linux/include/net/dst.h
Martin Varghese 394de110a7 net: Added pointer check for dst->ops->neigh_lookup in dst_neigh_lookup_skb
The packets from tunnel devices (eg bareudp) may have only
metadata in the dst pointer of skb. Hence a pointer check of
neigh_lookup is needed in dst_neigh_lookup_skb

Kernel crashes when packets from bareudp device is processed in
the kernel neighbour subsytem.

[  133.384484] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  133.385240] #PF: supervisor instruction fetch in kernel mode
[  133.385828] #PF: error_code(0x0010) - not-present page
[  133.386603] PGD 0 P4D 0
[  133.386875] Oops: 0010 [#1] SMP PTI
[  133.387275] CPU: 0 PID: 5045 Comm: ping Tainted: G        W         5.8.0-rc2+ #15
[  133.388052] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[  133.391076] RIP: 0010:0x0
[  133.392401] Code: Bad RIP value.
[  133.394029] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.396656] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.399018] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.399685] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.400350] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.401010] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.401667] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.402412] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.402948] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.403611] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.404270] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.404933] Call Trace:
[  133.405169]  <IRQ>
[  133.405367]  __neigh_update+0x5a4/0x8f0
[  133.405734]  arp_process+0x294/0x820
[  133.406076]  ? __netif_receive_skb_core+0x866/0xe70
[  133.406557]  arp_rcv+0x129/0x1c0
[  133.406882]  __netif_receive_skb_one_core+0x95/0xb0
[  133.407340]  process_backlog+0xa7/0x150
[  133.407705]  net_rx_action+0x2af/0x420
[  133.408457]  __do_softirq+0xda/0x2a8
[  133.408813]  asm_call_on_stack+0x12/0x20
[  133.409290]  </IRQ>
[  133.409519]  do_softirq_own_stack+0x39/0x50
[  133.410036]  do_softirq+0x50/0x60
[  133.410401]  __local_bh_enable_ip+0x50/0x60
[  133.410871]  ip_finish_output2+0x195/0x530
[  133.411288]  ip_output+0x72/0xf0
[  133.411673]  ? __ip_finish_output+0x1f0/0x1f0
[  133.412122]  ip_send_skb+0x15/0x40
[  133.412471]  raw_sendmsg+0x853/0xab0
[  133.412855]  ? insert_pfn+0xfe/0x270
[  133.413827]  ? vvar_fault+0xec/0x190
[  133.414772]  sock_sendmsg+0x57/0x80
[  133.415685]  __sys_sendto+0xdc/0x160
[  133.416605]  ? syscall_trace_enter+0x1d4/0x2b0
[  133.417679]  ? __audit_syscall_exit+0x1d9/0x280
[  133.418753]  ? __prepare_exit_to_usermode+0x5d/0x1a0
[  133.419819]  __x64_sys_sendto+0x24/0x30
[  133.420848]  do_syscall_64+0x4d/0x90
[  133.421768]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  133.422833] RIP: 0033:0x7fe013689c03
[  133.423749] Code: Bad RIP value.
[  133.424624] RSP: 002b:00007ffc7288f418 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[  133.425940] RAX: ffffffffffffffda RBX: 000056151fc63720 RCX: 00007fe013689c03
[  133.427225] RDX: 0000000000000040 RSI: 000056151fc63720 RDI: 0000000000000003
[  133.428481] RBP: 00007ffc72890b30 R08: 000056151fc60500 R09: 0000000000000010
[  133.429757] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
[  133.431041] R13: 000056151fc636e0 R14: 000056151fc616bc R15: 0000000000000080
[  133.432481] Modules linked in: mpls_iptunnel act_mirred act_tunnel_key cls_flower sch_ingress veth mpls_router ip_tunnel bareudp ip6_udp_tunnel udp_tunnel macsec udp_diag inet_diag unix_diag af_packet_diag netlink_diag binfmt_misc xt_MASQUERADE iptable_nat xt_addrtype xt_conntrack nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter bridge stp llc ebtable_filter ebtables overlay ip6table_filter ip6_tables iptable_filter sunrpc ext4 mbcache jbd2 pcspkr i2c_piix4 virtio_balloon joydev ip_tables xfs libcrc32c ata_generic qxl pata_acpi drm_ttm_helper ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm ata_piix libata virtio_net net_failover virtio_console failover virtio_blk i2c_core virtio_pci virtio_ring serio_raw floppy virtio dm_mirror dm_region_hash dm_log dm_mod
[  133.444045] CR2: 0000000000000000
[  133.445082] ---[ end trace f4aeee1958fd1638 ]---
[  133.446236] RIP: 0010:0x0
[  133.447180] Code: Bad RIP value.
[  133.448152] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.449363] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.450835] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.452237] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.453722] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.455149] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.456520] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.458046] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.459342] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.460782] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.462240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.463697] Kernel panic - not syncing: Fatal exception in interrupt
[  133.465226] Kernel Offset: 0xfa00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[  133.467025] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: aaa0c23cb9 ("Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-07 15:33:28 -07:00

549 lines
13 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* net/dst.h Protocol independent destination cache definitions.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
*/
#ifndef _NET_DST_H
#define _NET_DST_H
#include <net/dst_ops.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.h>
#include <linux/bug.h>
#include <linux/jiffies.h>
#include <linux/refcount.h>
#include <net/neighbour.h>
#include <asm/processor.h>
struct sk_buff;
struct dst_entry {
struct net_device *dev;
struct dst_ops *ops;
unsigned long _metrics;
unsigned long expires;
#ifdef CONFIG_XFRM
struct xfrm_state *xfrm;
#else
void *__pad1;
#endif
int (*input)(struct sk_buff *);
int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
unsigned short flags;
#define DST_NOXFRM 0x0002
#define DST_NOPOLICY 0x0004
#define DST_NOCOUNT 0x0008
#define DST_FAKE_RTABLE 0x0010
#define DST_XFRM_TUNNEL 0x0020
#define DST_XFRM_QUEUE 0x0040
#define DST_METADATA 0x0080
/* A non-zero value of dst->obsolete forces by-hand validation
* of the route entry. Positive values are set by the generic
* dst layer to indicate that the entry has been forcefully
* destroyed.
*
* Negative values are used by the implementation layer code to
* force invocation of the dst_ops->check() method.
*/
short obsolete;
#define DST_OBSOLETE_NONE 0
#define DST_OBSOLETE_DEAD 2
#define DST_OBSOLETE_FORCE_CHK -1
#define DST_OBSOLETE_KILL -2
unsigned short header_len; /* more space at head required */
unsigned short trailer_len; /* space to reserve at tail */
/*
* __refcnt wants to be on a different cache line from
* input/output/ops or performance tanks badly
*/
#ifdef CONFIG_64BIT
atomic_t __refcnt; /* 64-bit offset 64 */
#endif
int __use;
unsigned long lastuse;
struct lwtunnel_state *lwtstate;
struct rcu_head rcu_head;
short error;
short __pad;
__u32 tclassid;
#ifndef CONFIG_64BIT
atomic_t __refcnt; /* 32-bit offset 64 */
#endif
};
struct dst_metrics {
u32 metrics[RTAX_MAX];
refcount_t refcnt;
} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */
extern const struct dst_metrics dst_default_metrics;
u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
#define DST_METRICS_READ_ONLY 0x1UL
#define DST_METRICS_REFCOUNTED 0x2UL
#define DST_METRICS_FLAGS 0x3UL
#define __DST_METRICS_PTR(Y) \
((u32 *)((Y) & ~DST_METRICS_FLAGS))
#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics)
static inline bool dst_metrics_read_only(const struct dst_entry *dst)
{
return dst->_metrics & DST_METRICS_READ_ONLY;
}
void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
{
unsigned long val = dst->_metrics;
if (!(val & DST_METRICS_READ_ONLY))
__dst_destroy_metrics_generic(dst, val);
}
static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst)
{
unsigned long p = dst->_metrics;
BUG_ON(!p);
if (p & DST_METRICS_READ_ONLY)
return dst->ops->cow_metrics(dst, p);
return __DST_METRICS_PTR(p);
}
/* This may only be invoked before the entry has reached global
* visibility.
*/
static inline void dst_init_metrics(struct dst_entry *dst,
const u32 *src_metrics,
bool read_only)
{
dst->_metrics = ((unsigned long) src_metrics) |
(read_only ? DST_METRICS_READ_ONLY : 0);
}
static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
{
u32 *dst_metrics = dst_metrics_write_ptr(dest);
if (dst_metrics) {
u32 *src_metrics = DST_METRICS_PTR(src);
memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
}
}
static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
{
return DST_METRICS_PTR(dst);
}
static inline u32
dst_metric_raw(const struct dst_entry *dst, const int metric)
{
u32 *p = DST_METRICS_PTR(dst);
return p[metric-1];
}
static inline u32
dst_metric(const struct dst_entry *dst, const int metric)
{
WARN_ON_ONCE(metric == RTAX_HOPLIMIT ||
metric == RTAX_ADVMSS ||
metric == RTAX_MTU);
return dst_metric_raw(dst, metric);
}
static inline u32
dst_metric_advmss(const struct dst_entry *dst)
{
u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);
if (!advmss)
advmss = dst->ops->default_advmss(dst);
return advmss;
}
static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
{
u32 *p = dst_metrics_write_ptr(dst);
if (p)
p[metric-1] = val;
}
/* Kernel-internal feature bits that are unallocated in user space. */
#define DST_FEATURE_ECN_CA (1U << 31)
#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA)
#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN)
static inline u32
dst_feature(const struct dst_entry *dst, u32 feature)
{
return dst_metric(dst, RTAX_FEATURES) & feature;
}
static inline u32 dst_mtu(const struct dst_entry *dst)
{
return dst->ops->mtu(dst);
}
/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
{
return msecs_to_jiffies(dst_metric(dst, metric));
}
static inline u32
dst_allfrag(const struct dst_entry *dst)
{
int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG);
return ret;
}
static inline int
dst_metric_locked(const struct dst_entry *dst, int metric)
{
return dst_metric(dst, RTAX_LOCK) & (1<<metric);
}
static inline void dst_hold(struct dst_entry *dst)
{
/*
* If your kernel compilation stops here, please check
* the placement of __refcnt in struct dst_entry
*/
BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63);
WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0);
}
static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
{
if (unlikely(time != dst->lastuse)) {
dst->__use++;
dst->lastuse = time;
}
}
static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time)
{
dst_hold(dst);
dst_use_noref(dst, time);
}
static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
if (dst)
dst_hold(dst);
return dst;
}
void dst_release(struct dst_entry *dst);
void dst_release_immediate(struct dst_entry *dst);
static inline void refdst_drop(unsigned long refdst)
{
if (!(refdst & SKB_DST_NOREF))
dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK));
}
/**
* skb_dst_drop - drops skb dst
* @skb: buffer
*
* Drops dst reference count if a reference was taken.
*/
static inline void skb_dst_drop(struct sk_buff *skb)
{
if (skb->_skb_refdst) {
refdst_drop(skb->_skb_refdst);
skb->_skb_refdst = 0UL;
}
}
static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst)
{
nskb->_skb_refdst = refdst;
if (!(nskb->_skb_refdst & SKB_DST_NOREF))
dst_clone(skb_dst(nskb));
}
static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb)
{
__skb_dst_copy(nskb, oskb->_skb_refdst);
}
/**
* dst_hold_safe - Take a reference on a dst if possible
* @dst: pointer to dst entry
*
* This helper returns false if it could not safely
* take a reference on a dst.
*/
static inline bool dst_hold_safe(struct dst_entry *dst)
{
return atomic_inc_not_zero(&dst->__refcnt);
}
/**
* skb_dst_force - makes sure skb dst is refcounted
* @skb: buffer
*
* If dst is not yet refcounted and not destroyed, grab a ref on it.
* Returns true if dst is refcounted.
*/
static inline bool skb_dst_force(struct sk_buff *skb)
{
if (skb_dst_is_noref(skb)) {
struct dst_entry *dst = skb_dst(skb);
WARN_ON(!rcu_read_lock_held());
if (!dst_hold_safe(dst))
dst = NULL;
skb->_skb_refdst = (unsigned long)dst;
}
return skb->_skb_refdst != 0UL;
}
/**
* __skb_tunnel_rx - prepare skb for rx reinsert
* @skb: buffer
* @dev: tunnel device
* @net: netns for packet i/o
*
* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
* so make some cleanups. (no accounting done)
*/
static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
skb->dev = dev;
/*
* Clear hash so that we can recalulate the hash for the
* encapsulated packet, unless we have already determine the hash
* over the L4 4-tuple.
*/
skb_clear_hash_if_not_l4(skb);
skb_set_queue_mapping(skb, 0);
skb_scrub_packet(skb, !net_eq(net, dev_net(dev)));
}
/**
* skb_tunnel_rx - prepare skb for rx reinsert
* @skb: buffer
* @dev: tunnel device
* @net: netns for packet i/o
*
* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
* so make some cleanups, and perform accounting.
* Note: this accounting is not SMP safe.
*/
static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
/* TODO : stats should be SMP safe */
dev->stats.rx_packets++;
dev->stats.rx_bytes += skb->len;
__skb_tunnel_rx(skb, dev, net);
}
static inline u32 dst_tclassid(const struct sk_buff *skb)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
const struct dst_entry *dst;
dst = skb_dst(skb);
if (dst)
return dst->tclassid;
#endif
return 0;
}
int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static inline int dst_discard(struct sk_buff *skb)
{
return dst_discard_out(&init_net, skb->sk, skb);
}
void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
int initial_obsolete, unsigned short flags);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
struct net_device *dev, int initial_ref, int initial_obsolete,
unsigned short flags);
struct dst_entry *dst_destroy(struct dst_entry *dst);
void dst_dev_put(struct dst_entry *dst);
static inline void dst_confirm(struct dst_entry *dst)
{
}
static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
{
struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
return IS_ERR(n) ? NULL : n;
}
static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
struct sk_buff *skb)
{
struct neighbour *n = NULL;
/* The packets from tunnel devices (eg bareudp) may have only
* metadata in the dst pointer of skb. Hence a pointer check of
* neigh_lookup is needed.
*/
if (dst->ops->neigh_lookup)
n = dst->ops->neigh_lookup(dst, skb, NULL);
return IS_ERR(n) ? NULL : n;
}
static inline void dst_confirm_neigh(const struct dst_entry *dst,
const void *daddr)
{
if (dst->ops->confirm_neigh)
dst->ops->confirm_neigh(dst, daddr);
}
static inline void dst_link_failure(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
if (dst && dst->ops && dst->ops->link_failure)
dst->ops->link_failure(skb);
}
static inline void dst_set_expires(struct dst_entry *dst, int timeout)
{
unsigned long expires = jiffies + timeout;
if (expires == 0)
expires = 1;
if (dst->expires == 0 || time_before(expires, dst->expires))
dst->expires = expires;
}
/* Output packet to network from transport. */
static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return skb_dst(skb)->output(net, sk, skb);
}
/* Input packet from network to transport. */
static inline int dst_input(struct sk_buff *skb)
{
return skb_dst(skb)->input(skb);
}
static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
{
if (dst->obsolete)
dst = dst->ops->check(dst, cookie);
return dst;
}
/* Flags for xfrm_lookup flags argument. */
enum {
XFRM_LOOKUP_ICMP = 1 << 0,
XFRM_LOOKUP_QUEUE = 1 << 1,
XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
};
struct flowi;
#ifndef CONFIG_XFRM
static inline struct dst_entry *xfrm_lookup(struct net *net,
struct dst_entry *dst_orig,
const struct flowi *fl,
const struct sock *sk,
int flags)
{
return dst_orig;
}
static inline struct dst_entry *
xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig,
const struct flowi *fl, const struct sock *sk,
int flags, u32 if_id)
{
return dst_orig;
}
static inline struct dst_entry *xfrm_lookup_route(struct net *net,
struct dst_entry *dst_orig,
const struct flowi *fl,
const struct sock *sk,
int flags)
{
return dst_orig;
}
static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
{
return NULL;
}
#else
struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
const struct flowi *fl, const struct sock *sk,
int flags);
struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
struct dst_entry *dst_orig,
const struct flowi *fl,
const struct sock *sk, int flags,
u32 if_id);
struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
const struct flowi *fl, const struct sock *sk,
int flags);
/* skb attached with this dst needs transformation if dst->xfrm is valid */
static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
{
return dst->xfrm;
}
#endif
static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
{
struct dst_entry *dst = skb_dst(skb);
if (dst && dst->ops->update_pmtu)
dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
}
/* update dst pmtu but not do neighbor confirm */
static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
{
struct dst_entry *dst = skb_dst(skb);
if (dst && dst->ops->update_pmtu)
dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
}
static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
struct dst_entry *encap_dst,
int headroom)
{
u32 encap_mtu = dst_mtu(encap_dst);
if (skb->len > encap_mtu - headroom)
skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
}
#endif /* _NET_DST_H */