linux/net/ipv6/reassembly.c

610 lines
15 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 fragment reassembly
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on: net/ipv4/ip_fragment.c
*/
/*
* 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.
*/
#define pr_fmt(fmt) "IPv6: " fmt
#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 <linux/tcp.h>
#include <linux/udp.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/ipv6_frag.h>
#include <net/inet_ecn.h>
static const char ip6_frag_cache_name[] = "ip6-frags";
static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev);
static void ip6_frag_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
fq = container_of(frag, struct frag_queue, q);
ip6frag_expire_frag_queue(fq->q.fqdir->net, fq);
}
static struct frag_queue *
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
struct frag_v6_compare_key key = {
.id = id,
.saddr = hdr->saddr,
.daddr = hdr->daddr,
.user = IP6_DEFRAG_LOCAL_DELIVER,
.iif = iif,
};
struct inet_frag_queue *q;
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
IPV6_ADDR_LINKLOCAL)))
key.iif = 0;
q = inet_frag_find(net->ipv6.fqdir, &key);
if (!q)
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,
u32 *prob_offset)
{
struct net *net = dev_net(skb_dst(skb)->dev);
int offset, end, fragsize;
struct sk_buff *prev_tail;
struct net_device *dev;
int err = -ENOENT;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
err = -EINVAL;
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) {
*prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
/* note that if prob_offset is set, the skb is freed elsewhere,
* we do not free it here.
*/
return -1;
}
ecn = ip6_frag_ecn(ipv6_hdr(skb));
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.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
goto discard_fq;
fq->q.flags |= 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
*/
*prob_offset = offsetof(struct ipv6hdr, payload_len);
return -1;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
goto discard_fq;
fq->q.len = end;
}
}
if (end == offset)
goto discard_fq;
err = -ENOMEM;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto discard_fq;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto discard_fq;
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
prev_tail = fq->q.fragments_tail;
err = inet_frag_queue_insert(&fq->q, skb, offset, end);
if (err)
goto insert_error;
if (dev)
fq->iif = dev->ifindex;
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.fqdir, skb->truesize);
fragsize = -skb_network_offset(skb) + skb->len;
if (fragsize > fq->q.max_size)
fq->q.max_size = fragsize;
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.flags |= INET_FRAG_FIRST_IN;
}
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip6_frag_reasm(fq, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
insert_error:
if (err == IPFRAG_DUP) {
kfree_skb(skb);
return -EINVAL;
}
err = -EINVAL;
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASM_OVERLAPS);
discard_fq:
inet_frag_kill(&fq->q);
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
err:
kfree_skb(skb);
return err;
}
/*
* Check if this packet is complete.
*
* 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 *skb,
struct sk_buff *prev_tail, struct net_device *dev)
{
struct net *net = fq->q.fqdir->net;
unsigned int nhoff;
void *reasm_data;
int payload_len;
u8 ecn;
inet_frag_kill(&fq->q);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
goto out_fail;
reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
if (!reasm_data)
goto out_oom;
payload_len = ((skb->data - skb_network_header(skb)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0];
memmove(skb->head + sizeof(struct frag_hdr), skb->head,
(skb->data - skb->head) - sizeof(struct frag_hdr));
if (skb_mac_header_was_set(skb))
skb->mac_header += sizeof(struct frag_hdr);
skb->network_header += sizeof(struct frag_hdr);
skb_reset_transport_header(skb);
inet: frags: re-introduce skb coalescing for local delivery Before commit d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6 defrag"), a netperf UDP_STREAM test[0] using big IPv6 datagrams (thus generating many fragments) and running over an IPsec tunnel, reported more than 6Gbps throughput. After that patch, the same test gets only 9Mbps when receiving on a be2net nic (driver can make a big difference here, for example, ixgbe doesn't seem to be affected). By reusing the IPv4 defragmentation code, IPv6 lost fragment coalescing (IPv4 fragment coalescing was dropped by commit 14fe22e33462 ("Revert "ipv4: use skb coalescing in defragmentation"")). Without fragment coalescing, be2net runs out of Rx ring entries and starts to drop frames (ethtool reports rx_drops_no_frags errors). Since the netperf traffic is only composed of UDP fragments, any lost packet prevents reassembly of the full datagram. Therefore, fragments which have no possibility to ever get reassembled pile up in the reassembly queue, until the memory accounting exeeds the threshold. At that point no fragment is accepted anymore, which effectively discards all netperf traffic. When reassembly timeout expires, some stale fragments are removed from the reassembly queue, so a few packets can be received, reassembled and delivered to the netperf receiver. But the nic still drops frames and soon the reassembly queue gets filled again with stale fragments. These long time frames where no datagram can be received explain why the performance drop is so significant. Re-introducing fragment coalescing is enough to get the initial performances again (6.6Gbps with be2net): driver doesn't drop frames anymore (no more rx_drops_no_frags errors) and the reassembly engine works at full speed. This patch is quite conservative and only coalesces skbs for local IPv4 and IPv6 delivery (in order to avoid changing skb geometry when forwarding). Coalescing could be extended in the future if need be, as more scenarios would probably benefit from it. [0]: Test configuration Sender: ip xfrm policy flush ip xfrm state flush ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1 ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir in tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1 ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir out tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow netserver -D -L fc00:2::1 Receiver: ip xfrm policy flush ip xfrm state flush ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1 ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir in tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1 ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir out tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow netperf -H fc00:2::1 -f k -P 0 -L fc00:1::1 -l 60 -t UDP_STREAM -I 99,5 -i 5,5 -T5,5 -6 Signed-off-by: Guillaume Nault <gnault@redhat.com> Acked-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-02 15:15:03 +00:00
inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
skb->dev = dev;
ipv6_hdr(skb)->payload_len = htons(payload_len);
ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
IP6CB(skb)->nhoff = nhoff;
IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
IP6CB(skb)->frag_max_size = fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
skb_postpush_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
fq->q.last_run_head = 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(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
inet_frag_kill(&fq->q);
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);
u8 nexthdr;
ipv6/netfilter: Discard first fragment not including all headers Packets are processed even though the first fragment don't include all headers through the upper layer header. This breaks TAHI IPv6 Core Conformance Test v6LC.1.3.6. Referring to RFC8200 SECTION 4.5: "If the first fragment does not include all headers through an Upper-Layer header, then that fragment should be discarded and an ICMP Parameter Problem, Code 3, message should be sent to the source of the fragment, with the Pointer field set to zero." The fragment needs to be validated the same way it is done in commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") for ipv6. Wrap the validation into a common function, ipv6_frag_thdr_truncated() to check for truncation in the upper layer header. This validation does not fullfill all aspects of RFC 8200, section 4.5, but is at the moment sufficient to pass mentioned TAHI test. In netfilter, utilize the fragment offset returned by find_prev_fhdr() to let ipv6_frag_thdr_truncated() start it's traverse from the fragment header. Return 0 to drop the fragment in the netfilter. This is the same behaviour as used on other protocol errors in this function, e.g. when nf_ct_frag6_queue() returns -EPROTO. The Fragment will later be picked up by ipv6_frag_rcv() in reassembly.c. ipv6_frag_rcv() will then send an appropriate ICMP Parameter Problem message back to the source. References commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") Signed-off-by: Georg Kohmann <geokohma@cisco.com> Acked-by: Pablo Neira Ayuso <pablo@netfilter.org> Link: https://lore.kernel.org/r/20201111115025.28879-1-geokohma@cisco.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-11 11:50:25 +00:00
int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
__IP6_INC_STATS(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(net,
ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
return 1;
}
/* RFC 8200, Section 4.5 Fragment Header:
* If the first fragment does not include all headers through an
* Upper-Layer header, then that fragment should be discarded and
* an ICMP Parameter Problem, Code 3, message should be sent to
* the source of the fragment, with the Pointer field set to zero.
