[patch 21/52] fs: dcache per-inode inode alias locking

From: npiggin
Date: Wed Jun 23 2010 - 23:19:49 EST


dcache_inode_lock can be replaced with per-inode locking. Use existing
inode->i_lock for this. This is slightly non-trivial because we sometimes
need to find the inode from the dentry, which requires d_inode to be
stabilised (either with refcount or d_lock).

Signed-off-by: Nick Piggin <npiggin@xxxxxxx>
---
fs/affs/amigaffs.c | 4 -
fs/dcache.c | 117 +++++++++++++++++++++++++-------------------
fs/exportfs/expfs.c | 12 ++--
fs/nfs/getroot.c | 4 -
fs/notify/fsnotify.c | 4 -
fs/notify/inotify/inotify.c | 4 -
fs/ocfs2/dcache.c | 4 -
fs/sysfs/dir.c | 6 +-
include/linux/dcache.h | 1
9 files changed, 89 insertions(+), 67 deletions(-)

Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c
+++ linux-2.6/fs/dcache.c
@@ -39,8 +39,8 @@

/*
* Usage:
- * dcache_inode_lock protects:
- * - i_dentry, d_alias, d_inode
+ * dcache->d_inode->i_lock protects:
+ * - i_dentry, d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* dcache_lru_lock protects:
@@ -56,7 +56,7 @@
* - d_alias, d_inode
*
* Ordering:
- * dcache_inode_lock
+ * dentry->d_inode->i_lock
* dentry->d_lock
* dcache_lru_lock
* dcache_hash_bucket lock
@@ -75,12 +75,10 @@
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);

-__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_inode_lock);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);

EXPORT_SYMBOL(rename_lock);
-EXPORT_SYMBOL(dcache_inode_lock);

static struct kmem_cache *dentry_cache __read_mostly;

@@ -165,14 +163,13 @@ static void d_free(struct dentry *dentry
*/
static void dentry_iput(struct dentry * dentry)
__releases(dentry->d_lock)
- __releases(dcache_inode_lock)
{
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
list_del_init(&dentry->d_alias);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
@@ -181,7 +178,6 @@ static void dentry_iput(struct dentry *
iput(inode);
} else {
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
}
}

@@ -252,7 +248,6 @@ static void dentry_lru_del_init(struct d
*/
static struct dentry *d_kill(struct dentry *dentry)
__releases(dentry->d_lock)
- __releases(dcache_inode_lock)
{
struct dentry *parent;

@@ -376,6 +371,7 @@ EXPORT_SYMBOL(dget_parent);
void dput(struct dentry *dentry)
{
struct dentry *parent;
+ struct inode *inode;

if (!dentry)
return;
@@ -412,14 +408,21 @@ repeat:
return;

kill_it:
- spin_unlock(&dentry->d_lock);
- spin_lock(&dcache_inode_lock);
+ inode = dentry->d_inode;
+ if (inode) {
+ if (!spin_trylock(&inode->i_lock)) {
relock:
- spin_lock(&dentry->d_lock);
+ spin_unlock(&dentry->d_lock);
+ cpu_relax();
+ spin_lock(&dentry->d_lock);
+ goto kill_it;
+ }
+ }
parent = dentry->d_parent;
if (parent && parent != dentry) {
if (!spin_trylock(&parent->d_lock)) {
- spin_unlock(&dentry->d_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
goto relock;
}
}
@@ -429,7 +432,8 @@ relock:
spin_unlock(&dentry->d_lock);
if (parent && parent != dentry)
spin_unlock(&parent->d_lock);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
return;
}
/* if dentry was on the d_lru list delete it from there */
@@ -547,9 +551,9 @@ struct dentry * d_find_alias(struct inod
struct dentry *de = NULL;

if (!list_empty(&inode->i_dentry)) {
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
de = __d_find_alias(inode, 0);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}
return de;
}
@@ -563,20 +567,20 @@ void d_prune_aliases(struct inode *inode
{
struct dentry *dentry;
restart:
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_locked_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
dput(dentry);
goto restart;
}
spin_unlock(&dentry->d_lock);
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_prune_aliases);

@@ -599,8 +603,10 @@ static void prune_one_dentry(struct dent
*/
while (dentry) {
struct dentry *parent = NULL;
+ struct inode *inode = dentry->d_inode;

- spin_lock(&dcache_inode_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
again:
spin_lock(&dentry->d_lock);
if (dentry->d_parent && dentry != dentry->d_parent) {
@@ -615,7 +621,8 @@ again:
if (parent)
spin_unlock(&parent->d_lock);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
return;
}

@@ -684,10 +691,11 @@ restart:
}
spin_unlock(&dcache_lru_lock);

- spin_lock(&dcache_inode_lock);
again:
spin_lock(&dcache_lru_lock); /* lru_lock also protects tmp list */
while (!list_empty(&tmp)) {
+ struct inode *inode;
+
dentry = list_entry(tmp.prev, struct dentry, d_lru);

if (!spin_trylock(&dentry->d_lock)) {
@@ -705,10 +713,17 @@ again1:
spin_unlock(&dentry->d_lock);
continue;
}
+ inode = dentry->d_inode;
+ if (inode && !spin_trylock(&inode->i_lock)) {
+again2:
+ spin_unlock(&dentry->d_lock);
+ goto again1;
+ }
if (dentry->d_parent && dentry->d_parent != dentry) {
if (!spin_trylock(&dentry->d_parent->d_lock)) {
- spin_unlock(&dentry->d_lock);
- goto again1;
+ if (inode)
+ spin_unlock(&inode->i_lock);
+ goto again2;
}
}
__dentry_lru_del_init(dentry);
@@ -716,10 +731,8 @@ again1:

prune_one_dentry(dentry);
/* dentry->d_lock dropped */
- spin_lock(&dcache_inode_lock);
spin_lock(&dcache_lru_lock);
}
- spin_unlock(&dcache_inode_lock);

if (count == NULL && !list_empty(&sb->s_dentry_lru))
goto restart;
@@ -1287,9 +1300,11 @@ static void __d_instantiate(struct dentr
void d_instantiate(struct dentry *entry, struct inode * inode)
{
BUG_ON(!list_empty(&entry->d_alias));
- spin_lock(&dcache_inode_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
@@ -1348,9 +1363,11 @@ struct dentry *d_instantiate_unique(stru

BUG_ON(!list_empty(&entry->d_alias));

- spin_lock(&dcache_inode_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
result = __d_instantiate_unique(entry, inode);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);

if (!result) {
security_d_instantiate(entry, inode);
@@ -1431,10 +1448,10 @@ struct dentry *d_obtain_alias(struct ino
}
tmp->d_parent = tmp; /* make sure dput doesn't croak */

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
res = __d_find_alias(inode, 0);
if (res) {
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
dput(tmp);
goto out_iput;
}
@@ -1448,7 +1465,7 @@ struct dentry *d_obtain_alias(struct ino
list_add(&tmp->d_alias, &inode->i_dentry);
hlist_bl_add_head(&tmp->d_hash, &inode->i_sb->s_anon); /* XXX: make s_anon a bl list */
spin_unlock(&tmp->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);

return tmp;

@@ -1479,18 +1496,18 @@ struct dentry *d_splice_alias(struct ino
struct dentry *new = NULL;

if (inode && S_ISDIR(inode->i_mode)) {
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
new = __d_find_alias(inode, 1);
if (new) {
BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
iput(inode);
} else {
- /* already got dcache_inode_lock, so d_add() by hand */
+ /* already got inode->i_lock, so d_add() by hand */
__d_instantiate(dentry, inode);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(dentry, inode);
d_rehash(dentry);
}
@@ -1563,10 +1580,10 @@ struct dentry *d_add_ci(struct dentry *d
* Negative dentry: instantiate it unless the inode is a directory and
* already has a dentry.
*/
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
if (!S_ISDIR(inode->i_mode) || list_empty(&inode->i_dentry)) {
__d_instantiate(found, inode);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
return found;
}
@@ -1577,7 +1594,7 @@ struct dentry *d_add_ci(struct dentry *d
*/
new = list_entry(inode->i_dentry.next, struct dentry, d_alias);
dget_locked(new);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
d_move(new, found);
iput(inode);
@@ -1785,15 +1802,17 @@ EXPORT_SYMBOL(d_validate);

void d_delete(struct dentry * dentry)
{
+ struct inode *inode;
int isdir = 0;
/*
* Are we the only user?
*/
again:
spin_lock(&dentry->d_lock);
- isdir = S_ISDIR(dentry->d_inode->i_mode);
+ inode = dentry->d_inode;
+ isdir = S_ISDIR(inode->i_mode);
if (dentry->d_count == 1) {
- if (!spin_trylock(&dcache_inode_lock)) {
+ if (inode && !spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
goto again;
@@ -2034,6 +2053,7 @@ static struct dentry *__d_unalias(struct
{
struct mutex *m1 = NULL, *m2 = NULL;
struct dentry *ret;
+ struct inode *inode;

/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
@@ -2049,14 +2069,15 @@ static struct dentry *__d_unalias(struct
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
- if (!mutex_trylock(&alias->d_parent->d_inode->i_mutex))
+ inode = alias->d_parent->d_inode;
+ if (!mutex_trylock(&inode->i_mutex))
goto out_err;
- m2 = &alias->d_parent->d_inode->i_mutex;
+ m2 = &inode->i_mutex;
out_unalias:
d_move_locked(alias, dentry);
ret = alias;
out_err:
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (m2)
mutex_unlock(m2);
if (m1)
@@ -2127,7 +2148,7 @@ struct dentry *d_materialise_unique(stru
goto out_nolock;
}

