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
rmd256.c
/*
 * Cryptographic API.
 *
 * RIPEMD-256 - RACE Integrity Primitives Evaluation Message Digest.
 *
 * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
 *
 * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
 *
 * 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 <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <asm/byteorder.h>

#include "ripemd.h"

struct rmd256_ctx {
	u64 byte_count;
	u32 state[8];
	__le32 buffer[16];
};

#define K1  RMD_K1
#define K2  RMD_K2
#define K3  RMD_K3
#define K4  RMD_K4
#define KK1 RMD_K6
#define KK2 RMD_K7
#define KK3 RMD_K8
#define KK4 RMD_K1

#define F1(x, y, z) (x ^ y ^ z)		/* XOR */
#define F2(x, y, z) (z ^ (x & (y ^ z)))	/* x ? y : z */
#define F3(x, y, z) ((x | ~y) ^ z)
#define F4(x, y, z) (y ^ (z & (x ^ y)))	/* z ? x : y */

#define ROUND(a, b, c, d, f, k, x, s)  { \
	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
	(a) = rol32((a), (s)); \
}

static void rmd256_transform(u32 *state, const __le32 *in)
{
	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd, tmp;

	/* Initialize left lane */
	aa = state[0];
	bb = state[1];
	cc = state[2];
	dd = state[3];

	/* Initialize right lane */
	aaa = state[4];
	bbb = state[5];
	ccc = state[6];
	ddd = state[7];

	/* round 1: left lane */
	ROUND(aa, bb, cc, dd, F1, K1, in[0],  11);
	ROUND(dd, aa, bb, cc, F1, K1, in[1],  14);
	ROUND(cc, dd, aa, bb, F1, K1, in[2],  15);
	ROUND(bb, cc, dd, aa, F1, K1, in[3],  12);
	ROUND(aa, bb, cc, dd, F1, K1, in[4],   5);
	ROUND(dd, aa, bb, cc, F1, K1, in[5],   8);
	ROUND(cc, dd, aa, bb, F1, K1, in[6],   7);
	ROUND(bb, cc, dd, aa, F1, K1, in[7],   9);
	ROUND(aa, bb, cc, dd, F1, K1, in[8],  11);
	ROUND(dd, aa, bb, cc, F1, K1, in[9],  13);
	ROUND(cc, dd, aa, bb, F1, K1, in[10], 14);
	ROUND(bb, cc, dd, aa, F1, K1, in[11], 15);
	ROUND(aa, bb, cc, dd, F1, K1, in[12],  6);
	ROUND(dd, aa, bb, cc, F1, K1, in[13],  7);
	ROUND(cc, dd, aa, bb, F1, K1, in[14],  9);
	ROUND(bb, cc, dd, aa, F1, K1, in[15],  8);

	/* round 1: right lane */
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[5],   8);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[14],  9);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[7],   9);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[0],  11);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[9],  13);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[2],  15);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[11], 15);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[4],   5);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[13],  7);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[6],   7);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[15],  8);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[8],  11);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[1],  14);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[10], 14);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[3],  12);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12],  6);

	/* Swap contents of "a" registers */
	tmp = aa; aa = aaa; aaa = tmp;

	/* round 2: left lane */
	ROUND(aa, bb, cc, dd, F2, K2, in[7],   7);
	ROUND(dd, aa, bb, cc, F2, K2, in[4],   6);
	ROUND(cc, dd, aa, bb, F2, K2, in[13],  8);
	ROUND(bb, cc, dd, aa, F2, K2, in[1],  13);
	ROUND(aa, bb, cc, dd, F2, K2, in[10], 11);
	ROUND(dd, aa, bb, cc, F2, K2, in[6],   9);
	ROUND(cc, dd, aa, bb, F2, K2, in[15],  7);
	ROUND(bb, cc, dd, aa, F2, K2, in[3],  15);
	ROUND(aa, bb, cc, dd, F2, K2, in[12],  7);
	ROUND(dd, aa, bb, cc, F2, K2, in[0],  12);
	ROUND(cc, dd, aa, bb, F2, K2, in[9],  15);
	ROUND(bb, cc, dd, aa, F2, K2, in[5],   9);
	ROUND(aa, bb, cc, dd, F2, K2, in[2],  11);
	ROUND(dd, aa, bb, cc, F2, K2, in[14],  7);
	ROUND(cc, dd, aa, bb, F2, K2, in[11], 13);
	ROUND(bb, cc, dd, aa, F2, K2, in[8],  12);

	/* round 2: right lane */
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[6],   9);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[11], 13);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[3],  15);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[7],   7);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[0],  12);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[13],  8);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[5],   9);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[10], 11);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[14],  7);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[15],  7);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[8],  12);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[12],  7);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[4],   6);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[9],  15);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[1],  13);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2],  11);

	/* Swap contents of "b" registers */
	tmp = bb; bb = bbb; bbb = tmp;

	/* round 3: left lane */
	ROUND(aa, bb, cc, dd, F3, K3, in[3],  11);
	ROUND(dd, aa, bb, cc, F3, K3, in[10], 13);
	ROUND(cc, dd, aa, bb, F3, K3, in[14],  6);
	ROUND(bb, cc, dd, aa, F3, K3, in[4],   7);
	ROUND(aa, bb, cc, dd, F3, K3, in[9],  14);
	ROUND(dd, aa, bb, cc, F3, K3, in[15],  9);
	ROUND(cc, dd, aa, bb, F3, K3, in[8],  13);
	ROUND(bb, cc, dd, aa, F3, K3, in[1],  15);
	ROUND(aa, bb, cc, dd, F3, K3, in[2],  14);
	ROUND(dd, aa, bb, cc, F3, K3, in[7],   8);
	ROUND(cc, dd, aa, bb, F3, K3, in[0],  13);
	ROUND(bb, cc, dd, aa, F3, K3, in[6],   6);
	ROUND(aa, bb, cc, dd, F3, K3, in[13],  5);
	ROUND(dd, aa, bb, cc, F3, K3, in[11], 12);
	ROUND(cc, dd, aa, bb, F3, K3, in[5],   7);
	ROUND(bb, cc, dd, aa, F3, K3, in[12],  5);

