diff options
Diffstat (limited to 'net/ipv4/tcp_output.c')
| -rw-r--r-- | net/ipv4/tcp_output.c | 1327 |
1 files changed, 907 insertions, 420 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 71d01cf3c13e..479afb714bdf 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -38,12 +38,17 @@ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/mptcp.h> +#include <net/smc.h> +#include <net/proto_memory.h> +#include <net/psp.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> +#include <linux/skbuff_ref.h> #include <trace/events/tcp.h> @@ -170,15 +175,14 @@ static void tcp_event_data_sent(struct tcp_sock *tp, tp->lsndtime = now; /* If it is a reply for ato after last received - * packet, enter pingpong mode. + * packet, increase pingpong count. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - inet_csk_enter_pingpong_mode(sk); + inet_csk_inc_pingpong_cnt(sk); } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +196,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -204,16 +208,17 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, - __u32 *rcv_wnd, __u32 *window_clamp, + __u32 *rcv_wnd, __u32 *__window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); + u32 window_clamp = READ_ONCE(*__window_clamp); /* If no clamp set the clamp to the max possible scaled window */ - if (*window_clamp == 0) - (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); - space = min(*window_clamp, space); + if (window_clamp == 0) + window_clamp = (U16_MAX << TCP_MAX_WSCALE); + space = min(window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) @@ -230,7 +235,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else - (*rcv_wnd) = min_t(u32, space, U16_MAX); + (*rcv_wnd) = space; if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); @@ -240,14 +245,15 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); - space = min_t(u32, space, *window_clamp); + space = min_t(u32, space, window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ - (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); + WRITE_ONCE(*__window_clamp, + min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } -EXPORT_SYMBOL(tcp_select_initial_window); +EXPORT_IPV6_MOD(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return @@ -257,11 +263,22 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); u32 old_win = tp->rcv_wnd; - u32 cur_win = tcp_receive_window(tp); - u32 new_win = __tcp_select_window(sk); + u32 cur_win, new_win; + + /* Make the window 0 if we failed to queue the data because we + * are out of memory. + */ + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) { + tp->pred_flags = 0; + tp->rcv_wnd = 0; + tp->rcv_wup = tp->rcv_nxt; + return 0; + } - /* Never shrink the offered window */ + cur_win = tcp_receive_window(tp); + new_win = __tcp_select_window(sk); if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else @@ -270,11 +287,14 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ - if (new_win == 0) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPWANTZEROWINDOWADV); - new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); + if (!READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) || !tp->rx_opt.rcv_wscale) { + /* Never shrink the offered window */ + if (new_win == 0) + NET_INC_STATS(net, LINUX_MIB_TCPWANTZEROWINDOWADV); + new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); + } } + tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; @@ -282,7 +302,7 @@ static u16 tcp_select_window(struct sock *sk) * scaled window. */ if (!tp->rx_opt.rcv_wscale && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) + READ_ONCE(net->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); @@ -294,69 +314,14 @@ static u16 tcp_select_window(struct sock *sk) if (new_win == 0) { tp->pred_flags = 0; if (old_win) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPTOZEROWINDOWADV); + NET_INC_STATS(net, LINUX_MIB_TCPTOZEROWINDOWADV); } else if (old_win == 0) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + NET_INC_STATS(net, LINUX_MIB_TCPFROMZEROWINDOWADV); } return new_win; } -/* Packet ECN state for a SYN-ACK */ -static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) -{ - const struct tcp_sock *tp = tcp_sk(sk); - - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; - if (!(tp->ecn_flags & TCP_ECN_OK)) - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; - else if (tcp_ca_needs_ecn(sk) || - tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); -} - -/* Packet ECN state for a SYN. */ -static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); - bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || - tcp_ca_needs_ecn(sk) || bpf_needs_ecn; - - if (!use_ecn) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) - use_ecn = true; - } - - tp->ecn_flags = 0; - - if (use_ecn) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; - tp->ecn_flags = TCP_ECN_OK; - if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); - } -} - -static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) -{ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) - /* tp->ecn_flags are cleared at a later point in time when - * SYN ACK is ultimatively being received. - */ - TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); -} - -static void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) -{ - if (inet_rsk(req)->ecn_ok) - th->ece = 1; -} - /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ @@ -365,7 +330,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - if (tp->ecn_flags & TCP_ECN_OK) { + if (!tcp_ecn_mode_any(tp)) + return; + + if (tcp_ecn_mode_accecn(tp)) { + if (!tcp_accecn_ace_fail_recv(tp)) + INET_ECN_xmit(sk); + tcp_accecn_set_ace(tp, skb, th); + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; + } else { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { @@ -387,13 +360,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ -static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) +static void tcp_init_nondata_skb(struct sk_buff *skb, struct sock *sk, + u32 seq, u16 flags) { skb->ip_summed = CHECKSUM_PARTIAL; TCP_SKB_CB(skb)->tcp_flags = flags; tcp_skb_pcount_set(skb, 1); + psp_enqueue_set_decrypted(sk, skb); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) @@ -413,6 +388,8 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) +#define OPTION_AO BIT(11) +#define OPTION_ACCECN BIT(12) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -434,6 +411,8 @@ struct tcp_out_options { u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 num_accecn_fields:7, /* number of AccECN fields needed */ + use_synack_ecn_bytes:1; /* Use synack_ecn_bytes or not */ u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ @@ -508,6 +487,7 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk); sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; } @@ -553,6 +533,7 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk); sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; } @@ -591,6 +572,49 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, } #endif +static __be32 *process_tcp_ao_options(struct tcp_sock *tp, + const struct tcp_request_sock *tcprsk, + struct tcp_out_options *opts, + struct tcp_key *key, __be32 *ptr) +{ +#ifdef CONFIG_TCP_AO + u8 maclen = tcp_ao_maclen(key->ao_key); + + if (tcprsk) { + u8 aolen = maclen + sizeof(struct tcp_ao_hdr); + + *ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) | + (tcprsk->ao_keyid << 8) | + (tcprsk->ao_rcv_next)); + } else { + struct tcp_ao_key *rnext_key; + struct tcp_ao_info *ao_info; + + ao_info = rcu_dereference_check(tp->ao_info, + lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk)); + rnext_key = READ_ONCE(ao_info->rnext_key); + if (WARN_ON_ONCE(!rnext_key)) + return ptr; + *ptr++ = htonl((TCPOPT_AO << 24) | + (tcp_ao_len(key->ao_key) << 16) | + (key->ao_key->sndid << 8) | + (rnext_key->rcvid)); + } + opts->hash_location = (__u8 *)ptr; + ptr += maclen / sizeof(*ptr); + if (unlikely(maclen % sizeof(*ptr))) { + memset(ptr, TCPOPT_NOP, sizeof(*ptr)); + ptr++; + } +#endif + return ptr; +} + +/* Initial values for AccECN option, ordered is based on ECN field bits + * similar to received_ecn_bytes. Used for SYN/ACK AccECN option. + */ +static const u32 synack_ecn_bytes[3] = { 0, 0, 0 }; + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -605,19 +629,24 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, - struct tcp_out_options *opts) + const struct tcp_request_sock *tcprsk, + struct tcp_out_options *opts, + struct tcp_key *key) { + u8 leftover_highbyte = TCPOPT_NOP; /* replace 1st NOP if avail */ + u8 leftover_lowbyte = TCPOPT_NOP; /* replace 2nd NOP in succession */ __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ - if (unlikely(OPTION_MD5 & options)) { + if (tcp_key_is_md5(key)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; + } else if (tcp_key_is_ao(key)) { + ptr = process_tcp_ao_options(tp, tcprsk, opts, key, ptr); } - if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | @@ -641,15 +670,75 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, *ptr++ = htonl(opts->tsecr); } + if (OPTION_ACCECN & options) { + const u32 *ecn_bytes = opts->use_synack_ecn_bytes ? + synack_ecn_bytes : + tp->received_ecn_bytes; + const u8 ect0_idx = INET_ECN_ECT_0 - 1; + const u8 ect1_idx = INET_ECN_ECT_1 - 1; + const u8 ce_idx = INET_ECN_CE - 1; + u32 e0b; + u32 e1b; + u32 ceb; + u8 len; + + e0b = ecn_bytes[ect0_idx] + TCP_ACCECN_E0B_INIT_OFFSET; + e1b = ecn_bytes[ect1_idx] + TCP_ACCECN_E1B_INIT_OFFSET; + ceb = ecn_bytes[ce_idx] + TCP_ACCECN_CEB_INIT_OFFSET; + len = TCPOLEN_ACCECN_BASE + + opts->num_accecn_fields * TCPOLEN_ACCECN_PERFIELD; + + if (opts->num_accecn_fields == 2) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + *ptr++ = htonl(((e1b & 0xff) << 24) | + (ceb & 0xffffff)); + } else if (opts->num_accecn_fields == 1) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + leftover_highbyte = e1b & 0xff; + leftover_lowbyte = TCPOPT_NOP; + } else if (opts->num_accecn_fields == 0) { + leftover_highbyte = TCPOPT_ACCECN1; + leftover_lowbyte = len; + } else if (opts->num_accecn_fields == 3) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + *ptr++ = htonl(((e1b & 0xff) << 24) | + (ceb & 0xffffff)); + *ptr++ = htonl(((e0b & 0xffffff) << 8) | + TCPOPT_NOP); + } + if (tp) { + tp->accecn_minlen = 0; + tp->accecn_opt_tstamp = tp->tcp_mstamp; + if (tp->accecn_opt_demand) + tp->accecn_opt_demand--; + } + } + if (unlikely(OPTION_SACK_ADVERTISE & options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; } if (unlikely(OPTION_WSCALE & options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | + u8 highbyte = TCPOPT_NOP; + + /* Do not split the leftover 2-byte to fit into a single + * NOP, i.e., replace this NOP only when 1 byte is leftover + * within leftover_highbyte. + */ + if (unlikely(leftover_highbyte != TCPOPT_NOP && + leftover_lowbyte == TCPOPT_NOP)) { + highbyte = leftover_highbyte; + leftover_highbyte = TCPOPT_NOP; + } + *ptr++ = htonl((highbyte << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); @@ -660,11 +749,13 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, tp->duplicate_sack : tp->selective_acks; int this_sack; - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { @@ -673,6 +764,14 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, } tp->rx_opt.dsack = 0; + } else if (unlikely(leftover_highbyte != TCPOPT_NOP || + leftover_lowbyte != TCPOPT_NOP)) { + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | + (TCPOPT_NOP << 8) | + TCPOPT_NOP); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { @@ -704,34 +803,36 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, mptcp_options_write(th, ptr, tp, opts); } -static void smc_set_option(const struct tcp_sock *tp, +static void smc_set_option(struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc) { + tp->syn_smc = !!smc_call_hsbpf(1, tp, syn_option); + /* re-check syn_smc */ + if (tp->syn_smc && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, - const struct inet_request_sock *ireq, + struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc && ireq->smc_ok) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc && ireq->smc_ok) { + ireq->smc_ok = !!smc_call_hsbpf(1, tp, synack_option, ireq); + /* re-check smc_ok */ + if (ireq->smc_ok && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif @@ -753,28 +854,104 @@ static void mptcp_set_option_cond(const struct request_sock *req, } } +static u32 tcp_synack_options_combine_saving(struct tcp_out_options *opts) +{ + /* How much there's room for combining with the alignment padding? */ + if ((opts->options & (OPTION_SACK_ADVERTISE | OPTION_TS)) == + OPTION_SACK_ADVERTISE) + return 2; + else if (opts->options & OPTION_WSCALE) + return 1; + return 0; +} + +/* Calculates how long AccECN option will fit to @remaining option space. + * + * AccECN option can sometimes replace NOPs used for alignment of other + * TCP options (up to @max_combine_saving available). + * + * Only solutions with at least @required AccECN fields are accepted. + * + * Returns: The size of the AccECN option excluding space repurposed from + * the alignment of the other options. + */ +static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required, + int remaining) +{ + int size = TCP_ACCECN_MAXSIZE; + int sack_blocks_reduce = 0; + int max_combine_saving; + int rem = remaining; + int align_size; + + if (opts->use_synack_ecn_bytes) + max_combine_saving = tcp_synack_options_combine_saving(opts); + else + max_combine_saving = opts->num_sack_blocks > 0 ? 2 : 0; + opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS; + while (opts->num_accecn_fields >= required) { + /* Pad to dword if cannot combine */ + if ((size & 0x3) > max_combine_saving) + align_size = ALIGN(size, 4); + else + align_size = ALIGN_DOWN(size, 4); + + if (rem >= align_size) { + size = align_size; + break; + } else if (opts->num_accecn_fields == required && + opts->num_sack_blocks > 2 && + required > 0) { + /* Try to fit the option by removing one SACK block */ + opts->num_sack_blocks--; + sack_blocks_reduce++; + rem = rem + TCPOLEN_SACK_PERBLOCK; + + opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS; + size = TCP_ACCECN_MAXSIZE; + continue; + } + + opts->num_accecn_fields--; + size -= TCPOLEN_ACCECN_PERFIELD; + } + if (sack_blocks_reduce > 0) { + if (opts->num_accecn_fields >= required) + size -= sack_blocks_reduce * TCPOLEN_SACK_PERBLOCK; + else + opts->num_sack_blocks += sack_blocks_reduce; + } + if (opts->num_accecn_fields < required) + return 0; + + opts->options |= OPTION_ACCECN; + return size; +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) + struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; + bool timestamps; - *md5 = NULL; -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - rcu_access_pointer(tp->md5sig_info)) { - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - remaining -= TCPOLEN_MD5SIG_ALIGNED; + /* Better than switch (key.type) as it has static branches */ + if (tcp_key_is_md5(key)) { + timestamps = false; + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + } else { + timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); + if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + remaining -= tcp_ao_len_aligned(key->ao_key); } } -#endif /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS @@ -788,9 +965,9 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { + if (likely(timestamps)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; + opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -826,11 +1003,27 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { - opts->options |= OPTION_MPTCP; - remaining -= size; + if (remaining >= size) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } } } + /* Simultaneous open SYN/ACK needs AccECN option but not SYN. + * It is attempted to negotiate the use of AccECN also on the first + * retransmitted SYN, as mentioned in "3.1.4.1. Retransmitted SYNs" + * of AccECN draft. + */ + if (unlikely((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) && + tcp_ecn_mode_accecn(tp) && + inet_csk(sk)->icsk_retransmits < 2 && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && + remaining >= TCPOLEN_ACCECN_BASE)) { + opts->use_synack_ecn_bytes = 1; + remaining -= tcp_options_fit_accecn(opts, 0, remaining); + } + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; @@ -841,16 +1034,16 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, - const struct tcp_md5sig_key *md5, + const struct tcp_key *key, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; + struct tcp_request_sock *treq = tcp_rsk(req); -#ifdef CONFIG_TCP_MD5SIG - if (md5) { + if (tcp_key_is_md5(key)) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; @@ -861,8 +1054,11 @@ static unsigned int tcp_synack_options(const struct sock *sk, */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; + } else if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + remaining -= tcp_ao_len_aligned(key->ao_key); + ireq->tstamp_ok &= !ireq->sack_ok; } -#endif /* We always send an MSS option. */ opts->mss = mss; @@ -875,7 +1071,14 @@ static unsigned int tcp_synack_options(const struct sock *sk, } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; + opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + + tcp_rsk(req)->ts_off; + if (!tcp_rsk(req)->snt_tsval_first) { + if (!opts->tsval) + opts->tsval = ~0U; + tcp_rsk(req)->snt_tsval_first = opts->tsval; + } + WRITE_ONCE(tcp_rsk(req)->snt_tsval_last, opts->tsval); opts->tsecr = req->ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -901,6 +1104,13 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + if (treq->accecn_ok && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && + req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) { + opts->use_synack_ecn_bytes = 1; + remaining -= tcp_options_fit_accecn(opts, 0, remaining); + } + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); @@ -912,7 +1122,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) + struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; @@ -920,21 +1130,19 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->options = 0; - *md5 = NULL; -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - rcu_access_pointer(tp->md5sig_info)) { - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; - } + /* Better than switch (key.type) as it has static branches */ + if (tcp_key_is_md5(key)) { + opts->options |= OPTION_MD5; + size += TCPOLEN_MD5SIG_ALIGNED; + } else if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + size += tcp_ao_len_aligned(key->ao_key); } -#endif if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; + opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -959,17 +1167,32 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb 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; + if (likely(remaining >= TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) { + opts->num_sack_blocks = + min_t(unsigned int, eff_sacks, + (remaining - TCPOLEN_SACK_BASE_ALIGNED) / + TCPOLEN_SACK_PERBLOCK); + + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + } else { + opts->num_sack_blocks = 0; + } + } else { + opts->num_sack_blocks = 0; + } - opts->num_sack_blocks = - min_t(unsigned int, eff_sacks, - (remaining - TCPOLEN_SACK_BASE_ALIGNED) / - TCPOLEN_SACK_PERBLOCK); + if (tcp_ecn_mode_accecn(tp)) { + int ecn_opt = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (ecn_opt && tp->saw_accecn_opt && !tcp_accecn_opt_fail_send(tp) && + (ecn_opt >= TCP_ACCECN_OPTION_FULL || tp->accecn_opt_demand || + tcp_accecn_option_beacon_check(sk))) { + opts->use_synack_ecn_bytes = 0; + size += tcp_options_fit_accecn(opts, tp->accecn_minlen, + MAX_TCP_OPTION_SPACE - size); + } } if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, @@ -995,15 +1218,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * - * Since transmit from skb destructor is forbidden, we use a tasklet + * Since transmit from skb destructor is forbidden, we use a BH work item * to process all sockets that eventually need to send more skbs. - * We use one tasklet per cpu, with its own queue of sockets. + * We use one work item per cpu, with its own queue of sockets. */ -struct tsq_tasklet { - struct tasklet_struct tasklet; +struct tsq_work { + struct work_struct work; struct list_head head; /* queue of tcp sockets */ }; -static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); +static DEFINE_PER_CPU(struct tsq_work, tsq_work); static void tcp_tsq_write(struct sock *sk) { @@ -1033,14 +1256,14 @@ static void tcp_tsq_handler(struct sock *sk) bh_unlock_sock(sk); } /* - * One tasklet per cpu tries to send more skbs. - * We run in tasklet context but need to disable irqs when + * One work item per cpu tries to send more skbs. + * We run in BH context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ -static void tcp_tasklet_func(struct tasklet_struct *t) +static void tcp_tsq_workfn(struct work_struct *work) { - struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet); + struct tsq_work *tsq = container_of(work, struct tsq_work, work); LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; @@ -1067,7 +1290,8 @@ static void tcp_tasklet_func(struct tasklet_struct *t) #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ - TCPF_MTU_REDUCED_DEFERRED) + TCPF_MTU_REDUCED_DEFERRED | \ + TCPF_ACK_DEFERRED) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket @@ -1091,16 +1315,6 @@ void tcp_release_cb(struct sock *sk) tcp_tsq_write(sk); __sock_put(sk); } - /* Here begins the tricky part : - * We are called from release_sock() with : - * 1) BH disabled - * 2) sk_lock.slock spinlock held - * 3) socket owned by us (sk->sk_lock.owned == 1) - * - * But following code is meant to be called from BH handlers, - * so we should keep BH disabled, but early release socket ownership - */ - sock_release_ownership(sk); if (flags & TCPF_WRITE_TIMER_DEFERRED) { tcp_write_timer_handler(sk); @@ -1114,18 +1328,20 @@ void tcp_release_cb(struct sock *sk) inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } + if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk)) + tcp_send_ack(sk); } -EXPORT_SYMBOL(tcp_release_cb); +EXPORT_IPV6_MOD(tcp_release_cb); -void __init tcp_tasklet_init(void) +void __init tcp_tsq_work_init(void) { int i; for_each_possible_cpu(i) { - struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + struct tsq_work *tsq = &per_cpu(tsq_work, i); INIT_LIST_HEAD(&tsq->head); - tasklet_setup(&tsq->tasklet, tcp_tasklet_func); + INIT_WORK(&tsq->work, tcp_tsq_workfn); } } @@ -1139,11 +1355,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - struct tsq_tasklet *tsq; + struct tsq_work *tsq; bool empty; /* Keep one reference on sk_wmem_alloc. - * Will be released by sk_free() from here or tcp_tasklet_func() + * Will be released by sk_free() from here or tcp_tsq_workfn() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); @@ -1165,13 +1381,13 @@ void tcp_wfree(struct sk_buff *skb) nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); - /* queue this socket to tasklet queue */ + /* queue this socket to BH workqueue */ local_irq_save(flags); - tsq = this_cpu_ptr(&tsq_tasklet); + tsq = this_cpu_ptr(&tsq_work); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) - tasklet_schedule(&tsq->tasklet); + queue_work(system_bh_wq, &tsq->work); local_irq_restore(flags); return; out: @@ -1198,7 +1414,7 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); if (sk->sk_pacing_status != SK_PACING_NONE) { - unsigned long rate = sk->sk_pacing_rate; + unsigned long rate = READ_ONCE(sk->sk_pacing_rate); /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, @@ -1241,7 +1457,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; - struct tcp_md5sig_key *md5; + struct tcp_key key; struct tcphdr *th; u64 prior_wstamp; int err; @@ -1250,7 +1466,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); if (clone_it) { oskb = skb; @@ -1273,11 +1489,11 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); + tcp_get_current_key(sk, &key); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { - tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); + tcp_options_size = tcp_syn_options(sk, skb, &opts, &key); } else { - tcp_options_size = tcp_established_options(sk, skb, &opts, - &md5); + tcp_options_size = tcp_established_options(sk, skb, &opts, &key); /* Force a PSH flag on all (GSO) packets to expedite GRO flush * at receiver : This slightly improve GRO performance. * Note that we do not force the PSH flag for non GSO packets, @@ -1291,14 +1507,21 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, } tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - /* if no packet is in qdisc/device queue, then allow XPS to select - * another queue. We can be called from tcp_tsq_handler() - * which holds one reference to sk. - * - * TODO: Ideally, in-flight pure ACK packets should not matter here. - * One way to get this would be to set skb->truesize = 2 on them. + /* We set skb->ooo_okay to one if this packet can select + * a different TX queue than prior packets of this flow, + * to avoid self inflicted reorders. + * The 'other' queue decision is based on current cpu number + * if XPS is enabled, or sk->sk_txhash otherwise. + * We can switch to another (and better) queue if: + * 1) No packet with payload is in qdisc/device queues. + * Delays in TX completion can defeat the test + * even if packets were already sent. + * 2) Or rtx queue is empty. + * This mitigates above case if ACK packets for + * all prior packets were already processed. */ - skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1); + skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) || + tcp_rtx_queue_empty(sk); /* If we had to use memory reserve to allocate this skb, * this might cause drops if packet is looped back : @@ -1315,7 +1538,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; @@ -1324,7 +1547,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | - tcb->tcp_flags); + (tcb->tcp_flags & TCPHDR_FLAGS_MASK)); th->check = 0; th->urg_ptr = 0; @@ -1351,16 +1574,25 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, th->window = htons(min(tp->rcv_wnd, 65535U)); } - tcp_options_write(th, tp, &opts); + tcp_options_write(th, tp, NULL, &opts, &key); + if (tcp_key_is_md5(&key)) { #ifdef CONFIG_TCP_MD5SIG - /* Calculate the MD5 hash, as we have all we need now */ - if (md5) { + /* Calculate the MD5 hash, as we have all we need now */ sk_gso_disable(sk); tp->af_specific->calc_md5_hash(opts.hash_location, - md5, sk, skb); - } + key.md5_key, sk, skb); #endif + } else if (tcp_key_is_ao(&key)) { + int err; + + err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th, + opts.hash_location); + if (err) { + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED); + return -ENOMEM; + } + } /* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); @@ -1370,7 +1602,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1430,24 +1662,29 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) /* Advance write_seq and place onto the write_queue. */ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); + psp_enqueue_set_decrypted(sk, skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ -static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) +static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { + int tso_segs; + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ - tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; - } else { - tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); - TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tcp_skb_pcount_set(skb, 1); + return 1; } + TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tso_segs = DIV_ROUND_UP(skb->len, mss_now); + tcp_skb_pcount_set(skb, tso_segs); + return tso_segs; } /* Pcount in the middle of the write queue got changed, we need to do various @@ -1470,11 +1707,6 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); - if (tp->lost_skb_hint && - before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) - tp->lost_cnt_hint -= decr; - tcp_verify_left_out(tp); } @@ -1530,17 +1762,15 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; - int nsize, old_factor; + int old_factor; long limit; + u16 flags; int nlen; - u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; - nsize = skb_headlen(skb) - len; - if (nsize < 0) - nsize = 0; + DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb)); /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. * We need some allowance to not penalize applications setting small @@ -1560,7 +1790,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* Get a new skb... force flag on. */ - buff = tcp_stream_alloc_skb(sk, nsize, gfp, true); + buff = tcp_stream_alloc_skb(sk, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); @@ -1568,7 +1798,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); - nlen = skb->len - len - nsize; + nlen = skb->len - len; buff->truesize += nlen; skb->truesize -= nlen; @@ -1586,7 +1816,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, skb_split(skb, buff, len); - skb_set_delivery_time(buff, skb->tstamp, true); + skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC); tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); @@ -1626,13 +1856,7 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) struct skb_shared_info *shinfo; int i, k, eat; - eat = min_t(int, len, skb_headlen(skb)); - if (eat) { - __skb_pull(skb, eat); - len -= eat; - if (!len) - return 0; - } + DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb)); eat = len; k = 0; shinfo = skb_shinfo(skb); @@ -1671,12 +1895,10 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) TCP_SKB_CB(skb)->seq += len; - if (delta_truesize) { - skb->truesize -= delta_truesize; - sk_wmem_queued_add(sk, -delta_truesize); - if (!skb_zcopy_pure(skb)) - sk_mem_uncharge(sk, delta_truesize); - } + skb->truesize -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, delta_truesize); /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) @@ -1697,14 +1919,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mss_now -= icsk->icsk_af_ops->net_frag_header_len; - } - /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1725,28 +1939,18 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } -EXPORT_SYMBOL(tcp_mtu_to_mss); +EXPORT_IPV6_MOD(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - int mtu; - mtu = mss + + return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; - - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mtu += icsk->icsk_af_ops->net_frag_header_len; - } - return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); @@ -1765,7 +1969,6 @@ void tcp_mtup_init(struct sock *sk) if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } -EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. @@ -1809,7 +2012,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) return mss_now; } -EXPORT_SYMBOL(tcp_sync_mss); +EXPORT_IPV6_MOD(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. @@ -1821,7 +2024,7 @@ unsigned int tcp_current_mss(struct sock *sk) u32 mss_now; unsigned int header_len; struct tcp_out_options opts; - struct tcp_md5sig_key *md5; + struct tcp_key key; mss_now = tp->mss_cache; @@ -1830,8 +2033,8 @@ unsigned int tcp_current_mss(struct sock *sk) if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } - - header_len = tcp_established_options(sk, NULL, &opts, &md5) + + tcp_get_current_key(sk, &key); + header_len = tcp_established_options(sk, NULL, &opts, &key) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK @@ -1973,7 +2176,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, unsigned long bytes; u32 r; - bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift); + bytes = READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift); r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log); if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) @@ -2035,16 +2238,10 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ -static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, - const struct sk_buff *skb) +static u32 tcp_cwnd_test(const struct tcp_sock *tp) { u32 in_flight, cwnd, halfcwnd; - /* Don't be strict about the congestion window for the final FIN. */ - if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && - tcp_skb_pcount(skb) == 1) - return 1; - in_flight = tcp_packets_in_flight(tp); cwnd = tcp_snd_cwnd(tp); if (in_flight >= cwnd) @@ -2065,10 +2262,9 @@ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); - if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { - tcp_set_skb_tso_segs(skb, mss_now); - tso_segs = tcp_skb_pcount(skb); - } + if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) + return tcp_set_skb_tso_segs(skb, mss_now); + return tso_segs; } @@ -2123,14 +2319,12 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, { int nlen = skb->len - len; struct sk_buff *buff; - u8 flags; + u16 flags; /* All of a TSO frame must be composed of paged data. */ - if (skb->len != skb->data_len) - return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, - skb, len, mss_now, gfp); + DEBUG_NET_WARN_ON_ONCE(skb->len != skb->data_len); - buff = tcp_stream_alloc_skb(sk, 0, gfp, true); + buff = tcp_stream_alloc_skb(sk, gfp, true); if (unlikely(!buff)) return -ENOMEM; skb_copy_decrypted(buff, skb); @@ -2178,7 +2372,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); - u32 send_win, cong_win, limit, in_flight; + u32 send_win, cong_win, limit, in_flight, threshold; + u64 srtt_in_ns, expected_ack, how_far_is_the_ack; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; @@ -2240,9 +2435,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, head = tcp_rtx_queue_head(sk); if (!head) goto send_now; - delta = tp->tcp_clock_cache - head->tstamp; - /* If next ACK is likely to come too late (half srtt), do not defer */ - if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0) + + srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us; + /* When is the ACK expected ? */ + expected_ack = head->tstamp + srtt_in_ns; + /* How far from now is the ACK expected ? */ + how_far_is_the_ack = expected_ack - tp->tcp_clock_cache; + + /* If next ACK is likely to come too late, + * ie in more than min(1ms, half srtt), do not defer. + */ + threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC); + + if ((s64)(how_far_is_the_ack - threshold) > 0) goto send_now; /* Ok, it looks like it is advisable to defer. @@ -2308,9 +2513,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor) || - tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + if (tcp_has_tx_tstamp(skb) || !tcp_skb_can_collapse(skb, next)) return false; len -= skb->len; @@ -2319,6 +2522,72 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) return true; } +static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, + int probe_size) +{ + skb_frag_t *lastfrag = NULL, *fragto = skb_shinfo(to)->frags; + int i, todo, len = 0, nr_frags = 0; + const struct sk_buff *skb; + + if (!sk_wmem_schedule(sk, to->truesize + probe_size)) + return -ENOMEM; + + skb_queue_walk(&sk->sk_write_queue, skb) { + const skb_frag_t *fragfrom = skb_shinfo(skb)->frags; + + if (skb_headlen(skb)) + return -EINVAL; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, fragfrom++) { + if (len >= probe_size) + goto commit; + todo = min_t(int, skb_frag_size(fragfrom), + probe_size - len); + len += todo; + if (lastfrag && + skb_frag_page(fragfrom) == skb_frag_page(lastfrag) && + skb_frag_off(fragfrom) == skb_frag_off(lastfrag) + + skb_frag_size(lastfrag)) { + skb_frag_size_add(lastfrag, todo); + continue; + } + if (unlikely(nr_frags == MAX_SKB_FRAGS)) + return -E2BIG; + skb_frag_page_copy(fragto, fragfrom); + skb_frag_off_copy(fragto, fragfrom); + skb_frag_size_set(fragto, todo); + nr_frags++; + lastfrag = fragto++; + } + } +commit: + WARN_ON_ONCE(len != probe_size); + for (i = 0; i < nr_frags; i++) + skb_frag_ref(to, i); + + skb_shinfo(to)->nr_frags = nr_frags; + to->truesize += probe_size; + to->len += probe_size; + to->data_len += probe_size; + __skb_header_release(to); + return 0; +} + +/* tcp_mtu_probe() and tcp_grow_skb() can both eat an skb (src) if + * all its payload was moved to another one (dst). + * Make sure to transfer tcp_flags, eor, and tstamp. + */ +static void tcp_eat_one_skb(struct sock *sk, + struct sk_buff *dst, + struct sk_buff *src) +{ + TCP_SKB_CB(dst)->tcp_flags |= TCP_SKB_CB(src)->tcp_flags; + TCP_SKB_CB(dst)->eor = TCP_SKB_CB(src)->eor; + tcp_skb_collapse_tstamp(dst, src); + tcp_unlink_write_queue(src, sk); + tcp_wmem_free_skb(sk, src); +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2395,9 +2664,16 @@ static int tcp_mtu_probe(struct sock *sk) return -1; /* We're allowed to probe. Build it now. */ - nskb = tcp_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); + nskb = tcp_stream_alloc_skb(sk, GFP_ATOMIC, false); if (!nskb) return -1; + + /* build the payload, and be prepared to abort if this fails. */ + if (tcp_clone_payload(sk, nskb, probe_size)) { + tcp_skb_tsorted_anchor_cleanup(nskb); + consume_skb(nskb); + return -1; + } sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); @@ -2415,28 +2691,14 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { - /* We've eaten all the data from this skb. - * Throw it away. */ - TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; - /* If this is the last SKB we copy and eor is set - * we need to propagate it to the new skb. - */ - TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; - tcp_skb_collapse_tstamp(nskb, skb); - tcp_unlink_write_queue(skb, sk); - tcp_wmem_free_skb(sk, skb); + tcp_eat_one_skb(sk, nskb, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); - if (!skb_shinfo(skb)->nr_frags) { - skb_pull(skb, copy); - } else { - __pskb_trim_head(skb, copy); - tcp_set_skb_tso_segs(skb, mss_now); - } + __pskb_trim_head(skb, copy); + tcp_set_skb_tso_segs(skb, mss_now); TCP_SKB_CB(skb)->seq += copy; } @@ -2485,6 +2747,18 @@ static bool tcp_pacing_check(struct sock *sk) return true; } +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) +{ + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2503,15 +2777,15 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); - if (sk->sk_pacing_status == SK_PACING_NONE) - limit = min_t(unsigned long, limit, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); + READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift)); + limit = min_t(unsigned long, limit, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && tcp_sk(sk)->tcp_tx_delay) { - u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay; + u64 extra_bytes = (u64)READ_ONCE(sk->sk_pacing_rate) * + tcp_sk(sk)->tcp_tx_delay; /* TSQ is based on skb truesize sum (sk_wmem_alloc), so we * approximate our needs assuming an ~100% skb->truesize overhead. @@ -2522,12 +2796,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, - * after softirq/tasklet schedule. + * after softirq schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2584,6 +2858,35 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } +/* First skb in the write queue is smaller than ideal packet size. + * Check if we can move payload from the second skb in the queue. + */ +static void tcp_grow_skb(struct sock *sk, struct sk_buff *skb, int amount) +{ + struct sk_buff *next_skb = skb->next; + unsigned int nlen; + + if (tcp_skb_is_last(sk, skb)) + return; + + if (!tcp_skb_can_collapse(skb, next_skb)) + return; + + nlen = min_t(u32, amount, next_skb->len); + if (!nlen || !skb_shift(skb, next_skb, nlen)) + return; + + TCP_SKB_CB(skb)->end_seq += nlen; + TCP_SKB_CB(next_skb)->seq += nlen; + + if (!next_skb->len) { + /* In case FIN is set, we need to update end_seq */ + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; + + tcp_eat_one_skb(sk, skb, next_skb); + } +} + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -2604,14 +2907,18 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; - int cwnd_quota; + u32 cwnd_quota, max_segs; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; - u32 max_segs; sent_pkts = 0; tcp_mstamp_refresh(tp); + + /* AccECN option beacon depends on mstamp, it may change mss */ + if (tcp_ecn_mode_accecn(tp) && tcp_accecn_option_beacon_check(sk)) + mss_now = tcp_current_mss(sk); + if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); @@ -2625,11 +2932,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; + int missing_bytes; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ tp->tcp_wstamp_ns = tp->tcp_clock_cache; - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ @@ -2638,10 +2946,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_pacing_check(sk)) break; - tso_segs = tcp_init_tso_segs(skb, mss_now); - BUG_ON(!tso_segs); - - cwnd_quota = tcp_cwnd_test(tp, skb); + cwnd_quota = tcp_cwnd_test(tp); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ @@ -2649,6 +2954,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, else break; } + cwnd_quota = min(cwnd_quota, max_segs); + missing_bytes = cwnd_quota * mss_now - skb->len; + if (missing_bytes > 0) + tcp_grow_skb(sk, skb, missing_bytes); + + tso_segs = tcp_set_skb_tso_segs(skb, mss_now); if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; @@ -2670,9 +2981,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - min_t(unsigned int, - cwnd_quota, - max_segs), + cwnd_quota, nonagle); if (skb->len > limit && @@ -2731,7 +3040,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2755,11 +3064,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } @@ -2771,7 +3081,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); - tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, true); return true; } @@ -2819,10 +3129,8 @@ void tcp_send_loss_probe(struct sock *sk) } skb = skb_rb_last(&sk->tcp_rtx_queue); if (unlikely(!skb)) { - WARN_ONCE(tp->packets_out, - "invalid inflight: %u state %u cwnd %u mss %d\n", - tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss); - inet_csk(sk)->icsk_pending = 0; + tcp_warn_once(sk, tp->packets_out, "invalid inflight: "); + smp_store_release(&inet_csk(sk)->icsk_pending, 0); return; } @@ -2855,7 +3163,7 @@ probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ - inet_csk(sk)->icsk_pending = 0; + smp_store_release(&inet_csk(sk)->icsk_pending, 0); rearm_timer: tcp_rearm_rto(sk); } @@ -2947,6 +3255,7 @@ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct @@ -2968,6 +3277,15 @@ u32 __tcp_select_window(struct sock *sk) if (mss <= 0) return 0; } + + /* Only allow window shrink if the sysctl is enabled and we have + * a non-zero scaling factor in effect. + */ + if (READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) && tp->rx_opt.rcv_wscale) + goto shrink_window_allowed; + + /* do not allow window to shrink */ + if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; @@ -3022,6 +3340,36 @@ u32 __tcp_select_window(struct sock *sk) } return window; + +shrink_window_allowed: + /* new window should always be an exact multiple of scaling factor */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + if (free_space < (full_space >> 1)) { + icsk->icsk_ack.quick = 0; + + if (tcp_under_memory_pressure(sk)) + tcp_adjust_rcv_ssthresh(sk); + + /* if free space is too low, return a zero window */ + if (free_space < (allowed_space >> 4) || free_space < mss || + free_space < (1 << tp->rx_opt.rcv_wscale)) + return 0; + } + + if (free_space > tp->rcv_ssthresh) { + free_space = tp->rcv_ssthresh; + /* new window should always be an exact multiple of scaling factor + * + * For this case, we ALIGN "up" (increase free_space) because + * we know free_space is not zero here, it has been reduced from + * the memory-based limit, and rcv_ssthresh is not a hard limit + * (unlike sk_rcvbuf). + */ + free_space = ALIGN(free_space, (1 << tp->rx_opt.rcv_wscale)); + } + + return free_space; } void tcp_skb_collapse_tstamp(struct sk_buff *skb, @@ -3068,7 +3416,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ - tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; @@ -3087,6 +3434,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; + if (!skb_frags_readable(skb)) + return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -3150,20 +3499,33 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; - if (skb_still_in_host_queue(sk, skb)) - return -EBUSY; + if (skb_still_in_host_queue(sk, skb)) { + err = -EBUSY; + goto out; + } +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); - return -EINVAL; + err = -EINVAL; + goto out; + } + if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) { + err = -ENOMEM; + goto out; } - if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) - return -ENOMEM; } - if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) - return -EHOSTUNREACH; /* Routing failure or similar. */ + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) { + err = -EHOSTUNREACH; /* Routing failure or similar. */ + goto out; + } cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; @@ -3174,8 +3536,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { - if (TCP_SKB_CB(skb)->seq != tp->snd_una) - return -EAGAIN; + if (TCP_SKB_CB(skb)->seq != tp->snd_una) { + err = -EAGAIN; + goto out; + } avail_wnd = cur_mss; } @@ -3187,11 +3551,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, - cur_mss, GFP_ATOMIC)) - return -ENOMEM; /* We'll try again later. */ + cur_mss, GFP_ATOMIC)) { + err = -ENOMEM; /* We'll try again later. */ + goto out; + } } else { - if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) - return -ENOMEM; + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) { + err = -ENOMEM; + goto out; + } diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); @@ -3203,7 +3571,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tcp_retrans_try_collapse(sk, skb, avail_wnd); } - /* RFC3168, section 6.1.1.1. ECN fallback */ + /* RFC3168, section 6.1.1.1. ECN fallback + * As