Merge tag 'drm-xe-fixes-2024-10-17' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Driver Changes:
- New workaround to Xe2 (Aradhya)
- Fix unbalanced rpm put (Matthew Auld)
- Remove fragile lock optimization (Matthew Brost)
- Fix job release, delegating it to the drm scheduler (Matthew Brost)
- Fix timestamp bit width for Xe2 (Lucas)
- Fix external BO's dma-resv usag (Matthew Brost)
- Fix returning success for timeout in wait_token (Nirmoy)
- Initialize fence to avoid it being detected as signaled (Matthew Auld)
- Improve cache flush for BMG (Matthew Auld)
- Don't allow hflip for tile4 framebuffer on Xe2 (Juha-Pekka)

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

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/jkldrex5733ldxrla75b4ayvhujjhw2kccmasl5rotoufoacj4@pkvlrrv4orc7

16 files changed, 63 insertions, 44 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 5be7bb43e2e0..35557d98d7a7 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -438,6 +438,19 @@ bool intel_fb_needs_64k_phys(u64 modifier)
 				      INTEL_PLANE_CAP_NEED64K_PHYS);
 }
 
+/**
+ * intel_fb_is_tile4_modifier: Check if a modifier is a tile4 modifier type
+ * @modifier: Modifier to check
+ *
+ * Returns:
+ * Returns %true if @modifier is a tile4 modifier.
+ */
+bool intel_fb_is_tile4_modifier(u64 modifier)
+{
+	return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps,
+				      INTEL_PLANE_CAP_TILING_4);
+}
+
 static bool check_modifier_display_ver_range(const struct intel_modifier_desc *md,
 					     u8 display_ver_from, u8 display_ver_until)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h
index 10de437e8ef8..827be3f7934c 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.h
+++ b/drivers/gpu/drm/i915/display/intel_fb.h
@@ -35,6 +35,7 @@ bool intel_fb_is_ccs_modifier(u64 modifier);
 bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier);
 bool intel_fb_is_mc_ccs_modifier(u64 modifier);
 bool intel_fb_needs_64k_phys(u64 modifier);
+bool intel_fb_is_tile4_modifier(u64 modifier);
 
 bool intel_fb_is_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane);
 int intel_fb_rc_ccs_cc_plane(const struct drm_framebuffer *fb);
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 17d4c880ecc4..c8720d31d101 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1591,6 +1591,17 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
+	/*
+	 * Display20 onward tile4 hflip is not supported
+	 */
+	if (rotation & DRM_MODE_REFLECT_X &&
+	    intel_fb_is_tile4_modifier(fb->modifier) &&
+	    DISPLAY_VER(dev_priv) >= 20) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "horizontal flip is not supported with tile4 surface formats\n");
+		return -EINVAL;
+	}
+
 	if (drm_rotation_90_or_270(rotation)) {
 		if (!intel_fb_supports_90_270_rotation(to_intel_framebuffer(fb))) {
 			drm_dbg_kms(&dev_priv->drm,
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index ac9c437e103d..00ad34ed73a5 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -393,9 +393,6 @@
 
 #define XE2_GLOBAL_INVAL			XE_REG(0xb404)
 
-#define SCRATCH1LPFC				XE_REG(0xb474)
-#define   EN_L3_RW_CCS_CACHE_FLUSH		REG_BIT(0)
-
 #define XE2LPM_L3SQCREG2			XE_REG_MCR(0xb604)
 
 #define XE2LPM_L3SQCREG3			XE_REG_MCR(0xb608)
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 5a63d135ba96..0a9ffc19e92f 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -980,13 +980,13 @@ void xe_device_declare_wedged(struct xe_device *xe)
 		return;
 	}
 
+	xe_pm_runtime_get_noresume(xe);
+
 	if (drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe)) {
 		drm_err(&xe->drm, "Failed to register xe_device_wedged_fini clean-up. Although device is wedged.\n");
 		return;
 	}
 
-	xe_pm_runtime_get_noresume(xe);
-
 	if (!atomic_xchg(&xe->wedged.flag, 1)) {
 		xe->needs_flr_on_fini = true;
 		drm_err(&xe->drm,
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7b38485817dc..f23ac1e2ed88 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -41,11 +41,6 @@
  * user knows an exec writes to a BO and reads from the BO in the next exec, it
  * is the user's responsibility to pass in / out fence between the two execs).
  *
- * Implicit dependencies for external BOs are handled by using the dma-buf
- * implicit dependency uAPI (TODO: add link). To make this works each exec must
- * install the job's fence into the DMA_RESV_USAGE_WRITE slot of every external
- * BO mapped in the VM.
- *
  * We do not allow a user to trigger a bind at exec time rather we have a VM
  * bind IOCTL which uses the same in / out fence interface as exec. In that
  * sense, a VM bind is basically the same operation as an exec from the user
@@ -59,8 +54,8 @@
  * behind any pending kernel operations on any external BOs in VM or any BOs
  * private to the VM. This is accomplished by the rebinds waiting on BOs
  * DMA_RESV_USAGE_KERNEL slot (kernel ops) and kernel ops waiting on all BOs
- * slots (inflight execs are in the DMA_RESV_USAGE_BOOKING for private BOs and
- * in DMA_RESV_USAGE_WRITE for external BOs).
+ * slots (inflight execs are in the DMA_RESV_USAGE_BOOKKEEP for private BOs and
+ * for external BOs).
  *
  * Rebinds / dma-resv usage applies to non-compute mode VMs only as for compute
  * mode VMs we use preempt fences and a rebind worker (TODO: add link).
@@ -304,7 +299,8 @@ retry:
 	xe_sched_job_arm(job);
 	if (!xe_vm_in_lr_mode(vm))
 		drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, &job->drm.s_fence->finished,
-					 DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_WRITE);
+					 DMA_RESV_USAGE_BOOKKEEP,
+					 DMA_RESV_USAGE_BOOKKEEP);
 
