acpi_ps_complete_this_op(walk_state, op);
-			if (ACPI_FAILURE(status2)) {
-				return_ACPI_STATUS(status2);
+			status = acpi_ps_complete_this_op(walk_state, op);
+			if (ACPI_FAILURE(status)) {
+				ascending = FALSE;
+				if (ACPI_SUCCESS(return_status) ||
+				    return_status == AE_CTRL_TERMINATE) {
+					return_status = status;
+				}
 			}
 		}
 
@@ -724,5 +702,5 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 
 	} while (op);
 
-	return_ACPI_STATUS(status);
+	return_ACPI_STATUS(return_status);
 }
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index 39e31030e5f4..bf6103986f48 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psopcode - Parser/Interpreter opcode information table
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c
index bccf606e08b4..532ea307a675 100644
--- a/drivers/acpi/acpica/psopinfo.c
+++ b/drivers/acpi/acpica/psopinfo.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psopinfo - AML opcode information functions and dispatch tables
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -34,7 +34,7 @@ static const u8 acpi_gbl_argument_count[] =
 
 const struct acpi_opcode_info *acpi_ps_get_opcode_info(u16 opcode)
 {
-#ifdef ACPI_DEBUG_OUTPUT
+#if defined ACPI_ASL_COMPILER && defined ACPI_DEBUG_OUTPUT
 	const char *opcode_name = "Unknown AML opcode";
 #endif
 
@@ -102,11 +102,11 @@ const struct acpi_opcode_info *acpi_ps_get_opcode_info(u16 opcode)
 	default:
 		break;
 	}
-#endif
 
 	/* Unknown AML opcode */
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%s [%4.4X]\n", opcode_name, opcode));
+#endif
 
 	return (&acpi_gbl_aml_op_info[_UNK]);
 }
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index 10a072953d78..55a416e56fd8 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psparse - Parser top level AML parse routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c
index a0035bde7556..c4e4483f0a0b 100644
--- a/drivers/acpi/acpica/psscope.c
+++ b/drivers/acpi/acpica/psscope.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psscope - Parser scope stack management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c
index 7f7f5ecd4011..5a285d3f2cdb 100644
--- a/drivers/acpi/acpica/pstree.c
+++ b/drivers/acpi/acpica/pstree.c
@@ -3,7 +3,7 @@
  *
  * Module Name: pstree - Parser op tree manipulation/traversal/search
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index d550c4af4702..ada1dc304d25 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psutils - Parser miscellaneous utilities (Parser only)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c
index d92817c72b8d..2f3ebcd8aebe 100644
--- a/drivers/acpi/acpica/pswalk.c
+++ b/drivers/acpi/acpica/pswalk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: pswalk - Parser routines to walk parsed op tree(s)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c
index 6f4eace0ba69..d480de075a90 100644
--- a/drivers/acpi/acpica/psxface.c
+++ b/drivers/acpi/acpica/psxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psxface - Parser external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index fff48001d7ef..f92010e667cd 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -272,17 +272,13 @@ u8
 acpi_rs_get_address_common(struct acpi_resource *resource,
 			   union aml_resource *aml)
 {
-	struct aml_resource_address address;
-
 	ACPI_FUNCTION_ENTRY();
 
-	/* Avoid undefined behavior: member access within misaligned address */
-
-	memcpy(&address, aml, sizeof(address));
-
 	/* Validate the Resource Type */
 
-	if ((address.resource_type > 2) && (address.resource_type < 0xC0)) {
+	if ((aml->address.resource_type > 2) &&
+	    (aml->address.resource_type < 0xC0) &&
+	    (aml->address.resource_type != 0x0A)) {
 		return (FALSE);
 	}
 
@@ -303,7 +299,7 @@ acpi_rs_get_address_common(struct acpi_resource *resource,
 		/* Generic resource type, just grab the type_specific byte */
 
 		resource->data.address.info.type_specific =
-		    address.specific_flags;
+		    aml->address.specific_flags;
 	}
 
 	return (TRUE);
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index 6e7a152d6459..242daf45e20e 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -608,18 +608,12 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 
 		case ACPI_RESOURCE_NAME_SERIAL_BUS:{
 
-				/* Avoid undefined behavior: member access within misaligned address */
-
-				struct aml_resource_common_serialbus
-				    common_serial_bus;
-				memcpy(&common_serial_bus, aml_resource,
-				       sizeof(common_serial_bus));
-
 				minimum_aml_resource_length =
 				    acpi_gbl_resource_aml_serial_bus_sizes
-				    [common_serial_bus.type];
+				    [aml_resource->common_serial_bus.type];
 				extra_struct_bytes +=
-				    common_serial_bus.resource_length -
+				    aml_resource->common_serial_bus.
+				    resource_length -
 				    minimum_aml_resource_length;
 				break;
 			}
@@ -688,16 +682,10 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 		 */
 		if (acpi_ut_get_resource_type(aml_buffer) ==
 		    ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-			/* Avoid undefined behavior: member access within misaligned address */
-
-			struct aml_resource_common_serialbus common_serial_bus;
-			memcpy(&common_serial_bus, aml_resource,
-			       sizeof(common_serial_bus));
-
 			buffer_size =
 			    acpi_gbl_resource_struct_serial_bus_sizes
-			    [common_serial_bus.type] + extra_struct_bytes;
+			    [aml_resource->common_serial_bus.type] +
+			    extra_struct_bytes;
 		} else {
 			buffer_size =
 			    acpi_gbl_resource_struct_sizes[resource_index] +
diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c
index 611bc71c193f..5b7d7074ce4f 100644
--- a/drivers/acpi/acpica/rsdump.c
+++ b/drivers/acpi/acpica/rsdump.c
@@ -48,6 +48,7 @@ static void acpi_rs_dump_address_common(union acpi_resource_data *resource);
 static void
 acpi_rs_dump_descriptor(void *resource, struct acpi_rsdump_info *table);
 
+#ifdef ACPI_DEBUGGER
 /*******************************************************************************
  *
  * FUNCTION:    acpi_rs_dump_resource_list
@@ -160,6 +161,7 @@ void acpi_rs_dump_irq_list(u8 *route_table)
 					   prt_element, prt_element->length);
 	}
 }
+#endif
 
 /*******************************************************************************
  *
diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c
index 164c96e063c6..e46efaa889cd 100644
--- a/drivers/acpi/acpica/rslist.c
+++ b/drivers/acpi/acpica/rslist.c
@@ -55,21 +55,15 @@ acpi_rs_convert_aml_to_resources(u8 * aml,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 
 	if (acpi_ut_get_resource_type(aml) == ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
-		if (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE) {
+		if (aml_resource->common_serial_bus.type >
+		    AML_RESOURCE_MAX_SERIALBUSTYPE) {
 			conversion_table = NULL;
 		} else {
 			/* This is an I2C, SPI, UART, or CSI2 serial_bus descriptor */
 
 			conversion_table =
 			    acpi_gbl_convert_resource_serial_bus_dispatch
-			    [common_serial_bus.type];
+			    [aml_resource->common_serial_bus.type];
 		}
 	} else {
 		conversion_table =
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index a1f10e4409a3..5b98e09fff76 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbdata - Table manager data structure functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 44267a92bce5..c6658b2f3027 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbfadt   - FADT table utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -315,23 +315,19 @@ void acpi_tb_parse_fadt(void)
 				       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
 				       NULL, FALSE, TRUE, &acpi_gbl_dsdt_index);
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (!acpi_gbl_reduced_hardware) {
-		if (acpi_gbl_FADT.facs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.facs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_facs_index);
-		}
-		if (acpi_gbl_FADT.Xfacs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.Xfacs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_xfacs_index);
-		}
+	if (acpi_gbl_FADT.facs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.facs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_facs_index);
+	}
+	if (acpi_gbl_FADT.Xfacs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.Xfacs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_xfacs_index);
 	}
 }
 
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 1c1b2e284bd9..d71a73216380 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbfind   - find table
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -57,8 +57,8 @@ acpi_tb_find_table(char *signature,
 
 	memset(&header, 0, sizeof(struct acpi_table_header));
 	ACPI_COPY_NAMESEG(header.signature, signature);
-	strncpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
-	strncpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
+	memcpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
+	memcpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
 
 	/* Search for the table */
 
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 0dc003c20e4d..ee9b85bc238b 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbinstal - ACPI table installation and removal
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 58b02e4b254b..049f6c2f1e32 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbprint - Table output utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -121,6 +121,14 @@ acpi_tb_print_table_header(acpi_physical_address address,
 			   ACPI_CAST_PTR(struct acpi_table_rsdp,
 					 header)->revision,
 			   local_header.oem_id));
+	} else if (acpi_gbl_CDAT && !acpi_ut_valid_nameseg(header->signature)) {
+
+		/* CDAT does not use the common ACPI table header */
+
+		ACPI_INFO(("%-4.4s 0x%8.8X%8.8X %06X",
+			   ACPI_SIG_CDAT, ACPI_FORMAT_UINT64(address),
+			   ACPI_CAST_PTR(struct acpi_table_cdat,
+					 header)->length));
 	} else {
 		/* Standard ACPI table with full common header */
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index bb4a56e5673a..fa64851c7b62 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbutils - ACPI Table utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -18,7 +18,6 @@ ACPI_MODULE_NAME("tbutils")
 static acpi_physical_address
 acpi_tb_get_root_table_entry(u8 *table_entry, u32 table_entry_size);
 
-#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_tb_initialize_facs
@@ -36,12 +35,7 @@ acpi_status acpi_tb_initialize_facs(void)
 {
 	struct acpi_table_facs *facs;
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (acpi_gbl_reduced_hardware) {
-		acpi_gbl_FACS = NULL;
-		return (AE_OK);
-	} else if (acpi_gbl_FADT.Xfacs &&
+	if (acpi_gbl_FADT.Xfacs &&
 		   (!acpi_gbl_FADT.facs
 		    || !acpi_gbl_use32_bit_facs_addresses)) {
 		(void)acpi_get_table_by_index(acpi_gbl_xfacs_index,
@@ -61,7 +55,6 @@ acpi_status acpi_tb_initialize_facs(void)
 
 	return (AE_OK);
 }
-#endif				/* !ACPI_REDUCED_HARDWARE */
 
 /*******************************************************************************
  *
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 275b52dc42e9..a8f07d2641b6 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxface - ACPI table-oriented external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 0f2a7343de3a..2a17c60a9a39 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxfload - Table load/unload external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 5b413bbab338..961577ba9486 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxfroot - Find the root ACPI table (RSDT)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index be94d2fd99a7..c673d6c95e0a 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utaddress - op_region address range check
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index c1fb70457e20..2418a312733a 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utalloc - local memory allocation routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c
index 2be37676edd7..259c28d3fecd 100644
--- a/drivers/acpi/acpica/utascii.c
+++ b/drivers/acpi/acpica/utascii.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utascii - Utility ascii functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index b054bb5eeaf0..f6e6e98e9523 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utbuffer - Buffer dump routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index 85a85f7cf750..cabec193febb 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcache - local cache allocation routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -251,9 +251,9 @@ void *acpi_os_acquire_object(struct acpi_memory_list *cache)
 	} else {
 		/* The cache is empty, create a new object */
 
+#ifdef ACPI_DBG_TRACK_ALLOCATIONS
 		ACPI_MEM_TRACKING(cache->total_allocated++);
 
-#ifdef ACPI_DBG_TRACK_ALLOCATIONS
 		if ((cache->total_allocated - cache->total_freed) >
 		    cache->max_occupied) {
 			cache->max_occupied =
diff --git a/drivers/acpi/acpica/utcksum.c b/drivers/acpi/acpica/utcksum.c
index b483894c3629..e6f6030b3a3f 100644
--- a/drivers/acpi/acpica/utcksum.c
+++ b/drivers/acpi/acpica/utcksum.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcksum - Support generating table checksums
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index 2e17e657dfa4..80458e70ac2b 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcopy - Internal to external object translation utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index c5f6c85a3a09..9f197e293c7e 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utdebug - Debug print/trace routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -62,7 +62,12 @@ void acpi_ut_track_stack_ptr(void)
 	acpi_size current_sp;
 
 	if (&current_sp < acpi_gbl_lowest_stack_pointer) {
+#pragma GCC diagnostic push
+#if defined(__GNUC__) && __GNUC__ >= 12
+#pragma GCC diagnostic ignored "-Wdangling-pointer="
+#endif
 		acpi_gbl_lowest_stack_pointer = &current_sp;
+#pragma GCC diagnostic pop
 	}
 
 	if (acpi_gbl_nesting_level > acpi_gbl_deepest_nesting) {
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 95a4b7509e01..b82130d1a8bc 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utdecode - Utility decoding routines (value-to-string)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index 8d7736d2d269..e8180099d01f 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -140,7 +140,7 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object)
 			(void)
 			    acpi_os_delete_semaphore
 			    (acpi_gbl_global_lock_semaphore);
-			acpi_gbl_global_lock_semaphore = NULL;
+			acpi_gbl_global_lock_semaphore = ACPI_SEMAPHORE_NULL;
 
 			acpi_os_delete_mutex(object->mutex.os_mutex);
 			acpi_gbl_global_lock_mutex = NULL;
@@ -157,7 +157,7 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object)
 				  object, object->event.os_semaphore));
 
 		(void)acpi_os_delete_semaphore(object->event.os_semaphore);
-		object->event.os_semaphore = NULL;
+		object->event.os_semaphore = ACPI_SEMAPHORE_NULL;
 		break;
 
 	case ACPI_TYPE_METHOD:
@@ -404,7 +404,7 @@ acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action)
 				  object, object->common.type,
 				  acpi_ut_get_object_type_name(object),
 				  new_count));
-		message = "Incremement";
+		message = "Increment";
 		break;
 
 	case REF_DECREMENT:
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index 3e5173d03953..abc6583ed369 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uteval - Object evaluation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 820820ea8119..97c55a113bae 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utglobal - Global variables for the ACPI subsystem
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c
index e62802791dcf..8cd050e9cad5 100644
--- a/drivers/acpi/acpica/uthex.c
+++ b/drivers/acpi/acpica/uthex.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uthex -- Hex/ASCII support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index 15c2ce91d403..eb88335dea2c 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 92fbaef161a7..4bef97e8223a 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utinit - Common ACPI subsystem initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -154,7 +154,7 @@ acpi_status acpi_ut_init_globals(void)
 
 	/* Global Lock support */
 
-	acpi_gbl_global_lock_semaphore = NULL;
+	acpi_gbl_global_lock_semaphore = ACPI_SEMAPHORE_NULL;
 	acpi_gbl_global_lock_mutex = NULL;
 	acpi_gbl_global_lock_acquired = FALSE;
 	acpi_gbl_global_lock_handle = 0;
diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c
index ee6d72385c5c..123dbcbc60bc 100644
--- a/drivers/acpi/acpica/utlock.c
+++ b/drivers/acpi/acpica/utlock.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utlock - Reader/Writer lock interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index f4aae8f0d3a8..272e46208263 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utobject - ACPI object create/delete/size/cache routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 251bd396c6fd..f6ac16729e42 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utosi - Support for the _OSI predefined control method
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -75,6 +75,7 @@ static struct acpi_interface_info acpi_default_supported_interfaces[] = {
 	{"Windows 2019", NULL, 0, ACPI_OSI_WIN_10_19H1},	/* Windows 10 version 1903 - Added 08/2019 */
 	{"Windows 2020", NULL, 0, ACPI_OSI_WIN_10_20H1},	/* Windows 10 version 2004 - Added 08/2021 */
 	{"Windows 2021", NULL, 0, ACPI_OSI_WIN_11},	/* Windows 11 - Added 01/2022 */
+	{"Windows 2022", NULL, 0, ACPI_OSI_WIN_11_22H2},	/* Windows 11 version 22H2 - Added 04/2024 */
 
 	/* Feature Group Strings */
 
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index 29d2977d0746..d9bd80e2d32a 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utpredef - support functions for predefined names
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 42b30b9f9312..423d10569736 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utprint - Formatted printing routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -333,11 +333,8 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args)
 
 	pos = string;
 
-	if (size != ACPI_UINT32_MAX) {
-		end = string + size;
-	} else {
-		end = ACPI_CAST_PTR(char, ACPI_UINT32_MAX);
-	}
+	size = ACPI_MIN(size, ACPI_PTR_DIFF(ACPI_MAX_PTR, string));
+	end = string + size;
 
 	for (; *format; ++format) {
 		if (*format != '%') {
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index cff7901f7866..e1cc3d348750 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -361,20 +361,16 @@ acpi_ut_validate_resource(struct acpi_walk_state *walk_state,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 	if (resource_type == ACPI_RESOURCE_NAME_SERIAL_BUS) {
 
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
 		/* Validate the bus_type field */
 
-		if ((common_serial_bus.type == 0) ||
-		    (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE)) {
+		if ((aml_resource->common_serial_bus.type == 0) ||
+		    (aml_resource->common_serial_bus.type >
+		     AML_RESOURCE_MAX_SERIALBUSTYPE)) {
 			if (walk_state) {
 				ACPI_ERROR((AE_INFO,
 					    "Invalid/unsupported SerialBus resource descriptor: BusType 0x%2.2X",
-					    common_serial_bus.type));
+					    aml_resource->common_serial_bus.
+					    type));
 			}
 			return (AE_AML_INVALID_RESOURCE_TYPE);
 		}
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index f5f5da441458..a99c4c9e3d39 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uttrack - Memory allocation tracking routines (debug only)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c
index 8f10b413e928..0682554934ca 100644
--- a/drivers/acpi/acpica/utuuid.c
+++ b/drivers/acpi/acpica/utuuid.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utuuid -- UUID support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index aa2e923462b7..56942b5f026b 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utxface - External interfaces, miscellaneous utility functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 1915bec2b279..c1702f8fba67 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utxfinit - External interfaces for ACPICA initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -120,6 +120,18 @@ acpi_status ACPI_INIT_FUNCTION acpi_enable_subsystem(u32 flags)
 	 */
 	acpi_gbl_early_initialization = FALSE;
 
+	/*
+	 * Obtain a permanent mapping for the FACS. This is required for the
+	 * Global Lock and the Firmware Waking Vector
+	 */
+	if (!(flags & ACPI_NO_FACS_INIT)) {
+		status = acpi_tb_initialize_facs();
+		if (ACPI_FAILURE(status)) {
+			ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
+			return_ACPI_STATUS(status);
+		}
+	}
+
 #if (!ACPI_REDUCED_HARDWARE)
 
 	/* Enable ACPI mode */
@@ -138,18 +150,6 @@ acpi_status ACPI_INIT_FUNCTION acpi_enable_subsystem(u32 flags)
 	}
 
 	/*
-	 * Obtain a permanent mapping for the FACS. This is required for the
-	 * Global Lock and the Firmware Waking Vector
-	 */
-	if (!(flags & ACPI_NO_FACS_INIT)) {
-		status = acpi_tb_initialize_facs();
-		if (ACPI_FAILURE(status)) {
-			ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
-			return_ACPI_STATUS(status);
-		}
-	}
-
-	/*
 	 * Initialize ACPI Event handling (Fixed and General Purpose)
 	 *
 	 * Note1: We must have the hardware and events initialized before we can
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 6b18f8bc7be3..070c07d68dfb 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -23,6 +23,7 @@ config ACPI_APEI_GHES
 	select ACPI_HED
 	select IRQ_WORK
 	select GENERIC_ALLOCATOR
+	select ARM_SDE_INTERFACE if ARM64
 	help
 	  Generic Hardware Error Source provides a way to report
 	  platform hardware errors (such as that from chipset). It
@@ -60,6 +61,19 @@ config ACPI_APEI_EINJ
 	  mainly used for debugging and testing the other parts of
 	  APEI and some other RAS features.
 
+config ACPI_APEI_EINJ_CXL
+	bool "CXL Error INJection Support"
+	default ACPI_APEI_EINJ
+	depends on ACPI_APEI_EINJ
+	depends on CXL_BUS && CXL_BUS <= ACPI_APEI_EINJ
+	help
+	  Support for CXL protocol Error INJection through debugfs/cxl.
+	  Availability and which errors are supported is dependent on
+	  the host platform. Look to ACPI v6.5 section 18.6.4 and kernel
+	  EINJ documentation for more information.
+
+	  If unsure say 'n'
+
 config ACPI_APEI_ERST_DEBUG
 	tristate "APEI Error Record Serialization Table (ERST) Debug Support"
 	depends on ACPI_APEI
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 4dfac2128737..2c474e6477e1 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -2,6 +2,8 @@
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
 obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
 obj-$(CONFIG_ACPI_APEI_EINJ)	+= einj.o
+einj-y				:= einj-core.o
+einj-$(CONFIG_ACPI_APEI_EINJ_CXL) += einj-cxl.o
 obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
 
 apei-y := apei-base.o hest.o erst.o bert.o
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index c7c26872f4ce..9c84f3da7c09 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -28,7 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/debugfs.h>
 #include <acpi/apei.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 #include "apei-internal.h"
 
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 67c2c3b959e1..77c10a7a7a9f 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -130,4 +130,22 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
 }
 
 int apei_osc_setup(void);
+
+int einj_get_available_error_type(u32 *type, int einj_action);
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+		      u64 param4);
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			      u64 param3, u64 param4);
+bool einj_is_cxl_error_type(u64 type);
+int einj_validate_error_type(u64 type);
+
+#ifndef ACPI_EINJ_CXL_CACHE_CORRECTABLE
+#define ACPI_EINJ_CXL_CACHE_CORRECTABLE     BIT(12)
+#define ACPI_EINJ_CXL_CACHE_UNCORRECTABLE   BIT(13)
+#define ACPI_EINJ_CXL_CACHE_FATAL           BIT(14)
+#define ACPI_EINJ_CXL_MEM_CORRECTABLE       BIT(15)
+#define ACPI_EINJ_CXL_MEM_UNCORRECTABLE     BIT(16)
+#define ACPI_EINJ_CXL_MEM_FATAL             BIT(17)
+#endif
+
 #endif
diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
new file mode 100644
index 000000000000..3c87953dbd19
--- /dev/null
+++ b/drivers/acpi/apei/einj-core.c
@@ -0,0 +1,1183 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * APEI Error INJection support
+ *
+ * EINJ provides a hardware error injection mechanism, this is useful
+ * for debugging and testing of other APEI and RAS features.
+ *
+ * For more information about EINJ, please refer to ACPI Specification
+ * version 4.0, section 17.5.
+ *
+ * Copyright 2009-2010 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <linux/mm.h>
+#include <linux/device/faux.h>
+#include <linux/unaligned.h>
+
+#include "apei-internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "EINJ: " fmt
+
+#define SLEEP_UNIT_MIN		1000			/* 1ms */
+#define SLEEP_UNIT_MAX		5000			/* 5ms */
+/* Firmware should respond within 1 seconds */
+#define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
+#define COMPONENT_LEN		16
+#define ACPI65_EINJV2_SUPP	BIT(30)
+#define ACPI5_VENDOR_BIT	BIT(31)
+#define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
+				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
+				ACPI_EINJ_MEMORY_FATAL)
+#define CXL_ERROR_MASK		(ACPI_EINJ_CXL_CACHE_CORRECTABLE | \
+				ACPI_EINJ_CXL_CACHE_UNCORRECTABLE | \
+				ACPI_EINJ_CXL_CACHE_FATAL | \
+				ACPI_EINJ_CXL_MEM_CORRECTABLE | \
+				ACPI_EINJ_CXL_MEM_UNCORRECTABLE | \
+				ACPI_EINJ_CXL_MEM_FATAL)
+
+/*
+ * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
+ */
+static int acpi5;
+
+struct syndrome_array {
+	union {
+		u8	acpi_id[COMPONENT_LEN];
+		u8	device_id[COMPONENT_LEN];
+		u8	pcie_sbdf[COMPONENT_LEN];
+		u8	vendor_id[COMPONENT_LEN];
+	} comp_id;
+	union {
+		u8	proc_synd[COMPONENT_LEN];
+		u8	mem_synd[COMPONENT_LEN];
+		u8	pcie_synd[COMPONENT_LEN];
+		u8	vendor_synd[COMPONENT_LEN];
+	} comp_synd;
+};
+
+struct einjv2_extension_struct {
+	u32 length;
+	u16 revision;
+	u16 component_arr_count;
+	struct syndrome_array component_arr[] __counted_by(component_arr_count);
+};
+
+struct set_error_type_with_address {
+	u32	type;
+	u32	vendor_extension;
+	u32	flags;
+	u32	apicid;
+	u64	memory_address;
+	u64	memory_address_range;
+	u32	pcie_sbdf;
+	struct	einjv2_extension_struct einjv2_struct;
+};
+enum {
+	SETWA_FLAGS_APICID = 1,
+	SETWA_FLAGS_MEM = 2,
+	SETWA_FLAGS_PCIE_SBDF = 4,
+	SETWA_FLAGS_EINJV2 = 8,
+};
+
+/*
+ * Vendor extensions for platform specific operations
+ */
+struct vendor_error_type_extension {
+	u32	length;
+	u32	pcie_sbdf;
+	u16	vendor_id;
+	u16	device_id;
+	u8	rev_id;
+	u8	reserved[3];
+};
+
+static u32 notrigger;
+
+static u32 vendor_flags;
+static struct debugfs_blob_wrapper vendor_blob;
+static struct debugfs_blob_wrapper vendor_errors;
+static char vendor_dev[64];
+
+static u32 max_nr_components;
+static u32 available_error_type;
+static u32 available_error_type_v2;
+static struct syndrome_array *syndrome_data;
+
+/*
+ * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
+ * EINJ table through an unpublished extension. Use with caution as
+ * most will ignore the parameter and make their own choice of address
+ * for error injection.  This extension is used only if
+ * param_extension module parameter is specified.
+ */
+struct einj_parameter {
+	u64 type;
+	u64 reserved1;
+	u64 reserved2;
+	u64 param1;
+	u64 param2;
+};
+
+#define EINJ_OP_BUSY			0x1
+#define EINJ_STATUS_SUCCESS		0x0
+#define EINJ_STATUS_FAIL		0x1
+#define EINJ_STATUS_INVAL		0x2
+
+#define EINJ_TAB_ENTRY(tab)						\
+	((struct acpi_whea_header *)((char *)(tab) +			\
+				    sizeof(struct acpi_table_einj)))
+
+static bool param_extension;
+module_param(param_extension, bool, 0);
+
+static struct acpi_table_einj *einj_tab;
+
+static struct apei_resources einj_resources;
+
+static struct apei_exec_ins_type einj_ins_type[] = {
+	[ACPI_EINJ_READ_REGISTER] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_read_register,
+	},
+	[ACPI_EINJ_READ_REGISTER_VALUE] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_read_register_value,
+	},
+	[ACPI_EINJ_WRITE_REGISTER] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_write_register,
+	},
+	[ACPI_EINJ_WRITE_REGISTER_VALUE] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_write_register_value,
+	},
+	[ACPI_EINJ_NOOP] = {
+		.flags = 0,
+		.run   = apei_exec_noop,
+	},
+};
+
+/*
+ * Prevent EINJ interpreter to run simultaneously, because the
+ * corresponding firmware implementation may not work properly when
+ * invoked simultaneously.
+ */
+static DEFINE_MUTEX(einj_mutex);
+
+/*
+ * Exported APIs use this flag to exit early if einj_probe() failed.
+ */
+bool einj_initialized __ro_after_init;
+
+static void __iomem *einj_param;
+static u32 v5param_size;
+static bool is_v2;
+
+static void einj_exec_ctx_init(struct apei_exec_context *ctx)
+{
+	apei_exec_ctx_init(ctx, einj_ins_type, ARRAY_SIZE(einj_ins_type),
+			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
+}
+
+static int __einj_get_available_error_type(u32 *type, int einj_action)
+{
+	struct apei_exec_context ctx;
+	int rc;
+
+	einj_exec_ctx_init(&ctx);
+	rc = apei_exec_run(&ctx, einj_action);
+	if (rc)
+		return rc;
+	*type = apei_exec_ctx_get_output(&ctx);
+
+	return 0;
+}
+
+/* Get error injection capabilities of the platform */
+int einj_get_available_error_type(u32 *type, int einj_action)
+{
+	int rc;
+
+	mutex_lock(&einj_mutex);
+	rc = __einj_get_available_error_type(type, einj_action);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
+static int einj_get_available_error_types(u32 *type1, u32 *type2)
+{
+	int rc;
+
+	rc = einj_get_available_error_type(type1, ACPI_EINJ_GET_ERROR_TYPE);
+	if (rc)
+		return rc;
+	if (*type1 & ACPI65_EINJV2_SUPP) {
+		rc = einj_get_available_error_type(type2,
+						   ACPI_EINJV2_GET_ERROR_TYPE);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int einj_timedout(u64 *t)
+{
+	if ((s64)*t < SLEEP_UNIT_MIN) {
+		pr_warn(FW_WARN "Firmware does not respond in time\n");
+		return 1;
+	}
+	*t -= SLEEP_UNIT_MIN;
+	usleep_range(SLEEP_UNIT_MIN, SLEEP_UNIT_MAX);
+
+	return 0;
+}
+
+static void get_oem_vendor_struct(u64 paddr, int offset,
+				  struct vendor_error_type_extension *v)
+{
+	unsigned long vendor_size;
+	u64 target_pa = paddr + offset + sizeof(struct vendor_error_type_extension);
+
+	vendor_size = v->length - sizeof(struct vendor_error_type_extension);
+
+	if (vendor_size)
+		vendor_errors.data = acpi_os_map_memory(target_pa, vendor_size);
+
+	if (vendor_errors.data)
+		vendor_errors.size = vendor_size;
+}
+
+static void check_vendor_extension(u64 paddr,
+				   struct set_error_type_with_address *v5param)
+{
+	int	offset = v5param->vendor_extension;
+	struct	vendor_error_type_extension v;
+	struct vendor_error_type_extension __iomem *p;
+	u32	sbdf;
+
+	if (!offset)
+		return;
+	p = acpi_os_map_iomem(paddr + offset, sizeof(*p));
+	if (!p)
+		return;
+	memcpy_fromio(&v, p, sizeof(v));
+	get_oem_vendor_struct(paddr, offset, &v);
+	sbdf = v.pcie_sbdf;
+	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
+		sbdf >> 24, (sbdf >> 16) & 0xff,
+		(sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
+		 v.vendor_id, v.device_id, v.rev_id);
+	acpi_os_unmap_iomem(p, sizeof(v));
+}
+
+static void __iomem *einj_get_parameter_address(void)
+{
+	int i;
+	u64 pa_v4 = 0, pa_v5 = 0;
+	struct acpi_whea_header *entry;
+
+	entry = EINJ_TAB_ENTRY(einj_tab);
+	for (i = 0; i < einj_tab->entries; i++) {
+		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE &&
+		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
+		    entry->register_region.space_id ==
+		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
+			pa_v4 = get_unaligned(&entry->register_region.address);
+		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE_WITH_ADDRESS &&
+		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
+		    entry->register_region.space_id ==
+		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
+			pa_v5 = get_unaligned(&entry->register_region.address);
+		entry++;
+	}
+	if (pa_v5) {
+		struct set_error_type_with_address v5param;
+		struct set_error_type_with_address __iomem *p;
+
+		v5param_size = sizeof(v5param);
+		p = acpi_os_map_iomem(pa_v5, sizeof(*p));
+		if (p) {
+			int offset, len;
+
+			memcpy_fromio(&v5param, p, v5param_size);
+			acpi5 = 1;
+			check_vendor_extension(pa_v5, &v5param);
+			if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) {
+				len = v5param.einjv2_struct.length;
+				offset = offsetof(struct einjv2_extension_struct, component_arr);
+				max_nr_components = (len - offset) /
+						sizeof(v5param.einjv2_struct.component_arr[0]);
+				/*
+				 * The first call to acpi_os_map_iomem above does not include the
+				 * component array, instead it is used to read and calculate maximum
+				 * number of components supported by the system. Below, the mapping
+				 * is expanded to include the component array.
+				 */
+				acpi_os_unmap_iomem(p, v5param_size);
+				offset = offsetof(struct set_error_type_with_address, einjv2_struct);
+				v5param_size = offset + struct_size(&v5param.einjv2_struct,
+					component_arr, max_nr_components);
+				p = acpi_os_map_iomem(pa_v5, v5param_size);
+			}
+			return p;
+		}
+	}
+	if (param_extension && pa_v4) {
+		struct einj_parameter v4param;
+		struct einj_parameter __iomem *p;
+
+		p = acpi_os_map_iomem(pa_v4, sizeof(*p));
+		if (!p)
+			return NULL;
+		memcpy_fromio(&v4param, p, sizeof(v4param));
+		if (v4param.reserved1 || v4param.reserved2) {
+			acpi_os_unmap_iomem(p, sizeof(v4param));
+			return NULL;
+		}
+		return p;
+	}
+
+	return NULL;
+}
+
+/* do sanity check to trigger table */
+static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab)
+{
+	if (trigger_tab->header_size != sizeof(struct acpi_einj_trigger))
+		return -EINVAL;
+	if (trigger_tab->table_size > PAGE_SIZE ||
+	    trigger_tab->table_size < trigger_tab->header_size)
+		return -EINVAL;
+	if (trigger_tab->entry_count !=
+	    (trigger_tab->table_size - trigger_tab->header_size) /
+	    sizeof(struct acpi_einj_entry))
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct acpi_generic_address *einj_get_trigger_parameter_region(
+	struct acpi_einj_trigger *trigger_tab, u64 param1, u64 param2)
+{
+	int i;
+	struct acpi_whea_header *entry;
+
+	entry = (struct acpi_whea_header *)
+		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
+	for (i = 0; i < trigger_tab->entry_count; i++) {
+		if (entry->action == ACPI_EINJ_TRIGGER_ERROR &&
+		entry->instruction <= ACPI_EINJ_WRITE_REGISTER_VALUE &&
+		entry->register_region.space_id ==
+			ACPI_ADR_SPACE_SYSTEM_MEMORY &&
+		(entry->register_region.address & param2) == (param1 & param2))
+			return &entry->register_region;
+		entry++;
+	}
+
+	return NULL;
+}
+/* Execute instructions in trigger error action table */
+static int __einj_error_trigger(u64 trigger_paddr, u32 type,
+				u64 param1, u64 param2)
+{
+	struct acpi_einj_trigger trigger_tab;
+	struct acpi_einj_trigger *full_trigger_tab;
+	struct apei_exec_context trigger_ctx;
+	struct apei_resources trigger_resources;
+	struct acpi_whea_header *trigger_entry;
+	struct resource *r;
+	u32 table_size;
+	int rc = -EIO;
+	struct acpi_generic_address *trigger_param_region = NULL;
+	struct acpi_einj_trigger __iomem *p = NULL;
+
+	r = request_mem_region(trigger_paddr, sizeof(trigger_tab),
+			       "APEI EINJ Trigger Table");
+	if (!r) {
+		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger table\n",
+		       (unsigned long long)trigger_paddr,
+		       (unsigned long long)trigger_paddr +
+			    sizeof(trigger_tab) - 1);
+		goto out;
+	}
+	p = ioremap_cache(trigger_paddr, sizeof(*p));
+	if (!p) {
+		pr_err("Failed to map trigger table!\n");
+		goto out_rel_header;
+	}
+	memcpy_fromio(&trigger_tab, p, sizeof(trigger_tab));
+	rc = einj_check_trigger_header(&trigger_tab);
+	if (rc) {
+		pr_warn(FW_BUG "Invalid trigger error action table.\n");
+		goto out_rel_header;
+	}
+
+	/* No action structures in the TRIGGER_ERROR table, nothing to do */
+	if (!trigger_tab.entry_count)
+		goto out_rel_header;
+
+	rc = -EIO;
+	table_size = trigger_tab.table_size;
+	full_trigger_tab = kmalloc(table_size, GFP_KERNEL);
+	if (!full_trigger_tab)
+		goto out_rel_header;
+	r = request_mem_region(trigger_paddr + sizeof(trigger_tab),
+			       table_size - sizeof(trigger_tab),
+			       "APEI EINJ Trigger Table");
+	if (!r) {
+		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
+		       (unsigned long long)trigger_paddr + sizeof(trigger_tab),
+		       (unsigned long long)trigger_paddr + table_size - 1);
+		goto out_free_trigger_tab;
+	}
+	iounmap(p);
+	p = ioremap_cache(trigger_paddr, table_size);
+	if (!p) {
+		pr_err("Failed to map trigger table!\n");
+		goto out_rel_entry;
+	}
+	memcpy_fromio(full_trigger_tab, p, table_size);
+	trigger_entry = (struct acpi_whea_header *)
+		((char *)full_trigger_tab + sizeof(struct acpi_einj_trigger));
+	apei_resources_init(&trigger_resources);
+	apei_exec_ctx_init(&trigger_ctx, einj_ins_type,
+			   ARRAY_SIZE(einj_ins_type),
+			   trigger_entry, trigger_tab.entry_count);
+	rc = apei_exec_collect_resources(&trigger_ctx, &trigger_resources);
+	if (rc)
+		goto out_fini;
+	rc = apei_resources_sub(&trigger_resources, &einj_resources);
+	if (rc)
+		goto out_fini;
+	/*
+	 * Some firmware will access target address specified in
+	 * param1 to trigger the error when injecting memory error.
+	 * This will cause resource conflict with regular memory.  So
+	 * remove it from trigger table resources.
+	 */
+	if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) {
+		struct apei_resources addr_resources;
+
+		apei_resources_init(&addr_resources);
+		trigger_param_region = einj_get_trigger_parameter_region(
+			full_trigger_tab, param1, param2);
+		if (trigger_param_region) {
+			rc = apei_resources_add(&addr_resources,
+				trigger_param_region->address,
+				trigger_param_region->bit_width/8, true);
+			if (rc)
+				goto out_fini;
+			rc = apei_resources_sub(&trigger_resources,
+					&addr_resources);
+		}
+		apei_resources_fini(&addr_resources);
+		if (rc)
+			goto out_fini;
+	}
+	rc = apei_resources_request(&trigger_resources, "APEI EINJ Trigger");
+	if (rc)
+		goto out_fini;
+	rc = apei_exec_pre_map_gars(&trigger_ctx);
+	if (rc)
+		goto out_release;
+
+	rc = apei_exec_run(&trigger_ctx, ACPI_EINJ_TRIGGER_ERROR);
+
+	apei_exec_post_unmap_gars(&trigger_ctx);
+out_release:
+	apei_resources_release(&trigger_resources);
+out_fini:
+	apei_resources_fini(&trigger_resources);
+out_rel_entry:
+	release_mem_region(trigger_paddr + sizeof(trigger_tab),
+			   table_size - sizeof(trigger_tab));
+out_free_trigger_tab:
+	kfree(full_trigger_tab);
+out_rel_header:
+	release_mem_region(trigger_paddr, sizeof(trigger_tab));
+out:
+	if (p)
+		iounmap(p);
+
+	return rc;
+}
+
+static bool is_end_of_list(u8 *val)
+{
+	for (int i = 0; i < COMPONENT_LEN; ++i) {
+		if (val[i] != 0xFF)
+			return false;
+	}
+	return true;
+}
+static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			       u64 param3, u64 param4)
+{
+	struct apei_exec_context ctx;
+	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
+	int i, rc;
+
+	einj_exec_ctx_init(&ctx);
+
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION);
+	if (rc)
+		return rc;
+	apei_exec_ctx_set_input(&ctx, type);
+	if (acpi5) {
+		struct set_error_type_with_address *v5param;
+
+		v5param = kmalloc(v5param_size, GFP_KERNEL);
+		if (!v5param)
+			return -ENOMEM;
+
+		memcpy_fromio(v5param, einj_param, v5param_size);
+		v5param->type = type;
+		if (type & ACPI5_VENDOR_BIT) {
+			switch (vendor_flags) {
+			case SETWA_FLAGS_APICID:
+				v5param->apicid = param1;
+				break;
+			case SETWA_FLAGS_MEM:
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				break;
+			case SETWA_FLAGS_PCIE_SBDF:
+				v5param->pcie_sbdf = param1;
+				break;
+			}
+			v5param->flags = vendor_flags;
+		} else if (flags) {
+			v5param->flags = flags;
+			v5param->memory_address = param1;
+			v5param->memory_address_range = param2;
+
+			if (is_v2) {
+				for (i = 0; i < max_nr_components; i++) {
+					if (is_end_of_list(syndrome_data[i].comp_id.acpi_id))
+						break;
+					v5param->einjv2_struct.component_arr[i].comp_id =
+						syndrome_data[i].comp_id;
+					v5param->einjv2_struct.component_arr[i].comp_synd =
+						syndrome_data[i].comp_synd;
+				}
+				v5param->einjv2_struct.component_arr_count = i;
+			} else {
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
+			}
+		} else {
+			switch (type) {
+			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
+			case ACPI_EINJ_PROCESSOR_UNCORRECTABLE:
+			case ACPI_EINJ_PROCESSOR_FATAL:
+				v5param->apicid = param1;
+				v5param->flags = SETWA_FLAGS_APICID;
+				break;
+			case ACPI_EINJ_MEMORY_CORRECTABLE:
+			case ACPI_EINJ_MEMORY_UNCORRECTABLE:
+			case ACPI_EINJ_MEMORY_FATAL:
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				v5param->flags = SETWA_FLAGS_MEM;
+				break;
+			case ACPI_EINJ_PCIX_CORRECTABLE:
+			case ACPI_EINJ_PCIX_UNCORRECTABLE:
+			case ACPI_EINJ_PCIX_FATAL:
+				v5param->pcie_sbdf = param1;
+				v5param->flags = SETWA_FLAGS_PCIE_SBDF;
+				break;
+			}
+		}
+		memcpy_toio(einj_param, v5param, v5param_size);
+		kfree(v5param);
+	} else {
+		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
+		if (rc)
+			return rc;
+		if (einj_param) {
+			struct einj_parameter v4param;
+
+			memcpy_fromio(&v4param, einj_param, sizeof(v4param));
+			v4param.param1 = param1;
+			v4param.param2 = param2;
+			memcpy_toio(einj_param, &v4param, sizeof(v4param));
+		}
+	}
+	rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
+	if (rc)
+		return rc;
+	for (;;) {
+		rc = apei_exec_run(&ctx, ACPI_EINJ_CHECK_BUSY_STATUS);
+		if (rc)
+			return rc;
+		val = apei_exec_ctx_get_output(&ctx);
+		if (!(val & EINJ_OP_BUSY))
+			break;
+		if (einj_timedout(&timeout))
+			return -EIO;
+	}
+	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_COMMAND_STATUS);
+	if (rc)
+		return rc;
+	val = apei_exec_ctx_get_output(&ctx);
+	if (val == EINJ_STATUS_FAIL)
+		return -EBUSY;
+	else if (val == EINJ_STATUS_INVAL)
+		return -EINVAL;
+
+	/*
+	 * The error is injected into the platform successfully, then it needs
+	 * to trigger the error.
+	 */
+	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_TRIGGER_TABLE);
+	if (rc)
+		return rc;
+	trigger_paddr = apei_exec_ctx_get_output(&ctx);
+	if (notrigger == 0) {
+		rc = __einj_error_trigger(trigger_paddr, type, param1, param2);
+		if (rc)
+			return rc;
+	}
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
+
+	return rc;
+}
+
+/* Allow almost all types of address except MMIO. */
+static bool is_allowed_range(u64 base_addr, u64 size)
+{
+	int i;
+	/*
+	 * MMIO region is usually claimed with IORESOURCE_MEM + IORES_DESC_NONE.
+	 * However, IORES_DESC_NONE is treated like a wildcard when we check if
+	 * region intersects with known resource. So do an allow list check for
+	 * IORES_DESCs that definitely or most likely not MMIO.
+	 */
+	int non_mmio_desc[] = {
+		IORES_DESC_CRASH_KERNEL,
+		IORES_DESC_ACPI_TABLES,
+		IORES_DESC_ACPI_NV_STORAGE,
+		IORES_DESC_PERSISTENT_MEMORY,
+		IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+		/* Treat IORES_DESC_DEVICE_PRIVATE_MEMORY as MMIO. */
+		IORES_DESC_RESERVED,
+		IORES_DESC_SOFT_RESERVED,
+	};
+
+	if (region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
+			      == REGION_INTERSECTS)
+		return true;
+
+	for (i = 0; i < ARRAY_SIZE(non_mmio_desc); ++i) {
+		if (region_intersects(base_addr, size, IORESOURCE_MEM, non_mmio_desc[i])
+				      == REGION_INTERSECTS)
+			return true;
+	}
+
+	if (arch_is_platform_page(base_addr))
+		return true;
+
+	return false;
+}
+
+/* Inject the specified hardware error */
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+		      u64 param4)
+{
+	int rc;
+	u64 base_addr, size;
+
+	/* If user manually set "flags", make sure it is legal */
+	if (flags && (flags & ~(SETWA_FLAGS_APICID | SETWA_FLAGS_MEM |
+		      SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2)))
+		return -EINVAL;
+
+	/* check if type is a valid EINJv2 error type */
+	if (is_v2) {
+		if (!(type & available_error_type_v2))
+			return -EINVAL;
+	}
+	/*
+	 * We need extra sanity checks for memory errors.
+	 * Other types leap directly to injection.
+	 */
+
+	/* ensure param1/param2 existed */
+	if (!(param_extension || acpi5))
+		goto inject;
+
+	/* ensure injection is memory related */
+	if (type & ACPI5_VENDOR_BIT) {
+		if (vendor_flags != SETWA_FLAGS_MEM)
+			goto inject;
+	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) {
+		goto inject;
+	}
+
+	/*
+	 * Injections targeting a CXL 1.0/1.1 port have to be injected
+	 * via the einj_cxl_rch_error_inject() path as that does the proper
+	 * validation of the given RCRB base (MMIO) address.
+	 */
+	if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM))
+		return -EINVAL;
+
+	/*
+	 * Disallow crazy address masks that give BIOS leeway to pick
+	 * injection address almost anywhere. Insist on page or
+	 * better granularity and that target address is normal RAM or
+	 * as long as is not MMIO.
+	 */
+	base_addr = param1 & param2;
+	size = ~param2 + 1;
+
+	if ((param2 & PAGE_MASK) != PAGE_MASK)
+		return -EINVAL;
+
+	if (!is_allowed_range(base_addr, size))
+		return -EINVAL;
+
+	if (is_zero_pfn(base_addr >> PAGE_SHIFT))
+		return -EADDRINUSE;
+
+inject:
+	mutex_lock(&einj_mutex);
+	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			      u64 param3, u64 param4)
+{
+	int rc;
+
+	if (!(einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)))
+		return -EINVAL;
+
+	mutex_lock(&einj_mutex);
+	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
+static u32 error_type;
+static u32 error_flags;
+static u64 error_param1;
+static u64 error_param2;
+static u64 error_param3;
+static u64 error_param4;
+static struct dentry *einj_debug_dir;
+static char einj_buf[32];
+static bool einj_v2_enabled;
+static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
+	{ BIT(0), "Processor Correctable" },
+	{ BIT(1), "Processor Uncorrectable non-fatal" },
+	{ BIT(2), "Processor Uncorrectable fatal" },
+	{ BIT(3), "Memory Correctable" },
+	{ BIT(4), "Memory Uncorrectable non-fatal" },
+	{ BIT(5), "Memory Uncorrectable fatal" },
+	{ BIT(6), "PCI Express Correctable" },
+	{ BIT(7), "PCI Express Uncorrectable non-fatal" },
+	{ BIT(8), "PCI Express Uncorrectable fatal" },
+	{ BIT(9), "Platform Correctable" },
+	{ BIT(10), "Platform Uncorrectable non-fatal" },
+	{ BIT(11), "Platform Uncorrectable fatal"},
+	{ BIT(31), "Vendor Defined Error Types" },
+};
+
+static struct { u32 mask; const char *str; } const einjv2_error_type_string[] = {
+	{ BIT(0), "EINJV2 Processor Error" },
+	{ BIT(1), "EINJV2 Memory Error" },
+	{ BIT(2), "EINJV2 PCI Express Error" },
+};
+
+static int available_error_type_show(struct seq_file *m, void *v)
+{
+
+	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
+		if (available_error_type & einj_error_type_string[pos].mask)
+			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
+				   einj_error_type_string[pos].str);
+	if ((available_error_type & ACPI65_EINJV2_SUPP) && einj_v2_enabled) {
+		for (int pos = 0; pos < ARRAY_SIZE(einjv2_error_type_string); pos++) {
+			if (available_error_type_v2 & einjv2_error_type_string[pos].mask)
+				seq_printf(m, "V2_0x%08x\t%s\n", einjv2_error_type_string[pos].mask,
+					   einjv2_error_type_string[pos].str);
+		}
+	}
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(available_error_type);
+
+static ssize_t error_type_get(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, count, ppos, einj_buf, strlen(einj_buf));
+}
+
+bool einj_is_cxl_error_type(u64 type)
+{
+	return (type & CXL_ERROR_MASK) && (!(type & ACPI5_VENDOR_BIT));
+}
+
+int einj_validate_error_type(u64 type)
+{
+	u32 tval, vendor;
+
+	/* Only low 32 bits for error type are valid */
+	if (type & GENMASK_ULL(63, 32))
+		return -EINVAL;
+
+	/*
+	 * Vendor defined types have 0x80000000 bit set, and
+	 * are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
+	 */
+	vendor = type & ACPI5_VENDOR_BIT;
+	tval = type & GENMASK(30, 0);
+
+	/* Only one error type can be specified */
+	if (tval & (tval - 1))
+		return -EINVAL;
+	if (!vendor)
+		if (!(type & (available_error_type | available_error_type_v2)))
+			return -EINVAL;
+
+	return 0;
+}
+
+static ssize_t error_type_set(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	int rc;
+	u64 val;
+
+	/* Leave the last character for the NUL terminator */
+	if (count > sizeof(einj_buf) - 1)
+		return -EINVAL;
+
+	memset(einj_buf, 0, sizeof(einj_buf));
+	if (copy_from_user(einj_buf, buf, count))
+		return -EFAULT;
+
+	if (strncmp(einj_buf, "V2_", 3) == 0) {
+		if (!sscanf(einj_buf, "V2_%llx", &val))
+			return -EINVAL;
+		is_v2 = true;
+	} else {
+		if (!sscanf(einj_buf, "%llx", &val))
+			return -EINVAL;
+		is_v2 = false;
+	}
+
+	rc = einj_validate_error_type(val);
+	if (rc)
+		return rc;
+
+	error_type = val;
+
+	return count;
+}
+
+static const struct file_operations error_type_fops = {
+	.read		= error_type_get,
+	.write		= error_type_set,
+};
+
+static int error_inject_set(void *data, u64 val)
+{
+	if (!error_type)
+		return -EINVAL;
+
+	if (is_v2)
+		error_flags |= SETWA_FLAGS_EINJV2;
+	else
+		error_flags &= ~SETWA_FLAGS_EINJV2;
+
+	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
+		error_param3, error_param4);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(error_inject_fops, NULL, error_inject_set, "%llu\n");
+
+static int einj_check_table(struct acpi_table_einj *einj_tab)
+{
+	if ((einj_tab->header_length !=
+	     (sizeof(struct acpi_table_einj) - sizeof(einj_tab->header)))
+	    && (einj_tab->header_length != sizeof(struct acpi_table_einj)))
+		return -EINVAL;
+	if (einj_tab->header.length < sizeof(struct acpi_table_einj))
+		return -EINVAL;
+	if (einj_tab->entries !=
+	    (einj_tab->header.length - sizeof(struct acpi_table_einj)) /
+	    sizeof(struct acpi_einj_entry))
+		return -EINVAL;
+
+	return 0;
+}
+
+static ssize_t u128_read(struct file *f, char __user *buf, size_t count, loff_t *off)
+{
+	char output[2 * COMPONENT_LEN + 1];
+	u8 *data = f->f_inode->i_private;
+	int i;
+
+	if (*off >= sizeof(output))
+		return 0;
+
+	for (i = 0; i < COMPONENT_LEN; i++)
+		sprintf(output + 2 * i, "%.02x", data[COMPONENT_LEN - i - 1]);
+	output[2 * COMPONENT_LEN] = '\n';
+
+	return simple_read_from_buffer(buf, count, off, output, sizeof(output));
+}
+
+static ssize_t u128_write(struct file *f, const char __user *buf, size_t count, loff_t *off)
+{
+	char input[2 + 2 * COMPONENT_LEN + 2];
+	u8 *save = f->f_inode->i_private;
+	u8 tmp[COMPONENT_LEN];
+	char byte[3] = {};
+	char *s, *e;
+	ssize_t c;
+	long val;
+	int i;
+
+	/* Require that user supply whole input line in one write(2) syscall */
+	if (*off)
+		return -EINVAL;
+
+	c = simple_write_to_buffer(input, sizeof(input), off, buf, count);
+	if (c < 0)
+		return c;
+
+	if (c < 1 || input[c - 1] != '\n')
+		return -EINVAL;
+
+	/* Empty line means invalidate this entry */
+	if (c == 1) {
+		memset(save, 0xff, COMPONENT_LEN);
+		return c;
+	}
+
+	if (input[0] == '0' && (input[1] == 'x' || input[1] == 'X'))
+		s = input + 2;
+	else
+		s = input;
+	e = input + c - 1;
+
+	for (i = 0; i < COMPONENT_LEN; i++) {
+		byte[1] = *--e;
+		byte[0] = e > s ? *--e : '0';
+		if (kstrtol(byte, 16, &val))
+			return -EINVAL;
+		tmp[i] = val;
+		if (e <= s)
+			break;
+	}
+	while (++i < COMPONENT_LEN)
+		tmp[i] = 0;
+
+	memcpy(save, tmp, COMPONENT_LEN);
+
+	return c;
+}
+
+static const struct file_operations u128_fops = {
+	.read	= u128_read,
+	.write	= u128_write,
+};
+
+static bool setup_einjv2_component_files(void)
+{
+	char name[32];
+
+	syndrome_data = kcalloc(max_nr_components, sizeof(syndrome_data[0]), GFP_KERNEL);
+	if (!syndrome_data)
+		return false;
+
+	for (int i = 0; i < max_nr_components; i++) {
+		sprintf(name, "component_id%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_id, &u128_fops);
+		sprintf(name, "component_syndrome%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_synd, &u128_fops);
+	}
+
+	return true;
+}
+
+static int __init einj_probe(struct faux_device *fdev)
+{
+	int rc;
+	acpi_status status;
+	struct apei_exec_context ctx;
+
+	status = acpi_get_table(ACPI_SIG_EINJ, 0,
+				(struct acpi_table_header **)&einj_tab);
+	if (status == AE_NOT_FOUND) {
+		pr_debug("EINJ table not found.\n");
+		return -ENODEV;
+	} else if (ACPI_FAILURE(status)) {
+		pr_err("Failed to get EINJ table: %s\n",
+				acpi_format_exception(status));
+		return -EINVAL;
+	}
+
+	rc = einj_check_table(einj_tab);
+	if (rc) {
+		pr_warn(FW_BUG "Invalid EINJ table.\n");
+		goto err_put_table;
+	}
+
+	rc = einj_get_available_error_types(&available_error_type, &available_error_type_v2);
+	if (rc)
+		goto err_put_table;
+
+	rc = -ENOMEM;
+	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
+
+	debugfs_create_file("available_error_type", S_IRUSR, einj_debug_dir,
+			    NULL, &available_error_type_fops);
+	debugfs_create_file_unsafe("error_type", 0600, einj_debug_dir,
+				   NULL, &error_type_fops);
+	debugfs_create_file_unsafe("error_inject", 0200, einj_debug_dir,
+				   NULL, &error_inject_fops);
+
+	apei_resources_init(&einj_resources);
+	einj_exec_ctx_init(&ctx);
+	rc = apei_exec_collect_resources(&ctx, &einj_resources);
+	if (rc) {
+		pr_err("Error collecting EINJ resources.\n");
+		goto err_fini;
+	}
+
+	rc = apei_resources_request(&einj_resources, "APEI EINJ");
+	if (rc) {
+		pr_err("Error requesting memory/port resources.\n");
+		goto err_fini;
+	}
+
+	rc = apei_exec_pre_map_gars(&ctx);
+	if (rc) {
+		pr_err("Error pre-mapping GARs.\n");
+		goto err_release;
+	}
+
+	einj_param = einj_get_parameter_address();
+	if ((param_extension || acpi5) && einj_param) {
+		debugfs_create_x32("flags", S_IRUSR | S_IWUSR, einj_debug_dir,
+				   &error_flags);
+		debugfs_create_x64("param1", S_IRUSR | S_IWUSR, einj_debug_dir,
+				   &error_param1);
+		debugfs_create_x64("param2", S_IRUSR | S_IWUSR, einj_debug_dir,
+				   &error_param2);
+		debugfs_create_x64("param3", S_IRUSR | S_IWUSR, einj_debug_dir,
+				   &error_param3);
+		debugfs_create_x64("param4", S_IRUSR | S_IWUSR, einj_debug_dir,
+				   &error_param4);
+		debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
+				   einj_debug_dir, &notrigger);
+		if (available_error_type & ACPI65_EINJV2_SUPP)
+			einj_v2_enabled = setup_einjv2_component_files();
+	}
+
+	if (vendor_dev[0]) {
+		vendor_blob.data = vendor_dev;
+		vendor_blob.size = strlen(vendor_dev);
+		debugfs_create_blob("vendor", S_IRUSR, einj_debug_dir,
+				    &vendor_blob);
+		debugfs_create_x32("vendor_flags", S_IRUSR | S_IWUSR,
+				   einj_debug_dir, &vendor_flags);
+	}
+
+	if (vendor_errors.size)
+		debugfs_create_blob("oem_error", 0600, einj_debug_dir,
+				    &vendor_errors);
+
+	pr_info("Error INJection is initialized.\n");
+
+	return 0;
+
+err_release:
+	apei_resources_release(&einj_resources);
+err_fini:
+	apei_resources_fini(&einj_resources);
+	debugfs_remove_recursive(einj_debug_dir);
+err_put_table:
+	acpi_put_table((struct acpi_table_header *)einj_tab);
+
+	return rc;
+}
+
+static void einj_remove(struct faux_device *fdev)
+{
+	struct apei_exec_context ctx;
+
+	if (einj_param) {
+		acpi_size size = (acpi5) ?
+			v5param_size :
+			sizeof(struct einj_parameter);
+
+		acpi_os_unmap_iomem(einj_param, size);
+		if (vendor_errors.size)
+			acpi_os_unmap_memory(vendor_errors.data, vendor_errors.size);
+	}
+	einj_exec_ctx_init(&ctx);
+	apei_exec_post_unmap_gars(&ctx);
+	apei_resources_release(&einj_resources);
+	apei_resources_fini(&einj_resources);
+	debugfs_remove_recursive(einj_debug_dir);
+	kfree(syndrome_data);
+	acpi_put_table((struct acpi_table_header *)einj_tab);
+}
+
+static struct faux_device *einj_dev;
+static struct faux_device_ops einj_device_ops = {
+	.probe = einj_probe,
+	.remove = einj_remove,
+};
+
+static int __init einj_init(void)
+{
+	if (acpi_disabled) {
+		pr_debug("ACPI disabled.\n");
+		return -ENODEV;
+	}
+
+	einj_dev = faux_device_create("acpi-einj", NULL, &einj_device_ops);
+
+	if (einj_dev)
+		einj_initialized = true;
+
+	return 0;
+}
+
+static void __exit einj_exit(void)
+{
+	faux_device_destroy(einj_dev);
+}
+
+module_init(einj_init);
+module_exit(einj_exit);
+
+MODULE_AUTHOR("Huang Ying");
+MODULE_DESCRIPTION("APEI Error INJection support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
new file mode 100644
index 000000000000..e70a416ec925
--- /dev/null
+++ b/drivers/acpi/apei/einj-cxl.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CXL Error INJection support. Used by CXL core to inject
+ * protocol errors into CXL ports.
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Ben Cheatham <benjamin.cheatham@amd.com>
+ */
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+#include <cxl/einj.h>
+
+#include "apei-internal.h"
+
+/* Defined in einj-core.c */
+extern bool einj_initialized;
+
+static struct { u32 mask; const char *str; } const einj_cxl_error_type_string[] = {
+	{ ACPI_EINJ_CXL_CACHE_CORRECTABLE, "CXL.cache Protocol Correctable" },
+	{ ACPI_EINJ_CXL_CACHE_UNCORRECTABLE, "CXL.cache Protocol Uncorrectable non-fatal" },
+	{ ACPI_EINJ_CXL_CACHE_FATAL, "CXL.cache Protocol Uncorrectable fatal" },
+	{ ACPI_EINJ_CXL_MEM_CORRECTABLE, "CXL.mem Protocol Correctable" },
+	{ ACPI_EINJ_CXL_MEM_UNCORRECTABLE, "CXL.mem Protocol Uncorrectable non-fatal" },
+	{ ACPI_EINJ_CXL_MEM_FATAL, "CXL.mem Protocol Uncorrectable fatal" },
+};
+
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
+{
+	int cxl_err, rc;
+	u32 available_error_type = 0;
+
+	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
+	if (rc)
+		return rc;
+
+	for (int pos = 0; pos < ARRAY_SIZE(einj_cxl_error_type_string); pos++) {
+		cxl_err = ACPI_EINJ_CXL_CACHE_CORRECTABLE << pos;
+
+		if (available_error_type & cxl_err)
+			seq_printf(m, "0x%08x\t%s\n",
+				   einj_cxl_error_type_string[pos].mask,
+				   einj_cxl_error_type_string[pos].str);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_available_error_type_show, "CXL");
+
+static int cxl_dport_get_sbdf(struct pci_dev *dport_dev, u64 *sbdf)
+{
+	struct pci_bus *pbus;
+	struct pci_host_bridge *bridge;
+	u64 seg = 0, bus;
+
+	pbus = dport_dev->bus;
+	bridge = pci_find_host_bridge(pbus);
+
+	if (!bridge)
+		return -ENODEV;
+
+	if (bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET)
+		seg = bridge->domain_nr;
+
+	bus = pbus->number;
+	*sbdf = (seg << 24) | (bus << 16) | (dport_dev->devfn << 8);
+
+	return 0;
+}
+
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+	int rc;
+
+	/* Only CXL error types can be specified */
+	if (!einj_is_cxl_error_type(type))
+		return -EINVAL;
+
+	rc = einj_validate_error_type(type);
+	if (rc)
+		return rc;
+
+	return einj_cxl_rch_error_inject(type, 0x2, rcrb, GENMASK_ULL(63, 0),
+					 0, 0);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_rch_error, "CXL");
+
+int einj_cxl_inject_error(struct pci_dev *dport, u64 type)
+{
+	u64 param4 = 0;
+	int rc;
+
+	/* Only CXL error types can be specified */
+	if (!einj_is_cxl_error_type(type))
+		return -EINVAL;
+
+	rc = einj_validate_error_type(type);
+	if (rc)
+		return rc;
+
+	rc = cxl_dport_get_sbdf(dport, &param4);
+	if (rc)
+		return rc;
+
+	return einj_error_inject(type, 0x4, 0, 0, 0, param4);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_error, "CXL");
+
+bool einj_cxl_is_initialized(void)
+{
+	return einj_initialized;
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_is_initialized, "CXL");
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
deleted file mode 100644
index 013eb621dc92..000000000000
--- a/drivers/acpi/apei/einj.c
+++ /dev/null
@@ -1,809 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * APEI Error INJection support
- *
- * EINJ provides a hardware error injection mechanism, this is useful
- * for debugging and testing of other APEI and RAS features.
- *
- * For more information about EINJ, please refer to ACPI Specification
- * version 4.0, section 17.5.
- *
- * Copyright 2009-2010 Intel Corp.
- *   Author: Huang Ying <ying.huang@intel.com>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/nmi.h>
-#include <linux/delay.h>
-#include <linux/mm.h>
-#include <asm/unaligned.h>
-
-#include "apei-internal.h"
-
-#undef pr_fmt
-#define pr_fmt(fmt) "EINJ: " fmt
-
-#define SLEEP_UNIT_MIN		1000			/* 1ms */
-#define SLEEP_UNIT_MAX		5000			/* 5ms */
-/* Firmware should respond within 1 seconds */
-#define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
-#define ACPI5_VENDOR_BIT	BIT(31)
-#define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
-				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
-				ACPI_EINJ_MEMORY_FATAL)
-
-/*
- * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
- */
-static int acpi5;
-
-struct set_error_type_with_address {
-	u32	type;
-	u32	vendor_extension;
-	u32	flags;
-	u32	apicid;
-	u64	memory_address;
-	u64	memory_address_range;
-	u32	pcie_sbdf;
-};
-enum {
-	SETWA_FLAGS_APICID = 1,
-	SETWA_FLAGS_MEM = 2,
-	SETWA_FLAGS_PCIE_SBDF = 4,
-};
-
-/*
- * Vendor extensions for platform specific operations
- */
-struct vendor_error_type_extension {
-	u32	length;
-	u32	pcie_sbdf;
-	u16	vendor_id;
-	u16	device_id;
-	u8	rev_id;
-	u8	reserved[3];
-};
-
-static u32 notrigger;
-
-static u32 vendor_flags;
-static struct debugfs_blob_wrapper vendor_blob;
-static char vendor_dev[64];
-
-/*
- * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
- * EINJ table through an unpublished extension. Use with caution as
- * most will ignore the parameter and make their own choice of address
- * for error injection.  This extension is used only if
- * param_extension module parameter is specified.
- */
-struct einj_parameter {
-	u64 type;
-	u64 reserved1;
-	u64 reserved2;
-	u64 param1;
-	u64 param2;
-};
-
-#define EINJ_OP_BUSY			0x1
-#define EINJ_STATUS_SUCCESS		0x0
-#define EINJ_STATUS_FAIL		0x1
-#define EINJ_STATUS_INVAL		0x2
-
-#define EINJ_TAB_ENTRY(tab)						\
-	((struct acpi_whea_header *)((char *)(tab) +			\
-				    sizeof(struct acpi_table_einj)))
-
-static bool param_extension;
-module_param(param_extension, bool, 0);
-
-static struct acpi_table_einj *einj_tab;
-
-static struct apei_resources einj_resources;
-
-static struct apei_exec_ins_type einj_ins_type[] = {
-	[ACPI_EINJ_READ_REGISTER] = {
-		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
-		.run   = apei_exec_read_register,
-	},
-	[ACPI_EINJ_READ_REGISTER_VALUE] = {
-		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
-		.run   = apei_exec_read_register_value,
-	},
-	[ACPI_EINJ_WRITE_REGISTER] = {
-		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
-		.run   = apei_exec_write_register,
-	},
-	[ACPI_EINJ_WRITE_REGISTER_VALUE] = {
-		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
-		.run   = apei_exec_write_register_value,
-	},
-	[ACPI_EINJ_NOOP] = {
-		.flags = 0,
-		.run   = apei_exec_noop,
-	},
-};
-
-/*
- * Prevent EINJ interpreter to run simultaneously, because the
- * corresponding firmware implementation may not work properly when
- * invoked simultaneously.
- */
-static DEFINE_MUTEX(einj_mutex);
-
-static void *einj_param;
-
-static void einj_exec_ctx_init(struct apei_exec_context *ctx)
-{
-	apei_exec_ctx_init(ctx, einj_ins_type, ARRAY_SIZE(einj_ins_type),
-			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
-}
-
-static int __einj_get_available_error_type(u32 *type)
-{
-	struct apei_exec_context ctx;
-	int rc;
-
-	einj_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
-	if (rc)
-		return rc;
-	*type = apei_exec_ctx_get_output(&ctx);
-
-	return 0;
-}
-
-/* Get error injection capabilities of the platform */
-static int einj_get_available_error_type(u32 *type)
-{
-	int rc;
-
-	mutex_lock(&einj_mutex);
-	rc = __einj_get_available_error_type(type);
-	mutex_unlock(&einj_mutex);
-
-	return rc;
-}
-
-static int einj_timedout(u64 *t)
-{
-	if ((s64)*t < SLEEP_UNIT_MIN) {
-		pr_warn(FW_WARN "Firmware does not respond in time\n");
-		return 1;
-	}
-	*t -= SLEEP_UNIT_MIN;
-	usleep_range(SLEEP_UNIT_MIN, SLEEP_UNIT_MAX);
-
-	return 0;
-}
-
-static void check_vendor_extension(u64 paddr,
-				   struct set_error_type_with_address *v5param)
-{
-	int	offset = v5param->vendor_extension;
-	struct	vendor_error_type_extension *v;
-	u32	sbdf;
-
-	if (!offset)
-		return;
-	v = acpi_os_map_iomem(paddr + offset, sizeof(*v));
-	if (!v)
-		return;
-	sbdf = v->pcie_sbdf;
-	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
-		sbdf >> 24, (sbdf >> 16) & 0xff,
-		(sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
-		 v->vendor_id, v->device_id, v->rev_id);
-	acpi_os_unmap_iomem(v, sizeof(*v));
-}
-
-static void *einj_get_parameter_address(void)
-{
-	int i;
-	u64 pa_v4 = 0, pa_v5 = 0;
-	struct acpi_whea_header *entry;
-
-	entry = EINJ_TAB_ENTRY(einj_tab);
-	for (i = 0; i < einj_tab->entries; i++) {
-		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE &&
-		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
-		    entry->register_region.space_id ==
-		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
-			pa_v4 = get_unaligned(&entry->register_region.address);
-		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE_WITH_ADDRESS &&
-		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
-		    entry->register_region.space_id ==
-		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
-			pa_v5 = get_unaligned(&entry->register_region.address);
-		entry++;
-	}
-	if (pa_v5) {
-		struct set_error_type_with_address *v5param;
-
-		v5param = acpi_os_map_iomem(pa_v5, sizeof(*v5param));
-		if (v5param) {
-			acpi5 = 1;
-			check_vendor_extension(pa_v5, v5param);
-			return v5param;
-		}
-	}
-	if (param_extension && pa_v4) {
-		struct einj_parameter *v4param;
-
-		v4param = acpi_os_map_iomem(pa_v4, sizeof(*v4param));
-		if (!v4param)
-			return NULL;
-		if (v4param->reserved1 || v4param->reserved2) {
-			acpi_os_unmap_iomem(v4param, sizeof(*v4param));
-			return NULL;
-		}
-		return v4param;
-	}
-
-	return NULL;
-}
-
-/* do sanity check to trigger table */
-static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab)
-{
-	if (trigger_tab->header_size != sizeof(struct acpi_einj_trigger))
-		return -EINVAL;
-	if (trigger_tab->table_size > PAGE_SIZE ||
-	    trigger_tab->table_size < trigger_tab->header_size)
-		return -EINVAL;
-	if (trigger_tab->entry_count !=
-	    (trigger_tab->table_size - trigger_tab->header_size) /
-	    sizeof(struct acpi_einj_entry))
-		return -EINVAL;
-
-	return 0;
-}
-
-static struct acpi_generic_address *einj_get_trigger_parameter_region(
-	struct acpi_einj_trigger *trigger_tab, u64 param1, u64 param2)
-{
-	int i;
-	struct acpi_whea_header *entry;
-
-	entry = (struct acpi_whea_header *)
-		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
-	for (i = 0; i < trigger_tab->entry_count; i++) {
-		if (entry->action == ACPI_EINJ_TRIGGER_ERROR &&
-		entry->instruction <= ACPI_EINJ_WRITE_REGISTER_VALUE &&
-		entry->register_region.space_id ==
-			ACPI_ADR_SPACE_SYSTEM_MEMORY &&
-		(entry->register_region.address & param2) == (param1 & param2))
-			return &entry->register_region;
-		entry++;
-	}
-
-	return NULL;
-}
-/* Execute instructions in trigger error action table */
-static int __einj_error_trigger(u64 trigger_paddr, u32 type,
-				u64 param1, u64 param2)
-{
-	struct acpi_einj_trigger *trigger_tab = NULL;
-	struct apei_exec_context trigger_ctx;
-	struct apei_resources trigger_resources;
-	struct acpi_whea_header *trigger_entry;
-	struct resource *r;
-	u32 table_size;
-	int rc = -EIO;
-	struct acpi_generic_address *trigger_param_region = NULL;
-
-	r = request_mem_region(trigger_paddr, sizeof(*trigger_tab),
-			       "APEI EINJ Trigger Table");
-	if (!r) {
-		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger table\n",
-		       (unsigned long long)trigger_paddr,
-		       (unsigned long long)trigger_paddr +
-			    sizeof(*trigger_tab) - 1);
-		goto out;
-	}
-	trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab));
-	if (!trigger_tab) {
-		pr_err("Failed to map trigger table!\n");
-		goto out_rel_header;
-	}
-	rc = einj_check_trigger_header(trigger_tab);
-	if (rc) {
-		pr_warn(FW_BUG "Invalid trigger error action table.\n");
-		goto out_rel_header;
-	}
-
-	/* No action structures in the TRIGGER_ERROR table, nothing to do */
-	if (!trigger_tab->entry_count)
-		goto out_rel_header;
-
-	rc = -EIO;
-	table_size = trigger_tab->table_size;
-	r = request_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			       table_size - sizeof(*trigger_tab),
-			       "APEI EINJ Trigger Table");
-	if (!r) {
-		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
-		       (unsigned long long)trigger_paddr + sizeof(*trigger_tab),
-		       (unsigned long long)trigger_paddr + table_size - 1);
-		goto out_rel_header;
-	}
-	iounmap(trigger_tab);
-	trigger_tab = ioremap_cache(trigger_paddr, table_size);
-	if (!trigger_tab) {
-		pr_err("Failed to map trigger table!\n");
-		goto out_rel_entry;
-	}
-	trigger_entry = (struct acpi_whea_header *)
-		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
-	apei_resources_init(&trigger_resources);
-	apei_exec_ctx_init(&trigger_ctx, einj_ins_type,
-			   ARRAY_SIZE(einj_ins_type),
-			   trigger_entry, trigger_tab->entry_count);
-	rc = apei_exec_collect_resources(&trigger_ctx, &trigger_resources);
-	if (rc)
-		goto out_fini;
-	rc = apei_resources_sub(&trigger_resources, &einj_resources);
-	if (rc)
-		goto out_fini;
-	/*
-	 * Some firmware will access target address specified in
-	 * param1 to trigger the error when injecting memory error.
-	 * This will cause resource conflict with regular memory.  So
-	 * remove it from trigger table resources.
-	 */
-	if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) {
-		struct apei_resources addr_resources;
-
-		apei_resources_init(&addr_resources);
-		trigger_param_region = einj_get_trigger_parameter_region(
-			trigger_tab, param1, param2);
-		if (trigger_param_region) {
-			rc = apei_resources_add(&addr_resources,
-				trigger_param_region->address,
-				trigger_param_region->bit_width/8, true);
-			if (rc)
-				goto out_fini;
-			rc = apei_resources_sub(&trigger_resources,
-					&addr_resources);
-		}
-		apei_resources_fini(&addr_resources);
-		if (rc)
-			goto out_fini;
-	}
-	rc = apei_resources_request(&trigger_resources, "APEI EINJ Trigger");
-	if (rc)
-		goto out_fini;
-	rc = apei_exec_pre_map_gars(&trigger_ctx);
-	if (rc)
-		goto out_release;
-
-	rc = apei_exec_run(&trigger_ctx, ACPI_EINJ_TRIGGER_ERROR);
-
-	apei_exec_post_unmap_gars(&trigger_ctx);
-out_release:
-	apei_resources_release(&trigger_resources);
-out_fini:
-	apei_resources_fini(&trigger_resources);
-out_rel_entry:
-	release_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			   table_size - sizeof(*trigger_tab));
-out_rel_header:
-	release_mem_region(trigger_paddr, sizeof(*trigger_tab));
-out:
-	if (trigger_tab)
-		iounmap(trigger_tab);
-
-	return rc;
-}
-
-static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
-			       u64 param3, u64 param4)
-{
-	struct apei_exec_context ctx;
-	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
-	int rc;
-
-	einj_exec_ctx_init(&ctx);
-
-	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION);
-	if (rc)
-		return rc;
-	apei_exec_ctx_set_input(&ctx, type);
-	if (acpi5) {
-		struct set_error_type_with_address *v5param = einj_param;
-
-		v5param->type = type;
-		if (type & ACPI5_VENDOR_BIT) {
-			switch (vendor_flags) {
-			case SETWA_FLAGS_APICID:
-				v5param->apicid = param1;
-				break;
-			case SETWA_FLAGS_MEM:
-				v5param->memory_address = param1;
-				v5param->memory_address_range = param2;
-				break;
-			case SETWA_FLAGS_PCIE_SBDF:
-				v5param->pcie_sbdf = param1;
-				break;
-			}
-			v5param->flags = vendor_flags;
-		} else if (flags) {
-			v5param->flags = flags;
-			v5param->memory_address = param1;
-			v5param->memory_address_range = param2;
-			v5param->apicid = param3;
-			v5param->pcie_sbdf = param4;
-		} else {
-			switch (type) {
-			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
-			case ACPI_EINJ_PROCESSOR_UNCORRECTABLE:
-			case ACPI_EINJ_PROCESSOR_FATAL:
-				v5param->apicid = param1;
-				v5param->flags = SETWA_FLAGS_APICID;
-				break;
-			case ACPI_EINJ_MEMORY_CORRECTABLE:
-			case ACPI_EINJ_MEMORY_UNCORRECTABLE:
-			case ACPI_EINJ_MEMORY_FATAL:
-				v5param->memory_address = param1;
-				v5param->memory_address_range = param2;
-				v5param->flags = SETWA_FLAGS_MEM;
-				break;
-			case ACPI_EINJ_PCIX_CORRECTABLE:
-			case ACPI_EINJ_PCIX_UNCORRECTABLE:
-			case ACPI_EINJ_PCIX_FATAL:
-				v5param->pcie_sbdf = param1;
-				v5param->flags = SETWA_FLAGS_PCIE_SBDF;
-				break;
-			}
-		}
-	} else {
-		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
-		if (rc)
-			return rc;
-		if (einj_param) {
-			struct einj_parameter *v4param = einj_param;
-
-			v4param->param1 = param1;
-			v4param->param2 = param2;
-		}
-	}
-	rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
-	if (rc)
-		return rc;
-	for (;;) {
-		rc = apei_exec_run(&ctx, ACPI_EINJ_CHECK_BUSY_STATUS);
-		if (rc)
-			return rc;
-		val = apei_exec_ctx_get_output(&ctx);
-		if (!(val & EINJ_OP_BUSY))
-			break;
-		if (einj_timedout(&timeout))
-			return -EIO;
-	}
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_COMMAND_STATUS);
-	if (rc)
-		return rc;
-	val = apei_exec_ctx_get_output(&ctx);
-	if (val == EINJ_STATUS_FAIL)
-		return -EBUSY;
-	else if (val == EINJ_STATUS_INVAL)
-		return -EINVAL;
-
-	/*
-	 * The error is injected into the platform successfully, then it needs
-	 * to trigger the error.
-	 */
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_TRIGGER_TABLE);
-	if (rc)
-		return rc;
-	trigger_paddr = apei_exec_ctx_get_output(&ctx);
-	if (notrigger == 0) {
-		rc = __einj_error_trigger(trigger_paddr, type, param1, param2);
-		if (rc)
-			return rc;
-	}
-	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
-
-	return rc;
-}
-
-/* Inject the specified hardware error */
-static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
-			     u64 param3, u64 param4)
-{
-	int rc;
-	u64 base_addr, size;
-
-	/* If user manually set "flags", make sure it is legal */
-	if (flags && (flags &
-		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
-		return -EINVAL;
-
-	/*
-	 * We need extra sanity checks for memory errors.
-	 * Other types leap directly to injection.
-	 */
-
-	/* ensure param1/param2 existed */
-	if (!(param_extension || acpi5))
-		goto inject;
-
-	/* ensure injection is memory related */
-	if (type & ACPI5_VENDOR_BIT) {
-		if (vendor_flags != SETWA_FLAGS_MEM)
-			goto inject;
-	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
-		goto inject;
-
-	/*
-	 * Disallow crazy address masks that give BIOS leeway to pick
-	 * injection address almost anywhere. Insist on page or
-	 * better granularity and that target address is normal RAM or
-	 * NVDIMM.
-	 */
-	base_addr = param1 & param2;
-	size = ~param2 + 1;
-
-	if (((param2 & PAGE_MASK) != PAGE_MASK) ||
-	    ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
-				!= REGION_INTERSECTS) &&
-	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY)
-				!= REGION_INTERSECTS) &&
-	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_SOFT_RESERVED)
-				!= REGION_INTERSECTS) &&
-	     !arch_is_platform_page(base_addr)))
-		return -EINVAL;
-
-	if (is_zero_pfn(base_addr >> PAGE_SHIFT))
-		return -EADDRINUSE;
-
-inject:
-	mutex_lock(&einj_mutex);
-	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
-	mutex_unlock(&einj_mutex);
-
-	return rc;
-}
-
-static u32 error_type;
-static u32 error_flags;
-static u64 error_param1;
-static u64 error_param2;
-static u64 error_param3;
-static u64 error_param4;
-static struct dentry *einj_debug_dir;
-static const char * const einj_error_type_string[] = {
-	"0x00000001\tProcessor Correctable\n",
-	"0x00000002\tProcessor Uncorrectable non-fatal\n",
-	"0x00000004\tProcessor Uncorrectable fatal\n",
-	"0x00000008\tMemory Correctable\n",
-	"0x00000010\tMemory Uncorrectable non-fatal\n",
-	"0x00000020\tMemory Uncorrectable fatal\n",
-	"0x00000040\tPCI Express Correctable\n",
-	"0x00000080\tPCI Express Uncorrectable non-fatal\n",
-	"0x00000100\tPCI Express Uncorrectable fatal\n",
-	"0x00000200\tPlatform Correctable\n",
-	"0x00000400\tPlatform Uncorrectable non-fatal\n",
-	"0x00000800\tPlatform Uncorrectable fatal\n",
-	"0x00001000\tCXL.cache Protocol Correctable\n",
-	"0x00002000\tCXL.cache Protocol Uncorrectable non-fatal\n",
-	"0x00004000\tCXL.cache Protocol Uncorrectable fatal\n",
-	"0x00008000\tCXL.mem Protocol Correctable\n",
-	"0x00010000\tCXL.mem Protocol Uncorrectable non-fatal\n",
-	"0x00020000\tCXL.mem Protocol Uncorrectable fatal\n",
-};
-
-static int available_error_type_show(struct seq_file *m, void *v)
-{
-	int rc;
-	u32 available_error_type = 0;
-
-	rc = einj_get_available_error_type(&available_error_type);
-	if (rc)
-		return rc;
-	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
-		if (available_error_type & BIT(pos))
-			seq_puts(m, einj_error_type_string[pos]);
-
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(available_error_type);
-
-static int error_type_get(void *data, u64 *val)
-{
-	*val = error_type;
-
-	return 0;
-}
-
-static int error_type_set(void *data, u64 val)
-{
-	int rc;
-	u32 available_error_type = 0;
-	u32 tval, vendor;
-
-	/* Only low 32 bits for error type are valid */
-	if (val & GENMASK_ULL(63, 32))
-		return -EINVAL;
-
-	/*
-	 * Vendor defined types have 0x80000000 bit set, and
-	 * are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
-	 */
-	vendor = val & ACPI5_VENDOR_BIT;
-	tval = val & 0x7fffffff;
-
-	/* Only one error type can be specified */
-	if (tval & (tval - 1))
-		return -EINVAL;
-	if (!vendor) {
-		rc = einj_get_available_error_type(&available_error_type);
-		if (rc)
-			return rc;
-		if (!(val & available_error_type))
-			return -EINVAL;
-	}
-	error_type = val;
-
-	return 0;
-}
-
-DEFINE_DEBUGFS_ATTRIBUTE(error_type_fops, error_type_get, error_type_set,
-			 "0x%llx\n");
-
-static int error_inject_set(void *data, u64 val)
-{
-	if (!error_type)
-		return -EINVAL;
-
-	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
-		error_param3, error_param4);
-}
-
-DEFINE_DEBUGFS_ATTRIBUTE(error_inject_fops, NULL, error_inject_set, "%llu\n");
-
-static int einj_check_table(struct acpi_table_einj *einj_tab)
-{
-	if ((einj_tab->header_length !=
-	     (sizeof(struct acpi_table_einj) - sizeof(einj_tab->header)))
-	    && (einj_tab->header_length != sizeof(struct acpi_table_einj)))
-		return -EINVAL;
-	if (einj_tab->header.length < sizeof(struct acpi_table_einj))
-		return -EINVAL;
-	if (einj_tab->entries !=
-	    (einj_tab->header.length - sizeof(struct acpi_table_einj)) /
-	    sizeof(struct acpi_einj_entry))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __init einj_init(void)
-{
-	int rc;
-	acpi_status status;
-	struct apei_exec_context ctx;
-
-	if (acpi_disabled) {
-		pr_info("ACPI disabled.\n");
-		return -ENODEV;
-	}
-
-	status = acpi_get_table(ACPI_SIG_EINJ, 0,
-				(struct acpi_table_header **)&einj_tab);
-	if (status == AE_NOT_FOUND) {
-		pr_warn("EINJ table not found.\n");
-		return -ENODEV;
-	} else if (ACPI_FAILURE(status)) {
-		pr_err("Failed to get EINJ table: %s\n",
-				acpi_format_exception(status));
-		return -EINVAL;
-	}
-
-	rc = einj_check_table(einj_tab);
-	if (rc) {
-		pr_warn(FW_BUG "Invalid EINJ table.\n");
-		goto err_put_table;
-	}
-
-	rc = -ENOMEM;
-	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
-
-	debugfs_create_file("available_error_type", S_IRUSR, einj_debug_dir,
-			    NULL, &available_error_type_fops);
-	debugfs_create_file_unsafe("error_type", 0600, einj_debug_dir,
-				   NULL, &error_type_fops);
-	debugfs_create_file_unsafe("error_inject", 0200, einj_debug_dir,
-				   NULL, &error_inject_fops);
-
-	apei_resources_init(&einj_resources);
-	einj_exec_ctx_init(&ctx);
-	rc = apei_exec_collect_resources(&ctx, &einj_resources);
-	if (rc) {
-		pr_err("Error collecting EINJ resources.\n");
-		goto err_fini;
-	}
-
-	rc = apei_resources_request(&einj_resources, "APEI EINJ");
-	if (rc) {
-		pr_err("Error requesting memory/port resources.\n");
-		goto err_fini;
-	}
-
-	rc = apei_exec_pre_map_gars(&ctx);
-	if (rc) {
-		pr_err("Error pre-mapping GARs.\n");
-		goto err_release;
-	}
-
-	einj_param = einj_get_parameter_address();
-	if ((param_extension || acpi5) && einj_param) {
-		debugfs_create_x32("flags", S_IRUSR | S_IWUSR, einj_debug_dir,
-				   &error_flags);
-		debugfs_create_x64("param1", S_IRUSR | S_IWUSR, einj_debug_dir,
-				   &error_param1);
-		debugfs_create_x64("param2", S_IRUSR | S_IWUSR, einj_debug_dir,
-				   &error_param2);
-		debugfs_create_x64("param3", S_IRUSR | S_IWUSR, einj_debug_dir,
-				   &error_param3);
-		debugfs_create_x64("param4", S_IRUSR | S_IWUSR, einj_debug_dir,
-				   &error_param4);
-		debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
-				   einj_debug_dir, &notrigger);
-	}
-
-	if (vendor_dev[0]) {
-		vendor_blob.data = vendor_dev;
-		vendor_blob.size = strlen(vendor_dev);
-		debugfs_create_blob("vendor", S_IRUSR, einj_debug_dir,
-				    &vendor_blob);
-		debugfs_create_x32("vendor_flags", S_IRUSR | S_IWUSR,
-				   einj_debug_dir, &vendor_flags);
-	}
-
-	pr_info("Error INJection is initialized.\n");
-
-	return 0;
-
-err_release:
-	apei_resources_release(&einj_resources);
-err_fini:
-	apei_resources_fini(&einj_resources);
-	debugfs_remove_recursive(einj_debug_dir);
-err_put_table:
-	acpi_put_table((struct acpi_table_header *)einj_tab);
-
-	return rc;
-}
-
-static void __exit einj_exit(void)
-{
-	struct apei_exec_context ctx;
-
-	if (einj_param) {
-		acpi_size size = (acpi5) ?
-			sizeof(struct set_error_type_with_address) :
-			sizeof(struct einj_parameter);
-
-		acpi_os_unmap_iomem(einj_param, size);
-	}
-	einj_exec_ctx_init(&ctx);
-	apei_exec_post_unmap_gars(&ctx);
-	apei_resources_release(&einj_resources);
-	apei_resources_fini(&einj_resources);
-	debugfs_remove_recursive(einj_debug_dir);
-	acpi_put_table((struct acpi_table_header *)einj_tab);
-}
-
-module_init(einj_init);
-module_exit(einj_exit);
-
-MODULE_AUTHOR("Huang Ying");
-MODULE_DESCRIPTION("APEI Error INJection support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index 8bc71cdc2270..ff0e8bf8e97a 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -60,9 +60,8 @@ static long erst_dbg_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case APEI_ERST_CLEAR_RECORD:
-		rc = copy_from_user(&record_id, (void __user *)arg,
-				    sizeof(record_id));
-		if (rc)
+		if (copy_from_user(&record_id, (void __user *)arg,
+				   sizeof(record_id)))
 			return -EFAULT;
 		return erst_clear(record_id);
 	case APEI_ERST_GET_RECORD_COUNT:
@@ -175,8 +174,7 @@ static ssize_t erst_dbg_write(struct file *filp, const char __user *ubuf,
 		erst_dbg_buf = p;
 		erst_dbg_buf_len = usize;
 	}
-	rc = copy_from_user(erst_dbg_buf, ubuf, usize);
-	if (rc) {
+	if (copy_from_user(erst_dbg_buf, ubuf, usize)) {
 		rc = -EFAULT;
 		goto out;
 	}
@@ -199,7 +197,6 @@ static const struct file_operations erst_dbg_ops = {
 	.read		= erst_dbg_read,
 	.write		= erst_dbg_write,
 	.unlocked_ioctl	= erst_dbg_ioctl,
-	.llseek		= no_llseek,
 };
 
 static struct miscdevice erst_dbg_dev = {
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..97ee19f2cae0 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cleanup.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -33,6 +34,7 @@
 #include <linux/irq_work.h>
 #include <linux/llist.h>
 #include <linux/genalloc.h>
+#include <linux/kfifo.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/aer.h>
@@ -47,6 +49,7 @@
 #include <acpi/apei.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
+#include <cxl/event.h>
 #include <ras/ras_event.h>
 
 #include "apei-internal.h"
@@ -102,6 +105,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 }
 
 /*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
+/*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
  * compatible with existing boot arg use cases.
@@ -156,8 +173,6 @@ static struct gen_pool *ghes_estatus_pool;
 static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
-static int ghes_panic_timeout __read_mostly = 30;
-
 static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
@@ -449,28 +464,41 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-/*
- * Called as task_work before returning to user-space.
- * Ensure any queued work has been done before we return to the context that
- * triggered the notification.
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
  */
-static void ghes_kick_task_work(struct callback_head *head)
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
 {
-	struct acpi_hest_generic_status *estatus;
-	struct ghes_estatus_node *estatus_node;
-	u32 node_len;
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
 
-	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
-	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		memory_failure_queue_kick(estatus_node->task_work_cpu);
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
 
-	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
 }
 
 static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
+	struct ghes_task_work *twcb;
 	unsigned long pfn;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
@@ -484,12 +512,24 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 		return false;
 	}
 
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
+	}
+
 	memory_failure_queue(pfn, flags);
 	return true;
 }
 
 static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+				       int sev, bool sync)
 {
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
@@ -503,7 +543,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
 		flags = MF_SOFT_OFFLINE;
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = 0;
+		flags = sync ? MF_ACTION_REQUIRED : 0;
 
 	if (flags != -1)
 		return ghes_do_memory_failure(mem_err->physical_addr, flags);
@@ -511,9 +551,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	return false;
 }
 
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+				       int sev, bool sync)
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -538,7 +580,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 		 * and don't filter out 'corrected' error here.
 		 */
 		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
 			p += err_info->length;
 			continue;
 		}
@@ -657,7 +699,175 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
-static bool ghes_do_proc(struct ghes *ghes,
+/* Room for 8 entries */
+#define CXL_CPER_PROT_ERR_FIFO_DEPTH 8
+static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
+		    CXL_CPER_PROT_ERR_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
+static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
+struct work_struct *cxl_cper_prot_err_work;
+
+static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				   int severity)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+	u8 *dvsec_start, *cap_start;
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
+		pr_err_ratelimited("CXL CPER invalid agent type\n");
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
+		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
+		return;
+	}
+
+	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
+		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
+				   prot_err->err_len);
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
+		pr_warn(FW_WARN "CXL CPER no device serial number\n");
+
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
+	switch (prot_err->agent_type) {
+	case RCD:
+	case DEVICE:
+	case LD:
+	case FMLD:
+	case RP:
+	case DSP:
+	case USP:
+		memcpy(&wd.prot_err, prot_err, sizeof(wd.prot_err));
+
+		dvsec_start = (u8 *)(prot_err + 1);
+		cap_start = dvsec_start + prot_err->dvsec_len;
+
+		memcpy(&wd.ras_cap, cap_start, sizeof(wd.ras_cap));
+		wd.severity = cper_severity_to_aer(severity);
+		break;
+	default:
+		pr_err_ratelimited("CXL CPER invalid agent type: %d\n",
+				   prot_err->agent_type);
+		return;
+	}
+
+	if (!kfifo_put(&cxl_cper_prot_err_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_prot_err_work);
+#endif
+}
+
+int cxl_cper_register_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
+
+int cxl_cper_unregister_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
+
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_prot_err_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
+
+/* Room for 8 entries for each of the 4 event log queues */
+#define CXL_CPER_FIFO_DEPTH 32
+DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_work changes */
+static DEFINE_SPINLOCK(cxl_cper_work_lock);
+struct work_struct *cxl_cper_work;
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	struct cxl_cper_work_data wd;
+
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(spinlock_irqsave)(&cxl_cper_work_lock);
+
+	if (!cxl_cper_work)
+		return;
+
+	wd.event_type = event_type;
+	memcpy(&wd.rec, rec, sizeof(wd.rec));
+
+	if (!kfifo_put(&cxl_cper_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_work);
+}
+
+int cxl_cper_register_work(struct work_struct *work)
+{
+	if (cxl_cper_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_work_lock);
+	cxl_cper_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
+
+int cxl_cper_unregister_work(struct work_struct *work)
+{
+	if (cxl_cper_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_work_lock);
+	cxl_cper_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
+
+int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
+
+static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
@@ -666,6 +876,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 	const guid_t *fru_id = &guid_null;
 	char *fru_text = "";
 	bool queued = false;
+	bool sync = is_hest_sync_notify(ghes);
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -683,13 +894,29 @@ static bool ghes_do_proc(struct ghes *ghes,
 			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev);
+			queued = ghes_handle_memory_failure(gdata, sev, sync);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			queued = ghes_handle_arm_hw_error(gdata, sev);
+			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_prot_err(prot_err, gdata->error_severity);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
+			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
@@ -700,7 +927,16 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 	}
 
-	return queued;
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(ghes->dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -882,14 +1118,18 @@ static void __ghes_panic(struct ghes *ghes,
 			 struct acpi_hest_generic_status *estatus,
 			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
+	const char *msg = GHES_PFX "Fatal hardware error";
+
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
-	/* reboot to log the error! */
 	if (!panic_timeout)
-		panic_timeout = ghes_panic_timeout;
-	panic("Fatal hardware error!");
+		pr_emerg("%s but panic disabled\n", msg);
+
+	panic(msg);
 }
 
 static int ghes_proc(struct ghes *ghes)
@@ -934,7 +1174,7 @@ static void ghes_add_timer(struct ghes *ghes)
 
 static void ghes_poll_func(struct timer_list *t)
 {
-	struct ghes *ghes = from_timer(ghes, t, timer);
+	struct ghes *ghes = timer_container_of(ghes, t, timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -967,12 +1207,10 @@ static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
 	int ret = NOTIFY_DONE;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
-	rcu_read_lock();
 	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
 		if (!ghes_proc(ghes))
 			ret = NOTIFY_OK;
 	}
-	rcu_read_unlock();
 	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 
 	return ret;
@@ -1002,9 +1240,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	bool task_work_pending;
 	u32 len, node_len;
-	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -1019,25 +1255,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
-		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
+
+		ghes_do_proc(estatus_node->ghes, estatus);
+
 		if (!ghes_estatus_cached(estatus)) {
 			generic = estatus_node->generic;
 			if (ghes_print_estatus(NULL, generic, estatus))
 				ghes_estatus_cache_add(generic, estatus);
 		}
-
-		if (task_work_pending && current->mm) {
-			estatus_node->task_work.func = ghes_kick_task_work;
-			estatus_node->task_work_cpu = smp_processor_id();
-			ret = task_work_add(current, &estatus_node->task_work,
-					    TWA_RESUME);
-			if (ret)
-				estatus_node->task_work.func = NULL;
-		}
-
-		if (!estatus_node->task_work.func)
-			gen_pool_free(ghes_estatus_pool,
-				      (unsigned long)estatus_node, node_len);
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
 
 		llnode = next;
 	}
@@ -1098,7 +1325,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
-	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
@@ -1438,7 +1664,7 @@ err:
 	return rc;
 }
 
-static int ghes_remove(struct platform_device *ghes_dev)
+static void ghes_remove(struct platform_device *ghes_dev)
 {
 	int rc;
 	struct ghes *ghes;
@@ -1475,8 +1701,15 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		break;
 	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
 		rc = apei_sdei_unregister_ghes(ghes);
-		if (rc)
-			return rc;
+		if (rc) {
+			/*
+			 * Returning early results in a resource leak, but we're
+			 * only here if stopping the hardware failed.
+			 */
+			dev_err(&ghes_dev->dev, "Failed to unregister ghes (%pe)\n",
+				ERR_PTR(rc));
+			return;
+		}
 		break;
 	default:
 		BUG();
@@ -1490,8 +1723,6 @@ static int ghes_remove(struct platform_device *ghes_dev)
 	mutex_unlock(&ghes_devs_mutex);
 
 	kfree(ghes);
-
-	return 0;
 }
 
 static struct platform_driver ghes_platform_driver = {
@@ -1506,7 +1737,7 @@ void __init acpi_ghes_init(void)
 {
 	int rc;
 
-	sdei_init();
+	acpi_sdei_init();
 
 	if (acpi_disabled)
 		return;
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 6aef1ee5e1bd..20d757687e3d 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -37,6 +37,20 @@ EXPORT_SYMBOL_GPL(hest_disable);
 
 static struct acpi_table_hest *__read_mostly hest_tab;
 
+/*
+ * Since GHES_ASSIST is not supported, skip initialization of GHES_ASSIST
+ * structures for MCA.
+ * During HEST parsing, detected MCA error sources are cached from early
+ * table entries so that the Flags and Source Id fields from these cached
+ * values are then referred to in later table entries to determine if the
+ * encountered GHES_ASSIST structure should be initialized.
+ */
+static struct {
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_machine_check *mc;
+	struct acpi_hest_ia_deferred_check *dmc;
+} mces;
+
 static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
 	[ACPI_HEST_TYPE_IA32_CHECK] = -1,	/* need further calculation */
 	[ACPI_HEST_TYPE_IA32_CORRECTED_CHECK] = -1,
@@ -70,22 +84,54 @@ static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
 		cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
 		len = sizeof(*cmc) + cmc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.cmc = cmc;
 	} else if (hest_type == ACPI_HEST_TYPE_IA32_CHECK) {
 		struct acpi_hest_ia_machine_check *mc;
 		mc = (struct acpi_hest_ia_machine_check *)hest_hdr;
 		len = sizeof(*mc) + mc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.mc = mc;
 	} else if (hest_type == ACPI_HEST_TYPE_IA32_DEFERRED_CHECK) {
 		struct acpi_hest_ia_deferred_check *mc;
 		mc = (struct acpi_hest_ia_deferred_check *)hest_hdr;
 		len = sizeof(*mc) + mc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.dmc = mc;
 	}
 	BUG_ON(len == -1);
 
 	return len;
 };
 
+/*
+ * GHES and GHESv2 structures share the same format, starting from
+ * Source Id and ending in Error Status Block Length (inclusive).
+ */
+static bool is_ghes_assist_struct(struct acpi_hest_header *hest_hdr)
+{
+	struct acpi_hest_generic *ghes;
+	u16 related_source_id;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR &&
+	    hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR_V2)
+		return false;
+
+	ghes = (struct acpi_hest_generic *)hest_hdr;
+	related_source_id = ghes->related_source_id;
+
+	if (mces.cmc && mces.cmc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.cmc->header.source_id)
+		return true;
+	if (mces.mc && mces.mc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.mc->header.source_id)
+		return true;
+	if (mces.dmc && mces.dmc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.dmc->header.source_id)
+		return true;
+
+	return false;
+}
+
 typedef int (*apei_hest_func_t)(struct acpi_hest_header *hest_hdr, void *data);
 
 static int apei_hest_parse(apei_hest_func_t func, void *data)
@@ -114,6 +160,11 @@ static int apei_hest_parse(apei_hest_func_t func, void *data)
 			return -EINVAL;
 		}
 
+		if (is_ghes_assist_struct(hest_hdr)) {
+			hest_hdr = (void *)hest_hdr + len;
+			continue;
+		}
+
 		rc = func(hest_hdr, data);
 		if (rc)
 			return rc;
diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 143debc1ba4a..05ecde9eaabe 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -1,7 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ACPI_AGDI) 	+= agdi.o
-obj-$(CONFIG_ACPI_IORT) 	+= iort.o
-obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
 obj-$(CONFIG_ACPI_APMT) 	+= apmt.o
+obj-$(CONFIG_ACPI_FFH)		+= ffh.o
+obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
+obj-$(CONFIG_ACPI_IORT) 	+= iort.o
+obj-$(CONFIG_ACPI_PROCESSOR_IDLE) += cpuidle.o
 obj-$(CONFIG_ARM_AMBA)		+= amba.o
 obj-y				+= dma.o init.o
+obj-y				+= thermal_cpufreq.o
diff --git a/drivers/acpi/arm64/agdi.c b/drivers/acpi/arm64/agdi.c
index 8b3c7d42b41b..e0df3daa4abf 100644
--- a/drivers/acpi/arm64/agdi.c
+++ b/drivers/acpi/arm64/agdi.c
@@ -58,7 +58,7 @@ static int agdi_probe(struct platform_device *pdev)
 	return agdi_sdei_probe(pdev, adata);
 }
 
-static int agdi_remove(struct platform_device *pdev)
+static void agdi_remove(struct platform_device *pdev)
 {
 	struct agdi_data *adata = dev_get_platdata(&pdev->dev);
 	int err, i;
@@ -67,7 +67,7 @@ static int agdi_remove(struct platform_device *pdev)
 	if (err) {
 		dev_err(&pdev->dev, "Failed to disable sdei-event #%d (%pe)\n",
 			adata->sdei_event, ERR_PTR(err));
-		return 0;
+		return;
 	}
 
 	for (i = 0; i < 3; i++) {
@@ -81,8 +81,6 @@ static int agdi_remove(struct platform_device *pdev)
 	if (err)
 		dev_err(&pdev->dev, "Failed to unregister sdei-event #%d (%pe)\n",
 			adata->sdei_event, ERR_PTR(err));
-
-	return 0;
 }
 
 static struct platform_driver agdi_driver = {
diff --git a/drivers/acpi/arm64/amba.c b/drivers/acpi/arm64/amba.c
index 171b5c2c7edd..1350083bce5f 100644
--- a/drivers/acpi/arm64/amba.c
+++ b/drivers/acpi/arm64/amba.c
@@ -22,24 +22,12 @@
 static const struct acpi_device_id amba_id_list[] = {
 	{"ARMH0061", 0}, /* PL061 GPIO Device */
 	{"ARMH0330", 0}, /* ARM DMA Controller DMA-330 */
-	{"ARMHC501", 0}, /* ARM CoreSight ETR */
-	{"ARMHC502", 0}, /* ARM CoreSight STM */
-	{"ARMHC503", 0}, /* ARM CoreSight Debug */
-	{"ARMHC979", 0}, /* ARM CoreSight TPIU */
-	{"ARMHC97C", 0}, /* ARM CoreSight SoC-400 TMC, SoC-600 ETF/ETB */
-	{"ARMHC98D", 0}, /* ARM CoreSight Dynamic Replicator */
-	{"ARMHC9CA", 0}, /* ARM CoreSight CATU */
-	{"ARMHC9FF", 0}, /* ARM CoreSight Dynamic Funnel */
 	{"", 0},
 };
 
 static void amba_register_dummy_clk(void)
 {
-	static struct clk *amba_dummy_clk;
-
-	/* If clock already registered */
-	if (amba_dummy_clk)
-		return;
+	struct clk *amba_dummy_clk;
 
 	amba_dummy_clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL, 0, 0);
 	clk_register_clkdev(amba_dummy_clk, "apb_pclk", NULL);
diff --git a/drivers/acpi/arm64/cpuidle.c b/drivers/acpi/arm64/cpuidle.c
new file mode 100644
index 000000000000..801f9c450142
--- /dev/null
+++ b/drivers/acpi/arm64/cpuidle.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARM64 CPU idle arch support
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/psci.h>
+#include <acpi/processor.h>
+
+#define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
+
+static int psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i, count;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	count = pr->power.count - 1;
+	if (count <= 0)
+		return -ENODEV;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i + 1];
+		/*
+		 * Only bits[31:0] represent a PSCI power_state while
+		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
+		 */
+		state = lpi->address;
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+int acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+	return psci_acpi_cpu_init_idle(cpu);
+}
+
+__cpuidle int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+	u32 state = lpi->address;
+
+	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM_RCU(psci_cpu_suspend_enter,
+						lpi->index, state);
+	else
+		return CPU_PM_CPU_IDLE_ENTER_PARAM_RCU(psci_cpu_suspend_enter,
+					     lpi->index, state);
+}
diff --git a/drivers/acpi/arm64/dma.c b/drivers/acpi/arm64/dma.c
index 93d796531af3..f30f138352b7 100644
--- a/drivers/acpi/arm64/dma.c
+++ b/drivers/acpi/arm64/dma.c
@@ -8,7 +8,6 @@ void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
 	u64 end, mask;
-	u64 size = 0;
 	const struct bus_dma_region *map = NULL;
 
 	/*
@@ -23,31 +22,28 @@ void acpi_arch_dma_setup(struct device *dev)
 	}
 
 	if (dev->coherent_dma_mask)
-		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+		end = dev->coherent_dma_mask;
 	else
-		size = 1ULL << 32;
+		end = (1ULL << 32) - 1;
+
+	if (dev->dma_range_map) {
+		dev_dbg(dev, "dma_range_map already set\n");
+		return;
+	}
 
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
-		const struct bus_dma_region *r = map;
-
-		for (end = 0; r->size; r++) {
-			if (r->dma_start + r->size - 1 > end)
-				end = r->dma_start + r->size - 1;
-		}
-
-		size = end + 1;
+		end = dma_range_map_max(map);
 		dev->dma_range_map = map;
 	}
 
 	if (ret == -ENODEV)
-		ret = iort_dma_get_ranges(dev, &size);
+		ret = iort_dma_get_ranges(dev, &end);
 	if (!ret) {
 		/*
 		 * Limit coherent and dma mask based on size retrieved from
 		 * firmware.
 		 */
-		end = size - 1;
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;
 		dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask);
diff --git a/drivers/acpi/arm64/ffh.c b/drivers/acpi/arm64/ffh.c
new file mode 100644
index 000000000000..877edc6557e9
--- /dev/null
+++ b/drivers/acpi/arm64/ffh.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/acpi.h>
+#include <linux/arm-smccc.h>
+#include <linux/slab.h>
+
+/*
+ * Implements ARM64 specific callbacks to support ACPI FFH Operation Region as
+ * specified in https://developer.arm.com/docs/den0048/latest
+ */
+struct acpi_ffh_data {
+	struct acpi_ffh_info info;
+	void (*invoke_ffh_fn)(unsigned long a0, unsigned long a1,
+			      unsigned long a2, unsigned long a3,
+			      unsigned long a4, unsigned long a5,
+			      unsigned long a6, unsigned long a7,
+			      struct arm_smccc_res *args,
+			      struct arm_smccc_quirk *res);
+	void (*invoke_ffh64_fn)(const struct arm_smccc_1_2_regs *args,
+				struct arm_smccc_1_2_regs *res);
+};
+
+int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt)
+{
+	enum arm_smccc_conduit conduit;
+	struct acpi_ffh_data *ffh_ctxt;
+
+	if (arm_smccc_get_version() < ARM_SMCCC_VERSION_1_2)
+		return -EOPNOTSUPP;
+
+	conduit = arm_smccc_1_1_get_conduit();
+	if (conduit == SMCCC_CONDUIT_NONE) {
+		pr_err("%s: invalid SMCCC conduit\n", __func__);
+		return -EOPNOTSUPP;
+	}
+
+	ffh_ctxt = kzalloc(sizeof(*ffh_ctxt), GFP_KERNEL);
+	if (!ffh_ctxt)
+		return -ENOMEM;
+
+	if (conduit == SMCCC_CONDUIT_SMC) {
+		ffh_ctxt->invoke_ffh_fn = __arm_smccc_smc;
+		ffh_ctxt->invoke_ffh64_fn = arm_smccc_1_2_smc;
+	} else {
+		ffh_ctxt->invoke_ffh_fn = __arm_smccc_hvc;
+		ffh_ctxt->invoke_ffh64_fn = arm_smccc_1_2_hvc;
+	}
+
+	memcpy(ffh_ctxt, handler_ctxt, sizeof(ffh_ctxt->info));
+
+	*region_ctxt = ffh_ctxt;
+	return AE_OK;
+}
+
+static bool acpi_ffh_smccc_owner_allowed(u32 fid)
+{
+	int owner = ARM_SMCCC_OWNER_NUM(fid);
+
+	if (owner == ARM_SMCCC_OWNER_STANDARD ||
+	    owner == ARM_SMCCC_OWNER_SIP || owner == ARM_SMCCC_OWNER_OEM)
+		return true;
+
+	return false;
+}
+
+int acpi_ffh_address_space_arch_handler(acpi_integer *value, void *region_context)
+{
+	int ret = 0;
+	struct acpi_ffh_data *ffh_ctxt = region_context;
+
+	if (ffh_ctxt->info.offset == 0) {
+		/* SMC/HVC 32bit call */
+		struct arm_smccc_res res;
+		u32 a[8] = { 0 }, *ptr = (u32 *)value;
+
+		if (!ARM_SMCCC_IS_FAST_CALL(*ptr) || ARM_SMCCC_IS_64(*ptr) ||
+		    !acpi_ffh_smccc_owner_allowed(*ptr) ||
+		    ffh_ctxt->info.length > 32) {
+			ret = AE_ERROR;
+		} else {
+			int idx, len = ffh_ctxt->info.length >> 2;
+
+			for (idx = 0; idx < len; idx++)
+				a[idx] = *(ptr + idx);
+
+			ffh_ctxt->invoke_ffh_fn(a[0], a[1], a[2], a[3], a[4],
+						a[5], a[6], a[7], &res, NULL);
+			memcpy(value, &res, sizeof(res));
+		}
+
+	} else if (ffh_ctxt->info.offset == 1) {
+		/* SMC/HVC 64bit call */
+		struct arm_smccc_1_2_regs *r = (struct arm_smccc_1_2_regs *)value;
+
+		if (!ARM_SMCCC_IS_FAST_CALL(r->a0) || !ARM_SMCCC_IS_64(r->a0) ||
+		    !acpi_ffh_smccc_owner_allowed(r->a0) ||
+		    ffh_ctxt->info.length > sizeof(*r)) {
+			ret = AE_ERROR;
+		} else {
+			ffh_ctxt->invoke_ffh64_fn(r, r);
+			memcpy(value, r, ffh_ctxt->info.length);
+		}
+	} else {
+		ret = AE_ERROR;
+	}
+
+	return ret;
+}
diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
index c0e77c1c8e09..fd995a1d3d24 100644
--- a/drivers/acpi/arm64/gtdt.c
+++ b/drivers/acpi/arm64/gtdt.c
@@ -36,19 +36,25 @@ struct acpi_gtdt_descriptor {
 
 static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata;
 
-static inline __init void *next_platform_timer(void *platform_timer)
+static __init bool platform_timer_valid(void *platform_timer)
 {
 	struct acpi_gtdt_header *gh = platform_timer;
 
-	platform_timer += gh->length;
-	if (platform_timer < acpi_gtdt_desc.gtdt_end)
-		return platform_timer;
+	return (platform_timer >= (void *)(acpi_gtdt_desc.gtdt + 1) &&
+		platform_timer < acpi_gtdt_desc.gtdt_end &&
+		gh->length != 0 &&
+		platform_timer + gh->length <= acpi_gtdt_desc.gtdt_end);
+}
+
+static __init void *next_platform_timer(void *platform_timer)
+{
+	struct acpi_gtdt_header *gh = platform_timer;
 
-	return NULL;
+	return platform_timer + gh->length;
 }
 
 #define for_each_platform_timer(_g)				\
-	for (_g = acpi_gtdt_desc.platform_timer; _g;	\
+	for (_g = acpi_gtdt_desc.platform_timer; platform_timer_valid(_g);\
 	     _g = next_platform_timer(_g))
 
 static inline bool is_timer_block(void *platform_timer)
@@ -157,6 +163,7 @@ int __init acpi_gtdt_init(struct acpi_table_header *table,
 {
 	void *platform_timer;
 	struct acpi_table_gtdt *gtdt;
+	u32 cnt = 0;
 
 	gtdt = container_of(table, struct acpi_table_gtdt, header);
 	acpi_gtdt_desc.gtdt = gtdt;
@@ -176,14 +183,22 @@ int __init acpi_gtdt_init(struct acpi_table_header *table,
 		return 0;
 	}
 
-	platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
-	if (platform_timer < (void *)table + sizeof(struct acpi_table_gtdt)) {
-		pr_err(FW_BUG "invalid timer data.\n");
-		return -EINVAL;
+	acpi_gtdt_desc.platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
+	for_each_platform_timer(platform_timer)
+		cnt++;
+
+	if (cnt != gtdt->platform_timer_count) {
+		cnt = min(cnt, gtdt->platform_timer_count);
+		pr_err(FW_BUG "limiting Platform Timer count to %d\n", cnt);
 	}
-	acpi_gtdt_desc.platform_timer = platform_timer;
+
+	if (!cnt) {
+		acpi_gtdt_desc.platform_timer = NULL;
+		return 0;
+	}
+
 	if (platform_timer_count)
-		*platform_timer_count = gtdt->platform_timer_count;
+		*platform_timer_count = cnt;
 
 	return 0;
 }
@@ -283,7 +298,7 @@ error:
 		if (frame->virt_irq > 0)
 			acpi_unregister_gsi(gtdt_frame->virtual_timer_interrupt);
 		frame->virt_irq = 0;
-	} while (i-- >= 0 && gtdt_frame--);
+	} while (i-- > 0 && gtdt_frame--);
 
 	return -EINVAL;
 }
@@ -352,7 +367,7 @@ static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
 	}
 
 	irq = map_gt_gsi(wd->timer_interrupt, wd->timer_flags);
-	res[2] = (struct resource)DEFINE_RES_IRQ(irq);
+	res[2] = DEFINE_RES_IRQ(irq);
 	if (irq <= 0) {
 		pr_warn("failed to map the Watchdog interrupt.\n");
 		nr_res--;
@@ -373,11 +388,11 @@ static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
 	return 0;
 }
 
-static int __init gtdt_sbsa_gwdt_init(void)
+static int __init gtdt_platform_timer_init(void)
 {
 	void *platform_timer;
 	struct acpi_table_header *table;
-	int ret, timer_count, gwdt_count = 0;
+	int ret, timer_count, gwdt_count = 0, mmio_timer_count = 0;
 
 	if (acpi_disabled)
 		return 0;
@@ -399,20 +414,41 @@ static int __init gtdt_sbsa_gwdt_init(void)
 		goto out_put_gtdt;
 
 	for_each_platform_timer(platform_timer) {
+		ret = 0;
+
 		if (is_non_secure_watchdog(platform_timer)) {
 			ret = gtdt_import_sbsa_gwdt(platform_timer, gwdt_count);
 			if (ret)
-				break;
+				continue;
 			gwdt_count++;
+		} else 	if (is_timer_block(platform_timer)) {
+			struct arch_timer_mem atm = {};
+			struct platform_device *pdev;
+
+			ret = gtdt_parse_timer_block(platform_timer, &atm);
+			if (ret)
+				continue;
+
+			pdev = platform_device_register_data(NULL, "gtdt-arm-mmio-timer",
+							     gwdt_count, &atm,
+							     sizeof(atm));
+			if (IS_ERR(pdev)) {
+				pr_err("Can't register timer %d\n", gwdt_count);
+				continue;
+			}
+
+			mmio_timer_count++;
 		}
 	}
 
 	if (gwdt_count)
 		pr_info("found %d SBSA generic Watchdog(s).\n", gwdt_count);
+	if (mmio_timer_count)
+		pr_info("found %d Generic MMIO timer(s).\n", mmio_timer_count);
 
 out_put_gtdt:
 	acpi_put_table(table);
 	return ret;
 }
 
-device_initcall(gtdt_sbsa_gwdt_init);
+device_initcall(gtdt_platform_timer_init);
diff --git a/drivers/acpi/arm64/init.c b/drivers/acpi/arm64/init.c
index d0c8aed90fd1..7a47d8095a7d 100644
--- a/drivers/acpi/arm64/init.c
+++ b/drivers/acpi/arm64/init.c
@@ -2,7 +2,7 @@
 #include <linux/acpi.h>
 #include "init.h"
 
-void __init acpi_arm_init(void)
+void __init acpi_arch_init(void)
 {
 	if (IS_ENABLED(CONFIG_ACPI_AGDI))
 		acpi_agdi_init();
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 6496ff5a6ba2..65f0f56ad753 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -822,7 +822,7 @@ static struct iommu_iort_rmr_data *iort_rmr_alloc(
 		return NULL;
 
 	/* Create a copy of SIDs array to associate with this rmr_data */
-	sids_copy = kmemdup(sids, num_sids * sizeof(*sids), GFP_KERNEL);
+	sids_copy = kmemdup_array(sids, num_sids, sizeof(*sids), GFP_KERNEL);
 	if (!sids_copy) {
 		kfree(rmr_data);
 		return NULL;
@@ -937,8 +937,10 @@ static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start,
 
 	new_sids = krealloc_array(sids, count + new_count,
 				  sizeof(*new_sids), GFP_KERNEL);
-	if (!new_sids)
+	if (!new_sids) {
+		kfree(sids);
 		return NULL;
+	}
 
 	for (i = count; i < total_count; i++)
 		new_sids[i] = id_start++;
@@ -1218,13 +1220,24 @@ static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node)
 	return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED;
 }
 
+static bool iort_pci_rc_supports_canwbs(struct acpi_iort_node *node)
+{
+	struct acpi_iort_memory_access *memory_access;
+	struct acpi_iort_root_complex *pci_rc;
+
+	pci_rc = (struct acpi_iort_root_complex *)node->node_data;
+	memory_access =
+		(struct acpi_iort_memory_access *)&pci_rc->memory_properties;
+	return memory_access->memory_flags & ACPI_IORT_MF_CANWBS;
+}
+
 static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
 			    u32 streamid)
 {
-	const struct iommu_ops *ops;
 	struct fwnode_handle *iort_fwnode;
 
-	if (!node)
+	/* If there's no SMMU driver at all, give up now */
+	if (!node || !iort_iommu_driver_enabled(node->type))
 		return -ENODEV;
 
 	iort_fwnode = iort_get_fwnode(node);
@@ -1232,19 +1245,10 @@ static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
 		return -ENODEV;
 
 	/*
-	 * If the ops look-up fails, this means that either
-	 * the SMMU drivers have not been probed yet or that
-	 * the SMMU drivers are not built in the kernel;
-	 * Depending on whether the SMMU drivers are built-in
-	 * in the kernel or not, defer the IOMMU configuration
-	 * or just abort it.
+	 * If the SMMU drivers are enabled but not loaded/probed
+	 * yet, this will defer.
 	 */
-	ops = iommu_ops_from_fwnode(iort_fwnode);
-	if (!ops)
-		return iort_iommu_driver_enabled(node->type) ?
-		       -EPROBE_DEFER : -ENODEV;
-
-	return acpi_iommu_fwspec_init(dev, streamid, iort_fwnode, ops);
+	return acpi_iommu_fwspec_init(dev, streamid, iort_fwnode);
 }
 
 struct iort_pci_alias_info {
@@ -1344,6 +1348,8 @@ int iort_iommu_configure_id(struct device *dev, const u32 *id_in)
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (fwspec && iort_pci_rc_supports_ats(node))
 			fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS;
+		if (fwspec && iort_pci_rc_supports_canwbs(node))
+			fwspec->flags |= IOMMU_FWSPEC_PCI_RC_CANWBS;
 	} else {
 		node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
 				      iort_match_node_callback, dev);
@@ -1367,7 +1373,7 @@ int iort_iommu_configure_id(struct device *dev, const u32 *input_id)
 { return -ENODEV; }
 #endif
 
-static int nc_dma_get_range(struct device *dev, u64 *size)
+static int nc_dma_get_range(struct device *dev, u64 *limit)
 {
 	struct acpi_iort_node *node;
 	struct acpi_iort_named_component *ncomp;
@@ -1384,13 +1390,13 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 		return -EINVAL;
 	}
 
-	*size = ncomp->memory_address_limit >= 64 ? U64_MAX :
-			1ULL<<ncomp->memory_address_limit;
+	*limit = ncomp->memory_address_limit >= 64 ? U64_MAX :
+			(1ULL << ncomp->memory_address_limit) - 1;
 
 	return 0;
 }
 
-static int rc_dma_get_range(struct device *dev, u64 *size)
+static int rc_dma_get_range(struct device *dev, u64 *limit)
 {
 	struct acpi_iort_node *node;
 	struct acpi_iort_root_complex *rc;
@@ -1408,8 +1414,8 @@ static int rc_dma_get_range(struct device *dev, u64 *size)
 		return -EINVAL;
 	}
 
-	*size = rc->memory_address_limit >= 64 ? U64_MAX :
-			1ULL<<rc->memory_address_limit;
+	*limit = rc->memory_address_limit >= 64 ? U64_MAX :
+			(1ULL << rc->memory_address_limit) - 1;
 
 	return 0;
 }
@@ -1417,16 +1423,16 @@ static int rc_dma_get_range(struct device *dev, u64 *size)
 /**
  * iort_dma_get_ranges() - Look up DMA addressing limit for the device
  * @dev: device to lookup
- * @size: DMA range size result pointer
+ * @limit: DMA limit result pointer
  *
  * Return: 0 on success, an error otherwise.
  */
-int iort_dma_get_ranges(struct device *dev, u64 *size)
+int iort_dma_get_ranges(struct device *dev, u64 *limit)
 {
 	if (dev_is_pci(dev))
-		return rc_dma_get_range(dev, size);
+		return rc_dma_get_range(dev, limit);
 	else
-		return nc_dma_get_range(dev, size);
+		return nc_dma_get_range(dev, limit);
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
@@ -1712,6 +1718,15 @@ static struct acpi_platform_list pmcg_plat_info[] __initdata = {
 	/* HiSilicon Hip09 Platform */
 	{"HISI  ", "HIP09   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
 	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
+	{"HISI  ", "HIP09A  ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
+	/* HiSilicon Hip10/11 Platform uses the same SMMU IP with Hip09 */
+	{"HISI  ", "HIP10   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
+	{"HISI  ", "HIP10C  ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
+	{"HISI  ", "HIP11   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
 	{ }
 };
 
diff --git a/drivers/acpi/arm64/thermal_cpufreq.c b/drivers/acpi/arm64/thermal_cpufreq.c
new file mode 100644
index 000000000000..582854914c5c
--- /dev/null
+++ b/drivers/acpi/arm64/thermal_cpufreq.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/acpi.h>
+#include <linux/export.h>
+
+#include "../internal.h"
+
+#define SMCCC_SOC_ID_T241      0x036b0241
+
+int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	s32 soc_id = arm_smccc_get_soc_id_version();
+
+	/*
+	 * Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) and
+	 * reduce the CPUFREQ Thermal reduction percentage to 5%.
+	 */
+	if (soc_id == SMCCC_SOC_ID_T241)
+		return 5;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_arch_thermal_cpufreq_pctg);
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b379401ff1c2..67b76492c839 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -10,7 +10,6 @@
 
 #define pr_fmt(fmt) "ACPI: battery: " fmt
 
-#include <linux/async.h>
 #include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/jiffies.h>
@@ -22,7 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/types.h>
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 #include <linux/acpi.h>
 #include <linux/power_supply.h>
@@ -38,9 +37,10 @@
 /* Battery power unit: 0 means mW, 1 means mA */
 #define ACPI_BATTERY_POWER_UNIT_MA	1
 
-#define ACPI_BATTERY_STATE_DISCHARGING	0x1
-#define ACPI_BATTERY_STATE_CHARGING	0x2
-#define ACPI_BATTERY_STATE_CRITICAL	0x4
+#define ACPI_BATTERY_STATE_DISCHARGING		0x1
+#define ACPI_BATTERY_STATE_CHARGING		0x2
+#define ACPI_BATTERY_STATE_CRITICAL		0x4
+#define ACPI_BATTERY_STATE_CHARGE_LIMITING	0x8
 
 #define MAX_STRING_LENGTH	64
 
@@ -49,8 +49,6 @@ MODULE_AUTHOR("Alexey Starikovskiy <astarikovskiy@suse.de>");
 MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
-static async_cookie_t async_cookie;
-static bool battery_driver_registered;
 static int battery_bix_broken_package;
 static int battery_notification_delay_ms;
 static int battery_ac_is_broken;
@@ -94,7 +92,7 @@ enum {
 
 struct acpi_battery {
 	struct mutex lock;
-	struct mutex sysfs_lock;
+	struct mutex update_lock;
 	struct power_supply *bat;
 	struct power_supply_desc bat_desc;
 	struct acpi_device *device;
@@ -155,7 +153,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery);
 
 static int acpi_battery_is_charged(struct acpi_battery *battery)
 {
-	/* charging, discharging or critical low */
+	/* charging, discharging, critical low or charge limited */
 	if (battery->state != 0)
 		return 0;
 
@@ -215,6 +213,8 @@ static int acpi_battery_get_property(struct power_supply *psy,
 			val->intval = acpi_battery_handle_discharging(battery);
 		else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
 			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		else if (battery->state & ACPI_BATTERY_STATE_CHARGE_LIMITING)
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
 		else if (acpi_battery_is_charged(battery))
 			val->intval = POWER_SUPPLY_STATUS_FULL;
 		else
@@ -279,8 +279,8 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		    full_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
 			ret = -ENODEV;
 		else
-			val->intval = battery->capacity_now * 100/
-					full_capacity;
+			val->intval = DIV_ROUND_CLOSEST_ULL(battery->capacity_now * 100ULL,
+					full_capacity);
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
 		if (battery->state & ACPI_BATTERY_STATE_CRITICAL)
@@ -308,7 +308,7 @@ static int acpi_battery_get_property(struct power_supply *psy,
 	return ret;
 }
 
-static enum power_supply_property charge_battery_props[] = {
+static const enum power_supply_property charge_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -326,7 +326,7 @@ static enum power_supply_property charge_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
-static enum power_supply_property charge_battery_full_cap_broken_props[] = {
+static const enum power_supply_property charge_battery_full_cap_broken_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -340,7 +340,7 @@ static enum power_supply_property charge_battery_full_cap_broken_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
-static enum power_supply_property energy_battery_props[] = {
+static const enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -358,7 +358,7 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
-static enum power_supply_property energy_battery_full_cap_broken_props[] = {
+static const enum power_supply_property energy_battery_full_cap_broken_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -661,7 +661,7 @@ static ssize_t acpi_battery_alarm_show(struct device *dev,
 {
 	struct acpi_battery *battery = to_acpi_battery(dev_get_drvdata(dev));
 
-	return sprintf(buf, "%d\n", battery->alarm * 1000);
+	return sysfs_emit(buf, "%d\n", battery->alarm * 1000);
 }
 
 static ssize_t acpi_battery_alarm_store(struct device *dev,
@@ -678,12 +678,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
 	return count;
 }
 
-static const struct device_attribute alarm_attr = {
+static struct device_attribute alarm_attr = {
 	.attr = {.name = "alarm", .mode = 0644},
 	.show = acpi_battery_alarm_show,
 	.store = acpi_battery_alarm_store,
 };
 
+static struct attribute *acpi_battery_attrs[] = {
+	&alarm_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(acpi_battery);
+
 /*
  * The Battery Hooking API
  *
@@ -697,28 +703,35 @@ static LIST_HEAD(acpi_battery_list);
 static LIST_HEAD(battery_hook_list);
 static DEFINE_MUTEX(hook_mutex);
 
-static void __battery_hook_unregister(struct acpi_battery_hook *hook, int lock)
+static void battery_hook_unregister_unlocked(struct acpi_battery_hook *hook)
 {
 	struct acpi_battery *battery;
+
 	/*
 	 * In order to remove a hook, we first need to
 	 * de-register all the batteries that are registered.
 	 */
-	if (lock)
-		mutex_lock(&hook_mutex);
 	list_for_each_entry(battery, &acpi_battery_list, list) {
 		if (!hook->remove_battery(battery->bat, hook))
 			power_supply_changed(battery->bat);
 	}
-	list_del(&hook->list);
-	if (lock)
-		mutex_unlock(&hook_mutex);
-	pr_info("extension unregistered: %s\n", hook->name);
+	list_del_init(&hook->list);
+
+	pr_info("hook unregistered: %s\n", hook->name);
 }
 
 void battery_hook_unregister(struct acpi_battery_hook *hook)
 {
-	__battery_hook_unregister(hook, 1);
+	mutex_lock(&hook_mutex);
+	/*
+	 * Ignore already unregistered battery hooks. This might happen
+	 * if a battery hook was previously unloaded due to an error when
+	 * adding a new battery.
+	 */
+	if (!list_empty(&hook->list))
+		battery_hook_unregister_unlocked(hook);
+
+	mutex_unlock(&hook_mutex);
 }
 EXPORT_SYMBOL_GPL(battery_hook_unregister);
 
@@ -727,7 +740,6 @@ void battery_hook_register(struct acpi_battery_hook *hook)
 	struct acpi_battery *battery;
 
 	mutex_lock(&hook_mutex);
-	INIT_LIST_HEAD(&hook->list);
 	list_add(&hook->list, &battery_hook_list);
 	/*
 	 * Now that the driver is registered, we need
@@ -739,23 +751,38 @@ void battery_hook_register(struct acpi_battery_hook *hook)
 		if (hook->add_battery(battery->bat, hook)) {
 			/*
 			 * If a add-battery returns non-zero,
-			 * the registration of the extension has failed,
+			 * the registration of the hook has failed,
 			 * and we will not add it to the list of loaded
 			 * hooks.
 			 */
-			pr_err("extension failed to load: %s", hook->name);
-			__battery_hook_unregister(hook, 0);
+			pr_err("hook failed to load: %s", hook->name);
+			battery_hook_unregister_unlocked(hook);
 			goto end;
 		}
 
 		power_supply_changed(battery->bat);
 	}
-	pr_info("new extension: %s\n", hook->name);
+	pr_info("new hook: %s\n", hook->name);
 end:
 	mutex_unlock(&hook_mutex);
 }
 EXPORT_SYMBOL_GPL(battery_hook_register);
 
+static void devm_battery_hook_unregister(void *data)
+{
+	struct acpi_battery_hook *hook = data;
+
+	battery_hook_unregister(hook);
+}
+
+int devm_battery_hook_register(struct device *dev, struct acpi_battery_hook *hook)
+{
+	battery_hook_register(hook);
+
+	return devm_add_action_or_reset(dev, devm_battery_hook_unregister, hook);
+}
+EXPORT_SYMBOL_GPL(devm_battery_hook_register);
+
 /*
  * This function gets called right after the battery sysfs
  * attributes have been added, so that the drivers that
@@ -778,12 +805,12 @@ static void battery_hook_add_battery(struct acpi_battery *battery)
 	list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) {
 		if (hook_node->add_battery(battery->bat, hook_node)) {
 			/*
-			 * The notification of the extensions has failed, to
-			 * prevent further errors we will unload the extension.
+			 * The notification of the hook has failed, to
+			 * prevent further errors we will unload the hook.
 			 */
-			pr_err("error in extension, unloading: %s",
+			pr_err("error in hook, unloading: %s",
 					hook_node->name);
-			__battery_hook_unregister(hook_node, 0);
+			battery_hook_unregister_unlocked(hook_node);
 		}
 	}
 	mutex_unlock(&hook_mutex);
@@ -816,14 +843,18 @@ static void __exit battery_hook_exit(void)
 	 * need to remove the hooks.
 	 */
 	list_for_each_entry_safe(hook, ptr, &battery_hook_list, list) {
-		__battery_hook_unregister(hook, 1);
+		battery_hook_unregister(hook);
 	}
 	mutex_destroy(&hook_mutex);
 }
 
 static int sysfs_add_battery(struct acpi_battery *battery)
 {
-	struct power_supply_config psy_cfg = { .drv_data = battery, };
+	struct power_supply_config psy_cfg = {
+		.drv_data = battery,
+		.attr_grp = acpi_battery_groups,
+		.no_wakeup_source = true,
+	};
 	bool full_cap_broken = false;
 
 	if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) &&
@@ -858,7 +889,7 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 	battery->bat_desc.type = POWER_SUPPLY_TYPE_BATTERY;
 	battery->bat_desc.get_property = acpi_battery_get_property;
 
-	battery->bat = power_supply_register_no_ws(&battery->device->dev,
+	battery->bat = power_supply_register(&battery->device->dev,
 				&battery->bat_desc, &psy_cfg);
 
 	if (IS_ERR(battery->bat)) {
@@ -868,21 +899,17 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 		return result;
 	}
 	battery_hook_add_battery(battery);
-	return device_create_file(&battery->bat->dev, &alarm_attr);
+	return 0;
 }
 
 static void sysfs_remove_battery(struct acpi_battery *battery)
 {
-	mutex_lock(&battery->sysfs_lock);
-	if (!battery->bat) {
-		mutex_unlock(&battery->sysfs_lock);
+	if (!battery->bat)
 		return;
-	}
+
 	battery_hook_remove_battery(battery);
-	device_remove_file(&battery->bat->dev, &alarm_attr);
 	power_supply_unregister(battery->bat);
 	battery->bat = NULL;
-	mutex_unlock(&battery->sysfs_lock);
 }
 
 static void find_battery(const struct dmi_header *dm, void *private)
@@ -1042,6 +1069,9 @@ static void acpi_battery_notify(acpi_handle handle, u32 event, void *data)
 
 	if (!battery)
 		return;
+
+	guard(mutex)(&battery->update_lock);
+
 	old = battery->bat;
 	/*
 	 * On Acer Aspire V5-573G notifications are sometimes triggered too
@@ -1064,21 +1094,22 @@ static void acpi_battery_notify(acpi_handle handle, u32 event, void *data)
 }
 
 static int battery_notify(struct notifier_block *nb,
-			       unsigned long mode, void *_unused)
+			  unsigned long mode, void *_unused)
 {
 	struct acpi_battery *battery = container_of(nb, struct acpi_battery,
 						    pm_nb);
-	int result;
 
-	switch (mode) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
+	if (mode == PM_POST_SUSPEND || mode == PM_POST_HIBERNATION) {
+		guard(mutex)(&battery->update_lock);
+
 		if (!acpi_battery_present(battery))
 			return 0;
 
 		if (battery->bat) {
 			acpi_battery_refresh(battery);
 		} else {
+			int result;
+
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;
@@ -1090,7 +1121,6 @@ static int battery_notify(struct notifier_block *nb,
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
-		break;
 	}
 
 	return 0;
@@ -1168,6 +1198,8 @@ static int acpi_battery_update_retry(struct acpi_battery *battery)
 {
 	int retry, ret;
 
+	guard(mutex)(&battery->update_lock);
+
 	for (retry = 5; retry; retry--) {
 		ret = acpi_battery_update(battery, false);
 		if (!ret)
@@ -1178,10 +1210,17 @@ static int acpi_battery_update_retry(struct acpi_battery *battery)
 	return ret;
 }
 
+static void sysfs_battery_cleanup(struct acpi_battery *battery)
+{
+	guard(mutex)(&battery->update_lock);
+
+	sysfs_remove_battery(battery);
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
-	struct acpi_battery *battery = NULL;
+	struct acpi_battery *battery;
 
 	if (!device)
 		return -EINVAL;
@@ -1189,15 +1228,21 @@ static int acpi_battery_add(struct acpi_device *device)
 	if (device->dep_unmet)
 		return -EPROBE_DEFER;
 
-	battery = kzalloc(sizeof(struct acpi_battery), GFP_KERNEL);
+	battery = devm_kzalloc(&device->dev, sizeof(*battery), GFP_KERNEL);
 	if (!battery)
 		return -ENOMEM;
 	battery->device = device;
-	strcpy(acpi_device_name(device), ACPI_BATTERY_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_BATTERY_CLASS);
+	strscpy(acpi_device_name(device), ACPI_BATTERY_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_BATTERY_CLASS);
 	device->driver_data = battery;
-	mutex_init(&battery->lock);
-	mutex_init(&battery->sysfs_lock);
+	result = devm_mutex_init(&device->dev, &battery->lock);
+	if (result)
+		return result;
+
+	result = devm_mutex_init(&device->dev, &battery->update_lock);
+	if (result)
+		return result;
+
 	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
 
@@ -1209,7 +1254,9 @@ static int acpi_battery_add(struct acpi_device *device)
 		device->status.battery_present ? "present" : "absent");
 
 	battery->pm_nb.notifier_call = battery_notify;
-	register_pm_notifier(&battery->pm_nb);
+	result = register_pm_notifier(&battery->pm_nb);
+	if (result)
+		goto fail;
 
 	device_init_wakeup(&device->dev, 1);
 
@@ -1224,17 +1271,14 @@ fail_pm:
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
 fail:
-	sysfs_remove_battery(battery);
-	mutex_destroy(&battery->lock);
-	mutex_destroy(&battery->sysfs_lock);
-	kfree(battery);
+	sysfs_battery_cleanup(battery);
 
 	return result;
 }
 
 static void acpi_battery_remove(struct acpi_device *device)
 {
-	struct acpi_battery *battery = NULL;
+	struct acpi_battery *battery;
 
 	if (!device || !acpi_driver_data(device))
 		return;
@@ -1246,14 +1290,12 @@ static void acpi_battery_remove(struct acpi_device *device)
 
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
-	sysfs_remove_battery(battery);
 
-	mutex_destroy(&battery->lock);
-	mutex_destroy(&battery->sysfs_lock);
-	kfree(battery);
+	guard(mutex)(&battery->update_lock);
+
+	sysfs_remove_battery(battery);
 }
 
-#ifdef CONFIG_PM_SLEEP
 /* this is needed to learn about changes made in suspended state */
 static int acpi_battery_resume(struct device *dev)
 {
@@ -1267,14 +1309,14 @@ static int acpi_battery_resume(struct device *dev)
 		return -EINVAL;
 
 	battery->update_time = 0;
+
+	guard(mutex)(&battery->update_lock);
+
 	acpi_battery_update(battery, true);
 	return 0;
 }
-#else
-#define acpi_battery_resume NULL
-#endif
 
-static SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume);
 
 static struct acpi_driver acpi_battery_driver = {
 	.name = "battery",
@@ -1284,38 +1326,24 @@ static struct acpi_driver acpi_battery_driver = {
 		.add = acpi_battery_add,
 		.remove = acpi_battery_remove,
 		},
-	.drv.pm = &acpi_battery_pm,
+	.drv.pm = pm_sleep_ptr(&acpi_battery_pm),
+	.drv.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 };
 
-static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
-{
-	int result;
-
-	if (acpi_quirk_skip_acpi_ac_and_battery())
-		return;
-
-	dmi_check_system(bat_dmi_table);
-
-	result = acpi_bus_register_driver(&acpi_battery_driver);
-	battery_driver_registered = (result == 0);
-}
-
 static int __init acpi_battery_init(void)
 {
-	if (acpi_disabled)
+	if (acpi_disabled || acpi_quirk_skip_acpi_ac_and_battery())
 		return -ENODEV;
 
-	async_cookie = async_schedule(acpi_battery_init_async, NULL);
-	return 0;
+	dmi_check_system(bat_dmi_table);
+
+	return acpi_bus_register_driver(&acpi_battery_driver);
 }
 
 static void __exit acpi_battery_exit(void)
 {
-	async_synchronize_cookie(async_cookie + 1);
-	if (battery_driver_registered) {
-		acpi_bus_unregister_driver(&acpi_battery_driver);
-		battery_hook_exit();
-	}
+	acpi_bus_unregister_driver(&acpi_battery_driver);
+	battery_hook_exit();
 }
 
 module_init(acpi_battery_init);
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index e4fb9e225ddf..0fdd581ef96f 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -29,14 +29,7 @@ BGRT_SHOW(type, image_type);
 BGRT_SHOW(xoffset, image_offset_x);
 BGRT_SHOW(yoffset, image_offset_y);
 
-static ssize_t image_read(struct file *file, struct kobject *kobj,
-	       struct bin_attribute *attr, char *buf, loff_t off, size_t count)
-{
-	memcpy(buf, attr->private + off, count);
-	return count;
-}
-
-static BIN_ATTR_RO(image, 0);	/* size gets filled in later */
+static __ro_after_init BIN_ATTR_SIMPLE_RO(image);
 
 static struct attribute *bgrt_attributes[] = {
 	&bgrt_attr_version.attr,
@@ -47,7 +40,7 @@ static struct attribute *bgrt_attributes[] = {
 	NULL,
 };
 
-static struct bin_attribute *bgrt_bin_attributes[] = {
+static const struct bin_attribute *const bgrt_bin_attributes[] = {
 	&bin_attr_image,
 	NULL,
 };
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 72e64c0718c9..a984ccd4a2a0 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -112,6 +112,17 @@ int acpi_bus_get_status(struct acpi_device *device)
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	if (!device->status.present && device->status.enabled) {
+		pr_info(FW_BUG "Device [%s] status [%08x]: not present and enabled\n",
+			device->pnp.bus_id, (u32)sta);
+		device->status.enabled = 0;
+		/*
+		 * The status is clearly invalid, so clear the functional bit as
+		 * well to avoid attempting to use the device.
+		 */
+		device->status.functional = 0;
+	}
+
 	acpi_set_device_status(device, sta);
 
 	if (device->status.functional && !device->status.present) {
@@ -316,9 +327,16 @@ static void acpi_bus_osc_negotiate_platform_control(void)
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT;
 	if (IS_ENABLED(CONFIG_ACPI_PROCESSOR))
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT;
+	if (IS_ENABLED(CONFIG_ACPI_THERMAL))
+		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT;
+	if (IS_ENABLED(CONFIG_ACPI_BATTERY))
+		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT;
 
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_OVER_16_PSTATES_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GED_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT;
 	if (IS_ENABLED(CONFIG_ACPI_PRMT))
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PRM_SUPPORT;
 	if (IS_ENABLED(CONFIG_ACPI_FFH))
@@ -408,7 +426,7 @@ static void acpi_bus_decode_usb_osc(const char *msg, u32 bits)
 static u8 sb_usb_uuid_str[] = "23A0D13A-26AB-486C-9C5F-0FFA525A575A";
 static void acpi_bus_osc_negotiate_usb_control(void)
 {
-	u32 capbuf[3];
+	u32 capbuf[3], *capbuf_ret;
 	struct acpi_osc_context context = {
 		.uuid_str = sb_usb_uuid_str,
 		.rev = 1,
@@ -428,7 +446,12 @@ static void acpi_bus_osc_negotiate_usb_control(void)
 	control = OSC_USB_USB3_TUNNELING | OSC_USB_DP_TUNNELING |
 		  OSC_USB_PCIE_TUNNELING | OSC_USB_XDOMAIN;
 
-	capbuf[OSC_QUERY_DWORD] = 0;
+	/*
+	 * Run _OSC first with query bit set, trying to get control over
+	 * all tunneling. The platform can then clear out bits in the
+	 * control dword that it does not want to grant to the OS.
+	 */
+	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
 	capbuf[OSC_SUPPORT_DWORD] = 0;
 	capbuf[OSC_CONTROL_DWORD] = control;
 
@@ -441,8 +464,29 @@ static void acpi_bus_osc_negotiate_usb_control(void)
 		goto out_free;
 	}
 
+	/*
+	 * Run _OSC again now with query bit clear and the control dword
+	 * matching what the platform granted (which may not have all
+	 * the control bits set).
+	 */
+	capbuf_ret = context.ret.pointer;
+
+	capbuf[OSC_QUERY_DWORD] = 0;
+	capbuf[OSC_CONTROL_DWORD] = capbuf_ret[OSC_CONTROL_DWORD];
+
+	kfree(context.ret.pointer);
+
+	status = acpi_run_osc(handle, &context);
+	if (ACPI_FAILURE(status))
+		return;
+
+	if (context.ret.length != sizeof(capbuf)) {
+		pr_info("USB4 _OSC: returned invalid length buffer\n");
+		goto out_free;
+	}
+
 	osc_sb_native_usb4_control =
-		control &  acpi_osc_ctx_get_pci_control(&context);
+		control & acpi_osc_ctx_get_pci_control(&context);
 
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS supports", control);
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS controls",
@@ -964,25 +1008,26 @@ EXPORT_SYMBOL_GPL(acpi_driver_match_device);
    -------------------------------------------------------------------------- */
 
 /**
- * acpi_bus_register_driver - register a driver with the ACPI bus
+ * __acpi_bus_register_driver - register a driver with the ACPI bus
  * @driver: driver being registered
+ * @owner: owning module/driver
  *
  * Registers a driver with the ACPI bus.  Searches the namespace for all
  * devices that match the driver's criteria and binds.  Returns zero for
  * success or a negative error status for failure.
  */
-int acpi_bus_register_driver(struct acpi_driver *driver)
+int __acpi_bus_register_driver(struct acpi_driver *driver, struct module *owner)
 {
 	if (acpi_disabled)
 		return -ENODEV;
 	driver->drv.name = driver->name;
 	driver->drv.bus = &acpi_bus_type;
-	driver->drv.owner = driver->owner;
+	driver->drv.owner = owner;
 
 	return driver_register(&driver->drv);
 }
 
-EXPORT_SYMBOL(acpi_bus_register_driver);
+EXPORT_SYMBOL(__acpi_bus_register_driver);
 
 /**
  * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
@@ -1002,10 +1047,10 @@ EXPORT_SYMBOL(acpi_bus_unregister_driver);
                               ACPI Bus operations
    -------------------------------------------------------------------------- */
 
-static int acpi_bus_match(struct device *dev, struct device_driver *drv)
+static int acpi_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
+	const struct acpi_driver *acpi_drv = to_acpi_driver(drv);
 
 	return acpi_dev->flags.match_driver
 		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
@@ -1071,7 +1116,7 @@ static void acpi_device_remove(struct device *dev)
 	put_device(dev);
 }
 
-struct bus_type acpi_bus_type = {
+const struct bus_type acpi_bus_type = {
 	.name		= "acpi",
 	.match		= acpi_bus_match,
 	.probe		= acpi_device_probe,
@@ -1158,6 +1203,9 @@ static int __init acpi_bus_init_irq(void)
 	case ACPI_IRQ_MODEL_LPIC:
 		message = "LPIC";
 		break;
+	case ACPI_IRQ_MODEL_RINTC:
+		message = "RINTC";
+		break;
 	default:
 		pr_info("Unknown interrupt routing model\n");
 		return -ENODEV;
@@ -1358,7 +1406,7 @@ static int __init acpi_bus_init(void)
 		goto error1;
 
 	/*
-	 * Register the for all standard device notifications.
+	 * Register for all standard device notifications.
 	 */
 	status =
 	    acpi_install_notify_handler(ACPI_ROOT_OBJECT, ACPI_SYSTEM_NOTIFY,
@@ -1386,6 +1434,8 @@ static int __init acpi_bus_init(void)
 struct kobject *acpi_kobj;
 EXPORT_SYMBOL_GPL(acpi_kobj);
 
+void __weak __init acpi_arch_init(void) { }
+
 static int __init acpi_init(void)
 {
 	int result;
@@ -1396,8 +1446,10 @@ static int __init acpi_init(void)
 	}
 
 	acpi_kobj = kobject_create_and_add("acpi", firmware_kobj);
-	if (!acpi_kobj)
-		pr_debug("%s: kset create error\n", __func__);
+	if (!acpi_kobj) {
+		pr_err("Failed to register kobject\n");
+		return -ENOMEM;
+	}
 
 	init_prmt();
 	acpi_init_pcc();
@@ -1413,7 +1465,7 @@ static int __init acpi_init(void)
 	acpi_viot_early_init();
 	acpi_hest_init();
 	acpi_ghes_init();
-	acpi_arm_init();
+	acpi_arch_init();
 	acpi_scan_init();
 	acpi_ec_init();
 	acpi_debugfs_init();
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 1e76a64cce0a..0a7026040188 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -24,6 +24,7 @@
 #define ACPI_BUTTON_CLASS		"button"
 #define ACPI_BUTTON_FILE_STATE		"state"
 #define ACPI_BUTTON_TYPE_UNKNOWN	0x00
+#define ACPI_BUTTON_NOTIFY_WAKE		0x02
 #define ACPI_BUTTON_NOTIFY_STATUS	0x80
 
 #define ACPI_BUTTON_SUBCLASS_POWER	"power"
@@ -130,6 +131,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = {
 		},
 		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
 	},
+	{
+		/*
+		 * Samsung galaxybook2 ,initial _LID device notification returns
+		 * lid closed.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "750XED"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+	},
 	{}
 };
 
@@ -432,7 +444,12 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
 	struct input_dev *input;
 	int keycode;
 
-	if (event != ACPI_BUTTON_NOTIFY_STATUS) {
+	switch (event) {
+	case ACPI_BUTTON_NOTIFY_STATUS:
+		break;
+	case ACPI_BUTTON_NOTIFY_WAKE:
+		break;
+	default:
 		acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n",
 				  event);
 		return;
@@ -441,7 +458,7 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
 	acpi_pm_wakeup_event(&device->dev);
 
 	button = acpi_driver_data(device);
-	if (button->suspended)
+	if (button->suspended || event == ACPI_BUTTON_NOTIFY_WAKE)
 		return;
 
 	input = button->input;
@@ -480,6 +497,7 @@ static int acpi_button_suspend(struct device *dev)
 
 static int acpi_button_resume(struct device *dev)
 {
+	struct input_dev *input;
 	struct acpi_device *device = to_acpi_device(dev);
 	struct acpi_button *button = acpi_driver_data(device);
 
@@ -489,6 +507,14 @@ static int acpi_button_resume(struct device *dev)
 		button->last_time = ktime_get();
 		acpi_lid_initialize_state(device);
 	}
+
+	if (button->type == ACPI_BUTTON_TYPE_POWER) {
+		input = button->input;
+		input_report_key(input, KEY_WAKEUP, 1);
+		input_sync(input);
+		input_report_key(input, KEY_WAKEUP, 0);
+		input_sync(input);
+	}
 	return 0;
 }
 #endif
@@ -538,20 +564,20 @@ static int acpi_button_add(struct acpi_device *device)
 	    !strcmp(hid, ACPI_BUTTON_HID_POWERF)) {
 		button->type = ACPI_BUTTON_TYPE_POWER;
 		handler = acpi_button_notify;
-		strcpy(name, ACPI_BUTTON_DEVICE_NAME_POWER);
+		strscpy(name, ACPI_BUTTON_DEVICE_NAME_POWER, MAX_ACPI_DEVICE_NAME_LEN);
 		sprintf(class, "%s/%s",
 			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_POWER);
 	} else if (!strcmp(hid, ACPI_BUTTON_HID_SLEEP) ||
 		   !strcmp(hid, ACPI_BUTTON_HID_SLEEPF)) {
 		button->type = ACPI_BUTTON_TYPE_SLEEP;
 		handler = acpi_button_notify;
-		strcpy(name, ACPI_BUTTON_DEVICE_NAME_SLEEP);
+		strscpy(name, ACPI_BUTTON_DEVICE_NAME_SLEEP, MAX_ACPI_DEVICE_NAME_LEN);
 		sprintf(class, "%s/%s",
 			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_SLEEP);
 	} else if (!strcmp(hid, ACPI_BUTTON_HID_LID)) {
 		button->type = ACPI_BUTTON_TYPE_LID;
 		handler = acpi_lid_notify;
-		strcpy(name, ACPI_BUTTON_DEVICE_NAME_LID);
+		strscpy(name, ACPI_BUTTON_DEVICE_NAME_LID, MAX_ACPI_DEVICE_NAME_LEN);
 		sprintf(class, "%s/%s",
 			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_LID);
 		input->open = acpi_lid_input_open;
@@ -579,6 +605,7 @@ static int acpi_button_add(struct acpi_device *device)
 	switch (button->type) {
 	case ACPI_BUTTON_TYPE_POWER:
 		input_set_capability(input, EV_KEY, KEY_POWER);
+		input_set_capability(input, EV_KEY, KEY_WAKEUP);
 		break;
 
 	case ACPI_BUTTON_TYPE_SLEEP:
@@ -608,7 +635,7 @@ static int acpi_button_add(struct acpi_device *device)
 		break;
 	default:
 		status = acpi_install_notify_handler(device->handle,
-						     ACPI_DEVICE_NOTIFY, handler,
+						     ACPI_ALL_NOTIFY, handler,
 						     device);
 		break;
 	}
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 7ff269a78c20..ab4651205e8a 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,12 +39,14 @@
 #include <linux/rwsem.h>
 #include <linux/wait.h>
 #include <linux/topology.h>
+#include <linux/dmi.h>
+#include <linux/units.h>
+#include <linux/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 
 struct cppc_pcc_data {
 	struct pcc_mbox_chan *pcc_channel;
-	void __iomem *pcc_comm_addr;
 	bool pcc_channel_acquired;
 	unsigned int deadline_us;
 	unsigned int pcc_mpar, pcc_mrtt, pcc_nominal;
@@ -92,7 +94,7 @@ static DEFINE_PER_CPU(int, cpu_pcc_subspace_idx);
 static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
 
 /* pcc mapped address + header size + offset within PCC subspace */
-#define GET_PCC_VADDR(offs, pcc_ss_id) (pcc_data[pcc_ss_id]->pcc_comm_addr + \
+#define GET_PCC_VADDR(offs, pcc_ss_id) (pcc_data[pcc_ss_id]->pcc_channel->shmem + \
 						0x8 + (offs))
 
 /* Check if a CPC register is in PCC */
@@ -100,6 +102,11 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
 				(cpc)->cpc_entry.reg.space_id ==	\
 				ACPI_ADR_SPACE_PLATFORM_COMM)
 
+/* Check if a CPC register is in FFH */
+#define CPC_IN_FFH(cpc) ((cpc)->type == ACPI_TYPE_BUFFER &&		\
+				(cpc)->cpc_entry.reg.space_id ==	\
+				ACPI_ADR_SPACE_FIXED_HARDWARE)
+
 /* Check if a CPC register is in SystemMemory */
 #define CPC_IN_SYSTEM_MEMORY(cpc) ((cpc)->type == ACPI_TYPE_BUFFER &&	\
 				(cpc)->cpc_entry.reg.space_id ==	\
@@ -121,6 +128,20 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
 #define CPC_SUPPORTED(cpc) ((cpc)->type == ACPI_TYPE_INTEGER ?		\
 				!!(cpc)->cpc_entry.int_value :		\
 				!IS_NULL_REG(&(cpc)->cpc_entry.reg))
+
+/*
+ * Each bit indicates the optionality of the register in per-cpu
+ * cpc_regs[] with the corresponding index. 0 means mandatory and 1
+ * means optional.
+ */
+#define REG_OPTIONAL (0x1FC7D0)
+
+/*
+ * Use the index of the register in per-cpu cpc_regs[] to check if
+ * it's an optional one.
+ */
+#define IS_OPTIONAL_CPC_REG(reg_idx) (REG_OPTIONAL & (1U << (reg_idx)))
+
 /*
  * Arbitrary Retries in case the remote processor is slow to respond
  * to PCC commands. Keeping it high enough to cover emulators where
@@ -157,12 +178,23 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, guaranteed_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_freq);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq);
 
 show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
 show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
 
+/* Check for valid access_width, otherwise, fallback to using bit_width */
+#define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width)
+
+/* Shift and apply the mask for CPC reads/writes */
+#define MASK_VAL_READ(reg, val) (((val) >> (reg)->bit_offset) &				\
+					GENMASK(((reg)->bit_width) - 1, 0))
+#define MASK_VAL_WRITE(reg, prev_val, val)						\
+	((((val) & GENMASK(((reg)->bit_width) - 1, 0)) << (reg)->bit_offset) |		\
+	((prev_val) & ~(GENMASK(((reg)->bit_width) - 1, 0) << (reg)->bit_offset)))	\
+
 static ssize_t show_feedback_ctrs(struct kobject *kobj,
 		struct kobj_attribute *attr, char *buf)
 {
@@ -186,6 +218,7 @@ static struct attribute *cppc_attrs[] = {
 	&highest_perf.attr,
 	&lowest_perf.attr,
 	&lowest_nonlinear_perf.attr,
+	&guaranteed_perf.attr,
 	&nominal_perf.attr,
 	&nominal_freq.attr,
 	&lowest_freq.attr,
@@ -203,7 +236,7 @@ static int check_pcc_chan(int pcc_ss_id, bool chk_err_bit)
 	int ret, status;
 	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
 	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
-		pcc_ss_data->pcc_comm_addr;
+					pcc_ss_data->pcc_channel->shmem;
 
 	if (!pcc_ss_data->platform_owns_pcc)
 		return 0;
@@ -238,7 +271,7 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd)
 	int ret = -EIO, i;
 	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
 	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
-		pcc_ss_data->pcc_comm_addr;
+					pcc_ss_data->pcc_channel->shmem;
 	unsigned int time_delta;
 
 	/*
@@ -443,7 +476,7 @@ bool cppc_allow_fast_switch(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
 		if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&
@@ -551,15 +584,6 @@ static int register_pcc_channel(int pcc_ss_idx)
 		pcc_data[pcc_ss_idx]->pcc_mpar = pcc_chan->max_access_rate;
 		pcc_data[pcc_ss_idx]->pcc_nominal = pcc_chan->latency;
 
-		pcc_data[pcc_ss_idx]->pcc_comm_addr =
-			acpi_os_ioremap(pcc_chan->shmem_base_addr,
-					pcc_chan->shmem_size);
-		if (!pcc_data[pcc_ss_idx]->pcc_comm_addr) {
-			pr_err("Failed to ioremap PCC comm region mem for %d\n",
-			       pcc_ss_idx);
-			return -ENOMEM;
-		}
-
 		/* Set flag so that we don't come here for each CPU. */
 		pcc_data[pcc_ss_idx]->pcc_channel_acquired = true;
 	}
@@ -651,10 +675,6 @@ static int pcc_data_alloc(int pcc_ss_id)
  *  )
  */
 
-#ifndef arch_init_invariance_cppc
-static inline void arch_init_invariance_cppc(void) { }
-#endif
-
 /**
  * acpi_cppc_processor_probe - Search for per CPU _CPC objects.
  * @pr: Ptr to acpi_processor containing this CPU's logical ID.
@@ -676,8 +696,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 
 	if (!osc_sb_cppc2_support_acked) {
 		pr_debug("CPPC v2 _OSC not acked\n");
-		if (!cpc_supported_by_cpu())
+		if (!cpc_supported_by_cpu()) {
+			pr_debug("CPPC is not supported by the CPU\n");
 			return -ENODEV;
+		}
 	}
 
 	/* Parse the ACPI _CPC table for this CPU. */
@@ -777,6 +799,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 			} else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 				if (gas_t->address) {
 					void __iomem *addr;
+					size_t access_width;
 
 					if (!osc_cpc_flexible_adr_space_confirmed) {
 						pr_debug("Flexible address space capability not supported\n");
@@ -784,7 +807,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 							goto out_free;
 					}
 
-					addr = ioremap(gas_t->address, gas_t->bit_width/8);
+					access_width = GET_BIT_WIDTH(gas_t) / 8;
+					addr = ioremap(gas_t->address, access_width);
 					if (!addr)
 						goto out_free;
 					cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr;
@@ -843,6 +867,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 
 	/* Store CPU Logical ID */
 	cpc_ptr->cpu_id = pr->id;
+	raw_spin_lock_init(&cpc_ptr->rmw_lock);
 
 	/* Parse PSD data for this CPU */
 	ret = acpi_get_psd(cpc_ptr, handle);
@@ -880,8 +905,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 		goto out_free;
 	}
 
-	arch_init_invariance_cppc();
-
 	kfree(output.pointer);
 	return 0;
 
@@ -980,6 +1003,7 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
 {
 	void __iomem *vaddr = NULL;
+	int size;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cpc_reg *reg = &reg_res->cpc_entry.reg;
 
@@ -989,14 +1013,15 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
 	}
 
 	*val = 0;
+	size = GET_BIT_WIDTH(reg);
 
-	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
-		u32 width = 8 << (reg->access_width - 1);
+	if (IS_ENABLED(CONFIG_HAS_IOPORT) &&
+	    reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
 		u32 val_u32;
 		acpi_status status;
 
 		status = acpi_os_read_port((acpi_io_address)reg->address,
-					   &val_u32, width);
+					   &val_u32, size);
 		if (ACPI_FAILURE(status)) {
 			pr_debug("Error: Failed to read SystemIO port %llx\n",
 				 reg->address);
@@ -1005,17 +1030,24 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
 
 		*val = val_u32;
 		return 0;
-	} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
+	} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) {
+		/*
+		 * For registers in PCC space, the register size is determined
+		 * by the bit width field; the access size is used to indicate
+		 * the PCC subspace id.
+		 */
+		size = reg->bit_width;
 		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
+	}
 	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
 		vaddr = reg_res->sys_mem_vaddr;
 	else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
 		return cpc_read_ffh(cpu, reg, val);
 	else
 		return acpi_os_read_memory((acpi_physical_address)reg->address,
-				val, reg->bit_width);
+				val, size);
 
-	switch (reg->bit_width) {
+	switch (size) {
 	case 8:
 		*val = readb_relaxed(vaddr);
 		break;
@@ -1029,27 +1061,41 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
 		*val = readq_relaxed(vaddr);
 		break;
 	default:
-		pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
-			 reg->bit_width, pcc_ss_id);
+		if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+			pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n",
+				size, reg->address);
+		} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+			pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
+				size, pcc_ss_id);
+		}
 		return -EFAULT;
 	}
 
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		*val = MASK_VAL_READ(reg, *val);
+
 	return 0;
 }
 
 static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 {
 	int ret_val = 0;
+	int size;
+	u64 prev_val;
 	void __iomem *vaddr = NULL;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cpc_reg *reg = &reg_res->cpc_entry.reg;
+	struct cpc_desc *cpc_desc;
+	unsigned long flags;
+
+	size = GET_BIT_WIDTH(reg);
 
-	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
-		u32 width = 8 << (reg->access_width - 1);
+	if (IS_ENABLED(CONFIG_HAS_IOPORT) &&
+	    reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
 		acpi_status status;
 
 		status = acpi_os_write_port((acpi_io_address)reg->address,
-					    (u32)val, width);
+					    (u32)val, size);
 		if (ACPI_FAILURE(status)) {
 			pr_debug("Error: Failed to write SystemIO port %llx\n",
 				 reg->address);
@@ -1057,17 +1103,52 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 		}
 
 		return 0;
-	} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
+	} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) {
+		/*
+		 * For registers in PCC space, the register size is determined
+		 * by the bit width field; the access size is used to indicate
+		 * the PCC subspace id.
+		 */
+		size = reg->bit_width;
 		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
+	}
 	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
 		vaddr = reg_res->sys_mem_vaddr;
 	else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
 		return cpc_write_ffh(cpu, reg, val);
 	else
 		return acpi_os_write_memory((acpi_physical_address)reg->address,
-				val, reg->bit_width);
+				val, size);
 
-	switch (reg->bit_width) {
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+		cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+		if (!cpc_desc) {
+			pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+			return -ENODEV;
+		}
+
+		raw_spin_lock_irqsave(&cpc_desc->rmw_lock, flags);
+		switch (size) {
+		case 8:
+			prev_val = readb_relaxed(vaddr);
+			break;
+		case 16:
+			prev_val = readw_relaxed(vaddr);
+			break;
+		case 32:
+			prev_val = readl_relaxed(vaddr);
+			break;
+		case 64:
+			prev_val = readq_relaxed(vaddr);
+			break;
+		default:
+			raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags);
+			return -EFAULT;
+		}
+		val = MASK_VAL_WRITE(reg, prev_val, val);
+	}
+
+	switch (size) {
 	case 8:
 		writeb_relaxed(val, vaddr);
 		break;
@@ -1081,52 +1162,123 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 		writeq_relaxed(val, vaddr);
 		break;
 	default:
-		pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n",
-			 reg->bit_width, pcc_ss_id);
+		if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+			pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n",
+				size, reg->address);
+		} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+			pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n",
+				size, pcc_ss_id);
+		}
 		ret_val = -EFAULT;
 		break;
 	}
 
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags);
+
 	return ret_val;
 }
 
-static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
+static int cppc_get_reg_val_in_pcc(int cpu, struct cpc_register_resource *reg, u64 *val)
 {
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret;
+
+	if (pcc_ss_id < 0) {
+		pr_debug("Invalid pcc_ss_id\n");
+		return -ENODEV;
+	}
+
+	pcc_ss_data = pcc_data[pcc_ss_id];
+
+	down_write(&pcc_ss_data->pcc_lock);
+
+	if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
+		ret = cpc_read(cpu, reg, val);
+	else
+		ret = -EIO;
+
+	up_write(&pcc_ss_data->pcc_lock);
+
+	return ret;
+}
+
+static int cppc_get_reg_val(int cpu, enum cppc_regs reg_idx, u64 *val)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
 	struct cpc_register_resource *reg;
 
+	if (val == NULL)
+		return -EINVAL;
+
 	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
 		return -ENODEV;
 	}
 
 	reg = &cpc_desc->cpc_regs[reg_idx];
 
-	if (CPC_IN_PCC(reg)) {
-		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-		struct cppc_pcc_data *pcc_ss_data = NULL;
-		int ret = 0;
-
-		if (pcc_ss_id < 0)
-			return -EIO;
+	if ((reg->type == ACPI_TYPE_INTEGER && IS_OPTIONAL_CPC_REG(reg_idx) &&
+	     !reg->cpc_entry.int_value) || (reg->type != ACPI_TYPE_INTEGER &&
+	     IS_NULL_REG(&reg->cpc_entry.reg))) {
+		pr_debug("CPC register is not supported\n");
+		return -EOPNOTSUPP;
+	}
 
-		pcc_ss_data = pcc_data[pcc_ss_id];
+	if (CPC_IN_PCC(reg))
+		return cppc_get_reg_val_in_pcc(cpu, reg, val);
 
-		down_write(&pcc_ss_data->pcc_lock);
+	return cpc_read(cpu, reg, val);
+}
 
-		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
-			cpc_read(cpunum, reg, perf);
-		else
-			ret = -EIO;
+static int cppc_set_reg_val_in_pcc(int cpu, struct cpc_register_resource *reg, u64 val)
+{
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret;
 
-		up_write(&pcc_ss_data->pcc_lock);
+	if (pcc_ss_id < 0) {
+		pr_debug("Invalid pcc_ss_id\n");
+		return -ENODEV;
+	}
 
+	ret = cpc_write(cpu, reg, val);
+	if (ret)
 		return ret;
+
+	pcc_ss_data = pcc_data[pcc_ss_id];
+
+	down_write(&pcc_ss_data->pcc_lock);
+	/* after writing CPC, transfer the ownership of PCC to platform */
+	ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
+	up_write(&pcc_ss_data->pcc_lock);
+
+	return ret;
+}
+
+static int cppc_set_reg_val(int cpu, enum cppc_regs reg_idx, u64 val)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cpc_register_resource *reg;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	reg = &cpc_desc->cpc_regs[reg_idx];
+
+	/* if a register is writeable, it must be a buffer and not null */
+	if ((reg->type != ACPI_TYPE_BUFFER) || IS_NULL_REG(&reg->cpc_entry.reg)) {
+		pr_debug("CPC register is not supported\n");
+		return -EOPNOTSUPP;
 	}
 
-	cpc_read(cpunum, reg, perf);
+	if (CPC_IN_PCC(reg))
+		return cppc_set_reg_val_in_pcc(cpu, reg, val);
 
-	return 0;
+	return cpc_write(cpu, reg, val);
 }
 
 /**
@@ -1138,7 +1290,7 @@ static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
  */
 int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
-	return cppc_get_perf(cpunum, DESIRED_PERF, desired_perf);
+	return cppc_get_reg_val(cpunum, DESIRED_PERF, desired_perf);
 }
 EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
 
@@ -1151,10 +1303,23 @@ EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
  */
 int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 {
-	return cppc_get_perf(cpunum, NOMINAL_PERF, nominal_perf);
+	return cppc_get_reg_val(cpunum, NOMINAL_PERF, nominal_perf);
 }
 
 /**
+ * cppc_get_highest_perf - Get the highest performance register value.
+ * @cpunum: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return cppc_get_reg_val(cpunum, HIGHEST_PERF, highest_perf);
+}
+EXPORT_SYMBOL_GPL(cppc_get_highest_perf);
+
+/**
  * cppc_get_epp_perf - Get the epp register value.
  * @cpunum: CPU from which to get epp preference value.
  * @epp_perf: Return address.
@@ -1163,7 +1328,7 @@ int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
  */
 int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
 {
-	return cppc_get_perf(cpunum, ENERGY_PERF, epp_perf);
+	return cppc_get_reg_val(cpunum, ENERGY_PERF, epp_perf);
 }
 EXPORT_SYMBOL_GPL(cppc_get_epp_perf);
 
@@ -1424,9 +1589,12 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 		/* after writing CPC, transfer the ownership of PCC to platform */
 		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
 		up_write(&pcc_ss_data->pcc_lock);
+	} else if (osc_cpc_flexible_adr_space_confirmed &&
+		   CPC_SUPPORTED(epp_set_reg) && CPC_IN_FFH(epp_set_reg)) {
+		ret = cpc_write(cpu, epp_set_reg, perf_ctrls->energy_perf);
 	} else {
 		ret = -ENOTSUPP;
-		pr_debug("_CPC in PCC is not supported\n");
+		pr_debug("_CPC in PCC and _CPC in FFH are not supported\n");
 	}
 
 	return ret;
@@ -1434,53 +1602,110 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 EXPORT_SYMBOL_GPL(cppc_set_epp_perf);
 
 /**
- * cppc_get_auto_sel_caps - Read autonomous selection register.
- * @cpunum : CPU from which to read register.
- * @perf_caps : struct where autonomous selection register value is updated.
+ * cppc_set_epp() - Write the EPP register.
+ * @cpu: CPU on which to write register.
+ * @epp_val: Value to write to the EPP register.
  */
-int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+int cppc_set_epp(int cpu, u64 epp_val)
 {
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
-	struct cpc_register_resource *auto_sel_reg;
-	u64  auto_sel;
+	if (epp_val > CPPC_ENERGY_PERF_MAX)
+		return -EINVAL;
 
-	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
-		return -ENODEV;
-	}
+	return cppc_set_reg_val(cpu, ENERGY_PERF, epp_val);
+}
+EXPORT_SYMBOL_GPL(cppc_set_epp);
 
-	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+/**
+ * cppc_get_auto_act_window() - Read autonomous activity window register.
+ * @cpu: CPU from which to read register.
+ * @auto_act_window: Return address.
+ *
+ * According to ACPI 6.5, s8.4.6.1.6, the value read from the autonomous
+ * activity window register consists of two parts: a 7 bits value indicate
+ * significand and a 3 bits value indicate exponent.
+ */
+int cppc_get_auto_act_window(int cpu, u64 *auto_act_window)
+{
+	unsigned int exp;
+	u64 val, sig;
+	int ret;
 
-	if (!CPC_SUPPORTED(auto_sel_reg))
-		pr_warn_once("Autonomous mode is not unsupported!\n");
+	if (auto_act_window == NULL)
+		return -EINVAL;
 
-	if (CPC_IN_PCC(auto_sel_reg)) {
-		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-		struct cppc_pcc_data *pcc_ss_data = NULL;
-		int ret = 0;
+	ret = cppc_get_reg_val(cpu, AUTO_ACT_WINDOW, &val);
+	if (ret)
+		return ret;
 
-		if (pcc_ss_id < 0)
-			return -ENODEV;
+	sig = val & CPPC_AUTO_ACT_WINDOW_MAX_SIG;
+	exp = (val >> CPPC_AUTO_ACT_WINDOW_SIG_BIT_SIZE) & CPPC_AUTO_ACT_WINDOW_MAX_EXP;
+	*auto_act_window = sig * int_pow(10, exp);
 
-		pcc_ss_data = pcc_data[pcc_ss_id];
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_auto_act_window);
 
-		down_write(&pcc_ss_data->pcc_lock);
+/**
+ * cppc_set_auto_act_window() - Write autonomous activity window register.
+ * @cpu: CPU on which to write register.
+ * @auto_act_window: usec value to write to the autonomous activity window register.
+ *
+ * According to ACPI 6.5, s8.4.6.1.6, the value to write to the autonomous
+ * activity window register consists of two parts: a 7 bits value indicate
+ * significand and a 3 bits value indicate exponent.
+ */
+int cppc_set_auto_act_window(int cpu, u64 auto_act_window)
+{
+	/* The max value to store is 1270000000 */
+	u64 max_val = CPPC_AUTO_ACT_WINDOW_MAX_SIG * int_pow(10, CPPC_AUTO_ACT_WINDOW_MAX_EXP);
+	int exp = 0;
+	u64 val;
 
-		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) {
-			cpc_read(cpunum, auto_sel_reg, &auto_sel);
-			perf_caps->auto_sel = (bool)auto_sel;
-		} else {
-			ret = -EIO;
-		}
+	if (auto_act_window > max_val)
+		return -EINVAL;
 
-		up_write(&pcc_ss_data->pcc_lock);
+	/*
+	 * The max significand is 127, when auto_act_window is larger than
+	 * 129, discard the precision of the last digit and increase the
+	 * exponent by 1.
+	 */
+	while (auto_act_window > CPPC_AUTO_ACT_WINDOW_SIG_CARRY_THRESH) {
+		auto_act_window /= 10;
+		exp += 1;
+	}
+
+	/* For 128 and 129, cut it to 127. */
+	if (auto_act_window > CPPC_AUTO_ACT_WINDOW_MAX_SIG)
+		auto_act_window = CPPC_AUTO_ACT_WINDOW_MAX_SIG;
 
+	val = (exp << CPPC_AUTO_ACT_WINDOW_SIG_BIT_SIZE) + auto_act_window;
+
+	return cppc_set_reg_val(cpu, AUTO_ACT_WINDOW, val);
+}
+EXPORT_SYMBOL_GPL(cppc_set_auto_act_window);
+
+/**
+ * cppc_get_auto_sel() - Read autonomous selection register.
+ * @cpu: CPU from which to read register.
+ * @enable: Return address.
+ */
+int cppc_get_auto_sel(int cpu, bool *enable)
+{
+	u64 auto_sel;
+	int ret;
+
+	if (enable == NULL)
+		return -EINVAL;
+
+	ret = cppc_get_reg_val(cpu, AUTO_SEL_ENABLE, &auto_sel);
+	if (ret)
 		return ret;
-	}
+
+	*enable = (bool)auto_sel;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
+EXPORT_SYMBOL_GPL(cppc_get_auto_sel);
 
 /**
  * cppc_set_auto_sel - Write autonomous selection register.
@@ -1489,43 +1714,7 @@ EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
  */
 int cppc_set_auto_sel(int cpu, bool enable)
 {
-	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
-	struct cpc_register_resource *auto_sel_reg;
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
-	struct cppc_pcc_data *pcc_ss_data = NULL;
-	int ret = -EINVAL;
-
-	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
-		return -ENODEV;
-	}
-
-	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
-
-	if (CPC_IN_PCC(auto_sel_reg)) {
-		if (pcc_ss_id < 0) {
-			pr_debug("Invalid pcc_ss_id\n");
-			return -ENODEV;
-		}
-
-		if (CPC_SUPPORTED(auto_sel_reg)) {
-			ret = cpc_write(cpu, auto_sel_reg, enable);
-			if (ret)
-				return ret;
-		}
-
-		pcc_ss_data = pcc_data[pcc_ss_id];
-
-		down_write(&pcc_ss_data->pcc_lock);
-		/* after writing CPC, transfer the ownership of PCC to platform */
-		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
-		up_write(&pcc_ss_data->pcc_lock);
-	} else {
-		ret = -ENOTSUPP;
-		pr_debug("_CPC in PCC is not supported\n");
-	}
-
-	return ret;
+	return cppc_set_reg_val(cpu, AUTO_SEL_ENABLE, enable);
 }
 EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
 
@@ -1539,38 +1728,7 @@ EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
  */
 int cppc_set_enable(int cpu, bool enable)
 {
-	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
-	struct cpc_register_resource *enable_reg;
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
-	struct cppc_pcc_data *pcc_ss_data = NULL;
-	int ret = -EINVAL;
-
-	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
-		return -EINVAL;
-	}
-
-	enable_reg = &cpc_desc->cpc_regs[ENABLE];
-
-	if (CPC_IN_PCC(enable_reg)) {
-
-		if (pcc_ss_id < 0)
-			return -EIO;
-
-		ret = cpc_write(cpu, enable_reg, enable);
-		if (ret)
-			return ret;
-
-		pcc_ss_data = pcc_data[pcc_ss_id];
-
-		down_write(&pcc_ss_data->pcc_lock);
-		/* after writing CPC, transfer the ownership of PCC to platfrom */
-		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
-		up_write(&pcc_ss_data->pcc_lock);
-		return ret;
-	}
-
-	return cpc_write(cpu, enable_reg, enable);
+	return cppc_set_reg_val(cpu, ENABLE, enable);
 }
 EXPORT_SYMBOL_GPL(cppc_set_enable);
 
@@ -1718,7 +1876,7 @@ EXPORT_SYMBOL_GPL(cppc_set_perf);
  * If desired_reg is in the SystemMemory or SystemIo ACPI address space,
  * then assume there is no latency.
  */
-unsigned int cppc_get_transition_latency(int cpu_num)
+int cppc_get_transition_latency(int cpu_num)
 {
 	/*
 	 * Expected transition latency is based on the PCCT timing values
@@ -1731,32 +1889,143 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	 *              completion of a command before issuing the next command,
 	 *              in microseconds.
 	 */
-	unsigned int latency_ns = 0;
 	struct cpc_desc *cpc_desc;
 	struct cpc_register_resource *desired_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu_num);
 	struct cppc_pcc_data *pcc_ss_data;
+	int latency_ns = 0;
 
 	cpc_desc = per_cpu(cpc_desc_ptr, cpu_num);
 	if (!cpc_desc)
-		return CPUFREQ_ETERNAL;
+		return -ENODATA;
 
 	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
 	if (CPC_IN_SYSTEM_MEMORY(desired_reg) || CPC_IN_SYSTEM_IO(desired_reg))
 		return 0;
-	else if (!CPC_IN_PCC(desired_reg))
-		return CPUFREQ_ETERNAL;
 
-	if (pcc_ss_id < 0)
-		return CPUFREQ_ETERNAL;
+	if (!CPC_IN_PCC(desired_reg) || pcc_ss_id < 0)
+		return -ENODATA;
 
 	pcc_ss_data = pcc_data[pcc_ss_id];
 	if (pcc_ss_data->pcc_mpar)
 		latency_ns = 60 * (1000 * 1000 * 1000 / pcc_ss_data->pcc_mpar);
 
-	latency_ns = max(latency_ns, pcc_ss_data->pcc_nominal * 1000);
-	latency_ns = max(latency_ns, pcc_ss_data->pcc_mrtt * 1000);
+	latency_ns = max_t(int, latency_ns, pcc_ss_data->pcc_nominal * 1000);
+	latency_ns = max_t(int, latency_ns, pcc_ss_data->pcc_mrtt * 1000);
 
 	return latency_ns;
 }
 EXPORT_SYMBOL_GPL(cppc_get_transition_latency);
+
+/* Minimum struct length needed for the DMI processor entry we want */
+#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
+
+/* Offset in the DMI processor structure for the max frequency */
+#define DMI_PROCESSOR_MAX_SPEED		0x14
+
+/* Callback function used to retrieve the max frequency from DMI */
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+	const u8 *dmi_data = (const u8 *)dm;
+	u16 *mhz = (u16 *)private;
+
+	if (dm->type == DMI_ENTRY_PROCESSOR &&
+	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
+		u16 val = (u16)get_unaligned((const u16 *)
+				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
+		*mhz = umax(val, *mhz);
+	}
+}
+
+/* Look up the max frequency in DMI */
+static u64 cppc_get_dmi_max_khz(void)
+{
+	u16 mhz = 0;
+
+	dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+	/*
+	 * Real stupid fallback value, just in case there is no
+	 * actual value set.
+	 */
+	mhz = mhz ? mhz : 1;
+
+	return KHZ_PER_MHZ * mhz;
+}
+
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ *  - (Low perf, Low freq)
+ *  - (Nominal perf, Nominal freq)
+ */
+unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		/* Avoid special case when nominal_freq is equal to lowest_freq */
+		if (caps->lowest_freq == caps->nominal_freq) {
+			mul = caps->nominal_freq;
+			div = caps->nominal_perf;
+		} else {
+			mul = caps->nominal_freq - caps->lowest_freq;
+			div = caps->nominal_perf - caps->lowest_perf;
+		}
+		mul *= KHZ_PER_MHZ;
+		offset = caps->nominal_freq * KHZ_PER_MHZ -
+			 div64_u64(caps->nominal_perf * mul, div);
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = max_khz;
+		div = caps->highest_perf;
+	}
+
+	retval = offset + div64_u64(perf * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_perf_to_khz);
+
+unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		/* Avoid special case when nominal_freq is equal to lowest_freq */
+		if (caps->lowest_freq == caps->nominal_freq) {
+			mul = caps->nominal_perf;
+			div = caps->nominal_freq;
+		} else {
+			mul = caps->nominal_perf - caps->lowest_perf;
+			div = caps->nominal_freq - caps->lowest_freq;
+		}
+		/*
+		 * We don't need to convert to kHz for computing offset and can
+		 * directly use nominal_freq and lowest_freq as the div64_u64
+		 * will remove the frequency unit.
+		 */
+		offset = caps->nominal_perf -
+			 div64_u64(caps->nominal_freq * mul, div);
+		/* But we need it for computing the perf level. */
+		div *= KHZ_PER_MHZ;
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = caps->highest_perf;
+		div = max_khz;
+	}
+
+	retval = offset + div64_u64(freq * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_khz_to_perf);
diff --git a/drivers/acpi/custom_method.c b/drivers/acpi/custom_method.c
deleted file mode 100644
index d39a9b474727..000000000000
--- a/drivers/acpi/custom_method.c
+++ /dev/null
@@ -1,103 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * custom_method.c - debugfs interface for customizing ACPI control method
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/acpi.h>
-#include <linux/security.h>
-
-#include "internal.h"
-
-MODULE_LICENSE("GPL");
-
-static struct dentry *cm_dentry;
-
-/* /sys/kernel/debug/acpi/custom_method */
-
-static ssize_t cm_write(struct file *file, const char __user *user_buf,
-			size_t count, loff_t *ppos)
-{
-	static char *buf;
-	static u32 max_size;
-	static u32 uncopied_bytes;
-
-	struct acpi_table_header table;
-	acpi_status status;
-	int ret;
-
-	ret = security_locked_down(LOCKDOWN_ACPI_TABLES);
-	if (ret)
-		return ret;
-
-	if (!(*ppos)) {
-		/* parse the table header to get the table length */
-		if (count <= sizeof(struct acpi_table_header))
-			return -EINVAL;
-		if (copy_from_user(&table, user_buf,
-				   sizeof(struct acpi_table_header)))
-			return -EFAULT;
-		uncopied_bytes = max_size = table.length;
-		/* make sure the buf is not allocated */
-		kfree(buf);
-		buf = kzalloc(max_size, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-	}
-
-	if (buf == NULL)
-		return -EINVAL;
-
-	if ((*ppos > max_size) ||
-	    (*ppos + count > max_size) ||
-	    (*ppos + count < count) ||
-	    (count > uncopied_bytes)) {
-		kfree(buf);
-		buf = NULL;
-		return -EINVAL;
-	}
-
-	if (copy_from_user(buf + (*ppos), user_buf, count)) {
-		kfree(buf);
-		buf = NULL;
-		return -EFAULT;
-	}
-
-	uncopied_bytes -= count;
-	*ppos += count;
-
-	if (!uncopied_bytes) {
-		status = acpi_install_method(buf);
-		kfree(buf);
-		buf = NULL;
-		if (ACPI_FAILURE(status))
-			return -EINVAL;
-		add_taint(TAINT_OVERRIDDEN_ACPI_TABLE, LOCKDEP_NOW_UNRELIABLE);
-	}
-
-	return count;
-}
-
-static const struct file_operations cm_fops = {
-	.write = cm_write,
-	.llseek = default_llseek,
-};
-
-static int __init acpi_custom_method_init(void)
-{
-	cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
-					acpi_debugfs_dir, NULL, &cm_fops);
-	return 0;
-}
-
-static void __exit acpi_custom_method_exit(void)
-{
-	debugfs_remove(cm_dentry);
-}
-
-module_init(acpi_custom_method_init);
-module_exit(acpi_custom_method_exit);
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f007116a8427..4e0583274b8f 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -397,6 +397,19 @@ void acpi_device_fix_up_power_extended(struct acpi_device *adev)
 }
 EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_extended);
 
+/**
+ * acpi_device_fix_up_power_children - Force a device's children into D0.
+ * @adev: Parent device object whose children's power state is to be fixed up.
+ *
+ * Call acpi_device_fix_up_power() for @adev's children so long as they
+ * are reported as present and enabled.
+ */
+void acpi_device_fix_up_power_children(struct acpi_device *adev)
+{
+	acpi_dev_for_each_child(adev, fix_up_power_if_applicable, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_children);
+
 int acpi_device_update_power(struct acpi_device *device, int *state_p)
 {
 	int state;
@@ -1106,6 +1119,8 @@ int acpi_subsys_prepare(struct device *dev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(dev);
 
+	dev_pm_set_strict_midlayer(dev, true);
+
 	if (dev->driver && dev->driver->pm && dev->driver->pm->prepare) {
 		int ret = dev->driver->pm->prepare(dev);
 
@@ -1134,6 +1149,8 @@ void acpi_subsys_complete(struct device *dev)
 	 */
 	if (pm_runtime_suspended(dev) && pm_resume_via_firmware())
 		pm_request_resume(dev);
+
+	dev_pm_set_strict_midlayer(dev, false);
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_complete);
 
@@ -1148,7 +1165,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_complete);
  */
 int acpi_subsys_suspend(struct device *dev)
 {
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
+	if (!dev_pm_smart_suspend(dev) ||
 	    acpi_dev_needs_resume(dev, ACPI_COMPANION(dev)))
 		pm_runtime_resume(dev);
 
@@ -1307,7 +1324,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_restore_early);
  */
 int acpi_subsys_poweroff(struct device *dev)
 {
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
+	if (!dev_pm_smart_suspend(dev) ||
 	    acpi_dev_needs_resume(dev, ACPI_COMPANION(dev)))
 		pm_runtime_resume(dev);
 
@@ -1349,6 +1366,8 @@ static int acpi_subsys_poweroff_noirq(struct device *dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+static void acpi_dev_pm_detach(struct device *dev, bool power_off);
+
 static struct dev_pm_domain acpi_general_pm_domain = {
 	.ops = {
 		.runtime_suspend = acpi_subsys_runtime_suspend,
@@ -1369,6 +1388,7 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 		.restore_early = acpi_subsys_restore_early,
 #endif
 	},
+	.detach = acpi_dev_pm_detach,
 };
 
 /**
@@ -1452,7 +1472,6 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 		acpi_device_wakeup_disable(adev);
 	}
 
-	dev->pm_domain->detach = acpi_dev_pm_detach;
 	return 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c
index 23373faa35ec..cd199fbe4dc9 100644
--- a/drivers/acpi/device_sysfs.c
+++ b/drivers/acpi/device_sysfs.c
@@ -439,23 +439,33 @@ static ssize_t description_show(struct device *dev,
 				char *buf)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *str_obj;
+	acpi_status status;
 	int result;
 
-	if (acpi_dev->pnp.str_obj == NULL)
-		return 0;
+	status = acpi_evaluate_object_typed(acpi_dev->handle, "_STR",
+					    NULL, &buffer,
+					    ACPI_TYPE_BUFFER);
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	str_obj = buffer.pointer;
 
 	/*
 	 * The _STR object contains a Unicode identifier for a device.
 	 * We need to convert to utf-8 so it can be displayed.
 	 */
 	result = utf16s_to_utf8s(
-		(wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer,
-		acpi_dev->pnp.str_obj->buffer.length,
+		(wchar_t *)str_obj->buffer.pointer,
+		str_obj->buffer.length,
 		UTF16_LITTLE_ENDIAN, buf,
 		PAGE_SIZE - 1);
 
 	buf[result++] = '\n';
 
+	ACPI_FREE(str_obj);
+
 	return result;
 }
 static DEVICE_ATTR_RO(description);
@@ -507,96 +517,97 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(status);
 
-/**
- * acpi_device_setup_files - Create sysfs attributes of an ACPI device.
- * @dev: ACPI device object.
- */
-int acpi_device_setup_files(struct acpi_device *dev)
-{
-	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
-	int result = 0;
+static struct attribute *acpi_attrs[] = {
+	&dev_attr_path.attr,
+	&dev_attr_hid.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_description.attr,
+	&dev_attr_adr.attr,
+	&dev_attr_uid.attr,
+	&dev_attr_sun.attr,
+	&dev_attr_hrv.attr,
+	&dev_attr_status.attr,
+	&dev_attr_eject.attr,
+	&dev_attr_power_state.attr,
+	&dev_attr_real_power_state.attr,
+	NULL
+};
 
+static bool acpi_show_attr(struct acpi_device *dev, const struct device_attribute *attr)
+{
 	/*
 	 * Devices gotten from FADT don't have a "path" attribute
 	 */
-	if (dev->handle) {
-		result = device_create_file(&dev->dev, &dev_attr_path);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_path)
+		return dev->handle;
 
-	if (!list_empty(&dev->pnp.ids)) {
-		result = device_create_file(&dev->dev, &dev_attr_hid);
-		if (result)
-			goto end;
+	if (attr == &dev_attr_hid || attr == &dev_attr_modalias)
+		return !list_empty(&dev->pnp.ids);
 
-		result = device_create_file(&dev->dev, &dev_attr_modalias);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_description)
+		return acpi_has_method(dev->handle, "_STR");
 
-	/*
-	 * If device has _STR, 'description' file is created
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		status = acpi_evaluate_object(dev->handle, "_STR",
-					NULL, &buffer);
-		if (ACPI_FAILURE(status))
-			buffer.pointer = NULL;
-		dev->pnp.str_obj = buffer.pointer;
-		result = device_create_file(&dev->dev, &dev_attr_description);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_adr)
+		return dev->pnp.type.bus_address;
 
-	if (dev->pnp.type.bus_address)
-		result = device_create_file(&dev->dev, &dev_attr_adr);
-	if (acpi_device_uid(dev))
-		result = device_create_file(&dev->dev, &dev_attr_uid);
+	if (attr == &dev_attr_uid)
+		return acpi_device_uid(dev);
 
-	if (acpi_has_method(dev->handle, "_SUN")) {
-		result = device_create_file(&dev->dev, &dev_attr_sun);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_sun)
+		return acpi_has_method(dev->handle, "_SUN");
 
-	if (acpi_has_method(dev->handle, "_HRV")) {
-		result = device_create_file(&dev->dev, &dev_attr_hrv);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_hrv)
+		return acpi_has_method(dev->handle, "_HRV");
 
-	if (acpi_has_method(dev->handle, "_STA")) {
-		result = device_create_file(&dev->dev, &dev_attr_status);
-		if (result)
-			goto end;
-	}
+	if (attr == &dev_attr_status)
+		return acpi_has_method(dev->handle, "_STA");
 
 	/*
 	 * If device has _EJ0, 'eject' file is created that is used to trigger
 	 * hot-removal function from userland.
 	 */
-	if (acpi_has_method(dev->handle, "_EJ0")) {
-		result = device_create_file(&dev->dev, &dev_attr_eject);
-		if (result)
-			return result;
-	}
+	if (attr == &dev_attr_eject)
+		return acpi_has_method(dev->handle, "_EJ0");
 
-	if (dev->flags.power_manageable) {
-		result = device_create_file(&dev->dev, &dev_attr_power_state);
-		if (result)
-			return result;
+	if (attr == &dev_attr_power_state)
+		return dev->flags.power_manageable;
 
-		if (dev->power.flags.power_resources)
-			result = device_create_file(&dev->dev,
-						    &dev_attr_real_power_state);
-	}
+	if (attr == &dev_attr_real_power_state)
+		return dev->flags.power_manageable && dev->power.flags.power_resources;
 
-	acpi_expose_nondev_subnodes(&dev->dev.kobj, &dev->data);
+	dev_warn_once(&dev->dev, "Unexpected attribute: %s\n", attr->attr.name);
+	return false;
+}
 
-end:
-	return result;
+static umode_t acpi_attr_is_visible(struct kobject *kobj,
+				    struct attribute *attr,
+				    int attrno)
+{
+	struct acpi_device *dev = to_acpi_device(kobj_to_dev(kobj));
+
+	if (acpi_show_attr(dev, container_of(attr, struct device_attribute, attr)))
+		return attr->mode;
+	else
+		return 0;
+}
+
+static const struct attribute_group acpi_group = {
+	.attrs = acpi_attrs,
+	.is_visible = acpi_attr_is_visible,
+};
+
+const struct attribute_group *acpi_groups[] = {
+	&acpi_group,
+	NULL
+};
+
+/**
+ * acpi_device_setup_files - Create sysfs attributes of an ACPI device.
+ * @dev: ACPI device object.
+ */
+void acpi_device_setup_files(struct acpi_device *dev)
+{
+	acpi_expose_nondev_subnodes(&dev->dev.kobj, &dev->data);
 }
 
 /**
@@ -606,41 +617,4 @@ end:
 void acpi_device_remove_files(struct acpi_device *dev)
 {
 	acpi_hide_nondev_subnodes(&dev->data);
-
-	if (dev->flags.power_manageable) {
-		device_remove_file(&dev->dev, &dev_attr_power_state);
-		if (dev->power.flags.power_resources)
-			device_remove_file(&dev->dev,
-					   &dev_attr_real_power_state);
-	}
-
-	/*
-	 * If device has _STR, remove 'description' file
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		kfree(dev->pnp.str_obj);
-		device_remove_file(&dev->dev, &dev_attr_description);
-	}
-	/*
-	 * If device has _EJ0, remove 'eject' file.
-	 */
-	if (acpi_has_method(dev->handle, "_EJ0"))
-		device_remove_file(&dev->dev, &dev_attr_eject);
-
-	if (acpi_has_method(dev->handle, "_SUN"))
-		device_remove_file(&dev->dev, &dev_attr_sun);
-
-	if (acpi_has_method(dev->handle, "_HRV"))
-		device_remove_file(&dev->dev, &dev_attr_hrv);
-
-	if (acpi_device_uid(dev))
-		device_remove_file(&dev->dev, &dev_attr_uid);
-	if (dev->pnp.type.bus_address)
-		device_remove_file(&dev->dev, &dev_attr_adr);
-	device_remove_file(&dev->dev, &dev_attr_modalias);
-	device_remove_file(&dev->dev, &dev_attr_hid);
-	if (acpi_has_method(dev->handle, "_STA"))
-		device_remove_file(&dev->dev, &dev_attr_status);
-	if (dev->handle)
-		device_remove_file(&dev->dev, &dev_attr_path);
 }
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index a89bdbe00184..34affbda295e 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -88,43 +88,29 @@ static void dock_hotplug_event(struct dock_dependent_device *dd, u32 event,
 			       enum dock_callback_type cb_type)
 {
 	struct acpi_device *adev = dd->adev;
+	acpi_hp_fixup fixup = NULL;
+	acpi_hp_uevent uevent = NULL;
+	acpi_hp_notify notify = NULL;
 
 	acpi_lock_hp_context();
 
-	if (!adev->hp)
-		goto out;
-
-	if (cb_type == DOCK_CALL_FIXUP) {
-		void (*fixup)(struct acpi_device *);
-
-		fixup = adev->hp->fixup;
-		if (fixup) {
-			acpi_unlock_hp_context();
-			fixup(adev);
-			return;
-		}
-	} else if (cb_type == DOCK_CALL_UEVENT) {
-		void (*uevent)(struct acpi_device *, u32);
-
-		uevent = adev->hp->uevent;
-		if (uevent) {
-			acpi_unlock_hp_context();
-			uevent(adev, event);
-			return;
-		}
-	} else {
-		int (*notify)(struct acpi_device *, u32);
-
-		notify = adev->hp->notify;
-		if (notify) {
-			acpi_unlock_hp_context();
-			notify(adev, event);
-			return;
-		}
+	if (adev->hp) {
+		if (cb_type == DOCK_CALL_FIXUP)
+			fixup = adev->hp->fixup;
+		else if (cb_type == DOCK_CALL_UEVENT)
+			uevent = adev->hp->uevent;
+		else
+			notify = adev->hp->notify;
 	}
 
- out:
 	acpi_unlock_hp_context();
+
+	if (fixup)
+		fixup(adev);
+	else if (uevent)
+		uevent(adev, event);
+	else if (notify)
+		notify(adev, event);
 }
 
 static struct dock_station *find_dock_station(acpi_handle handle)
@@ -380,6 +366,8 @@ static int dock_in_progress(struct dock_station *ds)
 
 /**
  * handle_eject_request - handle an undock request checking for error conditions
+ * @ds: The dock station to undock.
+ * @event: The ACPI event number associated with the undock request.
  *
  * Check to make sure the dock device is still present, then undock and
  * hotremove all the devices that may need removing.
diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c
index 4919e7abe93f..952216c67d58 100644
--- a/drivers/acpi/dptf/dptf_pch_fivr.c
+++ b/drivers/acpi/dptf/dptf_pch_fivr.c
@@ -141,18 +141,18 @@ static int pch_fivr_add(struct platform_device *pdev)
 	return 0;
 }
 
-static int pch_fivr_remove(struct platform_device *pdev)
+static void pch_fivr_remove(struct platform_device *pdev)
 {
 	sysfs_remove_group(&pdev->dev.kobj, &pch_fivr_attribute_group);
-
-	return 0;
 }
 
 static const struct acpi_device_id pch_fivr_device_ids[] = {
 	{"INTC1045", 0},
 	{"INTC1049", 0},
 	{"INTC1064", 0},
+	{"INTC106B", 0},
 	{"INTC10A3", 0},
+	{"INTC10D7", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids);
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index 86561eda939f..776914f31b9e 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -209,7 +209,7 @@ static int dptf_power_add(struct platform_device *pdev)
 	return 0;
 }
 
-static int dptf_power_remove(struct platform_device *pdev)
+static void dptf_power_remove(struct platform_device *pdev)
 {
 	struct acpi_device *acpi_dev = platform_get_drvdata(pdev);
 
@@ -221,8 +221,6 @@ static int dptf_power_remove(struct platform_device *pdev)
 		sysfs_remove_group(&pdev->dev.kobj, &dptf_battery_attribute_group);
 	else
 		sysfs_remove_group(&pdev->dev.kobj, &dptf_power_attribute_group);
-
-	return 0;
 }
 
 static const struct acpi_device_id int3407_device_ids[] = {
@@ -234,8 +232,14 @@ static const struct acpi_device_id int3407_device_ids[] = {
 	{"INTC1061", 0},
 	{"INTC1065", 0},
 	{"INTC1066", 0},
+	{"INTC106C", 0},
+	{"INTC106D", 0},
 	{"INTC10A4", 0},
 	{"INTC10A5", 0},
+	{"INTC10D8", 0},
+	{"INTC10D9", 0},
+	{"INTC1100", 0},
+	{"INTC1101", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index b7113fa92fa6..a222df059a16 100644
--- a/drivers/acpi/dptf/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
@@ -43,12 +43,31 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = {
 	{"INTC1064"},
 	{"INTC1065"},
 	{"INTC1066"},
+	{"INTC1068"},
+	{"INTC1069"},
+	{"INTC106A"},
+	{"INTC106B"},
+	{"INTC106C"},
+	{"INTC106D"},
 	{"INTC10A0"},
 	{"INTC10A1"},
 	{"INTC10A2"},
 	{"INTC10A3"},
 	{"INTC10A4"},
 	{"INTC10A5"},
+	{"INTC10D4"},
+	{"INTC10D5"},
+	{"INTC10D6"},
+	{"INTC10D7"},
+	{"INTC10D8"},
+	{"INTC10D9"},
+	{"INTC10FC"},
+	{"INTC10FD"},
+	{"INTC10FE"},
+	{"INTC10FF"},
+	{"INTC1100"},
+	{"INTC1101"},
+	{"INTC1102"},
 	{""},
 };
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index a59c11df7375..7855bbf752b1 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -23,8 +23,10 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
@@ -783,6 +785,9 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	unsigned long tmp;
 	int ret = 0;
 
+	if (t->rdata)
+		memset(t->rdata, 0, t->rlen);
+
 	/* start transaction */
 	spin_lock_irqsave(&ec->lock, tmp);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */
@@ -819,8 +824,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 
 	if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata))
 		return -EINVAL;
-	if (t->rdata)
-		memset(t->rdata, 0, t->rlen);
 
 	mutex_lock(&ec->mutex);
 	if (ec->global_lock) {
@@ -847,7 +850,7 @@ static int acpi_ec_burst_enable(struct acpi_ec *ec)
 				.wdata = NULL, .rdata = &d,
 				.wlen = 0, .rlen = 1};
 
-	return acpi_ec_transaction(ec, &t);
+	return acpi_ec_transaction_unlocked(ec, &t);
 }
 
 static int acpi_ec_burst_disable(struct acpi_ec *ec)
@@ -857,7 +860,7 @@ static int acpi_ec_burst_disable(struct acpi_ec *ec)
 				.wlen = 0, .rlen = 0};
 
 	return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ?
-				acpi_ec_transaction(ec, &t) : 0;
+				acpi_ec_transaction_unlocked(ec, &t) : 0;
 }
 
 static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data)
@@ -873,6 +876,19 @@ static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data)
 	return result;
 }
 
+static int acpi_ec_read_unlocked(struct acpi_ec *ec, u8 address, u8 *data)
+{
+	int result;
+	u8 d;
+	struct transaction t = {.command = ACPI_EC_COMMAND_READ,
+				.wdata = &address, .rdata = &d,
+				.wlen = 1, .rlen = 1};
+
+	result = acpi_ec_transaction_unlocked(ec, &t);
+	*data = d;
+	return result;
+}
+
 static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data)
 {
 	u8 wdata[2] = { address, data };
@@ -883,6 +899,16 @@ static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data)
 	return acpi_ec_transaction(ec, &t);
 }
 
+static int acpi_ec_write_unlocked(struct acpi_ec *ec, u8 address, u8 data)
+{
+	u8 wdata[2] = { address, data };
+	struct transaction t = {.command = ACPI_EC_COMMAND_WRITE,
+				.wdata = wdata, .rdata = NULL,
+				.wlen = 2, .rlen = 0};
+
+	return acpi_ec_transaction_unlocked(ec, &t);
+}
+
 int ec_read(u8 addr, u8 *val)
 {
 	int err;
@@ -1323,6 +1349,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	struct acpi_ec *ec = handler_context;
 	int result = 0, i, bytes = bits / 8;
 	u8 *value = (u8 *)value64;
+	u32 glk;
 
 	if ((address > 0xFF) || !value || !handler_context)
 		return AE_BAD_PARAMETER;
@@ -1330,17 +1357,38 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (function != ACPI_READ && function != ACPI_WRITE)
 		return AE_BAD_PARAMETER;
 
+	mutex_lock(&ec->mutex);
+
+	if (ec->global_lock) {
+		acpi_status status;
+
+		status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
+		if (ACPI_FAILURE(status)) {
+			result = -ENODEV;
+			goto unlock;
+		}
+	}
+
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);
 
-	for (i = 0; i < bytes; ++i, ++address, ++value)
+	for (i = 0; i < bytes; ++i, ++address, ++value) {
 		result = (function == ACPI_READ) ?
-			acpi_ec_read(ec, address, value) :
-			acpi_ec_write(ec, address, *value);
+			acpi_ec_read_unlocked(ec, address, value) :
+			acpi_ec_write_unlocked(ec, address, *value);
+		if (result < 0)
+			break;
+	}
 
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
 
+	if (ec->global_lock)
+		acpi_release_global_lock(glk);
+
+unlock:
+	mutex_unlock(&ec->mutex);
+
 	switch (result) {
 	case -EINVAL:
 		return AE_BAD_PARAMETER;
@@ -1348,8 +1396,10 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 		return AE_NOT_FOUND;
 	case -ETIME:
 		return AE_TIME;
-	default:
+	case 0:
 		return AE_OK;
+	default:
+		return AE_ERROR;
 	}
 }
 
@@ -1458,8 +1508,8 @@ static bool install_gpe_event_handler(struct acpi_ec *ec)
 
 static bool install_gpio_irq_event_handler(struct acpi_ec *ec)
 {
-	return request_irq(ec->irq, acpi_ec_irq_handler, IRQF_SHARED,
-			   "ACPI EC", ec) >= 0;
+	return request_threaded_irq(ec->irq, NULL, acpi_ec_irq_handler,
+				    IRQF_SHARED | IRQF_ONESHOT, "ACPI EC", ec) >= 0;
 }
 
 /**
@@ -1487,8 +1537,10 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
 	acpi_ec_start(ec, false);
 
 	if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
+		acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
+
 		acpi_ec_enter_noirq(ec);
-		status = acpi_install_address_space_handler_no_reg(ec->handle,
+		status = acpi_install_address_space_handler_no_reg(scope_handle,
 								   ACPI_ADR_SPACE_EC,
 								   &acpi_ec_space_handler,
 								   NULL, ec);
@@ -1497,11 +1549,10 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
 			return -ENODEV;
 		}
 		set_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags);
-		ec->address_space_handler_holder = ec->handle;
 	}
 
 	if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) {
-		acpi_execute_reg_methods(ec->handle, ACPI_ADR_SPACE_EC);
+		acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC);
 		set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags);
 	}
 
@@ -1553,10 +1604,13 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
 
 static void ec_remove_handlers(struct acpi_ec *ec)
 {
+	acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
+
 	if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
 		if (ACPI_FAILURE(acpi_remove_address_space_handler(
-					ec->address_space_handler_holder,
-					ACPI_ADR_SPACE_EC, &acpi_ec_space_handler)))
+						scope_handle,
+						ACPI_ADR_SPACE_EC,
+						&acpi_ec_space_handler)))
 			pr_err("failed to remove space handler\n");
 		clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags);
 	}
@@ -1595,14 +1649,18 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca
 {
 	int ret;
 
-	ret = ec_install_handlers(ec, device, call_reg);
-	if (ret)
-		return ret;
-
 	/* First EC capable of handling transactions */
 	if (!first_ec)
 		first_ec = ec;
 
+	ret = ec_install_handlers(ec, device, call_reg);
+	if (ret) {
+		if (ec == first_ec)
+			first_ec = NULL;
+
+		return ret;
+	}
+
 	pr_info("EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n", ec->command_addr,
 		ec->data_addr);
 
@@ -1621,8 +1679,8 @@ static int acpi_ec_add(struct acpi_device *device)
 	struct acpi_ec *ec;
 	int ret;
 
-	strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_EC_CLASS);
+	strscpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_EC_CLASS);
 
 	if (boot_ec && (boot_ec->handle == device->handle ||
 	    !strcmp(acpi_device_hid(device), ACPI_ECDT_HID))) {
@@ -1709,6 +1767,12 @@ static void acpi_ec_remove(struct acpi_device *device)
 	}
 }
 
+void acpi_ec_register_opregions(struct acpi_device *adev)
+{
+	if (first_ec && first_ec->handle != adev->handle)
+		acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC);
+}
+
 static acpi_status
 ec_parse_io_ports(struct acpi_resource *resource, void *context)
 {
@@ -1969,6 +2033,25 @@ void __init acpi_ec_ecdt_probe(void)
 		goto out;
 	}
 
+	if (!strlen(ecdt_ptr->id)) {
+		/*
+		 * The ECDT table on some MSI notebooks contains invalid data, together
+		 * with an empty ID string ("").
+		 *
+		 * Section 5.2.15 of the ACPI specification requires the ID string to be
+		 * a "fully qualified reference to the (...) embedded controller device",
+		 * so this string always has to start with a backslash.
+		 *
+		 * However some ThinkBook machines have a ECDT table with a valid EC
+		 * description but an invalid ID string ("_SB.PC00.LPCB.EC0").
+		 *
+		 * Because of this we only check if the ID string is empty in order to
+		 * avoid the obvious cases.
+		 */
+		pr_err(FW_BUG "Ignoring ECDT due to empty ID string\n");
+		goto out;
+	}
+
 	ec = acpi_ec_alloc();
 	if (!ec)
 		goto out;
@@ -2239,6 +2322,40 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"),
 		},
 	},
+	/*
+	 * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC
+	 * https://gitlab.freedesktop.org/drm/amd/-/issues/3929
+	 */
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83L3"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83N6"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
+		}
+	},
+	{
+		// TUXEDO InfinityBook Pro AMD Gen9
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GXxHRXx"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index d199a19bb292..96a9aaaaf9f7 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -28,8 +28,8 @@ int acpi_notifier_call_chain(struct acpi_device *dev, u32 type, u32 data)
 {
 	struct acpi_bus_event event;
 
-	strcpy(event.device_class, dev->pnp.device_class);
-	strcpy(event.bus_id, dev->pnp.bus_id);
+	strscpy(event.device_class, dev->pnp.device_class);
+	strscpy(event.bus_id, dev->pnp.bus_id);
 	event.type = type;
 	event.data = data;
 	return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event)
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index fe6b6792c8bb..5c35cbc7f6ff 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -173,10 +173,9 @@ static void ged_shutdown(struct platform_device *pdev)
 	}
 }
 
-static int ged_remove(struct platform_device *pdev)
+static void ged_remove(struct platform_device *pdev)
 {
 	ged_shutdown(pdev);
-	return 0;
 }
 
 static const struct acpi_device_id ged_acpi_ids[] = {
diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h
index e7b4b4e4a55e..8a28a72a7c6a 100644
--- a/drivers/acpi/fan.h
+++ b/drivers/acpi/fan.h
@@ -10,12 +10,17 @@
 #ifndef _ACPI_FAN_H_
 #define _ACPI_FAN_H_
 
+#include <linux/kconfig.h>
+
 #define ACPI_FAN_DEVICE_IDS	\
 	{"INT3404", }, /* Fan */ \
 	{"INTC1044", }, /* Fan for Tiger Lake generation */ \
 	{"INTC1048", }, /* Fan for Alder Lake generation */ \
 	{"INTC1063", }, /* Fan for Meteor Lake generation */ \
+	{"INTC106A", }, /* Fan for Lunar Lake generation */ \
 	{"INTC10A2", }, /* Fan for Raptor Lake generation */ \
+	{"INTC10D6", }, /* Fan for Panther Lake generation */ \
+	{"INTC10FE", }, /* Fan for Wildcat Lake generation */ \
 	{"PNP0C0B", } /* Generic ACPI fan */
 
 #define ACPI_FPS_NAME_LEN	20
@@ -45,6 +50,7 @@ struct acpi_fan_fst {
 
 struct acpi_fan {
 	bool acpi4;
+	bool has_fst;
 	struct acpi_fan_fif fif;
 	struct acpi_fan_fps *fps;
 	int fps_count;
@@ -56,4 +62,11 @@ struct acpi_fan {
 int acpi_fan_get_fst(struct acpi_device *device, struct acpi_fan_fst *fst);
 int acpi_fan_create_attributes(struct acpi_device *device);
 void acpi_fan_delete_attributes(struct acpi_device *device);
+
+#if IS_REACHABLE(CONFIG_HWMON)
+int devm_acpi_fan_create_hwmon(struct acpi_device *device);
+#else
+static inline int devm_acpi_fan_create_hwmon(struct acpi_device *device) { return 0; };
+#endif
+
 #endif
diff --git a/drivers/acpi/fan_attr.c b/drivers/acpi/fan_attr.c
index f4f6e2381f1d..c1afb7b5ed3d 100644
--- a/drivers/acpi/fan_attr.c
+++ b/drivers/acpi/fan_attr.c
@@ -22,9 +22,9 @@ static ssize_t show_state(struct device *dev, struct device_attribute *attr, cha
 	int count;
 
 	if (fps->control == 0xFFFFFFFF || fps->control > 100)
-		count = scnprintf(buf, PAGE_SIZE, "not-defined:");
+		count = sysfs_emit(buf, "not-defined:");
 	else
-		count = scnprintf(buf, PAGE_SIZE, "%lld:", fps->control);
+		count = sysfs_emit(buf, "%lld:", fps->control);
 
 	if (fps->trip_point == 0xFFFFFFFF || fps->trip_point > 9)
 		count += sysfs_emit_at(buf, count, "not-defined:");
@@ -59,7 +59,7 @@ static ssize_t show_fan_speed(struct device *dev, struct device_attribute *attr,
 	if (status)
 		return status;
 
-	return sprintf(buf, "%lld\n", fst.speed);
+	return sysfs_emit(buf, "%lld\n", fst.speed);
 }
 
 static ssize_t show_fine_grain_control(struct device *dev, struct device_attribute *attr, char *buf)
@@ -67,7 +67,7 @@ static ssize_t show_fine_grain_control(struct device *dev, struct device_attribu
 	struct acpi_device *acpi_dev = container_of(dev, struct acpi_device, dev);
 	struct acpi_fan *fan = acpi_driver_data(acpi_dev);
 
-	return sprintf(buf, "%d\n", fan->fif.fine_grain_ctrl);
+	return sysfs_emit(buf, "%d\n", fan->fif.fine_grain_ctrl);
 }
 
 int acpi_fan_create_attributes(struct acpi_device *device)
@@ -75,15 +75,6 @@ int acpi_fan_create_attributes(struct acpi_device *device)
 	struct acpi_fan *fan = acpi_driver_data(device);
 	int i, status;
 
-	sysfs_attr_init(&fan->fine_grain_control.attr);
-	fan->fine_grain_control.show = show_fine_grain_control;
-	fan->fine_grain_control.store = NULL;
-	fan->fine_grain_control.attr.name = "fine_grain_control";
-	fan->fine_grain_control.attr.mode = 0444;
-	status = sysfs_create_file(&device->dev.kobj, &fan->fine_grain_control.attr);
-	if (status)
-		return status;
-
 	/* _FST is present if we are here */
 	sysfs_attr_init(&fan->fst_speed.attr);
 	fan->fst_speed.show = show_fan_speed;
@@ -92,7 +83,19 @@ int acpi_fan_create_attributes(struct acpi_device *device)
 	fan->fst_speed.attr.mode = 0444;
 	status = sysfs_create_file(&device->dev.kobj, &fan->fst_speed.attr);
 	if (status)
-		goto rem_fine_grain_attr;
+		return status;
+
+	if (!fan->acpi4)
+		return 0;
+
+	sysfs_attr_init(&fan->fine_grain_control.attr);
+	fan->fine_grain_control.show = show_fine_grain_control;
+	fan->fine_grain_control.store = NULL;
+	fan->fine_grain_control.attr.name = "fine_grain_control";
+	fan->fine_grain_control.attr.mode = 0444;
+	status = sysfs_create_file(&device->dev.kobj, &fan->fine_grain_control.attr);
+	if (status)
+		goto rem_fst_attr;
 
 	for (i = 0; i < fan->fps_count; ++i) {
 		struct acpi_fan_fps *fps = &fan->fps[i];
@@ -109,18 +112,18 @@ int acpi_fan_create_attributes(struct acpi_device *device)
 
 			for (j = 0; j < i; ++j)
 				sysfs_remove_file(&device->dev.kobj, &fan->fps[j].dev_attr.attr);
-			goto rem_fst_attr;
+			goto rem_fine_grain_attr;
 		}
 	}
 
 	return 0;
 
-rem_fst_attr:
-	sysfs_remove_file(&device->dev.kobj, &fan->fst_speed.attr);
-
 rem_fine_grain_attr:
 	sysfs_remove_file(&device->dev.kobj, &fan->fine_grain_control.attr);
 
+rem_fst_attr:
+	sysfs_remove_file(&device->dev.kobj, &fan->fst_speed.attr);
+
 	return status;
 }
 
@@ -129,9 +132,13 @@ void acpi_fan_delete_attributes(struct acpi_device *device)
 	struct acpi_fan *fan = acpi_driver_data(device);
 	int i;
 
+	sysfs_remove_file(&device->dev.kobj, &fan->fst_speed.attr);
+
+	if (!fan->acpi4)
+		return;
+
 	for (i = 0; i < fan->fps_count; ++i)
 		sysfs_remove_file(&device->dev.kobj, &fan->fps[i].dev_attr.attr);
 
-	sysfs_remove_file(&device->dev.kobj, &fan->fst_speed.attr);
 	sysfs_remove_file(&device->dev.kobj, &fan->fine_grain_control.attr);
 }
diff --git a/drivers/acpi/fan_core.c b/drivers/acpi/fan_core.c
index 9dccbae9e8ea..04ff608f2ff0 100644
--- a/drivers/acpi/fan_core.c
+++ b/drivers/acpi/fan_core.c
@@ -102,7 +102,7 @@ match_fps:
 			break;
 	}
 	if (i == fan->fps_count) {
-		dev_dbg(&device->dev, "Invalid control value returned\n");
+		dev_dbg(&device->dev, "No matching fps control value\n");
 		return -EINVAL;
 	}
 
@@ -203,14 +203,6 @@ static const struct thermal_cooling_device_ops fan_cooling_ops = {
  * --------------------------------------------------------------------------
 */
 
-static bool acpi_fan_is_acpi4(struct acpi_device *device)
-{
-	return acpi_has_method(device->handle, "_FIF") &&
-	       acpi_has_method(device->handle, "_FPS") &&
-	       acpi_has_method(device->handle, "_FSL") &&
-	       acpi_has_method(device->handle, "_FST");
-}
-
 static int acpi_fan_get_fif(struct acpi_device *device)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -327,7 +319,14 @@ static int acpi_fan_probe(struct platform_device *pdev)
 	device->driver_data = fan;
 	platform_set_drvdata(pdev, fan);
 
-	if (acpi_fan_is_acpi4(device)) {
+	if (acpi_has_method(device->handle, "_FST")) {
+		fan->has_fst = true;
+		fan->acpi4 = acpi_has_method(device->handle, "_FIF") &&
+				acpi_has_method(device->handle, "_FPS") &&
+				acpi_has_method(device->handle, "_FSL");
+	}
+
+	if (fan->acpi4) {
 		result = acpi_fan_get_fif(device);
 		if (result)
 			return result;
@@ -335,13 +334,19 @@ static int acpi_fan_probe(struct platform_device *pdev)
 		result = acpi_fan_get_fps(device);
 		if (result)
 			return result;
+	}
+
+	if (fan->has_fst) {
+		result = devm_acpi_fan_create_hwmon(device);
+		if (result)
+			return result;
 
 		result = acpi_fan_create_attributes(device);
 		if (result)
 			return result;
+	}
 
-		fan->acpi4 = true;
-	} else {
+	if (!fan->acpi4) {
 		result = acpi_device_update_power(device, NULL);
 		if (result) {
 			dev_err(&device->dev, "Failed to set initial power state\n");
@@ -367,31 +372,37 @@ static int acpi_fan_probe(struct platform_device *pdev)
 	result = sysfs_create_link(&pdev->dev.kobj,
 				   &cdev->device.kobj,
 				   "thermal_cooling");
-	if (result)
+	if (result) {
 		dev_err(&pdev->dev, "Failed to create sysfs link 'thermal_cooling'\n");
+		goto err_unregister;
+	}
 
 	result = sysfs_create_link(&cdev->device.kobj,
 				   &pdev->dev.kobj,
 				   "device");
 	if (result) {
 		dev_err(&pdev->dev, "Failed to create sysfs link 'device'\n");
-		goto err_end;
+		goto err_remove_link;
 	}
 
 	return 0;
 
+err_remove_link:
+	sysfs_remove_link(&pdev->dev.kobj, "thermal_cooling");
+err_unregister:
+	thermal_cooling_device_unregister(cdev);
 err_end:
-	if (fan->acpi4)
+	if (fan->has_fst)
 		acpi_fan_delete_attributes(device);
 
 	return result;
 }
 
-static int acpi_fan_remove(struct platform_device *pdev)
+static void acpi_fan_remove(struct platform_device *pdev)
 {
 	struct acpi_fan *fan = platform_get_drvdata(pdev);
 
-	if (fan->acpi4) {
+	if (fan->has_fst) {
 		struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
 
 		acpi_fan_delete_attributes(device);
@@ -399,8 +410,6 @@ static int acpi_fan_remove(struct platform_device *pdev)
 	sysfs_remove_link(&pdev->dev.kobj, "thermal_cooling");
 	sysfs_remove_link(&fan->cdev->device.kobj, "device");
 	thermal_cooling_device_unregister(fan->cdev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/acpi/fan_hwmon.c b/drivers/acpi/fan_hwmon.c
new file mode 100644
index 000000000000..e8d90605106e
--- /dev/null
+++ b/drivers/acpi/fan_hwmon.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * hwmon interface for the ACPI Fan driver.
+ *
+ * Copyright (C) 2024 Armin Wolf <W_Armin@gmx.de>
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/limits.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#include "fan.h"
+
+/* Returned when the ACPI fan does not support speed reporting */
+#define FAN_SPEED_UNAVAILABLE	U32_MAX
+#define FAN_POWER_UNAVAILABLE	U32_MAX
+
+static struct acpi_fan_fps *acpi_fan_get_current_fps(struct acpi_fan *fan, u64 control)
+{
+	unsigned int i;
+
+	for (i = 0; i < fan->fps_count; i++) {
+		if (fan->fps[i].control == control)
+			return &fan->fps[i];
+	}
+
+	return NULL;
+}
+
+static umode_t acpi_fan_hwmon_is_visible(const void *drvdata, enum hwmon_sensor_types type,
+					 u32 attr, int channel)
+{
+	const struct acpi_fan *fan = drvdata;
+	unsigned int i;
+
+	switch (type) {
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_input:
+			return 0444;
+		case hwmon_fan_target:
+			/* Only acpi4 fans support fan control. */
+			if (!fan->acpi4)
+				return 0;
+
+			/*
+			 * When in fine grain control mode, not every fan control value
+			 * has an associated fan performance state.
+			 */
+			if (fan->fif.fine_grain_ctrl)
+				return 0;
+
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_input:
+			/* Only acpi4 fans support fan control. */
+			if (!fan->acpi4)
+				return 0;
+
+			/*
+			 * When in fine grain control mode, not every fan control value
+			 * has an associated fan performance state.
+			 */
+			if (fan->fif.fine_grain_ctrl)
+				return 0;
+
+			/*
+			 * When all fan performance states contain no valid power data,
+			 * when the associated attribute should not be created.
+			 */
+			for (i = 0; i < fan->fps_count; i++) {
+				if (fan->fps[i].power != FAN_POWER_UNAVAILABLE)
+					return 0444;
+			}
+
+			return 0;
+		default:
+			return 0;
+		}
+	default:
+		return 0;
+	}
+}
+
+static int acpi_fan_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+			       int channel, long *val)
+{
+	struct acpi_device *adev = to_acpi_device(dev->parent);
+	struct acpi_fan *fan = dev_get_drvdata(dev);
+	struct acpi_fan_fps *fps;
+	struct acpi_fan_fst fst;
+	int ret;
+
+	ret = acpi_fan_get_fst(adev, &fst);
+	if (ret < 0)
+		return ret;
+
+	switch (type) {
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_input:
+			if (fst.speed == FAN_SPEED_UNAVAILABLE)
+				return -ENODEV;
+
+			if (fst.speed > LONG_MAX)
+				return -EOVERFLOW;
+
+			*val = fst.speed;
+			return 0;
+		case hwmon_fan_target:
+			fps = acpi_fan_get_current_fps(fan, fst.control);
+			if (!fps)
+				return -EIO;
+
+			if (fps->speed > LONG_MAX)
+				return -EOVERFLOW;
+
+			*val = fps->speed;
+			return 0;
+		default:
+			return -EOPNOTSUPP;
+		}
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_input:
+			fps = acpi_fan_get_current_fps(fan, fst.control);
+			if (!fps)
+				return -EIO;
+
+			if (fps->power == FAN_POWER_UNAVAILABLE)
+				return -ENODEV;
+
+			if (fps->power > LONG_MAX / MICROWATT_PER_MILLIWATT)
+				return -EOVERFLOW;
+
+			*val = fps->power * MICROWATT_PER_MILLIWATT;
+			return 0;
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops acpi_fan_hwmon_ops = {
+	.is_visible = acpi_fan_hwmon_is_visible,
+	.read = acpi_fan_hwmon_read,
+};
+
+static const struct hwmon_channel_info * const acpi_fan_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT | HWMON_F_TARGET),
+	HWMON_CHANNEL_INFO(power, HWMON_P_INPUT),
+	NULL
+};
+
+static const struct hwmon_chip_info acpi_fan_hwmon_chip_info = {
+	.ops = &acpi_fan_hwmon_ops,
+	.info = acpi_fan_hwmon_info,
+};
+
+int devm_acpi_fan_create_hwmon(struct acpi_device *device)
+{
+	struct acpi_fan *fan = acpi_driver_data(device);
+	struct device *hdev;
+
+	hdev = devm_hwmon_device_register_with_info(&device->dev, "acpi_fan", fan,
+						    &acpi_fan_hwmon_chip_info, NULL);
+	return PTR_ERR_OR_ZERO(hdev);
+}
diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c
index 7652515a6be1..3499f86c411e 100644
--- a/drivers/acpi/hed.c
+++ b/drivers/acpi/hed.c
@@ -80,7 +80,12 @@ static struct acpi_driver acpi_hed_driver = {
 		.remove = acpi_hed_remove,
 	},
 };
-module_acpi_driver(acpi_hed_driver);
+
+static int __init acpi_hed_driver_init(void)
+{
+	return acpi_bus_register_driver(&acpi_hed_driver);
+}
+subsys_initcall(acpi_hed_driver_init);
 
 MODULE_AUTHOR("Huang Ying");
 MODULE_DESCRIPTION("ACPI Hardware Error Device Driver");
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 866c7c4ed233..63354972ab0b 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -69,7 +69,8 @@ void acpi_debugfs_init(void);
 #else
 static inline void acpi_debugfs_init(void) { return; }
 #endif
-#ifdef CONFIG_PCI
+
+#if defined(CONFIG_X86) && defined(CONFIG_PCI)
 void acpi_lpss_init(void);
 #else
 static inline void acpi_lpss_init(void) {}
@@ -85,6 +86,20 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent);
 acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context);
 void acpi_scan_table_notify(void);
 
+int acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
+int acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
+int acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
+int acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
+
+#ifdef CONFIG_ARM64
+int acpi_arch_thermal_cpufreq_pctg(void);
+#else
+static inline int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                      Device Node Initialization / Removal
    -------------------------------------------------------------------------- */
@@ -103,10 +118,12 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 			     int type, void (*release)(struct device *));
 int acpi_tie_acpi_dev(struct acpi_device *adev);
 int acpi_device_add(struct acpi_device *device);
-int acpi_device_setup_files(struct acpi_device *dev);
+void acpi_device_setup_files(struct acpi_device *dev);
 void acpi_device_remove_files(struct acpi_device *dev);
+extern const struct attribute_group *acpi_groups[];
 void acpi_device_add_finalize(struct acpi_device *device);
 void acpi_free_pnp_ids(struct acpi_device_pnp *pnp);
+bool acpi_device_is_enabled(const struct acpi_device *adev);
 bool acpi_device_is_present(const struct acpi_device *adev);
 bool acpi_device_is_battery(struct acpi_device *adev);
 bool acpi_device_is_first_physical_node(struct acpi_device *adev,
@@ -123,6 +140,7 @@ int __acpi_device_uevent_modalias(const struct acpi_device *adev,
 /* --------------------------------------------------------------------------
                                   Power Resource
    -------------------------------------------------------------------------- */
+void acpi_power_resources_init(void);
 void acpi_power_resources_list_free(struct list_head *list);
 int acpi_extract_power_resources(union acpi_object *package, unsigned int start,
 				 struct list_head *list);
@@ -148,13 +166,22 @@ int acpi_wakeup_device_init(void);
 #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC
 void acpi_early_processor_control_setup(void);
 void acpi_early_processor_set_pdc(void);
-
+#ifdef CONFIG_X86
 void acpi_proc_quirk_mwait_check(void);
+#else
+static inline void acpi_proc_quirk_mwait_check(void) {}
+#endif
 bool processor_physically_present(acpi_handle handle);
 #else
 static inline void acpi_early_processor_control_setup(void) {}
 #endif
 
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void);
+#else
+static inline void acpi_idle_rescan_dead_smt_siblings(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */
@@ -167,7 +194,6 @@ enum acpi_ec_event_state {
 
 struct acpi_ec {
 	acpi_handle handle;
-	acpi_handle address_space_handler_holder;
 	int gpe;
 	int irq;
 	unsigned long command_addr;
@@ -196,6 +222,8 @@ extern struct acpi_ec *first_ec;
 /* External interfaces use first EC only, so remember */
 typedef int (*acpi_ec_query_func) (void *data);
 
+#ifdef CONFIG_ACPI_EC
+
 void acpi_ec_init(void);
 void acpi_ec_ecdt_probe(void);
 void acpi_ec_dsdt_probe(void);
@@ -205,12 +233,36 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
+void acpi_ec_register_opregions(struct acpi_device *adev);
 
 #ifdef CONFIG_PM_SLEEP
 void acpi_ec_flush_work(void);
 bool acpi_ec_dispatch_gpe(void);
 #endif
 
+#else
+
+static inline void acpi_ec_init(void) {}
+static inline void acpi_ec_ecdt_probe(void) {}
+static inline void acpi_ec_dsdt_probe(void) {}
+static inline void acpi_ec_block_transactions(void) {}
+static inline void acpi_ec_unblock_transactions(void) {}
+static inline int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
+			      acpi_handle handle, acpi_ec_query_func func,
+			      void *data)
+{
+	return -ENXIO;
+}
+static inline void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) {}
+static inline void acpi_ec_register_opregions(struct acpi_device *adev) {}
+
+static inline void acpi_ec_flush_work(void) {}
+static inline bool acpi_ec_dispatch_gpe(void)
+{
+	return false;
+}
+
+#endif
 
 /*--------------------------------------------------------------------------
                                   Suspend/Resume
@@ -276,4 +328,18 @@ void acpi_init_lpit(void);
 static inline void acpi_init_lpit(void) { }
 #endif
 
+/*--------------------------------------------------------------------------
+		ACPI _CRS CSI-2 and MIPI DisCo for Imaging
+  -------------------------------------------------------------------------- */
+
+void acpi_mipi_check_crs_csi2(acpi_handle handle);
+void acpi_mipi_scan_crs_csi2(void);
+void acpi_mipi_init_crs_csi2_swnodes(void);
+void acpi_mipi_crs_csi2_cleanup(void);
+#ifdef CONFIG_X86
+bool acpi_graph_ignore_port(acpi_handle handle);
+#else
+static inline bool acpi_graph_ignore_port(acpi_handle handle) { return false; }
+#endif
+
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c
index 1687483ff319..76a856c32c4d 100644
--- a/drivers/acpi/irq.c
+++ b/drivers/acpi/irq.c
@@ -12,7 +12,7 @@
 
 enum acpi_irq_model_id acpi_irq_model;
 
-static struct fwnode_handle *(*acpi_get_gsi_domain_id)(u32 gsi);
+static acpi_gsi_domain_disp_fn acpi_get_gsi_domain_id;
 static u32 (*acpi_gsi_to_irq_fallback)(u32 gsi);
 
 /**
@@ -307,12 +307,24 @@ EXPORT_SYMBOL_GPL(acpi_irq_get);
  *	for a given GSI
  */
 void __init acpi_set_irq_model(enum acpi_irq_model_id model,
-			       struct fwnode_handle *(*fn)(u32))
+			       acpi_gsi_domain_disp_fn fn)
 {
 	acpi_irq_model = model;
 	acpi_get_gsi_domain_id = fn;
 }
 
+/*
+ * acpi_get_gsi_dispatcher() - Get the GSI dispatcher function
+ *
+ * Return the dispatcher function that computes the domain fwnode for
+ * a given GSI.
+ */
+acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void)
+{
+	return acpi_get_gsi_domain_id;
+}
+EXPORT_SYMBOL_GPL(acpi_get_gsi_dispatcher);
+
 /**
  * acpi_set_gsi_to_irq_fallback - Register a GSI transfer
  * callback to fallback to arch specified implementation.
diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
new file mode 100644
index 000000000000..5b85989f96be
--- /dev/null
+++ b/drivers/acpi/mipi-disco-img.c
@@ -0,0 +1,805 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MIPI DisCo for Imaging support.
+ *
+ * Copyright (C) 2023 Intel Corporation
+ *
+ * Support MIPI DisCo for Imaging by parsing ACPI _CRS CSI-2 records defined in
+ * Section 6.4.3.8.2.4 "Camera Serial Interface (CSI-2) Connection Resource
+ * Descriptor" of ACPI 6.5 and using device properties defined by the MIPI DisCo
+ * for Imaging specification.
+ *
+ * The implementation looks for the information in the ACPI namespace (CSI-2
+ * resource descriptors in _CRS) and constructs software nodes compatible with
+ * Documentation/firmware-guide/acpi/dsd/graph.rst to represent the CSI-2
+ * connection graph.  The software nodes are then populated with the data
+ * extracted from the _CRS CSI-2 resource descriptors and the MIPI DisCo
+ * for Imaging device properties present in _DSD for the ACPI device objects
+ * with CSI-2 connections.
+ */
+
+#include <linux/acpi.h>
+#include <linux/dmi.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include <media/v4l2-fwnode.h>
+
+#include "internal.h"
+
+static LIST_HEAD(acpi_mipi_crs_csi2_list);
+
+static void acpi_mipi_data_tag(acpi_handle handle, void *context)
+{
+}
+
+/* Connection data extracted from one _CRS CSI-2 resource descriptor. */
+struct crs_csi2_connection {
+	struct list_head entry;
+	struct acpi_resource_csi2_serialbus csi2_data;
+	acpi_handle remote_handle;
+	char remote_name[];
+};
+
+/* Data extracted from _CRS CSI-2 resource descriptors for one device. */
+struct crs_csi2 {
+	struct list_head entry;
+	acpi_handle handle;
+	struct acpi_device_software_nodes *swnodes;
+	struct list_head connections;
+	u32 port_count;
+};
+
+struct csi2_resources_walk_data {
+	acpi_handle handle;
+	struct list_head connections;
+};
+
+static acpi_status parse_csi2_resource(struct acpi_resource *res, void *context)
+{
+	struct csi2_resources_walk_data *crwd = context;
+	struct acpi_resource_csi2_serialbus *csi2_res;
+	struct acpi_resource_source *csi2_res_src;
+	u16 csi2_res_src_length;
+	struct crs_csi2_connection *conn;
+	acpi_handle remote_handle;
+
+	if (res->type != ACPI_RESOURCE_TYPE_SERIAL_BUS)
+		return AE_OK;
+
+	csi2_res = &res->data.csi2_serial_bus;
+
+	if (csi2_res->type != ACPI_RESOURCE_SERIAL_TYPE_CSI2)
+		return AE_OK;
+
+	csi2_res_src = &csi2_res->resource_source;
+	if (ACPI_FAILURE(acpi_get_handle(NULL, csi2_res_src->string_ptr,
+					 &remote_handle))) {
+		acpi_handle_debug(crwd->handle,
+				  "unable to find resource source\n");
+		return AE_OK;
+	}
+	csi2_res_src_length = csi2_res_src->string_length;
+	if (!csi2_res_src_length) {
+		acpi_handle_debug(crwd->handle,
+				  "invalid resource source string length\n");
+		return AE_OK;
+	}
+
+	conn = kmalloc(struct_size(conn, remote_name, csi2_res_src_length + 1),
+		       GFP_KERNEL);
+	if (!conn)
+		return AE_OK;
+
+	conn->csi2_data = *csi2_res;
+	strscpy(conn->remote_name, csi2_res_src->string_ptr, csi2_res_src_length);
+	conn->csi2_data.resource_source.string_ptr = conn->remote_name;
+	conn->remote_handle = remote_handle;
+
+	list_add(&conn->entry, &crwd->connections);
+
+	return AE_OK;
+}
+
+static struct crs_csi2 *acpi_mipi_add_crs_csi2(acpi_handle handle,
+					       struct list_head *list)
+{
+	struct crs_csi2 *csi2;
+
+	csi2 = kzalloc(sizeof(*csi2), GFP_KERNEL);
+	if (!csi2)
+		return NULL;
+
+	csi2->handle = handle;
+	INIT_LIST_HEAD(&csi2->connections);
+	csi2->port_count = 1;
+
+	if (ACPI_FAILURE(acpi_attach_data(handle, acpi_mipi_data_tag, csi2))) {
+		kfree(csi2);
+		return NULL;
+	}
+
+	list_add(&csi2->entry, list);
+
+	return csi2;
+}
+
+static struct crs_csi2 *acpi_mipi_get_crs_csi2(acpi_handle handle)
+{
+	struct crs_csi2 *csi2;
+
+	if (ACPI_FAILURE(acpi_get_data_full(handle, acpi_mipi_data_tag,
+					    (void **)&csi2, NULL)))
+		return NULL;
+
+	return csi2;
+}
+
+static void csi_csr2_release_connections(struct list_head *list)
+{
+	struct crs_csi2_connection *conn, *conn_tmp;
+
+	list_for_each_entry_safe(conn, conn_tmp, list, entry) {
+		list_del(&conn->entry);
+		kfree(conn);
+	}
+}
+
+static void acpi_mipi_del_crs_csi2(struct crs_csi2 *csi2)
+{
+	list_del(&csi2->entry);
+	acpi_detach_data(csi2->handle, acpi_mipi_data_tag);
+	kfree(csi2->swnodes);
+	csi_csr2_release_connections(&csi2->connections);
+	kfree(csi2);
+}
+
+/**
+ * acpi_mipi_check_crs_csi2 - Look for CSI-2 resources in _CRS
+ * @handle: Device object handle to evaluate _CRS for.
+ *
+ * Find all CSI-2 resource descriptors in the given device's _CRS
+ * and collect them into a list.
+ */
+void acpi_mipi_check_crs_csi2(acpi_handle handle)
+{
+	struct csi2_resources_walk_data crwd = {
+		.handle = handle,
+		.connections = LIST_HEAD_INIT(crwd.connections),
+	};
+	struct crs_csi2 *csi2;
+
+	/*
+	 * Avoid allocating _CRS CSI-2 objects for devices without any CSI-2
+	 * resource descriptions in _CRS to reduce overhead.
+	 */
+	acpi_walk_resources(handle, METHOD_NAME__CRS, parse_csi2_resource, &crwd);
+	if (list_empty(&crwd.connections))
+		return;
+
+	/*
+	 * Create a _CRS CSI-2 entry to store the extracted connection
+	 * information and add it to the global list.
+	 */
+	csi2 = acpi_mipi_add_crs_csi2(handle, &acpi_mipi_crs_csi2_list);
+	if (!csi2) {
+		csi_csr2_release_connections(&crwd.connections);
+		return; /* Nothing really can be done about this. */
+	}
+
+	list_replace(&crwd.connections, &csi2->connections);
+}
+
+#define NO_CSI2_PORT (UINT_MAX - 1)
+
+static void alloc_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	size_t port_count = csi2->port_count;
+	struct acpi_device_software_nodes *swnodes;
+	size_t alloc_size;
+	unsigned int i;
+
+	/*
+	 * Allocate memory for ports, node pointers (number of nodes +
+	 * 1 (guardian), nodes (root + number of ports * 2 (because for
+	 * every port there is an endpoint)).
+	 */
+	if (check_mul_overflow(sizeof(*swnodes->ports) +
+			       sizeof(*swnodes->nodes) * 2 +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       port_count, &alloc_size) ||
+	    check_add_overflow(sizeof(*swnodes) +
+			       sizeof(*swnodes->nodes) +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       alloc_size, &alloc_size)) {
+		acpi_handle_info(csi2->handle,
+				 "too many _CRS CSI-2 resource handles (%zu)",
+				 port_count);
+		return;
+	}
+
+	swnodes = kmalloc(alloc_size, GFP_KERNEL);
+	if (!swnodes)
+		return;
+
+	swnodes->ports = (struct acpi_device_software_node_port *)(swnodes + 1);
+	swnodes->nodes = (struct software_node *)(swnodes->ports + port_count);
+	swnodes->nodeptrs = (const struct software_node **)(swnodes->nodes + 1 +
+				2 * port_count);
+	swnodes->num_ports = port_count;
+
+	for (i = 0; i < 2 * port_count + 1; i++)
+		swnodes->nodeptrs[i] = &swnodes->nodes[i];
+
+	swnodes->nodeptrs[i] = NULL;
+
+	for (i = 0; i < port_count; i++)
+		swnodes->ports[i].port_nr = NO_CSI2_PORT;
+
+	csi2->swnodes = swnodes;
+}
+
+#define ACPI_CRS_CSI2_PHY_TYPE_C	0
+#define ACPI_CRS_CSI2_PHY_TYPE_D	1
+
+static unsigned int next_csi2_port_index(struct acpi_device_software_nodes *swnodes,
+					 unsigned int port_nr)
+{
+	unsigned int i;
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+
+		if (port->port_nr == port_nr)
+			return i;
+
+		if (port->port_nr == NO_CSI2_PORT) {
+			port->port_nr = port_nr;
+			return i;
+		}
+	}
+
+	return NO_CSI2_PORT;
+}
+
+/* Print graph port name into a buffer, return non-zero on failure. */
+#define GRAPH_PORT_NAME(var, num)					    \
+	(snprintf((var), sizeof(var), SWNODE_GRAPH_PORT_NAME_FMT, (num)) >= \
+	 sizeof(var))
+
+static void extract_crs_csi2_conn_info(acpi_handle local_handle,
+				       struct acpi_device_software_nodes *local_swnodes,
+				       struct crs_csi2_connection *conn)
+{
+	struct crs_csi2 *remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+	struct acpi_device_software_nodes *remote_swnodes;
+	struct acpi_device_software_node_port *local_port, *remote_port;
+	struct software_node *local_node, *remote_node;
+	unsigned int local_index, remote_index;
+	unsigned int bus_type;
+
+	/*
+	 * If the previous steps have failed to make room for a _CRS CSI-2
+	 * representation for the remote end of the given connection, skip it.
+	 */
+	if (!remote_csi2)
+		return;
+
+	remote_swnodes = remote_csi2->swnodes;
+	if (!remote_swnodes)
+		return;
+
+	switch (conn->csi2_data.phy_type) {
+	case ACPI_CRS_CSI2_PHY_TYPE_C:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_CPHY;
+		break;
+
+	case ACPI_CRS_CSI2_PHY_TYPE_D:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_DPHY;
+		break;
+
+	default:
+		acpi_handle_info(local_handle, "unknown CSI-2 PHY type %u\n",
+				 conn->csi2_data.phy_type);
+		return;
+	}
+
+	local_index = next_csi2_port_index(local_swnodes,
+					   conn->csi2_data.local_port_instance);
+	if (WARN_ON_ONCE(local_index >= local_swnodes->num_ports))
+		return;
+
+	remote_index = next_csi2_port_index(remote_swnodes,
+					    conn->csi2_data.resource_source.index);
+	if (WARN_ON_ONCE(remote_index >= remote_swnodes->num_ports))
+		return;
+
+	local_port = &local_swnodes->ports[local_index];
+	local_node = &local_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(local_index)];
+	local_port->crs_csi2_local = true;
+
+	remote_port = &remote_swnodes->ports[remote_index];
+	remote_node = &remote_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(remote_index)];
+
+	local_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(remote_node);
+	remote_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(local_node);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 local_port->remote_ep);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	local_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.local_port_instance);
+
+	if (GRAPH_PORT_NAME(local_port->port_name,
+			    conn->csi2_data.local_port_instance))
+		acpi_handle_info(local_handle, "local port %u name too long",
+				 conn->csi2_data.local_port_instance);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 remote_port->remote_ep);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	remote_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.resource_source.index);
+
+	if (GRAPH_PORT_NAME(remote_port->port_name,
+			    conn->csi2_data.resource_source.index))
+		acpi_handle_info(local_handle, "remote port %u name too long",
+				 conn->csi2_data.resource_source.index);
+}
+
+static void prepare_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_device_software_nodes *local_swnodes = csi2->swnodes;
+	acpi_handle local_handle = csi2->handle;
+	struct crs_csi2_connection *conn;
+
+	/* Bail out if the allocation of swnodes has failed. */
+	if (!local_swnodes)
+		return;
+
+	list_for_each_entry(conn, &csi2->connections, entry)
+		extract_crs_csi2_conn_info(local_handle, local_swnodes, conn);
+}
+
+/**
+ * acpi_mipi_scan_crs_csi2 - Create ACPI _CRS CSI-2 software nodes
+ *
+ * Note that this function must be called before any struct acpi_device objects
+ * are bound to any ACPI drivers or scan handlers, so it cannot assume the
+ * existence of struct acpi_device objects for every device present in the ACPI
+ * namespace.
+ *
+ * acpi_scan_lock in scan.c must be held when calling this function.
+ */
+void acpi_mipi_scan_crs_csi2(void)
+{
+	struct crs_csi2 *csi2;
+	LIST_HEAD(aux_list);
+
+	/* Count references to each ACPI handle in the CSI-2 connection graph. */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry) {
+		struct crs_csi2_connection *conn;
+
+		list_for_each_entry(conn, &csi2->connections, entry) {
+			struct crs_csi2 *remote_csi2;
+
+			csi2->port_count++;
+
+			remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+			if (remote_csi2) {
+				remote_csi2->port_count++;
+				continue;
+			}
+			/*
+			 * The remote endpoint has no _CRS CSI-2 list entry yet,
+			 * so create one for it and add it to the list.
+			 */
+			acpi_mipi_add_crs_csi2(conn->remote_handle, &aux_list);
+		}
+	}
+	list_splice(&aux_list, &acpi_mipi_crs_csi2_list);
+
+	/*
+	 * Allocate software nodes for representing the CSI-2 information.
+	 *
+	 * This needs to be done for all of the list entries in one go, because
+	 * they may point to each other without restrictions and the next step
+	 * relies on the availability of swnodes memory for each list entry.
+	 */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		alloc_crs_csi2_swnodes(csi2);
+
+	/*
+	 * Set up software node properties using data from _CRS CSI-2 resource
+	 * descriptors.
+	 */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		prepare_crs_csi2_swnodes(csi2);
+}
+
+/*
+ * Get the index of the next property in the property array, with a given
+ * maximum value.
+ */
+#define NEXT_PROPERTY(index, max)			\
+	(WARN_ON((index) > ACPI_DEVICE_SWNODE_##max) ?	\
+	 ACPI_DEVICE_SWNODE_##max : (index)++)
+
+static void init_csi2_port_local(struct acpi_device *adev,
+				 struct acpi_device_software_node_port *port,
+				 struct fwnode_handle *port_fwnode,
+				 unsigned int index)
+{
+	acpi_handle handle = acpi_device_handle(adev);
+	unsigned int num_link_freqs;
+	int ret;
+
+	ret = fwnode_property_count_u64(port_fwnode, "mipi-img-link-frequencies");
+	if (ret <= 0)
+		return;
+
+	num_link_freqs = ret;
+	if (num_link_freqs > ACPI_DEVICE_CSI2_DATA_LANES) {
+		acpi_handle_info(handle, "Too many link frequencies: %u\n",
+				 num_link_freqs);
+		num_link_freqs = ACPI_DEVICE_CSI2_DATA_LANES;
+	}
+
+	ret = fwnode_property_read_u64_array(port_fwnode,
+					     "mipi-img-link-frequencies",
+					     port->link_frequencies,
+					     num_link_freqs);
+	if (ret) {
+		acpi_handle_info(handle, "Unable to get link frequencies (%d)\n",
+				 ret);
+		return;
+	}
+
+	port->ep_props[NEXT_PROPERTY(index, EP_LINK_FREQUENCIES)] =
+				PROPERTY_ENTRY_U64_ARRAY_LEN("link-frequencies",
+							     port->link_frequencies,
+							     num_link_freqs);
+}
+
+static void init_csi2_port(struct acpi_device *adev,
+			   struct acpi_device_software_nodes *swnodes,
+			   struct acpi_device_software_node_port *port,
+			   struct fwnode_handle *port_fwnode,
+			   unsigned int port_index)
+{
+	unsigned int ep_prop_index = ACPI_DEVICE_SWNODE_EP_CLOCK_LANES;
+	acpi_handle handle = acpi_device_handle(adev);
+	u8 val[ACPI_DEVICE_CSI2_DATA_LANES];
+	int num_lanes = 0;
+	int ret;
+
+	if (GRAPH_PORT_NAME(port->port_name, port->port_nr))
+		return;
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)] =
+			SOFTWARE_NODE(port->port_name, port->port_props,
+				      &swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT]);
+
+	ret = fwnode_property_read_u8(port_fwnode, "mipi-img-clock-lane", val);
+	if (!ret)
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_CLOCK_LANES)] =
+			PROPERTY_ENTRY_U32("clock-lanes", val[0]);
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-data-lanes");
+	if (ret > 0) {
+		num_lanes = ret;
+
+		if (num_lanes > ACPI_DEVICE_CSI2_DATA_LANES) {
+			acpi_handle_info(handle, "Too many data lanes: %u\n",
+					 num_lanes);
+			num_lanes = ACPI_DEVICE_CSI2_DATA_LANES;
+		}
+
+		ret = fwnode_property_read_u8_array(port_fwnode,
+						    "mipi-img-data-lanes",
+						    val, num_lanes);
+		if (!ret) {
+			unsigned int i;
+
+			for (i = 0; i < num_lanes; i++)
+				port->data_lanes[i] = val[i];
+
+			port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_DATA_LANES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("data-lanes",
+							     port->data_lanes,
+							     num_lanes);
+		}
+	}
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-lane-polarities");
+	if (ret < 0) {
+		acpi_handle_debug(handle, "Lane polarity bytes missing\n");
+	} else if (ret * BITS_PER_TYPE(u8) < num_lanes + 1) {
+		acpi_handle_info(handle, "Too few lane polarity bits (%zu vs. %d)\n",
+				 ret * BITS_PER_TYPE(u8), num_lanes + 1);
+	} else {
+		unsigned long mask = 0;
+		int byte_count = ret;
+		unsigned int i;
+
+		/*
+		 * The total number of lanes is ACPI_DEVICE_CSI2_DATA_LANES + 1
+		 * (data lanes + clock lane).  It is not expected to ever be
+		 * greater than the number of bits in an unsigned long
+		 * variable, but ensure that this is the case.
+		 */
+		BUILD_BUG_ON(BITS_PER_TYPE(unsigned long) <= ACPI_DEVICE_CSI2_DATA_LANES);
+
+		if (byte_count > sizeof(mask)) {
+			acpi_handle_info(handle, "Too many lane polarities: %d\n",
+					 byte_count);
+			byte_count = sizeof(mask);
+		}
+		fwnode_property_read_u8_array(port_fwnode, "mipi-img-lane-polarities",
+					      val, byte_count);
+
+		for (i = 0; i < byte_count; i++)
+			mask |= (unsigned long)val[i] << BITS_PER_TYPE(u8) * i;
+
+		for (i = 0; i <= num_lanes; i++)
+			port->lane_polarities[i] = test_bit(i, &mask);
+
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_LANE_POLARITIES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("lane-polarities",
+							     port->lane_polarities,
+							     num_lanes + 1);
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_EP(port_index)] =
+		SOFTWARE_NODE("endpoint@0", swnodes->ports[port_index].ep_props,
+			      &swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)]);
+
+	if (port->crs_csi2_local)
+		init_csi2_port_local(adev, port, port_fwnode, ep_prop_index);
+}
+
+#define MIPI_IMG_PORT_PREFIX "mipi-img-port-"
+
+static struct fwnode_handle *get_mipi_port_handle(struct fwnode_handle *adev_fwnode,
+						  unsigned int port_nr)
+{
+	char port_name[sizeof(MIPI_IMG_PORT_PREFIX) + 2];
+
+	if (snprintf(port_name, sizeof(port_name), "%s%u",
+		     MIPI_IMG_PORT_PREFIX, port_nr) >= sizeof(port_name))
+		return NULL;
+
+	return fwnode_get_named_child_node(adev_fwnode, port_name);
+}
+
+static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_buffer buffer = { .length = ACPI_ALLOCATE_BUFFER };
+	struct acpi_device_software_nodes *swnodes = csi2->swnodes;
+	acpi_handle handle = csi2->handle;
+	unsigned int prop_index = 0;
+	struct fwnode_handle *adev_fwnode;
+	struct acpi_device *adev;
+	acpi_status status;
+	unsigned int i;
+	u32 val;
+	int ret;
+
+	/*
+	 * Bail out if the swnodes are not available (either they have not been
+	 * allocated or they have been assigned to the device already).
+	 */
+	if (!swnodes)
+		return;
+
+	adev = acpi_fetch_acpi_dev(handle);
+	if (!adev)
+		return;
+
+	adev_fwnode = acpi_fwnode_handle(adev);
+
+	/*
+	 * If the "rotation" property is not present, but _PLD is there,
+	 * evaluate it to get the "rotation" value.
+	 */
+	if (!fwnode_property_present(adev_fwnode, "rotation")) {
+		struct acpi_pld_info *pld;
+
+		if (acpi_get_physical_device_location(handle, &pld)) {
+			swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_ROTATION)] =
+					PROPERTY_ENTRY_U32("rotation",
+							   pld->rotation * 45U);
+			kfree(pld);
+		}
+	}
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-clock-frequency", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_CLOCK_FREQUENCY)] =
+			PROPERTY_ENTRY_U32("clock-frequency", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-led-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_LED_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("led-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("flash-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-timeout-us", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_TIMEOUT_US)] =
+			PROPERTY_ENTRY_U32("flash-max-timeout-us", val);
+
+	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_info(handle, "Unable to get the path name\n");
+		return;
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT] =
+			SOFTWARE_NODE(buffer.pointer, swnodes->dev_props, NULL);
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+		struct fwnode_handle *port_fwnode;
+
+		/*
+		 * The MIPI DisCo for Imaging specification defines _DSD device
+		 * properties for providing CSI-2 port parameters that can be
+		 * accessed through the generic device properties framework.  To
+		 * access them, it is first necessary to find the data node
+		 * representing the port under the given ACPI device object.
+		 */
+		port_fwnode = get_mipi_port_handle(adev_fwnode, port->port_nr);
+		if (!port_fwnode) {
+			acpi_handle_info(handle,
+					 "MIPI port name too long for port %u\n",
+					 port->port_nr);
+			continue;
+		}
+
+		init_csi2_port(adev, swnodes, port, port_fwnode, i);
+
+		fwnode_handle_put(port_fwnode);
+	}
+
+	ret = software_node_register_node_group(swnodes->nodeptrs);
+	if (ret < 0) {
+		acpi_handle_info(handle,
+				 "Unable to register software nodes (%d)\n", ret);
+		return;
+	}
+
+	adev->swnodes = swnodes;
+	adev_fwnode->secondary = software_node_fwnode(swnodes->nodes);
+
+	/*
+	 * Prevents the swnodes from this csi2 entry from being assigned again
+	 * or freed prematurely.
+	 */
+	csi2->swnodes = NULL;
+}
+
+/**
+ * acpi_mipi_init_crs_csi2_swnodes - Initialize _CRS CSI-2 software nodes
+ *
+ * Use MIPI DisCo for Imaging device properties to finalize the initialization
+ * of CSI-2 software nodes for all ACPI device objects that have been already
+ * enumerated.
+ */
+void acpi_mipi_init_crs_csi2_swnodes(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		init_crs_csi2_swnodes(csi2);
+}
+
+/**
+ * acpi_mipi_crs_csi2_cleanup - Free _CRS CSI-2 temporary data
+ */
+void acpi_mipi_crs_csi2_cleanup(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		acpi_mipi_del_crs_csi2(csi2);
+}
+
+#ifdef CONFIG_X86
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+
+/* CPU matches for Dell generations with broken ACPI MIPI DISCO info */
+static const struct x86_cpu_id dell_broken_mipi_disco_cpu_gens[] = {
+	X86_MATCH_VFM(INTEL_TIGERLAKE, NULL),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L, NULL),
+	X86_MATCH_VFM(INTEL_ALDERLAKE, NULL),
+	X86_MATCH_VFM(INTEL_ALDERLAKE_L, NULL),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE, NULL),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_P, NULL),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_S, NULL),
+	{}
+};
+
+static const char *strnext(const char *s1, const char *s2)
+{
+	s1 = strstr(s1, s2);
+
+	if (!s1)
+		return NULL;
+
+	return s1 + strlen(s2);
+}
+
+/**
+ * acpi_graph_ignore_port - Tell whether a port node should be ignored
+ * @handle: The ACPI handle of the node (which may be a port node)
+ *
+ * Return: true if a port node should be ignored and the data to that should
+ * come from other sources instead (Windows ACPI definitions and
+ * ipu-bridge). This is currently used to ignore bad port nodes related to IPU6
+ * ("IPU?") and camera sensor devices ("LNK?") in certain Dell systems with
+ * Intel VSC.
+ */
+bool acpi_graph_ignore_port(acpi_handle handle)
+{
+	const char *path = NULL, *orig_path;
+	static bool dmi_tested, ignore_port;
+
+	if (!dmi_tested) {
+		if (dmi_name_in_vendors("Dell Inc.") &&
+		    x86_match_cpu(dell_broken_mipi_disco_cpu_gens))
+			ignore_port = true;
+
+		dmi_tested = true;
+	}
+
+	if (!ignore_port)
+		return false;
+
+	/* Check if the device is either "IPU" or "LNK" (sensor). */
+	orig_path = acpi_handle_path(handle);
+	if (!orig_path)
+		return false;
+	path = strnext(orig_path, "IPU");
+	if (!path)
+		path = strnext(orig_path, "LNK");
+	if (!path)
+		goto out_free;
+
+	if (!(isdigit(path[0]) && path[1] == '.'))
+		goto out_free;
+
+	/* Check if the node has a "PRT" prefix. */
+	path = strnext(path, "PRT");
+	if (path && isdigit(path[0]) && !path[1]) {
+		acpi_handle_debug(handle, "ignoring data node\n");
+
+		kfree(orig_path);
+		return true;
+	}
+
+out_free:
+	kfree(orig_path);
+	return false;
+}
+#endif
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 992385537757..3eb56b77cb6d 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -454,8 +454,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	if (cmd_rc)
 		*cmd_rc = -EINVAL;
 
-	if (cmd == ND_CMD_CALL)
+	if (cmd == ND_CMD_CALL) {
+		if (!buf || buf_len < sizeof(*call_pkg))
+			return -EINVAL;
+
 		call_pkg = buf;
+	}
+
 	func = cmd_to_func(nfit_mem, cmd, call_pkg, &family);
 	if (func < 0)
 		return func;
@@ -480,7 +485,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		cmd_mask = nd_desc->cmd_mask;
 		if (cmd == ND_CMD_CALL && call_pkg->nd_family) {
 			family = call_pkg->nd_family;
-			if (family > NVDIMM_BUS_FAMILY_MAX ||
+			if (call_pkg->nd_family > NVDIMM_BUS_FAMILY_MAX ||
 			    !test_bit(family, &nd_desc->bus_family_mask))
 				return -EINVAL;
 			family = array_index_nospec(family,
@@ -1186,7 +1191,7 @@ static ssize_t bus_dsm_mask_show(struct device *dev,
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%#lx\n", acpi_desc->bus_dsm_mask);
+	return sysfs_emit(buf, "%#lx\n", acpi_desc->bus_dsm_mask);
 }
 static struct device_attribute dev_attr_bus_dsm_mask =
 		__ATTR(dsm_mask, 0444, bus_dsm_mask_show, NULL);
@@ -1198,7 +1203,7 @@ static ssize_t revision_show(struct device *dev,
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision);
+	return sysfs_emit(buf, "%d\n", acpi_desc->acpi_header.revision);
 }
 static DEVICE_ATTR_RO(revision);
 
@@ -1209,7 +1214,7 @@ static ssize_t hw_error_scrub_show(struct device *dev,
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%d\n", acpi_desc->scrub_mode);
+	return sysfs_emit(buf, "%d\n", acpi_desc->scrub_mode);
 }
 
 /*
@@ -1278,7 +1283,7 @@ static ssize_t scrub_show(struct device *dev,
 	mutex_lock(&acpi_desc->init_mutex);
 	busy = test_bit(ARS_BUSY, &acpi_desc->scrub_flags)
 		&& !test_bit(ARS_CANCEL, &acpi_desc->scrub_flags);
-	rc = sprintf(buf, "%d%s", acpi_desc->scrub_count, busy ? "+\n" : "\n");
+	rc = sysfs_emit(buf, "%d%s", acpi_desc->scrub_count, busy ? "+\n" : "\n");
 	/* Allow an admin to poll the busy state at a higher rate */
 	if (busy && capable(CAP_SYS_RAWIO) && !test_and_set_bit(ARS_POLL,
 				&acpi_desc->scrub_flags)) {
@@ -1382,7 +1387,7 @@ static ssize_t handle_show(struct device *dev,
 {
 	struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);
 
-	return sprintf(buf, "%#x\n", memdev->device_handle);
+	return sysfs_emit(buf, "%#x\n", memdev->device_handle);
 }
 static DEVICE_ATTR_RO(handle);
 
@@ -1391,7 +1396,7 @@ static ssize_t phys_id_show(struct device *dev,
 {
 	struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);
 
-	return sprintf(buf, "%#x\n", memdev->physical_id);
+	return sysfs_emit(buf, "%#x\n", memdev->physical_id);
 }
 static DEVICE_ATTR_RO(phys_id);
 
@@ -1400,7 +1405,7 @@ static ssize_t vendor_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->vendor_id));
+	return sysfs_emit(buf, "0x%04x\n", be16_to_cpu(dcr->vendor_id));
 }
 static DEVICE_ATTR_RO(vendor);
 
@@ -1409,7 +1414,7 @@ static ssize_t rev_id_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->revision_id));
+	return sysfs_emit(buf, "0x%04x\n", be16_to_cpu(dcr->revision_id));
 }
 static DEVICE_ATTR_RO(rev_id);
 
@@ -1418,7 +1423,7 @@ static ssize_t device_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->device_id));
+	return sysfs_emit(buf, "0x%04x\n", be16_to_cpu(dcr->device_id));
 }
 static DEVICE_ATTR_RO(device);
 
@@ -1427,7 +1432,7 @@ static ssize_t subsystem_vendor_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_vendor_id));
+	return sysfs_emit(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_vendor_id));
 }
 static DEVICE_ATTR_RO(subsystem_vendor);
 
@@ -1436,7 +1441,7 @@ static ssize_t subsystem_rev_id_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n",
+	return sysfs_emit(buf, "0x%04x\n",
 			be16_to_cpu(dcr->subsystem_revision_id));
 }
 static DEVICE_ATTR_RO(subsystem_rev_id);
@@ -1446,7 +1451,7 @@ static ssize_t subsystem_device_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_device_id));
+	return sysfs_emit(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_device_id));
 }
 static DEVICE_ATTR_RO(subsystem_device);
 
@@ -1465,7 +1470,7 @@ static ssize_t format_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code));
+	return sysfs_emit(buf, "0x%04x\n", le16_to_cpu(dcr->code));
 }
 static DEVICE_ATTR_RO(format);
 
@@ -1498,7 +1503,7 @@ static ssize_t format1_show(struct device *dev,
 				continue;
 			if (nfit_dcr->dcr->code == dcr->code)
 				continue;
-			rc = sprintf(buf, "0x%04x\n",
+			rc = sysfs_emit(buf, "0x%04x\n",
 					le16_to_cpu(nfit_dcr->dcr->code));
 			break;
 		}
@@ -1515,7 +1520,7 @@ static ssize_t formats_show(struct device *dev,
 {
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	return sprintf(buf, "%d\n", num_nvdimm_formats(nvdimm));
+	return sysfs_emit(buf, "%d\n", num_nvdimm_formats(nvdimm));
 }
 static DEVICE_ATTR_RO(formats);
 
@@ -1524,7 +1529,7 @@ static ssize_t serial_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%08x\n", be32_to_cpu(dcr->serial_number));
+	return sysfs_emit(buf, "0x%08x\n", be32_to_cpu(dcr->serial_number));
 }
 static DEVICE_ATTR_RO(serial);
 
@@ -1536,7 +1541,7 @@ static ssize_t family_show(struct device *dev,
 
 	if (nfit_mem->family < 0)
 		return -ENXIO;
-	return sprintf(buf, "%d\n", nfit_mem->family);
+	return sysfs_emit(buf, "%d\n", nfit_mem->family);
 }
 static DEVICE_ATTR_RO(family);
 
@@ -1548,7 +1553,7 @@ static ssize_t dsm_mask_show(struct device *dev,
 
 	if (nfit_mem->family < 0)
 		return -ENXIO;
-	return sprintf(buf, "%#lx\n", nfit_mem->dsm_mask);
+	return sysfs_emit(buf, "%#lx\n", nfit_mem->dsm_mask);
 }
 static DEVICE_ATTR_RO(dsm_mask);
 
@@ -1562,7 +1567,7 @@ static ssize_t flags_show(struct device *dev,
 	if (test_bit(NFIT_MEM_DIRTY, &nfit_mem->flags))
 		flags |= ACPI_NFIT_MEM_FLUSH_FAILED;
 
-	return sprintf(buf, "%s%s%s%s%s%s%s\n",
+	return sysfs_emit(buf, "%s%s%s%s%s%s%s\n",
 		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
 		flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore_fail " : "",
 		flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush_fail " : "",
@@ -1579,7 +1584,7 @@ static ssize_t id_show(struct device *dev,
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 
-	return sprintf(buf, "%s\n", nfit_mem->id);
+	return sysfs_emit(buf, "%s\n", nfit_mem->id);
 }
 static DEVICE_ATTR_RO(id);
 
@@ -1589,7 +1594,7 @@ static ssize_t dirty_shutdown_show(struct device *dev,
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 
-	return sprintf(buf, "%d\n", nfit_mem->dirty_shutdown);
+	return sysfs_emit(buf, "%d\n", nfit_mem->dirty_shutdown);
 }
 static DEVICE_ATTR_RO(dirty_shutdown);
 
@@ -1737,9 +1742,8 @@ __weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 	if ((nfit_mem->dsm_mask & (1 << func)) == 0)
 		return;
 
-	out_obj = acpi_evaluate_dsm(handle, guid, revid, func, &in_obj);
-	if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER
-			|| out_obj->buffer.length < sizeof(smart)) {
+	out_obj = acpi_evaluate_dsm_typed(handle, guid, revid, func, &in_obj, ACPI_TYPE_BUFFER);
+	if (!out_obj || out_obj->buffer.length < sizeof(smart)) {
 		dev_dbg(dev->parent, "%s: failed to retrieve initial health\n",
 				dev_name(dev));
 		ACPI_FREE(out_obj);
@@ -2172,7 +2176,7 @@ static ssize_t range_index_show(struct device *dev,
 	struct nd_region *nd_region = to_nd_region(dev);
 	struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);
 
-	return sprintf(buf, "%d\n", nfit_spa->spa->range_index);
+	return sysfs_emit(buf, "%d\n", nfit_spa->spa->range_index);
 }
 static DEVICE_ATTR_RO(range_index);
 
@@ -2257,26 +2261,23 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 		struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_system_address *spa)
 {
+	u16 nr = ndr_desc->num_mappings;
+	struct nfit_set_info2 *info2 __free(kfree) =
+		kcalloc(nr, sizeof(*info2), GFP_KERNEL);
+	struct nfit_set_info *info __free(kfree) =
+		kcalloc(nr, sizeof(*info), GFP_KERNEL);
 	struct device *dev = acpi_desc->dev;
 	struct nd_interleave_set *nd_set;
-	u16 nr = ndr_desc->num_mappings;
-	struct nfit_set_info2 *info2;
-	struct nfit_set_info *info;
 	int i;
 
+	if (!info || !info2)
+		return -ENOMEM;
+
 	nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL);
 	if (!nd_set)
 		return -ENOMEM;
 	import_guid(&nd_set->type_guid, spa->range_guid);
 
-	info = devm_kcalloc(dev, nr, sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info2 = devm_kcalloc(dev, nr, sizeof(*info2), GFP_KERNEL);
-	if (!info2)
-		return -ENOMEM;
-
 	for (i = 0; i < nr; i++) {
 		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
 		struct nvdimm *nvdimm = mapping->nvdimm;
@@ -2337,8 +2338,6 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	ndr_desc->nd_set = nd_set;
-	devm_kfree(dev, info);
-	devm_kfree(dev, info2);
 
 	return 0;
 }
@@ -2638,7 +2637,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	if (ndr_desc->target_node == NUMA_NO_NODE) {
 		ndr_desc->target_node = phys_to_target_node(spa->address);
 		dev_info(acpi_desc->dev, "changing target node from %d to %d for nfit region [%pa-%pa]",
-			NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end);
+			NUMA_NO_NODE, ndr_desc->target_node, &res.start, &res.end);
 	}
 
 	/*
@@ -3537,5 +3536,6 @@ static __exit void nfit_exit(void)
 
 module_init(nfit_init);
 module_exit(nfit_exit);
+MODULE_DESCRIPTION("ACPI NVDIMM Firmware Interface Table (NFIT) driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c
index 3902759abcba..bce6f6a18426 100644
--- a/drivers/acpi/nfit/intel.c
+++ b/drivers/acpi/nfit/intel.c
@@ -55,10 +55,9 @@ static unsigned long intel_security_flags(struct nvdimm *nvdimm,
 {
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 	unsigned long security_flags = 0;
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_get_security_state cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_GET_SECURITY_STATE,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -120,10 +119,9 @@ static unsigned long intel_security_flags(struct nvdimm *nvdimm,
 static int intel_security_freeze(struct nvdimm *nvdimm)
 {
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_freeze_lock cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_FREEZE_LOCK,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -153,10 +151,9 @@ static int intel_security_change_key(struct nvdimm *nvdimm,
 	unsigned int cmd = ptype == NVDIMM_MASTER ?
 		NVDIMM_INTEL_SET_MASTER_PASSPHRASE :
 		NVDIMM_INTEL_SET_PASSPHRASE;
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_set_passphrase cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_family = NVDIMM_FAMILY_INTEL,
 			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE * 2,
@@ -195,10 +192,9 @@ static int __maybe_unused intel_security_unlock(struct nvdimm *nvdimm,
 		const struct nvdimm_key_data *key_data)
 {
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_unlock_unit cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_UNLOCK_UNIT,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -234,10 +230,9 @@ static int intel_security_disable(struct nvdimm *nvdimm,
 {
 	int rc;
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_disable_passphrase cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_DISABLE_PASSPHRASE,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -277,10 +272,9 @@ static int __maybe_unused intel_security_erase(struct nvdimm *nvdimm,
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 	unsigned int cmd = ptype == NVDIMM_MASTER ?
 		NVDIMM_INTEL_MASTER_SECURE_ERASE : NVDIMM_INTEL_SECURE_ERASE;
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_secure_erase cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_family = NVDIMM_FAMILY_INTEL,
 			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE,
@@ -318,10 +312,9 @@ static int __maybe_unused intel_security_query_overwrite(struct nvdimm *nvdimm)
 {
 	int rc;
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_query_overwrite cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_QUERY_OVERWRITE,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -354,10 +347,9 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
 {
 	int rc;
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_overwrite cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_OVERWRITE,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -407,10 +399,9 @@ const struct nvdimm_security_ops *intel_security_ops = &__intel_security_ops;
 static int intel_bus_fwa_businfo(struct nvdimm_bus_descriptor *nd_desc,
 		struct nd_intel_bus_fw_activate_businfo *info)
 {
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_bus_fw_activate_businfo cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO,
 			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
@@ -518,33 +509,31 @@ static enum nvdimm_fwa_capability intel_bus_fwa_capability(
 static int intel_bus_fwa_activate(struct nvdimm_bus_descriptor *nd_desc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_bus_fw_activate cmd;
-	} nd_cmd = {
-		.pkg = {
-			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE,
-			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
-			.nd_size_in = sizeof(nd_cmd.cmd.iodev_state),
-			.nd_size_out =
-				sizeof(struct nd_intel_bus_fw_activate),
-			.nd_fw_size =
-				sizeof(struct nd_intel_bus_fw_activate),
-		},
+	) nd_cmd;
+	int rc;
+
+	nd_cmd.pkg = (struct nd_cmd_pkg) {
+		.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE,
+		.nd_family = NVDIMM_BUS_FAMILY_INTEL,
+		.nd_size_in = sizeof(nd_cmd.cmd.iodev_state),
+		.nd_size_out =
+			sizeof(struct nd_intel_bus_fw_activate),
+		.nd_fw_size =
+			sizeof(struct nd_intel_bus_fw_activate),
+	};
+	nd_cmd.cmd = (struct nd_intel_bus_fw_activate) {
 		/*
 		 * Even though activate is run from a suspended context,
 		 * for safety, still ask platform firmware to force
 		 * quiesce devices by default. Let a module
 		 * parameter override that policy.
 		 */
-		.cmd = {
-			.iodev_state = acpi_desc->fwa_noidle
-				? ND_INTEL_BUS_FWA_IODEV_OS_IDLE
-				: ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE,
-		},
+		.iodev_state = acpi_desc->fwa_noidle
+			? ND_INTEL_BUS_FWA_IODEV_OS_IDLE
+			: ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE,
 	};
-	int rc;
-
 	switch (intel_bus_fwa_state(nd_desc)) {
 	case NVDIMM_FWA_ARMED:
 	case NVDIMM_FWA_ARM_OVERFLOW:
@@ -582,10 +571,9 @@ const struct nvdimm_bus_fw_ops *intel_bus_fw_ops = &__intel_bus_fw_ops;
 static int intel_fwa_dimminfo(struct nvdimm *nvdimm,
 		struct nd_intel_fw_activate_dimminfo *info)
 {
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_fw_activate_dimminfo cmd;
-	} nd_cmd = {
+	) nd_cmd = {
 		.pkg = {
 			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO,
 			.nd_family = NVDIMM_FAMILY_INTEL,
@@ -688,27 +676,24 @@ static int intel_fwa_arm(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arm)
 {
 	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
-	struct {
-		struct nd_cmd_pkg pkg;
+	TRAILING_OVERLAP(struct nd_cmd_pkg, pkg, nd_payload,
 		struct nd_intel_fw_activate_arm cmd;
-	} nd_cmd = {
-		.pkg = {
-			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_ARM,
-			.nd_family = NVDIMM_FAMILY_INTEL,
-			.nd_size_in = sizeof(nd_cmd.cmd.activate_arm),
-			.nd_size_out =
-				sizeof(struct nd_intel_fw_activate_arm),
-			.nd_fw_size =
-				sizeof(struct nd_intel_fw_activate_arm),
-		},
-		.cmd = {
-			.activate_arm = arm == NVDIMM_FWA_ARM
-				? ND_INTEL_DIMM_FWA_ARM
-				: ND_INTEL_DIMM_FWA_DISARM,
-		},
-	};
+	) nd_cmd;
 	int rc;
 
+	nd_cmd.pkg = (struct nd_cmd_pkg) {
+		.nd_command = NVDIMM_INTEL_FW_ACTIVATE_ARM,
+		.nd_family = NVDIMM_FAMILY_INTEL,
+		.nd_size_in = sizeof(nd_cmd.cmd.activate_arm),
+		.nd_size_out = sizeof(struct nd_intel_fw_activate_arm),
+		.nd_fw_size = sizeof(struct nd_intel_fw_activate_arm),
+	};
+	nd_cmd.cmd = (struct nd_intel_fw_activate_arm) {
+		.activate_arm = arm == NVDIMM_FWA_ARM ?
+					ND_INTEL_DIMM_FWA_ARM :
+					ND_INTEL_DIMM_FWA_DISARM,
+	};
+
 	switch (intel_fwa_state(nvdimm)) {
 	case NVDIMM_FWA_INVALID:
 		return -ENXIO;
diff --git a/drivers/acpi/nhlt.c b/drivers/acpi/nhlt.c
new file mode 100644
index 000000000000..dc1bd0df9228
--- /dev/null
+++ b/drivers/acpi/nhlt.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2023-2024 Intel Corporation
+ *
+ * Authors: Cezary Rojewski <cezary.rojewski@intel.com>
+ *          Amadeusz Slawinski <amadeuszx.slawinski@linux.intel.com>
+ */
+
+#define pr_fmt(fmt) "ACPI: NHLT: " fmt
+
+#include <linux/acpi.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
+#include <linux/types.h>
+#include <acpi/nhlt.h>
+
+static struct acpi_table_nhlt *acpi_gbl_nhlt;
+
+static struct acpi_table_nhlt empty_nhlt = {
+	.header = {
+		.signature = ACPI_SIG_NHLT,
+	},
+};
+
+/**
+ * acpi_nhlt_get_gbl_table - Retrieve a pointer to the first NHLT table.
+ *
+ * If there is no NHLT in the system, acpi_gbl_nhlt will instead point to an
+ * empty table.
+ *
+ * Return: ACPI status code of the operation.
+ */
+acpi_status acpi_nhlt_get_gbl_table(void)
+{
+	acpi_status status;
+
+	status = acpi_get_table(ACPI_SIG_NHLT, 0, (struct acpi_table_header **)(&acpi_gbl_nhlt));
+	if (!acpi_gbl_nhlt)
+		acpi_gbl_nhlt = &empty_nhlt;
+	return status;
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_get_gbl_table);
+
+/**
+ * acpi_nhlt_put_gbl_table - Release the global NHLT table.
+ */
+void acpi_nhlt_put_gbl_table(void)
+{
+	acpi_put_table((struct acpi_table_header *)acpi_gbl_nhlt);
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_put_gbl_table);
+
+/**
+ * acpi_nhlt_endpoint_match - Verify if an endpoint matches criteria.
+ * @ep:			the endpoint to check.
+ * @link_type:		the hardware link type, e.g.: PDM or SSP.
+ * @dev_type:		the device type.
+ * @dir:		stream direction.
+ * @bus_id:		the ID of virtual bus hosting the endpoint.
+ *
+ * Either of @link_type, @dev_type, @dir or @bus_id may be set to a negative
+ * value to ignore the parameter when matching.
+ *
+ * Return: %true if endpoint matches specified criteria or %false otherwise.
+ */
+bool acpi_nhlt_endpoint_match(const struct acpi_nhlt_endpoint *ep,
+			      int link_type, int dev_type, int dir, int bus_id)
+{
+	return ep &&
+	       (link_type < 0 || ep->link_type == link_type) &&
+	       (dev_type < 0 || ep->device_type == dev_type) &&
+	       (bus_id < 0 || ep->virtual_bus_id == bus_id) &&
+	       (dir < 0 || ep->direction == dir);
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_endpoint_match);
+
+/**
+ * acpi_nhlt_tb_find_endpoint - Search a NHLT table for an endpoint.
+ * @tb:			the table to search.
+ * @link_type:		the hardware link type, e.g.: PDM or SSP.
+ * @dev_type:		the device type.
+ * @dir:		stream direction.
+ * @bus_id:		the ID of virtual bus hosting the endpoint.
+ *
+ * Either of @link_type, @dev_type, @dir or @bus_id may be set to a negative
+ * value to ignore the parameter during the search.
+ *
+ * Return: A pointer to endpoint matching the criteria, %NULL if not found or
+ * an ERR_PTR() otherwise.
+ */
+struct acpi_nhlt_endpoint *
+acpi_nhlt_tb_find_endpoint(const struct acpi_table_nhlt *tb,
+			   int link_type, int dev_type, int dir, int bus_id)
+{
+	struct acpi_nhlt_endpoint *ep;
+
+	for_each_nhlt_endpoint(tb, ep)
+		if (acpi_nhlt_endpoint_match(ep, link_type, dev_type, dir, bus_id))
+			return ep;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_tb_find_endpoint);
+
+/**
+ * acpi_nhlt_find_endpoint - Search all NHLT tables for an endpoint.
+ * @link_type:		the hardware link type, e.g.: PDM or SSP.
+ * @dev_type:		the device type.
+ * @dir:		stream direction.
+ * @bus_id:		the ID of virtual bus hosting the endpoint.
+ *
+ * Either of @link_type, @dev_type, @dir or @bus_id may be set to a negative
+ * value to ignore the parameter during the search.
+ *
+ * Return: A pointer to endpoint matching the criteria, %NULL if not found or
+ * an ERR_PTR() otherwise.
+ */
+struct acpi_nhlt_endpoint *
+acpi_nhlt_find_endpoint(int link_type, int dev_type, int dir, int bus_id)
+{
+	/* TODO: Currently limited to table of index 0. */
+	return acpi_nhlt_tb_find_endpoint(acpi_gbl_nhlt, link_type, dev_type, dir, bus_id);
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_find_endpoint);
+
+/**
+ * acpi_nhlt_endpoint_find_fmtcfg - Search endpoint's formats configuration space
+ *                                  for a specific format.
+ * @ep:			the endpoint to search.
+ * @ch:			number of channels.
+ * @rate:		samples per second.
+ * @vbps:		valid bits per sample.
+ * @bps:		bits per sample.
+ *
+ * Return: A pointer to format matching the criteria, %NULL if not found or
+ * an ERR_PTR() otherwise.
+ */
+struct acpi_nhlt_format_config *
+acpi_nhlt_endpoint_find_fmtcfg(const struct acpi_nhlt_endpoint *ep,
+			       u16 ch, u32 rate, u16 vbps, u16 bps)
+{
+	struct acpi_nhlt_wave_formatext *wav;
+	struct acpi_nhlt_format_config *fmt;
+
+	for_each_nhlt_endpoint_fmtcfg(ep, fmt) {
+		wav = &fmt->format;
+
+		if (wav->valid_bits_per_sample == vbps &&
+		    wav->samples_per_sec == rate &&
+		    wav->bits_per_sample == bps &&
+		    wav->channel_count == ch)
+			return fmt;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_endpoint_find_fmtcfg);
+
+/**
+ * acpi_nhlt_tb_find_fmtcfg - Search a NHLT table for a specific format.
+ * @tb:			the table to search.
+ * @link_type:		the hardware link type, e.g.: PDM or SSP.
+ * @dev_type:		the device type.
+ * @dir:		stream direction.
+ * @bus_id:		the ID of virtual bus hosting the endpoint.
+ *
+ * @ch:			number of channels.
+ * @rate:		samples per second.
+ * @vbps:		valid bits per sample.
+ * @bps:		bits per sample.
+ *
+ * Either of @link_type, @dev_type, @dir or @bus_id may be set to a negative
+ * value to ignore the parameter during the search.
+ *
+ * Return: A pointer to format matching the criteria, %NULL if not found or
+ * an ERR_PTR() otherwise.
+ */
+struct acpi_nhlt_format_config *
+acpi_nhlt_tb_find_fmtcfg(const struct acpi_table_nhlt *tb,
+			 int link_type, int dev_type, int dir, int bus_id,
+			 u16 ch, u32 rate, u16 vbps, u16 bps)
+{
+	struct acpi_nhlt_format_config *fmt;
+	struct acpi_nhlt_endpoint *ep;
+
+	for_each_nhlt_endpoint(tb, ep) {
+		if (!acpi_nhlt_endpoint_match(ep, link_type, dev_type, dir, bus_id))
+			continue;
+
+		fmt = acpi_nhlt_endpoint_find_fmtcfg(ep, ch, rate, vbps, bps);
+		if (fmt)
+			return fmt;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_tb_find_fmtcfg);
+
+/**
+ * acpi_nhlt_find_fmtcfg - Search all NHLT tables for a specific format.
+ * @link_type:		the hardware link type, e.g.: PDM or SSP.
+ * @dev_type:		the device type.
+ * @dir:		stream direction.
+ * @bus_id:		the ID of virtual bus hosting the endpoint.
+ *
+ * @ch:			number of channels.
+ * @rate:		samples per second.
+ * @vbps:		valid bits per sample.
+ * @bps:		bits per sample.
+ *
+ * Either of @link_type, @dev_type, @dir or @bus_id may be set to a negative
+ * value to ignore the parameter during the search.
+ *
+ * Return: A pointer to format matching the criteria, %NULL if not found or
+ * an ERR_PTR() otherwise.
+ */
+struct acpi_nhlt_format_config *
+acpi_nhlt_find_fmtcfg(int link_type, int dev_type, int dir, int bus_id,
+		      u16 ch, u32 rate, u16 vbps, u16 bps)
+{
+	/* TODO: Currently limited to table of index 0. */
+	return acpi_nhlt_tb_find_fmtcfg(acpi_gbl_nhlt, link_type, dev_type, dir, bus_id,
+					ch, rate, vbps, bps);
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_find_fmtcfg);
+
+static bool acpi_nhlt_config_is_micdevice(struct acpi_nhlt_config *cfg)
+{
+	return cfg->capabilities_size >= sizeof(struct acpi_nhlt_micdevice_config);
+}
+
+static bool acpi_nhlt_config_is_vendor_micdevice(struct acpi_nhlt_config *cfg)
+{
+	struct acpi_nhlt_vendor_micdevice_config *devcfg = __acpi_nhlt_config_caps(cfg);
+
+	return cfg->capabilities_size >= sizeof(*devcfg) &&
+	       cfg->capabilities_size == struct_size(devcfg, mics, devcfg->mics_count);
+}
+
+/**
+ * acpi_nhlt_endpoint_mic_count - Retrieve number of digital microphones for a PDM endpoint.
+ * @ep:			the endpoint to return microphones count for.
+ *
+ * Return: A number of microphones or an error code if an invalid endpoint is provided.
+ */
+int acpi_nhlt_endpoint_mic_count(const struct acpi_nhlt_endpoint *ep)
+{
+	union acpi_nhlt_device_config *devcfg;
+	struct acpi_nhlt_format_config *fmt;
+	struct acpi_nhlt_config *cfg;
+	u16 max_ch = 0;
+
+	if (!ep || ep->link_type != ACPI_NHLT_LINKTYPE_PDM)
+		return -EINVAL;
+
+	/* Find max number of channels based on formats configuration. */
+	for_each_nhlt_endpoint_fmtcfg(ep, fmt)
+		max_ch = max(fmt->format.channel_count, max_ch);
+
+	cfg = __acpi_nhlt_endpoint_config(ep);
+	devcfg = __acpi_nhlt_config_caps(cfg);
+
+	/* If @ep is not a mic array, fallback to channels count. */
+	if (!acpi_nhlt_config_is_micdevice(cfg) ||
+	    devcfg->gen.config_type != ACPI_NHLT_CONFIGTYPE_MICARRAY)
+		return max_ch;
+
+	switch (devcfg->mic.array_type) {
+	case ACPI_NHLT_ARRAYTYPE_LINEAR2_SMALL:
+	case ACPI_NHLT_ARRAYTYPE_LINEAR2_BIG:
+		return 2;
+
+	case ACPI_NHLT_ARRAYTYPE_LINEAR4_GEO1:
+	case ACPI_NHLT_ARRAYTYPE_PLANAR4_LSHAPED:
+	case ACPI_NHLT_ARRAYTYPE_LINEAR4_GEO2:
+		return 4;
+
+	case ACPI_NHLT_ARRAYTYPE_VENDOR:
+		if (!acpi_nhlt_config_is_vendor_micdevice(cfg))
+			return -EINVAL;
+		return devcfg->vendor_mic.mics_count;
+
+	default:
+		pr_warn("undefined mic array type: %#x\n", devcfg->mic.array_type);
+		return max_ch;
+	}
+}
+EXPORT_SYMBOL_GPL(acpi_nhlt_endpoint_mic_count);
diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig
index 849c2bd820b9..f33194d1e43f 100644
--- a/drivers/acpi/numa/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 config ACPI_NUMA
-	bool "NUMA support"
-	depends on NUMA
-	depends on (X86 || ARM64 || LOONGARCH)
-	default y if ARM64
+	def_bool NUMA && !X86
 
 config ACPI_HMAT
 	bool "ACPI Heterogeneous Memory Attribute Table Support"
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 9ef5f1bdcfdb..5a36d57289b4 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -58,14 +58,21 @@ struct target_cache {
 	struct node_cache_attrs cache_attrs;
 };
 