*/
nexthdr = hdr->nexthdr;
if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
ipv6/netfilter: Discard first fragment not including all headers Packets are processed even though the first fragment don't include all headers through the upper layer header. This breaks TAHI IPv6 Core Conformance Test v6LC.1.3.6. Referring to RFC8200 SECTION 4.5: "If the first fragment does not include all headers through an Upper-Layer header, then that fragment should be discarded and an ICMP Parameter Problem, Code 3, message should be sent to the source of the fragment, with the Pointer field set to zero." The fragment needs to be validated the same way it is done in commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") for ipv6. Wrap the validation into a common function, ipv6_frag_thdr_truncated() to check for truncation in the upper layer header. This validation does not fullfill all aspects of RFC 8200, section 4.5, but is at the moment sufficient to pass mentioned TAHI test. In netfilter, utilize the fragment offset returned by find_prev_fhdr() to let ipv6_frag_thdr_truncated() start it's traverse from the fragment header. Return 0 to drop the fragment in the netfilter. This is the same behaviour as used on other protocol errors in this function, e.g. when nf_ct_frag6_queue() returns -EPROTO. The Fragment will later be picked up by ipv6_frag_rcv() in reassembly.c. ipv6_frag_rcv() will then send an appropriate ICMP Parameter Problem message back to the source. References commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") Signed-off-by: Georg Kohmann <geokohma@cisco.com> Acked-by: Pablo Neira Ayuso <pablo@netfilter.org> Link: https://lore.kernel.org/r/20201111115025.28879-1-geokohma@cisco.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-11 11:50:25 +00:00
__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
return -1;
}
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
u32 prob_offset = 0;
int ret;
spin_lock(&fq->q.lock);
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
&prob_offset);
spin_unlock(&fq->q.lock);
inet_frag_put(&fq->q);
if (prob_offset) {
__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
IPSTATS_MIB_INHDRERRORS);
/* icmpv6_param_prob() calls kfree_skb(skb) */
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
}
return ret;
}
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
fail_hdr:
__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
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",
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "ip6frag_low_thresh",
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "ip6frag_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{ }
};
/* secret interval has been deprecated */
static int ip6_frags_secret_interval_unused;
static struct ctl_table ip6_frags_ctl_table[] = {
{
.procname = "ip6frag_secret_interval",
.data = &ip6_frags_secret_interval_unused,
.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)
goto err_alloc;
}
table[0].data = &net->ipv6.fqdir->high_thresh;
table[0].extra1 = &net->ipv6.fqdir->low_thresh;
table[1].data = &net->ipv6.fqdir->low_thresh;
table[1].extra2 = &net->ipv6.fqdir->high_thresh;
table[2].data = &net->ipv6.fqdir->timeout;
hdr = register_net_sysctl(net, "net/ipv6", table);
if (!hdr)
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 int ip6_frags_ns_sysctl_register(struct net *net)
{
return 0;
}
static void ip6_frags_ns_sysctl_unregister(struct net *net)
{
}
static int ip6_frags_sysctl_register(void)
{
return 0;
}
static void ip6_frags_sysctl_unregister(void)
{
}
#endif
static int __net_init ipv6_frags_init_net(struct net *net)
{
int res;
res = fqdir_init(&net->ipv6.fqdir, &ip6_frags, net);
if (res < 0)
return res;
net->ipv6.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.fqdir->timeout = IPV6_FRAG_TIMEOUT;
res = ip6_frags_ns_sysctl_register(net);
if (res < 0)
fqdir_exit(net->ipv6.fqdir);
return res;
}
inet: fix various use-after-free in defrags units syzbot reported another issue caused by my recent patches. [1] The issue here is that fqdir_exit() is initiating a work queue and immediately returns. A bit later cleanup_net() was able to free the MIB (percpu data) and the whole struct net was freed, but we had active frag timers that fired and triggered use-after-free. We need to make sure that timers can catch fqdir->dead being set, to bailout. Since RCU is used for the reader side, this means we want to respect an RCU grace period between these operations : 1) qfdir->dead = 1; 2) netns dismantle (freeing of various data structure) This patch uses new new (struct pernet_operations)->pre_exit infrastructure to ensures a full RCU grace period happens between fqdir_pre_exit() and fqdir_exit() This also means we can use a regular work queue, we no longer need rcu_work. Tested: $ time for i in {1..1000}; do unshare -n /bin/false;done real 0m2.585s user 0m0.160s sys 0m2.214s [1] BUG: KASAN: use-after-free in ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 Read of size 8 at addr ffff88808b9fe330 by task syz-executor.4/11860 CPU: 1 PID: 11860 Comm: syz-executor.4 Not tainted 5.2.0-rc2+ #22 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 call_timer_fn+0x193/0x720 kernel/time/timer.c:1322 expire_timers kernel/time/timer.c:1366 [inline] __run_timers kernel/time/timer.c:1685 [inline] __run_timers kernel/time/timer.c:1653 [inline] run_timer_softirq+0x66f/0x1740 kernel/time/timer.c:1698 __do_softirq+0x25c/0x94c kernel/softirq.c:293 invoke_softirq kernel/softirq.c:374 [inline] irq_exit+0x180/0x1d0 kernel/softirq.c:414 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806 </IRQ> RIP: 0010:tomoyo_domain_quota_is_ok+0x131/0x540 security/tomoyo/util.c:1035 Code: 24 4c 3b 65 d0 0f 84 9c 00 00 00 e8 19 1d 73 fe 49 8d 7c 24 18 48 ba 00 00 00 00 00 fc ff df 48 89 f8 48 c1 e8 03 0f b6 04 10 <48> 89 fa 83 e2 07 38 d0 7f 08 84 c0 0f 85 69 03 00 00 41 0f b6 5c RSP: 0018:ffff88806ae079c0 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000000 RBX: 0000000000000010 RCX: ffffc9000e655000 RDX: dffffc0000000000 RSI: ffffffff82fd88a7 RDI: ffff888086202398 RBP: ffff88806ae07a00 R08: ffff88808b6c8700 R09: ffffed100d5c0f4d R10: ffffed100d5c0f4c R11: 0000000000000000 R12: ffff888086202380 R13: 0000000000000030 R14: 00000000000000d3 R15: 0000000000000000 tomoyo_supervisor+0x2e8/0xef0 security/tomoyo/common.c:2087 tomoyo_audit_path_number_log security/tomoyo/file.c:235 [inline] tomoyo_path_number_perm+0x42f/0x520 security/tomoyo/file.c:734 tomoyo_file_ioctl+0x23/0x30 security/tomoyo/tomoyo.c:335 security_file_ioctl+0x77/0xc0 security/security.c:1370 ksys_ioctl+0x57/0xd0 fs/ioctl.c:711 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4592c9 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8db5e44c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004592c9 RDX: 0000000020000080 RSI: 00000000000089f1 RDI: 0000000000000006 RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8db5e456d4 R13: 00000000004cc770 R14: 00000000004d5cd8 R15: 00000000ffffffff Allocated by task 9047: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3326 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3488 kmem_cache_zalloc include/linux/slab.h:732 [inline] net_alloc net/core/net_namespace.c:386 [inline] copy_net_ns+0xed/0x340 net/core/net_namespace.c:426 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206 ksys_unshare+0x440/0x980 kernel/fork.c:2692 __do_sys_unshare kernel/fork.c:2760 [inline] __se_sys_unshare kernel/fork.c:2758 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 2541: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3698 net_free net/core/net_namespace.c:402 [inline] net_drop_ns.part.0+0x70/0x90 net/core/net_namespace.c:409 net_drop_ns net/core/net_namespace.c:408 [inline] cleanup_net+0x538/0x960 net/core/net_namespace.c:571 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff88808b9fe100 which belongs to the cache net_namespace of size 6784 The buggy address is located 560 bytes inside of 6784-byte region [ffff88808b9fe100, ffff88808b9ffb80) The buggy address belongs to the page: page:ffffea00022e7f80 refcount:1 mapcount:0 mapping:ffff88821b6f60c0 index:0x0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea000256f288 ffffea0001bbef08 ffff88821b6f60c0 raw: 0000000000000000 ffff88808b9fe100 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808b9fe200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88808b9fe300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88808b9fe380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 3c8fc8782044 ("inet: frags: rework rhashtable dismantle") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 18:09:00 +00:00
static void __net_exit ipv6_frags_pre_exit_net(struct net *net)
{
fqdir_pre_exit(net->ipv6.fqdir);
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
fqdir_exit(net->ipv6.fqdir);
}
static struct pernet_operations ip6_frags_ops = {
inet: fix various use-after-free in defrags units syzbot reported another issue caused by my recent patches. [1] The issue here is that fqdir_exit() is initiating a work queue and immediately returns. A bit later cleanup_net() was able to free the MIB (percpu data) and the whole struct net was freed, but we had active frag timers that fired and triggered use-after-free. We need to make sure that timers can catch fqdir->dead being set, to bailout. Since RCU is used for the reader side, this means we want to respect an RCU grace period between these operations : 1) qfdir->dead = 1; 2) netns dismantle (freeing of various data structure) This patch uses new new (struct pernet_operations)->pre_exit infrastructure to ensures a full RCU grace period happens between fqdir_pre_exit() and fqdir_exit() This also means we can use a regular work queue, we no longer need rcu_work. Tested: $ time for i in {1..1000}; do unshare -n /bin/false;done real 0m2.585s user 0m0.160s sys 0m2.214s [1] BUG: KASAN: use-after-free in ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 Read of size 8 at addr ffff88808b9fe330 by task syz-executor.4/11860 CPU: 1 PID: 11860 Comm: syz-executor.4 Not tainted 5.2.0-rc2+ #22 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 call_timer_fn+0x193/0x720 kernel/time/timer.c:1322 expire_timers kernel/time/timer.c:1366 [inline] __run_timers kernel/time/timer.c:1685 [inline] __run_timers kernel/time/timer.c:1653 [inline] run_timer_softirq+0x66f/0x1740 kernel/time/timer.c:1698 __do_softirq+0x25c/0x94c kernel/softirq.c:293 invoke_softirq kernel/softirq.c:374 [inline] irq_exit+0x180/0x1d0 kernel/softirq.c:414 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806 </IRQ> RIP: 0010:tomoyo_domain_quota_is_ok+0x131/0x540 security/tomoyo/util.c:1035 Code: 24 4c 3b 65 d0 0f 84 9c 00 00 00 e8 19 1d 73 fe 49 8d 7c 24 18 48 ba 00 00 00 00 00 fc ff df 48 89 f8 48 c1 e8 03 0f b6 04 10 <48> 89 fa 83 e2 07 38 d0 7f 08 84 c0 0f 85 69 03 00 00 41 0f b6 5c RSP: 0018:ffff88806ae079c0 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000000 RBX: 0000000000000010 RCX: ffffc9000e655000 RDX: dffffc0000000000 RSI: ffffffff82fd88a7 RDI: ffff888086202398 RBP: ffff88806ae07a00 R08: ffff88808b6c8700 R09: ffffed100d5c0f4d R10: ffffed100d5c0f4c R11: 0000000000000000 R12: ffff888086202380 R13: 0000000000000030 R14: 00000000000000d3 R15: 0000000000000000 tomoyo_supervisor+0x2e8/0xef0 security/tomoyo/common.c:2087 tomoyo_audit_path_number_log security/tomoyo/file.c:235 [inline] tomoyo_path_number_perm+0x42f/0x520 security/tomoyo/file.c:734 tomoyo_file_ioctl+0x23/0x30 security/tomoyo/tomoyo.c:335 security_file_ioctl+0x77/0xc0 security/security.c:1370 ksys_ioctl+0x57/0xd0 fs/ioctl.c:711 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4592c9 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8db5e44c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004592c9 RDX: 0000000020000080 RSI: 00000000000089f1 RDI: 0000000000000006 RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8db5e456d4 R13: 00000000004cc770 R14: 00000000004d5cd8 R15: 00000000ffffffff Allocated by task 9047: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3326 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3488 kmem_cache_zalloc include/linux/slab.h:732 [inline] net_alloc net/core/net_namespace.c:386 [inline] copy_net_ns+0xed/0x340 net/core/net_namespace.c:426 