Merge tag 'drm-xe-next-2024-08-28' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

UAPI Changes:
- Fix OA format masks which were breaking build with gcc-5

Cross-subsystem Changes:

Driver Changes:
- Use dma_fence_chain_free in chain fence unused as a sync (Matthew Brost)
- Refactor hw engine lookup and mmio access to be used in more places
  (Dominik, Matt Auld, Mika Kuoppala)
- Enable priority mem read for Xe2 and later (Pallavi Mishra)
- Fix PL1 disable flow in xe_hwmon_power_max_write (Karthik)
- Fix refcount and speedup devcoredump (Matthew Brost)
- Add performance tuning changes to Xe2 (Akshata, Shekhar)
- Fix OA sysfs entry (Ashutosh)
- Add first GuC firmware support for BMG (Julia)
- Bump minimum GuC firmware for platforms under force_probe to match LNL
  and BMG (Julia)
- Fix access check on user fence creation (Nirmoy)
- Add/document workarounds for Xe2 (Julia, Daniele, John, Tejas)
- Document workaround and use proper WA infra (Matt Roper)
- Fix VF configuration on media GT (Michal Wajdeczko)
- Fix VM dma-resv lock (Matthew Brost)
- Allow suspend/resume exec queue backend op to be called multiple times
  (Matthew Brost)
- Add GT stats to debugfs (Nirmoy)
- Add hwconfig to debugfs (Matt Roper)
- Compile out all debugfs code with ONFIG_DEUBG_FS=n (Lucas)
- Remove dead kunit code (Jani Nikula)
- Refactor drvdata storing to help display (Jani Nikula)
- Cleanup unsused xe parameter in pte handling (Himal)
- Rename s/enable_display/probe_display/ for clarity (Lucas)
- Fix missing MCR annotation in couple of registers (Tejas)
- Fix DGFX display suspend/resume (Maarten)
- Prepare exec_queue_kill for PXP handling (Daniele)
- Fix devm/drmm issues (Daniele, Matthew Brost)
- Fix tile and ggtt fini sequences (Matthew Brost)
- Fix crashes when probing without firmware in place (Daniele, Matthew Brost)
- Use xe_managed for kernel BOs (Daniele, Matthew Brost)
- Future-proof dss_per_group calculation by using hwconfig (Matt Roper)
- Use reserved copy engine for user binds on faulting devices
  (Matthew Brost)
- Allow mixing dma-fence jobs and long-running faulting jobs (Francois)
- Cleanup redundant arg when creating use BO (Nirmoy)
- Prevent UAF around preempt fence (Auld)
- Fix display suspend/resume (Maarten)
- Use vma_pages() helper (Thorsten)
- Calculate pagefault queue size (Stuart, Matthew Auld)
- Fix missing pagefault wq destroy (Stuart)
- Fix lifetime handling of HW fence ctx (Matthew Brost)
- Fix order destroy order for jobs (Matthew Brost)
- Fix TLB invalidation for media GT (Matthew Brost)
- Document GGTT (Rodrigo Vivi)
- Refactor GGTT layering and fix runtime outer protection (Rodrigo Vivi)
- Handle HPD polling on display pm runtime suspend/resume (Imre, Vinod)
- Drop unrequired NULL checks (Apoorva, Himal)
- Use separate rpm lockdep map for non-d3cold-capable devices (Thomas Hellström)
- Support "nomodeset" kernel command-line option (Thomas Zimmermann)
- Drop force_probe requirement for LNL and BMG (Lucas, Balasubramani)

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

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/wd42jsh4i3q5zlrmi2cljejohdsrqc6hvtxf76lbxsp3ibrgmz@y54fa7wwxgsd

1 files changed, 37 insertions, 53 deletions

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index dab2a3b2e17f..4cc13eddb6b3 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -275,6 +275,8 @@ out_up_write:
  * xe_vm_remove_compute_exec_queue() - Remove compute exec queue from VM
  * @vm: The VM.
  * @q: The exec_queue
+ *
+ * Note that this function might be called multiple times on the same queue.
  */
 void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 {
@@ -282,8 +284,10 @@ void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 		return;
 
 	down_write(&vm->lock);
-	list_del(&q->lr.link);
-	--vm->preempt.num_exec_queues;
+	if (!list_empty(&q->lr.link)) {
+		list_del_init(&q->lr.link);
+		--vm->preempt.num_exec_queues;
+	}
 	if (q->lr.pfence) {
 		dma_fence_enable_sw_signaling(q->lr.pfence);
 		dma_fence_put(q->lr.pfence);
@@ -1191,7 +1195,7 @@ static const struct drm_gpuvm_ops gpuvm_ops = {
 	.vm_free = xe_vm_free,
 };
 
-static u64 pde_encode_pat_index(struct xe_device *xe, u16 pat_index)
+static u64 pde_encode_pat_index(u16 pat_index)
 {
 	u64 pte = 0;
 
@@ -1204,8 +1208,7 @@ static u64 pde_encode_pat_index(struct xe_device *xe, u16 pat_index)
 	return pte;
 }
 
-static u64 pte_encode_pat_index(struct xe_device *xe, u16 pat_index,
-				u32 pt_level)
+static u64 pte_encode_pat_index(u16 pat_index, u32 pt_level)
 {
 	u64 pte = 0;
 
@@ -1246,12 +1249,11 @@ static u64 pte_encode_ps(u32 pt_level)
 static u64 xelp_pde_encode_bo(struct xe_bo *bo, u64 bo_offset,
 			      const u16 pat_index)
 {
-	struct xe_device *xe = xe_bo_device(bo);
 	u64 pde;
 
 	pde = xe_bo_addr(bo, bo_offset, XE_PAGE_SIZE);
 	pde |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pde |= pde_encode_pat_index(xe, pat_index);
+	pde |= pde_encode_pat_index(pat_index);
 
 	return pde;
 }
@@ -1259,12 +1261,11 @@ static u64 xelp_pde_encode_bo(struct xe_bo *bo, u64 bo_offset,
 static u64 xelp_pte_encode_bo(struct xe_bo *bo, u64 bo_offset,
 			      u16 pat_index, u32 pt_level)
 {
-	struct xe_device *xe = xe_bo_device(bo);
 	u64 pte;
 
 	pte = xe_bo_addr(bo, bo_offset, XE_PAGE_SIZE);
 	pte |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
+	pte |= pte_encode_pat_index(pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo))
@@ -1276,14 +1277,12 @@ static u64 xelp_pte_encode_bo(struct xe_bo *bo, u64 bo_offset,
 static u64 xelp_pte_encode_vma(u64 pte, struct xe_vma *vma,
 			       u16 pat_index, u32 pt_level)
 {
-	struct xe_device *xe = xe_vma_vm(vma)->xe;
-
 	pte |= XE_PAGE_PRESENT;
 
 	if (likely(!xe_vma_read_only(vma)))
 		pte |= XE_PAGE_RW;
 
-	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
+	pte |= pte_encode_pat_index(pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (unlikely(xe_vma_is_null(vma)))
@@ -1303,7 +1302,7 @@ static u64 xelp_pte_encode_addr(struct xe_device *xe, u64 addr,
 
 	pte = addr;
 	pte |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
+	pte |= pte_encode_pat_index(pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (devmem)
@@ -1483,19 +1482,13 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	/* Kernel migration VM shouldn't have a circular loop.. */
 	if (!(flags & XE_VM_FLAG_MIGRATION)) {
 		for_each_tile(tile, xe, id) {
-			struct xe_gt *gt = tile->primary_gt;
-			struct xe_vm *migrate_vm;
 			struct xe_exec_queue *q;
 			u32 create_flags = EXEC_QUEUE_FLAG_VM;
 
 			if (!vm->pt_root[id])
 				continue;
 
-			migrate_vm = xe_migrate_get_vm(tile->migrate);
-			q = xe_exec_queue_create_class(xe, gt, migrate_vm,
-						       XE_ENGINE_CLASS_COPY,
-						       create_flags);
-			xe_vm_put(migrate_vm);
+			q = xe_exec_queue_create_bind(xe, tile, create_flags, 0);
 			if (IS_ERR(q)) {
 				err = PTR_ERR(q);
 				goto err_close;
@@ -1508,13 +1501,6 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	if (number_tiles > 1)
 		vm->composite_fence_ctx = dma_fence_context_alloc(1);
 
-	mutex_lock(&xe->usm.lock);
-	if (flags & XE_VM_FLAG_FAULT_MODE)
-		xe->usm.num_vm_in_fault_mode++;
-	else if (!(flags & XE_VM_FLAG_MIGRATION))
-		xe->usm.num_vm_in_non_fault_mode++;
-	mutex_unlock(&xe->usm.lock);
-
 	trace_xe_vm_create(vm);
 
 	return vm;
@@ -1628,11 +1614,6 @@ void xe_vm_close_and_put(struct xe_vm *vm)
 	up_write(&vm->lock);
 
 	mutex_lock(&xe->usm.lock);
-	if (vm->flags & XE_VM_FLAG_FAULT_MODE)
-		xe->usm.num_vm_in_fault_mode--;
-	else if (!(vm->flags & XE_VM_FLAG_MIGRATION))
-		xe->usm.num_vm_in_non_fault_mode--;
-
 	if (vm->usm.asid) {
 		void *lookup;
 
@@ -1770,14 +1751,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
 		return -EINVAL;
 
-	if (XE_IOCTL_DBG(xe, args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE &&
-			 xe_device_in_non_fault_mode(xe)))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !(args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE) &&
-			 xe_device_in_fault_mode(xe)))
-		return -EINVAL;
-
 	if (XE_IOCTL_DBG(xe, args->extensions))
 		return -EINVAL;
 
@@ -3185,9 +3158,10 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 {
 	struct xe_device *xe = xe_vma_vm(vma)->xe;
 	struct xe_tile *tile;
-	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE];
-	u32 tile_needs_invalidate = 0;
+	struct xe_gt_tlb_invalidation_fence
+		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
 	u8 id;
+	u32 fence_id = 0;
 	int ret = 0;
 
 	xe_assert(xe, !xe_vma_is_null(vma));
@@ -3215,27 +3189,37 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 		if (xe_pt_zap_ptes(tile, vma)) {
 			xe_device_wmb(xe);
 			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
-							  &fence[id], true);
+							  &fence[fence_id],
+							  true);
 
-			/*
-			 * FIXME: We potentially need to invalidate multiple
-			 * GTs within the tile
-			 */
 			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
-							 &fence[id], vma);
+							 &fence[fence_id], vma);
 			if (ret < 0) {
-				xe_gt_tlb_invalidation_fence_fini(&fence[id]);
+				xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
 				goto wait;
 			}
+			++fence_id;
+
+			if (!tile->media_gt)
+				continue;
 
-			tile_needs_invalidate |= BIT(id);
+			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
+							  &fence[fence_id],
+							  true);
+
+			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]);
+				goto wait;
+			}
+			++fence_id;
 		}
 	}
 
 wait:
-	for_each_tile(tile, xe, id)
-		if (tile_needs_invalidate & BIT(id))
-			xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+	for (id = 0; id < fence_id; ++id)
+		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
 
 	vma->tile_invalidated = vma->tile_mask;