util: Extend sock_probe_mem() to sock_probe_features()

sock_probe_mem() currently checks whether we're able to allocate large
socket buffers.  Extend it to also check whether the SO_BINDTODEVICE
socket option is available.  Rename to sock_probe_features() to reflect the
new functionality.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
[sbrivio: Add whitespace around "-" in sock_probe_features()]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

4 files changed, 21 insertions, 4 deletions

diff --git a/passt.c b/passt.c
index 4964427..0b84ac6 100644
--- a/passt.c
+++ b/passt.c
@@ -381,7 +381,7 @@ int main(int argc, char **argv)
 	if (setrlimit(RLIMIT_NOFILE, &limit))
 		die_perror("Failed to set current limit for open files");
 
-	sock_probe_mem(&c);
+	sock_probe_features(&c);
 
 	conf(&c, argc, argv);
 	trace_init(c.trace);
diff --git a/passt.h b/passt.h
index 15801b4..79d01dd 100644
--- a/passt.h
+++ b/passt.h
@@ -204,6 +204,7 @@ struct ip6_ctx {
  * @freebind:		Allow binding of non-local addresses for forwarding
  * @low_wmem:		Low probed net.core.wmem_max
  * @low_rmem:		Low probed net.core.rmem_max
+ * @no_bindtodevice:	Unprivileged SO_BINDTODEVICE not available
  * @vdev:		vhost-user device
  * @device_state_fd:	Device state migration channel
  * @device_state_result: Device state migration result
@@ -281,6 +282,7 @@ struct ctx {
 
 	int low_wmem;
 	int low_rmem;
+	int no_bindtodevice;
 
 	struct vu_dev *vdev;
 
diff --git a/util.c b/util.c
index 7493f98..3a63abd 100644
--- a/util.c
+++ b/util.c
@@ -233,12 +233,13 @@ int sock_unix(char *sock_path)
 }
 
 /**
- * sock_probe_mem() - Check if setting high SO_SNDBUF and SO_RCVBUF is allowed
+ * sock_probe_features() - Probe for socket features we might use
  * @c:		Execution context
  */
-void sock_probe_mem(struct ctx *c)
+void sock_probe_features(struct ctx *c)
 {
 	int v = INT_MAX / 2, s;
+	const char lo[] = "lo";
 	socklen_t sl;
 
 	s = socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
@@ -247,6 +248,7 @@ void sock_probe_mem(struct ctx *c)
 		return;
 	}
 
+	/* Check if setting high SO_SNDBUF and SO_RCVBUF is allowed */
 	sl = sizeof(v);
 	if (setsockopt(s, SOL_SOCKET, SO_SNDBUF, &v, sizeof(v))	||
 	    getsockopt(s, SOL_SOCKET, SO_SNDBUF, &v, &sl) ||
@@ -259,6 +261,19 @@ void sock_probe_mem(struct ctx *c)
 	    (size_t)v < RCVBUF_BIG)
 		c->low_rmem = 1;
 
+	/* Check if SO_BINDTODEVICE is available
+	 *
+	 * Supported since kernel version 5.7, commit c427bfec18f2 ("net: core:
+	 * enable SO_BINDTODEVICE for non-root users").  Some distro kernels may
+	 * have backports, of course.  Record whether we can use it so that we
+	 * can give more useful diagnostics.
+	 */
+	if (setsockopt(s, SOL_SOCKET, SO_BINDTODEVICE, lo, sizeof(lo) - 1)) {
+		if (errno != EPERM)
+			warn_perror("Unexpected error probing SO_BINDTODEVICE");
+		c->no_bindtodevice = 1;
+	}
+
 	close(s);
 }
 
diff --git a/util.h b/util.h
index 6dec14b..5e5978a 100644
--- a/util.h
+++ b/util.h
@@ -211,7 +211,7 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type,
 	       const void *sa, socklen_t sl,
 	       const char *ifname, bool v6only);
 int sock_unix(char *sock_path);
-void sock_probe_mem(struct ctx *c);
+void sock_probe_features(struct ctx *c);
 long timespec_diff_ms(const struct timespec *a, const struct timespec *b);
 int64_t timespec_diff_us(const struct timespec *a, const struct timespec *b);
 void bitmap_set(uint8_t *map, unsigned bit);