From 419f9f896074ce8b21e88066e6f3515f18e5641c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 11 Apr 2010 02:15:53 +0000 Subject: tcp: Handle CHECKSUM_PARTIAL for SYNACK packets for IPv4 tcp: Handle CHECKSUM_PARTIAL for SYNACK packets for IPv4 This patch moves the common code between tcp_v4_send_check and tcp_v4_gso_send_check into a new function __tcp_v4_send_check. It then uses the new function in tcp_v4_send_synack so that it handles CHECKSUM_PARTIAL properly. Signed-off-by: Herbert Xu Tested-by: Yinghai Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3c23e70885f..aebfd28c508 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -519,26 +519,31 @@ out: sock_put(sk); } -/* This routine computes an IPv4 TCP checksum. */ -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +static void __tcp_v4_send_check(struct sk_buff *skb, + __be32 saddr, __be32 daddr) { - struct inet_sock *inet = inet_sk(sk); struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(len, inet->inet_saddr, - inet->inet_daddr, 0); + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(len, inet->inet_saddr, - inet->inet_daddr, + th->check = tcp_v4_check(skb->len, saddr, daddr, csum_partial(th, th->doff << 2, skb->csum)); } } +/* This routine computes an IPv4 TCP checksum. */ +void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +{ + struct inet_sock *inet = inet_sk(sk); + + __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); +} + int tcp_v4_gso_send_check(struct sk_buff *skb) { const struct iphdr *iph; @@ -551,10 +556,8 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) th = tcp_hdr(skb); th->check = 0; - th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v4_send_check(skb, iph->saddr, iph->daddr); return 0; } @@ -763,13 +766,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { - struct tcphdr *th = tcp_hdr(skb); - - th->check = tcp_v4_check(skb->len, - ireq->loc_addr, - ireq->rmt_addr, - csum_partial(th, skb->len, - skb->csum)); + __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, -- cgit v1.2.3-70-g09d2 From bb29624614c2afe2873ee8ee97cf09df42701694 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 11 Apr 2010 02:15:55 +0000 Subject: inet: Remove unused send_check length argument inet: Remove unused send_check length argument This patch removes the unused length argument from the send_check function in struct inet_connection_sock_af_ops. Signed-off-by: Herbert Xu Tested-by: Yinghai Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 +-- include/net/tcp.h | 2 +- net/dccp/dccp.h | 2 +- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 3 +-- net/dccp/output.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 9 insertions(+), 11 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 696d6e4ce68..52c8b8b8a0b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -37,8 +37,7 @@ struct tcp_congestion_ops; */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sk_buff *skb, int ipfragok); - void (*send_check)(struct sock *sk, int len, - struct sk_buff *skb); + void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/tcp.h b/include/net/tcp.h index 75be5a28815..70c5159f4b3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -423,7 +423,7 @@ extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); * TCP v4 functions exported for the inet6 API */ -extern void tcp_v4_send_check(struct sock *sk, int len, +extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); extern int tcp_v4_conn_request(struct sock *sk, diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 53f8e12d0c1..a10a61a1ded 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -223,7 +223,7 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb) skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0); } -extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); +extern void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); extern int dccp_retransmit_skb(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 52ffa1cde15..d9b11ef8694 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -349,7 +349,7 @@ static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb, return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum); } -void dccp_v4_send_check(struct sock *sk, int unused, struct sk_buff *skb) +void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3b11e41a292..ab1ab95946d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -60,8 +60,7 @@ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } -static inline void dccp_v6_send_check(struct sock *sk, int unused_value, - struct sk_buff *skb) +static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); diff --git a/net/dccp/output.c b/net/dccp/output.c index fc3f436440b..b8d98e3c052 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -129,7 +129,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - icsk->icsk_af_ops->send_check(sk, 0, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (set_ack) dccp_event_ack_sent(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index aebfd28c508..a24995cdc4b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -537,7 +537,7 @@ static void __tcp_v4_send_check(struct sk_buff *skb, } /* This routine computes an IPv4 TCP checksum. */ -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0dda86e72ad..0ae7ce7a71a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } #endif - icsk->icsk_af_ops->send_check(sk, skb->len, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->flags & TCPCB_FLAG_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f84c506c588..b429dfdd69d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -933,7 +933,7 @@ static void __tcp_v6_send_check(struct sk_buff *skb, } } -static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) +static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); -- cgit v1.2.3-70-g09d2 From fec5e652e58fa6017b2c9e06466cb2a6538de5b4 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 16 Apr 2010 16:01:27 -0700 Subject: rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 69 +++++++++++++++++++++++++++- include/net/inet_sock.h | 38 ++++++++++++++++ net/core/dev.c | 111 +++++++++++++++++++++++++++++++++++++-------- net/core/net-sysfs.c | 94 ++++++++++++++++++++++++++++++++++++-- net/core/sysctl_net_core.c | 68 +++++++++++++++++++++++++++ net/ipv4/af_inet.c | 29 ++++++++++-- net/ipv4/tcp_ipv4.c | 2 + net/ipv4/udp.c | 7 ++- 8 files changed, 389 insertions(+), 29 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 55c2086e1f0..649a0252686 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,14 +530,73 @@ struct rps_map { }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU and the + * tail pointer for that CPU's input queue at the time of last enqueue. + */ +struct rps_dev_flow { + u16 cpu; + u16 fill; + unsigned int last_qtail; +}; + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct work_struct free_work; + struct rps_dev_flow flows[0]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + (_num * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + */ +struct rps_sock_flow_table { + unsigned int mask; + u16 ents[0]; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ + (_num * sizeof(u16))) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) { + unsigned int cpu, index = hash & table->mask; + + /* We only give a hint, preemption can change cpu under us */ + cpu = raw_smp_processor_id(); + + if (table->ents[index] != cpu) + table->ents[index] = cpu; + } +} + +static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) + table->ents[hash & table->mask] = RPS_NO_CPU; +} + +extern struct rps_sock_flow_table *rps_sock_flow_table; + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map *rps_map; + struct rps_dev_flow_table *rps_flow_table; struct kobject kobj; struct netdev_rx_queue *first; atomic_t count; } ____cacheline_aligned_in_smp; -#endif +#endif /* CONFIG_RPS */ /* * This structure defines the management hooks for network devices. @@ -1333,11 +1392,19 @@ struct softnet_data { /* Elements below can be accessed between CPUs for RPS */ #ifdef CONFIG_RPS struct call_single_data csd ____cacheline_aligned_in_smp; + unsigned int input_queue_head; #endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; }; +static inline void incr_input_queue_head(struct softnet_data *queue) +{ +#ifdef CONFIG_RPS + queue->input_queue_head++; +#endif +} + DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); #define HAVE_NETIF_QUEUE diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83fd34437cf..b487bc1b99a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -101,6 +102,7 @@ struct rtable; * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts + * @rxhash - flow hash received from netif layer * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -124,6 +126,9 @@ struct inet_sock { __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; +#ifdef CONFIG_RPS + __u32 rxhash; +#endif struct ip_options *opt; __u8 tos; @@ -219,4 +224,37 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; } +static inline void inet_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_save_rxhash(const struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(inet_sk(sk)->rxhash != rxhash)) { + inet_rps_reset_flow(sk); + inet_sk(sk)->rxhash = rxhash; + } +#endif +} #endif /* _INET_SOCK_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e8041eb76ac..d7107ac835f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2203,19 +2203,28 @@ int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; #ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table *rps_sock_flow_table; +EXPORT_SYMBOL(rps_sock_flow_table); + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ -static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) { struct ipv6hdr *ip6; struct iphdr *ip; struct netdev_rx_queue *rxqueue; struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u8 ip_proto; + u16 tcpu; u32 addr1, addr2, ports, ihl; if (skb_rx_queue_recorded(skb)) { @@ -2232,7 +2241,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) } else rxqueue = dev->_rx; - if (!rxqueue->rps_map) + if (!rxqueue->rps_map && !rxqueue->rps_flow_table) goto done; if (skb->rxhash) @@ -2284,9 +2293,48 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) skb->rxhash = 1; got_hash: + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[skb->rxhash & + sock_flow_table->mask]; + + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) + rflow->last_qtail = per_cpu(softnet_data, + tcpu).input_queue_head; + } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + map = rcu_dereference(rxqueue->rps_map); if (map) { - u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -2320,13 +2368,14 @@ static void trigger_softirq(void *data) __napi_schedule(&queue->backlog); __get_cpu_var(netdev_rx_stat).received_rps++; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_RPS */ /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ -static int enqueue_to_backlog(struct sk_buff *skb, int cpu) +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) { struct softnet_data *queue; unsigned long flags; @@ -2341,6 +2390,10 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu) if (queue->input_pkt_queue.qlen) { enqueue: __skb_queue_tail(&queue->input_pkt_queue, skb); +#ifdef CONFIG_RPS + *qtail = queue->input_queue_head + + queue->input_pkt_queue.qlen; +#endif rps_unlock(queue); local_irq_restore(flags); return NET_RX_SUCCESS; @@ -2355,11 +2408,10 @@ enqueue: cpu_set(cpu, rcpus->mask[rcpus->select]); __raise_softirq_irqoff(NET_RX_SOFTIRQ); - } else - __napi_schedule(&queue->backlog); -#else - __napi_schedule(&queue->backlog); + goto enqueue; + } #endif + __napi_schedule(&queue->backlog); } goto enqueue; } @@ -2401,18 +2453,25 @@ int netif_rx(struct sk_buff *skb) #ifdef CONFIG_RPS { + struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); - ret = enqueue_to_backlog(skb, cpu); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); } #else - ret = enqueue_to_backlog(skb, get_cpu()); - put_cpu(); + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } #endif return ret; } @@ -2830,14 +2889,22 @@ out: int netif_receive_skb(struct sk_buff *skb) { #ifdef CONFIG_RPS - int cpu; + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + cpu = get_rps_cpu(skb->dev, skb, &rflow); - if (cpu < 0) - return __netif_receive_skb(skb); - else - return enqueue_to_backlog(skb, cpu); + if (cpu >= 0) { + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + ret = __netif_receive_skb(skb); + } + + return ret; #else return __netif_receive_skb(skb); #endif @@ -2856,6 +2923,7 @@ static void flush_backlog(void *arg) if (skb->dev == dev) { __skb_unlink(skb, &queue->input_pkt_queue); kfree_skb(skb); + incr_input_queue_head(queue); } rps_unlock(queue); } @@ -3179,6 +3247,7 @@ static int process_backlog(struct napi_struct *napi, int quota) local_irq_enable(); break; } + incr_input_queue_head(queue); rps_unlock(queue); local_irq_enable(); @@ -5542,8 +5611,10 @@ static int dev_cpu_callback(struct notifier_block *nfb, local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); + incr_input_queue_head(oldsd); + } return NOTIFY_OK; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 96ed6905b82..143052a22b9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -601,22 +602,109 @@ ssize_t store_rps_map(struct netdev_rx_queue *queue, return len; } +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned int val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%u\n", val); +} + +static void rps_dev_flow_table_release_work(struct work_struct *work) +{ + struct rps_dev_flow_table *table = container_of(work, + struct rps_dev_flow_table, free_work); + + vfree(table); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + + INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); + schedule_work(&table->free_work); +} + +ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned int count; + char *endp; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + count = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (count) { + int i; + + if (count > 1<<30) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } + count = roundup_pow_of_two(count); + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); + if (!table) + return -ENOMEM; + + table->mask = count - 1; + for (i = 0; i < count; i++) + table->flows[i].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = queue->rps_flow_table; + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + static struct rx_queue_attribute rps_cpus_attribute = __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); + static struct attribute *rx_queue_default_attrs[] = { &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct rps_map *map = queue->rps_map; struct netdev_rx_queue *first = queue->first; - if (map) - call_rcu(&map->rcu, rps_map_release); + if (queue->rps_map) + call_rcu(&queue->rps_map->rcu, rps_map_release); + + if (queue->rps_flow_table) + call_rcu(&queue->rps_flow_table->rcu, + rps_dev_flow_table_release); if (atomic_dec_and_test(&first->count)) kfree(first); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b7b6b8208f7..dcc7d25996a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,12 +11,72 @@ #include #include #include +#include #include #include #include #include +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rps_sock_flow_table; + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -82,6 +142,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_RPS + { + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 193dcd6ed64..c5376c72550 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -419,6 +419,8 @@ int inet_release(struct socket *sock) if (sk) { long timeout; + inet_rps_reset_flow(sk); + /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -720,6 +722,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -728,12 +732,13 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(inet_sendmsg); - static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -743,6 +748,22 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, return sock_no_sendpage(sock, page, offset, size, flags); } +int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + int addr_len = 0; + int err; + + inet_rps_record_flow(sk); + + err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, + flags & ~MSG_DONTWAIT, &addr_len); + if (err >= 0) + msg->msg_namelen = addr_len; + return err; +} +EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { @@ -872,7 +893,7 @@ const struct proto_ops inet_stream_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = tcp_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = tcp_sendpage, .splice_read = tcp_splice_read, @@ -899,7 +920,7 @@ const struct proto_ops inet_dgram_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT @@ -929,7 +950,7 @@ static const struct proto_ops inet_sockraw_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a24995cdc4b..ad08392a738 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1672,6 +1672,8 @@ process: skb->dev = NULL; + inet_rps_save_rxhash(sk, skb->rxhash); + bh_lock_sock_nested(sk); ret = 0; if (!sock_owned_by_user(sk)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8fef859db35..666b963496f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1217,6 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; + inet_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1258,8 +1259,12 @@ EXPORT_SYMBOL(udp_lib_unhash); static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int rc = sock_queue_rcv_skb(sk, skb); + int rc; + + if (inet_sk(sk)->inet_daddr) + inet_rps_save_rxhash(sk, skb->rxhash); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); -- cgit v1.2.3-70-g09d2 From 0eae88f31ca2b88911ce843452054139e028771f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Apr 2010 19:06:52 -0700 Subject: net: Fix various endianness glitches Sparse can help us find endianness bugs, but we need to make some cleanups to be able to more easily spot real bugs. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 2 +- net/bridge/br_private.h | 15 ++++++++------- net/ethernet/eth.c | 2 +- net/ipv4/af_inet.c | 8 ++++---- net/ipv4/ipmr.c | 10 +++++----- net/ipv4/route.c | 29 ++++++++++++++--------------- net/ipv4/tcp.c | 15 ++++++++------- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/udp.c | 8 ++++---- net/ipv6/addrconf.c | 3 ++- net/ipv6/ip6_fib.c | 3 ++- net/ipv6/tcp_ipv6.c | 4 ++-- net/ipv6/udp.c | 4 ++-- net/sched/sch_sfq.c | 10 +++++----- net/sunrpc/xprt.c | 2 +- net/xfrm/xfrm_hash.h | 3 ++- 17 files changed, 65 insertions(+), 61 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3fe86ffc069..61e1d1094b8 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -29,7 +29,7 @@ static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, __be32 ip) { - return jhash_1word(mdb->secret, (u32)ip) & (mdb->max - 1); + return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1); } static struct net_bridge_mdb_entry *__br_mdb_ip_get( diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 791d4ab0fd4..63181e4a2a6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -130,19 +130,20 @@ struct net_bridge_port #endif }; +struct br_cpu_netstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + struct net_bridge { spinlock_t lock; struct list_head port_list; struct net_device *dev; - struct br_cpu_netstats __percpu { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; - } *stats; - + struct br_cpu_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; unsigned long feature_mask; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 205a1c12f3c..35846964082 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -136,7 +136,7 @@ int eth_rebuild_header(struct sk_buff *skb) default: printk(KERN_DEBUG "%s: unable to resolve type %X addresses.\n", - dev->name, (int)eth->h_proto); + dev->name, (__force int)eth->h_proto); memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); break; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ca7290c2e6..9f52880fae1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1323,8 +1323,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto out_unlock; - id = ntohl(*(u32 *)&iph->id); - flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); + id = ntohl(*(__be32 *)&iph->id); + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); id >>= 16; for (p = *head; p; p = p->next) { @@ -1337,8 +1337,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if ((iph->protocol ^ iph2->protocol) | (iph->tos ^ iph2->tos) | - (iph->saddr ^ iph2->saddr) | - (iph->daddr ^ iph2->daddr)) { + ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | + ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7d8a2bcecb7..a2df5012a1d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1772,10 +1772,10 @@ int ip_mr_input(struct sk_buff *skb) vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ipmr_cache_unresolved(mrt, vif, skb); + int err2 = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); - return err; + return err2; } read_unlock(&mrt_lock); kfree_skb(skb); @@ -2227,9 +2227,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) const struct ipmr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; - seq_printf(seq, "%08lX %08lX %-3hd", - (unsigned long) mfc->mfc_mcastgrp, - (unsigned long) mfc->mfc_origin, + seq_printf(seq, "%08X %08X %-3hd", + (__force u32) mfc->mfc_mcastgrp, + (__force u32) mfc->mfc_origin, mfc->mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cb562fdd9b9..a947428ef0a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -258,10 +258,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); (__raw_get_cpu_var(rt_cache_stat).field++) static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx, - int genid) + int genid) { - return jhash_3words((__force u32)(__be32)(daddr), - (__force u32)(__be32)(saddr), + return jhash_3words((__force u32)daddr, (__force u32)saddr, idx, genid) & rt_hash_mask; } @@ -378,12 +377,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) struct rtable *r = v; int len; - seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t" - "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", + seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" + "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->u.dst.dev ? r->u.dst.dev->name : "*", - (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway, + (__force u32)r->rt_dst, + (__force u32)r->rt_gateway, r->rt_flags, atomic_read(&r->u.dst.__refcnt), - r->u.dst.__use, 0, (unsigned long)r->rt_src, + r->u.dst.__use, 0, (__force u32)r->rt_src, (dst_metric(&r->u.dst, RTAX_ADVMSS) ? (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0), dst_metric(&r->u.dst, RTAX_WINDOW), @@ -685,18 +685,17 @@ static inline bool rt_caching(const struct net *net) static inline bool compare_hash_inputs(const struct flowi *fl1, const struct flowi *fl2) { - return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | - (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) | + return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | + ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | (fl1->iif ^ fl2->iif)) == 0); } static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) { - return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | - (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) | + return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | + ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | (fl1->mark ^ fl2->mark) | - (*(u16 *)&fl1->nl_u.ip4_u.tos ^ - *(u16 *)&fl2->nl_u.ip4_u.tos) | + (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) | (fl1->oif ^ fl2->oif) | (fl1->iif ^ fl2->iif)) == 0; } @@ -2319,8 +2318,8 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; rth = rcu_dereference(rth->u.dst.rt_next)) { - if (((rth->fl.fl4_dst ^ daddr) | - (rth->fl.fl4_src ^ saddr) | + if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) | + ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) | (rth->fl.iif ^ iif) | rth->fl.oif | (rth->fl.fl4_tos ^ tos)) == 0 && diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77208334a61..6689c61cab4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2721,7 +2721,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct tcphdr *th2; unsigned int len; unsigned int thlen; - unsigned int flags; + __be32 flags; unsigned int mss = 1; unsigned int hlen; unsigned int off; @@ -2771,10 +2771,10 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) found: flush = NAPI_GRO_CB(p)->flush; - flush |= flags & TCP_FLAG_CWR; - flush |= (flags ^ tcp_flag_word(th2)) & - ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); - flush |= th->ack_seq ^ th2->ack_seq; + flush |= (__force int)(flags & TCP_FLAG_CWR); + flush |= (__force int)((flags ^ tcp_flag_word(th2)) & + ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); + flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); @@ -2795,8 +2795,9 @@ found: out_check_final: flush = len < mss; - flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | - TCP_FLAG_SYN | TCP_FLAG_FIN); + flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH | + TCP_FLAG_RST | TCP_FLAG_SYN | + TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = head; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad08392a738..4d6717d1e61 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1286,8 +1286,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_release; /* Secret recipe starts with IP addresses */ - *mess++ ^= daddr; - *mess++ ^= saddr; + *mess++ ^= (__force u32)daddr; + *mess++ ^= (__force u32)saddr; /* plus variable length Initiator Cookie */ c = (u8 *)mess; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2b7d71fb843..429ad9286ef 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -861,7 +861,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { - th->urg_ptr = 0xFFFF; + th->urg_ptr = htons(0xFFFF); th->urg = 1; } } @@ -2485,7 +2485,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, *tail-- ^= TCP_SKB_CB(skb)->seq + 1; /* recommended */ - *tail-- ^= ((th->dest << 16) | th->source); + *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source); *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */ sha_transform((__u32 *)&xvp->cookie_bakery[0], diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 666b963496f..1e18f9cc924 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -307,13 +307,13 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, unsigned int port) { - return jhash_1word(saddr, net_hash_mix(net)) ^ port; + return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = - udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum); + udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); @@ -466,14 +466,14 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, daddr, hnum, dif, hslot2, slot2); if (!result) { - hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum); + hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) goto begin; result = udp4_lib_lookup2(net, saddr, sport, - INADDR_ANY, hnum, dif, + htonl(INADDR_ANY), hnum, dif, hslot2, slot2); } rcu_read_unlock(); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7cba8845242..34d2d649e39 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -588,7 +588,8 @@ static u32 ipv6_addr_hash(const struct in6_addr *addr) * We perform the hash function over the last 64 bits of the address * This will include the IEEE address token on links that support it. */ - return