public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-08-04 16:25:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

drm/amdgpu: add reset sources in gpu reset context

Browse source 
reset source or reset cause is very useful info
for reset context, it will be used by events API.

Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com>
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>
This commit is contained in:
Eric Huang 2024-06-03 11:56:03 -04:00 • committed by Alex Deucher
parent 3e538e4322
commit 2656e1ce78
2 changed files with 47 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
View file

@ -160,3 +160,37 @@ void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain)
atomic_set(&reset_domain->in_gpu_reset, 0);
up_write(&reset_domain->sem);
}
void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
size_t len)
{
struct amdgpu_ring *ring;
if (!buf || !len)
return;
switch (rst_ctxt->src) {
case AMDGPU_RESET_SRC_JOB:
if (rst_ctxt->job) {
ring = amdgpu_job_ring(rst_ctxt->job);
snprintf(buf, len, "job hang on ring:%s", ring->name);
} else {
strscpy(buf, "job hang", len);
}
break;
case AMDGPU_RESET_SRC_RAS:
strscpy(buf, "RAS error", len);
break;
case AMDGPU_RESET_SRC_MES:
strscpy(buf, "MES hang", len);
break;
case AMDGPU_RESET_SRC_HWS:
strscpy(buf, "HWS hang", len);
break;
case AMDGPU_RESET_SRC_USER:
strscpy(buf, "user trigger", len);
break;
default:
strscpy(buf, "unknown", len);
}
}

13
drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
View file

@ -36,6 +36,15 @@ enum AMDGPU_RESET_FLAGS {
AMDGPU_HOST_FLR = 3,
};
enum AMDGPU_RESET_SRCS {
AMDGPU_RESET_SRC_UNKNOWN,
AMDGPU_RESET_SRC_JOB,
AMDGPU_RESET_SRC_RAS,
AMDGPU_RESET_SRC_MES,
AMDGPU_RESET_SRC_HWS,
AMDGPU_RESET_SRC_USER,
};
struct amdgpu_reset_context {
enum amd_reset_method method;
struct amdgpu_device *reset_req_dev;
@ -43,6 +52,7 @@ struct amdgpu_reset_context {
struct amdgpu_hive_info *hive;
struct list_head *reset_device_list;
unsigned long flags;
enum AMDGPU_RESET_SRCS src;
};
struct amdgpu_reset_handler {
@ -130,6 +140,9 @@ void amdgpu_device_lock_reset_domain(struct amdgpu_reset_domain *reset_domain);
void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain);
void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
size_t len);
#define for_each_handler(i, handler, reset_ctl) \
for (i = 0; (i < AMDGPU_RESET_MAX_HANDLERS) && \
(handler = (*reset_ctl->reset_handlers)[i]); \