Re: [PATCH] accel/amdxdna: return early from a zero-length flush

Re: [PATCH] accel/amdxdna: return early from a zero-length flush

[Lizhi Hou]

On 8/17/26 16:06, Taimuraz Kaitmazov wrote:
> SYNC_BO does not constrain its size, so a request for zero bytes reaches
> drm_clflush_virt_range(), which ends with an unconditional
> clflushopt(end - 1). For an empty range that is the byte before the
> mapping, and abo->mem.kva comes from vmap(), so the access lands in the
> guard page below the vmalloc area and faults:
>
>    BUG: unable to handle page fault for address: ffffd16fbbc70fff
>    #PF: supervisor read access in kernel mode
>    Oops: Oops: 0000 [#1] SMP NOPTI
>    CPU: 7 UID: 1000 Comm: sync_bo_probe
>    RIP: 0010:drm_clflush_virt_range+0x3c/0x70
>    Call Trace:
>     amdxdna_drm_sync_bo_ioctl+0x124/0x430 [amdxdna]
>     drm_ioctl+0x301/0x4c0
>     __x64_sys_ioctl+0x115/0x2f0
>     do_syscall_64+0xa6/0x3d0
>
> Any process that can open the render node can do this. Reproduced 3 of 3
> times on a Strix Point NPU (1022:17f0), by calling SYNC_BO with size 0 on
> an AMDXDNA_BO_SHARE object. The import arm takes the same request but
> flushes the whole scatterlist, so it survives it.
>
> Nothing needs flushing for an empty range, so answer before choosing a
> path.
>
> Fixes: e252e3f3488a ("accel/amdxdna: Revise device bo creation and free")
> Cc: stable@vger.kernel.org
> Signed-off-by: Taimuraz Kaitmazov <taimuraz@kaitmazov.com>
> ---
> Trees before amdxdna_flush_bo() existed carry the same call inline in
> amdxdna_drm_sync_bo_ioctl(), with args->size passed to
> drm_clflush_virt_range() unclamped, so a backport wants the guard at that
> call site instead.
>
>   drivers/accel/amdxdna/amdxdna_gem.c | 3 +++
>   1 file changed, 3 insertions(+)
>
> diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c
> index 1c63eff0a4a8..2a16de96e6a4 100644
> --- a/drivers/accel/amdxdna/amdxdna_gem.c
> +++ b/drivers/accel/amdxdna/amdxdna_gem.c
> @@ -1247,6 +1247,9 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size)
>   		return -EINVAL;
>   
>   	size = min(abo->mem.size, end) - offset;
> +	if (!size)
> +		return 0;
> +
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
>   	if (is_import_bo(abo))
>   		drm_clflush_sg(abo->base.sgt);
>   	else if (amdxdna_gem_vmap(abo))

Re: [PATCH] accel/amdxdna: return early from a zero-length flush

[Lizhi Hou]

Applied to drm-misc-fixes

On 8/18/26 09:23, Lizhi Hou wrote:
>
> On 8/17/26 16:06, Taimuraz Kaitmazov wrote:
>> SYNC_BO does not constrain its size, so a request for zero bytes reaches
>> drm_clflush_virt_range(), which ends with an unconditional
>> clflushopt(end - 1). For an empty range that is the byte before the
>> mapping, and abo->mem.kva comes from vmap(), so the access lands in the
>> guard page below the vmalloc area and faults:
>>
>>    BUG: unable to handle page fault for address: ffffd16fbbc70fff
>>    #PF: supervisor read access in kernel mode
>>    Oops: Oops: 0000 [#1] SMP NOPTI
>>    CPU: 7 UID: 1000 Comm: sync_bo_probe
>>    RIP: 0010:drm_clflush_virt_range+0x3c/0x70
>>    Call Trace:
>>     amdxdna_drm_sync_bo_ioctl+0x124/0x430 [amdxdna]
>>     drm_ioctl+0x301/0x4c0
>>     __x64_sys_ioctl+0x115/0x2f0
>>     do_syscall_64+0xa6/0x3d0
>>
>> Any process that can open the render node can do this. Reproduced 3 of 3
>> times on a Strix Point NPU (1022:17f0), by calling SYNC_BO with size 
>> 0 on
>> an AMDXDNA_BO_SHARE object. The import arm takes the same request but
>> flushes the whole scatterlist, so it survives it.
>>
>> Nothing needs flushing for an empty range, so answer before choosing a
>> path.
>>
>> Fixes: e252e3f3488a ("accel/amdxdna: Revise device bo creation and 
>> free")
>> Cc: stable@vger.kernel.org
>> Signed-off-by: Taimuraz Kaitmazov <taimuraz@kaitmazov.com>
>> ---
>> Trees before amdxdna_flush_bo() existed carry the same call inline in
>> amdxdna_drm_sync_bo_ioctl(), with args->size passed to
>> drm_clflush_virt_range() unclamped, so a backport wants the guard at 
>> that
>> call site instead.
>>
>>   drivers/accel/amdxdna/amdxdna_gem.c | 3 +++
>>   1 file changed, 3 insertions(+)
>>
>> diff --git a/drivers/accel/amdxdna/amdxdna_gem.c 
>> b/drivers/accel/amdxdna/amdxdna_gem.c
>> index 1c63eff0a4a8..2a16de96e6a4 100644
>> --- a/drivers/accel/amdxdna/amdxdna_gem.c
>> +++ b/drivers/accel/amdxdna/amdxdna_gem.c
>> @@ -1247,6 +1247,9 @@ static int amdxdna_flush_bo(struct 
>> amdxdna_gem_obj *abo, u64 offset, u64 size)
>>           return -EINVAL;
>>         size = min(abo->mem.size, end) - offset;
>> +    if (!size)
>> +        return 0;
>> +
> Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
>>       if (is_import_bo(abo))
>>           drm_clflush_sg(abo->base.sgt);
>>       else if (amdxdna_gem_vmap(abo))