0 files changed, 0 insertions, 0 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 fe9ceb0d2288..8e1ffa4358d5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -17,6 +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-$(CONFIG_PARISC)		+= parisc/
@@ -130,9 +133,9 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-y				+= mmc/
 obj-y				+= ufs/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
-obj-y				+= leds/
 obj-$(CONFIG_INFINIBAND)	+= infiniband/
 obj-y				+= firmware/
+obj-$(CONFIG_FWCTL)		+= fwctl/
 obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
 obj-y				+= clocksource/
@@ -158,7 +161,7 @@ obj-$(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/
@@ -192,4 +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 16c3edb8c46e..ca3357acd127 100644
--- a/drivers/accel/drm_accel.c
+++ b/drivers/accel/drm_accel.c
@@ -8,7 +8,7 @@
 
 #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>
@@ -18,10 +18,7 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_print.h>
 
-static DEFINE_SPINLOCK(accel_minor_lock);
-static struct idr accel_minors_idr;
-
-static struct dentry *accel_debugfs_root;
+DEFINE_XARRAY_ALLOC(accel_minors_xa);
 
 static const struct device_type accel_sysfs_device_minor = {
 	.name = "accel_minor"
@@ -75,17 +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.
  *
@@ -118,99 +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.
@@ -227,7 +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);
 
@@ -246,7 +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);
@@ -257,7 +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);
 
@@ -274,7 +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;
 }
@@ -288,25 +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 59823e3c3bf7..dee487724918 100644
--- a/drivers/accel/habanalabs/common/command_submission.c
+++ b/drivers/accel/habanalabs/common/command_submission.c
@@ -2586,7 +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) {
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 ca7677293a55..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>
@@ -602,6 +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)
 {
@@ -788,6 +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)
 {
@@ -805,6 +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,
@@ -1403,7 +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;
 
@@ -1525,6 +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)
@@ -1723,6 +2031,11 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 				&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,
 					0644,
 					root,
@@ -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 e0cf3b4343bb..999c92d7036e 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -817,7 +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));
 	}
 }
 
@@ -1066,28 +1066,11 @@ static bool is_pci_link_healthy(struct hl_device *hdev)
 	return (device_id == hdev->pdev->device);
 }
 
-static void stringify_time_of_last_heartbeat(struct hl_device *hdev, char *time_str, size_t size,
-						bool is_pq_hb)
-{
-	time64_t seconds = is_pq_hb ? hdev->heartbeat_debug_info.last_pq_heartbeat_ts
-					: hdev->heartbeat_debug_info.last_eq_heartbeat_ts;
-	struct tm tm;
-
-	if (!seconds)
-		return;
-
-	time64_to_tm(seconds, 0, &tm);
-
-	snprintf(time_str, size, "%ld-%02d-%02d %02d:%02d:%02d (UTC)",
-		tm.tm_year + 1900, tm.tm_mon, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec);
-}
-
 static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 {
 	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;
-	char pq_time_str[64] = "N/A", eq_time_str[64] = "N/A";
 
 	if (!prop->cpucp_info.eq_health_check_supported)
 		return true;
@@ -1095,17 +1078,15 @@ static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 	if (!hdev->eq_heartbeat_received) {
 		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
 
-		stringify_time_of_last_heartbeat(hdev, pq_time_str, sizeof(pq_time_str), true);
-		stringify_time_of_last_heartbeat(hdev, eq_time_str, sizeof(eq_time_str), false);
 		dev_err(hdev->dev,
-			"EQ: {CI %u, HB counter %u, last HB time: %s}, PQ: {PI: %u, CI: %u (%u), last HB time: %s}\n",
+			"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,
-			eq_time_str,
+			&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,
-			pq_time_str);
+			&hdev->heartbeat_debug_info.last_pq_heartbeat_ts);
 
 		hl_eq_dump(hdev, &hdev->event_queue);
 
@@ -1649,6 +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;
@@ -2091,7 +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);
@@ -2595,6 +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 */
@@ -2962,3 +2956,13 @@ void hl_handle_clk_change_event(struct hl_device *hdev, u16 event_type, u64 *eve
 
 	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/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 6f27ce4fa01b..d94c2ba22a6a 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -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
@@ -702,6 +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;
@@ -822,6 +825,7 @@ struct asic_fixed_properties {
 	u8				supports_advanced_cpucp_rc;
 	u8				supports_engine_modes;
 	u8				support_dynamic_resereved_fw_size;
+	u8				supports_nvme;
 };
 
 /**
@@ -2274,6 +2278,9 @@ struct hl_vm {
 	u8			init_done;
 };
 
+#ifdef CONFIG_HL_HLDIO
+#include "hldio.h"
+#endif
 
 /*
  * DEBUG, PROFILING STRUCTURE
@@ -2344,7 +2351,6 @@ struct hl_fpriv {
 	struct mutex			ctx_lock;
 };
 
-
 /*
  * DebugFS
  */
@@ -2372,6 +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.
@@ -2403,6 +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;
@@ -2434,6 +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 */
 };
 
 /**
@@ -3281,6 +3318,7 @@ struct eq_heartbeat_debug_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.
@@ -3305,6 +3343,7 @@ struct eq_heartbeat_debug_info {
  * @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.
@@ -3357,6 +3396,7 @@ struct eq_heartbeat_debug_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
@@ -3461,6 +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;
@@ -3496,7 +3537,9 @@ 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;
@@ -3532,6 +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;
@@ -4089,6 +4133,7 @@ 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
 
@@ -4110,6 +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
 
@@ -4185,6 +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 708dfd10f39c..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,
@@ -362,8 +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;
@@ -388,7 +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;
 
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 1dd6e23172ca..fdfdabc85e54 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -17,8 +17,6 @@
 #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);
 
@@ -963,6 +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;
 	}
@@ -1279,13 +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);
@@ -1308,11 +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/memory.c b/drivers/accel/habanalabs/common/memory.c
index 3348ad12c237..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
 
@@ -1829,9 +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)
@@ -1840,7 +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);
@@ -1859,7 +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;
@@ -1872,13 +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);
@@ -1890,13 +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)
@@ -2341,7 +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 99cd83139d46..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);
 
diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index e9f8ccc0bbf9..8f55ba3b4e73 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -96,14 +96,21 @@ static ssize_t vrm_ver_show(struct device *dev, struct device_attribute *attr, c
 	infineon_second_stage_third_instance =
 					(infineon_second_stage_version >> 16) & mask;
 
-	if (cpucp_info->infineon_second_stage_version)
+	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
+	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);
@@ -368,7 +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);
@@ -443,7 +450,7 @@ 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
@@ -472,7 +479,7 @@ static struct attribute *hl_dev_attrs[] = {
 	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 fa893a9b826e..34771d75da9d 100644
--- a/drivers/accel/habanalabs/gaudi/gaudi.c
+++ b/drivers/accel/habanalabs/gaudi/gaudi.c
@@ -4168,10 +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 a38b88baadf2..b8c0689dba64 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -728,6 +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"
@@ -3150,7 +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;
 	}
@@ -3162,6 +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;
@@ -4836,7 +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);
@@ -6484,6 +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)
@@ -6774,7 +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;
 	}
 
@@ -7026,7 +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;
 }
@@ -7052,8 +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;
 	}
 
@@ -9603,8 +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");
@@ -10172,7 +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:
@@ -10260,6 +10623,7 @@ 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);
 }
@@ -10296,8 +10660,8 @@ static int gaudi2_memset_memory_chunk_using_edma_qm(struct hl_device *hdev,
 
 	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;
 }
@@ -10437,7 +10801,7 @@ end:
 				(u64 *)(lin_dma_pkts_arr), DEBUGFS_WRITE64);
 	WREG32(sob_addr, 0);
 
-	kfree(lin_dma_pkts_arr);
+	kvfree(lin_dma_pkts_arr);
 
 	return rc;
 }
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2P.h b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
index 05117272cac7..bdf5c1bd2d63 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2P.h
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
@@ -240,6 +240,15 @@
 #define GAUDI2_NUM_TESTED_QS		(GAUDI2_QUEUE_ID_CPU_PQ - GAUDI2_QUEUE_ID_PDMA_0_0)
 
 
+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,
 	GAUDI2_RESERVED_SOB_CS_COMPLETION_LAST =
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/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig
index 682c53245286..9e055b5ce03d 100644
--- a/drivers/accel/ivpu/Kconfig
+++ b/drivers/accel/ivpu/Kconfig
@@ -8,6 +8,7 @@ config DRM_ACCEL_IVPU
 	select FW_LOADER
 	select DRM_GEM_SHMEM_HELPER
 	select GENERIC_ALLOCATOR
+	select WANT_DEV_COREDUMP
 	help
 	  Choose this option if you have a system with an 14th generation
 	  Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU)
@@ -15,3 +16,12 @@ config DRM_ACCEL_IVPU
 	  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 ebd682a42eb1..1029e0bab061 100644
--- a/drivers/accel/ivpu/Makefile
+++ b/drivers/accel/ivpu/Makefile
@@ -16,8 +16,14 @@ intel_vpu-y := \
 	ivpu_mmu_context.o \
 	ivpu_ms.o \
 	ivpu_pm.o \
-	ivpu_sysfs.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 6f86f8df30db..cd24ccd20ba6 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/fault-inject.h>
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_file.h>
@@ -45,6 +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);
@@ -108,42 +117,43 @@ static int reset_pending_show(struct seq_file *s, void *v)
 	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 ssize_t
-dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+static int dvfs_mode_get(void *data, u64 *dvfs_mode)
 {
-	struct ivpu_device *vdev = file->private_data;
-	struct ivpu_fw_info *fw = vdev->fw;
-	u32 dvfs_mode;
-	int ret;
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	ret = kstrtou32_from_user(user_buf, size, 0, &dvfs_mode);
-	if (ret < 0)
-		return ret;
-
-	fw->dvfs_mode = dvfs_mode;
+	*dvfs_mode = vdev->fw->dvfs_mode;
+	return 0;
+}
 
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret)
-		return ret;
+static int dvfs_mode_set(void *data, u64 dvfs_mode)
+{
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	return size;
+	vdev->fw->dvfs_mode = (u32)dvfs_mode;
+	return pci_try_reset_function(to_pci_dev(vdev->drm.dev));
 }
 
-static const struct file_operations dvfs_mode_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = dvfs_mode_fops_write,
-};
+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)
@@ -192,7 +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;
 }
 
@@ -322,7 +332,7 @@ ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t si
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	ivpu_pm_trigger_recovery(vdev, "debugfs");
@@ -337,49 +347,23 @@ static const struct file_operations ivpu_force_recovery_fops = {
 	.write = ivpu_force_recovery_fn,
 };
 
-static ssize_t
-ivpu_reset_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+static int ivpu_reset_engine_fn(void *data, u64 val)
 {
-	struct ivpu_device *vdev = file->private_data;
-
-	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;
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	return size;
+	return ivpu_jsm_reset_engine(vdev, (u32)val);
 }
 
-static const struct file_operations ivpu_reset_engine_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_reset_engine_fn,
-};
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_reset_engine_fops, NULL, ivpu_reset_engine_fn, "0x%02llx\n");
 
-static ssize_t
-ivpu_resume_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+static int ivpu_resume_engine_fn(void *data, u64 val)
 {
-	struct ivpu_device *vdev = file->private_data;
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	if (!size)
-		return -EINVAL;
-
-	if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COMPUTE))
-		return -ENODEV;
-	if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COPY))
-		return -ENODEV;
-
-	return size;
+	return ivpu_jsm_hws_resume_engine(vdev, (u32)val);
 }
 
-static const struct file_operations ivpu_resume_engine_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_resume_engine_fn,
-};
+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)
 {
@@ -399,7 +383,7 @@ static int dct_active_set(void *data, u64 active_percent)
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	if (active_percent)
@@ -414,6 +398,88 @@ static int dct_active_set(void *data, u64 active_percent)
 
 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
+priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+{
+	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 >= 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;
+
+	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_hws_priority_bands_fops = {
+	.owner = THIS_MODULE,
+	.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)
 {
 	struct dentry *debugfs_root = vdev->drm.debugfs_root;
@@ -423,7 +489,7 @@ 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", 0200, debugfs_root, vdev,
+	debugfs_create_file("dvfs_mode", 0644, debugfs_root, vdev,
 			    &dvfs_mode_fops);
 
 	debugfs_create_file("fw_dyndbg", 0200, debugfs_root, vdev,
@@ -436,6 +502,8 @@ 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);
@@ -447,4 +515,8 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 				    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 c91400ecf926..3289751b4757 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,12 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 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>
@@ -14,7 +16,7 @@
 #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"
@@ -29,21 +31,21 @@
 #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 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 mask. See IVPU_TEST_MODE_* macros.");
+#endif
 
 u8 ivpu_pll_min_ratio;
 module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
@@ -53,9 +55,9 @@ 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 NPU frequency");
 
-int ivpu_sched_mode;
+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: 0 - Default scheduler, 1 - Force HW scheduler");
+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, 0444);
@@ -85,7 +87,7 @@ static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *fi
 
 		ivpu_cmdq_release_all_locked(file_priv);
 		ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx);
-		ivpu_mmu_user_context_fini(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));
 	}
@@ -103,6 +105,8 @@ static void file_priv_release(struct kref *ref)
 	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);
 
@@ -116,8 +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));
 
@@ -125,20 +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 = 1;
-		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_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
@@ -164,7 +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:
-		args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio);
+		args->value = ivpu_hw_dpu_max_freq_get(vdev);
 		break;
 	case DRM_IVPU_PARAM_NUM_CONTEXTS:
 		args->value = ivpu_get_context_count(vdev);
@@ -198,7 +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;
@@ -255,9 +255,14 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 		goto err_unlock;
 	}
 
-	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
-	if (ret)
-		goto err_xa_erase;
+	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);
@@ -269,8 +274,6 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 
 	return 0;
 
-err_xa_erase:
-	xa_erase_irq(&vdev->context_xa, ctx_id);
 err_unlock:
 	mutex_unlock(&vdev->context_list_lock);
 	mutex_destroy(&file_priv->ms_lock);
@@ -304,6 +307,9 @@ static const struct drm_ioctl_desc ivpu_drm_ioctls[] = {
 	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)
@@ -346,7 +352,7 @@ static int ivpu_hw_sched_init(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+	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);
@@ -368,6 +374,9 @@ 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, ivpu_bo_vaddr(vdev->fw->mem));
 
@@ -380,10 +389,7 @@ 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);
-		ivpu_hw_diagnose_failure(vdev);
-		ivpu_mmu_evtq_dump(vdev);
-		ivpu_fw_log_dump(vdev);
-		return ret;
+		goto err_diagnose_failure;
 	}
 
 	ivpu_hw_irq_clear(vdev);
@@ -394,18 +400,33 @@ int ivpu_boot(struct ivpu_device *vdev)
 	if (ivpu_fw_is_cold_boot(vdev)) {
 		ret = ivpu_pm_dct_init(vdev);
 		if (ret)
-			return ret;
+			goto err_disable_ipc;
 
-		return ivpu_hw_sched_init(vdev);
+		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);
 }
@@ -438,7 +459,7 @@ static const struct drm_driver driver = {
 	.postclose = ivpu_postclose,
 
 	.gem_create_object = ivpu_gem_create_object,
-	.gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table,
+	.gem_prime_import = ivpu_gem_prime_import,
 
 	.ioctls = ivpu_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls),
@@ -446,58 +467,9 @@ 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,
-};
-
-static void ivpu_context_abort_invalid(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) {
-		if (!file_priv->has_mmu_faults || file_priv->aborted)
-			continue;
-
-		mutex_lock(&file_priv->lock);
-		ivpu_context_abort_locked(file_priv);
-		file_priv->aborted = true;
-		mutex_unlock(&file_priv->lock);
-	}
-
-	mutex_unlock(&vdev->context_list_lock);
-}
-
-static irqreturn_t ivpu_irq_thread_handler(int irq, void *arg)
-{
-	struct ivpu_device *vdev = arg;
-	u8 irq_src;
-
-	if (kfifo_is_empty(&vdev->hw->irq.fifo))
-		return IRQ_NONE;
-
-	while (kfifo_get(&vdev->hw->irq.fifo, &irq_src)) {
-		switch (irq_src) {
-		case IVPU_HW_IRQ_SRC_IPC:
-			ivpu_ipc_irq_thread_handler(vdev);
-			break;
-		case IVPU_HW_IRQ_SRC_MMU_EVTQ:
-			ivpu_context_abort_invalid(vdev);
-			break;
-		case IVPU_HW_IRQ_SRC_DCT:
-			ivpu_pm_dct_irq_thread_handler(vdev);
-			break;
-		default:
-			ivpu_err_ratelimited(vdev, "Unknown IRQ source: %u\n", irq_src);
-			break;
-		}
-	}
-
-	return IRQ_HANDLED;
-}
+	.major = 1,
+};
 
 static int ivpu_irq_init(struct ivpu_device *vdev)
 {
@@ -510,12 +482,16 @@ 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_threaded_irq(vdev->drm.dev, vdev->irq, ivpu_hw_irq_handler,
-					ivpu_irq_thread_handler, IRQF_NO_AUTOEN, DRIVER_NAME, vdev);
+	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);
 
@@ -600,16 +576,23 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	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);
+	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);
 	xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
 	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;
@@ -632,9 +615,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (ret)
 		goto err_shutdown;
 
-	ret = ivpu_mmu_global_context_init(vdev);
-	if (ret)
-		goto err_shutdown;
+	ivpu_mmu_global_context_init(vdev);
 
 	ret = ivpu_mmu_init(vdev);
 	if (ret)
@@ -696,7 +677,7 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_jobs_abort_all(vdev);
-	ivpu_pm_cancel_recovery(vdev);
+	ivpu_pm_disable_recovery(vdev);
 	ivpu_pm_disable(vdev);
 	ivpu_prepare_for_reset(vdev);
 	ivpu_shutdown(vdev);
@@ -722,6 +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);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 63f13b697eed..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) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_DRV_H__
@@ -21,11 +21,12 @@
 
 #define DRIVER_NAME "intel_vpu"
 #define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)"
-#define DRIVER_DATE "20230117"
 
-#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_IP_37XX 37
 #define IVPU_HW_IP_40XX 40
@@ -46,17 +47,23 @@
 #define IVPU_MIN_DB 1
 #define IVPU_MAX_DB 255
 
-#define IVPU_NUM_ENGINES       2
+#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_ENGINES * IVPU_NUM_PRIORITIES)
+#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_PRIORITIES)
 
-#define IVPU_CMDQ_INDEX(engine, priority) ((engine) * IVPU_NUM_PRIORITIES + (priority))
+#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)
@@ -105,6 +112,7 @@ struct ivpu_wa_table {
 	bool disable_clock_relinquish;
 	bool disable_d0i3_msg;
 	bool wp0_during_power_up;
+	bool disable_d0i2;
 };
 
 struct ivpu_hw_info;
@@ -134,12 +142,20 @@ struct ivpu_device {
 	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 ivpu_ipc_consumer job_done_consumer;
+	atomic_t job_timeout_counter;
 
 	atomic64_t unique_id_counter;
 
@@ -150,8 +166,10 @@ struct ivpu_device {
 		int boot;
 		int jsm;
 		int tdr;
+		int inference;
 		int autosuspend;
 		int d0i3_entry_msg;
+		int state_dump_msg;
 	} timeout;
 };
 
@@ -163,11 +181,15 @@ struct ivpu_file_priv {
 	struct kref ref;
 	struct ivpu_device *vdev;
 	struct mutex lock; /* Protects cmdq */
-	struct ivpu_cmdq *cmdq[IVPU_NUM_CMDQS_PER_CTX];
+	struct xarray cmdq_xa;
 	struct ivpu_mmu_context ctx;
 	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;
@@ -185,9 +207,13 @@ extern bool ivpu_force_snoop;
 #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_PREEMPTION_DISABLE BIT(6)
-#define IVPU_TEST_MODE_HWS_EXTRA_EVENTS	  BIT(7)
+#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);
@@ -196,6 +222,7 @@ 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)
 {
@@ -215,6 +242,9 @@ static inline int ivpu_hw_ip_gen(struct ivpu_device *vdev)
 		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");
@@ -229,6 +259,8 @@ static inline int ivpu_hw_btrs_gen(struct ivpu_device *vdev)
 	case PCI_DEVICE_ID_ARL:
 		return IVPU_HW_BTRS_MTL;
 	case PCI_DEVICE_ID_LNL:
+	case PCI_DEVICE_ID_PTL_P:
+	case PCI_DEVICE_ID_WCL:
 		return IVPU_HW_BTRS_LNL;
 	default:
 		dump_stack();
@@ -267,7 +299,8 @@ 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)
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index de3d66116375..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) 2020-2024 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
@@ -47,19 +46,28 @@
 #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, "NPU firmware binary in /lib/firmware/..");
+#endif
 
 static struct {
 	int gen;
 	const char *name;
 } fw_names[] = {
-	{ IVPU_HW_IP_37XX, "vpu_37xx.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, "vpu_40xx.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;
@@ -131,6 +139,18 @@ static bool is_within_range(u64 addr, size_t size, u64 range_start, size_t range
 	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;
@@ -187,8 +207,10 @@ 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");
+
+	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;
@@ -204,14 +226,26 @@ 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->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
-	fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
+	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,
@@ -307,7 +341,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 		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;
@@ -510,6 +544,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 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)
@@ -540,7 +576,6 @@ 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_pll_freq_get(vdev);
 
 	/*
 	 * This param is a debug firmware feature.  It switches default clock
@@ -563,8 +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;
@@ -600,14 +637,16 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	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->hw->sched_mode;
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW)
+	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 */
diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h
index 40d9d17be3f5..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;
@@ -32,12 +38,14 @@ struct ivpu_fw_info {
 	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 ef0adb5e0fbe..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,
-		 "NPU 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, "NPU 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, "NPU 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 1b409dbd332d..59cfcf3eaded 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -20,15 +20,27 @@
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
 
+MODULE_IMPORT_NS("DMA_BUF");
+
 static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
 static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
 {
 	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 ? bo->ctx->id : 0,
+		 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)bo->base.base.import_attach);
+		 (bool)drm_gem_is_imported(&bo->base.base));
+}
+
+static inline int ivpu_bo_lock(struct ivpu_bo *bo)
+{
+	return dma_resv_lock(bo->base.base.resv, NULL);
+}
+
+static inline void ivpu_bo_unlock(struct ivpu_bo *bo)
+{
+	dma_resv_unlock(bo->base.base.resv);
 }
 
 /*
@@ -41,22 +53,22 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con
 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");
-	drm_WARN_ON(&vdev->drm, !bo->ctx);
 
-	if (!bo->mmu_mapped) {
-		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+	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 (IS_ERR(sgt)) {
-			ret = PTR_ERR(sgt);
-			ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
-			goto unlock;
-		}
+	ivpu_bo_lock(bo);
 
+	if (!bo->mmu_mapped) {
+		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) {
@@ -67,7 +79,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 	}
 
 unlock:
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	return ret;
 }
@@ -82,7 +94,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	if (!drm_dev_enter(&vdev->drm, &idx))
 		return -ENODEV;
 
-	mutex_lock(&bo->lock);
+	ivpu_bo_lock(bo);
 
 	ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
 	if (!ret) {
@@ -92,9 +104,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
 	}
 
-	ivpu_dbg_bo(vdev, bo, "alloc");
-
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	drm_dev_exit(idx);
 
@@ -105,7 +115,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
-	lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount));
+	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->ctx);
@@ -120,17 +130,15 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 		bo->ctx = NULL;
 	}
 
-	if (bo->base.base.import_attach)
+	if (drm_gem_is_imported(&bo->base.base))
 		return;
 
-	dma_resv_lock(bo->base.base.resv, NULL);
 	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;
 	}
-	dma_resv_unlock(bo->base.base.resv);
 }
 
 void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
@@ -142,12 +150,12 @@ void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
-		mutex_lock(&bo->lock);
+		ivpu_bo_lock(bo);
 		if (bo->ctx == ctx) {
 			ivpu_dbg_bo(vdev, bo, "unbind");
 			ivpu_bo_unbind_locked(bo);
 		}
-		mutex_unlock(&bo->lock);
+		ivpu_bo_unlock(bo);
 	}
 	mutex_unlock(&vdev->bo_list_lock);
 }
@@ -167,12 +175,52 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz
 	bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */
 
 	INIT_LIST_HEAD(&bo->bo_list_node);
-	mutex_init(&bo->lock);
 
 	return &bo->base.base;
 }
 
-static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags)
+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;
+	}
+
+	obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
+	if (IS_ERR(obj)) {
+		ret = PTR_ERR(obj);
+		goto fail_unmap;
+	}
+
+	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);
+
+	return ERR_PTR(ret);
+}
+
+static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, u32 ctx_id)
 {
 	struct drm_gem_shmem_object *shmem;
 	struct ivpu_bo *bo;
@@ -190,6 +238,7 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla
 		return ERR_CAST(shmem);
 
 	bo = to_ivpu_bo(&shmem->base);
+	bo->ctx_id = ctx_id;
 	bo->base.map_wc = flags & DRM_IVPU_BO_WC;
 	bo->flags = flags;
 
@@ -197,6 +246,8 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla
 	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
 	mutex_unlock(&vdev->bo_list_lock);
 
+	ivpu_dbg_bo(vdev, bo, "alloc");
+
 	return bo;
 }
 
@@ -234,12 +285,16 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj)
 	list_del(&bo->bo_list_node);
 	mutex_unlock(&vdev->bo_list_lock);
 
-	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
+	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);
 
 	ivpu_bo_unbind_locked(bo);
-	mutex_destroy(&bo->lock);
+	drm_WARN_ON(&vdev->drm, bo->mmu_mapped);
+	drm_WARN_ON(&vdev->drm, bo->ctx);
 
-	drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1);
+	drm_WARN_ON(obj->dev, refcount_read(&bo->base.pages_use_count) > 1);
 	drm_gem_shmem_free(&bo->base);
 }
 
@@ -271,7 +326,7 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	if (size == 0)
 		return -EINVAL;
 
-	bo = ivpu_bo_alloc(vdev, size, args->flags);
+	bo = ivpu_bo_alloc(vdev, size, args->flags, file_priv->ctx.id);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to allocate BO: %pe (ctx %u size %llu flags 0x%x)",
 			 bo, file_priv->ctx.id, args->size, args->flags);
@@ -279,7 +334,10 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	}
 
 	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
-	if (!ret)
+	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;
 
 	drm_gem_object_put(&bo->base.base);
@@ -302,7 +360,7 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->end));
 	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size));
 
-	bo = ivpu_bo_alloc(vdev, size, flags);
+	bo = ivpu_bo_alloc(vdev, size, flags, IVPU_GLOBAL_CONTEXT_MMU_SSID);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to allocate BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
 			 bo, range->start, size, flags);
@@ -318,9 +376,9 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		goto err_put;
 
 	if (flags & DRM_IVPU_BO_MAPPABLE) {
-		dma_resv_lock(bo->base.base.resv, NULL);
-		ret = drm_gem_shmem_vmap(&bo->base, &map);
-		dma_resv_unlock(bo->base.base.resv);
+		ivpu_bo_lock(bo);
+		ret = drm_gem_shmem_vmap_locked(&bo->base, &map);
+		ivpu_bo_unlock(bo);
 
 		if (ret)
 			goto err_put;
@@ -343,9 +401,9 @@ void ivpu_bo_free(struct ivpu_bo *bo)
 	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
 	if (bo->flags & DRM_IVPU_BO_MAPPABLE) {
-		dma_resv_lock(bo->base.base.resv, NULL);
-		drm_gem_shmem_vunmap(&bo->base, &map);
-		dma_resv_unlock(bo->base.base.resv);
+		ivpu_bo_lock(bo);
+		drm_gem_shmem_vunmap_locked(&bo->base, &map);
+		ivpu_bo_unlock(bo);
 	}
 
 	drm_gem_object_put(&bo->base.base);
@@ -364,12 +422,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	bo = to_ivpu_bo(obj);
 
-	mutex_lock(&bo->lock);
+	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;
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	drm_gem_object_put(obj);
 	return ret;
@@ -384,6 +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;
@@ -403,10 +464,10 @@ 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)
 {
-	mutex_lock(&bo->lock);
+	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, bo->ctx_id, bo->vpu_addr, bo->base.base.size,
 		   bo->flags, kref_read(&bo->base.base.refcount));
 
 	if (bo->base.pages)
@@ -415,12 +476,12 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 	if (bo->mmu_mapped)
 		drm_printf(p, " mmu_mapped");
 
-	if (bo->base.base.import_attach)
+	if (drm_gem_is_imported(&bo->base.base))
 		drm_printf(p, " imported");
 
 	drm_printf(p, "\n");
 
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 }
 
 void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index d975000abd78..aa8ff14f7aae 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -17,10 +17,10 @@ struct ivpu_bo {
 	struct list_head bo_list_node;
 	struct drm_mm_node mm_node;
 
-	struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */
 	u64 vpu_addr;
 	u32 flags;
 	u32 job_status; /* Valid only for command buffer */
+	u32 ctx_id;
 	bool mmu_mapped;
 };
 
@@ -28,6 +28,7 @@ int ivpu_bo_pin(struct ivpu_bo *bo);
 void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 
 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);
 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);
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index 27f0fe4d54e0..08dcc31b56f4 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -9,6 +9,16 @@
 #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)
 {
@@ -19,43 +29,36 @@ static char *platform_to_str(u32 platform)
 		return "SIMICS";
 	case IVPU_PLATFORM_FPGA:
 		return "FPGA";
+	case IVPU_PLATFORM_HSLE:
+		return "HSLE";
 	default:
 		return "Invalid platform";
 	}
 }
 
-static const struct dmi_system_id 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 platform_init(struct ivpu_device *vdev)
 {
-	if (dmi_check_system(dmi_platform_simulation))
-		vdev->platform = IVPU_PLATFORM_SIMICS;
-	else
-		vdev->platform = IVPU_PLATFORM_SILICON;
+	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;
 
-	ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n",
-		 platform_to_str(vdev->platform), vdev->platform);
+	default:
+		ivpu_err(vdev, "Invalid platform type: %d\n", platform);
+		break;
+	}
 }
 
 static void wa_init(struct ivpu_device *vdev)
 {
-	vdev->wa.punit_disabled = ivpu_is_fpga(vdev);
+	vdev->wa.punit_disabled = false;
 	vdev->wa.clear_runtime_mem = false;
 
 	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
@@ -65,14 +68,24 @@ static void wa_init(struct ivpu_device *vdev)
 	    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)
@@ -81,44 +94,71 @@ static void timeouts_init(struct ivpu_device *vdev)
 		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 = 100000;
-		vdev->timeout.jsm = 50000;
-		vdev->timeout.tdr = 2000000;
+		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.autosuspend = -1;
+		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,   0xc0000000, 255 * SZ_1M);
+		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_8G);
+		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.user,   0x80000000, SZ_256M);
-		ivpu_hw_range_init(&vdev->hw->ranges.shave,  0x80000000 + SZ_256M, SZ_2G - SZ_256M);
-		ivpu_hw_range_init(&vdev->hw->ranges.dma,   0x200000000, SZ_8G);
+		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;
 	}
 }
 
@@ -245,10 +285,17 @@ 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;
 }
@@ -281,8 +328,6 @@ void ivpu_hw_profiling_freq_drive(struct ivpu_device *vdev, bool enable)
 
 void ivpu_irq_handlers_init(struct ivpu_device *vdev)
 {
-	INIT_KFIFO(vdev->hw->irq.fifo);
-
 	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
 		vdev->hw->irq.ip_irq_handler = ivpu_hw_ip_irq_handler_37xx;
 	else
@@ -296,7 +341,6 @@ void ivpu_irq_handlers_init(struct ivpu_device *vdev)
 
 void ivpu_hw_irq_enable(struct ivpu_device *vdev)
 {
-	kfifo_reset(&vdev->hw->irq.fifo);
 	ivpu_hw_ip_irq_enable(vdev);
 	ivpu_hw_btrs_irq_enable(vdev);
 }
@@ -323,9 +367,9 @@ irqreturn_t ivpu_hw_irq_handler(int irq, void *ptr)
 	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
 	ivpu_hw_btrs_global_int_enable(vdev);
 
-	if (!kfifo_is_empty(&vdev->hw->irq.fifo))
-		return IRQ_WAKE_THREAD;
-	if (ip_handled || btrs_handled)
-		return IRQ_HANDLED;
-	return IRQ_NONE;
+	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 1c0c98e3afb8..d79668fe1609 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -1,23 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_H__
 #define __IVPU_HW_H__
 
-#include <linux/kfifo.h>
-
 #include "ivpu_drv.h"
 #include "ivpu_hw_btrs.h"
 #include "ivpu_hw_ip.h"
 
-#define IVPU_HW_IRQ_FIFO_LENGTH 1024
-
-#define IVPU_HW_IRQ_SRC_IPC 1
-#define IVPU_HW_IRQ_SRC_MMU_EVTQ 2
-#define IVPU_HW_IRQ_SRC_DCT 3
-
 struct ivpu_addr_range {
 	resource_size_t start;
 	resource_size_t end;
@@ -27,7 +19,6 @@ struct ivpu_hw_info {
 	struct {
 		bool (*btrs_irq_handler)(struct ivpu_device *vdev, int irq);
 		bool (*ip_irq_handler)(struct ivpu_device *vdev, int irq);
-		DECLARE_KFIFO(fifo, u8, IVPU_HW_IRQ_FIFO_LENGTH);
 	} irq;
 	struct {
 		struct ivpu_addr_range global;
@@ -45,13 +36,18 @@ 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 sched_mode;
 	u32 sku;
 	u16 config;
 	int dma_bits;
 	ktime_t d0i3_entry_host_ts;
 	u64 d0i3_entry_vpu_ts;
+	atomic_t firewall_irq_counter;
 };
 
 int ivpu_hw_init(struct ivpu_device *vdev);
@@ -86,19 +82,19 @@ static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
 	return range->end - range->start;
 }
 
-static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev)
 {
-	return ivpu_hw_btrs_ratio_to_freq(vdev, ratio);
+	return ivpu_hw_btrs_dpu_max_freq_get(vdev);
 }
 
-static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_dpu_freq_get(struct ivpu_device *vdev)
 {
-	ivpu_hw_ip_irq_clear(vdev);
+	return ivpu_hw_btrs_dpu_freq_get(vdev);
 }
 
-static inline u32 ivpu_hw_pll_freq_get(struct ivpu_device *vdev)
+static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
 {
-	return ivpu_hw_btrs_pll_freq_get(vdev);
+	ivpu_hw_ip_irq_clear(vdev);
 }
 
 static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
index d0b795b344c7..fc0ee8d637f9 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
@@ -115,6 +115,8 @@
 
 #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)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c
index 745e5248803d..afdb3b2aa72a 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.c
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
+#include <linux/units.h>
+
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
 #include "ivpu_hw_btrs.h"
@@ -28,17 +30,12 @@
 
 #define BTRS_LNL_ALL_IRQ_MASK ((u32)-1)
 
-#define BTRS_MTL_WP_CONFIG_1_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_1_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_0_TILE_PLL_OFF   WP_CONFIG(0, 0)
 
 #define PLL_CDYN_DEFAULT               0x80
 #define PLL_EPP_DEFAULT                0x80
-#define PLL_CONFIG_DEFAULT             0x0
-#define PLL_SIMULATION_FREQ            10000000
-#define PLL_REF_CLK_FREQ               50000000
+#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)
@@ -62,6 +59,8 @@
 #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);
@@ -141,16 +140,10 @@ static int read_tile_config_fuse(struct ivpu_device *vdev, u32 *tile_fuse_config
 	}
 
 	config = REG_GET_FLD(VPU_HW_BTRS_LNL_TILE_FUSE, CONFIG, fuse);
-	if (!tile_disable_check(config)) {
-		ivpu_err(vdev, "Fuse: Invalid tile disable config (0x%x)\n", config);
-		return -EIO;
-	}
+	if (!tile_disable_check(config))
+		ivpu_warn(vdev, "More than 1 tile disabled, tile fuse config mask: 0x%x\n", config);
 
-	if (config)
-		ivpu_dbg(vdev, MISC, "Fuse: %d tiles enabled. Tile number %d disabled\n",
-			 BTRS_LNL_TILE_MAX_NUM - 1, ffs(config) - 1);
-	else
-		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", BTRS_LNL_TILE_MAX_NUM);
+	ivpu_dbg(vdev, MISC, "Tile disable config mask: 0x%x\n", config);
 
 	*tile_fuse_config = config;
 	return 0;
@@ -162,8 +155,7 @@ static int info_init_mtl(struct ivpu_device *vdev)
 
 	hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH;
 	hw->sku = BTRS_MTL_TILE_SKU_BOTH;
-	hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO;
-	hw->sched_mode = ivpu_sched_mode;
+	hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3);
 
 	return 0;
 }
@@ -178,7 +170,6 @@ static int info_init_lnl(struct ivpu_device *vdev)
 	if (ret)
 		return ret;
 
-	hw->sched_mode = ivpu_sched_mode;
 	hw->tile_fuse = tile_fuse_config;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
@@ -311,14 +302,10 @@ static void prepare_wp_request(struct ivpu_device *vdev, struct wp_request *wp,
 		wp->epp = 0;
 	} else {
 		wp->target = hw->pll.pn_ratio;
-		wp->cfg = enable ? PLL_CONFIG_DEFAULT : 0;
+		wp->cfg = 0;
 		wp->cdyn = enable ? PLL_CDYN_DEFAULT : 0;
 		wp->epp = enable ? PLL_EPP_DEFAULT : 0;
 	}
-
-	/* Simics cannot start without at least one tile */
-	if (enable && ivpu_is_simics(vdev))
-		wp->cfg = 1;
 }
 
 static int wait_for_pll_lock(struct ivpu_device *vdev, bool enable)
@@ -346,8 +333,8 @@ int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable)
 
 	prepare_wp_request(vdev, &wp, enable);
 
-	ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
-		 PLL_RATIO_TO_FREQ(wp.target), wp.cfg, wp.epp, wp.cdyn);
+	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) {
@@ -465,9 +452,6 @@ 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;
 
-	if (ivpu_is_simics(vdev))
-		return 0;
-
 	return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US);
 }
 
@@ -588,6 +572,47 @@ int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev)
 		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)
 {
@@ -597,9 +622,12 @@ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
 	if (!status)
 		return false;
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
-			 REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL));
+	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));
@@ -645,12 +673,15 @@ bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq)
 
 	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, SURV_ERR, status)) {
 		ivpu_dbg(vdev, IRQ, "Survivability IRQ\n");
-		if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_DCT))
-			ivpu_err_ratelimited(vdev, "IRQ FIFO full\n");
+		queue_work(system_wq, &vdev->irq_dct_work);
 	}
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ));
+	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",
@@ -733,60 +764,6 @@ void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 acti
 	REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val);
 }
 
-static u32 pll_ratio_to_freq_mtl(u32 ratio, u32 config)
-{
-	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
-	u32 cpu_clock;
-
-	if ((config & 0xff) == MTL_PLL_RATIO_4_3)
-		cpu_clock = pll_clock * 2 / 4;
-	else
-		cpu_clock = pll_clock * 2 / 5;
-
-	return cpu_clock;
-}
-
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_ratio_to_freq_mtl(ratio, hw->config);
-	else
-		return PLL_RATIO_TO_FREQ(ratio);
-}
-
-static u32 pll_freq_get_mtl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
-	pll_curr_ratio &= VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK;
-
-	if (!ivpu_is_silicon(vdev))
-		return PLL_SIMULATION_FREQ;
-
-	return pll_ratio_to_freq_mtl(pll_curr_ratio, vdev->hw->config);
-}
-
-static u32 pll_freq_get_lnl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
-	pll_curr_ratio &= VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK;
-
-	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
-}
-
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev)
-{
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_freq_get_mtl(vdev);
-	else
-		return pll_freq_get_lnl(vdev);
-}
-
 u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev)
 {
 	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
@@ -903,3 +880,10 @@ void ivpu_hw_btrs_diagnose_failure(struct ivpu_device *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
index 04f14f50fed6..032c384ac3d4 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.h
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_BTRS_H__
@@ -13,9 +13,8 @@
 
 #define PLL_PROFILING_FREQ_DEFAULT   38400000
 #define PLL_PROFILING_FREQ_HIGH      400000000
-#define PLL_RATIO_TO_FREQ(x)         ((x) * PLL_REF_CLK_FREQ)
 
-#define DCT_DEFAULT_ACTIVE_PERCENT 15u
+#define DCT_DEFAULT_ACTIVE_PERCENT 30u
 #define DCT_PERIOD_US		   35300u
 
 int ivpu_hw_btrs_info_init(struct ivpu_device *vdev);
@@ -32,12 +31,12 @@ 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 dct_percent);
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev);
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio);
+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);
@@ -46,5 +45,6 @@ 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
index fc51f3098f97..fff2ef2cada6 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h
@@ -86,6 +86,7 @@
 #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)
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c
index dfd2f4a5b526..2bf9882ab52e 100644
--- a/drivers/accel/ivpu/ivpu_hw_ip.c
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -8,15 +8,12 @@
 #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_EN_POST_DLY_FREQ_DEFAULT 0
-#define PWR_ISLAND_EN_POST_DLY_FREQ_HIGH    18
-#define PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT  3
-#define PWR_ISLAND_STATUS_DLY_FREQ_HIGH	    46
 #define PWR_ISLAND_STATUS_TIMEOUT_US        (5 * USEC_PER_MSEC)
 
 #define TIM_SAFE_ENABLE		            0xf1d0dead
@@ -268,20 +265,15 @@ void ivpu_hw_ip_idle_gen_disable(struct ivpu_device *vdev)
 		idle_gen_drive_40xx(vdev, false);
 }
 
-static void pwr_island_delay_set_50xx(struct ivpu_device *vdev)
+static void
+pwr_island_delay_set_50xx(struct ivpu_device *vdev, u32 post, u32 post1, u32 post2, u32 status)
 {
-	u32 val, post, status;
-
-	if (vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_DEFAULT) {
-		post = PWR_ISLAND_EN_POST_DLY_FREQ_DEFAULT;
-		status = PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT;
-	} else {
-		post = PWR_ISLAND_EN_POST_DLY_FREQ_HIGH;
-		status = PWR_ISLAND_STATUS_DLY_FREQ_HIGH;
-	}
+	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);
@@ -311,9 +303,6 @@ static void pwr_island_trickle_drive_40xx(struct ivpu_device *vdev, bool enable)
 		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 pwr_island_drive_37xx(struct ivpu_device *vdev, bool enable)
@@ -326,9 +315,6 @@ static void pwr_island_drive_37xx(struct ivpu_device *vdev, bool enable)
 		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 void pwr_island_drive_40xx(struct ivpu_device *vdev, bool enable)
@@ -347,9 +333,11 @@ 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);
 	}
 }
@@ -686,13 +674,37 @@ static void dpu_active_drive_37xx(struct ivpu_device *vdev, bool enable)
 	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;
 
-	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_50XX)
-		pwr_island_delay_set_50xx(vdev);
-
+	pwr_island_delay_set(vdev);
 	pwr_island_enable(vdev);
 
 	ret = wait_for_pwr_island_status(vdev, 0x1);
@@ -957,14 +969,14 @@ void ivpu_hw_ip_wdt_disable(struct ivpu_device *vdev)
 
 static u32 ipc_rx_count_get_37xx(struct ivpu_device *vdev)
 {
-	u32 count = REGV_RD32_SILENT(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT);
+	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 = REGV_RD32_SILENT(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT);
+	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);
 }
@@ -1062,7 +1074,10 @@ static void irq_wdt_mss_handler(struct ivpu_device *vdev)
 
 static void irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
+	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 */
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 78b32a823241..5f00809d448a 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -15,6 +15,7 @@
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_pm.h"
+#include "ivpu_trace.h"
 
 #define IPC_MAX_RX_MSG	128
 
@@ -140,7 +141,6 @@ ivpu_ipc_rx_msg_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	struct ivpu_ipc_rx_msg *rx_msg;
 
 	lockdep_assert_held(&ipc->cons_lock);
-	lockdep_assert_irqs_disabled();
 
 	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
 	if (!rx_msg) {
@@ -227,6 +227,7 @@ int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, stru
 		goto unlock;
 
 	ivpu_ipc_tx(vdev, cons->tx_vpu_addr);
+	trace_jsm("[tx]", req);
 
 unlock:
 	mutex_unlock(&ipc->lock);
@@ -278,12 +279,13 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		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 (jsm_msg)
 			memcpy(jsm_msg, rx_msg->jsm_msg, size);
+		trace_jsm("[rx]", rx_msg->jsm_msg);
 	}
 
 	ivpu_ipc_rx_msg_del(vdev, rx_msg);
@@ -291,15 +293,17 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	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;
 
+	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);
@@ -325,19 +329,21 @@ consumer_del:
 	return ret;
 }
 
-int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-				 enum vpu_ipc_msg_type expected_resp, 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, 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;
 	int ret, hb_ret;
 
-	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev));
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
 
 	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms);
 	if (ret != -ETIMEDOUT)
-		return ret;
+		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,
@@ -345,21 +351,33 @@ int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *r
 	if (hb_ret == -ETIMEDOUT)
 		ivpu_pm_trigger_recovery(vdev, "IPC timeout");
 
+rpm_put:
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
-int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-			  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)
 {
+	struct ivpu_ipc_consumer cons;
 	int ret;
 
 	ret = ivpu_rpm_get(vdev);
 	if (ret < 0)
 		return ret;
 
-	ret = ivpu_ipc_send_receive_active(vdev, req, expected_resp, resp, channel, timeout_ms);
+	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;
 }
@@ -441,13 +459,12 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		}
 	}
 
-	if (!list_empty(&ipc->cb_msg_list))
-		if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_IPC))
-			ivpu_err_ratelimited(vdev, "IRQ FIFO full\n");
+	queue_work(system_wq, &vdev->irq_ipc_work);
 }
 
-void ivpu_ipc_irq_thread_handler(struct ivpu_device *vdev)
+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;
@@ -518,7 +535,6 @@ void ivpu_ipc_fini(struct ivpu_device *vdev)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
-	drm_WARN_ON(&vdev->drm, ipc->on);
 	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);
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 4fe38141045e..b524a1985b9d 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -90,7 +90,7 @@ void ivpu_ipc_disable(struct ivpu_device *vdev);
 void ivpu_ipc_reset(struct ivpu_device *vdev);
 
 void ivpu_ipc_irq_handler(struct ivpu_device *vdev);
-void ivpu_ipc_irq_thread_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, ivpu_ipc_rx_callback_t callback);
@@ -101,12 +101,13 @@ int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *jsm_msg,
 		     unsigned long timeout_ms);
-
-int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-				 enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
-				 u32 channel, 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, 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 be2e2bf0f43f..060f1fc031d3 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <drm/drm_file.h>
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/highmem.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 #include <linux/module.h>
 #include <uapi/drm/ivpu_accel.h>
 
@@ -17,12 +18,12 @@
 #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 void ivpu_cmdq_ring_db(struct ivpu_device *vdev, struct ivpu_cmdq *cmdq)
@@ -35,24 +36,20 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev,
 {
 	u64 primary_size = ALIGN(vdev->fw->primary_preempt_buf_size, PAGE_SIZE);
 	u64 secondary_size = ALIGN(vdev->fw->secondary_preempt_buf_size, PAGE_SIZE);
-	struct ivpu_addr_range range;
 
-	if (vdev->hw->sched_mode != VPU_SCHEDULING_MODE_HW)
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW ||
+	    ivpu_test_mode & IVPU_TEST_MODE_MIP_DISABLE)
 		return 0;
 
-	range.start = vdev->hw->ranges.user.end - (primary_size * IVPU_NUM_CMDQS_PER_CTX);
-	range.end = vdev->hw->ranges.user.end;
-	cmdq->primary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &range, primary_size,
-						   DRM_IVPU_BO_WC);
+	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;
 	}
 
-	range.start = vdev->hw->ranges.shave.end - (secondary_size * IVPU_NUM_CMDQS_PER_CTX);
-	range.end = vdev->hw->ranges.shave.end;
-	cmdq->secondary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &range, secondary_size,
-						     DRM_IVPU_BO_WC);
+	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;
@@ -62,24 +59,24 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev,
 
 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->hw->sched_mode != VPU_SCHEDULING_MODE_HW)
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
 		return;
 
-	drm_WARN_ON(&vdev->drm, !cmdq->primary_preempt_buf);
-	drm_WARN_ON(&vdev->drm, !cmdq->secondary_preempt_buf);
-	ivpu_bo_free(cmdq->primary_preempt_buf);
-	ivpu_bo_free(cmdq->secondary_preempt_buf);
+	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 xa_limit db_xa_limit = {.max = IVPU_MAX_DB, .min = IVPU_MIN_DB};
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_cmdq *cmdq;
 	int ret;
@@ -88,55 +85,114 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 	if (!cmdq)
 		return NULL;
 
-	ret = xa_alloc(&vdev->db_xa, &cmdq->db_id, NULL, db_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate doorbell id: %d\n", ret);
-		goto err_free_cmdq;
-	}
-
 	cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!cmdq->mem)
-		goto err_erase_xa;
+		goto err_free_cmdq;
 
 	ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq);
 	if (ret)
-		goto err_free_cmdq_mem;
+		ivpu_warn(vdev, "Failed to allocate preemption buffers, preemption limited\n");
 
 	return cmdq;
 
-err_free_cmdq_mem:
-	ivpu_bo_free(cmdq->mem);
-err_erase_xa:
-	xa_erase(&vdev->db_xa, cmdq->db_id);
 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_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);
-	xa_erase(&file_priv->vdev->db_xa, cmdq->db_id);
 	kfree(cmdq);
 }
 
+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 = NULL;
+	int ret;
+
+	lockdep_assert_held(&file_priv->lock);
+
+	cmdq = ivpu_cmdq_alloc(file_priv);
+	if (!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;
+
+	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;
+
+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->db_id,
+	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 ret;
 
-	ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->db_id,
+	ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id,
 							priority);
 	if (ret)
 		return ret;
@@ -149,43 +205,51 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *
 	struct ivpu_device *vdev = file_priv->vdev;
 	int ret;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW)
-		ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->db_id, cmdq->db_id,
+	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 ctx %d\n", cmdq->db_id, file_priv->ctx.id);
+		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 int
-ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 engine, u8 priority)
+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;
-	struct vpu_job_queue_header *jobq_header;
 	int ret;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	if (cmdq->db_registered)
+	if (cmdq->db_id)
 		return 0;
 
-	cmdq->entry_count = (u32)((ivpu_bo_size(cmdq->mem) - sizeof(struct vpu_job_queue_header)) /
-				  sizeof(struct vpu_job_queue_entry));
+	ivpu_cmdq_jobq_reset(vdev, cmdq->jobq);
 
-	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 */
-
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
-		ret = ivpu_hws_cmdq_init(file_priv, cmdq, engine, priority);
+	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;
 	}
@@ -194,83 +258,97 @@ ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 eng
 	if (ret)
 		return ret;
 
-	cmdq->db_registered = true;
-
 	return 0;
 }
 
-static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
+static int ivpu_cmdq_unregister(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->db_registered)
+	if (!cmdq->db_id)
 		return 0;
 
-	cmdq->db_registered = false;
+	ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id);
+	if (!ret)
+		ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id);
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
-		ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, 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\n", cmdq->db_id);
+			ivpu_dbg(vdev, JOB, "Command queue %d destroyed, ctx %d\n",
+				 cmdq->id, file_priv->ctx.id);
 	}
 
-	ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id);
-	if (!ret)
-		ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id);
+	xa_erase(&file_priv->vdev->db_xa, cmdq->db_id);
+	cmdq->db_id = 0;
 
 	return 0;
 }
 
-static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u16 engine,
-					   u8 priority)
+static inline u8 ivpu_job_to_jsm_priority(u8 priority)
 {
-	int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
-	int ret;
+	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);
 
+	xa_for_each(&file_priv->cmdq_xa, id, cmdq)
+		if (cmdq->is_legacy && cmdq->priority == priority)
+			break;
+
 	if (!cmdq) {
-		cmdq = ivpu_cmdq_alloc(file_priv);
+		cmdq = ivpu_cmdq_create(file_priv, priority, 0);
 		if (!cmdq)
 			return NULL;
-		file_priv->cmdq[cmdq_idx] = cmdq;
+		cmdq->is_legacy = true;
 	}
 
-	ret = ivpu_cmdq_init(file_priv, cmdq, engine, priority);
-	if (ret)
-		return NULL;
-
 	return cmdq;
 }
 
-static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engine, u8 priority)
+static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u32 cmdq_id)
 {
-	int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_cmdq *cmdq;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	if (cmdq) {
-		file_priv->cmdq[cmdq_idx] = NULL;
-		ivpu_cmdq_fini(file_priv, cmdq);
-		ivpu_cmdq_free(file_priv, cmdq);
+	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)
 {
-	u16 engine;
-	u8 priority;
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++)
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++)
-			ivpu_cmdq_release_locked(file_priv, engine, priority);
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_destroy(file_priv, cmdq);
 }
 
 /*
@@ -281,19 +359,14 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
  */
 static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv)
 {
-	u16 engine;
-	u8 priority;
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
 	mutex_lock(&file_priv->lock);
 
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) {
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) {
-			int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-			struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
-
-			if (cmdq)
-				cmdq->db_registered = false;
-		}
+	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);
@@ -312,31 +385,24 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev)
 	mutex_unlock(&vdev->context_list_lock);
 }
 
-static void ivpu_cmdq_fini_all(struct ivpu_file_priv *file_priv)
-{
-	u16 engine;
-	u8 priority;
-
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) {
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) {
-			int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-
-			if (file_priv->cmdq[cmdq_idx])
-				ivpu_cmdq_fini(file_priv, file_priv->cmdq[cmdq_idx]);
-		}
-	}
-}
-
 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);
 
-	ivpu_cmdq_fini_all(file_priv);
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_unregister(file_priv, cmdq);
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_OS)
+	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)
@@ -349,24 +415,29 @@ 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->hw->sched_mode == VPU_SCHEDULING_MODE_HW &&
-	    (unlikely(!(ivpu_test_mode & IVPU_TEST_MODE_PREEMPTION_DISABLE)))) {
-		entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr;
-		entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_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);
+	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 */
@@ -424,8 +495,8 @@ static void ivpu_job_destroy(struct ivpu_job *job)
 	struct ivpu_device *vdev = job->vdev;
 	u32 i;
 
-	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d",
-		 job->job_id, job->file_priv->ctx.id, job->engine_idx);
+	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])
@@ -457,6 +528,7 @@ ivpu_job_create(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;
 
@@ -469,16 +541,14 @@ static struct ivpu_job *ivpu_job_remove_from_submitted_jobs(struct ivpu_device *
 {
 	struct ivpu_job *job;
 
-	xa_lock(&vdev->submitted_jobs_xa);
-	job = __xa_erase(&vdev->submitted_jobs_xa, job_id);
+	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);
 	}
 
-	xa_unlock(&vdev->submitted_jobs_xa);
-
 	return job;
 }
 
@@ -486,6 +556,28 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 {
 	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;
@@ -496,13 +588,18 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 	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);
+
 	return 0;
 }
 
@@ -511,15 +608,32 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	struct ivpu_job *job;
 	unsigned long id;
 
+	mutex_lock(&vdev->submitted_jobs_lock);
+
 	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);
 }
 
-static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
+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)
+		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_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;
@@ -528,27 +642,35 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 	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, priority);
+	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_ratelimited(vdev, "Failed to get job queue, ctx %d engine %d prio %d\n",
-				      file_priv->ctx.id, job->engine_idx, priority);
+		ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d\n", file_priv->ctx.id);
 		ret = -EINVAL;
-		goto err_unlock_file_priv;
+		goto err_unlock;
+	}
+
+	ret = ivpu_cmdq_register(file_priv, cmdq);
+	if (ret) {
+		ivpu_err(vdev, "Failed to register command queue: %d\n", ret);
+		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->cmdq_id = cmdq->id;
 
-	xa_lock(&vdev->submitted_jobs_xa);
 	is_first_job = xa_empty(&vdev->submitted_jobs_xa);
-	ret = __xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
-	if (ret) {
+	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_submitted_jobs_xa;
+		goto err_unlock;
 	}
 
 	ret = ivpu_cmdq_push_job(cmdq, job);
@@ -566,25 +688,26 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 			vdev->busy_start_ts = ktime_get();
 	}
 
-	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d prio %d addr 0x%llx next %d\n",
-		 job->job_id, file_priv->ctx.id, job->engine_idx, priority,
+	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);
 
-	xa_unlock(&vdev->submitted_jobs_xa);
-
 	mutex_unlock(&file_priv->lock);
 
-	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW))
+	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_erase_xa:
-	__xa_erase(&vdev->submitted_jobs_xa, job->job_id);
-err_unlock_submitted_jobs_xa:
-	xa_unlock(&vdev->submitted_jobs_xa);
-err_unlock_file_priv:
+	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
+err_unlock:
 	mutex_unlock(&file_priv->lock);
+	mutex_unlock(&vdev->submitted_jobs_lock);
 	ivpu_rpm_put(vdev);
 	return ret;
 }
@@ -593,7 +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;
@@ -655,49 +778,20 @@ unlock_reservations:
 	return ret;
 }
 
-static inline u8 ivpu_job_to_hws_priority(struct ivpu_file_priv *file_priv, u8 priority)
-{
-	if (priority == DRM_IVPU_JOB_PRIORITY_DEFAULT)
-		return DRM_IVPU_JOB_PRIORITY_NORMAL;
-
-	return priority - 1;
-}
-
-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;
-	u8 priority;
 
-	if (params->engine > DRM_IVPU_ENGINE_COPY)
-		return -EINVAL;
-
-	if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
-		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 err_free_handles;
@@ -708,27 +802,24 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		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_job_create(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 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: %d\n", ret);
 		goto err_destroy_job;
 	}
 
-	priority = ivpu_job_to_hws_priority(file_priv, params->priority);
-
 	down_read(&vdev->pm->reset_lock);
-	ret = ivpu_job_submit(job, priority);
+	ret = ivpu_job_submit(job, priority, cmdq_id);
 	up_read(&vdev->pm->reset_lock);
 	if (ret)
 		goto err_signal_fence;
@@ -748,12 +839,137 @@ err_free_handles:
 	return ret;
 }
 
+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_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;
+
+	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;
+	}
+
+	mutex_unlock(&file_priv->lock);
+
+	/* Abort any pending jobs only if cmdq was destroyed */
+	if (!ret)
+		ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
+
+	ivpu_rpm_put(vdev);
+
+	return ret;
+}
+
 static void
 ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 		       struct vpu_jsm_msg *jsm_msg)
 {
 	struct vpu_ipc_msg_payload_job_done *payload;
-	int ret;
 
 	if (!jsm_msg) {
 		ivpu_err(vdev, "IPC message has no JSM payload\n");
@@ -766,9 +982,10 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 	}
 
 	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
-	ret = ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
-	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
-		ivpu_start_job_timeout_detection(vdev);
+
+	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_consumer_init(struct ivpu_device *vdev)
@@ -781,3 +998,57 @@ 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 6accb94028c7..2e301c2eea7b 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -28,8 +28,10 @@ struct ivpu_cmdq {
 	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;
 };
 
 /**
@@ -49,6 +51,7 @@ struct ivpu_job {
 	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;
@@ -56,14 +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_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);
 
 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 46ef16c3c069..0256b2dfefc1 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -7,6 +7,8 @@
 #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)
 {
@@ -48,9 +50,10 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	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);
+	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);
@@ -131,7 +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;
@@ -154,15 +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;
 }
@@ -173,7 +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;
@@ -196,7 +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);
@@ -270,9 +275,8 @@ int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev)
 
 	req.payload.pwr_d0i3_enter.send_response = 1;
 
-	ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE,
-					   &resp, VPU_IPC_CHAN_GEN_CMD,
-					   vdev->timeout.d0i3_entry_msg);
+	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;
 
@@ -346,15 +350,17 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine >= VPU_ENGINE_NB)
+	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)
+	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;
 }
@@ -394,8 +400,6 @@ int ivpu_jsm_hws_set_scheduling_log(struct ivpu_device *vdev, u32 engine_idx, u3
 	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;
-	req.payload.hws_set_scheduling_log.enable_extra_events =
-		ivpu_test_mode & IVPU_TEST_MODE_HWS_EXTRA_EVENTS;
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
@@ -409,29 +413,21 @@ 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;
 
-	/* Idle */
-	req.payload.hws_priority_band_setup.grace_period[0] = 0;
-	req.payload.hws_priority_band_setup.process_grace_period[0] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[0] = 160000;
-	/* Normal */
-	req.payload.hws_priority_band_setup.grace_period[1] = 50000;
-	req.payload.hws_priority_band_setup.process_grace_period[1] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[1] = 300000;
-	/* Focus */
-	req.payload.hws_priority_band_setup.grace_period[2] = 50000;
-	req.payload.hws_priority_band_setup.process_grace_period[2] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[2] = 200000;
-	/* Realtime */
-	req.payload.hws_priority_band_setup.grace_period[3] = 0;
-	req.payload.hws_priority_band_setup.process_grace_period[3] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[3] = 200000;
-
-	req.payload.hws_priority_band_setup.normal_band_percentage = 10;
-
-	ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP,
-					   &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
+	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);
 
@@ -544,9 +540,8 @@ int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us
 	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_active(vdev, &req, VPU_JSM_MSG_DCT_ENABLE_DONE,
-					    &resp, VPU_IPC_CHAN_ASYNC_CMD,
-					    vdev->timeout.jsm);
+	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)
@@ -554,7 +549,14 @@ 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_active(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE,
-					    &resp, VPU_IPC_CHAN_ASYNC_CMD,
-					    vdev->timeout.jsm);
+	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 e4e42c0ff6e6..9e84d3526a14 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.h
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.h
@@ -43,4 +43,6 @@ int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mas
 				  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 c078e214b221..5ea010568faa 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -20,6 +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
@@ -141,12 +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)
@@ -596,7 +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;
@@ -617,12 +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;
@@ -631,7 +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);
 }
 
@@ -696,7 +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;
@@ -708,30 +708,29 @@ 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]);
@@ -741,8 +740,8 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
 	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)
@@ -750,38 +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;
 }
 
@@ -808,12 +787,6 @@ int ivpu_mmu_init(struct ivpu_device *vdev)
 		return ret;
 	}
 
-	ret = ivpu_mmu_cd_add_gbl(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret);
-		return ret;
-	}
-
 	ret = ivpu_mmu_enable(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to resume MMU: %d\n", ret);
@@ -897,28 +870,107 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	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)
 {
+	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) {
+	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;
 		}
 
-		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
-		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
+		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 (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_MMU_EVTQ))
-		ivpu_err_ratelimited(vdev, "IRQ FIFO full\n");
+	queue_work(system_wq, &vdev->context_abort_work);
 }
 
 void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
@@ -966,12 +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 6fa35c240710..1ce7529746ad 100644
--- a/drivers/accel/ivpu/ivpu_mmu.h
+++ b/drivers/accel/ivpu/ivpu_mmu.h
@@ -40,12 +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 bbe652a7019d..f0267efa55aa 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -90,19 +90,6 @@ static void ivpu_pgtable_free_page(struct ivpu_device *vdev, u64 *cpu_addr, dma_
 	}
 }
 
-static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
-{
-	dma_addr_t pgd_dma;
-
-	pgtable->pgd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pgd_dma);
-	if (!pgtable->pgd_dma_ptr)
-		return -ENOMEM;
-
-	pgtable->pgd_dma = pgd_dma;
-
-	return 0;
-}
-
 static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
 {
 	int pgd_idx, pud_idx, pmd_idx;
@@ -140,6 +127,27 @@ static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgt
 	}
 
 	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*
@@ -237,6 +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;
@@ -418,6 +432,7 @@ 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;
@@ -448,20 +463,36 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		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;
 		}
 		vpu_addr += size;
 	}
 
+	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();
 
-	mutex_unlock(&ctx->lock);
-
 	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;
 }
 
@@ -530,109 +561,77 @@ ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *n
 	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);
 
-	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 7f9aaf3d10c2..f255310968cf 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.h
+++ b/drivers/accel/ivpu/ivpu_mmu_context.h
@@ -23,21 +23,20 @@ struct ivpu_mmu_pgtable {
 };
 
 struct ivpu_mmu_context {
-	struct mutex lock; /* Protects: mm, pgtable */
+	struct mutex lock; /* Protects: mm, pgtable, is_cd_valid */
 	struct drm_mm mm;
 	struct ivpu_mmu_pgtable pgtable;
+	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(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);
diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c
index 2f9d37f5c208..2a043baf10ca 100644
--- a/drivers/accel/ivpu/ivpu_ms.c
+++ b/drivers/accel/ivpu/ivpu_ms.c
@@ -4,6 +4,7 @@
  */
 
 #include <drm/drm_file.h>
+#include <linux/pm_runtime.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_gem.h"
@@ -11,7 +12,7 @@
 #include "ivpu_ms.h"
 #include "ivpu_pm.h"
 
-#define MS_INFO_BUFFER_SIZE	  SZ_16K
+#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
@@ -44,6 +45,10 @@ int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	    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)) {
@@ -96,6 +101,8 @@ err_free_ms:
 	kfree(ms);
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -160,6 +167,10 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 	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);
@@ -187,6 +198,7 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -204,11 +216,17 @@ 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);
@@ -217,6 +235,7 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ms ? 0 : -EINVAL;
 }
 
@@ -281,6 +300,9 @@ unlock:
 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);
 
@@ -293,6 +315,8 @@ void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
 		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)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 59d3170f5e35..475ddc94f1cf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -9,26 +9,34 @@
 #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 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
 
 static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev)
@@ -37,8 +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)
@@ -73,8 +83,8 @@ static int ivpu_resume(struct ivpu_device *vdev)
 	int ret;
 
 retry:
-	pci_restore_state(to_pci_dev(vdev->drm.dev));
 	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) {
@@ -110,40 +120,57 @@ err_power_down:
 	return ret;
 }
 
-static void ivpu_pm_recovery_work(struct work_struct *work)
+static void ivpu_pm_reset_begin(struct ivpu_device *vdev)
 {
-	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;
-
-	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
-
-	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	if (ret)
-		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
-
-	ivpu_fw_log_dump(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_suspend(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
 	ivpu_jobs_abort_all(vdev);
 	ivpu_ms_cleanup_all(vdev);
 
 	ret = ivpu_resume(vdev);
-	if (ret)
+	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);
 
-	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(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};
+
+	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);
+	}
+
+	ivpu_pm_reset_complete(vdev);
+
+	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 }
 
 void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
@@ -155,16 +182,11 @@ void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
 		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_long_wq, &vdev->pm->recovery_work);
+		queue_work(system_unbound_wq, &vdev->pm->recovery_work);
 	}
 }
 
@@ -172,7 +194,30 @@ 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;
+	}
+
+	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");
 }
 
@@ -187,6 +232,7 @@ void ivpu_start_job_timeout_detection(struct ivpu_device *vdev)
 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)
@@ -195,6 +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);
@@ -212,6 +259,7 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	ivpu_pm_prepare_warm_boot(vdev);
 
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
+	trace_pm("suspend done");
 
 	return 0;
 }
@@ -222,6 +270,7 @@ 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");
 
 	ret = ivpu_resume(vdev);
@@ -229,6 +278,7 @@ int ivpu_pm_resume_cb(struct device *dev)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);
 
 	ivpu_dbg(vdev, PM, "Resume done.\n");
+	trace_pm("resume done");
 
 	return ret;
 }
@@ -243,6 +293,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	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");
 
 	ivpu_mmu_disable(vdev);
@@ -262,13 +313,14 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	if (!is_idle || ret_d0i3) {
 		ivpu_err(vdev, "Forcing cold boot due to previous errors\n");
 		atomic_inc(&vdev->pm->reset_counter);
-		ivpu_fw_log_dump(vdev);
+		ivpu_dev_coredump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);
 	}
 
 	ivpu_dbg(vdev, PM, "Runtime suspend done.\n");
+	trace_pm("runtime suspend done");
 
 	return 0;
 }
@@ -279,6 +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);
@@ -286,6 +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;
 }
@@ -295,7 +349,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev)
 	int ret;
 
 	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	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;
 }
@@ -311,16 +368,13 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
-	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->reset_pending, 1);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-	down_write(&vdev->pm->reset_lock);
-	ivpu_prepare_for_reset(vdev);
-	ivpu_hw_reset(vdev);
-	ivpu_pm_prepare_cold_boot(vdev);
-	ivpu_jobs_abort_all(vdev);
-	ivpu_ms_cleanup_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");
 }
@@ -328,18 +382,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 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);
-	up_write(&vdev->pm->reset_lock);
-	atomic_set(&vdev->pm->reset_pending, 0);
-	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
-	pm_runtime_mark_last_busy(vdev->drm.dev);
-	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)
@@ -364,21 +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)
 {
 	drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work));
-	cancel_work_sync(&vdev->pm->recovery_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);
@@ -409,16 +457,17 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent)
 	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, "Filed to enable DCT: %d\n", ret);
+		ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = active_percent;
-
-	ivpu_dbg(vdev, PM, "DCT set to %u%% (D0: %uus, D0i2: %uus)\n",
-		 active_percent, active_us, inactive_us);
 	return 0;
 }
 
@@ -426,27 +475,29 @@ 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, "Filed to disable DCT: %d\n", ret);
+		ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = 0;
-
-	ivpu_dbg(vdev, PM, "DCT disabled\n");
 	return 0;
 }
 
-void ivpu_pm_dct_irq_thread_handler(struct ivpu_device *vdev)
+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 (vdev->pm->dct_active_percent)
+	if (enable)
 		ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT);
 	else
 		ret = ivpu_pm_dct_disable(vdev);
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index b70efe6c36e4..a2aa7a27f32e 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -25,7 +25,7 @@ struct ivpu_pm_info {
 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);
@@ -45,6 +45,6 @@ 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_dct_irq_thread_handler(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
index 913669f1786e..268ab7744a8b 100644
--- a/drivers/accel/ivpu/ivpu_sysfs.c
+++ b/drivers/accel/ivpu/ivpu_sysfs.c
@@ -1,15 +1,22 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2024 Intel Corporation
+ * 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.
  *
@@ -28,19 +35,112 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b
 	struct ivpu_device *vdev = to_ivpu_device(drm);
 	ktime_t total, now = 0;
 
-	xa_lock(&vdev->submitted_jobs_xa);
+	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);
-	xa_unlock(&vdev->submitted_jobs_xa);
+	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,
 };
 
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 82954b91b748..218468bbbcad 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -1,14 +1,13 @@
 /* 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
@@ -27,19 +26,18 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 24
+#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 0
+#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, 4)
 
@@ -78,8 +76,15 @@ struct vpu_firmware_header {
 	 * 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[6];
+	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 */
@@ -136,7 +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
@@ -164,8 +169,6 @@ enum vpu_trace_destination {
 /* 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
-#define VPU_TRACE_PROC_BIT_KMB_FIRST  VPU_TRACE_PROC_BIT_30XX_FIRST
-#define VPU_TRACE_PROC_BIT_KMB_LAST   VPU_TRACE_PROC_BIT_30XX_LAST
 
 struct vpu_boot_l2_cache_config {
 	u8 use;
@@ -199,6 +202,17 @@ struct vpu_warm_boot_section {
  */
 #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;
@@ -301,7 +315,14 @@ struct vpu_boot_params {
 	u32 temp_sensor_period_ms;
 	/** PLL ratio for efficient clock frequency */
 	u32 pn_freq_pll_ratio;
-	/** DVFS Mode: Default: 0, Max Performance: 1, On Demand: 2, Power Save: 3 */
+	/**
+	 * 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:
@@ -332,8 +353,8 @@ struct vpu_boot_params {
 	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.
+	 * 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.
 	 */
@@ -382,10 +403,7 @@ struct vpu_boot_params {
 	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 */
@@ -405,7 +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 33f462b1a25d..4b6b2b3d2583 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -22,7 +22,7 @@
 /*
  * Minor version changes when API backward compatibility is preserved.
  */
-#define VPU_JSM_API_VER_MINOR 16
+#define VPU_JSM_API_VER_MINOR 29
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -36,7 +36,7 @@
 
 /*
  * 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
 
@@ -53,8 +53,7 @@
  * 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.
@@ -74,6 +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.
@@ -86,18 +86,60 @@
 /*
  * Job flags bit masks.
  */
-#define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001
-#define VPU_JOB_FLAGS_PRIVATE_DATA_MASK	   0xFF000000
+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.
+ * Job queue flags bit masks.
  */
-#define VPU_JOB_RESERVED_BYTES 8
+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),
 
-/*
- * Sizes of the reserved areas in job queues, in bytes.
- */
-#define VPU_JOB_QUEUE_RESERVED_BYTES 52
+	/*
+	 * 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
@@ -141,23 +183,114 @@
 #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 primary_preempt_buf_addr;
+	/**< 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 */
-	u32 primary_preempt_buf_size;
+	u64 primary_preempt_buf_addr;
 	/**< Size of the primary preemption buffer to use for this job */
-	u32 secondary_preempt_buf_size;
+	u32 primary_preempt_buf_size;
 	/**< Size of secondary preemption buffer to use for this job */
-	u64 secondary_preempt_buf_addr;
+	u32 secondary_preempt_buf_size;
 	/**< Address of secondary preemption buffer to use for this job */
-	u8 reserved_0[VPU_JOB_RESERVED_BYTES];
+	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;
 };
 
 /*
@@ -167,7 +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];
 };
 
 /*
@@ -175,7 +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[];
 };
 
 /**
@@ -197,9 +344,7 @@ enum vpu_trace_entity_type {
 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 overwrites the 0th entry;
-	 * initialised by host to 0.
-	 */
+	/* 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.
@@ -230,14 +375,80 @@ struct vpu_hws_log_buffer_entry {
 	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,
@@ -323,9 +534,10 @@ enum vpu_ipc_msg_type {
 	 * 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`.
@@ -335,8 +547,12 @@ enum vpu_ipc_msg_type {
 	 * 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,
@@ -422,6 +638,7 @@ enum vpu_ipc_msg_type {
 	 * 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,
@@ -577,12 +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;
@@ -600,11 +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;
@@ -622,6 +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;
@@ -700,11 +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 {
 	/*
@@ -715,6 +947,7 @@ 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).
 	 */
 	u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
@@ -727,8 +960,10 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	 * 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;
 };
 
 /*
@@ -794,7 +1029,10 @@ 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;
@@ -802,7 +1040,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
 	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;
@@ -869,9 +1110,7 @@ struct vpu_ipc_msg_payload_hws_set_scheduling_log {
 	 */
 	u64 notify_index;
 	/*
-	 * Enable extra events to be output to log for debug of scheduling algorithm.
-	 * Interpreted by VPU as a boolean to enable or disable, expected values are
-	 * 0 and 1.
+	 * Field is now deprecated, will be removed when KMD is updated to support removal
 	 */
 	u32 enable_extra_events;
 	/* Zero Padding */
@@ -1243,10 +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;
@@ -1254,7 +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;
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 35e883515629..1106b876f737 100644
--- a/drivers/accel/qaic/Makefile
+++ b/drivers/accel/qaic/Makefile
@@ -10,6 +10,7 @@ qaic-y := \
 	qaic_control.o \
 	qaic_data.o \
 	qaic_drv.o \
+	qaic_ras.o \
 	qaic_timesync.o \
 	sahara.o
 
diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index ada9b1eb0787..13a14c6c6168 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -20,6 +20,11 @@ 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 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",
@@ -405,6 +410,329 @@ static const struct mhi_channel_config aic100_channels[] = {
 		.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_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 = 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[] = {
@@ -422,16 +750,44 @@ 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)
@@ -513,8 +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, bool shared_msi)
+						    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;
 
@@ -549,11 +906,18 @@ struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, voi
 	if (shared_msi) /* MSI shared with data path, no IRQF_NO_SUSPEND */
 		mhi_cntrl->irq_flags = IRQF_SHARED;
 
-	mhi_cntrl->fw_image = "qcom/aic100/sbl.bin";
+	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 500e7f4af2af..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, bool shared_msi);
+						    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 02561b6cecc6..c31081e42cee 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -32,6 +32,12 @@
 #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,
@@ -113,10 +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 */
@@ -161,6 +167,14 @@ struct qaic_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 {
@@ -207,8 +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;
 	/*
diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 9e8a8cbadf6b..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) {
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index e86e71c1cdd8..797289e9d780 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -172,9 +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 */
@@ -182,9 +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)
@@ -221,7 +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;
@@ -301,7 +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);
@@ -554,6 +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++) {
@@ -563,7 +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;
 	}
 
@@ -604,7 +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)) {
@@ -625,7 +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 {
@@ -726,7 +731,6 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	if (ret)
 		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);
@@ -865,7 +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);
@@ -889,7 +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);
diff --git a/drivers/accel/qaic/qaic_debugfs.c b/drivers/accel/qaic/qaic_debugfs.c
index 20b653d99e52..a991b8198dc4 100644
--- a/drivers/accel/qaic/qaic_debugfs.c
+++ b/drivers/accel/qaic/qaic_debugfs.c
@@ -64,20 +64,9 @@ static int bootlog_show(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int bootlog_fops_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bootlog_show, inode->i_private);
-}
-
-static const struct file_operations bootlog_fops = {
-	.owner = THIS_MODULE,
-	.open = bootlog_fops_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bootlog);
 
-static int read_dbc_fifo_size(struct seq_file *s, void *unused)
+static int fifo_size_show(struct seq_file *s, void *unused)
 {
 	struct dma_bridge_chan *dbc = s->private;
 
@@ -85,20 +74,9 @@ static int read_dbc_fifo_size(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int fifo_size_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, read_dbc_fifo_size, inode->i_private);
-}
-
-static const struct file_operations fifo_size_fops = {
-	.owner = THIS_MODULE,
-	.open = fifo_size_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(fifo_size);
 
-static int read_dbc_queued(struct seq_file *s, void *unused)
+static int queued_show(struct seq_file *s, void *unused)
 {
 	struct dma_bridge_chan *dbc = s->private;
 	u32 tail = 0, head = 0;
@@ -115,18 +93,7 @@ static int read_dbc_queued(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int queued_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, read_dbc_queued, inode->i_private);
-}
-
-static const struct file_operations queued_fops = {
-	.owner = THIS_MODULE,
-	.open = queued_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(queued);
 
 void qaic_debugfs_init(struct qaic_drm_device *qddev)
 {
@@ -273,7 +240,6 @@ static int qaic_bootlog_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_d
 mhi_unprepare:
 	mhi_unprepare_from_transfer(mhi_dev);
 destroy_workqueue:
-	flush_workqueue(qdev->bootlog_wq);
 	destroy_workqueue(qdev->bootlog_wq);
 out:
 	return ret;
@@ -286,7 +252,6 @@ static void qaic_bootlog_mhi_remove(struct mhi_device *mhi_dev)
 	qdev = dev_get_drvdata(&mhi_dev->dev);
 
 	mhi_unprepare_from_transfer(qdev->bootlog_ch);
-	flush_workqueue(qdev->bootlog_wq);
 	destroy_workqueue(qdev->bootlog_wq);
 	qdev->bootlog_ch = NULL;
 }
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 580b29ed1902..e31bcb0ecfc9 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -29,17 +29,52 @@
 #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");
@@ -53,12 +88,12 @@ static void qaicm_wq_release(struct drm_device *dev, void *res)
 	destroy_workqueue(wq);
 }
 
-static struct workqueue_struct *qaicm_wq_init(struct drm_device *dev, const char *fmt)
+static struct workqueue_struct *qaicm_wq_init(struct drm_device *dev, const char *name)
 {
 	struct workqueue_struct *wq;
 	int ret;
 
-	wq = alloc_workqueue(fmt, WQ_UNBOUND, 0);
+	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);
@@ -207,7 +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,
@@ -352,7 +386,8 @@ void qaic_dev_reset_clean_local_state(struct qaic_device *qdev)
 		release_dbc(qdev, i);
 }
 
-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;
@@ -365,12 +400,10 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de
 		return NULL;
 
 	qdev->dev_state = QAIC_OFFLINE;
-	if (id->device == PCI_DEV_AIC100) {
-		qdev->num_dbc = 16;
-		qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL);
-		if (!qdev->dbc)
-			return NULL;
-	}
+	qdev->num_dbc = 16;
+	qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL);
+	if (!qdev->dbc)
+		return NULL;
 
 	qddev = devm_drm_dev_alloc(&pdev->dev, &qaic_accel_driver, struct qaic_drm_device, drm);
 	if (IS_ERR(qddev))
@@ -426,17 +459,18 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de
 	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;
 	}
 
@@ -447,17 +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);
@@ -467,14 +499,15 @@ 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, 32, 32, PCI_IRQ_MSI);
+	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);
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_MSIX);
 		if (ret < 0)
 			return ret;
 
@@ -487,7 +520,8 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 		 * interrupted, it shouldn't race with itself.
 		 */
 		qdev->single_msi = true;
-		pci_info(pdev, "Allocating 32 MSIs failed, operating in 1 MSI mode. Performance may be impacted.\n");
+		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;
 	}
@@ -517,21 +551,22 @@ 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)
 		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)
@@ -541,8 +576,8 @@ static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		return ret;
 
-	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq,
-						       qdev->single_msi);
+	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);
 		qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
@@ -609,7 +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);
@@ -659,6 +696,10 @@ static int __init qaic_init(void)
 	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:
@@ -686,6 +727,7 @@ 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();
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
index 301f4462d51b..3fac540f8e03 100644
--- a/drivers/accel/qaic/qaic_timesync.c
+++ b/drivers/accel/qaic/qaic_timesync.c
@@ -129,7 +129,7 @@ static void qaic_timesync_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_resu
 
 static void qaic_timesync_timer(struct timer_list *t)
 {
-	struct mqts_dev *mqtsdev = from_timer(mqtsdev, t, timer);
+	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;
@@ -201,7 +201,7 @@ static int qaic_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_devi
 		goto free_sync_msg;
 
 	/* Qtimer register pointer */
-	mqtsdev->qtimer_addr = qdev->bar_0 + QTIMER_REG_OFFSET;
+	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);
@@ -221,7 +221,7 @@ static void qaic_timesync_remove(struct mhi_device *mhi_dev)
 {
 	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
 
-	del_timer_sync(&mqtsdev->timer);
+	timer_delete_sync(&mqtsdev->timer);
 	mhi_unprepare_from_transfer(mqtsdev->mhi_dev);
 	kfree(mqtsdev->sync_msg);
 	kfree(mqtsdev);
diff --git a/drivers/accel/qaic/sahara.c b/drivers/accel/qaic/sahara.c
index bf94bbab6be5..3ebcc1f7ff58 100644
--- a/drivers/accel/qaic/sahara.c
+++ b/drivers/accel/qaic/sahara.c
@@ -2,6 +2,7 @@
 
 /* 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>
@@ -9,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/overflow.h>
 #include <linux/types.h>
+#include <linux/vmalloc.h>
 #include <linux/workqueue.h>
 
 #include "sahara.h"
@@ -36,12 +38,14 @@
 
 #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
@@ -53,6 +57,8 @@
 #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;
@@ -80,21 +86,98 @@ struct sahara_packet {
 			__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		work;
+	struct work_struct		fw_work;
+	struct work_struct		dump_work;
 	struct mhi_device		*mhi_dev;
-	const char			**image_table;
+	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 *aic100_image_table[] = {
+static const char * const aic100_image_table[] = {
 	[1]  = "qcom/aic100/fw1.bin",
 	[2]  = "qcom/aic100/fw2.bin",
 	[4]  = "qcom/aic100/fw4.bin",
@@ -105,6 +188,34 @@ static const char *aic100_image_table[] = {
 	[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;
@@ -153,6 +264,8 @@ 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);
 
@@ -186,7 +299,8 @@ static void sahara_hello(struct sahara_context *context)
 	}
 
 	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_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;
@@ -320,9 +434,70 @@ static void sahara_end_of_image(struct sahara_context *context)
 		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, work);
+	struct sahara_context *context = container_of(work, struct sahara_context, fw_work);
 	int ret;
 
 	switch (le32_to_cpu(context->rx->cmd)) {
@@ -338,6 +513,12 @@ static void sahara_processing(struct work_struct *work)
 	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));
@@ -350,6 +531,217 @@ static void sahara_processing(struct work_struct *work)
 		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;
@@ -382,9 +774,17 @@ static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_
 	}
 
 	context->mhi_dev = mhi_dev;
-	INIT_WORK(&context->work, sahara_processing);
-	context->image_table = aic100_image_table;
-	context->table_size = ARRAY_SIZE(aic100_image_table);
+	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);
 
@@ -405,7 +805,9 @@ static void sahara_mhi_remove(struct mhi_device *mhi_dev)
 {
 	struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev);
 
-	cancel_work_sync(&context->work);
+	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);
 }
@@ -418,8 +820,14 @@ static void sahara_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result
 {
 	struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev);
 
-	if (!mhi_result->transaction_status)
-		schedule_work(&context->work);
+	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[] = {
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/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 f677ad2177c2..e68cf1d83787 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -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/synth.c b/drivers/accessibility/speakup/synth.c
index 85062e605d79..d8addbf3ad0d 100644
--- a/drivers/accessibility/speakup/synth.c
+++ b/drivers/accessibility/speakup/synth.c
@@ -521,7 +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 e3a7c2aedd5f..ca00a5dbcf75 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -132,8 +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
 
@@ -385,6 +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.
@@ -433,7 +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
@@ -443,7 +453,7 @@ 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
@@ -451,7 +461,7 @@ config ACPI_HED
 
 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
@@ -537,6 +547,10 @@ if ARM64
 source "drivers/acpi/arm64/Kconfig"
 endif
 
+if RISCV
+source "drivers/acpi/riscv/Kconfig"
+endif
+
 config ACPI_PPTT
 	bool
 
@@ -567,6 +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 61ca4afe83dc..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
 #
@@ -41,7 +45,7 @@ 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-$(CONFIG_ACPI_MCFG)		+= pci_mcfg.o
@@ -62,6 +66,7 @@ acpi-$(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
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index eaa70b23dd0b..1f69be8f51a2 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -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);
 
@@ -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_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 ca87a0939135..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>
@@ -234,7 +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;
@@ -251,6 +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;
@@ -268,6 +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 */
@@ -279,6 +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 */
@@ -300,6 +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;
diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c
index 794962c5c88e..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,
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 350d3a892889..c9a0bcaba2e4 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -19,6 +19,7 @@
 #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>
 
@@ -32,7 +33,7 @@
 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;
@@ -46,10 +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))
@@ -136,8 +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 */
@@ -428,8 +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);
@@ -460,7 +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 9916cc7ced39..7ec1dc04fd11 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -275,7 +275,7 @@ 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;
@@ -436,8 +436,8 @@ 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);
@@ -815,7 +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.
@@ -985,7 +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;
 
@@ -994,5 +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 b831cb8e53dc..33418dd6768a 100644
--- a/drivers/acpi/acpi_tad.c
+++ b/drivers/acpi/acpi_tad.c
@@ -233,7 +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);
 }
@@ -428,7 +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);
@@ -565,6 +565,9 @@ static void 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);
 
@@ -684,7 +687,7 @@ static struct platform_driver acpi_tad_driver = {
 		.acpi_match_table = acpi_tad_ids,
 	},
 	.probe = acpi_tad_probe,
-	.remove_new = acpi_tad_remove,
+	.remove = acpi_tad_remove,
 };
 MODULE_DEVICE_TABLE(acpi, acpi_tad_ids);
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 8274a17872ed..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"
@@ -610,16 +611,28 @@ 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, int 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;
 
@@ -636,16 +649,24 @@ acpi_video_device_EDID(struct acpi_video_device *device,
 
 	obj = buffer.pointer;
 
-	if (obj && obj->type == ACPI_TYPE_BUFFER)
-		*edid = obj;
-	else {
+	/*
+	 * 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);
-		status = -EFAULT;
-		kfree(obj);
+		ret = -EFAULT;
 	}
 
-	return status;
+	kfree(buffer.pointer);
+	return ret;
 }
 
 /* bus */
@@ -1435,9 +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;
@@ -1477,16 +1496,10 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id,
 		}
 
 		for (length = 512; length > 0; length -= 128) {
-			status = acpi_video_device_EDID(video_device, &buffer,
-							length);
-			if (ACPI_SUCCESS(status))
-				break;
+			ret = acpi_video_device_EDID(video_device, edid, length);
+			if (ret > 0)
+				return ret;
 		}
-		if (!length)
-			continue;
-
-		*edid = buffer->buffer.pointer;
-		return length;
 	}
 
 	return -ENODEV;
@@ -2034,9 +2047,9 @@ static int acpi_video_bus_add(struct acpi_device *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);
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 2133085deda7..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.
  *
  *****************************************************************************/
 
@@ -188,13 +188,9 @@ 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);
 
-void
-acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node,
-				  acpi_adr_space_type space_id);
-
 acpi_status
 acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);
 
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 02012168a087..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;
@@ -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 8fc02946d3cd..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.
  *
  *****************************************************************************/
 
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