mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 16:29:59 +00:00
![Eric Dumazet](/assets/img/avatar_default.png)
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: 3c8fc87820
("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>
551 lines
14 KiB
C
551 lines
14 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* inet fragments management
|
|
*
|
|
* Authors: Pavel Emelyanov <xemul@openvz.org>
|
|
* Started as consolidation of ipv4/ip_fragment.c,
|
|
* ipv6/reassembly. and ipv6 nf conntrack reassembly
|
|
*/
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/module.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/random.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/rhashtable.h>
|
|
|
|
#include <net/sock.h>
|
|
#include <net/inet_frag.h>
|
|
#include <net/inet_ecn.h>
|
|
#include <net/ip.h>
|
|
#include <net/ipv6.h>
|
|
|
|
/* Use skb->cb to track consecutive/adjacent fragments coming at
|
|
* the end of the queue. Nodes in the rb-tree queue will
|
|
* contain "runs" of one or more adjacent fragments.
|
|
*
|
|
* Invariants:
|
|
* - next_frag is NULL at the tail of a "run";
|
|
* - the head of a "run" has the sum of all fragment lengths in frag_run_len.
|
|
*/
|
|
struct ipfrag_skb_cb {
|
|
union {
|
|
struct inet_skb_parm h4;
|
|
struct inet6_skb_parm h6;
|
|
};
|
|
struct sk_buff *next_frag;
|
|
int frag_run_len;
|
|
};
|
|
|
|
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
|
|
|
|
static void fragcb_clear(struct sk_buff *skb)
|
|
{
|
|
RB_CLEAR_NODE(&skb->rbnode);
|
|
FRAG_CB(skb)->next_frag = NULL;
|
|
FRAG_CB(skb)->frag_run_len = skb->len;
|
|
}
|
|
|
|
/* Append skb to the last "run". */
|
|
static void fragrun_append_to_last(struct inet_frag_queue *q,
|
|
struct sk_buff *skb)
|
|
{
|
|
fragcb_clear(skb);
|
|
|
|
FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
|
|
FRAG_CB(q->fragments_tail)->next_frag = skb;
|
|
q->fragments_tail = skb;
|
|
}
|
|
|
|
/* Create a new "run" with the skb. */
|
|
static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb)
|
|
{
|
|
BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
|
|
fragcb_clear(skb);
|
|
|
|
if (q->last_run_head)
|
|
rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
|
|
&q->last_run_head->rbnode.rb_right);
|
|
else
|
|
rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
|
|
rb_insert_color(&skb->rbnode, &q->rb_fragments);
|
|
|
|
q->fragments_tail = skb;
|
|
q->last_run_head = skb;
|
|
}
|
|
|
|
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
|
|
* Value : 0xff if frame should be dropped.
|
|
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
|
|
*/
|
|
const u8 ip_frag_ecn_table[16] = {
|
|
/* at least one fragment had CE, and others ECT_0 or ECT_1 */
|
|
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE,
|
|
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
|
|
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
|
|
|
|
/* invalid combinations : drop frame */
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
|
|
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
|
|
};
|
|
EXPORT_SYMBOL(ip_frag_ecn_table);
|
|
|
|
int inet_frags_init(struct inet_frags *f)
|
|
{
|
|
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
|
|
NULL);
|
|
if (!f->frags_cachep)
|
|
return -ENOMEM;
|
|
|
|
refcount_set(&f->refcnt, 1);
|
|
init_completion(&f->completion);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(inet_frags_init);
|
|
|
|
void inet_frags_fini(struct inet_frags *f)
|
|
{
|
|
if (refcount_dec_and_test(&f->refcnt))
|
|
complete(&f->completion);
|
|
|
|
wait_for_completion(&f->completion);
|
|
|
|
kmem_cache_destroy(f->frags_cachep);
|
|
f->frags_cachep = NULL;
|
|
}
|
|
EXPORT_SYMBOL(inet_frags_fini);
|
|
|
|
/* called from rhashtable_free_and_destroy() at netns_frags dismantle */
|
|
static void inet_frags_free_cb(void *ptr, void *arg)
|
|
{
|
|
struct inet_frag_queue *fq = ptr;
|
|
int count;
|
|
|
|
count = del_timer_sync(&fq->timer) ? 1 : 0;
|
|
|
|
spin_lock_bh(&fq->lock);
|
|
if (!(fq->flags & INET_FRAG_COMPLETE)) {
|
|
fq->flags |= INET_FRAG_COMPLETE;
|
|
count++;
|
|
} else if (fq->flags & INET_FRAG_HASH_DEAD) {
|
|
count++;
|
|
}
|
|
spin_unlock_bh(&fq->lock);
|
|
|
|
if (refcount_sub_and_test(count, &fq->refcnt))
|
|
inet_frag_destroy(fq);
|
|
}
|
|
|
|
static void fqdir_work_fn(struct work_struct *work)
|
|
{
|
|
struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work);
|
|
struct inet_frags *f = fqdir->f;
|
|
|
|
rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
|
|
|
|
/* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu)
|
|
* have completed, since they need to dereference fqdir.
|
|
* Would it not be nice to have kfree_rcu_barrier() ? :)
|
|
*/
|
|
rcu_barrier();
|
|
|
|
if (refcount_dec_and_test(&f->refcnt))
|
|
complete(&f->completion);
|
|
|
|
kfree(fqdir);
|
|
}
|
|
|
|
int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
|
|
{
|
|
struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL);
|
|
int res;
|
|
|
|
if (!fqdir)
|
|
return -ENOMEM;
|
|
fqdir->f = f;
|
|
fqdir->net = net;
|
|
res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params);
|
|
if (res < 0) {
|
|
kfree(fqdir);
|
|
return res;
|
|
}
|
|
refcount_inc(&f->refcnt);
|
|
*fqdirp = fqdir;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(fqdir_init);
|
|
|
|
void fqdir_exit(struct fqdir *fqdir)
|
|
{
|
|
INIT_WORK(&fqdir->destroy_work, fqdir_work_fn);
|
|
queue_work(system_wq, &fqdir->destroy_work);
|
|
}
|
|
EXPORT_SYMBOL(fqdir_exit);
|
|
|
|
void inet_frag_kill(struct inet_frag_queue *fq)
|
|
{
|
|
if (del_timer(&fq->timer))
|
|
refcount_dec(&fq->refcnt);
|
|
|
|
if (!(fq->flags & INET_FRAG_COMPLETE)) {
|
|
struct fqdir *fqdir = fq->fqdir;
|
|
|
|
fq->flags |= INET_FRAG_COMPLETE;
|
|
rcu_read_lock();
|
|
/* The RCU read lock provides a memory barrier
|
|
* guaranteeing that if fqdir->dead is false then
|
|
* the hash table destruction will not start until
|
|
* after we unlock. Paired with inet_frags_exit_net().
|
|
*/
|
|
if (!fqdir->dead) {
|
|
rhashtable_remove_fast(&fqdir->rhashtable, &fq->node,
|
|
fqdir->f->rhash_params);
|
|
refcount_dec(&fq->refcnt);
|
|
} else {
|
|
fq->flags |= INET_FRAG_HASH_DEAD;
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_kill);
|
|
|
|
static void inet_frag_destroy_rcu(struct rcu_head *head)
|
|
{
|
|
struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
|
|
rcu);
|
|
struct inet_frags *f = q->fqdir->f;
|
|
|
|
if (f->destructor)
|
|
f->destructor(q);
|
|
kmem_cache_free(f->frags_cachep, q);
|
|
}
|
|
|
|
unsigned int inet_frag_rbtree_purge(struct rb_root *root)
|
|
{
|
|
struct rb_node *p = rb_first(root);
|
|
unsigned int sum = 0;
|
|
|
|
while (p) {
|
|
struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
|
|
|
|
p = rb_next(p);
|
|
rb_erase(&skb->rbnode, root);
|
|
while (skb) {
|
|
struct sk_buff *next = FRAG_CB(skb)->next_frag;
|
|
|
|
sum += skb->truesize;
|
|
kfree_skb(skb);
|
|
skb = next;
|
|
}
|
|
}
|
|
return sum;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_rbtree_purge);
|
|
|
|
void inet_frag_destroy(struct inet_frag_queue *q)
|
|
{
|
|
struct fqdir *fqdir;
|
|
unsigned int sum, sum_truesize = 0;
|
|
struct inet_frags *f;
|
|
|
|
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
|
|
WARN_ON(del_timer(&q->timer) != 0);
|
|
|
|
/* Release all fragment data. */
|
|
fqdir = q->fqdir;
|
|
f = fqdir->f;
|
|
sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
|
|
sum = sum_truesize + f->qsize;
|
|
|
|
call_rcu(&q->rcu, inet_frag_destroy_rcu);
|
|
|
|
sub_frag_mem_limit(fqdir, sum);
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_destroy);
|
|
|
|
static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir,
|
|
struct inet_frags *f,
|
|
void *arg)
|
|
{
|
|
struct inet_frag_queue *q;
