diff mbox series

[v2,bpf-next,03/15] bpf: net: Consider in_bpf() when testing capable() in sk_setsockopt()

Message ID 20220803204620.3077641-1-kafai@fb.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: net: Remove duplicated code from bpf_setsockopt() | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 2749 this patch: 2749
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 609 this patch: 609
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 2881 this patch: 2881
netdev/checkpatch warning CHECK: Unnecessary parentheses around 'val > sk->sk_ll_usec' WARNING: line length of 98 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-1 success Logs for Kernel LATEST on ubuntu-latest with gcc
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Kernel LATEST on ubuntu-latest with llvm-16
bpf/vmtest-bpf-next-VM_Test-3 fail Logs for Kernel LATEST on z15 with gcc

Commit Message

Martin KaFai Lau Aug. 3, 2022, 8:46 p.m. UTC 
When bpf program calling bpf_setsockopt(SOL_SOCKET),
it could be run in softirq and doesn't make sense to do the capable
check.  There was a similar situation in bpf_setsockopt(TCP_CONGESTION).
In commit 8d650cdedaab ("tcp: fix tcp_set_congestion_control() use from bpf hook"),
tcp_set_congestion_control(..., cap_net_admin) was added to skip
the cap check for bpf prog.

This patch adds sockopt_ns_capable() and sockopt_capable() for
the sk_setsockopt() to use.  They will consider the in_bpf()
before doing the ns_capable() and capable() test.  They are in
EXPORT_SYMBOL for the ipv6 module to use in a latter patch.

Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/net/sock.h |  2 ++
 net/core/sock.c    | 38 +++++++++++++++++++++++++-------------
 2 files changed, 27 insertions(+), 13 deletions(-)
diff mbox series

Patch

diff --git a/include/net/sock.h b/include/net/sock.h
index b2ff230860c6..72b78c2b6f83 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1723,6 +1723,8 @@  static inline void unlock_sock_fast(struct sock *sk, bool slow)
 
 void sockopt_lock_sock(struct sock *sk);
 void sockopt_release_sock(struct sock *sk);
+bool sockopt_ns_capable(struct user_namespace *ns, int cap);
+bool sockopt_capable(int cap);
 
 /* Used by processes to "lock" a socket state, so that
  * interrupts and bottom half handlers won't change it
diff --git a/net/core/sock.c b/net/core/sock.c
index 82759540ae2c..2d88c06c27b7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1056,6 +1056,18 @@  void sockopt_release_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(sockopt_release_sock);
 
+bool sockopt_ns_capable(struct user_namespace *ns, int cap)
+{
+	return in_bpf() || ns_capable(ns, cap);
+}
+EXPORT_SYMBOL(sockopt_ns_capable);
+
+bool sockopt_capable(int cap)
+{
+	return in_bpf() || capable(cap);
+}
+EXPORT_SYMBOL(sockopt_capable);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -1091,7 +1103,7 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 
 	switch (optname) {
 	case SO_DEBUG:
-		if (val && !capable(CAP_NET_ADMIN))
+		if (val && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EACCES;
 		else
 			sock_valbool_flag(sk, SOCK_DBG, valbool);
@@ -1135,7 +1147,7 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_SNDBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1157,7 +1169,7 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_RCVBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1184,8 +1196,8 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 
 	case SO_PRIORITY:
 		if ((val >= 0 && val <= 6) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			sk->sk_priority = val;
 		else
 			ret = -EPERM;
@@ -1330,8 +1342,8 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 			clear_bit(SOCK_PASSSEC, &sock->flags);
 		break;
 	case SO_MARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1339,8 +1351,8 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 		__sock_set_mark(sk, val);
 		break;
 	case SO_RCVMARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1374,7 +1386,7 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
 		/* allow unprivileged users to decrease the value */
-		if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+		if ((val > sk->sk_ll_usec) && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else {
 			if (val < 0)
@@ -1384,13 +1396,13 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 	case SO_PREFER_BUSY_POLL:
-		if (valbool && !capable(CAP_NET_ADMIN))
+		if (valbool && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else
 			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
 		break;
 	case SO_BUSY_POLL_BUDGET:
-		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 		} else {
 			if (val < 0 || val > U16_MAX)
@@ -1461,7 +1473,7 @@  static int sk_setsockopt(struct sock *sk, int level, int optname,
 		 * scheduler has enough safe guards.
 		 */
 		if (sk_txtime.clockid != CLOCK_MONOTONIC &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}