From: npiggin@suse.de
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: John Stultz <johnstul@us.ibm.com>, Frank Mayhar <fmayhar@google.com>
Subject: [patch 26/52] fs: icache lock s_inodes list
Date: Thu, 24 Jun 2010 13:02:38 +1000 [thread overview]
Message-ID: <20100624030729.765849671@suse.de> (raw)
In-Reply-To: 20100624030212.676457061@suse.de
[-- Attachment #1: fs-inode_lock-scale.patch --]
[-- Type: text/plain, Size: 7854 bytes --]
Protect sb->s_inodes with a new lock, sb_inode_list_lock.
Signed-off-by: Nick Piggin <npiggin@suse.de>
---
fs/drop_caches.c | 4 ++++
fs/fs-writeback.c | 4 ++++
fs/inode.c | 12 ++++++++++++
fs/notify/inode_mark.c | 2 ++
fs/notify/inotify/inotify.c | 2 ++
fs/quota/dquot.c | 6 ++++++
include/linux/writeback.h | 1 +
7 files changed, 31 insertions(+)
Index: linux-2.6/fs/drop_caches.c
===================================================================
--- linux-2.6.orig/fs/drop_caches.c
+++ linux-2.6/fs/drop_caches.c
@@ -17,18 +17,22 @@ static void drop_pagecache_sb(struct sup
struct inode *inode, *toput_inode = NULL;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
if (inode->i_mapping->nrpages == 0)
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(toput_inode);
}
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c
+++ linux-2.6/fs/fs-writeback.c
@@ -1166,6 +1166,7 @@ static void wait_sb_inodes(struct super_
WARN_ON(!rwsem_is_locked(&sb->s_umount));
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
/*
* Data integrity sync. Must wait for all pages under writeback,
@@ -1183,6 +1184,7 @@ static void wait_sb_inodes(struct super_
if (mapping->nrpages == 0)
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
/*
* We hold a reference to 'inode' so it couldn't have
@@ -1200,7 +1202,9 @@ static void wait_sb_inodes(struct super_
cond_resched();
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
}
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c
+++ linux-2.6/fs/inode.c
@@ -27,6 +27,15 @@
#include <linux/posix_acl.h>
/*
+ * Usage:
+ * sb_inode_list_lock protects:
+ * s_inodes, i_sb_list
+ *
+ * Ordering:
+ * inode_lock
+ * sb_inode_list_lock
+ */
+/*
* This is needed for the following functions:
* - inode_has_buffers
* - invalidate_inode_buffers
@@ -84,6 +93,7 @@ static struct hlist_head *inode_hashtabl
* the i_state of an inode while it is in use..
*/
DEFINE_SPINLOCK(inode_lock);
+DEFINE_SPINLOCK(sb_inode_list_lock);
/*
* iprune_sem provides exclusion between the kswapd or try_to_free_pages
@@ -344,7 +354,9 @@ static void dispose_list(struct list_hea
spin_lock(&inode_lock);
hlist_del_init(&inode->i_hash);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
wake_up_inode(inode);
@@ -376,6 +388,7 @@ static int invalidate_list(struct list_h
* shrink_icache_memory() away.
*/
cond_resched_lock(&inode_lock);
+ cond_resched_lock(&sb_inode_list_lock);
next = next->next;
if (tmp == head)
@@ -413,9 +426,11 @@ int invalidate_inodes(struct super_block
down_write(&iprune_sem);
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
inotify_unmount_inodes(&sb->s_inodes);
fsnotify_unmount_inodes(&sb->s_inodes);
busy = invalidate_list(&sb->s_inodes, &throw_away);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
dispose_list(&throw_away);
@@ -603,7 +618,9 @@ __inode_add_to_lists(struct super_block
{
inodes_stat.nr_inodes++;
list_add(&inode->i_list, &inode_in_use);
+ spin_lock(&sb_inode_list_lock);
list_add(&inode->i_sb_list, &sb->s_inodes);
+ spin_unlock(&sb_inode_list_lock);
if (head)
hlist_add_head(&inode->i_hash, head);
}
@@ -1197,7 +1214,9 @@ void generic_delete_inode(struct inode *
const struct super_operations *op = inode->i_sb->s_op;
list_del_init(&inode->i_list);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
@@ -1255,7 +1274,9 @@ int generic_detach_inode(struct inode *i
hlist_del_init(&inode->i_hash);
}
list_del_init(&inode->i_list);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
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
@@ -429,6 +429,7 @@ void inotify_unmount_inodes(struct list_
* will be added since the umount has begun. Finally,
* iprune_mutex keeps shrink_icache_memory() away.
