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
zlib.c
/*
 * Cryptographic API.
 *
 * Zlib algorithm
 *
 * Copyright 2008 Sony Corporation
 *
 * Based on deflate.c, which is
 * Copyright (c) 2003 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.
 *
 * FIXME: deflate transforms will require up to a total of about 436k of kernel
 * memory on i386 (390k for compression, the rest for decompression), as the
 * current zlib kernel code uses a worst case pre-allocation system by default.
 * This needs to be fixed so that the amount of memory required is properly
 * related to the winbits and memlevel parameters.
 */

#define pr_fmt(fmt)	"%s: " fmt, __func__

#include <linux/init.h>
#include <linux/module.h>
#include <linux/zlib.h>
#include <linux/vmalloc.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/net.h>

#include <crypto/internal/compress.h>

#include <net/netlink.h>


struct zlib_ctx {
	struct z_stream_s comp_stream;
	struct z_stream_s decomp_stream;
	int decomp_windowBits;
};


static void zlib_comp_exit(struct zlib_ctx *ctx)
{
	struct z_stream_s *stream = &ctx->comp_stream;

	if (stream->workspace) {
		zlib_deflateEnd(stream);
		vfree(stream->workspace);
		stream->workspace = NULL;
	}
}

static void zlib_decomp_exit(struct zlib_ctx *ctx)
{
	struct z_stream_s *stream = &ctx->decomp_stream;

	if (stream->workspace) {
		zlib_inflateEnd(stream);
		vfree(stream->workspace);
		stream->workspace = NULL;
	}
}

static int zlib_init(struct crypto_tfm *tfm)
{
	return 0;
}

static void zlib_exit(struct crypto_tfm *tfm)
{
	struct zlib_ctx *ctx = crypto_tfm_ctx(tfm);

	zlib_comp_exit(ctx);
	zlib_decomp_exit(ctx);
}


static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params,
			       unsigned int len)
{
	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &ctx->comp_stream;
	struct nlattr *tb[ZLIB_COMP_MAX + 1];
	int window_bits, mem_level;
	size_t workspacesize;
	int ret;

	ret = nla_parse(tb, ZLIB_COMP_MAX, params, len, NULL);
	if (ret)
		return ret;

	zlib_comp_exit(ctx);

	window_bits = tb[ZLIB_COMP_WINDOWBITS]
					? nla_get_u32(tb[ZLIB_COMP_WINDOWBITS])
					: MAX_WBITS;
	mem_level = tb[ZLIB_COMP_MEMLEVEL]
					? nla_get_u32(tb[ZLIB_COMP_MEMLEVEL])
					: DEF_MEM_LEVEL;

	workspacesize = zlib_deflate_workspacesize(window_bits, mem_level);
	stream->workspace = vzalloc(workspacesize);
	if (!stream->workspace)
		return -ENOMEM;

	ret = zlib_deflateInit2(stream,
				tb[ZLIB_COMP_LEVEL]
					? nla_get_u32(tb[ZLIB_COMP_LEVEL])
					: Z_DEFAULT_COMPRESSION,
				tb[ZLIB_COMP_METHOD]
					? nla_get_u32(tb[ZLIB_COMP_METHOD])
					: Z_DEFLATED,
				window_bits,
				mem_level,
				tb[ZLIB_COMP_STRATEGY]
					? nla_get_u32(tb[ZLIB_COMP_STRATEGY])
					: Z_DEFAULT_STRATEGY);
	if (ret != Z_OK) {
		vfree(stream->workspace);
		stream->workspace = NULL;
		return -EINVAL;
	}

	return 0;
}

static int zlib_compress_init(struct crypto_pcomp *tfm)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->comp_stream;

	ret = zlib_deflateReset(stream);
	if (ret != Z_OK)
		return -EINVAL;

	return 0;
}

static int zlib_compress_update(struct crypto_pcomp *tfm,
				struct comp_request *req)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->comp_stream;

	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
	stream->next_in = req->next_in;
	stream->avail_in = req->avail_in;
	stream->next_out = req->next_out;
	stream->avail_out = req->avail_out;

	ret = zlib_deflate(stream, Z_NO_FLUSH);
	switch (ret) {
	case Z_OK:
		break;

	case Z_BUF_ERROR:
		pr_debug("zlib_deflate could not make progress\n");
		return -EAGAIN;

	default:
		pr_debug("zlib_deflate failed %d\n", ret);
		return -EINVAL;
	}

	ret = req->avail_out - stream->avail_out;
	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
		 stream->avail_in, stream->avail_out,
		 req->avail_in - stream->avail_in, ret);
	req->next_in = stream->next_in;
	req->avail_in = stream->avail_in;
	req->next_out = stream->next_out;
	req->avail_out = stream->avail_out;
	return ret;
}

static int zlib_compress_final(struct crypto_pcomp *tfm,
			       struct comp_request *req)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->comp_stream;

	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
	stream->next_in = req->next_in;
	stream->avail_in = req->avail_in;
	stream->next_out = req->next_out;
	stream->avail_out = req->avail_out;

	ret = zlib_deflate(stream, Z_FINISH);
	if (ret != Z_STREAM_END) {
		pr_debug("zlib_deflate failed %d\n", ret);
		return -EINVAL;
	}

	ret = req->avail_out - stream->avail_out;
	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
		 stream->avail_in, stream->avail_out,
		 req->avail_in - stream->avail_in, ret);
	req->next_in = stream->next_in;
	req->avail_in = stream->avail_in;
	req->next_out = stream->next_out;
	req->avail_out = stream->avail_out;
	return ret;
}


static int zlib_decompress_setup(struct crypto_pcomp *tfm, void *params,
				 unsigned int len)
{
	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &ctx->decomp_stream;
	struct nlattr *tb[ZLIB_DECOMP_MAX + 1];
	int ret = 0;

	ret = nla_parse(tb, ZLIB_DECOMP_MAX, params, len, NULL);
	if (ret)
		return ret;

	zlib_decomp_exit(ctx);

	ctx->decomp_windowBits = tb[ZLIB_DECOMP_WINDOWBITS]
				 ? nla_get_u32(tb[ZLIB_DECOMP_WINDOWBITS])
				 : DEF_WBITS;

	stream->workspace = vzalloc(zlib_inflate_workspacesize());
	if (!stream->workspace)
		return -ENOMEM;

	ret = zlib_inflateInit2(stream, ctx->decomp_windowBits);
	if (ret != Z_OK) {
		vfree(stream->workspace);
		stream->workspace = NULL;
		return -EINVAL;
	}

	return 0;
}

static int zlib_decompress_init(struct crypto_pcomp *tfm)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->decomp_stream;

	ret = zlib_inflateReset(stream);
	if (ret != Z_OK)
		return -EINVAL;

	return 0;
}

static int zlib_decompress_update(struct crypto_pcomp *tfm,
				  struct comp_request *req)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->decomp_stream;

	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
	stream->next_in = req->next_in;
	stream->avail_in = req->avail_in;
	stream->next_out = req->next_out;
	stream->avail_out = req->avail_out;

	ret = zlib_inflate(stream, Z_SYNC_FLUSH);
	switch (ret) {
	case Z_OK:
	case Z_STREAM_END:
		break;

	case Z_BUF_ERROR:
		pr_debug("zlib_inflate could not make progress\n");
		return -EAGAIN;

	default:
		pr_debug("zlib_inflate failed %d\n", ret);
		return -EINVAL;
	}

	ret = req->avail_out - stream->avail_out;
	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
		 stream->avail_in, stream->avail_out,
		 req->avail_in - stream->avail_in, ret);
	req->next_in = stream->next_in;
	req->avail_in = stream->avail_in;
	req->next_out = stream->next_out;
	req->avail_out = stream->avail_out;
	return ret;
}

static int zlib_decompress_final(struct crypto_pcomp *tfm,
				 struct comp_request *req)
{
	int ret;
	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
	struct z_stream_s *stream = &dctx->decomp_stream;

	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
	stream->next_in = req->next_in;
	stream->avail_in = req->avail_in;
	stream->next_out = req->next_out;
	stream->avail_out = req->avail_out;

	if (dctx->decomp_windowBits < 0) {
		ret = zlib_inflate(stream, Z_SYNC_FLUSH);
		/*
		 * Work around a bug in zlib, which sometimes wants to taste an
		 * extra byte when being used in the (undocumented) raw deflate
		 * mode. (From USAGI).
		 */
		if (ret == Z_OK && !stream->avail_in && stream->avail_out) {
			const void *saved_next_in = stream->next_in;
			u8 zerostuff = 0;

			stream->next_in = &zerostuff;
			stream->avail_in = 1;
			ret = zlib_inflate(stream, Z_FINISH);
			stream->next_in = saved_next_in;
			stream->avail_in = 0;
		}
	} else
		ret = zlib_inflate(stream, Z_FINISH);
	if (ret != Z_STREAM_END) {
		pr_debug("zlib_inflate failed %d\n", ret);
		return -EINVAL;
	}

	ret = req->avail_out - stream->avail_out;
	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
		 stream->avail_in, stream->avail_out,
		 req->avail_in - stream->avail_in, ret);
	req->next_in = stream->next_in;
	req->avail_in = stream->avail_in;
	req->next_out = stream->next_out;
	req->avail_out = stream->avail_out;
	return ret;
}


static struct pcomp_alg zlib_alg = {
	.compress_setup		= zlib_compress_setup,
	.compress_init		= zlib_compress_init,
	.compress_update	= zlib_compress_update,
	.compress_final		= zlib_compress_final,
	.decompress_setup	= zlib_decompress_setup,
	.decompress_init	= zlib_decompress_init,
	.decompress_update	= zlib_decompress_update,
	.decompress_final	= zlib_decompress_final,

	.base			= {
		.cra_name	= "zlib",
		.cra_flags	= CRYPTO_ALG_TYPE_PCOMPRESS,
		.cra_ctxsize	= sizeof(struct zlib_ctx),
		.cra_module	= THIS_MODULE,
		.cra_init	= zlib_init,
		.cra_exit	= zlib_exit,
	}
};

static int __init zlib_mod_init(void)
{
	return crypto_register_pcomp(&zlib_alg);
}

static void __exit zlib_mod_fini(void)
{
	crypto_unregister_pcomp(&zlib_alg);
}

module_init(zlib_mod_init);
module_exit(zlib_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Zlib Compression Algorithm");
MODULE_AUTHOR("Sony Corporation");
MODULE_ALIAS_CRYPTO("zlib");
back to top