#define pr_fmt(fmt) "TCP: " fmt
#include <crypto/hash.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/inet_diag.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>
#include <linux/splice.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/random.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/errqueue.h>
#include <linux/static_key.h>
#include <linux/btf.h>
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/sock.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <net/busy_poll.h>
enum {
TCP_CMSG_INQ = 1,
TCP_CMSG_TS = 2
};
DEFINE_PER_CPU(unsigned int, tcp_orphan_count);
EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count);
long sysctl_tcp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_mem);
atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp;
EXPORT_SYMBOL(tcp_memory_allocated);
DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc);
EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc);
#if IS_ENABLED(CONFIG_SMC)
DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
EXPORT_SYMBOL(tcp_have_smc);
#endif
struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp;
EXPORT_SYMBOL(tcp_sockets_allocated);
struct tcp_splice_state {
struct pipe_inode_info *pipe;
size_t len;
unsigned int flags;
};
unsigned long tcp_memory_pressure __read_mostly;
EXPORT_SYMBOL_GPL(tcp_memory_pressure);
void tcp_enter_memory_pressure(struct sock *sk)
{
unsigned long val;
if (READ_ONCE(tcp_memory_pressure))
return;
val = jiffies;
if (!val)
val--;
if (!cmpxchg(&tcp_memory_pressure, 0, val))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
}
EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure);
void tcp_leave_memory_pressure(struct sock *sk)
{
unsigned long val;
if (!READ_ONCE(tcp_memory_pressure))
return;
val = xchg(&tcp_memory_pressure, 0);
if (val)
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO,
jiffies_to_msecs(jiffies - val));
}
EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure);
static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
{
u8 res = 0;
if (seconds > 0) {
int period = timeout;
res = 1;
while (seconds > period && res < 255) {
res++;
timeout <<= 1;
if (timeout > rto_max)
timeout = rto_max;
period += timeout;
}
}
return res;
}
static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
{
int period = 0;
if (retrans > 0) {
period = timeout;
while (--retrans) {
timeout <<= 1;
if (timeout > rto_max)
timeout = rto_max;
period += timeout;
}
}
return period;
}
static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp)
{
u32 rate = READ_ONCE(tp->rate_delivered);
u32 intv = READ_ONCE(tp->rate_interval_us);
u64 rate64 = 0;
if (rate && intv) {
rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
do_div(rate64, intv);
}
return rate64;
}
void tcp_init_sock(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
tp->out_of_order_queue = RB_ROOT;
sk->tcp_rtx_queue = RB_ROOT;
tcp_init_xmit_timers(sk);
INIT_LIST_HEAD(&tp->tsq_node);
INIT_LIST_HEAD(&tp->tsorted_sent_queue);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
icsk->icsk_rto_min = TCP_RTO_MIN;
icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
tp->app_limited = ~0U;
tp->rate_app_limited = 1;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
tp->rack.reo_wnd_steps = 1;
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
icsk->icsk_sync_mss = tcp_sync_mss;
WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
tcp_scaling_ratio_init(sk);
set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
sk_sockets_allocated_inc(sk);
}
EXPORT_SYMBOL(tcp_init_sock);
static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
{
struct sk_buff *skb = tcp_write_queue_tail(sk);
if (tsflags && skb) {
struct skb_shared_info *shinfo = skb_shinfo(skb);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags);
if (tsflags & SOF_TIMESTAMPING_TX_ACK)
tcb->txstamp_ack = 1;
if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
}
}
static bool tcp_stream_is_readable(struct sock *sk, int target)
{
if (tcp_epollin_ready(sk, target))
return true;
return sk_is_readable(sk);
}
__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
__poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
u8 shutdown;
int state;
sock_poll_wait(file, sock, wait);
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
mask = 0;
shutdown = READ_ONCE(sk->sk_shutdown);
if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
mask |= EPOLLHUP;
if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
if (state != TCP_SYN_SENT &&
(state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
int target = sock_rcvlowat(sk, 0, INT_MAX);
u16 urg_data = READ_ONCE(tp->urg_data);
if (unlikely(urg_data) &&
READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
!sock_flag(sk, SOCK_URGINLINE))
target++;
if (tcp_stream_is_readable(sk, target))
mask |= EPOLLIN | EPOLLRDNORM;
if (!(shutdown & SEND_SHUTDOWN)) {
if (__sk_stream_is_writeable(sk, 1)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
smp_mb__after_atomic();
if (__sk_stream_is_writeable(sk, 1))
mask |= EPOLLOUT | EPOLLWRNORM;
}
} else
mask |= EPOLLOUT | EPOLLWRNORM;
if (urg_data & TCP_URG_VALID)
mask |= EPOLLPRI;
} else if (state == TCP_SYN_SENT &&
inet_test_bit(DEFER_CONNECT, sk)) {
mask |= EPOLLOUT | EPOLLWRNORM;
}
smp_rmb();
if (READ_ONCE(sk->sk_err) ||
!skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR;
return mask;
}
EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, int *karg)
{
struct tcp_sock *tp = tcp_sk(sk);
int answ;
bool slow;
switch (cmd) {
case SIOCINQ:
if (sk->sk_state == TCP_LISTEN)
return -EINVAL;
slow = lock_sock_fast(sk);
answ = tcp_inq(sk);
unlock_sock_fast(sk, slow);
break;
case SIOCATMARK:
answ = READ_ONCE(tp->urg_data) &&
READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
break;
case SIOCOUTQ:
if (sk->sk_state == TCP_LISTEN)
return -EINVAL;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
answ = READ_ONCE(tp->write_seq) - tp->snd_una;
break;
case SIOCOUTQNSD:
if (sk->sk_state == TCP_LISTEN)
return -EINVAL;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
answ = READ_ONCE(tp->write_seq) -
READ_ONCE(tp->snd_nxt);
break;
default:
return -ENOIOCTLCMD;
}
*karg = answ;
return 0;
}
EXPORT_SYMBOL(tcp_ioctl);
void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
tp->pushed_seq = tp->write_seq;
}
static inline bool forced_push(const struct tcp_sock *tp)
{
return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}
void tcp_skb_entail(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
tcb->seq = tcb->end_seq = tp->write_seq;
tcb->tcp_flags = TCPHDR_ACK;
__skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
if (tp->nonagle & TCP_NAGLE_PUSH)
tp->nonagle &= ~TCP_NAGLE_PUSH;
tcp_slow_start_after_idle_check(sk);
}
static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
{
if (flags & MSG_OOB)
tp->snd_up = tp->write_seq;
}
static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
!tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
tcp_skb_can_collapse_to(skb);
}
void tcp_push(struct sock *sk, int flags, int mss_now,
int nonagle, int size_goal)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
skb = tcp_write_queue_tail(sk);
if (!skb)
return;
if (!(flags & MSG_MORE) || forced_push(tp))
tcp_mark_push(tp, skb);
tcp_mark_urg(tp, flags);
if (tcp_should_autocork(sk, skb, size_goal)) {
if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
}
if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize)
return;
}
if (flags & MSG_MORE)
nonagle = TCP_NAGLE_CORK;
__tcp_push_pending_frames(sk, mss_now, nonagle);
}
static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
unsigned int offset, size_t len)
{
struct tcp_splice_state *tss = rd_desc->arg.data;
int ret;
ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe,
min(rd_desc->count, len), tss->flags);
if (ret > 0)
rd_desc->count -= ret;
return ret;
}
static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
{
read_descriptor_t rd_desc = {
.arg.data = tss,
.count = tss->len,
};
return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
}
ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct sock *sk = sock->sk;
struct tcp_splice_state tss = {
.pipe = pipe,
.len = len,
.flags = flags,
};
long timeo;
ssize_t spliced;
int ret;
sock_rps_record_flow(sk);
if (unlikely(*ppos))
return -ESPIPE;
ret = spliced = 0;
lock_sock(sk);
timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
while (tss.len) {
ret = __tcp_splice_read(sk, &tss);
if (ret < 0)
break;
else if (!ret) {
if (spliced)
break;
if (sock_flag(sk, SOCK_DONE))
break;
if (sk->sk_err) {
ret = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN)
break;
if (sk->sk_state == TCP_CLOSE) {
ret = -ENOTCONN;
break;
}
if (!timeo) {
ret = -EAGAIN;
break;
}
if (!skb_queue_empty(&sk->sk_receive_queue))
break;
ret = sk_wait_data(sk, &timeo, NULL);
if (ret < 0)
break;
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
break;
}
continue;
}
tss.len -= ret;
spliced += ret;
if (!tss.len || !timeo)
break;
release_sock(sk);
lock_sock(sk);
if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
signal_pending(current))
break;
}
release_sock(sk);
if (spliced)
return spliced;
return ret;
}
EXPORT_SYMBOL(tcp_splice_read);
struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
bool force_schedule)
{
struct sk_buff *skb;
skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
if (likely(skb)) {
bool mem_scheduled;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
if (force_schedule) {
mem_scheduled = true;
sk_forced_mem_schedule(sk, skb->truesize);
} else {
mem_scheduled = sk_wmem_schedule(sk, skb->truesize);
}
if (likely(mem_scheduled)) {
skb_reserve(skb, MAX_TCP_HEADER);
skb->ip_summed = CHECKSUM_PARTIAL;
INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
return skb;
}
__kfree_skb(skb);
} else {
sk->sk_prot->enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
}
return NULL;
}
static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
int large_allowed)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 new_size_goal, size_goal;
if (!large_allowed)
return mss_now;
