From 451c2b5caf37b526ae34a1081b71115e1de2d063 Mon Sep 17 00:00:00 2001 From: Aya Mahfouz Date: Wed, 18 Nov 2015 08:36:44 +0200 Subject: net: dns_resolver: convert time_t to time64_t Changes the definition of the pointer _expiry from time_t to time64_t. This is to handle the Y2038 problem where time_t will overflow in the year 2038. The change is safe because the kernel subsystems that call dns_query pass NULL. Signed-off-by: Arnd Bergmann Signed-off-by: Aya Mahfouz Signed-off-by: David S. Miller --- include/linux/dns_resolver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index cc92268af89a..6ac3cad9aef1 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -27,7 +27,7 @@ #ifdef __KERNEL__ extern int dns_query(const char *type, const char *name, size_t namelen, - const char *options, char **_result, time_t *_expiry); + const char *options, char **_result, time64_t *_expiry); #endif /* KERNEL */ -- cgit v1.2.3-59-g8ed1b From ac0621971a26526cad8cf9db7626d5e50562a441 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Tue, 17 Nov 2015 10:24:38 +0200 Subject: mac80211: always set the buf_size in AddBA req to 64 Advertising reordering window in ADDBA less than 64 can crash some APs, an example is LinkSys WRT120N (with FW v1.0.07 build 002 Jun 18 2012). On the other hand, a driver may need to limit Tx A-MPDU size for its own reasons, like specific HW limitations. Signed-off-by: Gregory Greenman Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 ++++-- net/mac80211/agg-tx.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 82045fca388b..760bc4d5a2cf 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2003,8 +2003,10 @@ enum ieee80211_hw_flags { * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an - * aggregate an HT driver will transmit, used by the peer as a - * hint to size its reorder buffer. + * aggregate an HT driver will transmit. Though ADDBA will advertise + * a constant value of 64 as some older APs can crash if the window + * size is smaller (an example is LinkSys WRT120N with FW v1.0.07 + * build 002 Jun 18 2012). * * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX * (if %IEEE80211_HW_QUEUE_CONTROL is set) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index a758eb84e8f0..ff757181b0a8 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -500,7 +500,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, start_seq_num, - local->hw.max_tx_aggregation_subframes, + IEEE80211_MAX_AMPDU_BUF, tid_tx->timeout); } @@ -926,6 +926,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK; tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes); mutex_lock(&sta->ampdu_mlme.mtx); -- cgit v1.2.3-59-g8ed1b From 7d267278a9ece963d77eefec61630223fce08c6c Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Fri, 20 Nov 2015 22:07:23 +0000 Subject: unix: avoid use-after-free in ep_remove_wait_queue Rainer Weikusat writes: An AF_UNIX datagram socket being the client in an n:1 association with some server socket is only allowed to send messages to the server if the receive queue of this socket contains at most sk_max_ack_backlog datagrams. This implies that prospective writers might be forced to go to sleep despite none of the message presently enqueued on the server receive queue were sent by them. In order to ensure that these will be woken up once space becomes again available, the present unix_dgram_poll routine does a second sock_poll_wait call with the peer_wait wait queue of the server socket as queue argument (unix_dgram_recvmsg does a wake up on this queue after a datagram was received). This is inherently problematic because the server socket is only guaranteed to remain alive for as long as the client still holds a reference to it. In case the connection is dissolved via connect or by the dead peer detection logic in unix_dgram_sendmsg, the server socket may be freed despite "the polling mechanism" (in particular, epoll) still has a pointer to the corresponding peer_wait queue. There's no way to forcibly deregister a wait queue with epoll. Based on an idea by Jason Baron, the patch below changes the code such that a wait_queue_t belonging to the client socket is enqueued on the peer_wait queue of the server whenever the peer receive queue full condition is detected by either a sendmsg or a poll. A wake up on the peer queue is then relayed to the ordinary wait queue of the client socket via wake function. The connection to the peer wait queue is again dissolved if either a wake up is about to be relayed or the client socket reconnects or a dead peer is detected or the client socket is itself closed. This enables removing the second sock_poll_wait from unix_dgram_poll, thus avoiding the use-after-free, while still ensuring that no blocked writer sleeps forever. Signed-off-by: Rainer Weikusat Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets") Reviewed-by: Jason Baron Signed-off-by: David S. Miller --- include/net/af_unix.h | 1 + net/unix/af_unix.c | 183 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 165 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index b36d837c701e..2a91a0561a47 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_sock { #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; + wait_queue_t peer_wake; }; static inline struct unix_sock *unix_sk(const struct sock *sk) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 955ec152cb71..4e95bdf973d9 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -326,6 +326,118 @@ found: return s; } +/* Support code for asymmetrically connected dgram sockets + * + * If a datagram socket is connected to a socket not itself connected + * to the first socket (eg, /dev/log), clients may only enqueue more + * messages if the present receive queue of the server socket is not + * "too large". This means there's a second writeability condition + * poll and sendmsg need to test. The dgram recv code will do a wake + * up on the peer_wait wait queue of a socket upon reception of a + * datagram which needs to be propagated to sleeping would-be writers + * since these might not have sent anything so far. This can't be + * accomplished via poll_wait because the lifetime of the server + * socket might be less than that of its clients if these break their + * association with it or if the server socket is closed while clients + * are still connected to it and there's no way to inform "a polling + * implementation" that it should let go of a certain wait queue + * + * In order to propagate a wake up, a wait_queue_t of the client + * socket is enqueued on the peer_wait queue of the server socket + * whose wake function does a wake_up on the ordinary client socket + * wait queue. This connection is established whenever a write (or + * poll for write) hit the flow control condition and broken when the + * association to the server socket is dissolved or after a wake up + * was relayed. + */ + +static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags, + void *key) +{ + struct unix_sock *u; + wait_queue_head_t *u_sleep; + + u = container_of(q, struct unix_sock, peer_wake); + + __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait, + q); + u->peer_wake.private = NULL; + + /* relaying can only happen while the wq still exists */ + u_sleep = sk_sleep(&u->sk); + if (u_sleep) + wake_up_interruptible_poll(u_sleep, key); + + return 0; +} + +static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other) +{ + struct unix_sock *u, *u_other; + int rc; + + u = unix_sk(sk); + u_other = unix_sk(other); + rc = 0; + spin_lock(&u_other->peer_wait.lock); + + if (!u->peer_wake.private) { + u->peer_wake.private = other; + __add_wait_queue(&u_other->peer_wait, &u->peer_wake); + + rc = 1; + } + + spin_unlock(&u_other->peer_wait.lock); + return rc; +} + +static void unix_dgram_peer_wake_disconnect(struct sock *sk, + struct sock *other) +{ + struct unix_sock *u, *u_other; + + u = unix_sk(sk); + u_other = unix_sk(other); + spin_lock(&u_other->peer_wait.lock); + + if (u->peer_wake.private == other) { + __remove_wait_queue(&u_other->peer_wait, &u->peer_wake); + u->peer_wake.private = NULL; + } + + spin_unlock(&u_other->peer_wait.lock); +} + +static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk, + struct sock *other) +{ + unix_dgram_peer_wake_disconnect(sk, other); + wake_up_interruptible_poll(sk_sleep(sk), + POLLOUT | + POLLWRNORM | + POLLWRBAND); +} + +/* preconditions: + * - unix_peer(sk) == other + * - association is stable + */ +static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) +{ + int connected; + + connected = unix_dgram_peer_wake_connect(sk, other); + + if (unix_recvq_full(other)) + return 1; + + if (connected) + unix_dgram_peer_wake_disconnect(sk, other); + + return 0; +} + static int unix_writable(const struct sock *sk) { return sk->sk_state != TCP_LISTEN && @@ -431,6 +543,8 @@ static void unix_release_sock(struct sock *sk, int embrion) skpair->sk_state_change(skpair); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); } + + unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ unix_peer(sk) = NULL; } @@ -666,6 +780,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); + init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) @@ -1033,6 +1148,8 @@ restart: if (unix_peer(sk)) { struct sock *old_peer = unix_peer(sk); unix_peer(sk) = other; + unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); + unix_state_double_unlock(sk, other); if (other != old_peer) @@ -1472,6 +1589,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, struct scm_cookie scm; int max_level; int data_len = 0; + int sk_locked; wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); @@ -1550,12 +1668,14 @@ restart: goto out_free; } + sk_locked = 0; unix_state_lock(other); +restart_locked: err = -EPERM; if (!unix_may_send(sk, other)) goto out_unlock; - if (sock_flag(other, SOCK_DEAD)) { + if (unlikely(sock_flag(other, SOCK_DEAD))) { /* * Check with 1003.1g - what should * datagram error @@ -1563,10 +1683,14 @@ restart: unix_state_unlock(other); sock_put(other); + if (!sk_locked) + unix_state_lock(sk); + err = 0; - unix_state_lock(sk); if (unix_peer(sk) == other) { unix_peer(sk) = NULL; + unix_dgram_peer_wake_disconnect_wakeup(sk, other); + unix_state_unlock(sk); unix_dgram_disconnected(sk, other); @@ -1592,21 +1716,38 @@ restart: goto out_unlock; } - if (unix_peer(other) != sk && unix_recvq_full(other)) { - if (!timeo) { - err = -EAGAIN; - goto out_unlock; + if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + if (timeo) { + timeo = unix_wait_for_peer(other, timeo); + + err = sock_intr_errno(timeo); + if (signal_pending(current)) + goto out_free; + + goto restart; } - timeo = unix_wait_for_peer(other, timeo); + if (!sk_locked) { + unix_state_unlock(other); + unix_state_double_lock(sk, other); + } - err = sock_intr_errno(timeo); - if (signal_pending(current)) - goto out_free; + if (unix_peer(sk) != other || + unix_dgram_peer_wake_me(sk, other)) { + err = -EAGAIN; + sk_locked = 1; + goto out_unlock; + } - goto restart; + if (!sk_locked) { + sk_locked = 1; + goto restart_locked; + } } + if (unlikely(sk_locked)) + unix_state_unlock(sk); + if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); @@ -1620,6 +1761,8 @@ restart: return len; out_unlock: + if (sk_locked) + unix_state_unlock(sk); unix_state_unlock(other); out_free: kfree_skb(skb); @@ -2476,14 +2619,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; writable = unix_writable(sk); - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); - if (unix_recvq_full(other)) - writable = 0; - } - sock_put(other); + if (writable) { + unix_state_lock(sk); + + other = unix_peer(sk); + if (other && unix_peer(other) != sk && + unix_recvq_full(other) && + unix_dgram_peer_wake_me(sk, other)) + writable = 0; + + unix_state_unlock(sk); } if (writable) -- cgit v1.2.3-59-g8ed1b From 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Tue, 24 Nov 2015 15:07:11 +0100 Subject: ipv6: distinguish frag queues by device for multicast and link-local packets If a fragmented multicast packet is received on an ethernet device which has an active macvlan on top of it, each fragment is duplicated and received both on the underlying device and the macvlan. If some fragments for macvlan are processed before the whole packet for the underlying device is reassembled, the "overlapping fragments" test in ip6_frag_queue() discards the whole fragment queue. To resolve this, add device ifindex to the search key and require it to match reassembling multicast packets and packets to link-local addresses. Note: similar patch has been already submitted by Yoshifuji Hideaki in http://patchwork.ozlabs.org/patch/220979/ but got lost and forgotten for some reason. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 + net/ipv6/netfilter/nf_conntrack_reasm.c | 5 +++-- net/ipv6/reassembly.c | 10 +++++++--- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e1a10b0ac0b0..ea5a13ef85a6 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -490,6 +490,7 @@ struct ip6_create_arg { u32 user; const struct in6_addr *src; const struct in6_addr *dst; + int iif; u8 ecn; }; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index d5efeb87350e..bab4441ed4e4 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data) /* Creation primitives. */ static inline struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, struct in6_addr *src, - struct in6_addr *dst, u8 ecn) + struct in6_addr *dst, int iif, u8 ecn) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.user = user; arg.src = src; arg.dst = dst; + arg.iif = iif; arg.ecn = ecn; local_bh_disable(); @@ -601,7 +602,7 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use fhdr = (struct frag_hdr *)skb_transport_header(clone); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, - ip6_frag_ecn(hdr)); + skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 44e21a03cfc3..45f5ae51de65 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a) return fq->id == arg->id && fq->user == arg->user && ipv6_addr_equal(&fq->saddr, arg->src) && - ipv6_addr_equal(&fq->daddr, arg->dst); + ipv6_addr_equal(&fq->daddr, arg->dst) && + (arg->iif == fq->iif || + !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))); } EXPORT_SYMBOL(ip6_frag_match); @@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data) static struct frag_queue * fq_find(struct net *net, __be32 id, const struct in6_addr *src, - const struct in6_addr *dst, u8 ecn) + const struct in6_addr *dst, int iif, u8 ecn) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; + arg.iif = iif; arg.ecn = ecn; hash = inet6_hash_frag(id, src, dst); @@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) } fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - ip6_frag_ecn(hdr)); + skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq) { int ret; -- cgit v1.2.3-59-g8ed1b From c9da161c6517ba12154059d3b965c2cbaf16f90f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 24 Nov 2015 21:28:15 +0100 Subject: bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 5 ++++- kernel/bpf/inode.c | 6 +++--- kernel/bpf/syscall.c | 36 +++++++++++++++++++++++++----------- kernel/bpf/verifier.c | 3 +-- 4 files changed, 33 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index de464e6683b6..83d1926c61e4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -40,6 +40,7 @@ struct bpf_map { struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; + atomic_t usercnt; }; struct bpf_map_type_list { @@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); -struct bpf_map *bpf_map_get(u32 ufd); +struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); +void bpf_map_inc(struct bpf_map *map, bool uref); +void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); extern int sysctl_unprivileged_bpf_disabled; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index be6d726e31c9..5a8a797d50b7 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type) atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); break; case BPF_TYPE_MAP: - atomic_inc(&((struct bpf_map *)raw)->refcnt); + bpf_map_inc(raw, true); break; default: WARN_ON_ONCE(1); @@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type) bpf_prog_put(raw); break; case BPF_TYPE_MAP: - bpf_map_put(raw); + bpf_map_put_with_uref(raw); break; default: WARN_ON_ONCE(1); @@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) void *raw; *type = BPF_TYPE_MAP; - raw = bpf_map_get(ufd); + raw = bpf_map_get_with_uref(ufd); if (IS_ERR(raw)) { *type = BPF_TYPE_PROG; raw = bpf_prog_get(ufd); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0d3313d02a7e..4a8f3c1d7da6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work) map->ops->map_free(map); } +static void bpf_map_put_uref(struct bpf_map *map) +{ + if (atomic_dec_and_test(&map->usercnt)) { + if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) + bpf_fd_array_map_clear(map); + } +} + /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ @@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map) } } -static int bpf_map_release(struct inode *inode, struct file *filp) +void bpf_map_put_with_uref(struct bpf_map *map) { - struct bpf_map *map = filp->private_data; - - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) - /* prog_array stores refcnt-ed bpf_prog pointers - * release them all when user space closes prog_array_fd - */ - bpf_fd_array_map_clear(map); - + bpf_map_put_uref(map); bpf_map_put(map); +} + +static int bpf_map_release(struct inode *inode, struct file *filp) +{ + bpf_map_put_with_uref(filp->private_data); return 0; } @@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr) return PTR_ERR(map); atomic_set(&map->refcnt, 1); + atomic_set(&map->usercnt, 1); err = bpf_map_charge_memlock(map); if (err) @@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -struct bpf_map *bpf_map_get(u32 ufd) +void bpf_map_inc(struct bpf_map *map, bool uref) +{ + atomic_inc(&map->refcnt); + if (uref) + atomic_inc(&map->usercnt); +} + +struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; @@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd) if (IS_ERR(map)) return map; - atomic_inc(&map->refcnt); + bpf_map_inc(map, true); fdput(f); return map; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6073056badf..a7945d10b378 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) * will be used by the valid program until it's unloaded * and all maps are released in free_bpf_prog_info() */ - atomic_inc(&map->refcnt); - + bpf_map_inc(map, false); fdput(f); next_insn: insn++; -- cgit v1.2.3-59-g8ed1b From 880621c2605b82eb5af91a2c94223df6f5a3fb64 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 22 Nov 2015 17:46:09 +0100 Subject: packet: Allow packets with only a header (but no payload) Commit 9c7077622dd91 ("packet: make packet_snd fail on len smaller than l2 header") added validation for the packet size in packet_snd. This change enforces that every packet needs a header (with at least hard_header_len bytes) plus a payload with at least one byte. Before this change the payload was optional. This fixes PPPoE connections which do not have a "Service" or "Host-Uniq" configured (which is violating the spec, but is still widely used in real-world setups). Those are currently failing with the following message: "pppd: packet size is too short (24 <= 24)" Signed-off-by: Martin Blumenstingl Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- net/packet/af_packet.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67bfac1abfc1..3b5d134e945a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1398,7 +1398,8 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length + * @hard_header_len: Hardware header length, which means that this is the + * minimum size of a packet. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 1cf928fb573e..992396aa635c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2329,8 +2329,8 @@ static void tpacket_destruct_skb(struct sk_buff *skb) static bool ll_header_truncated(const struct net_device *dev, int len) { /* net device doesn't like empty head */ - if (unlikely(len <= dev->hard_header_len)) { - net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n", + if (unlikely(len < dev->hard_header_len)) { + net_warn_ratelimited("%s: packet size is too short (%d < %d)\n", current->comm, len, dev->hard_header_len); return true; } -- cgit v1.2.3-59-g8ed1b From 304d888b29cf96f1dd53511ee686499cd8cdf249 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 27 Nov 2015 18:17:05 +0100 Subject: Revert "ipv6: ndisc: inherit metadata dst when creating ndisc requests" This reverts commit ab450605b35caa768ca33e86db9403229bf42be4. In IPv6, we cannot inherit the dst of the original dst. ndisc packets are IPv6 packets and may take another route than the original packet. This patch breaks the following scenario: a packet comes from eth0 and is forwarded through vxlan1. The encapsulated packet triggers an NS which cannot be sent because of the wrong route. CC: Jiri Benc CC: Thomas Graf Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ndisc.h | 3 +-- net/ipv6/addrconf.c | 2 +- net/ipv6/ndisc.c | 10 +++------- net/ipv6/route.c | 2 +- 4 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index bf3937431030..2d8edaad29cb 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -181,8 +181,7 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr, - struct sk_buff *oskb); + const struct in6_addr *daddr, const struct in6_addr *saddr); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d84742f003a9..61f26851655c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3642,7 +3642,7 @@ static void addrconf_dad_work(struct work_struct *w) /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL); + ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any); out: in6_ifa_put(ifp); rtnl_unlock(); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3e0f855e1bea..d6161e1c48c8 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -556,8 +556,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) } void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr, - struct sk_buff *oskb) + const struct in6_addr *daddr, const struct in6_addr *saddr) { struct sk_buff *skb; struct in6_addr addr_buf; @@ -593,9 +592,6 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr); - if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb) - skb_dst_copy(skb, oskb); - ndisc_send_skb(skb, daddr, saddr); } @@ -682,12 +678,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } - ndisc_send_ns(dev, target, target, saddr, skb); + ndisc_send_ns(dev, target, target, saddr); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, target, &mcaddr, saddr, skb); + ndisc_send_ns(dev, target, &mcaddr, saddr); } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6f01fe122abd..826e6aa44f8d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -523,7 +523,7 @@ static void rt6_probe_deferred(struct work_struct *w) container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); - ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL); + ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL); dev_put(work->dev); kfree(work); } -- cgit v1.2.3-59-g8ed1b From 9cd3e072b0be17446e37d7414eac8a3499e0601e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 29 Nov 2015 20:03:10 -0800 Subject: net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA This patch is a cleanup to make following patch easier to review. Goal is to move SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA from (struct socket)->flags to a (struct socket_wq)->flags to benefit from RCU protection in sock_wake_async() To ease backports, we rename both constants. Two new helpers, sk_set_bit(int nr, struct sock *sk) and sk_clear_bit(int net, struct sock *sk) are added so that following patch can change their implementation. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- crypto/algif_aead.c | 4 ++-- crypto/algif_skcipher.c | 6 +++--- drivers/net/macvtap.c | 4 ++-- drivers/net/tun.c | 4 ++-- fs/dlm/lowcomms.c | 4 ++-- include/linux/net.h | 6 +++--- include/net/sock.h | 10 ++++++++++ net/bluetooth/af_bluetooth.c | 6 +++--- net/caif/caif_socket.c | 4 ++-- net/core/datagram.c | 2 +- net/core/sock.c | 8 ++++---- net/core/stream.c | 4 ++-- net/dccp/proto.c | 3 +-- net/decnet/af_decnet.c | 8 ++++---- net/ipv4/tcp.c | 7 +++---- net/iucv/af_iucv.c | 2 +- net/nfc/llcp_sock.c | 2 +- net/rxrpc/ar-output.c | 2 +- net/sctp/socket.c | 2 +- net/socket.c | 4 ++-- net/sunrpc/xprtsock.c | 14 +++++++------- net/unix/af_unix.c | 6 +++--- 22 files changed, 60 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 0aa6fdfb448a..6d4d4569447e 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -125,7 +125,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags) if (flags & MSG_DONTWAIT) return -EAGAIN; - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); for (;;) { if (signal_pending(current)) @@ -139,7 +139,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags) } finish_wait(sk_sleep(sk), &wait); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); return err; } diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index af31a0ee4057..ca9efe17db1a 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -212,7 +212,7 @@ static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags) if (flags & MSG_DONTWAIT) return -EAGAIN; - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (signal_pending(current)) @@ -258,7 +258,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags) return -EAGAIN; } - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); for (;;) { if (signal_pending(current)) @@ -272,7 +272,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags) } finish_wait(sk_sleep(sk), &wait); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); return err; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 54036ae0a388..0fc521941c71 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -498,7 +498,7 @@ static void macvtap_sock_write_space(struct sock *sk) wait_queue_head_t *wqueue; if (!sock_writeable(sk) || - !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) + !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); @@ -585,7 +585,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) mask |= POLLIN | POLLRDNORM; if (sock_writeable(&q->sk) || - (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) && + (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) && sock_writeable(&q->sk))) mask |= POLLOUT | POLLWRNORM; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b1878faea397..f0db770e8b2f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1040,7 +1040,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) mask |= POLLIN | POLLRDNORM; if (sock_writeable(sk) || - (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) && + (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && sock_writeable(sk))) mask |= POLLOUT | POLLWRNORM; @@ -1488,7 +1488,7 @@ static void tun_sock_write_space(struct sock *sk) if (!sock_writeable(sk)) return; - if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) + if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 87e9d796cf7d..3a37bd3f9637 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk) if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) { con->sock->sk->sk_write_pending--; - clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags); } if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) @@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con) msg_flags); if (ret == -EAGAIN || ret == 0) { if (ret == -EAGAIN && - test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) && + test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) && !test_and_set_bit(CF_APP_LIMITED, &con->flags)) { /* Notify TCP that we're limited by the * application window size. diff --git a/include/linux/net.h b/include/linux/net.h index 70ac5e28e6b7..f514e4dd5521 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -34,8 +34,8 @@ struct inode; struct file; struct net; -#define SOCK_ASYNC_NOSPACE 0 -#define SOCK_ASYNC_WAITDATA 1 +#define SOCKWQ_ASYNC_NOSPACE 0 +#define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 @@ -96,7 +96,7 @@ struct socket_wq { * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) - * @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc) + * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation diff --git a/include/net/sock.h b/include/net/sock.h index 7f89e4ba18d1..c155d09d8af4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2005,6 +2005,16 @@ static inline unsigned long sock_wspace(struct sock *sk) return amt; } +static inline void sk_set_bit(int nr, struct sock *sk) +{ + set_bit(nr, &sk->sk_socket->flags); +} + +static inline void sk_clear_bit(int nr, struct sock *sk) +{ + clear_bit(nr, &sk->sk_socket->flags); +} + static inline void sk_wake_async(struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index a3bffd1ec2b4..70306cc9d814 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -271,11 +271,11 @@ static long bt_sock_data_wait(struct sock *sk, long timeo) if (signal_pending(current) || !timeo) break; - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } __set_current_state(TASK_RUNNING); @@ -441,7 +441,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock, if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index cc858919108e..aa209b1066c9 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -323,7 +323,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) !timeo) break; - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); @@ -331,7 +331,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) if (sock_flag(sk, SOCK_DEAD)) break; - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } finish_wait(sk_sleep(sk), &wait); diff --git a/net/core/datagram.c b/net/core/datagram.c index 617088aee21d..d62af69ad844 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -785,7 +785,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, if (sock_writeable(sk)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } diff --git a/net/core/sock.c b/net/core/sock.c index 1e4dd54bfb5a..9d79569935a3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1815,7 +1815,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; @@ -1861,7 +1861,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) break; - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) @@ -2048,9 +2048,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); finish_wait(sk_sleep(sk), &wait); return rc; } diff --git a/net/core/stream.c b/net/core/stream.c index d70f77a0c889..43309428644d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); @@ -139,7 +139,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) } if (signal_pending(current)) goto do_interrupted; - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk_stream_memory_free(sk) && !vm_wait) break; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index b5cf13a28009..41e65804ddf5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -339,8 +339,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ - set_bit(SOCK_ASYNC_NOSPACE, - &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 675cf94e04f8..eebf5ac8ce18 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1747,9 +1747,9 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target)); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); finish_wait(sk_sleep(sk), &wait); } @@ -2004,10 +2004,10 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); sk_wait_event(sk, &timeo, !dn_queue_too_long(scp, queue, flags)); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); finish_wait(sk_sleep(sk), &wait); continue; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c1728771cf89..c82cca18c90f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ - set_bit(SOCK_ASYNC_NOSPACE, - &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after @@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, goto out_err; } - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); mss_now = tcp_send_mss(sk, &size_goal, flags); copied = 0; @@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) } /* This should be in poll */ - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); mss_now = tcp_send_mss(sk, &size_goal, flags); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index fcb2752419c6..435608c4306d 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1483,7 +1483,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, if (sock_writeable(sk) && iucv_below_msglim(sk)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index b7de0da46acd..ecf0a0196f18 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -572,7 +572,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock, if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); pr_debug("mask 0x%x\n", mask); diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index a40d3afe93b7..14c4e12c47b0 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -531,7 +531,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); /* this should be in poll */ - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) return -EPIPE; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 897c01c029ca..2353985d689c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6458,7 +6458,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sctp_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* * Since the socket is not locked, the buffer * might be made available after the writeable check and diff --git a/net/socket.c b/net/socket.c index dd2c247c99e3..16be908205fc 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1072,11 +1072,11 @@ int