Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 58 insertions, 115 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 555022c065..d3a771afb0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2160,12 +2160,6 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 
 #ifdef CONFIG_MMU_NOTIFIER
 	if (!err && (eb->args->flags & __EXEC_USERPTR_USED)) {
-		read_lock(&eb->i915->mm.notifier_lock);
-
-		/*
-		 * count is always at least 1, otherwise __EXEC_USERPTR_USED
-		 * could not have been set
-		 */
 		for (i = 0; i < count; i++) {
 			struct eb_vma *ev = &eb->vma[i];
 			struct drm_i915_gem_object *obj = ev->vma->obj;
@@ -2177,8 +2171,6 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 			if (err)
 				break;
 		}
-
-		read_unlock(&eb->i915->mm.notifier_lock);
 	}
 #endif
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 3560a062d2..5d7446a48a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -284,7 +284,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj);
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
 {
-	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE);
+	/* TODO: make DPT shrinkable when it has no bound vmas */
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) &&
+		!obj->is_dpt;
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 0d812f4d78..3b27218aab 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -28,6 +28,13 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
 	intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref, 0);
+	/*
+	 * On rare occasions, we've observed the fence completion triggers
+	 * free_engines asynchronously via rcu_call. Ensure those are done.
+	 * This path is only called on suspend, so it's an acceptable cost.
+	 */
+	rcu_barrier();
+
 	flush_workqueue(i915->wq);
 
 	/*
@@ -160,6 +167,9 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 	 * machine in an unusable condition.
 	 */
 
+	/* Like i915_gem_suspend, flush tasks staged from fence triggers */
+	rcu_barrier();
+
 	for_each_gt(gt, i915, i)
 		intel_gt_suspend_late(gt);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index a4fb577ece..b09b74a244 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -129,7 +129,7 @@ i915_gem_object_create_region_at(struct intel_memory_region *mem,
 		return ERR_PTR(-EINVAL);
 
 	if (!(flags & I915_BO_ALLOC_GPU_ONLY) &&
-	    offset + size > mem->io_size &&
+	    offset + size > resource_size(&mem->io) &&
 	    !i915_ggtt_has_aperture(to_gt(mem->i915)->ggtt))
 		return ERR_PTR(-ENOSPC);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 8c88075eea..ad6dd7f325 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -541,7 +541,9 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 
 	/* Exclude the reserved region from driver use */
 	mem->region.end = i915->dsm.reserved.start - 1;
-	mem->io_size = min(mem->io_size, resource_size(&mem->region));
+	mem->io = DEFINE_RES_MEM(mem->io.start,
+				 min(resource_size(&mem->io),
+				     resource_size(&mem->region)));
 
 	i915->dsm.usable_size = resource_size(&mem->region);
 
@@ -752,7 +754,7 @@ static int _i915_gem_object_stolen_init(struct intel_memory_region *mem,
 	 * With discrete devices, where we lack a mappable aperture there is no
 	 * possible way to ever access this memory on the CPU side.
 	 */
-	if (mem->type == INTEL_MEMORY_STOLEN_LOCAL && !mem->io_size &&
+	if (mem->type == INTEL_MEMORY_STOLEN_LOCAL && !resource_size(&mem->io) &&
 	    !(flags & I915_BO_ALLOC_GPU_ONLY))
 		return -ENOSPC;
 
@@ -826,7 +828,6 @@ static const struct intel_memory_region_ops i915_region_stolen_smem_ops = {
 
 static int init_stolen_lmem(struct intel_memory_region *mem)
 {
-	struct drm_i915_private *i915 = mem->i915;
 	int err;
 
 	if (GEM_WARN_ON(resource_size(&mem->region) == 0))
@@ -838,14 +839,10 @@ static int init_stolen_lmem(struct intel_memory_region *mem)
 		return 0;
 	}
 
