From: npiggin@suse.de
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [patch 11/27] fs: dcache scale d_unhashed
Date: Sat, 25 Apr 2009 11:20:31 +1000 [thread overview]
Message-ID: <20090425012210.597651512@suse.de> (raw)
In-Reply-To: 20090425012020.457460929@suse.de
[-- Attachment #1: fs-dcache-scale-d_unhashed.patch --]
[-- Type: text/plain, Size: 10789 bytes --]
Protect d_unhashed(dentry) condition with d_lock.
---
arch/powerpc/platforms/cell/spufs/inode.c | 3 ++
fs/configfs/configfs_internal.h | 2 +
fs/dcache.c | 40 +++++++++++++++++++++++-------
fs/libfs.c | 29 +++++++++++++++------
fs/ocfs2/dcache.c | 5 +++
fs/seq_file.c | 3 ++
fs/sysfs/dir.c | 8 +++---
7 files changed, 68 insertions(+), 22 deletions(-)
Index: linux-2.6/fs/sysfs/dir.c
===================================================================
--- linux-2.6.orig/fs/sysfs/dir.c
+++ linux-2.6/fs/sysfs/dir.c
@@ -549,10 +549,12 @@ static void sysfs_drop_dentry(struct sys
repeat:
spin_lock(&dcache_lock);
list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
- if (d_unhashed(dentry))
- continue;
- dget_locked(dentry);
spin_lock(&dentry->d_lock);
+ if (d_unhashed(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ continue;
+ }
+ dget_locked_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
Index: linux-2.6/fs/libfs.c
===================================================================
--- linux-2.6.orig/fs/libfs.c
+++ linux-2.6/fs/libfs.c
@@ -12,6 +12,11 @@
#include <asm/uaccess.h>
+static inline int simple_positive(struct dentry *dentry)
+{
+ return dentry->d_inode && !d_unhashed(dentry);
+}
+
int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
@@ -101,8 +106,10 @@ loff_t dcache_dir_lseek(struct file *fil
while (n && p != &file->f_path.dentry->d_subdirs) {
struct dentry *next;
next = list_entry(p, struct dentry, d_u.d_child);
- if (!d_unhashed(next) && next->d_inode)
+ spin_lock(&next->d_lock);
+ if (simple_positive(next))
n--;
+ spin_unlock(&next->d_lock);
p = p->next;
}
list_add_tail(&cursor->d_u.d_child, p);
@@ -156,9 +163,13 @@ int dcache_readdir(struct file * filp, v
for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
struct dentry *next;
next = list_entry(p, struct dentry, d_u.d_child);
- if (d_unhashed(next) || !next->d_inode)
+ spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
+ if (!simple_positive(next)) {
+ spin_unlock(&next->d_lock);
continue;
+ }
+ spin_unlock(&next->d_lock);
spin_unlock(&dcache_lock);
if (filldir(dirent, next->d_name.name,
next->d_name.len, filp->f_pos,
@@ -263,20 +274,20 @@ int simple_link(struct dentry *old_dentr
return 0;
}
-static inline int simple_positive(struct dentry *dentry)
-{
- return dentry->d_inode && !d_unhashed(dentry);
-}
-
int simple_empty(struct dentry *dentry)
{
struct dentry *child;
int ret = 0;
spin_lock(&dcache_lock);
- list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
- if (simple_positive(child))
+ list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) {
+ spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+ if (simple_positive(child)) {
+ spin_unlock(&child->d_lock);
goto out;
+ }
+ spin_unlock(&child->d_lock);
+ }
ret = 1;
out:
spin_unlock(&dcache_lock);
Index: linux-2.6/fs/seq_file.c
===================================================================
--- linux-2.6.orig/fs/seq_file.c
+++ linux-2.6/fs/seq_file.c
@@ -6,6 +6,7 @@
*/
#include <linux/fs.h>
+#include <linux/mount.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
@@ -460,7 +461,9 @@ int seq_path_root(struct seq_file *m, st
char *p;
spin_lock(&dcache_lock);
+ vfsmount_read_lock();
p = __d_path(path, root, s, m->size - m->count);
+ vfsmount_read_unlock();
spin_unlock(&dcache_lock);
err = PTR_ERR(p);
if (!IS_ERR(p)) {
Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c
+++ linux-2.6/fs/dcache.c
@@ -327,7 +327,9 @@ int d_invalidate(struct dentry * dentry)
* If it's already been dropped, return OK.
*/
spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
if (d_unhashed(dentry)) {
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
return 0;
}
@@ -336,6 +338,7 @@ int d_invalidate(struct dentry * dentry)
* to get rid of unused child entries.
*/
if (!list_empty(&dentry->d_subdirs)) {
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
shrink_dcache_parent(dentry);
spin_lock(&dcache_lock);
@@ -443,15 +446,18 @@ static struct dentry * __d_find_alias(st
next = tmp->next;
prefetch(next);
alias = list_entry(tmp, struct dentry, d_alias);
+ spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
(alias->d_flags & DCACHE_DISCONNECTED))
discon_alias = alias;
else if (!want_discon) {
- __dget_locked(alias);
+ __dget_locked_dlock(alias);
+ spin_unlock(&alias->d_lock);
return alias;
}
}
+ spin_unlock(&alias->d_lock);
}
if (discon_alias)
__dget_locked(discon_alias);
@@ -734,8 +740,8 @@ static void shrink_dcache_for_umount_sub
spin_lock(&dcache_lock);
spin_lock(&dentry->d_lock);
dentry_lru_del_init(dentry);
- spin_unlock(&dentry->d_lock);
__d_drop(dentry);
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
for (;;) {
@@ -750,8 +756,8 @@ static void shrink_dcache_for_umount_sub
d_u.d_child) {
spin_lock(&loop->d_lock);
dentry_lru_del_init(loop);
- spin_unlock(&loop->d_lock);
__d_drop(loop);
+ spin_unlock(&loop->d_lock);
cond_resched_lock(&dcache_lock);
}
spin_unlock(&dcache_lock);
@@ -2016,7 +2022,8 @@ static int prepend_name(char **buffer, i
* Returns a pointer into the buffer or an error code if the
* path was too long.
*
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * "buflen" should be positive. Caller holds the dcache_lock and
+ * path->dentry->d_lock.
*
* If path is not reachable from the supplied root, then the value of
* root is changed (without modifying refcounts).
@@ -2029,7 +2036,6 @@ char *__d_path(const struct path *path,
char *end = buffer + buflen;
char *retval;
- vfsmount_read_lock();
prepend(&end, &buflen, "\0", 1);
if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
(prepend(&end, &buflen, " (deleted)", 10) != 0))
@@ -2065,7 +2071,6 @@ char *__d_path(const struct path *path,
}
out:
- vfsmount_read_unlock();
return retval;
global_root:
@@ -2118,8 +2123,12 @@ char *d_path(const struct path *path, ch
path_get(&root);
read_unlock(¤t->fs->lock);
spin_lock(&dcache_lock);
+ vfsmount_read_lock();
+ spin_lock(&path->dentry->d_lock);
tmp = root;
res = __d_path(path, &tmp, buf, buflen);
+ spin_unlock(&path->dentry->d_lock);
+ vfsmount_read_unlock();
spin_unlock(&dcache_lock);
path_put(&root);
return res;
@@ -2155,6 +2164,7 @@ char *dentry_path(struct dentry *dentry,
char *retval;
spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
prepend(&end, &buflen, "\0", 1);
if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
(prepend(&end, &buflen, "//deleted", 9) != 0))
@@ -2176,9 +2186,11 @@ char *dentry_path(struct dentry *dentry,
retval = end;
dentry = parent;
}
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
return retval;
Elong:
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
return ERR_PTR(-ENAMETOOLONG);
}
@@ -2220,12 +2232,16 @@ SYSCALL_DEFINE2(getcwd, char __user *, b
error = -ENOENT;
/* Has the current directory has been unlinked? */
spin_lock(&dcache_lock);
+ vfsmount_read_lock();
+ spin_lock(&pwd.dentry->d_lock);
if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) {
unsigned long len;
struct path tmp = root;
char * cwd;
cwd = __d_path(&pwd, &tmp, page, PAGE_SIZE);
+ spin_unlock(&pwd.dentry->d_lock);
+ vfsmount_read_unlock();
spin_unlock(&dcache_lock);
error = PTR_ERR(cwd);
@@ -2239,8 +2255,11 @@ SYSCALL_DEFINE2(getcwd, char __user *, b
if (copy_to_user(buf, cwd, len))
error = -EFAULT;
}
- } else
+ } else {
+ spin_unlock(&pwd.dentry->d_lock);
+ vfsmount_read_unlock();
spin_unlock(&dcache_lock);
+ }
out:
path_put(&pwd);
@@ -2304,13 +2323,16 @@ resume:
struct list_head *tmp = next;
struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
next = tmp->next;
- if (d_unhashed(dentry)||!dentry->d_inode)
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ if (d_unhashed(dentry) || !dentry->d_inode) {
+ spin_unlock(&dentry->d_lock);
continue;
+ }
if (!list_empty(&dentry->d_subdirs)) {
+ spin_unlock(&dentry->d_lock);
this_parent = dentry;
goto repeat;
}
- spin_lock(&dentry->d_lock);
dentry->d_count--;
spin_unlock(&dentry->d_lock);
}
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/inode.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/inode.c
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/inode.c
@@ -165,6 +165,9 @@ static void spufs_prune_dir(struct dentr
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
