Merge tag 'drm-xe-fixes-2024-02-08' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Driver Changes:
- Fix a loop in an error path
- Fix a missing dma-fence reference
- Fix a retry path on userptr REMAP
- Workaround for a false gcc warning
- Fix missing map of the usm batch buffer
  in the migrate vm.
- Fix a memory leak.
- Fix a bad assumption of used page size
- Fix hitting a BUG() due to zero pages to map.
- Remove some leftover async bind queue relics

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

From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZcS2LllawGifubsk@fedora

9 files changed, 57 insertions, 65 deletions

diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae0e..e4db069f0db3f1 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c59f..254b1d3af4cb56 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -926,20 +926,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec129561..35474ddbaf97ec 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9c2fe1697d6eef..73f08f1924df2e 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c5462425217..70480c30560215 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad82..4e2ccad0e52fab 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115e9..aab92bee1d7cf2 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30db264d34a323..865e10d0a06aa3 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -114,11 +112,8 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
@@ -1984,6 +1979,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
@@ -2064,7 +2060,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2111,15 +2106,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
@@ -2199,8 +2185,10 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 		return SZ_1G;
 	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
 static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
@@ -2530,13 +2518,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
@@ -2548,13 +2548,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2669,7 +2662,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
@@ -2714,16 +2707,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
 #define SUPPORTED_FLAGS	\
 	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 1fec66ae2eb2dd..5ac9c5bebabc3c 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,9 +21,6 @@ struct xe_bo;
 struct xe_sync_entry;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -360,11 +357,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;