Merge tag 'amd-drm-fixes-6.15-2025-04-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.15-2025-04-09:

amdgpu:
- MES FW version caching fixes
- Only use GTT as a fallback if we already have a backing store
- dma_buf fix
- IP discovery fix
- Replay and PSR with VRR fix
- DC FP fixes
- eDP fixes
- KIQ TLB invalidate fix
- Enable dmem groups support
- Allow pinning VRAM dma bufs if imports can do P2P
- Workload profile fixes
- Prevent possible division by 0 in fan handling

amdkfd:
- Queue reset fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250409165238.1180153-1-alexander.deucher@amd.com

20 files changed, 187 insertions, 36 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6d83ccfa42ee..2c04ae133848 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -353,7 +353,6 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a30111d2c3ea..b34b915203f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3643,6 +3643,13 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			    adev, adev->ip_blocks[i].version->type))
 			continue;
 
+		/* Since we skip suspend for S0i3, we need to cancel the delayed
+		 * idle work here as the suspend callback never gets called.
+		 */
+		if (adev->in_s0ix &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX &&
+		    amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 0, 0))
+			cancel_delayed_work_sync(&adev->gfx.idle_work);
 		/* skip suspend of gfx/mes and psp for S0ix
 		 * gfx is in gfxoff state, so on resume it will exit gfxoff just
 		 * like at runtime. PSP is also part of the always on hardware
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index dc2713ec95a5..9e738fae2b74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -120,6 +120,8 @@ MODULE_FIRMWARE("amdgpu/vega20_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/raven_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/raven2_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/picasso_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/arcturus_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/aldebaran_ip_discovery.bin");
 
 #define mmIP_DISCOVERY_VERSION  0x16A00
 #define mmRCC_CONFIG_MEMSIZE	0xde3
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 9f627caedc3f..667080cc9ae1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -75,11 +75,25 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
  */
 static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
 {
-	struct drm_gem_object *obj = attach->dmabuf->priv;
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct dma_buf *dmabuf = attach->dmabuf;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
+	u32 domains = bo->preferred_domains;
 
-	/* pin buffer into GTT */
-	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	dma_resv_assert_held(dmabuf->resv);
+
+	/*
+	 * Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+	 * support if all attachments can do P2P. If any attachment can't do
+	 * P2P just pin into GTT instead.
+	 */
+	list_for_each_entry(attach, &dmabuf->attachments, node)
+		if (!attach->peer2peer)
+			domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+
+	if (domains & AMDGPU_GEM_DOMAIN_VRAM)
+		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+	return amdgpu_bo_pin(bo, domains);
 }
 
 /**
@@ -134,9 +148,6 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
 			return ERR_PTR(r);
-
-	} else if (bo->tbo.resource->mem_type != TTM_PL_TT) {
-		return ERR_PTR(-EBUSY);
 	}
 
 	switch (bo->tbo.resource->mem_type) {
@@ -184,7 +195,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
 				 struct sg_table *sgt,
 				 enum dma_data_direction dir)
 {
-	if (sgt->sgl->page_link) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 464625282872..ecb74ccf1d90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -699,12 +699,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 				   uint32_t flush_type, bool all_hub,
 				   uint32_t inst)
 {
-	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT :
-		adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	int r;
+	int r, cnt = 0;
 	uint32_t seq;
 
 	/*
@@ -761,10 +759,21 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+		might_sleep();
+		while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+		       !amdgpu_reset_pending(adev->reset_domain)) {
+			msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+			r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+		}
+
+		if (cnt > MAX_KIQ_REG_TRY) {
 			dev_err(adev->dev, "timeout waiting for kiq fence\n");
 			r = -ETIME;
-		}
+		} else
+			r = 0;
 	}
 
 error_unlock_reset:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 80cd6f5273db..0b9987781f76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -163,8 +163,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		 * When GTT is just an alternative to VRAM make sure that we
 		 * only use it as fallback and still try to fill up VRAM first.
 		 */
-		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
-		    !(adev->flags & AMD_IS_APU))
+		if (abo->tbo.resource && !(adev->flags & AMD_IS_APU) &&
+		    domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 6da8994e0469..2d7f82e98df9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -24,6 +24,7 @@
 
 #include <linux/dma-mapping.h>
 #include <drm/ttm/ttm_range_manager.h>
+#include <drm/drm_drv.h>
 
 #include "amdgpu.h"
 #include "amdgpu_vm.h"
@@ -907,6 +908,9 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	struct ttm_resource_manager *man = &mgr->manager;
 	int err;
 
+	man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size);
+	if (IS_ERR(man->cg))
+		return PTR_ERR(man->cg);
 	ttm_resource_manager_init(man, &adev->mman.bdev,
 				  adev->gmc.real_vram_size);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index e65916ada23b..ef9538fbbf53 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -894,6 +894,10 @@ static void mes_v11_0_get_fw_version(struct amdgpu_device *adev)
 {
 	int pipe;
 
