Merge tag 'v5.15-rc6' into asoc-5.16

Linux 5.15-rc6

17 files changed, 112 insertions, 26 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index dc3c6b3a00e5..269437b01328 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -758,7 +758,7 @@ enum amd_hw_ip_block_type {
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
 
 struct amd_powerplay {
 	void *pp_handle;
@@ -1087,6 +1087,7 @@ struct amdgpu_device {
 
 	bool                            no_hw_access;
 	struct pci_saved_state          *pci_state;
+	pci_channel_state_t		pci_channel_state;
 
 	struct amdgpu_reset_control     *reset_cntl;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 3003ee1c9487..1d41c2c00623 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
 		kgd2kfd_suspend(adev->kfd.dev, run_pm);
 }
 
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_iommu(adev->kfd.dev);
+
+	return r;
+}
+
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
 {
 	int r = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ec028cf963f5..3bc52b2c604f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev);
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
@@ -327,6 +328,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -365,6 +367,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 }
 
+static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 2d6b2d77b738..054c1a224def 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -563,6 +563,7 @@ kfd_mem_dmaunmap_userptr(struct kgd_mem *mem,
 
 	dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0);
 	sg_free_table(ttm->sg);
+	kfree(ttm->sg);
 	ttm->sg = NULL;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 277128846dd1..463b9c0283f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
-
-
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev,
 				  &fops_sclk_set);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	/* Register debugfs entries for amdgpu_ttm */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 41c6b3aacd37..af9bdf16eefd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2432,6 +2432,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -3148,6 +3152,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -4601,6 +4609,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
+				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
+				if (r)
+					goto out;
+
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)
 					goto out;
@@ -5387,6 +5399,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	adev->pci_channel_state = state;
+
 	switch (state) {
 	case pci_channel_io_normal:
 		return PCI_ERS_RESULT_CAN_RECOVER;
@@ -5529,6 +5543,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 	DRM_INFO("PCI error: resume callback!!\n");
 
+	/* Only continue execution for the case of pci_channel_io_frozen */
+	if (adev->pci_channel_state != pci_channel_io_frozen)
+		return;
+
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 7a7316731911..dc50c05f23fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb)
 	return 0;
 }
 
+/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */
+static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb)
+{
+	u64 micro_tile_mode;
+
+	/* Zero swizzle mode means linear */
+	if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0)
+		return 0;
+
+	micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE);
+	switch (micro_tile_mode) {
+	case 0: /* DISPLAY */
+	case 3: /* RENDER */
+		return 0;
+	default:
+		drm_dbg_kms(afb->base.dev,
+			    "Micro tile mode %llu not supported for scanout\n",
+			    micro_tile_mode);
+		return -EINVAL;
+	}
+}
+
 static void get_block_dimensions(unsigned int block_log2, unsigned int cpp,
 				 unsigned int *width, unsigned int *height)
 {
@@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 				    const struct drm_mode_fb_cmd2 *mode_cmd,
 				    struct drm_gem_object *obj)
 {
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int ret, i;
 
 	/*
@@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
+	if (!dev->mode_config.allow_fb_modifiers) {
+		drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI,
+			      "GFX9+ requires FB check based on format modifier\n");
+		ret = check_tiling_flags_gfx6(rfb);
+		if (ret)
+			return ret;
+	}
+
 	if (dev->mode_config.allow_fb_modifiers &&
 	    !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) {
 		ret = convert_tiling_flags_to_modifier(rfb);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index e7f06bd0f0cd..1916ec84dd71 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -31,6 +31,8 @@
 /* delay 0.1 second to enable gfx off feature */
 #define GFX_OFF_DELAY_ENABLE         msecs_to_jiffies(100)
 
+#define GFX_OFF_NO_DELAY 0
+
 /*
  * GPU GFX IP block helpers function.
  */
@@ -558,6 +560,8 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev)
 
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 {
+	unsigned long delay = GFX_OFF_DELAY_ENABLE;
+
 	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 		return;
 
@@ -573,8 +577,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		adev->gfx.gfx_off_req_count--;
 
-		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+		if (adev->gfx.gfx_off_req_count == 0 &&
+		    !adev->gfx.gfx_off_state) {
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix)
+				delay = GFX_OFF_NO_DELAY;
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+					      delay);
+		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
 			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index c7797eac83c3..9ff600a38559 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	default:
 		adev->gmc.tmz_enabled = false;
-		dev_warn(adev->dev,
+		dev_info(adev->dev,
 			 "Trusted Memory Zone (TMZ) feature not supported\n");
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index dc44c946a244..98732518543e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -757,7 +757,7 @@ Out:
 	return res;
 }
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void)
+uint32_t amdgpu_ras_eeprom_max_record_count(void)
 {
 	return RAS_MAX_RECORD_COUNT;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index f95fc61b3021..6bb00578bfbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 			     struct eeprom_table_record *records, const u32 num);
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void);
+uint32_t amdgpu_ras_eeprom_max_record_count(void);
 
 void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 7b634a1517f9..0554576d3695 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	ent = debugfs_create_file(name,
 				  S_IFREG | S_IRUGO, root,
 				  ring, &amdgpu_debugfs_ring_fops);
-	if (!ent)
-		return -ENOMEM;
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
 
 	i_size_write(ent->d_inode, ring->ring_size + 12);
 	ring->ent = ent;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 38dade421d46..94126dc39688 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		goto out;
 	}
 
+	if (bo->type == ttm_bo_type_device &&
+	    new_mem->mem_type == TTM_PL_VRAM &&
+	    old_mem->mem_type != TTM_PL_VRAM) {
+		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
+		 * accesses the BO after it's moved.
+		 */
+		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+	}
+
 	if (adev->mman.buffer_funcs_enabled) {
 		if (((old_mem->mem_type == TTM_PL_SYSTEM &&
 		      new_mem->mem_type == TTM_PL_VRAM) ||
@@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	if (bo->type == ttm_bo_type_device &&
-	    new_mem->mem_type == TTM_PL_VRAM &&
-	    old_mem->mem_type != TTM_PL_VRAM) {
-		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
-		 * accesses the BO after it's moved.
-		 */
-		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	}
-
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 603c259b073b..025184a556ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 
 	/* set static priority for a queue/ring */
 	gfx_v9_0_mqd_set_priority(ring, mqd);
-	mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM);
+	mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM);
 
 	/* map_queues packet doesn't need activate the queue,
 	 * so only kiq need set this field.
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 41c3a0d70b7c..e47104a1f559 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v10_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v10_0_gart_disable(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index d90c16a6b2b8..5551359d5dfd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v9_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v9_0_gart_disable(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 779f5c911e11..e32efcfb0c8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 			msleep(1000);
 	}
 
+	/* TODO: check whether can submit a doorbell request to raise
+	 * a doorbell fence to exit gfxoff.
+	 */
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, false);
+
 	sdma_v5_2_soft_reset(adev);
 	/* unhalt the MEs */
 	sdma_v5_2_enable(adev, true);
@@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v5_2_gfx_resume(adev);
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, true);
 	if (r)
 		return r;
 	r = sdma_v5_2_rlc_resume(adev);