diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
commit | b2fe5fa68642860e7de76167c3111623aa0d5de1 (patch) | |
tree | b7f9b89b7039ecefbc35fe3c8e73a6ff972641dd /net/ipv4/tcp.c | |
parent | a103950e0dd2058df5e8a8d4a915707bdcf205f0 (diff) | |
parent | a54667f6728c2714a400f3c884727da74b6d1717 (diff) | |
download | op-kernel-dev-b2fe5fa68642860e7de76167c3111623aa0d5de1.zip op-kernel-dev-b2fe5fa68642860e7de76167c3111623aa0d5de1.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Significantly shrink the core networking routing structures. Result
of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf
2) Add netdevsim driver for testing various offloads, from Jakub
Kicinski.
3) Support cross-chip FDB operations in DSA, from Vivien Didelot.
4) Add a 2nd listener hash table for TCP, similar to what was done for
UDP. From Martin KaFai Lau.
5) Add eBPF based queue selection to tun, from Jason Wang.
6) Lockless qdisc support, from John Fastabend.
7) SCTP stream interleave support, from Xin Long.
8) Smoother TCP receive autotuning, from Eric Dumazet.
9) Lots of erspan tunneling enhancements, from William Tu.
10) Add true function call support to BPF, from Alexei Starovoitov.
11) Add explicit support for GRO HW offloading, from Michael Chan.
12) Support extack generation in more netlink subsystems. From Alexander
Aring, Quentin Monnet, and Jakub Kicinski.
13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
Russell King.
14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.
15) Many improvements and simplifications to the NFP driver bpf JIT,
from Jakub Kicinski.
16) Support for ipv6 non-equal cost multipath routing, from Ido
Schimmel.
17) Add resource abstration to devlink, from Arkadi Sharshevsky.
18) Packet scheduler classifier shared filter block support, from Jiri
Pirko.
19) Avoid locking in act_csum, from Davide Caratti.
20) devinet_ioctl() simplifications from Al viro.
21) More TCP bpf improvements from Lawrence Brakmo.
22) Add support for onlink ipv6 route flag, similar to ipv4, from David
Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
tls: Add support for encryption using async offload accelerator
ip6mr: fix stale iterator
net/sched: kconfig: Remove blank help texts
openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
tcp_nv: fix potential integer overflow in tcpnv_acked
r8169: fix RTL8168EP take too long to complete driver initialization.
qmi_wwan: Add support for Quectel EP06
rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
ipmr: Fix ptrdiff_t print formatting
ibmvnic: Wait for device response when changing MAC
qlcnic: fix deadlock bug
tcp: release sk_frag.page in tcp_disconnect
ipv4: Get the address of interface correctly.
net_sched: gen_estimator: fix lockdep splat
net: macb: Handle HRESP error
net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
ipv6: addrconf: break critical section in addrconf_verify_rtnl()
ipv6: change route cache aging logic
i40e/i40evf: Update DESC_NEEDED value to reflect larger value
bnxt_en: cleanup DIM work on device shutdown
...
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r-- | net/ipv4/tcp.c | 73 |
1 files changed, 53 insertions, 20 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1b38b42..c059aa7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -283,8 +283,6 @@ #include <asm/ioctls.h> #include <net/busy_poll.h> -#include <trace/events/tcp.h> - struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); @@ -465,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tcp_mtup_init(sk); icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); - tcp_call_bpf(sk, bpf_op); + tcp_call_bpf(sk, bpf_op, 0, NULL); tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); } @@ -500,11 +498,9 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) const struct tcp_sock *tp = tcp_sk(sk); int state; - sock_rps_record_flow(sk); - sock_poll_wait(file, sk_sleep(sk), wait); - state = sk_state_load(sk); + state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -1106,12 +1102,15 @@ static int linear_payload_sz(bool first_skb) return 0; } -static int select_size(const struct sock *sk, bool sg, bool first_skb) +static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc) { const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; if (sg) { + if (zc) + return 0; + if (sk_can_gso(sk)) { tmp = linear_payload_sz(first_skb); } else { @@ -1188,7 +1187,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool process_backlog = false; - bool sg; + bool sg, zc = false; long timeo; flags = msg->msg_flags; @@ -1206,7 +1205,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - if (!(sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG)) + zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + if (!zc) uarg->zerocopy = 0; } @@ -1283,6 +1283,7 @@ restart: if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; + int linear; new_segment: /* Allocate new segment. If the interface is SG, @@ -1296,9 +1297,8 @@ new_segment: goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - skb = sk_stream_alloc_skb(sk, - select_size(sk, sg, first_skb), - sk->sk_allocation, + linear = select_size(sk, sg, first_skb, zc); + skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; @@ -1327,13 +1327,13 @@ new_segment: copy = msg_data_left(msg); /* Where to copy to? */ - if (skb_availroom(skb) > 0) { + if (skb_availroom(skb) > 0 && !zc) { /* We have some space in skb head. Superb! */ copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy); if (err) goto do_fault; - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); @@ -1373,8 +1373,10 @@ new_segment: pfrag->offset += copy; } else { err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); - if (err == -EMSGSIZE || err == -EEXIST) + if (err == -EMSGSIZE || err == -EEXIST) { + tcp_mark_push(tp, skb); goto new_segment; + } if (err < 0) goto do_error; copy = err; @@ -1731,8 +1733,8 @@ static void tcp_update_recv_tstamps(struct sk_buff *skb, } /* Similar to __sock_recv_timestamp, but does not require an skb */ -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping *tss) +static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping *tss) { struct timeval tv; bool has_timestamping = false; @@ -2040,7 +2042,29 @@ void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; - trace_tcp_set_state(sk, oldstate, state); + /* We defined a new enum for TCP states that are exported in BPF + * so as not force the internal TCP states to be frozen. The + * following checks will detect if an internal state value ever + * differs from the BPF value. If this ever happens, then we will + * need to remap the internal value to the BPF value before calling + * tcp_call_bpf_2arg. + */ + BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); + BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); + BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); + BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); + BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); + BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); + BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); + BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); + BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); + BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); + BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); + BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); + BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); + + if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: @@ -2065,7 +2089,7 @@ void tcp_set_state(struct sock *sk, int state) /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk_state_store(sk, state); + inet_sk_state_store(sk, state); #ifdef STATE_TRACE SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); @@ -2434,6 +2458,12 @@ int tcp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } @@ -2923,7 +2953,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) if (sk->sk_type != SOCK_STREAM) return; - info->tcpi_state = sk_state_load(sk); + info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); @@ -3581,6 +3611,9 @@ void __init tcp_init(void) percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); inet_hashinfo_init(&tcp_hashinfo); + inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", + thash_entries, 21, /* one slot per 2 MB*/ + 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, |