	/* round 3: right lane */
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[15],  9);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[5],   7);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[1],  15);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[3],  11);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[7],   8);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[14],  6);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[6],   6);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[9],  14);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[11], 12);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[8],  13);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[12],  5);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[2],  14);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[10], 13);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[0],  13);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[4],   7);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13],  5);

	/* Swap contents of "c" registers */
	tmp = cc; cc = ccc; ccc = tmp;

	/* round 4: left lane */
	ROUND(aa, bb, cc, dd, F4, K4, in[1],  11);
	ROUND(dd, aa, bb, cc, F4, K4, in[9],  12);
	ROUND(cc, dd, aa, bb, F4, K4, in[11], 14);
	ROUND(bb, cc, dd, aa, F4, K4, in[10], 15);
	ROUND(aa, bb, cc, dd, F4, K4, in[0],  14);
	ROUND(dd, aa, bb, cc, F4, K4, in[8],  15);
	ROUND(cc, dd, aa, bb, F4, K4, in[12],  9);
	ROUND(bb, cc, dd, aa, F4, K4, in[4],   8);
	ROUND(aa, bb, cc, dd, F4, K4, in[13],  9);
	ROUND(dd, aa, bb, cc, F4, K4, in[3],  14);
	ROUND(cc, dd, aa, bb, F4, K4, in[7],   5);
	ROUND(bb, cc, dd, aa, F4, K4, in[15],  6);
	ROUND(aa, bb, cc, dd, F4, K4, in[14],  8);
	ROUND(dd, aa, bb, cc, F4, K4, in[5],   6);
	ROUND(cc, dd, aa, bb, F4, K4, in[6],   5);
	ROUND(bb, cc, dd, aa, F4, K4, in[2],  12);

	/* round 4: right lane */
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[8],  15);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[6],   5);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[4],   8);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[1],  11);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[3],  14);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[11], 14);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[15],  6);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[0],  14);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[5],   6);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[12],  9);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[2],  12);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[13],  9);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[9],  12);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[7],   5);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[10], 15);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14],  8);

	/* Swap contents of "d" registers */
	tmp = dd; dd = ddd; ddd = tmp;

	/* combine results */
	state[0] += aa;
	state[1] += bb;
	state[2] += cc;
	state[3] += dd;
	state[4] += aaa;
	state[5] += bbb;
	state[6] += ccc;
	state[7] += ddd;

	return;
}

static int rmd256_init(struct shash_desc *desc)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);

	rctx->byte_count = 0;

	rctx->state[0] = RMD_H0;
	rctx->state[1] = RMD_H1;
	rctx->state[2] = RMD_H2;
	rctx->state[3] = RMD_H3;
	rctx->state[4] = RMD_H5;
	rctx->state[5] = RMD_H6;
	rctx->state[6] = RMD_H7;
	rctx->state[7] = RMD_H8;

	memset(rctx->buffer, 0, sizeof(rctx->buffer));

	return 0;
}

static int rmd256_update(struct shash_desc *desc, const u8 *data,
			 unsigned int len)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);

	rctx->byte_count += len;

	/* Enough space in buffer? If so copy and we're done */
	if (avail > len) {
		memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
		       data, len);
		goto out;
	}

	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
	       data, avail);

	rmd256_transform(rctx->state, rctx->buffer);
	data += avail;
	len -= avail;

	while (len >= sizeof(rctx->buffer)) {
		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
		rmd256_transform(rctx->state, rctx->buffer);
		data += sizeof(rctx->buffer);
		len -= sizeof(rctx->buffer);
	}

	memcpy(rctx->buffer, data, len);

out:
	return 0;
}

/* Add padding and return the message digest. */
static int rmd256_final(struct shash_desc *desc, u8 *out)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
	u32 i, index, padlen;
	__le64 bits;
	__le32 *dst = (__le32 *)out;
	static const u8 padding[64] = { 0x80, };

	bits = cpu_to_le64(rctx->byte_count << 3);

	/* Pad out to 56 mod 64 */
	index = rctx->byte_count & 0x3f;
	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
	rmd256_update(desc, padding, padlen);

	/* Append length */
	rmd256_update(desc, (const u8 *)&bits, sizeof(bits));

	/* Store state in digest */
	for (i = 0; i < 8; i++)
		dst[i] = cpu_to_le32p(&rctx->state[i]);

	/* Wipe context */
	memset(rctx, 0, sizeof(*rctx));

	return 0;
}

static struct shash_alg alg = {
	.digestsize	=	RMD256_DIGEST_SIZE,
	.init		=	rmd256_init,
	.update		=	rmd256_update,
	.final		=	rmd256_final,
	.descsize	=	sizeof(struct rmd256_ctx),
	.base		=	{
		.cra_name	 =	"rmd256",
		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	 =	RMD256_BLOCK_SIZE,
		.cra_module	 =	THIS_MODULE,
	}
};

static int __init rmd256_mod_init(void)
{
	return crypto_register_shash(&alg);
}

static void __exit rmd256_mod_fini(void)
{
	crypto_unregister_shash(&alg);
}

module_init(rmd256_mod_init);
module_exit(rmd256_mod_fini);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
MODULE_ALIAS_CRYPTO("rmd256");
back to top