[PATCH net] net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

[PATCH net] net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

[Nicolò Coccia]

A logic flaw in __smc_setsockopt() allows a local unprivileged user to
cause a Denial of Service (DoS) by holding the socket lock indefinitely.

The function __smc_setsockopt() calls copy_from_sockptr() while holding
lock_sock(sk). By passing a userfaultfd-monitored memory page (or
FUSE-backed memory on systems where unprivileged userfaultfd is disabled)
as the optval, an attacker can halt execution during the copy operation,
keeping the lock held.

Combined with asynchronous tear-down operations like shutdown(), this
exhausts the kernel wq (kworkers) and triggers the hung task watchdog.

[  240.123456] INFO: task kworker/u8:2 blocked for more than 120 seconds.
[  240.123489] Call Trace:
[  240.123501]  smc_shutdown+...
[  240.123512]  lock_sock_nested+...

This patch moves the user-space copy outside the lock_sock() critical
section to prevent the issue.

Fixes: a6a6fe27bab4 ("net/smc: Dynamic control handshake limitation by
socket options")
Signed-off-by: Nicolò Coccia <n.coccia96@gmail.com>
---
v1 -> v2:
 - Rebased against netdev/net tree
 - Added Fixes tag

 net/smc/af_smc.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 185dbed7de5d..da28652f6810 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3054,18 +3054,17 @@ static int __smc_setsockopt(struct socket
*sock, int level, int optname,

     smc = smc_sk(sk);

+    /* pre-fetch user data outside the lock */
+    if (optname == SMC_LIMIT_HS) {
+        if (optlen < sizeof(int))
+            return -EINVAL;
+        if (copy_from_sockptr(&val, optval, sizeof(int)))
+            return -EFAULT;
+    }
+
     lock_sock(sk);
     switch (optname) {
     case SMC_LIMIT_HS:
-        if (optlen < sizeof(int)) {
-            rc = -EINVAL;
-            break;
-        }
-        if (copy_from_sockptr(&val, optval, sizeof(int))) {
-            rc = -EFAULT;
-            break;
-        }
-
         smc->limit_smc_hs = !!val;
         rc = 0;
         break;
-- 
2.51.0

Re: [PATCH net] net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

[Dust Li]

On 2026-05-09 07:01:02, Nicolò Coccia wrote:
>A logic flaw in __smc_setsockopt() allows a local unprivileged user to
>cause a Denial of Service (DoS) by holding the socket lock indefinitely.
>
>The function __smc_setsockopt() calls copy_from_sockptr() while holding
>lock_sock(sk). By passing a userfaultfd-monitored memory page (or
>FUSE-backed memory on systems where unprivileged userfaultfd is disabled)
>as the optval, an attacker can halt execution during the copy operation,
>keeping the lock held.
>
>Combined with asynchronous tear-down operations like shutdown(), this
>exhausts the kernel wq (kworkers) and triggers the hung task watchdog.
>
>[  240.123456] INFO: task kworker/u8:2 blocked for more than 120 seconds.
>[  240.123489] Call Trace:
>[  240.123501]  smc_shutdown+...
>[  240.123512]  lock_sock_nested+...
>
>This patch moves the user-space copy outside the lock_sock() critical
>section to prevent the issue.
>
>Fixes: a6a6fe27bab4 ("net/smc: Dynamic control handshake limitation by
>socket options")
>Signed-off-by: Nicolò Coccia <n.coccia96@gmail.com>
>---
>v1 -> v2:
> - Rebased against netdev/net tree
> - Added Fixes tag
>
> net/smc/af_smc.c | 17 ++++++++---------
> 1 file changed, 8 insertions(+), 9 deletions(-)
>
>diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
>index 185dbed7de5d..da28652f6810 100644
>--- a/net/smc/af_smc.c
>+++ b/net/smc/af_smc.c
>@@ -3054,18 +3054,17 @@ static int __smc_setsockopt(struct socket
>*sock, int level, int optname,


Still not apply, have you changed this manually ?
You can produce the patch simply using `git format-patch `

Best regards,
Dust

[PATCH net] net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

[Nicolò Coccia]

A logic flaw in __smc_setsockopt() allows a local unprivileged user to
cause a Denial of Service (DoS) by holding the socket lock indefinitely.

The function __smc_setsockopt() calls copy_from_sockptr() while holding
lock_sock(sk). By passing a userfaultfd-monitored memory page (or
FUSE-backed memory on systems where unprivileged userfaultfd is disabled)
as the optval, an attacker can halt execution during the copy operation,
keeping the lock held.

Combined with asynchronous tear-down operations like shutdown(), this
exhausts the kernel wq (kworkers) and triggers the hung task watchdog.

[  240.123456] INFO: task kworker/u8:2 blocked for more than 120 seconds.
[  240.123489] Call Trace:
[  240.123501]  smc_shutdown+...
[  240.123512]  lock_sock_nested+...

This patch moves the user-space copy outside the lock_sock() critical
section to prevent the issue.

Signed-off-by: Nicolò Coccia nicolo.coccia@leonardo.com>
---
 net/smc/af_smc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -XXXX,X +XXXX,X @@ static int __smc_setsockopt(struct socket *sock,
int level, int optname,

  smc = smc_sk(sk);

+ /* pre-fetch user data outside the lock */
+ if (optname == SMC_LIMIT_HS) {
+ if (optlen < sizeof(int))
+ return -EINVAL;
+ if (copy_from_sockptr(&val, optval, sizeof(int)))
+ return -EFAULT;
+ }
+
  lock_sock(sk);
  switch (optname) {
  case SMC_LIMIT_HS:
- if (optlen < sizeof(int)) {
- rc = -EINVAL;
- break;
- }
- if (copy_from_sockptr(&val, optval, sizeof(int))) {
- rc = -EFAULT;
- break;
- }
-
  smc->limit_smc_hs = !!val;
  rc = 0;
  break;

Re: [PATCH net] net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

[Dust Li]

On 2026-05-08 21:33:10, Nicolò Coccia wrote:

Hi Nicolò,

This patch doesn't apply on net/main

>A logic flaw in __smc_setsockopt() allows a local unprivileged user to
>cause a Denial of Service (DoS) by holding the socket lock indefinitely.
>
>The function __smc_setsockopt() calls copy_from_sockptr() while holding
>lock_sock(sk). By passing a userfaultfd-monitored memory page (or
>FUSE-backed memory on systems where unprivileged userfaultfd is disabled)
>as the optval, an attacker can halt execution during the copy operation,
>keeping the lock held.
>
>Combined with asynchronous tear-down operations like shutdown(), this
>exhausts the kernel wq (kworkers) and triggers the hung task watchdog.
>
>[  240.123456] INFO: task kworker/u8:2 blocked for more than 120 seconds.
>[  240.123489] Call Trace:
>[  240.123501]  smc_shutdown+...
>[  240.123512]  lock_sock_nested+...
>
>This patch moves the user-space copy outside the lock_sock() critical
>section to prevent the issue.
>

You should add a Fixes tag here.
>Signed-off-by: Nicolò Coccia nicolo.coccia@leonardo.com>
>---
> net/smc/af_smc.c | 16 ++++++++--------
> 1 file changed, 8 insertions(+), 8 deletions(-)
>
>diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
>--- a/net/smc/af_smc.c
>+++ b/net/smc/af_smc.c
>@@ -XXXX,X +XXXX,X @@ static int __smc_setsockopt(struct socket *sock,
>int level, int optname,
>
>  smc = smc_sk(sk);
>
>+ /* pre-fetch user data outside the lock */
>+ if (optname == SMC_LIMIT_HS) {
>+ if (optlen < sizeof(int))
>+ return -EINVAL;
>+ if (copy_from_sockptr(&val, optval, sizeof(int)))
>+ return -EFAULT;
>+ }
>+
>  lock_sock(sk);
>  switch (optname) {
>  case SMC_LIMIT_HS:
>- if (optlen < sizeof(int)) {
>- rc = -EINVAL;
>- break;
>- }
>- if (copy_from_sockptr(&val, optval, sizeof(int))) {
>- rc = -EFAULT;
>- break;
>- }
>-

The indenting is all messed up

Best regards,
Dust