sock_wake_async(struct socket *sock, int how, int band) } switch (how) { case SOCK_WAKE_WAITD: - if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) + if (test_bit(SOCKWQ_ASYNC_WAITDATA, &sock->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: - if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags)) + if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags)) break; /* fall through */ case SOCK_WAKE_IO: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 1d1a70498910..2ffaf6a79499 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +442,7 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,7 +467,7 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { + if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { /* * Notify TCP that we're limited by the application * window size @@ -478,7 +478,7 @@ static int xs_nospace(struct rpc_task *task) xprt_wait_for_buffer_space(task, xs_nospace_callback); } } else { - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); ret = -ENOTCONN; } @@ -626,7 +626,7 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } return status; @@ -715,7 +715,7 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } return status; @@ -1618,7 +1618,7 @@ static void xs_write_space(struct sock *sk) if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0) + if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) return; xprt_write_space(xprt); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6ced74690eee..45aebd966978 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2191,7 +2191,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, !timeo) break; - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); timeo = freezable_schedule_timeout(timeo); unix_state_lock(sk); @@ -2199,7 +2199,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, if (sock_flag(sk, SOCK_DEAD)) break; - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } finish_wait(sk_sleep(sk), &wait); @@ -2683,7 +2683,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, if (writable) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } -- cgit v1.2.3-59-g8ed1b From ceb5d58b217098a657f3850b7a2640f995032e62 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 29 Nov 2015 20:03:11 -0800 Subject: net: fix sock_wake_async() rcu protection Dmitry provided a syzkaller (http://github.com/google/syzkaller) triggering a fault in sock_wake_async() when async IO is requested. Said program stressed af_unix sockets, but the issue is generic and should be addressed in core networking stack. The problem is that by the time sock_wake_async() is called, we should not access the @flags field of 'struct socket', as the inode containing this socket might be freed without further notice, and without RCU grace period. We already maintain an RCU protected structure, "struct socket_wq" so moving SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA into it is the safe route. It also reduces number of cache lines needing dirtying, so might provide a performance improvement anyway. In followup patches, we might move remaining flags (SOCK_NOSPACE, SOCK_PASSCRED, SOCK_PASSSEC) to save 8 bytes and let 'struct socket' being mostly read and let it being shared between cpus. Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/net.h | 7 ++++++- include/net/sock.h | 23 ++++++++++++++++------- net/core/stream.c | 2 +- net/sctp/socket.c | 24 ++++++++++++++---------- net/socket.c | 21 +++++++-------------- 5 files changed, 44 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index f514e4dd5521..0b4ac7da583a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -34,6 +34,10 @@ struct inode; struct file; struct net; +/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located + * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. + * Eventually all flags will be in sk->sk_wq_flags. + */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 @@ -89,6 +93,7 @@ struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; + unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; @@ -202,7 +207,7 @@ enum { SOCK_WAKE_URG, }; -int sock_wake_async(struct socket *sk, int how, int band); +int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); int __sock_create(struct net *net, int family, int type, int proto, diff --git a/include/net/sock.h b/include/net/sock.h index c155d09d8af4..0434138c5f95 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -384,8 +384,10 @@ struct sock { int sk_rcvbuf; struct sk_filter __rcu *sk_filter; - struct socket_wq __rcu *sk_wq; - + union { + struct socket_wq __rcu *sk_wq; + struct socket_wq *sk_wq_raw; + }; #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif @@ -2005,20 +2007,27 @@ static inline unsigned long sock_wspace(struct sock *sk) return amt; } +/* Note: + * We use sk->sk_wq_raw, from contexts knowing this + * pointer is not NULL and cannot disappear/change. + */ static inline void sk_set_bit(int nr, struct sock *sk) { - set_bit(nr, &sk->sk_socket->flags); + set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { - clear_bit(nr, &sk->sk_socket->flags); + clear_bit(nr, &sk->sk_wq_raw->flags); } -static inline void sk_wake_async(struct sock *sk, int how, int band) +static inline void sk_wake_async(const struct sock *sk, int how, int band) { - if (sock_flag(sk, SOCK_FASYNC)) - sock_wake_async(sk->sk_socket, how, band); + if (sock_flag(sk, SOCK_FASYNC)) { + rcu_read_lock(); + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); + rcu_read_unlock(); + } } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might diff --git a/net/core/stream.c b/net/core/stream.c index 43309428644d..b96f7a79e544 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -39,7 +39,7 @@ void sk_stream_write_space(struct sock *sk) wake_up_interruptible_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) - sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); + sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 2353985d689c..5e35ef34008b 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6801,26 +6801,30 @@ no_packet: static void __sctp_write_space(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; - struct socket *sock = sk->sk_socket; - if ((sctp_wspace(asoc) > 0) && sock) { - if (waitqueue_active(&asoc->wait)) - wake_up_interruptible(&asoc->wait); + if (sctp_wspace(asoc) <= 0) + return; + + if (waitqueue_active(&asoc->wait)) + wake_up_interruptible(&asoc->wait); - if (sctp_writeable(sk)) { - wait_queue_head_t *wq = sk_sleep(sk); + if (sctp_writeable(sk)) { + struct socket_wq *wq; - if (wq && waitqueue_active(wq)) - wake_up_interruptible(wq); + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq) { + if (waitqueue_active(&wq->wait)) + wake_up_interruptible(&wq->wait); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) - sock_wake_async(sock, - SOCK_WAKE_SPACE, POLL_OUT); + sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); } + rcu_read_unlock(); } } diff --git a/net/socket.c b/net/socket.c index 16be908205fc..456fadb3d819 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1056,27 +1056,20 @@ static int sock_fasync(int fd, struct file *filp, int on) return 0; } -/* This function may be called only under socket lock or callback_lock or rcu_lock */ +/* This function may be called only under rcu_lock */ -int sock_wake_async(struct socket *sock, int how, int band) +int sock_wake_async(struct socket_wq *wq, int how, int band) { - struct socket_wq *wq; - - if (!sock) - return -1; - rcu_read_lock(); - wq = rcu_dereference(sock->wq); - if (!wq || !wq->fasync_list) { - rcu_read_unlock(); + if (!wq || !wq->fasync_list) return -1; - } + switch (how) { case SOCK_WAKE_WAITD: - if (test_bit(SOCKWQ_ASYNC_WAITDATA, &sock->flags)) + if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: - if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags)) + if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; /* fall through */ case SOCK_WAKE_IO: @@ -1086,7 +1079,7 @@ call_kill: case SOCK_WAKE_URG: kill_fasync(&wq->fasync_list, SIGURG, band); } - rcu_read_unlock(); + return 0; } EXPORT_SYMBOL(sock_wake_async); -- cgit v1.2.3-59-g8ed1b From 45f6fad84cc305103b28d73482b344d7f5b76f39 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 29 Nov 2015 19:37:57 -0800 Subject: ipv6: add complete rcu protection around np->opt This patch addresses multiple problems : UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions while socket is not locked : Other threads can change np->opt concurrently. Dmitry posted a syzkaller (http://github.com/google/syzkaller) program desmonstrating use-after-free. Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock() and dccp_v6_request_recv_sock() also need to use RCU protection to dereference np->opt once (before calling ipv6_dup_options()) This patch adds full RCU protection to np->opt Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- include/net/ipv6.h | 21 ++++++++++++++++++++- net/dccp/ipv6.c | 33 +++++++++++++++++++++------------ net/ipv6/af_inet6.c | 13 +++++++++---- net/ipv6/datagram.c | 4 +++- net/ipv6/exthdrs.c | 3 ++- net/ipv6/inet6_connection_sock.c | 11 ++++++++--- net/ipv6/ipv6_sockglue.c | 33 ++++++++++++++++++++++----------- net/ipv6/raw.c | 8 ++++++-- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 28 +++++++++++++++++----------- net/ipv6/udp.c | 8 ++++++-- net/l2tp/l2tp_ip6.c | 8 ++++++-- 13 files changed, 122 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0ef2a97ccdb5..402753bccafa 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -227,7 +227,7 @@ struct ipv6_pinfo { struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; - struct ipv6_txoptions *opt; + struct ipv6_txoptions __rcu *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct inet6_cork cork; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ea5a13ef85a6..9a5c9f013784 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock; */ struct ipv6_txoptions { + atomic_t refcnt; /* Length of this structure */ int tot_len; @@ -217,7 +218,7 @@ struct ipv6_txoptions { struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; - + struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; @@ -252,6 +253,24 @@ struct ipv6_fl_socklist { struct rcu_head rcu; }; +static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) +{ + struct ipv6_txoptions *opt; + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt && !atomic_inc_not_zero(&opt->refcnt)) + opt = NULL; + rcu_read_unlock(); + return opt; +} + +static inline void txopt_put(struct ipv6_txoptions *opt) +{ + if (opt && atomic_dec_and_test(&opt->refcnt)) + kfree_rcu(opt, rcu); +} + struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index db5fc2440a23..e7e0b9bc2a43 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -202,7 +202,9 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { @@ -219,7 +221,10 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6.daddr = ireq->ir_v6_rmt_addr; - err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + rcu_read_lock(); + err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -387,6 +392,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; @@ -488,13 +494,15 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ - if (np->opt != NULL) - newnp->opt = ipv6_dup_options(newsk, np->opt); - + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt != NULL) - inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + - newnp->opt->opt_flen); + if (opt) + inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + + opt->opt_flen; dccp_sync_mss(newsk, dst_mtu(dst)); @@ -757,6 +765,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; + struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; @@ -856,7 +865,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + final_p = fl6_update_dst(&fl6, opt, &final); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { @@ -876,9 +886,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; - if (np->opt != NULL) - icsk->icsk_ext_hdr_len = (np->opt->opt_flen + - np->opt->opt_nflen); + if (opt) + icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; inet->inet_dport = usin->sin6_port; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 44bb66bde0e2..38d66ddfb937 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -428,9 +428,11 @@ void inet6_destroy_sock(struct sock *sk) /* Free tx options */ - opt = xchg(&np->opt, NULL); - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } } EXPORT_SYMBOL_GPL(inet6_destroy_sock); @@ -659,7 +661,10 @@ int inet6_sk_rebuild_header(struct sock *sk) fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), + &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index d70b0238f468..517c55b01ba8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -167,8 +167,10 @@ ipv4_connected: security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - opt = flowlabel ? flowlabel->opt : np->opt; + rcu_read_lock(); + opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); final_p = fl6_update_dst(&fl6, opt, &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); err = 0; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index ce203b0402be..ea7c4d64a00a 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; + atomic_set(&opt2->refcnt, 1); } return opt2; } @@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); - + atomic_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 5d1c7cee2cb2..3ff5208772bb 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -78,7 +78,9 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = proto; fl6->daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); fl6->saddr = ireq->ir_v6_loc_addr; fl6->flowi6_oif = ireq->ir_iif; fl6->flowi6_mark = ireq->ir_mark; @@ -142,7 +144,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, fl6->fl6_dport = inet->inet_dport; security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); - final_p = fl6_update_dst(fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { @@ -175,7 +179,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused /* Restore final destination back after routing done */ fl6.daddr = sk->sk_v6_daddr; - res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + np->tclass); rcu_read_unlock(); return res; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 63e6956917c9..4449ad1f8114 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } - opt = xchg(&inet6_sk(sk)->opt, opt); + opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt, + opt); sk_dst_reset(sk); return opt; @@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } - opt = xchg(&np->opt, NULL); - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + opt = xchg((__force struct ipv6_txoptions **)&np->opt, + NULL); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } pktopt = xchg(&np->pktoptions, NULL); kfree_skb(pktopt); @@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; - opt = ipv6_renew_options(sk, np->opt, optname, + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = ipv6_renew_options(sk, opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); if (IS_ERR(opt)) { @@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; opt = ipv6_update_options(sk, opt); sticky_done: - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } break; } @@ -486,6 +493,7 @@ sticky_done: break; memset(opt, 0, sizeof(*opt)); + atomic_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_user(opt+1, optval, optlen)) @@ -502,8 +510,10 @@ update: retv = 0; opt = ipv6_update_options(sk, opt); done: - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } break; } case IPV6_UNICAST_HOPS: @@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_RTHDR: case IPV6_DSTOPTS: { + struct ipv6_txoptions *opt; lock_sock(sk); - len = ipv6_getsockopt_sticky(sk, np->opt, - optname, optval, len); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len); release_sock(sk); /* check if ipv6_getsockopt_sticky() returns err code */ if (len < 0) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dc65ec198f7c..99140986e887 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -733,6 +733,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { + struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; @@ -839,8 +840,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } - if (!opt) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -906,6 +909,7 @@ done: dst_release(dst); out: fl6_sock_release(flowlabel); + txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: dst_confirm(dst); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bb8f2fa1c7fb..eaf7ac496d50 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -222,7 +222,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = ireq->ir_mark; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c5429a636f1a..6a50bb4a0dae 