From 3cd6bd8070d026c684158659f2a4bccfcb752d8d Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 17 Dec 2021 13:05:15 -0500
Subject: drm/amdgpu: Serialize non TDR gpu recovery with TDRs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 54f329cc7a7a7ea265c45b206d45e3d09192aba7
Patch-mainline: v5.18-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

Use reset domain wq also for non TDR gpu recovery trigers
such as sysfs and RAS. We must serialize all possible
GPU recoveries to gurantee no concurrency there.
For TDR call the original recovery function directly since
it's already executed from within the wq. For others just
use a wrapper to qeueue work and wait on it to finish.

v2: Rename to amdgpu_recover_work_struct

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://www.spinics.net/lists/amd-gfx/msg74113.html
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 33 +++++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    |  3 +-
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index f9be5b138f6d..20da46934473 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1299,6 +1299,8 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev);
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			      struct amdgpu_job* job);
+int amdgpu_device_gpu_recover_imp(struct amdgpu_device *adev,
+			      struct amdgpu_job *job);
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 76d96022cd1a..c474a7709db6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5096,7 +5096,7 @@ static void amdgpu_device_recheck_guilty_jobs(
  * Returns 0 for success or an error on failure.
  */
 
-int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+int amdgpu_device_gpu_recover_imp(struct amdgpu_device *adev,
 			      struct amdgpu_job *job)
 {
 	struct list_head device_list, *device_list_handle =  NULL;
@@ -5358,6 +5358,37 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	return r;
 }
 
+struct amdgpu_recover_work_struct {
+	struct work_struct base;
+	struct amdgpu_device *adev;
+	struct amdgpu_job *job;
+	int ret;
+};
+
+static void amdgpu_device_queue_gpu_recover_work(struct work_struct *work)
+{
+	struct amdgpu_recover_work_struct *recover_work = container_of(work, struct amdgpu_recover_work_struct, base);
+
+	recover_work->ret = amdgpu_device_gpu_recover_imp(recover_work->adev, recover_work->job);
+}
+/*
+ * Serialize gpu recover into reset domain single threaded wq
+ */
+int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+				    struct amdgpu_job *job)
+{
+	struct amdgpu_recover_work_struct work = {.adev = adev, .job = job};
+
+	INIT_WORK(&work.base, amdgpu_device_queue_gpu_recover_work);
+
+	if (!queue_work(adev->reset_domain.wq, &work.base))
+		return -EAGAIN;
+
+	flush_work(&work.base);
+
+	return work.ret;
+}
+
 /**
  * amdgpu_device_get_pcie_info - fence pcie info about the PCIE slot
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4870e093213d..d970336d2261 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -64,10 +64,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		  ti.process_name, ti.tgid, ti.task_name, ti.pid);
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
-		r = amdgpu_device_gpu_recover(ring->adev, job);
+		r = amdgpu_device_gpu_recover_imp(ring->adev, job);
 		if (r)
 			DRM_ERROR("GPU Recovery Failed: %d\n", r);
-
 	} else {
 		drm_sched_suspend_timeout(&ring->sched);
 		if (amdgpu_sriov_vf(adev))
-- 
2.38.1