Update Linux to v5.10.157
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 19ef457..eefd032 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -82,6 +82,7 @@
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
tcp_skb_pcount(skb));
+ tcp_check_space(sk);
}
/* SND.NXT, if window was not shrunk or the amount of shrunk was less than one
@@ -166,16 +167,13 @@
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
- /* If this is the first data packet sent in response to the
- * previous received data,
- * and it is a reply for ato after last received packet,
- * increase pingpong count.
- */
- if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
- (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- inet_csk_inc_pingpong_cnt(sk);
-
tp->lsndtime = now;
+
+ /* If it is a reply for ato after last received
+ * packet, enter pingpong mode.
+ */
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
@@ -240,8 +238,8 @@
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
- space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
- space = max_t(u32, space, sysctl_rmem_max);
+ 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);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
0, TCP_MAX_WSCALE);
@@ -788,18 +786,18 @@
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
opts->options |= OPTION_TS;
opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -1719,7 +1717,8 @@
mss_now -= icsk->icsk_ext_hdr_len;
/* Then reserve room for full set of TCP options and 8 bytes of data */
- mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
+ mss_now = max(mss_now,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss));
return mss_now;
}
@@ -1762,10 +1761,10 @@
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
- icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
+ icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
icsk->icsk_af_ops->net_header_len;
- icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
+ icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss));
icsk->icsk_mtup.probe_size = 0;
if (icsk->icsk_mtup.enabled)
icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
@@ -1877,15 +1876,20 @@
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
- /* Track the maximum number of outstanding packets in each
- * window, and remember whether we were cwnd-limited then.
+ /* Track the strongest available signal of the degree to which the cwnd
+ * is fully utilized. If cwnd-limited then remember that fact for the
+ * current window. If not cwnd-limited then track the maximum number of
+ * outstanding packets in the current window. (If cwnd-limited then we
+ * chose to not update tp->max_packets_out to avoid an extra else
+ * clause with no functional impact.)
*/
- if (!before(tp->snd_una, tp->max_packets_seq) ||
- tp->packets_out > tp->max_packets_out ||
- is_cwnd_limited) {
- tp->max_packets_out = tp->packets_out;
- tp->max_packets_seq = tp->snd_nxt;
+ if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
+ is_cwnd_limited ||
+ (!tp->is_cwnd_limited &&
+ tp->packets_out > tp->max_packets_out)) {
tp->is_cwnd_limited = is_cwnd_limited;
+ tp->max_packets_out = tp->packets_out;
+ tp->cwnd_usage_seq = tp->snd_nxt;
}
if (tcp_is_cwnd_limited(sk)) {
@@ -1897,7 +1901,7 @@
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
- if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
(s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
!ca_ops->cong_control)
tcp_cwnd_application_limited(sk);
@@ -1985,7 +1989,7 @@
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2276,7 +2280,7 @@
u32 interval;
s32 delta;
- interval = net->ipv4.sysctl_tcp_probe_interval;
+ interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
if (unlikely(delta >= interval * HZ)) {
int mss = tcp_current_mss(sk);
@@ -2358,7 +2362,7 @@
* probing process by not resetting search range to its orignal.
*/
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
- interval < net->ipv4.sysctl_tcp_probe_threshold) {
+ interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
/* Check whether enough time has elaplased for
* another round of probing.
*/
@@ -2500,7 +2504,7 @@
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
- sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
@@ -2733,7 +2737,7 @@
if (rcu_access_pointer(tp->fastopen_rsk))
return false;
- early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
+ early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
/* Schedule a loss probe in 2*RTT for SACK capable connections
* not in loss recovery, that are either limited by cwnd or application.
*/
@@ -3098,7 +3102,7 @@
struct sk_buff *skb = to, *tmp;
bool first = true;
- if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
return;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
return;
@@ -3138,7 +3142,7 @@
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cur_mss;
int diff, len, err;
-
+ int avail_wnd;
/* Inconclusive MTU probe */
if (icsk->icsk_mtup.probe_size)
@@ -3168,17 +3172,25 @@
return -EHOSTUNREACH; /* Routing failure or similar. */
cur_mss = tcp_current_mss(sk);
+ avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
- * our retransmit serves as a zero window probe.
+ * our retransmit of one segment serves as a zero window probe.
*/
- if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
- TCP_SKB_CB(skb)->seq != tp->snd_una)
- return -EAGAIN;
+ if (avail_wnd <= 0) {
+ if (TCP_SKB_CB(skb)->seq != tp->snd_una)
+ return -EAGAIN;
+ avail_wnd = cur_mss;
+ }
len = cur_mss * segs;
+ if (len > avail_wnd) {
+ len = rounddown(avail_wnd, cur_mss);
+ if (!len)
+ len = avail_wnd;
+ }
if (skb->len > len) {
if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
cur_mss, GFP_ATOMIC))
@@ -3192,8 +3204,9 @@
diff -= tcp_skb_pcount(skb);
if (diff)
tcp_adjust_pcount(sk, skb, diff);
- if (skb->len < cur_mss)
- tcp_retrans_try_collapse(sk, skb, cur_mss);
+ avail_wnd = min_t(int, avail_wnd, cur_mss);
+ if (skb->len < avail_wnd)
+ tcp_retrans_try_collapse(sk, skb, avail_wnd);
}
/* RFC3168, section 6.1.1.1. ECN fallback */
@@ -3364,11 +3377,12 @@
*/
void sk_forced_mem_schedule(struct sock *sk, int size)
{
- int amt;
+ int delta, amt;
- if (size <= sk->sk_forward_alloc)
+ delta = size - sk->sk_forward_alloc;
+ if (delta <= 0)
return;
- amt = sk_mem_pages(size);
+ amt = sk_mem_pages(delta);
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
sk_memory_allocated_add(sk, amt);
@@ -3646,7 +3660,7 @@
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr);
- if (sock_net(sk)->ipv4.sysctl_tcp_timestamps)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
@@ -3682,7 +3696,7 @@
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- sock_net(sk)->ipv4.sysctl_tcp_window_scaling,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling),
&rcv_wscale,
rcv_wnd);
@@ -3733,6 +3747,7 @@
*/
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;
@@ -3747,8 +3762,10 @@
* private TCP options. The cost is reduced data space in SYN :(
*/
tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+ /* Sync mss_cache after updating the mss_clamp */
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
- space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+ space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
space = min_t(size_t, space, fo->size);
@@ -4087,7 +4104,7 @@
icsk->icsk_probes_out++;
if (err <= 0) {
- if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
+ if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
icsk->icsk_backoff++;
timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
} else {
@@ -4111,8 +4128,8 @@
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);
+ 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++;
trace_tcp_retransmit_synack(sk, req);