Revision 12d94a804946af291e24b80fc53ec86264765781 authored by Eric Dumazet on 15 August 2017, 11:09:51 UTC, committed by David S. Miller on 16 August 2017, 00:06:34 UTC
Based on a syzkaller report [1], I found that a per cpu allocation
failure in snmp6_alloc_dev() would then lead to NULL dereference in
ip6_route_dev_notify().

It seems this is a very old bug, thus no Fixes tag in this submission.

Let's add in6_dev_put_clear() helper, as we will probably use
it elsewhere (once available/present in net-next)

[1]
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 17294 Comm: syz-executor6 Not tainted 4.13.0-rc2+ #10
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff88019f456680 task.stack: ffff8801c6e58000
RIP: 0010:__read_once_size include/linux/compiler.h:250 [inline]
RIP: 0010:atomic_read arch/x86/include/asm/atomic.h:26 [inline]
RIP: 0010:refcount_sub_and_test+0x7d/0x1b0 lib/refcount.c:178
RSP: 0018:ffff8801c6e5f1b0 EFLAGS: 00010202
RAX: 0000000000000037 RBX: dffffc0000000000 RCX: ffffc90005d25000
RDX: ffff8801c6e5f218 RSI: ffffffff82342bbf RDI: 0000000000000001
RBP: ffff8801c6e5f240 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 1ffff10038dcbe37
R13: 0000000000000006 R14: 0000000000000001 R15: 00000000000001b8
FS:  00007f21e0429700(0000) GS:ffff8801dc100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001ddbc22000 CR3: 00000001d632b000 CR4: 00000000001426e0
DR0: 0000000020000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
Call Trace:
 refcount_dec_and_test+0x1a/0x20 lib/refcount.c:211
 in6_dev_put include/net/addrconf.h:335 [inline]
 ip6_route_dev_notify+0x1c9/0x4a0 net/ipv6/route.c:3732
 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x51/0x90 net/core/dev.c:1678
 call_netdevice_notifiers net/core/dev.c:1694 [inline]
 rollback_registered_many+0x91c/0xe80 net/core/dev.c:7107
 rollback_registered+0x1be/0x3c0 net/core/dev.c:7149
 register_netdevice+0xbcd/0xee0 net/core/dev.c:7587
 register_netdev+0x1a/0x30 net/core/dev.c:7669
 loopback_net_init+0x76/0x160 drivers/net/loopback.c:214
 ops_init+0x10a/0x570 net/core/net_namespace.c:118
 setup_net+0x313/0x710 net/core/net_namespace.c:294
 copy_net_ns+0x27c/0x580 net/core/net_namespace.c:418
 create_new_namespaces+0x425/0x880 kernel/nsproxy.c:107
 unshare_nsproxy_namespaces+0xae/0x1e0 kernel/nsproxy.c:206
 SYSC_unshare kernel/fork.c:2347 [inline]
 SyS_unshare+0x653/0xfa0 kernel/fork.c:2297
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512c9
RSP: 002b:00007f21e0428c08 EFLAGS: 00000216 ORIG_RAX: 0000000000000110
RAX: ffffffffffffffda RBX: 0000000000718150 RCX: 00000000004512c9
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000062020200
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004b973d
R13: 00000000ffffffff R14: 000000002001d000 R15: 00000000000002dd
Code: 50 2b 34 82 c7 00 f1 f1 f1 f1 c7 40 04 04 f2 f2 f2 c7 40 08 f3 f3
f3 f3 e8 a1 43 39 ff 4c 89 f8 48 8b 95 70 ff ff ff 48 c1 e8 03 <0f> b6
0c 18 4c 89 f8 83 e0 07 83 c0 03 38 c8 7c 08 84 c9 0f 85
RIP: __read_once_size include/linux/compiler.h:250 [inline] RSP:
ffff8801c6e5f1b0
RIP: atomic_read arch/x86/include/asm/atomic.h:26 [inline] RSP:
ffff8801c6e5f1b0
RIP: refcount_sub_and_test+0x7d/0x1b0 lib/refcount.c:178 RSP:
ffff8801c6e5f1b0
---[ end trace e441d046c6410d31 ]---

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 0a6f041
Raw File
esp6_offload.c
/*
 * IPV6 GSO/GRO offload support
 * Linux INET implementation
 *
 * Copyright (C) 2016 secunet Security Networks AG
 * Author: Steffen Klassert <steffen.klassert@secunet.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * ESP GRO support
 */

#include <linux/skbuff.h>
#include <linux/init.h>
#include <net/protocol.h>
#include <crypto/aead.h>
#include <crypto/authenc.h>
#include <linux/err.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
#include <linux/scatterlist.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/ip6_route.h>
#include <net/ipv6.h>
#include <linux/icmpv6.h>

static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen)
{
	int off = sizeof(struct ipv6hdr);
	struct ipv6_opt_hdr *exthdr;

	if (likely(ipv6_hdr->nexthdr == NEXTHDR_ESP))
		return offsetof(struct ipv6hdr, nexthdr);

	while (off < nhlen) {
		exthdr = (void *)ipv6_hdr + off;
		if (exthdr->nexthdr == NEXTHDR_ESP)
			return off;

		off += ipv6_optlen(exthdr);
	}

	return 0;
}

static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
					 struct sk_buff *skb)
{
	int offset = skb_gro_offset(skb);
	struct xfrm_offload *xo;
	struct xfrm_state *x;
	__be32 seq;
	__be32 spi;
	int nhoff;
	int err;

	skb_pull(skb, offset);

	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
		goto out;

	xo = xfrm_offload(skb);
	if (!xo || !(xo->flags & CRYPTO_DONE)) {
		err = secpath_set(skb);
		if (err)
			goto out;

		if (skb->sp->len == XFRM_MAX_DEPTH)
			goto out;

		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
				      spi, IPPROTO_ESP, AF_INET6);
		if (!x)
			goto out;

		skb->sp->xvec[skb->sp->len++] = x;
		skb->sp->olen++;

		xo = xfrm_offload(skb);
		if (!xo) {
			xfrm_state_put(x);
			goto out;
		}
	}

	xo->flags |= XFRM_GRO;

	nhoff = esp6_nexthdr_esp_offset(ipv6_hdr(skb), offset);
	if (!nhoff)
		goto out;

	IP6CB(skb)->nhoff = nhoff;
	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
	XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
	XFRM_SPI_SKB_CB(skb)->seq = seq;

	/* We don't need to handle errors from xfrm_input, it does all
	 * the error handling and frees the resources on error. */
	xfrm_input(skb, IPPROTO_ESP, spi, -2);

	return ERR_PTR(-EINPROGRESS);
out:
	skb_push(skb, offset);
	NAPI_GRO_CB(skb)->same_flow = 0;
	NAPI_GRO_CB(skb)->flush = 1;

	return NULL;
}

static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
{
	struct ip_esp_hdr *esph;
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct xfrm_offload *xo = xfrm_offload(skb);
	int proto = iph->nexthdr;

	skb_push(skb, -skb_network_offset(skb));
	esph = ip_esp_hdr(skb);
	*skb_mac_header(skb) = IPPROTO_ESP;

	esph->spi = x->id.spi;
	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);

	xo->proto = proto;
}

static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
				        netdev_features_t features)
{
	__u32 seq;
	int err = 0;
	struct sk_buff *skb2;
	struct xfrm_state *x;
	struct ip_esp_hdr *esph;
	struct crypto_aead *aead;
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	netdev_features_t esp_features = features;
	struct xfrm_offload *xo = xfrm_offload(skb);

	if (!xo)
		goto out;

	seq = xo->seq.low;

	x = skb->sp->xvec[skb->sp->len - 1];
	aead = x->data;
	esph = ip_esp_hdr(skb);

	if (esph->spi != x->id.spi)
		goto out;

	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
		goto out;

	__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));

	skb->encap_hdr_csum = 1;

	if (!(features & NETIF_F_HW_ESP))
		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);

	segs = x->outer_mode->gso_segment(x, skb, esp_features);
	if (IS_ERR_OR_NULL(segs))
		goto out;