new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size);
size_goal = tp->gso_segs * mss_now;
if (unlikely(new_size_goal < size_goal ||
new_size_goal >= size_goal + mss_now)) {
tp->gso_segs = min_t(u16, new_size_goal / mss_now,
sk->sk_gso_max_segs);
size_goal = tp->gso_segs * mss_now;
}
return max(size_goal, mss_now);
}
int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
{
int mss_now;
mss_now = tcp_current_mss(sk);
*size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
return mss_now;
}
void tcp_remove_empty_skb(struct sock *sk)
{
struct sk_buff *skb = tcp_write_queue_tail(sk);
if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
tcp_unlink_write_queue(skb, sk);
if (tcp_write_queue_empty(sk))
tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
tcp_wmem_free_skb(sk, skb);
}
}
static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
{
if (unlikely(skb_zcopy_pure(skb))) {
u32 extra = skb->truesize -
SKB_TRUESIZE(skb_end_offset(skb));
if (!sk_wmem_schedule(sk, extra))
return -ENOMEM;
sk_mem_charge(sk, extra);
skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
}
return 0;
}
int tcp_wmem_schedule(struct sock *sk, int copy)
{
int left;
if (likely(sk_wmem_schedule(sk, copy)))
return copy;
left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued;
if (left > 0)
sk_forced_mem_schedule(sk, min(left, copy));
return min(copy, sk->sk_forward_alloc);
}
void tcp_free_fastopen_req(struct tcp_sock *tp)
{
if (tp->fastopen_req) {
kfree(tp->fastopen_req);
tp->fastopen_req = NULL;
}
}
int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
size_t size, struct ubuf_info *uarg)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
if (tp->fastopen_req)
return -EALREADY;
tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
sk->sk_allocation);
if (unlikely(!tp->fastopen_req))
return -ENOBUFS;
tp->fastopen_req->data = msg;
tp->fastopen_req->size = size;
tp->fastopen_req->uarg = uarg;
if (inet_test_bit(DEFER_CONNECT, sk)) {
err = tcp_connect(sk);
if (err) {
tcp_set_state(sk, TCP_CLOSE);
inet->inet_dport = 0;
sk->sk_route_caps = 0;
}
}
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, uaddr,
msg->msg_namelen, flags, 1);
if (tp->fastopen_req) {
*copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
inet_clear_bit(DEFER_CONNECT, sk);
}
return err;
}
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
struct ubuf_info *uarg = NULL;
struct sk_buff *skb;
struct sockcm_cookie sockc;
int flags, err, copied = 0;
int mss_now = 0, size_goal, copied_syn = 0;
int process_backlog = 0;
int zc = 0;
long timeo;
flags = msg->msg_flags;
if ((flags & MSG_ZEROCOPY) && size) {
if (msg->msg_ubuf) {
uarg = msg->msg_ubuf;
if (sk->sk_route_caps & NETIF_F_SG)
zc = MSG_ZEROCOPY;
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
skb = tcp_write_queue_tail(sk);
uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
if (!uarg) {
err = -ENOBUFS;
goto out_err;
}
if (sk->sk_route_caps & NETIF_F_SG)
zc = MSG_ZEROCOPY;
else
uarg_to_msgzc(uarg)->zerocopy = 0;
}
} else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) {
if (sk->sk_route_caps & NETIF_F_SG)
zc = MSG_SPLICE_PAGES;
}
if (unlikely(flags & MSG_FASTOPEN ||
inet_test_bit(DEFER_CONNECT, sk)) &&
!tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
else if (err)
goto out_err;
}
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
tcp_rate_check_app_limited(sk);
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
!tcp_passive_fastopen(sk)) {
err = sk_stream_wait_connect(sk, &timeo);
if (err != 0)
goto do_error;
}
if (unlikely(tp->repair)) {
if (tp->repair_queue == TCP_RECV_QUEUE) {
copied = tcp_send_rcvq(sk, msg, size);
goto out_nopush;
}
err = -EINVAL;
if (tp->repair_queue == TCP_NO_QUEUE)
goto out_err;
}
sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err)) {
err = -EINVAL;
goto out_err;
}
}
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
copied = 0;
restart:
mss_now = tcp_send_mss(sk, &size_goal, flags);
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
while (msg_data_left(msg)) {
ssize_t copy = 0;
skb = tcp_write_queue_tail(sk);
if (skb)
copy = size_goal - skb->len;
if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
bool first_skb;
new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_space;
if (unlikely(process_backlog >= 16)) {
process_backlog = 0;
if (sk_flush_backlog(sk))
goto restart;
}
first_skb = tcp_rtx_and_write_queues_empty(sk);
skb = tcp_stream_alloc_skb(sk, sk->sk_allocation,
first_skb);
if (!skb)
goto wait_for_space;
process_backlog++;
tcp_skb_entail(sk, skb);
copy = size_goal;
if (tp->repair)
TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
}
if (copy > msg_data_left(msg))
copy = msg_data_left(msg);
if (zc == 0) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
if (!sk_page_frag_refill(sk, pfrag))
goto wait_for_space;
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
if (i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}
merge = false;
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) {
if (tcp_downgrade_zcopy_pure(sk, skb))
goto wait_for_space;
skb_zcopy_downgrade_managed(skb);
}
copy = tcp_wmem_schedule(sk, copy);
if (!copy)
goto wait_for_space;
err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
pfrag->page,
pfrag->offset,
copy);
if (err)
goto do_error;
if (merge) {
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
} else {
skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, copy);
page_ref_inc(pfrag->page);
}
pfrag->offset += copy;
} else if (zc == MSG_ZEROCOPY) {
if (!skb->len)
skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY;
if (!skb_zcopy_pure(skb)) {
copy = tcp_wmem_schedule(sk, copy);
if (!copy)
goto wait_for_space;
}
err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
if (err == -EMSGSIZE || err == -EEXIST) {
tcp_mark_push(tp, skb);
goto new_segment;
}
if (err < 0)
goto do_error;
copy = err;
} else if (zc == MSG_SPLICE_PAGES) {
if (tcp_downgrade_zcopy_pure(sk, skb))
goto wait_for_space;
copy = tcp_wmem_schedule(sk, copy);
if (!copy)
goto wait_for_space;
err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
sk->sk_allocation);
if (err < 0) {
if (err == -EMSGSIZE) {
tcp_mark_push(tp, skb);
goto new_segment;
}
goto do_error;
}
copy = err;
if (!(flags & MSG_NO_SHARED_FRAGS))
skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
sk_wmem_queued_add(sk, copy);
sk_mem_charge(sk, copy);
}
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
TCP_SKB_CB(skb)->end_seq += copy;
tcp_skb_pcount_set(skb, 0);
copied += copy;
if (!msg_data_left(msg)) {
if (unlikely(flags & MSG_EOR))
TCP_SKB_CB(skb)->eor = 1;
goto out;
}
if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair))
continue;
if (forced_push(tp)) {
tcp_mark_push(tp, skb);
__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
} else if (skb == tcp_send_head(sk))
tcp_push_one(sk, mss_now);
continue;
wait_for_space:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
tcp_remove_empty_skb(sk);
if (copied)
tcp_push(sk, flags & ~MSG_MORE, mss_now,
TCP_NAGLE_PUSH, size_goal);
err = sk_stream_wait_memory(sk, &timeo);
if (err != 0)
goto do_error;
mss_now = tcp_send_mss(sk, &size_goal, flags);
}
out:
if (copied) {
tcp_tx_timestamp(sk, sockc.tsflags);
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
}
out_nopush:
if (uarg && !msg->msg_ubuf)
net_zcopy_put(uarg);
return copied + copied_syn;
do_error:
tcp_remove_empty_skb(sk);
if (copied + copied_syn)
goto out;
out_err:
if (uarg && !msg->msg_ubuf)
net_zcopy_put_abort(uarg, true);
err = sk_stream_error(sk, flags, err);
if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
sk->sk_write_space(sk);
tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
return err;
}
EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);
int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
int ret;
lock_sock(sk);
ret = tcp_sendmsg_locked(sk, msg, size);
release_sock(sk);
return ret;
}
EXPORT_SYMBOL(tcp_sendmsg);
void tcp_splice_eof(struct socket *sock)
{
struct sock *sk = sock->sk;
struct tcp_sock *tp = tcp_sk(sk);
int mss_now, size_goal;
if (!tcp_write_queue_tail(sk))
return;
lock_sock(sk);
mss_now = tcp_send_mss(sk, &size_goal, 0);
tcp_push(sk, 0, mss_now, tp->nonagle, size_goal);
release_sock(sk);
}
EXPORT_SYMBOL_GPL(tcp_splice_eof);
static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
{
struct tcp_sock *tp = tcp_sk(sk);
if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
tp->urg_data == TCP_URG_READ)
return -EINVAL;
if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
return -ENOTCONN;
if (tp->urg_data & TCP_URG_VALID) {
int err = 0;
char c = tp->urg_data;
if (!(flags & MSG_PEEK))
WRITE_ONCE(tp->urg_data, TCP_URG_READ);
msg->msg_flags |= MSG_OOB;
if (len > 0) {
if (!(flags & MSG_TRUNC))
err = memcpy_to_msg(msg, &c, 1);
len = 1;
} else
msg->msg_flags |= MSG_TRUNC;
return err ? -EFAULT : len;
}
if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
return 0;
return -EAGAIN;
}
static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
{
struct sk_buff *skb;
int copied = 0, err = 0;
skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
if (err)
return err;
copied += skb->len;
}
skb_queue_walk(&sk->sk_write_queue, skb) {
err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
if (err)
break;
copied += skb->len;
}
return err ?: copied;
}
void __tcp_cleanup_rbuf(struct sock *sk, int copied)
{
struct tcp_sock *tp = tcp_sk(sk);
bool time_to_ack = false;
if (inet_csk_ack_scheduled(sk)) {
const struct inet_connection_sock *icsk = inet_csk(sk);
if (
tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
(copied > 0 &&
((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
!inet_csk_in_pingpong_mode(sk))) &&
!atomic_read(&sk->sk_rmem_alloc)))
time_to_ack = true;
}
if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
__u32 rcv_window_now = tcp_receive_window(tp);
if (2*rcv_window_now <= tp->window_clamp) {
__u32 new_window = __tcp_select_window(sk);
if (new_window && new_window >= 2 * rcv_window_now)
time_to_ack = true;
}
}
if (time_to_ack)
tcp_send_ack(sk);
}
void tcp_cleanup_rbuf(struct sock *sk, int copied)
{
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
struct tcp_sock *tp = tcp_sk(sk);
WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
"cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
__tcp_cleanup_rbuf(sk, copied);
}
static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
{
__skb_unlink(skb, &sk->sk_receive_queue);
if (likely(skb->destructor == sock_rfree)) {
sock_rfree(skb);
skb->destructor = NULL;
skb->sk = NULL;
return skb_attempt_defer_free(skb);
}
__kfree_skb(skb);
}
struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
struct sk_buff *skb;
u32 offset;
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
offset = seq - TCP_SKB_CB(skb)->seq;
if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
}
if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
*off = offset;
return skb;
}
tcp_eat_recv_skb(sk, skb);
}
return NULL;
}
EXPORT_SYMBOL(tcp_recv_skb);
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor)
{
struct sk_buff *skb;
struct tcp_sock *tp = tcp_sk(sk);
u32 seq = tp->copied_seq;
u32 offset;
int copied = 0;
if (sk->sk_state == TCP_LISTEN)
return -ENOTCONN;
while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
if (offset < skb->len) {
int used;
size_t len;
len = skb->len - offset;
if (unlikely(tp->urg_data)) {
u32 urg_offset = tp->urg_seq - seq;
if (urg_offset < len)
len = urg_offset;
if (!len)
break;
}
used = recv_actor(desc, skb, offset, len);
if (used <= 0) {
if (!copied)
copied = used;
break;
}
if (WARN_ON_ONCE(used > len))
used = len;
seq += used;
copied += used;
offset += used;
skb = tcp_recv_skb(sk, seq - 1, &offset);
if (!skb)
break;
if (offset + 1 != skb->len)
continue;
}
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
tcp_eat_recv_skb(sk, skb);
++seq;
break;
}
tcp_eat_recv_skb(sk, skb);
if (!desc->count)
break;
WRITE_ONCE(tp->copied_seq, seq);
}
WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
if (copied > 0) {
tcp_recv_skb(sk, seq, &offset);
tcp_cleanup_rbuf(sk, copied);
}
return copied;
}
EXPORT_SYMBOL(tcp_read_sock);
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
struct sk_buff *skb;
int copied = 0;
if (sk->sk_state == TCP_LISTEN)
return -ENOTCONN;
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
u8 tcp_flags;
int used;
__skb_unlink(skb, &sk->sk_receive_queue);
WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
used = recv_actor(sk, skb);
if (used < 0) {
if (!copied)
copied = used;
break;
}
copied += used;
if (tcp_flags & TCPHDR_FIN)
break;
}
return copied;
}
EXPORT_SYMBOL(tcp_read_skb);
void tcp_read_done(struct sock *sk, size_t len)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 seq = tp->copied_seq;
struct sk_buff *skb;
size_t left;
u32 offset;
if (sk->sk_state == TCP_LISTEN)
return;
left = len;
while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
int used;
used = min_t(size_t, skb->len - offset, left);
seq += used;
left -= used;
if (skb->len > offset + used)
break;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
tcp_eat_recv_skb(sk, skb);
++seq;
break;
}
tcp_eat_recv_skb(sk, skb);
}
WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
if (left != len)
tcp_cleanup_rbuf(sk, len - left);
}
EXPORT_SYMBOL(tcp_read_done);
int tcp_peek_len(struct socket *sock)
{
return tcp_inq(sock->sk);
}
EXPORT_SYMBOL(tcp_peek_len);
int tcp_set_rcvlowat(struct sock *sk, int val)
{
int space, cap;
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
val = min(val, cap);
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
tcp_data_ready(sk);
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
return 0;
space = tcp_space_from_win(sk, val);
if (space > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, space);
tcp_sk(sk)->window_clamp = val;
}
return 0;
}
EXPORT_SYMBOL(tcp_set_rcvlowat);
void tcp_update_recv_tstamps(struct sk_buff *skb,
struct scm_timestamping_internal *tss)
{
if (skb->tstamp)
tss->ts[0] = ktime_to_timespec64(skb->tstamp);
else
tss->ts[0] = (struct timespec64) {0};
if (skb_hwtstamps(skb)->hwtstamp)
tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp);
else
tss->ts[2] = (struct timespec64) {0};
}
#ifdef CONFIG_MMU
static const struct vm_operations_struct tcp_vm_ops = {
};
int tcp_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_WRITE | VM_EXEC))
return -EPERM;
vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC);
vm_flags_set(vma, VM_MIXEDMAP);
vma->vm_ops = &tcp_vm_ops;
return 0;
}
EXPORT_SYMBOL(tcp_mmap);
static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
u32 *offset_frag)
{
skb_frag_t *frag;
if (unlikely(offset_skb >= skb->len))
return NULL;
offset_skb -= skb_headlen(skb);
if ((int)offset_skb < 0 || skb_has_frag_list(skb))
return NULL;
frag = skb_shinfo(skb)->frags;
while (offset_skb) {
if (skb_frag_size(frag) > offset_skb) {
*offset_frag = offset_skb;
return frag;
}
offset_skb -= skb_frag_size(frag);
++frag;
}
*offset_frag = 0;
return frag;
}
static bool can_map_frag(const skb_frag_t *frag)
{
return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
}
static int find_next_mappable_frag(const skb_frag_t *frag,
int remaining_in_skb)
{
int offset = 0;
if (likely(can_map_frag(frag)))
return 0;
while (offset < remaining_in_skb && !can_map_frag(frag)) {
offset += skb_frag_size(frag);
++frag;
}
return offset;
}
static void tcp_zerocopy_set_hint_for_skb(struct sock *sk,
struct tcp_zerocopy_receive *zc,
struct sk_buff *skb, u32 offset)
{
u32 frag_offset, partial_frag_remainder = 0;
int mappable_offset;
skb_frag_t *frag;
zc->recv_skip_hint = skb->len - offset;
frag = skb_advance_to_frag(skb, offset, &frag_offset);
if (!frag)
return;
if (frag_offset) {
struct skb_shared_info *info = skb_shinfo(skb);
if (frag == &info->frags[info->nr_frags - 1])
return;
partial_frag_remainder = skb_frag_size(frag) - frag_offset;
zc->recv_skip_hint -= partial_frag_remainder;
++frag;
}
mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint);
zc->recv_skip_hint = mappable_offset + partial_frag_remainder;
}
static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
int flags, struct scm_timestamping_internal *tss,
int *cmsg_flags);
static int receive_fallback_to_copy(struct sock *sk,
struct tcp_zerocopy_receive *zc, int inq,
struct scm_timestamping_internal *tss)
{
unsigned long copy_address = (unsigned long)zc->copybuf_address;
struct msghdr msg = {};
struct iovec iov;
int err;
zc->length = 0;
zc->recv_skip_hint = 0;
if (copy_address != zc->copybuf_address)
return -EINVAL;
err = import_single_range(ITER_DEST, (void __user *)copy_address,
inq, &iov, &msg.msg_iter);
if (err)
return err;
err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT,
tss, &zc->msg_flags);
if (err < 0)
return err;
zc->copybuf_len = err;
if (likely(zc->copybuf_len)) {
struct sk_buff *skb;
u32 offset;
skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset);
if (skb)
tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset);
}
return 0;
}
static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
struct sk_buff *skb, u32 copylen,
u32 *offset, u32 *seq)
{
unsigned long copy_address = (unsigned long)zc->copybuf_address;
struct msghdr msg = {};
struct iovec iov;
int err;
if (copy_address != zc->copybuf_address)
return -EINVAL;
err = import_single_range(ITER_DEST, (void __user *)copy_address,
copylen, &iov, &msg.msg_iter);
if (err)
return err;
err = skb_copy_datagram_msg(skb, *offset, &msg, copylen);
if (err)
return err;
zc->recv_skip_hint -= copylen;
*offset += copylen;
*seq += copylen;
return (__s32)copylen;
}
static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc,
struct sock *sk,
struct sk_buff *skb,
u32 *seq,
s32 copybuf_len,
struct scm_timestamping_internal *tss)
{
u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint);
if (!copylen)
return 0;
if (skb) {
offset = *seq - TCP_SKB_CB(skb)->seq;
} else {
skb = tcp_recv_skb(sk, *seq, &offset);
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, tss);
zc->msg_flags |= TCP_CMSG_TS;
}
}
zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset,
seq);
return zc->copybuf_len < 0 ? 0 : copylen;
}
static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
struct page **pending_pages,
unsigned long pages_remaining,
unsigned long *address,
u32 *length,
u32 *seq,
struct tcp_zerocopy_receive *zc,
u32 total_bytes_to_map,
int err)
{
if (err == -EBUSY &&
zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) {
u32 maybe_zap_len;
maybe_zap_len = total_bytes_to_map -
*length +
(pages_remaining * PAGE_SIZE);
zap_page_range_single(vma, *address, maybe_zap_len, NULL);
err = 0;
}
if (!err) {
unsigned long leftover_pages = pages_remaining;
int bytes_mapped;
err = vm_insert_pages(vma, *address,
pending_pages,
&pages_remaining);
bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining);
*seq += bytes_mapped;
*address += bytes_mapped;
}
if (err) {
const int bytes_not_mapped = PAGE_SIZE * pages_remaining;
*length -= bytes_not_mapped;
zc->recv_skip_hint += bytes_not_mapped;
}
return err;
}
static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma,
struct page **pages,
unsigned int pages_to_map,
unsigned long *address,
u32 *length,
u32 *seq,
struct tcp_zerocopy_receive *zc,
u32 total_bytes_to_map)
{
unsigned long pages_remaining = pages_to_map;
unsigned int pages_mapped;
unsigned int bytes_mapped;
int err;
err = vm_insert_pages(vma, *address, pages, &pages_remaining);
pages_mapped = pages_to_map - (unsigned int)pages_remaining;
bytes_mapped = PAGE_SIZE * pages_mapped;
*seq += bytes_mapped;
*address += bytes_mapped;
if (likely(!err))
return 0;
return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped,
pages_remaining, address, length, seq, zc, total_bytes_to_map,
err);
}
#define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS)
static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
struct tcp_zerocopy_receive *zc,
struct scm_timestamping_internal *tss)
{
unsigned long msg_control_addr;
struct msghdr cmsg_dummy;
msg_control_addr = (unsigned long)zc->msg_control;
cmsg_dummy.msg_control_user = (void __user *)msg_control_addr;
cmsg_dummy.msg_controllen =
(__kernel_size_t)zc->msg_controllen;
cmsg_dummy.msg_flags = in_compat_syscall()
