Commit 1e5289c9 authored by Eric W. Biederman's avatar Eric W. Biederman Committed by Greg Kroah-Hartman
Browse files

sysfs: Cache the last sysfs_dirent to improve readdir scalability v2 

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 abritrarily increasing the
hold time on the sysfs_mutex.

v2: Returned to using INT_MAX as the EOF condition.
    seekdir is ambiguous unless all directory entries have
    a unique f_pos value.

Fixes http://bugzilla.kernel.org/show_bug.cgi?id=14949



Signed-off-by: default avatarEric W. Biederman <ebiederm@aristanetworks.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable <stable@kernel.org>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@suse.de>
parent 3f5468c9

fs/sysfs/dir.c

+60 −22
Original line number Diff line number Diff line
@@ -837,11 +837,46 @@ 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 = NULL;

	if ((ino > 1) && (ino < INT_MAX)) {

		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) {
@@ -857,29 +892,31 @@ 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;



		for ( ; pos; pos = pos->s_sibling) {

	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;

			int len;

		unsigned int type;

		int len, ret;



		name = pos->s_name;

		len = strlen(name);

			filp->f_pos = ino = pos->s_ino;

		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)

		mutex_unlock(&sysfs_mutex);

		ret = filldir(dirent, name, len, filp->f_pos, ino, type);

		mutex_lock(&sysfs_mutex);

		if (ret < 0)

			break;

	}

		if (!pos)

			filp->f_pos = INT_MAX;

	mutex_unlock(&sysfs_mutex);

	if ((filp->f_pos > 1) && !pos) { /* EOF */

		filp->f_pos = INT_MAX;

		filp->private_data = NULL;

	}

	return 0;

}
@@ -888,5 +925,6 @@ 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,

};

CRA Git | Maintained and supported by SUSTech CRA and CCSE