From 97a0e1ea7b41c2db762c1258632f6ccc22719510 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Jan 2021 19:26:12 +0100 Subject: net, xdp: Introduce __xdp_build_skb_from_frame utility routine Introduce __xdp_build_skb_from_frame utility routine to build the skb from xdp_frame. Rely on __xdp_build_skb_from_frame in cpumap code. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/4f9f4c6b3dd3933770c617eb6689dbc0c6e25863.1610475660.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/xdp.h b/include/net/xdp.h index 0cf3976ce77c..689206dee6de 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -164,6 +164,9 @@ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); +struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct sk_buff *skb, + struct net_device *dev); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) -- cgit v1.2.3 From 89f479f0eccfc879e7bc0a69f44ed4a4639dfc32 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Jan 2021 19:26:13 +0100 Subject: net, xdp: Introduce xdp_build_skb_from_frame utility routine Introduce xdp_build_skb_from_frame utility routine to build the skb from xdp_frame. Respect to __xdp_build_skb_from_frame, xdp_build_skb_from_frame will allocate the skb object. Rely on xdp_build_skb_from_frame in veth driver. Introduce missing xdp metadata support in veth_xdp_rcv_one routine. Add missing metadata support in veth_xdp_rcv_one(). Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/94ade9e853162ae1947941965193190da97457bc.1610475660.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- drivers/net/veth.c | 18 +++--------------- include/net/xdp.h | 2 ++ net/core/xdp.c | 15 +++++++++++++++ 3 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 99caae7d1641..6e03b619c93c 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -567,16 +567,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { - void *hard_start = frame->data - frame->headroom; - int len = frame->len, delta = 0; struct xdp_frame orig_frame; struct bpf_prog *xdp_prog; - unsigned int headroom; struct sk_buff *skb; - /* bpf_xdp_adjust_head() assures BPF cannot access xdp_frame area */ - hard_start -= sizeof(struct xdp_frame); - rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (likely(xdp_prog)) { @@ -590,8 +584,8 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, switch (act) { case XDP_PASS: - delta = frame->data - xdp.data; - len = xdp.data_end - xdp.data; + if (xdp_update_frame_from_buff(&xdp, frame)) + goto err_xdp; break; case XDP_TX: orig_frame = *frame; @@ -629,18 +623,12 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, } rcu_read_unlock(); - headroom = sizeof(struct xdp_frame) + frame->headroom - delta; - skb = veth_build_skb(hard_start, headroom, len, frame->frame_sz); + skb = xdp_build_skb_from_frame(frame, rq->dev); if (!skb) { xdp_return_frame(frame); stats->rx_drops++; - goto err; } - xdp_release_frame(frame); - xdp_scrub_frame(frame); - skb->protocol = eth_type_trans(skb, rq->dev); -err: return skb; err_xdp: rcu_read_unlock(); diff --git a/include/net/xdp.h b/include/net/xdp.h index 689206dee6de..c4bfdc9a8b79 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -167,6 +167,8 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/net/core/xdp.c b/net/core/xdp.c index aeb09ed0704c..0d2630a35c3e 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -557,3 +557,18 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, return skb; } EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); + +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev) +{ + struct sk_buff *skb; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + memset(skb, 0, offsetof(struct sk_buff, tail)); + + return __xdp_build_skb_from_frame(xdpf, skb, dev); +} +EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); -- cgit v1.2.3 From 9cacf81f8161111db25f98e78a7a0e32ae142b3f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com --- include/linux/bpf-cgroup.h | 27 +- include/linux/indirect_call_wrapper.h | 6 + include/net/sock.h | 2 + include/net/tcp.h | 1 + kernel/bpf/cgroup.c | 46 +++ net/ipv4/tcp.c | 14 + net/ipv4/tcp_ipv4.c | 1 + net/ipv6/tcp_ipv6.c | 1 + net/socket.c | 3 + tools/include/uapi/linux/tcp.h | 357 +++++++++++++++++++++ .../testing/selftests/bpf/prog_tests/bpf_tcp_ca.c | 1 + .../selftests/bpf/prog_tests/cls_redirect.c | 1 + .../selftests/bpf/prog_tests/sockmap_basic.c | 1 + .../testing/selftests/bpf/prog_tests/sockopt_sk.c | 28 ++ tools/testing/selftests/bpf/progs/sockopt_sk.c | 23 +- tools/testing/selftests/bpf/test_progs.h | 1 - 16 files changed, 506 insertions(+), 7 deletions(-) create mode 100644 tools/include/uapi/linux/tcp.h (limited to 'include/net') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 72e69a0e1e8c..bcb2915e6124 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -364,10 +368,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ - optname, optval, \ - optlen, max_optlen, \ - retval); \ + if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ + !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ + tcp_bpf_bypass_getsockopt, \ + level, optname)) \ + __ret = __cgroup_bpf_run_filter_getsockopt( \ + sock, level, optname, optval, optlen, \ + max_optlen, retval); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ + sock, level, optname, optval, optlen, retval); \ __ret; \ }) @@ -452,6 +469,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..cfcfef37b2f1 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,4 +60,10 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) +#endif + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 129d200bccb4..7644ea64a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1174,6 +1174,8 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + bool (*bpf_bypass_getsockopt)(int level, + int optname); void (*release_cb)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 78d13c88720f..4bb42fb19711 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -403,6 +403,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +bool tcp_bpf_bypass_getsockopt(int level, int optname); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 96555a8a2c54..416e7738981b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1486,6 +1486,52 @@ out: sockopt_free_buf(&ctx); return ret; } + +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = level, + .optname = optname, + .retval = retval, + .optlen = *optlen, + .optval = optval, + .optval_end = optval + *optlen, + }; + int ret; + + /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy + * user data back into BPF buffer when reval != 0. This is + * done as an optimization to avoid extra copy, assuming + * kernel won't populate the data in case of an error. + * Here we always pass the data and memset() should + * be called if that data shouldn't be "exported". + */ + + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, BPF_PROG_RUN); + if (!ret) + return -EPERM; + + if (ctx.optlen > *optlen) + return -EFAULT; + + /* BPF programs only allowed to set retval to 0, not some + * arbitrary value. + */ + if (ctx.retval != 0 && ctx.retval != retval) + return -EFAULT; + + /* BPF programs can shrink the buffer, export the modifications. + */ + if (ctx.optlen != 0) + *optlen = ctx.optlen; + + return ctx.retval; +} #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 856ae516ac18..26aa923cf522 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4099,6 +4099,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, + &zc, &len, err); release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, err)) goto zerocopy_rcv_sk_err; @@ -4133,6 +4135,18 @@ zerocopy_rcv_out: return 0; } +bool tcp_bpf_bypass_getsockopt(int level, int optname) +{ + /* TCP do_tcp_getsockopt has optimized getsockopt implementation + * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. + */ + if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) + return true; + + return false; +} +EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); + int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 777306b5bc22..62b6fd385a47 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2793,6 +2793,7 @@ struct proto tcp_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0e1509b02cb3..8539715ff035 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2121,6 +2121,7 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/socket.c b/net/socket.c index 33e8b6c4e1d3..7f0617ab5437 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2126,6 +2126,9 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __sys_setsockopt(fd, level, optname, optval, optlen); } +INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, + int optname)); + /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h new file mode 100644 index 000000000000..13ceeb395eb8 --- /dev/null +++ b/tools/include/uapi/linux/tcp.h @@ -0,0 +1,357 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the TCP protocol. + * + * Version: @(#)tcp.h 1.0.2 04/28/93 + * + * Author: Fred N. van Kempen, + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_TCP_H +#define _UAPI_LINUX_TCP_H + +#include +#include +#include + +struct tcphdr { + __be16 source; + __be16 dest; + __be32 seq; + __be32 ack_seq; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 res1:4, + doff:4, + fin:1, + syn:1, + rst:1, + psh:1, + ack:1, + urg:1, + ece:1, + cwr:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u16 