From e472f88891abbc535a5e16a68a104073985f6061 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 15 Jan 2024 12:55:13 -0800 Subject: bpf: tcp: Support arbitrary SYN Cookie. This patch adds a new kfunc available at TC hook to support arbitrary SYN Cookie. The basic usage is as follows: struct bpf_tcp_req_attrs attrs = { .mss = mss, .wscale_ok = wscale_ok, .rcv_wscale = rcv_wscale, /* Server's WScale < 15 */ .snd_wscale = snd_wscale, /* Client's WScale < 15 */ .tstamp_ok = tstamp_ok, .rcv_tsval = tsval, .rcv_tsecr = tsecr, /* Server's Initial TSval */ .usec_ts_ok = usec_ts_ok, .sack_ok = sack_ok, .ecn_ok = ecn_ok, } skc = bpf_skc_lookup_tcp(...); sk = (struct sock *)bpf_skc_to_tcp_sock(skc); bpf_sk_assign_tcp_reqsk(skb, sk, attrs, sizeof(attrs)); bpf_sk_release(skc); bpf_sk_assign_tcp_reqsk() takes skb, a listener sk, and struct bpf_tcp_req_attrs and allocates reqsk and configures it. Then, bpf_sk_assign_tcp_reqsk() links reqsk with skb and the listener. The notable thing here is that we do not hold refcnt for both reqsk and listener. To differentiate that, we mark reqsk->syncookie, which is only used in TX for now. So, if reqsk->syncookie is 1 in RX, it means that the reqsk is allocated by kfunc. When skb is freed, sock_pfree() checks if reqsk->syncookie is 1, and in that case, we set NULL to reqsk->rsk_listener before calling reqsk_free() as reqsk does not hold a refcnt of the listener. When the TCP stack looks up a socket from the skb, we steal the listener from the reqsk in skb_steal_sock() and create a full sk in cookie_v[46]_check(). The refcnt of reqsk will finally be set to 1 in tcp_get_cookie_sock() after creating a full sk. Note that we can extend struct bpf_tcp_req_attrs in the future when we add a new attribute that is determined in 3WHS. Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240115205514.68364-6-kuniyu@amazon.com Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- net/core/sock.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 158dbdebce6a..147fb2656e6b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2582,8 +2582,18 @@ EXPORT_SYMBOL(sock_efree); #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { - if (sk_is_refcounted(skb->sk)) - sock_gen_put(skb->sk); + struct sock *sk = skb->sk; + + if (!sk_is_refcounted(sk)) + return; + + if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { + inet_reqsk(sk)->rsk_listener = NULL; + reqsk_free(inet_reqsk(sk)); + return; + } + + sock_gen_put(sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ -- cgit v1.2.3 From 5d4cc87414c5d11345c4b11d61377d351b5c28a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 16 Feb 2024 16:20:06 +0000 Subject: net: reorganize "struct sock" fields Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize struct sock for better data locality") Since then, many changes have been done. Before SO_PEEK_OFF support is added to TCP, we need to move sk_peek_off to a better location. It is time to make another pass, and add six groups, without explicit alignment. - sock_write_rx (following sk_refcnt) read-write fields in rx path. - sock_read_rx read-mostly fields in rx path. - sock_read_rxtx read-mostly fields in both rx and tx paths. - sock_write_rxtx read-write fields in both rx and tx paths. - sock_write_tx read-write fields in tx paths. - sock_read_tx read-mostly fields in tx paths. Results on TCP_RR benchmarks seem to show a gain (4 to 5 %). It is possible UDP needs a change, because sk_peek_off shares a cache line with sk_receive_queue. If this the case, we can exchange roles of sk->sk_receive and up->reader_queue queues. After this change, we have the following layout: struct sock { struct sock_common __sk_common; /* 0 0x88 */ /* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */ __u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */ atomic_t sk_drops; /* 0x88 0x4 */ __s32 sk_peek_off; /* 0x8c 0x4 */ struct sk_buff_head sk_error_queue; /* 0x90 0x18 */ struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct { atomic_t rmem_alloc; /* 0xc0 0x4 */ int len; /* 0xc4 0x4 */ struct sk_buff * head; /* 0xc8 0x8 */ struct sk_buff * tail; /* 0xd0 0x8 */ } sk_backlog; /* 0xc0 0x18 */ struct { atomic_t rmem_alloc; /* 0 0x4 */ int len; /* 0x4 0x4 */ struct sk_buff * head; /* 0x8 0x8 */ struct sk_buff * tail; /* 0x10 0x8 */ /* size: 24, cachelines: 1, members: 4 */ /* last cacheline: 24 bytes */ }; __u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */ __u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */ rcu * sk_rx_dst; /* 0xd8 0x8 */ int sk_rx_dst_ifindex; /* 0xe0 0x4 */ u32 sk_rx_dst_cookie; /* 0xe4 0x4 */ unsigned int sk_ll_usec; /* 0xe8 0x4 */ unsigned int sk_napi_id; /* 0xec 0x4 */ u16 sk_busy_poll_budget; /* 0xf0 0x2 */ u8 sk_prefer_busy_poll; /* 0xf2 0x1 */ u8 sk_userlocks; /* 0xf3 0x1 */ int sk_rcvbuf; /* 0xf4 0x4 */ rcu * sk_filter; /* 0xf8 0x8 */ /* --- cacheline 4 boundary (256 bytes) --- */ union { rcu * sk_wq; /* 0x100 0x8 */ struct socket_wq * sk_wq_raw; /* 0x100 0x8 */ }; /* 0x100 0x8 */ union { rcu * sk_wq; /* 0 0x8 */ struct socket_wq * sk_wq_raw; /* 0 0x8 */ }; void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */ long sk_rcvtimeo; /* 0x110 0x8 */ int sk_rcvlowat; /* 0x118 0x4 */ __u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */ __u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */ int sk_err; /* 0x11c 0x4 */ struct socket * sk_socket; /* 0x120 0x8 */ struct mem_cgroup * sk_memcg; /* 0x128 0x8 */ rcu * sk_policy[2]; /* 0x130 0x10 */ /* --- cacheline 5 boundary (320 bytes) --- */ __u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */ __u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */ socket_lock_t sk_lock; /* 0x140 0x20 */ u32 sk_reserved_mem; /* 0x160 0x4 */ int sk_forward_alloc; /* 0x164 0x4 */ u32 sk_tsflags; /* 0x168 0x4 */ __u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */ __u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */ int sk_write_pending; /* 0x16c 0x4 */ atomic_t sk_omem_alloc; /* 0x170 0x4 */ int sk_sndbuf; /* 0x174 0x4 */ int sk_wmem_queued; /* 0x178 0x4 */ refcount_t sk_wmem_alloc; /* 0x17c 0x4 */ /* --- cacheline 6 boundary (384 bytes) --- */ unsigned long sk_tsq_flags; /* 0x180 0x8 */ union { struct sk_buff * sk_send_head; /* 0x188 0x8 */ struct rb_root tcp_rtx_queue; /* 0x188 0x8 */ }; /* 0x188 0x8 */ union { struct sk_buff * sk_send_head; /* 0 0x8 */ struct rb_root tcp_rtx_queue; /* 0 0x8 */ }; struct sk_buff_head sk_write_queue; /* 0x190 0x18 */ u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */ u32 sk_pacing_status; /* 0x1ac 0x4 */ struct page_frag sk_frag; /* 0x1b0 0x10 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct timer_list sk_timer; /* 0x1c0 0x28 */ /* XXX last struct has 4 bytes of padding */ unsigned long sk_pacing_rate; /* 0x1e8 0x8 */ atomic_t sk_zckey; /* 0x1f0 0x4 */ atomic_t sk_tskey; /* 0x1f4 0x4 */ __u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */ __u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */ unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */ /* --- cacheline 8 boundary (512 bytes) --- */ long sk_sndtimeo; /* 0x200 0x8 */ u32 sk_priority; /* 0x208 0x4 */ u32 sk_mark; /* 0x20c 0x4 */ rcu * sk_dst_cache; /* 0x210 0x8 */ netdev_features_t sk_route_caps; /* 0x218 0x8 */ u16 sk_gso_type; /* 0x220 0x2 */ u16 sk_gso_max_segs; /* 0x222 0x2 */ unsigned int sk_gso_max_size; /* 0x224 0x4 */ gfp_t sk_allocation; /* 0x228 0x4 */ u32 sk_txhash; /* 0x22c 0x4 */ u8 sk_pacing_shift; /* 0x230 0x1 */ bool sk_use_task_frag; /* 0x231 0x1 */ __u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */ u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */ u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */ u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */ u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */ /* XXX 4 bits hole, try to pack */ u8 sk_shutdown; /* 0x233 0x1 */ u16 sk_type; /* 0x234 0x2 */ u16 sk_protocol; /* 0x236 0x2 */ unsigned long sk_lingertime; /* 0x238 0x8 */ /* --- cacheline 9 boundary (576 bytes) --- */ struct proto * sk_prot_creator; /* 0x240 0x8 */ rwlock_t sk_callback_lock; /* 0x248 0x8 */ int sk_err_soft; /* 0x250 0x4 */ u32 sk_ack_backlog; /* 0x254 0x4 */ u32 sk_max_ack_backlog; /* 0x258 0x4 */ kuid_t sk_uid; /* 