-	if (mem->io_size &&
-	    !io_mapping_init_wc(&mem->iomap, mem->io_start, mem->io_size))
+	if (resource_size(&mem->io) &&
+	    !io_mapping_init_wc(&mem->iomap, mem->io.start, resource_size(&mem->io)))
 		goto err_cleanup;
 
-	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
-		&mem->io_start);
-	drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &mem->region.start);
-
 	return 0;
 
 err_cleanup:
@@ -855,7 +852,7 @@ err_cleanup:
 
 static int release_stolen_lmem(struct intel_memory_region *mem)
 {
-	if (mem->io_size)
+	if (resource_size(&mem->io))
 		io_mapping_fini(&mem->iomap);
 	i915_gem_cleanup_stolen(mem->i915);
 	return 0;
@@ -938,13 +935,17 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 		GEM_BUG_ON((dsm_base + dsm_size) > lmem_size);
 	} else {
 		/* Use DSM base address instead for stolen memory */
-		dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK;
+		dsm_base = intel_uncore_read64(uncore, GEN6_DSMBASE) & GEN11_BDSM_MASK;
 		if (WARN_ON(lmem_size < dsm_base))
 			return ERR_PTR(-ENODEV);
 		dsm_size = ALIGN_DOWN(lmem_size - dsm_base, SZ_1M);
 	}
 
-	if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
+	if (i915_direct_stolen_access(i915)) {
+		drm_dbg(&i915->drm, "Using direct DSM access\n");
+		io_start = intel_uncore_read64(uncore, GEN6_DSMBASE) & GEN11_BDSM_MASK;
+		io_size = dsm_size;
+	} else if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
 		io_start = 0;
 		io_size = 0;
 	} else {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 9227f8146a..e6f177183c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -65,8 +65,6 @@ static const struct ttm_place sys_placement_flags = {
 static struct ttm_placement i915_sys_placement = {
 	.num_placement = 1,
 	.placement = &sys_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags,
 };
 
 /**
@@ -144,45 +142,41 @@ i915_ttm_place_from_region(const struct intel_memory_region *mr,
 		place->fpfn = offset >> PAGE_SHIFT;
 		WARN_ON(overflows_type(place->fpfn + (size >> PAGE_SHIFT), place->lpfn));
 		place->lpfn = place->fpfn + (size >> PAGE_SHIFT);
-	} else if (mr->io_size && mr->io_size < mr->total) {
+	} else if (resource_size(&mr->io) && resource_size(&mr->io) < mr->total) {
 		if (flags & I915_BO_ALLOC_GPU_ONLY) {
 			place->flags |= TTM_PL_FLAG_TOPDOWN;
 		} else {
 			place->fpfn = 0;
-			WARN_ON(overflows_type(mr->io_size >> PAGE_SHIFT, place->lpfn));
-			place->lpfn = mr->io_size >> PAGE_SHIFT;
+			WARN_ON(overflows_type(resource_size(&mr->io) >> PAGE_SHIFT, place->lpfn));
+			place->lpfn = resource_size(&mr->io) >> PAGE_SHIFT;
 		}
 	}
 }
 
 static void
 i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
-			    struct ttm_place *requested,
-			    struct ttm_place *busy,
+			    struct ttm_place *places,
 			    struct ttm_placement *placement)
 {
 	unsigned int num_allowed = obj->mm.n_placements;
 	unsigned int flags = obj->flags;
 	unsigned int i;
 
-	placement->num_placement = 1;
 	i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
-				   obj->mm.region, requested, obj->bo_offset,
+				   obj->mm.region, &places[0], obj->bo_offset,
 				   obj->base.size, flags);
+	places[0].flags |= TTM_PL_FLAG_DESIRED;
 