jhash_2words(addr->s6_addr32[2], addr->s6_addr32[3], 0) + return jhash_2words((__force u32)addr->s6_addr32[2], + (__force u32)addr->s6_addr32[3], 0) & (IN6_ADDR_HSIZE - 1); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index dc6e0b8f260..92a122b7795 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -144,7 +144,8 @@ static __inline__ __be32 addr_bit_set(void *token, int fn_bit) * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ - return (1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; + return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & + addr[fn_bit >> 5]; } static __inline__ struct fib6_node * node_alloc(void) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index bd5ef7b6e48..a92b4a5cd8b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1234,12 +1234,12 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; /* Secret recipe starts with IP addresses */ - d = &ipv6_hdr(skb)->daddr.s6_addr32[0]; + d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0]; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; - d = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0]; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 90824852f59..92bf9033e24 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -91,9 +91,9 @@ static unsigned int udp6_portaddr_hash(struct net *net, if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) - hash = jhash_1word(addr6->s6_addr32[3], mix); + hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else - hash = jhash2(addr6->s6_addr32, 4, mix); + hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c5a9ac56600..c65762823f5 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -123,8 +123,8 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) case htons(ETH_P_IP): { const struct iphdr *iph = ip_hdr(skb); - h = iph->daddr; - h2 = iph->saddr ^ iph->protocol; + h = (__force u32)iph->daddr; + h2 = (__force u32)iph->saddr ^ iph->protocol; if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) && (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP || @@ -138,8 +138,8 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) case htons(ETH_P_IPV6): { struct ipv6hdr *iph = ipv6_hdr(skb); - h = iph->daddr.s6_addr32[3]; - h2 = iph->saddr.s6_addr32[3] ^ iph->nexthdr; + h = (__force u32)iph->daddr.s6_addr32[3]; + h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr; if (iph->nexthdr == IPPROTO_TCP || iph->nexthdr == IPPROTO_UDP || iph->nexthdr == IPPROTO_UDPLITE || @@ -150,7 +150,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) break; } default: - h = (unsigned long)skb_dst(skb) ^ skb->protocol; + h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol; h2 = (unsigned long)skb->sk; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 42f09ade004..699ade68aac 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -974,7 +974,7 @@ void xprt_reserve(struct rpc_task *task) static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) { - return xprt->xid++; + return (__force __be32)xprt->xid++; } static inline void xprt_init_xid(struct rpc_xprt *xprt) diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index e5195c99f71..1396572d2ad 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -16,7 +16,8 @@ static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr) static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) { - return ntohl(daddr->a4 + saddr->a4); + u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; + return ntohl((__force __be32)sum); } static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) -- cgit v1.2.3-70-g09d2 From c58dc01babfd58ec9e71a6ce080150dc27755d88 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 27 Apr 2010 15:05:31 -0700 Subject: net: Make RFS socket operations not be inet specific. Idea from Eric Dumazet. As for placement inside of struct sock, I tried to choose a place that otherwise has a 32-bit hole on 64-bit systems. Signed-off-by: David S. Miller Acked-by: Eric Dumazet --- include/net/inet_sock.h | 37 ------------------------------------- include/net/sock.h | 38 ++++++++++++++++++++++++++++++++++++++ net/ipv4/af_inet.c | 8 ++++---- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 4 ++-- 5 files changed, 45 insertions(+), 44 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c1d42957b86..1653de515ce 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -102,7 +102,6 @@ struct rtable; * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts - * @rxhash - flow hash received from netif layer * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -126,9 +125,6 @@ struct inet_sock { __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; -#ifdef CONFIG_RPS - __u32 rxhash; -#endif struct ip_options *opt; __u8 tos; @@ -224,37 +220,4 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; } -static inline void inet_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); - rcu_read_unlock(); -#endif -} - -static inline void inet_rps_reset_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); - rcu_read_unlock(); -#endif -} - -static inline void inet_rps_save_rxhash(struct sock *sk, u32 rxhash) -{ -#ifdef CONFIG_RPS - if (unlikely(inet_sk(sk)->rxhash != rxhash)) { - inet_rps_reset_flow(sk); - inet_sk(sk)->rxhash = rxhash; - } -#endif -} #endif /* _INET_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 4081db86a35..07822280d95 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -198,6 +198,7 @@ struct sock_common { * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting + * @sk_rxhash: flow hash received from netif layer * @sk_filter: socket filtering instructions * @sk_protinfo: private area, net family specific, when not using slab * @sk_timer: sock cleanup timer @@ -279,6 +280,9 @@ struct sock { int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; +#ifdef CONFIG_RPS + __u32 sk_rxhash; +#endif unsigned long sk_flags; unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; @@ -620,6 +624,40 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) return sk->sk_backlog_rcv(sk, skb); } +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_save_rxhash(struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(sk->sk_rxhash != rxhash)) { + sock_rps_reset_flow(sk); + sk->sk_rxhash = rxhash; + } +#endif +} + #define sk_wait_event(__sk, __timeo, __condition) \ ({ int __rc; \ release_sock(__sk); \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9f52880fae1..c6c43bcd1c6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -419,7 +419,7 @@ int inet_release(struct socket *sock) if (sk) { long timeout; - inet_rps_reset_flow(sk); + sock_rps_reset_flow(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -722,7 +722,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) @@ -737,7 +737,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, { struct sock *sk = sock->sk; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) @@ -755,7 +755,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, int addr_len = 0; int err; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4d6717d1e61..771f8146a2e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1672,7 +1672,7 @@ process: skb->dev = NULL; - inet_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb->rxhash); bh_lock_sock_nested(sk); ret = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1e18f9cc924..fa3d2874db4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1217,7 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; - inet_rps_save_rxhash(sk, 0); + sock_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1262,7 +1262,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) int rc; if (inet_sk(sk)->inet_daddr) - inet_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb->rxhash); rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { -- cgit v1.2.3-70-g09d2 From a465419b1febb603821f924805529cff89cafeed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 May 2010 00:36:33 -0700 Subject: net: Introduce sk_route_nocaps TCP-MD5 sessions have intermittent failures, when route cache is invalidated. ip_queue_xmit() has to find a new route, calls sk_setup_caps(sk, &rt->u.dst), destroying the sk->sk_route_caps &= ~NETIF_F_GSO_MASK that MD5 desperately try to make all over its way (from tcp_transmit_skb() for example) So we send few bad packets, and everything is fine when tcp_transmit_skb() is called again for this socket. Since ip_queue_xmit() is at a lower level than TCP-MD5, I chose to use a socket field, sk_route_nocaps, containing bits to mask on sk_route_caps. Reported-by: Bhaskar Dutta Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 8 ++++++++ net/core/sock.c | 1 + net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- 5 files changed, 15 insertions(+), 6 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/sock.h b/include/net/sock.h index 328e03f47dd..aed16eb9db4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -177,6 +177,7 @@ struct sock_common { * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) + * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_lingertime: %SO_LINGER l_linger setting @@ -276,6 +277,7 @@ struct sock { int sk_forward_alloc; gfp_t sk_allocation; int sk_route_caps; + int sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; @@ -1335,6 +1337,12 @@ static inline int sk_can_gso(const struct sock *sk) extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst); +static inline void sk_nocaps_add(struct sock *sk, int flags) +{ + sk->sk_route_nocaps |= flags; + sk->sk_route_caps &= ~flags; +} + static inline int skb_copy_to_page(struct sock *sk, char __user *from, struct sk_buff *skb, struct page *page, int off, int copy) diff --git a/net/core/sock.c b/net/core/sock.c index 94c4affdda9..63530a03b8c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1231,6 +1231,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; + sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { if (dst->header_len) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 771f8146a2e..202cf09c4cd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -891,7 +891,7 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -1021,7 +1021,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, return -EINVAL; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); @@ -1462,7 +1462,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (newkey != NULL) tcp_v4_md5_do_add(newsk, newinet->inet_daddr, newkey, key->keylen); - newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5db3a2c6cb3..18a3302480c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -873,7 +873,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, NULL, skb); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6603511e367..2b7c3a100e2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -604,7 +604,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -741,7 +741,7 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, return -ENOMEM; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); -- cgit v1.2.3-70-g09d2