Merge drm/drm-next into drm-intel-next

Sync up with v5.18-rc1, in particular to get 5e3094cfd9fb
("drm/i915/xehpsdv: Add has_flat_ccs to device info").

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

4 files changed, 350 insertions, 47 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index e7e6c4b2c81d..ab751192eb3b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -27,9 +27,11 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_region.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_context.h"
 #include "gt/intel_gpu_commands.h"
+#include "gt/intel_gtt.h"
 
 #include "i915_random.h"
 #include "i915_selftest.h"
@@ -239,6 +241,8 @@ static int lowlevel_hole(struct i915_address_space *vm,
 			 u64 hole_start, u64 hole_end,
 			 unsigned long end_time)
 {
+	const unsigned int min_alignment =
+		i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
 	I915_RND_STATE(seed_prng);
 	struct i915_vma_resource *mock_vma_res;
 	unsigned int size;
@@ -252,9 +256,10 @@ static int lowlevel_hole(struct i915_address_space *vm,
 		I915_RND_SUBSTATE(prng, seed_prng);
 		struct drm_i915_gem_object *obj;
 		unsigned int *order, count, n;
-		u64 hole_size;
+		u64 hole_size, aligned_size;
 
-		hole_size = (hole_end - hole_start) >> size;
+		aligned_size = max_t(u32, ilog2(min_alignment), size);
+		hole_size = (hole_end - hole_start) >> aligned_size;
 		if (hole_size > KMALLOC_MAX_SIZE / sizeof(u32))
 			hole_size = KMALLOC_MAX_SIZE / sizeof(u32);
 		count = hole_size >> 1;
@@ -275,8 +280,8 @@ static int lowlevel_hole(struct i915_address_space *vm,
 		}
 		GEM_BUG_ON(!order);
 
-		GEM_BUG_ON(count * BIT_ULL(size) > vm->total);
-		GEM_BUG_ON(hole_start + count * BIT_ULL(size) > hole_end);
+		GEM_BUG_ON(count * BIT_ULL(aligned_size) > vm->total);
+		GEM_BUG_ON(hole_start + count * BIT_ULL(aligned_size) > hole_end);
 
 		/* Ignore allocation failures (i.e. don't report them as
 		 * a test failure) as we are purposefully allocating very
@@ -299,10 +304,10 @@ static int lowlevel_hole(struct i915_address_space *vm,
 		}
 
 		for (n = 0; n < count; n++) {
-			u64 addr = hole_start + order[n] * BIT_ULL(size);
+			u64 addr = hole_start + order[n] * BIT_ULL(aligned_size);
 			intel_wakeref_t wakeref;
 
-			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
+			GEM_BUG_ON(addr + BIT_ULL(aligned_size) > vm->total);
 
 			if (igt_timeout(end_time,
 					"%s timed out before %d/%d\n",
@@ -345,7 +350,7 @@ alloc_vm_end:
 			}
 
 			mock_vma_res->bi.pages = obj->mm.pages;
-			mock_vma_res->node_size = BIT_ULL(size);
+			mock_vma_res->node_size = BIT_ULL(aligned_size);
 			mock_vma_res->start = addr;
 
 			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
@@ -356,7 +361,7 @@ alloc_vm_end:
 
 		i915_random_reorder(order, count, &prng);
 		for (n = 0; n < count; n++) {
-			u64 addr = hole_start + order[n] * BIT_ULL(size);
+			u64 addr = hole_start + order[n] * BIT_ULL(aligned_size);
 			intel_wakeref_t wakeref;
 
