linux_dsm_epyc7002/net/ipv4/ip_fragment.c

899 lines
21 KiB
C
Raw Normal View History

/*
* 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.
*
* The IP fragmentation functionality.
*
* Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox <alan@lxorguk.ukuu.org.uk>
*
* Fixes:
* Alan Cox : Split from ip.c , see ip_input.c for history.
* David S. Miller : Begin massive cleanup...
* Andi Kleen : Add sysctls.
* xxxx : Overlapfrag bug.
* Ultima : ip_expire() kernel panic.
* Bill Hawes : Frag accounting and evictor fixes.
* John McDonald : 0 length frag bug.
* Alexey Kuznetsov: SMP races, threading, cleanup.
* Patrick McHardy : LRU queue of frag heads for evictor.
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/jiffies.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/jhash.h>
#include <linux/random.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 15:04:11 +07:00
#include <linux/slab.h>
#include <net/route.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/inet_frag.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/inet.h>
#include <linux/netfilter_ipv4.h>
#include <net/inet_ecn.h>
#include <net/l3mdev.h>
/* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
* code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
* as well. Or notify me, at least. --ANK
*/
static const char ip_frag_cache_name[] = "ip4-frags";
struct ipfrag_skb_cb
{
struct inet_skb_parm h;
int offset;
};
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
struct inet_frag_queue q;
u32 user;
__be32 saddr;
__be32 daddr;
__be16 id;
u8 protocol;
u8 ecn; /* RFC3168 support */
2015-05-22 21:32:51 +07:00
u16 max_df_size; /* largest frag with DF set seen */
int iif;
int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
static u8 ip4_frag_ecn(u8 tos)
{
return 1 << (tos & INET_ECN_MASK);
}
static struct inet_frags ip4_frags;
int ip_frag_mem(struct net *net)
{
return sum_frag_mem_limit(&net->ipv4.frags);
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
struct ip4_create_arg {
struct iphdr *iph;
u32 user;
int vif;
};
static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
{
net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
return jhash_3words((__force u32)id << 16 | prot,
(__force u32)saddr, (__force u32)daddr,
ip4_frags.rnd);
}
static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
{
const struct ipq *ipq;
ipq = container_of(q, struct ipq, q);
return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
}
static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
{
const struct ipq *qp;
const struct ip4_create_arg *arg = a;
qp = container_of(q, struct ipq, q);
return qp->id == arg->iph->id &&
qp->saddr == arg->iph->saddr &&
qp->daddr == arg->iph->daddr &&
qp->protocol == arg->iph->protocol &&
qp->user == arg->user &&
qp->vif == arg->vif;
}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
struct ipq *qp = container_of(q, struct ipq, q);
struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
const struct ip4_create_arg *arg = a;
qp->protocol = arg->iph->protocol;
qp->id = arg->iph->id;
qp->ecn = ip4_frag_ecn(arg->iph->tos);
qp->saddr = arg->iph->saddr;
qp->daddr = arg->iph->daddr;
qp->vif = arg->vif;
qp->user = arg->user;
qp->peer = q->net->max_dist ?
inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
NULL;
}
static void ip4_frag_free(struct inet_frag_queue *q)
{
struct ipq *qp;
qp = container_of(q, struct ipq, q);
if (qp->peer)
inet_putpeer(qp->peer);
}
/* Destruction primitives. */
static void ipq_put(struct ipq *ipq)
{
inet_frag_put(&ipq->q, &ip4_frags);
}
/* Kill ipq entry. It is not destroyed immediately,
* because caller (and someone more) holds reference count.
*/
static void ipq_kill(struct ipq *ipq)
{
inet_frag_kill(&ipq->q, &ip4_frags);
}
static bool frag_expire_skip_icmp(u32 user)
{
return user == IP_DEFRAG_AF_PACKET ||
ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN,
__IP_DEFRAG_CONNTRACK_IN_END) ||
ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP_DEFRAG_CONNTRACK_BRIDGE_IN);
}
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(unsigned long arg)
{
struct ipq *qp;
struct net *net;
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
if (!inet_frag_evicting(&qp->q)) {
struct sk_buff *head = qp->q.fragments;
const struct iphdr *iph;
int err;
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
rcu_read_lock();
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out_rcu_unlock;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out_rcu_unlock;
/* Send an ICMP "Fragment Reassembly Timeout" message. */
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
rcu_read_unlock();
}
out:
spin_unlock(&qp->q.lock);
ipq_put(qp);
}
/* Find the correct entry in the "incomplete datagrams" queue for
* this IP datagram, and create new one, if nothing is found.
