* [PATCH 01/22] fsnotify: Remove unnecessary tests when showing fdinfo
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 02/22] inotify: Remove inode pointers from debug messages Jan Kara
` (20 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
show_fdinfo() iterates group's list of marks. All marks found there are
guaranteed to be alive and they stay so until we release
group->mark_mutex. So remove uncecessary tests whether mark is alive.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fdinfo.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index fd98e5100cab..601a59c8d87e 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -76,8 +76,7 @@ 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) ||
- !(mark->flags & FSNOTIFY_MARK_FLAG_INODE))
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_INODE))
return;
inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
@@ -113,9 +112,6 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
unsigned int mflags = 0;
struct inode *inode;
- if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE))
- return;
-
if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 02/22] inotify: Remove inode pointers from debug messages
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
2017-01-20 13:21 ` [PATCH 01/22] fsnotify: Remove unnecessary tests when showing fdinfo Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 03/22] fanotify: Move recalculation of inode / vfsmount mask under mark_mutex Jan Kara
` (19 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Printing inode pointers in warnings has dubious value and with future
changes we won't be able to easily get them without either locking or
chances we oops along the way. So just remove inode pointers from the
warning messages.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/inotify/inotify_fsnotify.c | 4 ++--
fs/notify/inotify/inotify_user.c | 25 ++++++++++---------------
2 files changed, 12 insertions(+), 17 deletions(-)
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 19e7ec109a75..8421f44b3cb3 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -155,8 +155,8 @@ static int idr_callback(int id, void *p, void *data)
* BUG() that was here.
*/
if (fsn_mark)
- printk(KERN_WARNING "fsn_mark->group=%p inode=%p wd=%d\n",
- fsn_mark->group, fsn_mark->inode, i_mark->wd);
+ printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n",
+ fsn_mark->group, i_mark->wd);
return 0;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 69d1ea3d292a..3697567c7897 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -431,18 +431,16 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
* if it wasn't....
*/
if (wd == -1) {
- WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
- " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
- i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+ WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+ __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
goto out;
}
/* Lets look in the idr to see if we find it */
found_i_mark = inotify_idr_find_locked(group, wd);
if (unlikely(!found_i_mark)) {
- WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
- " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
- i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+ WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+ __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
goto out;
}
@@ -453,12 +451,10 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
*/
if (unlikely(found_i_mark != i_mark)) {
WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p "
- "mark->inode=%p found_i_mark=%p found_i_mark->wd=%d "
- "found_i_mark->group=%p found_i_mark->inode=%p\n",
- __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group,
- i_mark->fsn_mark.inode, found_i_mark, found_i_mark->wd,
- found_i_mark->fsn_mark.group,
- found_i_mark->fsn_mark.inode);
+ "found_i_mark=%p found_i_mark->wd=%d "
+ "found_i_mark->group=%p\n", __func__, i_mark,
+ i_mark->wd, i_mark->fsn_mark.group, found_i_mark,
+ found_i_mark->wd, found_i_mark->fsn_mark.group);
goto out;
}
@@ -468,9 +464,8 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
* one ref grabbed by inotify_idr_find
*/
if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 3)) {
- printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
- " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
- i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+ printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+ __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
/* we can't really recover with bad ref cnting.. */
BUG();
}
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 03/22] fanotify: Move recalculation of inode / vfsmount mask under mark_mutex
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
2017-01-20 13:21 ` [PATCH 01/22] fsnotify: Remove unnecessary tests when showing fdinfo Jan Kara
2017-01-20 13:21 ` [PATCH 02/22] inotify: Remove inode pointers from debug messages Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 04/22] audit: Abstract hash key handling Jan Kara
` (18 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Move recalculation of inode / vfsmount notification mask under
group->mark_mutex of the mark which was modified. These are the only
places where mask recalculation happens without mark being protected
from detaching from inode / vfsmount which will cause issues with the
following patches.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fanotify/fanotify_user.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 7ebfca6a1427..8dcec9eecafd 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -541,6 +541,8 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
+ if (removed & real_mount(mnt)->mnt_fsnotify_mask)
+ fsnotify_recalc_vfsmount_mask(mnt);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
@@ -548,9 +550,6 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
- if (removed & real_mount(mnt)->mnt_fsnotify_mask)
- fsnotify_recalc_vfsmount_mask(mnt);
-
return 0;
}
@@ -571,6 +570,8 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
+ if (removed & inode->i_fsnotify_mask)
+ fsnotify_recalc_inode_mask(inode);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
@@ -579,8 +580,6 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
/* matches the fsnotify_find_inode_mark() */
fsnotify_put_mark(fsn_mark);
- if (removed & inode->i_fsnotify_mask)
- fsnotify_recalc_inode_mask(inode);
return 0;
}
@@ -656,10 +655,9 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
}
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
- mutex_unlock(&group->mark_mutex);
-
if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
+ mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
return 0;
@@ -694,10 +692,9 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
}
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
- mutex_unlock(&group->mark_mutex);
-
if (added & ~inode->i_fsnotify_mask)
fsnotify_recalc_inode_mask(inode);
+ mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
return 0;
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 04/22] audit: Abstract hash key handling
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (2 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 03/22] fanotify: Move recalculation of inode / vfsmount mask under mark_mutex Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 05/22] fsnotify: Update comments Jan Kara
` (17 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Audit tree currently uses inode pointer as a key into the hash table.
Getting that from notification mark will be somewhat more difficult with
coming fsnotify changes. So abstract getting of hash key from the audit
chunk and inode so that we can change the method to obtain a key easily.
CC: Paul Moore <paul@paul-moore.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
kernel/audit_tree.c | 39 ++++++++++++++++++++++++++++-----------
1 file changed, 28 insertions(+), 11 deletions(-)
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 7b44195da81b..11c7ac441624 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -163,33 +163,48 @@ enum {HASH_SIZE = 128};
static struct list_head chunk_hash_heads[HASH_SIZE];
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);
-static inline struct list_head *chunk_hash(const struct inode *inode)
+/* Function to return search key in our hash from inode. */
+static unsigned long inode_to_key(const struct inode *inode)
{
- unsigned long n = (unsigned long)inode / L1_CACHE_BYTES;
+ return (unsigned long)inode;
+}
+
+/*
+ * Function to return search key in our hash from chunk. Key 0 is special and
+ * should never be present in the hash.
+ */
+static unsigned long chunk_to_key(struct audit_chunk *chunk)
+{
+ return (unsigned long)chunk->mark.inode;
+}
+
+static inline struct list_head *chunk_hash(unsigned long key)
+{
+ unsigned long n = key / L1_CACHE_BYTES;
return chunk_hash_heads + n % HASH_SIZE;
}
/* hash_lock & entry->lock is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
- struct fsnotify_mark *entry = &chunk->mark;
+ unsigned long key = chunk_to_key(chunk);
struct list_head *list;
- if (!entry->inode)
+ if (!key)
return;
- list = chunk_hash(entry->inode);
+ list = chunk_hash(key);
list_add_rcu(&chunk->hash, list);
}
/* called under rcu_read_lock */
struct audit_chunk *audit_tree_lookup(const struct inode *inode)
{
- struct list_head *list = chunk_hash(inode);
+ unsigned long key = inode_to_key(inode);
+ struct list_head *list = chunk_hash(key);
struct audit_chunk *p;
list_for_each_entry_rcu(p, list, hash) {
- /* mark.inode may have gone NULL, but who cares? */
- if (p->mark.inode == inode) {
+ if (chunk_to_key(p) == key) {
atomic_long_inc(&p->refs);
return p;
}
@@ -588,7 +603,8 @@ int audit_remove_tree_rule(struct audit_krule *rule)
static int compare_root(struct vfsmount *mnt, void *arg)
{
- return d_backing_inode(mnt->mnt_root) == arg;
+ return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
+ (unsigned long)arg;
}
void audit_trim_trees(void)
@@ -623,9 +639,10 @@ void audit_trim_trees(void)
list_for_each_entry(node, &tree->chunks, list) {
struct audit_chunk *chunk = find_chunk(node);
/* this could be NULL if the watch is dying else where... */
- struct inode *inode = chunk->mark.inode;
node->index |= 1U<<31;
- if (iterate_mounts(compare_root, inode, root_mnt))
+ if (iterate_mounts(compare_root,
+ (void *)chunk_to_key(chunk),
+ root_mnt))
node->index &= ~(1U<<31);
}
spin_unlock(&hash_lock);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 05/22] fsnotify: Update comments
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (3 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 04/22] audit: Abstract hash key handling Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure Jan Kara
` (16 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Add a comment that lifetime of a notification mark is protected by SRCU
and remove a comment about clearing of marks attached to the inode. It
is stale and more uptodate version is at fsnotify_destroy_marks() which
is the function handling this case.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/mark.c | 13 +------------
1 file changed, 1 insertion(+), 12 deletions(-)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 6043306e8e21..44836e539169 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -51,7 +51,7 @@
*
* LIFETIME:
* Inode marks survive between when they are added to an inode and when their
- * refcnt==0.
+ * refcnt==0. Marks are also protected by fsnotify_mark_srcu.
*
* The inode mark can be cleared for a number of different reasons including:
* - The inode is unlinked for the last time. (fsnotify_inode_remove)
@@ -61,17 +61,6 @@
* - The fsnotify_group associated with the mark is going away and all such marks
* need to be cleaned up. (fsnotify_clear_marks_by_group)
*
- * Worst case we are given an inode and need to clean up all the marks on that
- * inode. We take i_lock and walk the i_fsnotify_marks safely. For each
- * mark on the list we take a reference (so the mark can't disappear under us).
- * We remove that mark form the inode's list of marks and we add this mark to a
- * private list anchored on the stack using i_free_list; we walk i_free_list
- * and before we destroy the mark we make sure that we dont race with a
- * concurrent destroy_group by getting a ref to the marks group and taking the
- * groups mutex.
-
- * Very similarly for freeing by group, except we use free_g_list.
- *
* This has the very interesting property of being able to run concurrently with
* any (or all) other directions.
*/
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (4 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 05/22] fsnotify: Update comments Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-21 15:52 ` Amir Goldstein
2017-01-25 9:41 ` Miklos Szeredi
2017-01-20 13:21 ` [PATCH 07/22] inotify: Do not drop mark reference under idr_lock Jan Kara
` (15 subsequent siblings)
21 siblings, 2 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Currently notification marks are attached to object (inode or vfsmnt) by
a hlist_head in the object. The list is also protected by a spinlock in
the object. So while there is any mark attached to the list of marks,
the object must be pinned in memory (and thus e.g. last iput() deleting
inode cannot happen). Also for list iteration in fsnotify() to work, we
must hold fsnotify_mark_srcu lock so that mark itself and
mark->obj_list.next cannot get freed. Thus we are required to wait for
response to fanotify events from userspace process with
fsnotify_mark_srcu lock held. That causes issues when userspace process
is buggy and does not reply to some event - basically the whole
notification subsystem gets eventually stuck.
So to be able to drop fsnotify_mark_srcu lock while waiting for
response, we have to pin the mark in memory and make sure it stays in
the object list (as removing the mark waiting for response could lead to
lost notification events for groups later in the list). However we don't
want inode reclaim to block on such mark as that would lead to system
just locking up elsewhere.
This commit tries to pave a way towards solving these conflicting
lifetime needs. Instead of anchoring the list of marks directly in the
object, we anchor it in a dedicated structure (fsnotify_mark_connector) and
just point to that structure from the object. Also the list is protected
by a spinlock contained in that structure. With this, we can detach
notification marks from object without having to modify the list itself.
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/inode.c | 3 -
fs/mount.h | 2 +-
fs/namespace.c | 3 -
fs/notify/dnotify/dnotify.c | 3 +-
fs/notify/fdinfo.c | 12 +-
fs/notify/fsnotify.c | 31 +++-
fs/notify/fsnotify.h | 38 +----
fs/notify/inode_mark.c | 94 +-----------
fs/notify/mark.c | 313 ++++++++++++++++++++++++++++-----------
fs/notify/vfsmount_mark.c | 64 +-------
include/linux/fs.h | 4 +-
include/linux/fsnotify_backend.h | 43 ++++--
kernel/audit_tree.c | 30 +++-
kernel/auditsc.c | 4 +-
14 files changed, 336 insertions(+), 308 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 88110fd0b282..131b2bcebc48 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -371,9 +371,6 @@ void inode_init_once(struct inode *inode)
INIT_LIST_HEAD(&inode->i_lru);
address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
-#ifdef CONFIG_FSNOTIFY
- INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
-#endif
}
EXPORT_SYMBOL(inode_init_once);
diff --git a/fs/mount.h b/fs/mount.h
index 2c856fc47ae3..e1dc79713abe 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -59,7 +59,7 @@ struct mount {
struct mountpoint *mnt_mp; /* where is it mounted */
struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
#ifdef CONFIG_FSNOTIFY
- struct hlist_head mnt_fsnotify_marks;
+ struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
__u32 mnt_fsnotify_mask;
#endif
int mnt_id; /* mount identifier */
diff --git a/fs/namespace.c b/fs/namespace.c
index b5b1259e064f..22a91352e2d7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -233,9 +233,6 @@ static struct mount *alloc_vfsmnt(const char *name)
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
INIT_HLIST_NODE(&mnt->mnt_mp_list);
-#ifdef CONFIG_FSNOTIFY
- INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
-#endif
init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
}
return mnt;
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 5a4ec309e283..41b2a070761c 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -69,8 +69,7 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
if (old_mask == new_mask)
return;
- if (fsn_mark->inode)
- fsnotify_recalc_inode_mask(fsn_mark->inode);
+ fsnotify_recalc_mask(fsn_mark->connector);
}
/*
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 601a59c8d87e..dd63aa9a6f9a 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -76,11 +76,11 @@ 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_INODE))
+ if (!(mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE))
return;
inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
- inode = igrab(mark->inode);
+ inode = igrab(mark->connector->inode);
if (inode) {
/*
* IN_ALL_EVENTS represents all of the mask bits
@@ -115,8 +115,8 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
- if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
- inode = igrab(mark->inode);
+ if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+ inode = igrab(mark->connector->inode);
if (!inode)
return;
seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
@@ -125,8 +125,8 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
- } else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) {
- struct mount *mnt = real_mount(mark->mnt);
+ } else if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ struct mount *mnt = real_mount(mark->connector->mnt);
seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index b41515d3f081..d512ef9f75fc 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -193,6 +193,7 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
struct hlist_node *inode_node = NULL, *vfsmount_node = NULL;
struct fsnotify_mark *inode_mark = NULL, *vfsmount_mark = NULL;
struct fsnotify_group *inode_group, *vfsmount_group;
+ struct fsnotify_mark_connector *inode_conn, *vfsmount_conn;
struct mount *mnt;
int idx, ret = 0;
/* global tests shouldn't care about events on child only the specific event */
@@ -210,8 +211,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
* 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)))
+ if (!to_tell->i_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks))
return 0;
/*
* if this is a modify event we may need to clear the ignored masks
@@ -226,16 +227,27 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
idx = srcu_read_lock(&fsnotify_mark_srcu);
if ((mask & FS_MODIFY) ||
- (test_mask & to_tell->i_fsnotify_mask))
- inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+ (test_mask & to_tell->i_fsnotify_mask)) {
+ inode_conn = srcu_dereference(to_tell->i_fsnotify_marks,
&fsnotify_mark_srcu);
+ if (inode_conn)
+ inode_node = srcu_dereference(inode_conn->list.first,
+ &fsnotify_mark_srcu);
+ }
if (mnt && ((mask & FS_MODIFY) ||
(test_mask & mnt->mnt_fsnotify_mask))) {
- vfsmount_node = srcu_dereference(mnt->mnt_fsnotify_marks.first,
- &fsnotify_mark_srcu);
- inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+ inode_conn = srcu_dereference(to_tell->i_fsnotify_marks,
&fsnotify_mark_srcu);
+ if (inode_conn)
+ inode_node = srcu_dereference(inode_conn->list.first,
+ &fsnotify_mark_srcu);
+ vfsmount_conn = srcu_dereference(mnt->mnt_fsnotify_marks,
+ &fsnotify_mark_srcu);
+ if (vfsmount_conn)
+ vfsmount_node = srcu_dereference(
+ vfsmount_conn->list.first,
+ &fsnotify_mark_srcu);
}
/*
@@ -293,6 +305,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
}
EXPORT_SYMBOL_GPL(fsnotify);
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
static __init int fsnotify_init(void)
{
int ret;
@@ -303,6 +317,9 @@ static __init int fsnotify_init(void)
if (ret)
panic("initializing fsnotify_mark_srcu");
+ fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
+ SLAB_PANIC);
+
return 0;
}
core_initcall(fsnotify_init);
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 0a3bc2cf192c..24bc549e9709 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -14,47 +14,25 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
/* protects reads of inode and vfsmount marks list */
extern struct srcu_struct fsnotify_mark_srcu;
-/* Calculate mask of events for a list of marks */
-extern u32 fsnotify_recalc_mask(struct hlist_head *head);
-
/* compare two groups for sorting of marks lists */
extern int fsnotify_compare_groups(struct fsnotify_group *a,
struct fsnotify_group *b);
-extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
- __u32 mask);
-/* Add mark to a proper place in mark list */
-extern int fsnotify_add_mark_list(struct hlist_head *head,
- struct fsnotify_mark *mark,
- int allow_dups);
-/* add a mark to an inode */
-extern int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group, struct inode *inode,
- int allow_dups);
-/* add a mark to a vfsmount */
-extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group, struct vfsmount *mnt,
- int allow_dups);
-
-/* vfsmount specific destruction of a 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);
-/* 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);
-/* Destroy all marks in the given list protected by 'lock' */
-extern void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock);
+/* Find mark belonging to given group attached to given connector */
+extern struct fsnotify_mark *fsnotify_find_mark(
+ struct fsnotify_mark_connector **connp,
+ struct fsnotify_group *group);
+/* Destroy all marks connected via given connector */
+extern void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp);
/* 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);
+ fsnotify_destroy_marks(&inode->i_fsnotify_marks);
}
/* 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);
+ fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
}
/* prepare for freeing all marks associated with given group */
extern void fsnotify_detach_group_marks(struct fsnotify_group *group);
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index a3645249f7ec..b9370316727e 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -30,38 +30,9 @@
#include "../internal.h"
-/*
- * Recalculate the inode->i_fsnotify_mask, or the mask of all FS_* event types
- * any notifier is interested in hearing for this inode.
