smc_pnet_find_smcd() returns an smcd device pointer and releases the
lock, then smc_pnet_apply_smcd() is called to use this pointer. The
device could be removed between these two calls, leading to a potential
use-after-free when accessing the freed smcd pointer.

    CPU 0                           CPU 1
    ----                            ----
    smc_pnet_add_ib()
      smcd = smc_pnet_find_smcd()
        mutex_lock(&smcd_dev_list.mutex)
        list_for_each_entry() ...
        mutex_unlock(&smcd_dev_list.mutex)
                                    smcd_unregister_dev()
                                      mutex_lock(&smcd_dev_list.mutex)
                                      list_del_init(&smcd->list)
                                      mutex_unlock(&smcd_dev_list.mutex)
                                      kfree(smcd)
      smc_pnet_apply_smcd(smcd)
        smcd->pnetid                   <- UAF (smcd already freed)

Fix this by introducing smc_pnet_find_smcd_apply() which performs both
find and apply under the same lock, preventing the device from being
removed in between.

Also refactor smc_pnet_apply_smcd() into __smc_pnet_apply_smcd()
(without lock) and smc_pnet_apply_smcd() (with lock) for reuse.

Fixes: 69baaac9361e ("dibs: Define dibs_client_ops and dibs_dev_ops")
Signed-off-by: Li Xiasong <lixiasong1@huawei.com>
---
 net/smc/smc_pnet.c | 58 ++++++++++++++++++++++++++++------------------
 1 file changed, 36 insertions(+), 22 deletions(-)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 91c0b1c473b2..a1603740167b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -270,16 +270,22 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port,
 
 /* Apply pnetid to smcd device when no pnetid is set.
  */
-static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name)
+static bool __smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name)
 {
-	bool applied = false;
-
-	mutex_lock(&smcd_dev_list.mutex);
 	if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) {
 		memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN);
 		smcd_dev->pnetid_by_user = true;
-		applied = true;
+		return true;
 	}
+	return false;
+}
+
+static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name)
+{
+	bool applied;
+
+	mutex_lock(&smcd_dev_list.mutex);
+	applied = __smc_pnet_apply_smcd(smcd_dev, pnet_name);
 	mutex_unlock(&smcd_dev_list.mutex);
 	return applied;
 }
@@ -351,23 +357,39 @@ static bool smc_pnet_find_ib_apply(char *ib_name, u8 ib_port, char *pnet_name)
 }
 
 /* Find an smcd device by a given name. The device might not exist. */
-static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name)
+static struct smcd_dev *__smc_pnet_find_smcd(char *smcd_name)
 {
 	struct smcd_dev *smcd_dev;
 
-	mutex_lock(&smcd_dev_list.mutex);
 	list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
 		if (!strncmp(dev_name(&smcd_dev->dibs->dev), smcd_name,
 			     IB_DEVICE_NAME_MAX - 1) ||
 		    (smcd_dev->dibs->dev.parent &&
 		     !strncmp(dev_name(smcd_dev->dibs->dev.parent), smcd_name,
 			      IB_DEVICE_NAME_MAX - 1)))
-			goto out;
+			return smcd_dev;
+	}
+	return NULL;
+}
+
+/* Find an smcd device by name and apply pnetid under lock. */
+static bool smc_pnet_find_smcd_apply(char *smcd_name, char *pnet_name)
+{
+	struct smcd_dev *smcd_dev;
+	bool rc = true;
+
+	mutex_lock(&smcd_dev_list.mutex);
+	smcd_dev = __smc_pnet_find_smcd(smcd_name);
+	if (smcd_dev) {
+		if (!__smc_pnet_apply_smcd(smcd_dev, pnet_name))
+			rc = false;
+		else
+			pr_warn_ratelimited("smc: smcd device %s applied user defined pnetid %.16s\n",
+					    dev_name(&smcd_dev->dibs->dev),
+					    smcd_dev->pnetid);
 	}
-	smcd_dev = NULL;
-out:
 	mutex_unlock(&smcd_dev_list.mutex);
-	return smcd_dev;
+	return rc;
 }
 
 static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net,
@@ -437,22 +459,14 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name,
 			   u8 ib_port, char *pnet_name)
 {
 	struct smc_pnetentry *tmp_pe, *new_pe;
-	bool smcddev_applied = true;
+	bool smcddev_applied;
 	bool ibdev_applied;
-	struct smcd_dev *smcd;
 	bool new_ibdev;
 
 	/* try to apply the pnetid to active devices */
 	ibdev_applied = smc_pnet_find_ib_apply(ib_name, ib_port, pnet_name);
-	smcd = smc_pnet_find_smcd(ib_name);
-	if (smcd) {
-		smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name);
-		if (smcddev_applied) {
-			pr_warn_ratelimited("smc: smcd device %s applied user defined pnetid %.16s\n",
-					    dev_name(&smcd->dibs->dev),
-					    smcd->pnetid);
-		}
-	}
+	smcddev_applied = smc_pnet_find_smcd_apply(ib_name, pnet_name);
+
 	/* Apply fails when a device has a hardware-defined pnetid set, do not
 	 * add a pnet table entry in that case.
 	 */
-- 
2.34.1

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
---
net/smc: fix potential UAF in smc_pnet_add_ib for smcd device

This commit fixes a potential use-after-free when accessing an smcd device
in smc_pnet_add_ib(). It resolves the issue by combining the lookup and
apply operations into a single function that holds the smcd_dev_list.mutex
for the duration of both operations.

> diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
> index 91c0b1c473b2..a1603740167b 100644
> --- a/net/smc/smc_pnet.c
> +++ b/net/smc/smc_pnet.c

[ ... ]

> @@ -351,23 +357,39 @@ static bool smc_pnet_find_ib_apply(char *ib_name, u8 ib_port, char *pnet_name)
>  }
>  
>  /* Find an smcd device by a given name. The device might not exist. */
> -static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name)
> +static struct smcd_dev *__smc_pnet_find_smcd(char *smcd_name)
>  {
>  	struct smcd_dev *smcd_dev;
>  
> -	mutex_lock(&smcd_dev_list.mutex);
>  	list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
>  		if (!strncmp(dev_name(&smcd_dev->dibs->dev), smcd_name,
>  			     IB_DEVICE_NAME_MAX - 1) ||
>  		    (smcd_dev->dibs->dev.parent &&
>  		     !strncmp(dev_name(smcd_dev->dibs->dev.parent), smcd_name,
>  			      IB_DEVICE_NAME_MAX - 1)))
> -			goto out;
> +			return smcd_dev;
> +	}
> +	return NULL;
> +}
> +
> +/* Find an smcd device by name and apply pnetid under lock. */
> +static bool smc_pnet_find_smcd_apply(char *smcd_name, char *pnet_name)
> +{
> +	struct smcd_dev *smcd_dev;
> +	bool rc = true;
> +
> +	mutex_lock(&smcd_dev_list.mutex);
> +	smcd_dev = __smc_pnet_find_smcd(smcd_name);
> +	if (smcd_dev) {
> +		if (!__smc_pnet_apply_smcd(smcd_dev, pnet_name))

While this prevents the use-after-free in smc_pnet_add_ib() by expanding the
mutex coverage, does the same vulnerability pattern still exist in the
connection handshake paths?

Neither struct smcd_dev nor struct smc_ib_device appear to use reference
counting. During a connection handshake, functions like
smc_pnet_find_ism_resource() and _smc_pnet_find_roce_by_pnetid() find a
device under the mutex, store the raw pointer (e.g., into ini->ism_dev[0]),
and immediately release the mutex.

If a concurrent hot-unplug event triggers smcd_unregister_dev() or
smc_ib_remove_dev() while the handshake process is accessing the device
without holding a lock or reference, could it lead to another use-after-free?

Would a more complete fix require introducing reference counting for both
device structures to ensure they remain valid while pointed to by the
handshake structures?

> +			rc = false;
> +		else
> +			pr_warn_ratelimited("smc: smcd device %s applied user defined pnetid %.16s\n",
> +					    dev_name(&smcd_dev->dibs->dev),
> +					    smcd_dev->pnetid);
>  	}
> -	smcd_dev = NULL;
> -out:
>  	mutex_unlock(&smcd_dev_list.mutex);
> -	return smcd_dev;
> +	return rc;
>  }