From 64696c40d03c01e0ea2e3e9aa1c490a7b6a1b6be Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Sep 2022 00:04:03 -0700 Subject: bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline The struct_ops prog is to allow using bpf to implement the functions in a struct (eg. kernel module). The current usage is to implement the tcp_congestion. The kernel does not call the tcp-cc's ops (ie. the bpf prog) in a recursive way. The struct_ops is sharing the tracing-trampoline's enter/exit function which tracks prog->active to avoid recursion. It is needed for tracing prog. However, it turns out the struct_ops bpf prog will hit this prog->active and unnecessarily skipped running the struct_ops prog. eg. The '.ssthresh' may run in_task() and then interrupted by softirq that runs the same '.ssthresh'. Skip running the '.ssthresh' will end up returning random value to the caller. The patch adds __bpf_prog_{enter,exit}_struct_ops for the struct_ops trampoline. They do not track the prog->active to detect recursion. One exception is when the tcp_congestion's '.init' ops is doing bpf_setsockopt(TCP_CONGESTION) and then recurs to the same '.init' ops. This will be addressed in the following patches. Fixes: ca06f55b9002 ("bpf: Add per-program recursion prevention mechanism") Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220929070407.965581-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f3eaf3ed98c..9e7d46d16032 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -864,6 +864,10 @@ u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); -- cgit v1.2.3 From 061ff040710e9f6f043d1fa80b1b362d2845b17a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Sep 2022 00:04:06 -0700 Subject: bpf: tcp: Stop bpf_setsockopt(TCP_CONGESTION) in init ops to recur itself When a bad bpf prog '.init' calls bpf_setsockopt(TCP_CONGESTION, "itself"), it will trigger this loop: .init => bpf_setsockopt(tcp_cc) => .init => bpf_setsockopt(tcp_cc) ... ... => .init => bpf_setsockopt(tcp_cc). It was prevented by the prog->active counter before but the prog->active detection cannot be used in struct_ops as explained in the earlier patch of the set. In this patch, the second bpf_setsockopt(tcp_cc) is not allowed in order to break the loop. This is done by using a bit of an existing 1 byte hole in tcp_sock to check if there is on-going bpf_setsockopt(TCP_CONGESTION) in this tcp_sock. Note that this essentially limits only the first '.init' can call bpf_setsockopt(TCP_CONGESTION) to pick a fallback cc (eg. peer does not support ECN) and the second '.init' cannot fallback to another cc. This applies even the second bpf_setsockopt(TCP_CONGESTION) will not cause a loop. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220929070407.965581-5-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/tcp.h | 6 ++++++ net/core/filter.c | 28 +++++++++++++++++++++++++++- net/ipv4/tcp_minisocks.c | 1 + 3 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a9fbe22732c3..3bdf687e2fb3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -388,6 +388,12 @@ struct tcp_sock { u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs * values defined in uapi/linux/tcp.h */ + u8 bpf_chg_cc_inprogress:1; /* In the middle of + * bpf_setsockopt(TCP_CONGESTION), + * it is to avoid the bpf_tcp_cc->init() + * to recur itself by calling + * bpf_setsockopt(TCP_CONGESTION, "itself"). + */ #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG) #else #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 diff --git a/net/core/filter.c b/net/core/filter.c index 96f2f7a65e65..ac4c45c02da5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5105,6 +5105,9 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, int *optlen, bool getopt) { + struct tcp_sock *tp; + int ret; + if (*optlen < 2) return -EINVAL; @@ -5125,8 +5128,31 @@ static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) return -ENOTSUPP; - return do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + /* It stops this looping + * + * .init => bpf_setsockopt(tcp_cc) => .init => + * bpf_setsockopt(tcp_cc)" => .init => .... + * + * The second bpf_setsockopt(tcp_cc) is not allowed + * in order to break the loop when both .init + * are the same bpf prog. + * + * This applies even the second bpf_setsockopt(tcp_cc) + * does not cause a loop. This limits only the first + * '.init' can call bpf_setsockopt(TCP_CONGESTION) to + * pick a fallback cc (eg. peer does not support ECN) + * and the second '.init' cannot fallback to + * another. + */ + tp = tcp_sk(sk); + if (tp->bpf_chg_cc_inprogress) + return -EBUSY; + + tp->bpf_chg_cc_inprogress = 1; + ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), *optlen); + tp->bpf_chg_cc_inprogress = 0; + return ret; } static int sol_tcp_sockopt(struct sock *sk, int optname, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index cb95d88497ae..ddcdc2bc4c04 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -541,6 +541,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); + newtp->bpf_chg_cc_inprogress = 0; tcp_bpf_clone(sk, newsk); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); -- cgit v1.2.3