From: Alex Deucher <alexander.deucher@amd.com>
To: <amd-gfx@lists.freedesktop.org>, <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Subject: [PATCH 07/31] drm/amdgpu: move force completion into ring resets
Date: Wed, 4 Jun 2025 21:45:37 -0400 [thread overview]
Message-ID: <20250605014602.5915-8-alexander.deucher@amd.com> (raw)
In-Reply-To: <20250605014602.5915-1-alexander.deucher@amd.com>
Move the force completion handling into each ring
reset function so that each engine can determine
whether or not it needs to force completion on the
jobs in the ring.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 +-----
drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c | 1 +
drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 1 +
drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 1 +
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 4 ++++
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 5 ++++-
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 5 ++++-
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 5 ++---
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 1 +
drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 1 +
16 files changed, 26 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 821f88b64f3f6..23b6a0fc0c691 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -161,12 +161,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
r = amdgpu_ring_reset(ring, job->vmid);
if (!r) {
- if (is_guilty) {
+ if (is_guilty)
atomic_inc(&ring->adev->gpu_reset_counter);
- if ((ring->funcs->type != AMDGPU_RING_TYPE_GFX) &&
- (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE))
- amdgpu_fence_driver_force_completion(ring);
- }
drm_sched_wqueue_start(&ring->sched);
dev_err(adev->dev, "Ring %s reset succeeded\n",
ring->sched.name);
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index 4cde8a8bcc837..336ca44950dfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -768,6 +768,7 @@ static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
{
jpeg_v2_0_stop(ring->adev);
jpeg_v2_0_start(ring->adev);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 8b39e114f3be1..72d739e38a8ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -647,6 +647,7 @@ static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
{
jpeg_v2_5_stop_inst(ring->adev, ring->me);
jpeg_v2_5_start_inst(ring->adev, ring->me);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index 2f8510c2986b9..7974d04c15e92 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -559,6 +559,7 @@ static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
{
jpeg_v3_0_stop(ring->adev);
jpeg_v3_0_start(ring->adev);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index f17ec5414fd69..9301d0ff2593b 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -727,6 +727,7 @@ static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
jpeg_v4_0_stop(ring->adev);
jpeg_v4_0_start(ring->adev);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 79e342d5ab28d..ef5075e111300 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -1150,6 +1150,7 @@ static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
jpeg_v4_0_3_core_stall_reset(ring);
jpeg_v4_0_3_start_jrbc(ring);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 3b6f65a256464..858b930d1dd54 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -841,6 +841,7 @@ static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
jpeg_v5_0_1_core_stall_reset(ring);
jpeg_v5_0_1_init_jrbc(ring);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 9c169112a5e7b..eb78bf04a490b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1670,6 +1670,7 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
{
struct amdgpu_device *adev = ring->adev;
+ bool is_guilty = ring->funcs->is_guilty(ring);
u32 id = GET_INST(SDMA0, ring->me);
int r;
@@ -1680,6 +1681,9 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
r = amdgpu_sdma_reset_engine(adev, id);
amdgpu_amdkfd_resume(adev, false);
+ if (is_guilty)
+ amdgpu_fence_driver_force_completion(ring);
+
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 9505ae96fbecc..43885dc04b632 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1542,8 +1542,11 @@ static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
{
struct amdgpu_device *adev = ring->adev;
u32 inst_id = ring->me;
+ int r;
- return amdgpu_sdma_reset_engine(adev, inst_id);
+ r = amdgpu_sdma_reset_engine(adev, inst_id);
+ amdgpu_fence_driver_force_completion(ring);
+ return r;
}
static int sdma_v5_0_stop_queue(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index a6e612b4a8928..ee94e457ee25d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1455,8 +1455,11 @@ static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
{
struct amdgpu_device *adev = ring->adev;
u32 inst_id = ring->me;
+ int r;
- return amdgpu_sdma_reset_engine(adev, inst_id);
+ r = amdgpu_sdma_reset_engine(adev, inst_id);
+ amdgpu_fence_driver_force_completion(ring);
+ return r;
}
static int sdma_v5_2_stop_queue(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 5a70ae17be04e..86ef0e30a89e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1559,6 +1559,7 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
if (r)
return r;
+ amdgpu_fence_driver_force_completion(ring);
return sdma_v6_0_gfx_resume_instance(adev, i, true);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index ad47d0bdf7775..25cec4de13131 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -824,6 +824,7 @@ static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
if (r)
return r;
+ amdgpu_fence_driver_force_completion(ring);
return sdma_v7_0_gfx_resume_instance(adev, i, true);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index b5071f77f78d2..f1ccc6c7be390 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1977,6 +1977,7 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
vcn_v4_0_stop(vinst);
vcn_v4_0_start(vinst);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 5a33140f57235..6ef5944584e56 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -1620,9 +1620,8 @@ static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED);
vcn_v4_0_3_hw_init_inst(vinst);
vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[ring->me].indirect_sram);
- r = amdgpu_ring_test_helper(ring);
-
- return r;
+ amdgpu_fence_driver_force_completion(ring);
+ return amdgpu_ring_test_helper(ring);
}
static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 16ade84facc78..1c13ceb3bed8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -1475,6 +1475,7 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
vcn_v4_0_5_stop(vinst);
vcn_v4_0_5_start(vinst);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index f8e3f0b882da5..a998708bc0745 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -1202,6 +1202,7 @@ static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
vcn_v5_0_0_stop(vinst);
vcn_v5_0_0_start(vinst);
+ amdgpu_fence_driver_force_completion(ring);
return amdgpu_ring_test_helper(ring);
}
--
2.49.0
next prev parent reply other threads:[~2025-06-05 1:46 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-05 1:45 [PATCH V6 00/31] Reset improvements for GC10+ Alex Deucher
2025-06-05 1:45 ` [PATCH 01/31] drm/amdgpu: enable legacy enforce isolation by default Alex Deucher
2025-06-05 1:45 ` [PATCH 02/31] drm/amdgpu/gfx7: drop reset_kgq Alex Deucher
2025-06-05 1:45 ` [PATCH 03/31] drm/amdgpu/gfx8: " Alex Deucher
2025-06-05 1:45 ` [PATCH 04/31] drm/amdgpu/gfx9: " Alex Deucher
2025-06-05 1:45 ` [PATCH 05/31] drm/amdgpu: switch job hw_fence to amdgpu_fence Alex Deucher
2025-06-05 1:45 ` [PATCH 06/31] drm/amdgpu: rework queue reset scheduler interaction Alex Deucher
2025-06-05 1:45 ` Alex Deucher [this message]
2025-06-05 1:45 ` [PATCH 08/31] drm/amdgpu: track ring state associated with a job Alex Deucher
2025-06-05 12:11 ` Christian König
2025-06-05 13:21 ` Alex Deucher
2025-06-05 13:50 ` Christian König
2025-06-05 1:45 ` [PATCH 09/31] drm/amdgpu: optimize amdgpu_ring_reemit_unprocessed_jobs() Alex Deucher
2025-06-05 1:45 ` [PATCH 10/31] drm/amdgpu/gfx10: re-emit unprocessed state on ring reset Alex Deucher
2025-06-05 1:45 ` [PATCH 11/31] drm/amdgpu/gfx11: " Alex Deucher
2025-06-05 1:45 ` [PATCH 12/31] drm/amdgpu/gfx12: " Alex Deucher
2025-06-05 1:45 ` [PATCH 13/31] drm/amdgpu/gfx9: re-emit unprocessed state on kcq reset Alex Deucher
2025-06-05 1:45 ` [PATCH 14/31] drm/amdgpu/gfx9.4.3: " Alex Deucher
2025-06-05 1:45 ` [PATCH 15/31] drm/amdgpu/sdma4.4.2: re-emit unprocessed state on ring reset Alex Deucher
2025-06-05 1:45 ` [PATCH 16/31] drm/amdgpu/sdma5: " Alex Deucher
2025-06-05 1:45 ` [PATCH 17/31] drm/amdgpu/sdma5.2: " Alex Deucher
2025-06-05 1:45 ` [PATCH 18/31] drm/amdgpu/sdma6: " Alex Deucher
2025-06-05 1:45 ` [PATCH 19/31] drm/amdgpu/sdma7: " Alex Deucher
2025-06-05 1:45 ` [PATCH 20/31] drm/amdgpu/jpeg2: " Alex Deucher
2025-06-05 1:45 ` [PATCH 21/31] drm/amdgpu/jpeg2.5: " Alex Deucher
2025-06-05 1:45 ` [PATCH 22/31] drm/amdgpu/jpeg3: " Alex Deucher
2025-06-05 1:45 ` [PATCH 23/31] drm/amdgpu/jpeg4: " Alex Deucher
2025-06-05 1:45 ` [PATCH 24/31] drm/amdgpu/jpeg4.0.3: " Alex Deucher
2025-06-05 1:45 ` [PATCH 25/31] drm/amdgpu/jpeg5.0.0: add queue reset Alex Deucher
2025-06-05 1:45 ` [PATCH 26/31] drm/amdgpu/jpeg5: re-emit unprocessed state on ring reset Alex Deucher
2025-06-05 1:45 ` [PATCH 27/31] drm/amdgpu/jpeg5.0.1: " Alex Deucher
2025-06-05 1:45 ` [PATCH 28/31] drm/amdgpu/vcn4: " Alex Deucher
2025-06-05 1:45 ` [PATCH 29/31] drm/amdgpu/vcn4.0.3: " Alex Deucher
2025-06-05 1:46 ` [PATCH 30/31] drm/amdgpu/vcn4.0.5: " Alex Deucher
2025-06-05 1:46 ` [PATCH 31/31] drm/amdgpu/vcn5: " Alex Deucher
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250605014602.5915-8-alexander.deucher@amd.com \
--to=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.