Commit ed4596ea authored by Akash Goel's avatar Akash Goel Committed by Chris Wilson

drm/i915/guc: WA to address the Ringbuffer coherency issue

Driver accesses the ringbuffer pages, via GMADR BAR, if the pages are
pinned in mappable aperture portion of GGTT and for ringbuffer pages
allocated from Stolen memory, access can only be done through GMADR BAR.
In case of GuC based submission, updates done in ringbuffer via GMADR
may not get committed to memory by the time the Command streamer starts
reading them, resulting in fetching of stale data.

For Host based submission, such problem is not there as the write to Ring
Tail or ELSP register happens from the Host side prior to submission.
Access to any GFX register from CPU side goes to GTTMMADR BAR and Hw already
enforces the ordering between outstanding GMADR writes & new GTTMADR access.
MMIO writes from GuC side do not go to GTTMMADR BAR as GuC communication to
registers within GT is contained within GT, so ordering is not enforced
resulting in a race, which can manifest in form of a hang.

To ensure the flush of in-flight GMADR writes, a POSTING READ is done to
GuC register prior to doorbell ring.
There is already a similar WA in i915_gem_object_flush_gtt_write_domain(),
which takes care of GMADR writes from User space to GEM buffers, but not the
ringbuffer writes from KMD.
This WA is needed on all recent HW.

v2:
- Use POSTING_READ_FW instead of POSTING_READ as GuC register do not lie
  in any forcewake domain range and so the overhead of spinlock & search
  in the forcewake table is avoidable. (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: default avatarSagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: default avatarAkash Goel <akash.goel@intel.com>
Reviewed-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1477413323-1880-1-git-send-email-akash.goel@intel.com
parent de867c20
...@@ -634,6 +634,7 @@ static int guc_ring_doorbell(struct i915_guc_client *gc) ...@@ -634,6 +634,7 @@ static int guc_ring_doorbell(struct i915_guc_client *gc)
*/ */
static void i915_guc_submit(struct drm_i915_gem_request *rq) static void i915_guc_submit(struct drm_i915_gem_request *rq)
{ {
struct drm_i915_private *dev_priv = rq->i915;
unsigned int engine_id = rq->engine->id; unsigned int engine_id = rq->engine->id;
struct intel_guc *guc = &rq->i915->guc; struct intel_guc *guc = &rq->i915->guc;
struct i915_guc_client *client = guc->execbuf_client; struct i915_guc_client *client = guc->execbuf_client;
...@@ -641,6 +642,11 @@ static void i915_guc_submit(struct drm_i915_gem_request *rq) ...@@ -641,6 +642,11 @@ static void i915_guc_submit(struct drm_i915_gem_request *rq)
spin_lock(&client->wq_lock); spin_lock(&client->wq_lock);
guc_wq_item_append(client, rq); guc_wq_item_append(client, rq);
/* WA to flush out the pending GMADR writes to ring buffer. */
if (i915_vma_is_map_and_fenceable(rq->ring->vma))
POSTING_READ_FW(GUC_STATUS);
b_ret = guc_ring_doorbell(client); b_ret = guc_ring_doorbell(client);
client->submissions[engine_id] += 1; client->submissions[engine_id] += 1;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment