[PATCH RESEND v2 45/51] selftests/proc: check a sysctl listing while entries come and go

[Christian Brauner]

List /proc/sys/net/ipv4/conf of a new network namespace in two pieces:

- with a buffer that holds the dots and "all", register a tun device
  whose name sorts first, finish the listing: "all" is listed once

- with that device registered and a buffer that holds the dots and it,
  unregister it, finish the listing: "all" is still listed

Both fail without the fix, the first lists "all" twice, the second not
at all.

Signed-off-by: Christian Brauner (Amutable) <brauner@xxxxxxxxxx>
---
 tools/testing/selftests/proc/.gitignore            |   1 +
 tools/testing/selftests/proc/Makefile              |   1 +
 .../selftests/proc/proc-sysctl-readdir-churn.c     | 152 +++++++++++++++++++++
 3 files changed, 154 insertions(+)

diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 8520c7878ea2..5b5e24e39cbd 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -25,4 +25,5 @@
 /self
 /setns-dcache
 /setns-sysvipc
+/proc-sysctl-readdir-churn
 /thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index e0c0d313f4d0..dae09f333455 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -30,6 +30,7 @@ TEST_GEN_PROGS += setns-sysvipc
 TEST_GEN_PROGS += thread-self
 TEST_GEN_PROGS += proc-multiple-procfs
 TEST_GEN_PROGS += proc-fsconfig-hidepid
+TEST_GEN_PROGS += proc-sysctl-readdir-churn
 TEST_GEN_PROGS += proc-pidns
 
 include ../lib.mk
diff --git a/tools/testing/selftests/proc/proc-sysctl-readdir-churn.c b/tools/testing/selftests/proc/proc-sysctl-readdir-churn.c
new file mode 100644
index 000000000000..b2ad097b464a
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-sysctl-readdir-churn.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A listing of a /proc/sys directory that takes more than one getdents64()
+ * must not show an entry twice or skip one when an entry is registered or
+ * unregistered in between. /proc/sys/net/ipv4/conf/<dev> of a tun device
+ * comes and goes with the device.
+ */
+#define _GNU_SOURCE
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <sched.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define CONF_DIR	"/proc/sys/net/ipv4/conf"
+#define TUN_NAME	"a0"		/* sorts before "all" */
+#define TUN_PATH	CONF_DIR "/" TUN_NAME
+#define SMALL_BUF	80		/* ".", ".." and one short name */
+#define NAMES		64
+
+static int tun_open(const char *name)
+{
+	struct ifreq ifr = {};
+	int fd;
+
+	fd = open("/dev/net/tun", O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		return -1;
+	strncpy(ifr.ifr_name, name, IFNAMSIZ - 1);
+	ifr.ifr_flags = IFF_TUN | IFF_NO_PI;
+	if (ioctl(fd, TUNSETIFF, &ifr)) {
+		close(fd);
+		return -1;
+	}
+	return fd;
+}
+
+/* one getdents64() into @buf, the names appended to @names */
+static int list(int fd, char *buf, size_t size, char names[][NAME_MAX + 1],
+		int *n)
+{
+	long ret, off;
+	int got = 0;
+
+	ret = syscall(__NR_getdents64, fd, buf, size);
+	if (ret < 0)
+		return -errno;
+	for (off = 0; off < ret;) {
+		struct dirent64 *d = (void *)(buf + off);
+
+		if (*n < NAMES)
+			strcpy(names[(*n)++], d->d_name);
+		got++;
+		off += d->d_reclen;
+	}
+	return got;
+}
+
+static int count(char names[][NAME_MAX + 1], int n, const char *name)
+{
+	int i, c = 0;
+
+	for (i = 0; i < n; i++)
+		if (!strcmp(names[i], name))
+			c++;
+	return c;
+}
+
+FIXTURE(sysctl_readdir) {
+	int dir;
+	int n;
+	char names[NAMES][NAME_MAX + 1];
+	char buf[65536];
+};
+
+FIXTURE_SETUP(sysctl_readdir)
+{
+	int tun;
+
+	if (unshare(CLONE_NEWNET))
+		SKIP(return, "unshare(CLONE_NEWNET): %s", strerror(errno));
+	tun = open("/dev/net/tun", O_RDWR | O_CLOEXEC);
+	if (tun < 0)
+		SKIP(return, "/dev/net/tun: %s", strerror(errno));
+	close(tun);
+	self->dir = open(CONF_DIR, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	if (self->dir < 0)
+		SKIP(return, CONF_DIR ": %s", strerror(errno));
+	self->n = 0;
+}
+
+FIXTURE_TEARDOWN(sysctl_readdir)
+{
+	close(self->dir);
+}
+
+/* a device registered in front of the position doesn't repeat an entry */
+TEST_F(sysctl_readdir, register_in_front)
+{
+	int tun;
+
+	/* ".", ".." and "all", "default" doesn't fit */
+	ASSERT_EQ(list(self->dir, self->buf, SMALL_BUF, self->names, &self->n), 3);
+	ASSERT_EQ(count(self->names, self->n, "all"), 1);
+
+	tun = tun_open(TUN_NAME);
+	ASSERT_GE(tun, 0);
+	ASSERT_EQ(access(TUN_PATH, F_OK), 0);
+
+	while (list(self->dir, self->buf, sizeof(self->buf), self->names,
+		    &self->n) > 0)
+		;
+	EXPECT_EQ(count(self->names, self->n, "all"), 1);
+	EXPECT_EQ(count(self->names, self->n, "default"), 1);
+	EXPECT_EQ(count(self->names, self->n, "lo"), 1);
+	close(tun);
+}
+
+/* a device unregistered in front of the position doesn't skip an entry */
+TEST_F(sysctl_readdir, unregister_in_front)
+{
+	int tun;
+
+	tun = tun_open(TUN_NAME);
+	ASSERT_GE(tun, 0);
+	ASSERT_EQ(access(TUN_PATH, F_OK), 0);
+
+	/* ".", ".." and the device, "all" doesn't fit */
+	ASSERT_EQ(list(self->dir, self->buf, SMALL_BUF, self->names, &self->n), 3);
+	ASSERT_EQ(count(self->names, self->n, TUN_NAME), 1);
+
+	/* closing the device unregisters its sysctls under RTNL */
+	close(tun);
+	ASSERT_EQ(access(TUN_PATH, F_OK), -1);
+
+	while (list(self->dir, self->buf, sizeof(self->buf), self->names,
+		    &self->n) > 0)
+		;
+	EXPECT_EQ(count(self->names, self->n, "all"), 1);
+	EXPECT_EQ(count(self->names, self->n, "default"), 1);
+	EXPECT_EQ(count(self->names, self->n, "lo"), 1);
+}
+
+TEST_HARNESS_MAIN

-- 
2.53.0