Merge tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm…

…/kernel

Pull drm fixes from Dave Airlie:
 "Regular fixes for the week to end the merge window, i915 and xe have a
  few each, amdgpu makes up most of it with a bunch of SR-IOV related
  fixes amongst others.

  i915:
   - Fix BMG support to UHBR13.5
   - Two PSR fixes
   - Fix colorimetry detection for DP

  xe:
   - Fix macro for checking minimum GuC version
   - Fix CCS offset calculation for some BMG SKUs
   - Fix locking on memory usage reporting via fdinfo and BO destroy
   - Fix GPU page fault handler on a closed VM
   - Fix overflow in oa batch buffer

  amdgpu:
   - MES 12 fix
   - KFD fence sync fix
   - SR-IOV fixes
   - VCN 4.0.6 fix
   - SDMA 7.x fix
   - Bump driver version to note cleared VRAM support
   - SWSMU fix
   - CU occupancy logic fix
   - SDMA queue fix"

* tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm/kernel: (79 commits)
  drm/amd/pm: update workload mask after the setting
  drm/amdgpu: bump driver version for cleared VRAM
  drm/amdgpu: fix vbios fetching for SR-IOV
  drm/amdgpu: fix PTE copy corruption for sdma 7
  drm/amdkfd: Add SDMA queue quantum support for GFX12
  drm/amdgpu/vcn: enable AV1 on both instances
  drm/amdkfd: Fix CU occupancy for GFX 9.4.3
  drm/amdkfd: Update logic for CU occupancy calculations
  drm/amdgpu: skip coredump after job timeout in SRIOV
  drm/amdgpu: sync to KFD fences before clearing PTEs
  drm/amdgpu/mes12: set enable_level_process_quantum_check
  drm/i915/dp: Fix colorimetry detection
  drm/amdgpu/mes12: reduce timeout
  drm/amdgpu/mes11: reduce timeout
  drm/amdgpu: use GEM references instead of TTMs v2
  drm/amd/display: Allow backlight to go below `AMDGPU_DM_DEFAULT_MIN_BACKLIGHT`
  drm/amd/display: Fix kdoc entry for 'tps' in 'dc_process_dmub_dpia_set_tps_notification'
  drm/amdgpu: update golden regs for gfx12
  drm/amdgpu: clean up vbios fetching code
  drm/amd/display: handle nulled pipe context in DCE110's set_drr()
  ...

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1083,10 +1083,6 @@ struct amdgpu_device {
 
 	struct amdgpu_virt	virt;
 
-	/* link all shadow bo */
-	struct list_head                shadow_list;
-	struct mutex                    shadow_list_lock;
-
 	/* record hw reset is performed */
 	bool has_hw_reset;
 	u8				reset_magic[AMDGPU_RESET_MAGIC_NUM];

drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c

@@ -511,7 +511,7 @@ static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *h
 		return -EINVAL;
 	}
 
-	/* udpate aca bank to aca source error_cache first */
+	/* update aca bank to aca source error_cache first */
 	ret = aca_banks_update(adev, smu_type, handler_aca_log_bank_error, qctx, NULL);
 	if (ret)
 		return ret;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -950,28 +950,30 @@ static void unlock_spi_csq_mutexes(struct amdgpu_device *adev)
  * @inst: xcc's instance number on a multi-XCC setup
  */
 static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
-		int *wave_cnt, int *vmid, uint32_t inst)
+		struct kfd_cu_occupancy *queue_cnt, uint32_t inst)
 {
 	int pipe_idx;
 	int queue_slot;
 	unsigned int reg_val;
-
+	unsigned int wave_cnt;
 	/*
 	 * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID
 	 * parameters to read out waves in flight. Get VMID if there are
 	 * non-zero waves in flight.
 	 */
-	*vmid = 0xFF;
-	*wave_cnt = 0;
 	pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe;
 	queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe;
-	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, inst);
-	reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, inst, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
-			 queue_slot);
-	*wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
-	if (*wave_cnt != 0)
-		*vmid = (RREG32_SOC15(GC, inst, mmCP_HQD_VMID) &
-			 CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT;
+	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, GET_INST(GC, inst));
+	reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
+				  mmSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot);
+	wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
+	if (wave_cnt != 0) {
+		queue_cnt->wave_cnt += wave_cnt;
+		queue_cnt->doorbell_off =
+			(RREG32_SOC15(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL) &
+			 CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >>
+			 CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	}
 }
 