|
|
|
|
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
|
|
if (!q)
|
|
return NULL;
|
|
|
|
q->fqdir = fqdir;
|
|
f->constructor(q, arg);
|
|
add_frag_mem_limit(fqdir, f->qsize);
|
|
|
|
timer_setup(&q->timer, f->frag_expire, 0);
|
|
spin_lock_init(&q->lock);
|
|
refcount_set(&q->refcnt, 3);
|
|
|
|
return q;
|
|
}
|
|
|
|
static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
|
|
void *arg,
|
|
struct inet_frag_queue **prev)
|
|
{
|
|
struct inet_frags *f = fqdir->f;
|
|
struct inet_frag_queue *q;
|
|
|
|
q = inet_frag_alloc(fqdir, f, arg);
|
|
if (!q) {
|
|
*prev = ERR_PTR(-ENOMEM);
|
|
return NULL;
|
|
}
|
|
mod_timer(&q->timer, jiffies + fqdir->timeout);
|
|
|
|
*prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key,
|
|
&q->node, f->rhash_params);
|
|
if (*prev) {
|
|
q->flags |= INET_FRAG_COMPLETE;
|
|
inet_frag_kill(q);
|
|
inet_frag_destroy(q);
|
|
return NULL;
|
|
}
|
|
return q;
|
|
}
|
|
|
|
/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
|
|
struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
|
|
{
|
|
struct inet_frag_queue *fq = NULL, *prev;
|
|
|
|
if (!fqdir->high_thresh || frag_mem_limit(fqdir) > fqdir->high_thresh)
|
|
return NULL;
|
|
|
|
rcu_read_lock();
|
|
|
|
prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params);
|
|
if (!prev)
|
|
fq = inet_frag_create(fqdir, key, &prev);
|
|
if (prev && !IS_ERR(prev)) {
|
|
fq = prev;
|
|
if (!refcount_inc_not_zero(&fq->refcnt))
|
|
fq = NULL;
|
|
}
|
|
rcu_read_unlock();
|
|
return fq;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_find);
|
|
|
|
int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
|
|
int offset, int end)
|
|
{
|
|
struct sk_buff *last = q->fragments_tail;
|
|
|
|
/* 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.
|
|
*
|
|
* Duplicates, however, should be ignored (i.e. skb dropped, but the
|
|
* queue/fragments kept for later reassembly).
|
|
*/
|
|
if (!last)
|
|
fragrun_create(q, skb); /* First fragment. */
|
|
else if (last->ip_defrag_offset + last->len < end) {
|
|
/* This is the common case: skb goes to the end. */
|
|
/* Detect and discard overlaps. */
|
|
if (offset < last->ip_defrag_offset + last->len)
|
|
return IPFRAG_OVERLAP;
|
|
if (offset == last->ip_defrag_offset + last->len)
|
|
fragrun_append_to_last(q, skb);
|
|
else
|
|
fragrun_create(q, skb);
|
|
} else {
|
|
/* Binary search. Note that skb can become the first fragment,
|
|
* but not the last (covered above).
|
|
*/
|
|
struct rb_node **rbn, *parent;
|
|
|
|
rbn = &q->rb_fragments.rb_node;
|
|
do {
|
|
struct sk_buff *curr;
|
|
int curr_run_end;
|
|
|
|
parent = *rbn;
|
|
curr = rb_to_skb(parent);
|
|
curr_run_end = curr->ip_defrag_offset +
|
|
FRAG_CB(curr)->frag_run_len;
|
|
if (end <= curr->ip_defrag_offset)
|
|
rbn = &parent->rb_left;
|
|
else if (offset >= curr_run_end)
|
|
rbn = &parent->rb_right;
|
|
else if (offset >= curr->ip_defrag_offset &&
|
|
end <= curr_run_end)
|
|
return IPFRAG_DUP;
|
|
else
|
|
return IPFRAG_OVERLAP;
|
|
} while (*rbn);
|
|
/* Here we have parent properly set, and rbn pointing to
|
|
* one of its NULL left/right children. Insert skb.