+enum {
+	NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL = ACCESS_COORDINATE_MAX,
+	NODE_ACCESS_CLASS_GENPORT_SINK_CPU,
+	NODE_ACCESS_CLASS_MAX,
+};
+
 struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs[2];
+	struct access_coordinate coord[NODE_ACCESS_CLASS_MAX];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
+	u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
 	bool registered;
 };
 
@@ -100,6 +107,90 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+/**
+ * hmat_get_extended_linear_cache_size - Retrieve the extended linear cache size
+ * @backing_res: resource from the backing media
+ * @nid: node id for the memory region
+ * @cache_size: (Output) size of extended linear cache.
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ */
+int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid,
+					resource_size_t *cache_size)
+{
+	unsigned int pxm = node_to_pxm(nid);
+	struct memory_target *target;
+	struct target_cache *tcache;
+	struct resource *res;
+
+	target = find_mem_target(pxm);
+	if (!target)
+		return -ENOENT;
+
+	list_for_each_entry(tcache, &target->caches, node) {
+		if (tcache->cache_attrs.address_mode !=
+				NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR)
+			continue;
+
+		res = &target->memregions;
+		if (!resource_contains(res, backing_res))
+			continue;
+
+		*cache_size = tcache->cache_attrs.size;
+		return 0;
+	}
+
+	*cache_size = 0;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(hmat_get_extended_linear_cache_size, "CXL");
+
+static struct memory_target *acpi_find_genport_target(u32 uid)
+{
+	struct memory_target *target;
+	u32 target_uid;
+	u8 *uid_ptr;
+
+	list_for_each_entry(target, &targets, node) {
+		uid_ptr = target->gen_port_device_handle + 8;
+		target_uid = *(u32 *)uid_ptr;
+		if (uid == target_uid)
+			return target;
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
+ * @uid: ACPI unique id
+ * @coord: The access coordinates written back out for the generic port.
+ *	   Expect 2 levels array.
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL.
+ */
+int acpi_get_genport_coordinates(u32 uid,
+				 struct access_coordinate *coord)
+{
+	struct memory_target *target;
+
+	guard(mutex)(&target_lock);
+	target = acpi_find_genport_target(uid);
+	if (!target)
+		return -ENOENT;
+
+	coord[ACCESS_COORDINATE_LOCAL] =
+		target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL];
+	coord[ACCESS_COORDINATE_CPU] =
+		target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_CPU];
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, "CXL");
+
 static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 {
 	struct memory_initiator *initiator;
@@ -120,8 +211,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm,
-		resource_size_t start, resource_size_t len)
+static __init struct memory_target *alloc_target(unsigned int mem_pxm)
 {
 	struct memory_target *target;
 
@@ -129,7 +219,7 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 	if (!target) {
 		target = kzalloc(sizeof(*target), GFP_KERNEL);
 		if (!target)
-			return;
+			return NULL;
 		target->memory_pxm = mem_pxm;
 		target->processor_pxm = PXM_INVAL;
 		target->memregions = (struct resource) {
@@ -142,6 +232,19 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 		INIT_LIST_HEAD(&target->caches);
 	}
 
+	return target;
+}
+
+static __init void alloc_memory_target(unsigned int mem_pxm,
+				       resource_size_t start,
+				       resource_size_t len)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
 	/*
 	 * There are potentially multiple ranges per PXM, so record each
 	 * in the per-target memregions resource tree.
@@ -152,6 +255,18 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 				start, start + len, mem_pxm);
 }
 
+static __init void alloc_genport_target(unsigned int mem_pxm, u8 *handle)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
+	memcpy(target->gen_port_device_handle, handle,
+	       ACPI_SRAT_DEVICE_HANDLE_SIZE);
+}
+
 static __init const char *hmat_data_type(u8 type)
 {
 	switch (type) {
@@ -228,24 +343,24 @@ static void hmat_update_target_access(struct memory_target *target,
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].read_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
+		target->coord[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -291,11 +406,28 @@ static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
 	}
 }
 
+static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_pxm,
+				      u8 mem_hier, u8 type, u32 value)
+{
+	struct memory_target *target = find_mem_target(tgt_pxm);
+
+	if (mem_hier != ACPI_HMAT_MEMORY)
+		return;
+
+	if (target && target->processor_pxm == init_pxm) {
+		hmat_update_target_access(target, type, value,
+					  ACCESS_COORDINATE_LOCAL);
+		/* If the node has a CPU, update access ACCESS_COORDINATE_CPU */
+		if (node_state(pxm_to_node(init_pxm), N_CPU))
+			hmat_update_target_access(target, type, value,
+						  ACCESS_COORDINATE_CPU);
+	}
+}
+
 static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {
 	struct acpi_hmat_locality *hmat_loc = (void *)header;
-	struct memory_target *target;
 	unsigned int init, targ, total_size, ipds, tpds;
 	u32 *inits, *targs, value;
 	u16 *entries;
@@ -319,9 +451,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
-		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
-		hmat_loc->entry_base_unit);
+	pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
+		 hmat_loc->flags, hmat_data_type(type), ipds, tpds,
+		 hmat_loc->entry_base_unit);
 
 	inits = (u32 *)(hmat_loc + 1);
 	targs = inits + ipds;
@@ -332,19 +464,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			value = hmat_normalize(entries[init * tpds + targ],
 					       hmat_loc->entry_base_unit,
 					       type);
-			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
-				inits[init], targs[targ], value,
-				hmat_data_type_suffix(type));
-
-			if (mem_hier == ACPI_HMAT_MEMORY) {
-				target = find_mem_target(targs[targ]);
-				if (target && target->processor_pxm == inits[init]) {
-					hmat_update_target_access(target, type, value, 0);
-					/* If the node has a CPU, update access 1 */
-					if (node_state(pxm_to_node(inits[init]), N_CPU))
-						hmat_update_target_access(target, type, value, 1);
-				}
-			}
+			pr_debug("  Initiator-Target[%u-%u]:%u%s\n",
+				 inits[init], targs[targ], value,
+				 hmat_data_type_suffix(type));
+
+			hmat_update_target(targs[targ], inits[init],
+					   mem_hier, type, value);
 		}
 	}
 
@@ -369,9 +494,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
-		cache->memory_PD, cache->cache_size, attrs,
-		cache->number_of_SMBIOShandles);
+	pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+		 cache->memory_PD, cache->cache_size, attrs,
+		 cache->number_of_SMBIOShandles);
 
 	target = find_mem_target(cache->memory_PD);
 	if (!target)
@@ -390,6 +515,11 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	switch ((attrs & ACPI_HMAT_CACHE_ASSOCIATIVITY) >> 8) {
 	case ACPI_HMAT_CA_DIRECT_MAPPED:
 		tcache->cache_attrs.indexing = NODE_CACHE_DIRECT_MAP;
+		/* Extended Linear mode is only valid if cache is direct mapped */
+		if (cache->address_mode == ACPI_HMAT_CACHE_MODE_EXTENDED_LINEAR) {
+			tcache->cache_attrs.address_mode =
+				NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR;
+		}
 		break;
 	case ACPI_HMAT_CA_COMPLEX_CACHE_INDEXING:
 		tcache->cache_attrs.indexing = NODE_CACHE_INDEXED;
@@ -430,9 +560,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	}
 
 	if (hmat_revision == 1)
-		pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
-			p->reserved3, p->reserved4, p->flags, p->processor_PD,
-			p->memory_PD);
+		pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
+			 p->reserved3, p->reserved4, p->flags, p->processor_PD,
+			 p->memory_PD);
 	else
 		pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
@@ -491,6 +621,27 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+static __init int srat_parse_genport_affinity(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *ga = (void *)header;
+
+	if (!ga)
+		return -EINVAL;
+
+	if (!(ga->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return 0;
+
+	/* Skip PCI device_handle for now */
+	if (ga->device_handle_type != 0)
+		return 0;
+
+	alloc_genport_target(ga->proximity_domain,
+			     (u8 *)ga->device_handle);
+
+	return 0;
+}
+
 static u32 hmat_initiator_perf(struct memory_target *target,
 			       struct memory_initiator *initiator,
 			       struct acpi_hmat_locality *hmat_loc)
@@ -592,6 +743,12 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	u32 best = 0;
 	int i;
 
+	/* Don't update for generic port if there's no device handle */
+	if ((access == NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL ||
+	     access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
+	    !(*(u16 *)target->gen_port_device_handle))
+		return;
+
 	bitmap_zero(p_nodes, MAX_NUMNODES);
 	/*
 	 * If the Address Range Structure provides a local processor pxm, set
@@ -600,7 +757,8 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	 */
 	if (target->processor_pxm != PXM_INVAL) {
 		cpu_nid = pxm_to_node(target->processor_pxm);
-		if (access == 0 || node_state(cpu_nid, N_CPU)) {
+		if (access == ACCESS_COORDINATE_LOCAL ||
+		    node_state(cpu_nid, N_CPU)) {
 			set_bit(target->processor_pxm, p_nodes);
 			return;
 		}
@@ -628,7 +786,9 @@ static void hmat_update_target_attrs(struct memory_target *target,
 		list_for_each_entry(initiator, &initiators, node) {
 			u32 value;
 
-			if (access == 1 && !initiator->has_cpu) {
+			if ((access == ACCESS_COORDINATE_CPU ||
+			     access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
+			    !initiator->has_cpu) {
 				clear_bit(initiator->processor_pxm, p_nodes);
 				continue;
 			}
@@ -661,12 +821,24 @@ static void __hmat_register_target_initiators(struct memory_target *target,
 	}
 }
 
+static void hmat_update_generic_target(struct memory_target *target)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+
+	hmat_update_target_attrs(target, p_nodes,
+				 NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL);
+	hmat_update_target_attrs(target, p_nodes,
+				 NODE_ACCESS_CLASS_GENPORT_SINK_CPU);
+}
+
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 
-	__hmat_register_target_initiators(target, p_nodes, 0);
-	__hmat_register_target_initiators(target, p_nodes, 1);
+	__hmat_register_target_initiators(target, p_nodes,
+					  ACCESS_COORDINATE_LOCAL);
+	__hmat_register_target_initiators(target, p_nodes,
+					  ACCESS_COORDINATE_CPU);
 }
 
 static void hmat_register_target_cache(struct memory_target *target)
@@ -681,7 +853,7 @@ static void hmat_register_target_cache(struct memory_target *target)
 static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
+	node_set_perf_attrs(mem_nid, &target->coord[access], access);
 }
 
 static void hmat_register_target_devices(struct memory_target *target)
@@ -713,6 +885,17 @@ static void hmat_register_target(struct memory_target *target)
 	hmat_register_target_devices(target);
 
 	/*
+	 * Register generic port perf numbers. The nid may not be
+	 * initialized and is still NUMA_NO_NODE.
+	 */
+	mutex_lock(&target_lock);
+	if (*(u16 *)target->gen_port_device_handle) {
+		hmat_update_generic_target(target);
+		target->registered = true;
+	}
+	mutex_unlock(&target_lock);
+
+	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
 	 * to all the memory in a proximity domain leading to
@@ -726,8 +909,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target, 0);
-		hmat_register_target_perf(target, 1);
+		hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL);
+		hmat_register_target_perf(target, ACCESS_COORDINATE_CPU);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
@@ -745,10 +928,10 @@ static int hmat_callback(struct notifier_block *self,
 			 unsigned long action, void *arg)
 {
 	struct memory_target *target;
-	struct memory_notify *mnb = arg;
-	int pxm, nid = mnb->status_change_nid;
+	struct node_notify *nn = arg;
+	int pxm, nid = nn->nid;
 
-	if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
+	if (action != NODE_ADDED_FIRST_MEMORY)
 		return NOTIFY_OK;
 
 	pxm = node_to_pxm(nid);
@@ -760,22 +943,19 @@ static int hmat_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static int hmat_set_default_dram_perf(void)
+static int __init hmat_set_default_dram_perf(void)
 {
 	int rc;
 	int nid, pxm;
 	struct memory_target *target;
-	struct node_hmem_attrs *attrs;
-
-	if (!default_dram_type)
-		return -EIO;
+	struct access_coordinate *attrs;
 
-	for_each_node_mask(nid, default_dram_type->nodes) {
+	for_each_node_mask(nid, default_dram_nodes) {
 		pxm = node_to_pxm(nid);
 		target = find_mem_target(pxm);
 		if (!target)
 			continue;
-		attrs = &target->hmem_attrs[1];
+		attrs = &target->coord[ACCESS_COORDINATE_CPU];
 		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
 		if (rc)
 			return rc;
@@ -789,7 +969,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 	struct memory_target *target;
-	struct node_hmem_attrs *perf;
+	struct access_coordinate *perf;
 	int *adist = data;
 	int pxm;
 
@@ -799,10 +979,10 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 		return NOTIFY_OK;
 
 	mutex_lock(&target_lock);
-	hmat_update_target_attrs(target, p_nodes, 1);
+	hmat_update_target_attrs(target, p_nodes, ACCESS_COORDINATE_CPU);
 	mutex_unlock(&target_lock);
 
-	perf = &target->hmem_attrs[1];
+	perf = &target->coord[ACCESS_COORDINATE_CPU];
 
 	if (mt_perf_to_adistance(perf, adist))
 		return NOTIFY_OK;
@@ -870,6 +1050,13 @@ static __init int hmat_init(void)
 				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 				srat_parse_mem_affinity, 0) < 0)
 		goto out_put;
+
+	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
+				     sizeof(struct acpi_table_srat),
+				     ACPI_SRAT_TYPE_GENERIC_PORT_AFFINITY,
+				     srat_parse_genport_affinity, 0) < 0)
+		goto out_put;
+
 	acpi_put_table(tbl);
 
 	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
@@ -897,7 +1084,7 @@ static __init int hmat_init(void)
 	hmat_register_targets();
 
 	/* Keep the table and structures if the notifier may use them */
-	if (hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
+	if (hotplug_node_notifier(hmat_callback, HMAT_CALLBACK_PRI))
 		goto out_put;
 
 	if (!hmat_set_default_dram_perf())
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 12f330b0eac0..53816dfab645 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -14,9 +14,12 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/memblock.h>
+#include <linux/memory.h>
 #include <linux/numa.h>
 #include <linux/nodemask.h>
 #include <linux/topology.h>
+#include <linux/numa_memblks.h>
+#include <linux/string_choices.h>
 
 static nodemask_t nodes_found_map = NODE_MASK_NONE;
 
@@ -29,6 +32,8 @@ static int node_to_pxm_map[MAX_NUMNODES]
 unsigned char acpi_srat_revision __initdata;
 static int acpi_numa __initdata;
 
+static int last_real_pxm;
+
 void __init disable_srat(void)
 {
 	acpi_numa = -1;
@@ -48,6 +53,7 @@ int node_to_pxm(int node)
 		return PXM_INVAL;
 	return node_to_pxm_map[node];
 }
+EXPORT_SYMBOL_GPL(node_to_pxm);
 
 static void __acpi_map_pxm_to_node(int pxm, int node)
 {
@@ -67,9 +73,9 @@ int acpi_map_pxm_to_node(int pxm)
 	node = pxm_to_node_map[pxm];
 
 	if (node == NUMA_NO_NODE) {
-		if (nodes_weight(nodes_found_map) >= MAX_NUMNODES)
-			return NUMA_NO_NODE;
 		node = first_unset_node(nodes_found_map);
+		if (node >= MAX_NUMNODES)
+			return NUMA_NO_NODE;
 		__acpi_map_pxm_to_node(pxm, node);
 		node_set(node, nodes_found_map);
 	}
@@ -78,6 +84,101 @@ int acpi_map_pxm_to_node(int pxm)
 }
 EXPORT_SYMBOL(acpi_map_pxm_to_node);
 
+#ifdef CONFIG_NUMA_EMU
+/*
+ * Take max_nid - 1 fake-numa nodes into account in both
+ * pxm_to_node_map()/node_to_pxm_map[] tables.
+ */
+int __init fix_pxm_node_maps(int max_nid)
+{
+	static int pxm_to_node_map_copy[MAX_PXM_DOMAINS] __initdata
+			= { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE };
+	static int node_to_pxm_map_copy[MAX_NUMNODES] __initdata
+			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
+	int i, j, index = -1, count = 0;
+	nodemask_t nodes_to_enable;
+
+	if (numa_off)
+		return -1;
+
+	/* no or incomplete node/PXM mapping set, nothing to do */
+	if (srat_disabled())
+		return 0;
+
+	/* find fake nodes PXM mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++) {
+				if ((emu_nid_to_phys[j] == i) &&
+				    WARN(node_to_pxm_map_copy[j] != PXM_INVAL,
+					 "Node %d is already binded to PXM %d\n",
+					 j, node_to_pxm_map_copy[j]))
+					return -1;
+				if (emu_nid_to_phys[j] == i) {
+					node_to_pxm_map_copy[j] =
+						node_to_pxm_map[i];
+					if (j > index)
+						index = j;
+					count++;
+				}
+			}
+		}
+	}
+	if (index == -1) {
+		pr_debug("No node/PXM mapping has been set\n");
+		/* nothing more to be done */
+		return 0;
+	}
+	if (WARN(index != max_nid, "%d max nid  when expected %d\n",
+		      index, max_nid))
+		return -1;
+
+	nodes_clear(nodes_to_enable);
+
+	/* map phys nodes not used for fake nodes */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++)
+				if (emu_nid_to_phys[j] == i)
+					break;
+			/* fake nodes PXM mapping has been done */
+			if (j <= max_nid)
+				continue;
+			/* find first hole */
+			for (j = 0;
+			     j < MAX_NUMNODES &&
+				 node_to_pxm_map_copy[j] != PXM_INVAL;
+			     j++)
+			;
+			if (WARN(j == MAX_NUMNODES,
+			    "Number of nodes exceeds MAX_NUMNODES\n"))
+				return -1;
+			node_to_pxm_map_copy[j] = node_to_pxm_map[i];
+			node_set(j, nodes_to_enable);
+			count++;
+		}
+	}
+
+	/* creating reverse mapping in pxm_to_node_map[] */
+	for (i = 0; i < MAX_NUMNODES; i++)
+		if (node_to_pxm_map_copy[i] != PXM_INVAL &&
+		    pxm_to_node_map_copy[node_to_pxm_map_copy[i]] == NUMA_NO_NODE)
+			pxm_to_node_map_copy[node_to_pxm_map_copy[i]] = i;
+
+	/* overwrite with new mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		node_to_pxm_map[i] = node_to_pxm_map_copy[i];
+		pxm_to_node_map[i] = pxm_to_node_map_copy[i];
+	}
+
+	/* enable other nodes found in PXM for hotplug */
+	nodes_or(numa_nodes_parsed, nodes_to_enable, numa_nodes_parsed);
+
+	pr_debug("found %d total number of nodes\n", count);
+	return 0;
+}
+#endif
+
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
@@ -89,8 +190,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
 				 p->apic_id, p->local_sapic_eid,
 				 p->proximity_domain_lo,
-				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_CPU_ENABLED));
 		}
 		break;
 
@@ -102,8 +202,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				 (unsigned long long)p->base_address,
 				 (unsigned long long)p->length,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_MEM_ENABLED) ?
-				 "enabled" : "disabled",
+				 str_enabled_disabled(p->flags & ACPI_SRAT_MEM_ENABLED),
 				 (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
 				 " hot-pluggable" : "",
 				 (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
@@ -118,8 +217,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
 				 p->apic_id,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_CPU_ENABLED));
 		}
 		break;
 
@@ -130,8 +228,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
 				 p->acpi_processor_uid,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_GICC_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_GICC_ENABLED));
 		}
 		break;
 
@@ -149,8 +246,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				 *(u16 *)(&p->device_handle[0]),
 				 *(u16 *)(&p->device_handle[2]),
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
-				"enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED));
 		} else {
 			/*
 			 * In this case we can rely on the device having a
@@ -160,11 +256,22 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				(char *)(&p->device_handle[0]),
 				(char *)(&p->device_handle[8]),
 				p->proximity_domain,
-				(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
-				"enabled" : "disabled");
+				str_enabled_disabled(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED));
 		}
 	}
 	break;
+
+	case ACPI_SRAT_TYPE_RINTC_AFFINITY:
+		{
+			struct acpi_srat_rintc_affinity *p =
+			    (struct acpi_srat_rintc_affinity *)header;
+			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+				 p->acpi_processor_uid,
+				 p->proximity_domain,
+				 str_enabled_disabled(p->flags & ACPI_SRAT_RINTC_ENABLED));
+		}
+		break;
+
 	default:
 		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
 			header->type);
@@ -183,7 +290,7 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 	int i, j;
 	int d = slit->locality_count;
 	for (i = 0; i < d; i++) {
-		for (j = 0; j < d; j++)  {
+		for (j = 0; j < d; j++) {
 			u8 val = slit->entry[d*i + j];
 			if (i == j) {
 				if (val != LOCAL_DISTANCE)
@@ -206,16 +313,26 @@ int __init srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH)
+__weak int __init numa_fill_memblks(u64 start, u64 end)
+{
+	return NUMA_NO_MEMBLK;
+}
+
 /*
  * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
  * I/O localities since SRAT does not list them.  I/O localities are
  * not supported at this point.
  */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
+static int __init acpi_parse_slit(struct acpi_table_header *table)
 {
+	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
 	int i, j;
 
+	if (!slit_valid(slit)) {
+		pr_info("SLIT table looks invalid. Not used.\n");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < slit->locality_count; i++) {
 		const int from_node = pxm_to_node(i);
 
@@ -232,28 +349,34 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 				slit->entry[slit->locality_count * i + j]);
 		}
 	}
+
+	return 0;
 }
 
-/*
- * Default callback for parsing of the Proximity Domain <-> Memory
- * Area mappings
- */
-int __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
+static int parsed_numa_memblks __initdata;
+
+static int __init
+acpi_parse_memory_affinity(union acpi_subtable_headers *header,
+			   const unsigned long table_end)
 {
+	struct acpi_srat_mem_affinity *ma;
 	u64 start, end;
 	u32 hotpluggable;
 	int node, pxm;
 
+	ma = (struct acpi_srat_mem_affinity *)header;
+
+	acpi_table_print_srat_entry(&header->common);
+
 	if (srat_disabled())
-		goto out_err;
+		return 0;
 	if (ma->header.length < sizeof(struct acpi_srat_mem_affinity)) {
 		pr_err("SRAT: Unexpected header length: %d\n",
 		       ma->header.length);
 		goto out_err_bad_srat;
 	}
 	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-		goto out_err;
+		return 0;
 	hotpluggable = IS_ENABLED(CONFIG_MEMORY_HOTPLUG) &&
 		(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE);
 
@@ -291,11 +414,15 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
 
+	parsed_numa_memblks++;
+
 	return 0;
+
 out_err_bad_srat:
+	/* Just disable SRAT, but do not fail and ignore errors. */
 	bad_srat();
-out_err:
-	return -EINVAL;
+
+	return 0;
 }
 
 static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
@@ -303,13 +430,23 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 {
 	struct acpi_cedt_cfmws *cfmws;
 	int *fake_pxm = arg;
-	u64 start, end;
+	u64 start, end, align;
 	int node;
+	int err;
 
 	cfmws = (struct acpi_cedt_cfmws *)header;
 	start = cfmws->base_hpa;
 	end = cfmws->base_hpa + cfmws->window_size;
 
+	/* Align memblock size to CFMW regions if possible */
+	align = 1UL << __ffs(start | end);
+	if (align >= SZ_256M) {
+		err = memory_block_advise_max_size(align);
+		if (err)
+			pr_warn("CFMWS: memblock size advise failed (%d)\n", err);
+	} else
+		pr_err("CFMWS: [BIOS BUG] base/size alignment violates spec\n");
+
 	/*
 	 * The SRAT may have already described NUMA details for all,
 	 * or a portion of, this CFMWS HPA range. Extend the memblks
@@ -327,7 +464,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	if (numa_add_memblk(node, start, end) < 0) {
+	if (numa_add_reserved_memblk(node, start, end) < 0) {
 		/* CXL driver must handle the NUMA_NO_NODE case */
 		pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n",
 			node, start, end);
@@ -338,26 +475,6 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 	(*fake_pxm)++;
 	return 0;
 }
-#else
-static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
-				   void *arg, const unsigned long table_end)
-{
-	return 0;
-}
-#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
-
-static int __init acpi_parse_slit(struct acpi_table_header *table)
-{
-	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
-
-	if (!slit_valid(slit)) {
-		pr_info("SLIT table looks invalid. Not used.\n");
-		return -EINVAL;
-	}
-	acpi_numa_slit_init(slit);
-
-	return 0;
-}
 
 void __init __weak
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -430,7 +547,7 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header,
 		return -EINVAL;
 
 	node = acpi_map_pxm_to_node(gi_affinity->proximity_domain);
-	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+	if (node == NUMA_NO_NODE) {
 		pr_err("SRAT: Too many proximity domains.\n");
 		return -EINVAL;
 	}
@@ -448,21 +565,18 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header,
 }
 #endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
 
-static int __initdata parsed_numa_memblks;
-
 static int __init
-acpi_parse_memory_affinity(union acpi_subtable_headers * header,
-			   const unsigned long end)
+acpi_parse_rintc_affinity(union acpi_subtable_headers *header,
+			  const unsigned long end)
 {
-	struct acpi_srat_mem_affinity *memory_affinity;
-
-	memory_affinity = (struct acpi_srat_mem_affinity *)header;
+	struct acpi_srat_rintc_affinity *rintc_affinity;
 
+	rintc_affinity = (struct acpi_srat_rintc_affinity *)header;
 	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
-	if (!acpi_numa_memory_affinity_init(memory_affinity))
-		parsed_numa_memblks++;
+	acpi_numa_rintc_affinity_init(rintc_affinity);
+
 	return 0;
 }
 
@@ -501,7 +615,7 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: System Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[4];
+		struct acpi_subtable_proc srat_proc[5];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
@@ -512,6 +626,8 @@ int __init acpi_numa_init(void)
 		srat_proc[2].handler = acpi_parse_gicc_affinity;
 		srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY;
 		srat_proc[3].handler = acpi_parse_gi_affinity;
+		srat_proc[4].id = ACPI_SRAT_TYPE_RINTC_AFFINITY;
+		srat_proc[4].handler = acpi_parse_rintc_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),
@@ -532,10 +648,11 @@ int __init acpi_numa_init(void)
 	 */
 
 	/* fake_pxm is the next unused PXM value after SRAT parsing */
-	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES - 1; i++) {
+	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) {
 		if (node_to_pxm_map[i] > fake_pxm)
 			fake_pxm = node_to_pxm_map[i];
 	}
+	last_real_pxm = fake_pxm;
 	fake_pxm++;
 	acpi_table_parse_cedt(ACPI_CEDT_TYPE_CFMWS, acpi_parse_cfmws,
 			      &fake_pxm);
@@ -547,6 +664,14 @@ int __init acpi_numa_init(void)
 	return 0;
 }
 
+bool acpi_node_backed_by_real_pxm(int nid)
+{
+	int pxm = node_to_pxm(nid);
+
+	return pxm <= last_real_pxm;
+}
+EXPORT_SYMBOL_GPL(acpi_node_backed_by_real_pxm);
+
 static int acpi_get_pxm(acpi_handle h)
 {
 	unsigned long long pxm;
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index df9328c850bd..f2c943b934be 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -42,7 +42,6 @@ static struct acpi_osi_entry
 osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	{"Module Device", true},
 	{"Processor Device", true},
-	{"3.0 _SCP Extensions", true},
 	{"Processor Aggregator Device", true},
 };
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c09cc3c68633..5ff343096ece 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -544,11 +544,7 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
 
 static irqreturn_t acpi_irq(int irq, void *dev_id)
 {
-	u32 handled;
-
-	handled = (*acpi_irq_handler) (acpi_irq_context);
-
-	if (handled) {
+	if ((*acpi_irq_handler)(acpi_irq_context)) {
 		acpi_irq_handled++;
 		return IRQ_HANDLED;
 	} else {
@@ -582,7 +578,8 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler,
 
 	acpi_irq_handler = handler;
 	acpi_irq_context = context;
-	if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) {
+	if (request_threaded_irq(irq, NULL, acpi_irq, IRQF_SHARED | IRQF_ONESHOT,
+			         "acpi", acpi_irq)) {
 		pr_err("SCI (IRQ%d) allocation failed\n", irq);
 		acpi_irq_handler = NULL;
 		return AE_NOT_ACQUIRED;
@@ -610,7 +607,27 @@ acpi_status acpi_os_remove_interrupt_handler(u32 gsi, acpi_osd_handler handler)
 
 void acpi_os_sleep(u64 ms)
 {
-	msleep(ms);
+	u64 usec = ms * USEC_PER_MSEC, delta_us = 50;
+
+	/*
+	 * Use a hrtimer because the timer wheel timers are optimized for
+	 * cancelation before they expire and this timer is not going to be
+	 * canceled.
+	 *
+	 * Set the delta between the requested sleep time and the effective
+	 * deadline to at least 50 us in case there is an opportunity for timer
+	 * coalescing.
+	 *
+	 * Moreover, longer sleeps can be assumed to need somewhat less timer
+	 * precision, so sacrifice some of it for making the timer a more likely
+	 * candidate for coalescing by setting the delta to 1% of the sleep time
+	 * if it is above 5 ms (this value is chosen so that the delta is a
+	 * continuous function of the sleep time).
+	 */
+	if (ms > 5)
+		delta_us = (USEC_PER_MSEC / 100) * ms;
+
+	usleep_range(usec, usec + delta_us);
 }
 
 void acpi_os_stall(u32 us)
@@ -645,6 +662,15 @@ acpi_status acpi_os_read_port(acpi_io_address port, u32 *value, u32 width)
 {
 	u32 dummy;
 
+	if (!IS_ENABLED(CONFIG_HAS_IOPORT)) {
+		/*
+		 * set all-1 result as if reading from non-existing
+		 * I/O port
+		 */
+		*value = GENMASK(width, 0);
+		return AE_NOT_IMPLEMENTED;
+	}
+
 	if (value)
 		*value = 0;
 	else
@@ -668,6 +694,9 @@ EXPORT_SYMBOL(acpi_os_read_port);
 
 acpi_status acpi_os_write_port(acpi_io_address port, u32 value, u32 width)
 {
+	if (!IS_ENABLED(CONFIG_HAS_IOPORT))
+		return AE_NOT_IMPLEMENTED;
+
 	if (width <= 8) {
 		outb(value, port);
 	} else if (width <= 16) {
@@ -1063,9 +1092,7 @@ int __init acpi_debugger_init(void)
 acpi_status acpi_os_execute(acpi_execute_type type,
 			    acpi_osd_exec_callback function, void *context)
 {
-	acpi_status status = AE_OK;
 	struct acpi_os_dpc *dpc;
-	struct workqueue_struct *queue;
 	int ret;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
@@ -1076,9 +1103,9 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 		ret = acpi_debugger_create_thread(function, context);
 		if (ret) {
 			pr_err("Kernel thread creation failed\n");
-			status = AE_ERROR;
+			return AE_ERROR;
 		}
-		goto out_thread;
+		return AE_OK;
 	}
 
 	/*
@@ -1096,43 +1123,41 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 
 	dpc->function = function;
 	dpc->context = context;
+	INIT_WORK(&dpc->work, acpi_os_execute_deferred);
 
 	/*
 	 * To prevent lockdep from complaining unnecessarily, make sure that
 	 * there is a different static lockdep key for each workqueue by using
 	 * INIT_WORK() for each of them separately.
 	 */
-	if (type == OSL_NOTIFY_HANDLER) {
-		queue = kacpi_notify_wq;
-		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	} else if (type == OSL_GPE_HANDLER) {
-		queue = kacpid_wq;
-		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	} else {
+	switch (type) {
+	case OSL_NOTIFY_HANDLER:
+		ret = queue_work(kacpi_notify_wq, &dpc->work);
+		break;
+	case OSL_GPE_HANDLER:
+		/*
+		 * On some machines, a software-initiated SMI causes corruption
+		 * unless the SMI runs on CPU 0.  An SMI can be initiated by
+		 * any AML, but typically it's done in GPE-related methods that
+		 * are run via workqueues, so we can avoid the known corruption
+		 * cases by always queueing on CPU 0.
+		 */
+		ret = queue_work_on(0, kacpid_wq, &dpc->work);
+		break;
+	default:
 		pr_err("Unsupported os_execute type %d.\n", type);
-		status = AE_ERROR;
+		goto err;
 	}
-
-	if (ACPI_FAILURE(status))
-		goto err_workqueue;
-
-	/*
-	 * On some machines, a software-initiated SMI causes corruption unless
-	 * the SMI runs on CPU 0.  An SMI can be initiated by any AML, but
-	 * typically it's done in GPE-related methods that are run via
-	 * workqueues, so we can avoid the known corruption cases by always
-	 * queueing on CPU 0.
-	 */
-	ret = queue_work_on(0, queue, &dpc->work);
 	if (!ret) {
 		pr_err("Unable to queue work\n");
-		status = AE_ERROR;
+		goto err;
 	}
-err_workqueue:
-	if (ACPI_FAILURE(status))
-		kfree(dpc);
-out_thread:
-	return status;
+
+	return AE_OK;
+
+err:
+	kfree(dpc);
+	return AE_ERROR;
 }
 EXPORT_SYMBOL(acpi_os_execute);
 
@@ -1522,20 +1547,18 @@ void acpi_os_delete_lock(acpi_spinlock handle)
 acpi_cpu_flags acpi_os_acquire_lock(acpi_spinlock lockp)
 	__acquires(lockp)
 {
-	acpi_cpu_flags flags;
-
-	spin_lock_irqsave(lockp, flags);
-	return flags;
+	spin_lock(lockp);
+	return 0;
 }
 
 /*
  * Release a spinlock. See above.
  */
 
-void acpi_os_release_lock(acpi_spinlock lockp, acpi_cpu_flags flags)
+void acpi_os_release_lock(acpi_spinlock lockp, acpi_cpu_flags not_used)
 	__releases(lockp)
 {
-	spin_unlock_irqrestore(lockp, flags);
+	spin_unlock(lockp);
 }
 
 #ifndef ACPI_USE_LOCAL_CACHE
@@ -1672,7 +1695,7 @@ acpi_status __init acpi_os_initialize(void)
 acpi_status __init acpi_os_initialize1(void)
 {
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
-	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
+	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 0);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
 	BUG_ON(!kacpid_wq);
 	BUG_ON(!kacpi_notify_wq);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index ff30ceca2203..ad81aa03fe2f 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -22,6 +22,7 @@
 #include <linux/acpi.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/string_choices.h>
 
 struct acpi_prt_entry {
 	struct acpi_pci_id	id;
@@ -288,7 +289,7 @@ static int acpi_reroute_boot_interrupt(struct pci_dev *dev,
 }
 #endif /* CONFIG_X86_IO_APIC */
 
-static struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
 {
 	struct acpi_prt_entry *entry = NULL;
 	struct pci_dev *bridge;
@@ -468,7 +469,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "PCI INT %c%s -> GSI %u (%s, %s) -> IRQ %d\n",
 		pin_name(pin), link_desc, gsi,
 		(triggering == ACPI_LEVEL_SENSITIVE) ? "level" : "edge",
-		(polarity == ACPI_ACTIVE_LOW) ? "low" : "high", dev->irq);
+		str_low_high(polarity == ACPI_ACTIVE_LOW), dev->irq);
 
 	kfree(entry);
 	return 0;
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index aa1038b8aec4..e4560b33b8ad 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -268,7 +268,7 @@ static int acpi_pci_link_get_current(struct acpi_pci_link *link)
 
 	link->irq.active = irq;
 
-	acpi_handle_debug(handle, "Link at IRQ %d \n", link->irq.active);
+	acpi_handle_debug(handle, "Link at IRQ %d\n", link->irq.active);
 
       end:
 	return result;
@@ -714,8 +714,8 @@ static int acpi_pci_link_add(struct acpi_device *device,
 		return -ENOMEM;
 
 	link->device = device;
-	strcpy(acpi_device_name(device), ACPI_PCI_LINK_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_PCI_LINK_CLASS);
+	strscpy(acpi_device_name(device), ACPI_PCI_LINK_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_PCI_LINK_CLASS);
 	device->driver_data = link;
 
 	mutex_lock(&acpi_link_lock);
@@ -748,6 +748,8 @@ static int acpi_pci_link_add(struct acpi_device *device,
 	if (result)
 		kfree(link);
 
+	acpi_dev_clear_dependencies(device);
+
 	return result < 0 ? result : 1;
 }
 
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index 860014b89b8e..58e10a980114 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -181,6 +181,18 @@ static struct mcfg_fixup mcfg_quirks[] = {
 	LOONGSON_ECAM_MCFG("LOONGSON", 0),
 	LOONGSON_ECAM_MCFG("\0", 1),
 	LOONGSON_ECAM_MCFG("LOONGSON", 1),
+	LOONGSON_ECAM_MCFG("\0", 2),
+	LOONGSON_ECAM_MCFG("LOONGSON", 2),
+	LOONGSON_ECAM_MCFG("\0", 3),
+	LOONGSON_ECAM_MCFG("LOONGSON", 3),
+	LOONGSON_ECAM_MCFG("\0", 4),
+	LOONGSON_ECAM_MCFG("LOONGSON", 4),
+	LOONGSON_ECAM_MCFG("\0", 5),
+	LOONGSON_ECAM_MCFG("LOONGSON", 5),
+	LOONGSON_ECAM_MCFG("\0", 6),
+	LOONGSON_ECAM_MCFG("LOONGSON", 6),
+	LOONGSON_ECAM_MCFG("\0", 7),
+	LOONGSON_ECAM_MCFG("LOONGSON", 7),
 #endif /* LOONGARCH */
 };
 
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 58b89b8d950e..74ade4160314 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -293,11 +293,6 @@ struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle)
 }
 EXPORT_SYMBOL_GPL(acpi_pci_find_root);
 
-struct acpi_handle_node {
-	struct list_head node;
-	acpi_handle handle;
-};
-
 /**
  * acpi_get_pci_dev - convert ACPI CA handle to struct pci_dev
  * @handle: the handle in question
@@ -694,8 +689,8 @@ static int acpi_pci_root_add(struct acpi_device *device,
 
 	root->device = device;
 	root->segment = segment & 0xFFFF;
-	strcpy(acpi_device_name(device), ACPI_PCI_ROOT_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS);
+	strscpy(acpi_device_name(device), ACPI_PCI_ROOT_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS);
 	device->driver_data = root;
 
 	if (hotadd && dmar_device_add(handle)) {
@@ -863,7 +858,7 @@ next:
 	}
 }
 
-static void acpi_pci_root_remap_iospace(struct fwnode_handle *fwnode,
+static void acpi_pci_root_remap_iospace(const struct fwnode_handle *fwnode,
 			struct resource_entry *entry)
 {
 #ifdef PCI_IOBASE
@@ -1008,7 +1003,6 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root,
 	int node = acpi_get_node(device->handle);
 	struct pci_bus *bus;
 	struct pci_host_bridge *host_bridge;
-	union acpi_object *obj;
 
 	info->root = root;
 	info->bridge = device;
@@ -1050,17 +1044,6 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root,
 	if (!(root->osc_ext_control_set & OSC_CXL_ERROR_REPORTING_CONTROL))
 		host_bridge->native_cxl_error = 0;
 
-	/*
-	 * Evaluate the "PCI Boot Configuration" _DSM Function.  If it
-	 * exists and returns 0, we must preserve any PCI resource
-	 * assignments made by firmware for this host bridge.
-	 */
-	obj = acpi_evaluate_dsm_typed(ACPI_HANDLE(bus->bridge), &pci_acpi_dsm_guid, 1,
-				      DSM_PCI_PRESERVE_BOOT_CONFIG, NULL, ACPI_TYPE_INTEGER);
-	if (obj && obj->integer.value == 0)
-		host_bridge->preserve_config = 1;
-	ACPI_FREE(obj);
-
 	acpi_dev_power_up_children_with_adr(device);
 
 	pci_scan_child_bus(bus);
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index d6cb2c27a23b..741bcc9d6d6a 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -111,7 +111,7 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	snprintf(name, sizeof(name), "%llu", sun);
 	pci_slot = pci_create_slot(pci_bus, device, name, NULL);
 	if (IS_ERR(pci_slot)) {
-		pr_err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot));
+		pr_err("pci_create_slot returned %pe\n", pci_slot);
 		kfree(slot);
 		return AE_OK;
 	}
diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c
index 843f678ade0c..32bdf8cbe8f2 100644
--- a/drivers/acpi/pfr_telemetry.c
+++ b/drivers/acpi/pfr_telemetry.c
@@ -272,9 +272,6 @@ static long pfrt_log_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 
 	case PFRT_LOG_IOC_GET_INFO:
 		info.log_level = get_pfrt_log_level(pfrt_log_dev);
-		if (ret < 0)
-			return ret;
-
 		info.log_type = pfrt_log_dev->info.log_type;
 		info.log_revid = pfrt_log_dev->info.log_revid;
 		if (copy_to_user(p, &info, sizeof(info)))
@@ -347,13 +344,11 @@ static const struct file_operations acpi_pfrt_log_fops = {
 	.llseek		= noop_llseek,
 };
 
-static int acpi_pfrt_log_remove(struct platform_device *pdev)
+static void acpi_pfrt_log_remove(struct platform_device *pdev)
 {
 	struct pfrt_log_device *pfrt_log_dev = platform_get_drvdata(pdev);
 
 	misc_deregister(&pfrt_log_dev->miscdev);
-
-	return 0;
 }
 
 static void pfrt_log_put_idx(void *data)
diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c
index 98267f163e2b..11b1c2828005 100644
--- a/drivers/acpi/pfr_update.c
+++ b/drivers/acpi/pfr_update.c
@@ -127,8 +127,11 @@ static int query_capability(struct pfru_update_cap_info *cap_hdr,
 					  pfru_dev->rev_id,
 					  PFRU_FUNC_QUERY_UPDATE_CAP,
 					  NULL, ACPI_TYPE_PACKAGE);
-	if (!out_obj)
+	if (!out_obj) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Query cap failed with no object\n");
 		return ret;
+	}
 
 	if (out_obj->package.count < CAP_NR_IDX ||
 	    out_obj->package.elements[CAP_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
@@ -141,13 +144,17 @@ static int query_capability(struct pfru_update_cap_info *cap_hdr,
 	    out_obj->package.elements[CAP_DRV_SVN_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[CAP_PLAT_ID_IDX].type != ACPI_TYPE_BUFFER ||
 	    out_obj->package.elements[CAP_OEM_ID_IDX].type != ACPI_TYPE_BUFFER ||
-	    out_obj->package.elements[CAP_OEM_INFO_IDX].type != ACPI_TYPE_BUFFER)
+	    out_obj->package.elements[CAP_OEM_INFO_IDX].type != ACPI_TYPE_BUFFER) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Query cap failed with invalid package count/type\n");
 		goto free_acpi_buffer;
+	}
 
 	cap_hdr->status = out_obj->package.elements[CAP_STATUS_IDX].integer.value;
 	if (cap_hdr->status != DSM_SUCCEED) {
 		ret = -EBUSY;
-		dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", cap_hdr->status);
+		dev_dbg(pfru_dev->parent_dev, "Query cap Error Status:%d\n",
+			cap_hdr->status);
 		goto free_acpi_buffer;
 	}
 
@@ -193,24 +200,32 @@ static int query_buffer(struct pfru_com_buf_info *info,
 	out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid,
 					  pfru_dev->rev_id, PFRU_FUNC_QUERY_BUF,
 					  NULL, ACPI_TYPE_PACKAGE);
-	if (!out_obj)
+	if (!out_obj) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Query buf failed with no object\n");
 		return ret;
+	}
 
 	if (out_obj->package.count < BUF_NR_IDX ||
 	    out_obj->package.elements[BUF_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[BUF_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[BUF_ADDR_LOW_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[BUF_ADDR_HI_IDX].type != ACPI_TYPE_INTEGER ||
-	    out_obj->package.elements[BUF_SIZE_IDX].type != ACPI_TYPE_INTEGER)
+	    out_obj->package.elements[BUF_SIZE_IDX].type != ACPI_TYPE_INTEGER) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Query buf failed with invalid package count/type\n");
 		goto free_acpi_buffer;
+	}
 
 	info->status = out_obj->package.elements[BUF_STATUS_IDX].integer.value;
 	info->ext_status =
 		out_obj->package.elements[BUF_EXT_STATUS_IDX].integer.value;
 	if (info->status != DSM_SUCCEED) {
 		ret = -EBUSY;
-		dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", info->status);
-		dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", info->ext_status);
+		dev_dbg(pfru_dev->parent_dev,
+			"Query buf failed with Error Status:%d\n", info->status);
+		dev_dbg(pfru_dev->parent_dev,
+			"Query buf failed with Error Extended Status:%d\n", info->ext_status);
 
 		goto free_acpi_buffer;
 	}
@@ -295,12 +310,16 @@ static bool applicable_image(const void *data, struct pfru_update_cap_info *cap,
 	m_img_hdr = data + size;
 
 	type = get_image_type(m_img_hdr, pfru_dev);
-	if (type < 0)
+	if (type < 0) {
+		dev_dbg(pfru_dev->parent_dev, "Invalid image type\n");
 		return false;
+	}
 
 	size = adjust_efi_size(m_img_hdr, size);
-	if (size < 0)
+	if (size < 0) {
+		dev_dbg(pfru_dev->parent_dev, "Invalid image size\n");
 		return false;
+	}
 
 	auth = data + size;
 	size += sizeof(u64) + auth->auth_info.hdr.len;
@@ -310,7 +329,7 @@ static bool applicable_image(const void *data, struct pfru_update_cap_info *cap,
 	if (type == PFRU_CODE_INJECT_TYPE)
 		return payload_hdr->rt_ver >= cap->code_rt_version;
 
-	return payload_hdr->rt_ver >= cap->drv_rt_version;
+	return payload_hdr->svn_ver >= cap->drv_svn;
 }
 
 static void print_update_debug_info(struct pfru_updated_result *result,
@@ -346,8 +365,11 @@ static int start_update(int action, struct pfru_device *pfru_dev)
 	out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid,
 					  pfru_dev->rev_id, PFRU_FUNC_START,
 					  &in_obj, ACPI_TYPE_PACKAGE);
-	if (!out_obj)
+	if (!out_obj) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Update failed to start with no object\n");
 		return ret;
+	}
 
 	if (out_obj->package.count < UPDATE_NR_IDX ||
 	    out_obj->package.elements[UPDATE_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
@@ -355,8 +377,11 @@ static int start_update(int action, struct pfru_device *pfru_dev)
 	    out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].type != ACPI_TYPE_INTEGER ||
 	    out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER ||
-	    out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].type != ACPI_TYPE_INTEGER)
+	    out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].type != ACPI_TYPE_INTEGER) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Update failed with invalid package count/type\n");
 		goto free_acpi_buffer;
+	}
 
 	update_result.status =
 		out_obj->package.elements[UPDATE_STATUS_IDX].integer.value;
@@ -365,8 +390,10 @@ static int start_update(int action, struct pfru_device *pfru_dev)
 
 	if (update_result.status != DSM_SUCCEED) {
 		ret = -EBUSY;
-		dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", update_result.status);
-		dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n",
+		dev_dbg(pfru_dev->parent_dev,
+			"Update failed with Error Status:%d\n", update_result.status);
+		dev_dbg(pfru_dev->parent_dev,
+			"Update failed with Error Extended Status:%d\n",
 			update_result.ext_status);
 
 		goto free_acpi_buffer;
@@ -450,8 +477,10 @@ static ssize_t pfru_write(struct file *file, const char __user *buf,
 	if (ret)
 		return ret;
 
-	if (len > buf_info.buf_size)
+	if (len > buf_info.buf_size) {
+		dev_dbg(pfru_dev->parent_dev, "Capsule image size too large\n");
 		return -EINVAL;
+	}
 
 	iov.iov_base = (void __user *)buf;
 	iov.iov_len = len;
@@ -460,10 +489,14 @@ static ssize_t pfru_write(struct file *file, const char __user *buf,
 	/* map the communication buffer */
 	phy_addr = (phys_addr_t)((buf_info.addr_hi << 32) | buf_info.addr_lo);
 	buf_ptr = memremap(phy_addr, buf_info.buf_size, MEMREMAP_WB);
-	if (!buf_ptr)
+	if (!buf_ptr) {
+		dev_dbg(pfru_dev->parent_dev, "Failed to remap the buffer\n");
 		return -ENOMEM;
+	}
 
 	if (!copy_from_iter_full(buf_ptr, len, &iter)) {
+		dev_dbg(pfru_dev->parent_dev,
+			"Failed to copy the data from the user space buffer\n");
 		ret = -EINVAL;
 		goto unmap;
 	}
@@ -489,13 +522,11 @@ static const struct file_operations acpi_pfru_fops = {
 	.llseek		= noop_llseek,
 };
 
-static int acpi_pfru_remove(struct platform_device *pdev)
+static void acpi_pfru_remove(struct platform_device *pdev)
 {
 	struct pfru_device *pfru_dev = platform_get_drvdata(pdev);
 
 	misc_deregister(&pfru_dev->miscdev);
-
-	return 0;
 }
 
 static void pfru_put_idx(void *data)
diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index d418462ab791..b43f4459a4f6 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -2,16 +2,34 @@
 
 /* Platform profile sysfs interface */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/acpi.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/platform_profile.h>
 #include <linux/sysfs.h>
 
-static struct platform_profile_handler *cur_profile;
+#define to_pprof_handler(d)	(container_of(d, struct platform_profile_handler, dev))
+
 static DEFINE_MUTEX(profile_lock);
 
+struct platform_profile_handler {
+	const char *name;
+	struct device dev;
+	int minor;
+	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	unsigned long hidden_choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	const struct platform_profile_ops *ops;
+};
+
+struct aggregate_choices_data {
+	unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	int count;
+};
+
 static const char * const profile_names[] = {
 	[PLATFORM_PROFILE_LOW_POWER] = "low-power",
 	[PLATFORM_PROFILE_COOL] = "cool",
@@ -19,163 +37,679 @@ static const char * const profile_names[] = {
 	[PLATFORM_PROFILE_BALANCED] = "balanced",
 	[PLATFORM_PROFILE_BALANCED_PERFORMANCE] = "balanced-performance",
 	[PLATFORM_PROFILE_PERFORMANCE] = "performance",
+	[PLATFORM_PROFILE_CUSTOM] = "custom",
 };
 static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST);
 
-static ssize_t platform_profile_choices_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
-{
-	int len = 0;
-	int err, i;
-
-	err = mutex_lock_interruptible(&profile_lock);
-	if (err)
-		return err;
+static DEFINE_IDA(platform_profile_ida);
 
-	if (!cur_profile) {
-		mutex_unlock(&profile_lock);
-		return -ENODEV;
-	}
+/**
+ * _commmon_choices_show - Show the available profile choices
+ * @choices: The available profile choices
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t _commmon_choices_show(unsigned long *choices, char *buf)
+{
+	int i, len = 0;
 
-	for_each_set_bit(i, cur_profile->choices, PLATFORM_PROFILE_LAST) {
+	for_each_set_bit(i, choices, PLATFORM_PROFILE_LAST) {
 		if (len == 0)
 			len += sysfs_emit_at(buf, len, "%s", profile_names[i]);
 		else
 			len += sysfs_emit_at(buf, len, " %s", profile_names[i]);
 	}
 	len += sysfs_emit_at(buf, len, "\n");
-	mutex_unlock(&profile_lock);
+
 	return len;
 }
 
-static ssize_t platform_profile_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
+/**
+ * _store_class_profile - Set the profile for a class device
+ * @dev: The class device
+ * @data: The profile to set
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _store_class_profile(struct device *dev, void *data)
+{
+	struct platform_profile_handler *handler;
+	int *bit = (int *)data;
+
+	lockdep_assert_held(&profile_lock);
+	handler = to_pprof_handler(dev);
+	if (!test_bit(*bit, handler->choices) && !test_bit(*bit, handler->hidden_choices))
+		return -EOPNOTSUPP;
+
+	return handler->ops->profile_set(dev, *bit);
+}
+
+/**
+ * _notify_class_profile - Notify the class device of a profile change
+ * @dev: The class device
+ * @data: Unused
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _notify_class_profile(struct device *dev, void *data)
+{
+	struct platform_profile_handler *handler = to_pprof_handler(dev);
+
+	lockdep_assert_held(&profile_lock);
+	sysfs_notify(&handler->dev.kobj, NULL, "profile");
+	kobject_uevent(&handler->dev.kobj, KOBJ_CHANGE);
+
+	return 0;
+}
+
+/**
+ * get_class_profile - Show the current profile for a class device
+ * @dev: The class device
+ * @profile: The profile to return
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int get_class_profile(struct device *dev,
+			     enum platform_profile_option *profile)
 {
-	enum platform_profile_option profile = PLATFORM_PROFILE_BALANCED;
+	struct platform_profile_handler *handler;
+	enum platform_profile_option val;
 	int err;
 
-	err = mutex_lock_interruptible(&profile_lock);
-	if (err)
+	lockdep_assert_held(&profile_lock);
+	handler = to_pprof_handler(dev);
+	err = handler->ops->profile_get(dev, &val);
+	if (err) {
+		pr_err("Failed to get profile for handler %s\n", handler->name);
 		return err;
+	}
+
+	if (WARN_ON(val >= PLATFORM_PROFILE_LAST))
+		return -EINVAL;
+	*profile = val;
+
+	return 0;
+}
+
+/**
+ * name_show - Show the name of the profile handler
+ * @dev: The device
+ * @attr: The attribute
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct platform_profile_handler *handler = to_pprof_handler(dev);
+
+	return sysfs_emit(buf, "%s\n", handler->name);
+}
+static DEVICE_ATTR_RO(name);
+
+/**
+ * choices_show - Show the available profile choices
+ * @dev: The device
+ * @attr: The attribute
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t choices_show(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	struct platform_profile_handler *handler = to_pprof_handler(dev);
+
+	return _commmon_choices_show(handler->choices, buf);
+}
+static DEVICE_ATTR_RO(choices);
+
+/**
+ * profile_show - Show the current profile for a class device
+ * @dev: The device
+ * @attr: The attribute
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t profile_show(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	enum platform_profile_option profile = PLATFORM_PROFILE_LAST;
+	int err;
+
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		err = get_class_profile(dev, &profile);
+		if (err)
+			return err;
+	}
+
+	return sysfs_emit(buf, "%s\n", profile_names[profile]);
+}
+
+/**
+ * profile_store - Set the profile for a class device
+ * @dev: The device
+ * @attr: The attribute
+ * @buf: The buffer to read from
+ * @count: The number of bytes to read
+ *
+ * Return: The number of bytes read
+ */
+static ssize_t profile_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	int index, ret;
+
+	index = sysfs_match_string(profile_names, buf);
+	if (index < 0)
+		return -EINVAL;
+
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		ret = _store_class_profile(dev, &index);
+		if (ret)
+			return ret;
+	}
+
+	sysfs_notify(acpi_kobj, NULL, "platform_profile");
+
+	return count;
+}
+static DEVICE_ATTR_RW(profile);
+
+static struct attribute *profile_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_choices.attr,
+	&dev_attr_profile.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(profile);
+
+static void pprof_device_release(struct device *dev)
+{
+	struct platform_profile_handler *pprof = to_pprof_handler(dev);
+
+	kfree(pprof);
+}
+
+static const struct class platform_profile_class = {
+	.name = "platform-profile",
+	.dev_groups = profile_groups,
+	.dev_release = pprof_device_release,
+};
+
+/**
+ * _aggregate_choices - Aggregate the available profile choices
+ * @dev: The device
+ * @arg: struct aggregate_choices_data, with it's aggregate member bitmap
+ *	 initially filled with ones
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _aggregate_choices(struct device *dev, void *arg)
+{
+	unsigned long tmp[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data *data = arg;
+	struct platform_profile_handler *handler;
+
+	lockdep_assert_held(&profile_lock);
 
-	if (!cur_profile) {
-		mutex_unlock(&profile_lock);
-		return -ENODEV;
+	handler = to_pprof_handler(dev);
+	bitmap_or(tmp, handler->choices, handler->hidden_choices, PLATFORM_PROFILE_LAST);
+	bitmap_and(data->aggregate, tmp, data->aggregate, PLATFORM_PROFILE_LAST);
+	data->count++;
+
+	return 0;
+}
+
+/**
+ * _remove_hidden_choices - Remove hidden choices from aggregate data
+ * @dev: The device
+ * @arg: struct aggregate_choices_data
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _remove_hidden_choices(struct device *dev, void *arg)
+{
+	struct aggregate_choices_data *data = arg;
+	struct platform_profile_handler *handler;
+
+	lockdep_assert_held(&profile_lock);
+	handler = to_pprof_handler(dev);
+	bitmap_andnot(data->aggregate, handler->choices,
+		      handler->hidden_choices, PLATFORM_PROFILE_LAST);
+
+	return 0;
+}
+
+/**
+ * platform_profile_choices_show - Show the available profile choices for legacy sysfs interface
+ * @kobj: The kobject
+ * @attr: The attribute
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t platform_profile_choices_show(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     char *buf)
+{
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
+	int err;
+
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		err = class_for_each_device(&platform_profile_class, NULL,
+					    &data, _aggregate_choices);
+		if (err)
+			return err;
+		if (data.count == 1) {
+			err = class_for_each_device(&platform_profile_class, NULL,
+						    &data, _remove_hidden_choices);
+			if (err)
+				return err;
+		}
 	}
 
-	err = cur_profile->profile_get(cur_profile, &profile);
-	mutex_unlock(&profile_lock);
+	/* no profile handler registered any more */
+	if (bitmap_empty(data.aggregate, PLATFORM_PROFILE_LAST))
+		return -EINVAL;
+
+	return _commmon_choices_show(data.aggregate, buf);
+}
+
+/**
+ * _aggregate_profiles - Aggregate the profiles for legacy sysfs interface
+ * @dev: The device
+ * @data: The profile to return
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _aggregate_profiles(struct device *dev, void *data)
+{
+	enum platform_profile_option *profile = data;
+	enum platform_profile_option val;
+	int err;
+
+	err = get_class_profile(dev, &val);
 	if (err)
 		return err;
 
-	/* Check that profile is valid index */
-	if (WARN_ON((profile < 0) || (profile >= ARRAY_SIZE(profile_names))))
-		return -EIO;
+	if (*profile != PLATFORM_PROFILE_LAST && *profile != val)
+		*profile = PLATFORM_PROFILE_CUSTOM;
+	else
+		*profile = val;
 
-	return sysfs_emit(buf, "%s\n", profile_names[profile]);
+	return 0;
 }
 
-static ssize_t platform_profile_store(struct device *dev,
-			    struct device_attribute *attr,
-			    const char *buf, size_t count)
+/**
+ * _store_and_notify - Store and notify a class from legacy sysfs interface
+ * @dev: The device
+ * @data: The profile to return
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _store_and_notify(struct device *dev, void *data)
 {
-	int err, i;
+	enum platform_profile_option *profile = data;
+	int err;
 
-	err = mutex_lock_interruptible(&profile_lock);
+	err = _store_class_profile(dev, profile);
 	if (err)
 		return err;
+	return _notify_class_profile(dev, NULL);
+}
+
+/**
+ * platform_profile_show - Show the current profile for legacy sysfs interface
+ * @kobj: The kobject
+ * @attr: The attribute
+ * @buf: The buffer to write to
+ *
+ * Return: The number of bytes written
+ */
+static ssize_t platform_profile_show(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     char *buf)
+{
+	enum platform_profile_option profile = PLATFORM_PROFILE_LAST;
+	int err;
 
-	if (!cur_profile) {
-		mutex_unlock(&profile_lock);
-		return -ENODEV;
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		err = class_for_each_device(&platform_profile_class, NULL,
+					    &profile, _aggregate_profiles);
+		if (err)
+			return err;
 	}
 
+	/* no profile handler registered any more */
+	if (profile == PLATFORM_PROFILE_LAST)
+		return -EINVAL;
+
+	return sysfs_emit(buf, "%s\n", profile_names[profile]);
+}
+
+/**
+ * platform_profile_store - Set the profile for legacy sysfs interface
+ * @kobj: The kobject
+ * @attr: The attribute
+ * @buf: The buffer to read from
+ * @count: The number of bytes to read
+ *
+ * Return: The number of bytes read
+ */
+static ssize_t platform_profile_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t count)
+{
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
+	int ret;
+	int i;
+
 	/* Scan for a matching profile */
 	i = sysfs_match_string(profile_names, buf);
-	if (i < 0) {
-		mutex_unlock(&profile_lock);
+	if (i < 0 || i == PLATFORM_PROFILE_CUSTOM)
 		return -EINVAL;
-	}
 
-	/* Check that platform supports this profile choice */
-	if (!test_bit(i, cur_profile->choices)) {
-		mutex_unlock(&profile_lock);
-		return -EOPNOTSUPP;
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		ret = class_for_each_device(&platform_profile_class, NULL,
+					    &data, _aggregate_choices);
+		if (ret)
+			return ret;
+		if (!test_bit(i, data.aggregate))
+			return -EOPNOTSUPP;
+
+		ret = class_for_each_device(&platform_profile_class, NULL, &i,
+					    _store_and_notify);
+		if (ret)
+			return ret;
 	}
 
-	err = cur_profile->profile_set(cur_profile, i);
-	if (!err)
-		sysfs_notify(acpi_kobj, NULL, "platform_profile");
+	sysfs_notify(acpi_kobj, NULL, "platform_profile");
 
-	mutex_unlock(&profile_lock);
-	if (err)
-		return err;
 	return count;
 }
 
-static DEVICE_ATTR_RO(platform_profile_choices);
-static DEVICE_ATTR_RW(platform_profile);
+static struct kobj_attribute attr_platform_profile_choices = __ATTR_RO(platform_profile_choices);
+static struct kobj_attribute attr_platform_profile = __ATTR_RW(platform_profile);
 
 static struct attribute *platform_profile_attrs[] = {
-	&dev_attr_platform_profile_choices.attr,
-	&dev_attr_platform_profile.attr,
+	&attr_platform_profile_choices.attr,
+	&attr_platform_profile.attr,
 	NULL
 };
 
+static int profile_class_registered(struct device *dev, const void *data)
+{
+	return 1;
+}
+
+static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx)
+{
+	struct device *dev;
+
+	dev = class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered);
+	if (!dev)
+		return 0;
+
+	put_device(dev);
+
+	return attr->mode;
+}
+
 static const struct attribute_group platform_profile_group = {
-	.attrs = platform_profile_attrs
+	.attrs = platform_profile_attrs,
+	.is_visible = profile_class_is_visible,
 };
 
-void platform_profile_notify(void)
+/**
+ * platform_profile_notify - Notify class device and legacy sysfs interface
+ * @dev: The class device
+ */
+void platform_profile_notify(struct device *dev)
 {
-	if (!cur_profile)
-		return;
+	scoped_cond_guard(mutex_intr, return, &profile_lock) {
+		_notify_class_profile(dev, NULL);
+	}
 	sysfs_notify(acpi_kobj, NULL, "platform_profile");
 }
 EXPORT_SYMBOL_GPL(platform_profile_notify);
 
-int platform_profile_register(struct platform_profile_handler *pprof)
+/**
+ * platform_profile_cycle - Cycles profiles available on all registered class devices
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int platform_profile_cycle(void)
 {
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
+	enum platform_profile_option next = PLATFORM_PROFILE_LAST;
+	enum platform_profile_option profile = PLATFORM_PROFILE_LAST;
 	int err;
 
-	mutex_lock(&profile_lock);
-	/* We can only have one active profile */
-	if (cur_profile) {
-		mutex_unlock(&profile_lock);
-		return -EEXIST;
+	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
+		err = class_for_each_device(&platform_profile_class, NULL,
+					    &profile, _aggregate_profiles);
+		if (err)
+			return err;
+
+		if (profile == PLATFORM_PROFILE_CUSTOM ||
+		    profile == PLATFORM_PROFILE_LAST)
+			return -EINVAL;
+
+		err = class_for_each_device(&platform_profile_class, NULL,
+					    &data, _aggregate_choices);
+		if (err)
+			return err;
+
+		/* never iterate into a custom if all drivers supported it */
+		clear_bit(PLATFORM_PROFILE_CUSTOM, data.aggregate);
+
+		next = find_next_bit_wrap(data.aggregate,
+					  PLATFORM_PROFILE_LAST,
+					  profile + 1);
+
+		err = class_for_each_device(&platform_profile_class, NULL, &next,
+					    _store_and_notify);
+
+		if (err)
+			return err;
 	}
 
-	/* Sanity check the profile handler field are set */
-	if (!pprof || bitmap_empty(pprof->choices, PLATFORM_PROFILE_LAST) ||
-		!pprof->profile_set || !pprof->profile_get) {
-		mutex_unlock(&profile_lock);
-		return -EINVAL;
+	sysfs_notify(acpi_kobj, NULL, "platform_profile");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(platform_profile_cycle);
+
+/**
+ * platform_profile_register - Creates and registers a platform profile class device
+ * @dev: Parent device
+ * @name: Name of the class device
+ * @drvdata: Driver data that will be attached to the class device
+ * @ops: Platform profile's mandatory operations
+ *
+ * Return: pointer to the new class device on success, ERR_PTR on failure
+ */
+struct device *platform_profile_register(struct device *dev, const char *name,
+					 void *drvdata,
+					 const struct platform_profile_ops *ops)
+{
+	struct device *ppdev;
+	int minor;
+	int err;
+
+	/* Sanity check */
+	if (WARN_ON_ONCE(!dev || !name || !ops || !ops->profile_get ||
+	    !ops->profile_set || !ops->probe))
+		return ERR_PTR(-EINVAL);
+
+	struct platform_profile_handler *pprof __free(kfree) = kzalloc(
+		sizeof(*pprof), GFP_KERNEL);
+	if (!pprof)
+		return ERR_PTR(-ENOMEM);
+
+	err = ops->probe(drvdata, pprof->choices);
+	if (err) {
+		dev_err(dev, "platform_profile probe failed\n");
+		return ERR_PTR(err);
 	}
 
-	err = sysfs_create_group(acpi_kobj, &platform_profile_group);
+	if (bitmap_empty(pprof->choices, PLATFORM_PROFILE_LAST)) {
+		dev_err(dev, "Failed to register platform_profile class device with empty choices\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (ops->hidden_choices) {
+		err = ops->hidden_choices(drvdata, pprof->hidden_choices);
+		if (err) {
+			dev_err(dev, "platform_profile hidden_choices failed\n");
+			return ERR_PTR(err);
+		}
+	}
+
+	guard(mutex)(&profile_lock);
+
+	/* create class interface for individual handler */
+	minor = ida_alloc(&platform_profile_ida, GFP_KERNEL);
+	if (minor < 0)
+		return ERR_PTR(minor);
+
+	pprof->name = name;
+	pprof->ops = ops;
+	pprof->minor = minor;
+	pprof->dev.class = &platform_profile_class;
+	pprof->dev.parent = dev;
+	dev_set_drvdata(&pprof->dev, drvdata);
+	dev_set_name(&pprof->dev, "platform-profile-%d", pprof->minor);
+	/* device_register() takes ownership of pprof/ppdev */
+	ppdev = &no_free_ptr(pprof)->dev;
+	err = device_register(ppdev);
 	if (err) {
-		mutex_unlock(&profile_lock);
-		return err;
+		put_device(ppdev);
+		goto cleanup_ida;
 	}
 
-	cur_profile = pprof;
-	mutex_unlock(&profile_lock);
-	return 0;
+	sysfs_notify(acpi_kobj, NULL, "platform_profile");
+
+	err = sysfs_update_group(acpi_kobj, &platform_profile_group);
+	if (err)
+		goto cleanup_cur;
+
+	return ppdev;
+
+cleanup_cur:
+	device_unregister(ppdev);
+
+cleanup_ida:
+	ida_free(&platform_profile_ida, minor);
+
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(platform_profile_register);
 
-int platform_profile_remove(void)
+/**
+ * platform_profile_remove - Unregisters a platform profile class device
+ * @dev: Class device
+ */
+void platform_profile_remove(struct device *dev)
 {
-	sysfs_remove_group(acpi_kobj, &platform_profile_group);
+	struct platform_profile_handler *pprof;
 
-	mutex_lock(&profile_lock);
-	cur_profile = NULL;
-	mutex_unlock(&profile_lock);
-	return 0;
+	if (IS_ERR_OR_NULL(dev))
+		return;
+
+	pprof = to_pprof_handler(dev);
+
+	guard(mutex)(&profile_lock);
+
+	ida_free(&platform_profile_ida, pprof->minor);
+	device_unregister(&pprof->dev);
+
+	sysfs_notify(acpi_kobj, NULL, "platform_profile");
+	sysfs_update_group(acpi_kobj, &platform_profile_group);
 }
 EXPORT_SYMBOL_GPL(platform_profile_remove);
 
+static void devm_platform_profile_release(struct device *dev, void *res)
+{
+	struct device **ppdev = res;
+
+	platform_profile_remove(*ppdev);
+}
+
+/**
+ * devm_platform_profile_register - Device managed version of platform_profile_register
+ * @dev: Parent device
+ * @name: Name of the class device
+ * @drvdata: Driver data that will be attached to the class device
+ * @ops: Platform profile's mandatory operations
+ *
+ * Return: pointer to the new class device on success, ERR_PTR on failure
+ */
+struct device *devm_platform_profile_register(struct device *dev, const char *name,
+					      void *drvdata,
+					      const struct platform_profile_ops *ops)
+{
+	struct device *ppdev;
+	struct device **dr;
+
+	dr = devres_alloc(devm_platform_profile_release, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	ppdev = platform_profile_register(dev, name, drvdata, ops);
+	if (IS_ERR(ppdev)) {
+		devres_free(dr);
+		return ppdev;
+	}
+
+	*dr = ppdev;
+	devres_add(dev, dr);
+
+	return ppdev;
+}
+EXPORT_SYMBOL_GPL(devm_platform_profile_register);
+
+static int __init platform_profile_init(void)
+{
+	int err;
+
+	if (acpi_disabled)
+		return -EOPNOTSUPP;
+
+	err = class_register(&platform_profile_class);
+	if (err)
+		return err;
+
+	err = sysfs_create_group(acpi_kobj, &platform_profile_group);
+	if (err)
+		class_unregister(&platform_profile_class);
+
+	return err;
+}
+
+static void __exit platform_profile_exit(void)
+{
+	sysfs_remove_group(acpi_kobj, &platform_profile_group);
+	class_unregister(&platform_profile_class);
+}
+module_init(platform_profile_init);
+module_exit(platform_profile_exit);
+
 MODULE_AUTHOR("Mark Pearson <markpearson@lenovo.com>");
+MODULE_DESCRIPTION("ACPI platform profile sysfs interface");
 MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/pmic/intel_pmic.c b/drivers/acpi/pmic/intel_pmic.c
index f20dbda1a831..134e9ca8eaa2 100644
--- a/drivers/acpi/pmic/intel_pmic.c
+++ b/drivers/acpi/pmic/intel_pmic.c
@@ -31,7 +31,7 @@ struct intel_pmic_opregion {
 
 static struct intel_pmic_opregion *intel_pmic_opregion;
 
-static int pmic_get_reg_bit(int address, struct pmic_table *table,
+static int pmic_get_reg_bit(int address, const struct pmic_table *table,
 			    int count, int *reg, int *bit)
 {
 	int i;
diff --git a/drivers/acpi/pmic/intel_pmic.h b/drivers/acpi/pmic/intel_pmic.h
index d956b03a6ca0..006f0780ffab 100644
--- a/drivers/acpi/pmic/intel_pmic.h
+++ b/drivers/acpi/pmic/intel_pmic.h
@@ -21,9 +21,9 @@ struct intel_pmic_opregion_data {
 					  u32 reg_address, u32 value, u32 mask);
 	int (*lpat_raw_to_temp)(struct acpi_lpat_conversion_table *lpat_table,
 				int raw);
-	struct pmic_table *power_table;
+	const struct pmic_table *power_table;
 	int power_table_count;
-	struct pmic_table *thermal_table;
+	const struct pmic_table *thermal_table;
 	int thermal_table_count;
 	/* For generic exec_mipi_pmic_seq_element handling */
 	int pmic_i2c_address;
diff --git a/drivers/acpi/pmic/intel_pmic_bxtwc.c b/drivers/acpi/pmic/intel_pmic_bxtwc.c
index e247615189fa..c332afbf82bd 100644
--- a/drivers/acpi/pmic/intel_pmic_bxtwc.c
+++ b/drivers/acpi/pmic/intel_pmic_bxtwc.c
@@ -24,7 +24,7 @@
 #define VSWITCH1_OUTPUT         BIT(4)
 #define VUSBPHY_CHARGE          BIT(1)
 
-static struct pmic_table power_table[] = {
+static const struct pmic_table power_table[] = {
 	{
 		.address = 0x0,
 		.reg = 0x63,
@@ -177,7 +177,7 @@ static struct pmic_table power_table[] = {
 	} /* MOFF -> MODEMCTRL Bit 0 */
 };
 
-static struct pmic_table thermal_table[] = {
+static const struct pmic_table thermal_table[] = {
 	{
 		.address = 0x00,
 		.reg = 0x4F39
diff --git a/drivers/acpi/pmic/intel_pmic_bytcrc.c b/drivers/acpi/pmic/intel_pmic_bytcrc.c
index 2b09f8da5400..b4c21a75294a 100644
--- a/drivers/acpi/pmic/intel_pmic_bytcrc.c
+++ b/drivers/acpi/pmic/intel_pmic_bytcrc.c
@@ -16,7 +16,7 @@
 
 #define PMIC_A0LOCK_REG		0xc5
 
-static struct pmic_table power_table[] = {
+static const struct pmic_table power_table[] = {
 /*	{
 		.address = 0x00,
 		.reg = ??,
@@ -134,7 +134,7 @@ static struct pmic_table power_table[] = {
 	}, /* V105 -> V1P05S, L2 SRAM */
 };
 
-static struct pmic_table thermal_table[] = {
+static const struct pmic_table thermal_table[] = {
 	{
 		.address = 0x00,
 		.reg = 0x75
diff --git a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
index c84ef3d15181..ecb36fbc1e7f 100644
--- a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
+++ b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
@@ -8,18 +8,22 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/bits.h>
 #include <linux/init.h>
 #include <linux/mfd/intel_soc_pmic.h>
 #include <linux/platform_device.h>
+#include <asm/byteorder.h>
 #include "intel_pmic.h"
 
 /* registers stored in 16bit BE (high:low, total 10bit) */
+#define PMIC_REG_MASK		GENMASK(9, 0)
+
 #define CHTDC_TI_VBAT		0x54
 #define CHTDC_TI_DIETEMP	0x56
 #define CHTDC_TI_BPTHERM	0x58
 #define CHTDC_TI_GPADC		0x5a
 
-static struct pmic_table chtdc_ti_power_table[] = {
+static const struct pmic_table chtdc_ti_power_table[] = {
 	{ .address = 0x00, .reg = 0x41 }, /* LDO1 */
 	{ .address = 0x04, .reg = 0x42 }, /* LDO2 */
 	{ .address = 0x08, .reg = 0x43 }, /* LDO3 */
@@ -35,7 +39,7 @@ static struct pmic_table chtdc_ti_power_table[] = {
 	{ .address = 0x30, .reg = 0x4e }, /* LD14 */
 };
 
-static struct pmic_table chtdc_ti_thermal_table[] = {
+static const struct pmic_table chtdc_ti_thermal_table[] = {
 	{
 		.address = 0x00,
 		.reg = CHTDC_TI_GPADC
@@ -73,7 +77,7 @@ static int chtdc_ti_pmic_get_power(struct regmap *regmap, int reg, int bit,
 	if (regmap_read(regmap, reg, &data))
 		return -EIO;
 
-	*value = data & 1;
+	*value = data & BIT(0);
 	return 0;
 }
 
@@ -85,13 +89,12 @@ static int chtdc_ti_pmic_update_power(struct regmap *regmap, int reg, int bit,
 
 static int chtdc_ti_pmic_get_raw_temp(struct regmap *regmap, int reg)
 {
-	u8 buf[2];
+	__be16 buf;
 
-	if (regmap_bulk_read(regmap, reg, buf, 2))
+	if (regmap_bulk_read(regmap, reg, &buf, sizeof(buf)))
 		return -EIO;
 
-	/* stored in big-endian */
-	return ((buf[0] & 0x03) << 8) | buf[1];
+	return be16_to_cpu(buf) & PMIC_REG_MASK;
 }
 
 static const struct intel_pmic_opregion_data chtdc_ti_pmic_opregion_data = {
diff --git a/drivers/acpi/pmic/intel_pmic_chtwc.c b/drivers/acpi/pmic/intel_pmic_chtwc.c
index f2c42f4c79ca..81caede51ca2 100644
--- a/drivers/acpi/pmic/intel_pmic_chtwc.c
+++ b/drivers/acpi/pmic/intel_pmic_chtwc.c
@@ -70,7 +70,7 @@
  * "regulator: whiskey_cove: implements Whiskey Cove pmic VRF support"
  * https://github.com/intel-aero/meta-intel-aero/blob/master/recipes-kernel/linux/linux-yocto/0019-regulator-whiskey_cove-implements-WhiskeyCove-pmic-V.patch
  */
-static struct pmic_table power_table[] = {
+static const struct pmic_table power_table[] = {
 	{
 		.address = 0x0,
 		.reg = CHT_WC_V1P8A_CTRL,
@@ -236,11 +236,12 @@ static int intel_cht_wc_exec_mipi_pmic_seq_element(struct regmap *regmap,
 						   u32 reg_address,
 						   u32 value, u32 mask)
 {
+	struct device *dev = regmap_get_device(regmap);
 	u32 address;
 
 	if (i2c_client_address > 0xff || reg_address > 0xff) {
-		pr_warn("%s warning addresses too big client 0x%x reg 0x%x\n",
-			__func__, i2c_client_address, reg_address);
+		dev_warn(dev, "warning addresses too big client 0x%x reg 0x%x\n",
+			 i2c_client_address, reg_address);
 		return -ERANGE;
 	}
 
diff --git a/drivers/acpi/pmic/intel_pmic_xpower.c b/drivers/acpi/pmic/intel_pmic_xpower.c
index 61bbe4c24d87..49bda5e0c8aa 100644
--- a/drivers/acpi/pmic/intel_pmic_xpower.c
+++ b/drivers/acpi/pmic/intel_pmic_xpower.c
@@ -26,7 +26,7 @@
 #define AXP288_ADC_TS_CURRENT_ON_ONDEMAND		(2 << 0)
 #define AXP288_ADC_TS_CURRENT_ON			(3 << 0)
 
-static struct pmic_table power_table[] = {
+static const struct pmic_table power_table[] = {
 	{
 		.address = 0x00,
 		.reg = 0x13,
@@ -129,7 +129,7 @@ static struct pmic_table power_table[] = {
 };
 
 /* TMP0 - TMP5 are the same, all from GPADC */
-static struct pmic_table thermal_table[] = {
+static const struct pmic_table thermal_table[] = {
 	{
 		.address = 0x00,
 		.reg = XPOWER_GPADC_LOW
@@ -255,7 +255,7 @@ static int intel_xpower_pmic_get_raw_temp(struct regmap *regmap, int reg)
 	if (ret)
 		return ret;
 
-	ret = regmap_bulk_read(regmap, AXP288_GP_ADC_H, buf, 2);
+	ret = regmap_bulk_read(regmap, AXP288_GP_ADC_H, buf, sizeof(buf));
 	if (ret == 0)
 		ret = (buf[0] << 4) + ((buf[1] >> 4) & 0x0f);
 
@@ -274,11 +274,12 @@ static int intel_xpower_exec_mipi_pmic_seq_element(struct regmap *regmap,
 						   u16 i2c_address, u32 reg_address,
 						   u32 value, u32 mask)
 {
+	struct device *dev = regmap_get_device(regmap);
 	int ret;
 
 	if (i2c_address != 0x34) {
-		pr_err("%s: Unexpected i2c-addr: 0x%02x (reg-addr 0x%x value 0x%x mask 0x%x)\n",
-		       __func__, i2c_address, reg_address, value, mask);
+		dev_err(dev, "Unexpected i2c-addr: 0x%02x (reg-addr 0x%x value 0x%x mask 0x%x)\n",
+			i2c_address, reg_address, value, mask);
 		return -ENXIO;
 	}
 
diff --git a/drivers/acpi/pmic/tps68470_pmic.c b/drivers/acpi/pmic/tps68470_pmic.c
index ebd03e472955..0d1a82eeb4b0 100644
--- a/drivers/acpi/pmic/tps68470_pmic.c
+++ b/drivers/acpi/pmic/tps68470_pmic.c
@@ -376,10 +376,8 @@ static int tps68470_pmic_opregion_probe(struct platform_device *pdev)
 	struct tps68470_pmic_opregion *opregion;
 	acpi_status status;
 
-	if (!dev || !tps68470_regmap) {
-		dev_warn(dev, "dev or regmap is NULL\n");
-		return -EINVAL;
-	}
+	if (!tps68470_regmap)
+		return dev_err_probe(dev, -EINVAL, "regmap is missing\n");
 
 	if (!handle) {
 		dev_warn(dev, "acpi handle is NULL\n");
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index c2c70139c4f1..361a7721a6a8 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -23,12 +23,14 @@
 
 #define pr_fmt(fmt) "ACPI: PM: " fmt
 
+#include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/pm_runtime.h>
 #include <linux/sysfs.h>
 #include <linux/acpi.h>
@@ -62,6 +64,9 @@ struct acpi_power_resource_entry {
 	struct acpi_power_resource *resource;
 };
 
+static bool hp_eb_gp12pxp_quirk;
+static bool unused_power_resources_quirk;
+
 static LIST_HEAD(acpi_power_resource_list);
 static DEFINE_MUTEX(power_resource_list_lock);
 
@@ -197,7 +202,7 @@ static int __get_state(acpi_handle handle, u8 *state)
 	cur_state = sta & ACPI_POWER_RESOURCE_STATE_ON;
 
 	acpi_handle_debug(handle, "Power resource is %s\n",
-			  cur_state ? "on" : "off");
+			  str_on_off(cur_state));
 
 	*state = cur_state;
 	return 0;
@@ -240,7 +245,7 @@ static int acpi_power_get_list_state(struct list_head *list, u8 *state)
 			break;
 	}
 
-	pr_debug("Power resource list is %s\n", cur_state ? "on" : "off");
+	pr_debug("Power resource list is %s\n", str_on_off(cur_state));
 
 	*state = cur_state;
 	return 0;
@@ -950,8 +955,8 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle)
 	mutex_init(&resource->resource_lock);
 	INIT_LIST_HEAD(&resource->list_node);
 	INIT_LIST_HEAD(&resource->dependents);
-	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
+	strscpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_POWER_CLASS);
 	device->power.state = ACPI_STATE_UNKNOWN;
 	device->flags.match_driver = true;
 
@@ -991,6 +996,38 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle)
 }
 
 #ifdef CONFIG_ACPI_SLEEP
+static bool resource_is_gp12pxp(acpi_handle handle)
+{
+	const char *path;
+	bool ret;
+
+	path = acpi_handle_path(handle);
+	ret = path && strcmp(path, "\\_SB_.PCI0.GP12.PXP_") == 0;
+	kfree(path);
+
+	return ret;
+}
+
+static void acpi_resume_on_eb_gp12pxp(struct acpi_power_resource *resource)
+{
+	acpi_handle_notice(resource->device.handle,
+			   "HP EB quirk - turning OFF then ON\n");
+
+	__acpi_power_off(resource);
+	__acpi_power_on(resource);
+
+	/*
+	 * Use the same delay as DSDT uses in modem _RST method.
+	 *
+	 * Otherwise we get "Unable to change power state from unknown to D0,
+	 * device inaccessible" error for the modem PCI device after thaw.
+	 *
+	 * This power resource is normally being enabled only during thaw (once)
+	 * so this wait is not a performance issue.
+	 */
+	msleep(200);
+}
+
 void acpi_resume_power_resources(void)
 {
 	struct acpi_power_resource *resource;
@@ -1012,8 +1049,14 @@ void acpi_resume_power_resources(void)
 
 		if (state == ACPI_POWER_RESOURCE_STATE_OFF
 		    && resource->ref_count) {
-			acpi_handle_debug(resource->device.handle, "Turning ON\n");
-			__acpi_power_on(resource);
+			if (hp_eb_gp12pxp_quirk &&
+			    resource_is_gp12pxp(resource->device.handle)) {
+				acpi_resume_on_eb_gp12pxp(resource);
+			} else {
+				acpi_handle_debug(resource->device.handle,
+						  "Turning ON\n");
+				__acpi_power_on(resource);
+			}
 		}
 
 		mutex_unlock(&resource->resource_lock);
@@ -1023,6 +1066,41 @@ void acpi_resume_power_resources(void)
 }
 #endif
 
+static const struct dmi_system_id dmi_hp_elitebook_gp12pxp_quirk[] = {
+/*
+ * This laptop (and possibly similar models too) has power resource called
+ * "GP12.PXP_" for its WWAN modem.
+ *
+ * For this power resource to turn ON power for the modem it needs certain
+ * internal flag called "ONEN" to be set.
+ * This flag only gets set from this power resource "_OFF" method, while the
+ * actual modem power gets turned off during suspend by "GP12.PTS" method
+ * called from the global "_PTS" (Prepare To Sleep) method.
+ * On the other hand, this power resource "_OFF" method implementation just
+ * sets the aforementioned flag without actually doing anything else (it
+ * doesn't contain any code to actually turn off power).
+ *
+ * The above means that when upon hibernation finish we try to set this
+ * power resource back ON since its "_STA" method returns 0 (while the resource
+ * is still considered in use) its "_ON" method won't do anything since
+ * that "ONEN" flag is not set.
+ * Overall, this means the modem is dead until laptop is rebooted since its
+ * power has been cut by "_PTS" and its PCI configuration was lost and not able
+ * to be restored.
+ *
+ * The easiest way to workaround the issue is to call this power resource
+ * "_OFF" method before calling the "_ON" method to make sure the "ONEN"
+ * flag gets properly set.
+ */
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 855 G7 Notebook PC"),
+		},
+	},
+	{}
+};
+
 static const struct dmi_system_id dmi_leave_unused_power_resources_on[] = {
 	{
 		/*
@@ -1045,7 +1123,7 @@ void acpi_turn_off_unused_power_resources(void)
 {
 	struct acpi_power_resource *resource;
 
-	if (dmi_check_system(dmi_leave_unused_power_resources_on))
+	if (unused_power_resources_quirk)
 		return;
 
 	mutex_lock(&power_resource_list_lock);
@@ -1064,3 +1142,10 @@ void acpi_turn_off_unused_power_resources(void)
 
 	mutex_unlock(&power_resource_list_lock);
 }
+
+void __init acpi_power_resources_init(void)
+{
+	hp_eb_gp12pxp_quirk = dmi_check_system(dmi_hp_elitebook_gp12pxp_quirk);
+	unused_power_resources_quirk =
+		dmi_check_system(dmi_leave_unused_power_resources_on);
+}
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index a35dd0e41c27..54676e3d82dd 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -229,18 +229,20 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
 	node_entry = ACPI_PTR_DIFF(node, table_hdr);
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
-	while ((unsigned long)entry + proc_sz < table_end) {
+	/* ignore subtable types that are smaller than a processor node */
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
+
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    cpu_node->parent == node_entry)
 			return 0;
 		if (entry->length == 0)
 			return 0;
+
 		entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
 				     entry->length);
-
 	}
 	return 1;
 }
@@ -270,18 +272,21 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he
 	table_end = (unsigned long)table_hdr + table_hdr->length;
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
 	/* find the processor structure associated with this cpuid */
-	while ((unsigned long)entry + proc_sz < table_end) {
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
 
 		if (entry->length == 0) {
 			pr_warn("Invalid zero length subtable\n");
 			break;
 		}
+		/* entry->length may not equal proc_sz, revalidate the processor structure length */
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    acpi_cpu_id == cpu_node->acpi_processor_id &&
+		    (unsigned long)entry + entry->length <= table_end &&
+		    entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) &&
 		     acpi_pptt_leaf_node(table_hdr, cpu_node)) {
 			return (struct acpi_pptt_processor *)entry;
 		}
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index c78453c74ef5..6792d4385eee 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -52,7 +52,7 @@ struct prm_context_buffer {
 static LIST_HEAD(prm_module_list);
 
 struct prm_handler_info {
-	guid_t guid;
+	efi_guid_t guid;
 	efi_status_t (__efiapi *handler_addr)(u64, void *);
 	u64 static_data_buffer_addr;
 	u64 acpi_param_buffer_addr;
@@ -72,15 +72,17 @@ struct prm_module_info {
 	struct prm_handler_info handlers[] __counted_by(handler_count);
 };
 
-static u64 efi_pa_va_lookup(u64 pa)
+static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa)
 {
 	efi_memory_desc_t *md;
 	u64 pa_offset = pa & ~PAGE_MASK;
 	u64 page = pa & PAGE_MASK;
 
 	for_each_efi_memory_desc(md) {
-		if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)
+		if ((md->attribute & EFI_MEMORY_RUNTIME) &&
+		    (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) {
 			return pa_offset + md->virt_addr + page - md->phys_addr;
+		}
 	}
 
 	return 0;
@@ -148,9 +150,52 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end)
 		th = &tm->handlers[cur_handler];
 
 		guid_copy(&th->guid, (guid_t *)handler_info->handler_guid);
-		th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address);
-		th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address);
-		th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address);
+
+		/*
+		 * Print an error message if handler_address is NULL, the parse of VA also
+		 * can be skipped.
+		 */
+		if (unlikely(!handler_info->handler_address)) {
+			pr_info("Skipping handler with NULL address for GUID: %pUL",
+					(guid_t *)handler_info->handler_guid);
+			continue;
+		}
+
+		th->handler_addr =
+			(void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address);
+		/*
+		 * Print a warning message and skip the parse of VA if handler_addr is zero
+		 * which is not expected to ever happen.
+		 */
+		if (unlikely(!th->handler_addr)) {
+			pr_warn("Failed to find VA of handler for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->handler_address);
+			continue;
+		}
+
+		th->static_data_buffer_addr =
+			efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address);
+		/*
+		 * According to the PRM specification, static_data_buffer_address can be zero,
+		 * so avoid printing a warning message in that case.  Otherwise, if the
+		 * return value of efi_pa_va_lookup() is zero, print the message.
+		 */
+		if (unlikely(!th->static_data_buffer_addr && handler_info->static_data_buffer_address))
+			pr_warn("Failed to find VA of static data buffer for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->static_data_buffer_address);
+
+		th->acpi_param_buffer_addr =
+			efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address);
+
+		/*
+		 * According to the PRM specification, acpi_param_buffer_address can be zero,
+		 * so avoid printing a warning message in that case.  Otherwise, if the
+		 * return value of efi_pa_va_lookup() is zero, print the message.
+		 */
+		if (unlikely(!th->acpi_param_buffer_addr && handler_info->acpi_param_buffer_address))
+			pr_warn("Failed to find VA of acpi param buffer for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->acpi_param_buffer_address);
+
 	} while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info)));
 
 	return 0;
@@ -214,6 +259,30 @@ static struct prm_handler_info *find_prm_handler(const guid_t *guid)
 #define UPDATE_LOCK_ALREADY_HELD 	4
 #define UPDATE_UNLOCK_WITHOUT_LOCK 	5
 
+int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer)
+{
+	struct prm_handler_info *handler = find_prm_handler(&handler_guid);
+	struct prm_module_info *module = find_prm_module(&handler_guid);
+	struct prm_context_buffer context;
+	efi_status_t status;
+
+	if (!module || !handler)
+		return -ENODEV;
+
+	memset(&context, 0, sizeof(context));
+	ACPI_COPY_NAMESEG(context.signature, "PRMC");
+	context.identifier         = handler->guid;
+	context.static_data_buffer = handler->static_data_buffer_addr;
+	context.mmio_ranges        = module->mmio_info;
+
+	status = efi_call_acpi_prm_handler(handler->handler_addr,
+					   (u64)param_buffer,
+					   &context);
+
+	return efi_status_to_err(status);
+}
+EXPORT_SYMBOL_GPL(acpi_call_prm_handler);
+
 /*
  * This is the PlatformRtMechanism opregion space handler.
  * @function: indicates the read/write. In fact as the PlatformRtMechanism
@@ -253,6 +322,11 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
 		if (!handler || !module)
 			goto invalid_guid;
 
+		if (!handler->handler_addr) {
+			buffer->prm_status = PRM_HANDLER_ERROR;
+			return AE_OK;
+		}
+
 		ACPI_COPY_NAMESEG(context.signature, "PRMC");
 		context.revision = 0x0;
 		context.reserved = 0x0;
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index 4322f2da6d10..c08ead07252b 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/export.h>
+#include <linux/string_choices.h>
 #include <linux/suspend.h>
 #include <linux/bcd.h>
 #include <linux/acpi.h>
@@ -30,17 +30,16 @@ acpi_system_wakeup_device_seq_show(struct seq_file *seq, void *offset)
 		if (!dev->wakeup.flags.valid)
 			continue;
 
-		seq_printf(seq, "%s\t  S%d\t",
+		seq_printf(seq, "%s\t  S%llu\t",
 			   dev->pnp.bus_id,
-			   (u32) dev->wakeup.sleep_state);
+			   dev->wakeup.sleep_state);
 
 		mutex_lock(&dev->physical_node_lock);
 
 		if (!dev->physical_node_count) {
 			seq_printf(seq, "%c%-8s\n",
 				dev->wakeup.flags.valid ? '*' : ' ',
-				device_may_wakeup(&dev->dev) ?
-					"enabled" : "disabled");
+				str_enabled_disabled(device_may_wakeup(&dev->dev)));
 		} else {
 			struct device *ldev;
 			list_for_each_entry(entry, &dev->physical_node_list,
@@ -55,9 +54,8 @@ acpi_system_wakeup_device_seq_show(struct seq_file *seq, void *offset)
 
 				seq_printf(seq, "%c%-8s  %s:%s\n",
 					dev->wakeup.flags.valid ? '*' : ' ',
-					(device_may_wakeup(&dev->dev) ||
-					device_may_wakeup(ldev)) ?
-					"enabled" : "disabled",
+					str_enabled_disabled(device_may_wakeup(ldev) ||
+							     device_may_wakeup(&dev->dev)),
 					ldev->bus ? ldev->bus->name :
 					"no-bus", dev_name(ldev));
 				put_device(ldev);
@@ -141,6 +139,5 @@ static const struct proc_ops acpi_system_wakeup_device_proc_ops = {
 void __init acpi_sleep_proc_init(void)
 {
 	/* 'wakeup device' [R/W] */
-	proc_create("wakeup", S_IFREG | S_IRUGO | S_IWUSR,
-		    acpi_root_dir, &acpi_system_wakeup_device_proc_ops);
+	proc_create("wakeup", 0644, acpi_root_dir, &acpi_system_wakeup_device_proc_ops);
 }
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index b203cfe28550..9b6b71a2ffb5 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -90,7 +90,8 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry,
 	struct acpi_madt_generic_interrupt *gicc =
 	    container_of(entry, struct acpi_madt_generic_interrupt, header);
 
-	if (!acpi_gicc_is_usable(gicc))
+	if (!(gicc->flags &
+	      (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE)))
 		return -ENODEV;
 
 	/* device_declaration means Device object in DSDT, in the
@@ -215,6 +216,21 @@ phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id)
 	return rv;
 }
 
+int __init acpi_get_madt_revision(void)
+{
+	struct acpi_table_header *madt = NULL;
+	int revision;
+
+	if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0, &madt)))
+		return -EINVAL;
+
+	revision = madt->revision;
+
+	acpi_put_table(madt);
+
+	return revision;
+}
+
 static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 4bd16b3f0781..5d824435b26b 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -27,12 +27,12 @@
 #define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80
 #define ACPI_PROCESSOR_NOTIFY_POWER	0x81
 #define ACPI_PROCESSOR_NOTIFY_THROTTLING	0x82
+#define ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED	0x85
 
 MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI Processor Driver");
 MODULE_LICENSE("GPL");
 
-static int acpi_processor_start(struct device *dev);
 static int acpi_processor_stop(struct device *dev);
 
 static const struct acpi_device_id processor_device_ids[] = {
@@ -46,7 +46,6 @@ static struct device_driver acpi_processor_driver = {
 	.name = "processor",
 	.bus = &cpu_subsys,
 	.acpi_match_table = processor_device_ids,
-	.probe = acpi_processor_start,
 	.remove = acpi_processor_stop,
 };
 
@@ -83,6 +82,11 @@ static void acpi_processor_notify(acpi_handle handle, u32 event, void *data)
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
+	case ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED:
+		cpufreq_update_limits(pr->id);
+		acpi_bus_generate_netlink_event(device->pnp.device_class,
+						  dev_name(&device->dev), event, 0);
+		break;
 	default:
 		acpi_handle_debug(handle, "Unsupported event [0x%x]\n", event);
 		break;
@@ -109,12 +113,9 @@ static int acpi_soft_cpu_online(unsigned int cpu)
 	 * CPU got physically hotplugged and onlined for the first time:
 	 * Initialize missing things.
 	 */
-	if (pr->flags.need_hotplug_init) {
+	if (!pr->flags.previously_online) {
 		int ret;
 
-		pr_info("Will online and init hotplugged CPU: %d\n",
-			pr->id);
-		pr->flags.need_hotplug_init = 0;
 		ret = __acpi_processor_start(device);
 		WARN(ret, "Failed to start CPU: %d\n", pr->id);
 	} else {
@@ -161,15 +162,11 @@ static int __acpi_processor_start(struct acpi_device *device)
 	if (!pr)
 		return -ENODEV;
 
-	if (pr->flags.need_hotplug_init)
-		return 0;
-
 	result = acpi_cppc_processor_probe(pr);
 	if (result && !IS_ENABLED(CONFIG_ACPI_CPU_FREQ_PSS))
 		dev_dbg(&device->dev, "CPPC data invalid or not present\n");
 
-	if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
-		acpi_processor_power_init(pr);
+	acpi_processor_power_init(pr);
 
 	acpi_pss_perf_init(pr);
 
@@ -179,32 +176,21 @@ static int __acpi_processor_start(struct acpi_device *device)
 
 	status = acpi_install_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
 					     acpi_processor_notify, device);
-	if (ACPI_SUCCESS(status))
-		return 0;
+	if (!ACPI_SUCCESS(status)) {
+		result = -ENODEV;
+		goto err_thermal_exit;
+	}
+	pr->flags.previously_online = 1;
 
-	result = -ENODEV;
-	acpi_processor_thermal_exit(pr, device);
+	return 0;
 
+err_thermal_exit:
+	acpi_processor_thermal_exit(pr, device);
 err_power_exit:
 	acpi_processor_power_exit(pr);
 	return result;
 }
 
-static int acpi_processor_start(struct device *dev)
-{
-	struct acpi_device *device = ACPI_COMPANION(dev);
-	int ret;
-
-	if (!device)
-		return -ENODEV;
-
-	/* Protect against concurrent CPU hotplug operations */
-	cpu_hotplug_disable();
-	ret = __acpi_processor_start(device);
-	cpu_hotplug_enable();
-	return ret;
-}
-
 static int acpi_processor_stop(struct device *dev)
 {
 	struct acpi_device *device = ACPI_COMPANION(dev);
@@ -250,6 +236,9 @@ static struct notifier_block acpi_processor_notifier_block = {
 	.notifier_call = acpi_processor_notifier,
 };
 
+void __weak acpi_processor_init_invariance_cppc(void)
+{ }
+
 /*
  * We keep the driver loaded even when ACPI is not running.
  * This is needed for the powernow-k8 driver, that works even without
@@ -273,9 +262,11 @@ static int __init acpi_processor_driver_init(void)
 	if (result < 0)
 		return result;
 
-	result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					   "acpi/cpu-drv:online",
-					   acpi_soft_cpu_online, NULL);
+	acpi_processor_register_idle_driver();
+
+	result = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				   "acpi/cpu-drv:online",
+				   acpi_soft_cpu_online, NULL);
 	if (result < 0)
 		goto err;
 	hp_online = result;
@@ -283,6 +274,15 @@ static int __init acpi_processor_driver_init(void)
 				  NULL, acpi_soft_cpu_dead);
 
 	acpi_processor_throttling_init();
+
+	/*
+	 * Frequency invariance calculations on AMD platforms can't be run until
+	 * after acpi_cppc_processor_probe() has been called for all online CPUs
+	 */
+	acpi_processor_init_invariance_cppc();
+
+	acpi_idle_rescan_dead_smt_siblings();
+
 	return 0;
 err:
 	driver_unregister(&acpi_processor_driver);
@@ -302,6 +302,7 @@ static void __exit acpi_processor_driver_exit(void)
 
 	cpuhp_remove_state_nocalls(hp_online);
 	cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD);
+	acpi_processor_unregister_idle_driver();
 	driver_unregister(&acpi_processor_driver);
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 3a34a8c425fe..22b051b94a86 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -16,7 +16,6 @@
 #include <linux/acpi.h>
 #include <linux/dmi.h>
 #include <linux/sched.h>       /* need_resched() */
-#include <linux/sort.h>
 #include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
@@ -25,6 +24,8 @@
 #include <acpi/processor.h>
 #include <linux/context_tracking.h>
 
+#include "internal.h"
+
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
  * available also for UP (on SMP it gets magically included via linux/smp.h).
@@ -50,12 +51,18 @@ module_param(latency_factor, uint, 0644);
 
 static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device);
 
-struct cpuidle_driver acpi_idle_driver = {
+static struct cpuidle_driver acpi_idle_driver = {
 	.name =		"acpi_idle",
 	.owner =	THIS_MODULE,
 };
 
 #ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void)
+{
+	if (cpuidle_get_driver() == &acpi_idle_driver)
+		arch_cpu_rescan_dead_smt_siblings();
+}
+
 static
 DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 
@@ -269,6 +276,10 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
 			 ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x",
 			 pr->power.states[ACPI_STATE_C3].address);
 
+	if (!pr->power.states[ACPI_STATE_C2].address &&
+	    !pr->power.states[ACPI_STATE_C3].address)
+		return -ENODEV;
+
 	return 0;
 }
 
@@ -386,25 +397,24 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr,
 	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 1);
 }
 
-static int acpi_cst_latency_cmp(const void *a, const void *b)
+static void acpi_cst_latency_sort(struct acpi_processor_cx *states, size_t length)
 {
-	const struct acpi_processor_cx *x = a, *y = b;
+	int i, j, k;
 
-	if (!(x->valid && y->valid))
-		return 0;
-	if (x->latency > y->latency)
-		return 1;
-	if (x->latency < y->latency)
-		return -1;
-	return 0;
-}
-static void acpi_cst_latency_swap(void *a, void *b, int n)
-{
-	struct acpi_processor_cx *x = a, *y = b;
+	for (i = 1; i < length; i++) {
+		if (!states[i].valid)
+			continue;
 
-	if (!(x->valid && y->valid))
-		return;
-	swap(x->latency, y->latency);
+		for (j = i - 1, k = i; j >= 0; j--) {
+			if (!states[j].valid)
+				continue;
+
+			if (states[j].latency > states[k].latency)
+				swap(states[j].latency, states[k].latency);
+
+			k = j;
+		}
+	}
 }
 
 static int acpi_processor_power_verify(struct acpi_processor *pr)
@@ -449,10 +459,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr)
 
 	if (buggy_latency) {
 		pr_notice("FW issue: working around C-state latencies out of order\n");
-		sort(&pr->power.states[1], max_cstate,
-		     sizeof(struct acpi_processor_cx),
-		     acpi_cst_latency_cmp,
-		     acpi_cst_latency_swap);
+		acpi_cst_latency_sort(&pr->power.states[1], max_cstate);
 	}
 
 	lapic_timer_propagate_broadcast(pr);
@@ -462,10 +469,8 @@ static int acpi_processor_power_verify(struct acpi_processor *pr)
 
 static int acpi_processor_get_cstate_info(struct acpi_processor *pr)
 {
-	unsigned int i;
 	int result;
 
-
 	/* NOTE: the idle thread may not be running while calling
 	 * this function */
 
@@ -482,17 +487,7 @@ static int acpi_processor_get_cstate_info(struct acpi_processor *pr)
 	acpi_processor_get_power_info_default(pr);
 
 	pr->power.count = acpi_processor_power_verify(pr);
-
-	/*
-	 * if one state of type C2 or C3 is available, mark this
-	 * CPU as being "idle manageable"
-	 */
-	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
-		if (pr->power.states[i].valid) {
-			pr->power.count = i;
-			pr->flags.power = 1;
-		}
-	}
+	pr->flags.power = 1;
 
 	return 0;
 }
@@ -583,7 +578,7 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
  * @dev: the target CPU
  * @index: the index of suggested state
  */
-static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
+static void acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
 
@@ -592,15 +587,14 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 	while (1) {
 
 		if (cx->entry_method == ACPI_CSTATE_HALT)
-			safe_halt();
+			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
+		} else if (cx->entry_method == ACPI_CSTATE_FFH) {
+			acpi_processor_ffh_play_dead(cx);
 		} else
-			return -ENODEV;
+			return;
 	}
-
-	/* Never reached */
-	return 0;
 }
 
 static __always_inline bool acpi_idle_fallback_to_c1(struct acpi_processor *pr)
@@ -808,12 +802,12 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 		state->enter = acpi_idle_enter;
 
 		state->flags = 0;
-		if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2 ||
-		    cx->type == ACPI_STATE_C3) {
-			state->enter_dead = acpi_idle_play_dead;
-			if (cx->type != ACPI_STATE_C3)
-				drv->safe_state_index = count;
-		}
+
+		state->enter_dead = acpi_idle_play_dead;
+
+		if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2)
+			drv->safe_state_index = count;
+
 		/*
 		 * Halt-induced C1 is not good for ->enter_s2idle, because it
 		 * re-enables interrupts on exit.  Moreover, C1 is generally not
@@ -1004,11 +998,6 @@ end:
 	return ret;
 }
 
-/*
- * flat_state_cnt - the number of composite LPI states after the process of flattening
- */
-static int flat_state_cnt;
-
 /**
  * combine_lpi_states - combine local and parent LPI states to form a composite LPI state
  *
@@ -1051,9 +1040,10 @@ static void stash_composite_state(struct acpi_lpi_states_array *curr_level,
 	curr_level->composite_states[curr_level->composite_states_size++] = t;
 }
 
-static int flatten_lpi_states(struct acpi_processor *pr,
-			      struct acpi_lpi_states_array *curr_level,
-			      struct acpi_lpi_states_array *prev_level)
+static unsigned int flatten_lpi_states(struct acpi_processor *pr,
+				       unsigned int flat_state_cnt,
+				       struct acpi_lpi_states_array *curr_level,
+				       struct acpi_lpi_states_array *prev_level)
 {
 	int i, j, state_count = curr_level->size;
 	struct acpi_lpi_state *p, *t = curr_level->entries;
@@ -1093,7 +1083,7 @@ static int flatten_lpi_states(struct acpi_processor *pr,
 	}
 
 	kfree(curr_level->entries);
-	return 0;
+	return flat_state_cnt;
 }
 
 int __weak acpi_processor_ffh_lpi_probe(unsigned int cpu)
@@ -1108,6 +1098,7 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr)
 	acpi_handle handle = pr->handle, pr_ahandle;
 	struct acpi_device *d = NULL;
 	struct acpi_lpi_states_array info[2], *tmp, *prev, *curr;
+	unsigned int state_count;
 
 	/* make sure our architecture has support */
 	ret = acpi_processor_ffh_lpi_probe(pr->id);
@@ -1120,14 +1111,13 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr)
 	if (!acpi_has_method(handle, "_LPI"))
 		return -EINVAL;
 
-	flat_state_cnt = 0;
 	prev = &info[0];
 	curr = &info[1];
 	handle = pr->handle;
 	ret = acpi_processor_evaluate_lpi(handle, prev);
 	if (ret)
 		return ret;
-	flatten_lpi_states(pr, prev, NULL);
+	state_count = flatten_lpi_states(pr, 0, prev, NULL);
 
 	status = acpi_get_parent(handle, &pr_ahandle);
 	while (ACPI_SUCCESS(status)) {
@@ -1149,18 +1139,19 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr)
 			break;
 
 		/* flatten all the LPI states in this level of hierarchy */
-		flatten_lpi_states(pr, curr, prev);
+		state_count = flatten_lpi_states(pr, state_count, curr, prev);
 
 		tmp = prev, prev = curr, curr = tmp;
 
 		status = acpi_get_parent(handle, &pr_ahandle);
 	}
 
-	pr->power.count = flat_state_cnt;
 	/* reset the index after flattening */
-	for (i = 0; i < pr->power.count; i++)
+	for (i = 0; i < state_count; i++)
 		pr->power.lpi_states[i].index = i;
 
+	pr->power.count = state_count;
+
 	/* Tell driver that _LPI is supported. */
 	pr->flags.has_lpi = 1;
 	pr->flags.power = 1;
@@ -1366,72 +1357,102 @@ int acpi_processor_power_state_has_changed(struct acpi_processor *pr)
 	return 0;
 }
 
-static int acpi_processor_registered;
+void acpi_processor_register_idle_driver(void)
+{
+	struct acpi_processor *pr;
+	int ret = -ENODEV;
+	int cpu;
 
-int acpi_processor_power_init(struct acpi_processor *pr)
+	/*
+	 * Acpi idle driver is used by all possible CPUs.
+	 * Install the idle handler by the processor power info of one in them.
+	 * Note that we use previously set idle handler will be used on
+	 * platforms that only support C1.
+	 */
+	for_each_cpu(cpu, (struct cpumask *)cpu_possible_mask) {
+		pr = per_cpu(processors, cpu);
+		if (!pr)
+			continue;
+
+		ret = acpi_processor_get_power_info(pr);
+		if (!ret) {
+			pr->flags.power_setup_done = 1;
+			acpi_processor_setup_cpuidle_states(pr);
+			break;
+		}
+	}
+
+	if (ret) {
+		pr_debug("No ACPI power information from any CPUs.\n");
+		return;
+	}
+
+	ret = cpuidle_register_driver(&acpi_idle_driver);
+	if (ret) {
+		pr_debug("register %s failed.\n", acpi_idle_driver.name);
+		return;
+	}
+	pr_debug("%s registered with cpuidle.\n", acpi_idle_driver.name);
+}
+
+void acpi_processor_unregister_idle_driver(void)
+{
+	cpuidle_unregister_driver(&acpi_idle_driver);
+}
+
+void acpi_processor_power_init(struct acpi_processor *pr)
 {
-	int retval;
 	struct cpuidle_device *dev;
 
+	/*
+	 * The code below only works if the current cpuidle driver is the ACPI
+	 * idle driver.
+	 */
+	if (cpuidle_get_driver() != &acpi_idle_driver)
+		return;
+
 	if (disabled_by_idle_boot_param())
-		return 0;
+		return;
 
 	acpi_processor_cstate_first_run_checks();
 
 	if (!acpi_processor_get_power_info(pr))
 		pr->flags.power_setup_done = 1;
 
-	/*
-	 * Install the idle handler if processor power management is supported.
-	 * Note that we use previously set idle handler will be used on
-	 * platforms that only support C1.
-	 */
-	if (pr->flags.power) {
-		/* Register acpi_idle_driver if not already registered */
-		if (!acpi_processor_registered) {
-			acpi_processor_setup_cpuidle_states(pr);
-			retval = cpuidle_register_driver(&acpi_idle_driver);
-			if (retval)
-				return retval;
-			pr_debug("%s registered with cpuidle\n",
-				 acpi_idle_driver.name);
-		}
+	if (!pr->flags.power)
+		return;
 
-		dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-		if (!dev)
-			return -ENOMEM;
-		per_cpu(acpi_cpuidle_device, pr->id) = dev;
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return;
 
-		acpi_processor_setup_cpuidle_dev(pr, dev);
+	per_cpu(acpi_cpuidle_device, pr->id) = dev;
 
-		/* Register per-cpu cpuidle_device. Cpuidle driver
-		 * must already be registered before registering device
-		 */
-		retval = cpuidle_register_device(dev);
-		if (retval) {
-			if (acpi_processor_registered == 0)
-				cpuidle_unregister_driver(&acpi_idle_driver);
-			return retval;
-		}
-		acpi_processor_registered++;
+	acpi_processor_setup_cpuidle_dev(pr, dev);
+
+	/*
+	 * Register a cpuidle device for this CPU.  The cpuidle driver using
+	 * this device is expected to be registered.
+	 */
+	if (cpuidle_register_device(dev)) {
+		per_cpu(acpi_cpuidle_device, pr->id) = NULL;
+		kfree(dev);
 	}
-	return 0;
 }
 
-int acpi_processor_power_exit(struct acpi_processor *pr)
+void acpi_processor_power_exit(struct acpi_processor *pr)
 {
 	struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id);
 
 	if (disabled_by_idle_boot_param())
-		return 0;
+		return;
 
 	if (pr->flags.power) {
 		cpuidle_unregister_device(dev);
-		acpi_processor_registered--;
-		if (acpi_processor_registered == 0)
-			cpuidle_unregister_driver(&acpi_idle_driver);
+		kfree(dev);
 	}
 
 	pr->flags.power_setup_done = 0;
-	return 0;
 }
+
+MODULE_IMPORT_NS("ACPI_PROCESSOR_IDLE");
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 4265814c74f8..8972446b7162 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -20,12 +20,11 @@
 #include <acpi/processor.h>
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
+#include <asm/msr.h>
 #endif
 
 #define ACPI_PROCESSOR_FILE_PERFORMANCE	"performance"
 
-static DEFINE_MUTEX(performance_mutex);
-
 /*
  * _PPC support is implemented as a CPUfreq policy notifier:
  * This means each time a CPUfreq driver registered also with
@@ -174,6 +173,9 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu;
 
+	if (ignore_ppc == 1)
+		return;
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
@@ -194,6 +196,14 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 		if (ret < 0)
 			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
 			       cpu, ret);
+
+		if (!pr->performance)
+			continue;
+
+		ret = acpi_processor_get_platform_limit(pr);
+		if (ret)
+			pr_err("Failed to update freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
 	}
 }
 
@@ -209,6 +219,10 @@ void acpi_processor_ppc_exit(struct cpufreq_policy *policy)
 	}
 }
 
+#ifdef CONFIG_X86
+
+static DEFINE_MUTEX(performance_mutex);
+
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
 {
 	int result = 0;
@@ -267,7 +281,6 @@ end:
 	return result;
 }
 
-#ifdef CONFIG_X86
 /*
  * Some AMDs have 50MHz frequency multiples, but only provide 100MHz rounding
  * in their ACPI data. Calculate the real values and fix up the _PSS data.
@@ -298,9 +311,6 @@ static void amd_fixup_frequency(struct acpi_processor_px *px, int i)
 			px->core_frequency = (100 * (fid + 8)) >> did;
 	}
 }
-#else
-static void amd_fixup_frequency(struct acpi_processor_px *px, int i) {};
-#endif
 
 static int acpi_processor_get_performance_states(struct acpi_processor *pr)
 {
@@ -440,13 +450,11 @@ int acpi_processor_get_performance_info(struct acpi_processor *pr)
 	 * the BIOS is older than the CPU and does not know its frequencies
 	 */
  update_bios:
-#ifdef CONFIG_X86
 	if (acpi_has_method(pr->handle, "_PPC")) {
 		if(boot_cpu_has(X86_FEATURE_EST))
 			pr_warn(FW_BUG "BIOS needs update for CPU "
 			       "frequency support\n");
 	}
-#endif
 	return result;
 }
 EXPORT_SYMBOL_GPL(acpi_processor_get_performance_info);
@@ -788,3 +796,4 @@ unlock:
 	mutex_unlock(&performance_mutex);
 }
 EXPORT_SYMBOL(acpi_processor_unregister_performance);
+#endif
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index b7c6287eccca..c7b1dc5687ec 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -17,6 +17,8 @@
 #include <acpi/processor.h>
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 #ifdef CONFIG_CPU_FREQ
 
 /* If a passive cooling situation is detected, primarily CPUfreq is used, as it
@@ -26,12 +28,21 @@
  */
 
 #define CPUFREQ_THERMAL_MIN_STEP 0
-#define CPUFREQ_THERMAL_MAX_STEP 3
 
-static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
+static int cpufreq_thermal_max_step __read_mostly = 3;
+
+/*
+ * Minimum throttle percentage for processor_thermal cooling device.
+ * The processor_thermal driver uses it to calculate the percentage amount by
+ * which cpu frequency must be reduced for each cooling state. This is also used
+ * to calculate the maximum number of throttling steps or cooling states.
+ */
+static int cpufreq_thermal_reduction_pctg __read_mostly = 20;
+
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_step);
 
-#define reduction_pctg(cpu) \
-	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
+#define reduction_step(cpu) \
+	per_cpu(cpufreq_thermal_reduction_step, phys_package_first_cpu(cpu))
 
 /*
  * Emulate "per package data" using per cpu data (which should really be
@@ -51,19 +62,14 @@ static int phys_package_first_cpu(int cpu)
 	return 0;
 }
 
-static int cpu_has_cpufreq(unsigned int cpu)
+static bool cpu_has_cpufreq(unsigned int cpu)
 {
-	struct cpufreq_policy *policy;
-
 	if (!acpi_processor_cpufreq_init)
 		return 0;
 
-	policy = cpufreq_cpu_get(cpu);
-	if (policy) {
-		cpufreq_cpu_put(policy);
-		return 1;
-	}
-	return 0;
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
+
+	return policy != NULL;
 }
 
 static int cpufreq_get_max_state(unsigned int cpu)
@@ -71,7 +77,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return CPUFREQ_THERMAL_MAX_STEP;
+	return cpufreq_thermal_max_step;
 }
 
 static int cpufreq_get_cur_state(unsigned int cpu)
@@ -79,20 +85,39 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return reduction_pctg(cpu);
+	return reduction_step(cpu);
+}
+
+static bool cpufreq_update_thermal_limit(unsigned int cpu, struct acpi_processor *pr)
+{
+	unsigned long max_freq;
+	int ret;
+
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
+	if (!policy)
+		return false;
+
+	max_freq = (policy->cpuinfo.max_freq *
+		(100 - reduction_step(cpu) * cpufreq_thermal_reduction_pctg)) / 100;
+
+	ret = freq_qos_update_request(&pr->thermal_req, max_freq);
+	if (ret < 0) {
+		pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
+			pr->id, ret);
+	}
+
+	return true;
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
 {
-	struct cpufreq_policy *policy;
 	struct acpi_processor *pr;
-	unsigned long max_freq;
-	int i, ret;
+	int i;
 
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	reduction_pctg(cpu) = state;
+	reduction_step(cpu) = state;
 
 	/*
 	 * Update all the CPUs in the same package because they all
@@ -109,27 +134,35 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 		if (unlikely(!freq_qos_request_active(&pr->thermal_req)))
 			continue;
 
-		policy = cpufreq_cpu_get(i);
-		if (!policy)
+		if (!cpufreq_update_thermal_limit(i, pr))
 			return -EINVAL;
+	}
+	return 0;
+}
+
+static void acpi_thermal_cpufreq_config(void)
+{
+	int cpufreq_pctg = acpi_arch_thermal_cpufreq_pctg();
 
-		max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+	if (!cpufreq_pctg)
+		return;
 
-		cpufreq_cpu_put(policy);
+	cpufreq_thermal_reduction_pctg = cpufreq_pctg;
 
-		ret = freq_qos_update_request(&pr->thermal_req, max_freq);
-		if (ret < 0) {
-			pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
-				pr->id, ret);
-		}
-	}
-	return 0;
+	/*
+	 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
+	 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
+	 * the CPU performance doesn't become 0.
+	 */
+	cpufreq_thermal_max_step = (100 / cpufreq_pctg) - 2;
 }
 
 void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu;
 
+	acpi_thermal_cpufreq_config();
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
@@ -190,7 +223,7 @@ static int acpi_processor_max_state(struct acpi_processor *pr)
 
 	/*
 	 * There exists four states according to
-	 * cpufreq_thermal_reduction_pctg. 0, 1, 2, 3
+	 * cpufreq_thermal_reduction_step. 0, 1, 2, 3
 	 */
 	max_state += cpufreq_get_max_state(pr->id);
 	if (pr->flags.throttling)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 00d045e5f524..f9c2bc1d4a3a 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -18,9 +18,12 @@
 #include <linux/sched.h>
 #include <linux/cpufreq.h>
 #include <linux/acpi.h>
+#include <linux/uaccess.h>
 #include <acpi/processor.h>
 #include <asm/io.h>
-#include <linux/uaccess.h>
+#ifdef CONFIG_X86
+#include <asm/msr.h>
+#endif
 
 /* ignore_tpc:
  *  0 -> acpi processor driver doesn't ignore _TPC values
@@ -232,7 +235,7 @@ static int acpi_processor_throttling_notifier(unsigned long event, void *data)
 		if (pr->throttling_platform_limit > target_state)
 			target_state = pr->throttling_platform_limit;
 		if (target_state >= p_throttling->state_count) {
-			pr_warn("Exceed the limit of T-state \n");
+			pr_warn("Exceed the limit of T-state\n");
 			target_state = p_throttling->state_count - 1;
 		}
 		p_tstate->target_state = target_state;
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 6979a3f9f90a..1b997a5497e7 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -2,14 +2,17 @@
 /*
  * ACPI device specific properties support.
  *
- * Copyright (C) 2014, Intel Corporation
+ * Copyright (C) 2014 - 2023, Intel Corporation
  * All rights reserved.
  *
  * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
  *          Darren Hart <dvhart@linux.intel.com>
  *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Sakari Ailus <sakari.ailus@linux.intel.com>
  */
 
+#define pr_fmt(fmt) "ACPI: " fmt
+
 #include <linux/acpi.h>
 #include <linux/device.h>
 #include <linux/export.h>
@@ -28,9 +31,14 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
  * not defined without a warning. For instance if any of the properties
  * from different GUID appear in a property list of another, it will be
  * accepted by the kernel. Firmware validation tools should catch these.
+ *
+ * References:
+ *
+ * [1] UEFI DSD Guide.
+ *     https://github.com/UEFI/DSD-Guide/blob/main/src/dsd-guide.adoc
  */
 static const guid_t prp_guids[] = {
-	/* ACPI _DSD device properties GUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */
+	/* ACPI _DSD device properties GUID [1]: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */
 	GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c,
 		  0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01),
 	/* Hotplug in D3 GUID: 6211e2c0-58a3-4af3-90e1-927a4e0c55a4 */
@@ -50,12 +58,12 @@ static const guid_t prp_guids[] = {
 		  0xa5, 0x61, 0x99, 0xa5, 0x18, 0x97, 0x62, 0xd0),
 };
 
-/* ACPI _DSD data subnodes GUID: dbb8e3e6-5886-4ba6-8795-1319f52a966b */
+/* ACPI _DSD data subnodes GUID [1]: dbb8e3e6-5886-4ba6-8795-1319f52a966b */
 static const guid_t ads_guid =
 	GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6,
 		  0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b);
 
-/* ACPI _DSD data buffer GUID: edb12dd0-363d-4085-a3d2-49522ca160c4 */
+/* ACPI _DSD data buffer GUID [1]: edb12dd0-363d-4085-a3d2-49522ca160c4 */
 static const guid_t buffer_prop_guid =
 	GUID_INIT(0xedb12dd0, 0x363d, 0x4085,
 		  0xa3, 0xd2, 0x49, 0x52, 0x2c, 0xa1, 0x60, 0xc4);
@@ -75,8 +83,12 @@ static bool acpi_nondev_subnode_extract(union acpi_object *desc,
 					struct fwnode_handle *parent)
 {
 	struct acpi_data_node *dn;
+	acpi_handle scope = NULL;
 	bool result;
 
+	if (acpi_graph_ignore_port(handle))
+		return false;
+
 	dn = kzalloc(sizeof(*dn), GFP_KERNEL);
 	if (!dn)
 		return false;
@@ -87,59 +99,45 @@ static bool acpi_nondev_subnode_extract(union acpi_object *desc,
 	INIT_LIST_HEAD(&dn->data.properties);
 	INIT_LIST_HEAD(&dn->data.subnodes);
 
-	result = acpi_extract_properties(handle, desc, &dn->data);
-
-	if (handle) {
-		acpi_handle scope;
-		acpi_status status;
+	/*
+	 * The scope for the completion of relative pathname segments and
+	 * subnode object lookup is the one of the namespace node (device)
+	 * containing the object that has returned the package.  That is, it's
+	 * the scope of that object's parent device.
+	 */
+	if (handle)
+		acpi_get_parent(handle, &scope);
 
-		/*
-		 * The scope for the subnode object lookup is the one of the
-		 * namespace node (device) containing the object that has
-		 * returned the package.  That is, it's the scope of that
-		 * object's parent.
-		 */
-		status = acpi_get_parent(handle, &scope);
-		if (ACPI_SUCCESS(status)
-		    && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data,
-						      &dn->fwnode))
-			result = true;
-	} else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data,
-						  &dn->fwnode)) {
+	/*
+	 * Extract properties from the _DSD-equivalent package pointed to by
+	 * desc and use scope (if not NULL) for the completion of relative
+	 * pathname segments.
+	 *
+	 * The extracted properties will be held in the new data node dn.
+	 */
+	result = acpi_extract_properties(scope, desc, &dn->data);
+	/*
+	 * Look for subnodes in the _DSD-equivalent package pointed to by desc
+	 * and create child nodes of dn if there are any.
+	 */
+	if (acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode))
 		result = true;
-	}
-
-	if (result) {
-		dn->handle = handle;
-		dn->data.pointer = desc;
-		list_add_tail(&dn->sibling, list);
-		return true;
-	}
-
-	kfree(dn);
-	acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n");
-	return false;
-}
-
-static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
-					const union acpi_object *link,
-					struct list_head *list,
-					struct fwnode_handle *parent)
-{
-	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
-	acpi_status status;
 
-	status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf,
-					    ACPI_TYPE_PACKAGE);
-	if (ACPI_FAILURE(status))
+	if (!result) {
+		kfree(dn);
+		acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n");
 		return false;
+	}
 
-	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
-					parent))
-		return true;
+	/*
+	 * This will be NULL if the desc package is embedded in an outer
+	 * _DSD-equivalent package and its scope cannot be determined.
+	 */
+	dn->handle = handle;
+	dn->data.pointer = desc;
+	list_add_tail(&dn->sibling, list);
 
-	ACPI_FREE(buf.pointer);
-	return false;
+	return true;
 }
 
 static bool acpi_nondev_subnode_ok(acpi_handle scope,
@@ -147,9 +145,16 @@ static bool acpi_nondev_subnode_ok(acpi_handle scope,
 				   struct list_head *list,
 				   struct fwnode_handle *parent)
 {
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
 	acpi_handle handle;
 	acpi_status status;
 
+	/*
+	 * If the scope is unknown, the _DSD-equivalent package being parsed
+	 * was embedded in an outer _DSD-equivalent package as a result of
+	 * direct evaluation of an object pointed to by a reference.  In that
+	 * case, using a pathname as the target object pointer is invalid.
+	 */
 	if (!scope)
 		return false;
 
@@ -158,7 +163,17 @@ static bool acpi_nondev_subnode_ok(acpi_handle scope,
 	if (ACPI_FAILURE(status))
 		return false;
 
-	return acpi_nondev_subnode_data_ok(handle, link, list, parent);
+	status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf,
+					    ACPI_TYPE_PACKAGE);
+	if (ACPI_FAILURE(status))
+		return false;
+
+	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
+					parent))
+		return true;
+
+	ACPI_FREE(buf.pointer);
+	return false;
 }
 
 static bool acpi_add_nondev_subnodes(acpi_handle scope,
@@ -169,9 +184,12 @@ static bool acpi_add_nondev_subnodes(acpi_handle scope,
 	bool ret = false;
 	int i;
 
+	/*
+	 * Every element in the links package is expected to represent a link
+	 * to a non-device node in a tree containing device-specific data.
+	 */
 	for (i = 0; i < links->package.count; i++) {
 		union acpi_object *link, *desc;
-		acpi_handle handle;
 		bool result;
 
 		link = &links->package.elements[i];
@@ -179,26 +197,53 @@ static bool acpi_add_nondev_subnodes(acpi_handle scope,
 		if (link->package.count != 2)
 			continue;
 
-		/* The first one must be a string. */
+		/* The first one (the key) must be a string. */
 		if (link->package.elements[0].type != ACPI_TYPE_STRING)
 			continue;
 
-		/* The second one may be a string, a reference or a package. */
+		/* The second one (the target) may be a string or a package. */
 		switch (link->package.elements[1].type) {
 		case ACPI_TYPE_STRING:
+			/*
+			 * The string is expected to be a full pathname or a
+			 * pathname segment relative to the given scope.  That
+			 * pathname is expected to point to an object returning
+			 * a package that contains _DSD-equivalent information.
+			 */
 			result = acpi_nondev_subnode_ok(scope, link, list,
 							 parent);
 			break;
-		case ACPI_TYPE_LOCAL_REFERENCE:
-			handle = link->package.elements[1].reference.handle;
-			result = acpi_nondev_subnode_data_ok(handle, link, list,
-							     parent);
-			break;
 		case ACPI_TYPE_PACKAGE:
+			/*
+			 * This happens when a reference is used in AML to
+			 * point to the target.  Since the target is expected
+			 * to be a named object, a reference to it will cause it
+			 * to be avaluated in place and its return package will
+			 * be embedded in the links package at the location of
+			 * the reference.
+			 *
+			 * The target package is expected to contain _DSD-
+			 * equivalent information, but the scope in which it
+			 * is located in the original AML is unknown.  Thus
+			 * it cannot contain pathname segments represented as
+			 * strings because there is no way to build full
+			 * pathnames out of them.
+			 */
+			acpi_handle_debug(scope, "subnode %s: Unknown scope\n",
+					  link->package.elements[0].string.pointer);
 			desc = &link->package.elements[1];
 			result = acpi_nondev_subnode_extract(desc, NULL, link,
 							     list, parent);
 			break;
+		case ACPI_TYPE_LOCAL_REFERENCE:
+			/*
+			 * It is not expected to see any local references in
+			 * the links package because referencing a named object
+			 * should cause it to be evaluated in place.
+			 */
+			acpi_handle_info(scope, "subnode %s: Unexpected reference\n",
+					 link->package.elements[0].string.pointer);
+			fallthrough;
 		default:
 			result = false;
 			break;
@@ -358,6 +403,9 @@ static void acpi_untie_nondev_subnodes(struct acpi_device_data *data)
 	struct acpi_data_node *dn;
 
 	list_for_each_entry(dn, &data->subnodes, sibling) {
+		if (!dn->handle)
+			continue;
+
 		acpi_detach_data(dn->handle, acpi_nondev_subnode_tag);
 
 		acpi_untie_nondev_subnodes(&dn->data);
@@ -372,6 +420,9 @@ static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data)
 		acpi_status status;
 		bool ret;
 
+		if (!dn->handle)
+			continue;
+
 		status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn);
 		if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) {
 			acpi_handle_err(dn->handle, "Can't tag data node\n");
@@ -793,35 +844,45 @@ acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
 	return NULL;
 }
 
+static unsigned int acpi_fwnode_get_args_count(struct fwnode_handle *fwnode,
+					       const char *nargs_prop)
+{
+	const struct acpi_device_data *data;
+	const union acpi_object *obj;
+	int ret;
+
+	data = acpi_device_data_of_node(fwnode);
+	if (!data)
+		return 0;
+
+	ret = acpi_data_get_property(data, nargs_prop, ACPI_TYPE_INTEGER, &obj);
+	if (ret)
+		return 0;
+
+	return obj->integer.value;
+}
+
 static int acpi_get_ref_args(struct fwnode_reference_args *args,
 			     struct fwnode_handle *ref_fwnode,
+			     const char *nargs_prop,
 			     const union acpi_object **element,
 			     const union acpi_object *end, size_t num_args)
 {
 	u32 nargs = 0, i;
 
-	/*
-	 * Find the referred data extension node under the
-	 * referred device node.
-	 */
-	for (; *element < end && (*element)->type == ACPI_TYPE_STRING;
-	     (*element)++) {
-		const char *child_name = (*element)->string.pointer;
-
-		ref_fwnode = acpi_fwnode_get_named_child_node(ref_fwnode, child_name);
-		if (!ref_fwnode)
-			return -EINVAL;
-	}
+	if (nargs_prop)
+		num_args = acpi_fwnode_get_args_count(ref_fwnode, nargs_prop);
 
 	/*
 	 * Assume the following integer elements are all args. Stop counting on
-	 * the first reference or end of the package arguments. In case of
-	 * neither reference, nor integer, return an error, we can't parse it.
+	 * the first reference (possibly represented as a string) or end of the
+	 * package arguments. In case of neither reference, nor integer, return
+	 * an error, we can't parse it.
 	 */
 	for (i = 0; (*element) + i < end && i < num_args; i++) {
 		acpi_object_type type = (*element)[i].type;
 
-		if (type == ACPI_TYPE_LOCAL_REFERENCE)
+		if (type == ACPI_TYPE_LOCAL_REFERENCE || type == ACPI_TYPE_STRING)
 			break;
 
 		if (type == ACPI_TYPE_INTEGER)
@@ -845,48 +906,53 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args,
 	return 0;
 }
 
-/**
- * __acpi_node_get_property_reference - returns handle to the referenced object
- * @fwnode: Firmware node to get the property from
- * @propname: Name of the property
- * @index: Index of the reference to return
- * @num_args: Maximum number of arguments after each reference
- * @args: Location to store the returned reference with optional arguments
- *
- * Find property with @name, verifify that it is a package containing at least
- * one object reference and if so, store the ACPI device object pointer to the
- * target object in @args->adev.  If the reference includes arguments, store
- * them in the @args->args[] array.
- *
- * If there's more than one reference in the property value package, @index is
- * used to select the one to return.
- *
- * It is possible to leave holes in the property value set like in the
- * example below:
- *
- * Package () {
- *     "cs-gpios",
- *     Package () {
- *        ^GPIO, 19, 0, 0,
- *        ^GPIO, 20, 0, 0,
- *        0,
- *        ^GPIO, 21, 0, 0,
- *     }
- * }
- *
- * Calling this function with index %2 or index %3 return %-ENOENT. If the
- * property does not contain any more values %-ENOENT is returned. The NULL
- * entry must be single integer and preferably contain value %0.
- *
- * Return: %0 on success, negative error code on failure.
- */
-int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
-	const char *propname, size_t index, size_t num_args,
-	struct fwnode_reference_args *args)
+static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *fwnode,
+						   const char *refstring)
+{
+	acpi_handle scope, handle;
+	struct acpi_data_node *dn;
+	struct acpi_device *device;
+	acpi_status status;
+
+	if (is_acpi_device_node(fwnode)) {
+		scope = to_acpi_device_node(fwnode)->handle;
+	} else if (is_acpi_data_node(fwnode)) {
+		scope = to_acpi_data_node(fwnode)->handle;
+	} else {
+		pr_debug("Bad node type for node %pfw\n", fwnode);
+		return NULL;
+	}
+
+	status = acpi_get_handle(scope, refstring, &handle);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_debug(scope, "Unable to get an ACPI handle for %s\n",
+				  refstring);
+		return NULL;
+	}
+
+	device = acpi_fetch_acpi_dev(handle);
+	if (device)
+		return acpi_fwnode_handle(device);
+
+	status = acpi_get_data_full(handle, acpi_nondev_subnode_tag,
+				    (void **)&dn, NULL);
+	if (ACPI_FAILURE(status) || !dn) {
+		acpi_handle_debug(handle, "Subnode not found\n");
+		return NULL;
+	}
+
+	return &dn->fwnode;
+}
+
+static int acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
+					  const char *propname, const char *nargs_prop,
+					  unsigned int args_count, unsigned int index,
+					  struct fwnode_reference_args *args)
 {
 	const union acpi_object *element, *end;
 	const union acpi_object *obj;
 	const struct acpi_device_data *data;
+	struct fwnode_handle *ref_fwnode;
 	struct acpi_device *device;
 	int ret, idx = 0;
 
@@ -908,18 +974,35 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (!device)
 			return -EINVAL;
 
+		if (!args)
+			return 0;
+
 		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
+
+		return 0;
+	case ACPI_TYPE_STRING:
+		if (index)
+			return -ENOENT;
+
+		ref_fwnode = acpi_parse_string_ref(fwnode, obj->string.pointer);
+		if (!ref_fwnode)
+			return -EINVAL;
+
+		args->fwnode = ref_fwnode;
+		args->nargs = 0;
+
 		return 0;
 	case ACPI_TYPE_PACKAGE:
 		/*
 		 * If it is not a single reference, then it is a package of
-		 * references followed by number of ints as follows:
+		 * references, followed by number of ints as follows:
 		 *
 		 *  Package () { REF, INT, REF, INT, INT }
 		 *
-		 * The index argument is then used to determine which reference
-		 * the caller wants (along with the arguments).
+		 * Here, REF may be either a local reference or a string. The
+		 * index argument is then used to determine which reference the
+		 * caller wants (along with the arguments).
 		 */
 		break;
 	default:
@@ -940,10 +1023,27 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				return -EINVAL;
 
 			element++;
-
 			ret = acpi_get_ref_args(idx == index ? args : NULL,
 						acpi_fwnode_handle(device),
-						&element, end, num_args);
+						nargs_prop, &element, end,
+						args_count);
+			if (ret < 0)
+				return ret;
+
+			if (idx == index)
+				return 0;
+
+			break;
+		case ACPI_TYPE_STRING:
+			ref_fwnode = acpi_parse_string_ref(fwnode,
+							   element->string.pointer);
+			if (!ref_fwnode)
+				return -EINVAL;
+
+			element++;
+			ret = acpi_get_ref_args(idx == index ? args : NULL,
+						ref_fwnode, nargs_prop, &element, end,
+						args_count);
 			if (ret < 0)
 				return ret;
 
@@ -965,6 +1065,50 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 
 	return -ENOENT;
 }
+
+/**
+ * __acpi_node_get_property_reference - returns handle to the referenced object
+ * @fwnode: Firmware node to get the property from
+ * @propname: Name of the property
+ * @index: Index of the reference to return
+ * @num_args: Maximum number of arguments after each reference
+ * @args: Location to store the returned reference with optional arguments
+ *	  (may be NULL)
+ *
+ * Find property with @name, verifify that it is a package containing at least
+ * one object reference and if so, store the ACPI device object pointer to the
+ * target object in @args->adev.  If the reference includes arguments, store
+ * them in the @args->args[] array.
+ *
+ * If there's more than one reference in the property value package, @index is
+ * used to select the one to return.
+ *
+ * It is possible to leave holes in the property value set like in the
+ * example below:
+ *
+ * Package () {
+ *     "cs-gpios",
+ *     Package () {
+ *        ^GPIO, 19, 0, 0,
+ *        ^GPIO, 20, 0, 0,
+ *        0,
+ *        ^GPIO, 21, 0, 0,
+ *     }
+ * }
+ *
+ * Calling this function with index %2 or index %3 return %-ENOENT. If the
+ * property does not contain any more values %-ENOENT is returned. The NULL
+ * entry must be single integer and preferably contain value %0.
+ *
+ * Return: %0 on success, negative error code on failure.
+ */
+int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
+				       const char *propname, size_t index,
+				       size_t num_args,
+				       struct fwnode_reference_args *args)
+{
+	return acpi_fwnode_get_reference_args(fwnode, propname, NULL, index, num_args, args);
+}
 EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference);
 
 static int acpi_data_prop_read_single(const struct acpi_device_data *data,
@@ -1113,8 +1257,6 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		}
 		break;
 	}
-	if (nval == 0)
-		return -EINVAL;
 
 	if (obj->type == ACPI_TYPE_BUFFER) {
 		if (proptype != DEV_PROP_U8)
@@ -1138,9 +1280,11 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		ret = acpi_copy_property_array_uint(items, (u64 *)val, nval);
 		break;
 	case DEV_PROP_STRING:
-		ret = acpi_copy_property_array_string(
-			items, (char **)val,
-			min_t(u32, nval, obj->package.count));
+		nval = min_t(u32, nval, obj->package.count);
+		if (nval == 0)
+			return -ENODATA;
+
+		ret = acpi_copy_property_array_string(items, (char **)val, nval);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1244,6 +1388,28 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 	return NULL;
 }
 
+/*
+ * acpi_get_next_present_subnode - Return the next present child node handle
+ * @fwnode: Firmware node to find the next child node for.
+ * @child: Handle to one of the device's child nodes or a null handle.
+ *
+ * Like acpi_get_next_subnode(), but the device nodes returned by
+ * acpi_get_next_present_subnode() are guaranteed to be present.
+ *
+ * Returns: The fwnode handle of the next present sub-node.
+ */
+static struct fwnode_handle *
+acpi_get_next_present_subnode(const struct fwnode_handle *fwnode,
+			      struct fwnode_handle *child)
+{
+	do {
+		child = acpi_get_next_subnode(fwnode, child);
+	} while (is_acpi_device_node(child) &&
+		 !acpi_device_is_present(to_acpi_device_node(child)));
+
+	return child;
+}
+
 /**
  * acpi_node_get_parent - Return parent fwnode of this fwnode
  * @fwnode: Firmware node whose parent to get
@@ -1418,7 +1584,7 @@ acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
 {
 	if (!is_acpi_device_node(fwnode))
-		return false;
+		return true;
 
 	return acpi_device_is_present(to_acpi_device_node(fwnode));
 }
@@ -1484,16 +1650,6 @@ acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 				   val, nval);
 }
 