simple_unlink(dir->d_inode, dentry);
+ /* XXX: what is dcache_lock protecting here? Other
+ * filesystems (IB, configfs) release dcache_lock
+ * before unlink */
spin_unlock(&dcache_lock);
dput(dentry);
} else {
Index: linux-2.6/fs/configfs/configfs_internal.h
===================================================================
--- linux-2.6.orig/fs/configfs/configfs_internal.h
+++ linux-2.6/fs/configfs/configfs_internal.h
@@ -118,6 +118,7 @@ static inline struct config_item *config
struct config_item * item = NULL;
spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
if (!d_unhashed(dentry)) {
struct configfs_dirent * sd = dentry->d_fsdata;
if (sd->s_type & CONFIGFS_ITEM_LINK) {
@@ -126,6 +127,7 @@ static inline struct config_item *config
} else
item = config_item_get(sd->s_element);
}
+ spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
return item;
Index: linux-2.6/fs/ocfs2/dcache.c
===================================================================
--- linux-2.6.orig/fs/ocfs2/dcache.c
+++ linux-2.6/fs/ocfs2/dcache.c
@@ -145,13 +145,16 @@ struct dentry *ocfs2_find_local_alias(st
list_for_each(p, &inode->i_dentry) {
dentry = list_entry(p, struct dentry, d_alias);
+ spin_lock(&dentry->d_lock);
if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
mlog(0, "dentry found: %.*s\n",
dentry->d_name.len, dentry->d_name.name);
- dget_locked(dentry);
+ dget_locked_dlock(dentry);
+ spin_unlock(&dentry->d_lock);
break;
}
+ spin_unlock(&dentry->d_lock);
dentry = NULL;
}
next prev parent reply other threads:[~2009-04-25 1:33 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-25 1:20 [patch 00/27] [rfc] vfs scalability patchset npiggin
2009-04-25 1:20 ` [patch 01/27] fs: cleanup files_lock npiggin
2009-04-25 3:20 ` Al Viro
2009-04-25 5:35 ` Eric W. Biederman
2009-04-26 6:12 ` Nick Piggin
2009-04-25 9:42 ` Alan Cox
2009-04-26 6:15 ` Nick Piggin
2009-04-25 1:20 ` [patch 02/27] fs: scale files_lock npiggin
2009-04-25 3:32 ` Al Viro
2009-04-25 1:20 ` [patch 03/27] fs: mnt_want_write speedup npiggin
2009-04-25 1:20 ` [patch 04/27] fs: introduce mnt_clone_write npiggin
2009-04-25 3:35 ` Al Viro
2009-04-25 1:20 ` [patch 05/27] fs: brlock vfsmount_lock npiggin
2009-04-25 3:50 ` Al Viro
2009-04-26 6:36 ` Nick Piggin
2009-04-25 1:20 ` [patch 06/27] fs: dcache fix LRU ordering npiggin
2009-04-25 1:20 ` [patch 07/27] fs: dcache scale hash npiggin
2009-04-25 1:20 ` [patch 08/27] fs: dcache scale lru npiggin
2009-04-25 1:20 ` [patch 09/27] fs: dcache scale nr_dentry npiggin
2009-04-25 1:20 ` [patch 10/27] fs: dcache scale dentry refcount npiggin
2009-04-25 1:20 ` npiggin [this message]
2009-04-25 1:20 ` [patch 12/27] fs: dcache scale subdirs npiggin
2009-04-25 1:20 ` [patch 13/27] fs: scale inode alias list npiggin
2009-04-25 1:20 ` [patch 14/27] fs: use RCU / seqlock logic for reverse and multi-step operaitons npiggin
2009-04-25 1:20 ` [patch 15/27] fs: dcache remove dcache_lock npiggin
2009-04-25 1:20 ` [patch 16/27] fs: dcache reduce dput locking npiggin
2009-04-25 1:20 ` [patch 17/27] fs: dcache per-bucket dcache hash locking npiggin
2009-04-25 1:20 ` [patch 18/27] fs: dcache reduce dcache_inode_lock npiggin
2009-04-25 1:20 ` [patch 19/27] fs: dcache per-inode inode alias locking npiggin
2009-04-25 1:20 ` [patch 20/27] fs: icache lock s_inodes list npiggin
2009-04-25 1:20 ` [patch 21/27] fs: icache lock inode hash npiggin
2009-04-25 1:20 ` [patch 22/27] fs: icache lock i_state npiggin
2009-04-25 1:20 ` [patch 23/27] fs: icache lock i_count npiggin
2009-04-25 1:20 ` [patch 24/27] fs: icache atomic inodes_stat npiggin
2009-04-25 1:20 ` [patch 25/27] fs: icache lock lru/writeback lists npiggin
2009-04-25 1:20 ` [patch 26/27] fs: icache protect inode state npiggin
2009-04-25 1:20 ` [patch 27/27] fs: icache remove inode_lock npiggin
2009-04-25 4:18 ` [patch 00/27] [rfc] vfs scalability patchset Al Viro
2009-04-25 5:02 ` Nick Piggin
2009-04-25 8:01 ` Christoph Hellwig
2009-04-25 8:06 ` Al Viro
2009-04-28 9:09 ` Christoph Hellwig
2009-04-28 9:48 ` Nick Piggin
2009-04-28 10:58 ` Peter Zijlstra
2009-04-28 11:32 ` Eric W. Biederman
2009-04-30 6:14 ` Nick Piggin
2009-04-25 19:08 ` Eric W. Biederman
2009-04-25 19:31 ` Al Viro
2009-04-25 20:29 ` Eric W. Biederman
2009-04-25 22:05 ` Theodore Tso
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090425012210.597651512@suse.de \
--to=npiggin@suse.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox