udp: Update reuse->has_conns under reuseport_lock.
Subsystems (4)
PATCH v2 1/1 udp: Update reuse->has_conns under reuseport_lock.
When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket.
However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now.
For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking.
cpu1 cpu2
+----+ +----+
__ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED
---
v2:
* Fix build failure for CONFIG_IPV6=m
* Drop SO_INCOMING_CPU fix, which will be sent for net-next after the v6.1 merge window
v1: https://lore.kernel.org/netdev/[email protected]/
--- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 15 +++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 24 insertions(+), 10 deletions(-)
include/net/sock_reuseport.h +5 -6
@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,extern int reuseport_attach_prog (struct sock *sk,struct bpf_prog *prog);extern int reuseport_detach_prog (struct sock *sk); -static inline bool reuseport_has_conns (struct sock *sk,bool set) +static inline bool reuseport_has_conns (struct sock *sk) {struct sock_reuseport *reuse;bool ret = false;rcu_read_lock (); reuse =rcu_dereference (sk->sk_reuseport_cb); -if (reuse) { -if (set) - reuse->has_conns =1 ; - ret = reuse->has_conns; - } +if (reuse && reuse->has_conns) + ret = true;rcu_read_unlock ();return ret; } +void reuseport_has_conns_set (struct sock *sk); +#endif /* _SOCK_REUSEPORT_H */
net/core/sock_reuseport.c +15 -0
@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany); +void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock); + reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock)); + reuse->has_conns =1 ; +spin_unlock (&reuseport_lock); +} +EXPORT_SYMBOL (reuseport_has_conns_set); +static int reuseport_sock_index (struct sock *sk,const struct sock_reuseport *reuse,bool closed)
net/ipv4/datagram.c +1 -1
@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); inet->inet_id =prandom_u32 ();
net/ipv4/udp.c +1 -1
@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;
net/ipv6/datagram.c +1 -1
@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); out:
net/ipv6/udp.c +1 -1
@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;
Signature · 1 line
2.30.2
Quoted 93 lines · Kuniyuki Iwashima
When we call
connect()for a UDP socket in a reuseport group, we have to updatesk->sk_reuseport_cb->has_connsto 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket.However, the current way to set
has_connsis illegal and possible to trigger that problem.reuseport_has_conns()changeshas_connsunderrcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock,reuseport_lock, but it doesn't for now.For this reason, there is a race below where we fail to set
has_connsresulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking.cpu1 cpu2
+----+ +----+__ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHEDFixes acdcecc61285 ("udp: correct reuseport selection with connected sockets")Signed-off-by Kuniyuki Iwashima <[email protected]>---
v2:
* Fix build failure forCONFIG_IPV6=m
* DropSO_INCOMING_CPUfix, which will be sent for net-next after the v6.1 merge windowv1: https://lore.kernel.org/netdev/[email protected]/
--- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 15 +++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 24 insertions(+), 10 deletions(-)include/net/sock_reuseport.h +5
-6@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,extern int reuseport_attach_prog (struct sock *sk,struct bpf_prog *prog);extern int reuseport_detach_prog (struct sock *sk); -static inline bool reuseport_has_conns (struct sock *sk,bool set) +static inline bool reuseport_has_conns (struct sock *sk) {struct sock_reuseport *reuse;bool ret = false;rcu_read_lock (); reuse =rcu_dereference (sk->sk_reuseport_cb); -if (reuse) { -if (set) - reuse->has_conns =1 ; - ret = reuse->has_conns; - } +if (reuse && reuse->has_conns) + ret = true;rcu_read_unlock ();return ret; } +void reuseport_has_conns_set (struct sock *sk); +#endif /* _SOCK_REUSEPORT_H */ net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);
net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 10 lines
net/core/sock_reuseport.c +10
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock); + reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));
Could @reuse be NULL at this point ?
Previous test was performed without reuseport_lock being held.