doff:4, + res1:4, + cwr:1, + ece:1, + urg:1, + ack:1, + psh:1, + rst:1, + syn:1, + fin:1; +#else +#error "Adjust your defines" +#endif + __be16 window; + __sum16 check; + __be16 urg_ptr; +}; + +/* + * The union cast uses a gcc extension to avoid aliasing problems + * (union is compatible to any of its members) + * This means this part of the code is -fstrict-aliasing safe now. + */ +union tcp_word_hdr { + struct tcphdr hdr; + __be32 words[5]; +}; + +#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) + +enum { + TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), + TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), + TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), + TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000), + TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000), + TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), + TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), + TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), + TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), + TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) +}; + +/* + * TCP general constants + */ +#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */ +#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */ + +/* TCP socket options */ +#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */ +#define TCP_MAXSEG 2 /* Limit MSS */ +#define TCP_CORK 3 /* Never send partially complete segments */ +#define TCP_KEEPIDLE 4 /* Start keeplives after this period */ +#define TCP_KEEPINTVL 5 /* Interval between keepalives */ +#define TCP_KEEPCNT 6 /* Number of keepalives before death */ +#define TCP_SYNCNT 7 /* Number of SYN retransmits */ +#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */ +#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */ +#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */ +#define TCP_INFO 11 /* Information about this connection. */ +#define TCP_QUICKACK 12 /* Block/reenable quick acks */ +#define TCP_CONGESTION 13 /* Congestion control algorithm */ +#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ +#define TCP_REPAIR_QUEUE 20 +#define TCP_QUEUE_SEQ 21 +#define TCP_REPAIR_OPTIONS 22 +#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ +#define TCP_TIMESTAMP 24 +#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ +#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ +#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ +#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ +#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ +#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ +#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ +#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ +#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ +#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ +#define TCP_ZEROCOPY_RECEIVE 35 +#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */ + +#define TCP_CM_INQ TCP_INQ + +#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ + + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + +struct tcp_repair_opt { + __u32 opt_code; + __u32 opt_val; +}; + +struct tcp_repair_window { + __u32 snd_wl1; + __u32 snd_wnd; + __u32 max_window; + + __u32 rcv_wnd; + __u32 rcv_wup; +}; + +enum { + TCP_NO_QUEUE, + TCP_RECV_QUEUE, + TCP_SEND_QUEUE, + TCP_QUEUES_NR, +}; + +/* why fastopen failed from client perspective */ +enum tcp_fastopen_client_fail { + TFO_STATUS_UNSPEC, /* catch-all */ + TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */ + TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */ + TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */ +}; + +/* for TCP_INFO socket option */ +#define TCPI_OPT_TIMESTAMPS 1 +#define TCPI_OPT_SACK 2 +#define TCPI_OPT_WSCALE 4 +#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ +#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ +#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ + +/* + * Sender's congestion state indicating normal or abnormal situations + * in the last round of packets sent. The state is driven by the ACK + * information and timer events. + */ +enum tcp_ca_state { + /* + * Nothing bad has been observed recently. + * No apparent reordering, packet loss, or ECN marks. + */ + TCP_CA_Open = 0, +#define TCPF_CA_Open (1< +#include #include #include "bpf_dctcp.skel.h" #include "bpf_cubic.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index 9781d85cb223..e075d03ab630 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -7,6 +7,7 @@ #include #include +#include #include diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85f73261fab0..b8b48cac2ac3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Cloudflare #include +#include #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index b25c9c45c148..d5b44b135c00 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -2,6 +2,12 @@ #include #include "cgroup_helpers.h" +#include + +#ifndef SOL_TCP +#define SOL_TCP IPPROTO_TCP +#endif + #define SOL_CUSTOM 0xdeadbeef static int getsetsockopt(void) @@ -11,6 +17,7 @@ static int getsetsockopt(void) char u8[4]; __u32 u32; char cc[16]; /* TCP_CA_NAME_MAX */ + struct tcp_zerocopy_receive zc; } buf = {}; socklen_t optlen; char *big_buf = NULL; @@ -154,6 +161,27 @@ static int getsetsockopt(void) goto err; } + /* TCP_ZEROCOPY_RECEIVE triggers */ + memset(&buf, 0, sizeof(buf)); + optlen = sizeof(buf.zc); + err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); + if (err) { + log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", + err, errno); + goto err; + } + + memset(&buf, 0, sizeof(buf)); + buf.zc.address = 12345; /* rejected by BPF */ + optlen = sizeof(buf.zc); + errno = 0; + err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); + if (errno != EPERM) { + log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", + err, errno); + goto err; + } + free(big_buf); close(fd); return 0; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 712df7b49cb1..d3597f81e6e9 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include -#include +#include #include +#include #include char _license[] SEC("license") = "GPL"; @@ -12,6 +12,10 @@ __u32 _version SEC("version") = 1; #define PAGE_SIZE 4096 #endif +#ifndef SOL_TCP +#define SOL_TCP IPPROTO_TCP +#endif + #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { @@ -57,6 +61,21 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { + /* Verify that TCP_ZEROCOPY_RECEIVE triggers. + * It has a custom implementation for performance + * reasons. + */ + + if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) + return 0; /* EPERM, bounds check */ + + if (((struct tcp_zerocopy_receive *)optval)->address != 0) + return 0; /* EPERM, unexpected data */ + + return 1; + } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index e49e2fdde942..f7c2fd89d01a 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -16,7 +16,6 @@ typedef __u16 __sum16; #include #include #include -#include #include #include #include -- cgit v1.2.3 From 772412176fb98493158929b220fe250127f611af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 27 Jan 2021 11:31:39 -0800 Subject: bpf: Allow rewriting to ports under ip_unprivileged_port_start At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port to the privileged ones (< ip_unprivileged_port_start), but it will be rejected later on in the __inet_bind or __inet6_bind. Let's add another return value to indicate that CAP_NET_BIND_SERVICE check should be ignored. Use the same idea as we currently use in cgroup/egress where bit #1 indicates CN. Instead, for cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should be bypassed. v5: - rename flags to be less confusing (Andrey Ignatov) - rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags and accept BPF_RET_SET_CN (no behavioral changes) v4: - Add missing IPv6 support (Martin KaFai Lau) v3: - Update description (Martin KaFai Lau) - Fix capability restore in selftest (Martin KaFai Lau) v2: - Switch to explicit return code (Martin KaFai Lau) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Reviewed-by: Martin KaFai Lau Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++--------- include/linux/bpf.h | 52 +++++++++++++++++++++++++++++----------------- include/net/inet_common.h | 2 ++ kernel/bpf/cgroup.c | 8 +++++-- kernel/bpf/verifier.c | 3 +++ net/ipv4/af_inet.c | 9 +++++--- net/ipv6/af_inet6.c | 9 +++++--- 7 files changed, 84 insertions(+), 37 deletions(-) (limited to 'include/net') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0748fd87969e..c42e02b4d84b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -125,7 +125,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx); + void *t_ctx, + u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -231,30 +232,48 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - NULL); \ + NULL, \ + &__unused_flags); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - t_ctx); \ + t_ctx, \ + &__unused_flags); \ release_sock(sk); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL) - -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) +/* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags + * via upper bits of return code. The only flag that is supported + * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check + * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). + */ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +({ \ + u32 __flags = 0; \ + int __ret = 0; \ + if (cgroup_bpf_enabled(type)) { \ + lock_sock(sk); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL, &__flags); \ + release_sock(sk); \ + if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ + *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ + } \ + __ret; \ +}) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ @@ -453,8 +472,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1aac2af12fed..321966fc35db 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1073,6 +1073,34 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ +#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) +/* BPF program asks to set CN on the packet. */ +#define BPF_RET_SET_CN (1 << 0) + +#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + u32 func_ret; \ + migrate_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + func_ret = func(_prog, ctx); \ + _ret &= (func_ret & 1); \ + *(ret_flags) |= (func_ret >> 1); \ + _item++; \ + } \ + rcu_read_unlock(); \ + migrate_enable(); \ + _ret; \ + }) + #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ struct bpf_prog_array_item *_item; \ @@ -1120,25 +1148,11 @@ _out: \ */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - u32 ret; \ - u32 _ret = 1; \ - u32 _cn = 0; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - ret = func(_prog, ctx); \ - _ret &= (ret & 1); \ - _cn |= (ret & 2); \ - _item++; \ - } \ - rcu_read_unlock(); \ - migrate_enable(); \ + u32 _flags = 0; \ + bool _cn; \ + u32 _ret; \ + _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index cb2818862919..cad2a611efde 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -41,6 +41,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); #define BIND_WITH_LOCK (1 << 1) /* Called from BPF program. */ #define BIND_FROM_BPF (1 << 2) +/* Skip CAP_NET_BIND_SERVICE check. */ +#define BIND_NO_CAP_NET_BIND_SERVICE (1 << 3) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index da649f20d6b2..cdf3c7e611d9 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1055,6 +1055,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted * @t_ctx: Pointer to attach type specific context + * @flags: Pointer to u32 which contains higher bits of BPF program + * return value (OR'ed together). * * socket is expected to be of type INET or INET6. * @@ -1064,7 +1066,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx) + void *t_ctx, + u32 *flags) { struct bpf_sock_addr_kern ctx = { .sk = sk, @@ -1087,7 +1090,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + ret = BPF_PROG_RUN_ARRAY_FLAGS(cgrp->bpf.effective[type], &ctx, + BPF_PROG_RUN, flags); return ret == 1 ? 0 : -EPERM; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d0eae51b31e4..972fc38eb62d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7986,6 +7986,9 @@ static int check_return_code(struct bpf_verifier_env *env) env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) range = tnum_range(1, 1); + if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || + env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) + range = tnum_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6ba2930ff49b..aaa94bea19c3 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -438,6 +438,7 @@ EXPORT_SYMBOL(inet_release); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; + u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ @@ -450,11 +451,12 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + BPF_CGROUP_INET4_BIND, &flags); if (err) return err; - return __inet_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); + return __inet_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet_bind); @@ -499,7 +501,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && inet_port_requires_bind_service(net, snum) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b9c654836b72..f091fe9b4da5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -295,7 +295,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && inet_port_requires_bind_service(net, snum) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; @@ -439,6 +440,7 @@ out_unlock: int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; + u32 flags = BIND_WITH_LOCK; int err = 0; /* If the socket has its own bind function then use it. */ @@ -451,11 +453,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + BPF_CGROUP_INET6_BIND, &flags); if (err) return err; - return __inet6_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); + return __inet6_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet6_bind); -- cgit v1.2.3 From 65e6dcf73398ddb64bb782ff2acd918d3a37a53a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 29 Jan 2021 23:04:08 +0100 Subject: net, veth: Alloc skb in bulk for ndo_xdp_xmit Split ndo_xdp_xmit and ndo_start_xmit use cases in veth_xdp_rcv routine in order to alloc skbs in bulk for XDP_PASS verdict. Introduce xdp_alloc_skb_bulk utility routine to alloc skb bulk list. The proposed approach has been tested in the following scenario: eth (ixgbe) --> XDP_REDIRECT --> veth0 --> (remote-ns) veth1 --> XDP_PASS XDP_REDIRECT: xdp_redirect_map bpf sample XDP_PASS: xdp_rxq_info bpf sample traffic generator: pkt_gen sending udp traffic on a remote device bpf-next master: ~3.64Mpps bpf-next + skb bulking allocation: ~3.79Mpps Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/a14a30d3c06fff24e13f836c733d80efc0bd6eb5.1611957532.git.lorenzo@kernel.org --- drivers/net/veth.c | 78 ++++++++++++++++++++++++++++++++++++++++-------------- include/net/xdp.h | 1 + net/core/xdp.c | 11 ++++++++ 3 files changed, 70 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 6e03b619c93c..aa1a66ad2ce5 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -35,6 +35,7 @@ #define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) #define VETH_XDP_TX_BULK_SIZE 16 +#define VETH_XDP_BATCH 16 struct veth_stats { u64 rx_drops; @@ -562,14 +563,13 @@ static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp, return 0; } -static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, - struct xdp_frame *frame, - struct veth_xdp_tx_bq *bq, - struct veth_stats *stats) +static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, + struct xdp_frame *frame, + struct veth_xdp_tx_bq *bq, + struct veth_stats *stats) { struct xdp_frame orig_frame; struct bpf_prog *xdp_prog; - struct sk_buff *skb; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -623,13 +623,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, } rcu_read_unlock(); - skb = xdp_build_skb_from_frame(frame, rq->dev); - if (!skb) { - xdp_return_frame(frame); - stats->rx_drops++; - } - - return skb; + return frame; err_xdp: rcu_read_unlock(); xdp_return_frame(frame); @@ -637,6 +631,37 @@ xdp_xmit: return NULL; } +/* frames array contains VETH_XDP_BATCH at most */ +static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames, + int n_xdpf, struct veth_xdp_tx_bq *bq, + struct veth_stats *stats) +{ + void *skbs[VETH_XDP_BATCH]; + int i; + + if (xdp_alloc_skb_bulk(skbs, n_xdpf, + GFP_ATOMIC | __GFP_ZERO) < 0) { + for (i = 0; i < n_xdpf; i++) + xdp_return_frame(frames[i]); + stats->rx_drops += n_xdpf; + + return; + } + + for (i = 0; i < n_xdpf; i++) { + struct sk_buff *skb = skbs[i]; + + skb = __xdp_build_skb_from_frame(frames[i], skb, + rq->dev); + if (!skb) { + xdp_return_frame(frames[i]); + stats->rx_drops++; + continue; + } + napi_gro_receive(&rq->xdp_napi, skb); + } +} + static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, struct veth_xdp_tx_bq *bq, @@ -784,32 +809,45 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { - int i, done = 0; + int i, done = 0, n_xdpf = 0; + void *xdpf[VETH_XDP_BATCH]; for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); - struct sk_buff *skb; if (!ptr) break; if (veth_is_xdp_frame(ptr)) { + /* ndo_xdp_xmit */ struct xdp_frame *frame = veth_ptr_to_xdp(ptr); stats->xdp_bytes += frame->len; - skb = veth_xdp_rcv_one(rq, frame, bq, stats); + frame = veth_xdp_rcv_one(rq, frame, bq, stats); + if (frame) { + /* XDP_PASS */ + xdpf[n_xdpf++] = frame; + if (n_xdpf == VETH_XDP_BATCH) { + veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, + bq, stats); + n_xdpf = 0; + } + } } else { - skb = ptr; + /* ndo_start_xmit */ + struct sk_buff *skb = ptr; + stats->xdp_bytes += skb->len; skb = veth_xdp_rcv_skb(rq, skb, bq, stats); + if (skb) + napi_gro_receive(&rq->xdp_napi, skb); } - - if (skb) - napi_gro_receive(&rq->xdp_napi, skb); - done++; } + if (n_xdpf) + veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); + u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_redirect += stats->xdp_redirect; rq->stats.vs.xdp_bytes += stats->xdp_bytes; diff --git a/include/net/xdp.h b/include/net/xdp.h index c4bfdc9a8b79..a5bc214a49d9 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -169,6 +169,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); +int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/net/core/xdp.c b/net/core/xdp.c index 0d2630a35c3e..05354976c1fc 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -514,6 +514,17 @@ void xdp_warn(const char *msg, const char *func, const int line) }; EXPORT_SYMBOL_GPL(xdp_warn); +int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) +{ + n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, + n_skb, skbs); + if (unlikely(!n_skb)) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk); + struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) -- cgit v1.2.3