 	for (i = 0; i < num_syncs; i++) {
 		xe_sync_entry_signal(&syncs[i], &job->drm.s_fence->finished);
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 5ad5629a6c60..64b2ae6839db 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -63,7 +63,9 @@ xe_sched_invalidate_job(struct xe_sched_job *job, int threshold)
 static inline void xe_sched_add_pending_job(struct xe_gpu_scheduler *sched,
 					    struct xe_sched_job *job)
 {
+	spin_lock(&sched->base.job_list_lock);
 	list_add(&job->drm.list, &sched->base.pending_list);
+	spin_unlock(&sched->base.job_list_lock);
 }
 
 static inline
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index ea65cf59372c..d5fd6a089b7c 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -108,7 +108,6 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
 		return;
 
 	if (!xe_gt_is_media_type(gt)) {
-		xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH);
 		reg = xe_gt_mcr_unicast_read_any(gt, XE2_GAMREQSTRM_CTRL);
 		reg |= CG_DIS_CNTLBUS;
 		xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index cca9cf536f76..bbb9e411d21f 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -37,6 +37,15 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
 	return hw_tlb_timeout + 2 * delay;
 }
 
+static void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+	if (WARN_ON_ONCE(!fence->gt))
+		return;
+
+	xe_pm_runtime_put(gt_to_xe(fence->gt));
+	fence->gt = NULL; /* fini() should be called once */
+}
+
 static void
 __invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
 {
@@ -204,7 +213,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 						   tlb_timeout_jiffies(gt));
 		}
 		spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
-	} else if (ret < 0) {
+	} else {
 		__invalidation_fence_signal(xe, fence);
 	}
 	if (!ret) {
@@ -267,10 +276,8 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 
 		xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
 		ret = xe_gt_tlb_invalidation_guc(gt, &fence);
-		if (ret < 0) {
-			xe_gt_tlb_invalidation_fence_fini(&fence);
+		if (ret)
 			return ret;
-		}
 
 		xe_gt_tlb_invalidation_fence_wait(&fence);
 	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
@@ -496,7 +503,8 @@ static const struct dma_fence_ops invalidation_fence_ops = {
  * @stack: fence is stack variable
  *
  * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
- * must be called if fence is not signaled.
+ * will be automatically called when fence is signalled (all fences must signal),
+ * even on error.
  */
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
@@ -516,14 +524,3 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 		dma_fence_get(&fence->base);
 	fence->gt = gt;
 }
-
-/**
- * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
- * @fence: TLB invalidation fence to finalize
- *
- * Drop PM ref which fence took durinig init.
- */
-void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
-{
-	xe_pm_runtime_put(gt_to_xe(fence->gt));
-}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index a84065fa324c..f430d5797af7 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -28,7 +28,6 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
 				       bool stack);
-void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
 
 static inline void
 xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 63495007f336..8a9254e5af6e 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1030,10 +1030,13 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 
 	/*
 	 * TDR has fired before free job worker. Common if exec queue
-	 * immediately closed after last fence signaled.
+	 * immediately closed after last fence signaled. Add back to pending
+	 * list so job can be freed and kick scheduler ensuring free job is not
+	 * lost.
 	 */
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) {
-		guc_exec_queue_free_job(drm_job);
+		xe_sched_add_pending_job(sched, job);
+		xe_sched_submission_start(sched);
 
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 28d9bb3b825d..848da8e68c7a 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -161,7 +161,11 @@ query_engine_cycles(struct xe_device *xe,
 			  cpu_clock);
 
 	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	resp.width = 36;
+
+	if (GRAPHICS_VER(xe) >= 20)
+		resp.width = 64;
+	else
+		resp.width = 36;
 
 	/* Only write to the output fields of user query */
 	if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp))
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index bb3c2a830362..c6cf227ead40 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -58,7 +58,7 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 	if (!access_ok(ptr, sizeof(*ptr)))
 		return ERR_PTR(-EFAULT);
 
-	ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
+	ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);
 	if (!ufence)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ce9dca4d4e87..c99380271de6 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3199,10 +3199,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 
 			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
 							 &fence[fence_id], vma);
-			if (ret < 0) {
-				xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+			if (ret)
 				goto wait;
-			}
 			++fence_id;
 
 			if (!tile->media_gt)
@@ -3214,10 +3212,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 
 			ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
 							 &fence[fence_id], vma);
-			if (ret < 0) {
-				xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+			if (ret)
 				goto wait;
-			}
 			++fence_id;
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index d424992514a4..353936a0f877 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -710,6 +710,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
 			     DIS_PARTIAL_AUTOSTRIP |
 			     DIS_AUTOSTRIP))
 	},
+	{ XE_RTP_NAME("15016589081"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
+	},
 
 	/* Xe2_HPG */
 	{ XE_RTP_NAME("15010599737"),
diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c
index d46fa8374980..f5deb81eba01 100644
--- a/drivers/gpu/drm/xe/xe_wait_user_fence.c
+++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c
@@ -169,9 +169,6 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data,
 			args->timeout = 0;
 	}
 
-	if (!timeout && !(err < 0))
-		err = -ETIME;
-
 	if (q)
 		xe_exec_queue_put(q);