kernel-ark/net/packet/internal.h
Daniel Borkmann e40526cb20 packet: fix use after free race in send path when dev is released
Salam reported a use after free bug in PF_PACKET that occurs when
we're sending out frames on a socket bound device and suddenly the
net device is being unregistered. It appears that commit 827d9780
introduced a possible race condition between {t,}packet_snd() and
packet_notifier(). In the case of a bound socket, packet_notifier()
can drop the last reference to the net_device and {t,}packet_snd()
might end up suddenly sending a packet over a freed net_device.

To avoid reverting 827d9780 and thus introducing a performance
regression compared to the current state of things, we decided to
hold a cached RCU protected pointer to the net device and maintain
it on write side via bind spin_lock protected register_prot_hook()
and __unregister_prot_hook() calls.

In {t,}packet_snd() path, we access this pointer under rcu_read_lock
through packet_cached_dev_get() that holds reference to the device
to prevent it from being freed through packet_notifier() while
we're in send path. This is okay to do as dev_put()/dev_hold() are
per-cpu counters, so this should not be a performance issue. Also,
the code simplifies a bit as we don't need need_rls_dev anymore.

Fixes: 827d978037 ("af-packet: Use existing netdev reference for bound sockets.")
Reported-by: Salam Noureddine <noureddine@aristanetworks.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Salam Noureddine <noureddine@aristanetworks.com>
Cc: Ben Greear <greearb@candelatech.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-21 13:09:43 -05:00

126 lines
2.7 KiB
C

#ifndef __PACKET_INTERNAL_H__
#define __PACKET_INTERNAL_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 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;
atomic_t pending;
struct tpacket_kbdq_core prb_bdqc;
};
extern struct mutex fanout_mutex;
#define PACKET_FANOUT_MAX 256
struct packet_fanout {
#ifdef CONFIG_NET_NS
struct net *net;
#endif
unsigned int num_members;
u16 id;
u8 type;
u8 flags;
atomic_t rr_cur;
struct list_head list;
struct sock *arr[PACKET_FANOUT_MAX];
int next[PACKET_FANOUT_MAX];
spinlock_t lock;
atomic_t sk_ref;
struct packet_type prot_hook ____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 ifindex; /* bound device */
__be16 num;
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;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
static struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
#endif