mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-26 08:35:06 +07:00
9f6c61f96f
If mounts are deleted after a read(2) call on /proc/self/mounts (or its kin), the subsequent read(2) could miss a mount that comes after the deleted one in the list. This is because the file position is interpreted as the number mount entries from the start of the list. E.g. first read gets entries #0 to #9; the seq file index will be 10. Then entry #5 is deleted, resulting in #10 becoming #9 and #11 becoming #10, etc... The next read will continue from entry #10, and #9 is missed. Solve this by adding a cursor entry for each open instance. Taking the global namespace_sem for write seems excessive, since we are only dealing with a per-namespace list. Instead add a per-namespace spinlock and use that together with namespace_sem taken for read to protect against concurrent modification of the mount list. This may reduce parallelism of is_local_mountpoint(), but it's hardly a big contention point. We could also use RCU freeing of cursors to make traversal not need additional locks, if that turns out to be neceesary. Only move the cursor once for each read (cursor is not added on open) to minimize cacheline invalidation. When EOF is reached, the cursor is taken off the list, in order to prevent an excessive number of cursors due to inactive open file descriptors. Reported-by: Karel Zak <kzak@redhat.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
115 lines
3.6 KiB
C
115 lines
3.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
*
|
|
* Definitions for mount interface. This describes the in the kernel build
|
|
* linkedlist with mounted filesystems.
|
|
*
|
|
* Author: Marco van Wieringen <mvw@planets.elm.net>
|
|
*
|
|
*/
|
|
#ifndef _LINUX_MOUNT_H
|
|
#define _LINUX_MOUNT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/nodemask.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/seqlock.h>
|
|
#include <linux/atomic.h>
|
|
|
|
struct super_block;
|
|
struct vfsmount;
|
|
struct dentry;
|
|
struct mnt_namespace;
|
|
struct fs_context;
|
|
|
|
#define MNT_NOSUID 0x01
|
|
#define MNT_NODEV 0x02
|
|
#define MNT_NOEXEC 0x04
|
|
#define MNT_NOATIME 0x08
|
|
#define MNT_NODIRATIME 0x10
|
|
#define MNT_RELATIME 0x20
|
|
#define MNT_READONLY 0x40 /* does the user want this to be r/o? */
|
|
|
|
#define MNT_SHRINKABLE 0x100
|
|
#define MNT_WRITE_HOLD 0x200
|
|
|
|
#define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */
|
|
#define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */
|
|
/*
|
|
* MNT_SHARED_MASK is the set of flags that should be cleared when a
|
|
* mount becomes shared. Currently, this is only the flag that says a
|
|
* mount cannot be bind mounted, since this is how we create a mount
|
|
* that shares events with another mount. If you add a new MNT_*
|
|
* flag, consider how it interacts with shared mounts.
|
|
*/
|
|
#define MNT_SHARED_MASK (MNT_UNBINDABLE)
|
|
#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
|
|
| MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
|
|
| MNT_READONLY)
|
|
#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
|
|
|
|
#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
|
|
MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
|
|
MNT_CURSOR)
|
|
|
|
#define MNT_INTERNAL 0x4000
|
|
|
|
#define MNT_LOCK_ATIME 0x040000
|
|
#define MNT_LOCK_NOEXEC 0x080000
|
|
#define MNT_LOCK_NOSUID 0x100000
|
|
#define MNT_LOCK_NODEV 0x200000
|
|
#define MNT_LOCK_READONLY 0x400000
|
|
#define MNT_LOCKED 0x800000
|
|
#define MNT_DOOMED 0x1000000
|
|
#define MNT_SYNC_UMOUNT 0x2000000
|
|
#define MNT_MARKED 0x4000000
|
|
#define MNT_UMOUNT 0x8000000
|
|
#define MNT_CURSOR 0x10000000
|
|
|
|
struct vfsmount {
|
|
struct dentry *mnt_root; /* root of the mounted tree */
|
|
struct super_block *mnt_sb; /* pointer to superblock */
|
|
int mnt_flags;
|
|
} __randomize_layout;
|
|
|
|
struct file; /* forward dec */
|
|
struct path;
|
|
|
|
extern int mnt_want_write(struct vfsmount *mnt);
|
|
extern int mnt_want_write_file(struct file *file);
|
|
extern int mnt_clone_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write_file(struct file *file);
|
|
extern void mntput(struct vfsmount *mnt);
|
|
extern struct vfsmount *mntget(struct vfsmount *mnt);
|
|
extern struct vfsmount *mnt_clone_internal(const struct path *path);
|
|
extern bool __mnt_is_readonly(struct vfsmount *mnt);
|
|
extern bool mnt_may_suid(struct vfsmount *mnt);
|
|
|
|
struct path;
|
|
extern struct vfsmount *clone_private_mount(const struct path *path);
|
|
extern int __mnt_want_write(struct vfsmount *);
|
|
extern void __mnt_drop_write(struct vfsmount *);
|
|
|
|
struct file_system_type;
|
|
extern struct vfsmount *fc_mount(struct fs_context *fc);
|
|
extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
|
|
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
|
|
int flags, const char *name,
|
|
void *data);
|
|
extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
|
|
struct file_system_type *type,
|
|
const char *name, void *data);
|
|
|
|
extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
|
|
extern void mark_mounts_for_expiry(struct list_head *mounts);
|
|
|
|
extern dev_t name_to_dev_t(const char *name);
|
|
|
|
extern unsigned int sysctl_mount_max;
|
|
|
|
extern bool path_is_mountpoint(const struct path *path);
|
|
|
|
#endif /* _LINUX_MOUNT_H */
|