-static int
-acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
-			       const char *prop, const char *nargs_prop,
-			       unsigned int args_count, unsigned int index,
-			       struct fwnode_reference_args *args)
-{
-	return __acpi_node_get_property_reference(fwnode, prop, index,
-						  args_count, args);
-}
-
 static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode)
 {
 	const struct acpi_device *adev;
@@ -1582,12 +1738,13 @@ static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode,
 			acpi_fwnode_device_dma_supported,		\
 		.device_get_dma_attr = acpi_fwnode_device_get_dma_attr,	\
 		.property_present = acpi_fwnode_property_present,	\
+		.property_read_bool = acpi_fwnode_property_present,	\
 		.property_read_int_array =				\
 			acpi_fwnode_property_read_int_array,		\
 		.property_read_string_array =				\
 			acpi_fwnode_property_read_string_array,		\
 		.get_parent = acpi_node_get_parent,			\
-		.get_next_child_node = acpi_get_next_subnode,		\
+		.get_next_child_node = acpi_get_next_present_subnode,	\
 		.get_named_child_node = acpi_fwnode_get_named_child_node, \
 		.get_name = acpi_fwnode_get_name,			\
 		.get_name_prefix = acpi_fwnode_get_name_prefix,		\
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 15a3bdbd0755..d16906f46484 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/irq.h>
 #include <linux/dmi.h>
+#include <linux/string_choices.h>
 
 #ifdef CONFIG_X86
 #define valid_IRQ(i) (((i) != 0) && ((i) != 2))
@@ -250,6 +251,9 @@ static bool acpi_decode_space(struct resource_win *win,
 	switch (addr->resource_type) {
 	case ACPI_MEMORY_RANGE:
 		acpi_dev_memresource_flags(res, len, wp);
+
+		if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
+			res->flags |= IORESOURCE_PREFETCH;
 		break;
 	case ACPI_IO_RANGE:
 		acpi_dev_ioresource_flags(res, len, iodec,
@@ -265,9 +269,6 @@ static bool acpi_decode_space(struct resource_win *win,
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 
-	if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
-		res->flags |= IORESOURCE_PREFETCH;
-
 	return !(res->flags & IORESOURCE_DISABLED);
 }
 
@@ -441,38 +442,80 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
-		/* Asus ExpertBook B1402CBA */
+		/* Asus Vivobook X1404VAP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "X1404VAP"),
+		},
+	},
+	{
+		/* Asus Vivobook X1504VAP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "X1504VAP"),
+		},
+	},
+	{
+		/* Asus Vivobook X1704VAP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "X1704VAP"),
+		},
+	},
+	{
+		/* Asus ExpertBook B1402C* */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1402C"),
+		},
+	},
+	{
+		/* Asus ExpertBook B1502C* */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1502C"),
+		},
+	},
+	{
+		/* Asus ExpertBook B2402 (B2402CBA / B2402FBA / B2402CVA / B2402FVA) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B2402"),
+		},
+	},
+	{
+		/* Asus ExpertBook B2502 (B2502CBA / B2502FBA / B2502CVA / B2502FVA) */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_BOARD_NAME, "B1402CBA"),
+			DMI_MATCH(DMI_BOARD_NAME, "B2502"),
 		},
 	},
 	{
-		/* Asus ExpertBook B1502CBA */
+		/* Asus Vivobook Go E1404GA* */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_BOARD_NAME, "B1502CBA"),
+			DMI_MATCH(DMI_BOARD_NAME, "E1404GA"),
 		},
 	},
 	{
-		/* Asus ExpertBook B2402CBA */
+		/* Asus Vivobook E1504GA* */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"),
+			DMI_MATCH(DMI_BOARD_NAME, "E1504GA"),
 		},
 	},
 	{
-		/* Asus ExpertBook B2402FBA */
+		/* Asus Vivobook Pro N6506M* */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_BOARD_NAME, "B2402FBA"),
+			DMI_MATCH(DMI_BOARD_NAME, "N6506M"),
 		},
 	},
 	{
-		/* Asus ExpertBook B2502 */
+		/* Asus Vivobook Pro N6506CU* */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"),
+			DMI_MATCH(DMI_BOARD_NAME, "N6506CU"),
 		},
 	},
 	{
@@ -482,6 +525,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "17U70P"),
 		},
 	},
+	{
+		/* LG Electronics 16T90SP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+			DMI_MATCH(DMI_BOARD_NAME, "16T90SP"),
+		},
+	},
 	{ }
 };
 
@@ -492,6 +542,18 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
  */
 static const struct dmi_system_id irq1_edge_low_force_override[] = {
 	{
+		/* MECHREVO Jiaolong17KS Series GM7XG0M */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GM7XG0M"),
+		},
+	},
+	{
+		/* XMG APEX 17 (M23) */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GMxBGxx"),
+		},
+	},
+	{
 		/* TongFang GMxRGxx/XMG CORE 15 (M22)/TUXEDO Stellaris 15 Gen4 AMD */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"),
@@ -504,6 +566,25 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 		},
 	},
 	{
+		/* TongFang GMxXGxX/TUXEDO Polaris 15 Gen5 AMD */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GMxXGxX"),
+		},
+	},
+	{
+		/* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "RP-15"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "MECH-17"),
+		},
+	},
+	{
 		/* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"),
@@ -541,6 +622,76 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6BG0Q"),
 		},
 	},
+	{
+		/* Infinity E15-5A165-BM */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GM5RG1E0009COM"),
+		},
+	},
+	{
+		/* Infinity E15-5A305-1M */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GM5RGEE0016COM"),
+		},
+	},
+	{
+		/* Lunnen Ground 15 / AMD Ryzen 5 5500U */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"),
+			DMI_MATCH(DMI_BOARD_NAME, "LLL5DAW"),
+		},
+	},
+	{
+		/* Lunnen Ground 16 / AMD Ryzen 7 5800U */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"),
+			DMI_MATCH(DMI_BOARD_NAME, "LL6FA"),
+		},
+	},
+	{
+		/* MAIBENBEN X577 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MAIBENBEN"),
+			DMI_MATCH(DMI_BOARD_NAME, "X577"),
+		},
+	},
+	{
+		/* Maibenben X565 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MAIBENBEN"),
+			DMI_MATCH(DMI_BOARD_NAME, "X565"),
+		},
+	},
+	{
+		/* TongFang GXxHRXx/TUXEDO InfinityBook Pro Gen9 AMD */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GXxHRXx"),
+		},
+	},
+	{
+		/* TongFang GMxHGxx/TUXEDO Stellaris Slim Gen1 AMD */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"),
+		},
+	},
+	{
+		/* MACHENIKE L16P/L16P */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MACHENIKE"),
+			DMI_MATCH(DMI_BOARD_NAME, "L16P"),
+		},
+	},
+	{
+		/*
+		 * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the
+		 * board-name is changed, so check OEM strings instead. Note
+		 * OEM string matches are always exact matches.
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=219614
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_OEM_STRING, "GM5HG0A"),
+		},
+	},
 	{ }
 };
 
@@ -566,11 +717,11 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,
 	for (i = 0; i < ARRAY_SIZE(override_table); i++) {
 		const struct irq_override_cmp *entry = &override_table[i];
 
-		if (dmi_check_system(entry->system) &&
-		    entry->irq == gsi &&
+		if (entry->irq == gsi &&
 		    entry->triggering == triggering &&
 		    entry->polarity == polarity &&
-		    entry->shareable == shareable)
+		    entry->shareable == shareable &&
+		    dmi_check_system(entry->system))
 			return entry->override;
 	}
 
@@ -630,7 +781,7 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
 			pr_warn("ACPI: IRQ %d override to %s%s, %s%s\n", gsi,
 				t ? "level" : "edge",
 				trig == triggering ? "" : "(!)",
-				p ? "low" : "high",
+				str_low_high(p),
 				pol == polarity ? "" : "(!)");
 			triggering = trig;
 			polarity = pol;
diff --git a/drivers/acpi/riscv/Kconfig b/drivers/acpi/riscv/Kconfig
new file mode 100644
index 000000000000..046296a18d00
--- /dev/null
+++ b/drivers/acpi/riscv/Kconfig
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# ACPI Configuration for RISC-V
+#
+
+config ACPI_RIMT
+	bool
diff --git a/drivers/acpi/riscv/Makefile b/drivers/acpi/riscv/Makefile
index 8b3b126e0b94..1284a076fa88 100644
--- a/drivers/acpi/riscv/Makefile
+++ b/drivers/acpi/riscv/Makefile
@@ -1,2 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y 	+= rhct.o
+obj-y					+= rhct.o init.o irq.o
+obj-$(CONFIG_ACPI_PROCESSOR_IDLE)	+= cpuidle.o
+obj-$(CONFIG_ACPI_CPPC_LIB)		+= cppc.o
+obj-$(CONFIG_ACPI_RIMT)			+= rimt.o
diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c
new file mode 100644
index 000000000000..42c1a9052470
--- /dev/null
+++ b/drivers/acpi/riscv/cppc.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implement CPPC FFH helper routines for RISC-V.
+ *
+ * Copyright (C) 2024 Ventana Micro Systems Inc.
+ */
+
+#include <acpi/cppc_acpi.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+
+#define SBI_EXT_CPPC 0x43505043
+
+/* CPPC interfaces defined in SBI spec */
+#define SBI_CPPC_PROBE			0x0
+#define SBI_CPPC_READ			0x1
+#define SBI_CPPC_READ_HI		0x2
+#define SBI_CPPC_WRITE			0x3
+
+/* RISC-V FFH definitions from RISC-V FFH spec */
+#define FFH_CPPC_TYPE(r)		(((r) & GENMASK_ULL(63, 60)) >> 60)
+#define FFH_CPPC_SBI_REG(r)		((r) & GENMASK(31, 0))
+#define FFH_CPPC_CSR_NUM(r)		((r) & GENMASK(11, 0))
+
+#define FFH_CPPC_SBI			0x1
+#define FFH_CPPC_CSR			0x2
+
+struct sbi_cppc_data {
+	u64 val;
+	u32 reg;
+	struct sbiret ret;
+};
+
+static bool cppc_ext_present;
+
+static int __init sbi_cppc_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_CPPC) > 0) {
+		cppc_ext_present = true;
+	} else {
+		cppc_ext_present = false;
+	}
+
+	return 0;
+}
+device_initcall(sbi_cppc_init);
+
+static void sbi_cppc_read(void *read_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)read_data;
+
+	data->ret = sbi_ecall(SBI_EXT_CPPC, SBI_CPPC_READ,
+			      data->reg, 0, 0, 0, 0, 0);
+}
+
+static void sbi_cppc_write(void *write_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)write_data;
+
+	data->ret = sbi_ecall(SBI_EXT_CPPC, SBI_CPPC_WRITE,
+			      data->reg, data->val, 0, 0, 0, 0);
+}
+
+static void cppc_ffh_csr_read(void *read_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)read_data;
+
+	switch (data->reg) {
+	/* Support only TIME CSR for now */
+	case CSR_TIME:
+		data->ret.value = csr_read(CSR_TIME);
+		data->ret.error = 0;
+		break;
+	default:
+		data->ret.error = -EINVAL;
+		break;
+	}
+}
+
+static void cppc_ffh_csr_write(void *write_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)write_data;
+
+	data->ret.error = -EINVAL;
+}
+
+/*
+ * Refer to drivers/acpi/cppc_acpi.c for the description of the functions
+ * below.
+ */
+bool cpc_ffh_supported(void)
+{
+	return true;
+}
+
+int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
+{
+	struct sbi_cppc_data data;
+
+	if (WARN_ON_ONCE(irqs_disabled()))
+		return -EPERM;
+
+	if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_SBI) {
+		if (!cppc_ext_present)
+			return -EINVAL;
+
+		data.reg = FFH_CPPC_SBI_REG(reg->address);
+
+		smp_call_function_single(cpu, sbi_cppc_read, &data, 1);
+
+		*val = data.ret.value;
+
+		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+	} else if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_CSR) {
+		data.reg = FFH_CPPC_CSR_NUM(reg->address);
+
+		smp_call_function_single(cpu, cppc_ffh_csr_read, &data, 1);
+
+		*val = data.ret.value;
+
+		return data.ret.error;
+	}
+
+	return -EINVAL;
+}
+
+int cpc_write_ffh(int cpu, struct cpc_reg *reg, u64 val)
+{
+	struct sbi_cppc_data data;
+
+	if (WARN_ON_ONCE(irqs_disabled()))
+		return -EPERM;
+
+	if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_SBI) {
+		if (!cppc_ext_present)
+			return -EINVAL;
+
+		data.reg = FFH_CPPC_SBI_REG(reg->address);
+		data.val = val;
+
+		smp_call_function_single(cpu, sbi_cppc_write, &data, 1);
+
+		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+	} else if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_CSR) {
+		data.reg = FFH_CPPC_CSR_NUM(reg->address);
+		data.val = val;
+
+		smp_call_function_single(cpu, cppc_ffh_csr_write, &data, 1);
+
+		return data.ret.error;
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/acpi/riscv/cpuidle.c b/drivers/acpi/riscv/cpuidle.c
new file mode 100644
index 000000000000..624f9bbdb58c
--- /dev/null
+++ b/drivers/acpi/riscv/cpuidle.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024, Ventana Micro Systems Inc
+ *	Author: Sunil V L <sunilvl@ventanamicro.com>
+ *
+ */
+
+#include <linux/acpi.h>
+#include <acpi/processor.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpuidle.h>
+#include <linux/suspend.h>
+#include <asm/cpuidle.h>
+#include <asm/sbi.h>
+#include <asm/suspend.h>
+
+#define RISCV_FFH_LPI_TYPE_MASK	GENMASK_ULL(63, 60)
+#define RISCV_FFH_LPI_RSVD_MASK	GENMASK_ULL(59, 32)
+
+#define RISCV_FFH_LPI_TYPE_SBI	BIT_ULL(60)
+
+static int acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	if (!riscv_sbi_hsm_is_supported())
+		return -ENODEV;
+
+	if (pr->power.count <= 1)
+		return -ENODEV;
+
+	for (i = 1; i < pr->power.count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i];
+
+		/*
+		 * Validate Entry Method as per FFH spec.
+		 * bits[63:60] should be 0x1
+		 * bits[59:32] should be 0x0
+		 * bits[31:0] represent a SBI power_state
+		 */
+		if (((lpi->address & RISCV_FFH_LPI_TYPE_MASK) != RISCV_FFH_LPI_TYPE_SBI) ||
+		    (lpi->address & RISCV_FFH_LPI_RSVD_MASK)) {
+			pr_warn("Invalid LPI entry method %#llx\n", lpi->address);
+			return -EINVAL;
+		}
+
+		state = lpi->address;
+		if (!riscv_sbi_suspend_state_is_valid(state)) {
+			pr_warn("Invalid SBI power state %#x\n", state);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+int acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+	return acpi_cpu_init_idle(cpu);
+}
+
+int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+	u32 state = lpi->address;
+
+	if (state & SBI_HSM_SUSP_NON_RET_BIT)
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(riscv_sbi_hart_suspend,
+						   lpi->index,
+						   state);
+	else
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(riscv_sbi_hart_suspend,
+							     lpi->index,
+							     state);
+}
diff --git a/drivers/acpi/riscv/init.c b/drivers/acpi/riscv/init.c
new file mode 100644
index 000000000000..7c00f7995e86
--- /dev/null
+++ b/drivers/acpi/riscv/init.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023-2024, Ventana Micro Systems Inc
+ *	Author: Sunil V L <sunilvl@ventanamicro.com>
+ */
+
+#include <linux/acpi.h>
+#include "init.h"
+
+void __init acpi_arch_init(void)
+{
+	riscv_acpi_init_gsi_mapping();
+	if (IS_ENABLED(CONFIG_ACPI_RIMT))
+		riscv_acpi_rimt_init();
+}
diff --git a/drivers/acpi/riscv/init.h b/drivers/acpi/riscv/init.h
new file mode 100644
index 000000000000..1680aa2aaf23
--- /dev/null
+++ b/drivers/acpi/riscv/init.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/init.h>
+
+void __init riscv_acpi_init_gsi_mapping(void);
+void __init riscv_acpi_rimt_init(void);
diff --git a/drivers/acpi/riscv/irq.c b/drivers/acpi/riscv/irq.c
new file mode 100644
index 000000000000..d9a2154d6c6a
--- /dev/null
+++ b/drivers/acpi/riscv/irq.c
@@ -0,0 +1,404 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023-2024, Ventana Micro Systems Inc
+ *	Author: Sunil V L <sunilvl@ventanamicro.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/sort.h>
+#include <linux/irq.h>
+
+#include "init.h"
+
+#define RISCV_ACPI_INTC_FLAG_PENDING BIT(0)
+
+struct riscv_ext_intc_list {
+	acpi_handle		handle;
+	u32			gsi_base;
+	u32			nr_irqs;
+	u32			nr_idcs;
+	u32			id;
+	u32			type;
+	u32			flag;
+	struct list_head	list;
+};
+
+struct acpi_irq_dep_ctx {
+	int		rc;
+	unsigned int	index;
+	acpi_handle	handle;
+};
+
+LIST_HEAD(ext_intc_list);
+
+static int irqchip_cmp_func(const void *in0, const void *in1)
+{
+	struct acpi_probe_entry *elem0 = (struct acpi_probe_entry *)in0;
+	struct acpi_probe_entry *elem1 = (struct acpi_probe_entry *)in1;
+
+	return (elem0->type > elem1->type) - (elem0->type < elem1->type);
+}
+
+/*
+ * On RISC-V, RINTC structures in MADT should be probed before any other
+ * interrupt controller structures and IMSIC before APLIC. The interrupt
+ * controller subtypes in MADT of ACPI spec for RISC-V are defined in
+ * the incremental order like RINTC(24)->IMSIC(25)->APLIC(26)->PLIC(27).
+ * Hence, simply sorting the subtypes in incremental order will
+ * establish the required order.
+ */
+void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr)
+{
+	struct acpi_probe_entry *ape = ap_head;
+
+	if (nr == 1 || !ACPI_COMPARE_NAMESEG(ACPI_SIG_MADT, ape->id))
+		return;
+	sort(ape, nr, sizeof(*ape), irqchip_cmp_func, NULL);
+}
+
+static acpi_status riscv_acpi_update_gsi_handle(u32 gsi_base, acpi_handle handle)
+{
+	struct riscv_ext_intc_list *ext_intc_element;
+	struct list_head *i, *tmp;
+
+	list_for_each_safe(i, tmp, &ext_intc_list) {
+		ext_intc_element = list_entry(i, struct riscv_ext_intc_list, list);
+		if (gsi_base == ext_intc_element->gsi_base) {
+			ext_intc_element->handle = handle;
+			return AE_OK;
+		}
+	}
+
+	return AE_NOT_FOUND;
+}
+
+int riscv_acpi_update_gsi_range(u32 gsi_base, u32 nr_irqs)
+{
+	struct riscv_ext_intc_list *ext_intc_element;
+
+	list_for_each_entry(ext_intc_element, &ext_intc_list, list) {
+		if (gsi_base == ext_intc_element->gsi_base &&
+		    (ext_intc_element->flag & RISCV_ACPI_INTC_FLAG_PENDING)) {
+			ext_intc_element->nr_irqs = nr_irqs;
+			ext_intc_element->flag &= ~RISCV_ACPI_INTC_FLAG_PENDING;
+			return 0;
+		}
+	}
+
+	return -ENODEV;
+}
+
+int riscv_acpi_get_gsi_info(struct fwnode_handle *fwnode, u32 *gsi_base,
+			    u32 *id, u32 *nr_irqs, u32 *nr_idcs)
+{
+	struct riscv_ext_intc_list *ext_intc_element;
+	struct list_head *i;
+
+	list_for_each(i, &ext_intc_list) {
+		ext_intc_element = list_entry(i, struct riscv_ext_intc_list, list);
+		if (ext_intc_element->handle == ACPI_HANDLE_FWNODE(fwnode)) {
+			*gsi_base = ext_intc_element->gsi_base;
+			*id = ext_intc_element->id;
+			*nr_irqs = ext_intc_element->nr_irqs;
+			if (nr_idcs)
+				*nr_idcs = ext_intc_element->nr_idcs;
+
+			return 0;
+		}
+	}
+
+	return -ENODEV;
+}
+
+struct fwnode_handle *riscv_acpi_get_gsi_domain_id(u32 gsi)
+{
+	struct riscv_ext_intc_list *ext_intc_element;
+	struct acpi_device *adev;
+	struct list_head *i;
+
+	list_for_each(i, &ext_intc_list) {
+		ext_intc_element = list_entry(i, struct riscv_ext_intc_list, list);
+		if (gsi >= ext_intc_element->gsi_base &&
+		    gsi < (ext_intc_element->gsi_base + ext_intc_element->nr_irqs)) {
+			adev = acpi_fetch_acpi_dev(ext_intc_element->handle);
+			if (!adev)
+				return NULL;
+
+			return acpi_fwnode_handle(adev);
+		}
+	}
+
+	return NULL;
+}
+
+static int __init riscv_acpi_register_ext_intc(u32 gsi_base, u32 nr_irqs, u32 nr_idcs,
+					       u32 id, u32 type)
+{
+	struct riscv_ext_intc_list *ext_intc_element, *node, *prev;
+
+	ext_intc_element = kzalloc(sizeof(*ext_intc_element), GFP_KERNEL);
+	if (!ext_intc_element)
+		return -ENOMEM;
+
+	ext_intc_element->gsi_base = gsi_base;
+
+	/* If nr_irqs is zero, indicate it in flag and set to max range possible */
+	if (nr_irqs) {
+		ext_intc_element->nr_irqs = nr_irqs;
+	} else {
+		ext_intc_element->flag |= RISCV_ACPI_INTC_FLAG_PENDING;
+		ext_intc_element->nr_irqs = U32_MAX - ext_intc_element->gsi_base;
+	}
+
+	ext_intc_element->nr_idcs = nr_idcs;
+	ext_intc_element->id = id;
+	list_for_each_entry(node, &ext_intc_list, list) {
+		if (node->gsi_base < ext_intc_element->gsi_base)
+			break;
+	}
+
+	/* Adjust the previous node's GSI range if that has pending registration */
+	prev = list_prev_entry(node, list);
+	if (!list_entry_is_head(prev, &ext_intc_list, list)) {
+		if (prev->flag & RISCV_ACPI_INTC_FLAG_PENDING)
+			prev->nr_irqs = ext_intc_element->gsi_base - prev->gsi_base;
+	}
+
+	list_add_tail(&ext_intc_element->list, &node->list);
+	return 0;
+}
+
+static acpi_status __init riscv_acpi_create_gsi_map_smsi(acpi_handle handle, u32 level,
+							 void *context, void **return_value)
+{
+	acpi_status status;
+	u64 gbase;
+
+	if (!acpi_has_method(handle, "_GSB")) {
+		acpi_handle_err(handle, "_GSB method not found\n");
+		return AE_ERROR;
+	}
+
+	status = acpi_evaluate_integer(handle, "_GSB", NULL, &gbase);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_err(handle, "failed to evaluate _GSB method\n");
+		return status;
+	}
+
+	riscv_acpi_register_ext_intc(gbase, 0, 0, 0, ACPI_RISCV_IRQCHIP_SMSI);
+	status = riscv_acpi_update_gsi_handle((u32)gbase, handle);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_err(handle, "failed to find the GSI mapping entry\n");
+		return status;
+	}
+
+	return AE_OK;
+}
+
+static acpi_status __init riscv_acpi_create_gsi_map(acpi_handle handle, u32 level,
+						    void *context, void **return_value)
+{
+	acpi_status status;
+	u64 gbase;
+
+	if (!acpi_has_method(handle, "_GSB")) {
+		acpi_handle_err(handle, "_GSB method not found\n");
+		return AE_ERROR;
+	}
+
+	status = acpi_evaluate_integer(handle, "_GSB", NULL, &gbase);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_err(handle, "failed to evaluate _GSB method\n");
+		return status;
+	}
+
+	status = riscv_acpi_update_gsi_handle((u32)gbase, handle);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_err(handle, "failed to find the GSI mapping entry\n");
+		return status;
+	}
+
+	return AE_OK;
+}
+
+static int __init riscv_acpi_aplic_parse_madt(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_madt_aplic *aplic = (struct acpi_madt_aplic *)header;
+
+	return riscv_acpi_register_ext_intc(aplic->gsi_base, aplic->num_sources, aplic->num_idcs,
+					    aplic->id, ACPI_RISCV_IRQCHIP_APLIC);
+}
+
+static int __init riscv_acpi_plic_parse_madt(union acpi_subtable_headers *header,
+					     const unsigned long end)
+{
+	struct acpi_madt_plic *plic = (struct acpi_madt_plic *)header;
+
+	return riscv_acpi_register_ext_intc(plic->gsi_base, plic->num_irqs, 0,
+					    plic->id, ACPI_RISCV_IRQCHIP_PLIC);
+}
+
+void __init riscv_acpi_init_gsi_mapping(void)
+{
+	/* There can be either PLIC or APLIC */
+	if (acpi_table_parse_madt(ACPI_MADT_TYPE_PLIC, riscv_acpi_plic_parse_madt, 0) > 0) {
+		acpi_get_devices("RSCV0001", riscv_acpi_create_gsi_map, NULL, NULL);
+		return;
+	}
+
+	if (acpi_table_parse_madt(ACPI_MADT_TYPE_APLIC, riscv_acpi_aplic_parse_madt, 0) > 0)
+		acpi_get_devices("RSCV0002", riscv_acpi_create_gsi_map, NULL, NULL);
+
+	/* Unlike PLIC/APLIC, SYSMSI doesn't have MADT */
+	acpi_get_devices("RSCV0006", riscv_acpi_create_gsi_map_smsi, NULL, NULL);
+}
+
+static acpi_handle riscv_acpi_get_gsi_handle(u32 gsi)
+{
+	struct riscv_ext_intc_list *ext_intc_element;
+	struct list_head *i;
+
+	list_for_each(i, &ext_intc_list) {
+		ext_intc_element = list_entry(i, struct riscv_ext_intc_list, list);
+		if (gsi >= ext_intc_element->gsi_base &&
+		    gsi < (ext_intc_element->gsi_base + ext_intc_element->nr_irqs))
+			return ext_intc_element->handle;
+	}
+
+	return NULL;
+}
+
+static acpi_status riscv_acpi_irq_get_parent(struct acpi_resource *ares, void *context)
+{
+	struct acpi_irq_dep_ctx *ctx = context;
+	struct acpi_resource_irq *irq;
+	struct acpi_resource_extended_irq *eirq;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_IRQ:
+		irq = &ares->data.irq;
+		if (ctx->index >= irq->interrupt_count) {
+			ctx->index -= irq->interrupt_count;
+			return AE_OK;
+		}
+		ctx->handle = riscv_acpi_get_gsi_handle(irq->interrupts[ctx->index]);
+		return AE_CTRL_TERMINATE;
+	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+		eirq = &ares->data.extended_irq;
+		if (eirq->producer_consumer == ACPI_PRODUCER)
+			return AE_OK;
+
+		if (ctx->index >= eirq->interrupt_count) {
+			ctx->index -= eirq->interrupt_count;
+			return AE_OK;
+		}
+
+		/* Support GSIs only */
+		if (eirq->resource_source.string_length)
+			return AE_OK;
+
+		ctx->handle = riscv_acpi_get_gsi_handle(eirq->interrupts[ctx->index]);
+		return AE_CTRL_TERMINATE;
+	}
+
+	return AE_OK;
+}
+
+static int riscv_acpi_irq_get_dep(acpi_handle handle, unsigned int index, acpi_handle *gsi_handle)
+{
+	struct acpi_irq_dep_ctx ctx = {-EINVAL, index, NULL};
+
+	if (!gsi_handle)
+		return 0;
+
+	acpi_walk_resources(handle, METHOD_NAME__CRS, riscv_acpi_irq_get_parent, &ctx);
+	*gsi_handle = ctx.handle;
+	if (*gsi_handle)
+		return 1;
+
+	return 0;
+}
+
+static u32 riscv_acpi_add_prt_dep(acpi_handle handle)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_pci_routing_table *entry;
+	struct acpi_handle_list dep_devices;
+	acpi_handle gsi_handle;
+	acpi_handle link_handle;
+	acpi_status status;
+	u32 count = 0;
+
+	status = acpi_get_irq_routing_table(handle, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_err(handle, "failed to get IRQ routing table\n");
+		kfree(buffer.pointer);
+		return 0;
+	}
+
+	entry = buffer.pointer;
+	while (entry && (entry->length > 0)) {
+		if (entry->source[0]) {
+			acpi_get_handle(handle, entry->source, &link_handle);
+			dep_devices.count = 1;
+			dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL);
+			if (!dep_devices.handles) {
+				acpi_handle_err(handle, "failed to allocate memory\n");
+				continue;
+			}
+
+			dep_devices.handles[0] = link_handle;
+			count += acpi_scan_add_dep(handle, &dep_devices);
+		} else {
+			gsi_handle = riscv_acpi_get_gsi_handle(entry->source_index);
+			dep_devices.count = 1;
+			dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL);
+			if (!dep_devices.handles) {
+				acpi_handle_err(handle, "failed to allocate memory\n");
+				continue;
+			}
+
+			dep_devices.handles[0] = gsi_handle;
+			count += acpi_scan_add_dep(handle, &dep_devices);
+		}
+
+		entry = (struct acpi_pci_routing_table *)
+			((unsigned long)entry + entry->length);
+	}
+
+	kfree(buffer.pointer);
+	return count;
+}
+
+static u32 riscv_acpi_add_irq_dep(acpi_handle handle)
+{
+	struct acpi_handle_list dep_devices;
+	acpi_handle gsi_handle;
+	u32 count = 0;
+	int i;
+
+	for (i = 0;
+	     riscv_acpi_irq_get_dep(handle, i, &gsi_handle);
+	     i++) {
+		dep_devices.count = 1;
+		dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL);
+		if (!dep_devices.handles) {
+			acpi_handle_err(handle, "failed to allocate memory\n");
+			continue;
+		}
+
+		dep_devices.handles[0] = gsi_handle;
+		count += acpi_scan_add_dep(handle, &dep_devices);
+	}
+
+	return count;
+}
+
+u32 arch_acpi_add_auto_dep(acpi_handle handle)
+{
+	if (acpi_has_method(handle, "_PRT"))
+		return riscv_acpi_add_prt_dep(handle);
+
+	return riscv_acpi_add_irq_dep(handle);
+}
diff --git a/drivers/acpi/riscv/rimt.c b/drivers/acpi/riscv/rimt.c
new file mode 100644
index 000000000000..683fcfe35c31
--- /dev/null
+++ b/drivers/acpi/riscv/rimt.c
@@ -0,0 +1,520 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025, Ventana Micro Systems Inc
+ *	Author: Sunil V L <sunilvl@ventanamicro.com>
+ *
+ */
+
+#define pr_fmt(fmt)	"ACPI: RIMT: " fmt
+
+#include <linux/acpi.h>
+#include <linux/acpi_rimt.h>
+#include <linux/iommu.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include "init.h"
+
+struct rimt_fwnode {
+	struct list_head list;
+	struct acpi_rimt_node *rimt_node;
+	struct fwnode_handle *fwnode;
+};
+
+static LIST_HEAD(rimt_fwnode_list);
+static DEFINE_SPINLOCK(rimt_fwnode_lock);
+
+#define RIMT_TYPE_MASK(type)	(1 << (type))
+#define RIMT_IOMMU_TYPE		BIT(0)
+
+/* Root pointer to the mapped RIMT table */
+static struct acpi_table_header *rimt_table;
+
+/**
+ * rimt_set_fwnode() - Create rimt_fwnode and use it to register
+ *		       iommu data in the rimt_fwnode_list
+ *
+ * @rimt_node: RIMT table node associated with the IOMMU
+ * @fwnode: fwnode associated with the RIMT node
+ *
+ * Returns: 0 on success
+ *          <0 on failure
+ */
+static int rimt_set_fwnode(struct acpi_rimt_node *rimt_node,
+			   struct fwnode_handle *fwnode)
+{
+	struct rimt_fwnode *np;
+
+	np = kzalloc(sizeof(*np), GFP_ATOMIC);
+
+	if (WARN_ON(!np))
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&np->list);
+	np->rimt_node = rimt_node;
+	np->fwnode = fwnode;
+
+	spin_lock(&rimt_fwnode_lock);
+	list_add_tail(&np->list, &rimt_fwnode_list);
+	spin_unlock(&rimt_fwnode_lock);
+
+	return 0;
+}
+
+/**
+ * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node
+ *
+ * @node: RIMT table node to be looked-up
+ *
+ * Returns: fwnode_handle pointer on success, NULL on failure
+ */
+static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node)
+{
+	struct fwnode_handle *fwnode = NULL;
+	struct rimt_fwnode *curr;
+
+	spin_lock(&rimt_fwnode_lock);
+	list_for_each_entry(curr, &rimt_fwnode_list, list) {
+		if (curr->rimt_node == node) {
+			fwnode = curr->fwnode;
+			break;
+		}
+	}
+	spin_unlock(&rimt_fwnode_lock);
+
+	return fwnode;
+}
+
+static acpi_status rimt_match_node_callback(struct acpi_rimt_node *node,
+					    void *context)
+{
+	acpi_status status = AE_NOT_FOUND;
+	struct device *dev = context;
+
+	if (node->type == ACPI_RIMT_NODE_TYPE_IOMMU) {
+		struct acpi_rimt_iommu *iommu_node = (struct acpi_rimt_iommu *)&node->node_data;
+
+		if (dev_is_pci(dev)) {
+			struct pci_dev *pdev;
+			u16 bdf;
+
+			pdev = to_pci_dev(dev);
+			bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
+			if ((pci_domain_nr(pdev->bus) == iommu_node->pcie_segment_number) &&
+			    bdf == iommu_node->pcie_bdf) {
+				status = AE_OK;
+			} else {
+				status = AE_NOT_FOUND;
+			}
+		} else {
+			struct platform_device *pdev = to_platform_device(dev);
+			struct resource *res;
+
+			res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+			if (res && res->start == iommu_node->base_address)
+				status = AE_OK;
+			else
+				status = AE_NOT_FOUND;
+		}
+	} else if (node->type == ACPI_RIMT_NODE_TYPE_PCIE_ROOT_COMPLEX) {
+		struct acpi_rimt_pcie_rc *pci_rc;
+		struct pci_bus *bus;
+
+		bus = to_pci_bus(dev);
+		pci_rc = (struct acpi_rimt_pcie_rc *)node->node_data;
+
+		/*
+		 * It is assumed that PCI segment numbers maps one-to-one
+		 * with root complexes. Each segment number can represent only
+		 * one root complex.
+		 */
+		status = pci_rc->pcie_segment_number == pci_domain_nr(bus) ?
+							AE_OK : AE_NOT_FOUND;
+	} else if (node->type == ACPI_RIMT_NODE_TYPE_PLAT_DEVICE) {
+		struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+		struct acpi_rimt_platform_device *ncomp;
+		struct device *plat_dev = dev;
+		struct acpi_device *adev;
+
+		/*
+		 * Walk the device tree to find a device with an
+		 * ACPI companion; there is no point in scanning
+		 * RIMT for a device matching a platform device if
+		 * the device does not have an ACPI companion to
+		 * start with.
+		 */
+		do {
+			adev = ACPI_COMPANION(plat_dev);
+			if (adev)
+				break;
+
+			plat_dev = plat_dev->parent;
+		} while (plat_dev);
+
+		if (!adev)
+			return status;
+
+		status = acpi_get_name(adev->handle, ACPI_FULL_PATHNAME, &buf);
+		if (ACPI_FAILURE(status)) {
+			dev_warn(plat_dev, "Can't get device full path name\n");
+			return status;
+		}
+
+		ncomp = (struct acpi_rimt_platform_device *)node->node_data;
+		status = !strcmp(ncomp->device_name, buf.pointer) ?
+							AE_OK : AE_NOT_FOUND;
+		acpi_os_free(buf.pointer);
+	}
+
+	return status;
+}
+
+static struct acpi_rimt_node *rimt_scan_node(enum acpi_rimt_node_type type,
+					     void *context)
+{
+	struct acpi_rimt_node *rimt_node, *rimt_end;
+	struct acpi_table_rimt *rimt;
+	int i;
+
+	if (!rimt_table)
+		return NULL;
+
+	/* Get the first RIMT node */
+	rimt = (struct acpi_table_rimt *)rimt_table;
+	rimt_node = ACPI_ADD_PTR(struct acpi_rimt_node, rimt,
+				 rimt->node_offset);
+	rimt_end = ACPI_ADD_PTR(struct acpi_rimt_node, rimt_table,
+				rimt_table->length);
+
+	for (i = 0; i < rimt->num_nodes; i++) {
+		if (WARN_TAINT(rimt_node >= rimt_end, TAINT_FIRMWARE_WORKAROUND,
+			       "RIMT node pointer overflows, bad table!\n"))
+			return NULL;
+
+		if (rimt_node->type == type &&
+		    ACPI_SUCCESS(rimt_match_node_callback(rimt_node, context)))
+			return rimt_node;
+
+		rimt_node = ACPI_ADD_PTR(struct acpi_rimt_node, rimt_node,
+					 rimt_node->length);
+	}
+
+	return NULL;
+}
+
+static bool rimt_pcie_rc_supports_ats(struct acpi_rimt_node *node)
+{
+	struct acpi_rimt_pcie_rc *pci_rc;
+
+	pci_rc = (struct acpi_rimt_pcie_rc *)node->node_data;
+	return pci_rc->flags & ACPI_RIMT_PCIE_ATS_SUPPORTED;
+}
+
+static int rimt_iommu_xlate(struct device *dev, struct acpi_rimt_node *node, u32 deviceid)
+{
+	struct fwnode_handle *rimt_fwnode;
+
+	if (!node)
+		return -ENODEV;
+
+	rimt_fwnode = rimt_get_fwnode(node);
+
+	/*
+	 * The IOMMU drivers may not be probed yet.
+	 * Defer the IOMMU configuration
+	 */
+	if (!rimt_fwnode)
+		return -EPROBE_DEFER;
+
+	return acpi_iommu_fwspec_init(dev, deviceid, rimt_fwnode);
+}
+
+struct rimt_pci_alias_info {
+	struct device *dev;
+	struct acpi_rimt_node *node;
+	const struct iommu_ops *ops;
+};
+
+static int rimt_id_map(struct acpi_rimt_id_mapping *map, u8 type, u32 rid_in, u32 *rid_out)
+{
+	if (rid_in < map->source_id_base ||
+	    (rid_in > map->source_id_base + map->num_ids))
+		return -ENXIO;
+
+	*rid_out = map->dest_id_base + (rid_in - map->source_id_base);
+	return 0;
+}
+
+static struct acpi_rimt_node *rimt_node_get_id(struct acpi_rimt_node *node,
+					       u32 *id_out, int index)
+{
+	struct acpi_rimt_platform_device *plat_node;
+	u32 id_mapping_offset, num_id_mapping;
+	struct acpi_rimt_pcie_rc *pci_node;
+	struct acpi_rimt_id_mapping *map;
+	struct acpi_rimt_node *parent;
+
+	if (node->type == ACPI_RIMT_NODE_TYPE_PCIE_ROOT_COMPLEX) {
+		pci_node = (struct acpi_rimt_pcie_rc *)&node->node_data;
+		id_mapping_offset = pci_node->id_mapping_offset;
+		num_id_mapping = pci_node->num_id_mappings;
+	} else if (node->type == ACPI_RIMT_NODE_TYPE_PLAT_DEVICE) {
+		plat_node = (struct acpi_rimt_platform_device *)&node->node_data;
+		id_mapping_offset = plat_node->id_mapping_offset;
+		num_id_mapping = plat_node->num_id_mappings;
+	} else {
+		return NULL;
+	}
+
+	if (!id_mapping_offset || !num_id_mapping || index >= num_id_mapping)
+		return NULL;
+
+	map = ACPI_ADD_PTR(struct acpi_rimt_id_mapping, node,
+			   id_mapping_offset + index * sizeof(*map));
+
+	/* Firmware bug! */
+	if (!map->dest_offset) {
+		pr_err(FW_BUG "[node %p type %d] ID map has NULL parent reference\n",
+		       node, node->type);
+		return NULL;
+	}
+
+	parent = ACPI_ADD_PTR(struct acpi_rimt_node, rimt_table, map->dest_offset);
+
+	if (node->type == ACPI_RIMT_NODE_TYPE_PLAT_DEVICE ||
+	    node->type == ACPI_RIMT_NODE_TYPE_PCIE_ROOT_COMPLEX) {
+		*id_out = map->dest_id_base;
+		return parent;
+	}
+
+	return NULL;
+}
+
+/*
+ * RISC-V supports IOMMU as a PCI device or a platform device.
+ * When it is a platform device, there should be a namespace device as
+ * well along with RIMT. To create the link between RIMT information and
+ * the platform device, the IOMMU driver should register itself with the
+ * RIMT module. This is true for PCI based IOMMU as well.
+ */
+int rimt_iommu_register(struct device *dev)
+{
+	struct fwnode_handle *rimt_fwnode;
+	struct acpi_rimt_node *node;
+
+	node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev);
+	if (!node) {
+		pr_err("Could not find IOMMU node in RIMT\n");
+		return -ENODEV;
+	}
+
+	if (dev_is_pci(dev)) {
+		rimt_fwnode = acpi_alloc_fwnode_static();
+		if (!rimt_fwnode)
+			return -ENOMEM;
+
+		rimt_fwnode->dev = dev;
+		if (!dev->fwnode)
+			dev->fwnode = rimt_fwnode;
+
+		rimt_set_fwnode(node, rimt_fwnode);
+	} else {
+		rimt_set_fwnode(node, dev->fwnode);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_IOMMU_API
+
+static struct acpi_rimt_node *rimt_node_map_id(struct acpi_rimt_node *node,
+					       u32 id_in, u32 *id_out,
+					       u8 type_mask)
+{
+	struct acpi_rimt_platform_device *plat_node;
+	u32 id_mapping_offset, num_id_mapping;
+	struct acpi_rimt_pcie_rc *pci_node;
+	u32 id = id_in;
+
+	/* Parse the ID mapping tree to find specified node type */
+	while (node) {
+		struct acpi_rimt_id_mapping *map;
+		int i, rc = 0;
+		u32 map_id = id;
+
+		if (RIMT_TYPE_MASK(node->type) & type_mask) {
+			if (id_out)
+				*id_out = id;
+			return node;
+		}
+
+		if (node->type == ACPI_RIMT_NODE_TYPE_PCIE_ROOT_COMPLEX) {
+			pci_node = (struct acpi_rimt_pcie_rc *)&node->node_data;
+			id_mapping_offset = pci_node->id_mapping_offset;
+			num_id_mapping = pci_node->num_id_mappings;
+		} else if (node->type == ACPI_RIMT_NODE_TYPE_PLAT_DEVICE) {
+			plat_node = (struct acpi_rimt_platform_device *)&node->node_data;
+			id_mapping_offset = plat_node->id_mapping_offset;
+			num_id_mapping = plat_node->num_id_mappings;
+		} else {
+			goto fail_map;
+		}
+
+		if (!id_mapping_offset || !num_id_mapping)
+			goto fail_map;
+
+		map = ACPI_ADD_PTR(struct acpi_rimt_id_mapping, node,
+				   id_mapping_offset);
+
+		/* Firmware bug! */
+		if (!map->dest_offset) {
+			pr_err(FW_BUG "[node %p type %d] ID map has NULL parent reference\n",
+			       node, node->type);
+			goto fail_map;
+		}
+
+		/* Do the ID translation */
+		for (i = 0; i < num_id_mapping; i++, map++) {
+			rc = rimt_id_map(map, node->type, map_id, &id);
+			if (!rc)
+				break;
+		}
+
+		if (i == num_id_mapping)
+			goto fail_map;
+
+		node = ACPI_ADD_PTR(struct acpi_rimt_node, rimt_table,
+				    rc ? 0 : map->dest_offset);
+	}
+
+fail_map:
+	/* Map input ID to output ID unchanged on mapping failure */
+	if (id_out)
+		*id_out = id_in;
+
+	return NULL;
+}
+
+static struct acpi_rimt_node *rimt_node_map_platform_id(struct acpi_rimt_node *node, u32 *id_out,
+							u8 type_mask, int index)
+{
+	struct acpi_rimt_node *parent;
+	u32 id;
+
+	parent = rimt_node_get_id(node, &id, index);
+	if (!parent)
+		return NULL;
+
+	if (!(RIMT_TYPE_MASK(parent->type) & type_mask))
+		parent = rimt_node_map_id(parent, id, id_out, type_mask);
+	else
+		if (id_out)
+			*id_out = id;
+
+	return parent;
+}
+
+static int rimt_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct rimt_pci_alias_info *info = data;
+	struct acpi_rimt_node *parent;
+	u32 deviceid;
+
+	parent = rimt_node_map_id(info->node, alias, &deviceid, RIMT_IOMMU_TYPE);
+	return rimt_iommu_xlate(info->dev, parent, deviceid);
+}
+
+static int rimt_plat_iommu_map(struct device *dev, struct acpi_rimt_node *node)
+{
+	struct acpi_rimt_node *parent;
+	int err = -ENODEV, i = 0;
+	u32 deviceid = 0;
+
+	do {
+		parent = rimt_node_map_platform_id(node, &deviceid,
+						   RIMT_IOMMU_TYPE,
+						   i++);
+
+		if (parent)
+			err = rimt_iommu_xlate(dev, parent, deviceid);
+	} while (parent && !err);
+
+	return err;
+}
+
+static int rimt_plat_iommu_map_id(struct device *dev,
+				  struct acpi_rimt_node *node,
+				  const u32 *in_id)
+{
+	struct acpi_rimt_node *parent;
+	u32 deviceid;
+
+	parent = rimt_node_map_id(node, *in_id, &deviceid, RIMT_IOMMU_TYPE);
+	if (parent)
+		return rimt_iommu_xlate(dev, parent, deviceid);
+
+	return -ENODEV;
+}
+
+/**
+ * rimt_iommu_configure_id - Set-up IOMMU configuration for a device.
+ *
+ * @dev: device to configure
+ * @id_in: optional input id const value pointer
+ *
+ * Returns: 0 on success, <0 on failure
+ */
+int rimt_iommu_configure_id(struct device *dev, const u32 *id_in)
+{
+	struct acpi_rimt_node *node;
+	int err = -ENODEV;
+
+	if (dev_is_pci(dev)) {
+		struct iommu_fwspec *fwspec;
+		struct pci_bus *bus = to_pci_dev(dev)->bus;
+		struct rimt_pci_alias_info info = { .dev = dev };
+
+		node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_PCIE_ROOT_COMPLEX, &bus->dev);
+		if (!node)
+			return -ENODEV;
+
+		info.node = node;
+		err = pci_for_each_dma_alias(to_pci_dev(dev),
+					     rimt_pci_iommu_init, &info);
+
+		fwspec = dev_iommu_fwspec_get(dev);
+		if (fwspec && rimt_pcie_rc_supports_ats(node))
+			fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS;
+	} else {
+		node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_PLAT_DEVICE, dev);
+		if (!node)
+			return -ENODEV;
+
+		err = id_in ? rimt_plat_iommu_map_id(dev, node, id_in) :
+			      rimt_plat_iommu_map(dev, node);
+	}
+
+	return err;
+}
+
+#endif
+
+void __init riscv_acpi_rimt_init(void)
+{
+	acpi_status status;
+
+	/* rimt_table will be used at runtime after the rimt init,
+	 * so we don't need to call acpi_put_table() to release
+	 * the RIMT table mapping.
+	 */
+	status = acpi_get_table(ACPI_SIG_RIMT, 0, &rimt_table);
+	if (ACPI_FAILURE(status)) {
+		if (status != AE_NOT_FOUND) {
+			const char *msg = acpi_format_exception(status);
+
+			pr_err("Failed to get table, %s\n", msg);
+		}
+
+		return;
+	}
+}
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 94e3c000df2e..a3f95a3fffde 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -77,7 +77,6 @@ struct acpi_battery {
 	u16 spec;
 	u8 id;
 	u8 present:1;
-	u8 have_sysfs_alarm:1;
 };
 
 #define to_acpi_battery(x) power_supply_get_drvdata(x)
@@ -241,11 +240,11 @@ static int acpi_sbs_battery_get_property(struct power_supply *psy,
 	return 0;
 }
 
-static enum power_supply_property sbs_ac_props[] = {
+static const enum power_supply_property sbs_ac_props[] = {
 	POWER_SUPPLY_PROP_ONLINE,
 };
 
-static enum power_supply_property sbs_charge_battery_props[] = {
+static const enum power_supply_property sbs_charge_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -263,7 +262,7 @@ static enum power_supply_property sbs_charge_battery_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
-static enum power_supply_property sbs_energy_battery_props[] = {
+static const enum power_supply_property sbs_energy_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
@@ -462,12 +461,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
 	return count;
 }
 
-static const struct device_attribute alarm_attr = {
+static struct device_attribute alarm_attr = {
 	.attr = {.name = "alarm", .mode = 0644},
 	.show = acpi_battery_alarm_show,
 	.store = acpi_battery_alarm_store,
 };
 
+static struct attribute *acpi_battery_attrs[] = {
+	&alarm_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(acpi_battery);
+
 /* --------------------------------------------------------------------------
                                  Driver Interface
    -------------------------------------------------------------------------- */
@@ -518,7 +523,10 @@ static int acpi_battery_read(struct acpi_battery *battery)
 static int acpi_battery_add(struct acpi_sbs *sbs, int id)
 {
 	struct acpi_battery *battery = &sbs->battery[id];
-	struct power_supply_config psy_cfg = { .drv_data = battery, };
+	struct power_supply_config psy_cfg = {
+		.drv_data = battery,
+		.attr_grp = acpi_battery_groups,
+	};
 	int result;
 
 	battery->id = id;
@@ -548,10 +556,6 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id)
 		goto end;
 	}
 
-	result = device_create_file(&battery->bat->dev, &alarm_attr);
-	if (result)
-		goto end;
-	battery->have_sysfs_alarm = 1;
       end:
 	pr_info("%s [%s]: Battery Slot [%s] (battery %s)\n",
 	       ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device),
@@ -563,11 +567,8 @@ static void acpi_battery_remove(struct acpi_sbs *sbs, int id)
 {
 	struct acpi_battery *battery = &sbs->battery[id];
 
-	if (battery->bat) {
-		if (battery->have_sysfs_alarm)
-			device_remove_file(&battery->bat->dev, &alarm_attr);
+	if (battery->bat)
 		power_supply_unregister(battery->bat);
-	}
 }
 
 static int acpi_charger_add(struct acpi_sbs *sbs)
@@ -610,7 +611,7 @@ static void acpi_sbs_callback(void *context)
 	if (sbs->charger_exists) {
 		acpi_ac_get_present(sbs);
 		if (sbs->charger_present != saved_charger_state)
-			kobject_uevent(&sbs->charger->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(sbs->charger);
 	}
 
 	if (sbs->manager_present) {
@@ -622,7 +623,7 @@ static void acpi_sbs_callback(void *context)
 			acpi_battery_read(bat);
 			if (saved_battery_state == bat->present)
 				continue;
-			kobject_uevent(&bat->bat->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(bat->bat);
 		}
 	}
 }
@@ -643,8 +644,8 @@ static int acpi_sbs_add(struct acpi_device *device)
 
 	sbs->hc = acpi_driver_data(acpi_dev_parent(device));
 	sbs->device = device;
-	strcpy(acpi_device_name(device), ACPI_SBS_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_SBS_CLASS);
+	strscpy(acpi_device_name(device), ACPI_SBS_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_SBS_CLASS);
 	device->driver_data = sbs;
 
 	result = acpi_charger_add(sbs);
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 16f2daaa2c45..1a2bf520be23 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include "sbshc.h"
+#include "internal.h"
 
 #define ACPI_SMB_HC_CLASS	"smbus_host_ctl"
 #define ACPI_SMB_HC_DEVICE_NAME	"ACPI SMBus HC"
@@ -236,12 +237,6 @@ static int smbus_alarm(void *context)
 	return 0;
 }
 
-typedef int (*acpi_ec_query_func) (void *data);
-
-extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
-			      acpi_handle handle, acpi_ec_query_func func,
-			      void *data);
-
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
@@ -257,8 +252,8 @@ static int acpi_smbus_hc_add(struct acpi_device *device)
 		return -EIO;
 	}
 
-	strcpy(acpi_device_name(device), ACPI_SMB_HC_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_SMB_HC_CLASS);
+	strscpy(acpi_device_name(device), ACPI_SMB_HC_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_SMB_HC_CLASS);
 
 	hc = kzalloc(sizeof(struct acpi_smb_hc), GFP_KERNEL);
 	if (!hc)
@@ -278,8 +273,6 @@ static int acpi_smbus_hc_add(struct acpi_device *device)
 	return 0;
 }
 
-extern void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
-
 static void acpi_smbus_hc_remove(struct acpi_device *device)
 {
 	struct acpi_smb_hc *hc;
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fa5dd71a80fa..ef16d58b2949 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/acpi.h>
 #include <linux/acpi_iort.h>
+#include <linux/acpi_rimt.h>
 #include <linux/acpi_viot.h>
 #include <linux/iommu.h>
 #include <linux/signal.h>
@@ -73,8 +74,7 @@ void acpi_unlock_hp_context(void)
 
 void acpi_initialize_hp_context(struct acpi_device *adev,
 				struct acpi_hotplug_context *hp,
-				int (*notify)(struct acpi_device *, u32),
-				void (*uevent)(struct acpi_device *, u32))
+				acpi_hp_notify notify, acpi_hp_uevent uevent)
 {
 	acpi_lock_hp_context();
 	hp->notify = notify;
@@ -244,11 +244,85 @@ static int acpi_scan_try_to_offline(struct acpi_device *device)
 	return 0;
 }
 
+#define ACPI_SCAN_CHECK_FLAG_STATUS	BIT(0)
+#define ACPI_SCAN_CHECK_FLAG_EJECT	BIT(1)
+
+static int acpi_scan_check_and_detach(struct acpi_device *adev, void *p)
+{
+	struct acpi_scan_handler *handler = adev->handler;
+	uintptr_t flags = (uintptr_t)p;
+
+	acpi_dev_for_each_child_reverse(adev, acpi_scan_check_and_detach, p);
+
+	if (flags & ACPI_SCAN_CHECK_FLAG_STATUS) {
+		acpi_bus_get_status(adev);
+		/*
+		 * Skip devices that are still there and take the enabled
+		 * flag into account.
+		 */
+		if (acpi_device_is_enabled(adev))
+			return 0;
+
+		/* Skip device that have not been enumerated. */
+		if (!acpi_device_enumerated(adev)) {
+			dev_dbg(&adev->dev, "Still not enumerated\n");
+			return 0;
+		}
+	}
+
+	adev->flags.match_driver = false;
+	if (handler) {
+		if (handler->detach)
+			handler->detach(adev);
+	} else {
+		device_release_driver(&adev->dev);
+	}
+	/*
+	 * Most likely, the device is going away, so put it into D3cold before
+	 * that.
+	 */
+	acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
+	adev->flags.initialized = false;
+
+	/* For eject this is deferred to acpi_bus_post_eject() */
+	if (!(flags & ACPI_SCAN_CHECK_FLAG_EJECT)) {
+		adev->handler = NULL;
+		acpi_device_clear_enumerated(adev);
+	}
+	return 0;
+}
+
+static int acpi_bus_post_eject(struct acpi_device *adev, void *not_used)
+{
+	struct acpi_scan_handler *handler = adev->handler;
+
+	acpi_dev_for_each_child_reverse(adev, acpi_bus_post_eject, NULL);
+
+	if (handler) {
+		if (handler->post_eject)
+			handler->post_eject(adev);
+
+		adev->handler = NULL;
+	}
+
+	acpi_device_clear_enumerated(adev);
+
+	return 0;
+}
+
+static void acpi_scan_check_subtree(struct acpi_device *adev)
+{
+	uintptr_t flags = ACPI_SCAN_CHECK_FLAG_STATUS;
+
+	acpi_scan_check_and_detach(adev, (void *)flags);
+}
+
 static int acpi_scan_hot_remove(struct acpi_device *device)
 {
 	acpi_handle handle = device->handle;
 	unsigned long long sta;
 	acpi_status status;
+	uintptr_t flags = ACPI_SCAN_CHECK_FLAG_EJECT;
 
 	if (device->handler && device->handler->hotplug.demand_offline) {
 		if (!acpi_scan_is_offline(device, true))
@@ -261,7 +335,7 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 
 	acpi_handle_debug(handle, "Ejecting\n");
 
-	acpi_bus_trim(device);
+	acpi_scan_check_and_detach(device, (void *)flags);
 
 	acpi_evaluate_lck(handle, 0);
 	/*
@@ -284,80 +358,69 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 	} else if (sta & ACPI_STA_DEVICE_ENABLED) {
 		acpi_handle_warn(handle,
 			"Eject incomplete - status 0x%llx\n", sta);
+	} else {
+		acpi_bus_post_eject(device, NULL);
 	}
 
 	return 0;
 }
 
-static int acpi_scan_device_not_enumerated(struct acpi_device *adev)
+static int acpi_scan_rescan_bus(struct acpi_device *adev)
 {
-	if (!acpi_device_enumerated(adev)) {
-		dev_warn(&adev->dev, "Still not enumerated\n");
-		return -EALREADY;
-	}
-	acpi_bus_trim(adev);
-	return 0;
+	struct acpi_scan_handler *handler = adev->handler;
+	int ret;
+
+	if (handler && handler->hotplug.scan_dependent)
+		ret = handler->hotplug.scan_dependent(adev);
+	else
+		ret = acpi_bus_scan(adev->handle);
+
+	if (ret)
+		dev_info(&adev->dev, "Namespace scan failure\n");
+
+	return ret;
 }
 
 static int acpi_scan_device_check(struct acpi_device *adev)
 {
-	int error;
+	struct acpi_device *parent;
 
-	acpi_bus_get_status(adev);
-	if (acpi_device_is_present(adev)) {
-		/*
-		 * This function is only called for device objects for which
-		 * matching scan handlers exist.  The only situation in which
-		 * the scan handler is not attached to this device object yet
-		 * is when the device has just appeared (either it wasn't
-		 * present at all before or it was removed and then added
-		 * again).
-		 */
-		if (adev->handler) {
-			dev_warn(&adev->dev, "Already enumerated\n");
-			return -EALREADY;
-		}
-		error = acpi_bus_scan(adev->handle);
-		if (error) {
-			dev_warn(&adev->dev, "Namespace scan failure\n");
-			return error;
-		}
-		if (!adev->handler) {
-			dev_warn(&adev->dev, "Enumeration failure\n");
-			error = -ENODEV;
-		}
-	} else {
-		error = acpi_scan_device_not_enumerated(adev);
-	}
-	return error;
-}
+	acpi_scan_check_subtree(adev);
 
-static int acpi_scan_bus_check(struct acpi_device *adev, void *not_used)
-{
-	struct acpi_scan_handler *handler = adev->handler;
-	int error;
+	if (!acpi_device_is_present(adev))
+		return 0;
 
-	acpi_bus_get_status(adev);
-	if (!acpi_device_is_present(adev)) {
-		acpi_scan_device_not_enumerated(adev);
+	/*
+	 * This function is only called for device objects for which matching
+	 * scan handlers exist.  The only situation in which the scan handler
+	 * is not attached to this device object yet is when the device has
+	 * just appeared (either it wasn't present at all before or it was
+	 * removed and then added again).
+	 */
+	if (adev->handler) {
+		dev_dbg(&adev->dev, "Already enumerated\n");
 		return 0;
 	}
-	if (handler && handler->hotplug.scan_dependent)
-		return handler->hotplug.scan_dependent(adev);
 
-	error = acpi_bus_scan(adev->handle);
-	if (error) {
-		dev_warn(&adev->dev, "Namespace scan failure\n");
-		return error;
-	}
-	return acpi_dev_for_each_child(adev, acpi_scan_bus_check, NULL);
+	parent = acpi_dev_parent(adev);
+	if (!parent)
+		parent = adev;
+
+	return acpi_scan_rescan_bus(parent);
+}
+
+static int acpi_scan_bus_check(struct acpi_device *adev)
+{
+	acpi_scan_check_subtree(adev);
+
+	return acpi_scan_rescan_bus(adev);
 }
 
 static int acpi_generic_hotplug_event(struct acpi_device *adev, u32 type)
 {
 	switch (type) {
 	case ACPI_NOTIFY_BUS_CHECK:
-		return acpi_scan_bus_check(adev, NULL);
+		return acpi_scan_bus_check(adev);
 	case ACPI_NOTIFY_DEVICE_CHECK:
 		return acpi_scan_device_check(adev);
 	case ACPI_NOTIFY_EJECT_REQUEST:
@@ -394,7 +457,7 @@ void acpi_device_hotplug(struct acpi_device *adev, u32 src)
 	} else if (adev->flags.hotplug_notify) {
 		error = acpi_generic_hotplug_event(adev, src);
 	} else {
-		int (*notify)(struct acpi_device *, u32);
+		acpi_hp_notify notify;
 
 		acpi_lock_hp_context();
 		notify = adev->hp ? adev->hp->notify : NULL;
@@ -661,10 +724,8 @@ int acpi_tie_acpi_dev(struct acpi_device *adev)
 static void acpi_store_pld_crc(struct acpi_device *adev)
 {
 	struct acpi_pld_info *pld;
-	acpi_status status;
 
-	status = acpi_get_physical_device_location(adev->handle, &pld);
-	if (ACPI_FAILURE(status))
+	if (!acpi_get_physical_device_location(adev->handle, &pld))
 		return;
 
 	adev->pld_crc = crc32(~0, pld, sizeof(*pld));
@@ -733,10 +794,7 @@ int acpi_device_add(struct acpi_device *device)
 		goto err;
 	}
 
-	result = acpi_device_setup_files(device);
-	if (result)
-		pr_err("Error creating sysfs interface for device %s\n",
-		       dev_name(&device->dev));
+	acpi_device_setup_files(device);
 
 	return 0;
 
@@ -788,6 +846,8 @@ static bool acpi_info_matches_ids(struct acpi_device_info *info,
 static const char * const acpi_ignore_dep_ids[] = {
 	"PNP0D80", /* Windows-compatible System Power Management Controller */
 	"INT33BD", /* Intel Baytrail Mailbox Device */
+	"INTC10DE", /* Intel CVS LNL */
+	"INTC10E0", /* Intel CVS ARL */
 	"LATT2021", /* Lattice FW Update Client Driver */
 	NULL
 };
@@ -798,6 +858,12 @@ static const char * const acpi_honor_dep_ids[] = {
 	"INTC1059", /* IVSC (TGL) driver must be loaded to allow i2c access to camera sensors */
 	"INTC1095", /* IVSC (ADL) driver must be loaded to allow i2c access to camera sensors */
 	"INTC100A", /* IVSC (RPL) driver must be loaded to allow i2c access to camera sensors */
+	"INTC10CF", /* IVSC (MTL) driver must be loaded to allow i2c access to camera sensors */
+	"RSCV0001", /* RISC-V PLIC */
+	"RSCV0002", /* RISC-V APLIC */
+	"RSCV0005", /* RISC-V SBI MPXY MBOX */
+	"RSCV0006", /* RISC-V RPMI SYSMSI */
+	"PNP0C0F",  /* PCI Link Device */
 	NULL
 };
 
@@ -1116,19 +1182,19 @@ static void acpi_device_get_busid(struct acpi_device *device)
 	 * TBD: Shouldn't this value be unique (within the ACPI namespace)?
 	 */
 	if (!acpi_dev_parent(device)) {
-		strcpy(device->pnp.bus_id, "ACPI");
+		strscpy(device->pnp.bus_id, "ACPI");
 		return;
 	}
 
 	switch (device->device_type) {
 	case ACPI_BUS_TYPE_POWER_BUTTON:
-		strcpy(device->pnp.bus_id, "PWRF");
+		strscpy(device->pnp.bus_id, "PWRF");
 		break;
 	case ACPI_BUS_TYPE_SLEEP_BUTTON:
-		strcpy(device->pnp.bus_id, "SLPF");
+		strscpy(device->pnp.bus_id, "SLPF");
 		break;
 	case ACPI_BUS_TYPE_ECDT_EC:
-		strcpy(device->pnp.bus_id, "ECDT");
+		strscpy(device->pnp.bus_id, "ECDT");
 		break;
 	default:
 		acpi_get_name(device->handle, ACPI_SINGLE_NAME, &buffer);
@@ -1139,7 +1205,7 @@ static void acpi_device_get_busid(struct acpi_device *device)
 			else
 				break;
 		}
-		strcpy(device->pnp.bus_id, bus_id);
+		strscpy(device->pnp.bus_id, bus_id);
 		break;
 	}
 }
@@ -1263,10 +1329,10 @@ const char *acpi_device_hid(struct acpi_device *device)
 {
 	struct acpi_hardware_id *hid;
 
-	if (list_empty(&device->pnp.ids))
+	hid = list_first_entry_or_null(&device->pnp.ids, struct acpi_hardware_id, list);
+	if (!hid)
 		return dummy_hid;
 
-	hid = list_first_entry(&device->pnp.ids, struct acpi_hardware_id, list);
 	return hid->id;
 }
 EXPORT_SYMBOL(acpi_device_hid);
@@ -1390,8 +1456,8 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
 			 acpi_object_is_system_bus(handle)) {
 			/* \_SB, \_TZ, LNXSYBUS */
 			acpi_add_id(pnp, ACPI_BUS_HID);
-			strcpy(pnp->device_name, ACPI_BUS_DEVICE_NAME);
-			strcpy(pnp->device_class, ACPI_BUS_CLASS);
+			strscpy(pnp->device_name, ACPI_BUS_DEVICE_NAME);
+			strscpy(pnp->device_class, ACPI_BUS_CLASS);
 		}
 
 		break;
@@ -1532,7 +1598,6 @@ int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 			r->cpu_start = rentry->res->start;
 			r->dma_start = rentry->res->start - rentry->offset;
 			r->size = resource_size(rentry->res);
-			r->offset = rentry->offset;
 			r++;
 		}
 	}
@@ -1544,72 +1609,51 @@ int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 
 #ifdef CONFIG_IOMMU_API
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
-			   struct fwnode_handle *fwnode,
-			   const struct iommu_ops *ops)
+			   struct fwnode_handle *fwnode)
 {
-	int ret = iommu_fwspec_init(dev, fwnode, ops);
-
-	if (!ret)
-		ret = iommu_fwspec_add_ids(dev, &id, 1);
-
-	return ret;
-}
+	int ret;
 
-static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	ret = iommu_fwspec_init(dev, fwnode);
+	if (ret)
+		return ret;
 
-	return fwspec ? fwspec->ops : NULL;
+	return iommu_fwspec_add_ids(dev, &id, 1);
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
 	int err;
-	const struct iommu_ops *ops;
 
-	/*
-	 * If we already translated the fwspec there is nothing left to do,
-	 * return the iommu_ops.
-	 */
-	ops = acpi_iommu_fwspec_ops(dev);
-	if (ops)
-		return ops;
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
+	/* If we already translated the fwspec there is nothing left to do */
+	if (dev_iommu_fwspec_get(dev)) {
+		mutex_unlock(&iommu_probe_device_lock);
+		return 0;
+	}
 
 	err = iort_iommu_configure_id(dev, id_in);
 	if (err && err != -EPROBE_DEFER)
+		err = rimt_iommu_configure_id(dev, id_in);
+	if (err && err != -EPROBE_DEFER)
 		err = viot_iommu_configure(dev);
 
-	/*
-	 * If we have reason to believe the IOMMU driver missed the initial
-	 * iommu_probe_device() call for dev, replay it to get things in order.
-	 */
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
+	mutex_unlock(&iommu_probe_device_lock);
 
-	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		return ERR_PTR(err);
-	} else if (err) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		return NULL;
-	}
-	return acpi_iommu_fwspec_ops(dev);
+	return err;
 }
 
 #else /* !CONFIG_IOMMU_API */
 
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
-			   struct fwnode_handle *fwnode,
-			   const struct iommu_ops *ops)
+			   struct fwnode_handle *fwnode)
 {
 	return -ENODEV;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 #endif /* !CONFIG_IOMMU_API */
@@ -1623,7 +1667,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			  const u32 *input_id)
 {
-	const struct iommu_ops *iommu;
+	int ret;
 
 	if (attr == DEV_DMA_NOT_SUPPORTED) {
 		set_dma_ops(dev, &dma_dummy_ops);
@@ -1632,12 +1676,14 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 
 	acpi_arch_dma_setup(dev);
 
-	iommu = acpi_iommu_configure_id(dev, input_id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	/* Ignore all other errors apart from EPROBE_DEFER */
+	ret = acpi_iommu_configure_id(dev, input_id);
+	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
+	if (ret)
+		dev_dbg(dev, "Adding to IOMMU failed: %d\n", ret);
 
-	arch_setup_dma_ops(dev, 0, U64_MAX,
-				iommu, attr == DEV_DMA_COHERENT);
+	arch_setup_dma_ops(dev, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }
@@ -1717,9 +1763,12 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 		{"BSG1160", },
 		{"BSG2150", },
 		{"CSC3551", },
+		{"CSC3554", },
 		{"CSC3556", },
+		{"CSC3557", },
 		{"INT33FE", },
 		{"INT3515", },
+		{"TXNW2781", },
 		/* Non-conforming _HID for Cirrus Logic already released */
 		{"CLSA0100", },
 		{"CLSA0101", },
@@ -1727,6 +1776,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 	 * Some ACPI devs contain SerialBus resources even though they are not
 	 * attached to a serial bus at all.
 	 */
+		{ACPI_VIDEO_HID, },
 		{"MSHW0028", },
 	/*
 	 * HIDs of device with an UartSerialBusV2 resource for which userspace
@@ -1772,6 +1822,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device->dev.parent = parent ? &parent->dev : NULL;
 	device->dev.release = release;
 	device->dev.bus = &acpi_bus_type;
+	device->dev.groups = acpi_groups;
 	fwnode_init(&device->fwnode, &acpi_device_fwnode_ops);
 	acpi_set_device_status(device, ACPI_STA_DEFAULT);
 	acpi_device_get_busid(device);
@@ -1797,7 +1848,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev)
 			if (dep->honor_dep)
 				adev->flags.honor_deps = 1;
 
-			adev->dep_unmet++;
+			if (!dep->met)
+				adev->dep_unmet++;
 		}
 	}
 }
@@ -1913,6 +1965,11 @@ bool acpi_device_is_present(const struct acpi_device *adev)
 	return adev->status.present || adev->status.functional;
 }
 
+bool acpi_device_is_enabled(const struct acpi_device *adev)
+{
+	return adev->status.enabled;
+}
+
 static bool acpi_scan_handler_matching(struct acpi_scan_handler *handler,
 				       const char *idstr,
 				       const struct acpi_device_id **matchid)
@@ -1957,54 +2014,18 @@ void acpi_scan_hotplug_enabled(struct acpi_hotplug_profile *hotplug, bool val)
 	mutex_unlock(&acpi_scan_lock);
 }
 
-static void acpi_scan_init_hotplug(struct acpi_device *adev)
+int acpi_scan_add_dep(acpi_handle handle, struct acpi_handle_list *dep_devices)
 {
-	struct acpi_hardware_id *hwid;
-
-	if (acpi_dock_match(adev->handle) || is_ejectable_bay(adev)) {
-		acpi_dock_add(adev);
-		return;
-	}
-	list_for_each_entry(hwid, &adev->pnp.ids, list) {
-		struct acpi_scan_handler *handler;
-
-		handler = acpi_scan_match_handler(hwid->id, NULL);
-		if (handler) {
-			adev->flags.hotplug_notify = true;
-			break;
-		}
-	}
-}
-
-static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
-{
-	struct acpi_handle_list dep_devices;
-	acpi_status status;
 	u32 count;
 	int i;
 
-	/*
-	 * Check for _HID here to avoid deferring the enumeration of:
-	 * 1. PCI devices.
-	 * 2. ACPI nodes describing USB ports.
-	 * Still, checking for _HID catches more then just these cases ...
-	 */
-	if (!check_dep || !acpi_has_method(handle, "_DEP") ||
-	    !acpi_has_method(handle, "_HID"))
-		return 0;
-
-	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
-	if (ACPI_FAILURE(status)) {
-		acpi_handle_debug(handle, "Failed to evaluate _DEP.\n");
-		return 0;
-	}
-
-	for (count = 0, i = 0; i < dep_devices.count; i++) {
+	for (count = 0, i = 0; i < dep_devices->count; i++) {
 		struct acpi_device_info *info;
 		struct acpi_dep_data *dep;
 		bool skip, honor_dep;
+		acpi_status status;
 
-		status = acpi_get_object_info(dep_devices.handles[i], &info);
+		status = acpi_get_object_info(dep_devices->handles[i], &info);
 		if (ACPI_FAILURE(status)) {
 			acpi_handle_debug(handle, "Error reading _DEP device info\n");
 			continue;
@@ -2023,20 +2044,79 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 
 		count++;
 
-		dep->supplier = dep_devices.handles[i];
+		dep->supplier = dep_devices->handles[i];
 		dep->consumer = handle;
 		dep->honor_dep = honor_dep;
 
 		mutex_lock(&acpi_dep_list_lock);
-		list_add_tail(&dep->node , &acpi_dep_list);
+		list_add_tail(&dep->node, &acpi_dep_list);
 		mutex_unlock(&acpi_dep_list_lock);
 	}
 
-	acpi_handle_list_free(&dep_devices);
+	acpi_handle_list_free(dep_devices);
+	return count;
+}
+
+static void acpi_scan_init_hotplug(struct acpi_device *adev)
+{
+	struct acpi_hardware_id *hwid;
+
+	if (acpi_dock_match(adev->handle) || is_ejectable_bay(adev)) {
+		acpi_dock_add(adev);
+		return;
+	}
+	list_for_each_entry(hwid, &adev->pnp.ids, list) {
+		struct acpi_scan_handler *handler;
+
+		handler = acpi_scan_match_handler(hwid->id, NULL);
+		if (handler) {
+			adev->flags.hotplug_notify = true;
+			break;
+		}
+	}
+}
+
+u32 __weak arch_acpi_add_auto_dep(acpi_handle handle) { return 0; }
+
+static u32 acpi_scan_check_dep(acpi_handle handle)
+{
+	struct acpi_handle_list dep_devices;
+	u32 count = 0;
+
+	/*
+	 * Some architectures like RISC-V need to add dependencies for
+	 * all devices which use GSI to the interrupt controller so that
+	 * interrupt controller is probed before any of those devices.
+	 * Instead of mandating _DEP on all the devices, detect the
+	 * dependency and add automatically.
+	 */
+	count += arch_acpi_add_auto_dep(handle);
+
+	/*
+	 * Check for _HID here to avoid deferring the enumeration of:
+	 * 1. PCI devices.
+	 * 2. ACPI nodes describing USB ports.
+	 * Still, checking for _HID catches more then just these cases ...
+	 */
+	if (!acpi_has_method(handle, "_DEP") || !acpi_has_method(handle, "_HID"))
+		return count;
+
+	if (!acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices)) {
+		acpi_handle_debug(handle, "Failed to evaluate _DEP.\n");
+		return count;
+	}
+
+	count += acpi_scan_add_dep(handle, &dep_devices);
 	return count;
 }
 
-static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
+static acpi_status acpi_scan_check_crs_csi2_cb(acpi_handle handle, u32 a, void *b, void **c)
+{
+	acpi_mipi_check_crs_csi2(handle);
+	return AE_OK;
+}
+
+static acpi_status acpi_bus_check_add(acpi_handle handle, bool first_pass,
 				      struct acpi_device **adev_p)
 {
 	struct acpi_device *device = acpi_fetch_acpi_dev(handle);
@@ -2054,9 +2134,25 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 		if (acpi_device_should_be_hidden(handle))
 			return AE_OK;
 
-		/* Bail out if there are dependencies. */
-		if (acpi_scan_check_dep(handle, check_dep) > 0)
-			return AE_CTRL_DEPTH;
+		if (first_pass) {
+			acpi_mipi_check_crs_csi2(handle);
+
+			/* Bail out if there are dependencies. */
+			if (acpi_scan_check_dep(handle) > 0) {
+				/*
+				 * The entire CSI-2 connection graph needs to be
+				 * extracted before any drivers or scan handlers
+				 * are bound to struct device objects, so scan
+				 * _CRS CSI-2 resource descriptors for all
+				 * devices below the current handle.
+				 */
+				acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+						    ACPI_UINT32_MAX,
+						    acpi_scan_check_crs_csi2_cb,
+						    NULL, NULL, NULL);
+				return AE_CTRL_DEPTH;
+			}
+		}
 
 		fallthrough;
 	case ACPI_TYPE_ANY:	/* for ACPI_ROOT_OBJECT */
@@ -2079,10 +2175,10 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 	}
 
 	/*
-	 * If check_dep is true at this point, the device has no dependencies,
+	 * If first_pass is true at this point, the device has no dependencies,
 	 * or the creation of the device object would have been postponed above.
 	 */
-	acpi_add_single_object(&device, handle, type, !check_dep);
+	acpi_add_single_object(&device, handle, type, !first_pass);
 	if (!device)
 		return AE_CTRL_DEPTH;
 
@@ -2197,6 +2293,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass)
 	if (device->handler)
 		goto ok;
 
+	acpi_ec_register_opregions(device);
+
 	if (!device->flags.initialized) {
 		device->flags.power_manageable =
 			device->power.states[ACPI_STATE_D0].flags.valid;
@@ -2426,6 +2524,13 @@ static void acpi_scan_postponed_branch(acpi_handle handle)
 
 	acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
 			    acpi_bus_check_add_2, NULL, NULL, (void **)&adev);
+
+	/*
+	 * Populate the ACPI _CRS CSI-2 software nodes for the ACPI devices that
+	 * have been added above.
+	 */
+	acpi_mipi_init_crs_csi2_swnodes();
+
 	acpi_bus_attach(adev, NULL);
 }
 
@@ -2494,41 +2599,25 @@ int acpi_bus_scan(acpi_handle handle)
 	if (!device)
 		return -ENODEV;
 
+	/*
+	 * Set up ACPI _CRS CSI-2 software nodes using information extracted
+	 * from the _CRS CSI-2 resource descriptors during the ACPI namespace
+	 * walk above and MIPI DisCo for Imaging device properties.
+	 */
+	acpi_mipi_scan_crs_csi2();
+	acpi_mipi_init_crs_csi2_swnodes();
+
 	acpi_bus_attach(device, (void *)true);
 
 	/* Pass 2: Enumerate all of the remaining devices. */
 
 	acpi_scan_postponed();
 
-	return 0;
-}
-EXPORT_SYMBOL(acpi_bus_scan);
-
-static int acpi_bus_trim_one(struct acpi_device *adev, void *not_used)
-{
-	struct acpi_scan_handler *handler = adev->handler;
-
-	acpi_dev_for_each_child_reverse(adev, acpi_bus_trim_one, NULL);
-
-	adev->flags.match_driver = false;
-	if (handler) {
-		if (handler->detach)
-			handler->detach(adev);
-
-		adev->handler = NULL;
-	} else {
-		device_release_driver(&adev->dev);
-	}
-	/*
-	 * Most likely, the device is going away, so put it into D3cold before
-	 * that.
-	 */
-	acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
-	adev->flags.initialized = false;
-	acpi_device_clear_enumerated(adev);
+	acpi_mipi_crs_csi2_cleanup();
 
 	return 0;
 }
+EXPORT_SYMBOL(acpi_bus_scan);
 
 /**
  * acpi_bus_trim - Detach scan handlers and drivers from ACPI device objects.
@@ -2538,7 +2627,9 @@ static int acpi_bus_trim_one(struct acpi_device *adev, void *not_used)
  */
 void acpi_bus_trim(struct acpi_device *adev)
 {
-	acpi_bus_trim_one(adev, NULL);
+	uintptr_t flags = 0;
+
+	acpi_scan_check_and_detach(adev, (void *)flags);
 }
 EXPORT_SYMBOL_GPL(acpi_bus_trim);
 
@@ -2619,6 +2710,7 @@ void __init acpi_scan_init(void)
 	acpi_memory_hotplug_init();
 	acpi_watchdog_init();
 	acpi_pnp_init();
+	acpi_power_resources_init();
 	acpi_int340x_thermal_init();
 	acpi_init_lpit();
 
@@ -2686,6 +2778,8 @@ static int __init acpi_match_madt(union acpi_subtable_headers *header,
 	return 0;
 }
 
+void __weak arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr) { }
+
 int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 {
 	int count = 0;
@@ -2694,6 +2788,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 		return 0;
 
 	mutex_lock(&acpi_probe_mutex);
+	arch_sort_irqchip_probe(ap_head, nr);
 	for (ape = ap_head; nr; ape++, nr--) {
 		if (ACPI_COMPARE_NAMESEG(ACPI_SIG_MADT, ape->id)) {
 			acpi_probe_count = 0;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 808484d11209..c8ee8e42b0f6 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -352,6 +352,20 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		},
 	},
 	/*
+	 * The ASUS ROG M16 from 2023 has many events which wake it from s2idle
+	 * resulting in excessive battery drain and risk of laptop overheating,
+	 * these events can be caused by the MMC or  y AniMe display if installed.
+	 * The match is valid for all of the GU604V<x> range.
+	 */
+	{
+	.callback = init_default_s3,
+	.ident = "ASUS ROG Zephyrus M16 (2023)",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus M16 GU604V"),
+		},
+	},
+	/*
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
 	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
 	 * saving during S3.
@@ -385,18 +399,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"),
 		},
 	},
-	/*
-	 * ASUS B1400CEAE hangs on resume from suspend (see
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=215742).
-	 */
-	{
-	.callback = init_default_s3,
-	.ident = "ASUS B1400CEAE",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"),
-		},
-	},
 	{},
 };
 
@@ -514,6 +516,7 @@ static void acpi_pm_finish(void)
 
 /**
  * acpi_pm_start - Start system PM transition.
+ * @acpi_state: The target ACPI power state to transition to.
  */
 static void acpi_pm_start(u32 acpi_state)
 {
@@ -552,8 +555,9 @@ static u32 acpi_suspend_states[] = {
 };
 
 /**
- *	acpi_suspend_begin - Set the target system sleep state to the state
- *		associated with given @pm_state, if supported.
+ * acpi_suspend_begin - Set the target system sleep state to the state
+ *	associated with given @pm_state, if supported.
+ * @pm_state: The target system power management state.
  */
 static int acpi_suspend_begin(suspend_state_t pm_state)
 {
@@ -683,10 +687,11 @@ static const struct platform_suspend_ops acpi_suspend_ops = {
 };
 
 /**
- *	acpi_suspend_begin_old - Set the target system sleep state to the
- *		state associated with given @pm_state, if supported, and
- *		execute the _PTS control method.  This function is used if the
- *		pre-ACPI 2.0 suspend ordering has been requested.
+ * acpi_suspend_begin_old - Set the target system sleep state to the
+ *	state associated with given @pm_state, if supported, and
+ *	execute the _PTS control method.  This function is used if the
+ *	pre-ACPI 2.0 suspend ordering has been requested.
+ * @pm_state: The target suspend state for the system.
  */
 static int acpi_suspend_begin_old(suspend_state_t pm_state)
 {
@@ -979,10 +984,11 @@ static const struct platform_hibernation_ops acpi_hibernation_ops = {
 };
 
 /**
- *	acpi_hibernation_begin_old - Set the target system sleep state to
- *		ACPI_STATE_S4 and execute the _PTS control method.  This
- *		function is used if the pre-ACPI 2.0 suspend ordering has been
- *		requested.
+ * acpi_hibernation_begin_old - Set the target system sleep state to
+ *	ACPI_STATE_S4 and execute the _PTS control method.  This
+ *	function is used if the pre-ACPI 2.0 suspend ordering has been
+ *	requested.
+ * @stage: The power management event message.
  */
 static int acpi_hibernation_begin_old(pm_message_t stage)
 {
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index cd36a97b0ea2..d4d52d5e9016 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -141,12 +141,23 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console)
 	case ACPI_DBG2_16550_NVIDIA:
 		uart = "uart";
 		break;
+	case ACPI_DBG2_RISCV_SBI_CON:
+		uart = "sbi";
+		break;
 	default:
 		err = -ENOENT;
 		goto done;
 	}
 
-	switch (table->baud_rate) {
+	/*
+	 * SPCR 1.09 defines Precise Baud Rate Filed contains a specific
+	 * non-zero baud rate which overrides the value of the Configured
+	 * Baud Rate field. If this field is zero or not present, Configured
+	 * Baud Rate is used.
+	 */
+	if (table->precise_baudrate)
+		baud_rate = table->precise_baudrate;
+	else switch (table->baud_rate) {
 	case 0:
 		/*
 		 * SPCR 1.04 defines 0 as a preconfigured state of UART.
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 687524b50085..e596224302f4 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -319,7 +319,7 @@ struct acpi_data_attr {
 };
 
 static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr, char *buf,
+			       const struct bin_attribute *bin_attr, char *buf,
 			       loff_t offset, size_t count)
 {
 	struct acpi_table_attr *table_attr =
@@ -412,7 +412,7 @@ acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context)
 }
 
 static ssize_t acpi_data_show(struct file *filp, struct kobject *kobj,
-			      struct bin_attribute *bin_attr, char *buf,
+			      const struct bin_attribute *bin_attr, char *buf,
 			      loff_t offset, size_t count)
 {
 	struct acpi_data_attr *data_attr;
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index c1516337f668..57fc8bc56166 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -56,7 +56,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 			    (struct acpi_madt_local_apic *)header;
 			pr_debug("LAPIC (acpi_id[0x%02x] lapic_id[0x%02x] %s)\n",
 				 p->processor_id, p->id,
-				 (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED));
 		}
 		break;
 
@@ -66,7 +66,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 			    (struct acpi_madt_local_x2apic *)header;
 			pr_debug("X2APIC (apic_id[0x%02x] uid[0x%02x] %s)\n",
 				 p->local_apic_id, p->uid,
-				 (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED));
 		}
 		break;
 
@@ -160,7 +160,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 			    (struct acpi_madt_local_sapic *)header;
 			pr_debug("LSAPIC (acpi_id[0x%02x] lsapic_id[0x%02x] lsapic_eid[0x%02x] %s)\n",
 				 p->processor_id, p->id, p->eid,
-				 (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED));
 		}
 		break;
 
@@ -183,7 +183,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 			pr_debug("GICC (acpi_id[0x%04x] address[%llx] MPIDR[0x%llx] %s)\n",
 				 p->uid, p->base_address,
 				 p->arm_mpidr,
-				 (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_MADT_ENABLED));
 
 		}
 		break;
@@ -198,13 +198,27 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 		}
 		break;
 
+	case ACPI_MADT_TYPE_MULTIPROC_WAKEUP:
+		{
+			struct acpi_madt_multiproc_wakeup *p =
+				(struct acpi_madt_multiproc_wakeup *)header;
+			u64 reset_vector = 0;
+
+			if (p->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1)
+				reset_vector = p->reset_vector;
+
+			pr_debug("MP Wakeup (version[%d], mailbox[%#llx], reset[%#llx])\n",
+				 p->version, p->mailbox_address, reset_vector);
+		}
+		break;
+
 	case ACPI_MADT_TYPE_CORE_PIC:
 		{
 			struct acpi_madt_core_pic *p = (struct acpi_madt_core_pic *)header;
 
 			pr_debug("CORE PIC (processor_id[0x%02x] core_id[0x%02x] %s)\n",
 				 p->processor_id, p->core_id,
-				 (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_MADT_ENABLED));
 		}
 		break;
 
@@ -214,7 +228,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 
 			pr_debug("RISC-V INTC (acpi_uid[0x%04x] hart_id[0x%llx] %s)\n",
 				 p->uid, p->hart_id,
-				 (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_MADT_ENABLED));
 		}
 		break;
 
@@ -251,8 +265,9 @@ int __init_or_acpilib acpi_table_parse_entries_array(
 		return -ENODEV;
 	}
 
-	count = acpi_parse_entries_array(id, table_size, table_header,
-			proc, proc_num, max_entries);
+	count = acpi_parse_entries_array(id, table_size,
+					 (union fw_table_header *)table_header,
+					 0, proc, proc_num, max_entries);
 
 	acpi_put_table(table_header);
 	return count;
@@ -381,7 +396,7 @@ static u8 __init acpi_table_checksum(u8 *buffer, u32 length)
 }
 
 /* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
-static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst = {
+static const char table_sigs[][ACPI_NAMESEG_SIZE] __nonstring_array __initconst = {
 	ACPI_SIG_BERT, ACPI_SIG_BGRT, ACPI_SIG_CPEP, ACPI_SIG_ECDT,
 	ACPI_SIG_EINJ, ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT,
 	ACPI_SIG_MSCT, ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT,
@@ -393,7 +408,7 @@ static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst = {
 	ACPI_SIG_PSDT, ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT,
 	ACPI_SIG_IORT, ACPI_SIG_NFIT, ACPI_SIG_HMAT, ACPI_SIG_PPTT,
 	ACPI_SIG_NHLT, ACPI_SIG_AEST, ACPI_SIG_CEDT, ACPI_SIG_AGDI,
-	ACPI_SIG_NBFT };
+	ACPI_SIG_NBFT, ACPI_SIG_SWFT};
 
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 
@@ -704,8 +719,12 @@ int __init acpi_locate_initial_tables(void)
 	}
 
 	status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
-	if (ACPI_FAILURE(status))
+	if (ACPI_FAILURE(status)) {
+		const char *msg = acpi_format_exception(status);
+
+		pr_warn("Failed to initialize tables, status=0x%x (%s)", status, msg);
 		return -EINVAL;
+	}
 
 	return 0;
 }
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index f74d81abdbfc..8537395b417b 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -31,6 +31,8 @@
 #include <linux/uaccess.h>
 #include <linux/units.h>
 
+#include "internal.h"
+
 #define ACPI_THERMAL_CLASS		"thermal_zone"
 #define ACPI_THERMAL_DEVICE_NAME	"Thermal Zone"
 #define ACPI_THERMAL_NOTIFY_TEMPERATURE	0x80
@@ -45,6 +47,8 @@
 
 #define ACPI_THERMAL_TRIP_PASSIVE	(-1)
 
+#define ACPI_THERMAL_MAX_NR_TRIPS	(ACPI_THERMAL_MAX_ACTIVE + 3)
+
 /*
  * This exception is thrown out in two cases:
  * 1.An invalid trip point becomes invalid or a valid trip point becomes invalid
@@ -90,7 +94,7 @@ struct acpi_thermal_passive {
 	struct acpi_thermal_trip trip;
 	unsigned long tc1;
 	unsigned long tc2;
-	unsigned long tsp;
+	unsigned long delay;
 };
 
 struct acpi_thermal_active {
@@ -110,7 +114,6 @@ struct acpi_thermal {
 	unsigned long polling_frequency;
 	volatile u8 zombie;
 	struct acpi_thermal_trips trips;
-	struct thermal_trip *trip_table;
 	struct thermal_zone_device *thermal_zone;
 	int kelvin_offset;	/* in millidegrees */
 	struct work_struct thermal_check_work;
@@ -165,11 +168,17 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz)
 
 static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k)
 {
+	int temp;
+
 	if (temp_deci_k == THERMAL_TEMP_INVALID)
 		return THERMAL_TEMP_INVALID;
 
-	return deci_kelvin_to_millicelsius_with_offset(temp_deci_k,
+	temp = deci_kelvin_to_millicelsius_with_offset(temp_deci_k,
 						       tz->kelvin_offset);
+	if (temp <= 0)
+		return THERMAL_TEMP_INVALID;
+
+	return temp;
 }
 
 static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip)
@@ -188,24 +197,19 @@ static int active_trip_index(struct acpi_thermal *tz,
 
 static long get_passive_temp(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, "_PSV", NULL, &tmp);
-	if (ACPI_FAILURE(status))
+	if (acpi_passive_trip_temp(tz->device, &temp))
 		return THERMAL_TEMP_INVALID;
 
-	return tmp;
+	return temp;
 }
 
 static long get_active_temp(struct acpi_thermal *tz, int index)
 {
-	char method[] = { '_', 'A', 'C', '0' + index, '\0' };
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, method, NULL, &tmp);
-	if (ACPI_FAILURE(status))
+	if (acpi_active_trip_temp(tz->device, index, &temp))
 		return THERMAL_TEMP_INVALID;
 
 	/*
@@ -215,10 +219,10 @@ static long get_active_temp(struct acpi_thermal *tz, int index)
 	if (act > 0) {
 		unsigned long long override = celsius_to_deci_kelvin(act);
 
-		if (tmp > override)
-			tmp = override;
+		if (temp > override)
+			return override;
 	}
-	return tmp;
+	return temp;
 }
 
 static void acpi_thermal_update_trip(struct acpi_thermal *tz,
@@ -247,7 +251,6 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 {
 	struct acpi_handle_list devices = { 0 };
 	char method[] = "_PSL";
-	acpi_status status;
 
 	if (index != ACPI_THERMAL_TRIP_PASSIVE) {
 		method[1] = 'A';
@@ -255,8 +258,7 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 		method[3] = '0' + index;
 	}
 
-	status = acpi_evaluate_reference(tz->device->handle, method, NULL, &devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(tz->device->handle, method, NULL, &devices)) {
 		acpi_handle_info(tz->device->handle, "%s evaluation failure\n", method);
 		return false;
 	}
@@ -297,6 +299,7 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 	struct acpi_thermal_trip *acpi_trip = trip->priv;
 	struct adjust_trip_data *atd = data;
 	struct acpi_thermal *tz = atd->tz;
+	int temp;
 
 	if (!acpi_trip || !acpi_thermal_trip_valid(acpi_trip))
 		return 0;
@@ -307,9 +310,11 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 		acpi_thermal_update_trip_devices(tz, trip);
 
 	if (acpi_thermal_trip_valid(acpi_trip))
-		trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
+		temp = acpi_thermal_temp(tz, acpi_trip->temp_dk);
 	else
-		trip->temperature = THERMAL_TEMP_INVALID;
+		temp = THERMAL_TEMP_INVALID;
+
+	thermal_zone_set_trip_temp(tz->thermal_zone, trip, temp);
 
 	return 0;
 }
@@ -339,13 +344,12 @@ static void acpi_thermal_trips_update(struct acpi_thermal *tz, u32 event)
 					dev_name(&adev->dev), event, 0);
 }
 
-static long acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
+static int acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
 	if (crt > 0) {
-		tmp = celsius_to_deci_kelvin(crt);
+		temp = celsius_to_deci_kelvin(crt);
 		goto set;
 	}
 	if (crt == -1) {
@@ -353,38 +357,34 @@ static long acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
 		return THERMAL_TEMP_INVALID;
 	}
 
-	status = acpi_evaluate_integer(tz->device->handle, "_CRT", NULL, &tmp);
-	if (ACPI_FAILURE(status)) {
-		acpi_handle_debug(tz->device->handle, "No critical threshold\n");
+	if (acpi_critical_trip_temp(tz->device, &temp))
 		return THERMAL_TEMP_INVALID;
-	}
-	if (tmp <= 2732) {
+
+	if (temp <= 2732) {
 		/*
 		 * Below zero (Celsius) values clearly aren't right for sure,
 		 * so discard them as invalid.
 		 */
-		pr_info(FW_BUG "Invalid critical threshold (%llu)\n", tmp);
+		pr_info(FW_BUG "Invalid critical threshold (%d)\n", temp);
 		return THERMAL_TEMP_INVALID;
 	}
 
 set:
-	acpi_handle_debug(tz->device->handle, "Critical threshold [%llu]\n", tmp);
-	return tmp;
+	acpi_handle_debug(tz->device->handle, "Critical threshold [%d]\n", temp);
+	return temp;
 }
 
-static long acpi_thermal_get_hot_trip(struct acpi_thermal *tz)
+static int acpi_thermal_get_hot_trip(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, "_HOT", NULL, &tmp);
-	if (ACPI_FAILURE(status)) {
+	if (acpi_hot_trip_temp(tz->device, &temp) || temp == THERMAL_TEMP_INVALID) {
 		acpi_handle_debug(tz->device->handle, "No hot threshold\n");
 		return THERMAL_TEMP_INVALID;
 	}
 
-	acpi_handle_debug(tz->device->handle, "Hot threshold [%llu]\n", tmp);
-	return tmp;
+	acpi_handle_debug(tz->device->handle, "Hot threshold [%d]\n", temp);
+	return temp;
 }
 
 static bool passive_trip_params_init(struct acpi_thermal *tz)
@@ -404,11 +404,17 @@ static bool passive_trip_params_init(struct acpi_thermal *tz)
 
 	tz->trips.passive.tc2 = tmp;
 
+	status = acpi_evaluate_integer(tz->device->handle, "_TFP", NULL, &tmp);
+	if (ACPI_SUCCESS(status)) {
+		tz->trips.passive.delay = tmp;
+		return true;
+	}
+
 	status = acpi_evaluate_integer(tz->device->handle, "_TSP", NULL, &tmp);
 	if (ACPI_FAILURE(status))
 		return false;
 
-	tz->trips.passive.tsp = tmp;
+	tz->trips.passive.delay = tmp * 100;
 
 	return true;
 }
@@ -452,26 +458,19 @@ fail:
 	return false;
 }
 
-static int acpi_thermal_get_trip_points(struct acpi_thermal *tz)
+static void acpi_thermal_get_trip_points(struct acpi_thermal *tz)
 {
-	unsigned int count = 0;
 	int i;
 
-	if (acpi_thermal_init_trip(tz, ACPI_THERMAL_TRIP_PASSIVE))
-		count++;
+	acpi_thermal_init_trip(tz, ACPI_THERMAL_TRIP_PASSIVE);
 
 	for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
-		if (acpi_thermal_init_trip(tz, i))
-			count++;
-		else
+		if (!acpi_thermal_init_trip(tz, i))
 			break;
-
 	}
 
 	while (++i < ACPI_THERMAL_MAX_ACTIVE)
 		tz->trips.active[i].trip.temp_dk = THERMAL_TEMP_INVALID;
-
-	return count;
 }
 
 /* sys I/F for generic thermal sysfs support */
@@ -559,77 +558,31 @@ static void acpi_thermal_zone_device_critical(struct thermal_zone_device *therma
 	thermal_zone_device_critical(thermal);
 }
 
-struct acpi_thermal_bind_data {
-	struct thermal_zone_device *thermal;
-	struct thermal_cooling_device *cdev;
-	bool bind;
-};
-
-static int bind_unbind_cdev_cb(struct thermal_trip *trip, void *arg)
+static bool acpi_thermal_should_bind_cdev(struct thermal_zone_device *thermal,
+					  const struct thermal_trip *trip,
+					  struct thermal_cooling_device *cdev,
+					  struct cooling_spec *c)
 {
 	struct acpi_thermal_trip *acpi_trip = trip->priv;
-	struct acpi_thermal_bind_data *bd = arg;
-	struct thermal_zone_device *thermal = bd->thermal;
-	struct thermal_cooling_device *cdev = bd->cdev;
 	struct acpi_device *cdev_adev = cdev->devdata;
 	int i;
 
 	/* Skip critical and hot trips. */
 	if (!acpi_trip)
-		return 0;
+		return false;
 
 	for (i = 0; i < acpi_trip->devices.count; i++) {
 		acpi_handle handle = acpi_trip->devices.handles[i];
-		struct acpi_device *adev = acpi_fetch_acpi_dev(handle);
-
-		if (adev != cdev_adev)
-			continue;
-
-		if (bd->bind) {
-			int ret;
-
-			ret = thermal_bind_cdev_to_trip(thermal, trip, cdev,
-							THERMAL_NO_LIMIT,
-							THERMAL_NO_LIMIT,
-							THERMAL_WEIGHT_DEFAULT);
-			if (ret)
-				return ret;
-		} else {
-			thermal_unbind_cdev_from_trip(thermal, trip, cdev);
-		}
-	}
-
-	return 0;
-}
-
-static int acpi_thermal_bind_unbind_cdev(struct thermal_zone_device *thermal,
-					 struct thermal_cooling_device *cdev,
-					 bool bind)
-{
-	struct acpi_thermal_bind_data bd = {
-		.thermal = thermal, .cdev = cdev, .bind = bind
-	};
-
-	return for_each_thermal_trip(thermal, bind_unbind_cdev_cb, &bd);
-}
 
-static int
-acpi_thermal_bind_cooling_device(struct thermal_zone_device *thermal,
-				 struct thermal_cooling_device *cdev)
-{
-	return acpi_thermal_bind_unbind_cdev(thermal, cdev, true);
-}
+		if (acpi_fetch_acpi_dev(handle) == cdev_adev)
+			return true;
+	}
 
-static int
-acpi_thermal_unbind_cooling_device(struct thermal_zone_device *thermal,
-				   struct thermal_cooling_device *cdev)
-{
-	return acpi_thermal_bind_unbind_cdev(thermal, cdev, false);
+	return false;
 }
 
-static struct thermal_zone_device_ops acpi_thermal_zone_ops = {
-	.bind = acpi_thermal_bind_cooling_device,
-	.unbind	= acpi_thermal_unbind_cooling_device,
+static const struct thermal_zone_device_ops acpi_thermal_zone_ops = {
+	.should_bind = acpi_thermal_should_bind_cdev,
 	.get_temp = thermal_get_temp,
 	.get_trend = thermal_get_trend,
 	.hot = acpi_thermal_zone_device_hot,
@@ -663,19 +616,21 @@ static void acpi_thermal_zone_sysfs_remove(struct acpi_thermal *tz)
 }
 
 static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz,
+					      const struct thermal_trip *trip_table,
 					      unsigned int trip_count,
 					      int passive_delay)
 {
 	int result;
 
-	tz->thermal_zone = thermal_zone_device_register_with_trips("acpitz",
-								   tz->trip_table,
-								   trip_count,
-								   0, tz,
-								   &acpi_thermal_zone_ops,
-								   NULL,
-								   passive_delay,
-								   tz->polling_frequency * 100);
+	if (trip_count)
+		tz->thermal_zone = thermal_zone_device_register_with_trips(
+					"acpitz", trip_table, trip_count, tz,
+					&acpi_thermal_zone_ops, NULL, passive_delay,
+					tz->polling_frequency * 100);
+	else
+		tz->thermal_zone = thermal_tripless_zone_device_register(
+					"acpitz", tz, &acpi_thermal_zone_ops, NULL);
+
 	if (IS_ERR(tz->thermal_zone))
 		return PTR_ERR(tz->thermal_zone);
 
@@ -824,10 +779,10 @@ static void acpi_thermal_free_thermal_zone(struct acpi_thermal *tz)
 
 static int acpi_thermal_add(struct acpi_device *device)
 {
+	struct thermal_trip trip_table[ACPI_THERMAL_MAX_NR_TRIPS] = { 0 };
 	struct acpi_thermal_trip *acpi_trip;
 	struct thermal_trip *trip;
 	struct acpi_thermal *tz;
-	unsigned int trip_count;
 	int crit_temp, hot_temp;
 	int passive_delay = 0;
 	int result;
@@ -841,39 +796,30 @@ static int acpi_thermal_add(struct acpi_device *device)
 		return -ENOMEM;
 
 	tz->device = device;
-	strcpy(tz->name, device->pnp.bus_id);
-	strcpy(acpi_device_name(device), ACPI_THERMAL_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_THERMAL_CLASS);
+	strscpy(tz->name, device->pnp.bus_id);
+	strscpy(acpi_device_name(device), ACPI_THERMAL_DEVICE_NAME);
+	strscpy(acpi_device_class(device), ACPI_THERMAL_CLASS);
 	device->driver_data = tz;
 
 	acpi_thermal_aml_dependency_fix(tz);
 
-	/* Get trip points [_CRT, _PSV, etc.] (required). */
-	trip_count = acpi_thermal_get_trip_points(tz);
+	/*
+	 * Set the cooling mode [_SCP] to active cooling. This needs to happen before
+	 * we retrieve the trip point values.
+	 */
+	acpi_execute_simple_method(tz->device->handle, "_SCP", ACPI_THERMAL_MODE_ACTIVE);
 
-	crit_temp = acpi_thermal_get_critical_trip(tz);
-	if (crit_temp != THERMAL_TEMP_INVALID)
-		trip_count++;
+	/* Get trip points [_ACi, _PSV, etc.] (required). */
+	acpi_thermal_get_trip_points(tz);
 
+	crit_temp = acpi_thermal_get_critical_trip(tz);
 	hot_temp = acpi_thermal_get_hot_trip(tz);
-	if (hot_temp != THERMAL_TEMP_INVALID)
-		trip_count++;
-
-	if (!trip_count) {
-		pr_warn(FW_BUG "No valid trip points!\n");
-		result = -ENODEV;
-		goto free_memory;
-	}
 
 	/* Get temperature [_TMP] (required). */
 	result = acpi_thermal_get_temperature(tz);
 	if (result)
 		goto free_memory;
 
-	/* Set the cooling mode [_SCP] to active cooling. */
-	acpi_execute_simple_method(tz->device->handle, "_SCP",
-				   ACPI_THERMAL_MODE_ACTIVE);
-
 	/* Determine the default polling frequency [_TZP]. */
 	if (tzp)
 		tz->polling_frequency = tzp;
@@ -882,13 +828,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 
 	acpi_thermal_guess_offset(tz, crit_temp);
 
-	trip = kcalloc(trip_count, sizeof(*trip), GFP_KERNEL);
-	if (!trip) {
-		result = -ENOMEM;
-		goto free_memory;
-	}
-
-	tz->trip_table = trip;
+	trip = trip_table;
 
 	if (crit_temp != THERMAL_TEMP_INVALID) {
 		trip->type = THERMAL_TRIP_CRITICAL;
@@ -904,7 +844,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 
 	acpi_trip = &tz->trips.passive.trip;
 	if (acpi_thermal_trip_valid(acpi_trip)) {
-		passive_delay = tz->trips.passive.tsp * 100;
+		passive_delay = tz->trips.passive.delay;
 
 		trip->type = THERMAL_TRIP_PASSIVE;
 		trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
@@ -924,9 +864,14 @@ static int acpi_thermal_add(struct acpi_device *device)
 		trip++;
 	}
 
-	result = acpi_thermal_register_thermal_zone(tz, trip_count, passive_delay);
+	if (trip == trip_table)
+		pr_warn(FW_BUG "No valid trip points!\n");
+
+	result = acpi_thermal_register_thermal_zone(tz, trip_table,
+						    trip - trip_table,
+						    passive_delay);
 	if (result)
-		goto free_trips;
+		goto free_memory;
 
 	refcount_set(&tz->thermal_check_count, 3);
 	mutex_init(&tz->thermal_check_lock);
@@ -945,8 +890,6 @@ static int acpi_thermal_add(struct acpi_device *device)
 flush_wq:
 	flush_workqueue(acpi_thermal_pm_queue);
 	acpi_thermal_unregister_thermal_zone(tz);
-free_trips:
-	kfree(tz->trip_table);
 free_memory:
 	acpi_thermal_free_thermal_zone(tz);
 
@@ -967,7 +910,6 @@ static void acpi_thermal_remove(struct acpi_device *device)
 
 	flush_workqueue(acpi_thermal_pm_queue);
 	acpi_thermal_unregister_thermal_zone(tz);
-	kfree(tz->trip_table);
 	acpi_thermal_free_thermal_zone(tz);
 }
 
@@ -982,7 +924,7 @@ static int acpi_thermal_suspend(struct device *dev)
 static int acpi_thermal_resume(struct device *dev)
 {
 	struct acpi_thermal *tz;
-	int i, j, power_state;
+	int i, j;
 
 	if (!dev)
 		return -EINVAL;
@@ -997,10 +939,8 @@ static int acpi_thermal_resume(struct device *dev)
 		if (!acpi_thermal_trip_valid(acpi_trip))
 			break;
 
-		for (j = 0; j < acpi_trip->devices.count; j++) {
-			acpi_bus_update_power(acpi_trip->devices.handles[j],
-					      &power_state);
-		}
+		for (j = 0; j < acpi_trip->devices.count; j++)
+			acpi_bus_update_power(acpi_trip->devices.handles[j], NULL);
 	}
 
 	acpi_queue_thermal_check(tz);
@@ -1142,6 +1082,7 @@ static void __exit acpi_thermal_exit(void)
 module_init(acpi_thermal_init);
 module_exit(acpi_thermal_exit);
 
+MODULE_IMPORT_NS("ACPI_THERMAL");
 MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI Thermal Zone Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/thermal_lib.c b/drivers/acpi/thermal_lib.c
new file mode 100644
index 000000000000..f81591927e86
--- /dev/null
+++ b/drivers/acpi/thermal_lib.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Linaro Limited
+ * Copyright 2023 Intel Corporation
+ *
+ * Library routines for retrieving trip point temperature values from the
+ * platform firmware via ACPI.
+ */
+#include <linux/acpi.h>
+#include <linux/units.h>
+#include <linux/thermal.h>
+#include "internal.h"
+
+/*
+ * Minimum temperature for full military grade is 218°K (-55°C) and
+ * max temperature is 448°K (175°C). We can consider those values as
+ * the boundaries for the [trips] temperature returned by the
+ * firmware. Any values out of these boundaries may be considered
+ * bogus and we can assume the firmware has no data to provide.
+ */
+#define TEMP_MIN_DECIK	2180ULL
+#define TEMP_MAX_DECIK	4480ULL
+
+static int acpi_trip_temp(struct acpi_device *adev, char *obj_name,
+			  int *ret_temp)
+{
+	unsigned long long temp;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(adev->handle, obj_name, NULL, &temp);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_debug(adev->handle, "%s evaluation failed\n", obj_name);
+		return -ENODATA;
+	}
+
+	if (temp >= TEMP_MIN_DECIK && temp <= TEMP_MAX_DECIK) {
+		*ret_temp = temp;
+	} else {
+		acpi_handle_debug(adev->handle, "%s result %llu out of range\n",
+				  obj_name, temp);
+		*ret_temp = THERMAL_TEMP_INVALID;
+	}
+
+	return 0;
+}
+
+int acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
+{
+	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
+
+	if (id < 0 || id > 9)
+		return -EINVAL;
+
+	return acpi_trip_temp(adev, obj_name, ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_active_trip_temp, "ACPI_THERMAL");
+
+int acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_PSV", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_passive_trip_temp, "ACPI_THERMAL");
+
+int acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_HOT", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_hot_trip_temp, "ACPI_THERMAL");
+
+int acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_CRT", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_critical_trip_temp, "ACPI_THERMAL");
+
+static int thermal_temp(int error, int temp_decik, int *ret_temp)
+{
+	if (error)
+		return error;
+
+	if (temp_decik == THERMAL_TEMP_INVALID)
+		*ret_temp = THERMAL_TEMP_INVALID;
+	else
+		*ret_temp = deci_kelvin_to_millicelsius(temp_decik);
+
+	return 0;
+}
+
+/**
+ * thermal_acpi_active_trip_temp - Retrieve active trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @id: Active cooling level (0 - 9).
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _ACx object for the thermal zone represented by @adev to obtain
+ * the temperature of the active cooling trip point corresponding to the active
+ * cooling level given by @id.
+ *
+ * Return 0 on success or a negative error value on failure.
+ */
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
+{
+	int temp_decik = 0;
+	int ret = acpi_active_trip_temp(adev, id, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
+
+/**
+ * thermal_acpi_passive_trip_temp - Retrieve passive trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _PSV object for the thermal zone represented by @adev to obtain
+ * the temperature of the passive cooling trip point.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	int temp_decik = 0;
+	int ret = acpi_passive_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
+
+/**
+ * thermal_acpi_hot_trip_temp - Retrieve hot trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _HOT object for the thermal zone represented by @adev to obtain
+ * the temperature of the trip point at which the system is expected to be put
+ * into the S4 sleep state.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	int temp_decik = 0;
+	int ret = acpi_hot_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
+
+/**
+ * thermal_acpi_critical_trip_temp - Retrieve critical trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _CRT object for the thermal zone represented by @adev to obtain
+ * the temperature of the critical cooling trip point.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	int temp_decik = 0;
+	int ret = acpi_critical_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_critical_trip_temp);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 28c75242fca9..526563a0d188 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -277,15 +277,25 @@ acpi_evaluate_integer(acpi_handle handle,
 
 EXPORT_SYMBOL(acpi_evaluate_integer);
 
-int acpi_get_local_address(acpi_handle handle, u32 *addr)
+int acpi_get_local_u64_address(acpi_handle handle, u64 *addr)
 {
-	unsigned long long adr;
 	acpi_status status;
 
-	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr);
+	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, addr);
 	if (ACPI_FAILURE(status))
 		return -ENODATA;
+	return 0;
+}
+EXPORT_SYMBOL(acpi_get_local_u64_address);
+
+int acpi_get_local_address(acpi_handle handle, u32 *addr)
+{
+	u64 adr;
+	int ret;
 
+	ret = acpi_get_local_u64_address(handle, &adr);
+	if (ret < 0)
+		return ret;
 	*addr = (u32)adr;
 	return 0;
 }
@@ -329,21 +339,18 @@ const char *acpi_get_subsystem_id(acpi_handle handle)
 }
 EXPORT_SYMBOL_GPL(acpi_get_subsystem_id);
 
-acpi_status
-acpi_evaluate_reference(acpi_handle handle,
-			acpi_string pathname,
-			struct acpi_object_list *arguments,
-			struct acpi_handle_list *list)
+bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname,
+			     struct acpi_object_list *arguments,
+			     struct acpi_handle_list *list)
 {
-	acpi_status status = AE_OK;
-	union acpi_object *package = NULL;
-	union acpi_object *element = NULL;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	u32 i = 0;
-
+	union acpi_object *package;
+	acpi_status status;
+	bool ret = false;
+	u32 i;
 
 	if (!list)
-		return AE_BAD_PARAMETER;
+		return false;
 
 	/* Evaluate object. */
 
@@ -353,62 +360,47 @@ acpi_evaluate_reference(acpi_handle handle,
 
 	package = buffer.pointer;
 
-	if ((buffer.length == 0) || !package) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
-	if (package->type != ACPI_TYPE_PACKAGE) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
-	if (!package->package.count) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
+	if (buffer.length == 0 || !package ||
+	    package->type != ACPI_TYPE_PACKAGE || !package->package.count)
+		goto err;
 
-	list->handles = kcalloc(package->package.count, sizeof(*list->handles), GFP_KERNEL);
-	if (!list->handles) {
-		kfree(package);
-		return AE_NO_MEMORY;
-	}
 	list->count = package->package.count;
+	list->handles = kcalloc(list->count, sizeof(*list->handles), GFP_KERNEL);
+	if (!list->handles)
+		goto err_clear;
 
 	/* Extract package data. */
 
 	for (i = 0; i < list->count; i++) {
+		union acpi_object *element = &(package->package.elements[i]);
 
-		element = &(package->package.elements[i]);
-
-		if (element->type != ACPI_TYPE_LOCAL_REFERENCE) {
-			status = AE_BAD_DATA;
-			acpi_util_eval_error(handle, pathname, status);
-			break;
-		}
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE ||
+		    !element->reference.handle)
+			goto err_free;
 
-		if (!element->reference.handle) {
-			status = AE_NULL_ENTRY;
-			acpi_util_eval_error(handle, pathname, status);
-			break;
-		}
 		/* Get the  acpi_handle. */
 
 		list->handles[i] = element->reference.handle;
 		acpi_handle_debug(list->handles[i], "Found in reference list\n");
 	}
 
-end:
-	if (ACPI_FAILURE(status)) {
-		list->count = 0;
-		kfree(list->handles);
-		list->handles = NULL;
-	}
+	ret = true;
 
+end:
 	kfree(buffer.pointer);
 
-	return status;
+	return ret;
+
+err_free:
+	kfree(list->handles);
+	list->handles = NULL;
+
+err_clear:
+	list->count = 0;
+
+err:
+	acpi_util_eval_error(handle, pathname, status);
+	goto end;
 }
 
 EXPORT_SYMBOL(acpi_evaluate_reference);
@@ -426,7 +418,7 @@ bool acpi_handle_list_equal(struct acpi_handle_list *list1,
 {
 	return list1->count == list2->count &&
 		!memcmp(list1->handles, list2->handles,
-		        list1->count * sizeof(acpi_handle));
+		        list1->count * sizeof(*list1->handles));
 }
 EXPORT_SYMBOL_GPL(acpi_handle_list_equal);
 
@@ -468,7 +460,41 @@ void acpi_handle_list_free(struct acpi_handle_list *list)
 }
 EXPORT_SYMBOL_GPL(acpi_handle_list_free);
 
-acpi_status
+/**
+ * acpi_device_dep - Check ACPI device dependency
+ * @target: ACPI handle of the target ACPI device.
+ * @match: ACPI handle to look up in the target's _DEP list.
+ *
+ * Return true if @match is present in the list returned by _DEP for
+ * @target or false otherwise.
+ */
+bool acpi_device_dep(acpi_handle target, acpi_handle match)
+{
+	struct acpi_handle_list dep_devices;
+	bool ret = false;
+	int i;
+
+	if (!acpi_has_method(target, "_DEP"))
+		return false;
+
+	if (!acpi_evaluate_reference(target, "_DEP", NULL, &dep_devices)) {
+		acpi_handle_debug(target, "Failed to evaluate _DEP.\n");
+		return false;
+	}
+
+	for (i = 0; i < dep_devices.count; i++) {
+		if (dep_devices.handles[i] == match) {
+			ret = true;
+			break;
+		}
+	}
+
+	acpi_handle_list_free(&dep_devices);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(acpi_device_dep);
+
+bool
 acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld)
 {
 	acpi_status status;
@@ -476,9 +502,8 @@ acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld
 	union acpi_object *output;
 
 	status = acpi_evaluate_object(handle, "_PLD", NULL, &buffer);
-
 	if (ACPI_FAILURE(status))
-		return status;
+		return false;
 
 	output = buffer.pointer;
 
@@ -497,7 +522,7 @@ acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld
 
 out:
 	kfree(buffer.pointer);
-	return status;
+	return ACPI_SUCCESS(status);
 }
 EXPORT_SYMBOL(acpi_get_physical_device_location);
 
@@ -543,7 +568,7 @@ EXPORT_SYMBOL(acpi_evaluate_ost);
  *
  * Caller must free the returned buffer
  */
-static char *acpi_handle_path(acpi_handle handle)
+char *acpi_handle_path(acpi_handle handle)
 {
 	struct acpi_buffer buffer = {
 		.length = ACPI_ALLOCATE_BUFFER,
@@ -775,7 +800,8 @@ acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func,
 
 	if (ret != AE_NOT_FOUND)
 		acpi_handle_warn(handle,
-				 "failed to evaluate _DSM %pUb (0x%x)\n", guid, ret);
+				 "failed to evaluate _DSM %pUb rev:%lld func:%lld (0x%x)\n",
+				 guid, rev, func, ret);
 
 	return NULL;
 }
@@ -825,54 +851,6 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
 EXPORT_SYMBOL(acpi_check_dsm);
 
 /**
- * acpi_dev_uid_match - Match device by supplied UID
- * @adev: ACPI device to match.
- * @uid2: Unique ID of the device.
- *
- * Matches UID in @adev with given @uid2.
- *
- * Returns:
- *  - %true if matches.
- *  - %false otherwise.
- */
-bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2)
-{
-	const char *uid1 = acpi_device_uid(adev);
-
-	return uid1 && uid2 && !strcmp(uid1, uid2);
-}
-EXPORT_SYMBOL_GPL(acpi_dev_uid_match);
-
-/**
- * acpi_dev_hid_uid_match - Match device by supplied HID and UID
- * @adev: ACPI device to match.
- * @hid2: Hardware ID of the device.
- * @uid2: Unique ID of the device, pass NULL to not check _UID.
- *
- * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
- * will be treated as a match. If user wants to validate @uid2, it should be
- * done before calling this function.
- *
- * Returns:
- *  - %true if matches or @uid2 is NULL.
- *  - %false otherwise.
- */
-bool acpi_dev_hid_uid_match(struct acpi_device *adev,
-			    const char *hid2, const char *uid2)
-{
-	const char *hid1 = acpi_device_hid(adev);
-
-	if (strcmp(hid1, hid2))
-		return false;
-
-	if (!uid2)
-		return true;
-
-	return acpi_dev_uid_match(adev, uid2);
-}
-EXPORT_SYMBOL(acpi_dev_hid_uid_match);
-
-/**
  * acpi_dev_uid_to_integer - treat ACPI device _UID as integer
  * @adev: ACPI device to get _UID from
  * @integer: output buffer for integer
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 9fdcc620c652..4cf74f173c78 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void)
 		acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
 	if (!strcmp("apple_gmux", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_apple_gmux;
+	if (!strcmp("dell_uart", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_dell_uart;
 	if (!strcmp("none", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_none;
 }
@@ -252,6 +254,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "PCG-FRV35"),
 		},
 	},
+	{
+	 .callback = video_detect_force_vendor,
+	 /* Panasonic Toughbook CF-18 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Matsushita Electric Industrial"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "CF-18"),
+		},
+	},
 
 	/*
 	 * Toshiba models with Transflective display, these need to use
@@ -499,6 +509,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	},
 	{
 	 .callback = video_detect_force_native,
+	 /* Lenovo Slim 7 16ARH7 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "82UX"),
+		},
+	},
+	{
+	 .callback = video_detect_force_native,
 	 /* Lenovo ThinkPad X131e (3371 AMD version) */
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -532,6 +550,38 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		},
 	},
 	{
+	 .callback = video_detect_force_native,
+	 /* Apple MacBook Air 7,2 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookAir7,2"),
+		},
+	},
+	{
+	 .callback = video_detect_force_native,
+	 /* Apple MacBook Air 9,1 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookAir9,1"),
+		},
+	},
+	{
+	 .callback = video_detect_force_native,
+	 /* Apple MacBook Pro 9,2 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,2"),
+		},
+	},
+	{
+	 .callback = video_detect_force_native,
+	 /* Apple MacBook Pro 11,2 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro11,2"),
+		},
+	},
+	{
 	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */
 	 .callback = video_detect_force_native,
 	 /* Apple MacBook Pro 12,1 */
@@ -542,6 +592,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	},
 	{
 	 .callback = video_detect_force_native,
+	 /* Apple MacBook Pro 16,2 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro16,2"),
+		},
+	},
+	{
+	 .callback = video_detect_force_native,
 	 /* Dell Inspiron N4010 */
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -798,6 +856,30 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	},
 
 	/*
+	 * Dell AIO (All in Ones) which advertise an UART attached backlight
+	 * controller board in their ACPI tables (and may even have one), but
+	 * which need native backlight control nevertheless.
+	 */
+	{
+	 /* https://github.com/zabbly/linux/issues/26 */
+	 .callback = video_detect_force_native,
+	 /* Dell OptiPlex 5480 AIO */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 5480 AIO"),
+		},
+	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */
+	 .callback = video_detect_force_native,
+	 /* Dell OptiPlex 7760 AIO */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"),
+		},
+	},
+
+	/*
 	 * Models which have nvidia-ec-wmi support, but should not use it.
 	 * Note this indicates a likely firmware bug on these models and should
 	 * be revisited if/when Linux gets support for dynamic mux mode.
@@ -855,7 +937,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	 /* Lenovo Yoga Tab 3 Pro YT3-X90F */
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
 		DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
 		},
 	},
@@ -867,6 +948,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Mipad2"),
 		},
 	},
+	/* https://gitlab.freedesktop.org/drm/amd/-/issues/4512 */
+	{
+	 .callback = video_detect_force_native,
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "82K8"),
+		},
+	},
 	{ },
 };
 
@@ -894,6 +983,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 	static DEFINE_MUTEX(init_mutex);
 	static bool nvidia_wmi_ec_present;
 	static bool apple_gmux_present;
+	static bool dell_uart_present;
 	static bool native_available;
 	static bool init_done;
 	static long video_caps;
@@ -908,6 +998,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 				    &video_caps, NULL);
 		nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
 		apple_gmux_present = apple_gmux_detect(NULL, NULL);
+		dell_uart_present = acpi_dev_present("DELL0501", NULL, -1);
 		init_done = true;
 	}
 	if (native)
@@ -938,6 +1029,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 	if (apple_gmux_present)
 		return acpi_backlight_apple_gmux;
 
+	if (dell_uart_present)
+		return acpi_backlight_dell_uart;
+
 	/* Use ACPI video if available, except when native should be preferred. */
 	if ((video_caps & ACPI_VIDEO_BACKLIGHT) &&
 	     !(native_available && prefer_native_over_acpi_video()))
diff --git a/drivers/acpi/viot.c b/drivers/acpi/viot.c
index c8025921c129..c13a20365c2c 100644
--- a/drivers/acpi/viot.c
+++ b/drivers/acpi/viot.c
@@ -19,11 +19,11 @@
 #define pr_fmt(fmt) "ACPI: VIOT: " fmt
 
 #include <linux/acpi_viot.h>
-#include <linux/fwnode.h>
 #include <linux/iommu.h>
 #include <linux/list.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 
 struct viot_iommu {
 	/* Node offset within the table */
@@ -307,21 +307,14 @@ void __init acpi_viot_init(void)
 static int viot_dev_iommu_init(struct device *dev, struct viot_iommu *viommu,
 			       u32 epid)
 {
-	const struct iommu_ops *ops;
-
-	if (!viommu)
+	if (!viommu || !IS_ENABLED(CONFIG_VIRTIO_IOMMU))
 		return -ENODEV;
 
 	/* We're not translating ourself */
 	if (device_match_fwnode(dev, viommu->fwnode))
 		return -EINVAL;
 
-	ops = iommu_ops_from_fwnode(viommu->fwnode);
-	if (!ops)
-		return IS_ENABLED(CONFIG_VIRTIO_IOMMU) ?
-			-EPROBE_DEFER : -ENODEV;
-
-	return acpi_iommu_fwspec_init(dev, epid, viommu->fwnode, ops);
+	return acpi_iommu_fwspec_init(dev, epid, viommu->fwnode);
 }
 
 static int viot_pci_dev_iommu_init(struct pci_dev *pdev, u16 dev_id, void *data)
diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c
index b02bf770aead..ff6dc957bc11 100644
--- a/drivers/acpi/wakeup.c
+++ b/drivers/acpi/wakeup.c
@@ -42,7 +42,7 @@ void acpi_enable_wakeup_devices(u8 sleep_state)
 	list_for_each_entry_safe(dev, tmp, &acpi_wakeup_device_list,
 				 wakeup_list) {
 		if (!dev->wakeup.flags.valid
-		    || sleep_state > (u32) dev->wakeup.sleep_state
+		    || sleep_state > dev->wakeup.sleep_state
 		    || !(device_may_wakeup(&dev->dev)
 			 || dev->wakeup.prepare_count))
 			continue;
@@ -67,7 +67,7 @@ void acpi_disable_wakeup_devices(u8 sleep_state)
 	list_for_each_entry_safe(dev, tmp, &acpi_wakeup_device_list,
 				 wakeup_list) {
 		if (!dev->wakeup.flags.valid
-		    || sleep_state > (u32) dev->wakeup.sleep_state
+		    || sleep_state > dev->wakeup.sleep_state
 		    || !(device_may_wakeup(&dev->dev)
 			 || dev->wakeup.prepare_count))
 			continue;
diff --git a/drivers/acpi/x86/Makefile b/drivers/acpi/x86/Makefile
new file mode 100644
index 000000000000..63c99509ed9d
--- /dev/null
+++ b/drivers/acpi/x86/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_ACPI)	+= acpi-x86.o
+acpi-x86-y		+= apple.o
+acpi-x86-y		+= cmos_rtc.o
+acpi-x86-$(CONFIG_PCI)	+= lpss.o
+acpi-x86-y		+= s2idle.o
+acpi-x86-y		+= utils.o
+
+obj-$(CONFIG_X86)	+= blacklist.o
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/x86/blacklist.c
index a558d24fb788..55214d0a12b1 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/x86/blacklist.c
@@ -17,7 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/dmi.h>
 
-#include "internal.h"
+#include "../internal.h"
 