*/
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
struct inet_frag_queue *q;
struct ip4_create_arg arg;
unsigned int hash;
arg.iph = iph;
arg.user = user;
arg.vif = vif;
hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
}
return container_of(q, struct ipq, q);
}
/* Is the fragment too far ahead to be part of ipq? */
static int ip_frag_too_far(struct ipq *qp)
{
struct inet_peer *peer = qp->peer;
unsigned int max = qp->q.net->max_dist;
unsigned int start, end;
int rc;
if (!peer || !max)
return 0;
start = qp->rid;
end = atomic_inc_return(&peer->rid);
qp->rid = end;
rc = qp->q.fragments && (end - start) > max;
if (rc) {
struct net *net;
net = container_of(qp->q.net, struct net, ipv4.frags);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
}
return rc;
}
static int ip_frag_reinit(struct ipq *qp)
{
struct sk_buff *fp;
unsigned int sum_truesize = 0;
if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
atomic_inc(&qp->q.refcnt);
return -ETIMEDOUT;
}
fp = qp->q.fragments;
do {
struct sk_buff *xp = fp->next;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
} while (fp);
sub_frag_mem_limit(qp->q.net, sum_truesize);
qp->q.flags = 0;
qp->q.len = 0;
qp->q.meat = 0;
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
qp->iif = 0;
qp->ecn = 0;
return 0;
}
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct sk_buff *prev, *next;
struct net_device *dev;
2015-05-22 21:32:51 +07:00
unsigned int fragsize;
int flags, offset;
int ihl, end;
int err = -ENOENT;
u8 ecn;
if (qp->q.flags & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
unlikely(ip_frag_too_far(qp)) &&
unlikely(err = ip_frag_reinit(qp))) {
ipq_kill(qp);
goto err;
}
ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
offset <<= 3; /* offset is in 8-byte chunks */
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
if ((flags & IP_MF) == 0) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < qp->q.len ||
((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
goto err;
qp->q.flags |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
end &= ~7;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.flags & INET_FRAG_LAST_IN)
goto err;
qp->q.len = end;
}
}
if (end == offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
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 = qp->q.fragments_tail;
if (!prev || FRAG_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
if (FRAG_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* We found where to put this one. Check for overlap with
* preceding fragment, and, if needed, align things so that
* any overlaps are eliminated.
*/
if (prev) {
int i = (FRAG_CB(prev)->offset + prev->len) - offset;
if (i > 0) {
offset += i;
err = -EINVAL;
if (end <= offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, i))
goto err;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
}
err = -ENOMEM;
while (next && FRAG_CB(next)->offset < end) {
int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
if (i < next->len) {
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
FRAG_CB(next)->offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
break;
} else {
struct sk_buff *free_it = next;
/* Old fragment is completely overridden with
* new one drop it.
*/
next = next->next;
if (prev)
prev->next = next;
else
qp->q.fragments = next;
qp->q.meat -= free_it->len;
sub_frag_mem_limit(qp->q.net, free_it->truesize);
kfree_skb(free_it);
}
}
FRAG_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
qp->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
qp->q.fragments = skb;
dev = skb->dev;
if (dev) {
qp->iif = dev->ifindex;
skb->dev = NULL;
}
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
add_frag_mem_limit(qp->q.net, skb->truesize);
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
2015-05-22 21:32:51 +07:00
fragsize = skb->len + ihl;
if (fragsize > qp->q.max_size)
qp->q.max_size = fragsize;
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
2015-05-22 21:32:51 +07:00
fragsize > qp->max_df_size)
qp->max_df_size = fragsize;
if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, prev, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
err:
kfree_skb(skb);
return err;
}
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(!head);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* 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;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_nomem;
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;
add_frag_mem_limit(qp->q.net, clone->truesize);
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
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);
head->truesize += fp->truesize;
}
sub_frag_mem_limit(qp->q.net, head->truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
2015-05-22 21:32:51 +07:00
IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(head);
iph->tot_len = htons(len);
iph->tos |= ecn;
2015-05-22 21:32:51 +07:00
/* When we set IP_DF on a refragmented skb we must also force a
* call to ip_fragment to avoid forwarding a DF-skb of size s while
* original sender only sent fragments of size f (where f < s).
*
* We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
* frag seen to avoid sending tiny DF-fragments in case skb was built
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
IPCB(head)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
}
ip_send_check(iph);
__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
}
/* Process an incoming IP datagram fragment. */
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
int vif = l3mdev_master_ifindex_rcu(dev);
struct ipq *qp;
__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
inet: frag: Always orphan skbs inside ip_defrag() Later parts of the stack (including fragmentation) expect that there is never a socket attached to frag in a frag_list, however this invariant was not enforced on all defrag paths. This could lead to the BUG_ON(skb->sk) during ip_do_fragment(), as per the call stack at the end of this commit message. While the call could be added to openvswitch to fix this particular error, the head and tail of the frags list are already orphaned indirectly inside ip_defrag(), so it seems like the remaining fragments should all be orphaned in all circumstances. kernel BUG at net/ipv4/ip_output.c:586! [...] Call Trace: <IRQ> [<ffffffffa0205270>] ? do_output.isra.29+0x1b0/0x1b0 [openvswitch] [<ffffffffa02167a7>] ovs_fragment+0xcc/0x214 [openvswitch] [<ffffffff81667830>] ? dst_discard_out+0x20/0x20 [<ffffffff81667810>] ? dst_ifdown+0x80/0x80 [<ffffffffa0212072>] ? find_bucket.isra.2+0x62/0x70 [openvswitch] [<ffffffff810e0ba5>] ? mod_timer_pending+0x65/0x210 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90 [<ffffffffa03205a2>] ? nf_conntrack_in+0x252/0x500 [nf_conntrack] [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70 [<ffffffffa02051a3>] do_output.isra.29+0xe3/0x1b0 [openvswitch] [<ffffffffa0206411>] do_execute_actions+0xe11/0x11f0 [openvswitch] [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70 [<ffffffffa0206822>] ovs_execute_actions+0x32/0xd0 [openvswitch] [<ffffffffa020b505>] ovs_dp_process_packet+0x85/0x140 [openvswitch] [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70 [<ffffffffa02068a2>] ovs_execute_actions+0xb2/0xd0 [openvswitch] [<ffffffffa020b505>] ovs_dp_process_packet+0x85/0x140 [openvswitch] [<ffffffffa0215019>] ? ovs_ct_get_labels+0x49/0x80 [openvswitch] [<ffffffffa0213a1d>] ovs_vport_receive+0x5d/0xa0 [openvswitch] [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90 [<ffffffffa0214895>] ? internal_dev_xmit+0x5/0x140 [openvswitch] [<ffffffffa02148fc>] internal_dev_xmit+0x6c/0x140 [openvswitch] [<ffffffffa0214895>] ? internal_dev_xmit+0x5/0x140 [openvswitch] [<ffffffff81660299>] dev_hard_start_xmit+0x2b9/0x5e0 [<ffffffff8165fc21>] ? netif_skb_features+0xd1/0x1f0 [<ffffffff81660f20>] __dev_queue_xmit+0x800/0x930 [<ffffffff81660770>] ? __dev_queue_xmit+0x50/0x930 [<ffffffff810b53f1>] ? mark_held_locks+0x71/0x90 [<ffffffff81669876>] ? neigh_resolve_output+0x106/0x220 [<ffffffff81661060>] dev_queue_xmit+0x10/0x20 [<ffffffff816698e8>] neigh_resolve_output+0x178/0x220 [<ffffffff816a8e6f>] ? ip_finish_output2+0x1ff/0x590 [<ffffffff816a8e6f>] ip_finish_output2+0x1ff/0x590 [<ffffffff816a8cee>] ? ip_finish_output2+0x7e/0x590 [<ffffffff816a9a31>] ip_do_fragment+0x831/0x8a0 [<ffffffff816a8c70>] ? ip_copy_metadata+0x1b0/0x1b0 [<ffffffff816a9ae3>] ip_fragment.constprop.49+0x43/0x80 [<ffffffff816a9c9c>] ip_finish_output+0x17c/0x340 [<ffffffff8169a6f4>] ? nf_hook_slow+0xe4/0x190 [<ffffffff816ab4c0>] ip_output+0x70/0x110 [<ffffffff816a9b20>] ? ip_fragment.constprop.49+0x80/0x80 [<ffffffff816aa9f9>] ip_local_out+0x39/0x70 [<ffffffff816abf89>] ip_send_skb+0x19/0x40 [<ffffffff816abfe3>] ip_push_pending_frames+0x33/0x40 [<ffffffff816df21a>] icmp_push_reply+0xea/0x120 [<ffffffff816df93d>] icmp_reply.constprop.23+0x1ed/0x230 [<ffffffff816df9ce>] icmp_echo.part.21+0x4e/0x50 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70 [<ffffffff810d5f9e>] ? rcu_read_lock_held+0x5e/0x70 [<ffffffff816dfa06>] icmp_echo+0x36/0x70 [<ffffffff816e0d11>] icmp_rcv+0x271/0x450 [<ffffffff816a4ca7>] ip_local_deliver_finish+0x127/0x3a0 [<ffffffff816a4bc1>] ? ip_local_deliver_finish+0x41/0x3a0 [<ffffffff816a5160>] ip_local_deliver+0x60/0xd0 [<ffffffff816a4b80>] ? ip_rcv_finish+0x560/0x560 [<ffffffff816a46fd>] ip_rcv_finish+0xdd/0x560 [<ffffffff816a5453>] ip_rcv+0x283/0x3e0 [<ffffffff810b6302>] ? match_held_lock+0x192/0x200 [<ffffffff816a4620>] ? inet_del_offload+0x40/0x40 [<ffffffff8165d062>] __netif_receive_skb_core+0x392/0xae0 [<ffffffff8165e68e>] ? process_backlog+0x8e/0x230 [<ffffffff810b53f1>] ? mark_held_locks+0x71/0x90 [<ffffffff8165d7c8>] __netif_receive_skb+0x18/0x60 [<ffffffff8165e678>] process_backlog+0x78/0x230 [<ffffffff8165e6dd>] ? process_backlog+0xdd/0x230 [<ffffffff8165e355>] net_rx_action+0x155/0x400 [<ffffffff8106b48c>] __do_softirq+0xcc/0x420 [<ffffffff816a8e87>] ? ip_finish_output2+0x217/0x590 [<ffffffff8178e78c>] do_softirq_own_stack+0x1c/0x30 <EOI> [<ffffffff8106b88e>] do_softirq+0x4e/0x60 [<ffffffff8106b948>] __local_bh_enable_ip+0xa8/0xb0 [<ffffffff816a8eb0>] ip_finish_output2+0x240/0x590 [<ffffffff816a9a31>] ? ip_do_fragment+0x831/0x8a0 [<ffffffff816a9a31>] ip_do_fragment+0x831/0x8a0 [<ffffffff816a8c70>] ? ip_copy_metadata+0x1b0/0x1b0 [<ffffffff816a9ae3>] ip_fragment.constprop.49+0x43/0x80 [<ffffffff816a9c9c>] ip_finish_output+0x17c/0x340 [<ffffffff8169a6f4>] ? nf_hook_slow+0xe4/0x190 [<ffffffff816ab4c0>] ip_output+0x70/0x110 [<ffffffff816a9b20>] ? ip_fragment.constprop.49+0x80/0x80 [<ffffffff816aa9f9>] ip_local_out+0x39/0x70 [<ffffffff816abf89>] ip_send_skb+0x19/0x40 [<ffffffff816abfe3>] ip_push_pending_frames+0x33/0x40 [<ffffffff816d55d3>] raw_sendmsg+0x7d3/0xc30 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90 [<ffffffff816e7557>] ? inet_sendmsg+0xc7/0x1d0 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70 [<ffffffff816e759a>] inet_sendmsg+0x10a/0x1d0 [<ffffffff816e7495>] ? inet_sendmsg+0x5/0x1d0 [<ffffffff8163e398>] sock_sendmsg+0x38/0x50 [<ffffffff8163ec5f>] ___sys_sendmsg+0x25f/0x270 [<ffffffff811aadad>] ? handle_mm_fault+0x8dd/0x1320 [<ffffffff8178c147>] ? _raw_spin_unlock+0x27/0x40 [<ffffffff810529b2>] ? __do_page_fault+0x1e2/0x460 [<ffffffff81204886>] ? __fget_light+0x66/0x90 [<ffffffff8163f8e2>] __sys_sendmsg+0x42/0x80 [<ffffffff8163f932>] SyS_sendmsg+0x12/0x20 [<ffffffff8178cb17>] entry_SYSCALL_64_fastpath+0x12/0x6f Code: 00 00 44 89 e0 e9 7c fb ff ff 4c 89 ff e8 e7 e7 ff ff 41 8b 9d 80 00 00 00 2b 5d d4 89 d8 c1 f8 03 0f b7 c0 e9 33 ff ff f 66 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48 RIP [<ffffffff816a9a92>] ip_do_fragment+0x892/0x8a0 RSP <ffff88006d603170> Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action") Signed-off-by: Joe Stringer <joe@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-23 06:49:12 +07:00
skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
if (qp) {
int ret;
spin_lock(&qp->q.lock);
ret = ip_frag_queue(qp, skb);
spin_unlock(&qp->q.lock);
ipq_put(qp);
return ret;
}
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -ENOMEM;
}
EXPORT_SYMBOL(ip_defrag);
struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct iphdr iph;
int netoff;
u32 len;
if (skb->protocol != htons(ETH_P_IP))
return skb;
netoff = skb_network_offset(skb);
if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
return skb;
if (iph.ihl < 5 || iph.version != 4)
return skb;
len = ntohs(iph.tot_len);
if (skb->len < netoff + len || len < (iph.ihl * 4))
return skb;
if (ip_is_fragment(&iph)) {
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb) {
if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
return skb;
if (pskb_trim_rcsum(skb, netoff + len))
return skb;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (ip_defrag(net, skb, user))
return NULL;
skb_clear_hash(skb);
}
}
return skb;
}
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
static int zero;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &init_net.ipv4.frags.low_thresh
},
{
.procname = "ipfrag_low_thresh",
.data = &init_net.ipv4.frags.low_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ipv4.frags.high_thresh
},
{
.procname = "ipfrag_time",
.data = &init_net.ipv4.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "ipfrag_max_dist",
.data = &init_net.ipv4.frags.max_dist,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero
},
{ }
};
/* secret interval has been deprecated */
static int ip4_frags_secret_interval_unused;
static struct ctl_table ip4_frags_ctl_table[] = {
{
.procname = "ipfrag_secret_interval",
.data = &ip4_frags_secret_interval_unused,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{ }
};
static int __net_init ip4_frags_ns_ctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = ip4_frags_ns_ctl_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
if (!table)
goto err_alloc;
table[0].data = &net->ipv4.frags.high_thresh;
table[0].extra1 = &net->ipv4.frags.low_thresh;
table[0].extra2 = &init_net.ipv4.frags.high_thresh;
table[1].data = &net->ipv4.frags.low_thresh;
table[1].extra2 = &net->ipv4.frags.high_thresh;
table[2].data = &net->ipv4.frags.timeout;
table[3].data = &net->ipv4.frags.max_dist;
}
hdr = register_net_sysctl(net, "net/ipv4", table);
if (!hdr)
goto err_reg;
net->ipv4.frags_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
{
struct ctl_table *table;
table = net->ipv4.frags_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.frags_hdr);
kfree(table);
}
static void __init ip4_frags_ctl_register(void)
{
register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
}
#else
static int ip4_frags_ns_ctl_register(struct net *net)
{
return 0;
}
static void ip4_frags_ns_ctl_unregister(struct net *net)
{
}
static void __init ip4_frags_ctl_register(void)
{
}
#endif
static int __net_init ipv4_frags_init_net(struct net *net)
{
int res;
net: increase fragment memory usage limits Increase the amount of memory usage limits for incomplete IP fragments. Arguing for new thresh high/low values: High threshold = 4 MBytes Low threshold = 3 MBytes The fragmentation memory accounting code, tries to account for the real memory usage, by measuring both the size of frag queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) and the SKB's truesize. We want to be able to handle/hold-on-to enough fragments, to ensure good performance, without causing incomplete fragments to hurt scalability, by causing the number of inet_frag_queue to grow too much (resulting longer searches for frag queues). For IPv4, how much memory does the largest frag consume. Maximum size fragment is 64K, which is approx 44 fragments with MTU(1500) sized packets. Sizeof(struct ipq) is 200. A 1500 byte packet results in a truesize of 2944 (not 2048 as I first assumed) (44*2944)+200 = 129736 bytes The current default high thresh of 262144 bytes, is obviously problematic, as only two 64K fragments can fit in the queue at the same time. How many 64K fragment can we fit into 4 MBytes: 4*2^20/((44*2944)+200) = 32.34 fragment in queues An attacker could send a separate/distinct fake fragment packets per queue, causing us to allocate one inet_frag_queue per packet, and thus attacking the hash table and its lists. How many frag queue do we need to store, and given a current hash size of 64, what is the average list length. Using one MTU sized fragment per inet_frag_queue, each consuming (2944+200) 3144 bytes. 4*2^20/(2944+200) = 1334 frag queues -> 21 avg list length An attack could send small fragments, the smallest packet I could send resulted in a truesize of 896 bytes (I'm a little surprised by this). 4*2^20/(896+200) = 3827 frag queues -> 59 avg list length When increasing these number, we also need to followup with improvements, that is going to help scalability. Simply increasing the hash size, is not enough as the current implementation does not have a per hash bucket locking. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-15 14:16:35 +07:00
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
* the real memory usage, by measuring both the size of frag
* queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
* and the SKB's truesize.
*
* A 64K fragment consumes 129736 bytes (44*2944)+200
* (1500 truesize == 2944, sizeof(struct ipq) == 200)
*
* We will commit 4MB at one time. Should we cross that limit
* we will prune down to 3MB, making room for approx 8 big 64K
* fragments 8x128k.
*/
net: increase fragment memory usage limits Increase the amount of memory usage limits for incomplete IP fragments. Arguing for new thresh high/low values: High threshold = 4 MBytes Low threshold = 3 MBytes The fragmentation memory accounting code, tries to account for the real memory usage, by measuring both the size of frag queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) and the SKB's truesize. We want to be able to handle/hold-on-to enough fragments, to ensure good performance, without causing incomplete fragments to hurt scalability, by causing the number of inet_frag_queue to grow too much (resulting longer searches for frag queues). For IPv4, how much memory does the largest frag consume. Maximum size fragment is 64K, which is approx 44 fragments with MTU(1500) sized packets. Sizeof(struct ipq) is 200. A 1500 byte packet results in a truesize of 2944 (not 2048 as I first assumed) (44*2944)+200 = 129736 bytes The current default high thresh of 262144 bytes, is obviously problematic, as only two 64K fragments can fit in the queue at the same time. How many 64K fragment can we fit into 4 MBytes: 4*2^20/((44*2944)+200) = 32.34 fragment in queues An attacker could send a separate/distinct fake fragment packets per queue, causing us to allocate one inet_frag_queue per packet, and thus attacking the hash table and its lists. How many frag queue do we need to store, and given a current hash size of 64, what is the average list length. Using one MTU sized fragment per inet_frag_queue, each consuming (2944+200) 3144 bytes. 4*2^20/(2944+200) = 1334 frag queues -> 21 avg list length An attack could send small fragments, the smallest packet I could send resulted in a truesize of 896 bytes (I'm a little surprised by this). 4*2^20/(896+200) = 3827 frag queues -> 59 avg list length When increasing these number, we also need to followup with improvements, that is going to help scalability. Simply increasing the hash size, is not enough as the current implementation does not have a per hash bucket locking. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-15 14:16:35 +07:00
net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
net->ipv4.frags.low_thresh = 3 * 1024 * 1024;
/*
* Important NOTE! Fragment queue must be destroyed before MSL expires.
* RFC791 is wrong proposing to prolongate timer each fragment arrival
* by TTL.
*/
net->ipv4.frags.timeout = IP_FRAG_TIME;
net->ipv4.frags.max_dist = 64;
res = inet_frags_init_net(&net->ipv4.frags);
if (res)
return res;
res = ip4_frags_ns_ctl_register(net);
if (res)
inet_frags_uninit_net(&net->ipv4.frags);
return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
{
ip4_frags_ns_ctl_unregister(net);
inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
}
static struct pernet_operations ip4_frags_ops = {
.init = ipv4_frags_init_net,
.exit = ipv4_frags_exit_net,
};
void __init ipfrag_init(void)
{
ip4_frags_ctl_register();
register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
}