diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-01-28 16:02:33 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-01-28 16:02:33 -0800 |
commit | bd2463ac7d7ec51d432f23bf0e893fb371a908cd (patch) | |
tree | 3da32c23be83adb9d9bda7e51b51fa39f69f2447 /net/ipv4/tcp_output.c | |
parent | a78208e2436963d0b2c7d186277d6e1a9755029a (diff) | |
parent | f76e4c167ea2212e23c15ee7e601a865e822c291 (diff) | |
download | linux-bd2463ac7d7ec51d432f23bf0e893fb371a908cd.tar.gz linux-bd2463ac7d7ec51d432f23bf0e893fb371a908cd.tar.bz2 linux-bd2463ac7d7ec51d432f23bf0e893fb371a908cd.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Add WireGuard
2) Add HE and TWT support to ath11k driver, from John Crispin.
3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.
4) Add variable window congestion control to TIPC, from Jon Maloy.
5) Add BCM84881 PHY driver, from Russell King.
6) Start adding netlink support for ethtool operations, from Michal
Kubecek.
7) Add XDP drop and TX action support to ena driver, from Sameeh
Jubran.
8) Add new ipv4 route notifications so that mlxsw driver does not have
to handle identical routes itself. From Ido Schimmel.
9) Add BPF dynamic program extensions, from Alexei Starovoitov.
10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.
11) Add support for macsec HW offloading, from Antoine Tenart.
12) Add initial support for MPTCP protocol, from Christoph Paasch,
Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.
13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
Cherian, and others.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
udp: segment looped gso packets correctly
netem: change mailing list
qed: FW 8.42.2.0 debug features
qed: rt init valid initialization changed
qed: Debug feature: ilt and mdump
qed: FW 8.42.2.0 Add fw overlay feature
qed: FW 8.42.2.0 HSI changes
qed: FW 8.42.2.0 iscsi/fcoe changes
qed: Add abstraction for different hsi values per chip
qed: FW 8.42.2.0 Additional ll2 type
qed: Use dmae to write to widebus registers in fw_funcs
qed: FW 8.42.2.0 Parser offsets modified
qed: FW 8.42.2.0 Queue Manager changes
qed: FW 8.42.2.0 Expose new registers and change windows
qed: FW 8.42.2.0 Internal ram offsets modifications
MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
Documentation: net: octeontx2: Add RVU HW and drivers overview
octeontx2-pf: ethtool RSS config support
octeontx2-pf: Add basic ethtool support
...
Diffstat (limited to 'net/ipv4/tcp_output.c')
-rw-r--r-- | net/ipv4/tcp_output.c | 73 |
1 files changed, 67 insertions, 6 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b62b59b18db9..306e25d743e8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -38,6 +38,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> +#include <net/mptcp.h> #include <linux/compiler.h> #include <linux/gfp.h> @@ -414,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) #define OPTION_SMC (1 << 9) +#define OPTION_MPTCP (1 << 10) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -439,8 +441,17 @@ struct tcp_out_options { __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ + struct mptcp_out_options mptcp; }; +static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) +{ +#if IS_ENABLED(CONFIG_MPTCP) + if (unlikely(OPTION_MPTCP & opts->options)) + mptcp_write_options(ptr, &opts->mptcp); +#endif +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -549,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, } smc_options_write(ptr, &options); + + mptcp_options_write(ptr, opts); } static void smc_set_option(const struct tcp_sock *tp, @@ -584,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp, #endif } +static void mptcp_set_option_cond(const struct request_sock *req, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + if (rsk_is_mptcp(req)) { + unsigned int size; + + if (mptcp_synack_options(req, &size, &opts->mptcp)) { + if (*remaining >= size) { + opts->options |= OPTION_MPTCP; + *remaining -= size; + } + } + } +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ @@ -653,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, smc_set_option(tp, opts, &remaining); + if (sk_is_mptcp(sk)) { + unsigned int size; + + if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } @@ -714,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } } + mptcp_set_option_cond(req, opts, &remaining); + smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; @@ -751,16 +791,37 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_TSTAMP_ALIGNED; } + /* MPTCP options have precedence over SACK for the limited TCP + * option space because a MPTCP connection would be forced to + * fall back to regular TCP if a required multipath option is + * missing. SACK still gets a chance to use whatever space is + * left. + */ + if (sk_is_mptcp(sk)) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + unsigned int opt_size = 0; + + if (mptcp_established_options(sk, skb, &opt_size, remaining, + &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + size += opt_size; + } + } + eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) + return size; + opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - if (likely(opts->num_sack_blocks)) - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -2865,7 +2926,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!tcp_can_collapse(sk, skb)) break; - if (!tcp_skb_can_collapse_to(to)) + if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; @@ -3369,8 +3430,8 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) rcu_read_lock(); ca = tcp_ca_find_key(ca_key); - if (likely(ca && try_module_get(ca->owner))) { - module_put(icsk->icsk_ca_ops->owner); + if (likely(ca && bpf_try_module_get(ca, ca->owner))) { + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } |