mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Nick Piggin <npiggin@kernel.dk>
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 34/46] fs: fs_struct use seqlock
Date: Sat, 27 Nov 2010 20:45:04 +1100	[thread overview]
Message-ID: <5c27a30f9abfb0efe7ec9e6ce2ddadca37110980.1290852959.git.npiggin@kernel.dk> (raw)
In-Reply-To: <cover.1290852958.git.npiggin@kernel.dk>

Use a seqlock in the fs_struct to enable us to take an atomic copy of the
complete cwd and root paths. Use this in the RCU lookup path to avoid a
thread-shared spinlock in RCU lookup operations.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
 fs/fs_struct.c            |   10 ++++++++++
 fs/namei.c                |   36 ++++++++++++++++++++++--------------
 include/linux/fs_struct.h |    3 +++
 3 files changed, 35 insertions(+), 14 deletions(-)

diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index ed45a9c..60b8531 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -14,9 +14,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 	struct path old_root;
 
 	spin_lock(&fs->lock);
+	write_seqcount_begin(&fs->seq);
 	old_root = fs->root;
 	fs->root = *path;
 	path_get(path);
+	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 	if (old_root.dentry)
 		path_put(&old_root);
@@ -31,9 +33,11 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 	struct path old_pwd;
 
 	spin_lock(&fs->lock);
+	write_seqcount_begin(&fs->seq);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
 	path_get(path);
+	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 
 	if (old_pwd.dentry)
@@ -52,6 +56,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 		fs = p->fs;
 		if (fs) {
 			spin_lock(&fs->lock);
+			write_seqcount_begin(&fs->seq);
 			if (fs->root.dentry == old_root->dentry
 			    && fs->root.mnt == old_root->mnt) {
 				path_get(new_root);
@@ -64,6 +69,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 				fs->pwd = *new_root;
 				count++;
 			}
+			write_seqcount_end(&fs->seq);
 			spin_unlock(&fs->lock);
 		}
 		task_unlock(p);
@@ -88,8 +94,10 @@ void exit_fs(struct task_struct *tsk)
 		int kill;
 		task_lock(tsk);
 		spin_lock(&fs->lock);
+		write_seqcount_begin(&fs->seq);
 		tsk->fs = NULL;
 		kill = !--fs->users;
+		write_seqcount_end(&fs->seq);
 		spin_unlock(&fs->lock);
 		task_unlock(tsk);
 		if (kill)
@@ -105,6 +113,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 		fs->users = 1;
 		fs->in_exec = 0;
 		spin_lock_init(&fs->lock);
+		seqcount_init(&fs->seq);
 		fs->umask = old->umask;
 		get_fs_root_and_pwd(old, &fs->root, &fs->pwd);
 	}
@@ -144,6 +153,7 @@ EXPORT_SYMBOL(current_umask);
 struct fs_struct init_fs = {
 	.users		= 1,
 	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
+	.seq		= SEQCNT_ZERO,
 	.umask		= 0022,
 };
 
diff --git a/fs/namei.c b/fs/namei.c
index 5185752..c48d208 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -640,9 +640,12 @@ static __always_inline void set_root_rcu(struct nameidata *nd)
 {
 	if (!nd->root.mnt) {
 		struct fs_struct *fs = current->fs;
-		spin_lock(&fs->lock);
-		nd->root = fs->root;
-		spin_unlock(&fs->lock);
+		unsigned seq;
+
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+		} while (read_seqcount_retry(&fs->seq, seq));
 	}
 }
 
@@ -1324,26 +1327,31 @@ static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct n
 
 	if (*name=='/') {
 		struct fs_struct *fs = current->fs;
+		unsigned seq;
 
 		br_read_lock(vfsmount_lock);
 		rcu_read_lock();
 
-		spin_lock(&fs->lock);
-		nd->root = fs->root;
-		nd->path = nd->root;
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-		spin_unlock(&fs->lock);
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+			nd->path = nd->root;
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
 
 	} else if (dfd == AT_FDCWD) {
 		struct fs_struct *fs = current->fs;
+		unsigned seq;
 
 		br_read_lock(vfsmount_lock);
 		rcu_read_lock();
 
-		spin_lock(&fs->lock);
-		nd->path = fs->pwd;
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-		spin_unlock(&fs->lock);
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->path = fs->pwd;
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
+
 	} else {
 		struct dentry *dentry;
 
@@ -1366,7 +1374,7 @@ static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct n
 		if (fput_needed)
 			nd->file = file;
 
