From 1658ab6757caa108781fffdd8f2771fe95ea0a61 Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Fri, 8 Jul 2022 11:14:05 +0800
Subject: drm/amdgpu: support reset flag set for gpu reset
Git-commit: f1549c09c520877be211d483d3c6f4e7f77d2588
Patch-mainline: v6.0-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 jsc#PED-2849
Move reset_context out of gpu recover function to make it configurable
for different reset purpose.
For the reset way of call gpu_recovery sysfs, force to use full reset
method. Otherwise, try soft reset by default if the related ASIC
supportted, if soft reset failed, will use full reset.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 5 ++---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 9 ++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 +++++++-------------
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 ++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 10 +++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 12 ++++++++++--
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 12 ++++++++++--
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 12 ++++++++++--
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 12 ++++++++++--
9 files changed, 74 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index fb9399a999ae..2871a3e3801f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1253,9 +1253,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
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(struct amdgpu_device *adev,
- struct amdgpu_job *job);
+ struct amdgpu_job *job,
+ struct amdgpu_reset_context *reset_context);
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_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 567597469a8a..5e53a5293935 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -129,7 +129,14 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
kfd.reset_work);
- amdgpu_device_gpu_recover(adev, NULL);
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
void amdgpu_amdkfd_device_init(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 64f37713b270..e1c9587f659b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5109,7 +5109,8 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
*/
int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
- struct amdgpu_job *job)
+ struct amdgpu_job *job,
+ struct amdgpu_reset_context *reset_context)
{
struct list_head device_list, *device_list_handle = NULL;
bool job_signaled = false;
@@ -5119,9 +5120,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
bool need_emergency_restart = false;
bool audio_suspended = false;
int tmp_vram_lost_counter;
- struct amdgpu_reset_context reset_context;
-
- memset(&reset_context, 0, sizeof(reset_context));
/*
* Special case: RAS triggered and full reset isn't supported
@@ -5147,12 +5145,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (hive)
mutex_lock(&hive->hive_lock);
- reset_context.method = AMD_RESET_METHOD_NONE;
- reset_context.reset_req_dev = adev;
- reset_context.job = job;
- reset_context.hive = hive;
- clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-
+ reset_context->job = job;
+ reset_context->hive = hive;
/*
* Build list of devices to reset.
* In case we are in XGMI hive mode, resort the device list
@@ -5245,7 +5239,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
retry: /* Rest of adevs pre asic reset from XGMI hive. */
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
- r = amdgpu_device_pre_asic_reset(tmp_adev, &reset_context);
+ r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
/*TODO Should we stop ?*/
if (r) {
dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
@@ -5272,7 +5266,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
amdgpu_ras_resume(adev);
} else {
- r = amdgpu_do_asic_reset(device_list_handle, &reset_context);
+ r = amdgpu_do_asic_reset(device_list_handle, reset_context);
if (r && r == -EAGAIN)
goto retry;
}
@@ -5292,7 +5286,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (amdgpu_gpu_recovery == 2 &&
!(tmp_vram_lost_counter < atomic_read(&adev->vram_lost_counter)))
amdgpu_device_recheck_guilty_jobs(
- tmp_adev, device_list_handle, &reset_context);
+ tmp_adev, device_list_handle, reset_context);
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = tmp_adev->rings[i];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 39597ab807d1..ff659d4f772b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -844,7 +844,14 @@ static void amdgpu_debugfs_reset_work(struct work_struct *work)
struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
reset_work);
- amdgpu_device_gpu_recover(adev, NULL);
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 22735790fe50..36c1be77bf8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -29,6 +29,7 @@
#include "amdgpu.h"
#include "amdgpu_trace.h"
+#include "amdgpu_reset.h"
static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
{
@@ -64,7 +65,14 @@ 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);
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
if (r)
DRM_ERROR("GPU Recovery Failed: %d\n", r);
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index a5b6db5ab53c..ff5361f5c2d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1942,8 +1942,16 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
amdgpu_put_xgmi_hive(hive);
}
- if (amdgpu_device_should_recover_gpu(ras->adev))
- amdgpu_device_gpu_recover(ras->adev, NULL);
+ if (amdgpu_device_should_recover_gpu(ras->adev)) {
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
+ }
atomic_set(&ras->in_recovery, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 7ec5b5cf4bb9..12906ba74462 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -283,8 +283,16 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
&& (!amdgpu_device_has_job_running(adev) ||
- adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
- amdgpu_device_gpu_recover(adev, NULL);
+ adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)) {
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
}
static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index e18b75c8fde6..e07757eea7ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -310,8 +310,16 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
- adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
- amdgpu_device_gpu_recover(adev, NULL);
+ adev->video_timeout == MAX_SCHEDULE_TIMEOUT)) {
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
}
static int xgpu_nv_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index c5016a926331..288c414babdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -522,8 +522,16 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
}
/* Trigger recovery due to world switch failure */
- if (amdgpu_device_should_recover_gpu(adev))
- amdgpu_device_gpu_recover(adev, NULL);
+ if (amdgpu_device_should_recover_gpu(adev)) {
+ struct amdgpu_reset_context reset_context;
+ memset(&reset_context, 0, sizeof(reset_context));
+
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
}
static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
--
2.38.1