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);

if (S_ISDIR(inode->i_mode)) {
struct dentry *alias;
@@ -2162,7 +2183,7 @@ struct dentry *d_materialise_unique(stru
found:
_d_rehash(actual);
spin_unlock(&actual->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
out_nolock:
if (actual == dentry) {
security_d_instantiate(dentry, inode);
Index: linux-2.6/include/linux/dcache.h
===================================================================
--- linux-2.6.orig/include/linux/dcache.h
+++ linux-2.6/include/linux/dcache.h
@@ -190,7 +190,6 @@ d_iput: no no yes
#define DCACHE_CANT_MOUNT 0x0100
#define DCACHE_GENOCIDE 0x0200

-extern spinlock_t dcache_inode_lock;
extern seqlock_t rename_lock;

/**
Index: linux-2.6/fs/notify/inotify/inotify.c
===================================================================
--- linux-2.6.orig/fs/notify/inotify/inotify.c
+++ linux-2.6/fs/notify/inotify/inotify.c
@@ -181,7 +181,7 @@ static void set_dentry_child_flags(struc
{
struct dentry *alias;

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
list_for_each_entry(alias, &inode->i_dentry, d_alias) {
struct dentry *child;

@@ -199,7 +199,7 @@ static void set_dentry_child_flags(struc
}
spin_unlock(&alias->d_lock);
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}

/*
Index: linux-2.6/fs/exportfs/expfs.c
===================================================================
--- linux-2.6.orig/fs/exportfs/expfs.c
+++ linux-2.6/fs/exportfs/expfs.c
@@ -43,24 +43,26 @@ find_acceptable_alias(struct dentry *res
void *context)
{
struct dentry *dentry, *toput = NULL;
+ struct inode *inode;

if (acceptable(context, result))
return result;

- spin_lock(&dcache_inode_lock);
- list_for_each_entry(dentry, &result->d_inode->i_dentry, d_alias) {
+ inode = result->d_inode;
+ spin_lock(&inode->i_lock);
+ list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
dget_locked(dentry);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (toput)
dput(toput);
if (dentry != result && acceptable(context, dentry)) {
dput(result);
return dentry;
}
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
toput = dentry;
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);

if (toput)
dput(toput);
Index: linux-2.6/fs/affs/amigaffs.c
===================================================================
--- linux-2.6.orig/fs/affs/amigaffs.c
+++ linux-2.6/fs/affs/amigaffs.c
@@ -128,7 +128,7 @@ affs_fix_dcache(struct dentry *dentry, u
void *data = dentry->d_fsdata;
struct list_head *head, *next;

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
head = &inode->i_dentry;
next = head->next;
while (next != head) {
@@ -139,7 +139,7 @@ affs_fix_dcache(struct dentry *dentry, u
}
next = next->next;
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}


Index: linux-2.6/fs/nfs/getroot.c
===================================================================
--- linux-2.6.orig/fs/nfs/getroot.c
+++ linux-2.6/fs/nfs/getroot.c
@@ -64,11 +64,11 @@ static int nfs_superblock_set_dummy_root
* This again causes shrink_dcache_for_umount_subtree() to
* Oops, since the test for IS_ROOT() will fail.
*/
- spin_lock(&dcache_inode_lock);
+ spin_lock(&sb->s_root->d_inode->i_lock);
spin_lock(&sb->s_root->d_lock);
list_del_init(&sb->s_root->d_alias);
spin_unlock(&sb->s_root->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&sb->s_root->d_inode->i_lock);
}
return 0;
}
Index: linux-2.6/fs/ocfs2/dcache.c
===================================================================
--- linux-2.6.orig/fs/ocfs2/dcache.c
+++ linux-2.6/fs/ocfs2/dcache.c
@@ -151,7 +151,7 @@ struct dentry *ocfs2_find_local_alias(st
struct list_head *p;
struct dentry *dentry = NULL;

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
list_for_each(p, &inode->i_dentry) {
dentry = list_entry(p, struct dentry, d_alias);

@@ -169,7 +169,7 @@ struct dentry *ocfs2_find_local_alias(st
dentry = NULL;
}

- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);

return dentry;
}
Index: linux-2.6/fs/notify/fsnotify.c
===================================================================
--- linux-2.6.orig/fs/notify/fsnotify.c
+++ linux-2.6/fs/notify/fsnotify.c
@@ -53,7 +53,7 @@ void __fsnotify_update_child_dentry_flag
/* determine if the children should tell inode about their events */
watched = fsnotify_inode_watches_children(inode);

- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
list_for_each_entry(alias, &inode->i_dentry, d_alias) {
@@ -76,7 +76,7 @@ void __fsnotify_update_child_dentry_flag
}
spin_unlock(&alias->d_lock);
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}

/* Notify this dentry's parent about a child's events. */


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/