Merge tag 'amd-drm-fixes-7.0-2026-04-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-7.0-2026-04-01: amdgpu: - UserQ fixes - PASID handling fix - S4 fix for smu11 chips - Misc small fixes amdkfd: - Non-4K page fixes Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patch.msgid.link/20260401174731.3576021-1-alexander.deucher@amd.com
2026-05-16 11:21:26 -04:00 · 2026-04-02 10:05:57 +10:00
parent 7aaa8047ea 78746a474e
commit 2aa5a6d933
16 changed files with 115 additions and 46 deletions
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2703,8 +2703,12 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	if (r)
 		return r;

-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 	return 0;
 }

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -403,6 +403,50 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
 	drm_dev_exit(idx);
 }

+/**
+ * amdgpu_gart_map_gfx9_mqd - map mqd and ctrl_stack dma_addresses into GART entries
+ *
+ * @adev: amdgpu_device pointer
+ * @offset: offset into the GPU's gart aperture
+ * @pages: number of pages to bind
+ * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
+ *
+ * Map the MQD and control stack addresses into GART entries with the correct
+ * memory types on gfxv9. The MQD occupies the first 4KB and is followed by
+ * the control stack. The MQD uses UC (uncached) memory, while the control stack
+ * uses NC (non-coherent) memory.
+ */
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags)
+{
+	uint64_t page_base;
+	unsigned int i, j, t;
+	int idx;
+	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
+	void *dst;
+
+	if (!adev->gart.ptr)
+		return;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return;
+
+	t = offset / AMDGPU_GPU_PAGE_SIZE;
+	dst = adev->gart.ptr;
+	for (i = 0; i < pages; i++) {
+		page_base = dma_addr[i];
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
+			if ((i == 0) && (j == 0))
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
+			else
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, ctrl_flags);
+			page_base += AMDGPU_GPU_PAGE_SIZE;
+		}
+	}
+	drm_dev_exit(idx);
+}
+
 /**
 * amdgpu_gart_bind - bind pages into the gart page table
 *
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -62,6 +62,8 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, dma_addr_t *dma_addr, uint64_t flags,
 		     void *dst);
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		      int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -68,8 +68,11 @@ int amdgpu_pasid_alloc(unsigned int bits)
 		return -EINVAL;

 	spin_lock(&amdgpu_pasid_idr_lock);
+	/* TODO: Need to replace the idr with an xarry, and then
+	 * handle the internal locking with ATOMIC safe paths.
+	 */
 	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
-				 1U << bits, GFP_KERNEL);
+				 1U << bits, GFP_ATOMIC);
 	spin_unlock(&amdgpu_pasid_idr_lock);

 	if (pasid >= 0)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -853,25 +853,15 @@ static void amdgpu_ttm_gart_bind_gfx9_mqd(struct amdgpu_device *adev,
 	int num_xcc = max(1U, adev->gfx.num_xcc_per_xcp);
 	uint64_t page_idx, pages_per_xcc;
 	int i;
-	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);

 	pages_per_xcc = total_pages;
 	do_div(pages_per_xcc, num_xcc);

 	for (i = 0, page_idx = 0; i < num_xcc; i++, page_idx += pages_per_xcc) {
-		/* MQD page: use default flags */
-		amdgpu_gart_bind(adev,
+		amdgpu_gart_map_gfx9_mqd(adev,
 				gtt->offset + (page_idx << PAGE_SHIFT),
-				1, &gtt->ttm.dma_address[page_idx], flags);
-		/*
-		 * Ctrl pages - modify the memory type to NC (ctrl_flags) from
-		 * the second page of the BO onward.
-		 */
-		amdgpu_gart_bind(adev,
-				gtt->offset + ((page_idx + 1) << PAGE_SHIFT),
-				pages_per_xcc - 1,
-				&gtt->ttm.dma_address[page_idx + 1],
-				ctrl_flags);
+				pages_per_xcc, &gtt->ttm.dma_address[page_idx],
+				flags);
 	}
 }

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -600,6 +600,13 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 		goto unpin_bo;
 	}

+	/* Validate doorbell_offset is within the doorbell BO */
+	if ((u64)db_info->doorbell_offset * db_size + db_size >
+	    amdgpu_bo_size(db_obj->obj)) {
+		r = -EINVAL;
+		goto unpin_bo;
+	}
+
 	index = amdgpu_doorbell_index_on_bar(uq_mgr->adev, db_obj->obj,
 					     db_info->doorbell_offset, db_size);
 	drm_dbg_driver(adev_to_drm(uq_mgr->adev),
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -173,7 +173,7 @@ struct amdgpu_bo_vm;
 #define AMDGPU_VA_RESERVED_SEQ64_SIZE		(2ULL << 20)
 #define AMDGPU_VA_RESERVED_SEQ64_START(adev)	(AMDGPU_VA_RESERVED_CSA_START(adev) \
 						 - AMDGPU_VA_RESERVED_SEQ64_SIZE)
-#define AMDGPU_VA_RESERVED_TRAP_SIZE		(2ULL << 12)
+#define AMDGPU_VA_RESERVED_TRAP_SIZE		(1ULL << 16)
 #define AMDGPU_VA_RESERVED_TRAP_START(adev)	(AMDGPU_VA_RESERVED_SEQ64_START(adev) \
 						 - AMDGPU_VA_RESERVED_TRAP_SIZE)
 #define AMDGPU_VA_RESERVED_BOTTOM		(1ULL << 16)
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -324,8 +324,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,

 		r = amdgpu_userq_input_va_validate(adev, queue, compute_mqd->eop_va,
 						   2048);
-		if (r)
+		if (r) {
+			kfree(compute_mqd);
 			goto free_mqd;
+		}

 		userq_props->eop_gpu_addr = compute_mqd->eop_va;
 		userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL;
@@ -365,12 +367,16 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,

 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->shadow_va,
 						   shadow_info.shadow_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->csa_va,
 						   shadow_info.csa_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}

 		kfree(mqd_gfx_v11);
 	} else if (queue->queue_type == AMDGPU_HW_IP_DMA) {
@@ -390,8 +396,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_sdma_v11->csa_va,
 						   32);
-		if (r)
+		if (r) {
+			kfree(mqd_sdma_v11);
 			goto free_mqd;
+		}

 		userq_props->csa_addr = mqd_sdma_v11->csa_va;
 		kfree(mqd_sdma_v11);
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -170,7 +170,8 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 	int retry_loop;

 	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
-	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+	if ((adev->in_s4 || adev->in_s3) && !(adev->flags & AMD_IS_APU) &&
+	    amdgpu_in_reset(adev))
 		return psp_v11_wait_for_tos_unload(psp);

 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -42,9 +42,16 @@ static uint64_t mqd_stride_v9(struct mqd_manager *mm,
 				struct queue_properties *q)
 {
 	if (mm->dev->kfd->cwsr_enabled &&
-	    q->type == KFD_QUEUE_TYPE_COMPUTE)
-		return ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE);
+	    q->type == KFD_QUEUE_TYPE_COMPUTE) {
+
+		/* On gfxv9, the MQD resides in the first 4K page,
+		 * followed by the control stack. Align both to
+		 * AMDGPU_GPU_PAGE_SIZE to maintain the required 4K boundary.
+		 */
+
+		return ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE);
+	}

 	return mm->mqd_size;
 }
@@ -151,8 +158,8 @@ static struct kfd_mem_obj *allocate_mqd(struct mqd_manager *mm,
 		if (!mqd_mem_obj)
 			return NULL;
 		retval = amdgpu_amdkfd_alloc_kernel_mem(node->adev,
-			(ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE)) *
+			(ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE)) *
 			NUM_XCC(node->xcc_mask),
 			mqd_on_vram(node->adev) ? AMDGPU_GEM_DOMAIN_VRAM :
 						  AMDGPU_GEM_DOMAIN_GTT,
@@ -360,7 +367,7 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	struct kfd_context_save_area_header header;

 	/* Control stack is located one page after MQD. */
-	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);

 	m = get_mqd(mqd);

@@ -397,7 +404,7 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, voi
 {
 	struct v9_mqd *m;
 	/* Control stack is located one page after MQD. */
-	void *ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);

 	m = get_mqd(mqd);

@@ -443,7 +450,7 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd,
 		*gart_addr = addr;

 	/* Control stack is located one page after MQD. */
-	ctl_stack = (void *)((uintptr_t)*mqd + PAGE_SIZE);
+	ctl_stack = (void *)((uintptr_t)*mqd + AMDGPU_GPU_PAGE_SIZE);
 	memcpy(ctl_stack, ctl_stack_src, ctl_stack_size);

 	m->cp_hqd_pq_doorbell_control =
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -102,8 +102,8 @@
 * The first chunk is the TBA used for the CWSR ISA code. The second
 * chunk is used as TMA for user-mode trap handler setup in daisy-chain mode.
 */
-#define KFD_CWSR_TBA_TMA_SIZE (PAGE_SIZE * 2)
-#define KFD_CWSR_TMA_OFFSET (PAGE_SIZE + 2048)
+#define KFD_CWSR_TBA_TMA_SIZE (AMDGPU_GPU_PAGE_SIZE * 2)
+#define KFD_CWSR_TMA_OFFSET (AMDGPU_GPU_PAGE_SIZE + 2048)

 #define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
 	(KFD_MAX_NUM_OF_PROCESSES *			\
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -249,10 +249,10 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	    topo_dev->node_props.gfx_target_version < 90000)
 		/* metadata_queue_size not supported on GFX7/GFX8 */
 		expected_queue_size =
-			properties->queue_size / 2;
+			PAGE_ALIGN(properties->queue_size / 2);
 	else
 		expected_queue_size =
-			properties->queue_size + properties->metadata_queue_size;
+			PAGE_ALIGN(properties->queue_size + properties->metadata_queue_size);

 	vm = drm_priv_to_vm(pdd->drm_priv);
 	err = amdgpu_bo_reserve(vm->root.bo, false);
@@ -492,10 +492,11 @@ void kfd_queue_ctx_save_restore_size(struct kfd_topology_device *dev)
 	cu_num = props->simd_count / props->simd_per_cu / NUM_XCC(dev->gpu->xcc_mask);
 	wave_num = get_num_waves(props, gfxv, cu_num);

-	wg_data_size = ALIGN(cu_num * WG_CONTEXT_DATA_SIZE_PER_CU(gfxv, props), PAGE_SIZE);
+	wg_data_size = ALIGN(cu_num * WG_CONTEXT_DATA_SIZE_PER_CU(gfxv, props),
+				AMDGPU_GPU_PAGE_SIZE);
 	ctl_stack_size = wave_num * CNTL_STACK_BYTES_PER_WAVE(gfxv) + 8;
 	ctl_stack_size = ALIGN(SIZEOF_HSA_USER_CONTEXT_SAVE_AREA_HEADER + ctl_stack_size,
-			       PAGE_SIZE);
+			       AMDGPU_GPU_PAGE_SIZE);

 	if ((gfxv / 10000 * 10000) == 100000) {
 		/* HW design limits control stack size to 0x7000.
@@ -507,7 +508,7 @@ void kfd_queue_ctx_save_restore_size(struct kfd_topology_device *dev)

 	props->ctl_stack_size = ctl_stack_size;
 	props->debug_memory_size = ALIGN(wave_num * DEBUGGER_BYTES_PER_WAVE, DEBUGGER_BYTES_ALIGN);
-	props->cwsr_size = ctl_stack_size + wg_data_size;
+	props->cwsr_size = ALIGN(ctl_stack_size + wg_data_size, PAGE_SIZE);

 	if (gfxv == 80002)	/* GFX_VERSION_TONGA */
 		props->eop_buffer_size = 0x8000;
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -147,6 +147,7 @@ void dcn401_init_hw(struct dc *dc)
 	int edp_num;
 	uint32_t backlight = MAX_BACKLIGHT_LEVEL;
 	uint32_t user_level = MAX_BACKLIGHT_LEVEL;
+	bool dchub_ref_freq_changed;
 	int current_dchub_ref_freq = 0;

 	if (dc->clk_mgr && dc->clk_mgr->funcs && dc->clk_mgr->funcs->init_clocks) {
@@ -360,14 +361,18 @@ void dcn401_init_hw(struct dc *dc)
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
 		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver > 0;
 		dc->caps.dmub_caps.fams_ver = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
+
+		/* sw and fw FAMS versions must match for support */
 		dc->debug.fams2_config.bits.enable &=
-				dc->caps.dmub_caps.fams_ver == dc->debug.fams_version.ver; // sw & fw fams versions must match for support
-		if ((!dc->debug.fams2_config.bits.enable && dc->res_pool->funcs->update_bw_bounding_box)
-			|| res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 != current_dchub_ref_freq) {
+			dc->caps.dmub_caps.fams_ver == dc->debug.fams_version.ver;
+		dchub_ref_freq_changed =
+			res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 != current_dchub_ref_freq;
+		if ((!dc->debug.fams2_config.bits.enable || dchub_ref_freq_changed) &&
+		    dc->res_pool->funcs->update_bw_bounding_box &&
+		    dc->clk_mgr && dc->clk_mgr->bw_params) {
 			/* update bounding box if FAMS2 disabled, or if dchub clk has changed */
-			if (dc->clk_mgr)
-				dc->res_pool->funcs->update_bw_bounding_box(dc,
-									    dc->clk_mgr->bw_params);
+			dc->res_pool->funcs->update_bw_bounding_box(dc,
+								    dc->clk_mgr->bw_params);
 		}
 	}
 }
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -262,7 +262,6 @@ int smu_v11_0_check_fw_version(struct smu_context *smu)
 			"smu fw program = %d, version = 0x%08x (%d.%d.%d)\n",
 			smu->smc_driver_if_version, if_version,
 			smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(smu->adev->dev, "SMU driver if version not matched\n");
 	}

 	return ret;
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -101,7 +101,6 @@ int smu_v12_0_check_fw_version(struct smu_context *smu)
 			"smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			smu->smc_driver_if_version, if_version,
 			smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(smu->adev->dev, "SMU driver if version not matched\n");
 	}

 	return ret;
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -284,7 +284,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 			 "smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			 smu->smc_driver_if_version, if_version,
 			 smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(adev->dev, "SMU driver if version not matched\n");
 	}

 	return ret;