kernel_optimize_test/net/packet/internal.h
Mike Maloney 57f015f5ec packet: fix crash in fanout_demux_rollover()
syzkaller found a race condition fanout_demux_rollover() while removing
a packet socket from a fanout group.

po->rollover is read and operated on during packet_rcv_fanout(), via
fanout_demux_rollover(), but the pointer is currently cleared before the
synchronization in packet_release().   It is safer to delay the cleanup
until after synchronize_net() has been called, ensuring all calls to
packet_rcv_fanout() for this socket have finished.

To further simplify synchronization around the rollover structure, set
po->rollover in fanout_add() only if there are no errors.  This removes
the need for rcu in the struct and in the call to
packet_getsockopt(..., PACKET_ROLLOVER_STATS, ...).

Crashing stack trace:
 fanout_demux_rollover+0xb6/0x4d0 net/packet/af_packet.c:1392
 packet_rcv_fanout+0x649/0x7c8 net/packet/af_packet.c:1487
 dev_queue_xmit_nit+0x835/0xc10 net/core/dev.c:1953
 xmit_one net/core/dev.c:2975 [inline]
 dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:2995
 __dev_queue_xmit+0x17a4/0x2050 net/core/dev.c:3476
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3509
 neigh_connected_output+0x489/0x720 net/core/neighbour.c:1379
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xad1/0x22a0 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x2f9/0x920 net/ipv6/ip6_output.c:146
 NF_HOOK_COND include/linux/netfilter.h:239 [inline]
 ip6_output+0x1f4/0x850 net/ipv6/ip6_output.c:163
 dst_output include/net/dst.h:459 [inline]
 NF_HOOK.constprop.35+0xff/0x630 include/linux/netfilter.h:250
 mld_sendpack+0x6a8/0xcc0 net/ipv6/mcast.c:1660
 mld_send_initial_cr.part.24+0x103/0x150 net/ipv6/mcast.c:2072
 mld_send_initial_cr net/ipv6/mcast.c:2056 [inline]
 ipv6_mc_dad_complete+0x99/0x130 net/ipv6/mcast.c:2079
 addrconf_dad_completed+0x595/0x970 net/ipv6/addrconf.c:4039
 addrconf_dad_work+0xac9/0x1160 net/ipv6/addrconf.c:3971
 process_one_work+0xbf0/0x1bc0 kernel/workqueue.c:2113
 worker_thread+0x223/0x1990 kernel/workqueue.c:2247
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:432

Fixes: 0648ab70af ("packet: rollover prepare: per-socket state")
Fixes: 509c7a1ecc ("packet: avoid panic in packet_getsockopt()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-28 11:13:30 -05:00

142 lines
3.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PACKET_INTERNAL_H__
#define __PACKET_INTERNAL_H__
#include <linux/refcount.h>
struct packet_mclist {
struct packet_mclist *next;
int ifindex;
int count;
unsigned short type;
unsigned short alen;
unsigned char addr[MAX_ADDR_LEN];
};
/* kbdq - kernel block descriptor queue */
struct tpacket_kbdq_core {
struct pgv *pkbdq;
unsigned int feature_req_word;
unsigned int hdrlen;
unsigned char reset_pending_on_curr_blk;
unsigned char delete_blk_timer;
unsigned short kactive_blk_num;
unsigned short blk_sizeof_priv;
/* last_kactive_blk_num:
* trick to see if user-space has caught up
* in order to avoid refreshing timer when every single pkt arrives.
*/
unsigned short last_kactive_blk_num;
char *pkblk_start;
char *pkblk_end;
int kblk_size;
unsigned int max_frame_len;
unsigned int knum_blocks;
uint64_t knxt_seq_num;
char *prev;
char *nxt_offset;
struct sk_buff *skb;
atomic_t blk_fill_in_prog;
/* Default is set to 8ms */
#define DEFAULT_PRB_RETIRE_TOV (8)
unsigned short retire_blk_tov;
unsigned short version;
unsigned long tov_in_jiffies;
/* timer to retire an outstanding block */
struct timer_list retire_blk_timer;
};
struct pgv {
char *buffer;
};
struct packet_ring_buffer {
struct pgv *pg_vec;
unsigned int head;
unsigned int frames_per_block;
unsigned int frame_size;
unsigned int frame_max;
unsigned int pg_vec_order;
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
unsigned int __percpu *pending_refcnt;
struct tpacket_kbdq_core prb_bdqc;
};
extern struct mutex fanout_mutex;
#define PACKET_FANOUT_MAX 256
struct packet_fanout {
possible_net_t net;
unsigned int num_members;
u16 id;
u8 type;
u8 flags;
union {
atomic_t rr_cur;
struct bpf_prog __rcu *bpf_prog;
};
struct list_head list;
struct sock *arr[PACKET_FANOUT_MAX];
spinlock_t lock;
refcount_t sk_ref;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
struct packet_rollover {
int sock;
atomic_long_t num;
atomic_long_t num_huge;
atomic_long_t num_failed;
#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32))
u32 history[ROLLOVER_HLEN] ____cacheline_aligned;
} ____cacheline_aligned_in_smp;
struct packet_sock {
/* struct sock has to be the first member of packet_sock */
struct sock sk;
struct packet_fanout *fanout;
union tpacket_stats_u stats;
struct packet_ring_buffer rx_ring;
struct packet_ring_buffer tx_ring;
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
unsigned int running:1, /* prot_hook is attached*/
auxdata:1,
origdev:1,
has_vnet_hdr:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
struct packet_rollover *rollover;
struct packet_mclist *mclist;
atomic_t mapped;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
unsigned int tp_loss:1;
unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
static struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
#endif