 	/* Cache this on object? */
-	placement->num_busy_placement = num_allowed;
-	for (i = 0; i < placement->num_busy_placement; ++i)
-		i915_ttm_place_from_region(obj->mm.placements[i], busy + i,
-					   obj->bo_offset, obj->base.size, flags);
-
-	if (num_allowed == 0) {
-		*busy = *requested;
-		placement->num_busy_placement = 1;
+	for (i = 0; i < num_allowed; ++i) {
+		i915_ttm_place_from_region(obj->mm.placements[i],
+					   &places[i + 1], obj->bo_offset,
+					   obj->base.size, flags);
+		places[i + 1].flags |= TTM_PL_FLAG_FALLBACK;
 	}
 
-	placement->placement = requested;
-	placement->busy_placement = busy;
+	placement->num_placement = num_allowed + 1;
+	placement->placement = places;
 }
 
 static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
@@ -789,7 +783,8 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 	int ret;
 
 	/* First try only the requested placement. No eviction. */
-	real_num_busy = fetch_and_zero(&placement->num_busy_placement);
+	real_num_busy = placement->num_placement;
+	placement->num_placement = 1;
 	ret = ttm_bo_validate(bo, placement, &ctx);
 	if (ret) {
 		ret = i915_ttm_err_to_gem(ret);
@@ -805,7 +800,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 		 * If the initial attempt fails, allow all accepted placements,
 		 * evicting if necessary.
 		 */
-		placement->num_busy_placement = real_num_busy;
+		placement->num_placement = real_num_busy;
 		ret = ttm_bo_validate(bo, placement, &ctx);
 		if (ret)
 			return i915_ttm_err_to_gem(ret);
@@ -839,7 +834,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 
 static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
 {
-	struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
+	struct ttm_place places[I915_TTM_MAX_PLACEMENTS + 1];
 	struct ttm_placement placement;
 
 	/* restricted by sg_alloc_table */
@@ -849,7 +844,7 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
 	GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS);
 
 	/* Move to the requested placement. */
-	i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
+	i915_ttm_placement_from_obj(obj, places, &placement);
 
 	return __i915_ttm_get_pages(obj, &placement);
 }
@@ -879,9 +874,7 @@ static int __i915_ttm_migrate(struct drm_i915_gem_object *obj,
 	i915_ttm_place_from_region(mr, &requested, obj->bo_offset,
 				   obj->base.size, flags);
 	placement.num_placement = 1;
-	placement.num_busy_placement = 1;
 	placement.placement = &requested;
-	placement.busy_placement = &requested;
 
 	ret = __i915_ttm_get_pages(obj, &placement);
 	if (ret)
@@ -1090,7 +1083,7 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 			struct intel_memory_region *mr = obj->mm.placements[i];
 			unsigned int flags;
 
-			if (!mr->io_size && mr->type != INTEL_MEMORY_SYSTEM)
+			if (!resource_size(&mr->io) && mr->type != INTEL_MEMORY_SYSTEM)
 				continue;
 
 			flags = obj->flags;
@@ -1101,8 +1094,9 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 		}
 
 		if (err) {
-			drm_dbg(dev, "Unable to make resource CPU accessible(err = %pe)\n",
-				ERR_PTR(err));
+			drm_dbg_ratelimited(dev,
+					    "Unable to make resource CPU accessible(err = %pe)\n",
+					    ERR_PTR(err));
 			dma_resv_unlock(bo->base.resv);
 			ret = VM_FAULT_SIGBUS;
 			goto out_rpm;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index c08b675935..61abfb5057 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -42,7 +42,6 @@
 #include "i915_drv.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
-#include "i915_gem_userptr.h"
 #include "i915_scatterlist.h"
 
 #ifdef CONFIG_MMU_NOTIFIER
@@ -61,36 +60,7 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni,
 					const struct mmu_notifier_range *range,
 					unsigned long cur_seq)
 {
-	struct drm_i915_gem_object *obj = container_of(mni, struct drm_i915_gem_object, userptr.notifier);
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	long r;
-
-	if (!mmu_notifier_range_blockable(range))
-		return false;
-
-	write_lock(&i915->mm.notifier_lock);
-
 	mmu_interval_set_seq(mni, cur_seq);
-
-	write_unlock(&i915->mm.notifier_lock);
-
-	/*
-	 * We don't wait when the process is exiting. This is valid
-	 * because the object will be cleaned up anyway.
-	 *
-	 * This is also temporarily required as a hack, because we
-	 * cannot currently force non-consistent batch buffers to preempt
-	 * and reschedule by waiting on it, hanging processes on exit.
-	 */
-	if (current->flags & PF_EXITING)
-		return true;
-
-	/* we will unbind on next submission, still have userptr pins */
-	r = dma_resv_wait_timeout(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP, false,
-				  MAX_SCHEDULE_TIMEOUT);
-	if (r <= 0)
-		drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r);
-
 	return true;
 }
 
@@ -583,15 +553,3 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 #endif
 }
 
-int i915_gem_init_userptr(struct drm_i915_private *dev_priv)
-{
-#ifdef CONFIG_MMU_NOTIFIER
-	rwlock_init(&dev_priv->mm.notifier_lock);
-#endif
-
-	return 0;
-}
-
-void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv)
-{
-}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.h b/drivers/gpu/drm/i915/gem/i915_gem_userptr.h
deleted file mode 100644
index 8dadb2f843..0000000000
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2021 Intel Corporation
- */
-
-#ifndef __I915_GEM_USERPTR_H__
-#define __I915_GEM_USERPTR_H__
-
-struct drm_i915_private;
-
-int i915_gem_init_userptr(struct drm_i915_private *dev_priv);
-void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
-
-#endif /* __I915_GEM_USERPTR_H__ */
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 2c51a2c452..99a9ade739 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -1054,7 +1054,7 @@ static int igt_fill_mappable(struct intel_memory_region *mr,
 	int err;
 
 	total = 0;
-	size = mr->io_size;
+	size = resource_size(&mr->io);
 	do {
 		struct drm_i915_gem_object *obj;
 
@@ -1315,28 +1315,28 @@ static int igt_mmap_migrate(void *arg)
 		struct intel_memory_region *mixed[] = { mr, system };
 		struct intel_memory_region *single[] = { mr };
 		struct ttm_resource_manager *man = mr->region_private;
-		resource_size_t saved_io_size;
+		struct resource saved_io;
 		int err;
 
 		if (mr->private)
 			continue;
 
-		if (!mr->io_size)
+		if (!resource_size(&mr->io))
 			continue;
 
 		/*
 		 * For testing purposes let's force small BAR, if not already
 		 * present.
 		 */
-		saved_io_size = mr->io_size;
-		if (mr->io_size == mr->total) {
-			resource_size_t io_size = mr->io_size;
+		saved_io = mr->io;
+		if (resource_size(&mr->io) == mr->total) {
+			resource_size_t io_size = resource_size(&mr->io);
 
 			io_size = rounddown_pow_of_two(io_size >> 1);
 			if (io_size < PAGE_SIZE)
 				continue;
 
-			mr->io_size = io_size;
+			mr->io = DEFINE_RES_MEM(mr->io.start, io_size);
 			i915_ttm_buddy_man_force_visible_size(man,
 							      io_size >> PAGE_SHIFT);
 		}
@@ -1396,9 +1396,9 @@ static int igt_mmap_migrate(void *arg)
 					 IGT_MMAP_MIGRATE_FAIL_GPU |
 					 IGT_MMAP_MIGRATE_UNFAULTABLE);
 out_io_size:
-		mr->io_size = saved_io_size;
+		mr->io = saved_io;
 		i915_ttm_buddy_man_force_visible_size(man,
-						      mr->io_size >> PAGE_SHIFT);
+						      resource_size(&mr->io) >> PAGE_SHIFT);
 		if (err)
 			return err;
 	}