mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Lizhi Hou <lizhi.hou@amd.com>
To: Max Zhen <max.zhen@amd.com>, <ogabbay@kernel.org>,
	<quic_jhugo@quicinc.com>, <dri-devel@lists.freedesktop.org>,
	<mario.limonciello@amd.com>, <karol.wachowski@linux.intel.com>
Cc: <linux-kernel@vger.kernel.org>, <sonal.santan@amd.com>
Subject: Re: [PATCH V1] accel/amdxdna: Fix hardware context race in amdxdna_update_heap()
Date: Tue, 7 Jul 2026 10:13:21 -0700	[thread overview]
Message-ID: <6724ba79-1db6-aaeb-f7cc-36bde605b5b6@amd.com> (raw)
In-Reply-To: <afc73e8a-5948-417b-92d7-b4ae492c9072@amd.com>

Applied to drm-misc-fixes

On 7/7/26 08:18, Max Zhen wrote:
>
>
> On 7/6/2026 Mon 22:58, Lizhi Hou wrote:
>> amdxdna_update_heap() iterates over hardware contexts while holding
>> xdna->dev_lock. During the iteration, amdxdna_pm_resume_get_locked() may
>> temporarily release and reacquire the lock, allowing hardware 
>> contexts to
>> be modified concurrently.
>>
>> Fix the race by calling amdxdna_pm_resume_get_locked() before
>> iterating over hardware contexts.
>>
>> Fixes: dbc8fd7a03cb ("accel/amdxdna: Add expandable device heap 
>> support")
>> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
> Reviewed-by: Max Zhen <max.zhen@amd.com>
>> ---
>>   drivers/accel/amdxdna/aie2_ctx.c    |  6 ------
>>   drivers/accel/amdxdna/amdxdna_ctx.c | 24 +++++++++++++++---------
>>   2 files changed, 15 insertions(+), 15 deletions(-)
>>
>> diff --git a/drivers/accel/amdxdna/aie2_ctx.c 
>> b/drivers/accel/amdxdna/aie2_ctx.c
>> index 30ccb8d5e23d..101f324ee178 100644
>> --- a/drivers/accel/amdxdna/aie2_ctx.c
>> +++ b/drivers/accel/amdxdna/aie2_ctx.c
>> @@ -1222,10 +1222,6 @@ int aie2_hwctx_heap_expand(struct 
>> amdxdna_hwctx *hwctx,
>>       u64 addr;
>>       int ret;
>>   -    ret = amdxdna_pm_resume_get_locked(xdna);
>> -    if (ret)
>> -        return ret;
>> -
>>       addr = amdxdna_obj_dma_addr(heap);
>>       ret = aie2_add_host_buf(xdna->dev_handle, hwctx->fw_ctx_id,
>>                   addr, heap->mem.size);
>> @@ -1234,7 +1230,5 @@ int aie2_hwctx_heap_expand(struct amdxdna_hwctx 
>> *hwctx,
>>                hwctx->name, heap->mem.size, ret);
>>       }
>>   -    amdxdna_pm_suspend_put(xdna);
>> -
>>       return ret;
>>   }
>> diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c 
>> b/drivers/accel/amdxdna/amdxdna_ctx.c
>> index 9ae19393e488..8f8df9d04ec5 100644
>> --- a/drivers/accel/amdxdna/amdxdna_ctx.c
>> +++ b/drivers/accel/amdxdna/amdxdna_ctx.c
>> @@ -472,9 +472,7 @@ static int amdxdna_hwctx_expand_heap(struct 
>> amdxdna_hwctx *hwctx)
>>               break;
>>           }
>>   -        mutex_unlock(&client->mm_lock);
>>           ret = xdna->dev_info->ops->hwctx_heap_expand(hwctx, heap);
>> -        mutex_lock(&client->mm_lock);
>>           if (ret) {
>>               amdxdna_gem_unpin(heap);
>>               drm_gem_object_put(to_gobj(heap));
>> @@ -493,18 +491,26 @@ int amdxdna_update_heap(struct amdxdna_client 
>> *client, struct amdxdna_hwctx *hwc
>>       unsigned long hwctx_id;
>>       int ret;
>>   -    guard(mutex)(&client->mm_lock);
>> +    ret = amdxdna_pm_resume_get_locked(client->xdna);
>> +    if (ret)
>> +        return ret;
>>   -    if (hwctx)
>> -        return amdxdna_hwctx_expand_heap(hwctx);
>> +    mutex_lock(&client->mm_lock);
>>   -    amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
>> +    if (hwctx) {
>>           ret = amdxdna_hwctx_expand_heap(hwctx);
>> -        if (ret)
>> -            return ret;
>> +    } else {
>> +        amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
>> +            ret = amdxdna_hwctx_expand_heap(hwctx);
>> +            if (ret)
>> +                break;
>> +        }
>>       }
>> +    mutex_unlock(&client->mm_lock);
>>   -    return 0;
>> +    amdxdna_pm_suspend_put(client->xdna);
>> +
>> +    return ret;
>>   }
>>     static void
>

      reply	other threads:[~2026-07-07 17:13 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-07  5:58 Lizhi Hou
2026-07-07 15:18 ` Max Zhen
2026-07-07 17:13   ` Lizhi Hou [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=6724ba79-1db6-aaeb-f7cc-36bde605b5b6@amd.com \
    --to=lizhi.hou@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=karol.wachowski@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mario.limonciello@amd.com \
    --cc=max.zhen@amd.com \
    --cc=ogabbay@kernel.org \
    --cc=quic_jhugo@quicinc.com \
    --cc=sonal.santan@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®