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+		nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 		br_read_lock(vfsmount_lock);
 		rcu_read_lock();
 	}
@@ -2199,7 +2207,7 @@ creat:
 	if (error)
 		goto out_filp;
 	error = path_walk_rcu(pathname, &nd);
-	path_finish_rcu(&nd);
+	path_finish_rcu(&nd); /* XXX: ok to throw out root here?? */
 	if (unlikely(error == -ECHILD || error == -ESTALE)) {
 		/* slower, locked walk */
 		if (error == -ESTALE) {
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index a42b5bf..003dc0f 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -2,10 +2,13 @@
 #define _LINUX_FS_STRUCT_H
 
 #include <linux/path.h>
+#include <linux/spinlock.h>
+#include <linux/seqlock.h>
 
 struct fs_struct {
 	int users;
 	spinlock_t lock;
+	seqcount_t seq;
 	int umask;
 	int in_exec;
 	struct path root, pwd;
-- 
1.7.1


  parent reply	other threads:[~2010-11-27 10:27 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-27 10:15 [PATCH 00/46] rcu-walk and dcache scaling Nick Piggin
2010-11-27  9:44 ` [PATCH 02/46] fs: d_validate fixes Nick Piggin
2010-12-08  1:53   ` Dave Chinner
2010-12-08  6:59     ` Nick Piggin
2010-12-09  0:50       ` Dave Chinner
2010-12-09  4:50         ` Nick Piggin
2010-11-27  9:44 ` [PATCH 03/46] kernel: kmem_ptr_validate considered harmful Nick Piggin
2010-11-27  9:44 ` [PATCH 04/46] fs: dcache documentation cleanup Nick Piggin
2010-11-27  9:44 ` [PATCH 05/46] fs: change d_delete semantics Nick Piggin
2010-11-27  9:44 ` [PATCH 06/46] cifs: dont overwrite dentry name in d_revalidate Nick Piggin
2010-11-27  9:44 ` [PATCH 07/46] jfs: " Nick Piggin
2010-11-27  9:44 ` [PATCH 08/46] fs: change d_compare for rcu-walk Nick Piggin
2010-11-27  9:44 ` [PATCH 09/46] fs: change d_hash " Nick Piggin
2010-11-27  9:44 ` [PATCH 10/46] hostfs: simplify locking Nick Piggin
2010-11-27  9:44 ` [PATCH 11/46] fs: dcache scale hash Nick Piggin
2010-12-09  6:09   ` Dave Chinner
2010-12-09  6:28     ` Nick Piggin
2010-12-09  8:17       ` Dave Chinner
2010-12-09 12:53         ` Nick Piggin
2010-12-09 23:42           ` Dave Chinner
2010-12-10  2:35             ` Nick Piggin
2010-12-10  9:01               ` Dave Chinner
2010-12-13  4:48                 ` Nick Piggin
2010-12-13  5:05                 ` Nick Piggin
2010-11-27  9:44 ` [PATCH 12/46] fs: dcache scale lru Nick Piggin
2010-12-09  7:22   ` Dave Chinner
2010-12-09 12:34     ` Nick Piggin
2010-11-27  9:44 ` [PATCH 13/46] fs: dcache scale dentry refcount Nick Piggin
2010-11-27  9:44 ` [PATCH 14/46] fs: dcache scale d_unhashed Nick Piggin
2010-11-27  9:44 ` [PATCH 15/46] fs: dcache scale subdirs Nick Piggin
2010-11-27  9:44 ` [PATCH 16/46] fs: scale inode alias list Nick Piggin
2010-11-27  9:44 ` [PATCH 17/46] fs: Use rename lock and RCU for multi-step operations Nick Piggin
2011-01-18 22:32   ` Yehuda Sadeh Weinraub
2011-01-18 22:42     ` Nick Piggin
2011-01-19 22:27       ` Yehuda Sadeh Weinraub
2011-01-19 22:32         ` Nick Piggin
2011-01-25 22:10           ` Yehuda Sadeh Weinraub
2011-01-27  5:18             ` Nick Piggin
2011-02-07 18:52               ` Jim Schutt
2011-02-07 21:04                 ` Yehuda Sadeh Weinraub
2011-02-07 21:31                   ` Jim Schutt
2011-02-07 22:25                   ` Jim Schutt
2011-02-14 17:57               ` Yehuda Sadeh Weinraub
2010-11-27  9:44 ` [PATCH 18/46] fs: increase d_name lock coverage Nick Piggin
2010-11-27  9:44 ` [PATCH 19/46] fs: dcache remove dcache_lock Nick Piggin
2010-11-27  9:44 ` [PATCH 20/46] fs: dcache avoid starvation in dcache multi-step operations Nick Piggin
2010-11-27  9:44 ` [PATCH 21/46] fs: dcache reduce dput locking Nick Piggin
2010-11-27  9:44 ` [PATCH 22/46] fs: dcache reduce locking in d_alloc Nick Piggin
2010-11-27  9:44 ` [PATCH 23/46] fs: dcache reduce dcache_inode_lock Nick Piggin
2010-11-27  9:44 ` [PATCH 24/46] fs: dcache rationalise dget variants Nick Piggin
2010-11-27  9:44 ` [PATCH 25/46] fs: dcache reduce d_parent locking Nick Piggin
2010-11-27  9:44 ` [PATCH 26/46] fs: dcache reduce prune_one_dentry locking Nick Piggin
2010-11-27  9:44 ` [PATCH 27/46] fs: reduce dcache_inode_lock width in lru scanning Nick Piggin
2010-11-27  9:44 ` [PATCH 28/46] fs: use RCU in shrink_dentry_list to reduce lock nesting Nick Piggin
2010-11-27  9:44 ` [PATCH 29/46] fs: consolidate dentry kill sequence Nick Piggin
2010-11-27  9:45 ` [PATCH 30/46] fs: icache RCU free inodes Nick Piggin
2010-11-27  9:45 ` [PATCH 31/46] fs: avoid inode RCU freeing for pseudo fs Nick Piggin
2010-11-27  9:45 ` [PATCH 32/46] kernel: optimise seqlock Nick Piggin
2010-11-27  9:45 ` [PATCH 33/46] fs: rcu-walk for path lookup Nick Piggin
2010-11-27  9:45 ` Nick Piggin [this message]
2010-11-27  9:45 ` [PATCH 35/46] fs: dcache remove d_mounted Nick Piggin
2010-11-27  9:45 ` [PATCH 36/46] fs: dcache reduce branches in lookup path Nick Piggin
2010-11-27  9:45 ` [PATCH 37/46] fs: cache optimise dentry and inode for rcu-walk Nick Piggin
2010-11-27  9:45 ` [PATCH 38/46] fs: prefetch inode data in dcache lookup Nick Piggin
2010-11-27  9:45 ` [PATCH 39/46] fs: d_revalidate_rcu for rcu-walk Nick Piggin
2010-11-27  9:45 ` [PATCH 40/46] fs: provide rcu-walk aware permission i_ops Nick Piggin
2010-11-27  9:45 ` [PATCH 41/46] fs: provide simple rcu-walk ACL implementation Nick Piggin
2010-11-27  9:45 ` [PATCH 42/46] kernel: add bl_list Nick Piggin
2010-11-27  9:45 ` [PATCH 43/46] bit_spinlock: add required includes Nick Piggin
2010-11-27  9:45 ` [PATCH 44/46] fs: dcache per-bucket dcache hash locking Nick Piggin
2010-11-27  9:45 ` [PATCH 45/46] fs: dcache per-inode inode alias locking Nick Piggin
2010-11-27  9:45 ` [PATCH 46/46] fs: improve scalability of pseudo filesystems Nick Piggin
2010-11-27  9:56 ` [PATCH 01/46] Revert "fs: use RCU read side protection in d_validate" Nick Piggin
2010-12-08  1:16   ` Dave Chinner
2010-12-08  9:38     ` Nick Piggin
2010-12-09  0:44       ` Dave Chinner
2010-12-09  4:38         ` Nick Piggin
2010-12-09  5:16           ` Nick Piggin
2010-11-27 15:04 ` [PATCH 00/46] rcu-walk and dcache scaling Anca Emanuel
2010-11-28  3:28   ` Nick Piggin
2010-11-28  6:24     ` Sedat Dilek
2010-12-01 18:03 ` David Miller
2010-12-03 16:55   ` Nick Piggin
2010-12-07 11:25 ` Dave Chinner
2010-12-07 15:24   ` Nick Piggin
2010-12-07 15:49     ` Peter Zijlstra
2010-12-07 15:59       ` Nick Piggin
2010-12-07 16:23         ` Peter Zijlstra
2010-12-08  3:28     ` Nick Piggin
2010-12-07 21:56 ` Dave Chinner
2010-12-08  1:47   ` Nick Piggin
2010-12-08  3:32     ` Dave Chinner
2010-12-08  4:28       ` Dave Chinner
2010-12-08  7:09         ` Nick Piggin
2010-12-10 20:32           ` Paul E. McKenney
2010-12-12 14:54             ` Paul E. McKenney

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=5c27a30f9abfb0efe7ec9e6ce2ddadca37110980.1290852959.git.npiggin@kernel.dk \
    --to=npiggin@kernel.dk \
    --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

all inboxes | Powered by JetHome®