tcp: add tcp_tx_skb_cache sysctl

Feng Tang reported a performance regression after introduction
of per TCP socket tx/rx caches, for TCP over loopback (netperf)

There is high chance the regression is caused by a change on
how well the 32 KB per-thread page (current->task_frag) can
be recycled, and lack of pcp caches for order-3 pages.

I could not reproduce the regression myself, cpus all being
spinning on the mm spinlocks for page allocs/freeing, regardless
of enabling or disabling the per tcp socket caches.

It seems best to disable the feature by default, and let
admins enabling it.

MM layer either needs to provide scalable order-3 pages
allocations, or could attempt a trylock on zone->lock if
the caller only attempts to get a high-order page and is
able to fallback to order-0 ones in case of pressure.

Tests run on a 56 cores host (112 hyper threads)

-	35.49%	netperf 		 [kernel.vmlinux]	  [k] queued_spin_lock_slowpath
   - 35.49% queued_spin_lock_slowpath
	  - 18.18% get_page_from_freelist
		 - __alloc_pages_nodemask
			- 18.18% alloc_pages_current
				 skb_page_frag_refill
				 sk_page_frag_refill
				 tcp_sendmsg_locked
				 tcp_sendmsg
				 inet_sendmsg
				 sock_sendmsg
				 __sys_sendto
				 __x64_sys_sendto
				 do_syscall_64
				 entry_SYSCALL_64_after_hwframe
				 __libc_send
	  + 17.31% __free_pages_ok
+	31.43%	swapper 		 [kernel.vmlinux]	  [k] intel_idle
+	 9.12%	netperf 		 [kernel.vmlinux]	  [k] copy_user_enhanced_fast_string
+	 6.53%	netserver		 [kernel.vmlinux]	  [k] copy_user_enhanced_fast_string
+	 0.69%	netserver		 [kernel.vmlinux]	  [k] queued_spin_lock_slowpath
+	 0.68%	netperf 		 [kernel.vmlinux]	  [k] skb_release_data
+	 0.52%	netperf 		 [kernel.vmlinux]	  [k] tcp_sendmsg_locked
	 0.46%	netperf 		 [kernel.vmlinux]	  [k] _raw_spin_lock_irqsave

Fixes: 472c2e07ee ("tcp: add one skb cache for tx")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sock.h

@@ -1463,12 +1463,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 		__sk_mem_reclaim(sk, 1 << 20);
 }
 
+DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	sk->sk_wmem_queued -= skb->truesize;
 	sk_mem_uncharge(sk, skb->truesize);
-	if (!sk->sk_tx_skb_cache && !skb_cloned(skb)) {
+	if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
+	    !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
 		skb_zcopy_clear(skb, true);
 		sk->sk_tx_skb_cache = skb;
 		return;

net/ipv4/sysctl_net_ipv4.c

@@ -54,6 +54,8 @@ static int one_day_secs = 24 * 3600;
 DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 EXPORT_SYMBOL(tcp_rx_skb_cache_key);
 
+DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
+
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
 
@@ -568,6 +570,12 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_do_static_key,
 	},
+	{
+		.procname	= "tcp_tx_skb_cache",
+		.data		= &tcp_tx_skb_cache_key.key,
+		.mode		= 0644,
+		.proc_handler	= proc_do_static_key,
+	},
 	{ }
 };