Revision 732256b9335f8456623bb772d86c2a24e3cafca2 authored by Erik Hugne on 07 January 2014, 20:51:36 UTC, committed by David S. Miller on 07 January 2014, 21:15:24 UTC
When we pull a received packet from a link's 'deferred packets' queue
for processing, its 'next' pointer is not cleared, and still refers to
the next packet in that queue, if any. This is incorrect, but caused
no harm before commit 40ba3cdf542a469aaa9083fa041656e59b109b90 ("tipc:
message reassembly using fragment chain") was introduced. After that
commit, it may sometimes lead to the following oops:

general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
Modules linked in: tipc
CPU: 4 PID: 0 Comm: swapper/4 Tainted: G        W 3.13.0-rc2+ #6
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
task: ffff880017af4880 ti: ffff880017aee000 task.ti: ffff880017aee000
RIP: 0010:[<ffffffff81710694>]  [<ffffffff81710694>] skb_try_coalesce+0x44/0x3d0
RSP: 0018:ffff880016603a78  EFLAGS: 00010212
RAX: 6b6b6b6bd6d6d6d6 RBX: ffff880013106ac0 RCX: ffff880016603ad0
RDX: ffff880016603ad7 RSI: ffff88001223ed00 RDI: ffff880013106ac0
RBP: ffff880016603ab8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88001223ed00
R13: ffff880016603ad0 R14: 000000000000058c R15: ffff880012297650
FS:  0000000000000000(0000) GS:ffff880016600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 000000000805b000 CR3: 0000000011f5d000 CR4: 00000000000006e0
Stack:
 ffff880016603a88 ffffffff810a38ed ffff880016603aa8 ffff88001223ed00
 0000000000000001 ffff880012297648 ffff880016603b68 ffff880012297650
 ffff880016603b08 ffffffffa0006c51 ffff880016603b08 00ffffffa00005fc
Call Trace:
 <IRQ>
 [<ffffffff810a38ed>] ? trace_hardirqs_on+0xd/0x10
 [<ffffffffa0006c51>] tipc_link_recv_fragment+0xd1/0x1b0 [tipc]
 [<ffffffffa0007214>] tipc_recv_msg+0x4e4/0x920 [tipc]
 [<ffffffffa00016f0>] ? tipc_l2_rcv_msg+0x40/0x250 [tipc]
 [<ffffffffa000177c>] tipc_l2_rcv_msg+0xcc/0x250 [tipc]
 [<ffffffffa00016f0>] ? tipc_l2_rcv_msg+0x40/0x250 [tipc]
 [<ffffffff8171e65b>] __netif_receive_skb_core+0x80b/0xd00
 [<ffffffff8171df94>] ? __netif_receive_skb_core+0x144/0xd00
 [<ffffffff8171eb76>] __netif_receive_skb+0x26/0x70
 [<ffffffff8171ed6d>] netif_receive_skb+0x2d/0x200
 [<ffffffff8171fe70>] napi_gro_receive+0xb0/0x130
 [<ffffffff815647c2>] e1000_clean_rx_irq+0x2c2/0x530
 [<ffffffff81565986>] e1000_clean+0x266/0x9c0
 [<ffffffff81985f7b>] ? notifier_call_chain+0x2b/0x160
 [<ffffffff8171f971>] net_rx_action+0x141/0x310
 [<ffffffff81051c1b>] __do_softirq+0xeb/0x480
 [<ffffffff819817bb>] ? _raw_spin_unlock+0x2b/0x40
 [<ffffffff810b8c42>] ? handle_fasteoi_irq+0x72/0x100
 [<ffffffff81052346>] irq_exit+0x96/0xc0
 [<ffffffff8198cbc3>] do_IRQ+0x63/0xe0
 [<ffffffff81981def>] common_interrupt+0x6f/0x6f
 <EOI>

This happens when the last fragment of a message has passed through the
the receiving link's 'deferred packets' queue, and at least one other
packet was added to that queue while it was there. After the fragment
chain with the complete message has been successfully delivered to the
receiving socket, it is released. Since 'next' pointer of the last
fragment in the released chain now is non-NULL, we get the crash shown
above.

We fix this by clearing the 'next' pointer of all received packets,
including those being pulled from the 'deferred' queue, before they
undergo any further processing.

Fixes: 40ba3cdf542a4 ("tipc: message reassembly using fragment chain")
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reported-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 657e5d1
Raw File
deflate.c
/*
 * Cryptographic API.
 *
 * Deflate algorithm (RFC 1951), implemented here primarily for use
 * by IPCOMP (RFC 3173 & RFC 2394).
 *
 * 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.
 *
 * The default winbits of 11 should suit most packets, and it may be something
 * to configure on a per-tfm basis in the future.
 *
 * Currently, compression history is not maintained between tfm calls, as
 * it is not needed for IPCOMP and keeps the code simpler.  It can be
 * implemented if someone wants it.
 */
#include <linux/init.h>
#include <linux/module.h>
#include <linux/crypto.h>
#include <linux/zlib.h>
#include <linux/vmalloc.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/net.h>

#define DEFLATE_DEF_LEVEL		Z_DEFAULT_COMPRESSION
#define DEFLATE_DEF_WINBITS		11
#define DEFLATE_DEF_MEMLEVEL		MAX_MEM_LEVEL

struct deflate_ctx {
	struct z_stream_s comp_stream;
	struct z_stream_s decomp_stream;
};

static int deflate_comp_init(struct deflate_ctx *ctx)
{
	int ret = 0;
	struct z_stream_s *stream = &ctx->comp_stream;

	stream->workspace = vzalloc(zlib_deflate_workspacesize(
				-DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL));
	if (!stream->workspace) {
		ret = -ENOMEM;
		goto out;
	}
	ret = zlib_deflateInit2(stream, DEFLATE_DEF_LEVEL, Z_DEFLATED,
	                        -DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL,
	                        Z_DEFAULT_STRATEGY);
	if (ret != Z_OK) {
		ret = -EINVAL;
		goto out_free;
	}
out:
	return ret;
out_free:
	vfree(stream->workspace);
	goto out;
}

static int deflate_decomp_init(struct deflate_ctx *ctx)
{
	int ret = 0;
	struct z_stream_s *stream = &ctx->decomp_stream;

	stream->workspace = vzalloc(zlib_inflate_workspacesize());
	if (!stream->workspace) {
		ret = -ENOMEM;
		goto out;
	}
	ret = zlib_inflateInit2(stream, -DEFLATE_DEF_WINBITS);
	if (ret != Z_OK) {
		ret = -EINVAL;
		goto out_free;
	}
out:
	return ret;
out_free:
	vfree(stream->workspace);
	goto out;
}

static void deflate_comp_exit(struct deflate_ctx *ctx)
{
	zlib_deflateEnd(&ctx->comp_stream);
	vfree(ctx->comp_stream.workspace);
}

static void deflate_decomp_exit(struct deflate_ctx *ctx)
{
	zlib_inflateEnd(&ctx->decomp_stream);
	vfree(ctx->decomp_stream.workspace);
}

static int deflate_init(struct crypto_tfm *tfm)
{
	struct deflate_ctx *ctx = crypto_tfm_ctx(tfm);
	int ret;

	ret = deflate_comp_init(ctx);
	if (ret)
		goto out;
	ret = deflate_decomp_init(ctx);
	if (ret)
		deflate_comp_exit(ctx);
out:
	return ret;
}

static void deflate_exit(struct crypto_tfm *tfm)
{
	struct deflate_ctx *ctx = crypto_tfm_ctx(tfm);

	deflate_comp_exit(ctx);
	deflate_decomp_exit(ctx);
}

static int deflate_compress(struct crypto_tfm *tfm, const u8 *src,
			    unsigned int slen, u8 *dst, unsigned int *dlen)
{
	int ret = 0;
	struct deflate_ctx *dctx = crypto_tfm_ctx(tfm);
	struct z_stream_s *stream = &dctx->comp_stream;

	ret = zlib_deflateReset(stream);
	if (ret != Z_OK) {
		ret = -EINVAL;
		goto out;
	}

	stream->next_in = (u8 *)src;
	stream->avail_in = slen;
	stream->next_out = (u8 *)dst;
	stream->avail_out = *dlen;

	ret = zlib_deflate(stream, Z_FINISH);
	if (ret != Z_STREAM_END) {
		ret = -EINVAL;
		goto out;
	}
	ret = 0;
	*dlen = stream->total_out;
out:
	return ret;
}

static int deflate_decompress(struct crypto_tfm *tfm, const u8 *src,
			      unsigned int slen, u8 *dst, unsigned int *dlen)
{

	int ret = 0;
	struct deflate_ctx *dctx = crypto_tfm_ctx(tfm);
	struct z_stream_s *stream = &dctx->decomp_stream;

	ret = zlib_inflateReset(stream);
	if (ret != Z_OK) {
		ret = -EINVAL;
		goto out;
	}

	stream->next_in = (u8 *)src;
	stream->avail_in = slen;
	stream->next_out = (u8 *)dst;
	stream->avail_out = *dlen;

	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) {
		u8 zerostuff = 0;
		stream->next_in = &zerostuff;
		stream->avail_in = 1;
		ret = zlib_inflate(stream, Z_FINISH);
	}
	if (ret != Z_STREAM_END) {
		ret = -EINVAL;
		goto out;
	}
	ret = 0;
	*dlen = stream->total_out;
out:
	return ret;
}

static struct crypto_alg alg = {
	.cra_name		= "deflate",
	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
	.cra_ctxsize		= sizeof(struct deflate_ctx),
	.cra_module		= THIS_MODULE,
	.cra_init		= deflate_init,
	.cra_exit		= deflate_exit,
	.cra_u			= { .compress = {
	.coa_compress 		= deflate_compress,
	.coa_decompress  	= deflate_decompress } }
};

static int __init deflate_mod_init(void)
{
	return crypto_register_alg(&alg);
}

static void __exit deflate_mod_fini(void)
{
	crypto_unregister_alg(&alg);
}

module_init(deflate_mod_init);
module_exit(deflate_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");

back to top