 			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
@@ -400,8 +405,10 @@ static int fill_hole(struct i915_address_space *vm,
 {
 	const u64 hole_size = hole_end - hole_start;
 	struct drm_i915_gem_object *obj;
+	const unsigned int min_alignment =
+		i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
 	const unsigned long max_pages =
-		min_t(u64, ULONG_MAX - 1, hole_size/2 >> PAGE_SHIFT);
+		min_t(u64, ULONG_MAX - 1, (hole_size / 2) >> ilog2(min_alignment));
 	const unsigned long max_step = max(int_sqrt(max_pages), 2UL);
 	unsigned long npages, prime, flags;
 	struct i915_vma *vma;
@@ -442,14 +449,17 @@ static int fill_hole(struct i915_address_space *vm,
 
 				offset = p->offset;
 				list_for_each_entry(obj, &objects, st_link) {
+					u64 aligned_size = round_up(obj->base.size,
+								    min_alignment);
+
 					vma = i915_vma_instance(obj, vm, NULL);
 					if (IS_ERR(vma))
 						continue;
 
 					if (p->step < 0) {
-						if (offset < hole_start + obj->base.size)
+						if (offset < hole_start + aligned_size)
 							break;
-						offset -= obj->base.size;
+						offset -= aligned_size;
 					}
 
 					err = i915_vma_pin(vma, 0, 0, offset | flags);
@@ -471,22 +481,25 @@ static int fill_hole(struct i915_address_space *vm,
 					i915_vma_unpin(vma);
 
 					if (p->step > 0) {
-						if (offset + obj->base.size > hole_end)
+						if (offset + aligned_size > hole_end)
 							break;
-						offset += obj->base.size;
+						offset += aligned_size;
 					}
 				}
 
 				offset = p->offset;
 				list_for_each_entry(obj, &objects, st_link) {
+					u64 aligned_size = round_up(obj->base.size,
+								    min_alignment);
+
 					vma = i915_vma_instance(obj, vm, NULL);
 					if (IS_ERR(vma))
 						continue;
 
 					if (p->step < 0) {
-						if (offset < hole_start + obj->base.size)
+						if (offset < hole_start + aligned_size)
 							break;
-						offset -= obj->base.size;
+						offset -= aligned_size;
 					}
 
 					if (!drm_mm_node_allocated(&vma->node) ||
@@ -507,22 +520,25 @@ static int fill_hole(struct i915_address_space *vm,
 					}
 
 					if (p->step > 0) {
-						if (offset + obj->base.size > hole_end)
+						if (offset + aligned_size > hole_end)
 							break;
-						offset += obj->base.size;
+						offset += aligned_size;
 					}
 				}
 
 				offset = p->offset;
 				list_for_each_entry_reverse(obj, &objects, st_link) {
+					u64 aligned_size = round_up(obj->base.size,
+								    min_alignment);
+
 					vma = i915_vma_instance(obj, vm, NULL);
 					if (IS_ERR(vma))
 						continue;
 
 					if (p->step < 0) {
-						if (offset < hole_start + obj->base.size)
+						if (offset < hole_start + aligned_size)
 							break;
-						offset -= obj->base.size;
+						offset -= aligned_size;
 					}
 
 					err = i915_vma_pin(vma, 0, 0, offset | flags);
@@ -544,22 +560,25 @@ static int fill_hole(struct i915_address_space *vm,
 					i915_vma_unpin(vma);
 
 					if (p->step > 0) {
-						if (offset + obj->base.size > hole_end)
+						if (offset + aligned_size > hole_end)
 							break;
-						offset += obj->base.size;
+						offset += aligned_size;
 					}
 				}
 
 				offset = p->offset;
 				list_for_each_entry_reverse(obj, &objects, st_link) {
+					u64 aligned_size = round_up(obj->base.size,
+								    min_alignment);
+
 					vma = i915_vma_instance(obj, vm, NULL);
 					if (IS_ERR(vma))
 						continue;
 
 					if (p->step < 0) {
-						if (offset < hole_start + obj->base.size)
+						if (offset < hole_start + aligned_size)
 							break;
-						offset -= obj->base.size;
+						offset -= aligned_size;
 					}
 
 					if (!drm_mm_node_allocated(&vma->node) ||
@@ -580,9 +599,9 @@ static int fill_hole(struct i915_address_space *vm,
 					}
 
 					if (p->step > 0) {
-						if (offset + obj->base.size > hole_end)
+						if (offset + aligned_size > hole_end)
 							break;
-						offset += obj->base.size;
+						offset += aligned_size;
 					}
 				}
 			}
@@ -612,6 +631,7 @@ static int walk_hole(struct i915_address_space *vm,
 	const u64 hole_size = hole_end - hole_start;
 	const unsigned long max_pages =
 		min_t(u64, ULONG_MAX - 1, hole_size >> PAGE_SHIFT);
+	unsigned long min_alignment;
 	unsigned long flags;
 	u64 size;
 