	__skb_pull(skb, skb->data - skb_mac_header(skb));

	skb2 = segs;
	do {
		struct sk_buff *nskb = skb2->next;

		xo = xfrm_offload(skb2);
		xo->flags |= XFRM_GSO_SEGMENT;
		xo->seq.low = seq;
		xo->seq.hi = xfrm_replay_seqhi(x, seq);

		if(!(features & NETIF_F_HW_ESP))
			xo->flags |= CRYPTO_FALLBACK;

		x->outer_mode->xmit(x, skb2);

		err = x->type_offload->xmit(x, skb2, esp_features);
		if (err) {
			kfree_skb_list(segs);
			return ERR_PTR(err);
		}

		if (!skb_is_gso(skb2))
			seq++;
		else
			seq += skb_shinfo(skb2)->gso_segs;

		skb_push(skb2, skb2->mac_len);
		skb2 = nskb;
	} while (skb2);

out:
	return segs;
}

static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb)
{
	struct crypto_aead *aead = x->data;

	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
		return -EINVAL;

	skb->ip_summed = CHECKSUM_NONE;

	return esp6_input_done2(skb, 0);
}

static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_t features)
{
	int err;
	int alen;
	int blksize;
	struct xfrm_offload *xo;
	struct ip_esp_hdr *esph;
	struct crypto_aead *aead;
	struct esp_info esp;
	bool hw_offload = true;

	esp.inplace = true;

	xo = xfrm_offload(skb);

	if (!xo)
		return -EINVAL;

	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
	    (x->xso.dev != skb->dev)) {
		xo->flags |= CRYPTO_FALLBACK;
		hw_offload = false;
	}

	esp.proto = xo->proto;

	/* skb is pure payload to encrypt */

	aead = x->data;
	alen = crypto_aead_authsize(aead);

	esp.tfclen = 0;
	/* XXX: Add support for tfc padding here. */

	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
	esp.plen = esp.clen - skb->len - esp.tfclen;
	esp.tailen = esp.tfclen + esp.plen + alen;

	if (!hw_offload || (hw_offload && !skb_is_gso(skb))) {
		esp.nfrags = esp6_output_head(x, skb, &esp);
		if (esp.nfrags < 0)
			return esp.nfrags;
	}

	esph = ip_esp_hdr(skb);
	esph->spi = x->id.spi;

	skb_push(skb, -skb_network_offset(skb));

	if (xo->flags & XFRM_GSO_SEGMENT) {
		esph->seq_no = htonl(xo->seq.low);
	} else {
		int len;

		len = skb->len - sizeof(struct ipv6hdr);
		if (len > IPV6_MAXPLEN)
			len = 0;

		ipv6_hdr(skb)->payload_len = htons(len);
	}

	if (hw_offload)
		return 0;

	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));

	err = esp6_output_tail(x, skb, &esp);
	if (err < 0)
		return err;

	secpath_reset(skb);

	return 0;
}

static const struct net_offload esp6_offload = {
	.callbacks = {
		.gro_receive = esp6_gro_receive,
		.gso_segment = esp6_gso_segment,
	},
};

static const struct xfrm_type_offload esp6_type_offload = {
	.description	= "ESP6 OFFLOAD",
	.owner		= THIS_MODULE,
	.proto	     	= IPPROTO_ESP,
	.input_tail	= esp6_input_tail,
	.xmit		= esp6_xmit,
	.encap		= esp6_gso_encap,
};

static int __init esp6_offload_init(void)
{
	if (xfrm_register_type_offload(&esp6_type_offload, AF_INET6) < 0) {
		pr_info("%s: can't add xfrm type offload\n", __func__);
		return -EAGAIN;
	}

	return inet6_add_offload(&esp6_offload, IPPROTO_ESP);
}

static void __exit esp6_offload_exit(void)
{
	if (xfrm_unregister_type_offload(&esp6_type_offload, AF_INET6) < 0)
		pr_info("%s: can't remove xfrm type offload\n", __func__);

	inet6_del_offload(&esp6_offload, IPPROTO_ESP);
}

module_init(esp6_offload_init);
module_exit(esp6_offload_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
back to top