2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
|
|
* operating system. INET is implemented using the BSD Socket
|
|
|
|
* interface as the means of communication with the user level.
|
|
|
|
*
|
|
|
|
* PACKET - implements raw packet sockets.
|
|
|
|
*
|
2005-05-05 23:16:16 +00:00
|
|
|
* Authors: Ross Biro
|
2005-04-16 22:20:36 +00:00
|
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
|
|
* Alan Cox, <gw4pts@gw4pts.ampr.org>
|
|
|
|
*
|
2007-02-09 14:25:10 +00:00
|
|
|
* Fixes:
|
2005-04-16 22:20:36 +00:00
|
|
|
* Alan Cox : verify_area() now used correctly
|
|
|
|
* Alan Cox : new skbuff lists, look ma no backlogs!
|
|
|
|
* Alan Cox : tidied skbuff lists.
|
|
|
|
* Alan Cox : Now uses generic datagram routines I
|
|
|
|
* added. Also fixed the peek/read crash
|
|
|
|
* from all old Linux datagram code.
|
|
|
|
* Alan Cox : Uses the improved datagram code.
|
|
|
|
* Alan Cox : Added NULL's for socket options.
|
|
|
|
* Alan Cox : Re-commented the code.
|
|
|
|
* Alan Cox : Use new kernel side addressing
|
|
|
|
* Rob Janssen : Correct MTU usage.
|
|
|
|
* Dave Platt : Counter leaks caused by incorrect
|
|
|
|
* interrupt locking and some slightly
|
|
|
|
* dubious gcc output. Can you read
|
|
|
|
* compiler: it said _VOLATILE_
|
|
|
|
* Richard Kooijman : Timestamp fixes.
|
|
|
|
* Alan Cox : New buffers. Use sk->mac.raw.
|
|
|
|
* Alan Cox : sendmsg/recvmsg support.
|
|
|
|
* Alan Cox : Protocol setting support
|
|
|
|
* Alexey Kuznetsov : Untied from IPv4 stack.
|
|
|
|
* Cyrus Durgin : Fixed kerneld for kmod.
|
|
|
|
* Michal Ostrowski : Module initialization cleanup.
|
2007-02-09 14:25:10 +00:00
|
|
|
* Ulises Alonso : Frame number limit removal and
|
2005-04-16 22:20:36 +00:00
|
|
|
* packet_set_ring memory leak.
|
2005-09-21 07:11:37 +00:00
|
|
|
* Eric Biederman : Allow for > 8 byte hardware addresses.
|
|
|
|
* The convention is that longer addresses
|
|
|
|
* will simply extend the hardware address
|
2007-02-09 14:25:10 +00:00
|
|
|
* byte arrays at the end of sockaddr_ll
|
2005-09-21 07:11:37 +00:00
|
|
|
* and packet_mreq.
|
2009-05-19 05:11:22 +00:00
|
|
|
* Johann Baudy : Added TX RING.
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/mm.h>
|
2006-01-11 20:17:47 +00:00
|
|
|
#include <linux/capability.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/fcntl.h>
|
|
|
|
#include <linux/socket.h>
|
|
|
|
#include <linux/in.h>
|
|
|
|
#include <linux/inet.h>
|
|
|
|
#include <linux/netdevice.h>
|
|
|
|
#include <linux/if_packet.h>
|
|
|
|
#include <linux/wireless.h>
|
2007-02-05 07:33:10 +00:00
|
|
|
#include <linux/kernel.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/kmod.h>
|
2007-09-12 10:01:34 +00:00
|
|
|
#include <net/net_namespace.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <net/ip.h>
|
|
|
|
#include <net/protocol.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <net/sock.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/timer.h>
|
|
|
|
#include <asm/system.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/ioctls.h>
|
|
|
|
#include <asm/page.h>
|
2006-10-19 20:08:53 +00:00
|
|
|
#include <asm/cacheflush.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <asm/io.h>
|
|
|
|
#include <linux/proc_fs.h>
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/init.h>
|
2009-01-30 22:12:06 +00:00
|
|
|
#include <linux/mutex.h>
|
2009-10-27 01:40:35 +00:00
|
|
|
#include <linux/if_vlan.h>
|
2010-02-05 04:24:10 +00:00
|
|
|
#include <linux/virtio_net.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
#ifdef CONFIG_INET
|
|
|
|
#include <net/inet_common.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
Assumptions:
|
|
|
|
- if device has no dev->hard_header routine, it adds and removes ll header
|
|
|
|
inside itself. In this case ll header is invisible outside of device,
|
|
|
|
but higher levels still should reserve dev->hard_header_len.
|
|
|
|
Some devices are enough clever to reallocate skb, when header
|
|
|
|
will not fit to reserved space (tunnel), another ones are silly
|
|
|
|
(PPP).
|
|
|
|
- packet socket receives packets with pulled ll header,
|
|
|
|
so that SOCK_RAW should push it back.
|
|
|
|
|
|
|
|
On receive:
|
|
|
|
-----------
|
|
|
|
|
|
|
|
Incoming, dev->hard_header!=NULL
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> ll header
|
|
|
|
data -> data
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
Outgoing, dev->hard_header!=NULL
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> ll header
|
|
|
|
data -> ll header
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
Incoming, dev->hard_header==NULL
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> UNKNOWN position. It is very likely, that it points to ll
|
|
|
|
header. PPP makes it, that is wrong, because introduce
|
2007-07-19 01:44:35 +00:00
|
|
|
assymetry between rx and tx paths.
|
2007-04-11 04:21:55 +00:00
|
|
|
data -> data
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
Outgoing, dev->hard_header==NULL
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> data. ll header is still not built!
|
|
|
|
data -> data
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
Resume
|
|
|
|
If dev->hard_header==NULL we are unlikely to restore sensible ll header.
|
|
|
|
|
|
|
|
|
|
|
|
On transmit:
|
|
|
|
------------
|
|
|
|
|
|
|
|
dev->hard_header != NULL
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> ll header
|
|
|
|
data -> ll header
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
dev->hard_header == NULL (ll header is added by device, we cannot control it)
|
2007-04-11 04:21:55 +00:00
|
|
|
mac_header -> data
|
|
|
|
data -> data
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
We should set nh.raw on output to correct posistion,
|
|
|
|
packet classifier depends on it.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Private packet socket structures. */
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
struct packet_mclist {
|
2005-04-16 22:20:36 +00:00
|
|
|
struct packet_mclist *next;
|
|
|
|
int ifindex;
|
|
|
|
int count;
|
|
|
|
unsigned short type;
|
|
|
|
unsigned short alen;
|
2005-09-21 07:11:37 +00:00
|
|
|
unsigned char addr[MAX_ADDR_LEN];
|
|
|
|
};
|
|
|
|
/* identical to struct packet_mreq except it has
|
|
|
|
* a longer address field.
|
|
|
|
*/
|
2009-07-21 21:57:59 +00:00
|
|
|
struct packet_mreq_max {
|
2005-09-21 07:11:37 +00:00
|
|
|
int mr_ifindex;
|
|
|
|
unsigned short mr_type;
|
|
|
|
unsigned short mr_alen;
|
|
|
|
unsigned char mr_address[MAX_ADDR_LEN];
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
2007-05-29 20:12:50 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
|
|
|
|
int closing, int tx_ring);
|
|
|
|
|
|
|
|
struct packet_ring_buffer {
|
2009-07-21 21:57:59 +00:00
|
|
|
char **pg_vec;
|
2009-05-19 05:11:22 +00:00
|
|
|
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 packet_sock;
|
|
|
|
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
static void packet_flush_mclist(struct sock *sk);
|
|
|
|
|
|
|
|
struct packet_sock {
|
|
|
|
/* struct sock has to be the first member of packet_sock */
|
|
|
|
struct sock sk;
|
|
|
|
struct tpacket_stats stats;
|
2009-05-19 05:11:22 +00:00
|
|
|
struct packet_ring_buffer rx_ring;
|
|
|
|
struct packet_ring_buffer tx_ring;
|
2005-04-16 22:20:36 +00:00
|
|
|
int copy_thresh;
|
|
|
|
spinlock_t bind_lock;
|
2009-01-30 22:12:06 +00:00
|
|
|
struct mutex pg_vec_lock;
|
2007-02-05 07:31:32 +00:00
|
|
|
unsigned int running:1, /* prot_hook is attached*/
|
2007-04-20 23:05:39 +00:00
|
|
|
auxdata:1,
|
2010-02-05 04:24:10 +00:00
|
|
|
origdev:1,
|
|
|
|
has_vnet_hdr:1;
|
2005-04-16 22:20:36 +00:00
|
|
|
int ifindex; /* bound device */
|
2006-11-08 08:26:29 +00:00
|
|
|
__be16 num;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct packet_mclist *mclist;
|
|
|
|
atomic_t mapped;
|
2008-07-15 05:50:15 +00:00
|
|
|
enum tpacket_versions tp_version;
|
|
|
|
unsigned int tp_hdrlen;
|
2008-07-19 01:05:19 +00:00
|
|
|
unsigned int tp_reserve;
|
2009-05-19 05:11:22 +00:00
|
|
|
unsigned int tp_loss:1;
|
2009-10-16 04:02:20 +00:00
|
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
2007-02-05 07:33:10 +00:00
|
|
|
struct packet_skb_cb {
|
|
|
|
unsigned int origlen;
|
|
|
|
union {
|
|
|
|
struct sockaddr_pkt pkt;
|
|
|
|
struct sockaddr_ll ll;
|
|
|
|
} sa;
|
|
|
|
};
|
|
|
|
|
|
|
|
#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb))
|
2007-02-05 07:31:32 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static void __packet_set_status(struct packet_sock *po, void *frame, int status)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2008-07-15 05:50:15 +00:00
|
|
|
union {
|
|
|
|
struct tpacket_hdr *h1;
|
|
|
|
struct tpacket2_hdr *h2;
|
|
|
|
void *raw;
|
|
|
|
} h;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
h.raw = frame;
|
2008-07-15 05:50:15 +00:00
|
|
|
switch (po->tp_version) {
|
|
|
|
case TPACKET_V1:
|
2009-05-19 05:11:22 +00:00
|
|
|
h.h1->tp_status = status;
|
|
|
|
flush_dcache_page(virt_to_page(&h.h1->tp_status));
|
2008-07-15 05:50:15 +00:00
|
|
|
break;
|
|
|
|
case TPACKET_V2:
|
2009-05-19 05:11:22 +00:00
|
|
|
h.h2->tp_status = status;
|
|
|
|
flush_dcache_page(virt_to_page(&h.h2->tp_status));
|
2008-07-15 05:50:15 +00:00
|
|
|
break;
|
2009-05-19 05:11:22 +00:00
|
|
|
default:
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("TPACKET version not supported\n");
|
2009-05-19 05:11:22 +00:00
|
|
|
BUG();
|
2008-07-15 05:50:15 +00:00
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
smp_wmb();
|
2008-07-15 05:50:15 +00:00
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int __packet_get_status(struct packet_sock *po, void *frame)
|
2008-07-15 05:50:15 +00:00
|
|
|
{
|
|
|
|
union {
|
|
|
|
struct tpacket_hdr *h1;
|
|
|
|
struct tpacket2_hdr *h2;
|
|
|
|
void *raw;
|
|
|
|
} h;
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
smp_rmb();
|
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
h.raw = frame;
|
|
|
|
switch (po->tp_version) {
|
|
|
|
case TPACKET_V1:
|
2009-05-19 05:11:22 +00:00
|
|
|
flush_dcache_page(virt_to_page(&h.h1->tp_status));
|
|
|
|
return h.h1->tp_status;
|
2008-07-15 05:50:15 +00:00
|
|
|
case TPACKET_V2:
|
2009-05-19 05:11:22 +00:00
|
|
|
flush_dcache_page(virt_to_page(&h.h2->tp_status));
|
|
|
|
return h.h2->tp_status;
|
|
|
|
default:
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("TPACKET version not supported\n");
|
2009-05-19 05:11:22 +00:00
|
|
|
BUG();
|
|
|
|
return 0;
|
2008-07-15 05:50:15 +00:00
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
static void *packet_lookup_frame(struct packet_sock *po,
|
|
|
|
struct packet_ring_buffer *rb,
|
|
|
|
unsigned int position,
|
|
|
|
int status)
|
|
|
|
{
|
|
|
|
unsigned int pg_vec_pos, frame_offset;
|
|
|
|
union {
|
|
|
|
struct tpacket_hdr *h1;
|
|
|
|
struct tpacket2_hdr *h2;
|
|
|
|
void *raw;
|
|
|
|
} h;
|
|
|
|
|
|
|
|
pg_vec_pos = position / rb->frames_per_block;
|
|
|
|
frame_offset = position % rb->frames_per_block;
|
|
|
|
|
|
|
|
h.raw = rb->pg_vec[pg_vec_pos] + (frame_offset * rb->frame_size);
|
|
|
|
|
|
|
|
if (status != __packet_get_status(po, h.raw))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
return h.raw;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void *packet_current_frame(struct packet_sock *po,
|
|
|
|
struct packet_ring_buffer *rb,
|
|
|
|
int status)
|
|
|
|
{
|
|
|
|
return packet_lookup_frame(po, rb, rb->head, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void *packet_previous_frame(struct packet_sock *po,
|
|
|
|
struct packet_ring_buffer *rb,
|
|
|
|
int status)
|
|
|
|
{
|
|
|
|
unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max;
|
|
|
|
return packet_lookup_frame(po, rb, previous, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void packet_increment_head(struct packet_ring_buffer *buff)
|
|
|
|
{
|
|
|
|
buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
static inline struct packet_sock *pkt_sk(struct sock *sk)
|
|
|
|
{
|
|
|
|
return (struct packet_sock *)sk;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void packet_sock_destruct(struct sock *sk)
|
|
|
|
{
|
2008-07-26 04:43:18 +00:00
|
|
|
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
|
|
|
|
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (!sock_flag(sk, SOCK_DEAD)) {
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("Attempt to release alive packet socket: %p\n", sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2007-11-11 05:38:48 +00:00
|
|
|
sk_refcnt_debug_dec(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2005-12-22 20:49:22 +00:00
|
|
|
static const struct proto_ops packet_ops;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2005-12-22 20:49:22 +00:00
|
|
|
static const struct proto_ops packet_ops_spkt;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,
|
|
|
|
struct packet_type *pt, struct net_device *orig_dev)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
struct sockaddr_pkt *spkt;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When we registered the protocol we saved the socket in the data
|
|
|
|
* field for just this event.
|
|
|
|
*/
|
|
|
|
|
|
|
|
sk = pt->af_packet_priv;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Yank back the headers [hope the device set this
|
|
|
|
* right or kerboom...]
|
|
|
|
*
|
|
|
|
* Incoming packets have ll header pulled,
|
|
|
|
* push it back.
|
|
|
|
*
|
2007-03-19 22:33:04 +00:00
|
|
|
* For outgoing ones skb->data == skb_mac_header(skb)
|
2005-04-16 22:20:36 +00:00
|
|
|
* so that this procedure is noop.
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (skb->pkt_type == PACKET_LOOPBACK)
|
|
|
|
goto out;
|
|
|
|
|
2009-11-25 23:14:13 +00:00
|
|
|
if (!net_eq(dev_net(dev), sock_net(sk)))
|
2007-11-20 06:28:35 +00:00
|
|
|
goto out;
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
skb = skb_share_check(skb, GFP_ATOMIC);
|
|
|
|
if (skb == NULL)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto oom;
|
|
|
|
|
|
|
|
/* drop any routing info */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2005-07-12 18:57:52 +00:00
|
|
|
/* drop conntrack reference */
|
|
|
|
nf_reset(skb);
|
|
|
|
|
2007-02-05 07:33:10 +00:00
|
|
|
spkt = &PACKET_SKB_CB(skb)->sa.pkt;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-03-19 22:33:04 +00:00
|
|
|
skb_push(skb, skb->data - skb_mac_header(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The SOCK_PACKET socket receives _all_ frames.
|
|
|
|
*/
|
|
|
|
|
|
|
|
spkt->spkt_family = dev->type;
|
|
|
|
strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
|
|
|
|
spkt->spkt_protocol = skb->protocol;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Charge the memory to the socket. This is done specifically
|
|
|
|
* to prevent sockets using all the memory up.
|
|
|
|
*/
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
if (sock_queue_rcv_skb(sk, skb) == 0)
|
2005-04-16 22:20:36 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
kfree_skb(skb);
|
|
|
|
oom:
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Output a raw packet to a device layer. This bypasses all the other
|
|
|
|
* protocol layers and you must therefore supply it with a complete frame
|
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
|
|
|
|
struct msghdr *msg, size_t len)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
2009-07-21 21:57:59 +00:00
|
|
|
struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name;
|
2009-12-15 05:47:03 +00:00
|
|
|
struct sk_buff *skb = NULL;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct net_device *dev;
|
2009-07-21 21:57:59 +00:00
|
|
|
__be16 proto = 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
int err;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
2007-02-09 14:25:10 +00:00
|
|
|
* Get and verify the address.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
if (saddr) {
|
2005-04-16 22:20:36 +00:00
|
|
|
if (msg->msg_namelen < sizeof(struct sockaddr))
|
2009-07-21 21:57:59 +00:00
|
|
|
return -EINVAL;
|
|
|
|
if (msg->msg_namelen == sizeof(struct sockaddr_pkt))
|
|
|
|
proto = saddr->spkt_protocol;
|
|
|
|
} else
|
|
|
|
return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
2007-02-09 14:25:10 +00:00
|
|
|
* Find the device first to size check it
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
saddr->spkt_device[13] = 0;
|
2009-12-15 05:47:03 +00:00
|
|
|
retry:
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_lock();
|
|
|
|
dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device);
|
2005-04-16 22:20:36 +00:00
|
|
|
err = -ENODEV;
|
|
|
|
if (dev == NULL)
|
|
|
|
goto out_unlock;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2007-01-26 03:30:36 +00:00
|
|
|
err = -ENETDOWN;
|
|
|
|
if (!(dev->flags & IFF_UP))
|
|
|
|
goto out_unlock;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
2009-07-21 21:57:59 +00:00
|
|
|
* You may not queue a frame bigger than the mtu. This is the lowest level
|
|
|
|
* raw protocol and you must do your own fragmentation at this level.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
err = -EMSGSIZE;
|
2006-01-24 00:28:02 +00:00
|
|
|
if (len > dev->mtu + dev->hard_header_len)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out_unlock;
|
|
|
|
|
2009-12-15 05:47:03 +00:00
|
|
|
if (!skb) {
|
|
|
|
size_t reserved = LL_RESERVED_SPACE(dev);
|
|
|
|
unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
|
|
|
|
|
|
|
|
rcu_read_unlock();
|
|
|
|
skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL);
|
|
|
|
if (skb == NULL)
|
|
|
|
return -ENOBUFS;
|
|
|
|
/* FIXME: Save some space for broken drivers that write a hard
|
|
|
|
* header at transmission time by themselves. PPP is the notable
|
|
|
|
* one here. This should really be fixed at the driver level.
|
|
|
|
*/
|
|
|
|
skb_reserve(skb, reserved);
|
|
|
|
skb_reset_network_header(skb);
|
|
|
|
|
|
|
|
/* Try to align data part correctly */
|
|
|
|
if (hhlen) {
|
|
|
|
skb->data -= hhlen;
|
|
|
|
skb->tail -= hhlen;
|
|
|
|
if (len < hhlen)
|
|
|
|
skb_reset_network_header(skb);
|
|
|
|
}
|
|
|
|
err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
|
|
|
|
if (err)
|
|
|
|
goto out_free;
|
|
|
|
goto retry;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2009-12-15 05:47:03 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
skb->protocol = proto;
|
|
|
|
skb->dev = dev;
|
|
|
|
skb->priority = sk->sk_priority;
|
2009-10-01 19:14:46 +00:00
|
|
|
skb->mark = sk->sk_mark;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
dev_queue_xmit(skb);
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_unlock();
|
2009-07-21 21:57:59 +00:00
|
|
|
return len;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
out_unlock:
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_unlock();
|
2009-12-15 05:47:03 +00:00
|
|
|
out_free:
|
|
|
|
kfree_skb(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2007-01-24 23:21:02 +00:00
|
|
|
static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk,
|
|
|
|
unsigned int res)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sk_filter *filter;
|
2006-08-31 22:28:39 +00:00
|
|
|
|
|
|
|
rcu_read_lock_bh();
|
|
|
|
filter = rcu_dereference(sk->sk_filter);
|
2007-01-24 23:21:02 +00:00
|
|
|
if (filter != NULL)
|
|
|
|
res = sk_run_filter(skb, filter->insns, filter->len);
|
2006-08-31 22:28:39 +00:00
|
|
|
rcu_read_unlock_bh();
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-01-24 23:21:02 +00:00
|
|
|
return res;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
This function makes lazy skb cloning in hope that most of packets
|
|
|
|
are discarded by BPF.
|
|
|
|
|
|
|
|
Note tricky part: we DO mangle shared skb! skb->data, skb->len
|
|
|
|
and skb->cb are mangled. It works because (and until) packets
|
|
|
|
falling here are owned by current CPU. Output packets are cloned
|
|
|
|
by dev_queue_xmit_nit(), input packets are processed by net_bh
|
|
|
|
sequencially, so that if we return skb to original state on exit,
|
|
|
|
we will not harm anyone.
|
|
|
|
*/
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
|
|
|
|
struct packet_type *pt, struct net_device *orig_dev)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
struct sockaddr_ll *sll;
|
|
|
|
struct packet_sock *po;
|
2009-07-21 21:57:59 +00:00
|
|
|
u8 *skb_head = skb->data;
|
2005-04-16 22:20:36 +00:00
|
|
|
int skb_len = skb->len;
|
2007-01-24 23:21:02 +00:00
|
|
|
unsigned int snaplen, res;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (skb->pkt_type == PACKET_LOOPBACK)
|
|
|
|
goto drop;
|
|
|
|
|
|
|
|
sk = pt->af_packet_priv;
|
|
|
|
po = pkt_sk(sk);
|
|
|
|
|
2009-11-25 23:14:13 +00:00
|
|
|
if (!net_eq(dev_net(dev), sock_net(sk)))
|
2007-11-20 06:28:35 +00:00
|
|
|
goto drop;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
skb->dev = dev;
|
|
|
|
|
2007-10-09 08:40:57 +00:00
|
|
|
if (dev->header_ops) {
|
2005-04-16 22:20:36 +00:00
|
|
|
/* The device has an explicit notion of ll header,
|
|
|
|
exported to higher levels.
|
|
|
|
|
|
|
|
Otherwise, the device hides datails of it frame
|
|
|
|
structure, so that corresponding packet head
|
|
|
|
never delivered to user.
|
|
|
|
*/
|
|
|
|
if (sk->sk_type != SOCK_DGRAM)
|
2007-03-19 22:33:04 +00:00
|
|
|
skb_push(skb, skb->data - skb_mac_header(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
else if (skb->pkt_type == PACKET_OUTGOING) {
|
|
|
|
/* Special case: outgoing packets have ll header at head */
|
2007-03-11 01:16:10 +00:00
|
|
|
skb_pull(skb, skb_network_offset(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
snaplen = skb->len;
|
|
|
|
|
2007-01-24 23:21:02 +00:00
|
|
|
res = run_filter(skb, sk, snaplen);
|
|
|
|
if (!res)
|
2006-08-31 22:28:39 +00:00
|
|
|
goto drop_n_restore;
|
2007-01-24 23:21:02 +00:00
|
|
|
if (snaplen > res)
|
|
|
|
snaplen = res;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
|
|
|
|
(unsigned)sk->sk_rcvbuf)
|
|
|
|
goto drop_n_acct;
|
|
|
|
|
|
|
|
if (skb_shared(skb)) {
|
|
|
|
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
|
|
|
|
if (nskb == NULL)
|
|
|
|
goto drop_n_acct;
|
|
|
|
|
|
|
|
if (skb_head != skb->data) {
|
|
|
|
skb->data = skb_head;
|
|
|
|
skb->len = skb_len;
|
|
|
|
}
|
|
|
|
kfree_skb(skb);
|
|
|
|
skb = nskb;
|
|
|
|
}
|
|
|
|
|
2007-02-05 07:33:10 +00:00
|
|
|
BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 >
|
|
|
|
sizeof(skb->cb));
|
|
|
|
|
|
|
|
sll = &PACKET_SKB_CB(skb)->sa.ll;
|
2005-04-16 22:20:36 +00:00
|
|
|
sll->sll_family = AF_PACKET;
|
|
|
|
sll->sll_hatype = dev->type;
|
|
|
|
sll->sll_protocol = skb->protocol;
|
|
|
|
sll->sll_pkttype = skb->pkt_type;
|
2007-11-11 06:03:25 +00:00
|
|
|
if (unlikely(po->origdev))
|
2007-04-20 23:05:39 +00:00
|
|
|
sll->sll_ifindex = orig_dev->ifindex;
|
|
|
|
else
|
|
|
|
sll->sll_ifindex = dev->ifindex;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-09-27 05:13:38 +00:00
|
|
|
sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-02-05 07:33:10 +00:00
|
|
|
PACKET_SKB_CB(skb)->origlen = skb->len;
|
2007-02-05 07:31:32 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (pskb_trim(skb, snaplen))
|
|
|
|
goto drop_n_acct;
|
|
|
|
|
|
|
|
skb_set_owner_r(skb, sk);
|
|
|
|
skb->dev = NULL;
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2005-07-12 18:57:52 +00:00
|
|
|
/* drop conntrack reference */
|
|
|
|
nf_reset(skb);
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
spin_lock(&sk->sk_receive_queue.lock);
|
|
|
|
po->stats.tp_packets++;
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
|
|
|
skb->dropcount = atomic_read(&sk->sk_drops);
|
2005-04-16 22:20:36 +00:00
|
|
|
__skb_queue_tail(&sk->sk_receive_queue, skb);
|
|
|
|
spin_unlock(&sk->sk_receive_queue.lock);
|
|
|
|
sk->sk_data_ready(sk, skb->len);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
drop_n_acct:
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
|
|
|
po->stats.tp_drops = atomic_inc_return(&sk->sk_drops);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
drop_n_restore:
|
|
|
|
if (skb_head != skb->data && skb_shared(skb)) {
|
|
|
|
skb->data = skb_head;
|
|
|
|
skb->len = skb_len;
|
|
|
|
}
|
|
|
|
drop:
|
2009-03-11 09:49:55 +00:00
|
|
|
consume_skb(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
|
|
|
|
struct packet_type *pt, struct net_device *orig_dev)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
struct packet_sock *po;
|
|
|
|
struct sockaddr_ll *sll;
|
2008-07-15 05:50:15 +00:00
|
|
|
union {
|
|
|
|
struct tpacket_hdr *h1;
|
|
|
|
struct tpacket2_hdr *h2;
|
|
|
|
void *raw;
|
|
|
|
} h;
|
2009-07-21 21:57:59 +00:00
|
|
|
u8 *skb_head = skb->data;
|
2005-04-16 22:20:36 +00:00
|
|
|
int skb_len = skb->len;
|
2007-01-24 23:21:02 +00:00
|
|
|
unsigned int snaplen, res;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER;
|
2008-07-15 05:50:15 +00:00
|
|
|
unsigned short macoff, netoff, hdrlen;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct sk_buff *copy_skb = NULL;
|
2007-04-19 23:16:32 +00:00
|
|
|
struct timeval tv;
|
2008-07-15 05:50:15 +00:00
|
|
|
struct timespec ts;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (skb->pkt_type == PACKET_LOOPBACK)
|
|
|
|
goto drop;
|
|
|
|
|
|
|
|
sk = pt->af_packet_priv;
|
|
|
|
po = pkt_sk(sk);
|
|
|
|
|
2009-11-25 23:14:13 +00:00
|
|
|
if (!net_eq(dev_net(dev), sock_net(sk)))
|
2007-11-20 06:28:35 +00:00
|
|
|
goto drop;
|
|
|
|
|
2007-10-09 08:40:57 +00:00
|
|
|
if (dev->header_ops) {
|
2005-04-16 22:20:36 +00:00
|
|
|
if (sk->sk_type != SOCK_DGRAM)
|
2007-03-19 22:33:04 +00:00
|
|
|
skb_push(skb, skb->data - skb_mac_header(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
else if (skb->pkt_type == PACKET_OUTGOING) {
|
|
|
|
/* Special case: outgoing packets have ll header at head */
|
2007-03-11 01:16:10 +00:00
|
|
|
skb_pull(skb, skb_network_offset(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-02-05 07:31:32 +00:00
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL)
|
|
|
|
status |= TP_STATUS_CSUMNOTREADY;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
snaplen = skb->len;
|
|
|
|
|
2007-01-24 23:21:02 +00:00
|
|
|
res = run_filter(skb, sk, snaplen);
|
|
|
|
if (!res)
|
2006-08-31 22:28:39 +00:00
|
|
|
goto drop_n_restore;
|
2007-01-24 23:21:02 +00:00
|
|
|
if (snaplen > res)
|
|
|
|
snaplen = res;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (sk->sk_type == SOCK_DGRAM) {
|
2008-07-19 01:05:19 +00:00
|
|
|
macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 +
|
|
|
|
po->tp_reserve;
|
2005-04-16 22:20:36 +00:00
|
|
|
} else {
|
2007-03-11 01:16:10 +00:00
|
|
|
unsigned maclen = skb_network_offset(skb);
|
2008-07-15 05:50:15 +00:00
|
|
|
netoff = TPACKET_ALIGN(po->tp_hdrlen +
|
2008-07-19 01:05:19 +00:00
|
|
|
(maclen < 16 ? 16 : maclen)) +
|
|
|
|
po->tp_reserve;
|
2005-04-16 22:20:36 +00:00
|
|
|
macoff = netoff - maclen;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
if (macoff + snaplen > po->rx_ring.frame_size) {
|
2005-04-16 22:20:36 +00:00
|
|
|
if (po->copy_thresh &&
|
|
|
|
atomic_read(&sk->sk_rmem_alloc) + skb->truesize <
|
|
|
|
(unsigned)sk->sk_rcvbuf) {
|
|
|
|
if (skb_shared(skb)) {
|
|
|
|
copy_skb = skb_clone(skb, GFP_ATOMIC);
|
|
|
|
} else {
|
|
|
|
copy_skb = skb_get(skb);
|
|
|
|
skb_head = skb->data;
|
|
|
|
}
|
|
|
|
if (copy_skb)
|
|
|
|
skb_set_owner_r(copy_skb, sk);
|
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
snaplen = po->rx_ring.frame_size - macoff;
|
2005-04-16 22:20:36 +00:00
|
|
|
if ((int)snaplen < 0)
|
|
|
|
snaplen = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_lock(&sk->sk_receive_queue.lock);
|
2009-05-19 05:11:22 +00:00
|
|
|
h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL);
|
2008-07-15 05:50:15 +00:00
|
|
|
if (!h.raw)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto ring_is_full;
|
2009-05-19 05:11:22 +00:00
|
|
|
packet_increment_head(&po->rx_ring);
|
2005-04-16 22:20:36 +00:00
|
|
|
po->stats.tp_packets++;
|
|
|
|
if (copy_skb) {
|
|
|
|
status |= TP_STATUS_COPY;
|
|
|
|
__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
|
|
|
|
}
|
|
|
|
if (!po->stats.tp_drops)
|
|
|
|
status &= ~TP_STATUS_LOSING;
|
|
|
|
spin_unlock(&sk->sk_receive_queue.lock);
|
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
switch (po->tp_version) {
|
|
|
|
case TPACKET_V1:
|
|
|
|
h.h1->tp_len = skb->len;
|
|
|
|
h.h1->tp_snaplen = snaplen;
|
|
|
|
h.h1->tp_mac = macoff;
|
|
|
|
h.h1->tp_net = netoff;
|
|
|
|
if (skb->tstamp.tv64)
|
|
|
|
tv = ktime_to_timeval(skb->tstamp);
|
|
|
|
else
|
|
|
|
do_gettimeofday(&tv);
|
|
|
|
h.h1->tp_sec = tv.tv_sec;
|
|
|
|
h.h1->tp_usec = tv.tv_usec;
|
|
|
|
hdrlen = sizeof(*h.h1);
|
|
|
|
break;
|
|
|
|
case TPACKET_V2:
|
|
|
|
h.h2->tp_len = skb->len;
|
|
|
|
h.h2->tp_snaplen = snaplen;
|
|
|
|
h.h2->tp_mac = macoff;
|
|
|
|
h.h2->tp_net = netoff;
|
|
|
|
if (skb->tstamp.tv64)
|
|
|
|
ts = ktime_to_timespec(skb->tstamp);
|
|
|
|
else
|
|
|
|
getnstimeofday(&ts);
|
|
|
|
h.h2->tp_sec = ts.tv_sec;
|
|
|
|
h.h2->tp_nsec = ts.tv_nsec;
|
2009-10-27 01:40:35 +00:00
|
|
|
h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
|
2008-07-15 05:50:15 +00:00
|
|
|
hdrlen = sizeof(*h.h2);
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
sll = h.raw + TPACKET_ALIGN(hdrlen);
|
2007-09-27 05:13:38 +00:00
|
|
|
sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
|
2005-04-16 22:20:36 +00:00
|
|
|
sll->sll_family = AF_PACKET;
|
|
|
|
sll->sll_hatype = dev->type;
|
|
|
|
sll->sll_protocol = skb->protocol;
|
|
|
|
sll->sll_pkttype = skb->pkt_type;
|
2007-11-11 06:03:25 +00:00
|
|
|
if (unlikely(po->origdev))
|
2007-04-20 23:05:39 +00:00
|
|
|
sll->sll_ifindex = orig_dev->ifindex;
|
|
|
|
else
|
|
|
|
sll->sll_ifindex = dev->ifindex;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
__packet_set_status(po, h.raw, status);
|
2006-12-07 08:11:33 +00:00
|
|
|
smp_mb();
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct page *p_start, *p_end;
|
2008-07-15 05:50:15 +00:00
|
|
|
u8 *h_end = h.raw + macoff + snaplen - 1;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
p_start = virt_to_page(h.raw);
|
2005-04-16 22:20:36 +00:00
|
|
|
p_end = virt_to_page(h_end);
|
|
|
|
while (p_start <= p_end) {
|
|
|
|
flush_dcache_page(p_start);
|
|
|
|
p_start++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
sk->sk_data_ready(sk, 0);
|
|
|
|
|
|
|
|
drop_n_restore:
|
|
|
|
if (skb_head != skb->data && skb_shared(skb)) {
|
|
|
|
skb->data = skb_head;
|
|
|
|
skb->len = skb_len;
|
|
|
|
}
|
|
|
|
drop:
|
2007-02-09 14:25:10 +00:00
|
|
|
kfree_skb(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
ring_is_full:
|
|
|
|
po->stats.tp_drops++;
|
|
|
|
spin_unlock(&sk->sk_receive_queue.lock);
|
|
|
|
|
|
|
|
sk->sk_data_ready(sk, 0);
|
2009-02-25 00:36:42 +00:00
|
|
|
kfree_skb(copy_skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto drop_n_restore;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static void tpacket_destruct_skb(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct packet_sock *po = pkt_sk(skb->sk);
|
2009-07-21 21:57:59 +00:00
|
|
|
void *ph;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
BUG_ON(skb == NULL);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
if (likely(po->tx_ring.pg_vec)) {
|
|
|
|
ph = skb_shinfo(skb)->destructor_arg;
|
|
|
|
BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING);
|
|
|
|
BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
|
|
|
|
atomic_dec(&po->tx_ring.pending);
|
|
|
|
__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
|
|
|
|
}
|
|
|
|
|
|
|
|
sock_wfree(skb);
|
|
|
|
}
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
|
|
|
|
void *frame, struct net_device *dev, int size_max,
|
|
|
|
__be16 proto, unsigned char *addr)
|
2009-05-19 05:11:22 +00:00
|
|
|
{
|
|
|
|
union {
|
|
|
|
struct tpacket_hdr *h1;
|
|
|
|
struct tpacket2_hdr *h2;
|
|
|
|
void *raw;
|
|
|
|
} ph;
|
|
|
|
int to_write, offset, len, tp_len, nr_frags, len_max;
|
|
|
|
struct socket *sock = po->sk.sk_socket;
|
|
|
|
struct page *page;
|
|
|
|
void *data;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
ph.raw = frame;
|
|
|
|
|
|
|
|
skb->protocol = proto;
|
|
|
|
skb->dev = dev;
|
|
|
|
skb->priority = po->sk.sk_priority;
|
2009-10-01 19:14:46 +00:00
|
|
|
skb->mark = po->sk.sk_mark;
|
2009-05-19 05:11:22 +00:00
|
|
|
skb_shinfo(skb)->destructor_arg = ph.raw;
|
|
|
|
|
|
|
|
switch (po->tp_version) {
|
|
|
|
case TPACKET_V2:
|
|
|
|
tp_len = ph.h2->tp_len;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
tp_len = ph.h1->tp_len;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (unlikely(tp_len > size_max)) {
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("packet size is too long (%d > %d)\n", tp_len, size_max);
|
2009-05-19 05:11:22 +00:00
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
|
|
|
|
|
|
|
skb_reserve(skb, LL_RESERVED_SPACE(dev));
|
|
|
|
skb_reset_network_header(skb);
|
|
|
|
|
|
|
|
data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
|
|
|
|
to_write = tp_len;
|
|
|
|
|
|
|
|
if (sock->type == SOCK_DGRAM) {
|
|
|
|
err = dev_hard_header(skb, dev, ntohs(proto), addr,
|
|
|
|
NULL, tp_len);
|
|
|
|
if (unlikely(err < 0))
|
|
|
|
return -EINVAL;
|
2009-07-21 21:57:59 +00:00
|
|
|
} else if (dev->hard_header_len) {
|
2009-05-19 05:11:22 +00:00
|
|
|
/* net device doesn't like empty head */
|
|
|
|
if (unlikely(tp_len <= dev->hard_header_len)) {
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("packet size is too short (%d < %d)\n",
|
|
|
|
tp_len, dev->hard_header_len);
|
2009-05-19 05:11:22 +00:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
skb_push(skb, dev->hard_header_len);
|
|
|
|
err = skb_store_bits(skb, 0, data,
|
|
|
|
dev->hard_header_len);
|
|
|
|
if (unlikely(err))
|
|
|
|
return err;
|
|
|
|
|
|
|
|
data += dev->hard_header_len;
|
|
|
|
to_write -= dev->hard_header_len;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = -EFAULT;
|
|
|
|
page = virt_to_page(data);
|
|
|
|
offset = offset_in_page(data);
|
|
|
|
len_max = PAGE_SIZE - offset;
|
|
|
|
len = ((to_write > len_max) ? len_max : to_write);
|
|
|
|
|
|
|
|
skb->data_len = to_write;
|
|
|
|
skb->len += to_write;
|
|
|
|
skb->truesize += to_write;
|
|
|
|
atomic_add(to_write, &po->sk.sk_wmem_alloc);
|
|
|
|
|
|
|
|
while (likely(to_write)) {
|
|
|
|
nr_frags = skb_shinfo(skb)->nr_frags;
|
|
|
|
|
|
|
|
if (unlikely(nr_frags >= MAX_SKB_FRAGS)) {
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("Packet exceed the number of skb frags(%lu)\n",
|
|
|
|
MAX_SKB_FRAGS);
|
2009-05-19 05:11:22 +00:00
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
|
|
|
|
flush_dcache_page(page);
|
|
|
|
get_page(page);
|
|
|
|
skb_fill_page_desc(skb,
|
|
|
|
nr_frags,
|
|
|
|
page++, offset, len);
|
|
|
|
to_write -= len;
|
|
|
|
offset = 0;
|
|
|
|
len_max = PAGE_SIZE;
|
|
|
|
len = ((to_write > len_max) ? len_max : to_write);
|
|
|
|
}
|
|
|
|
|
|
|
|
return tp_len;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
|
|
|
|
{
|
|
|
|
struct socket *sock;
|
|
|
|
struct sk_buff *skb;
|
|
|
|
struct net_device *dev;
|
|
|
|
__be16 proto;
|
|
|
|
int ifindex, err, reserve = 0;
|
2009-07-21 21:57:59 +00:00
|
|
|
void *ph;
|
|
|
|
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
|
2009-05-19 05:11:22 +00:00
|
|
|
int tp_len, size_max;
|
|
|
|
unsigned char *addr;
|
|
|
|
int len_sum = 0;
|
|
|
|
int status = 0;
|
|
|
|
|
|
|
|
sock = po->sk.sk_socket;
|
|
|
|
|
|
|
|
mutex_lock(&po->pg_vec_lock);
|
|
|
|
|
|
|
|
err = -EBUSY;
|
|
|
|
if (saddr == NULL) {
|
|
|
|
ifindex = po->ifindex;
|
|
|
|
proto = po->num;
|
|
|
|
addr = NULL;
|
|
|
|
} else {
|
|
|
|
err = -EINVAL;
|
|
|
|
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
|
|
|
|
goto out;
|
|
|
|
if (msg->msg_namelen < (saddr->sll_halen
|
|
|
|
+ offsetof(struct sockaddr_ll,
|
|
|
|
sll_addr)))
|
|
|
|
goto out;
|
|
|
|
ifindex = saddr->sll_ifindex;
|
|
|
|
proto = saddr->sll_protocol;
|
|
|
|
addr = saddr->sll_addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
dev = dev_get_by_index(sock_net(&po->sk), ifindex);
|
|
|
|
err = -ENXIO;
|
|
|
|
if (unlikely(dev == NULL))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
reserve = dev->hard_header_len;
|
|
|
|
|
|
|
|
err = -ENETDOWN;
|
|
|
|
if (unlikely(!(dev->flags & IFF_UP)))
|
|
|
|
goto out_put;
|
|
|
|
|
|
|
|
size_max = po->tx_ring.frame_size
|
2009-10-29 10:19:11 +00:00
|
|
|
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
if (size_max > dev->mtu + reserve)
|
|
|
|
size_max = dev->mtu + reserve;
|
|
|
|
|
|
|
|
do {
|
|
|
|
ph = packet_current_frame(po, &po->tx_ring,
|
|
|
|
TP_STATUS_SEND_REQUEST);
|
|
|
|
|
|
|
|
if (unlikely(ph == NULL)) {
|
|
|
|
schedule();
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
status = TP_STATUS_SEND_REQUEST;
|
|
|
|
skb = sock_alloc_send_skb(&po->sk,
|
|
|
|
LL_ALLOCATED_SPACE(dev)
|
|
|
|
+ sizeof(struct sockaddr_ll),
|
|
|
|
0, &err);
|
|
|
|
|
|
|
|
if (unlikely(skb == NULL))
|
|
|
|
goto out_status;
|
|
|
|
|
|
|
|
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
|
|
|
|
addr);
|
|
|
|
|
|
|
|
if (unlikely(tp_len < 0)) {
|
|
|
|
if (po->tp_loss) {
|
|
|
|
__packet_set_status(po, ph,
|
|
|
|
TP_STATUS_AVAILABLE);
|
|
|
|
packet_increment_head(&po->tx_ring);
|
|
|
|
kfree_skb(skb);
|
|
|
|
continue;
|
|
|
|
} else {
|
|
|
|
status = TP_STATUS_WRONG_FORMAT;
|
|
|
|
err = tp_len;
|
|
|
|
goto out_status;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
skb->destructor = tpacket_destruct_skb;
|
|
|
|
__packet_set_status(po, ph, TP_STATUS_SENDING);
|
|
|
|
atomic_inc(&po->tx_ring.pending);
|
|
|
|
|
|
|
|
status = TP_STATUS_SEND_REQUEST;
|
|
|
|
err = dev_queue_xmit(skb);
|
2010-01-10 22:04:19 +00:00
|
|
|
if (unlikely(err > 0)) {
|
|
|
|
err = net_xmit_errno(err);
|
|
|
|
if (err && __packet_get_status(po, ph) ==
|
|
|
|
TP_STATUS_AVAILABLE) {
|
|
|
|
/* skb was destructed already */
|
|
|
|
skb = NULL;
|
|
|
|
goto out_status;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* skb was dropped but not destructed yet;
|
|
|
|
* let's treat it like congestion or err < 0
|
|
|
|
*/
|
|
|
|
err = 0;
|
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
packet_increment_head(&po->tx_ring);
|
|
|
|
len_sum += tp_len;
|
2009-11-30 00:55:45 +00:00
|
|
|
} while (likely((ph != NULL) ||
|
|
|
|
((!(msg->msg_flags & MSG_DONTWAIT)) &&
|
|
|
|
(atomic_read(&po->tx_ring.pending))))
|
|
|
|
);
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
err = len_sum;
|
|
|
|
goto out_put;
|
|
|
|
|
|
|
|
out_status:
|
|
|
|
__packet_set_status(po, ph, status);
|
|
|
|
kfree_skb(skb);
|
|
|
|
out_put:
|
|
|
|
dev_put(dev);
|
|
|
|
out:
|
|
|
|
mutex_unlock(&po->pg_vec_lock);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
static inline struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
|
|
|
|
size_t reserve, size_t len,
|
|
|
|
size_t linear, int noblock,
|
|
|
|
int *err)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
|
|
|
/* Under a page? Don't bother with paged skb. */
|
|
|
|
if (prepad + len < PAGE_SIZE || !linear)
|
|
|
|
linear = len;
|
|
|
|
|
|
|
|
skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
|
|
|
|
err);
|
|
|
|
if (!skb)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
skb_reserve(skb, reserve);
|
|
|
|
skb_put(skb, linear);
|
|
|
|
skb->data_len = len - linear;
|
|
|
|
skb->len += len - linear;
|
|
|
|
|
|
|
|
return skb;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int packet_snd(struct socket *sock,
|
2005-04-16 22:20:36 +00:00
|
|
|
struct msghdr *msg, size_t len)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
2009-07-21 21:57:59 +00:00
|
|
|
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct sk_buff *skb;
|
|
|
|
struct net_device *dev;
|
2006-11-08 08:26:29 +00:00
|
|
|
__be16 proto;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned char *addr;
|
|
|
|
int ifindex, err, reserve = 0;
|
2010-02-05 04:24:10 +00:00
|
|
|
struct virtio_net_hdr vnet_hdr = { 0 };
|
|
|
|
int offset = 0;
|
|
|
|
int vnet_hdr_len;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
unsigned short gso_type = 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
2007-02-09 14:25:10 +00:00
|
|
|
* Get and verify the address.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (saddr == NULL) {
|
|
|
|
ifindex = po->ifindex;
|
|
|
|
proto = po->num;
|
|
|
|
addr = NULL;
|
|
|
|
} else {
|
|
|
|
err = -EINVAL;
|
|
|
|
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
|
|
|
|
goto out;
|
2005-09-21 07:11:37 +00:00
|
|
|
if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
|
|
|
|
goto out;
|
2005-04-16 22:20:36 +00:00
|
|
|
ifindex = saddr->sll_ifindex;
|
|
|
|
proto = saddr->sll_protocol;
|
|
|
|
addr = saddr->sll_addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2008-03-25 17:26:21 +00:00
|
|
|
dev = dev_get_by_index(sock_net(sk), ifindex);
|
2005-04-16 22:20:36 +00:00
|
|
|
err = -ENXIO;
|
|
|
|
if (dev == NULL)
|
|
|
|
goto out_unlock;
|
|
|
|
if (sock->type == SOCK_RAW)
|
|
|
|
reserve = dev->hard_header_len;
|
|
|
|
|
2007-01-26 03:30:36 +00:00
|
|
|
err = -ENETDOWN;
|
|
|
|
if (!(dev->flags & IFF_UP))
|
|
|
|
goto out_unlock;
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
if (po->has_vnet_hdr) {
|
|
|
|
vnet_hdr_len = sizeof(vnet_hdr);
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (len < vnet_hdr_len)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
len -= vnet_hdr_len;
|
|
|
|
|
|
|
|
err = memcpy_fromiovec((void *)&vnet_hdr, msg->msg_iov,
|
|
|
|
vnet_hdr_len);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
|
|
|
|
(vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
|
|
|
|
vnet_hdr.hdr_len))
|
|
|
|
vnet_hdr.hdr_len = vnet_hdr.csum_start +
|
|
|
|
vnet_hdr.csum_offset + 2;
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (vnet_hdr.hdr_len > len)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
|
|
|
|
switch (vnet_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
|
|
|
|
case VIRTIO_NET_HDR_GSO_TCPV4:
|
|
|
|
gso_type = SKB_GSO_TCPV4;
|
|
|
|
break;
|
|
|
|
case VIRTIO_NET_HDR_GSO_TCPV6:
|
|
|
|
gso_type = SKB_GSO_TCPV6;
|
|
|
|
break;
|
|
|
|
case VIRTIO_NET_HDR_GSO_UDP:
|
|
|
|
gso_type = SKB_GSO_UDP;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (vnet_hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
|
|
|
|
gso_type |= SKB_GSO_TCP_ECN;
|
|
|
|
|
|
|
|
if (vnet_hdr.gso_size == 0)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
err = -EMSGSIZE;
|
2010-02-05 04:24:10 +00:00
|
|
|
if (!gso_type && (len > dev->mtu+reserve))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out_unlock;
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
err = -ENOBUFS;
|
|
|
|
skb = packet_alloc_skb(sk, LL_ALLOCATED_SPACE(dev),
|
|
|
|
LL_RESERVED_SPACE(dev), len, vnet_hdr.hdr_len,
|
|
|
|
msg->msg_flags & MSG_DONTWAIT, &err);
|
2009-07-21 21:57:59 +00:00
|
|
|
if (skb == NULL)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out_unlock;
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
skb_set_network_header(skb, reserve);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-10-09 08:36:32 +00:00
|
|
|
err = -EINVAL;
|
|
|
|
if (sock->type == SOCK_DGRAM &&
|
2010-02-05 04:24:10 +00:00
|
|
|
(offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len)) < 0)
|
2007-10-09 08:36:32 +00:00
|
|
|
goto out_free;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* Returns -EFAULT on error */
|
2010-02-05 04:24:10 +00:00
|
|
|
err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (err)
|
|
|
|
goto out_free;
|
|
|
|
|
|
|
|
skb->protocol = proto;
|
|
|
|
skb->dev = dev;
|
|
|
|
skb->priority = sk->sk_priority;
|
2009-10-01 19:14:46 +00:00
|
|
|
skb->mark = sk->sk_mark;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
if (po->has_vnet_hdr) {
|
|
|
|
if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
|
|
|
|
if (!skb_partial_csum_set(skb, vnet_hdr.csum_start,
|
|
|
|
vnet_hdr.csum_offset)) {
|
|
|
|
err = -EINVAL;
|
|
|
|
goto out_free;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
skb_shinfo(skb)->gso_size = vnet_hdr.gso_size;
|
|
|
|
skb_shinfo(skb)->gso_type = gso_type;
|
|
|
|
|
|
|
|
/* Header must be checked, and gso_segs computed. */
|
|
|
|
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
|
|
|
|
skb_shinfo(skb)->gso_segs = 0;
|
|
|
|
|
|
|
|
len += vnet_hdr_len;
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Now send it
|
|
|
|
*/
|
|
|
|
|
|
|
|
err = dev_queue_xmit(skb);
|
|
|
|
if (err > 0 && (err = net_xmit_errno(err)) != 0)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
dev_put(dev);
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
return len;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
out_free:
|
|
|
|
kfree_skb(skb);
|
|
|
|
out_unlock:
|
|
|
|
if (dev)
|
|
|
|
dev_put(dev);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
|
|
|
|
struct msghdr *msg, size_t len)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
if (po->tx_ring.pg_vec)
|
|
|
|
return tpacket_snd(po, msg);
|
|
|
|
else
|
|
|
|
return packet_snd(sock, msg, len);
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Close a PACKET socket. This is fairly simple. We immediately go
|
|
|
|
* to 'closed' state and remove our protocol entry in the device list.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int packet_release(struct socket *sock)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po;
|
2007-11-20 06:28:35 +00:00
|
|
|
struct net *net;
|
2009-05-19 05:11:22 +00:00
|
|
|
struct tpacket_req req;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (!sk)
|
|
|
|
return 0;
|
|
|
|
|
2008-03-25 17:26:21 +00:00
|
|
|
net = sock_net(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
po = pkt_sk(sk);
|
|
|
|
|
2007-12-11 12:19:54 +00:00
|
|
|
write_lock_bh(&net->packet.sklist_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
sk_del_node_init(sk);
|
2008-11-24 08:09:29 +00:00
|
|
|
sock_prot_inuse_add(net, sk->sk_prot, -1);
|
2007-12-11 12:19:54 +00:00
|
|
|
write_unlock_bh(&net->packet.sklist_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Unhook packet receive handler.
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (po->running) {
|
|
|
|
/*
|
|
|
|
* Remove the protocol hook
|
|
|
|
*/
|
|
|
|
dev_remove_pack(&po->prot_hook);
|
|
|
|
po->running = 0;
|
|
|
|
po->num = 0;
|
|
|
|
__sock_put(sk);
|
|
|
|
}
|
|
|
|
|
|
|
|
packet_flush_mclist(sk);
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
memset(&req, 0, sizeof(req));
|
|
|
|
|
|
|
|
if (po->rx_ring.pg_vec)
|
|
|
|
packet_set_ring(sk, &req, 1, 0);
|
|
|
|
|
|
|
|
if (po->tx_ring.pg_vec)
|
|
|
|
packet_set_ring(sk, &req, 1, 1);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Now the socket is dead. No more input will appear.
|
|
|
|
*/
|
|
|
|
|
|
|
|
sock_orphan(sk);
|
|
|
|
sock->sk = NULL;
|
|
|
|
|
|
|
|
/* Purge queues */
|
|
|
|
|
|
|
|
skb_queue_purge(&sk->sk_receive_queue);
|
2007-11-11 05:38:48 +00:00
|
|
|
sk_refcnt_debug_release(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
sock_put(sk);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Attach a packet hook.
|
|
|
|
*/
|
|
|
|
|
2006-11-08 08:26:29 +00:00
|
|
|
static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
/*
|
|
|
|
* Detach an existing hook if present.
|
|
|
|
*/
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
if (po->running) {
|
|
|
|
__sock_put(sk);
|
|
|
|
po->running = 0;
|
|
|
|
po->num = 0;
|
|
|
|
spin_unlock(&po->bind_lock);
|
|
|
|
dev_remove_pack(&po->prot_hook);
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
po->num = protocol;
|
|
|
|
po->prot_hook.type = protocol;
|
|
|
|
po->prot_hook.dev = dev;
|
|
|
|
|
|
|
|
po->ifindex = dev ? dev->ifindex : 0;
|
|
|
|
|
|
|
|
if (protocol == 0)
|
|
|
|
goto out_unlock;
|
|
|
|
|
2007-11-13 05:05:20 +00:00
|
|
|
if (!dev || (dev->flags & IFF_UP)) {
|
2005-04-16 22:20:36 +00:00
|
|
|
dev_add_pack(&po->prot_hook);
|
|
|
|
sock_hold(sk);
|
|
|
|
po->running = 1;
|
2007-11-13 05:05:20 +00:00
|
|
|
} else {
|
|
|
|
sk->sk_err = ENETDOWN;
|
|
|
|
if (!sock_flag(sk, SOCK_DEAD))
|
|
|
|
sk->sk_error_report(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
out_unlock:
|
|
|
|
spin_unlock(&po->bind_lock);
|
|
|
|
release_sock(sk);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Bind a packet socket to a device
|
|
|
|
*/
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
|
|
|
|
int addr_len)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-07-21 21:57:59 +00:00
|
|
|
struct sock *sk = sock->sk;
|
2005-04-16 22:20:36 +00:00
|
|
|
char name[15];
|
|
|
|
struct net_device *dev;
|
|
|
|
int err = -ENODEV;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Check legality
|
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2006-01-24 00:28:02 +00:00
|
|
|
if (addr_len != sizeof(struct sockaddr))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EINVAL;
|
2009-07-21 21:57:59 +00:00
|
|
|
strlcpy(name, uaddr->sa_data, sizeof(name));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-03-25 17:26:21 +00:00
|
|
|
dev = dev_get_by_name(sock_net(sk), name);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (dev) {
|
|
|
|
err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
|
|
|
|
dev_put(dev);
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
|
|
|
|
{
|
2009-07-21 21:57:59 +00:00
|
|
|
struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
|
|
|
|
struct sock *sk = sock->sk;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct net_device *dev = NULL;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check legality
|
|
|
|
*/
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (addr_len < sizeof(struct sockaddr_ll))
|
|
|
|
return -EINVAL;
|
|
|
|
if (sll->sll_family != AF_PACKET)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (sll->sll_ifindex) {
|
|
|
|
err = -ENODEV;
|
2008-03-25 17:26:21 +00:00
|
|
|
dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (dev == NULL)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
|
|
|
|
if (dev)
|
|
|
|
dev_put(dev);
|
|
|
|
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct proto packet_proto = {
|
|
|
|
.name = "PACKET",
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.obj_size = sizeof(struct packet_sock),
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
2007-02-09 14:25:10 +00:00
|
|
|
* Create a packet of type SOCK_PACKET.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
|
2009-11-06 06:18:14 +00:00
|
|
|
static int packet_create(struct net *net, struct socket *sock, int protocol,
|
|
|
|
int kern)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
struct packet_sock *po;
|
2006-11-08 08:26:29 +00:00
|
|
|
__be16 proto = (__force __be16)protocol; /* weird, but documented */
|
2005-04-16 22:20:36 +00:00
|
|
|
int err;
|
|
|
|
|
|
|
|
if (!capable(CAP_NET_RAW))
|
|
|
|
return -EPERM;
|
2007-05-29 20:16:31 +00:00
|
|
|
if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW &&
|
|
|
|
sock->type != SOCK_PACKET)
|
2005-04-16 22:20:36 +00:00
|
|
|
return -ESOCKTNOSUPPORT;
|
|
|
|
|
|
|
|
sock->state = SS_UNCONNECTED;
|
|
|
|
|
|
|
|
err = -ENOBUFS;
|
2007-11-01 07:39:31 +00:00
|
|
|
sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (sk == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
sock->ops = &packet_ops;
|
|
|
|
if (sock->type == SOCK_PACKET)
|
|
|
|
sock->ops = &packet_ops_spkt;
|
2007-05-29 20:16:31 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
sock_init_data(sock, sk);
|
|
|
|
|
|
|
|
po = pkt_sk(sk);
|
|
|
|
sk->sk_family = PF_PACKET;
|
2006-11-08 08:26:29 +00:00
|
|
|
po->num = proto;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
sk->sk_destruct = packet_sock_destruct;
|
2007-11-11 05:38:48 +00:00
|
|
|
sk_refcnt_debug_inc(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Attach a protocol block
|
|
|
|
*/
|
|
|
|
|
|
|
|
spin_lock_init(&po->bind_lock);
|
2009-01-30 22:12:06 +00:00
|
|
|
mutex_init(&po->pg_vec_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
po->prot_hook.func = packet_rcv;
|
2007-05-29 20:16:31 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (sock->type == SOCK_PACKET)
|
|
|
|
po->prot_hook.func = packet_rcv_spkt;
|
2007-05-29 20:16:31 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
po->prot_hook.af_packet_priv = sk;
|
|
|
|
|
2006-11-08 08:26:29 +00:00
|
|
|
if (proto) {
|
|
|
|
po->prot_hook.type = proto;
|
2005-04-16 22:20:36 +00:00
|
|
|
dev_add_pack(&po->prot_hook);
|
|
|
|
sock_hold(sk);
|
|
|
|
po->running = 1;
|
|
|
|
}
|
|
|
|
|
2007-12-11 12:19:54 +00:00
|
|
|
write_lock_bh(&net->packet.sklist_lock);
|
|
|
|
sk_add_node(sk, &net->packet.sklist);
|
2008-11-19 22:25:35 +00:00
|
|
|
sock_prot_inuse_add(net, &packet_proto, 1);
|
2008-11-24 08:09:29 +00:00
|
|
|
write_unlock_bh(&net->packet.sklist_lock);
|
2009-07-21 21:57:59 +00:00
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Pull a packet from our receive queue and hand it to the user.
|
|
|
|
* If necessary we block.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
|
|
|
|
struct msghdr *msg, size_t len, int flags)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int copied, err;
|
2005-09-21 07:11:37 +00:00
|
|
|
struct sockaddr_ll *sll;
|
2010-02-05 04:24:10 +00:00
|
|
|
int vnet_hdr_len = 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
#if 0
|
|
|
|
/* What error should we return now? EUNATTACH? */
|
|
|
|
if (pkt_sk(sk)->ifindex < 0)
|
|
|
|
return -ENODEV;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call the generic datagram receiver. This handles all sorts
|
|
|
|
* of horrible races and re-entrancy so we can forget about it
|
|
|
|
* in the protocol layers.
|
|
|
|
*
|
|
|
|
* Now it will return ENETDOWN, if device have just gone down,
|
|
|
|
* but then it will block.
|
|
|
|
*/
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
2007-02-09 14:25:10 +00:00
|
|
|
* An error occurred so return it. Because skb_recv_datagram()
|
2005-04-16 22:20:36 +00:00
|
|
|
* handles the blocking we don't see and worry about blocking
|
|
|
|
* retries.
|
|
|
|
*/
|
|
|
|
|
2006-01-24 00:28:02 +00:00
|
|
|
if (skb == NULL)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out;
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
if (pkt_sk(sk)->has_vnet_hdr) {
|
|
|
|
struct virtio_net_hdr vnet_hdr = { 0 };
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
vnet_hdr_len = sizeof(vnet_hdr);
|
|
|
|
if ((len -= vnet_hdr_len) < 0)
|
|
|
|
goto out_free;
|
|
|
|
|
|
|
|
if (skb_is_gso(skb)) {
|
|
|
|
struct skb_shared_info *sinfo = skb_shinfo(skb);
|
|
|
|
|
|
|
|
/* This is a hint as to how much should be linear. */
|
|
|
|
vnet_hdr.hdr_len = skb_headlen(skb);
|
|
|
|
vnet_hdr.gso_size = sinfo->gso_size;
|
|
|
|
if (sinfo->gso_type & SKB_GSO_TCPV4)
|
|
|
|
vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
|
|
|
|
else if (sinfo->gso_type & SKB_GSO_TCPV6)
|
|
|
|
vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
|
|
|
|
else if (sinfo->gso_type & SKB_GSO_UDP)
|
|
|
|
vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
|
|
|
|
else if (sinfo->gso_type & SKB_GSO_FCOE)
|
|
|
|
goto out_free;
|
|
|
|
else
|
|
|
|
BUG();
|
|
|
|
if (sinfo->gso_type & SKB_GSO_TCP_ECN)
|
|
|
|
vnet_hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
|
|
|
|
} else
|
|
|
|
vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
|
|
|
|
|
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL) {
|
|
|
|
vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
|
|
|
|
vnet_hdr.csum_start = skb->csum_start -
|
|
|
|
skb_headroom(skb);
|
|
|
|
vnet_hdr.csum_offset = skb->csum_offset;
|
|
|
|
} /* else everything is zero */
|
|
|
|
|
|
|
|
err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr,
|
|
|
|
vnet_hdr_len);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_free;
|
|
|
|
}
|
|
|
|
|
2005-09-21 07:11:37 +00:00
|
|
|
/*
|
|
|
|
* If the address length field is there to be filled in, we fill
|
|
|
|
* it in now.
|
|
|
|
*/
|
|
|
|
|
2007-02-05 07:33:10 +00:00
|
|
|
sll = &PACKET_SKB_CB(skb)->sa.ll;
|
2005-09-21 07:11:37 +00:00
|
|
|
if (sock->type == SOCK_PACKET)
|
|
|
|
msg->msg_namelen = sizeof(struct sockaddr_pkt);
|
|
|
|
else
|
|
|
|
msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* You lose any data beyond the buffer you gave. If it worries a
|
|
|
|
* user program they can ask the device for its MTU anyway.
|
|
|
|
*/
|
|
|
|
|
|
|
|
copied = skb->len;
|
2009-07-21 21:57:59 +00:00
|
|
|
if (copied > len) {
|
|
|
|
copied = len;
|
|
|
|
msg->msg_flags |= MSG_TRUNC;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
|
|
|
|
if (err)
|
|
|
|
goto out_free;
|
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
|
|
|
sock_recv_ts_and_drops(msg, sk, skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (msg->msg_name)
|
2007-02-05 07:33:10 +00:00
|
|
|
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
|
|
|
|
msg->msg_namelen);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-02-05 07:31:32 +00:00
|
|
|
if (pkt_sk(sk)->auxdata) {
|
2007-02-05 07:33:10 +00:00
|
|
|
struct tpacket_auxdata aux;
|
|
|
|
|
|
|
|
aux.tp_status = TP_STATUS_USER;
|
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL)
|
|
|
|
aux.tp_status |= TP_STATUS_CSUMNOTREADY;
|
|
|
|
aux.tp_len = PACKET_SKB_CB(skb)->origlen;
|
|
|
|
aux.tp_snaplen = skb->len;
|
|
|
|
aux.tp_mac = 0;
|
2007-03-11 01:16:10 +00:00
|
|
|
aux.tp_net = skb_network_offset(skb);
|
2009-10-27 01:40:35 +00:00
|
|
|
aux.tp_vlan_tci = vlan_tx_tag_get(skb);
|
2007-02-05 07:33:10 +00:00
|
|
|
|
|
|
|
put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
|
2007-02-05 07:31:32 +00:00
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Free or return the buffer as appropriate. Again this
|
|
|
|
* hides all the races and re-entrancy issues from us.
|
|
|
|
*/
|
2010-02-05 04:24:10 +00:00
|
|
|
err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
out_free:
|
|
|
|
skb_free_datagram(sk, skb);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
|
|
|
|
int *uaddr_len, int peer)
|
|
|
|
{
|
|
|
|
struct net_device *dev;
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
|
|
|
|
if (peer)
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
uaddr->sa_family = AF_PACKET;
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_lock();
|
|
|
|
dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex);
|
|
|
|
if (dev)
|
2005-04-16 22:20:36 +00:00
|
|
|
strlcpy(uaddr->sa_data, dev->name, 15);
|
2009-11-02 09:43:32 +00:00
|
|
|
else
|
2005-04-16 22:20:36 +00:00
|
|
|
memset(uaddr->sa_data, 0, 14);
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_unlock();
|
2005-04-16 22:20:36 +00:00
|
|
|
*uaddr_len = sizeof(*uaddr);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
|
|
|
|
int *uaddr_len, int peer)
|
|
|
|
{
|
|
|
|
struct net_device *dev;
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
2009-11-08 05:51:19 +00:00
|
|
|
DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (peer)
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
sll->sll_family = AF_PACKET;
|
|
|
|
sll->sll_ifindex = po->ifindex;
|
|
|
|
sll->sll_protocol = po->num;
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_lock();
|
|
|
|
dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (dev) {
|
|
|
|
sll->sll_hatype = dev->type;
|
|
|
|
sll->sll_halen = dev->addr_len;
|
|
|
|
memcpy(sll->sll_addr, dev->dev_addr, dev->addr_len);
|
|
|
|
} else {
|
|
|
|
sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */
|
|
|
|
sll->sll_halen = 0;
|
|
|
|
}
|
2009-11-02 09:43:32 +00:00
|
|
|
rcu_read_unlock();
|
2005-09-21 07:11:37 +00:00
|
|
|
*uaddr_len = offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-07-15 03:49:46 +00:00
|
|
|
static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i,
|
|
|
|
int what)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
switch (i->type) {
|
|
|
|
case PACKET_MR_MULTICAST:
|
|
|
|
if (what > 0)
|
2009-05-19 18:27:17 +00:00
|
|
|
return dev_mc_add(dev, i->addr, i->alen, 0);
|
2005-04-16 22:20:36 +00:00
|
|
|
else
|
2009-05-19 18:27:17 +00:00
|
|
|
return dev_mc_delete(dev, i->addr, i->alen, 0);
|
2005-04-16 22:20:36 +00:00
|
|
|
break;
|
|
|
|
case PACKET_MR_PROMISC:
|
2008-07-15 03:49:46 +00:00
|
|
|
return dev_set_promiscuity(dev, what);
|
2005-04-16 22:20:36 +00:00
|
|
|
break;
|
|
|
|
case PACKET_MR_ALLMULTI:
|
2008-07-15 03:49:46 +00:00
|
|
|
return dev_set_allmulti(dev, what);
|
2005-04-16 22:20:36 +00:00
|
|
|
break;
|
2009-05-19 18:27:17 +00:00
|
|
|
case PACKET_MR_UNICAST:
|
|
|
|
if (what > 0)
|
2009-05-22 23:22:17 +00:00
|
|
|
return dev_unicast_add(dev, i->addr);
|
2009-05-19 18:27:17 +00:00
|
|
|
else
|
2009-05-22 23:22:17 +00:00
|
|
|
return dev_unicast_delete(dev, i->addr);
|
2009-05-19 18:27:17 +00:00
|
|
|
break;
|
2009-07-21 21:57:59 +00:00
|
|
|
default:
|
|
|
|
break;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2008-07-15 03:49:46 +00:00
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what)
|
|
|
|
{
|
2009-07-21 21:57:59 +00:00
|
|
|
for ( ; i; i = i->next) {
|
2005-04-16 22:20:36 +00:00
|
|
|
if (i->ifindex == dev->ifindex)
|
|
|
|
packet_dev_mc(dev, i, what);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-09-21 07:11:37 +00:00
|
|
|
static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
struct packet_mclist *ml, *i;
|
|
|
|
struct net_device *dev;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
rtnl_lock();
|
|
|
|
|
|
|
|
err = -ENODEV;
|
2008-03-25 17:26:21 +00:00
|
|
|
dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (!dev)
|
|
|
|
goto done;
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (mreq->mr_alen > dev->addr_len)
|
|
|
|
goto done;
|
|
|
|
|
|
|
|
err = -ENOBUFS;
|
2006-01-11 23:56:43 +00:00
|
|
|
i = kmalloc(sizeof(*i), GFP_KERNEL);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (i == NULL)
|
|
|
|
goto done;
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
for (ml = po->mclist; ml; ml = ml->next) {
|
|
|
|
if (ml->ifindex == mreq->mr_ifindex &&
|
|
|
|
ml->type == mreq->mr_type &&
|
|
|
|
ml->alen == mreq->mr_alen &&
|
|
|
|
memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
|
|
|
|
ml->count++;
|
|
|
|
/* Free the new element ... */
|
|
|
|
kfree(i);
|
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
i->type = mreq->mr_type;
|
|
|
|
i->ifindex = mreq->mr_ifindex;
|
|
|
|
i->alen = mreq->mr_alen;
|
|
|
|
memcpy(i->addr, mreq->mr_address, i->alen);
|
|
|
|
i->count = 1;
|
|
|
|
i->next = po->mclist;
|
|
|
|
po->mclist = i;
|
2008-07-15 03:49:46 +00:00
|
|
|
err = packet_dev_mc(dev, i, 1);
|
|
|
|
if (err) {
|
|
|
|
po->mclist = i->next;
|
|
|
|
kfree(i);
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
done:
|
|
|
|
rtnl_unlock();
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2005-09-21 07:11:37 +00:00
|
|
|
static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct packet_mclist *ml, **mlp;
|
|
|
|
|
|
|
|
rtnl_lock();
|
|
|
|
|
|
|
|
for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) {
|
|
|
|
if (ml->ifindex == mreq->mr_ifindex &&
|
|
|
|
ml->type == mreq->mr_type &&
|
|
|
|
ml->alen == mreq->mr_alen &&
|
|
|
|
memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
|
|
|
|
if (--ml->count == 0) {
|
|
|
|
struct net_device *dev;
|
|
|
|
*mlp = ml->next;
|
2009-10-16 06:38:46 +00:00
|
|
|
dev = __dev_get_by_index(sock_net(sk), ml->ifindex);
|
|
|
|
if (dev)
|
2005-04-16 22:20:36 +00:00
|
|
|
packet_dev_mc(dev, ml, -1);
|
|
|
|
kfree(ml);
|
|
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
return -EADDRNOTAVAIL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void packet_flush_mclist(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
struct packet_mclist *ml;
|
|
|
|
|
|
|
|
if (!po->mclist)
|
|
|
|
return;
|
|
|
|
|
|
|
|
rtnl_lock();
|
|
|
|
while ((ml = po->mclist) != NULL) {
|
|
|
|
struct net_device *dev;
|
|
|
|
|
|
|
|
po->mclist = ml->next;
|
2009-10-16 06:38:46 +00:00
|
|
|
dev = __dev_get_by_index(sock_net(sk), ml->ifindex);
|
|
|
|
if (dev != NULL)
|
2005-04-16 22:20:36 +00:00
|
|
|
packet_dev_mc(dev, ml, -1);
|
|
|
|
kfree(ml);
|
|
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2009-09-30 23:12:20 +00:00
|
|
|
packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
2007-02-05 07:31:32 +00:00
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
2005-04-16 22:20:36 +00:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (level != SOL_PACKET)
|
|
|
|
return -ENOPROTOOPT;
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
switch (optname) {
|
2007-02-09 14:25:10 +00:00
|
|
|
case PACKET_ADD_MEMBERSHIP:
|
2005-04-16 22:20:36 +00:00
|
|
|
case PACKET_DROP_MEMBERSHIP:
|
|
|
|
{
|
2005-09-21 07:11:37 +00:00
|
|
|
struct packet_mreq_max mreq;
|
|
|
|
int len = optlen;
|
|
|
|
memset(&mreq, 0, sizeof(mreq));
|
|
|
|
if (len < sizeof(struct packet_mreq))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EINVAL;
|
2005-09-21 07:11:37 +00:00
|
|
|
if (len > sizeof(mreq))
|
|
|
|
len = sizeof(mreq);
|
2009-07-21 21:57:59 +00:00
|
|
|
if (copy_from_user(&mreq, optval, len))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EFAULT;
|
2005-09-21 07:11:37 +00:00
|
|
|
if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address)))
|
|
|
|
return -EINVAL;
|
2005-04-16 22:20:36 +00:00
|
|
|
if (optname == PACKET_ADD_MEMBERSHIP)
|
|
|
|
ret = packet_mc_add(sk, &mreq);
|
|
|
|
else
|
|
|
|
ret = packet_mc_drop(sk, &mreq);
|
|
|
|
return ret;
|
|
|
|
}
|
2007-05-29 20:12:50 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
case PACKET_RX_RING:
|
2009-05-19 05:11:22 +00:00
|
|
|
case PACKET_TX_RING:
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct tpacket_req req;
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
if (optlen < sizeof(req))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EINVAL;
|
2010-02-05 04:24:10 +00:00
|
|
|
if (pkt_sk(sk)->has_vnet_hdr)
|
|
|
|
return -EINVAL;
|
2009-07-21 21:57:59 +00:00
|
|
|
if (copy_from_user(&req, optval, sizeof(req)))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EFAULT;
|
2009-05-19 05:11:22 +00:00
|
|
|
return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
case PACKET_COPY_THRESH:
|
|
|
|
{
|
|
|
|
int val;
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
if (optlen != sizeof(val))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EINVAL;
|
2009-07-21 21:57:59 +00:00
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
2005-04-16 22:20:36 +00:00
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
pkt_sk(sk)->copy_thresh = val;
|
|
|
|
return 0;
|
|
|
|
}
|
2008-07-15 05:50:15 +00:00
|
|
|
case PACKET_VERSION:
|
|
|
|
{
|
|
|
|
int val;
|
|
|
|
|
|
|
|
if (optlen != sizeof(val))
|
|
|
|
return -EINVAL;
|
2009-05-19 05:11:22 +00:00
|
|
|
if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
|
2008-07-15 05:50:15 +00:00
|
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
switch (val) {
|
|
|
|
case TPACKET_V1:
|
|
|
|
case TPACKET_V2:
|
|
|
|
po->tp_version = val;
|
|
|
|
return 0;
|
|
|
|
default:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
2008-07-19 01:05:19 +00:00
|
|
|
case PACKET_RESERVE:
|
|
|
|
{
|
|
|
|
unsigned int val;
|
|
|
|
|
|
|
|
if (optlen != sizeof(val))
|
|
|
|
return -EINVAL;
|
2009-05-19 05:11:22 +00:00
|
|
|
if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
|
2008-07-19 01:05:19 +00:00
|
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
po->tp_reserve = val;
|
|
|
|
return 0;
|
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
case PACKET_LOSS:
|
|
|
|
{
|
|
|
|
unsigned int val;
|
|
|
|
|
|
|
|
if (optlen != sizeof(val))
|
|
|
|
return -EINVAL;
|
|
|
|
if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
|
|
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
po->tp_loss = !!val;
|
|
|
|
return 0;
|
|
|
|
}
|
2007-02-05 07:31:32 +00:00
|
|
|
case PACKET_AUXDATA:
|
|
|
|
{
|
|
|
|
int val;
|
|
|
|
|
|
|
|
if (optlen < sizeof(val))
|
|
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
po->auxdata = !!val;
|
|
|
|
return 0;
|
|
|
|
}
|
2007-04-20 23:05:39 +00:00
|
|
|
case PACKET_ORIGDEV:
|
|
|
|
{
|
|
|
|
int val;
|
|
|
|
|
|
|
|
if (optlen < sizeof(val))
|
|
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
po->origdev = !!val;
|
|
|
|
return 0;
|
|
|
|
}
|
2010-02-05 04:24:10 +00:00
|
|
|
case PACKET_VNET_HDR:
|
|
|
|
{
|
|
|
|
int val;
|
|
|
|
|
|
|
|
if (sock->type != SOCK_RAW)
|
|
|
|
return -EINVAL;
|
|
|
|
if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
|
|
|
|
return -EBUSY;
|
|
|
|
if (optlen < sizeof(val))
|
|
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(&val, optval, sizeof(val)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
po->has_vnet_hdr = !!val;
|
|
|
|
return 0;
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
default:
|
|
|
|
return -ENOPROTOOPT;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int packet_getsockopt(struct socket *sock, int level, int optname,
|
|
|
|
char __user *optval, int __user *optlen)
|
|
|
|
{
|
|
|
|
int len;
|
2007-02-05 07:31:32 +00:00
|
|
|
int val;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
2007-02-05 07:31:32 +00:00
|
|
|
void *data;
|
|
|
|
struct tpacket_stats st;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (level != SOL_PACKET)
|
|
|
|
return -ENOPROTOOPT;
|
|
|
|
|
2006-01-24 00:28:02 +00:00
|
|
|
if (get_user(len, optlen))
|
|
|
|
return -EFAULT;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (len < 0)
|
|
|
|
return -EINVAL;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
switch (optname) {
|
2005-04-16 22:20:36 +00:00
|
|
|
case PACKET_STATISTICS:
|
|
|
|
if (len > sizeof(struct tpacket_stats))
|
|
|
|
len = sizeof(struct tpacket_stats);
|
|
|
|
spin_lock_bh(&sk->sk_receive_queue.lock);
|
|
|
|
st = po->stats;
|
|
|
|
memset(&po->stats, 0, sizeof(st));
|
|
|
|
spin_unlock_bh(&sk->sk_receive_queue.lock);
|
|
|
|
st.tp_packets += st.tp_drops;
|
|
|
|
|
2007-02-05 07:31:32 +00:00
|
|
|
data = &st;
|
|
|
|
break;
|
|
|
|
case PACKET_AUXDATA:
|
|
|
|
if (len > sizeof(int))
|
|
|
|
len = sizeof(int);
|
|
|
|
val = po->auxdata;
|
|
|
|
|
2007-04-20 23:05:39 +00:00
|
|
|
data = &val;
|
|
|
|
break;
|
|
|
|
case PACKET_ORIGDEV:
|
|
|
|
if (len > sizeof(int))
|
|
|
|
len = sizeof(int);
|
|
|
|
val = po->origdev;
|
|
|
|
|
2010-02-05 04:24:10 +00:00
|
|
|
data = &val;
|
|
|
|
break;
|
|
|
|
case PACKET_VNET_HDR:
|
|
|
|
if (len > sizeof(int))
|
|
|
|
len = sizeof(int);
|
|
|
|
val = po->has_vnet_hdr;
|
|
|
|
|
2007-02-05 07:31:32 +00:00
|
|
|
data = &val;
|
2005-04-16 22:20:36 +00:00
|
|
|
break;
|
2008-07-15 05:50:15 +00:00
|
|
|
case PACKET_VERSION:
|
|
|
|
if (len > sizeof(int))
|
|
|
|
len = sizeof(int);
|
|
|
|
val = po->tp_version;
|
|
|
|
data = &val;
|
|
|
|
break;
|
|
|
|
case PACKET_HDRLEN:
|
|
|
|
if (len > sizeof(int))
|
|
|
|
len = sizeof(int);
|
|
|
|
if (copy_from_user(&val, optval, len))
|
|
|
|
return -EFAULT;
|
|
|
|
switch (val) {
|
|
|
|
case TPACKET_V1:
|
|
|
|
val = sizeof(struct tpacket_hdr);
|
|
|
|
break;
|
|
|
|
case TPACKET_V2:
|
|
|
|
val = sizeof(struct tpacket2_hdr);
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
data = &val;
|
|
|
|
break;
|
2008-07-19 01:05:19 +00:00
|
|
|
case PACKET_RESERVE:
|
|
|
|
if (len > sizeof(unsigned int))
|
|
|
|
len = sizeof(unsigned int);
|
|
|
|
val = po->tp_reserve;
|
|
|
|
data = &val;
|
|
|
|
break;
|
2009-05-19 05:11:22 +00:00
|
|
|
case PACKET_LOSS:
|
|
|
|
if (len > sizeof(unsigned int))
|
|
|
|
len = sizeof(unsigned int);
|
|
|
|
val = po->tp_loss;
|
|
|
|
data = &val;
|
|
|
|
break;
|
2005-04-16 22:20:36 +00:00
|
|
|
default:
|
|
|
|
return -ENOPROTOOPT;
|
|
|
|
}
|
|
|
|
|
2006-01-24 00:28:02 +00:00
|
|
|
if (put_user(len, optlen))
|
|
|
|
return -EFAULT;
|
2007-02-05 07:31:32 +00:00
|
|
|
if (copy_to_user(optval, data, len))
|
|
|
|
return -EFAULT;
|
2006-01-24 00:28:02 +00:00
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data)
|
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
struct hlist_node *node;
|
2007-02-21 07:19:54 +00:00
|
|
|
struct net_device *dev = data;
|
2008-03-25 12:47:49 +00:00
|
|
|
struct net *net = dev_net(dev);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-12-11 12:19:54 +00:00
|
|
|
read_lock(&net->packet.sklist_lock);
|
|
|
|
sk_for_each(sk, node, &net->packet.sklist) {
|
2005-04-16 22:20:36 +00:00
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
|
|
|
|
switch (msg) {
|
|
|
|
case NETDEV_UNREGISTER:
|
|
|
|
if (po->mclist)
|
|
|
|
packet_dev_mclist(dev, po->mclist, -1);
|
2007-05-29 20:12:50 +00:00
|
|
|
/* fallthrough */
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
case NETDEV_DOWN:
|
|
|
|
if (dev->ifindex == po->ifindex) {
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
if (po->running) {
|
|
|
|
__dev_remove_pack(&po->prot_hook);
|
|
|
|
__sock_put(sk);
|
|
|
|
po->running = 0;
|
|
|
|
sk->sk_err = ENETDOWN;
|
|
|
|
if (!sock_flag(sk, SOCK_DEAD))
|
|
|
|
sk->sk_error_report(sk);
|
|
|
|
}
|
|
|
|
if (msg == NETDEV_UNREGISTER) {
|
|
|
|
po->ifindex = -1;
|
|
|
|
po->prot_hook.dev = NULL;
|
|
|
|
}
|
|
|
|
spin_unlock(&po->bind_lock);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case NETDEV_UP:
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
if (dev->ifindex == po->ifindex && po->num &&
|
|
|
|
!po->running) {
|
|
|
|
dev_add_pack(&po->prot_hook);
|
|
|
|
sock_hold(sk);
|
|
|
|
po->running = 1;
|
|
|
|
}
|
|
|
|
spin_unlock(&po->bind_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2007-12-11 12:19:54 +00:00
|
|
|
read_unlock(&net->packet.sklist_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
return NOTIFY_DONE;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int packet_ioctl(struct socket *sock, unsigned int cmd,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
switch (cmd) {
|
2009-07-21 21:57:59 +00:00
|
|
|
case SIOCOUTQ:
|
|
|
|
{
|
|
|
|
int amount = sk_wmem_alloc_get(sk);
|
2009-06-18 02:05:41 +00:00
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
return put_user(amount, (int __user *)arg);
|
|
|
|
}
|
|
|
|
case SIOCINQ:
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int amount = 0;
|
|
|
|
|
|
|
|
spin_lock_bh(&sk->sk_receive_queue.lock);
|
|
|
|
skb = skb_peek(&sk->sk_receive_queue);
|
|
|
|
if (skb)
|
|
|
|
amount = skb->len;
|
|
|
|
spin_unlock_bh(&sk->sk_receive_queue.lock);
|
|
|
|
return put_user(amount, (int __user *)arg);
|
|
|
|
}
|
|
|
|
case SIOCGSTAMP:
|
|
|
|
return sock_get_timestamp(sk, (struct timeval __user *)arg);
|
|
|
|
case SIOCGSTAMPNS:
|
|
|
|
return sock_get_timestampns(sk, (struct timespec __user *)arg);
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#ifdef CONFIG_INET
|
2009-07-21 21:57:59 +00:00
|
|
|
case SIOCADDRT:
|
|
|
|
case SIOCDELRT:
|
|
|
|
case SIOCDARP:
|
|
|
|
case SIOCGARP:
|
|
|
|
case SIOCSARP:
|
|
|
|
case SIOCGIFADDR:
|
|
|
|
case SIOCSIFADDR:
|
|
|
|
case SIOCGIFBRDADDR:
|
|
|
|
case SIOCSIFBRDADDR:
|
|
|
|
case SIOCGIFNETMASK:
|
|
|
|
case SIOCSIFNETMASK:
|
|
|
|
case SIOCGIFDSTADDR:
|
|
|
|
case SIOCSIFDSTADDR:
|
|
|
|
case SIOCSIFFLAGS:
|
|
|
|
if (!net_eq(sock_net(sk), &init_net))
|
|
|
|
return -ENOIOCTLCMD;
|
|
|
|
return inet_dgram_ops.ioctl(sock, cmd, arg);
|
2005-04-16 22:20:36 +00:00
|
|
|
#endif
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
default:
|
|
|
|
return -ENOIOCTLCMD;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-07-21 21:57:59 +00:00
|
|
|
static unsigned int packet_poll(struct file *file, struct socket *sock,
|
2005-04-16 22:20:36 +00:00
|
|
|
poll_table *wait)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
|
|
|
unsigned int mask = datagram_poll(file, sock, wait);
|
|
|
|
|
|
|
|
spin_lock_bh(&sk->sk_receive_queue.lock);
|
2009-05-19 05:11:22 +00:00
|
|
|
if (po->rx_ring.pg_vec) {
|
|
|
|
if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL))
|
2005-04-16 22:20:36 +00:00
|
|
|
mask |= POLLIN | POLLRDNORM;
|
|
|
|
}
|
|
|
|
spin_unlock_bh(&sk->sk_receive_queue.lock);
|
2009-05-19 05:11:22 +00:00
|
|
|
spin_lock_bh(&sk->sk_write_queue.lock);
|
|
|
|
if (po->tx_ring.pg_vec) {
|
|
|
|
if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE))
|
|
|
|
mask |= POLLOUT | POLLWRNORM;
|
|
|
|
}
|
|
|
|
spin_unlock_bh(&sk->sk_write_queue.lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
return mask;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Dirty? Well, I still did not learn better way to account
|
|
|
|
* for user mmaps.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void packet_mm_open(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
2009-07-21 21:57:59 +00:00
|
|
|
struct socket *sock = file->private_data;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct sock *sk = sock->sk;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (sk)
|
|
|
|
atomic_inc(&pkt_sk(sk)->mapped);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void packet_mm_close(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
2009-07-21 21:57:59 +00:00
|
|
|
struct socket *sock = file->private_data;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct sock *sk = sock->sk;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (sk)
|
|
|
|
atomic_dec(&pkt_sk(sk)->mapped);
|
|
|
|
}
|
|
|
|
|
2009-09-27 18:29:37 +00:00
|
|
|
static const struct vm_operations_struct packet_mmap_ops = {
|
2009-07-21 21:57:59 +00:00
|
|
|
.open = packet_mm_open,
|
|
|
|
.close = packet_mm_close,
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
2005-12-07 00:38:35 +00:00
|
|
|
static void free_pg_vec(char **pg_vec, unsigned int order, unsigned int len)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2005-12-07 00:38:35 +00:00
|
|
|
for (i = 0; i < len; i++) {
|
|
|
|
if (likely(pg_vec[i]))
|
|
|
|
free_pages((unsigned long) pg_vec[i], order);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
kfree(pg_vec);
|
|
|
|
}
|
|
|
|
|
2005-12-07 00:38:35 +00:00
|
|
|
static inline char *alloc_one_pg_vec_page(unsigned long order)
|
|
|
|
{
|
2009-04-15 10:39:52 +00:00
|
|
|
gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN;
|
|
|
|
|
|
|
|
return (char *) __get_free_pages(gfp_flags, order);
|
2005-12-07 00:38:35 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static char **alloc_pg_vec(struct tpacket_req *req, int order)
|
|
|
|
{
|
|
|
|
unsigned int block_nr = req->tp_block_nr;
|
|
|
|
char **pg_vec;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
pg_vec = kzalloc(block_nr * sizeof(char *), GFP_KERNEL);
|
|
|
|
if (unlikely(!pg_vec))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
for (i = 0; i < block_nr; i++) {
|
|
|
|
pg_vec[i] = alloc_one_pg_vec_page(order);
|
|
|
|
if (unlikely(!pg_vec[i]))
|
|
|
|
goto out_free_pgvec;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
return pg_vec;
|
|
|
|
|
|
|
|
out_free_pgvec:
|
|
|
|
free_pg_vec(pg_vec, order, block_nr);
|
|
|
|
pg_vec = NULL;
|
|
|
|
goto out;
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
|
|
|
|
int closing, int tx_ring)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
char **pg_vec = NULL;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
2006-11-08 08:26:29 +00:00
|
|
|
int was_running, order = 0;
|
2009-05-19 05:11:22 +00:00
|
|
|
struct packet_ring_buffer *rb;
|
|
|
|
struct sk_buff_head *rb_queue;
|
2006-11-08 08:26:29 +00:00
|
|
|
__be16 num;
|
2009-05-19 05:11:22 +00:00
|
|
|
int err;
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
rb = tx_ring ? &po->tx_ring : &po->rx_ring;
|
|
|
|
rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
err = -EBUSY;
|
|
|
|
if (!closing) {
|
|
|
|
if (atomic_read(&po->mapped))
|
|
|
|
goto out;
|
|
|
|
if (atomic_read(&rb->pending))
|
|
|
|
goto out;
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
if (req->tp_block_nr) {
|
|
|
|
/* Sanity tests and some calculations */
|
|
|
|
err = -EBUSY;
|
|
|
|
if (unlikely(rb->pg_vec))
|
|
|
|
goto out;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2008-07-15 05:50:15 +00:00
|
|
|
switch (po->tp_version) {
|
|
|
|
case TPACKET_V1:
|
|
|
|
po->tp_hdrlen = TPACKET_HDRLEN;
|
|
|
|
break;
|
|
|
|
case TPACKET_V2:
|
|
|
|
po->tp_hdrlen = TPACKET2_HDRLEN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
err = -EINVAL;
|
2005-12-07 00:38:35 +00:00
|
|
|
if (unlikely((int)req->tp_block_size <= 0))
|
2009-05-19 05:11:22 +00:00
|
|
|
goto out;
|
2005-12-07 00:38:35 +00:00
|
|
|
if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
|
2009-05-19 05:11:22 +00:00
|
|
|
goto out;
|
2008-07-19 01:05:19 +00:00
|
|
|
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
|
2009-05-19 05:11:22 +00:00
|
|
|
po->tp_reserve))
|
|
|
|
goto out;
|
2005-12-07 00:38:35 +00:00
|
|
|
if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
|
2009-05-19 05:11:22 +00:00
|
|
|
goto out;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
rb->frames_per_block = req->tp_block_size/req->tp_frame_size;
|
|
|
|
if (unlikely(rb->frames_per_block <= 0))
|
|
|
|
goto out;
|
|
|
|
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
|
|
|
|
req->tp_frame_nr))
|
|
|
|
goto out;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
err = -ENOMEM;
|
2005-12-07 00:38:35 +00:00
|
|
|
order = get_order(req->tp_block_size);
|
|
|
|
pg_vec = alloc_pg_vec(req, order);
|
|
|
|
if (unlikely(!pg_vec))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out;
|
2009-05-19 05:11:22 +00:00
|
|
|
}
|
|
|
|
/* Done */
|
|
|
|
else {
|
|
|
|
err = -EINVAL;
|
2005-12-07 00:38:35 +00:00
|
|
|
if (unlikely(req->tp_frame_nr))
|
2009-05-19 05:11:22 +00:00
|
|
|
goto out;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
/* Detach socket from network */
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
was_running = po->running;
|
|
|
|
num = po->num;
|
|
|
|
if (was_running) {
|
|
|
|
__dev_remove_pack(&po->prot_hook);
|
|
|
|
po->num = 0;
|
|
|
|
po->running = 0;
|
|
|
|
__sock_put(sk);
|
|
|
|
}
|
|
|
|
spin_unlock(&po->bind_lock);
|
2007-02-09 14:25:10 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
synchronize_net();
|
|
|
|
|
|
|
|
err = -EBUSY;
|
2009-01-30 22:12:06 +00:00
|
|
|
mutex_lock(&po->pg_vec_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (closing || atomic_read(&po->mapped) == 0) {
|
|
|
|
err = 0;
|
|
|
|
#define XC(a, b) ({ __typeof__ ((a)) __t; __t = (a); (a) = (b); __t; })
|
2009-05-19 05:11:22 +00:00
|
|
|
spin_lock_bh(&rb_queue->lock);
|
|
|
|
pg_vec = XC(rb->pg_vec, pg_vec);
|
|
|
|
rb->frame_max = (req->tp_frame_nr - 1);
|
|
|
|
rb->head = 0;
|
|
|
|
rb->frame_size = req->tp_frame_size;
|
|
|
|
spin_unlock_bh(&rb_queue->lock);
|
|
|
|
|
|
|
|
order = XC(rb->pg_vec_order, order);
|
|
|
|
req->tp_block_nr = XC(rb->pg_vec_len, req->tp_block_nr);
|
|
|
|
|
|
|
|
rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
|
|
|
|
po->prot_hook.func = (po->rx_ring.pg_vec) ?
|
|
|
|
tpacket_rcv : packet_rcv;
|
|
|
|
skb_queue_purge(rb_queue);
|
2005-04-16 22:20:36 +00:00
|
|
|
#undef XC
|
|
|
|
if (atomic_read(&po->mapped))
|
2009-07-21 21:57:59 +00:00
|
|
|
pr_err("packet_mmap: vma is busy: %d\n",
|
|
|
|
atomic_read(&po->mapped));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2009-01-30 22:12:06 +00:00
|
|
|
mutex_unlock(&po->pg_vec_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
spin_lock(&po->bind_lock);
|
|
|
|
if (was_running && !po->running) {
|
|
|
|
sock_hold(sk);
|
|
|
|
po->running = 1;
|
|
|
|
po->num = num;
|
|
|
|
dev_add_pack(&po->prot_hook);
|
|
|
|
}
|
|
|
|
spin_unlock(&po->bind_lock);
|
|
|
|
|
|
|
|
release_sock(sk);
|
|
|
|
|
|
|
|
if (pg_vec)
|
|
|
|
free_pg_vec(pg_vec, order, req->tp_block_nr);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2009-05-19 05:11:22 +00:00
|
|
|
static int packet_mmap(struct file *file, struct socket *sock,
|
|
|
|
struct vm_area_struct *vma)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct packet_sock *po = pkt_sk(sk);
|
2009-05-19 05:11:22 +00:00
|
|
|
unsigned long size, expected_size;
|
|
|
|
struct packet_ring_buffer *rb;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned long start;
|
|
|
|
int err = -EINVAL;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (vma->vm_pgoff)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2009-01-30 22:12:06 +00:00
|
|
|
mutex_lock(&po->pg_vec_lock);
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
expected_size = 0;
|
|
|
|
for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) {
|
|
|
|
if (rb->pg_vec) {
|
|
|
|
expected_size += rb->pg_vec_len
|
|
|
|
* rb->pg_vec_pages
|
|
|
|
* PAGE_SIZE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (expected_size == 0)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out;
|
2009-05-19 05:11:22 +00:00
|
|
|
|
|
|
|
size = vma->vm_end - vma->vm_start;
|
|
|
|
if (size != expected_size)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
start = vma->vm_start;
|
2009-05-19 05:11:22 +00:00
|
|
|
for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) {
|
|
|
|
if (rb->pg_vec == NULL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
for (i = 0; i < rb->pg_vec_len; i++) {
|
|
|
|
struct page *page = virt_to_page(rb->pg_vec[i]);
|
|
|
|
int pg_num;
|
|
|
|
|
|
|
|
for (pg_num = 0; pg_num < rb->pg_vec_pages;
|
2009-07-21 21:57:59 +00:00
|
|
|
pg_num++, page++) {
|
2009-05-19 05:11:22 +00:00
|
|
|
err = vm_insert_page(vma, start, page);
|
|
|
|
if (unlikely(err))
|
|
|
|
goto out;
|
|
|
|
start += PAGE_SIZE;
|
|
|
|
}
|
2005-12-07 00:38:35 +00:00
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2009-05-19 05:11:22 +00:00
|
|
|
|
2005-12-07 00:38:35 +00:00
|
|
|
atomic_inc(&po->mapped);
|
2005-04-16 22:20:36 +00:00
|
|
|
vma->vm_ops = &packet_mmap_ops;
|
|
|
|
err = 0;
|
|
|
|
|
|
|
|
out:
|
2009-01-30 22:12:06 +00:00
|
|
|
mutex_unlock(&po->pg_vec_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2005-12-22 20:49:22 +00:00
|
|
|
static const struct proto_ops packet_ops_spkt = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.family = PF_PACKET,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.release = packet_release,
|
|
|
|
.bind = packet_bind_spkt,
|
|
|
|
.connect = sock_no_connect,
|
|
|
|
.socketpair = sock_no_socketpair,
|
|
|
|
.accept = sock_no_accept,
|
|
|
|
.getname = packet_getname_spkt,
|
|
|
|
.poll = datagram_poll,
|
|
|
|
.ioctl = packet_ioctl,
|
|
|
|
.listen = sock_no_listen,
|
|
|
|
.shutdown = sock_no_shutdown,
|
|
|
|
.setsockopt = sock_no_setsockopt,
|
|
|
|
.getsockopt = sock_no_getsockopt,
|
|
|
|
.sendmsg = packet_sendmsg_spkt,
|
|
|
|
.recvmsg = packet_recvmsg,
|
|
|
|
.mmap = sock_no_mmap,
|
|
|
|
.sendpage = sock_no_sendpage,
|
|
|
|
};
|
|
|
|
|
2005-12-22 20:49:22 +00:00
|
|
|
static const struct proto_ops packet_ops = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.family = PF_PACKET,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.release = packet_release,
|
|
|
|
.bind = packet_bind,
|
|
|
|
.connect = sock_no_connect,
|
|
|
|
.socketpair = sock_no_socketpair,
|
|
|
|
.accept = sock_no_accept,
|
2007-02-09 14:25:10 +00:00
|
|
|
.getname = packet_getname,
|
2005-04-16 22:20:36 +00:00
|
|
|
.poll = packet_poll,
|
|
|
|
.ioctl = packet_ioctl,
|
|
|
|
.listen = sock_no_listen,
|
|
|
|
.shutdown = sock_no_shutdown,
|
|
|
|
.setsockopt = packet_setsockopt,
|
|
|
|
.getsockopt = packet_getsockopt,
|
|
|
|
.sendmsg = packet_sendmsg,
|
|
|
|
.recvmsg = packet_recvmsg,
|
|
|
|
.mmap = packet_mmap,
|
|
|
|
.sendpage = sock_no_sendpage,
|
|
|
|
};
|
|
|
|
|
2009-10-05 05:58:39 +00:00
|
|
|
static const struct net_proto_family packet_family_ops = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.family = PF_PACKET,
|
|
|
|
.create = packet_create,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct notifier_block packet_netdev_notifier = {
|
2009-07-21 21:57:59 +00:00
|
|
|
.notifier_call = packet_notifier,
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
|
|
|
|
static void *packet_seq_start(struct seq_file *seq, loff_t *pos)
|
2008-01-08 06:39:57 +00:00
|
|
|
__acquires(seq_file_net(seq)->packet.sklist_lock)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2007-11-20 06:31:54 +00:00
|
|
|
struct net *net = seq_file_net(seq);
|
2007-12-11 12:19:54 +00:00
|
|
|
read_lock(&net->packet.sklist_lock);
|
2010-02-08 23:19:29 +00:00
|
|
|
return seq_hlist_start_head(&net->packet.sklist, *pos);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
|
|
|
|
{
|
2007-12-16 22:04:02 +00:00
|
|
|
struct net *net = seq_file_net(seq);
|
2010-02-08 23:19:29 +00:00
|
|
|
return seq_hlist_next(v, &net->packet.sklist, pos);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void packet_seq_stop(struct seq_file *seq, void *v)
|
2008-01-08 06:39:57 +00:00
|
|
|
__releases(seq_file_net(seq)->packet.sklist_lock)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2007-12-16 22:04:02 +00:00
|
|
|
struct net *net = seq_file_net(seq);
|
2007-12-11 12:19:54 +00:00
|
|
|
read_unlock(&net->packet.sklist_lock);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2007-02-09 14:25:10 +00:00
|
|
|
static int packet_seq_show(struct seq_file *seq, void *v)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
if (v == SEQ_START_TOKEN)
|
|
|
|
seq_puts(seq, "sk RefCnt Type Proto Iface R Rmem User Inode\n");
|
|
|
|
else {
|
2010-02-08 23:19:29 +00:00
|
|
|
struct sock *s = sk_entry(v);
|
2005-04-16 22:20:36 +00:00
|
|
|
const struct packet_sock *po = pkt_sk(s);
|
|
|
|
|
|
|
|
seq_printf(seq,
|
|
|
|
"%p %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n",
|
|
|
|
s,
|
|
|
|
atomic_read(&s->sk_refcnt),
|
|
|
|
s->sk_type,
|
|
|
|
ntohs(po->num),
|
|
|
|
po->ifindex,
|
|
|
|
po->running,
|
|
|
|
atomic_read(&s->sk_rmem_alloc),
|
|
|
|
sock_i_uid(s),
|
2009-07-21 21:57:59 +00:00
|
|
|
sock_i_ino(s));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-07-11 06:07:31 +00:00
|
|
|
static const struct seq_operations packet_seq_ops = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.start = packet_seq_start,
|
|
|
|
.next = packet_seq_next,
|
|
|
|
.stop = packet_seq_stop,
|
|
|
|
.show = packet_seq_show,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int packet_seq_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
2007-11-20 06:31:54 +00:00
|
|
|
return seq_open_net(inode, file, &packet_seq_ops,
|
|
|
|
sizeof(struct seq_net_private));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2007-02-12 08:55:36 +00:00
|
|
|
static const struct file_operations packet_seq_fops = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.open = packet_seq_open,
|
|
|
|
.read = seq_read,
|
|
|
|
.llseek = seq_lseek,
|
2007-11-20 06:31:54 +00:00
|
|
|
.release = seq_release_net,
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
2010-01-17 03:35:32 +00:00
|
|
|
static int __net_init packet_net_init(struct net *net)
|
2007-11-20 06:28:35 +00:00
|
|
|
{
|
2007-12-11 12:19:54 +00:00
|
|
|
rwlock_init(&net->packet.sklist_lock);
|
|
|
|
INIT_HLIST_HEAD(&net->packet.sklist);
|
2007-11-20 06:28:35 +00:00
|
|
|
|
|
|
|
if (!proc_net_fops_create(net, "packet", 0, &packet_seq_fops))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-01-17 03:35:32 +00:00
|
|
|
static void __net_exit packet_net_exit(struct net *net)
|
2007-11-20 06:28:35 +00:00
|
|
|
{
|
|
|
|
proc_net_remove(net, "packet");
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct pernet_operations packet_net_ops = {
|
|
|
|
.init = packet_net_init,
|
|
|
|
.exit = packet_net_exit,
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
static void __exit packet_exit(void)
|
|
|
|
{
|
|
|
|
unregister_netdevice_notifier(&packet_netdev_notifier);
|
2007-11-20 06:28:35 +00:00
|
|
|
unregister_pernet_subsys(&packet_net_ops);
|
2005-04-16 22:20:36 +00:00
|
|
|
sock_unregister(PF_PACKET);
|
|
|
|
proto_unregister(&packet_proto);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init packet_init(void)
|
|
|
|
{
|
|
|
|
int rc = proto_register(&packet_proto, 0);
|
|
|
|
|
|
|
|
if (rc != 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
sock_register(&packet_family_ops);
|
2007-11-20 06:28:35 +00:00
|
|
|
register_pernet_subsys(&packet_net_ops);
|
2005-04-16 22:20:36 +00:00
|
|
|
register_netdevice_notifier(&packet_netdev_notifier);
|
|
|
|
out:
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(packet_init);
|
|
|
|
module_exit(packet_exit);
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
MODULE_ALIAS_NETPROTO(PF_PACKET);
|