@@ -621,6 +641,8 @@ static int walk_hole(struct i915_address_space *vm,
 	if (i915_is_ggtt(vm))
 		flags |= PIN_GLOBAL;
 
+	min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
+
 	for_each_prime_number_from(size, 1, max_pages) {
 		struct drm_i915_gem_object *obj;
 		struct i915_vma *vma;
@@ -639,7 +661,7 @@ static int walk_hole(struct i915_address_space *vm,
 
 		for (addr = hole_start;
 		     addr + obj->base.size < hole_end;
-		     addr += obj->base.size) {
+		     addr += round_up(obj->base.size, min_alignment)) {
 			err = i915_vma_pin(vma, 0, 0, addr | flags);
 			if (err) {
 				pr_err("%s bind failed at %llx + %llx [hole %llx- %llx] with err=%d\n",
@@ -691,6 +713,7 @@ static int pot_hole(struct i915_address_space *vm,
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
+	unsigned int min_alignment;
 	unsigned long flags;
 	unsigned int pot;
 	int err = 0;
@@ -699,6 +722,8 @@ static int pot_hole(struct i915_address_space *vm,
 	if (i915_is_ggtt(vm))
 		flags |= PIN_GLOBAL;
 
+	min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
+
 	obj = i915_gem_object_create_internal(vm->i915, 2 * I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
@@ -711,13 +736,13 @@ static int pot_hole(struct i915_address_space *vm,
 
 	/* Insert a pair of pages across every pot boundary within the hole */
 	for (pot = fls64(hole_end - 1) - 1;
-	     pot > ilog2(2 * I915_GTT_PAGE_SIZE);
+	     pot > ilog2(2 * min_alignment);
 	     pot--) {
 		u64 step = BIT_ULL(pot);
 		u64 addr;
 
-		for (addr = round_up(hole_start + I915_GTT_PAGE_SIZE, step) - I915_GTT_PAGE_SIZE;
-		     addr <= round_down(hole_end - 2*I915_GTT_PAGE_SIZE, step) - I915_GTT_PAGE_SIZE;
+		for (addr = round_up(hole_start + min_alignment, step) - min_alignment;
+		     addr <= round_down(hole_end - (2 * min_alignment), step) - min_alignment;
 		     addr += step) {
 			err = i915_vma_pin(vma, 0, 0, addr | flags);
 			if (err) {
@@ -762,6 +787,7 @@ static int drunk_hole(struct i915_address_space *vm,
 		      unsigned long end_time)
 {
 	I915_RND_STATE(prng);
+	unsigned int min_alignment;
 	unsigned int size;
 	unsigned long flags;
 
@@ -769,15 +795,18 @@ static int drunk_hole(struct i915_address_space *vm,
 	if (i915_is_ggtt(vm))
 		flags |= PIN_GLOBAL;
 
+	min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
+
 	/* Keep creating larger objects until one cannot fit into the hole */
 	for (size = 12; (hole_end - hole_start) >> size; size++) {
 		struct drm_i915_gem_object *obj;
 		unsigned int *order, count, n;
 		struct i915_vma *vma;
-		u64 hole_size;
+		u64 hole_size, aligned_size;
 		int err = -ENODEV;
 
-		hole_size = (hole_end - hole_start) >> size;
+		aligned_size = max_t(u32, ilog2(min_alignment), size);
+		hole_size = (hole_end - hole_start) >> aligned_size;
 		if (hole_size > KMALLOC_MAX_SIZE / sizeof(u32))
 			hole_size = KMALLOC_MAX_SIZE / sizeof(u32);
 		count = hole_size >> 1;
@@ -817,7 +846,7 @@ static int drunk_hole(struct i915_address_space *vm,
 		GEM_BUG_ON(vma->size != BIT_ULL(size));
 
 		for (n = 0; n < count; n++) {
-			u64 addr = hole_start + order[n] * BIT_ULL(size);
+			u64 addr = hole_start + order[n] * BIT_ULL(aligned_size);
 
 			err = i915_vma_pin(vma, 0, 0, addr | flags);
 			if (err) {
@@ -869,11 +898,14 @@ static int __shrink_hole(struct i915_address_space *vm,
 {
 	struct drm_i915_gem_object *obj;
 	unsigned long flags = PIN_OFFSET_FIXED | PIN_USER;
+	unsigned int min_alignment;
 	unsigned int order = 12;
 	LIST_HEAD(objects);
 	int err = 0;
 	u64 addr;
 
+	min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM);
+
 	/* Keep creating larger objects until one cannot fit into the hole */
 	for (addr = hole_start; addr < hole_end; ) {
 		struct i915_vma *vma;
@@ -914,7 +946,7 @@ static int __shrink_hole(struct i915_address_space *vm,
 		}
 
 		i915_vma_unpin(vma);
-		addr += size;
+		addr += round_up(size, min_alignment);
 
 		/*
 		 * Since we are injecting allocation faults at random intervals,
@@ -1038,6 +1070,118 @@ err_purge:
 	return err;
 }
 
+static int misaligned_case(struct i915_address_space *vm, struct intel_memory_region *mr,
+			   u64 addr, u64 size, unsigned long flags)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err = 0;
+	u64 expected_vma_size, expected_node_size;
+	bool is_stolen = mr->type == INTEL_MEMORY_STOLEN_SYSTEM ||
+			 mr->type == INTEL_MEMORY_STOLEN_LOCAL;
+
+	obj = i915_gem_object_create_region(mr, size, 0, 0);
+	if (IS_ERR(obj)) {
+		/* if iGVT-g or DMAR is active, stolen mem will be uninitialized */
+		if (PTR_ERR(obj) == -ENODEV && is_stolen)
+			return 0;
+		return PTR_ERR(obj);
+	}
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_put;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, addr | flags);
+	if (err)
+		goto err_put;
+	i915_vma_unpin(vma);
+
+	if (!drm_mm_node_allocated(&vma->node)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	if (i915_vma_misplaced(vma, 0, 0, addr | flags)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	expected_vma_size = round_up(size, 1 << (ffs(vma->resource->page_sizes_gtt) - 1));
+	expected_node_size = expected_vma_size;
+
+	if (NEEDS_COMPACT_PT(vm->i915) && i915_gem_object_is_lmem(obj)) {
+		/* compact-pt should expand lmem node to 2MB */
+		expected_vma_size = round_up(size, I915_GTT_PAGE_SIZE_64K);
+		expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_2M);
+	}
+
+	if (vma->size != expected_vma_size || vma->node.size != expected_node_size) {
+		err = i915_vma_unbind_unlocked(vma);
+		err = -EBADSLT;
+		goto err_put;
+	}
+
+	err = i915_vma_unbind_unlocked(vma);
+	if (err)
+		goto err_put;
+
+	GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
+
+err_put:
+	i915_gem_object_put(obj);
+	cleanup_freed_objects(vm->i915);
+	return err;
+}
+
+static int misaligned_pin(struct i915_address_space *vm,
+			  u64 hole_start, u64 hole_end,
+			  unsigned long end_time)
+{
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+	unsigned long flags = PIN_OFFSET_FIXED | PIN_USER;
+	int err = 0;
+	u64 hole_size = hole_end - hole_start;
+
+	if (i915_is_ggtt(vm))
+		flags |= PIN_GLOBAL;
+
+	for_each_memory_region(mr, vm->i915, id) {
+		u64 min_alignment = i915_vm_min_alignment(vm, (enum intel_memory_type)id);
+		u64 size = min_alignment;
+		u64 addr = round_down(hole_start + (hole_size / 2), min_alignment);
+
+		/* avoid -ENOSPC on very small hole setups */
+		if (hole_size < 3 * min_alignment)
+			continue;
+
+		/* we can't test < 4k alignment due to flags being encoded in lower bits */
+		if (min_alignment != I915_GTT_PAGE_SIZE_4K) {
+			err = misaligned_case(vm, mr, addr + (min_alignment / 2), size, flags);
+			/* misaligned should error with -EINVAL*/
+			if (!err)
+				err = -EBADSLT;
+			if (err != -EINVAL)
+				return err;
+		}
+
+		/* test for vma->size expansion to min page size */
+		err = misaligned_case(vm, mr, addr, PAGE_SIZE, flags);
+		if (err)
+			return err;
+
+		/* test for intermediate size not expanding vma->size for large alignments */
+		err = misaligned_case(vm, mr, addr, size / 2, flags);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 			  int (*func)(struct i915_address_space *vm,
 				      u64 hole_start, u64 hole_end,
@@ -1107,6 +1251,11 @@ static int igt_ppgtt_shrink_boom(void *arg)
 	return exercise_ppgtt(arg, shrink_boom);
 }
 
