--- /dev/null
+From ee2e3f50629f17b0752b55b2566c15ce8dafb557 Mon Sep 17 00:00:00 2001
+From: Christian Brauner <christian.brauner@ubuntu.com>
+Date: Sat, 6 Mar 2021 11:10:10 +0100
+Subject: mount: fix mounting of detached mounts onto targets that reside on shared mounts
+
+From: Christian Brauner <christian.brauner@ubuntu.com>
+
+commit ee2e3f50629f17b0752b55b2566c15ce8dafb557 upstream.
+
+Creating a series of detached mounts, attaching them to the filesystem,
+and unmounting them can be used to trigger an integer overflow in
+ns->mounts causing the kernel to block any new mounts in count_mounts()
+and returning ENOSPC because it falsely assumes that the maximum number
+of mounts in the mount namespace has been reached, i.e. it thinks it
+can't fit the new mounts into the mount namespace anymore.
+
+Depending on the number of mounts in your system, this can be reproduced
+on any kernel that supportes open_tree() and move_mount() by compiling
+and running the following program:
+
+ /* SPDX-License-Identifier: LGPL-2.1+ */
+
+ #define _GNU_SOURCE
+ #include <errno.h>
+ #include <fcntl.h>
+ #include <getopt.h>
+ #include <limits.h>
+ #include <stdbool.h>
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <string.h>
+ #include <sys/mount.h>
+ #include <sys/stat.h>
+ #include <sys/syscall.h>
+ #include <sys/types.h>
+ #include <unistd.h>
+
+ /* open_tree() */
+ #ifndef OPEN_TREE_CLONE
+ #define OPEN_TREE_CLONE 1
+ #endif
+
+ #ifndef OPEN_TREE_CLOEXEC
+ #define OPEN_TREE_CLOEXEC O_CLOEXEC
+ #endif
+
+ #ifndef __NR_open_tree
+ #if defined __alpha__
+ #define __NR_open_tree 538
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_open_tree 4428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_open_tree 6428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_open_tree 5428
+ #endif
+ #elif defined __ia64__
+ #define __NR_open_tree (428 + 1024)
+ #else
+ #define __NR_open_tree 428
+ #endif
+ #endif
+
+ /* move_mount() */
+ #ifndef MOVE_MOUNT_F_EMPTY_PATH
+ #define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
+ #endif
+
+ #ifndef __NR_move_mount
+ #if defined __alpha__
+ #define __NR_move_mount 539
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_move_mount 4429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_move_mount 6429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_move_mount 5429
+ #endif
+ #elif defined __ia64__
+ #define __NR_move_mount (428 + 1024)
+ #else
+ #define __NR_move_mount 429
+ #endif
+ #endif
+
+ static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+ {
+ return syscall(__NR_open_tree, dfd, filename, flags);
+ }
+
+ static inline int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd,
+ const char *to_pathname, unsigned int flags)
+ {
+ return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags);
+ }
+
+ static bool is_shared_mountpoint(const char *path)
+ {
+ bool shared = false;
+ FILE *f = NULL;
+ char *line = NULL;
+ int i;
+ size_t len = 0;
+
+ f = fopen("/proc/self/mountinfo", "re");
+ if (!f)
+ return 0;
+
+ while (getline(&line, &len, f) > 0) {
+ char *slider1, *slider2;
+
+ for (slider1 = line, i = 0; slider1 && i < 4; i++)
+ slider1 = strchr(slider1 + 1, ' ');
+
+ if (!slider1)
+ continue;
+
+ slider2 = strchr(slider1 + 1, ' ');
+ if (!slider2)
+ continue;
+
+ *slider2 = '\0';
+ if (strcmp(slider1 + 1, path) == 0) {
+ /* This is the path. Is it shared? */
+ slider1 = strchr(slider2 + 1, ' ');
+ if (slider1 && strstr(slider1, "shared:")) {
+ shared = true;
+ break;
+ }
+ }
+ }
+ fclose(f);
+ free(line);
+
+ return shared;
+ }
+
+ static void usage(void)
+ {
+ const char *text = "mount-new [--recursive] <base-dir>\n";
+ fprintf(stderr, "%s", text);
+ _exit(EXIT_SUCCESS);
+ }
+
+ #define exit_usage(format, ...) \
+ ({ \
+ fprintf(stderr, format "\n", ##__VA_ARGS__); \
+ usage(); \
+ })
+
+ #define exit_log(format, ...) \
+ ({ \
+ fprintf(stderr, format "\n", ##__VA_ARGS__); \
+ exit(EXIT_FAILURE); \
+ })
+
+ static const struct option longopts[] = {
+ {"help", no_argument, 0, 'a'},
+ { NULL, no_argument, 0, 0 },
+ };
+
+ int main(int argc, char *argv[])
+ {
+ int exit_code = EXIT_SUCCESS, index = 0;
+ int dfd, fd_tree, new_argc, ret;
+ char *base_dir;
+ char *const *new_argv;
+ char target[PATH_MAX];
+
+ while ((ret = getopt_long_only(argc, argv, "", longopts, &index)) != -1) {
+ switch (ret) {
+ case 'a':
+ /* fallthrough */
+ default:
+ usage();
+ }
+ }
+
+ new_argv = &argv[optind];
+ new_argc = argc - optind;
+ if (new_argc < 1)
+ exit_usage("Missing base directory\n");
+ base_dir = new_argv[0];
+
+ if (*base_dir != '/')
+ exit_log("Please specify an absolute path");
+
+ /* Ensure that target is a shared mountpoint. */
+ if (!is_shared_mountpoint(base_dir))
+ exit_log("Please ensure that \"%s\" is a shared mountpoint", base_dir);
+
+ dfd = open(base_dir, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+ if (dfd < 0)
+ exit_log("%m - Failed to open base directory \"%s\"", base_dir);
+
+ ret = mkdirat(dfd, "detached-move-mount", 0755);
+ if (ret < 0)
+ exit_log("%m - Failed to create required temporary directories");
+
+ ret = snprintf(target, sizeof(target), "%s/detached-move-mount", base_dir);
+ if (ret < 0 || (size_t)ret >= sizeof(target))
+ exit_log("%m - Failed to assemble target path");
+
+ /*
+ * Having a mount table with 10000 mounts is already quite excessive
+ * and shoult account even for weird test systems.
+ */
+ for (size_t i = 0; i < 10000; i++) {
+ fd_tree = sys_open_tree(dfd, "detached-move-mount",
+ OPEN_TREE_CLONE |
+ OPEN_TREE_CLOEXEC |
+ AT_EMPTY_PATH);
+ if (fd_tree < 0) {
+ fprintf(stderr, "%m - Failed to open %d(detached-move-mount)", dfd);
+ exit_code = EXIT_FAILURE;
+ break;
+ }
+
+ ret = sys_move_mount(fd_tree, "", dfd, "detached-move-mount", MOVE_MOUNT_F_EMPTY_PATH);
+ if (ret < 0) {
+ if (errno == ENOSPC)
+ fprintf(stderr, "%m - Buggy mount counting");
+ else
+ fprintf(stderr, "%m - Failed to attach mount to %d(detached-move-mount)", dfd);
+ exit_code = EXIT_FAILURE;
+ break;
+ }
+ close(fd_tree);
+
+ ret = umount2(target, MNT_DETACH);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to unmount %s", target);
+ exit_code = EXIT_FAILURE;
+ break;
+ }
+ }
+
+ (void)unlinkat(dfd, "detached-move-mount", AT_REMOVEDIR);
+ close(dfd);
+
+ exit(exit_code);
+ }
+
+and wait for the kernel to refuse any new mounts by returning ENOSPC.
+How many iterations are needed depends on the number of mounts in your
+system. Assuming you have something like 50 mounts on a standard system
+it should be almost instantaneous.
+
+The root cause of this is that detached mounts aren't handled correctly
+when source and target mount are identical and reside on a shared mount
+causing a broken mount tree where the detached source itself is
+propagated which propagation prevents for regular bind-mounts and new
+mounts. This ultimately leads to a miscalculation of the number of
+mounts in the mount namespace.
+
+Detached mounts created via
+open_tree(fd, path, OPEN_TREE_CLONE)
+are essentially like an unattached new mount, or an unattached
+bind-mount. They can then later on be attached to the filesystem via
+move_mount() which calls into attach_recursive_mount(). Part of
+attaching it to the filesystem is making sure that mounts get correctly
+propagated in case the destination mountpoint is MS_SHARED, i.e. is a
+shared mountpoint. This is done by calling into propagate_mnt() which
+walks the list of peers calling propagate_one() on each mount in this
+list making sure it receives the propagation event.
+The propagate_one() functions thereby skips both new mounts and bind
+mounts to not propagate them "into themselves". Both are identified by
+checking whether the mount is already attached to any mount namespace in
+mnt->mnt_ns. The is what the IS_MNT_NEW() helper is responsible for.
+
+However, detached mounts have an anonymous mount namespace attached to
+them stashed in mnt->mnt_ns which means that IS_MNT_NEW() doesn't
+realize they need to be skipped causing the mount to propagate "into
+itself" breaking the mount table and causing a disconnect between the
+number of mounts recorded as being beneath or reachable from the target
+mountpoint and the number of mounts actually recorded/counted in
+ns->mounts ultimately causing an overflow which in turn prevents any new
+mounts via the ENOSPC issue.
+
+So teach propagation to handle detached mounts by making it aware of
+them. I've been tracking this issue down for the last couple of days and
+then verifying that the fix is correct by
+unmounting everything in my current mount table leaving only /proc and
+/sys mounted and running the reproducer above overnight verifying the
+number of mounts counted in ns->mounts. With this fix the counts are
+correct and the ENOSPC issue can't be reproduced.
+
+This change will only have an effect on mounts created with the new
+mount API since detached mounts cannot be created with the old mount API
+so regressions are extremely unlikely.
+
+Link: https://lore.kernel.org/r/20210306101010.243666-1-christian.brauner@ubuntu.com
+Fixes: 2db154b3ea8e ("vfs: syscall: Add move_mount(2) to move mounts around")
+Cc: David Howells <dhowells@redhat.com>
+Cc: Al Viro <viro@zeniv.linux.org.uk>
+Cc: linux-fsdevel@vger.kernel.org
+Cc: <stable@vger.kernel.org>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/pnode.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/fs/pnode.h
++++ b/fs/pnode.h
+@@ -12,7 +12,7 @@
+
+ #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
+ #define IS_MNT_SLAVE(m) ((m)->mnt_master)
+-#define IS_MNT_NEW(m) (!(m)->mnt_ns)
++#define IS_MNT_NEW(m) (!(m)->mnt_ns || is_anon_ns((m)->mnt_ns))
+ #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
+ #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
+ #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
--- /dev/null
+From 9b1ea29bc0d7b94d420f96a0f4121403efc3dd85 Mon Sep 17 00:00:00 2001
+From: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Wed, 10 Mar 2021 10:18:04 -0800
+Subject: Revert "mm, slub: consider rest of partial list if acquire_slab() fails"
+
+From: Linus Torvalds <torvalds@linux-foundation.org>
+
+commit 9b1ea29bc0d7b94d420f96a0f4121403efc3dd85 upstream.
+
+This reverts commit 8ff60eb052eeba95cfb3efe16b08c9199f8121cf.
+
+The kernel test robot reports a huge performance regression due to the
+commit, and the reason seems fairly straightforward: when there is
+contention on the page list (which is what causes acquire_slab() to
+fail), we do _not_ want to just loop and try again, because that will
+transfer the contention to the 'n->list_lock' spinlock we hold, and
+just make things even worse.
+
+This is admittedly likely a problem only on big machines - the kernel
+test robot report comes from a 96-thread dual socket Intel Xeon Gold
+6252 setup, but the regression there really is quite noticeable:
+
+ -47.9% regression of stress-ng.rawpkt.ops_per_sec
+
+and the commit that was marked as being fixed (7ced37197196: "slub:
+Acquire_slab() avoid loop") actually did the loop exit early very
+intentionally (the hint being that "avoid loop" part of that commit
+message), exactly to avoid this issue.
+
+The correct thing to do may be to pick some kind of reasonable middle
+ground: instead of breaking out of the loop on the very first sign of
+contention, or trying over and over and over again, the right thing may
+be to re-try _once_, and then give up on the second failure (or pick
+your favorite value for "once"..).
+
+Reported-by: kernel test robot <oliver.sang@intel.com>
+Link: https://lore.kernel.org/lkml/20210301080404.GF12822@xsang-OptiPlex-9020/
+Cc: Jann Horn <jannh@google.com>
+Cc: David Rientjes <rientjes@google.com>
+Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
+Acked-by: Christoph Lameter <cl@linux.com>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ mm/slub.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/mm/slub.c
++++ b/mm/slub.c
+@@ -1887,7 +1887,7 @@ static void *get_partial_node(struct kme
+
+ t = acquire_slab(s, n, page, object == NULL, &objects);
+ if (!t)
+- continue; /* cmpxchg raced */
++ break;
+
+ available += objects;
+ if (!object) {
projects / thirdparty / kernel / stable-queue.git / commitdiff
