linux-sg2042/net/ipv4/inet_diag.c

949 lines
22 KiB
C
Raw Normal View History

/*
* inet_diag.c Module for monitoring INET transport protocols sockets.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* 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.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/time.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/inet6_hashtables.h>
#include <net/netlink.h>
#include <linux/inet.h>
#include <linux/stddef.h>
#include <linux/inet_diag.h>
static const struct inet_diag_handler **inet_diag_table;
struct inet_diag_entry {
__be32 *saddr;
__be32 *daddr;
u16 sport;
u16 dport;
u16 family;
u16 userlocks;
};
static struct sock *idiagnl;
#define INET_DIAG_PUT(skb, attrtype, attrlen) \
RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
static DEFINE_MUTEX(inet_diag_table_mutex);
static const struct inet_diag_handler *inet_diag_lock_handler(int type)
{
#ifdef CONFIG_KMOD
if (!inet_diag_table[type])
request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
NETLINK_INET_DIAG, type);
#endif
mutex_lock(&inet_diag_table_mutex);
if (!inet_diag_table[type])
return ERR_PTR(-ENOENT);
return inet_diag_table[type];
}
static inline void inet_diag_unlock_handler(
const struct inet_diag_handler *handler)
{
mutex_unlock(&inet_diag_table_mutex);
}
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
int ext, u32 pid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
void *info = NULL;
struct inet_diag_meminfo *minfo = NULL;
unsigned char *b = skb_tail_pointer(skb);
const struct inet_diag_handler *handler;
handler = inet_diag_table[unlh->nlmsg_type];
BUG_ON(handler == NULL);
nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
nlh->nlmsg_flags = nlmsg_flags;
r = NLMSG_DATA(nlh);
BUG_ON(sk->sk_state == TCP_TIME_WAIT);
if (ext & (1 << (INET_DIAG_MEMINFO - 1)))
minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo));
if (ext & (1 << (INET_DIAG_INFO - 1)))
info = INET_DIAG_PUT(skb, INET_DIAG_INFO,
handler->idiag_info_size);
if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
const size_t len = strlen(icsk->icsk_ca_ops->name);
strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
icsk->icsk_ca_ops->name);
}
r->idiag_family = sk->sk_family;
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->id.idiag_if = sk->sk_bound_dev_if;
r->id.idiag_cookie[0] = (u32)(unsigned long)sk;
r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
r->id.idiag_sport = inet->sport;
r->id.idiag_dport = inet->dport;
r->id.idiag_src[0] = inet->rcv_saddr;
r->id.idiag_dst[0] = inet->daddr;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
if (r->idiag_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
&np->rcv_saddr);
ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
&np->daddr);
}
#endif
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
#undef EXPIRES_IN_MS
r->idiag_uid = sock_i_uid(sk);
r->idiag_inode = sock_i_ino(sk);
if (minfo) {
minfo->idiag_rmem = atomic_read(&sk->sk_rmem_alloc);
minfo->idiag_wmem = sk->sk_wmem_queued;
minfo->idiag_fmem = sk->sk_forward_alloc;
minfo->idiag_tmem = atomic_read(&sk->sk_wmem_alloc);
}
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT &&
icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
icsk->icsk_ca_ops->get_info(sk, ext, skb);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
rtattr_failure:
nlmsg_failure:
nlmsg_trim(skb, b);
return -EMSGSIZE;
}
static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
struct sk_buff *skb, int ext, u32 pid,
u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
long tmo;
struct inet_diag_msg *r;
const unsigned char *previous_tail = skb_tail_pointer(skb);
struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq,
unlh->nlmsg_type, sizeof(*r));
r = NLMSG_DATA(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
nlh->nlmsg_flags = nlmsg_flags;
tmo = tw->tw_ttd - jiffies;
if (tmo < 0)
tmo = 0;
r->idiag_family = tw->tw_family;
r->idiag_state = tw->tw_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->id.idiag_if = tw->tw_bound_dev_if;
r->id.idiag_cookie[0] = (u32)(unsigned long)tw;
r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1);
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->id.idiag_dst[0] = tw->tw_daddr;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
if (tw->tw_family == AF_INET6) {
const struct inet6_timewait_sock *tw6 =
inet6_twsk((struct sock *)tw);
ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
&tw6->tw_v6_rcv_saddr);
ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
&tw6->tw_v6_daddr);
}
#endif
nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail;
return skb->len;
nlmsg_failure:
nlmsg_trim(skb, previous_tail);
return -EMSGSIZE;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
int ext, u32 pid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
skb, ext, pid, seq, nlmsg_flags,
unlh);
return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh);
}
static int inet_diag_get_exact(struct sk_buff *in_skb,
const struct nlmsghdr *nlh)
{
int err;
struct sock *sk;
struct inet_diag_req *req = NLMSG_DATA(nlh);
struct sk_buff *rep;
struct inet_hashinfo *hashinfo;
const struct inet_diag_handler *handler;
handler = inet_diag_lock_handler(nlh->nlmsg_type);
if (IS_ERR(handler)) {
err = PTR_ERR(handler);
goto unlock;
}
hashinfo = handler->idiag_hashinfo;
err = -EINVAL;
if (req->idiag_family == AF_INET) {
sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
}
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
else if (req->idiag_family == AF_INET6) {
sk = inet6_lookup(&init_net, hashinfo,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else {
goto unlock;
}
err = -ENOENT;
if (sk == NULL)
goto unlock;
err = -ESTALE;
if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE ||
req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) &&
((u32)(unsigned long)sk != req->id.idiag_cookie[0] ||
(u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1]))
goto out;
err = -ENOMEM;
rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
sizeof(struct inet_diag_meminfo) +
handler->idiag_info_size + 64)),
GFP_KERNEL);
if (!rep)
goto out;
err = sk_diag_fill(sk, rep, req->idiag_ext,
NETLINK_CB(in_skb).pid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(rep);
goto out;
}
err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk) {
if (sk->sk_state == TCP_TIME_WAIT)
inet_twsk_put((struct inet_timewait_sock *)sk);
else
sock_put(sk);
}
unlock:
inet_diag_unlock_handler(handler);
return err;
}
static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
int words = bits >> 5;
bits &= 0x1f;
if (words) {
if (memcmp(a1, a2, words << 2))
return 0;
}
if (bits) {
__be32 w1, w2;
__be32 mask;
w1 = a1[words];
w2 = a2[words];
mask = htonl((0xffffffff) << (32 - bits));
if ((w1 ^ w2) & mask)
return 0;
}
return 1;
}
static int inet_diag_bc_run(const void *bc, int len,
const struct inet_diag_entry *entry)
{
while (len > 0) {
int yes = 1;
const struct inet_diag_bc_op *op = bc;
switch (op->code) {
case INET_DIAG_BC_NOP:
break;
case INET_DIAG_BC_JMP:
yes = 0;
break;
case INET_DIAG_BC_S_GE:
yes = entry->sport >= op[1].no;
break;
case INET_DIAG_BC_S_LE:
yes = entry->dport <= op[1].no;
break;
case INET_DIAG_BC_D_GE:
yes = entry->dport >= op[1].no;
break;
case INET_DIAG_BC_D_LE:
yes = entry->dport <= op[1].no;
break;
case INET_DIAG_BC_AUTO:
yes = !(entry->userlocks & SOCK_BINDPORT_LOCK);
break;
case INET_DIAG_BC_S_COND:
case INET_DIAG_BC_D_COND: {
struct inet_diag_hostcond *cond;
__be32 *addr;
cond = (struct inet_diag_hostcond *)(op + 1);
if (cond->port != -1 &&
cond->port != (op->code == INET_DIAG_BC_S_COND ?
entry->sport : entry->dport)) {
yes = 0;
break;
}
if (cond->prefix_len == 0)
break;
if (op->code == INET_DIAG_BC_S_COND)
addr = entry->saddr;
else
addr = entry->daddr;
if (bitstring_match(addr, cond->addr,
cond->prefix_len))
break;
if (entry->family == AF_INET6 &&
cond->family == AF_INET) {
if (addr[0] == 0 && addr[1] == 0 &&
addr[2] == htonl(0xffff) &&
bitstring_match(addr + 3, cond->addr,
cond->prefix_len))
break;
}
yes = 0;
break;
}
}
if (yes) {
len -= op->yes;
bc += op->yes;
} else {
len -= op->no;
bc += op->no;
}
}
return (len == 0);
}
static int valid_cc(const void *bc, int len, int cc)
{
while (len >= 0) {
const struct inet_diag_bc_op *op = bc;
if (cc > len)
return 0;
if (cc == len)
return 1;
if (op->yes < 4)
return 0;
len -= op->yes;
bc += op->yes;
}
return 0;
}
static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
{
const unsigned char *bc = bytecode;
int len = bytecode_len;
while (len > 0) {
struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc;
//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
switch (op->code) {
case INET_DIAG_BC_AUTO:
case INET_DIAG_BC_S_COND:
case INET_DIAG_BC_D_COND:
case INET_DIAG_BC_S_GE:
case INET_DIAG_BC_S_LE:
case INET_DIAG_BC_D_GE:
case INET_DIAG_BC_D_LE:
if (op->yes < 4 || op->yes > len + 4)
return -EINVAL;
case INET_DIAG_BC_JMP:
if (op->no < 4 || op->no > len + 4)
return -EINVAL;
if (op->no < len &&
!valid_cc(bytecode, bytecode_len, len - op->no))
return -EINVAL;
break;
case INET_DIAG_BC_NOP:
if (op->yes < 4 || op->yes > len + 4)
return -EINVAL;
break;
default:
return -EINVAL;
}
bc += op->yes;
len -= op->yes;
}
return len == 0 ? 0 : -EINVAL;
}
static int inet_csk_diag_dump(struct sock *sk,
struct sk_buff *skb,
struct netlink_callback *cb)
{
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
struct inet_diag_entry entry;
struct rtattr *bc = (struct rtattr *)(r + 1);
struct inet_sock *inet = inet_sk(sk);
entry.family = sk->sk_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
if (entry.family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
entry.saddr = np->rcv_saddr.s6_addr32;
entry.daddr = np->daddr.s6_addr32;
} else
#endif
{
entry.saddr = &inet->rcv_saddr;
entry.daddr = &inet->daddr;
}
entry.sport = inet->num;
entry.dport = ntohs(inet->dport);
entry.userlocks = sk->sk_userlocks;
if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
return 0;
}
return inet_csk_diag_fill(sk, skb, r->idiag_ext,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
struct sk_buff *skb,
struct netlink_callback *cb)
{
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
struct inet_diag_entry entry;
struct rtattr *bc = (struct rtattr *)(r + 1);
entry.family = tw->tw_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
if (tw->tw_family == AF_INET6) {
struct inet6_timewait_sock *tw6 =
inet6_twsk((struct sock *)tw);
entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
entry.daddr = tw6->tw_v6_daddr.s6_addr32;
} else
#endif
{
entry.saddr = &tw->tw_rcv_saddr;
entry.daddr = &tw->tw_daddr;
}
entry.sport = tw->tw_num;
entry.dport = ntohs(tw->tw_dport);
entry.userlocks = 0;
if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
return 0;
}
return inet_twsk_diag_fill(tw, skb, r->idiag_ext,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
struct request_sock *req, u32 pid, u32 seq,
const struct nlmsghdr *unlh)
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct inet_sock *inet = inet_sk(sk);
unsigned char *b = skb_tail_pointer(skb);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
nlh->nlmsg_flags = NLM_F_MULTI;
r = NLMSG_DATA(nlh);
r->idiag_family = sk->sk_family;
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = req->retrans;
r->id.idiag_if = sk->sk_bound_dev_if;
r->id.idiag_cookie[0] = (u32)(unsigned long)req;
r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1);
tmo = req->expires - jiffies;
if (tmo < 0)
tmo = 0;
r->id.idiag_sport = inet->sport;
r->id.idiag_dport = ireq->rmt_port;
r->id.idiag_src[0] = ireq->loc_addr;
r->id.idiag_dst[0] = ireq->rmt_addr;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = sock_i_uid(sk);
r->idiag_inode = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
if (r->idiag_family == AF_INET6) {
ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
&inet6_rsk(req)->loc_addr);
ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
&inet6_rsk(req)->rmt_addr);
}
#endif
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
nlmsg_failure:
nlmsg_trim(skb, b);
return -1;
}
static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
struct netlink_callback *cb)
{
struct inet_diag_entry entry;
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt;
struct rtattr *bc = NULL;
struct inet_sock *inet = inet_sk(sk);
int j, s_j;
int reqnum, s_reqnum;
int err = 0;
s_j = cb->args[3];
s_reqnum = cb->args[4];
if (s_j > 0)
s_j--;
entry.family = sk->sk_family;
read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
lopt = icsk->icsk_accept_queue.listen_opt;
if (!lopt || !lopt->qlen)
goto out;
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
bc = (struct rtattr *)(r + 1);
entry.sport = inet->num;
entry.userlocks = sk->sk_userlocks;
}
for (j = s_j; j < lopt->nr_table_entries; j++) {
struct request_sock *req, *head = lopt->syn_table[j];
reqnum = 0;
for (req = head; req; reqnum++, req = req->dl_next) {
struct inet_request_sock *ireq = inet_rsk(req);
if (reqnum < s_reqnum)
continue;
if (r->id.idiag_dport != ireq->rmt_port &&
r->id.idiag_dport)
continue;
if (bc) {
entry.saddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
(entry.family == AF_INET6) ?
inet6_rsk(req)->loc_addr.s6_addr32 :
#endif
&ireq->loc_addr;
entry.daddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
(entry.family == AF_INET6) ?
inet6_rsk(req)->rmt_addr.s6_addr32 :
#endif
&ireq->rmt_addr;
entry.dport = ntohs(ireq->rmt_port);
if (!inet_diag_bc_run(RTA_DATA(bc),
RTA_PAYLOAD(bc), &entry))
continue;
}
err = inet_diag_fill_req(skb, sk, req,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, cb->nlh);
if (err < 0) {
cb->args[3] = j + 1;
cb->args[4] = reqnum;
goto out;
}
}
s_reqnum = 0;
}
out:
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
return err;
}
static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
int i, num;
int s_i, s_num;
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
const struct inet_diag_handler *handler;
struct inet_hashinfo *hashinfo;
handler = inet_diag_lock_handler(cb->nlh->nlmsg_type);
if (IS_ERR(handler))
goto unlock;
hashinfo = handler->idiag_hashinfo;
s_i = cb->args[1];
s_num = num = cb->args[2];
if (cb->args[0] == 0) {
if (!(r->idiag_states & (TCPF_LISTEN | TCPF_SYN_RECV)))
goto skip_listen_ht;
inet_listen_lock(hashinfo);
for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
struct sock *sk;
struct hlist_node *node;
num = 0;
sk_for_each(sk, node, &hashinfo->listening_hash[i]) {