Quoted 63 lines
net/core/sock_reuseport.c +5
-0+ reuse->has_conns =1 ; +spin_unlock (&reuseport_lock); +} +EXPORT_SYMBOL (reuseport_has_conns_set); +static int reuseport_sock_index (struct sock *sk,const struct sock_reuseport *reuse,bool closed)net/ipv4/datagram.c +1
-1@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); inet->inet_id =prandom_u32 ();net/ipv4/udp.c +1
-1@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;net/ipv6/datagram.c +1
-1@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); out:net/ipv6/udp.c +1
-2@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk; --2.30.2
From: Eric Dumazet <[email protected]> Date: Wed, 12 Oct 2022 11:59:43 -0700
Quoted 107 lines · Kuniyuki Iwashima
Quoted 93 lines
When we call
connect()for a UDP socket in a reuseport group, we have to updatesk->sk_reuseport_cb->has_connsto 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket.However, the current way to set
has_connsis illegal and possible to trigger that problem.reuseport_has_conns()changeshas_connsunderrcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock,reuseport_lock, but it doesn't for now.For this reason, there is a race below where we fail to set
has_connsresulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking.cpu1 cpu2
+----+ +----+__ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHEDFixes acdcecc61285 ("udp: correct reuseport selection with connected sockets")Signed-off-by Kuniyuki Iwashima <[email protected]>---
v2:
* Fix build failure forCONFIG_IPV6=m
* DropSO_INCOMING_CPUfix, which will be sent for net-next after the v6.1 merge windowv1: https://lore.kernel.org/netdev/[email protected]/
--- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 15 +++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 24 insertions(+), 10 deletions(-)include/net/sock_reuseport.h +5
-6@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,extern int reuseport_attach_prog (struct sock *sk,struct bpf_prog *prog);extern int reuseport_detach_prog (struct sock *sk); -static inline bool reuseport_has_conns (struct sock *sk,bool set) +static inline bool reuseport_has_conns (struct sock *sk) {struct sock_reuseport *reuse;bool ret = false;rcu_read_lock (); reuse =rcu_dereference (sk->sk_reuseport_cb); -if (reuse) { -if (set) - reuse->has_conns =1 ; - ret = reuse->has_conns; - } +if (reuse && reuse->has_conns) + ret = true;rcu_read_unlock ();return ret; } +void reuseport_has_conns_set (struct sock *sk); +#endif /* _SOCK_REUSEPORT_H */ net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 10 lines
net/core/sock_reuseport.c +10
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock); + reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));Could @reuse be NULL at this point ?
Quoted 1 line
Previous test was performed without
reuseport_lockbeing held.
Usually, sk_reuseport_cb is changed under lock_sock().
The only exception is reuseport_grow() & TCP reqsk migration case.
1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk.
2) New listen() overflows reuse->socks[] and call reuseport_grow().
3) reuse->max_socks overflows u16 with the new listener.
4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock().
shutdown()ed sk->sk_reuseport_cb can be changed without lock_sock().
But, reuseport_has_conns_set() is called only for UDP and under lock_sock(), so @reuse never be NULL in this case.
Quoted 62 lines
Quoted 62 lines
net/core/sock_reuseport.c +5
-0+ reuse->has_conns =1 ; +spin_unlock (&reuseport_lock); +} +EXPORT_SYMBOL (reuseport_has_conns_set); +static int reuseport_sock_index (struct sock *sk,const struct sock_reuseport *reuse,bool closed)net/ipv4/datagram.c +1
-1@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); inet->inet_id =prandom_u32 ();net/ipv4/udp.c +1
-1@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;net/ipv6/datagram.c +1
-1@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); out:net/ipv6/udp.c +1
-2@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk; --2.30.2
Quoted 123 lines · Kuniyuki Iwashima
From: Eric Dumazet <[email protected]> Date: Wed, 12 Oct 2022 11:59:43 -0700Quoted 107 lines · Kuniyuki Iwashima
Quoted 93 lines
When we call
connect()for a UDP socket in a reuseport group, we have to updatesk->sk_reuseport_cb->has_connsto 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket.However, the current way to set
has_connsis illegal and possible to trigger that problem.reuseport_has_conns()changeshas_connsunderrcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock,reuseport_lock, but it doesn't for now.For this reason, there is a race below where we fail to set
has_connsresulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking.cpu1 cpu2
+----+ +----+__ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHEDFixes acdcecc61285 ("udp: correct reuseport selection with connected sockets")Signed-off-by Kuniyuki Iwashima <[email protected]>---
v2:
* Fix build failure forCONFIG_IPV6=m
* DropSO_INCOMING_CPUfix, which will be sent for net-next after the v6.1 merge windowv1: https://lore.kernel.org/netdev/[email protected]/
--- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 15 +++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 24 insertions(+), 10 deletions(-)include/net/sock_reuseport.h +5
-6@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,extern int reuseport_attach_prog (struct sock *sk,struct bpf_prog *prog);extern int reuseport_detach_prog (struct sock *sk); -static inline bool reuseport_has_conns (struct sock *sk,bool set) +static inline bool reuseport_has_conns (struct sock *sk) {struct sock_reuseport *reuse;bool ret = false;rcu_read_lock (); reuse =rcu_dereference (sk->sk_reuseport_cb); -if (reuse) { -if (set) - reuse->has_conns =1 ; - ret = reuse->has_conns; - } +if (reuse && reuse->has_conns) + ret = true;rcu_read_unlock ();return ret; } +void reuseport_has_conns_set (struct sock *sk); +#endif /* _SOCK_REUSEPORT_H */ net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 10 lines
net/core/sock_reuseport.c +10
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock); + reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));Could @reuse be NULL at this point ?