+	/* return early if we have already fetched these */
+	if (adev->mes.sched_version && adev->mes.kiq_version)
+		return;
+
 	/* get MES scheduler/KIQ versions */
 	mutex_lock(&adev->srbm_mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 183dd3346da5..e6ab617b9a40 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1392,17 +1392,20 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
 		mes_v12_0_queue_init_register(ring);
 	}
 
-	/* get MES scheduler/KIQ versions */
-	mutex_lock(&adev->srbm_mutex);
-	soc21_grbm_select(adev, 3, pipe, 0, 0);
+	if (((pipe == AMDGPU_MES_SCHED_PIPE) && !adev->mes.sched_version) ||
+	    ((pipe == AMDGPU_MES_KIQ_PIPE) && !adev->mes.kiq_version)) {
+		/* get MES scheduler/KIQ versions */
+		mutex_lock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 3, pipe, 0, 0);
 
-	if (pipe == AMDGPU_MES_SCHED_PIPE)
-		adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
-	else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
-		adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		if (pipe == AMDGPU_MES_SCHED_PIPE)
+			adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
+			adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
 
-	soc21_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e477d7509646..9bbee484d57c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1983,9 +1983,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 	if (kfd_dbg_has_ttmps_always_setup(dev->gpu))
 		dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
 
-	if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
-		dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
-
 	if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) {
 		if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) ||
 		    KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4))
@@ -2001,7 +1998,11 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 			dev->node_props.capability |=
 				HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
 
-		dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+		if (!amdgpu_sriov_vf(dev->gpu->adev))
+			dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+
+		if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+			dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
 	} else {
 		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
 					HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d0d8ad5368c3..9fed4471405f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1726,9 +1726,30 @@ static const struct dmi_system_id dmi_quirk_table[] = {
 		.callback = edp0_on_dp1_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 645 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
 		},
 	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 445 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 465 16 inch G11 Notebook PC"),
+		},
+	},
 	{}
 	/* TODO: refactor this from a fixed table to a dynamic option */
 };
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 36a830a7440f..e8bdd7f0c460 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -113,6 +113,7 @@ bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state)
  *
  * Panel Replay and PSR SU
  * - Enable when:
+ *      - VRR is disabled
  *      - vblank counter is disabled
  *      - entry is allowed: usermode demonstrates an adequate number of fast
  *        commits)
@@ -131,19 +132,20 @@ static void amdgpu_dm_crtc_set_panel_sr_feature(
 	bool is_sr_active = (link->replay_settings.replay_allow_active ||
 				 link->psr_settings.psr_allow_active);
 	bool is_crc_window_active = false;
+	bool vrr_active = amdgpu_dm_crtc_vrr_active_irq(vblank_work->acrtc);
 
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 	is_crc_window_active =
 		amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base);
 #endif
 
-	if (link->replay_settings.replay_feature_enabled &&
+	if (link->replay_settings.replay_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 		amdgpu_dm_replay_enable(vblank_work->stream, true);
 	} else if (vblank_enabled) {
 		if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && is_sr_active)
 			amdgpu_dm_psr_disable(vblank_work->stream, false);
-	} else if (link->psr_settings.psr_feature_enabled &&
+	} else if (link->psr_settings.psr_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 
 		struct amdgpu_dm_connector *aconn =
@@ -244,6 +246,8 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	struct vblank_control_work *vblank_work =
 		container_of(work, struct vblank_control_work, work);
 	struct amdgpu_display_manager *dm = vblank_work->dm;
+	struct amdgpu_device *adev = drm_to_adev(dm->ddev);
+	int r;
 
 	mutex_lock(&dm->dc_lock);
 
@@ -271,8 +275,15 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
-	if (dm->active_vblank_irq_count == 0)
+	if (dm->active_vblank_irq_count == 0) {
+		r = amdgpu_dpm_pause_power_profile(adev, true);
+		if (r)
+			dev_warn(adev->dev, "failed to set default power profile mode\n");
 		dc_allow_idle_optimizations(dm->dc, true);
+		r = amdgpu_dpm_pause_power_profile(adev, false);
+		if (r)
+			dev_warn(adev->dev, "failed to restore the power profile mode\n");
+	}
 
 	mutex_unlock(&dm->dc_lock);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index be54f0e696ce..94e99e540691 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -86,6 +86,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 	/* Store configuration options */
 	(*dml_ctx)->config = *config;
 
+	DC_FP_START();
+
 	/*Initialize SOCBB and DCNIP params */
 	dml21_initialize_soc_bb_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
 	dml21_initialize_ip_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
@@ -96,6 +98,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 
 	/*Initialize DML21 instance */
 	dml2_initialize_instance(&(*dml_ctx)->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const struct dml2_configuration_options *config)
@@ -283,11 +287,16 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml
 {
 	bool out = false;
 
+	DC_FP_START();
+
 	/* Use dml_validate_only for fast_validate path */
-	if (fast_validate) {
+	if (fast_validate)
 		out = dml21_check_mode_support(in_dc, context, dml_ctx);
-	} else
+	else
 		out = dml21_mode_check_and_programming(in_dc, context, dml_ctx);
+
+	DC_FP_END();
+
 	return out;
 }
 