0x25c 0x4 */ spinlock_t sk_peer_lock; /* 0x260 0x4 */ int sk_bind_phc; /* 0x264 0x4 */ struct pid * sk_peer_pid; /* 0x268 0x8 */ const struct cred * sk_peer_cred; /* 0x270 0x8 */ ktime_t sk_stamp; /* 0x278 0x8 */ /* --- cacheline 10 boundary (640 bytes) --- */ int sk_disconnects; /* 0x280 0x4 */ u8 sk_txrehash; /* 0x284 0x1 */ u8 sk_clockid; /* 0x285 0x1 */ u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */ u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */ u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */ /* XXX 1 byte hole, try to pack */ void * sk_user_data; /* 0x288 0x8 */ void * sk_security; /* 0x290 0x8 */ struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */ void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */ void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */ void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */ int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */ /* --- cacheline 11 boundary (704 bytes) --- */ void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */ rcu * sk_reuseport_cb; /* 0x2c8 0x8 */ rcu * sk_bpf_storage; /* 0x2d0 0x8 */ struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */ netns_tracker ns_tracker; /* 0x2e8 0x8 */ /* size: 752, cachelines: 12, members: 105 */ /* sum members: 749, holes: 1, sum holes: 1 */ /* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */ /* paddings: 1, sum paddings: 4 */ /* forced alignments: 1 */ /* last cacheline: 48 bytes */ }; Signed-off-by: Eric Dumazet Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com Signed-off-by: Paolo Abeni --- include/net/sock.h | 108 ++++++++++++++++++++++++++++++----------------------- net/core/sock.c | 62 ++++++++++++++++++++++++++++++ 2 files changed, 123 insertions(+), 47 deletions(-) (limited to 'net/core/sock.c') diff --git a/include/net/sock.h b/include/net/sock.h index a9d99a9c583f..796a902cf4c1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -378,14 +378,10 @@ struct sock { #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash - /* early demux fields */ - struct dst_entry __rcu *sk_rx_dst; - int sk_rx_dst_ifindex; - u32 sk_rx_dst_cookie; + __cacheline_group_begin(sock_write_rx); - socket_lock_t sk_lock; atomic_t sk_drops; - int sk_rcvlowat; + __s32 sk_peek_off; struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* @@ -402,18 +398,24 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; - #define sk_rmem_alloc sk_backlog.rmem_alloc - int sk_forward_alloc; - u32 sk_reserved_mem; + __cacheline_group_end(sock_write_rx); + + __cacheline_group_begin(sock_read_rx); + /* early demux fields */ + struct dst_entry __rcu *sk_rx_dst; + int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; - /* ===== mostly read cache line ===== */ unsigned int sk_napi_id; + u16 sk_busy_poll_budget; + u8 sk_prefer_busy_poll; #endif + u8 sk_userlocks; int sk_rcvbuf; - int sk_disconnects; struct sk_filter __rcu *sk_filter; union { @@ -422,15 +424,33 @@ struct sock { struct socket_wq *sk_wq_raw; /* public: */ }; + + void (*sk_data_ready)(struct sock *sk); + long sk_rcvtimeo; + int sk_rcvlowat; + __cacheline_group_end(sock_read_rx); + + __cacheline_group_begin(sock_read_rxtx); + int sk_err; + struct socket *sk_socket; + struct mem_cgroup *sk_memcg; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif + __cacheline_group_end(sock_read_rxtx); - struct dst_entry __rcu *sk_dst_cache; + __cacheline_group_begin(sock_write_rxtx); + socket_lock_t sk_lock; + u32 sk_reserved_mem; + int sk_forward_alloc; + u32 sk_tsflags; + __cacheline_group_end(sock_write_rxtx); + + __cacheline_group_begin(sock_write_tx); + int sk_write_pending; atomic_t sk_omem_alloc; int sk_sndbuf; - /* ===== cache line for TX ===== */ int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; @@ -439,22 +459,36 @@ struct sock { struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; - __s32 sk_peek_off; - int sk_write_pending; - __u32 sk_dst_pending_confirm; + u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ - long sk_sndtimeo; + struct page_frag sk_frag; struct timer_list sk_timer; - __u32 sk_priority; - __u32 sk_mark; + unsigned long sk_pacing_rate; /* bytes per second */ + atomic_t sk_zckey; + atomic_t sk_tskey; + __cacheline_group_end(sock_write_tx); + + __cacheline_group_begin(sock_read_tx); unsigned long sk_max_pacing_rate; - struct page_frag sk_frag; + long sk_sndtimeo; + u32 sk_priority; + u32 sk_mark; + struct dst_entry __rcu *sk_dst_cache; netdev_features_t sk_route_caps; - int sk_gso_type; +#ifdef CONFIG_SOCK_VALIDATE_XMIT + struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb); +#endif + u16 sk_gso_type; + u16 sk_gso_max_segs; unsigned int sk_gso_max_size; gfp_t sk_allocation; - __u32 sk_txhash; + u32 sk_txhash; + u8 sk_pacing_shift; + bool sk_use_task_frag; + __cacheline_group_end(sock_read_tx); /* * Because of non atomicity rules, all @@ -463,64 +497,44 @@ struct sock { u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, - sk_no_check_rx : 1, - sk_userlocks : 4; - u8 sk_pacing_shift; + sk_no_check_rx : 1; + u8 sk_shutdown; u16 sk_type; u16 sk_protocol; - u16 sk_gso_max_segs; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; - int sk_err, - sk_err_soft; + int sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; - u8 sk_txrehash; -#ifdef CONFIG_NET_RX_BUSY_POLL - u8 sk_prefer_busy_poll; - u16 sk_busy_poll_budget; -#endif spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; - long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif - atomic_t sk_tskey; - atomic_t sk_zckey; - u32 sk_tsflags; - u8 sk_shutdown; + int sk_disconnects; + u8 sk_txrehash; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; - bool sk_use_task_frag; - struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; - struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); - void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); -#ifdef CONFIG_SOCK_VALIDATE_XMIT - struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, - struct net_device *dev, - struct sk_buff *skb); -#endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL diff --git a/net/core/sock.c b/net/core/sock.c index 88bf810394a5..3fef3407383e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -4234,3 +4234,65 @@ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return sock_ioctl_out(sk, cmd, arg); } EXPORT_SYMBOL(sk_ioctl); + +static int __init sock_struct_check(void) +{ + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_sndbuf); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag); + return 0; +} + +core_initcall(sock_struct_check); -- cgit v1.2.3 From 12a686c2e761f1f1f6e6e2117a9ab9c6de2ac8a7 Mon Sep 17 00:00:00 2001 From: Adam Li Date: Mon, 26 Feb 2024 02:24:52 +0000 Subject: net: make SK_MEMORY_PCPU_RESERV tunable This patch adds /proc/sys/net/core/mem_pcpu_rsv sysctl file, to make SK_MEMORY_PCPU_RESERV tunable. Commit 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated") introduced per-cpu forward alloc cache: "Implement a per-cpu cache of +1/-1 MB, to reduce number of changes to sk->sk_prot->memory_allocated, which would otherwise be cause of false sharing." sk_prot->memory_allocated points to global atomic variable: atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; If increasing the per-cpu cache size from 1MB to e.g. 16MB, changes to sk->sk_prot->memory_allocated can be further reduced. Performance may be improved on system with many cores. Signed-off-by: Adam Li Reviewed-by: Christoph Lameter (Ampere) Signed-off-by: David S. Miller --- Documentation/admin-guide/sysctl/net.rst | 5 +++++ include/net/sock.h | 5 +++-- net/core/sock.c | 1 + net/core/sysctl_net_core.c | 9 +++++++++ 4 files changed, 18 insertions(+), 2 deletions(-) (limited to 'net/core/sock.c') diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 396091651955..7250c0542828 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -206,6 +206,11 @@ Will increase power usage. Default: 0 (off) +mem_pcpu_rsv +------------ + +Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. + rmem_default ------------ diff --git a/include/net/sock.h b/include/net/sock.h index 796a902cf4c1..09a0cde8bf52 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1443,6 +1443,7 @@ sk_memory_allocated(const struct sock *sk) /* 1 MB per cpu, in page units */ #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) +extern int sysctl_mem_pcpu_rsv; static inline void sk_memory_allocated_add(struct sock *sk, int amt) @@ -1451,7 +1452,7 @@ sk_memory_allocated_add(struct sock *sk, int amt) preempt_disable(); local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + if (local_reserve >= READ_ONCE(sysctl_mem_pcpu_rsv)) { __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); } @@ -1465,7 +1466,7 @@ sk_memory_allocated_sub(struct sock *sk, int amt) preempt_disable(); local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + if (local_reserve <= -READ_ONCE(sysctl_mem_pcpu_rsv)) { __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); } diff --git a/net/core/sock.c b/net/core/sock.c index 8d86886e39fa..df2ac54a8f74 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -283,6 +283,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; +int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; int sysctl_tstamp_allow_data __read_mostly = 1; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0f0cb1465e08..986f15e5d6c4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -30,6 +30,7 @@ static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -407,6 +408,14 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, }, + { + .procname = "mem_pcpu_rsv", + .data = &sysctl_mem_pcpu_rsv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_mem_pcpu_rsv, + }, { .procname = "dev_weight", .data = &weight_p, -- cgit v1.2.3 From ff73f8344e58e7557819f92c88f289ffa6116be7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 4 Mar 2024 13:29:31 -0800 Subject: sock: Use unsafe_memcpy() for sock_copy() While testing for places where zero-sized destinations were still showing up in the kernel, sock_copy() and inet_reqsk_clone() were found, which are using very specific memcpy() offsets for both avoiding a portion of struct sock, and copying beyond the end of it (since struct sock is really just a common header before the protocol-specific allocation). Instead of trying to unravel this historical lack of container_of(), just switch to unsafe_memcpy(), since that's effectively what was happening already (memcpy() wasn't checking 0-sized destinations while the code base was being converted away from fake flexible arrays). Avoid the following false positive warning with future changes to CONFIG_FORTIFY_SOURCE: memcpy: detected field-spanning write (size 3068) of destination "&nsk->__sk_common.skc_dontcopy_end" at net/core/sock.c:2057 (size 0) Signed-off-by: Kees Cook Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240304212928.make.772-kees@kernel.org Signed-off-by: Jakub Kicinski --- net/core/sock.c | 5 +++-- net/ipv4/inet_connection_sock.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index df2ac54a8f74..43bf3818c19e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2053,8 +2053,9 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, - prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + prot->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 747ed7344cbe..7d8090f109ef 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,8 +906,9 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, - req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; -- cgit v1.2.3 From c2deb2e971f5d9aca941ef13ee05566979e337a4 Mon Sep 17 00:00:00 2001 From: linke li Date: Thu, 21 Mar 2024 16:44:10 +0800 Subject: net: mark racy access on sk->sk_rcvbuf sk->sk_rcvbuf in __sock_queue_rcv_skb() and __sk_receive_skb() can be changed by other threads. Mark this as benign using READ_ONCE(). This patch is aimed at reducing the number of benign races reported by KCSAN in order to focus future debugging effort on harmful races. Signed-off-by: linke li Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 43bf3818c19e..0963689a5950 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -482,7 +482,7 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; @@ -552,7 +552,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, skb->dev = NULL; - if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } -- cgit v1.2.3