KVM: x86: fix TRACE_INCLUDE_PATH and remove -I. header search paths

The header search path -I. in kernel Makefiles is very suspicious; it allows the compiler to search for headers in the top of $(srctree), where obviously no header file exists. The reason of having -I. here is to make the incorrectly set TRACE_INCLUDE_PATH working. As the comment block in include/trace/define_trace.h says, TRACE_INCLUDE_PATH should be a relative path to the define_trace.h Fix the TRACE_INCLUDE_PATH, and remove the iffy include paths. Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
author: Masahiro Yamada <yamada.masahiro@socionext.com> 2019-01-25 16:32:46 +0900
committer: Paolo Bonzini <pbonzini@redhat.com> 2019-01-25 19:12:37 +0100
commit: 5cd5548ff439b916cf72448109994394c2bf4b3c (patch)
tree: cf7edbe7a691111e86b5fcaea9f08ea64f3026cb /tools/perf/scripts/python/stackcollapse.py
parent: 35b531a1e7fc30ac8c62e5ac1794eb1460da614e (diff)
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 45d1c3e630f7..8e1ffa4358d5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -135,6 +135,7 @@ obj-y				+= ufs/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
 obj-$(CONFIG_INFINIBAND)	+= infiniband/
 obj-y				+= firmware/
+obj-$(CONFIG_FWCTL)		+= fwctl/
 obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
 obj-y				+= clocksource/
@@ -160,7 +161,7 @@ obj-$(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/
@@ -194,4 +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 5b9490367a39..bb01cebc42bf 100644
--- a/drivers/accel/Kconfig
+++ b/drivers/accel/Kconfig
@@ -28,5 +28,6 @@ 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 a301fb6089d4..ffc3fa588666 100644
--- a/drivers/accel/Makefile
+++ b/drivers/accel/Makefile
@@ -4,3 +4,4 @@ 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/Makefile b/drivers/accel/amdxdna/Makefile
index 0e9adf6890a0..6797dac65efa 100644
--- a/drivers/accel/amdxdna/Makefile
+++ b/drivers/accel/amdxdna/Makefile
@@ -15,6 +15,7 @@ amdxdna-y := \
 	amdxdna_mailbox_helper.o \
 	amdxdna_pci_drv.o \
 	amdxdna_sysfs.o \
+	amdxdna_ubuf.o \
 	npu1_regs.o \
 	npu2_regs.o \
 	npu4_regs.o \
diff --git a/drivers/accel/amdxdna/TODO b/drivers/accel/amdxdna/TODO
index 5119bccd1917..ad8ac6e315b6 100644
--- a/drivers/accel/amdxdna/TODO
+++ b/drivers/accel/amdxdna/TODO
@@ -1,3 +1,2 @@
-- Add import and export BO support
 - Add debugfs support
 - Add debug BO support
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 5f43db02b240..e9f9b1fa5dc1 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -34,6 +34,8 @@ static void aie2_job_release(struct kref *ref)
 
 	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);
@@ -44,6 +46,17 @@ 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)
@@ -87,25 +100,6 @@ out:
 	return ret;
 }
 
-void aie2_restart_ctx(struct amdxdna_client *client)
-{
-	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_hwctx *hwctx;
-	unsigned long hwctx_id;
-
-	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
-	mutex_lock(&client->hwctx_lock);
-	amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
-		if (hwctx->status != HWCTX_STAT_STOP)
-			continue;
-
-		hwctx->status = hwctx->old_status;
-		XDNA_DBG(xdna, "Resetting %s", hwctx->name);
-		aie2_hwctx_restart(xdna, hwctx);
-	}
-	mutex_unlock(&client->hwctx_lock);
-}
-
 static struct dma_fence *aie2_cmd_get_out_fence(struct amdxdna_hwctx *hwctx, u64 seq)
 {
 	struct dma_fence *fence, *out_fence = NULL;
@@ -134,38 +128,54 @@ static void aie2_hwctx_wait_for_idle(struct amdxdna_hwctx *hwctx)
 	if (!fence)
 		return;
 
-	dma_fence_wait(fence, false);
+	/* 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);
 }
 
-void aie2_hwctx_suspend(struct amdxdna_hwctx *hwctx)
+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));
-	aie2_hwctx_wait_for_idle(hwctx);
-	aie2_hwctx_stop(xdna, hwctx, NULL);
-	hwctx->old_status = hwctx->status;
-	hwctx->status = HWCTX_STAT_STOP;
+	amdxdna_hwctx_walk(client, NULL, aie2_hwctx_suspend_cb);
 }
 
-void aie2_hwctx_resume(struct amdxdna_hwctx *hwctx)
+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));
-	hwctx->status = hwctx->old_status;
-	aie2_hwctx_restart(xdna, hwctx);
+	return amdxdna_hwctx_walk(client, NULL, aie2_hwctx_resume_cb);
 }
 
 static void
@@ -185,11 +195,11 @@ aie2_sched_notify(struct amdxdna_sched_job *job)
 }
 
 static int
-aie2_sched_resp_handler(void *handle, const u32 *data, size_t size)
+aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
 {
 	struct amdxdna_sched_job *job = handle;
 	struct amdxdna_gem_obj *cmd_abo;
-	u32 ret = 0;
+	int ret = 0;
 	u32 status;
 
 	cmd_abo = job->cmd_bo;
@@ -203,7 +213,7 @@ aie2_sched_resp_handler(void *handle, const u32 *data, size_t size)
 		goto out;
 	}
 
-	status = *data;
+	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);
@@ -216,10 +226,10 @@ out:
 }
 
 static int
-aie2_sched_nocmd_resp_handler(void *handle, const u32 *data, size_t size)
+aie2_sched_nocmd_resp_handler(void *handle, void __iomem *data, size_t size)
 {
 	struct amdxdna_sched_job *job = handle;
-	u32 ret = 0;
+	int ret = 0;
 	u32 status;
 
 	if (unlikely(!data))
@@ -230,7 +240,7 @@ aie2_sched_nocmd_resp_handler(void *handle, const u32 *data, size_t size)
 		goto out;
 	}
 
-	status = *data;
+	status = readl(data);
 	XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status);
 
 out:
@@ -239,15 +249,15 @@ out:
 }
 
 static int
-aie2_sched_cmdlist_resp_handler(void *handle, const u32 *data, size_t size)
+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 cmd_chain_resp *resp;
 	struct amdxdna_dev *xdna;
 	u32 fail_cmd_status;
 	u32 fail_cmd_idx;
-	u32 ret = 0;
+	u32 cmd_status;
+	int ret = 0;
 
 	cmd_abo = job->cmd_bo;
 	if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) {
@@ -256,17 +266,17 @@ aie2_sched_cmdlist_resp_handler(void *handle, const u32 *data, size_t size)
 		goto out;
 	}
 
-	resp = (struct cmd_chain_resp *)data;
+	cmd_status = readl(data + offsetof(struct cmd_chain_resp, status));
 	xdna = job->hwctx->client->xdna;
-	XDNA_DBG(xdna, "Status 0x%x", resp->status);
-	if (resp->status == AIE2_STATUS_SUCCESS) {
+	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 = resp->fail_cmd_idx;
-	fail_cmd_status = resp->fail_cmd_status;
+	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);
 
@@ -358,10 +368,10 @@ aie2_sched_job_timedout(struct drm_sched_job *sched_job)
 	aie2_hwctx_restart(xdna, hwctx);
 	mutex_unlock(&xdna->dev_lock);
 
-	return DRM_GPU_SCHED_STAT_NOMINAL;
+	return DRM_GPU_SCHED_STAT_RESET;
 }
 
-const struct drm_sched_backend_ops sched_ops = {
+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,
@@ -516,6 +526,14 @@ 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;
@@ -555,7 +573,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx)
 			.size = MAX_CHAIN_CMDBUF_SIZE,
 		};
 
-		abo = amdxdna_drm_alloc_dev_bo(&xdna->ddev, &args, client->filp, true);
+		abo = amdxdna_drm_alloc_dev_bo(&xdna->ddev, &args, client->filp);
 		if (IS_ERR(abo)) {
 			ret = PTR_ERR(abo);
 			goto free_cmd_bufs;
@@ -573,9 +591,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx)
 	might_lock(&priv->io_lock);
 	fs_reclaim_release(GFP_KERNEL);
 
-	ret = drm_sched_init(sched, &sched_ops, NULL, DRM_SCHED_PRIORITY_COUNT,
-			     HWCTX_MAX_CMDS, 0, msecs_to_jiffies(HWCTX_MAX_TIMEOUT),
-			     NULL, NULL, hwctx->name, xdna->ddev.dev);
+	ret = drm_sched_init(sched, &args);
 	if (ret) {
 		XDNA_ERR(xdna, "Failed to init DRM scheduler. ret %d", ret);
 		goto free_cmd_bufs;
@@ -616,6 +632,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx)
 	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);
 
@@ -652,25 +669,23 @@ void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx)
 	xdna = hwctx->client->xdna;
 	ndev = xdna->dev_handle;
 	ndev->hwctx_num--;
-	drm_sched_wqueue_stop(&hwctx->priv->sched);
 
-	/* Now, scheduler will not send command to device. */
+	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);
 
-	/*
-	 * All submitted commands are aborted.
-	 * Restart scheduler queues to cleanup jobs. The amdxdna_sched_job_run()
-	 * will return NODEV if it is called.
-	 */
-	drm_sched_wqueue_start(&hwctx->priv->sched);
+	/* 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));
 
-	aie2_hwctx_wait_for_idle(hwctx);
-	drm_sched_entity_destroy(&hwctx->priv->entity);
 	drm_sched_fini(&hwctx->priv->sched);
 	aie2_ctx_syncobj_destroy(hwctx);
 
-	XDNA_DBG(xdna, "%s sequence number %lld", hwctx->name, hwctx->priv->seq);
-
 	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);
@@ -750,27 +765,42 @@ int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *bu
 static int aie2_populate_range(struct amdxdna_gem_obj *abo)
 {
 	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
-	struct mm_struct *mm = abo->mem.notifier.mm;
-	struct hmm_range range = { 0 };
+	struct amdxdna_umap *mapp;
 	unsigned long timeout;
+	struct mm_struct *mm;
+	bool found;
 	int ret;
 
-	XDNA_INFO_ONCE(xdna, "populate memory range %llx size %lx",
-		       abo->mem.userptr, abo->mem.size);
-	range.notifier = &abo->mem.notifier;
-	range.start = abo->mem.userptr;
-	range.end = abo->mem.userptr + abo->mem.size;
-	range.hmm_pfns = abo->mem.pfns;
-	range.default_flags = HMM_PFN_REQ_FAULT;
+	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);
 
-	if (!mmget_not_zero(mm))
+	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;
+	}
 
-	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
-again:
-	range.notifier_seq = mmu_interval_read_begin(&abo->mem.notifier);
+	mapp->range.notifier_seq = mmu_interval_read_begin(&mapp->notifier);
 	mmap_read_lock(mm);
-	ret = hmm_range_fault(&range);
+	ret = hmm_range_fault(&mapp->range);
 	mmap_read_unlock(mm);
 	if (ret) {
 		if (time_after(jiffies, timeout)) {
@@ -778,21 +808,27 @@ again:
 			goto put_mm;
 		}
 
-		if (ret == -EBUSY)
+		if (ret == -EBUSY) {
+			amdxdna_umap_put(mapp);
 			goto again;
+		}
 
 		goto put_mm;
 	}
 
-	down_read(&xdna->notifier_lock);
-	if (mmu_interval_read_retry(&abo->mem.notifier, range.notifier_seq)) {
-		up_read(&xdna->notifier_lock);
+	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;
 	}
-	abo->mem.map_invalid = false;
-	up_read(&xdna->notifier_lock);
+	mapp->invalid = false;
+	up_write(&xdna->notifier_lock);
+	amdxdna_umap_put(mapp);
+	goto again;
 
 put_mm:
+	amdxdna_umap_put(mapp);
 	mmput(mm);
 	return ret;
 }
@@ -819,7 +855,8 @@ int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
 		goto up_sem;
 	}
 
-	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx);
+	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;
@@ -879,6 +916,7 @@ retry:
 	drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx);
 
 	aie2_job_put(job);
+	atomic64_inc(&hwctx->job_submit_cnt);
 
 	return 0;
 
@@ -899,10 +937,6 @@ void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo,
 	struct drm_gem_object *gobj = to_gobj(abo);
 	long ret;
 
-	down_write(&xdna->notifier_lock);
-	abo->mem.map_invalid = true;
-	mmu_interval_set_seq(&abo->mem.notifier, cur_seq);
-	up_write(&xdna->notifier_lock);
 	ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP,
 				    true, MAX_SCHEDULE_TIMEOUT);
 	if (!ret || ret == -ERESTARTSYS)
diff --git a/drivers/accel/amdxdna/aie2_error.c b/drivers/accel/amdxdna/aie2_error.c
index b1defaa8513b..5ee905632a39 100644
--- a/drivers/accel/amdxdna/aie2_error.c
+++ b/drivers/accel/amdxdna/aie2_error.c
@@ -209,16 +209,14 @@ static u32 aie2_error_backtrack(struct amdxdna_dev_hdl *ndev, void *err_info, u3
 	return err_col;
 }
 
-static int aie2_error_async_cb(void *handle, const u32 *data, size_t size)
+static int aie2_error_async_cb(void *handle, void __iomem *data, size_t size)
 {
-	struct async_event_msg_resp *resp;
 	struct async_event *e = handle;
 
 	if (data) {
-		resp = (struct async_event_msg_resp *)data;
-		e->resp.type = resp->type;
+		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 = resp->status;
+		e->resp.status = readl(data + offsetof(struct async_event_msg_resp, status));
 	}
 	queue_work(e->wq, &e->work);
 	return 0;
diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 9e2c9a44f76a..9caad083543d 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -290,18 +290,25 @@ int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u6
 	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;
-	struct amdxdna_hwctx *hwctx;
-	unsigned long hwctx_id;
 	dma_addr_t dma_addr;
 	u32 aie_bitmap = 0;
 	u8 *buff_addr;
-	int ret, idx;
+	int ret;
 
 	buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr,
 					  DMA_FROM_DEVICE, GFP_KERNEL);
@@ -309,12 +316,8 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
 		return -ENOMEM;
 
 	/* Go through each hardware context and mark the AIE columns that are active */
-	list_for_each_entry(client, &xdna->client_list, node) {
-		idx = srcu_read_lock(&client->hwctx_srcu);
-		amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
-			aie_bitmap |= amdxdna_hwctx_col_map(hwctx);
-		srcu_read_unlock(&client->hwctx_srcu, idx);
-	}
+	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;
@@ -356,7 +359,7 @@ fail:
 }
 
 int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size,
-				 void *handle, int (*cb)(void*, const u32 *, size_t))
+				 void *handle, int (*cb)(void*, void __iomem *, size_t))
 {
 	struct async_event_msg_req req = { 0 };
 	struct xdna_mailbox_msg msg = {
@@ -435,7 +438,7 @@ int aie2_config_cu(struct amdxdna_hwctx *hwctx)
 }
 
 int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
-		 int (*notify_cb)(void *, const u32 *, size_t))
+		 int (*notify_cb)(void *, void __iomem *, size_t))
 {
 	struct mailbox_channel *chann = hwctx->priv->mbox_chann;
 	struct amdxdna_dev *xdna = hwctx->client->xdna;
@@ -525,7 +528,7 @@ aie2_cmdlist_fill_one_slot_cf(void *cmd_buf, u32 offset,
 	if (!payload)
 		return -EINVAL;
 
-	if (!slot_cf_has_space(offset, payload_len))
+	if (!slot_has_space(*buf, offset, payload_len))
 		return -ENOSPC;
 
 	buf->cu_idx = cu_idx;
@@ -558,7 +561,7 @@ aie2_cmdlist_fill_one_slot_dpu(void *cmd_buf, u32 offset,
 	if (payload_len < sizeof(*sn) || arg_sz > MAX_DPU_ARGS_SIZE)
 		return -EINVAL;
 
-	if (!slot_dpu_has_space(offset, arg_sz))
+	if (!slot_has_space(*buf, offset, arg_sz))
 		return -ENOSPC;
 
 	buf->inst_buf_addr = sn->buffer;
@@ -569,7 +572,7 @@ aie2_cmdlist_fill_one_slot_dpu(void *cmd_buf, u32 offset,
 	memcpy(buf->args, sn->prop_args, arg_sz);
 
 	/* Accurate buf size to hint firmware to do necessary copy */
-	*size += sizeof(*buf) + arg_sz;
+	*size = sizeof(*buf) + arg_sz;
 	return 0;
 }
 
@@ -640,7 +643,7 @@ aie2_cmd_op_to_msg_op(u32 op)
 
 int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx,
 			       struct amdxdna_sched_job *job,
-			       int (*notify_cb)(void *, const u32 *, size_t))
+			       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;
@@ -705,7 +708,7 @@ int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx,
 
 int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx,
 				struct amdxdna_sched_job *job,
-				int (*notify_cb)(void *, const u32 *, size_t))
+				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;
@@ -740,7 +743,7 @@ int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx,
 }
 
 int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
-		 int (*notify_cb)(void *, const u32 *, size_t))
+		 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]);
diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h b/drivers/accel/amdxdna/aie2_msg_priv.h
index 4e02e744b470..6df9065b13f6 100644
--- a/drivers/accel/amdxdna/aie2_msg_priv.h
+++ b/drivers/accel/amdxdna/aie2_msg_priv.h
@@ -319,18 +319,16 @@ struct async_event_msg_resp {
 } __packed;
 
 #define MAX_CHAIN_CMDBUF_SIZE SZ_4K
-#define slot_cf_has_space(offset, payload_size) \
-	(MAX_CHAIN_CMDBUF_SIZE - ((offset) + (payload_size)) > \
-	 offsetof(struct cmd_chain_slot_execbuf_cf, args[0]))
+#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);
 };
 
-#define slot_dpu_has_space(offset, payload_size) \
-	(MAX_CHAIN_CMDBUF_SIZE - ((offset) + (payload_size)) > \
-	 offsetof(struct cmd_chain_slot_dpu, args[0]))
 struct cmd_chain_slot_dpu {
 	__u64 inst_buf_addr;
 	__u32 inst_size;
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 5a058e565b01..87c425e3d2b9 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -10,6 +10,7 @@
 #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>
@@ -440,6 +441,40 @@ disable_dev:
 	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);
@@ -512,12 +547,6 @@ static int aie2_init(struct amdxdna_dev *xdna)
 		goto release_fw;
 	}
 
-	ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
-	if (ret) {
-		XDNA_ERR(xdna, "Enable PASID failed, ret %d", ret);
-		goto free_irq;
-	}
-
 	psp_conf.fw_size = fw->size;
 	psp_conf.fw_buf = fw->data;
 	for (i = 0; i < PSP_MAX_REGS; i++)
@@ -526,14 +555,14 @@ static int aie2_init(struct amdxdna_dev *xdna)
 	if (!ndev->psp_hdl) {
 		XDNA_ERR(xdna, "failed to create psp");
 		ret = -ENOMEM;
-		goto disable_sva;
+		goto release_fw;
 	}
 	xdna->dev_handle = ndev;
 
 	ret = aie2_hw_start(xdna);
 	if (ret) {
 		XDNA_ERR(xdna, "start npu failed, ret %d", ret);
-		goto disable_sva;
+		goto release_fw;
 	}
 
 	ret = aie2_mgmt_fw_query(ndev);
@@ -584,10 +613,6 @@ async_event_free:
 	aie2_error_async_events_free(ndev);
 stop_hw:
 	aie2_hw_stop(xdna);
-disable_sva:
-	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
-free_irq:
-	pci_free_irq_vectors(pdev);
 release_fw:
 	release_firmware(fw);
 
@@ -596,13 +621,10 @@ release_fw:
 
 static void aie2_fini(struct amdxdna_dev *xdna)
 {
-	struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
 	struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
 
 	aie2_hw_stop(xdna);
 	aie2_error_async_events_free(ndev);
-	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
-	pci_free_irq_vectors(pdev);
 }
 
 static int aie2_get_aie_status(struct amdxdna_client *client,
@@ -761,65 +783,68 @@ static int aie2_get_clock_metadata(struct amdxdna_client *client,
 	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_query_hwctx __user *buf;
+	struct amdxdna_drm_get_array array_args;
 	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_drm_query_hwctx *tmp;
 	struct amdxdna_client *tmp_client;
-	struct amdxdna_hwctx *hwctx;
-	unsigned long hwctx_id;
-	bool overflow = false;
-	u32 req_bytes = 0;
-	u32 hw_i = 0;
-	int ret = 0;
-	int idx;
+	int ret;
 
 	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
 
-	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	buf = u64_to_user_ptr(args->buffer);
+	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) {
-		idx = srcu_read_lock(&tmp_client->hwctx_srcu);
-		amdxdna_for_each_hwctx(tmp_client, hwctx_id, hwctx) {
-			req_bytes += sizeof(*tmp);
-			if (args->buffer_size < req_bytes) {
-				/* Continue iterating to get the required size */
-				overflow = true;
-				continue;
-			}
-
-			memset(tmp, 0, sizeof(*tmp));
-			tmp->pid = tmp_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;
-
-			if (copy_to_user(&buf[hw_i], tmp, sizeof(*tmp))) {
-				ret = -EFAULT;
-				srcu_read_unlock(&tmp_client->hwctx_srcu, idx);
-				goto out;
-			}
-			hw_i++;
-		}
-		srcu_read_unlock(&tmp_client->hwctx_srcu, idx);
+		ret = amdxdna_hwctx_walk(tmp_client, &array_args,
+					 aie2_hwctx_status_cb);
+		if (ret)
+			break;
 	}
 
-	if (overflow) {
-		XDNA_ERR(xdna, "Invalid buffer size. Given: %u Need: %u.",
-			 args->buffer_size, req_bytes);
-		ret = -EINVAL;
-	}
-
-out:
-	kfree(tmp);
-	args->buffer_size = req_bytes;
+	args->buffer_size -= (u32)(array_args.buffer - args->buffer);
 	return ret;
 }
 
@@ -863,6 +888,58 @@ static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_i
 	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)
 {
@@ -912,17 +989,16 @@ static int aie2_set_state(struct amdxdna_client *client,
 }
 
 const struct amdxdna_dev_ops aie2_ops = {
-	.init           = aie2_init,
-	.fini           = aie2_fini,
-	.resume         = aie2_hw_start,
-	.suspend        = aie2_hw_stop,
-	.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,
+	.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,
-	.hwctx_suspend  = aie2_hwctx_suspend,
-	.hwctx_resume   = aie2_hwctx_resume,
+	.get_array = aie2_get_array,
 };
diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h
index f2d95531ddc2..91a8e948f82a 100644
--- a/drivers/accel/amdxdna/aie2_pci.h
+++ b/drivers/accel/amdxdna/aie2_pci.h
@@ -271,27 +271,26 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc
 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*, const u32 *, size_t));
+				 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 *, const u32 *, size_t));
+		 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 *, const u32 *, size_t));
+				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 *, const u32 *, size_t));
+			       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 *, const u32 *, size_t));
+		 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_hwctx *hwctx);
-void aie2_hwctx_resume(struct amdxdna_hwctx *hwctx);
+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);
-void aie2_restart_ctx(struct amdxdna_client *client);
 
 #endif /* _AIE2_PCI_H_ */
diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c
index dc3a072ce3b6..f28a060a8810 100644
--- a/drivers/accel/amdxdna/aie2_psp.c
+++ b/drivers/accel/amdxdna/aie2_psp.c
@@ -126,8 +126,8 @@ struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *
 	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_ALIGN;
-	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz, GFP_KERNEL);
+	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;
diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c
index 73388443c676..d303701b0ded 100644
--- a/drivers/accel/amdxdna/aie2_smu.c
+++ b/drivers/accel/amdxdna/aie2_smu.c
@@ -64,6 +64,7 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
 	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;
 
@@ -72,6 +73,7 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
 	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;
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
index d11b1c83d9c3..4bfe4ef20550 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -60,32 +60,6 @@ static struct dma_fence *amdxdna_fence_create(struct amdxdna_hwctx *hwctx)
 	return &fence->base;
 }
 
-void amdxdna_hwctx_suspend(struct amdxdna_client *client)
-{
-	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_hwctx *hwctx;
-	unsigned long hwctx_id;
-
-	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
-	mutex_lock(&client->hwctx_lock);
-	amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
-		xdna->dev_info->ops->hwctx_suspend(hwctx);
-	mutex_unlock(&client->hwctx_lock);
-}
-
-void amdxdna_hwctx_resume(struct amdxdna_client *client)
-{
-	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_hwctx *hwctx;
-	unsigned long hwctx_id;
-
-	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
-	mutex_lock(&client->hwctx_lock);
-	amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
-		xdna->dev_info->ops->hwctx_resume(hwctx);
-	mutex_unlock(&client->hwctx_lock);
-}
-
 static void amdxdna_hwctx_destroy_rcu(struct amdxdna_hwctx *hwctx,
 				      struct srcu_struct *ss)
 {
@@ -94,14 +68,30 @@ static void amdxdna_hwctx_destroy_rcu(struct amdxdna_hwctx *hwctx,
 	synchronize_srcu(ss);
 
 	/* At this point, user is not able to submit new commands */
-	mutex_lock(&xdna->dev_lock);
 	xdna->dev_info->ops->hwctx_fini(hwctx);
-	mutex_unlock(&xdna->dev_lock);
 
 	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;
@@ -152,16 +142,12 @@ void amdxdna_hwctx_remove_all(struct amdxdna_client *client)
 	struct amdxdna_hwctx *hwctx;
 	unsigned long hwctx_id;
 
-	mutex_lock(&client->hwctx_lock);
 	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);
-		mutex_unlock(&client->hwctx_lock);
 		amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu);
-		mutex_lock(&client->hwctx_lock);
 	}
-	mutex_unlock(&client->hwctx_lock);
 }
 
 int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
@@ -220,6 +206,8 @@ int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
 	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;
@@ -249,6 +237,7 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d
 	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;
@@ -265,6 +254,7 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d
 
 	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;
 }
@@ -494,11 +484,11 @@ 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;
+	u32 *arg_bo_hdls = NULL;
 	u32 cmd_bo_hdl;
 	int ret;
 
-	if (!args->arg_count || args->arg_count > MAX_ARG_COUNT) {
+	if (args->arg_count > MAX_ARG_COUNT) {
 		XDNA_ERR(xdna, "Invalid arg bo count %d", args->arg_count);
 		return -EINVAL;
 	}
@@ -510,14 +500,16 @@ static int amdxdna_drm_submit_execbuf(struct amdxdna_client *client,
 	}
 
 	cmd_bo_hdl = (u32)args->cmd_handles;
-	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;
+	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,
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h
index 80b0304193ec..7cd7a55936f0 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.h
+++ b/drivers/accel/amdxdna/amdxdna_ctx.h
@@ -87,6 +87,9 @@ struct amdxdna_hwctx {
 	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) \
@@ -136,16 +139,10 @@ amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo)
 void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size);
 int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo);
 
-static inline u32 amdxdna_hwctx_col_map(struct amdxdna_hwctx *hwctx)
-{
-	return GENMASK(hwctx->start_col + hwctx->num_col - 1,
-		       hwctx->start_col);
-}
-
 void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job);
 void amdxdna_hwctx_remove_all(struct amdxdna_client *client);
-void amdxdna_hwctx_suspend(struct amdxdna_client *client);
-void amdxdna_hwctx_resume(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,
diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c
index 606433d73236..d407a36eb412 100644
--- a/drivers/accel/amdxdna/amdxdna_gem.c
+++ b/drivers/accel/amdxdna/amdxdna_gem.c
@@ -9,103 +9,129 @@
 #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_insert_node_locked(struct amdxdna_gem_obj *abo, bool use_vmap)
+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(&abo->dev_heap->mm, &abo->mm_node,
+	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);
-		return ret;
+		goto unlock_out;
 	}
 
 	mem->dev_addr = abo->mm_node.start;
-	offset = mem->dev_addr - abo->dev_heap->mem.dev_addr;
-	mem->userptr = abo->dev_heap->mem.userptr + offset;
-	mem->pages = &abo->dev_heap->base.pages[offset >> PAGE_SHIFT];
-	mem->nr_pages = mem->size >> PAGE_SHIFT;
-
-	if (use_vmap) {
-		mem->kva = vmap(mem->pages, mem->nr_pages, VM_MAP, PAGE_KERNEL);
-		if (!mem->kva) {
-			XDNA_ERR(xdna, "Failed to vmap");
-			drm_mm_remove_node(&abo->mm_node);
-			return -EFAULT;
-		}
-	}
+	offset = mem->dev_addr - heap->mem.dev_addr;
+	mem->userptr = heap->mem.userptr + offset;
+	mem->kva = heap->mem.kva + offset;
 
-	return 0;
+	drm_gem_object_get(to_gobj(heap));
+
+unlock_out:
+	mutex_unlock(&client->mm_lock);
+
+	return ret;
 }
 
-static void amdxdna_gem_obj_free(struct drm_gem_object *gobj)
+static void
+amdxdna_gem_destroy_obj(struct amdxdna_gem_obj *abo)
 {
-	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);
+	mutex_destroy(&abo->lock);
+	kfree(abo);
+}
 
-	XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr);
-	if (abo->pinned)
-		amdxdna_gem_unpin(abo);
+static void
+amdxdna_gem_heap_free(struct amdxdna_gem_obj *abo)
+{
+	struct amdxdna_gem_obj *heap;
 
-	if (abo->type == AMDXDNA_BO_DEV) {
-		mutex_lock(&abo->client->mm_lock);
-		drm_mm_remove_node(&abo->mm_node);
-		mutex_unlock(&abo->client->mm_lock);
+	mutex_lock(&abo->client->mm_lock);
 
-		vunmap(abo->mem.kva);
-		drm_gem_object_put(to_gobj(abo->dev_heap));
-		drm_gem_object_release(gobj);
-		mutex_destroy(&abo->lock);
-		kfree(abo);
-		return;
-	}
+	drm_mm_remove_node(&abo->mm_node);
 
-	if (abo->type == AMDXDNA_BO_DEV_HEAP)
-		drm_mm_takedown(&abo->mm);
+	heap = abo->client->dev_heap;
+	drm_gem_object_put(to_gobj(heap));
 
-	drm_gem_vunmap_unlocked(gobj, &map);
-	mutex_destroy(&abo->lock);
-	drm_gem_shmem_free(&abo->base);
+	mutex_unlock(&abo->client->mm_lock);
 }
 
-static const struct drm_gem_object_funcs amdxdna_gem_dev_obj_funcs = {
-	.free = amdxdna_gem_obj_free,
-};
-
 static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni,
 				   const struct mmu_notifier_range *range,
 				   unsigned long cur_seq)
 {
-	struct amdxdna_gem_obj *abo = container_of(mni, struct amdxdna_gem_obj,
-						   mem.notifier);
-	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
+	struct amdxdna_umap *mapp = container_of(mni, struct amdxdna_umap, notifier);
+	struct amdxdna_gem_obj *abo = mapp->abo;
+	struct amdxdna_dev *xdna;
 
-	XDNA_DBG(xdna, "Invalid range 0x%llx, 0x%lx, type %d",
-		 abo->mem.userptr, abo->mem.size, abo->type);
+	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;
 }
 
@@ -113,102 +139,348 @@ static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = {
 	.invalidate = amdxdna_hmm_invalidate,
 };
 
-static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo)
+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);
+}
 
-	if (!xdna->dev_info->ops->hmm_invalidate)
-		return;
+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(&abo->mem.notifier);
-	kvfree(abo->mem.pfns);
-	abo->mem.pfns = NULL;
+	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 int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, unsigned long addr,
-				size_t len)
+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;
 
-	if (abo->mem.pfns)
-		return -EEXIST;
+	mapp = kzalloc(sizeof(*mapp), GFP_KERNEL);
+	if (!mapp)
+		return -ENOMEM;
 
 	nr_pages = (PAGE_ALIGN(addr + len) - (addr & PAGE_MASK)) >> PAGE_SHIFT;
-	abo->mem.pfns = kvcalloc(nr_pages, sizeof(*abo->mem.pfns),
-				 GFP_KERNEL);
-	if (!abo->mem.pfns)
-		return -ENOMEM;
+	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(&abo->mem.notifier,
+	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);
-		kvfree(abo->mem.pfns);
+		goto free_pfns;
 	}
-	abo->mem.userptr = addr;
 
+	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);
-	unsigned long num_pages;
 	int ret;
 
-	ret = amdxdna_hmm_register(abo, vma->vm_start, gobj->size);
+	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 hmm_unreg;
+		goto put_obj;
 
-	num_pages = gobj->size >> PAGE_SHIFT;
-	/* Try to insert the pages */
+	/* 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);
+	ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages,
+			      &num_pages);
 	if (ret)
-		XDNA_ERR(abo->client->xdna, "Failed insert pages, ret %d", ret);
+		goto close_vma;
 
 	return 0;
 
-hmm_unreg:
-	amdxdna_hmm_unregister(abo);
+close_vma:
+	vma->vm_ops->close(vma);
+put_obj:
+	drm_gem_object_put(gobj);
 	return ret;
 }
 
-static vm_fault_t amdxdna_gem_vm_fault(struct vm_fault *vmf)
+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)
 {
-	return drm_gem_shmem_vm_ops.fault(vmf);
+	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_gem_vm_open(struct vm_area_struct *vma)
+static void amdxdna_imported_obj_free(struct amdxdna_gem_obj *abo)
 {
-	drm_gem_shmem_vm_ops.open(vma);
+	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_vm_close(struct vm_area_struct *vma)
+static void amdxdna_gem_obj_free(struct drm_gem_object *gobj)
 {
-	struct drm_gem_object *gobj = vma->vm_private_data;
+	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);
 
-	amdxdna_hmm_unregister(to_xdna_obj(gobj));
-	drm_gem_shmem_vm_ops.close(vma);
+	if (is_import_bo(abo)) {
+		amdxdna_imported_obj_free(abo);
+		return;
+	}
+
+	drm_gem_shmem_free(&abo->base);
 }
 
-static const struct vm_operations_struct amdxdna_gem_vm_ops = {
-	.fault = amdxdna_gem_vm_fault,
-	.open = amdxdna_gem_vm_open,
-	.close = amdxdna_gem_vm_close,
+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 = {
@@ -217,10 +489,11 @@ static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = {
 	.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,
+	.vmap = amdxdna_gem_obj_vmap,
+	.vunmap = amdxdna_gem_obj_vunmap,
 	.mmap = amdxdna_gem_obj_mmap,
-	.vm_ops = &amdxdna_gem_vm_ops,
+	.vm_ops = &drm_gem_shmem_vm_ops,
+	.export = amdxdna_gem_prime_export,
 };
 
 static struct amdxdna_gem_obj *
@@ -239,6 +512,7 @@ amdxdna_gem_create_obj(struct drm_device *dev, size_t size)
 	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;
 }
@@ -259,21 +533,124 @@ amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size)
 }
 
 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 drm_gem_shmem_object *shmem;
 	struct amdxdna_gem_obj *abo;
 
-	shmem = drm_gem_shmem_create(dev, args->size);
-	if (IS_ERR(shmem))
-		return ERR_CAST(shmem);
-
-	shmem->map_wc = false;
+	abo = amdxdna_gem_create_object(dev, args);
+	if (IS_ERR(abo))
+		return ERR_CAST(abo);
 
-	abo = to_xdna_obj(&shmem->base);
 	abo->client = client;
 	abo->type = AMDXDNA_BO_SHMEM;
 
@@ -286,8 +663,8 @@ amdxdna_drm_create_dev_heap(struct drm_device *dev,
 			    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 drm_gem_shmem_object *shmem;
 	struct amdxdna_gem_obj *abo;
 	int ret;
 
@@ -304,26 +681,32 @@ amdxdna_drm_create_dev_heap(struct drm_device *dev,
 		goto mm_unlock;
 	}
 
-	shmem = drm_gem_shmem_create(dev, args->size);
-	if (IS_ERR(shmem)) {
-		ret = PTR_ERR(shmem);
+	abo = amdxdna_gem_create_object(dev, args);
+	if (IS_ERR(abo)) {
+		ret = PTR_ERR(abo);
 		goto mm_unlock;
 	}
 
-	shmem->map_wc = false;
-	abo = to_xdna_obj(&shmem->base);
-
 	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);
@@ -332,58 +715,32 @@ mm_unlock:
 struct amdxdna_gem_obj *
 amdxdna_drm_alloc_dev_bo(struct drm_device *dev,
 			 struct amdxdna_drm_create_bo *args,
-			 struct drm_file *filp, bool use_vmap)
+			 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, *heap;
+	struct amdxdna_gem_obj *abo;
 	int ret;
 
-	mutex_lock(&client->mm_lock);
-	heap = client->dev_heap;
-	if (!heap) {
-		ret = -EINVAL;
-		goto mm_unlock;
-	}
-
-	if (heap->mem.userptr == AMDXDNA_INVALID_ADDR) {
-		XDNA_ERR(xdna, "Invalid dev heap userptr");
-		ret = -EINVAL;
-		goto mm_unlock;
-	}
-
-	if (args->size > heap->mem.size) {
-		XDNA_ERR(xdna, "Invalid dev bo size 0x%llx, limit 0x%lx",
-			 args->size, heap->mem.size);
-		ret = -EINVAL;
-		goto mm_unlock;
-	}
-
 	abo = amdxdna_gem_create_obj(&xdna->ddev, aligned_sz);
-	if (IS_ERR(abo)) {
-		ret = PTR_ERR(abo);
-		goto mm_unlock;
-	}
+	if (IS_ERR(abo))
+		return abo;
+
 	to_gobj(abo)->funcs = &amdxdna_gem_dev_obj_funcs;
 	abo->type = AMDXDNA_BO_DEV;
 	abo->client = client;
-	abo->dev_heap = heap;
-	ret = amdxdna_gem_insert_node_locked(abo, use_vmap);
+
+	ret = amdxdna_gem_heap_alloc(abo);
 	if (ret) {
 		XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret);
-		goto mm_unlock;
+		amdxdna_gem_destroy_obj(abo);
+		return ERR_PTR(ret);
 	}
 
-	drm_gem_object_get(to_gobj(heap));
 	drm_gem_private_object_init(&xdna->ddev, to_gobj(abo), aligned_sz);
 
-	mutex_unlock(&client->mm_lock);
 	return abo;
-
-mm_unlock:
-	mutex_unlock(&client->mm_lock);
-	return ERR_PTR(ret);
 }
 
 static struct amdxdna_gem_obj *
@@ -391,10 +748,9 @@ 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 drm_gem_shmem_object *shmem;
 	struct amdxdna_gem_obj *abo;
-	struct iosys_map map;
 	int ret;
 
 	if (args->size > XDNA_MAX_CMD_BO_SIZE) {
@@ -407,17 +763,14 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	shmem = drm_gem_shmem_create(dev, args->size);
-	if (IS_ERR(shmem))
-		return ERR_CAST(shmem);
-
-	shmem->map_wc = false;
-	abo = to_xdna_obj(&shmem->base);
+	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_unlocked(to_gobj(abo), &map);
+	ret = drm_gem_vmap(to_gobj(abo), &map);
 	if (ret) {
 		XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret);
 		goto release_obj;
@@ -427,7 +780,7 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev,
 	return abo;
 
 release_obj:
-	drm_gem_shmem_free(shmem);
+	drm_gem_object_put(to_gobj(abo));
 	return ERR_PTR(ret);
 }
 
@@ -438,7 +791,7 @@ int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_f
 	struct amdxdna_gem_obj *abo;
 	int ret;
 
-	if (args->flags || args->vaddr || !args->size)
+	if (args->flags)
 		return -EINVAL;
 
 	XDNA_DBG(xdna, "BO arg type %d vaddr 0x%llx size 0x%llx flags 0x%llx",
@@ -451,7 +804,7 @@ int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_f
 		abo = amdxdna_drm_create_dev_heap(dev, args, filp);
 		break;
 	case AMDXDNA_BO_DEV:
-		abo = amdxdna_drm_alloc_dev_bo(dev, args, filp, false);
+		abo = amdxdna_drm_alloc_dev_bo(dev, args, filp);
 		break;
 	case AMDXDNA_BO_CMD:
 		abo = amdxdna_drm_create_cmd_bo(dev, args, filp);
@@ -483,17 +836,13 @@ int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo)
 	struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev);
 	int ret;
 
-	switch (abo->type) {
-	case AMDXDNA_BO_SHMEM:
-	case AMDXDNA_BO_DEV_HEAP:
-		ret = drm_gem_shmem_pin(&abo->base);
-		break;
-	case AMDXDNA_BO_DEV:
-		ret = drm_gem_shmem_pin(&abo->dev_heap->base);
-		break;
-	default:
-		ret = -EOPNOTSUPP;
-	}
+	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;
@@ -503,9 +852,6 @@ int amdxdna_gem_pin(struct amdxdna_gem_obj *abo)
 {
 	int ret;
 
-	if (abo->type == AMDXDNA_BO_DEV)
-		abo = abo->dev_heap;
-
 	mutex_lock(&abo->lock);
 	ret = amdxdna_gem_pin_nolock(abo);
 	mutex_unlock(&abo->lock);
@@ -516,7 +862,10 @@ int amdxdna_gem_pin(struct amdxdna_gem_obj *abo)
 void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo)
 {
 	if (abo->type == AMDXDNA_BO_DEV)
-		abo = abo->dev_heap;
+		abo = abo->client->dev_heap;
+
+	if (is_import_bo(abo))
+		return;
 
 	mutex_lock(&abo->lock);
 	drm_gem_shmem_unpin(&abo->base);
@@ -606,10 +955,14 @@ int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev,
 		goto put_obj;
 	}
 
-	if (abo->type == AMDXDNA_BO_DEV)
-		drm_clflush_pages(abo->mem.pages, abo->mem.nr_pages);
-	else
+	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);
 
diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h
index 8ccc0375dd9d..ae29db94a9d3 100644
--- a/drivers/accel/amdxdna/amdxdna_gem.h
+++ b/drivers/accel/amdxdna/amdxdna_gem.h
@@ -6,6 +6,20 @@
 #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;
@@ -13,8 +27,7 @@ struct amdxdna_mem {
 	size_t				size;
 	struct page			**pages;
 	u32				nr_pages;
-	struct mmu_interval_notifier	notifier;
-	unsigned long			*pfns;
+	struct list_head		umap_list;
 	bool				map_invalid;
 };
 
@@ -28,12 +41,14 @@ struct amdxdna_gem_obj {
 
 	/* Below members is uninitialized when needed */
 	struct drm_mm			mm; /* For AMDXDNA_BO_DEV_HEAP */
-	struct amdxdna_gem_obj		*dev_heap; /* For AMDXDNA_BO_DEV */
 	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)
 {
@@ -47,12 +62,16 @@ 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, bool use_vmap);
+			 struct drm_file *filp);
 
 int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo);
 int amdxdna_gem_pin(struct amdxdna_gem_obj *abo);
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
index 814b16bb1953..da1ac89bb78f 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 #define CREATE_TRACE_POINTS
@@ -90,7 +91,7 @@ struct mailbox_pkg {
 
 struct mailbox_msg {
 	void			*handle;
-	int			(*notify_cb)(void *handle, const u32 *data, size_t size);
+	int			(*notify_cb)(void *handle, void __iomem *data, size_t size);
 	size_t			pkg_size; /* package size in bytes */
 	struct mailbox_pkg	pkg;
 };
@@ -243,7 +244,7 @@ no_space:
 
 static int
 mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *header,
-		 void *data)
+		 void __iomem *data)
 {
 	struct mailbox_msg *mb_msg;
 	int msg_id;
@@ -331,7 +332,7 @@ static int mailbox_get_msg(struct mailbox_channel *mb_chann)
 	memcpy_fromio((u32 *)&header + 1, read_addr, rest);
 	read_addr += rest;
 
-	ret = mailbox_get_resp(mb_chann, &header, (u32 *)read_addr);
+	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. */
@@ -348,8 +349,6 @@ static irqreturn_t mailbox_irq_handler(int irq, void *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);
-	/* Clear IOHUB register */
-	mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0);
 
 	return IRQ_HANDLED;
 }
@@ -366,6 +365,9 @@ static void mailbox_rx_worker(struct work_struct *rx_work)
 		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
@@ -379,10 +381,18 @@ static void mailbox_rx_worker(struct work_struct *rx_work)
 		if (unlikely(ret)) {
 			MB_ERR(mb_chann, "Unexpected ret %d, disable irq", ret);
 			WRITE_ONCE(mb_chann->bad_state, true);
-			disable_irq(mb_chann->msix_irq);
-			break;
+			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,
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h
index 57954c303bdd..ea367f2fb738 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.h
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.h
@@ -25,7 +25,7 @@ struct mailbox_channel;
 struct xdna_mailbox_msg {
 	u32		opcode;
 	void		*handle;
-	int		(*notify_cb)(void *handle, const u32 *data, size_t size);
+	int		(*notify_cb)(void *handle, void __iomem *data, size_t size);
 	u8		*send_data;
 	size_t		send_size;
 };
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c
index 5139a9c96a91..6d0c24513476 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c
@@ -16,7 +16,7 @@
 #include "amdxdna_mailbox_helper.h"
 #include "amdxdna_pci_drv.h"
 
-int xdna_msg_cb(void *handle, const u32 *data, size_t size)
+int xdna_msg_cb(void *handle, void __iomem *data, size_t size)
 {
 	struct xdna_notify *cb_arg = handle;
 	int ret;
@@ -29,9 +29,9 @@ int xdna_msg_cb(void *handle, const u32 *data, size_t size)
 		goto out;
 	}
 
+	memcpy_fromio(cb_arg->data, data, cb_arg->size);
 	print_hex_dump_debug("resp data: ", DUMP_PREFIX_OFFSET,
-			     16, 4, data, cb_arg->size, true);
-	memcpy(cb_arg->data, data, cb_arg->size);
+			     16, 4, cb_arg->data, cb_arg->size, true);
 out:
 	ret = cb_arg->error;
 	complete(&cb_arg->comp);
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.h b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h
index 23e1317b79fe..710ff8873d61 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox_helper.h
+++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h
@@ -35,7 +35,7 @@ struct xdna_notify {
 		.notify_cb = xdna_msg_cb,				\
 	}
 
-int xdna_msg_cb(void *handle, const u32 *data, size_t size);
+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);
 
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index f5b8497cf5ad..569cd703729d 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -27,6 +27,13 @@ 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.
@@ -81,7 +88,6 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp)
 		ret = -ENODEV;
 		goto unbind_sva;
 	}
-	mutex_init(&client->hwctx_lock);
 	init_srcu_struct(&client->hwctx_srcu);
 	xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC);
 	mutex_init(&client->mm_lock);
@@ -116,7 +122,6 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp)
 
 	xa_destroy(&client->hwctx_xa);
 	cleanup_srcu_struct(&client->hwctx_srcu);
-	mutex_destroy(&client->hwctx_lock);
 	mutex_destroy(&client->mm_lock);
 	if (client->dev_heap)
 		drm_gem_object_put(to_gobj(client->dev_heap));
@@ -142,8 +147,8 @@ static int amdxdna_flush(struct file *f, fl_owner_t id)
 
 	mutex_lock(&xdna->dev_lock);
 	list_del_init(&client->node);
-	mutex_unlock(&xdna->dev_lock);
 	amdxdna_hwctx_remove_all(client);
+	mutex_unlock(&xdna->dev_lock);
 
 	drm_dev_exit(idx);
 	return 0;
@@ -166,6 +171,23 @@ static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct
 	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;
@@ -197,6 +219,7 @@ static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = {
 	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),
 };
 
@@ -220,12 +243,15 @@ const struct drm_driver amdxdna_drm_drv = {
 	.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 *
@@ -266,12 +292,16 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		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);
-		return ret;
+		goto destroy_notifier_wq;
 	}
 
 	ret = amdxdna_sysfs_init(xdna);
@@ -301,6 +331,8 @@ 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;
 }
 
@@ -310,6 +342,8 @@ static void amdxdna_remove(struct pci_dev *pdev)
 	struct device *dev = &pdev->dev;
 	struct amdxdna_client *client;
 
+	destroy_workqueue(xdna->notifier_wq);
+
 	pm_runtime_get_noresume(dev);
 	pm_runtime_forbid(dev);
 
@@ -321,11 +355,8 @@ static void amdxdna_remove(struct pci_dev *pdev)
 					  struct amdxdna_client, node);
 	while (client) {
 		list_del_init(&client->node);
-		mutex_unlock(&xdna->dev_lock);
-
 		amdxdna_hwctx_remove_all(client);
 
-		mutex_lock(&xdna->dev_lock);
 		client = list_first_entry_or_null(&xdna->client_list,
 						  struct amdxdna_client, node);
 	}
@@ -334,89 +365,29 @@ static void amdxdna_remove(struct pci_dev *pdev)
 	mutex_unlock(&xdna->dev_lock);
 }
 
-static int amdxdna_dev_suspend_nolock(struct amdxdna_dev *xdna)
-{
-	if (xdna->dev_info->ops->suspend)
-		xdna->dev_info->ops->suspend(xdna);
-
-	return 0;
-}
-
-static int amdxdna_dev_resume_nolock(struct amdxdna_dev *xdna)
-{
-	if (xdna->dev_info->ops->resume)
-		return xdna->dev_info->ops->resume(xdna);
-
-	return 0;
-}
-
 static int amdxdna_pmops_suspend(struct device *dev)
 {
 	struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev));
-	struct amdxdna_client *client;
-
-	mutex_lock(&xdna->dev_lock);
-	list_for_each_entry(client, &xdna->client_list, node)
-		amdxdna_hwctx_suspend(client);
 
-	amdxdna_dev_suspend_nolock(xdna);
-	mutex_unlock(&xdna->dev_lock);
+	if (!xdna->dev_info->ops->suspend)
+		return -EOPNOTSUPP;
 
-	return 0;
+	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));
-	struct amdxdna_client *client;
-	int ret;
-
-	XDNA_INFO(xdna, "firmware resuming...");
-	mutex_lock(&xdna->dev_lock);
-	ret = amdxdna_dev_resume_nolock(xdna);
-	if (ret) {
-		XDNA_ERR(xdna, "resume NPU firmware failed");
-		mutex_unlock(&xdna->dev_lock);
-		return ret;
-	}
-
-	XDNA_INFO(xdna, "hardware context resuming...");
-	list_for_each_entry(client, &xdna->client_list, node)
-		amdxdna_hwctx_resume(client);
-	mutex_unlock(&xdna->dev_lock);
-
-	return 0;
-}
-
-static int amdxdna_rpmops_suspend(struct device *dev)
-{
-	struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev));
-	int ret;
-
-	mutex_lock(&xdna->dev_lock);
-	ret = amdxdna_dev_suspend_nolock(xdna);
-	mutex_unlock(&xdna->dev_lock);
-
-	XDNA_DBG(xdna, "Runtime suspend done ret: %d", ret);
-	return ret;
-}
-
-static int amdxdna_rpmops_resume(struct device *dev)
-{
-	struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev));
-	int ret;
 
-	mutex_lock(&xdna->dev_lock);
-	ret = amdxdna_dev_resume_nolock(xdna);
-	mutex_unlock(&xdna->dev_lock);
+	if (!xdna->dev_info->ops->resume)
+		return -EOPNOTSUPP;
 
-	XDNA_DBG(xdna, "Runtime resume done ret: %d", ret);
-	return ret;
+	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_rpmops_suspend, amdxdna_rpmops_resume, NULL)
+	RUNTIME_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume, NULL)
 };
 
 static struct pci_driver amdxdna_pci_driver = {
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
index 37848a8d8031..72d6696d49da 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -6,6 +6,7 @@
 #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)
@@ -49,16 +50,15 @@ struct amdxdna_dev_ops {
 	int (*init)(struct amdxdna_dev *xdna);
 	void (*fini)(struct amdxdna_dev *xdna);
 	int (*resume)(struct amdxdna_dev *xdna);
-	void (*suspend)(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);
-	void (*hwctx_suspend)(struct amdxdna_hwctx *hwctx);
-	void (*hwctx_resume)(struct amdxdna_hwctx *hwctx);
 	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);
 };
 
 /*
@@ -98,6 +98,7 @@ struct amdxdna_dev {
 	struct list_head		client_list;
 	struct amdxdna_fw_ver		fw_ver;
 	struct rw_semaphore		notifier_lock; /* for mmu notifier*/
+	struct workqueue_struct		*notifier_wq;
 };
 
 /*
@@ -116,8 +117,6 @@ struct amdxdna_device_id {
 struct amdxdna_client {
 	struct list_head		node;
 	pid_t				pid;
-	struct mutex			hwctx_lock; /* protect hwctx */
-	/* do NOT wait this srcu when hwctx_lock is held */
 	struct srcu_struct		hwctx_srcu;
 	struct xarray			hwctx_xa;
 	u32				next_hwctxid;
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/drm_accel.c b/drivers/accel/drm_accel.c
index aa826033b0ce..ca3357acd127 100644
--- a/drivers/accel/drm_accel.c
+++ b/drivers/accel/drm_accel.c
@@ -20,8 +20,6 @@
 
 DEFINE_XARRAY_ALLOC(accel_minors_xa);
 
-static struct dentry *accel_debugfs_root;
-
 static const struct device_type accel_sysfs_device_minor = {
 	.name = "accel_minor"
 };
@@ -74,17 +72,6 @@ static const struct drm_info_list accel_debugfs_list[] = {
 #define ACCEL_DEBUGFS_ENTRIES ARRAY_SIZE(accel_debugfs_list)
 
 /**
- * accel_debugfs_init() - Initialize debugfs for device
- * @dev: Pointer to the device instance.
- *
- * This function creates a root directory for the device in debugfs.
- */
-void accel_debugfs_init(struct drm_device *dev)
-{
-	drm_debugfs_dev_init(dev, accel_debugfs_root);
-}
-
-/**
  * accel_debugfs_register() - Register debugfs for device
  * @dev: Pointer to the device instance.
  *
@@ -194,7 +181,6 @@ 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();
 	WARN_ON(!xa_empty(&accel_minors_xa));
 }
@@ -209,8 +195,6 @@ int __init accel_core_init(void)
 		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/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 30277ae410d4..999c92d7036e 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -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 596c52e8aa26..0035748f3228 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -386,7 +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 8729a0c57d78..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;
 	}
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 601fdbe70179..633db4bff46f 100644
--- a/drivers/accel/habanalabs/common/memory.c
+++ b/drivers/accel/habanalabs/common/memory.c
@@ -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/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 8180b95ed69d..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>
@@ -331,7 +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");
@@ -382,7 +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)
@@ -397,6 +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;
@@ -419,6 +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);
@@ -430,4 +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 38cf1c342c72..3289751b4757 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,12 +1,13 @@
 // 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>
@@ -36,8 +37,6 @@
 #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.");
@@ -128,20 +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)
@@ -167,7 +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);
@@ -201,7 +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;
@@ -310,6 +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)
@@ -374,6 +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));
 
@@ -421,6 +424,9 @@ 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);
 }
@@ -453,7 +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),
@@ -465,54 +471,6 @@ static const struct drm_driver driver = {
 	.major = 1,
 };
 
-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;
-}
-
 static int ivpu_irq_init(struct ivpu_device *vdev)
 {
 	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
@@ -524,12 +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);
 
@@ -614,10 +576,10 @@ 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;
@@ -627,6 +589,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	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;
@@ -711,7 +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);
@@ -738,6 +704,7 @@ static struct pci_device_id ivpu_pci_ids[] = {
 	{ 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 3fdff3f6cffd..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__
@@ -26,6 +26,7 @@
 #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
@@ -58,6 +59,7 @@
 #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
@@ -110,6 +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;
@@ -142,11 +145,17 @@ struct ivpu_device {
 	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;
 
@@ -157,6 +166,7 @@ struct ivpu_device {
 		int boot;
 		int jsm;
 		int tdr;
+		int inference;
 		int autosuspend;
 		int d0i3_entry_msg;
 		int state_dump_msg;
@@ -199,7 +209,11 @@ extern bool ivpu_force_snoop;
 #define IVPU_TEST_MODE_D0I3_MSG_ENABLE    BIT(5)
 #define IVPU_TEST_MODE_MIP_DISABLE        BIT(6)
 #define IVPU_TEST_MODE_DISABLE_TIMEOUTS   BIT(8)
-#define IVPU_TEST_MODE_TURBO		  BIT(9)
+#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);
@@ -208,6 +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)
 {
@@ -228,6 +243,7 @@ static inline int ivpu_hw_ip_gen(struct ivpu_device *vdev)
 	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();
@@ -244,6 +260,7 @@ static inline int ivpu_hw_btrs_gen(struct ivpu_device *vdev)
 		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();
@@ -282,7 +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 6037ec0b3096..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>
@@ -55,18 +55,18 @@ 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, "vpu_50xx.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_v0.0.bin");
-MODULE_FIRMWARE("intel/vpu/vpu_40xx_v0.0.bin");
-MODULE_FIRMWARE("intel/vpu/vpu_50xx_v0.0.bin");
+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)
 {
@@ -145,7 +145,10 @@ ivpu_fw_sched_mode_select(struct ivpu_device *vdev, const struct vpu_firmware_he
 	if (ivpu_sched_mode != IVPU_SCHED_MODE_AUTO)
 		return ivpu_sched_mode;
 
-	return VPU_SCHEDULING_MODE_OS;
+	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)
@@ -230,10 +233,20 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	fw->dvfs_mode = 0;
 
 	fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr);
-	fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
-	fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
 	ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS");
 
+	if (fw_hdr->preemption_buffer_1_max_size)
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_max_size;
+	else
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
+
+	if (fw_hdr->preemption_buffer_2_max_size)
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_max_size;
+	else
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
+	ivpu_dbg(vdev, FW_BOOT, "Preemption buffer sizes: primary %u, secondary %u\n",
+		 fw->primary_preempt_buf_size, fw->secondary_preempt_buf_size);
+
 	if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address,
 								 fw_hdr->ro_section_size,
 								 fw_hdr->image_load_address,
@@ -531,6 +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)
@@ -561,7 +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
@@ -631,6 +645,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 		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 1d0b2bd9d65c..7081913fb0dd 100644
--- a/drivers/accel/ivpu/ivpu_fw.h
+++ b/drivers/accel/ivpu/ivpu_fw.h
@@ -39,12 +39,13 @@ struct ivpu_fw_info {
 	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_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 16178054e629..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;
@@ -406,10 +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 ? bo->ctx->id : 0, 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)
@@ -418,12 +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 4e1054f3466e..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(vdev->platform), vdev->platform);
+	ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n", platform_to_str(platform), platform);
+
+	switch (platform) {
+	case IVPU_PLATFORM_SILICON:
+	case IVPU_PLATFORM_SIMICS:
+	case IVPU_PLATFORM_FPGA:
+	case IVPU_PLATFORM_HSLE:
+		vdev->platform = platform;
+		break;
+
+	default:
+		ivpu_err(vdev, "Invalid platform type: %d\n", platform);
+		break;
+	}
 }
 
 static void wa_init(struct ivpu_device *vdev)
 {
-	vdev->wa.punit_disabled = 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)
@@ -81,19 +94,22 @@ 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 = 10;
+		vdev->timeout.state_dump_msg = 10000;
 	} else if (ivpu_is_simics(vdev)) {
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 10000;
+		vdev->timeout.inference = 300000;
 		vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 100;
 		vdev->timeout.state_dump_msg = 10;
@@ -101,15 +117,36 @@ static void timeouts_init(struct ivpu_device *vdev)
 		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 = 10;
+		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) {
@@ -248,12 +285,18 @@ 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;
 }
 
@@ -285,8 +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
@@ -300,7 +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);
 }
@@ -327,9 +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 fc4dbfc980c8..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;
@@ -45,6 +36,11 @@ struct ivpu_hw_info {
 		u8 pn_ratio;
 		u32 profiling_freq;
 	} pll;
+	struct {
+		u32 grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+	} hws;
 	u32 tile_fuse;
 	u32 sku;
 	u16 config;
@@ -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_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c
index 3212c99f3682..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);
@@ -156,7 +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->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3);
 
 	return 0;
 }
@@ -303,7 +302,7 @@ 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;
 	}
@@ -334,8 +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) {
@@ -573,6 +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)
 {
@@ -582,9 +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));
@@ -630,12 +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",
@@ -718,60 +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)
@@ -888,3 +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 029dd065614b..2bf9882ab52e 100644
--- a/drivers/accel/ivpu/ivpu_hw_ip.c
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -683,6 +683,7 @@ static void pwr_island_delay_set(struct ivpu_device *vdev)
 		return;
 
 	switch (ivpu_device_id(vdev)) {
+	case PCI_DEVICE_ID_WCL:
 	case PCI_DEVICE_ID_PTL_P:
 		post = high ? 18 : 0;
 		post1 = 0;
@@ -968,14 +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);
 }
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 01ebf88fe6ef..5f00809d448a 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -141,7 +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) {
@@ -302,7 +301,8 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req
 	struct ivpu_ipc_consumer cons;
 	int ret;
 
-	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev));
+	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);
 
@@ -459,13 +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;
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index b4dfb504679b..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);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 7149312f16e1..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>
 
@@ -17,6 +18,7 @@
 #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"
@@ -83,23 +85,9 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 	if (!cmdq)
 		return NULL;
 
-	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);
-		goto err_free_cmdq;
-	}
-
-	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_erase_db_xa;
-	}
-
 	cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!cmdq->mem)
-		goto err_erase_cmdq_xa;
+		goto err_free_cmdq;
 
 	ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq);
 	if (ret)
@@ -107,26 +95,91 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 
 	return cmdq;
 
-err_erase_cmdq_xa:
-	xa_erase(&file_priv->cmdq_xa, cmdq->id);
-err_erase_db_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)
 {
@@ -152,6 +205,13 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *
 	struct ivpu_device *vdev = file_priv->vdev;
 	int ret;
 
+	ret = xa_alloc_cyclic(&vdev->db_xa, &cmdq->db_id, NULL, vdev->db_limit, &vdev->db_next,
+			      GFP_KERNEL);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to allocate doorbell ID: %d\n", ret);
+		return ret;
+	}
+
 	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
 		ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->id, cmdq->db_id,
 					       cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
@@ -160,41 +220,36 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *
 					   cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
 
 	if (!ret)
-		ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d\n",
-			 cmdq->db_id, cmdq->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, 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));
-
-	cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem);
-	jobq_header = &cmdq->jobq->header;
-	jobq_header->engine_idx = VPU_ENGINE_COMPUTE;
-	jobq_header->head = 0;
-	jobq_header->tail = 0;
-	if (ivpu_test_mode & IVPU_TEST_MODE_TURBO) {
-		ivpu_dbg(vdev, JOB, "Turbo mode enabled");
-		jobq_header->flags = VPU_JOB_QUEUE_FLAGS_TURBO_MODE;
-	}
-
-	wmb(); /* Flush WC buffer for jobq->header */
+	ivpu_cmdq_jobq_reset(vdev, cmdq->jobq);
 
 	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
-		ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, priority);
+		ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, cmdq->priority);
 		if (ret)
 			return ret;
 	}
@@ -203,58 +258,84 @@ ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u8 prio
 	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->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->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, u8 priority)
+static inline u8 ivpu_job_to_jsm_priority(u8 priority)
+{
+	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 cmdq_id;
-	int ret;
+	unsigned long id;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
-		if (cmdq->priority == priority)
+	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;
-		cmdq->priority = priority;
+		cmdq->is_legacy = true;
 	}
 
-	ret = ivpu_cmdq_init(file_priv, cmdq, priority);
-	if (ret)
+	return cmdq;
+}
+
+static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u32 cmdq_id)
+{
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_cmdq *cmdq;
+
+	lockdep_assert_held(&file_priv->lock);
+
+	cmdq = xa_load(&file_priv->cmdq_xa, cmdq_id);
+	if (!cmdq) {
+		ivpu_warn_ratelimited(vdev, "Failed to find command queue with ID: %u\n", cmdq_id);
 		return NULL;
+	}
 
 	return cmdq;
 }
@@ -266,11 +347,8 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
 
 	lockdep_assert_held(&file_priv->lock);
 
-	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) {
-		xa_erase(&file_priv->cmdq_xa, cmdq_id);
-		ivpu_cmdq_fini(file_priv, cmdq);
-		ivpu_cmdq_free(file_priv, cmdq);
-	}
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_destroy(file_priv, cmdq);
 }
 
 /*
@@ -286,8 +364,10 @@ static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv)
 
 	mutex_lock(&file_priv->lock);
 
-	xa_for_each(&file_priv->cmdq_xa, cmdq_id, 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);
 }
@@ -305,25 +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)
-{
-	struct ivpu_cmdq *cmdq;
-	unsigned long cmdq_id;
-
-	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
-		ivpu_cmdq_fini(file_priv, cmdq);
-}
-
 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->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)
@@ -416,8 +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])
@@ -462,16 +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;
 }
 
@@ -479,6 +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;
@@ -490,13 +589,17 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 	dma_fence_signal(job->done_fence);
 
 	trace_job("done", job);
-	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);
+	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;
 }
 
@@ -505,11 +608,29 @@ 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);
+}
+
+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)
+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;
@@ -521,25 +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(file_priv, 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;
 	}
 
-	xa_lock(&vdev->submitted_jobs_xa);
+	ret = ivpu_cmdq_register(file_priv, cmdq);
+	if (ret) {
+		ivpu_err(vdev, "Failed to register command queue: %d\n", ret);
+		goto err_unlock;
+	}
+
+	job->cmdq_id = cmdq->id;
+
 	is_first_job = xa_empty(&vdev->submitted_jobs_xa);
-	ret = __xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit,
-				&file_priv->job_id_next, GFP_KERNEL);
+	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);
@@ -558,25 +689,25 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 	}
 
 	trace_job("submit", job);
-	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,
+	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;
 }
@@ -585,7 +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;
@@ -647,49 +778,20 @@ unlock_reservations:
 	return ret;
 }
 
-static inline u8 ivpu_job_to_hws_priority(struct ivpu_file_priv *file_priv, u8 priority)
+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)
 {
-	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)
-{
-	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_COMPUTE)
-		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;
@@ -700,27 +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;
@@ -740,12 +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");
@@ -758,9 +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)
@@ -773,3 +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 8b19e3f8b4cf..2e301c2eea7b 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -30,8 +30,8 @@ struct ivpu_cmdq {
 	u32 entry_count;
 	u32 id;
 	u32 db_id;
-	bool db_registered;
 	u8 priority;
+	bool is_legacy;
 };
 
 /**
@@ -51,6 +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;
@@ -58,14 +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 30a40be76930..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)
 {
@@ -162,8 +164,10 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 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;
 }
@@ -353,8 +357,10 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 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;
 }
@@ -407,26 +413,18 @@ 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;
+	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);
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 26ef52fbb93e..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);
 }
 
@@ -725,8 +725,8 @@ static int ivpu_mmu_cdtab_entry_set(struct ivpu_device *vdev, u32 ssid, u64 cd_d
 	cd[2] = 0;
 	cd[3] = 0x0000000000007444;
 
-	/* For global context generate memory fault on VPU */
-	if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
+	/* 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)
@@ -870,28 +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)
diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h
index 7afea9cd8731..1ce7529746ad 100644
--- a/drivers/accel/ivpu/ivpu_mmu.h
+++ b/drivers/accel/ivpu/ivpu_mmu.h
@@ -47,5 +47,7 @@ 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 0af614dfb6f9..f0267efa55aa 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -635,16 +635,3 @@ void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev)
 	ivpu_mmu_cd_clear(vdev, vdev->rctx.id);
 	ivpu_mmu_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);
-}
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.h b/drivers/accel/ivpu/ivpu_mmu_context.h
index 8042fc067062..f255310968cf 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.h
+++ b/drivers/accel/ivpu/ivpu_mmu_context.h
@@ -37,8 +37,6 @@ 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);
 
-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 ffe7b10f8a76..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"
@@ -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 5060c5dd40d1..475ddc94f1cf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -33,6 +33,10 @@ 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)
@@ -44,6 +48,7 @@ static void ivpu_pm_prepare_cold_boot(struct ivpu_device *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)
@@ -177,16 +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);
 	}
 }
 
@@ -194,7 +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");
 }
 
@@ -209,6 +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)
@@ -393,10 +417,10 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 	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)
@@ -433,16 +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, "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;
 }
 
@@ -450,27 +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, "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 616477fc17fa..268ab7744a8b 100644
--- a/drivers/accel/ivpu/ivpu_sysfs.c
+++ b/drivers/accel/ivpu/ivpu_sysfs.c
@@ -1,17 +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.
  *
@@ -30,11 +35,12 @@ 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)));
 }
@@ -42,6 +48,30 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b
 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.
@@ -62,9 +92,55 @@ sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 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/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 908e68ea1c39..218468bbbcad 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -26,7 +26,7 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 26
+#define VPU_BOOT_API_VER_MINOR 28
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -76,8 +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 */
@@ -134,7 +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
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 7215c144158c..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 25
+#define VPU_JSM_API_VER_MINOR 29
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -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.
@@ -126,11 +125,13 @@ enum {
 	 * 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.
-	 * NOTE: 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.
+	 * 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),
 
@@ -275,6 +276,8 @@ struct vpu_inline_cmd {
 			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. */
@@ -791,12 +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;
@@ -934,6 +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];
 	/*
@@ -946,8 +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;
 };
 
 /*
@@ -1024,7 +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;
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 8ab82e78dd94..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",
@@ -439,6 +444,297 @@ static const struct mhi_channel_config aic100_channels[] = {
 	},
 };
 
+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[] = {
 	{
 		.num_elements = 32,
@@ -454,16 +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)
@@ -545,8 +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;
 
@@ -581,11 +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_data.c b/drivers/accel/qaic/qaic_data.c
index c20eb63750f5..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 */
@@ -182,6 +183,8 @@ 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_each_sgtable_dma_sg(sgt_in, sg, j) {
@@ -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 ba0cf2f94732..a991b8198dc4 100644
--- a/drivers/accel/qaic/qaic_debugfs.c
+++ b/drivers/accel/qaic/qaic_debugfs.c
@@ -240,7 +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;
@@ -253,7 +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 81819b9ef8d4..e31bcb0ecfc9 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -29,18 +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");
 
-#define PCI_DEV_AIC080			0xa080
-#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");
@@ -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_AIC080 || 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;
 	}
 
@@ -449,13 +483,13 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev)
 		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);
@@ -465,14 +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;
 
@@ -485,7 +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;
 	}
@@ -515,21 +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)
@@ -539,8 +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);
@@ -607,8 +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_AIC080), },
-	{ 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);
@@ -658,6 +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:
@@ -685,6 +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 21d58aed0deb..3ebcc1f7ff58 100644
--- a/drivers/accel/qaic/sahara.c
+++ b/drivers/accel/qaic/sahara.c
@@ -160,7 +160,7 @@ struct sahara_context {
 	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;
@@ -177,7 +177,7 @@ struct sahara_context {
 	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",
@@ -188,6 +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;
@@ -748,8 +776,15 @@ static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_
 	context->mhi_dev = mhi_dev;
 	INIT_WORK(&context->fw_work, sahara_processing);
 	INIT_WORK(&context->dump_work, sahara_dump_processing);
-	context->image_table = aic100_image_table;
-	context->table_size = ARRAY_SIZE(aic100_image_table);
+
+	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);
 
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/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/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 d81b55f5068c..ca00a5dbcf75 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -394,6 +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.
@@ -452,7 +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
@@ -460,7 +461,7 @@ config ACPI_HED
 
 config ACPI_BGRT
 	bool "Boottime Graphics Resource Table support"
-	depends on EFI && (X86 || ARM64 || LOONGARCH)
+	depends on EFI
 	help
 	  This driver adds support for exposing the ACPI Boottime Graphics
 	  Resource Table, which allows the operating system to obtain
@@ -546,6 +547,10 @@ if ARM64
 source "drivers/acpi/arm64/Kconfig"
 endif
 
+if RISCV
+source "drivers/acpi/riscv/Kconfig"
+endif
+
 config ACPI_PPTT
 	bool
 
@@ -576,6 +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 40208a0f5dfb..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
 #
@@ -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/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 f7fb7205028d..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;
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 3fde4496f8a2..c9a0bcaba2e4 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -19,7 +19,7 @@
 #include <linux/acpi.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/mwait.h>
 #include <xen/xen.h>
 
@@ -33,7 +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;
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 7cf6101cb4c7..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;
@@ -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.
@@ -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 825c2a8acea4..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);
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index a972831dbd66..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"
@@ -648,6 +649,13 @@ acpi_video_device_EDID(struct acpi_video_device *device, void **edid, int length
 
 	obj = buffer.pointer;
 
+	/*
+	 * 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;
@@ -657,7 +665,7 @@ acpi_video_device_EDID(struct acpi_video_device *device, void **edid, int length
 		ret = -EFAULT;
 	}
 
-	kfree(obj);
+	kfree(buffer.pointer);
 	return ret;
 }
 
@@ -2039,9 +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 1c5218b79fc2..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.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 309ce8efb4f6..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.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index b8543a34caea..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.
  *
  *****************************************************************************/
 
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 6f4fe47c955b..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;
@@ -1141,7 +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 ef068f4c864a..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_ANY) | ARG_COUNT_IS_MINIMUM,
+		       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/dbhistry.c b/drivers/acpi/acpica/dbhistry.c
index e874c1dddefa..554ae35108bd 100644
--- a/drivers/acpi/acpica/dbhistry.c
+++ b/drivers/acpi/acpica/dbhistry.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dbhistry - debugger HISTORY command
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c
index 4354c175e12e..e2f00c54cb36 100644
--- a/drivers/acpi/acpica/dsargs.c
+++ b/drivers/acpi/acpica/dsargs.c
@@ -4,7 +4,7 @@
  * Module Name: dsargs - Support for execution of dynamic arguments for static
  *                       objects (regions, fields, buffer fields, etc.)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 80c69af06948..c1f79d7a2026 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -4,7 +4,7 @@
  * Module Name: dscontrol - Support for execution control opcodes -
  *                          if/else/while/return
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c
index c5c8380a3114..274b74255551 100644
--- a/drivers/acpi/acpica/dsdebug.c
+++ b/drivers/acpi/acpica/dsdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsdebug - Parser/Interpreter interface - debugging
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 532401ecdab0..df132c9089c7 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsfield - Dispatcher field routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index 6e0e362e461f..57cd9e2d1109 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsinit - Object initialization namespace walk
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index e809c2aed78a..45ec32e81903 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsmethod - Parser/Interpreter interface - control method parsing
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -462,7 +462,6 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 	struct acpi_walk_state *next_walk_state = NULL;
 	union acpi_operand_object *obj_desc;
 	struct acpi_evaluate_info *info;
-	u32 i;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_call_control_method, this_walk_state);
 
@@ -483,6 +482,20 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 		return_ACPI_STATUS(AE_NULL_OBJECT);
 	}
 
+	if (this_walk_state->num_operands < obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Missing argument(s) for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_TOO_FEW_ARGUMENTS);
+	}
+
+	else if (this_walk_state->num_operands > obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Too many arguments for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_TOO_MANY_ARGUMENTS);
+	}
+
 	/* Init for new method, possibly wait on method mutex */
 
 	status =
@@ -539,14 +552,7 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 	 * Delete the operands on the previous walkstate operand stack
 	 * (they were copied to new objects)
 	 */
-	for (i = 0; i < obj_desc->method.param_count; i++) {
-		acpi_ut_remove_reference(this_walk_state->operands[i]);
-		this_walk_state->operands[i] = NULL;
-	}
-
-	/* Clear the operand stack */
-
-	this_walk_state->num_operands = 0;
+	acpi_ds_clear_operands(this_walk_state);
 
 	ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
 			  "**** Begin nested execution of [%4.4s] **** WalkState=%p\n",
diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c
index eca50517ad82..5393de4dbc4c 100644
--- a/drivers/acpi/acpica/dsmthdat.c
+++ b/drivers/acpi/acpica/dsmthdat.c
@@ -188,6 +188,7 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
 
 		index++;
 	}
+	acpi_ex_trace_args(params, index);
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%u args passed to method\n", index));
 	return_ACPI_STATUS(AE_OK);
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index 555f148d666b..1bf7eec49899 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsobject - Dispatcher object management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index dd3059000885..5699b0872848 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dsopcode - Dispatcher support for regions and fields
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c
index ecf793fe9919..1ed2386fab82 100644
--- a/drivers/acpi/acpica/dspkginit.c
+++ b/drivers/acpi/acpica/dspkginit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dspkginit - Completion of deferred package initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index fb9ed5e1da89..baf6a1f27605 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -668,6 +668,8 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 	union acpi_parse_object *arguments[ACPI_OBJ_NUM_OPERANDS];
 	u32 arg_count = 0;
 	u32 index = walk_state->num_operands;
+	u32 prev_num_operands = walk_state->num_operands;
+	u32 new_num_operands;
 	u32 i;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_create_operands, first_arg);
@@ -696,6 +698,7 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 
 	/* Create the interpreter arguments, in reverse order */
 
+	new_num_operands = index;
 	index--;
 	for (i = 0; i < arg_count; i++) {
 		arg = arguments[index];
@@ -720,7 +723,11 @@ cleanup:
 	 * pop everything off of the operand stack and delete those
 	 * objects
 	 */
-	acpi_ds_obj_stack_pop_and_delete(arg_count, walk_state);
+	walk_state->num_operands = (u8)(i);
+	acpi_ds_obj_stack_pop_and_delete(new_num_operands, walk_state);
+
+	/* Restore operand count */
+	walk_state->num_operands = (u8)(prev_num_operands);
 
 	ACPI_EXCEPTION((AE_INFO, status, "While creating Arg %u", index));
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index a43336f05206..5c5c6d8a4e48 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -4,7 +4,7 @@
  * Module Name: dswexec - Dispatcher method execution callbacks;
  *                        dispatch to interpreter.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index f7b8496c8bdd..666419b6a5c6 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswload - Dispatcher first pass namespace load callbacks
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 541235f498c2..bfc54c914757 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswload2 - Dispatcher second pass namespace load callbacks
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index 1fdd07ae862c..375a8fa43d9d 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswscope - Scope stack manipulation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index 75338a13c802..02aaddb89df9 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -3,7 +3,7 @@
  *
  * Module Name: dswstate - Dispatcher parse tree walk management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index 9e78c5b9ad52..6cdd39c987b8 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evevent - Fixed Event handling and dispatch
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
index 989dc01af03f..df2a4ab0e0da 100644
--- a/drivers/acpi/acpica/evglock.c
+++ b/drivers/acpi/acpica/evglock.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evglock - Global Lock support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -42,6 +42,10 @@ acpi_status acpi_ev_init_global_lock_handler(void)
 		return_ACPI_STATUS(AE_OK);
 	}
 
+	if (!acpi_gbl_use_global_lock) {
+		return_ACPI_STATUS(AE_OK);
+	}
+
 	/* Attempt installation of the global lock handler */
 
 	status = acpi_install_fixed_event_handler(ACPI_EVENT_GLOBAL,
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 934b201d3820..ba65b2ea49b2 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpe - General Purpose Event handling and dispatch
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index 58e1890ab25b..fadd93caf1d5 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeblk - GPE block creation and initialization.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 38f408cf13ce..eb769739420e 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeinit - System GPE initialization and update
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index ee3b1ea656d4..d15b1d75c8ec 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evgpeutil - GPE utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c
index 1c8cb6d924df..5a35dae945e2 100644
--- a/drivers/acpi/acpica/evhandler.c
+++ b/drivers/acpi/acpica/evhandler.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evhandler - Support for Address Space handlers
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index e68e876d3b84..04a23a6c3bb1 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evmisc - Miscellaneous event manager support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index cf53b9535f18..fa3475da7ea9 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evregion - Operation Region support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 46d1b3f5582d..b03952798af5 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evrgnini- ACPI address_space (op_region) init
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 24fa6433d562..86a8d41c079c 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxface - External interfaces for ACPI events
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index 48bf845191d2..4b052908d2e7 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxfevnt - External Interfaces, ACPI event disable/enable
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 4eeeb3b7ab7e..60dacec1b121 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: evxfgpe - External Interfaces for General Purpose Events (GPEs)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index bff2d099f469..bccc672c934c 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -4,7 +4,7 @@
  * Module Name: evxfregn - External Interfaces, ACPI Operation Regions and
  *                         Address Spaces.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c
index 2fb78b35565b..c248c9b162fa 100644
--- a/drivers/acpi/acpica/exconcat.c
+++ b/drivers/acpi/acpica/exconcat.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconcat - Concatenate-type AML operators
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 473115309860..4d7dd0fc6b07 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconfig - Namespace reconfiguration (Load/Unload opcodes)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index bb1be42daee1..fded9bfc2436 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exconvrt - Object conversion routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -226,8 +226,8 @@ acpi_ex_convert_to_buffer(union acpi_operand_object *obj_desc,
 		/* Copy the string to the buffer */
 
 		new_buf = return_desc->buffer.pointer;
-		strncpy((char *)new_buf, (char *)obj_desc->string.pointer,
-			obj_desc->string.length);
+		memcpy((char *)new_buf, (char *)obj_desc->string.pointer,
+		       obj_desc->string.length);
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 1bea9d97652c..052c69567997 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -3,7 +3,7 @@
  *
  * Module Name: excreate - Named object creation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index 3f86bfada510..81a07a52b73c 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exdebug - Support for stores to the AML Debug Object
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 2e2da8790224..d8aeebaab70a 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exdump - Interpreter debug output routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index 61ff36189ace..ced3ff9d0a86 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exfield - AML execution - field_unit read/write
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index cf6c812a8b6d..0771934c0455 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exfldio - Aml Field I/O
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index c6f2a9166ac0..07cbac58ed21 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c
index 65c487facdda..1fa013197fcf 100644
--- a/drivers/acpi/acpica/exmutex.c
+++ b/drivers/acpi/acpica/exmutex.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exmutex - ASL Mutex Acquire/Release functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index 9a448165bfeb..76ab73c37e90 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exnames - interpreter/scanner name load/execute
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 20fb34b68bee..6ac7e0ca5c9d 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg1 - AML execution - opcodes with 1 argument
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index 743c258bf2e8..a94fa4d70e99 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg2 - AML execution - opcodes with 2 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index d3091f619909..bf08110ed6d2 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg3 - AML execution - opcodes with 3 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index 1af35e143ba9..cb078e39abf7 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exoparg6 - AML execution - opcodes with 6 arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 82b1fa2d201f..1b1a006e82de 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exprep - ACPI AML field prep utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index c49b9f8de723..a390a1c2b0ab 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exregion - ACPI default op_region (address space) handlers
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index 873de01b8ad2..dd83631090fc 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresnte - AML Interpreter object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index 24a78b5e266c..4589de3f3012 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresolv - AML Interpreter object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index 3a437e6ace5c..782ee353a709 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exresop - AML Interpreter operand/object resolution
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c
index 5241f4c01c76..6d2581ec22ad 100644
--- a/drivers/acpi/acpica/exserial.c
+++ b/drivers/acpi/acpica/exserial.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exserial - field_unit support for serial address spaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -201,6 +201,12 @@ acpi_ex_read_serial_bus(union acpi_operand_object *obj_desc,
 		function = ACPI_READ;
 		break;
 
