linux/net/ipv6/reassembly.c

783 lines
19 KiB
C
Raw Normal View History

/*
* IPv6 fragment reassembly
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on: net/ipv4/ip_fragment.c
*
* 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.
*/
/*
* Fixes:
* Andi Kleen Make it work with multiple hosts.
* More RFC compliance.
*
* Horst von Brand Add missing #include <linux/string.h>
* Alexey Kuznetsov SMP races, threading, cleanup.
* Patrick McHardy LRU queue of frag heads for evictor.
* Mitsuru KANDA @USAGI Register inet6_protocol{}.
* David Stevens and
* YOSHIFUJI,H. @USAGI Always remove fragment header to
* calculate ICV correctly.
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/net.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/skbuff.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
struct ip6frag_skb_cb
{
struct inet6_skb_parm h;
int offset;
};
#define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb))
/*
* Equivalent of ipv4 struct ipq
*/
struct frag_queue
{
struct inet_frag_queue q;
__be32 id; /* fragment id */
u32 user;
struct in6_addr saddr;
struct in6_addr daddr;
int iif;
unsigned int csum;
__u16 nhoffset;
};
static struct inet_frags ip6_frags;
int ip6_frag_nqueues(struct net *net)
{
return net->ipv6.frags.nqueues;
}
int ip6_frag_mem(struct net *net)
{
return atomic_read(&net->ipv6.frags.mem);
}
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
/*
* callers should be careful not to use the hash value outside the ipfrag_lock
* as doing so could race with ipfrag_hash_rnd being recalculated.
*/
unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
const struct in6_addr *daddr, u32 rnd)
{
u32 c;
c = jhash_3words((__force u32)saddr->s6_addr32[0],
(__force u32)saddr->s6_addr32[1],
(__force u32)saddr->s6_addr32[2],
rnd);
c = jhash_3words((__force u32)saddr->s6_addr32[3],
(__force u32)daddr->s6_addr32[0],
(__force u32)daddr->s6_addr32[1],
c);
c = jhash_3words((__force u32)daddr->s6_addr32[2],
(__force u32)daddr->s6_addr32[3],
(__force u32)id,
c);
return c & (INETFRAGS_HASHSZ - 1);
}
EXPORT_SYMBOL_GPL(inet6_hash_frag);
static unsigned int ip6_hashfn(struct inet_frag_queue *q)
{
struct frag_queue *fq;
fq = container_of(q, struct frag_queue, q);
return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
}
bool ip6_frag_match(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq;
struct ip6_create_arg *arg = a;
fq = container_of(q, struct frag_queue, q);
return fq->id == arg->id &&
fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
ipv6_addr_equal(&fq->daddr, arg->dst);
}
EXPORT_SYMBOL(ip6_frag_match);
void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
struct ip6_create_arg *arg = a;
fq->id = arg->id;
fq->user = arg->user;
fq->saddr = *arg->src;
fq->daddr = *arg->dst;
}
EXPORT_SYMBOL(ip6_frag_init);
/* Destruction primitives. */
static __inline__ void fq_put(struct frag_queue *fq)
{
inet_frag_put(&fq->q, &ip6_frags);
}
/* Kill fq entry. It is not destroyed immediately,
* because caller (and someone more) holds reference count.
*/
static __inline__ void fq_kill(struct frag_queue *fq)
{
inet_frag_kill(&fq->q, &ip6_frags);
}
static void ip6_evictor(struct net *net, struct inet6_dev *idev)
{
int evicted;
evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags);
if (evicted)
IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted);
}
static void ip6_frag_expire(unsigned long data)
{
struct frag_queue *fq;
struct net_device *dev = NULL;
struct net *net;
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
spin_lock(&fq->q.lock);
if (fq->q.last_in & INET_FRAG_COMPLETE)
goto out;
fq_kill(fq);
net = container_of(fq->q.net, struct net, ipv6.frags);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
if (!dev)
goto out_rcu_unlock;
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
/* Don't send error if the first segment did not arrive. */
if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
goto out_rcu_unlock;
/*
But use as source device on which LAST ARRIVED
segment was received. And do not use fq->dev
pointer directly, device might already disappeared.
*/
fq->q.fragments->dev = dev;
icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
out_rcu_unlock:
rcu_read_unlock();
out:
spin_unlock(&fq->q.lock);
fq_put(fq);
}
static __inline__ struct frag_queue *
fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6_addr *dst)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
unsigned int hash;
arg.id = id;
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
read_lock(&ip6_frags.lock);
hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
if (q == NULL)
return NULL;
return container_of(q, struct frag_queue, q);
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int offset, end;
struct net *net = dev_net(skb_dst(skb)->dev);
if (fq->q.last_in & INET_FRAG_COMPLETE)
goto err;
offset = ntohs(fhdr->frag_off) & ~0x7;
end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
((u8 *)&fhdr->frag_off -
skb_network_header(skb)));
return -1;
}
if (skb->ip_summed == CHECKSUM_COMPLETE) {
const unsigned char *nh = skb_network_header(skb);
skb->csum = csum_sub(skb->csum,
csum_partial(nh, (u8 *)(fhdr + 1) - nh,
0));
}
/* Is this the final fragment? */
if (!(fhdr->frag_off & htons(IP6_MF))) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < fq->q.len ||
((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.last_in |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
/* Check if the fragment is rounded to 8 bytes.
* Required by the RFC.
*/
if (end & 0x7) {
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, payload_len));
return -1;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.last_in & INET_FRAG_LAST_IN)
goto err;
fq->q.len = end;
}
}
if (end == offset)
goto err;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto err;
if (pskb_trim_rcsum(skb, end - offset))
goto err;
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
* this fragment, right?
*/
prev = fq->q.fragments_tail;
if (!prev || FRAG6_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for(next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* RFC5722, Section 4, amended by Errata ID : 3089
* When reassembling an IPv6 datagram, if
* one or more its constituent fragments is determined to be an
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*/
/* Check for overlap with preceding fragment. */
if (prev &&
(FRAG6_CB(prev)->offset + prev->len) > offset)
goto discard_fq;
/* Look for overlap with succeeding segment. */
if (next && FRAG6_CB(next)->offset < end)
goto discard_fq;
FRAG6_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
fq->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
fq->q.fragments = skb;
dev = skb->dev;
if (dev) {
fq->iif = dev->ifindex;
skb->dev = NULL;
}
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
atomic_add(skb->truesize, &fq->q.net->mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.last_in |= INET_FRAG_FIRST_IN;
}
if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len)
return ip6_frag_reasm(fq, prev, dev);
write_lock(&ip6_frags.lock);
list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
write_unlock(&ip6_frags.lock);
return -1;
discard_fq:
fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
/*
* Check if this packet is complete.
* Returns NULL on failure by any reason, and pointer
* to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
int sum_truesize;
fq_kill(fq);
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
consume_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG6_CB(head)->offset != 0);
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_oom;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_oom;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
atomic_add(clone->truesize, &fq->q.net->mem);
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
sum_truesize = head->truesize;
for (fp = head->next; fp;) {
bool headstolen;
int delta;
struct sk_buff *next = fp->next;
sum_truesize += fp->truesize;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
kfree_skb_partial(fp, headstolen);
} else {
if (!skb_shinfo(head)->frag_list)
skb_shinfo(head)->frag_list = fp;
head->data_len += fp->len;
head->len += fp->len;
head->truesize += fp->truesize;
}
fp = next;
}
atomic_sub(sum_truesize, &fq->q.net->mem);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
/* Yes, and fold redundant checksum back. 8) */
if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_partial(skb_network_header(head),
skb_network_header_len(head),
head->csum);
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.fragments_tail = NULL;
return 1;
out_oversize:
net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
static int ipv6_frag_rcv(struct sk_buff *skb)
{
struct frag_hdr *fhdr;
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
if (hdr->payload_len==0)
goto fail_hdr;
if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
sizeof(struct frag_hdr))))
goto fail_hdr;
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
if (!(fhdr->frag_off & htons(0xFFF9))) {
/* It is not a fragmented frame */
skb->transport_header += sizeof(struct frag_hdr);
IP6_INC_STATS_BH(net,
ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
return 1;
}
if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
ip6_evictor(net, ip6_dst_idev(skb_dst(skb)));
fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr);
if (fq != NULL) {
int ret;
spin_lock(&fq->q.lock);
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
fq_put(fq);
return ret;
}
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
fail_hdr:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
return -1;
}
static const struct inet6_protocol frag_protocol =
{
.handler = ipv6_frag_rcv,
.flags = INET6_PROTO_NOPOLICY,
};
#ifdef CONFIG_SYSCTL
static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
.procname = "ip6frag_high_thresh",
.data = &init_net.ipv6.frags.high_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip6frag_low_thresh",
.data = &init_net.ipv6.frags.low_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip6frag_time",
.data = &init_net.ipv6.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{ }
};
static struct ctl_table ip6_frags_ctl_table[] = {
{
.procname = "ip6frag_secret_interval",
.data = &ip6_frags.secret_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{ }
};
static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = ip6_frags_ns_ctl_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
table[0].data = &net->ipv6.frags.high_thresh;
table[1].data = &net->ipv6.frags.low_thresh;
table[2].data = &net->ipv6.frags.timeout;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
if (hdr == NULL)
goto err_reg;
net->ipv6.sysctl.frags_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
{
struct ctl_table *table;
table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
ipv6: fix an oops when force unload ipv6 module When I do an ipv6 module force unload,I got the following oops: #rmmod -f ipv6 ------------[ cut here ]------------ kernel BUG at mm/slub.c:2969! invalid opcode: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:11.0/0000:02:03.0/net/eth2/ifindex Modules linked in: ipv6(-) dm_multipath uinput ppdev tpm_tis tpm tpm_bios pcspkr pcnet32 mii parport_pc i2c_piix4 parport i2c_core floppy mptspi mptscsih mptbase scsi_transport_spi Pid: 2530, comm: rmmod Tainted: G R 2.6.32 #2 440BX Desktop Reference Platform/VMware Virtual Platform EIP: 0060:[<c04b73f2>] EFLAGS: 00010246 CPU: 0 EIP is at kfree+0x6a/0xdd EAX: 00000000 EBX: c09e86bc ECX: c043e4dd EDX: c14293e0 ESI: e141f1d8 EDI: e140fc31 EBP: dec58ef0 ESP: dec58ed0 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process rmmod (pid: 2530, ti=dec58000 task=decb1940 task.ti=dec58000) Stack: c14293e0 00000282 df624240 c0897d08 c09e86bc c09e86bc e141f1d8 dec58f1c <0> dec58f00 e140fc31 c09e84c4 e141f1bc dec58f14 c0689d21 dec58f1c e141f1bc <0> 00000000 dec58f2c c0689eff c09e84d8 c09e84d8 e141f1bc bff33a90 dec58f38 Call Trace: [<e140fc31>] ? ipv6_frags_exit_net+0x22/0x32 [ipv6] [<c0689d21>] ? ops_exit_list+0x19/0x3d [<c0689eff>] ? unregister_pernet_operations+0x2a/0x51 [<c0689f70>] ? unregister_pernet_subsys+0x17/0x24 [<e140fbfe>] ? ipv6_frag_exit+0x21/0x32 [ipv6] [<e141a361>] ? inet6_exit+0x47/0x122 [ipv6] [<c045f5de>] ? sys_delete_module+0x198/0x1f6 [<c04a8acf>] ? remove_vma+0x57/0x5d [<c070f63f>] ? do_page_fault+0x2e7/0x315 [<c0403218>] ? sysenter_do_call+0x12/0x28 Code: 86 00 00 00 40 c1 e8 0c c1 e0 05 01 d0 89 45 e0 66 83 38 00 79 06 8b 40 0c 89 45 e0 8b 55 e0 8b 02 84 c0 78 14 66 a9 00 c0 75 04 <0f> 0b eb fe 8b 45 e0 e8 35 15 fe ff eb 5d 8b 45 04 8b 55 e0 89 EIP: [<c04b73f2>] kfree+0x6a/0xdd SS:ESP 0068:dec58ed0 ---[ end trace 4475d1a5b0afa7e5 ]--- It's because in ip6_frags_ns_sysctl_register, "table" only alloced when "net" is not equals to "init_net".So when we free "table" in ip6_frags_ns_sysctl_unregister,we should check this first. This patch fix the problem. Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-19 04:25:13 +00:00
if (!net_eq(net, &init_net))
kfree(table);
}
static struct ctl_table_header *ip6_ctl_header;
static int ip6_frags_sysctl_register(void)
{
ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6",
ip6_frags_ctl_table);
return ip6_ctl_header == NULL ? -ENOMEM : 0;
}
static void ip6_frags_sysctl_unregister(void)
{
unregister_net_sysctl_table(ip6_ctl_header);
}
#else
static inline int ip6_frags_ns_sysctl_register(struct net *net)
{
return 0;
}
static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
{
}
static inline int ip6_frags_sysctl_register(void)
{
return 0;
}
static inline void ip6_frags_sysctl_unregister(void)
{
}
#endif
static int __net_init ipv6_frags_init_net(struct net *net)
{
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
inet_frags_init_net(&net->ipv6.frags);
return ip6_frags_ns_sysctl_register(net);
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
}
static struct pernet_operations ip6_frags_ops = {
.init = ipv6_frags_init_net,
.exit = ipv6_frags_exit_net,
};
int __init ipv6_frag_init(void)
{
int ret;
ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
if (ret)
goto out;
ret = ip6_frags_sysctl_register();
if (ret)
goto err_sysctl;
ret = register_pernet_subsys(&ip6_frags_ops);
if (ret)
goto err_pernet;
ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
ip6_frags.skb_free = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
ip6_frags.match = ip6_frag_match;
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.secret_interval = 10 * 60 * HZ;
inet_frags_init(&ip6_frags);
out:
return ret;
err_pernet:
ip6_frags_sysctl_unregister();
err_sysctl:
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
goto out;
}
void ipv6_frag_exit(void)
{
inet_frags_fini(&ip6_frags);
ip6_frags_sysctl_unregister();
unregister_pernet_subsys(&ip6_frags_ops);
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
}