 #ifdef CONFIG_DMI
 static const struct dmi_system_id acpi_rev_dmi_table[] __initconst;
diff --git a/drivers/acpi/x86/cmos_rtc.c b/drivers/acpi/x86/cmos_rtc.c
new file mode 100644
index 000000000000..51643ff6fe5f
--- /dev/null
+++ b/drivers/acpi/x86/cmos_rtc.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ACPI support for CMOS RTC Address Space access
+ *
+ * Copyright (C) 2013, Intel Corporation
+ * Authors: Lan Tianyu <tianyu.lan@intel.com>
+ */
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mc146818rtc.h>
+
+#include "../internal.h"
+
+static const struct acpi_device_id acpi_cmos_rtc_ids[] = {
+	{ "PNP0B00" },
+	{ "PNP0B01" },
+	{ "PNP0B02" },
+	{}
+};
+
+static acpi_status
+acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address,
+		      u32 bits, u64 *value64,
+		      void *handler_context, void *region_context)
+{
+	int i;
+	u8 *value = (u8 *)value64;
+
+	if (address > 0xff || !value64)
+		return AE_BAD_PARAMETER;
+
+	if (function != ACPI_WRITE && function != ACPI_READ)
+		return AE_BAD_PARAMETER;
+
+	spin_lock_irq(&rtc_lock);
+
+	for (i = 0; i < DIV_ROUND_UP(bits, 8); ++i, ++address, ++value)
+		if (function == ACPI_READ)
+			*value = CMOS_READ(address);
+		else
+			CMOS_WRITE(*value, address);
+
+	spin_unlock_irq(&rtc_lock);
+
+	return AE_OK;
+}
+
+int acpi_install_cmos_rtc_space_handler(acpi_handle handle)
+{
+	acpi_status status;
+
+	status = acpi_install_address_space_handler(handle,
+			ACPI_ADR_SPACE_CMOS,
+			&acpi_cmos_rtc_space_handler,
+			NULL, NULL);
+	if (ACPI_FAILURE(status)) {
+		pr_err("Error installing CMOS-RTC region handler\n");
+		return -ENODEV;
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(acpi_install_cmos_rtc_space_handler);
+
+void acpi_remove_cmos_rtc_space_handler(acpi_handle handle)
+{
+	if (ACPI_FAILURE(acpi_remove_address_space_handler(handle,
+			ACPI_ADR_SPACE_CMOS, &acpi_cmos_rtc_space_handler)))
+		pr_err("Error removing CMOS-RTC region handler\n");
+}
+EXPORT_SYMBOL_GPL(acpi_remove_cmos_rtc_space_handler);
+
+static int acpi_cmos_rtc_attach_handler(struct acpi_device *adev, const struct acpi_device_id *id)
+{
+	return acpi_install_cmos_rtc_space_handler(adev->handle);
+}
+
+static void acpi_cmos_rtc_detach_handler(struct acpi_device *adev)
+{
+	acpi_remove_cmos_rtc_space_handler(adev->handle);
+}
+
+static struct acpi_scan_handler cmos_rtc_handler = {
+	.ids = acpi_cmos_rtc_ids,
+	.attach = acpi_cmos_rtc_attach_handler,
+	.detach = acpi_cmos_rtc_detach_handler,
+};
+
+void __init acpi_cmos_rtc_init(void)
+{
+	acpi_scan_add_handler(&cmos_rtc_handler);
+}
diff --git a/drivers/acpi/x86/lpss.c b/drivers/acpi/x86/lpss.c
new file mode 100644
index 000000000000..6daa6372f980
--- /dev/null
+++ b/drivers/acpi/x86/lpss.c
@@ -0,0 +1,1352 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ACPI support for Intel Lynxpoint LPSS.
+ *
+ * Copyright (C) 2013, Intel Corporation
+ * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/dmi.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/x86/clk-lpss.h>
+#include <linux/platform_data/x86/pmc_atom.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/pwm.h>
+#include <linux/pxa2xx_ssp.h>
+#include <linux/suspend.h>
+#include <linux/delay.h>
+
+#include "../internal.h"
+
+#ifdef CONFIG_X86_INTEL_LPSS
+
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/iosf_mbi.h>
+
+#define LPSS_ADDR(desc) ((unsigned long)&desc)
+
+#define LPSS_CLK_SIZE	0x04
+#define LPSS_LTR_SIZE	0x18
+
+/* Offsets relative to LPSS_PRIVATE_OFFSET */
+#define LPSS_CLK_DIVIDER_DEF_MASK	(BIT(1) | BIT(16))
+#define LPSS_RESETS			0x04
+#define LPSS_RESETS_RESET_FUNC		BIT(0)
+#define LPSS_RESETS_RESET_APB		BIT(1)
+#define LPSS_GENERAL			0x08
+#define LPSS_GENERAL_LTR_MODE_SW	BIT(2)
+#define LPSS_GENERAL_UART_RTS_OVRD	BIT(3)
+#define LPSS_SW_LTR			0x10
+#define LPSS_AUTO_LTR			0x14
+#define LPSS_LTR_SNOOP_REQ		BIT(15)
+#define LPSS_LTR_SNOOP_MASK		0x0000FFFF
+#define LPSS_LTR_SNOOP_LAT_1US		0x800
+#define LPSS_LTR_SNOOP_LAT_32US		0xC00
+#define LPSS_LTR_SNOOP_LAT_SHIFT	5
+#define LPSS_LTR_SNOOP_LAT_CUTOFF	3000
+#define LPSS_LTR_MAX_VAL		0x3FF
+#define LPSS_TX_INT			0x20
+#define LPSS_TX_INT_MASK		BIT(1)
+
+#define LPSS_PRV_REG_COUNT		9
+
+/* LPSS Flags */
+#define LPSS_CLK			BIT(0)
+#define LPSS_CLK_GATE			BIT(1)
+#define LPSS_CLK_DIVIDER		BIT(2)
+#define LPSS_LTR			BIT(3)
+#define LPSS_SAVE_CTX			BIT(4)
+/*
+ * For some devices the DSDT AML code for another device turns off the device
+ * before our suspend handler runs, causing us to read/save all 1-s (0xffffffff)
+ * as ctx register values.
+ * Luckily these devices always use the same ctx register values, so we can
+ * work around this by saving the ctx registers once on activation.
+ */
+#define LPSS_SAVE_CTX_ONCE		BIT(5)
+#define LPSS_NO_D3_DELAY		BIT(6)
+
+struct lpss_private_data;
+
+struct lpss_device_desc {
+	unsigned int flags;
+	const char *clk_con_id;
+	unsigned int prv_offset;
+	size_t prv_size_override;
+	const struct property_entry *properties;
+	void (*setup)(struct lpss_private_data *pdata);
+	bool resume_from_noirq;
+};
+
+static const struct lpss_device_desc lpss_dma_desc = {
+	.flags = LPSS_CLK,
+};
+
+struct lpss_private_data {
+	struct acpi_device *adev;
+	void __iomem *mmio_base;
+	resource_size_t mmio_size;
+	unsigned int fixed_clk_rate;
+	struct clk *clk;
+	const struct lpss_device_desc *dev_desc;
+	u32 prv_reg_ctx[LPSS_PRV_REG_COUNT];
+};
+
+/* Devices which need to be in D3 before lpss_iosf_enter_d3_state() proceeds */
+static u32 pmc_atom_d3_mask = 0xfe000ffe;
+
+/* LPSS run time quirks */
+static unsigned int lpss_quirks;
+
+/*
+ * LPSS_QUIRK_ALWAYS_POWER_ON: override power state for LPSS DMA device.
+ *
+ * The LPSS DMA controller has neither _PS0 nor _PS3 method. Moreover
+ * it can be powered off automatically whenever the last LPSS device goes down.
+ * In case of no power any access to the DMA controller will hang the system.
+ * The behaviour is reproduced on some HP laptops based on Intel BayTrail as
+ * well as on ASuS T100TA transformer.
+ *
+ * This quirk overrides power state of entire LPSS island to keep DMA powered
+ * on whenever we have at least one other device in use.
+ */
+#define LPSS_QUIRK_ALWAYS_POWER_ON	BIT(0)
+
+/* UART Component Parameter Register */
+#define LPSS_UART_CPR			0xF4
+#define LPSS_UART_CPR_AFCE		BIT(4)
+
+static void lpss_uart_setup(struct lpss_private_data *pdata)
+{
+	unsigned int offset;
+	u32 val;
+
+	offset = pdata->dev_desc->prv_offset + LPSS_TX_INT;
+	val = readl(pdata->mmio_base + offset);
+	writel(val | LPSS_TX_INT_MASK, pdata->mmio_base + offset);
+
+	val = readl(pdata->mmio_base + LPSS_UART_CPR);
+	if (!(val & LPSS_UART_CPR_AFCE)) {
+		offset = pdata->dev_desc->prv_offset + LPSS_GENERAL;
+		val = readl(pdata->mmio_base + offset);
+		val |= LPSS_GENERAL_UART_RTS_OVRD;
+		writel(val, pdata->mmio_base + offset);
+	}
+}
+
+static void lpss_deassert_reset(struct lpss_private_data *pdata)
+{
+	unsigned int offset;
+	u32 val;
+
+	offset = pdata->dev_desc->prv_offset + LPSS_RESETS;
+	val = readl(pdata->mmio_base + offset);
+	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
+	writel(val, pdata->mmio_base + offset);
+}
+
+/*
+ * BYT PWM used for backlight control by the i915 driver on systems without
+ * the Crystal Cove PMIC.
+ */
+static struct pwm_lookup byt_pwm_lookup[] = {
+	PWM_LOOKUP_WITH_MODULE("80860F09:00", 0, "0000:00:02.0",
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm-lpss-platform"),
+};
+
+static void byt_pwm_setup(struct lpss_private_data *pdata)
+{
+	/* Only call pwm_add_table for the first PWM controller */
+	if (acpi_dev_uid_match(pdata->adev, 1))
+		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
+}
+
+#define LPSS_I2C_ENABLE			0x6c
+
+static void byt_i2c_setup(struct lpss_private_data *pdata)
+{
+	acpi_handle handle = pdata->adev->handle;
+	unsigned long long shared_host = 0;
+	acpi_status status;
+	u64 uid;
+
+	/* Expected to always be successfull, but better safe then sorry */
+	if (!acpi_dev_uid_to_integer(pdata->adev, &uid) && uid) {
+		/* Detect I2C bus shared with PUNIT and ignore its d3 status */
+		status = acpi_evaluate_integer(handle, "_SEM", NULL, &shared_host);
+		if (ACPI_SUCCESS(status) && shared_host)
+			pmc_atom_d3_mask &= ~(BIT_LPSS2_F1_I2C1 << (uid - 1));
+	}
+
+	lpss_deassert_reset(pdata);
+
+	if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset))
+		pdata->fixed_clk_rate = 133000000;
+
+	writel(0, pdata->mmio_base + LPSS_I2C_ENABLE);
+}
+
+/*
+ * BSW PWM1 is used for backlight control by the i915 driver
+ * BSW PWM2 is used for backlight control for fixed (etched into the glass)
+ * touch controls on some models. These touch-controls have specialized
+ * drivers which know they need the "pwm_soc_lpss_2" con-id.
+ */
+static struct pwm_lookup bsw_pwm_lookup[] = {
+	PWM_LOOKUP_WITH_MODULE("80862288:00", 0, "0000:00:02.0",
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm-lpss-platform"),
+	PWM_LOOKUP_WITH_MODULE("80862289:00", 0, NULL,
+			       "pwm_soc_lpss_2", 0, PWM_POLARITY_NORMAL,
+			       "pwm-lpss-platform"),
+};
+
+static void bsw_pwm_setup(struct lpss_private_data *pdata)
+{
+	/* Only call pwm_add_table for the first PWM controller */
+	if (acpi_dev_uid_match(pdata->adev, 1))
+		pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
+}
+
+static const struct property_entry lpt_spi_properties[] = {
+	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_LPT_SSP),
+	{ }
+};
+
+static const struct lpss_device_desc lpt_spi_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR
+			| LPSS_SAVE_CTX,
+	.prv_offset = 0x800,
+	.properties = lpt_spi_properties,
+};
+
+static const struct lpss_device_desc lpt_i2c_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_LTR | LPSS_SAVE_CTX,
+	.prv_offset = 0x800,
+};
+
+static struct property_entry uart_properties[] = {
+	PROPERTY_ENTRY_U32("reg-io-width", 4),
+	PROPERTY_ENTRY_U32("reg-shift", 2),
+	PROPERTY_ENTRY_BOOL("snps,uart-16550-compatible"),
+	{ },
+};
+
+static const struct lpss_device_desc lpt_uart_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR
+			| LPSS_SAVE_CTX,
+	.clk_con_id = "baudclk",
+	.prv_offset = 0x800,
+	.setup = lpss_uart_setup,
+	.properties = uart_properties,
+};
+
+static const struct lpss_device_desc lpt_sdio_dev_desc = {
+	.flags = LPSS_LTR,
+	.prv_offset = 0x1000,
+	.prv_size_override = 0x1018,
+};
+
+static const struct lpss_device_desc byt_pwm_dev_desc = {
+	.flags = LPSS_SAVE_CTX,
+	.prv_offset = 0x800,
+	.setup = byt_pwm_setup,
+};
+
+static const struct lpss_device_desc bsw_pwm_dev_desc = {
+	.flags = LPSS_SAVE_CTX_ONCE | LPSS_NO_D3_DELAY,
+	.prv_offset = 0x800,
+	.setup = bsw_pwm_setup,
+	.resume_from_noirq = true,
+};
+
+static const struct lpss_device_desc bsw_pwm2_dev_desc = {
+	.flags = LPSS_SAVE_CTX_ONCE | LPSS_NO_D3_DELAY,
+	.prv_offset = 0x800,
+	.resume_from_noirq = true,
+};
+
+static const struct lpss_device_desc byt_uart_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.clk_con_id = "baudclk",
+	.prv_offset = 0x800,
+	.setup = lpss_uart_setup,
+	.properties = uart_properties,
+};
+
+static const struct lpss_device_desc bsw_uart_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
+			| LPSS_NO_D3_DELAY,
+	.clk_con_id = "baudclk",
+	.prv_offset = 0x800,
+	.setup = lpss_uart_setup,
+	.properties = uart_properties,
+};
+
+static const struct property_entry byt_spi_properties[] = {
+	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BYT_SSP),
+	{ }
+};
+
+static const struct lpss_device_desc byt_spi_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.prv_offset = 0x400,
+	.properties = byt_spi_properties,
+};
+
+static const struct lpss_device_desc byt_sdio_dev_desc = {
+	.flags = LPSS_CLK,
+};
+
+static const struct lpss_device_desc byt_i2c_dev_desc = {
+	.flags = LPSS_CLK | LPSS_SAVE_CTX,
+	.prv_offset = 0x800,
+	.setup = byt_i2c_setup,
+	.resume_from_noirq = true,
+};
+
+static const struct lpss_device_desc bsw_i2c_dev_desc = {
+	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_NO_D3_DELAY,
+	.prv_offset = 0x800,
+	.setup = byt_i2c_setup,
+	.resume_from_noirq = true,
+};
+
+static const struct property_entry bsw_spi_properties[] = {
+	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BSW_SSP),
+	PROPERTY_ENTRY_U32("num-cs", 2),
+	{ }
+};
+
+static const struct lpss_device_desc bsw_spi_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
+			| LPSS_NO_D3_DELAY,
+	.prv_offset = 0x400,
+	.setup = lpss_deassert_reset,
+	.properties = bsw_spi_properties,
+};
+
+static const struct x86_cpu_id lpss_cpu_ids[] = {
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	NULL),
+	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	NULL),
+	{}
+};
+
+#else
+
+#define LPSS_ADDR(desc) (0UL)
+
+#endif /* CONFIG_X86_INTEL_LPSS */
+
+static const struct acpi_device_id acpi_lpss_device_ids[] = {
+	/* Generic LPSS devices */
+	{ "INTL9C60", LPSS_ADDR(lpss_dma_desc) },
+
+	/* Lynxpoint LPSS devices */
+	{ "INT33C0", LPSS_ADDR(lpt_spi_dev_desc) },
+	{ "INT33C1", LPSS_ADDR(lpt_spi_dev_desc) },
+	{ "INT33C2", LPSS_ADDR(lpt_i2c_dev_desc) },
+	{ "INT33C3", LPSS_ADDR(lpt_i2c_dev_desc) },
+	{ "INT33C4", LPSS_ADDR(lpt_uart_dev_desc) },
+	{ "INT33C5", LPSS_ADDR(lpt_uart_dev_desc) },
+	{ "INT33C6", LPSS_ADDR(lpt_sdio_dev_desc) },
+
+	/* BayTrail LPSS devices */
+	{ "80860F09", LPSS_ADDR(byt_pwm_dev_desc) },
+	{ "80860F0A", LPSS_ADDR(byt_uart_dev_desc) },
+	{ "80860F0E", LPSS_ADDR(byt_spi_dev_desc) },
+	{ "80860F14", LPSS_ADDR(byt_sdio_dev_desc) },
+	{ "80860F41", LPSS_ADDR(byt_i2c_dev_desc) },
+
+	/* Braswell LPSS devices */
+	{ "80862286", LPSS_ADDR(lpss_dma_desc) },
+	{ "80862288", LPSS_ADDR(bsw_pwm_dev_desc) },
+	{ "80862289", LPSS_ADDR(bsw_pwm2_dev_desc) },
+	{ "8086228A", LPSS_ADDR(bsw_uart_dev_desc) },
+	{ "8086228E", LPSS_ADDR(bsw_spi_dev_desc) },
+	{ "808622C0", LPSS_ADDR(lpss_dma_desc) },
+	{ "808622C1", LPSS_ADDR(bsw_i2c_dev_desc) },
+
+	/* Broadwell LPSS devices */
+	{ "INT3430", LPSS_ADDR(lpt_spi_dev_desc) },
+	{ "INT3431", LPSS_ADDR(lpt_spi_dev_desc) },
+	{ "INT3432", LPSS_ADDR(lpt_i2c_dev_desc) },
+	{ "INT3433", LPSS_ADDR(lpt_i2c_dev_desc) },
+	{ "INT3434", LPSS_ADDR(lpt_uart_dev_desc) },
+	{ "INT3435", LPSS_ADDR(lpt_uart_dev_desc) },
+	{ "INT3436", LPSS_ADDR(lpt_sdio_dev_desc) },
+
+	{ }
+};
+
+#ifdef CONFIG_X86_INTEL_LPSS
+
+/* LPSS main clock device. */
+static struct platform_device *lpss_clk_dev;
+
+static inline void lpt_register_clock_device(void)
+{
+	lpss_clk_dev = platform_device_register_simple("clk-lpss-atom",
+						       PLATFORM_DEVID_NONE,
+						       NULL, 0);
+}
+
+static int register_device_clock(struct acpi_device *adev,
+				 struct lpss_private_data *pdata)
+{
+	const struct lpss_device_desc *dev_desc = pdata->dev_desc;
+	const char *devname = dev_name(&adev->dev);
+	struct clk *clk;
+	struct lpss_clk_data *clk_data;
+	const char *parent, *clk_name;
+	void __iomem *prv_base;
+
+	if (!lpss_clk_dev)
+		lpt_register_clock_device();
+
+	if (IS_ERR(lpss_clk_dev))
+		return PTR_ERR(lpss_clk_dev);
+
+	clk_data = platform_get_drvdata(lpss_clk_dev);
+	if (!clk_data)
+		return -ENODEV;
+	clk = clk_data->clk;
+
+	if (!pdata->mmio_base
+	    || pdata->mmio_size < dev_desc->prv_offset + LPSS_CLK_SIZE)
+		return -ENODATA;
+
+	parent = clk_data->name;
+	prv_base = pdata->mmio_base + dev_desc->prv_offset;
+
+	if (pdata->fixed_clk_rate) {
+		clk = clk_register_fixed_rate(NULL, devname, parent, 0,
+					      pdata->fixed_clk_rate);
+		goto out;
+	}
+
+	if (dev_desc->flags & LPSS_CLK_GATE) {
+		clk = clk_register_gate(NULL, devname, parent, 0,
+					prv_base, 0, 0, NULL);
+		parent = devname;
+	}
+
+	if (dev_desc->flags & LPSS_CLK_DIVIDER) {
+		/* Prevent division by zero */
+		if (!readl(prv_base))
+			writel(LPSS_CLK_DIVIDER_DEF_MASK, prv_base);
+
+		clk_name = kasprintf(GFP_KERNEL, "%s-div", devname);
+		if (!clk_name)
+			return -ENOMEM;
+		clk = clk_register_fractional_divider(NULL, clk_name, parent,
+						      0, prv_base, 1, 15, 16, 15,
+						      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
+						      NULL);
+		parent = clk_name;
+
+		clk_name = kasprintf(GFP_KERNEL, "%s-update", devname);
+		if (!clk_name) {
+			kfree(parent);
+			return -ENOMEM;
+		}
+		clk = clk_register_gate(NULL, clk_name, parent,
+					CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
+					prv_base, 31, 0, NULL);
+		kfree(parent);
+		kfree(clk_name);
+	}
+out:
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	pdata->clk = clk;
+	clk_register_clkdev(clk, dev_desc->clk_con_id, devname);
+	return 0;
+}
+
+struct lpss_device_links {
+	const char *supplier_hid;
+	const char *supplier_uid;
+	const char *consumer_hid;
+	const char *consumer_uid;
+	u32 flags;
+	const struct dmi_system_id *dep_missing_ids;
+};
+
+/* Please keep this list sorted alphabetically by vendor and model */
+static const struct dmi_system_id i2c1_dep_missing_dmi_ids[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+		},
+	},
+	{}
+};
+
+/*
+ * The _DEP method is used to identify dependencies but instead of creating
+ * device links for every handle in _DEP, only links in the following list are
+ * created. That is necessary because, in the general case, _DEP can refer to
+ * devices that might not have drivers, or that are on different buses, or where
+ * the supplier is not enumerated until after the consumer is probed.
+ */
+static const struct lpss_device_links lpss_device_links[] = {
+	/* CHT External sdcard slot controller depends on PMIC I2C ctrl */
+	{"808622C1", "7", "80860F14", "3", DL_FLAG_PM_RUNTIME},
+	/* CHT iGPU depends on PMIC I2C controller */
+	{"808622C1", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
+	/* BYT iGPU depends on the Embedded Controller I2C controller (UID 1) */
+	{"80860F41", "1", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME,
+	 i2c1_dep_missing_dmi_ids},
+	/* BYT CR iGPU depends on PMIC I2C controller (UID 5 on CR) */
+	{"80860F41", "5", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
+	/* BYT iGPU depends on PMIC I2C controller (UID 7 on non CR) */
+	{"80860F41", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
+};
+
+static bool acpi_lpss_is_supplier(struct acpi_device *adev,
+				  const struct lpss_device_links *link)
+{
+	return acpi_dev_hid_uid_match(adev, link->supplier_hid, link->supplier_uid);
+}
+
+static bool acpi_lpss_is_consumer(struct acpi_device *adev,
+				  const struct lpss_device_links *link)
+{
+	return acpi_dev_hid_uid_match(adev, link->consumer_hid, link->consumer_uid);
+}
+
+struct hid_uid {
+	const char *hid;
+	const char *uid;
+};
+
+static int match_hid_uid(struct device *dev, const void *data)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	const struct hid_uid *id = data;
+
+	if (!adev)
+		return 0;
+
+	return acpi_dev_hid_uid_match(adev, id->hid, id->uid);
+}
+
+static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
+{
+	struct device *dev;
+
+	struct hid_uid data = {
+		.hid = hid,
+		.uid = uid,
+	};
+
+	dev = bus_find_device(&platform_bus_type, NULL, &data, match_hid_uid);
+	if (dev)
+		return dev;
+
+	return bus_find_device(&pci_bus_type, NULL, &data, match_hid_uid);
+}
+
+static void acpi_lpss_link_consumer(struct device *dev1,
+				    const struct lpss_device_links *link)
+{
+	struct device *dev2;
+
+	dev2 = acpi_lpss_find_device(link->consumer_hid, link->consumer_uid);
+	if (!dev2)
+		return;
+
+	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
+	    || acpi_device_dep(ACPI_HANDLE(dev2), ACPI_HANDLE(dev1)))
+		device_link_add(dev2, dev1, link->flags);
+
+	put_device(dev2);
+}
+
+static void acpi_lpss_link_supplier(struct device *dev1,
+				    const struct lpss_device_links *link)
+{
+	struct device *dev2;
+
+	dev2 = acpi_lpss_find_device(link->supplier_hid, link->supplier_uid);
+	if (!dev2)
+		return;
+
+	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
+	    || acpi_device_dep(ACPI_HANDLE(dev1), ACPI_HANDLE(dev2)))
+		device_link_add(dev1, dev2, link->flags);
+
+	put_device(dev2);
+}
+
+static void acpi_lpss_create_device_links(struct acpi_device *adev,
+					  struct platform_device *pdev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lpss_device_links); i++) {
+		const struct lpss_device_links *link = &lpss_device_links[i];
+
+		if (acpi_lpss_is_supplier(adev, link))
+			acpi_lpss_link_consumer(&pdev->dev, link);
+
+		if (acpi_lpss_is_consumer(adev, link))
+			acpi_lpss_link_supplier(&pdev->dev, link);
+	}
+}
+
+static int acpi_lpss_create_device(struct acpi_device *adev,
+				   const struct acpi_device_id *id)
+{
+	const struct lpss_device_desc *dev_desc;
+	struct lpss_private_data *pdata;
+	struct resource_entry *rentry;
+	struct list_head resource_list;
+	struct platform_device *pdev;
+	int ret;
+
+	dev_desc = (const struct lpss_device_desc *)id->driver_data;
+	if (!dev_desc)
+		return -EINVAL;
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
+	if (ret < 0)
+		goto err_out;
+
+	rentry = list_first_entry_or_null(&resource_list, struct resource_entry, node);
+	if (rentry) {
+		if (dev_desc->prv_size_override)
+			pdata->mmio_size = dev_desc->prv_size_override;
+		else
+			pdata->mmio_size = resource_size(rentry->res);
+		pdata->mmio_base = ioremap(rentry->res->start, pdata->mmio_size);
+	}
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	if (!pdata->mmio_base) {
+		/* Avoid acpi_bus_attach() instantiating a pdev for this dev. */
+		adev->pnp.type.platform_id = 0;
+		goto out_free;
+	}
+
+	pdata->adev = adev;
+	pdata->dev_desc = dev_desc;
+
+	if (dev_desc->setup)
+		dev_desc->setup(pdata);
+
+	if (dev_desc->flags & LPSS_CLK) {
+		ret = register_device_clock(adev, pdata);
+		if (ret)
+			goto out_free;
+	}
+
+	/*
+	 * This works around a known issue in ACPI tables where LPSS devices
+	 * have _PS0 and _PS3 without _PSC (and no power resources), so
+	 * acpi_bus_init_power() will assume that the BIOS has put them into D0.
+	 */
+	acpi_device_fix_up_power(adev);
+
+	adev->driver_data = pdata;
+	pdev = acpi_create_platform_device(adev, dev_desc->properties);
+	if (IS_ERR_OR_NULL(pdev)) {
+		adev->driver_data = NULL;
+		ret = PTR_ERR(pdev);
+		goto err_out;
+	}
+
+	acpi_lpss_create_device_links(adev, pdev);
+	return 1;
+
+out_free:
+	/* Skip the device, but continue the namespace scan */
+	ret = 0;
+err_out:
+	kfree(pdata);
+	return ret;
+}
+
+static u32 __lpss_reg_read(struct lpss_private_data *pdata, unsigned int reg)
+{
+	return readl(pdata->mmio_base + pdata->dev_desc->prv_offset + reg);
+}
+
+static void __lpss_reg_write(u32 val, struct lpss_private_data *pdata,
+			     unsigned int reg)
+{
+	writel(val, pdata->mmio_base + pdata->dev_desc->prv_offset + reg);
+}
+
+static int lpss_reg_read(struct device *dev, unsigned int reg, u32 *val)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct lpss_private_data *pdata;
+	unsigned long flags;
+	int ret;
+
+	if (WARN_ON(!adev))
+		return -ENODEV;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (pm_runtime_suspended(dev)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+	pdata = acpi_driver_data(adev);
+	if (WARN_ON(!pdata || !pdata->mmio_base)) {
+		ret = -ENODEV;
+		goto out;
+	}
+	*val = __lpss_reg_read(pdata, reg);
+	ret = 0;
+
+ out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return ret;
+}
+
+static ssize_t lpss_ltr_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	u32 ltr_value = 0;
+	unsigned int reg;
+	int ret;
+
+	reg = strcmp(attr->attr.name, "auto_ltr") ? LPSS_SW_LTR : LPSS_AUTO_LTR;
+	ret = lpss_reg_read(dev, reg, &ltr_value);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%08x\n", ltr_value);
+}
+
+static ssize_t lpss_ltr_mode_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	u32 ltr_mode = 0;
+	char *outstr;
+	int ret;
+
+	ret = lpss_reg_read(dev, LPSS_GENERAL, &ltr_mode);
+	if (ret)
+		return ret;
+
+	outstr = (ltr_mode & LPSS_GENERAL_LTR_MODE_SW) ? "sw" : "auto";
+	return sprintf(buf, "%s\n", outstr);
+}
+
+static DEVICE_ATTR(auto_ltr, S_IRUSR, lpss_ltr_show, NULL);
+static DEVICE_ATTR(sw_ltr, S_IRUSR, lpss_ltr_show, NULL);
+static DEVICE_ATTR(ltr_mode, S_IRUSR, lpss_ltr_mode_show, NULL);
+
+static struct attribute *lpss_attrs[] = {
+	&dev_attr_auto_ltr.attr,
+	&dev_attr_sw_ltr.attr,
+	&dev_attr_ltr_mode.attr,
+	NULL,
+};
+
+static const struct attribute_group lpss_attr_group = {
+	.attrs = lpss_attrs,
+	.name = "lpss_ltr",
+};
+
+static void acpi_lpss_set_ltr(struct device *dev, s32 val)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	u32 ltr_mode, ltr_val;
+
+	ltr_mode = __lpss_reg_read(pdata, LPSS_GENERAL);
+	if (val < 0) {
+		if (ltr_mode & LPSS_GENERAL_LTR_MODE_SW) {
+			ltr_mode &= ~LPSS_GENERAL_LTR_MODE_SW;
+			__lpss_reg_write(ltr_mode, pdata, LPSS_GENERAL);
+		}
+		return;
+	}
+	ltr_val = __lpss_reg_read(pdata, LPSS_SW_LTR) & ~LPSS_LTR_SNOOP_MASK;
+	if (val >= LPSS_LTR_SNOOP_LAT_CUTOFF) {
+		ltr_val |= LPSS_LTR_SNOOP_LAT_32US;
+		val = LPSS_LTR_MAX_VAL;
+	} else if (val > LPSS_LTR_MAX_VAL) {
+		ltr_val |= LPSS_LTR_SNOOP_LAT_32US | LPSS_LTR_SNOOP_REQ;
+		val >>= LPSS_LTR_SNOOP_LAT_SHIFT;
+	} else {
+		ltr_val |= LPSS_LTR_SNOOP_LAT_1US | LPSS_LTR_SNOOP_REQ;
+	}
+	ltr_val |= val;
+	__lpss_reg_write(ltr_val, pdata, LPSS_SW_LTR);
+	if (!(ltr_mode & LPSS_GENERAL_LTR_MODE_SW)) {
+		ltr_mode |= LPSS_GENERAL_LTR_MODE_SW;
+		__lpss_reg_write(ltr_mode, pdata, LPSS_GENERAL);
+	}
+}
+
+#ifdef CONFIG_PM
+/**
+ * acpi_lpss_save_ctx() - Save the private registers of LPSS device
+ * @dev: LPSS device
+ * @pdata: pointer to the private data of the LPSS device
+ *
+ * Most LPSS devices have private registers which may loose their context when
+ * the device is powered down. acpi_lpss_save_ctx() saves those registers into
+ * prv_reg_ctx array.
+ */
+static void acpi_lpss_save_ctx(struct device *dev,
+			       struct lpss_private_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < LPSS_PRV_REG_COUNT; i++) {
+		unsigned long offset = i * sizeof(u32);
+
+		pdata->prv_reg_ctx[i] = __lpss_reg_read(pdata, offset);
+		dev_dbg(dev, "saving 0x%08x from LPSS reg at offset 0x%02lx\n",
+			pdata->prv_reg_ctx[i], offset);
+	}
+}
+
+/**
+ * acpi_lpss_restore_ctx() - Restore the private registers of LPSS device
+ * @dev: LPSS device
+ * @pdata: pointer to the private data of the LPSS device
+ *
+ * Restores the registers that were previously stored with acpi_lpss_save_ctx().
+ */
+static void acpi_lpss_restore_ctx(struct device *dev,
+				  struct lpss_private_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < LPSS_PRV_REG_COUNT; i++) {
+		unsigned long offset = i * sizeof(u32);
+
+		__lpss_reg_write(pdata->prv_reg_ctx[i], pdata, offset);
+		dev_dbg(dev, "restoring 0x%08x to LPSS reg at offset 0x%02lx\n",
+			pdata->prv_reg_ctx[i], offset);
+	}
+}
+
+static void acpi_lpss_d3_to_d0_delay(struct lpss_private_data *pdata)
+{
+	/*
+	 * The following delay is needed or the subsequent write operations may
+	 * fail. The LPSS devices are actually PCI devices and the PCI spec
+	 * expects 10ms delay before the device can be accessed after D3 to D0
+	 * transition. However some platforms like BSW does not need this delay.
+	 */
+	unsigned int delay = 10;	/* default 10ms delay */
+
+	if (pdata->dev_desc->flags & LPSS_NO_D3_DELAY)
+		delay = 0;
+
+	msleep(delay);
+}
+
+static int acpi_lpss_activate(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	ret = acpi_dev_resume(dev);
+	if (ret)
+		return ret;
+
+	acpi_lpss_d3_to_d0_delay(pdata);
+
+	/*
+	 * This is called only on ->probe() stage where a device is either in
+	 * known state defined by BIOS or most likely powered off. Due to this
+	 * we have to deassert reset line to be sure that ->probe() will
+	 * recognize the device.
+	 */
+	if (pdata->dev_desc->flags & (LPSS_SAVE_CTX | LPSS_SAVE_CTX_ONCE))
+		lpss_deassert_reset(pdata);
+
+	if (pdata->dev_desc->flags & LPSS_SAVE_CTX_ONCE)
+		acpi_lpss_save_ctx(dev, pdata);
+
+	return 0;
+}
+
+static void acpi_lpss_dismiss(struct device *dev)
+{
+	acpi_dev_suspend(dev, false);
+}
+
+/* IOSF SB for LPSS island */
+#define LPSS_IOSF_UNIT_LPIOEP		0xA0
+#define LPSS_IOSF_UNIT_LPIO1		0xAB
+#define LPSS_IOSF_UNIT_LPIO2		0xAC
+
+#define LPSS_IOSF_PMCSR			0x84
+#define LPSS_PMCSR_D0			0
+#define LPSS_PMCSR_D3hot		3
+#define LPSS_PMCSR_Dx_MASK		GENMASK(1, 0)
+
+#define LPSS_IOSF_GPIODEF0		0x154
+#define LPSS_GPIODEF0_DMA1_D3		BIT(2)
+#define LPSS_GPIODEF0_DMA2_D3		BIT(3)
+#define LPSS_GPIODEF0_DMA_D3_MASK	GENMASK(3, 2)
+#define LPSS_GPIODEF0_DMA_LLP		BIT(13)
+
+static DEFINE_MUTEX(lpss_iosf_mutex);
+static bool lpss_iosf_d3_entered = true;
+
+static void lpss_iosf_enter_d3_state(void)
+{
+	u32 value1 = 0;
+	u32 mask1 = LPSS_GPIODEF0_DMA_D3_MASK | LPSS_GPIODEF0_DMA_LLP;
+	u32 value2 = LPSS_PMCSR_D3hot;
+	u32 mask2 = LPSS_PMCSR_Dx_MASK;
+	/*
+	 * PMC provides an information about actual status of the LPSS devices.
+	 * Here we read the values related to LPSS power island, i.e. LPSS
+	 * devices, excluding both LPSS DMA controllers, along with SCC domain.
+	 */
+	u32 func_dis, d3_sts_0, pmc_status;
+	int ret;
+
+	ret = pmc_atom_read(PMC_FUNC_DIS, &func_dis);
+	if (ret)
+		return;
+
+	mutex_lock(&lpss_iosf_mutex);
+
+	ret = pmc_atom_read(PMC_D3_STS_0, &d3_sts_0);
+	if (ret)
+		goto exit;
+
+	/*
+	 * Get the status of entire LPSS power island per device basis.
+	 * Shutdown both LPSS DMA controllers if and only if all other devices
+	 * are already in D3hot.
+	 */
+	pmc_status = (~(d3_sts_0 | func_dis)) & pmc_atom_d3_mask;
+	if (pmc_status)
+		goto exit;
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
+			LPSS_IOSF_PMCSR, value2, mask2);
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO2, MBI_CFG_WRITE,
+			LPSS_IOSF_PMCSR, value2, mask2);
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
+			LPSS_IOSF_GPIODEF0, value1, mask1);
+
+	lpss_iosf_d3_entered = true;
+
+exit:
+	mutex_unlock(&lpss_iosf_mutex);
+}
+
+static void lpss_iosf_exit_d3_state(void)
+{
+	u32 value1 = LPSS_GPIODEF0_DMA1_D3 | LPSS_GPIODEF0_DMA2_D3 |
+		     LPSS_GPIODEF0_DMA_LLP;
+	u32 mask1 = LPSS_GPIODEF0_DMA_D3_MASK | LPSS_GPIODEF0_DMA_LLP;
+	u32 value2 = LPSS_PMCSR_D0;
+	u32 mask2 = LPSS_PMCSR_Dx_MASK;
+
+	mutex_lock(&lpss_iosf_mutex);
+
+	if (!lpss_iosf_d3_entered)
+		goto exit;
+
+	lpss_iosf_d3_entered = false;
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
+			LPSS_IOSF_GPIODEF0, value1, mask1);
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO2, MBI_CFG_WRITE,
+			LPSS_IOSF_PMCSR, value2, mask2);
+
+	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
+			LPSS_IOSF_PMCSR, value2, mask2);
+
+exit:
+	mutex_unlock(&lpss_iosf_mutex);
+}
+
+static int acpi_lpss_suspend(struct device *dev, bool wakeup)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
+		acpi_lpss_save_ctx(dev, pdata);
+
+	ret = acpi_dev_suspend(dev, wakeup);
+
+	/*
+	 * This call must be last in the sequence, otherwise PMC will return
+	 * wrong status for devices being about to be powered off. See
+	 * lpss_iosf_enter_d3_state() for further information.
+	 */
+	if (acpi_target_system_state() == ACPI_STATE_S0 &&
+	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+		lpss_iosf_enter_d3_state();
+
+	return ret;
+}
+
+static int acpi_lpss_resume(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	/*
+	 * This call is kept first to be in symmetry with
+	 * acpi_lpss_runtime_suspend() one.
+	 */
+	if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+		lpss_iosf_exit_d3_state();
+
+	ret = acpi_dev_resume(dev);
+	if (ret)
+		return ret;
+
+	acpi_lpss_d3_to_d0_delay(pdata);
+
+	if (pdata->dev_desc->flags & (LPSS_SAVE_CTX | LPSS_SAVE_CTX_ONCE))
+		acpi_lpss_restore_ctx(dev, pdata);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_lpss_do_suspend_late(struct device *dev)
+{
+	int ret;
+
+	if (dev_pm_skip_suspend(dev))
+		return 0;
+
+	ret = pm_generic_suspend_late(dev);
+	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
+}
+
+static int acpi_lpss_suspend_late(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	return acpi_lpss_do_suspend_late(dev);
+}
+
+static int acpi_lpss_suspend_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	if (pdata->dev_desc->resume_from_noirq) {
+		/*
+		 * The driver's ->suspend_late callback will be invoked by
+		 * acpi_lpss_do_suspend_late(), with the assumption that the
+		 * driver really wanted to run that code in ->suspend_noirq, but
+		 * it could not run after acpi_dev_suspend() and the driver
+		 * expected the latter to be called in the "late" phase.
+		 */
+		ret = acpi_lpss_do_suspend_late(dev);
+		if (ret)
+			return ret;
+	}
+
+	return acpi_subsys_suspend_noirq(dev);
+}
+
+static int acpi_lpss_do_resume_early(struct device *dev)
+{
+	int ret = acpi_lpss_resume(dev);
+
+	return ret ? ret : pm_generic_resume_early(dev);
+}
+
+static int acpi_lpss_resume_early(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	if (dev_pm_skip_resume(dev))
+		return 0;
+
+	return acpi_lpss_do_resume_early(dev);
+}
+
+static int acpi_lpss_resume_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	/* Follow acpi_subsys_resume_noirq(). */
+	if (dev_pm_skip_resume(dev))
+		return 0;
+
+	ret = pm_generic_resume_noirq(dev);
+	if (ret)
+		return ret;
+
+	if (!pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	/*
+	 * The driver's ->resume_early callback will be invoked by
+	 * acpi_lpss_do_resume_early(), with the assumption that the driver
+	 * really wanted to run that code in ->resume_noirq, but it could not
+	 * run before acpi_dev_resume() and the driver expected the latter to be
+	 * called in the "early" phase.
+	 */
+	return acpi_lpss_do_resume_early(dev);
+}
+
+static int acpi_lpss_do_restore_early(struct device *dev)
+{
+	int ret = acpi_lpss_resume(dev);
+
+	return ret ? ret : pm_generic_restore_early(dev);
+}
+
+static int acpi_lpss_restore_early(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	return acpi_lpss_do_restore_early(dev);
+}
+
+static int acpi_lpss_restore_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	ret = pm_generic_restore_noirq(dev);
+	if (ret)
+		return ret;
+
+	if (!pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	/* This is analogous to what happens in acpi_lpss_resume_noirq(). */
+	return acpi_lpss_do_restore_early(dev);
+}
+
+static int acpi_lpss_do_poweroff_late(struct device *dev)
+{
+	int ret = pm_generic_poweroff_late(dev);
+
+	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
+}
+
+static int acpi_lpss_poweroff_late(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (dev_pm_skip_suspend(dev))
+		return 0;
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	return acpi_lpss_do_poweroff_late(dev);
+}
+
+static int acpi_lpss_poweroff_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (dev_pm_skip_suspend(dev))
+		return 0;
+
+	if (pdata->dev_desc->resume_from_noirq) {
+		/* This is analogous to the acpi_lpss_suspend_noirq() case. */
+		int ret = acpi_lpss_do_poweroff_late(dev);
+
+		if (ret)
+			return ret;
+	}
+
+	return pm_generic_poweroff_noirq(dev);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static int acpi_lpss_runtime_suspend(struct device *dev)
+{
+	int ret = pm_generic_runtime_suspend(dev);
+
+	return ret ? ret : acpi_lpss_suspend(dev, true);
+}
+
+static int acpi_lpss_runtime_resume(struct device *dev)
+{
+	int ret = acpi_lpss_resume(dev);
+
+	return ret ? ret : pm_generic_runtime_resume(dev);
+}
+#endif /* CONFIG_PM */
+
+static struct dev_pm_domain acpi_lpss_pm_domain = {
+#ifdef CONFIG_PM
+	.activate = acpi_lpss_activate,
+	.dismiss = acpi_lpss_dismiss,
+#endif
+	.ops = {
+#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
+		.prepare = acpi_subsys_prepare,
+		.complete = acpi_subsys_complete,
+		.suspend = acpi_subsys_suspend,
+		.suspend_late = acpi_lpss_suspend_late,
+		.suspend_noirq = acpi_lpss_suspend_noirq,
+		.resume_noirq = acpi_lpss_resume_noirq,
+		.resume_early = acpi_lpss_resume_early,
+		.freeze = acpi_subsys_freeze,
+		.poweroff = acpi_subsys_poweroff,
+		.poweroff_late = acpi_lpss_poweroff_late,
+		.poweroff_noirq = acpi_lpss_poweroff_noirq,
+		.restore_noirq = acpi_lpss_restore_noirq,
+		.restore_early = acpi_lpss_restore_early,
+#endif
+		.runtime_suspend = acpi_lpss_runtime_suspend,
+		.runtime_resume = acpi_lpss_runtime_resume,
+#endif
+	},
+};
+
+static int acpi_lpss_platform_notify(struct notifier_block *nb,
+				     unsigned long action, void *data)
+{
+	struct platform_device *pdev = to_platform_device(data);
+	struct lpss_private_data *pdata;
+	struct acpi_device *adev;
+	const struct acpi_device_id *id;
+
+	id = acpi_match_device(acpi_lpss_device_ids, &pdev->dev);
+	if (!id || !id->driver_data)
+		return 0;
+
+	adev = ACPI_COMPANION(&pdev->dev);
+	if (!adev)
+		return 0;
+
+	pdata = acpi_driver_data(adev);
+	if (!pdata)
+		return 0;
+
+	if (pdata->mmio_base &&
+	    pdata->mmio_size < pdata->dev_desc->prv_offset + LPSS_LTR_SIZE) {
+		dev_err(&pdev->dev, "MMIO size insufficient to access LTR\n");
+		return 0;
+	}
+
+	switch (action) {
+	case BUS_NOTIFY_BIND_DRIVER:
+		dev_pm_domain_set(&pdev->dev, &acpi_lpss_pm_domain);
+		break;
+	case BUS_NOTIFY_DRIVER_NOT_BOUND:
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		dev_pm_domain_set(&pdev->dev, NULL);
+		break;
+	case BUS_NOTIFY_ADD_DEVICE:
+		dev_pm_domain_set(&pdev->dev, &acpi_lpss_pm_domain);
+		if (pdata->dev_desc->flags & LPSS_LTR)
+			return sysfs_create_group(&pdev->dev.kobj,
+						  &lpss_attr_group);
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (pdata->dev_desc->flags & LPSS_LTR)
+			sysfs_remove_group(&pdev->dev.kobj, &lpss_attr_group);
+		dev_pm_domain_set(&pdev->dev, NULL);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static struct notifier_block acpi_lpss_nb = {
+	.notifier_call = acpi_lpss_platform_notify,
+};
+
+static void acpi_lpss_bind(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (!pdata || !pdata->mmio_base || !(pdata->dev_desc->flags & LPSS_LTR))
+		return;
+
+	if (pdata->mmio_size >= pdata->dev_desc->prv_offset + LPSS_LTR_SIZE)
+		dev->power.set_latency_tolerance = acpi_lpss_set_ltr;
+	else
+		dev_err(dev, "MMIO size insufficient to access LTR\n");
+}
+
+static void acpi_lpss_unbind(struct device *dev)
+{
+	dev->power.set_latency_tolerance = NULL;
+}
+
+static struct acpi_scan_handler lpss_handler = {
+	.ids = acpi_lpss_device_ids,
+	.attach = acpi_lpss_create_device,
+	.bind = acpi_lpss_bind,
+	.unbind = acpi_lpss_unbind,
+};
+
+void __init acpi_lpss_init(void)
+{
+	const struct x86_cpu_id *id;
+	int ret;
+
+	ret = lpss_atom_clk_init();
+	if (ret)
+		return;
+
+	id = x86_match_cpu(lpss_cpu_ids);
+	if (id)
+		lpss_quirks |= LPSS_QUIRK_ALWAYS_POWER_ON;
+
+	bus_register_notifier(&platform_bus_type, &acpi_lpss_nb);
+	acpi_scan_add_handler(&lpss_handler);
+}
+
+#else
+
+static struct acpi_scan_handler lpss_handler = {
+	.ids = acpi_lpss_device_ids,
+};
+
+void __init acpi_lpss_init(void)
+{
+	acpi_scan_add_handler(&lpss_handler);
+}
+
+#endif /* CONFIG_X86_INTEL_LPSS */
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index 7d64e655f1b8..dd0b40b9bbe8 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -488,7 +488,19 @@ static int lps0_device_attach(struct acpi_device *adev,
 		rev_id = 1;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid);
-		lps0_dsm_func_mask_microsoft = -EINVAL;
+		if (lps0_dsm_func_mask > 0 && lps0_dsm_func_mask_microsoft > 0) {
+			unsigned int func_mask;
+
+			/*
+			 * Log a message if the _DSM function sets for two
+			 * different UUIDs overlap.
+			 */
+			func_mask = lps0_dsm_func_mask & lps0_dsm_func_mask_microsoft;
+			if (func_mask)
+				acpi_handle_info(adev->handle,
+						 "Duplicate LPS0 _DSM functions (mask: 0x%x)\n",
+						 func_mask);
+		}
 	}
 
 	if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0)
@@ -549,19 +561,22 @@ int acpi_s2idle_prepare_late(void)
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
 
 	/* LPS0 entry */
-	if (lps0_dsm_func_mask > 0)
-		acpi_sleep_run_lps0_dsm(acpi_s2idle_vendor_amd() ?
-					ACPI_LPS0_ENTRY_AMD :
-					ACPI_LPS0_ENTRY,
+	if (lps0_dsm_func_mask > 0 && acpi_s2idle_vendor_amd())
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY_AMD,
 					lps0_dsm_func_mask, lps0_dsm_guid);
+
 	if (lps0_dsm_func_mask_microsoft > 0) {
-		/* modern standby entry */
+		/* Modern Standby entry */
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_ENTRY,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
 	}
 
+	if (lps0_dsm_func_mask > 0 && !acpi_s2idle_vendor_amd())
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY,
+					lps0_dsm_func_mask, lps0_dsm_guid);
+
 	list_for_each_entry(handler, &lps0_s2idle_devops_head, list_node) {
 		if (handler->prepare)
 			handler->prepare();
@@ -600,14 +615,14 @@ void acpi_s2idle_restore_early(void)
 					ACPI_LPS0_EXIT_AMD :
 					ACPI_LPS0_EXIT,
 					lps0_dsm_func_mask, lps0_dsm_guid);
-	if (lps0_dsm_func_mask_microsoft > 0)
+
+	if (lps0_dsm_func_mask_microsoft > 0) {
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
-
-	/* Modern standby exit */
-	if (lps0_dsm_func_mask_microsoft > 0)
+		/* Modern Standby exit */
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_EXIT,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
+	}
 
 	/* Screen on */
 	if (lps0_dsm_func_mask_microsoft > 0)
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index bc65ebfcdf76..4ee30c2897a2 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -12,6 +12,7 @@
 
 #include <linux/acpi.h>
 #include <linux/dmi.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
@@ -45,37 +46,37 @@ struct override_status_id {
 	unsigned long long status;
 };
 
-#define ENTRY(status, hid, uid, path, cpu_model, dmi...) {		\
+#define ENTRY(status, hid, uid, path, cpu_vfm, dmi...) {		\
 	{ { hid, }, {} },						\
-	{ X86_MATCH_INTEL_FAM6_MODEL(cpu_model, NULL), {} },		\
+	{ X86_MATCH_VFM(cpu_vfm, NULL), {} },				\
 	{ { .matches = dmi }, {} },					\
 	uid,								\
 	path,								\
 	status,								\
 }
 
-#define PRESENT_ENTRY_HID(hid, uid, cpu_model, dmi...) \
-	ENTRY(ACPI_STA_DEFAULT, hid, uid, NULL, cpu_model, dmi)
+#define PRESENT_ENTRY_HID(hid, uid, cpu_vfm, dmi...) \
+	ENTRY(ACPI_STA_DEFAULT, hid, uid, NULL, cpu_vfm, dmi)
 
-#define NOT_PRESENT_ENTRY_HID(hid, uid, cpu_model, dmi...) \
-	ENTRY(0, hid, uid, NULL, cpu_model, dmi)
+#define NOT_PRESENT_ENTRY_HID(hid, uid, cpu_vfm, dmi...) \
+	ENTRY(0, hid, uid, NULL, cpu_vfm, dmi)
 
-#define PRESENT_ENTRY_PATH(path, cpu_model, dmi...) \
-	ENTRY(ACPI_STA_DEFAULT, "", NULL, path, cpu_model, dmi)
+#define PRESENT_ENTRY_PATH(path, cpu_vfm, dmi...) \
+	ENTRY(ACPI_STA_DEFAULT, "", NULL, path, cpu_vfm, dmi)
 
-#define NOT_PRESENT_ENTRY_PATH(path, cpu_model, dmi...) \
-	ENTRY(0, "", NULL, path, cpu_model, dmi)
+#define NOT_PRESENT_ENTRY_PATH(path, cpu_vfm, dmi...) \
+	ENTRY(0, "", NULL, path, cpu_vfm, dmi)
 
 static const struct override_status_id override_status_ids[] = {
 	/*
 	 * Bay / Cherry Trail PWM directly poked by GPU driver in win10,
 	 * but Linux uses a separate PWM driver, harmless if not used.
 	 */
-	PRESENT_ENTRY_HID("80860F09", "1", ATOM_SILVERMONT, {}),
-	PRESENT_ENTRY_HID("80862288", "1", ATOM_AIRMONT, {}),
+	PRESENT_ENTRY_HID("80860F09", "1", INTEL_ATOM_SILVERMONT, {}),
+	PRESENT_ENTRY_HID("80862288", "1", INTEL_ATOM_AIRMONT, {}),
 
 	/* The Xiaomi Mi Pad 2 uses PWM2 for touchkeys backlight control */
-	PRESENT_ENTRY_HID("80862289", "2", ATOM_AIRMONT, {
+	PRESENT_ENTRY_HID("80862289", "2", INTEL_ATOM_AIRMONT, {
 		DMI_MATCH(DMI_SYS_VENDOR, "Xiaomi Inc"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Mipad2"),
 	      }),
@@ -84,23 +85,32 @@ static const struct override_status_id override_status_ids[] = {
 	 * The INT0002 device is necessary to clear wakeup interrupt sources
 	 * on Cherry Trail devices, without it we get nobody cared IRQ msgs.
 	 */
-	PRESENT_ENTRY_HID("INT0002", "1", ATOM_AIRMONT, {}),
+	PRESENT_ENTRY_HID("INT0002", "1", INTEL_ATOM_AIRMONT, {}),
 	/*
 	 * On the Dell Venue 11 Pro 7130 and 7139, the DSDT hides
 	 * the touchscreen ACPI device until a certain time
 	 * after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed
 	 * *and* _STA has been called at least 3 times since.
 	 */
-	PRESENT_ENTRY_HID("SYNA7500", "1", HASWELL_L, {
+	PRESENT_ENTRY_HID("SYNA7500", "1", INTEL_HASWELL_L, {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
 	      }),
-	PRESENT_ENTRY_HID("SYNA7500", "1", HASWELL_L, {
+	PRESENT_ENTRY_HID("SYNA7500", "1", INTEL_HASWELL_L, {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7139"),
 	      }),
 
 	/*
+	 * The Dell XPS 15 9550 has a SMO8110 accelerometer /
+	 * HDD freefall sensor which is wrongly marked as not present.
+	 */
+	PRESENT_ENTRY_HID("SMO8810", "1", INTEL_SKYLAKE, {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9550"),
+	      }),
+
+	/*
 	 * The GPD win BIOS dated 20170221 has disabled the accelerometer, the
 	 * drivers sometimes cause crashes under Windows and this is how the
 	 * manufacturer has solved this :|  The DMI match may not seem unique,
@@ -112,19 +122,19 @@ static const struct override_status_id override_status_ids[] = {
 	 * was copy-pasted from the GPD win, so it has a disabled KIOX000A
 	 * node which we should not enable, thus we also check the BIOS date.
 	 */
-	PRESENT_ENTRY_HID("KIOX000A", "1", ATOM_AIRMONT, {
+	PRESENT_ENTRY_HID("KIOX000A", "1", INTEL_ATOM_AIRMONT, {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
 		DMI_MATCH(DMI_BIOS_DATE, "02/21/2017")
 	      }),
-	PRESENT_ENTRY_HID("KIOX000A", "1", ATOM_AIRMONT, {
+	PRESENT_ENTRY_HID("KIOX000A", "1", INTEL_ATOM_AIRMONT, {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
 		DMI_MATCH(DMI_BIOS_DATE, "03/20/2017")
 	      }),
-	PRESENT_ENTRY_HID("KIOX000A", "1", ATOM_AIRMONT, {
+	PRESENT_ENTRY_HID("KIOX000A", "1", INTEL_ATOM_AIRMONT, {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
@@ -137,7 +147,7 @@ static const struct override_status_id override_status_ids[] = {
 	 * method sets a GPIO causing the PCI wifi card to turn off.
 	 * See above remark about uniqueness of the DMI match.
 	 */
-	NOT_PRESENT_ENTRY_PATH("\\_SB_.PCI0.SDHB.BRC1", ATOM_AIRMONT, {
+	NOT_PRESENT_ENTRY_PATH("\\_SB_.PCI0.SDHB.BRC1", INTEL_ATOM_AIRMONT, {
 		DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_EXACT_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_EXACT_MATCH(DMI_BOARD_SERIAL, "Default string"),
@@ -149,7 +159,7 @@ static const struct override_status_id override_status_ids[] = {
 	 * as both ACCL0001 and MAGN0001. As we can only ever register an
 	 * i2c client for one of them, ignore MAGN0001.
 	 */
-	NOT_PRESENT_ENTRY_HID("MAGN0001", "1", ATOM_SILVERMONT, {
+	NOT_PRESENT_ENTRY_HID("MAGN0001", "1", INTEL_ATOM_SILVERMONT, {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 		DMI_MATCH(DMI_PRODUCT_FAMILY, "YOGATablet2"),
 	      }),
@@ -197,16 +207,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s
 }
 
 /*
- * AMD systems from Renoir and Lucienne *require* that the NVME controller
+ * AMD systems from Renoir onwards *require* that the NVME controller
  * is put into D3 over a Modern Standby / suspend-to-idle cycle.
  *
  * This is "typically" accomplished using the `StorageD3Enable`
  * property in the _DSD that is checked via the `acpi_storage_d3` function
- * but this property was introduced after many of these systems launched
- * and most OEM systems don't have it in their BIOS.
+ * but some OEM systems still don't have it in their BIOS.
  *
  * The Microsoft documentation for StorageD3Enable mentioned that Windows has
- * a hardcoded allowlist for D3 support, which was used for these platforms.
+ * a hardcoded allowlist for D3 support as well as a registry key to override
+ * the BIOS, which has been used for these cases.
  *
  * This allows quirking on Linux in a similar fashion.
  *
@@ -219,19 +229,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s
  *    https://bugzilla.kernel.org/show_bug.cgi?id=216773
  *    https://bugzilla.kernel.org/show_bug.cgi?id=217003
  * 2) On at least one HP system StorageD3Enable is missing on the second NVME
-      disk in the system.
+ *    disk in the system.
+ * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only
+ *    NVME device.
  */
-static const struct x86_cpu_id storage_d3_cpu_ids[] = {
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL),  /* Picasso */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL),	/* Renoir */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL),	/* Lucienne */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL),	/* Cezanne */
-	{}
-};
-
 bool force_storage_d3(void)
 {
-	return x86_match_cpu(storage_d3_cpu_ids);
+	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+		return false;
+	return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0;
 }
 
 /*
@@ -260,9 +266,10 @@ bool force_storage_d3(void)
 #define ACPI_QUIRK_SKIP_I2C_CLIENTS				BIT(0)
 #define ACPI_QUIRK_UART1_SKIP					BIT(1)
 #define ACPI_QUIRK_UART1_TTY_UART2_SKIP				BIT(2)
-#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY			BIT(3)
-#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY			BIT(4)
-#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS			BIT(5)
+#define ACPI_QUIRK_PNP_UART1_SKIP				BIT(3)
+#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY			BIT(4)
+#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY			BIT(5)
+#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS			BIT(6)
 
 static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 	/*
@@ -289,6 +296,7 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 	/*
 	 * 2. Devices which also have the skip i2c/serdev quirks and which
 	 *    need the x86-android-tablets module to properly work.
+	 *    Sorted alphabetically.
 	 */
 #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS)
 	{
@@ -302,6 +310,19 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
+		/* Acer Iconia One 8 A1-840 (non FHD version) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "BayTrail"),
+			/* Above strings are too generic also match BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "04/01/2014"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
+					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
+	},
+	{
+		/* Asus ME176C tablet */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ME176C"),
@@ -312,23 +333,24 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
-		/* Lenovo Yoga Book X90F/L */
+		/* Asus TF103C transformer 2-in-1 */
 		.matches = {
-			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
-					ACPI_QUIRK_UART1_SKIP |
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
+		/* Lenovo Yoga Book X90F/L */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"),
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_UART1_SKIP |
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
 					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
@@ -342,17 +364,18 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_PNP_UART1_SKIP |
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
 	},
 	{
 		/* Lenovo Yoga Tab 3 Pro X90F */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
-					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
+					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
 		/* Medion Lifetab S10346 */
@@ -386,6 +409,32 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
 	},
 	{
+		/* Vexia Edu Atla 10 tablet 5V version */
+		.matches = {
+			/* Having all 3 of these not set is somewhat unique */
+			DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
+	},
+	{
+		/* Vexia Edu Atla 10 tablet 9V version */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "08/25/2014"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_UART1_SKIP |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
+					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
+	},
+	{
 		/* Whitelabel (sold as various brands) TM800A550L */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
@@ -405,6 +454,7 @@ static const struct acpi_device_id i2c_acpi_known_good_ids[] = {
 	{ "10EC5640", 0 }, /* RealTek ALC5640 audio codec */
 	{ "10EC5651", 0 }, /* RealTek ALC5651 audio codec */
 	{ "INT33F4", 0 },  /* X-Powers AXP288 PMIC */
+	{ "INT33F5", 0 },  /* TI Dollar Cove PMIC */
 	{ "INT33FD", 0 },  /* Intel Crystal Cove PMIC */
 	{ "INT34D3", 0 },  /* Intel Whiskey Cove PMIC */
 	{ "NPCE69A", 0 },  /* Asus Transformer keyboard dock */
@@ -428,27 +478,46 @@ bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev)
 }
 EXPORT_SYMBOL_GPL(acpi_quirk_skip_i2c_client_enumeration);
 
-int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip)
+static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip)
 {
 	struct acpi_device *adev = ACPI_COMPANION(controller_parent);
 	const struct dmi_system_id *dmi_id;
 	long quirks = 0;
-	u64 uid;
-	int ret;
+	u64 uid = 0;
 
-	*skip = false;
-
-	ret = acpi_dev_uid_to_integer(adev, &uid);
-	if (ret)
+	dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids);
+	if (!dmi_id)
 		return 0;
 
-	/* to not match on PNP enumerated debug UARTs */
-	if (!dev_is_platform(controller_parent))
+	quirks = (unsigned long)dmi_id->driver_data;
+
+	/* uid is left at 0 on errors and 0 is not a valid UART UID */
+	acpi_dev_uid_to_integer(adev, &uid);
+
+	/* For PCI UARTs without an UID */
+	if (!uid && dev_is_pci(controller_parent)) {
+		struct pci_dev *pdev = to_pci_dev(controller_parent);
+
+		/*
+		 * Devfn values for PCI UARTs on Bay Trail SoCs, which are
+		 * the only devices where this fallback is necessary.
+		 */
+		if (pdev->devfn == PCI_DEVFN(0x1e, 3))
+			uid = 1;
+		else if (pdev->devfn == PCI_DEVFN(0x1e, 4))
+			uid = 2;
+	}
+
+	if (!uid)
 		return 0;
 
-	dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids);
-	if (dmi_id)
-		quirks = (unsigned long)dmi_id->driver_data;
+	if (!dev_is_platform(controller_parent) && !dev_is_pci(controller_parent)) {
+		/* PNP enumerated UARTs */
+		if ((quirks & ACPI_QUIRK_PNP_UART1_SKIP) && uid == 1)
+			*skip = true;
+
+		return 0;
+	}
 
 	if ((quirks & ACPI_QUIRK_UART1_SKIP) && uid == 1)
 		*skip = true;
@@ -463,7 +532,6 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration);
 
 bool acpi_quirk_skip_gpio_event_handlers(void)
 {
@@ -478,8 +546,41 @@ bool acpi_quirk_skip_gpio_event_handlers(void)
 	return (quirks & ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS);
 }
 EXPORT_SYMBOL_GPL(acpi_quirk_skip_gpio_event_handlers);
+#else
+static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip)
+{
+	return 0;
+}
 #endif
 
+int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip)
+{
+	struct acpi_device *adev = ACPI_COMPANION(controller_parent);
+
+	*skip = false;
+
+	/*
+	 * The DELL0501 ACPI HID represents an UART (CID is set to PNP0501) with
+	 * a backlight-controller attached. There is no separate ACPI device with
+	 * an UartSerialBusV2() resource to model the backlight-controller.
+	 * Set skip to true so that the tty core creates a serdev ctrl device.
+	 * The backlight driver will manually create the serdev client device.
+	 */
+	if (adev && acpi_dev_hid_match(adev, "DELL0501")) {
+		*skip = true;
+		/*
+		 * Create a platform dev for dell-uart-backlight to bind to.
+		 * This is a static device, so no need to store the result.
+		 */
+		platform_device_register_simple("dell-uart-backlight", PLATFORM_DEVID_NONE,
+						NULL, 0);
+		return 0;
+	}
+
+	return acpi_dmi_skip_serdev_enumeration(controller_parent, skip);
+}
+EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration);
+
 /* Lists of PMIC ACPI HIDs with an (often better) native charger driver */
 static const struct {
 	const char *hid;
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index a24c152bfaac..74e34a07ef72 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -26,7 +26,7 @@
 #include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
 
-#define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
+#define to_amba_driver(d)	container_of_const(d, struct amba_driver, drv)
 
 /* called on periphid match and class 0x9 coresight device. */
 static int
@@ -138,7 +138,7 @@ static int amba_read_periphid(struct amba_device *dev)
 	void __iomem *tmp;
 	int i, ret;
 
-	ret = dev_pm_domain_attach(&dev->dev, true);
+	ret = dev_pm_domain_attach(&dev->dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret) {
 		dev_dbg(&dev->dev, "can't get PM domain: %d\n", ret);
 		goto err_out;
@@ -205,10 +205,10 @@ err_out:
 	return ret;
 }
 
-static int amba_match(struct device *dev, struct device_driver *drv)
+static int amba_match(struct device *dev, const struct device_driver *drv)
 {
 	struct amba_device *pcdev = to_amba_device(dev);
-	struct amba_driver *pcdrv = to_amba_driver(drv);
+	const struct amba_driver *pcdrv = to_amba_driver(drv);
 
 	mutex_lock(&pcdev->periphid_lock);
 	if (!pcdev->periphid) {
@@ -291,7 +291,7 @@ static int amba_probe(struct device *dev)
 		if (ret < 0)
 			break;
 
-		ret = dev_pm_domain_attach(dev, true);
+		ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 		if (ret)
 			break;
 
@@ -364,7 +364,8 @@ static int amba_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
-	if (!ret && !drv->driver_managed_dma) {
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);
@@ -435,7 +436,7 @@ static const struct dev_pm_ops amba_pm = {
  * DMA configuration for platform and AMBA bus is same. So here we reuse
  * platform's DMA config routine.
  */
-struct bus_type amba_bustype = {
+const struct bus_type amba_bustype = {
 	.name		= "amba",
 	.dev_groups	= amba_dev_groups,
 	.match		= amba_match,
@@ -449,6 +450,12 @@ struct bus_type amba_bustype = {
 };
 EXPORT_SYMBOL_GPL(amba_bustype);
 
+bool dev_is_amba(const struct device *dev)
+{
+	return dev->bus == &amba_bustype;
+}
+EXPORT_SYMBOL_GPL(dev_is_amba);
+
 static int __init amba_init(void)
 {
 	return bus_register(&amba_bustype);
@@ -488,28 +495,31 @@ static int __init amba_stub_drv_init(void)
 	 * waiting on amba_match(). So, register a stub driver to make sure
 	 * amba_match() is called even if no amba driver has been registered.
 	 */
-	return amba_driver_register(&amba_proxy_drv);
+	return __amba_driver_register(&amba_proxy_drv, NULL);
 }
 late_initcall_sync(amba_stub_drv_init);
 
 /**
- *	amba_driver_register - register an AMBA device driver
+ *	__amba_driver_register - register an AMBA device driver
  *	@drv: amba device driver structure
+ *	@owner: owning module/driver
  *
  *	Register an AMBA device driver with the Linux device model
  *	core.  If devices pre-exist, the drivers probe function will
  *	be called.
  */
-int amba_driver_register(struct amba_driver *drv)
+int __amba_driver_register(struct amba_driver *drv,
+			   struct module *owner)
 {
 	if (!drv->probe)
 		return -EINVAL;
 
+	drv->drv.owner = owner;
 	drv->drv.bus = &amba_bustype;
 
 	return driver_register(&drv->drv);
 }
-EXPORT_SYMBOL(amba_driver_register);
+EXPORT_SYMBOL(__amba_driver_register);
 
 /**
  *	amba_driver_unregister - remove an AMBA device driver
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
index 07aa8ae0a058..e2e402c9d175 100644
--- a/drivers/android/Kconfig
+++ b/drivers/android/Kconfig
@@ -4,6 +4,7 @@ menu "Android"
 config ANDROID_BINDER_IPC
 	bool "Android Binder IPC Driver"
 	depends on MMU
+	depends on NET
 	default n
 	help
 	  Binder is used in Android for both communication between processes,
@@ -13,6 +14,19 @@ config ANDROID_BINDER_IPC
 	  Android process, using Binder to identify, invoke and pass arguments
 	  between said processes.
 
+config ANDROID_BINDER_IPC_RUST
+	bool "Rust version of Android Binder IPC Driver"
+	depends on RUST && MMU && !ANDROID_BINDER_IPC
+	help
+	  This enables the Rust implementation of the Binder driver.
+
+	  Binder is used in Android for both communication between processes,
+	  and remote method invocation.
+
+	  This means one Android process can call a method/routine in another
+	  Android process, using Binder to identify, invoke and pass arguments
+	  between said processes.
+
 config ANDROID_BINDERFS
 	bool "Android Binderfs filesystem"
 	depends on ANDROID_BINDER_IPC
@@ -27,7 +41,7 @@ config ANDROID_BINDERFS
 
 config ANDROID_BINDER_DEVICES
 	string "Android Binder devices"
-	depends on ANDROID_BINDER_IPC
+	depends on ANDROID_BINDER_IPC || ANDROID_BINDER_IPC_RUST
 	default "binder,hwbinder,vndbinder"
 	help
 	  Default value for the binder.devices parameter.
@@ -37,14 +51,15 @@ config ANDROID_BINDER_DEVICES
 	  created. Each binder device has its own context manager, and is
 	  therefore logically separated from the other devices.
 
-config ANDROID_BINDER_IPC_SELFTEST
-	bool "Android Binder IPC Driver Selftest"
-	depends on ANDROID_BINDER_IPC
+config ANDROID_BINDER_ALLOC_KUNIT_TEST
+	tristate "KUnit Tests for Android Binder Alloc" if !KUNIT_ALL_TESTS
+	depends on ANDROID_BINDER_IPC && KUNIT
+	default KUNIT_ALL_TESTS
 	help
-	  This feature allows binder selftest to run.
+	  This feature builds the binder alloc KUnit tests.
 
-	  Binder selftest checks the allocation and free of binder buffers
-	  exhaustively with combinations of various buffer sizes and
-	  alignments.
+	  Each test case runs using a pared-down binder_alloc struct and
+	  test-specific freelist, which allows this KUnit module to be loaded
+	  for testing without interfering with a running system.
 
 endmenu
diff --git a/drivers/android/Makefile b/drivers/android/Makefile
index c9d3d0c99c25..e0c650d3898e 100644
--- a/drivers/android/Makefile
+++ b/drivers/android/Makefile
@@ -2,5 +2,6 @@
 ccflags-y += -I$(src)			# needed for trace events
 
 obj-$(CONFIG_ANDROID_BINDERFS)		+= binderfs.o
-obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o binder_alloc.o
-obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o
+obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o binder_alloc.o binder_netlink.o
+obj-$(CONFIG_ANDROID_BINDER_ALLOC_KUNIT_TEST)	+= tests/
+obj-$(CONFIG_ANDROID_BINDER_IPC_RUST)	+= binder/
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 92128aae2d06..8c99ceaa303b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -68,10 +68,13 @@
 #include <linux/sizes.h>
 #include <linux/ktime.h>
 
+#include <kunit/visibility.h>
+
 #include <uapi/linux/android/binder.h>
 
 #include <linux/cacheflush.h>
 
+#include "binder_netlink.h"
 #include "binder_internal.h"
 #include "binder_trace.h"
 
@@ -79,6 +82,8 @@ static HLIST_HEAD(binder_deferred_list);
 static DEFINE_MUTEX(binder_deferred_lock);
 
 static HLIST_HEAD(binder_devices);
+static DEFINE_SPINLOCK(binder_devices_lock);
+
 static HLIST_HEAD(binder_procs);
 static DEFINE_MUTEX(binder_procs_lock);
 
@@ -277,7 +282,7 @@ _binder_proc_lock(struct binder_proc *proc, int line)
 }
 
 /**
- * binder_proc_unlock() - Release spinlock for given binder_proc
+ * binder_proc_unlock() - Release outer lock for given binder_proc
  * @proc:                struct binder_proc to acquire
  *
  * Release lock acquired via binder_proc_lock()
@@ -478,6 +483,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
 {
 	WARN_ON(!list_empty(&thread->waiting_thread_node));
 	binder_enqueue_work_ilocked(work, &thread->todo);
+
+	/* (e)poll-based threads require an explicit wakeup signal when
+	 * queuing their own work; they rely on these events to consume
+	 * messages without I/O block. Without it, threads risk waiting
+	 * indefinitely without handling the work.
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+	    thread->pid == current->pid && !thread->process_todo)
+		wake_up_interruptible_sync(&thread->wait);
+
 	thread->process_todo = true;
 }
 
@@ -560,9 +575,7 @@ static bool binder_has_work(struct binder_thread *thread, bool do_proc_work)
 static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread)
 {
 	return !thread->transaction_stack &&
-		binder_worklist_empty_ilocked(&thread->todo) &&
-		(thread->looper & (BINDER_LOOPER_STATE_ENTERED |
-				   BINDER_LOOPER_STATE_REGISTERED));
+		binder_worklist_empty_ilocked(&thread->todo);
 }
 
 static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc,
@@ -1035,6 +1048,63 @@ static struct binder_ref *binder_get_ref_olocked(struct binder_proc *proc,
 	return NULL;
 }
 
+/* Find the smallest unused descriptor the "slow way" */
+static u32 slow_desc_lookup_olocked(struct binder_proc *proc, u32 offset)
+{
+	struct binder_ref *ref;
+	struct rb_node *n;
+	u32 desc;
+
+	desc = offset;
+	for (n = rb_first(&proc->refs_by_desc); n; n = rb_next(n)) {
+		ref = rb_entry(n, struct binder_ref, rb_node_desc);
+		if (ref->data.desc > desc)
+			break;
+		desc = ref->data.desc + 1;
+	}
+
+	return desc;
+}
+
+/*
+ * Find an available reference descriptor ID. The proc->outer_lock might
+ * be released in the process, in which case -EAGAIN is returned and the
+ * @desc should be considered invalid.
+ */
+static int get_ref_desc_olocked(struct binder_proc *proc,
+				struct binder_node *node,
+				u32 *desc)
+{
+	struct dbitmap *dmap = &proc->dmap;
+	unsigned int nbits, offset;
+	unsigned long *new, bit;
+
+	/* 0 is reserved for the context manager */
+	offset = (node == proc->context->binder_context_mgr_node) ? 0 : 1;
+
+	if (!dbitmap_enabled(dmap)) {
+		*desc = slow_desc_lookup_olocked(proc, offset);
+		return 0;
+	}
+
+	if (dbitmap_acquire_next_zero_bit(dmap, offset, &bit) == 0) {
+		*desc = bit;
+		return 0;
+	}
+
+	/*
+	 * The dbitmap is full and needs to grow. The proc->outer_lock
+	 * is briefly released to allocate the new bitmap safely.
+	 */
+	nbits = dbitmap_grow_nbits(dmap);
+	binder_proc_unlock(proc);
+	new = bitmap_zalloc(nbits, GFP_KERNEL);
+	binder_proc_lock(proc);
+	dbitmap_grow(dmap, new, nbits);
+
+	return -EAGAIN;
+}
+
 /**
  * binder_get_ref_for_node_olocked() - get the ref associated with given node
  * @proc:	binder_proc that owns the ref
@@ -1058,12 +1128,14 @@ static struct binder_ref *binder_get_ref_for_node_olocked(
 					struct binder_node *node,
 					struct binder_ref *new_ref)
 {
-	struct binder_context *context = proc->context;
-	struct rb_node **p = &proc->refs_by_node.rb_node;
-	struct rb_node *parent = NULL;
 	struct binder_ref *ref;
-	struct rb_node *n;
+	struct rb_node *parent;
+	struct rb_node **p;
+	u32 desc;
 
+retry:
+	p = &proc->refs_by_node.rb_node;
+	parent = NULL;
 	while (*p) {
 		parent = *p;
 		ref = rb_entry(parent, struct binder_ref, rb_node_node);
@@ -1078,6 +1150,10 @@ static struct binder_ref *binder_get_ref_for_node_olocked(
 	if (!new_ref)
 		return NULL;
 
+	/* might release the proc->outer_lock */
+	if (get_ref_desc_olocked(proc, node, &desc) == -EAGAIN)
+		goto retry;
+
 	binder_stats_created(BINDER_STAT_REF);
 	new_ref->data.debug_id = atomic_inc_return(&binder_last_id);
 	new_ref->proc = proc;
@@ -1085,14 +1161,7 @@ static struct binder_ref *binder_get_ref_for_node_olocked(
 	rb_link_node(&new_ref->rb_node_node, parent, p);
 	rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node);
 
-	new_ref->data.desc = (node == context->binder_context_mgr_node) ? 0 : 1;
-	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
-		ref = rb_entry(n, struct binder_ref, rb_node_desc);
-		if (ref->data.desc > new_ref->data.desc)
-			break;
-		new_ref->data.desc = ref->data.desc + 1;
-	}
-
+	new_ref->data.desc = desc;
 	p = &proc->refs_by_desc.rb_node;
 	while (*p) {
 		parent = *p;
@@ -1121,6 +1190,7 @@ static struct binder_ref *binder_get_ref_for_node_olocked(
 
 static void binder_cleanup_ref_olocked(struct binder_ref *ref)
 {
+	struct dbitmap *dmap = &ref->proc->dmap;
 	bool delete_node = false;
 
 	binder_debug(BINDER_DEBUG_INTERNAL_REFS,
@@ -1128,6 +1198,8 @@ static void binder_cleanup_ref_olocked(struct binder_ref *ref)
 		      ref->proc->pid, ref->data.debug_id, ref->data.desc,
 		      ref->node->debug_id);
 
+	if (dbitmap_enabled(dmap))
+		dbitmap_clear_bit(dmap, ref->data.desc);
 	rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc);
 	rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node);
 
@@ -1158,6 +1230,12 @@ static void binder_cleanup_ref_olocked(struct binder_ref *ref)
 		binder_dequeue_work(ref->proc, &ref->death->work);
 		binder_stats_deleted(BINDER_STAT_DEATH);
 	}
+
+	if (ref->freeze) {
+		binder_dequeue_work(ref->proc, &ref->freeze->work);
+		binder_stats_deleted(BINDER_STAT_FREEZE);
+	}
+
 	binder_stats_deleted(BINDER_STAT_REF);
 }
 
@@ -1285,9 +1363,29 @@ static void binder_free_ref(struct binder_ref *ref)
 	if (ref->node)
 		binder_free_node(ref->node);
 	kfree(ref->death);
+	kfree(ref->freeze);
 	kfree(ref);
 }
 
+/* shrink descriptor bitmap if needed */
+static void try_shrink_dmap(struct binder_proc *proc)
+{
+	unsigned long *new;
+	int nbits;
+
+	binder_proc_lock(proc);
+	nbits = dbitmap_shrink_nbits(&proc->dmap);
+	binder_proc_unlock(proc);
+
+	if (!nbits)
+		return;
+
+	new = bitmap_zalloc(nbits, GFP_KERNEL);
+	binder_proc_lock(proc);
+	dbitmap_shrink(&proc->dmap, new, nbits);
+	binder_proc_unlock(proc);
+}
+
 /**
  * binder_update_ref_for_handle() - inc/dec the ref for given handle
  * @proc:	proc containing the ref
@@ -1324,8 +1422,10 @@ static int binder_update_ref_for_handle(struct binder_proc *proc,
 		*rdata = ref->data;
 	binder_proc_unlock(proc);
 
-	if (delete_ref)
+	if (delete_ref) {
 		binder_free_ref(ref);
+		try_shrink_dmap(proc);
+	}
 	return ret;
 
 err_no_ref:
@@ -1458,7 +1558,7 @@ static void binder_thread_dec_tmpref(struct binder_thread *thread)
  * by threads that are being released. When done with the binder_proc,
  * this function is called to decrement the counter and free the
  * proc if appropriate (proc has been released, all threads have
- * been released and not currenly in-use to process a transaction).
+ * been released and not currently in-use to process a transaction).
  */
 static void binder_proc_dec_tmpref(struct binder_proc *proc)
 {
@@ -1488,11 +1588,10 @@ static struct binder_thread *binder_get_txn_from(
 {
 	struct binder_thread *from;
 
-	spin_lock(&t->lock);
+	guard(spinlock)(&t->lock);
 	from = t->from;
 	if (from)
 		atomic_inc(&from->tmp_ref);
-	spin_unlock(&t->lock);
 	return from;
 }
 
@@ -1698,8 +1797,10 @@ static size_t binder_get_object(struct binder_proc *proc,
 	size_t object_size = 0;
 
 	read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
-	if (offset > buffer->data_size || read_size < sizeof(*hdr))
+	if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
+	    !IS_ALIGNED(offset, sizeof(u32)))
 		return 0;
+
 	if (u) {
 		if (copy_from_user(object, u + offset, read_size))
 			return 0;
@@ -1874,7 +1975,7 @@ static bool binder_validate_fixup(struct binder_proc *proc,
  * struct binder_task_work_cb - for deferred close
  *
  * @twork:                callback_head for task work
- * @fd:                   fd to close
+ * @file:                 file to close
  *
  * Structure to pass task work to be handled after
  * returning from binder_ioctl() via task_work_add().
@@ -1921,7 +2022,7 @@ static void binder_deferred_fd_close(int fd)
 	if (!twcb)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
-	twcb->file = close_fd_get_file(fd);
+	twcb->file = file_close_fd(fd);
 	if (twcb->file) {
 		// pin it until binder_do_fd_close(); see comments there
 		get_file(twcb->file);
@@ -2077,9 +2178,8 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 			 * Convert the address to an offset relative to
 			 * the base of the transaction buffer.
 			 */
-			fda_offset =
-			    (parent->buffer - (uintptr_t)buffer->user_data) +
-			    fda->parent_offset;
+			fda_offset = parent->buffer - buffer->user_data +
+				fda->parent_offset;
 			for (fd_index = 0; fd_index < fda->num_fds;
 			     fd_index++) {
 				u32 fd;
@@ -2597,7 +2697,7 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 	 * Convert the address to an offset relative to
 	 * the base of the transaction buffer.
 	 */
-	fda_offset = (parent->buffer - (uintptr_t)t->buffer->user_data) +
+	fda_offset = parent->buffer - t->buffer->user_data +
 		fda->parent_offset;
 	sender_ufda_base = (void __user *)(uintptr_t)sender_uparent->buffer +
 				fda->parent_offset;
@@ -2672,8 +2772,9 @@ static int binder_fixup_parent(struct list_head *pf_head,
 				  proc->pid, thread->pid);
 		return -EINVAL;
 	}
-	buffer_offset = bp->parent_offset +
-			(uintptr_t)parent->buffer - (uintptr_t)b->user_data;
+
+	buffer_offset = bp->parent_offset + parent->buffer - b->user_data;
+
 	return binder_add_fixup(pf_head, buffer_offset, bp->buffer, 0);
 }
 
@@ -2893,6 +2994,69 @@ static void binder_set_txn_from_error(struct binder_transaction *t, int id,
 	binder_thread_dec_tmpref(from);
 }
 
+/**
+ * binder_netlink_report() - report a transaction failure via netlink
+ * @proc:	the binder proc sending the transaction
+ * @t:		the binder transaction that failed
+ * @data_size:	the user provided data size for the transaction
+ * @error:	enum binder_driver_return_protocol returned to sender
+ */
+static void binder_netlink_report(struct binder_proc *proc,
+				  struct binder_transaction *t,
+				  u32 data_size,
+				  u32 error)
+{
+	const char *context = proc->context->name;
+	struct sk_buff *skb;
+	void *hdr;
+
+	if (!genl_has_listeners(&binder_nl_family, &init_net,
+				BINDER_NLGRP_REPORT))
+		return;
+
+	trace_binder_netlink_report(context, t, data_size, error);
+
+	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return;
+
+	hdr = genlmsg_put(skb, 0, 0, &binder_nl_family, 0, BINDER_CMD_REPORT);
+	if (!hdr)
+		goto free_skb;
+
+	if (nla_put_u32(skb, BINDER_A_REPORT_ERROR, error) ||
+	    nla_put_string(skb, BINDER_A_REPORT_CONTEXT, context) ||
+	    nla_put_u32(skb, BINDER_A_REPORT_FROM_PID, t->from_pid) ||
+	    nla_put_u32(skb, BINDER_A_REPORT_FROM_TID, t->from_tid))
+		goto cancel_skb;
+
+	if (t->to_proc &&
+	    nla_put_u32(skb, BINDER_A_REPORT_TO_PID, t->to_proc->pid))
+		goto cancel_skb;
+
+	if (t->to_thread &&
+	    nla_put_u32(skb, BINDER_A_REPORT_TO_TID, t->to_thread->pid))
+		goto cancel_skb;
+
+	if (t->is_reply && nla_put_flag(skb, BINDER_A_REPORT_IS_REPLY))
+		goto cancel_skb;
+
+	if (nla_put_u32(skb, BINDER_A_REPORT_FLAGS, t->flags) ||
+	    nla_put_u32(skb, BINDER_A_REPORT_CODE, t->code) ||
+	    nla_put_u32(skb, BINDER_A_REPORT_DATA_SIZE, data_size))
+		goto cancel_skb;
+
+	genlmsg_end(skb, hdr);
+	genlmsg_multicast(&binder_nl_family, skb, 0, BINDER_NLGRP_REPORT,
+			  GFP_KERNEL);
+	return;
+
+cancel_skb:
+	genlmsg_cancel(skb, hdr);
+free_skb:
+	nlmsg_free(skb);
+}
+
 static void binder_transaction(struct binder_proc *proc,
 			       struct binder_thread *thread,
 			       struct binder_transaction_data *tr, int reply,
@@ -2920,8 +3084,7 @@ static void binder_transaction(struct binder_proc *proc,
 	struct binder_context *context = proc->context;
 	int t_debug_id = atomic_inc_return(&binder_last_id);
 	ktime_t t_start_time = ktime_get();
-	char *secctx = NULL;
-	u32 secctx_sz = 0;
+	struct lsm_context lsmctx = { };
 	struct list_head sgc_head;
 	struct list_head pf_head;
 	const void __user *user_buffer = (const void __user *)
@@ -2943,6 +3106,32 @@ static void binder_transaction(struct binder_proc *proc,
 	binder_set_extended_error(&thread->ee, t_debug_id, BR_OK, 0);
 	binder_inner_proc_unlock(proc);
 
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (!t) {
+		binder_txn_error("%d:%d cannot allocate transaction\n",
+				 thread->pid, proc->pid);
+		return_error = BR_FAILED_REPLY;
+		return_error_param = -ENOMEM;
+		return_error_line = __LINE__;
+		goto err_alloc_t_failed;
+	}
+	INIT_LIST_HEAD(&t->fd_fixups);
+	binder_stats_created(BINDER_STAT_TRANSACTION);
+	spin_lock_init(&t->lock);
+	t->debug_id = t_debug_id;
+	t->start_time = t_start_time;
+	t->from_pid = proc->pid;
+	t->from_tid = thread->pid;
+	t->sender_euid = task_euid(proc->tsk);
+	t->code = tr->code;
+	t->flags = tr->flags;
+	t->priority = task_nice(current);
+	t->work.type = BINDER_WORK_TRANSACTION;
+	t->is_async = !reply && (tr->flags & TF_ONE_WAY);
+	t->is_reply = reply;
+	if (!reply && !(tr->flags & TF_ONE_WAY))
+		t->from = thread;
+
 	if (reply) {
 		binder_inner_proc_lock(proc);
 		in_reply_to = thread->transaction_stack;
@@ -3046,10 +3235,8 @@ static void binder_transaction(struct binder_proc *proc,
 		}
 		if (!target_node) {
 			binder_txn_error("%d:%d cannot find target node\n",
-				thread->pid, proc->pid);
-			/*
-			 * return_error is set above
-			 */
+					 proc->pid, thread->pid);
+			/* return_error is set above */
 			return_error_param = -EINVAL;
 			return_error_line = __LINE__;
 			goto err_dead_binder;
@@ -3131,24 +3318,13 @@ static void binder_transaction(struct binder_proc *proc,
 		}
 		binder_inner_proc_unlock(proc);
 	}
+
+	t->to_proc = target_proc;
+	t->to_thread = target_thread;
 	if (target_thread)
 		e->to_thread = target_thread->pid;
 	e->to_proc = target_proc->pid;
 
-	/* TODO: reuse incoming transaction for reply */
-	t = kzalloc(sizeof(*t), GFP_KERNEL);
-	if (t == NULL) {
-		binder_txn_error("%d:%d cannot allocate transaction\n",
-			thread->pid, proc->pid);
-		return_error = BR_FAILED_REPLY;
-		return_error_param = -ENOMEM;
-		return_error_line = __LINE__;
-		goto err_alloc_t_failed;
-	}
-	INIT_LIST_HEAD(&t->fd_fixups);
-	binder_stats_created(BINDER_STAT_TRANSACTION);
-	spin_lock_init(&t->lock);
-
 	tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL);
 	if (tcomplete == NULL) {
 		binder_txn_error("%d:%d cannot allocate work for transaction\n",
@@ -3160,48 +3336,28 @@ static void binder_transaction(struct binder_proc *proc,
 	}
 	binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE);
 
-	t->debug_id = t_debug_id;
-	t->start_time = t_start_time;
-
 	if (reply)
 		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld-%lld\n",
+			     "%d:%d BC_REPLY %d -> %d:%d, data size %lld-%lld-%lld\n",
 			     proc->pid, thread->pid, t->debug_id,
 			     target_proc->pid, target_thread->pid,
-			     (u64)tr->data.ptr.buffer,
-			     (u64)tr->data.ptr.offsets,
 			     (u64)tr->data_size, (u64)tr->offsets_size,
 			     (u64)extra_buffers_size);
 	else
 		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld-%lld\n",
+			     "%d:%d BC_TRANSACTION %d -> %d - node %d, data size %lld-%lld-%lld\n",
 			     proc->pid, thread->pid, t->debug_id,
 			     target_proc->pid, target_node->debug_id,
-			     (u64)tr->data.ptr.buffer,
-			     (u64)tr->data.ptr.offsets,
 			     (u64)tr->data_size, (u64)tr->offsets_size,
 			     (u64)extra_buffers_size);
 
-	if (!reply && !(tr->flags & TF_ONE_WAY))
-		t->from = thread;
-	else
-		t->from = NULL;
-	t->from_pid = proc->pid;
-	t->from_tid = thread->pid;
-	t->sender_euid = task_euid(proc->tsk);
-	t->to_proc = target_proc;
-	t->to_thread = target_thread;
-	t->code = tr->code;
-	t->flags = tr->flags;
-	t->priority = task_nice(current);
-
 	if (target_node && target_node->txn_security_ctx) {
 		u32 secid;
 		size_t added_size;
 
 		security_cred_getsecid(proc->cred, &secid);
-		ret = security_secid_to_secctx(secid, &secctx, &secctx_sz);
-		if (ret) {
+		ret = security_secid_to_secctx(secid, &lsmctx);
+		if (ret < 0) {
 			binder_txn_error("%d:%d failed to get security context\n",
 				thread->pid, proc->pid);
 			return_error = BR_FAILED_REPLY;
@@ -3209,7 +3365,7 @@ static void binder_transaction(struct binder_proc *proc,
 			return_error_line = __LINE__;
 			goto err_get_secctx_failed;
 		}
-		added_size = ALIGN(secctx_sz, sizeof(u64));
+		added_size = ALIGN(lsmctx.len, sizeof(u64));
 		extra_buffers_size += added_size;
 		if (extra_buffers_size < added_size) {
 			binder_txn_error("%d:%d integer overflow of extra_buffers_size\n",
@@ -3225,7 +3381,7 @@ static void binder_transaction(struct binder_proc *proc,
 
 	t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size,
 		tr->offsets_size, extra_buffers_size,
-		!reply && (t->flags & TF_ONE_WAY), current->tgid);
+		!reply && (t->flags & TF_ONE_WAY));
 	if (IS_ERR(t->buffer)) {
 		char *s;
 
@@ -3243,23 +3399,23 @@ static void binder_transaction(struct binder_proc *proc,
 		t->buffer = NULL;
 		goto err_binder_alloc_buf_failed;
 	}
-	if (secctx) {
+	if (lsmctx.context) {
 		int err;
 		size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) +
 				    ALIGN(tr->offsets_size, sizeof(void *)) +
 				    ALIGN(extra_buffers_size, sizeof(void *)) -
-				    ALIGN(secctx_sz, sizeof(u64));
+				    ALIGN(lsmctx.len, sizeof(u64));
 
-		t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset;
+		t->security_ctx = t->buffer->user_data + buf_offset;
 		err = binder_alloc_copy_to_buffer(&target_proc->alloc,
 						  t->buffer, buf_offset,
-						  secctx, secctx_sz);
+						  lsmctx.context, lsmctx.len);
 		if (err) {
 			t->security_ctx = 0;
 			WARN_ON(1);
 		}
-		security_release_secctx(secctx, secctx_sz);
-		secctx = NULL;
+		security_release_secctx(&lsmctx);
+		lsmctx.context = NULL;
 	}
 	t->buffer->debug_id = t->debug_id;
 	t->buffer->transaction = t;
@@ -3303,7 +3459,7 @@ static void binder_transaction(struct binder_proc *proc,
 	off_end_offset = off_start_offset + tr->offsets_size;
 	sg_buf_offset = ALIGN(off_end_offset, sizeof(void *));
 	sg_buf_end_offset = sg_buf_offset + extra_buffers_size -
-		ALIGN(secctx_sz, sizeof(u64));
+		ALIGN(lsmctx.len, sizeof(u64));
 	off_min = 0;
 	for (buffer_offset = off_start_offset; buffer_offset < off_end_offset;
 	     buffer_offset += sizeof(binder_size_t)) {
@@ -3332,6 +3488,7 @@ static void binder_transaction(struct binder_proc *proc,
 		 */
 		copy_size = object_offset - user_offset;
 		if (copy_size && (user_offset > object_offset ||
+				object_offset > tr->data_size ||
 				binder_alloc_copy_user_to_buffer(
 					&target_proc->alloc,
 					t->buffer, user_offset,
@@ -3527,8 +3684,7 @@ static void binder_transaction(struct binder_proc *proc,
 				goto err_translate_failed;
 			}
 			/* Fixup buffer pointer to target proc address space */
-			bp->buffer = (uintptr_t)
-				t->buffer->user_data + sg_buf_offset;
+			bp->buffer = t->buffer->user_data + sg_buf_offset;
 			sg_buf_offset += ALIGN(bp->length, sizeof(u64));
 
 			num_valid = (buffer_offset - off_start_offset) /
@@ -3587,11 +3743,13 @@ static void binder_transaction(struct binder_proc *proc,
 		return_error_line = __LINE__;
 		goto err_copy_data_failed;
 	}
-	if (t->buffer->oneway_spam_suspect)
+	if (t->buffer->oneway_spam_suspect) {
 		tcomplete->type = BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT;
-	else
+		binder_netlink_report(proc, t, tr->data_size,
+				      BR_ONEWAY_SPAM_SUSPECT);
+	} else {
 		tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
-	t->work.type = BINDER_WORK_TRANSACTION;
+	}
 
 	if (reply) {
 		binder_enqueue_thread_work(thread, tcomplete);
@@ -3619,7 +3777,6 @@ static void binder_transaction(struct binder_proc *proc,
 		 * the target replies (or there is an error).
 		 */
 		binder_enqueue_deferred_thread_work_ilocked(thread, tcomplete);
-		t->need_reply = 1;
 		t->from_parent = thread->transaction_stack;
 		thread->transaction_stack = t;
 		binder_inner_proc_unlock(proc);
@@ -3640,8 +3797,11 @@ static void binder_transaction(struct binder_proc *proc,
 		 * process and is put in a pending queue, waiting for the target
 		 * process to be unfrozen.
 		 */
-		if (return_error == BR_TRANSACTION_PENDING_FROZEN)
+		if (return_error == BR_TRANSACTION_PENDING_FROZEN) {
 			tcomplete->type = BINDER_WORK_TRANSACTION_PENDING;
+			binder_netlink_report(proc, t, tr->data_size,
+					      return_error);
+		}
 		binder_enqueue_thread_work(thread, tcomplete);
 		if (return_error &&
 		    return_error != BR_TRANSACTION_PENDING_FROZEN)
@@ -3682,17 +3842,14 @@ err_copy_data_failed:
 	binder_alloc_free_buf(&target_proc->alloc, t->buffer);
 err_binder_alloc_buf_failed:
 err_bad_extra_size:
-	if (secctx)
-		security_release_secctx(secctx, secctx_sz);
+	if (lsmctx.context)
+		security_release_secctx(&lsmctx);
 err_get_secctx_failed:
 	kfree(tcomplete);
 	binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
 err_alloc_tcomplete_failed:
 	if (trace_binder_txn_latency_free_enabled())
 		binder_txn_latency_free(t);
-	kfree(t);
-	binder_stats_deleted(BINDER_STAT_TRANSACTION);
-err_alloc_t_failed:
 err_bad_todo_list:
 err_bad_call_stack:
 err_empty_call_stack:
@@ -3703,14 +3860,19 @@ err_invalid_target_handle:
 		binder_dec_node_tmpref(target_node);
 	}
 
+	binder_netlink_report(proc, t, tr->data_size, return_error);
+	kfree(t);
+	binder_stats_deleted(BINDER_STAT_TRANSACTION);
+err_alloc_t_failed:
+
 	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-		     "%d:%d transaction %s to %d:%d failed %d/%d/%d, size %lld-%lld line %d\n",
+		     "%d:%d transaction %s to %d:%d failed %d/%d/%d, code %u size %lld-%lld line %d\n",
 		     proc->pid, thread->pid, reply ? "reply" :
 		     (tr->flags & TF_ONE_WAY ? "async" : "call"),
 		     target_proc ? target_proc->pid : 0,
 		     target_thread ? target_thread->pid : 0,
 		     t_debug_id, return_error, return_error_param,
-		     (u64)tr->data_size, (u64)tr->offsets_size,
+		     tr->code, (u64)tr->data_size, (u64)tr->offsets_size,
 		     return_error_line);
 
 	if (target_thread)
@@ -3752,6 +3914,153 @@ err_invalid_target_handle:
 	}
 }
 
+static int
+binder_request_freeze_notification(struct binder_proc *proc,
+				   struct binder_thread *thread,
+				   struct binder_handle_cookie *handle_cookie)
+{
+	struct binder_ref_freeze *freeze;
+	struct binder_ref *ref;
+
+	freeze = kzalloc(sizeof(*freeze), GFP_KERNEL);
+	if (!freeze)
+		return -ENOMEM;
+	binder_proc_lock(proc);
+	ref = binder_get_ref_olocked(proc, handle_cookie->handle, false);
+	if (!ref) {
+		binder_user_error("%d:%d BC_REQUEST_FREEZE_NOTIFICATION invalid ref %d\n",
+				  proc->pid, thread->pid, handle_cookie->handle);
+		binder_proc_unlock(proc);
+		kfree(freeze);
+		return -EINVAL;
+	}
+
+	binder_node_lock(ref->node);
+	if (ref->freeze) {
+		binder_user_error("%d:%d BC_REQUEST_FREEZE_NOTIFICATION already set\n",
+				  proc->pid, thread->pid);
+		binder_node_unlock(ref->node);
+		binder_proc_unlock(proc);
+		kfree(freeze);
+		return -EINVAL;
+	}
+
+	binder_stats_created(BINDER_STAT_FREEZE);
+	INIT_LIST_HEAD(&freeze->work.entry);
+	freeze->cookie = handle_cookie->cookie;
+	freeze->work.type = BINDER_WORK_FROZEN_BINDER;
+	ref->freeze = freeze;
+
+	if (ref->node->proc) {
+		binder_inner_proc_lock(ref->node->proc);
+		freeze->is_frozen = ref->node->proc->is_frozen;
+		binder_inner_proc_unlock(ref->node->proc);
+
+		binder_inner_proc_lock(proc);
+		binder_enqueue_work_ilocked(&freeze->work, &proc->todo);
+		binder_wakeup_proc_ilocked(proc);
+		binder_inner_proc_unlock(proc);
+	}
+
+	binder_node_unlock(ref->node);
+	binder_proc_unlock(proc);
+	return 0;
+}
+
+static int
+binder_clear_freeze_notification(struct binder_proc *proc,
+				 struct binder_thread *thread,
+				 struct binder_handle_cookie *handle_cookie)
+{
+	struct binder_ref_freeze *freeze;
+	struct binder_ref *ref;
+
+	binder_proc_lock(proc);
+	ref = binder_get_ref_olocked(proc, handle_cookie->handle, false);
+	if (!ref) {
+		binder_user_error("%d:%d BC_CLEAR_FREEZE_NOTIFICATION invalid ref %d\n",
+				  proc->pid, thread->pid, handle_cookie->handle);
+		binder_proc_unlock(proc);
+		return -EINVAL;
+	}
+
+	binder_node_lock(ref->node);
+
+	if (!ref->freeze) {
+		binder_user_error("%d:%d BC_CLEAR_FREEZE_NOTIFICATION freeze notification not active\n",
+				  proc->pid, thread->pid);
+		binder_node_unlock(ref->node);
+		binder_proc_unlock(proc);
+		return -EINVAL;
+	}
+	freeze = ref->freeze;
+	binder_inner_proc_lock(proc);
+	if (freeze->cookie != handle_cookie->cookie) {
+		binder_user_error("%d:%d BC_CLEAR_FREEZE_NOTIFICATION freeze notification cookie mismatch %016llx != %016llx\n",
+				  proc->pid, thread->pid, (u64)freeze->cookie,
+				  (u64)handle_cookie->cookie);
+		binder_inner_proc_unlock(proc);
+		binder_node_unlock(ref->node);
+		binder_proc_unlock(proc);
+		return -EINVAL;
+	}
+	ref->freeze = NULL;
+	/*
+	 * Take the existing freeze object and overwrite its work type. There are three cases here:
+	 * 1. No pending notification. In this case just add the work to the queue.
+	 * 2. A notification was sent and is pending an ack from userspace. Once an ack arrives, we
+	 *    should resend with the new work type.
+	 * 3. A notification is pending to be sent. Since the work is already in the queue, nothing
+	 *    needs to be done here.
+	 */
+	freeze->work.type = BINDER_WORK_CLEAR_FREEZE_NOTIFICATION;
+	if (list_empty(&freeze->work.entry)) {
+		binder_enqueue_work_ilocked(&freeze->work, &proc->todo);
+		binder_wakeup_proc_ilocked(proc);
+	} else if (freeze->sent) {
+		freeze->resend = true;
+	}
+	binder_inner_proc_unlock(proc);
+	binder_node_unlock(ref->node);
+	binder_proc_unlock(proc);
+	return 0;
+}
+
+static int
+binder_freeze_notification_done(struct binder_proc *proc,
+				struct binder_thread *thread,
+				binder_uintptr_t cookie)
+{
+	struct binder_ref_freeze *freeze = NULL;
+	struct binder_work *w;
+
+	binder_inner_proc_lock(proc);
+	list_for_each_entry(w, &proc->delivered_freeze, entry) {
+		struct binder_ref_freeze *tmp_freeze =
+			container_of(w, struct binder_ref_freeze, work);
+
+		if (tmp_freeze->cookie == cookie) {
+			freeze = tmp_freeze;
+			break;
+		}
+	}
+	if (!freeze) {
+		binder_user_error("%d:%d BC_FREEZE_NOTIFICATION_DONE %016llx not found\n",
+				  proc->pid, thread->pid, (u64)cookie);
+		binder_inner_proc_unlock(proc);
+		return -EINVAL;
+	}
+	binder_dequeue_work_ilocked(&freeze->work);
+	freeze->sent = false;
+	if (freeze->resend) {
+		freeze->resend = false;
+		binder_enqueue_work_ilocked(&freeze->work, &proc->todo);
+		binder_wakeup_proc_ilocked(proc);
+	}
+	binder_inner_proc_unlock(proc);
+	return 0;
+}
+
 /**
  * binder_free_buf() - free the specified buffer
  * @proc:	binder proc that owns buffer
@@ -3980,20 +4289,21 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (IS_ERR_OR_NULL(buffer)) {
 				if (PTR_ERR(buffer) == -EPERM) {
 					binder_user_error(
-						"%d:%d BC_FREE_BUFFER u%016llx matched unreturned or currently freeing buffer\n",
+						"%d:%d BC_FREE_BUFFER matched unreturned or currently freeing buffer at offset %lx\n",
 						proc->pid, thread->pid,
-						(u64)data_ptr);
+						(unsigned long)data_ptr - proc->alloc.vm_start);
 				} else {
 					binder_user_error(
-						"%d:%d BC_FREE_BUFFER u%016llx no match\n",
+						"%d:%d BC_FREE_BUFFER no match for buffer at offset %lx\n",
 						proc->pid, thread->pid,
-						(u64)data_ptr);
+						(unsigned long)data_ptr - proc->alloc.vm_start);
 				}
 				break;
 			}
 			binder_debug(BINDER_DEBUG_FREE_BUFFER,
-				     "%d:%d BC_FREE_BUFFER u%016llx found buffer %d for %s transaction\n",
-				     proc->pid, thread->pid, (u64)data_ptr,
+				     "%d:%d BC_FREE_BUFFER at offset %lx found buffer %d for %s transaction\n",
+				     proc->pid, thread->pid,
+				     (unsigned long)data_ptr - proc->alloc.vm_start,
 				     buffer->debug_id,
 				     buffer->transaction ? "active" : "finished");
 			binder_free_buf(proc, thread, buffer, false);
@@ -4235,6 +4545,44 @@ static int binder_thread_write(struct binder_proc *proc,
 			binder_inner_proc_unlock(proc);
 		} break;
 
+		case BC_REQUEST_FREEZE_NOTIFICATION: {
+			struct binder_handle_cookie handle_cookie;
+			int error;
+
+			if (copy_from_user(&handle_cookie, ptr, sizeof(handle_cookie)))
+				return -EFAULT;
+			ptr += sizeof(handle_cookie);
+			error = binder_request_freeze_notification(proc, thread,
+								   &handle_cookie);
+			if (error)
+				return error;
+		} break;
+
+		case BC_CLEAR_FREEZE_NOTIFICATION: {
+			struct binder_handle_cookie handle_cookie;
+			int error;
+
+			if (copy_from_user(&handle_cookie, ptr, sizeof(handle_cookie)))
+				return -EFAULT;
+			ptr += sizeof(handle_cookie);
+			error = binder_clear_freeze_notification(proc, thread, &handle_cookie);
+			if (error)
+				return error;
+		} break;
+
+		case BC_FREEZE_NOTIFICATION_DONE: {
+			binder_uintptr_t cookie;
+			int error;
+
+			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+
+			ptr += sizeof(cookie);
+			error = binder_freeze_notification_done(proc, thread, cookie);
+			if (error)
+				return error;
+		} break;
+
 		default:
 			pr_err("%d:%d unknown command %u\n",
 			       proc->pid, thread->pid, cmd);
@@ -4624,6 +4972,46 @@ retry:
 			if (cmd == BR_DEAD_BINDER)
 				goto done; /* DEAD_BINDER notifications can cause transactions */
 		} break;
+
+		case BINDER_WORK_FROZEN_BINDER: {
+			struct binder_ref_freeze *freeze;
+			struct binder_frozen_state_info info;
+
+			memset(&info, 0, sizeof(info));
+			freeze = container_of(w, struct binder_ref_freeze, work);
+			info.is_frozen = freeze->is_frozen;
+			info.cookie = freeze->cookie;
+			freeze->sent = true;
+			binder_enqueue_work_ilocked(w, &proc->delivered_freeze);
+			binder_inner_proc_unlock(proc);
+
+			if (put_user(BR_FROZEN_BINDER, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			if (copy_to_user(ptr, &info, sizeof(info)))
+				return -EFAULT;
+			ptr += sizeof(info);
+			binder_stat_br(proc, thread, BR_FROZEN_BINDER);
+			goto done; /* BR_FROZEN_BINDER notifications can cause transactions */
+		} break;
+
+		case BINDER_WORK_CLEAR_FREEZE_NOTIFICATION: {
+			struct binder_ref_freeze *freeze =
+			    container_of(w, struct binder_ref_freeze, work);
+			binder_uintptr_t cookie = freeze->cookie;
+
+			binder_inner_proc_unlock(proc);
+			kfree(freeze);
+			binder_stats_deleted(BINDER_STAT_FREEZE);
+			if (put_user(BR_CLEAR_FREEZE_NOTIFICATION_DONE, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			if (put_user(cookie, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+			binder_stat_br(proc, thread, BR_CLEAR_FREEZE_NOTIFICATION_DONE);
+		} break;
+
 		default:
 			binder_inner_proc_unlock(proc);
 			pr_err("%d:%d: bad work type %d\n",
@@ -4698,7 +5086,7 @@ retry:
 		}
 		trd->data_size = t->buffer->data_size;
 		trd->offsets_size = t->buffer->offsets_size;
-		trd->data.ptr.buffer = (uintptr_t)t->buffer->user_data;
+		trd->data.ptr.buffer = t->buffer->user_data;
 		trd->data.ptr.offsets = trd->data.ptr.buffer +
 					ALIGN(t->buffer->data_size,
 					    sizeof(void *));
@@ -4732,16 +5120,14 @@ retry:
 		trace_binder_transaction_received(t);
 		binder_stat_br(proc, thread, cmd);
 		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d %s %d %d:%d, cmd %u size %zd-%zd ptr %016llx-%016llx\n",
+			     "%d:%d %s %d %d:%d, cmd %u size %zd-%zd\n",
 			     proc->pid, thread->pid,
 			     (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" :
 				(cmd == BR_TRANSACTION_SEC_CTX) ?
 				     "BR_TRANSACTION_SEC_CTX" : "BR_REPLY",
 			     t->debug_id, t_from ? t_from->proc->pid : 0,
 			     t_from ? t_from->pid : 0, cmd,
-			     t->buffer->data_size, t->buffer->offsets_size,
-			     (u64)trd->data.ptr.buffer,
-			     (u64)trd->data.ptr.offsets);
+			     t->buffer->data_size, t->buffer->offsets_size);
 
 		if (t_from)
 			binder_thread_dec_tmpref(t_from);
@@ -4833,6 +5219,16 @@ static void binder_release_work(struct binder_proc *proc,
 		} break;
 		case BINDER_WORK_NODE:
 			break;
+		case BINDER_WORK_CLEAR_FREEZE_NOTIFICATION: {
+			struct binder_ref_freeze *freeze;
+
+			freeze = container_of(w, struct binder_ref_freeze, work);
+			binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+				     "undelivered freeze notification, %016llx\n",
+				     (u64)freeze->cookie);
+			kfree(freeze);
+			binder_stats_deleted(BINDER_STAT_FREEZE);
+		} break;
 		default:
 			pr_err("unexpected work type, %d, not freed\n",
 			       wtype);
@@ -4913,6 +5309,7 @@ static void binder_free_proc(struct binder_proc *proc)
 			__func__, proc->outstanding_txns);
 	device = container_of(proc->context, struct binder_device, context);
 	if (refcount_dec_and_test(&device->ref)) {
+		binder_remove_device(device);
 		kfree(proc->context->name);
 		kfree(device);
 	}
@@ -4920,6 +5317,7 @@ static void binder_free_proc(struct binder_proc *proc)
 	put_task_struct(proc->tsk);
 	put_cred(proc->cred);
 	binder_stats_deleted(BINDER_STAT_PROC);
+	dbitmap_free(&proc->dmap);
 	kfree(proc);
 }
 
@@ -5030,7 +5428,7 @@ static __poll_t binder_poll(struct file *filp,
 
 	thread = binder_get_thread(proc);
 	if (!thread)
-		return POLLERR;
+		return EPOLLERR;
 
 	binder_inner_proc_lock(thread->proc);
 	thread->looper |= BINDER_LOOPER_STATE_POLL;
@@ -5054,10 +5452,9 @@ static int binder_ioctl_write_read(struct file *filp, unsigned long arg,
 	void __user *ubuf = (void __user *)arg;
 	struct binder_write_read bwr;
 
-	if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
-		ret = -EFAULT;
-		goto out;
-	}
+	if (copy_from_user(&bwr, ubuf, sizeof(bwr)))
+		return -EFAULT;
+
 	binder_debug(BINDER_DEBUG_READ_WRITE,
 		     "%d:%d write %lld at %016llx, read %lld at %016llx\n",
 		     proc->pid, thread->pid,
@@ -5072,8 +5469,6 @@ static int binder_ioctl_write_read(struct file *filp, unsigned long arg,
 		trace_binder_write_done(ret);
 		if (ret < 0) {
 			bwr.read_consumed = 0;
-			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
-				ret = -EFAULT;
 			goto out;
 		}
 	}
@@ -5087,22 +5482,17 @@ static int binder_ioctl_write_read(struct file *filp, unsigned long arg,
 		if (!binder_worklist_empty_ilocked(&proc->todo))
 			binder_wakeup_proc_ilocked(proc);
 		binder_inner_proc_unlock(proc);
-		if (ret < 0) {
-			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
-				ret = -EFAULT;
+		if (ret < 0)
 			goto out;
-		}
 	}
 	binder_debug(BINDER_DEBUG_READ_WRITE,
 		     "%d:%d wrote %lld of %lld, read return %lld of %lld\n",
 		     proc->pid, thread->pid,
 		     (u64)bwr.write_consumed, (u64)bwr.write_size,
 		     (u64)bwr.read_consumed, (u64)bwr.read_size);
-	if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
-		ret = -EFAULT;
-		goto out;
-	}
 out:
+	if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
+		ret = -EFAULT;
 	return ret;
 }
 
@@ -5115,32 +5505,28 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp,
 	struct binder_node *new_node;
 	kuid_t curr_euid = current_euid();
 
-	mutex_lock(&context->context_mgr_node_lock);
+	guard(mutex)(&context->context_mgr_node_lock);
 	if (context->binder_context_mgr_node) {
 		pr_err("BINDER_SET_CONTEXT_MGR already set\n");
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 	ret = security_binder_set_context_mgr(proc->cred);
 	if (ret < 0)
-		goto out;
+		return ret;
 	if (uid_valid(context->binder_context_mgr_uid)) {
 		if (!uid_eq(context->binder_context_mgr_uid, curr_euid)) {
 			pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
 			       from_kuid(&init_user_ns, curr_euid),
 			       from_kuid(&init_user_ns,
 					 context->binder_context_mgr_uid));
-			ret = -EPERM;
-			goto out;
+			return -EPERM;
 		}
 	} else {
 		context->binder_context_mgr_uid = curr_euid;
 	}
 	new_node = binder_new_node(proc, fbo);
-	if (!new_node) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!new_node)
+		return -ENOMEM;
 	binder_node_lock(new_node);
 	new_node->local_weak_refs++;
 	new_node->local_strong_refs++;
@@ -5149,8 +5535,6 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp,
 	context->binder_context_mgr_node = new_node;
 	binder_node_unlock(new_node);
 	binder_put_node(new_node);
-out:
-	mutex_unlock(&context->context_mgr_node_lock);
 	return ret;
 }
 
@@ -5231,6 +5615,57 @@ static bool binder_txns_pending_ilocked(struct binder_proc *proc)
 	return false;
 }
 
+static void binder_add_freeze_work(struct binder_proc *proc, bool is_frozen)
+{
+	struct binder_node *prev = NULL;
+	struct rb_node *n;
+	struct binder_ref *ref;
+
+	binder_inner_proc_lock(proc);
+	for (n = rb_first(&proc->nodes); n; n = rb_next(n)) {
+		struct binder_node *node;
+
+		node = rb_entry(n, struct binder_node, rb_node);
+		binder_inc_node_tmpref_ilocked(node);
+		binder_inner_proc_unlock(proc);
+		if (prev)
+			binder_put_node(prev);
+		binder_node_lock(node);
+		hlist_for_each_entry(ref, &node->refs, node_entry) {
+			/*
+			 * Need the node lock to synchronize
+			 * with new notification requests and the
+			 * inner lock to synchronize with queued
+			 * freeze notifications.
+			 */
+			binder_inner_proc_lock(ref->proc);
+			if (!ref->freeze) {
+				binder_inner_proc_unlock(ref->proc);
+				continue;
+			}
+			ref->freeze->work.type = BINDER_WORK_FROZEN_BINDER;
+			if (list_empty(&ref->freeze->work.entry)) {
+				ref->freeze->is_frozen = is_frozen;
+				binder_enqueue_work_ilocked(&ref->freeze->work, &ref->proc->todo);
+				binder_wakeup_proc_ilocked(ref->proc);
+			} else {
+				if (ref->freeze->sent && ref->freeze->is_frozen != is_frozen)
+					ref->freeze->resend = true;
+				ref->freeze->is_frozen = is_frozen;
+			}
+			binder_inner_proc_unlock(ref->proc);
+		}
+		prev = node;
+		binder_node_unlock(node);
+		binder_inner_proc_lock(proc);
+		if (proc->is_dead)
+			break;
+	}
+	binder_inner_proc_unlock(proc);
+	if (prev)
+		binder_put_node(prev);
+}
+
 static int binder_ioctl_freeze(struct binder_freeze_info *info,
 			       struct binder_proc *target_proc)
 {
@@ -5242,6 +5677,7 @@ static int binder_ioctl_freeze(struct binder_freeze_info *info,
 		target_proc->async_recv = false;
 		target_proc->is_frozen = false;
 		binder_inner_proc_unlock(target_proc);
+		binder_add_freeze_work(target_proc, false);
 		return 0;
 	}
 
@@ -5274,6 +5710,8 @@ static int binder_ioctl_freeze(struct binder_freeze_info *info,
 		binder_inner_proc_lock(target_proc);
 		target_proc->is_frozen = false;
 		binder_inner_proc_unlock(target_proc);
+	} else {
+		binder_add_freeze_work(target_proc, true);
 	}
 
 	return ret;
@@ -5332,11 +5770,6 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	struct binder_thread *thread;
 	void __user *ubuf = (void __user *)arg;
 
-	/*pr_info("binder_ioctl: %d:%d %x %lx\n",
-			proc->pid, current->pid, cmd, arg);*/
-
-	binder_selftest_alloc(&proc->alloc);
-
 	trace_binder_ioctl(cmd, arg);
 
 	ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
@@ -5356,7 +5789,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			goto err;
 		break;
 	case BINDER_SET_MAX_THREADS: {
-		int max_threads;
+		u32 max_threads;
 
 		if (copy_from_user(&max_threads, ubuf,
 				   sizeof(max_threads))) {
@@ -5572,10 +6005,11 @@ static void binder_vma_close(struct vm_area_struct *vma)
 	binder_alloc_vma_close(&proc->alloc);
 }
 
-static vm_fault_t binder_vm_fault(struct vm_fault *vmf)
+VISIBLE_IF_KUNIT vm_fault_t binder_vm_fault(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_vm_fault);
 
 static const struct vm_operations_struct binder_vm_ops = {
 	.open = binder_vma_open,
@@ -5623,6 +6057,8 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
 	if (proc == NULL)
 		return -ENOMEM;
+
+	dbitmap_init(&proc->dmap);
 	spin_lock_init(&proc->inner_lock);
 	spin_lock_init(&proc->outer_lock);
 	get_task_struct(current->group_leader);
@@ -5647,6 +6083,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	binder_stats_created(BINDER_STAT_PROC);
 	proc->pid = current->group_leader->pid;
 	INIT_LIST_HEAD(&proc->delivered_death);
+	INIT_LIST_HEAD(&proc->delivered_freeze);
 	INIT_LIST_HEAD(&proc->waiting_threads);
 	filp->private_data = proc;
 
@@ -5741,7 +6178,7 @@ static int binder_release(struct inode *nodp, struct file *filp)
 	debugfs_remove(proc->debugfs_entry);
 
 	if (proc->binderfs_entry) {
-		binderfs_remove_file(proc->binderfs_entry);
+		simple_recursive_removal(proc->binderfs_entry, NULL);
 		proc->binderfs_entry = NULL;
 	}
 
@@ -5893,6 +6330,7 @@ static void binder_deferred_release(struct binder_proc *proc)
 
 	binder_release_work(proc, &proc->todo);
 	binder_release_work(proc, &proc->delivered_death);
+	binder_release_work(proc, &proc->delivered_freeze);
 
 	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
 		     "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d\n",
@@ -5934,14 +6372,13 @@ static DECLARE_WORK(binder_deferred_work, binder_deferred_func);
 static void
 binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer)
 {
-	mutex_lock(&binder_deferred_lock);
+	guard(mutex)(&binder_deferred_lock);
 	proc->deferred_work |= defer;
 	if (hlist_unhashed(&proc->deferred_work_node)) {
 		hlist_add_head(&proc->deferred_work_node,
 				&binder_deferred_list);
 		schedule_work(&binder_deferred_work);
 	}
-	mutex_unlock(&binder_deferred_lock);
 }
 
 static void print_binder_transaction_ilocked(struct seq_file *m,
@@ -5956,13 +6393,13 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 	spin_lock(&t->lock);
 	to_proc = t->to_proc;
 	seq_printf(m,
-		   "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d elapsed %lldms",
+		   "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld a%d r%d elapsed %lldms",
 		   prefix, t->debug_id, t,
 		   t->from_pid,
 		   t->from_tid,
 		   to_proc ? to_proc->pid : 0,
 		   t->to_thread ? t->to_thread->pid : 0,
-		   t->code, t->flags, t->priority, t->need_reply,
+		   t->code, t->flags, t->priority, t->is_async, t->is_reply,
 		   ktime_ms_delta(current_time, t->start_time));
 	spin_unlock(&t->lock);
 
@@ -5981,16 +6418,16 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 	}
 	if (buffer->target_node)
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %pK\n",
+	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   buffer->user_data);
+		   buffer->user_data - proc->alloc.vm_start);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
-				     struct binder_proc *proc,
-				     const char *prefix,
-				     const char *transaction_prefix,
-				     struct binder_work *w)
+				      struct binder_proc *proc,
+				      const char *prefix,
+				      const char *transaction_prefix,
+				      struct binder_work *w, bool hash_ptrs)
 {
 	struct binder_node *node;
 	struct binder_transaction *t;
@@ -6013,9 +6450,15 @@ static void print_binder_work_ilocked(struct seq_file *m,
 		break;
 	case BINDER_WORK_NODE:
 		node = container_of(w, struct binder_node, work);
-		seq_printf(m, "%snode work %d: u%016llx c%016llx\n",
-			   prefix, node->debug_id,
-			   (u64)node->ptr, (u64)node->cookie);
+		if (hash_ptrs)
+			seq_printf(m, "%snode work %d: u%p c%p\n",
+				   prefix, node->debug_id,
+				   (void *)(long)node->ptr,
+				   (void *)(long)node->cookie);
+		else
+			seq_printf(m, "%snode work %d: u%016llx c%016llx\n",
+				   prefix, node->debug_id,
+				   (u64)node->ptr, (u64)node->cookie);
 		break;
 	case BINDER_WORK_DEAD_BINDER:
 		seq_printf(m, "%shas dead binder\n", prefix);
@@ -6026,6 +6469,12 @@ static void print_binder_work_ilocked(struct seq_file *m,
 	case BINDER_WORK_CLEAR_DEATH_NOTIFICATION:
 		seq_printf(m, "%shas cleared death notification\n", prefix);
 		break;
+	case BINDER_WORK_FROZEN_BINDER:
+		seq_printf(m, "%shas frozen binder\n", prefix);
+		break;
+	case BINDER_WORK_CLEAR_FREEZE_NOTIFICATION:
+		seq_printf(m, "%shas cleared freeze notification\n", prefix);
+		break;
 	default:
 		seq_printf(m, "%sunknown work: type %d\n", prefix, w->type);
 		break;
@@ -6034,7 +6483,7 @@ static void print_binder_work_ilocked(struct seq_file *m,
 
 static void print_binder_thread_ilocked(struct seq_file *m,
 					struct binder_thread *thread,
-					int print_always)
+					bool print_always, bool hash_ptrs)
 {
 	struct binder_transaction *t;
 	struct binder_work *w;
@@ -6064,25 +6513,30 @@ static void print_binder_thread_ilocked(struct seq_file *m,
 	}
 	list_for_each_entry(w, &thread->todo, entry) {
 		print_binder_work_ilocked(m, thread->proc, "    ",
-					  "    pending transaction", w);
+					  "    pending transaction",
+					  w, hash_ptrs);
 	}
 	if (!print_always && m->count == header_pos)
 		m->count = start_pos;
 }
 
 static void print_binder_node_nilocked(struct seq_file *m,
-				       struct binder_node *node)
+				       struct binder_node *node,
+				       bool hash_ptrs)
 {
 	struct binder_ref *ref;
 	struct binder_work *w;
 	int count;
 
-	count = 0;
-	hlist_for_each_entry(ref, &node->refs, node_entry)
-		count++;
+	count = hlist_count_nodes(&node->refs);
 
-	seq_printf(m, "  node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d tr %d",
-		   node->debug_id, (u64)node->ptr, (u64)node->cookie,
+	if (hash_ptrs)
+		seq_printf(m, "  node %d: u%p c%p", node->debug_id,
+			   (void *)(long)node->ptr, (void *)(long)node->cookie);
+	else
+		seq_printf(m, "  node %d: u%016llx c%016llx", node->debug_id,
+			   (u64)node->ptr, (u64)node->cookie);
+	seq_printf(m, " hs %d hw %d ls %d lw %d is %d iw %d tr %d",
 		   node->has_strong_ref, node->has_weak_ref,
 		   node->local_strong_refs, node->local_weak_refs,
 		   node->internal_strong_refs, count, node->tmp_refs);
@@ -6095,7 +6549,8 @@ static void print_binder_node_nilocked(struct seq_file *m,
 	if (node->proc) {
 		list_for_each_entry(w, &node->async_todo, entry)
 			print_binder_work_ilocked(m, node->proc, "    ",
-					  "    pending async transaction", w);
+					  "    pending async transaction",
+					  w, hash_ptrs);
 	}
 }
 
@@ -6111,8 +6566,54 @@ static void print_binder_ref_olocked(struct seq_file *m,
 	binder_node_unlock(ref->node);
 }
 
-static void print_binder_proc(struct seq_file *m,
-			      struct binder_proc *proc, int print_all)
+/**
+ * print_next_binder_node_ilocked() - Print binder_node from a locked list
+ * @m:          struct seq_file for output via seq_printf()
+ * @proc:       struct binder_proc we hold the inner_proc_lock to (if any)
+ * @node:       struct binder_node to print fields of
+ * @prev_node:	struct binder_node we hold a temporary reference to (if any)
+ * @hash_ptrs:  whether to hash @node's binder_uintptr_t fields
+ *
+ * Helper function to handle synchronization around printing a struct
+ * binder_node while iterating through @proc->nodes or the dead nodes list.
+ * Caller must hold either @proc->inner_lock (for live nodes) or
+ * binder_dead_nodes_lock. This lock will be released during the body of this
+ * function, but it will be reacquired before returning to the caller.
+ *
+ * Return:	pointer to the struct binder_node we hold a tmpref on
+ */
+static struct binder_node *
+print_next_binder_node_ilocked(struct seq_file *m, struct binder_proc *proc,
+			       struct binder_node *node,
+			       struct binder_node *prev_node, bool hash_ptrs)
+{
+	/*
+	 * Take a temporary reference on the node so that isn't freed while
+	 * we print it.
+	 */
+	binder_inc_node_tmpref_ilocked(node);
+	/*
+	 * Live nodes need to drop the inner proc lock and dead nodes need to
+	 * drop the binder_dead_nodes_lock before trying to take the node lock.
+	 */
+	if (proc)
+		binder_inner_proc_unlock(proc);
+	else
+		spin_unlock(&binder_dead_nodes_lock);
+	if (prev_node)
+		binder_put_node(prev_node);
+	binder_node_inner_lock(node);
+	print_binder_node_nilocked(m, node, hash_ptrs);
+	binder_node_inner_unlock(node);
+	if (proc)
+		binder_inner_proc_lock(proc);
+	else
+		spin_lock(&binder_dead_nodes_lock);
+	return node;
+}
+
+static void print_binder_proc(struct seq_file *m, struct binder_proc *proc,
+			      bool print_all, bool hash_ptrs)
 {
 	struct binder_work *w;
 	struct rb_node *n;
@@ -6125,31 +6626,19 @@ static void print_binder_proc(struct seq_file *m,
 	header_pos = m->count;
 
 	binder_inner_proc_lock(proc);
-	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
+	for (n = rb_first(&proc->threads); n; n = rb_next(n))
 		print_binder_thread_ilocked(m, rb_entry(n, struct binder_thread,
-						rb_node), print_all);
+						rb_node), print_all, hash_ptrs);
 
-	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) {
+	for (n = rb_first(&proc->nodes); n; n = rb_next(n)) {
 		struct binder_node *node = rb_entry(n, struct binder_node,
 						    rb_node);
 		if (!print_all && !node->has_async_transaction)
 			continue;
 
-		/*
-		 * take a temporary reference on the node so it
-		 * survives and isn't removed from the tree
-		 * while we print it.
-		 */
-		binder_inc_node_tmpref_ilocked(node);
-		/* Need to drop inner lock to take node lock */
-		binder_inner_proc_unlock(proc);
-		if (last_node)
-			binder_put_node(last_node);
-		binder_node_inner_lock(node);
-		print_binder_node_nilocked(m, node);
-		binder_node_inner_unlock(node);
-		last_node = node;
-		binder_inner_proc_lock(proc);
+		last_node = print_next_binder_node_ilocked(m, proc, node,
+							   last_node,
+							   hash_ptrs);
 	}
 	binder_inner_proc_unlock(proc);
 	if (last_node)
@@ -6157,23 +6646,26 @@ static void print_binder_proc(struct seq_file *m,
 
 	if (print_all) {
 		binder_proc_lock(proc);
-		for (n = rb_first(&proc->refs_by_desc);
-		     n != NULL;
-		     n = rb_next(n))
+		for (n = rb_first(&proc->refs_by_desc); n; n = rb_next(n))
 			print_binder_ref_olocked(m, rb_entry(n,
-							    struct binder_ref,
-							    rb_node_desc));
+							     struct binder_ref,
+							     rb_node_desc));
 		binder_proc_unlock(proc);
 	}
 	binder_alloc_print_allocated(m, &proc->alloc);
 	binder_inner_proc_lock(proc);
 	list_for_each_entry(w, &proc->todo, entry)
 		print_binder_work_ilocked(m, proc, "  ",
-					  "  pending transaction", w);
+					  "  pending transaction", w,
+					  hash_ptrs);
 	list_for_each_entry(w, &proc->delivered_death, entry) {
 		seq_puts(m, "  has delivered dead binder\n");
 		break;
 	}
+	list_for_each_entry(w, &proc->delivered_freeze, entry) {
+		seq_puts(m, "  has delivered freeze binder\n");
+		break;
+	}
 	binder_inner_proc_unlock(proc);
 	if (!print_all && m->count == header_pos)
 		m->count = start_pos;
@@ -6200,7 +6692,9 @@ static const char * const binder_return_strings[] = {
 	"BR_FAILED_REPLY",
 	"BR_FROZEN_REPLY",
 	"BR_ONEWAY_SPAM_SUSPECT",
-	"BR_TRANSACTION_PENDING_FROZEN"
+	"BR_TRANSACTION_PENDING_FROZEN",
+	"BR_FROZEN_BINDER",
+	"BR_CLEAR_FREEZE_NOTIFICATION_DONE",
 };
 
 static const char * const binder_command_strings[] = {
@@ -6223,6 +6717,9 @@ static const char * const binder_command_strings[] = {
 	"BC_DEAD_BINDER_DONE",
 	"BC_TRANSACTION_SG",
 	"BC_REPLY_SG",
+	"BC_REQUEST_FREEZE_NOTIFICATION",
+	"BC_CLEAR_FREEZE_NOTIFICATION",
+	"BC_FREEZE_NOTIFICATION_DONE",
 };
 
 static const char * const binder_objstat_strings[] = {
@@ -6232,7 +6729,8 @@ static const char * const binder_objstat_strings[] = {
 	"ref",
 	"death",
 	"transaction",
-	"transaction_complete"
+	"transaction_complete",
+	"freeze",
 };
 
 static void print_binder_stats(struct seq_file *m, const char *prefix,
@@ -6292,7 +6790,7 @@ static void print_binder_proc_stats(struct seq_file *m,
 	count = 0;
 	ready_threads = 0;
 	binder_inner_proc_lock(proc);
-	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
+	for (n = rb_first(&proc->threads); n; n = rb_next(n))
 		count++;
 
 	list_for_each_entry(thread, &proc->waiting_threads, waiting_thread_node)
@@ -6306,7 +6804,7 @@ static void print_binder_proc_stats(struct seq_file *m,
 			ready_threads,
 			free_async_space);
 	count = 0;
-	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n))
+	for (n = rb_first(&proc->nodes); n; n = rb_next(n))
 		count++;
 	binder_inner_proc_unlock(proc);
 	seq_printf(m, "  nodes: %d\n", count);
@@ -6314,7 +6812,7 @@ static void print_binder_proc_stats(struct seq_file *m,
 	strong = 0;
 	weak = 0;
 	binder_proc_lock(proc);
-	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
+	for (n = rb_first(&proc->refs_by_desc); n; n = rb_next(n)) {
 		struct binder_ref *ref = rb_entry(n, struct binder_ref,
 						  rb_node_desc);
 		count++;
@@ -6341,7 +6839,7 @@ static void print_binder_proc_stats(struct seq_file *m,
 	print_binder_stats(m, "  ", &proc->stats);
 }
 
-static int state_show(struct seq_file *m, void *unused)
+static void print_binder_state(struct seq_file *m, bool hash_ptrs)
 {
 	struct binder_proc *proc;
 	struct binder_node *node;
@@ -6352,31 +6850,40 @@ static int state_show(struct seq_file *m, void *unused)
 	spin_lock(&binder_dead_nodes_lock);
 	if (!hlist_empty(&binder_dead_nodes))
 		seq_puts(m, "dead nodes:\n");
-	hlist_for_each_entry(node, &binder_dead_nodes, dead_node) {
-		/*
-		 * take a temporary reference on the node so it
-		 * survives and isn't removed from the list
-		 * while we print it.
-		 */
-		node->tmp_refs++;
-		spin_unlock(&binder_dead_nodes_lock);
-		if (last_node)
-			binder_put_node(last_node);
-		binder_node_lock(node);
-		print_binder_node_nilocked(m, node);
-		binder_node_unlock(node);
-		last_node = node;
-		spin_lock(&binder_dead_nodes_lock);
-	}
+	hlist_for_each_entry(node, &binder_dead_nodes, dead_node)
+		last_node = print_next_binder_node_ilocked(m, NULL, node,
+							   last_node,
+							   hash_ptrs);
 	spin_unlock(&binder_dead_nodes_lock);
 	if (last_node)
 		binder_put_node(last_node);
 
 	mutex_lock(&binder_procs_lock);
 	hlist_for_each_entry(proc, &binder_procs, proc_node)
-		print_binder_proc(m, proc, 1);
+		print_binder_proc(m, proc, true, hash_ptrs);
 	mutex_unlock(&binder_procs_lock);
+}
+
+static void print_binder_transactions(struct seq_file *m, bool hash_ptrs)
+{
+	struct binder_proc *proc;
+
+	seq_puts(m, "binder transactions:\n");
+	mutex_lock(&binder_procs_lock);
+	hlist_for_each_entry(proc, &binder_procs, proc_node)
+		print_binder_proc(m, proc, false, hash_ptrs);
+	mutex_unlock(&binder_procs_lock);
+}
 
+static int state_show(struct seq_file *m, void *unused)
+{
+	print_binder_state(m, false);
+	return 0;
+}
+
+static int state_hashed_show(struct seq_file *m, void *unused)
+{
+	print_binder_state(m, true);
 	return 0;
 }
 
@@ -6398,14 +6905,13 @@ static int stats_show(struct seq_file *m, void *unused)
 
 static int transactions_show(struct seq_file *m, void *unused)
 {
-	struct binder_proc *proc;
-
-	seq_puts(m, "binder transactions:\n");
-	mutex_lock(&binder_procs_lock);
-	hlist_for_each_entry(proc, &binder_procs, proc_node)
-		print_binder_proc(m, proc, 0);
-	mutex_unlock(&binder_procs_lock);
+	print_binder_transactions(m, false);
+	return 0;
+}
 
+static int transactions_hashed_show(struct seq_file *m, void *unused)
+{
+	print_binder_transactions(m, true);
 	return 0;
 }
 
@@ -6414,14 +6920,13 @@ static int proc_show(struct seq_file *m, void *unused)
 	struct binder_proc *itr;
 	int pid = (unsigned long)m->private;
 
-	mutex_lock(&binder_procs_lock);
+	guard(mutex)(&binder_procs_lock);
 	hlist_for_each_entry(itr, &binder_procs, proc_node) {
 		if (itr->pid == pid) {
 			seq_puts(m, "binder proc state:\n");
-			print_binder_proc(m, itr, 1);
+			print_binder_proc(m, itr, true, false);
 		}
 	}
-	mutex_unlock(&binder_procs_lock);
 
 	return 0;
 }
@@ -6485,8 +6990,10 @@ const struct file_operations binder_fops = {
 };
 
 DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(state_hashed);
 DEFINE_SHOW_ATTRIBUTE(stats);
 DEFINE_SHOW_ATTRIBUTE(transactions);
+DEFINE_SHOW_ATTRIBUTE(transactions_hashed);
 DEFINE_SHOW_ATTRIBUTE(transaction_log);
 
 const struct binder_debugfs_entry binder_debugfs_entries[] = {
@@ -6497,6 +7004,12 @@ const struct binder_debugfs_entry binder_debugfs_entries[] = {
 		.data = NULL,
 	},
 	{
+		.name = "state_hashed",
+		.mode = 0444,
+		.fops = &state_hashed_fops,
+		.data = NULL,
+	},
+	{
 		.name = "stats",
 		.mode = 0444,
 		.fops = &stats_fops,
@@ -6509,6 +7022,12 @@ const struct binder_debugfs_entry binder_debugfs_entries[] = {
 		.data = NULL,
 	},
 	{
+		.name = "transactions_hashed",
+		.mode = 0444,
+		.fops = &transactions_hashed_fops,
+		.data = NULL,
+	},
+	{
 		.name = "transaction_log",
 		.mode = 0444,
 		.fops = &transaction_log_fops,
@@ -6523,6 +7042,18 @@ const struct binder_debugfs_entry binder_debugfs_entries[] = {
 	{} /* terminator */
 };
 
+void binder_add_device(struct binder_device *device)
+{
+	guard(spinlock)(&binder_devices_lock);
+	hlist_add_head(&device->hlist, &binder_devices);
+}
+
+void binder_remove_device(struct binder_device *device)
+{
+	guard(spinlock)(&binder_devices_lock);
+	hlist_del_init(&device->hlist);
+}
+
 static int __init init_binder_device(const char *name)
 {
 	int ret;
@@ -6547,7 +7078,7 @@ static int __init init_binder_device(const char *name)
 		return ret;
 	}
 
-	hlist_add_head(&binder_device->hlist, &binder_devices);
+	binder_add_device(binder_device);
 
 	return ret;
 }
@@ -6600,16 +7131,23 @@ static int __init binder_init(void)
 		}
 	}
 
-	ret = init_binderfs();
+	ret = genl_register_family(&binder_nl_family);
 	if (ret)
 		goto err_init_binder_device_failed;
 
+	ret = init_binderfs();
+	if (ret)
+		goto err_init_binderfs_failed;
+
 	return ret;
 
+err_init_binderfs_failed:
+	genl_unregister_family(&binder_nl_family);
+
 err_init_binder_device_failed:
 	hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) {
 		misc_deregister(&device->miscdev);
-		hlist_del(&device->hlist);
+		binder_remove_device(device);
 		kfree(device);
 	}
 
@@ -6626,5 +7164,3 @@ device_initcall(binder_init);
 
 #define CREATE_TRACE_POINTS
 #include "binder_trace.h"
-
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/android/binder/Makefile b/drivers/android/binder/Makefile
new file mode 100644
index 000000000000..09eabb527fa0
--- /dev/null
+++ b/drivers/android/binder/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+ccflags-y += -I$(src)	# needed for trace events
+
+obj-$(CONFIG_ANDROID_BINDER_IPC_RUST) += rust_binder.o
+rust_binder-y := \
+	rust_binder_main.o	\
+	rust_binderfs.o		\
+	rust_binder_events.o	\
+	page_range_helper.o
diff --git a/drivers/android/binder/allocation.rs b/drivers/android/binder/allocation.rs
new file mode 100644
index 000000000000..7f65a9c3a0e5
--- /dev/null
+++ b/drivers/android/binder/allocation.rs
@@ -0,0 +1,602 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use core::mem::{size_of, size_of_val, MaybeUninit};
+use core::ops::Range;
+
+use kernel::{
+    bindings,
+    fs::file::{File, FileDescriptorReservation},
+    prelude::*,
+    sync::{aref::ARef, Arc},
+    transmute::{AsBytes, FromBytes},
+    uaccess::UserSliceReader,
+    uapi,
+};
+
+use crate::{
+    deferred_close::DeferredFdCloser,
+    defs::*,
+    node::{Node, NodeRef},
+    process::Process,
+    DArc,
+};
+
+#[derive(Default)]
+pub(crate) struct AllocationInfo {
+    /// Range within the allocation where we can find the offsets to the object descriptors.
+    pub(crate) offsets: Option<Range<usize>>,
+    /// The target node of the transaction this allocation is associated to.
+    /// Not set for replies.
+    pub(crate) target_node: Option<NodeRef>,
+    /// When this allocation is dropped, call `pending_oneway_finished` on the node.
+    ///
+    /// This is used to serialize oneway transaction on the same node. Binder guarantees that
+    /// oneway transactions to the same node are delivered sequentially in the order they are sent.
+    pub(crate) oneway_node: Option<DArc<Node>>,
+    /// Zero the data in the buffer on free.
+    pub(crate) clear_on_free: bool,
+    /// List of files embedded in this transaction.
+    file_list: FileList,
+}
+
+/// Represents an allocation that the kernel is currently using.
+///
+/// When allocations are idle, the range allocator holds the data related to them.
+///
+/// # Invariants
+///
+/// This allocation corresponds to an allocation in the range allocator, so the relevant pages are
+/// marked in use in the page range.
+pub(crate) struct Allocation {
+    pub(crate) offset: usize,
+    size: usize,
+    pub(crate) ptr: usize,
+    pub(crate) process: Arc<Process>,
+    allocation_info: Option<AllocationInfo>,
+    free_on_drop: bool,
+    pub(crate) oneway_spam_detected: bool,
+    #[allow(dead_code)]
+    pub(crate) debug_id: usize,
+}
+
+impl Allocation {
+    pub(crate) fn new(
+        process: Arc<Process>,
+        debug_id: usize,
+        offset: usize,
+        size: usize,
+        ptr: usize,
+        oneway_spam_detected: bool,
+    ) -> Self {
+        Self {
+            process,
+            offset,
+            size,
+            ptr,
+            debug_id,
+            oneway_spam_detected,
+            allocation_info: None,
+            free_on_drop: true,
+        }
+    }
+
+    fn size_check(&self, offset: usize, size: usize) -> Result {
+        let overflow_fail = offset.checked_add(size).is_none();
+        let cmp_size_fail = offset.wrapping_add(size) > self.size;
+        if overflow_fail || cmp_size_fail {
+            return Err(EFAULT);
+        }
+        Ok(())
+    }
+
+    pub(crate) fn copy_into(
+        &self,
+        reader: &mut UserSliceReader,
+        offset: usize,
+        size: usize,
+    ) -> Result {
+        self.size_check(offset, size)?;
+
+        // SAFETY: While this object exists, the range allocator will keep the range allocated, and
+        // in turn, the pages will be marked as in use.
+        unsafe {
+            self.process
+                .pages
+                .copy_from_user_slice(reader, self.offset + offset, size)
+        }
+    }
+
+    pub(crate) fn read<T: FromBytes>(&self, offset: usize) -> Result<T> {
+        self.size_check(offset, size_of::<T>())?;
+
+        // SAFETY: While this object exists, the range allocator will keep the range allocated, and
+        // in turn, the pages will be marked as in use.
+        unsafe { self.process.pages.read(self.offset + offset) }
+    }
+
+    pub(crate) fn write<T: ?Sized>(&self, offset: usize, obj: &T) -> Result {
+        self.size_check(offset, size_of_val::<T>(obj))?;
+
+        // SAFETY: While this object exists, the range allocator will keep the range allocated, and
+        // in turn, the pages will be marked as in use.
+        unsafe { self.process.pages.write(self.offset + offset, obj) }
+    }
+
+    pub(crate) fn fill_zero(&self) -> Result {
+        // SAFETY: While this object exists, the range allocator will keep the range allocated, and
+        // in turn, the pages will be marked as in use.
+        unsafe { self.process.pages.fill_zero(self.offset, self.size) }
+    }
+
+    pub(crate) fn keep_alive(mut self) {
+        self.process
+            .buffer_make_freeable(self.offset, self.allocation_info.take());
+        self.free_on_drop = false;
+    }
+
+    pub(crate) fn set_info(&mut self, info: AllocationInfo) {
+        self.allocation_info = Some(info);
+    }
+
+    pub(crate) fn get_or_init_info(&mut self) -> &mut AllocationInfo {
+        self.allocation_info.get_or_insert_with(Default::default)
+    }
+
+    pub(crate) fn set_info_offsets(&mut self, offsets: Range<usize>) {
+        self.get_or_init_info().offsets = Some(offsets);
+    }
+
+    pub(crate) fn set_info_oneway_node(&mut self, oneway_node: DArc<Node>) {
+        self.get_or_init_info().oneway_node = Some(oneway_node);
+    }
+
+    pub(crate) fn set_info_clear_on_drop(&mut self) {
+        self.get_or_init_info().clear_on_free = true;
+    }
+
+    pub(crate) fn set_info_target_node(&mut self, target_node: NodeRef) {
+        self.get_or_init_info().target_node = Some(target_node);
+    }
+
+    /// Reserve enough space to push at least `num_fds` fds.
+    pub(crate) fn info_add_fd_reserve(&mut self, num_fds: usize) -> Result {
+        self.get_or_init_info()
+            .file_list
+            .files_to_translate
+            .reserve(num_fds, GFP_KERNEL)?;
+
+        Ok(())
+    }
+
+    pub(crate) fn info_add_fd(
+        &mut self,
+        file: ARef<File>,
+        buffer_offset: usize,
+        close_on_free: bool,
+    ) -> Result {
+        self.get_or_init_info().file_list.files_to_translate.push(
+            FileEntry {
+                file,
+                buffer_offset,
+                close_on_free,
+            },
+            GFP_KERNEL,
+        )?;
+
+        Ok(())
+    }
+
+    pub(crate) fn set_info_close_on_free(&mut self, cof: FdsCloseOnFree) {
+        self.get_or_init_info().file_list.close_on_free = cof.0;
+    }
+
+    pub(crate) fn translate_fds(&mut self) -> Result<TranslatedFds> {
+        let file_list = match self.allocation_info.as_mut() {
+            Some(info) => &mut info.file_list,
+            None => return Ok(TranslatedFds::new()),
+        };
+
+        let files = core::mem::take(&mut file_list.files_to_translate);
+
+        let num_close_on_free = files.iter().filter(|entry| entry.close_on_free).count();
+        let mut close_on_free = KVec::with_capacity(num_close_on_free, GFP_KERNEL)?;
+
+        let mut reservations = KVec::with_capacity(files.len(), GFP_KERNEL)?;
+        for file_info in files {
+            let res = FileDescriptorReservation::get_unused_fd_flags(bindings::O_CLOEXEC)?;
+            let fd = res.reserved_fd();
+            self.write::<u32>(file_info.buffer_offset, &fd)?;
+
+            reservations.push(
+                Reservation {
+                    res,
+                    file: file_info.file,
+                },
+                GFP_KERNEL,
+            )?;
+            if file_info.close_on_free {
+                close_on_free.push(fd, GFP_KERNEL)?;
+            }
+        }
+
+        Ok(TranslatedFds {
+            reservations,
+            close_on_free: FdsCloseOnFree(close_on_free),
+        })
+    }
+
+    /// Should the looper return to userspace when freeing this allocation?
+    pub(crate) fn looper_need_return_on_free(&self) -> bool {
+        // Closing fds involves pushing task_work for execution when we return to userspace. Hence,
+        // we should return to userspace asap if we are closing fds.
+        match self.allocation_info {
+            Some(ref info) => !info.file_list.close_on_free.is_empty(),
+            None => false,
+        }
+    }
+}
+
+impl Drop for Allocation {
+    fn drop(&mut self) {
+        if !self.free_on_drop {
+            return;
+        }
+
+        if let Some(mut info) = self.allocation_info.take() {
+            if let Some(oneway_node) = info.oneway_node.as_ref() {
+                oneway_node.pending_oneway_finished();
+            }
+
+            info.target_node = None;
+
+            if let Some(offsets) = info.offsets.clone() {
+                let view = AllocationView::new(self, offsets.start);
+                for i in offsets.step_by(size_of::<usize>()) {
+                    if view.cleanup_object(i).is_err() {
+                        pr_warn!("Error cleaning up object at offset {}\n", i)
+                    }
+                }
+            }
+
+            for &fd in &info.file_list.close_on_free {
+                let closer = match DeferredFdCloser::new(GFP_KERNEL) {
+                    Ok(closer) => closer,
+                    Err(kernel::alloc::AllocError) => {
+                        // Ignore allocation failures.
+                        break;
+                    }
+                };
+
+                // Here, we ignore errors. The operation can fail if the fd is not valid, or if the
+                // method is called from a kthread. However, this is always called from a syscall,
+                // so the latter case cannot happen, and we don't care about the first case.
+                let _ = closer.close_fd(fd);
+            }
+
+            if info.clear_on_free {
+                if let Err(e) = self.fill_zero() {
+                    pr_warn!("Failed to clear data on free: {:?}", e);
+                }
+            }
+        }
+
+        self.process.buffer_raw_free(self.ptr);
+    }
+}
+
+/// A wrapper around `Allocation` that is being created.
+///
+/// If the allocation is destroyed while wrapped in this wrapper, then the allocation will be
+/// considered to be part of a failed transaction. Successful transactions avoid that by calling
+/// `success`, which skips the destructor.
+#[repr(transparent)]
+pub(crate) struct NewAllocation(pub(crate) Allocation);
+
+impl NewAllocation {
+    pub(crate) fn success(self) -> Allocation {
+        // This skips the destructor.
+        //
+        // SAFETY: This type is `#[repr(transparent)]`, so the layout matches.
+        unsafe { core::mem::transmute(self) }
+    }
+}
+
+impl core::ops::Deref for NewAllocation {
+    type Target = Allocation;
+    fn deref(&self) -> &Allocation {
+        &self.0
+    }
+}
+
+impl core::ops::DerefMut for NewAllocation {
+    fn deref_mut(&mut self) -> &mut Allocation {
+        &mut self.0
+    }
+}
+
+/// A view into the beginning of an allocation.
+///
+/// All attempts to read or write outside of the view will fail. To intentionally access outside of
+/// this view, use the `alloc` field of this struct directly.
+pub(crate) struct AllocationView<'a> {
+    pub(crate) alloc: &'a mut Allocation,
+    limit: usize,
+}
+
+impl<'a> AllocationView<'a> {
+    pub(crate) fn new(alloc: &'a mut Allocation, limit: usize) -> Self {
+        AllocationView { alloc, limit }
+    }
+
+    pub(crate) fn read<T: FromBytes>(&self, offset: usize) -> Result<T> {
+        if offset.checked_add(size_of::<T>()).ok_or(EINVAL)? > self.limit {
+            return Err(EINVAL);
+        }
+        self.alloc.read(offset)
+    }
+
+    pub(crate) fn write<T: AsBytes>(&self, offset: usize, obj: &T) -> Result {
+        if offset.checked_add(size_of::<T>()).ok_or(EINVAL)? > self.limit {
+            return Err(EINVAL);
+        }
+        self.alloc.write(offset, obj)
+    }
+
+    pub(crate) fn copy_into(
+        &self,
+        reader: &mut UserSliceReader,
+        offset: usize,
+        size: usize,
+    ) -> Result {
+        if offset.checked_add(size).ok_or(EINVAL)? > self.limit {
+            return Err(EINVAL);
+        }
+        self.alloc.copy_into(reader, offset, size)
+    }
+
+    pub(crate) fn transfer_binder_object(
+        &self,
+        offset: usize,
+        obj: &uapi::flat_binder_object,
+        strong: bool,
+        node_ref: NodeRef,
+    ) -> Result {
+        let mut newobj = FlatBinderObject::default();
+        let node = node_ref.node.clone();
+        if Arc::ptr_eq(&node_ref.node.owner, &self.alloc.process) {
+            // The receiving process is the owner of the node, so send it a binder object (instead
+            // of a handle).
+            let (ptr, cookie) = node.get_id();
+            newobj.hdr.type_ = if strong {
+                BINDER_TYPE_BINDER
+            } else {
+                BINDER_TYPE_WEAK_BINDER
+            };
+            newobj.flags = obj.flags;
+            newobj.__bindgen_anon_1.binder = ptr as _;
+            newobj.cookie = cookie as _;
+            self.write(offset, &newobj)?;
+            // Increment the user ref count on the node. It will be decremented as part of the
+            // destruction of the buffer, when we see a binder or weak-binder object.
+            node.update_refcount(true, 1, strong);
+        } else {
+            // The receiving process is different from the owner, so we need to insert a handle to
+            // the binder object.
+            let handle = self
+                .alloc
+                .process
+                .as_arc_borrow()
+                .insert_or_update_handle(node_ref, false)?;
+            newobj.hdr.type_ = if strong {
+                BINDER_TYPE_HANDLE
+            } else {
+                BINDER_TYPE_WEAK_HANDLE
+            };
+            newobj.flags = obj.flags;
+            newobj.__bindgen_anon_1.handle = handle;
+            if self.write(offset, &newobj).is_err() {
+                // Decrement ref count on the handle we just created.
+                let _ = self
+                    .alloc
+                    .process
+                    .as_arc_borrow()
+                    .update_ref(handle, false, strong);
+                return Err(EINVAL);
+            }
+        }
+
+        Ok(())
+    }
+
+    fn cleanup_object(&self, index_offset: usize) -> Result {
+        let offset = self.alloc.read(index_offset)?;
+        let header = self.read::<BinderObjectHeader>(offset)?;
+        match header.type_ {
+            BINDER_TYPE_WEAK_BINDER | BINDER_TYPE_BINDER => {
+                let obj = self.read::<FlatBinderObject>(offset)?;
+                let strong = header.type_ == BINDER_TYPE_BINDER;
+                // SAFETY: The type is `BINDER_TYPE_{WEAK_}BINDER`, so the `binder` field is
+                // populated.
+                let ptr = unsafe { obj.__bindgen_anon_1.binder };
+                let cookie = obj.cookie;
+                self.alloc.process.update_node(ptr, cookie, strong);
+                Ok(())
+            }
+            BINDER_TYPE_WEAK_HANDLE | BINDER_TYPE_HANDLE => {
+                let obj = self.read::<FlatBinderObject>(offset)?;
+                let strong = header.type_ == BINDER_TYPE_HANDLE;
+                // SAFETY: The type is `BINDER_TYPE_{WEAK_}HANDLE`, so the `handle` field is
+                // populated.
+                let handle = unsafe { obj.__bindgen_anon_1.handle };
+                self.alloc
+                    .process
+                    .as_arc_borrow()
+                    .update_ref(handle, false, strong)
+            }
+            _ => Ok(()),
+        }
+    }
+}
+
+/// A binder object as it is serialized.
+///
+/// # Invariants
+///
+/// All bytes must be initialized, and the value of `self.hdr.type_` must be one of the allowed
+/// types.
+#[repr(C)]
+pub(crate) union BinderObject {
+    hdr: uapi::binder_object_header,
+    fbo: uapi::flat_binder_object,
+    fdo: uapi::binder_fd_object,
+    bbo: uapi::binder_buffer_object,
+    fdao: uapi::binder_fd_array_object,
+}
+
+/// A view into a `BinderObject` that can be used in a match statement.
+pub(crate) enum BinderObjectRef<'a> {
+    Binder(&'a mut uapi::flat_binder_object),
+    Handle(&'a mut uapi::flat_binder_object),
+    Fd(&'a mut uapi::binder_fd_object),
+    Ptr(&'a mut uapi::binder_buffer_object),
+    Fda(&'a mut uapi::binder_fd_array_object),
+}
+
+impl BinderObject {
+    pub(crate) fn read_from(reader: &mut UserSliceReader) -> Result<BinderObject> {
+        let object = Self::read_from_inner(|slice| {
+            let read_len = usize::min(slice.len(), reader.len());
+            reader.clone_reader().read_slice(&mut slice[..read_len])?;
+            Ok(())
+        })?;
+
+        // If we used a object type smaller than the largest object size, then we've read more
+        // bytes than we needed to. However, we used `.clone_reader()` to avoid advancing the
+        // original reader. Now, we call `skip` so that the caller's reader is advanced by the
+        // right amount.
+        //
+        // The `skip` call fails if the reader doesn't have `size` bytes available. This could
+        // happen if the type header corresponds to an object type that is larger than the rest of
+        // the reader.
+        //
+        // Any extra bytes beyond the size of the object are inaccessible after this call, so
+        // reading them again from the `reader` later does not result in TOCTOU bugs.
+        reader.skip(object.size())?;
+
+        Ok(object)
+    }
+
+    /// Use the provided reader closure to construct a `BinderObject`.
+    ///
+    /// The closure should write the bytes for the object into the provided slice.
+    pub(crate) fn read_from_inner<R>(reader: R) -> Result<BinderObject>
+    where
+        R: FnOnce(&mut [u8; size_of::<BinderObject>()]) -> Result<()>,
+    {
+        let mut obj = MaybeUninit::<BinderObject>::zeroed();
+
+        // SAFETY: The lengths of `BinderObject` and `[u8; size_of::<BinderObject>()]` are equal,
+        // and the byte array has an alignment requirement of one, so the pointer cast is okay.
+        // Additionally, `obj` was initialized to zeros, so the byte array will not be
+        // uninitialized.
+        (reader)(unsafe { &mut *obj.as_mut_ptr().cast() })?;
+
+        // SAFETY: The entire object is initialized, so accessing this field is safe.
+        let type_ = unsafe { obj.assume_init_ref().hdr.type_ };
+        if Self::type_to_size(type_).is_none() {
+            // The value of `obj.hdr_type_` was invalid.
+            return Err(EINVAL);
+        }
+
+        // SAFETY: All bytes are initialized (since we zeroed them at the start) and we checked
+        // that `self.hdr.type_` is one of the allowed types, so the type invariants are satisfied.
+        unsafe { Ok(obj.assume_init()) }
+    }
+
+    pub(crate) fn as_ref(&mut self) -> BinderObjectRef<'_> {
+        use BinderObjectRef::*;
+        // SAFETY: The constructor ensures that all bytes of `self` are initialized, and all
+        // variants of this union accept all initialized bit patterns.
+        unsafe {
+            match self.hdr.type_ {
+                BINDER_TYPE_WEAK_BINDER | BINDER_TYPE_BINDER => Binder(&mut self.fbo),
+                BINDER_TYPE_WEAK_HANDLE | BINDER_TYPE_HANDLE => Handle(&mut self.fbo),
+                BINDER_TYPE_FD => Fd(&mut self.fdo),
+                BINDER_TYPE_PTR => Ptr(&mut self.bbo),
+                BINDER_TYPE_FDA => Fda(&mut self.fdao),
+                // SAFETY: By the type invariant, the value of `self.hdr.type_` cannot have any
+                // other value than the ones checked above.
+                _ => core::hint::unreachable_unchecked(),
+            }
+        }
+    }
+
+    pub(crate) fn size(&self) -> usize {
+        // SAFETY: The entire object is initialized, so accessing this field is safe.
+        let type_ = unsafe { self.hdr.type_ };
+
+        // SAFETY: The type invariants guarantee that the type field is correct.
+        unsafe { Self::type_to_size(type_).unwrap_unchecked() }
+    }
+
+    fn type_to_size(type_: u32) -> Option<usize> {
+        match type_ {
+            BINDER_TYPE_WEAK_BINDER => Some(size_of::<uapi::flat_binder_object>()),
+            BINDER_TYPE_BINDER => Some(size_of::<uapi::flat_binder_object>()),
+            BINDER_TYPE_WEAK_HANDLE => Some(size_of::<uapi::flat_binder_object>()),
+            BINDER_TYPE_HANDLE => Some(size_of::<uapi::flat_binder_object>()),
+            BINDER_TYPE_FD => Some(size_of::<uapi::binder_fd_object>()),
+            BINDER_TYPE_PTR => Some(size_of::<uapi::binder_buffer_object>()),
+            BINDER_TYPE_FDA => Some(size_of::<uapi::binder_fd_array_object>()),
+            _ => None,
+        }
+    }
+}
+
+#[derive(Default)]
+struct FileList {
+    files_to_translate: KVec<FileEntry>,
+    close_on_free: KVec<u32>,
+}
+
+struct FileEntry {
+    /// The file for which a descriptor will be created in the recipient process.
+    file: ARef<File>,
+    /// The offset in the buffer where the file descriptor is stored.
+    buffer_offset: usize,
+    /// Whether this fd should be closed when the allocation is freed.
+    close_on_free: bool,
+}
+
+pub(crate) struct TranslatedFds {
+    reservations: KVec<Reservation>,
+    /// If commit is called, then these fds should be closed. (If commit is not called, then they
+    /// shouldn't be closed.)
+    close_on_free: FdsCloseOnFree,
+}
+
+struct Reservation {
+    res: FileDescriptorReservation,
+    file: ARef<File>,
+}
+
+impl TranslatedFds {
+    pub(crate) fn new() -> Self {
+        Self {
+            reservations: KVec::new(),
+            close_on_free: FdsCloseOnFree(KVec::new()),
+        }
+    }
+
+    pub(crate) fn commit(self) -> FdsCloseOnFree {
+        for entry in self.reservations {
+            entry.res.fd_install(entry.file);
+        }
+
+        self.close_on_free
+    }
+}
+
+pub(crate) struct FdsCloseOnFree(KVec<u32>);
diff --git a/drivers/android/binder/context.rs b/drivers/android/binder/context.rs
new file mode 100644
index 000000000000..3d135ec03ca7
--- /dev/null
+++ b/drivers/android/binder/context.rs
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{
+    error::Error,
+    list::{List, ListArc, ListLinks},
+    prelude::*,
+    security,
+    str::{CStr, CString},
+    sync::{Arc, Mutex},
+    task::Kuid,
+};
+
+use crate::{error::BinderError, node::NodeRef, process::Process};
+
+kernel::sync::global_lock! {
+    // SAFETY: We call `init` in the module initializer, so it's initialized before first use.
+    pub(crate) unsafe(uninit) static CONTEXTS: Mutex<ContextList> = ContextList {
+        list: List::new(),
+    };
+}
+
+pub(crate) struct ContextList {
+    list: List<Context>,
+}
+
+pub(crate) fn get_all_contexts() -> Result<KVec<Arc<Context>>> {
+    let lock = CONTEXTS.lock();
+
+    let count = lock.list.iter().count();
+
+    let mut ctxs = KVec::with_capacity(count, GFP_KERNEL)?;
+    for ctx in &lock.list {
+        ctxs.push(Arc::from(ctx), GFP_KERNEL)?;
+    }
+    Ok(ctxs)
+}
+
+/// This struct keeps track of the processes using this context, and which process is the context
+/// manager.
+struct Manager {
+    node: Option<NodeRef>,
+    uid: Option<Kuid>,
+    all_procs: List<Process>,
+}
+
+/// There is one context per binder file (/dev/binder, /dev/hwbinder, etc)
+#[pin_data]
+pub(crate) struct Context {
+    #[pin]
+    manager: Mutex<Manager>,
+    pub(crate) name: CString,
+    #[pin]
+    links: ListLinks,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for Context { untracked; }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<0> for Context {
+        using ListLinks { self.links };
+    }
+}
+
+impl Context {
+    pub(crate) fn new(name: &CStr) -> Result<Arc<Self>> {
+        let name = CString::try_from(name)?;
+        let list_ctx = ListArc::pin_init::<Error>(
+            try_pin_init!(Context {
+                name,
+                links <- ListLinks::new(),
+                manager <- kernel::new_mutex!(Manager {
+                    all_procs: List::new(),
+                    node: None,
+                    uid: None,
+                }, "Context::manager"),
+            }),
+            GFP_KERNEL,
+        )?;
+
+        let ctx = list_ctx.clone_arc();
+        CONTEXTS.lock().list.push_back(list_ctx);
+
+        Ok(ctx)
+    }
+
+    /// Called when the file for this context is unlinked.
+    ///
+    /// No-op if called twice.
+    pub(crate) fn deregister(&self) {
+        // SAFETY: We never add the context to any other linked list than this one, so it is either
+        // in this list, or not in any list.
+        unsafe { CONTEXTS.lock().list.remove(self) };
+    }
+
+    pub(crate) fn register_process(self: &Arc<Self>, proc: ListArc<Process>) {
+        if !Arc::ptr_eq(self, &proc.ctx) {
+            pr_err!("Context::register_process called on the wrong context.");
+            return;
+        }
+        self.manager.lock().all_procs.push_back(proc);
+    }
+
+    pub(crate) fn deregister_process(self: &Arc<Self>, proc: &Process) {
+        if !Arc::ptr_eq(self, &proc.ctx) {
+            pr_err!("Context::deregister_process called on the wrong context.");
+            return;
+        }
+        // SAFETY: We just checked that this is the right list.
+        unsafe { self.manager.lock().all_procs.remove(proc) };
+    }
+
+    pub(crate) fn set_manager_node(&self, node_ref: NodeRef) -> Result {
+        let mut manager = self.manager.lock();
+        if manager.node.is_some() {
+            pr_warn!("BINDER_SET_CONTEXT_MGR already set");
+            return Err(EBUSY);
+        }
+        security::binder_set_context_mgr(&node_ref.node.owner.cred)?;
+
+        // If the context manager has been set before, ensure that we use the same euid.
+        let caller_uid = Kuid::current_euid();
+        if let Some(ref uid) = manager.uid {
+            if *uid != caller_uid {
+                return Err(EPERM);
+            }
+        }
+
+        manager.node = Some(node_ref);
+        manager.uid = Some(caller_uid);
+        Ok(())
+    }
+
+    pub(crate) fn unset_manager_node(&self) {
+        let node_ref = self.manager.lock().node.take();
+        drop(node_ref);
+    }
+
+    pub(crate) fn get_manager_node(&self, strong: bool) -> Result<NodeRef, BinderError> {
+        self.manager
+            .lock()
+            .node
+            .as_ref()
+            .ok_or_else(BinderError::new_dead)?
+            .clone(strong)
+            .map_err(BinderError::from)
+    }
+
+    pub(crate) fn for_each_proc<F>(&self, mut func: F)
+    where
+        F: FnMut(&Process),
+    {
+        let lock = self.manager.lock();
+        for proc in &lock.all_procs {
+            func(&proc);
+        }
+    }
+
+    pub(crate) fn get_all_procs(&self) -> Result<KVec<Arc<Process>>> {
+        let lock = self.manager.lock();
+        let count = lock.all_procs.iter().count();
+
+        let mut procs = KVec::with_capacity(count, GFP_KERNEL)?;
+        for proc in &lock.all_procs {
+            procs.push(Arc::from(proc), GFP_KERNEL)?;
+        }
+        Ok(procs)
+    }
+
+    pub(crate) fn get_procs_with_pid(&self, pid: i32) -> Result<KVec<Arc<Process>>> {
+        let orig = self.get_all_procs()?;
+        let mut backing = KVec::with_capacity(orig.len(), GFP_KERNEL)?;
+        for proc in orig.into_iter().filter(|proc| proc.task.pid() == pid) {
+            backing.push(proc, GFP_KERNEL)?;
+        }
+        Ok(backing)
+    }
+}
diff --git a/drivers/android/binder/deferred_close.rs b/drivers/android/binder/deferred_close.rs
new file mode 100644
index 000000000000..ac895c04d0cb
--- /dev/null
+++ b/drivers/android/binder/deferred_close.rs
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! Logic for closing files in a deferred manner.
+//!
+//! This file could make sense to have in `kernel::fs`, but it was rejected for being too
+//! Binder-specific.
+
+use core::mem::MaybeUninit;
+use kernel::{
+    alloc::{AllocError, Flags},
+    bindings,
+    prelude::*,
+};
+
+/// Helper used for closing file descriptors in a way that is safe even if the file is currently
+/// held using `fdget`.
+///
+/// Additional motivation can be found in commit 80cd795630d6 ("binder: fix use-after-free due to
+/// ksys_close() during fdget()") and in the comments on `binder_do_fd_close`.
+pub(crate) struct DeferredFdCloser {
+    inner: KBox<DeferredFdCloserInner>,
+}
+
+/// SAFETY: This just holds an allocation with no real content, so there's no safety issue with
+/// moving it across threads.
+unsafe impl Send for DeferredFdCloser {}
+/// SAFETY: This just holds an allocation with no real content, so there's no safety issue with
+/// moving it across threads.
+unsafe impl Sync for DeferredFdCloser {}
+
+/// # Invariants
+///
+/// If the `file` pointer is non-null, then it points at a `struct file` and owns a refcount to
+/// that file.
+#[repr(C)]
+struct DeferredFdCloserInner {
+    twork: MaybeUninit<bindings::callback_head>,
+    file: *mut bindings::file,
+}
+
+impl DeferredFdCloser {
+    /// Create a new [`DeferredFdCloser`].
+    pub(crate) fn new(flags: Flags) -> Result<Self, AllocError> {
+        Ok(Self {
+            // INVARIANT: The `file` pointer is null, so the type invariant does not apply.
+            inner: KBox::new(
+                DeferredFdCloserInner {
+                    twork: MaybeUninit::uninit(),
+                    file: core::ptr::null_mut(),
+                },
+                flags,
+            )?,
+        })
+    }
+
+    /// Schedule a task work that closes the file descriptor when this task returns to userspace.
+    ///
+    /// Fails if this is called from a context where we cannot run work when returning to
+    /// userspace. (E.g., from a kthread.)
+    pub(crate) fn close_fd(self, fd: u32) -> Result<(), DeferredFdCloseError> {
+        use bindings::task_work_notify_mode_TWA_RESUME as TWA_RESUME;
+
+        // In this method, we schedule the task work before closing the file. This is because
+        // scheduling a task work is fallible, and we need to know whether it will fail before we
+        // attempt to close the file.
+
+        // Task works are not available on kthreads.
+        let current = kernel::current!();
+
+        // Check if this is a kthread.
+        // SAFETY: Reading `flags` from a task is always okay.
+        if unsafe { ((*current.as_ptr()).flags & bindings::PF_KTHREAD) != 0 } {
+            return Err(DeferredFdCloseError::TaskWorkUnavailable);
+        }
+
+        // Transfer ownership of the box's allocation to a raw pointer. This disables the
+        // destructor, so we must manually convert it back to a KBox to drop it.
+        //
+        // Until we convert it back to a `KBox`, there are no aliasing requirements on this
+        // pointer.
+        let inner = KBox::into_raw(self.inner);
+
+        // The `callback_head` field is first in the struct, so this cast correctly gives us a
+        // pointer to the field.
+        let callback_head = inner.cast::<bindings::callback_head>();
+        // SAFETY: This pointer offset operation does not go out-of-bounds.
+        let file_field = unsafe { core::ptr::addr_of_mut!((*inner).file) };
+
+        let current = current.as_ptr();
+
+        // SAFETY: This function currently has exclusive access to the `DeferredFdCloserInner`, so
+        // it is okay for us to perform unsynchronized writes to its `callback_head` field.
+        unsafe { bindings::init_task_work(callback_head, Some(Self::do_close_fd)) };
+
+        // SAFETY: This inserts the `DeferredFdCloserInner` into the task workqueue for the current
+        // task. If this operation is successful, then this transfers exclusive ownership of the
+        // `callback_head` field to the C side until it calls `do_close_fd`, and we don't touch or
+        // invalidate the field during that time.
+        //
+        // When the C side calls `do_close_fd`, the safety requirements of that method are
+        // satisfied because when a task work is executed, the callback is given ownership of the
+        // pointer.
+        //
+        // The file pointer is currently null. If it is changed to be non-null before `do_close_fd`
+        // is called, then that change happens due to the write at the end of this function, and
+        // that write has a safety comment that explains why the refcount can be dropped when
+        // `do_close_fd` runs.
+        let res = unsafe { bindings::task_work_add(current, callback_head, TWA_RESUME) };
+
+        if res != 0 {
+            // SAFETY: Scheduling the task work failed, so we still have ownership of the box, so
+            // we may destroy it.
+            unsafe { drop(KBox::from_raw(inner)) };
+
+            return Err(DeferredFdCloseError::TaskWorkUnavailable);
+        }
+
+        // This removes the fd from the fd table in `current`. The file is not fully closed until
+        // `filp_close` is called. We are given ownership of one refcount to the file.
+        //
+        // SAFETY: This is safe no matter what `fd` is. If the `fd` is valid (that is, if the
+        // pointer is non-null), then we call `filp_close` on the returned pointer as required by
+        // `file_close_fd`.
+        let file = unsafe { bindings::file_close_fd(fd) };
+        if file.is_null() {
+            // We don't clean up the task work since that might be expensive if the task work queue
+            // is long. Just let it execute and let it clean up for itself.
+            return Err(DeferredFdCloseError::BadFd);
+        }
+
+        // Acquire a second refcount to the file.
+        //
+        // SAFETY: The `file` pointer points at a file with a non-zero refcount.
+        unsafe { bindings::get_file(file) };
+
+        // This method closes the fd, consuming one of our two refcounts. There could be active
+        // light refcounts created from that fd, so we must ensure that the file has a positive
+        // refcount for the duration of those active light refcounts. We do that by holding on to
+        // the second refcount until the current task returns to userspace.
+        //
+        // SAFETY: The `file` pointer is valid. Passing `current->files` as the file table to close
+        // it in is correct, since we just got the `fd` from `file_close_fd` which also uses
+        // `current->files`.
+        //
+        // Note: fl_owner_t is currently a void pointer.
+        unsafe { bindings::filp_close(file, (*current).files as bindings::fl_owner_t) };
+
+        // We update the file pointer that the task work is supposed to fput. This transfers
+        // ownership of our last refcount.
+        //
+        // INVARIANT: This changes the `file` field of a `DeferredFdCloserInner` from null to
+        // non-null. This doesn't break the type invariant for `DeferredFdCloserInner` because we
+        // still own a refcount to the file, so we can pass ownership of that refcount to the
+        // `DeferredFdCloserInner`.
+        //
+        // When `do_close_fd` runs, it must be safe for it to `fput` the refcount. However, this is
+        // the case because all light refcounts that are associated with the fd we closed
+        // previously must be dropped when `do_close_fd`, since light refcounts must be dropped
+        // before returning to userspace.
+        //
+        // SAFETY: Task works are executed on the current thread right before we return to
+        // userspace, so this write is guaranteed to happen before `do_close_fd` is called, which
+        // means that a race is not possible here.
+        unsafe { *file_field = file };
+
+        Ok(())
+    }
+
+    /// # Safety
+    ///
+    /// The provided pointer must point at the `twork` field of a `DeferredFdCloserInner` stored in
+    /// a `KBox`, and the caller must pass exclusive ownership of that `KBox`. Furthermore, if the
+    /// file pointer is non-null, then it must be okay to release the refcount by calling `fput`.
+    unsafe extern "C" fn do_close_fd(inner: *mut bindings::callback_head) {
+        // SAFETY: The caller just passed us ownership of this box.
+        let inner = unsafe { KBox::from_raw(inner.cast::<DeferredFdCloserInner>()) };
+        if !inner.file.is_null() {
+            // SAFETY: By the type invariants, we own a refcount to this file, and the caller
+            // guarantees that dropping the refcount now is okay.
+            unsafe { bindings::fput(inner.file) };
+        }
+        // The allocation is freed when `inner` goes out of scope.
+    }
+}
+
+/// Represents a failure to close an fd in a deferred manner.
+#[derive(Copy, Clone, Debug, Eq, PartialEq)]
+pub(crate) enum DeferredFdCloseError {
+    /// Closing the fd failed because we were unable to schedule a task work.
+    TaskWorkUnavailable,
+    /// Closing the fd failed because the fd does not exist.
+    BadFd,
+}
+
+impl From<DeferredFdCloseError> for Error {
+    fn from(err: DeferredFdCloseError) -> Error {
+        match err {
+            DeferredFdCloseError::TaskWorkUnavailable => ESRCH,
+            DeferredFdCloseError::BadFd => EBADF,
+        }
+    }
+}
diff --git a/drivers/android/binder/defs.rs b/drivers/android/binder/defs.rs
new file mode 100644
index 000000000000..33f51b4139c7
--- /dev/null
+++ b/drivers/android/binder/defs.rs
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use core::mem::MaybeUninit;
+use core::ops::{Deref, DerefMut};
+use kernel::{
+    transmute::{AsBytes, FromBytes},
+    uapi::{self, *},
+};
+
+macro_rules! pub_no_prefix {
+    ($prefix:ident, $($newname:ident),+ $(,)?) => {
+        $(pub(crate) const $newname: u32 = kernel::macros::concat_idents!($prefix, $newname);)+
+    };
+}
+
+pub_no_prefix!(
+    binder_driver_return_protocol_,
+    BR_TRANSACTION,
+    BR_TRANSACTION_SEC_CTX,
+    BR_REPLY,
+    BR_DEAD_REPLY,
+    BR_FAILED_REPLY,
+    BR_FROZEN_REPLY,
+    BR_NOOP,
+    BR_SPAWN_LOOPER,
+    BR_TRANSACTION_COMPLETE,
+    BR_TRANSACTION_PENDING_FROZEN,
+    BR_ONEWAY_SPAM_SUSPECT,
+    BR_OK,
+    BR_ERROR,
+    BR_INCREFS,
+    BR_ACQUIRE,
+    BR_RELEASE,
+    BR_DECREFS,
+    BR_DEAD_BINDER,
+    BR_CLEAR_DEATH_NOTIFICATION_DONE,
+    BR_FROZEN_BINDER,
+    BR_CLEAR_FREEZE_NOTIFICATION_DONE,
+);
+
+pub_no_prefix!(
+    binder_driver_command_protocol_,
+    BC_TRANSACTION,
+    BC_TRANSACTION_SG,
+    BC_REPLY,
+    BC_REPLY_SG,
+    BC_FREE_BUFFER,
+    BC_ENTER_LOOPER,
+    BC_EXIT_LOOPER,
+    BC_REGISTER_LOOPER,
+    BC_INCREFS,
+    BC_ACQUIRE,
+    BC_RELEASE,
+    BC_DECREFS,
+    BC_INCREFS_DONE,
+    BC_ACQUIRE_DONE,
+    BC_REQUEST_DEATH_NOTIFICATION,
+    BC_CLEAR_DEATH_NOTIFICATION,
+    BC_DEAD_BINDER_DONE,
+    BC_REQUEST_FREEZE_NOTIFICATION,
+    BC_CLEAR_FREEZE_NOTIFICATION,
+    BC_FREEZE_NOTIFICATION_DONE,
+);
+
+pub_no_prefix!(
+    flat_binder_object_flags_,
+    FLAT_BINDER_FLAG_ACCEPTS_FDS,
+    FLAT_BINDER_FLAG_TXN_SECURITY_CTX
+);
+
+pub_no_prefix!(
+    transaction_flags_,
+    TF_ONE_WAY,
+    TF_ACCEPT_FDS,
+    TF_CLEAR_BUF,
+    TF_UPDATE_TXN
+);
+
+pub(crate) use uapi::{
+    BINDER_TYPE_BINDER, BINDER_TYPE_FD, BINDER_TYPE_FDA, BINDER_TYPE_HANDLE, BINDER_TYPE_PTR,
+    BINDER_TYPE_WEAK_BINDER, BINDER_TYPE_WEAK_HANDLE,
+};
+
+macro_rules! decl_wrapper {
+    ($newname:ident, $wrapped:ty) => {
+        // Define a wrapper around the C type. Use `MaybeUninit` to enforce that the value of
+        // padding bytes must be preserved.
+        #[derive(Copy, Clone)]
+        #[repr(transparent)]
+        pub(crate) struct $newname(MaybeUninit<$wrapped>);
+
+        // SAFETY: This macro is only used with types where this is ok.
+        unsafe impl FromBytes for $newname {}
+        // SAFETY: This macro is only used with types where this is ok.
+        unsafe impl AsBytes for $newname {}
+
+        impl Deref for $newname {
+            type Target = $wrapped;
+            fn deref(&self) -> &Self::Target {
+                // SAFETY: We use `MaybeUninit` only to preserve padding. The value must still
+                // always be valid.
+                unsafe { self.0.assume_init_ref() }
+            }
+        }
+
+        impl DerefMut for $newname {
+            fn deref_mut(&mut self) -> &mut Self::Target {
+                // SAFETY: We use `MaybeUninit` only to preserve padding. The value must still
+                // always be valid.
+                unsafe { self.0.assume_init_mut() }
+            }
+        }
+
+        impl Default for $newname {
+            fn default() -> Self {
+                // Create a new value of this type where all bytes (including padding) are zeroed.
+                Self(MaybeUninit::zeroed())
+            }
+        }
+    };
+}
+
+decl_wrapper!(BinderNodeDebugInfo, uapi::binder_node_debug_info);
+decl_wrapper!(BinderNodeInfoForRef, uapi::binder_node_info_for_ref);
+decl_wrapper!(FlatBinderObject, uapi::flat_binder_object);
+decl_wrapper!(BinderFdObject, uapi::binder_fd_object);
+decl_wrapper!(BinderFdArrayObject, uapi::binder_fd_array_object);
+decl_wrapper!(BinderObjectHeader, uapi::binder_object_header);
+decl_wrapper!(BinderBufferObject, uapi::binder_buffer_object);
+decl_wrapper!(BinderTransactionData, uapi::binder_transaction_data);
+decl_wrapper!(
+    BinderTransactionDataSecctx,
+    uapi::binder_transaction_data_secctx
+);
+decl_wrapper!(BinderTransactionDataSg, uapi::binder_transaction_data_sg);
+decl_wrapper!(BinderWriteRead, uapi::binder_write_read);
+decl_wrapper!(BinderVersion, uapi::binder_version);
+decl_wrapper!(BinderFrozenStatusInfo, uapi::binder_frozen_status_info);
+decl_wrapper!(BinderFreezeInfo, uapi::binder_freeze_info);
+decl_wrapper!(BinderFrozenStateInfo, uapi::binder_frozen_state_info);
+decl_wrapper!(BinderHandleCookie, uapi::binder_handle_cookie);
+decl_wrapper!(ExtendedError, uapi::binder_extended_error);
+
+impl BinderVersion {
+    pub(crate) fn current() -> Self {
+        Self(MaybeUninit::new(uapi::binder_version {
+            protocol_version: BINDER_CURRENT_PROTOCOL_VERSION as _,
+        }))
+    }
+}
+
+impl BinderTransactionData {
+    pub(crate) fn with_buffers_size(self, buffers_size: u64) -> BinderTransactionDataSg {
+        BinderTransactionDataSg(MaybeUninit::new(uapi::binder_transaction_data_sg {
+            transaction_data: *self,
+            buffers_size,
+        }))
+    }
+}
+
+impl BinderTransactionDataSecctx {
+    /// View the inner data as wrapped in `BinderTransactionData`.
+    pub(crate) fn tr_data(&mut self) -> &mut BinderTransactionData {
+        // SAFETY: Transparent wrapper is safe to transmute.
+        unsafe {
+            &mut *(&mut self.transaction_data as *mut uapi::binder_transaction_data
+                as *mut BinderTransactionData)
+        }
+    }
+}
+
+impl ExtendedError {
+    pub(crate) fn new(id: u32, command: u32, param: i32) -> Self {
+        Self(MaybeUninit::new(uapi::binder_extended_error {
+            id,
+            command,
+            param,
+        }))
+    }
+}
diff --git a/drivers/android/binder/error.rs b/drivers/android/binder/error.rs
new file mode 100644
index 000000000000..9921827267d0
--- /dev/null
+++ b/drivers/android/binder/error.rs
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::prelude::*;
+
+use crate::defs::*;
+
+pub(crate) type BinderResult<T = ()> = core::result::Result<T, BinderError>;
+
+/// An error that will be returned to userspace via the `BINDER_WRITE_READ` ioctl rather than via
+/// errno.
+pub(crate) struct BinderError {
+    pub(crate) reply: u32,
+    source: Option<Error>,
+}
+
+impl BinderError {
+    pub(crate) fn new_dead() -> Self {
+        Self {
+            reply: BR_DEAD_REPLY,
+            source: None,
+        }
+    }
+
+    pub(crate) fn new_frozen() -> Self {
+        Self {
+            reply: BR_FROZEN_REPLY,
+            source: None,
+        }
+    }
+
+    pub(crate) fn new_frozen_oneway() -> Self {
+        Self {
+            reply: BR_TRANSACTION_PENDING_FROZEN,
+            source: None,
+        }
+    }
+
+    pub(crate) fn is_dead(&self) -> bool {
+        self.reply == BR_DEAD_REPLY
+    }
+
+    pub(crate) fn as_errno(&self) -> kernel::ffi::c_int {
+        self.source.unwrap_or(EINVAL).to_errno()
+    }
+
+    pub(crate) fn should_pr_warn(&self) -> bool {
+        self.source.is_some()
+    }
+}
+
+/// Convert an errno into a `BinderError` and store the errno used to construct it. The errno
+/// should be stored as the thread's extended error when given to userspace.
+impl From<Error> for BinderError {
+    fn from(source: Error) -> Self {
+        Self {
+            reply: BR_FAILED_REPLY,
+            source: Some(source),
+        }
+    }
+}
+
+impl From<kernel::fs::file::BadFdError> for BinderError {
+    fn from(source: kernel::fs::file::BadFdError) -> Self {
+        BinderError::from(Error::from(source))
+    }
+}
+
+impl From<kernel::alloc::AllocError> for BinderError {
+    fn from(_: kernel::alloc::AllocError) -> Self {
+        Self {
+            reply: BR_FAILED_REPLY,
+            source: Some(ENOMEM),
+        }
+    }
+}
+
+impl core::fmt::Debug for BinderError {
+    fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
+        match self.reply {
+            BR_FAILED_REPLY => match self.source.as_ref() {
+                Some(source) => f
+                    .debug_struct("BR_FAILED_REPLY")
+                    .field("source", source)
+                    .finish(),
+                None => f.pad("BR_FAILED_REPLY"),
+            },
+            BR_DEAD_REPLY => f.pad("BR_DEAD_REPLY"),
+            BR_FROZEN_REPLY => f.pad("BR_FROZEN_REPLY"),
+            BR_TRANSACTION_PENDING_FROZEN => f.pad("BR_TRANSACTION_PENDING_FROZEN"),
+            BR_TRANSACTION_COMPLETE => f.pad("BR_TRANSACTION_COMPLETE"),
+            _ => f
+                .debug_struct("BinderError")
+                .field("reply", &self.reply)
+                .finish(),
+        }
+    }
+}
diff --git a/drivers/android/binder/freeze.rs b/drivers/android/binder/freeze.rs
new file mode 100644
index 000000000000..e68c3c8bc55a
--- /dev/null
+++ b/drivers/android/binder/freeze.rs
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{
+    alloc::AllocError,
+    list::ListArc,
+    prelude::*,
+    rbtree::{self, RBTreeNodeReservation},
+    seq_file::SeqFile,
+    seq_print,
+    sync::{Arc, UniqueArc},
+    uaccess::UserSliceReader,
+};
+
+use crate::{
+    defs::*, node::Node, process::Process, thread::Thread, BinderReturnWriter, DArc, DLArc,
+    DTRWrap, DeliverToRead,
+};
+
+#[derive(Clone, Copy, Eq, PartialEq, Ord, PartialOrd)]
+pub(crate) struct FreezeCookie(u64);
+
+/// Represents a listener for changes to the frozen state of a process.
+pub(crate) struct FreezeListener {
+    /// The node we are listening for.
+    pub(crate) node: DArc<Node>,
+    /// The cookie of this freeze listener.
+    cookie: FreezeCookie,
+    /// What value of `is_frozen` did we most recently tell userspace about?
+    last_is_frozen: Option<bool>,
+    /// We sent a `BR_FROZEN_BINDER` and we are waiting for `BC_FREEZE_NOTIFICATION_DONE` before
+    /// sending any other commands.
+    is_pending: bool,
+    /// Userspace sent `BC_CLEAR_FREEZE_NOTIFICATION` and we need to reply with
+    /// `BR_CLEAR_FREEZE_NOTIFICATION_DONE` as soon as possible. If `is_pending` is set, then we
+    /// must wait for it to be unset before we can reply.
+    is_clearing: bool,
+    /// Number of cleared duplicates that can't be deleted until userspace sends
+    /// `BC_FREEZE_NOTIFICATION_DONE`.
+    num_pending_duplicates: u64,
+    /// Number of cleared duplicates that can be deleted.
+    num_cleared_duplicates: u64,
+}
+
+impl FreezeListener {
+    /// Is it okay to create a new listener with the same cookie as this one for the provided node?
+    ///
+    /// Under some scenarios, userspace may delete a freeze listener and immediately recreate it
+    /// with the same cookie. This results in duplicate listeners. To avoid issues with ambiguity,
+    /// we allow this only if the new listener is for the same node, and we also require that the
+    /// old listener has already been cleared.
+    fn allow_duplicate(&self, node: &DArc<Node>) -> bool {
+        Arc::ptr_eq(&self.node, node) && self.is_clearing
+    }
+}
+
+type UninitFM = UniqueArc<core::mem::MaybeUninit<DTRWrap<FreezeMessage>>>;
+
+/// Represents a notification that the freeze state has changed.
+pub(crate) struct FreezeMessage {
+    cookie: FreezeCookie,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for FreezeMessage {
+        untracked;
+    }
+}
+
+impl FreezeMessage {
+    fn new(flags: kernel::alloc::Flags) -> Result<UninitFM, AllocError> {
+        UniqueArc::new_uninit(flags)
+    }
+
+    fn init(ua: UninitFM, cookie: FreezeCookie) -> DLArc<FreezeMessage> {
+        match ua.pin_init_with(DTRWrap::new(FreezeMessage { cookie })) {
+            Ok(msg) => ListArc::from(msg),
+            Err(err) => match err {},
+        }
+    }
+}
+
+impl DeliverToRead for FreezeMessage {
+    fn do_work(
+        self: DArc<Self>,
+        thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let _removed_listener;
+        let mut node_refs = thread.process.node_refs.lock();
+        let Some(mut freeze_entry) = node_refs.freeze_listeners.find_mut(&self.cookie) else {
+            return Ok(true);
+        };
+        let freeze = freeze_entry.get_mut();
+
+        if freeze.num_cleared_duplicates > 0 {
+            freeze.num_cleared_duplicates -= 1;
+            drop(node_refs);
+            writer.write_code(BR_CLEAR_FREEZE_NOTIFICATION_DONE)?;
+            writer.write_payload(&self.cookie.0)?;
+            return Ok(true);
+        }
+
+        if freeze.is_pending {
+            return Ok(true);
+        }
+        if freeze.is_clearing {
+            _removed_listener = freeze_entry.remove_node();
+            drop(node_refs);
+            writer.write_code(BR_CLEAR_FREEZE_NOTIFICATION_DONE)?;
+            writer.write_payload(&self.cookie.0)?;
+            Ok(true)
+        } else {
+            let is_frozen = freeze.node.owner.inner.lock().is_frozen;
+            if freeze.last_is_frozen == Some(is_frozen) {
+                return Ok(true);
+            }
+
+            let mut state_info = BinderFrozenStateInfo::default();
+            state_info.is_frozen = is_frozen as u32;
+            state_info.cookie = freeze.cookie.0;
+            freeze.is_pending = true;
+            freeze.last_is_frozen = Some(is_frozen);
+            drop(node_refs);
+
+            writer.write_code(BR_FROZEN_BINDER)?;
+            writer.write_payload(&state_info)?;
+            // BR_FROZEN_BINDER notifications can cause transactions
+            Ok(false)
+        }
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    #[inline(never)]
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        seq_print!(m, "{}has frozen binder\n", prefix);
+        Ok(())
+    }
+}
+
+impl FreezeListener {
+    pub(crate) fn on_process_exit(&self, proc: &Arc<Process>) {
+        if !self.is_clearing {
+            self.node.remove_freeze_listener(proc);
+        }
+    }
+}
+
+impl Process {
+    pub(crate) fn request_freeze_notif(
+        self: &Arc<Self>,
+        reader: &mut UserSliceReader,
+    ) -> Result<()> {
+        let hc = reader.read::<BinderHandleCookie>()?;
+        let handle = hc.handle;
+        let cookie = FreezeCookie(hc.cookie);
+
+        let msg = FreezeMessage::new(GFP_KERNEL)?;
+        let alloc = RBTreeNodeReservation::new(GFP_KERNEL)?;
+
+        let mut node_refs_guard = self.node_refs.lock();
+        let node_refs = &mut *node_refs_guard;
+        let Some(info) = node_refs.by_handle.get_mut(&handle) else {
+            pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION invalid ref {}\n", handle);
+            return Err(EINVAL);
+        };
+        if info.freeze().is_some() {
+            pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION already set\n");
+            return Err(EINVAL);
+        }
+        let node_ref = info.node_ref();
+        let freeze_entry = node_refs.freeze_listeners.entry(cookie);
+
+        if let rbtree::Entry::Occupied(ref dupe) = freeze_entry {
+            if !dupe.get().allow_duplicate(&node_ref.node) {
+                pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION duplicate cookie\n");
+                return Err(EINVAL);
+            }
+        }
+
+        // All failure paths must come before this call, and all modifications must come after this
+        // call.
+        node_ref.node.add_freeze_listener(self, GFP_KERNEL)?;
+
+        match freeze_entry {
+            rbtree::Entry::Vacant(entry) => {
+                entry.insert(
+                    FreezeListener {
+                        cookie,
+                        node: node_ref.node.clone(),
+                        last_is_frozen: None,
+                        is_pending: false,
+                        is_clearing: false,
+                        num_pending_duplicates: 0,
+                        num_cleared_duplicates: 0,
+                    },
+                    alloc,
+                );
+            }
+            rbtree::Entry::Occupied(mut dupe) => {
+                let dupe = dupe.get_mut();
+                if dupe.is_pending {
+                    dupe.num_pending_duplicates += 1;
+                } else {
+                    dupe.num_cleared_duplicates += 1;
+                }
+                dupe.last_is_frozen = None;
+                dupe.is_pending = false;
+                dupe.is_clearing = false;
+            }
+        }
+
+        *info.freeze() = Some(cookie);
+        let msg = FreezeMessage::init(msg, cookie);
+        drop(node_refs_guard);
+        let _ = self.push_work(msg);
+        Ok(())
+    }
+
+    pub(crate) fn freeze_notif_done(self: &Arc<Self>, reader: &mut UserSliceReader) -> Result<()> {
+        let cookie = FreezeCookie(reader.read()?);
+        let alloc = FreezeMessage::new(GFP_KERNEL)?;
+        let mut node_refs_guard = self.node_refs.lock();
+        let node_refs = &mut *node_refs_guard;
+        let Some(freeze) = node_refs.freeze_listeners.get_mut(&cookie) else {
+            pr_warn!("BC_FREEZE_NOTIFICATION_DONE {:016x} not found\n", cookie.0);
+            return Err(EINVAL);
+        };
+        let mut clear_msg = None;
+        if freeze.num_pending_duplicates > 0 {
+            clear_msg = Some(FreezeMessage::init(alloc, cookie));
+            freeze.num_pending_duplicates -= 1;
+            freeze.num_cleared_duplicates += 1;
+        } else {
+            if !freeze.is_pending {
+                pr_warn!(
+                    "BC_FREEZE_NOTIFICATION_DONE {:016x} not pending\n",
+                    cookie.0
+                );
+                return Err(EINVAL);
+            }
+            if freeze.is_clearing {
+                // Immediately send another FreezeMessage for BR_CLEAR_FREEZE_NOTIFICATION_DONE.
+                clear_msg = Some(FreezeMessage::init(alloc, cookie));
+            }
+            freeze.is_pending = false;
+        }
+        drop(node_refs_guard);
+        if let Some(clear_msg) = clear_msg {
+            let _ = self.push_work(clear_msg);
+        }
+        Ok(())
+    }
+
+    pub(crate) fn clear_freeze_notif(self: &Arc<Self>, reader: &mut UserSliceReader) -> Result<()> {
+        let hc = reader.read::<BinderHandleCookie>()?;
+        let handle = hc.handle;
+        let cookie = FreezeCookie(hc.cookie);
+
+        let alloc = FreezeMessage::new(GFP_KERNEL)?;
+        let mut node_refs_guard = self.node_refs.lock();
+        let node_refs = &mut *node_refs_guard;
+        let Some(info) = node_refs.by_handle.get_mut(&handle) else {
+            pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION invalid ref {}\n", handle);
+            return Err(EINVAL);
+        };
+        let Some(info_cookie) = info.freeze() else {
+            pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION freeze notification not active\n");
+            return Err(EINVAL);
+        };
+        if *info_cookie != cookie {
+            pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION freeze notification cookie mismatch\n");
+            return Err(EINVAL);
+        }
+        let Some(listener) = node_refs.freeze_listeners.get_mut(&cookie) else {
+            pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION invalid cookie {}\n", handle);
+            return Err(EINVAL);
+        };
+        listener.is_clearing = true;
+        listener.node.remove_freeze_listener(self);
+        *info.freeze() = None;
+        let mut msg = None;
+        if !listener.is_pending {
+            msg = Some(FreezeMessage::init(alloc, cookie));
+        }
+        drop(node_refs_guard);
+
+        if let Some(msg) = msg {
+            let _ = self.push_work(msg);
+        }
+        Ok(())
+    }
+
+    fn get_freeze_cookie(&self, node: &DArc<Node>) -> Option<FreezeCookie> {
+        let node_refs = &mut *self.node_refs.lock();
+        let handle = node_refs.by_node.get(&node.global_id())?;
+        let node_ref = node_refs.by_handle.get_mut(handle)?;
+        *node_ref.freeze()
+    }
+
+    /// Creates a vector of every freeze listener on this process.
+    ///
+    /// Returns pairs of the remote process listening for notifications and the local node it is
+    /// listening on.
+    #[expect(clippy::type_complexity)]
+    fn find_freeze_recipients(&self) -> Result<KVVec<(DArc<Node>, Arc<Process>)>, AllocError> {
+        // Defined before `inner` to drop after releasing spinlock if `push_within_capacity` fails.
+        let mut node_proc_pair;
+
+        // We pre-allocate space for up to 8 recipients before we take the spinlock. However, if
+        // the allocation fails, use a vector with a capacity of zero instead of failing. After
+        // all, there might not be any freeze listeners, in which case this operation could still
+        // succeed.
+        let mut recipients =
+            KVVec::with_capacity(8, GFP_KERNEL).unwrap_or_else(|_err| KVVec::new());
+
+        let mut inner = self.lock_with_nodes();
+        let mut curr = inner.nodes.cursor_front();
+        while let Some(cursor) = curr {
+            let (key, node) = cursor.current();
+            let key = *key;
+            let list = node.freeze_list(&inner.inner);
+            let len = list.len();
+
+            if recipients.spare_capacity_mut().len() < len {
+                drop(inner);
+                recipients.reserve(len, GFP_KERNEL)?;
+                inner = self.lock_with_nodes();
+                // Find the node we were looking at and try again. If the set of nodes was changed,
+                // then just proceed to the next node. This is ok because we don't guarantee the
+                // inclusion of nodes that are added or removed in parallel with this operation.
+                curr = inner.nodes.cursor_lower_bound(&key);
+                continue;
+            }
+
+            for proc in list {
+                node_proc_pair = (node.clone(), proc.clone());
+                recipients
+                    .push_within_capacity(node_proc_pair)
+                    .map_err(|_| {
+                        pr_err!(
+                            "push_within_capacity failed even though we checked the capacity\n"
+                        );
+                        AllocError
+                    })?;
+            }
+
+            curr = cursor.move_next();
+        }
+        Ok(recipients)
+    }
+
+    /// Prepare allocations for sending freeze messages.
+    pub(crate) fn prepare_freeze_messages(&self) -> Result<FreezeMessages, AllocError> {
+        let recipients = self.find_freeze_recipients()?;
+        let mut batch = KVVec::with_capacity(recipients.len(), GFP_KERNEL)?;
+        for (node, proc) in recipients {
+            let Some(cookie) = proc.get_freeze_cookie(&node) else {
+                // If the freeze listener was removed in the meantime, just discard the
+                // notification.
+                continue;
+            };
+            let msg_alloc = FreezeMessage::new(GFP_KERNEL)?;
+            let msg = FreezeMessage::init(msg_alloc, cookie);
+            batch.push((proc, msg), GFP_KERNEL)?;
+        }
+
+        Ok(FreezeMessages { batch })
+    }
+}
+
+pub(crate) struct FreezeMessages {
+    batch: KVVec<(Arc<Process>, DLArc<FreezeMessage>)>,
+}
+
+impl FreezeMessages {
+    pub(crate) fn send_messages(self) {
+        for (proc, msg) in self.batch {
+            let _ = proc.push_work(msg);
+        }
+    }
+}
diff --git a/drivers/android/binder/node.rs b/drivers/android/binder/node.rs
new file mode 100644
index 000000000000..ade895ef791e
--- /dev/null
+++ b/drivers/android/binder/node.rs
@@ -0,0 +1,1131 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{
+    list::{AtomicTracker, List, ListArc, ListLinks, TryNewListArc},
+    prelude::*,
+    seq_file::SeqFile,
+    seq_print,
+    sync::lock::{spinlock::SpinLockBackend, Guard},
+    sync::{Arc, LockedBy, SpinLock},
+};
+
+use crate::{
+    defs::*,
+    error::BinderError,
+    process::{NodeRefInfo, Process, ProcessInner},
+    thread::Thread,
+    transaction::Transaction,
+    BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead,
+};
+
+use core::mem;
+
+mod wrapper;
+pub(crate) use self::wrapper::CritIncrWrapper;
+
+#[derive(Debug)]
+pub(crate) struct CouldNotDeliverCriticalIncrement;
+
+/// Keeps track of how this node is scheduled.
+///
+/// There are two ways to schedule a node to a work list. Just schedule the node itself, or
+/// allocate a wrapper that references the node and schedule the wrapper. These wrappers exists to
+/// make it possible to "move" a node from one list to another - when `do_work` is called directly
+/// on the `Node`, then it's a no-op if there's also a pending wrapper.
+///
+/// Wrappers are generally only needed for zero-to-one refcount increments, and there are two cases
+/// of this: weak increments and strong increments. We call such increments "critical" because it
+/// is critical that they are delivered to the thread doing the increment. Some examples:
+///
+/// * One thread makes a zero-to-one strong increment, and another thread makes a zero-to-one weak
+///   increment. Delivering the node to the thread doing the weak increment is wrong, since the
+///   thread doing the strong increment may have ended a long time ago when the command is actually
+///   processed by userspace.
+///
+/// * We have a weak reference and are about to drop it on one thread. But then another thread does
+///   a zero-to-one strong increment. If the strong increment gets sent to the thread that was
+///   about to drop the weak reference, then the strong increment could be processed after the
+///   other thread has already exited, which would be too late.
+///
+/// Note that trying to create a `ListArc` to the node can succeed even if `has_normal_push` is
+/// set. This is because another thread might just have popped the node from a todo list, but not
+/// yet called `do_work`. However, if `has_normal_push` is false, then creating a `ListArc` should
+/// always succeed.
+///
+/// Like the other fields in `NodeInner`, the delivery state is protected by the process lock.
+struct DeliveryState {
+    /// Is the `Node` currently scheduled?
+    has_pushed_node: bool,
+
+    /// Is a wrapper currently scheduled?
+    ///
+    /// The wrapper is used only for strong zero2one increments.
+    has_pushed_wrapper: bool,
+
+    /// Is the currently scheduled `Node` scheduled due to a weak zero2one increment?
+    ///
+    /// Weak zero2one operations are always scheduled using the `Node`.
+    has_weak_zero2one: bool,
+
+    /// Is the currently scheduled wrapper/`Node` scheduled due to a strong zero2one increment?
+    ///
+    /// If `has_pushed_wrapper` is set, then the strong zero2one increment was scheduled using the
+    /// wrapper. Otherwise, `has_pushed_node` must be set and it was scheduled using the `Node`.
+    has_strong_zero2one: bool,
+}
+
+impl DeliveryState {
+    fn should_normal_push(&self) -> bool {
+        !self.has_pushed_node && !self.has_pushed_wrapper
+    }
+
+    fn did_normal_push(&mut self) {
+        assert!(self.should_normal_push());
+        self.has_pushed_node = true;
+    }
+
+    fn should_push_weak_zero2one(&self) -> bool {
+        !self.has_weak_zero2one && !self.has_strong_zero2one
+    }
+
+    fn can_push_weak_zero2one_normally(&self) -> bool {
+        !self.has_pushed_node
+    }
+
+    fn did_push_weak_zero2one(&mut self) {
+        assert!(self.should_push_weak_zero2one());
+        assert!(self.can_push_weak_zero2one_normally());
+        self.has_pushed_node = true;
+        self.has_weak_zero2one = true;
+    }
+
+    fn should_push_strong_zero2one(&self) -> bool {
+        !self.has_strong_zero2one
+    }
+
+    fn can_push_strong_zero2one_normally(&self) -> bool {
+        !self.has_pushed_node
+    }
+
+    fn did_push_strong_zero2one(&mut self) {
+        assert!(self.should_push_strong_zero2one());
+        assert!(self.can_push_strong_zero2one_normally());
+        self.has_pushed_node = true;
+        self.has_strong_zero2one = true;
+    }
+
+    fn did_push_strong_zero2one_wrapper(&mut self) {
+        assert!(self.should_push_strong_zero2one());
+        assert!(!self.can_push_strong_zero2one_normally());
+        self.has_pushed_wrapper = true;
+        self.has_strong_zero2one = true;
+    }
+}
+
+struct CountState {
+    /// The reference count.
+    count: usize,
+    /// Whether the process that owns this node thinks that we hold a refcount on it. (Note that
+    /// even if count is greater than one, we only increment it once in the owning process.)
+    has_count: bool,
+}
+
+impl CountState {
+    fn new() -> Self {
+        Self {
+            count: 0,
+            has_count: false,
+        }
+    }
+}
+
+struct NodeInner {
+    /// Strong refcounts held on this node by `NodeRef` objects.
+    strong: CountState,
+    /// Weak refcounts held on this node by `NodeRef` objects.
+    weak: CountState,
+    delivery_state: DeliveryState,
+    /// The binder driver guarantees that oneway transactions sent to the same node are serialized,
+    /// that is, userspace will not be given the next one until it has finished processing the
+    /// previous oneway transaction. This is done to avoid the case where two oneway transactions
+    /// arrive in opposite order from the order in which they were sent. (E.g., they could be
+    /// delivered to two different threads, which could appear as-if they were sent in opposite
+    /// order.)
+    ///
+    /// To fix that, we store pending oneway transactions in a separate list in the node, and don't
+    /// deliver the next oneway transaction until userspace signals that it has finished processing
+    /// the previous oneway transaction by calling the `BC_FREE_BUFFER` ioctl.
+    oneway_todo: List<DTRWrap<Transaction>>,
+    /// Keeps track of whether this node has a pending oneway transaction.
+    ///
+    /// When this is true, incoming oneway transactions are stored in `oneway_todo`, instead of
+    /// being delivered directly to the process.
+    has_oneway_transaction: bool,
+    /// List of processes to deliver a notification to when this node is destroyed (usually due to
+    /// the process dying).
+    death_list: List<DTRWrap<NodeDeath>, 1>,
+    /// List of processes to deliver freeze notifications to.
+    freeze_list: KVVec<Arc<Process>>,
+    /// The number of active BR_INCREFS or BR_ACQUIRE operations. (should be maximum two)
+    ///
+    /// If this is non-zero, then we postpone any BR_RELEASE or BR_DECREFS notifications until the
+    /// active operations have ended. This avoids the situation an increment and decrement get
+    /// reordered from userspace's perspective.
+    active_inc_refs: u8,
+    /// List of `NodeRefInfo` objects that reference this node.
+    refs: List<NodeRefInfo, { NodeRefInfo::LIST_NODE }>,
+}
+
+#[pin_data]
+pub(crate) struct Node {
+    pub(crate) debug_id: usize,
+    ptr: u64,
+    pub(crate) cookie: u64,
+    pub(crate) flags: u32,
+    pub(crate) owner: Arc<Process>,
+    inner: LockedBy<NodeInner, ProcessInner>,
+    #[pin]
+    links_track: AtomicTracker,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for Node {
+        tracked_by links_track: AtomicTracker;
+    }
+}
+
+// Make `oneway_todo` work.
+kernel::list::impl_list_item! {
+    impl ListItem<0> for DTRWrap<Transaction> {
+        using ListLinks { self.links.inner };
+    }
+}
+
+impl Node {
+    pub(crate) fn new(
+        ptr: u64,
+        cookie: u64,
+        flags: u32,
+        owner: Arc<Process>,
+    ) -> impl PinInit<Self> {
+        pin_init!(Self {
+            inner: LockedBy::new(
+                &owner.inner,
+                NodeInner {
+                    strong: CountState::new(),
+                    weak: CountState::new(),
+                    delivery_state: DeliveryState {
+                        has_pushed_node: false,
+                        has_pushed_wrapper: false,
+                        has_weak_zero2one: false,
+                        has_strong_zero2one: false,
+                    },
+                    death_list: List::new(),
+                    oneway_todo: List::new(),
+                    freeze_list: KVVec::new(),
+                    has_oneway_transaction: false,
+                    active_inc_refs: 0,
+                    refs: List::new(),
+                },
+            ),
+            debug_id: super::next_debug_id(),
+            ptr,
+            cookie,
+            flags,
+            owner,
+            links_track <- AtomicTracker::new(),
+        })
+    }
+
+    pub(crate) fn has_oneway_transaction(&self, owner_inner: &mut ProcessInner) -> bool {
+        let inner = self.inner.access_mut(owner_inner);
+        inner.has_oneway_transaction
+    }
+
+    #[inline(never)]
+    pub(crate) fn full_debug_print(
+        &self,
+        m: &SeqFile,
+        owner_inner: &mut ProcessInner,
+    ) -> Result<()> {
+        let inner = self.inner.access_mut(owner_inner);
+        seq_print!(
+            m,
+            "  node {}: u{:016x} c{:016x} hs {} hw {} cs {} cw {}",
+            self.debug_id,
+            self.ptr,
+            self.cookie,
+            inner.strong.has_count,
+            inner.weak.has_count,
+            inner.strong.count,
+            inner.weak.count,
+        );
+        if !inner.refs.is_empty() {
+            seq_print!(m, " proc");
+            for node_ref in &inner.refs {
+                seq_print!(m, " {}", node_ref.process.task.pid());
+            }
+        }
+        seq_print!(m, "\n");
+        for t in &inner.oneway_todo {
+            t.debug_print_inner(m, "    pending async transaction ");
+        }
+        Ok(())
+    }
+
+    /// Insert the `NodeRef` into this `refs` list.
+    ///
+    /// # Safety
+    ///
+    /// It must be the case that `info.node_ref.node` is this node.
+    pub(crate) unsafe fn insert_node_info(
+        &self,
+        info: ListArc<NodeRefInfo, { NodeRefInfo::LIST_NODE }>,
+    ) {
+        self.inner
+            .access_mut(&mut self.owner.inner.lock())
+            .refs
+            .push_front(info);
+    }
+
+    /// Insert the `NodeRef` into this `refs` list.
+    ///
+    /// # Safety
+    ///
+    /// It must be the case that `info.node_ref.node` is this node.
+    pub(crate) unsafe fn remove_node_info(
+        &self,
+        info: &NodeRefInfo,
+    ) -> Option<ListArc<NodeRefInfo, { NodeRefInfo::LIST_NODE }>> {
+        // SAFETY: We always insert `NodeRefInfo` objects into the `refs` list of the node that it
+        // references in `info.node_ref.node`. That is this node, so `info` cannot possibly be in
+        // the `refs` list of another node.
+        unsafe {
+            self.inner
+                .access_mut(&mut self.owner.inner.lock())
+                .refs
+                .remove(info)
+        }
+    }
+
+    /// An id that is unique across all binder nodes on the system. Used as the key in the
+    /// `by_node` map.
+    pub(crate) fn global_id(&self) -> usize {
+        self as *const Node as usize
+    }
+
+    pub(crate) fn get_id(&self) -> (u64, u64) {
+        (self.ptr, self.cookie)
+    }
+
+    pub(crate) fn add_death(
+        &self,
+        death: ListArc<DTRWrap<NodeDeath>, 1>,
+        guard: &mut Guard<'_, ProcessInner, SpinLockBackend>,
+    ) {
+        self.inner.access_mut(guard).death_list.push_back(death);
+    }
+
+    pub(crate) fn inc_ref_done_locked(
+        self: &DArc<Node>,
+        _strong: bool,
+        owner_inner: &mut ProcessInner,
+    ) -> Option<DLArc<Node>> {
+        let inner = self.inner.access_mut(owner_inner);
+        if inner.active_inc_refs == 0 {
+            pr_err!("inc_ref_done called when no active inc_refs");
+            return None;
+        }
+
+        inner.active_inc_refs -= 1;
+        if inner.active_inc_refs == 0 {
+            // Having active inc_refs can inhibit dropping of ref-counts. Calculate whether we
+            // would send a refcount decrement, and if so, tell the caller to schedule us.
+            let strong = inner.strong.count > 0;
+            let has_strong = inner.strong.has_count;
+            let weak = strong || inner.weak.count > 0;
+            let has_weak = inner.weak.has_count;
+
+            let should_drop_weak = !weak && has_weak;
+            let should_drop_strong = !strong && has_strong;
+
+            // If we want to drop the ref-count again, tell the caller to schedule a work node for
+            // that.
+            let need_push = should_drop_weak || should_drop_strong;
+
+            if need_push && inner.delivery_state.should_normal_push() {
+                let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap();
+                inner.delivery_state.did_normal_push();
+                Some(list_arc)
+            } else {
+                None
+            }
+        } else {
+            None
+        }
+    }
+
+    pub(crate) fn update_refcount_locked(
+        self: &DArc<Node>,
+        inc: bool,
+        strong: bool,
+        count: usize,
+        owner_inner: &mut ProcessInner,
+    ) -> Option<DLArc<Node>> {
+        let is_dead = owner_inner.is_dead;
+        let inner = self.inner.access_mut(owner_inner);
+
+        // Get a reference to the state we'll update.
+        let state = if strong {
+            &mut inner.strong
+        } else {
+            &mut inner.weak
+        };
+
+        // Update the count and determine whether we need to push work.
+        let need_push = if inc {
+            state.count += count;
+            // TODO: This method shouldn't be used for zero-to-one increments.
+            !is_dead && !state.has_count
+        } else {
+            if state.count < count {
+                pr_err!("Failure: refcount underflow!");
+                return None;
+            }
+            state.count -= count;
+            !is_dead && state.count == 0 && state.has_count
+        };
+
+        if need_push && inner.delivery_state.should_normal_push() {
+            let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap();
+            inner.delivery_state.did_normal_push();
+            Some(list_arc)
+        } else {
+            None
+        }
+    }
+
+    pub(crate) fn incr_refcount_allow_zero2one(
+        self: &DArc<Self>,
+        strong: bool,
+        owner_inner: &mut ProcessInner,
+    ) -> Result<Option<DLArc<Node>>, CouldNotDeliverCriticalIncrement> {
+        let is_dead = owner_inner.is_dead;
+        let inner = self.inner.access_mut(owner_inner);
+
+        // Get a reference to the state we'll update.
+        let state = if strong {
+            &mut inner.strong
+        } else {
+            &mut inner.weak
+        };
+
+        // Update the count and determine whether we need to push work.
+        state.count += 1;
+        if is_dead || state.has_count {
+            return Ok(None);
+        }
+
+        // Userspace needs to be notified of this.
+        if !strong && inner.delivery_state.should_push_weak_zero2one() {
+            assert!(inner.delivery_state.can_push_weak_zero2one_normally());
+            let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap();
+            inner.delivery_state.did_push_weak_zero2one();
+            Ok(Some(list_arc))
+        } else if strong && inner.delivery_state.should_push_strong_zero2one() {
+            if inner.delivery_state.can_push_strong_zero2one_normally() {
+                let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap();
+                inner.delivery_state.did_push_strong_zero2one();
+                Ok(Some(list_arc))
+            } else {
+                state.count -= 1;
+                Err(CouldNotDeliverCriticalIncrement)
+            }
+        } else {
+            // Work is already pushed, and we don't need to push again.
+            Ok(None)
+        }
+    }
+
+    pub(crate) fn incr_refcount_allow_zero2one_with_wrapper(
+        self: &DArc<Self>,
+        strong: bool,
+        wrapper: CritIncrWrapper,
+        owner_inner: &mut ProcessInner,
+    ) -> Option<DLArc<dyn DeliverToRead>> {
+        match self.incr_refcount_allow_zero2one(strong, owner_inner) {
+            Ok(Some(node)) => Some(node as _),
+            Ok(None) => None,
+            Err(CouldNotDeliverCriticalIncrement) => {
+                assert!(strong);
+                let inner = self.inner.access_mut(owner_inner);
+                inner.strong.count += 1;
+                inner.delivery_state.did_push_strong_zero2one_wrapper();
+                Some(wrapper.init(self.clone()))
+            }
+        }
+    }
+
+    pub(crate) fn update_refcount(self: &DArc<Self>, inc: bool, count: usize, strong: bool) {
+        self.owner
+            .inner
+            .lock()
+            .update_node_refcount(self, inc, strong, count, None);
+    }
+
+    pub(crate) fn populate_counts(
+        &self,
+        out: &mut BinderNodeInfoForRef,
+        guard: &Guard<'_, ProcessInner, SpinLockBackend>,
+    ) {
+        let inner = self.inner.access(guard);
+        out.strong_count = inner.strong.count as _;
+        out.weak_count = inner.weak.count as _;
+    }
+
+    pub(crate) fn populate_debug_info(
+        &self,
+        out: &mut BinderNodeDebugInfo,
+        guard: &Guard<'_, ProcessInner, SpinLockBackend>,
+    ) {
+        out.ptr = self.ptr as _;
+        out.cookie = self.cookie as _;
+        let inner = self.inner.access(guard);
+        if inner.strong.has_count {
+            out.has_strong_ref = 1;
+        }
+        if inner.weak.has_count {
+            out.has_weak_ref = 1;
+        }
+    }
+
+    pub(crate) fn force_has_count(&self, guard: &mut Guard<'_, ProcessInner, SpinLockBackend>) {
+        let inner = self.inner.access_mut(guard);
+        inner.strong.has_count = true;
+        inner.weak.has_count = true;
+    }
+
+    fn write(&self, writer: &mut BinderReturnWriter<'_>, code: u32) -> Result {
+        writer.write_code(code)?;
+        writer.write_payload(&self.ptr)?;
+        writer.write_payload(&self.cookie)?;
+        Ok(())
+    }
+
+    pub(crate) fn submit_oneway(
+        &self,
+        transaction: DLArc<Transaction>,
+        guard: &mut Guard<'_, ProcessInner, SpinLockBackend>,
+    ) -> Result<(), (BinderError, DLArc<dyn DeliverToRead>)> {
+        if guard.is_dead {
+            return Err((BinderError::new_dead(), transaction));
+        }
+
+        let inner = self.inner.access_mut(guard);
+        if inner.has_oneway_transaction {
+            inner.oneway_todo.push_back(transaction);
+        } else {
+            inner.has_oneway_transaction = true;
+            guard.push_work(transaction)?;
+        }
+        Ok(())
+    }
+
+    pub(crate) fn release(&self) {
+        let mut guard = self.owner.inner.lock();
+        while let Some(work) = self.inner.access_mut(&mut guard).oneway_todo.pop_front() {
+            drop(guard);
+            work.into_arc().cancel();
+            guard = self.owner.inner.lock();
+        }
+
+        let death_list = core::mem::take(&mut self.inner.access_mut(&mut guard).death_list);
+        drop(guard);
+        for death in death_list {
+            death.into_arc().set_dead();
+        }
+    }
+
+    pub(crate) fn pending_oneway_finished(&self) {
+        let mut guard = self.owner.inner.lock();
+        if guard.is_dead {
+            // Cleanup will happen in `Process::deferred_release`.
+            return;
+        }
+
+        let inner = self.inner.access_mut(&mut guard);
+
+        let transaction = inner.oneway_todo.pop_front();
+        inner.has_oneway_transaction = transaction.is_some();
+        if let Some(transaction) = transaction {
+            match guard.push_work(transaction) {
+                Ok(()) => {}
+                Err((_err, work)) => {
+                    // Process is dead.
+                    // This shouldn't happen due to the `is_dead` check, but if it does, just drop
+                    // the transaction and return.
+                    drop(guard);
+                    drop(work);
+                }
+            }
+        }
+    }
+
+    /// Finds an outdated transaction that the given transaction can replace.
+    ///
+    /// If one is found, it is removed from the list and returned.
+    pub(crate) fn take_outdated_transaction(
+        &self,
+        new: &Transaction,
+        guard: &mut Guard<'_, ProcessInner, SpinLockBackend>,
+    ) -> Option<DLArc<Transaction>> {
+        let inner = self.inner.access_mut(guard);
+        let mut cursor = inner.oneway_todo.cursor_front();
+        while let Some(next) = cursor.peek_next() {
+            if new.can_replace(&next) {
+                return Some(next.remove());
+            }
+            cursor.move_next();
+        }
+        None
+    }
+
+    /// This is split into a separate function since it's called by both `Node::do_work` and
+    /// `NodeWrapper::do_work`.
+    fn do_work_locked(
+        &self,
+        writer: &mut BinderReturnWriter<'_>,
+        mut guard: Guard<'_, ProcessInner, SpinLockBackend>,
+    ) -> Result<bool> {
+        let inner = self.inner.access_mut(&mut guard);
+        let strong = inner.strong.count > 0;
+        let has_strong = inner.strong.has_count;
+        let weak = strong || inner.weak.count > 0;
+        let has_weak = inner.weak.has_count;
+
+        if weak && !has_weak {
+            inner.weak.has_count = true;
+            inner.active_inc_refs += 1;
+        }
+
+        if strong && !has_strong {
+            inner.strong.has_count = true;
+            inner.active_inc_refs += 1;
+        }
+
+        let no_active_inc_refs = inner.active_inc_refs == 0;
+        let should_drop_weak = no_active_inc_refs && (!weak && has_weak);
+        let should_drop_strong = no_active_inc_refs && (!strong && has_strong);
+        if should_drop_weak {
+            inner.weak.has_count = false;
+        }
+        if should_drop_strong {
+            inner.strong.has_count = false;
+        }
+        if no_active_inc_refs && !weak {
+            // Remove the node if there are no references to it.
+            guard.remove_node(self.ptr);
+        }
+        drop(guard);
+
+        if weak && !has_weak {
+            self.write(writer, BR_INCREFS)?;
+        }
+        if strong && !has_strong {
+            self.write(writer, BR_ACQUIRE)?;
+        }
+        if should_drop_strong {
+            self.write(writer, BR_RELEASE)?;
+        }
+        if should_drop_weak {
+            self.write(writer, BR_DECREFS)?;
+        }
+
+        Ok(true)
+    }
+
+    pub(crate) fn add_freeze_listener(
+        &self,
+        process: &Arc<Process>,
+        flags: kernel::alloc::Flags,
+    ) -> Result {
+        let mut vec_alloc = KVVec::<Arc<Process>>::new();
+        loop {
+            let mut guard = self.owner.inner.lock();
+            // Do not check for `guard.dead`. The `dead` flag that matters here is the owner of the
+            // listener, no the target.
+            let inner = self.inner.access_mut(&mut guard);
+            let len = inner.freeze_list.len();
+            if len >= inner.freeze_list.capacity() {
+                if len >= vec_alloc.capacity() {
+                    drop(guard);
+                    vec_alloc = KVVec::with_capacity((1 + len).next_power_of_two(), flags)?;
+                    continue;
+                }
+                mem::swap(&mut inner.freeze_list, &mut vec_alloc);
+                for elem in vec_alloc.drain_all() {
+                    inner.freeze_list.push_within_capacity(elem)?;
+                }
+            }
+            inner.freeze_list.push_within_capacity(process.clone())?;
+            return Ok(());
+        }
+    }
+
+    pub(crate) fn remove_freeze_listener(&self, p: &Arc<Process>) {
+        let _unused_capacity;
+        let mut guard = self.owner.inner.lock();
+        let inner = self.inner.access_mut(&mut guard);
+        let len = inner.freeze_list.len();
+        inner.freeze_list.retain(|proc| !Arc::ptr_eq(proc, p));
+        if len == inner.freeze_list.len() {
+            pr_warn!(
+                "Could not remove freeze listener for {}\n",
+                p.pid_in_current_ns()
+            );
+        }
+        if inner.freeze_list.is_empty() {
+            _unused_capacity = mem::replace(&mut inner.freeze_list, KVVec::new());
+        }
+    }
+
+    pub(crate) fn freeze_list<'a>(&'a self, guard: &'a ProcessInner) -> &'a [Arc<Process>] {
+        &self.inner.access(guard).freeze_list
+    }
+}
+
+impl DeliverToRead for Node {
+    fn do_work(
+        self: DArc<Self>,
+        _thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let mut owner_inner = self.owner.inner.lock();
+        let inner = self.inner.access_mut(&mut owner_inner);
+
+        assert!(inner.delivery_state.has_pushed_node);
+        if inner.delivery_state.has_pushed_wrapper {
+            // If the wrapper is scheduled, then we are either a normal push or weak zero2one
+            // increment, and the wrapper is a strong zero2one increment, so the wrapper always
+            // takes precedence over us.
+            assert!(inner.delivery_state.has_strong_zero2one);
+            inner.delivery_state.has_pushed_node = false;
+            inner.delivery_state.has_weak_zero2one = false;
+            return Ok(true);
+        }
+
+        inner.delivery_state.has_pushed_node = false;
+        inner.delivery_state.has_weak_zero2one = false;
+        inner.delivery_state.has_strong_zero2one = false;
+
+        self.do_work_locked(writer, owner_inner)
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    #[inline(never)]
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        seq_print!(
+            m,
+            "{}node work {}: u{:016x} c{:016x}\n",
+            prefix,
+            self.debug_id,
+            self.ptr,
+            self.cookie,
+        );
+        Ok(())
+    }
+}
+
+/// Represents something that holds one or more ref-counts to a `Node`.
+///
+/// Whenever process A holds a refcount to a node owned by a different process B, then process A
+/// will store a `NodeRef` that refers to the `Node` in process B. When process A releases the
+/// refcount, we destroy the NodeRef, which decrements the ref-count in process A.
+///
+/// This type is also used for some other cases. For example, a transaction allocation holds a
+/// refcount on the target node, and this is implemented by storing a `NodeRef` in the allocation
+/// so that the destructor of the allocation will drop a refcount of the `Node`.
+pub(crate) struct NodeRef {
+    pub(crate) node: DArc<Node>,
+    /// How many times does this NodeRef hold a refcount on the Node?
+    strong_node_count: usize,
+    weak_node_count: usize,
+    /// How many times does userspace hold a refcount on this NodeRef?
+    strong_count: usize,
+    weak_count: usize,
+}
+
+impl NodeRef {
+    pub(crate) fn new(node: DArc<Node>, strong_count: usize, weak_count: usize) -> Self {
+        Self {
+            node,
+            strong_node_count: strong_count,
+            weak_node_count: weak_count,
+            strong_count,
+            weak_count,
+        }
+    }
+
+    pub(crate) fn absorb(&mut self, mut other: Self) {
+        assert!(
+            Arc::ptr_eq(&self.node, &other.node),
+            "absorb called with differing nodes"
+        );
+        self.strong_node_count += other.strong_node_count;
+        self.weak_node_count += other.weak_node_count;
+        self.strong_count += other.strong_count;
+        self.weak_count += other.weak_count;
+        other.strong_count = 0;
+        other.weak_count = 0;
+        other.strong_node_count = 0;
+        other.weak_node_count = 0;
+
+        if self.strong_node_count >= 2 || self.weak_node_count >= 2 {
+            let mut guard = self.node.owner.inner.lock();
+            let inner = self.node.inner.access_mut(&mut guard);
+
+            if self.strong_node_count >= 2 {
+                inner.strong.count -= self.strong_node_count - 1;
+                self.strong_node_count = 1;
+                assert_ne!(inner.strong.count, 0);
+            }
+            if self.weak_node_count >= 2 {
+                inner.weak.count -= self.weak_node_count - 1;
+                self.weak_node_count = 1;
+                assert_ne!(inner.weak.count, 0);
+            }
+        }
+    }
+
+    pub(crate) fn get_count(&self) -> (usize, usize) {
+        (self.strong_count, self.weak_count)
+    }
+
+    pub(crate) fn clone(&self, strong: bool) -> Result<NodeRef> {
+        if strong && self.strong_count == 0 {
+            return Err(EINVAL);
+        }
+        Ok(self
+            .node
+            .owner
+            .inner
+            .lock()
+            .new_node_ref(self.node.clone(), strong, None))
+    }
+
+    /// Updates (increments or decrements) the number of references held against the node. If the
+    /// count being updated transitions from 0 to 1 or from 1 to 0, the node is notified by having
+    /// its `update_refcount` function called.
+    ///
+    /// Returns whether `self` should be removed (when both counts are zero).
+    pub(crate) fn update(&mut self, inc: bool, strong: bool) -> bool {
+        if strong && self.strong_count == 0 {
+            return false;
+        }
+        let (count, node_count, other_count) = if strong {
+            (
+                &mut self.strong_count,
+                &mut self.strong_node_count,
+                self.weak_count,
+            )
+        } else {
+            (
+                &mut self.weak_count,
+                &mut self.weak_node_count,
+                self.strong_count,
+            )
+        };
+        if inc {
+            if *count == 0 {
+                *node_count = 1;
+                self.node.update_refcount(true, 1, strong);
+            }
+            *count += 1;
+        } else {
+            if *count == 0 {
+                pr_warn!(
+                    "pid {} performed invalid decrement on ref\n",
+                    kernel::current!().pid()
+                );
+                return false;
+            }
+            *count -= 1;
+            if *count == 0 {
+                self.node.update_refcount(false, *node_count, strong);
+                *node_count = 0;
+                return other_count == 0;
+            }
+        }
+        false
+    }
+}
+
+impl Drop for NodeRef {
+    // This destructor is called conditionally from `Allocation::drop`. That branch is often
+    // mispredicted. Inlining this method call reduces the cost of those branch mispredictions.
+    #[inline(always)]
+    fn drop(&mut self) {
+        if self.strong_node_count > 0 {
+            self.node
+                .update_refcount(false, self.strong_node_count, true);
+        }
+        if self.weak_node_count > 0 {
+            self.node
+                .update_refcount(false, self.weak_node_count, false);
+        }
+    }
+}
+
+struct NodeDeathInner {
+    dead: bool,
+    cleared: bool,
+    notification_done: bool,
+    /// Indicates whether the normal flow was interrupted by removing the handle. In this case, we
+    /// need behave as if the death notification didn't exist (i.e., we don't deliver anything to
+    /// the user.
+    aborted: bool,
+}
+
+/// Used to deliver notifications when a process dies.
+///
+/// A process can request to be notified when a process dies using `BC_REQUEST_DEATH_NOTIFICATION`.
+/// This will make the driver send a `BR_DEAD_BINDER` to userspace when the process dies (or
+/// immediately if it is already dead). Userspace is supposed to respond with `BC_DEAD_BINDER_DONE`
+/// once it has processed the notification.
+///
+/// Userspace can unregister from death notifications using the `BC_CLEAR_DEATH_NOTIFICATION`
+/// command. In this case, the kernel will respond with `BR_CLEAR_DEATH_NOTIFICATION_DONE` once the
+/// notification has been removed. Note that if the remote process dies before the kernel has
+/// responded with `BR_CLEAR_DEATH_NOTIFICATION_DONE`, then the kernel will still send a
+/// `BR_DEAD_BINDER`, which userspace must be able to process. In this case, the kernel will wait
+/// for the `BC_DEAD_BINDER_DONE` command before it sends `BR_CLEAR_DEATH_NOTIFICATION_DONE`.
+///
+/// Note that even if the kernel sends a `BR_DEAD_BINDER`, this does not remove the death
+/// notification. Userspace must still remove it manually using `BC_CLEAR_DEATH_NOTIFICATION`.
+///
+/// If a process uses `BC_RELEASE` to destroy its last refcount on a node that has an active death
+/// registration, then the death registration is immediately deleted (we implement this using the
+/// `aborted` field). However, userspace is not supposed to delete a `NodeRef` without first
+/// deregistering death notifications, so this codepath is not executed under normal circumstances.
+#[pin_data]
+pub(crate) struct NodeDeath {
+    node: DArc<Node>,
+    process: Arc<Process>,
+    pub(crate) cookie: u64,
+    #[pin]
+    links_track: AtomicTracker<0>,
+    /// Used by the owner `Node` to store a list of registered death notifications.
+    ///
+    /// # Invariants
+    ///
+    /// Only ever used with the `death_list` list of `self.node`.
+    #[pin]
+    death_links: ListLinks<1>,
+    /// Used by the process to keep track of the death notifications for which we have sent a
+    /// `BR_DEAD_BINDER` but not yet received a `BC_DEAD_BINDER_DONE`.
+    ///
+    /// # Invariants
+    ///
+    /// Only ever used with the `delivered_deaths` list of `self.process`.
+    #[pin]
+    delivered_links: ListLinks<2>,
+    #[pin]
+    delivered_links_track: AtomicTracker<2>,
+    #[pin]
+    inner: SpinLock<NodeDeathInner>,
+}
+
+impl NodeDeath {
+    /// Constructs a new node death notification object.
+    pub(crate) fn new(
+        node: DArc<Node>,
+        process: Arc<Process>,
+        cookie: u64,
+    ) -> impl PinInit<DTRWrap<Self>> {
+        DTRWrap::new(pin_init!(
+            Self {
+                node,
+                process,
+                cookie,
+                links_track <- AtomicTracker::new(),
+                death_links <- ListLinks::new(),
+                delivered_links <- ListLinks::new(),
+                delivered_links_track <- AtomicTracker::new(),
+                inner <- kernel::new_spinlock!(NodeDeathInner {
+                    dead: false,
+                    cleared: false,
+                    notification_done: false,
+                    aborted: false,
+                }, "NodeDeath::inner"),
+            }
+        ))
+    }
+
+    /// Sets the cleared flag to `true`.
+    ///
+    /// It removes `self` from the node's death notification list if needed.
+    ///
+    /// Returns whether it needs to be queued.
+    pub(crate) fn set_cleared(self: &DArc<Self>, abort: bool) -> bool {
+        let (needs_removal, needs_queueing) = {
+            // Update state and determine if we need to queue a work item. We only need to do it
+            // when the node is not dead or if the user already completed the death notification.
+            let mut inner = self.inner.lock();
+            if abort {
+                inner.aborted = true;
+            }
+            if inner.cleared {
+                // Already cleared.
+                return false;
+            }
+            inner.cleared = true;
+            (!inner.dead, !inner.dead || inner.notification_done)
+        };
+
+        // Remove death notification from node.
+        if needs_removal {
+            let mut owner_inner = self.node.owner.inner.lock();
+            let node_inner = self.node.inner.access_mut(&mut owner_inner);
+            // SAFETY: A `NodeDeath` is never inserted into the death list of any node other than
+            // its owner, so it is either in this death list or in no death list.
+            unsafe { node_inner.death_list.remove(self) };
+        }
+        needs_queueing
+    }
+
+    /// Sets the 'notification done' flag to `true`.
+    pub(crate) fn set_notification_done(self: DArc<Self>, thread: &Thread) {
+        let needs_queueing = {
+            let mut inner = self.inner.lock();
+            inner.notification_done = true;
+            inner.cleared
+        };
+        if needs_queueing {
+            if let Some(death) = ListArc::try_from_arc_or_drop(self) {
+                let _ = thread.push_work_if_looper(death);
+            }
+        }
+    }
+
+    /// Sets the 'dead' flag to `true` and queues work item if needed.
+    pub(crate) fn set_dead(self: DArc<Self>) {
+        let needs_queueing = {
+            let mut inner = self.inner.lock();
+            if inner.cleared {
+                false
+            } else {
+                inner.dead = true;
+                true
+            }
+        };
+        if needs_queueing {
+            // Push the death notification to the target process. There is nothing else to do if
+            // it's already dead.
+            if let Some(death) = ListArc::try_from_arc_or_drop(self) {
+                let process = death.process.clone();
+                let _ = process.push_work(death);
+            }
+        }
+    }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for NodeDeath {
+        tracked_by links_track: AtomicTracker;
+    }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<1> for DTRWrap<NodeDeath> { untracked; }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<1> for DTRWrap<NodeDeath> {
+        using ListLinks { self.wrapped.death_links };
+    }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<2> for DTRWrap<NodeDeath> {
+        tracked_by wrapped: NodeDeath;
+    }
+}
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<2> for NodeDeath {
+        tracked_by delivered_links_track: AtomicTracker<2>;
+    }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<2> for DTRWrap<NodeDeath> {
+        using ListLinks { self.wrapped.delivered_links };
+    }
+}
+
+impl DeliverToRead for NodeDeath {
+    fn do_work(
+        self: DArc<Self>,
+        _thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let done = {
+            let inner = self.inner.lock();
+            if inner.aborted {
+                return Ok(true);
+            }
+            inner.cleared && (!inner.dead || inner.notification_done)
+        };
+
+        let cookie = self.cookie;
+        let cmd = if done {
+            BR_CLEAR_DEATH_NOTIFICATION_DONE
+        } else {
+            let process = self.process.clone();
+            let mut process_inner = process.inner.lock();
+            let inner = self.inner.lock();
+            if inner.aborted {
+                return Ok(true);
+            }
+            // We're still holding the inner lock, so it cannot be aborted while we insert it into
+            // the delivered list.
+            process_inner.death_delivered(self.clone());
+            BR_DEAD_BINDER
+        };
+
+        writer.write_code(cmd)?;
+        writer.write_payload(&cookie)?;
+        // DEAD_BINDER notifications can cause transactions, so stop processing work items when we
+        // get to a death notification.
+        Ok(cmd != BR_DEAD_BINDER)
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    #[inline(never)]
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        let inner = self.inner.lock();
+
+        let dead_binder = inner.dead && !inner.notification_done;
+
+        if dead_binder {
+            if inner.cleared {
+                seq_print!(m, "{}has cleared dead binder\n", prefix);
+            } else {
+                seq_print!(m, "{}has dead binder\n", prefix);
+            }
+        } else {
+            seq_print!(m, "{}has cleared death notification\n", prefix);
+        }
+
+        Ok(())
+    }
+}
diff --git a/drivers/android/binder/node/wrapper.rs b/drivers/android/binder/node/wrapper.rs
new file mode 100644
index 000000000000..43294c050502
--- /dev/null
+++ b/drivers/android/binder/node/wrapper.rs
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{list::ListArc, prelude::*, seq_file::SeqFile, seq_print, sync::UniqueArc};
+
+use crate::{node::Node, thread::Thread, BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead};
+
+use core::mem::MaybeUninit;
+
+pub(crate) struct CritIncrWrapper {
+    inner: UniqueArc<MaybeUninit<DTRWrap<NodeWrapper>>>,
+}
+
+impl CritIncrWrapper {
+    pub(crate) fn new() -> Result<Self> {
+        Ok(CritIncrWrapper {
+            inner: UniqueArc::new_uninit(GFP_KERNEL)?,
+        })
+    }
+
+    pub(super) fn init(self, node: DArc<Node>) -> DLArc<dyn DeliverToRead> {
+        match self.inner.pin_init_with(DTRWrap::new(NodeWrapper { node })) {
+            Ok(initialized) => ListArc::from(initialized) as _,
+            Err(err) => match err {},
+        }
+    }
+}
+
+struct NodeWrapper {
+    node: DArc<Node>,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for NodeWrapper {
+        untracked;
+    }
+}
+
+impl DeliverToRead for NodeWrapper {
+    fn do_work(
+        self: DArc<Self>,
+        _thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let node = &self.node;
+        let mut owner_inner = node.owner.inner.lock();
+        let inner = node.inner.access_mut(&mut owner_inner);
+
+        let ds = &mut inner.delivery_state;
+
+        assert!(ds.has_pushed_wrapper);
+        assert!(ds.has_strong_zero2one);
+        ds.has_pushed_wrapper = false;
+        ds.has_strong_zero2one = false;
+
+        node.do_work_locked(writer, owner_inner)
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    #[inline(never)]
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        seq_print!(
+            m,
+            "{}node work {}: u{:016x} c{:016x}\n",
+            prefix,
+            self.node.debug_id,
+            self.node.ptr,
+            self.node.cookie,
+        );
+        Ok(())
+    }
+}
diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
new file mode 100644
index 000000000000..9379038f61f5
--- /dev/null
+++ b/drivers/android/binder/page_range.rs
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! This module has utilities for managing a page range where unused pages may be reclaimed by a
+//! vma shrinker.
+
+// To avoid deadlocks, locks are taken in the order:
+//
+//  1. mmap lock
+//  2. spinlock
+//  3. lru spinlock
+//
+// The shrinker will use trylock methods because it locks them in a different order.
+
+use core::{
+    marker::PhantomPinned,
+    mem::{size_of, size_of_val, MaybeUninit},
+    ptr,
+};
+
+use kernel::{
+    bindings,
+    error::Result,
+    ffi::{c_ulong, c_void},
+    mm::{virt, Mm, MmWithUser},
+    new_mutex, new_spinlock,
+    page::{Page, PAGE_SHIFT, PAGE_SIZE},
+    prelude::*,
+    str::CStr,
+    sync::{aref::ARef, Mutex, SpinLock},
+    task::Pid,
+    transmute::FromBytes,
+    types::Opaque,
+    uaccess::UserSliceReader,
+};
+
+/// Represents a shrinker that can be registered with the kernel.
+///
+/// Each shrinker can be used by many `ShrinkablePageRange` objects.
+#[repr(C)]
+pub(crate) struct Shrinker {
+    inner: Opaque<*mut bindings::shrinker>,
+    list_lru: Opaque<bindings::list_lru>,
+}
+
+// SAFETY: The shrinker and list_lru are thread safe.
+unsafe impl Send for Shrinker {}
+// SAFETY: The shrinker and list_lru are thread safe.
+unsafe impl Sync for Shrinker {}
+
+impl Shrinker {
+    /// Create a new shrinker.
+    ///
+    /// # Safety
+    ///
+    /// Before using this shrinker with a `ShrinkablePageRange`, the `register` method must have
+    /// been called exactly once, and it must not have returned an error.
+    pub(crate) const unsafe fn new() -> Self {
+        Self {
+            inner: Opaque::uninit(),
+            list_lru: Opaque::uninit(),
+        }
+    }
+
+    /// Register this shrinker with the kernel.
+    pub(crate) fn register(&'static self, name: &CStr) -> Result<()> {
+        // SAFETY: These fields are not yet used, so it's okay to zero them.
+        unsafe {
+            self.inner.get().write(ptr::null_mut());
+            self.list_lru.get().write_bytes(0, 1);
+        }
+
+        // SAFETY: The field is not yet used, so we can initialize it.
+        let ret = unsafe { bindings::__list_lru_init(self.list_lru.get(), false, ptr::null_mut()) };
+        if ret != 0 {
+            return Err(Error::from_errno(ret));
+        }
+
+        // SAFETY: The `name` points at a valid c string.
+        let shrinker = unsafe { bindings::shrinker_alloc(0, name.as_char_ptr()) };
+        if shrinker.is_null() {
+            // SAFETY: We initialized it, so its okay to destroy it.
+            unsafe { bindings::list_lru_destroy(self.list_lru.get()) };
+            return Err(Error::from_errno(ret));
+        }
+
+        // SAFETY: We're about to register the shrinker, and these are the fields we need to
+        // initialize. (All other fields are already zeroed.)
+        unsafe {
+            (&raw mut (*shrinker).count_objects).write(Some(rust_shrink_count));
+            (&raw mut (*shrinker).scan_objects).write(Some(rust_shrink_scan));
+            (&raw mut (*shrinker).private_data).write(self.list_lru.get().cast());
+        }
+
+        // SAFETY: The new shrinker has been fully initialized, so we can register it.
+        unsafe { bindings::shrinker_register(shrinker) };
+
+        // SAFETY: This initializes the pointer to the shrinker so that we can use it.
+        unsafe { self.inner.get().write(shrinker) };
+
+        Ok(())
+    }
+}
+
+/// A container that manages a page range in a vma.
+///
+/// The pages can be thought of as an array of booleans of whether the pages are usable. The
+/// methods `use_range` and `stop_using_range` set all booleans in a range to true or false
+/// respectively. Initially, no pages are allocated. When a page is not used, it is not freed
+/// immediately. Instead, it is made available to the memory shrinker to free it if the device is
+/// under memory pressure.
+///
+/// It's okay for `use_range` and `stop_using_range` to race with each other, although there's no
+/// way to know whether an index ends up with true or false if a call to `use_range` races with
+/// another call to `stop_using_range` on a given index.
+///
+/// It's also okay for the two methods to race with themselves, e.g. if two threads call
+/// `use_range` on the same index, then that's fine and neither call will return until the page is
+/// allocated and mapped.
+///
+/// The methods that read or write to a range require that the page is marked as in use. So it is
+/// _not_ okay to call `stop_using_range` on a page that is in use by the methods that read or
+/// write to the page.
+#[pin_data(PinnedDrop)]
+pub(crate) struct ShrinkablePageRange {
+    /// Shrinker object registered with the kernel.
+    shrinker: &'static Shrinker,
+    /// Pid using this page range. Only used as debugging information.
+    pid: Pid,
+    /// The mm for the relevant process.
+    mm: ARef<Mm>,
+    /// Used to synchronize calls to `vm_insert_page` and `zap_page_range_single`.
+    #[pin]
+    mm_lock: Mutex<()>,
+    /// Spinlock protecting changes to pages.
+    #[pin]
+    lock: SpinLock<Inner>,
+
+    /// Must not move, since page info has pointers back.
+    #[pin]
+    _pin: PhantomPinned,
+}
+
+struct Inner {
+    /// Array of pages.
+    ///
+    /// Since this is also accessed by the shrinker, we can't use a `Box`, which asserts exclusive
+    /// ownership. To deal with that, we manage it using raw pointers.
+    pages: *mut PageInfo,
+    /// Length of the `pages` array.
+    size: usize,
+    /// The address of the vma to insert the pages into.
+    vma_addr: usize,
+}
+
+// SAFETY: proper locking is in place for `Inner`
+unsafe impl Send for Inner {}
+
+type StableMmGuard =
+    kernel::sync::lock::Guard<'static, (), kernel::sync::lock::mutex::MutexBackend>;
+
+/// An array element that describes the current state of a page.
+///
+/// There are three states:
+///
+///  * Free. The page is None. The `lru` element is not queued.
+///  * Available. The page is Some. The `lru` element is queued to the shrinker's lru.
+///  * Used. The page is Some. The `lru` element is not queued.
+///
+/// When an element is available, the shrinker is able to free the page.
+#[repr(C)]
+struct PageInfo {
+    lru: bindings::list_head,
+    page: Option<Page>,
+    range: *const ShrinkablePageRange,
+}
+
+impl PageInfo {
+    /// # Safety
+    ///
+    /// The caller ensures that writing to `me.page` is ok, and that the page is not currently set.
+    unsafe fn set_page(me: *mut PageInfo, page: Page) {
+        // SAFETY: This pointer offset is in bounds.
+        let ptr = unsafe { &raw mut (*me).page };
+
+        // SAFETY: The pointer is valid for writing, so also valid for reading.
+        if unsafe { (*ptr).is_some() } {
+            pr_err!("set_page called when there is already a page");
+            // SAFETY: We will initialize the page again below.
+            unsafe { ptr::drop_in_place(ptr) };
+        }
+
+        // SAFETY: The pointer is valid for writing.
+        unsafe { ptr::write(ptr, Some(page)) };
+    }
+
+    /// # Safety
+    ///
+    /// The caller ensures that reading from `me.page` is ok for the duration of 'a.
+    unsafe fn get_page<'a>(me: *const PageInfo) -> Option<&'a Page> {
+        // SAFETY: This pointer offset is in bounds.
+        let ptr = unsafe { &raw const (*me).page };
+
+        // SAFETY: The pointer is valid for reading.
+        unsafe { (*ptr).as_ref() }
+    }
+
+    /// # Safety
+    ///
+    /// The caller ensures that writing to `me.page` is ok for the duration of 'a.
+    unsafe fn take_page(me: *mut PageInfo) -> Option<Page> {
+        // SAFETY: This pointer offset is in bounds.
+        let ptr = unsafe { &raw mut (*me).page };
+
+        // SAFETY: The pointer is valid for reading.
+        unsafe { (*ptr).take() }
+    }
+
+    /// Add this page to the lru list, if not already in the list.
+    ///
+    /// # Safety
+    ///
+    /// The pointer must be valid, and it must be the right shrinker and nid.
+    unsafe fn list_lru_add(me: *mut PageInfo, nid: i32, shrinker: &'static Shrinker) {
+        // SAFETY: This pointer offset is in bounds.
+        let lru_ptr = unsafe { &raw mut (*me).lru };
+        // SAFETY: The lru pointer is valid, and we're not using it with any other lru list.
+        unsafe { bindings::list_lru_add(shrinker.list_lru.get(), lru_ptr, nid, ptr::null_mut()) };
+    }
+
+    /// Remove this page from the lru list, if it is in the list.
+    ///
+    /// # Safety
+    ///
+    /// The pointer must be valid, and it must be the right shrinker and nid.
+    unsafe fn list_lru_del(me: *mut PageInfo, nid: i32, shrinker: &'static Shrinker) {
+        // SAFETY: This pointer offset is in bounds.
+        let lru_ptr = unsafe { &raw mut (*me).lru };
+        // SAFETY: The lru pointer is valid, and we're not using it with any other lru list.
+        unsafe { bindings::list_lru_del(shrinker.list_lru.get(), lru_ptr, nid, ptr::null_mut()) };
+    }
+}
+
+impl ShrinkablePageRange {
+    /// Create a new `ShrinkablePageRange` using the given shrinker.
+    pub(crate) fn new(shrinker: &'static Shrinker) -> impl PinInit<Self, Error> {
+        try_pin_init!(Self {
+            shrinker,
+            pid: kernel::current!().pid(),
+            mm: ARef::from(&**kernel::current!().mm().ok_or(ESRCH)?),
+            mm_lock <- new_mutex!((), "ShrinkablePageRange::mm"),
+            lock <- new_spinlock!(Inner {
+                pages: ptr::null_mut(),
+                size: 0,
+                vma_addr: 0,
+            }, "ShrinkablePageRange"),
+            _pin: PhantomPinned,
+        })
+    }
+
+    pub(crate) fn stable_trylock_mm(&self) -> Option<StableMmGuard> {
+        // SAFETY: This extends the duration of the reference. Since this call happens before
+        // `mm_lock` is taken in the destructor of `ShrinkablePageRange`, the destructor will block
+        // until the returned guard is dropped. This ensures that the guard is valid until dropped.
+        let mm_lock = unsafe { &*ptr::from_ref(&self.mm_lock) };
+
+        mm_lock.try_lock()
+    }
+
+    /// Register a vma with this page range. Returns the size of the region.
+    pub(crate) fn register_with_vma(&self, vma: &virt::VmaNew) -> Result<usize> {
+        let num_bytes = usize::min(vma.end() - vma.start(), bindings::SZ_4M as usize);
+        let num_pages = num_bytes >> PAGE_SHIFT;
+
+        if !ptr::eq::<Mm>(&*self.mm, &**vma.mm()) {
+            pr_debug!("Failed to register with vma: invalid vma->vm_mm");
+            return Err(EINVAL);
+        }
+        if num_pages == 0 {
+            pr_debug!("Failed to register with vma: size zero");
+            return Err(EINVAL);
+        }
+
+        let mut pages = KVVec::<PageInfo>::with_capacity(num_pages, GFP_KERNEL)?;
+
+        // SAFETY: This just initializes the pages array.
+        unsafe {
+            let self_ptr = self as *const ShrinkablePageRange;
+            for i in 0..num_pages {
+                let info = pages.as_mut_ptr().add(i);
+                (&raw mut (*info).range).write(self_ptr);
+                (&raw mut (*info).page).write(None);
+                let lru = &raw mut (*info).lru;
+                (&raw mut (*lru).next).write(lru);
+                (&raw mut (*lru).prev).write(lru);
+            }
+        }
+
+        let mut inner = self.lock.lock();
+        if inner.size > 0 {
+            pr_debug!("Failed to register with vma: already registered");
+            drop(inner);
+            return Err(EBUSY);
+        }
+
+        inner.pages = pages.into_raw_parts().0;
+        inner.size = num_pages;
+        inner.vma_addr = vma.start();
+
+        Ok(num_pages)
+    }
+
+    /// Make sure that the given pages are allocated and mapped.
+    ///
+    /// Must not be called from an atomic context.
+    pub(crate) fn use_range(&self, start: usize, end: usize) -> Result<()> {
+        if start >= end {
+            return Ok(());
+        }
+        let mut inner = self.lock.lock();
+        assert!(end <= inner.size);
+
+        for i in start..end {
+            // SAFETY: This pointer offset is in bounds.
+            let page_info = unsafe { inner.pages.add(i) };
+
+            // SAFETY: The pointer is valid, and we hold the lock so reading from the page is okay.
+            if let Some(page) = unsafe { PageInfo::get_page(page_info) } {
+                // Since we're going to use the page, we should remove it from the lru list so that
+                // the shrinker will not free it.
+                //
+                // SAFETY: The pointer is valid, and this is the right shrinker.
+                //
+                // The shrinker can't free the page between the check and this call to
+                // `list_lru_del` because we hold the lock.
+                unsafe { PageInfo::list_lru_del(page_info, page.nid(), self.shrinker) };
+            } else {
+                // We have to allocate a new page. Use the slow path.
+                drop(inner);
+                // SAFETY: `i < end <= inner.size` so `i` is in bounds.
+                match unsafe { self.use_page_slow(i) } {
+                    Ok(()) => {}
+                    Err(err) => {
+                        pr_warn!("Error in use_page_slow: {:?}", err);
+                        return Err(err);
+                    }
+                }
+                inner = self.lock.lock();
+            }
+        }
+        Ok(())
+    }
+
+    /// Mark the given page as in use, slow path.
+    ///
+    /// Must not be called from an atomic context.
+    ///
+    /// # Safety
+    ///
+    /// Assumes that `i` is in bounds.
+    #[cold]
+    unsafe fn use_page_slow(&self, i: usize) -> Result<()> {
+        let new_page = Page::alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO)?;
+
+        let mm_mutex = self.mm_lock.lock();
+        let inner = self.lock.lock();
+
+        // SAFETY: This pointer offset is in bounds.
+        let page_info = unsafe { inner.pages.add(i) };
+
+        // SAFETY: The pointer is valid, and we hold the lock so reading from the page is okay.
+        if let Some(page) = unsafe { PageInfo::get_page(page_info) } {
+            // The page was already there, or someone else added the page while we didn't hold the
+            // spinlock.
+            //
+            // SAFETY: The pointer is valid, and this is the right shrinker.
+            //
+            // The shrinker can't free the page between the check and this call to
+            // `list_lru_del` because we hold the lock.
+            unsafe { PageInfo::list_lru_del(page_info, page.nid(), self.shrinker) };
+            return Ok(());
+        }
+
+        let vma_addr = inner.vma_addr;
+        // Release the spinlock while we insert the page into the vma.
+        drop(inner);
+
+        // No overflow since we stay in bounds of the vma.
+        let user_page_addr = vma_addr + (i << PAGE_SHIFT);
+
+        // We use `mmput_async` when dropping the `mm` because `use_page_slow` is usually used from
+        // a remote process. If the call to `mmput` races with the process shutting down, then the
+        // caller of `use_page_slow` becomes responsible for cleaning up the `mm`, which doesn't
+        // happen until it returns to userspace. However, the caller might instead go to sleep and
+        // wait for the owner of the `mm` to wake it up, which doesn't happen because it's in the
+        // middle of a shutdown process that won't complete until the `mm` is dropped. This can
+        // amount to a deadlock.
+        //
+        // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a
+        // workqueue.
+        MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
+            .mmap_read_lock()
+            .vma_lookup(vma_addr)
+            .ok_or(ESRCH)?
+            .as_mixedmap_vma()
+            .ok_or(ESRCH)?
+            .vm_insert_page(user_page_addr, &new_page)
+            .inspect_err(|err| {
+                pr_warn!(
+                    "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
+                    user_page_addr,
+                    vma_addr,
+                    i,
+                    err
+                )
+            })?;
+
+        let inner = self.lock.lock();
+
+        // SAFETY: The `page_info` pointer is valid and currently does not have a page. The page
+        // can be written to since we hold the lock.
+        //
+        // We released and reacquired the spinlock since we checked that the page is null, but we
+        // always hold the mm_lock mutex when setting the page to a non-null value, so it's not
+        // possible for someone else to have changed it since our check.
+        unsafe { PageInfo::set_page(page_info, new_page) };
+
+        drop(inner);
+        drop(mm_mutex);
+
+        Ok(())
+    }
+
+    /// If the given page is in use, then mark it as available so that the shrinker can free it.
+    ///
+    /// May be called from an atomic context.
+    pub(crate) fn stop_using_range(&self, start: usize, end: usize) {
+        if start >= end {
+            return;
+        }
+        let inner = self.lock.lock();
+        assert!(end <= inner.size);
+
+        for i in (start..end).rev() {
+            // SAFETY: The pointer is in bounds.
+            let page_info = unsafe { inner.pages.add(i) };
+
+            // SAFETY: Okay for reading since we have the lock.
+            if let Some(page) = unsafe { PageInfo::get_page(page_info) } {
+                // SAFETY: The pointer is valid, and it's the right shrinker.
+                unsafe { PageInfo::list_lru_add(page_info, page.nid(), self.shrinker) };
+            }
+        }
+    }
+
+    /// Helper for reading or writing to a range of bytes that may overlap with several pages.
+    ///
+    /// # Safety
+    ///
+    /// All pages touched by this operation must be in use for the duration of this call.
+    unsafe fn iterate<T>(&self, mut offset: usize, mut size: usize, mut cb: T) -> Result
+    where
+        T: FnMut(&Page, usize, usize) -> Result,
+    {
+        if size == 0 {
+            return Ok(());
+        }
+
+        let (pages, num_pages) = {
+            let inner = self.lock.lock();
+            (inner.pages, inner.size)
+        };
+        let num_bytes = num_pages << PAGE_SHIFT;
+
+        // Check that the request is within the buffer.
+        if offset.checked_add(size).ok_or(EFAULT)? > num_bytes {
+            return Err(EFAULT);
+        }
+
+        let mut page_index = offset >> PAGE_SHIFT;
+        offset &= PAGE_SIZE - 1;
+        while size > 0 {
+            let available = usize::min(size, PAGE_SIZE - offset);
+            // SAFETY: The pointer is in bounds.
+            let page_info = unsafe { pages.add(page_index) };
+            // SAFETY: The caller guarantees that this page is in the "in use" state for the
+            // duration of this call to `iterate`, so nobody will change the page.
+            let page = unsafe { PageInfo::get_page(page_info) };
+            if page.is_none() {
+                pr_warn!("Page is null!");
+            }
+            let page = page.ok_or(EFAULT)?;
+            cb(page, offset, available)?;
+            size -= available;
+            page_index += 1;
+            offset = 0;
+        }
+        Ok(())
+    }
+
+    /// Copy from userspace into this page range.
+    ///
+    /// # Safety
+    ///
+    /// All pages touched by this operation must be in use for the duration of this call.
+    pub(crate) unsafe fn copy_from_user_slice(
+        &self,
+        reader: &mut UserSliceReader,
+        offset: usize,
+        size: usize,
+    ) -> Result {
+        // SAFETY: `self.iterate` has the same safety requirements as `copy_from_user_slice`.
+        unsafe {
+            self.iterate(offset, size, |page, offset, to_copy| {
+                page.copy_from_user_slice_raw(reader, offset, to_copy)
+            })
+        }
+    }
+
+    /// Copy from this page range into kernel space.
+    ///
+    /// # Safety
+    ///
+    /// All pages touched by this operation must be in use for the duration of this call.
+    pub(crate) unsafe fn read<T: FromBytes>(&self, offset: usize) -> Result<T> {
+        let mut out = MaybeUninit::<T>::uninit();
+        let mut out_offset = 0;
+        // SAFETY: `self.iterate` has the same safety requirements as `read`.
+        unsafe {
+            self.iterate(offset, size_of::<T>(), |page, offset, to_copy| {
+                // SAFETY: The sum of `offset` and `to_copy` is bounded by the size of T.
+                let obj_ptr = (out.as_mut_ptr() as *mut u8).add(out_offset);
+                // SAFETY: The pointer points is in-bounds of the `out` variable, so it is valid.
+                page.read_raw(obj_ptr, offset, to_copy)?;
+                out_offset += to_copy;
+                Ok(())
+            })?;
+        }
+        // SAFETY: We just initialised the data.
+        Ok(unsafe { out.assume_init() })
+    }
+
+    /// Copy from kernel space into this page range.
+    ///
+    /// # Safety
+    ///
+    /// All pages touched by this operation must be in use for the duration of this call.
+    pub(crate) unsafe fn write<T: ?Sized>(&self, offset: usize, obj: &T) -> Result {
+        let mut obj_offset = 0;
+        // SAFETY: `self.iterate` has the same safety requirements as `write`.
+        unsafe {
+            self.iterate(offset, size_of_val(obj), |page, offset, to_copy| {
+                // SAFETY: The sum of `offset` and `to_copy` is bounded by the size of T.
+                let obj_ptr = (obj as *const T as *const u8).add(obj_offset);
+                // SAFETY: We have a reference to the object, so the pointer is valid.
+                page.write_raw(obj_ptr, offset, to_copy)?;
+                obj_offset += to_copy;
+                Ok(())
+            })
+        }
+    }
+
+    /// Write zeroes to the given range.
+    ///
+    /// # Safety
+    ///
+    /// All pages touched by this operation must be in use for the duration of this call.
+    pub(crate) unsafe fn fill_zero(&self, offset: usize, size: usize) -> Result {
+        // SAFETY: `self.iterate` has the same safety requirements as `copy_into`.
+        unsafe {
+            self.iterate(offset, size, |page, offset, len| {
+                page.fill_zero_raw(offset, len)
+            })
+        }
+    }
+}
+
+#[pinned_drop]
+impl PinnedDrop for ShrinkablePageRange {
+    fn drop(self: Pin<&mut Self>) {
+        let (pages, size) = {
+            let lock = self.lock.lock();
+            (lock.pages, lock.size)
+        };
+
+        if size == 0 {
+            return;
+        }
+
+        // Note: This call is also necessary for the safety of `stable_trylock_mm`.
+        let mm_lock = self.mm_lock.lock();
+
+        // This is the destructor, so unlike the other methods, we only need to worry about races
+        // with the shrinker here. Since we hold the `mm_lock`, we also can't race with the
+        // shrinker, and after this loop, the shrinker will not access any of our pages since we
+        // removed them from the lru list.
+        for i in 0..size {
+            // SAFETY: Loop is in-bounds of the size.
+            let p_ptr = unsafe { pages.add(i) };
+            // SAFETY: No other readers, so we can read.
+            if let Some(p) = unsafe { PageInfo::get_page(p_ptr) } {
+                // SAFETY: The pointer is valid and it's the right shrinker.
+                unsafe { PageInfo::list_lru_del(p_ptr, p.nid(), self.shrinker) };
+            }
+        }
+
+        drop(mm_lock);
+
+        // SAFETY: `pages` was allocated as an `KVVec<PageInfo>` with capacity `size`. Furthermore,
+        // all `size` elements are initialized. Also, the array is no longer shared with the
+        // shrinker due to the above loop.
+        drop(unsafe { KVVec::from_raw_parts(pages, size, size) });
+    }
+}
+
+/// # Safety
+/// Called by the shrinker.
+#[no_mangle]
+unsafe extern "C" fn rust_shrink_count(
+    shrink: *mut bindings::shrinker,
+    _sc: *mut bindings::shrink_control,
+) -> c_ulong {
+    // SAFETY: We can access our own private data.
+    let list_lru = unsafe { (*shrink).private_data.cast::<bindings::list_lru>() };
+    // SAFETY: Accessing the lru list is okay. Just an FFI call.
+    unsafe { bindings::list_lru_count(list_lru) }
+}
+
+/// # Safety
+/// Called by the shrinker.
+#[no_mangle]
+unsafe extern "C" fn rust_shrink_scan(
+    shrink: *mut bindings::shrinker,
+    sc: *mut bindings::shrink_control,
+) -> c_ulong {
+    // SAFETY: We can access our own private data.
+    let list_lru = unsafe { (*shrink).private_data.cast::<bindings::list_lru>() };
+    // SAFETY: Caller guarantees that it is safe to read this field.
+    let nr_to_scan = unsafe { (*sc).nr_to_scan };
+    // SAFETY: Accessing the lru list is okay. Just an FFI call.
+    unsafe {
+        bindings::list_lru_walk(
+            list_lru,
+            Some(bindings::rust_shrink_free_page_wrap),
+            ptr::null_mut(),
+            nr_to_scan,
+        )
+    }
+}
+
+const LRU_SKIP: bindings::lru_status = bindings::lru_status_LRU_SKIP;
+const LRU_REMOVED_ENTRY: bindings::lru_status = bindings::lru_status_LRU_REMOVED_RETRY;
+
+/// # Safety
+/// Called by the shrinker.
+#[no_mangle]
+unsafe extern "C" fn rust_shrink_free_page(
+    item: *mut bindings::list_head,
+    lru: *mut bindings::list_lru_one,
+    _cb_arg: *mut c_void,
+) -> bindings::lru_status {
+    // Fields that should survive after unlocking the lru lock.
+    let page;
+    let page_index;
+    let mm;
+    let mmap_read;
+    let mm_mutex;
+    let vma_addr;
+
+    {
+        // CAST: The `list_head` field is first in `PageInfo`.
+        let info = item as *mut PageInfo;
+        // SAFETY: The `range` field of `PageInfo` is immutable.
+        let range = unsafe { &*((*info).range) };
+
+        mm = match range.mm.mmget_not_zero() {
+            Some(mm) => MmWithUser::into_mmput_async(mm),
+            None => return LRU_SKIP,
+        };
+
+        mm_mutex = match range.stable_trylock_mm() {
+            Some(guard) => guard,
+            None => return LRU_SKIP,
+        };
+
+        mmap_read = match mm.mmap_read_trylock() {
+            Some(guard) => guard,
+            None => return LRU_SKIP,
+        };
+
+        // We can't lock it normally here, since we hold the lru lock.
+        let inner = match range.lock.try_lock() {
+            Some(inner) => inner,
+            None => return LRU_SKIP,
+        };
+
+        // SAFETY: The item is in this lru list, so it's okay to remove it.
+        unsafe { bindings::list_lru_isolate(lru, item) };
+
+        // SAFETY: Both pointers are in bounds of the same allocation.
+        page_index = unsafe { info.offset_from(inner.pages) } as usize;
+
+        // SAFETY: We hold the spinlock, so we can take the page.
+        //
+        // This sets the page pointer to zero before we unmap it from the vma. However, we call
+        // `zap_page_range` before we release the mmap lock, so `use_page_slow` will not be able to
+        // insert a new page until after our call to `zap_page_range`.
+        page = unsafe { PageInfo::take_page(info) };
+        vma_addr = inner.vma_addr;
+
+        // From this point on, we don't access this PageInfo or ShrinkablePageRange again, because
+        // they can be freed at any point after we unlock `lru_lock`. This is with the exception of
+        // `mm_mutex` which is kept alive by holding the lock.
+    }
+
+    // SAFETY: The lru lock is locked when this method is called.
+    unsafe { bindings::spin_unlock(&raw mut (*lru).lock) };
+
+    if let Some(vma) = mmap_read.vma_lookup(vma_addr) {
+        let user_page_addr = vma_addr + (page_index << PAGE_SHIFT);
+        vma.zap_page_range_single(user_page_addr, PAGE_SIZE);
+    }
+
+    drop(mmap_read);
+    drop(mm_mutex);
+    drop(mm);
+    drop(page);
+
+    // SAFETY: We just unlocked the lru lock, but it should be locked when we return.
+    unsafe { bindings::spin_lock(&raw mut (*lru).lock) };
+
+    LRU_REMOVED_ENTRY
+}
diff --git a/drivers/android/binder/page_range_helper.c b/drivers/android/binder/page_range_helper.c
new file mode 100644
index 000000000000..496887723ee0
--- /dev/null
+++ b/drivers/android/binder/page_range_helper.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* C helper for page_range.rs to work around a CFI violation.
+ *
+ * Bindgen currently pretends that `enum lru_status` is the same as an integer.
+ * This assumption is fine ABI-wise, but once you add CFI to the mix, it
+ * triggers a CFI violation because `enum lru_status` gets a different CFI tag.
+ *
+ * This file contains a workaround until bindgen can be fixed.
+ *
+ * Copyright (C) 2025 Google LLC.
+ */
+#include "page_range_helper.h"
+
+unsigned int rust_shrink_free_page(struct list_head *item,
+				   struct list_lru_one *list,
+				   void *cb_arg);
+
+enum lru_status
+rust_shrink_free_page_wrap(struct list_head *item, struct list_lru_one *list,
+			   void *cb_arg)
+{
+	return rust_shrink_free_page(item, list, cb_arg);
+}
diff --git a/drivers/android/binder/page_range_helper.h b/drivers/android/binder/page_range_helper.h
new file mode 100644
index 000000000000..18dd2dd117b2
--- /dev/null
+++ b/drivers/android/binder/page_range_helper.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025 Google, Inc.
+ */
+
+#ifndef _LINUX_PAGE_RANGE_HELPER_H
+#define _LINUX_PAGE_RANGE_HELPER_H
+
+#include <linux/list_lru.h>
+
+enum lru_status
+rust_shrink_free_page_wrap(struct list_head *item, struct list_lru_one *list,
+			   void *cb_arg);
+
+#endif /* _LINUX_PAGE_RANGE_HELPER_H */
diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs
new file mode 100644
index 000000000000..f13a747e784c
--- /dev/null
+++ b/drivers/android/binder/process.rs
@@ -0,0 +1,1696 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! This module defines the `Process` type, which represents a process using a particular binder
+//! context.
+//!
+//! The `Process` object keeps track of all of the resources that this process owns in the binder
+//! context.
+//!
+//! There is one `Process` object for each binder fd that a process has opened, so processes using
+//! several binder contexts have several `Process` objects. This ensures that the contexts are
+//! fully separated.
+
+use core::mem::take;
+
+use kernel::{
+    bindings,
+    cred::Credential,
+    error::Error,
+    fs::file::{self, File},
+    list::{List, ListArc, ListArcField, ListLinks},
+    mm,
+    prelude::*,
+    rbtree::{self, RBTree, RBTreeNode, RBTreeNodeReservation},
+    seq_file::SeqFile,
+    seq_print,
+    sync::poll::PollTable,
+    sync::{
+        lock::{spinlock::SpinLockBackend, Guard},
+        Arc, ArcBorrow, CondVar, CondVarTimeoutResult, Mutex, SpinLock, UniqueArc,
+    },
+    task::Task,
+    types::ARef,
+    uaccess::{UserSlice, UserSliceReader},
+    uapi,
+    workqueue::{self, Work},
+};
+
+use crate::{
+    allocation::{Allocation, AllocationInfo, NewAllocation},
+    context::Context,
+    defs::*,
+    error::{BinderError, BinderResult},
+    node::{CouldNotDeliverCriticalIncrement, CritIncrWrapper, Node, NodeDeath, NodeRef},
+    page_range::ShrinkablePageRange,
+    range_alloc::{RangeAllocator, ReserveNew, ReserveNewArgs},
+    stats::BinderStats,
+    thread::{PushWorkRes, Thread},
+    BinderfsProcFile, DArc, DLArc, DTRWrap, DeliverToRead,
+};
+
+#[path = "freeze.rs"]
+mod freeze;
+use self::freeze::{FreezeCookie, FreezeListener};
+
+struct Mapping {
+    address: usize,
+    alloc: RangeAllocator<AllocationInfo>,
+}
+
+impl Mapping {
+    fn new(address: usize, size: usize) -> Self {
+        Self {
+            address,
+            alloc: RangeAllocator::new(size),
+        }
+    }
+}
+
+// bitflags for defer_work.
+const PROC_DEFER_FLUSH: u8 = 1;
+const PROC_DEFER_RELEASE: u8 = 2;
+
+/// The fields of `Process` protected by the spinlock.
+pub(crate) struct ProcessInner {
+    is_manager: bool,
+    pub(crate) is_dead: bool,
+    threads: RBTree<i32, Arc<Thread>>,
+    /// INVARIANT: Threads pushed to this list must be owned by this process.
+    ready_threads: List<Thread>,
+    nodes: RBTree<u64, DArc<Node>>,
+    mapping: Option<Mapping>,
+    work: List<DTRWrap<dyn DeliverToRead>>,
+    delivered_deaths: List<DTRWrap<NodeDeath>, 2>,
+
+    /// The number of requested threads that haven't registered yet.
+    requested_thread_count: u32,
+    /// The maximum number of threads used by the process thread pool.
+    max_threads: u32,
+    /// The number of threads the started and registered with the thread pool.
+    started_thread_count: u32,
+
+    /// Bitmap of deferred work to do.
+    defer_work: u8,
+
+    /// Number of transactions to be transmitted before processes in freeze_wait
+    /// are woken up.
+    outstanding_txns: u32,
+    /// Process is frozen and unable to service binder transactions.
+    pub(crate) is_frozen: bool,
+    /// Process received sync transactions since last frozen.
+    pub(crate) sync_recv: bool,
+    /// Process received async transactions since last frozen.
+    pub(crate) async_recv: bool,
+    pub(crate) binderfs_file: Option<BinderfsProcFile>,
+    /// Check for oneway spam
+    oneway_spam_detection_enabled: bool,
+}
+
+impl ProcessInner {
+    fn new() -> Self {
+        Self {
+            is_manager: false,
+            is_dead: false,
+            threads: RBTree::new(),
+            ready_threads: List::new(),
+            mapping: None,
+            nodes: RBTree::new(),
+            work: List::new(),
+            delivered_deaths: List::new(),
+            requested_thread_count: 0,
+            max_threads: 0,
+            started_thread_count: 0,
+            defer_work: 0,
+            outstanding_txns: 0,
+            is_frozen: false,
+            sync_recv: false,
+            async_recv: false,
+            binderfs_file: None,
+            oneway_spam_detection_enabled: false,
+        }
+    }
+
+    /// Schedule the work item for execution on this process.
+    ///
+    /// If any threads are ready for work, then the work item is given directly to that thread and
+    /// it is woken up. Otherwise, it is pushed to the process work list.
+    ///
+    /// This call can fail only if the process is dead. In this case, the work item is returned to
+    /// the caller so that the caller can drop it after releasing the inner process lock. This is
+    /// necessary since the destructor of `Transaction` will take locks that can't necessarily be
+    /// taken while holding the inner process lock.
+    pub(crate) fn push_work(
+        &mut self,
+        work: DLArc<dyn DeliverToRead>,
+    ) -> Result<(), (BinderError, DLArc<dyn DeliverToRead>)> {
+        // Try to find a ready thread to which to push the work.
+        if let Some(thread) = self.ready_threads.pop_front() {
+            // Push to thread while holding state lock. This prevents the thread from giving up
+            // (for example, because of a signal) when we're about to deliver work.
+            match thread.push_work(work) {
+                PushWorkRes::Ok => Ok(()),
+                PushWorkRes::FailedDead(work) => Err((BinderError::new_dead(), work)),
+            }
+        } else if self.is_dead {
+            Err((BinderError::new_dead(), work))
+        } else {
+            let sync = work.should_sync_wakeup();
+
+            // Didn't find a thread waiting for proc work; this can happen
+            // in two scenarios:
+            // 1. All threads are busy handling transactions
+            //    In that case, one of those threads should call back into
+            //    the kernel driver soon and pick up this work.
+            // 2. Threads are using the (e)poll interface, in which case
+            //    they may be blocked on the waitqueue without having been
+            //    added to waiting_threads. For this case, we just iterate
+            //    over all threads not handling transaction work, and
+            //    wake them all up. We wake all because we don't know whether
+            //    a thread that called into (e)poll is handling non-binder
+            //    work currently.
+            self.work.push_back(work);
+
+            // Wake up polling threads, if any.
+            for thread in self.threads.values() {
+                thread.notify_if_poll_ready(sync);
+            }
+
+            Ok(())
+        }
+    }
+
+    pub(crate) fn remove_node(&mut self, ptr: u64) {
+        self.nodes.remove(&ptr);
+    }
+
+    /// Updates the reference count on the given node.
+    pub(crate) fn update_node_refcount(
+        &mut self,
+        node: &DArc<Node>,
+        inc: bool,
+        strong: bool,
+        count: usize,
+        othread: Option<&Thread>,
+    ) {
+        let push = node.update_refcount_locked(inc, strong, count, self);
+
+        // If we decided that we need to push work, push either to the process or to a thread if
+        // one is specified.
+        if let Some(node) = push {
+            if let Some(thread) = othread {
+                thread.push_work_deferred(node);
+            } else {
+                let _ = self.push_work(node);
+                // Nothing to do: `push_work` may fail if the process is dead, but that's ok as in
+                // that case, it doesn't care about the notification.
+            }
+        }
+    }
+
+    pub(crate) fn new_node_ref(
+        &mut self,
+        node: DArc<Node>,
+        strong: bool,
+        thread: Option<&Thread>,
+    ) -> NodeRef {
+        self.update_node_refcount(&node, true, strong, 1, thread);
+        let strong_count = if strong { 1 } else { 0 };
+        NodeRef::new(node, strong_count, 1 - strong_count)
+    }
+
+    pub(crate) fn new_node_ref_with_thread(
+        &mut self,
+        node: DArc<Node>,
+        strong: bool,
+        thread: &Thread,
+        wrapper: Option<CritIncrWrapper>,
+    ) -> Result<NodeRef, CouldNotDeliverCriticalIncrement> {
+        let push = match wrapper {
+            None => node
+                .incr_refcount_allow_zero2one(strong, self)?
+                .map(|node| node as _),
+            Some(wrapper) => node.incr_refcount_allow_zero2one_with_wrapper(strong, wrapper, self),
+        };
+        if let Some(node) = push {
+            thread.push_work_deferred(node);
+        }
+        let strong_count = if strong { 1 } else { 0 };
+        Ok(NodeRef::new(node, strong_count, 1 - strong_count))
+    }
+
+    /// Returns an existing node with the given pointer and cookie, if one exists.
+    ///
+    /// Returns an error if a node with the given pointer but a different cookie exists.
+    fn get_existing_node(&self, ptr: u64, cookie: u64) -> Result<Option<DArc<Node>>> {
+        match self.nodes.get(&ptr) {
+            None => Ok(None),
+            Some(node) => {
+                let (_, node_cookie) = node.get_id();
+                if node_cookie == cookie {
+                    Ok(Some(node.clone()))
+                } else {
+                    Err(EINVAL)
+                }
+            }
+        }
+    }
+
+    fn register_thread(&mut self) -> bool {
+        if self.requested_thread_count == 0 {
+            return false;
+        }
+
+        self.requested_thread_count -= 1;
+        self.started_thread_count += 1;
+        true
+    }
+
+    /// Finds a delivered death notification with the given cookie, removes it from the thread's
+    /// delivered list, and returns it.
+    fn pull_delivered_death(&mut self, cookie: u64) -> Option<DArc<NodeDeath>> {
+        let mut cursor = self.delivered_deaths.cursor_front();
+        while let Some(next) = cursor.peek_next() {
+            if next.cookie == cookie {
+                return Some(next.remove().into_arc());
+            }
+            cursor.move_next();
+        }
+        None
+    }
+
+    pub(crate) fn death_delivered(&mut self, death: DArc<NodeDeath>) {
+        if let Some(death) = ListArc::try_from_arc_or_drop(death) {
+            self.delivered_deaths.push_back(death);
+        } else {
+            pr_warn!("Notification added to `delivered_deaths` twice.");
+        }
+    }
+
+    pub(crate) fn add_outstanding_txn(&mut self) {
+        self.outstanding_txns += 1;
+    }
+
+    fn txns_pending_locked(&self) -> bool {
+        if self.outstanding_txns > 0 {
+            return true;
+        }
+        for thread in self.threads.values() {
+            if thread.has_current_transaction() {
+                return true;
+            }
+        }
+        false
+    }
+}
+
+/// Used to keep track of a node that this process has a handle to.
+#[pin_data]
+pub(crate) struct NodeRefInfo {
+    debug_id: usize,
+    /// The refcount that this process owns to the node.
+    node_ref: ListArcField<NodeRef, { Self::LIST_PROC }>,
+    death: ListArcField<Option<DArc<NodeDeath>>, { Self::LIST_PROC }>,
+    /// Cookie of the active freeze listener for this node.
+    freeze: ListArcField<Option<FreezeCookie>, { Self::LIST_PROC }>,
+    /// Used to store this `NodeRefInfo` in the node's `refs` list.
+    #[pin]
+    links: ListLinks<{ Self::LIST_NODE }>,
+    /// The handle for this `NodeRefInfo`.
+    handle: u32,
+    /// The process that has a handle to the node.
+    pub(crate) process: Arc<Process>,
+}
+
+impl NodeRefInfo {
+    /// The id used for the `Node::refs` list.
+    pub(crate) const LIST_NODE: u64 = 0x2da16350fb724a10;
+    /// The id used for the `ListArc` in `ProcessNodeRefs`.
+    const LIST_PROC: u64 = 0xd703a5263dcc8650;
+
+    fn new(node_ref: NodeRef, handle: u32, process: Arc<Process>) -> impl PinInit<Self> {
+        pin_init!(Self {
+            debug_id: super::next_debug_id(),
+            node_ref: ListArcField::new(node_ref),
+            death: ListArcField::new(None),
+            freeze: ListArcField::new(None),
+            links <- ListLinks::new(),
+            handle,
+            process,
+        })
+    }
+
+    kernel::list::define_list_arc_field_getter! {
+        pub(crate) fn death(&mut self<{Self::LIST_PROC}>) -> &mut Option<DArc<NodeDeath>> { death }
+        pub(crate) fn freeze(&mut self<{Self::LIST_PROC}>) -> &mut Option<FreezeCookie> { freeze }
+        pub(crate) fn node_ref(&mut self<{Self::LIST_PROC}>) -> &mut NodeRef { node_ref }
+        pub(crate) fn node_ref2(&self<{Self::LIST_PROC}>) -> &NodeRef { node_ref }
+    }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<{Self::LIST_NODE}> for NodeRefInfo { untracked; }
+    impl ListArcSafe<{Self::LIST_PROC}> for NodeRefInfo { untracked; }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<{Self::LIST_NODE}> for NodeRefInfo {
+        using ListLinks { self.links };
+    }
+}
+
+/// Keeps track of references this process has to nodes owned by other processes.
+///
+/// TODO: Currently, the rbtree requires two allocations per node reference, and two tree
+/// traversals to look up a node by `Node::global_id`. Once the rbtree is more powerful, these
+/// extra costs should be eliminated.
+struct ProcessNodeRefs {
+    /// Used to look up nodes using the 32-bit id that this process knows it by.
+    by_handle: RBTree<u32, ListArc<NodeRefInfo, { NodeRefInfo::LIST_PROC }>>,
+    /// Used to look up nodes without knowing their local 32-bit id. The usize is the address of
+    /// the underlying `Node` struct as returned by `Node::global_id`.
+    by_node: RBTree<usize, u32>,
+    /// Used to look up a `FreezeListener` by cookie.
+    ///
+    /// There might be multiple freeze listeners for the same node, but at most one of them is
+    /// active.
+    freeze_listeners: RBTree<FreezeCookie, FreezeListener>,
+}
+
+impl ProcessNodeRefs {
+    fn new() -> Self {
+        Self {
+            by_handle: RBTree::new(),
+            by_node: RBTree::new(),
+            freeze_listeners: RBTree::new(),
+        }
+    }
+}
+
+/// A process using binder.
+///
+/// Strictly speaking, there can be multiple of these per process. There is one for each binder fd
+/// that a process has opened, so processes using several binder contexts have several `Process`
+/// objects. This ensures that the contexts are fully separated.
+#[pin_data]
+pub(crate) struct Process {
+    pub(crate) ctx: Arc<Context>,
+
+    // The task leader (process).
+    pub(crate) task: ARef<Task>,
+
+    // Credential associated with file when `Process` is created.
+    pub(crate) cred: ARef<Credential>,
+
+    #[pin]
+    pub(crate) inner: SpinLock<ProcessInner>,
+
+    #[pin]
+    pub(crate) pages: ShrinkablePageRange,
+
+    // Waitqueue of processes waiting for all outstanding transactions to be
+    // processed.
+    #[pin]
+    freeze_wait: CondVar,
+
+    // Node references are in a different lock to avoid recursive acquisition when
+    // incrementing/decrementing a node in another process.
+    #[pin]
+    node_refs: Mutex<ProcessNodeRefs>,
+
+    // Work node for deferred work item.
+    #[pin]
+    defer_work: Work<Process>,
+
+    // Links for process list in Context.
+    #[pin]
+    links: ListLinks,
+
+    pub(crate) stats: BinderStats,
+}
+
+kernel::impl_has_work! {
+    impl HasWork<Process> for Process { self.defer_work }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for Process { untracked; }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<0> for Process {
+        using ListLinks { self.links };
+    }
+}
+
+impl workqueue::WorkItem for Process {
+    type Pointer = Arc<Process>;
+
+    fn run(me: Arc<Self>) {
+        let defer;
+        {
+            let mut inner = me.inner.lock();
+            defer = inner.defer_work;
+            inner.defer_work = 0;
+        }
+
+        if defer & PROC_DEFER_FLUSH != 0 {
+            me.deferred_flush();
+        }
+        if defer & PROC_DEFER_RELEASE != 0 {
+            me.deferred_release();
+        }
+    }
+}
+
+impl Process {
+    fn new(ctx: Arc<Context>, cred: ARef<Credential>) -> Result<Arc<Self>> {
+        let current = kernel::current!();
+        let list_process = ListArc::pin_init::<Error>(
+            try_pin_init!(Process {
+                ctx,
+                cred,
+                inner <- kernel::new_spinlock!(ProcessInner::new(), "Process::inner"),
+                pages <- ShrinkablePageRange::new(&super::BINDER_SHRINKER),
+                node_refs <- kernel::new_mutex!(ProcessNodeRefs::new(), "Process::node_refs"),
+                freeze_wait <- kernel::new_condvar!("Process::freeze_wait"),
+                task: current.group_leader().into(),
+                defer_work <- kernel::new_work!("Process::defer_work"),
+                links <- ListLinks::new(),
+                stats: BinderStats::new(),
+            }),
+            GFP_KERNEL,
+        )?;
+
+        let process = list_process.clone_arc();
+        process.ctx.register_process(list_process);
+
+        Ok(process)
+    }
+
+    pub(crate) fn pid_in_current_ns(&self) -> kernel::task::Pid {
+        self.task.tgid_nr_ns(None)
+    }
+
+    #[inline(never)]
+    pub(crate) fn debug_print_stats(&self, m: &SeqFile, ctx: &Context) -> Result<()> {
+        seq_print!(m, "proc {}\n", self.pid_in_current_ns());
+        seq_print!(m, "context {}\n", &*ctx.name);
+
+        let inner = self.inner.lock();
+        seq_print!(m, "  threads: {}\n", inner.threads.iter().count());
+        seq_print!(
+            m,
+            "  requested threads: {}+{}/{}\n",
+            inner.requested_thread_count,
+            inner.started_thread_count,
+            inner.max_threads,
+        );
+        if let Some(mapping) = &inner.mapping {
+            seq_print!(
+                m,
+                "  free oneway space: {}\n",
+                mapping.alloc.free_oneway_space()
+            );
+            seq_print!(m, "  buffers: {}\n", mapping.alloc.count_buffers());
+        }
+        seq_print!(
+            m,
+            "  outstanding transactions: {}\n",
+            inner.outstanding_txns
+        );
+        seq_print!(m, "  nodes: {}\n", inner.nodes.iter().count());
+        drop(inner);
+
+        {
+            let mut refs = self.node_refs.lock();
+            let (mut count, mut weak, mut strong) = (0, 0, 0);
+            for r in refs.by_handle.values_mut() {
+                let node_ref = r.node_ref();
+                let (nstrong, nweak) = node_ref.get_count();
+                count += 1;
+                weak += nweak;
+                strong += nstrong;
+            }
+            seq_print!(m, "  refs: {count} s {strong} w {weak}\n");
+        }
+
+        self.stats.debug_print("  ", m);
+
+        Ok(())
+    }
+
+    #[inline(never)]
+    pub(crate) fn debug_print(&self, m: &SeqFile, ctx: &Context, print_all: bool) -> Result<()> {
+        seq_print!(m, "proc {}\n", self.pid_in_current_ns());
+        seq_print!(m, "context {}\n", &*ctx.name);
+
+        let mut all_threads = KVec::new();
+        let mut all_nodes = KVec::new();
+        loop {
+            let inner = self.inner.lock();
+            let num_threads = inner.threads.iter().count();
+            let num_nodes = inner.nodes.iter().count();
+
+            if all_threads.capacity() < num_threads || all_nodes.capacity() < num_nodes {
+                drop(inner);
+                all_threads.reserve(num_threads, GFP_KERNEL)?;
+                all_nodes.reserve(num_nodes, GFP_KERNEL)?;
+                continue;
+            }
+
+            for thread in inner.threads.values() {
+                assert!(all_threads.len() < all_threads.capacity());
+                let _ = all_threads.push(thread.clone(), GFP_ATOMIC);
+            }
+
+            for node in inner.nodes.values() {
+                assert!(all_nodes.len() < all_nodes.capacity());
+                let _ = all_nodes.push(node.clone(), GFP_ATOMIC);
+            }
+
+            break;
+        }
+
+        for thread in all_threads {
+            thread.debug_print(m, print_all)?;
+        }
+
+        let mut inner = self.inner.lock();
+        for node in all_nodes {
+            if print_all || node.has_oneway_transaction(&mut inner) {
+                node.full_debug_print(m, &mut inner)?;
+            }
+        }
+        drop(inner);
+
+        if print_all {
+            let mut refs = self.node_refs.lock();
+            for r in refs.by_handle.values_mut() {
+                let node_ref = r.node_ref();
+                let dead = node_ref.node.owner.inner.lock().is_dead;
+                let (strong, weak) = node_ref.get_count();
+                let debug_id = node_ref.node.debug_id;
+
+                seq_print!(
+                    m,
+                    "  ref {}: desc {} {}node {debug_id} s {strong} w {weak}",
+                    r.debug_id,
+                    r.handle,
+                    if dead { "dead " } else { "" },
+                );
+            }
+        }
+
+        let inner = self.inner.lock();
+        for work in &inner.work {
+            work.debug_print(m, "  ", "  pending transaction ")?;
+        }
+        for _death in &inner.delivered_deaths {
+            seq_print!(m, "  has delivered dead binder\n");
+        }
+        if let Some(mapping) = &inner.mapping {
+            mapping.alloc.debug_print(m)?;
+        }
+        drop(inner);
+
+        Ok(())
+    }
+
+    /// Attempts to fetch a work item from the process queue.
+    pub(crate) fn get_work(&self) -> Option<DLArc<dyn DeliverToRead>> {
+        self.inner.lock().work.pop_front()
+    }
+
+    /// Attempts to fetch a work item from the process queue. If none is available, it registers the
+    /// given thread as ready to receive work directly.
+    ///
+    /// This must only be called when the thread is not participating in a transaction chain; when
+    /// it is, work will always be delivered directly to the thread (and not through the process
+    /// queue).
+    pub(crate) fn get_work_or_register<'a>(
+        &'a self,
+        thread: &'a Arc<Thread>,
+    ) -> GetWorkOrRegister<'a> {
+        let mut inner = self.inner.lock();
+        // Try to get work from the process queue.
+        if let Some(work) = inner.work.pop_front() {
+            return GetWorkOrRegister::Work(work);
+        }
+
+        // Register the thread as ready.
+        GetWorkOrRegister::Register(Registration::new(thread, &mut inner))
+    }
+
+    fn get_current_thread(self: ArcBorrow<'_, Self>) -> Result<Arc<Thread>> {
+        let id = {
+            let current = kernel::current!();
+            if !core::ptr::eq(current.group_leader(), &*self.task) {
+                pr_err!("get_current_thread was called from the wrong process.");
+                return Err(EINVAL);
+            }
+            current.pid()
+        };
+
+        {
+            let inner = self.inner.lock();
+            if let Some(thread) = inner.threads.get(&id) {
+                return Ok(thread.clone());
+            }
+        }
+
+        // Allocate a new `Thread` without holding any locks.
+        let reservation = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        let ta: Arc<Thread> = Thread::new(id, self.into())?;
+
+        let mut inner = self.inner.lock();
+        match inner.threads.entry(id) {
+            rbtree::Entry::Vacant(entry) => {
+                entry.insert(ta.clone(), reservation);
+                Ok(ta)
+            }
+            rbtree::Entry::Occupied(_entry) => {
+                pr_err!("Cannot create two threads with the same id.");
+                Err(EINVAL)
+            }
+        }
+    }
+
+    pub(crate) fn push_work(&self, work: DLArc<dyn DeliverToRead>) -> BinderResult {
+        // If push_work fails, drop the work item outside the lock.
+        let res = self.inner.lock().push_work(work);
+        match res {
+            Ok(()) => Ok(()),
+            Err((err, work)) => {
+                drop(work);
+                Err(err)
+            }
+        }
+    }
+
+    fn set_as_manager(
+        self: ArcBorrow<'_, Self>,
+        info: Option<FlatBinderObject>,
+        thread: &Thread,
+    ) -> Result {
+        let (ptr, cookie, flags) = if let Some(obj) = info {
+            (
+                // SAFETY: The object type for this ioctl is implicitly `BINDER_TYPE_BINDER`, so it
+                // is safe to access the `binder` field.
+                unsafe { obj.__bindgen_anon_1.binder },
+                obj.cookie,
+                obj.flags,
+            )
+        } else {
+            (0, 0, 0)
+        };
+        let node_ref = self.get_node(ptr, cookie, flags as _, true, thread)?;
+        let node = node_ref.node.clone();
+        self.ctx.set_manager_node(node_ref)?;
+        self.inner.lock().is_manager = true;
+
+        // Force the state of the node to prevent the delivery of acquire/increfs.
+        let mut owner_inner = node.owner.inner.lock();
+        node.force_has_count(&mut owner_inner);
+        Ok(())
+    }
+
+    fn get_node_inner(
+        self: ArcBorrow<'_, Self>,
+        ptr: u64,
+        cookie: u64,
+        flags: u32,
+        strong: bool,
+        thread: &Thread,
+        wrapper: Option<CritIncrWrapper>,
+    ) -> Result<Result<NodeRef, CouldNotDeliverCriticalIncrement>> {
+        // Try to find an existing node.
+        {
+            let mut inner = self.inner.lock();
+            if let Some(node) = inner.get_existing_node(ptr, cookie)? {
+                return Ok(inner.new_node_ref_with_thread(node, strong, thread, wrapper));
+            }
+        }
+
+        // Allocate the node before reacquiring the lock.
+        let node = DTRWrap::arc_pin_init(Node::new(ptr, cookie, flags, self.into()))?.into_arc();
+        let rbnode = RBTreeNode::new(ptr, node.clone(), GFP_KERNEL)?;
+        let mut inner = self.inner.lock();
+        if let Some(node) = inner.get_existing_node(ptr, cookie)? {
+            return Ok(inner.new_node_ref_with_thread(node, strong, thread, wrapper));
+        }
+
+        inner.nodes.insert(rbnode);
+        // This can only fail if someone has already pushed the node to a list, but we just created
+        // it and still hold the lock, so it can't fail right now.
+        let node_ref = inner
+            .new_node_ref_with_thread(node, strong, thread, wrapper)
+            .unwrap();
+
+        Ok(Ok(node_ref))
+    }
+
+    pub(crate) fn get_node(
+        self: ArcBorrow<'_, Self>,
+        ptr: u64,
+        cookie: u64,
+        flags: u32,
+        strong: bool,
+        thread: &Thread,
+    ) -> Result<NodeRef> {
+        let mut wrapper = None;
+        for _ in 0..2 {
+            match self.get_node_inner(ptr, cookie, flags, strong, thread, wrapper) {
+                Err(err) => return Err(err),
+                Ok(Ok(node_ref)) => return Ok(node_ref),
+                Ok(Err(CouldNotDeliverCriticalIncrement)) => {
+                    wrapper = Some(CritIncrWrapper::new()?);
+                }
+            }
+        }
+        // We only get a `CouldNotDeliverCriticalIncrement` error if `wrapper` is `None`, so the
+        // loop should run at most twice.
+        unreachable!()
+    }
+
+    pub(crate) fn insert_or_update_handle(
+        self: ArcBorrow<'_, Process>,
+        node_ref: NodeRef,
+        is_mananger: bool,
+    ) -> Result<u32> {
+        {
+            let mut refs = self.node_refs.lock();
+
+            // Do a lookup before inserting.
+            if let Some(handle_ref) = refs.by_node.get(&node_ref.node.global_id()) {
+                let handle = *handle_ref;
+                let info = refs.by_handle.get_mut(&handle).unwrap();
+                info.node_ref().absorb(node_ref);
+                return Ok(handle);
+            }
+        }
+
+        // Reserve memory for tree nodes.
+        let reserve1 = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        let reserve2 = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        let info = UniqueArc::new_uninit(GFP_KERNEL)?;
+
+        let mut refs = self.node_refs.lock();
+
+        // Do a lookup again as node may have been inserted before the lock was reacquired.
+        if let Some(handle_ref) = refs.by_node.get(&node_ref.node.global_id()) {
+            let handle = *handle_ref;
+            let info = refs.by_handle.get_mut(&handle).unwrap();
+            info.node_ref().absorb(node_ref);
+            return Ok(handle);
+        }
+
+        // Find id.
+        let mut target: u32 = if is_mananger { 0 } else { 1 };
+        for handle in refs.by_handle.keys() {
+            if *handle > target {
+                break;
+            }
+            if *handle == target {
+                target = target.checked_add(1).ok_or(ENOMEM)?;
+            }
+        }
+
+        let gid = node_ref.node.global_id();
+        let (info_proc, info_node) = {
+            let info_init = NodeRefInfo::new(node_ref, target, self.into());
+            match info.pin_init_with(info_init) {
+                Ok(info) => ListArc::pair_from_pin_unique(info),
+                // error is infallible
+                Err(err) => match err {},
+            }
+        };
+
+        // Ensure the process is still alive while we insert a new reference.
+        //
+        // This releases the lock before inserting the nodes, but since `is_dead` is set as the
+        // first thing in `deferred_release`, process cleanup will not miss the items inserted into
+        // `refs` below.
+        if self.inner.lock().is_dead {
+            return Err(ESRCH);
+        }
+
+        // SAFETY: `info_proc` and `info_node` reference the same node, so we are inserting
+        // `info_node` into the right node's `refs` list.
+        unsafe { info_proc.node_ref2().node.insert_node_info(info_node) };
+
+        refs.by_node.insert(reserve1.into_node(gid, target));
+        refs.by_handle.insert(reserve2.into_node(target, info_proc));
+        Ok(target)
+    }
+
+    pub(crate) fn get_transaction_node(&self, handle: u32) -> BinderResult<NodeRef> {
+        // When handle is zero, try to get the context manager.
+        if handle == 0 {
+            Ok(self.ctx.get_manager_node(true)?)
+        } else {
+            Ok(self.get_node_from_handle(handle, true)?)
+        }
+    }
+
+    pub(crate) fn get_node_from_handle(&self, handle: u32, strong: bool) -> Result<NodeRef> {
+        self.node_refs
+            .lock()
+            .by_handle
+            .get_mut(&handle)
+            .ok_or(ENOENT)?
+            .node_ref()
+            .clone(strong)
+    }
+
+    pub(crate) fn remove_from_delivered_deaths(&self, death: &DArc<NodeDeath>) {
+        let mut inner = self.inner.lock();
+        // SAFETY: By the invariant on the `delivered_links` field, this is the right linked list.
+        let removed = unsafe { inner.delivered_deaths.remove(death) };
+        drop(inner);
+        drop(removed);
+    }
+
+    pub(crate) fn update_ref(
+        self: ArcBorrow<'_, Process>,
+        handle: u32,
+        inc: bool,
+        strong: bool,
+    ) -> Result {
+        if inc && handle == 0 {
+            if let Ok(node_ref) = self.ctx.get_manager_node(strong) {
+                if core::ptr::eq(&*self, &*node_ref.node.owner) {
+                    return Err(EINVAL);
+                }
+                let _ = self.insert_or_update_handle(node_ref, true);
+                return Ok(());
+            }
+        }
+
+        // To preserve original binder behaviour, we only fail requests where the manager tries to
+        // increment references on itself.
+        let mut refs = self.node_refs.lock();
+        if let Some(info) = refs.by_handle.get_mut(&handle) {
+            if info.node_ref().update(inc, strong) {
+                // Clean up death if there is one attached to this node reference.
+                if let Some(death) = info.death().take() {
+                    death.set_cleared(true);
+                    self.remove_from_delivered_deaths(&death);
+                }
+
+                // Remove reference from process tables, and from the node's `refs` list.
+
+                // SAFETY: We are removing the `NodeRefInfo` from the right node.
+                unsafe { info.node_ref2().node.remove_node_info(info) };
+
+                let id = info.node_ref().node.global_id();
+                refs.by_handle.remove(&handle);
+                refs.by_node.remove(&id);
+            }
+        } else {
+            // All refs are cleared in process exit, so this warning is expected in that case.
+            if !self.inner.lock().is_dead {
+                pr_warn!("{}: no such ref {handle}\n", self.pid_in_current_ns());
+            }
+        }
+        Ok(())
+    }
+
+    /// Decrements the refcount of the given node, if one exists.
+    pub(crate) fn update_node(&self, ptr: u64, cookie: u64, strong: bool) {
+        let mut inner = self.inner.lock();
+        if let Ok(Some(node)) = inner.get_existing_node(ptr, cookie) {
+            inner.update_node_refcount(&node, false, strong, 1, None);
+        }
+    }
+
+    pub(crate) fn inc_ref_done(&self, reader: &mut UserSliceReader, strong: bool) -> Result {
+        let ptr = reader.read::<u64>()?;
+        let cookie = reader.read::<u64>()?;
+        let mut inner = self.inner.lock();
+        if let Ok(Some(node)) = inner.get_existing_node(ptr, cookie) {
+            if let Some(node) = node.inc_ref_done_locked(strong, &mut inner) {
+                // This only fails if the process is dead.
+                let _ = inner.push_work(node);
+            }
+        }
+        Ok(())
+    }
+
+    pub(crate) fn buffer_alloc(
+        self: &Arc<Self>,
+        debug_id: usize,
+        size: usize,
+        is_oneway: bool,
+        from_pid: i32,
+    ) -> BinderResult<NewAllocation> {
+        use kernel::page::PAGE_SIZE;
+
+        let mut reserve_new_args = ReserveNewArgs {
+            debug_id,
+            size,
+            is_oneway,
+            pid: from_pid,
+            ..ReserveNewArgs::default()
+        };
+
+        let (new_alloc, addr) = loop {
+            let mut inner = self.inner.lock();
+            let mapping = inner.mapping.as_mut().ok_or_else(BinderError::new_dead)?;
+            let alloc_request = match mapping.alloc.reserve_new(reserve_new_args)? {
+                ReserveNew::Success(new_alloc) => break (new_alloc, mapping.address),
+                ReserveNew::NeedAlloc(request) => request,
+            };
+            drop(inner);
+            // We need to allocate memory and then call `reserve_new` again.
+            reserve_new_args = alloc_request.make_alloc()?;
+        };
+
+        let res = Allocation::new(
+            self.clone(),
+            debug_id,
+            new_alloc.offset,
+            size,
+            addr + new_alloc.offset,
+            new_alloc.oneway_spam_detected,
+        );
+
+        // This allocation will be marked as in use until the `Allocation` is used to free it.
+        //
+        // This method can't be called while holding a lock, so we release the lock first. It's
+        // okay for several threads to use the method on the same index at the same time. In that
+        // case, one of the calls will allocate the given page (if missing), and the other call
+        // will wait for the other call to finish allocating the page.
+        //
+        // We will not call `stop_using_range` in parallel with this on the same page, because the
+        // allocation can only be removed via the destructor of the `Allocation` object that we
+        // currently own.
+        match self.pages.use_range(
+            new_alloc.offset / PAGE_SIZE,
+            (new_alloc.offset + size).div_ceil(PAGE_SIZE),
+        ) {
+            Ok(()) => {}
+            Err(err) => {
+                pr_warn!("use_range failure {:?}", err);
+                return Err(err.into());
+            }
+        }
+
+        Ok(NewAllocation(res))
+    }
+
+    pub(crate) fn buffer_get(self: &Arc<Self>, ptr: usize) -> Option<Allocation> {
+        let mut inner = self.inner.lock();
+        let mapping = inner.mapping.as_mut()?;
+        let offset = ptr.checked_sub(mapping.address)?;
+        let (size, debug_id, odata) = mapping.alloc.reserve_existing(offset).ok()?;
+        let mut alloc = Allocation::new(self.clone(), debug_id, offset, size, ptr, false);
+        if let Some(data) = odata {
+            alloc.set_info(data);
+        }
+        Some(alloc)
+    }
+
+    pub(crate) fn buffer_raw_free(&self, ptr: usize) {
+        let mut inner = self.inner.lock();
+        if let Some(ref mut mapping) = &mut inner.mapping {
+            let offset = match ptr.checked_sub(mapping.address) {
+                Some(offset) => offset,
+                None => return,
+            };
+
+            let freed_range = match mapping.alloc.reservation_abort(offset) {
+                Ok(freed_range) => freed_range,
+                Err(_) => {
+                    pr_warn!(
+                        "Pointer {:x} failed to free, base = {:x}\n",
+                        ptr,
+                        mapping.address
+                    );
+                    return;
+                }
+            };
+
+            // No more allocations in this range. Mark them as not in use.
+            //
+            // Must be done before we release the lock so that `use_range` is not used on these
+            // indices until `stop_using_range` returns.
+            self.pages
+                .stop_using_range(freed_range.start_page_idx, freed_range.end_page_idx);
+        }
+    }
+
+    pub(crate) fn buffer_make_freeable(&self, offset: usize, mut data: Option<AllocationInfo>) {
+        let mut inner = self.inner.lock();
+        if let Some(ref mut mapping) = &mut inner.mapping {
+            if mapping.alloc.reservation_commit(offset, &mut data).is_err() {
+                pr_warn!("Offset {} failed to be marked freeable\n", offset);
+            }
+        }
+    }
+
+    fn create_mapping(&self, vma: &mm::virt::VmaNew) -> Result {
+        use kernel::page::PAGE_SIZE;
+        let size = usize::min(vma.end() - vma.start(), bindings::SZ_4M as usize);
+        let mapping = Mapping::new(vma.start(), size);
+        let page_count = self.pages.register_with_vma(vma)?;
+        if page_count * PAGE_SIZE != size {
+            return Err(EINVAL);
+        }
+
+        // Save range allocator for later.
+        self.inner.lock().mapping = Some(mapping);
+
+        Ok(())
+    }
+
+    fn version(&self, data: UserSlice) -> Result {
+        data.writer().write(&BinderVersion::current())
+    }
+
+    pub(crate) fn register_thread(&self) -> bool {
+        self.inner.lock().register_thread()
+    }
+
+    fn remove_thread(&self, thread: Arc<Thread>) {
+        self.inner.lock().threads.remove(&thread.id);
+        thread.release();
+    }
+
+    fn set_max_threads(&self, max: u32) {
+        self.inner.lock().max_threads = max;
+    }
+
+    fn set_oneway_spam_detection_enabled(&self, enabled: u32) {
+        self.inner.lock().oneway_spam_detection_enabled = enabled != 0;
+    }
+
+    pub(crate) fn is_oneway_spam_detection_enabled(&self) -> bool {
+        self.inner.lock().oneway_spam_detection_enabled
+    }
+
+    fn get_node_debug_info(&self, data: UserSlice) -> Result {
+        let (mut reader, mut writer) = data.reader_writer();
+
+        // Read the starting point.
+        let ptr = reader.read::<BinderNodeDebugInfo>()?.ptr;
+        let mut out = BinderNodeDebugInfo::default();
+
+        {
+            let inner = self.inner.lock();
+            for (node_ptr, node) in &inner.nodes {
+                if *node_ptr > ptr {
+                    node.populate_debug_info(&mut out, &inner);
+                    break;
+                }
+            }
+        }
+
+        writer.write(&out)
+    }
+
+    fn get_node_info_from_ref(&self, data: UserSlice) -> Result {
+        let (mut reader, mut writer) = data.reader_writer();
+        let mut out = reader.read::<BinderNodeInfoForRef>()?;
+
+        if out.strong_count != 0
+            || out.weak_count != 0
+            || out.reserved1 != 0
+            || out.reserved2 != 0
+            || out.reserved3 != 0
+        {
+            return Err(EINVAL);
+        }
+
+        // Only the context manager is allowed to use this ioctl.
+        if !self.inner.lock().is_manager {
+            return Err(EPERM);
+        }
+
+        {
+            let mut node_refs = self.node_refs.lock();
+            let node_info = node_refs.by_handle.get_mut(&out.handle).ok_or(ENOENT)?;
+            let node_ref = node_info.node_ref();
+            let owner_inner = node_ref.node.owner.inner.lock();
+            node_ref.node.populate_counts(&mut out, &owner_inner);
+        }
+
+        // Write the result back.
+        writer.write(&out)
+    }
+
+    pub(crate) fn needs_thread(&self) -> bool {
+        let mut inner = self.inner.lock();
+        let ret = inner.requested_thread_count == 0
+            && inner.ready_threads.is_empty()
+            && inner.started_thread_count < inner.max_threads;
+        if ret {
+            inner.requested_thread_count += 1
+        }
+        ret
+    }
+
+    pub(crate) fn request_death(
+        self: &Arc<Self>,
+        reader: &mut UserSliceReader,
+        thread: &Thread,
+    ) -> Result {
+        let handle: u32 = reader.read()?;
+        let cookie: u64 = reader.read()?;
+
+        // Queue BR_ERROR if we can't allocate memory for the death notification.
+        let death = UniqueArc::new_uninit(GFP_KERNEL).inspect_err(|_| {
+            thread.push_return_work(BR_ERROR);
+        })?;
+        let mut refs = self.node_refs.lock();
+        let Some(info) = refs.by_handle.get_mut(&handle) else {
+            pr_warn!("BC_REQUEST_DEATH_NOTIFICATION invalid ref {handle}\n");
+            return Ok(());
+        };
+
+        // Nothing to do if there is already a death notification request for this handle.
+        if info.death().is_some() {
+            pr_warn!("BC_REQUEST_DEATH_NOTIFICATION death notification already set\n");
+            return Ok(());
+        }
+
+        let death = {
+            let death_init = NodeDeath::new(info.node_ref().node.clone(), self.clone(), cookie);
+            match death.pin_init_with(death_init) {
+                Ok(death) => death,
+                // error is infallible
+                Err(err) => match err {},
+            }
+        };
+
+        // Register the death notification.
+        {
+            let owner = info.node_ref2().node.owner.clone();
+            let mut owner_inner = owner.inner.lock();
+            if owner_inner.is_dead {
+                let death = Arc::from(death);
+                *info.death() = Some(death.clone());
+                drop(owner_inner);
+                death.set_dead();
+            } else {
+                let death = ListArc::from(death);
+                *info.death() = Some(death.clone_arc());
+                info.node_ref().node.add_death(death, &mut owner_inner);
+            }
+        }
+        Ok(())
+    }
+
+    pub(crate) fn clear_death(&self, reader: &mut UserSliceReader, thread: &Thread) -> Result {
+        let handle: u32 = reader.read()?;
+        let cookie: u64 = reader.read()?;
+
+        let mut refs = self.node_refs.lock();
+        let Some(info) = refs.by_handle.get_mut(&handle) else {
+            pr_warn!("BC_CLEAR_DEATH_NOTIFICATION invalid ref {handle}\n");
+            return Ok(());
+        };
+
+        let Some(death) = info.death().take() else {
+            pr_warn!("BC_CLEAR_DEATH_NOTIFICATION death notification not active\n");
+            return Ok(());
+        };
+        if death.cookie != cookie {
+            *info.death() = Some(death);
+            pr_warn!("BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch\n");
+            return Ok(());
+        }
+
+        // Update state and determine if we need to queue a work item. We only need to do it when
+        // the node is not dead or if the user already completed the death notification.
+        if death.set_cleared(false) {
+            if let Some(death) = ListArc::try_from_arc_or_drop(death) {
+                let _ = thread.push_work_if_looper(death);
+            }
+        }
+
+        Ok(())
+    }
+
+    pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) {
+        if let Some(death) = self.inner.lock().pull_delivered_death(cookie) {
+            death.set_notification_done(thread);
+        }
+    }
+
+    /// Locks the spinlock and move the `nodes` rbtree out.
+    ///
+    /// This allows you to iterate through `nodes` while also allowing you to give other parts of
+    /// the codebase exclusive access to `ProcessInner`.
+    pub(crate) fn lock_with_nodes(&self) -> WithNodes<'_> {
+        let mut inner = self.inner.lock();
+        WithNodes {
+            nodes: take(&mut inner.nodes),
+            inner,
+        }
+    }
+
+    fn deferred_flush(&self) {
+        let inner = self.inner.lock();
+        for thread in inner.threads.values() {
+            thread.exit_looper();
+        }
+    }
+
+    fn deferred_release(self: Arc<Self>) {
+        let is_manager = {
+            let mut inner = self.inner.lock();
+            inner.is_dead = true;
+            inner.is_frozen = false;
+            inner.sync_recv = false;
+            inner.async_recv = false;
+            inner.is_manager
+        };
+
+        if is_manager {
+            self.ctx.unset_manager_node();
+        }
+
+        self.ctx.deregister_process(&self);
+
+        let binderfs_file = self.inner.lock().binderfs_file.take();
+        drop(binderfs_file);
+
+        // Release threads.
+        let threads = {
+            let mut inner = self.inner.lock();
+            let threads = take(&mut inner.threads);
+            let ready = take(&mut inner.ready_threads);
+            drop(inner);
+            drop(ready);
+
+            for thread in threads.values() {
+                thread.release();
+            }
+            threads
+        };
+
+        // Release nodes.
+        {
+            while let Some(node) = {
+                let mut lock = self.inner.lock();
+                lock.nodes.cursor_front().map(|c| c.remove_current().1)
+            } {
+                node.to_key_value().1.release();
+            }
+        }
+
+        // Clean up death listeners and remove nodes from external node info lists.
+        for info in self.node_refs.lock().by_handle.values_mut() {
+            // SAFETY: We are removing the `NodeRefInfo` from the right node.
+            unsafe { info.node_ref2().node.remove_node_info(info) };
+
+            // Remove all death notifications from the nodes (that belong to a different process).
+            let death = if let Some(existing) = info.death().take() {
+                existing
+            } else {
+                continue;
+            };
+            death.set_cleared(false);
+        }
+
+        // Clean up freeze listeners.
+        let freeze_listeners = take(&mut self.node_refs.lock().freeze_listeners);
+        for listener in freeze_listeners.values() {
+            listener.on_process_exit(&self);
+        }
+        drop(freeze_listeners);
+
+        // Release refs on foreign nodes.
+        {
+            let mut refs = self.node_refs.lock();
+            let by_handle = take(&mut refs.by_handle);
+            let by_node = take(&mut refs.by_node);
+            drop(refs);
+            drop(by_node);
+            drop(by_handle);
+        }
+
+        // Cancel all pending work items.
+        while let Some(work) = self.get_work() {
+            work.into_arc().cancel();
+        }
+
+        let delivered_deaths = take(&mut self.inner.lock().delivered_deaths);
+        drop(delivered_deaths);
+
+        // Free any resources kept alive by allocated buffers.
+        let omapping = self.inner.lock().mapping.take();
+        if let Some(mut mapping) = omapping {
+            let address = mapping.address;
+            mapping
+                .alloc
+                .take_for_each(|offset, size, debug_id, odata| {
+                    let ptr = offset + address;
+                    pr_warn!(
+                        "{}: removing orphan mapping {offset}:{size}\n",
+                        self.pid_in_current_ns()
+                    );
+                    let mut alloc =
+                        Allocation::new(self.clone(), debug_id, offset, size, ptr, false);
+                    if let Some(data) = odata {
+                        alloc.set_info(data);
+                    }
+                    drop(alloc)
+                });
+        }
+
+        // calls to synchronize_rcu() in thread drop will happen here
+        drop(threads);
+    }
+
+    pub(crate) fn drop_outstanding_txn(&self) {
+        let wake = {
+            let mut inner = self.inner.lock();
+            if inner.outstanding_txns == 0 {
+                pr_err!("outstanding_txns underflow");
+                return;
+            }
+            inner.outstanding_txns -= 1;
+            inner.is_frozen && inner.outstanding_txns == 0
+        };
+
+        if wake {
+            self.freeze_wait.notify_all();
+        }
+    }
+
+    pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result {
+        if info.enable == 0 {
+            let msgs = self.prepare_freeze_messages()?;
+            let mut inner = self.inner.lock();
+            inner.sync_recv = false;
+            inner.async_recv = false;
+            inner.is_frozen = false;
+            drop(inner);
+            msgs.send_messages();
+            return Ok(());
+        }
+
+        let mut inner = self.inner.lock();
+        inner.sync_recv = false;
+        inner.async_recv = false;
+        inner.is_frozen = true;
+
+        if info.timeout_ms > 0 {
+            let mut jiffies = kernel::time::msecs_to_jiffies(info.timeout_ms);
+            while jiffies > 0 {
+                if inner.outstanding_txns == 0 {
+                    break;
+                }
+
+                match self
+                    .freeze_wait
+                    .wait_interruptible_timeout(&mut inner, jiffies)
+                {
+                    CondVarTimeoutResult::Signal { .. } => {
+                        inner.is_frozen = false;
+                        return Err(ERESTARTSYS);
+                    }
+                    CondVarTimeoutResult::Woken { jiffies: remaining } => {
+                        jiffies = remaining;
+                    }
+                    CondVarTimeoutResult::Timeout => {
+                        jiffies = 0;
+                    }
+                }
+            }
+        }
+
+        if inner.txns_pending_locked() {
+            inner.is_frozen = false;
+            Err(EAGAIN)
+        } else {
+            drop(inner);
+            match self.prepare_freeze_messages() {
+                Ok(batch) => {
+                    batch.send_messages();
+                    Ok(())
+                }
+                Err(kernel::alloc::AllocError) => {
+                    self.inner.lock().is_frozen = false;
+                    Err(ENOMEM)
+                }
+            }
+        }
+    }
+}
+
+fn get_frozen_status(data: UserSlice) -> Result {
+    let (mut reader, mut writer) = data.reader_writer();
+
+    let mut info = reader.read::<BinderFrozenStatusInfo>()?;
+    info.sync_recv = 0;
+    info.async_recv = 0;
+    let mut found = false;
+
+    for ctx in crate::context::get_all_contexts()? {
+        ctx.for_each_proc(|proc| {
+            if proc.task.pid() == info.pid as _ {
+                found = true;
+                let inner = proc.inner.lock();
+                let txns_pending = inner.txns_pending_locked();
+                info.async_recv |= inner.async_recv as u32;
+                info.sync_recv |= inner.sync_recv as u32;
+                info.sync_recv |= (txns_pending as u32) << 1;
+            }
+        });
+    }
+
+    if found {
+        writer.write(&info)?;
+        Ok(())
+    } else {
+        Err(EINVAL)
+    }
+}
+
+fn ioctl_freeze(reader: &mut UserSliceReader) -> Result {
+    let info = reader.read::<BinderFreezeInfo>()?;
+
+    // Very unlikely for there to be more than 3, since a process normally uses at most binder and
+    // hwbinder.
+    let mut procs = KVec::with_capacity(3, GFP_KERNEL)?;
+
+    let ctxs = crate::context::get_all_contexts()?;
+    for ctx in ctxs {
+        for proc in ctx.get_procs_with_pid(info.pid as i32)? {
+            procs.push(proc, GFP_KERNEL)?;
+        }
+    }
+
+    for proc in procs {
+        proc.ioctl_freeze(&info)?;
+    }
+    Ok(())
+}
+
+/// The ioctl handler.
+impl Process {
+    /// Ioctls that are write-only from the perspective of userspace.
+    ///
+    /// The kernel will only read from the pointer that userspace provided to us.
+    fn ioctl_write_only(
+        this: ArcBorrow<'_, Process>,
+        _file: &File,
+        cmd: u32,
+        reader: &mut UserSliceReader,
+    ) -> Result {
+        let thread = this.get_current_thread()?;
+        match cmd {
+            uapi::BINDER_SET_MAX_THREADS => this.set_max_threads(reader.read()?),
+            uapi::BINDER_THREAD_EXIT => this.remove_thread(thread),
+            uapi::BINDER_SET_CONTEXT_MGR => this.set_as_manager(None, &thread)?,
+            uapi::BINDER_SET_CONTEXT_MGR_EXT => {
+                this.set_as_manager(Some(reader.read()?), &thread)?
+            }
+            uapi::BINDER_ENABLE_ONEWAY_SPAM_DETECTION => {
+                this.set_oneway_spam_detection_enabled(reader.read()?)
+            }
+            uapi::BINDER_FREEZE => ioctl_freeze(reader)?,
+            _ => return Err(EINVAL),
+        }
+        Ok(())
+    }
+
+    /// Ioctls that are read/write from the perspective of userspace.
+    ///
+    /// The kernel will both read from and write to the pointer that userspace provided to us.
+    fn ioctl_write_read(
+        this: ArcBorrow<'_, Process>,
+        file: &File,
+        cmd: u32,
+        data: UserSlice,
+    ) -> Result {
+        let thread = this.get_current_thread()?;
+        let blocking = (file.flags() & file::flags::O_NONBLOCK) == 0;
+        match cmd {
+            uapi::BINDER_WRITE_READ => thread.write_read(data, blocking)?,
+            uapi::BINDER_GET_NODE_DEBUG_INFO => this.get_node_debug_info(data)?,
+            uapi::BINDER_GET_NODE_INFO_FOR_REF => this.get_node_info_from_ref(data)?,
+            uapi::BINDER_VERSION => this.version(data)?,
+            uapi::BINDER_GET_FROZEN_INFO => get_frozen_status(data)?,
+            uapi::BINDER_GET_EXTENDED_ERROR => thread.get_extended_error(data)?,
+            _ => return Err(EINVAL),
+        }
+        Ok(())
+    }
+}
+
+/// The file operations supported by `Process`.
+impl Process {
+    pub(crate) fn open(ctx: ArcBorrow<'_, Context>, file: &File) -> Result<Arc<Process>> {
+        Self::new(ctx.into(), ARef::from(file.cred()))
+    }
+
+    pub(crate) fn release(this: Arc<Process>, _file: &File) {
+        let binderfs_file;
+        let should_schedule;
+        {
+            let mut inner = this.inner.lock();
+            should_schedule = inner.defer_work == 0;
+            inner.defer_work |= PROC_DEFER_RELEASE;
+            binderfs_file = inner.binderfs_file.take();
+        }
+
+        if should_schedule {
+            // Ignore failures to schedule to the workqueue. Those just mean that we're already
+            // scheduled for execution.
+            let _ = workqueue::system().enqueue(this);
+        }
+
+        drop(binderfs_file);
+    }
+
+    pub(crate) fn flush(this: ArcBorrow<'_, Process>) -> Result {
+        let should_schedule;
+        {
+            let mut inner = this.inner.lock();
+            should_schedule = inner.defer_work == 0;
+            inner.defer_work |= PROC_DEFER_FLUSH;
+        }
+
+        if should_schedule {
+            // Ignore failures to schedule to the workqueue. Those just mean that we're already
+            // scheduled for execution.
+            let _ = workqueue::system().enqueue(Arc::from(this));
+        }
+        Ok(())
+    }
+
+    pub(crate) fn ioctl(this: ArcBorrow<'_, Process>, file: &File, cmd: u32, arg: usize) -> Result {
+        use kernel::ioctl::{_IOC_DIR, _IOC_SIZE};
+        use kernel::uapi::{_IOC_READ, _IOC_WRITE};
+
+        crate::trace::trace_ioctl(cmd, arg);
+
+        let user_slice = UserSlice::new(UserPtr::from_addr(arg), _IOC_SIZE(cmd));
+
+        const _IOC_READ_WRITE: u32 = _IOC_READ | _IOC_WRITE;
+
+        match _IOC_DIR(cmd) {
+            _IOC_WRITE => Self::ioctl_write_only(this, file, cmd, &mut user_slice.reader()),
+            _IOC_READ_WRITE => Self::ioctl_write_read(this, file, cmd, user_slice),
+            _ => Err(EINVAL),
+        }
+    }
+
+    pub(crate) fn compat_ioctl(
+        this: ArcBorrow<'_, Process>,
+        file: &File,
+        cmd: u32,
+        arg: usize,
+    ) -> Result {
+        Self::ioctl(this, file, cmd, arg)
+    }
+
+    pub(crate) fn mmap(
+        this: ArcBorrow<'_, Process>,
+        _file: &File,
+        vma: &mm::virt::VmaNew,
+    ) -> Result {
+        // We don't allow mmap to be used in a different process.
+        if !core::ptr::eq(kernel::current!().group_leader(), &*this.task) {
+            return Err(EINVAL);
+        }
+        if vma.start() == 0 {
+            return Err(EINVAL);
+        }
+
+        vma.try_clear_maywrite().map_err(|_| EPERM)?;
+        vma.set_dontcopy();
+        vma.set_mixedmap();
+
+        // TODO: Set ops. We need to learn when the user unmaps so that we can stop using it.
+        this.create_mapping(vma)
+    }
+
+    pub(crate) fn poll(
+        this: ArcBorrow<'_, Process>,
+        file: &File,
+        table: PollTable<'_>,
+    ) -> Result<u32> {
+        let thread = this.get_current_thread()?;
+        let (from_proc, mut mask) = thread.poll(file, table);
+        if mask == 0 && from_proc && !this.inner.lock().work.is_empty() {
+            mask |= bindings::POLLIN;
+        }
+        Ok(mask)
+    }
+}
+
+/// Represents that a thread has registered with the `ready_threads` list of its process.
+///
+/// The destructor of this type will unregister the thread from the list of ready threads.
+pub(crate) struct Registration<'a> {
+    thread: &'a Arc<Thread>,
+}
+
+impl<'a> Registration<'a> {
+    fn new(thread: &'a Arc<Thread>, guard: &mut Guard<'_, ProcessInner, SpinLockBackend>) -> Self {
+        assert!(core::ptr::eq(&thread.process.inner, guard.lock_ref()));
+        // INVARIANT: We are pushing this thread to the right `ready_threads` list.
+        if let Ok(list_arc) = ListArc::try_from_arc(thread.clone()) {
+            guard.ready_threads.push_front(list_arc);
+        } else {
+            // It is an error to hit this branch, and it should not be reachable. We try to do
+            // something reasonable when the failure path happens. Most likely, the thread in
+            // question will sleep forever.
+            pr_err!("Same thread registered with `ready_threads` twice.");
+        }
+        Self { thread }
+    }
+}
+
+impl Drop for Registration<'_> {
+    fn drop(&mut self) {
+        let mut inner = self.thread.process.inner.lock();
+        // SAFETY: The thread has the invariant that we never push it to any other linked list than
+        // the `ready_threads` list of its parent process. Therefore, the thread is either in that
+        // list, or in no list.
+        unsafe { inner.ready_threads.remove(self.thread) };
+    }
+}
+
+pub(crate) struct WithNodes<'a> {
+    pub(crate) inner: Guard<'a, ProcessInner, SpinLockBackend>,
+    pub(crate) nodes: RBTree<u64, DArc<Node>>,
+}
+
+impl Drop for WithNodes<'_> {
+    fn drop(&mut self) {
+        core::mem::swap(&mut self.nodes, &mut self.inner.nodes);
+        if self.nodes.iter().next().is_some() {
+            pr_err!("nodes array was modified while using lock_with_nodes\n");
+        }
+    }
+}
+
+pub(crate) enum GetWorkOrRegister<'a> {
+    Work(DLArc<dyn DeliverToRead>),
+    Register(Registration<'a>),
+}
diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs
new file mode 100644
index 000000000000..07e1dec2ce63
--- /dev/null
+++ b/drivers/android/binder/range_alloc/array.rs
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{
+    page::{PAGE_MASK, PAGE_SIZE},
+    prelude::*,
+    seq_file::SeqFile,
+    seq_print,
+    task::Pid,
+};
+
+use crate::range_alloc::{DescriptorState, FreedRange, Range};
+
+/// Keeps track of allocations in a process' mmap.
+///
+/// Each process has an mmap where the data for incoming transactions will be placed. This struct
+/// keeps track of allocations made in the mmap. For each allocation, we store a descriptor that
+/// has metadata related to the allocation. We also keep track of available free space.
+pub(super) struct ArrayRangeAllocator<T> {
+    /// This stores all ranges that are allocated. Unlike the tree based allocator, we do *not*
+    /// store the free ranges.
+    ///
+    /// Sorted by offset.
+    pub(super) ranges: KVec<Range<T>>,
+    size: usize,
+    free_oneway_space: usize,
+}
+
+struct FindEmptyRes {
+    /// Which index in `ranges` should we insert the new range at?
+    ///
+    /// Inserting the new range at this index keeps `ranges` sorted.
+    insert_at_idx: usize,
+    /// Which offset should we insert the new range at?
+    insert_at_offset: usize,
+}
+
+impl<T> ArrayRangeAllocator<T> {
+    pub(crate) fn new(size: usize, alloc: EmptyArrayAlloc<T>) -> Self {
+        Self {
+            ranges: alloc.ranges,
+            size,
+            free_oneway_space: size / 2,
+        }
+    }
+
+    pub(crate) fn free_oneway_space(&self) -> usize {
+        self.free_oneway_space
+    }
+
+    pub(crate) fn count_buffers(&self) -> usize {
+        self.ranges.len()
+    }
+
+    pub(crate) fn total_size(&self) -> usize {
+        self.size
+    }
+
+    pub(crate) fn is_full(&self) -> bool {
+        self.ranges.len() == self.ranges.capacity()
+    }
+
+    pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> {
+        for range in &self.ranges {
+            seq_print!(
+                m,
+                "  buffer {}: {} size {} pid {} oneway {}",
+                0,
+                range.offset,
+                range.size,
+                range.state.pid(),
+                range.state.is_oneway(),
+            );
+            if let DescriptorState::Reserved(_) = range.state {
+                seq_print!(m, " reserved\n");
+            } else {
+                seq_print!(m, " allocated\n");
+            }
+        }
+        Ok(())
+    }
+
+    /// Find somewhere to put a new range.
+    ///
+    /// Unlike the tree implementation, we do not bother to find the smallest gap. The idea is that
+    /// fragmentation isn't a big issue when we don't have many ranges.
+    ///
+    /// Returns the index that the new range should have in `self.ranges` after insertion.
+    fn find_empty_range(&self, size: usize) -> Option<FindEmptyRes> {
+        let after_last_range = self.ranges.last().map(Range::endpoint).unwrap_or(0);
+
+        if size <= self.total_size() - after_last_range {
+            // We can put the range at the end, so just do that.
+            Some(FindEmptyRes {
+                insert_at_idx: self.ranges.len(),
+                insert_at_offset: after_last_range,
+            })
+        } else {
+            let mut end_of_prev = 0;
+            for (i, range) in self.ranges.iter().enumerate() {
+                // Does it fit before the i'th range?
+                if size <= range.offset - end_of_prev {
+                    return Some(FindEmptyRes {
+                        insert_at_idx: i,
+                        insert_at_offset: end_of_prev,
+                    });
+                }
+                end_of_prev = range.endpoint();
+            }
+            None
+        }
+    }
+
+    pub(crate) fn reserve_new(
+        &mut self,
+        debug_id: usize,
+        size: usize,
+        is_oneway: bool,
+        pid: Pid,
+    ) -> Result<usize> {
+        // Compute new value of free_oneway_space, which is set only on success.
+        let new_oneway_space = if is_oneway {
+            match self.free_oneway_space.checked_sub(size) {
+                Some(new_oneway_space) => new_oneway_space,
+                None => return Err(ENOSPC),
+            }
+        } else {
+            self.free_oneway_space
+        };
+
+        let FindEmptyRes {
+            insert_at_idx,
+            insert_at_offset,
+        } = self.find_empty_range(size).ok_or(ENOSPC)?;
+        self.free_oneway_space = new_oneway_space;
+
+        let new_range = Range {
+            offset: insert_at_offset,
+            size,
+            state: DescriptorState::new(is_oneway, debug_id, pid),
+        };
+        // Insert the value at the given index to keep the array sorted.
+        self.ranges
+            .insert_within_capacity(insert_at_idx, new_range)
+            .ok()
+            .unwrap();
+
+        Ok(insert_at_offset)
+    }
+
+    pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> {
+        // This could use a binary search, but linear scans are usually faster for small arrays.
+        let i = self
+            .ranges
+            .iter()
+            .position(|range| range.offset == offset)
+            .ok_or(EINVAL)?;
+        let range = &self.ranges[i];
+
+        if let DescriptorState::Allocated(_) = range.state {
+            return Err(EPERM);
+        }
+
+        let size = range.size;
+        let offset = range.offset;
+
+        if range.state.is_oneway() {
+            self.free_oneway_space += size;
+        }
+
+        // This computes the range of pages that are no longer used by *any* allocated range. The
+        // caller will mark them as unused, which means that they can be freed if the system comes
+        // under memory pressure.
+        let mut freed_range = FreedRange::interior_pages(offset, size);
+        #[expect(clippy::collapsible_if)] // reads better like this
+        if offset % PAGE_SIZE != 0 {
+            if i == 0 || self.ranges[i - 1].endpoint() <= (offset & PAGE_MASK) {
+                freed_range.start_page_idx -= 1;
+            }
+        }
+        if range.endpoint() % PAGE_SIZE != 0 {
+            let page_after = (range.endpoint() & PAGE_MASK) + PAGE_SIZE;
+            if i + 1 == self.ranges.len() || page_after <= self.ranges[i + 1].offset {
+                freed_range.end_page_idx += 1;
+            }
+        }
+
+        self.ranges.remove(i)?;
+        Ok(freed_range)
+    }
+
+    pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result {
+        // This could use a binary search, but linear scans are usually faster for small arrays.
+        let range = self
+            .ranges
+            .iter_mut()
+            .find(|range| range.offset == offset)
+            .ok_or(ENOENT)?;
+
+        let DescriptorState::Reserved(reservation) = &range.state else {
+            return Err(ENOENT);
+        };
+
+        range.state = DescriptorState::Allocated(reservation.clone().allocate(data.take()));
+        Ok(())
+    }
+
+    pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> {
+        // This could use a binary search, but linear scans are usually faster for small arrays.
+        let range = self
+            .ranges
+            .iter_mut()
+            .find(|range| range.offset == offset)
+            .ok_or(ENOENT)?;
+
+        let DescriptorState::Allocated(allocation) = &mut range.state else {
+            return Err(ENOENT);
+        };
+
+        let data = allocation.take();
+        let debug_id = allocation.reservation.debug_id;
+        range.state = DescriptorState::Reserved(allocation.reservation.clone());
+        Ok((range.size, debug_id, data))
+    }
+
+    pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) {
+        for range in self.ranges.iter_mut() {
+            if let DescriptorState::Allocated(allocation) = &mut range.state {
+                callback(
+                    range.offset,
+                    range.size,
+                    allocation.reservation.debug_id,
+                    allocation.data.take(),
+                );
+            }
+        }
+    }
+}
+
+pub(crate) struct EmptyArrayAlloc<T> {
+    ranges: KVec<Range<T>>,
+}
+
+impl<T> EmptyArrayAlloc<T> {
+    pub(crate) fn try_new(capacity: usize) -> Result<Self> {
+        Ok(Self {
+            ranges: KVec::with_capacity(capacity, GFP_KERNEL)?,
+        })
+    }
+}
diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs
new file mode 100644
index 000000000000..2301e2bc1a1f
--- /dev/null
+++ b/drivers/android/binder/range_alloc/mod.rs
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{page::PAGE_SIZE, prelude::*, seq_file::SeqFile, task::Pid};
+
+mod tree;
+use self::tree::{FromArrayAllocs, ReserveNewTreeAlloc, TreeRangeAllocator};
+
+mod array;
+use self::array::{ArrayRangeAllocator, EmptyArrayAlloc};
+
+enum DescriptorState<T> {
+    Reserved(Reservation),
+    Allocated(Allocation<T>),
+}
+
+impl<T> DescriptorState<T> {
+    fn new(is_oneway: bool, debug_id: usize, pid: Pid) -> Self {
+        DescriptorState::Reserved(Reservation {
+            debug_id,
+            is_oneway,
+            pid,
+        })
+    }
+
+    fn pid(&self) -> Pid {
+        match self {
+            DescriptorState::Reserved(inner) => inner.pid,
+            DescriptorState::Allocated(inner) => inner.reservation.pid,
+        }
+    }
+
+    fn is_oneway(&self) -> bool {
+        match self {
+            DescriptorState::Reserved(inner) => inner.is_oneway,
+            DescriptorState::Allocated(inner) => inner.reservation.is_oneway,
+        }
+    }
+}
+
+#[derive(Clone)]
+struct Reservation {
+    debug_id: usize,
+    is_oneway: bool,
+    pid: Pid,
+}
+
+impl Reservation {
+    fn allocate<T>(self, data: Option<T>) -> Allocation<T> {
+        Allocation {
+            data,
+            reservation: self,
+        }
+    }
+}
+
+struct Allocation<T> {
+    reservation: Reservation,
+    data: Option<T>,
+}
+
+impl<T> Allocation<T> {
+    fn deallocate(self) -> (Reservation, Option<T>) {
+        (self.reservation, self.data)
+    }
+
+    fn debug_id(&self) -> usize {
+        self.reservation.debug_id
+    }
+
+    fn take(&mut self) -> Option<T> {
+        self.data.take()
+    }
+}
+
+/// The array implementation must switch to the tree if it wants to go beyond this number of
+/// ranges.
+const TREE_THRESHOLD: usize = 8;
+
+/// Represents a range of pages that have just become completely free.
+#[derive(Copy, Clone)]
+pub(crate) struct FreedRange {
+    pub(crate) start_page_idx: usize,
+    pub(crate) end_page_idx: usize,
+}
+
+impl FreedRange {
+    fn interior_pages(offset: usize, size: usize) -> FreedRange {
+        FreedRange {
+            // Divide round up
+            start_page_idx: offset.div_ceil(PAGE_SIZE),
+            // Divide round down
+            end_page_idx: (offset + size) / PAGE_SIZE,
+        }
+    }
+}
+
+struct Range<T> {
+    offset: usize,
+    size: usize,
+    state: DescriptorState<T>,
+}
+
+impl<T> Range<T> {
+    fn endpoint(&self) -> usize {
+        self.offset + self.size
+    }
+}
+
+pub(crate) struct RangeAllocator<T> {
+    inner: Impl<T>,
+}
+
+enum Impl<T> {
+    Empty(usize),
+    Array(ArrayRangeAllocator<T>),
+    Tree(TreeRangeAllocator<T>),
+}
+
+impl<T> RangeAllocator<T> {
+    pub(crate) fn new(size: usize) -> Self {
+        Self {
+            inner: Impl::Empty(size),
+        }
+    }
+
+    pub(crate) fn free_oneway_space(&self) -> usize {
+        match &self.inner {
+            Impl::Empty(size) => size / 2,
+            Impl::Array(array) => array.free_oneway_space(),
+            Impl::Tree(tree) => tree.free_oneway_space(),
+        }
+    }
+
+    pub(crate) fn count_buffers(&self) -> usize {
+        match &self.inner {
+            Impl::Empty(_size) => 0,
+            Impl::Array(array) => array.count_buffers(),
+            Impl::Tree(tree) => tree.count_buffers(),
+        }
+    }
+
+    pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> {
+        match &self.inner {
+            Impl::Empty(_size) => Ok(()),
+            Impl::Array(array) => array.debug_print(m),
+            Impl::Tree(tree) => tree.debug_print(m),
+        }
+    }
+
+    /// Try to reserve a new buffer, using the provided allocation if necessary.
+    pub(crate) fn reserve_new(&mut self, mut args: ReserveNewArgs<T>) -> Result<ReserveNew<T>> {
+        match &mut self.inner {
+            Impl::Empty(size) => {
+                let empty_array = match args.empty_array_alloc.take() {
+                    Some(empty_array) => ArrayRangeAllocator::new(*size, empty_array),
+                    None => {
+                        return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc {
+                            args,
+                            need_empty_array_alloc: true,
+                            need_new_tree_alloc: false,
+                            need_tree_alloc: false,
+                        }))
+                    }
+                };
+
+                self.inner = Impl::Array(empty_array);
+                self.reserve_new(args)
+            }
+            Impl::Array(array) if array.is_full() => {
+                let allocs = match args.new_tree_alloc {
+                    Some(ref mut allocs) => allocs,
+                    None => {
+                        return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc {
+                            args,
+                            need_empty_array_alloc: false,
+                            need_new_tree_alloc: true,
+                            need_tree_alloc: true,
+                        }))
+                    }
+                };
+
+                let new_tree =
+                    TreeRangeAllocator::from_array(array.total_size(), &mut array.ranges, allocs);
+
+                self.inner = Impl::Tree(new_tree);
+                self.reserve_new(args)
+            }
+            Impl::Array(array) => {
+                let offset =
+                    array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?;
+                Ok(ReserveNew::Success(ReserveNewSuccess {
+                    offset,
+                    oneway_spam_detected: false,
+                    _empty_array_alloc: args.empty_array_alloc,
+                    _new_tree_alloc: args.new_tree_alloc,
+                    _tree_alloc: args.tree_alloc,
+                }))
+            }
+            Impl::Tree(tree) => {
+                let alloc = match args.tree_alloc {
+                    Some(alloc) => alloc,
+                    None => {
+                        return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc {
+                            args,
+                            need_empty_array_alloc: false,
+                            need_new_tree_alloc: false,
+                            need_tree_alloc: true,
+                        }));
+                    }
+                };
+                let (offset, oneway_spam_detected) =
+                    tree.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid, alloc)?;
+                Ok(ReserveNew::Success(ReserveNewSuccess {
+                    offset,
+                    oneway_spam_detected,
+                    _empty_array_alloc: args.empty_array_alloc,
+                    _new_tree_alloc: args.new_tree_alloc,
+                    _tree_alloc: None,
+                }))
+            }
+        }
+    }
+
+    /// Deletes the allocations at `offset`.
+    pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> {
+        match &mut self.inner {
+            Impl::Empty(_size) => Err(EINVAL),
+            Impl::Array(array) => array.reservation_abort(offset),
+            Impl::Tree(tree) => {
+                let freed_range = tree.reservation_abort(offset)?;
+                if tree.is_empty() {
+                    self.inner = Impl::Empty(tree.total_size());
+                }
+                Ok(freed_range)
+            }
+        }
+    }
+
+    /// Called when an allocation is no longer in use by the kernel.
+    ///
+    /// The value in `data` will be stored, if any. A mutable reference is used to avoid dropping
+    /// the `T` when an error is returned.
+    pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result {
+        match &mut self.inner {
+            Impl::Empty(_size) => Err(EINVAL),
+            Impl::Array(array) => array.reservation_commit(offset, data),
+            Impl::Tree(tree) => tree.reservation_commit(offset, data),
+        }
+    }
+
+    /// Called when the kernel starts using an allocation.
+    ///
+    /// Returns the size of the existing entry and the data associated with it.
+    pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> {
+        match &mut self.inner {
+            Impl::Empty(_size) => Err(EINVAL),
+            Impl::Array(array) => array.reserve_existing(offset),
+            Impl::Tree(tree) => tree.reserve_existing(offset),
+        }
+    }
+
+    /// Call the provided callback at every allocated region.
+    ///
+    /// This destroys the range allocator. Used only during shutdown.
+    pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) {
+        match &mut self.inner {
+            Impl::Empty(_size) => {}
+            Impl::Array(array) => array.take_for_each(callback),
+            Impl::Tree(tree) => tree.take_for_each(callback),
+        }
+    }
+}
+
+/// The arguments for `reserve_new`.
+#[derive(Default)]
+pub(crate) struct ReserveNewArgs<T> {
+    pub(crate) size: usize,
+    pub(crate) is_oneway: bool,
+    pub(crate) debug_id: usize,
+    pub(crate) pid: Pid,
+    pub(crate) empty_array_alloc: Option<EmptyArrayAlloc<T>>,
+    pub(crate) new_tree_alloc: Option<FromArrayAllocs<T>>,
+    pub(crate) tree_alloc: Option<ReserveNewTreeAlloc<T>>,
+}
+
+/// The return type of `ReserveNew`.
+pub(crate) enum ReserveNew<T> {
+    Success(ReserveNewSuccess<T>),
+    NeedAlloc(ReserveNewNeedAlloc<T>),
+}
+
+/// Returned by `reserve_new` when the reservation was successul.
+pub(crate) struct ReserveNewSuccess<T> {
+    pub(crate) offset: usize,
+    pub(crate) oneway_spam_detected: bool,
+
+    // If the user supplied an allocation that we did not end up using, then we return it here.
+    // The caller will kfree it outside of the lock.
+    _empty_array_alloc: Option<EmptyArrayAlloc<T>>,
+    _new_tree_alloc: Option<FromArrayAllocs<T>>,
+    _tree_alloc: Option<ReserveNewTreeAlloc<T>>,
+}
+
+/// Returned by `reserve_new` to request the caller to make an allocation before calling the method
+/// again.
+pub(crate) struct ReserveNewNeedAlloc<T> {
+    args: ReserveNewArgs<T>,
+    need_empty_array_alloc: bool,
+    need_new_tree_alloc: bool,
+    need_tree_alloc: bool,
+}
+
+impl<T> ReserveNewNeedAlloc<T> {
+    /// Make the necessary allocations for another call to `reserve_new`.
+    pub(crate) fn make_alloc(mut self) -> Result<ReserveNewArgs<T>> {
+        if self.need_empty_array_alloc && self.args.empty_array_alloc.is_none() {
+            self.args.empty_array_alloc = Some(EmptyArrayAlloc::try_new(TREE_THRESHOLD)?);
+        }
+        if self.need_new_tree_alloc && self.args.new_tree_alloc.is_none() {
+            self.args.new_tree_alloc = Some(FromArrayAllocs::try_new(TREE_THRESHOLD)?);
+        }
+        if self.need_tree_alloc && self.args.tree_alloc.is_none() {
+            self.args.tree_alloc = Some(ReserveNewTreeAlloc::try_new()?);
+        }
+        Ok(self.args)
+    }
+}
diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs
new file mode 100644
index 000000000000..7b1a248fcb02
--- /dev/null
+++ b/drivers/android/binder/range_alloc/tree.rs
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::{
+    page::PAGE_SIZE,
+    prelude::*,
+    rbtree::{RBTree, RBTreeNode, RBTreeNodeReservation},
+    seq_file::SeqFile,
+    seq_print,
+    task::Pid,
+};
+
+use crate::range_alloc::{DescriptorState, FreedRange, Range};
+
+/// Keeps track of allocations in a process' mmap.
+///
+/// Each process has an mmap where the data for incoming transactions will be placed. This struct
+/// keeps track of allocations made in the mmap. For each allocation, we store a descriptor that
+/// has metadata related to the allocation. We also keep track of available free space.
+pub(super) struct TreeRangeAllocator<T> {
+    /// This collection contains descriptors for *both* ranges containing an allocation, *and* free
+    /// ranges between allocations. The free ranges get merged, so there are never two free ranges
+    /// next to each other.
+    tree: RBTree<usize, Descriptor<T>>,
+    /// Contains an entry for every free range in `self.tree`. This tree sorts the ranges by size,
+    /// letting us look up the smallest range whose size is at least some lower bound.
+    free_tree: RBTree<FreeKey, ()>,
+    size: usize,
+    free_oneway_space: usize,
+}
+
+impl<T> TreeRangeAllocator<T> {
+    pub(crate) fn from_array(
+        size: usize,
+        ranges: &mut KVec<Range<T>>,
+        alloc: &mut FromArrayAllocs<T>,
+    ) -> Self {
+        let mut tree = TreeRangeAllocator {
+            tree: RBTree::new(),
+            free_tree: RBTree::new(),
+            size,
+            free_oneway_space: size / 2,
+        };
+
+        let mut free_offset = 0;
+        for range in ranges.drain_all() {
+            let free_size = range.offset - free_offset;
+            if free_size > 0 {
+                let free_node = alloc.free_tree.pop().unwrap();
+                tree.free_tree
+                    .insert(free_node.into_node((free_size, free_offset), ()));
+                let tree_node = alloc.tree.pop().unwrap();
+                tree.tree.insert(
+                    tree_node.into_node(free_offset, Descriptor::new(free_offset, free_size)),
+                );
+            }
+            free_offset = range.endpoint();
+
+            if range.state.is_oneway() {
+                tree.free_oneway_space = tree.free_oneway_space.saturating_sub(range.size);
+            }
+
+            let free_res = alloc.free_tree.pop().unwrap();
+            let tree_node = alloc.tree.pop().unwrap();
+            let mut desc = Descriptor::new(range.offset, range.size);
+            desc.state = Some((range.state, free_res));
+            tree.tree.insert(tree_node.into_node(range.offset, desc));
+        }
+
+        // After the last range, we may need a free range.
+        if free_offset < size {
+            let free_size = size - free_offset;
+            let free_node = alloc.free_tree.pop().unwrap();
+            tree.free_tree
+                .insert(free_node.into_node((free_size, free_offset), ()));
+            let tree_node = alloc.tree.pop().unwrap();
+            tree.tree
+                .insert(tree_node.into_node(free_offset, Descriptor::new(free_offset, free_size)));
+        }
+
+        tree
+    }
+
+    pub(crate) fn is_empty(&self) -> bool {
+        let mut tree_iter = self.tree.values();
+        // There's always at least one range, because index zero is either the start of a free or
+        // allocated range.
+        let first_value = tree_iter.next().unwrap();
+        if tree_iter.next().is_some() {
+            // There are never two free ranges next to each other, so if there is more than one
+            // descriptor, then at least one of them must hold an allocated range.
+            return false;
+        }
+        // There is only one descriptor. Return true if it is for a free range.
+        first_value.state.is_none()
+    }
+
+    pub(crate) fn total_size(&self) -> usize {
+        self.size
+    }
+
+    pub(crate) fn free_oneway_space(&self) -> usize {
+        self.free_oneway_space
+    }
+
+    pub(crate) fn count_buffers(&self) -> usize {
+        self.tree
+            .values()
+            .filter(|desc| desc.state.is_some())
+            .count()
+    }
+
+    pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> {
+        for desc in self.tree.values() {
+            let state = match &desc.state {
+                Some(state) => &state.0,
+                None => continue,
+            };
+            seq_print!(
+                m,
+                "  buffer: {} size {} pid {}",
+                desc.offset,
+                desc.size,
+                state.pid(),
+            );
+            if state.is_oneway() {
+                seq_print!(m, " oneway");
+            }
+            match state {
+                DescriptorState::Reserved(_res) => {
+                    seq_print!(m, " reserved\n");
+                }
+                DescriptorState::Allocated(_alloc) => {
+                    seq_print!(m, " allocated\n");
+                }
+            }
+        }
+        Ok(())
+    }
+
+    fn find_best_match(&mut self, size: usize) -> Option<&mut Descriptor<T>> {
+        let free_cursor = self.free_tree.cursor_lower_bound(&(size, 0))?;
+        let ((_, offset), ()) = free_cursor.current();
+        self.tree.get_mut(offset)
+    }
+
+    /// Try to reserve a new buffer, using the provided allocation if necessary.
+    pub(crate) fn reserve_new(
+        &mut self,
+        debug_id: usize,
+        size: usize,
+        is_oneway: bool,
+        pid: Pid,
+        alloc: ReserveNewTreeAlloc<T>,
+    ) -> Result<(usize, bool)> {
+        // Compute new value of free_oneway_space, which is set only on success.
+        let new_oneway_space = if is_oneway {
+            match self.free_oneway_space.checked_sub(size) {
+                Some(new_oneway_space) => new_oneway_space,
+                None => return Err(ENOSPC),
+            }
+        } else {
+            self.free_oneway_space
+        };
+
+        // Start detecting spammers once we have less than 20%
+        // of async space left (which is less than 10% of total
+        // buffer size).
+        //
+        // (This will short-circut, so `low_oneway_space` is
+        // only called when necessary.)
+        let oneway_spam_detected =
+            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
+
+        let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) {
+            None => {
+                pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size);
+                return Err(ENOSPC);
+            }
+            Some(desc) => {
+                let found_size = desc.size;
+                let found_offset = desc.offset;
+
+                // In case we need to break up the descriptor
+                let new_desc = Descriptor::new(found_offset + size, found_size - size);
+                let (tree_node, free_tree_node, desc_node_res) = alloc.initialize(new_desc);
+
+                desc.state = Some((
+                    DescriptorState::new(is_oneway, debug_id, pid),
+                    desc_node_res,
+                ));
+                desc.size = size;
+
+                (found_size, found_offset, tree_node, free_tree_node)
+            }
+        };
+        self.free_oneway_space = new_oneway_space;
+        self.free_tree.remove(&(found_size, found_off));
+
+        if found_size != size {
+            self.tree.insert(tree_node);
+            self.free_tree.insert(free_tree_node);
+        }
+
+        Ok((found_off, oneway_spam_detected))
+    }
+
+    pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> {
+        let mut cursor = self.tree.cursor_lower_bound(&offset).ok_or_else(|| {
+            pr_warn!(
+                "EINVAL from range_alloc.reservation_abort - offset: {}",
+                offset
+            );
+            EINVAL
+        })?;
+
+        let (_, desc) = cursor.current_mut();
+
+        if desc.offset != offset {
+            pr_warn!(
+                "EINVAL from range_alloc.reservation_abort - offset: {}",
+                offset
+            );
+            return Err(EINVAL);
+        }
+
+        let (reservation, free_node_res) = desc.try_change_state(|state| match state {
+            Some((DescriptorState::Reserved(reservation), free_node_res)) => {
+                (None, Ok((reservation, free_node_res)))
+            }
+            None => {
+                pr_warn!(
+                    "EINVAL from range_alloc.reservation_abort - offset: {}",
+                    offset
+                );
+                (None, Err(EINVAL))
+            }
+            allocated => {
+                pr_warn!(
+                    "EPERM from range_alloc.reservation_abort - offset: {}",
+                    offset
+                );
+                (allocated, Err(EPERM))
+            }
+        })?;
+
+        let mut size = desc.size;
+        let mut offset = desc.offset;
+        let free_oneway_space_add = if reservation.is_oneway { size } else { 0 };
+
+        self.free_oneway_space += free_oneway_space_add;
+
+        let mut freed_range = FreedRange::interior_pages(offset, size);
+        // Compute how large the next free region needs to be to include one more page in
+        // the newly freed range.
+        let add_next_page_needed = match (offset + size) % PAGE_SIZE {
+            0 => usize::MAX,
+            unalign => PAGE_SIZE - unalign,
+        };
+        // Compute how large the previous free region needs to be to include one more page
+        // in the newly freed range.
+        let add_prev_page_needed = match offset % PAGE_SIZE {
+            0 => usize::MAX,
+            unalign => unalign,
+        };
+
+        // Merge next into current if next is free
+        let remove_next = match cursor.peek_next() {
+            Some((_, next)) if next.state.is_none() => {
+                if next.size >= add_next_page_needed {
+                    freed_range.end_page_idx += 1;
+                }
+                self.free_tree.remove(&(next.size, next.offset));
+                size += next.size;
+                true
+            }
+            _ => false,
+        };
+
+        if remove_next {
+            let (_, desc) = cursor.current_mut();
+            desc.size = size;
+            cursor.remove_next();
+        }
+
+        // Merge current into prev if prev is free
+        match cursor.peek_prev_mut() {
+            Some((_, prev)) if prev.state.is_none() => {
+                if prev.size >= add_prev_page_needed {
+                    freed_range.start_page_idx -= 1;
+                }
+                // merge previous with current, remove current
+                self.free_tree.remove(&(prev.size, prev.offset));
+                offset = prev.offset;
+                size += prev.size;
+                prev.size = size;
+                cursor.remove_current();
+            }
+            _ => {}
+        };
+
+        self.free_tree
+            .insert(free_node_res.into_node((size, offset), ()));
+
+        Ok(freed_range)
+    }
+
+    pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result {
+        let desc = self.tree.get_mut(&offset).ok_or(ENOENT)?;
+
+        desc.try_change_state(|state| match state {
+            Some((DescriptorState::Reserved(reservation), free_node_res)) => (
+                Some((
+                    DescriptorState::Allocated(reservation.allocate(data.take())),
+                    free_node_res,
+                )),
+                Ok(()),
+            ),
+            other => (other, Err(ENOENT)),
+        })
+    }
+
+    /// Takes an entry at the given offset from [`DescriptorState::Allocated`] to
+    /// [`DescriptorState::Reserved`].
+    ///
+    /// Returns the size of the existing entry and the data associated with it.
+    pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> {
+        let desc = self.tree.get_mut(&offset).ok_or_else(|| {
+            pr_warn!(
+                "ENOENT from range_alloc.reserve_existing - offset: {}",
+                offset
+            );
+            ENOENT
+        })?;
+
+        let (debug_id, data) = desc.try_change_state(|state| match state {
+            Some((DescriptorState::Allocated(allocation), free_node_res)) => {
+                let (reservation, data) = allocation.deallocate();
+                let debug_id = reservation.debug_id;
+                (
+                    Some((DescriptorState::Reserved(reservation), free_node_res)),
+                    Ok((debug_id, data)),
+                )
+            }
+            other => {
+                pr_warn!(
+                    "ENOENT from range_alloc.reserve_existing - offset: {}",
+                    offset
+                );
+                (other, Err(ENOENT))
+            }
+        })?;
+
+        Ok((desc.size, debug_id, data))
+    }
+
+    /// Call the provided callback at every allocated region.
+    ///
+    /// This destroys the range allocator. Used only during shutdown.
+    pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) {
+        for (_, desc) in self.tree.iter_mut() {
+            if let Some((DescriptorState::Allocated(allocation), _)) = &mut desc.state {
+                callback(
+                    desc.offset,
+                    desc.size,
+                    allocation.debug_id(),
+                    allocation.take(),
+                );
+            }
+        }
+    }
+
+    /// Find the amount and size of buffers allocated by the current caller.
+    ///
+    /// The idea is that once we cross the threshold, whoever is responsible
+    /// for the low async space is likely to try to send another async transaction,
+    /// and at some point we'll catch them in the act.  This is more efficient
+    /// than keeping a map per pid.
+    fn low_oneway_space(&self, calling_pid: Pid) -> bool {
+        let mut total_alloc_size = 0;
+        let mut num_buffers = 0;
+        for (_, desc) in self.tree.iter() {
+            if let Some((state, _)) = &desc.state {
+                if state.is_oneway() && state.pid() == calling_pid {
+                    total_alloc_size += desc.size;
+                    num_buffers += 1;
+                }
+            }
+        }
+
+        // Warn if this pid has more than 50 transactions, or more than 50% of
+        // async space (which is 25% of total buffer size). Oneway spam is only
+        // detected when the threshold is exceeded.
+        num_buffers > 50 || total_alloc_size > self.size / 4
+    }
+}
+
+type TreeDescriptorState<T> = (DescriptorState<T>, FreeNodeRes);
+struct Descriptor<T> {
+    size: usize,
+    offset: usize,
+    state: Option<TreeDescriptorState<T>>,
+}
+
+impl<T> Descriptor<T> {
+    fn new(offset: usize, size: usize) -> Self {
+        Self {
+            size,
+            offset,
+            state: None,
+        }
+    }
+
+    fn try_change_state<F, Data>(&mut self, f: F) -> Result<Data>
+    where
+        F: FnOnce(Option<TreeDescriptorState<T>>) -> (Option<TreeDescriptorState<T>>, Result<Data>),
+    {
+        let (new_state, result) = f(self.state.take());
+        self.state = new_state;
+        result
+    }
+}
+
+// (Descriptor.size, Descriptor.offset)
+type FreeKey = (usize, usize);
+type FreeNodeRes = RBTreeNodeReservation<FreeKey, ()>;
+
+/// An allocation for use by `reserve_new`.
+pub(crate) struct ReserveNewTreeAlloc<T> {
+    tree_node_res: RBTreeNodeReservation<usize, Descriptor<T>>,
+    free_tree_node_res: FreeNodeRes,
+    desc_node_res: FreeNodeRes,
+}
+
+impl<T> ReserveNewTreeAlloc<T> {
+    pub(crate) fn try_new() -> Result<Self> {
+        let tree_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        let free_tree_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        let desc_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?;
+        Ok(Self {
+            tree_node_res,
+            free_tree_node_res,
+            desc_node_res,
+        })
+    }
+
+    fn initialize(
+        self,
+        desc: Descriptor<T>,
+    ) -> (
+        RBTreeNode<usize, Descriptor<T>>,
+        RBTreeNode<FreeKey, ()>,
+        FreeNodeRes,
+    ) {
+        let size = desc.size;
+        let offset = desc.offset;
+        (
+            self.tree_node_res.into_node(offset, desc),
+            self.free_tree_node_res.into_node((size, offset), ()),
+            self.desc_node_res,
+        )
+    }
+}
+
+/// An allocation for creating a tree from an `ArrayRangeAllocator`.
+pub(crate) struct FromArrayAllocs<T> {
+    tree: KVec<RBTreeNodeReservation<usize, Descriptor<T>>>,
+    free_tree: KVec<RBTreeNodeReservation<FreeKey, ()>>,
+}
+
+impl<T> FromArrayAllocs<T> {
+    pub(crate) fn try_new(len: usize) -> Result<Self> {
+        let num_descriptors = 2 * len + 1;
+
+        let mut tree = KVec::with_capacity(num_descriptors, GFP_KERNEL)?;
+        for _ in 0..num_descriptors {
+            tree.push(RBTreeNodeReservation::new(GFP_KERNEL)?, GFP_KERNEL)?;
+        }
+
+        let mut free_tree = KVec::with_capacity(num_descriptors, GFP_KERNEL)?;
+        for _ in 0..num_descriptors {
+            free_tree.push(RBTreeNodeReservation::new(GFP_KERNEL)?, GFP_KERNEL)?;
+        }
+
+        Ok(Self { tree, free_tree })
+    }
+}
diff --git a/drivers/android/binder/rust_binder.h b/drivers/android/binder/rust_binder.h
new file mode 100644
index 000000000000..31806890ed1a
--- /dev/null
+++ b/drivers/android/binder/rust_binder.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025 Google, Inc.
+ */
+
+#ifndef _LINUX_RUST_BINDER_H
+#define _LINUX_RUST_BINDER_H
+
+#include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
+
+/*
+ * These symbols are exposed by `rust_binderfs.c` and exist here so that Rust
+ * Binder can call them.
+ */
+int init_rust_binderfs(void);
+
+struct dentry;
+struct inode;
+struct dentry *rust_binderfs_create_proc_file(struct inode *nodp, int pid);
+void rust_binderfs_remove_file(struct dentry *dentry);
+
+#endif
diff --git a/drivers/android/binder/rust_binder_events.c b/drivers/android/binder/rust_binder_events.c
new file mode 100644
index 000000000000..488b1470060c
--- /dev/null
+++ b/drivers/android/binder/rust_binder_events.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* rust_binder_events.c
+ *
+ * Rust Binder tracepoints.
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "rust_binder.h"
+
+const char * const binder_command_strings[] = {
+	"BC_TRANSACTION",
+	"BC_REPLY",
+	"BC_ACQUIRE_RESULT",
+	"BC_FREE_BUFFER",
+	"BC_INCREFS",
+	"BC_ACQUIRE",
+	"BC_RELEASE",
+	"BC_DECREFS",
+	"BC_INCREFS_DONE",
+	"BC_ACQUIRE_DONE",
+	"BC_ATTEMPT_ACQUIRE",
+	"BC_REGISTER_LOOPER",
+	"BC_ENTER_LOOPER",
+	"BC_EXIT_LOOPER",
+	"BC_REQUEST_DEATH_NOTIFICATION",
+	"BC_CLEAR_DEATH_NOTIFICATION",
+	"BC_DEAD_BINDER_DONE",
+	"BC_TRANSACTION_SG",
+	"BC_REPLY_SG",
+};
+
+const char * const binder_return_strings[] = {
+	"BR_ERROR",
+	"BR_OK",
+	"BR_TRANSACTION",
+	"BR_REPLY",
+	"BR_ACQUIRE_RESULT",
+	"BR_DEAD_REPLY",
+	"BR_TRANSACTION_COMPLETE",
+	"BR_INCREFS",
+	"BR_ACQUIRE",
+	"BR_RELEASE",
+	"BR_DECREFS",
+	"BR_ATTEMPT_ACQUIRE",
+	"BR_NOOP",
+	"BR_SPAWN_LOOPER",
+	"BR_FINISHED",
+	"BR_DEAD_BINDER",
+	"BR_CLEAR_DEATH_NOTIFICATION_DONE",
+	"BR_FAILED_REPLY",
+	"BR_FROZEN_REPLY",
+	"BR_ONEWAY_SPAM_SUSPECT",
+	"BR_TRANSACTION_PENDING_FROZEN"
+};
+
+#define CREATE_TRACE_POINTS
+#define CREATE_RUST_TRACE_POINTS
+#include "rust_binder_events.h"
diff --git a/drivers/android/binder/rust_binder_events.h b/drivers/android/binder/rust_binder_events.h
new file mode 100644
index 000000000000..2f3efbf9dba6
--- /dev/null
+++ b/drivers/android/binder/rust_binder_events.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 Google, Inc.
+ */
+
+#undef TRACE_SYSTEM
+#undef TRACE_INCLUDE_FILE
+#undef TRACE_INCLUDE_PATH
+#define TRACE_SYSTEM rust_binder
+#define TRACE_INCLUDE_FILE rust_binder_events
+#define TRACE_INCLUDE_PATH ../drivers/android/binder
+
+#if !defined(_RUST_BINDER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _RUST_BINDER_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(rust_binder_ioctl,
+	TP_PROTO(unsigned int cmd, unsigned long arg),
+	TP_ARGS(cmd, arg),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cmd)
+		__field(unsigned long, arg)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->arg = arg;
+	),
+	TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg)
+);
+
+#endif /* _RUST_BINDER_TRACE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/drivers/android/binder/rust_binder_internal.h b/drivers/android/binder/rust_binder_internal.h
new file mode 100644
index 000000000000..78288fe7964d
--- /dev/null
+++ b/drivers/android/binder/rust_binder_internal.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* rust_binder_internal.h
+ *
+ * This file contains internal data structures used by Rust Binder. Mostly,
+ * these are type definitions used only by binderfs or things that Rust Binder
+ * define and export to binderfs.
+ *
+ * It does not include things exported by binderfs to Rust Binder since this
+ * file is not included as input to bindgen.
+ *
+ * Copyright (C) 2025 Google LLC.
+ */
+
+#ifndef _LINUX_RUST_BINDER_INTERNAL_H
+#define _LINUX_RUST_BINDER_INTERNAL_H
+
+#define RUST_BINDERFS_SUPER_MAGIC	0x6c6f6f71
+
+#include <linux/seq_file.h>
+#include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
+
+/*
+ * The internal data types in the Rust Binder driver are opaque to C, so we use
+ * void pointer typedefs for these types.
+ */
+typedef void *rust_binder_context;
+
+/**
+ * struct binder_device - information about a binder device node
+ * @minor:     the minor number used by this device
+ * @ctx:       the Rust Context used by this device, or null for binder-control
+ *
+ * This is used as the private data for files directly in binderfs, but not
+ * files in the binder_logs subdirectory. This struct owns a refcount on `ctx`
+ * and the entry for `minor` in `binderfs_minors`. For binder-control `ctx` is
+ * null.
+ */
+struct binder_device {
+	int minor;
+	rust_binder_context ctx;
+};
+
+int rust_binder_stats_show(struct seq_file *m, void *unused);
+int rust_binder_state_show(struct seq_file *m, void *unused);
+int rust_binder_transactions_show(struct seq_file *m, void *unused);
+int rust_binder_proc_show(struct seq_file *m, void *pid);
+
+extern const struct file_operations rust_binder_fops;
+rust_binder_context rust_binder_new_context(char *name);
+void rust_binder_remove_context(rust_binder_context device);
+
+/**
+ * binderfs_mount_opts - mount options for binderfs
+ * @max: maximum number of allocatable binderfs binder devices
+ * @stats_mode: enable binder stats in binderfs.
+ */
+struct binderfs_mount_opts {
+	int max;
+	int stats_mode;
+};
+
+/**
+ * binderfs_info - information about a binderfs mount
+ * @ipc_ns:         The ipc namespace the binderfs mount belongs to.
+ * @control_dentry: This records the dentry of this binderfs mount
+ *                  binder-control device.
+ * @root_uid:       uid that needs to be used when a new binder device is
+ *                  created.
+ * @root_gid:       gid that needs to be used when a new binder device is
+ *                  created.
+ * @mount_opts:     The mount options in use.
+ * @device_count:   The current number of allocated binder devices.
+ * @proc_log_dir:   Pointer to the directory dentry containing process-specific
+ *                  logs.
+ */
+struct binderfs_info {
+	struct ipc_namespace *ipc_ns;
+	struct dentry *control_dentry;
+	kuid_t root_uid;
+	kgid_t root_gid;
+	struct binderfs_mount_opts mount_opts;
+	int device_count;
+	struct dentry *proc_log_dir;
+};
+
+#endif /* _LINUX_RUST_BINDER_INTERNAL_H */
diff --git a/drivers/android/binder/rust_binder_main.rs b/drivers/android/binder/rust_binder_main.rs
new file mode 100644
index 000000000000..6773b7c273ec
--- /dev/null
+++ b/drivers/android/binder/rust_binder_main.rs
@@ -0,0 +1,627 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! Binder -- the Android IPC mechanism.
+#![recursion_limit = "256"]
+#![allow(
+    clippy::as_underscore,
+    clippy::ref_as_ptr,
+    clippy::ptr_as_ptr,
+    clippy::cast_lossless
+)]
+
+use kernel::{
+    bindings::{self, seq_file},
+    fs::File,
+    list::{ListArc, ListArcSafe, ListLinksSelfPtr, TryNewListArc},
+    prelude::*,
+    seq_file::SeqFile,
+    seq_print,
+    sync::poll::PollTable,
+    sync::Arc,
+    task::Pid,
+    transmute::AsBytes,
+    types::ForeignOwnable,
+    uaccess::UserSliceWriter,
+};
+
+use crate::{context::Context, page_range::Shrinker, process::Process, thread::Thread};
+
+use core::{
+    ptr::NonNull,
+    sync::atomic::{AtomicBool, AtomicUsize, Ordering},
+};
+
+mod allocation;
+mod context;
+mod deferred_close;
+mod defs;
+mod error;
+mod node;
+mod page_range;
+mod process;
+mod range_alloc;
+mod stats;
+mod thread;
+mod trace;
+mod transaction;
+
+#[allow(warnings)] // generated bindgen code
+mod binderfs {
+    use kernel::bindings::{dentry, inode};
+
+    extern "C" {
+        pub fn init_rust_binderfs() -> kernel::ffi::c_int;
+    }
+    extern "C" {
+        pub fn rust_binderfs_create_proc_file(
+            nodp: *mut inode,
+            pid: kernel::ffi::c_int,
+        ) -> *mut dentry;
+    }
+    extern "C" {
+        pub fn rust_binderfs_remove_file(dentry: *mut dentry);
+    }
+    pub type rust_binder_context = *mut kernel::ffi::c_void;
+    #[repr(C)]
+    #[derive(Copy, Clone)]
+    pub struct binder_device {
+        pub minor: kernel::ffi::c_int,
+        pub ctx: rust_binder_context,
+    }
+    impl Default for binder_device {
+        fn default() -> Self {
+            let mut s = ::core::mem::MaybeUninit::<Self>::uninit();
+            unsafe {
+                ::core::ptr::write_bytes(s.as_mut_ptr(), 0, 1);
+                s.assume_init()
+            }
+        }
+    }
+}
+
+module! {
+    type: BinderModule,
+    name: "rust_binder",
+    authors: ["Wedson Almeida Filho", "Alice Ryhl"],
+    description: "Android Binder",
+    license: "GPL",
+}
+
+fn next_debug_id() -> usize {
+    static NEXT_DEBUG_ID: AtomicUsize = AtomicUsize::new(0);
+
+    NEXT_DEBUG_ID.fetch_add(1, Ordering::Relaxed)
+}
+
+/// Provides a single place to write Binder return values via the
+/// supplied `UserSliceWriter`.
+pub(crate) struct BinderReturnWriter<'a> {
+    writer: UserSliceWriter,
+    thread: &'a Thread,
+}
+
+impl<'a> BinderReturnWriter<'a> {
+    fn new(writer: UserSliceWriter, thread: &'a Thread) -> Self {
+        BinderReturnWriter { writer, thread }
+    }
+
+    /// Write a return code back to user space.
+    /// Should be a `BR_` constant from [`defs`] e.g. [`defs::BR_TRANSACTION_COMPLETE`].
+    fn write_code(&mut self, code: u32) -> Result {
+        stats::GLOBAL_STATS.inc_br(code);
+        self.thread.process.stats.inc_br(code);
+        self.writer.write(&code)
+    }
+
+    /// Write something *other than* a return code to user space.
+    fn write_payload<T: AsBytes>(&mut self, payload: &T) -> Result {
+        self.writer.write(payload)
+    }
+
+    fn len(&self) -> usize {
+        self.writer.len()
+    }
+}
+
+/// Specifies how a type should be delivered to the read part of a BINDER_WRITE_READ ioctl.
+///
+/// When a value is pushed to the todo list for a process or thread, it is stored as a trait object
+/// with the type `Arc<dyn DeliverToRead>`. Trait objects are a Rust feature that lets you
+/// implement dynamic dispatch over many different types. This lets us store many different types
+/// in the todo list.
+trait DeliverToRead: ListArcSafe + Send + Sync {
+    /// Performs work. Returns true if remaining work items in the queue should be processed
+    /// immediately, or false if it should return to caller before processing additional work
+    /// items.
+    fn do_work(
+        self: DArc<Self>,
+        thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool>;
+
+    /// Cancels the given work item. This is called instead of [`DeliverToRead::do_work`] when work
+    /// won't be delivered.
+    fn cancel(self: DArc<Self>);
+
+    /// Should we use `wake_up_interruptible_sync` or `wake_up_interruptible` when scheduling this
+    /// work item?
+    ///
+    /// Generally only set to true for non-oneway transactions.
+    fn should_sync_wakeup(&self) -> bool;
+
+    fn debug_print(&self, m: &SeqFile, prefix: &str, transaction_prefix: &str) -> Result<()>;
+}
+
+// Wrapper around a `DeliverToRead` with linked list links.
+#[pin_data]
+struct DTRWrap<T: ?Sized> {
+    #[pin]
+    links: ListLinksSelfPtr<DTRWrap<dyn DeliverToRead>>,
+    #[pin]
+    wrapped: T,
+}
+kernel::list::impl_list_arc_safe! {
+    impl{T: ListArcSafe + ?Sized} ListArcSafe<0> for DTRWrap<T> {
+        tracked_by wrapped: T;
+    }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<0> for DTRWrap<dyn DeliverToRead> {
+        using ListLinksSelfPtr { self.links };
+    }
+}
+
+impl<T: ?Sized> core::ops::Deref for DTRWrap<T> {
+    type Target = T;
+    fn deref(&self) -> &T {
+        &self.wrapped
+    }
+}
+
+type DArc<T> = kernel::sync::Arc<DTRWrap<T>>;
+type DLArc<T> = kernel::list::ListArc<DTRWrap<T>>;
+
+impl<T: ListArcSafe> DTRWrap<T> {
+    fn new(val: impl PinInit<T>) -> impl PinInit<Self> {
+        pin_init!(Self {
+            links <- ListLinksSelfPtr::new(),
+            wrapped <- val,
+        })
+    }
+
+    fn arc_try_new(val: T) -> Result<DLArc<T>, kernel::alloc::AllocError> {
+        ListArc::pin_init(
+            try_pin_init!(Self {
+                links <- ListLinksSelfPtr::new(),
+                wrapped: val,
+            }),
+            GFP_KERNEL,
+        )
+        .map_err(|_| kernel::alloc::AllocError)
+    }
+
+    fn arc_pin_init(init: impl PinInit<T>) -> Result<DLArc<T>, kernel::error::Error> {
+        ListArc::pin_init(
+            try_pin_init!(Self {
+                links <- ListLinksSelfPtr::new(),
+                wrapped <- init,
+            }),
+            GFP_KERNEL,
+        )
+    }
+}
+
+struct DeliverCode {
+    code: u32,
+    skip: AtomicBool,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for DeliverCode { untracked; }
+}
+
+impl DeliverCode {
+    fn new(code: u32) -> Self {
+        Self {
+            code,
+            skip: AtomicBool::new(false),
+        }
+    }
+
+    /// Disable this DeliverCode and make it do nothing.
+    ///
+    /// This is used instead of removing it from the work list, since `LinkedList::remove` is
+    /// unsafe, whereas this method is not.
+    fn skip(&self) {
+        self.skip.store(true, Ordering::Relaxed);
+    }
+}
+
+impl DeliverToRead for DeliverCode {
+    fn do_work(
+        self: DArc<Self>,
+        _thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        if !self.skip.load(Ordering::Relaxed) {
+            writer.write_code(self.code)?;
+        }
+        Ok(true)
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        seq_print!(m, "{}", prefix);
+        if self.skip.load(Ordering::Relaxed) {
+            seq_print!(m, "(skipped) ");
+        }
+        if self.code == defs::BR_TRANSACTION_COMPLETE {
+            seq_print!(m, "transaction complete\n");
+        } else {
+            seq_print!(m, "transaction error: {}\n", self.code);
+        }
+        Ok(())
+    }
+}
+
+fn ptr_align(value: usize) -> Option<usize> {
+    let size = core::mem::size_of::<usize>() - 1;
+    Some(value.checked_add(size)? & !size)
+}
+
+// SAFETY: We call register in `init`.
+static BINDER_SHRINKER: Shrinker = unsafe { Shrinker::new() };
+
+struct BinderModule {}
+
+impl kernel::Module for BinderModule {
+    fn init(_module: &'static kernel::ThisModule) -> Result<Self> {
+        // SAFETY: The module initializer never runs twice, so we only call this once.
+        unsafe { crate::context::CONTEXTS.init() };
+
+        pr_warn!("Loaded Rust Binder.");
+
+        BINDER_SHRINKER.register(kernel::c_str!("android-binder"))?;
+
+        // SAFETY: The module is being loaded, so we can initialize binderfs.
+        unsafe { kernel::error::to_result(binderfs::init_rust_binderfs())? };
+
+        Ok(Self {})
+    }
+}
+
+/// Makes the inner type Sync.
+#[repr(transparent)]
+pub struct AssertSync<T>(T);
+// SAFETY: Used only to insert `file_operations` into a global, which is safe.
+unsafe impl<T> Sync for AssertSync<T> {}
+
+/// File operations that rust_binderfs.c can use.
+#[no_mangle]
+#[used]
+pub static rust_binder_fops: AssertSync<kernel::bindings::file_operations> = {
+    // SAFETY: All zeroes is safe for the `file_operations` type.
+    let zeroed_ops = unsafe { core::mem::MaybeUninit::zeroed().assume_init() };
+
+    let ops = kernel::bindings::file_operations {
+        owner: THIS_MODULE.as_ptr(),
+        poll: Some(rust_binder_poll),
+        unlocked_ioctl: Some(rust_binder_unlocked_ioctl),
+        compat_ioctl: Some(rust_binder_compat_ioctl),
+        mmap: Some(rust_binder_mmap),
+        open: Some(rust_binder_open),
+        release: Some(rust_binder_release),
+        flush: Some(rust_binder_flush),
+        ..zeroed_ops
+    };
+    AssertSync(ops)
+};
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_new_context(
+    name: *const kernel::ffi::c_char,
+) -> *mut kernel::ffi::c_void {
+    // SAFETY: The caller will always provide a valid c string here.
+    let name = unsafe { kernel::str::CStr::from_char_ptr(name) };
+    match Context::new(name) {
+        Ok(ctx) => Arc::into_foreign(ctx),
+        Err(_err) => core::ptr::null_mut(),
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_remove_context(device: *mut kernel::ffi::c_void) {
+    if !device.is_null() {
+        // SAFETY: The caller ensures that the `device` pointer came from a previous call to
+        // `rust_binder_new_device`.
+        let ctx = unsafe { Arc::<Context>::from_foreign(device) };
+        ctx.deregister();
+        drop(ctx);
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_open(
+    inode: *mut bindings::inode,
+    file_ptr: *mut bindings::file,
+) -> kernel::ffi::c_int {
+    // SAFETY: The `rust_binderfs.c` file ensures that `i_private` is set to a
+    // `struct binder_device`.
+    let device = unsafe { (*inode).i_private } as *const binderfs::binder_device;
+
+    assert!(!device.is_null());
+
+    // SAFETY: The `rust_binderfs.c` file ensures that `device->ctx` holds a binder context when
+    // using the rust binder fops.
+    let ctx = unsafe { Arc::<Context>::borrow((*device).ctx) };
+
+    // SAFETY: The caller provides a valid file pointer to a new `struct file`.
+    let file = unsafe { File::from_raw_file(file_ptr) };
+    let process = match Process::open(ctx, file) {
+        Ok(process) => process,
+        Err(err) => return err.to_errno(),
+    };
+
+    // SAFETY: This is an `inode` for a newly created binder file.
+    match unsafe { BinderfsProcFile::new(inode, process.task.pid()) } {
+        Ok(Some(file)) => process.inner.lock().binderfs_file = Some(file),
+        Ok(None) => { /* pid already exists */ }
+        Err(err) => return err.to_errno(),
+    }
+
+    // SAFETY: This file is associated with Rust binder, so we own the `private_data` field.
+    unsafe { (*file_ptr).private_data = process.into_foreign() };
+    0
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_release(
+    _inode: *mut bindings::inode,
+    file: *mut bindings::file,
+) -> kernel::ffi::c_int {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let process = unsafe { Arc::<Process>::from_foreign((*file).private_data) };
+    // SAFETY: The caller ensures that the file is valid.
+    let file = unsafe { File::from_raw_file(file) };
+    Process::release(process, file);
+    0
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_compat_ioctl(
+    file: *mut bindings::file,
+    cmd: kernel::ffi::c_uint,
+    arg: kernel::ffi::c_ulong,
+) -> kernel::ffi::c_long {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let f = unsafe { Arc::<Process>::borrow((*file).private_data) };
+    // SAFETY: The caller ensures that the file is valid.
+    match Process::compat_ioctl(f, unsafe { File::from_raw_file(file) }, cmd as _, arg as _) {
+        Ok(()) => 0,
+        Err(err) => err.to_errno() as isize,
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_unlocked_ioctl(
+    file: *mut bindings::file,
+    cmd: kernel::ffi::c_uint,
+    arg: kernel::ffi::c_ulong,
+) -> kernel::ffi::c_long {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let f = unsafe { Arc::<Process>::borrow((*file).private_data) };
+    // SAFETY: The caller ensures that the file is valid.
+    match Process::ioctl(f, unsafe { File::from_raw_file(file) }, cmd as _, arg as _) {
+        Ok(()) => 0,
+        Err(err) => err.to_errno() as isize,
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_mmap(
+    file: *mut bindings::file,
+    vma: *mut bindings::vm_area_struct,
+) -> kernel::ffi::c_int {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let f = unsafe { Arc::<Process>::borrow((*file).private_data) };
+    // SAFETY: The caller ensures that the vma is valid.
+    let area = unsafe { kernel::mm::virt::VmaNew::from_raw(vma) };
+    // SAFETY: The caller ensures that the file is valid.
+    match Process::mmap(f, unsafe { File::from_raw_file(file) }, area) {
+        Ok(()) => 0,
+        Err(err) => err.to_errno(),
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_poll(
+    file: *mut bindings::file,
+    wait: *mut bindings::poll_table_struct,
+) -> bindings::__poll_t {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let f = unsafe { Arc::<Process>::borrow((*file).private_data) };
+    // SAFETY: The caller ensures that the file is valid.
+    let fileref = unsafe { File::from_raw_file(file) };
+    // SAFETY: The caller ensures that the `PollTable` is valid.
+    match Process::poll(f, fileref, unsafe { PollTable::from_raw(wait) }) {
+        Ok(v) => v,
+        Err(_) => bindings::POLLERR,
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+unsafe extern "C" fn rust_binder_flush(
+    file: *mut bindings::file,
+    _id: bindings::fl_owner_t,
+) -> kernel::ffi::c_int {
+    // SAFETY: We previously set `private_data` in `rust_binder_open`.
+    let f = unsafe { Arc::<Process>::borrow((*file).private_data) };
+    match Process::flush(f) {
+        Ok(()) => 0,
+        Err(err) => err.to_errno(),
+    }
+}
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_stats_show(
+    ptr: *mut seq_file,
+    _: *mut kernel::ffi::c_void,
+) -> kernel::ffi::c_int {
+    // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which
+    // this method is called.
+    let m = unsafe { SeqFile::from_raw(ptr) };
+    if let Err(err) = rust_binder_stats_show_impl(m) {
+        seq_print!(m, "failed to generate state: {:?}\n", err);
+    }
+    0
+}
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_state_show(
+    ptr: *mut seq_file,
+    _: *mut kernel::ffi::c_void,
+) -> kernel::ffi::c_int {
+    // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which
+    // this method is called.
+    let m = unsafe { SeqFile::from_raw(ptr) };
+    if let Err(err) = rust_binder_state_show_impl(m) {
+        seq_print!(m, "failed to generate state: {:?}\n", err);
+    }
+    0
+}
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_proc_show(
+    ptr: *mut seq_file,
+    _: *mut kernel::ffi::c_void,
+) -> kernel::ffi::c_int {
+    // SAFETY: Accessing the private field of `seq_file` is okay.
+    let pid = (unsafe { (*ptr).private }) as usize as Pid;
+    // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which
+    // this method is called.
+    let m = unsafe { SeqFile::from_raw(ptr) };
+    if let Err(err) = rust_binder_proc_show_impl(m, pid) {
+        seq_print!(m, "failed to generate state: {:?}\n", err);
+    }
+    0
+}
+
+/// # Safety
+/// Only called by binderfs.
+#[no_mangle]
+unsafe extern "C" fn rust_binder_transactions_show(
+    ptr: *mut seq_file,
+    _: *mut kernel::ffi::c_void,
+) -> kernel::ffi::c_int {
+    // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which
+    // this method is called.
+    let m = unsafe { SeqFile::from_raw(ptr) };
+    if let Err(err) = rust_binder_transactions_show_impl(m) {
+        seq_print!(m, "failed to generate state: {:?}\n", err);
+    }
+    0
+}
+
+fn rust_binder_transactions_show_impl(m: &SeqFile) -> Result<()> {
+    seq_print!(m, "binder transactions:\n");
+    let contexts = context::get_all_contexts()?;
+    for ctx in contexts {
+        let procs = ctx.get_all_procs()?;
+        for proc in procs {
+            proc.debug_print(m, &ctx, false)?;
+            seq_print!(m, "\n");
+        }
+    }
+    Ok(())
+}
+
+fn rust_binder_stats_show_impl(m: &SeqFile) -> Result<()> {
+    seq_print!(m, "binder stats:\n");
+    stats::GLOBAL_STATS.debug_print("", m);
+    let contexts = context::get_all_contexts()?;
+    for ctx in contexts {
+        let procs = ctx.get_all_procs()?;
+        for proc in procs {
+            proc.debug_print_stats(m, &ctx)?;
+            seq_print!(m, "\n");
+        }
+    }
+    Ok(())
+}
+
+fn rust_binder_state_show_impl(m: &SeqFile) -> Result<()> {
+    seq_print!(m, "binder state:\n");
+    let contexts = context::get_all_contexts()?;
+    for ctx in contexts {
+        let procs = ctx.get_all_procs()?;
+        for proc in procs {
+            proc.debug_print(m, &ctx, true)?;
+            seq_print!(m, "\n");
+        }
+    }
+    Ok(())
+}
+
+fn rust_binder_proc_show_impl(m: &SeqFile, pid: Pid) -> Result<()> {
+    seq_print!(m, "binder proc state:\n");
+    let contexts = context::get_all_contexts()?;
+    for ctx in contexts {
+        let procs = ctx.get_procs_with_pid(pid)?;
+        for proc in procs {
+            proc.debug_print(m, &ctx, true)?;
+            seq_print!(m, "\n");
+        }
+    }
+    Ok(())
+}
+
+struct BinderfsProcFile(NonNull<bindings::dentry>);
+
+// SAFETY: Safe to drop any thread.
+unsafe impl Send for BinderfsProcFile {}
+
+impl BinderfsProcFile {
+    /// # Safety
+    ///
+    /// Takes an inode from a newly created binder file.
+    unsafe fn new(nodp: *mut bindings::inode, pid: i32) -> Result<Option<Self>> {
+        // SAFETY: The caller passes an `inode` for a newly created binder file.
+        let dentry = unsafe { binderfs::rust_binderfs_create_proc_file(nodp, pid) };
+        match kernel::error::from_err_ptr(dentry) {
+            Ok(dentry) => Ok(NonNull::new(dentry).map(Self)),
+            Err(err) if err == EEXIST => Ok(None),
+            Err(err) => Err(err),
+        }
+    }
+}
+
+impl Drop for BinderfsProcFile {
+    fn drop(&mut self) {
+        // SAFETY: This is a dentry from `rust_binderfs_remove_file` that has not been deleted yet.
+        unsafe { binderfs::rust_binderfs_remove_file(self.0.as_ptr()) };
+    }
+}
diff --git a/drivers/android/binder/rust_binderfs.c b/drivers/android/binder/rust_binderfs.c
new file mode 100644
index 000000000000..6b497146b698
--- /dev/null
+++ b/drivers/android/binder/rust_binderfs.c
@@ -0,0 +1,850 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/compiler_types.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/gfp.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/ipc_namespace.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/namei.h>
+#include <linux/magic.h>
+#include <linux/major.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mount.h>
+#include <linux/fs_parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/user_namespace.h>
+#include <linux/xarray.h>
+#include <uapi/asm-generic/errno-base.h>
+#include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
+
+#include "rust_binder.h"
+#include "rust_binder_internal.h"
+
+#define FIRST_INODE 1
+#define SECOND_INODE 2
+#define INODE_OFFSET 3
+#define BINDERFS_MAX_MINOR (1U << MINORBITS)
+/* Ensure that the initial ipc namespace always has devices available. */
+#define BINDERFS_MAX_MINOR_CAPPED (BINDERFS_MAX_MINOR - 4)
+
+DEFINE_SHOW_ATTRIBUTE(rust_binder_stats);
+DEFINE_SHOW_ATTRIBUTE(rust_binder_state);
+DEFINE_SHOW_ATTRIBUTE(rust_binder_transactions);
+DEFINE_SHOW_ATTRIBUTE(rust_binder_proc);
+
+char *rust_binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES;
+module_param_named(rust_devices, rust_binder_devices_param, charp, 0444);
+
+static dev_t binderfs_dev;
+static DEFINE_MUTEX(binderfs_minors_mutex);
+static DEFINE_IDA(binderfs_minors);
+
+enum binderfs_param {
+	Opt_max,
+	Opt_stats_mode,
+};
+
+enum binderfs_stats_mode {
+	binderfs_stats_mode_unset,
+	binderfs_stats_mode_global,
+};
+
+struct binder_features {
+	bool oneway_spam_detection;
+	bool extended_error;
+	bool freeze_notification;
+};
+
+static const struct constant_table binderfs_param_stats[] = {
+	{ "global", binderfs_stats_mode_global },
+	{}
+};
+
+static const struct fs_parameter_spec binderfs_fs_parameters[] = {
+	fsparam_u32("max",	Opt_max),
+	fsparam_enum("stats",	Opt_stats_mode, binderfs_param_stats),
+	{}
+};
+
+static struct binder_features binder_features = {
+	.oneway_spam_detection = true,
+	.extended_error = true,
+	.freeze_notification = true,
+};
+
+static inline struct binderfs_info *BINDERFS_SB(const struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/**
+ * binderfs_binder_device_create - allocate inode from super block of a
+ *                                 binderfs mount
+ * @ref_inode: inode from wich the super block will be taken
+ * @userp:     buffer to copy information about new device for userspace to
+ * @req:       struct binderfs_device as copied from userspace
+ *
+ * This function allocates a new binder_device and reserves a new minor
+ * number for it.
+ * Minor numbers are limited and tracked globally in binderfs_minors. The
+ * function will stash a struct binder_device for the specific binder
+ * device in i_private of the inode.
+ * It will go on to allocate a new inode from the super block of the
+ * filesystem mount, stash a struct binder_device in its i_private field
+ * and attach a dentry to that inode.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_device_create(struct inode *ref_inode,
+					 struct binderfs_device __user *userp,
+					 struct binderfs_device *req)
+{
+	int minor, ret;
+	struct dentry *dentry, *root;
+	struct binder_device *device = NULL;
+	rust_binder_context ctx = NULL;
+	struct inode *inode = NULL;
+	struct super_block *sb = ref_inode->i_sb;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	/* Reserve new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	if (++info->device_count <= info->mount_opts.max)
+		minor = ida_alloc_max(&binderfs_minors,
+				      use_reserve ? BINDERFS_MAX_MINOR :
+						    BINDERFS_MAX_MINOR_CAPPED,
+				      GFP_KERNEL);
+	else
+		minor = -ENOSPC;
+	if (minor < 0) {
+		--info->device_count;
+		mutex_unlock(&binderfs_minors_mutex);
+		return minor;
+	}
+	mutex_unlock(&binderfs_minors_mutex);
+
+	ret = -ENOMEM;
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		goto err;
+
+	req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */
+
+	ctx = rust_binder_new_context(req->name);
+	if (!ctx)
+		goto err;
+
+	inode = new_inode(sb);
+	if (!inode)
+		goto err;
+
+	inode->i_ino = minor + INODE_OFFSET;
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &rust_binder_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	req->major = MAJOR(binderfs_dev);
+	req->minor = minor;
+	device->ctx = ctx;
+	device->minor = minor;
+
+	if (userp && copy_to_user(userp, req, sizeof(*req))) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	root = sb->s_root;
+	inode_lock(d_inode(root));
+
+	/* look it up */
+	dentry = lookup_noperm(&QSTR(req->name), root);
+	if (IS_ERR(dentry)) {
+		inode_unlock(d_inode(root));
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	if (d_really_is_positive(dentry)) {
+		/* already exists */
+		dput(dentry);
+		inode_unlock(d_inode(root));
+		ret = -EEXIST;
+		goto err;
+	}
+
+	inode->i_private = device;
+	d_instantiate(dentry, inode);
+	fsnotify_create(root->d_inode, dentry);
+	inode_unlock(d_inode(root));
+
+	return 0;
+
+err:
+	kfree(device);
+	rust_binder_remove_context(ctx);
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, minor);
+	mutex_unlock(&binderfs_minors_mutex);
+	iput(inode);
+
+	return ret;
+}
+
+/**
+ * binder_ctl_ioctl - handle binder device node allocation requests
+ *
+ * The request handler for the binder-control device. All requests operate on
+ * the binderfs mount the binder-control device resides in:
+ * - BINDER_CTL_ADD
+ *   Allocate a new binder device.
+ *
+ * Return: %0 on success, negative errno on failure.
+ */
+static long binder_ctl_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	int ret = -EINVAL;
+	struct inode *inode = file_inode(file);
+	struct binderfs_device __user *device = (struct binderfs_device __user *)arg;
+	struct binderfs_device device_req;
+
+	switch (cmd) {
+	case BINDER_CTL_ADD:
+		ret = copy_from_user(&device_req, device, sizeof(device_req));
+		if (ret) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret = binderfs_binder_device_create(inode, device, &device_req);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void binderfs_evict_inode(struct inode *inode)
+{
+	struct binder_device *device = inode->i_private;
+	struct binderfs_info *info = BINDERFS_SB(inode->i_sb);
+
+	clear_inode(inode);
+
+	if (!S_ISCHR(inode->i_mode) || !device)
+		return;
+
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, device->minor);
+	mutex_unlock(&binderfs_minors_mutex);
+
+	/* ctx is null for binder-control, but this function ignores null pointers */
+	rust_binder_remove_context(device->ctx);
+
+	kfree(device);
+}
+
+static int binderfs_fs_context_parse_param(struct fs_context *fc,
+					   struct fs_parameter *param)
+{
+	int opt;
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct fs_parse_result result;
+
+	opt = fs_parse(fc, binderfs_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_max:
+		if (result.uint_32 > BINDERFS_MAX_MINOR)
+			return invalfc(fc, "Bad value for '%s'", param->key);
+
+		ctx->max = result.uint_32;
+		break;
+	case Opt_stats_mode:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		ctx->stats_mode = result.uint_32;
+		break;
+	default:
+		return invalfc(fc, "Unsupported parameter '%s'", param->key);
+	}
+
+	return 0;
+}
+
+static int binderfs_fs_context_reconfigure(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct binderfs_info *info = BINDERFS_SB(fc->root->d_sb);
+
+	if (info->mount_opts.stats_mode != ctx->stats_mode)
+		return invalfc(fc, "Binderfs stats mode cannot be changed during a remount");
+
+	info->mount_opts.stats_mode = ctx->stats_mode;
+	info->mount_opts.max = ctx->max;
+	return 0;
+}
+
+static int binderfs_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct binderfs_info *info = BINDERFS_SB(root->d_sb);
+
+	if (info->mount_opts.max <= BINDERFS_MAX_MINOR)
+		seq_printf(seq, ",max=%d", info->mount_opts.max);
+
+	switch (info->mount_opts.stats_mode) {
+	case binderfs_stats_mode_unset:
+		break;
+	case binderfs_stats_mode_global:
+		seq_puts(seq, ",stats=global");
+		break;
+	}
+
+	return 0;
+}
+
+static const struct super_operations binderfs_super_ops = {
+	.evict_inode    = binderfs_evict_inode,
+	.show_options	= binderfs_show_options,
+	.statfs         = simple_statfs,
+};
+
+static inline bool is_binderfs_control_device(const struct dentry *dentry)
+{
+	struct binderfs_info *info = dentry->d_sb->s_fs_info;
+
+	return info->control_dentry == dentry;
+}
+
+static int binderfs_rename(struct mnt_idmap *idmap,
+			   struct inode *old_dir, struct dentry *old_dentry,
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
+{
+	if (is_binderfs_control_device(old_dentry) ||
+	    is_binderfs_control_device(new_dentry))
+		return -EPERM;
+
+	return simple_rename(idmap, old_dir, old_dentry, new_dir,
+			     new_dentry, flags);
+}
+
+static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	if (is_binderfs_control_device(dentry))
+		return -EPERM;
+
+	return simple_unlink(dir, dentry);
+}
+
+static const struct file_operations binder_ctl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nonseekable_open,
+	.unlocked_ioctl	= binder_ctl_ioctl,
+	.compat_ioctl	= binder_ctl_ioctl,
+	.llseek		= noop_llseek,
+};
+
+/**
+ * binderfs_binder_ctl_create - create a new binder-control device
+ * @sb: super block of the binderfs mount
+ *
+ * This function creates a new binder-control device node in the binderfs mount
+ * referred to by @sb.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_ctl_create(struct super_block *sb)
+{
+	int minor, ret;
+	struct dentry *dentry;
+	struct binder_device *device;
+	struct inode *inode = NULL;
+	struct dentry *root = sb->s_root;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	/* If we have already created a binder-control node, return. */
+	if (info->control_dentry) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = -ENOMEM;
+	inode = new_inode(sb);
+	if (!inode)
+		goto out;
+
+	/* Reserve a new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	minor = ida_alloc_max(&binderfs_minors,
+			      use_reserve ? BINDERFS_MAX_MINOR :
+					    BINDERFS_MAX_MINOR_CAPPED,
+			      GFP_KERNEL);
+	mutex_unlock(&binderfs_minors_mutex);
+	if (minor < 0) {
+		ret = minor;
+		goto out;
+	}
+
+	inode->i_ino = SECOND_INODE;
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &binder_ctl_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	device->minor = minor;
+	device->ctx = NULL;
+
+	dentry = d_alloc_name(root, "binder-control");
+	if (!dentry)
+		goto out;
+
+	inode->i_private = device;
+	info->control_dentry = dentry;
+	d_add(dentry, inode);
+
+	return 0;
+
+out:
+	kfree(device);
+	iput(inode);
+
+	return ret;
+}
+
+static const struct inode_operations binderfs_dir_inode_operations = {
+	.lookup = simple_lookup,
+	.rename = binderfs_rename,
+	.unlink = binderfs_unlink,
+};
+
+static struct inode *binderfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret;
+
+	ret = new_inode(sb);
+	if (ret) {
+		ret->i_ino = iunique(sb, BINDERFS_MAX_MINOR + INODE_OFFSET);
+		ret->i_mode = mode;
+		simple_inode_init_ts(ret);
+	}
+	return ret;
+}
+
+static struct dentry *binderfs_create_dentry(struct dentry *parent,
+					     const char *name)
+{
+	struct dentry *dentry;
+
+	dentry = lookup_noperm(&QSTR(name), parent);
+	if (IS_ERR(dentry))
+		return dentry;
+
+	/* Return error if the file/dir already exists. */
+	if (d_really_is_positive(dentry)) {
+		dput(dentry);
+		return ERR_PTR(-EEXIST);
+	}
+
+	return dentry;
+}
+
+void rust_binderfs_remove_file(struct dentry *dentry)
+{
+	struct inode *parent_inode;
+
+	parent_inode = d_inode(dentry->d_parent);
+	inode_lock(parent_inode);
+	if (simple_positive(dentry)) {
+		dget(dentry);
+		simple_unlink(parent_inode, dentry);
+		d_delete(dentry);
+		dput(dentry);
+	}
+	inode_unlock(parent_inode);
+}
+
+static struct dentry *rust_binderfs_create_file(struct dentry *parent, const char *name,
+						const struct file_operations *fops,
+						void *data)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+	inode_lock(parent_inode);
+
+	dentry = binderfs_create_dentry(parent, name);
+	if (IS_ERR(dentry))
+		goto out;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFREG | 0444);
+	if (!new_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	new_inode->i_fop = fops;
+	new_inode->i_private = data;
+	d_instantiate(dentry, new_inode);
+	fsnotify_create(parent_inode, dentry);
+
+out:
+	inode_unlock(parent_inode);
+	return dentry;
+}
+
+struct dentry *rust_binderfs_create_proc_file(struct inode *nodp, int pid)
+{
+	struct binderfs_info *info = nodp->i_sb->s_fs_info;
+	struct dentry *dir = info->proc_log_dir;
+	char strbuf[20 + 1];
+	void *data = (void *)(unsigned long) pid;
+
+	if (!dir)
+		return NULL;
+
+	snprintf(strbuf, sizeof(strbuf), "%u", pid);
+	return rust_binderfs_create_file(dir, strbuf, &rust_binder_proc_fops, data);
+}
+
+static struct dentry *binderfs_create_dir(struct dentry *parent,
+					  const char *name)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+	inode_lock(parent_inode);
+
+	dentry = binderfs_create_dentry(parent, name);
+	if (IS_ERR(dentry))
+		goto out;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFDIR | 0755);
+	if (!new_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	new_inode->i_fop = &simple_dir_operations;
+	new_inode->i_op = &simple_dir_inode_operations;
+
+	set_nlink(new_inode, 2);
+	d_instantiate(dentry, new_inode);
+	inc_nlink(parent_inode);
+	fsnotify_mkdir(parent_inode, dentry);
+
+out:
+	inode_unlock(parent_inode);
+	return dentry;
+}
+
+static int binder_features_show(struct seq_file *m, void *unused)
+{
+	bool *feature = m->private;
+
+	seq_printf(m, "%d\n", *feature);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(binder_features);
+
+static int init_binder_features(struct super_block *sb)
+{
+	struct dentry *dentry, *dir;
+
+	dir = binderfs_create_dir(sb->s_root, "features");
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	dentry = rust_binderfs_create_file(dir, "oneway_spam_detection",
+				      &binder_features_fops,
+				      &binder_features.oneway_spam_detection);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = rust_binderfs_create_file(dir, "extended_error",
+				      &binder_features_fops,
+				      &binder_features.extended_error);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = rust_binderfs_create_file(dir, "freeze_notification",
+				      &binder_features_fops,
+				      &binder_features.freeze_notification);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return 0;
+}
+
+static int init_binder_logs(struct super_block *sb)
+{
+	struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir;
+	struct binderfs_info *info;
+	int ret = 0;
+
+	binder_logs_root_dir = binderfs_create_dir(sb->s_root,
+						   "binder_logs");
+	if (IS_ERR(binder_logs_root_dir)) {
+		ret = PTR_ERR(binder_logs_root_dir);
+		goto out;
+	}
+
+	dentry = rust_binderfs_create_file(binder_logs_root_dir, "stats",
+				      &rust_binder_stats_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = rust_binderfs_create_file(binder_logs_root_dir, "state",
+				      &rust_binder_state_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = rust_binderfs_create_file(binder_logs_root_dir, "transactions",
+				      &rust_binder_transactions_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc");
+	if (IS_ERR(proc_log_dir)) {
+		ret = PTR_ERR(proc_log_dir);
+		goto out;
+	}
+	info = sb->s_fs_info;
+	info->proc_log_dir = proc_log_dir;
+
+out:
+	return ret;
+}
+
+static int binderfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	int ret;
+	struct binderfs_info *info;
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct inode *inode = NULL;
+	struct binderfs_device device_info = {};
+	const char *name;
+	size_t len;
+
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+
+	/*
+	 * The binderfs filesystem can be mounted by userns root in a
+	 * non-initial userns. By default such mounts have the SB_I_NODEV flag
+	 * set in s_iflags to prevent security issues where userns root can
+	 * just create random device nodes via mknod() since it owns the
+	 * filesystem mount. But binderfs does not allow to create any files
+	 * including devices nodes. The only way to create binder devices nodes
+	 * is through the binder-control device which userns root is explicitly
+	 * allowed to do. So removing the SB_I_NODEV flag from s_iflags is both
+	 * necessary and safe.
+	 */
+	sb->s_iflags &= ~SB_I_NODEV;
+	sb->s_iflags |= SB_I_NOEXEC;
+	sb->s_magic = RUST_BINDERFS_SUPER_MAGIC;
+	sb->s_op = &binderfs_super_ops;
+	sb->s_time_gran = 1;
+
+	sb->s_fs_info = kzalloc(sizeof(struct binderfs_info), GFP_KERNEL);
+	if (!sb->s_fs_info)
+		return -ENOMEM;
+	info = sb->s_fs_info;
+
+	info->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
+
+	info->root_gid = make_kgid(sb->s_user_ns, 0);
+	if (!gid_valid(info->root_gid))
+		info->root_gid = GLOBAL_ROOT_GID;
+	info->root_uid = make_kuid(sb->s_user_ns, 0);
+	if (!uid_valid(info->root_uid))
+		info->root_uid = GLOBAL_ROOT_UID;
+	info->mount_opts.max = ctx->max;
+	info->mount_opts.stats_mode = ctx->stats_mode;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return -ENOMEM;
+
+	inode->i_ino = FIRST_INODE;
+	inode->i_fop = &simple_dir_operations;
+	inode->i_mode = S_IFDIR | 0755;
+	simple_inode_init_ts(inode);
+	inode->i_op = &binderfs_dir_inode_operations;
+	set_nlink(inode, 2);
+
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root)
+		return -ENOMEM;
+
+	ret = binderfs_binder_ctl_create(sb);
+	if (ret)
+		return ret;
+
+	name = rust_binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		strscpy(device_info.name, name, len + 1);
+		ret = binderfs_binder_device_create(inode, NULL, &device_info);
+		if (ret)
+			return ret;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	ret = init_binder_features(sb);
+	if (ret)
+		return ret;
+
+	if (info->mount_opts.stats_mode == binderfs_stats_mode_global)
+		return init_binder_logs(sb);
+
+	return 0;
+}
+
+static int binderfs_fs_context_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, binderfs_fill_super);
+}
+
+static void binderfs_fs_context_free(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+
+	kfree(ctx);
+}
+
+static const struct fs_context_operations binderfs_fs_context_ops = {
+	.free		= binderfs_fs_context_free,
+	.get_tree	= binderfs_fs_context_get_tree,
+	.parse_param	= binderfs_fs_context_parse_param,
+	.reconfigure	= binderfs_fs_context_reconfigure,
+};
+
+static int binderfs_init_fs_context(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx;
+
+	ctx = kzalloc(sizeof(struct binderfs_mount_opts), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->max = BINDERFS_MAX_MINOR;
+	ctx->stats_mode = binderfs_stats_mode_unset;
+
+	fc->fs_private = ctx;
+	fc->ops = &binderfs_fs_context_ops;
+
+	return 0;
+}
+
+static void binderfs_kill_super(struct super_block *sb)
+{
+	struct binderfs_info *info = sb->s_fs_info;
+
+	/*
+	 * During inode eviction struct binderfs_info is needed.
+	 * So first wipe the super_block then free struct binderfs_info.
+	 */
+	kill_litter_super(sb);
+
+	if (info && info->ipc_ns)
+		put_ipc_ns(info->ipc_ns);
+
+	kfree(info);
+}
+
+static struct file_system_type binder_fs_type = {
+	.name			= "binder",
+	.init_fs_context	= binderfs_init_fs_context,
+	.parameters		= binderfs_fs_parameters,
+	.kill_sb		= binderfs_kill_super,
+	.fs_flags		= FS_USERNS_MOUNT,
+};
+
+int init_rust_binderfs(void)
+{
+	int ret;
+	const char *name;
+	size_t len;
+
+	/* Verify that the default binderfs device names are valid. */
+	name = rust_binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		if (len > BINDERFS_MAX_NAME)
+			return -E2BIG;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	/* Allocate new major number for binderfs. */
+	ret = alloc_chrdev_region(&binderfs_dev, 0, BINDERFS_MAX_MINOR,
+				  "rust_binder");
+	if (ret)
+		return ret;
+
+	ret = register_filesystem(&binder_fs_type);
+	if (ret) {
+		unregister_chrdev_region(binderfs_dev, BINDERFS_MAX_MINOR);
+		return ret;
+	}
+
+	return ret;
+}
diff --git a/drivers/android/binder/stats.rs b/drivers/android/binder/stats.rs
new file mode 100644
index 000000000000..a83ec111d2cb
--- /dev/null
+++ b/drivers/android/binder/stats.rs
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! Keep track of statistics for binder_logs.
+
+use crate::defs::*;
+use core::sync::atomic::{AtomicU32, Ordering::Relaxed};
+use kernel::{ioctl::_IOC_NR, seq_file::SeqFile, seq_print};
+
+const BC_COUNT: usize = _IOC_NR(BC_REPLY_SG) as usize + 1;
+const BR_COUNT: usize = _IOC_NR(BR_TRANSACTION_PENDING_FROZEN) as usize + 1;
+
+pub(crate) static GLOBAL_STATS: BinderStats = BinderStats::new();
+
+pub(crate) struct BinderStats {
+    bc: [AtomicU32; BC_COUNT],
+    br: [AtomicU32; BR_COUNT],
+}
+
+impl BinderStats {
+    pub(crate) const fn new() -> Self {
+        #[expect(clippy::declare_interior_mutable_const)]
+        const ZERO: AtomicU32 = AtomicU32::new(0);
+
+        Self {
+            bc: [ZERO; BC_COUNT],
+            br: [ZERO; BR_COUNT],
+        }
+    }
+
+    pub(crate) fn inc_bc(&self, bc: u32) {
+        let idx = _IOC_NR(bc) as usize;
+        if let Some(bc_ref) = self.bc.get(idx) {
+            bc_ref.fetch_add(1, Relaxed);
+        }
+    }
+
+    pub(crate) fn inc_br(&self, br: u32) {
+        let idx = _IOC_NR(br) as usize;
+        if let Some(br_ref) = self.br.get(idx) {
+            br_ref.fetch_add(1, Relaxed);
+        }
+    }
+
+    pub(crate) fn debug_print(&self, prefix: &str, m: &SeqFile) {
+        for (i, cnt) in self.bc.iter().enumerate() {
+            let cnt = cnt.load(Relaxed);
+            if cnt > 0 {
+                seq_print!(m, "{}{}: {}\n", prefix, command_string(i), cnt);
+            }
+        }
+        for (i, cnt) in self.br.iter().enumerate() {
+            let cnt = cnt.load(Relaxed);
+            if cnt > 0 {
+                seq_print!(m, "{}{}: {}\n", prefix, return_string(i), cnt);
+            }
+        }
+    }
+}
+
+mod strings {
+    use core::str::from_utf8_unchecked;
+    use kernel::str::CStr;
+
+    extern "C" {
+        static binder_command_strings: [*const u8; super::BC_COUNT];
+        static binder_return_strings: [*const u8; super::BR_COUNT];
+    }
+
+    pub(super) fn command_string(i: usize) -> &'static str {
+        // SAFETY: Accessing `binder_command_strings` is always safe.
+        let c_str_ptr = unsafe { binder_command_strings[i] };
+        // SAFETY: The `binder_command_strings` array only contains nul-terminated strings.
+        let bytes = unsafe { CStr::from_char_ptr(c_str_ptr) }.as_bytes();
+        // SAFETY: The `binder_command_strings` array only contains strings with ascii-chars.
+        unsafe { from_utf8_unchecked(bytes) }
+    }
+
+    pub(super) fn return_string(i: usize) -> &'static str {
+        // SAFETY: Accessing `binder_return_strings` is always safe.
+        let c_str_ptr = unsafe { binder_return_strings[i] };
+        // SAFETY: The `binder_command_strings` array only contains nul-terminated strings.
+        let bytes = unsafe { CStr::from_char_ptr(c_str_ptr) }.as_bytes();
+        // SAFETY: The `binder_command_strings` array only contains strings with ascii-chars.
+        unsafe { from_utf8_unchecked(bytes) }
+    }
+}
+use strings::{command_string, return_string};
diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs
new file mode 100644
index 000000000000..7e34ccd394f8
--- /dev/null
+++ b/drivers/android/binder/thread.rs
@@ -0,0 +1,1596 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! This module defines the `Thread` type, which represents a userspace thread that is using
+//! binder.
+//!
+//! The `Process` object stores all of the threads in an rb tree.
+
+use kernel::{
+    bindings,
+    fs::{File, LocalFile},
+    list::{AtomicTracker, List, ListArc, ListLinks, TryNewListArc},
+    prelude::*,
+    security,
+    seq_file::SeqFile,
+    seq_print,
+    sync::poll::{PollCondVar, PollTable},
+    sync::{Arc, SpinLock},
+    task::Task,
+    types::ARef,
+    uaccess::UserSlice,
+    uapi,
+};
+
+use crate::{
+    allocation::{Allocation, AllocationView, BinderObject, BinderObjectRef, NewAllocation},
+    defs::*,
+    error::BinderResult,
+    process::{GetWorkOrRegister, Process},
+    ptr_align,
+    stats::GLOBAL_STATS,
+    transaction::Transaction,
+    BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverCode, DeliverToRead,
+};
+
+use core::{
+    mem::size_of,
+    sync::atomic::{AtomicU32, Ordering},
+};
+
+/// Stores the layout of the scatter-gather entries. This is used during the `translate_objects`
+/// call and is discarded when it returns.
+struct ScatterGatherState {
+    /// A struct that tracks the amount of unused buffer space.
+    unused_buffer_space: UnusedBufferSpace,
+    /// Scatter-gather entries to copy.
+    sg_entries: KVec<ScatterGatherEntry>,
+    /// Indexes into `sg_entries` corresponding to the last binder_buffer_object that
+    /// was processed and all of its ancestors. The array is in sorted order.
+    ancestors: KVec<usize>,
+}
+
+/// This entry specifies an additional buffer that should be copied using the scatter-gather
+/// mechanism.
+struct ScatterGatherEntry {
+    /// The index in the offset array of the BINDER_TYPE_PTR that this entry originates from.
+    obj_index: usize,
+    /// Offset in target buffer.
+    offset: usize,
+    /// User address in source buffer.
+    sender_uaddr: usize,
+    /// Number of bytes to copy.
+    length: usize,
+    /// The minimum offset of the next fixup in this buffer.
+    fixup_min_offset: usize,
+    /// The offsets within this buffer that contain pointers which should be translated.
+    pointer_fixups: KVec<PointerFixupEntry>,
+}
+
+/// This entry specifies that a fixup should happen at `target_offset` of the
+/// buffer. If `skip` is nonzero, then the fixup is a `binder_fd_array_object`
+/// and is applied later. Otherwise if `skip` is zero, then the size of the
+/// fixup is `sizeof::<u64>()` and `pointer_value` is written to the buffer.
+struct PointerFixupEntry {
+    /// The number of bytes to skip, or zero for a `binder_buffer_object` fixup.
+    skip: usize,
+    /// The translated pointer to write when `skip` is zero.
+    pointer_value: u64,
+    /// The offset at which the value should be written. The offset is relative
+    /// to the original buffer.
+    target_offset: usize,
+}
+
+/// Return type of `apply_and_validate_fixup_in_parent`.
+struct ParentFixupInfo {
+    /// The index of the parent buffer in `sg_entries`.
+    parent_sg_index: usize,
+    /// The number of ancestors of the buffer.
+    ///
+    /// The buffer is considered an ancestor of itself, so this is always at
+    /// least one.
+    num_ancestors: usize,
+    /// New value of `fixup_min_offset` if this fixup is applied.
+    new_min_offset: usize,
+    /// The offset of the fixup in the target buffer.
+    target_offset: usize,
+}
+
+impl ScatterGatherState {
+    /// Called when a `binder_buffer_object` or `binder_fd_array_object` tries
+    /// to access a region in its parent buffer. These accesses have various
+    /// restrictions, which this method verifies.
+    ///
+    /// The `parent_offset` and `length` arguments describe the offset and
+    /// length of the access in the parent buffer.
+    ///
+    /// # Detailed restrictions
+    ///
+    /// Obviously the fixup must be in-bounds for the parent buffer.
+    ///
+    /// For safety reasons, we only allow fixups inside a buffer to happen
+    /// at increasing offsets; additionally, we only allow fixup on the last
+    /// buffer object that was verified, or one of its parents.
+    ///
+    /// Example of what is allowed:
+    ///
+    /// A
+    ///   B (parent = A, offset = 0)
+    ///   C (parent = A, offset = 16)
+    ///     D (parent = C, offset = 0)
+    ///   E (parent = A, offset = 32) // min_offset is 16 (C.parent_offset)
+    ///
+    /// Examples of what is not allowed:
+    ///
+    /// Decreasing offsets within the same parent:
+    /// A
+    ///   C (parent = A, offset = 16)
+    ///   B (parent = A, offset = 0) // decreasing offset within A
+    ///
+    /// Arcerring to a parent that wasn't the last object or any of its parents:
+    /// A
+    ///   B (parent = A, offset = 0)
+    ///   C (parent = A, offset = 0)
+    ///   C (parent = A, offset = 16)
+    ///     D (parent = B, offset = 0) // B is not A or any of A's parents
+    fn validate_parent_fixup(
+        &self,
+        parent: usize,
+        parent_offset: usize,
+        length: usize,
+    ) -> Result<ParentFixupInfo> {
+        // Using `position` would also be correct, but `rposition` avoids
+        // quadratic running times.
+        let ancestors_i = self
+            .ancestors
+            .iter()
+            .copied()
+            .rposition(|sg_idx| self.sg_entries[sg_idx].obj_index == parent)
+            .ok_or(EINVAL)?;
+        let sg_idx = self.ancestors[ancestors_i];
+        let sg_entry = match self.sg_entries.get(sg_idx) {
+            Some(sg_entry) => sg_entry,
+            None => {
+                pr_err!(
+                    "self.ancestors[{}] is {}, but self.sg_entries.len() is {}",
+                    ancestors_i,
+                    sg_idx,
+                    self.sg_entries.len()
+                );
+                return Err(EINVAL);
+            }
+        };
+        if sg_entry.fixup_min_offset > parent_offset {
+            pr_warn!(
+                "validate_parent_fixup: fixup_min_offset={}, parent_offset={}",
+                sg_entry.fixup_min_offset,
+                parent_offset
+            );
+            return Err(EINVAL);
+        }
+        let new_min_offset = parent_offset.checked_add(length).ok_or(EINVAL)?;
+        if new_min_offset > sg_entry.length {
+            pr_warn!(
+                "validate_parent_fixup: new_min_offset={}, sg_entry.length={}",
+                new_min_offset,
+                sg_entry.length
+            );
+            return Err(EINVAL);
+        }
+        let target_offset = sg_entry.offset.checked_add(parent_offset).ok_or(EINVAL)?;
+        // The `ancestors_i + 1` operation can't overflow since the output of the addition is at
+        // most `self.ancestors.len()`, which also fits in a usize.
+        Ok(ParentFixupInfo {
+            parent_sg_index: sg_idx,
+            num_ancestors: ancestors_i + 1,
+            new_min_offset,
+            target_offset,
+        })
+    }
+}
+
+/// Keeps track of how much unused buffer space is left. The initial amount is the number of bytes
+/// requested by the user using the `buffers_size` field of `binder_transaction_data_sg`. Each time
+/// we translate an object of type `BINDER_TYPE_PTR`, some of the unused buffer space is consumed.
+struct UnusedBufferSpace {
+    /// The start of the remaining space.
+    offset: usize,
+    /// The end of the remaining space.
+    limit: usize,
+}
+impl UnusedBufferSpace {
+    /// Claim the next `size` bytes from the unused buffer space. The offset for the claimed chunk
+    /// into the buffer is returned.
+    fn claim_next(&mut self, size: usize) -> Result<usize> {
+        // We require every chunk to be aligned.
+        let size = ptr_align(size).ok_or(EINVAL)?;
+        let new_offset = self.offset.checked_add(size).ok_or(EINVAL)?;
+
+        if new_offset <= self.limit {
+            let offset = self.offset;
+            self.offset = new_offset;
+            Ok(offset)
+        } else {
+            Err(EINVAL)
+        }
+    }
+}
+
+pub(crate) enum PushWorkRes {
+    Ok,
+    FailedDead(DLArc<dyn DeliverToRead>),
+}
+
+impl PushWorkRes {
+    fn is_ok(&self) -> bool {
+        match self {
+            PushWorkRes::Ok => true,
+            PushWorkRes::FailedDead(_) => false,
+        }
+    }
+}
+
+/// The fields of `Thread` protected by the spinlock.
+struct InnerThread {
+    /// Determines the looper state of the thread. It is a bit-wise combination of the constants
+    /// prefixed with `LOOPER_`.
+    looper_flags: u32,
+
+    /// Determines whether the looper should return.
+    looper_need_return: bool,
+
+    /// Determines if thread is dead.
+    is_dead: bool,
+
+    /// Work item used to deliver error codes to the thread that started a transaction. Stored here
+    /// so that it can be reused.
+    reply_work: DArc<ThreadError>,
+
+    /// Work item used to deliver error codes to the current thread. Stored here so that it can be
+    /// reused.
+    return_work: DArc<ThreadError>,
+
+    /// Determines whether the work list below should be processed. When set to false, `work_list`
+    /// is treated as if it were empty.
+    process_work_list: bool,
+    /// List of work items to deliver to userspace.
+    work_list: List<DTRWrap<dyn DeliverToRead>>,
+    current_transaction: Option<DArc<Transaction>>,
+
+    /// Extended error information for this thread.
+    extended_error: ExtendedError,
+}
+
+const LOOPER_REGISTERED: u32 = 0x01;
+const LOOPER_ENTERED: u32 = 0x02;
+const LOOPER_EXITED: u32 = 0x04;
+const LOOPER_INVALID: u32 = 0x08;
+const LOOPER_WAITING: u32 = 0x10;
+const LOOPER_WAITING_PROC: u32 = 0x20;
+const LOOPER_POLL: u32 = 0x40;
+
+impl InnerThread {
+    fn new() -> Result<Self> {
+        fn next_err_id() -> u32 {
+            static EE_ID: AtomicU32 = AtomicU32::new(0);
+            EE_ID.fetch_add(1, Ordering::Relaxed)
+        }
+
+        Ok(Self {
+            looper_flags: 0,
+            looper_need_return: false,
+            is_dead: false,
+            process_work_list: false,
+            reply_work: ThreadError::try_new()?,
+            return_work: ThreadError::try_new()?,
+            work_list: List::new(),
+            current_transaction: None,
+            extended_error: ExtendedError::new(next_err_id(), BR_OK, 0),
+        })
+    }
+
+    fn pop_work(&mut self) -> Option<DLArc<dyn DeliverToRead>> {
+        if !self.process_work_list {
+            return None;
+        }
+
+        let ret = self.work_list.pop_front();
+        self.process_work_list = !self.work_list.is_empty();
+        ret
+    }
+
+    fn push_work(&mut self, work: DLArc<dyn DeliverToRead>) -> PushWorkRes {
+        if self.is_dead {
+            PushWorkRes::FailedDead(work)
+        } else {
+            self.work_list.push_back(work);
+            self.process_work_list = true;
+            PushWorkRes::Ok
+        }
+    }
+
+    fn push_reply_work(&mut self, code: u32) {
+        if let Ok(work) = ListArc::try_from_arc(self.reply_work.clone()) {
+            work.set_error_code(code);
+            self.push_work(work);
+        } else {
+            pr_warn!("Thread reply work is already in use.");
+        }
+    }
+
+    fn push_return_work(&mut self, reply: u32) {
+        if let Ok(work) = ListArc::try_from_arc(self.return_work.clone()) {
+            work.set_error_code(reply);
+            self.push_work(work);
+        } else {
+            pr_warn!("Thread return work is already in use.");
+        }
+    }
+
+    /// Used to push work items that do not need to be processed immediately and can wait until the
+    /// thread gets another work item.
+    fn push_work_deferred(&mut self, work: DLArc<dyn DeliverToRead>) {
+        self.work_list.push_back(work);
+    }
+
+    /// Fetches the transaction this thread can reply to. If the thread has a pending transaction
+    /// (that it could respond to) but it has also issued a transaction, it must first wait for the
+    /// previously-issued transaction to complete.
+    ///
+    /// The `thread` parameter should be the thread containing this `ThreadInner`.
+    fn pop_transaction_to_reply(&mut self, thread: &Thread) -> Result<DArc<Transaction>> {
+        let transaction = self.current_transaction.take().ok_or(EINVAL)?;
+        if core::ptr::eq(thread, transaction.from.as_ref()) {
+            self.current_transaction = Some(transaction);
+            return Err(EINVAL);
+        }
+        // Find a new current transaction for this thread.
+        self.current_transaction = transaction.find_from(thread).cloned();
+        Ok(transaction)
+    }
+
+    fn pop_transaction_replied(&mut self, transaction: &DArc<Transaction>) -> bool {
+        match self.current_transaction.take() {
+            None => false,
+            Some(old) => {
+                if !Arc::ptr_eq(transaction, &old) {
+                    self.current_transaction = Some(old);
+                    return false;
+                }
+                self.current_transaction = old.clone_next();
+                true
+            }
+        }
+    }
+
+    fn looper_enter(&mut self) {
+        self.looper_flags |= LOOPER_ENTERED;
+        if self.looper_flags & LOOPER_REGISTERED != 0 {
+            self.looper_flags |= LOOPER_INVALID;
+        }
+    }
+
+    fn looper_register(&mut self, valid: bool) {
+        self.looper_flags |= LOOPER_REGISTERED;
+        if !valid || self.looper_flags & LOOPER_ENTERED != 0 {
+            self.looper_flags |= LOOPER_INVALID;
+        }
+    }
+
+    fn looper_exit(&mut self) {
+        self.looper_flags |= LOOPER_EXITED;
+    }
+
+    /// Determines whether the thread is part of a pool, i.e., if it is a looper.
+    fn is_looper(&self) -> bool {
+        self.looper_flags & (LOOPER_ENTERED | LOOPER_REGISTERED) != 0
+    }
+
+    /// Determines whether the thread should attempt to fetch work items from the process queue.
+    /// This is generally case when the thread is registered as a looper and not part of a
+    /// transaction stack. But if there is local work, we want to return to userspace before we
+    /// deliver any remote work.
+    fn should_use_process_work_queue(&self) -> bool {
+        self.current_transaction.is_none() && !self.process_work_list && self.is_looper()
+    }
+
+    fn poll(&mut self) -> u32 {
+        self.looper_flags |= LOOPER_POLL;
+        if self.process_work_list || self.looper_need_return {
+            bindings::POLLIN
+        } else {
+            0
+        }
+    }
+}
+
+/// This represents a thread that's used with binder.
+#[pin_data]
+pub(crate) struct Thread {
+    pub(crate) id: i32,
+    pub(crate) process: Arc<Process>,
+    pub(crate) task: ARef<Task>,
+    #[pin]
+    inner: SpinLock<InnerThread>,
+    #[pin]
+    work_condvar: PollCondVar,
+    /// Used to insert this thread into the process' `ready_threads` list.
+    ///
+    /// INVARIANT: May never be used for any other list than the `self.process.ready_threads`.
+    #[pin]
+    links: ListLinks,
+    #[pin]
+    links_track: AtomicTracker,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for Thread {
+        tracked_by links_track: AtomicTracker;
+    }
+}
+kernel::list::impl_list_item! {
+    impl ListItem<0> for Thread {
+        using ListLinks { self.links };
+    }
+}
+
+impl Thread {
+    pub(crate) fn new(id: i32, process: Arc<Process>) -> Result<Arc<Self>> {
+        let inner = InnerThread::new()?;
+
+        Arc::pin_init(
+            try_pin_init!(Thread {
+                id,
+                process,
+                task: ARef::from(&**kernel::current!()),
+                inner <- kernel::new_spinlock!(inner, "Thread::inner"),
+                work_condvar <- kernel::new_poll_condvar!("Thread::work_condvar"),
+                links <- ListLinks::new(),
+                links_track <- AtomicTracker::new(),
+            }),
+            GFP_KERNEL,
+        )
+    }
+
+    #[inline(never)]
+    pub(crate) fn debug_print(self: &Arc<Self>, m: &SeqFile, print_all: bool) -> Result<()> {
+        let inner = self.inner.lock();
+
+        if print_all || inner.current_transaction.is_some() || !inner.work_list.is_empty() {
+            seq_print!(
+                m,
+                "  thread {}: l {:02x} need_return {}\n",
+                self.id,
+                inner.looper_flags,
+                inner.looper_need_return,
+            );
+        }
+
+        let mut t_opt = inner.current_transaction.as_ref();
+        while let Some(t) = t_opt {
+            if Arc::ptr_eq(&t.from, self) {
+                t.debug_print_inner(m, "    outgoing transaction ");
+                t_opt = t.from_parent.as_ref();
+            } else if Arc::ptr_eq(&t.to, &self.process) {
+                t.debug_print_inner(m, "    incoming transaction ");
+                t_opt = t.find_from(self);
+            } else {
+                t.debug_print_inner(m, "    bad transaction ");
+                t_opt = None;
+            }
+        }
+
+        for work in &inner.work_list {
+            work.debug_print(m, "    ", "    pending transaction ")?;
+        }
+        Ok(())
+    }
+
+    pub(crate) fn get_extended_error(&self, data: UserSlice) -> Result {
+        let mut writer = data.writer();
+        let ee = self.inner.lock().extended_error;
+        writer.write(&ee)?;
+        Ok(())
+    }
+
+    pub(crate) fn set_current_transaction(&self, transaction: DArc<Transaction>) {
+        self.inner.lock().current_transaction = Some(transaction);
+    }
+
+    pub(crate) fn has_current_transaction(&self) -> bool {
+        self.inner.lock().current_transaction.is_some()
+    }
+
+    /// Attempts to fetch a work item from the thread-local queue. The behaviour if the queue is
+    /// empty depends on `wait`: if it is true, the function waits for some work to be queued (or a
+    /// signal); otherwise it returns indicating that none is available.
+    fn get_work_local(self: &Arc<Self>, wait: bool) -> Result<Option<DLArc<dyn DeliverToRead>>> {
+        {
+            let mut inner = self.inner.lock();
+            if inner.looper_need_return {
+                return Ok(inner.pop_work());
+            }
+        }
+
+        // Try once if the caller does not want to wait.
+        if !wait {
+            return self.inner.lock().pop_work().ok_or(EAGAIN).map(Some);
+        }
+
+        // Loop waiting only on the local queue (i.e., not registering with the process queue).
+        let mut inner = self.inner.lock();
+        loop {
+            if let Some(work) = inner.pop_work() {
+                return Ok(Some(work));
+            }
+
+            inner.looper_flags |= LOOPER_WAITING;
+            let signal_pending = self.work_condvar.wait_interruptible_freezable(&mut inner);
+            inner.looper_flags &= !LOOPER_WAITING;
+
+            if signal_pending {
+                return Err(EINTR);
+            }
+            if inner.looper_need_return {
+                return Ok(None);
+            }
+        }
+    }
+
+    /// Attempts to fetch a work item from the thread-local queue, falling back to the process-wide
+    /// queue if none is available locally.
+    ///
+    /// This must only be called when the thread is not participating in a transaction chain. If it
+    /// is, the local version (`get_work_local`) should be used instead.
+    fn get_work(self: &Arc<Self>, wait: bool) -> Result<Option<DLArc<dyn DeliverToRead>>> {
+        // Try to get work from the thread's work queue, using only a local lock.
+        {
+            let mut inner = self.inner.lock();
+            if let Some(work) = inner.pop_work() {
+                return Ok(Some(work));
+            }
+            if inner.looper_need_return {
+                drop(inner);
+                return Ok(self.process.get_work());
+            }
+        }
+
+        // If the caller doesn't want to wait, try to grab work from the process queue.
+        //
+        // We know nothing will have been queued directly to the thread queue because it is not in
+        // a transaction and it is not in the process' ready list.
+        if !wait {
+            return self.process.get_work().ok_or(EAGAIN).map(Some);
+        }
+
+        // Get work from the process queue. If none is available, atomically register as ready.
+        let reg = match self.process.get_work_or_register(self) {
+            GetWorkOrRegister::Work(work) => return Ok(Some(work)),
+            GetWorkOrRegister::Register(reg) => reg,
+        };
+
+        let mut inner = self.inner.lock();
+        loop {
+            if let Some(work) = inner.pop_work() {
+                return Ok(Some(work));
+            }
+
+            inner.looper_flags |= LOOPER_WAITING | LOOPER_WAITING_PROC;
+            let signal_pending = self.work_condvar.wait_interruptible_freezable(&mut inner);
+            inner.looper_flags &= !(LOOPER_WAITING | LOOPER_WAITING_PROC);
+
+            if signal_pending || inner.looper_need_return {
+                // We need to return now. We need to pull the thread off the list of ready threads
+                // (by dropping `reg`), then check the state again after it's off the list to
+                // ensure that something was not queued in the meantime. If something has been
+                // queued, we just return it (instead of the error).
+                drop(inner);
+                drop(reg);
+
+                let res = match self.inner.lock().pop_work() {
+                    Some(work) => Ok(Some(work)),
+                    None if signal_pending => Err(EINTR),
+                    None => Ok(None),
+                };
+                return res;
+            }
+        }
+    }
+
+    /// Push the provided work item to be delivered to user space via this thread.
+    ///
+    /// Returns whether the item was successfully pushed. This can only fail if the thread is dead.
+    pub(crate) fn push_work(&self, work: DLArc<dyn DeliverToRead>) -> PushWorkRes {
+        let sync = work.should_sync_wakeup();
+
+        let res = self.inner.lock().push_work(work);
+
+        if res.is_ok() {
+            if sync {
+                self.work_condvar.notify_sync();
+            } else {
+                self.work_condvar.notify_one();
+            }
+        }
+
+        res
+    }
+
+    /// Attempts to push to given work item to the thread if it's a looper thread (i.e., if it's
+    /// part of a thread pool) and is alive. Otherwise, push the work item to the process instead.
+    pub(crate) fn push_work_if_looper(&self, work: DLArc<dyn DeliverToRead>) -> BinderResult {
+        let mut inner = self.inner.lock();
+        if inner.is_looper() && !inner.is_dead {
+            inner.push_work(work);
+            Ok(())
+        } else {
+            drop(inner);
+            self.process.push_work(work)
+        }
+    }
+
+    pub(crate) fn push_work_deferred(&self, work: DLArc<dyn DeliverToRead>) {
+        self.inner.lock().push_work_deferred(work);
+    }
+
+    pub(crate) fn push_return_work(&self, reply: u32) {
+        self.inner.lock().push_return_work(reply);
+    }
+
+    fn translate_object(
+        &self,
+        obj_index: usize,
+        offset: usize,
+        object: BinderObjectRef<'_>,
+        view: &mut AllocationView<'_>,
+        allow_fds: bool,
+        sg_state: &mut ScatterGatherState,
+    ) -> BinderResult {
+        match object {
+            BinderObjectRef::Binder(obj) => {
+                let strong = obj.hdr.type_ == BINDER_TYPE_BINDER;
+                // SAFETY: `binder` is a `binder_uintptr_t`; any bit pattern is a valid
+                // representation.
+                let ptr = unsafe { obj.__bindgen_anon_1.binder } as _;
+                let cookie = obj.cookie as _;
+                let flags = obj.flags as _;
+                let node = self
+                    .process
+                    .as_arc_borrow()
+                    .get_node(ptr, cookie, flags, strong, self)?;
+                security::binder_transfer_binder(&self.process.cred, &view.alloc.process.cred)?;
+                view.transfer_binder_object(offset, obj, strong, node)?;
+            }
+            BinderObjectRef::Handle(obj) => {
+                let strong = obj.hdr.type_ == BINDER_TYPE_HANDLE;
+                // SAFETY: `handle` is a `u32`; any bit pattern is a valid representation.
+                let handle = unsafe { obj.__bindgen_anon_1.handle } as _;
+                let node = self.process.get_node_from_handle(handle, strong)?;
+                security::binder_transfer_binder(&self.process.cred, &view.alloc.process.cred)?;
+                view.transfer_binder_object(offset, obj, strong, node)?;
+            }
+            BinderObjectRef::Fd(obj) => {
+                if !allow_fds {
+                    return Err(EPERM.into());
+                }
+
+                // SAFETY: `fd` is a `u32`; any bit pattern is a valid representation.
+                let fd = unsafe { obj.__bindgen_anon_1.fd };
+                let file = LocalFile::fget(fd)?;
+                // SAFETY: The binder driver never calls `fdget_pos` and this code runs from an
+                // ioctl, so there are no active calls to `fdget_pos` on this thread.
+                let file = unsafe { LocalFile::assume_no_fdget_pos(file) };
+                security::binder_transfer_file(
+                    &self.process.cred,
+                    &view.alloc.process.cred,
+                    &file,
+                )?;
+
+                let mut obj_write = BinderFdObject::default();
+                obj_write.hdr.type_ = BINDER_TYPE_FD;
+                // This will be overwritten with the actual fd when the transaction is received.
+                obj_write.__bindgen_anon_1.fd = u32::MAX;
+                obj_write.cookie = obj.cookie;
+                view.write::<BinderFdObject>(offset, &obj_write)?;
+
+                const FD_FIELD_OFFSET: usize =
+                    core::mem::offset_of!(uapi::binder_fd_object, __bindgen_anon_1.fd);
+
+                let field_offset = offset + FD_FIELD_OFFSET;
+
+                view.alloc.info_add_fd(file, field_offset, false)?;
+            }
+            BinderObjectRef::Ptr(obj) => {
+                let obj_length = obj.length.try_into().map_err(|_| EINVAL)?;
+                let alloc_offset = match sg_state.unused_buffer_space.claim_next(obj_length) {
+                    Ok(alloc_offset) => alloc_offset,
+                    Err(err) => {
+                        pr_warn!(
+                            "Failed to claim space for a BINDER_TYPE_PTR. (offset: {}, limit: {}, size: {})",
+                            sg_state.unused_buffer_space.offset,
+                            sg_state.unused_buffer_space.limit,
+                            obj_length,
+                        );
+                        return Err(err.into());
+                    }
+                };
+
+                let sg_state_idx = sg_state.sg_entries.len();
+                sg_state.sg_entries.push(
+                    ScatterGatherEntry {
+                        obj_index,
+                        offset: alloc_offset,
+                        sender_uaddr: obj.buffer as _,
+                        length: obj_length,
+                        pointer_fixups: KVec::new(),
+                        fixup_min_offset: 0,
+                    },
+                    GFP_KERNEL,
+                )?;
+
+                let buffer_ptr_in_user_space = (view.alloc.ptr + alloc_offset) as u64;
+
+                if obj.flags & uapi::BINDER_BUFFER_FLAG_HAS_PARENT == 0 {
+                    sg_state.ancestors.clear();
+                    sg_state.ancestors.push(sg_state_idx, GFP_KERNEL)?;
+                } else {
+                    // Another buffer also has a pointer to this buffer, and we need to fixup that
+                    // pointer too.
+
+                    let parent_index = usize::try_from(obj.parent).map_err(|_| EINVAL)?;
+                    let parent_offset = usize::try_from(obj.parent_offset).map_err(|_| EINVAL)?;
+
+                    let info = sg_state.validate_parent_fixup(
+                        parent_index,
+                        parent_offset,
+                        size_of::<u64>(),
+                    )?;
+
+                    sg_state.ancestors.truncate(info.num_ancestors);
+                    sg_state.ancestors.push(sg_state_idx, GFP_KERNEL)?;
+
+                    let parent_entry = match sg_state.sg_entries.get_mut(info.parent_sg_index) {
+                        Some(parent_entry) => parent_entry,
+                        None => {
+                            pr_err!(
+                                "validate_parent_fixup returned index out of bounds for sg.entries"
+                            );
+                            return Err(EINVAL.into());
+                        }
+                    };
+
+                    parent_entry.fixup_min_offset = info.new_min_offset;
+                    parent_entry.pointer_fixups.push(
+                        PointerFixupEntry {
+                            skip: 0,
+                            pointer_value: buffer_ptr_in_user_space,
+                            target_offset: info.target_offset,
+                        },
+                        GFP_KERNEL,
+                    )?;
+                }
+
+                let mut obj_write = BinderBufferObject::default();
+                obj_write.hdr.type_ = BINDER_TYPE_PTR;
+                obj_write.flags = obj.flags;
+                obj_write.buffer = buffer_ptr_in_user_space;
+                obj_write.length = obj.length;
+                obj_write.parent = obj.parent;
+                obj_write.parent_offset = obj.parent_offset;
+                view.write::<BinderBufferObject>(offset, &obj_write)?;
+            }
+            BinderObjectRef::Fda(obj) => {
+                if !allow_fds {
+                    return Err(EPERM.into());
+                }
+                let parent_index = usize::try_from(obj.parent).map_err(|_| EINVAL)?;
+                let parent_offset = usize::try_from(obj.parent_offset).map_err(|_| EINVAL)?;
+                let num_fds = usize::try_from(obj.num_fds).map_err(|_| EINVAL)?;
+                let fds_len = num_fds.checked_mul(size_of::<u32>()).ok_or(EINVAL)?;
+
+                let info = sg_state.validate_parent_fixup(parent_index, parent_offset, fds_len)?;
+                view.alloc.info_add_fd_reserve(num_fds)?;
+
+                sg_state.ancestors.truncate(info.num_ancestors);
+                let parent_entry = match sg_state.sg_entries.get_mut(info.parent_sg_index) {
+                    Some(parent_entry) => parent_entry,
+                    None => {
+                        pr_err!(
+                            "validate_parent_fixup returned index out of bounds for sg.entries"
+                        );
+                        return Err(EINVAL.into());
+                    }
+                };
+
+                parent_entry.fixup_min_offset = info.new_min_offset;
+                parent_entry
+                    .pointer_fixups
+                    .push(
+                        PointerFixupEntry {
+                            skip: fds_len,
+                            pointer_value: 0,
+                            target_offset: info.target_offset,
+                        },
+                        GFP_KERNEL,
+                    )
+                    .map_err(|_| ENOMEM)?;
+
+                let fda_uaddr = parent_entry
+                    .sender_uaddr
+                    .checked_add(parent_offset)
+                    .ok_or(EINVAL)?;
+                let mut fda_bytes = KVec::new();
+                UserSlice::new(UserPtr::from_addr(fda_uaddr as _), fds_len)
+                    .read_all(&mut fda_bytes, GFP_KERNEL)?;
+
+                if fds_len != fda_bytes.len() {
+                    pr_err!("UserSlice::read_all returned wrong length in BINDER_TYPE_FDA");
+                    return Err(EINVAL.into());
+                }
+
+                for i in (0..fds_len).step_by(size_of::<u32>()) {
+                    let fd = {
+                        let mut fd_bytes = [0u8; size_of::<u32>()];
+                        fd_bytes.copy_from_slice(&fda_bytes[i..i + size_of::<u32>()]);
+                        u32::from_ne_bytes(fd_bytes)
+                    };
+
+                    let file = LocalFile::fget(fd)?;
+                    // SAFETY: The binder driver never calls `fdget_pos` and this code runs from an
+                    // ioctl, so there are no active calls to `fdget_pos` on this thread.
+                    let file = unsafe { LocalFile::assume_no_fdget_pos(file) };
+                    security::binder_transfer_file(
+                        &self.process.cred,
+                        &view.alloc.process.cred,
+                        &file,
+                    )?;
+
+                    // The `validate_parent_fixup` call ensuers that this addition will not
+                    // overflow.
+                    view.alloc.info_add_fd(file, info.target_offset + i, true)?;
+                }
+                drop(fda_bytes);
+
+                let mut obj_write = BinderFdArrayObject::default();
+                obj_write.hdr.type_ = BINDER_TYPE_FDA;
+                obj_write.num_fds = obj.num_fds;
+                obj_write.parent = obj.parent;
+                obj_write.parent_offset = obj.parent_offset;
+                view.write::<BinderFdArrayObject>(offset, &obj_write)?;
+            }
+        }
+        Ok(())
+    }
+
+    fn apply_sg(&self, alloc: &mut Allocation, sg_state: &mut ScatterGatherState) -> BinderResult {
+        for sg_entry in &mut sg_state.sg_entries {
+            let mut end_of_previous_fixup = sg_entry.offset;
+            let offset_end = sg_entry.offset.checked_add(sg_entry.length).ok_or(EINVAL)?;
+
+            let mut reader =
+                UserSlice::new(UserPtr::from_addr(sg_entry.sender_uaddr), sg_entry.length).reader();
+            for fixup in &mut sg_entry.pointer_fixups {
+                let fixup_len = if fixup.skip == 0 {
+                    size_of::<u64>()
+                } else {
+                    fixup.skip
+                };
+
+                let target_offset_end = fixup.target_offset.checked_add(fixup_len).ok_or(EINVAL)?;
+                if fixup.target_offset < end_of_previous_fixup || offset_end < target_offset_end {
+                    pr_warn!(
+                        "Fixups oob {} {} {} {}",
+                        fixup.target_offset,
+                        end_of_previous_fixup,
+                        offset_end,
+                        target_offset_end
+                    );
+                    return Err(EINVAL.into());
+                }
+
+                let copy_off = end_of_previous_fixup;
+                let copy_len = fixup.target_offset - end_of_previous_fixup;
+                if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) {
+                    pr_warn!("Failed copying into alloc: {:?}", err);
+                    return Err(err.into());
+                }
+                if fixup.skip == 0 {
+                    let res = alloc.write::<u64>(fixup.target_offset, &fixup.pointer_value);
+                    if let Err(err) = res {
+                        pr_warn!("Failed copying ptr into alloc: {:?}", err);
+                        return Err(err.into());
+                    }
+                }
+                if let Err(err) = reader.skip(fixup_len) {
+                    pr_warn!("Failed skipping {} from reader: {:?}", fixup_len, err);
+                    return Err(err.into());
+                }
+                end_of_previous_fixup = target_offset_end;
+            }
+            let copy_off = end_of_previous_fixup;
+            let copy_len = offset_end - end_of_previous_fixup;
+            if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) {
+                pr_warn!("Failed copying remainder into alloc: {:?}", err);
+                return Err(err.into());
+            }
+        }
+        Ok(())
+    }
+
+    /// This method copies the payload of a transaction into the target process.
+    ///
+    /// The resulting payload will have several different components, which will be stored next to
+    /// each other in the allocation. Furthermore, various objects can be embedded in the payload,
+    /// and those objects have to be translated so that they make sense to the target transaction.
+    pub(crate) fn copy_transaction_data(
+        &self,
+        to_process: Arc<Process>,
+        tr: &BinderTransactionDataSg,
+        debug_id: usize,
+        allow_fds: bool,
+        txn_security_ctx_offset: Option<&mut usize>,
+    ) -> BinderResult<NewAllocation> {
+        let trd = &tr.transaction_data;
+        let is_oneway = trd.flags & TF_ONE_WAY != 0;
+        let mut secctx = if let Some(offset) = txn_security_ctx_offset {
+            let secid = self.process.cred.get_secid();
+            let ctx = match security::SecurityCtx::from_secid(secid) {
+                Ok(ctx) => ctx,
+                Err(err) => {
+                    pr_warn!("Failed to get security ctx for id {}: {:?}", secid, err);
+                    return Err(err.into());
+                }
+            };
+            Some((offset, ctx))
+        } else {
+            None
+        };
+
+        let data_size = trd.data_size.try_into().map_err(|_| EINVAL)?;
+        let aligned_data_size = ptr_align(data_size).ok_or(EINVAL)?;
+        let offsets_size = trd.offsets_size.try_into().map_err(|_| EINVAL)?;
+        let aligned_offsets_size = ptr_align(offsets_size).ok_or(EINVAL)?;
+        let buffers_size = tr.buffers_size.try_into().map_err(|_| EINVAL)?;
+        let aligned_buffers_size = ptr_align(buffers_size).ok_or(EINVAL)?;
+        let aligned_secctx_size = match secctx.as_ref() {
+            Some((_offset, ctx)) => ptr_align(ctx.len()).ok_or(EINVAL)?,
+            None => 0,
+        };
+
+        // This guarantees that at least `sizeof(usize)` bytes will be allocated.
+        let len = usize::max(
+            aligned_data_size
+                .checked_add(aligned_offsets_size)
+                .and_then(|sum| sum.checked_add(aligned_buffers_size))
+                .and_then(|sum| sum.checked_add(aligned_secctx_size))
+                .ok_or(ENOMEM)?,
+            size_of::<usize>(),
+        );
+        let secctx_off = aligned_data_size + aligned_offsets_size + aligned_buffers_size;
+        let mut alloc =
+            match to_process.buffer_alloc(debug_id, len, is_oneway, self.process.task.pid()) {
+                Ok(alloc) => alloc,
+                Err(err) => {
+                    pr_warn!(
+                        "Failed to allocate buffer. len:{}, is_oneway:{}",
+                        len,
+                        is_oneway
+                    );
+                    return Err(err);
+                }
+            };
+
+        // SAFETY: This accesses a union field, but it's okay because the field's type is valid for
+        // all bit-patterns.
+        let trd_data_ptr = unsafe { &trd.data.ptr };
+        let mut buffer_reader =
+            UserSlice::new(UserPtr::from_addr(trd_data_ptr.buffer as _), data_size).reader();
+        let mut end_of_previous_object = 0;
+        let mut sg_state = None;
+
+        // Copy offsets if there are any.
+        if offsets_size > 0 {
+            {
+                let mut reader =
+                    UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size)
+                        .reader();
+                alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?;
+            }
+
+            let offsets_start = aligned_data_size;
+            let offsets_end = aligned_data_size + aligned_offsets_size;
+
+            // This state is used for BINDER_TYPE_PTR objects.
+            let sg_state = sg_state.insert(ScatterGatherState {
+                unused_buffer_space: UnusedBufferSpace {
+                    offset: offsets_end,
+                    limit: len,
+                },
+                sg_entries: KVec::new(),
+                ancestors: KVec::new(),
+            });
+
+            // Traverse the objects specified.
+            let mut view = AllocationView::new(&mut alloc, data_size);
+            for (index, index_offset) in (offsets_start..offsets_end)
+                .step_by(size_of::<usize>())
+                .enumerate()
+            {
+                let offset = view.alloc.read(index_offset)?;
+
+                if offset < end_of_previous_object {
+                    pr_warn!("Got transaction with invalid offset.");
+                    return Err(EINVAL.into());
+                }
+
+                // Copy data between two objects.
+                if end_of_previous_object < offset {
+                    view.copy_into(
+                        &mut buffer_reader,
+                        end_of_previous_object,
+                        offset - end_of_previous_object,
+                    )?;
+                }
+
+                let mut object = BinderObject::read_from(&mut buffer_reader)?;
+
+                match self.translate_object(
+                    index,
+                    offset,
+                    object.as_ref(),
+                    &mut view,
+                    allow_fds,
+                    sg_state,
+                ) {
+                    Ok(()) => end_of_previous_object = offset + object.size(),
+                    Err(err) => {
+                        pr_warn!("Error while translating object.");
+                        return Err(err);
+                    }
+                }
+
+                // Update the indexes containing objects to clean up.
+                let offset_after_object = index_offset + size_of::<usize>();
+                view.alloc
+                    .set_info_offsets(offsets_start..offset_after_object);
+            }
+        }
+
+        // Copy remaining raw data.
+        alloc.copy_into(
+            &mut buffer_reader,
+            end_of_previous_object,
+            data_size - end_of_previous_object,
+        )?;
+
+        if let Some(sg_state) = sg_state.as_mut() {
+            if let Err(err) = self.apply_sg(&mut alloc, sg_state) {
+                pr_warn!("Failure in apply_sg: {:?}", err);
+                return Err(err);
+            }
+        }
+
+        if let Some((off_out, secctx)) = secctx.as_mut() {
+            if let Err(err) = alloc.write(secctx_off, secctx.as_bytes()) {
+                pr_warn!("Failed to write security context: {:?}", err);
+                return Err(err.into());
+            }
+            **off_out = secctx_off;
+        }
+        Ok(alloc)
+    }
+
+    fn unwind_transaction_stack(self: &Arc<Self>) {
+        let mut thread = self.clone();
+        while let Ok(transaction) = {
+            let mut inner = thread.inner.lock();
+            inner.pop_transaction_to_reply(thread.as_ref())
+        } {
+            let reply = Err(BR_DEAD_REPLY);
+            if !transaction.from.deliver_single_reply(reply, &transaction) {
+                break;
+            }
+
+            thread = transaction.from.clone();
+        }
+    }
+
+    pub(crate) fn deliver_reply(
+        &self,
+        reply: Result<DLArc<Transaction>, u32>,
+        transaction: &DArc<Transaction>,
+    ) {
+        if self.deliver_single_reply(reply, transaction) {
+            transaction.from.unwind_transaction_stack();
+        }
+    }
+
+    /// Delivers a reply to the thread that started a transaction. The reply can either be a
+    /// reply-transaction or an error code to be delivered instead.
+    ///
+    /// Returns whether the thread is dead. If it is, the caller is expected to unwind the
+    /// transaction stack by completing transactions for threads that are dead.
+    fn deliver_single_reply(
+        &self,
+        reply: Result<DLArc<Transaction>, u32>,
+        transaction: &DArc<Transaction>,
+    ) -> bool {
+        if let Ok(transaction) = &reply {
+            transaction.set_outstanding(&mut self.process.inner.lock());
+        }
+
+        {
+            let mut inner = self.inner.lock();
+            if !inner.pop_transaction_replied(transaction) {
+                return false;
+            }
+
+            if inner.is_dead {
+                return true;
+            }
+
+            match reply {
+                Ok(work) => {
+                    inner.push_work(work);
+                }
+                Err(code) => inner.push_reply_work(code),
+            }
+        }
+
+        // Notify the thread now that we've released the inner lock.
+        self.work_condvar.notify_sync();
+        false
+    }
+
+    /// Determines if the given transaction is the current transaction for this thread.
+    fn is_current_transaction(&self, transaction: &DArc<Transaction>) -> bool {
+        let inner = self.inner.lock();
+        match &inner.current_transaction {
+            None => false,
+            Some(current) => Arc::ptr_eq(current, transaction),
+        }
+    }
+
+    /// Determines the current top of the transaction stack. It fails if the top is in another
+    /// thread (i.e., this thread belongs to a stack but it has called another thread). The top is
+    /// [`None`] if the thread is not currently participating in a transaction stack.
+    fn top_of_transaction_stack(&self) -> Result<Option<DArc<Transaction>>> {
+        let inner = self.inner.lock();
+        if let Some(cur) = &inner.current_transaction {
+            if core::ptr::eq(self, cur.from.as_ref()) {
+                pr_warn!("got new transaction with bad transaction stack");
+                return Err(EINVAL);
+            }
+            Ok(Some(cur.clone()))
+        } else {
+            Ok(None)
+        }
+    }
+
+    fn transaction<T>(self: &Arc<Self>, tr: &BinderTransactionDataSg, inner: T)
+    where
+        T: FnOnce(&Arc<Self>, &BinderTransactionDataSg) -> BinderResult,
+    {
+        if let Err(err) = inner(self, tr) {
+            if err.should_pr_warn() {
+                let mut ee = self.inner.lock().extended_error;
+                ee.command = err.reply;
+                ee.param = err.as_errno();
+                pr_warn!(
+                    "Transaction failed: {:?} my_pid:{}",
+                    err,
+                    self.process.pid_in_current_ns()
+                );
+            }
+
+            self.push_return_work(err.reply);
+        }
+    }
+
+    fn transaction_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult {
+        // SAFETY: Handle's type has no invalid bit patterns.
+        let handle = unsafe { tr.transaction_data.target.handle };
+        let node_ref = self.process.get_transaction_node(handle)?;
+        security::binder_transaction(&self.process.cred, &node_ref.node.owner.cred)?;
+        // TODO: We need to ensure that there isn't a pending transaction in the work queue. How
+        // could this happen?
+        let top = self.top_of_transaction_stack()?;
+        let list_completion = DTRWrap::arc_try_new(DeliverCode::new(BR_TRANSACTION_COMPLETE))?;
+        let completion = list_completion.clone_arc();
+        let transaction = Transaction::new(node_ref, top, self, tr)?;
+
+        // Check that the transaction stack hasn't changed while the lock was released, then update
+        // it with the new transaction.
+        {
+            let mut inner = self.inner.lock();
+            if !transaction.is_stacked_on(&inner.current_transaction) {
+                pr_warn!("Transaction stack changed during transaction!");
+                return Err(EINVAL.into());
+            }
+            inner.current_transaction = Some(transaction.clone_arc());
+            // We push the completion as a deferred work so that we wait for the reply before
+            // returning to userland.
+            inner.push_work_deferred(list_completion);
+        }
+
+        if let Err(e) = transaction.submit() {
+            completion.skip();
+            // Define `transaction` first to drop it after `inner`.
+            let transaction;
+            let mut inner = self.inner.lock();
+            transaction = inner.current_transaction.take().unwrap();
+            inner.current_transaction = transaction.clone_next();
+            Err(e)
+        } else {
+            Ok(())
+        }
+    }
+
+    fn reply_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult {
+        let orig = self.inner.lock().pop_transaction_to_reply(self)?;
+        if !orig.from.is_current_transaction(&orig) {
+            return Err(EINVAL.into());
+        }
+
+        // We need to complete the transaction even if we cannot complete building the reply.
+        let out = (|| -> BinderResult<_> {
+            let completion = DTRWrap::arc_try_new(DeliverCode::new(BR_TRANSACTION_COMPLETE))?;
+            let process = orig.from.process.clone();
+            let allow_fds = orig.flags & TF_ACCEPT_FDS != 0;
+            let reply = Transaction::new_reply(self, process, tr, allow_fds)?;
+            self.inner.lock().push_work(completion);
+            orig.from.deliver_reply(Ok(reply), &orig);
+            Ok(())
+        })()
+        .map_err(|mut err| {
+            // At this point we only return `BR_TRANSACTION_COMPLETE` to the caller, and we must let
+            // the sender know that the transaction has completed (with an error in this case).
+            pr_warn!(
+                "Failure {:?} during reply - delivering BR_FAILED_REPLY to sender.",
+                err
+            );
+            let reply = Err(BR_FAILED_REPLY);
+            orig.from.deliver_reply(reply, &orig);
+            err.reply = BR_TRANSACTION_COMPLETE;
+            err
+        });
+
+        out
+    }
+
+    fn oneway_transaction_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult {
+        // SAFETY: The `handle` field is valid for all possible byte values, so reading from the
+        // union is okay.
+        let handle = unsafe { tr.transaction_data.target.handle };
+        let node_ref = self.process.get_transaction_node(handle)?;
+        security::binder_transaction(&self.process.cred, &node_ref.node.owner.cred)?;
+        let transaction = Transaction::new(node_ref, None, self, tr)?;
+        let code = if self.process.is_oneway_spam_detection_enabled()
+            && transaction.oneway_spam_detected
+        {
+            BR_ONEWAY_SPAM_SUSPECT
+        } else {
+            BR_TRANSACTION_COMPLETE
+        };
+        let list_completion = DTRWrap::arc_try_new(DeliverCode::new(code))?;
+        let completion = list_completion.clone_arc();
+        self.inner.lock().push_work(list_completion);
+        match transaction.submit() {
+            Ok(()) => Ok(()),
+            Err(err) => {
+                completion.skip();
+                Err(err)
+            }
+        }
+    }
+
+    fn write(self: &Arc<Self>, req: &mut BinderWriteRead) -> Result {
+        let write_start = req.write_buffer.wrapping_add(req.write_consumed);
+        let write_len = req.write_size.saturating_sub(req.write_consumed);
+        let mut reader =
+            UserSlice::new(UserPtr::from_addr(write_start as _), write_len as _).reader();
+
+        while reader.len() >= size_of::<u32>() && self.inner.lock().return_work.is_unused() {
+            let before = reader.len();
+            let cmd = reader.read::<u32>()?;
+            GLOBAL_STATS.inc_bc(cmd);
+            self.process.stats.inc_bc(cmd);
+            match cmd {
+                BC_TRANSACTION => {
+                    let tr = reader.read::<BinderTransactionData>()?.with_buffers_size(0);
+                    if tr.transaction_data.flags & TF_ONE_WAY != 0 {
+                        self.transaction(&tr, Self::oneway_transaction_inner);
+                    } else {
+                        self.transaction(&tr, Self::transaction_inner);
+                    }
+                }
+                BC_TRANSACTION_SG => {
+                    let tr = reader.read::<BinderTransactionDataSg>()?;
+                    if tr.transaction_data.flags & TF_ONE_WAY != 0 {
+                        self.transaction(&tr, Self::oneway_transaction_inner);
+                    } else {
+                        self.transaction(&tr, Self::transaction_inner);
+                    }
+                }
+                BC_REPLY => {
+                    let tr = reader.read::<BinderTransactionData>()?.with_buffers_size(0);
+                    self.transaction(&tr, Self::reply_inner)
+                }
+                BC_REPLY_SG => {
+                    let tr = reader.read::<BinderTransactionDataSg>()?;
+                    self.transaction(&tr, Self::reply_inner)
+                }
+                BC_FREE_BUFFER => {
+                    let buffer = self.process.buffer_get(reader.read()?);
+                    if let Some(buffer) = &buffer {
+                        if buffer.looper_need_return_on_free() {
+                            self.inner.lock().looper_need_return = true;
+                        }
+                    }
+                    drop(buffer);
+                }
+                BC_INCREFS => {
+                    self.process
+                        .as_arc_borrow()
+                        .update_ref(reader.read()?, true, false)?
+                }
+                BC_ACQUIRE => {
+                    self.process
+                        .as_arc_borrow()
+                        .update_ref(reader.read()?, true, true)?
+                }
+                BC_RELEASE => {
+                    self.process
+                        .as_arc_borrow()
+                        .update_ref(reader.read()?, false, true)?
+                }
+                BC_DECREFS => {
+                    self.process
+                        .as_arc_borrow()
+                        .update_ref(reader.read()?, false, false)?
+                }
+                BC_INCREFS_DONE => self.process.inc_ref_done(&mut reader, false)?,
+                BC_ACQUIRE_DONE => self.process.inc_ref_done(&mut reader, true)?,
+                BC_REQUEST_DEATH_NOTIFICATION => self.process.request_death(&mut reader, self)?,
+                BC_CLEAR_DEATH_NOTIFICATION => self.process.clear_death(&mut reader, self)?,
+                BC_DEAD_BINDER_DONE => self.process.dead_binder_done(reader.read()?, self),
+                BC_REGISTER_LOOPER => {
+                    let valid = self.process.register_thread();
+                    self.inner.lock().looper_register(valid);
+                }
+                BC_ENTER_LOOPER => self.inner.lock().looper_enter(),
+                BC_EXIT_LOOPER => self.inner.lock().looper_exit(),
+                BC_REQUEST_FREEZE_NOTIFICATION => self.process.request_freeze_notif(&mut reader)?,
+                BC_CLEAR_FREEZE_NOTIFICATION => self.process.clear_freeze_notif(&mut reader)?,
+                BC_FREEZE_NOTIFICATION_DONE => self.process.freeze_notif_done(&mut reader)?,
+
+                // Fail if given an unknown error code.
+                // BC_ATTEMPT_ACQUIRE and BC_ACQUIRE_RESULT are no longer supported.
+                _ => return Err(EINVAL),
+            }
+            // Update the number of write bytes consumed.
+            req.write_consumed += (before - reader.len()) as u64;
+        }
+
+        Ok(())
+    }
+
+    fn read(self: &Arc<Self>, req: &mut BinderWriteRead, wait: bool) -> Result {
+        let read_start = req.read_buffer.wrapping_add(req.read_consumed);
+        let read_len = req.read_size.saturating_sub(req.read_consumed);
+        let mut writer = BinderReturnWriter::new(
+            UserSlice::new(UserPtr::from_addr(read_start as _), read_len as _).writer(),
+            self,
+        );
+        let (in_pool, use_proc_queue) = {
+            let inner = self.inner.lock();
+            (inner.is_looper(), inner.should_use_process_work_queue())
+        };
+
+        let getter = if use_proc_queue {
+            Self::get_work
+        } else {
+            Self::get_work_local
+        };
+
+        // Reserve some room at the beginning of the read buffer so that we can send a
+        // BR_SPAWN_LOOPER if we need to.
+        let mut has_noop_placeholder = false;
+        if req.read_consumed == 0 {
+            if let Err(err) = writer.write_code(BR_NOOP) {
+                pr_warn!("Failure when writing BR_NOOP at beginning of buffer.");
+                return Err(err);
+            }
+            has_noop_placeholder = true;
+        }
+
+        // Loop doing work while there is room in the buffer.
+        let initial_len = writer.len();
+        while writer.len() >= size_of::<uapi::binder_transaction_data_secctx>() + 4 {
+            match getter(self, wait && initial_len == writer.len()) {
+                Ok(Some(work)) => match work.into_arc().do_work(self, &mut writer) {
+                    Ok(true) => {}
+                    Ok(false) => break,
+                    Err(err) => {
+                        return Err(err);
+                    }
+                },
+                Ok(None) => {
+                    break;
+                }
+                Err(err) => {
+                    // Propagate the error if we haven't written anything else.
+                    if err != EINTR && err != EAGAIN {
+                        pr_warn!("Failure in work getter: {:?}", err);
+                    }
+                    if initial_len == writer.len() {
+                        return Err(err);
+                    } else {
+                        break;
+                    }
+                }
+            }
+        }
+
+        req.read_consumed += read_len - writer.len() as u64;
+
+        // Write BR_SPAWN_LOOPER if the process needs more threads for its pool.
+        if has_noop_placeholder && in_pool && self.process.needs_thread() {
+            let mut writer =
+                UserSlice::new(UserPtr::from_addr(req.read_buffer as _), req.read_size as _)
+                    .writer();
+            writer.write(&BR_SPAWN_LOOPER)?;
+        }
+        Ok(())
+    }
+
+    pub(crate) fn write_read(self: &Arc<Self>, data: UserSlice, wait: bool) -> Result {
+        let (mut reader, mut writer) = data.reader_writer();
+        let mut req = reader.read::<BinderWriteRead>()?;
+
+        // Go through the write buffer.
+        let mut ret = Ok(());
+        if req.write_size > 0 {
+            ret = self.write(&mut req);
+            if let Err(err) = ret {
+                pr_warn!(
+                    "Write failure {:?} in pid:{}",
+                    err,
+                    self.process.pid_in_current_ns()
+                );
+                req.read_consumed = 0;
+                writer.write(&req)?;
+                self.inner.lock().looper_need_return = false;
+                return ret;
+            }
+        }
+
+        // Go through the work queue.
+        if req.read_size > 0 {
+            ret = self.read(&mut req, wait);
+            if ret.is_err() && ret != Err(EINTR) {
+                pr_warn!(
+                    "Read failure {:?} in pid:{}",
+                    ret,
+                    self.process.pid_in_current_ns()
+                );
+            }
+        }
+
+        // Write the request back so that the consumed fields are visible to the caller.
+        writer.write(&req)?;
+
+        self.inner.lock().looper_need_return = false;
+
+        ret
+    }
+
+    pub(crate) fn poll(&self, file: &File, table: PollTable<'_>) -> (bool, u32) {
+        table.register_wait(file, &self.work_condvar);
+        let mut inner = self.inner.lock();
+        (inner.should_use_process_work_queue(), inner.poll())
+    }
+
+    /// Make the call to `get_work` or `get_work_local` return immediately, if any.
+    pub(crate) fn exit_looper(&self) {
+        let mut inner = self.inner.lock();
+        let should_notify = inner.looper_flags & LOOPER_WAITING != 0;
+        if should_notify {
+            inner.looper_need_return = true;
+        }
+        drop(inner);
+
+        if should_notify {
+            self.work_condvar.notify_one();
+        }
+    }
+
+    pub(crate) fn notify_if_poll_ready(&self, sync: bool) {
+        // Determine if we need to notify. This requires the lock.
+        let inner = self.inner.lock();
+        let notify = inner.looper_flags & LOOPER_POLL != 0 && inner.should_use_process_work_queue();
+        drop(inner);
+
+        // Now that the lock is no longer held, notify the waiters if we have to.
+        if notify {
+            if sync {
+                self.work_condvar.notify_sync();
+            } else {
+                self.work_condvar.notify_one();
+            }
+        }
+    }
+
+    pub(crate) fn release(self: &Arc<Self>) {
+        self.inner.lock().is_dead = true;
+
+        //self.work_condvar.clear();
+        self.unwind_transaction_stack();
+
+        // Cancel all pending work items.
+        while let Ok(Some(work)) = self.get_work_local(false) {
+            work.into_arc().cancel();
+        }
+    }
+}
+
+#[pin_data]
+struct ThreadError {
+    error_code: AtomicU32,
+    #[pin]
+    links_track: AtomicTracker,
+}
+
+impl ThreadError {
+    fn try_new() -> Result<DArc<Self>> {
+        DTRWrap::arc_pin_init(pin_init!(Self {
+            error_code: AtomicU32::new(BR_OK),
+            links_track <- AtomicTracker::new(),
+        }))
+        .map(ListArc::into_arc)
+    }
+
+    fn set_error_code(&self, code: u32) {
+        self.error_code.store(code, Ordering::Relaxed);
+    }
+
+    fn is_unused(&self) -> bool {
+        self.error_code.load(Ordering::Relaxed) == BR_OK
+    }
+}
+
+impl DeliverToRead for ThreadError {
+    fn do_work(
+        self: DArc<Self>,
+        _thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let code = self.error_code.load(Ordering::Relaxed);
+        self.error_code.store(BR_OK, Ordering::Relaxed);
+        writer.write_code(code)?;
+        Ok(true)
+    }
+
+    fn cancel(self: DArc<Self>) {}
+
+    fn should_sync_wakeup(&self) -> bool {
+        false
+    }
+
+    fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> {
+        seq_print!(
+            m,
+            "{}transaction error: {}\n",
+            prefix,
+            self.error_code.load(Ordering::Relaxed)
+        );
+        Ok(())
+    }
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for ThreadError {
+        tracked_by links_track: AtomicTracker;
+    }
+}
diff --git a/drivers/android/binder/trace.rs b/drivers/android/binder/trace.rs
new file mode 100644
index 000000000000..af0e4392805e
--- /dev/null
+++ b/drivers/android/binder/trace.rs
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use kernel::ffi::{c_uint, c_ulong};
+use kernel::tracepoint::declare_trace;
+
+declare_trace! {
+    unsafe fn rust_binder_ioctl(cmd: c_uint, arg: c_ulong);
+}
+
+#[inline]
+pub(crate) fn trace_ioctl(cmd: u32, arg: usize) {
+    // SAFETY: Always safe to call.
+    unsafe { rust_binder_ioctl(cmd, arg as c_ulong) }
+}
diff --git a/drivers/android/binder/transaction.rs b/drivers/android/binder/transaction.rs
new file mode 100644
index 000000000000..02512175d622
--- /dev/null
+++ b/drivers/android/binder/transaction.rs
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+use core::sync::atomic::{AtomicBool, Ordering};
+use kernel::{
+    prelude::*,
+    seq_file::SeqFile,
+    seq_print,
+    sync::{Arc, SpinLock},
+    task::Kuid,
+    time::{Instant, Monotonic},
+    types::ScopeGuard,
+};
+
+use crate::{
+    allocation::{Allocation, TranslatedFds},
+    defs::*,
+    error::{BinderError, BinderResult},
+    node::{Node, NodeRef},
+    process::{Process, ProcessInner},
+    ptr_align,
+    thread::{PushWorkRes, Thread},
+    BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead,
+};
+
+#[pin_data(PinnedDrop)]
+pub(crate) struct Transaction {
+    pub(crate) debug_id: usize,
+    target_node: Option<DArc<Node>>,
+    pub(crate) from_parent: Option<DArc<Transaction>>,
+    pub(crate) from: Arc<Thread>,
+    pub(crate) to: Arc<Process>,
+    #[pin]
+    allocation: SpinLock<Option<Allocation>>,
+    is_outstanding: AtomicBool,
+    code: u32,
+    pub(crate) flags: u32,
+    data_size: usize,
+    offsets_size: usize,
+    data_address: usize,
+    sender_euid: Kuid,
+    txn_security_ctx_off: Option<usize>,
+    pub(crate) oneway_spam_detected: bool,
+    start_time: Instant<Monotonic>,
+}
+
+kernel::list::impl_list_arc_safe! {
+    impl ListArcSafe<0> for Transaction { untracked; }
+}
+
+impl Transaction {
+    pub(crate) fn new(
+        node_ref: NodeRef,
+        from_parent: Option<DArc<Transaction>>,
+        from: &Arc<Thread>,
+        tr: &BinderTransactionDataSg,
+    ) -> BinderResult<DLArc<Self>> {
+        let debug_id = super::next_debug_id();
+        let trd = &tr.transaction_data;
+        let allow_fds = node_ref.node.flags & FLAT_BINDER_FLAG_ACCEPTS_FDS != 0;
+        let txn_security_ctx = node_ref.node.flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX != 0;
+        let mut txn_security_ctx_off = if txn_security_ctx { Some(0) } else { None };
+        let to = node_ref.node.owner.clone();
+        let mut alloc = match from.copy_transaction_data(
+            to.clone(),
+            tr,
+            debug_id,
+            allow_fds,
+            txn_security_ctx_off.as_mut(),
+        ) {
+            Ok(alloc) => alloc,
+            Err(err) => {
+                if !err.is_dead() {
+                    pr_warn!("Failure in copy_transaction_data: {:?}", err);
+                }
+                return Err(err);
+            }
+        };
+        let oneway_spam_detected = alloc.oneway_spam_detected;
+        if trd.flags & TF_ONE_WAY != 0 {
+            if from_parent.is_some() {
+                pr_warn!("Oneway transaction should not be in a transaction stack.");
+                return Err(EINVAL.into());
+            }
+            alloc.set_info_oneway_node(node_ref.node.clone());
+        }
+        if trd.flags & TF_CLEAR_BUF != 0 {
+            alloc.set_info_clear_on_drop();
+        }
+        let target_node = node_ref.node.clone();
+        alloc.set_info_target_node(node_ref);
+        let data_address = alloc.ptr;
+
+        Ok(DTRWrap::arc_pin_init(pin_init!(Transaction {
+            debug_id,
+            target_node: Some(target_node),
+            from_parent,
+            sender_euid: from.process.task.euid(),
+            from: from.clone(),
+            to,
+            code: trd.code,
+            flags: trd.flags,
+            data_size: trd.data_size as _,
+            offsets_size: trd.offsets_size as _,
+            data_address,
+            allocation <- kernel::new_spinlock!(Some(alloc.success()), "Transaction::new"),
+            is_outstanding: AtomicBool::new(false),
+            txn_security_ctx_off,
+            oneway_spam_detected,
+            start_time: Instant::now(),
+        }))?)
+    }
+
+    pub(crate) fn new_reply(
+        from: &Arc<Thread>,
+        to: Arc<Process>,
+        tr: &BinderTransactionDataSg,
+        allow_fds: bool,
+    ) -> BinderResult<DLArc<Self>> {
+        let debug_id = super::next_debug_id();
+        let trd = &tr.transaction_data;
+        let mut alloc = match from.copy_transaction_data(to.clone(), tr, debug_id, allow_fds, None)
+        {
+            Ok(alloc) => alloc,
+            Err(err) => {
+                pr_warn!("Failure in copy_transaction_data: {:?}", err);
+                return Err(err);
+            }
+        };
+        let oneway_spam_detected = alloc.oneway_spam_detected;
+        if trd.flags & TF_CLEAR_BUF != 0 {
+            alloc.set_info_clear_on_drop();
+        }
+        Ok(DTRWrap::arc_pin_init(pin_init!(Transaction {
+            debug_id,
+            target_node: None,
+            from_parent: None,
+            sender_euid: from.process.task.euid(),
+            from: from.clone(),
+            to,
+            code: trd.code,
+            flags: trd.flags,
+            data_size: trd.data_size as _,
+            offsets_size: trd.offsets_size as _,
+            data_address: alloc.ptr,
+            allocation <- kernel::new_spinlock!(Some(alloc.success()), "Transaction::new"),
+            is_outstanding: AtomicBool::new(false),
+            txn_security_ctx_off: None,
+            oneway_spam_detected,
+            start_time: Instant::now(),
+        }))?)
+    }
+
+    #[inline(never)]
+    pub(crate) fn debug_print_inner(&self, m: &SeqFile, prefix: &str) {
+        seq_print!(
+            m,
+            "{}{}: from {}:{} to {} code {:x} flags {:x} elapsed {}ms",
+            prefix,
+            self.debug_id,
+            self.from.process.task.pid(),
+            self.from.id,
+            self.to.task.pid(),
+            self.code,
+            self.flags,
+            self.start_time.elapsed().as_millis(),
+        );
+        if let Some(target_node) = &self.target_node {
+            seq_print!(m, " node {}", target_node.debug_id);
+        }
+        seq_print!(m, " size {}:{}\n", self.data_size, self.offsets_size);
+    }
+
+    /// Determines if the transaction is stacked on top of the given transaction.
+    pub(crate) fn is_stacked_on(&self, onext: &Option<DArc<Self>>) -> bool {
+        match (&self.from_parent, onext) {
+            (None, None) => true,
+            (Some(from_parent), Some(next)) => Arc::ptr_eq(from_parent, next),
+            _ => false,
+        }
+    }
+
+    /// Returns a pointer to the next transaction on the transaction stack, if there is one.
+    pub(crate) fn clone_next(&self) -> Option<DArc<Self>> {
+        Some(self.from_parent.as_ref()?.clone())
+    }
+
+    /// Searches in the transaction stack for a thread that belongs to the target process. This is
+    /// useful when finding a target for a new transaction: if the node belongs to a process that
+    /// is already part of the transaction stack, we reuse the thread.
+    fn find_target_thread(&self) -> Option<Arc<Thread>> {
+        let mut it = &self.from_parent;
+        while let Some(transaction) = it {
+            if Arc::ptr_eq(&transaction.from.process, &self.to) {
+                return Some(transaction.from.clone());
+            }
+            it = &transaction.from_parent;
+        }
+        None
+    }
+
+    /// Searches in the transaction stack for a transaction originating at the given thread.
+    pub(crate) fn find_from(&self, thread: &Thread) -> Option<&DArc<Transaction>> {
+        let mut it = &self.from_parent;
+        while let Some(transaction) = it {
+            if core::ptr::eq(thread, transaction.from.as_ref()) {
+                return Some(transaction);
+            }
+
+            it = &transaction.from_parent;
+        }
+        None
+    }
+
+    pub(crate) fn set_outstanding(&self, to_process: &mut ProcessInner) {
+        // No race because this method is only called once.
+        if !self.is_outstanding.load(Ordering::Relaxed) {
+            self.is_outstanding.store(true, Ordering::Relaxed);
+            to_process.add_outstanding_txn();
+        }
+    }
+
+    /// Decrement `outstanding_txns` in `to` if it hasn't already been decremented.
+    fn drop_outstanding_txn(&self) {
+        // No race because this is called at most twice, and one of the calls are in the
+        // destructor, which is guaranteed to not race with any other operations on the
+        // transaction. It also cannot race with `set_outstanding`, since submission happens
+        // before delivery.
+        if self.is_outstanding.load(Ordering::Relaxed) {
+            self.is_outstanding.store(false, Ordering::Relaxed);
+            self.to.drop_outstanding_txn();
+        }
+    }
+
+    /// Submits the transaction to a work queue. Uses a thread if there is one in the transaction
+    /// stack, otherwise uses the destination process.
+    ///
+    /// Not used for replies.
+    pub(crate) fn submit(self: DLArc<Self>) -> BinderResult {
+        // Defined before `process_inner` so that the destructor runs after releasing the lock.
+        let mut _t_outdated;
+
+        let oneway = self.flags & TF_ONE_WAY != 0;
+        let process = self.to.clone();
+        let mut process_inner = process.inner.lock();
+
+        self.set_outstanding(&mut process_inner);
+
+        if oneway {
+            if let Some(target_node) = self.target_node.clone() {
+                if process_inner.is_frozen {
+                    process_inner.async_recv = true;
+                    if self.flags & TF_UPDATE_TXN != 0 {
+                        if let Some(t_outdated) =
+                            target_node.take_outdated_transaction(&self, &mut process_inner)
+                        {
+                            // Save the transaction to be dropped after locks are released.
+                            _t_outdated = t_outdated;
+                        }
+                    }
+                }
+                match target_node.submit_oneway(self, &mut process_inner) {
+                    Ok(()) => {}
+                    Err((err, work)) => {
+                        drop(process_inner);
+                        // Drop work after releasing process lock.
+                        drop(work);
+                        return Err(err);
+                    }
+                }
+
+                if process_inner.is_frozen {
+                    return Err(BinderError::new_frozen_oneway());
+                } else {
+                    return Ok(());
+                }
+            } else {
+                pr_err!("Failed to submit oneway transaction to node.");
+            }
+        }
+
+        if process_inner.is_frozen {
+            process_inner.sync_recv = true;
+            return Err(BinderError::new_frozen());
+        }
+
+        let res = if let Some(thread) = self.find_target_thread() {
+            match thread.push_work(self) {
+                PushWorkRes::Ok => Ok(()),
+                PushWorkRes::FailedDead(me) => Err((BinderError::new_dead(), me)),
+            }
+        } else {
+            process_inner.push_work(self)
+        };
+        drop(process_inner);
+
+        match res {
+            Ok(()) => Ok(()),
+            Err((err, work)) => {
+                // Drop work after releasing process lock.
+                drop(work);
+                Err(err)
+            }
+        }
+    }
+
+    /// Check whether one oneway transaction can supersede another.
+    pub(crate) fn can_replace(&self, old: &Transaction) -> bool {
+        if self.from.process.task.pid() != old.from.process.task.pid() {
+            return false;
+        }
+
+        if self.flags & old.flags & (TF_ONE_WAY | TF_UPDATE_TXN) != (TF_ONE_WAY | TF_UPDATE_TXN) {
+            return false;
+        }
+
+        let target_node_match = match (self.target_node.as_ref(), old.target_node.as_ref()) {
+            (None, None) => true,
+            (Some(tn1), Some(tn2)) => Arc::ptr_eq(tn1, tn2),
+            _ => false,
+        };
+
+        self.code == old.code && self.flags == old.flags && target_node_match
+    }
+
+    fn prepare_file_list(&self) -> Result<TranslatedFds> {
+        let mut alloc = self.allocation.lock().take().ok_or(ESRCH)?;
+
+        match alloc.translate_fds() {
+            Ok(translated) => {
+                *self.allocation.lock() = Some(alloc);
+                Ok(translated)
+            }
+            Err(err) => {
+                // Free the allocation eagerly.
+                drop(alloc);
+                Err(err)
+            }
+        }
+    }
+}
+
+impl DeliverToRead for Transaction {
+    fn do_work(
+        self: DArc<Self>,
+        thread: &Thread,
+        writer: &mut BinderReturnWriter<'_>,
+    ) -> Result<bool> {
+        let send_failed_reply = ScopeGuard::new(|| {
+            if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 {
+                let reply = Err(BR_FAILED_REPLY);
+                self.from.deliver_reply(reply, &self);
+            }
+            self.drop_outstanding_txn();
+        });
+
+        let files = if let Ok(list) = self.prepare_file_list() {
+            list
+        } else {
+            // On failure to process the list, we send a reply back to the sender and ignore the
+            // transaction on the recipient.
+            return Ok(true);
+        };
+
+        let mut tr_sec = BinderTransactionDataSecctx::default();
+        let tr = tr_sec.tr_data();
+        if let Some(target_node) = &self.target_node {
+            let (ptr, cookie) = target_node.get_id();
+            tr.target.ptr = ptr as _;
+            tr.cookie = cookie as _;
+        };
+        tr.code = self.code;
+        tr.flags = self.flags;
+        tr.data_size = self.data_size as _;
+        tr.data.ptr.buffer = self.data_address as _;
+        tr.offsets_size = self.offsets_size as _;
+        if tr.offsets_size > 0 {
+            tr.data.ptr.offsets = (self.data_address + ptr_align(self.data_size).unwrap()) as _;
+        }
+        tr.sender_euid = self.sender_euid.into_uid_in_current_ns();
+        tr.sender_pid = 0;
+        if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 {
+            // Not a reply and not one-way.
+            tr.sender_pid = self.from.process.pid_in_current_ns();
+        }
+        let code = if self.target_node.is_none() {
+            BR_REPLY
+        } else if self.txn_security_ctx_off.is_some() {
+            BR_TRANSACTION_SEC_CTX
+        } else {
+            BR_TRANSACTION
+        };
+
+        // Write the transaction code and data to the user buffer.
+        writer.write_code(code)?;
+        if let Some(off) = self.txn_security_ctx_off {
+            tr_sec.secctx = (self.data_address + off) as u64;
+            writer.write_payload(&tr_sec)?;
+        } else {
+            writer.write_payload(&*tr)?;
+        }
+
+        let mut alloc = self.allocation.lock().take().ok_or(ESRCH)?;
+
+        // Dismiss the completion of transaction with a failure. No failure paths are allowed from
+        // here on out.
+        send_failed_reply.dismiss();
+
+        // Commit files, and set FDs in FDA to be closed on buffer free.
+        let close_on_free = files.commit();
+        alloc.set_info_close_on_free(close_on_free);
+
+        // It is now the user's responsibility to clear the allocation.
+        alloc.keep_alive();
+
+        self.drop_outstanding_txn();
+
+        // When this is not a reply and not a oneway transaction, update `current_transaction`. If
+        // it's a reply, `current_transaction` has already been updated appropriately.
+        if self.target_node.is_some() && tr_sec.transaction_data.flags & TF_ONE_WAY == 0 {
+            thread.set_current_transaction(self);
+        }
+
+        Ok(false)
+    }
+
+    fn cancel(self: DArc<Self>) {
+        let allocation = self.allocation.lock().take();
+        drop(allocation);
+
+        // If this is not a reply or oneway transaction, then send a dead reply.
+        if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 {
+            let reply = Err(BR_DEAD_REPLY);
+            self.from.deliver_reply(reply, &self);
+        }
+
+        self.drop_outstanding_txn();
+    }
+
+    fn should_sync_wakeup(&self) -> bool {
+        self.flags & TF_ONE_WAY == 0
+    }
+
+    fn debug_print(&self, m: &SeqFile, _prefix: &str, tprefix: &str) -> Result<()> {
+        self.debug_print_inner(m, tprefix);
+        Ok(())
+    }
+}
+
+#[pinned_drop]
+impl PinnedDrop for Transaction {
+    fn drop(self: Pin<&mut Self>) {
+        self.drop_outstanding_txn();
+    }
+}
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 138f6d43d13b..979c96b74cad 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -23,10 +23,11 @@
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
 #include <linux/sizes.h>
+#include <kunit/visibility.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
-struct list_lru binder_alloc_lru;
+static struct list_lru binder_freelist;
 
 static DEFINE_MUTEX(binder_alloc_mmap_lock);
 
@@ -57,13 +58,14 @@ static struct binder_buffer *binder_buffer_prev(struct binder_buffer *buffer)
 	return list_entry(buffer->entry.prev, struct binder_buffer, entry);
 }
 
-static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
-				       struct binder_buffer *buffer)
+VISIBLE_IF_KUNIT size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
+						 struct binder_buffer *buffer)
 {
 	if (list_is_last(&buffer->entry, &alloc->buffers))
-		return alloc->buffer + alloc->buffer_size - buffer->user_data;
+		return alloc->vm_start + alloc->buffer_size - buffer->user_data;
 	return binder_buffer_next(buffer)->user_data - buffer->user_data;
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_buffer_size);
 
 static void binder_insert_free_buffer(struct binder_alloc *alloc,
 				      struct binder_buffer *new_buffer)
@@ -125,23 +127,20 @@ static void binder_insert_allocated_buffer_locked(
 
 static struct binder_buffer *binder_alloc_prepare_to_free_locked(
 		struct binder_alloc *alloc,
-		uintptr_t user_ptr)
+		unsigned long user_ptr)
 {
 	struct rb_node *n = alloc->allocated_buffers.rb_node;
 	struct binder_buffer *buffer;
-	void __user *uptr;
-
-	uptr = (void __user *)user_ptr;
 
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(buffer->free);
 
-		if (uptr < buffer->user_data)
+		if (user_ptr < buffer->user_data) {
 			n = n->rb_left;
-		else if (uptr > buffer->user_data)
+		} else if (user_ptr > buffer->user_data) {
 			n = n->rb_right;
-		else {
+		} else {
 			/*
 			 * Guard against user threads attempting to
 			 * free the buffer when in use by kernel or
@@ -168,162 +167,299 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked(
  * Return:	Pointer to buffer or NULL
  */
 struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-						   uintptr_t user_ptr)
+						   unsigned long user_ptr)
 {
-	struct binder_buffer *buffer;
+	guard(mutex)(&alloc->mutex);
+	return binder_alloc_prepare_to_free_locked(alloc, user_ptr);
+}
 
-	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
-	mutex_unlock(&alloc->mutex);
-	return buffer;
+static inline void
+binder_set_installed_page(struct binder_alloc *alloc,
+			  unsigned long index,
+			  struct page *page)
+{
+	/* Pairs with acquire in binder_get_installed_page() */
+	smp_store_release(&alloc->pages[index], page);
 }
 
-static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
-				    void __user *start, void __user *end)
+static inline struct page *
+binder_get_installed_page(struct binder_alloc *alloc, unsigned long index)
 {
-	void __user *page_addr;
-	unsigned long user_page_addr;
-	struct binder_lru_page *page;
-	struct vm_area_struct *vma = NULL;
-	struct mm_struct *mm = NULL;
-	bool need_mm = false;
+	/* Pairs with release in binder_set_installed_page() */
+	return smp_load_acquire(&alloc->pages[index]);
+}
 
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: %s pages %pK-%pK\n", alloc->pid,
-		     allocate ? "allocate" : "free", start, end);
+static void binder_lru_freelist_add(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
+{
+	unsigned long page_addr;
+	struct page *page;
 
-	if (end <= start)
-		return 0;
+	trace_binder_update_page_range(alloc, false, start, end);
 
-	trace_binder_update_page_range(alloc, allocate, start, end);
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		size_t index;
+		int ret;
 
-	if (allocate == 0)
-		goto free_range;
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		page = binder_get_installed_page(alloc, index);
+		if (!page)
+			continue;
 
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
-		if (!page->page_ptr) {
-			need_mm = true;
-			break;
-		}
+		trace_binder_free_lru_start(alloc, index);
+
+		ret = list_lru_add(alloc->freelist,
+				   page_to_lru(page),
+				   page_to_nid(page),
+				   NULL);
+		WARN_ON(!ret);
+
+		trace_binder_free_lru_end(alloc, index);
 	}
+}
 
-	if (need_mm && mmget_not_zero(alloc->mm))
-		mm = alloc->mm;
+static inline
+void binder_alloc_set_mapped(struct binder_alloc *alloc, bool state)
+{
+	/* pairs with smp_load_acquire in binder_alloc_is_mapped() */
+	smp_store_release(&alloc->mapped, state);
+}
+
+static inline bool binder_alloc_is_mapped(struct binder_alloc *alloc)
+{
+	/* pairs with smp_store_release in binder_alloc_set_mapped() */
+	return smp_load_acquire(&alloc->mapped);
+}
+
+static struct page *binder_page_lookup(struct binder_alloc *alloc,
+				       unsigned long addr)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct page *page;
+	long npages = 0;
+
+	/*
+	 * Find an existing page in the remote mm. If missing,
+	 * don't attempt to fault-in just propagate an error.
+	 */
+	mmap_read_lock(mm);
+	if (binder_alloc_is_mapped(alloc))
+		npages = get_user_pages_remote(mm, addr, 1, FOLL_NOFAULT,
+					       &page, NULL);
+	mmap_read_unlock(mm);
+
+	return npages > 0 ? page : NULL;
+}
+
+static int binder_page_insert(struct binder_alloc *alloc,
+			      unsigned long addr,
+			      struct page *page)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct vm_area_struct *vma;
+	int ret = -ESRCH;
 
-	if (mm) {
-		mmap_write_lock(mm);
-		vma = alloc->vma;
+	/* attempt per-vma lock first */
+	vma = lock_vma_under_rcu(mm, addr);
+	if (vma) {
+		if (binder_alloc_is_mapped(alloc))
+			ret = vm_insert_page(vma, addr, page);
+		vma_end_read(vma);
+		return ret;
 	}
 
-	if (!vma && need_mm) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
-				   alloc->pid);
-		goto err_no_vma;
+	/* fall back to mmap_lock */
+	mmap_read_lock(mm);
+	vma = vma_lookup(mm, addr);
+	if (vma && binder_alloc_is_mapped(alloc))
+		ret = vm_insert_page(vma, addr, page);
+	mmap_read_unlock(mm);
+
+	return ret;
+}
+
+static struct page *binder_page_alloc(struct binder_alloc *alloc,
+				      unsigned long index)
+{
+	struct binder_shrinker_mdata *mdata;
+	struct page *page;
+
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page)
+		return NULL;
+
+	/* allocate and install shrinker metadata under page->private */
+	mdata = kzalloc(sizeof(*mdata), GFP_KERNEL);
+	if (!mdata) {
+		__free_page(page);
+		return NULL;
 	}
 
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		int ret;
-		bool on_lru;
-		size_t index;
+	mdata->alloc = alloc;
+	mdata->page_index = index;
+	INIT_LIST_HEAD(&mdata->lru);
+	set_page_private(page, (unsigned long)mdata);
 
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
+	return page;
+}
 
-		if (page->page_ptr) {
-			trace_binder_alloc_lru_start(alloc, index);
+static void binder_free_page(struct page *page)
+{
+	kfree((struct binder_shrinker_mdata *)page_private(page));
+	__free_page(page);
+}
 
-			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
-			WARN_ON(!on_lru);
+static int binder_install_single_page(struct binder_alloc *alloc,
+				      unsigned long index,
+				      unsigned long addr)
+{
+	struct page *page;
+	int ret;
 
-			trace_binder_alloc_lru_end(alloc, index);
-			continue;
+	if (!mmget_not_zero(alloc->mm))
+		return -ESRCH;
+
+	page = binder_page_alloc(alloc, index);
+	if (!page) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = binder_page_insert(alloc, addr, page);
+	switch (ret) {
+	case -EBUSY:
+		/*
+		 * EBUSY is ok. Someone installed the pte first but the
+		 * alloc->pages[index] has not been updated yet. Discard
+		 * our page and look up the one already installed.
+		 */
+		ret = 0;
+		binder_free_page(page);
+		page = binder_page_lookup(alloc, addr);
+		if (!page) {
+			pr_err("%d: failed to find page at offset %lx\n",
+			       alloc->pid, addr - alloc->vm_start);
+			ret = -ESRCH;
+			break;
 		}
+		fallthrough;
+	case 0:
+		/* Mark page installation complete and safe to use */
+		binder_set_installed_page(alloc, index, page);
+		break;
+	default:
+		binder_free_page(page);
+		pr_err("%d: %s failed to insert page at offset %lx with %d\n",
+		       alloc->pid, __func__, addr - alloc->vm_start, ret);
+		break;
+	}
+out:
+	mmput_async(alloc->mm);
+	return ret;
+}
 
-		if (WARN_ON(!vma))
-			goto err_page_ptr_cleared;
+static int binder_install_buffer_pages(struct binder_alloc *alloc,
+				       struct binder_buffer *buffer,
+				       size_t size)
+{
+	unsigned long start, final;
+	unsigned long page_addr;
+
+	start = buffer->user_data & PAGE_MASK;
+	final = PAGE_ALIGN(buffer->user_data + size);
+
+	for (page_addr = start; page_addr < final; page_addr += PAGE_SIZE) {
+		unsigned long index;
+		int ret;
+
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		if (binder_get_installed_page(alloc, index))
+			continue;
 
 		trace_binder_alloc_page_start(alloc, index);
-		page->page_ptr = alloc_page(GFP_KERNEL |
-					    __GFP_HIGHMEM |
-					    __GFP_ZERO);
-		if (!page->page_ptr) {
-			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
-				alloc->pid, page_addr);
-			goto err_alloc_page_failed;
-		}
-		page->alloc = alloc;
-		INIT_LIST_HEAD(&page->lru);
-
-		user_page_addr = (uintptr_t)page_addr;
-		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
-		if (ret) {
-			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
-			       alloc->pid, user_page_addr);
-			goto err_vm_insert_page_failed;
-		}
 
-		if (index + 1 > alloc->pages_high)
-			alloc->pages_high = index + 1;
+		ret = binder_install_single_page(alloc, index, page_addr);
+		if (ret)
+			return ret;
 
 		trace_binder_alloc_page_end(alloc, index);
 	}
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput(mm);
-	}
+
 	return 0;
+}
 
-free_range:
-	for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) {
-		bool ret;
-		size_t index;
+/* The range of pages should exclude those shared with other buffers */
+static void binder_lru_freelist_del(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
+{
+	unsigned long page_addr;
+	struct page *page;
 
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
+	trace_binder_update_page_range(alloc, true, start, end);
 
-		trace_binder_free_lru_start(alloc, index);
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		unsigned long index;
+		bool on_lru;
 
-		ret = list_lru_add(&binder_alloc_lru, &page->lru);
-		WARN_ON(!ret);
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		page = binder_get_installed_page(alloc, index);
 
-		trace_binder_free_lru_end(alloc, index);
-		if (page_addr == start)
-			break;
-		continue;
-
-err_vm_insert_page_failed:
-		__free_page(page->page_ptr);
-		page->page_ptr = NULL;
-err_alloc_page_failed:
-err_page_ptr_cleared:
-		if (page_addr == start)
-			break;
-	}
-err_no_vma:
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput(mm);
+		if (page) {
+			trace_binder_alloc_lru_start(alloc, index);
+
+			on_lru = list_lru_del(alloc->freelist,
+					      page_to_lru(page),
+					      page_to_nid(page),
+					      NULL);
+			WARN_ON(!on_lru);
+
+			trace_binder_alloc_lru_end(alloc, index);
+			continue;
+		}
+
+		if (index + 1 > alloc->pages_high)
+			alloc->pages_high = index + 1;
 	}
-	return vma ? -ENOMEM : -ESRCH;
 }
 
-static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
-		struct vm_area_struct *vma)
+static void debug_no_space_locked(struct binder_alloc *alloc)
 {
-	/* pairs with smp_load_acquire in binder_alloc_get_vma() */
-	smp_store_release(&alloc->vma, vma);
-}
+	size_t largest_alloc_size = 0;
+	struct binder_buffer *buffer;
+	size_t allocated_buffers = 0;
+	size_t largest_free_size = 0;
+	size_t total_alloc_size = 0;
+	size_t total_free_size = 0;
+	size_t free_buffers = 0;
+	size_t buffer_size;
+	struct rb_node *n;
 
-static inline struct vm_area_struct *binder_alloc_get_vma(
-		struct binder_alloc *alloc)
-{
-	/* pairs with smp_store_release in binder_alloc_set_vma() */
-	return smp_load_acquire(&alloc->vma);
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		allocated_buffers++;
+		total_alloc_size += buffer_size;
+		if (buffer_size > largest_alloc_size)
+			largest_alloc_size = buffer_size;
+	}
+
+	for (n = rb_first(&alloc->free_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		free_buffers++;
+		total_free_size += buffer_size;
+		if (buffer_size > largest_free_size)
+			largest_free_size = buffer_size;
+	}
+
+	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+			   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
+			   total_alloc_size, allocated_buffers,
+			   largest_alloc_size, total_free_size,
+			   free_buffers, largest_free_size);
 }
 
-static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
+static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 {
 	/*
 	 * Find the amount and size of buffers allocated by the current caller;
@@ -332,10 +468,20 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 	 * and at some point we'll catch them in the act. This is more efficient
 	 * than keeping a map per pid.
 	 */
-	struct rb_node *n;
 	struct binder_buffer *buffer;
 	size_t total_alloc_size = 0;
+	int pid = current->tgid;
 	size_t num_buffers = 0;
+	struct rb_node *n;
+
+	/*
+	 * Only start detecting spammers once we have less than 20% of async
+	 * space left (which is less than 10% of total buffer size).
+	 */
+	if (alloc->free_async_space >= alloc->buffer_size / 10) {
+		alloc->oneway_spam_detected = false;
+		return false;
+	}
 
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL;
 		 n = rb_next(n)) {
@@ -344,8 +490,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 			continue;
 		if (!buffer->async_transaction)
 			continue;
-		total_alloc_size += binder_alloc_buffer_size(alloc, buffer)
-			+ sizeof(struct binder_buffer);
+		total_alloc_size += binder_alloc_buffer_size(alloc, buffer);
 		num_buffers++;
 	}
 
@@ -366,58 +511,28 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 	return false;
 }
 
+/* Callers preallocate @new_buffer, it is freed by this function if unused */
 static struct binder_buffer *binder_alloc_new_buf_locked(
 				struct binder_alloc *alloc,
-				size_t data_size,
-				size_t offsets_size,
-				size_t extra_buffers_size,
-				int is_async,
-				int pid)
+				struct binder_buffer *new_buffer,
+				size_t size,
+				int is_async)
 {
 	struct rb_node *n = alloc->free_buffers.rb_node;
+	struct rb_node *best_fit = NULL;
 	struct binder_buffer *buffer;
+	unsigned long next_used_page;
+	unsigned long curr_last_page;
 	size_t buffer_size;
-	struct rb_node *best_fit = NULL;
-	void __user *has_page_addr;
-	void __user *end_page_addr;
-	size_t size, data_offsets_size;
-	int ret;
-
-	/* Check binder_alloc is fully initialized */
-	if (!binder_alloc_get_vma(alloc)) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf, no vma\n",
-				   alloc->pid);
-		return ERR_PTR(-ESRCH);
-	}
 
-	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
-		ALIGN(offsets_size, sizeof(void *));
-
-	if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid size %zd-%zd\n",
-				alloc->pid, data_size, offsets_size);
-		return ERR_PTR(-EINVAL);
-	}
-	size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
-	if (size < data_offsets_size || size < extra_buffers_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid extra_buffers_size %zd\n",
-				alloc->pid, extra_buffers_size);
-		return ERR_PTR(-EINVAL);
-	}
-	if (is_async &&
-	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
+	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
 			      alloc->pid, size);
-		return ERR_PTR(-ENOSPC);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
 
-	/* Pad 0-size buffers so they get assigned unique addresses */
-	size = max(size, sizeof(void *));
-
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(!buffer->free);
@@ -426,121 +541,92 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		if (size < buffer_size) {
 			best_fit = n;
 			n = n->rb_left;
-		} else if (size > buffer_size)
+		} else if (size > buffer_size) {
 			n = n->rb_right;
-		else {
+		} else {
 			best_fit = n;
 			break;
 		}
 	}
-	if (best_fit == NULL) {
-		size_t allocated_buffers = 0;
-		size_t largest_alloc_size = 0;
-		size_t total_alloc_size = 0;
-		size_t free_buffers = 0;
-		size_t largest_free_size = 0;
-		size_t total_free_size = 0;
-
-		for (n = rb_first(&alloc->allocated_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			allocated_buffers++;
-			total_alloc_size += buffer_size;
-			if (buffer_size > largest_alloc_size)
-				largest_alloc_size = buffer_size;
-		}
-		for (n = rb_first(&alloc->free_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			free_buffers++;
-			total_free_size += buffer_size;
-			if (buffer_size > largest_free_size)
-				largest_free_size = buffer_size;
-		}
+
+	if (unlikely(!best_fit)) {
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf size %zd failed, no address space\n",
 				   alloc->pid, size);
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
-				   total_alloc_size, allocated_buffers,
-				   largest_alloc_size, total_free_size,
-				   free_buffers, largest_free_size);
-		return ERR_PTR(-ENOSPC);
+		debug_no_space_locked(alloc);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
-	if (n == NULL) {
+
+	if (buffer_size != size) {
+		/* Found an oversized buffer and needs to be split */
 		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
 		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+		WARN_ON(n || buffer_size == size);
+		new_buffer->user_data = buffer->user_data + size;
+		list_add(&new_buffer->entry, &buffer->entry);
+		new_buffer->free = 1;
+		binder_insert_free_buffer(alloc, new_buffer);
+		new_buffer = NULL;
 	}
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	has_page_addr = (void __user *)
-		(((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK);
-	WARN_ON(n && buffer_size != size);
-	end_page_addr =
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
-	if (end_page_addr > has_page_addr)
-		end_page_addr = has_page_addr;
-	ret = binder_update_page_range(alloc, 1, (void __user *)
-		PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (buffer_size != size) {
-		struct binder_buffer *new_buffer;
-
-		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
-		if (!new_buffer) {
-			pr_err("%s: %d failed to alloc new buffer struct\n",
-			       __func__, alloc->pid);
-			goto err_alloc_buf_struct_failed;
-		}
-		new_buffer->user_data = (u8 __user *)buffer->user_data + size;
-		list_add(&new_buffer->entry, &buffer->entry);
-		new_buffer->free = 1;
-		binder_insert_free_buffer(alloc, new_buffer);
-	}
+	/*
+	 * Now we remove the pages from the freelist. A clever calculation
+	 * with buffer_size determines if the last page is shared with an
+	 * adjacent in-use buffer. In such case, the page has been already
+	 * removed from the freelist so we trim our range short.
+	 */
+	next_used_page = (buffer->user_data + buffer_size) & PAGE_MASK;
+	curr_last_page = PAGE_ALIGN(buffer->user_data + size);
+	binder_lru_freelist_del(alloc, PAGE_ALIGN(buffer->user_data),
+				min(next_used_page, curr_last_page));
 
-	rb_erase(best_fit, &alloc->free_buffers);
+	rb_erase(&buffer->rb_node, &alloc->free_buffers);
 	buffer->free = 0;
 	buffer->allow_user_free = 0;
 	binder_insert_allocated_buffer_locked(alloc, buffer);
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_alloc_buf size %zd got %pK\n",
-		      alloc->pid, size, buffer);
-	buffer->data_size = data_size;
-	buffer->offsets_size = offsets_size;
 	buffer->async_transaction = is_async;
-	buffer->extra_buffers_size = extra_buffers_size;
-	buffer->pid = pid;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
-		alloc->free_async_space -= size + sizeof(struct binder_buffer);
+		alloc->free_async_space -= size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_alloc_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
-		if (alloc->free_async_space < alloc->buffer_size / 10) {
-			/*
-			 * Start detecting spammers once we have less than 20%
-			 * of async space left (which is less than 10% of total
-			 * buffer size).
-			 */
-			buffer->oneway_spam_suspect = debug_low_async_space_locked(alloc, pid);
-		} else {
-			alloc->oneway_spam_detected = false;
-		}
+		if (debug_low_async_space_locked(alloc))
+			buffer->oneway_spam_suspect = true;
 	}
+
+out:
+	/* Discard possibly unused new_buffer */
+	kfree(new_buffer);
 	return buffer;
+}
 
-err_alloc_buf_struct_failed:
-	binder_update_page_range(alloc, 0, (void __user *)
-				 PAGE_ALIGN((uintptr_t)buffer->user_data),
-				 end_page_addr);
-	return ERR_PTR(-ENOMEM);
+/* Calculate the sanitized total size, returns 0 for invalid request */
+static inline size_t sanitized_size(size_t data_size,
+				    size_t offsets_size,
+				    size_t extra_buffers_size)
+{
+	size_t total, tmp;
+
+	/* Align to pointer size and check for overflows */
+	tmp = ALIGN(data_size, sizeof(void *)) +
+		ALIGN(offsets_size, sizeof(void *));
+	if (tmp < data_size || tmp < offsets_size)
+		return 0;
+	total = tmp + ALIGN(extra_buffers_size, sizeof(void *));
+	if (total < tmp || total < extra_buffers_size)
+		return 0;
+
+	/* Pad 0-sized buffers so they get a unique address */
+	total = max(total, sizeof(void *));
+
+	return total;
 }
 
 /**
@@ -550,87 +636,102 @@ err_alloc_buf_struct_failed:
  * @offsets_size:       user specified buffer offset
  * @extra_buffers_size: size of extra space for meta-data (eg, security context)
  * @is_async:           buffer for async transaction
- * @pid:				pid to attribute allocation to (used for debugging)
  *
  * Allocate a new buffer given the requested sizes. Returns
  * the kernel version of the buffer pointer. The size allocated
  * is the sum of the three given sizes (each rounded up to
  * pointer-sized boundary)
  *
- * Return:	The allocated buffer or %NULL if error
+ * Return:	The allocated buffer or %ERR_PTR(-errno) if error
  */
 struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t data_size,
 					   size_t offsets_size,
 					   size_t extra_buffers_size,
-					   int is_async,
-					   int pid)
+					   int is_async)
 {
-	struct binder_buffer *buffer;
+	struct binder_buffer *buffer, *next;
+	size_t size;
+	int ret;
+
+	/* Check binder_alloc is fully initialized */
+	if (!binder_alloc_is_mapped(alloc)) {
+		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+				   "%d: binder_alloc_buf, no vma\n",
+				   alloc->pid);
+		return ERR_PTR(-ESRCH);
+	}
+
+	size = sanitized_size(data_size, offsets_size, extra_buffers_size);
+	if (unlikely(!size)) {
+		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				   "%d: got transaction with invalid size %zd-%zd-%zd\n",
+				   alloc->pid, data_size, offsets_size,
+				   extra_buffers_size);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Preallocate the next buffer */
+	next = kzalloc(sizeof(*next), GFP_KERNEL);
+	if (!next)
+		return ERR_PTR(-ENOMEM);
 
 	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
-					     extra_buffers_size, is_async, pid);
+	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
+	if (IS_ERR(buffer)) {
+		mutex_unlock(&alloc->mutex);
+		goto out;
+	}
+
+	buffer->data_size = data_size;
+	buffer->offsets_size = offsets_size;
+	buffer->extra_buffers_size = extra_buffers_size;
+	buffer->pid = current->tgid;
 	mutex_unlock(&alloc->mutex);
+
+	ret = binder_install_buffer_pages(alloc, buffer, size);
+	if (ret) {
+		binder_alloc_free_buf(alloc, buffer);
+		buffer = ERR_PTR(ret);
+	}
+out:
 	return buffer;
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_new_buf);
 
-static void __user *buffer_start_page(struct binder_buffer *buffer)
+static unsigned long buffer_start_page(struct binder_buffer *buffer)
 {
-	return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK);
+	return buffer->user_data & PAGE_MASK;
 }
 
-static void __user *prev_buffer_end_page(struct binder_buffer *buffer)
+static unsigned long prev_buffer_end_page(struct binder_buffer *buffer)
 {
-	return (void __user *)
-		(((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK);
+	return (buffer->user_data - 1) & PAGE_MASK;
 }
 
 static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				      struct binder_buffer *buffer)
 {
-	struct binder_buffer *prev, *next = NULL;
-	bool to_free = true;
+	struct binder_buffer *prev, *next;
+
+	if (PAGE_ALIGNED(buffer->user_data))
+		goto skip_freelist;
 
 	BUG_ON(alloc->buffers.next == &buffer->entry);
 	prev = binder_buffer_prev(buffer);
 	BUG_ON(!prev->free);
-	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
-		to_free = false;
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK share page with %pK\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data);
-	}
+	if (prev_buffer_end_page(prev) == buffer_start_page(buffer))
+		goto skip_freelist;
 
 	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
 		next = binder_buffer_next(buffer);
-		if (buffer_start_page(next) == buffer_start_page(buffer)) {
-			to_free = false;
-			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-					   "%d: merge free, buffer %pK share page with %pK\n",
-					   alloc->pid,
-					   buffer->user_data,
-					   next->user_data);
-		}
-	}
-
-	if (PAGE_ALIGNED(buffer->user_data)) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer start %pK is page aligned\n",
-				   alloc->pid, buffer->user_data);
-		to_free = false;
+		if (buffer_start_page(next) == buffer_start_page(buffer))
+			goto skip_freelist;
 	}
 
-	if (to_free) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data,
-				   next ? next->user_data : NULL);
-		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
-					 buffer_start_page(buffer) + PAGE_SIZE);
-	}
+	binder_lru_freelist_add(alloc, buffer_start_page(buffer),
+				buffer_start_page(buffer) + PAGE_SIZE);
+skip_freelist:
 	list_del(&buffer->entry);
 	kfree(buffer);
 }
@@ -653,21 +754,18 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->free);
 	BUG_ON(size > buffer_size);
 	BUG_ON(buffer->transaction != NULL);
-	BUG_ON(buffer->user_data < alloc->buffer);
-	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
+	BUG_ON(buffer->user_data < alloc->vm_start);
+	BUG_ON(buffer->user_data > alloc->vm_start + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
-		alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
-
+		alloc->free_async_space += buffer_size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_free_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
 	}
 
-	binder_update_page_range(alloc, 0,
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data),
-		(void __user *)(((uintptr_t)
-			  buffer->user_data + buffer_size) & PAGE_MASK));
+	binder_lru_freelist_add(alloc, PAGE_ALIGN(buffer->user_data),
+				(buffer->user_data + buffer_size) & PAGE_MASK);
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
@@ -691,8 +789,67 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	binder_insert_free_buffer(alloc, buffer);
 }
 
+/**
+ * binder_alloc_get_page() - get kernel pointer for given buffer offset
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @buffer_offset: offset into @buffer data
+ * @pgoffp: address to copy final page offset to
+ *
+ * Lookup the struct page corresponding to the address
+ * at @buffer_offset into @buffer->user_data. If @pgoffp is not
+ * NULL, the byte-offset into the page is written there.
+ *
+ * The caller is responsible to ensure that the offset points
+ * to a valid address within the @buffer and that @buffer is
+ * not freeable by the user. Since it can't be freed, we are
+ * guaranteed that the corresponding elements of @alloc->pages[]
+ * cannot change.
+ *
+ * Return: struct page
+ */
+static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
+					  struct binder_buffer *buffer,
+					  binder_size_t buffer_offset,
+					  pgoff_t *pgoffp)
+{
+	binder_size_t buffer_space_offset = buffer_offset +
+		(buffer->user_data - alloc->vm_start);
+	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
+	size_t index = buffer_space_offset >> PAGE_SHIFT;
+
+	*pgoffp = pgoff;
+
+	return alloc->pages[index];
+}
+
+/**
+ * binder_alloc_clear_buf() - zero out buffer
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be cleared
+ *
+ * memset the given buffer to 0
+ */
 static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer);
+				   struct binder_buffer *buffer)
+{
+	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
+	binder_size_t buffer_offset = 0;
+
+	while (bytes) {
+		unsigned long size;
+		struct page *page;
+		pgoff_t pgoff;
+
+		page = binder_alloc_get_page(alloc, buffer,
+					     buffer_offset, &pgoff);
+		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
+		memset_page(page, pgoff, 0, size);
+		bytes -= size;
+		buffer_offset += size;
+	}
+}
+
 /**
  * binder_alloc_free_buf() - free a binder buffer
  * @alloc:	binder_alloc for this proc
@@ -706,7 +863,7 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	/*
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
-	 * binder_alloc_free_buf_locked(). However, that could
+	 * binder_free_buf_locked(). However, that could
 	 * increase contention for the alloc mutex if clear_on_free
 	 * is used frequently for large buffers. The mutex is not
 	 * needed for correctness here.
@@ -719,6 +876,7 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	binder_free_buf_locked(alloc, buffer);
 	mutex_unlock(&alloc->mutex);
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_free_buf);
 
 /**
  * binder_alloc_mmap_handler() - map virtual address space for proc
@@ -736,9 +894,9 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 			      struct vm_area_struct *vma)
 {
-	int ret;
-	const char *failure_string;
 	struct binder_buffer *buffer;
+	const char *failure_string;
+	int ret;
 
 	if (unlikely(vma->vm_mm != alloc->mm)) {
 		ret = -EINVAL;
@@ -756,12 +914,12 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 				   SZ_4M);
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->buffer = (void __user *)vma->vm_start;
+	alloc->vm_start = vma->vm_start;
 
-	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
-			       sizeof(alloc->pages[0]),
-			       GFP_KERNEL);
-	if (alloc->pages == NULL) {
+	alloc->pages = kvcalloc(alloc->buffer_size / PAGE_SIZE,
+				sizeof(alloc->pages[0]),
+				GFP_KERNEL);
+	if (!alloc->pages) {
 		ret = -ENOMEM;
 		failure_string = "alloc page array";
 		goto err_alloc_pages_failed;
@@ -774,22 +932,22 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		goto err_alloc_buf_struct_failed;
 	}
 
-	buffer->user_data = alloc->buffer;
+	buffer->user_data = alloc->vm_start;
 	list_add(&buffer->entry, &alloc->buffers);
 	buffer->free = 1;
 	binder_insert_free_buffer(alloc, buffer);
 	alloc->free_async_space = alloc->buffer_size / 2;
 
 	/* Signal binder_alloc is fully initialized */
-	binder_alloc_set_vma(alloc, vma);
+	binder_alloc_set_mapped(alloc, true);
 
 	return 0;
 
 err_alloc_buf_struct_failed:
-	kfree(alloc->pages);
+	kvfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
-	alloc->buffer = NULL;
+	alloc->vm_start = 0;
 	mutex_lock(&binder_alloc_mmap_lock);
 	alloc->buffer_size = 0;
 err_already_mapped:
@@ -801,7 +959,7 @@ err_invalid_mm:
 			   failure_string, ret);
 	return ret;
 }
-
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_mmap_handler);
 
 void binder_alloc_deferred_release(struct binder_alloc *alloc)
 {
@@ -811,7 +969,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 
 	buffers = 0;
 	mutex_lock(&alloc->mutex);
-	BUG_ON(alloc->vma);
+	BUG_ON(alloc->mapped);
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
@@ -842,25 +1000,27 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		int i;
 
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			void __user *page_addr;
+			struct page *page;
 			bool on_lru;
 
-			if (!alloc->pages[i].page_ptr)
+			page = binder_get_installed_page(alloc, i);
+			if (!page)
 				continue;
 
-			on_lru = list_lru_del(&binder_alloc_lru,
-					      &alloc->pages[i].lru);
-			page_addr = alloc->buffer + i * PAGE_SIZE;
+			on_lru = list_lru_del(alloc->freelist,
+					      page_to_lru(page),
+					      page_to_nid(page),
+					      NULL);
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %pK %s\n",
-				     __func__, alloc->pid, i, page_addr,
+				     "%s: %d: page %d %s\n",
+				     __func__, alloc->pid, i,
 				     on_lru ? "on lru" : "active");
-			__free_page(alloc->pages[i].page_ptr);
+			binder_free_page(page);
 			page_count++;
 		}
-		kfree(alloc->pages);
 	}
 	mutex_unlock(&alloc->mutex);
+	kvfree(alloc->pages);
 	if (alloc->mm)
 		mmdrop(alloc->mm);
 
@@ -868,16 +1028,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		     "%s: %d buffers %d, pages %d\n",
 		     __func__, alloc->pid, buffers, page_count);
 }
-
-static void print_binder_buffer(struct seq_file *m, const char *prefix,
-				struct binder_buffer *buffer)
-{
-	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
-		   prefix, buffer->debug_id, buffer->user_data,
-		   buffer->data_size, buffer->offsets_size,
-		   buffer->extra_buffers_size,
-		   buffer->transaction ? "active" : "delivered");
-}
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_deferred_release);
 
 /**
  * binder_alloc_print_allocated() - print buffer info
@@ -890,13 +1041,19 @@ static void print_binder_buffer(struct seq_file *m, const char *prefix,
 void binder_alloc_print_allocated(struct seq_file *m,
 				  struct binder_alloc *alloc)
 {
+	struct binder_buffer *buffer;
 	struct rb_node *n;
 
-	mutex_lock(&alloc->mutex);
-	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
-		print_binder_buffer(m, "  buffer",
-				    rb_entry(n, struct binder_buffer, rb_node));
-	mutex_unlock(&alloc->mutex);
+	guard(mutex)(&alloc->mutex);
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
+			   buffer->debug_id,
+			   buffer->user_data - alloc->vm_start,
+			   buffer->data_size, buffer->offsets_size,
+			   buffer->extra_buffers_size,
+			   buffer->transaction ? "active" : "delivered");
+	}
 }
 
 /**
@@ -907,7 +1064,7 @@ void binder_alloc_print_allocated(struct seq_file *m,
 void binder_alloc_print_pages(struct seq_file *m,
 			      struct binder_alloc *alloc)
 {
-	struct binder_lru_page *page;
+	struct page *page;
 	int i;
 	int active = 0;
 	int lru = 0;
@@ -918,12 +1075,12 @@ void binder_alloc_print_pages(struct seq_file *m,
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
+	if (binder_alloc_is_mapped(alloc)) {
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			page = &alloc->pages[i];
-			if (!page->page_ptr)
+			page = binder_get_installed_page(alloc, i);
+			if (!page)
 				free++;
-			else if (list_empty(&page->lru))
+			else if (list_empty(page_to_lru(page)))
 				active++;
 			else
 				lru++;
@@ -945,10 +1102,9 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 	struct rb_node *n;
 	int count = 0;
 
-	mutex_lock(&alloc->mutex);
+	guard(mutex)(&alloc->mutex);
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
 		count++;
-	mutex_unlock(&alloc->mutex);
 	return count;
 }
 
@@ -958,18 +1114,19 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
  * @alloc: binder_alloc for this proc
  *
  * Called from binder_vma_close() when releasing address space.
- * Clears alloc->vma to prevent new incoming transactions from
+ * Clears alloc->mapped to prevent new incoming transactions from
  * allocating more buffers.
  */
 void binder_alloc_vma_close(struct binder_alloc *alloc)
 {
-	binder_alloc_set_vma(alloc, NULL);
+	binder_alloc_set_mapped(alloc, false);
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_vma_close);
 
 /**
  * binder_alloc_free_page() - shrinker callback to free pages
  * @item:   item to free
- * @lock:   lock protecting the item
+ * @lru:    list_lru instance of the item
  * @cb_arg: callback argument
  *
  * Called from list_lru_walk() in binder_shrink_scan() to free
@@ -977,38 +1134,54 @@ void binder_alloc_vma_close(struct binder_alloc *alloc)
  */
 enum lru_status binder_alloc_free_page(struct list_head *item,
 				       struct list_lru_one *lru,
-				       spinlock_t *lock,
 				       void *cb_arg)
-	__must_hold(lock)
+	__must_hold(&lru->lock)
 {
-	struct mm_struct *mm = NULL;
-	struct binder_lru_page *page = container_of(item,
-						    struct binder_lru_page,
-						    lru);
-	struct binder_alloc *alloc;
-	uintptr_t page_addr;
-	size_t index;
+	struct binder_shrinker_mdata *mdata = container_of(item, typeof(*mdata), lru);
+	struct binder_alloc *alloc = mdata->alloc;
+	struct mm_struct *mm = alloc->mm;
 	struct vm_area_struct *vma;
+	struct page *page_to_free;
+	unsigned long page_addr;
+	int mm_locked = 0;
+	size_t index;
+
+	if (!mmget_not_zero(mm))
+		goto err_mmget;
+
+	index = mdata->page_index;
+	page_addr = alloc->vm_start + index * PAGE_SIZE;
+
+	/* attempt per-vma lock first */
+	vma = lock_vma_under_rcu(mm, page_addr);
+	if (!vma) {
+		/* fall back to mmap_lock */
+		if (!mmap_read_trylock(mm))
+			goto err_mmap_read_lock_failed;
+		mm_locked = 1;
+		vma = vma_lookup(mm, page_addr);
+	}
 
-	alloc = page->alloc;
 	if (!mutex_trylock(&alloc->mutex))
 		goto err_get_alloc_mutex_failed;
 
-	if (!page->page_ptr)
-		goto err_page_already_freed;
+	/*
+	 * Since a binder_alloc can only be mapped once, we ensure
+	 * the vma corresponds to this mapping by checking whether
+	 * the binder_alloc is still mapped.
+	 */
+	if (vma && !binder_alloc_is_mapped(alloc))
+		goto err_invalid_vma;
 
-	index = page - alloc->pages;
-	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+	trace_binder_unmap_kernel_start(alloc, index);
 
-	mm = alloc->mm;
-	if (!mmget_not_zero(mm))
-		goto err_mmget;
-	if (!mmap_read_trylock(mm))
-		goto err_mmap_read_lock_failed;
-	vma = binder_alloc_get_vma(alloc);
+	page_to_free = alloc->pages[index];
+	binder_set_installed_page(alloc, index, NULL);
+
+	trace_binder_unmap_kernel_end(alloc, index);
 
 	list_lru_isolate(lru, item);
-	spin_unlock(lock);
+	spin_unlock(&lru->lock);
 
 	if (vma) {
 		trace_binder_unmap_user_start(alloc, index);
@@ -1017,44 +1190,58 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 		trace_binder_unmap_user_end(alloc, index);
 	}
-	mmap_read_unlock(mm);
-	mmput_async(mm);
-
-	trace_binder_unmap_kernel_start(alloc, index);
-
-	__free_page(page->page_ptr);
-	page->page_ptr = NULL;
-
-	trace_binder_unmap_kernel_end(alloc, index);
 
-	spin_lock(lock);
 	mutex_unlock(&alloc->mutex);
+	if (mm_locked)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
+	mmput_async(mm);
+	binder_free_page(page_to_free);
+
 	return LRU_REMOVED_RETRY;
 
+err_invalid_vma:
+	mutex_unlock(&alloc->mutex);
+err_get_alloc_mutex_failed:
+	if (mm_locked)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
-err_page_already_freed:
-	mutex_unlock(&alloc->mutex);
-err_get_alloc_mutex_failed:
 	return LRU_SKIP;
 }
+EXPORT_SYMBOL_IF_KUNIT(binder_alloc_free_page);
 
 static unsigned long
 binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_count(&binder_alloc_lru);
+	return list_lru_count(&binder_freelist);
 }
 
 static unsigned long
 binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+	return list_lru_walk(&binder_freelist, binder_alloc_free_page,
 			    NULL, sc->nr_to_scan);
 }
 
 static struct shrinker *binder_shrinker;
 
+VISIBLE_IF_KUNIT void __binder_alloc_init(struct binder_alloc *alloc,
+					  struct list_lru *freelist)
+{
+	alloc->pid = current->group_leader->pid;
+	alloc->mm = current->mm;
+	mmgrab(alloc->mm);
+	mutex_init(&alloc->mutex);
+	INIT_LIST_HEAD(&alloc->buffers);
+	alloc->freelist = freelist;
+}
+EXPORT_SYMBOL_IF_KUNIT(__binder_alloc_init);
+
 /**
  * binder_alloc_init() - called by binder_open() for per-proc initialization
  * @alloc: binder_alloc for this proc
@@ -1064,24 +1251,20 @@ static struct shrinker *binder_shrinker;
  */
 void binder_alloc_init(struct binder_alloc *alloc)
 {
-	alloc->pid = current->group_leader->pid;
-	alloc->mm = current->mm;
-	mmgrab(alloc->mm);
-	mutex_init(&alloc->mutex);
-	INIT_LIST_HEAD(&alloc->buffers);
+	__binder_alloc_init(alloc, &binder_freelist);
 }
 
 int binder_alloc_shrinker_init(void)
 {
 	int ret;
 
-	ret = list_lru_init(&binder_alloc_lru);
+	ret = list_lru_init(&binder_freelist);
 	if (ret)
 		return ret;
 
 	binder_shrinker = shrinker_alloc(0, "android-binder");
 	if (!binder_shrinker) {
-		list_lru_destroy(&binder_alloc_lru);
+		list_lru_destroy(&binder_freelist);
 		return -ENOMEM;
 	}
 
@@ -1096,7 +1279,7 @@ int binder_alloc_shrinker_init(void)
 void binder_alloc_shrinker_exit(void)
 {
 	shrinker_free(binder_shrinker);
-	list_lru_destroy(&binder_alloc_lru);
+	list_lru_destroy(&binder_freelist);
 }
 
 /**
@@ -1132,68 +1315,6 @@ static inline bool check_buffer(struct binder_alloc *alloc,
 }
 
 /**
- * binder_alloc_get_page() - get kernel pointer for given buffer offset
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be accessed
- * @buffer_offset: offset into @buffer data
- * @pgoffp: address to copy final page offset to
- *
- * Lookup the struct page corresponding to the address
- * at @buffer_offset into @buffer->user_data. If @pgoffp is not
- * NULL, the byte-offset into the page is written there.
- *
- * The caller is responsible to ensure that the offset points
- * to a valid address within the @buffer and that @buffer is
- * not freeable by the user. Since it can't be freed, we are
- * guaranteed that the corresponding elements of @alloc->pages[]
- * cannot change.
- *
- * Return: struct page
- */
-static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
-					  struct binder_buffer *buffer,
-					  binder_size_t buffer_offset,
-					  pgoff_t *pgoffp)
-{
-	binder_size_t buffer_space_offset = buffer_offset +
-		(buffer->user_data - alloc->buffer);
-	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
-	size_t index = buffer_space_offset >> PAGE_SHIFT;
-	struct binder_lru_page *lru_page;
-
-	lru_page = &alloc->pages[index];
-	*pgoffp = pgoff;
-	return lru_page->page_ptr;
-}
-
-/**
- * binder_alloc_clear_buf() - zero out buffer
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be cleared
- *
- * memset the given buffer to 0
- */
-static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer)
-{
-	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
-	binder_size_t buffer_offset = 0;
-
-	while (bytes) {
-		unsigned long size;
-		struct page *page;
-		pgoff_t pgoff;
-
-		page = binder_alloc_get_page(alloc, buffer,
-					     buffer_offset, &pgoff);
-		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
-		memset_page(page, pgoff, 0, size);
-		bytes -= size;
-		buffer_offset += size;
-	}
-}
-
-/**
  * binder_alloc_copy_user_to_buffer() - copy src user to tgt user
  * @alloc: binder_alloc for this proc
  * @buffer: binder buffer to be accessed
@@ -1287,4 +1408,3 @@ int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
 	return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
 					   dest, bytes);
 }
-
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index dc1e2b01dd64..d6f1f6f2d00e 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -15,7 +15,6 @@
 #include <linux/list_lru.h>
 #include <uapi/linux/android/binder.h>
 
-extern struct list_lru binder_alloc_lru;
 struct binder_transaction;
 
 /**
@@ -49,46 +48,54 @@ struct binder_buffer {
 	unsigned async_transaction:1;
 	unsigned oneway_spam_suspect:1;
 	unsigned debug_id:27;
-
 	struct binder_transaction *transaction;
-
 	struct binder_node *target_node;
 	size_t data_size;
 	size_t offsets_size;
 	size_t extra_buffers_size;
-	void __user *user_data;
-	int    pid;
+	unsigned long user_data;
+	int pid;
 };
 
 /**
- * struct binder_lru_page - page object used for binder shrinker
- * @page_ptr: pointer to physical page in mmap'd space
- * @lru:      entry in binder_alloc_lru
- * @alloc:    binder_alloc for a proc
+ * struct binder_shrinker_mdata - binder metadata used to reclaim pages
+ * @lru:         LRU entry in binder_freelist
+ * @alloc:       binder_alloc owning the page to reclaim
+ * @page_index:  offset in @alloc->pages[] into the page to reclaim
  */
-struct binder_lru_page {
+struct binder_shrinker_mdata {
 	struct list_head lru;
-	struct page *page_ptr;
 	struct binder_alloc *alloc;
+	unsigned long page_index;
 };
 
+static inline struct list_head *page_to_lru(struct page *p)
+{
+	struct binder_shrinker_mdata *mdata;
+
+	mdata = (struct binder_shrinker_mdata *)page_private(p);
+
+	return &mdata->lru;
+}
+
 /**
  * struct binder_alloc - per-binder proc state for binder allocator
  * @mutex:              protects binder_alloc fields
- * @vma:                vm_area_struct passed to mmap_handler
- *                      (invariant after mmap)
  * @mm:                 copy of task->mm (invariant after open)
- * @buffer:             base of per-proc address space mapped via mmap
+ * @vm_start:           base of per-proc address space mapped via mmap
  * @buffers:            list of all buffers for this proc
  * @free_buffers:       rb tree of buffers available for allocation
  *                      sorted by size
  * @allocated_buffers:  rb tree of allocated buffers sorted by address
  * @free_async_space:   VA space available for async buffers. This is
  *                      initialized at mmap time to 1/2 the full VA space
- * @pages:              array of binder_lru_page
+ * @pages:              array of struct page *
+ * @freelist:           lru list to use for free pages (invariant after init)
  * @buffer_size:        size of address space specified via mmap
  * @pid:                pid for associated binder_proc (invariant after init)
  * @pages_high:         high watermark of offset in @pages
+ * @mapped:             whether the vm area is mapped, each binder instance is
+ *                      allowed a single mapping throughout its lifetime
  * @oneway_spam_detected: %true if oneway spam detection fired, clear that
  * flag once the async buffer has returned to a healthy state
  *
@@ -99,49 +106,44 @@ struct binder_lru_page {
  */
 struct binder_alloc {
 	struct mutex mutex;
-	struct vm_area_struct *vma;
 	struct mm_struct *mm;
-	void __user *buffer;
+	unsigned long vm_start;
 	struct list_head buffers;
 	struct rb_root free_buffers;
 	struct rb_root allocated_buffers;
 	size_t free_async_space;
-	struct binder_lru_page *pages;
+	struct page **pages;
+	struct list_lru *freelist;
 	size_t buffer_size;
 	int pid;
 	size_t pages_high;
+	bool mapped;
 	bool oneway_spam_detected;
 };
 
-#ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST
-void binder_selftest_alloc(struct binder_alloc *alloc);
-#else
-static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
-#endif
 enum lru_status binder_alloc_free_page(struct list_head *item,
 				       struct list_lru_one *lru,
-				       spinlock_t *lock, void *cb_arg);
-extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
-						  size_t data_size,
-						  size_t offsets_size,
-						  size_t extra_buffers_size,
-						  int is_async,
-						  int pid);
-extern void binder_alloc_init(struct binder_alloc *alloc);
-extern int binder_alloc_shrinker_init(void);
-extern void binder_alloc_shrinker_exit(void);
-extern void binder_alloc_vma_close(struct binder_alloc *alloc);
-extern struct binder_buffer *
+				       void *cb_arg);
+struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
+					   size_t data_size,
+					   size_t offsets_size,
+					   size_t extra_buffers_size,
+					   int is_async);
+void binder_alloc_init(struct binder_alloc *alloc);
+int binder_alloc_shrinker_init(void);
+void binder_alloc_shrinker_exit(void);
+void binder_alloc_vma_close(struct binder_alloc *alloc);
+struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-			     uintptr_t user_ptr);
-extern void binder_alloc_free_buf(struct binder_alloc *alloc,
-				  struct binder_buffer *buffer);
-extern int binder_alloc_mmap_handler(struct binder_alloc *alloc,
-				     struct vm_area_struct *vma);
-extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
-extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
-extern void binder_alloc_print_allocated(struct seq_file *m,
-					 struct binder_alloc *alloc);
+			     unsigned long user_ptr);
+void binder_alloc_free_buf(struct binder_alloc *alloc,
+			   struct binder_buffer *buffer);
+int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+			      struct vm_area_struct *vma);
+void binder_alloc_deferred_release(struct binder_alloc *alloc);
+int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
+void binder_alloc_print_allocated(struct seq_file *m,
+				  struct binder_alloc *alloc);
 void binder_alloc_print_pages(struct seq_file *m,
 			      struct binder_alloc *alloc);
 
@@ -154,12 +156,8 @@ void binder_alloc_print_pages(struct seq_file *m,
 static inline size_t
 binder_alloc_get_free_async_space(struct binder_alloc *alloc)
 {
-	size_t free_async_space;
-
-	mutex_lock(&alloc->mutex);
-	free_async_space = alloc->free_async_space;
-	mutex_unlock(&alloc->mutex);
-	return free_async_space;
+	guard(mutex)(&alloc->mutex);
+	return alloc->free_async_space;
 }
 
 unsigned long
@@ -181,5 +179,11 @@ int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
 				  binder_size_t buffer_offset,
 				  size_t bytes);
 
+#if IS_ENABLED(CONFIG_KUNIT)
+void __binder_alloc_init(struct binder_alloc *alloc, struct list_lru *freelist);
+size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
+				struct binder_buffer *buffer);
+#endif
+
 #endif /* _LINUX_BINDER_ALLOC_H */
 
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
deleted file mode 100644
index c2b323bc3b3a..000000000000
--- a/drivers/android/binder_alloc_selftest.c
+++ /dev/null
@@ -1,302 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* binder_alloc_selftest.c
- *
- * Android IPC Subsystem
- *
- * Copyright (C) 2017 Google, Inc.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/mm_types.h>
-#include <linux/err.h>
-#include "binder_alloc.h"
-
-#define BUFFER_NUM 5
-#define BUFFER_MIN_SIZE (PAGE_SIZE / 8)
-
-static bool binder_selftest_run = true;
-static int binder_selftest_failures;
-static DEFINE_MUTEX(binder_selftest_lock);
-
-/**
- * enum buf_end_align_type - Page alignment of a buffer
- * end with regard to the end of the previous buffer.
- *
- * In the pictures below, buf2 refers to the buffer we
- * are aligning. buf1 refers to previous buffer by addr.
- * Symbol [ means the start of a buffer, ] means the end
- * of a buffer, and | means page boundaries.
- */
-enum buf_end_align_type {
-	/**
-	 * @SAME_PAGE_UNALIGNED: The end of this buffer is on
-	 * the same page as the end of the previous buffer and
-	 * is not page aligned. Examples:
-	 * buf1 ][ buf2 ][ ...
-	 * buf1 ]|[ buf2 ][ ...
-	 */
-	SAME_PAGE_UNALIGNED = 0,
-	/**
-	 * @SAME_PAGE_ALIGNED: When the end of the previous buffer
-	 * is not page aligned, the end of this buffer is on the
-	 * same page as the end of the previous buffer and is page
-	 * aligned. When the previous buffer is page aligned, the
-	 * end of this buffer is aligned to the next page boundary.
-	 * Examples:
-	 * buf1 ][ buf2 ]| ...
-	 * buf1 ]|[ buf2 ]| ...
-	 */
-	SAME_PAGE_ALIGNED,
-	/**
-	 * @NEXT_PAGE_UNALIGNED: The end of this buffer is on
-	 * the page next to the end of the previous buffer and
-	 * is not page aligned. Examples:
-	 * buf1 ][ buf2 | buf2 ][ ...
-	 * buf1 ]|[ buf2 | buf2 ][ ...
-	 */
-	NEXT_PAGE_UNALIGNED,
-	/**
-	 * @NEXT_PAGE_ALIGNED: The end of this buffer is on
-	 * the page next to the end of the previous buffer and
-	 * is page aligned. Examples:
-	 * buf1 ][ buf2 | buf2 ]| ...
-	 * buf1 ]|[ buf2 | buf2 ]| ...
-	 */
-	NEXT_PAGE_ALIGNED,
-	/**
-	 * @NEXT_NEXT_UNALIGNED: The end of this buffer is on
-	 * the page that follows the page after the end of the
-	 * previous buffer and is not page aligned. Examples:
-	 * buf1 ][ buf2 | buf2 | buf2 ][ ...
-	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
-	 */
-	NEXT_NEXT_UNALIGNED,
-	LOOP_END,
-};
-
-static void pr_err_size_seq(size_t *sizes, int *seq)
-{
-	int i;
-
-	pr_err("alloc sizes: ");
-	for (i = 0; i < BUFFER_NUM; i++)
-		pr_cont("[%zu]", sizes[i]);
-	pr_cont("\n");
-	pr_err("free seq: ");
-	for (i = 0; i < BUFFER_NUM; i++)
-		pr_cont("[%d]", seq[i]);
-	pr_cont("\n");
-}
-
-static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
-					 struct binder_buffer *buffer,
-					 size_t size)
-{
-	void __user *page_addr;
-	void __user *end;
-	int page_index;
-
-	end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
-	page_addr = buffer->user_data;
-	for (; page_addr < end; page_addr += PAGE_SIZE) {
-		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		if (!alloc->pages[page_index].page_ptr ||
-		    !list_empty(&alloc->pages[page_index].lru)) {
-			pr_err("expect alloc but is %s at page index %d\n",
-			       alloc->pages[page_index].page_ptr ?
-			       "lru" : "free", page_index);
-			return false;
-		}
-	}
-	return true;
-}
-
-static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
-				      struct binder_buffer *buffers[],
-				      size_t *sizes, int *seq)
-{
-	int i;
-
-	for (i = 0; i < BUFFER_NUM; i++) {
-		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0, 0);
-		if (IS_ERR(buffers[i]) ||
-		    !check_buffer_pages_allocated(alloc, buffers[i],
-						  sizes[i])) {
-			pr_err_size_seq(sizes, seq);
-			binder_selftest_failures++;
-		}
-	}
-}
-
-static void binder_selftest_free_buf(struct binder_alloc *alloc,
-				     struct binder_buffer *buffers[],
-				     size_t *sizes, int *seq, size_t end)
-{
-	int i;
-
-	for (i = 0; i < BUFFER_NUM; i++)
-		binder_alloc_free_buf(alloc, buffers[seq[i]]);
-
-	for (i = 0; i < end / PAGE_SIZE; i++) {
-		/**
-		 * Error message on a free page can be false positive
-		 * if binder shrinker ran during binder_alloc_free_buf
-		 * calls above.
-		 */
-		if (list_empty(&alloc->pages[i].lru)) {
-			pr_err_size_seq(sizes, seq);
-			pr_err("expect lru but is %s at page index %d\n",
-			       alloc->pages[i].page_ptr ? "alloc" : "free", i);
-			binder_selftest_failures++;
-		}
-	}
-}
-
-static void binder_selftest_free_page(struct binder_alloc *alloc)
-{
-	int i;
-	unsigned long count;
-
-	while ((count = list_lru_count(&binder_alloc_lru))) {
-		list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
-			      NULL, count);
-	}
-
-	for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
-		if (alloc->pages[i].page_ptr) {
-			pr_err("expect free but is %s at page index %d\n",
-			       list_empty(&alloc->pages[i].lru) ?
-			       "alloc" : "lru", i);
-			binder_selftest_failures++;
-		}
-	}
-}
-
-static void binder_selftest_alloc_free(struct binder_alloc *alloc,
-				       size_t *sizes, int *seq, size_t end)
-{
-	struct binder_buffer *buffers[BUFFER_NUM];
-
-	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
-	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
-
-	/* Allocate from lru. */
-	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
-	if (list_lru_count(&binder_alloc_lru))
-		pr_err("lru list should be empty but is not\n");
-
-	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
-	binder_selftest_free_page(alloc);
-}
-
-static bool is_dup(int *seq, int index, int val)
-{
-	int i;
-
-	for (i = 0; i < index; i++) {
-		if (seq[i] == val)
-			return true;
-	}
-	return false;
-}
-
-/* Generate BUFFER_NUM factorial free orders. */
-static void binder_selftest_free_seq(struct binder_alloc *alloc,
-				     size_t *sizes, int *seq,
-				     int index, size_t end)
-{
-	int i;
-
-	if (index == BUFFER_NUM) {
-		binder_selftest_alloc_free(alloc, sizes, seq, end);
-		return;
-	}
-	for (i = 0; i < BUFFER_NUM; i++) {
-		if (is_dup(seq, index, i))
-			continue;
-		seq[index] = i;
-		binder_selftest_free_seq(alloc, sizes, seq, index + 1, end);
-	}
-}
-
-static void binder_selftest_alloc_size(struct binder_alloc *alloc,
-				       size_t *end_offset)
-{
-	int i;
-	int seq[BUFFER_NUM] = {0};
-	size_t front_sizes[BUFFER_NUM];
-	size_t back_sizes[BUFFER_NUM];
-	size_t last_offset, offset = 0;
-
-	for (i = 0; i < BUFFER_NUM; i++) {
-		last_offset = offset;
-		offset = end_offset[i];
-		front_sizes[i] = offset - last_offset;
-		back_sizes[BUFFER_NUM - i - 1] = front_sizes[i];
-	}
-	/*
-	 * Buffers share the first or last few pages.
-	 * Only BUFFER_NUM - 1 buffer sizes are adjustable since
-	 * we need one giant buffer before getting to the last page.
-	 */
-	back_sizes[0] += alloc->buffer_size - end_offset[BUFFER_NUM - 1];
-	binder_selftest_free_seq(alloc, front_sizes, seq, 0,
-				 end_offset[BUFFER_NUM - 1]);
-	binder_selftest_free_seq(alloc, back_sizes, seq, 0, alloc->buffer_size);
-}
-
-static void binder_selftest_alloc_offset(struct binder_alloc *alloc,
-					 size_t *end_offset, int index)
-{
-	int align;
-	size_t end, prev;
-
-	if (index == BUFFER_NUM) {
-		binder_selftest_alloc_size(alloc, end_offset);
-		return;
-	}
-	prev = index == 0 ? 0 : end_offset[index - 1];
-	end = prev;
-
-	BUILD_BUG_ON(BUFFER_MIN_SIZE * BUFFER_NUM >= PAGE_SIZE);
-
-	for (align = SAME_PAGE_UNALIGNED; align < LOOP_END; align++) {
-		if (align % 2)
-			end = ALIGN(end, PAGE_SIZE);
-		else
-			end += BUFFER_MIN_SIZE;
-		end_offset[index] = end;
-		binder_selftest_alloc_offset(alloc, end_offset, index + 1);
-	}
-}
-
-/**
- * binder_selftest_alloc() - Test alloc and free of buffer pages.
- * @alloc: Pointer to alloc struct.
- *
- * Allocate BUFFER_NUM buffers to cover all page alignment cases,
- * then free them in all orders possible. Check that pages are
- * correctly allocated, put onto lru when buffers are freed, and
- * are freed when binder_alloc_free_page is called.
- */
-void binder_selftest_alloc(struct binder_alloc *alloc)
-{
-	size_t end_offset[BUFFER_NUM];
-
-	if (!binder_selftest_run)
-		return;
-	mutex_lock(&binder_selftest_lock);
-	if (!binder_selftest_run || !alloc->vma)
-		goto done;
-	pr_info("STARTED\n");
-	binder_selftest_alloc_offset(alloc, end_offset, 0);
-	binder_selftest_run = false;
-	if (binder_selftest_failures > 0)
-		pr_info("%d tests FAILED\n", binder_selftest_failures);
-	else
-		pr_info("PASSED\n");
-
-done:
-	mutex_unlock(&binder_selftest_lock);
-}
diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h
index 7270d4d22207..342574bfd28a 100644
--- a/drivers/android/binder_internal.h
+++ b/drivers/android/binder_internal.h
@@ -3,7 +3,6 @@
 #ifndef _LINUX_BINDER_INTERNAL_H
 #define _LINUX_BINDER_INTERNAL_H
 
-#include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/list.h>
 #include <linux/miscdevice.h>
@@ -14,6 +13,7 @@
 #include <linux/uidgid.h>
 #include <uapi/linux/android/binderfs.h>
 #include "binder_alloc.h"
+#include "dbitmap.h"
 
 struct binder_context {
 	struct binder_node *binder_context_mgr_node;
@@ -24,8 +24,7 @@ struct binder_context {
 
 /**
  * struct binder_device - information about a binder device node
- * @hlist:          list of binder devices (only used for devices requested via
- *                  CONFIG_ANDROID_BINDER_DEVICES)
+ * @hlist:          list of binder devices
  * @miscdev:        information about a binder character device node
  * @context:        binder context information
  * @binderfs_inode: This is the inode of the root dentry of the super block
@@ -82,7 +81,6 @@ extern bool is_binderfs_device(const struct inode *inode);
 extern struct dentry *binderfs_create_file(struct dentry *dir, const char *name,
 					   const struct file_operations *fops,
 					   void *data);
-extern void binderfs_remove_file(struct dentry *dentry);
 #else
 static inline bool is_binderfs_device(const struct inode *inode)
 {
@@ -95,7 +93,6 @@ static inline struct dentry *binderfs_create_file(struct dentry *dir,
 {
 	return NULL;
 }
-static inline void binderfs_remove_file(struct dentry *dentry) {}
 #endif
 
 #ifdef CONFIG_ANDROID_BINDERFS
@@ -129,12 +126,13 @@ enum binder_stat_types {
 	BINDER_STAT_DEATH,
 	BINDER_STAT_TRANSACTION,
 	BINDER_STAT_TRANSACTION_COMPLETE,
+	BINDER_STAT_FREEZE,
 	BINDER_STAT_COUNT
 };
 
 struct binder_stats {
-	atomic_t br[_IOC_NR(BR_TRANSACTION_PENDING_FROZEN) + 1];
-	atomic_t bc[_IOC_NR(BC_REPLY_SG) + 1];
+	atomic_t br[_IOC_NR(BR_CLEAR_FREEZE_NOTIFICATION_DONE) + 1];
+	atomic_t bc[_IOC_NR(BC_FREEZE_NOTIFICATION_DONE) + 1];
 	atomic_t obj_created[BINDER_STAT_COUNT];
 	atomic_t obj_deleted[BINDER_STAT_COUNT];
 };
@@ -159,6 +157,8 @@ struct binder_work {
 		BINDER_WORK_DEAD_BINDER,
 		BINDER_WORK_DEAD_BINDER_AND_CLEAR,
 		BINDER_WORK_CLEAR_DEATH_NOTIFICATION,
+		BINDER_WORK_FROZEN_BINDER,
+		BINDER_WORK_CLEAR_FREEZE_NOTIFICATION,
 	} type;
 };
 
@@ -275,6 +275,14 @@ struct binder_ref_death {
 	binder_uintptr_t cookie;
 };
 
+struct binder_ref_freeze {
+	struct binder_work work;
+	binder_uintptr_t cookie;
+	bool is_frozen:1;
+	bool sent:1;
+	bool resend:1;
+};
+
 /**
  * struct binder_ref_data - binder_ref counts and id
  * @debug_id:        unique ID for the ref
@@ -307,6 +315,8 @@ struct binder_ref_data {
  *               @node indicates the node must be freed
  * @death:       pointer to death notification (ref_death) if requested
  *               (protected by @node->lock)
+ * @freeze:      pointer to freeze notification (ref_freeze) if requested
+ *               (protected by @node->lock)
  *
  * Structure to track references from procA to target node (on procB). This
  * structure is unsafe to access without holding @proc->outer_lock.
@@ -323,6 +333,7 @@ struct binder_ref {
 	struct binder_proc *proc;
 	struct binder_node *node;
 	struct binder_ref_death *death;
+	struct binder_ref_freeze *freeze;
 };
 
 /**
@@ -368,12 +379,16 @@ struct binder_ref {
  * @freeze_wait:          waitqueue of processes waiting for all outstanding
  *                        transactions to be processed
  *                        (protected by @inner_lock)
+ * @dmap                  dbitmap to manage available reference descriptors
+ *                        (protected by @outer_lock)
  * @todo:                 list of work for this process
  *                        (protected by @inner_lock)
  * @stats:                per-process binder statistics
  *                        (atomics, no lock needed)
  * @delivered_death:      list of delivered death notification
  *                        (protected by @inner_lock)
+ * @delivered_freeze:     list of delivered freeze notification
+ *                        (protected by @inner_lock)
  * @max_threads:          cap on number of binder threads
  *                        (protected by @inner_lock)
  * @requested_threads:    number of binder threads requested but not
@@ -417,11 +432,12 @@ struct binder_proc {
 	bool sync_recv;
 	bool async_recv;
 	wait_queue_head_t freeze_wait;
-
+	struct dbitmap dmap;
 	struct list_head todo;
 	struct binder_stats stats;
 	struct list_head delivered_death;
-	int max_threads;
+	struct list_head delivered_freeze;
+	u32 max_threads;
 	int requested_threads;
 	int requested_threads_started;
 	int tmp_ref;
@@ -521,8 +537,8 @@ struct binder_transaction {
 	struct binder_proc *to_proc;
 	struct binder_thread *to_thread;
 	struct binder_transaction *to_parent;
-	unsigned need_reply:1;
-	/* unsigned is_dead:1; */       /* not used at the moment */
+	unsigned is_async:1;
+	unsigned is_reply:1;
 
 	struct binder_buffer *buffer;
 	unsigned int    code;
@@ -562,4 +578,20 @@ struct binder_object {
 	};
 };
 
+/**
+ * Add a binder device to binder_devices
+ * @device: the new binder device to add to the global list
+ */
+void binder_add_device(struct binder_device *device);
+
+/**
+ * Remove a binder device to binder_devices
+ * @device: the binder device to remove from the global list
+ */
+void binder_remove_device(struct binder_device *device);
+
+#if IS_ENABLED(CONFIG_KUNIT)
+vm_fault_t binder_vm_fault(struct vm_fault *vmf);
+#endif
+
 #endif /* _LINUX_BINDER_INTERNAL_H */
diff --git a/drivers/android/binder_netlink.c b/drivers/android/binder_netlink.c
new file mode 100644
index 000000000000..d05397a50ca6
--- /dev/null
+++ b/drivers/android/binder_netlink.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/binder.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "binder_netlink.h"
+
+#include <uapi/linux/android/binder_netlink.h>
+
+/* Ops table for binder */
+static const struct genl_split_ops binder_nl_ops[] = {
+};
+
+static const struct genl_multicast_group binder_nl_mcgrps[] = {
+	[BINDER_NLGRP_REPORT] = { "report", },
+};
+
+struct genl_family binder_nl_family __ro_after_init = {
+	.name		= BINDER_FAMILY_NAME,
+	.version	= BINDER_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= binder_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(binder_nl_ops),
+	.mcgrps		= binder_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(binder_nl_mcgrps),
+};
diff --git a/drivers/android/binder_netlink.h b/drivers/android/binder_netlink.h
new file mode 100644
index 000000000000..882c7a6b537e
--- /dev/null
+++ b/drivers/android/binder_netlink.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/binder.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_BINDER_GEN_H
+#define _LINUX_BINDER_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/android/binder_netlink.h>
+
+enum {
+	BINDER_NLGRP_REPORT,
+};
+
+extern struct genl_family binder_nl_family;
+
+#endif /* _LINUX_BINDER_GEN_H */
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
index 8cc07e6a4273..fa5eb61cf580 100644
--- a/drivers/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -34,27 +34,6 @@ TRACE_EVENT(binder_ioctl,
 	TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg)
 );
 
-DECLARE_EVENT_CLASS(binder_lock_class,
-	TP_PROTO(const char *tag),
-	TP_ARGS(tag),
-	TP_STRUCT__entry(
-		__field(const char *, tag)
-	),
-	TP_fast_assign(
-		__entry->tag = tag;
-	),
-	TP_printk("tag=%s", __entry->tag)
-);
-
-#define DEFINE_BINDER_LOCK_EVENT(name)	\
-DEFINE_EVENT(binder_lock_class, name,	\
-	TP_PROTO(const char *func), \
-	TP_ARGS(func))
-
-DEFINE_BINDER_LOCK_EVENT(binder_lock);
-DEFINE_BINDER_LOCK_EVENT(binder_locked);
-DEFINE_BINDER_LOCK_EVENT(binder_unlock);
-
 DECLARE_EVENT_CLASS(binder_function_return_class,
 	TP_PROTO(int ret),
 	TP_ARGS(ret),
@@ -317,7 +296,7 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_update_buffer_release,
 
 TRACE_EVENT(binder_update_page_range,
 	TP_PROTO(struct binder_alloc *alloc, bool allocate,
-		 void __user *start, void __user *end),
+		 unsigned long start, unsigned long end),
 	TP_ARGS(alloc, allocate, start, end),
 	TP_STRUCT__entry(
 		__field(int, proc)
@@ -328,7 +307,7 @@ TRACE_EVENT(binder_update_page_range,
 	TP_fast_assign(
 		__entry->proc = alloc->pid;
 		__entry->allocate = allocate;
-		__entry->offset = start - alloc->buffer;
+		__entry->offset = start - alloc->vm_start;
 		__entry->size = end - start;
 	),
 	TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
@@ -423,6 +402,43 @@ TRACE_EVENT(binder_return,
 			  "unknown")
 );
 
+TRACE_EVENT(binder_netlink_report,
+	TP_PROTO(const char *context,
+		 struct binder_transaction *t,
+		 u32 data_size,
+		 u32 error),
+	TP_ARGS(context, t, data_size, error),
+	TP_STRUCT__entry(
+		__field(const char *, context)
+		__field(u32, error)
+		__field(int, from_pid)
+		__field(int, from_tid)
+		__field(int, to_pid)
+		__field(int, to_tid)
+		__field(bool, is_reply)
+		__field(unsigned int, flags)
+		__field(unsigned int, code)
+		__field(size_t, data_size)
+	),
+	TP_fast_assign(
+		__entry->context = context;
+		__entry->error = error;
+		__entry->from_pid = t->from_pid;
+		__entry->from_tid = t->from_tid;
+		__entry->to_pid = t->to_proc ? t->to_proc->pid : 0;
+		__entry->to_tid = t->to_thread ? t->to_thread->pid : 0;
+		__entry->is_reply = t->is_reply;
+		__entry->flags = t->flags;
+		__entry->code = t->code;
+		__entry->data_size = data_size;
+	),
+	TP_printk("from %d:%d to %d:%d context=%s error=%d is_reply=%d flags=0x%x code=0x%x size=%zu",
+		  __entry->from_pid, __entry->from_tid,
+		  __entry->to_pid, __entry->to_tid,
+		  __entry->context, __entry->error, __entry->is_reply,
+		  __entry->flags, __entry->code, __entry->data_size)
+);
+
 #endif /* _BINDER_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index 1224ab7aa070..be8e64eb39ec 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -29,7 +29,6 @@
 #include <linux/uaccess.h>
 #include <linux/user_namespace.h>
 #include <linux/xarray.h>
-#include <uapi/asm-generic/errno-base.h>
 #include <uapi/linux/android/binder.h>
 #include <uapi/linux/android/binderfs.h>
 
@@ -59,6 +58,8 @@ enum binderfs_stats_mode {
 struct binder_features {
 	bool oneway_spam_detection;
 	bool extended_error;
+	bool freeze_notification;
+	bool transaction_report;
 };
 
 static const struct constant_table binderfs_param_stats[] = {
@@ -75,6 +76,8 @@ static const struct fs_parameter_spec binderfs_fs_parameters[] = {
 static struct binder_features binder_features = {
 	.oneway_spam_detection = true,
 	.extended_error = true,
+	.freeze_notification = true,
+	.transaction_report = true,
 };
 
 static inline struct binderfs_info *BINDERFS_SB(const struct super_block *sb)
@@ -116,7 +119,6 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	struct dentry *dentry, *root;
 	struct binder_device *device;
 	char *name = NULL;
-	size_t name_len;
 	struct inode *inode = NULL;
 	struct super_block *sb = ref_inode->i_sb;
 	struct binderfs_info *info = sb->s_fs_info;
@@ -160,9 +162,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	inode->i_gid = info->root_gid;
 
 	req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */
-	name_len = strlen(req->name);
-	/* Make sure to include terminating NUL byte */
-	name = kmemdup(req->name, name_len + 1, GFP_KERNEL);
+	name = kstrdup(req->name, GFP_KERNEL);
 	if (!name)
 		goto err;
 
@@ -186,7 +186,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	inode_lock(d_inode(root));
 
 	/* look it up */
-	dentry = lookup_one_len(name, root, name_len);
+	dentry = lookup_noperm(&QSTR(name), root);
 	if (IS_ERR(dentry)) {
 		inode_unlock(d_inode(root));
 		ret = PTR_ERR(dentry);
@@ -206,6 +206,8 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	fsnotify_create(root->d_inode, dentry);
 	inode_unlock(d_inode(root));
 
+	binder_add_device(device);
+
 	return 0;
 
 err:
@@ -271,6 +273,7 @@ static void binderfs_evict_inode(struct inode *inode)
 	mutex_unlock(&binderfs_minors_mutex);
 
 	if (refcount_dec_and_test(&device->ref)) {
+		binder_remove_device(device);
 		kfree(device->context.name);
 		kfree(device);
 	}
@@ -483,7 +486,7 @@ static struct dentry *binderfs_create_dentry(struct dentry *parent,
 {
 	struct dentry *dentry;
 
-	dentry = lookup_one_len(name, parent, strlen(name));
+	dentry = lookup_noperm(&QSTR(name), parent);
 	if (IS_ERR(dentry))
 		return dentry;
 
@@ -496,21 +499,6 @@ static struct dentry *binderfs_create_dentry(struct dentry *parent,
 	return dentry;
 }
 
-void binderfs_remove_file(struct dentry *dentry)
-{
-	struct inode *parent_inode;
-
-	parent_inode = d_inode(dentry->d_parent);
-	inode_lock(parent_inode);
-	if (simple_positive(dentry)) {
-		dget(dentry);
-		simple_unlink(parent_inode, dentry);
-		d_delete(dentry);
-		dput(dentry);
-	}
-	inode_unlock(parent_inode);
-}
-
 struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
 				    const struct file_operations *fops,
 				    void *data)
@@ -609,6 +597,18 @@ static int init_binder_features(struct super_block *sb)
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
+	dentry = binderfs_create_file(dir, "freeze_notification",
+				      &binder_features_fops,
+				      &binder_features.freeze_notification);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = binderfs_create_file(dir, "transaction_report",
+				      &binder_features_fops,
+				      &binder_features.transaction_report);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
 	return 0;
 }
 
diff --git a/drivers/android/dbitmap.h b/drivers/android/dbitmap.h
new file mode 100644
index 000000000000..c7299ce8b374
--- /dev/null
+++ b/drivers/android/dbitmap.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2024 Google LLC
+ *
+ * dbitmap - dynamically sized bitmap library.
+ *
+ * Used by the binder driver to optimize the allocation of the smallest
+ * available descriptor ID. Each bit in the bitmap represents the state
+ * of an ID.
+ *
+ * A dbitmap can grow or shrink as needed. This part has been designed
+ * considering that users might need to briefly release their locks in
+ * order to allocate memory for the new bitmap. These operations then,
+ * are verified to determine if the grow or shrink is sill valid.
+ *
+ * This library does not provide protection against concurrent access
+ * by itself. Binder uses the proc->outer_lock for this purpose.
+ */
+
+#ifndef _LINUX_DBITMAP_H
+#define _LINUX_DBITMAP_H
+#include <linux/bitmap.h>
+
+#define NBITS_MIN	BITS_PER_TYPE(unsigned long)
+
+struct dbitmap {
+	unsigned int nbits;
+	unsigned long *map;
+};
+
+static inline int dbitmap_enabled(struct dbitmap *dmap)
+{
+	return !!dmap->nbits;
+}
+
+static inline void dbitmap_free(struct dbitmap *dmap)
+{
+	dmap->nbits = 0;
+	kfree(dmap->map);
+	dmap->map = NULL;
+}
+
+/* Returns the nbits that a dbitmap can shrink to, 0 if not possible. */
+static inline unsigned int dbitmap_shrink_nbits(struct dbitmap *dmap)
+{
+	unsigned int bit;
+
+	if (dmap->nbits <= NBITS_MIN)
+		return 0;
+
+	/*
+	 * Determine if the bitmap can shrink based on the position of
+	 * its last set bit. If the bit is within the first quarter of
+	 * the bitmap then shrinking is possible. In this case, the
+	 * bitmap should shrink to half its current size.
+	 */
+	bit = find_last_bit(dmap->map, dmap->nbits);
+	if (bit < (dmap->nbits >> 2))
+		return dmap->nbits >> 1;
+
+	/* find_last_bit() returns dmap->nbits when no bits are set. */
+	if (bit == dmap->nbits)
+		return NBITS_MIN;
+
+	return 0;
+}
+
+/* Replace the internal bitmap with a new one of different size */
+static inline void
+dbitmap_replace(struct dbitmap *dmap, unsigned long *new, unsigned int nbits)
+{
+	bitmap_copy(new, dmap->map, min(dmap->nbits, nbits));
+	kfree(dmap->map);
+	dmap->map = new;
+	dmap->nbits = nbits;
+}
+
+static inline void
+dbitmap_shrink(struct dbitmap *dmap, unsigned long *new, unsigned int nbits)
+{
+	if (!new)
+		return;
+
+	/*
+	 * Verify that shrinking to @nbits is still possible. The @new
+	 * bitmap might have been allocated without locks, so this call
+	 * could now be outdated. In this case, free @new and move on.
+	 */
+	if (!dbitmap_enabled(dmap) || dbitmap_shrink_nbits(dmap) != nbits) {
+		kfree(new);
+		return;
+	}
+
+	dbitmap_replace(dmap, new, nbits);
+}
+
+/* Returns the nbits that a dbitmap can grow to. */
+static inline unsigned int dbitmap_grow_nbits(struct dbitmap *dmap)
+{
+	return dmap->nbits << 1;
+}
+
+static inline void
+dbitmap_grow(struct dbitmap *dmap, unsigned long *new, unsigned int nbits)
+{
+	/*
+	 * Verify that growing to @nbits is still possible. The @new
+	 * bitmap might have been allocated without locks, so this call
+	 * could now be outdated. In this case, free @new and move on.
+	 */
+	if (!dbitmap_enabled(dmap) || nbits <= dmap->nbits) {
+		kfree(new);
+		return;
+	}
+
+	/*
+	 * Check for ENOMEM after confirming the grow operation is still
+	 * required. This ensures we only disable the dbitmap when it's
+	 * necessary. Once the dbitmap is disabled, binder will fallback
+	 * to slow_desc_lookup_olocked().
+	 */
+	if (!new) {
+		dbitmap_free(dmap);
+		return;
+	}
+
+	dbitmap_replace(dmap, new, nbits);
+}
+
+/*
+ * Finds and sets the next zero bit in the bitmap. Upon success @bit
+ * is populated with the index and 0 is returned. Otherwise, -ENOSPC
+ * is returned to indicate that a dbitmap_grow() is needed.
+ */
+static inline int
+dbitmap_acquire_next_zero_bit(struct dbitmap *dmap, unsigned long offset,
+			      unsigned long *bit)
+{
+	unsigned long n;
+
+	n = find_next_zero_bit(dmap->map, dmap->nbits, offset);
+	if (n == dmap->nbits)
+		return -ENOSPC;
+
+	*bit = n;
+	set_bit(n, dmap->map);
+
+	return 0;
+}
+
+static inline void
+dbitmap_clear_bit(struct dbitmap *dmap, unsigned long bit)
+{
+	clear_bit(bit, dmap->map);
+}
+
+static inline int dbitmap_init(struct dbitmap *dmap)
+{
+	dmap->map = bitmap_zalloc(NBITS_MIN, GFP_KERNEL);
+	if (!dmap->map) {
+		dmap->nbits = 0;
+		return -ENOMEM;
+	}
+
+	dmap->nbits = NBITS_MIN;
+
+	return 0;
+}
+#endif
diff --git a/drivers/android/tests/.kunitconfig b/drivers/android/tests/.kunitconfig
new file mode 100644
index 000000000000..39b76bab9d9a
--- /dev/null
+++ b/drivers/android/tests/.kunitconfig
@@ -0,0 +1,7 @@
+#
+# Copyright 2025 Google LLC.
+#
+
+CONFIG_KUNIT=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_BINDER_ALLOC_KUNIT_TEST=y
diff --git a/drivers/android/tests/Makefile b/drivers/android/tests/Makefile
new file mode 100644
index 000000000000..27268418eb03
--- /dev/null
+++ b/drivers/android/tests/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright 2025 Google LLC.
+#
+
+obj-$(CONFIG_ANDROID_BINDER_ALLOC_KUNIT_TEST)	+= binder_alloc_kunit.o
diff --git a/drivers/android/tests/binder_alloc_kunit.c b/drivers/android/tests/binder_alloc_kunit.c
new file mode 100644
index 000000000000..9b884d977f76
--- /dev/null
+++ b/drivers/android/tests/binder_alloc_kunit.c
@@ -0,0 +1,572 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test cases for binder allocator code.
+ *
+ * Copyright 2025 Google LLC.
+ * Author: Tiffany Yang <ynaffit@google.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <kunit/test.h>
+#include <linux/anon_inodes.h>
+#include <linux/err.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/seq_buf.h>
+#include <linux/sizes.h>
+
+#include "../binder_alloc.h"
+#include "../binder_internal.h"
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+#define BINDER_MMAP_SIZE SZ_128K
+
+#define BUFFER_NUM 5
+#define BUFFER_MIN_SIZE (PAGE_SIZE / 8)
+
+#define FREESEQ_BUFLEN ((3 * BUFFER_NUM) + 1)
+
+#define ALIGN_TYPE_STRLEN (12)
+
+#define ALIGNMENTS_BUFLEN (((ALIGN_TYPE_STRLEN + 6) * BUFFER_NUM) + 1)
+
+#define PRINT_ALL_CASES (0)
+
+/* 5^5 alignment combinations * 2 places to share pages * 5! free sequences */
+#define TOTAL_EXHAUSTIVE_CASES (3125 * 2 * 120)
+
+/**
+ * enum buf_end_align_type - Page alignment of a buffer
+ * end with regard to the end of the previous buffer.
+ *
+ * In the pictures below, buf2 refers to the buffer we
+ * are aligning. buf1 refers to previous buffer by addr.
+ * Symbol [ means the start of a buffer, ] means the end
+ * of a buffer, and | means page boundaries.
+ */
+enum buf_end_align_type {
+	/**
+	 * @SAME_PAGE_UNALIGNED: The end of this buffer is on
+	 * the same page as the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 ][ ...
+	 * buf1 ]|[ buf2 ][ ...
+	 */
+	SAME_PAGE_UNALIGNED = 0,
+	/**
+	 * @SAME_PAGE_ALIGNED: When the end of the previous buffer
+	 * is not page aligned, the end of this buffer is on the
+	 * same page as the end of the previous buffer and is page
+	 * aligned. When the previous buffer is page aligned, the
+	 * end of this buffer is aligned to the next page boundary.
+	 * Examples:
+	 * buf1 ][ buf2 ]| ...
+	 * buf1 ]|[ buf2 ]| ...
+	 */
+	SAME_PAGE_ALIGNED,
+	/**
+	 * @NEXT_PAGE_UNALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 ][ ...
+	 */
+	NEXT_PAGE_UNALIGNED,
+	/**
+	 * @NEXT_PAGE_ALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ]| ...
+	 * buf1 ]|[ buf2 | buf2 ]| ...
+	 */
+	NEXT_PAGE_ALIGNED,
+	/**
+	 * @NEXT_NEXT_UNALIGNED: The end of this buffer is on
+	 * the page that follows the page after the end of the
+	 * previous buffer and is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
+	 */
+	NEXT_NEXT_UNALIGNED,
+	/**
+	 * @LOOP_END: The number of enum values in &buf_end_align_type.
+	 * It is used for controlling loop termination.
+	 */
+	LOOP_END,
+};
+
+static const char *const buf_end_align_type_strs[LOOP_END] = {
+	[SAME_PAGE_UNALIGNED] = "SP_UNALIGNED",
+	[SAME_PAGE_ALIGNED]   = " SP_ALIGNED ",
+	[NEXT_PAGE_UNALIGNED] = "NP_UNALIGNED",
+	[NEXT_PAGE_ALIGNED]   = " NP_ALIGNED ",
+	[NEXT_NEXT_UNALIGNED] = "NN_UNALIGNED",
+};
+
+struct binder_alloc_test_case_info {
+	char alignments[ALIGNMENTS_BUFLEN];
+	struct seq_buf alignments_sb;
+	size_t *buffer_sizes;
+	int *free_sequence;
+	bool front_pages;
+};
+
+static void stringify_free_seq(struct kunit *test, int *seq, struct seq_buf *sb)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++)
+		seq_buf_printf(sb, "[%d]", seq[i]);
+
+	KUNIT_EXPECT_FALSE(test, seq_buf_has_overflowed(sb));
+}
+
+static void stringify_alignments(struct kunit *test, int *alignments,
+				 struct seq_buf *sb)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++)
+		seq_buf_printf(sb, "[ %d:%s ]", i,
+			       buf_end_align_type_strs[alignments[i]]);
+
+	KUNIT_EXPECT_FALSE(test, seq_buf_has_overflowed(sb));
+}
+
+static bool check_buffer_pages_allocated(struct kunit *test,
+					 struct binder_alloc *alloc,
+					 struct binder_buffer *buffer,
+					 size_t size)
+{
+	unsigned long page_addr;
+	unsigned long end;
+	int page_index;
+
+	end = PAGE_ALIGN(buffer->user_data + size);
+	page_addr = buffer->user_data;
+	for (; page_addr < end; page_addr += PAGE_SIZE) {
+		page_index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		if (!alloc->pages[page_index] ||
+		    !list_empty(page_to_lru(alloc->pages[page_index]))) {
+			kunit_err(test, "expect alloc but is %s at page index %d\n",
+				  alloc->pages[page_index] ?
+				  "lru" : "free", page_index);
+			return false;
+		}
+	}
+	return true;
+}
+
+static unsigned long binder_alloc_test_alloc_buf(struct kunit *test,
+						 struct binder_alloc *alloc,
+						 struct binder_buffer *buffers[],
+						 size_t *sizes, int *seq)
+{
+	unsigned long failures = 0;
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++) {
+		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0);
+		if (IS_ERR(buffers[i]) ||
+		    !check_buffer_pages_allocated(test, alloc, buffers[i], sizes[i]))
+			failures++;
+	}
+
+	return failures;
+}
+
+static unsigned long binder_alloc_test_free_buf(struct kunit *test,
+						struct binder_alloc *alloc,
+						struct binder_buffer *buffers[],
+						size_t *sizes, int *seq, size_t end)
+{
+	unsigned long failures = 0;
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++)
+		binder_alloc_free_buf(alloc, buffers[seq[i]]);
+
+	for (i = 0; i <= (end - 1) / PAGE_SIZE; i++) {
+		if (list_empty(page_to_lru(alloc->pages[i]))) {
+			kunit_err(test, "expect lru but is %s at page index %d\n",
+				  alloc->pages[i] ? "alloc" : "free", i);
+			failures++;
+		}
+	}
+
+	return failures;
+}
+
+static unsigned long binder_alloc_test_free_page(struct kunit *test,
+						 struct binder_alloc *alloc)
+{
+	unsigned long failures = 0;
+	unsigned long count;
+	int i;
+
+	while ((count = list_lru_count(alloc->freelist))) {
+		list_lru_walk(alloc->freelist, binder_alloc_free_page,
+			      NULL, count);
+	}
+
+	for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
+		if (alloc->pages[i]) {
+			kunit_err(test, "expect free but is %s at page index %d\n",
+				  list_empty(page_to_lru(alloc->pages[i])) ?
+				  "alloc" : "lru", i);
+			failures++;
+		}
+	}
+
+	return failures;
+}
+
+/* Executes one full test run for the given test case. */
+static bool binder_alloc_test_alloc_free(struct kunit *test,
+					 struct binder_alloc *alloc,
+					 struct binder_alloc_test_case_info *tc,
+					 size_t end)
+{
+	unsigned long pages = PAGE_ALIGN(end) / PAGE_SIZE;
+	struct binder_buffer *buffers[BUFFER_NUM];
+	unsigned long failures;
+	bool failed = false;
+
+	failures = binder_alloc_test_alloc_buf(test, alloc, buffers,
+					       tc->buffer_sizes,
+					       tc->free_sequence);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "Initial allocation failed: %lu/%u buffers with errors",
+			    failures, BUFFER_NUM);
+
+	failures = binder_alloc_test_free_buf(test, alloc, buffers,
+					      tc->buffer_sizes,
+					      tc->free_sequence, end);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "Initial buffers not freed correctly: %lu/%lu pages not on lru list",
+			    failures, pages);
+
+	/* Allocate from lru. */
+	failures = binder_alloc_test_alloc_buf(test, alloc, buffers,
+					       tc->buffer_sizes,
+					       tc->free_sequence);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "Reallocation failed: %lu/%u buffers with errors",
+			    failures, BUFFER_NUM);
+
+	failures = list_lru_count(alloc->freelist);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "lru list should be empty after reallocation but still has %lu pages",
+			    failures);
+
+	failures = binder_alloc_test_free_buf(test, alloc, buffers,
+					      tc->buffer_sizes,
+					      tc->free_sequence, end);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "Reallocated buffers not freed correctly: %lu/%lu pages not on lru list",
+			    failures, pages);
+
+	failures = binder_alloc_test_free_page(test, alloc);
+	failed = failed || failures;
+	KUNIT_EXPECT_EQ_MSG(test, failures, 0,
+			    "Failed to clean up allocated pages: %lu/%lu pages still installed",
+			    failures, (alloc->buffer_size / PAGE_SIZE));
+
+	return failed;
+}
+
+static bool is_dup(int *seq, int index, int val)
+{
+	int i;
+
+	for (i = 0; i < index; i++) {
+		if (seq[i] == val)
+			return true;
+	}
+	return false;
+}
+
+/* Generate BUFFER_NUM factorial free orders. */
+static void permute_frees(struct kunit *test, struct binder_alloc *alloc,
+			  struct binder_alloc_test_case_info *tc,
+			  unsigned long *runs, unsigned long *failures,
+			  int index, size_t end)
+{
+	bool case_failed;
+	int i;
+
+	if (index == BUFFER_NUM) {
+		DECLARE_SEQ_BUF(freeseq_sb, FREESEQ_BUFLEN);
+
+		case_failed = binder_alloc_test_alloc_free(test, alloc, tc, end);
+		*runs += 1;
+		*failures += case_failed;
+
+		if (case_failed || PRINT_ALL_CASES) {
+			stringify_free_seq(test, tc->free_sequence,
+					   &freeseq_sb);
+			kunit_err(test, "case %lu: [%s] | %s - %s - %s", *runs,
+				  case_failed ? "FAILED" : "PASSED",
+				  tc->front_pages ? "front" : "back ",
+				  seq_buf_str(&tc->alignments_sb),
+				  seq_buf_str(&freeseq_sb));
+		}
+
+		return;
+	}
+	for (i = 0; i < BUFFER_NUM; i++) {
+		if (is_dup(tc->free_sequence, index, i))
+			continue;
+		tc->free_sequence[index] = i;
+		permute_frees(test, alloc, tc, runs, failures, index + 1, end);
+	}
+}
+
+static void gen_buf_sizes(struct kunit *test,
+			  struct binder_alloc *alloc,
+			  struct binder_alloc_test_case_info *tc,
+			  size_t *end_offset, unsigned long *runs,
+			  unsigned long *failures)
+{
+	size_t last_offset, offset = 0;
+	size_t front_sizes[BUFFER_NUM];
+	size_t back_sizes[BUFFER_NUM];
+	int seq[BUFFER_NUM] = {0};
+	int i;
+
+	tc->free_sequence = seq;
+	for (i = 0; i < BUFFER_NUM; i++) {
+		last_offset = offset;
+		offset = end_offset[i];
+		front_sizes[i] = offset - last_offset;
+		back_sizes[BUFFER_NUM - i - 1] = front_sizes[i];
+	}
+	back_sizes[0] += alloc->buffer_size - end_offset[BUFFER_NUM - 1];
+
+	/*
+	 * Buffers share the first or last few pages.
+	 * Only BUFFER_NUM - 1 buffer sizes are adjustable since
+	 * we need one giant buffer before getting to the last page.
+	 */
+	tc->front_pages = true;
+	tc->buffer_sizes = front_sizes;
+	permute_frees(test, alloc, tc, runs, failures, 0,
+		      end_offset[BUFFER_NUM - 1]);
+
+	tc->front_pages = false;
+	tc->buffer_sizes = back_sizes;
+	permute_frees(test, alloc, tc, runs, failures, 0, alloc->buffer_size);
+}
+
+static void gen_buf_offsets(struct kunit *test, struct binder_alloc *alloc,
+			    size_t *end_offset, int *alignments,
+			    unsigned long *runs, unsigned long *failures,
+			    int index)
+{
+	size_t end, prev;
+	int align;
+
+	if (index == BUFFER_NUM) {
+		struct binder_alloc_test_case_info tc = {0};
+
+		seq_buf_init(&tc.alignments_sb, tc.alignments,
+			     ALIGNMENTS_BUFLEN);
+		stringify_alignments(test, alignments, &tc.alignments_sb);
+
+		gen_buf_sizes(test, alloc, &tc, end_offset, runs, failures);
+		return;
+	}
+	prev = index == 0 ? 0 : end_offset[index - 1];
+	end = prev;
+
+	BUILD_BUG_ON(BUFFER_MIN_SIZE * BUFFER_NUM >= PAGE_SIZE);
+
+	for (align = SAME_PAGE_UNALIGNED; align < LOOP_END; align++) {
+		if (align % 2)
+			end = ALIGN(end, PAGE_SIZE);
+		else
+			end += BUFFER_MIN_SIZE;
+		end_offset[index] = end;
+		alignments[index] = align;
+		gen_buf_offsets(test, alloc, end_offset, alignments, runs,
+				failures, index + 1);
+	}
+}
+
+struct binder_alloc_test {
+	struct binder_alloc alloc;
+	struct list_lru binder_test_freelist;
+	struct file *filp;
+	unsigned long mmap_uaddr;
+};
+
+static void binder_alloc_test_init_freelist(struct kunit *test)
+{
+	struct binder_alloc_test *priv = test->priv;
+
+	KUNIT_EXPECT_PTR_EQ(test, priv->alloc.freelist,
+			    &priv->binder_test_freelist);
+}
+
+static void binder_alloc_test_mmap(struct kunit *test)
+{
+	struct binder_alloc_test *priv = test->priv;
+	struct binder_alloc *alloc = &priv->alloc;
+	struct binder_buffer *buf;
+	struct rb_node *n;
+
+	KUNIT_EXPECT_EQ(test, alloc->mapped, true);
+	KUNIT_EXPECT_EQ(test, alloc->buffer_size, BINDER_MMAP_SIZE);
+
+	n = rb_first(&alloc->allocated_buffers);
+	KUNIT_EXPECT_PTR_EQ(test, n, NULL);
+
+	n = rb_first(&alloc->free_buffers);
+	buf = rb_entry(n, struct binder_buffer, rb_node);
+	KUNIT_EXPECT_EQ(test, binder_alloc_buffer_size(alloc, buf),
+			BINDER_MMAP_SIZE);
+	KUNIT_EXPECT_TRUE(test, list_is_last(&buf->entry, &alloc->buffers));
+}
+
+/**
+ * binder_alloc_exhaustive_test() - Exhaustively test alloc and free of buffer pages.
+ * @test: The test context object.
+ *
+ * Allocate BUFFER_NUM buffers to cover all page alignment cases,
+ * then free them in all orders possible. Check that pages are
+ * correctly allocated, put onto lru when buffers are freed, and
+ * are freed when binder_alloc_free_page() is called.
+ */
+static void binder_alloc_exhaustive_test(struct kunit *test)
+{
+	struct binder_alloc_test *priv = test->priv;
+	size_t end_offset[BUFFER_NUM];
+	int alignments[BUFFER_NUM];
+	unsigned long failures = 0;
+	unsigned long runs = 0;
+
+	gen_buf_offsets(test, &priv->alloc, end_offset, alignments, &runs,
+			&failures, 0);
+
+	KUNIT_EXPECT_EQ(test, runs, TOTAL_EXHAUSTIVE_CASES);
+	KUNIT_EXPECT_EQ(test, failures, 0);
+}
+
+/* ===== End test cases ===== */
+
+static void binder_alloc_test_vma_close(struct vm_area_struct *vma)
+{
+	struct binder_alloc *alloc = vma->vm_private_data;
+
+	binder_alloc_vma_close(alloc);
+}
+
+static const struct vm_operations_struct binder_alloc_test_vm_ops = {
+	.close = binder_alloc_test_vma_close,
+	.fault = binder_vm_fault,
+};
+
+static int binder_alloc_test_mmap_handler(struct file *filp,
+					  struct vm_area_struct *vma)
+{
+	struct binder_alloc *alloc = filp->private_data;
+
+	vm_flags_mod(vma, VM_DONTCOPY | VM_MIXEDMAP, VM_MAYWRITE);
+
+	vma->vm_ops = &binder_alloc_test_vm_ops;
+	vma->vm_private_data = alloc;
+
+	return binder_alloc_mmap_handler(alloc, vma);
+}
+
+static const struct file_operations binder_alloc_test_fops = {
+	.mmap = binder_alloc_test_mmap_handler,
+};
+
+static int binder_alloc_test_init(struct kunit *test)
+{
+	struct binder_alloc_test *priv;
+	int ret;
+
+	priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	test->priv = priv;
+
+	ret = list_lru_init(&priv->binder_test_freelist);
+	if (ret) {
+		kunit_err(test, "Failed to initialize test freelist\n");
+		return ret;
+	}
+
+	/* __binder_alloc_init requires mm to be attached */
+	ret = kunit_attach_mm();
+	if (ret) {
+		kunit_err(test, "Failed to attach mm\n");
+		return ret;
+	}
+	__binder_alloc_init(&priv->alloc, &priv->binder_test_freelist);
+
+	priv->filp = anon_inode_getfile("binder_alloc_kunit",
+					&binder_alloc_test_fops, &priv->alloc,
+					O_RDWR | O_CLOEXEC);
+	if (IS_ERR_OR_NULL(priv->filp)) {
+		kunit_err(test, "Failed to open binder alloc test driver file\n");
+		return priv->filp ? PTR_ERR(priv->filp) : -ENOMEM;
+	}
+
+	priv->mmap_uaddr = kunit_vm_mmap(test, priv->filp, 0, BINDER_MMAP_SIZE,
+					 PROT_READ, MAP_PRIVATE | MAP_NORESERVE,
+					 0);
+	if (!priv->mmap_uaddr) {
+		kunit_err(test, "Could not map the test's transaction memory\n");