Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 06:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: trigger ip dump before suspend of IP's

Browse Source 
Problem:
IP dump right now is done post suspend of all
IP's which for some IP's could change power
state and software state too which we do not want
to reflect in the dump as it might not be same at
the time of hang.

Solution:
IP should be dumped as close to the HW state when
the GPU was in hung state without trying to reinitialize
any resource.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Sunil Khatri 2024-07-26 18:07:41 +05:30 committed by Alex Deucher
parent a15268787b
commit 13d8850a33
1 changed files with 30 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@ -5277,11 +5277,29 @@ mode1_reset_failed:
return ret;
}
static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
{
int i;
lockdep_assert_held(&adev->reset_domain->sem);
for (i = 0; i < adev->reset_info.num_regs; i++) {
adev->reset_info.reset_dump_reg_value[i] =
RREG32(adev->reset_info.reset_dump_reg_list[i]);
trace_amdgpu_reset_reg_dumps(adev->reset_info.reset_dump_reg_list[i],
adev->reset_info.reset_dump_reg_value[i]);
}
return 0;
}
int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
struct amdgpu_reset_context *reset_context)
{
int i, r = 0;
struct amdgpu_job *job = NULL;
struct amdgpu_device *tmp_adev = reset_context->reset_req_dev;
bool need_full_reset =
test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@ -5340,6 +5358,18 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
}
}
if (!test_bit(AMDGPU_SKIP_COREDUMP, &reset_context->flags)) {
amdgpu_reset_reg_dumps(tmp_adev);
dev_info(tmp_adev->dev, "Dumping IP State\n");
/* Trigger ip dump before we reset the asic */
for (i = 0; i < tmp_adev->num_ip_blocks; i++)
if (tmp_adev->ip_blocks[i].version->funcs->dump_ip_state)
tmp_adev->ip_blocks[i].version->funcs
->dump_ip_state((void *)tmp_adev);
dev_info(tmp_adev->dev, "Dumping IP State Completed\n");
}
if (need_full_reset)
r = amdgpu_device_ip_suspend(adev);
if (need_full_reset)
@ -5352,47 +5382,17 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
return r;
}
static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
{
int i;
lockdep_assert_held(&adev->reset_domain->sem);
for (i = 0; i < adev->reset_info.num_regs; i++) {
adev->reset_info.reset_dump_reg_value[i] =
RREG32(adev->reset_info.reset_dump_reg_list[i]);
trace_amdgpu_reset_reg_dumps(adev->reset_info.reset_dump_reg_list[i],
adev->reset_info.reset_dump_reg_value[i]);
}
return 0;
}
int amdgpu_do_asic_reset(struct list_head *device_list_handle,
struct amdgpu_reset_context *reset_context)
{
struct amdgpu_device *tmp_adev = NULL;
bool need_full_reset, skip_hw_reset, vram_lost = false;
int r = 0;
uint32_t i;
/* Try reset handler method first */
tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
reset_list);
if (!test_bit(AMDGPU_SKIP_COREDUMP, &reset_context->flags)) {
amdgpu_reset_reg_dumps(tmp_adev);
dev_info(tmp_adev->dev, "Dumping IP State\n");
/* Trigger ip dump before we reset the asic */
for (i = 0; i < tmp_adev->num_ip_blocks; i++)
if (tmp_adev->ip_blocks[i].version->funcs->dump_ip_state)
tmp_adev->ip_blocks[i].version->funcs
->dump_ip_state((void *)tmp_adev);
dev_info(tmp_adev->dev, "Dumping IP State Completed\n");
}
reset_context->reset_device_list = device_list_handle;
r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
/* If reset handler not implemented, continue; otherwise return */