|
|
*/
|
|
fragcb_clear(skb);
|
|
rb_link_node(&skb->rbnode, parent, rbn);
|
|
rb_insert_color(&skb->rbnode, &q->rb_fragments);
|
|
}
|
|
|
|
skb->ip_defrag_offset = offset;
|
|
|
|
return IPFRAG_OK;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_queue_insert);
|
|
|
|
void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
|
|
struct sk_buff *parent)
|
|
{
|
|
struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
|
|
struct sk_buff **nextp;
|
|
int delta;
|
|
|
|
if (head != skb) {
|
|
fp = skb_clone(skb, GFP_ATOMIC);
|
|
if (!fp)
|
|
return NULL;
|
|
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
|
|
if (RB_EMPTY_NODE(&skb->rbnode))
|
|
FRAG_CB(parent)->next_frag = fp;
|
|
else
|
|
rb_replace_node(&skb->rbnode, &fp->rbnode,
|
|
&q->rb_fragments);
|
|
if (q->fragments_tail == skb)
|
|
q->fragments_tail = fp;
|
|
skb_morph(skb, head);
|
|
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
|
|
rb_replace_node(&head->rbnode, &skb->rbnode,
|
|
&q->rb_fragments);
|
|
consume_skb(head);
|
|
head = skb;
|
|
}
|
|
WARN_ON(head->ip_defrag_offset != 0);
|
|
|
|
delta = -head->truesize;
|
|
|
|
/* Head of list must not be cloned. */
|
|
if (skb_unclone(head, GFP_ATOMIC))
|
|
return NULL;
|
|
|
|
delta += head->truesize;
|
|
if (delta)
|
|
add_frag_mem_limit(q->fqdir, delta);
|
|
|
|
/* 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)
|
|
return NULL;
|
|
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->data_len = head->data_len - plen;
|
|
clone->len = clone->data_len;
|
|
head->truesize += clone->truesize;
|
|
clone->csum = 0;
|
|
clone->ip_summed = head->ip_summed;
|
|
add_frag_mem_limit(q->fqdir, clone->truesize);
|
|
skb_shinfo(head)->frag_list = clone;
|
|
nextp = &clone->next;
|
|
} else {
|
|
nextp = &skb_shinfo(head)->frag_list;
|
|
}
|
|
|
|
return nextp;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_reasm_prepare);
|
|
|
|
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
|
|
void *reasm_data)
|
|
{
|
|
struct sk_buff **nextp = (struct sk_buff **)reasm_data;
|
|
struct rb_node *rbn;
|
|
struct sk_buff *fp;
|
|
|
|
skb_push(head, head->data - skb_network_header(head));
|
|
|
|
/* Traverse the tree in order, to build frag_list. */
|
|
fp = FRAG_CB(head)->next_frag;
|
|
rbn = rb_next(&head->rbnode);
|
|
rb_erase(&head->rbnode, &q->rb_fragments);
|
|
while (rbn || fp) {
|
|
/* fp points to the next sk_buff in the current run;
|
|
* rbn points to the next run.
|
|
*/
|
|
/* Go through the current run. */
|
|
while (fp) {
|
|
*nextp = fp;
|
|
nextp = &fp->next;
|
|
fp->prev = NULL;
|
|
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
|
|
fp->sk = NULL;
|
|
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;
|
|
fp = FRAG_CB(fp)->next_frag;
|
|
}
|
|
/* Move to the next run. */
|
|
if (rbn) {
|
|
struct rb_node *rbnext = rb_next(rbn);
|
|
|
|
fp = rb_to_skb(rbn);
|
|
rb_erase(rbn, &q->rb_fragments);
|
|
rbn = rbnext;
|
|
}
|
|
}
|
|
sub_frag_mem_limit(q->fqdir, head->truesize);
|
|
|
|
*nextp = NULL;
|
|
skb_mark_not_on_list(head);
|
|
head->prev = NULL;
|
|
head->tstamp = q->stamp;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_reasm_finish);
|
|
|
|
struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q)
|
|
{
|
|
struct sk_buff *head, *skb;
|
|
|
|
head = skb_rb_first(&q->rb_fragments);
|
|
if (!head)
|
|
return NULL;
|
|
skb = FRAG_CB(head)->next_frag;
|
|
if (skb)
|
|
rb_replace_node(&head->rbnode, &skb->rbnode,
|
|
&q->rb_fragments);
|
|
else
|
|
rb_erase(&head->rbnode, &q->rb_fragments);
|
|
memset(&head->rbnode, 0, sizeof(head->rbnode));
|
|
barrier();
|
|
|
|
if (head == q->fragments_tail)
|
|
q->fragments_tail = NULL;
|
|
|
|
sub_frag_mem_limit(q->fqdir, head->truesize);
|
|
|
|
return head;
|
|
}
|
|
EXPORT_SYMBOL(inet_frag_pull_head);
|