| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 28 Oct 2010 22:42:39 +1100
From: Dave Chinner <david@...morbit.com>
To: viro@...IV.linux.org.uk
Cc: linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH 1/3] fs: move i_sb_list out from under inode_lock
From: Dave Chinner <dchinner@...hat.com>
Protect the per-sb inode list with a new global lock
inode_sb_list_lock and use it to protect the list manipulations and
traversals. This lock replaces the inode_lock as the inodes on the
list can be validity checked while holding the inode->i_lock and
hence the inode_lock is no longer needed to protect the list.
Signed-off-by: Dave Chinner <dchinner@...hat.com>
---
fs/drop_caches.c | 9 +++++----
fs/fs-writeback.c | 21 +++++++++++----------
fs/inode.c | 43 +++++++++++++++++++++++--------------------
fs/internal.h | 2 ++
fs/notify/inode_mark.c | 15 ++++++++-------
fs/quota/dquot.c | 28 ++++++++++++++++------------
6 files changed, 65 insertions(+), 53 deletions(-)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 62dd8ee..86cd2f1 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -8,6 +8,7 @@
#include <linux/writeback.h>
#include <linux/sysctl.h>
#include <linux/gfp.h>
+#include "internal.h"
/* A global variable is a bit ugly, but it keeps the code simple */
int sysctl_drop_caches;
@@ -16,7 +17,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
{
struct inode *inode, *toput_inode = NULL;
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@@ -26,13 +27,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
iput(toput_inode);
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 50de4f1..7707a62 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1053,7 +1053,7 @@ static void wait_sb_inodes(struct super_block *sb)
*/
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
/*
* Data integrity sync. Must wait for all pages under writeback,
@@ -1073,14 +1073,15 @@ static void wait_sb_inodes(struct super_block *sb)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
+
/*
- * We hold a reference to 'inode' so it couldn't have
- * been removed from s_inodes list while we dropped the
- * inode_lock. We cannot iput the inode now as we can
- * be holding the last reference and we cannot iput it
- * under inode_lock. So we keep the reference and iput
- * it later.
+ * We hold a reference to 'inode' so it couldn't have been
+ * removed from s_inodes list while we dropped the
+ * inode_sb_list_lock. We cannot iput the inode now as we can
+ * be holding the last reference and we cannot iput it under
+ * inode_sb_list_lock. So we keep the reference and iput it
+ * later.
*/
iput(old_inode);
old_inode = inode;
@@ -1089,9 +1090,9 @@ static void wait_sb_inodes(struct super_block *sb)
cond_resched();
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
iput(old_inode);
}
diff --git a/fs/inode.c b/fs/inode.c
index f64aeda..44f28dd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -32,10 +32,15 @@
* inode->i_state, __iget()
* inode_lru_lock protects:
* inode_lru, inode->i_lru
+ * inode_sb_list_lock protects:
+ * sb->s_inodes, inode->i_sb_list
*
* Lock ordering:
* inode_lock
* inode->i_lock
+ *
+ * inode_sb_list_lock
+ * inode->i_lock
* inode_lru_lock
*/
@@ -97,6 +102,8 @@ static struct hlist_head *inode_hashtable __read_mostly;
*/
DEFINE_SPINLOCK(inode_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
+
/*
* iprune_sem provides exclusion between the kswapd or try_to_free_pages
* icache shrinking path, and the umount path. Without this exclusion,
@@ -365,26 +372,23 @@ static void inode_lru_list_del(struct inode *inode)
spin_unlock(&inode_lru_lock);
}
-static inline void __inode_sb_list_add(struct inode *inode)
-{
- list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
-}
-
/**
* inode_sb_list_add - add inode to the superblock list of inodes
* @inode: inode to add
*/
void inode_sb_list_add(struct inode *inode)
{
- spin_lock(&inode_lock);
- __inode_sb_list_add(inode);
- spin_unlock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
+ list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
+ spin_unlock(&inode_sb_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);
-static inline void __inode_sb_list_del(struct inode *inode)
+static inline void inode_sb_list_del(struct inode *inode)
{
+ spin_lock(&inode_sb_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&inode_sb_list_lock);
}
static unsigned long hash(struct super_block *sb, unsigned long hashval)
@@ -460,9 +464,10 @@ static void evict(struct inode *inode)
spin_lock(&inode_lock);
list_del_init(&inode->i_wb_list);
- __inode_sb_list_del(inode);
spin_unlock(&inode_lock);
+ inode_sb_list_del(inode);
+
if (op->evict_inode) {
op->evict_inode(inode);
} else {
@@ -516,7 +521,7 @@ void evict_inodes(struct super_block *sb)
down_write(&iprune_sem);
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;
@@ -534,7 +539,7 @@ void evict_inodes(struct super_block *sb)
list_add(&inode->i_lru, &dispose);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
dispose_list(&dispose);
up_write(&iprune_sem);
@@ -555,7 +560,7 @@ int invalidate_inodes(struct super_block *sb)
down_write(&iprune_sem);
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
@@ -574,7 +579,7 @@ int invalidate_inodes(struct super_block *sb)
list_add(&inode->i_lru, &dispose);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
dispose_list(&dispose);
up_write(&iprune_sem);
@@ -839,16 +844,14 @@ struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;
- spin_lock_prefetch(&inode_lock);
+ spin_lock_prefetch(&inode_sb_list_lock);
inode = alloc_inode(sb);
if (inode) {
- spin_lock(&inode_lock);
spin_lock(&inode->i_lock);
inode->i_state = 0;
spin_unlock(&inode->i_lock);
- __inode_sb_list_add(inode);
- spin_unlock(&inode_lock);
+ inode_sb_list_add(inode);
}
return inode;
}
@@ -918,7 +921,7 @@ static struct inode *get_new_inode(struct super_block *sb,
inode->i_state = I_NEW;
spin_unlock(&inode->i_lock);
hlist_add_head(&inode->i_hash, head);
- __inode_sb_list_add(inode);
+ inode_sb_list_add(inode);
spin_unlock(&inode_lock);
/* Return the locked inode with I_NEW set, the
@@ -967,7 +970,7 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
inode->i_state = I_NEW;
spin_unlock(&inode->i_lock);
hlist_add_head(&inode->i_hash, head);
- __inode_sb_list_add(inode);
+ inode_sb_list_add(inode);
spin_unlock(&inode_lock);
/* Return the locked inode with I_NEW set, the
diff --git a/fs/internal.h b/fs/internal.h
index ebad3b9..493baa1 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -108,3 +108,5 @@ extern void release_open_intent(struct nameidata *);
extern int get_nr_dirty_inodes(void);
extern int evict_inodes(struct super_block *);
extern int invalidate_inodes(struct super_block *);
+
+extern spinlock_t inode_sb_list_lock;
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 9c0fb09..06c8216 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -29,6 +29,8 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
+#include "../internal.h"
+
/*
* Recalculate the mask of events relevant to a given inode locked.
*/
@@ -232,15 +234,14 @@ out:
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
* @list: list of inodes being unmounted (sb->s_inodes)
*
- * Called with inode_lock held, protecting the unmounting super block's list
- * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
- * We temporarily drop inode_lock, however, and CAN block.
+ * Called during unmount with no locks held, so needs to be safe against
+ * concurrent modifiers. We temporarily drop inode_sb_list_lock and CAN block.
*/
void fsnotify_unmount_inodes(struct list_head *list)
{
struct inode *inode, *next_i, *need_iput = NULL;
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
struct inode *need_iput_tmp;
@@ -293,7 +294,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
* will be added since the umount has begun. Finally,
* iprune_mutex keeps shrink_icache_memory() away.
*/
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
if (need_iput_tmp)
iput(need_iput_tmp);
@@ -305,7 +306,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
iput(inode);
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a2d89f8..440f64c 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -76,7 +76,7 @@
#include <linux/buffer_head.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
-#include <linux/writeback.h> /* for inode_lock, oddly enough.. */
+#include "../internal.h" /* ugh */
#include <asm/uaccess.h>
@@ -896,7 +896,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
int reserved = 0;
#endif
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@@ -911,19 +911,23 @@ static void add_dquot_ref(struct super_block *sb, int type)
#endif
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
iput(old_inode);
__dquot_initialize(inode, type);
- /* We hold a reference to 'inode' so it couldn't have been
- * removed from s_inodes list while we dropped the inode_lock.
- * We cannot iput the inode now as we can be holding the last
- * reference and we cannot iput it under inode_lock. So we
- * keep the reference and iput it later. */
+
+ /*
+ * We hold a reference to 'inode' so it couldn't have been
+ * removed from s_inodes list while we dropped the
+ * inode_sb_list_lock We cannot iput the inode now as we can be
+ * holding the last reference and we cannot iput it under
+ * inode_sb_list_lock. So we keep the reference and iput it
+ * later.
+ */
old_inode = inode;
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
iput(old_inode);
#ifdef CONFIG_QUOTA_DEBUG
@@ -1004,7 +1008,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
struct inode *inode;
int reserved = 0;
- spin_lock(&inode_lock);
+ spin_lock(&inode_sb_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
/*
* We have to scan also I_NEW inodes because they can already
@@ -1018,7 +1022,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
remove_inode_dquot_ref(inode, type, tofree_head);
}
}
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_sb_list_lock);
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
printk(KERN_WARNING "VFS (%s): Writes happened after quota"
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists