From a615f67e1a426f35366b8398c11f31c148e7df48 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:39 -0700 Subject: bpf: Add sockptr support for getsockopt The whole network stack uses sockptr, and while it doesn't move to something more modern, let's use sockptr in getsockptr BPF hooks, so, it could be used by other callers. The main motivation for this change is to use it in the io_uring {g,s}etsockopt(), which will use a userspace pointer for *optval, but, a kernel value for optlen. Link: https://lore.kernel.org/all/ZSArfLaaGcfd8LH8@gmail.com/ Signed-off-by: Breno Leitao Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20231016134750.1381153-2-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/bpf-cgroup.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8506690dbb9c..f5b4fb6ed8c6 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -139,9 +139,10 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, int *optname, char __user *optval, int *optlen, char **kernel_optval); + int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, - int optname, char __user *optval, - int __user *optlen, int max_optlen, + int optname, sockptr_t optval, + sockptr_t optlen, int max_optlen, int retval); int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, -- cgit v1.2.3 From 3f31e0d14d44ad491a81b7c1f83f32fbc300a867 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:40 -0700 Subject: bpf: Add sockptr support for setsockopt The whole network stack uses sockptr, and while it doesn't move to something more modern, let's use sockptr in setsockptr BPF hooks, so, it could be used by other callers. The main motivation for this change is to use it in the io_uring {g,s}etsockopt(), which will use a userspace pointer for *optval, but, a kernel value for optlen. Link: https://lore.kernel.org/all/ZSArfLaaGcfd8LH8@gmail.com/ Signed-off-by: Breno Leitao Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20231016134750.1381153-3-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/bpf-cgroup.h | 2 +- kernel/bpf/cgroup.c | 5 +++-- net/socket.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index f5b4fb6ed8c6..cecfe8c99f28 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -137,7 +137,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, - int *optname, char __user *optval, + int *optname, sockptr_t optval, int *optlen, char **kernel_optval); int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ebc8c58f7e46..f0dedd4f7f2e 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1785,7 +1785,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, } int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, - int *optname, char __user *optval, + int *optname, sockptr_t optval, int *optlen, char **kernel_optval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -1808,7 +1808,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, ctx.optlen = *optlen; - if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { + if (copy_from_sockptr(ctx.optval, optval, + min(*optlen, max_optlen))) { ret = -EFAULT; goto out; } diff --git a/net/socket.c b/net/socket.c index 82cd6890a4f0..9a43f6e850c7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2288,7 +2288,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, if (!in_compat_syscall()) err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, - user_optval, &optlen, + optval, &optlen, &kernel_optval); if (err < 0) goto out_put; -- cgit v1.2.3 From 0b05b0cd78c92371fdde6333d006f39eaf9e0860 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:42 -0700 Subject: net/socket: Break down __sys_getsockopt Split __sys_getsockopt() into two functions by removing the core logic into a sub-function (do_sock_getsockopt()). This will avoid code duplication when doing the same operation in other callers, for instance. do_sock_getsockopt() will be called by io_uring getsockopt() command operation in the following patch. The same was done for the setsockopt pair. Suggested-by: Martin KaFai Lau Signed-off-by: Breno Leitao Acked-by: Jakub Kicinski Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20231016134750.1381153-5-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/bpf-cgroup.h | 2 +- include/net/sock.h | 4 +-- net/core/sock.c | 8 ------ net/socket.c | 64 +++++++++++++++++++++++++++++----------------- 4 files changed, 44 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index cecfe8c99f28..ffaca1ab5e8d 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -378,7 +378,7 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ - get_user(__ret, optlen); \ + copy_from_sockptr(&__ret, optlen, sizeof(int)); \ __ret; \ }) diff --git a/include/net/sock.h b/include/net/sock.h index 24fbf7182386..cffb77aa71ab 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1869,11 +1869,11 @@ int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen); +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, sockptr_t optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); -int sock_getsockopt(struct socket *sock, int level, int op, - char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, diff --git a/net/core/sock.c b/net/core/sock.c index 16584e2dd648..223eed53fb7d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2010,14 +2010,6 @@ lenout: return 0; } -int sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - return sk_getsockopt(sock->sk, level, optname, - USER_SOCKPTR(optval), - USER_SOCKPTR(optlen)); -} - /* * Initialize an sk_lock. * diff --git a/net/socket.c b/net/socket.c index 63be25d762f6..eb6960958026 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2333,6 +2333,43 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int optname)); +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, sockptr_t optlen) +{ + int max_optlen __maybe_unused; + const struct proto_ops *ops; + int err; + + err = security_socket_getsockopt(sock, level, optname); + if (err) + return err; + + if (!compat) + max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + + ops = READ_ONCE(sock->ops); + if (level == SOL_SOCKET) { + err = sk_getsockopt(sock->sk, level, optname, optval, optlen); + } else if (unlikely(!ops->getsockopt)) { + err = -EOPNOTSUPP; + } else { + if (WARN_ONCE(optval.is_kernel || optlen.is_kernel, + "Invalid argument type")) + return -EOPNOTSUPP; + + err = ops->getsockopt(sock, level, optname, optval.user, + optlen.user); + } + + if (!compat) + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, + optval, optlen, max_optlen, + err); + + return err; +} +EXPORT_SYMBOL(do_sock_getsockopt); + /* * 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. @@ -2340,37 +2377,18 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { - int max_optlen __maybe_unused; - const struct proto_ops *ops; int err, fput_needed; struct socket *sock; + bool compat; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; - err = security_socket_getsockopt(sock, level, optname); - if (err) - goto out_put; + compat = in_compat_syscall(); + err = do_sock_getsockopt(sock, compat, level, optname, + USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); - if (!in_compat_syscall()) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); - - ops = READ_ONCE(sock->ops); - if (level == SOL_SOCKET) - err = sock_getsockopt(sock, level, optname, optval, optlen); - else if (unlikely(!ops->getsockopt)) - err = -EOPNOTSUPP; - else - err = ops->getsockopt(sock, level, optname, optval, - optlen); - - if (!in_compat_syscall()) - err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, - USER_SOCKPTR(optval), - USER_SOCKPTR(optlen), - max_optlen, err); -out_put: fput_light(sock->file, fput_needed); return err; } -- cgit v1.2.3 From 5fea44a6e05b86bf49019fbbf2ab30098d03e0dc Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:43 -0700 Subject: io_uring/cmd: Pass compat mode in issue_flags Create a new flag to track if the operation is running compat mode. This basically check the context->compat and pass it to the issue_flags, so, it could be queried later in the callbacks. Signed-off-by: Breno Leitao Reviewed-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20231016134750.1381153-6-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 1 + io_uring/uring_cmd.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index b4391e0a9bc8..aefb73eeeebf 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -23,6 +23,7 @@ enum io_uring_cmd_flags { /* set when uring wants to cancel a previously issued command */ IO_URING_F_CANCEL = (1 << 11), + IO_URING_F_COMPAT = (1 << 12), }; /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 00a5e5621a28..4bedd633c08c 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -175,6 +175,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) issue_flags |= IO_URING_F_SQE128; if (ctx->flags & IORING_SETUP_CQE32) issue_flags |= IO_URING_F_CQE32; + if (ctx->compat) + issue_flags |= IO_URING_F_COMPAT; if (ctx->flags & IORING_SETUP_IOPOLL) { if (!file->f_op->uring_cmd_iopoll) return -EOPNOTSUPP; -- cgit v1.2.3