Commit 35fc07ae authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-add-three-static-keys' 



Eric Dumazet says:

====================
tcp: add three static keys

Recent addition of per TCP socket rx/tx cache brought
regressions for some workloads, as reported by Feng Tang.

It seems better to make them opt-in, before we adopt better
heuristics.

The last patch adds high_order_alloc_disable sysctl
to ask TCP sendmsg() to exclusively use order-0 allocations,
as mm layer has specific optimizations.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 9a33629b ce27ec60

Documentation/networking/ip-sysctl.txt

+8 −0
Original line number Diff line number Diff line
@@ -772,6 +772,14 @@ tcp_challenge_ack_limit - INTEGER 
	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)

	Default: 100



tcp_rx_skb_cache - BOOLEAN

	Controls a per TCP socket cache of one skb, that might help

	performance of some workloads. This might be dangerous

	on systems with a lot of TCP sockets, since it increases

	memory usage.



	Default: 0 (disabled)



UDP variables:



udp_l3mdev_accept - BOOLEAN

include/linux/bpf.h

+0 −1
Original line number Diff line number Diff line
@@ -600,7 +600,6 @@ void bpf_map_area_free(void *base); 
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);



extern int sysctl_unprivileged_bpf_disabled;

extern int sysctl_bpf_stats_enabled;



int bpf_map_new_fd(struct bpf_map *map, int flags);

int bpf_prog_new_fd(struct bpf_prog *prog);

include/linux/sysctl.h

+3 −0
Original line number Diff line number Diff line
@@ -63,6 +63,9 @@ extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, 
				      void __user *, size_t *, loff_t *);

extern int proc_do_large_bitmap(struct ctl_table *, int,

				void __user *, size_t *, loff_t *);

extern int proc_do_static_key(struct ctl_table *table, int write,

			      void __user *buffer, size_t *lenp,

			      loff_t *ppos);



/*

 * Register a set of sysctl names by calling register_sysctl_table

include/net/sock.h

+7 −5
Original line number Diff line number Diff line
@@ -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;
@@ -2433,13 +2435,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) 
 * This routine must be called with interrupts disabled or with the socket

 * locked so that the sk_buff queue operation is ok.

*/

DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);

static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)

{

	__skb_unlink(skb, &sk->sk_receive_queue);

	if (

#ifdef CONFIG_RPS

	    !static_branch_unlikely(&rps_needed) &&

#endif

	if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&

	    !sk->sk_rx_skb_cache) {

		sk->sk_rx_skb_cache = skb;

		skb_orphan(skb);
@@ -2534,6 +2534,8 @@ extern int sysctl_optmem_max; 
extern __u32 sysctl_wmem_default;

extern __u32 sysctl_rmem_default;



DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);



static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)

{

	/* Does this proto have per netns sysctl_wmem ? */

kernel/bpf/core.c

+0 −1
Original line number Diff line number Diff line
@@ -2097,7 +2097,6 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, 


DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);

EXPORT_SYMBOL(bpf_stats_enabled_key);

int sysctl_bpf_stats_enabled __read_mostly;



/* All definitions of tracepoints related to BPF. */

#define CREATE_TRACE_POINTS

CRA Git | Maintained and supported by SUSTech CRA and CCSE