summaryrefslogtreecommitdiff
path: root/fs/mount.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-01-08 10:57:34 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2024-01-08 10:57:34 -0800
commit8c9440fea77440772542d6dbcb5c36182495c164 (patch)
treec344e1f8ff4ecaa85e91abf275f49b1753d54341 /fs/mount.h
parent3f6984e7301f4a37285cc5962f97c83c7c3b8239 (diff)
parent5bd3cf8cbc8a286308ef3f40656659d5abc89995 (diff)
downloadlwn-8c9440fea77440772542d6dbcb5c36182495c164.tar.gz
lwn-8c9440fea77440772542d6dbcb5c36182495c164.zip
Merge tag 'vfs-6.8.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs mount updates from Christian Brauner: "This contains the work to retrieve detailed information about mounts via two new system calls. This is hopefully the beginning of the end of the saga that started with fsinfo() years ago. The LWN articles in [1] and [2] can serve as a summary so we can avoid rehashing everything here. At LSFMM in May 2022 we got into a room and agreed on what we want to do about fsinfo(). Basically, split it into pieces. This is the first part of that agreement. Specifically, it is concerned with retrieving information about mounts. So this only concerns the mount information retrieval, not the mount table change notification, or the extended filesystem specific mount option work. That is separate work. Currently mounts have a 32bit id. Mount ids are already in heavy use by libmount and other low-level userspace but they can't be relied upon because they're recycled very quickly. We agreed that mounts should carry a unique 64bit id by which they can be referenced directly. This is now implemented as part of this work. The new 64bit mount id is exposed in statx() through the new STATX_MNT_ID_UNIQUE flag. If the flag isn't raised the old mount id is returned. If it is raised and the kernel supports the new 64bit mount id the flag is raised in the result mask and the new 64bit mount id is returned. New and old mount ids do not overlap so they cannot be conflated. Two new system calls are introduced that operate on the 64bit mount id: statmount() and listmount(). A summary of the api and usage can be found on LWN as well (cf. [3]) but of course, I'll provide a summary here as well. Both system calls rely on struct mnt_id_req. Which is the request struct used to pass the 64bit mount id identifying the mount to operate on. It is extensible to allow for the addition of new parameters and for future use in other apis that make use of mount ids. statmount() mimicks the semantics of statx() and exposes a set flags that userspace may raise in mnt_id_req to request specific information to be retrieved. A statmount() call returns a struct statmount filled in with information about the requested mount. Supported requests are indicated by raising the request flag passed in struct mnt_id_req in the @mask argument in struct statmount. Currently we do support: - STATMOUNT_SB_BASIC: Basic filesystem info - STATMOUNT_MNT_BASIC Mount information (mount id, parent mount id, mount attributes etc) - STATMOUNT_PROPAGATE_FROM Propagation from what mount in current namespace - STATMOUNT_MNT_ROOT Path of the root of the mount (e.g., mount --bind /bla /mnt returns /bla) - STATMOUNT_MNT_POINT Path of the mount point (e.g., mount --bind /bla /mnt returns /mnt) - STATMOUNT_FS_TYPE Name of the filesystem type as the magic number isn't enough due to submounts The string options STATMOUNT_MNT_{ROOT,POINT} and STATMOUNT_FS_TYPE are appended to the end of the struct. Userspace can use the offsets in @fs_type, @mnt_root, and @mnt_point to reference those strings easily. The struct statmount reserves quite a bit of space currently for future extensibility. This isn't really a problem and if this bothers us we can just send a follow-up pull request during this cycle. listmount() is given a 64bit mount id via mnt_id_req just as statmount(). It takes a buffer and a size to return an array of the 64bit ids of the child mounts of the requested mount. Userspace can thus choose to either retrieve child mounts for a mount in batches or iterate through the child mounts. For most use-cases it will be sufficient to just leave space for a few child mounts. But for big mount tables having an iterator is really helpful. Iterating through a mount table works by setting @param in mnt_id_req to the mount id of the last child mount retrieved in the previous listmount() call" Link: https://lwn.net/Articles/934469 [1] Link: https://lwn.net/Articles/829212 [2] Link: https://lwn.net/Articles/950569 [3] * tag 'vfs-6.8.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: add selftest for statmount/listmount fs: keep struct mnt_id_req extensible wire up syscalls for statmount/listmount add listmount(2) syscall statmount: simplify string option retrieval statmount: simplify numeric option retrieval add statmount(2) syscall namespace: extract show_path() helper mounts: keep list of mounts in an rbtree add unique mount ID
Diffstat (limited to 'fs/mount.h')
-rw-r--r--fs/mount.h27
1 files changed, 16 insertions, 11 deletions
diff --git a/fs/mount.h b/fs/mount.h
index 130c07c2f8d2..4a42fc68f4cc 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -8,19 +8,13 @@
struct mnt_namespace {
struct ns_common ns;
struct mount * root;
- /*
- * Traversal and modification of .list is protected by either
- * - taking namespace_sem for write, OR
- * - taking namespace_sem for read AND taking .ns_lock.
- */
- struct list_head list;
- spinlock_t ns_lock;
+ struct rb_root mounts; /* Protected by namespace_sem */
struct user_namespace *user_ns;
struct ucounts *ucounts;
u64 seq; /* Sequence number to prevent loops */
wait_queue_head_t poll;
u64 event;
- unsigned int mounts; /* # of mounts in the namespace */
+ unsigned int nr_mounts; /* # of mounts in the namespace */
unsigned int pending_mounts;
} __randomize_layout;
@@ -55,7 +49,10 @@ struct mount {
struct list_head mnt_child; /* and going through their mnt_child */
struct list_head mnt_instance; /* mount instance on sb->s_mounts */
const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */
- struct list_head mnt_list;
+ union {
+ struct rb_node mnt_node; /* Under ns->mounts */
+ struct list_head mnt_list;
+ };
struct list_head mnt_expire; /* link in fs-specific expiry list */
struct list_head mnt_share; /* circular list of shared mounts */
struct list_head mnt_slave_list;/* list of slave mounts */
@@ -72,7 +69,8 @@ struct mount {
struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
__u32 mnt_fsnotify_mask;
#endif
- int mnt_id; /* mount identifier */
+ int mnt_id; /* mount identifier, reused */
+ u64 mnt_id_unique; /* mount ID unique until reboot */
int mnt_group_id; /* peer group identifier */
int mnt_expiry_mark; /* true if marked for expiry */
struct hlist_head mnt_pins;
@@ -127,7 +125,6 @@ struct proc_mounts {
struct mnt_namespace *ns;
struct path root;
int (*show)(struct seq_file *, struct vfsmount *);
- struct mount cursor;
};
extern const struct seq_operations mounts_op;
@@ -146,4 +143,12 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
return ns->seq == 0;
}
+static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+{
+ WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
+ mnt->mnt.mnt_flags &= ~MNT_ONRB;
+ rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
+ list_add_tail(&mnt->mnt_list, dt_list);
+}
+
extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);