*/
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
if (need_iput_tmp)
@@ -451,6 +452,7 @@ void inotify_unmount_inodes(struct list_
iput(inode);
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
}
EXPORT_SYMBOL_GPL(inotify_unmount_inodes);
Index: linux-2.6/fs/quota/dquot.c
===================================================================
--- linux-2.6.orig/fs/quota/dquot.c
+++ linux-2.6/fs/quota/dquot.c
@@ -884,6 +884,7 @@ static void add_dquot_ref(struct super_b
#endif
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
@@ -897,6 +898,7 @@ static void add_dquot_ref(struct super_b
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
@@ -908,7 +910,9 @@ static void add_dquot_ref(struct super_b
* keep the reference and iput it later. */
old_inode = inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
@@ -988,6 +992,7 @@ static void remove_dquot_ref(struct supe
struct inode *inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_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
@@ -998,6 +1003,7 @@ static void remove_dquot_ref(struct supe
if (!IS_NOQUOTA(inode))
remove_inode_dquot_ref(inode, type, tofree_head);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
}
Index: linux-2.6/include/linux/writeback.h
===================================================================
--- linux-2.6.orig/include/linux/writeback.h
+++ linux-2.6/include/linux/writeback.h
@@ -10,6 +10,7 @@
struct backing_dev_info;
extern spinlock_t inode_lock;
+extern spinlock_t sb_inode_list_lock;
extern struct list_head inode_in_use;
extern struct list_head inode_unused;
Index: linux-2.6/fs/notify/inode_mark.c
===================================================================
--- linux-2.6.orig/fs/notify/inode_mark.c
+++ linux-2.6/fs/notify/inode_mark.c
@@ -408,6 +408,7 @@ void fsnotify_unmount_inodes(struct list
* will be added since the umount has begun. Finally,
* iprune_mutex keeps shrink_icache_memory() away.
*/
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
if (need_iput_tmp)
@@ -421,5 +422,6 @@ void fsnotify_unmount_inodes(struct list
iput(inode);
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
}
next prev parent reply other threads:[~2010-06-24 3:16 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-24 3:02 [patch 00/52] vfs scalability patches updated npiggin
2010-06-24 3:02 ` [patch 01/52] kernel: add bl_list npiggin
2010-06-24 6:04 ` Eric Dumazet
2010-06-24 14:42 ` Nick Piggin
2010-06-24 16:01 ` Eric Dumazet
2010-06-28 21:37 ` Paul E. McKenney
2010-06-29 6:30 ` Nick Piggin
2010-06-24 3:02 ` [patch 02/52] fs: fix superblock iteration race npiggin
2010-06-29 13:02 ` Christoph Hellwig
2010-06-29 14:56 ` Nick Piggin
2010-06-29 17:35 ` Linus Torvalds
2010-06-29 17:41 ` Nick Piggin
2010-06-29 17:52 ` Linus Torvalds
2010-06-29 17:58 ` Linus Torvalds
2010-06-29 20:04 ` Chris Clayton
2010-06-29 20:14 ` Nick Piggin
2010-06-29 20:38 ` Chris Clayton
2010-06-30 7:13 ` Chris Clayton
2010-06-30 12:51 ` Al Viro
2010-06-24 3:02 ` [patch 03/52] fs: fs_struct rwlock to spinlock npiggin
2010-06-24 3:02 ` [patch 04/52] fs: cleanup files_lock npiggin
2010-06-24 3:02 ` [patch 05/52] lglock: introduce special lglock and brlock spin locks npiggin