? MSG_CMSG_COMPAT : 0;
cmsg_dummy.msg_control_is_user = true;
zc->msg_flags = 0;
if (zc->msg_control == msg_control_addr &&
zc->msg_controllen == cmsg_dummy.msg_controllen) {
tcp_recv_timestamp(&cmsg_dummy, sk, tss);
zc->msg_control = (__u64)
((uintptr_t)cmsg_dummy.msg_control_user);
zc->msg_controllen =
(__u64)cmsg_dummy.msg_controllen;
zc->msg_flags = (__u32)cmsg_dummy.msg_flags;
}
}
static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
unsigned long address,
bool *mmap_locked)
{
struct vm_area_struct *vma = lock_vma_under_rcu(mm, address);
if (vma) {
if (vma->vm_ops != &tcp_vm_ops) {
vma_end_read(vma);
return NULL;
}
*mmap_locked = false;
return vma;
}
mmap_read_lock(mm);
vma = vma_lookup(mm, address);
if (!vma || vma->vm_ops != &tcp_vm_ops) {
mmap_read_unlock(mm);
return NULL;
}
*mmap_locked = true;
return vma;
}
#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32
static int tcp_zerocopy_receive(struct sock *sk,
struct tcp_zerocopy_receive *zc,
struct scm_timestamping_internal *tss)
{
u32 length = 0, offset, vma_len, avail_len, copylen = 0;
unsigned long address = (unsigned long)zc->address;
struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE];
s32 copybuf_len = zc->copybuf_len;
struct tcp_sock *tp = tcp_sk(sk);
const skb_frag_t *frags = NULL;
unsigned int pages_to_map = 0;
struct vm_area_struct *vma;
struct sk_buff *skb = NULL;
u32 seq = tp->copied_seq;
u32 total_bytes_to_map;
int inq = tcp_inq(sk);
bool mmap_locked;
int ret;
zc->copybuf_len = 0;
zc->msg_flags = 0;
if (address & (PAGE_SIZE - 1) || address != zc->address)
return -EINVAL;
if (sk->sk_state == TCP_LISTEN)
return -ENOTCONN;
sock_rps_record_flow(sk);
if (inq && inq <= copybuf_len)
return receive_fallback_to_copy(sk, zc, inq, tss);
if (inq < PAGE_SIZE) {
zc->length = 0;
zc->recv_skip_hint = inq;
if (!inq && sock_flag(sk, SOCK_DONE))
return -EIO;
return 0;
}
vma = find_tcp_vma(current->mm, address, &mmap_locked);
if (!vma)
return -EINVAL;
vma_len = min_t(unsigned long, zc->length, vma->vm_end - address);
avail_len = min_t(u32, vma_len, inq);
total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1);
if (total_bytes_to_map) {
if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT))
zap_page_range_single(vma, address, total_bytes_to_map,
NULL);
zc->length = total_bytes_to_map;
zc->recv_skip_hint = 0;
} else {
zc->length = avail_len;
zc->recv_skip_hint = avail_len;
}
ret = 0;
while (length + PAGE_SIZE <= zc->length) {
int mappable_offset;
struct page *page;
if (zc->recv_skip_hint < PAGE_SIZE) {
u32 offset_frag;
if (skb) {
if (zc->recv_skip_hint > 0)
break;
skb = skb->next;
offset = seq - TCP_SKB_CB(skb)->seq;
} else {
skb = tcp_recv_skb(sk, seq, &offset);
}
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, tss);
zc->msg_flags |= TCP_CMSG_TS;
}
zc->recv_skip_hint = skb->len - offset;
frags = skb_advance_to_frag(skb, offset, &offset_frag);
if (!frags || offset_frag)
break;
}
mappable_offset = find_next_mappable_frag(frags,
zc->recv_skip_hint);
if (mappable_offset) {
zc->recv_skip_hint = mappable_offset;
break;
}
page = skb_frag_page(frags);
prefetchw(page);
pages[pages_to_map++] = page;
length += PAGE_SIZE;
zc->recv_skip_hint -= PAGE_SIZE;
frags++;
if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE ||
zc->recv_skip_hint < PAGE_SIZE) {
ret = tcp_zerocopy_vm_insert_batch(vma, pages,
pages_to_map,
&address, &length,
&seq, zc,
total_bytes_to_map);
if (ret)
goto out;
pages_to_map = 0;
}
}
if (pages_to_map) {
ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map,
&address, &length, &seq,
zc, total_bytes_to_map);
}
out:
if (mmap_locked)
mmap_read_unlock(current->mm);
else
vma_end_read(vma);
if (!ret)
copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss);
if (length + copylen) {
WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
tcp_recv_skb(sk, seq, &offset);
tcp_cleanup_rbuf(sk, length + copylen);
ret = 0;
if (length == zc->length)
zc->recv_skip_hint = 0;
} else {
if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE))
ret = -EIO;
}
zc->length = length;
return ret;
}
#endif
void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
struct scm_timestamping_internal *tss)
{
int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
bool has_timestamping = false;
if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
if (sock_flag(sk, SOCK_RCVTSTAMP)) {
if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
if (new_tstamp) {
struct __kernel_timespec kts = {
.tv_sec = tss->ts[0].tv_sec,
.tv_nsec = tss->ts[0].tv_nsec,
};
put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
sizeof(kts), &kts);
} else {
struct __kernel_old_timespec ts_old = {
.tv_sec = tss->ts[0].tv_sec,
.tv_nsec = tss->ts[0].tv_nsec,
};
put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD,
sizeof(ts_old), &ts_old);
}
} else {
if (new_tstamp) {
struct __kernel_sock_timeval stv = {
.tv_sec = tss->ts[0].tv_sec,
.tv_usec = tss->ts[0].tv_nsec / 1000,
};
put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW,
sizeof(stv), &stv);
} else {
struct __kernel_old_timeval tv = {
.tv_sec = tss->ts[0].tv_sec,
.tv_usec = tss->ts[0].tv_nsec / 1000,
};
put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD,
sizeof(tv), &tv);
}
}
}
if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE)
has_timestamping = true;
else
tss->ts[0] = (struct timespec64) {0};
}
if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE)
has_timestamping = true;
else
tss->ts[2] = (struct timespec64) {0};
}
if (has_timestamping) {
tss->ts[1] = (struct timespec64) {0};
if (sock_flag(sk, SOCK_TSTAMP_NEW))
put_cmsg_scm_timestamping64(msg, tss);
else
put_cmsg_scm_timestamping(msg, tss);
}
}
static int tcp_inq_hint(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
u32 copied_seq = READ_ONCE(tp->copied_seq);
u32 rcv_nxt = READ_ONCE(tp->rcv_nxt);
int inq;
inq = rcv_nxt - copied_seq;
if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) {
lock_sock(sk);
inq = tp->rcv_nxt - tp->copied_seq;
release_sock(sk);
}
if (inq == 0 && sock_flag(sk, SOCK_DONE))
inq = 1;
return inq;
}
static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
int flags, struct scm_timestamping_internal *tss,
int *cmsg_flags)
{
struct tcp_sock *tp = tcp_sk(sk);
int copied = 0;
u32 peek_seq;
u32 *seq;
unsigned long used;
int err;
int target;
long timeo;
struct sk_buff *skb, *last;
u32 urg_hole = 0;
err = -ENOTCONN;
if (sk->sk_state == TCP_LISTEN)
goto out;
if (tp->recvmsg_inq) {
*cmsg_flags = TCP_CMSG_INQ;
msg->msg_get_inq = 1;
}
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
if (flags & MSG_OOB)
goto recv_urg;
if (unlikely(tp->repair)) {
err = -EPERM;
if (!(flags & MSG_PEEK))
goto out;
if (tp->repair_queue == TCP_SEND_QUEUE)
goto recv_sndq;
err = -EINVAL;
if (tp->repair_queue == TCP_NO_QUEUE)
goto out;
}
seq = &tp->copied_seq;
if (flags & MSG_PEEK) {
peek_seq = tp->copied_seq;
seq = &peek_seq;
}
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
do {
u32 offset;
if (unlikely(tp->urg_data) && tp->urg_seq == *seq) {
if (copied)
break;
if (signal_pending(current)) {
copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
break;
}
}
last = skb_peek_tail(&sk->sk_receive_queue);
skb_queue_walk(&sk->sk_receive_queue, skb) {
last = skb;
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
"TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
flags))
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
}
if (offset < skb->len)
goto found_ok_skb;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
"TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
break;
if (copied) {
if (!timeo ||
sk->sk_err ||
sk->sk_state == TCP_CLOSE ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
signal_pending(current))
break;
} else {
if (sock_flag(sk, SOCK_DONE))
break;
if (sk->sk_err) {
copied = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN)
break;
if (sk->sk_state == TCP_CLOSE) {
copied = -ENOTCONN;
break;
}
if (!timeo) {
copied = -EAGAIN;
break;
}
if (signal_pending(current)) {
copied = sock_intr_errno(timeo);
break;
}
}
if (copied >= target) {
__sk_flush_backlog(sk);
} else {
tcp_cleanup_rbuf(sk, copied);
err = sk_wait_data(sk, &timeo, last);
if (err < 0) {
err = copied ? : err;
goto out;
}
}
if ((flags & MSG_PEEK) &&
(peek_seq - copied - urg_hole != tp->copied_seq)) {
net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
current->comm,
task_pid_nr(current));
peek_seq = tp->copied_seq;
}
continue;
found_ok_skb:
used = skb->len - offset;
if (len < used)
used = len;
if (unlikely(tp->urg_data)) {
u32 urg_offset = tp->urg_seq - *seq;
if (urg_offset < used) {
if (!urg_offset) {
if (!sock_flag(sk, SOCK_URGINLINE)) {
WRITE_ONCE(*seq, *seq + 1);
urg_hole++;
offset++;
used--;
if (!used)
goto skip_copy;
}
} else
used = urg_offset;
}
}
if (!(flags & MSG_TRUNC)) {
err = skb_copy_datagram_msg(skb, offset, msg, used);
if (err) {
if (!copied)
copied = -EFAULT;
break;
}
}
WRITE_ONCE(*seq, *seq + used);
copied += used;
len -= used;
tcp_rcv_space_adjust(sk);
skip_copy:
if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) {
WRITE_ONCE(tp->urg_data, 0);
tcp_fast_path_check(sk);
}
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, tss);
*cmsg_flags |= TCP_CMSG_TS;
}
if (used + offset < skb->len)
continue;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
if (!(flags & MSG_PEEK))
tcp_eat_recv_skb(sk, skb);
continue;
found_fin_ok:
WRITE_ONCE(*seq, *seq + 1);
if (!(flags & MSG_PEEK))
tcp_eat_recv_skb(sk, skb);
break;
} while (len > 0);
tcp_cleanup_rbuf(sk, copied);
return copied;
out:
return err;
recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
goto out;
recv_sndq:
err = tcp_peek_sndq(sk, msg, len);
goto out;
}
int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
int *addr_len)
{
int cmsg_flags = 0, ret;
struct scm_timestamping_internal tss;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
if (sk_can_busy_loop(sk) &&
skb_queue_empty_lockless(&sk->sk_receive_queue) &&
sk->sk_state == TCP_ESTABLISHED)
sk_busy_loop(sk, flags & MSG_DONTWAIT);
lock_sock(sk);
ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags);
release_sock(sk);
if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
if (cmsg_flags & TCP_CMSG_TS)
tcp_recv_timestamp(msg, sk, &tss);
if (msg->msg_get_inq) {
msg->msg_inq = tcp_inq_hint(sk);
if (cmsg_flags & TCP_CMSG_INQ)
put_cmsg(msg, SOL_TCP, TCP_CM_INQ,
sizeof(msg->msg_inq), &msg->msg_inq);
}
}
return ret;
}
EXPORT_SYMBOL(tcp_recvmsg);
void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
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);
BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED);
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:
if (oldstate != TCP_ESTABLISHED)
TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
break;
case TCP_CLOSE:
if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
inet_put_port(sk);
fallthrough;
default:
if (oldstate == TCP_ESTABLISHED)
TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
}
inet_sk_state_store(sk, state);
}
EXPORT_SYMBOL_GPL(tcp_set_state);
static const unsigned char new_state[16] = {
[0 ] = TCP_CLOSE,
[TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
[TCP_SYN_SENT] = TCP_CLOSE,
[TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
[TCP_FIN_WAIT1] = TCP_FIN_WAIT1,
[TCP_FIN_WAIT2] = TCP_FIN_WAIT2,
[TCP_TIME_WAIT] = TCP_CLOSE,
[TCP_CLOSE] = TCP_CLOSE,
[TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN,
[TCP_LAST_ACK] = TCP_LAST_ACK,
[TCP_LISTEN] = TCP_CLOSE,
[TCP_CLOSING] = TCP_CLOSING,
[TCP_NEW_SYN_RECV] = TCP_CLOSE,
};
static int tcp_close_state(struct sock *sk)
{
int next = (int)new_state[sk->sk_state];
int ns = next & TCP_STATE_MASK;
tcp_set_state(sk, ns);
return next & TCP_ACTION_FIN;
}
void tcp_shutdown(struct sock *sk, int how)
{
if (!(how & SEND_SHUTDOWN))
return;
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_SYN_SENT |
TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
if (tcp_close_state(sk))
tcp_send_fin(sk);
}
}
EXPORT_SYMBOL(tcp_shutdown);
int tcp_orphan_count_sum(void)
{
int i, total = 0;
for_each_possible_cpu(i)
total += per_cpu(tcp_orphan_count, i);
return max(total, 0);
}
static int tcp_orphan_cache;
static struct timer_list tcp_orphan_timer;
#define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100)
static void tcp_orphan_update(struct timer_list *unused)
{
WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum());
mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD);
}
static bool tcp_too_many_orphans(int shift)
{
return READ_ONCE(tcp_orphan_cache) << shift >
READ_ONCE(sysctl_tcp_max_orphans);
}
bool tcp_check_oom(struct sock *sk, int shift)
{
bool too_many_orphans, out_of_socket_memory;
too_many_orphans = tcp_too_many_orphans(shift);
out_of_socket_memory = tcp_out_of_memory(sk);
if (too_many_orphans)
net_info_ratelimited("too many orphaned sockets\n");
if (out_of_socket_memory)
net_info_ratelimited("out of memory -- consider tuning tcp_mem\n");
return too_many_orphans || out_of_socket_memory;
}
void __tcp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
int data_was_unread = 0;
int state;
WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
len--;
data_was_unread += len;
__kfree_skb(skb);
}
if (sk->sk_state == TCP_CLOSE)
goto adjudge_to_death;
if (unlikely(tcp_sk(sk)->repair)) {
sk->sk_prot->disconnect(sk, 0);
} else if (data_was_unread) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, sk->sk_allocation);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
sk->sk_prot->disconnect(sk, 0);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
} else if (tcp_close_state(sk)) {
tcp_send_fin(sk);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
local_bh_disable();
bh_lock_sock(sk);
__release_sock(sk);
this_cpu_inc(tcp_orphan_count);
if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
goto out;
if (sk->sk_state == TCP_FIN_WAIT2) {
struct tcp_sock *tp = tcp_sk(sk);
if (READ_ONCE(tp->linger2) < 0) {
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONLINGER);
} else {
const int tmo = tcp_fin_time(sk);
if (tmo > TCP_TIMEWAIT_LEN) {
inet_csk_reset_keepalive_timer(sk,
tmo - TCP_TIMEWAIT_LEN);
} else {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto out;
}
}
}
if (sk->sk_state != TCP_CLOSE) {
if (tcp_check_oom(sk, 0)) {
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONMEMORY);
} else if (!check_net(sock_net(sk))) {
tcp_set_state(sk, TCP_CLOSE);
}
}
if (sk->sk_state == TCP_CLOSE) {
struct request_sock *req;
req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
lockdep_sock_is_held(sk));
if (req)
reqsk_fastopen_remove(sk, req, false);
inet_csk_destroy_sock(sk);
}
out:
bh_unlock_sock(sk);
local_bh_enable();
}
void tcp_close(struct sock *sk, long timeout)
{
lock_sock(sk);
__tcp_close(sk, timeout);
release_sock(sk);
sock_put(sk);
}
EXPORT_SYMBOL(tcp_close);
static inline bool tcp_need_reset(int state)
{
return (1 << state) &
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 |
TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
}
static void tcp_rtx_queue_purge(struct sock *sk)
{
struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
tcp_sk(sk)->highest_sack = NULL;
while (p) {
struct sk_buff *skb = rb_to_skb(p);
p = rb_next(p);
tcp_rtx_queue_unlink(skb, sk);
tcp_wmem_free_skb(sk, skb);
}
}
void tcp_write_queue_purge(struct sock *sk)
{
struct sk_buff *skb;
tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
tcp_skb_tsorted_anchor_cleanup(skb);
tcp_wmem_free_skb(sk, skb);
}
tcp_rtx_queue_purge(sk);
INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
tcp_clear_all_retrans_hints(tcp_sk(sk));
tcp_sk(sk)->packets_out = 0;
inet_csk(sk)->icsk_backoff = 0;
}
int tcp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int old_state = sk->sk_state;
u32 seq;
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
if (old_state == TCP_LISTEN) {
inet_csk_listen_stop(sk);
} else if (unlikely(tp->repair)) {
WRITE_ONCE(sk->sk_err, ECONNABORTED);
} else if (tcp_need_reset(old_state) ||
(tp->snd_nxt != tp->write_seq &&
(1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
tcp_send_active_reset(sk, gfp_any());
WRITE_ONCE(sk->sk_err, ECONNRESET);
} else if (old_state == TCP_SYN_SENT)
WRITE_ONCE(sk->sk_err, ECONNRESET);
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
WRITE_ONCE(tp->urg_data, 0);
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
skb_rbtree_purge(&tp->out_of_order_queue);
inet->inet_dport = 0;
inet_bhash2_reset_saddr(sk);
WRITE_ONCE(sk->sk_shutdown, 0);
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
tp->rcv_rtt_last_tsecr = 0;
seq = tp->write_seq + tp->max_window + 2;
if (!seq)
seq = 1;
WRITE_ONCE(tp->write_seq, seq);
icsk->icsk_backoff = 0;
icsk->icsk_probes_out = 0;
icsk->icsk_probes_tstamp = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
icsk->icsk_rto_min = TCP_RTO_MIN;
icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
tp->snd_cwnd_cnt = 0;
tp->is_cwnd_limited = 0;
tp->max_packets_out = 0;
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
if (icsk->icsk_ca_ops->release)
icsk->icsk_ca_ops->release(sk);
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
icsk->icsk_ca_initialized = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
tp->total_retrans = 0;
inet_csk_delack_init(sk);
icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
tcp_saved_syn_free(tp);
tp->compressed_ack = 0;
tp->segs_in = 0;
tp->segs_out = 0;
tp->bytes_sent = 0;
tp->bytes_acked = 0;
tp->bytes_received = 0;
tp->bytes_retrans = 0;
tp->data_segs_in = 0;
tp->data_segs_out = 0;
tp->duplicate_sack[0].start_seq = 0;
tp->duplicate_sack[0].end_seq = 0;
tp->dsack_dups = 0;
tp->reord_seen = 0;
tp->retrans_out = 0;
tp->sacked_out = 0;
tp->tlp_high_seq = 0;
tp->last_oow_ack_time = 0;
tp->plb_rehash = 0;
tp->app_limited = ~0U;
tp->rate_app_limited = 1;
tp->rack.mstamp = 0;
tp->rack.advanced = 0;
tp->rack.reo_wnd_steps = 1;
tp->rack.last_delivered = 0;
tp->rack.reo_wnd_persist = 0;
tp->rack.dsack_seen = 0;
tp->syn_data_acked = 0;
tp->rx_opt.saw_tstamp = 0;
tp->rx_opt.dsack = 0;
tp->rx_opt.num_sacks = 0;
tp->rcv_ooopack = 0;
tcp_free_fastopen_req(tp);
inet_clear_bit(DEFER_CONNECT, sk);
tp->fastopen_client_fail = 0;
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_error_report(sk);
return 0;
}
EXPORT_SYMBOL(tcp_disconnect);
static inline bool tcp_can_repair_sock(const struct sock *sk)
{
return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
(sk->sk_state != TCP_LISTEN);
}
static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len)
{
struct tcp_repair_window opt;
if (!tp->repair)
return -EPERM;
if (len != sizeof(opt))
return -EINVAL;
if (copy_from_sockptr(&opt, optbuf, sizeof(opt)))
return -EFAULT;
if (opt.max_window < opt.snd_wnd)
return -EINVAL;
if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd))
return -EINVAL;
if (after(opt.rcv_wup, tp->rcv_nxt))
return -EINVAL;
tp->snd_wl1 = opt.snd_wl1;
tp->snd_wnd = opt.snd_wnd;
tp->max_window = opt.max_window;
tp->rcv_wnd = opt.rcv_wnd;
tp->rcv_wup = opt.rcv_wup;
return 0;
}
static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf,
unsigned int len)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_repair_opt opt;
size_t offset = 0;
while (len >= sizeof(opt)) {
if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt)))
return -EFAULT;
offset += sizeof(opt);
len -= sizeof(opt);
switch (opt.opt_code) {
case TCPOPT_MSS:
tp->rx_opt.mss_clamp = opt.opt_val;
tcp_mtup_init(sk);
break;
case TCPOPT_WINDOW:
{
u16 snd_wscale = opt.opt_val & 0xFFFF;
u16 rcv_wscale = opt.opt_val >> 16;
if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE)
return -EFBIG;
tp->rx_opt.snd_wscale = snd_wscale;
tp->rx_opt.rcv_wscale = rcv_wscale;
tp->rx_opt.wscale_ok = 1;
}
break;
case TCPOPT_SACK_PERM:
if (opt.opt_val != 0)
return -EINVAL;
tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
break;
case TCPOPT_TIMESTAMP:
if (opt.opt_val != 0)
return -EINVAL;
tp->rx_opt.tstamp_ok = 1;
break;
}
}
return 0;
}
DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled);
EXPORT_SYMBOL(tcp_tx_delay_enabled);
static void tcp_enable_tx_delay(void)
{
if (!static_branch_unlikely(&tcp_tx_delay_enabled)) {
static int __tcp_tx_delay_enabled = 0;
if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) {
static_branch_enable(&tcp_tx_delay_enabled);
pr_info("TCP_TX_DELAY enabled\n");
}
}
}
void __tcp_sock_set_cork(struct sock *sk, bool on)
{
struct tcp_sock *tp = tcp_sk(sk);
if (on) {
tp->nonagle |= TCP_NAGLE_CORK;
} else {
tp->nonagle &= ~TCP_NAGLE_CORK;
if (tp->nonagle & TCP_NAGLE_OFF)
tp->nonagle |= TCP_NAGLE_PUSH;
tcp_push_pending_frames(sk);
}
}
void tcp_sock_set_cork(struct sock *sk, bool on)
{
lock_sock(sk);
__tcp_sock_set_cork(sk, on);
release_sock(sk);
}
EXPORT_SYMBOL(tcp_sock_set_cork);
void __tcp_sock_set_nodelay(struct sock *sk, bool on)
{
if (on) {
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
tcp_push_pending_frames(sk);
} else {
tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF;
}
}
void tcp_sock_set_nodelay(struct sock *sk)
{
lock_sock(sk);
__tcp_sock_set_nodelay(sk, true);
release_sock(sk);
}
EXPORT_SYMBOL(tcp_sock_set_nodelay);
static void __tcp_sock_set_quickack(struct sock *sk, int val)
{
if (!val) {
inet_csk_enter_pingpong_mode(sk);
return;
}
inet_csk_exit_pingpong_mode(sk);
if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
inet_csk_ack_scheduled(sk)) {
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED;
tcp_cleanup_rbuf(sk, 1);
if (!(val & 1))
inet_csk_enter_pingpong_mode(sk);
}
}
void tcp_sock_set_quickack(struct sock *sk, int val)
{
lock_sock(sk);
__tcp_sock_set_quickack(sk, val);
release_sock(sk);
}
EXPORT_SYMBOL(tcp_sock_set_quickack);
int tcp_sock_set_syncnt(struct sock *sk, int val)
{
if (val < 1 || val > MAX_TCP_SYNCNT)
return -EINVAL;
WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_syncnt);
int tcp_sock_set_user_timeout(struct sock *sk, int val)
{
if (val < 0)
return -EINVAL;
WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_user_timeout);
int tcp_sock_set_keepidle_locked(struct sock *sk, int val)
{
struct tcp_sock *tp = tcp_sk(sk);
if (val < 1 || val > MAX_TCP_KEEPIDLE)
return -EINVAL;
WRITE_ONCE(tp->keepalive_time, val * HZ);
if (sock_flag(sk, SOCK_KEEPOPEN) &&
!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
u32 elapsed = keepalive_time_elapsed(tp);
if (tp->keepalive_time > elapsed)
elapsed = tp->keepalive_time - elapsed;
else
elapsed = 0;
inet_csk_reset_keepalive_timer(sk, elapsed);
}
return 0;
}
int tcp_sock_set_keepidle(struct sock *sk, int val)
{
int err;
lock_sock(sk);
err = tcp_sock_set_keepidle_locked(sk, val);
release_sock(sk);
return err;
}
EXPORT_SYMBOL(tcp_sock_set_keepidle);
int tcp_sock_set_keepintvl(struct sock *sk, int val)
{
if (val < 1 || val > MAX_TCP_KEEPINTVL)
return -EINVAL;
WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_keepintvl);
int tcp_sock_set_keepcnt(struct sock *sk, int val)
{
if (val < 1 || val > MAX_TCP_KEEPCNT)
return -EINVAL;
WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_keepcnt);
int tcp_set_window_clamp(struct sock *sk, int val)
{
struct tcp_sock *tp = tcp_sk(sk);
if (!val) {
if (sk->sk_state != TCP_CLOSE)
return -EINVAL;
tp->window_clamp = 0;
} else {
tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
SOCK_MIN_RCVBUF / 2 : val;
tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
}
return 0;
}
int do_tcp_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
int val;
int err = 0;
switch (optname) {
case TCP_CONGESTION: {
char name[TCP_CA_NAME_MAX];
if (optlen < 1)
return -EINVAL;
val = strncpy_from_sockptr(name, optval,
min_t(long, TCP_CA_NAME_MAX-1, optlen));
if (val < 0)
return -EFAULT;
name[val] = 0;
sockopt_lock_sock(sk);
err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(),
sockopt_ns_capable(sock_net(sk)->user_ns,
CAP_NET_ADMIN));
sockopt_release_sock(sk);
return err;
}
case TCP_ULP: {
char name[TCP_ULP_NAME_MAX];
if (optlen < 1)
return -EINVAL;
val = strncpy_from_sockptr(name, optval,
min_t(long, TCP_ULP_NAME_MAX - 1,
optlen));
if (val < 0)
return -EFAULT;
name[val] = 0;
sockopt_lock_sock(sk);
err = tcp_set_ulp(sk, name);
sockopt_release_sock(sk);
return err;
}
case TCP_FASTOPEN_KEY: {
__u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH];
__u8 *backup_key = NULL;
if (optlen != TCP_FASTOPEN_KEY_LENGTH &&
optlen != TCP_FASTOPEN_KEY_BUF_LENGTH)
return -EINVAL;
if (copy_from_sockptr(key, optval, optlen))
return -EFAULT;
if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH)
backup_key = key + TCP_FASTOPEN_KEY_LENGTH;
return tcp_fastopen_reset_cipher(net, sk, key, backup_key);
}
default:
break;
}
if (optlen < sizeof(int))
return -EINVAL;
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
switch (optname) {
case TCP_SYNCNT:
return tcp_sock_set_syncnt(sk, val);
case TCP_USER_TIMEOUT:
return tcp_sock_set_user_timeout(sk, val);
case TCP_KEEPINTVL:
return tcp_sock_set_keepintvl(sk, val);
case TCP_KEEPCNT:
return tcp_sock_set_keepcnt(sk, val);
case TCP_LINGER2:
if (val < 0)
WRITE_ONCE(tp->linger2, -1);
else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
else
WRITE_ONCE(tp->linger2, val * HZ);
return 0;
case TCP_DEFER_ACCEPT:
WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
TCP_RTO_MAX / HZ));
return 0;
}
sockopt_lock_sock(sk);
switch (optname) {
case TCP_MAXSEG:
if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) {
err = -EINVAL;
break;
}
tp->rx_opt.user_mss = val;
break;
case TCP_NODELAY:
__tcp_sock_set_nodelay(sk, val);
break;
case TCP_THIN_LINEAR_TIMEOUTS:
if (val < 0 || val > 1)
err = -EINVAL;
else
tp->thin_lto = val;
break;
case TCP_THIN_DUPACK:
if (val < 0 || val > 1)
err = -EINVAL;
break;
case TCP_REPAIR:
if (!tcp_can_repair_sock(sk))
err = -EPERM;
else if (val == TCP_REPAIR_ON) {
tp->repair = 1;
sk->sk_reuse = SK_FORCE_REUSE;
tp->repair_queue = TCP_NO_QUEUE;
} else if (val == TCP_REPAIR_OFF) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
tcp_send_window_probe(sk);
} else if (val == TCP_REPAIR_OFF_NO_WP) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
} else
err = -EINVAL;
break;
case TCP_REPAIR_QUEUE:
if (!tp->repair)
err = -EPERM;
else if ((unsigned int)val < TCP_QUEUES_NR)
tp->repair_queue = val;
else
err = -EINVAL;
break;
case TCP_QUEUE_SEQ:
if (sk->sk_state != TCP_CLOSE) {
err = -EPERM;
} else if (tp->repair_queue == TCP_SEND_QUEUE) {
if (!tcp_rtx_queue_empty(sk))
err = -EPERM;
else
WRITE_ONCE(tp->write_seq, val);
} else if (tp->repair_queue == TCP_RECV_QUEUE) {
if (tp->rcv_nxt != tp->copied_seq) {
err = -EPERM;
} else {
WRITE_ONCE(tp->rcv_nxt, val);
WRITE_ONCE(tp->copied_seq, val);
}
} else {
err = -EINVAL;
}
break;
case TCP_REPAIR_OPTIONS:
if (!tp->repair)
err = -EINVAL;
else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent)
err = tcp_repair_options_est(sk, optval, optlen);
else
err = -EPERM;
break;
case TCP_CORK:
__tcp_sock_set_cork(sk, val);
break;
case TCP_KEEPIDLE:
err = tcp_sock_set_keepidle_locked(sk, val);
break;
case TCP_SAVE_SYN:
if (val < 0 || val > 2)
err = -EINVAL;
else
tp->save_syn = val;
break;
case TCP_WINDOW_CLAMP:
err = tcp_set_window_clamp(sk, val);
break;
case TCP_QUICKACK:
__tcp_sock_set_quickack(sk, val);
break;
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
break;
#endif
case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
TCPF_LISTEN))) {
tcp_fastopen_init_key_once(net);
fastopen_queue_tune(sk, val);
} else {
err = -EINVAL;
}
break;
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
} else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
err = -EINVAL;
} else {
err = -EOPNOTSUPP;
}
break;
case TCP_FASTOPEN_NO_COOKIE:
if (val > 1 || val < 0)
err = -EINVAL;
else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
err = -EINVAL;
else
tp->fastopen_no_cookie = val;
break;
case TCP_TIMESTAMP:
if (!tp->repair)
err = -EPERM;
else
WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw());
break;
case TCP_REPAIR_WINDOW:
err = tcp_repair_set_window(tp, optval, optlen);
break;
case TCP_NOTSENT_LOWAT:
WRITE_ONCE(tp->notsent_lowat, val);
sk->sk_write_space(sk);
break;
case TCP_INQ:
if (val > 1 || val < 0)
err = -EINVAL;
else
tp->recvmsg_inq = val;
break;
case TCP_TX_DELAY:
if (val)
tcp_enable_tx_delay();
WRITE_ONCE(tp->tcp_tx_delay, val);
break;
default:
err = -ENOPROTOOPT;
break;
}
sockopt_release_sock(sk);
return err;
}
int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname,
optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(tcp_setsockopt);
static void tcp_get_info_chrono_stats(const struct tcp_sock *tp,
struct tcp_info *info)
{
u64 stats[__TCP_CHRONO_MAX], total = 0;
enum tcp_chrono i;
for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) {
stats[i] = tp->chrono_stat[i - 1];
if (i == tp->chrono_type)
stats[i] += tcp_jiffies32 - tp->chrono_start;
stats[i] *= USEC_PER_SEC / HZ;
total += stats[i];
}
info->tcpi_busy_time = total;
info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED];
info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED];
}
void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long rate;
u32 now;
u64 rate64;
bool slow;
memset(info, 0, sizeof(*info));
if (sk->sk_type != SOCK_STREAM)
return;
info->tcpi_state = inet_sk_state_load(sk);
rate = READ_ONCE(sk->sk_pacing_rate);
rate64 = (rate != ~0UL) ? rate : ~0ULL;
info->tcpi_pacing_rate = rate64;
rate = READ_ONCE(sk->sk_max_pacing_rate);
rate64 = (rate != ~0UL) ? rate : ~0ULL;
info->tcpi_max_pacing_rate = rate64;
info->tcpi_reordering = tp->reordering;
info->tcpi_snd_cwnd = tcp_snd_cwnd(tp);
if (info->tcpi_state == TCP_LISTEN) {
info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog);
info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog);
return;
}
slow = lock_sock_fast(sk);
info->tcpi_ca_state = icsk->icsk_ca_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
info->tcpi_backoff = icsk->icsk_backoff;
if (tp->rx_opt.tstamp_ok)
info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
if (tcp_is_sack(tp))
info->tcpi_options |= TCPI_OPT_SACK;
if (tp->rx_opt.wscale_ok) {
info->tcpi_options |= TCPI_OPT_WSCALE;
info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
}
if (tp->ecn_flags & TCP_ECN_OK)
info->tcpi_options |= TCPI_OPT_ECN;
if (tp->ecn_flags & TCP_ECN_SEEN)
info->tcpi_options |= TCPI_OPT_ECN_SEEN;
if (tp->syn_data_acked)
info->tcpi_options |= TCPI_OPT_SYN_DATA;
info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
info->tcpi_snd_mss = tp->mss_cache;
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
info->tcpi_unacked = tp->packets_out;
info->tcpi_sacked = tp->sacked_out;
info->tcpi_lost = tp->lost_out;
info->tcpi_retrans = tp->retrans_out;
now = tcp_jiffies32;
info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
info->tcpi_rtt = tp->srtt_us >> 3;
info->tcpi_rttvar = tp->mdev_us >> 2;
info->tcpi_snd_ssthresh = tp->snd_ssthresh;
info->tcpi_advmss = tp->advmss;
info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3;
info->tcpi_rcv_space = tp->rcvq_space.space;
info->tcpi_total_retrans = tp->total_retrans;
info->tcpi_bytes_acked = tp->bytes_acked;
info->tcpi_bytes_received = tp->bytes_received;
info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt);
tcp_get_info_chrono_stats(tp, info);
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = READ_ONCE(tp->segs_in);
info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in);
info->tcpi_min_rtt = tcp_min_rtt(tp);
info->tcpi_data_segs_out = tp->data_segs_out;
info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0;
rate64 = tcp_compute_delivery_rate(tp);
if (rate64)
info->tcpi_delivery_rate = rate64;
info->tcpi_delivered = tp->delivered;
info->tcpi_delivered_ce = tp->delivered_ce;
info->tcpi_bytes_sent = tp->bytes_sent;
info->tcpi_bytes_retrans = tp->bytes_retrans;
info->tcpi_dsack_dups = tp->dsack_dups;
info->tcpi_reord_seen = tp->reord_seen;
info->tcpi_rcv_ooopack = tp->rcv_ooopack;
info->tcpi_snd_wnd = tp->snd_wnd;
info->tcpi_rcv_wnd = tp->rcv_wnd;
info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash;
info->tcpi_fastopen_client_fail = tp->fastopen_client_fail;
unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(tcp_get_info);
static size_t tcp_opt_stats_get_size(void)
{
return
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u8)) +
nla_total_size(sizeof(u8)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u8)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(u16)) +
nla_total_size(sizeof(u32)) +
nla_total_size_64bit(sizeof(u64)) +
nla_total_size(sizeof(u8)) +
nla_total_size(sizeof(u32)) +
0;
}
static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return ip_hdr(skb)->ttl;
else if (skb->protocol == htons(ETH_P_IPV6))
return ipv6_hdr(skb)->hop_limit;
else
return 0;
}
struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
const struct sk_buff *orig_skb,
const struct sk_buff *ack_skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *stats;
struct tcp_info info;
unsigned long rate;
u64 rate64;
stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC);
if (!stats)
return NULL;
tcp_get_info_chrono_stats(tp, &info);
nla_put_u64_64bit(stats, TCP_NLA_BUSY,
info.tcpi_busy_time, TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED,
info.tcpi_rwnd_limited, TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED,
info.tcpi_sndbuf_limited, TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT,
tp->data_segs_out, TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS,
tp->total_retrans, TCP_NLA_PAD);
rate = READ_ONCE(sk->sk_pacing_rate);
rate64 = (rate != ~0UL) ? rate : ~0ULL;
nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD);
rate64 = tcp_compute_delivery_rate(tp);
nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD);
nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp));
nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);
nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));
nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits);
nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);
nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh);
nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered);
nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce);
nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
TCP_NLA_PAD);
nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3);
nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash);
nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT,
max_t(int, 0, tp->write_seq - tp->snd_nxt));
nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns,
TCP_NLA_PAD);
if (ack_skb)
nla_put_u8(stats, TCP_NLA_TTL,
tcp_skb_ttl_or_hop_limit(ack_skb));
nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash);
return stats;
}
int do_tcp_getsockopt(struct sock *sk, int level,
int optname, sockptr_t optval, sockptr_t optlen)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
int val, len;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
len = min_t(unsigned int, len, sizeof(int));
if (len < 0)
return -EINVAL;
switch (optname) {
case TCP_MAXSEG:
val = tp->mss_cache;
if (tp->rx_opt.user_mss &&
((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
val = tp->rx_opt.user_mss;
if (tp->repair)
val = tp->rx_opt.mss_clamp;
break;
case TCP_NODELAY:
val = !!(tp->nonagle&TCP_NAGLE_OFF);
break;
case TCP_CORK:
val = !!(tp->nonagle&TCP_NAGLE_CORK);
break;
case TCP_KEEPIDLE:
val = keepalive_time_when(tp) / HZ;
break;
case TCP_KEEPINTVL:
val = keepalive_intvl_when(tp) / HZ;
break;
case TCP_KEEPCNT:
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
val = READ_ONCE(icsk->icsk_syn_retries) ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
break;
case TCP_LINGER2:
val = READ_ONCE(tp->linger2);
if (val >= 0)
val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept);
val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ,
TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
break;
case TCP_INFO: {
struct tcp_info info;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
tcp_get_info(sk, &info);
len = min_t(unsigned int, len, sizeof(info));
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, &info, len))
return -EFAULT;
return 0;
}
case TCP_CC_INFO: {
const struct tcp_congestion_ops *ca_ops;
union tcp_cc_info info;
size_t sz = 0;
int attr;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
ca_ops = icsk->icsk_ca_ops;
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ~0U, &attr, &info);
len = min_t(unsigned int, len, sz);
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, &info, len))
return -EFAULT;
return 0;
}
case TCP_QUICKACK:
val = !inet_csk_in_pingpong_mode(sk);
break;
case TCP_CONGESTION:
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len))
return -EFAULT;
return 0;
case TCP_ULP:
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
len = min_t(unsigned int, len, TCP_ULP_NAME_MAX);
if (!icsk->icsk_ulp_ops) {
len = 0;
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
return 0;
}
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len))
return -EFAULT;
return 0;
case TCP_FASTOPEN_KEY: {
u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)];
unsigned int key_len;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
key_len = tcp_fastopen_get_cipher(net, icsk, key) *
TCP_FASTOPEN_KEY_LENGTH;
len = min_t(unsigned int, len, key_len);
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, key, len))
return -EFAULT;
return 0;
}
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
break;
case TCP_THIN_DUPACK:
val = 0;
break;
case TCP_REPAIR:
val = tp->repair;
break;
case TCP_REPAIR_QUEUE:
if (tp->repair)
val = tp->repair_queue;
else
return -EINVAL;
break;
case TCP_REPAIR_WINDOW: {
struct tcp_repair_window opt;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
if (len != sizeof(opt))
return -EINVAL;
if (!tp->repair)
return -EPERM;
opt.snd_wl1 = tp->snd_wl1;
opt.snd_wnd = tp->snd_wnd;
opt.max_window = tp->max_window;
opt.rcv_wnd = tp->rcv_wnd;
opt.rcv_wup = tp->rcv_wup;
if (copy_to_sockptr(optval, &opt, len))
return -EFAULT;
return 0;
}
case TCP_QUEUE_SEQ:
if (tp->repair_queue == TCP_SEND_QUEUE)
val = tp->write_seq;
else if (tp->repair_queue == TCP_RECV_QUEUE)
val = tp->rcv_nxt;
else
return -EINVAL;
break;
case TCP_USER_TIMEOUT:
val = READ_ONCE(icsk->icsk_user_timeout);
break;
case TCP_FASTOPEN:
val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen);
break;
case TCP_FASTOPEN_CONNECT:
val = tp->fastopen_connect;
break;
case TCP_FASTOPEN_NO_COOKIE:
val = tp->fastopen_no_cookie;
break;
case TCP_TX_DELAY:
val = READ_ONCE(tp->tcp_tx_delay);
break;
case TCP_TIMESTAMP:
val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
break;
case TCP_NOTSENT_LOWAT:
val = READ_ONCE(tp->notsent_lowat);
break;
case TCP_INQ:
val = tp->recvmsg_inq;
break;
case TCP_SAVE_SYN:
val = tp->save_syn;
break;
case TCP_SAVED_SYN: {
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
sockopt_lock_sock(sk);
if (tp->saved_syn) {
if (len < tcp_saved_syn_len(tp->saved_syn)) {
len = tcp_saved_syn_len(tp->saved_syn);
if (copy_to_sockptr(optlen, &len, sizeof(int))) {
sockopt_release_sock(sk);
return -EFAULT;
}
sockopt_release_sock(sk);
return -EINVAL;
}
len = tcp_saved_syn_len(tp->saved_syn);
if (copy_to_sockptr(optlen, &len, sizeof(int))) {
sockopt_release_sock(sk);
return -EFAULT;
}
if (copy_to_sockptr(optval, tp->saved_syn->data, len)) {
sockopt_release_sock(sk);
return -EFAULT;
}
tcp_saved_syn_free(tp);
sockopt_release_sock(sk);
} else {
sockopt_release_sock(sk);
len = 0;
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
}
return 0;
}
#ifdef CONFIG_MMU
case TCP_ZEROCOPY_RECEIVE: {
struct scm_timestamping_internal tss;
struct tcp_zerocopy_receive zc = {};
int err;
if (copy_from_sockptr(&len, optlen, sizeof(int)))
return -EFAULT;
if (len < 0 ||
len < offsetofend(struct tcp_zerocopy_receive, length))
return -EINVAL;
if (unlikely(len > sizeof(zc))) {
err = check_zeroed_sockptr(optval, sizeof(zc),
len - sizeof(zc));
if (err < 1)
return err == 0 ? -EINVAL : err;
len = sizeof(zc);
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
}
if (copy_from_sockptr(&zc, optval, len))
return -EFAULT;
if (zc.reserved)
return -EINVAL;
if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS))
return -EINVAL;
sockopt_lock_sock(sk);
err = tcp_zerocopy_receive(sk, &zc, &tss);
err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
&zc, &len, err);
sockopt_release_sock(sk);
if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
goto zerocopy_rcv_cmsg;
switch (len) {
case offsetofend(struct tcp_zerocopy_receive, msg_flags):
goto zerocopy_rcv_cmsg;
case offsetofend(struct tcp_zerocopy_receive, msg_controllen):
case offsetofend(struct tcp_zerocopy_receive, msg_control):
case offsetofend(struct tcp_zerocopy_receive, flags):
case offsetofend(struct tcp_zerocopy_receive, copybuf_len):
case offsetofend(struct tcp_zerocopy_receive, copybuf_address):
case offsetofend(struct tcp_zerocopy_receive, err):
goto zerocopy_rcv_sk_err;
case offsetofend(struct tcp_zerocopy_receive, inq):
goto zerocopy_rcv_inq;
case offsetofend(struct tcp_zerocopy_receive, length):
default:
goto zerocopy_rcv_out;
}
zerocopy_rcv_cmsg:
if (zc.msg_flags & TCP_CMSG_TS)
tcp_zc_finalize_rx_tstamp(sk, &zc, &tss);
else
zc.msg_flags = 0;
zerocopy_rcv_sk_err:
if (!err)
zc.err = sock_error(sk);
zerocopy_rcv_inq:
zc.inq = tcp_inq_hint(sk);
zerocopy_rcv_out:
if (!err && copy_to_sockptr(optval, &zc, len))
err = -EFAULT;
return err;
}
#endif
default:
return -ENOPROTOOPT;
}
if (copy_to_sockptr(optlen, &len, sizeof(int)))
return -EFAULT;
if (copy_to_sockptr(optval, &val, len))
return -EFAULT;
return 0;
}
bool tcp_bpf_bypass_getsockopt(int level, int optname)
{
if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE)
return true;
return false;
}
EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt);
int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
int __user *optlen)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname,
optval, optlen);
return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval),
USER_SOCKPTR(optlen));
}
EXPORT_SYMBOL(tcp_getsockopt);
#ifdef CONFIG_TCP_MD5SIG
static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
static DEFINE_MUTEX(tcp_md5sig_mutex);
static bool tcp_md5sig_pool_populated = false;
static void __tcp_alloc_md5sig_pool(void)
{
struct crypto_ahash *hash;
int cpu;
hash = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(hash))
return;
for_each_possible_cpu(cpu) {
void *scratch = per_cpu(tcp_md5sig_pool, cpu).scratch;
struct ahash_request *req;
if (!scratch) {
scratch = kmalloc_node(sizeof(union tcp_md5sum_block) +
sizeof(struct tcphdr),
GFP_KERNEL,
cpu_to_node(cpu));
if (!scratch)
return;
per_cpu(tcp_md5sig_pool, cpu).scratch = scratch;
}
if (per_cpu(tcp_md5sig_pool, cpu).md5_req)
continue;
req = ahash_request_alloc(hash, GFP_KERNEL);
if (!req)
return;
ahash_request_set_callback(req, 0, NULL, NULL);
per_cpu(tcp_md5sig_pool, cpu).md5_req = req;
}
smp_wmb();
WRITE_ONCE(tcp_md5sig_pool_populated, true);
}
bool tcp_alloc_md5sig_pool(void)
{
if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) {
mutex_lock(&tcp_md5sig_mutex);
if (!tcp_md5sig_pool_populated)
__tcp_alloc_md5sig_pool();
mutex_unlock(&tcp_md5sig_mutex);
}
return READ_ONCE(tcp_md5sig_pool_populated);
}
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
{
local_bh_disable();
if (READ_ONCE(tcp_md5sig_pool_populated)) {
smp_rmb();
return this_cpu_ptr(&tcp_md5sig_pool);
}
local_bh_enable();
return NULL;
}
EXPORT_SYMBOL(tcp_get_md5sig_pool);
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
const struct sk_buff *skb, unsigned int header_len)
{
struct scatterlist sg;
const struct tcphdr *tp = tcp_hdr(skb);
struct ahash_request *req = hp->md5_req;
unsigned int i;
const unsigned int head_data_len = skb_headlen(skb) > header_len ?
skb_headlen(skb) - header_len : 0;
const struct skb_shared_info *shi = skb_shinfo(skb);
struct sk_buff *frag_iter;
sg_init_table(&sg, 1);
sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len);
ahash_request_set_crypt(req, &sg, NULL, head_data_len);
if (crypto_ahash_update(req))
return 1;
for (i = 0; i < shi->nr_frags; ++i) {
const skb_frag_t *f = &shi->frags[i];
unsigned int offset = skb_frag_off(f);
struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT);
sg_set_page(&sg, page, skb_frag_size(f),
offset_in_page(offset));
ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f));
if (crypto_ahash_update(req))
return 1;
}
skb_walk_frags(skb, frag_iter)
if (tcp_md5_hash_skb_data(hp, frag_iter, 0))
return 1;
return 0;
}
EXPORT_SYMBOL(tcp_md5_hash_skb_data);
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
{
u8 keylen = READ_ONCE(key->keylen);
struct scatterlist sg;
sg_init_one(&sg, key->key, keylen);
ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
return data_race(crypto_ahash_update(hp->md5_req));
}
EXPORT_SYMBOL(tcp_md5_hash_key);
enum skb_drop_reason
tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
const void *saddr, const void *daddr,
int family, int dif, int sdif)
{
const __u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
const struct tcphdr *th = tcp_hdr(skb);
const struct tcp_sock *tp = tcp_sk(sk);
int genhash, l3index;
u8 newhash[16];
l3index = sdif ? dif : 0;
hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family);
hash_location = tcp_parse_md5sig_option(th);
if (!hash_expected && !hash_location)
return SKB_NOT_DROPPED_YET;
if (hash_expected && !hash_location) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
return SKB_DROP_REASON_TCP_MD5NOTFOUND;
}
if (!hash_expected && hash_location) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
}
if (family == AF_INET)
genhash = tcp_v4_md5_hash_skb(newhash,
hash_expected,
NULL, skb);
else
genhash = tp->af_specific->calc_md5_hash(newhash,
hash_expected,
NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
if (family == AF_INET) {
net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n",
saddr, ntohs(th->source),
daddr, ntohs(th->dest),
genhash ? " tcp_v4_calc_md5_hash failed"
: "", l3index);
} else {
net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n",
genhash ? "failed" : "mismatch",
saddr, ntohs(th->source),
daddr, ntohs(th->dest), l3index);
}
return SKB_DROP_REASON_TCP_MD5FAILURE;
}
return SKB_NOT_DROPPED_YET;
}
EXPORT_SYMBOL(tcp_inbound_md5_hash);
#endif
void tcp_done(struct sock *sk)
{
struct request_sock *req;
req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);
if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
tcp_set_state(sk, TCP_CLOSE);
tcp_clear_xmit_timers(sk);
if (req)
reqsk_fastopen_remove(sk, req, false);
WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
else
inet_csk_destroy_sock(sk);
}
EXPORT_SYMBOL_GPL(tcp_done);
int tcp_abort(struct sock *sk, int err)
{
int state = inet_sk_state_load(sk);
if (state == TCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
local_bh_disable();
inet_csk_reqsk_queue_drop(req->rsk_listener, req);
local_bh_enable();
return 0;
}
if (state == TCP_TIME_WAIT) {
struct inet_timewait_sock *tw = inet_twsk(sk);
refcount_inc(&tw->tw_refcnt);
local_bh_disable();
inet_twsk_deschedule_put(tw);
local_bh_enable();
return 0;
}
if (!has_current_bpf_ctx())
lock_sock(sk);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
inet_csk_listen_stop(sk);
}
local_bh_disable();
bh_lock_sock(sk);
if (!sock_flag(sk, SOCK_DEAD)) {
WRITE_ONCE(sk->sk_err, err);
smp_wmb();
sk_error_report(sk);
if (tcp_need_reset(sk->sk_state))
tcp_send_active_reset(sk, GFP_ATOMIC);
tcp_done(sk);
}
bh_unlock_sock(sk);
local_bh_enable();
tcp_write_queue_purge(sk);
if (!has_current_bpf_ctx())
release_sock(sk);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_abort);
extern struct tcp_congestion_ops tcp_reno;
static __initdata unsigned long thash_entries;
static int __init set_thash_entries(char *str)
{
ssize_t ret;
if (!str)
return 0;
ret = kstrtoul(str, 0, &thash_entries);
if (ret)
return 0;
return 1;
}
__setup("thash_entries=", set_thash_entries);
static void __init tcp_init_mem(void)
{
unsigned long limit = nr_free_buffer_pages() / 16;
limit = max(limit, 128UL);
sysctl_tcp_mem[0] = limit / 4 * 3;
sysctl_tcp_mem[1] = limit;
sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
}
void __init tcp_init(void)
{
int max_rshare, max_wshare, cnt;
unsigned long limit;
unsigned int i;
BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
sizeof_field(struct sk_buff, cb));
percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE);
mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD);
inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash",
thash_entries, 21,
0, 64 * 1024);
tcp_hashinfo.bind_bucket_cachep =
kmem_cache_create("tcp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT,
NULL);
tcp_hashinfo.bind2_bucket_cachep =
kmem_cache_create("tcp_bind2_bucket",
sizeof(struct inet_bind2_bucket), 0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT,
NULL);
tcp_hashinfo.ehash =
alloc_large_system_hash("TCP established",
sizeof(struct inet_ehash_bucket),
thash_entries,
17,
0,
NULL,
&tcp_hashinfo.ehash_mask,
0,
thash_entries ? 0 : 512 * 1024);
for (i = 0; i <= tcp_hashinfo.ehash_mask; i++)
INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
if (inet_ehash_locks_alloc(&tcp_hashinfo))
panic("TCP: failed to alloc ehash_locks");
tcp_hashinfo.bhash =
alloc_large_system_hash("TCP bind",
2 * sizeof(struct inet_bind_hashbucket),
tcp_hashinfo.ehash_mask + 1,
17,
0,
&tcp_hashinfo.bhash_size,
NULL,
0,
64 * 1024);
tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size;
for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
spin_lock_init(&tcp_hashinfo.bhash[i].lock);
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
spin_lock_init(&tcp_hashinfo.bhash2[i].lock);
INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain);
}
tcp_hashinfo.pernet = false;
cnt = tcp_hashinfo.ehash_mask + 1;
sysctl_tcp_max_orphans = cnt / 2;
tcp_init_mem();
limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
max_wshare = min(4UL*1024*1024, limit);
max_rshare = min(6UL*1024*1024, limit);
init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE;
init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024;
init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE;
init_net.ipv4.sysctl_tcp_rmem[1] = 131072;
init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare);
pr_info("Hash tables configured (established %u bind %u)\n",
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
tcp_v4_init();
tcp_metrics_init();
BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
tcp_tasklet_init();
mptcp_init();
}