If the request->wa_tail is 0 (because it landed exactly on the end of
the ringbuffer), when we reconstruct request->tail following a reset we
fill in an illegal value (-8 or 0x001ffff8). As a result, RING_HEAD is
never able to catch up with RING_TAIL and the GPU spins endlessly. If
the ring contains a couple of breadcrumbs, even our hangcheck is unable
to catch the busy-looping as the ACTHD and seqno continually advance.
v2: Move the wrap into a common intel_ring_wrap().
Fixes: a3aabe86a340 ("drm/i915/execlists: Reinitialise context image after GPU hang")
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v4.10+
Link: http://patchwork.freedesktop.org/patch/msgid/20170327130009.4678-1-chris@xxxxxxxxxxxxxxxxxx
Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxx>
(cherry picked from commit 450362d3fe866b14304f309b5fffba0c33fbfbc3)
---
drivers/gpu/drm/i915/intel_lrc.c | 4 +++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 8 +++++++-
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 471af3b480ad..91555d4e9129 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1440,7 +1440,9 @@ static void reset_common_ring(struct intel_engine_cs *engine,
GEM_BUG_ON(request->ctx != port[0].request->ctx);
/* Reset WaIdleLiteRestore:bdw,skl as well */
- request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
+ request->tail =
+ intel_ring_wrap(request->ring,
+ request->wa_tail - WA_TAIL_DWORDS*sizeof(u32));
}
static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 13dccb18cd43..8cb2078c5bfc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -521,11 +521,17 @@ static inline void intel_ring_advance(struct intel_ring *ring)
*/
}
+static inline u32
+intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+ return pos & (ring->size - 1);
+}
+
static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr)
{
/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
u32 offset = addr - ring->vaddr;
- return offset & (ring->size - 1);
+ return intel_ring_wrap(ring, offset);
}
int __intel_ring_space(int head, int tail, int size);
--
2.11.0