summaryrefslogtreecommitdiffstats
path: root/fs/dcache.c
diff options
context:
space:
mode:
authorAl Viro <viro@zeniv.linux.org.uk>2013-09-29 22:06:07 -0400
committerAl Viro <viro@zeniv.linux.org.uk>2013-11-09 00:16:19 -0500
commit48a066e72d970a3e225a9c18690d570c736fc455 (patch)
tree9a1861c1be4309cf69964742d238eadd5d0b1832 /fs/dcache.c
parent42c326082d8a2c91506f951ace638deae1faf083 (diff)
downloadlinux-48a066e72d970a3e225a9c18690d570c736fc455.tar.bz2
RCU'd vfsmounts
* RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'fs/dcache.c')
-rw-r--r--fs/dcache.c20
1 files changed, 14 insertions, 6 deletions
diff --git a/fs/dcache.c b/fs/dcache.c
index eb0978da1bd4..aafa2a146434 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2887,24 +2887,28 @@ static int prepend_path(const struct path *path,
struct vfsmount *vfsmnt = path->mnt;
struct mount *mnt = real_mount(vfsmnt);
int error = 0;
- unsigned seq = 0;
+ unsigned seq, m_seq = 0;
char *bptr;
int blen;
- br_read_lock(&vfsmount_lock);
rcu_read_lock();
+restart_mnt:
+ read_seqbegin_or_lock(&mount_lock, &m_seq);
+ seq = 0;
restart:
bptr = *buffer;
blen = *buflen;
+ error = 0;
read_seqbegin_or_lock(&rename_lock, &seq);
while (dentry != root->dentry || vfsmnt != root->mnt) {
struct dentry * parent;
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
+ struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
/* Global root? */
- if (mnt_has_parent(mnt)) {
- dentry = mnt->mnt_mountpoint;
- mnt = mnt->mnt_parent;
+ if (mnt != parent) {
+ dentry = ACCESS_ONCE(mnt->mnt_mountpoint);
+ mnt = parent;
vfsmnt = &mnt->mnt;
continue;
}
@@ -2938,7 +2942,11 @@ restart:
goto restart;
}
done_seqretry(&rename_lock, seq);
- br_read_unlock(&vfsmount_lock);
+ if (need_seqretry(&mount_lock, m_seq)) {
+ m_seq = 1;
+ goto restart_mnt;
+ }
+ done_seqretry(&mount_lock, m_seq);
if (error >= 0 && bptr == *buffer) {
if (--blen < 0)