- */
void fsnotify_recalc_inode_mask(struct inode *inode)
{
- spin_lock(&inode->i_lock);
- inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
- spin_unlock(&inode->i_lock);
-
- __fsnotify_update_child_dentry_flags(inode);
-}
-
-void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
-{
- struct inode *inode = mark->inode;
-
- BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
- assert_spin_locked(&mark->lock);
-
- spin_lock(&inode->i_lock);
-
- hlist_del_init_rcu(&mark->obj_list);
- mark->inode = NULL;
-
- /*
- * this mark is now off the inode->i_fsnotify_marks list and we
- * hold the inode->i_lock, so this is the perfect time to update the
- * inode->i_fsnotify_mask
- */
- inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
- spin_unlock(&inode->i_lock);
+ fsnotify_recalc_mask(inode->i_fsnotify_marks);
}
/*
@@ -69,7 +40,7 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
*/
void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_INODE);
+ fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_INODE);
}
/*
@@ -79,66 +50,7 @@ void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
struct inode *inode)
{
- struct fsnotify_mark *mark;
-
- spin_lock(&inode->i_lock);
- mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
- spin_unlock(&inode->i_lock);
-
- return mark;
-}
-
-/*
- * If we are setting a mark mask on an inode mark we should pin the inode
- * in memory.
- */
-void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
- __u32 mask)
-{
- struct inode *inode;
-
- assert_spin_locked(&mark->lock);
-
- if (mask &&
- mark->inode &&
- !(mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED)) {
- mark->flags |= FSNOTIFY_MARK_FLAG_OBJECT_PINNED;
- inode = igrab(mark->inode);
- /*
- * we shouldn't be able to get here if the inode wasn't
- * already safely held in memory. But bug in case it
- * ever is wrong.
- */
- BUG_ON(!inode);
- }
-}
-
-/*
- * Attach an initialized mark to a given inode.
- * These marks may be used for the fsnotify backend to determine which
- * event types should be delivered to which group and for which inodes. These
- * marks are ordered according to priority, highest number first, and then by
- * the group's location in memory.
- */
-int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group, struct inode *inode,
- int allow_dups)
-{
- int ret;
-
- mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
-
- BUG_ON(!mutex_is_locked(&group->mark_mutex));
- assert_spin_locked(&mark->lock);
-
- spin_lock(&inode->i_lock);
- mark->inode = inode;
- ret = fsnotify_add_mark_list(&inode->i_fsnotify_marks, mark,
- allow_dups);
- inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
- spin_unlock(&inode->i_lock);
-
- return ret;
+ return fsnotify_find_mark(&inode->i_fsnotify_marks, group);
}
/**
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 44836e539169..719e71d313e8 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -33,7 +33,7 @@
*
* group->mark_mutex
* mark->lock
- * inode->i_lock
+ * mark->connector->lock
*
* group->mark_mutex protects the marks_list anchored inside a given group and
* each mark is hooked via the g_list. It also protects the groups private
@@ -44,10 +44,12 @@
* is assigned to as well as the access to a reference of the inode/vfsmount
* that is being watched by the mark.
*
- * inode->i_lock protects the i_fsnotify_marks list anchored inside a
- * given inode and each mark is hooked via the i_list. (and sorta the
- * free_i_list)
+ * mark->connector->lock protects the list of marks anchored inside an
+ * inode / vfsmount and each mark is hooked via the i_list.
*
+ * A list of notification marks relating to inode / mnt is contained in
+ * fsnotify_mark_connector. That structure is alive as long as there are any marks
+ * in the list and is also protected by fsnotify_mark_srcu.
*
* LIFETIME:
* Inode marks survive between when they are added to an inode and when their
@@ -83,12 +85,18 @@
#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */
struct srcu_struct fsnotify_mark_srcu;
+struct kmem_cache *fsnotify_mark_connector_cachep;
+
static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
+static struct fsnotify_mark_connector *connector_destroy_list;
static void fsnotify_mark_destroy_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
+static void fsnotify_connector_destroy_workfn(struct work_struct *work);
+static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);
+
void fsnotify_get_mark(struct fsnotify_mark *mark)
{
atomic_inc(&mark->refcnt);
@@ -103,15 +111,99 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
}
}
-/* Calculate mask of events for a list of marks */
-u32 fsnotify_recalc_mask(struct hlist_head *head)
+static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
u32 new_mask = 0;
struct fsnotify_mark *mark;
- hlist_for_each_entry(mark, head, obj_list)
- new_mask |= mark->mask;
- return new_mask;
+ assert_spin_locked(&conn->lock);
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
+ if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
+ new_mask |= mark->mask;
+ }
+ if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+ conn->inode->i_fsnotify_mask = new_mask;
+ else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+ real_mount(conn->mnt)->mnt_fsnotify_mask = new_mask;
+}
+
+/*
+ * Calculate mask of events for a list of marks. The caller must make sure list
+ * cannot disappear under us (usually by holding a mark->lock or
+ * mark->group->mark_mutex for a mark on this list).
+ */
+void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+{
+ struct inode *inode = NULL;
+
+ spin_lock(&conn->lock);
+ __fsnotify_recalc_mask(conn);
+ if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+ inode = igrab(conn->inode);
+ spin_unlock(&conn->lock);
+ if (inode) {
+ __fsnotify_update_child_dentry_flags(inode);
+ iput(inode);
+ }
+}
+
+/* Free all connectors queued for freeing once SRCU period ends */
+static void fsnotify_connector_destroy_workfn(struct work_struct *work)
+{
+ struct fsnotify_mark_connector *conn, *free;
+
+ spin_lock(&destroy_lock);
+ conn = connector_destroy_list;
+ connector_destroy_list = NULL;
+ spin_unlock(&destroy_lock);
+
+ synchronize_srcu(&fsnotify_mark_srcu);
+ while (conn) {
+ free = conn;
+ conn = conn->destroy_next;
+ kmem_cache_free(fsnotify_mark_connector_cachep, free);
+ }
+}
+
+static struct inode *fsnotify_detach_from_object(struct fsnotify_mark *mark)
+{
+ struct fsnotify_mark_connector *conn;
+ struct inode *inode = NULL;
+ bool free_conn = false;
+
+ conn = mark->connector;
+ spin_lock(&conn->lock);
+ hlist_del_init_rcu(&mark->obj_list);
+ if (hlist_empty(&conn->list)) {
+ if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+ inode = conn->inode;
+ rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
+ inode->i_fsnotify_mask = 0;
+ conn->inode = NULL;
+ conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
+ } else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ rcu_assign_pointer(
+ real_mount(conn->mnt)->mnt_fsnotify_marks,
+ NULL);
+ real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
+ conn->mnt = NULL;
+ conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ }
+ free_conn = true;
+ } else
+ __fsnotify_recalc_mask(conn);
+ mark->connector = NULL;
+ spin_unlock(&conn->lock);
+
+ if (free_conn) {
+ spin_lock(&destroy_lock);
+ conn->destroy_next = connector_destroy_list;
+ connector_destroy_list = conn;
+ spin_unlock(&destroy_lock);
+ queue_work(system_unbound_wq, &connector_reaper_work);
+ }
+
+ return inode;
}
/*
@@ -137,13 +229,8 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
- if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
- inode = mark->inode;
- fsnotify_destroy_inode_mark(mark);
- } else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT)
- fsnotify_destroy_vfsmount_mark(mark);
- else
- BUG();
+ inode = fsnotify_detach_from_object(mark);
+
/*
* Note that we didn't update flags telling whether inode cares about
* what's happening with children. We update these flags from
@@ -155,7 +242,7 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
spin_unlock(&mark->lock);
- if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
+ if (inode)
iput(inode);
atomic_dec(&group->num_marks);
@@ -220,45 +307,11 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
fsnotify_free_mark(mark);
}
-void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
-{
- struct fsnotify_mark *mark;
-
- 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);
- }
-}
-
void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
{
assert_spin_locked(&mark->lock);
mark->mask = mask;
-
- if (mark->flags & FSNOTIFY_MARK_FLAG_INODE)
- fsnotify_set_inode_mark_mask_locked(mark, mask);
}
void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask)
@@ -304,37 +357,113 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
return -1;
}
-/* Add mark into proper place in given list of marks */
-int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
- int allow_dups)
+/*
+ * Get mark connector, make sure it is alive and return with its lock held.
+ * This is for users that get connector pointer from inode or mount. Users that
+ * hold reference to a mark on the list may directly lock connector->lock as
+ * they are sure list cannot go away under them.
+ */
+static struct fsnotify_mark_connector *fsnotify_grab_connector(
+ struct fsnotify_mark_connector * __rcu *connp)
+{
+ struct fsnotify_mark_connector *conn;
+ int idx;
+
+ idx = srcu_read_lock(&fsnotify_mark_srcu);
+ conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
+ if (!conn)
+ goto out;
+ spin_lock(&conn->lock);
+ if (!(conn->flags & (FSNOTIFY_OBJ_TYPE_INODE |
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT))) {
+ spin_unlock(&conn->lock);
+ srcu_read_unlock(&fsnotify_mark_srcu, idx);
+ return NULL;
+ }
+out:
+ srcu_read_unlock(&fsnotify_mark_srcu, idx);
+ return conn;
+}
+
+/*
+ * Add mark into proper place in given list of marks. These marks may be used
+ * for the fsnotify backend to determine which event types should be delivered
+ * to which group and for which inodes. These marks are ordered according to
+ * priority, highest number first, and then by the group's location in memory.
+ */
+static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
+ struct inode *inode, struct vfsmount *mnt,
+ int allow_dups)
{
struct fsnotify_mark *lmark, *last = NULL;
+ struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark_connector **connp;
int cmp;
+ int err = 0;
+
+ BUG_ON(!inode && !mnt);
+ if (inode)
+ connp = &inode->i_fsnotify_marks;
+ else
+ connp = &real_mount(mnt)->mnt_fsnotify_marks;
+restart:
+ spin_lock(&mark->lock);
+ conn = fsnotify_grab_connector(connp);
+ if (!conn) {
+ spin_unlock(&mark->lock);
+ conn = kmem_cache_alloc(fsnotify_mark_connector_cachep,
+ GFP_KERNEL);
+ if (!conn)
+ return -ENOMEM;
+ spin_lock_init(&conn->lock);
+ INIT_HLIST_HEAD(&conn->list);
+ if (inode) {
+ conn->flags = FSNOTIFY_OBJ_TYPE_INODE;
+ conn->inode = igrab(inode);
+ } else {
+ conn->flags = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ conn->mnt = mnt;
+ }
+ if (cmpxchg(connp, NULL, conn)) {
+ /* Someone else created list structure for us */
+ if (inode)
+ iput(inode);
+ kmem_cache_free(fsnotify_mark_connector_cachep, conn);
+ }
+ goto restart;
+ }
/* is mark the first mark? */
- if (hlist_empty(head)) {
- hlist_add_head_rcu(&mark->obj_list, head);
- return 0;
+ if (hlist_empty(&conn->list)) {
+ hlist_add_head_rcu(&mark->obj_list, &conn->list);
+ goto added;
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, head, obj_list) {
+ hlist_for_each_entry(lmark, &conn->list, obj_list) {
last = lmark;
- if ((lmark->group == mark->group) && !allow_dups)
- return -EEXIST;
+ if ((lmark->group == mark->group) && !allow_dups) {
+ err = -EEXIST;
+ goto out_err;
+ }
cmp = fsnotify_compare_groups(lmark->group, mark->group);
if (cmp >= 0) {
hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
- return 0;
+ goto added;
}
}
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
- return 0;
+added:
+ mark->connector = conn;
+out_err:
+ spin_unlock(&conn->lock);
+ spin_unlock(&mark->lock);
+ return err;
}
/*
@@ -356,7 +485,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
* LOCKING ORDER!!!!
* group->mark_mutex
* mark->lock
- * inode->i_lock
+ * mark->connector->lock
*/
spin_lock(&mark->lock);
mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
@@ -366,25 +495,14 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
list_add(&mark->g_list, &group->marks_list);
atomic_inc(&group->num_marks);
fsnotify_get_mark(mark); /* for i_list and g_list */
-
- if (inode) {
- ret = fsnotify_add_inode_mark(mark, group, inode, allow_dups);
- if (ret)
- goto err;
- } else if (mnt) {
- ret = fsnotify_add_vfsmount_mark(mark, group, mnt, allow_dups);
- if (ret)
- goto err;
- } else {
- BUG();
- }
-
- /* this will pin the object if appropriate */
- fsnotify_set_mark_mask_locked(mark, mark->mask);
spin_unlock(&mark->lock);
- if (inode)
- __fsnotify_update_child_dentry_flags(inode);
+ ret = fsnotify_add_mark_list(mark, inode, mnt, allow_dups);
+ if (ret)
+ goto err;
+
+ if (mark->mask)
+ fsnotify_recalc_mask(mark->connector);
return ret;
err:
@@ -419,17 +537,23 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
* Given a list of marks, find the mark associated with given group. If found
* take a reference to that mark and return it, else return NULL.
*/
-struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_mark_connector **connp,
struct fsnotify_group *group)
{
struct fsnotify_mark *mark;
+ struct fsnotify_mark_connector *conn;
- hlist_for_each_entry(mark, head, obj_list) {
+ conn = fsnotify_grab_connector(connp);
+ if (!conn)
+ return NULL;
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
+ spin_unlock(&conn->lock);
return mark;
}
}
+ spin_unlock(&conn->lock);
return NULL;
}
@@ -453,7 +577,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
*/
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
- if (mark->flags & flags)
+ if (mark->connector->flags & flags)
list_move(&mark->g_list, &to_free);
}
mutex_unlock(&group->mark_mutex);
@@ -499,6 +623,29 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
}
}
+/* Destroy all marks attached to inode / vfsmount */
+void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp)
+{
+ struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark *mark;
+
+ while ((conn = fsnotify_grab_connector(connp))) {
+ /*
+ * We have to be careful since we can race with e.g.
+ * fsnotify_clear_marks_by_group() and once we drop the list
+ * 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.
+ */
+ mark = hlist_entry(conn->list.first, struct fsnotify_mark,
+ obj_list);
+ fsnotify_get_mark(mark);
+ spin_unlock(&conn->lock);
+ fsnotify_destroy_mark(mark, mark->group);
+ fsnotify_put_mark(mark);
+ }
+}
+
/*
* Nothing fancy, just initialize lists and locks and counters.
*/
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index a8fcab68faef..8fc1aca21bcf 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -29,39 +29,14 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_VFSMOUNT);
-}
-
-/*
- * Recalculate the mnt->mnt_fsnotify_mask, or the mask of all FS_* event types
- * any notifier is interested in hearing for this mount point
- */
void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
{
- struct mount *m = real_mount(mnt);
-
- spin_lock(&mnt->mnt_root->d_lock);
- m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
- spin_unlock(&mnt->mnt_root->d_lock);
+ fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
}
-void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
+void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{
- struct vfsmount *mnt = mark->mnt;
- struct mount *m = real_mount(mnt);
-
- BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
- assert_spin_locked(&mark->lock);
-
- spin_lock(&mnt->mnt_root->d_lock);
-
- hlist_del_init_rcu(&mark->obj_list);
- mark->mnt = NULL;
-
- m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
- spin_unlock(&mnt->mnt_root->d_lock);
+ fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
}
/*
@@ -72,37 +47,6 @@ struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt)
{
struct mount *m = real_mount(mnt);
- struct fsnotify_mark *mark;
-
- spin_lock(&mnt->mnt_root->d_lock);
- mark = fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
- spin_unlock(&mnt->mnt_root->d_lock);
-
- return mark;
-}
-
-/*
- * Attach an initialized mark to a given group and vfsmount.
- * These marks may be used for the fsnotify backend to determine which
- * event types should be delivered to which groups.
- */
-int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group, struct vfsmount *mnt,
- int allow_dups)
-{
- struct mount *m = real_mount(mnt);
- int ret;
-
- mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
-
- BUG_ON(!mutex_is_locked(&group->mark_mutex));
- assert_spin_locked(&mark->lock);
-
- spin_lock(&mnt->mnt_root->d_lock);
- mark->mnt = mnt;
- ret = fsnotify_add_mark_list(&m->mnt_fsnotify_marks, mark, allow_dups);
- m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
- spin_unlock(&mnt->mnt_root->d_lock);
- return ret;
+ return fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ba074328894..8fc09316f996 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -545,6 +545,8 @@ is_uncached_acl(struct posix_acl *acl)
#define IOP_XATTR 0x0008
#define IOP_DEFAULT_READLINK 0x0010
+struct fsnotify_mark_connector;
+
/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
@@ -644,7 +646,7 @@ struct inode {
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
- struct hlist_head i_fsnotify_marks;
+ struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 487246546ebe..f3df68a64ee6 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -194,6 +194,28 @@ struct fsnotify_group {
#define FSNOTIFY_EVENT_INODE 2
/*
+ * Inode / vfsmount point to this structure which tracks all marks attached to
+ * the inode / vfsmount. The reference to inode / vfsmount is held by this
+ * structure. We destroy this structure when there are no more marks attached
+ * to it. The structure is protected by fsnotify_mark_srcu.
+ */
+struct fsnotify_mark_connector {
+ spinlock_t lock;
+#define FSNOTIFY_OBJ_TYPE_INODE 0x01
+#define FSNOTIFY_OBJ_TYPE_VFSMOUNT 0x02
+ unsigned int flags; /* Type of object [lock] */
+ union { /* Object pointer [lock] */
+ struct inode *inode;
+ struct vfsmount *mnt;
+ };
+ union {
+ struct hlist_head list;
+ /* Used listing heads to free after srcu period expires */
+ struct fsnotify_mark_connector *destroy_next;
+ };
+};
+
+/*
* A mark is simply an object attached to an in core inode which allows an
* fsnotify listener to indicate they are either no longer interested in events
* of a type matching mask or only interested in those events.
@@ -222,20 +244,15 @@ struct fsnotify_mark {
struct list_head g_list;
/* Protects inode / mnt pointers, flags, masks */
spinlock_t lock;
- /* List of marks for inode / vfsmount [obj_lock] */
+ /* List of marks for inode / vfsmount [connector->lock] */
struct hlist_node obj_list;
- union { /* Object pointer [mark->lock, group->mark_mutex] */
- struct inode *inode; /* inode this mark is associated with */
- struct vfsmount *mnt; /* vfsmount this mark is associated with */
- };
+ /* Head of list of marks for an object [mark->lock, group->mark_mutex] */
+ struct fsnotify_mark_connector *connector;
/* Events types to ignore [mark->lock, group->mark_mutex] */
__u32 ignored_mask;
-#define FSNOTIFY_MARK_FLAG_INODE 0x01
-#define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02
-#define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04
-#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08
-#define FSNOTIFY_MARK_FLAG_ALIVE 0x10
-#define FSNOTIFY_MARK_FLAG_ATTACHED 0x20
+#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01
+#define FSNOTIFY_MARK_FLAG_ALIVE 0x02
+#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04
unsigned int flags; /* flags [mark->lock] */
void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */
};
@@ -314,6 +331,8 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group
/* functions used to manipulate the marks attached to inodes */
+/* Calculate mask of events for a list of marks */
+extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
/* run all marks associated with a vfsmount and update mnt->mnt_fsnotify_mask */
extern void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt);
/* run all marks associated with an inode and update inode->i_fsnotify_mask */
@@ -343,7 +362,7 @@ extern void fsnotify_free_mark(struct fsnotify_mark *mark);
extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group);
/* run all the marks in a group, and clear all of the inode marks */
extern void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group);
-/* run all the marks in a group, and clear all of the marks where mark->flags & flags is true*/
+/* run all the marks in a group, and clear all of the marks attached to given object type */
extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags);
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 11c7ac441624..a878a98f55b3 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -172,10 +172,25 @@ static unsigned long inode_to_key(const struct inode *inode)
/*
* Function to return search key in our hash from chunk. Key 0 is special and
* should never be present in the hash.
+ *
+ * Must be called with chunk->mark.lock held to protect from connector
+ * becoming NULL.
*/
+static unsigned long __chunk_to_key(struct audit_chunk *chunk)
+{
+ if (!chunk->mark.connector)
+ return 0;
+ return (unsigned long)chunk->mark.connector->inode;
+}
+
static unsigned long chunk_to_key(struct audit_chunk *chunk)
{
- return (unsigned long)chunk->mark.inode;
+ unsigned long key;
+
+ spin_lock(&chunk->mark.lock);
+ key = __chunk_to_key(chunk);
+ spin_unlock(&chunk->mark.lock);
+ return key;
}
static inline struct list_head *chunk_hash(unsigned long key)
@@ -187,7 +202,7 @@ static inline struct list_head *chunk_hash(unsigned long key)
/* hash_lock & entry->lock is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
- unsigned long key = chunk_to_key(chunk);
+ unsigned long key = __chunk_to_key(chunk);
struct list_head *list;
if (!key)
@@ -248,7 +263,8 @@ static void untag_chunk(struct node *p)
mutex_lock(&entry->group->mark_mutex);
spin_lock(&entry->lock);
- if (chunk->dead || !entry->inode) {
+ if (chunk->dead || !entry->connector ||
+ !entry->connector->inode) {
spin_unlock(&entry->lock);
mutex_unlock(&entry->group->mark_mutex);
if (new)
@@ -276,8 +292,8 @@ static void untag_chunk(struct node *p)
if (!new)
goto Fallback;
- if (fsnotify_add_mark_locked(&new->mark, entry->group, entry->inode,
- NULL, 1)) {
+ if (fsnotify_add_mark_locked(&new->mark, entry->group,
+ entry->connector->inode, NULL, 1)) {
fsnotify_put_mark(&new->mark);
goto Fallback;
}
@@ -408,7 +424,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
mutex_lock(&old_entry->group->mark_mutex);
spin_lock(&old_entry->lock);
- if (!old_entry->inode) {
+ if (!old_entry->connector || !old_entry->connector->inode) {
/* old_entry is being shot, lets just lie */
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
@@ -418,7 +434,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
}
if (fsnotify_add_mark_locked(chunk_entry, old_entry->group,
- old_entry->inode, NULL, 1)) {
+ old_entry->connector->inode, NULL, 1)) {
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
fsnotify_put_mark(chunk_entry);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index cf1fa43512c1..e990de915341 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1591,7 +1591,7 @@ static inline void handle_one(const struct inode *inode)
struct audit_tree_refs *p;
struct audit_chunk *chunk;
int count;
- if (likely(hlist_empty(&inode->i_fsnotify_marks)))
+ if (likely(!inode->i_fsnotify_marks))
return;
context = current->audit_context;
p = context->trees;
@@ -1634,7 +1634,7 @@ static void handle_path(const struct dentry *dentry)
seq = read_seqbegin(&rename_lock);
for(;;) {
struct inode *inode = d_backing_inode(d);
- if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
+ if (inode && unlikely(inode->i_fsnotify_marks)) {
struct audit_chunk *chunk;
chunk = audit_tree_lookup(inode);
if (chunk) {
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* Re: [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure
2017-01-20 13:21 ` [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure Jan Kara
@ 2017-01-21 15:52 ` Amir Goldstein
2017-01-25 9:41 ` Miklos Szeredi
1 sibling, 0 replies; 29+ messages in thread
From: Amir Goldstein @ 2017-01-21 15:52 UTC (permalink / raw)
To: Jan Kara; +Cc: linux-fsdevel, Miklos Szeredi, Paul Moore
On Fri, Jan 20, 2017 at 3:21 PM, Jan Kara <jack@suse.cz> wrote:
> Currently notification marks are attached to object (inode or vfsmnt) by
> a hlist_head in the object. The list is also protected by a spinlock in
> the object. So while there is any mark attached to the list of marks,
> the object must be pinned in memory (and thus e.g. last iput() deleting
> inode cannot happen). Also for list iteration in fsnotify() to work, we
> must hold fsnotify_mark_srcu lock so that mark itself and
> mark->obj_list.next cannot get freed. Thus we are required to wait for
> response to fanotify events from userspace process with
> fsnotify_mark_srcu lock held. That causes issues when userspace process
> is buggy and does not reply to some event - basically the whole
> notification subsystem gets eventually stuck.
>
> So to be able to drop fsnotify_mark_srcu lock while waiting for
> response, we have to pin the mark in memory and make sure it stays in
> the object list (as removing the mark waiting for response could lead to
> lost notification events for groups later in the list). However we don't
> want inode reclaim to block on such mark as that would lead to system
> just locking up elsewhere.
>
> This commit tries to pave a way towards solving these conflicting
> lifetime needs. Instead of anchoring the list of marks directly in the
> object, we anchor it in a dedicated structure (fsnotify_mark_connector) and
> just point to that structure from the object. Also the list is protected
> by a spinlock contained in that structure. With this, we can detach
> notification marks from object without having to modify the list itself.
>
> Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure
2017-01-20 13:21 ` [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure Jan Kara
2017-01-21 15:52 ` Amir Goldstein
@ 2017-01-25 9:41 ` Miklos Szeredi
2017-01-31 15:41 ` Jan Kara
1 sibling, 1 reply; 29+ messages in thread
From: Miklos Szeredi @ 2017-01-25 9:41 UTC (permalink / raw)
To: Jan Kara; +Cc: linux-fsdevel, Amir Goldstein, Paul Moore
On Fri, Jan 20, 2017 at 2:21 PM, Jan Kara <jack@suse.cz> wrote:
> Currently notification marks are attached to object (inode or vfsmnt) by
> a hlist_head in the object. The list is also protected by a spinlock in
> the object. So while there is any mark attached to the list of marks,
> the object must be pinned in memory (and thus e.g. last iput() deleting
> inode cannot happen). Also for list iteration in fsnotify() to work, we
> must hold fsnotify_mark_srcu lock so that mark itself and
> mark->obj_list.next cannot get freed. Thus we are required to wait for
> response to fanotify events from userspace process with
> fsnotify_mark_srcu lock held. That causes issues when userspace process
> is buggy and does not reply to some event - basically the whole
> notification subsystem gets eventually stuck.
>
> So to be able to drop fsnotify_mark_srcu lock while waiting for
> response, we have to pin the mark in memory and make sure it stays in
> the object list (as removing the mark waiting for response could lead to
> lost notification events for groups later in the list). However we don't
> want inode reclaim to block on such mark as that would lead to system
> just locking up elsewhere.
>
> This commit tries to pave a way towards solving these conflicting
> lifetime needs. Instead of anchoring the list of marks directly in the
> object, we anchor it in a dedicated structure (fsnotify_mark_connector) and
> just point to that structure from the object. Also the list is protected
> by a spinlock contained in that structure. With this, we can detach
> notification marks from object without having to modify the list itself.
I wonder if this big patch could be conveniently split up into
structural and functional parts.
I.e. first add the connector structure but make its lifetime match
that of the inode. That would mean just adding the extra
dereferences, but not the tricky rcu-conformant creation and
destruction of the connecor.
Also there seems to be a fair amount of moving code around, which
could warrant a separate patch for clarity.
Thanks,
Miklos
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure
2017-01-25 9:41 ` Miklos Szeredi
@ 2017-01-31 15:41 ` Jan Kara
0 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-31 15:41 UTC (permalink / raw)
To: Miklos Szeredi; +Cc: Jan Kara, linux-fsdevel, Amir Goldstein, Paul Moore
On Wed 25-01-17 10:41:12, Miklos Szeredi wrote:
> On Fri, Jan 20, 2017 at 2:21 PM, Jan Kara <jack@suse.cz> wrote:
> > Currently notification marks are attached to object (inode or vfsmnt) by
> > a hlist_head in the object. The list is also protected by a spinlock in
> > the object. So while there is any mark attached to the list of marks,
> > the object must be pinned in memory (and thus e.g. last iput() deleting
> > inode cannot happen). Also for list iteration in fsnotify() to work, we
> > must hold fsnotify_mark_srcu lock so that mark itself and
> > mark->obj_list.next cannot get freed. Thus we are required to wait for
> > response to fanotify events from userspace process with
> > fsnotify_mark_srcu lock held. That causes issues when userspace process
> > is buggy and does not reply to some event - basically the whole
> > notification subsystem gets eventually stuck.
> >
> > So to be able to drop fsnotify_mark_srcu lock while waiting for
> > response, we have to pin the mark in memory and make sure it stays in
> > the object list (as removing the mark waiting for response could lead to
> > lost notification events for groups later in the list). However we don't
> > want inode reclaim to block on such mark as that would lead to system
> > just locking up elsewhere.
> >
> > This commit tries to pave a way towards solving these conflicting
> > lifetime needs. Instead of anchoring the list of marks directly in the
> > object, we anchor it in a dedicated structure (fsnotify_mark_connector) and
> > just point to that structure from the object. Also the list is protected
> > by a spinlock contained in that structure. With this, we can detach
> > notification marks from object without having to modify the list itself.
>
> I wonder if this big patch could be conveniently split up into
> structural and functional parts.
>
> I.e. first add the connector structure but make its lifetime match
> that of the inode. That would mean just adding the extra
> dereferences, but not the tricky rcu-conformant creation and
> destruction of the connecor.
Yeah, probably I could split it into three parts. The addition of
dynamically added (but freed only on object free) connector structure,
the change of locking from i_lock/d_lock into connector->lock, the freeing
of connector when the last mark on the list gets freed (RCU bits go there).
> Also there seems to be a fair amount of moving code around, which
> could warrant a separate patch for clarity.
I don't think there's substantial moving of code. However the locking
change above results in some functions becoming redundant so I just deleted
them. After the split it should be easier to understand.
