From: Martin KaFai Lau Date: Wed, 17 Aug 2022 06:18:04 +0000 (-0700) Subject: bpf: Change bpf_setsockopt(SOL_SOCKET) to reuse sk_setsockopt() X-Git-Tag: v6.1~448^2~251^2~45^2~6 X-Git-Url: https://git.proxmox.com/?a=commitdiff_plain;h=29003875bd5bab262a29d1c6e76a2124bd07e4c2;p=mirror_ubuntu-kernels.git bpf: Change bpf_setsockopt(SOL_SOCKET) to reuse sk_setsockopt() After the prep work in the previous patches, this patch removes most of the dup code from bpf_setsockopt(SOL_SOCKET) and reuses them from sk_setsockopt(). The sock ptr test is added to the SO_RCVLOWAT because the sk->sk_socket could be NULL in some of the bpf hooks. The existing optname white-list is refactored into a new function sol_socket_setsockopt(). Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061804.4178920-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- diff --git a/include/net/sock.h b/include/net/sock.h index 13089d88a2e2..ee44b424d952 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1828,6 +1828,8 @@ void sock_pfree(struct sk_buff *skb); #define sock_edemux sock_efree #endif +int sk_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); diff --git a/net/core/filter.c b/net/core/filter.c index a663d7b96bad..6f5bcc8df487 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5013,109 +5013,43 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static int sol_socket_setsockopt(struct sock *sk, int optname, + char *optval, int optlen) +{ + switch (optname) { + case SO_SNDBUF: + case SO_RCVBUF: + case SO_KEEPALIVE: + case SO_PRIORITY: + case SO_REUSEPORT: + case SO_RCVLOWAT: + case SO_MARK: + case SO_MAX_PACING_RATE: + case SO_BINDTOIFINDEX: + case SO_TXREHASH: + if (optlen != sizeof(int)) + return -EINVAL; + break; + case SO_BINDTODEVICE: + break; + default: + return -EINVAL; + } + + return sk_setsockopt(sk, SOL_SOCKET, optname, + KERNEL_SOCKPTR(optval), optlen); +} + static int __bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { - char devname[IFNAMSIZ]; - int val, valbool; - struct net *net; - int ifindex; - int ret = 0; + int val, ret = 0; if (!sk_fullsock(sk)) return -EINVAL; if (level == SOL_SOCKET) { - if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) - return -EINVAL; - val = *((int *)optval); - valbool = val ? 1 : 0; - - /* Only some socketops are supported */ - switch (optname) { - case SO_RCVBUF: - val = min_t(u32, val, sysctl_rmem_max); - val = min_t(int, val, INT_MAX / 2); - sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - WRITE_ONCE(sk->sk_rcvbuf, - max_t(int, val * 2, SOCK_MIN_RCVBUF)); - break; - case SO_SNDBUF: - val = min_t(u32, val, sysctl_wmem_max); - val = min_t(int, val, INT_MAX / 2); - sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - WRITE_ONCE(sk->sk_sndbuf, - max_t(int, val * 2, SOCK_MIN_SNDBUF)); - break; - case SO_MAX_PACING_RATE: /* 32bit version */ - if (val != ~0U) - cmpxchg(&sk->sk_pacing_status, - SK_PACING_NONE, - SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? - ~0UL : (unsigned int)val; - sk->sk_pacing_rate = min(sk->sk_pacing_rate, - sk->sk_max_pacing_rate); - break; - case SO_PRIORITY: - sk->sk_priority = val; - break; - case SO_RCVLOWAT: - if (val < 0) - val = INT_MAX; - if (sk->sk_socket && sk->sk_socket->ops->set_rcvlowat) - ret = sk->sk_socket->ops->set_rcvlowat(sk, val); - else - WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); - break; - case SO_MARK: - if (sk->sk_mark != val) { - sk->sk_mark = val; - sk_dst_reset(sk); - } - break; - case SO_BINDTODEVICE: - optlen = min_t(long, optlen, IFNAMSIZ - 1); - strncpy(devname, optval, optlen); - devname[optlen] = 0; - - ifindex = 0; - if (devname[0] != '\0') { - struct net_device *dev; - - ret = -ENODEV; - - net = sock_net(sk); - dev = dev_get_by_name(net, devname); - if (!dev) - break; - ifindex = dev->ifindex; - dev_put(dev); - } - fallthrough; - case SO_BINDTOIFINDEX: - if (optname == SO_BINDTOIFINDEX) - ifindex = val; - ret = sock_bindtoindex(sk, ifindex, false); - break; - case SO_KEEPALIVE: - if (sk->sk_prot->keepalive) - sk->sk_prot->keepalive(sk, valbool); - sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); - break; - case SO_REUSEPORT: - sk->sk_reuseport = valbool; - break; - case SO_TXREHASH: - if (val < -1 || val > 1) { - ret = -EINVAL; - break; - } - sk->sk_txrehash = (u8)val; - break; - default: - ret = -EINVAL; - } + return sol_socket_setsockopt(sk, optname, optval, optlen); } else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) { if (optlen != sizeof(int) || sk->sk_family != AF_INET) return -EINVAL; diff --git a/net/core/sock.c b/net/core/sock.c index 7ea46e4700fd..2a6f84702eb9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1077,8 +1077,8 @@ EXPORT_SYMBOL(sockopt_capable); * at the socket level. Everything here is generic. */ -static int sk_setsockopt(struct sock *sk, int level, int optname, - sockptr_t optval, unsigned int optlen) +int sk_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen) { struct so_timestamping timestamping; struct socket *sock = sk->sk_socket; @@ -1264,7 +1264,7 @@ set_sndbuf: case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - if (sock->ops->set_rcvlowat) + if (sock && sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);