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; + struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; @@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; - final_p = fl6_update_dst(&fl6, np->opt, &final); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); @@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; - if (np->opt) - icsk->icsk_ext_hdr_len = (np->opt->opt_flen + - np->opt->opt_nflen); + if (opt) + icsk->icsk_ext_hdr_len = opt->opt_flen + + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); @@ -461,7 +463,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), + np->tclass); err = net_xmit_eval(err); } @@ -972,6 +975,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * struct inet_request_sock *ireq; struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; struct tcp_sock *newtp; @@ -1098,13 +1102,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * but we make one more one thing there: reattach optmem to newsk. */ - if (np->opt) - newnp->opt = ipv6_dup_options(newsk, np->opt); - + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt) - inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + - newnp->opt->opt_flen); + if (opt) + inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 01bcb49619ee..9da3287a3923 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1110,6 +1110,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; + struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; struct flowi6 fl6; struct dst_entry *dst; @@ -1263,8 +1264,10 @@ do_udp_sendmsg: opt = NULL; connected = 0; } - if (!opt) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -1373,6 +1376,7 @@ release_dst: out: dst_release(dst); fl6_sock_release(flowlabel); + txopt_put(opt_to_free); if (!err) return len; /* diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index aca38d8aed8e..a2c8747d2936 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; @@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) opt = NULL; } - if (opt == NULL) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -631,6 +634,7 @@ done: dst_release(dst); out: fl6_sock_release(flowlabel); + txopt_put(opt_to_free); return err < 0 ? err : len; -- cgit v1.2.3-59-g8ed1b From 38ee8fb67c3457f36f5137073c4b8ac2436d2393 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Mon, 30 Nov 2015 12:17:06 -0200 Subject: sctp: convert sack_needed and sack_generation to bits They don't need to be any bigger than that and with this we start a new bitfield for tracking association runtime stuff, like zero window situation. Signed-off-by: Marcelo Ricardo Leitner Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 495c87e367b3..7bbb71081aeb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -775,10 +775,10 @@ struct sctp_transport { hb_sent:1, /* Is the Path MTU update pending on this tranport */ - pmtu_pending:1; + pmtu_pending:1, - /* Has this transport moved the ctsn since we last sacked */ - __u32 sack_generation; + /* Has this transport moved the ctsn since we last sacked */ + sack_generation:1; u32 dst_cookie; struct flowi fl; @@ -1482,19 +1482,19 @@ struct sctp_association { prsctp_capable:1, /* Can peer do PR-SCTP? */ auth_capable:1; /* Is peer doing SCTP-AUTH? */ - /* Ack State : This flag indicates if the next received + /* sack_needed : This flag indicates if the next received * : packet is to be responded to with a - * : SACK. This is initializedto 0. When a packet - * : is received it is incremented. If this value + * : SACK. This is initialized to 0. When a packet + * : is received sack_cnt is incremented. If this value * : reaches 2 or more, a SACK is sent and the * : value is reset to 0. Note: This is used only * : when no DATA chunks are received out of * : order. When DATA chunks are out of order, * : SACK's are not delayed (see Section 6). */ - __u8 sack_needed; /* Do we need to sack the peer? */ + __u8 sack_needed:1, /* Do we need to sack the peer? */ + sack_generation:1; __u32 sack_cnt; - __u32 sack_generation; __u32 adaptation_ind; /* Adaptation Code point. */ -- cgit v1.2.3-59-g8ed1b From 6bd4f355df2eae80b8a5c7b097371cd1e05f20d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Dec 2015 21:53:57 -0800 Subject: ipv6: kill sk_dst_lock While testing the np->opt RCU conversion, I found that UDP/IPv6 was using a mixture of xchg() and sk_dst_lock to protect concurrent changes to sk->sk_dst_cache, leading to possible corruptions and crashes. ip6_sk_dst_lookup_flow() uses sk_dst_check() anyway, so the simplest way to fix the mess is to remove sk_dst_lock completely, as we did for IPv4. __ip6_dst_store() and ip6_dst_store() share same implementation. sk_setup_caps() being called with socket lock being held or not, we have to use sk_dst_set() instead of __sk_dst_set() Note that I had to move the "np->dst_cookie = rt6_get_cookie(rt);" in ip6_dst_store() before the sk_setup_caps(sk, dst) call. This is because ip6_dst_store() can be called from process context, without any lock held. As soon as the dst is installed in sk->sk_dst_cache, dst can be freed from another cpu doing a concurrent ip6_dst_store() Doing the dst dereference before doing the install is needed to make sure no use after free would trigger. Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Signed-off-by: David S. Miller --- include/net/ip6_route.h | 17 ++++------------- include/net/sock.h | 3 +-- net/core/sock.c | 4 +--- net/dccp/ipv6.c | 4 ++-- net/ipv6/af_inet6.c | 2 +- net/ipv6/icmp.c | 14 -------------- net/ipv6/inet6_connection_sock.c | 10 +--------- net/ipv6/tcp_ipv6.c | 4 ++-- 8 files changed, 12 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 2bfb2ad2fab1..877f682989b8 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -133,27 +133,18 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); /* * Store a destination cache entry in a socket */ -static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, - const struct in6_addr *daddr, - const struct in6_addr *saddr) +static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); - struct rt6_info *rt = (struct rt6_info *) dst; + np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif - np->dst_cookie = rt6_get_cookie(rt); -} - -static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) -{ - spin_lock(&sk->sk_dst_lock); - __ip6_dst_store(sk, dst, daddr, saddr); - spin_unlock(&sk->sk_dst_lock); } static inline bool ipv6_unicast_destination(const struct sk_buff *skb) diff --git a/include/net/sock.h b/include/net/sock.h index 0434138c5f95..52d27ee924f4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -254,7 +254,6 @@ struct cg_proto; * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_dst_cache: destination cache - * @sk_dst_lock: destination cache lock * @sk_policy: flow policy * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed @@ -393,7 +392,7 @@ struct sock { #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; - spinlock_t sk_dst_lock; + /* Note: 32bit hole on 64bit arches */ atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; diff --git a/net/core/sock.c b/net/core/sock.c index 9d79569935a3..e31dfcee1729 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1530,7 +1530,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) skb_queue_head_init(&newsk->sk_receive_queue); skb_queue_head_init(&newsk->sk_write_queue); - spin_lock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); lockdep_set_class_and_name(&newsk->sk_callback_lock, af_callback_keys + newsk->sk_family, @@ -1607,7 +1606,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - __sk_dst_set(sk, dst); + sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; @@ -2388,7 +2387,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) } else sk->sk_wq = NULL; - spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e7e0b9bc2a43..9c6d0508e63a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -459,7 +459,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, * comment in that function for the gory details. -acme */ - __ip6_dst_store(newsk, dst, NULL, NULL); + ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; @@ -883,7 +883,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; - __ip6_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 38d66ddfb937..8ec0df75f1c4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -673,7 +673,7 @@ int inet6_sk_rebuild_header(struct sock *sk) return PTR_ERR(dst); } - __ip6_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, NULL, NULL); } return 0; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 36c5a98b0472..0a37ddc7af51 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -834,11 +834,6 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); } -/* - * Special lock-class for __icmpv6_sk: - */ -static struct lock_class_key icmpv6_socket_sk_dst_lock_key; - static int __net_init icmpv6_sk_init(struct net *net) { struct sock *sk; @@ -860,15 +855,6 @@ static int __net_init icmpv6_sk_init(struct net *net) net->ipv6.icmp_sk[i] = sk; - /* - * Split off their lock-class, because sk->sk_dst_lock - * gets used from softirqs, which is safe for - * __icmpv6_sk (because those never get directly used - * via userspace syscalls), but unsafe for normal sockets. - */ - lockdep_set_class(&sk->sk_dst_lock, - &icmpv6_socket_sk_dst_lock_key); - /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 3ff5208772bb..a7ca2cde2ecb 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -110,14 +110,6 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) } EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); -static inline -void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, - const struct in6_addr *daddr, - const struct in6_addr *saddr) -{ - __ip6_dst_store(sk, dst, daddr, saddr); -} - static inline struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) { @@ -153,7 +145,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = ip6_dst_lookup_flow(sk, fl6, final_p); if (!IS_ERR(dst)) - __inet6_csk_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, NULL, NULL); } return dst; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6a50bb4a0dae..e7aab561b7b4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -257,7 +257,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, NULL, NULL); if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && @@ -1060,7 +1060,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * */ newsk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(newsk, dst, NULL, NULL); + ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; -- cgit v1.2.3-59-g8ed1b From 4eaf3b84f2881c9c028f1d5e76c52ab575fe3a66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 1 Dec 2015 20:08:51 -0800 Subject: net_sched: fix qdisc_tree_decrease_qlen() races qdisc_tree_decrease_qlen() suffers from two problems on multiqueue devices. One problem is that it updates sch->q.qlen and sch->qstats.drops on the mq/mqprio root qdisc, while it should not : Daniele reported underflows errors : [ 681.774821] PAX: sch->q.qlen: 0 n: 1 [ 681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head; [ 681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G O 4.2.6.201511282239-1-grsec #1 [ 681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015 [ 681.774956] ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c [ 681.774959] ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b [ 681.774960] ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001 [ 681.774962] Call Trace: [ 681.774967] [] dump_stack+0x4c/0x7f [ 681.774970] [] report_size_overflow+0x34/0x50 [ 681.774972] [] qdisc_tree_decrease_qlen+0x152/0x160 [ 681.774976] [] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel] [ 681.774978] [] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel] [ 681.774980] [] __qdisc_run+0x4d/0x1d0 [ 681.774983] [] net_tx_action+0xc2/0x160 [ 681.774985] [] __do_softirq+0xf1/0x200 [ 681.774987] [] run_ksoftirqd+0x1e/0x30 [ 681.774989] [] smpboot_thread_fn+0x150/0x260 [ 681.774991] [] ? sort_range+0x40/0x40 [ 681.774992] [] kthread+0xe4/0x100 [ 681.774994] [] ? kthread_worker_fn+0x170/0x170 [ 681.774995] [] ret_from_fork+0x3e/0x70 mq/mqprio have their own ways to report qlen/drops by folding stats on all their queues, with appropriate locking. A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup() without proper locking : concurrent qdisc updates could corrupt the list that qdisc_match_from_root() parses to find a qdisc given its handle. Fix first problem adding a TCQ_F_NOPARENT qdisc flag that qdisc_tree_decrease_qlen() can use to abort its tree traversal, as soon as it meets a mq/mqprio qdisc children. Second problem can be fixed by RCU protection. Qdisc are already freed after RCU grace period, so qdisc_list_add() and qdisc_list_del() simply have to use appropriate rcu list variants. A future patch will add a per struct netdev_queue list anchor, so that qdisc_tree_decrease_qlen() can have more efficient lookups. Reported-by: Daniele Fucini Signed-off-by: Eric Dumazet Cc: Cong Wang Cc: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 +++ net/sched/sch_api.c | 27 ++++++++++++++++++--------- net/sched/sch_generic.c | 2 +- net/sched/sch_mq.c | 4 ++-- net/sched/sch_mqprio.c | 4 ++-- 5 files changed, 26 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4c79ce8c1f92..b2a8e6338576 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -61,6 +61,9 @@ struct Qdisc { */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ +#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : + * qdisc_tree_decrease_qlen() should stop. + */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index f43c8f33f09e..7ec667dd4ce1 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -253,7 +253,8 @@ int qdisc_set_default(const char *name) } /* We know handle. Find qdisc among all qdisc's attached to device - (root qdisc, all its children, children of children etc.) + * (root qdisc, all its children, children of children etc.) + * Note: caller either uses rtnl or rcu_read_lock() */ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) @@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) root->handle == handle) return root; - list_for_each_entry(q, &root->list, list) { + list_for_each_entry_rcu(q, &root->list, list) { if (q->handle == handle) return q; } @@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q) struct Qdisc *root = qdisc_dev(q)->qdisc; WARN_ON_ONCE(root == &noop_qdisc); - list_add_tail(&q->list, &root->list); + ASSERT_RTNL(); + list_add_tail_rcu(&q->list, &root->list); } } EXPORT_SYMBOL(qdisc_list_add); void qdisc_list_del(struct Qdisc *q) { - if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) - list_del(&q->list); + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + ASSERT_RTNL(); + list_del_rcu(&q->list); + } } EXPORT_SYMBOL(qdisc_list_del); @@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) if (n == 0) return; drops = max_t(int, n, 0); + rcu_read_lock(); while ((parentid = sch->parent)) { if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS)) - return; + break; + if (sch->flags & TCQ_F_NOPARENT) + break; + /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { - WARN_ON(parentid != TC_H_ROOT); - return; + WARN_ON_ONCE(parentid != TC_H_ROOT); + break; } cops = sch->ops->cl_ops; if (cops->qlen_notify) { @@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) sch->q.qlen -= n; __qdisc_qstats_drop(sch, drops); } + rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_decrease_qlen); @@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) - sch->flags |= TCQ_F_ONETXQUEUE; + sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->handle = handle; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index cb5d4ad32946..e82a1ad80aa5 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -737,7 +737,7 @@ static void attach_one_default_qdisc(struct net_device *dev, return; } if (!netif_is_multiqueue(dev)) - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; dev_queue->qdisc_sleeping = qdisc; } diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index f3cbaecd283a..3e82f047caaf 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) if (qdisc == NULL) goto err; priv->qdiscs[ntx] = qdisc; - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; @@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, *old = dev_graft_qdisc(dev_queue, new); if (new) - new->flags |= TCQ_F_ONETXQUEUE; + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 3811a745452c..ad70ecf57ce7 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) goto err; } priv->qdiscs[i] = qdisc; - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } /* If the mqprio options indicate that hardware should own @@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, *old = dev_graft_qdisc(dev_queue, new); if (new) - new->flags |= TCQ_F_ONETXQUEUE; + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); -- cgit v1.2.3-59-g8ed1b