Honza
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
^ permalink raw reply [flat|nested] 29+ messages in thread
* [PATCH 07/22] inotify: Do not drop mark reference under idr_lock
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (5 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 06/22] fsnotify: Attach marks to object via dedicated head structure Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 08/22] fsnotify: Move queueing of mark for destruction into fsnotify_put_mark() Jan Kara
` (14 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Dropping mark reference can result in mark being freed. Although it
should not happen in inotify_remove_from_idr() since caller should hold
another reference, just don't risk lock up just after WARN_ON
unnecessarily. Also fold do_inotify_remove_from_idr() into the single
callsite as that function really is just two lines of real code.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/inotify/inotify_user.c | 24 ++++++------------------
1 file changed, 6 insertions(+), 18 deletions(-)
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 3697567c7897..06dae605158d 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -397,21 +397,6 @@ static struct inotify_inode_mark *inotify_idr_find(struct fsnotify_group *group,
return i_mark;
}
-static void do_inotify_remove_from_idr(struct fsnotify_group *group,
- struct inotify_inode_mark *i_mark)
-{
- struct idr *idr = &group->inotify_data.idr;
- spinlock_t *idr_lock = &group->inotify_data.idr_lock;
- int wd = i_mark->wd;
-
- assert_spin_locked(idr_lock);
-
- idr_remove(idr, wd);
-
- /* removed from the idr, drop that ref */
- fsnotify_put_mark(&i_mark->fsn_mark);
-}
-
/*
* Remove the mark from the idr (if present) and drop the reference
* on the mark because it was in the idr.
@@ -419,6 +404,7 @@ static void do_inotify_remove_from_idr(struct fsnotify_group *group,
static void inotify_remove_from_idr(struct fsnotify_group *group,
struct inotify_inode_mark *i_mark)
{
+ struct idr *idr = &group->inotify_data.idr;
spinlock_t *idr_lock = &group->inotify_data.idr_lock;
struct inotify_inode_mark *found_i_mark = NULL;
int wd;
@@ -470,13 +456,15 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
BUG();
}
- do_inotify_remove_from_idr(group, i_mark);
+ idr_remove(idr, wd);
+ /* Removed from the idr, drop that ref. */
+ fsnotify_put_mark(&i_mark->fsn_mark);
out:
+ i_mark->wd = -1;
+ spin_unlock(idr_lock);
/* match the ref taken by inotify_idr_find_locked() */
if (found_i_mark)
fsnotify_put_mark(&found_i_mark->fsn_mark);
- i_mark->wd = -1;
- spin_unlock(idr_lock);
}
/*
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 08/22] fsnotify: Move queueing of mark for destruction into fsnotify_put_mark()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (6 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 07/22] inotify: Do not drop mark reference under idr_lock Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 09/22] fsnotify: Detach mark from object list when last reference is dropped Jan Kara
` (13 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Currently we queue mark into a list of marks for destruction in
__fsnotify_free_mark() and keep the last mark reference dangling. After the
worker waits for SRCU period, it drops the last reference to the mark
which frees it. This scheme has the disadvantage that if we hold
reference to a mark and drop and reacquire SRCU lock, the mark can get
freed immediately which is slightly inconvenient and we will need to
avoid this in the future.
Move to a scheme where queueing of mark into a list of marks for
destruction happens when the last reference to the mark is dropped. Also
drop reference to the mark held by group list already when mark is
removed from that list instead of dropping it only from the destruction
worker.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/mark.c | 73 ++++++++++++++++++++++----------------------------------
1 file changed, 29 insertions(+), 44 deletions(-)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 719e71d313e8..fd56af55f941 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -99,15 +99,18 @@ static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);
void fsnotify_get_mark(struct fsnotify_mark *mark)
{
+ WARN_ON_ONCE(!atomic_read(&mark->refcnt));
atomic_inc(&mark->refcnt);
}
void fsnotify_put_mark(struct fsnotify_mark *mark)
{
if (atomic_dec_and_test(&mark->refcnt)) {
- if (mark->group)
- fsnotify_put_group(mark->group);
- mark->free_mark(mark);
+ spin_lock(&destroy_lock);
+ list_add(&mark->g_list, &destroy_list);
+ spin_unlock(&destroy_lock);
+ queue_delayed_work(system_unbound_wq, &reaper_work,
+ FSNOTIFY_REAPER_DELAY);
}
}
@@ -210,14 +213,18 @@ static struct inode *fsnotify_detach_from_object(struct fsnotify_mark *mark)
* Remove mark from inode / vfsmount list, group list, drop inode reference
* if we got one.
*
- * Must be called with group->mark_mutex held.
+ * Must be called with group->mark_mutex held. The caller must either hold
+ * reference to the mark or be protected by fsnotify_mark_srcu.
*/
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));
+ WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
+ WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
+ atomic_read(&mark->refcnt) < 1 +
+ !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
spin_lock(&mark->lock);
@@ -246,18 +253,20 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
iput(inode);
atomic_dec(&group->num_marks);
+
+ /* Drop mark reference acquired in fsnotify_add_mark_locked() */
+ fsnotify_put_mark(mark);
}
/*
- * Prepare mark for freeing and add it to the list of marks prepared for
- * freeing. The actual freeing must happen after SRCU period ends and the
- * caller is responsible for this.
+ * Free fsnotify mark. The mark is actually only marked as being freed. The
+ * freeing is actually happening only once last reference to the mark is
+ * dropped from a workqueue which first waits for srcu period end.
*
- * The function returns true if the mark was added to the list of marks for
- * freeing. The function returns false if someone else has already called
- * __fsnotify_free_mark() for the mark.
+ * Caller must have a reference to the mark or be protected by
+ * fsnotify_mark_srcu.
*/
-static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
+void fsnotify_free_mark(struct fsnotify_mark *mark)
{
struct fsnotify_group *group = mark->group;
@@ -265,7 +274,7 @@ static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
spin_unlock(&mark->lock);
- return false;
+ return;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
spin_unlock(&mark->lock);
@@ -277,25 +286,6 @@ static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
*/
if (group->ops->freeing_mark)
group->ops->freeing_mark(mark, group);
-
- spin_lock(&destroy_lock);
- list_add(&mark->g_list, &destroy_list);
- spin_unlock(&destroy_lock);
-
- return true;
-}
-
-/*
- * Free fsnotify mark. The freeing is actually happening from a workqueue 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)
-{
- if (__fsnotify_free_mark(mark)) {
- queue_delayed_work(system_unbound_wq, &reaper_work,
- FSNOTIFY_REAPER_DELAY);
- }
}
void fsnotify_destroy_mark(struct fsnotify_mark *mark,
@@ -506,20 +496,13 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
return ret;
err:
- mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
+ mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE |
+ FSNOTIFY_MARK_FLAG_ATTACHED);
list_del_init(&mark->g_list);
- fsnotify_put_group(group);
- mark->group = NULL;
atomic_dec(&group->num_marks);
-
spin_unlock(&mark->lock);
- spin_lock(&destroy_lock);
- list_add(&mark->g_list, &destroy_list);
- spin_unlock(&destroy_lock);
- queue_delayed_work(system_unbound_wq, &reaper_work,
- FSNOTIFY_REAPER_DELAY);
-
+ fsnotify_put_mark(mark);
return ret;
}
@@ -618,7 +601,7 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
fsnotify_get_mark(mark);
fsnotify_detach_mark(mark);
mutex_unlock(&group->mark_mutex);
- __fsnotify_free_mark(mark);
+ fsnotify_free_mark(mark);
fsnotify_put_mark(mark);
}
}
@@ -676,7 +659,9 @@ void fsnotify_mark_destroy_list(void)
list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
list_del_init(&mark->g_list);
- fsnotify_put_mark(mark);
+ if (mark->group)
+ fsnotify_put_group(mark->group);
+ mark->free_mark(mark);
}
}
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 09/22] fsnotify: Detach mark from object list when last reference is dropped
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (7 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 08/22] fsnotify: Move queueing of mark for destruction into fsnotify_put_mark() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-21 15:50 ` Amir Goldstein
2017-01-20 13:21 ` [PATCH 10/22] fsnotify: Remove special handling of mark destruction on group shutdown Jan Kara
` (12 subsequent siblings)
21 siblings, 1 reply; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Instead of removing mark from object list from fsnotify_detach_mark(),
remove the mark when last reference to the mark is dropped. This will
allow fanotify to wait for userspace response to event without having to
hold onto fsnotify_mark_srcu.
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/mark.c | 172 ++++++++++++++++++++++++---------------
include/linux/fsnotify_backend.h | 4 +-
kernel/audit_tree.c | 20 +----
3 files changed, 111 insertions(+), 85 deletions(-)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index fd56af55f941..648f198f56ec 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -49,7 +49,13 @@
*
* A list of notification marks relating to inode / mnt is contained in
* fsnotify_mark_connector. That structure is alive as long as there are any marks
- * in the list and is also protected by fsnotify_mark_srcu.
+ * in the list and is also protected by fsnotify_mark_srcu. A mark gets
+ * detached from fsnotify_mark_connector when last reference to the mark is dropped.
+ * Thus having mark reference is enough to protect mark->connector pointer
+ * and to make sure fsnotify_mark_connector cannot disappear. Also because we remove
+ * mark from g_list before dropping mark reference associated with that, any
+ * mark found through g_list is guaranteed to have mark->connector set
+ * until we drop group->mark_mutex.
*
* LIFETIME:
* Inode marks survive between when they are added to an inode and when their
@@ -103,17 +109,6 @@ void fsnotify_get_mark(struct fsnotify_mark *mark)
atomic_inc(&mark->refcnt);
}
-void fsnotify_put_mark(struct fsnotify_mark *mark)
-{
- if (atomic_dec_and_test(&mark->refcnt)) {
- spin_lock(&destroy_lock);
- list_add(&mark->g_list, &destroy_list);
- spin_unlock(&destroy_lock);
- queue_delayed_work(system_unbound_wq, &reaper_work,
- FSNOTIFY_REAPER_DELAY);
- }
-}
-
static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
u32 new_mask = 0;
@@ -168,36 +163,67 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work)
}
}
-static struct inode *fsnotify_detach_from_object(struct fsnotify_mark *mark)
+static struct inode *fsnotify_detach_connector_from_object(
+ struct fsnotify_mark_connector *conn)
+{
+ struct inode *inode = NULL;
+
+ if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+ inode = conn->inode;
+ rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
+ inode->i_fsnotify_mask = 0;
+ conn->inode = NULL;
+ conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
+ } else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ rcu_assign_pointer(real_mount(conn->mnt)->mnt_fsnotify_marks,
+ NULL);
+ real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
+ conn->mnt = NULL;
+ conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ }
+
+ return inode;
+}
+
+static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
+{
+ if (mark->group)
+ fsnotify_put_group(mark->group);
+ mark->free_mark(mark);
+}
+
+void fsnotify_put_mark(struct fsnotify_mark *mark)
{
struct fsnotify_mark_connector *conn;
struct inode *inode = NULL;
bool free_conn = false;
+ /* Catch marks that were actually never attached to object */
+ if (!mark->connector && atomic_dec_and_test(&mark->refcnt)) {
+ fsnotify_final_mark_destroy(mark);
+ return;
+ }
+
+ /*
+ * We have to be careful so that traversals of obj_list under lock can
+ * safely grab mark reference.
+ */
+ if (!atomic_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+ return;
+
conn = mark->connector;
- spin_lock(&conn->lock);
hlist_del_init_rcu(&mark->obj_list);
if (hlist_empty(&conn->list)) {
- if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
- inode = conn->inode;
- rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
- inode->i_fsnotify_mask = 0;
- conn->inode = NULL;
- conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
- } else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
- rcu_assign_pointer(
- real_mount(conn->mnt)->mnt_fsnotify_marks,
- NULL);
- real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
- conn->mnt = NULL;
- conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
- }
+ inode = fsnotify_detach_connector_from_object(conn);
free_conn = true;
} else
__fsnotify_recalc_mask(conn);
mark->connector = NULL;
spin_unlock(&conn->lock);
+ if (inode)
+ iput(inode);
+
if (free_conn) {
spin_lock(&destroy_lock);
conn->destroy_next = connector_destroy_list;
@@ -205,20 +231,31 @@ static struct inode *fsnotify_detach_from_object(struct fsnotify_mark *mark)
spin_unlock(&destroy_lock);
queue_work(system_unbound_wq, &connector_reaper_work);
}
-
- return inode;
+ /*
+ * 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.
+ */
+ spin_lock(&destroy_lock);
+ list_add(&mark->g_list, &destroy_list);
+ spin_unlock(&destroy_lock);
+ queue_delayed_work(system_unbound_wq, &reaper_work,
+ FSNOTIFY_REAPER_DELAY);
}
/*
- * Remove mark from inode / vfsmount list, group list, drop inode reference
- * if we got one.
+ * Mark mark as detached, remove it from group list. Mark still stays in object
+ * list until its last reference is dropped. Note that we rely on mark being
+ * removed from group list before corresponding reference to it is dropped. In
+ * particular we rely on mark->connector being valid while we hold
+ * group->mark_mutex if we found the mark through g_list.
*
* Must be called with group->mark_mutex held. The caller must either hold
* reference to the mark or be protected by fsnotify_mark_srcu.
*/
void fsnotify_detach_mark(struct fsnotify_mark *mark)
{
- struct inode *inode = NULL;
struct fsnotify_group *group = mark->group;
WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
@@ -227,31 +264,15 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
!!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
spin_lock(&mark->lock);
-
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
spin_unlock(&mark->lock);
return;
}
-
mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
-
- inode = fsnotify_detach_from_object(mark);
-
- /*
- * 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);
-
spin_unlock(&mark->lock);
- if (inode)
- iput(inode);
-
atomic_dec(&group->num_marks);
/* Drop mark reference acquired in fsnotify_add_mark_locked() */
@@ -433,7 +454,9 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
hlist_for_each_entry(lmark, &conn->list, obj_list) {
last = lmark;
- if ((lmark->group == mark->group) && !allow_dups) {
+ if ((lmark->group == mark->group) &&
+ (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
+ !allow_dups) {
err = -EEXIST;
goto out_err;
}
@@ -484,7 +507,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
mark->group = group;
list_add(&mark->g_list, &group->marks_list);
atomic_inc(&group->num_marks);
- fsnotify_get_mark(mark); /* for i_list and g_list */
+ fsnotify_get_mark(mark); /* for g_list */
spin_unlock(&mark->lock);
ret = fsnotify_add_mark_list(mark, inode, mnt, allow_dups);
@@ -530,7 +553,8 @@ struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_mark_connector **connp,
if (!conn)
return NULL;
hlist_for_each_entry(mark, &conn->list, obj_list) {
- if (mark->group == group) {
+ if (mark->group == group &&
+ (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
fsnotify_get_mark(mark);
spin_unlock(&conn->lock);
return mark;
@@ -610,23 +634,39 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp)
{
struct fsnotify_mark_connector *conn;
- struct fsnotify_mark *mark;
+ struct fsnotify_mark *mark, *old_mark = NULL;
+ struct inode *inode;
- while ((conn = fsnotify_grab_connector(connp))) {
- /*
- * We have to be careful since we can race with e.g.
- * fsnotify_clear_marks_by_group() and once we drop the list
- * 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.
- */
- mark = hlist_entry(conn->list.first, struct fsnotify_mark,
- obj_list);
+ conn = fsnotify_grab_connector(connp);
+ if (!conn)
+ return;
+ /*
+ * We have to be careful since we can race with e.g.
+ * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
+ * list can get modified. However we are holding mark reference and
+ * thus our mark cannot be removed from obj_list so we can continue
+ * iteration after regaining conn->lock.
+ */
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
fsnotify_get_mark(mark);
spin_unlock(&conn->lock);
+ if (old_mark)
+ fsnotify_put_mark(old_mark);
+ old_mark = mark;
fsnotify_destroy_mark(mark, mark->group);
- fsnotify_put_mark(mark);
+ spin_lock(&conn->lock);
}
+ /*
+ * Detach list from object now so that we don't pin inode until all
+ * mark references get dropped. It would lead to strange results such
+ * as delaying inode deletion or blocking unmount.
+ */
+ inode = fsnotify_detach_connector_from_object(conn);
+ spin_unlock(&conn->lock);
+ if (old_mark)
+ fsnotify_put_mark(old_mark);
+ if (inode)
+ iput(inode);
}
/*
@@ -659,9 +699,7 @@ void fsnotify_mark_destroy_list(void)
list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
list_del_init(&mark->g_list);
- if (mark->group)
- fsnotify_put_group(mark->group);
- mark->free_mark(mark);
+ fsnotify_final_mark_destroy(mark);
}
}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index f3df68a64ee6..64ce249288ad 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -244,9 +244,9 @@ struct fsnotify_mark {
struct list_head g_list;
/* Protects inode / mnt pointers, flags, masks */
spinlock_t lock;
- /* List of marks for inode / vfsmount [connector->lock] */
+ /* List of marks for inode / vfsmount [connector->lock, mark ref] */
struct hlist_node obj_list;
- /* Head of list of marks for an object [mark->lock, group->mark_mutex] */
+ /* Head of list of marks for an object [mark ref] */
struct fsnotify_mark_connector *connector;
/* Events types to ignore [mark->lock, group->mark_mutex] */
__u32 ignored_mask;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index a878a98f55b3..6962443f2216 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -172,27 +172,15 @@ static unsigned long inode_to_key(const struct inode *inode)
/*
* Function to return search key in our hash from chunk. Key 0 is special and
* should never be present in the hash.
- *
- * Must be called with chunk->mark.lock held to protect from connector
- * becoming NULL.
*/
-static unsigned long __chunk_to_key(struct audit_chunk *chunk)
+static unsigned long chunk_to_key(struct audit_chunk *chunk)
{
- if (!chunk->mark.connector)
+ /* We have a reference to the mark so it should be attached. */
+ if (WARN_ON_ONCE(!chunk->mark.connector))
return 0;
return (unsigned long)chunk->mark.connector->inode;
}
-static unsigned long chunk_to_key(struct audit_chunk *chunk)
-{
- unsigned long key;
-
- spin_lock(&chunk->mark.lock);
- key = __chunk_to_key(chunk);
- spin_unlock(&chunk->mark.lock);
- return key;
-}
-
static inline struct list_head *chunk_hash(unsigned long key)
{
unsigned long n = key / L1_CACHE_BYTES;
@@ -202,7 +190,7 @@ static inline struct list_head *chunk_hash(unsigned long key)
/* hash_lock & entry->lock is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
- unsigned long key = __chunk_to_key(chunk);
+ unsigned long key = chunk_to_key(chunk);
struct list_head *list;
if (!key)
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 10/22] fsnotify: Remove special handling of mark destruction on group shutdown
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (8 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 09/22] fsnotify: Detach mark from object list when last reference is dropped Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 11/22] fsnotify: Provide framework for dropping SRCU lock in ->handle_event Jan Kara
` (11 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Currently we queue all marks for destruction on group shutdown and then
destroy them from fsnotify_destroy_group() instead from a worker thread
which is the usual path. However worker can already be processing some
list of marks to destroy so this does not make 100% all marks are really
destroyed by the time group is shut down. This isn't a big problem as
each mark holds group reference and thus group stays partially alive
until all marks are really freed but there's no point in complicating
our lives - just wait for the delayed work to be finished instead.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fsnotify.h | 6 ++----
fs/notify/group.c | 10 ++++++----
fs/notify/mark.c | 7 ++++---
3 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 24bc549e9709..cbb9df3b10d0 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -36,10 +36,8 @@ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
}
/* prepare for freeing all marks associated with given group */
extern void fsnotify_detach_group_marks(struct fsnotify_group *group);
-/*
- * wait for fsnotify_mark_srcu period to end and free all marks in destroy_list
- */
-extern void fsnotify_mark_destroy_list(void);
+/* Wait until all marks queued for destruction are destroyed */
+extern void fsnotify_wait_marks_destroyed(void);
/*
* update the dentry->d_flags of all of inode's children to indicate if inode cares
diff --git a/fs/notify/group.c b/fs/notify/group.c
index fbe3cbebec16..0fb4aadcc19f 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -66,14 +66,16 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
*/
fsnotify_group_stop_queueing(group);
- /* clear all inode marks for this group, attach them to destroy_list */
+ /* Clear all marks for this group and queue them for destruction */
fsnotify_detach_group_marks(group);
/*
- * Wait for fsnotify_mark_srcu period to end and free all marks in
- * destroy_list
+ * Wait until all marks get really destroyed. We could actually destroy
+ * them ourselves instead of waiting for worker to do it, however that
+ * would be racy as worker can already be processing some marks before
+ * we even entered fsnotify_destroy_group().
*/
- fsnotify_mark_destroy_list();
+ fsnotify_wait_marks_destroyed();
/*
* Since we have waited for fsnotify_mark_srcu in
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 648f198f56ec..e22e87bbcd84 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -685,7 +685,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
* Destroy all marks in destroy_list, waits for SRCU period to finish before
* actually freeing marks.
*/
-void fsnotify_mark_destroy_list(void)
+static void fsnotify_mark_destroy_workfn(struct work_struct *work)
{
struct fsnotify_mark *mark, *next;
struct list_head private_destroy_list;
@@ -703,7 +703,8 @@ void fsnotify_mark_destroy_list(void)
}
}
-static void fsnotify_mark_destroy_workfn(struct work_struct *work)
+/* Wait for all marks queued for destruction to be actually destroyed */
+void fsnotify_wait_marks_destroyed(void)
{
- fsnotify_mark_destroy_list();
+ flush_delayed_work(&reaper_work);
}
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 11/22] fsnotify: Provide framework for dropping SRCU lock in ->handle_event
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (9 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 10/22] fsnotify: Remove special handling of mark destruction on group shutdown Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 12/22] fsnotify: Pass SRCU index into handle_event handler Jan Kara
` (10 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
fanotify wants to drop fsnotify_mark_srcu lock when waiting for response
from userspace so that the whole notification subsystem is not blocked
during that time. This patch provides a framework for safely getting
mark reference for a mark found in the object list which pins the mark
in that list. We can then drop fsnotify_mark_srcu, wait for userspace
response and then safely continue iteration of the object list once we
reaquire fsnotify_mark_srcu.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/group.c | 1 +
fs/notify/mark.c | 86 ++++++++++++++++++++++++++++++++++++++++
include/linux/fsnotify_backend.h | 8 ++++
3 files changed, 95 insertions(+)
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 0fb4aadcc19f..79439cdf16e0 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -126,6 +126,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
/* set to 0 when there a no external references to this group */
atomic_set(&group->refcnt, 1);
atomic_set(&group->num_marks, 0);
+ atomic_set(&group->user_waits, 0);
spin_lock_init(&group->notification_lock);
INIT_LIST_HEAD(&group->notification_list);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index e22e87bbcd84..8800db34e19f 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -109,6 +109,16 @@ void fsnotify_get_mark(struct fsnotify_mark *mark)
atomic_inc(&mark->refcnt);
}
+/*
+ * Get mark reference when we found the mark via lockless traversal of object
+ * list. Mark can be already removed from the list by now and on its way to be
+ * destroyed once SRCU period ends.
+ */
+static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark)
+{
+ return atomic_inc_not_zero(&mark->refcnt);
+}
+
static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
u32 new_mask = 0;
@@ -244,6 +254,76 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
FSNOTIFY_REAPER_DELAY);
}
+bool fsnotify_prepare_user_wait(struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
+ int *srcu_idx)
+{
+ struct fsnotify_group *group;
+
+ if (WARN_ON_ONCE(!inode_mark && !vfsmount_mark))
+ return false;
+
+ if (inode_mark)
+ group = inode_mark->group;
+ else
+ group = vfsmount_mark->group;
+
+ /*
+ * Since acquisition of mark reference is an atomic op as well, we can
+ * be sure this inc is seen before any effect of refcount increment.
+ */
+ atomic_inc(&group->user_waits);
+
+ if (inode_mark) {
+ /* This can fail if mark is being removed */
+ if (!fsnotify_get_mark_safe(inode_mark))
+ goto out_wait;
+ }
+ if (vfsmount_mark) {
+ if (!fsnotify_get_mark_safe(vfsmount_mark))
+ goto out_inode;
+ }
+
+ /*
+ * Now that both marks are pinned by refcount in the inode / vfsmount
+ * lists, we can drop SRCU lock, and safely resume the list iteration
+ * once userspace returns.
+ */
+ srcu_read_unlock(&fsnotify_mark_srcu, *srcu_idx);
+
+ return true;
+out_inode:
+ if (inode_mark)
+ fsnotify_put_mark(inode_mark);
+out_wait:
+ if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
+ wake_up(&group->notification_waitq);
+ return false;
+}
+
+void fsnotify_finish_user_wait(struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
+ int *srcu_idx)
+{
+ struct fsnotify_group *group = NULL;
+
+ *srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+ if (inode_mark) {
+ group = inode_mark->group;
+ fsnotify_put_mark(inode_mark);
+ }
+ if (vfsmount_mark) {
+ group = vfsmount_mark->group;
+ fsnotify_put_mark(vfsmount_mark);
+ }
+ /*
+ * We abuse notification_waitq on group shutdown for waiting for all
+ * marks pinned when waiting for userspace.
+ */
+ if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
+ wake_up(&group->notification_waitq);
+}
+
/*
* Mark mark as detached, remove it from group list. Mark still stays in object
* list until its last reference is dropped. Note that we rely on mark being
@@ -628,6 +708,12 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
fsnotify_free_mark(mark);
fsnotify_put_mark(mark);
}
+ /*
+ * Some marks can still be pinned when waiting for response from
+ * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+ * not succeed now so this wait is race-free.
+ */
+ wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
}
/* Destroy all marks attached to inode / vfsmount */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 64ce249288ad..786dc1cf715c 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -162,6 +162,8 @@ struct fsnotify_group {
struct fsnotify_event *overflow_event; /* Event we queue when the
* notification list is too
* full */
+ atomic_t user_waits; /* Number of tasks waiting for user
+ * response */
/* groups can define private fields here or use the void *private */
union {
@@ -367,6 +369,12 @@ extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, un
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_unmount_inodes(struct super_block *sb);
+extern void fsnotify_finish_user_wait(struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
+ int *srcu_idx);
+extern bool fsnotify_prepare_user_wait(struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
+ int *srcu_idx);
/* put here because inotify does some weird stuff when destroying watches */
extern void fsnotify_init_event(struct fsnotify_event *event,
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 12/22] fsnotify: Pass SRCU index into handle_event handler
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (10 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 11/22] fsnotify: Provide framework for dropping SRCU lock in ->handle_event Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response Jan Kara
` (9 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Pass index acquired from srcu_read_lock into ->handle_event() handler so
that it can release and reacquire SRCU lock via
fsnotify_prepare_user_wait() and fsnotify_finish_user_wait() functions.
These functions also make sure current marks are appropriately pinned so
that iteration protected by srcu in fsnotify() stays safe.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/dnotify/dnotify.c | 3 ++-
fs/notify/fanotify/fanotify.c | 3 ++-
fs/notify/fsnotify.c | 7 ++++---
fs/notify/inotify/inotify.h | 3 ++-
fs/notify/inotify/inotify_fsnotify.c | 3 ++-
fs/notify/inotify/inotify_user.c | 2 +-
include/linux/fsnotify_backend.h | 3 ++-
kernel/audit_fsnotify.c | 3 ++-
kernel/audit_tree.c | 3 ++-
kernel/audit_watch.c | 3 ++-
10 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 41b2a070761c..19abc5f717dd 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -85,7 +85,8 @@ static int dnotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie)
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx)
{
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index bbc175d4213d..2e8ca885fb3e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -178,7 +178,8 @@ static int fanotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *fanotify_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie)
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx)
{
int ret = 0;
struct fanotify_event_info *event;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index d512ef9f75fc..f9920e4acd10 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -127,7 +127,8 @@ static int send_to_group(struct inode *to_tell,
struct fsnotify_mark *vfsmount_mark,
__u32 mask, const void *data,
int data_is, u32 cookie,
- const unsigned char *file_name)
+ const unsigned char *file_name,
+ int *srcu_idx)
{
struct fsnotify_group *group = NULL;
__u32 inode_test_mask = 0;
@@ -178,7 +179,7 @@ static int send_to_group(struct inode *to_tell,
return group->ops->handle_event(group, to_tell, inode_mark,
vfsmount_mark, mask, data, data_is,
- file_name, cookie);
+ file_name, cookie, srcu_idx);
}
/*
@@ -285,7 +286,7 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
}
}
ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
- data, data_is, cookie, file_name);
+ data, data_is, cookie, file_name, &idx);
if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
goto out;
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index a6f5907a3fee..507840969edc 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,7 @@ extern int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie);
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx);
extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 8421f44b3cb3..35f2f39514b8 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,8 @@ int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie)
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx)
{
struct inotify_inode_mark *i_mark;
struct inotify_event_info *event;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 06dae605158d..9fe125f58113 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -477,7 +477,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
/* Queue ignore event for the watch */
inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
- NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
+ NULL, FSNOTIFY_EVENT_NONE, NULL, 0, NULL);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
/* remove this mark from the idr */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 786dc1cf715c..b944f084cb95 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -97,7 +97,8 @@ struct fsnotify_ops {
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie);
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx);
void (*free_group_priv)(struct fsnotify_group *group);
void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
void (*free_event)(struct fsnotify_event *event);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 7ea57e516029..ae8599c7aa81 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -168,7 +168,8 @@ static int audit_mark_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *dname, u32 cookie)
+ const unsigned char *dname, u32 cookie,
+ int *srcu_idx)
{
struct audit_fsnotify_mark *audit_mark;
const struct inode *inode = NULL;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 6962443f2216..0fe77336a2cd 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -979,7 +979,8 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *file_name, u32 cookie)
+ const unsigned char *file_name, u32 cookie,
+ int *srcu_idx)
{
return 0;
}
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index f79e4658433d..4c06e961e4ba 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -472,7 +472,8 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
- const unsigned char *dname, u32 cookie)
+ const unsigned char *dname, u32 cookie,
+ int *srcu_idx)
{
const struct inode *inode;
struct audit_parent *parent;
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (11 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 12/22] fsnotify: Pass SRCU index into handle_event handler Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-25 15:22 ` Miklos Szeredi
2017-01-20 13:21 ` [PATCH 14/22] fsnotify: Remove fsnotify_set_mark_{,ignored_}mask_locked() Jan Kara
` (8 subsequent siblings)
21 siblings, 1 reply; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
When userspace task processing fanotify permission events screws up and
does not respond, fsnotify_mark_srcu SRCU is held indefinitely which
causes further hangs in the whole notification subsystem. Although we
cannot easily solve the problem of operations blocked waiting for
response from userspace, we can at least somewhat localize the damage by
dropping SRCU lock before waiting for userspace response and reacquiring
it when userspace responds.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fanotify/fanotify.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 2e8ca885fb3e..98d7dc94d34c 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -61,14 +61,28 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
static int fanotify_get_response(struct fsnotify_group *group,
- struct fanotify_perm_event_info *event)
+ struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
+ struct fanotify_perm_event_info *event,
+ int *srcu_idx)
{
int ret;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+ /*
+ * fsnotify_prepare_user_wait() fails if we race with mark deletion.
+ * Just let the operation pass in that case.
+ */
+ if (!fsnotify_prepare_user_wait(inode_mark, vfsmount_mark, srcu_idx)) {
+ event->response = FAN_ALLOW;
+ goto out;
+ }
+
wait_event(group->fanotify_data.access_waitq, event->response);
+ fsnotify_finish_user_wait(inode_mark, vfsmount_mark, srcu_idx);
+out:
/* userspace responded, convert to something usable */
switch (event->response) {
case FAN_ALLOW:
@@ -220,7 +234,8 @@ static int fanotify_handle_event(struct fsnotify_group *group,
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
if (mask & FAN_ALL_PERM_EVENTS) {
- ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event));
+ ret = fanotify_get_response(group, inode_mark, fanotify_mark,
+ FANOTIFY_PE(fsn_event), srcu_idx);
fsnotify_destroy_event(group, fsn_event);
}
#endif
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* Re: [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response
2017-01-20 13:21 ` [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response Jan Kara
@ 2017-01-25 15:22 ` Miklos Szeredi
2017-01-31 13:28 ` Jan Kara
0 siblings, 1 reply; 29+ messages in thread
From: Miklos Szeredi @ 2017-01-25 15:22 UTC (permalink / raw)
To: Jan Kara; +Cc: linux-fsdevel, Amir Goldstein, Paul Moore
On Fri, Jan 20, 2017 at 2:21 PM, Jan Kara <jack@suse.cz> wrote:
> When userspace task processing fanotify permission events screws up and
> does not respond, fsnotify_mark_srcu SRCU is held indefinitely which
> causes further hangs in the whole notification subsystem. Although we
> cannot easily solve the problem of operations blocked waiting for
> response from userspace, we can at least somewhat localize the damage by
> dropping SRCU lock before waiting for userspace response and reacquiring
> it when userspace responds.
>
> Reviewed-by: Amir Goldstein <amir73il@gmail.com>
> Signed-off-by: Jan Kara <jack@suse.cz>
> ---
> fs/notify/fanotify/fanotify.c | 19 +++++++++++++++++--
> 1 file changed, 17 insertions(+), 2 deletions(-)
>
> diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
> index 2e8ca885fb3e..98d7dc94d34c 100644
> --- a/fs/notify/fanotify/fanotify.c
> +++ b/fs/notify/fanotify/fanotify.c
> @@ -61,14 +61,28 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
>
> #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
> static int fanotify_get_response(struct fsnotify_group *group,
> - struct fanotify_perm_event_info *event)
> + struct fsnotify_mark *inode_mark,
> + struct fsnotify_mark *vfsmount_mark,
> + struct fanotify_perm_event_info *event,
> + int *srcu_idx)
Should these (inode_mark, vfsmount_mark, srcu_idx) be passed in an
opaque struct to simplify the interface?
Alternatively, waiting could be done by fsnotify core (a-la poll).
That's a bit bigger change though.
Thanks,
Miklos
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response
2017-01-25 15:22 ` Miklos Szeredi
@ 2017-01-31 13:28 ` Jan Kara
0 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-31 13:28 UTC (permalink / raw)
To: Miklos Szeredi; +Cc: Jan Kara, linux-fsdevel, Amir Goldstein, Paul Moore
On Wed 25-01-17 16:22:12, Miklos Szeredi wrote:
> On Fri, Jan 20, 2017 at 2:21 PM, Jan Kara <jack@suse.cz> wrote:
> > When userspace task processing fanotify permission events screws up and
> > does not respond, fsnotify_mark_srcu SRCU is held indefinitely which
> > causes further hangs in the whole notification subsystem. Although we
> > cannot easily solve the problem of operations blocked waiting for
> > response from userspace, we can at least somewhat localize the damage by
> > dropping SRCU lock before waiting for userspace response and reacquiring
> > it when userspace responds.
> >
> > Reviewed-by: Amir Goldstein <amir73il@gmail.com>
> > Signed-off-by: Jan Kara <jack@suse.cz>
> > ---
> > fs/notify/fanotify/fanotify.c | 19 +++++++++++++++++--
> > 1 file changed, 17 insertions(+), 2 deletions(-)
> >
> > diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
> > index 2e8ca885fb3e..98d7dc94d34c 100644
> > --- a/fs/notify/fanotify/fanotify.c
> > +++ b/fs/notify/fanotify/fanotify.c
> > @@ -61,14 +61,28 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
> >
> > #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
> > static int fanotify_get_response(struct fsnotify_group *group,
> > - struct fanotify_perm_event_info *event)
> > + struct fsnotify_mark *inode_mark,
> > + struct fsnotify_mark *vfsmount_mark,
> > + struct fanotify_perm_event_info *event,
> > + int *srcu_idx)
>
> Should these (inode_mark, vfsmount_mark, srcu_idx) be passed in an
> opaque struct to simplify the interface?
After some thought, having an opaque struct containing also mark pointers
and pass it around instead of srcu_idx looks like a neat idea. We will have
mark pointers in two places (explicit arguments of ->handle_event and the
opaque struct) but that should not be a problem as notification frameworks
cannot play any tricks with them anyway as it would break iteration in the
generic notification core. I'll do this, thanks for the idea.
Honza
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
^ permalink raw reply [flat|nested] 29+ messages in thread
* [PATCH 14/22] fsnotify: Remove fsnotify_set_mark_{,ignored_}mask_locked()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (12 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 13/22] fanotify: Release SRCU lock when waiting for userspace response Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 15/22] fsnotify: Remove fsnotify_recalc_{inode|vfsmount}_mask() Jan Kara
` (7 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
These helpers are now only a simple assignment and just obfuscate
what is going on. Remove them.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/dnotify/dnotify.c | 9 +++------
fs/notify/fanotify/fanotify_user.c | 9 ++++-----
fs/notify/inotify/inotify_user.c | 6 ++----
fs/notify/mark.c | 14 --------------
include/linux/fsnotify_backend.h | 4 ----
5 files changed, 9 insertions(+), 33 deletions(-)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 19abc5f717dd..2f89ed821ebc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -52,7 +52,7 @@ struct dnotify_mark {
*/
static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
{
- __u32 new_mask, old_mask;
+ __u32 new_mask = 0;
struct dnotify_struct *dn;
struct dnotify_mark *dn_mark = container_of(fsn_mark,
struct dnotify_mark,
@@ -60,14 +60,11 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
assert_spin_locked(&fsn_mark->lock);
- old_mask = fsn_mark->mask;
- new_mask = 0;
for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
- fsnotify_set_mark_mask_locked(fsn_mark, new_mask);
-
- if (old_mask == new_mask)
+ if (fsn_mark->mask == new_mask)
return;
+ fsn_mark->mask = new_mask;
fsnotify_recalc_mask(fsn_mark->connector);
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8dcec9eecafd..14a1036eee06 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -510,13 +510,12 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
tmask &= ~FAN_ONDIR;
oldmask = fsn_mark->mask;
- fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+ fsn_mark->mask = tmask;
} else {
__u32 tmask = fsn_mark->ignored_mask & ~mask;
if (flags & FAN_MARK_ONDIR)
tmask &= ~FAN_ONDIR;
-
- fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+ fsn_mark->ignored_mask = tmask;
}
*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
spin_unlock(&fsn_mark->lock);
@@ -598,13 +597,13 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
tmask |= FAN_ONDIR;
oldmask = fsn_mark->mask;
- fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+ fsn_mark->mask = tmask;
} else {
__u32 tmask = fsn_mark->ignored_mask | mask;
if (flags & FAN_MARK_ONDIR)
tmask |= FAN_ONDIR;
- fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+ fsn_mark->ignored_mask = tmask;
if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 9fe125f58113..ee12b8f01c01 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -516,14 +516,12 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
-
old_mask = fsn_mark->mask;
if (add)
- fsnotify_set_mark_mask_locked(fsn_mark, (fsn_mark->mask | mask));
+ fsn_mark->mask |= mask;
else
- fsnotify_set_mark_mask_locked(fsn_mark, mask);
+ fsn_mark->mask = mask;
new_mask = fsn_mark->mask;
-
spin_unlock(&fsn_mark->lock);
if (old_mask != new_mask) {
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 8800db34e19f..18184f26ec68 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -398,20 +398,6 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
fsnotify_free_mark(mark);
}
-void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
-{
- assert_spin_locked(&mark->lock);
-
- mark->mask = mask;
-}
-
-void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask)
-{
- assert_spin_locked(&mark->lock);
-
- mark->ignored_mask = mask;
-}
-
/*
* Sorting function for lists of fsnotify marks.
*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index b944f084cb95..c41afada7fe9 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -345,10 +345,6 @@ extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(str
extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode);
/* find (and take a reference) to a mark associated with group and vfsmount */
extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt);
-/* set the ignored_mask of a mark */
-extern void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask);
-/* set the mask of a mark (might pin the object into memory */
-extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask);
/* attach the mark to both the group and the inode */
extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
struct inode *inode, struct vfsmount *mnt, int allow_dups);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 15/22] fsnotify: Remove fsnotify_recalc_{inode|vfsmount}_mask()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (13 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 14/22] fsnotify: Remove fsnotify_set_mark_{,ignored_}mask_locked() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 16/22] fsnotify: Inline fsnotify_clear_{inode|vfsmount}_mark_group() Jan Kara
` (6 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
These helpers are just very thin wrappers now. Remove them.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fanotify/fanotify_user.c | 8 ++++----
fs/notify/inode_mark.c | 5 -----
fs/notify/inotify/inotify_user.c | 2 +-
fs/notify/vfsmount_mark.c | 5 -----
include/linux/fsnotify_backend.h | 4 ----
5 files changed, 5 insertions(+), 19 deletions(-)
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 14a1036eee06..b68cec253a21 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -541,7 +541,7 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (removed & real_mount(mnt)->mnt_fsnotify_mask)
- fsnotify_recalc_vfsmount_mask(mnt);
+ fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
@@ -570,7 +570,7 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (removed & inode->i_fsnotify_mask)
- fsnotify_recalc_inode_mask(inode);
+ fsnotify_recalc_mask(inode->i_fsnotify_marks);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
@@ -655,7 +655,7 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
- fsnotify_recalc_vfsmount_mask(mnt);
+ fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
@@ -692,7 +692,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
if (added & ~inode->i_fsnotify_mask)
- fsnotify_recalc_inode_mask(inode);
+ fsnotify_recalc_mask(inode->i_fsnotify_marks);
mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index b9370316727e..2188329da3c2 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -30,11 +30,6 @@
#include "../internal.h"
-void fsnotify_recalc_inode_mask(struct inode *inode)
-{
- fsnotify_recalc_mask(inode->i_fsnotify_marks);
-}
-
/*
* Given a group clear all of the inode marks associated with that group.
*/
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index ee12b8f01c01..bbcebf6beeb9 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -532,7 +532,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
/* update the inode with this new fsn_mark */
if (dropped || do_inode)
- fsnotify_recalc_inode_mask(inode);
+ fsnotify_recalc_mask(inode->i_fsnotify_marks);
}
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 8fc1aca21bcf..41bff46576c2 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -29,11 +29,6 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
-{
- fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
-}
-
void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{
fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index c41afada7fe9..606b24e6d2a9 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -336,10 +336,6 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group
/* Calculate mask of events for a list of marks */
extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
-/* run all marks associated with a vfsmount and update mnt->mnt_fsnotify_mask */
-extern void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt);
-/* run all marks associated with an inode and update inode->i_fsnotify_mask */
-extern void fsnotify_recalc_inode_mask(struct inode *inode);
extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark));
/* find (and take a reference) to a mark associated with group and inode */
extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 16/22] fsnotify: Inline fsnotify_clear_{inode|vfsmount}_mark_group()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (14 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 15/22] fsnotify: Remove fsnotify_recalc_{inode|vfsmount}_mask() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 17/22] fsnotify: Rename fsnotify_clear_marks_by_group_flags() Jan Kara
` (5 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Inline these helpers as they are very thin. We still keep them as we
don't want to expose details about how list type is determined.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/inode_mark.c | 8 --------
fs/notify/vfsmount_mark.c | 5 -----
include/linux/fsnotify_backend.h | 14 ++++++++++----
3 files changed, 10 insertions(+), 17 deletions(-)
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 2188329da3c2..bdc15f736082 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -31,14 +31,6 @@
#include "../internal.h"
/*
- * Given a group clear all of the inode marks associated with that group.
- */
-void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_INODE);
-}
-
-/*
* given a group and inode, find the mark associated with that combination.
* if found take a reference to that mark and return it, else return NULL
*/
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 41bff46576c2..1e692c56deec 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -29,11 +29,6 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
-}
-
/*
* given a group and vfsmount, find the mark associated with that combination.
* if found take a reference to that mark and return it, else return NULL
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 606b24e6d2a9..86586aa022ce 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -353,12 +353,18 @@ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
extern void fsnotify_detach_mark(struct fsnotify_mark *mark);
/* free mark */
extern void fsnotify_free_mark(struct fsnotify_mark *mark);
-/* run all the marks in a group, and clear all of the vfsmount marks */
-extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group);
-/* run all the marks in a group, and clear all of the inode marks */
-extern void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group);
/* run all the marks in a group, and clear all of the marks attached to given object type */
extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags);
+/* run all the marks in a group, and clear all of the vfsmount marks */
+static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
+{
+ fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
+}
+/* run all the marks in a group, and clear all of the inode marks */
+static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
+{
+ fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_INODE);
+}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_unmount_inodes(struct super_block *sb);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 17/22] fsnotify: Rename fsnotify_clear_marks_by_group_flags()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (15 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 16/22] fsnotify: Inline fsnotify_clear_{inode|vfsmount}_mark_group() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 18/22] fsnotify: Remove fsnotify_detach_group_marks() Jan Kara
` (4 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
The _flags() suffix in the function name was more confusing than
explaining so just remove it. Also rename the argument from 'flags' to
'type' to better explain what the function expects.
Suggested-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/mark.c | 12 +++++-------
include/linux/fsnotify_backend.h | 6 +++---
2 files changed, 8 insertions(+), 10 deletions(-)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 18184f26ec68..5eba0f4e9677 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -67,7 +67,7 @@
* - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes)
* - Something explicitly requests that it be removed. (fsnotify_destroy_mark)
* - The fsnotify_group associated with the mark is going away and all such marks
- * need to be cleaned up. (fsnotify_clear_marks_by_group)
+ * need to be cleaned up. (fsnotify_detach_group_marks)
*
* This has the very interesting property of being able to run concurrently with
* any (or all) other directions.
@@ -630,11 +630,9 @@ struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_mark_connector **connp,
return NULL;
}
-/*
- * clear any marks in a group in which mark->flags & flags is true
- */
-void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
- unsigned int flags)
+/* Clear any marks in a group with given type */
+void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
+ unsigned int type)
{
struct fsnotify_mark *lmark, *mark;
LIST_HEAD(to_free);
@@ -650,7 +648,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
*/
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
- if (mark->connector->flags & flags)
+ if (mark->connector->flags & type)
list_move(&mark->g_list, &to_free);
}
mutex_unlock(&group->mark_mutex);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 86586aa022ce..680b7e92101b 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -354,16 +354,16 @@ extern void fsnotify_detach_mark(struct fsnotify_mark *mark);
/* free mark */
extern void fsnotify_free_mark(struct fsnotify_mark *mark);
/* run all the marks in a group, and clear all of the marks attached to given object type */
-extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags);
+extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type);
/* run all the marks in a group, and clear all of the vfsmount marks */
static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
}
/* run all the marks in a group, and clear all of the inode marks */
static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_OBJ_TYPE_INODE);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 18/22] fsnotify: Remove fsnotify_detach_group_marks()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (16 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 17/22] fsnotify: Rename fsnotify_clear_marks_by_group_flags() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 19/22] fsnotify: Remove fsnotify_find_{inode|vfsmount}_mark() Jan Kara
` (3 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
The function is already mostly contained in what
fsnotify_clear_marks_by_group() does. Just update that function to not
select marks when all of them should be destroyed and remove
fsnotify_detach_group_marks().
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/fsnotify.h | 2 --
fs/notify/group.c | 9 +++++++-
fs/notify/mark.c | 45 +++++++++-------------------------------
include/linux/fsnotify_backend.h | 2 ++
4 files changed, 20 insertions(+), 38 deletions(-)
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index cbb9df3b10d0..da28dc44b244 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -34,8 +34,6 @@ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
{
fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
}
-/* prepare for freeing all marks associated with given group */
-extern void fsnotify_detach_group_marks(struct fsnotify_group *group);
/* Wait until all marks queued for destruction are destroyed */
extern void fsnotify_wait_marks_destroyed(void);
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 79439cdf16e0..32357534de18 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -67,7 +67,14 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
fsnotify_group_stop_queueing(group);
/* Clear all marks for this group and queue them for destruction */
- fsnotify_detach_group_marks(group);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES);
+
+ /*
+ * Some marks can still be pinned when waiting for response from
+ * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+ * not succeed now so this wait is race-free.
+ */
+ wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
/*
* Wait until all marks get really destroyed. We could actually destroy
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 5eba0f4e9677..b0db0a24d177 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -67,7 +67,7 @@
* - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes)
* - Something explicitly requests that it be removed. (fsnotify_destroy_mark)
* - The fsnotify_group associated with the mark is going away and all such marks
- * need to be cleaned up. (fsnotify_detach_group_marks)
+ * need to be cleaned up. (fsnotify_clear_marks_by_group)
*
* This has the very interesting property of being able to run concurrently with
* any (or all) other directions.
@@ -636,7 +636,13 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
{
struct fsnotify_mark *lmark, *mark;
LIST_HEAD(to_free);
+ struct list_head *head = &to_free;
+ /* Skip selection step if we want to clear all marks. */
+ if (type == FSNOTIFY_OBJ_ALL_TYPES) {
+ head = &group->marks_list;
+ goto clear;
+ }
/*
* We have to be really careful here. Anytime we drop mark_mutex, e.g.
* fsnotify_clear_marks_by_inode() can come and free marks. Even in our
@@ -653,13 +659,14 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
}
mutex_unlock(&group->mark_mutex);
+clear:
while (1) {
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
- if (list_empty(&to_free)) {
+ if (list_empty(head)) {
mutex_unlock(&group->mark_mutex);
break;
}
- mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+ mark = list_first_entry(head, struct fsnotify_mark, g_list);
fsnotify_get_mark(mark);
fsnotify_detach_mark(mark);
mutex_unlock(&group->mark_mutex);
@@ -668,38 +675,6 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
}
}
-/*
- * Given a group, prepare for freeing all the marks associated with that group.
- * The marks are attached to the list of marks prepared for destruction, the
- * caller is responsible for freeing marks in that list after SRCU period has
- * ended.
- */
-void fsnotify_detach_group_marks(struct fsnotify_group *group)
-{
- struct fsnotify_mark *mark;
-
- while (1) {
- mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
- if (list_empty(&group->marks_list)) {
- mutex_unlock(&group->mark_mutex);
- break;
- }
- mark = list_first_entry(&group->marks_list,
- struct fsnotify_mark, g_list);
- fsnotify_get_mark(mark);
- fsnotify_detach_mark(mark);
- mutex_unlock(&group->mark_mutex);
- fsnotify_free_mark(mark);
- fsnotify_put_mark(mark);
- }
- /*
- * Some marks can still be pinned when waiting for response from
- * userspace. Wait for those now. fsnotify_prepare_user_wait() will
- * not succeed now so this wait is race-free.
- */
- wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
-}
-
/* Destroy all marks attached to inode / vfsmount */
void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp)
{
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 680b7e92101b..812b1b151020 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -206,6 +206,8 @@ struct fsnotify_mark_connector {
spinlock_t lock;
#define FSNOTIFY_OBJ_TYPE_INODE 0x01
#define FSNOTIFY_OBJ_TYPE_VFSMOUNT 0x02
+#define FSNOTIFY_OBJ_ALL_TYPES (FSNOTIFY_OBJ_TYPE_INODE | \
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT)
unsigned int flags; /* Type of object [lock] */
union { /* Object pointer [lock] */
struct inode *inode;
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 19/22] fsnotify: Remove fsnotify_find_{inode|vfsmount}_mark()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (17 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 18/22] fsnotify: Remove fsnotify_detach_group_marks() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 20/22] fsnotify: Drop inode_mark.c Jan Kara
` (2 subsequent siblings)
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
These are very thin wrappers, just remove them. Drop
fs/notify/vfsmount_mark.c as it is empty now.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/Makefile | 2 +-
fs/notify/dnotify/dnotify.c | 4 ++--
fs/notify/fanotify/fanotify_user.c | 12 ++++++-----
fs/notify/fsnotify.h | 4 ----
fs/notify/inode_mark.c | 10 ---------
fs/notify/inotify/inotify_user.c | 2 +-
fs/notify/vfsmount_mark.c | 42 --------------------------------------
include/linux/fsnotify_backend.h | 8 ++++----
kernel/audit_tree.c | 3 ++-
kernel/audit_watch.c | 2 +-
10 files changed, 18 insertions(+), 71 deletions(-)
delete mode 100644 fs/notify/vfsmount_mark.c
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
index 96d3420d0242..ebb64a0282d1 100644
--- a/fs/notify/Makefile
+++ b/fs/notify/Makefile
@@ -1,5 +1,5 @@
obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o \
- mark.o vfsmount_mark.o fdinfo.o
+ mark.o fdinfo.o
obj-y += dnotify/
obj-y += inotify/
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 2f89ed821ebc..4c3bb4059f88 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -157,7 +157,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
if (!S_ISDIR(inode->i_mode))
return;
- fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
if (!fsn_mark)
return;
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
@@ -313,7 +313,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
mutex_lock(&dnotify_group->mark_mutex);
/* add the new_fsn_mark or find an old one. */
- fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
if (fsn_mark) {
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b68cec253a21..7b4d9d67f4f9 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -532,7 +532,8 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
int destroy_mark;
mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+ fsn_mark = fsnotify_find_mark(&real_mount(mnt)->mnt_fsnotify_marks,
+ group);
if (!fsn_mark) {
mutex_unlock(&group->mark_mutex);
return -ENOENT;
@@ -561,7 +562,7 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
int destroy_mark;
mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_inode_mark(group, inode);
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
if (!fsn_mark) {
mutex_unlock(&group->mark_mutex);
return -ENOENT;
@@ -577,7 +578,7 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
if (destroy_mark)
fsnotify_free_mark(fsn_mark);
- /* matches the fsnotify_find_inode_mark() */
+ /* matches the fsnotify_find_mark() */
fsnotify_put_mark(fsn_mark);
return 0;
@@ -645,7 +646,8 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
__u32 added;
mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+ fsn_mark = fsnotify_find_mark(&real_mount(mnt)->mnt_fsnotify_marks,
+ group);
if (!fsn_mark) {
fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
if (IS_ERR(fsn_mark)) {
@@ -682,7 +684,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
return 0;
mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_inode_mark(group, inode);
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
if (!fsn_mark) {
fsn_mark = fanotify_add_new_mark(group, inode, NULL);
if (IS_ERR(fsn_mark)) {
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index da28dc44b244..797daadad0bb 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -18,10 +18,6 @@ extern struct srcu_struct fsnotify_mark_srcu;
extern int fsnotify_compare_groups(struct fsnotify_group *a,
struct fsnotify_group *b);
-/* Find mark belonging to given group attached to given connector */
-extern struct fsnotify_mark *fsnotify_find_mark(
- struct fsnotify_mark_connector **connp,
- struct fsnotify_group *group);
/* Destroy all marks connected via given connector */
extern void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp);
/* run the list of all marks associated with inode and destroy them */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index bdc15f736082..5cc317bad082 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -30,16 +30,6 @@
#include "../internal.h"
-/*
- * given a group and inode, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
-struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
- struct inode *inode)
-{
- return fsnotify_find_mark(&inode->i_fsnotify_marks, group);
-}
-
/**
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
* @sb: superblock being unmounted.
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index bbcebf6beeb9..546a4c7d0f03 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -509,7 +509,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
mask = inotify_arg_to_mask(arg);
- fsn_mark = fsnotify_find_inode_mark(group, inode);
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
if (!fsn_mark)
return -ENOENT;
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
deleted file mode 100644
index 1e692c56deec..000000000000
--- a/fs/notify/vfsmount_mark.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mount.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-
-#include <linux/atomic.h>
-
-#include <linux/fsnotify_backend.h>
-#include "fsnotify.h"
-
-/*
- * given a group and vfsmount, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
-struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
- struct vfsmount *mnt)
-{
- struct mount *m = real_mount(mnt);
-
- return fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
-}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 812b1b151020..093f66818c6f 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -339,10 +339,10 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group
/* Calculate mask of events for a list of marks */
extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark));
-/* find (and take a reference) to a mark associated with group and inode */
-extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode);
-/* find (and take a reference) to a mark associated with group and vfsmount */
-extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt);
+/* Find mark belonging to given group in the list of marks */
+extern struct fsnotify_mark *fsnotify_find_mark(
+ struct fsnotify_mark_connector **connp,
+ struct fsnotify_group *group);
/* attach the mark to both the group and the inode */
extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
struct inode *inode, struct vfsmount *mnt, int allow_dups);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 0fe77336a2cd..b6785489fd3d 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -385,7 +385,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
struct node *p;
int n;
- old_entry = fsnotify_find_inode_mark(audit_tree_group, inode);
+ old_entry = fsnotify_find_mark(&inode->i_fsnotify_marks,
+ audit_tree_group);
if (!old_entry)
return create_chunk(inode, tree);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 4c06e961e4ba..800084cf0539 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -102,7 +102,7 @@ static inline struct audit_parent *audit_find_parent(struct inode *inode)
struct audit_parent *parent = NULL;
struct fsnotify_mark *entry;
- entry = fsnotify_find_inode_mark(audit_watch_group, inode);
+ entry = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_watch_group);
if (entry)
parent = container_of(entry, struct audit_parent, mark);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 20/22] fsnotify: Drop inode_mark.c
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (18 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 19/22] fsnotify: Remove fsnotify_find_{inode|vfsmount}_mark() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 21/22] fsnotify: Add group pointer in fsnotify_init_mark() Jan Kara
2017-01-20 13:21 ` [PATCH 22/22] fsnotify: Move ->free_mark callback to fsnotify_ops Jan Kara
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
inode_mark.c now contains only a single function. Move it to
fs/notify/fsnotify.c and remove inode_mark.c.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/Makefile | 4 +--
fs/notify/fsnotify.c | 57 ++++++++++++++++++++++++++++++++
fs/notify/inode_mark.c | 88 --------------------------------------------------
3 files changed, 59 insertions(+), 90 deletions(-)
delete mode 100644 fs/notify/inode_mark.c
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
index ebb64a0282d1..3e969ae91b60 100644
--- a/fs/notify/Makefile
+++ b/fs/notify/Makefile
@@ -1,5 +1,5 @@
-obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o \
- mark.o fdinfo.o
+obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o mark.o \
+ fdinfo.o
obj-y += dnotify/
obj-y += inotify/
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index f9920e4acd10..8d3eaf47199f 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -41,6 +41,63 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
fsnotify_clear_marks_by_mount(mnt);
}
+/**
+ * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
+ * @sb: superblock being unmounted.
+ *
+ * Called during unmount with no locks held, so needs to be safe against
+ * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
+ */
+void fsnotify_unmount_inodes(struct super_block *sb)
+{
+ struct inode *inode, *iput_inode = NULL;
+
+ spin_lock(&sb->s_inode_list_lock);
+ list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ /*
+ * We cannot __iget() an inode in state I_FREEING,
+ * I_WILL_FREE, or I_NEW which is fine because by that point
+ * the inode cannot have any associated watches.
+ */
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ /*
+ * If i_count is zero, the inode cannot have any watches and
+ * doing an __iget/iput with MS_ACTIVE clear would actually
+ * evict all inodes with zero i_count from icache which is
+ * unnecessarily violent and may in fact be illegal to do.
+ */
+ if (!atomic_read(&inode->i_count)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&sb->s_inode_list_lock);
+
+ if (iput_inode)
+ iput(iput_inode);
+
+ /* for each watch, send FS_UNMOUNT and then remove it */
+ fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+
+ fsnotify_inode_delete(inode);
+
+ iput_inode = inode;
+
+ spin_lock(&sb->s_inode_list_lock);
+ }
+ spin_unlock(&sb->s_inode_list_lock);
+
+ if (iput_inode)
+ iput(iput_inode);
+}
+
/*
* Given an inode, first check if we care what happens to our children. Inotify
* and dnotify both tell their parents about events. If we care about any event
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
deleted file mode 100644
index 5cc317bad082..000000000000
--- a/fs/notify/inode_mark.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-
-#include <linux/atomic.h>
-
-#include <linux/fsnotify_backend.h>
-#include "fsnotify.h"
-
-#include "../internal.h"
-
-/**
- * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
- * @sb: superblock being unmounted.
- *
- * Called during unmount with no locks held, so needs to be safe against
- * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
- */
-void fsnotify_unmount_inodes(struct super_block *sb)
-{
- struct inode *inode, *iput_inode = NULL;
-
- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- /*
- * We cannot __iget() an inode in state I_FREEING,
- * I_WILL_FREE, or I_NEW which is fine because by that point
- * the inode cannot have any associated watches.
- */
- spin_lock(&inode->i_lock);
- if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
- spin_unlock(&inode->i_lock);
- continue;
- }
-
- /*
- * If i_count is zero, the inode cannot have any watches and
- * doing an __iget/iput with MS_ACTIVE clear would actually
- * evict all inodes with zero i_count from icache which is
- * unnecessarily violent and may in fact be illegal to do.
- */
- if (!atomic_read(&inode->i_count)) {
- spin_unlock(&inode->i_lock);
- continue;
- }
-
- __iget(inode);
- spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_list_lock);
-
- if (iput_inode)
- iput(iput_inode);
-
- /* for each watch, send FS_UNMOUNT and then remove it */
- fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
-
- fsnotify_inode_delete(inode);
-
- iput_inode = inode;
-
- spin_lock(&sb->s_inode_list_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
-
- if (iput_inode)
- iput(iput_inode);
-}
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 21/22] fsnotify: Add group pointer in fsnotify_init_mark()
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (19 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 20/22] fsnotify: Drop inode_mark.c Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
2017-01-20 13:21 ` [PATCH 22/22] fsnotify: Move ->free_mark callback to fsnotify_ops Jan Kara
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Currently we initialize mark->group only in fsnotify_add_mark_lock().
However we will need to access fsnotify_ops of corresponding group from
fsnotify_put_mark() so we need mark->group initialized earlier. Do that
in fsnotify_init_mark() which has a consequence that once
fsnotify_init_mark() is called on a mark, the mark has to be destroyed
by fsnotify_put_mark().
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/dnotify/dnotify.c | 5 ++---
fs/notify/fanotify/fanotify_user.c | 4 ++--
fs/notify/inotify/inotify_user.c | 5 ++---
fs/notify/mark.c | 17 ++++++++++-------
include/linux/fsnotify_backend.h | 12 +++++++-----
kernel/audit_fsnotify.c | 7 ++++---
kernel/audit_tree.c | 15 ++++++++-------
kernel/audit_watch.c | 5 +++--
8 files changed, 38 insertions(+), 32 deletions(-)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 4c3bb4059f88..eb8ee2cbdb8f 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -305,7 +305,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
/* set up the new_fsn_mark and new_dn_mark */
new_fsn_mark = &new_dn_mark->fsn_mark;
- fsnotify_init_mark(new_fsn_mark, dnotify_free_mark);
+ fsnotify_init_mark(new_fsn_mark, dnotify_group, dnotify_free_mark);
new_fsn_mark->mask = mask;
new_dn_mark->dn = NULL;
@@ -318,8 +318,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
} else {
- fsnotify_add_mark_locked(new_fsn_mark, dnotify_group, inode,
- NULL, 0);
+ fsnotify_add_mark_locked(new_fsn_mark, inode, NULL, 0);
spin_lock(&new_fsn_mark->lock);
fsn_mark = new_fsn_mark;
dn_mark = new_dn_mark;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 7b4d9d67f4f9..4ba51b836a44 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -627,8 +627,8 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
if (!mark)
return ERR_PTR(-ENOMEM);
- fsnotify_init_mark(mark, fanotify_free_mark);
- ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
+ fsnotify_init_mark(mark, group, fanotify_free_mark);
+ ret = fsnotify_add_mark_locked(mark, inode, mnt, 0);
if (ret) {
fsnotify_put_mark(mark);
return ERR_PTR(ret);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 546a4c7d0f03..38e66d497b3b 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -561,7 +561,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
if (unlikely(!tmp_i_mark))
return -ENOMEM;
- fsnotify_init_mark(&tmp_i_mark->fsn_mark, inotify_free_mark);
+ fsnotify_init_mark(&tmp_i_mark->fsn_mark, group, inotify_free_mark);
tmp_i_mark->fsn_mark.mask = mask;
tmp_i_mark->wd = -1;
@@ -574,8 +574,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
goto out_err;
/* we are on the idr, now get on the inode */
- ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
- NULL, 0);
+ ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, inode, NULL, 0);
if (ret) {
/* we failed to get on the inode, get off the idr */
inotify_remove_from_idr(group, tmp_i_mark);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index b0db0a24d177..fae0c69c8cae 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -550,10 +550,10 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
* These marks may be used for the fsnotify backend to determine which
* event types should be delivered to which group.
*/
-int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
- struct fsnotify_group *group, struct inode *inode,
+int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct inode *inode,
struct vfsmount *mnt, int allow_dups)
{
+ struct fsnotify_group *group = mark->group;
int ret = 0;
BUG_ON(inode && mnt);
@@ -569,8 +569,6 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
spin_lock(&mark->lock);
mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
- fsnotify_get_group(group);
- mark->group = group;
list_add(&mark->g_list, &group->marks_list);
atomic_inc(&group->num_marks);
fsnotify_get_mark(mark); /* for g_list */
@@ -595,12 +593,14 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
return ret;
}
-int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
- struct inode *inode, struct vfsmount *mnt, int allow_dups)
+int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
+ struct vfsmount *mnt, int allow_dups)
{
int ret;
+ struct fsnotify_group *group = mark->group;
+
mutex_lock(&group->mark_mutex);
- ret = fsnotify_add_mark_locked(mark, group, inode, mnt, allow_dups);
+ ret = fsnotify_add_mark_locked(mark, inode, mnt, allow_dups);
mutex_unlock(&group->mark_mutex);
return ret;
}
@@ -718,12 +718,15 @@ void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp)
* Nothing fancy, just initialize lists and locks and counters.
*/
void fsnotify_init_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group,
void (*free_mark)(struct fsnotify_mark *mark))
{
memset(mark, 0, sizeof(*mark));
spin_lock_init(&mark->lock);
atomic_set(&mark->refcnt, 1);
mark->free_mark = free_mark;
+ fsnotify_get_group(group);
+ mark->group = group;
}
/*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 093f66818c6f..f87d447c1457 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -338,15 +338,17 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group
/* Calculate mask of events for a list of marks */
extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
-extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark));
+extern void fsnotify_init_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group,
+ void (*free_mark)(struct fsnotify_mark *mark));
/* Find mark belonging to given group in the list of marks */
extern struct fsnotify_mark *fsnotify_find_mark(
struct fsnotify_mark_connector **connp,
struct fsnotify_group *group);
-/* attach the mark to both the group and the inode */
-extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
- struct inode *inode, struct vfsmount *mnt, int allow_dups);
-extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct fsnotify_group *group,
+/* attach the mark to the inode or vfsmount */
+extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
+ struct vfsmount *mnt, int allow_dups);
+extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
struct inode *inode, struct vfsmount *mnt, int allow_dups);
/* given a group and a mark, flag mark to be freed when all references are dropped */
extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index ae8599c7aa81..5bb7e920f126 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -103,15 +103,16 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
goto out;
}
- fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_free_mark);
+ fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group,
+ audit_fsnotify_free_mark);
audit_mark->mark.mask = AUDIT_FS_EVENTS;
audit_mark->path = pathname;
audit_update_mark(audit_mark, dentry->d_inode);
audit_mark->rule = krule;
- ret = fsnotify_add_mark(&audit_mark->mark, audit_fsnotify_group, inode, NULL, true);
+ ret = fsnotify_add_mark(&audit_mark->mark, inode, NULL, true);
if (ret < 0) {
- audit_fsnotify_mark_free(audit_mark);
+ fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
}
out:
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index b6785489fd3d..a799cea717de 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,7 +154,8 @@ static struct audit_chunk *alloc_chunk(int count)
INIT_LIST_HEAD(&chunk->owners[i].list);
chunk->owners[i].index = i;
}
- fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+ fsnotify_init_mark(&chunk->mark, audit_tree_group,
+ audit_tree_destroy_watch);
chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
@@ -256,7 +257,7 @@ static void untag_chunk(struct node *p)
spin_unlock(&entry->lock);
mutex_unlock(&entry->group->mark_mutex);
if (new)
- free_chunk(new);
+ fsnotify_put_mark(&new->mark);
goto out;
}
@@ -280,8 +281,8 @@ static void untag_chunk(struct node *p)
if (!new)
goto Fallback;
- if (fsnotify_add_mark_locked(&new->mark, entry->group,
- entry->connector->inode, NULL, 1)) {
+ if (fsnotify_add_mark_locked(&new->mark, entry->connector->inode,
+ NULL, 1)) {
fsnotify_put_mark(&new->mark);
goto Fallback;
}
@@ -346,7 +347,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
return -ENOMEM;
entry = &chunk->mark;
- if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
+ if (fsnotify_add_mark(entry, inode, NULL, 0)) {
fsnotify_put_mark(entry);
return -ENOSPC;
}
@@ -418,11 +419,11 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
fsnotify_put_mark(old_entry);
- free_chunk(chunk);
+ fsnotify_put_mark(&chunk->mark);
return -ENOENT;
}
- if (fsnotify_add_mark_locked(chunk_entry, old_entry->group,
+ if (fsnotify_add_mark_locked(chunk_entry,
old_entry->connector->inode, NULL, 1)) {
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 800084cf0539..0f355086215a 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -157,9 +157,10 @@ static struct audit_parent *audit_init_parent(struct path *path)
INIT_LIST_HEAD(&parent->watches);
- fsnotify_init_mark(&parent->mark, audit_watch_free_mark);
+ fsnotify_init_mark(&parent->mark, audit_watch_group,
+ audit_watch_free_mark);
parent->mark.mask = AUDIT_FS_WATCH;
- ret = fsnotify_add_mark(&parent->mark, audit_watch_group, inode, NULL, 0);
+ ret = fsnotify_add_mark(&parent->mark, inode, NULL, 0);
if (ret < 0) {
audit_free_parent(parent);
return ERR_PTR(ret);
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread* [PATCH 22/22] fsnotify: Move ->free_mark callback to fsnotify_ops
2017-01-20 13:21 [PATCH 0/22 v3] fsnotify: Avoid SRCU stalls with fanotify permission events Jan Kara
` (20 preceding siblings ...)
2017-01-20 13:21 ` [PATCH 21/22] fsnotify: Add group pointer in fsnotify_init_mark() Jan Kara
@ 2017-01-20 13:21 ` Jan Kara
21 siblings, 0 replies; 29+ messages in thread
From: Jan Kara @ 2017-01-20 13:21 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Amir Goldstein, Miklos Szeredi, Paul Moore, Jan Kara
Pointer to ->free_mark callback unnecessarily occupies one long in each
fsnotify_mark although they are the same for all marks from one
notification group. Move the callback pointer to fsnotify_ops.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/notify/dnotify/dnotify.c | 3 ++-
fs/notify/fanotify/fanotify.c | 6 ++++++
fs/notify/fanotify/fanotify.h | 1 +
fs/notify/fanotify/fanotify_user.c | 9 ++-------
fs/notify/inotify/inotify.h | 2 ++
fs/notify/inotify/inotify_fsnotify.c | 11 +++++++++++
fs/notify/inotify/inotify_user.c | 14 ++------------
fs/notify/mark.c | 13 +++++++------
include/linux/fsnotify_backend.h | 6 +++---
kernel/audit_fsnotify.c | 4 ++--
kernel/audit_tree.c | 4 ++--
kernel/audit_watch.c | 4 ++--
12 files changed, 42 insertions(+), 35 deletions(-)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index eb8ee2cbdb8f..7ff92308aa54 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -135,6 +135,7 @@ static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
static struct fsnotify_ops dnotify_fsnotify_ops = {
.handle_event = dnotify_handle_event,
+ .free_mark = dnotify_free_mark,
};
/*
@@ -305,7 +306,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
/* set up the new_fsn_mark and new_dn_mark */
new_fsn_mark = &new_dn_mark->fsn_mark;
- fsnotify_init_mark(new_fsn_mark, dnotify_group, dnotify_free_mark);
+ fsnotify_init_mark(new_fsn_mark, dnotify_group);
new_fsn_mark->mask = mask;
new_dn_mark->dn = NULL;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 98d7dc94d34c..9e2ce260c444 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -268,8 +268,14 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
kmem_cache_free(fanotify_event_cachep, event);
}
+static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+ kmem_cache_free(fanotify_mark_cache, fsn_mark);
+}
+
const struct fsnotify_ops fanotify_fsnotify_ops = {
.handle_event = fanotify_handle_event,
.free_group_priv = fanotify_free_group_priv,
.free_event = fanotify_free_event,
+ .free_mark = fanotify_free_mark,
};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 4500a74f8d38..4eb6f5efa282 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -2,6 +2,7 @@
#include <linux/path.h>
#include <linux/slab.h>
+extern struct kmem_cache *fanotify_mark_cache;
extern struct kmem_cache *fanotify_event_cachep;
extern struct kmem_cache *fanotify_perm_event_cachep;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 4ba51b836a44..a1d5b121fdf8 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -40,7 +40,7 @@
extern const struct fsnotify_ops fanotify_fsnotify_ops;
-static struct kmem_cache *fanotify_mark_cache __read_mostly;
+struct kmem_cache *fanotify_mark_cache __read_mostly;
struct kmem_cache *fanotify_event_cachep __read_mostly;
struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
@@ -444,11 +444,6 @@ static const struct file_operations fanotify_fops = {
.llseek = noop_llseek,
};
-static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
-{
- kmem_cache_free(fanotify_mark_cache, fsn_mark);
-}
-
static int fanotify_find_path(int dfd, const char __user *filename,
struct path *path, unsigned int flags)
{
@@ -627,7 +622,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
if (!mark)
return ERR_PTR(-ENOMEM);
- fsnotify_init_mark(mark, group, fanotify_free_mark);
+ fsnotify_init_mark(mark, group);
ret = fsnotify_add_mark_locked(mark, inode, mnt, 0);
if (ret) {
fsnotify_put_mark(mark);
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 507840969edc..049e15da5564 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -31,3 +31,5 @@ extern int inotify_handle_event(struct fsnotify_group *group,
int *srcu_idx);
extern const struct fsnotify_ops inotify_fsnotify_ops;
+
+extern struct kmem_cache *inotify_inode_mark_cachep;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 35f2f39514b8..a33aa3173a2d 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -177,9 +177,20 @@ static void inotify_free_event(struct fsnotify_event *fsn_event)
kfree(INOTIFY_E(fsn_event));
}
+/* ding dong the mark is dead */
+static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+ struct inotify_inode_mark *i_mark;
+
+ i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+ kmem_cache_free(inotify_inode_mark_cachep, i_mark);
+}
+
const struct fsnotify_ops inotify_fsnotify_ops = {
.handle_event = inotify_handle_event,
.free_group_priv = inotify_free_group_priv,
.free_event = inotify_free_event,
.freeing_mark = inotify_freeing_mark,
+ .free_mark = inotify_free_mark,
};
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 38e66d497b3b..f16d591f0b41 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -49,7 +49,7 @@ static int inotify_max_user_instances __read_mostly;
static int inotify_max_queued_events __read_mostly;
static int inotify_max_user_watches __read_mostly;
-static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
+struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
#ifdef CONFIG_SYSCTL
@@ -486,16 +486,6 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
atomic_dec(&group->inotify_data.user->inotify_watches);
}
-/* ding dong the mark is dead */
-static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
-{
- struct inotify_inode_mark *i_mark;
-
- i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
-
- kmem_cache_free(inotify_inode_mark_cachep, i_mark);
-}
-
static int inotify_update_existing_watch(struct fsnotify_group *group,
struct inode *inode,
u32 arg)
@@ -561,7 +551,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
if (unlikely(!tmp_i_mark))
return -ENOMEM;
- fsnotify_init_mark(&tmp_i_mark->fsn_mark, group, inotify_free_mark);
+ fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
tmp_i_mark->fsn_mark.mask = mask;
tmp_i_mark->wd = -1;
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index fae0c69c8cae..63449d155f78 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -197,9 +197,12 @@ static struct inode *fsnotify_detach_connector_from_object(
static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
{
- if (mark->group)
- fsnotify_put_group(mark->group);
- mark->free_mark(mark);
+ struct fsnotify_group *group = mark->group;
+
+ if (WARN_ON_ONCE(!group))
+ return;
+ group->ops->free_mark(mark);
+ fsnotify_put_group(group);
}
void fsnotify_put_mark(struct fsnotify_mark *mark)
@@ -718,13 +721,11 @@ void fsnotify_destroy_marks(struct fsnotify_mark_connector **connp)
* Nothing fancy, just initialize lists and locks and counters.
*/
void fsnotify_init_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group,
- void (*free_mark)(struct fsnotify_mark *mark))
+ struct fsnotify_group *group)
{
memset(mark, 0, sizeof(*mark));
spin_lock_init(&mark->lock);
atomic_set(&mark->refcnt, 1);
- mark->free_mark = free_mark;
fsnotify_get_group(group);
mark->group = group;
}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index f87d447c1457..0239741b0dc8 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -102,6 +102,8 @@ struct fsnotify_ops {
void (*free_group_priv)(struct fsnotify_group *group);
void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
void (*free_event)(struct fsnotify_event *event);
+ /* called on final put+free to free memory */
+ void (*free_mark)(struct fsnotify_mark *mark);
};
/*
@@ -259,7 +261,6 @@ struct fsnotify_mark {
#define FSNOTIFY_MARK_FLAG_ALIVE 0x02
#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04
unsigned int flags; /* flags [mark->lock] */
- void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */
};
#ifdef CONFIG_FSNOTIFY
@@ -339,8 +340,7 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group
/* Calculate mask of events for a list of marks */
extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
extern void fsnotify_init_mark(struct fsnotify_mark *mark,
- struct fsnotify_group *group,
- void (*free_mark)(struct fsnotify_mark *mark));
+ struct fsnotify_group *group);
/* Find mark belonging to given group in the list of marks */
extern struct fsnotify_mark *fsnotify_find_mark(
struct fsnotify_mark_connector **connp,
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 5bb7e920f126..7c724b59fe7d 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -103,8 +103,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
goto out;
}
- fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group,
- audit_fsnotify_free_mark);
+ fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group);
audit_mark->mark.mask = AUDIT_FS_EVENTS;
audit_mark->path = pathname;
audit_update_mark(audit_mark, dentry->d_inode);
@@ -203,6 +202,7 @@ static int audit_mark_handle_event(struct fsnotify_group *group,
static const struct fsnotify_ops audit_mark_fsnotify_ops = {
.handle_event = audit_mark_handle_event,
+ .free_mark = audit_fsnotify_free_mark,
};
static int __init audit_fsnotify_init(void)
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index a799cea717de..b625908b835c 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,8 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
INIT_LIST_HEAD(&chunk->owners[i].list);
chunk->owners[i].index = i;
}
- fsnotify_init_mark(&chunk->mark, audit_tree_group,
- audit_tree_destroy_watch);
+ fsnotify_init_mark(&chunk->mark, audit_tree_group);
chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
@@ -1003,6 +1002,7 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
static const struct fsnotify_ops audit_tree_ops = {
.handle_event = audit_tree_handle_event,
.freeing_mark = audit_tree_freeing_mark,
+ .free_mark = audit_tree_destroy_watch,
};
static int __init audit_tree_init(void)
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 0f355086215a..d32b68b10cf7 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -157,8 +157,7 @@ static struct audit_parent *audit_init_parent(struct path *path)
INIT_LIST_HEAD(&parent->watches);
- fsnotify_init_mark(&parent->mark, audit_watch_group,
- audit_watch_free_mark);
+ fsnotify_init_mark(&parent->mark, audit_watch_group);
parent->mark.mask = AUDIT_FS_WATCH;
ret = fsnotify_add_mark(&parent->mark, inode, NULL, 0);
if (ret < 0) {
@@ -508,6 +507,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
static const struct fsnotify_ops audit_watch_fsnotify_ops = {
.handle_event = audit_watch_handle_event,
+ .free_mark = audit_watch_free_mark,
};
static int __init audit_watch_init(void)
--
2.10.2
^ permalink raw reply related [flat|nested] 29+ messages in thread