2010-06-24 18:15 ` Thomas Gleixner
2010-06-25 6:22 ` Nick Piggin
2010-06-25 9:50 ` Thomas Gleixner
2010-06-25 10:11 ` Nick Piggin
2010-06-24 3:02 ` [patch 06/52] fs: scale files_lock npiggin
2010-06-24 7:52 ` Peter Zijlstra
2010-06-24 15:00 ` Nick Piggin
2010-06-24 3:02 ` [patch 07/52] fs: brlock vfsmount_lock npiggin
2010-06-24 3:02 ` [patch 08/52] fs: scale mntget/mntput npiggin
2010-06-24 3:02 ` [patch 09/52] fs: dcache scale hash npiggin
2010-06-24 3:02 ` [patch 10/52] fs: dcache scale lru npiggin
2010-06-24 3:02 ` [patch 11/52] fs: dcache scale nr_dentry npiggin
2010-06-24 3:02 ` [patch 12/52] fs: dcache scale dentry refcount npiggin
2010-06-24 3:02 ` [patch 13/52] fs: dcache scale d_unhashed npiggin
2010-06-24 3:02 ` [patch 14/52] fs: dcache scale subdirs npiggin
2010-06-24 7:56 ` Peter Zijlstra
2010-06-24 9:50 ` Andi Kleen
2010-06-24 15:53 ` Nick Piggin
2010-06-24 3:02 ` [patch 15/52] fs: dcache scale inode alias list npiggin
2010-06-24 3:02 ` [patch 16/52] fs: dcache RCU for multi-step operaitons npiggin
2010-06-24 7:58 ` Peter Zijlstra
2010-06-24 15:03 ` Nick Piggin
2010-06-24 17:22 ` john stultz
2010-06-24 17:26 ` john stultz
2010-06-25 6:45 ` Nick Piggin
2010-06-24 3:02 ` [patch 17/52] fs: dcache remove dcache_lock npiggin
2010-06-24 3:02 ` [patch 18/52] fs: dcache reduce dput locking npiggin
2010-06-24 3:02 ` [patch 19/52] fs: dcache per-bucket dcache hash locking npiggin
2010-06-24 3:02 ` [patch 20/52] fs: dcache reduce dcache_inode_lock npiggin
2010-06-24 3:02 ` [patch 21/52] fs: dcache per-inode inode alias locking npiggin
2010-06-24 3:02 ` [patch 22/52] fs: dcache rationalise dget variants npiggin
2010-06-24 3:02 ` [patch 23/52] fs: dcache percpu nr_dentry npiggin
2010-06-24 3:02 ` [patch 24/52] fs: dcache reduce d_parent locking npiggin
2010-06-24 8:44 ` Peter Zijlstra
2010-06-24 15:07 ` Nick Piggin
2010-06-24 15:32 ` Paul E. McKenney
2010-06-24 16:05 ` Nick Piggin
2010-06-24 16:41 ` Paul E. McKenney
2010-06-28 21:50 ` Paul E. McKenney
2010-07-07 14:35 ` Nick Piggin
2010-06-24 3:02 ` [patch 25/52] fs: dcache DCACHE_REFERENCED improve npiggin
2010-06-24 3:02 ` npiggin [this message]
2010-06-24 3:02 ` [patch 27/52] fs: icache lock inode hash npiggin
2010-06-24 3:02 ` [patch 28/52] fs: icache lock i_state npiggin
2010-06-24 3:02 ` [patch 29/52] fs: icache lock i_count npiggin
2010-06-30 7:27 ` Dave Chinner
2010-06-30 12:05 ` Nick Piggin
2010-07-01 2:36 ` Dave Chinner
2010-07-01 7:54 ` Nick Piggin
2010-07-01 9:36 ` Nick Piggin
2010-07-01 16:21 ` Frank Mayhar
2010-07-03 2:03 ` Andrew Morton
2010-07-03 3:41 ` Nick Piggin
2010-07-03 4:31 ` Andrew Morton
2010-07-03 5:06 ` Nick Piggin
2010-07-03 5:18 ` Nick Piggin
2010-07-05 22:41 ` Dave Chinner
2010-07-06 4:34 ` Nick Piggin
2010-07-06 10:38 ` Theodore Tso
2010-07-06 13:04 ` Nick Piggin
2010-07-07 17:00 ` Frank Mayhar
2010-06-24 3:02 ` [patch 30/52] fs: icache lock lru/writeback lists npiggin
2010-06-24 8:58 ` Peter Zijlstra
2010-06-24 15:09 ` Nick Piggin
2010-06-24 15:13 ` Peter Zijlstra
2010-06-24 3:02 ` [patch 31/52] fs: icache atomic inodes_stat npiggin
2010-06-24 3:02 ` [patch 32/52] fs: icache protect inode state npiggin
2010-06-24 3:02 ` [patch 33/52] fs: icache atomic last_ino, iunique lock npiggin
2010-06-24 3:02 ` [patch 34/52] fs: icache remove inode_lock npiggin
2010-06-24 3:02 ` [patch 35/52] fs: icache factor hash lock into functions npiggin
2010-06-24 3:02 ` [patch 36/52] fs: icache per-bucket inode hash locks npiggin
2010-06-24 3:02 ` [patch 37/52] fs: icache lazy lru npiggin
2010-06-24 9:52 ` Andi Kleen
2010-06-24 15:59 ` Nick Piggin
2010-06-30 8:38 ` Dave Chinner
2010-06-30 12:06 ` Nick Piggin
2010-07-01 2:46 ` Dave Chinner
2010-07-01 7:57 ` Nick Piggin
2010-06-24 3:02 ` [patch 38/52] fs: icache RCU free inodes npiggin
2010-06-30 8:57 ` Dave Chinner
2010-06-30 12:07 ` Nick Piggin
2010-06-24 3:02 ` [patch 39/52] fs: icache rcu walk for i_sb_list npiggin
2010-06-24 3:02 ` [patch 40/52] fs: dcache improve scalability of pseudo filesystems npiggin
2010-06-24 3:02 ` [patch 41/52] fs: icache reduce atomics npiggin
2010-06-24 3:02 ` [patch 42/52] fs: icache per-cpu last_ino allocator npiggin
2010-06-24 9:48 ` Andi Kleen
2010-06-24 15:52 ` Nick Piggin
2010-06-24 16:19 ` Andi Kleen
2010-06-24 16:38 ` Nick Piggin
2010-06-24 3:02 ` [patch 43/52] fs: icache per-cpu nr_inodes counter npiggin
2010-06-24 3:02 ` [patch 44/52] fs: icache per-CPU sb inode lists and locks npiggin
2010-06-30 9:26 ` Dave Chinner
2010-06-30 12:08 ` Nick Piggin
2010-07-01 3:12 ` Dave Chinner
2010-07-01 8:00 ` Nick Piggin
2010-06-24 3:02 ` [patch 45/52] fs: icache RCU hash lookups npiggin
2010-06-24 3:02 ` [patch 46/52] fs: icache reduce locking npiggin
2010-06-24 3:02 ` [patch 47/52] fs: keep inode with backing-dev npiggin
2010-06-24 3:03 ` [patch 48/52] fs: icache split IO and LRU lists npiggin
2010-06-24 3:03 ` [patch 49/52] fs: icache scale writeback list locking npiggin
2010-06-24 3:03 ` [patch 50/52] mm: implement per-zone shrinker npiggin
2010-06-24 10:06 ` Andi Kleen
2010-06-24 16:00 ` Nick Piggin
2010-06-24 16:27 ` Andi Kleen
2010-06-24 16:32 ` Andi Kleen
2010-06-24 16:37 ` Andi Kleen
2010-06-30 6:28 ` Dave Chinner
2010-06-30 12:03 ` Nick Piggin
2010-06-24 3:03 ` [patch 51/52] fs: per-zone dentry and inode LRU npiggin
2010-06-30 10:09 ` Dave Chinner
2010-06-30 12:13 ` Nick Piggin
2010-06-24 3:03 ` [patch 52/52] fs: icache less I_FREEING time npiggin
2010-06-30 10:13 ` Dave Chinner
2010-06-30 12:14 ` Nick Piggin
2010-07-01 3:33 ` Dave Chinner
2010-07-01 8:06 ` Nick Piggin
2010-06-25 7:12 ` [patch 00/52] vfs scalability patches updated Christoph Hellwig
2010-06-25 8:05 ` Nick Piggin
2010-06-30 11:30 ` Dave Chinner
2010-06-30 12:40 ` Nick Piggin
2010-07-01 3:56 ` Dave Chinner
2010-07-01 8:20 ` Nick Piggin
2010-07-01 17:36 ` Andi Kleen
2010-07-01 17:23 ` Nick Piggin
2010-07-01 17:28 ` Andi Kleen
2010-07-06 17:49 ` Nick Piggin
2010-07-01 17:35 ` Linus Torvalds
2010-07-01 17:52 ` Nick Piggin
2010-07-02 4:01 ` Paul E. McKenney
2010-06-30 17:08 ` Frank Mayhar
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=20100624030729.765849671@suse.de \
--to=npiggin@suse.de \
--cc=fmayhar@google.com \
--cc=johnstul@us.ibm.com \
--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;
as well as URLs for NNTP newsgroup(s).