* [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept
@ 2026-08-25 13:09 Guoqing Jiang
2026-08-25 13:53 ` Bernard Metzler
0 siblings, 1 reply; 5+ messages in thread
From: Guoqing Jiang @ 2026-08-25 13:09 UTC (permalink / raw)
To: bernard.metzler, jgg, leon; +Cc: linux-rdma, shuangpeng.kernel
We need to clear qp and cep before release state_lock as siw_qp_llp_close
and siw_qp_modify->siw_qp_llp_close did.
Otherwise if siw_qp_modify() fails in siw_accept(), the QP's state_lock
is released before the error path cleanup. A concurrent ibv_modify_qp()
transitioning the QP to ERROR can race in this window:
siw_accept() ibv_modify_qp(ERROR)
---------------------- ----------------------
siw_qp_modify() fails
up_write(&qp->state_lock)
down_write(&qp->state_lock)
nextstate_from_idle():
if (qp->cep)
siw_cep_put(qp->cep) <- frees cep
qp->cep = NULL
goto error
cep->qp = NULL <- UAF
Clear qp->cep and cep->qp, and drop the association reference taken by
siw_cep_get(), all under the write lock held from the initial
down_write(&qp->state_lock). Thread B therefore sees qp->cep == NULL,
skips its own put, and cannot free the cep before siw_accept() is done
with it.
Reported-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
Link: https://lore.kernel.org/linux-rdma/d6fbe475-a5c2-f975-99b0-a0bd6b6d10e8@linux.dev/T/#m5876c1ff2de8686a9a1173b8f1aa0ff5363a785c
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
---
drivers/infiniband/sw/siw/siw_cm.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 0245b25e7271..1573f2e888b2 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -1719,9 +1719,13 @@ int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params)
SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
SIW_QP_ATTR_MPA);
+ if (rv) {
+ cep->qp = NULL;
+ qp->cep = NULL;
+ siw_cep_put(cep);
+ goto error_unlock;
+ }
up_write(&qp->state_lock);
- if (rv)
- goto error;
siw_dbg_cep(cep, "[QP %u]: send mpa reply, %d byte pdata\n",
qp_id(qp), params->private_data_len);
--
2.35.3
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept
2026-08-25 13:09 [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept Guoqing Jiang
@ 2026-08-25 13:53 ` Bernard Metzler
2026-08-26 6:38 ` Guoqing Jiang
0 siblings, 1 reply; 5+ messages in thread
From: Bernard Metzler @ 2026-08-25 13:53 UTC (permalink / raw)
To: Guoqing Jiang, jgg, leon; +Cc: linux-rdma, shuangpeng.kernel
On 25.08.2026 15:09, Guoqing Jiang wrote:
> We need to clear qp and cep before release state_lock as siw_qp_llp_closeo
> and siw_qp_modify->siw_qp_llp_close did.
>
> Otherwise if siw_qp_modify() fails in siw_accept(), the QP's state_lock
> is released before the error path cleanup. A concurrent ibv_modify_qp()
> transitioning the QP to ERROR can race in this window:
>
> siw_accept() ibv_modify_qp(ERROR)
> ---------------------- ----------------------
> siw_qp_modify() fails
> up_write(&qp->state_lock)
> down_write(&qp->state_lock)
> nextstate_from_idle():
> if (qp->cep)
> siw_cep_put(qp->cep) <- frees cep
> qp->cep = NULL
> goto error
> cep->qp = NULL <- UAF
>
> Clear qp->cep and cep->qp, and drop the association reference taken by
> siw_cep_get(), all under the write lock held from the initial
> down_write(&qp->state_lock). Thread B therefore sees qp->cep == NULL,
> skips its own put, and cannot free the cep before siw_accept() is done
> with it.
>
> Reported-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
> Link: https://lore.kernel.org/linux-rdma/d6fbe475-a5c2-f975-99b0-a0bd6b6d10e8@linux.dev/T/#m5876c1ff2de8686a9a1173b8f1aa0ff5363a785c
> Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
> ---
> drivers/infiniband/sw/siw/siw_cm.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
> index 0245b25e7271..1573f2e888b2 100644
> --- a/drivers/infiniband/sw/siw/siw_cm.c
> +++ b/drivers/infiniband/sw/siw/siw_cm.c
> @@ -1719,9 +1719,13 @@ int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params)
> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
> SIW_QP_ATTR_MPA);
> + if (rv) {
> + cep->qp = NULL;
This can better be omitted since done in error_unlock path
anyway and is redundant otherwise. It would also better
retain the logic of calling siw_qp_put(qp) right after
clearing cep's reference to the qp, as done in error path.
Thank you!
Bernard.> + qp->cep = NULL;
> + siw_cep_put(cep);
> + goto error_unlock;
> + }
> up_write(&qp->state_lock);
> - if (rv)
> - goto error;
>
> siw_dbg_cep(cep, "[QP %u]: send mpa reply, %d byte pdata\n",
> qp_id(qp), params->private_data_len);
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept
2026-08-25 13:53 ` Bernard Metzler
@ 2026-08-26 6:38 ` Guoqing Jiang
2026-08-26 12:19 ` Bernard Metzler
0 siblings, 1 reply; 5+ messages in thread
From: Guoqing Jiang @ 2026-08-26 6:38 UTC (permalink / raw)
To: Bernard Metzler, jgg, leon; +Cc: linux-rdma, shuangpeng.kernel
Hi Bernard,
On 8/25/26 21:53, Bernard Metzler wrote:
> On 25.08.2026 15:09, Guoqing Jiang wrote:
>> We need to clear qp and cep before release state_lock as
>> siw_qp_llp_closeo
>> and siw_qp_modify->siw_qp_llp_close did.
>>
>> Otherwise if siw_qp_modify() fails in siw_accept(), the QP's state_lock
>> is released before the error path cleanup. A concurrent ibv_modify_qp()
>> transitioning the QP to ERROR can race in this window:
>>
>> siw_accept() ibv_modify_qp(ERROR)
>> ---------------------- ----------------------
>> siw_qp_modify() fails
>> up_write(&qp->state_lock)
>> down_write(&qp->state_lock)
>> nextstate_from_idle():
>> if (qp->cep)
>> siw_cep_put(qp->cep) <- frees
>> cep
>> qp->cep = NULL
>> goto error
>> cep->qp = NULL <- UAF
>>
>> Clear qp->cep and cep->qp, and drop the association reference taken by
>> siw_cep_get(), all under the write lock held from the initial
>> down_write(&qp->state_lock). Thread B therefore sees qp->cep == NULL,
>> skips its own put, and cannot free the cep before siw_accept() is done
>> with it.
>>
>> Reported-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
>> Link:
>> https://lore.kernel.org/linux-rdma/d6fbe475-a5c2-f975-99b0-a0bd6b6d10e8@linux.dev/T/#m5876c1ff2de8686a9a1173b8f1aa0ff5363a785c
>> Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
>> ---
>> drivers/infiniband/sw/siw/siw_cm.c | 8 ++++++--
>> 1 file changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/infiniband/sw/siw/siw_cm.c
>> b/drivers/infiniband/sw/siw/siw_cm.c
>> index 0245b25e7271..1573f2e888b2 100644
>> --- a/drivers/infiniband/sw/siw/siw_cm.c
>> +++ b/drivers/infiniband/sw/siw/siw_cm.c
>> @@ -1719,9 +1719,13 @@ int siw_accept(struct iw_cm_id *id, struct
>> iw_cm_conn_param *params)
>> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
>> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
>> SIW_QP_ATTR_MPA);
>> + if (rv) {
>> + cep->qp = NULL;
> This can better be omitted since done in error_unlock path
> anyway and is redundant otherwise.
Right, thanks for the review! And probably call siw_cep_put before set
qp->cep to
NULL as other places did.
> It would also better retain the logic of calling siw_qp_put(qp) right
> after
> clearing cep's reference to the qp, as done in error path.
I suppose this change could be okay.
@@ -1719,9 +1719,12 @@ int siw_accept(struct iw_cm_id *id, struct
iw_cm_conn_param *params)
SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
SIW_QP_ATTR_MPA);
+ if (rv) {
+ siw_cep_put(cep);
+ qp->cep = NULL;
+ goto error_unlock;
+ }
up_write(&qp->state_lock);
- if (rv)
- goto error;
I am wondering if there is another use-after-free case in
siw_qp_cm_drop. Because
the beginning of siw_qp_cm_drop borrows the qp->cep pointer without
holding a
reference. If another thread put the last reference of cep, then
siw_qp_cm_drop
wakes and deferences cep which has been freed.
>
> Thank you!
> Bernard.> + qp->cep = NULL;
>> + siw_cep_put(cep);
>> + goto error_unlock;
>> + }
>> up_write(&qp->state_lock);
>> - if (rv)
>> - goto error;
>> siw_dbg_cep(cep, "[QP %u]: send mpa reply, %d byte pdata\n",
>> qp_id(qp), params->private_data_len);
Thanks,
Guoqing
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept
2026-08-26 6:38 ` Guoqing Jiang
@ 2026-08-26 12:19 ` Bernard Metzler
2026-08-26 13:15 ` Guoqing Jiang
0 siblings, 1 reply; 5+ messages in thread
From: Bernard Metzler @ 2026-08-26 12:19 UTC (permalink / raw)
To: Guoqing Jiang, jgg, leon; +Cc: linux-rdma, shuangpeng.kernel
On 26.08.2026 08:38, Guoqing Jiang wrote:
> Hi Bernard,
>
> On 8/25/26 21:53, Bernard Metzler wrote:
>> On 25.08.2026 15:09, Guoqing Jiang wrote:
>>> We need to clear qp and cep before release state_lock as siw_qp_llp_closeo
>>> and siw_qp_modify->siw_qp_llp_close did.
>>>
>>> Otherwise if siw_qp_modify() fails in siw_accept(), the QP's state_lock
>>> is released before the error path cleanup. A concurrent ibv_modify_qp()
>>> transitioning the QP to ERROR can race in this window:
>>>
>>> siw_accept() ibv_modify_qp(ERROR)
>>> ---------------------- ----------------------
>>> siw_qp_modify() fails
>>> up_write(&qp->state_lock)
>>> down_write(&qp->state_lock)
>>> nextstate_from_idle():
>>> if (qp->cep)
>>> siw_cep_put(qp->cep) <- frees cep
>>> qp->cep = NULL
>>> goto error
>>> cep->qp = NULL <- UAF
>>>
>>> Clear qp->cep and cep->qp, and drop the association reference taken by
>>> siw_cep_get(), all under the write lock held from the initial
>>> down_write(&qp->state_lock). Thread B therefore sees qp->cep == NULL,
>>> skips its own put, and cannot free the cep before siw_accept() is done
>>> with it.
>>>
>>> Reported-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
>>> Link: https://lore.kernel.org/linux-rdma/d6fbe475-a5c2-f975-99b0-a0bd6b6d10e8@linux.dev/T/#m5876c1ff2de8686a9a1173b8f1aa0ff5363a785c
>>> Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
>>> ---
>>> drivers/infiniband/sw/siw/siw_cm.c | 8 ++++++--
>>> 1 file changed, 6 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
>>> index 0245b25e7271..1573f2e888b2 100644
>>> --- a/drivers/infiniband/sw/siw/siw_cm.c
>>> +++ b/drivers/infiniband/sw/siw/siw_cm.c
>>> @@ -1719,9 +1719,13 @@ int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params)
>>> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
>>> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
>>> SIW_QP_ATTR_MPA);
>>> + if (rv) {
>>> + cep->qp = NULL;
>> This can better be omitted since done in error_unlock path
>> anyway and is redundant otherwise.
>
> Right, thanks for the review! And probably call siw_cep_put before set qp->cep to
> NULL as other places did.
>
>> It would also better retain the logic of calling siw_qp_put(qp) right after
>> clearing cep's reference to the qp, as done in error path.
>
> I suppose this change could be okay.
>
> @@ -1719,9 +1719,12 @@ int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params)
> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
> SIW_QP_ATTR_MPA);
> + if (rv) {
> + siw_cep_put(cep);
> + qp->cep = NULL;
> + goto error_unlock;
> + }
> up_write(&qp->state_lock);
> - if (rv)
> - goto error;
>
That looks good, while I think we should always NULL a pointer to
something before releasing a hold/reference to it. Putting the reference
implies a memory barrier and so it's guaranteed others see that NULL as well.
You are right - there are places where this is not done as it should.
> I am wondering if there is another use-after-free case in siw_qp_cm_drop. Because
> the beginning of siw_qp_cm_drop borrows the qp->cep pointer without holding a
> reference. If another thread put the last reference of cep, then siw_qp_cm_drop
> wakes and deferences cep which has been freed.
>
Let's put this in an extra thread. You may have a point ;)
Thanks,
Bernard.
>>
>> Thank you!
>> Bernard.> + qp->cep = NULL;
>>> + siw_cep_put(cep);
>>> + goto error_unlock;
>>> + }
>>> up_write(&qp->state_lock);
>>> - if (rv)
>>> - goto error;
>>> siw_dbg_cep(cep, "[QP %u]: send mpa reply, %d byte pdata\n",
>>> qp_id(qp), params->private_data_len);
>
> Thanks,
> Guoqing
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept
2026-08-26 12:19 ` Bernard Metzler
@ 2026-08-26 13:15 ` Guoqing Jiang
0 siblings, 0 replies; 5+ messages in thread
From: Guoqing Jiang @ 2026-08-26 13:15 UTC (permalink / raw)
To: Bernard Metzler, jgg, leon; +Cc: linux-rdma, shuangpeng.kernel
On 8/26/26 20:19, Bernard Metzler wrote:
> On 26.08.2026 08:38, Guoqing Jiang wrote:
>> Hi Bernard,
>>
>> On 8/25/26 21:53, Bernard Metzler wrote:
>>> On 25.08.2026 15:09, Guoqing Jiang wrote:
>>>> We need to clear qp and cep before release state_lock as
>>>> siw_qp_llp_closeo
>>>> and siw_qp_modify->siw_qp_llp_close did.
>>>>
>>>> Otherwise if siw_qp_modify() fails in siw_accept(), the QP's
>>>> state_lock
>>>> is released before the error path cleanup. A concurrent
>>>> ibv_modify_qp()
>>>> transitioning the QP to ERROR can race in this window:
>>>>
>>>> siw_accept() ibv_modify_qp(ERROR)
>>>> ---------------------- ----------------------
>>>> siw_qp_modify() fails
>>>> up_write(&qp->state_lock)
>>>> down_write(&qp->state_lock)
>>>> nextstate_from_idle():
>>>> if (qp->cep)
>>>> siw_cep_put(qp->cep) <- frees cep
>>>> qp->cep = NULL
>>>> goto error
>>>> cep->qp = NULL <- UAF
>>>>
>>>> Clear qp->cep and cep->qp, and drop the association reference taken by
>>>> siw_cep_get(), all under the write lock held from the initial
>>>> down_write(&qp->state_lock). Thread B therefore sees qp->cep == NULL,
>>>> skips its own put, and cannot free the cep before siw_accept() is done
>>>> with it.
>>>>
>>>> Reported-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
>>>> Link:
>>>> https://lore.kernel.org/linux-rdma/d6fbe475-a5c2-f975-99b0-a0bd6b6d10e8@linux.dev/T/#m5876c1ff2de8686a9a1173b8f1aa0ff5363a785c
>>>> Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
>>>> ---
>>>> drivers/infiniband/sw/siw/siw_cm.c | 8 ++++++--
>>>> 1 file changed, 6 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/drivers/infiniband/sw/siw/siw_cm.c
>>>> b/drivers/infiniband/sw/siw/siw_cm.c
>>>> index 0245b25e7271..1573f2e888b2 100644
>>>> --- a/drivers/infiniband/sw/siw/siw_cm.c
>>>> +++ b/drivers/infiniband/sw/siw/siw_cm.c
>>>> @@ -1719,9 +1719,13 @@ int siw_accept(struct iw_cm_id *id, struct
>>>> iw_cm_conn_param *params)
>>>> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
>>>> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
>>>> SIW_QP_ATTR_MPA);
>>>> + if (rv) {
>>>> + cep->qp = NULL;
>>> This can better be omitted since done in error_unlock path
>>> anyway and is redundant otherwise.
>>
>> Right, thanks for the review! And probably call siw_cep_put before
>> set qp->cep to
>> NULL as other places did.
>>
>>> It would also better retain the logic of calling siw_qp_put(qp)
>>> right after
>>> clearing cep's reference to the qp, as done in error path.
>>
>> I suppose this change could be okay.
>>
>> @@ -1719,9 +1719,12 @@ int siw_accept(struct iw_cm_id *id, struct
>> iw_cm_conn_param *params)
>> SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
>> SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD |
>> SIW_QP_ATTR_MPA);
>> + if (rv) {
>> + siw_cep_put(cep);
>> + qp->cep = NULL;
>> + goto error_unlock;
>> + }
>> up_write(&qp->state_lock);
>> - if (rv)
>> - goto error;
>>
> That looks good, while I think we should always NULL a pointer to
> something before releasing a hold/reference to it. Putting the reference
> implies a memory barrier and so it's guaranteed others see that NULL
> as well.
Hmm, good point.
> You are right - there are places where this is not done as it should.
>
>> I am wondering if there is another use-after-free case in
>> siw_qp_cm_drop. Because
>> the beginning of siw_qp_cm_drop borrows the qp->cep pointer without
>> holding a
>> reference. If another thread put the last reference of cep, then
>> siw_qp_cm_drop
>> wakes and deferences cep which has been freed.
>>
> Let's put this in an extra thread. You may have a point ;)
I will dig a little bit more before start a new thread.
Thanks,
Guoqing
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2026-08-26 13:15 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-08-25 13:09 [PATCH] RDMA/siw: Clear association under lock if siw_qp_modify fails in siw_accept Guoqing Jiang
2026-08-25 13:53 ` Bernard Metzler
2026-08-26 6:38 ` Guoqing Jiang
2026-08-26 12:19 ` Bernard Metzler
2026-08-26 13:15 ` Guoqing Jiang
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.