From cf66ba58b5cb8b1526e9dd2fb96ff8db048d4d44 Mon Sep 17 00:00:00 2001 From: Koki Sanagi Date: Mon, 23 Aug 2010 18:45:02 +0900 Subject: netdev: Add tracepoints to netdev layer This patch adds tracepoint to dev_queue_xmit, dev_hard_start_xmit, netif_rx and netif_receive_skb. These tracepoints help you to monitor network driver's input/output. -0 [001] 112447.902030: netif_rx: dev=eth1 skbaddr=f3ef0900 len=84 -0 [001] 112447.902039: netif_receive_skb: dev=eth1 skbaddr=f3ef0900 len=84 sshd-6828 [000] 112447.903257: net_dev_queue: dev=eth4 skbaddr=f3fca538 len=226 sshd-6828 [000] 112447.903260: net_dev_xmit: dev=eth4 skbaddr=f3fca538 len=226 rc=0 Signed-off-by: Koki Sanagi Acked-by: David S. Miller Acked-by: Neil Horman Cc: Mathieu Desnoyers Cc: Kaneshige Kenji Cc: Izumo Taku Cc: Kosaki Motohiro Cc: Lai Jiangshan Cc: Scott Mcmillan Cc: Steven Rostedt Cc: Eric Dumazet LKML-Reference: <4C72431E.3000901@jp.fujitsu.com> Signed-off-by: Frederic Weisbecker --- net/core/dev.c | 6 ++++++ net/core/net-traces.c | 1 + 2 files changed, 7 insertions(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 3721fbb9a83c..5a4fbc7405e2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -128,6 +128,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -1978,6 +1979,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } rc = ops->ndo_start_xmit(skb, dev); + trace_net_dev_xmit(skb, rc); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; @@ -1998,6 +2000,7 @@ gso: skb_dst_drop(nskb); rc = ops->ndo_start_xmit(nskb, dev); + trace_net_dev_xmit(nskb, rc); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; @@ -2186,6 +2189,7 @@ int dev_queue_xmit(struct sk_buff *skb) #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif + trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; @@ -2512,6 +2516,7 @@ int netif_rx(struct sk_buff *skb) if (netdev_tstamp_prequeue) net_timestamp_check(skb); + trace_netif_rx(skb); #ifdef CONFIG_RPS { struct rps_dev_flow voidflow, *rflow = &voidflow; @@ -2828,6 +2833,7 @@ static int __netif_receive_skb(struct sk_buff *skb) if (!netdev_tstamp_prequeue) net_timestamp_check(skb); + trace_netif_receive_skb(skb); if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb)) return NET_RX_SUCCESS; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index afa6380ed88a..7f1bb2aba03b 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -26,6 +26,7 @@ #define CREATE_TRACE_POINTS #include +#include #include EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); -- cgit v1.2.3 From 07dc22e7295f25526f110d704655ff0ea7687420 Mon Sep 17 00:00:00 2001 From: Koki Sanagi Date: Mon, 23 Aug 2010 18:46:12 +0900 Subject: skb: Add tracepoints to freeing skb This patch adds tracepoint to consume_skb and add trace_kfree_skb before __kfree_skb in skb_free_datagram_locked and net_tx_action. Combinating with tracepoint on dev_hard_start_xmit, we can check how long it takes to free transmitted packets. And using it, we can calculate how many packets driver had at that time. It is useful when a drop of transmitted packet is a problem. sshd-6828 [000] 112689.258154: consume_skb: skbaddr=f2d99bb8 Signed-off-by: Koki Sanagi Acked-by: David S. Miller Acked-by: Neil Horman Cc: Mathieu Desnoyers Cc: Kaneshige Kenji Cc: Izumo Taku Cc: Kosaki Motohiro Cc: Lai Jiangshan Cc: Scott Mcmillan Cc: Steven Rostedt Cc: Eric Dumazet LKML-Reference: <4C724364.50903@jp.fujitsu.com> Signed-off-by: Frederic Weisbecker --- include/trace/events/skb.h | 17 +++++++++++++++++ net/core/datagram.c | 1 + net/core/dev.c | 2 ++ net/core/skbuff.c | 1 + 4 files changed, 21 insertions(+) (limited to 'net/core') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 4b2be6dc76f0..75ce9d500d8e 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb, __entry->skbaddr, __entry->protocol, __entry->location) ); +TRACE_EVENT(consume_skb, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb), + + TP_STRUCT__entry( + __field( void *, skbaddr ) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + ), + + TP_printk("skbaddr=%p", __entry->skbaddr) +); + TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), diff --git a/net/core/datagram.c b/net/core/datagram.c index 251997a95483..282806ba7a57 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -243,6 +243,7 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ + trace_kfree_skb(skb, skb_free_datagram_locked); __kfree_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); diff --git a/net/core/dev.c b/net/core/dev.c index 5a4fbc7405e2..2308cce48048 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -129,6 +129,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -2576,6 +2577,7 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3a2513f0d0c3..12e61e351d0e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -466,6 +466,7 @@ void consume_skb(struct sk_buff *skb) smp_rmb(); else if (likely(!atomic_dec_and_test(&skb->users))) return; + trace_consume_skb(skb); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); -- cgit v1.2.3 From f064af1e500a2bf4607706f0f458163bdb2a6ea5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Sep 2010 12:43:39 +0000 Subject: net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) spin_lock_bh(slock) We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa Tested-by: Tetsuo Handa Signed-off-by: Eric Dumazet CC: Jarek Poplawski Tested-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 8 ++++---- net/rds/tcp_connect.c | 4 ++-- net/rds/tcp_listen.c | 4 ++-- net/rds/tcp_recv.c | 4 ++-- net/rds/tcp_send.c | 4 ++-- net/sunrpc/xprtsock.c | 28 ++++++++++++++-------------- 6 files changed, 26 insertions(+), 26 deletions(-) (limited to 'net/core') diff --git a/net/core/sock.c b/net/core/sock.c index b05b9b6ddb87..ef30e9d286e7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk) { int uid; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); @@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index c397524c039c..c519939e8da9 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { state_change = sk->sk_state_change; @@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk) break; } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); state_change(sk); } diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 975183fe6950..27844f231d10 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) rdsdebug("listen data ready sk %p\n", sk); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ready = sk->sk_user_data; if (ready == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) queue_work(rds_wq, &rds_tcp_listen_work); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 1aba6878fa5d..e43797404102 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) rdsdebug("data ready sk %p bytes %d\n", sk, bytes); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM) queue_delayed_work(rds_wq, &conn->c_recv_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index a28b895ff0d1..2f012a07d94d 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { write_space = sk->sk_write_space; @@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk) queue_delayed_work(rds_wq, &conn->c_send_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); /* * write_space is only called when data leaves tcp's send queue if diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index b6309db56226..fe9306bf10cc 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) u32 _xid; __be32 *xp; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); dprintk("RPC: xs_udp_data_ready...\n"); if (!(xprt = xprt_from_sock(sk))) goto out; @@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) dropit: skb_free_datagram(sk, skb); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) @@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) dprintk("RPC: xs_tcp_data_ready...\n"); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; if (xprt->shutdown) @@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); } while (read > 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); @@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk) switch (sk->sk_state) { case TCP_ESTABLISHED: - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt_wake_pending_tasks(xprt, -EAGAIN); } - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->transport_lock); break; case TCP_FIN_WAIT1: /* The client initiated a shutdown of the socket */ @@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk) xs_sock_mark_closed(xprt); } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" @@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk) __func__, xprt, sk->sk_err); xprt_wake_pending_tasks(xprt, -EAGAIN); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) @@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk) */ static void xs_udp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) -- cgit v1.2.3 From 01db403cf99f739f86903314a489fb420e0e254f Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 27 Sep 2010 20:24:54 -0700 Subject: tcp: Fix >4GB writes on 64-bit. Fixes kernel bugzilla #16603 tcp_sendmsg() truncates iov_len to an 'int' which a 4GB write to write zero bytes, for example. There is also the problem higher up of how verify_iovec() works. It wants to prevent the total length from looking like an error return value. However it does this using 'int', but syscalls return 'long' (and thus signed 64-bit on 64-bit machines). So it could trigger false-positives on 64-bit as written. So fix it to use 'long'. Reported-by: Olaf Bonorden Reported-by: Daniel Büse Reported-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/socket.h | 2 +- net/core/iovec.c | 5 +++-- net/ipv4/tcp.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/include/linux/socket.h b/include/linux/socket.h index a2fada9becb6..a8f56e1ec760 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -322,7 +322,7 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, int offset, unsigned int len, __wsum *csump); -extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); +extern long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, int offset, int len); diff --git a/net/core/iovec.c b/net/core/iovec.c index 1cd98df412df..e6b133b77ccb 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,9 +35,10 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct; + long err; if (m->msg_namelen) { if (mode == VERIFY_READ) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 95d75d443927..f115ea68a4ef 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -943,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; -- cgit v1.2.3