drm/i915: Fix write-read race with multiple rings

Daniel noticed a problem where is we wrote to an object with ring A in
the middle of a very long running batch, then executed a quick batch on
ring B before a batch that reads from the same object, its obj->ring would
now point to ring B, but its last_write_seqno would be still relative to
ring A. This would allow for the user to read from the object before the
GPU had completed the write, as set_domain would only check that ring B
had passed the last_write_seqno.

To fix this simply (and inelegantly), we bump the last_write_seqno when
switching rings so that the last_write_seqno is always relative to the
current obj->ring.

This fixes igt/tests/gem_write_read_ring_switch.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
[danvet: Add note about the newly created igt which exercises this
bug.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 4 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7f368d79f7d2..8fd8e82ebda4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1880,6 +1880,10 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
         u32 seqno = intel_ring_get_seqno(ring);
 
         BUG_ON(ring == NULL);
+        if (obj->ring != ring && obj->last_write_seqno) {
+                /* Keep the seqno relative to the current ring */
+                obj->last_write_seqno = seqno;
+        }
         obj->ring = ring;
 
         /* Add a reference if we're newly entering the active list. */