Merge branch 'drm-next-4.18' of git://people.freedesktop.org/~agd5f/linux into drm-next

Fixes for 4.18. Highlights:
- Fixes for gfxoff on Raven
- Remove an ATPX quirk now that the root cause is fixed
- Runtime PM fixes
- Vega20 register header update
- Wattman fixes
- Misc bug fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614141428.2909-1-alexander.deucher@amd.com

15 files changed, 123 insertions, 96 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 8f6f45567bfa..305143fcc1ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -342,15 +342,12 @@ void get_local_mem_info(struct kgd_dev *kgd,
 			mem_info->local_mem_size_public,
 			mem_info->local_mem_size_private);
 
-	if (amdgpu_emu_mode == 1) {
-		mem_info->mem_clk_max = 100;
-		return;
-	}
-
 	if (amdgpu_sriov_vf(adev))
 		mem_info->mem_clk_max = adev->clock.default_mclk / 100;
-	else
+	else if (adev->powerplay.pp_funcs)
 		mem_info->mem_clk_max = amdgpu_dpm_get_mclk(adev, false) / 100;
+	else
+		mem_info->mem_clk_max = 100;
 }
 
 uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
@@ -367,13 +364,12 @@ uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd)
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
 	/* the sclk is in quantas of 10kHz */
-	if (amdgpu_emu_mode == 1)
-		return 100;
-
 	if (amdgpu_sriov_vf(adev))
 		return adev->clock.default_sclk / 100;
-
-	return amdgpu_dpm_get_sclk(adev, false) / 100;
+	else if (adev->powerplay.pp_funcs)
+		return amdgpu_dpm_get_sclk(adev, false) / 100;
+	else
+		return 100;
 }
 
 void get_cu_info(struct kgd_dev *kgd, struct kfd_cu_info *cu_info)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 1bcb2b247335..daa06e7c5bb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -569,7 +569,6 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
-	{ 0x1002, 0x67DF, 0x1028, 0x0774, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9c1d491d742e..82312a7bc6ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -522,6 +522,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	struct amdgpu_bo_list_entry *e;
 	struct list_head duplicates;
 	unsigned i, tries = 10;
+	struct amdgpu_bo *gds;
+	struct amdgpu_bo *gws;
+	struct amdgpu_bo *oa;
 	int r;
 
 	INIT_LIST_HEAD(&p->validated);
@@ -652,31 +655,36 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
 				     p->bytes_moved_vis);
+
 	if (p->bo_list) {
-		struct amdgpu_bo *gds = p->bo_list->gds_obj;
-		struct amdgpu_bo *gws = p->bo_list->gws_obj;
-		struct amdgpu_bo *oa = p->bo_list->oa_obj;
 		struct amdgpu_vm *vm = &fpriv->vm;
 		unsigned i;
 
+		gds = p->bo_list->gds_obj;
+		gws = p->bo_list->gws_obj;
+		oa = p->bo_list->oa_obj;
 		for (i = 0; i < p->bo_list->num_entries; i++) {
 			struct amdgpu_bo *bo = p->bo_list->array[i].robj;
 
 			p->bo_list->array[i].bo_va = amdgpu_vm_bo_find(vm, bo);
 		}
+	} else {
+		gds = p->adev->gds.gds_gfx_bo;
+		gws = p->adev->gds.gws_gfx_bo;
+		oa = p->adev->gds.oa_gfx_bo;
+	}
 
-		if (gds) {
-			p->job->gds_base = amdgpu_bo_gpu_offset(gds);
-			p->job->gds_size = amdgpu_bo_size(gds);
-		}
-		if (gws) {
-			p->job->gws_base = amdgpu_bo_gpu_offset(gws);
-			p->job->gws_size = amdgpu_bo_size(gws);
-		}
-		if (oa) {
-			p->job->oa_base = amdgpu_bo_gpu_offset(oa);
-			p->job->oa_size = amdgpu_bo_size(oa);
-		}
+	if (gds) {
+		p->job->gds_base = amdgpu_bo_gpu_offset(gds);
+		p->job->gds_size = amdgpu_bo_size(gds);
+	}
+	if (gws) {
+		p->job->gws_base = amdgpu_bo_gpu_offset(gws);
+		p->job->gws_size = amdgpu_bo_size(gws);
+	}
+	if (oa) {
+		p->job->oa_base = amdgpu_bo_gpu_offset(oa);
+		p->job->oa_size = amdgpu_bo_size(oa);
 	}
 
 	if (!r && p->uf_entry.robj) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 290e279abf0d..3317d1536f4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1730,6 +1730,18 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 			}
 		}
 	}
+
+	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
+		/* enable gfx powergating */
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_GFX,
+						       AMD_PG_STATE_GATE);
+		/* enable gfxoff */
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_SMC,
+						       AMD_PG_STATE_GATE);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 2c8e27370284..5fb156a01774 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -30,6 +30,7 @@
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
+#include "amdgpu_display.h"
 
 void amdgpu_gem_object_free(struct drm_gem_object *gobj)
 {
@@ -235,6 +236,13 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	/* create a gem object to contain this object in */
 	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
 	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
+		if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
+			/* if gds bo is created from user space, it must be
+			 * passed to bo list
+			 */
+			DRM_ERROR("GDS bo cannot be per-vm-bo\n");
+			return -EINVAL;
+		}
 		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 		if (args->in.domains == AMDGPU_GEM_DOMAIN_GDS)
 			size = size << AMDGPU_GDS_SHIFT;
@@ -749,15 +757,16 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 	struct amdgpu_device *adev = dev->dev_private;
 	struct drm_gem_object *gobj;
 	uint32_t handle;
+	u32 domain;
 	int r;
 
 	args->pitch = amdgpu_align_pitch(adev, args->width,
 					 DIV_ROUND_UP(args->bpp, 8), 0);
 	args->size = (u64)args->pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
-
-	r = amdgpu_gem_object_create(adev, args->size, 0,
-				     AMDGPU_GEM_DOMAIN_VRAM,
+	domain = amdgpu_bo_get_preferred_pin_domain(adev,
+				amdgpu_display_supported_domains(adev));
+	r = amdgpu_gem_object_create(adev, args->size, 0, domain,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
 				     false, NULL, &gobj);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6a9e46ae7f0a..5e4e1bd90383 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -703,11 +703,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
 	 * See function amdgpu_display_supported_domains()
 	 */
-	if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
-		domain = AMDGPU_GEM_DOMAIN_VRAM;
-		if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD)
-			domain = AMDGPU_GEM_DOMAIN_GTT;
-	}
+	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
 
 	if (bo->pin_count) {
 		uint32_t mem_type = bo->tbo.mem.mem_type;
@@ -1066,3 +1062,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 
 	return bo->tbo.offset;
 }
+
+uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+					    uint32_t domain)
+{
+	if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
+		domain = AMDGPU_GEM_DOMAIN_VRAM;
+		if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD)
+			domain = AMDGPU_GEM_DOMAIN_GTT;
+	}
+	return domain;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 540e03fa159f..731748033878 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -289,7 +289,8 @@ int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
 				  struct reservation_object *resv,
 				  struct dma_fence **fence,
 				  bool direct);
-
+uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+					    uint32_t domain);
 
 /*
  * sub allocation
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 8851bcdfc260..127e87b470ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -49,8 +49,6 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
 
 int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
@@ -84,6 +82,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	}
 
 	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 	family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
 	version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
 	version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
@@ -102,24 +101,6 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	ring = &adev->vcn.ring_dec;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_dec,
-				  rq, NULL);
-	if (r != 0) {
-		DRM_ERROR("Failed setting up VCN dec run queue.\n");
-		return r;
-	}
-
-	ring = &adev->vcn.ring_enc[0];
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_enc,
-				  rq, NULL);
-	if (r != 0) {
-		DRM_ERROR("Failed setting up VCN enc run queue.\n");
-		return r;
-	}
-
 	return 0;
 }
 
@@ -129,10 +110,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 	kfree(adev->vcn.saved_bo);
 
-	drm_sched_entity_fini(&adev->vcn.ring_dec.sched, &adev->vcn.entity_dec);
-
-	drm_sched_entity_fini(&adev->vcn.ring_enc[0].sched, &adev->vcn.entity_enc);
-
 	amdgpu_bo_free_kernel(&adev->vcn.vcpu_bo,
 			      &adev->vcn.gpu_addr,
 			      (void **)&adev->vcn.cpu_addr);
@@ -278,7 +255,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
-				   struct amdgpu_bo *bo, bool direct,
+				   struct amdgpu_bo *bo,
 				   struct dma_fence **fence)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -306,19 +283,12 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 	}
 	ib->length_dw = 16;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err_free;
+	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+	job->fence = dma_fence_get(f);
+	if (r)
+		goto err_free;
 
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &adev->vcn.entity_dec,
-				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err_free;
-	}
+	amdgpu_job_free(job);
 
 	amdgpu_bo_fence(bo, f, false);
 	amdgpu_bo_unreserve(bo);
@@ -370,11 +340,11 @@ static int amdgpu_vcn_dec_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = 14; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	return amdgpu_vcn_dec_send_msg(ring, bo, true, fence);
+	return amdgpu_vcn_dec_send_msg(ring, bo, fence);
 }
 
 static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-			       bool direct, struct dma_fence **fence)
+			       struct dma_fence **fence)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_bo *bo = NULL;
@@ -396,7 +366,7 @@ static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = 6; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	return amdgpu_vcn_dec_send_msg(ring, bo, direct, fence);
+	return amdgpu_vcn_dec_send_msg(ring, bo, fence);
 }
 
 int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
@@ -410,7 +380,7 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		goto error;
 	}
 
-	r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, true, &fence);
+	r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, &fence);
 	if (r) {
 		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
 		goto error;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 181e6afa9847..773010b9ff15 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -67,8 +67,6 @@ struct amdgpu_vcn {
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	struct drm_sched_entity entity_dec;
-	struct drm_sched_entity entity_enc;
 	unsigned		num_enc_rings;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ccba88cc8c54..b0eb2f537392 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2123,7 +2123,8 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 			before->last = saddr - 1;
 			before->offset = tmp->offset;
 			before->flags = tmp->flags;
-			list_add(&before->list, &tmp->list);
+			before->bo_va = tmp->bo_va;
+			list_add(&before->list, &tmp->bo_va->invalids);
 		}
 
 		/* Remember mapping split at the end */
@@ -2133,7 +2134,8 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 			after->offset = tmp->offset;
 			after->offset += after->start - tmp->start;
 			after->flags = tmp->flags;
-			list_add(&after->list, &tmp->list);
+			after->bo_va = tmp->bo_va;
+			list_add(&after->list, &tmp->bo_va->invalids);
 		}
 
 		list_del(&tmp->list);
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 60608b3df881..d5ebe566809b 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -64,7 +64,7 @@ static u32 df_v3_6_get_hbm_channel_number(struct amdgpu_device *adev)
 	int fb_channel_number;
 
 	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
-	if (fb_channel_number > ARRAY_SIZE(df_v3_6_channel_number))
+	if (fb_channel_number >= ARRAY_SIZE(df_v3_6_channel_number))
 		fb_channel_number = 0;
 
 	return df_v3_6_channel_number[fb_channel_number];
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d7530fdfaad5..a69153435ea7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -111,6 +111,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
 {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_DCC_CONFIG, 0x0f000080, 0x04000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_2, 0x0f000000, 0x0a000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xf3e777ff, 0x22014042),
@@ -1837,13 +1838,15 @@ static void gfx_v9_1_parse_ind_reg_list(int *register_list_format,
 				int indirect_offset,
 				int list_size,
 				int *unique_indirect_regs,
-				int *unique_indirect_reg_count,
+				int unique_indirect_reg_count,
 				int *indirect_start_offsets,
-				int *indirect_start_offsets_count)
+				int *indirect_start_offsets_count,
+				int max_start_offsets_count)
 {
 	int idx;
 
 	for (; indirect_offset < list_size; indirect_offset++) {
+		WARN_ON(*indirect_start_offsets_count >= max_start_offsets_count);
 		indirect_start_offsets[*indirect_start_offsets_count] = indirect_offset;
 		*indirect_start_offsets_count = *indirect_start_offsets_count + 1;
 
@@ -1851,14 +1854,14 @@ static void gfx_v9_1_parse_ind_reg_list(int *register_list_format,
 			indirect_offset += 2;
 
 			/* look for the matching indice */
-			for (idx = 0; idx < *unique_indirect_reg_count; idx++) {
+			for (idx = 0; idx < unique_indirect_reg_count; idx++) {
 				if (unique_indirect_regs[idx] ==
 					register_list_format[indirect_offset] ||
 					!unique_indirect_regs[idx])
 					break;
 			}
 
-			BUG_ON(idx >= *unique_indirect_reg_count);
+			BUG_ON(idx >= unique_indirect_reg_count);
 
 			if (!unique_indirect_regs[idx])
 				unique_indirect_regs[idx] = register_list_format[indirect_offset];
@@ -1893,9 +1896,10 @@ static int gfx_v9_1_init_rlc_save_restore_list(struct amdgpu_device *adev)
 				    adev->gfx.rlc.reg_list_format_direct_reg_list_length,
 				    adev->gfx.rlc.reg_list_format_size_bytes >> 2,
 				    unique_indirect_regs,
-				    &unique_indirect_reg_count,
+				    unique_indirect_reg_count,
 				    indirect_start_offsets,
-				    &indirect_start_offsets_count);
+				    &indirect_start_offsets_count,
+				    ARRAY_SIZE(indirect_start_offsets));
 
 	/* enable auto inc in case it is disabled */
 	tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL));
@@ -3404,11 +3408,6 @@ static int gfx_v9_0_late_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_GFX,
-						   AMD_PG_STATE_GATE);
-	if (r)
-		return r;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index 0c768e388ace..727071fee6f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -47,6 +47,8 @@ MODULE_FIRMWARE("amdgpu/vega20_asd.bin");
 
 #define smnMP1_FIRMWARE_FLAGS 0x3010028
 
+static uint32_t sos_old_versions[] = {1517616, 1510592, 1448594, 1446554};
+
 static int
 psp_v3_1_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type *type)
 {
@@ -210,12 +212,31 @@ static int psp_v3_1_bootloader_load_sysdrv(struct psp_context *psp)
 	return ret;
 }
 
+static bool psp_v3_1_match_version(struct amdgpu_device *adev, uint32_t ver)
+{
+	int i;
+
+	if (ver == adev->psp.sos_fw_version)
+		return true;
+
+	/*
+	 * Double check if the latest four legacy versions.
+	 * If yes, it is still the right version.
+	 */
+	for (i = 0; i < sizeof(sos_old_versions) / sizeof(uint32_t); i++) {
+		if (sos_old_versions[i] == adev->psp.sos_fw_version)
+			return true;
+	}
+
+	return false;
+}
+
 static int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
 {
 	int ret;
 	unsigned int psp_gfxdrv_command_reg = 0;
 	struct amdgpu_device *adev = psp->adev;
-	uint32_t sol_reg;
+	uint32_t sol_reg, ver;
 
 	/* Check sOS sign of life register to confirm sys driver and sOS
 	 * are already been loaded.
@@ -248,6 +269,10 @@ static int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
 			   RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81),
 			   0, true);
 
+	ver = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58);
+	if (!psp_v3_1_match_version(adev, ver))
+		DRM_WARN("SOS version doesn't match\n");
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 68b4a22a8892..83f2717fcf81 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -685,6 +685,7 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS |
 			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_ROM_MGCG |
 			AMD_CG_SUPPORT_VCE_MGCG |
 			AMD_CG_SUPPORT_UVD_MGCG;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 110b294ebed3..29684c3ea4ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -769,14 +769,14 @@ static int vcn_v1_0_stop(struct amdgpu_device *adev)
 	return 0;
 }
 
-bool vcn_v1_0_is_idle(void *handle)
+static bool vcn_v1_0_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == 0x2);
 }
 
-int vcn_v1_0_wait_for_idle(void *handle)
+static int vcn_v1_0_wait_for_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int ret = 0;