+static int igt_ppgtt_misaligned_pin(void *arg)
+{
+	return exercise_ppgtt(arg, misaligned_pin);
+}
+
 static int sort_holes(void *priv, const struct list_head *A,
 		      const struct list_head *B)
 {
@@ -1179,6 +1328,11 @@ static int igt_ggtt_lowlevel(void *arg)
 	return exercise_ggtt(arg, lowlevel_hole);
 }
 
+static int igt_ggtt_misaligned_pin(void *arg)
+{
+	return exercise_ggtt(arg, misaligned_pin);
+}
+
 static int igt_ggtt_page(void *arg)
 {
 	const unsigned int count = PAGE_SIZE/sizeof(u32);
@@ -2151,12 +2305,14 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_fill),
 		SUBTEST(igt_ppgtt_shrink),
 		SUBTEST(igt_ppgtt_shrink_boom),
+		SUBTEST(igt_ppgtt_misaligned_pin),
 		SUBTEST(igt_ggtt_lowlevel),
 		SUBTEST(igt_ggtt_drunk),
 		SUBTEST(igt_ggtt_walk),
 		SUBTEST(igt_ggtt_pot),
 		SUBTEST(igt_ggtt_fill),
 		SUBTEST(igt_ggtt_page),
+		SUBTEST(igt_ggtt_misaligned_pin),
 		SUBTEST(igt_cs_tlb),
 	};
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 7acba1d2135e..ba32893e0873 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -17,6 +17,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
+#include "gem/i915_gem_ttm.h"
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_engine_pm.h"
@@ -170,7 +171,7 @@ static int igt_mock_reserve(void *arg)
 	if (!order)
 		return 0;
 
-	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0, 0);
 	if (IS_ERR(mem)) {
 		pr_err("failed to create memory region\n");
 		err = PTR_ERR(mem);
@@ -383,7 +384,7 @@ static int igt_mock_splintered_region(void *arg)
 	 */
 
 	size = (SZ_4G - 1) & PAGE_MASK;
-	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
+	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0);
 	if (IS_ERR(mem))
 		return PTR_ERR(mem);
 
@@ -471,7 +472,7 @@ static int igt_mock_max_segment(void *arg)
 	 */
 
 	size = SZ_8G;
-	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
+	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0);
 	if (IS_ERR(mem))
 		return PTR_ERR(mem);
 
@@ -512,6 +513,147 @@ out_put:
 	return err;
 }
 
+static u64 igt_object_mappable_total(struct drm_i915_gem_object *obj)
+{
+	struct intel_memory_region *mr = obj->mm.region;
+	struct i915_ttm_buddy_resource *bman_res =
+		to_ttm_buddy_resource(obj->mm.res);
+	struct drm_buddy *mm = bman_res->mm;
+	struct drm_buddy_block *block;
+	u64 total;
+
+	total = 0;
+	list_for_each_entry(block, &bman_res->blocks, link) {
+		u64 start = drm_buddy_block_offset(block);
+		u64 end = start + drm_buddy_block_size(mm, block);
+
+		if (start < mr->io_size)
+			total += min_t(u64, end, mr->io_size) - start;
+	}
+
+	return total;
+}
+
+static int igt_mock_io_size(void *arg)
+{
+	struct intel_memory_region *mr = arg;
+	struct drm_i915_private *i915 = mr->i915;
+	struct drm_i915_gem_object *obj;
+	u64 mappable_theft_total;
+	u64 io_size;
+	u64 total;
+	u64 ps;
+	u64 rem;
+	u64 size;
+	I915_RND_STATE(prng);
+	LIST_HEAD(objects);
+	int err = 0;
+
+	ps = SZ_4K;
+	if (i915_prandom_u64_state(&prng) & 1)
+		ps = SZ_64K; /* For something like DG2 */
+
+	div64_u64_rem(i915_prandom_u64_state(&prng), SZ_8G, &total);
+	total = round_down(total, ps);
+	total = max_t(u64, total, SZ_1G);
+
+	div64_u64_rem(i915_prandom_u64_state(&prng), total - ps, &io_size);
+	io_size = round_down(io_size, ps);
+	io_size = max_t(u64, io_size, SZ_256M); /* 256M seems to be the common lower limit */
+
+	pr_info("%s with ps=%llx, io_size=%llx, total=%llx\n",
+		__func__, ps, io_size, total);
+
+	mr = mock_region_create(i915, 0, total, ps, 0, io_size);
+	if (IS_ERR(mr)) {
+		err = PTR_ERR(mr);
+		goto out_err;
+	}
+
+	mappable_theft_total = 0;
+	rem = total - io_size;
+	do {
+		div64_u64_rem(i915_prandom_u64_state(&prng), rem, &size);
+		size = round_down(size, ps);
+		size = max(size, ps);
+
+		obj = igt_object_create(mr, &objects, size,
+					I915_BO_ALLOC_GPU_ONLY);
+		if (IS_ERR(obj)) {
+			pr_err("%s TOPDOWN failed with rem=%llx, size=%llx\n",
+			       __func__, rem, size);
+			err = PTR_ERR(obj);
+			goto out_close;
+		}
+
+		mappable_theft_total += igt_object_mappable_total(obj);
+		rem -= size;
+	} while (rem);
+
+	pr_info("%s mappable theft=(%lluMiB/%lluMiB), total=%lluMiB\n",
+		__func__,
+		(u64)mappable_theft_total >> 20,
+		(u64)io_size >> 20,
+		(u64)total >> 20);
+
+	/*
+	 * Even if we allocate all of the non-mappable portion, we should still
+	 * be able to dip into the mappable portion.
+	 */
+	obj = igt_object_create(mr, &objects, io_size,
+				I915_BO_ALLOC_GPU_ONLY);
+	if (IS_ERR(obj)) {
+		pr_err("%s allocation unexpectedly failed\n", __func__);
+		err = PTR_ERR(obj);
+		goto out_close;
+	}
+
+	close_objects(mr, &objects);
+
+	rem = io_size;
+	do {
+		div64_u64_rem(i915_prandom_u64_state(&prng), rem, &size);
+		size = round_down(size, ps);
+		size = max(size, ps);
+
+		obj = igt_object_create(mr, &objects, size, 0);
+		if (IS_ERR(obj)) {
+			pr_err("%s MAPPABLE failed with rem=%llx, size=%llx\n",
+			       __func__, rem, size);
+			err = PTR_ERR(obj);
+			goto out_close;
+		}
+
+		if (igt_object_mappable_total(obj) != size) {
+			pr_err("%s allocation is not mappable(size=%llx)\n",
+			       __func__, size);
+			err = -EINVAL;
+			goto out_close;
+		}
+		rem -= size;
+	} while (rem);
+
+	/*
+	 * We assume CPU access is required by default, which should result in a
+	 * failure here, even though the non-mappable portion is free.
+	 */
+	obj = igt_object_create(mr, &objects, ps, 0);
+	if (!IS_ERR(obj)) {
+		pr_err("%s allocation unexpectedly succeeded\n", __func__);
+		err = -EINVAL;
+		goto out_close;
+	}
+
+out_close:
+	close_objects(mr, &objects);
+	intel_memory_region_destroy(mr);
+out_err:
+	if (err == -ENOMEM)
+		err = 0;
+
+	return err;
+}
+
 static int igt_gpu_write_dw(struct intel_context *ce,
 			    struct i915_vma *vma,
 			    u32 dword,
@@ -680,8 +822,14 @@ static int igt_lmem_create_with_ps(void *arg)
 
 		i915_gem_object_lock(obj, NULL);
 		err = i915_gem_object_pin_pages(obj);
-		if (err)
+		if (err) {
+			if (err == -ENXIO || err == -E2BIG || err == -ENOMEM) {
+				pr_info("%s not enough lmem for ps(%u) err=%d\n",
+					__func__, ps, err);
+				err = 0;
+			}
 			goto out_put;
+		}
 
 		daddr = i915_gem_object_get_dma_address(obj, 0);
 		if (!IS_ALIGNED(daddr, ps)) {
@@ -1179,6 +1327,7 @@ int intel_memory_region_mock_selftests(void)
 		SUBTEST(igt_mock_contiguous),
 		SUBTEST(igt_mock_splintered_region),
 		SUBTEST(igt_mock_max_segment),
+		SUBTEST(igt_mock_io_size),
 	};
 	struct intel_memory_region *mem;
 	struct drm_i915_private *i915;
@@ -1188,7 +1337,7 @@ int intel_memory_region_mock_selftests(void)
 	if (!i915)
 		return -ENOMEM;
 
-	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0, 0);
 	if (IS_ERR(mem)) {
 		pr_err("failed to create memory region\n");
 		err = PTR_ERR(mem);
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 19bff8afcaaa..f64325491f35 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -22,17 +22,12 @@ static void mock_region_put_pages(struct drm_i915_gem_object *obj,
 
 static int mock_region_get_pages(struct drm_i915_gem_object *obj)
 {
-	unsigned int flags;
 	struct sg_table *pages;
 	int err;
 
-	flags = 0;
-	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
-		flags |= TTM_PL_FLAG_CONTIGUOUS;
-
 	obj->mm.res = intel_region_ttm_resource_alloc(obj->mm.region,
 						      obj->base.size,
-						      flags);
+						      obj->flags);
 	if (IS_ERR(obj->mm.res))
 		return PTR_ERR(obj->mm.res);
 
@@ -107,7 +102,8 @@ mock_region_create(struct drm_i915_private *i915,
 		   resource_size_t start,
 		   resource_size_t size,
 		   resource_size_t min_page_size,
-		   resource_size_t io_start)
+		   resource_size_t io_start,
+		   resource_size_t io_size)
 {
 	int instance = ida_alloc_max(&i915->selftest.mock_region_instances,
 				     TTM_NUM_MEM_TYPES - TTM_PL_PRIV - 1,
@@ -117,6 +113,7 @@ mock_region_create(struct drm_i915_private *i915,
 		return ERR_PTR(instance);
 
 	return intel_memory_region_create(i915, start, size, min_page_size,
-					  io_start, INTEL_MEMORY_MOCK, instance,
+					  io_start, io_size,
+					  INTEL_MEMORY_MOCK, instance,
 					  &mock_region_ops);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.h b/drivers/gpu/drm/i915/selftests/mock_region.h
index 329bf74dfaca..e36c3a433551 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.h
+++ b/drivers/gpu/drm/i915/selftests/mock_region.h
@@ -16,6 +16,7 @@ mock_region_create(struct drm_i915_private *i915,
 		   resource_size_t start,
 		   resource_size_t size,
 		   resource_size_t min_page_size,
-		   resource_size_t io_start);
+		   resource_size_t io_start,
+		   resource_size_t io_size);
 
 #endif /* !__MOCK_REGION_H */