drm/i915: Add soft-pinning API for execbuffer

Userspace can pass in an offset that it presumes the object is located
at. The kernel will then do its utmost to fit the object into that
location. The assumption is that userspace is handling its own object
locations (for example along with full-ppgtt) and that the kernel will
rarely have to make space for the user's requests.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

v2: Fixed incorrect eviction found by Michal Winiarski - fix suggested by Chris
Wilson.  Fixed incorrect error paths causing crash found by Michal Winiarski.
(Not published externally)

v3: Rebased because of trivial conflict in object_bind_to_vm.  Fixed eviction
to allow eviction of soft-pinned objects when another soft-pinned object used
by a subsequent execbuffer overlaps reported by Michal Winiarski.
(Not published externally)

v4: Moved soft-pinned objects to the front of ordered_vmas so that they are
pinned first after an address conflict happens to avoid repeated conflicts in
rare cases (Suggested by Chris Wilson).  Expanded comment on
drm_i915_gem_exec_object2.offset to cover this new API.

v5: Added I915_PARAM_HAS_EXEC_SOFTPIN parameter for detecting this capability
(Kristian). Added check for multiple pinnings on eviction (Akash). Made sure
buffers are not considered misplaced without the user specifying
EXEC_OBJECT_SUPPORTS_48B_ADDRESS.  User must assume responsibility for any
addressing workarounds.  Updated object2.offset field comment again to clarify
NO_RELOC case (Chris).  checkpatch cleanup.

v6: Trivial rebase on latest drm-intel-nightly

v7: Catch attempts to pin above the max virtual address size and return
EINVAL (Tvrtko). Decouple EXEC_OBJECT_SUPPORTS_48B_ADDRESS and
EXEC_OBJECT_PINNED flags, user must pass both flags in any attempt to pin
something at an offset above 4GB (Chris, Daniel Vetter).

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Zou Nanhai <nanhai.zou@intel.com>
Cc: Kristian Høgsberg <hoegsberg@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Acked-by: PDT
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449575707-20933-1-git-send-email-thomas.daniel@intel.com

1 files changed, 14 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a4c243cec4aa..48ec4846e6f2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -599,6 +599,8 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 			flags |= PIN_GLOBAL | PIN_MAPPABLE;
 		if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
 			flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
+		if (entry->flags & EXEC_OBJECT_PINNED)
+			flags |= entry->offset | PIN_OFFSET_FIXED;
 		if ((flags & PIN_MAPPABLE) == 0)
 			flags |= PIN_HIGH;
 	}
@@ -670,6 +672,10 @@ eb_vma_misplaced(struct i915_vma *vma)
 	    vma->node.start & (entry->alignment - 1))
 		return true;
 
+	if (entry->flags & EXEC_OBJECT_PINNED &&
+	    vma->node.start != entry->offset)
+		return true;
+
 	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS &&
 	    vma->node.start < BATCH_OFFSET_BIAS)
 		return true;
@@ -695,6 +701,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 	struct i915_vma *vma;
 	struct i915_address_space *vm;
 	struct list_head ordered_vmas;
+	struct list_head pinned_vmas;
 	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
 	int retry;
 
@@ -703,6 +710,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 	vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
 
 	INIT_LIST_HEAD(&ordered_vmas);
+	INIT_LIST_HEAD(&pinned_vmas);
 	while (!list_empty(vmas)) {
 		struct drm_i915_gem_exec_object2 *entry;
 		bool need_fence, need_mappable;
@@ -721,7 +729,9 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 			obj->tiling_mode != I915_TILING_NONE;
 		need_mappable = need_fence || need_reloc_mappable(vma);
 
-		if (need_mappable) {
+		if (entry->flags & EXEC_OBJECT_PINNED)
+			list_move_tail(&vma->exec_list, &pinned_vmas);
+		else if (need_mappable) {
 			entry->flags |= __EXEC_OBJECT_NEEDS_MAP;
 			list_move(&vma->exec_list, &ordered_vmas);
 		} else
@@ -731,6 +741,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 		obj->base.pending_write_domain = 0;
 	}
 	list_splice(&ordered_vmas, vmas);
+	list_splice(&pinned_vmas, vmas);
 
 	/* Attempt to pin all of the buffers into the GTT.
 	 * This is done in 3 phases:
@@ -1317,7 +1328,8 @@ eb_get_batch(struct eb_vmas *eb)
 	 * Note that actual hangs have only been observed on gen7, but for
 	 * paranoia do it everywhere.
 	 */
-	vma->exec_entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;
+	if ((vma->exec_entry->flags & EXEC_OBJECT_PINNED) == 0)
+		vma->exec_entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;
 
 	return vma->obj;
 }