@@ -426,8 +435,12 @@ void dml21_copy(struct dml2_context *dst_dml_ctx,
 
 	dst_dml_ctx->v21.mode_programming.programming = dst_dml2_programming;
 
+	DC_FP_START();
+
 	/* need to initialize copied instance for internal references to be correct */
 	dml2_initialize_instance(&dst_dml_ctx->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create_copy(struct dml2_context **dst_dml_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 939ee0708bd2..f549a778f6f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -732,11 +732,16 @@ bool dml2_validate(const struct dc *in_dc, struct dc_state *context, struct dml2
 		return out;
 	}
 
+	DC_FP_START();
+
 	/* Use dml_validate_only for fast_validate path */
 	if (fast_validate)
 		out = dml2_validate_only(context);
 	else
 		out = dml2_validate_and_build_resource(in_dc, context);
+
+	DC_FP_END();
+
 	return out;
 }
 
@@ -779,11 +784,15 @@ static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_op
 		break;
 	}
 
+	DC_FP_START();
+
 	initialize_dml2_ip_params(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.ip);
 
 	initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc);
 
 	initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states);
+
+	DC_FP_END();
 }
 
 bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 2a9606118d89..21dc956b5f35 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -429,6 +429,7 @@ struct amd_pm_funcs {
 	int (*set_pp_table)(void *handle, const char *buf, size_t size);
 	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
 	int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
+	int (*pause_power_profile)(void *handle, bool pause);
 /* export to amdgpu */
 	struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
 	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 81e9b443ca0a..3533d43ed1e7 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -349,6 +349,25 @@ int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+				   bool pause)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	int ret = 0;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	if (pp_funcs && pp_funcs->pause_power_profile) {
+		mutex_lock(&adev->pm.mutex);
+		ret = pp_funcs->pause_power_profile(
+			adev->powerplay.pp_handle, pause);
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
 			       uint32_t pstate)
 {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index f93d287dbf13..4c0f7ad14816 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -410,6 +410,8 @@ int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
 int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
 				    enum PP_SMC_POWER_PROFILE type,
 				    bool en);
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+				   bool pause);
 
 int amdgpu_dpm_baco_reset(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 033c3229b555..46cce1d2aaf3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2398,7 +2398,11 @@ static int smu_switch_power_profile(void *handle,
 			smu_power_profile_mode_get(smu, type);
 		else
 			smu_power_profile_mode_put(smu, type);
-		ret = smu_bump_power_profile_mode(smu, NULL, 0);
+		/* don't switch the active workload when paused */
+		if (smu->pause_workload)
+			ret = 0;
+		else
+			ret = smu_bump_power_profile_mode(smu, NULL, 0);
 		if (ret) {
 			if (enable)
 				smu_power_profile_mode_put(smu, type);
@@ -2411,6 +2415,35 @@ static int smu_switch_power_profile(void *handle,
 	return 0;
 }
 
+static int smu_pause_power_profile(void *handle,
+				   bool pause)
+{
+	struct smu_context *smu = handle;
+	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+	u32 workload_mask = 1 << PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
+	int ret;
+
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+		return -EOPNOTSUPP;
+
+	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+	    smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+		smu->pause_workload = pause;
+
+		/* force to bootup default profile */
+		if (smu->pause_workload && smu->ppt_funcs->set_power_profile_mode)
+			ret = smu->ppt_funcs->set_power_profile_mode(smu,
+								     workload_mask,
+								     NULL,
+								     0);
+		else
+			ret = smu_bump_power_profile_mode(smu, NULL, 0);
+		return ret;
+	}
+
+	return 0;
+}
+
 static enum amd_dpm_forced_level smu_get_performance_level(void *handle)
 {
 	struct smu_context *smu = handle;
@@ -3733,6 +3766,7 @@ static const struct amd_pm_funcs swsmu_pm_funcs = {
 	.get_pp_table            = smu_sys_get_pp_table,
 	.set_pp_table            = smu_sys_set_pp_table,
 	.switch_power_profile    = smu_switch_power_profile,
+	.pause_power_profile     = smu_pause_power_profile,
 	/* export to amdgpu */
 	.dispatch_tasks          = smu_handle_dpm_task,
 	.load_firmware           = smu_load_microcode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 3ba169639f54..dd6d0e7aa242 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -558,6 +558,7 @@ struct smu_context {
 
 	/* asic agnostic workload mask */
 	uint32_t workload_mask;
+	bool pause_workload;
 	/* default/user workload preference */
 	uint32_t power_profile_mode;
 	uint32_t workload_refcount[PP_SMC_POWER_PROFILE_COUNT];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 78391d8f35a9..25fabf336a64 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1204,7 +1204,7 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
-	if (speed == 0)
+	if (!speed || speed > UINT_MAX/8)
 		return -EINVAL;
 	/*
 	 * To prevent from possible overheat, some ASICs may have requirement