diff mbox

[v7] drm/i915: Avoid writing relocs with addresses in non-canonical form

Message ID 1451404141-30354-1-git-send-email-michal.winiarski@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Michał Winiarski Dec. 29, 2015, 3:49 p.m. UTC 
According to PRM, some parts of HW require the addresses to be in
a canonical form, where bits [63:48] == [47]. Let's convert addresses to
canonical form prior to relocating and return converted offsets to
userspace. We also need to make sure that userspace is using addresses
in canonical form in case of softpin.

v2: Whitespace fixup, gen8_canonical_addr description (Chris, Ville)
v3: Rebase on top of softpin, fix a hole in relocate_entry,
    s/expect/require (Chris)
v4: Handle softpin in validate_exec_list (Chris)
v5: Convert back to canonical form at copy_to_user time (Chris)
v6: Don't use struct exec_object2 in place of exec_object
v7: Use sign_extend64 for converting to canonical form (Joonas),
    reject non-canonical and non-page-aligned offset for softpin (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Micha? Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 45 +++++++++++++++++++++++++++---
 1 file changed, 41 insertions(+), 4 deletions(-)

Comments

Chris Wilson Dec. 29, 2015, 4:25 p.m. UTC | #1 
On Tue, Dec 29, 2015 at 04:49:01PM +0100, Micha? Winiarski wrote:
> @@ -994,6 +1013,20 @@ validate_exec_list(struct drm_device *dev,
>  		if (exec[i].flags & invalid_flags)
>  			return -EINVAL;
>  
> +		/* Offset can be used as input (EXEC_OBJECT_PINNED), reject
> +		 * any non-page-aligned or non-canonial addresses.
> +		 */
> +		if (exec[i].flags & EXEC_OBJECT_PINNED &&
> +		    (exec[i].offset != gen8_canonical_addr(exec[i].offset) ||
> +		     offset_in_page(exec[i].offset)))
> +			return -EINVAL;
> +

if (exec[i].flags & EXEC_OBJECT_PINNED) {
	if (exec[i].offset != gen8_canonical_addr(exec[i].offset & PAGE_MASK))
		return -EINVAL;

	/* From drm_mm perspective address space is continuous,
	 * so from this point we're always using non-canonical form
	 * internally.
	 */
	exec[i].offset &= (1ULL << 48) - 1;
}

Splitting up the two tests just makes it a bit easier to read (imo, and
I've been told on numerous occasions to do the same :) Whilst not as
obvious atm, it also helps when we have multiple extension checks in the
validate(). As a secondary point, we can then also demonstate that we
can fully restrict manipulating exec[i].offset to the pinned path.

#define GEN8_HIGH_ADDRESS_BIT 47
#define GEN8_ADDRESS_MASK (1ULL << (GEN8_HIGH_ADDRESS_BIT+1)) - 1

GEN8_CANONICAL_HIGH_BIT ?

since we have two places now that know about the address format, or
perhaps

static u64 gen8_undo_canonical_addr(u64);
exec[i].offset = gen8_undo_canonical_addr(exec[i].offset);

so that we can put them next to each other. That seems a better idea.
-Chris
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 5d01ea6..dd081fd 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -249,6 +249,25 @@  static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 		obj->cache_level != I915_CACHE_NONE);
 }
 
+/* Used to convert any address to canonical form.
+ * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
+ * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
+ * addresses to be in a canonical form:
+ * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
+ * canonical form [63:48] == [47]."
+ */
+static inline uint64_t gen8_canonical_addr(uint64_t address)
+{
+	return sign_extend64(address, 47);
+}
+
+static inline uint64_t
+relocation_target(struct drm_i915_gem_relocation_entry *reloc,
+		  uint64_t target_offset)
+{
+	return gen8_canonical_addr((int)reloc->delta + target_offset);
+}
+
 static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
 		   struct drm_i915_gem_relocation_entry *reloc,
@@ -256,7 +275,7 @@  relocate_entry_cpu(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
-	uint64_t delta = reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	char *vaddr;
 	int ret;
 
@@ -292,7 +311,7 @@  relocate_entry_gtt(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint64_t delta = reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	uint64_t offset;
 	void __iomem *reloc_page;
 	int ret;
@@ -347,7 +366,7 @@  relocate_entry_clflush(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
-	uint64_t delta = (int)reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	char *vaddr;
 	int ret;
 
@@ -395,7 +414,7 @@  i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	target_i915_obj = target_vma->obj;
 	target_obj = &target_vma->obj->base;
 
-	target_offset = target_vma->node.start;
+	target_offset = gen8_canonical_addr(target_vma->node.start);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -994,6 +1013,20 @@  validate_exec_list(struct drm_device *dev,
 		if (exec[i].flags & invalid_flags)
 			return -EINVAL;
 
+		/* Offset can be used as input (EXEC_OBJECT_PINNED), reject
+		 * any non-page-aligned or non-canonial addresses.
+		 */
+		if (exec[i].flags & EXEC_OBJECT_PINNED &&
+		    (exec[i].offset != gen8_canonical_addr(exec[i].offset) ||
+		     offset_in_page(exec[i].offset)))
+			return -EINVAL;
+
+		/* From drm_mm perspective address space is continuous,
+		 * so from this point we're always using non-canonical form
+		 * internally.
+		 */
+		exec[i].offset &= (1ULL << 48) - 1;
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
@@ -1687,6 +1720,8 @@  i915_gem_execbuffer(struct drm_device *dev, void *data,
 
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++) {
+			exec2_list[i].offset =
+				gen8_canonical_addr(exec2_list[i].offset);
 			ret = __copy_to_user(&user_exec_list[i].offset,
 					     &exec2_list[i].offset,
 					     sizeof(user_exec_list[i].offset));
@@ -1752,6 +1787,8 @@  i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		int i;
 
 		for (i = 0; i < args->buffer_count; i++) {
+			exec2_list[i].offset =
+				gen8_canonical_addr(exec2_list[i].offset);
 			ret = __copy_to_user(&user_exec_list[i].offset,
 					     &exec2_list[i].offset,
 					     sizeof(user_exec_list[i].offset));