diff options
author | Jakub Kicinski <kuba@kernel.org> | 2020-12-04 07:48:11 -0800 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2020-12-04 07:48:12 -0800 |
commit | a1dd1d86973182458da7798a95f26cfcbea599b4 (patch) | |
tree | 1adda22ea30ccfac7651a7eed7b7c90356f8243a /include/net | |
parent | 55fd59b003f6e8fd88cf16590e79823d7ccf3026 (diff) | |
parent | eceae70bdeaeb6b8ceb662983cf663ff352fbc96 (diff) | |
download | linux-a1dd1d86973182458da7798a95f26cfcbea599b4.tar.gz linux-a1dd1d86973182458da7798a95f26cfcbea599b4.tar.bz2 linux-a1dd1d86973182458da7798a95f26cfcbea599b4.zip |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2020-12-03
The main changes are:
1) Support BTF in kernel modules, from Andrii.
2) Introduce preferred busy-polling, from Björn.
3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.
4) Memcg-based memory accounting for bpf objects, from Roman.
5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
selftests/bpf: Fix invalid use of strncat in test_sockmap
libbpf: Use memcpy instead of strncpy to please GCC
selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
selftests/bpf: Add tp_btf CO-RE reloc test for modules
libbpf: Support attachment of BPF tracing programs to kernel modules
libbpf: Factor out low-level BPF program loading helper
bpf: Allow to specify kernel module BTFs when attaching BPF programs
bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
selftests/bpf: Add support for marking sub-tests as skipped
selftests/bpf: Add bpf_testmod kernel module for testing
libbpf: Add kernel module BTF support for CO-RE relocations
libbpf: Refactor CO-RE relocs to not assume a single BTF object
libbpf: Add internal helper to load BTF data by FD
bpf: Keep module's btf_data_size intact after load
bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
bpf: Adds support for setting window clamp
samples/bpf: Fix spelling mistake "recieving" -> "receiving"
bpf: Fix cold build of test_progs-no_alu32
...
====================
Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net')
-rw-r--r-- | include/net/busy_poll.h | 27 | ||||
-rw-r--r-- | include/net/sock.h | 6 | ||||
-rw-r--r-- | include/net/tcp.h | 1 | ||||
-rw-r--r-- | include/net/xdp.h | 3 | ||||
-rw-r--r-- | include/net/xdp_sock_drv.h | 7 |
5 files changed, 39 insertions, 5 deletions
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index b001fa91c14e..73af4a64a599 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -23,6 +23,8 @@ */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +#define BUSY_POLL_BUDGET 8 + #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; @@ -43,7 +45,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg); + void *loop_end_arg, bool prefer_busy_poll, u16 budget); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) @@ -105,7 +107,9 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id >= MIN_NAPI_ID) - napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk); + napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, + READ_ONCE(sk->sk_prefer_busy_poll), + READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); #endif } @@ -131,13 +135,28 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) sk_rx_queue_set(sk, skb); } +static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + if (!READ_ONCE(sk->sk_napi_id)) + WRITE_ONCE(sk->sk_napi_id, napi_id); +#endif +} + /* variant used for unconnected sockets */ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL - if (!READ_ONCE(sk->sk_napi_id)) - WRITE_ONCE(sk->sk_napi_id, skb->napi_id); + __sk_mark_napi_id_once(sk, skb->napi_id); +#endif +} + +static inline void sk_mark_napi_id_once_xdp(struct sock *sk, + const struct xdp_buff *xdp) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); #endif } diff --git a/include/net/sock.h b/include/net/sock.h index f59764614e30..ffacdfdd9894 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -301,6 +301,8 @@ struct bpf_local_storage; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_prefer_busy_poll: prefer busypolling over softirq processing + * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family @@ -479,6 +481,10 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; +#ifdef CONFIG_NET_RX_BUSY_POLL + u8 sk_prefer_busy_poll; + u16 sk_busy_poll_budget; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; diff --git a/include/net/tcp.h b/include/net/tcp.h index 4525d6256321..a62fb7f8a1e3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -410,6 +410,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); +int tcp_set_window_clamp(struct sock *sk, int val); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, diff --git a/include/net/xdp.h b/include/net/xdp.h index 7d48b2ae217a..700ad5db7f5d 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -59,6 +59,7 @@ struct xdp_rxq_info { u32 queue_index; u32 reg_state; struct xdp_mem_info mem; + unsigned int napi_id; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { @@ -226,7 +227,7 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf) } int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index); + struct net_device *dev, u32 queue_index, unsigned int napi_id); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 5b1ee8a9976d..4e295541e396 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -13,6 +13,7 @@ void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, u32 max); void xsk_tx_release(struct xsk_buff_pool *pool); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id); @@ -128,6 +129,12 @@ static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, return false; } +static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, + u32 max) +{ + return 0; +} + static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } |