* [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump
@ 2026-08-27 16:37 Sunil Khatri
2026-08-28 8:25 ` Khatri, Sunil
0 siblings, 1 reply; 4+ messages in thread
From: Sunil Khatri @ 2026-08-27 16:37 UTC (permalink / raw)
To: Alex Deucher, Christian König, Prosyak Vitaly; +Cc: amd-gfx, Sunil Khatri
In amdgpu_devcoredump_print_ibs(), the NO_CPU_ACCESS VRAM path passed
cursor.start/4 and cursor.size/4 to amdgpu_device_mm_access(), but that
function's pos/size parameters are byte offsets/lengths (confirmed by
amdgpu_ttm_vram_mm_access() and leading to wrong size calculation.
Similarly with that change the off index needs to be calculated
based on dword since that is a u32 type.
Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump")
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
index 76771ad30c41..2d3fb87af00a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
@@ -297,10 +297,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer *p,
amdgpu_res_first(abo->tbo.resource, offset,
coredump->ibs[i].ib_size_dw * 4, &cursor);
while (cursor.remaining) {
- amdgpu_device_mm_access(adev, cursor.start / 4,
- &ib_content[off], cursor.size / 4,
+ amdgpu_device_mm_access(adev, cursor.start,
+ &ib_content[off], cursor.size,
false);
- off += cursor.size;
+ off += cursor.size / 4;
amdgpu_res_next(&cursor, cursor.size);
}
emit_content = true;
--
2.34.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump
2026-08-27 16:37 [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump Sunil Khatri
@ 2026-08-28 8:25 ` Khatri, Sunil
2026-08-31 15:09 ` Khatri, Sunil
0 siblings, 1 reply; 4+ messages in thread
From: Khatri, Sunil @ 2026-08-28 8:25 UTC (permalink / raw)
To: Sunil Khatri, Alex Deucher, Christian König, Prosyak Vitaly,
Pelloux-Prayer, Pierre-Eric
Cc: amd-gfx
+ pierre-eric
On 27-08-2026 10:07 pm, Sunil Khatri wrote:
> In amdgpu_devcoredump_print_ibs(), the NO_CPU_ACCESS VRAM path passed
> cursor.start/4 and cursor.size/4 to amdgpu_device_mm_access(), but that
> function's pos/size parameters are byte offsets/lengths (confirmed by
> amdgpu_ttm_vram_mm_access() and leading to wrong size calculation.
>
> Similarly with that change the off index needs to be calculated
> based on dword since that is a u32 type.
>
> Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump")
> Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
> index 76771ad30c41..2d3fb87af00a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
> @@ -297,10 +297,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer *p,
> amdgpu_res_first(abo->tbo.resource, offset,
> coredump->ibs[i].ib_size_dw * 4, &cursor);
> while (cursor.remaining) {
> - amdgpu_device_mm_access(adev, cursor.start / 4,
> - &ib_content[off], cursor.size / 4,
> + amdgpu_device_mm_access(adev, cursor.start,
> + &ib_content[off], cursor.size,
> false);
> - off += cursor.size;
> + off += cursor.size / 4;
> amdgpu_res_next(&cursor, cursor.size);
> }
> emit_content = true;
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump
2026-08-28 8:25 ` Khatri, Sunil
@ 2026-08-31 15:09 ` Khatri, Sunil
2026-08-31 15:22 ` vitaly prosyak
0 siblings, 1 reply; 4+ messages in thread
From: Khatri, Sunil @ 2026-08-31 15:09 UTC (permalink / raw)
To: Sunil Khatri, Alex Deucher, Christian König, Prosyak Vitaly,
Pelloux-Prayer, Pierre-Eric
Cc: amd-gfx
Ping for review please.
On 28-08-2026 01:55 pm, Khatri, Sunil wrote:
> + pierre-eric
>
> On 27-08-2026 10:07 pm, Sunil Khatri wrote:
>> In amdgpu_devcoredump_print_ibs(), the NO_CPU_ACCESS VRAM path passed
>> cursor.start/4 and cursor.size/4 to amdgpu_device_mm_access(), but that
>> function's pos/size parameters are byte offsets/lengths (confirmed by
>> amdgpu_ttm_vram_mm_access() and leading to wrong size calculation.
>>
>> Similarly with that change the off index needs to be calculated
>> based on dword since that is a u32 type.
>>
>> Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump")
>> Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 6 +++---
>> 1 file changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>> index 76771ad30c41..2d3fb87af00a 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>> @@ -297,10 +297,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer
>> *p,
>> amdgpu_res_first(abo->tbo.resource, offset,
>> coredump->ibs[i].ib_size_dw * 4, &cursor);
>> while (cursor.remaining) {
>> - amdgpu_device_mm_access(adev, cursor.start / 4,
>> - &ib_content[off], cursor.size / 4,
>> + amdgpu_device_mm_access(adev, cursor.start,
>> + &ib_content[off], cursor.size,
>> false);
>> - off += cursor.size;
>> + off += cursor.size / 4;
>> amdgpu_res_next(&cursor, cursor.size);
>> }
>> emit_content = true;
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump
2026-08-31 15:09 ` Khatri, Sunil
@ 2026-08-31 15:22 ` vitaly prosyak
0 siblings, 0 replies; 4+ messages in thread
From: vitaly prosyak @ 2026-08-31 15:22 UTC (permalink / raw)
To: Khatri, Sunil, Sunil Khatri, Alex Deucher, Christian König,
Prosyak Vitaly, Pelloux-Prayer, Pierre-Eric
Cc: amd-gfx
LGTM, Reviewed-by Vitaly Prosyak <vitaly.prosyak@amd.com>
On 2026-08-31 11:09, Khatri, Sunil wrote:
> Ping for review please.
>
> On 28-08-2026 01:55 pm, Khatri, Sunil wrote:
>> + pierre-eric
>>
>> On 27-08-2026 10:07 pm, Sunil Khatri wrote:
>>> In amdgpu_devcoredump_print_ibs(), the NO_CPU_ACCESS VRAM path passed
>>> cursor.start/4 and cursor.size/4 to amdgpu_device_mm_access(), but that
>>> function's pos/size parameters are byte offsets/lengths (confirmed by
>>> amdgpu_ttm_vram_mm_access() and leading to wrong size calculation.
>>>
>>> Similarly with that change the off index needs to be calculated
>>> based on dword since that is a u32 type.
>>>
>>> Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump")
>>> Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
>>> ---
>>> drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 6 +++---
>>> 1 file changed, 3 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>>> index 76771ad30c41..2d3fb87af00a 100644
>>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
>>> @@ -297,10 +297,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer
>>> *p,
>>> amdgpu_res_first(abo->tbo.resource, offset,
>>> coredump->ibs[i].ib_size_dw * 4, &cursor);
>>> while (cursor.remaining) {
>>> - amdgpu_device_mm_access(adev, cursor.start / 4,
>>> - &ib_content[off], cursor.size / 4,
>>> + amdgpu_device_mm_access(adev, cursor.start,
>>> + &ib_content[off], cursor.size,
>>> false);
>>> - off += cursor.size;
>>> + off += cursor.size / 4;
>>> amdgpu_res_next(&cursor, cursor.size);
>>> }
>>> emit_content = true;
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-08-31 15:22 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-08-27 16:37 [PATCH v1] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump Sunil Khatri
2026-08-28 8:25 ` Khatri, Sunil
2026-08-31 15:09 ` Khatri, Sunil
2026-08-31 15:22 ` vitaly prosyak
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.