Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Breno Leitao <leitao@debian.org>
To:     sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com,
        willemdebruijn.kernel@gmail.com, martin.lau@linux.dev,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        John Fastabend <john.fastabend@gmail.com>,
        Andrii Nakryiko <andrii@kernel.org>,
        Song Liu <song@kernel.org>, Yonghong Song <yhs@fb.com>,
        KP Singh <kpsingh@kernel.org>, Hao Luo <haoluo@google.com>,
        Jiri Olsa <jolsa@kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>
Cc:     bpf@vger.kernel.org, linux-kernel@vger.kernel.org,
        netdev@vger.kernel.org, io-uring@vger.kernel.org, krisman@suse.de
Subject: [PATCH v3 1/9] bpf: Leverage sockptr_t in BPF getsockopt hook
Date:   Thu, 17 Aug 2023 07:55:46 -0700
Message-Id: <20230817145554.892543-2-leitao@debian.org>
In-Reply-To: <20230817145554.892543-1-leitao@debian.org>
References: <20230817145554.892543-1-leitao@debian.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Leverage sockptr_t structure to have an argument that is either an
userspace pointer, or, a kernel pointer.

This makes this function flexible, so, we can mix and match user and
kernel space pointers. 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.

Signed-off-by: Breno Leitao <leitao@debian.org>
---
 include/linux/bpf-cgroup.h |  5 +++--
 kernel/bpf/cgroup.c        | 20 +++++++++++---------
 net/socket.c               |  5 +++--
 3 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 57e9e109257e..d16cb99fd4f1 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,
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b2741aa0d9b..ebc8c58f7e46 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1875,8 +1875,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 }
 
 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)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1903,8 +1903,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		 * one that kernel returned as well to let
 		 * BPF programs inspect the value.
 		 */
-
-		if (get_user(ctx.optlen, optlen)) {
+		if (copy_from_sockptr(&ctx.optlen, optlen,
+				      sizeof(ctx.optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1915,8 +1915,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		}
 		orig_optlen = ctx.optlen;
 
-		if (copy_from_user(ctx.optval, optval,
-				   min(ctx.optlen, max_optlen)) != 0) {
+		if (copy_from_sockptr(ctx.optval, optval,
+				      min(ctx.optlen, max_optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1930,7 +1930,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	if (ret < 0)
 		goto out;
 
-	if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+	if (!sockptr_is_null(optval) &&
+	    (ctx.optlen > max_optlen || ctx.optlen < 0)) {
 		if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
 			pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
 				     ctx.optlen, max_optlen);
@@ -1942,11 +1943,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	}
 
 	if (ctx.optlen != 0) {
-		if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) {
+		if (!sockptr_is_null(optval) &&
+		    copy_to_sockptr(optval, ctx.optval, ctx.optlen)) {
 			ret = -EFAULT;
 			goto out;
 		}
-		if (put_user(ctx.optlen, optlen)) {
+		if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}
diff --git a/net/socket.c b/net/socket.c
index 1dc23f5298ba..33ea5eb91ade 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2311,8 +2311,9 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
 
 	if (!in_compat_syscall())
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
-						     optval, optlen, max_optlen,
-						     err);
+						     USER_SOCKPTR(optval),
+						     USER_SOCKPTR(optlen),
+						     max_optlen, err);
 out_put:
 	fput_light(sock->file, fput_needed);
 	return err;
-- 
2.34.1