 /**
@@ -981,9 +983,8 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
  * or more queues running and submitting waves to compute units.
  *
  * @adev: Handle of device from which to get number of waves in flight
- * @pasid: Identifies the process for which this query call is invoked
- * @pasid_wave_cnt: Output parameter updated with number of waves in flight that
- *                  belong to process with given pasid
+ * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset
+ *		  for comparison later.
  * @max_waves_per_cu: Output parameter updated with maximum number of waves
  *                    possible per Compute Unit
  * @inst: xcc's instance number on a multi-XCC setup
@@ -1011,34 +1012,28 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
  *    number of waves that are in flight for the queue at specified index. The
  *    index ranges from 0 to 7.
  *
- *    If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID
- *    of the wave(s).
+ *    If non-zero waves are in flight, store the corresponding doorbell offset
+ *    of the queue, along with the wave count.
  *
- *    Determine if VMID from above step maps to pasid provided as parameter. If
- *    it matches agrregate the wave count. That the VMID will not match pasid is
- *    a normal condition i.e. a device is expected to support multiple queues
- *    from multiple proceses.
+ *    Determine if the queue belongs to the process by comparing the doorbell
+ *    offset against the process's queues. If it matches, aggregate the wave
+ *    count for the process.
  *
  *  Reading registers referenced above involves programming GRBM appropriately
  */
-void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid,
-		int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst)
+void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev,
+				 struct kfd_cu_occupancy *cu_occupancy,
+				 int *max_waves_per_cu, uint32_t inst)
 {
 	int qidx;
-	int vmid;
 	int se_idx;
-	int sh_idx;
 	int se_cnt;
-	int sh_cnt;
-	int wave_cnt;
 	int queue_map;
-	int pasid_tmp;
 	int max_queue_cnt;
-	int vmid_wave_cnt = 0;
 	DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES);
 
 	lock_spi_csq_mutexes(adev);
-	soc15_grbm_select(adev, 1, 0, 0, 0, inst);
+	soc15_grbm_select(adev, 1, 0, 0, 0, GET_INST(GC, inst));
 
 	/*
 	 * Iterate through the shader engines and arrays of the device
@@ -1048,51 +1043,38 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid,
 			  AMDGPU_MAX_QUEUES);
 	max_queue_cnt = adev->gfx.mec.num_pipe_per_mec *
 			adev->gfx.mec.num_queue_per_pipe;
-	sh_cnt = adev->gfx.config.max_sh_per_se;
 	se_cnt = adev->gfx.config.max_shader_engines;
 	for (se_idx = 0; se_idx < se_cnt; se_idx++) {
-		for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) {
+		amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst);
+		queue_map = RREG32_SOC15(GC, GET_INST(GC, inst), mmSPI_CSQ_WF_ACTIVE_STATUS);
+
+		/*
+		 * Assumption: queue map encodes following schema: four
+		 * pipes per each micro-engine, with each pipe mapping
+		 * eight queues. This schema is true for GFX9 devices
+		 * and must be verified for newer device families
+		 */
+		for (qidx = 0; qidx < max_queue_cnt; qidx++) {
+			/* Skip qeueus that are not associated with
+			 * compute functions
+			 */
+			if (!test_bit(qidx, cp_queue_bitmap))
+				continue;
 
-			amdgpu_gfx_select_se_sh(adev, se_idx, sh_idx, 0xffffffff, inst);
-			queue_map = RREG32_SOC15(GC, inst, mmSPI_CSQ_WF_ACTIVE_STATUS);
+			if (!(queue_map & (1 << qidx)))
+				continue;
 
-			/*
-			 * Assumption: queue map encodes following schema: four
-			 * pipes per each micro-engine, with each pipe mapping
-			 * eight queues. This schema is true for GFX9 devices
-			 * and must be verified for newer device families
-			 */
-			for (qidx = 0; qidx < max_queue_cnt; qidx++) {
-
-				/* Skip qeueus that are not associated with
-				 * compute functions
-				 */
-				if (!test_bit(qidx, cp_queue_bitmap))
-					continue;
-
-				if (!(queue_map & (1 << qidx)))
-					continue;
-
-				/* Get number of waves in flight and aggregate them */
-				get_wave_count(adev, qidx, &wave_cnt, &vmid,
-						inst);
-				if (wave_cnt != 0) {
-					pasid_tmp =
-					  RREG32(SOC15_REG_OFFSET(OSSSYS, inst,
-						 mmIH_VMID_0_LUT) + vmid);
-					if (pasid_tmp == pasid)
-						vmid_wave_cnt += wave_cnt;
-				}
-			}
+			/* Get number of waves in flight and aggregate them */
+			get_wave_count(adev, qidx, &cu_occupancy[qidx],
+					inst);
 		}
 	}
 
 	amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst);
-	soc15_grbm_select(adev, 0, 0, 0, 0, inst);
+	soc15_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, inst));
 	unlock_spi_csq_mutexes(adev);
 
 	/* Update the output parameters and return */
-	*pasid_wave_cnt = vmid_wave_cnt;
 	*max_waves_per_cu = adev->gfx.cu_info.simd_per_cu *
 				adev->gfx.cu_info.max_waves_per_simd;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h

@@ -52,8 +52,9 @@ bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct amdgpu_device *adev,
 					uint8_t vmid, uint16_t *p_pasid);
 void kgd_gfx_v9_set_vm_context_page_table_base(struct amdgpu_device *adev,
 			uint32_t vmid, uint64_t page_table_base);
-void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid,
-		int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst);
+void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev,
+				 struct kfd_cu_occupancy *cu_occupancy,
+				 int *max_waves_per_cu, uint32_t inst);
 void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev,
 		uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr,
 		uint32_t inst);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -1499,7 +1499,7 @@ static int amdgpu_amdkfd_gpuvm_pin_bo(struct amdgpu_bo *bo, u32 domain)
 		}
 	}
 
-	ret = amdgpu_bo_pin_restricted(bo, domain, 0, 0);
+	ret = amdgpu_bo_pin(bo, domain);
 	if (ret)
 		pr_err("Error in Pinning BO to domain: %d\n", domain);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c

@@ -87,8 +87,9 @@ static bool check_atom_bios(uint8_t *bios, size_t size)
  * part of the system bios.  On boot, the system bios puts a
  * copy of the igp rom at the start of vram if a discrete card is
  * present.
+ * For SR-IOV, the vbios image is also put in VRAM in the VF.
  */
-static bool igp_read_bios_from_vram(struct amdgpu_device *adev)
+static bool amdgpu_read_bios_from_vram(struct amdgpu_device *adev)
 {
 	uint8_t __iomem *bios;
 	resource_size_t vram_base;
@@ -284,10 +285,6 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev)
 	acpi_status status;
 	bool found = false;
 
-	/* ATRM is for the discrete card only */
-	if (adev->flags & AMD_IS_APU)
-		return false;
-
 	/* ATRM is for on-platform devices only */
 	if (dev_is_removable(&adev->pdev->dev))
 		return false;
@@ -343,11 +340,8 @@ static inline bool amdgpu_atrm_get_bios(struct amdgpu_device *adev)
 
 static bool amdgpu_read_disabled_bios(struct amdgpu_device *adev)
 {
-	if (adev->flags & AMD_IS_APU)
-		return igp_read_bios_from_vram(adev);
-	else
-		return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ?
-			false : amdgpu_asic_read_disabled_bios(adev);
+	return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ?
+		false : amdgpu_asic_read_disabled_bios(adev);
 }
 
 #ifdef CONFIG_ACPI
@@ -414,7 +408,36 @@ static inline bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
 }
 #endif
 
-bool amdgpu_get_bios(struct amdgpu_device *adev)
+static bool amdgpu_get_bios_apu(struct amdgpu_device *adev)
+{
+	if (amdgpu_acpi_vfct_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from VFCT\n");
+		goto success;
+	}
+
+	if (amdgpu_read_bios_from_vram(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n");
+		goto success;
+	}
+
+	if (amdgpu_read_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
+		goto success;
+	}
+
+	if (amdgpu_read_platform_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from platform\n");
+		goto success;
+	}
+
+	dev_err(adev->dev, "Unable to locate a BIOS ROM\n");
+	return false;
+
+success:
+	return true;
+}
+
+static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev)
 {
 	if (amdgpu_atrm_get_bios(adev)) {
 		dev_info(adev->dev, "Fetched VBIOS from ATRM\n");
@@ -426,7 +449,8 @@ bool amdgpu_get_bios(struct amdgpu_device *adev)
 		goto success;
 	}
 
-	if (igp_read_bios_from_vram(adev)) {
+	/* this is required for SR-IOV */
+	if (amdgpu_read_bios_from_vram(adev)) {
 		dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n");
 		goto success;
 	}
@@ -455,10 +479,24 @@ bool amdgpu_get_bios(struct amdgpu_device *adev)
 	return false;
 
 success:
-	adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10;
 	return true;
 }
 
+bool amdgpu_get_bios(struct amdgpu_device *adev)
+{
+	bool found;
+
+	if (adev->flags & AMD_IS_APU)
+		found = amdgpu_get_bios_apu(adev);
+	else
+		found = amdgpu_get_bios_dgpu(adev);
+
+	if (found)
+		adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10;
+
+	return found;
+}
+
 /* helper function for soc15 and onwards to read bios from rom */
 bool amdgpu_soc15_read_bios_from_rom(struct amdgpu_device *adev,
 				     u8 *bios, u32 length_bytes)