Re: [Intel-gfx] [PATCH v5 2/5] drm/i915: enforce min GTT alignment for discrete cards
On 26/01/2022 15:45, Thomas Hellström (Intel) wrote: On 1/25/22 20:35, Robert Beckett wrote: From: Matthew Auld For local-memory objects we need to align the GTT addresses to 64K, both for the ppgtt and ggtt. We need to support vm->min_alignment > 4K, depending on the vm itself and the type of object we are inserting. With this in mind update the GTT selftests to take this into account. For compact-pt we further align and pad lmem object GTT addresses to 2MB to ensure PDEs contain consistent page sizes as required by the HW. v3: * use needs_compact_pt flag to discriminate between 64K and 64K with compact-pt * add i915_vm_obj_min_alignment * use i915_vm_obj_min_alignment to round up vma reservation if compact-pt instead of hard coding v5: * fix i915_vm_obj_min_alignment for internal objects which have no memory region Signed-off-by: Matthew Auld Signed-off-by: Ramalingam C Signed-off-by: Robert Beckett Cc: Joonas Lahtinen Cc: Rodrigo Vivi --- .../i915/gem/selftests/i915_gem_client_blt.c | 23 +++-- drivers/gpu/drm/i915/gt/intel_gtt.c | 12 +++ drivers/gpu/drm/i915/gt/intel_gtt.h | 18 drivers/gpu/drm/i915/i915_vma.c | 9 ++ drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 96 --- 5 files changed, 117 insertions(+), 41 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index c8ff8bf0986d..f0bfce53258f 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -39,6 +39,7 @@ struct tiled_blits { struct blit_buffer scratch; struct i915_vma *batch; u64 hole; + u64 align; u32 width; u32 height; }; @@ -410,14 +411,21 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_free; } - hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4); + t->align = I915_GTT_PAGE_SIZE_2M; /* XXX worst case, derive from vm! */ + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_LOCAL)); + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_SYSTEM)); Don't we always end up with 2M here, regardless of the vm restrictions? agreed. I will drop the 2M worst case.
Re: [Intel-gfx] [PATCH v5 2/5] drm/i915: enforce min GTT alignment for discrete cards
On 1/25/22 20:35, Robert Beckett wrote: From: Matthew Auld For local-memory objects we need to align the GTT addresses to 64K, both for the ppgtt and ggtt. We need to support vm->min_alignment > 4K, depending on the vm itself and the type of object we are inserting. With this in mind update the GTT selftests to take this into account. For compact-pt we further align and pad lmem object GTT addresses to 2MB to ensure PDEs contain consistent page sizes as required by the HW. v3: * use needs_compact_pt flag to discriminate between 64K and 64K with compact-pt * add i915_vm_obj_min_alignment * use i915_vm_obj_min_alignment to round up vma reservation if compact-pt instead of hard coding v5: * fix i915_vm_obj_min_alignment for internal objects which have no memory region Signed-off-by: Matthew Auld Signed-off-by: Ramalingam C Signed-off-by: Robert Beckett Cc: Joonas Lahtinen Cc: Rodrigo Vivi --- .../i915/gem/selftests/i915_gem_client_blt.c | 23 +++-- drivers/gpu/drm/i915/gt/intel_gtt.c | 12 +++ drivers/gpu/drm/i915/gt/intel_gtt.h | 18 drivers/gpu/drm/i915/i915_vma.c | 9 ++ drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 96 --- 5 files changed, 117 insertions(+), 41 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index c8ff8bf0986d..f0bfce53258f 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -39,6 +39,7 @@ struct tiled_blits { struct blit_buffer scratch; struct i915_vma *batch; u64 hole; + u64 align; u32 width; u32 height; }; @@ -410,14 +411,21 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_free; } - hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4); + t->align = I915_GTT_PAGE_SIZE_2M; /* XXX worst case, derive from vm! */ + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_LOCAL)); + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_SYSTEM)); Don't we always end up with 2M here, regardless of the vm restrictions?
[Intel-gfx] [PATCH v5 2/5] drm/i915: enforce min GTT alignment for discrete cards
From: Matthew Auld For local-memory objects we need to align the GTT addresses to 64K, both for the ppgtt and ggtt. We need to support vm->min_alignment > 4K, depending on the vm itself and the type of object we are inserting. With this in mind update the GTT selftests to take this into account. For compact-pt we further align and pad lmem object GTT addresses to 2MB to ensure PDEs contain consistent page sizes as required by the HW. v3: * use needs_compact_pt flag to discriminate between 64K and 64K with compact-pt * add i915_vm_obj_min_alignment * use i915_vm_obj_min_alignment to round up vma reservation if compact-pt instead of hard coding v5: * fix i915_vm_obj_min_alignment for internal objects which have no memory region Signed-off-by: Matthew Auld Signed-off-by: Ramalingam C Signed-off-by: Robert Beckett Cc: Joonas Lahtinen Cc: Rodrigo Vivi --- .../i915/gem/selftests/i915_gem_client_blt.c | 23 +++-- drivers/gpu/drm/i915/gt/intel_gtt.c | 12 +++ drivers/gpu/drm/i915/gt/intel_gtt.h | 18 drivers/gpu/drm/i915/i915_vma.c | 9 ++ drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 96 --- 5 files changed, 117 insertions(+), 41 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index c8ff8bf0986d..f0bfce53258f 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -39,6 +39,7 @@ struct tiled_blits { struct blit_buffer scratch; struct i915_vma *batch; u64 hole; + u64 align; u32 width; u32 height; }; @@ -410,14 +411,21 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_free; } - hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4); + t->align = I915_GTT_PAGE_SIZE_2M; /* XXX worst case, derive from vm! */ + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_LOCAL)); + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_SYSTEM)); + + hole_size = 2 * round_up(WIDTH * HEIGHT * 4, t->align); hole_size *= 2; /* room to maneuver */ - hole_size += 2 * I915_GTT_MIN_ALIGNMENT; + hole_size += 2 * t->align; /* padding on either side */ mutex_lock(>ce->vm->mutex); memset(, 0, sizeof(hole)); err = drm_mm_insert_node_in_range(>ce->vm->mm, , - hole_size, 0, I915_COLOR_UNEVICTABLE, + hole_size, t->align, + I915_COLOR_UNEVICTABLE, 0, U64_MAX, DRM_MM_INSERT_BEST); if (!err) @@ -428,7 +436,7 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_put; } - t->hole = hole.start + I915_GTT_MIN_ALIGNMENT; + t->hole = hole.start + t->align; pr_info("Using hole at %llx\n", t->hole); err = tiled_blits_create_buffers(t, WIDTH, HEIGHT, prng); @@ -455,7 +463,7 @@ static void tiled_blits_destroy(struct tiled_blits *t) static int tiled_blits_prepare(struct tiled_blits *t, struct rnd_state *prng) { - u64 offset = PAGE_ALIGN(t->width * t->height * 4); + u64 offset = round_up(t->width * t->height * 4, t->align); u32 *map; int err; int i; @@ -486,8 +494,7 @@ static int tiled_blits_prepare(struct tiled_blits *t, static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng) { - u64 offset = - round_up(t->width * t->height * 4, 2 * I915_GTT_MIN_ALIGNMENT); + u64 offset = round_up(t->width * t->height * 4, 2 * t->align); int err; /* We want to check position invariant tiling across GTT eviction */ @@ -500,7 +507,7 @@ static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng) /* Reposition so that we overlap the old addresses, and slightly off */ err = tiled_blit(t, ->buffers[2], t->hole + I915_GTT_MIN_ALIGNMENT, +>buffers[2], t->hole + t->align, >buffers[1], t->hole + 3 * offset / 2); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 46be4197b93f..df23ebdfc994 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -223,6 +223,18 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) GEM_BUG_ON(!vm->total); drm_mm_init(>mm, 0, vm->total); + + memset64(vm->min_alignment,