diff options
| -rw-r--r-- | Documentation/networking/ip-sysctl.txt | 13 | ||||
| -rw-r--r-- | include/linux/tcp.h | 1 | ||||
| -rw-r--r-- | include/net/sock.h | 19 | ||||
| -rw-r--r-- | include/net/tcp.h | 14 | ||||
| -rw-r--r-- | include/uapi/linux/tcp.h | 1 | ||||
| -rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 7 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 7 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 1 | ||||
| -rw-r--r-- | net/ipv4/tcp_output.c | 3 | ||||
| -rw-r--r-- | net/ipv6/tcp_ipv6.c | 1 |
10 files changed, 61 insertions, 6 deletions
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 10742902146f..53cea9bcb14c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -516,6 +516,19 @@ tcp_wmem - vector of 3 INTEGERs: min, default, max this value is ignored. Default: between 64K and 4MB, depending on RAM size. +tcp_notsent_lowat - UNSIGNED INTEGER + A TCP socket can control the amount of unsent bytes in its write queue, + thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll() + reports POLLOUT events if the amount of unsent bytes is below a per + socket value, and if the write queue is not full. sendmsg() will + also not add new buffers if the limit is hit. + + This global variable controls the amount of unsent data for + sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change + to the global variable has immediate effect. + + Default: UINT_MAX (0xFFFFFFFF) + tcp_workaround_signed_windows - BOOLEAN If set, assume no receipt of a window scaling option means the remote TCP is broken and treats the window as a signed quantity. diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 472120b4fac5..9640803a17a7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -238,6 +238,7 @@ struct tcp_sock { u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ diff --git a/include/net/sock.h b/include/net/sock.h index d0b5fdee50a2..b9f2b095b1ab 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -746,11 +746,6 @@ static inline int sk_stream_wspace(const struct sock *sk) extern void sk_stream_write_space(struct sock *sk); -static inline bool sk_stream_memory_free(const struct sock *sk) -{ - return sk->sk_wmem_queued < sk->sk_sndbuf; -} - /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { @@ -950,6 +945,7 @@ struct proto { unsigned int inuse_idx; #endif + bool (*stream_memory_free)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ @@ -1088,11 +1084,22 @@ static inline struct cg_proto *parent_cg_proto(struct proto *proto, } #endif +static inline bool sk_stream_memory_free(const struct sock *sk) +{ + if (sk->sk_wmem_queued >= sk->sk_sndbuf) + return false; + + return sk->sk_prot->stream_memory_free ? + sk->sk_prot->stream_memory_free(sk) : true; +} + static inline bool sk_stream_is_writeable(const struct sock *sk) { - return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk); + return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && + sk_stream_memory_free(sk); } + static inline bool sk_has_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure != NULL; diff --git a/include/net/tcp.h b/include/net/tcp.h index c5868471abae..18fc999dae3c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -284,6 +284,7 @@ extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; +extern unsigned int sysctl_tcp_notsent_lowat; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -1539,6 +1540,19 @@ extern int tcp_gro_complete(struct sk_buff *skb); extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); +static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) +{ + return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat; +} + +static inline bool tcp_stream_memory_free(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 notsent_bytes = tp->write_seq - tp->snd_nxt; + + return notsent_bytes < tcp_notsent_lowat(tp); +} + #ifdef CONFIG_PROC_FS extern int tcp4_proc_init(void); extern void tcp4_proc_exit(void); diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8d776ebc4829..377f1e59411d 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -111,6 +111,7 @@ enum { #define TCP_REPAIR_OPTIONS 22 #define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ #define TCP_TIMESTAMP 24 +#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b2c123c44d69..69ed203802da 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -555,6 +555,13 @@ static struct ctl_table ipv4_table[] = { .extra1 = &one, }, { + .procname = "tcp_notsent_lowat", + .data = &sysctl_tcp_notsent_lowat, + .maxlen = sizeof(sysctl_tcp_notsent_lowat), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5eca9060bb8e..c27e81392398 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2631,6 +2631,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else tp->tsoffset = val - tcp_time_stamp; break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: err = -ENOPROTOOPT; break; @@ -2847,6 +2851,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_TIMESTAMP: val = tcp_time_stamp + tp->tsoffset; break; + case TCP_NOTSENT_LOWAT: + val = tp->notsent_lowat; + break; default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2e3f129df0eb..2a5d5c469d17 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2800,6 +2800,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 92fde8d1aa82..884efff5b531 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX; +EXPORT_SYMBOL(sysctl_tcp_notsent_lowat); + static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 80fe69ef2188..b792e870686b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1924,6 +1924,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, |
