linux-kernel - [PATCH 4/4] fs: remove inode_lock from iput_final and prune

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1288153384-8878-5-git-send-email-david@fromorbit.com>
Date:	Wed, 27 Oct 2010 15:23:04 +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 4/4] fs: remove inode_lock from iput_final and prune_icache

From: Dave Chinner <dchinner@...hat.com>

Now that inode state changes are protected by the inode->i_lock and
the inode LRU manipulations by the inode_lru_lock, we can remove the
inode_lock from prune_icache and the initial part of iput_final().

instead of using the inode_lock to protect the inode during
iput_final, use the inode->i_lock instead. This protects the inode
against new references being taken while we change the inode state
to I_FREEING, as well as preventing prune_icache from grabbing the
inode while we are manipulating it. Hence we no longer need the
iṉode_lock in iput_final prior to setting I_FREEING on the inode.

For prune_icache, we no longer need the inode_lock to protect the
LRU list, and the inodes themselves are protected against freeing
races by the inode->i_lock. Hence we can lift the inode_lock from
prune_icache as well.

Signed-off-by: Dave Chinner <dchinner@...hat.com>
---
 fs/inode.c |   19 +++++--------------
 1 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index e04371e..b5f1585 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -634,7 +634,6 @@ static void prune_icache(int nr_to_scan)
 	unsigned long reap = 0;
 
 	down_read(&iprune_sem);
-	spin_lock(&inode_lock);
 	spin_lock(&inode_lru_lock);
 	for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
 		struct inode *inode;
@@ -660,8 +659,8 @@ static void prune_icache(int nr_to_scan)
 		 */
 		if (atomic_read(&inode->i_count) ||
 		    (inode->i_state & ~I_REFERENCED)) {
-			spin_unlock(&inode->i_lock);
 			list_del_init(&inode->i_lru);
+			spin_unlock(&inode->i_lock);
 			percpu_counter_dec(&nr_inodes_unused);
 			continue;
 		}
@@ -669,20 +668,18 @@ static void prune_icache(int nr_to_scan)
 		/* recently referenced inodes get one more pass */
 		if (inode->i_state & I_REFERENCED) {
 			inode->i_state &= ~I_REFERENCED;
-			spin_unlock(&inode->i_lock);
 			list_move(&inode->i_lru, &inode_lru);
+			spin_unlock(&inode->i_lock);
 			continue;
 		}
 		if (inode_has_buffers(inode) || inode->i_data.nrpages) {
 			__iget(inode);
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_lru_lock);
-			spin_unlock(&inode_lock);
 			if (remove_inode_buffers(inode))
 				reap += invalidate_mapping_pages(&inode->i_data,
 								0, -1);
 			iput(inode);
-			spin_lock(&inode_lock);
 			spin_lock(&inode_lru_lock);
 
 			if (inode != list_entry(inode_lru.next,
@@ -701,8 +698,8 @@ static void prune_icache(int nr_to_scan)
 		spin_unlock(&inode->i_lock);
 
 		/*
-		 * Move the inode off the IO lists and LRU once I_FREEING is
-		 * set so that it won't get moved back on there if it is dirty.
+		 * Move the inode off the LRU once I_FREEING is set so that it
+		 * won't get moved back on there if it is dirty.
 		 */
 		list_move(&inode->i_lru, &freeable);
 		percpu_counter_dec(&nr_inodes_unused);
@@ -712,7 +709,6 @@ static void prune_icache(int nr_to_scan)
 	else
 		__count_vm_events(PGINODESTEAL, reap);
 	spin_unlock(&inode_lru_lock);
-	spin_unlock(&inode_lock);
 
 	dispose_list(&freeable);
 	up_read(&iprune_sem);
@@ -1429,7 +1425,6 @@ static void iput_final(struct inode *inode)
 	const struct super_operations *op = inode->i_sb->s_op;
 	int drop;
 
-	spin_lock(&inode->i_lock);
 	WARN_ON(inode->i_state & I_NEW);
 
 	if (op && op->drop_inode)
@@ -1442,16 +1437,13 @@ static void iput_final(struct inode *inode)
 		if (!(inode->i_state & (I_DIRTY|I_SYNC)))
 			inode_lru_list_add(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_lock);
 		return;
 	}
 
 	if (!drop) {
 		inode->i_state |= I_WILL_FREE;
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_lock);
 		write_inode_now(inode, 1);
-		spin_lock(&inode_lock);
 		spin_lock(&inode->i_lock);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state &= ~I_WILL_FREE;
@@ -1460,7 +1452,6 @@ static void iput_final(struct inode *inode)
 	inode->i_state |= I_FREEING;
 	inode_lru_list_del(inode);
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_lock);
 
 	dispose_one_inode(inode);
 }
@@ -1479,7 +1470,7 @@ void iput(struct inode *inode)
 	if (inode) {
 		BUG_ON(inode->i_state & I_CLEAR);
 
-		if (atomic_dec_and_lock(&inode->i_count, &inode_lock))
+		if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
 			iput_final(inode);
 	}
 }
-- 
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/