+	case ACPI_ADR_SPACE_FIXED_HARDWARE:
+
+		buffer_length = ACPI_FFH_INPUT_BUFFER_SIZE;
+		function = ACPI_READ;
+		break;
+
 	default:
 		return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID);
 	}
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 575c7a39f1aa..cbc42207496d 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exstore - AML Interpreter object store support
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index b01ae015e1b5..0470b2639831 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -4,7 +4,7 @@
  * Module Name: exstoren - AML Interpreter object store support,
  *                        Store to Node (namespace object)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index 37c3131a82fa..5b168fbc03e8 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exstorob - AML object store support, store to object
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index 2c384bd52b9c..7f843c9d8a06 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exsystem - Interface to OS services
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c
index f1730221ff13..36934d4f26fb 100644
--- a/drivers/acpi/acpica/extrace.c
+++ b/drivers/acpi/acpica/extrace.c
@@ -3,7 +3,7 @@
  *
  * Module Name: extrace - Support for interpreter execution tracing
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -136,9 +136,9 @@ acpi_ex_trace_point(acpi_trace_event_type type,
 
 	if (pathname) {
 		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
-				  "%s %s [0x%p:%s] execution.\n",
+				  "%s %s [%s] execution.\n",
 				  acpi_ex_get_trace_event_name(type),
-				  begin ? "Begin" : "End", aml, pathname));
+				  begin ? "Begin" : "End", pathname));
 	} else {
 		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
 				  "%s %s [0x%p] execution.\n",
@@ -149,6 +149,57 @@ acpi_ex_trace_point(acpi_trace_event_type type,
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ex_trace_args
+ *
+ * PARAMETERS:  params            - AML method arguments
+ *              count             - numer of method arguments
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Trace any arguments
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_trace_args(union acpi_operand_object **params, u32 count)
+{
+	u32 i;
+
+	ACPI_FUNCTION_NAME(ex_trace_args);
+
+	for (i = 0; i < count; i++) {
+		union acpi_operand_object *obj_desc = params[i];
+
+		if (!i) {
+			ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT, " "));
+		}
+
+		switch (obj_desc->common.type) {
+		case ACPI_TYPE_INTEGER:
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "%llx", obj_desc->integer.value));
+			break;
+		case ACPI_TYPE_STRING:
+			if (!obj_desc->string.length) {
+				ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "NULL"));
+				continue;
+			}
+			if (ACPI_IS_DEBUG_ENABLED(ACPI_LV_TRACE_POINT, _COMPONENT))
+				acpi_ut_print_string(obj_desc->string.pointer, ACPI_UINT8_MAX);
+			break;
+		default:
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "Unknown"));
+			break;
+		}
+		if (i+1 == count) {
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, "\n"));
+		} else {
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_TRACE_POINT, ", "));
+		}
+	}
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ex_start_trace_method
  *
  * PARAMETERS:  method_node         - Node of the method
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index f4d4a033f166..cc10c0732218 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: exutils - interpreter/scanner utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index 790f342dcd25..a1e1fa787566 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
index a9ba9190408b..631fd8e2b774 100644
--- a/drivers/acpi/acpica/hwesleep.c
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -4,7 +4,7 @@
  * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the
  *                    extended FADT-V5 sleep registers.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index e0c847ab8324..386f4759c317 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwgpe - Low level GPE enable/disable/clear functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index e0921f08b71a..87d78bef6323 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -4,7 +4,7 @@
  * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the
  *                   original/legacy sleep/PM registers.
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 192c04b5a599..a5e0bccae6a4 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -3,7 +3,7 @@
  *
  * Name: hwtimer.c - ACPI Power Management Timer Interface
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index b8de458f0368..496fd9e49f0b 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwvalid - I/O request validation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index c31f803995c6..847cd1b2493d 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: hwxface - Public ACPICA hardware interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 8dbf83aeb455..9aabe30416da 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -3,7 +3,7 @@
  *
  * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c
index 3efb46f0dc54..366d54a1d157 100644
--- a/drivers/acpi/acpica/nsarguments.c
+++ b/drivers/acpi/acpica/nsarguments.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsarguments - Validation of args for ACPI predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 7e5a683ae957..f05a92b88642 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -4,7 +4,7 @@
  * Module Name: nsconvert - Object conversions for objects returned by
  *                          predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 90a26cb0c472..6dc20486ad51 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsdump - table dumping routines for debug
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c
index fa116ebe49a3..d5b16aaec233 100644
--- a/drivers/acpi/acpica/nsdumpdv.c
+++ b/drivers/acpi/acpica/nsdumpdv.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsdump - table dumping routines for debug
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 86d126fdb27d..03373e7f7978 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsinit - namespace initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index fcb9de0f77a2..6ec4c646fff7 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsload - namespace loading/expanding/contracting procedures
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index d91153f65700..22aeeeb56cff 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -194,7 +194,7 @@ acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 			      char *full_path, u32 path_size, u8 no_trailing)
 {
 	u32 length = 0, i;
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	u8 do_no_trailing;
 	char c, *left, *right;
 	struct acpi_namespace_node *next_node;
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index 31e551cf4ea6..959e6379bc4c 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsparse - namespace interface to AML parser
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index cf57bd69616d..81995ee48c49 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nspredef - Validation of ACPI predefined methods and objects
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c
index dd37fc108fce..ca137ce5674f 100644
--- a/drivers/acpi/acpica/nsprepkg.c
+++ b/drivers/acpi/acpica/nsprepkg.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsprepkg - Validation of package objects for predefined names
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index b8657004190d..accfdcfb7e62 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nsrepair - Repair for objects returned by predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index 1bb7b71f07f1..8dbb870f40d2 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -4,7 +4,7 @@
  * Module Name: nsrepair2 - Repair for objects returned by specific
  *                          predefined methods
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
 				     return_object_ptr);
 
 typedef struct acpi_repair_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] ACPI_NONSTRING;
 	acpi_repair_function repair_function;
 
 } acpi_repair_info;
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 06ffdb6808f5..49cc07e2ac5a 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -4,7 +4,7 @@
  * Module Name: nsutils - Utilities for accessing ACPI namespace, accessing
  *                        parents and siblings and Scope manipulation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index eee396a77bae..a2ac06a26e92 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: nswalk - Functions for walking the ACPI namespace
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 5d5bcf165298..1db831545ec8 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -4,7 +4,7 @@
  * Module Name: nsxfname - Public interfaces to the ACPI subsystem
  *                         ACPI Namespace oriented interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 28582adfc0ac..6f6ae38ec044 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psargs - Parse AML opcode arguments
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index d0fd55636129..c989cadf271c 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psloop - Main AML parse loop
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 54471083ba54..496a1c1d5b0b 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psobject - Support for parse objects
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -636,7 +636,8 @@ acpi_status
 acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  union acpi_parse_object *op, acpi_status status)
 {
-	acpi_status status2;
+	acpi_status return_status = status;
+	u8 ascending = TRUE;
 
 	ACPI_FUNCTION_TRACE_PTR(ps_complete_final_op, walk_state);
 
@@ -650,7 +651,7 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  op));
 	do {
 		if (op) {
-			if (walk_state->ascending_callback != NULL) {
+			if (ascending && walk_state->ascending_callback != NULL) {
 				walk_state->op = op;
 				walk_state->op_info =
 				    acpi_ps_get_opcode_info(op->common.
@@ -672,49 +673,26 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 				}
 
 				if (status == AE_CTRL_TERMINATE) {
-					status = AE_OK;
-
-					/* Clean up */
-					do {
-						if (op) {
-							status2 =
-							    acpi_ps_complete_this_op
-							    (walk_state, op);
-							if (ACPI_FAILURE
-							    (status2)) {
-								return_ACPI_STATUS
-								    (status2);
-							}
-						}
-
-						acpi_ps_pop_scope(&
-								  (walk_state->
-								   parser_state),
-								  &op,
-								  &walk_state->
-								  arg_types,
-								  &walk_state->
-								  arg_count);
-
-					} while (op);
-
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = AE_CTRL_TERMINATE;
 				}
 
 				else if (ACPI_FAILURE(status)) {
 
 					/* First error is most important */
 
-					(void)
-					    acpi_ps_complete_this_op(walk_state,
-								     op);
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = status;
 				}
 			}
 
-			status2 = acpi_ps_complete_this_op(walk_state, op);
-			if (ACPI_FAILURE(status2)) {
-				return_ACPI_STATUS(status2);
+			status = acpi_ps_complete_this_op(walk_state, op);
+			if (ACPI_FAILURE(status)) {
+				ascending = FALSE;
+				if (ACPI_SUCCESS(return_status) ||
+				    return_status == AE_CTRL_TERMINATE) {
+					return_status = status;
+				}
 			}
 		}
 
@@ -724,5 +702,5 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 
 	} while (op);
 
-	return_ACPI_STATUS(status);
+	return_ACPI_STATUS(return_status);
 }
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index 39e31030e5f4..bf6103986f48 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psopcode - Parser/Interpreter opcode information table
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c
index bccf606e08b4..532ea307a675 100644
--- a/drivers/acpi/acpica/psopinfo.c
+++ b/drivers/acpi/acpica/psopinfo.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psopinfo - AML opcode information functions and dispatch tables
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -34,7 +34,7 @@ static const u8 acpi_gbl_argument_count[] =
 
 const struct acpi_opcode_info *acpi_ps_get_opcode_info(u16 opcode)
 {
-#ifdef ACPI_DEBUG_OUTPUT
+#if defined ACPI_ASL_COMPILER && defined ACPI_DEBUG_OUTPUT
 	const char *opcode_name = "Unknown AML opcode";
 #endif
 
@@ -102,11 +102,11 @@ const struct acpi_opcode_info *acpi_ps_get_opcode_info(u16 opcode)
 	default:
 		break;
 	}
-#endif
 
 	/* Unknown AML opcode */
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%s [%4.4X]\n", opcode_name, opcode));
+#endif
 
 	return (&acpi_gbl_aml_op_info[_UNK]);
 }
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index 10a072953d78..55a416e56fd8 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psparse - Parser top level AML parse routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c
index a0035bde7556..c4e4483f0a0b 100644
--- a/drivers/acpi/acpica/psscope.c
+++ b/drivers/acpi/acpica/psscope.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psscope - Parser scope stack management routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c
index 7f7f5ecd4011..5a285d3f2cdb 100644
--- a/drivers/acpi/acpica/pstree.c
+++ b/drivers/acpi/acpica/pstree.c
@@ -3,7 +3,7 @@
  *
  * Module Name: pstree - Parser op tree manipulation/traversal/search
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index d550c4af4702..ada1dc304d25 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psutils - Parser miscellaneous utilities (Parser only)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c
index d92817c72b8d..2f3ebcd8aebe 100644
--- a/drivers/acpi/acpica/pswalk.c
+++ b/drivers/acpi/acpica/pswalk.c
@@ -3,7 +3,7 @@
  *
  * Module Name: pswalk - Parser routines to walk parsed op tree(s)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c
index 6f4eace0ba69..d480de075a90 100644
--- a/drivers/acpi/acpica/psxface.c
+++ b/drivers/acpi/acpica/psxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: psxface - Parser external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index 27384ee245f0..f92010e667cd 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -272,18 +272,13 @@ u8
 acpi_rs_get_address_common(struct acpi_resource *resource,
 			   union aml_resource *aml)
 {
-	struct aml_resource_address address;
-
 	ACPI_FUNCTION_ENTRY();
 
-	/* Avoid undefined behavior: member access within misaligned address */
-
-	memcpy(&address, aml, sizeof(address));
-
 	/* Validate the Resource Type */
 
-	if ((address.resource_type > 2) &&
-	    (address.resource_type < 0xC0) && (address.resource_type != 0x0A)) {
+	if ((aml->address.resource_type > 2) &&
+	    (aml->address.resource_type < 0xC0) &&
+	    (aml->address.resource_type != 0x0A)) {
 		return (FALSE);
 	}
 
@@ -304,7 +299,7 @@ acpi_rs_get_address_common(struct acpi_resource *resource,
 		/* Generic resource type, just grab the type_specific byte */
 
 		resource->data.address.info.type_specific =
-		    address.specific_flags;
+		    aml->address.specific_flags;
 	}
 
 	return (TRUE);
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index 6e7a152d6459..242daf45e20e 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -608,18 +608,12 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 
 		case ACPI_RESOURCE_NAME_SERIAL_BUS:{
 
-				/* Avoid undefined behavior: member access within misaligned address */
-
-				struct aml_resource_common_serialbus
-				    common_serial_bus;
-				memcpy(&common_serial_bus, aml_resource,
-				       sizeof(common_serial_bus));
-
 				minimum_aml_resource_length =
 				    acpi_gbl_resource_aml_serial_bus_sizes
-				    [common_serial_bus.type];
+				    [aml_resource->common_serial_bus.type];
 				extra_struct_bytes +=
-				    common_serial_bus.resource_length -
+				    aml_resource->common_serial_bus.
+				    resource_length -
 				    minimum_aml_resource_length;
 				break;
 			}
@@ -688,16 +682,10 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 		 */
 		if (acpi_ut_get_resource_type(aml_buffer) ==
 		    ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-			/* Avoid undefined behavior: member access within misaligned address */
-
-			struct aml_resource_common_serialbus common_serial_bus;
-			memcpy(&common_serial_bus, aml_resource,
-			       sizeof(common_serial_bus));
-
 			buffer_size =
 			    acpi_gbl_resource_struct_serial_bus_sizes
-			    [common_serial_bus.type] + extra_struct_bytes;
+			    [aml_resource->common_serial_bus.type] +
+			    extra_struct_bytes;
 		} else {
 			buffer_size =
 			    acpi_gbl_resource_struct_sizes[resource_index] +
diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c
index 164c96e063c6..e46efaa889cd 100644
--- a/drivers/acpi/acpica/rslist.c
+++ b/drivers/acpi/acpica/rslist.c
@@ -55,21 +55,15 @@ acpi_rs_convert_aml_to_resources(u8 * aml,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 
 	if (acpi_ut_get_resource_type(aml) == ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
-		if (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE) {
+		if (aml_resource->common_serial_bus.type >
+		    AML_RESOURCE_MAX_SERIALBUSTYPE) {
 			conversion_table = NULL;
 		} else {
 			/* This is an I2C, SPI, UART, or CSI2 serial_bus descriptor */
 
 			conversion_table =
 			    acpi_gbl_convert_resource_serial_bus_dispatch
-			    [common_serial_bus.type];
+			    [aml_resource->common_serial_bus.type];
 		}
 	} else {
 		conversion_table =
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index a1f10e4409a3..5b98e09fff76 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbdata - Table manager data structure functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 3c126c6d306b..c6658b2f3027 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbfadt   - FADT table utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 1c1b2e284bd9..d71a73216380 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbfind   - find table
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -57,8 +57,8 @@ acpi_tb_find_table(char *signature,
 
 	memset(&header, 0, sizeof(struct acpi_table_header));
 	ACPI_COPY_NAMESEG(header.signature, signature);
-	strncpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
-	strncpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
+	memcpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
+	memcpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
 
 	/* Search for the table */
 
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 0dc003c20e4d..ee9b85bc238b 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbinstal - ACPI table installation and removal
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 58b02e4b254b..049f6c2f1e32 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbprint - Table output utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -121,6 +121,14 @@ acpi_tb_print_table_header(acpi_physical_address address,
 			   ACPI_CAST_PTR(struct acpi_table_rsdp,
 					 header)->revision,
 			   local_header.oem_id));
+	} else if (acpi_gbl_CDAT && !acpi_ut_valid_nameseg(header->signature)) {
+
+		/* CDAT does not use the common ACPI table header */
+
+		ACPI_INFO(("%-4.4s 0x%8.8X%8.8X %06X",
+			   ACPI_SIG_CDAT, ACPI_FORMAT_UINT64(address),
+			   ACPI_CAST_PTR(struct acpi_table_cdat,
+					 header)->length));
 	} else {
 		/* Standard ACPI table with full common header */
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index dad7425fce3f..fa64851c7b62 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbutils - ACPI Table utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 275b52dc42e9..a8f07d2641b6 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxface - ACPI table-oriented external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 0f2a7343de3a..2a17c60a9a39 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxfload - Table load/unload external interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 5b413bbab338..961577ba9486 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -3,7 +3,7 @@
  *
  * Module Name: tbxfroot - Find the root ACPI table (RSDT)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index be94d2fd99a7..c673d6c95e0a 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utaddress - op_region address range check
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index c1fb70457e20..2418a312733a 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utalloc - local memory allocation routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c
index 2be37676edd7..259c28d3fecd 100644
--- a/drivers/acpi/acpica/utascii.c
+++ b/drivers/acpi/acpica/utascii.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utascii - Utility ascii functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index b054bb5eeaf0..f6e6e98e9523 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utbuffer - Buffer dump routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index 85a85f7cf750..cabec193febb 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcache - local cache allocation routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -251,9 +251,9 @@ void *acpi_os_acquire_object(struct acpi_memory_list *cache)
 	} else {
 		/* The cache is empty, create a new object */
 
+#ifdef ACPI_DBG_TRACK_ALLOCATIONS
 		ACPI_MEM_TRACKING(cache->total_allocated++);
 
-#ifdef ACPI_DBG_TRACK_ALLOCATIONS
 		if ((cache->total_allocated - cache->total_freed) >
 		    cache->max_occupied) {
 			cache->max_occupied =
diff --git a/drivers/acpi/acpica/utcksum.c b/drivers/acpi/acpica/utcksum.c
index b483894c3629..e6f6030b3a3f 100644
--- a/drivers/acpi/acpica/utcksum.c
+++ b/drivers/acpi/acpica/utcksum.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcksum - Support generating table checksums
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index 2e17e657dfa4..80458e70ac2b 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utcopy - Internal to external object translation utilities
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 3d71bd9245c7..9f197e293c7e 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utdebug - Debug print/trace routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 95a4b7509e01..b82130d1a8bc 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utdecode - Utility decoding routines (value-to-string)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index c85bfa13ac1e..e8180099d01f 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -404,7 +404,7 @@ acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action)
 				  object, object->common.type,
 				  acpi_ut_get_object_type_name(object),
 				  new_count));
-		message = "Incremement";
+		message = "Increment";
 		break;
 
 	case REF_DECREMENT:
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index 3e5173d03953..abc6583ed369 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uteval - Object evaluation
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 820820ea8119..97c55a113bae 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utglobal - Global variables for the ACPI subsystem
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c
index e62802791dcf..8cd050e9cad5 100644
--- a/drivers/acpi/acpica/uthex.c
+++ b/drivers/acpi/acpica/uthex.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uthex -- Hex/ASCII support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index 15c2ce91d403..eb88335dea2c 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 6d78504e9fbc..4bef97e8223a 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utinit - Common ACPI subsystem initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c
index ee6d72385c5c..123dbcbc60bc 100644
--- a/drivers/acpi/acpica/utlock.c
+++ b/drivers/acpi/acpica/utlock.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utlock - Reader/Writer lock interfaces
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index f4aae8f0d3a8..272e46208263 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utobject - ACPI object create/delete/size/cache routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 99b85fd6eccf..f6ac16729e42 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utosi - Support for the _OSI predefined control method
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index 29d2977d0746..d9bd80e2d32a 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utpredef - support functions for predefined names
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 42b30b9f9312..423d10569736 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utprint - Formatted printing routines
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
@@ -333,11 +333,8 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args)
 
 	pos = string;
 
-	if (size != ACPI_UINT32_MAX) {
-		end = string + size;
-	} else {
-		end = ACPI_CAST_PTR(char, ACPI_UINT32_MAX);
-	}
+	size = ACPI_MIN(size, ACPI_PTR_DIFF(ACPI_MAX_PTR, string));
+	end = string + size;
 
 	for (; *format; ++format) {
 		if (*format != '%') {
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index cff7901f7866..e1cc3d348750 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -361,20 +361,16 @@ acpi_ut_validate_resource(struct acpi_walk_state *walk_state,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 	if (resource_type == ACPI_RESOURCE_NAME_SERIAL_BUS) {
 
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
 		/* Validate the bus_type field */
 
-		if ((common_serial_bus.type == 0) ||
-		    (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE)) {
+		if ((aml_resource->common_serial_bus.type == 0) ||
+		    (aml_resource->common_serial_bus.type >
+		     AML_RESOURCE_MAX_SERIALBUSTYPE)) {
 			if (walk_state) {
 				ACPI_ERROR((AE_INFO,
 					    "Invalid/unsupported SerialBus resource descriptor: BusType 0x%2.2X",
-					    common_serial_bus.type));
+					    aml_resource->common_serial_bus.
+					    type));
 			}
 			return (AE_AML_INVALID_RESOURCE_TYPE);
 		}
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index f5f5da441458..a99c4c9e3d39 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -3,7 +3,7 @@
  *
  * Module Name: uttrack - Memory allocation tracking routines (debug only)
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c
index 8f10b413e928..0682554934ca 100644
--- a/drivers/acpi/acpica/utuuid.c
+++ b/drivers/acpi/acpica/utuuid.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utuuid -- UUID support functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index aa2e923462b7..56942b5f026b 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utxface - External interfaces, miscellaneous utility functions
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 70ae0afa7939..c1702f8fba67 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -3,7 +3,7 @@
  *
  * Module Name: utxfinit - External interfaces for ACPICA initialization
  *
- * Copyright (C) 2000 - 2023, Intel Corp.
+ * Copyright (C) 2000 - 2025, Intel Corp.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 3cfe7e7475f2..070c07d68dfb 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -23,6 +23,7 @@ config ACPI_APEI_GHES
 	select ACPI_HED
 	select IRQ_WORK
 	select GENERIC_ALLOCATOR
+	select ARM_SDE_INTERFACE if ARM64
 	help
 	  Generic Hardware Error Source provides a way to report
 	  platform hardware errors (such as that from chipset). It
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index cd2766c69d78..77c10a7a7a9f 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -131,7 +131,7 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
 
 int apei_osc_setup(void);
 
-int einj_get_available_error_type(u32 *type);
+int einj_get_available_error_type(u32 *type, int einj_action);
 int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 		      u64 param4);
 int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index 04731a5b01fa..3c87953dbd19 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -21,7 +21,7 @@
 #include <linux/nmi.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
-#include <linux/platform_device.h>
+#include <linux/device/faux.h>
 #include <linux/unaligned.h>
 
 #include "apei-internal.h"
@@ -33,6 +33,8 @@
 #define SLEEP_UNIT_MAX		5000			/* 5ms */
 /* Firmware should respond within 1 seconds */
 #define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
+#define COMPONENT_LEN		16
+#define ACPI65_EINJV2_SUPP	BIT(30)
 #define ACPI5_VENDOR_BIT	BIT(31)
 #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
 				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
@@ -49,6 +51,28 @@
  */
 static int acpi5;
 
+struct syndrome_array {
+	union {
+		u8	acpi_id[COMPONENT_LEN];
+		u8	device_id[COMPONENT_LEN];
+		u8	pcie_sbdf[COMPONENT_LEN];
+		u8	vendor_id[COMPONENT_LEN];
+	} comp_id;
+	union {
+		u8	proc_synd[COMPONENT_LEN];
+		u8	mem_synd[COMPONENT_LEN];
+		u8	pcie_synd[COMPONENT_LEN];
+		u8	vendor_synd[COMPONENT_LEN];
+	} comp_synd;
+};
+
+struct einjv2_extension_struct {
+	u32 length;
+	u16 revision;
+	u16 component_arr_count;
+	struct syndrome_array component_arr[] __counted_by(component_arr_count);
+};
+
 struct set_error_type_with_address {
 	u32	type;
 	u32	vendor_extension;
@@ -57,11 +81,13 @@ struct set_error_type_with_address {
 	u64	memory_address;
 	u64	memory_address_range;
 	u32	pcie_sbdf;
+	struct	einjv2_extension_struct einjv2_struct;
 };
 enum {
 	SETWA_FLAGS_APICID = 1,
 	SETWA_FLAGS_MEM = 2,
 	SETWA_FLAGS_PCIE_SBDF = 4,
+	SETWA_FLAGS_EINJV2 = 8,
 };
 
 /*
@@ -83,6 +109,11 @@ static struct debugfs_blob_wrapper vendor_blob;
 static struct debugfs_blob_wrapper vendor_errors;
 static char vendor_dev[64];
 
+static u32 max_nr_components;
+static u32 available_error_type;
+static u32 available_error_type_v2;
+static struct syndrome_array *syndrome_data;
+
 /*
  * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
  * EINJ table through an unpublished extension. Use with caution as
@@ -149,7 +180,9 @@ static DEFINE_MUTEX(einj_mutex);
  */
 bool einj_initialized __ro_after_init;
 
-static void *einj_param;
+static void __iomem *einj_param;
+static u32 v5param_size;
+static bool is_v2;
 
 static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 {
@@ -157,13 +190,13 @@ static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
 }
 
-static int __einj_get_available_error_type(u32 *type)
+static int __einj_get_available_error_type(u32 *type, int einj_action)
 {
 	struct apei_exec_context ctx;
 	int rc;
 
 	einj_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
+	rc = apei_exec_run(&ctx, einj_action);
 	if (rc)
 		return rc;
 	*type = apei_exec_ctx_get_output(&ctx);
@@ -172,17 +205,34 @@ static int __einj_get_available_error_type(u32 *type)
 }
 
 /* Get error injection capabilities of the platform */
-int einj_get_available_error_type(u32 *type)
+int einj_get_available_error_type(u32 *type, int einj_action)
 {
 	int rc;
 
 	mutex_lock(&einj_mutex);
-	rc = __einj_get_available_error_type(type);
+	rc = __einj_get_available_error_type(type, einj_action);
 	mutex_unlock(&einj_mutex);
 
 	return rc;
 }
 
+static int einj_get_available_error_types(u32 *type1, u32 *type2)
+{
+	int rc;
+
+	rc = einj_get_available_error_type(type1, ACPI_EINJ_GET_ERROR_TYPE);
+	if (rc)
+		return rc;
+	if (*type1 & ACPI65_EINJV2_SUPP) {
+		rc = einj_get_available_error_type(type2,
+						   ACPI_EINJV2_GET_ERROR_TYPE);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static int einj_timedout(u64 *t)
 {
 	if ((s64)*t < SLEEP_UNIT_MIN) {
@@ -214,24 +264,26 @@ static void check_vendor_extension(u64 paddr,
 				   struct set_error_type_with_address *v5param)
 {
 	int	offset = v5param->vendor_extension;
-	struct	vendor_error_type_extension *v;
+	struct	vendor_error_type_extension v;
+	struct vendor_error_type_extension __iomem *p;
 	u32	sbdf;
 
 	if (!offset)
 		return;
-	v = acpi_os_map_iomem(paddr + offset, sizeof(*v));
-	if (!v)
+	p = acpi_os_map_iomem(paddr + offset, sizeof(*p));
+	if (!p)
 		return;
-	get_oem_vendor_struct(paddr, offset, v);
-	sbdf = v->pcie_sbdf;
+	memcpy_fromio(&v, p, sizeof(v));
+	get_oem_vendor_struct(paddr, offset, &v);
+	sbdf = v.pcie_sbdf;
 	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
 		sbdf >> 24, (sbdf >> 16) & 0xff,
 		(sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
-		 v->vendor_id, v->device_id, v->rev_id);
-	acpi_os_unmap_iomem(v, sizeof(*v));
+		 v.vendor_id, v.device_id, v.rev_id);
+	acpi_os_unmap_iomem(p, sizeof(v));
 }
 
-static void *einj_get_parameter_address(void)
+static void __iomem *einj_get_parameter_address(void)
 {
 	int i;
 	u64 pa_v4 = 0, pa_v5 = 0;
@@ -252,26 +304,50 @@ static void *einj_get_parameter_address(void)
 		entry++;
 	}
 	if (pa_v5) {
-		struct set_error_type_with_address *v5param;
+		struct set_error_type_with_address v5param;
+		struct set_error_type_with_address __iomem *p;
 
-		v5param = acpi_os_map_iomem(pa_v5, sizeof(*v5param));
-		if (v5param) {
+		v5param_size = sizeof(v5param);
+		p = acpi_os_map_iomem(pa_v5, sizeof(*p));
+		if (p) {
+			int offset, len;
+
+			memcpy_fromio(&v5param, p, v5param_size);
 			acpi5 = 1;
-			check_vendor_extension(pa_v5, v5param);
-			return v5param;
+			check_vendor_extension(pa_v5, &v5param);
+			if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) {
+				len = v5param.einjv2_struct.length;
+				offset = offsetof(struct einjv2_extension_struct, component_arr);
+				max_nr_components = (len - offset) /
+						sizeof(v5param.einjv2_struct.component_arr[0]);
+				/*
+				 * The first call to acpi_os_map_iomem above does not include the
+				 * component array, instead it is used to read and calculate maximum
+				 * number of components supported by the system. Below, the mapping
+				 * is expanded to include the component array.
+				 */
+				acpi_os_unmap_iomem(p, v5param_size);
+				offset = offsetof(struct set_error_type_with_address, einjv2_struct);
+				v5param_size = offset + struct_size(&v5param.einjv2_struct,
+					component_arr, max_nr_components);
+				p = acpi_os_map_iomem(pa_v5, v5param_size);
+			}
+			return p;
 		}
 	}
 	if (param_extension && pa_v4) {
-		struct einj_parameter *v4param;
+		struct einj_parameter v4param;
+		struct einj_parameter __iomem *p;
 
-		v4param = acpi_os_map_iomem(pa_v4, sizeof(*v4param));
-		if (!v4param)
+		p = acpi_os_map_iomem(pa_v4, sizeof(*p));
+		if (!p)
 			return NULL;
-		if (v4param->reserved1 || v4param->reserved2) {
-			acpi_os_unmap_iomem(v4param, sizeof(*v4param));
+		memcpy_fromio(&v4param, p, sizeof(v4param));
+		if (v4param.reserved1 || v4param.reserved2) {
+			acpi_os_unmap_iomem(p, sizeof(v4param));
 			return NULL;
 		}
-		return v4param;
+		return p;
 	}
 
 	return NULL;
@@ -317,7 +393,8 @@ static struct acpi_generic_address *einj_get_trigger_parameter_region(
 static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 				u64 param1, u64 param2)
 {
-	struct acpi_einj_trigger *trigger_tab = NULL;
+	struct acpi_einj_trigger trigger_tab;
+	struct acpi_einj_trigger *full_trigger_tab;
 	struct apei_exec_context trigger_ctx;
 	struct apei_resources trigger_resources;
 	struct acpi_whea_header *trigger_entry;
@@ -325,54 +402,60 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	u32 table_size;
 	int rc = -EIO;
 	struct acpi_generic_address *trigger_param_region = NULL;
+	struct acpi_einj_trigger __iomem *p = NULL;
 
-	r = request_mem_region(trigger_paddr, sizeof(*trigger_tab),
+	r = request_mem_region(trigger_paddr, sizeof(trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
 		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger table\n",
 		       (unsigned long long)trigger_paddr,
 		       (unsigned long long)trigger_paddr +
-			    sizeof(*trigger_tab) - 1);
+			    sizeof(trigger_tab) - 1);
 		goto out;
 	}
-	trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab));
-	if (!trigger_tab) {
+	p = ioremap_cache(trigger_paddr, sizeof(*p));
+	if (!p) {
 		pr_err("Failed to map trigger table!\n");
 		goto out_rel_header;
 	}
-	rc = einj_check_trigger_header(trigger_tab);
+	memcpy_fromio(&trigger_tab, p, sizeof(trigger_tab));
+	rc = einj_check_trigger_header(&trigger_tab);
 	if (rc) {
 		pr_warn(FW_BUG "Invalid trigger error action table.\n");
 		goto out_rel_header;
 	}
 
 	/* No action structures in the TRIGGER_ERROR table, nothing to do */
-	if (!trigger_tab->entry_count)
+	if (!trigger_tab.entry_count)
 		goto out_rel_header;
 
 	rc = -EIO;
-	table_size = trigger_tab->table_size;
-	r = request_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			       table_size - sizeof(*trigger_tab),
+	table_size = trigger_tab.table_size;
+	full_trigger_tab = kmalloc(table_size, GFP_KERNEL);
+	if (!full_trigger_tab)
+		goto out_rel_header;
+	r = request_mem_region(trigger_paddr + sizeof(trigger_tab),
+			       table_size - sizeof(trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
 		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
-		       (unsigned long long)trigger_paddr + sizeof(*trigger_tab),
+		       (unsigned long long)trigger_paddr + sizeof(trigger_tab),
 		       (unsigned long long)trigger_paddr + table_size - 1);
-		goto out_rel_header;
+		goto out_free_trigger_tab;
 	}
-	iounmap(trigger_tab);
-	trigger_tab = ioremap_cache(trigger_paddr, table_size);
-	if (!trigger_tab) {
+	iounmap(p);
+	p = ioremap_cache(trigger_paddr, table_size);
+	if (!p) {
 		pr_err("Failed to map trigger table!\n");
 		goto out_rel_entry;
 	}
+	memcpy_fromio(full_trigger_tab, p, table_size);
 	trigger_entry = (struct acpi_whea_header *)
-		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
+		((char *)full_trigger_tab + sizeof(struct acpi_einj_trigger));
 	apei_resources_init(&trigger_resources);
 	apei_exec_ctx_init(&trigger_ctx, einj_ins_type,
 			   ARRAY_SIZE(einj_ins_type),
-			   trigger_entry, trigger_tab->entry_count);
+			   trigger_entry, trigger_tab.entry_count);
 	rc = apei_exec_collect_resources(&trigger_ctx, &trigger_resources);
 	if (rc)
 		goto out_fini;
@@ -390,7 +473,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 
 		apei_resources_init(&addr_resources);
 		trigger_param_region = einj_get_trigger_parameter_region(
-			trigger_tab, param1, param2);
+			full_trigger_tab, param1, param2);
 		if (trigger_param_region) {
 			rc = apei_resources_add(&addr_resources,
 				trigger_param_region->address,
@@ -419,23 +502,33 @@ out_release:
 out_fini:
 	apei_resources_fini(&trigger_resources);
 out_rel_entry:
-	release_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			   table_size - sizeof(*trigger_tab));
+	release_mem_region(trigger_paddr + sizeof(trigger_tab),
+			   table_size - sizeof(trigger_tab));
+out_free_trigger_tab:
+	kfree(full_trigger_tab);
 out_rel_header:
-	release_mem_region(trigger_paddr, sizeof(*trigger_tab));
+	release_mem_region(trigger_paddr, sizeof(trigger_tab));
 out:
-	if (trigger_tab)
-		iounmap(trigger_tab);
+	if (p)
+		iounmap(p);
 
 	return rc;
 }
 
+static bool is_end_of_list(u8 *val)
+{
+	for (int i = 0; i < COMPONENT_LEN; ++i) {
+		if (val[i] != 0xFF)
+			return false;
+	}
+	return true;
+}
 static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			       u64 param3, u64 param4)
 {
 	struct apei_exec_context ctx;
 	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
-	int rc;
+	int i, rc;
 
 	einj_exec_ctx_init(&ctx);
 
@@ -444,8 +537,13 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 		return rc;
 	apei_exec_ctx_set_input(&ctx, type);
 	if (acpi5) {
-		struct set_error_type_with_address *v5param = einj_param;
+		struct set_error_type_with_address *v5param;
 
+		v5param = kmalloc(v5param_size, GFP_KERNEL);
+		if (!v5param)
+			return -ENOMEM;
+
+		memcpy_fromio(v5param, einj_param, v5param_size);
 		v5param->type = type;
 		if (type & ACPI5_VENDOR_BIT) {
 			switch (vendor_flags) {
@@ -465,8 +563,21 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			v5param->flags = flags;
 			v5param->memory_address = param1;
 			v5param->memory_address_range = param2;
-			v5param->apicid = param3;
-			v5param->pcie_sbdf = param4;
+
+			if (is_v2) {
+				for (i = 0; i < max_nr_components; i++) {
+					if (is_end_of_list(syndrome_data[i].comp_id.acpi_id))
+						break;
+					v5param->einjv2_struct.component_arr[i].comp_id =
+						syndrome_data[i].comp_id;
+					v5param->einjv2_struct.component_arr[i].comp_synd =
+						syndrome_data[i].comp_synd;
+				}
+				v5param->einjv2_struct.component_arr_count = i;
+			} else {
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
+			}
 		} else {
 			switch (type) {
 			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -490,15 +601,19 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 				break;
 			}
 		}
+		memcpy_toio(einj_param, v5param, v5param_size);
+		kfree(v5param);
 	} else {
 		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
 		if (rc)
 			return rc;
 		if (einj_param) {
-			struct einj_parameter *v4param = einj_param;
+			struct einj_parameter v4param;
 
-			v4param->param1 = param1;
-			v4param->param2 = param2;
+			memcpy_fromio(&v4param, einj_param, sizeof(v4param));
+			v4param.param1 = param1;
+			v4param.param2 = param2;
+			memcpy_toio(einj_param, &v4param, sizeof(v4param));
 		}
 	}
 	rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
@@ -541,6 +656,43 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	return rc;
 }
 
+/* Allow almost all types of address except MMIO. */
+static bool is_allowed_range(u64 base_addr, u64 size)
+{
+	int i;
+	/*
+	 * MMIO region is usually claimed with IORESOURCE_MEM + IORES_DESC_NONE.
+	 * However, IORES_DESC_NONE is treated like a wildcard when we check if
+	 * region intersects with known resource. So do an allow list check for
+	 * IORES_DESCs that definitely or most likely not MMIO.
+	 */
+	int non_mmio_desc[] = {
+		IORES_DESC_CRASH_KERNEL,
+		IORES_DESC_ACPI_TABLES,
+		IORES_DESC_ACPI_NV_STORAGE,
+		IORES_DESC_PERSISTENT_MEMORY,
+		IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+		/* Treat IORES_DESC_DEVICE_PRIVATE_MEMORY as MMIO. */
+		IORES_DESC_RESERVED,
+		IORES_DESC_SOFT_RESERVED,
+	};
+
+	if (region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
+			      == REGION_INTERSECTS)
+		return true;
+
+	for (i = 0; i < ARRAY_SIZE(non_mmio_desc); ++i) {
+		if (region_intersects(base_addr, size, IORESOURCE_MEM, non_mmio_desc[i])
+				      == REGION_INTERSECTS)
+			return true;
+	}
+
+	if (arch_is_platform_page(base_addr))
+		return true;
+
+	return false;
+}
+
 /* Inject the specified hardware error */
 int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 		      u64 param4)
@@ -549,10 +701,15 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 	u64 base_addr, size;
 
 	/* If user manually set "flags", make sure it is legal */
-	if (flags && (flags &
-		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
+	if (flags && (flags & ~(SETWA_FLAGS_APICID | SETWA_FLAGS_MEM |
+		      SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2)))
 		return -EINVAL;
 
+	/* check if type is a valid EINJv2 error type */
+	if (is_v2) {
+		if (!(type & available_error_type_v2))
+			return -EINVAL;
+	}
 	/*
 	 * We need extra sanity checks for memory errors.
 	 * Other types leap directly to injection.
@@ -582,19 +739,15 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 	 * Disallow crazy address masks that give BIOS leeway to pick
 	 * injection address almost anywhere. Insist on page or
 	 * better granularity and that target address is normal RAM or
-	 * NVDIMM.
+	 * as long as is not MMIO.
 	 */
 	base_addr = param1 & param2;
 	size = ~param2 + 1;
 
-	if (((param2 & PAGE_MASK) != PAGE_MASK) ||
-	    ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
-				!= REGION_INTERSECTS) &&
-	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY)
-				!= REGION_INTERSECTS) &&
-	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_SOFT_RESERVED)
-				!= REGION_INTERSECTS) &&
-	     !arch_is_platform_page(base_addr)))
+	if ((param2 & PAGE_MASK) != PAGE_MASK)
+		return -EINVAL;
+
+	if (!is_allowed_range(base_addr, size))
 		return -EINVAL;
 
 	if (is_zero_pfn(base_addr >> PAGE_SHIFT))
@@ -630,6 +783,8 @@ static u64 error_param2;
 static u64 error_param3;
 static u64 error_param4;
 static struct dentry *einj_debug_dir;
+static char einj_buf[32];
+static bool einj_v2_enabled;
 static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(0), "Processor Correctable" },
 	{ BIT(1), "Processor Uncorrectable non-fatal" },
@@ -646,29 +801,35 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(31), "Vendor Defined Error Types" },
 };
 
+static struct { u32 mask; const char *str; } const einjv2_error_type_string[] = {
+	{ BIT(0), "EINJV2 Processor Error" },
+	{ BIT(1), "EINJV2 Memory Error" },
+	{ BIT(2), "EINJV2 PCI Express Error" },
+};
+
 static int available_error_type_show(struct seq_file *m, void *v)
 {
-	int rc;
-	u32 error_type = 0;
 
-	rc = einj_get_available_error_type(&error_type);
-	if (rc)
-		return rc;
 	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
-		if (error_type & einj_error_type_string[pos].mask)
+		if (available_error_type & einj_error_type_string[pos].mask)
 			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
 				   einj_error_type_string[pos].str);
-
+	if ((available_error_type & ACPI65_EINJV2_SUPP) && einj_v2_enabled) {
+		for (int pos = 0; pos < ARRAY_SIZE(einjv2_error_type_string); pos++) {
+			if (available_error_type_v2 & einjv2_error_type_string[pos].mask)
+				seq_printf(m, "V2_0x%08x\t%s\n", einjv2_error_type_string[pos].mask,
+					   einjv2_error_type_string[pos].str);
+		}
+	}
 	return 0;
 }
 
 DEFINE_SHOW_ATTRIBUTE(available_error_type);
 
-static int error_type_get(void *data, u64 *val)
+static ssize_t error_type_get(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
 {
-	*val = error_type;
-
-	return 0;
+	return simple_read_from_buffer(buf, count, ppos, einj_buf, strlen(einj_buf));
 }
 
 bool einj_is_cxl_error_type(u64 type)
@@ -678,8 +839,7 @@ bool einj_is_cxl_error_type(u64 type)
 
 int einj_validate_error_type(u64 type)
 {
-	u32 tval, vendor, available_error_type = 0;
-	int rc;
+	u32 tval, vendor;
 
 	/* Only low 32 bits for error type are valid */
 	if (type & GENMASK_ULL(63, 32))
@@ -695,20 +855,36 @@ int einj_validate_error_type(u64 type)
 	/* Only one error type can be specified */
 	if (tval & (tval - 1))
 		return -EINVAL;
-	if (!vendor) {
-		rc = einj_get_available_error_type(&available_error_type);
-		if (rc)
-			return rc;
-		if (!(type & available_error_type))
+	if (!vendor)
+		if (!(type & (available_error_type | available_error_type_v2)))
 			return -EINVAL;
-	}
 
 	return 0;
 }
 
-static int error_type_set(void *data, u64 val)
+static ssize_t error_type_set(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
 {
 	int rc;
+	u64 val;
+
+	/* Leave the last character for the NUL terminator */
+	if (count > sizeof(einj_buf) - 1)
+		return -EINVAL;
+
+	memset(einj_buf, 0, sizeof(einj_buf));
+	if (copy_from_user(einj_buf, buf, count))
+		return -EFAULT;
+
+	if (strncmp(einj_buf, "V2_", 3) == 0) {
+		if (!sscanf(einj_buf, "V2_%llx", &val))
+			return -EINVAL;
+		is_v2 = true;
+	} else {
+		if (!sscanf(einj_buf, "%llx", &val))
+			return -EINVAL;
+		is_v2 = false;
+	}
 
 	rc = einj_validate_error_type(val);
 	if (rc)
@@ -716,17 +892,24 @@ static int error_type_set(void *data, u64 val)
 
 	error_type = val;
 
-	return 0;
+	return count;
 }
 
-DEFINE_DEBUGFS_ATTRIBUTE(error_type_fops, error_type_get, error_type_set,
-			 "0x%llx\n");
+static const struct file_operations error_type_fops = {
+	.read		= error_type_get,
+	.write		= error_type_set,
+};
 
 static int error_inject_set(void *data, u64 val)
 {
 	if (!error_type)
 		return -EINVAL;
 
+	if (is_v2)
+		error_flags |= SETWA_FLAGS_EINJV2;
+	else
+		error_flags &= ~SETWA_FLAGS_EINJV2;
+
 	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
 		error_param3, error_param4);
 }
@@ -749,17 +932,104 @@ static int einj_check_table(struct acpi_table_einj *einj_tab)
 	return 0;
 }
 
-static int __init einj_probe(struct platform_device *pdev)
+static ssize_t u128_read(struct file *f, char __user *buf, size_t count, loff_t *off)
+{
+	char output[2 * COMPONENT_LEN + 1];
+	u8 *data = f->f_inode->i_private;
+	int i;
+
+	if (*off >= sizeof(output))
+		return 0;
+
+	for (i = 0; i < COMPONENT_LEN; i++)
+		sprintf(output + 2 * i, "%.02x", data[COMPONENT_LEN - i - 1]);
+	output[2 * COMPONENT_LEN] = '\n';
+
+	return simple_read_from_buffer(buf, count, off, output, sizeof(output));
+}
+
+static ssize_t u128_write(struct file *f, const char __user *buf, size_t count, loff_t *off)
+{
+	char input[2 + 2 * COMPONENT_LEN + 2];
+	u8 *save = f->f_inode->i_private;
+	u8 tmp[COMPONENT_LEN];
+	char byte[3] = {};
+	char *s, *e;
+	ssize_t c;
+	long val;
+	int i;
+
+	/* Require that user supply whole input line in one write(2) syscall */
+	if (*off)
+		return -EINVAL;
+
+	c = simple_write_to_buffer(input, sizeof(input), off, buf, count);
+	if (c < 0)
+		return c;
+
+	if (c < 1 || input[c - 1] != '\n')
+		return -EINVAL;
+
+	/* Empty line means invalidate this entry */
+	if (c == 1) {
+		memset(save, 0xff, COMPONENT_LEN);
+		return c;
+	}
+
+	if (input[0] == '0' && (input[1] == 'x' || input[1] == 'X'))
+		s = input + 2;
+	else
+		s = input;
+	e = input + c - 1;
+
+	for (i = 0; i < COMPONENT_LEN; i++) {
+		byte[1] = *--e;
+		byte[0] = e > s ? *--e : '0';
+		if (kstrtol(byte, 16, &val))
+			return -EINVAL;
+		tmp[i] = val;
+		if (e <= s)
+			break;
+	}
+	while (++i < COMPONENT_LEN)
+		tmp[i] = 0;
+
+	memcpy(save, tmp, COMPONENT_LEN);
+
+	return c;
+}
+
+static const struct file_operations u128_fops = {
+	.read	= u128_read,
+	.write	= u128_write,
+};
+
+static bool setup_einjv2_component_files(void)
+{
+	char name[32];
+
+	syndrome_data = kcalloc(max_nr_components, sizeof(syndrome_data[0]), GFP_KERNEL);
+	if (!syndrome_data)
+		return false;
+
+	for (int i = 0; i < max_nr_components; i++) {
+		sprintf(name, "component_id%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_id, &u128_fops);
+		sprintf(name, "component_syndrome%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_synd, &u128_fops);
+	}
+
+	return true;
+}
+
+static int __init einj_probe(struct faux_device *fdev)
 {
 	int rc;
 	acpi_status status;
 	struct apei_exec_context ctx;
 
-	if (acpi_disabled) {
-		pr_debug("ACPI disabled.\n");
-		return -ENODEV;
-	}
-
 	status = acpi_get_table(ACPI_SIG_EINJ, 0,
 				(struct acpi_table_header **)&einj_tab);
 	if (status == AE_NOT_FOUND) {
@@ -777,6 +1047,10 @@ static int __init einj_probe(struct platform_device *pdev)
 		goto err_put_table;
 	}
 
+	rc = einj_get_available_error_types(&available_error_type, &available_error_type_v2);
+	if (rc)
+		goto err_put_table;
+
 	rc = -ENOMEM;
 	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
 
@@ -821,6 +1095,8 @@ static int __init einj_probe(struct platform_device *pdev)
 				   &error_param4);
 		debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
 				   einj_debug_dir, &notrigger);
+		if (available_error_type & ACPI65_EINJV2_SUPP)
+			einj_v2_enabled = setup_einjv2_component_files();
 	}
 
 	if (vendor_dev[0]) {
@@ -851,13 +1127,13 @@ err_put_table:
 	return rc;
 }
 
-static void __exit einj_remove(struct platform_device *pdev)
+static void einj_remove(struct faux_device *fdev)
 {
 	struct apei_exec_context ctx;
 
 	if (einj_param) {
 		acpi_size size = (acpi5) ?
-			sizeof(struct set_error_type_with_address) :
+			v5param_size :
 			sizeof(struct einj_parameter);
 
 		acpi_os_unmap_iomem(einj_param, size);
@@ -869,47 +1145,34 @@ static void __exit einj_remove(struct platform_device *pdev)
 	apei_resources_release(&einj_resources);
 	apei_resources_fini(&einj_resources);
 	debugfs_remove_recursive(einj_debug_dir);
+	kfree(syndrome_data);
 	acpi_put_table((struct acpi_table_header *)einj_tab);
 }
 
-static struct platform_device *einj_dev;
-/*
- * einj_remove() lives in .exit.text. For drivers registered via
- * platform_driver_probe() this is ok because they cannot get unbound at
- * runtime. So mark the driver struct with __refdata to prevent modpost
- * triggering a section mismatch warning.
- */
-static struct platform_driver einj_driver __refdata = {
-	.remove = __exit_p(einj_remove),
-	.driver = {
-		.name = "acpi-einj",
-	},
+static struct faux_device *einj_dev;
+static struct faux_device_ops einj_device_ops = {
+	.probe = einj_probe,
+	.remove = einj_remove,
 };
 
 static int __init einj_init(void)
 {
-	struct platform_device_info einj_dev_info = {
-		.name = "acpi-einj",
-		.id = -1,
-	};
-	int rc;
+	if (acpi_disabled) {
+		pr_debug("ACPI disabled.\n");
+		return -ENODEV;
+	}
 
-	einj_dev = platform_device_register_full(&einj_dev_info);
-	if (IS_ERR(einj_dev))
-		return PTR_ERR(einj_dev);
+	einj_dev = faux_device_create("acpi-einj", NULL, &einj_device_ops);
 
-	rc = platform_driver_probe(&einj_driver, einj_probe);
-	einj_initialized = rc == 0;
+	if (einj_dev)
+		einj_initialized = true;
 
 	return 0;
 }
 
 static void __exit einj_exit(void)
 {
-	if (einj_initialized)
-		platform_driver_unregister(&einj_driver);
-
-	platform_device_unregister(einj_dev);
+	faux_device_destroy(einj_dev);
 }
 
 module_init(einj_init);
diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
index 78da9ae543a2..e70a416ec925 100644
--- a/drivers/acpi/apei/einj-cxl.c
+++ b/drivers/acpi/apei/einj-cxl.c
@@ -30,7 +30,7 @@ int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
 	int cxl_err, rc;
 	u32 available_error_type = 0;
 
-	rc = einj_get_available_error_type(&available_error_type);
+	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
 	if (rc)
 		return rc;
 
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index 246076341e8c..ff0e8bf8e97a 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -60,9 +60,8 @@ static long erst_dbg_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case APEI_ERST_CLEAR_RECORD:
-		rc = copy_from_user(&record_id, (void __user *)arg,
-				    sizeof(record_id));
-		if (rc)
+		if (copy_from_user(&record_id, (void __user *)arg,
+				   sizeof(record_id)))
 			return -EFAULT;
 		return erst_clear(record_id);
 	case APEI_ERST_GET_RECORD_COUNT:
@@ -175,8 +174,7 @@ static ssize_t erst_dbg_write(struct file *filp, const char __user *ubuf,
 		erst_dbg_buf = p;
 		erst_dbg_buf_len = usize;
 	}
-	rc = copy_from_user(erst_dbg_buf, ubuf, usize);
-	if (rc) {
+	if (copy_from_user(erst_dbg_buf, ubuf, usize)) {
 		rc = -EFAULT;
 		goto out;
 	}
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index b72772494655..97ee19f2cae0 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -464,28 +464,41 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-/*
- * Called as task_work before returning to user-space.
- * Ensure any queued work has been done before we return to the context that
- * triggered the notification.
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
  */
-static void ghes_kick_task_work(struct callback_head *head)
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
 {
-	struct acpi_hest_generic_status *estatus;
-	struct ghes_estatus_node *estatus_node;
-	u32 node_len;
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
 
-	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
-	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		memory_failure_queue_kick(estatus_node->task_work_cpu);
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
 
-	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
 }
 
 static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
+	struct ghes_task_work *twcb;
 	unsigned long pfn;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
@@ -499,6 +512,18 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 		return false;
 	}
 
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
+	}
+
 	memory_failure_queue(pfn, flags);
 	return true;
 }
@@ -674,6 +699,105 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/* Room for 8 entries */
+#define CXL_CPER_PROT_ERR_FIFO_DEPTH 8
+static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
+		    CXL_CPER_PROT_ERR_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
+static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
+struct work_struct *cxl_cper_prot_err_work;
+
+static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				   int severity)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+	u8 *dvsec_start, *cap_start;
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
+		pr_err_ratelimited("CXL CPER invalid agent type\n");
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
+		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
+		return;
+	}
+
+	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
+		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
+				   prot_err->err_len);
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
+		pr_warn(FW_WARN "CXL CPER no device serial number\n");
+
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
+	switch (prot_err->agent_type) {
+	case RCD:
+	case DEVICE:
+	case LD:
+	case FMLD:
+	case RP:
+	case DSP:
+	case USP:
+		memcpy(&wd.prot_err, prot_err, sizeof(wd.prot_err));
+
+		dvsec_start = (u8 *)(prot_err + 1);
+		cap_start = dvsec_start + prot_err->dvsec_len;
+
+		memcpy(&wd.ras_cap, cap_start, sizeof(wd.ras_cap));
+		wd.severity = cper_severity_to_aer(severity);
+		break;
+	default:
+		pr_err_ratelimited("CXL CPER invalid agent type: %d\n",
+				   prot_err->agent_type);
+		return;
+	}
+
+	if (!kfifo_put(&cxl_cper_prot_err_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_prot_err_work);
+#endif
+}
+
+int cxl_cper_register_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
+
+int cxl_cper_unregister_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
+
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_prot_err_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
+
 /* Room for 8 entries for each of the 4 event log queues */
 #define CXL_CPER_FIFO_DEPTH 32
 DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
@@ -743,7 +867,7 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
 
-static bool ghes_do_proc(struct ghes *ghes,
+static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
@@ -777,6 +901,10 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_prot_err(prot_err, gdata->error_severity);
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
 
@@ -799,7 +927,16 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 	}
 
-	return queued;
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(ghes->dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -985,6 +1122,8 @@ static void __ghes_panic(struct ghes *ghes,
 
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
 	if (!panic_timeout)
@@ -1035,7 +1174,7 @@ static void ghes_add_timer(struct ghes *ghes)
 
 static void ghes_poll_func(struct timer_list *t)
 {
-	struct ghes *ghes = from_timer(ghes, t, timer);
+	struct ghes *ghes = timer_container_of(ghes, t, timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -1068,12 +1207,10 @@ static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
 	int ret = NOTIFY_DONE;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
-	rcu_read_lock();
 	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
 		if (!ghes_proc(ghes))
 			ret = NOTIFY_OK;
 	}
-	rcu_read_unlock();
 	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 
 	return ret;
@@ -1103,9 +1240,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	bool task_work_pending;
 	u32 len, node_len;
-	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -1120,25 +1255,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
-		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
+
+		ghes_do_proc(estatus_node->ghes, estatus);
+
 		if (!ghes_estatus_cached(estatus)) {
 			generic = estatus_node->generic;
 			if (ghes_print_estatus(NULL, generic, estatus))
 				ghes_estatus_cache_add(generic, estatus);
 		}
-
-		if (task_work_pending && current->mm) {
-			estatus_node->task_work.func = ghes_kick_task_work;
-			estatus_node->task_work_cpu = smp_processor_id();
-			ret = task_work_add(current, &estatus_node->task_work,
-					    TWA_RESUME);
-			if (ret)
-				estatus_node->task_work.func = NULL;
-		}
-
-		if (!estatus_node->task_work.func)
-			gen_pool_free(ghes_estatus_pool,
-				      (unsigned long)estatus_node, node_len);
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
 
 		llnode = next;
 	}
@@ -1199,7 +1325,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
-	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
@@ -1612,7 +1737,7 @@ void __init acpi_ghes_init(void)
 {
 	int rc;
 
-	sdei_init();
+	acpi_sdei_init();
 
 	if (acpi_disabled)
 		return;
diff --git a/drivers/acpi/arm64/dma.c b/drivers/acpi/arm64/dma.c
index 52b2abf88689..f30f138352b7 100644
--- a/drivers/acpi/arm64/dma.c
+++ b/drivers/acpi/arm64/dma.c
@@ -26,6 +26,11 @@ void acpi_arch_dma_setup(struct device *dev)
 	else
 		end = (1ULL << 32) - 1;
 
+	if (dev->dma_range_map) {
+		dev_dbg(dev, "dma_range_map already set\n");
+		return;
+	}
+
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
 		end = dma_range_map_max(map);
diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
index 70f8290b659d..fd995a1d3d24 100644
--- a/drivers/acpi/arm64/gtdt.c
+++ b/drivers/acpi/arm64/gtdt.c
@@ -388,11 +388,11 @@ static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
 	return 0;
 }
 
-static int __init gtdt_sbsa_gwdt_init(void)
+static int __init gtdt_platform_timer_init(void)
 {
 	void *platform_timer;
 	struct acpi_table_header *table;
-	int ret, timer_count, gwdt_count = 0;
+	int ret, timer_count, gwdt_count = 0, mmio_timer_count = 0;
 
 	if (acpi_disabled)
 		return 0;
@@ -414,20 +414,41 @@ static int __init gtdt_sbsa_gwdt_init(void)
 		goto out_put_gtdt;
 
 	for_each_platform_timer(platform_timer) {
+		ret = 0;
+
 		if (is_non_secure_watchdog(platform_timer)) {
 			ret = gtdt_import_sbsa_gwdt(platform_timer, gwdt_count);
 			if (ret)
-				break;
+				continue;
 			gwdt_count++;
+		} else 	if (is_timer_block(platform_timer)) {
+			struct arch_timer_mem atm = {};
+			struct platform_device *pdev;
+
+			ret = gtdt_parse_timer_block(platform_timer, &atm);
+			if (ret)
+				continue;
+
+			pdev = platform_device_register_data(NULL, "gtdt-arm-mmio-timer",
+							     gwdt_count, &atm,
+							     sizeof(atm));
+			if (IS_ERR(pdev)) {
+				pr_err("Can't register timer %d\n", gwdt_count);
+				continue;
+			}
+
+			mmio_timer_count++;
 		}
 	}
 
 	if (gwdt_count)
 		pr_info("found %d SBSA generic Watchdog(s).\n", gwdt_count);
+	if (mmio_timer_count)
+		pr_info("found %d Generic MMIO timer(s).\n", mmio_timer_count);
 
 out_put_gtdt:
 	acpi_put_table(table);
 	return ret;
 }
 
-device_initcall(gtdt_sbsa_gwdt_init);
+device_initcall(gtdt_platform_timer_init);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 98759d6199d3..65f0f56ad753 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -937,8 +937,10 @@ static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start,
 
 	new_sids = krealloc_array(sids, count + new_count,
 				  sizeof(*new_sids), GFP_KERNEL);
-	if (!new_sids)
+	if (!new_sids) {
+		kfree(sids);
 		return NULL;
+	}
 
 	for (i = count; i < total_count; i++)
 		new_sids[i] = id_start++;
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 6760330a8af5..67b76492c839 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -92,7 +92,7 @@ enum {
 
 struct acpi_battery {
 	struct mutex lock;
-	struct mutex sysfs_lock;
+	struct mutex update_lock;
 	struct power_supply *bat;
 	struct power_supply_desc bat_desc;
 	struct acpi_device *device;
@@ -279,8 +279,8 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		    full_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
 			ret = -ENODEV;
 		else
-			val->intval = battery->capacity_now * 100/
-					full_capacity;
+			val->intval = DIV_ROUND_CLOSEST_ULL(battery->capacity_now * 100ULL,
+					full_capacity);
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
 		if (battery->state & ACPI_BATTERY_STATE_CRITICAL)
@@ -904,15 +904,12 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 
 static void sysfs_remove_battery(struct acpi_battery *battery)
 {
-	mutex_lock(&battery->sysfs_lock);
-	if (!battery->bat) {
-		mutex_unlock(&battery->sysfs_lock);
+	if (!battery->bat)
 		return;
-	}
+
 	battery_hook_remove_battery(battery);
 	power_supply_unregister(battery->bat);
 	battery->bat = NULL;
-	mutex_unlock(&battery->sysfs_lock);
 }
 
 static void find_battery(const struct dmi_header *dm, void *private)
@@ -1072,6 +1069,9 @@ static void acpi_battery_notify(acpi_handle handle, u32 event, void *data)
 
 	if (!battery)
 		return;
+
+	guard(mutex)(&battery->update_lock);
+
 	old = battery->bat;
 	/*
 	 * On Acer Aspire V5-573G notifications are sometimes triggered too
@@ -1094,21 +1094,22 @@ static void acpi_battery_notify(acpi_handle handle, u32 event, void *data)
 }
 
 static int battery_notify(struct notifier_block *nb,
-			       unsigned long mode, void *_unused)
+			  unsigned long mode, void *_unused)
 {
 	struct acpi_battery *battery = container_of(nb, struct acpi_battery,
 						    pm_nb);
-	int result;
 
-	switch (mode) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
+	if (mode == PM_POST_SUSPEND || mode == PM_POST_HIBERNATION) {
+		guard(mutex)(&battery->update_lock);
+
 		if (!acpi_battery_present(battery))
 			return 0;
 
 		if (battery->bat) {
 			acpi_battery_refresh(battery);
 		} else {
+			int result;
+
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;
@@ -1120,7 +1121,6 @@ static int battery_notify(struct notifier_block *nb,
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
-		break;
 	}
 
 	return 0;
@@ -1198,6 +1198,8 @@ static int acpi_battery_update_retry(struct acpi_battery *battery)
 {
 	int retry, ret;
 
+	guard(mutex)(&battery->update_lock);
+
 	for (retry = 5; retry; retry--) {
 		ret = acpi_battery_update(battery, false);
 		if (!ret)
@@ -1208,6 +1210,13 @@ static int acpi_battery_update_retry(struct acpi_battery *battery)
 	return ret;
 }
 
+static void sysfs_battery_cleanup(struct acpi_battery *battery)
+{
+	guard(mutex)(&battery->update_lock);
+
+	sysfs_remove_battery(battery);
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -1230,7 +1239,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	if (result)
 		return result;
 
-	result = devm_mutex_init(&device->dev, &battery->sysfs_lock);
+	result = devm_mutex_init(&device->dev, &battery->update_lock);
 	if (result)
 		return result;
 
@@ -1262,7 +1271,7 @@ fail_pm:
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
 fail:
-	sysfs_remove_battery(battery);
+	sysfs_battery_cleanup(battery);
 
 	return result;
 }
@@ -1281,6 +1290,9 @@ static void acpi_battery_remove(struct acpi_device *device)
 
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
+
+	guard(mutex)(&battery->update_lock);
+
 	sysfs_remove_battery(battery);
 }
 
@@ -1297,6 +1309,9 @@ static int acpi_battery_resume(struct device *dev)
 		return -EINVAL;
 
 	battery->update_time = 0;
+
+	guard(mutex)(&battery->update_lock);
+
 	acpi_battery_update(battery, true);
 	return 0;
 }
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index 35ece8e9f15d..0fdd581ef96f 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -47,7 +47,7 @@ static const struct bin_attribute *const bgrt_bin_attributes[] = {
 
 static const struct attribute_group bgrt_attribute_group = {
 	.attrs = bgrt_attributes,
-	.bin_attrs_new = bgrt_bin_attributes,
+	.bin_attrs = bgrt_bin_attributes,
 };
 
 int __init acpi_parse_bgrt(struct acpi_table_header *table)
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 058910af82bc..a984ccd4a2a0 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1406,7 +1406,7 @@ static int __init acpi_bus_init(void)
 		goto error1;
 
 	/*
-	 * Register the for all standard device notifications.
+	 * Register for all standard device notifications.
 	 */
 	status =
 	    acpi_install_notify_handler(ACPI_ROOT_OBJECT, ACPI_SYSTEM_NOTIFY,
@@ -1446,8 +1446,10 @@ static int __init acpi_init(void)
 	}
 
 	acpi_kobj = kobject_create_and_add("acpi", firmware_kobj);
-	if (!acpi_kobj)
-		pr_debug("%s: kset create error\n", __func__);
+	if (!acpi_kobj) {
+		pr_err("Failed to register kobject\n");
+		return -ENOMEM;
+	}
 
 	init_prmt();
 	acpi_init_pcc();
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 7773e6b860e7..0a7026040188 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -24,6 +24,7 @@
 #define ACPI_BUTTON_CLASS		"button"
 #define ACPI_BUTTON_FILE_STATE		"state"
 #define ACPI_BUTTON_TYPE_UNKNOWN	0x00
+#define ACPI_BUTTON_NOTIFY_WAKE		0x02
 #define ACPI_BUTTON_NOTIFY_STATUS	0x80
 
 #define ACPI_BUTTON_SUBCLASS_POWER	"power"
@@ -443,7 +444,12 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
 	struct input_dev *input;
 	int keycode;
 
-	if (event != ACPI_BUTTON_NOTIFY_STATUS) {
+	switch (event) {
+	case ACPI_BUTTON_NOTIFY_STATUS:
+		break;
+	case ACPI_BUTTON_NOTIFY_WAKE:
+		break;
+	default:
 		acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n",
 				  event);
 		return;
@@ -452,7 +458,7 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
 	acpi_pm_wakeup_event(&device->dev);
 
 	button = acpi_driver_data(device);
-	if (button->suspended)
+	if (button->suspended || event == ACPI_BUTTON_NOTIFY_WAKE)
 		return;
 
 	input = button->input;
@@ -629,7 +635,7 @@ static int acpi_button_add(struct acpi_device *device)
 		break;
 	default:
 		status = acpi_install_notify_handler(device->handle,
-						     ACPI_DEVICE_NOTIFY, handler,
+						     ACPI_ALL_NOTIFY, handler,
 						     device);
 		break;
 	}
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index f193e713825a..ab4651205e8a 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -47,7 +47,6 @@
 
 struct cppc_pcc_data {
 	struct pcc_mbox_chan *pcc_channel;
-	void __iomem *pcc_comm_addr;
 	bool pcc_channel_acquired;
 	unsigned int deadline_us;
 	unsigned int pcc_mpar, pcc_mrtt, pcc_nominal;
@@ -95,7 +94,7 @@ static DEFINE_PER_CPU(int, cpu_pcc_subspace_idx);
 static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
 
 /* pcc mapped address + header size + offset within PCC subspace */
-#define GET_PCC_VADDR(offs, pcc_ss_id) (pcc_data[pcc_ss_id]->pcc_comm_addr + \
+#define GET_PCC_VADDR(offs, pcc_ss_id) (pcc_data[pcc_ss_id]->pcc_channel->shmem + \
 						0x8 + (offs))
 
 /* Check if a CPC register is in PCC */
@@ -129,6 +128,20 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
 #define CPC_SUPPORTED(cpc) ((cpc)->type == ACPI_TYPE_INTEGER ?		\
 				!!(cpc)->cpc_entry.int_value :		\
 				!IS_NULL_REG(&(cpc)->cpc_entry.reg))
+
+/*
+ * Each bit indicates the optionality of the register in per-cpu
+ * cpc_regs[] with the corresponding index. 0 means mandatory and 1
+ * means optional.
+ */
+#define REG_OPTIONAL (0x1FC7D0)
+
+/*
+ * Use the index of the register in per-cpu cpc_regs[] to check if
+ * it's an optional one.
+ */
+#define IS_OPTIONAL_CPC_REG(reg_idx) (REG_OPTIONAL & (1U << (reg_idx)))
+
 /*
  * Arbitrary Retries in case the remote processor is slow to respond
  * to PCC commands. Keeping it high enough to cover emulators where
@@ -223,7 +236,7 @@ static int check_pcc_chan(int pcc_ss_id, bool chk_err_bit)
 	int ret, status;
 	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
 	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
-		pcc_ss_data->pcc_comm_addr;
+					pcc_ss_data->pcc_channel->shmem;
 
 	if (!pcc_ss_data->platform_owns_pcc)
 		return 0;
@@ -258,7 +271,7 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd)
 	int ret = -EIO, i;
 	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
 	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
-		pcc_ss_data->pcc_comm_addr;
+					pcc_ss_data->pcc_channel->shmem;
 	unsigned int time_delta;
 
 	/*
@@ -463,7 +476,7 @@ bool cppc_allow_fast_switch(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
 		if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&
@@ -571,15 +584,6 @@ static int register_pcc_channel(int pcc_ss_idx)
 		pcc_data[pcc_ss_idx]->pcc_mpar = pcc_chan->max_access_rate;
 		pcc_data[pcc_ss_idx]->pcc_nominal = pcc_chan->latency;
 
-		pcc_data[pcc_ss_idx]->pcc_comm_addr =
-			acpi_os_ioremap(pcc_chan->shmem_base_addr,
-					pcc_chan->shmem_size);
-		if (!pcc_data[pcc_ss_idx]->pcc_comm_addr) {
-			pr_err("Failed to ioremap PCC comm region mem for %d\n",
-			       pcc_ss_idx);
-			return -ENOMEM;
-		}
-
 		/* Set flag so that we don't come here for each CPU. */
 		pcc_data[pcc_ss_idx]->pcc_channel_acquired = true;
 	}
@@ -1175,43 +1179,106 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 	return ret_val;
 }
 
-static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
+static int cppc_get_reg_val_in_pcc(int cpu, struct cpc_register_resource *reg, u64 *val)
 {
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret;
+
+	if (pcc_ss_id < 0) {
+		pr_debug("Invalid pcc_ss_id\n");
+		return -ENODEV;
+	}
+
+	pcc_ss_data = pcc_data[pcc_ss_id];
+
+	down_write(&pcc_ss_data->pcc_lock);
+
+	if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
+		ret = cpc_read(cpu, reg, val);
+	else
+		ret = -EIO;
+
+	up_write(&pcc_ss_data->pcc_lock);
+
+	return ret;
+}
+
+static int cppc_get_reg_val(int cpu, enum cppc_regs reg_idx, u64 *val)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
 	struct cpc_register_resource *reg;
 
+	if (val == NULL)
+		return -EINVAL;
+
 	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
 		return -ENODEV;
 	}
 
 	reg = &cpc_desc->cpc_regs[reg_idx];
 
-	if (CPC_IN_PCC(reg)) {
-		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-		struct cppc_pcc_data *pcc_ss_data = NULL;
-		int ret = 0;
-
-		if (pcc_ss_id < 0)
-			return -EIO;
+	if ((reg->type == ACPI_TYPE_INTEGER && IS_OPTIONAL_CPC_REG(reg_idx) &&
+	     !reg->cpc_entry.int_value) || (reg->type != ACPI_TYPE_INTEGER &&
+	     IS_NULL_REG(&reg->cpc_entry.reg))) {
+		pr_debug("CPC register is not supported\n");
+		return -EOPNOTSUPP;
+	}
 
-		pcc_ss_data = pcc_data[pcc_ss_id];
+	if (CPC_IN_PCC(reg))
+		return cppc_get_reg_val_in_pcc(cpu, reg, val);
 
-		down_write(&pcc_ss_data->pcc_lock);
+	return cpc_read(cpu, reg, val);
+}
 
-		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
-			cpc_read(cpunum, reg, perf);
-		else
-			ret = -EIO;
+static int cppc_set_reg_val_in_pcc(int cpu, struct cpc_register_resource *reg, u64 val)
+{
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret;
 
-		up_write(&pcc_ss_data->pcc_lock);
+	if (pcc_ss_id < 0) {
+		pr_debug("Invalid pcc_ss_id\n");
+		return -ENODEV;
+	}
 
+	ret = cpc_write(cpu, reg, val);
+	if (ret)
 		return ret;
+
+	pcc_ss_data = pcc_data[pcc_ss_id];
+
+	down_write(&pcc_ss_data->pcc_lock);
+	/* after writing CPC, transfer the ownership of PCC to platform */
+	ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
+	up_write(&pcc_ss_data->pcc_lock);
+
+	return ret;
+}
+
+static int cppc_set_reg_val(int cpu, enum cppc_regs reg_idx, u64 val)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cpc_register_resource *reg;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
 	}
 
-	cpc_read(cpunum, reg, perf);
+	reg = &cpc_desc->cpc_regs[reg_idx];
 
-	return 0;
+	/* if a register is writeable, it must be a buffer and not null */
+	if ((reg->type != ACPI_TYPE_BUFFER) || IS_NULL_REG(&reg->cpc_entry.reg)) {
+		pr_debug("CPC register is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (CPC_IN_PCC(reg))
+		return cppc_set_reg_val_in_pcc(cpu, reg, val);
+
+	return cpc_write(cpu, reg, val);
 }
 
 /**
@@ -1223,7 +1290,7 @@ static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
  */
 int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
-	return cppc_get_perf(cpunum, DESIRED_PERF, desired_perf);
+	return cppc_get_reg_val(cpunum, DESIRED_PERF, desired_perf);
 }
 EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
 
@@ -1236,7 +1303,7 @@ EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
  */
 int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 {
-	return cppc_get_perf(cpunum, NOMINAL_PERF, nominal_perf);
+	return cppc_get_reg_val(cpunum, NOMINAL_PERF, nominal_perf);
 }
 
 /**
@@ -1248,7 +1315,7 @@ int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
  */
 int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
 {
-	return cppc_get_perf(cpunum, HIGHEST_PERF, highest_perf);
+	return cppc_get_reg_val(cpunum, HIGHEST_PERF, highest_perf);
 }
 EXPORT_SYMBOL_GPL(cppc_get_highest_perf);
 
@@ -1261,7 +1328,7 @@ EXPORT_SYMBOL_GPL(cppc_get_highest_perf);
  */
 int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
 {
-	return cppc_get_perf(cpunum, ENERGY_PERF, epp_perf);
+	return cppc_get_reg_val(cpunum, ENERGY_PERF, epp_perf);
 }
 EXPORT_SYMBOL_GPL(cppc_get_epp_perf);
 
@@ -1535,53 +1602,110 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 EXPORT_SYMBOL_GPL(cppc_set_epp_perf);
 
 /**
- * cppc_get_auto_sel_caps - Read autonomous selection register.
- * @cpunum : CPU from which to read register.
- * @perf_caps : struct where autonomous selection register value is updated.
+ * cppc_set_epp() - Write the EPP register.
+ * @cpu: CPU on which to write register.
+ * @epp_val: Value to write to the EPP register.
  */
-int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+int cppc_set_epp(int cpu, u64 epp_val)
 {
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
-	struct cpc_register_resource *auto_sel_reg;
-	u64  auto_sel;
+	if (epp_val > CPPC_ENERGY_PERF_MAX)
+		return -EINVAL;
 
-	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
-		return -ENODEV;
-	}
+	return cppc_set_reg_val(cpu, ENERGY_PERF, epp_val);
+}
+EXPORT_SYMBOL_GPL(cppc_set_epp);
 
-	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+/**
+ * cppc_get_auto_act_window() - Read autonomous activity window register.
+ * @cpu: CPU from which to read register.
+ * @auto_act_window: Return address.
+ *
+ * According to ACPI 6.5, s8.4.6.1.6, the value read from the autonomous
+ * activity window register consists of two parts: a 7 bits value indicate
+ * significand and a 3 bits value indicate exponent.
+ */
+int cppc_get_auto_act_window(int cpu, u64 *auto_act_window)
+{
+	unsigned int exp;
+	u64 val, sig;
+	int ret;
 
-	if (!CPC_SUPPORTED(auto_sel_reg))
-		pr_warn_once("Autonomous mode is not unsupported!\n");
+	if (auto_act_window == NULL)
+		return -EINVAL;
 
-	if (CPC_IN_PCC(auto_sel_reg)) {
-		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-		struct cppc_pcc_data *pcc_ss_data = NULL;
-		int ret = 0;
+	ret = cppc_get_reg_val(cpu, AUTO_ACT_WINDOW, &val);
+	if (ret)
+		return ret;
 
-		if (pcc_ss_id < 0)
-			return -ENODEV;
+	sig = val & CPPC_AUTO_ACT_WINDOW_MAX_SIG;
+	exp = (val >> CPPC_AUTO_ACT_WINDOW_SIG_BIT_SIZE) & CPPC_AUTO_ACT_WINDOW_MAX_EXP;
+	*auto_act_window = sig * int_pow(10, exp);
 
-		pcc_ss_data = pcc_data[pcc_ss_id];
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_auto_act_window);
 
-		down_write(&pcc_ss_data->pcc_lock);
+/**
+ * cppc_set_auto_act_window() - Write autonomous activity window register.
+ * @cpu: CPU on which to write register.
+ * @auto_act_window: usec value to write to the autonomous activity window register.
+ *
+ * According to ACPI 6.5, s8.4.6.1.6, the value to write to the autonomous
+ * activity window register consists of two parts: a 7 bits value indicate
+ * significand and a 3 bits value indicate exponent.
+ */
+int cppc_set_auto_act_window(int cpu, u64 auto_act_window)
+{
+	/* The max value to store is 1270000000 */
+	u64 max_val = CPPC_AUTO_ACT_WINDOW_MAX_SIG * int_pow(10, CPPC_AUTO_ACT_WINDOW_MAX_EXP);
+	int exp = 0;
+	u64 val;
 
-		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) {
-			cpc_read(cpunum, auto_sel_reg, &auto_sel);
-			perf_caps->auto_sel = (bool)auto_sel;
-		} else {
-			ret = -EIO;
-		}
+	if (auto_act_window > max_val)
+		return -EINVAL;
 
-		up_write(&pcc_ss_data->pcc_lock);
+	/*
+	 * The max significand is 127, when auto_act_window is larger than
+	 * 129, discard the precision of the last digit and increase the
+	 * exponent by 1.
+	 */
+	while (auto_act_window > CPPC_AUTO_ACT_WINDOW_SIG_CARRY_THRESH) {
+		auto_act_window /= 10;
+		exp += 1;
+	}
+
+	/* For 128 and 129, cut it to 127. */
+	if (auto_act_window > CPPC_AUTO_ACT_WINDOW_MAX_SIG)
+		auto_act_window = CPPC_AUTO_ACT_WINDOW_MAX_SIG;
 
+	val = (exp << CPPC_AUTO_ACT_WINDOW_SIG_BIT_SIZE) + auto_act_window;
+
+	return cppc_set_reg_val(cpu, AUTO_ACT_WINDOW, val);
+}
+EXPORT_SYMBOL_GPL(cppc_set_auto_act_window);
+
+/**
+ * cppc_get_auto_sel() - Read autonomous selection register.
+ * @cpu: CPU from which to read register.
+ * @enable: Return address.
+ */
+int cppc_get_auto_sel(int cpu, bool *enable)
+{
+	u64 auto_sel;
+	int ret;
+
+	if (enable == NULL)
+		return -EINVAL;
+
+	ret = cppc_get_reg_val(cpu, AUTO_SEL_ENABLE, &auto_sel);
+	if (ret)
 		return ret;
-	}
+
+	*enable = (bool)auto_sel;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
+EXPORT_SYMBOL_GPL(cppc_get_auto_sel);
 
 /**
  * cppc_set_auto_sel - Write autonomous selection register.
@@ -1590,43 +1714,7 @@ EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
  */
 int cppc_set_auto_sel(int cpu, bool enable)
 {
-	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
-	struct cpc_register_resource *auto_sel_reg;
-	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
-	struct cppc_pcc_data *pcc_ss_data = NULL;
-	int ret = -EINVAL;
-
-	if (!cpc_desc) {
-		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
-		return -ENODEV;
-	}
-
-	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
-
-	if (CPC_IN_PCC(auto_sel_reg)) {
-		if (pcc_ss_id < 0) {
-			pr_debug("Invalid pcc_ss_id\n");
-			return -ENODEV;
-		}
-
-		if (CPC_SUPPORTED(auto_sel_reg)) {
-			ret = cpc_write(cpu, auto_sel_reg, enable);
-			if (ret)
-				return ret;
-		}
-
-		pcc_ss_data = pcc_data[pcc_ss_id];
-
-		down_write(&pcc_ss_data->pcc_lock);
-		/* after writing CPC, transfer the ownership of PCC to platform */
-		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
-		up_write(&pcc_ss_data->pcc_lock);
-	} else {
-		ret = -ENOTSUPP;
-		pr_debug("_CPC in PCC is not supported\n");
-	}
-
-	return ret;
+	return cppc_set_reg_val(cpu, AUTO_SEL_ENABLE, enable);
 }
 EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
 
@@ -1640,38 +1728,7 @@ EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
  */
 int cppc_set_enable(int cpu, bool enable)
 {
author	Masahiro Yamada <yamada.masahiro@socionext.com>	2019-01-25 16:32:46 +0900
committer	Paolo Bonzini <pbonzini@redhat.com>	2019-01-25 19:12:37 +0100
commit	5cd5548ff439b916cf72448109994394c2bf4b3c (patch)
tree	cf7edbe7a691111e86b5fcaea9f08ea64f3026cb /tools/perf/scripts/python/stackcollapse.py
parent	35b531a1e7fc30ac8c62e5ac1794eb1460da614e (diff)