* FAILED: patch "[PATCH] drm/amdgpu/mes: fix mes ring buffer overflow" failed to apply to 6.10-stable tree
@ 2024-08-19 10:21 gregkh
0 siblings, 0 replies; only message in thread
From: gregkh @ 2024-08-19 10:21 UTC (permalink / raw)
To: Jack.Xiao, alexander.deucher; +Cc: stable
The patch below does not apply to the 6.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.10.y
git checkout FETCH_HEAD
git cherry-pick -x 11752c013f562a1124088a35bd314aa0e9f0e88f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2024081941-flavorful-extrovert-01b9@gregkh' --subject-prefix 'PATCH 6.10.y' HEAD^..
Possible dependencies:
11752c013f56 ("drm/amdgpu/mes: fix mes ring buffer overflow")
fffe347e1478 ("drm/amdgpu: cleanup MES12 command submission")
de3246254156 ("drm/amdgpu: cleanup MES11 command submission")
ade887c63394 ("drm/amdgpu/mes12: Use a separate fence per transaction")
94b51a3d01ed ("drm/amdgpu/mes12: increase mes submission timeout")
b1d852920b31 ("drm/amdgpu/mes12: print MES opcodes rather than numbers")
785f0f9fe742 ("drm/amdgpu: Add mes v12_0 ip block support (v4)")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 11752c013f562a1124088a35bd314aa0e9f0e88f Mon Sep 17 00:00:00 2001
From: Jack Xiao <Jack.Xiao@amd.com>
Date: Thu, 18 Jul 2024 16:38:50 +0800
Subject: [PATCH] drm/amdgpu/mes: fix mes ring buffer overflow
wait memory room until enough before writing mes packets
to avoid ring buffer overflow.
v2: squash in sched_hw_submission fix
Fixes: de3246254156 ("drm/amdgpu: cleanup MES11 command submission")
Fixes: fffe347e1478 ("drm/amdgpu: cleanup MES12 command submission")
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 34e087e8920e635c62e2ed6a758b0cd27f836d13)
Cc: stable@vger.kernel.org
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index ad49cecb20b8..e6344a6b0a9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -212,6 +212,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
*/
if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
sched_hw_submission = max(sched_hw_submission, 256);
+ if (ring->funcs->type == AMDGPU_RING_TYPE_MES)
+ sched_hw_submission = 8;
else if (ring == &adev->sdma.instance[0].page)
sched_hw_submission = 256;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index f9343642ae7e..1a5ad5be33bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -168,7 +168,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
const char *op_str, *misc_op_str;
unsigned long flags;
u64 status_gpu_addr;
- u32 status_offset;
+ u32 seq, status_offset;
u64 *status_ptr;
signed long r;
int ret;
@@ -196,6 +196,13 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
if (r)
goto error_unlock_free;
+ seq = ++ring->fence_drv.sync_seq;
+ r = amdgpu_fence_wait_polling(ring,
+ seq - ring->fence_drv.num_fences_mask,
+ timeout);
+ if (r < 1)
+ goto error_undo;
+
api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
api_status->api_completion_fence_addr = status_gpu_addr;
api_status->api_completion_fence_value = 1;
@@ -208,8 +215,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
mes_status_pkt.api_status.api_completion_fence_addr =
ring->fence_drv.gpu_addr;
- mes_status_pkt.api_status.api_completion_fence_value =
- ++ring->fence_drv.sync_seq;
+ mes_status_pkt.api_status.api_completion_fence_value = seq;
amdgpu_ring_write_multiple(ring, &mes_status_pkt,
sizeof(mes_status_pkt) / 4);
@@ -229,7 +235,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
dev_dbg(adev->dev, "MES msg=%d was emitted\n",
x_pkt->header.opcode);
- r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+ r = amdgpu_fence_wait_polling(ring, seq, timeout);
if (r < 1 || !*status_ptr) {
if (misc_op_str)
@@ -252,6 +258,10 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
amdgpu_device_wb_free(adev, status_offset);
return 0;
+error_undo:
+ dev_err(adev->dev, "MES ring buffer is full.\n");
+ amdgpu_ring_undo(ring);
+
error_unlock_free:
spin_unlock_irqrestore(&mes->ring_lock, flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 0713bc3eb263..249e5a66205c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -154,7 +154,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
const char *op_str, *misc_op_str;
unsigned long flags;
u64 status_gpu_addr;
- u32 status_offset;
+ u32 seq, status_offset;
u64 *status_ptr;
signed long r;
int ret;
@@ -182,6 +182,13 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
if (r)
goto error_unlock_free;
+ seq = ++ring->fence_drv.sync_seq;
+ r = amdgpu_fence_wait_polling(ring,
+ seq - ring->fence_drv.num_fences_mask,
+ timeout);
+ if (r < 1)
+ goto error_undo;
+
api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
api_status->api_completion_fence_addr = status_gpu_addr;
api_status->api_completion_fence_value = 1;
@@ -194,8 +201,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
mes_status_pkt.api_status.api_completion_fence_addr =
ring->fence_drv.gpu_addr;
- mes_status_pkt.api_status.api_completion_fence_value =
- ++ring->fence_drv.sync_seq;
+ mes_status_pkt.api_status.api_completion_fence_value = seq;
amdgpu_ring_write_multiple(ring, &mes_status_pkt,
sizeof(mes_status_pkt) / 4);
@@ -215,7 +221,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
dev_dbg(adev->dev, "MES msg=%d was emitted\n",
x_pkt->header.opcode);
- r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+ r = amdgpu_fence_wait_polling(ring, seq, timeout);
if (r < 1 || !*status_ptr) {
if (misc_op_str)
@@ -238,6 +244,10 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
amdgpu_device_wb_free(adev, status_offset);
return 0;
+error_undo:
+ dev_err(adev->dev, "MES ring buffer is full.\n");
+ amdgpu_ring_undo(ring);
+
error_unlock_free:
spin_unlock_irqrestore(&mes->ring_lock, flags);
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2024-08-19 10:21 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-08-19 10:21 FAILED: patch "[PATCH] drm/amdgpu/mes: fix mes ring buffer overflow" failed to apply to 6.10-stable tree gregkh
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox