From 51b5c911168d98fd4f5b1bb71afa213c576e87ad Mon Sep 17 00:00:00 2001
From: Victor Skvortsov <victor.skvortsov@amd.com>
Date: Mon, 13 Dec 2021 21:38:20 +0000
Subject: drm/amdgpu: SRIOV flr_work should use down_write
Git-commit: fa4a427d84f9b797970a3d5139d7645403e4e989
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
Host initiated VF FLR may fail if someone else is
already holding a read_lock. Change from down_write_trylock
to down_write to guarantee the reset goes through.
Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
Reviewed by: Shaoyun.liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 5 +++--
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 5 +++--
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 23b066bcffb2..0077e738db31 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -252,11 +252,12 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*/
- if (!down_write_trylock(&adev->reset_sem))
+ if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
return;
+ down_write(&adev->reset_sem);
+
amdgpu_virt_fini_data_exchange(adev);
- atomic_set(&adev->in_gpu_reset, 1);
xgpu_ai_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index a35e6d87e537..477d0dde19c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -281,11 +281,12 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*/
- if (!down_write_trylock(&adev->reset_sem))
+ if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
return;
+ down_write(&adev->reset_sem);
+
amdgpu_virt_fini_data_exchange(adev);
- atomic_set(&adev->in_gpu_reset, 1);
xgpu_nv_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
--
2.38.1