Revision e34a314c5e49fe6b763568f6576b19f1299c33c2 authored by Dave Chinner on 27 January 2011, 01:13:35 UTC, committed by Alex Elder on 28 January 2011, 15:01:33 UTC
After test 139, kmemleak shows:

unreferenced object 0xffff880078b405d8 (size 400):
  comm "xfs_io", pid 4904, jiffies 4294909383 (age 1186.728s)
  hex dump (first 32 bytes):
    60 c1 17 79 00 88 ff ff 60 c1 17 79 00 88 ff ff  `..y....`..y....
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff81afb04d>] kmemleak_alloc+0x2d/0x60
    [<ffffffff8115c6cf>] kmem_cache_alloc+0x13f/0x2b0
    [<ffffffff814aaa97>] kmem_zone_alloc+0x77/0xf0
    [<ffffffff814aab2e>] kmem_zone_zalloc+0x1e/0x50
    [<ffffffff8147cd6b>] xfs_efi_init+0x4b/0xb0
    [<ffffffff814a4ee8>] xfs_trans_get_efi+0x58/0x90
    [<ffffffff81455fab>] xfs_bmap_finish+0x8b/0x1d0
    [<ffffffff814851b4>] xfs_itruncate_finish+0x2c4/0x5d0
    [<ffffffff814a970f>] xfs_setattr+0x8df/0xa70
    [<ffffffff814b5c7b>] xfs_vn_setattr+0x1b/0x20
    [<ffffffff8117dc00>] notify_change+0x170/0x2e0
    [<ffffffff81163bf6>] do_truncate+0x66/0xa0
    [<ffffffff81163d0b>] sys_ftruncate+0xdb/0xe0
    [<ffffffff8103a002>] system_call_fastpath+0x16/0x1b
    [<ffffffffffffffff>] 0xffffffffffffffff

The cause of the leak is that the "remove" parameter of IOP_UNPIN()
is never set when a CIL push is aborted. This means that the EFI
item is never freed if it was in the push being cancelled. The
problem is specific to delayed logging, but has uncovered a couple
of problems with the handling of IOP_UNPIN(remove).

Firstly, we cannot safely call xfs_trans_del_item() from IOP_UNPIN()
in the CIL commit failure path or the iclog write failure path
because for delayed loging we have no transaction context. Hence we
must only call xfs_trans_del_item() if the log item being unpinned
has an active log item descriptor.

Secondly, xfs_trans_uncommit() does not handle log item descriptor
freeing during the traversal of log items on a transaction. It can
reference a freed log item descriptor when unpinning an EFI item.
Hence it needs to use a safe list traversal method to allow items to
be removed from the transaction during IOP_UNPIN().

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Alex Elder <aelder@sgi.com>
1 parent 7db37c5
Raw File
stat.c
/*
 *  linux/fs/stat.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>

void generic_fillattr(struct inode *inode, struct kstat *stat)
{
	stat->dev = inode->i_sb->s_dev;
	stat->ino = inode->i_ino;
	stat->mode = inode->i_mode;
	stat->nlink = inode->i_nlink;
	stat->uid = inode->i_uid;
	stat->gid = inode->i_gid;
	stat->rdev = inode->i_rdev;
	stat->atime = inode->i_atime;
	stat->mtime = inode->i_mtime;
	stat->ctime = inode->i_ctime;
	stat->size = i_size_read(inode);
	stat->blocks = inode->i_blocks;
	stat->blksize = (1 << inode->i_blkbits);
}

EXPORT_SYMBOL(generic_fillattr);

int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	int retval;

	retval = security_inode_getattr(mnt, dentry);
	if (retval)
		return retval;

	if (inode->i_op->getattr)
		return inode->i_op->getattr(mnt, dentry, stat);

	generic_fillattr(inode, stat);
	return 0;
}

EXPORT_SYMBOL(vfs_getattr);

int vfs_fstat(unsigned int fd, struct kstat *stat)
{
	struct file *f = fget(fd);
	int error = -EBADF;

	if (f) {
		error = vfs_getattr(f->f_path.mnt, f->f_path.dentry, stat);
		fput(f);
	}
	return error;
}
EXPORT_SYMBOL(vfs_fstat);

int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
		int flag)
{
	struct path path;
	int error = -EINVAL;
	int lookup_flags = 0;

	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0)
		goto out;

	if (!(flag & AT_SYMLINK_NOFOLLOW))
		lookup_flags |= LOOKUP_FOLLOW;
	if (flag & AT_NO_AUTOMOUNT)
		lookup_flags |= LOOKUP_NO_AUTOMOUNT;

	error = user_path_at(dfd, filename, lookup_flags, &path);
	if (error)
		goto out;

	error = vfs_getattr(path.mnt, path.dentry, stat);
	path_put(&path);
out:
	return error;
}
EXPORT_SYMBOL(vfs_fstatat);

int vfs_stat(const char __user *name, struct kstat *stat)
{
	return vfs_fstatat(AT_FDCWD, name, stat, 0);
}
EXPORT_SYMBOL(vfs_stat);

int vfs_lstat(const char __user *name, struct kstat *stat)
{
	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}
EXPORT_SYMBOL(vfs_lstat);


#ifdef __ARCH_WANT_OLD_STAT

/*
 * For backward compatibility?  Maybe this should be moved
 * into arch/i386 instead?
 */
static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf)
{
	static int warncount = 5;
	struct __old_kernel_stat tmp;
	
	if (warncount > 0) {
		warncount--;
		printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
			current->comm);
	} else if (warncount < 0) {
		/* it's laughable, but... */
		warncount = 0;
	}

	memset(&tmp, 0, sizeof(struct __old_kernel_stat));
	tmp.st_dev = old_encode_dev(stat->dev);
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, stat->uid);
	SET_GID(tmp.st_gid, stat->gid);
	tmp.st_rdev = old_encode_dev(stat->rdev);
#if BITS_PER_LONG == 32
	if (stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
#endif	
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_ctime = stat->ctime.tv_sec;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(stat, const char __user *, filename,
		struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_stat(filename, &stat);
	if (error)
		return error;

	return cp_old_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(lstat, const char __user *, filename,
		struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;

	return cp_old_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_old_stat(&stat, statbuf);

	return error;
}

#endif /* __ARCH_WANT_OLD_STAT */

static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
{
	struct stat tmp;

#if BITS_PER_LONG == 32
	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
		return -EOVERFLOW;
#else
	if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
		return -EOVERFLOW;
#endif

	memset(&tmp, 0, sizeof(tmp));
#if BITS_PER_LONG == 32
	tmp.st_dev = old_encode_dev(stat->dev);
#else
	tmp.st_dev = new_encode_dev(stat->dev);
#endif
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, stat->uid);
	SET_GID(tmp.st_gid, stat->gid);
#if BITS_PER_LONG == 32
	tmp.st_rdev = old_encode_dev(stat->rdev);
#else
	tmp.st_rdev = new_encode_dev(stat->rdev);
#endif
#if BITS_PER_LONG == 32
	if (stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
#endif	
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_ctime = stat->ctime.tv_sec;
#ifdef STAT_HAVE_NSEC
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
#endif
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(newstat, const char __user *, filename,
		struct stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_stat(filename, &stat);

	if (error)
		return error;
	return cp_new_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(newlstat, const char __user *, filename,
		struct stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;

	return cp_new_stat(&stat, statbuf);
}

#if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename,
		struct stat __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_new_stat(&stat, statbuf);
}
#endif

SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_new_stat(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
		char __user *, buf, int, bufsiz)
{
	struct path path;
	int error;

	if (bufsiz <= 0)
		return -EINVAL;

	error = user_path_at(dfd, pathname, 0, &path);
	if (!error) {
		struct inode *inode = path.dentry->d_inode;

		error = -EINVAL;
		if (inode->i_op->readlink) {
			error = security_inode_readlink(path.dentry);
			if (!error) {
				touch_atime(path.mnt, path.dentry);
				error = inode->i_op->readlink(path.dentry,
							      buf, bufsiz);
			}
		}
		path_put(&path);
	}
	return error;
}

SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf,
		int, bufsiz)
{
	return sys_readlinkat(AT_FDCWD, path, buf, bufsiz);
}


/* ---------- LFS-64 ----------- */
#ifdef __ARCH_WANT_STAT64

static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
{
	struct stat64 tmp;

	memset(&tmp, 0, sizeof(struct stat64));
#ifdef CONFIG_MIPS
	/* mips has weird padding, so we don't get 64 bits there */
	if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
		return -EOVERFLOW;
	tmp.st_dev = new_encode_dev(stat->dev);
	tmp.st_rdev = new_encode_dev(stat->rdev);
#else
	tmp.st_dev = huge_encode_dev(stat->dev);
	tmp.st_rdev = huge_encode_dev(stat->rdev);
#endif
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
#ifdef STAT64_HAS_BROKEN_ST_INO
	tmp.__st_ino = stat->ino;
#endif
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	tmp.st_uid = stat->uid;
	tmp.st_gid = stat->gid;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime = stat->ctime.tv_sec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
	tmp.st_size = stat->size;
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(stat64, const char __user *, filename,
		struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_stat(filename, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE2(lstat64, const char __user *, filename,
		struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_lstat(filename, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
		struct stat64 __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_new_stat64(&stat, statbuf);
}
#endif /* __ARCH_WANT_STAT64 */

/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
void __inode_add_bytes(struct inode *inode, loff_t bytes)
{
	inode->i_blocks += bytes >> 9;
	bytes &= 511;
	inode->i_bytes += bytes;
	if (inode->i_bytes >= 512) {
		inode->i_blocks++;
		inode->i_bytes -= 512;
	}
}

void inode_add_bytes(struct inode *inode, loff_t bytes)
{
	spin_lock(&inode->i_lock);
	__inode_add_bytes(inode, bytes);
	spin_unlock(&inode->i_lock);
}

EXPORT_SYMBOL(inode_add_bytes);

void inode_sub_bytes(struct inode *inode, loff_t bytes)
{
	spin_lock(&inode->i_lock);
	inode->i_blocks -= bytes >> 9;
	bytes &= 511;
	if (inode->i_bytes < bytes) {
		inode->i_blocks--;
		inode->i_bytes += 512;
	}
	inode->i_bytes -= bytes;
	spin_unlock(&inode->i_lock);
}

EXPORT_SYMBOL(inode_sub_bytes);

loff_t inode_get_bytes(struct inode *inode)
{
	loff_t ret;

	spin_lock(&inode->i_lock);
	ret = (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
	spin_unlock(&inode->i_lock);
	return ret;
}

EXPORT_SYMBOL(inode_get_bytes);

void inode_set_bytes(struct inode *inode, loff_t bytes)
{
	/* Caller is here responsible for sufficient locking
	 * (ie. inode->i_lock) */
	inode->i_blocks = bytes >> 9;
	inode->i_bytes = bytes & 511;
}

EXPORT_SYMBOL(inode_set_bytes);
back to top