This is a note to let you know that I've just added the patch titled
drm/msm/a5xx: workaround early ring-buffer emptiness check
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-msm-a5xx-workaround-early-ring-buffer-emptiness-.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 7ee9a75dedc777dc7c70a1956af410bacb743dd0
Author: Vladimir Lypak <vladimir.lypak@xxxxxxxxx>
Date: Sun Sep 1 13:54:03 2024 +0000
drm/msm/a5xx: workaround early ring-buffer emptiness check
[ Upstream commit a30f9f65b5ac82d4390548c32ed9c7f05de7ddf5 ]
There is another cause for soft lock-up of GPU in empty ring-buffer:
race between GPU executing last commands and CPU checking ring for
emptiness. On GPU side IRQ for retire is triggered by CACHE_FLUSH_TS
event and RPTR shadow (which is used to check ring emptiness) is updated
a bit later from CP_CONTEXT_SWITCH_YIELD. Thus if GPU is executing its
last commands slow enough or we check that ring too fast we will miss a
chance to trigger switch to lower priority ring because current ring isn't
empty just yet. This can escalate to lock-up situation described in
previous patch.
To work-around this issue we keep track of last submit sequence number
for each ring and compare it with one written to memptrs from GPU during
execution of CACHE_FLUSH_TS event.
Fixes: b1fc2839d2f9 ("drm/msm: Implement preemption for A5XX targets")
Signed-off-by: Vladimir Lypak <vladimir.lypak@xxxxxxxxx>
Patchwork: https://patchwork.freedesktop.org/patch/612047/
Signed-off-by: Rob Clark <robdclark@xxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index aa2b2958237f4..e0cf42323cf91 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -56,6 +56,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
+ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+ struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
struct msm_ringbuffer *ring = submit->ring;
struct msm_gem_object *obj;
uint32_t *ptr, dwords;
@@ -100,6 +102,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
}
}
+ a5xx_gpu->last_seqno[ring->id] = submit->seqno;
a5xx_flush(gpu, ring, true);
a5xx_preempt_trigger(gpu);
@@ -191,6 +194,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
/* Write the fence to the scratch register */
OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1);
OUT_RING(ring, submit->seqno);
+ a5xx_gpu->last_seqno[ring->id] = submit->seqno;
/*
* Execute a CACHE_FLUSH_TS event. This will ensure that the
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
index b4d06ca3e499d..9c0d701fe4b85 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
@@ -34,6 +34,7 @@ struct a5xx_gpu {
struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
+ uint32_t last_seqno[MSM_GPU_MAX_RINGS];
atomic_t preempt_state;
spinlock_t preempt_start_lock;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index 096da495e721c..8976c30df1a2e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -55,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
/* Return the highest priority ringbuffer with something in it */
static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
{
+ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+ struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
unsigned long flags;
int i;
@@ -64,6 +66,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
spin_lock_irqsave(&ring->preempt_lock, flags);
empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring));
+ if (!empty && ring == a5xx_gpu->cur_ring)
+ empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i];
spin_unlock_irqrestore(&ring->preempt_lock, flags);
if (!empty)
