From 19757cebf0c5016a1f36f7fe9810a9f0b33c0832 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Oct 2021 06:41:26 -0700 Subject: tcp: switch orphan_count to bare per-cpu counters Use of percpu_counter structure to track count of orphaned sockets is causing problems on modern hosts with 256 cpus or more. Stefan Bach reported a serious spinlock contention in real workloads, that I was able to reproduce with a netfilter rule dropping incoming FIN packets. 53.56% server [kernel.kallsyms] [k] queued_spin_lock_slowpath | ---queued_spin_lock_slowpath | --53.51%--_raw_spin_lock_irqsave | --53.51%--__percpu_counter_sum tcp_check_oom | |--39.03%--__tcp_close | tcp_close | inet_release | inet6_release | sock_close | __fput | ____fput | task_work_run | exit_to_usermode_loop | do_syscall_64 | entry_SYSCALL_64_after_hwframe | __GI___libc_close | --14.48%--tcp_out_of_resources tcp_write_timeout tcp_retransmit_timer tcp_write_timer_handler tcp_write_timer call_timer_fn expire_timers __run_timers run_timer_softirq __softirqentry_text_start As explained in commit cf86a086a180 ("net/dst: use a smaller percpu_counter batch for dst entries accounting"), default batch size is too big for the default value of tcp_max_orphans (262144). But even if we reduce batch sizes, there would still be cases where the estimated count of orphans is beyond the limit, and where tcp_too_many_orphans() has to call the expensive percpu_counter_sum_positive(). One solution is to use plain per-cpu counters, and have a timer to periodically refresh this cache. Updating this cache every 100ms seems about right, tcp pressure state is not radically changing over shorter periods. percpu_counter was nice 15 years ago while hosts had less than 16 cpus, not anymore by current standards. v2: Fix the build issue for CONFIG_CRYPTO_DEV_CHELSIO_TLS=m, reported by kernel test robot Remove unused socket argument from tcp_too_many_orphans() Fixes: dd24c00191d5 ("net: Use a percpu_counter for orphan_count") Signed-off-by: Eric Dumazet Reported-by: Stefan Bach Cc: Neal Cardwell Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/chelsio') diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index bcad69c48074..4af5561cbfc5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -870,7 +870,7 @@ static void do_abort_syn_rcv(struct sock *child, struct sock *parent) * created only after 3 way handshake is done. */ sock_orphan(child); - percpu_counter_inc((child)->sk_prot->orphan_count); + INC_ORPHAN_COUNT(child); chtls_release_resources(child); chtls_conn_done(child); } else { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h index b1161bdeda4d..f61ca657601c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h @@ -95,7 +95,7 @@ struct deferred_skb_cb { #define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok) #define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok) #define SACK_OK(tp) ((tp)->rx_opt.sack_ok) -#define INC_ORPHAN_COUNT(sk) percpu_counter_inc((sk)->sk_prot->orphan_count) +#define INC_ORPHAN_COUNT(sk) this_cpu_inc(*(sk)->sk_prot->orphan_count) /* TLS SKB */ #define skb_ulp_tls_inline(skb) (ULP_SKB_CB(skb)->ulp.tls.ofld) -- cgit