Dan Carpenter spotted a race condition in a couple of situations like
these in the test_firmware driver:
static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
{
u8 val;
int ret;
ret = kstrtou8(buf, 10, &val);
if (ret)
return ret;
mutex_lock(&test_fw_mutex);
*(u8 *)cfg = val;
mutex_unlock(&test_fw_mutex);
/* Always return full write size even if we didn't consume all */
return size;
}
static ssize_t config_num_requests_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
int rc;
mutex_lock(&test_fw_mutex);
if (test_fw_config->reqs) {
pr_err("Must call release_all_firmware prior to changing config\n");
rc = -EINVAL;
mutex_unlock(&test_fw_mutex);
goto out;
}
mutex_unlock(&test_fw_mutex);
rc = test_dev_config_update_u8(buf, count,
&test_fw_config->num_requests);
out:
return rc;
}
static ssize_t config_read_fw_idx_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
return test_dev_config_update_u8(buf, count,
&test_fw_config->read_fw_idx);
}
The function test_dev_config_update_u8() is called from both the locked
and the unlocked context, function config_num_requests_store() and
config_read_fw_idx_store() which can both be called asynchronously as
they are driver's methods, while test_dev_config_update_u8() and siblings
change their argument pointed to by u8 *cfg or similar pointer.
To avoid deadlock on test_fw_mutex, the lock is dropped before calling
test_dev_config_update_u8() and re-acquired within test_dev_config_update_u8()
itself, but alas this creates a race condition.
Having two locks wouldn't assure a race-proof mutual exclusion.
This situation is best avoided by the introduction of a new, unlocked
function __test_dev_config_update_u8() which can be called from the locked
context and reducing test_dev_config_update_u8() to:
static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
{
int ret;
mutex_lock(&test_fw_mutex);
ret = __test_dev_config_update_u8(buf, size, cfg);
mutex_unlock(&test_fw_mutex);
return ret;
}
doing the locking and calling the unlocked primitive, which enables both
locked and unlocked versions without duplication of code.
The similar approach was applied to all functions called from the locked
and the unlocked context, which safely mitigates both deadlocks and race
conditions in the driver.
__test_dev_config_update_bool(), __test_dev_config_update_u8() and
__test_dev_config_update_size_t() unlocked versions of the functions
were introduced to be called from the locked contexts as a workaround
without releasing the main driver's lock and thereof causing a race
condition.
The test_dev_config_update_bool(), test_dev_config_update_u8() and
test_dev_config_update_size_t() locked versions of the functions
are being called from driver methods without the unnecessary multiplying
of the locking and unlocking code for each method, and complicating
the code with saving of the return value across lock.
Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf")
Cc: Luis Chamberlain <mcgrof(a)kernel.org>
Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Cc: Russ Weight <russell.h.weight(a)intel.com>
Cc: Takashi Iwai <tiwai(a)suse.de>
Cc: Tianfei Zhang <tianfei.zhang(a)intel.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Colin Ian King <colin.i.king(a)gmail.com>
Cc: Randy Dunlap <rdunlap(a)infradead.org>
Cc: linux-kselftest(a)vger.kernel.org
Cc: stable(a)vger.kernel.org # v5.4
Suggested-by: Dan Carpenter <error27(a)gmail.com>
Signed-off-by: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr>
---
lib/test_firmware.c | 52 ++++++++++++++++++++++++++++++---------------
1 file changed, 35 insertions(+), 17 deletions(-)
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 05ed84c2fc4c..35417e0af3f4 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -353,16 +353,26 @@ static ssize_t config_test_show_str(char *dst,
return len;
}
-static int test_dev_config_update_bool(const char *buf, size_t size,
+static inline int __test_dev_config_update_bool(const char *buf, size_t size,
bool *cfg)
{
int ret;
- mutex_lock(&test_fw_mutex);
if (kstrtobool(buf, cfg) < 0)
ret = -EINVAL;
else
ret = size;
+
+ return ret;
+}
+
+static int test_dev_config_update_bool(const char *buf, size_t size,
+ bool *cfg)
+{
+ int ret;
+
+ mutex_lock(&test_fw_mutex);
+ ret = __test_dev_config_update_bool(buf, size, cfg);
mutex_unlock(&test_fw_mutex);
return ret;
@@ -373,7 +383,8 @@ static ssize_t test_dev_config_show_bool(char *buf, bool val)
return snprintf(buf, PAGE_SIZE, "%d\n", val);
}
-static int test_dev_config_update_size_t(const char *buf,
+static int __test_dev_config_update_size_t(
+ const char *buf,
size_t size,
size_t *cfg)
{
@@ -384,9 +395,7 @@ static int test_dev_config_update_size_t(const char *buf,
if (ret)
return ret;
- mutex_lock(&test_fw_mutex);
*(size_t *)cfg = new;
- mutex_unlock(&test_fw_mutex);
/* Always return full write size even if we didn't consume all */
return size;
@@ -402,7 +411,7 @@ static ssize_t test_dev_config_show_int(char *buf, int val)
return snprintf(buf, PAGE_SIZE, "%d\n", val);
}
-static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
+static int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
{
u8 val;
int ret;
@@ -411,14 +420,23 @@ static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
if (ret)
return ret;
- mutex_lock(&test_fw_mutex);
*(u8 *)cfg = val;
- mutex_unlock(&test_fw_mutex);
/* Always return full write size even if we didn't consume all */
return size;
}
+static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
+{
+ int ret;
+
+ mutex_lock(&test_fw_mutex);
+ ret = __test_dev_config_update_u8(buf, size, cfg);
+ mutex_unlock(&test_fw_mutex);
+
+ return ret;
+}
+
static ssize_t test_dev_config_show_u8(char *buf, u8 val)
{
return snprintf(buf, PAGE_SIZE, "%u\n", val);
@@ -471,10 +489,10 @@ static ssize_t config_num_requests_store(struct device *dev,
mutex_unlock(&test_fw_mutex);
goto out;
}
- mutex_unlock(&test_fw_mutex);
- rc = test_dev_config_update_u8(buf, count,
- &test_fw_config->num_requests);
+ rc = __test_dev_config_update_u8(buf, count,
+ &test_fw_config->num_requests);
+ mutex_unlock(&test_fw_mutex);
out:
return rc;
@@ -518,10 +536,10 @@ static ssize_t config_buf_size_store(struct device *dev,
mutex_unlock(&test_fw_mutex);
goto out;
}
- mutex_unlock(&test_fw_mutex);
- rc = test_dev_config_update_size_t(buf, count,
- &test_fw_config->buf_size);
+ rc = __test_dev_config_update_size_t(buf, count,
+ &test_fw_config->buf_size);
+ mutex_unlock(&test_fw_mutex);
out:
return rc;
@@ -548,10 +566,10 @@ static ssize_t config_file_offset_store(struct device *dev,
mutex_unlock(&test_fw_mutex);
goto out;
}
- mutex_unlock(&test_fw_mutex);
- rc = test_dev_config_update_size_t(buf, count,
- &test_fw_config->file_offset);
+ rc = __test_dev_config_update_size_t(buf, count,
+ &test_fw_config->file_offset);
+ mutex_unlock(&test_fw_mutex);
out:
return rc;
--
2.30.2
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052637-smudge-shucking-ac36@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
91d0b78c5177 ("inet: Add IP_LOCAL_PORT_RANGE socket option")
28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
d2c135619cb8 ("inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict()")
ca7af0402550 ("tcp: add small random increments to the source port")
ffa84b5ffb37 ("net: add netns refcount tracker to struct sock")
938cca9e4109 ("sock: fix /proc/net/sockstat underflow in sk_clone_lock()")
990c74e3f41d ("memcg: enable accounting for inet_bin_bucket cache")
333bb73f620e ("tcp: Keep TCP_CLOSE sockets in the reuseport group.")
5c040eaf5d17 ("tcp: Add num_closed_socks to struct sock_reuseport.")
c579bd1b4021 ("tcp: add some entropy in __inet_hash_connect()")
190cc82489f4 ("tcp: change source port randomizarion at connect() time")
bbc20b70424a ("net: reduce indentation level in sk_clone_lock()")
62ffc589abb1 ("net: refactor bind_bucket fastreuse into helper")
47ec5303d73e ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Date: Mon, 22 May 2023 14:08:20 +0200
Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol
With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.
For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.
For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable(a)vger.kernel.org
Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
diff --git a/include/net/ip.h b/include/net/ip.h
index c3fffaa92d6e..acec504c469a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
+ __u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
+ ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 4b7f2df66b99..e682ab628dfa 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -163,6 +163,7 @@ struct in_addr {
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7d0adb612bdd..44ee7a2e72ac 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052636-scrounger-dirtiness-37d2@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
91d0b78c5177 ("inet: Add IP_LOCAL_PORT_RANGE socket option")
28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
d2c135619cb8 ("inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict()")
ca7af0402550 ("tcp: add small random increments to the source port")
ffa84b5ffb37 ("net: add netns refcount tracker to struct sock")
938cca9e4109 ("sock: fix /proc/net/sockstat underflow in sk_clone_lock()")
990c74e3f41d ("memcg: enable accounting for inet_bin_bucket cache")
333bb73f620e ("tcp: Keep TCP_CLOSE sockets in the reuseport group.")
5c040eaf5d17 ("tcp: Add num_closed_socks to struct sock_reuseport.")
c579bd1b4021 ("tcp: add some entropy in __inet_hash_connect()")
190cc82489f4 ("tcp: change source port randomizarion at connect() time")
bbc20b70424a ("net: reduce indentation level in sk_clone_lock()")
62ffc589abb1 ("net: refactor bind_bucket fastreuse into helper")
47ec5303d73e ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Date: Mon, 22 May 2023 14:08:20 +0200
Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol
With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.
For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.
For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable(a)vger.kernel.org
Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
diff --git a/include/net/ip.h b/include/net/ip.h
index c3fffaa92d6e..acec504c469a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
+ __u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
+ ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 4b7f2df66b99..e682ab628dfa 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -163,6 +163,7 @@ struct in_addr {
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7d0adb612bdd..44ee7a2e72ac 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052635-styling-unbutton-ac91@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
91d0b78c5177 ("inet: Add IP_LOCAL_PORT_RANGE socket option")
28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
d2c135619cb8 ("inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict()")
ca7af0402550 ("tcp: add small random increments to the source port")
ffa84b5ffb37 ("net: add netns refcount tracker to struct sock")
938cca9e4109 ("sock: fix /proc/net/sockstat underflow in sk_clone_lock()")
990c74e3f41d ("memcg: enable accounting for inet_bin_bucket cache")
333bb73f620e ("tcp: Keep TCP_CLOSE sockets in the reuseport group.")
5c040eaf5d17 ("tcp: Add num_closed_socks to struct sock_reuseport.")
c579bd1b4021 ("tcp: add some entropy in __inet_hash_connect()")
190cc82489f4 ("tcp: change source port randomizarion at connect() time")
bbc20b70424a ("net: reduce indentation level in sk_clone_lock()")
62ffc589abb1 ("net: refactor bind_bucket fastreuse into helper")
47ec5303d73e ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Date: Mon, 22 May 2023 14:08:20 +0200
Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol
With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.
For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.
For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable(a)vger.kernel.org
Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
diff --git a/include/net/ip.h b/include/net/ip.h
index c3fffaa92d6e..acec504c469a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
+ __u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
+ ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 4b7f2df66b99..e682ab628dfa 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -163,6 +163,7 @@ struct in_addr {
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7d0adb612bdd..44ee7a2e72ac 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052634-surgical-sulfite-a551@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
91d0b78c5177 ("inet: Add IP_LOCAL_PORT_RANGE socket option")
28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
d2c135619cb8 ("inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict()")
ca7af0402550 ("tcp: add small random increments to the source port")
ffa84b5ffb37 ("net: add netns refcount tracker to struct sock")
938cca9e4109 ("sock: fix /proc/net/sockstat underflow in sk_clone_lock()")
990c74e3f41d ("memcg: enable accounting for inet_bin_bucket cache")
333bb73f620e ("tcp: Keep TCP_CLOSE sockets in the reuseport group.")
5c040eaf5d17 ("tcp: Add num_closed_socks to struct sock_reuseport.")
c579bd1b4021 ("tcp: add some entropy in __inet_hash_connect()")
190cc82489f4 ("tcp: change source port randomizarion at connect() time")
bbc20b70424a ("net: reduce indentation level in sk_clone_lock()")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Date: Mon, 22 May 2023 14:08:20 +0200
Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol
With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.
For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.
For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable(a)vger.kernel.org
Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
diff --git a/include/net/ip.h b/include/net/ip.h
index c3fffaa92d6e..acec504c469a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
+ __u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
+ ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 4b7f2df66b99..e682ab628dfa 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -163,6 +163,7 @@ struct in_addr {
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7d0adb612bdd..44ee7a2e72ac 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052623-available-vagueness-5c1e@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Date: Mon, 22 May 2023 14:08:20 +0200
Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol
With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.
For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.
For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable(a)vger.kernel.org
Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
diff --git a/include/net/ip.h b/include/net/ip.h
index c3fffaa92d6e..acec504c469a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
+ __u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
+ ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 4b7f2df66b99..e682ab628dfa 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -163,6 +163,7 @@ struct in_addr {
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7d0adb612bdd..44ee7a2e72ac 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 7e01c7f7046efc2c7c192c3619db43292b98e997
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052621-karaoke-try-d2ba@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
7e01c7f7046e ("net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize")
2be6d4d16a08 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
0fa81b304a79 ("cdc_ncm: Implement the 32-bit version of NCM Transfer Block")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7e01c7f7046efc2c7c192c3619db43292b98e997 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Date: Wed, 17 May 2023 13:38:08 +0000
Subject: [PATCH] net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize
Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than
the calculated "min" value, but greater than zero, the logic sets
tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in
cdc_ncm_fill_tx_frame() where all the data is handled.
For small values of dwNtbOutMaxSize the memory allocated during
alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to
how size is aligned at alloc time:
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
Thus we hit the same bug that we tried to squash with
commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
Low values of dwNtbOutMaxSize do not cause an issue presently because at
alloc_skb() time more memory (512b) is allocated than required for the
SKB headers alone (320b), leaving some space (512b - 320b = 192b)
for CDC data (172b).
However, if more elements (for example 3 x u64 = [24b]) were added to
one of the SKB header structs, say 'struct skb_shared_info',
increasing its original size (320b [320b aligned]) to something larger
(344b [384b aligned]), then suddenly the CDC data (172b) no longer
fits in the spare SKB data area (512b - 384b = 128b).
Consequently the SKB bounds checking semantics fails and panics:
skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:113!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023
Workqueue: mld mld_ifc_work
RIP: 0010:skb_panic net/core/skbuff.c:113 [inline]
RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118
[snip]
Call Trace:
<TASK>
skb_put+0x151/0x210 net/core/skbuff.c:2047
skb_put_zero include/linux/skbuff.h:2422 [inline]
cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline]
cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308
cdc_ncm_tx_fixup+0xa3/0x100
Deal with too low values of dwNtbOutMaxSize, clamp it in the range
[USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure
enough data space is allocated to handle CDC data by making sure
dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE.
Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning")
Cc: stable(a)vger.kernel.org
Reported-by: syzbot+9f575a1f15fc0c01ed69(a)syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d
Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/
Signed-off-by: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Reviewed-by: Simon Horman <simon.horman(a)corigine.com>
Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 6ce8f4f0c70e..db05622f1f70 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -181,9 +181,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
else
min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
- max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
- if (max == 0)
+ if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0)
max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
+ else
+ max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize),
+ USB_CDC_NCM_NTB_MIN_OUT_SIZE,
+ CDC_NCM_NTB_MAX_SIZE_TX);
/* some devices set dwNtbOutMaxSize too low for the above default */
min = min(min, max);
@@ -1244,6 +1247,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
* further.
*/
if (skb_out == NULL) {
+ /* If even the smallest allocation fails, abort. */
+ if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE)
+ goto alloc_failed;
ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1,
(unsigned)CDC_NCM_LOW_MEM_MAX_CNT);
ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt;
@@ -1262,13 +1268,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC);
/* No allocation possible so we will abort */
- if (skb_out == NULL) {
- if (skb != NULL) {
- dev_kfree_skb_any(skb);
- dev->net->stats.tx_dropped++;
- }
- goto exit_no_skb;
- }
+ if (!skb_out)
+ goto alloc_failed;
ctx->tx_low_mem_val--;
}
if (ctx->is_ndp16) {
@@ -1461,6 +1462,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
return skb_out;
+alloc_failed:
+ if (skb) {
+ dev_kfree_skb_any(skb);
+ dev->net->stats.tx_dropped++;
+ }
exit_no_skb:
/* Start timer, if there is a remaining non-empty skb */
if (ctx->tx_curr_skb != NULL && n > 0)
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 003fb0a51162d940f25fc35e70b0996a12c9e08a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052611-wrangle-clock-fb09@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
003fb0a51162 ("mmc: block: ensure error propagation for non-blk")
b84ba30b6c7a ("block: remove the gendisk argument to blk_execute_rq")
4054cff92c35 ("block: remove blk-exec.c")
0bf6d96cb829 ("block: remove blk_{get,put}_request")
4abafdc4360d ("block: remove the initialize_rq_fn blk_mq_ops method")
68ec3b819a5d ("scsi: add a scsi_alloc_request helper")
5a72e899ceb4 ("block: add a struct io_comp_batch argument to fops->iopoll()")
013a7f954381 ("block: provide helpers for rq_list manipulation")
afd7de03c526 ("block: remove some blk_mq_hw_ctx debugfs entries")
3e08773c3841 ("block: switch polling to be bio based")
6ce913fe3eee ("block: rename REQ_HIPRI to REQ_POLLED")
d729cf9acb93 ("io_uring: don't sleep when polling for I/O")
ef99b2d37666 ("block: replace the spin argument to blk_iopoll with a flags argument")
28a1ae6b9dab ("blk-mq: remove blk_qc_t_valid")
efbabbe121f9 ("blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal")
c6699d6fe0ff ("blk-mq: factor out a "classic" poll helper")
f70299f0d58e ("blk-mq: factor out a blk_qc_to_hctx helper")
71fc3f5e2c00 ("block: don't try to poll multi-bio I/Os in __blkdev_direct_IO")
349302da8352 ("block: improve batched tag allocation")
0f38d7664615 ("blk-mq: cleanup blk_mq_submit_bio")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 003fb0a51162d940f25fc35e70b0996a12c9e08a Mon Sep 17 00:00:00 2001
From: Christian Loehle <CLoehle(a)hyperstone.com>
Date: Wed, 26 Apr 2023 16:59:39 +0000
Subject: [PATCH] mmc: block: ensure error propagation for non-blk
Requests to the mmc layer usually come through a block device IO.
The exceptions are the ioctl interface, RPMB chardev ioctl
and debugfs, which issue their own blk_mq requests through
blk_execute_rq and do not query the BLK_STS error but the
mmcblk-internal drv_op_result. This patch ensures that drv_op_result
defaults to an error and has to be overwritten by the operation
to be considered successful.
The behavior leads to a bug where the request never propagates
the error, e.g. by directly erroring out at mmc_blk_mq_issue_rq if
mmc_blk_part_switch fails. The ioctl caller of the rpmb chardev then
can never see an error (BLK_STS_IOERR, but drv_op_result is unchanged)
and thus may assume that their call executed successfully when it did not.
While always checking the blk_execute_rq return value would be
advised, let's eliminate the error by always setting
drv_op_result as -EIO to be overwritten on success (or other error)
Fixes: 614f0388f580 ("mmc: block: move single ioctl() commands to block requests")
Signed-off-by: Christian Loehle <cloehle(a)hyperstone.com>
Acked-by: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/59c17ada35664b818b7bd83752119b2d@hyperstone.com
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 00c33edb9fb9..d920c4178389 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
goto out_put;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
blk_mq_free_request(req);
@@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
idatas[0] = idata;
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idatas;
req_to_mmc_queue_req(req)->ioc_count = 1;
blk_execute_rq(req, false);
@@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
}
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idata;
req_to_mmc_queue_req(req)->ioc_count = n;
blk_execute_rq(req, false);
@@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
if (IS_ERR(req))
return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
if (ret >= 0) {
@@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
goto out_free;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
blk_execute_rq(req, false);
err = req_to_mmc_queue_req(req)->drv_op_result;
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 003fb0a51162d940f25fc35e70b0996a12c9e08a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052610-deluxe-amuck-9628@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
003fb0a51162 ("mmc: block: ensure error propagation for non-blk")
b84ba30b6c7a ("block: remove the gendisk argument to blk_execute_rq")
4054cff92c35 ("block: remove blk-exec.c")
0bf6d96cb829 ("block: remove blk_{get,put}_request")
4abafdc4360d ("block: remove the initialize_rq_fn blk_mq_ops method")
68ec3b819a5d ("scsi: add a scsi_alloc_request helper")
5a72e899ceb4 ("block: add a struct io_comp_batch argument to fops->iopoll()")
013a7f954381 ("block: provide helpers for rq_list manipulation")
afd7de03c526 ("block: remove some blk_mq_hw_ctx debugfs entries")
3e08773c3841 ("block: switch polling to be bio based")
6ce913fe3eee ("block: rename REQ_HIPRI to REQ_POLLED")
d729cf9acb93 ("io_uring: don't sleep when polling for I/O")
ef99b2d37666 ("block: replace the spin argument to blk_iopoll with a flags argument")
28a1ae6b9dab ("blk-mq: remove blk_qc_t_valid")
efbabbe121f9 ("blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal")
c6699d6fe0ff ("blk-mq: factor out a "classic" poll helper")
f70299f0d58e ("blk-mq: factor out a blk_qc_to_hctx helper")
71fc3f5e2c00 ("block: don't try to poll multi-bio I/Os in __blkdev_direct_IO")
349302da8352 ("block: improve batched tag allocation")
0f38d7664615 ("blk-mq: cleanup blk_mq_submit_bio")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 003fb0a51162d940f25fc35e70b0996a12c9e08a Mon Sep 17 00:00:00 2001
From: Christian Loehle <CLoehle(a)hyperstone.com>
Date: Wed, 26 Apr 2023 16:59:39 +0000
Subject: [PATCH] mmc: block: ensure error propagation for non-blk
Requests to the mmc layer usually come through a block device IO.
The exceptions are the ioctl interface, RPMB chardev ioctl
and debugfs, which issue their own blk_mq requests through
blk_execute_rq and do not query the BLK_STS error but the
mmcblk-internal drv_op_result. This patch ensures that drv_op_result
defaults to an error and has to be overwritten by the operation
to be considered successful.
The behavior leads to a bug where the request never propagates
the error, e.g. by directly erroring out at mmc_blk_mq_issue_rq if
mmc_blk_part_switch fails. The ioctl caller of the rpmb chardev then
can never see an error (BLK_STS_IOERR, but drv_op_result is unchanged)
and thus may assume that their call executed successfully when it did not.
While always checking the blk_execute_rq return value would be
advised, let's eliminate the error by always setting
drv_op_result as -EIO to be overwritten on success (or other error)
Fixes: 614f0388f580 ("mmc: block: move single ioctl() commands to block requests")
Signed-off-by: Christian Loehle <cloehle(a)hyperstone.com>
Acked-by: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/59c17ada35664b818b7bd83752119b2d@hyperstone.com
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 00c33edb9fb9..d920c4178389 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
goto out_put;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
blk_mq_free_request(req);
@@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
idatas[0] = idata;
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idatas;
req_to_mmc_queue_req(req)->ioc_count = 1;
blk_execute_rq(req, false);
@@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
}
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idata;
req_to_mmc_queue_req(req)->ioc_count = n;
blk_execute_rq(req, false);
@@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
if (IS_ERR(req))
return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
if (ret >= 0) {
@@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
goto out_free;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
blk_execute_rq(req, false);
err = req_to_mmc_queue_req(req)->drv_op_result;
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 003fb0a51162d940f25fc35e70b0996a12c9e08a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052609-regulator-registry-2991@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
003fb0a51162 ("mmc: block: ensure error propagation for non-blk")
b84ba30b6c7a ("block: remove the gendisk argument to blk_execute_rq")
4054cff92c35 ("block: remove blk-exec.c")
0bf6d96cb829 ("block: remove blk_{get,put}_request")
4abafdc4360d ("block: remove the initialize_rq_fn blk_mq_ops method")
68ec3b819a5d ("scsi: add a scsi_alloc_request helper")
5a72e899ceb4 ("block: add a struct io_comp_batch argument to fops->iopoll()")
013a7f954381 ("block: provide helpers for rq_list manipulation")
afd7de03c526 ("block: remove some blk_mq_hw_ctx debugfs entries")
3e08773c3841 ("block: switch polling to be bio based")
6ce913fe3eee ("block: rename REQ_HIPRI to REQ_POLLED")
d729cf9acb93 ("io_uring: don't sleep when polling for I/O")
ef99b2d37666 ("block: replace the spin argument to blk_iopoll with a flags argument")
28a1ae6b9dab ("blk-mq: remove blk_qc_t_valid")
efbabbe121f9 ("blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal")
c6699d6fe0ff ("blk-mq: factor out a "classic" poll helper")
f70299f0d58e ("blk-mq: factor out a blk_qc_to_hctx helper")
71fc3f5e2c00 ("block: don't try to poll multi-bio I/Os in __blkdev_direct_IO")
349302da8352 ("block: improve batched tag allocation")
0f38d7664615 ("blk-mq: cleanup blk_mq_submit_bio")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 003fb0a51162d940f25fc35e70b0996a12c9e08a Mon Sep 17 00:00:00 2001
From: Christian Loehle <CLoehle(a)hyperstone.com>
Date: Wed, 26 Apr 2023 16:59:39 +0000
Subject: [PATCH] mmc: block: ensure error propagation for non-blk
Requests to the mmc layer usually come through a block device IO.
The exceptions are the ioctl interface, RPMB chardev ioctl
and debugfs, which issue their own blk_mq requests through
blk_execute_rq and do not query the BLK_STS error but the
mmcblk-internal drv_op_result. This patch ensures that drv_op_result
defaults to an error and has to be overwritten by the operation
to be considered successful.
The behavior leads to a bug where the request never propagates
the error, e.g. by directly erroring out at mmc_blk_mq_issue_rq if
mmc_blk_part_switch fails. The ioctl caller of the rpmb chardev then
can never see an error (BLK_STS_IOERR, but drv_op_result is unchanged)
and thus may assume that their call executed successfully when it did not.
While always checking the blk_execute_rq return value would be
advised, let's eliminate the error by always setting
drv_op_result as -EIO to be overwritten on success (or other error)
Fixes: 614f0388f580 ("mmc: block: move single ioctl() commands to block requests")
Signed-off-by: Christian Loehle <cloehle(a)hyperstone.com>
Acked-by: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/59c17ada35664b818b7bd83752119b2d@hyperstone.com
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 00c33edb9fb9..d920c4178389 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
goto out_put;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
blk_mq_free_request(req);
@@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
idatas[0] = idata;
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idatas;
req_to_mmc_queue_req(req)->ioc_count = 1;
blk_execute_rq(req, false);
@@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
}
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = idata;
req_to_mmc_queue_req(req)->ioc_count = n;
blk_execute_rq(req, false);
@@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
if (IS_ERR(req))
return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
blk_execute_rq(req, false);
ret = req_to_mmc_queue_req(req)->drv_op_result;
if (ret >= 0) {
@@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
goto out_free;
}
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD;
+ req_to_mmc_queue_req(req)->drv_op_result = -EIO;
req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
blk_execute_rq(req, false);
err = req_to_mmc_queue_req(req)->drv_op_result;