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
binfmt_em86.c
/*
 *  linux/fs/binfmt_em86.c
 *
 *  Based on linux/fs/binfmt_script.c
 *  Copyright (C) 1996  Martin von Löwis
 *  original #!-checking implemented by tytso.
 *
 *  em86 changes Copyright (C) 1997  Jim Paradis
 */

#include <linux/module.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/binfmts.h>
#include <linux/elf.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/errno.h>


#define EM86_INTERP	"/usr/bin/em86"
#define EM86_I_NAME	"em86"

static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
{
	char *interp, *i_name, *i_arg;
	struct file * file;
	int retval;
	struct elfhdr	elf_ex;

	/* Make sure this is a Linux/Intel ELF executable... */
	elf_ex = *((struct elfhdr *)bprm->buf);

	if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
		return  -ENOEXEC;

	/* First of all, some simple consistency checks */
	if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
		(!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
		(!bprm->file->f_op || !bprm->file->f_op->mmap)) {
			return -ENOEXEC;
	}

	bprm->recursion_depth++; /* Well, the bang-shell is implicit... */
	allow_write_access(bprm->file);
	fput(bprm->file);
	bprm->file = NULL;

	/* Unlike in the script case, we don't have to do any hairy
	 * parsing to find our interpreter... it's hardcoded!
	 */
	interp = EM86_INTERP;
	i_name = EM86_I_NAME;
	i_arg = NULL;		/* We reserve the right to add an arg later */

	/*
	 * Splice in (1) the interpreter's name for argv[0]
	 *           (2) (optional) argument to interpreter
	 *           (3) filename of emulated file (replace argv[0])
	 *
	 * This is done in reverse order, because of how the
	 * user environment and arguments are stored.
	 */
	remove_arg_zero(bprm);
	retval = copy_strings_kernel(1, &bprm->filename, bprm);
	if (retval < 0) return retval; 
	bprm->argc++;
	if (i_arg) {
		retval = copy_strings_kernel(1, &i_arg, bprm);
		if (retval < 0) return retval; 
		bprm->argc++;
	}
	retval = copy_strings_kernel(1, &i_name, bprm);
	if (retval < 0)	return retval;
	bprm->argc++;

	/*
	 * OK, now restart the process with the interpreter's inode.
	 * Note that we use open_exec() as the name is now in kernel
	 * space, and we don't need to copy it.
	 */
	file = open_exec(interp);
	if (IS_ERR(file))
		return PTR_ERR(file);

	bprm->file = file;

	retval = prepare_binprm(bprm);
	if (retval < 0)
		return retval;

	return search_binary_handler(bprm, regs);
}

static struct linux_binfmt em86_format = {
	.module		= THIS_MODULE,
	.load_binary	= load_em86,
};

static int __init init_em86_binfmt(void)
{
	return register_binfmt(&em86_format);
}

static void __exit exit_em86_binfmt(void)
{
	unregister_binfmt(&em86_format);
}

core_initcall(init_em86_binfmt);
module_exit(exit_em86_binfmt);
MODULE_LICENSE("GPL");
back to top