mirror of
https://github.com/openvswitch/ovs
synced 2025-10-25 15:07:05 +00:00
ccd0a13bfa
The core fragmentation handling logic is exported on all supported
kernels, so it's not necessary to backport the latest version of this.
This greatly simplifies the code due to inconsistencies between the old
per-lookup garbage collection and the newer workqueue based garbage
collection.
As a result of simplifying and removing unnecessary backport code, a few
bugs are fixed for corner cases such as when some fragments remain in
the fragment cache when openvswitch is unloaded.
Some backported ip functions need a little extra logic than what is seen
on the latest code due to this, for instance on kernels <3.17:
* Call inet_frag_evictor() before defrag
* Limit hashsize in ip{,6}_fragment logic
The pernet init/exit logic also differs a little from upstream. Upstream
ipv[46]_defrag logic initializes the various pernet fragment parameters
and its own global fragments cache. In the OVS backport, the pernet
parameters are shared while the fragments cache is separate. The
backport relies upon upstream pernet initialization to perform the
shared setup, and performs no pernet initialization of its own. When it
comes to pernet exit however, the backport must ensure that all
OVS-specific fragment state is cleared, while the shared state remains
untouched so that the regular ipv[46] logic may do its own cleanup. In
practice this means that OVS must have its own divergent implementation
of inet_frags_exit_net().
Fixes the following crash:
Call Trace:
<IRQ>
[<ffffffff810744f6>] ? call_timer_fn+0x36/0x100
[<ffffffff8107548f>] run_timer_softirq+0x1ef/0x2f0
[<ffffffff8106cccc>] __do_softirq+0xec/0x2c0
[<ffffffff8106d215>] irq_exit+0x105/0x110
[<ffffffff81737095>] smp_apic_timer_interrupt+0x45/0x60
[<ffffffff81735a1d>] apic_timer_interrupt+0x6d/0x80
<EOI>
[<ffffffff8104f596>] ? native_safe_halt+0x6/0x10
[<ffffffff8101cb2f>] default_idle+0x1f/0xc0
[<ffffffff8101d406>] arch_cpu_idle+0x26/0x30
[<ffffffff810bf3a5>] cpu_startup_entry+0xc5/0x290
[<ffffffff810415ed>] start_secondary+0x21d/0x2d0
Code: Bad RIP value.
RIP [<ffffffffa0177480>] 0xffffffffa0177480
RSP <ffff88003f703e78>
CR2: ffffffffa0177480
---[ end trace eb98ca80ba07bd9c ]---
Kernel panic - not syncing: Fatal exception in interrupt
Signed-off-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
115 lines
2.6 KiB
C
115 lines
2.6 KiB
C
/*
|
|
* inet fragments management
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*
|
|
* Authors: Pavel Emelyanov <xemul@openvz.org>
|
|
* Started as consolidation of ipv4/ip_fragment.c,
|
|
* ipv6/reassembly. and ipv6 nf conntrack reassembly
|
|
*/
|
|
|
|
#ifndef HAVE_CORRECT_MRU_HANDLING
|
|
|
|
#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 <net/sock.h>
|
|
#include <net/inet_frag.h>
|
|
#include <net/inet_ecn.h>
|
|
|
|
#ifdef HAVE_INET_FRAGS_WITH_FRAGS_WORK
|
|
static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
|
|
{
|
|
return q->net->low_thresh == 0 ||
|
|
frag_mem_limit(q->net) >= q->net->low_thresh;
|
|
}
|
|
|
|
static unsigned int
|
|
inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
|
|
{
|
|
struct inet_frag_queue *fq;
|
|
struct hlist_node *n;
|
|
unsigned int evicted = 0;
|
|
HLIST_HEAD(expired);
|
|
|
|
spin_lock(&hb->chain_lock);
|
|
|
|
hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
|
|
if (!inet_fragq_should_evict(fq))
|
|
continue;
|
|
|
|
if (!del_timer(&fq->timer))
|
|
continue;
|
|
|
|
#ifdef HAVE_INET_FRAG_QUEUE_WITH_LIST_EVICTOR
|
|
hlist_add_head(&fq->list_evictor, &expired);
|
|
#else
|
|
hlist_del(&fq->list);
|
|
hlist_add_head(&fq->list, &expired);
|
|
#endif
|
|
++evicted;
|
|
}
|
|
|
|
spin_unlock(&hb->chain_lock);
|
|
|
|
#ifdef HAVE_INET_FRAG_QUEUE_WITH_LIST_EVICTOR
|
|
hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
|
|
#else
|
|
hlist_for_each_entry_safe(fq, n, &expired, list)
|
|
#endif
|
|
f->frag_expire((unsigned long) fq);
|
|
|
|
return evicted;
|
|
}
|
|
|
|
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
|
|
{
|
|
int thresh = nf->low_thresh;
|
|
unsigned int seq;
|
|
int i;
|
|
|
|
nf->low_thresh = 0;
|
|
|
|
evict_again:
|
|
local_bh_disable();
|
|
seq = read_seqbegin(&f->rnd_seqlock);
|
|
|
|
for (i = 0; i < INETFRAGS_HASHSZ ; i++)
|
|
inet_evict_bucket(f, &f->hash[i]);
|
|
|
|
local_bh_enable();
|
|
cond_resched();
|
|
|
|
if (read_seqretry(&f->rnd_seqlock, seq) ||
|
|
percpu_counter_sum(&nf->mem))
|
|
goto evict_again;
|
|
|
|
nf->low_thresh = thresh;
|
|
}
|
|
#else /* HAVE_INET_FRAGS_WITH_FRAGS_WORK */
|
|
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
|
|
{
|
|
int thresh = nf->low_thresh;
|
|
|
|
nf->low_thresh = 0;
|
|
|
|
local_bh_disable();
|
|
inet_frag_evictor(nf, f, true);
|
|
local_bh_enable();
|
|
|
|
nf->low_thresh = thresh;
|
|
}
|
|
#endif /* HAVE_INET_FRAGS_WITH_FRAGS_WORK */
|
|
|
|
#endif /* !HAVE_CORRECT_MRU_HANDLING */
|