Taking socket spinlock in tcp_get_info() can deadlock, as
inet_diag_dump_icsk() holds the &hashinfo->ehash_locks[i],
while packet processing can use the reverse locking order.
We could avoid this locking for TCP_LISTEN states, but lockdep would
certainly get confused as all TCP sockets share same lockdep classes.
[ 523.722504] ======================================================
[ 523.728706] [ INFO: possible circular locking dependency detected ]
[ 523.734990] 4.1.0-dbg-DEV #1676 Not tainted
[ 523.739202] -------------------------------------------------------
[ 523.745474] ss/18032 is trying to acquire lock:
[ 523.750002] (slock-AF_INET){+.-...}, at: [<
ffffffff81669d44>] tcp_get_info+0x2c4/0x360
[ 523.758129]
[ 523.758129] but task is already holding lock:
[ 523.763968] (&(&hashinfo->ehash_locks[i])->rlock){+.-...}, at: [<
ffffffff816bcb75>] inet_diag_dump_icsk+0x1d5/0x6c0
[ 523.774661]
[ 523.774661] which lock already depends on the new lock.
[ 523.774661]
[ 523.782850]
[ 523.782850] the existing dependency chain (in reverse order) is:
[ 523.790326]
-> #1 (&(&hashinfo->ehash_locks[i])->rlock){+.-...}:
[ 523.796599] [<
ffffffff811126bb>] lock_acquire+0xbb/0x270
[ 523.802565] [<
ffffffff816f5868>] _raw_spin_lock+0x38/0x50
[ 523.808628] [<
ffffffff81665af8>] __inet_hash_nolisten+0x78/0x110
[ 523.815273] [<
ffffffff816819db>] tcp_v4_syn_recv_sock+0x24b/0x350
[ 523.822067] [<
ffffffff81684d41>] tcp_check_req+0x3c1/0x500
[ 523.828199] [<
ffffffff81682d09>] tcp_v4_do_rcv+0x239/0x3d0
[ 523.834331] [<
ffffffff816842fe>] tcp_v4_rcv+0xa8e/0xc10
[ 523.840202] [<
ffffffff81658fa3>] ip_local_deliver_finish+0x133/0x3e0
[ 523.847214] [<
ffffffff81659a9a>] ip_local_deliver+0xaa/0xc0
[ 523.853440] [<
ffffffff816593b8>] ip_rcv_finish+0x168/0x5c0
[ 523.859624] [<
ffffffff81659db7>] ip_rcv+0x307/0x420
Lets use u64_sync infrastructure instead. As a bonus, 64bit
arches get optimized, as these are nop for them.
Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* sum(delta(snd_una)), or how many bytes
* were acked.
*/
+ struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */
+
u32 snd_una; /* First byte we want an ack for */
u32 snd_sml; /* Last byte of the most recently transmitted small packet */
u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
+ u64_stats_init(&tp->syncp);
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
+ unsigned int start;
u32 rate;
memset(info, 0, sizeof(*info));
rate = READ_ONCE(sk->sk_max_pacing_rate);
info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
- spin_lock_bh(&sk->sk_lock.slock);
- info->tcpi_bytes_acked = tp->bytes_acked;
- info->tcpi_bytes_received = tp->bytes_received;
- spin_unlock_bh(&sk->sk_lock.slock);
+ do {
+ start = u64_stats_fetch_begin_irq(&tp->syncp);
+ info->tcpi_bytes_acked = tp->bytes_acked;
+ info->tcpi_bytes_received = tp->bytes_received;
+ } while (u64_stats_fetch_retry_irq(&tp->syncp, start));
}
EXPORT_SYMBOL_GPL(tcp_get_info);
skb_set_owner_r(skb2, child);
__skb_queue_tail(&child->sk_receive_queue, skb2);
tp->syn_data_acked = 1;
+
+ /* u64_stats_update_begin(&tp->syncp) not needed here,
+ * as we certainly are not changing upper 32bit value (0)
+ */
tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
} else {
end_seq = TCP_SKB_CB(skb)->seq + 1;
{
u32 delta = ack - tp->snd_una;
+ u64_stats_update_begin(&tp->syncp);
tp->bytes_acked += delta;
+ u64_stats_update_end(&tp->syncp);
tp->snd_una = ack;
}
{
u32 delta = seq - tp->rcv_nxt;
+ u64_stats_update_begin(&tp->syncp);
tp->bytes_received += delta;
+ u64_stats_update_end(&tp->syncp);
tp->rcv_nxt = seq;
}