Quoted 1 line
Previous test was performed without
reuseport_lockbeing held.Usually,
sk_reuseport_cbis changed underlock_sock().The only exception is
reuseport_grow()& TCP reqsk migration case.1)
shutdown()TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk.2) New
listen()overflows reuse->socks[] and callreuseport_grow().3)
reuse->max_socksoverflows u16 with the new listener.
Quoted 7 lines
4)
reuseport_grow()pops the old shutdown()ed listener from the array and update itssk->sk_reuseport_cbas NULL withoutlock_sock().shutdown()ed
sk->sk_reuseport_cbcan be changed withoutlock_sock().But,
reuseport_has_conns_set()is called only for UDP and underlock_sock(), so @reuse never be NULL in this case.
Given the complexity of this code and how much time is needed to review all possibilities, please add an additional
if (reuse)
reuse->has_conns = 1;
I doubt anyone will object to such safety measures.
Thanks.
Quoted 64 lines
Quoted 64 lines
Quoted 64 lines
net/core/sock_reuseport.c +5
-0+ reuse->has_conns =1 ; +spin_unlock (&reuseport_lock); +} +EXPORT_SYMBOL (reuseport_has_conns_set); +static int reuseport_sock_index (struct sock *sk,const struct sock_reuseport *reuse,bool closed)net/ipv4/datagram.c +1
-1@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); inet->inet_id =prandom_u32 ();net/ipv4/udp.c +1
-1@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;net/ipv6/datagram.c +1
-1@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); out:net/ipv6/udp.c +1
-2@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk; --2.30.2
From: Eric Dumazet <[email protected]> Date: Thu, 13 Oct 2022 09:09:31 -0700
Quoted 132 lines · Kuniyuki Iwashima
Quoted 123 lines
From: Eric Dumazet <[email protected]> Date: Wed, 12 Oct 2022 11:59:43 -0700Quoted 107 lines · Kuniyuki Iwashima
Quoted 93 lines
When we call
connect()for a UDP socket in a reuseport group, we have to updatesk->sk_reuseport_cb->has_connsto 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket.However, the current way to set
has_connsis illegal and possible to trigger that problem.reuseport_has_conns()changeshas_connsunderrcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock,reuseport_lock, but it doesn't for now.For this reason, there is a race below where we fail to set
has_connsresulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking.cpu1 cpu2
+----+ +----+__ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHEDFixes acdcecc61285 ("udp: correct reuseport selection with connected sockets")Signed-off-by Kuniyuki Iwashima <[email protected]>---
v2:
* Fix build failure forCONFIG_IPV6=m
* DropSO_INCOMING_CPUfix, which will be sent for net-next after the v6.1 merge windowv1: https://lore.kernel.org/netdev/[email protected]/
--- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 15 +++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 24 insertions(+), 10 deletions(-)include/net/sock_reuseport.h +5
-6@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,extern int reuseport_attach_prog (struct sock *sk,struct bpf_prog *prog);extern int reuseport_detach_prog (struct sock *sk); -static inline bool reuseport_has_conns (struct sock *sk,bool set) +static inline bool reuseport_has_conns (struct sock *sk) {struct sock_reuseport *reuse;bool ret = false;rcu_read_lock (); reuse =rcu_dereference (sk->sk_reuseport_cb); -if (reuse) { -if (set) - reuse->has_conns =1 ; - ret = reuse->has_conns; - } +if (reuse && reuse->has_conns) + ret = true;rcu_read_unlock ();return ret; } +void reuseport_has_conns_set (struct sock *sk); +#endif /* _SOCK_REUSEPORT_H */ net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 10 lines
net/core/sock_reuseport.c +10
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock); + reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));Could @reuse be NULL at this point ?
Quoted 1 line
Previous test was performed without
reuseport_lockbeing held.Usually,
sk_reuseport_cbis changed underlock_sock().The only exception is
reuseport_grow()& TCP reqsk migration case.1)
shutdown()TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk.2) New
listen()overflows reuse->socks[] and callreuseport_grow().3)
reuse->max_socksoverflows u16 with the new listener.Quoted 7 lines
4)
reuseport_grow()pops the old shutdown()ed listener from the array and update itssk->sk_reuseport_cbas NULL withoutlock_sock().shutdown()ed
sk->sk_reuseport_cbcan be changed withoutlock_sock().But,
reuseport_has_conns_set()is called only for UDP and underlock_sock(), so @reuse never be NULL in this case.
Quoted 7 lines
Given the complexity of this code and how much time is needed to review all possibilities, please add an additional
if (reuse)
reuse->has_conns= 1;I doubt anyone will object to such safety measures.
I see.
If no one has any objections, I'll respin tomorrow with likely().
Thank you.
Quoted 67 lines
Thanks.
Quoted 64 lines
Quoted 64 lines
Quoted 64 lines
net/core/sock_reuseport.c +5
-0+ reuse->has_conns =1 ; +spin_unlock (&reuseport_lock); +} +EXPORT_SYMBOL (reuseport_has_conns_set); +static int reuseport_sock_index (struct sock *sk,const struct sock_reuseport *reuse,bool closed)net/ipv4/datagram.c +1
-1@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); inet->inet_id =prandom_u32 ();net/ipv4/udp.c +1
-1@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk;net/ipv6/datagram.c +1
-1@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } -reuseport_has_conns (sk, true); +reuseport_has_conns_set (sk); sk->sk_state =TCP_ESTABLISHED ;sk_set_txhash (sk); out:net/ipv6/udp.c +1
-2@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result =lookup_reuseport (net, sk, skb, saddr, sport, daddr, hnum);/* Fall back to scoring if group has connections */ -if (result && !reuseport_has_conns (sk, false)) +if (result && !reuseport_has_conns (sk))return result; result = result ? : sk; --2.30.2
Quoted 8 lines · Eric Dumazet
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 31
Quoted 8 lines
net/core/sock_reuseport.c +8
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock);
It seems other paths are still using the spin_lock_bh(). It will be useful to have a few words here why _bh() is not needed.
Quoted 23 lines
Quoted 23 lines
Quoted 6 lines
net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 2 lines
net/core/sock_reuseport.c +2
-0+ reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));Could @reuse be NULL at this point ?
Previous test was performed without
reuseport_lockbeing held.Usually,
sk_reuseport_cbis changed underlock_sock().The only exception is
reuseport_grow()& TCP reqsk migration case.1)
shutdown()TCP listener, which is moved into the latter part ofreuse->socks[] to migrate reqsk.2) New
listen()overflows reuse->socks[] and callreuseport_grow().3)
reuse->max_socksoverflows u16 with the new listener.4)
reuseport_grow()pops the old shutdown()ed listener from the arrayand update its sk->sk_reuseport_cb as NULL without lock_sock().shutdown()ed
sk->sk_reuseport_cbcan be changed withoutlock_sock().
Quoted 8 lines
Quoted 2 lines
But,
reuseport_has_conns_set()is called only for UDP and underlock_sock(), so @reuse never be NULL in this case.Given the complexity of this code and how much time is needed to review all possibilities, please add an additional
if (reuse)
reuse->has_conns = 1;
+1
From: Martin KaFai Lau <[email protected]> Date: Thu, 13 Oct 2022 10:41:53 -0700
Quoted 9 lines · Eric Dumazet
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
net/core/sock_reuseport.c +0
-0@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);static int reuseport_resurrect (struct sock *sk,struct sock_reuseport *old_reuse,struct sock_reuseport *reuse,bool bind_inany);
Quoted 11 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 31
Quoted 8 lines
net/core/sock_reuseport.c +8
-0+void reuseport_has_conns_set (struct sock *sk) +{ +struct sock_reuseport *reuse; + +if (!rcu_access_pointer (sk->sk_reuseport_cb)) +return ; + +spin_lock (&reuseport_lock);It seems other paths are still using the
spin_lock_bh(). It will be useful to have a few words here why_bh()is not needed.
I think I forgot to add _bh(), but I'm now wondering what is the hlist lock mentioned in reuseport_alloc()...
Quoted 26 lines
Quoted 26 lines
Quoted 25 lines
Quoted 6 lines
net/core/sock_reuseport.c static DEFINE_IDA(reuseport_ida); · line 33
Quoted 2 lines
net/core/sock_reuseport.c +2
-0+ reuse =rcu_dereference_protected (sk->sk_reuseport_cb, +lockdep_is_held (&reuseport_lock));Could @reuse be NULL at this point ?
Previous test was performed without
reuseport_lockbeing held.Usually,
sk_reuseport_cbis changed underlock_sock().The only exception is
reuseport_grow()& TCP reqsk migration case.1)
shutdown()TCP listener, which is moved into the latter part ofreuse->socks[] to migrate reqsk.2) New
listen()overflows reuse->socks[] and callreuseport_grow().3)
reuse->max_socksoverflows u16 with the new listener.4)
reuseport_grow()pops the old shutdown()ed listener from the arrayand update its sk->sk_reuseport_cb as NULL without lock_sock().shutdown()ed
sk->sk_reuseport_cbcan be changed withoutlock_sock().But,
reuseport_has_conns_set()is called only for UDP and underlock_sock(), so @reuse never be NULL in this case.
Quoted 7 lines
Quoted 5 lines
Given the complexity of this code and how much time is needed to review all possibilities, please add an additional
if (reuse)
reuse->has_conns = 1;+1
Acked.
Thank you.