Merge tag 'drm-fixes-2023-10-27' of git://anongit.freedesktop.org/drm/drm

torvalds · torvalds · commit 750b95887e56 · 2023-10-26T20:42:02.000-10:00
Pull drm fixes from Dave Airlie:
 "This is the final set of fixes for 6.6, just misc bits mainly in
  amdgpu and i915, nothing too noteworthy.

  amdgpu:
   - ignore duplicated BOs in CS parser
   - remove redundant call to amdgpu_ctx_priority_is_valid()
   - Extend VI APSM quirks to more platforms

  amdkfd:
   - reserve fence slot while locking BO

  dp_mst:
   - Fix NULL deref in get_mst_branch_device_by_guid_helper()

  logicvc:
   - Kconfig: Select REGMAP and REGMAP_MMIO

  ivpu:
   - Fix missing VPUIP interrupts

  i915:
   - Determine context valid in OA reports
   - Hold GT forcewake during steering operations
   - Check if PMU is closed before stopping event"

* tag 'drm-fixes-2023-10-27' of git://anongit.freedesktop.org/drm/drm:
  accel/ivpu/37xx: Fix missing VPUIP interrupts
  drm/amd: Disable ASPM for VI w/ all Intel systems
  drm/i915/pmu: Check if pmu is closed before stopping event
  drm/i915/mcr: Hold GT forcewake during steering operations
  drm/logicvc: Kconfig: select REGMAP and REGMAP_MMIO
  drm/i915/perf: Determine context valid in OA reports
  drm/amdkfd: reserve a fence slot while locking the BO
  drm/amdgpu: Remove redundant call to priority_is_valid()
  drm/dp_mst: Fix NULL deref in get_mst_branch_device_by_guid_helper()
  drm/amdgpu: ignore duplicate BOs again
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -940,9 +940,6 @@ static u32 ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	if (status == 0)
 		return 0;
 
-	/* Disable global interrupt before handling local buttress interrupts */
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-
 	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
 		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
 			 REGB_RD32(VPU_37XX_BUTTRESS_CURRENT_PLL));
@@ -974,9 +971,6 @@ static u32 ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	else
 		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, status);
 
-	/* Re-enable global interrupt */
-	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-
 	if (schedule_recovery)
 		ivpu_pm_schedule_recovery(vdev);
 
@@ -988,9 +982,14 @@ static irqreturn_t ivpu_hw_37xx_irq_handler(int irq, void *ptr)
 	struct ivpu_device *vdev = ptr;
 	u32 ret_irqv, ret_irqb;
 
+	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
+
 	ret_irqv = ivpu_hw_37xx_irqv_handler(vdev, irq);
 	ret_irqb = ivpu_hw_37xx_irqb_handler(vdev, irq);
 
+	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
+	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
+
 	return IRQ_RETVAL(ret_irqb | ret_irqv);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1103,7 +1103,7 @@ static int reserve_bo_and_vm(struct kgd_mem *mem,
 		if (unlikely(ret))
 			goto error;
 
-		ret = drm_exec_lock_obj(&ctx->exec, &bo->tbo.base);
+		ret = drm_exec_prepare_obj(&ctx->exec, &bo->tbo.base, 1);
 		drm_exec_retry_on_contention(&ctx->exec);
 		if (unlikely(ret))
 			goto error;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -65,7 +65,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
 	}
 
 	amdgpu_sync_create(&p->sync);
-	drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
+		      DRM_EXEC_IGNORE_DUPLICATES);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -55,6 +55,10 @@ bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio)
 		return true;
 	default:
 	case AMDGPU_CTX_PRIORITY_UNSET:
+		/* UNSET priority is not valid and we don't carry that
+		 * around, but set it to NORMAL in the only place this
+		 * function is called, amdgpu_ctx_ioctl().
+		 */
 		return false;
 	}
 }
@@ -95,9 +99,6 @@ amdgpu_ctx_to_drm_sched_prio(int32_t ctx_prio)
 static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 				      int32_t priority)
 {
-	if (!amdgpu_ctx_priority_is_valid(priority))
-		return -EINVAL;
-
 	/* NORMAL and below are accessible by everyone */
 	if (priority <= AMDGPU_CTX_PRIORITY_NORMAL)
 		return 0;
@@ -632,8 +633,6 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 	return 0;
 }
 
-
-
 static int amdgpu_ctx_stable_pstate(struct amdgpu_device *adev,
 				    struct amdgpu_fpriv *fpriv, uint32_t id,
 				    bool set, u32 *stable_pstate)
@@ -676,8 +675,10 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 	id = args->in.ctx_id;
 	priority = args->in.priority;
 
-	/* For backwards compatibility reasons, we need to accept
-	 * ioctls with garbage in the priority field */
+	/* For backwards compatibility, we need to accept ioctls with garbage
+	 * in the priority field. Garbage values in the priority field, result
+	 * in the priority being set to NORMAL.
+	 */
 	if (!amdgpu_ctx_priority_is_valid(priority))
 		priority = AMDGPU_CTX_PRIORITY_NORMAL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1124,7 +1124,7 @@ static void vi_program_aspm(struct amdgpu_device *adev)
 	bool bL1SS = false;
 	bool bClkReqSupport = true;
 
-	if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_aspm_support_quirk())
+	if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_pcie_dynamic_switching_supported())
 		return;
 
 	if (adev->flags & AMD_IS_APU ||
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -2574,14 +2574,14 @@ static struct drm_dp_mst_branch *get_mst_branch_device_by_guid_helper(
 	struct drm_dp_mst_branch *found_mstb;
 	struct drm_dp_mst_port *port;
 
+	if (!mstb)
+		return NULL;
+
 	if (memcmp(mstb->guid, guid, 16) == 0)
 		return mstb;
 
 
 	list_for_each_entry(port, &mstb->ports, next) {
-		if (!port->mstb)
-			continue;
-
 		found_mstb = get_mst_branch_device_by_guid_helper(port->mstb, guid);
 
 		if (found_mstb)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -376,9 +376,26 @@ void intel_gt_mcr_lock(struct intel_gt *gt, unsigned long *flags)
 	 * driver threads, but also with hardware/firmware agents.  A dedicated
 	 * locking register is used.
 	 */
-	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) {
+		/*
+		 * The steering control and semaphore registers are inside an
+		 * "always on" power domain with respect to RC6.  However there
+		 * are some issues if higher-level platform sleep states are
+		 * entering/exiting at the same time these registers are
+		 * accessed.  Grabbing GT forcewake and holding it over the
+		 * entire lock/steer/unlock cycle ensures that those sleep
+		 * states have been fully exited before we access these
+		 * registers.  This wakeref will be released in the unlock
+		 * routine.
+		 *
+		 * This is expected to become a formally documented/numbered
+		 * workaround soon.
+		 */
+		intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_GT);
+
 		err = wait_for(intel_uncore_read_fw(gt->uncore,
 						    MTL_STEER_SEMAPHORE) == 0x1, 100);
+	}
 
 	/*
 	 * Even on platforms with a hardware lock, we'll continue to grab
@@ -415,8 +432,11 @@ void intel_gt_mcr_unlock(struct intel_gt *gt, unsigned long flags)
 {
 	spin_unlock_irqrestore(&gt->mcr_lock, flags);
 
-	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) {
 		intel_uncore_write_fw(gt->uncore, MTL_STEER_SEMAPHORE, 0x1);
+
+		intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_GT);
+	}
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
@@ -482,8 +482,7 @@ static void oa_report_id_clear(struct i915_perf_stream *stream, u32 *report)
 static bool oa_report_ctx_invalid(struct i915_perf_stream *stream, void *report)
 {
 	return !(oa_report_id(stream, report) &
-	       stream->perf->gen8_valid_ctx_bit) &&
-	       GRAPHICS_VER(stream->perf->i915) <= 11;
+	       stream->perf->gen8_valid_ctx_bit);
 }
 
 static u64 oa_timestamp(struct i915_perf_stream *stream, void *report)
@@ -5106,6 +5105,7 @@ static void i915_perf_init_info(struct drm_i915_private *i915)
 		perf->gen8_valid_ctx_bit = BIT(16);
 		break;
 	case 12:
+		perf->gen8_valid_ctx_bit = BIT(16);
 		/*
 		 * Calculate offset at runtime in oa_pin_context for gen12 and
 		 * cache the value in perf->ctx_oactxctrl_offset.
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
@@ -832,9 +832,18 @@ static void i915_pmu_event_start(struct perf_event *event, int flags)
 
 static void i915_pmu_event_stop(struct perf_event *event, int flags)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->closed)
+		goto out;
+
 	if (flags & PERF_EF_UPDATE)
 		i915_pmu_event_read(event);
 	i915_pmu_disable(event);
+
+out:
 	event->hw.state = PERF_HES_STOPPED;
 }
 
diff --git a/drivers/gpu/drm/logicvc/Kconfig b/drivers/gpu/drm/logicvc/Kconfig
@@ -5,5 +5,7 @@ config DRM_LOGICVC
 	select DRM_KMS_HELPER
 	select DRM_KMS_DMA_HELPER
 	select DRM_GEM_DMA_HELPER
+	select REGMAP
+	select REGMAP_MMIO
 	help
 	  DRM display driver for the logiCVC programmable logic block from Xylon

Original file line number	Diff line number	Diff line change
`@@ -65,7 +65,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,`
`65`	`65`	`}`
`66`	`66`
`67`	`67`	`amdgpu_sync_create(&p->sync);`
`68`		`- drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT);`
	`68`	`+ drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT \|`
	`69`	`+ DRM_EXEC_IGNORE_DUPLICATES);`
`69`	`70`	`return 0;`
`70`	`71`	`}`
`71`	`72`