[patch 09/52] fs: dcache scale hash

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Add a new lock, dcache_hash_lock, to protect the dcache hash table from
concurrent modification. d_hash is also protected by d_lock.

Signed-off-by: Nick Piggin <npiggin@xxxxxxx>
---
 fs/dcache.c            |   35 ++++++++++++++++++++++++-----------
 include/linux/dcache.h |    3 +++
 2 files changed, 27 insertions(+), 11 deletions(-)

Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c
+++ linux-2.6/fs/dcache.c
@@ -35,12 +35,27 @@
 #include <linux/hardirq.h>
 #include "internal.h"
 
+/*
+ * Usage:
+ * dcache_hash_lock protects dcache hash table
+ *
+ * Ordering:
+ * dcache_lock
+ *   dentry->d_lock
+ *     dcache_hash_lock
+ *
+ * if (dentry1 < dentry2)
+ *   dentry1->d_lock
+ *     dentry2->d_lock
+ */
 int sysctl_vfs_cache_pressure __read_mostly = 100;
 EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
 
- __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_hash_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
+EXPORT_SYMBOL(dcache_hash_lock);
 EXPORT_SYMBOL(dcache_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
@@ -1480,17 +1495,20 @@ int d_validate(struct dentry *dentry, st
 		goto out;
 
 	spin_lock(&dcache_lock);
+	spin_lock(&dcache_hash_lock);
 	base = d_hash(dparent, dentry->d_name.hash);
 	hlist_for_each(lhp,base) { 
 		/* hlist_for_each_entry_rcu() not required for d_hash list
 		 * as it is parsed under dcache_lock
 		 */
 		if (dentry == hlist_entry(lhp, struct dentry, d_hash)) {
+			spin_unlock(&dcache_hash_lock);
 			__dget_locked(dentry);
 			spin_unlock(&dcache_lock);
 			return 1;
 		}
 	}
+	spin_unlock(&dcache_hash_lock);
 	spin_unlock(&dcache_lock);
 out:
 	return 0;
@@ -1567,7 +1585,9 @@ void d_rehash(struct dentry * entry)
 {
 	spin_lock(&dcache_lock);
 	spin_lock(&entry->d_lock);
+	spin_lock(&dcache_hash_lock);
 	_d_rehash(entry);
+	spin_unlock(&dcache_hash_lock);
 	spin_unlock(&entry->d_lock);
 	spin_unlock(&dcache_lock);
 }
@@ -1647,8 +1667,6 @@ static void switch_names(struct dentry *
  */
 static void d_move_locked(struct dentry * dentry, struct dentry * target)
 {
-	struct hlist_head *list;
-
 	if (!dentry->d_inode)
 		printk(KERN_WARNING "VFS: moving negative dcache entry\n");
 
@@ -1665,14 +1683,11 @@ static void d_move_locked(struct dentry
 	}
 
 	/* Move the dentry to the target hash queue, if on different bucket */
-	if (d_unhashed(dentry))
-		goto already_unhashed;
-
-	hlist_del_rcu(&dentry->d_hash);
-
-already_unhashed:
-	list = d_hash(target->d_parent, target->d_name.hash);
-	__d_rehash(dentry, list);
+	spin_lock(&dcache_hash_lock);
+	if (!d_unhashed(dentry))
+		hlist_del_rcu(&dentry->d_hash);
+	__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
+	spin_unlock(&dcache_hash_lock);
 
 	/* Unhash the target: dput() will then get rid of it */
 	__d_drop(target);
@@ -1869,7 +1884,9 @@ struct dentry *d_materialise_unique(stru
 found_lock:
 	spin_lock(&actual->d_lock);
 found:
+	spin_lock(&dcache_hash_lock);
 	_d_rehash(actual);
+	spin_unlock(&dcache_hash_lock);
 	spin_unlock(&actual->d_lock);
 	spin_unlock(&dcache_lock);
 out_nolock:
Index: linux-2.6/include/linux/dcache.h
===================================================================
--- linux-2.6.orig/include/linux/dcache.h
+++ linux-2.6/include/linux/dcache.h
@@ -188,6 +188,7 @@ d_iput:		no		no		no       yes
 
 #define DCACHE_CANT_MOUNT	0x0100
 
+extern spinlock_t dcache_hash_lock;
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -211,7 +212,9 @@ static inline void __d_drop(struct dentr
 {
 	if (!(dentry->d_flags & DCACHE_UNHASHED)) {
 		dentry->d_flags |= DCACHE_UNHASHED;
+		spin_lock(&dcache_hash_lock);
 		hlist_del_rcu(&dentry->d_hash);
+		spin_unlock(&dcache_hash_lock);
 	}
 }
 


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


[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux