linux-kernel - [PATCH] sysfs: Cache the last sysfs_dirent to improve readdir scalability

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]

Date:	Fri, 01 Jan 2010 05:58:00 -0800
From:	ebiederm@...ssion.com (Eric W. Biederman)
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
	Borislav Petkov <petkovbb@...glemail.com>,
	David Airlie <airlied@...ux.ie>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Greg KH <greg@...ah.com>, Al Viro <viro@...IV.linux.org.uk>
Subject: [PATCH] sysfs: Cache the last sysfs_dirent to improve readdir scalability


When sysfs_readdir stops short we now cache the next sysfs_dirent to
return to user space in filp->private_data.  There is no impact on the
rest of sysfs by doing this and in the common case it allows us to
pick up exactly where we left off with no seeking.

Additionally I drop and regrab the sysfs_mutex around filldir to avoid
a page fault arbitrarily increasing the hold time on the sysfs_mutex.

Signed-off-by: Eric W. Biederman <ebiederm@...stanetworks.com>
---

I haven't stressed this patch but it is sound in principle, and is a
general sysfs improvement, regardless of any locking issues.

 fs/sysfs/dir.c |   85 ++++++++++++++++++++++++++++++++++++++++---------------
 1 files changed, 62 insertions(+), 23 deletions(-)

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index f05f230..ad8a57e 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -827,19 +827,51 @@ static inline unsigned char dt_type(struct sysfs_dirent *sd)
 	return (sd->s_mode >> 12) & 15;
 }
 
+static int sysfs_dir_release(struct inode *inode, struct file *filp)
+{
+	sysfs_put(filp->private_data);
+	return 0;
+}
+
+static struct sysfs_dirent *sysfs_dir_pos(struct sysfs_dirent *parent_sd,
+	ino_t ino, struct sysfs_dirent *pos)
+{
+	if (pos) {
+		int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) &&
+			pos->s_parent == parent_sd &&
+			ino == pos->s_ino;
+		sysfs_put(pos);
+		if (valid)
+			return pos;
+	}
+	pos = parent_sd->s_dir.children;
+	while (pos && (ino > pos->s_ino))
+		pos = pos->s_sibling;
+	return pos;
+}
+
+static struct sysfs_dirent *sysfs_dir_next_pos(struct sysfs_dirent *parent_sd,
+	ino_t ino, struct sysfs_dirent *pos)
+{
+	pos = sysfs_dir_pos(parent_sd, ino, pos);
+	if (pos)
+		pos = pos->s_sibling;
+	return pos;
+}
+
 static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct sysfs_dirent * parent_sd = dentry->d_fsdata;
-	struct sysfs_dirent *pos;
+	struct sysfs_dirent *pos = filp->private_data;
 	ino_t ino;
 
-	if (filp->f_pos == 0) {
+	if (!pos && filp->f_pos == 0) {
 		ino = parent_sd->s_ino;
 		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
 	}
-	if (filp->f_pos == 1) {
+	if (!pos && filp->f_pos == 1) {
 		if (parent_sd->s_parent)
 			ino = parent_sd->s_parent->s_ino;
 		else
@@ -847,29 +879,35 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
 	}
-	if ((filp->f_pos > 1) && (filp->f_pos < INT_MAX)) {
-		mutex_lock(&sysfs_mutex);
-
-		/* Skip the dentries we have already reported */
-		pos = parent_sd->s_dir.children;
-		while (pos && (filp->f_pos > pos->s_ino))
-			pos = pos->s_sibling;
+	/* EOF? */
+	if (!pos && filp->f_pos > 2)
+		return 0;
 
-		for ( ; pos; pos = pos->s_sibling) {
-			const char * name;
-			int len;
-
-			name = pos->s_name;
-			len = strlen(name);
-			filp->f_pos = ino = pos->s_ino;
+	mutex_lock(&sysfs_mutex);
+	for (pos = sysfs_dir_pos(parent_sd, filp->f_pos, pos);
+	     pos;
+	     pos = sysfs_dir_next_pos(parent_sd, filp->f_pos, pos)) {
+		const char * name;
+		unsigned int type;
+		int len, ret;
+
+		name = pos->s_name;
+		len = strlen(name);
+		ino = pos->s_ino;
+		type = dt_type(pos);
+		filp->f_pos = ino;
+		filp->private_data = sysfs_get(pos);
 
-			if (filldir(dirent, name, len, filp->f_pos, ino,
-					 dt_type(pos)) < 0)
-				break;
-		}
-		if (!pos)
-			filp->f_pos = INT_MAX;
 		mutex_unlock(&sysfs_mutex);
+		ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+		mutex_lock(&sysfs_mutex);
+		if (ret < 0)
+			break;
+	}
+	mutex_unlock(&sysfs_mutex);
+	if (!pos) { /* EOF */
+		filp->f_pos = 3;
+		filp->private_data = NULL;
 	}
 	return 0;
 }
@@ -878,5 +916,6 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 const struct file_operations sysfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= sysfs_readdir,
+	.release	= sysfs_dir_release,
 	.llseek		= generic_file_llseek,
 };
-- 
1.6.5.2.143.g8cc62

--
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/