AccECN uses the same SYN flags (+ AE), this check covers both + * cases. + */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); @@ -3241,20 +3612,20 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } - /* To avoid taking spuriously low RTT samples based on a timestamp - * for a transmit that never happened, always mark EVER_RETRANS - */ - TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; - if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); - if (likely(!err)) { - trace_tcp_retransmit_skb(sk, skb); - } else if (err != -EBUSY) { + if (unlikely(err) && err != -EBUSY) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); - } + + /* To avoid taking spuriously low RTT samples based on a timestamp + * for a transmit that never happened, always mark EVER_RETRANS + */ + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + +out: + trace_tcp_retransmit_skb(sk, skb, err); return err; } @@ -3275,7 +3646,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); + tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; @@ -3358,8 +3729,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) } if (rearm_timer) tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX); + inet_csk(sk)->icsk_rto, true); } /* We allow to exceed memory limits for FIN packets to expedite @@ -3376,13 +3746,17 @@ void sk_forced_mem_schedule(struct sock *sk, int size) delta = size - sk->sk_forward_alloc; if (delta <= 0) return; + amt = sk_mem_pages(delta); - sk->sk_forward_alloc += amt << PAGE_SHIFT; - sk_memory_allocated_add(sk, amt); + sk_forward_alloc_add(sk, amt << PAGE_SHIFT); + + if (mem_cgroup_sk_enabled(sk)) + mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge() | __GFP_NOFAIL); - if (mem_cgroup_sockets_enabled && sk->sk_memcg) - mem_cgroup_charge_skmem(sk->sk_memcg, amt, - gfp_memcg_charge() | __GFP_NOFAIL); + if (sk->sk_bypass_prot_mem) + return; + + sk_memory_allocated_add(sk, amt); } /* Send a FIN. The caller locks the socket for us. @@ -3417,7 +3791,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; @@ -3425,7 +3801,7 @@ void tcp_send_fin(struct sock *sk) skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ - tcp_init_nondata_skb(skb, tp->write_seq, + tcp_init_nondata_skb(skb, sk, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } @@ -3437,7 +3813,8 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority) +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason) { struct sk_buff *skb; @@ -3452,7 +3829,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); - tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), + tcp_init_nondata_skb(skb, sk, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ @@ -3462,7 +3839,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL); + trace_tcp_send_reset(sk, NULL, reason); } /* Send a crossed SYN-ACK during socket establishment. @@ -3523,8 +3900,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_key *md5 = NULL; struct tcp_out_options opts; + struct tcp_key key = {}; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; @@ -3541,7 +3918,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, switch (synack_type) { case TCP_SYNACK_NORMAL: - skb_set_owner_w(skb, req_to_sk(req)); + skb_set_owner_edemux(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: /* Under synflood, we do not attach skb to a socket, @@ -3565,25 +3942,56 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb_set_delivery_time(skb, cookie_init_timestamp(req, now), - true); + SKB_CLOCK_MONOTONIC); else #endif { - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); - md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + if (tcp_rsk_used_ao(req)) { +#ifdef CONFIG_TCP_AO + struct tcp_ao_key *ao_key = NULL; + u8 keyid = tcp_rsk(req)->ao_keyid; + u8 rnext = tcp_rsk(req)->ao_rcv_next; + + ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), + keyid, -1); + /* If there is no matching key - avoid sending anything, + * especially usigned segments. It could try harder and lookup + * for another peer-matching key, but the peer has requested + * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. + */ + if (unlikely(!ao_key)) { + trace_tcp_ao_synack_no_key(sk, keyid, rnext); + rcu_read_unlock(); + kfree_skb(skb); + net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", + keyid); + return NULL; + } + key.ao_key = ao_key; + key.type = TCP_KEY_AO; +#endif + } else { +#ifdef CONFIG_TCP_MD5SIG + key.md5_key = tcp_rsk(req)->af_specific->req_md5_lookup(sk, + req_to_sk(req)); + if (key.md5_key) + key.type = TCP_KEY_MD5; +#endif + } + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; - tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc, synack_type, - syn_skb) + sizeof(*th); + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, + &key, foc, synack_type, syn_skb) + + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3603,27 +4011,36 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); - tcp_options_write(th, NULL, &opts); + tcp_options_write(th, NULL, tcp_rsk(req), &opts, &key); th->doff = (tcp_header_size >> 2); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); -#ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ - if (md5) + if (tcp_key_is_md5(&key)) { +#ifdef CONFIG_TCP_MD5SIG tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, - md5, req_to_sk(req), skb); + key.md5_key, req_to_sk(req), skb); +#endif + } else if (tcp_key_is_ao(&key)) { +#ifdef CONFIG_TCP_AO + tcp_rsk(req)->af_specific->ao_synack_hash(opts.hash_location, + key.ao_key, req, skb, + opts.hash_location - (u8 *)th, 0); +#endif + } +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_unlock(); #endif bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); tcp_add_tx_delay(skb, tp); return skb; } -EXPORT_SYMBOL(tcp_make_synack); +EXPORT_IPV6_MOD(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { @@ -3650,6 +4067,7 @@ static void tcp_connect_init(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; + u16 user_mss; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. @@ -3659,14 +4077,12 @@ static void tcp_connect_init(struct sock *sk) if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; -#ifdef CONFIG_TCP_MD5SIG - if (tp->af_specific->md5_lookup(sk, sk)) - tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; -#endif + tcp_ao_connect_init(sk); /* If user gave his TCP_MAXSEG, record it to clamp */ - if (tp->rx_opt.user_mss) - tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; + user_mss = READ_ONCE(tp->rx_opt.user_mss); + if (user_mss) + tp->rx_opt.mss_clamp = user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); @@ -3674,7 +4090,7 @@ static void tcp_connect_init(struct sock *sk) tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) - tp->window_clamp = dst_metric(dst, RTAX_WINDOW); + WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW)); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); @@ -3682,7 +4098,7 @@ static void tcp_connect_init(struct sock *sk) /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) - tp->window_clamp = tcp_full_space(sk); + WRITE_ONCE(tp->window_clamp, tcp_full_space(sk)); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) @@ -3699,7 +4115,7 @@ static void tcp_connect_init(struct sock *sk) tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; - sk->sk_err = 0; + WRITE_ONCE(sk->sk_err, 0); sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); @@ -3717,7 +4133,7 @@ static void tcp_connect_init(struct sock *sk) WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); - inet_csk(sk)->icsk_retransmits = 0; + WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0); tcp_clear_retrans(tp); } @@ -3746,8 +4162,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int space, err = 0; + struct page_frag *pfrag = sk_page_frag(sk); struct sk_buff *syn_data; + int space, err = 0; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie)) @@ -3766,25 +4183,31 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = min_t(size_t, space, fo->size); - /* limit to order-0 allocations */ - space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); - - syn_data = tcp_stream_alloc_skb(sk, space, sk->sk_allocation, false); + if (space && + !skb_page_frag_refill(min_t(size_t, space, PAGE_SIZE), + pfrag, sk->sk_allocation)) + goto fallback; + syn_data = tcp_stream_alloc_skb(sk, sk->sk_allocation, false); if (!syn_data) goto fallback; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (space) { - int copied = copy_from_iter(skb_put(syn_data, space), space, - &fo->data->msg_iter); - if (unlikely(!copied)) { + space = min_t(size_t, space, pfrag->size - pfrag->offset); + space = tcp_wmem_schedule(sk, space); + } + if (space) { + space = copy_page_from_iter(pfrag->page, pfrag->offset, + space, &fo->data->msg_iter); + if (unlikely(!space)) { tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } - if (copied != space) { - skb_trim(syn_data, copied); - space = copied; - } + skb_fill_page_desc(syn_data, 0, pfrag->page, + pfrag->offset, space); + page_ref_inc(pfrag->page); + pfrag->offset += space; + skb_len_add(syn_data, space); skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ @@ -3798,7 +4221,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true); + skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, SKB_CLOCK_MONOTONIC); /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) @@ -3839,6 +4262,53 @@ int tcp_connect(struct sock *sk) tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); +#if defined(CONFIG_TCP_MD5SIG) && defined(CONFIG_TCP_AO) + /* Has to be checked late, after setting daddr/saddr/ops. + * Return error if the peer has both a md5 and a tcp-ao key + * configured as this is ambiguous. + */ + if (unlikely(rcu_dereference_protected(tp->md5sig_info, + lockdep_sock_is_held(sk)))) { + bool needs_ao = !!tp->af_specific->ao_lookup(sk, sk, -1, -1); + bool needs_md5 = !!tp->af_specific->md5_lookup(sk, sk); + struct tcp_ao_info *ao_info; + + ao_info = rcu_dereference_check(tp->ao_info, + lockdep_sock_is_held(sk)); + if (ao_info) { + /* This is an extra check: tcp_ao_required() in + * tcp_v{4,6}_parse_md5_keys() should prevent adding + * md5 keys on ao_required socket. + */ + needs_ao |= ao_info->ao_required; + WARN_ON_ONCE(ao_info->ao_required && needs_md5); + } + if (needs_md5 && needs_ao) + return -EKEYREJECTED; + + /* If we have a matching md5 key and no matching tcp-ao key + * then free up ao_info if allocated. + */ + if (needs_md5) { + tcp_ao_destroy_sock(sk, false); + } else if (needs_ao) { + tcp_clear_md5_list(sk); + kfree(rcu_replace_pointer(tp->md5sig_info, NULL, + lockdep_sock_is_held(sk))); + } + } +#endif +#ifdef CONFIG_TCP_AO + if (unlikely(rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)))) { + /* Don't allow connecting if ao is configured but no + * matching key is found. + */ + if (!tp->af_specific->ao_lookup(sk, sk, -1, -1)) + return -EKEYREJECTED; + } +#endif + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ @@ -3849,13 +4319,16 @@ int tcp_connect(struct sock *sk) return 0; } - buff = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, true); + buff = tcp_stream_alloc_skb(sk, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; - tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); + /* SYN eats a sequence byte, write_seq updated by + * tcp_connect_queue_skb(). + */ + tcp_init_nondata_skb(buff, sk, tp->write_seq, TCPHDR_SYN); tcp_mstamp_refresh(tp); - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); @@ -3879,12 +4352,19 @@ int tcp_connect(struct sock *sk) TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, false); return 0; } EXPORT_SYMBOL(tcp_connect); +u32 tcp_delack_max(const struct sock *sk) +{ + u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1; + + return min(READ_ONCE(inet_csk(sk)->icsk_delack_max), delack_from_rto_min); +} + /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. @@ -3920,7 +4400,7 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } - ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + ato = min_t(u32, ato, tcp_delack_max(sk)); /* Stay within the limit we were given */ timeout = jiffies + ato; @@ -3928,21 +4408,21 @@ void tcp_send_delayed_ack(struct sock *sk) /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer is about to expire, send ACK now. */ - if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { + if (time_before_eq(icsk_delack_timeout(icsk), jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } - if (!time_before(timeout, icsk->icsk_ack.timeout)) - timeout = icsk->icsk_ack.timeout; + if (!time_before(timeout, icsk_delack_timeout(icsk))) + timeout = icsk_delack_timeout(icsk); } - icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = timeout; + smp_store_release(&icsk->icsk_ack.pending, + icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER); sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ -void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags) { struct sk_buff *buff; @@ -3961,17 +4441,18 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) unsigned long delay; delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; - if (delay < TCP_RTO_MAX) + if (delay < tcp_rto_max(sk)) icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, false); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); + tcp_init_nondata_skb(buff, sk, + tcp_acceptable_seq(sk), TCPHDR_ACK | flags); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. @@ -3986,7 +4467,7 @@ EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { - __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt, 0); } /* This routine sends a packet with an out of date sequence @@ -4017,7 +4498,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) * end to send an ack. Don't queue or clone SKB, just * send it. */ - tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); + tcp_init_nondata_skb(skb, sk, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } @@ -4091,17 +4572,17 @@ void tcp_send_probe0(struct sock *sk) if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ - icsk->icsk_probes_out = 0; + WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_backoff = 0; icsk->icsk_probes_tstamp = 0; return; } - icsk->icsk_probes_out++; + WRITE_ONCE(icsk->icsk_probes_out, icsk->icsk_probes_out + 1); if (err <= 0) { if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; - timeout = tcp_probe0_when(sk, TCP_RTO_MAX); + timeout = tcp_probe0_when(sk, tcp_rto_max(sk)); } else { /* If packet was not sent due to local congestion, * Let senders fight for local resources conservatively. @@ -4110,7 +4591,7 @@ void tcp_send_probe0(struct sock *sk) } timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, true); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) @@ -4121,16 +4602,22 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); - if (unlikely(tcp_passive_fastopen(sk))) - tcp_sk(sk)->total_retrans++; + if (unlikely(tcp_passive_fastopen(sk))) { + /* sk has const attribute because listeners are lockless. + * However in this case, we are dealing with a passive fastopen + * socket thus we can change total_retrans value. + */ + tcp_sk_rw(sk)->total_retrans++; + } trace_tcp_retransmit_synack(sk, req); + WRITE_ONCE(req->num_retrans, req->num_retrans + 1); } return res; } -EXPORT_SYMBOL(tcp_rtx_synack); +EXPORT_IPV6_MOD(tcp_rtx_synack); |