aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
authorEric Huang <jinhuieric.huang@amd.com>2024-06-03 12:04:59 -0400
committerAlex Deucher <alexander.deucher@amd.com>2024-06-05 11:25:14 -0400
commitdbe2c4c8ab92211a57ca4d23bf8eaf6f23e31a54 (patch)
treee92295a47a040ec7d299bba35c8269a1323dbb86 /drivers/gpu/drm/amd/amdgpu
parent3c7758beb269667373421fe7c7c44adcc7129d02 (diff)
drm/amdkfd: add reset cause in gpu pre-reset smi event
reset cause is requested by customer as additional info for gpu reset smi event. v2: integerate reset sources suggested by Lijo Lazar Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c2
3 files changed, 14 insertions, 6 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index e3738d417245..03205e3c3746 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -133,6 +133,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
+ reset_context.src = adev->enable_mes ?
+ AMDGPU_RESET_SRC_MES :
+ AMDGPU_RESET_SRC_HWS;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
@@ -261,12 +264,13 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
return r;
}
-int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev,
+ struct amdgpu_reset_context *reset_context)
{
int r = 0;
if (adev->kfd.dev)
- r = kgd2kfd_pre_reset(adev->kfd.dev);
+ r = kgd2kfd_pre_reset(adev->kfd.dev, reset_context);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 1de021ebdd46..e7bb1ca35801 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -47,6 +47,7 @@ enum TLB_FLUSH_TYPE {
};
struct amdgpu_device;
+struct amdgpu_reset_context;
enum kfd_mem_attachment_type {
KFD_MEM_ATT_SHARED, /* Share kgd_mem->bo or another attachment's */
@@ -170,7 +171,8 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
-int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev,
+ struct amdgpu_reset_context *reset_context);
int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
@@ -416,7 +418,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
void kgd2kfd_device_exit(struct kfd_dev *kfd);
void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
-int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_pre_reset(struct kfd_dev *kfd,
+ struct amdgpu_reset_context *reset_context);
int kgd2kfd_post_reset(struct kfd_dev *kfd);
void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
@@ -459,7 +462,8 @@ static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
return 0;
}
-static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd,
+ struct amdgpu_reset_context *reset_context)
{
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6711836054f9..4096cb3e937e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5775,7 +5775,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
- amdgpu_amdkfd_pre_reset(tmp_adev);
+ amdgpu_amdkfd_pre_reset(tmp_adev, reset_context);
/*
* Mark these ASICs to be reseted as untracked first