summaryrefslogtreecommitdiffstats
path: root/kernel/fs/notify
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fs/notify')
-rw-r--r--kernel/fs/notify/dnotify/dnotify.c14
-rw-r--r--kernel/fs/notify/fanotify/fanotify_user.c8
-rw-r--r--kernel/fs/notify/fdinfo.c12
-rw-r--r--kernel/fs/notify/fsnotify.c11
-rw-r--r--kernel/fs/notify/fsnotify.h21
-rw-r--r--kernel/fs/notify/inode_mark.c40
-rw-r--r--kernel/fs/notify/inotify/inotify_user.c18
-rw-r--r--kernel/fs/notify/mark.c113
-rw-r--r--kernel/fs/notify/vfsmount_mark.c19
9 files changed, 141 insertions, 115 deletions
diff --git a/kernel/fs/notify/dnotify/dnotify.c b/kernel/fs/notify/dnotify/dnotify.c
index 44523f4a6..6faaf710e 100644
--- a/kernel/fs/notify/dnotify/dnotify.c
+++ b/kernel/fs/notify/dnotify/dnotify.c
@@ -154,6 +154,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
struct dnotify_struct *dn;
struct dnotify_struct **prev;
struct inode *inode;
+ bool free = false;
inode = file_inode(filp);
if (!S_ISDIR(inode->i_mode))
@@ -182,11 +183,15 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
/* nothing else could have found us thanks to the dnotify_groups
mark_mutex */
- if (dn_mark->dn == NULL)
- fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
+ if (dn_mark->dn == NULL) {
+ fsnotify_detach_mark(fsn_mark);
+ free = true;
+ }
mutex_unlock(&dnotify_group->mark_mutex);
+ if (free)
+ fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
}
@@ -362,9 +367,10 @@ out:
spin_unlock(&fsn_mark->lock);
if (destroy)
- fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
-
+ fsnotify_detach_mark(fsn_mark);
mutex_unlock(&dnotify_group->mark_mutex);
+ if (destroy)
+ fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
out_err:
if (new_fsn_mark)
diff --git a/kernel/fs/notify/fanotify/fanotify_user.c b/kernel/fs/notify/fanotify/fanotify_user.c
index cf275500a..8e8e6bcd1 100644
--- a/kernel/fs/notify/fanotify/fanotify_user.c
+++ b/kernel/fs/notify/fanotify/fanotify_user.c
@@ -529,8 +529,10 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (destroy_mark)
- fsnotify_destroy_mark_locked(fsn_mark, group);
+ fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
+ if (destroy_mark)
+ fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
if (removed & real_mount(mnt)->mnt_fsnotify_mask)
@@ -557,8 +559,10 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (destroy_mark)
- fsnotify_destroy_mark_locked(fsn_mark, group);
+ fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
+ if (destroy_mark)
+ fsnotify_free_mark(fsn_mark);
/* matches the fsnotify_find_inode_mark() */
fsnotify_put_mark(fsn_mark);
diff --git a/kernel/fs/notify/fdinfo.c b/kernel/fs/notify/fdinfo.c
index 58b7cdb63..fd98e5100 100644
--- a/kernel/fs/notify/fdinfo.c
+++ b/kernel/fs/notify/fdinfo.c
@@ -76,15 +76,23 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
struct inotify_inode_mark *inode_mark;
struct inode *inode;
- if (!(mark->flags & (FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_INODE)))
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE) ||
+ !(mark->flags & FSNOTIFY_MARK_FLAG_INODE))
return;
inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
inode = igrab(mark->inode);
if (inode) {
+ /*
+ * IN_ALL_EVENTS represents all of the mask bits
+ * that we expose to userspace. There is at
+ * least one bit (FS_EVENT_ON_CHILD) which is
+ * used only internally to the kernel.
+ */
+ u32 mask = mark->mask & IN_ALL_EVENTS;
seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
- mark->mask, mark->ignored_mask);
+ mask, mark->ignored_mask);
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
diff --git a/kernel/fs/notify/fsnotify.c b/kernel/fs/notify/fsnotify.c
index dd3fb0b17..db39de2dd 100644
--- a/kernel/fs/notify/fsnotify.c
+++ b/kernel/fs/notify/fsnotify.c
@@ -26,7 +26,6 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-#include "../mount.h"
/*
* Clear all of the marks on an inode when it is being evicted from core
@@ -205,6 +204,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
mnt = NULL;
/*
+ * Optimization: srcu_read_lock() has a memory barrier which can
+ * be expensive. It protects walking the *_fsnotify_marks lists.
+ * However, if we do not walk the lists, we do not have to do
+ * SRCU because we have no references to any objects and do not
+ * need SRCU to keep them "alive".
+ */
+ if (hlist_empty(&to_tell->i_fsnotify_marks) &&
+ (!mnt || hlist_empty(&mnt->mnt_fsnotify_marks)))
+ return 0;
+ /*
* if this is a modify event we may need to clear the ignored masks
* otherwise return if neither the inode nor the vfsmount care about
* this type of event.
diff --git a/kernel/fs/notify/fsnotify.h b/kernel/fs/notify/fsnotify.h
index 13a00be51..b44c68a85 100644
--- a/kernel/fs/notify/fsnotify.h
+++ b/kernel/fs/notify/fsnotify.h
@@ -6,6 +6,8 @@
#include <linux/srcu.h>
#include <linux/types.h>
+#include "../mount.h"
+
/* destroy all events sitting in this groups notification queue */
extern void fsnotify_flush_notify(struct fsnotify_group *group);
@@ -38,15 +40,22 @@ extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
/* inode specific destruction of a mark */
extern void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark);
-/* Destroy all marks in the given list */
-extern void fsnotify_destroy_marks(struct list_head *to_free);
/* Find mark belonging to given group in the list of marks */
extern struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
struct fsnotify_group *group);
-/* run the list of all marks associated with inode and flag them to be freed */
-extern void fsnotify_clear_marks_by_inode(struct inode *inode);
-/* run the list of all marks associated with vfsmount and flag them to be freed */
-extern void fsnotify_clear_marks_by_mount(struct vfsmount *mnt);
+/* Destroy all marks in the given list protected by 'lock' */
+extern void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock);
+/* run the list of all marks associated with inode and destroy them */
+static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
+{
+ fsnotify_destroy_marks(&inode->i_fsnotify_marks, &inode->i_lock);
+}
+/* run the list of all marks associated with vfsmount and destroy them */
+static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
+{
+ fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks,
+ &mnt->mnt_root->d_lock);
+}
/*
* update the dentry->d_flags of all of inode's children to indicate if inode cares
* about events that happen to its children.
diff --git a/kernel/fs/notify/inode_mark.c b/kernel/fs/notify/inode_mark.c
index 3daf513ee..e785fd954 100644
--- a/kernel/fs/notify/inode_mark.c
+++ b/kernel/fs/notify/inode_mark.c
@@ -65,26 +65,6 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
}
/*
- * Given an inode, destroy all of the marks associated with that inode.
- */
-void fsnotify_clear_marks_by_inode(struct inode *inode)
-{
- struct fsnotify_mark *mark;
- struct hlist_node *n;
- LIST_HEAD(free_list);
-
- spin_lock(&inode->i_lock);
- hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, obj_list) {
- list_add(&mark->free_list, &free_list);
- hlist_del_init_rcu(&mark->obj_list);
- fsnotify_get_mark(mark);
- }
- spin_unlock(&inode->i_lock);
-
- fsnotify_destroy_marks(&free_list);
-}
-
-/*
* Given a group clear all of the inode marks associated with that group.
*/
void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
@@ -163,17 +143,17 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
/**
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
- * @list: list of inodes being unmounted (sb->s_inodes)
+ * @sb: superblock being unmounted.
*
* Called during unmount with no locks held, so needs to be safe against
- * concurrent modifiers. We temporarily drop inode_sb_list_lock and CAN block.
+ * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
*/
-void fsnotify_unmount_inodes(struct list_head *list)
+void fsnotify_unmount_inodes(struct super_block *sb)
{
struct inode *inode, *next_i, *need_iput = NULL;
- spin_lock(&inode_sb_list_lock);
- list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+ spin_lock(&sb->s_inode_list_lock);
+ list_for_each_entry_safe(inode, next_i, &sb->s_inodes, i_sb_list) {
struct inode *need_iput_tmp;
/*
@@ -209,7 +189,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
spin_unlock(&inode->i_lock);
/* In case the dropping of a reference would nuke next_i. */
- while (&next_i->i_sb_list != list) {
+ while (&next_i->i_sb_list != &sb->s_inodes) {
spin_lock(&next_i->i_lock);
if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
atomic_read(&next_i->i_count)) {
@@ -224,12 +204,12 @@ void fsnotify_unmount_inodes(struct list_head *list)
}
/*
- * We can safely drop inode_sb_list_lock here because either
+ * We can safely drop s_inode_list_lock here because either
* we actually hold references on both inode and next_i or
* end of list. Also no new inodes will be added since the
* umount has begun.
*/
- spin_unlock(&inode_sb_list_lock);
+ spin_unlock(&sb->s_inode_list_lock);
if (need_iput_tmp)
iput(need_iput_tmp);
@@ -241,7 +221,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
iput(inode);
- spin_lock(&inode_sb_list_lock);
+ spin_lock(&sb->s_inode_list_lock);
}
- spin_unlock(&inode_sb_list_lock);
+ spin_unlock(&sb->s_inode_list_lock);
}
diff --git a/kernel/fs/notify/inotify/inotify_user.c b/kernel/fs/notify/inotify/inotify_user.c
index 450648697..b8d08d0d0 100644
--- a/kernel/fs/notify/inotify/inotify_user.c
+++ b/kernel/fs/notify/inotify/inotify_user.c
@@ -26,7 +26,7 @@
#include <linux/fs.h> /* struct inode */
#include <linux/fsnotify_backend.h>
#include <linux/idr.h>
-#include <linux/init.h> /* module_init */
+#include <linux/init.h> /* fs_initcall */
#include <linux/inotify.h>
#include <linux/kernel.h> /* roundup() */
#include <linux/namei.h> /* LOOKUP_FOLLOW */
@@ -706,7 +706,19 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
int ret;
unsigned flags = 0;
- /* don't allow invalid bits: we don't want flags set */
+ /*
+ * We share a lot of code with fs/dnotify. We also share
+ * the bit layout between inotify's IN_* and the fsnotify
+ * FS_*. This check ensures that only the inotify IN_*
+ * bits get passed in and set in watches/events.
+ */
+ if (unlikely(mask & ~ALL_INOTIFY_BITS))
+ return -EINVAL;
+ /*
+ * Require at least one valid bit set in the mask.
+ * Without _something_ set, we would have no events to
+ * watch for.
+ */
if (unlikely(!(mask & ALL_INOTIFY_BITS)))
return -EINVAL;
@@ -812,4 +824,4 @@ static int __init inotify_user_setup(void)
return 0;
}
-module_init(inotify_user_setup);
+fs_initcall(inotify_user_setup);
diff --git a/kernel/fs/notify/mark.c b/kernel/fs/notify/mark.c
index 39ddcaf09..fc0df4442 100644
--- a/kernel/fs/notify/mark.c
+++ b/kernel/fs/notify/mark.c
@@ -122,26 +122,27 @@ u32 fsnotify_recalc_mask(struct hlist_head *head)
}
/*
- * Any time a mark is getting freed we end up here.
- * The caller had better be holding a reference to this mark so we don't actually
- * do the final put under the mark->lock
+ * Remove mark from inode / vfsmount list, group list, drop inode reference
+ * if we got one.
+ *
+ * Must be called with group->mark_mutex held.
*/
-void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
- struct fsnotify_group *group)
+void fsnotify_detach_mark(struct fsnotify_mark *mark)
{
struct inode *inode = NULL;
+ struct fsnotify_group *group = mark->group;
BUG_ON(!mutex_is_locked(&group->mark_mutex));
spin_lock(&mark->lock);
/* something else already called this function on this mark */
- if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
spin_unlock(&mark->lock);
return;
}
- mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
+ mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
inode = mark->inode;
@@ -150,6 +151,12 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
fsnotify_destroy_vfsmount_mark(mark);
else
BUG();
+ /*
+ * Note that we didn't update flags telling whether inode cares about
+ * what's happening with children. We update these flags from
+ * __fsnotify_parent() lazily when next event happens on one of our
+ * children.
+ */
list_del_init(&mark->g_list);
@@ -157,18 +164,32 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
iput(inode);
- /* release lock temporarily */
- mutex_unlock(&group->mark_mutex);
+
+ atomic_dec(&group->num_marks);
+}
+
+/*
+ * Free fsnotify mark. The freeing is actually happening from a kthread which
+ * first waits for srcu period end. Caller must have a reference to the mark
+ * or be protected by fsnotify_mark_srcu.
+ */
+void fsnotify_free_mark(struct fsnotify_mark *mark)
+{
+ struct fsnotify_group *group = mark->group;
+
+ spin_lock(&mark->lock);
+ /* something else already called this function on this mark */
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
+ spin_unlock(&mark->lock);
+ return;
+ }
+ mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
+ spin_unlock(&mark->lock);
spin_lock(&destroy_lock);
list_add(&mark->g_list, &destroy_list);
spin_unlock(&destroy_lock);
wake_up(&destroy_waitq);
- /*
- * We don't necessarily have a ref on mark from caller so the above destroy
- * may have actually freed it, unless this group provides a 'freeing_mark'
- * function which must be holding a reference.
- */
/*
* Some groups like to know that marks are being freed. This is a
@@ -177,50 +198,45 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
*/
if (group->ops->freeing_mark)
group->ops->freeing_mark(mark, group);
-
- /*
- * __fsnotify_update_child_dentry_flags(inode);
- *
- * I really want to call that, but we can't, we have no idea if the inode
- * still exists the second we drop the mark->lock.
- *
- * The next time an event arrive to this inode from one of it's children
- * __fsnotify_parent will see that the inode doesn't care about it's
- * children and will update all of these flags then. So really this
- * is just a lazy update (and could be a perf win...)
- */
-
- atomic_dec(&group->num_marks);
-
- mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
}
void fsnotify_destroy_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group)
{
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
- fsnotify_destroy_mark_locked(mark, group);
+ fsnotify_detach_mark(mark);
mutex_unlock(&group->mark_mutex);
+ fsnotify_free_mark(mark);
}
-/*
- * Destroy all marks in the given list. The marks must be already detached from
- * the original inode / vfsmount.
- */
-void fsnotify_destroy_marks(struct list_head *to_free)
+void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
{
- struct fsnotify_mark *mark, *lmark;
- struct fsnotify_group *group;
-
- list_for_each_entry_safe(mark, lmark, to_free, free_list) {
- spin_lock(&mark->lock);
- fsnotify_get_group(mark->group);
- group = mark->group;
- spin_unlock(&mark->lock);
+ struct fsnotify_mark *mark;
- fsnotify_destroy_mark(mark, group);
+ while (1) {
+ /*
+ * We have to be careful since we can race with e.g.
+ * fsnotify_clear_marks_by_group() and once we drop 'lock',
+ * mark can get removed from the obj_list and destroyed. But
+ * we are holding mark reference so mark cannot be freed and
+ * calling fsnotify_destroy_mark() more than once is fine.
+ */
+ spin_lock(lock);
+ if (hlist_empty(head)) {
+ spin_unlock(lock);
+ break;
+ }
+ mark = hlist_entry(head->first, struct fsnotify_mark, obj_list);
+ /*
+ * We don't update i_fsnotify_mask / mnt_fsnotify_mask here
+ * since inode / mount is going away anyway. So just remove
+ * mark from the list.
+ */
+ hlist_del_init_rcu(&mark->obj_list);
+ fsnotify_get_mark(mark);
+ spin_unlock(lock);
+ fsnotify_destroy_mark(mark, mark->group);
fsnotify_put_mark(mark);
- fsnotify_put_group(group);
}
}
@@ -332,7 +348,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
* inode->i_lock
*/
spin_lock(&mark->lock);
- mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE;
+ mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
fsnotify_get_group(group);
mark->group = group;
@@ -438,8 +454,9 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
}
mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
fsnotify_get_mark(mark);
- fsnotify_destroy_mark_locked(mark, group);
+ fsnotify_detach_mark(mark);
mutex_unlock(&group->mark_mutex);
+ fsnotify_free_mark(mark);
fsnotify_put_mark(mark);
}
}
diff --git a/kernel/fs/notify/vfsmount_mark.c b/kernel/fs/notify/vfsmount_mark.c
index 326b148e6..a8fcab68f 100644
--- a/kernel/fs/notify/vfsmount_mark.c
+++ b/kernel/fs/notify/vfsmount_mark.c
@@ -28,25 +28,6 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-#include "../mount.h"
-
-void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
-{
- struct fsnotify_mark *mark;
- struct hlist_node *n;
- struct mount *m = real_mount(mnt);
- LIST_HEAD(free_list);
-
- spin_lock(&mnt->mnt_root->d_lock);
- hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, obj_list) {
- list_add(&mark->free_list, &free_list);
- hlist_del_init_rcu(&mark->obj_list);
- fsnotify_get_mark(mark);
- }
- spin_unlock(&mnt->mnt_root->d_lock);
-
- fsnotify_destroy_marks(&free_list);
-}
void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{