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206 ksys_unshare+0x440/0x980 kernel/fork.c:2692 __do_sys_unshare kernel/fork.c:2760 [inline] __se_sys_unshare kernel/fork.c:2758 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 2541: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3698 net_free net/core/net_namespace.c:402 [inline] net_drop_ns.part.0+0x70/0x90 net/core/net_namespace.c:409 net_drop_ns net/core/net_namespace.c:408 [inline] cleanup_net+0x538/0x960 net/core/net_namespace.c:571 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff88808b9fe100 which belongs to the cache net_namespace of size 6784 The buggy address is located 560 bytes inside of 6784-byte region [ffff88808b9fe100, ffff88808b9ffb80) The buggy address belongs to the page: page:ffffea00022e7f80 refcount:1 mapcount:0 mapping:ffff88821b6f60c0 index:0x0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea000256f288 ffffea0001bbef08 ffff88821b6f60c0 raw: 0000000000000000 ffff88808b9fe100 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808b9fe200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88808b9fe300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88808b9fe380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 3c8fc8782044 ("inet: frags: rework rhashtable dismantle") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 18:09:00 +00:00
.init = ipv6_frags_init_net,
.pre_exit = ipv6_frags_pre_exit_net,
.exit = ipv6_frags_exit_net,
};
static const struct rhashtable_params ip6_rhash_params = {
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
.head_offset = offsetof(struct inet_frag_queue, node),
.hashfn = ip6frag_key_hashfn,
.obj_hashfn = ip6frag_obj_hashfn,
.obj_cmpfn = ip6frag_obj_cmpfn,
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
.automatic_shrinking = true,
};
int __init ipv6_frag_init(void)
{
int ret;
ip6_frags.constructor = ip6frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
inet: frags: use rhashtables for reassembly units Some applications still rely on IP fragmentation, and to be fair linux reassembly unit is not working under any serious load. It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!) A work queue is supposed to garbage collect items when host is under memory pressure, and doing a hash rebuild, changing seed used in hash computations. This work queue blocks softirqs for up to 25 ms when doing a hash rebuild, occurring every 5 seconds if host is under fire. Then there is the problem of sharing this hash table for all netns. It is time to switch to rhashtables, and allocate one of them per netns to speedup netns dismantle, since this is a critical metric these days. Lookup is now using RCU. A followup patch will even remove the refcount hold/release left from prior implementation and save a couple of atomic operations. Before this patch, 16 cpus (16 RX queue NIC) could not handle more than 1 Mpps frags DDOS. After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB of storage for the fragments (exact number depends on frags being evicted after timeout) $ grep FRAG /proc/net/sockstat FRAG: inuse 1966916 memory 2140004608 A followup patch will change the limits for 64bit arches. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Florian Westphal <fw@strlen.de> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Alexander Aring <alex.aring@gmail.com> Cc: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-31 19:58:49 +00:00
ip6_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&ip6_frags);
if (ret)
goto out;
ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
if (ret)
goto err_protocol;
ret = ip6_frags_sysctl_register();
if (ret)
goto err_sysctl;
ret = register_pernet_subsys(&ip6_frags_ops);
if (ret)
goto err_pernet;
out:
return ret;
err_pernet:
ip6_frags_sysctl_unregister();
err_sysctl:
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
err_protocol:
inet_frags_fini(&ip6_frags);
goto out;
}
void ipv6_frag_exit(void)
{
ip6_frags_sysctl_unregister();
unregister_pernet_subsys(&ip6_frags_ops);
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
inet_frags_fini(&ip6_frags);
}