Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node:

    BUG: unable to handle kernel paging request at ffffc90008963690
    IP: __wake_up_bit+0x20/0x70
    Oops: 0000 [#1] SMP
    CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80
    Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015
    task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000
    RIP: 0010:[<ffffffff810dff80>]  [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
    RSP: 0018:ffff880017b97be8  EFLAGS: 00010246
    RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9
    RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648
    RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000
    R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800
    R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000
    FS:  00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0
    Call Trace:
      unlock_page+0x6d/0x70
      generic_write_end+0x53/0xb0
      xfs_vm_write_end+0x29/0x80 [xfs]
      generic_perform_write+0x10a/0x1e0
      xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs]
      xfs_file_write_iter+0x79/0x120 [xfs]
      __vfs_write+0xd4/0x110
      vfs_write+0xac/0x1c0
      SyS_write+0x58/0xd0
      system_call_fastpath+0x12/0x76
    Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48
    RIP  [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
     RSP <ffff880017b97be8>
    CR2: ffffc90008963690

Reproduce method (re-add a node)::
  Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic)

This seems an use-after-free problem, and the root cause is
zone->wait_table was not set to *NULL* after free it in
try_offline_node.

When hot re-add a node, we will reuse the pgdat of it, so does the zone
struct, and when add pages to the target zone, it will init the zone
first (including the wait_table) if the zone is not initialized.  The
judgement of zone initialized is based on zone->wait_table:

	static inline bool zone_is_initialized(struct zone *zone)
	{
		return !!zone->wait_table;
	}

so if we do not set the zone->wait_table to *NULL* after free it, the
memory hotplug routine will skip the init of new zone when hot re-add
the node, and the wait_table still points to the freed memory, then we
will access the invalid address when trying to wake up the waiting
people after the i/o operation with the page is done, such as mentioned
above.

Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com>
Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5879ae5
Raw File
md5.c
/* 
 * Cryptographic API.
 *
 * MD5 Message Digest Algorithm (RFC1321).
 *
 * Derived from cryptoapi implementation, originally based on the
 * public domain implementation written by Colin Plumb in 1993.
 *
 * Copyright (c) Cryptoapi developers.
 * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
 * 
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option) 
 * any later version.
 *
 */
#include <crypto/internal/hash.h>
#include <crypto/md5.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/cryptohash.h>
#include <asm/byteorder.h>

/* XXX: this stuff can be optimized */
static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
{
	while (words--) {
		__le32_to_cpus(buf);
		buf++;
	}
}

static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
{
	while (words--) {
		__cpu_to_le32s(buf);
		buf++;
	}
}

static inline void md5_transform_helper(struct md5_state *ctx)
{
	le32_to_cpu_array(ctx->block, sizeof(ctx->block) / sizeof(u32));
	md5_transform(ctx->hash, ctx->block);
}

static int md5_init(struct shash_desc *desc)
{
	struct md5_state *mctx = shash_desc_ctx(desc);

	mctx->hash[0] = 0x67452301;
	mctx->hash[1] = 0xefcdab89;
	mctx->hash[2] = 0x98badcfe;
	mctx->hash[3] = 0x10325476;
	mctx->byte_count = 0;

	return 0;
}

static int md5_update(struct shash_desc *desc, const u8 *data, unsigned int len)
{
	struct md5_state *mctx = shash_desc_ctx(desc);
	const u32 avail = sizeof(mctx->block) - (mctx->byte_count & 0x3f);

	mctx->byte_count += len;

	if (avail > len) {
		memcpy((char *)mctx->block + (sizeof(mctx->block) - avail),
		       data, len);
		return 0;
	}

	memcpy((char *)mctx->block + (sizeof(mctx->block) - avail),
	       data, avail);

	md5_transform_helper(mctx);
	data += avail;
	len -= avail;

	while (len >= sizeof(mctx->block)) {
		memcpy(mctx->block, data, sizeof(mctx->block));
		md5_transform_helper(mctx);
		data += sizeof(mctx->block);
		len -= sizeof(mctx->block);
	}

	memcpy(mctx->block, data, len);

	return 0;
}

static int md5_final(struct shash_desc *desc, u8 *out)
{
	struct md5_state *mctx = shash_desc_ctx(desc);
	const unsigned int offset = mctx->byte_count & 0x3f;
	char *p = (char *)mctx->block + offset;
	int padding = 56 - (offset + 1);

	*p++ = 0x80;
	if (padding < 0) {
		memset(p, 0x00, padding + sizeof (u64));
		md5_transform_helper(mctx);
		p = (char *)mctx->block;
		padding = 56;
	}

	memset(p, 0, padding);
	mctx->block[14] = mctx->byte_count << 3;
	mctx->block[15] = mctx->byte_count >> 29;
	le32_to_cpu_array(mctx->block, (sizeof(mctx->block) -
	                  sizeof(u64)) / sizeof(u32));
	md5_transform(mctx->hash, mctx->block);
	cpu_to_le32_array(mctx->hash, sizeof(mctx->hash) / sizeof(u32));
	memcpy(out, mctx->hash, sizeof(mctx->hash));
	memset(mctx, 0, sizeof(*mctx));

	return 0;
}

static int md5_export(struct shash_desc *desc, void *out)
{
	struct md5_state *ctx = shash_desc_ctx(desc);

	memcpy(out, ctx, sizeof(*ctx));
	return 0;
}

static int md5_import(struct shash_desc *desc, const void *in)
{
	struct md5_state *ctx = shash_desc_ctx(desc);

	memcpy(ctx, in, sizeof(*ctx));
	return 0;
}

static struct shash_alg alg = {
	.digestsize	=	MD5_DIGEST_SIZE,
	.init		=	md5_init,
	.update		=	md5_update,
	.final		=	md5_final,
	.export		=	md5_export,
	.import		=	md5_import,
	.descsize	=	sizeof(struct md5_state),
	.statesize	=	sizeof(struct md5_state),
	.base		=	{
		.cra_name	=	"md5",
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
};

static int __init md5_mod_init(void)
{
	return crypto_register_shash(&alg);
}

static void __exit md5_mod_fini(void)
{
	crypto_unregister_shash(&alg);
}

module_init(md5_mod_init);
module_exit(md5_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MD5 Message Digest Algorithm");
MODULE_ALIAS_CRYPTO("md5");
back to top