Merge tag 'timers-v6.11-rc1' of https://git.linaro.org/people/daniel.lezcano/linux into timers/core

Pull clocksource/event driver updates from Daniel Lezcano:

  - Remove unnecessary local variables initialization as they will be
    initialized in the code path anyway right after on the ARM arch
    timer and the ARM global timer (Li kunyu)

  - Fix a race condition in the interrupt leading to a deadlock on the
    SH CMT driver. Note that this fix was not tested on the platform
    using this timer but the fix seems reasonable enough to be picked
    confidently (Niklas Söderlund)

  - Increase the rating of the gic-timer and use the configured width
    clocksource register on the MIPS architecture (Jiaxun Yang)

  - Add the DT bindings for the TMU on the Renesas platforms (Geert
    Uytterhoeven)

  - Add the DT bindings for the SOPHGO SG2002 clint on RiscV (Thomas
    Bonnefille)

  - Add the rtl-otto timer driver along with the DT bindings for the
    Realtek platform (Chris Packham)

Link: https://lore.kernel.org/all/91cd05de-4c5d-4242-a381-3b8a4fe6a2a2@linaro.org

14 files changed, 147 insertions, 126 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 108003bdf1e9..2e13c7c4b2b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -400,7 +400,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = vram_info->v30.channel_num;
 					mem_channel_width = vram_info->v30.channel_width;
 					if (vram_width)
-						*vram_width = mem_channel_number * (1 << mem_channel_width);
+						*vram_width = mem_channel_number * 16;
 					break;
 				default:
 					return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 932dc93b2e63..33f791d92ddf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5220,11 +5220,14 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 
 	dev_info(adev->dev, "GPU mode1 reset\n");
 
+	/* Cache the state before bus master disable. The saved config space
+	 * values are used in other cases like restore after mode-2 reset.
+	 */
+	amdgpu_device_cache_pci_state(adev->pdev);
+
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 
-	amdgpu_device_cache_pci_state(adev->pdev);
-
 	if (amdgpu_dpm_is_mode1_reset_supported(adev)) {
 		dev_info(adev->dev, "GPU smu mode1 reset\n");
 		ret = amdgpu_dpm_mode1_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 055ba2ea4c12..662d0f28f358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -41,8 +41,6 @@
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
-#include <linux/pm_runtime.h>
-#include "amdgpu_trace.h"
 
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
@@ -58,42 +56,11 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	int r;
 
 	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
-	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(1, __func__);
-	if (r < 0)
-		goto out;
-
 	return 0;
-
-out:
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(0, __func__);
-	return r;
-}
-
-/**
- * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
- *
- * @dmabuf: DMA-buf where we remove the attachment from
- * @attach: the attachment to remove
- *
- * Called when an attachment is removed from the DMA-buf.
- */
-static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
-				  struct dma_buf_attachment *attach)
-{
-	struct drm_gem_object *obj = dmabuf->priv;
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-
-	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(0, __func__);
 }
 
 /**
@@ -267,7 +234,6 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.attach = amdgpu_dma_buf_attach,
-	.detach = amdgpu_dma_buf_detach,
 	.pin = amdgpu_dma_buf_pin,
 	.unpin = amdgpu_dma_buf_unpin,
 	.map_dma_buf = amdgpu_dma_buf_map,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 10832b470448..bc3ac73b6b8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -181,7 +181,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
 	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(1, __func__);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
 		struct dma_fence *old;
@@ -309,7 +308,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 		dma_fence_put(fence);
 		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-		trace_amdgpu_runpm_reference_dumps(0, __func__);
 	} while (last_seq != seq);
 
 	return true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 67c234bcf89f..3adaa4670103 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -108,6 +108,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 
 	memset(&bp, 0, sizeof(bp));
 	*obj = NULL;
+	flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
 
 	bp.size = size;
 	bp.byte_align = alignment;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index be4629cdac04..08b9dfb65335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -684,12 +684,17 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	signed long r;
+	int r;
 	uint32_t seq;
 
-	if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready ||
-	    !down_read_trylock(&adev->reset_domain->sem)) {
+	/*
+	 * A GPU reset should flush all TLBs anyway, so no need to do
+	 * this while one is ongoing.
+	 */
+	if (!down_read_trylock(&adev->reset_domain->sem))
+		return 0;
 
+	if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) {
 		if (adev->gmc.flush_tlb_needs_extra_type_2)
 			adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid,
 								 2, all_hub,
@@ -703,43 +708,40 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 		adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid,
 							 flush_type, all_hub,
 							 inst);
-		return 0;
-	}
+		r = 0;
+	} else {
+		/* 2 dwords flush + 8 dwords fence */
+		ndw = kiq->pmf->invalidate_tlbs_size + 8;
 
-	/* 2 dwords flush + 8 dwords fence */
-	ndw = kiq->pmf->invalidate_tlbs_size + 8;
+		if (adev->gmc.flush_tlb_needs_extra_type_2)
+			ndw += kiq->pmf->invalidate_tlbs_size;
 
-	if (adev->gmc.flush_tlb_needs_extra_type_2)
-		ndw += kiq->pmf->invalidate_tlbs_size;
+		if (adev->gmc.flush_tlb_needs_extra_type_0)
+			ndw += kiq->pmf->invalidate_tlbs_size;
 
-	if (adev->gmc.flush_tlb_needs_extra_type_0)
-		ndw += kiq->pmf->invalidate_tlbs_size;
+		spin_lock(&adev->gfx.kiq[inst].ring_lock);
+		amdgpu_ring_alloc(ring, ndw);
+		if (adev->gmc.flush_tlb_needs_extra_type_2)
+			kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);
 
-	spin_lock(&adev->gfx.kiq[inst].ring_lock);
-	amdgpu_ring_alloc(ring, ndw);
-	if (adev->gmc.flush_tlb_needs_extra_type_2)
-		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);
+		if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0)
+			kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub);
 
-	if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0)
-		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub);
+		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub);
+		r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+		if (r) {
+			amdgpu_ring_undo(ring);
+			spin_unlock(&adev->gfx.kiq[inst].ring_lock);
+			goto error_unlock_reset;
+		}
 
-	kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub);
-	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
-	if (r) {
-		amdgpu_ring_undo(ring);
+		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		goto error_unlock_reset;
-	}
-
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-	r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
-	if (r < 1) {
-		dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
-		r = -ETIME;
-		goto error_unlock_reset;
+		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+			dev_err(adev->dev, "timeout waiting for kiq fence\n");
+			r = -ETIME;
+		}
 	}
-	r = 0;
 
 error_unlock_reset:
 	up_read(&adev->reset_domain->sem);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 8d8c39be6129..c556c8b653fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -604,8 +604,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (!amdgpu_bo_support_uswc(bo->flags))
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 
-	bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
-
 	bo->tbo.bdev = &adev->mman.bdev;
 	if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA |
 			  AMDGPU_GEM_DOMAIN_GDS))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 4bd4602d11b1..cef9dd0a012b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -640,6 +640,20 @@ static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id)
 	}
 }
 
+static bool psp_err_warn(struct psp_context *psp)
+{
+	struct psp_gfx_cmd_resp *cmd = psp->cmd_buf_mem;
+
+	/* This response indicates reg list is already loaded */
+	if (amdgpu_ip_version(psp->adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 2) &&
+	    cmd->cmd_id == GFX_CMD_ID_LOAD_IP_FW &&
+	    cmd->cmd.cmd_load_ip_fw.fw_type == GFX_FW_TYPE_REG_LIST &&
+	    cmd->resp.status == TEE_ERROR_CANCEL)
+		return false;
+
+	return true;
+}
+
 static int
 psp_cmd_submit_buf(struct psp_context *psp,
 		   struct amdgpu_firmware_info *ucode,
@@ -699,10 +713,13 @@ psp_cmd_submit_buf(struct psp_context *psp,
 			dev_warn(psp->adev->dev,
 				 "failed to load ucode %s(0x%X) ",
 				 amdgpu_ucode_name(ucode->ucode_id), ucode->ucode_id);
-		dev_warn(psp->adev->dev,
-			 "psp gfx command %s(0x%X) failed and response status is (0x%X)\n",
-			 psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id), psp->cmd_buf_mem->cmd_id,
-			 psp->cmd_buf_mem->resp.status);
+		if (psp_err_warn(psp))
+			dev_warn(
+				psp->adev->dev,
+				"psp gfx command %s(0x%X) failed and response status is (0x%X)\n",
+				psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id),
+				psp->cmd_buf_mem->cmd_id,
+				psp->cmd_buf_mem->resp.status);
 		/* If any firmware (including CAP) load fails under SRIOV, it should
 		 * return failure to stop the VF from initializing.
 		 * Also return failure in case of timeout
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 7aafeb763e5d..383fce40d4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -554,21 +554,6 @@ TRACE_EVENT(amdgpu_reset_reg_dumps,
 		      __entry->value)
 );
 
-TRACE_EVENT(amdgpu_runpm_reference_dumps,
-	    TP_PROTO(uint32_t index, const char *func),
-	    TP_ARGS(index, func),
-	    TP_STRUCT__entry(
-			     __field(uint32_t, index)
-			     __string(func, func)
-			     ),
-	    TP_fast_assign(
-			   __entry->index = index;
-			   __assign_str(func);
-			   ),
-	    TP_printk("amdgpu runpm reference dump 0x%x: 0x%s\n",
-		      __entry->index,
-		      __get_str(func))
-);
 #undef AMDGPU_JOB_GET_TIMELINE_NAME
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index e30eecd02ae1..fde66225c481 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -3,6 +3,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_simple_kms_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_vblank.h>
 
 #include "amdgpu.h"
@@ -314,7 +315,13 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
 		return 0;
 	}
 	afb = to_amdgpu_framebuffer(new_state->fb);
-	obj = new_state->fb->obj[0];
+
+	obj = drm_gem_fb_get_obj(new_state->fb, 0);
+	if (!obj) {
+		DRM_ERROR("Failed to get obj from framebuffer\n");
+		return -EINVAL;
+	}
+
 	rbo = gem_to_amdgpu_bo(obj);
 	adev = amdgpu_ttm_adev(rbo->tbo.bdev);
 
@@ -368,12 +375,19 @@ static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane,
 				   struct drm_plane_state *old_state)
 {
 	struct amdgpu_bo *rbo;
+	struct drm_gem_object *obj;
 	int r;
 
 	if (!old_state->fb)
 		return;
 
-	rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]);
+	obj = drm_gem_fb_get_obj(old_state->fb, 0);
+	if (!obj) {
+		DRM_ERROR("Failed to get obj from framebuffer\n");
+		return;
+	}
+
+	rbo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(rbo, false);
 	if (unlikely(r)) {
 		DRM_ERROR("failed to reserve rbo before unpin\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 7b16e8cca86a..f5b9f443cfdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -4195,9 +4195,10 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_i
 static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				 struct amdgpu_cu_info *cu_info)
 {
-	int i, j, k, counter, xcc_id, active_cu_number = 0;
-	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
+	int i, j, k, prev_counter, counter, xcc_id, active_cu_number = 0;
+	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0, tmp;
 	unsigned disable_masks[4 * 4];
+	bool is_symmetric_cus;
 
 	if (!adev || !cu_info)
 		return -EINVAL;
@@ -4215,6 +4216,7 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) {
+		is_symmetric_cus = true;
 		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
 				mask = 1;
@@ -4242,6 +4244,15 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 					ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
 				cu_info->ao_cu_bitmap[i][j] = ao_bitmap;
 			}
+			if (i && is_symmetric_cus && prev_counter != counter)
+				is_symmetric_cus = false;
+			prev_counter = counter;
+		}
+		if (is_symmetric_cus) {
+			tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG);
+			tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_RELAUNCH_DISABLE, 1);
+			tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_DISPATCH_DISABLE, 1);
+			WREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG, tmp);
 		}
 		gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
 					    xcc_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 0d1407f25005..32d4519541c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -154,18 +154,18 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 						    void *pkt, int size,
 						    int api_status_off)
 {
-	int ndw = size / 4;
-	signed long r;
-	union MESAPI__MISC *x_pkt = pkt;
-	struct MES_API_STATUS *api_status;
+	union MESAPI__QUERY_MES_STATUS mes_status_pkt;
+	signed long timeout = 3000000; /* 3000 ms */
 	struct amdgpu_device *adev = mes->adev;
 	struct amdgpu_ring *ring = &mes->ring;
-	unsigned long flags;
-	signed long timeout = 3000000; /* 3000 ms */
+	struct MES_API_STATUS *api_status;
+	union MESAPI__MISC *x_pkt = pkt;
 	const char *op_str, *misc_op_str;
-	u32 fence_offset;
-	u64 fence_gpu_addr;
-	u64 *fence_ptr;
+	unsigned long flags;
+	u64 status_gpu_addr;
+	u32 status_offset;
+	u64 *status_ptr;
+	signed long r;
 	int ret;
 
 	if (x_pkt->header.opcode >= MES_SCH_API_MAX)
@@ -177,28 +177,38 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 		/* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
 		timeout = 15 * 600 * 1000;
 	}
-	BUG_ON(size % 4 != 0);
 
-	ret = amdgpu_device_wb_get(adev, &fence_offset);
+	ret = amdgpu_device_wb_get(adev, &status_offset);
 	if (ret)
 		return ret;
-	fence_gpu_addr =
-		adev->wb.gpu_addr + (fence_offset * 4);
-	fence_ptr = (u64 *)&adev->wb.wb[fence_offset];
-	*fence_ptr = 0;
+
+	status_gpu_addr = adev->wb.gpu_addr + (status_offset * 4);
+	status_ptr = (u64 *)&adev->wb.wb[status_offset];
+	*status_ptr = 0;
 
 	spin_lock_irqsave(&mes->ring_lock, flags);
-	if (amdgpu_ring_alloc(ring, ndw)) {
-		spin_unlock_irqrestore(&mes->ring_lock, flags);
-		amdgpu_device_wb_free(adev, fence_offset);
-		return -ENOMEM;
-	}
+	r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4);
+	if (r)
+		goto error_unlock_free;
 
 	api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
-	api_status->api_completion_fence_addr = fence_gpu_addr;
+	api_status->api_completion_fence_addr = status_gpu_addr;
 	api_status->api_completion_fence_value = 1;
 
-	amdgpu_ring_write_multiple(ring, pkt, ndw);
+	amdgpu_ring_write_multiple(ring, pkt, size / 4);
+
+	memset(&mes_status_pkt, 0, sizeof(mes_status_pkt));
+	mes_status_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS;
+	mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+	mes_status_pkt.api_status.api_completion_fence_addr =
+		ring->fence_drv.gpu_addr;
+	mes_status_pkt.api_status.api_completion_fence_value =
+		++ring->fence_drv.sync_seq;
+
+	amdgpu_ring_write_multiple(ring, &mes_status_pkt,
+				   sizeof(mes_status_pkt) / 4);
+
 	amdgpu_ring_commit(ring);
 	spin_unlock_irqrestore(&mes->ring_lock, flags);
 
@@ -206,15 +216,16 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	misc_op_str = mes_v11_0_get_misc_op_string(x_pkt);
 
 	if (misc_op_str)
-		dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, misc_op_str);
+		dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str,
+			misc_op_str);
 	else if (op_str)
 		dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str);
 	else
-		dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode);
+		dev_dbg(adev->dev, "MES msg=%d was emitted\n",
+			x_pkt->header.opcode);
 
-	r = amdgpu_mes_fence_wait_polling(fence_ptr, (u64)1, timeout);
-	amdgpu_device_wb_free(adev, fence_offset);
-	if (r < 1) {
+	r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+	if (r < 1 || !*status_ptr) {
 
 		if (misc_op_str)
 			dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n",
@@ -229,10 +240,19 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 		while (halt_if_hws_hang)
 			schedule();
 
-		return -ETIMEDOUT;
+		r = -ETIMEDOUT;
+		goto error_wb_free;
 	}
 
+	amdgpu_device_wb_free(adev, status_offset);
 	return 0;
+
+error_unlock_free:
+	spin_unlock_irqrestore(&mes->ring_lock, flags);
+
+error_wb_free:
+	amdgpu_device_wb_free(adev, status_offset);
+	return r;
 }
 
 static int convert_to_mes_queue_type(int queue_type)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 7566973ed8f5..37b5ddd6f13b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -464,8 +464,9 @@ struct psp_gfx_rb_frame
 #define PSP_ERR_UNKNOWN_COMMAND 0x00000100
 
 enum tee_error_code {
-    TEE_SUCCESS                         = 0x00000000,
-    TEE_ERROR_NOT_SUPPORTED             = 0xFFFF000A,
+	TEE_SUCCESS			= 0x00000000,
+	TEE_ERROR_CANCEL		= 0xFFFF0002,
+	TEE_ERROR_NOT_SUPPORTED		= 0xFFFF000A,
 };
 
 #endif /* _PSP_TEE_GFX_IF_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index f08a32c18694..40b28298af30 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -32,7 +32,9 @@
 #include "mp/mp_14_0_2_sh_mask.h"
 
 MODULE_FIRMWARE("amdgpu/psp_14_0_2_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_2_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_14_0_3_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_3_ta.bin");
 
 /* For large FW files the time to complete can be very long */
 #define USBC_PD_POLLING_LIMIT_S 240
@@ -66,6 +68,9 @@ static int psp_v14_0_init_microcode(struct psp_context *psp)
 		err = psp_init_sos_microcode(psp, ucode_prefix);
 		if (err)
 			return err;
+		err = psp_init_ta_microcode(psp, ucode_prefix);
+		if (err)
+			return err;
 		break;
 	default:
 		BUG();