struct inet_sock *inet = inet_sk(sk);
if (num < s_num) {
num++;
continue;
}
if (r->id.idiag_sport != inet->sport &&
r->id.idiag_sport)
goto next_listen;
if (!(r->idiag_states & TCPF_LISTEN) ||
r->id.idiag_dport ||
cb->args[3] > 0)
goto syn_recv;
if (inet_csk_diag_dump(sk, skb, cb) < 0) {
inet_listen_unlock(hashinfo);
goto done;
}
syn_recv:
if (!(r->idiag_states & TCPF_SYN_RECV))
goto next_listen;
if (inet_diag_dump_reqs(skb, sk, cb) < 0) {
inet_listen_unlock(hashinfo);
goto done;
}
next_listen:
cb->args[3] = 0;
cb->args[4] = 0;
++num;
}
s_num = 0;
cb->args[3] = 0;
cb->args[4] = 0;
}
inet_listen_unlock(hashinfo);
skip_listen_ht:
cb->args[0] = 1;
s_i = num = s_num = 0;
}
if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV)))
goto unlock;
for (i = s_i; i < hashinfo->ehash_size; i++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[i];
rwlock_t *lock = inet_ehash_lockp(hashinfo, i);
struct sock *sk;
struct hlist_node *node;
num = 0;
if (hlist_empty(&head->chain) && hlist_empty(&head->twchain))
continue;
if (i > s_i)
s_num = 0;
read_lock_bh(lock);
sk_for_each(sk, node, &head->chain) {
struct inet_sock *inet = inet_sk(sk);
if (num < s_num)
goto next_normal;
if (!(r->idiag_states & (1 << sk->sk_state)))
goto next_normal;
if (r->id.idiag_sport != inet->sport &&
r->id.idiag_sport)
goto next_normal;
if (r->id.idiag_dport != inet->dport &&
r->id.idiag_dport)
goto next_normal;
if (inet_csk_diag_dump(sk, skb, cb) < 0) {
read_unlock_bh(lock);
goto done;
}
next_normal:
++num;
}
if (r->idiag_states & TCPF_TIME_WAIT) {
struct inet_timewait_sock *tw;
inet_twsk_for_each(tw, node,
[NET]: change layout of ehash table ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-09 06:16:46 +08:00
&head->twchain) {
if (num < s_num)
goto next_dying;
if (r->id.idiag_sport != tw->tw_sport &&
r->id.idiag_sport)
goto next_dying;
if (r->id.idiag_dport != tw->tw_dport &&
r->id.idiag_dport)
goto next_dying;
if (inet_twsk_diag_dump(tw, skb, cb) < 0) {
read_unlock_bh(lock);
goto done;
}
next_dying:
++num;
}
}
read_unlock_bh(lock);
}
done:
cb->args[1] = i;
cb->args[2] = num;
unlock:
inet_diag_unlock_handler(handler);
return skb->len;
}
static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int hdrlen = sizeof(struct inet_diag_req);
if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
nlmsg_len(nlh) < hdrlen)
return -EINVAL;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
if (nlmsg_attrlen(nlh, hdrlen)) {
struct nlattr *attr;
attr = nlmsg_find_attr(nlh, hdrlen,
INET_DIAG_REQ_BYTECODE);
if (attr == NULL ||
nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
return -EINVAL;
}
return netlink_dump_start(idiagnl, skb, nlh,
inet_diag_dump, NULL);
}
return inet_diag_get_exact(skb, nlh);
}
[INET_DIAG]: Fix oops in netlink_rcv_skb netlink_run_queue() doesn't handle multiple processes processing the queue concurrently. Serialize queue processing in inet_diag to fix a oops in netlink_rcv_skb caused by netlink_run_queue passing a NULL for the skb. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000054 [349587.500454] printing eip: [349587.500457] c03318ae [349587.500459] *pde = 00000000 [349587.500464] Oops: 0000 [#1] [349587.500466] PREEMPT SMP [349587.500474] Modules linked in: w83627hf hwmon_vid i2c_isa [349587.500483] CPU: 0 [349587.500485] EIP: 0060:[<c03318ae>] Not tainted VLI [349587.500487] EFLAGS: 00010246 (2.6.22.3 #1) [349587.500499] EIP is at netlink_rcv_skb+0xa/0x7e [349587.500506] eax: 00000000 ebx: 00000000 ecx: c148d2a0 edx: c0398819 [349587.500510] esi: 00000000 edi: c0398819 ebp: c7a21c8c esp: c7a21c80 [349587.500517] ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068 [349587.500521] Process oidentd (pid: 17943, ti=c7a20000 task=cee231c0 task.ti=c7a20000) [349587.500527] Stack: 00000000 c7a21cac f7c8ba78 c7a21ca4 c0331962 c0398819 f7c8ba00 0000004c [349587.500542] f736f000 c7a21cb4 c03988e3 00000001 f7c8ba00 c7a21cc4 c03312a5 0000004c [349587.500558] f7c8ba00 c7a21cd4 c0330681 f7c8ba00 e4695280 c7a21d00 c03307c6 7fffffff [349587.500578] Call Trace: [349587.500581] [<c010361a>] show_trace_log_lvl+0x1c/0x33 [349587.500591] [<c01036d4>] show_stack_log_lvl+0x8d/0xaa [349587.500595] [<c010390e>] show_registers+0x1cb/0x321 [349587.500604] [<c0103bff>] die+0x112/0x1e1 [349587.500607] [<c01132d2>] do_page_fault+0x229/0x565 [349587.500618] [<c03c8d3a>] error_code+0x72/0x78 [349587.500625] [<c0331962>] netlink_run_queue+0x40/0x76 [349587.500632] [<c03988e3>] inet_diag_rcv+0x1f/0x2c [349587.500639] [<c03312a5>] netlink_data_ready+0x57/0x59 [349587.500643] [<c0330681>] netlink_sendskb+0x24/0x45 [349587.500651] [<c03307c6>] netlink_unicast+0x100/0x116 [349587.500656] [<c0330f83>] netlink_sendmsg+0x1c2/0x280 [349587.500664] [<c02fcce9>] sock_sendmsg+0xba/0xd5 [349587.500671] [<c02fe4d1>] sys_sendmsg+0x17b/0x1e8 [349587.500676] [<c02fe92d>] sys_socketcall+0x230/0x24d [349587.500684] [<c01028d2>] syscall_call+0x7/0xb [349587.500691] ======================= [349587.500693] Code: f0 ff 4e 18 0f 94 c0 84 c0 0f 84 66 ff ff ff 89 f0 e8 86 e2 fc ff e9 5a ff ff ff f0 ff 40 10 eb be 55 89 e5 57 89 d7 56 89 c6 53 <8b> 50 54 83 fa 10 72 55 8b 9e 9c 00 00 00 31 c9 8b 03 83 f8 0f Reported by Athanasius <link@miggy.org> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-11 17:33:28 +08:00
static DEFINE_MUTEX(inet_diag_mutex);
static void inet_diag_rcv(struct sk_buff *skb)
{
mutex_lock(&inet_diag_mutex);
netlink_rcv_skb(skb, &inet_diag_rcv_msg);
mutex_unlock(&inet_diag_mutex);
}
int inet_diag_register(const struct inet_diag_handler *h)
{
const __u16 type = h->idiag_type;
int err = -EINVAL;
if (type >= INET_DIAG_GETSOCK_MAX)
goto out;
mutex_lock(&inet_diag_table_mutex);
err = -EEXIST;
if (inet_diag_table[type] == NULL) {
inet_diag_table[type] = h;
err = 0;
}
mutex_unlock(&inet_diag_table_mutex);
out:
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_register);
void inet_diag_unregister(const struct inet_diag_handler *h)
{
const __u16 type = h->idiag_type;
if (type >= INET_DIAG_GETSOCK_MAX)
return;
mutex_lock(&inet_diag_table_mutex);
inet_diag_table[type] = NULL;
mutex_unlock(&inet_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(inet_diag_unregister);
static int __init inet_diag_init(void)
{
const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX *
sizeof(struct inet_diag_handler *));
int err = -ENOMEM;
inet_diag_table = kzalloc(inet_diag_table_size, GFP_KERNEL);
if (!inet_diag_table)
goto out;
idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0,
inet_diag_rcv, NULL, THIS_MODULE);
if (idiagnl == NULL)
goto out_free_table;
err = 0;
out:
return err;
out_free_table:
kfree(inet_diag_table);
goto out;
}
static void __exit inet_diag_exit(void)
{
netlink_kernel_release(idiagnl);
kfree(inet_diag_table);
}
module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG);